diff options
author | Jiri Kosina <jkosina@suse.cz> | 2013-01-29 10:48:30 +0100 |
---|---|---|
committer | Jiri Kosina <jkosina@suse.cz> | 2013-01-29 10:48:30 +0100 |
commit | 617677295b53a40d0e54aac4cbbc216ffbc755dd (patch) | |
tree | 51b9e87213243ed5efff252c8e8d8fec4eebc588 /net | |
parent | 5c8d1b68e01a144813e38795fe6dbe7ebb506131 (diff) | |
parent | 6abb7c25775b7fb2225ad0508236d63ca710e65f (diff) | |
download | linux-617677295b53a40d0e54aac4cbbc216ffbc755dd.tar.bz2 |
Merge branch 'master' into for-next
Conflicts:
drivers/devfreq/exynos4_bus.c
Sync with Linus' tree to be able to apply patches that are
against newer code (mvneta).
Diffstat (limited to 'net')
422 files changed, 23564 insertions, 7872 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index ee070722a3a3..a292e8050ef2 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -242,6 +242,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) * hope the underlying device can handle it. */ new_dev->mtu = real_dev->mtu; + new_dev->priv_flags |= (real_dev->priv_flags & IFF_UNICAST_FLT); vlan_dev_priv(new_dev)->vlan_id = vlan_id; vlan_dev_priv(new_dev)->real_dev = real_dev; @@ -294,7 +295,7 @@ static void vlan_transfer_features(struct net_device *dev, else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; -#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) +#if IS_ENABLED(CONFIG_FCOE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif @@ -529,7 +530,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; vlan_dev_set_ingress_priority(dev, args.u.skb_priority, @@ -539,7 +540,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) case SET_VLAN_EGRESS_PRIORITY_CMD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_set_egress_priority(dev, args.u.skb_priority, @@ -548,7 +549,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) case SET_VLAN_FLAG_CMD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_change_flags(dev, args.vlan_qos ? args.u.flag : 0, @@ -557,7 +558,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) case SET_VLAN_NAME_TYPE_CMD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if ((args.u.name_type >= 0) && (args.u.name_type < VLAN_NAME_TYPE_HIGHEST)) { @@ -573,14 +574,14 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) case ADD_VLAN_CMD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = register_vlan_device(dev, args.u.VID); break; case DEL_VLAN_CMD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; unregister_vlan_dev(dev, NULL); err = 0; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 402442402af7..4a6d31a082b9 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -409,7 +409,7 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa) return err; } -#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) +#if IS_ENABLED(CONFIG_FCOE) static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc) { @@ -531,6 +531,10 @@ static const struct header_ops vlan_header_ops = { .parse = eth_header_parse, }; +static struct device_type vlan_type = { + .name = "vlan", +}; + static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) @@ -564,7 +568,7 @@ static int vlan_dev_init(struct net_device *dev) if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); -#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) +#if IS_ENABLED(CONFIG_FCOE) dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid; #endif @@ -579,6 +583,8 @@ static int vlan_dev_init(struct net_device *dev) dev->netdev_ops = &vlan_netdev_ops; + SET_NETDEV_DEVTYPE(dev, &vlan_type); + if (is_vlan_dev(real_dev)) subclass = 1; @@ -741,7 +747,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_do_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, .ndo_get_stats64 = vlan_dev_get_stats64, -#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) +#if IS_ENABLED(CONFIG_FCOE) .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 35b8911b1c8e..fd05c81cb348 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -39,6 +39,7 @@ #include <linux/inet.h> #include <linux/idr.h> #include <linux/file.h> +#include <linux/highmem.h> #include <linux/slab.h> #include <net/9p/9p.h> #include <linux/parser.h> @@ -325,7 +326,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, int count = nr_pages; while (nr_pages) { s = rest_of_page(data); - pages[index++] = virt_to_page(data); + pages[index++] = kmap_to_page(data); data += s; nr_pages--; } diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index f49da5814bc3..350bf62b2ae3 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -14,49 +14,45 @@ static ssize_t show_type(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); - return sprintf(buf, "%s\n", adev->type); + + return scnprintf(buf, PAGE_SIZE, "%s\n", adev->type); } static ssize_t show_address(struct device *cdev, struct device_attribute *attr, char *buf) { - char *pos = buf; struct atm_dev *adev = to_atm_dev(cdev); - int i; - - for (i = 0; i < (ESI_LEN - 1); i++) - pos += sprintf(pos, "%02x:", adev->esi[i]); - pos += sprintf(pos, "%02x\n", adev->esi[i]); - return pos - buf; + return scnprintf(buf, PAGE_SIZE, "%pM\n", adev->esi); } static ssize_t show_atmaddress(struct device *cdev, struct device_attribute *attr, char *buf) { unsigned long flags; - char *pos = buf; struct atm_dev *adev = to_atm_dev(cdev); struct atm_dev_addr *aaddr; int bin[] = { 1, 2, 10, 6, 1 }, *fmt = bin; - int i, j; + int i, j, count = 0; spin_lock_irqsave(&adev->lock, flags); list_for_each_entry(aaddr, &adev->local, entry) { for (i = 0, j = 0; i < ATM_ESA_LEN; ++i, ++j) { if (j == *fmt) { - pos += sprintf(pos, "."); + count += scnprintf(buf + count, + PAGE_SIZE - count, "."); ++fmt; j = 0; } - pos += sprintf(pos, "%02x", - aaddr->addr.sas_addr.prv[i]); + count += scnprintf(buf + count, + PAGE_SIZE - count, "%02x", + aaddr->addr.sas_addr.prv[i]); } - pos += sprintf(pos, "\n"); + count += scnprintf(buf + count, PAGE_SIZE - count, "\n"); } spin_unlock_irqrestore(&adev->lock, flags); - return pos - buf; + return count; } static ssize_t show_atmindex(struct device *cdev, @@ -64,25 +60,21 @@ static ssize_t show_atmindex(struct device *cdev, { struct atm_dev *adev = to_atm_dev(cdev); - return sprintf(buf, "%d\n", adev->number); + return scnprintf(buf, PAGE_SIZE, "%d\n", adev->number); } static ssize_t show_carrier(struct device *cdev, struct device_attribute *attr, char *buf) { - char *pos = buf; struct atm_dev *adev = to_atm_dev(cdev); - pos += sprintf(pos, "%d\n", - adev->signal == ATM_PHY_SIG_LOST ? 0 : 1); - - return pos - buf; + return scnprintf(buf, PAGE_SIZE, "%d\n", + adev->signal == ATM_PHY_SIG_LOST ? 0 : 1); } static ssize_t show_link_rate(struct device *cdev, struct device_attribute *attr, char *buf) { - char *pos = buf; struct atm_dev *adev = to_atm_dev(cdev); int link_rate; @@ -100,9 +92,7 @@ static ssize_t show_link_rate(struct device *cdev, default: link_rate = adev->link_rate * 8 * 53; } - pos += sprintf(pos, "%d\n", link_rate); - - return pos - buf; + return scnprintf(buf, PAGE_SIZE, "%d\n", link_rate); } static DEVICE_ATTR(address, S_IRUGO, show_address, NULL); diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 4819d31533e0..403e71fa88fe 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -68,12 +68,15 @@ struct br2684_vcc { /* keep old push, pop functions for chaining */ void (*old_push)(struct atm_vcc *vcc, struct sk_buff *skb); void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); + void (*old_release_cb)(struct atm_vcc *vcc); + struct module *old_owner; enum br2684_encaps encaps; struct list_head brvccs; #ifdef CONFIG_ATM_BR2684_IPFILTER struct br2684_filter filter; #endif /* CONFIG_ATM_BR2684_IPFILTER */ unsigned int copies_needed, copies_failed; + atomic_t qspace; }; struct br2684_dev { @@ -181,18 +184,15 @@ static struct notifier_block atm_dev_notifier = { static void br2684_pop(struct atm_vcc *vcc, struct sk_buff *skb) { struct br2684_vcc *brvcc = BR2684_VCC(vcc); - struct net_device *net_dev = skb->dev; - pr_debug("(vcc %p ; net_dev %p )\n", vcc, net_dev); + pr_debug("(vcc %p ; net_dev %p )\n", vcc, brvcc->device); brvcc->old_pop(vcc, skb); - if (!net_dev) - return; - - if (atm_may_send(vcc, 0)) - netif_wake_queue(net_dev); - + /* If the queue space just went up from zero, wake */ + if (atomic_inc_return(&brvcc->qspace) == 1) + netif_wake_queue(brvcc->device); } + /* * Send a packet out a particular vcc. Not to useful right now, but paves * the way for multiple vcc's per itf. Returns true if we can send, @@ -256,16 +256,30 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, ATM_SKB(skb)->atm_options = atmvcc->atm_options; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - atmvcc->send(atmvcc, skb); - if (!atm_may_send(atmvcc, 0)) { + if (atomic_dec_return(&brvcc->qspace) < 1) { + /* No more please! */ netif_stop_queue(brvcc->device); - /*check for race with br2684_pop*/ - if (atm_may_send(atmvcc, 0)) - netif_start_queue(brvcc->device); + /* We might have raced with br2684_pop() */ + if (unlikely(atomic_read(&brvcc->qspace) > 0)) + netif_wake_queue(brvcc->device); } - return 1; + /* If this fails immediately, the skb will be freed and br2684_pop() + will wake the queue if appropriate. Just return an error so that + the stats are updated correctly */ + return !atmvcc->send(atmvcc, skb); +} + +static void br2684_release_cb(struct atm_vcc *atmvcc) +{ + struct br2684_vcc *brvcc = BR2684_VCC(atmvcc); + + if (atomic_read(&brvcc->qspace) > 0) + netif_wake_queue(brvcc->device); + + if (brvcc->old_release_cb) + brvcc->old_release_cb(atmvcc); } static inline struct br2684_vcc *pick_outgoing_vcc(const struct sk_buff *skb, @@ -279,6 +293,8 @@ static netdev_tx_t br2684_start_xmit(struct sk_buff *skb, { struct br2684_dev *brdev = BRPRIV(dev); struct br2684_vcc *brvcc; + struct atm_vcc *atmvcc; + netdev_tx_t ret = NETDEV_TX_OK; pr_debug("skb_dst(skb)=%p\n", skb_dst(skb)); read_lock(&devs_lock); @@ -289,9 +305,26 @@ static netdev_tx_t br2684_start_xmit(struct sk_buff *skb, dev->stats.tx_carrier_errors++; /* netif_stop_queue(dev); */ dev_kfree_skb(skb); - read_unlock(&devs_lock); - return NETDEV_TX_OK; + goto out_devs; } + atmvcc = brvcc->atmvcc; + + bh_lock_sock(sk_atm(atmvcc)); + + if (test_bit(ATM_VF_RELEASED, &atmvcc->flags) || + test_bit(ATM_VF_CLOSE, &atmvcc->flags) || + !test_bit(ATM_VF_READY, &atmvcc->flags)) { + dev->stats.tx_dropped++; + dev_kfree_skb(skb); + goto out; + } + + if (sock_owned_by_user(sk_atm(atmvcc))) { + netif_stop_queue(brvcc->device); + ret = NETDEV_TX_BUSY; + goto out; + } + if (!br2684_xmit_vcc(skb, dev, brvcc)) { /* * We should probably use netif_*_queue() here, but that @@ -303,8 +336,11 @@ static netdev_tx_t br2684_start_xmit(struct sk_buff *skb, dev->stats.tx_errors++; dev->stats.tx_fifo_errors++; } + out: + bh_unlock_sock(sk_atm(atmvcc)); + out_devs: read_unlock(&devs_lock); - return NETDEV_TX_OK; + return ret; } /* @@ -377,9 +413,10 @@ static void br2684_close_vcc(struct br2684_vcc *brvcc) list_del(&brvcc->brvccs); write_unlock_irq(&devs_lock); brvcc->atmvcc->user_back = NULL; /* what about vcc->recvq ??? */ + brvcc->atmvcc->release_cb = brvcc->old_release_cb; brvcc->old_push(brvcc->atmvcc, NULL); /* pass on the bad news */ + module_put(brvcc->old_owner); kfree(brvcc); - module_put(THIS_MODULE); } /* when AAL5 PDU comes in: */ @@ -504,6 +541,13 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) brvcc = kzalloc(sizeof(struct br2684_vcc), GFP_KERNEL); if (!brvcc) return -ENOMEM; + /* + * Allow two packets in the ATM queue. One actually being sent, and one + * for the ATM 'TX done' handler to send. It shouldn't take long to get + * the next one from the netdev queue, when we need it. More than that + * would be bufferbloat. + */ + atomic_set(&brvcc->qspace, 2); write_lock_irq(&devs_lock); net_dev = br2684_find_dev(&be.ifspec); if (net_dev == NULL) { @@ -546,9 +590,13 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) brvcc->encaps = (enum br2684_encaps)be.encaps; brvcc->old_push = atmvcc->push; brvcc->old_pop = atmvcc->pop; + brvcc->old_release_cb = atmvcc->release_cb; + brvcc->old_owner = atmvcc->owner; barrier(); atmvcc->push = br2684_push; atmvcc->pop = br2684_pop; + atmvcc->release_cb = br2684_release_cb; + atmvcc->owner = THIS_MODULE; /* initialize netdev carrier state */ if (atmvcc->dev->signal == ATM_PHY_SIG_LOST) @@ -687,10 +735,13 @@ static int br2684_ioctl(struct socket *sock, unsigned int cmd, return -ENOIOCTLCMD; if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (cmd == ATM_SETBACKEND) + if (cmd == ATM_SETBACKEND) { + if (sock->state != SS_CONNECTED) + return -EINVAL; return br2684_regvcc(atmvcc, argp); - else + } else { return br2684_create(argp); + } #ifdef CONFIG_ATM_BR2684_IPFILTER case BR2684_SETFILT: if (atmvcc->push != br2684_push) diff --git a/net/atm/common.c b/net/atm/common.c index 0c0ad930a632..806fc0a40051 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -126,10 +126,19 @@ static void vcc_write_space(struct sock *sk) rcu_read_unlock(); } +static void vcc_release_cb(struct sock *sk) +{ + struct atm_vcc *vcc = atm_sk(sk); + + if (vcc->release_cb) + vcc->release_cb(vcc); +} + static struct proto vcc_proto = { .name = "VCC", .owner = THIS_MODULE, .obj_size = sizeof(struct atm_vcc), + .release_cb = vcc_release_cb, }; int vcc_create(struct net *net, struct socket *sock, int protocol, int family) @@ -156,7 +165,9 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family) atomic_set(&sk->sk_rmem_alloc, 0); vcc->push = NULL; vcc->pop = NULL; + vcc->owner = NULL; vcc->push_oam = NULL; + vcc->release_cb = NULL; vcc->vpi = vcc->vci = 0; /* no VCI/VPI yet */ vcc->atm_options = vcc->aal_options = 0; sk->sk_destruct = vcc_sock_destruct; @@ -175,6 +186,7 @@ static void vcc_destroy_socket(struct sock *sk) vcc->dev->ops->close(vcc); if (vcc->push) vcc->push(vcc, NULL); /* atmarpd has no push */ + module_put(vcc->owner); while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { atm_return(vcc, skb->truesize); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index 226dca989448..8c93267ce969 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -60,6 +60,8 @@ struct pppoatm_vcc { struct atm_vcc *atmvcc; /* VCC descriptor */ void (*old_push)(struct atm_vcc *, struct sk_buff *); void (*old_pop)(struct atm_vcc *, struct sk_buff *); + void (*old_release_cb)(struct atm_vcc *); + struct module *old_owner; /* keep old push/pop for detaching */ enum pppoatm_encaps encaps; atomic_t inflight; @@ -107,6 +109,24 @@ static void pppoatm_wakeup_sender(unsigned long arg) ppp_output_wakeup((struct ppp_channel *) arg); } +static void pppoatm_release_cb(struct atm_vcc *atmvcc) +{ + struct pppoatm_vcc *pvcc = atmvcc_to_pvcc(atmvcc); + + /* + * As in pppoatm_pop(), it's safe to clear the BLOCKED bit here because + * the wakeup *can't* race with pppoatm_send(). They both hold the PPP + * channel's ->downl lock. And the potential race with *setting* it, + * which leads to the double-check dance in pppoatm_may_send(), doesn't + * exist here. In the sock_owned_by_user() case in pppoatm_send(), we + * set the BLOCKED bit while the socket is still locked. We know that + * ->release_cb() can't be called until that's done. + */ + if (test_and_clear_bit(BLOCKED, &pvcc->blocked)) + tasklet_schedule(&pvcc->wakeup_tasklet); + if (pvcc->old_release_cb) + pvcc->old_release_cb(atmvcc); +} /* * This gets called every time the ATM card has finished sending our * skb. The ->old_pop will take care up normal atm flow control, @@ -151,12 +171,11 @@ static void pppoatm_unassign_vcc(struct atm_vcc *atmvcc) pvcc = atmvcc_to_pvcc(atmvcc); atmvcc->push = pvcc->old_push; atmvcc->pop = pvcc->old_pop; + atmvcc->release_cb = pvcc->old_release_cb; tasklet_kill(&pvcc->wakeup_tasklet); ppp_unregister_channel(&pvcc->chan); atmvcc->user_back = NULL; kfree(pvcc); - /* Gee, I hope we have the big kernel lock here... */ - module_put(THIS_MODULE); } /* Called when an AAL5 PDU comes in */ @@ -165,9 +184,13 @@ static void pppoatm_push(struct atm_vcc *atmvcc, struct sk_buff *skb) struct pppoatm_vcc *pvcc = atmvcc_to_pvcc(atmvcc); pr_debug("\n"); if (skb == NULL) { /* VCC was closed */ + struct module *module; + pr_debug("removing ATMPPP VCC %p\n", pvcc); + module = pvcc->old_owner; pppoatm_unassign_vcc(atmvcc); atmvcc->push(atmvcc, NULL); /* Pass along bad news */ + module_put(module); return; } atm_return(atmvcc, skb->truesize); @@ -211,7 +234,7 @@ error: ppp_input_error(&pvcc->chan, 0); } -static inline int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size) +static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size) { /* * It's not clear that we need to bother with using atm_may_send() @@ -269,10 +292,33 @@ static inline int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size) static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) { struct pppoatm_vcc *pvcc = chan_to_pvcc(chan); + struct atm_vcc *vcc; + int ret; + ATM_SKB(skb)->vcc = pvcc->atmvcc; pr_debug("(skb=0x%p, vcc=0x%p)\n", skb, pvcc->atmvcc); if (skb->data[0] == '\0' && (pvcc->flags & SC_COMP_PROT)) (void) skb_pull(skb, 1); + + vcc = ATM_SKB(skb)->vcc; + bh_lock_sock(sk_atm(vcc)); + if (sock_owned_by_user(sk_atm(vcc))) { + /* + * Needs to happen (and be flushed, hence test_and_) before we unlock + * the socket. It needs to be seen by the time our ->release_cb gets + * called. + */ + test_and_set_bit(BLOCKED, &pvcc->blocked); + goto nospace; + } + if (test_bit(ATM_VF_RELEASED, &vcc->flags) || + test_bit(ATM_VF_CLOSE, &vcc->flags) || + !test_bit(ATM_VF_READY, &vcc->flags)) { + bh_unlock_sock(sk_atm(vcc)); + kfree_skb(skb); + return DROP_PACKET; + } + switch (pvcc->encaps) { /* LLC encapsulation needed */ case e_llc: if (skb_headroom(skb) < LLC_LEN) { @@ -285,8 +331,10 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) } consume_skb(skb); skb = n; - if (skb == NULL) + if (skb == NULL) { + bh_unlock_sock(sk_atm(vcc)); return DROP_PACKET; + } } else if (!pppoatm_may_send(pvcc, skb->truesize)) goto nospace; memcpy(skb_push(skb, LLC_LEN), pppllc, LLC_LEN); @@ -296,6 +344,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) goto nospace; break; case e_autodetect: + bh_unlock_sock(sk_atm(vcc)); pr_debug("Trying to send without setting encaps!\n"); kfree_skb(skb); return 1; @@ -305,9 +354,12 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev); - return ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb) + ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb) ? DROP_PACKET : 1; + bh_unlock_sock(sk_atm(vcc)); + return ret; nospace: + bh_unlock_sock(sk_atm(vcc)); /* * We don't have space to send this SKB now, but we might have * already applied SC_COMP_PROT compression, so may need to undo @@ -362,6 +414,8 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) atomic_set(&pvcc->inflight, NONE_INFLIGHT); pvcc->old_push = atmvcc->push; pvcc->old_pop = atmvcc->pop; + pvcc->old_owner = atmvcc->owner; + pvcc->old_release_cb = atmvcc->release_cb; pvcc->encaps = (enum pppoatm_encaps) be.encaps; pvcc->chan.private = pvcc; pvcc->chan.ops = &pppoatm_ops; @@ -377,7 +431,9 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) atmvcc->user_back = pvcc; atmvcc->push = pppoatm_push; atmvcc->pop = pppoatm_pop; + atmvcc->release_cb = pppoatm_release_cb; __module_get(THIS_MODULE); + atmvcc->owner = THIS_MODULE; /* re-process everything received between connection setup and backend setup */ @@ -406,6 +462,8 @@ static int pppoatm_ioctl(struct socket *sock, unsigned int cmd, return -ENOIOCTLCMD; if (!capable(CAP_NET_ADMIN)) return -EPERM; + if (sock->state != SS_CONNECTED) + return -EINVAL; return pppoatm_assign_vcc(atmvcc, argp); } case PPPIOCGCHAN: diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 53f5244e28f8..8d8afb134b3a 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -6,6 +6,7 @@ config BATMAN_ADV tristate "B.A.T.M.A.N. Advanced Meshing Protocol" depends on NET select CRC16 + select LIBCRC32C default n help B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is @@ -25,6 +26,16 @@ config BATMAN_ADV_BLA more than one mesh node in the same LAN, you can safely remove this feature and save some space. +config BATMAN_ADV_DAT + bool "Distributed ARP Table" + depends on BATMAN_ADV && INET + default n + help + This option enables DAT (Distributed ARP Table), a DHT based + mechanism that increases ARP reliability on sparse wireless + mesh networks. If you think that your network does not need + this option you can safely remove it and save some space. + config BATMAN_ADV_DEBUG bool "B.A.T.M.A.N. debugging" depends on BATMAN_ADV diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 8676d2b1d574..e45e3b4e32e3 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -23,6 +23,7 @@ batman-adv-y += bat_iv_ogm.o batman-adv-y += bitarray.o batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o batman-adv-y += debugfs.o +batman-adv-$(CONFIG_BATMAN_ADV_DAT) += distributed-arp-table.o batman-adv-y += gateway_client.o batman-adv-y += gateway_common.o batman-adv-y += hard-interface.o diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index b02b75dae3a8..7d02ebd11a7f 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -57,20 +57,22 @@ out: static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; + unsigned char *ogm_buff; uint32_t random_seqno; int res = -ENOMEM; /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); - atomic_set(&hard_iface->seqno, random_seqno); + atomic_set(&hard_iface->bat_iv.ogm_seqno, random_seqno); - hard_iface->packet_len = BATADV_OGM_HLEN; - hard_iface->packet_buff = kmalloc(hard_iface->packet_len, GFP_ATOMIC); - - if (!hard_iface->packet_buff) + hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN; + ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC); + if (!ogm_buff) goto out; - batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; + hard_iface->bat_iv.ogm_buff = ogm_buff; + + batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; batadv_ogm_packet->header.packet_type = BATADV_IV_OGM; batadv_ogm_packet->header.version = BATADV_COMPAT_VERSION; batadv_ogm_packet->header.ttl = 2; @@ -87,15 +89,16 @@ out: static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) { - kfree(hard_iface->packet_buff); - hard_iface->packet_buff = NULL; + kfree(hard_iface->bat_iv.ogm_buff); + hard_iface->bat_iv.ogm_buff = NULL; } static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; + unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; + batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; memcpy(batadv_ogm_packet->orig, hard_iface->net_dev->dev_addr, ETH_ALEN); memcpy(batadv_ogm_packet->prev_sender, @@ -106,8 +109,9 @@ static void batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; + unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; + batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; batadv_ogm_packet->flags = BATADV_PRIMARIES_FIRST_HOP; batadv_ogm_packet->header.ttl = BATADV_TTL; } @@ -119,7 +123,7 @@ batadv_iv_ogm_emit_send_time(const struct batadv_priv *bat_priv) unsigned int msecs; msecs = atomic_read(&bat_priv->orig_interval) - BATADV_JITTER; - msecs += (random32() % 2 * BATADV_JITTER); + msecs += random32() % (2 * BATADV_JITTER); return jiffies + msecs_to_jiffies(msecs); } @@ -407,9 +411,11 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, if ((atomic_read(&bat_priv->aggregated_ogms)) && (packet_len < BATADV_MAX_AGGREGATION_BYTES)) - skb_size = BATADV_MAX_AGGREGATION_BYTES + ETH_HLEN; + skb_size = BATADV_MAX_AGGREGATION_BYTES; else - skb_size = packet_len + ETH_HLEN; + skb_size = packet_len; + + skb_size += ETH_HLEN + NET_IP_ALIGN; forw_packet_aggr->skb = dev_alloc_skb(skb_size); if (!forw_packet_aggr->skb) { @@ -418,7 +424,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, kfree(forw_packet_aggr); goto out; } - skb_reserve(forw_packet_aggr->skb, ETH_HLEN); + skb_reserve(forw_packet_aggr->skb, ETH_HLEN + NET_IP_ALIGN); INIT_HLIST_NODE(&forw_packet_aggr->list); @@ -590,8 +596,10 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff; struct batadv_ogm_packet *batadv_ogm_packet; struct batadv_hard_iface *primary_if; + int *ogm_buff_len = &hard_iface->bat_iv.ogm_buff_len; int vis_server, tt_num_changes = 0; uint32_t seqno; uint8_t bandwidth; @@ -600,17 +608,16 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) primary_if = batadv_primary_if_get_selected(bat_priv); if (hard_iface == primary_if) - tt_num_changes = batadv_tt_append_diff(bat_priv, - &hard_iface->packet_buff, - &hard_iface->packet_len, + tt_num_changes = batadv_tt_append_diff(bat_priv, ogm_buff, + ogm_buff_len, BATADV_OGM_HLEN); - batadv_ogm_packet = (struct batadv_ogm_packet *)hard_iface->packet_buff; + batadv_ogm_packet = (struct batadv_ogm_packet *)(*ogm_buff); /* change sequence number to network order */ - seqno = (uint32_t)atomic_read(&hard_iface->seqno); + seqno = (uint32_t)atomic_read(&hard_iface->bat_iv.ogm_seqno); batadv_ogm_packet->seqno = htonl(seqno); - atomic_inc(&hard_iface->seqno); + atomic_inc(&hard_iface->bat_iv.ogm_seqno); batadv_ogm_packet->ttvn = atomic_read(&bat_priv->tt.vn); batadv_ogm_packet->tt_crc = htons(bat_priv->tt.local_crc); @@ -631,8 +638,8 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) } batadv_slide_own_bcast_window(hard_iface); - batadv_iv_ogm_queue_add(bat_priv, hard_iface->packet_buff, - hard_iface->packet_len, hard_iface, 1, + batadv_iv_ogm_queue_add(bat_priv, hard_iface->bat_iv.ogm_buff, + hard_iface->bat_iv.ogm_buff_len, hard_iface, 1, batadv_iv_ogm_emit_send_time(bat_priv)); if (primary_if) @@ -1015,7 +1022,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, return; /* could be changed by schedule_own_packet() */ - if_incoming_seqno = atomic_read(&if_incoming->seqno); + if_incoming_seqno = atomic_read(&if_incoming->bat_iv.ogm_seqno); if (batadv_ogm_packet->flags & BATADV_DIRECTLINK) has_directlink_flag = 1; diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index aea174cdbfbd..5453b17d8df2 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -79,20 +79,17 @@ int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, * or the old packet got delayed somewhere in the network. The * packet should be dropped without calling this function if the * seqno window is protected. + * + * seq_num_diff <= -BATADV_TQ_LOCAL_WINDOW_SIZE + * or + * seq_num_diff >= BATADV_EXPECTED_SEQNO_RANGE */ - if (seq_num_diff <= -BATADV_TQ_LOCAL_WINDOW_SIZE || - seq_num_diff >= BATADV_EXPECTED_SEQNO_RANGE) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Other host probably restarted!\n"); - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Other host probably restarted!\n"); - - bitmap_zero(seq_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); - if (set_mark) - batadv_set_bit(seq_bits, 0); - - return 1; - } + bitmap_zero(seq_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); + if (set_mark) + batadv_set_bit(seq_bits, 0); - /* never reached */ - return 0; + return 1; } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index fd8d5afec0dd..5aebe9327d68 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -40,15 +40,11 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, /* return the index of the claim */ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) { - const unsigned char *key = data; + struct batadv_claim *claim = (struct batadv_claim *)data; uint32_t hash = 0; - size_t i; - for (i = 0; i < ETH_ALEN + sizeof(short); i++) { - hash += key[i]; - hash += (hash << 10); - hash ^= (hash >> 6); - } + hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr)); + hash = batadv_hash_bytes(hash, &claim->vid, sizeof(claim->vid)); hash += (hash << 3); hash ^= (hash >> 11); @@ -61,15 +57,11 @@ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) static inline uint32_t batadv_choose_backbone_gw(const void *data, uint32_t size) { - const unsigned char *key = data; + struct batadv_claim *claim = (struct batadv_claim *)data; uint32_t hash = 0; - size_t i; - for (i = 0; i < ETH_ALEN + sizeof(short); i++) { - hash += key[i]; - hash += (hash << 10); - hash ^= (hash >> 6); - } + hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr)); + hash = batadv_hash_bytes(hash, &claim->vid, sizeof(claim->vid)); hash += (hash << 3); hash ^= (hash >> 11); @@ -85,8 +77,15 @@ static int batadv_compare_backbone_gw(const struct hlist_node *node, { const void *data1 = container_of(node, struct batadv_backbone_gw, hash_entry); + const struct batadv_backbone_gw *gw1 = data1, *gw2 = data2; + + if (!batadv_compare_eth(gw1->orig, gw2->orig)) + return 0; + + if (gw1->vid != gw2->vid) + return 0; - return (memcmp(data1, data2, ETH_ALEN + sizeof(short)) == 0 ? 1 : 0); + return 1; } /* compares address and vid of two claims */ @@ -95,8 +94,15 @@ static int batadv_compare_claim(const struct hlist_node *node, { const void *data1 = container_of(node, struct batadv_claim, hash_entry); + const struct batadv_claim *cl1 = data1, *cl2 = data2; + + if (!batadv_compare_eth(cl1->addr, cl2->addr)) + return 0; + + if (cl1->vid != cl2->vid) + return 0; - return (memcmp(data1, data2, ETH_ALEN + sizeof(short)) == 0 ? 1 : 0); + return 1; } /* free a backbone gw */ @@ -362,7 +368,7 @@ out: */ static struct batadv_backbone_gw * batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, - short vid) + short vid, bool own_backbone) { struct batadv_backbone_gw *entry; struct batadv_orig_node *orig_node; @@ -386,6 +392,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; atomic_set(&entry->request_sent, 0); + atomic_set(&entry->wait_periods, 0); memcpy(entry->orig, orig, ETH_ALEN); /* one for the hash, one for returning */ @@ -409,6 +416,16 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, "became a backbone gateway"); batadv_orig_node_free_ref(orig_node); } + + if (own_backbone) { + batadv_bla_send_announce(bat_priv, entry); + + /* this will be decreased in the worker thread */ + atomic_inc(&entry->request_sent); + atomic_set(&entry->wait_periods, BATADV_BLA_WAIT_PERIODS); + atomic_inc(&bat_priv->bla.num_requests); + } + return entry; } @@ -424,7 +441,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, backbone_gw = batadv_bla_get_backbone_gw(bat_priv, primary_if->net_dev->dev_addr, - vid); + vid, true); if (unlikely(!backbone_gw)) return; @@ -632,7 +649,8 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, if (memcmp(an_addr, batadv_announce_mac, 4) != 0) return 0; - backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid); + backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid, + false); if (unlikely(!backbone_gw)) return 1; @@ -730,7 +748,8 @@ static int batadv_handle_claim(struct batadv_priv *bat_priv, /* register the gateway if not yet available, and add the claim. */ - backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid); + backbone_gw = batadv_bla_get_backbone_gw(bat_priv, backbone_addr, vid, + false); if (unlikely(!backbone_gw)) return 1; @@ -1140,6 +1159,24 @@ static void batadv_bla_periodic_work(struct work_struct *work) backbone_gw->lasttime = jiffies; batadv_bla_send_announce(bat_priv, backbone_gw); + + /* request_sent is only set after creation to avoid + * problems when we are not yet known as backbone gw + * in the backbone. + * + * We can reset this now after we waited some periods + * to give bridge forward delays and bla group forming + * some grace time. + */ + + if (atomic_read(&backbone_gw->request_sent) == 0) + continue; + + if (!atomic_dec_and_test(&backbone_gw->wait_periods)) + continue; + + atomic_dec(&backbone_gw->bat_priv->bla.num_requests); + atomic_set(&backbone_gw->request_sent, 0); } rcu_read_unlock(); } @@ -1212,8 +1249,7 @@ int batadv_bla_init(struct batadv_priv *bat_priv) /** * batadv_bla_check_bcast_duplist * @bat_priv: the bat priv with all the soft interface information - * @bcast_packet: encapsulated broadcast frame plus batman header - * @bcast_packet_len: length of encapsulated broadcast frame plus batman header + * @skb: contains the bcast_packet to be checked * * check if it is on our broadcast list. Another gateway might * have sent the same packet because it is connected to the same backbone, @@ -1225,20 +1261,17 @@ int batadv_bla_init(struct batadv_priv *bat_priv) * the same host however as this might be intended. */ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, - struct batadv_bcast_packet *bcast_packet, - int bcast_packet_len) + struct sk_buff *skb) { - int i, length, curr, ret = 0; - uint8_t *content; - uint16_t crc; + int i, curr, ret = 0; + __be32 crc; + struct batadv_bcast_packet *bcast_packet; struct batadv_bcast_duplist_entry *entry; - length = bcast_packet_len - sizeof(*bcast_packet); - content = (uint8_t *)bcast_packet; - content += sizeof(*bcast_packet); + bcast_packet = (struct batadv_bcast_packet *)skb->data; /* calculate the crc ... */ - crc = crc16(0, content, length); + crc = batadv_skb_crc32(skb, (u8 *)(bcast_packet + 1)); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); @@ -1585,23 +1618,11 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct hlist_head *head; uint32_t i; bool is_own; - int ret = 0; uint8_t *primary_addr; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - please specify interfaces to enable it\n", - net_dev->name); - goto out; - } - - if (primary_if->if_status != BATADV_IF_ACTIVE) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - primary interface not active\n", - net_dev->name); + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) goto out; - } primary_addr = primary_if->net_dev->dev_addr; seq_printf(seq, @@ -1628,7 +1649,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) out: if (primary_if) batadv_hardif_free_ref(primary_if); - return ret; + return 0; } int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) @@ -1643,23 +1664,11 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) int secs, msecs; uint32_t i; bool is_own; - int ret = 0; uint8_t *primary_addr; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - please specify interfaces to enable it\n", - net_dev->name); - goto out; - } - - if (primary_if->if_status != BATADV_IF_ACTIVE) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - primary interface not active\n", - net_dev->name); + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) goto out; - } primary_addr = primary_if->net_dev->dev_addr; seq_printf(seq, @@ -1693,5 +1702,5 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) out: if (primary_if) batadv_hardif_free_ref(primary_if); - return ret; + return 0; } diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 789cb73bde67..196d9a0254bc 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -31,8 +31,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset); int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig); int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, - struct batadv_bcast_packet *bcast_packet, - int hdr_size); + struct sk_buff *skb); void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct batadv_hard_iface *oldif); @@ -81,8 +80,7 @@ static inline int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, static inline int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, - struct batadv_bcast_packet *bcast_packet, - int hdr_size) + struct sk_buff *skb) { return 0; } diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 391d4fb2026f..6f58ddd53bff 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -31,6 +31,7 @@ #include "vis.h" #include "icmp_socket.h" #include "bridge_loop_avoidance.h" +#include "distributed-arp-table.h" static struct dentry *batadv_debugfs; @@ -99,15 +100,17 @@ int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...) static int batadv_log_open(struct inode *inode, struct file *file) { + if (!try_module_get(THIS_MODULE)) + return -EBUSY; + nonseekable_open(inode, file); file->private_data = inode->i_private; - batadv_inc_module_count(); return 0; } static int batadv_log_release(struct inode *inode, struct file *file) { - batadv_dec_module_count(); + module_put(THIS_MODULE); return 0; } @@ -278,6 +281,19 @@ static int batadv_bla_backbone_table_open(struct inode *inode, #endif +#ifdef CONFIG_BATMAN_ADV_DAT +/** + * batadv_dat_cache_open - Prepare file handler for reads from dat_chache + * @inode: inode which was opened + * @file: file handle to be initialized + */ +static int batadv_dat_cache_open(struct inode *inode, struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_dat_cache_seq_print_text, net_dev); +} +#endif + static int batadv_transtable_local_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; @@ -307,7 +323,17 @@ struct batadv_debuginfo batadv_debuginfo_##_name = { \ } \ }; +/* the following attributes are general and therefore they will be directly + * placed in the BATADV_DEBUGFS_SUBDIR subdirectory of debugfs + */ static BATADV_DEBUGINFO(routing_algos, S_IRUGO, batadv_algorithms_open); + +static struct batadv_debuginfo *batadv_general_debuginfos[] = { + &batadv_debuginfo_routing_algos, + NULL, +}; + +/* The following attributes are per soft interface */ static BATADV_DEBUGINFO(originators, S_IRUGO, batadv_originators_open); static BATADV_DEBUGINFO(gateways, S_IRUGO, batadv_gateways_open); static BATADV_DEBUGINFO(transtable_global, S_IRUGO, @@ -317,6 +343,9 @@ static BATADV_DEBUGINFO(bla_claim_table, S_IRUGO, batadv_bla_claim_table_open); static BATADV_DEBUGINFO(bla_backbone_table, S_IRUGO, batadv_bla_backbone_table_open); #endif +#ifdef CONFIG_BATMAN_ADV_DAT +static BATADV_DEBUGINFO(dat_cache, S_IRUGO, batadv_dat_cache_open); +#endif static BATADV_DEBUGINFO(transtable_local, S_IRUGO, batadv_transtable_local_open); static BATADV_DEBUGINFO(vis_data, S_IRUGO, batadv_vis_data_open); @@ -329,6 +358,9 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = { &batadv_debuginfo_bla_claim_table, &batadv_debuginfo_bla_backbone_table, #endif +#ifdef CONFIG_BATMAN_ADV_DAT + &batadv_debuginfo_dat_cache, +#endif &batadv_debuginfo_transtable_local, &batadv_debuginfo_vis_data, NULL, @@ -336,7 +368,7 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = { void batadv_debugfs_init(void) { - struct batadv_debuginfo *bat_debug; + struct batadv_debuginfo **bat_debug; struct dentry *file; batadv_debugfs = debugfs_create_dir(BATADV_DEBUGFS_SUBDIR, NULL); @@ -344,17 +376,23 @@ void batadv_debugfs_init(void) batadv_debugfs = NULL; if (!batadv_debugfs) - goto out; + goto err; - bat_debug = &batadv_debuginfo_routing_algos; - file = debugfs_create_file(bat_debug->attr.name, - S_IFREG | bat_debug->attr.mode, - batadv_debugfs, NULL, &bat_debug->fops); - if (!file) - pr_err("Can't add debugfs file: %s\n", bat_debug->attr.name); + for (bat_debug = batadv_general_debuginfos; *bat_debug; ++bat_debug) { + file = debugfs_create_file(((*bat_debug)->attr).name, + S_IFREG | ((*bat_debug)->attr).mode, + batadv_debugfs, NULL, + &(*bat_debug)->fops); + if (!file) { + pr_err("Can't add general debugfs file: %s\n", + ((*bat_debug)->attr).name); + goto err; + } + } -out: return; +err: + debugfs_remove_recursive(batadv_debugfs); } void batadv_debugfs_destroy(void) diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c new file mode 100644 index 000000000000..183f97a86bb2 --- /dev/null +++ b/net/batman-adv/distributed-arp-table.c @@ -0,0 +1,1083 @@ +/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: + * + * Antonio Quartulli + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + */ + +#include <linux/if_ether.h> +#include <linux/if_arp.h> +#include <net/arp.h> + +#include "main.h" +#include "hash.h" +#include "distributed-arp-table.h" +#include "hard-interface.h" +#include "originator.h" +#include "send.h" +#include "types.h" +#include "translation-table.h" +#include "unicast.h" + +static void batadv_dat_purge(struct work_struct *work); + +/** + * batadv_dat_start_timer - initialise the DAT periodic worker + * @bat_priv: the bat priv with all the soft interface information + */ +static void batadv_dat_start_timer(struct batadv_priv *bat_priv) +{ + INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); + queue_delayed_work(batadv_event_workqueue, &bat_priv->dat.work, + msecs_to_jiffies(10000)); +} + +/** + * batadv_dat_entry_free_ref - decrements the dat_entry refcounter and possibly + * free it + * @dat_entry: the oentry to free + */ +static void batadv_dat_entry_free_ref(struct batadv_dat_entry *dat_entry) +{ + if (atomic_dec_and_test(&dat_entry->refcount)) + kfree_rcu(dat_entry, rcu); +} + +/** + * batadv_dat_to_purge - checks whether a dat_entry has to be purged or not + * @dat_entry: the entry to check + * + * Returns true if the entry has to be purged now, false otherwise + */ +static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry) +{ + return batadv_has_timed_out(dat_entry->last_update, + BATADV_DAT_ENTRY_TIMEOUT); +} + +/** + * __batadv_dat_purge - delete entries from the DAT local storage + * @bat_priv: the bat priv with all the soft interface information + * @to_purge: function in charge to decide whether an entry has to be purged or + * not. This function takes the dat_entry as argument and has to + * returns a boolean value: true is the entry has to be deleted, + * false otherwise + * + * Loops over each entry in the DAT local storage and delete it if and only if + * the to_purge function passed as argument returns true + */ +static void __batadv_dat_purge(struct batadv_priv *bat_priv, + bool (*to_purge)(struct batadv_dat_entry *)) +{ + spinlock_t *list_lock; /* protects write access to the hash lists */ + struct batadv_dat_entry *dat_entry; + struct hlist_node *node, *node_tmp; + struct hlist_head *head; + uint32_t i; + + if (!bat_priv->dat.hash) + return; + + for (i = 0; i < bat_priv->dat.hash->size; i++) { + head = &bat_priv->dat.hash->table[i]; + list_lock = &bat_priv->dat.hash->list_locks[i]; + + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(dat_entry, node, node_tmp, head, + hash_entry) { + /* if an helper function has been passed as parameter, + * ask it if the entry has to be purged or not + */ + if (to_purge && !to_purge(dat_entry)) + continue; + + hlist_del_rcu(node); + batadv_dat_entry_free_ref(dat_entry); + } + spin_unlock_bh(list_lock); + } +} + +/** + * batadv_dat_purge - periodic task that deletes old entries from the local DAT + * hash table + * @work: kernel work struct + */ +static void batadv_dat_purge(struct work_struct *work) +{ + struct delayed_work *delayed_work; + struct batadv_priv_dat *priv_dat; + struct batadv_priv *bat_priv; + + delayed_work = container_of(work, struct delayed_work, work); + priv_dat = container_of(delayed_work, struct batadv_priv_dat, work); + bat_priv = container_of(priv_dat, struct batadv_priv, dat); + + __batadv_dat_purge(bat_priv, batadv_dat_to_purge); + batadv_dat_start_timer(bat_priv); +} + +/** + * batadv_compare_dat - comparing function used in the local DAT hash table + * @node: node in the local table + * @data2: second object to compare the node to + * + * Returns 1 if the two entry are the same, 0 otherwise + */ +static int batadv_compare_dat(const struct hlist_node *node, const void *data2) +{ + const void *data1 = container_of(node, struct batadv_dat_entry, + hash_entry); + + return (memcmp(data1, data2, sizeof(__be32)) == 0 ? 1 : 0); +} + +/** + * batadv_arp_hw_src - extract the hw_src field from an ARP packet + * @skb: ARP packet + * @hdr_size: size of the possible header before the ARP packet + * + * Returns the value of the hw_src field in the ARP packet + */ +static uint8_t *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) +{ + uint8_t *addr; + + addr = (uint8_t *)(skb->data + hdr_size); + addr += ETH_HLEN + sizeof(struct arphdr); + + return addr; +} + +/** + * batadv_arp_ip_src - extract the ip_src field from an ARP packet + * @skb: ARP packet + * @hdr_size: size of the possible header before the ARP packet + * + * Returns the value of the ip_src field in the ARP packet + */ +static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size) +{ + return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN); +} + +/** + * batadv_arp_hw_dst - extract the hw_dst field from an ARP packet + * @skb: ARP packet + * @hdr_size: size of the possible header before the ARP packet + * + * Returns the value of the hw_dst field in the ARP packet + */ +static uint8_t *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) +{ + return batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN + 4; +} + +/** + * batadv_arp_ip_dst - extract the ip_dst field from an ARP packet + * @skb: ARP packet + * @hdr_size: size of the possible header before the ARP packet + * + * Returns the value of the ip_dst field in the ARP packet + */ +static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size) +{ + return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4); +} + +/** + * batadv_hash_dat - compute the hash value for an IP address + * @data: data to hash + * @size: size of the hash table + * + * Returns the selected index in the hash table for the given data + */ +static uint32_t batadv_hash_dat(const void *data, uint32_t size) +{ + const unsigned char *key = data; + uint32_t hash = 0; + size_t i; + + for (i = 0; i < 4; i++) { + hash += key[i]; + hash += (hash << 10); + hash ^= (hash >> 6); + } + + hash += (hash << 3); + hash ^= (hash >> 11); + hash += (hash << 15); + + return hash % size; +} + +/** + * batadv_dat_entry_hash_find - looks for a given dat_entry in the local hash + * table + * @bat_priv: the bat priv with all the soft interface information + * @ip: search key + * + * Returns the dat_entry if found, NULL otherwise + */ +static struct batadv_dat_entry * +batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip) +{ + struct hlist_head *head; + struct hlist_node *node; + struct batadv_dat_entry *dat_entry, *dat_entry_tmp = NULL; + struct batadv_hashtable *hash = bat_priv->dat.hash; + uint32_t index; + + if (!hash) + return NULL; + + index = batadv_hash_dat(&ip, hash->size); + head = &hash->table[index]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(dat_entry, node, head, hash_entry) { + if (dat_entry->ip != ip) + continue; + + if (!atomic_inc_not_zero(&dat_entry->refcount)) + continue; + + dat_entry_tmp = dat_entry; + break; + } + rcu_read_unlock(); + + return dat_entry_tmp; +} + +/** + * batadv_dat_entry_add - add a new dat entry or update it if already exists + * @bat_priv: the bat priv with all the soft interface information + * @ip: ipv4 to add/edit + * @mac_addr: mac address to assign to the given ipv4 + */ +static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip, + uint8_t *mac_addr) +{ + struct batadv_dat_entry *dat_entry; + int hash_added; + + dat_entry = batadv_dat_entry_hash_find(bat_priv, ip); + /* if this entry is already known, just update it */ + if (dat_entry) { + if (!batadv_compare_eth(dat_entry->mac_addr, mac_addr)) + memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN); + dat_entry->last_update = jiffies; + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Entry updated: %pI4 %pM\n", &dat_entry->ip, + dat_entry->mac_addr); + goto out; + } + + dat_entry = kmalloc(sizeof(*dat_entry), GFP_ATOMIC); + if (!dat_entry) + goto out; + + dat_entry->ip = ip; + memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN); + dat_entry->last_update = jiffies; + atomic_set(&dat_entry->refcount, 2); + + hash_added = batadv_hash_add(bat_priv->dat.hash, batadv_compare_dat, + batadv_hash_dat, &dat_entry->ip, + &dat_entry->hash_entry); + + if (unlikely(hash_added != 0)) { + /* remove the reference for the hash */ + batadv_dat_entry_free_ref(dat_entry); + goto out; + } + + batadv_dbg(BATADV_DBG_DAT, bat_priv, "New entry added: %pI4 %pM\n", + &dat_entry->ip, dat_entry->mac_addr); + +out: + if (dat_entry) + batadv_dat_entry_free_ref(dat_entry); +} + +#ifdef CONFIG_BATMAN_ADV_DEBUG + +/** + * batadv_dbg_arp - print a debug message containing all the ARP packet details + * @bat_priv: the bat priv with all the soft interface information + * @skb: ARP packet + * @type: ARP type + * @hdr_size: size of the possible header before the ARP packet + * @msg: message to print together with the debugging information + */ +static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, + uint16_t type, int hdr_size, char *msg) +{ + struct batadv_unicast_4addr_packet *unicast_4addr_packet; + struct batadv_bcast_packet *bcast_pkt; + uint8_t *orig_addr; + __be32 ip_src, ip_dst; + + if (msg) + batadv_dbg(BATADV_DBG_DAT, bat_priv, "%s\n", msg); + + ip_src = batadv_arp_ip_src(skb, hdr_size); + ip_dst = batadv_arp_ip_dst(skb, hdr_size); + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "ARP MSG = [src: %pM-%pI4 dst: %pM-%pI4]\n", + batadv_arp_hw_src(skb, hdr_size), &ip_src, + batadv_arp_hw_dst(skb, hdr_size), &ip_dst); + + if (hdr_size == 0) + return; + + /* if the ARP packet is encapsulated in a batman packet, let's print + * some debug messages + */ + unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; + + switch (unicast_4addr_packet->u.header.packet_type) { + case BATADV_UNICAST: + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "* encapsulated within a UNICAST packet\n"); + break; + case BATADV_UNICAST_4ADDR: + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "* encapsulated within a UNICAST_4ADDR packet (src: %pM)\n", + unicast_4addr_packet->src); + switch (unicast_4addr_packet->subtype) { + case BATADV_P_DAT_DHT_PUT: + batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: DAT_DHT_PUT\n"); + break; + case BATADV_P_DAT_DHT_GET: + batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: DAT_DHT_GET\n"); + break; + case BATADV_P_DAT_CACHE_REPLY: + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "* type: DAT_CACHE_REPLY\n"); + break; + case BATADV_P_DATA: + batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: DATA\n"); + break; + default: + batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: Unknown (%u)!\n", + unicast_4addr_packet->u.header.packet_type); + } + break; + case BATADV_BCAST: + bcast_pkt = (struct batadv_bcast_packet *)unicast_4addr_packet; + orig_addr = bcast_pkt->orig; + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "* encapsulated within a BCAST packet (src: %pM)\n", + orig_addr); + break; + default: + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "* encapsulated within an unknown packet type (0x%x)\n", + unicast_4addr_packet->u.header.packet_type); + } +} + +#else + +static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, + uint16_t type, int hdr_size, char *msg) +{ +} + +#endif /* CONFIG_BATMAN_ADV_DEBUG */ + +/** + * batadv_is_orig_node_eligible - check whether a node can be a DHT candidate + * @res: the array with the already selected candidates + * @select: number of already selected candidates + * @tmp_max: address of the currently evaluated node + * @max: current round max address + * @last_max: address of the last selected candidate + * @candidate: orig_node under evaluation + * @max_orig_node: last selected candidate + * + * Returns true if the node has been elected as next candidate or false othrwise + */ +static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, + int select, batadv_dat_addr_t tmp_max, + batadv_dat_addr_t max, + batadv_dat_addr_t last_max, + struct batadv_orig_node *candidate, + struct batadv_orig_node *max_orig_node) +{ + bool ret = false; + int j; + + /* Check if this node has already been selected... */ + for (j = 0; j < select; j++) + if (res[j].orig_node == candidate) + break; + /* ..and possibly skip it */ + if (j < select) + goto out; + /* sanity check: has it already been selected? This should not happen */ + if (tmp_max > last_max) + goto out; + /* check if during this iteration an originator with a closer dht + * address has already been found + */ + if (tmp_max < max) + goto out; + /* this is an hash collision with the temporary selected node. Choose + * the one with the lowest address + */ + if ((tmp_max == max) && + (batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0)) + goto out; + + ret = true; +out: + return ret; +} + +/** + * batadv_choose_next_candidate - select the next DHT candidate + * @bat_priv: the bat priv with all the soft interface information + * @cands: candidates array + * @select: number of candidates already present in the array + * @ip_key: key to look up in the DHT + * @last_max: pointer where the address of the selected candidate will be saved + */ +static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, + struct batadv_dat_candidate *cands, + int select, batadv_dat_addr_t ip_key, + batadv_dat_addr_t *last_max) +{ + batadv_dat_addr_t max = 0, tmp_max = 0; + struct batadv_orig_node *orig_node, *max_orig_node = NULL; + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct hlist_node *node; + struct hlist_head *head; + int i; + + /* if no node is eligible as candidate, leave the candidate type as + * NOT_FOUND + */ + cands[select].type = BATADV_DAT_CANDIDATE_NOT_FOUND; + + /* iterate over the originator list and find the node with closest + * dat_address which has not been selected yet + */ + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + /* the dht space is a ring and addresses are unsigned */ + tmp_max = BATADV_DAT_ADDR_MAX - orig_node->dat_addr + + ip_key; + + if (!batadv_is_orig_node_eligible(cands, select, + tmp_max, max, + *last_max, orig_node, + max_orig_node)) + continue; + + if (!atomic_inc_not_zero(&orig_node->refcount)) + continue; + + max = tmp_max; + if (max_orig_node) + batadv_orig_node_free_ref(max_orig_node); + max_orig_node = orig_node; + } + rcu_read_unlock(); + } + if (max_orig_node) { + cands[select].type = BATADV_DAT_CANDIDATE_ORIG; + cands[select].orig_node = max_orig_node; + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "dat_select_candidates() %d: selected %pM addr=%u dist=%u\n", + select, max_orig_node->orig, max_orig_node->dat_addr, + max); + } + *last_max = max; +} + +/** + * batadv_dat_select_candidates - selects the nodes which the DHT message has to + * be sent to + * @bat_priv: the bat priv with all the soft interface information + * @ip_dst: ipv4 to look up in the DHT + * + * An originator O is selected if and only if its DHT_ID value is one of three + * closest values (from the LEFT, with wrap around if needed) then the hash + * value of the key. ip_dst is the key. + * + * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM + */ +static struct batadv_dat_candidate * +batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) +{ + int select; + batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key; + struct batadv_dat_candidate *res; + + if (!bat_priv->orig_hash) + return NULL; + + res = kmalloc(BATADV_DAT_CANDIDATES_NUM * sizeof(*res), GFP_ATOMIC); + if (!res) + return NULL; + + ip_key = (batadv_dat_addr_t)batadv_hash_dat(&ip_dst, + BATADV_DAT_ADDR_MAX); + + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "dat_select_candidates(): IP=%pI4 hash(IP)=%u\n", &ip_dst, + ip_key); + + for (select = 0; select < BATADV_DAT_CANDIDATES_NUM; select++) + batadv_choose_next_candidate(bat_priv, res, select, ip_key, + &last_max); + + return res; +} + +/** + * batadv_dat_send_data - send a payload to the selected candidates + * @bat_priv: the bat priv with all the soft interface information + * @skb: payload to send + * @ip: the DHT key + * @packet_subtype: unicast4addr packet subtype to use + * + * In this function the skb is copied by means of pskb_copy() and is sent as + * unicast packet to each of the selected candidates + * + * Returns true if the packet is sent to at least one candidate, false otherwise + */ +static bool batadv_dat_send_data(struct batadv_priv *bat_priv, + struct sk_buff *skb, __be32 ip, + int packet_subtype) +{ + int i; + bool ret = false; + int send_status; + struct batadv_neigh_node *neigh_node = NULL; + struct sk_buff *tmp_skb; + struct batadv_dat_candidate *cand; + + cand = batadv_dat_select_candidates(bat_priv, ip); + if (!cand) + goto out; + + batadv_dbg(BATADV_DBG_DAT, bat_priv, "DHT_SEND for %pI4\n", &ip); + + for (i = 0; i < BATADV_DAT_CANDIDATES_NUM; i++) { + if (cand[i].type == BATADV_DAT_CANDIDATE_NOT_FOUND) + continue; + + neigh_node = batadv_orig_node_get_router(cand[i].orig_node); + if (!neigh_node) + goto free_orig; + + tmp_skb = pskb_copy(skb, GFP_ATOMIC); + if (!batadv_unicast_4addr_prepare_skb(bat_priv, tmp_skb, + cand[i].orig_node, + packet_subtype)) { + kfree_skb(tmp_skb); + goto free_neigh; + } + + send_status = batadv_send_skb_packet(tmp_skb, + neigh_node->if_incoming, + neigh_node->addr); + if (send_status == NET_XMIT_SUCCESS) { + /* count the sent packet */ + switch (packet_subtype) { + case BATADV_P_DAT_DHT_GET: + batadv_inc_counter(bat_priv, + BATADV_CNT_DAT_GET_TX); + break; + case BATADV_P_DAT_DHT_PUT: + batadv_inc_counter(bat_priv, + BATADV_CNT_DAT_PUT_TX); + break; + } + + /* packet sent to a candidate: return true */ + ret = true; + } +free_neigh: + batadv_neigh_node_free_ref(neigh_node); +free_orig: + batadv_orig_node_free_ref(cand[i].orig_node); + } + +out: + kfree(cand); + return ret; +} + +/** + * batadv_dat_hash_free - free the local DAT hash table + * @bat_priv: the bat priv with all the soft interface information + */ +static void batadv_dat_hash_free(struct batadv_priv *bat_priv) +{ + if (!bat_priv->dat.hash) + return; + + __batadv_dat_purge(bat_priv, NULL); + + batadv_hash_destroy(bat_priv->dat.hash); + + bat_priv->dat.hash = NULL; +} + +/** + * batadv_dat_init - initialise the DAT internals + * @bat_priv: the bat priv with all the soft interface information + */ +int batadv_dat_init(struct batadv_priv *bat_priv) +{ + if (bat_priv->dat.hash) + return 0; + + bat_priv->dat.hash = batadv_hash_new(1024); + + if (!bat_priv->dat.hash) + return -ENOMEM; + + batadv_dat_start_timer(bat_priv); + + return 0; +} + +/** + * batadv_dat_free - free the DAT internals + * @bat_priv: the bat priv with all the soft interface information + */ +void batadv_dat_free(struct batadv_priv *bat_priv) +{ + cancel_delayed_work_sync(&bat_priv->dat.work); + + batadv_dat_hash_free(bat_priv); +} + +/** + * batadv_dat_cache_seq_print_text - print the local DAT hash table + * @seq: seq file to print on + * @offset: not used + */ +int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hashtable *hash = bat_priv->dat.hash; + struct batadv_dat_entry *dat_entry; + struct batadv_hard_iface *primary_if; + struct hlist_node *node; + struct hlist_head *head; + unsigned long last_seen_jiffies; + int last_seen_msecs, last_seen_secs, last_seen_mins; + uint32_t i; + + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) + goto out; + + seq_printf(seq, "Distributed ARP Table (%s):\n", net_dev->name); + seq_printf(seq, " %-7s %-13s %5s\n", "IPv4", "MAC", + "last-seen"); + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(dat_entry, node, head, hash_entry) { + last_seen_jiffies = jiffies - dat_entry->last_update; + last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); + last_seen_mins = last_seen_msecs / 60000; + last_seen_msecs = last_seen_msecs % 60000; + last_seen_secs = last_seen_msecs / 1000; + + seq_printf(seq, " * %15pI4 %14pM %6i:%02i\n", + &dat_entry->ip, dat_entry->mac_addr, + last_seen_mins, last_seen_secs); + } + rcu_read_unlock(); + } + +out: + if (primary_if) + batadv_hardif_free_ref(primary_if); + return 0; +} + +/** + * batadv_arp_get_type - parse an ARP packet and gets the type + * @bat_priv: the bat priv with all the soft interface information + * @skb: packet to analyse + * @hdr_size: size of the possible header before the ARP packet in the skb + * + * Returns the ARP type if the skb contains a valid ARP packet, 0 otherwise + */ +static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ + struct arphdr *arphdr; + struct ethhdr *ethhdr; + __be32 ip_src, ip_dst; + uint8_t *hw_src, *hw_dst; + uint16_t type = 0; + + /* pull the ethernet header */ + if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN))) + goto out; + + ethhdr = (struct ethhdr *)(skb->data + hdr_size); + + if (ethhdr->h_proto != htons(ETH_P_ARP)) + goto out; + + /* pull the ARP payload */ + if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN + + arp_hdr_len(skb->dev)))) + goto out; + + arphdr = (struct arphdr *)(skb->data + hdr_size + ETH_HLEN); + + /* Check whether the ARP packet carries a valid + * IP information + */ + if (arphdr->ar_hrd != htons(ARPHRD_ETHER)) + goto out; + + if (arphdr->ar_pro != htons(ETH_P_IP)) + goto out; + + if (arphdr->ar_hln != ETH_ALEN) + goto out; + + if (arphdr->ar_pln != 4) + goto out; + + /* Check for bad reply/request. If the ARP message is not sane, DAT + * will simply ignore it + */ + ip_src = batadv_arp_ip_src(skb, hdr_size); + ip_dst = batadv_arp_ip_dst(skb, hdr_size); + if (ipv4_is_loopback(ip_src) || ipv4_is_multicast(ip_src) || + ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst) || + ipv4_is_zeronet(ip_src) || ipv4_is_lbcast(ip_src) || + ipv4_is_zeronet(ip_dst) || ipv4_is_lbcast(ip_dst)) + goto out; + + hw_src = batadv_arp_hw_src(skb, hdr_size); + if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src)) + goto out; + + /* we don't care about the destination MAC address in ARP requests */ + if (arphdr->ar_op != htons(ARPOP_REQUEST)) { + hw_dst = batadv_arp_hw_dst(skb, hdr_size); + if (is_zero_ether_addr(hw_dst) || + is_multicast_ether_addr(hw_dst)) + goto out; + } + + type = ntohs(arphdr->ar_op); +out: + return type; +} + +/** + * batadv_dat_snoop_outgoing_arp_request - snoop the ARP request and try to + * answer using DAT + * @bat_priv: the bat priv with all the soft interface information + * @skb: packet to check + * + * Returns true if the message has been sent to the dht candidates, false + * otherwise. In case of true the message has to be enqueued to permit the + * fallback + */ +bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + uint16_t type = 0; + __be32 ip_dst, ip_src; + uint8_t *hw_src; + bool ret = false; + struct batadv_dat_entry *dat_entry = NULL; + struct sk_buff *skb_new; + struct batadv_hard_iface *primary_if = NULL; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + goto out; + + type = batadv_arp_get_type(bat_priv, skb, 0); + /* If the node gets an ARP_REQUEST it has to send a DHT_GET unicast + * message to the selected DHT candidates + */ + if (type != ARPOP_REQUEST) + goto out; + + batadv_dbg_arp(bat_priv, skb, type, 0, "Parsing outgoing ARP REQUEST"); + + ip_src = batadv_arp_ip_src(skb, 0); + hw_src = batadv_arp_hw_src(skb, 0); + ip_dst = batadv_arp_ip_dst(skb, 0); + + batadv_dat_entry_add(bat_priv, ip_src, hw_src); + + dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst); + if (dat_entry) { + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + skb_new = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_src, + primary_if->soft_iface, ip_dst, hw_src, + dat_entry->mac_addr, hw_src); + if (!skb_new) + goto out; + + skb_reset_mac_header(skb_new); + skb_new->protocol = eth_type_trans(skb_new, + primary_if->soft_iface); + bat_priv->stats.rx_packets++; + bat_priv->stats.rx_bytes += skb->len + ETH_HLEN; + primary_if->soft_iface->last_rx = jiffies; + + netif_rx(skb_new); + batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP request replied locally\n"); + ret = true; + } else { + /* Send the request on the DHT */ + ret = batadv_dat_send_data(bat_priv, skb, ip_dst, + BATADV_P_DAT_DHT_GET); + } +out: + if (dat_entry) + batadv_dat_entry_free_ref(dat_entry); + if (primary_if) + batadv_hardif_free_ref(primary_if); + return ret; +} + +/** + * batadv_dat_snoop_incoming_arp_request - snoop the ARP request and try to + * answer using the local DAT storage + * @bat_priv: the bat priv with all the soft interface information + * @skb: packet to check + * @hdr_size: size of the encapsulation header + * + * Returns true if the request has been answered, false otherwise + */ +bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ + uint16_t type; + __be32 ip_src, ip_dst; + uint8_t *hw_src; + struct sk_buff *skb_new; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_dat_entry *dat_entry = NULL; + bool ret = false; + int err; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + goto out; + + type = batadv_arp_get_type(bat_priv, skb, hdr_size); + if (type != ARPOP_REQUEST) + goto out; + + hw_src = batadv_arp_hw_src(skb, hdr_size); + ip_src = batadv_arp_ip_src(skb, hdr_size); + ip_dst = batadv_arp_ip_dst(skb, hdr_size); + + batadv_dbg_arp(bat_priv, skb, type, hdr_size, + "Parsing incoming ARP REQUEST"); + + batadv_dat_entry_add(bat_priv, ip_src, hw_src); + + dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst); + if (!dat_entry) + goto out; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + skb_new = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_src, + primary_if->soft_iface, ip_dst, hw_src, + dat_entry->mac_addr, hw_src); + + if (!skb_new) + goto out; + + /* to preserve backwards compatibility, here the node has to answer + * using the same packet type it received for the request. This is due + * to that if a node is not using the 4addr packet format it may not + * support it. + */ + if (hdr_size == sizeof(struct batadv_unicast_4addr_packet)) + err = batadv_unicast_4addr_send_skb(bat_priv, skb_new, + BATADV_P_DAT_CACHE_REPLY); + else + err = batadv_unicast_send_skb(bat_priv, skb_new); + + if (!err) { + batadv_inc_counter(bat_priv, BATADV_CNT_DAT_CACHED_REPLY_TX); + ret = true; + } +out: + if (dat_entry) + batadv_dat_entry_free_ref(dat_entry); + if (primary_if) + batadv_hardif_free_ref(primary_if); + if (ret) + kfree_skb(skb); + return ret; +} + +/** + * batadv_dat_snoop_outgoing_arp_reply - snoop the ARP reply and fill the DHT + * @bat_priv: the bat priv with all the soft interface information + * @skb: packet to check + */ +void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + uint16_t type; + __be32 ip_src, ip_dst; + uint8_t *hw_src, *hw_dst; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + return; + + type = batadv_arp_get_type(bat_priv, skb, 0); + if (type != ARPOP_REPLY) + return; + + batadv_dbg_arp(bat_priv, skb, type, 0, "Parsing outgoing ARP REPLY"); + + hw_src = batadv_arp_hw_src(skb, 0); + ip_src = batadv_arp_ip_src(skb, 0); + hw_dst = batadv_arp_hw_dst(skb, 0); + ip_dst = batadv_arp_ip_dst(skb, 0); + + batadv_dat_entry_add(bat_priv, ip_src, hw_src); + batadv_dat_entry_add(bat_priv, ip_dst, hw_dst); + + /* Send the ARP reply to the candidates for both the IP addresses that + * the node got within the ARP reply + */ + batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT); +} +/** + * batadv_dat_snoop_incoming_arp_reply - snoop the ARP reply and fill the local + * DAT storage only + * @bat_priv: the bat priv with all the soft interface information + * @skb: packet to check + * @hdr_size: siaze of the encapsulation header + */ +bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ + uint16_t type; + __be32 ip_src, ip_dst; + uint8_t *hw_src, *hw_dst; + bool ret = false; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + goto out; + + type = batadv_arp_get_type(bat_priv, skb, hdr_size); + if (type != ARPOP_REPLY) + goto out; + + batadv_dbg_arp(bat_priv, skb, type, hdr_size, + "Parsing incoming ARP REPLY"); + + hw_src = batadv_arp_hw_src(skb, hdr_size); + ip_src = batadv_arp_ip_src(skb, hdr_size); + hw_dst = batadv_arp_hw_dst(skb, hdr_size); + ip_dst = batadv_arp_ip_dst(skb, hdr_size); + + /* Update our internal cache with both the IP addresses the node got + * within the ARP reply + */ + batadv_dat_entry_add(bat_priv, ip_src, hw_src); + batadv_dat_entry_add(bat_priv, ip_dst, hw_dst); + + /* if this REPLY is directed to a client of mine, let's deliver the + * packet to the interface + */ + ret = !batadv_is_my_client(bat_priv, hw_dst); +out: + if (ret) + kfree_skb(skb); + /* if ret == false -> packet has to be delivered to the interface */ + return ret; +} + +/** + * batadv_dat_drop_broadcast_packet - check if an ARP request has to be dropped + * (because the node has already got the reply via DAT) or not + * @bat_priv: the bat priv with all the soft interface information + * @forw_packet: the broadcast packet + * + * Returns true if the node can drop the packet, false otherwise + */ +bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, + struct batadv_forw_packet *forw_packet) +{ + uint16_t type; + __be32 ip_dst; + struct batadv_dat_entry *dat_entry = NULL; + bool ret = false; + const size_t bcast_len = sizeof(struct batadv_bcast_packet); + + if (!atomic_read(&bat_priv->distributed_arp_table)) + goto out; + + /* If this packet is an ARP_REQUEST and the node already has the + * information that it is going to ask, then the packet can be dropped + */ + if (forw_packet->num_packets) + goto out; + + type = batadv_arp_get_type(bat_priv, forw_packet->skb, bcast_len); + if (type != ARPOP_REQUEST) + goto out; + + ip_dst = batadv_arp_ip_dst(forw_packet->skb, bcast_len); + dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst); + /* check if the node already got this entry */ + if (!dat_entry) { + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "ARP Request for %pI4: fallback\n", &ip_dst); + goto out; + } + + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "ARP Request for %pI4: fallback prevented\n", &ip_dst); + ret = true; + +out: + if (dat_entry) + batadv_dat_entry_free_ref(dat_entry); + return ret; +} diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h new file mode 100644 index 000000000000..d060c033e7de --- /dev/null +++ b/net/batman-adv/distributed-arp-table.h @@ -0,0 +1,167 @@ +/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: + * + * Antonio Quartulli + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + */ + +#ifndef _NET_BATMAN_ADV_ARP_H_ +#define _NET_BATMAN_ADV_ARP_H_ + +#ifdef CONFIG_BATMAN_ADV_DAT + +#include "types.h" +#include "originator.h" + +#include <linux/if_arp.h> + +#define BATADV_DAT_ADDR_MAX ((batadv_dat_addr_t)~(batadv_dat_addr_t)0) + +bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, + struct sk_buff *skb); +bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size); +void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, + struct sk_buff *skb); +bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size); +bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, + struct batadv_forw_packet *forw_packet); + +/** + * batadv_dat_init_orig_node_addr - assign a DAT address to the orig_node + * @orig_node: the node to assign the DAT address to + */ +static inline void +batadv_dat_init_orig_node_addr(struct batadv_orig_node *orig_node) +{ + uint32_t addr; + + addr = batadv_choose_orig(orig_node->orig, BATADV_DAT_ADDR_MAX); + orig_node->dat_addr = (batadv_dat_addr_t)addr; +} + +/** + * batadv_dat_init_own_addr - assign a DAT address to the node itself + * @bat_priv: the bat priv with all the soft interface information + * @primary_if: a pointer to the primary interface + */ +static inline void +batadv_dat_init_own_addr(struct batadv_priv *bat_priv, + struct batadv_hard_iface *primary_if) +{ + uint32_t addr; + + addr = batadv_choose_orig(primary_if->net_dev->dev_addr, + BATADV_DAT_ADDR_MAX); + + bat_priv->dat.addr = (batadv_dat_addr_t)addr; +} + +int batadv_dat_init(struct batadv_priv *bat_priv); +void batadv_dat_free(struct batadv_priv *bat_priv); +int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset); + +/** + * batadv_dat_inc_counter - increment the correct DAT packet counter + * @bat_priv: the bat priv with all the soft interface information + * @subtype: the 4addr subtype of the packet to be counted + * + * Updates the ethtool statistics for the received packet if it is a DAT subtype + */ +static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv, + uint8_t subtype) +{ + switch (subtype) { + case BATADV_P_DAT_DHT_GET: + batadv_inc_counter(bat_priv, + BATADV_CNT_DAT_GET_RX); + break; + case BATADV_P_DAT_DHT_PUT: + batadv_inc_counter(bat_priv, + BATADV_CNT_DAT_PUT_RX); + break; + } +} + +#else + +static inline bool +batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return false; +} + +static inline bool +batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ + return false; +} + +static inline bool +batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return false; +} + +static inline bool +batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ + return false; +} + +static inline bool +batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, + struct batadv_forw_packet *forw_packet) +{ + return false; +} + +static inline void +batadv_dat_init_orig_node_addr(struct batadv_orig_node *orig_node) +{ +} + +static inline void batadv_dat_init_own_addr(struct batadv_priv *bat_priv, + struct batadv_hard_iface *iface) +{ +} + +static inline void batadv_arp_change_timeout(struct net_device *soft_iface, + const char *name) +{ +} + +static inline int batadv_dat_init(struct batadv_priv *bat_priv) +{ + return 0; +} + +static inline void batadv_dat_free(struct batadv_priv *bat_priv) +{ +} + +static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv, + uint8_t subtype) +{ +} + +#endif /* CONFIG_BATMAN_ADV_DAT */ + +#endif /* _NET_BATMAN_ADV_ARP_H_ */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 15d67abc10a4..dd07c7e3654f 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -477,22 +477,11 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hard_iface *primary_if; struct batadv_gw_node *gw_node; struct hlist_node *node; - int gw_count = 0, ret = 0; + int gw_count = 0; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - please specify interfaces to enable it\n", - net_dev->name); + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) goto out; - } - - if (primary_if->if_status != BATADV_IF_ACTIVE) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - primary interface not active\n", - net_dev->name); - goto out; - } seq_printf(seq, " %-12s (%s/%i) %17s [%10s]: gw_class ... [B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", @@ -519,7 +508,7 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) out: if (primary_if) batadv_hardif_free_ref(primary_if); - return ret; + return 0; } static bool batadv_is_type_dhcprequest(struct sk_buff *skb, int header_len) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index d112fd6750b0..f1d37cd81815 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -18,6 +18,7 @@ */ #include "main.h" +#include "distributed-arp-table.h" #include "hard-interface.h" #include "soft-interface.h" #include "send.h" @@ -29,6 +30,7 @@ #include "bridge_loop_avoidance.h" #include <linux/if_arp.h> +#include <linux/if_ether.h> void batadv_hardif_free_rcu(struct rcu_head *rcu) { @@ -58,6 +60,45 @@ out: return hard_iface; } +/** + * batadv_is_on_batman_iface - check if a device is a batman iface descendant + * @net_dev: the device to check + * + * If the user creates any virtual device on top of a batman-adv interface, it + * is important to prevent this new interface to be used to create a new mesh + * network (this behaviour would lead to a batman-over-batman configuration). + * This function recursively checks all the fathers of the device passed as + * argument looking for a batman-adv soft interface. + * + * Returns true if the device is descendant of a batman-adv mesh interface (or + * if it is a batman-adv interface itself), false otherwise + */ +static bool batadv_is_on_batman_iface(const struct net_device *net_dev) +{ + struct net_device *parent_dev; + bool ret; + + /* check if this is a batman-adv mesh interface */ + if (batadv_softif_is_valid(net_dev)) + return true; + + /* no more parents..stop recursion */ + if (net_dev->iflink == net_dev->ifindex) + return false; + + /* recurse over the parent device */ + parent_dev = dev_get_by_index(&init_net, net_dev->iflink); + /* if we got a NULL parent_dev there is something broken.. */ + if (WARN(!parent_dev, "Cannot find parent device")) + return false; + + ret = batadv_is_on_batman_iface(parent_dev); + + if (parent_dev) + dev_put(parent_dev); + return ret; +} + static int batadv_is_valid_iface(const struct net_device *net_dev) { if (net_dev->flags & IFF_LOOPBACK) @@ -70,7 +111,7 @@ static int batadv_is_valid_iface(const struct net_device *net_dev) return 0; /* no batman over batman */ - if (batadv_softif_is_valid(net_dev)) + if (batadv_is_on_batman_iface(net_dev)) return 0; return 1; @@ -109,6 +150,8 @@ static void batadv_primary_if_update_addr(struct batadv_priv *bat_priv, if (!primary_if) goto out; + batadv_dat_init_own_addr(bat_priv, primary_if); + skb = bat_priv->vis.my_info->skb_packet; vis_packet = (struct batadv_vis_packet *)skb->data; memcpy(vis_packet->vis_orig, primary_if->net_dev->dev_addr, ETH_ALEN); @@ -269,7 +312,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, { struct batadv_priv *bat_priv; struct net_device *soft_iface; - __be16 ethertype = __constant_htons(BATADV_ETH_P_BATMAN); + __be16 ethertype = __constant_htons(ETH_P_BATMAN); int ret; if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) @@ -450,8 +493,8 @@ batadv_hardif_add_interface(struct net_device *net_dev) /* This can't be called via a bat_priv callback because * we have no bat_priv yet. */ - atomic_set(&hard_iface->seqno, 1); - hard_iface->packet_buff = NULL; + atomic_set(&hard_iface->bat_iv.ogm_seqno, 1); + hard_iface->bat_iv.ogm_buff = NULL; return hard_iface; diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 977de9c75fc2..e05333905afd 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -82,6 +82,28 @@ static inline void batadv_hash_delete(struct batadv_hashtable *hash, } /** + * batadv_hash_bytes - hash some bytes and add them to the previous hash + * @hash: previous hash value + * @data: data to be hashed + * @size: number of bytes to be hashed + * + * Returns the new hash value. + */ +static inline uint32_t batadv_hash_bytes(uint32_t hash, void *data, + uint32_t size) +{ + const unsigned char *key = data; + int i; + + for (i = 0; i < size; i++) { + hash += key[i]; + hash += (hash << 10); + hash ^= (hash >> 6); + } + return hash; +} + +/** * batadv_hash_add - adds data to the hashtable * @hash: storage hash table * @compare: callback to determine if 2 hash elements are identical diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index bde3cf747507..87ca8095b011 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -42,12 +42,16 @@ static int batadv_socket_open(struct inode *inode, struct file *file) unsigned int i; struct batadv_socket_client *socket_client; + if (!try_module_get(THIS_MODULE)) + return -EBUSY; + nonseekable_open(inode, file); socket_client = kmalloc(sizeof(*socket_client), GFP_KERNEL); - - if (!socket_client) + if (!socket_client) { + module_put(THIS_MODULE); return -ENOMEM; + } for (i = 0; i < ARRAY_SIZE(batadv_socket_client_hash); i++) { if (!batadv_socket_client_hash[i]) { @@ -59,6 +63,7 @@ static int batadv_socket_open(struct inode *inode, struct file *file) if (i == ARRAY_SIZE(batadv_socket_client_hash)) { pr_err("Error - can't add another packet client: maximum number of clients reached\n"); kfree(socket_client); + module_put(THIS_MODULE); return -EXFULL; } @@ -71,7 +76,6 @@ static int batadv_socket_open(struct inode *inode, struct file *file) file->private_data = socket_client; - batadv_inc_module_count(); return 0; } @@ -96,7 +100,7 @@ static int batadv_socket_release(struct inode *inode, struct file *file) spin_unlock_bh(&socket_client->lock); kfree(socket_client); - batadv_dec_module_count(); + module_put(THIS_MODULE); return 0; } @@ -173,13 +177,13 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, if (len >= sizeof(struct batadv_icmp_packet_rr)) packet_len = sizeof(struct batadv_icmp_packet_rr); - skb = dev_alloc_skb(packet_len + ETH_HLEN); + skb = dev_alloc_skb(packet_len + ETH_HLEN + NET_IP_ALIGN); if (!skb) { len = -ENOMEM; goto out; } - skb_reserve(skb, ETH_HLEN); + skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); icmp_packet = (struct batadv_icmp_packet_rr *)skb_put(skb, packet_len); if (copy_from_user(icmp_packet, buff, packet_len)) { diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index b4aa470bc4a6..f65a222b7b83 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -17,6 +17,8 @@ * 02110-1301, USA */ +#include <linux/crc32c.h> +#include <linux/highmem.h> #include "main.h" #include "sysfs.h" #include "debugfs.h" @@ -29,6 +31,7 @@ #include "hard-interface.h" #include "gateway_client.h" #include "bridge_loop_avoidance.h" +#include "distributed-arp-table.h" #include "vis.h" #include "hash.h" #include "bat_algo.h" @@ -128,6 +131,10 @@ int batadv_mesh_init(struct net_device *soft_iface) if (ret < 0) goto err; + ret = batadv_dat_init(bat_priv); + if (ret < 0) + goto err; + atomic_set(&bat_priv->gw.reselect, 0); atomic_set(&bat_priv->mesh_state, BATADV_MESH_ACTIVE); @@ -155,21 +162,13 @@ void batadv_mesh_free(struct net_device *soft_iface) batadv_bla_free(bat_priv); + batadv_dat_free(bat_priv); + free_percpu(bat_priv->bat_counters); atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); } -void batadv_inc_module_count(void) -{ - try_module_get(THIS_MODULE); -} - -void batadv_dec_module_count(void) -{ - module_put(THIS_MODULE); -} - int batadv_is_my_mac(const uint8_t *addr) { const struct batadv_hard_iface *hard_iface; @@ -188,6 +187,42 @@ int batadv_is_my_mac(const uint8_t *addr) return 0; } +/** + * batadv_seq_print_text_primary_if_get - called from debugfs table printing + * function that requires the primary interface + * @seq: debugfs table seq_file struct + * + * Returns primary interface if found or NULL otherwise. + */ +struct batadv_hard_iface * +batadv_seq_print_text_primary_if_get(struct seq_file *seq) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hard_iface *primary_if; + + primary_if = batadv_primary_if_get_selected(bat_priv); + + if (!primary_if) { + seq_printf(seq, + "BATMAN mesh %s disabled - please specify interfaces to enable it\n", + net_dev->name); + goto out; + } + + if (primary_if->if_status == BATADV_IF_ACTIVE) + goto out; + + seq_printf(seq, + "BATMAN mesh %s disabled - primary interface not active\n", + net_dev->name); + batadv_hardif_free_ref(primary_if); + primary_if = NULL; + +out: + return primary_if; +} + static int batadv_recv_unhandled_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if) { @@ -274,6 +309,8 @@ static void batadv_recv_handler_init(void) /* batman icmp packet */ batadv_rx_handler[BATADV_ICMP] = batadv_recv_icmp_packet; + /* unicast with 4 addresses packet */ + batadv_rx_handler[BATADV_UNICAST_4ADDR] = batadv_recv_unicast_packet; /* unicast packet */ batadv_rx_handler[BATADV_UNICAST] = batadv_recv_unicast_packet; /* fragmented unicast packet */ @@ -385,6 +422,38 @@ int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) return 0; } +/** + * batadv_skb_crc32 - calculate CRC32 of the whole packet and skip bytes in + * the header + * @skb: skb pointing to fragmented socket buffers + * @payload_ptr: Pointer to position inside the head buffer of the skb + * marking the start of the data to be CRC'ed + * + * payload_ptr must always point to an address in the skb head buffer and not to + * a fragment. + */ +__be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr) +{ + u32 crc = 0; + unsigned int from; + unsigned int to = skb->len; + struct skb_seq_state st; + const u8 *data; + unsigned int len; + unsigned int consumed = 0; + + from = (unsigned int)(payload_ptr - skb->data); + + skb_prepare_seq_read(skb, from, to, &st); + while ((len = skb_seq_read(consumed, &data, &st)) != 0) { + crc = crc32c(crc, data, len); + consumed += len; + } + skb_abort_seq_read(&st); + + return htonl(crc); +} + static int batadv_param_set_ra(const char *val, const struct kernel_param *kp) { struct batadv_algo_ops *bat_algo_ops; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index d57b746219de..2f85577086a7 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -26,7 +26,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2012.4.0" +#define BATADV_SOURCE_VERSION "2012.5.0" #endif /* B.A.T.M.A.N. parameters */ @@ -44,6 +44,7 @@ #define BATADV_TT_LOCAL_TIMEOUT 3600000 /* in milliseconds */ #define BATADV_TT_CLIENT_ROAM_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_CLIENT_TEMP_TIMEOUT 600000 /* in milliseconds */ +#define BATADV_DAT_ENTRY_TIMEOUT (5*60000) /* 5 mins in milliseconds */ /* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) */ @@ -73,6 +74,11 @@ #define BATADV_LOG_BUF_LEN 8192 /* has to be a power of 2 */ +/* msecs after which an ARP_REQUEST is sent in broadcast as fallback */ +#define ARP_REQ_DELAY 250 +/* numbers of originator to contact for any PUT/GET DHT operation */ +#define BATADV_DAT_CANDIDATES_NUM 3 + #define BATADV_VIS_INTERVAL 5000 /* 5 seconds */ /* how much worse secondary interfaces may be to be considered as bonding @@ -89,6 +95,7 @@ #define BATADV_BLA_PERIOD_LENGTH 10000 /* 10 seconds */ #define BATADV_BLA_BACKBONE_TIMEOUT (BATADV_BLA_PERIOD_LENGTH * 3) #define BATADV_BLA_CLAIM_TIMEOUT (BATADV_BLA_PERIOD_LENGTH * 10) +#define BATADV_BLA_WAIT_PERIODS 3 #define BATADV_DUPLIST_SIZE 16 #define BATADV_DUPLIST_TIMEOUT 500 /* 500 ms */ @@ -117,6 +124,9 @@ enum batadv_uev_type { #define BATADV_GW_THRESHOLD 50 +#define BATADV_DAT_CANDIDATE_NOT_FOUND 0 +#define BATADV_DAT_CANDIDATE_ORIG 1 + /* Debug Messages */ #ifdef pr_fmt #undef pr_fmt @@ -150,9 +160,9 @@ extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); -void batadv_inc_module_count(void); -void batadv_dec_module_count(void); int batadv_is_my_mac(const uint8_t *addr); +struct batadv_hard_iface * +batadv_seq_print_text_primary_if_get(struct seq_file *seq); int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev); @@ -164,14 +174,24 @@ void batadv_recv_handler_unregister(uint8_t packet_type); int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops); int batadv_algo_select(struct batadv_priv *bat_priv, char *name); int batadv_algo_seq_print_text(struct seq_file *seq, void *offset); +__be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr); -/* all messages related to routing / flooding / broadcasting / etc */ +/** + * enum batadv_dbg_level - available log levels + * @BATADV_DBG_BATMAN: OGM and TQ computations related messages + * @BATADV_DBG_ROUTES: route added / changed / deleted + * @BATADV_DBG_TT: translation table messages + * @BATADV_DBG_BLA: bridge loop avoidance messages + * @BATADV_DBG_DAT: ARP snooping and DAT related messages + * @BATADV_DBG_ALL: the union of all the above log levels + */ enum batadv_dbg_level { BATADV_DBG_BATMAN = BIT(0), - BATADV_DBG_ROUTES = BIT(1), /* route added / changed / deleted */ - BATADV_DBG_TT = BIT(2), /* translation table operations */ - BATADV_DBG_BLA = BIT(3), /* bridge loop avoidance */ - BATADV_DBG_ALL = 15, + BATADV_DBG_ROUTES = BIT(1), + BATADV_DBG_TT = BIT(2), + BATADV_DBG_BLA = BIT(3), + BATADV_DBG_DAT = BIT(4), + BATADV_DBG_ALL = 31, }; #ifdef CONFIG_BATMAN_ADV_DEBUG diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index ac9bdf8f80a6..8c32cf1c2dec 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -18,6 +18,7 @@ */ #include "main.h" +#include "distributed-arp-table.h" #include "originator.h" #include "hash.h" #include "translation-table.h" @@ -220,9 +221,9 @@ struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, atomic_set(&orig_node->refcount, 2); orig_node->tt_initialised = false; - orig_node->tt_poss_change = false; orig_node->bat_priv = bat_priv; memcpy(orig_node->orig, addr, ETH_ALEN); + batadv_dat_init_orig_node_addr(orig_node); orig_node->router = NULL; orig_node->tt_crc = 0; atomic_set(&orig_node->last_ttvn, 0); @@ -415,23 +416,10 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) int last_seen_msecs; unsigned long last_seen_jiffies; uint32_t i; - int ret = 0; - primary_if = batadv_primary_if_get_selected(bat_priv); - - if (!primary_if) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - please specify interfaces to enable it\n", - net_dev->name); - goto out; - } - - if (primary_if->if_status != BATADV_IF_ACTIVE) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - primary interface not active\n", - net_dev->name); + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) goto out; - } seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", BATADV_SOURCE_VERSION, primary_if->net_dev->name, @@ -485,7 +473,7 @@ next: out: if (primary_if) batadv_hardif_free_ref(primary_if); - return ret; + return 0; } static int batadv_orig_node_add_if(struct batadv_orig_node *orig_node, diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 2d23a14c220e..cb6405bf755c 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -20,17 +20,30 @@ #ifndef _NET_BATMAN_ADV_PACKET_H_ #define _NET_BATMAN_ADV_PACKET_H_ -#define BATADV_ETH_P_BATMAN 0x4305 /* unofficial/not registered Ethertype */ - enum batadv_packettype { - BATADV_IV_OGM = 0x01, - BATADV_ICMP = 0x02, - BATADV_UNICAST = 0x03, - BATADV_BCAST = 0x04, - BATADV_VIS = 0x05, - BATADV_UNICAST_FRAG = 0x06, - BATADV_TT_QUERY = 0x07, - BATADV_ROAM_ADV = 0x08, + BATADV_IV_OGM = 0x01, + BATADV_ICMP = 0x02, + BATADV_UNICAST = 0x03, + BATADV_BCAST = 0x04, + BATADV_VIS = 0x05, + BATADV_UNICAST_FRAG = 0x06, + BATADV_TT_QUERY = 0x07, + BATADV_ROAM_ADV = 0x08, + BATADV_UNICAST_4ADDR = 0x09, +}; + +/** + * enum batadv_subtype - packet subtype for unicast4addr + * @BATADV_P_DATA: user payload + * @BATADV_P_DAT_DHT_GET: DHT request message + * @BATADV_P_DAT_DHT_PUT: DHT store message + * @BATADV_P_DAT_CACHE_REPLY: ARP reply generated by DAT + */ +enum batadv_subtype { + BATADV_P_DATA = 0x01, + BATADV_P_DAT_DHT_GET = 0x02, + BATADV_P_DAT_DHT_PUT = 0x03, + BATADV_P_DAT_CACHE_REPLY = 0x04, }; /* this file is included by batctl which needs these defines */ @@ -106,13 +119,16 @@ struct batadv_bla_claim_dst { uint8_t magic[3]; /* FF:43:05 */ uint8_t type; /* bla_claimframe */ __be16 group; /* group id */ -} __packed; +}; struct batadv_header { uint8_t packet_type; uint8_t version; /* batman version field */ uint8_t ttl; -} __packed; + /* the parent struct has to add a byte after the header to make + * everything 4 bytes aligned again + */ +}; struct batadv_ogm_packet { struct batadv_header header; @@ -137,7 +153,7 @@ struct batadv_icmp_packet { __be16 seqno; uint8_t uid; uint8_t reserved; -} __packed; +}; #define BATADV_RR_LEN 16 @@ -153,13 +169,44 @@ struct batadv_icmp_packet_rr { uint8_t uid; uint8_t rr_cur; uint8_t rr[BATADV_RR_LEN][ETH_ALEN]; -} __packed; +}; + +/* All packet headers in front of an ethernet header have to be completely + * divisible by 2 but not by 4 to make the payload after the ethernet + * header again 4 bytes boundary aligned. + * + * A packing of 2 is necessary to avoid extra padding at the end of the struct + * caused by a structure member which is larger than two bytes. Otherwise + * the structure would not fulfill the previously mentioned rule to avoid the + * misalignment of the payload after the ethernet header. It may also lead to + * leakage of information when the padding it not initialized before sending. + */ +#pragma pack(2) struct batadv_unicast_packet { struct batadv_header header; uint8_t ttvn; /* destination translation table version number */ uint8_t dest[ETH_ALEN]; -} __packed; + /* "4 bytes boundary + 2 bytes" long to make the payload after the + * following ethernet header again 4 bytes boundary aligned + */ +}; + +/** + * struct batadv_unicast_4addr_packet - extended unicast packet + * @u: common unicast packet header + * @src: address of the source + * @subtype: packet subtype + */ +struct batadv_unicast_4addr_packet { + struct batadv_unicast_packet u; + uint8_t src[ETH_ALEN]; + uint8_t subtype; + uint8_t reserved; + /* "4 bytes boundary + 2 bytes" long to make the payload after the + * following ethernet header again 4 bytes boundary aligned + */ +}; struct batadv_unicast_frag_packet { struct batadv_header header; @@ -176,7 +223,12 @@ struct batadv_bcast_packet { uint8_t reserved; __be32 seqno; uint8_t orig[ETH_ALEN]; -} __packed; + /* "4 bytes boundary + 2 bytes" long to make the payload after the + * following ethernet header again 4 bytes boundary aligned + */ +}; + +#pragma pack() struct batadv_vis_packet { struct batadv_header header; @@ -187,7 +239,7 @@ struct batadv_vis_packet { uint8_t vis_orig[ETH_ALEN]; /* originator reporting its neighbors */ uint8_t target_orig[ETH_ALEN]; /* who should receive this packet */ uint8_t sender_orig[ETH_ALEN]; /* who sent or forwarded this packet */ -} __packed; +}; struct batadv_tt_query_packet { struct batadv_header header; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 376b4cc6ca82..1aa1722d0187 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -28,6 +28,7 @@ #include "vis.h" #include "unicast.h" #include "bridge_loop_avoidance.h" +#include "distributed-arp-table.h" static int batadv_route_unicast_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); @@ -284,7 +285,6 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, { struct batadv_hard_iface *primary_if = NULL; struct batadv_orig_node *orig_node = NULL; - struct batadv_neigh_node *router = NULL; struct batadv_icmp_packet_rr *icmp_packet; int ret = NET_RX_DROP; @@ -306,10 +306,6 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, if (!orig_node) goto out; - router = batadv_orig_node_get_router(orig_node); - if (!router) - goto out; - /* create a copy of the skb, if needed, to modify it. */ if (skb_cow(skb, ETH_HLEN) < 0) goto out; @@ -321,14 +317,12 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, icmp_packet->msg_type = BATADV_ECHO_REPLY; icmp_packet->header.ttl = BATADV_TTL; - batadv_send_skb_packet(skb, router->if_incoming, router->addr); - ret = NET_RX_SUCCESS; + if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + ret = NET_RX_SUCCESS; out: if (primary_if) batadv_hardif_free_ref(primary_if); - if (router) - batadv_neigh_node_free_ref(router); if (orig_node) batadv_orig_node_free_ref(orig_node); return ret; @@ -339,7 +333,6 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv, { struct batadv_hard_iface *primary_if = NULL; struct batadv_orig_node *orig_node = NULL; - struct batadv_neigh_node *router = NULL; struct batadv_icmp_packet *icmp_packet; int ret = NET_RX_DROP; @@ -361,10 +354,6 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv, if (!orig_node) goto out; - router = batadv_orig_node_get_router(orig_node); - if (!router) - goto out; - /* create a copy of the skb, if needed, to modify it. */ if (skb_cow(skb, ETH_HLEN) < 0) goto out; @@ -376,14 +365,12 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv, icmp_packet->msg_type = BATADV_TTL_EXCEEDED; icmp_packet->header.ttl = BATADV_TTL; - batadv_send_skb_packet(skb, router->if_incoming, router->addr); - ret = NET_RX_SUCCESS; + if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + ret = NET_RX_SUCCESS; out: if (primary_if) batadv_hardif_free_ref(primary_if); - if (router) - batadv_neigh_node_free_ref(router); if (orig_node) batadv_orig_node_free_ref(orig_node); return ret; @@ -397,7 +384,6 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, struct batadv_icmp_packet_rr *icmp_packet; struct ethhdr *ethhdr; struct batadv_orig_node *orig_node = NULL; - struct batadv_neigh_node *router = NULL; int hdr_size = sizeof(struct batadv_icmp_packet); int ret = NET_RX_DROP; @@ -446,10 +432,6 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, if (!orig_node) goto out; - router = batadv_orig_node_get_router(orig_node); - if (!router) - goto out; - /* create a copy of the skb, if needed, to modify it. */ if (skb_cow(skb, ETH_HLEN) < 0) goto out; @@ -460,12 +442,10 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, icmp_packet->header.ttl--; /* route it */ - batadv_send_skb_packet(skb, router->if_incoming, router->addr); - ret = NET_RX_SUCCESS; + if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) + ret = NET_RX_SUCCESS; out: - if (router) - batadv_neigh_node_free_ref(router); if (orig_node) batadv_orig_node_free_ref(orig_node); return ret; @@ -549,25 +529,18 @@ batadv_find_ifalter_router(struct batadv_orig_node *primary_orig, if (tmp_neigh_node->if_incoming == recv_if) continue; - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + if (router && tmp_neigh_node->tq_avg <= router->tq_avg) continue; - /* if we don't have a router yet - * or this one is better, choose it. - */ - if ((!router) || - (tmp_neigh_node->tq_avg > router->tq_avg)) { - /* decrement refcount of - * previously selected router - */ - if (router) - batadv_neigh_node_free_ref(router); + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; - router = tmp_neigh_node; - atomic_inc_not_zero(&router->refcount); - } + /* decrement refcount of previously selected router */ + if (router) + batadv_neigh_node_free_ref(router); - batadv_neigh_node_free_ref(tmp_neigh_node); + /* we found a better router (or at least one valid router) */ + router = tmp_neigh_node; } /* use the first candidate if nothing was found. */ @@ -687,21 +660,8 @@ int batadv_recv_roam_adv(struct sk_buff *skb, struct batadv_hard_iface *recv_if) struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct batadv_roam_adv_packet *roam_adv_packet; struct batadv_orig_node *orig_node; - struct ethhdr *ethhdr; - - /* drop packet if it has not necessary minimum size */ - if (unlikely(!pskb_may_pull(skb, - sizeof(struct batadv_roam_adv_packet)))) - goto out; - - ethhdr = (struct ethhdr *)skb_mac_header(skb); - - /* packet with unicast indication but broadcast recipient */ - if (is_broadcast_ether_addr(ethhdr->h_dest)) - goto out; - /* packet with broadcast sender address */ - if (is_broadcast_ether_addr(ethhdr->h_source)) + if (batadv_check_unicast_packet(skb, sizeof(*roam_adv_packet)) < 0) goto out; batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_RX); @@ -730,12 +690,6 @@ int batadv_recv_roam_adv(struct sk_buff *skb, struct batadv_hard_iface *recv_if) BATADV_TT_CLIENT_ROAM, atomic_read(&orig_node->last_ttvn) + 1); - /* Roaming phase starts: I have new information but the ttvn has not - * been incremented yet. This flag will make me check all the incoming - * packets for the correct destination. - */ - bat_priv->tt.poss_change = true; - batadv_orig_node_free_ref(orig_node); out: /* returning NET_RX_DROP will make the caller function kfree the skb */ @@ -907,8 +861,8 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, skb->len + ETH_HLEN); /* route it */ - batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - ret = NET_RX_SUCCESS; + if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) + ret = NET_RX_SUCCESS; out: if (neigh_node) @@ -918,80 +872,161 @@ out: return ret; } +/** + * batadv_reroute_unicast_packet - update the unicast header for re-routing + * @bat_priv: the bat priv with all the soft interface information + * @unicast_packet: the unicast header to be updated + * @dst_addr: the payload destination + * + * Search the translation table for dst_addr and update the unicast header with + * the new corresponding information (originator address where the destination + * client currently is and its known TTVN) + * + * Returns true if the packet header has been updated, false otherwise + */ +static bool +batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, + struct batadv_unicast_packet *unicast_packet, + uint8_t *dst_addr) +{ + struct batadv_orig_node *orig_node = NULL; + struct batadv_hard_iface *primary_if = NULL; + bool ret = false; + uint8_t *orig_addr, orig_ttvn; + + if (batadv_is_my_client(bat_priv, dst_addr)) { + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + orig_addr = primary_if->net_dev->dev_addr; + orig_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); + } else { + orig_node = batadv_transtable_search(bat_priv, NULL, dst_addr); + if (!orig_node) + goto out; + + if (batadv_compare_eth(orig_node->orig, unicast_packet->dest)) + goto out; + + orig_addr = orig_node->orig; + orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + } + + /* update the packet header */ + memcpy(unicast_packet->dest, orig_addr, ETH_ALEN); + unicast_packet->ttvn = orig_ttvn; + + ret = true; +out: + if (primary_if) + batadv_hardif_free_ref(primary_if); + if (orig_node) + batadv_orig_node_free_ref(orig_node); + + return ret; +} + static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, struct sk_buff *skb) { - uint8_t curr_ttvn; + uint8_t curr_ttvn, old_ttvn; struct batadv_orig_node *orig_node; struct ethhdr *ethhdr; struct batadv_hard_iface *primary_if; struct batadv_unicast_packet *unicast_packet; - bool tt_poss_change; int is_old_ttvn; - /* I could need to modify it */ - if (skb_cow(skb, sizeof(struct batadv_unicast_packet)) < 0) + /* check if there is enough data before accessing it */ + if (pskb_may_pull(skb, sizeof(*unicast_packet) + ETH_HLEN) < 0) + return 0; + + /* create a copy of the skb (in case of for re-routing) to modify it. */ + if (skb_cow(skb, sizeof(*unicast_packet)) < 0) return 0; unicast_packet = (struct batadv_unicast_packet *)skb->data; + ethhdr = (struct ethhdr *)(skb->data + sizeof(*unicast_packet)); - if (batadv_is_my_mac(unicast_packet->dest)) { - tt_poss_change = bat_priv->tt.poss_change; - curr_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); - } else { + /* check if the destination client was served by this node and it is now + * roaming. In this case, it means that the node has got a ROAM_ADV + * message and that it knows the new destination in the mesh to re-route + * the packet to + */ + if (batadv_tt_local_client_is_roaming(bat_priv, ethhdr->h_dest)) { + if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + ethhdr->h_dest)) + net_ratelimited_function(batadv_dbg, BATADV_DBG_TT, + bat_priv, + "Rerouting unicast packet to %pM (dst=%pM): Local Roaming\n", + unicast_packet->dest, + ethhdr->h_dest); + /* at this point the mesh destination should have been + * substituted with the originator address found in the global + * table. If not, let the packet go untouched anyway because + * there is nothing the node can do + */ + return 1; + } + + /* retrieve the TTVN known by this node for the packet destination. This + * value is used later to check if the node which sent (or re-routed + * last time) the packet had an updated information or not + */ + curr_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); + if (!batadv_is_my_mac(unicast_packet->dest)) { orig_node = batadv_orig_hash_find(bat_priv, unicast_packet->dest); - + /* if it is not possible to find the orig_node representing the + * destination, the packet can immediately be dropped as it will + * not be possible to deliver it + */ if (!orig_node) return 0; curr_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); - tt_poss_change = orig_node->tt_poss_change; batadv_orig_node_free_ref(orig_node); } - /* Check whether I have to reroute the packet */ + /* check if the TTVN contained in the packet is fresher than what the + * node knows + */ is_old_ttvn = batadv_seq_before(unicast_packet->ttvn, curr_ttvn); - if (is_old_ttvn || tt_poss_change) { - /* check if there is enough data before accessing it */ - if (pskb_may_pull(skb, sizeof(struct batadv_unicast_packet) + - ETH_HLEN) < 0) - return 0; + if (!is_old_ttvn) + return 1; - ethhdr = (struct ethhdr *)(skb->data + sizeof(*unicast_packet)); + old_ttvn = unicast_packet->ttvn; + /* the packet was forged based on outdated network information. Its + * destination can possibly be updated and forwarded towards the new + * target host + */ + if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + ethhdr->h_dest)) { + net_ratelimited_function(batadv_dbg, BATADV_DBG_TT, bat_priv, + "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", + unicast_packet->dest, ethhdr->h_dest, + old_ttvn, curr_ttvn); + return 1; + } - /* we don't have an updated route for this client, so we should - * not try to reroute the packet!! - */ - if (batadv_tt_global_client_is_roaming(bat_priv, - ethhdr->h_dest)) - return 1; + /* the packet has not been re-routed: either the destination is + * currently served by this node or there is no destination at all and + * it is possible to drop the packet + */ + if (!batadv_is_my_client(bat_priv, ethhdr->h_dest)) + return 0; - orig_node = batadv_transtable_search(bat_priv, NULL, - ethhdr->h_dest); - - if (!orig_node) { - if (!batadv_is_my_client(bat_priv, ethhdr->h_dest)) - return 0; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - return 0; - memcpy(unicast_packet->dest, - primary_if->net_dev->dev_addr, ETH_ALEN); - batadv_hardif_free_ref(primary_if); - } else { - memcpy(unicast_packet->dest, orig_node->orig, - ETH_ALEN); - curr_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); - batadv_orig_node_free_ref(orig_node); - } + /* update the header in order to let the packet be delivered to this + * node's soft interface + */ + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + return 0; - batadv_dbg(BATADV_DBG_ROUTES, bat_priv, - "TTVN mismatch (old_ttvn %u new_ttvn %u)! Rerouting unicast packet (for %pM) to %pM\n", - unicast_packet->ttvn, curr_ttvn, ethhdr->h_dest, - unicast_packet->dest); + memcpy(unicast_packet->dest, primary_if->net_dev->dev_addr, ETH_ALEN); + + batadv_hardif_free_ref(primary_if); + + unicast_packet->ttvn = curr_ttvn; - unicast_packet->ttvn = curr_ttvn; - } return 1; } @@ -1000,7 +1035,19 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct batadv_unicast_packet *unicast_packet; + struct batadv_unicast_4addr_packet *unicast_4addr_packet; + uint8_t *orig_addr; + struct batadv_orig_node *orig_node = NULL; int hdr_size = sizeof(*unicast_packet); + bool is4addr; + + unicast_packet = (struct batadv_unicast_packet *)skb->data; + unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; + + is4addr = unicast_packet->header.packet_type == BATADV_UNICAST_4ADDR; + /* the caller function should have already pulled 2 bytes */ + if (is4addr) + hdr_size = sizeof(*unicast_4addr_packet); if (batadv_check_unicast_packet(skb, hdr_size) < 0) return NET_RX_DROP; @@ -1008,12 +1055,28 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, if (!batadv_check_unicast_ttvn(bat_priv, skb)) return NET_RX_DROP; - unicast_packet = (struct batadv_unicast_packet *)skb->data; - /* packet for me */ if (batadv_is_my_mac(unicast_packet->dest)) { + if (is4addr) { + batadv_dat_inc_counter(bat_priv, + unicast_4addr_packet->subtype); + orig_addr = unicast_4addr_packet->src; + orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + } + + if (batadv_dat_snoop_incoming_arp_request(bat_priv, skb, + hdr_size)) + goto rx_success; + if (batadv_dat_snoop_incoming_arp_reply(bat_priv, skb, + hdr_size)) + goto rx_success; + batadv_interface_rx(recv_if->soft_iface, skb, recv_if, hdr_size, - NULL); + orig_node); + +rx_success: + if (orig_node) + batadv_orig_node_free_ref(orig_node); return NET_RX_SUCCESS; } @@ -1050,8 +1113,17 @@ int batadv_recv_ucast_frag_packet(struct sk_buff *skb, if (!new_skb) return NET_RX_SUCCESS; + if (batadv_dat_snoop_incoming_arp_request(bat_priv, new_skb, + hdr_size)) + goto rx_success; + if (batadv_dat_snoop_incoming_arp_reply(bat_priv, new_skb, + hdr_size)) + goto rx_success; + batadv_interface_rx(recv_if->soft_iface, new_skb, recv_if, sizeof(struct batadv_unicast_packet), NULL); + +rx_success: return NET_RX_SUCCESS; } @@ -1124,14 +1196,8 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, spin_unlock_bh(&orig_node->bcast_seqno_lock); - /* keep skb linear for crc calculation */ - if (skb_linearize(skb) < 0) - goto out; - - bcast_packet = (struct batadv_bcast_packet *)skb->data; - /* check whether this has been sent by another originator before */ - if (batadv_bla_check_bcast_duplist(bat_priv, bcast_packet, skb->len)) + if (batadv_bla_check_bcast_duplist(bat_priv, skb)) goto out; /* rebroadcast packet */ @@ -1143,9 +1209,16 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, if (batadv_bla_is_backbone_gw(skb, orig_node, hdr_size)) goto out; + if (batadv_dat_snoop_incoming_arp_request(bat_priv, skb, hdr_size)) + goto rx_success; + if (batadv_dat_snoop_incoming_arp_reply(bat_priv, skb, hdr_size)) + goto rx_success; + /* broadcast for me */ batadv_interface_rx(recv_if->soft_iface, skb, recv_if, hdr_size, orig_node); + +rx_success: ret = NET_RX_SUCCESS; goto out; diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 570a8bce0364..4425af9dad40 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -18,6 +18,7 @@ */ #include "main.h" +#include "distributed-arp-table.h" #include "send.h" #include "routing.h" #include "translation-table.h" @@ -27,6 +28,8 @@ #include "gateway_common.h" #include "originator.h" +#include <linux/if_ether.h> + static void batadv_send_outstanding_bcast_packet(struct work_struct *work); /* send out an already prepared packet to the given address via the @@ -59,11 +62,11 @@ int batadv_send_skb_packet(struct sk_buff *skb, ethhdr = (struct ethhdr *)skb_mac_header(skb); memcpy(ethhdr->h_source, hard_iface->net_dev->dev_addr, ETH_ALEN); memcpy(ethhdr->h_dest, dst_addr, ETH_ALEN); - ethhdr->h_proto = __constant_htons(BATADV_ETH_P_BATMAN); + ethhdr->h_proto = __constant_htons(ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); skb->priority = TC_PRIO_CONTROL; - skb->protocol = __constant_htons(BATADV_ETH_P_BATMAN); + skb->protocol = __constant_htons(ETH_P_BATMAN); skb->dev = hard_iface->net_dev; @@ -77,6 +80,39 @@ send_skb_err: return NET_XMIT_DROP; } +/** + * batadv_send_skb_to_orig - Lookup next-hop and transmit skb. + * @skb: Packet to be transmitted. + * @orig_node: Final destination of the packet. + * @recv_if: Interface used when receiving the packet (can be NULL). + * + * Looks up the best next-hop towards the passed originator and passes the + * skb on for preparation of MAC header. If the packet originated from this + * host, NULL can be passed as recv_if and no interface alternating is + * attempted. + * + * Returns TRUE on success; FALSE otherwise. + */ +bool batadv_send_skb_to_orig(struct sk_buff *skb, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if) +{ + struct batadv_priv *bat_priv = orig_node->bat_priv; + struct batadv_neigh_node *neigh_node; + + /* batadv_find_router() increases neigh_nodes refcount if found. */ + neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); + if (!neigh_node) + return false; + + /* route it */ + batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + + batadv_neigh_node_free_ref(neigh_node); + + return true; +} + void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); @@ -209,6 +245,9 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; + if (batadv_dat_drop_broadcast_packet(bat_priv, forw_packet)) + goto out; + /* rebroadcast packet */ rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 643329b787ed..0078dece1abc 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -23,6 +23,9 @@ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, const uint8_t *dst_addr); +bool batadv_send_skb_to_orig(struct sk_buff *skb, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if); void batadv_schedule_bat_ogm(struct batadv_hard_iface *hard_iface); int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, const struct sk_buff *skb, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index b9a28d2dd3e8..6b548fde8e04 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -20,6 +20,7 @@ #include "main.h" #include "soft-interface.h" #include "hard-interface.h" +#include "distributed-arp-table.h" #include "routing.h" #include "send.h" #include "debugfs.h" @@ -33,6 +34,7 @@ #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> +#include <linux/if_ether.h> #include "unicast.h" #include "bridge_loop_avoidance.h" @@ -145,14 +147,17 @@ static int batadv_interface_tx(struct sk_buff *skb, struct batadv_hard_iface *primary_if = NULL; struct batadv_bcast_packet *bcast_packet; struct vlan_ethhdr *vhdr; - __be16 ethertype = __constant_htons(BATADV_ETH_P_BATMAN); - static const uint8_t stp_addr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00, 0x00, - 0x00}; + __be16 ethertype = __constant_htons(ETH_P_BATMAN); + static const uint8_t stp_addr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00, + 0x00, 0x00}; + static const uint8_t ectp_addr[ETH_ALEN] = {0xCF, 0x00, 0x00, 0x00, + 0x00, 0x00}; unsigned int header_len = 0; int data_len = skb->len, ret; short vid __maybe_unused = -1; bool do_bcast = false; uint32_t seqno; + unsigned long brd_delay = 1; if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; @@ -168,7 +173,7 @@ static int batadv_interface_tx(struct sk_buff *skb, break; /* fall through */ - case BATADV_ETH_P_BATMAN: + case ETH_P_BATMAN: goto dropped; } @@ -180,10 +185,16 @@ static int batadv_interface_tx(struct sk_buff *skb, /* don't accept stp packets. STP does not help in meshes. * better use the bridge loop avoidance ... + * + * The same goes for ECTP sent at least by some Cisco Switches, + * it might confuse the mesh when used with bridge loop avoidance. */ if (batadv_compare_eth(ethhdr->h_dest, stp_addr)) goto dropped; + if (batadv_compare_eth(ethhdr->h_dest, ectp_addr)) + goto dropped; + if (is_multicast_ether_addr(ethhdr->h_dest)) { do_bcast = true; @@ -216,6 +227,13 @@ static int batadv_interface_tx(struct sk_buff *skb, if (!primary_if) goto dropped; + /* in case of ARP request, we do not immediately broadcasti the + * packet, instead we first wait for DAT to try to retrieve the + * correct ARP entry + */ + if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb)) + brd_delay = msecs_to_jiffies(ARP_REQ_DELAY); + if (batadv_skb_head_push(skb, sizeof(*bcast_packet)) < 0) goto dropped; @@ -237,7 +255,7 @@ static int batadv_interface_tx(struct sk_buff *skb, seqno = atomic_inc_return(&bat_priv->bcast_seqno); bcast_packet->seqno = htonl(seqno); - batadv_add_bcast_packet_to_list(bat_priv, skb, 1); + batadv_add_bcast_packet_to_list(bat_priv, skb, brd_delay); /* a copy is stored in the bcast list, therefore removing * the original skb. @@ -252,7 +270,12 @@ static int batadv_interface_tx(struct sk_buff *skb, goto dropped; } - ret = batadv_unicast_send_skb(skb, bat_priv); + if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb)) + goto dropped; + + batadv_dat_snoop_outgoing_arp_reply(bat_priv, skb); + + ret = batadv_unicast_send_skb(bat_priv, skb); if (ret != 0) goto dropped_freed; } @@ -280,7 +303,7 @@ void batadv_interface_rx(struct net_device *soft_iface, struct vlan_ethhdr *vhdr; struct batadv_header *batadv_header = (struct batadv_header *)skb->data; short vid __maybe_unused = -1; - __be16 ethertype = __constant_htons(BATADV_ETH_P_BATMAN); + __be16 ethertype = __constant_htons(ETH_P_BATMAN); bool is_bcast; is_bcast = (batadv_header->packet_type == BATADV_BCAST); @@ -303,7 +326,7 @@ void batadv_interface_rx(struct net_device *soft_iface, break; /* fall through */ - case BATADV_ETH_P_BATMAN: + case ETH_P_BATMAN: goto dropped; } @@ -325,6 +348,12 @@ void batadv_interface_rx(struct net_device *soft_iface, soft_iface->last_rx = jiffies; + /* Let the bridge loop avoidance check the packet. If will + * not handle it, we can safely push it up. + */ + if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) + goto out; + if (orig_node) batadv_tt_add_temporary_global_entry(bat_priv, orig_node, ethhdr->h_source); @@ -332,12 +361,6 @@ void batadv_interface_rx(struct net_device *soft_iface, if (batadv_is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest)) goto dropped; - /* Let the bridge loop avoidance check the packet. If will - * not handle it, we can safely push it up. - */ - if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) - goto out; - netif_rx(skb); goto out; @@ -347,7 +370,51 @@ out: return; } +/* batman-adv network devices have devices nesting below it and are a special + * "super class" of normal network devices; split their locks off into a + * separate class since they always nest. + */ +static struct lock_class_key batadv_netdev_xmit_lock_key; +static struct lock_class_key batadv_netdev_addr_lock_key; + +/** + * batadv_set_lockdep_class_one - Set lockdep class for a single tx queue + * @dev: device which owns the tx queue + * @txq: tx queue to modify + * @_unused: always NULL + */ +static void batadv_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *_unused) +{ + lockdep_set_class(&txq->_xmit_lock, &batadv_netdev_xmit_lock_key); +} + +/** + * batadv_set_lockdep_class - Set txq and addr_list lockdep class + * @dev: network device to modify + */ +static void batadv_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key); + netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL); +} + +/** + * batadv_softif_init - Late stage initialization of soft interface + * @dev: registered network device to modify + * + * Returns error code on failures + */ +static int batadv_softif_init(struct net_device *dev) +{ + batadv_set_lockdep_class(dev); + + return 0; +} + static const struct net_device_ops batadv_netdev_ops = { + .ndo_init = batadv_softif_init, .ndo_open = batadv_interface_open, .ndo_stop = batadv_interface_release, .ndo_get_stats = batadv_interface_stats, @@ -414,6 +481,9 @@ struct net_device *batadv_softif_create(const char *name) atomic_set(&bat_priv->aggregated_ogms, 1); atomic_set(&bat_priv->bonding, 0); atomic_set(&bat_priv->bridge_loop_avoidance, 0); +#ifdef CONFIG_BATMAN_ADV_DAT + atomic_set(&bat_priv->distributed_arp_table, 1); +#endif atomic_set(&bat_priv->ap_isolation, 0); atomic_set(&bat_priv->vis_mode, BATADV_VIS_TYPE_CLIENT_UPDATE); atomic_set(&bat_priv->gw_mode, BATADV_GW_MODE_OFF); @@ -436,7 +506,6 @@ struct net_device *batadv_softif_create(const char *name) #endif bat_priv->tt.last_changeset = NULL; bat_priv->tt.last_changeset_len = 0; - bat_priv->tt.poss_change = false; bat_priv->primary_if = NULL; bat_priv->num_ifaces = 0; @@ -556,6 +625,13 @@ static const struct { { "tt_response_rx" }, { "tt_roam_adv_tx" }, { "tt_roam_adv_rx" }, +#ifdef CONFIG_BATMAN_ADV_DAT + { "dat_get_tx" }, + { "dat_get_rx" }, + { "dat_put_tx" }, + { "dat_put_rx" }, + { "dat_cached_reply_tx" }, +#endif }; static void batadv_get_strings(struct net_device *dev, uint32_t stringset, diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 66518c75c217..84a55cb19b0b 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -20,6 +20,7 @@ #include "main.h" #include "sysfs.h" #include "translation-table.h" +#include "distributed-arp-table.h" #include "originator.h" #include "hard-interface.h" #include "gateway_common.h" @@ -122,55 +123,6 @@ ssize_t batadv_show_##_name(struct kobject *kobj, \ batadv_store_##_name) -#define BATADV_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func) \ -ssize_t batadv_store_##_name(struct kobject *kobj, \ - struct attribute *attr, char *buff, \ - size_t count) \ -{ \ - struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ - struct batadv_hard_iface *hard_iface; \ - ssize_t length; \ - \ - hard_iface = batadv_hardif_get_by_netdev(net_dev); \ - if (!hard_iface) \ - return 0; \ - \ - length = __batadv_store_uint_attr(buff, count, _min, _max, \ - _post_func, attr, \ - &hard_iface->_name, net_dev); \ - \ - batadv_hardif_free_ref(hard_iface); \ - return length; \ -} - -#define BATADV_ATTR_HIF_SHOW_UINT(_name) \ -ssize_t batadv_show_##_name(struct kobject *kobj, \ - struct attribute *attr, char *buff) \ -{ \ - struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ - struct batadv_hard_iface *hard_iface; \ - ssize_t length; \ - \ - hard_iface = batadv_hardif_get_by_netdev(net_dev); \ - if (!hard_iface) \ - return 0; \ - \ - length = sprintf(buff, "%i\n", atomic_read(&hard_iface->_name));\ - \ - batadv_hardif_free_ref(hard_iface); \ - return length; \ -} - -/* Use this, if you are going to set [name] in hard_iface to an - * unsigned integer value - */ -#define BATADV_ATTR_HIF_UINT(_name, _mode, _min, _max, _post_func) \ - static BATADV_ATTR_HIF_STORE_UINT(_name, _min, _max, _post_func)\ - static BATADV_ATTR_HIF_SHOW_UINT(_name) \ - static BATADV_ATTR(_name, _mode, batadv_show_##_name, \ - batadv_store_##_name) - - static int batadv_store_bool_attr(char *buff, size_t count, struct net_device *net_dev, const char *attr_name, atomic_t *attr) @@ -469,6 +421,9 @@ BATADV_ATTR_SIF_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); #ifdef CONFIG_BATMAN_ADV_BLA BATADV_ATTR_SIF_BOOL(bridge_loop_avoidance, S_IRUGO | S_IWUSR, NULL); #endif +#ifdef CONFIG_BATMAN_ADV_DAT +BATADV_ATTR_SIF_BOOL(distributed_arp_table, S_IRUGO | S_IWUSR, NULL); +#endif BATADV_ATTR_SIF_BOOL(fragmentation, S_IRUGO | S_IWUSR, batadv_update_min_mtu); BATADV_ATTR_SIF_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL); static BATADV_ATTR(vis_mode, S_IRUGO | S_IWUSR, batadv_show_vis_mode, @@ -494,6 +449,9 @@ static struct batadv_attribute *batadv_mesh_attrs[] = { #ifdef CONFIG_BATMAN_ADV_BLA &batadv_attr_bridge_loop_avoidance, #endif +#ifdef CONFIG_BATMAN_ADV_DAT + &batadv_attr_distributed_arp_table, +#endif &batadv_attr_fragmentation, &batadv_attr_ap_isolation, &batadv_attr_vis_mode, @@ -730,7 +688,7 @@ int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type, enum batadv_uev_action action, const char *data) { int ret = -ENOMEM; - struct batadv_hard_iface *primary_if = NULL; + struct batadv_hard_iface *primary_if; struct kobject *bat_kobj; char *uevent_env[4] = { NULL, NULL, NULL, NULL }; diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 112edd371b2f..22457a7952ba 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -238,92 +238,134 @@ static int batadv_tt_local_init(struct batadv_priv *bat_priv) return 0; } +static void batadv_tt_global_free(struct batadv_priv *bat_priv, + struct batadv_tt_global_entry *tt_global, + const char *message) +{ + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Deleting global tt entry %pM: %s\n", + tt_global->common.addr, message); + + batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, + batadv_choose_orig, tt_global->common.addr); + batadv_tt_global_entry_free_ref(tt_global); + +} + void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, int ifindex) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); - struct batadv_tt_local_entry *tt_local_entry = NULL; - struct batadv_tt_global_entry *tt_global_entry = NULL; + struct batadv_tt_local_entry *tt_local; + struct batadv_tt_global_entry *tt_global; struct hlist_head *head; struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry; int hash_added; + bool roamed_back = false; - tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr); + tt_local = batadv_tt_local_hash_find(bat_priv, addr); + tt_global = batadv_tt_global_hash_find(bat_priv, addr); - if (tt_local_entry) { - tt_local_entry->last_seen = jiffies; - /* possibly unset the BATADV_TT_CLIENT_PENDING flag */ - tt_local_entry->common.flags &= ~BATADV_TT_CLIENT_PENDING; - goto out; + if (tt_local) { + tt_local->last_seen = jiffies; + if (tt_local->common.flags & BATADV_TT_CLIENT_PENDING) { + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Re-adding pending client %pM\n", addr); + /* whatever the reason why the PENDING flag was set, + * this is a client which was enqueued to be removed in + * this orig_interval. Since it popped up again, the + * flag can be reset like it was never enqueued + */ + tt_local->common.flags &= ~BATADV_TT_CLIENT_PENDING; + goto add_event; + } + + if (tt_local->common.flags & BATADV_TT_CLIENT_ROAM) { + batadv_dbg(BATADV_DBG_TT, bat_priv, + "Roaming client %pM came back to its original location\n", + addr); + /* the ROAM flag is set because this client roamed away + * and the node got a roaming_advertisement message. Now + * that the client popped up again at its original + * location such flag can be unset + */ + tt_local->common.flags &= ~BATADV_TT_CLIENT_ROAM; + roamed_back = true; + } + goto check_roaming; } - tt_local_entry = kmalloc(sizeof(*tt_local_entry), GFP_ATOMIC); - if (!tt_local_entry) + tt_local = kmalloc(sizeof(*tt_local), GFP_ATOMIC); + if (!tt_local) goto out; batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new local tt entry: %pM (ttvn: %d)\n", addr, (uint8_t)atomic_read(&bat_priv->tt.vn)); - memcpy(tt_local_entry->common.addr, addr, ETH_ALEN); - tt_local_entry->common.flags = BATADV_NO_FLAGS; + memcpy(tt_local->common.addr, addr, ETH_ALEN); + tt_local->common.flags = BATADV_NO_FLAGS; if (batadv_is_wifi_iface(ifindex)) - tt_local_entry->common.flags |= BATADV_TT_CLIENT_WIFI; - atomic_set(&tt_local_entry->common.refcount, 2); - tt_local_entry->last_seen = jiffies; - tt_local_entry->common.added_at = tt_local_entry->last_seen; + tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; + atomic_set(&tt_local->common.refcount, 2); + tt_local->last_seen = jiffies; + tt_local->common.added_at = tt_local->last_seen; /* the batman interface mac address should never be purged */ if (batadv_compare_eth(addr, soft_iface->dev_addr)) - tt_local_entry->common.flags |= BATADV_TT_CLIENT_NOPURGE; + tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE; /* The local entry has to be marked as NEW to avoid to send it in * a full table response going out before the next ttvn increment * (consistency check) */ - tt_local_entry->common.flags |= BATADV_TT_CLIENT_NEW; + tt_local->common.flags |= BATADV_TT_CLIENT_NEW; hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt, - batadv_choose_orig, - &tt_local_entry->common, - &tt_local_entry->common.hash_entry); + batadv_choose_orig, &tt_local->common, + &tt_local->common.hash_entry); if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ - batadv_tt_local_entry_free_ref(tt_local_entry); + batadv_tt_local_entry_free_ref(tt_local); goto out; } - batadv_tt_local_event(bat_priv, addr, tt_local_entry->common.flags); - - /* remove address from global hash if present */ - tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr); +add_event: + batadv_tt_local_event(bat_priv, addr, tt_local->common.flags); - /* Check whether it is a roaming! */ - if (tt_global_entry) { +check_roaming: + /* Check whether it is a roaming, but don't do anything if the roaming + * process has already been handled + */ + if (tt_global && !(tt_global->common.flags & BATADV_TT_CLIENT_ROAM)) { /* These node are probably going to update their tt table */ - head = &tt_global_entry->orig_list; + head = &tt_global->orig_list; rcu_read_lock(); hlist_for_each_entry_rcu(orig_entry, node, head, list) { - orig_entry->orig_node->tt_poss_change = true; - - batadv_send_roam_adv(bat_priv, - tt_global_entry->common.addr, + batadv_send_roam_adv(bat_priv, tt_global->common.addr, orig_entry->orig_node); } rcu_read_unlock(); - /* The global entry has to be marked as ROAMING and - * has to be kept for consistency purpose - */ - tt_global_entry->common.flags |= BATADV_TT_CLIENT_ROAM; - tt_global_entry->roam_at = jiffies; + if (roamed_back) { + batadv_tt_global_free(bat_priv, tt_global, + "Roaming canceled"); + tt_global = NULL; + } else { + /* The global entry has to be marked as ROAMING and + * has to be kept for consistency purpose + */ + tt_global->common.flags |= BATADV_TT_CLIENT_ROAM; + tt_global->roam_at = jiffies; + } } + out: - if (tt_local_entry) - batadv_tt_local_entry_free_ref(tt_local_entry); - if (tt_global_entry) - batadv_tt_global_entry_free_ref(tt_global_entry); + if (tt_local) + batadv_tt_local_entry_free_ref(tt_local); + if (tt_global) + batadv_tt_global_entry_free_ref(tt_global); } static void batadv_tt_realloc_packet_buff(unsigned char **packet_buff, @@ -434,22 +476,10 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct hlist_node *node; struct hlist_head *head; uint32_t i; - int ret = 0; - - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - please specify interfaces to enable it\n", - net_dev->name); - goto out; - } - if (primary_if->if_status != BATADV_IF_ACTIVE) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - primary interface not active\n", - net_dev->name); + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) goto out; - } seq_printf(seq, "Locally retrieved addresses (from %s) announced via TT (TTVN: %u):\n", @@ -479,7 +509,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) out: if (primary_if) batadv_hardif_free_ref(primary_if); - return ret; + return 0; } static void @@ -501,24 +531,57 @@ batadv_tt_local_set_pending(struct batadv_priv *bat_priv, tt_local_entry->common.addr, message); } -void batadv_tt_local_remove(struct batadv_priv *bat_priv, const uint8_t *addr, - const char *message, bool roaming) +/** + * batadv_tt_local_remove - logically remove an entry from the local table + * @bat_priv: the bat priv with all the soft interface information + * @addr: the MAC address of the client to remove + * @message: message to append to the log on deletion + * @roaming: true if the deletion is due to a roaming event + * + * Returns the flags assigned to the local entry before being deleted + */ +uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, + const uint8_t *addr, const char *message, + bool roaming) { - struct batadv_tt_local_entry *tt_local_entry = NULL; - uint16_t flags; + struct batadv_tt_local_entry *tt_local_entry; + uint16_t flags, curr_flags = BATADV_NO_FLAGS; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr); if (!tt_local_entry) goto out; + curr_flags = tt_local_entry->common.flags; + flags = BATADV_TT_CLIENT_DEL; - if (roaming) + /* if this global entry addition is due to a roaming, the node has to + * mark the local entry as "roamed" in order to correctly reroute + * packets later + */ + if (roaming) { flags |= BATADV_TT_CLIENT_ROAM; + /* mark the local client as ROAMed */ + tt_local_entry->common.flags |= BATADV_TT_CLIENT_ROAM; + } + + if (!(tt_local_entry->common.flags & BATADV_TT_CLIENT_NEW)) { + batadv_tt_local_set_pending(bat_priv, tt_local_entry, flags, + message); + goto out; + } + /* if this client has been added right now, it is possible to + * immediately purge it + */ + batadv_tt_local_event(bat_priv, tt_local_entry->common.addr, + curr_flags | BATADV_TT_CLIENT_DEL); + hlist_del_rcu(&tt_local_entry->common.hash_entry); + batadv_tt_local_entry_free_ref(tt_local_entry); - batadv_tt_local_set_pending(bat_priv, tt_local_entry, flags, message); out: if (tt_local_entry) batadv_tt_local_entry_free_ref(tt_local_entry); + + return curr_flags; } static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, @@ -721,12 +784,23 @@ int batadv_tt_global_add(struct batadv_priv *bat_priv, const unsigned char *tt_addr, uint8_t flags, uint8_t ttvn) { - struct batadv_tt_global_entry *tt_global_entry = NULL; + struct batadv_tt_global_entry *tt_global_entry; + struct batadv_tt_local_entry *tt_local_entry; int ret = 0; int hash_added; struct batadv_tt_common_entry *common; + uint16_t local_flags; tt_global_entry = batadv_tt_global_hash_find(bat_priv, tt_addr); + tt_local_entry = batadv_tt_local_hash_find(bat_priv, tt_addr); + + /* if the node already has a local client for this entry, it has to wait + * for a roaming advertisement instead of manually messing up the global + * table + */ + if ((flags & BATADV_TT_CLIENT_TEMP) && tt_local_entry && + !(tt_local_entry->common.flags & BATADV_TT_CLIENT_NEW)) + goto out; if (!tt_global_entry) { tt_global_entry = kzalloc(sizeof(*tt_global_entry), GFP_ATOMIC); @@ -738,6 +812,12 @@ int batadv_tt_global_add(struct batadv_priv *bat_priv, common->flags = flags; tt_global_entry->roam_at = 0; + /* node must store current time in case of roaming. This is + * needed to purge this entry out on timeout (if nobody claims + * it) + */ + if (flags & BATADV_TT_CLIENT_ROAM) + tt_global_entry->roam_at = jiffies; atomic_set(&common->refcount, 2); common->added_at = jiffies; @@ -755,19 +835,37 @@ int batadv_tt_global_add(struct batadv_priv *bat_priv, goto out_remove; } } else { + common = &tt_global_entry->common; /* If there is already a global entry, we can use this one for * our processing. - * But if we are trying to add a temporary client we can exit - * directly because the temporary information should never - * override any already known client state (whatever it is) + * But if we are trying to add a temporary client then here are + * two options at this point: + * 1) the global client is not a temporary client: the global + * client has to be left as it is, temporary information + * should never override any already known client state + * 2) the global client is a temporary client: purge the + * originator list and add the new one orig_entry */ - if (flags & BATADV_TT_CLIENT_TEMP) - goto out; + if (flags & BATADV_TT_CLIENT_TEMP) { + if (!(common->flags & BATADV_TT_CLIENT_TEMP)) + goto out; + if (batadv_tt_global_entry_has_orig(tt_global_entry, + orig_node)) + goto out_remove; + batadv_tt_global_del_orig_list(tt_global_entry); + goto add_orig_entry; + } /* if the client was temporary added before receiving the first * OGM announcing it, we have to clear the TEMP flag */ - tt_global_entry->common.flags &= ~BATADV_TT_CLIENT_TEMP; + common->flags &= ~BATADV_TT_CLIENT_TEMP; + + /* the change can carry possible "attribute" flags like the + * TT_CLIENT_WIFI, therefore they have to be copied in the + * client entry + */ + tt_global_entry->common.flags |= flags; /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a @@ -776,33 +874,81 @@ int batadv_tt_global_add(struct batadv_priv *bat_priv, * We should first delete the old originator before adding the * new one. */ - if (tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM) { + if (common->flags & BATADV_TT_CLIENT_ROAM) { batadv_tt_global_del_orig_list(tt_global_entry); - tt_global_entry->common.flags &= ~BATADV_TT_CLIENT_ROAM; + common->flags &= ~BATADV_TT_CLIENT_ROAM; tt_global_entry->roam_at = 0; } } +add_orig_entry: /* add the new orig_entry (if needed) or update it */ batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn); batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new global tt entry: %pM (via %pM)\n", - tt_global_entry->common.addr, orig_node->orig); + common->addr, orig_node->orig); + ret = 1; out_remove: + /* remove address from local hash if present */ - batadv_tt_local_remove(bat_priv, tt_global_entry->common.addr, - "global tt received", - flags & BATADV_TT_CLIENT_ROAM); - ret = 1; + local_flags = batadv_tt_local_remove(bat_priv, tt_addr, + "global tt received", + !!(flags & BATADV_TT_CLIENT_ROAM)); + tt_global_entry->common.flags |= local_flags & BATADV_TT_CLIENT_WIFI; + + if (!(flags & BATADV_TT_CLIENT_ROAM)) + /* this is a normal global add. Therefore the client is not in a + * roaming state anymore. + */ + tt_global_entry->common.flags &= ~BATADV_TT_CLIENT_ROAM; + out: if (tt_global_entry) batadv_tt_global_entry_free_ref(tt_global_entry); + if (tt_local_entry) + batadv_tt_local_entry_free_ref(tt_local_entry); return ret; } -/* print all orig nodes who announce the address for this global entry. - * it is assumed that the caller holds rcu_read_lock(); +/* batadv_transtable_best_orig - Get best originator list entry from tt entry + * @tt_global_entry: global translation table entry to be analyzed + * + * This functon assumes the caller holds rcu_read_lock(). + * Returns best originator list entry or NULL on errors. + */ +static struct batadv_tt_orig_list_entry * +batadv_transtable_best_orig(struct batadv_tt_global_entry *tt_global_entry) +{ + struct batadv_neigh_node *router = NULL; + struct hlist_head *head; + struct hlist_node *node; + struct batadv_tt_orig_list_entry *orig_entry, *best_entry = NULL; + int best_tq = 0; + + head = &tt_global_entry->orig_list; + hlist_for_each_entry_rcu(orig_entry, node, head, list) { + router = batadv_orig_node_get_router(orig_entry->orig_node); + if (!router) + continue; + + if (router->tq_avg > best_tq) { + best_entry = orig_entry; + best_tq = router->tq_avg; + } + + batadv_neigh_node_free_ref(router); + } + + return best_entry; +} + +/* batadv_tt_global_print_entry - print all orig nodes who announce the address + * for this global entry + * @tt_global_entry: global translation table entry to be printed + * @seq: debugfs table seq_file struct + * + * This functon assumes the caller holds rcu_read_lock(). */ static void batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, @@ -810,21 +956,37 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, { struct hlist_head *head; struct hlist_node *node; - struct batadv_tt_orig_list_entry *orig_entry; + struct batadv_tt_orig_list_entry *orig_entry, *best_entry; struct batadv_tt_common_entry *tt_common_entry; uint16_t flags; uint8_t last_ttvn; tt_common_entry = &tt_global_entry->common; + flags = tt_common_entry->flags; + + best_entry = batadv_transtable_best_orig(tt_global_entry); + if (best_entry) { + last_ttvn = atomic_read(&best_entry->orig_node->last_ttvn); + seq_printf(seq, " %c %pM (%3u) via %pM (%3u) [%c%c%c]\n", + '*', tt_global_entry->common.addr, + best_entry->ttvn, best_entry->orig_node->orig, + last_ttvn, + (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), + (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'), + (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.')); + } head = &tt_global_entry->orig_list; hlist_for_each_entry_rcu(orig_entry, node, head, list) { - flags = tt_common_entry->flags; + if (best_entry == orig_entry) + continue; + last_ttvn = atomic_read(&orig_entry->orig_node->last_ttvn); - seq_printf(seq, " * %pM (%3u) via %pM (%3u) [%c%c%c]\n", - tt_global_entry->common.addr, orig_entry->ttvn, - orig_entry->orig_node->orig, last_ttvn, + seq_printf(seq, " %c %pM (%3u) via %pM (%3u) [%c%c%c]\n", + '+', tt_global_entry->common.addr, + orig_entry->ttvn, orig_entry->orig_node->orig, + last_ttvn, (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'), (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.')); @@ -842,22 +1004,10 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) struct hlist_node *node; struct hlist_head *head; uint32_t i; - int ret = 0; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - please specify interfaces to enable it\n", - net_dev->name); - goto out; - } - - if (primary_if->if_status != BATADV_IF_ACTIVE) { - ret = seq_printf(seq, - "BATMAN mesh %s disabled - primary interface not active\n", - net_dev->name); + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) goto out; - } seq_printf(seq, "Globally announced TT entries received via the mesh %s\n", @@ -881,7 +1031,7 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) out: if (primary_if) batadv_hardif_free_ref(primary_if); - return ret; + return 0; } /* deletes the orig list of a tt_global_entry */ @@ -927,21 +1077,6 @@ batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv, spin_unlock_bh(&tt_global_entry->list_lock); } -static void -batadv_tt_global_del_struct(struct batadv_priv *bat_priv, - struct batadv_tt_global_entry *tt_global_entry, - const char *message) -{ - batadv_dbg(BATADV_DBG_TT, bat_priv, - "Deleting global tt entry %pM: %s\n", - tt_global_entry->common.addr, message); - - batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, - batadv_choose_orig, tt_global_entry->common.addr); - batadv_tt_global_entry_free_ref(tt_global_entry); - -} - /* If the client is to be deleted, we check if it is the last origantor entry * within tt_global entry. If yes, we set the BATADV_TT_CLIENT_ROAM flag and the * timer, otherwise we simply remove the originator scheduled for deletion. @@ -990,7 +1125,7 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, const unsigned char *addr, const char *message, bool roaming) { - struct batadv_tt_global_entry *tt_global_entry = NULL; + struct batadv_tt_global_entry *tt_global_entry; struct batadv_tt_local_entry *local_entry = NULL; tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr); @@ -1002,8 +1137,8 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, orig_node, message); if (hlist_empty(&tt_global_entry->orig_list)) - batadv_tt_global_del_struct(bat_priv, tt_global_entry, - message); + batadv_tt_global_free(bat_priv, tt_global_entry, + message); goto out; } @@ -1026,7 +1161,7 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, if (local_entry) { /* local entry exists, case 2: client roamed to us. */ batadv_tt_global_del_orig_list(tt_global_entry); - batadv_tt_global_del_struct(bat_priv, tt_global_entry, message); + batadv_tt_global_free(bat_priv, tt_global_entry, message); } else /* no local entry exists, case 1: check for roaming */ batadv_tt_global_del_roaming(bat_priv, tt_global_entry, @@ -1197,15 +1332,12 @@ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry = NULL; struct batadv_tt_global_entry *tt_global_entry = NULL; struct batadv_orig_node *orig_node = NULL; - struct batadv_neigh_node *router = NULL; - struct hlist_head *head; - struct hlist_node *node; - struct batadv_tt_orig_list_entry *orig_entry; - int best_tq; + struct batadv_tt_orig_list_entry *best_entry; if (src && atomic_read(&bat_priv->ap_isolation)) { tt_local_entry = batadv_tt_local_hash_find(bat_priv, src); - if (!tt_local_entry) + if (!tt_local_entry || + (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING)) goto out; } @@ -1220,25 +1352,15 @@ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, _batadv_is_ap_isolated(tt_local_entry, tt_global_entry)) goto out; - best_tq = 0; - rcu_read_lock(); - head = &tt_global_entry->orig_list; - hlist_for_each_entry_rcu(orig_entry, node, head, list) { - router = batadv_orig_node_get_router(orig_entry->orig_node); - if (!router) - continue; - - if (router->tq_avg > best_tq) { - orig_node = orig_entry->orig_node; - best_tq = router->tq_avg; - } - batadv_neigh_node_free_ref(router); - } + best_entry = batadv_transtable_best_orig(tt_global_entry); /* found anything? */ + if (best_entry) + orig_node = best_entry->orig_node; if (orig_node && !atomic_inc_not_zero(&orig_node->refcount)) orig_node = NULL; rcu_read_unlock(); + out: if (tt_global_entry) batadv_tt_global_entry_free_ref(tt_global_entry); @@ -1471,11 +1593,11 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, tt_tot = tt_len / sizeof(struct batadv_tt_change); len = tt_query_size + tt_len; - skb = dev_alloc_skb(len + ETH_HLEN); + skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); if (!skb) goto out; - skb_reserve(skb, ETH_HLEN); + skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); tt_response = (struct batadv_tt_query_packet *)skb_put(skb, len); tt_response->ttvn = ttvn; @@ -1496,7 +1618,7 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, memcpy(tt_change->addr, tt_common_entry->addr, ETH_ALEN); - tt_change->flags = BATADV_NO_FLAGS; + tt_change->flags = tt_common_entry->flags; tt_count++; tt_change++; @@ -1520,7 +1642,6 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv, { struct sk_buff *skb = NULL; struct batadv_tt_query_packet *tt_request; - struct batadv_neigh_node *neigh_node = NULL; struct batadv_hard_iface *primary_if; struct batadv_tt_req_node *tt_req_node = NULL; int ret = 1; @@ -1537,11 +1658,11 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv, if (!tt_req_node) goto out; - skb = dev_alloc_skb(sizeof(*tt_request) + ETH_HLEN); + skb = dev_alloc_skb(sizeof(*tt_request) + ETH_HLEN + NET_IP_ALIGN); if (!skb) goto out; - skb_reserve(skb, ETH_HLEN); + skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); tt_req_len = sizeof(*tt_request); tt_request = (struct batadv_tt_query_packet *)skb_put(skb, tt_req_len); @@ -1558,23 +1679,15 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv, if (full_table) tt_request->flags |= BATADV_TT_FULL_TABLE; - neigh_node = batadv_orig_node_get_router(dst_orig_node); - if (!neigh_node) - goto out; - - batadv_dbg(BATADV_DBG_TT, bat_priv, - "Sending TT_REQUEST to %pM via %pM [%c]\n", - dst_orig_node->orig, neigh_node->addr, - (full_table ? 'F' : '.')); + batadv_dbg(BATADV_DBG_TT, bat_priv, "Sending TT_REQUEST to %pM [%c]\n", + dst_orig_node->orig, (full_table ? 'F' : '.')); batadv_inc_counter(bat_priv, BATADV_CNT_TT_REQUEST_TX); - batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - ret = 0; + if (batadv_send_skb_to_orig(skb, dst_orig_node, NULL)) + ret = 0; out: - if (neigh_node) - batadv_neigh_node_free_ref(neigh_node); if (primary_if) batadv_hardif_free_ref(primary_if); if (ret) @@ -1592,9 +1705,8 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, struct batadv_tt_query_packet *tt_request) { - struct batadv_orig_node *req_dst_orig_node = NULL; + struct batadv_orig_node *req_dst_orig_node; struct batadv_orig_node *res_dst_orig_node = NULL; - struct batadv_neigh_node *neigh_node = NULL; struct batadv_hard_iface *primary_if = NULL; uint8_t orig_ttvn, req_ttvn, ttvn; int ret = false; @@ -1620,10 +1732,6 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv, if (!res_dst_orig_node) goto out; - neigh_node = batadv_orig_node_get_router(res_dst_orig_node); - if (!neigh_node) - goto out; - primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; @@ -1652,11 +1760,11 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv, tt_tot = tt_len / sizeof(struct batadv_tt_change); len = sizeof(*tt_response) + tt_len; - skb = dev_alloc_skb(len + ETH_HLEN); + skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); if (!skb) goto unlock; - skb_reserve(skb, ETH_HLEN); + skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); packet_pos = skb_put(skb, len); tt_response = (struct batadv_tt_query_packet *)packet_pos; tt_response->ttvn = req_ttvn; @@ -1695,14 +1803,13 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv, tt_response->flags |= BATADV_TT_FULL_TABLE; batadv_dbg(BATADV_DBG_TT, bat_priv, - "Sending TT_RESPONSE %pM via %pM for %pM (ttvn: %u)\n", - res_dst_orig_node->orig, neigh_node->addr, - req_dst_orig_node->orig, req_ttvn); + "Sending TT_RESPONSE %pM for %pM (ttvn: %u)\n", + res_dst_orig_node->orig, req_dst_orig_node->orig, req_ttvn); batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); - batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - ret = true; + if (batadv_send_skb_to_orig(skb, res_dst_orig_node, NULL)) + ret = true; goto out; unlock: @@ -1713,8 +1820,6 @@ out: batadv_orig_node_free_ref(res_dst_orig_node); if (req_dst_orig_node) batadv_orig_node_free_ref(req_dst_orig_node); - if (neigh_node) - batadv_neigh_node_free_ref(neigh_node); if (primary_if) batadv_hardif_free_ref(primary_if); if (!ret) @@ -1727,8 +1832,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, struct batadv_tt_query_packet *tt_request) { - struct batadv_orig_node *orig_node = NULL; - struct batadv_neigh_node *neigh_node = NULL; + struct batadv_orig_node *orig_node; struct batadv_hard_iface *primary_if = NULL; uint8_t my_ttvn, req_ttvn, ttvn; int ret = false; @@ -1753,10 +1857,6 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv, if (!orig_node) goto out; - neigh_node = batadv_orig_node_get_router(orig_node); - if (!neigh_node) - goto out; - primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; @@ -1779,11 +1879,11 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv, tt_tot = tt_len / sizeof(struct batadv_tt_change); len = sizeof(*tt_response) + tt_len; - skb = dev_alloc_skb(len + ETH_HLEN); + skb = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); if (!skb) goto unlock; - skb_reserve(skb, ETH_HLEN); + skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); packet_pos = skb_put(skb, len); tt_response = (struct batadv_tt_query_packet *)packet_pos; tt_response->ttvn = req_ttvn; @@ -1820,14 +1920,14 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv, tt_response->flags |= BATADV_TT_FULL_TABLE; batadv_dbg(BATADV_DBG_TT, bat_priv, - "Sending TT_RESPONSE to %pM via %pM [%c]\n", - orig_node->orig, neigh_node->addr, + "Sending TT_RESPONSE to %pM [%c]\n", + orig_node->orig, (tt_response->flags & BATADV_TT_FULL_TABLE ? 'F' : '.')); batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_TX); - batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - ret = true; + if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + ret = true; goto out; unlock: @@ -1835,8 +1935,6 @@ unlock: out: if (orig_node) batadv_orig_node_free_ref(orig_node); - if (neigh_node) - batadv_neigh_node_free_ref(neigh_node); if (primary_if) batadv_hardif_free_ref(primary_if); if (!ret) @@ -1893,7 +1991,7 @@ static void _batadv_tt_update_changes(struct batadv_priv *bat_priv, static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv, struct batadv_tt_query_packet *tt_response) { - struct batadv_orig_node *orig_node = NULL; + struct batadv_orig_node *orig_node; orig_node = batadv_orig_hash_find(bat_priv, tt_response->src); if (!orig_node) @@ -1935,7 +2033,7 @@ static void batadv_tt_update_changes(struct batadv_priv *bat_priv, bool batadv_is_my_client(struct batadv_priv *bat_priv, const uint8_t *addr) { - struct batadv_tt_local_entry *tt_local_entry = NULL; + struct batadv_tt_local_entry *tt_local_entry; bool ret = false; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr); @@ -1944,7 +2042,8 @@ bool batadv_is_my_client(struct batadv_priv *bat_priv, const uint8_t *addr) /* Check if the client has been logically deleted (but is kept for * consistency purpose) */ - if (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING) + if ((tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING) || + (tt_local_entry->common.flags & BATADV_TT_CLIENT_ROAM)) goto out; ret = true; out: @@ -1995,10 +2094,6 @@ void batadv_handle_tt_response(struct batadv_priv *bat_priv, /* Recalculate the CRC for this orig_node and store it */ orig_node->tt_crc = batadv_tt_global_crc(bat_priv, orig_node); - /* Roaming phase is over: tables are in sync again. I can - * unset the flag - */ - orig_node->tt_poss_change = false; out: if (orig_node) batadv_orig_node_free_ref(orig_node); @@ -2104,7 +2199,6 @@ unlock: static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, struct batadv_orig_node *orig_node) { - struct batadv_neigh_node *neigh_node = NULL; struct sk_buff *skb = NULL; struct batadv_roam_adv_packet *roam_adv_packet; int ret = 1; @@ -2117,11 +2211,11 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, if (!batadv_tt_check_roam_count(bat_priv, client)) goto out; - skb = dev_alloc_skb(sizeof(*roam_adv_packet) + ETH_HLEN); + skb = dev_alloc_skb(sizeof(*roam_adv_packet) + ETH_HLEN + NET_IP_ALIGN); if (!skb) goto out; - skb_reserve(skb, ETH_HLEN); + skb_reserve(skb, ETH_HLEN + NET_IP_ALIGN); roam_adv_packet = (struct batadv_roam_adv_packet *)skb_put(skb, len); @@ -2137,23 +2231,17 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, memcpy(roam_adv_packet->dst, orig_node->orig, ETH_ALEN); memcpy(roam_adv_packet->client, client, ETH_ALEN); - neigh_node = batadv_orig_node_get_router(orig_node); - if (!neigh_node) - goto out; - batadv_dbg(BATADV_DBG_TT, bat_priv, - "Sending ROAMING_ADV to %pM (client %pM) via %pM\n", - orig_node->orig, client, neigh_node->addr); + "Sending ROAMING_ADV to %pM (client %pM)\n", + orig_node->orig, client); batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_TX); - batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - ret = 0; + if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + ret = 0; out: - if (neigh_node) - batadv_neigh_node_free_ref(neigh_node); - if (ret) + if (ret && skb) kfree_skb(skb); return; } @@ -2289,7 +2377,6 @@ static int batadv_tt_commit_changes(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_TT, bat_priv, "Local changes committed, updating to ttvn %u\n", (uint8_t)atomic_read(&bat_priv->tt.vn)); - bat_priv->tt.poss_change = false; /* reset the sending counter */ atomic_set(&bat_priv->tt.ogm_append_cnt, BATADV_TT_OGM_APPEND_MAX); @@ -2401,11 +2488,6 @@ void batadv_tt_update_orig(struct batadv_priv *bat_priv, */ if (orig_node->tt_crc != tt_crc) goto request_table; - - /* Roaming phase is over: tables are in sync again. I can - * unset the flag - */ - orig_node->tt_poss_change = false; } else { /* if we missed more than one change or our tables are not * in sync anymore -> request fresh tt data @@ -2438,18 +2520,51 @@ bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, if (!tt_global_entry) goto out; - ret = tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM; + ret = !!(tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM); batadv_tt_global_entry_free_ref(tt_global_entry); out: return ret; } +/** + * batadv_tt_local_client_is_roaming - tells whether the client is roaming + * @bat_priv: the bat priv with all the soft interface information + * @addr: the MAC address of the local client to query + * + * Returns true if the local client is known to be roaming (it is not served by + * this node anymore) or not. If yes, the client is still present in the table + * to keep the latter consistent with the node TTVN + */ +bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, + uint8_t *addr) +{ + struct batadv_tt_local_entry *tt_local_entry; + bool ret = false; + + tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr); + if (!tt_local_entry) + goto out; + + ret = tt_local_entry->common.flags & BATADV_TT_CLIENT_ROAM; + batadv_tt_local_entry_free_ref(tt_local_entry); +out: + return ret; + +} + bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr) { bool ret = false; + /* if the originator is a backbone node (meaning it belongs to the same + * LAN of this node) the temporary client must not be added because to + * reach such destination the node must use the LAN instead of the mesh + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig)) + goto out; + if (!batadv_tt_global_add(bat_priv, orig_node, addr, BATADV_TT_CLIENT_TEMP, atomic_read(&orig_node->last_ttvn))) diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 811fffd4760c..46d4451a59ee 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -24,9 +24,9 @@ int batadv_tt_len(int changes_num); int batadv_tt_init(struct batadv_priv *bat_priv); void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, int ifindex); -void batadv_tt_local_remove(struct batadv_priv *bat_priv, - const uint8_t *addr, const char *message, - bool roaming); +uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, + const uint8_t *addr, const char *message, + bool roaming); int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset); void batadv_tt_global_add_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, @@ -59,6 +59,8 @@ int batadv_tt_append_diff(struct batadv_priv *bat_priv, int packet_min_len); bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, uint8_t *addr); +bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, + uint8_t *addr); bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ac1e07a80454..ae9ac9aca8c5 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -28,20 +28,41 @@ (ETH_HLEN + max(sizeof(struct batadv_unicast_packet), \ sizeof(struct batadv_bcast_packet))) +#ifdef CONFIG_BATMAN_ADV_DAT + +/* batadv_dat_addr_t is the type used for all DHT addresses. If it is changed, + * BATADV_DAT_ADDR_MAX is changed as well. + * + * *Please be careful: batadv_dat_addr_t must be UNSIGNED* + */ +#define batadv_dat_addr_t uint16_t + +#endif /* CONFIG_BATMAN_ADV_DAT */ + +/** + * struct batadv_hard_iface_bat_iv - per hard interface B.A.T.M.A.N. IV data + * @ogm_buff: buffer holding the OGM packet + * @ogm_buff_len: length of the OGM packet buffer + * @ogm_seqno: OGM sequence number - used to identify each OGM + */ +struct batadv_hard_iface_bat_iv { + unsigned char *ogm_buff; + int ogm_buff_len; + atomic_t ogm_seqno; +}; + struct batadv_hard_iface { struct list_head list; int16_t if_num; char if_status; struct net_device *net_dev; - atomic_t seqno; atomic_t frag_seqno; - unsigned char *packet_buff; - int packet_len; struct kobject *hardif_obj; atomic_t refcount; struct packet_type batman_adv_ptype; struct net_device *soft_iface; struct rcu_head rcu; + struct batadv_hard_iface_bat_iv bat_iv; }; /** @@ -63,6 +84,9 @@ struct batadv_orig_node { uint8_t orig[ETH_ALEN]; uint8_t primary_addr[ETH_ALEN]; struct batadv_neigh_node __rcu *router; /* rcu protected pointer */ +#ifdef CONFIG_BATMAN_ADV_DAT + batadv_dat_addr_t dat_addr; +#endif unsigned long *bcast_own; uint8_t *bcast_own_sum; unsigned long last_seen; @@ -77,13 +101,6 @@ struct batadv_orig_node { spinlock_t tt_buff_lock; /* protects tt_buff */ atomic_t tt_size; bool tt_initialised; - /* The tt_poss_change flag is used to detect an ongoing roaming phase. - * If true, then I sent a Roaming_adv to this orig_node and I have to - * inspect every packet directed to it to check whether it is still - * the true destination or not. This flag will be reset to false as - * soon as I receive a new TTVN from this orig_node - */ - bool tt_poss_change; uint32_t last_real_seqno; uint8_t last_ttl; DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); @@ -139,7 +156,7 @@ struct batadv_neigh_node { #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_bcast_duplist_entry { uint8_t orig[ETH_ALEN]; - uint16_t crc; + __be32 crc; unsigned long entrytime; }; #endif @@ -162,6 +179,13 @@ enum batadv_counters { BATADV_CNT_TT_RESPONSE_RX, BATADV_CNT_TT_ROAM_ADV_TX, BATADV_CNT_TT_ROAM_ADV_RX, +#ifdef CONFIG_BATMAN_ADV_DAT + BATADV_CNT_DAT_GET_TX, + BATADV_CNT_DAT_GET_RX, + BATADV_CNT_DAT_PUT_TX, + BATADV_CNT_DAT_PUT_RX, + BATADV_CNT_DAT_CACHED_REPLY_TX, +#endif BATADV_CNT_NUM, }; @@ -181,7 +205,6 @@ struct batadv_priv_tt { atomic_t vn; atomic_t ogm_append_cnt; atomic_t local_changes; - bool poss_change; struct list_head changes_list; struct batadv_hashtable *local_hash; struct batadv_hashtable *global_hash; @@ -228,6 +251,20 @@ struct batadv_priv_vis { struct batadv_vis_info *my_info; }; +/** + * struct batadv_priv_dat - per mesh interface DAT private data + * @addr: node DAT address + * @hash: hashtable representing the local ARP cache + * @work: work queue callback item for cache purging + */ +#ifdef CONFIG_BATMAN_ADV_DAT +struct batadv_priv_dat { + batadv_dat_addr_t addr; + struct batadv_hashtable *hash; + struct delayed_work work; +}; +#endif + struct batadv_priv { atomic_t mesh_state; struct net_device_stats stats; @@ -237,6 +274,9 @@ struct batadv_priv { atomic_t fragmentation; /* boolean */ atomic_t ap_isolation; /* boolean */ atomic_t bridge_loop_avoidance; /* boolean */ +#ifdef CONFIG_BATMAN_ADV_DAT + atomic_t distributed_arp_table; /* boolean */ +#endif atomic_t vis_mode; /* VIS_TYPE_* */ atomic_t gw_mode; /* GW_MODE_* */ atomic_t gw_sel_class; /* uint */ @@ -255,7 +295,7 @@ struct batadv_priv { struct hlist_head forw_bcast_list; struct batadv_hashtable *orig_hash; spinlock_t forw_bat_list_lock; /* protects forw_bat_list */ - spinlock_t forw_bcast_list_lock; /* protects */ + spinlock_t forw_bcast_list_lock; /* protects forw_bcast_list */ struct delayed_work orig_work; struct batadv_hard_iface __rcu *primary_if; /* rcu protected pointer */ struct batadv_algo_ops *bat_algo_ops; @@ -265,6 +305,9 @@ struct batadv_priv { struct batadv_priv_gw gw; struct batadv_priv_tt tt; struct batadv_priv_vis vis; +#ifdef CONFIG_BATMAN_ADV_DAT + struct batadv_priv_dat dat; +#endif }; struct batadv_socket_client { @@ -318,6 +361,7 @@ struct batadv_backbone_gw { struct hlist_node hash_entry; struct batadv_priv *bat_priv; unsigned long lasttime; /* last time we heard of this backbone gw */ + atomic_t wait_periods; atomic_t request_sent; atomic_t refcount; struct rcu_head rcu; @@ -437,4 +481,36 @@ struct batadv_algo_ops { void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); }; +/** + * struct batadv_dat_entry - it is a single entry of batman-adv ARP backend. It + * is used to stored ARP entries needed for the global DAT cache + * @ip: the IPv4 corresponding to this DAT/ARP entry + * @mac_addr: the MAC address associated to the stored IPv4 + * @last_update: time in jiffies when this entry was refreshed last time + * @hash_entry: hlist node for batadv_priv_dat::hash + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ +struct batadv_dat_entry { + __be32 ip; + uint8_t mac_addr[ETH_ALEN]; + unsigned long last_update; + struct hlist_node hash_entry; + atomic_t refcount; + struct rcu_head rcu; +}; + +/** + * struct batadv_dat_candidate - candidate destination for DAT operations + * @type: the type of the selected candidate. It can one of the following: + * - BATADV_DAT_CANDIDATE_NOT_FOUND + * - BATADV_DAT_CANDIDATE_ORIG + * @orig_node: if type is BATADV_DAT_CANDIDATE_ORIG this field points to the + * corresponding originator node structure + */ +struct batadv_dat_candidate { + int type; + struct batadv_orig_node *orig_node; +}; + #endif /* _NET_BATMAN_ADV_TYPES_H_ */ diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index f39723281ca1..10aff49fcf25 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -291,14 +291,118 @@ out: return ret; } -int batadv_unicast_send_skb(struct sk_buff *skb, struct batadv_priv *bat_priv) +/** + * batadv_unicast_push_and_fill_skb - extends the buffer and initializes the + * common fields for unicast packets + * @skb: packet + * @hdr_size: amount of bytes to push at the beginning of the skb + * @orig_node: the destination node + * + * Returns false if the buffer extension was not possible or true otherwise + */ +static bool batadv_unicast_push_and_fill_skb(struct sk_buff *skb, int hdr_size, + struct batadv_orig_node *orig_node) +{ + struct batadv_unicast_packet *unicast_packet; + uint8_t ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + + if (batadv_skb_head_push(skb, hdr_size) < 0) + return false; + + unicast_packet = (struct batadv_unicast_packet *)skb->data; + unicast_packet->header.version = BATADV_COMPAT_VERSION; + /* batman packet type: unicast */ + unicast_packet->header.packet_type = BATADV_UNICAST; + /* set unicast ttl */ + unicast_packet->header.ttl = BATADV_TTL; + /* copy the destination for faster routing */ + memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN); + /* set the destination tt version number */ + unicast_packet->ttvn = ttvn; + + return true; +} + +/** + * batadv_unicast_prepare_skb - encapsulate an skb with a unicast header + * @skb: the skb containing the payload to encapsulate + * @orig_node: the destination node + * + * Returns false if the payload could not be encapsulated or true otherwise + */ +static bool batadv_unicast_prepare_skb(struct sk_buff *skb, + struct batadv_orig_node *orig_node) +{ + size_t uni_size = sizeof(struct batadv_unicast_packet); + return batadv_unicast_push_and_fill_skb(skb, uni_size, orig_node); +} + +/** + * batadv_unicast_4addr_prepare_skb - encapsulate an skb with a unicast4addr + * header + * @bat_priv: the bat priv with all the soft interface information + * @skb: the skb containing the payload to encapsulate + * @orig_node: the destination node + * @packet_subtype: the batman 4addr packet subtype to use + * + * Returns false if the payload could not be encapsulated or true otherwise + */ +bool batadv_unicast_4addr_prepare_skb(struct batadv_priv *bat_priv, + struct sk_buff *skb, + struct batadv_orig_node *orig, + int packet_subtype) +{ + struct batadv_hard_iface *primary_if; + struct batadv_unicast_4addr_packet *unicast_4addr_packet; + bool ret = false; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + /* pull the header space and fill the unicast_packet substructure. + * We can do that because the first member of the unicast_4addr_packet + * is of type struct unicast_packet + */ + if (!batadv_unicast_push_and_fill_skb(skb, + sizeof(*unicast_4addr_packet), + orig)) + goto out; + + unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; + unicast_4addr_packet->u.header.packet_type = BATADV_UNICAST_4ADDR; + memcpy(unicast_4addr_packet->src, primary_if->net_dev->dev_addr, + ETH_ALEN); + unicast_4addr_packet->subtype = packet_subtype; + unicast_4addr_packet->reserved = 0; + + ret = true; +out: + if (primary_if) + batadv_hardif_free_ref(primary_if); + return ret; +} + +/** + * batadv_unicast_generic_send_skb - send an skb as unicast + * @bat_priv: the bat priv with all the soft interface information + * @skb: payload to send + * @packet_type: the batman unicast packet type to use + * @packet_subtype: the batman packet subtype. It is ignored if packet_type is + * not BATADV_UNICAT_4ADDR + * + * Returns 1 in case of error or 0 otherwise + */ +int batadv_unicast_generic_send_skb(struct batadv_priv *bat_priv, + struct sk_buff *skb, int packet_type, + int packet_subtype) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_unicast_packet *unicast_packet; struct batadv_orig_node *orig_node; struct batadv_neigh_node *neigh_node; int data_len = skb->len; - int ret = 1; + int ret = NET_RX_DROP; unsigned int dev_mtu; /* get routing information */ @@ -324,21 +428,23 @@ find_router: if (!neigh_node) goto out; - if (batadv_skb_head_push(skb, sizeof(*unicast_packet)) < 0) + switch (packet_type) { + case BATADV_UNICAST: + batadv_unicast_prepare_skb(skb, orig_node); + break; + case BATADV_UNICAST_4ADDR: + batadv_unicast_4addr_prepare_skb(bat_priv, skb, orig_node, + packet_subtype); + break; + default: + /* this function supports UNICAST and UNICAST_4ADDR only. It + * should never be invoked with any other packet type + */ goto out; + } unicast_packet = (struct batadv_unicast_packet *)skb->data; - unicast_packet->header.version = BATADV_COMPAT_VERSION; - /* batman packet type: unicast */ - unicast_packet->header.packet_type = BATADV_UNICAST; - /* set unicast ttl */ - unicast_packet->header.ttl = BATADV_TTL; - /* copy the destination for faster routing */ - memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN); - /* set the destination tt version number */ - unicast_packet->ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); - /* inform the destination node that we are still missing a correct route * for this client. The destination will receive this packet and will * try to reroute it because the ttvn contained in the header is less @@ -348,7 +454,9 @@ find_router: unicast_packet->ttvn = unicast_packet->ttvn - 1; dev_mtu = neigh_node->if_incoming->net_dev->mtu; - if (atomic_read(&bat_priv->fragmentation) && + /* fragmentation mechanism only works for UNICAST (now) */ + if (packet_type == BATADV_UNICAST && + atomic_read(&bat_priv->fragmentation) && data_len + sizeof(*unicast_packet) > dev_mtu) { /* send frag skb decreases ttl */ unicast_packet->header.ttl++; @@ -358,16 +466,15 @@ find_router: goto out; } - batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); - ret = 0; - goto out; + if (batadv_send_skb_to_orig(skb, orig_node, NULL)) + ret = 0; out: if (neigh_node) batadv_neigh_node_free_ref(neigh_node); if (orig_node) batadv_orig_node_free_ref(orig_node); - if (ret == 1) + if (ret == NET_RX_DROP) kfree_skb(skb); return ret; } diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index 1c46e2eb1ef9..61abba58bd8f 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -29,10 +29,44 @@ int batadv_frag_reassemble_skb(struct sk_buff *skb, struct batadv_priv *bat_priv, struct sk_buff **new_skb); void batadv_frag_list_free(struct list_head *head); -int batadv_unicast_send_skb(struct sk_buff *skb, struct batadv_priv *bat_priv); int batadv_frag_send_skb(struct sk_buff *skb, struct batadv_priv *bat_priv, struct batadv_hard_iface *hard_iface, const uint8_t dstaddr[]); +bool batadv_unicast_4addr_prepare_skb(struct batadv_priv *bat_priv, + struct sk_buff *skb, + struct batadv_orig_node *orig_node, + int packet_subtype); +int batadv_unicast_generic_send_skb(struct batadv_priv *bat_priv, + struct sk_buff *skb, int packet_type, + int packet_subtype); + + +/** + * batadv_unicast_send_skb - send the skb encapsulated in a unicast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: the payload to send + */ +static inline int batadv_unicast_send_skb(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return batadv_unicast_generic_send_skb(bat_priv, skb, BATADV_UNICAST, + 0); +} + +/** + * batadv_unicast_send_skb - send the skb encapsulated in a unicast4addr packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: the payload to send + * @packet_subtype: the batman 4addr packet subtype to use + */ +static inline int batadv_unicast_4addr_send_skb(struct batadv_priv *bat_priv, + struct sk_buff *skb, + int packet_subtype) +{ + return batadv_unicast_generic_send_skb(bat_priv, skb, + BATADV_UNICAST_4ADDR, + packet_subtype); +} static inline int batadv_frag_can_reassemble(const struct sk_buff *skb, int mtu) { diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 5abd1454fb07..0f65a9de5f74 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -396,12 +396,12 @@ batadv_add_packet(struct batadv_priv *bat_priv, return NULL; len = sizeof(*packet) + vis_info_len; - info->skb_packet = dev_alloc_skb(len + ETH_HLEN); + info->skb_packet = dev_alloc_skb(len + ETH_HLEN + NET_IP_ALIGN); if (!info->skb_packet) { kfree(info); return NULL; } - skb_reserve(info->skb_packet, ETH_HLEN); + skb_reserve(info->skb_packet, ETH_HLEN + NET_IP_ALIGN); packet = (struct batadv_vis_packet *)skb_put(info->skb_packet, len); kref_init(&info->refcount); @@ -698,15 +698,12 @@ static void batadv_purge_vis_packets(struct batadv_priv *bat_priv) static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, struct batadv_vis_info *info) { - struct batadv_neigh_node *router; struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; struct batadv_vis_packet *packet; struct sk_buff *skb; - struct batadv_hard_iface *hard_iface; - uint8_t dstaddr[ETH_ALEN]; uint32_t i; @@ -722,30 +719,20 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, if (!(orig_node->flags & BATADV_VIS_SERVER)) continue; - router = batadv_orig_node_get_router(orig_node); - if (!router) - continue; - /* don't send it if we already received the packet from * this node. */ if (batadv_recv_list_is_in(bat_priv, &info->recv_list, - orig_node->orig)) { - batadv_neigh_node_free_ref(router); + orig_node->orig)) continue; - } memcpy(packet->target_orig, orig_node->orig, ETH_ALEN); - hard_iface = router->if_incoming; - memcpy(dstaddr, router->addr, ETH_ALEN); - - batadv_neigh_node_free_ref(router); - skb = skb_clone(info->skb_packet, GFP_ATOMIC); - if (skb) - batadv_send_skb_packet(skb, hard_iface, - dstaddr); + if (!skb) + continue; + if (!batadv_send_skb_to_orig(skb, orig_node, NULL)) + kfree_skb(skb); } rcu_read_unlock(); } @@ -755,7 +742,6 @@ static void batadv_unicast_vis_packet(struct batadv_priv *bat_priv, struct batadv_vis_info *info) { struct batadv_orig_node *orig_node; - struct batadv_neigh_node *router = NULL; struct sk_buff *skb; struct batadv_vis_packet *packet; @@ -765,17 +751,14 @@ static void batadv_unicast_vis_packet(struct batadv_priv *bat_priv, if (!orig_node) goto out; - router = batadv_orig_node_get_router(orig_node); - if (!router) + skb = skb_clone(info->skb_packet, GFP_ATOMIC); + if (!skb) goto out; - skb = skb_clone(info->skb_packet, GFP_ATOMIC); - if (skb) - batadv_send_skb_packet(skb, router->if_incoming, router->addr); + if (!batadv_send_skb_to_orig(skb, orig_node, NULL)) + kfree_skb(skb); out: - if (router) - batadv_neigh_node_free_ref(router); if (orig_node) batadv_orig_node_free_ref(orig_node); } @@ -873,12 +856,13 @@ int batadv_vis_init(struct batadv_priv *bat_priv) if (!bat_priv->vis.my_info) goto err; - len = sizeof(*packet) + BATADV_MAX_VIS_PACKET_SIZE + ETH_HLEN; + len = sizeof(*packet) + BATADV_MAX_VIS_PACKET_SIZE; + len += ETH_HLEN + NET_IP_ALIGN; bat_priv->vis.my_info->skb_packet = dev_alloc_skb(len); if (!bat_priv->vis.my_info->skb_packet) goto free_info; - skb_reserve(bat_priv->vis.my_info->skb_packet, ETH_HLEN); + skb_reserve(bat_priv->vis.my_info->skb_packet, ETH_HLEN + NET_IP_ALIGN); tmp_skb = bat_priv->vis.my_info->skb_packet; packet = (struct batadv_vis_packet *)skb_put(tmp_skb, sizeof(*packet)); diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 3537d385035e..d3f3f7b1d32c 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -11,6 +11,7 @@ menuconfig BT select CRYPTO_BLKCIPHER select CRYPTO_AES select CRYPTO_ECB + select CRYPTO_SHA256 help Bluetooth is low-cost, low-power, short-range wireless technology. It was designed as a replacement for cables and other short-range @@ -47,4 +48,3 @@ source "net/bluetooth/cmtp/Kconfig" source "net/bluetooth/hidp/Kconfig" source "drivers/bluetooth/Kconfig" - diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index fa6d94a4602a..dea6a287daca 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -10,4 +10,4 @@ obj-$(CONFIG_BT_HIDP) += hidp/ bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \ - a2mp.o + a2mp.o amp.o diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 0760d1fed6f0..2f67d5ecc907 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -16,6 +16,11 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/a2mp.h> +#include <net/bluetooth/amp.h> + +/* Global AMP Manager list */ +LIST_HEAD(amp_mgr_list); +DEFINE_MUTEX(amp_mgr_list_lock); /* A2MP build & send command helper functions */ static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) @@ -37,8 +42,7 @@ static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) return cmd; } -static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, - void *data) +void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) { struct l2cap_chan *chan = mgr->a2mp_chan; struct a2mp_cmd *cmd; @@ -63,6 +67,14 @@ static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, kfree(cmd); } +u8 __next_ident(struct amp_mgr *mgr) +{ + if (++mgr->ident == 0) + mgr->ident = 1; + + return mgr->ident; +} + static inline void __a2mp_cl_bredr(struct a2mp_cl *cl) { cl->id = 0; @@ -161,6 +173,83 @@ static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb, return 0; } +static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_discov_rsp *rsp = (void *) skb->data; + u16 len = le16_to_cpu(hdr->len); + struct a2mp_cl *cl; + u16 ext_feat; + bool found = false; + + if (len < sizeof(*rsp)) + return -EINVAL; + + len -= sizeof(*rsp); + skb_pull(skb, sizeof(*rsp)); + + ext_feat = le16_to_cpu(rsp->ext_feat); + + BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(rsp->mtu), ext_feat); + + /* check that packet is not broken for now */ + while (ext_feat & A2MP_FEAT_EXT) { + if (len < sizeof(ext_feat)) + return -EINVAL; + + ext_feat = get_unaligned_le16(skb->data); + BT_DBG("efm 0x%4.4x", ext_feat); + len -= sizeof(ext_feat); + skb_pull(skb, sizeof(ext_feat)); + } + + cl = (void *) skb->data; + while (len >= sizeof(*cl)) { + BT_DBG("Remote AMP id %d type %d status %d", cl->id, cl->type, + cl->status); + + if (cl->id != HCI_BREDR_ID && cl->type == HCI_AMP) { + struct a2mp_info_req req; + + found = true; + req.id = cl->id; + a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr), + sizeof(req), &req); + } + + len -= sizeof(*cl); + cl = (void *) skb_pull(skb, sizeof(*cl)); + } + + /* Fall back to L2CAP init sequence */ + if (!found) { + struct l2cap_conn *conn = mgr->l2cap_conn; + struct l2cap_chan *chan; + + mutex_lock(&conn->chan_lock); + + list_for_each_entry(chan, &conn->chan_l, list) { + + BT_DBG("chan %p state %s", chan, + state_to_string(chan->state)); + + if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) + continue; + + l2cap_chan_lock(chan); + + if (chan->state == BT_CONNECT) + l2cap_send_conn_req(chan); + + l2cap_chan_unlock(chan); + } + + mutex_unlock(&conn->chan_lock); + } + + return 0; +} + static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { @@ -181,7 +270,6 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { struct a2mp_info_req *req = (void *) skb->data; - struct a2mp_info_rsp rsp; struct hci_dev *hdev; if (le16_to_cpu(hdr->len) < sizeof(*req)) @@ -189,53 +277,93 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("id %d", req->id); - rsp.id = req->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - hdev = hci_dev_get(req->id); - if (hdev && hdev->amp_type != HCI_BREDR) { - rsp.status = 0; - rsp.total_bw = cpu_to_le32(hdev->amp_total_bw); - rsp.max_bw = cpu_to_le32(hdev->amp_max_bw); - rsp.min_latency = cpu_to_le32(hdev->amp_min_latency); - rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap); - rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size); + if (!hdev || hdev->dev_type != HCI_AMP) { + struct a2mp_info_rsp rsp; + + rsp.id = req->id; + rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + + a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp), + &rsp); + + goto done; } + mgr->state = READ_LOC_AMP_INFO; + hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); + +done: if (hdev) hci_dev_put(hdev); - a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp), &rsp); - skb_pull(skb, sizeof(*req)); return 0; } +static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_info_rsp *rsp = (struct a2mp_info_rsp *) skb->data; + struct a2mp_amp_assoc_req req; + struct amp_ctrl *ctrl; + + if (le16_to_cpu(hdr->len) < sizeof(*rsp)) + return -EINVAL; + + BT_DBG("id %d status 0x%2.2x", rsp->id, rsp->status); + + if (rsp->status) + return -EINVAL; + + ctrl = amp_ctrl_add(mgr, rsp->id); + if (!ctrl) + return -ENOMEM; + + req.id = rsp->id; + a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req), + &req); + + skb_pull(skb, sizeof(*rsp)); + return 0; +} + static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { struct a2mp_amp_assoc_req *req = (void *) skb->data; struct hci_dev *hdev; + struct amp_mgr *tmp; if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; BT_DBG("id %d", req->id); + /* Make sure that other request is not processed */ + tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); + hdev = hci_dev_get(req->id); - if (!hdev || hdev->amp_type == HCI_BREDR) { + if (!hdev || hdev->amp_type == HCI_BREDR || tmp) { struct a2mp_amp_assoc_rsp rsp; rsp.id = req->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + + if (tmp) { + rsp.status = A2MP_STATUS_COLLISION_OCCURED; + amp_mgr_put(tmp); + } else { + rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + } a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, hdr->ident, sizeof(rsp), &rsp); - goto clean; + + goto done; } - /* Placeholder for HCI Read AMP Assoc */ + amp_read_loc_assoc(hdev, mgr); -clean: +done: if (hdev) hci_dev_put(hdev); @@ -243,6 +371,68 @@ clean: return 0; } +static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, + struct a2mp_cmd *hdr) +{ + struct a2mp_amp_assoc_rsp *rsp = (void *) skb->data; + u16 len = le16_to_cpu(hdr->len); + struct hci_dev *hdev; + struct amp_ctrl *ctrl; + struct hci_conn *hcon; + size_t assoc_len; + + if (len < sizeof(*rsp)) + return -EINVAL; + + assoc_len = len - sizeof(*rsp); + + BT_DBG("id %d status 0x%2.2x assoc len %zu", rsp->id, rsp->status, + assoc_len); + + if (rsp->status) + return -EINVAL; + + /* Save remote ASSOC data */ + ctrl = amp_ctrl_lookup(mgr, rsp->id); + if (ctrl) { + u8 *assoc; + + assoc = kzalloc(assoc_len, GFP_KERNEL); + if (!assoc) { + amp_ctrl_put(ctrl); + return -ENOMEM; + } + + memcpy(assoc, rsp->amp_assoc, assoc_len); + ctrl->assoc = assoc; + ctrl->assoc_len = assoc_len; + ctrl->assoc_rem_len = assoc_len; + ctrl->assoc_len_so_far = 0; + + amp_ctrl_put(ctrl); + } + + /* Create Phys Link */ + hdev = hci_dev_get(rsp->id); + if (!hdev) + return -EINVAL; + + hcon = phylink_add(hdev, mgr, rsp->id, true); + if (!hcon) + goto done; + + BT_DBG("Created hcon %p: loc:%d -> rem:%d", hcon, hdev->id, rsp->id); + + mgr->bredr_chan->remote_amp_id = rsp->id; + + amp_create_phylink(hdev, mgr, hcon); + +done: + hci_dev_put(hdev); + skb_pull(skb, len); + return 0; +} + static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { @@ -250,6 +440,8 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_physlink_rsp rsp; struct hci_dev *hdev; + struct hci_conn *hcon; + struct amp_ctrl *ctrl; if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; @@ -265,9 +457,43 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, goto send_rsp; } - /* TODO process physlink create */ + ctrl = amp_ctrl_lookup(mgr, rsp.remote_id); + if (!ctrl) { + ctrl = amp_ctrl_add(mgr, rsp.remote_id); + if (ctrl) { + amp_ctrl_get(ctrl); + } else { + rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; + goto send_rsp; + } + } - rsp.status = A2MP_STATUS_SUCCESS; + if (ctrl) { + size_t assoc_len = le16_to_cpu(hdr->len) - sizeof(*req); + u8 *assoc; + + assoc = kzalloc(assoc_len, GFP_KERNEL); + if (!assoc) { + amp_ctrl_put(ctrl); + return -ENOMEM; + } + + memcpy(assoc, req->amp_assoc, assoc_len); + ctrl->assoc = assoc; + ctrl->assoc_len = assoc_len; + ctrl->assoc_rem_len = assoc_len; + ctrl->assoc_len_so_far = 0; + + amp_ctrl_put(ctrl); + } + + hcon = phylink_add(hdev, mgr, req->local_id, false); + if (hcon) { + amp_accept_phylink(hdev, mgr, hcon); + rsp.status = A2MP_STATUS_SUCCESS; + } else { + rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; + } send_rsp: if (hdev) @@ -286,6 +512,7 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_physlink_req *req = (void *) skb->data; struct a2mp_physlink_rsp rsp; struct hci_dev *hdev; + struct hci_conn *hcon; if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; @@ -296,14 +523,22 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, rsp.remote_id = req->local_id; rsp.status = A2MP_STATUS_SUCCESS; - hdev = hci_dev_get(req->local_id); + hdev = hci_dev_get(req->remote_id); if (!hdev) { rsp.status = A2MP_STATUS_INVALID_CTRL_ID; goto send_rsp; } + hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, mgr->l2cap_conn->dst); + if (!hcon) { + BT_ERR("No phys link exist"); + rsp.status = A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS; + goto clean; + } + /* TODO Disconnect Phys Link here */ +clean: hci_dev_put(hdev); send_rsp: @@ -377,10 +612,19 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) err = a2mp_discphyslink_req(mgr, skb, hdr); break; - case A2MP_CHANGE_RSP: case A2MP_DISCOVER_RSP: + err = a2mp_discover_rsp(mgr, skb, hdr); + break; + case A2MP_GETINFO_RSP: + err = a2mp_getinfo_rsp(mgr, skb, hdr); + break; + case A2MP_GETAMPASSOC_RSP: + err = a2mp_getampassoc_rsp(mgr, skb, hdr); + break; + + case A2MP_CHANGE_RSP: case A2MP_CREATEPHYSLINK_RSP: case A2MP_DISCONNPHYSLINK_RSP: err = a2mp_cmd_rsp(mgr, skb, hdr); @@ -455,9 +699,10 @@ static struct l2cap_ops a2mp_chan_ops = { .new_connection = l2cap_chan_no_new_connection, .teardown = l2cap_chan_no_teardown, .ready = l2cap_chan_no_ready, + .defer = l2cap_chan_no_defer, }; -static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn) +static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) { struct l2cap_chan *chan; int err; @@ -492,7 +737,10 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn) chan->conf_state = 0; - l2cap_chan_add(conn, chan); + if (locked) + __l2cap_chan_add(conn, chan); + else + l2cap_chan_add(conn, chan); chan->remote_mps = chan->omtu; chan->mps = chan->omtu; @@ -503,11 +751,13 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn) } /* AMP Manager functions */ -void amp_mgr_get(struct amp_mgr *mgr) +struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr) { BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount)); kref_get(&mgr->kref); + + return mgr; } static void amp_mgr_destroy(struct kref *kref) @@ -516,6 +766,11 @@ static void amp_mgr_destroy(struct kref *kref) BT_DBG("mgr %p", mgr); + mutex_lock(&_mgr_list_lock); + list_del(&mgr->list); + mutex_unlock(&_mgr_list_lock); + + amp_ctrl_list_flush(mgr); kfree(mgr); } @@ -526,7 +781,7 @@ int amp_mgr_put(struct amp_mgr *mgr) return kref_put(&mgr->kref, &_mgr_destroy); } -static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn) +static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn, bool locked) { struct amp_mgr *mgr; struct l2cap_chan *chan; @@ -539,7 +794,7 @@ static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn) mgr->l2cap_conn = conn; - chan = a2mp_chan_open(conn); + chan = a2mp_chan_open(conn, locked); if (!chan) { kfree(mgr); return NULL; @@ -552,6 +807,14 @@ static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn) kref_init(&mgr->kref); + /* Remote AMP ctrl list initialization */ + INIT_LIST_HEAD(&mgr->amp_ctrls); + mutex_init(&mgr->amp_ctrls_lock); + + mutex_lock(&_mgr_list_lock); + list_add(&mgr->list, &_mgr_list); + mutex_unlock(&_mgr_list_lock); + return mgr; } @@ -560,7 +823,7 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, { struct amp_mgr *mgr; - mgr = amp_mgr_create(conn); + mgr = amp_mgr_create(conn, false); if (!mgr) { BT_ERR("Could not create AMP manager"); return NULL; @@ -570,3 +833,139 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, return mgr->a2mp_chan; } + +struct amp_mgr *amp_mgr_lookup_by_state(u8 state) +{ + struct amp_mgr *mgr; + + mutex_lock(&_mgr_list_lock); + list_for_each_entry(mgr, &_mgr_list, list) { + if (mgr->state == state) { + amp_mgr_get(mgr); + mutex_unlock(&_mgr_list_lock); + return mgr; + } + } + mutex_unlock(&_mgr_list_lock); + + return NULL; +} + +void a2mp_send_getinfo_rsp(struct hci_dev *hdev) +{ + struct amp_mgr *mgr; + struct a2mp_info_rsp rsp; + + mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_INFO); + if (!mgr) + return; + + BT_DBG("%s mgr %p", hdev->name, mgr); + + rsp.id = hdev->id; + rsp.status = A2MP_STATUS_INVALID_CTRL_ID; + + if (hdev->amp_type != HCI_BREDR) { + rsp.status = 0; + rsp.total_bw = cpu_to_le32(hdev->amp_total_bw); + rsp.max_bw = cpu_to_le32(hdev->amp_max_bw); + rsp.min_latency = cpu_to_le32(hdev->amp_min_latency); + rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap); + rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size); + } + + a2mp_send(mgr, A2MP_GETINFO_RSP, mgr->ident, sizeof(rsp), &rsp); + amp_mgr_put(mgr); +} + +void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status) +{ + struct amp_mgr *mgr; + struct amp_assoc *loc_assoc = &hdev->loc_assoc; + struct a2mp_amp_assoc_rsp *rsp; + size_t len; + + mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); + if (!mgr) + return; + + BT_DBG("%s mgr %p", hdev->name, mgr); + + len = sizeof(struct a2mp_amp_assoc_rsp) + loc_assoc->len; + rsp = kzalloc(len, GFP_KERNEL); + if (!rsp) { + amp_mgr_put(mgr); + return; + } + + rsp->id = hdev->id; + + if (status) { + rsp->status = A2MP_STATUS_INVALID_CTRL_ID; + } else { + rsp->status = A2MP_STATUS_SUCCESS; + memcpy(rsp->amp_assoc, loc_assoc->data, loc_assoc->len); + } + + a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, mgr->ident, len, rsp); + amp_mgr_put(mgr); + kfree(rsp); +} + +void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status) +{ + struct amp_mgr *mgr; + struct amp_assoc *loc_assoc = &hdev->loc_assoc; + struct a2mp_physlink_req *req; + struct l2cap_chan *bredr_chan; + size_t len; + + mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC_FINAL); + if (!mgr) + return; + + len = sizeof(*req) + loc_assoc->len; + + BT_DBG("%s mgr %p assoc_len %zu", hdev->name, mgr, len); + + req = kzalloc(len, GFP_KERNEL); + if (!req) { + amp_mgr_put(mgr); + return; + } + + bredr_chan = mgr->bredr_chan; + if (!bredr_chan) + goto clean; + + req->local_id = hdev->id; + req->remote_id = bredr_chan->remote_amp_id; + memcpy(req->amp_assoc, loc_assoc->data, loc_assoc->len); + + a2mp_send(mgr, A2MP_CREATEPHYSLINK_REQ, __next_ident(mgr), len, req); + +clean: + amp_mgr_put(mgr); + kfree(req); +} + +void a2mp_discover_amp(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + struct amp_mgr *mgr = conn->hcon->amp_mgr; + struct a2mp_discov_req req; + + BT_DBG("chan %p conn %p mgr %p", chan, conn, mgr); + + if (!mgr) { + mgr = amp_mgr_create(conn, true); + if (!mgr) + return; + } + + mgr->bredr_chan = chan; + + req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); + req.ext_feat = 0; + a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req); +} diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ba033f09196e..5355df63d39b 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -569,7 +569,6 @@ static int bt_seq_show(struct seq_file *seq, void *v) { struct bt_seq_state *s = seq->private; struct bt_sock_list *l = s->l; - bdaddr_t src_baswapped, dst_baswapped; if (v == SEQ_START_TOKEN) { seq_puts(seq ,"sk RefCnt Rmem Wmem User Inode Src Dst Parent"); @@ -583,18 +582,17 @@ static int bt_seq_show(struct seq_file *seq, void *v) } else { struct sock *sk = sk_entry(v); struct bt_sock *bt = bt_sk(sk); - baswap(&src_baswapped, &bt->src); - baswap(&dst_baswapped, &bt->dst); - seq_printf(seq, "%pK %-6d %-6u %-6u %-6u %-6lu %pM %pM %-6lu", + seq_printf(seq, + "%pK %-6d %-6u %-6u %-6u %-6lu %pMR %pMR %-6lu", sk, atomic_read(&sk->sk_refcnt), sk_rmem_alloc_get(sk), sk_wmem_alloc_get(sk), from_kuid(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), - &src_baswapped, - &dst_baswapped, + &bt->src, + &bt->dst, bt->parent? sock_i_ino(bt->parent): 0LU); if (l->custom_seq_show) { diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c new file mode 100644 index 000000000000..1b0d92c0643a --- /dev/null +++ b/net/bluetooth/amp.c @@ -0,0 +1,471 @@ +/* + Copyright (c) 2011,2012 Intel Corp. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License version 2 and + only version 2 as published by the Free Software Foundation. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. +*/ + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci.h> +#include <net/bluetooth/hci_core.h> +#include <net/bluetooth/a2mp.h> +#include <net/bluetooth/amp.h> +#include <crypto/hash.h> + +/* Remote AMP Controllers interface */ +void amp_ctrl_get(struct amp_ctrl *ctrl) +{ + BT_DBG("ctrl %p orig refcnt %d", ctrl, + atomic_read(&ctrl->kref.refcount)); + + kref_get(&ctrl->kref); +} + +static void amp_ctrl_destroy(struct kref *kref) +{ + struct amp_ctrl *ctrl = container_of(kref, struct amp_ctrl, kref); + + BT_DBG("ctrl %p", ctrl); + + kfree(ctrl->assoc); + kfree(ctrl); +} + +int amp_ctrl_put(struct amp_ctrl *ctrl) +{ + BT_DBG("ctrl %p orig refcnt %d", ctrl, + atomic_read(&ctrl->kref.refcount)); + + return kref_put(&ctrl->kref, &_ctrl_destroy); +} + +struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id) +{ + struct amp_ctrl *ctrl; + + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return NULL; + + kref_init(&ctrl->kref); + ctrl->id = id; + + mutex_lock(&mgr->amp_ctrls_lock); + list_add(&ctrl->list, &mgr->amp_ctrls); + mutex_unlock(&mgr->amp_ctrls_lock); + + BT_DBG("mgr %p ctrl %p", mgr, ctrl); + + return ctrl; +} + +void amp_ctrl_list_flush(struct amp_mgr *mgr) +{ + struct amp_ctrl *ctrl, *n; + + BT_DBG("mgr %p", mgr); + + mutex_lock(&mgr->amp_ctrls_lock); + list_for_each_entry_safe(ctrl, n, &mgr->amp_ctrls, list) { + list_del(&ctrl->list); + amp_ctrl_put(ctrl); + } + mutex_unlock(&mgr->amp_ctrls_lock); +} + +struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id) +{ + struct amp_ctrl *ctrl; + + BT_DBG("mgr %p id %d", mgr, id); + + mutex_lock(&mgr->amp_ctrls_lock); + list_for_each_entry(ctrl, &mgr->amp_ctrls, list) { + if (ctrl->id == id) { + amp_ctrl_get(ctrl); + mutex_unlock(&mgr->amp_ctrls_lock); + return ctrl; + } + } + mutex_unlock(&mgr->amp_ctrls_lock); + + return NULL; +} + +/* Physical Link interface */ +static u8 __next_handle(struct amp_mgr *mgr) +{ + if (++mgr->handle == 0) + mgr->handle = 1; + + return mgr->handle; +} + +struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, + u8 remote_id, bool out) +{ + bdaddr_t *dst = mgr->l2cap_conn->dst; + struct hci_conn *hcon; + + hcon = hci_conn_add(hdev, AMP_LINK, dst); + if (!hcon) + return NULL; + + BT_DBG("hcon %p dst %pMR", hcon, dst); + + hcon->state = BT_CONNECT; + hcon->attempt++; + hcon->handle = __next_handle(mgr); + hcon->remote_id = remote_id; + hcon->amp_mgr = amp_mgr_get(mgr); + hcon->out = out; + + return hcon; +} + +/* AMP crypto key generation interface */ +static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output) +{ + int ret = 0; + struct crypto_shash *tfm; + + if (!ksize) + return -EINVAL; + + tfm = crypto_alloc_shash("hmac(sha256)", 0, 0); + if (IS_ERR(tfm)) { + BT_DBG("crypto_alloc_ahash failed: err %ld", PTR_ERR(tfm)); + return PTR_ERR(tfm); + } + + ret = crypto_shash_setkey(tfm, key, ksize); + if (ret) { + BT_DBG("crypto_ahash_setkey failed: err %d", ret); + } else { + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(tfm)]; + } desc; + + desc.shash.tfm = tfm; + desc.shash.flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + ret = crypto_shash_digest(&desc.shash, plaintext, psize, + output); + } + + crypto_free_shash(tfm); + return ret; +} + +int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) +{ + struct hci_dev *hdev = conn->hdev; + struct link_key *key; + u8 keybuf[HCI_AMP_LINK_KEY_SIZE]; + u8 gamp_key[HCI_AMP_LINK_KEY_SIZE]; + int err; + + if (!hci_conn_check_link_mode(conn)) + return -EACCES; + + BT_DBG("conn %p key_type %d", conn, conn->key_type); + + /* Legacy key */ + if (conn->key_type < 3) { + BT_ERR("Legacy key type %d", conn->key_type); + return -EACCES; + } + + *type = conn->key_type; + *len = HCI_AMP_LINK_KEY_SIZE; + + key = hci_find_link_key(hdev, &conn->dst); + if (!key) { + BT_DBG("No Link key for conn %p dst %pMR", conn, &conn->dst); + return -EACCES; + } + + /* BR/EDR Link Key concatenated together with itself */ + memcpy(&keybuf[0], key->val, HCI_LINK_KEY_SIZE); + memcpy(&keybuf[HCI_LINK_KEY_SIZE], key->val, HCI_LINK_KEY_SIZE); + + /* Derive Generic AMP Link Key (gamp) */ + err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key); + if (err) { + BT_ERR("Could not derive Generic AMP Key: err %d", err); + return err; + } + + if (conn->key_type == HCI_LK_DEBUG_COMBINATION) { + BT_DBG("Use Generic AMP Key (gamp)"); + memcpy(data, gamp_key, HCI_AMP_LINK_KEY_SIZE); + return err; + } + + /* Derive Dedicated AMP Link Key: "802b" is 802.11 PAL keyID */ + return hmac_sha256(gamp_key, HCI_AMP_LINK_KEY_SIZE, "802b", 4, data); +} + +void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) +{ + struct hci_cp_read_local_amp_assoc cp; + struct amp_assoc *loc_assoc = &hdev->loc_assoc; + + BT_DBG("%s handle %d", hdev->name, phy_handle); + + cp.phy_handle = phy_handle; + cp.max_len = cpu_to_le16(hdev->amp_assoc_size); + cp.len_so_far = cpu_to_le16(loc_assoc->offset); + + hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); +} + +void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) +{ + struct hci_cp_read_local_amp_assoc cp; + + memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc)); + memset(&cp, 0, sizeof(cp)); + + cp.max_len = cpu_to_le16(hdev->amp_assoc_size); + + mgr->state = READ_LOC_AMP_ASSOC; + hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); +} + +void amp_read_loc_assoc_final_data(struct hci_dev *hdev, + struct hci_conn *hcon) +{ + struct hci_cp_read_local_amp_assoc cp; + struct amp_mgr *mgr = hcon->amp_mgr; + + cp.phy_handle = hcon->handle; + cp.len_so_far = cpu_to_le16(0); + cp.max_len = cpu_to_le16(hdev->amp_assoc_size); + + mgr->state = READ_LOC_AMP_ASSOC_FINAL; + + /* Read Local AMP Assoc final link information data */ + hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); +} + +/* Write AMP Assoc data fragments, returns true with last fragment written*/ +static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, + struct hci_conn *hcon) +{ + struct hci_cp_write_remote_amp_assoc *cp; + struct amp_mgr *mgr = hcon->amp_mgr; + struct amp_ctrl *ctrl; + u16 frag_len, len; + + ctrl = amp_ctrl_lookup(mgr, hcon->remote_id); + if (!ctrl) + return false; + + if (!ctrl->assoc_rem_len) { + BT_DBG("all fragments are written"); + ctrl->assoc_rem_len = ctrl->assoc_len; + ctrl->assoc_len_so_far = 0; + + amp_ctrl_put(ctrl); + return true; + } + + frag_len = min_t(u16, 248, ctrl->assoc_rem_len); + len = frag_len + sizeof(*cp); + + cp = kzalloc(len, GFP_KERNEL); + if (!cp) { + amp_ctrl_put(ctrl); + return false; + } + + BT_DBG("hcon %p ctrl %p frag_len %u assoc_len %u rem_len %u", + hcon, ctrl, frag_len, ctrl->assoc_len, ctrl->assoc_rem_len); + + cp->phy_handle = hcon->handle; + cp->len_so_far = cpu_to_le16(ctrl->assoc_len_so_far); + cp->rem_len = cpu_to_le16(ctrl->assoc_rem_len); + memcpy(cp->frag, ctrl->assoc, frag_len); + + ctrl->assoc_len_so_far += frag_len; + ctrl->assoc_rem_len -= frag_len; + + amp_ctrl_put(ctrl); + + hci_send_cmd(hdev, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp); + + kfree(cp); + + return false; +} + +void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle) +{ + struct hci_conn *hcon; + + BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); + + hcon = hci_conn_hash_lookup_handle(hdev, handle); + if (!hcon) + return; + + amp_write_rem_assoc_frag(hdev, hcon); +} + +void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle) +{ + struct hci_conn *hcon; + + BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); + + hcon = hci_conn_hash_lookup_handle(hdev, handle); + if (!hcon) + return; + + BT_DBG("%s phy handle 0x%2.2x hcon %p", hdev->name, handle, hcon); + + amp_write_rem_assoc_frag(hdev, hcon); +} + +void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, + struct hci_conn *hcon) +{ + struct hci_cp_create_phy_link cp; + + cp.phy_handle = hcon->handle; + + BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, + hcon->handle); + + if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, + &cp.key_type)) { + BT_DBG("Cannot create link key"); + return; + } + + hci_send_cmd(hdev, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); +} + +void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, + struct hci_conn *hcon) +{ + struct hci_cp_accept_phy_link cp; + + cp.phy_handle = hcon->handle; + + BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, + hcon->handle); + + if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, + &cp.key_type)) { + BT_DBG("Cannot create link key"); + return; + } + + hci_send_cmd(hdev, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); +} + +void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon) +{ + struct hci_dev *bredr_hdev = hci_dev_hold(bredr_hcon->hdev); + struct amp_mgr *mgr = hs_hcon->amp_mgr; + struct l2cap_chan *bredr_chan; + + BT_DBG("bredr_hcon %p hs_hcon %p mgr %p", bredr_hcon, hs_hcon, mgr); + + if (!bredr_hdev || !mgr || !mgr->bredr_chan) + return; + + bredr_chan = mgr->bredr_chan; + + l2cap_chan_lock(bredr_chan); + + set_bit(FLAG_EFS_ENABLE, &bredr_chan->flags); + bredr_chan->remote_amp_id = hs_hcon->remote_id; + bredr_chan->local_amp_id = hs_hcon->hdev->id; + bredr_chan->hs_hcon = hs_hcon; + bredr_chan->conn->mtu = hs_hcon->hdev->block_mtu; + + __l2cap_physical_cfm(bredr_chan, 0); + + l2cap_chan_unlock(bredr_chan); + + hci_dev_put(bredr_hdev); +} + +void amp_create_logical_link(struct l2cap_chan *chan) +{ + struct hci_cp_create_accept_logical_link cp; + struct hci_conn *hcon; + struct hci_dev *hdev; + + BT_DBG("chan %p", chan); + + if (!chan->hs_hcon) + return; + + hdev = hci_dev_hold(chan->hs_hcon->hdev); + if (!hdev) + return; + + BT_DBG("chan %p dst %pMR", chan, chan->conn->dst); + + hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, chan->conn->dst); + if (!hcon) + goto done; + + cp.phy_handle = hcon->handle; + + cp.tx_flow_spec.id = chan->local_id; + cp.tx_flow_spec.stype = chan->local_stype; + cp.tx_flow_spec.msdu = cpu_to_le16(chan->local_msdu); + cp.tx_flow_spec.sdu_itime = cpu_to_le32(chan->local_sdu_itime); + cp.tx_flow_spec.acc_lat = cpu_to_le32(chan->local_acc_lat); + cp.tx_flow_spec.flush_to = cpu_to_le32(chan->local_flush_to); + + cp.rx_flow_spec.id = chan->remote_id; + cp.rx_flow_spec.stype = chan->remote_stype; + cp.rx_flow_spec.msdu = cpu_to_le16(chan->remote_msdu); + cp.rx_flow_spec.sdu_itime = cpu_to_le32(chan->remote_sdu_itime); + cp.rx_flow_spec.acc_lat = cpu_to_le32(chan->remote_acc_lat); + cp.rx_flow_spec.flush_to = cpu_to_le32(chan->remote_flush_to); + + if (hcon->out) + hci_send_cmd(hdev, HCI_OP_CREATE_LOGICAL_LINK, sizeof(cp), + &cp); + else + hci_send_cmd(hdev, HCI_OP_ACCEPT_LOGICAL_LINK, sizeof(cp), + &cp); + +done: + hci_dev_put(hdev); +} + +void amp_disconnect_logical_link(struct hci_chan *hchan) +{ + struct hci_conn *hcon = hchan->conn; + struct hci_cp_disconn_logical_link cp; + + if (hcon->state != BT_CONNECTED) { + BT_DBG("hchan %p not connected", hchan); + return; + } + + cp.log_handle = cpu_to_le16(hchan->handle); + hci_send_cmd(hcon->hdev, HCI_OP_DISCONN_LOGICAL_LINK, sizeof(cp), &cp); +} + +void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason) +{ + BT_DBG("hchan %p", hchan); + + hci_chan_del(hchan); +} diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 4a6620bc1570..a5b639702637 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -182,8 +182,7 @@ static int bnep_ctrl_set_mcfilter(struct bnep_session *s, u8 *data, int len) a2 = data; data += ETH_ALEN; - BT_DBG("mc filter %s -> %s", - batostr((void *) a1), batostr((void *) a2)); + BT_DBG("mc filter %pMR -> %pMR", a1, a2); /* Iterate from a1 to a2 */ set_bit(bnep_mc_hash(a1), (ulong *) &s->mc_filter); diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 98f86f91d47c..e58c8b32589c 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -25,7 +25,6 @@ SOFTWARE IS DISCLAIMED. */ -#include <linux/export.h> #include <linux/etherdevice.h> #include <net/bluetooth/bluetooth.h> diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index 50f0d135eb8f..a4a9d4b6816c 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -20,7 +20,7 @@ SOFTWARE IS DISCLAIMED. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/types.h> diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 6c9c1fd601ca..e0a6ebf2baa6 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -353,7 +353,7 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) BT_DBG("mtu %d", session->mtu); - sprintf(session->name, "%s", batostr(&bt_sk(sock->sk)->dst)); + sprintf(session->name, "%pMR", &bt_sk(sock->sk)->dst); session->sock = sock; session->state = BT_CONFIG; diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c index aacb802d1ee4..1c57482112b6 100644 --- a/net/bluetooth/cmtp/sock.c +++ b/net/bluetooth/cmtp/sock.c @@ -20,7 +20,7 @@ SOFTWARE IS DISCLAIMED. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/types.h> #include <linux/capability.h> diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index b9196a44f759..25bfce0666eb 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -130,6 +130,20 @@ void hci_acl_disconn(struct hci_conn *conn, __u8 reason) hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, sizeof(cp), &cp); } +static void hci_amp_disconn(struct hci_conn *conn, __u8 reason) +{ + struct hci_cp_disconn_phy_link cp; + + BT_DBG("hcon %p", conn); + + conn->state = BT_DISCONN; + + cp.phy_handle = HCI_PHY_HANDLE(conn->handle); + cp.reason = reason; + hci_send_cmd(conn->hdev, HCI_OP_DISCONN_PHY_LINK, + sizeof(cp), &cp); +} + static void hci_add_sco(struct hci_conn *conn, __u16 handle) { struct hci_dev *hdev = conn->hdev; @@ -230,11 +244,24 @@ void hci_sco_setup(struct hci_conn *conn, __u8 status) } } +static void hci_conn_disconnect(struct hci_conn *conn) +{ + __u8 reason = hci_proto_disconn_ind(conn); + + switch (conn->type) { + case ACL_LINK: + hci_acl_disconn(conn, reason); + break; + case AMP_LINK: + hci_amp_disconn(conn, reason); + break; + } +} + static void hci_conn_timeout(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, disc_work.work); - __u8 reason; BT_DBG("hcon %p state %s", conn, state_to_string(conn->state)); @@ -253,8 +280,7 @@ static void hci_conn_timeout(struct work_struct *work) break; case BT_CONFIG: case BT_CONNECTED: - reason = hci_proto_disconn_ind(conn); - hci_acl_disconn(conn, reason); + hci_conn_disconnect(conn); break; default: conn->state = BT_CLOSED; @@ -320,7 +346,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) { struct hci_conn *conn; - BT_DBG("%s dst %s", hdev->name, batostr(dst)); + BT_DBG("%s dst %pMR", hdev->name, dst); conn = kzalloc(sizeof(struct hci_conn), GFP_KERNEL); if (!conn) @@ -437,7 +463,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src) int use_src = bacmp(src, BDADDR_ANY); struct hci_dev *hdev = NULL, *d; - BT_DBG("%s -> %s", batostr(src), batostr(dst)); + BT_DBG("%pMR -> %pMR", src, dst); read_lock(&hci_dev_list_lock); @@ -476,6 +502,9 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, { struct hci_conn *le; + if (test_bit(HCI_LE_PERIPHERAL, &hdev->flags)) + return ERR_PTR(-ENOTSUPP); + le = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst); if (!le) { le = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); @@ -567,7 +596,7 @@ static struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 dst_type, __u8 sec_level, __u8 auth_type) { - BT_DBG("%s dst %s type 0x%x", hdev->name, batostr(dst), type); + BT_DBG("%s dst %pMR type 0x%x", hdev->name, dst, type); switch (type) { case LE_LINK: @@ -933,6 +962,7 @@ struct hci_chan *hci_chan_create(struct hci_conn *conn) chan->conn = conn; skb_queue_head_init(&chan->data_q); + chan->state = BT_CONNECTED; list_add_rcu(&chan->list, &conn->chan_list); @@ -950,6 +980,8 @@ void hci_chan_del(struct hci_chan *chan) synchronize_rcu(); + hci_conn_put(conn); + skb_queue_purge(&chan->data_q); kfree(chan); } @@ -963,3 +995,35 @@ void hci_chan_list_flush(struct hci_conn *conn) list_for_each_entry_safe(chan, n, &conn->chan_list, list) hci_chan_del(chan); } + +static struct hci_chan *__hci_chan_lookup_handle(struct hci_conn *hcon, + __u16 handle) +{ + struct hci_chan *hchan; + + list_for_each_entry(hchan, &hcon->chan_list, list) { + if (hchan->handle == handle) + return hchan; + } + + return NULL; +} + +struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *hcon; + struct hci_chan *hchan = NULL; + + rcu_read_lock(); + + list_for_each_entry_rcu(hcon, &h->list, list) { + hchan = __hci_chan_lookup_handle(hcon, handle); + if (hchan) + break; + } + + rcu_read_unlock(); + + return hchan; +} diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 8de421d28cb5..6a2d0387475c 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -178,48 +178,13 @@ static void hci_reset_req(struct hci_dev *hdev, unsigned long opt) static void bredr_init(struct hci_dev *hdev) { - struct hci_cp_delete_stored_link_key cp; - __le16 param; - __u8 flt_type; - hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_PACKET_BASED; - /* Mandatory initialization */ - /* Read Local Supported Features */ hci_send_cmd(hdev, HCI_OP_READ_LOCAL_FEATURES, 0, NULL); /* Read Local Version */ hci_send_cmd(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL); - - /* Read Buffer Size (ACL mtu, max pkt, etc.) */ - hci_send_cmd(hdev, HCI_OP_READ_BUFFER_SIZE, 0, NULL); - - /* Read BD Address */ - hci_send_cmd(hdev, HCI_OP_READ_BD_ADDR, 0, NULL); - - /* Read Class of Device */ - hci_send_cmd(hdev, HCI_OP_READ_CLASS_OF_DEV, 0, NULL); - - /* Read Local Name */ - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_NAME, 0, NULL); - - /* Read Voice Setting */ - hci_send_cmd(hdev, HCI_OP_READ_VOICE_SETTING, 0, NULL); - - /* Optional initialization */ - - /* Clear Event Filters */ - flt_type = HCI_FLT_CLEAR_ALL; - hci_send_cmd(hdev, HCI_OP_SET_EVENT_FLT, 1, &flt_type); - - /* Connection accept timeout ~20 secs */ - param = __constant_cpu_to_le16(0x7d00); - hci_send_cmd(hdev, HCI_OP_WRITE_CA_TIMEOUT, 2, ¶m); - - bacpy(&cp.bdaddr, BDADDR_ANY); - cp.delete_all = 1; - hci_send_cmd(hdev, HCI_OP_DELETE_STORED_LINK_KEY, sizeof(cp), &cp); } static void amp_init(struct hci_dev *hdev) @@ -273,14 +238,6 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) } } -static void hci_le_init_req(struct hci_dev *hdev, unsigned long opt) -{ - BT_DBG("%s", hdev->name); - - /* Read LE buffer size */ - hci_send_cmd(hdev, HCI_OP_LE_READ_BUFFER_SIZE, 0, NULL); -} - static void hci_scan_req(struct hci_dev *hdev, unsigned long opt) { __u8 scan = opt; @@ -405,7 +362,7 @@ struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; - BT_DBG("cache %p, %s", cache, batostr(bdaddr)); + BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->all, all) { if (!bacmp(&e->data.bdaddr, bdaddr)) @@ -421,7 +378,7 @@ struct inquiry_entry *hci_inquiry_cache_lookup_unknown(struct hci_dev *hdev, struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; - BT_DBG("cache %p, %s", cache, batostr(bdaddr)); + BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->unknown, list) { if (!bacmp(&e->data.bdaddr, bdaddr)) @@ -438,7 +395,7 @@ struct inquiry_entry *hci_inquiry_cache_lookup_resolve(struct hci_dev *hdev, struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; - BT_DBG("cache %p bdaddr %s state %d", cache, batostr(bdaddr), state); + BT_DBG("cache %p bdaddr %pMR state %d", cache, bdaddr, state); list_for_each_entry(e, &cache->resolve, list) { if (!bacmp(bdaddr, BDADDR_ANY) && e->name_state == state) @@ -475,7 +432,9 @@ bool hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *ie; - BT_DBG("cache %p, %s", cache, batostr(&data->bdaddr)); + BT_DBG("cache %p, %pMR", cache, &data->bdaddr); + + hci_remove_remote_oob_data(hdev, &data->bdaddr); if (ssp) *ssp = data->ssp_mode; @@ -637,6 +596,99 @@ done: return err; } +static u8 create_ad(struct hci_dev *hdev, u8 *ptr) +{ + u8 ad_len = 0, flags = 0; + size_t name_len; + + if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) + flags |= LE_AD_GENERAL; + + if (!lmp_bredr_capable(hdev)) + flags |= LE_AD_NO_BREDR; + + if (lmp_le_br_capable(hdev)) + flags |= LE_AD_SIM_LE_BREDR_CTRL; + + if (lmp_host_le_br_capable(hdev)) + flags |= LE_AD_SIM_LE_BREDR_HOST; + + if (flags) { + BT_DBG("adv flags 0x%02x", flags); + + ptr[0] = 2; + ptr[1] = EIR_FLAGS; + ptr[2] = flags; + + ad_len += 3; + ptr += 3; + } + + if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) { + ptr[0] = 2; + ptr[1] = EIR_TX_POWER; + ptr[2] = (u8) hdev->adv_tx_power; + + ad_len += 3; + ptr += 3; + } + + name_len = strlen(hdev->dev_name); + if (name_len > 0) { + size_t max_len = HCI_MAX_AD_LENGTH - ad_len - 2; + + if (name_len > max_len) { + name_len = max_len; + ptr[1] = EIR_NAME_SHORT; + } else + ptr[1] = EIR_NAME_COMPLETE; + + ptr[0] = name_len + 1; + + memcpy(ptr + 2, hdev->dev_name, name_len); + + ad_len += (name_len + 2); + ptr += (name_len + 2); + } + + return ad_len; +} + +int hci_update_ad(struct hci_dev *hdev) +{ + struct hci_cp_le_set_adv_data cp; + u8 len; + int err; + + hci_dev_lock(hdev); + + if (!lmp_le_capable(hdev)) { + err = -EINVAL; + goto unlock; + } + + memset(&cp, 0, sizeof(cp)); + + len = create_ad(hdev, cp.data); + + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) { + err = 0; + goto unlock; + } + + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; + + cp.length = len; + err = hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); + +unlock: + hci_dev_unlock(hdev); + + return err; +} + /* ---- HCI ioctl helpers ---- */ int hci_dev_open(__u16 dev) @@ -687,10 +739,6 @@ int hci_dev_open(__u16 dev) ret = __hci_request(hdev, hci_init_req, 0, HCI_INIT_TIMEOUT); - if (lmp_host_le_capable(hdev)) - ret = __hci_request(hdev, hci_le_init_req, 0, - HCI_INIT_TIMEOUT); - clear_bit(HCI_INIT, &hdev->flags); } @@ -698,6 +746,7 @@ int hci_dev_open(__u16 dev) hci_dev_hold(hdev); set_bit(HCI_UP, &hdev->flags); hci_notify(hdev, HCI_DEV_UP); + hci_update_ad(hdev); if (!test_bit(HCI_SETUP, &hdev->dev_flags) && mgmt_valid_hdev(hdev)) { hci_dev_lock(hdev); @@ -812,6 +861,9 @@ static int hci_dev_do_close(struct hci_dev *hdev) /* Clear flags */ hdev->flags = 0; + /* Controller radio is available but is currently powered down */ + hdev->amp_status = 0; + memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); @@ -1039,10 +1091,17 @@ int hci_get_dev_info(void __user *arg) di.type = (hdev->bus & 0x0f) | (hdev->dev_type << 4); di.flags = hdev->flags; di.pkt_type = hdev->pkt_type; - di.acl_mtu = hdev->acl_mtu; - di.acl_pkts = hdev->acl_pkts; - di.sco_mtu = hdev->sco_mtu; - di.sco_pkts = hdev->sco_pkts; + if (lmp_bredr_capable(hdev)) { + di.acl_mtu = hdev->acl_mtu; + di.acl_pkts = hdev->acl_pkts; + di.sco_mtu = hdev->sco_mtu; + di.sco_pkts = hdev->sco_pkts; + } else { + di.acl_mtu = hdev->le_mtu; + di.acl_pkts = hdev->le_pkts; + di.sco_mtu = 0; + di.sco_pkts = 0; + } di.link_policy = hdev->link_policy; di.link_mode = hdev->link_mode; @@ -1259,7 +1318,7 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, list_add(&key->list, &hdev->link_keys); } - BT_DBG("%s key for %s type %u", hdev->name, batostr(bdaddr), type); + BT_DBG("%s key for %pMR type %u", hdev->name, bdaddr, type); /* Some buggy controller combinations generate a changed * combination key for legacy pairing even when there's no @@ -1338,7 +1397,7 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) if (!key) return -ENOENT; - BT_DBG("%s removing %s", hdev->name, batostr(bdaddr)); + BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del(&key->list); kfree(key); @@ -1354,7 +1413,7 @@ int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr) if (bacmp(bdaddr, &k->bdaddr)) continue; - BT_DBG("%s removing %s", hdev->name, batostr(bdaddr)); + BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del(&k->list); kfree(k); @@ -1401,7 +1460,7 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr) if (!data) return -ENOENT; - BT_DBG("%s removing %s", hdev->name, batostr(bdaddr)); + BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del(&data->list); kfree(data); @@ -1440,7 +1499,7 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash, memcpy(data->hash, hash, sizeof(data->hash)); memcpy(data->randomizer, randomizer, sizeof(data->randomizer)); - BT_DBG("%s for %s", hdev->name, batostr(bdaddr)); + BT_DBG("%s for %pMR", hdev->name, bdaddr); return 0; } @@ -1617,6 +1676,9 @@ int hci_le_scan(struct hci_dev *hdev, u8 type, u16 interval, u16 window, BT_DBG("%s", hdev->name); + if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) + return -ENOTSUPP; + if (work_busy(&hdev->le_scan)) return -EINPROGRESS; @@ -1643,6 +1705,8 @@ struct hci_dev *hci_alloc_dev(void) hdev->esco_type = (ESCO_HV1); hdev->link_mode = (HCI_LM_ACCEPT); hdev->io_capability = 0x03; /* No Input No Output */ + hdev->inq_tx_power = HCI_TX_POWER_INVALID; + hdev->adv_tx_power = HCI_TX_POWER_INVALID; hdev->sniff_max_interval = 800; hdev->sniff_min_interval = 80; @@ -1754,11 +1818,11 @@ int hci_register_dev(struct hci_dev *hdev) if (hdev->dev_type != HCI_AMP) set_bit(HCI_AUTO_OFF, &hdev->dev_flags); - schedule_work(&hdev->power_on); - hci_notify(hdev, HCI_DEV_REG); hci_dev_hold(hdev); + schedule_work(&hdev->power_on); + return id; err_wqueue: @@ -1793,6 +1857,8 @@ void hci_unregister_dev(struct hci_dev *hdev) for (i = 0; i < NUM_REASSEMBLY; i++) kfree_skb(hdev->reassembly[i]); + cancel_work_sync(&hdev->power_on); + if (!test_bit(HCI_INIT, &hdev->flags) && !test_bit(HCI_SETUP, &hdev->dev_flags)) { hci_dev_lock(hdev); @@ -2153,9 +2219,10 @@ static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags) hdr->dlen = cpu_to_le16(len); } -static void hci_queue_acl(struct hci_conn *conn, struct sk_buff_head *queue, +static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue, struct sk_buff *skb, __u16 flags) { + struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; struct sk_buff *list; @@ -2163,7 +2230,18 @@ static void hci_queue_acl(struct hci_conn *conn, struct sk_buff_head *queue, skb->data_len = 0; bt_cb(skb)->pkt_type = HCI_ACLDATA_PKT; - hci_add_acl_hdr(skb, conn->handle, flags); + + switch (hdev->dev_type) { + case HCI_BREDR: + hci_add_acl_hdr(skb, conn->handle, flags); + break; + case HCI_AMP: + hci_add_acl_hdr(skb, chan->handle, flags); + break; + default: + BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type); + return; + } list = skb_shinfo(skb)->frag_list; if (!list) { @@ -2202,14 +2280,13 @@ static void hci_queue_acl(struct hci_conn *conn, struct sk_buff_head *queue, void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags) { - struct hci_conn *conn = chan->conn; - struct hci_dev *hdev = conn->hdev; + struct hci_dev *hdev = chan->conn->hdev; BT_DBG("%s chan %p flags 0x%4.4x", hdev->name, chan, flags); skb->dev = (void *) hdev; - hci_queue_acl(conn, &chan->data_q, skb, flags); + hci_queue_acl(chan, &chan->data_q, skb, flags); queue_work(hdev->workqueue, &hdev->tx_work); } @@ -2311,8 +2388,8 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) /* Kill stalled connections */ list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->sent) { - BT_ERR("%s killing stalled connection %s", - hdev->name, batostr(&c->dst)); + BT_ERR("%s killing stalled connection %pMR", + hdev->name, &c->dst); hci_acl_disconn(c, HCI_ERROR_REMOTE_USER_TERM); } } @@ -2381,6 +2458,9 @@ static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, case ACL_LINK: cnt = hdev->acl_cnt; break; + case AMP_LINK: + cnt = hdev->block_cnt; + break; case SCO_LINK: case ESCO_LINK: cnt = hdev->sco_cnt; @@ -2510,11 +2590,19 @@ static void hci_sched_acl_blk(struct hci_dev *hdev) struct hci_chan *chan; struct sk_buff *skb; int quote; + u8 type; __check_timeout(hdev, cnt); + BT_DBG("%s", hdev->name); + + if (hdev->dev_type == HCI_AMP) + type = AMP_LINK; + else + type = ACL_LINK; + while (hdev->block_cnt > 0 && - (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { + (chan = hci_chan_sent(hdev, type, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote > 0 && (skb = skb_peek(&chan->data_q))) { int blocks; @@ -2547,14 +2635,19 @@ static void hci_sched_acl_blk(struct hci_dev *hdev) } if (cnt != hdev->block_cnt) - hci_prio_recalculate(hdev, ACL_LINK); + hci_prio_recalculate(hdev, type); } static void hci_sched_acl(struct hci_dev *hdev) { BT_DBG("%s", hdev->name); - if (!hci_conn_num(hdev, ACL_LINK)) + /* No ACL link over BR/EDR controller */ + if (!hci_conn_num(hdev, ACL_LINK) && hdev->dev_type == HCI_BREDR) + return; + + /* No AMP link over AMP controller */ + if (!hci_conn_num(hdev, AMP_LINK) && hdev->dev_type == HCI_AMP) return; switch (hdev->flow_ctl_mode) { @@ -2717,14 +2810,6 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) if (conn) { hci_conn_enter_active_mode(conn, BT_POWER_FORCE_ACTIVE_OFF); - hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags) && - !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, &conn->dst, conn->type, - conn->dst_type, 0, NULL, 0, - conn->dev_class); - hci_dev_unlock(hdev); - /* Send to upper protocol */ l2cap_recv_acldata(conn, skb, flags); return; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 2022b43c7353..81b44481d0d9 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -24,12 +24,13 @@ /* Bluetooth HCI event handling. */ -#include <linux/export.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/mgmt.h> +#include <net/bluetooth/a2mp.h> +#include <net/bluetooth/amp.h> /* Handle HCI Event packets */ @@ -201,6 +202,11 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) BIT(HCI_PERIODIC_INQ)); hdev->discovery.state = DISCOVERY_STOPPED; + hdev->inq_tx_power = HCI_TX_POWER_INVALID; + hdev->adv_tx_power = HCI_TX_POWER_INVALID; + + memset(hdev->adv_data, 0, sizeof(hdev->adv_data)); + hdev->adv_data_len = 0; } static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb) @@ -223,6 +229,9 @@ static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); + if (!status && !test_bit(HCI_INIT, &hdev->flags)) + hci_update_ad(hdev); + hci_req_complete(hdev, HCI_OP_WRITE_LOCAL_NAME, status); } @@ -438,7 +447,7 @@ static void hci_cc_host_buffer_size(struct hci_dev *hdev, struct sk_buff *skb) static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); - void *sent; + struct hci_cp_write_ssp_mode *sent; BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -446,10 +455,17 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb) if (!sent) return; + if (!status) { + if (sent->mode) + hdev->host_features[0] |= LMP_HOST_SSP; + else + hdev->host_features[0] &= ~LMP_HOST_SSP; + } + if (test_bit(HCI_MGMT, &hdev->dev_flags)) - mgmt_ssp_enable_complete(hdev, *((u8 *) sent), status); + mgmt_ssp_enable_complete(hdev, sent->mode, status); else if (!status) { - if (*((u8 *) sent)) + if (sent->mode) set_bit(HCI_SSP_ENABLED, &hdev->dev_flags); else clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags); @@ -458,10 +474,10 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb) static u8 hci_get_inquiry_mode(struct hci_dev *hdev) { - if (hdev->features[6] & LMP_EXT_INQ) + if (lmp_ext_inq_capable(hdev)) return 2; - if (hdev->features[3] & LMP_RSSI_INQ) + if (lmp_inq_rssi_capable(hdev)) return 1; if (hdev->manufacturer == 11 && hdev->hci_rev == 0x00 && @@ -505,28 +521,30 @@ static void hci_setup_event_mask(struct hci_dev *hdev) if (hdev->hci_ver < BLUETOOTH_VER_1_2) return; - events[4] |= 0x01; /* Flow Specification Complete */ - events[4] |= 0x02; /* Inquiry Result with RSSI */ - events[4] |= 0x04; /* Read Remote Extended Features Complete */ - events[5] |= 0x08; /* Synchronous Connection Complete */ - events[5] |= 0x10; /* Synchronous Connection Changed */ + if (lmp_bredr_capable(hdev)) { + events[4] |= 0x01; /* Flow Specification Complete */ + events[4] |= 0x02; /* Inquiry Result with RSSI */ + events[4] |= 0x04; /* Read Remote Extended Features Complete */ + events[5] |= 0x08; /* Synchronous Connection Complete */ + events[5] |= 0x10; /* Synchronous Connection Changed */ + } - if (hdev->features[3] & LMP_RSSI_INQ) + if (lmp_inq_rssi_capable(hdev)) events[4] |= 0x02; /* Inquiry Result with RSSI */ if (lmp_sniffsubr_capable(hdev)) events[5] |= 0x20; /* Sniff Subrating */ - if (hdev->features[5] & LMP_PAUSE_ENC) + if (lmp_pause_enc_capable(hdev)) events[5] |= 0x80; /* Encryption Key Refresh Complete */ - if (hdev->features[6] & LMP_EXT_INQ) + if (lmp_ext_inq_capable(hdev)) events[5] |= 0x40; /* Extended Inquiry Result */ if (lmp_no_flush_capable(hdev)) events[7] |= 0x01; /* Enhanced Flush Complete */ - if (hdev->features[7] & LMP_LSTO) + if (lmp_lsto_capable(hdev)) events[6] |= 0x80; /* Link Supervision Timeout Changed */ if (lmp_ssp_capable(hdev)) { @@ -546,6 +564,53 @@ static void hci_setup_event_mask(struct hci_dev *hdev) events[7] |= 0x20; /* LE Meta-Event */ hci_send_cmd(hdev, HCI_OP_SET_EVENT_MASK, sizeof(events), events); + + if (lmp_le_capable(hdev)) { + memset(events, 0, sizeof(events)); + events[0] = 0x1f; + hci_send_cmd(hdev, HCI_OP_LE_SET_EVENT_MASK, + sizeof(events), events); + } +} + +static void bredr_setup(struct hci_dev *hdev) +{ + struct hci_cp_delete_stored_link_key cp; + __le16 param; + __u8 flt_type; + + /* Read Buffer Size (ACL mtu, max pkt, etc.) */ + hci_send_cmd(hdev, HCI_OP_READ_BUFFER_SIZE, 0, NULL); + + /* Read Class of Device */ + hci_send_cmd(hdev, HCI_OP_READ_CLASS_OF_DEV, 0, NULL); + + /* Read Local Name */ + hci_send_cmd(hdev, HCI_OP_READ_LOCAL_NAME, 0, NULL); + + /* Read Voice Setting */ + hci_send_cmd(hdev, HCI_OP_READ_VOICE_SETTING, 0, NULL); + + /* Clear Event Filters */ + flt_type = HCI_FLT_CLEAR_ALL; + hci_send_cmd(hdev, HCI_OP_SET_EVENT_FLT, 1, &flt_type); + + /* Connection accept timeout ~20 secs */ + param = __constant_cpu_to_le16(0x7d00); + hci_send_cmd(hdev, HCI_OP_WRITE_CA_TIMEOUT, 2, ¶m); + + bacpy(&cp.bdaddr, BDADDR_ANY); + cp.delete_all = 1; + hci_send_cmd(hdev, HCI_OP_DELETE_STORED_LINK_KEY, sizeof(cp), &cp); +} + +static void le_setup(struct hci_dev *hdev) +{ + /* Read LE Buffer Size */ + hci_send_cmd(hdev, HCI_OP_LE_READ_BUFFER_SIZE, 0, NULL); + + /* Read LE Advertising Channel TX Power */ + hci_send_cmd(hdev, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL); } static void hci_setup(struct hci_dev *hdev) @@ -553,6 +618,15 @@ static void hci_setup(struct hci_dev *hdev) if (hdev->dev_type != HCI_BREDR) return; + /* Read BD Address */ + hci_send_cmd(hdev, HCI_OP_READ_BD_ADDR, 0, NULL); + + if (lmp_bredr_capable(hdev)) + bredr_setup(hdev); + + if (lmp_le_capable(hdev)) + le_setup(hdev); + hci_setup_event_mask(hdev); if (hdev->hci_ver > BLUETOOTH_VER_1_1) @@ -573,13 +647,13 @@ static void hci_setup(struct hci_dev *hdev) } } - if (hdev->features[3] & LMP_RSSI_INQ) + if (lmp_inq_rssi_capable(hdev)) hci_setup_inquiry_mode(hdev); - if (hdev->features[7] & LMP_INQ_TX_PWR) + if (lmp_inq_tx_pwr_capable(hdev)) hci_send_cmd(hdev, HCI_OP_READ_INQ_RSP_TX_POWER, 0, NULL); - if (hdev->features[7] & LMP_EXTFEATURES) { + if (lmp_ext_feat_capable(hdev)) { struct hci_cp_read_local_ext_features cp; cp.page = 0x01; @@ -626,11 +700,11 @@ static void hci_setup_link_policy(struct hci_dev *hdev) if (lmp_rswitch_capable(hdev)) link_policy |= HCI_LP_RSWITCH; - if (hdev->features[0] & LMP_HOLD) + if (lmp_hold_capable(hdev)) link_policy |= HCI_LP_HOLD; if (lmp_sniff_capable(hdev)) link_policy |= HCI_LP_SNIFF; - if (hdev->features[1] & LMP_PARK) + if (lmp_park_capable(hdev)) link_policy |= HCI_LP_PARK; cp.policy = cpu_to_le16(link_policy); @@ -720,10 +794,10 @@ static void hci_set_le_support(struct hci_dev *hdev) if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) { cp.le = 1; - cp.simul = !!(hdev->features[6] & LMP_SIMUL_LE_BR); + cp.simul = lmp_le_br_capable(hdev); } - if (cp.le != !!(hdev->host_features[0] & LMP_HOST_LE)) + if (cp.le != lmp_host_le_capable(hdev)) hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(cp), &cp); } @@ -846,7 +920,7 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) - return; + goto a2mp_rsp; hdev->amp_status = rp->amp_status; hdev->amp_total_bw = __le32_to_cpu(rp->total_bw); @@ -860,6 +934,46 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev, hdev->amp_max_flush_to = __le32_to_cpu(rp->max_flush_to); hci_req_complete(hdev, HCI_OP_READ_LOCAL_AMP_INFO, rp->status); + +a2mp_rsp: + a2mp_send_getinfo_rsp(hdev); +} + +static void hci_cc_read_local_amp_assoc(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_read_local_amp_assoc *rp = (void *) skb->data; + struct amp_assoc *assoc = &hdev->loc_assoc; + size_t rem_len, frag_len; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + goto a2mp_rsp; + + frag_len = skb->len - sizeof(*rp); + rem_len = __le16_to_cpu(rp->rem_len); + + if (rem_len > frag_len) { + BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); + + memcpy(assoc->data + assoc->offset, rp->frag, frag_len); + assoc->offset += frag_len; + + /* Read other fragments */ + amp_read_loc_assoc_frag(hdev, rp->phy_handle); + + return; + } + + memcpy(assoc->data + assoc->offset, rp->frag, rem_len); + assoc->len = assoc->offset + rem_len; + assoc->offset = 0; + +a2mp_rsp: + /* Send A2MP Rsp when all fragments are received */ + a2mp_send_getampassoc_rsp(hdev, rp->status); + a2mp_send_create_phy_link_req(hdev, rp->status); } static void hci_cc_delete_stored_link_key(struct hci_dev *hdev, @@ -976,6 +1090,31 @@ static void hci_cc_le_read_buffer_size(struct hci_dev *hdev, hci_req_complete(hdev, HCI_OP_LE_READ_BUFFER_SIZE, rp->status); } +static void hci_cc_le_read_adv_tx_power(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_le_read_adv_tx_power *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (!rp->status) { + hdev->adv_tx_power = rp->tx_power; + if (!test_bit(HCI_INIT, &hdev->flags)) + hci_update_ad(hdev); + } + + hci_req_complete(hdev, HCI_OP_LE_READ_ADV_TX_POWER, rp->status); +} + +static void hci_cc_le_set_event_mask(struct hci_dev *hdev, struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + hci_req_complete(hdev, HCI_OP_LE_SET_EVENT_MASK, status); +} + static void hci_cc_user_confirm_reply(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = (void *) skb->data; @@ -1051,6 +1190,33 @@ static void hci_cc_read_local_oob_data_reply(struct hci_dev *hdev, hci_dev_unlock(hdev); } +static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) +{ + __u8 *sent, status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_ENABLE); + if (!sent) + return; + + hci_dev_lock(hdev); + + if (!status) { + if (*sent) + set_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags); + else + clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags); + } + + hci_dev_unlock(hdev); + + if (!test_bit(HCI_INIT, &hdev->flags)) + hci_update_ad(hdev); + + hci_req_complete(hdev, HCI_OP_LE_SET_ADV_ENABLE, status); +} + static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); @@ -1165,6 +1331,11 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev, hdev->host_features[0] |= LMP_HOST_LE; else hdev->host_features[0] &= ~LMP_HOST_LE; + + if (sent->simul) + hdev->host_features[0] |= LMP_HOST_LE_BREDR; + else + hdev->host_features[0] &= ~LMP_HOST_LE_BREDR; } if (test_bit(HCI_MGMT, &hdev->dev_flags) && @@ -1174,6 +1345,20 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev, hci_req_complete(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, status); } +static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_write_remote_amp_assoc *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", + hdev->name, rp->status, rp->phy_handle); + + if (rp->status) + return; + + amp_write_rem_assoc_continue(hdev, rp->phy_handle); +} + static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -1210,7 +1395,7 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); - BT_DBG("%s bdaddr %s hcon %p", hdev->name, batostr(&cp->bdaddr), conn); + BT_DBG("%s bdaddr %pMR hcon %p", hdev->name, &cp->bdaddr, conn); if (status) { if (conn && conn->state == BT_CONNECT) { @@ -1639,8 +1824,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, __u8 status) return; } - BT_DBG("%s bdaddr %s conn %p", hdev->name, batostr(&conn->dst), - conn); + BT_DBG("%s bdaddr %pMR conn %p", hdev->name, &conn->dst, conn); conn->state = BT_CLOSED; mgmt_connect_failed(hdev, &conn->dst, conn->type, @@ -1657,6 +1841,52 @@ static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status) BT_DBG("%s status 0x%2.2x", hdev->name, status); } +static void hci_cs_create_phylink(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_create_phy_link *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); + if (!cp) + return; + + hci_dev_lock(hdev); + + if (status) { + struct hci_conn *hcon; + + hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); + if (hcon) + hci_conn_del(hcon); + } else { + amp_write_remote_assoc(hdev, cp->phy_handle); + } + + hci_dev_unlock(hdev); +} + +static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_accept_phy_link *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); + if (!cp) + return; + + amp_write_remote_assoc(hdev, cp->phy_handle); +} + +static void hci_cs_create_logical_link(struct hci_dev *hdev, u8 status) +{ + BT_DBG("%s status 0x%2.2x", hdev->name, status); +} + static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); @@ -1817,15 +2047,53 @@ unlock: hci_conn_check_pending(hdev); } +void hci_conn_accept(struct hci_conn *conn, int mask) +{ + struct hci_dev *hdev = conn->hdev; + + BT_DBG("conn %p", conn); + + conn->state = BT_CONFIG; + + if (!lmp_esco_capable(hdev)) { + struct hci_cp_accept_conn_req cp; + + bacpy(&cp.bdaddr, &conn->dst); + + if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER)) + cp.role = 0x00; /* Become master */ + else + cp.role = 0x01; /* Remain slave */ + + hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); + } else /* lmp_esco_capable(hdev)) */ { + struct hci_cp_accept_sync_conn_req cp; + + bacpy(&cp.bdaddr, &conn->dst); + cp.pkt_type = cpu_to_le16(conn->pkt_type); + + cp.tx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.rx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.max_latency = __constant_cpu_to_le16(0xffff); + cp.content_format = cpu_to_le16(hdev->voice_setting); + cp.retrans_effort = 0xff; + + hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, + sizeof(cp), &cp); + } +} + static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_conn_request *ev = (void *) skb->data; int mask = hdev->link_mode; + __u8 flags = 0; - BT_DBG("%s bdaddr %s type 0x%x", hdev->name, batostr(&ev->bdaddr), + BT_DBG("%s bdaddr %pMR type 0x%x", hdev->name, &ev->bdaddr, ev->link_type); - mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type); + mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type, + &flags); if ((mask & HCI_LM_ACCEPT) && !hci_blacklist_lookup(hdev, &ev->bdaddr)) { @@ -1851,12 +2119,13 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) } memcpy(conn->dev_class, ev->dev_class, 3); - conn->state = BT_CONNECT; hci_dev_unlock(hdev); - if (ev->link_type == ACL_LINK || !lmp_esco_capable(hdev)) { + if (ev->link_type == ACL_LINK || + (!(flags & HCI_PROTO_DEFER) && !lmp_esco_capable(hdev))) { struct hci_cp_accept_conn_req cp; + conn->state = BT_CONNECT; bacpy(&cp.bdaddr, &ev->bdaddr); @@ -1867,8 +2136,9 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); - } else { + } else if (!(flags & HCI_PROTO_DEFER)) { struct hci_cp_accept_sync_conn_req cp; + conn->state = BT_CONNECT; bacpy(&cp.bdaddr, &ev->bdaddr); cp.pkt_type = cpu_to_le16(conn->pkt_type); @@ -1881,6 +2151,10 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, sizeof(cp), &cp); + } else { + conn->state = BT_CONNECT2; + hci_proto_connect_cfm(conn, 0); + hci_conn_put(conn); } } else { /* Connection rejected */ @@ -2314,6 +2588,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_read_local_amp_info(hdev, skb); break; + case HCI_OP_READ_LOCAL_AMP_ASSOC: + hci_cc_read_local_amp_assoc(hdev, skb); + break; + case HCI_OP_DELETE_STORED_LINK_KEY: hci_cc_delete_stored_link_key(hdev, skb); break; @@ -2350,6 +2628,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_le_read_buffer_size(hdev, skb); break; + case HCI_OP_LE_READ_ADV_TX_POWER: + hci_cc_le_read_adv_tx_power(hdev, skb); + break; + + case HCI_OP_LE_SET_EVENT_MASK: + hci_cc_le_set_event_mask(hdev, skb); + break; + case HCI_OP_USER_CONFIRM_REPLY: hci_cc_user_confirm_reply(hdev, skb); break; @@ -2370,6 +2656,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_le_set_scan_param(hdev, skb); break; + case HCI_OP_LE_SET_ADV_ENABLE: + hci_cc_le_set_adv_enable(hdev, skb); + break; + case HCI_OP_LE_SET_SCAN_ENABLE: hci_cc_le_set_scan_enable(hdev, skb); break; @@ -2386,6 +2676,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_write_le_host_supported(hdev, skb); break; + case HCI_OP_WRITE_REMOTE_AMP_ASSOC: + hci_cc_write_remote_amp_assoc(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; @@ -2394,7 +2688,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (ev->opcode != HCI_OP_NOP) del_timer(&hdev->cmd_timer); - if (ev->ncmd) { + if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) { atomic_set(&hdev->cmd_cnt, 1); if (!skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); @@ -2467,6 +2761,18 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cs_le_start_enc(hdev, ev->status); break; + case HCI_OP_CREATE_PHY_LINK: + hci_cs_create_phylink(hdev, ev->status); + break; + + case HCI_OP_ACCEPT_PHY_LINK: + hci_cs_accept_phylink(hdev, ev->status); + break; + + case HCI_OP_CREATE_LOGICAL_LINK: + hci_cs_create_logical_link(hdev, ev->status); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; @@ -2574,6 +2880,27 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb) queue_work(hdev->workqueue, &hdev->tx_work); } +static struct hci_conn *__hci_conn_lookup_handle(struct hci_dev *hdev, + __u16 handle) +{ + struct hci_chan *chan; + + switch (hdev->dev_type) { + case HCI_BREDR: + return hci_conn_hash_lookup_handle(hdev, handle); + case HCI_AMP: + chan = hci_chan_lookup_handle(hdev, handle); + if (chan) + return chan->conn; + break; + default: + BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type); + break; + } + + return NULL; +} + static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_num_comp_blocks *ev = (void *) skb->data; @@ -2595,13 +2922,13 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb) for (i = 0; i < ev->num_hndl; i++) { struct hci_comp_blocks_info *info = &ev->handles[i]; - struct hci_conn *conn; + struct hci_conn *conn = NULL; __u16 handle, block_count; handle = __le16_to_cpu(info->handle); block_count = __le16_to_cpu(info->blocks); - conn = hci_conn_hash_lookup_handle(hdev, handle); + conn = __hci_conn_lookup_handle(hdev, handle); if (!conn) continue; @@ -2609,6 +2936,7 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb) switch (conn->type) { case ACL_LINK: + case AMP_LINK: hdev->block_cnt += block_count; if (hdev->block_cnt > hdev->num_blocks) hdev->block_cnt = hdev->num_blocks; @@ -2705,13 +3033,13 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) key = hci_find_link_key(hdev, &ev->bdaddr); if (!key) { - BT_DBG("%s link key not found for %s", hdev->name, - batostr(&ev->bdaddr)); + BT_DBG("%s link key not found for %pMR", hdev->name, + &ev->bdaddr); goto not_found; } - BT_DBG("%s found key type %u for %s", hdev->name, key->type, - batostr(&ev->bdaddr)); + BT_DBG("%s found key type %u for %pMR", hdev->name, key->type, + &ev->bdaddr); if (!test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags) && key->type == HCI_LK_DEBUG_COMBINATION) { @@ -3419,6 +3747,130 @@ unlock: hci_dev_unlock(hdev); } +static void hci_phy_link_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_phy_link_complete *ev = (void *) skb->data; + struct hci_conn *hcon, *bredr_hcon; + + BT_DBG("%s handle 0x%2.2x status 0x%2.2x", hdev->name, ev->phy_handle, + ev->status); + + hci_dev_lock(hdev); + + hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); + if (!hcon) { + hci_dev_unlock(hdev); + return; + } + + if (ev->status) { + hci_conn_del(hcon); + hci_dev_unlock(hdev); + return; + } + + bredr_hcon = hcon->amp_mgr->l2cap_conn->hcon; + + hcon->state = BT_CONNECTED; + bacpy(&hcon->dst, &bredr_hcon->dst); + + hci_conn_hold(hcon); + hcon->disc_timeout = HCI_DISCONN_TIMEOUT; + hci_conn_put(hcon); + + hci_conn_hold_device(hcon); + hci_conn_add_sysfs(hcon); + + amp_physical_cfm(bredr_hcon, hcon); + + hci_dev_unlock(hdev); +} + +static void hci_loglink_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_ev_logical_link_complete *ev = (void *) skb->data; + struct hci_conn *hcon; + struct hci_chan *hchan; + struct amp_mgr *mgr; + + BT_DBG("%s log_handle 0x%4.4x phy_handle 0x%2.2x status 0x%2.2x", + hdev->name, le16_to_cpu(ev->handle), ev->phy_handle, + ev->status); + + hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); + if (!hcon) + return; + + /* Create AMP hchan */ + hchan = hci_chan_create(hcon); + if (!hchan) + return; + + hchan->handle = le16_to_cpu(ev->handle); + + BT_DBG("hcon %p mgr %p hchan %p", hcon, hcon->amp_mgr, hchan); + + mgr = hcon->amp_mgr; + if (mgr && mgr->bredr_chan) { + struct l2cap_chan *bredr_chan = mgr->bredr_chan; + + l2cap_chan_lock(bredr_chan); + + bredr_chan->conn->mtu = hdev->block_mtu; + l2cap_logical_cfm(bredr_chan, hchan, 0); + hci_conn_hold(hcon); + + l2cap_chan_unlock(bredr_chan); + } +} + +static void hci_disconn_loglink_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_disconn_logical_link_complete *ev = (void *) skb->data; + struct hci_chan *hchan; + + BT_DBG("%s log handle 0x%4.4x status 0x%2.2x", hdev->name, + le16_to_cpu(ev->handle), ev->status); + + if (ev->status) + return; + + hci_dev_lock(hdev); + + hchan = hci_chan_lookup_handle(hdev, le16_to_cpu(ev->handle)); + if (!hchan) + goto unlock; + + amp_destroy_logical_link(hchan, ev->reason); + +unlock: + hci_dev_unlock(hdev); +} + +static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_disconn_phy_link_complete *ev = (void *) skb->data; + struct hci_conn *hcon; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + if (ev->status) + return; + + hci_dev_lock(hdev); + + hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); + if (hcon) { + hcon->state = BT_CLOSED; + hci_conn_del(hcon); + } + + hci_dev_unlock(hdev); +} + static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_conn_complete *ev = (void *) skb->data; @@ -3558,6 +4010,22 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) } } +static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_ev_channel_selected *ev = (void *) skb->data; + struct hci_conn *hcon; + + BT_DBG("%s handle 0x%2.2x", hdev->name, ev->phy_handle); + + skb_pull(skb, sizeof(*ev)); + + hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); + if (!hcon) + return; + + amp_read_loc_assoc_final_data(hdev, hcon); +} + void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_event_hdr *hdr = (void *) skb->data; @@ -3722,10 +4190,30 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) hci_le_meta_evt(hdev, skb); break; + case HCI_EV_CHANNEL_SELECTED: + hci_chan_selected_evt(hdev, skb); + break; + case HCI_EV_REMOTE_OOB_DATA_REQUEST: hci_remote_oob_data_request_evt(hdev, skb); break; + case HCI_EV_PHY_LINK_COMPLETE: + hci_phy_link_complete_evt(hdev, skb); + break; + + case HCI_EV_LOGICAL_LINK_COMPLETE: + hci_loglink_complete_evt(hdev, skb); + break; + + case HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE: + hci_disconn_loglink_complete_evt(hdev, skb); + break; + + case HCI_EV_DISCONN_PHY_LINK_COMPLETE: + hci_disconn_phylink_complete_evt(hdev, skb); + break; + case HCI_EV_NUM_COMP_BLOCKS: hci_num_comp_blocks_evt(hdev, skb); break; diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index a20e61c3653d..55cceee02a84 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -38,7 +38,7 @@ static ssize_t show_link_address(struct device *dev, struct device_attribute *attr, char *buf) { struct hci_conn *conn = to_hci_conn(dev); - return sprintf(buf, "%s\n", batostr(&conn->dst)); + return sprintf(buf, "%pMR\n", &conn->dst); } static ssize_t show_link_features(struct device *dev, @@ -224,7 +224,7 @@ static ssize_t show_address(struct device *dev, struct device_attribute *attr, char *buf) { struct hci_dev *hdev = to_hci_dev(dev); - return sprintf(buf, "%s\n", batostr(&hdev->bdaddr)); + return sprintf(buf, "%pMR\n", &hdev->bdaddr); } static ssize_t show_features(struct device *dev, @@ -406,8 +406,8 @@ static int inquiry_cache_show(struct seq_file *f, void *p) list_for_each_entry(e, &cache->all, all) { struct inquiry_data *data = &e->data; - seq_printf(f, "%s %d %d %d 0x%.2x%.2x%.2x 0x%.4x %d %d %u\n", - batostr(&data->bdaddr), + seq_printf(f, "%pMR %d %d %d 0x%.2x%.2x%.2x 0x%.4x %d %d %u\n", + &data->bdaddr, data->pscan_rep_mode, data->pscan_period_mode, data->pscan_mode, data->dev_class[2], data->dev_class[1], data->dev_class[0], @@ -440,7 +440,7 @@ static int blacklist_show(struct seq_file *f, void *p) hci_dev_lock(hdev); list_for_each_entry(b, &hdev->blacklist, list) - seq_printf(f, "%s\n", batostr(&b->bdaddr)); + seq_printf(f, "%pMR\n", &b->bdaddr); hci_dev_unlock(hdev); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index ccd985da6518..a7352ff3fd1e 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -931,9 +931,13 @@ static int hidp_setup_hid(struct hidp_session *session, hid->version = req->version; hid->country = req->country; - strncpy(hid->name, req->name, 128); - strncpy(hid->phys, batostr(&bt_sk(session->ctrl_sock->sk)->src), 64); - strncpy(hid->uniq, batostr(&bt_sk(session->ctrl_sock->sk)->dst), 64); + strncpy(hid->name, req->name, sizeof(req->name) - 1); + + snprintf(hid->phys, sizeof(hid->phys), "%pMR", + &bt_sk(session->ctrl_sock->sk)->src); + + snprintf(hid->uniq, sizeof(hid->uniq), "%pMR", + &bt_sk(session->ctrl_sock->sk)->dst); hid->dev.parent = &session->conn->dev; hid->ll_driver = &hidp_hid_driver; @@ -941,6 +945,13 @@ static int hidp_setup_hid(struct hidp_session *session, hid->hid_get_raw_report = hidp_get_raw_report; hid->hid_output_raw_report = hidp_output_raw_report; + /* True if device is blacklisted in drivers/hid/hid-core.c */ + if (hid_ignore(hid)) { + hid_destroy_device(session->hid); + session->hid = NULL; + return -ENODEV; + } + return 0; fault: @@ -1013,7 +1024,7 @@ int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock, if (req->rd_size > 0) { err = hidp_setup_hid(session, req); - if (err) + if (err && err != -ENODEV) goto purge; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a91239dcda41..22e658322845 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -38,6 +38,7 @@ #include <net/bluetooth/l2cap.h> #include <net/bluetooth/smp.h> #include <net/bluetooth/a2mp.h> +#include <net/bluetooth/amp.h> bool disable_ertm; @@ -48,19 +49,19 @@ static LIST_HEAD(chan_list); static DEFINE_RWLOCK(chan_list_lock); static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, - u8 code, u8 ident, u16 dlen, void *data); + u8 code, u8 ident, u16 dlen, void *data); static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, - void *data); + void *data); static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data); -static void l2cap_send_disconn_req(struct l2cap_conn *conn, - struct l2cap_chan *chan, int err); +static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err); static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control, - struct sk_buff_head *skbs, u8 event); + struct sk_buff_head *skbs, u8 event); /* ---- L2CAP channels ---- */ -static struct l2cap_chan *__l2cap_get_chan_by_dcid(struct l2cap_conn *conn, u16 cid) +static struct l2cap_chan *__l2cap_get_chan_by_dcid(struct l2cap_conn *conn, + u16 cid) { struct l2cap_chan *c; @@ -71,7 +72,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_dcid(struct l2cap_conn *conn, u16 return NULL; } -static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn, u16 cid) +static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn, + u16 cid) { struct l2cap_chan *c; @@ -84,7 +86,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn, u16 /* Find channel with given SCID. * Returns locked channel. */ -static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, u16 cid) +static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, + u16 cid) { struct l2cap_chan *c; @@ -97,7 +100,25 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, u16 ci return c; } -static struct l2cap_chan *__l2cap_get_chan_by_ident(struct l2cap_conn *conn, u8 ident) +/* Find channel with given DCID. + * Returns locked channel. + */ +static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, + u16 cid) +{ + struct l2cap_chan *c; + + mutex_lock(&conn->chan_lock); + c = __l2cap_get_chan_by_dcid(conn, cid); + if (c) + l2cap_chan_lock(c); + mutex_unlock(&conn->chan_lock); + + return c; +} + +static struct l2cap_chan *__l2cap_get_chan_by_ident(struct l2cap_conn *conn, + u8 ident) { struct l2cap_chan *c; @@ -108,6 +129,20 @@ static struct l2cap_chan *__l2cap_get_chan_by_ident(struct l2cap_conn *conn, u8 return NULL; } +static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn, + u8 ident) +{ + struct l2cap_chan *c; + + mutex_lock(&conn->chan_lock); + c = __l2cap_get_chan_by_ident(conn, ident); + if (c) + l2cap_chan_lock(c); + mutex_unlock(&conn->chan_lock); + + return c; +} + static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src) { struct l2cap_chan *c; @@ -178,7 +213,7 @@ static u16 l2cap_alloc_cid(struct l2cap_conn *conn) static void __l2cap_state_change(struct l2cap_chan *chan, int state) { BT_DBG("chan %p %s -> %s", chan, state_to_string(chan->state), - state_to_string(state)); + state_to_string(state)); chan->state = state; chan->ops->state_change(chan, state); @@ -361,7 +396,7 @@ static void l2cap_seq_list_append(struct l2cap_seq_list *seq_list, u16 seq) static void l2cap_chan_timeout(struct work_struct *work) { struct l2cap_chan *chan = container_of(work, struct l2cap_chan, - chan_timer.work); + chan_timer.work); struct l2cap_conn *conn = chan->conn; int reason; @@ -373,7 +408,7 @@ static void l2cap_chan_timeout(struct work_struct *work) if (chan->state == BT_CONNECTED || chan->state == BT_CONFIG) reason = ECONNREFUSED; else if (chan->state == BT_CONNECT && - chan->sec_level != BT_SECURITY_SDP) + chan->sec_level != BT_SECURITY_SDP) reason = ECONNREFUSED; else reason = ETIMEDOUT; @@ -455,7 +490,7 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) set_bit(FLAG_FORCE_ACTIVE, &chan->flags); } -static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) +void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) { BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn, __le16_to_cpu(chan->psm), chan->dcid); @@ -504,7 +539,7 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) chan->local_msdu = L2CAP_DEFAULT_MAX_SDU_SIZE; chan->local_sdu_itime = L2CAP_DEFAULT_SDU_ITIME; chan->local_acc_lat = L2CAP_DEFAULT_ACC_LAT; - chan->local_flush_to = L2CAP_DEFAULT_FLUSH_TO; + chan->local_flush_to = L2CAP_EFS_DEFAULT_FLUSH_TO; l2cap_chan_hold(chan); @@ -527,6 +562,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) BT_DBG("chan %p, conn %p, err %d", chan, conn, err); if (conn) { + struct amp_mgr *mgr = conn->hcon->amp_mgr; /* Delete from channel list */ list_del(&chan->list); @@ -536,10 +572,19 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) if (chan->chan_type != L2CAP_CHAN_CONN_FIX_A2MP) hci_conn_put(conn->hcon); + + if (mgr && mgr->bredr_chan == chan) + mgr->bredr_chan = NULL; } - if (chan->ops->teardown) - chan->ops->teardown(chan, err); + if (chan->hs_hchan) { + struct hci_chan *hs_hchan = chan->hs_hchan; + + BT_DBG("chan %p disconnect hs_hchan %p", chan, hs_hchan); + amp_disconnect_logical_link(hs_hchan); + } + + chan->ops->teardown(chan, err); if (test_bit(CONF_NOT_COMPLETE, &chan->conf_state)) return; @@ -573,28 +618,27 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) struct l2cap_conn *conn = chan->conn; struct sock *sk = chan->sk; - BT_DBG("chan %p state %s sk %p", chan, - state_to_string(chan->state), sk); + BT_DBG("chan %p state %s sk %p", chan, state_to_string(chan->state), + sk); switch (chan->state) { case BT_LISTEN: - if (chan->ops->teardown) - chan->ops->teardown(chan, 0); + chan->ops->teardown(chan, 0); break; case BT_CONNECTED: case BT_CONFIG: if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && - conn->hcon->type == ACL_LINK) { + conn->hcon->type == ACL_LINK) { __set_chan_timer(chan, sk->sk_sndtimeo); - l2cap_send_disconn_req(conn, chan, reason); + l2cap_send_disconn_req(chan, reason); } else l2cap_chan_del(chan, reason); break; case BT_CONNECT2: if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && - conn->hcon->type == ACL_LINK) { + conn->hcon->type == ACL_LINK) { struct l2cap_conn_rsp rsp; __u16 result; @@ -609,7 +653,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) rsp.result = cpu_to_le16(result); rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, - sizeof(rsp), &rsp); + sizeof(rsp), &rsp); } l2cap_chan_del(chan, reason); @@ -621,8 +665,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) break; default: - if (chan->ops->teardown) - chan->ops->teardown(chan, 0); + chan->ops->teardown(chan, 0); break; } } @@ -691,7 +734,8 @@ static u8 l2cap_get_ident(struct l2cap_conn *conn) return id; } -static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data) +static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, + void *data) { struct sk_buff *skb = l2cap_build_cmd(conn, code, ident, len, data); u8 flags; @@ -712,16 +756,31 @@ static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, hci_send_acl(conn->hchan, skb, flags); } +static bool __chan_is_moving(struct l2cap_chan *chan) +{ + return chan->move_state != L2CAP_MOVE_STABLE && + chan->move_state != L2CAP_MOVE_WAIT_PREPARE; +} + static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) { struct hci_conn *hcon = chan->conn->hcon; u16 flags; BT_DBG("chan %p, skb %p len %d priority %u", chan, skb, skb->len, - skb->priority); + skb->priority); + + if (chan->hs_hcon && !__chan_is_moving(chan)) { + if (chan->hs_hchan) + hci_send_acl(chan->hs_hchan, skb, ACL_COMPLETE); + else + kfree_skb(skb); + + return; + } if (!test_bit(FLAG_FLUSHABLE, &chan->flags) && - lmp_no_flush_capable(hcon->hdev)) + lmp_no_flush_capable(hcon->hdev)) flags = ACL_START_NO_FLUSH; else flags = ACL_START; @@ -895,6 +954,9 @@ static void l2cap_send_sframe(struct l2cap_chan *chan, if (!control->sframe) return; + if (__chan_is_moving(chan)) + return; + if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state) && !control->poll) control->final = 1; @@ -946,7 +1008,26 @@ static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan) return !test_bit(CONF_CONNECT_PEND, &chan->conf_state); } -static void l2cap_send_conn_req(struct l2cap_chan *chan) +static bool __amp_capable(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + + if (enable_hs && + hci_amp_capable() && + chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED && + conn->fixed_chan_mask & L2CAP_FC_A2MP) + return true; + else + return false; +} + +static bool l2cap_check_efs(struct l2cap_chan *chan) +{ + /* Check EFS parameters */ + return true; +} + +void l2cap_send_conn_req(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; struct l2cap_conn_req req; @@ -961,6 +1042,76 @@ static void l2cap_send_conn_req(struct l2cap_chan *chan) l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_REQ, sizeof(req), &req); } +static void l2cap_send_create_chan_req(struct l2cap_chan *chan, u8 amp_id) +{ + struct l2cap_create_chan_req req; + req.scid = cpu_to_le16(chan->scid); + req.psm = chan->psm; + req.amp_id = amp_id; + + chan->ident = l2cap_get_ident(chan->conn); + + l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_REQ, + sizeof(req), &req); +} + +static void l2cap_move_setup(struct l2cap_chan *chan) +{ + struct sk_buff *skb; + + BT_DBG("chan %p", chan); + + if (chan->mode != L2CAP_MODE_ERTM) + return; + + __clear_retrans_timer(chan); + __clear_monitor_timer(chan); + __clear_ack_timer(chan); + + chan->retry_count = 0; + skb_queue_walk(&chan->tx_q, skb) { + if (bt_cb(skb)->control.retries) + bt_cb(skb)->control.retries = 1; + else + break; + } + + chan->expected_tx_seq = chan->buffer_seq; + + clear_bit(CONN_REJ_ACT, &chan->conn_state); + clear_bit(CONN_SREJ_ACT, &chan->conn_state); + l2cap_seq_list_clear(&chan->retrans_list); + l2cap_seq_list_clear(&chan->srej_list); + skb_queue_purge(&chan->srej_q); + + chan->tx_state = L2CAP_TX_STATE_XMIT; + chan->rx_state = L2CAP_RX_STATE_MOVE; + + set_bit(CONN_REMOTE_BUSY, &chan->conn_state); +} + +static void l2cap_move_done(struct l2cap_chan *chan) +{ + u8 move_role = chan->move_role; + BT_DBG("chan %p", chan); + + chan->move_state = L2CAP_MOVE_STABLE; + chan->move_role = L2CAP_MOVE_ROLE_NONE; + + if (chan->mode != L2CAP_MODE_ERTM) + return; + + switch (move_role) { + case L2CAP_MOVE_ROLE_INITIATOR: + l2cap_tx(chan, NULL, NULL, L2CAP_EV_EXPLICIT_POLL); + chan->rx_state = L2CAP_RX_STATE_WAIT_F; + break; + case L2CAP_MOVE_ROLE_RESPONDER: + chan->rx_state = L2CAP_RX_STATE_WAIT_P; + break; + } +} + static void l2cap_chan_ready(struct l2cap_chan *chan) { /* This clears all conf flags, including CONF_NOT_COMPLETE */ @@ -972,6 +1123,16 @@ static void l2cap_chan_ready(struct l2cap_chan *chan) chan->ops->ready(chan); } +static void l2cap_start_connection(struct l2cap_chan *chan) +{ + if (__amp_capable(chan)) { + BT_DBG("chan %p AMP capable: discover AMPs", chan); + a2mp_discover_amp(chan); + } else { + l2cap_send_conn_req(chan); + } +} + static void l2cap_do_start(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; @@ -986,8 +1147,9 @@ static void l2cap_do_start(struct l2cap_chan *chan) return; if (l2cap_chan_check_security(chan) && - __l2cap_no_conn_pending(chan)) - l2cap_send_conn_req(chan); + __l2cap_no_conn_pending(chan)) { + l2cap_start_connection(chan); + } } else { struct l2cap_info_req req; req.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK); @@ -997,8 +1159,8 @@ static void l2cap_do_start(struct l2cap_chan *chan) schedule_delayed_work(&conn->info_timer, L2CAP_INFO_TIMEOUT); - l2cap_send_cmd(conn, conn->info_ident, - L2CAP_INFO_REQ, sizeof(req), &req); + l2cap_send_cmd(conn, conn->info_ident, L2CAP_INFO_REQ, + sizeof(req), &req); } } @@ -1018,9 +1180,10 @@ static inline int l2cap_mode_supported(__u8 mode, __u32 feat_mask) } } -static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *chan, int err) +static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err) { struct sock *sk = chan->sk; + struct l2cap_conn *conn = chan->conn; struct l2cap_disconn_req req; if (!conn) @@ -1033,14 +1196,14 @@ static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *c } if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { - __l2cap_state_change(chan, BT_DISCONN); + l2cap_state_change(chan, BT_DISCONN); return; } req.dcid = cpu_to_le16(chan->dcid); req.scid = cpu_to_le16(chan->scid); - l2cap_send_cmd(conn, l2cap_get_ident(conn), - L2CAP_DISCONN_REQ, sizeof(req), &req); + l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_DISCONN_REQ, + sizeof(req), &req); lock_sock(sk); __l2cap_state_change(chan, BT_DISCONN); @@ -1069,20 +1232,20 @@ static void l2cap_conn_start(struct l2cap_conn *conn) if (chan->state == BT_CONNECT) { if (!l2cap_chan_check_security(chan) || - !__l2cap_no_conn_pending(chan)) { + !__l2cap_no_conn_pending(chan)) { l2cap_chan_unlock(chan); continue; } if (!l2cap_mode_supported(chan->mode, conn->feat_mask) - && test_bit(CONF_STATE2_DEVICE, + && test_bit(CONF_STATE2_DEVICE, &chan->conf_state)) { l2cap_chan_close(chan, ECONNRESET); l2cap_chan_unlock(chan); continue; } - l2cap_send_conn_req(chan); + l2cap_start_connection(chan); } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; @@ -1094,11 +1257,9 @@ static void l2cap_conn_start(struct l2cap_conn *conn) lock_sock(sk); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { - struct sock *parent = bt_sk(sk)->parent; rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND); rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHOR_PEND); - if (parent) - parent->sk_data_ready(parent, 0); + chan->ops->defer(chan); } else { __l2cap_state_change(chan, BT_CONFIG); @@ -1112,17 +1273,17 @@ static void l2cap_conn_start(struct l2cap_conn *conn) } l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, - sizeof(rsp), &rsp); + sizeof(rsp), &rsp); if (test_bit(CONF_REQ_SENT, &chan->conf_state) || - rsp.result != L2CAP_CR_SUCCESS) { + rsp.result != L2CAP_CR_SUCCESS) { l2cap_chan_unlock(chan); continue; } set_bit(CONF_REQ_SENT, &chan->conf_state); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, buf), buf); + l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; } @@ -1204,8 +1365,6 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) bacpy(&bt_sk(sk)->src, conn->src); bacpy(&bt_sk(sk)->dst, conn->dst); - bt_accept_enqueue(parent, sk); - l2cap_chan_add(conn, chan); l2cap_chan_ready(chan); @@ -1270,7 +1429,7 @@ static void l2cap_conn_unreliable(struct l2cap_conn *conn, int err) list_for_each_entry(chan, &conn->chan_l, list) { if (test_bit(FLAG_FORCE_RELIABLE, &chan->flags)) - __l2cap_chan_set_err(chan, err); + l2cap_chan_set_err(chan, err); } mutex_unlock(&conn->chan_lock); @@ -1279,7 +1438,7 @@ static void l2cap_conn_unreliable(struct l2cap_conn *conn, int err) static void l2cap_info_timeout(struct work_struct *work) { struct l2cap_conn *conn = container_of(work, struct l2cap_conn, - info_timer.work); + info_timer.work); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; conn->info_ident = 0; @@ -1333,7 +1492,7 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) static void security_timeout(struct work_struct *work) { struct l2cap_conn *conn = container_of(work, struct l2cap_conn, - security_timer.work); + security_timer.work); BT_DBG("conn %p", conn); @@ -1355,7 +1514,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status) if (!hchan) return NULL; - conn = kzalloc(sizeof(struct l2cap_conn), GFP_ATOMIC); + conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL); if (!conn) { hci_chan_del(hchan); return NULL; @@ -1367,10 +1526,22 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status) BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan); - if (hcon->hdev->le_mtu && hcon->type == LE_LINK) - conn->mtu = hcon->hdev->le_mtu; - else + switch (hcon->type) { + case AMP_LINK: + conn->mtu = hcon->hdev->block_mtu; + break; + + case LE_LINK: + if (hcon->hdev->le_mtu) { + conn->mtu = hcon->hdev->le_mtu; + break; + } + /* fall through */ + + default: conn->mtu = hcon->hdev->acl_mtu; + break; + } conn->src = &hcon->hdev->bdaddr; conn->dst = &hcon->dst; @@ -1448,7 +1619,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, __u8 auth_type; int err; - BT_DBG("%s -> %s (type %u) psm 0x%2.2x", batostr(src), batostr(dst), + BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", src, dst, dst_type, __le16_to_cpu(psm)); hdev = hci_get_route(dst, src); @@ -1461,7 +1632,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, /* PSM must be odd and lsb of upper byte must be 0 */ if ((__le16_to_cpu(psm) & 0x0101) != 0x0001 && !cid && - chan->chan_type != L2CAP_CHAN_RAW) { + chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; goto done; } @@ -1657,6 +1828,9 @@ static void l2cap_streaming_send(struct l2cap_chan *chan, BT_DBG("chan %p, skbs %p", chan, skbs); + if (__chan_is_moving(chan)) + return; + skb_queue_splice_tail_init(skbs, &chan->tx_q); while (!skb_queue_empty(&chan->tx_q)) { @@ -1699,6 +1873,9 @@ static int l2cap_ertm_send(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return 0; + if (__chan_is_moving(chan)) + return 0; + while (chan->tx_send_head && chan->unacked_frames < chan->remote_tx_win && chan->tx_state == L2CAP_TX_STATE_XMIT) { @@ -1764,13 +1941,16 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return; + if (__chan_is_moving(chan)) + return; + while (chan->retrans_list.head != L2CAP_SEQ_LIST_CLEAR) { seq = l2cap_seq_list_pop(&chan->retrans_list); skb = l2cap_ertm_seq_in_queue(&chan->tx_q, seq); if (!skb) { BT_DBG("Error: Can't retransmit seq %d, frame missing", - seq); + seq); continue; } @@ -1780,7 +1960,7 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan) if (chan->max_tx != 0 && bt_cb(skb)->control.retries > chan->max_tx) { BT_DBG("Retry limit exceeded (%d)", chan->max_tx); - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); l2cap_seq_list_clear(&chan->retrans_list); break; } @@ -1795,9 +1975,9 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan) /* Cloned sk_buffs are read-only, so we need a * writeable copy */ - tx_skb = skb_copy(skb, GFP_ATOMIC); + tx_skb = skb_copy(skb, GFP_KERNEL); } else { - tx_skb = skb_clone(skb, GFP_ATOMIC); + tx_skb = skb_clone(skb, GFP_KERNEL); } if (!tx_skb) { @@ -1855,7 +2035,7 @@ static void l2cap_retransmit_all(struct l2cap_chan *chan, if (chan->unacked_frames) { skb_queue_walk(&chan->tx_q, skb) { if (bt_cb(skb)->control.txseq == control->reqseq || - skb == chan->tx_send_head) + skb == chan->tx_send_head) break; } @@ -2106,7 +2286,9 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, /* PDU size is derived from the HCI MTU */ pdu_len = chan->conn->mtu; - pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); + /* Constrain PDU size for BR/EDR connections */ + if (!chan->hs_hcon) + pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); /* Adjust for largest possible L2CAP overhead. */ if (chan->fcs) @@ -2156,7 +2338,7 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, } int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, - u32 priority) + u32 priority) { struct sk_buff *skb; int err; @@ -2484,7 +2666,7 @@ static void l2cap_tx_state_wait_f(struct l2cap_chan *chan, __set_monitor_timer(chan); chan->retry_count++; } else { - l2cap_send_disconn_req(chan->conn, chan, ECONNABORTED); + l2cap_send_disconn_req(chan, ECONNABORTED); } break; default: @@ -2543,7 +2725,7 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) /* Don't send frame to the socket it came from */ if (skb->sk == sk) continue; - nskb = skb_clone(skb, GFP_ATOMIC); + nskb = skb_clone(skb, GFP_KERNEL); if (!nskb) continue; @@ -2569,7 +2751,7 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, len = L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE + dlen; count = min_t(unsigned int, conn->mtu, len); - skb = bt_skb_alloc(count, GFP_ATOMIC); + skb = bt_skb_alloc(count, GFP_KERNEL); if (!skb) return NULL; @@ -2599,7 +2781,7 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, while (len) { count = min_t(unsigned int, conn->mtu, len); - *frag = bt_skb_alloc(count, GFP_ATOMIC); + *frag = bt_skb_alloc(count, GFP_KERNEL); if (!*frag) goto fail; @@ -2618,7 +2800,8 @@ fail: return NULL; } -static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen, unsigned long *val) +static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen, + unsigned long *val) { struct l2cap_conf_opt *opt = *ptr; int len; @@ -2692,7 +2875,7 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan) efs.msdu = cpu_to_le16(chan->local_msdu); efs.sdu_itime = cpu_to_le32(chan->local_sdu_itime); efs.acc_lat = __constant_cpu_to_le32(L2CAP_DEFAULT_ACC_LAT); - efs.flush_to = __constant_cpu_to_le32(L2CAP_DEFAULT_FLUSH_TO); + efs.flush_to = __constant_cpu_to_le32(L2CAP_EFS_DEFAULT_FLUSH_TO); break; case L2CAP_MODE_STREAMING: @@ -2709,7 +2892,7 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan) } l2cap_add_conf_opt(ptr, L2CAP_CONF_EFS, sizeof(efs), - (unsigned long) &efs); + (unsigned long) &efs); } static void l2cap_ack_timeout(struct work_struct *work) @@ -2749,6 +2932,11 @@ int l2cap_ertm_init(struct l2cap_chan *chan) skb_queue_head_init(&chan->tx_q); + chan->local_amp_id = 0; + chan->move_id = 0; + chan->move_state = L2CAP_MOVE_STABLE; + chan->move_role = L2CAP_MOVE_ROLE_NONE; + if (chan->mode != L2CAP_MODE_ERTM) return 0; @@ -2795,16 +2983,54 @@ static inline bool __l2cap_efs_supported(struct l2cap_chan *chan) return enable_hs && chan->conn->feat_mask & L2CAP_FEAT_EXT_FLOW; } +static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan, + struct l2cap_conf_rfc *rfc) +{ + if (chan->local_amp_id && chan->hs_hcon) { + u64 ertm_to = chan->hs_hcon->hdev->amp_be_flush_to; + + /* Class 1 devices have must have ERTM timeouts + * exceeding the Link Supervision Timeout. The + * default Link Supervision Timeout for AMP + * controllers is 10 seconds. + * + * Class 1 devices use 0xffffffff for their + * best-effort flush timeout, so the clamping logic + * will result in a timeout that meets the above + * requirement. ERTM timeouts are 16-bit values, so + * the maximum timeout is 65.535 seconds. + */ + + /* Convert timeout to milliseconds and round */ + ertm_to = DIV_ROUND_UP_ULL(ertm_to, 1000); + + /* This is the recommended formula for class 2 devices + * that start ERTM timers when packets are sent to the + * controller. + */ + ertm_to = 3 * ertm_to + 500; + + if (ertm_to > 0xffff) + ertm_to = 0xffff; + + rfc->retrans_timeout = cpu_to_le16((u16) ertm_to); + rfc->monitor_timeout = rfc->retrans_timeout; + } else { + rfc->retrans_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc->monitor_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); + } +} + static inline void l2cap_txwin_setup(struct l2cap_chan *chan) { if (chan->tx_win > L2CAP_DEFAULT_TX_WINDOW && - __l2cap_ews_supported(chan)) { + __l2cap_ews_supported(chan)) { /* use extended control field */ set_bit(FLAG_EXT_CTRL, &chan->flags); chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW; } else { chan->tx_win = min_t(u16, chan->tx_win, - L2CAP_DEFAULT_TX_WINDOW); + L2CAP_DEFAULT_TX_WINDOW); chan->tx_win_max = L2CAP_DEFAULT_TX_WINDOW; } chan->ack_win = chan->tx_win; @@ -2844,7 +3070,7 @@ done: switch (chan->mode) { case L2CAP_MODE_BASIC: if (!(chan->conn->feat_mask & L2CAP_FEAT_ERTM) && - !(chan->conn->feat_mask & L2CAP_FEAT_STREAMING)) + !(chan->conn->feat_mask & L2CAP_FEAT_STREAMING)) break; rfc.mode = L2CAP_MODE_BASIC; @@ -2855,44 +3081,42 @@ done: rfc.max_pdu_size = 0; l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), - (unsigned long) &rfc); + (unsigned long) &rfc); break; case L2CAP_MODE_ERTM: rfc.mode = L2CAP_MODE_ERTM; rfc.max_transmit = chan->max_tx; - rfc.retrans_timeout = 0; - rfc.monitor_timeout = 0; + + __l2cap_set_ertm_timeouts(chan, &rfc); size = min_t(u16, L2CAP_DEFAULT_MAX_PDU_SIZE, chan->conn->mtu - - L2CAP_EXT_HDR_SIZE - - L2CAP_SDULEN_SIZE - - L2CAP_FCS_SIZE); + L2CAP_EXT_HDR_SIZE - L2CAP_SDULEN_SIZE - + L2CAP_FCS_SIZE); rfc.max_pdu_size = cpu_to_le16(size); l2cap_txwin_setup(chan); rfc.txwin_size = min_t(u16, chan->tx_win, - L2CAP_DEFAULT_TX_WINDOW); + L2CAP_DEFAULT_TX_WINDOW); l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), - (unsigned long) &rfc); + (unsigned long) &rfc); if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) l2cap_add_opt_efs(&ptr, chan); - if (!(chan->conn->feat_mask & L2CAP_FEAT_FCS)) - break; - - if (chan->fcs == L2CAP_FCS_NONE || - test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) { - chan->fcs = L2CAP_FCS_NONE; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, chan->fcs); - } - if (test_bit(FLAG_EXT_CTRL, &chan->flags)) l2cap_add_conf_opt(&ptr, L2CAP_CONF_EWS, 2, - chan->tx_win); + chan->tx_win); + + if (chan->conn->feat_mask & L2CAP_FEAT_FCS) + if (chan->fcs == L2CAP_FCS_NONE || + test_bit(CONF_RECV_NO_FCS, &chan->conf_state)) { + chan->fcs = L2CAP_FCS_NONE; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, + chan->fcs); + } break; case L2CAP_MODE_STREAMING: @@ -2904,25 +3128,23 @@ done: rfc.monitor_timeout = 0; size = min_t(u16, L2CAP_DEFAULT_MAX_PDU_SIZE, chan->conn->mtu - - L2CAP_EXT_HDR_SIZE - - L2CAP_SDULEN_SIZE - - L2CAP_FCS_SIZE); + L2CAP_EXT_HDR_SIZE - L2CAP_SDULEN_SIZE - + L2CAP_FCS_SIZE); rfc.max_pdu_size = cpu_to_le16(size); l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), - (unsigned long) &rfc); + (unsigned long) &rfc); if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) l2cap_add_opt_efs(&ptr, chan); - if (!(chan->conn->feat_mask & L2CAP_FEAT_FCS)) - break; - - if (chan->fcs == L2CAP_FCS_NONE || - test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) { - chan->fcs = L2CAP_FCS_NONE; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, chan->fcs); - } + if (chan->conn->feat_mask & L2CAP_FEAT_FCS) + if (chan->fcs == L2CAP_FCS_NONE || + test_bit(CONF_RECV_NO_FCS, &chan->conf_state)) { + chan->fcs = L2CAP_FCS_NONE; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, + chan->fcs); + } break; } @@ -2974,7 +3196,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data) case L2CAP_CONF_FCS: if (val == L2CAP_FCS_NONE) - set_bit(CONF_NO_FCS_RECV, &chan->conf_state); + set_bit(CONF_RECV_NO_FCS, &chan->conf_state); break; case L2CAP_CONF_EFS: @@ -3011,7 +3233,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data) case L2CAP_MODE_ERTM: if (!test_bit(CONF_STATE2_DEVICE, &chan->conf_state)) { chan->mode = l2cap_select_mode(rfc.mode, - chan->conn->feat_mask); + chan->conn->feat_mask); break; } @@ -3036,8 +3258,8 @@ done: if (chan->num_conf_rsp == 1) return -ECONNREFUSED; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), + (unsigned long) &rfc); } if (result == L2CAP_CONF_SUCCESS) { @@ -3054,8 +3276,8 @@ done: if (remote_efs) { if (chan->local_stype != L2CAP_SERV_NOTRAFIC && - efs.stype != L2CAP_SERV_NOTRAFIC && - efs.stype != chan->local_stype) { + efs.stype != L2CAP_SERV_NOTRAFIC && + efs.stype != chan->local_stype) { result = L2CAP_CONF_UNACCEPT; @@ -3063,8 +3285,8 @@ done: return -ECONNREFUSED; l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, - sizeof(efs), - (unsigned long) &efs); + sizeof(efs), + (unsigned long) &efs); } else { /* Send PENDING Conf Rsp */ result = L2CAP_CONF_PENDING; @@ -3087,51 +3309,45 @@ done: chan->remote_max_tx = rfc.max_transmit; size = min_t(u16, le16_to_cpu(rfc.max_pdu_size), - chan->conn->mtu - - L2CAP_EXT_HDR_SIZE - - L2CAP_SDULEN_SIZE - - L2CAP_FCS_SIZE); + chan->conn->mtu - L2CAP_EXT_HDR_SIZE - + L2CAP_SDULEN_SIZE - L2CAP_FCS_SIZE); rfc.max_pdu_size = cpu_to_le16(size); chan->remote_mps = size; - rfc.retrans_timeout = - __constant_cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); - rfc.monitor_timeout = - __constant_cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); + __l2cap_set_ertm_timeouts(chan, &rfc); set_bit(CONF_MODE_DONE, &chan->conf_state); l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc); + sizeof(rfc), (unsigned long) &rfc); if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->remote_id = efs.id; chan->remote_stype = efs.stype; chan->remote_msdu = le16_to_cpu(efs.msdu); chan->remote_flush_to = - le32_to_cpu(efs.flush_to); + le32_to_cpu(efs.flush_to); chan->remote_acc_lat = - le32_to_cpu(efs.acc_lat); + le32_to_cpu(efs.acc_lat); chan->remote_sdu_itime = le32_to_cpu(efs.sdu_itime); l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, - sizeof(efs), (unsigned long) &efs); + sizeof(efs), + (unsigned long) &efs); } break; case L2CAP_MODE_STREAMING: size = min_t(u16, le16_to_cpu(rfc.max_pdu_size), - chan->conn->mtu - - L2CAP_EXT_HDR_SIZE - - L2CAP_SDULEN_SIZE - - L2CAP_FCS_SIZE); + chan->conn->mtu - L2CAP_EXT_HDR_SIZE - + L2CAP_SDULEN_SIZE - L2CAP_FCS_SIZE); rfc.max_pdu_size = cpu_to_le16(size); chan->remote_mps = size; set_bit(CONF_MODE_DONE, &chan->conf_state); - l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), + (unsigned long) &rfc); break; @@ -3152,7 +3368,8 @@ done: return ptr - data; } -static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, void *data, u16 *result) +static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, + void *data, u16 *result) { struct l2cap_conf_req *req = data; void *ptr = req->data; @@ -3179,7 +3396,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi case L2CAP_CONF_FLUSH_TO: chan->flush_to = val; l2cap_add_conf_opt(&ptr, L2CAP_CONF_FLUSH_TO, - 2, chan->flush_to); + 2, chan->flush_to); break; case L2CAP_CONF_RFC: @@ -3187,13 +3404,13 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi memcpy(&rfc, (void *)val, olen); if (test_bit(CONF_STATE2_DEVICE, &chan->conf_state) && - rfc.mode != chan->mode) + rfc.mode != chan->mode) return -ECONNREFUSED; chan->fcs = 0; l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc); + sizeof(rfc), (unsigned long) &rfc); break; case L2CAP_CONF_EWS: @@ -3207,12 +3424,19 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi memcpy(&efs, (void *)val, olen); if (chan->local_stype != L2CAP_SERV_NOTRAFIC && - efs.stype != L2CAP_SERV_NOTRAFIC && - efs.stype != chan->local_stype) + efs.stype != L2CAP_SERV_NOTRAFIC && + efs.stype != chan->local_stype) return -ECONNREFUSED; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, - sizeof(efs), (unsigned long) &efs); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), + (unsigned long) &efs); + break; + + case L2CAP_CONF_FCS: + if (*result == L2CAP_CONF_PENDING) + if (val == L2CAP_FCS_NONE) + set_bit(CONF_RECV_NO_FCS, + &chan->conf_state); break; } } @@ -3235,10 +3459,10 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->local_msdu = le16_to_cpu(efs.msdu); chan->local_sdu_itime = - le32_to_cpu(efs.sdu_itime); + le32_to_cpu(efs.sdu_itime); chan->local_acc_lat = le32_to_cpu(efs.acc_lat); chan->local_flush_to = - le32_to_cpu(efs.flush_to); + le32_to_cpu(efs.flush_to); } break; @@ -3253,7 +3477,8 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi return ptr - data; } -static int l2cap_build_conf_rsp(struct l2cap_chan *chan, void *data, u16 result, u16 flags) +static int l2cap_build_conf_rsp(struct l2cap_chan *chan, void *data, + u16 result, u16 flags) { struct l2cap_conf_rsp *rsp = data; void *ptr = rsp->data; @@ -3272,19 +3497,27 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) struct l2cap_conn_rsp rsp; struct l2cap_conn *conn = chan->conn; u8 buf[128]; + u8 rsp_code; rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); - l2cap_send_cmd(conn, chan->ident, - L2CAP_CONN_RSP, sizeof(rsp), &rsp); + + if (chan->hs_hcon) + rsp_code = L2CAP_CREATE_CHAN_RSP; + else + rsp_code = L2CAP_CONN_RSP; + + BT_DBG("chan %p rsp_code %u", chan, rsp_code); + + l2cap_send_cmd(conn, chan->ident, rsp_code, sizeof(rsp), &rsp); if (test_and_set_bit(CONF_REQ_SENT, &chan->conf_state)) return; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, buf), buf); + l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; } @@ -3339,7 +3572,8 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) } } -static inline int l2cap_command_rej(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static inline int l2cap_command_rej(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) { struct l2cap_cmd_rej_unk *rej = (struct l2cap_cmd_rej_unk *) data; @@ -3347,7 +3581,7 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, struct l2cap_cmd_hd return 0; if ((conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) && - cmd->ident == conn->info_ident) { + cmd->ident == conn->info_ident) { cancel_delayed_work(&conn->info_timer); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; @@ -3359,7 +3593,9 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, struct l2cap_cmd_hd return 0; } -static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, + u8 *data, u8 rsp_code, u8 amp_id) { struct l2cap_conn_req *req = (struct l2cap_conn_req *) data; struct l2cap_conn_rsp rsp; @@ -3386,7 +3622,7 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd /* Check if the ACL is secure enough (if not SDP) */ if (psm != __constant_cpu_to_le16(L2CAP_PSM_SDP) && - !hci_conn_check_link_mode(conn->hcon)) { + !hci_conn_check_link_mode(conn->hcon)) { conn->disc_reason = HCI_ERROR_AUTH_FAILURE; result = L2CAP_CR_SEC_BLOCK; goto response; @@ -3410,8 +3646,7 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd bacpy(&bt_sk(sk)->dst, conn->dst); chan->psm = psm; chan->dcid = scid; - - bt_accept_enqueue(parent, sk); + chan->local_amp_id = amp_id; __l2cap_chan_add(conn, chan); @@ -3427,10 +3662,19 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd __l2cap_state_change(chan, BT_CONNECT2); result = L2CAP_CR_PEND; status = L2CAP_CS_AUTHOR_PEND; - parent->sk_data_ready(parent, 0); + chan->ops->defer(chan); } else { - __l2cap_state_change(chan, BT_CONFIG); - result = L2CAP_CR_SUCCESS; + /* Force pending result for AMP controllers. + * The connection will succeed after the + * physical link is up. + */ + if (amp_id) { + __l2cap_state_change(chan, BT_CONNECT2); + result = L2CAP_CR_PEND; + } else { + __l2cap_state_change(chan, BT_CONFIG); + result = L2CAP_CR_SUCCESS; + } status = L2CAP_CS_NO_INFO; } } else { @@ -3453,7 +3697,7 @@ sendresp: rsp.dcid = cpu_to_le16(dcid); rsp.result = cpu_to_le16(result); rsp.status = cpu_to_le16(status); - l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); + l2cap_send_cmd(conn, cmd->ident, rsp_code, sizeof(rsp), &rsp); if (result == L2CAP_CR_PEND && status == L2CAP_CS_NO_INFO) { struct l2cap_info_req info; @@ -3464,23 +3708,42 @@ sendresp: schedule_delayed_work(&conn->info_timer, L2CAP_INFO_TIMEOUT); - l2cap_send_cmd(conn, conn->info_ident, - L2CAP_INFO_REQ, sizeof(info), &info); + l2cap_send_cmd(conn, conn->info_ident, L2CAP_INFO_REQ, + sizeof(info), &info); } if (chan && !test_bit(CONF_REQ_SENT, &chan->conf_state) && - result == L2CAP_CR_SUCCESS) { + result == L2CAP_CR_SUCCESS) { u8 buf[128]; set_bit(CONF_REQ_SENT, &chan->conf_state); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, buf), buf); + l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; } + return chan; +} + +static int l2cap_connect_req(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) +{ + struct hci_dev *hdev = conn->hcon->hdev; + struct hci_conn *hcon = conn->hcon; + + hci_dev_lock(hdev); + if (test_bit(HCI_MGMT, &hdev->dev_flags) && + !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags)) + mgmt_device_connected(hdev, &hcon->dst, hcon->type, + hcon->dst_type, 0, NULL, 0, + hcon->dev_class); + hci_dev_unlock(hdev); + + l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0); return 0; } -static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static int l2cap_connect_create_rsp(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) { struct l2cap_conn_rsp *rsp = (struct l2cap_conn_rsp *) data; u16 scid, dcid, result, status; @@ -3494,7 +3757,7 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd status = __le16_to_cpu(rsp->status); BT_DBG("dcid 0x%4.4x scid 0x%4.4x result 0x%2.2x status 0x%2.2x", - dcid, scid, result, status); + dcid, scid, result, status); mutex_lock(&conn->chan_lock); @@ -3527,7 +3790,7 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd break; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, req), req); + l2cap_build_conf_req(chan, req), req); chan->num_conf_req++; break; @@ -3555,11 +3818,29 @@ static inline void set_default_fcs(struct l2cap_chan *chan) */ if (chan->mode != L2CAP_MODE_ERTM && chan->mode != L2CAP_MODE_STREAMING) chan->fcs = L2CAP_FCS_NONE; - else if (!test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) + else if (!test_bit(CONF_RECV_NO_FCS, &chan->conf_state)) chan->fcs = L2CAP_FCS_CRC16; } -static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) +static void l2cap_send_efs_conf_rsp(struct l2cap_chan *chan, void *data, + u8 ident, u16 flags) +{ + struct l2cap_conn *conn = chan->conn; + + BT_DBG("conn %p chan %p ident %d flags 0x%4.4x", conn, chan, ident, + flags); + + clear_bit(CONF_LOC_CONF_PEND, &chan->conf_state); + set_bit(CONF_OUTPUT_DONE, &chan->conf_state); + + l2cap_send_cmd(conn, ident, L2CAP_CONF_RSP, + l2cap_build_conf_rsp(chan, data, + L2CAP_CONF_SUCCESS, flags), data); +} + +static inline int l2cap_config_req(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) { struct l2cap_conf_req *req = (struct l2cap_conf_req *) data; u16 dcid, flags; @@ -3584,7 +3865,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr rej.dcid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ, - sizeof(rej), &rej); + sizeof(rej), &rej); goto unlock; } @@ -3592,8 +3873,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr len = cmd_len - sizeof(*req); if (len < 0 || chan->conf_len + len > sizeof(chan->conf_req)) { l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, - l2cap_build_conf_rsp(chan, rsp, - L2CAP_CONF_REJECT, flags), rsp); + l2cap_build_conf_rsp(chan, rsp, + L2CAP_CONF_REJECT, flags), rsp); goto unlock; } @@ -3604,18 +3885,19 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (flags & L2CAP_CONF_FLAG_CONTINUATION) { /* Incomplete config. Send empty response. */ l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, - l2cap_build_conf_rsp(chan, rsp, - L2CAP_CONF_SUCCESS, flags), rsp); + l2cap_build_conf_rsp(chan, rsp, + L2CAP_CONF_SUCCESS, flags), rsp); goto unlock; } /* Complete config. */ len = l2cap_parse_conf_req(chan, rsp); if (len < 0) { - l2cap_send_disconn_req(conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); goto unlock; } + chan->ident = cmd->ident; l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, len, rsp); chan->num_conf_rsp++; @@ -3633,7 +3915,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr err = l2cap_ertm_init(chan); if (err < 0) - l2cap_send_disconn_req(chan->conn, chan, -err); + l2cap_send_disconn_req(chan, -err); else l2cap_chan_ready(chan); @@ -3643,23 +3925,22 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (!test_and_set_bit(CONF_REQ_SENT, &chan->conf_state)) { u8 buf[64]; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, buf), buf); + l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; } /* Got Conf Rsp PENDING from remote side and asume we sent Conf Rsp PENDING in the code above */ if (test_bit(CONF_REM_CONF_PEND, &chan->conf_state) && - test_bit(CONF_LOC_CONF_PEND, &chan->conf_state)) { + test_bit(CONF_LOC_CONF_PEND, &chan->conf_state)) { /* check compatibility */ - clear_bit(CONF_LOC_CONF_PEND, &chan->conf_state); - set_bit(CONF_OUTPUT_DONE, &chan->conf_state); - - l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, - l2cap_build_conf_rsp(chan, rsp, - L2CAP_CONF_SUCCESS, flags), rsp); + /* Send rsp for BR/EDR channel */ + if (!chan->hs_hcon) + l2cap_send_efs_conf_rsp(chan, rsp, cmd->ident, flags); + else + chan->ident = cmd->ident; } unlock: @@ -3667,7 +3948,8 @@ unlock: return err; } -static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static inline int l2cap_config_rsp(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) { struct l2cap_conf_rsp *rsp = (struct l2cap_conf_rsp *)data; u16 scid, flags, result; @@ -3699,20 +3981,21 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr char buf[64]; len = l2cap_parse_conf_rsp(chan, rsp->data, len, - buf, &result); + buf, &result); if (len < 0) { - l2cap_send_disconn_req(conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); goto done; } - /* check compatibility */ - - clear_bit(CONF_LOC_CONF_PEND, &chan->conf_state); - set_bit(CONF_OUTPUT_DONE, &chan->conf_state); - - l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, - l2cap_build_conf_rsp(chan, buf, - L2CAP_CONF_SUCCESS, 0x0000), buf); + if (!chan->hs_hcon) { + l2cap_send_efs_conf_rsp(chan, buf, cmd->ident, + 0); + } else { + if (l2cap_check_efs(chan)) { + amp_create_logical_link(chan); + chan->ident = cmd->ident; + } + } } goto done; @@ -3721,21 +4004,21 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr char req[64]; if (len > sizeof(req) - sizeof(struct l2cap_conf_req)) { - l2cap_send_disconn_req(conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); goto done; } /* throw out any old stored conf requests */ result = L2CAP_CONF_SUCCESS; len = l2cap_parse_conf_rsp(chan, rsp->data, len, - req, &result); + req, &result); if (len < 0) { - l2cap_send_disconn_req(conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); goto done; } l2cap_send_cmd(conn, l2cap_get_ident(conn), - L2CAP_CONF_REQ, len, req); + L2CAP_CONF_REQ, len, req); chan->num_conf_req++; if (result != L2CAP_CONF_SUCCESS) goto done; @@ -3746,7 +4029,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr l2cap_chan_set_err(chan, ECONNRESET); __set_chan_timer(chan, L2CAP_DISC_REJ_TIMEOUT); - l2cap_send_disconn_req(conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); goto done; } @@ -3763,7 +4046,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr err = l2cap_ertm_init(chan); if (err < 0) - l2cap_send_disconn_req(chan->conn, chan, -err); + l2cap_send_disconn_req(chan, -err); else l2cap_chan_ready(chan); } @@ -3773,7 +4056,8 @@ done: return err; } -static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static inline int l2cap_disconnect_req(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) { struct l2cap_disconn_req *req = (struct l2cap_disconn_req *) data; struct l2cap_disconn_rsp rsp; @@ -3819,7 +4103,8 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd return 0; } -static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) { struct l2cap_disconn_rsp *rsp = (struct l2cap_disconn_rsp *) data; u16 dcid, scid; @@ -3853,7 +4138,8 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd return 0; } -static inline int l2cap_information_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static inline int l2cap_information_req(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) { struct l2cap_info_req *req = (struct l2cap_info_req *) data; u16 type; @@ -3870,14 +4156,14 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, struct l2cap_cm rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS); if (!disable_ertm) feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING - | L2CAP_FEAT_FCS; + | L2CAP_FEAT_FCS; if (enable_hs) feat_mask |= L2CAP_FEAT_EXT_FLOW - | L2CAP_FEAT_EXT_WINDOW; + | L2CAP_FEAT_EXT_WINDOW; put_unaligned_le32(feat_mask, rsp->data); - l2cap_send_cmd(conn, cmd->ident, - L2CAP_INFO_RSP, sizeof(buf), buf); + l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), + buf); } else if (type == L2CAP_IT_FIXED_CHAN) { u8 buf[12]; struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf; @@ -3890,20 +4176,21 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, struct l2cap_cm rsp->type = __constant_cpu_to_le16(L2CAP_IT_FIXED_CHAN); rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS); memcpy(rsp->data, l2cap_fixed_chan, sizeof(l2cap_fixed_chan)); - l2cap_send_cmd(conn, cmd->ident, - L2CAP_INFO_RSP, sizeof(buf), buf); + l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), + buf); } else { struct l2cap_info_rsp rsp; rsp.type = cpu_to_le16(type); rsp.result = __constant_cpu_to_le16(L2CAP_IR_NOTSUPP); - l2cap_send_cmd(conn, cmd->ident, - L2CAP_INFO_RSP, sizeof(rsp), &rsp); + l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(rsp), + &rsp); } return 0; } -static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) +static inline int l2cap_information_rsp(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u8 *data) { struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) data; u16 type, result; @@ -3915,7 +4202,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm /* L2CAP Info req/rsp are unbound to channels, add extra checks */ if (cmd->ident != conn->info_ident || - conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) + conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) return 0; cancel_delayed_work(&conn->info_timer); @@ -3940,7 +4227,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm conn->info_ident = l2cap_get_ident(conn); l2cap_send_cmd(conn, conn->info_ident, - L2CAP_INFO_REQ, sizeof(req), &req); + L2CAP_INFO_REQ, sizeof(req), &req); } else { conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; conn->info_ident = 0; @@ -3961,12 +4248,14 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm return 0; } -static inline int l2cap_create_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u16 cmd_len, - void *data) +static int l2cap_create_channel_req(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, void *data) { struct l2cap_create_chan_req *req = data; struct l2cap_create_chan_rsp rsp; + struct l2cap_chan *chan; + struct hci_dev *hdev; u16 psm, scid; if (cmd_len != sizeof(*req)) @@ -3980,56 +4269,119 @@ static inline int l2cap_create_channel_req(struct l2cap_conn *conn, BT_DBG("psm 0x%2.2x, scid 0x%4.4x, amp_id %d", psm, scid, req->amp_id); - /* Placeholder: Always reject */ + /* For controller id 0 make BR/EDR connection */ + if (req->amp_id == HCI_BREDR_ID) { + l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, + req->amp_id); + return 0; + } + + /* Validate AMP controller id */ + hdev = hci_dev_get(req->amp_id); + if (!hdev) + goto error; + + if (hdev->dev_type != HCI_AMP || !test_bit(HCI_UP, &hdev->flags)) { + hci_dev_put(hdev); + goto error; + } + + chan = l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, + req->amp_id); + if (chan) { + struct amp_mgr *mgr = conn->hcon->amp_mgr; + struct hci_conn *hs_hcon; + + hs_hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, conn->dst); + if (!hs_hcon) { + hci_dev_put(hdev); + return -EFAULT; + } + + BT_DBG("mgr %p bredr_chan %p hs_hcon %p", mgr, chan, hs_hcon); + + mgr->bredr_chan = chan; + chan->hs_hcon = hs_hcon; + chan->fcs = L2CAP_FCS_NONE; + conn->mtu = hdev->block_mtu; + } + + hci_dev_put(hdev); + + return 0; + +error: rsp.dcid = 0; rsp.scid = cpu_to_le16(scid); - rsp.result = __constant_cpu_to_le16(L2CAP_CR_NO_MEM); + rsp.result = __constant_cpu_to_le16(L2CAP_CR_BAD_AMP); rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); l2cap_send_cmd(conn, cmd->ident, L2CAP_CREATE_CHAN_RSP, sizeof(rsp), &rsp); - return 0; + return -EFAULT; } -static inline int l2cap_create_channel_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, void *data) +static void l2cap_send_move_chan_req(struct l2cap_chan *chan, u8 dest_amp_id) { - BT_DBG("conn %p", conn); + struct l2cap_move_chan_req req; + u8 ident; - return l2cap_connect_rsp(conn, cmd, data); + BT_DBG("chan %p, dest_amp_id %d", chan, dest_amp_id); + + ident = l2cap_get_ident(chan->conn); + chan->ident = ident; + + req.icid = cpu_to_le16(chan->scid); + req.dest_amp_id = dest_amp_id; + + l2cap_send_cmd(chan->conn, ident, L2CAP_MOVE_CHAN_REQ, sizeof(req), + &req); + + __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); } -static void l2cap_send_move_chan_rsp(struct l2cap_conn *conn, u8 ident, - u16 icid, u16 result) +static void l2cap_send_move_chan_rsp(struct l2cap_chan *chan, u16 result) { struct l2cap_move_chan_rsp rsp; - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); + BT_DBG("chan %p, result 0x%4.4x", chan, result); - rsp.icid = cpu_to_le16(icid); + rsp.icid = cpu_to_le16(chan->dcid); rsp.result = cpu_to_le16(result); - l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_RSP, sizeof(rsp), &rsp); + l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_RSP, + sizeof(rsp), &rsp); } -static void l2cap_send_move_chan_cfm(struct l2cap_conn *conn, - struct l2cap_chan *chan, - u16 icid, u16 result) +static void l2cap_send_move_chan_cfm(struct l2cap_chan *chan, u16 result) { struct l2cap_move_chan_cfm cfm; - u8 ident; - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); + BT_DBG("chan %p, result 0x%4.4x", chan, result); - ident = l2cap_get_ident(conn); - if (chan) - chan->ident = ident; + chan->ident = l2cap_get_ident(chan->conn); - cfm.icid = cpu_to_le16(icid); + cfm.icid = cpu_to_le16(chan->scid); cfm.result = cpu_to_le16(result); - l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_CFM, sizeof(cfm), &cfm); + l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_CFM, + sizeof(cfm), &cfm); + + __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); +} + +static void l2cap_send_move_chan_cfm_icid(struct l2cap_conn *conn, u16 icid) +{ + struct l2cap_move_chan_cfm cfm; + + BT_DBG("conn %p, icid 0x%4.4x", conn, icid); + + cfm.icid = cpu_to_le16(icid); + cfm.result = __constant_cpu_to_le16(L2CAP_MC_UNCONFIRMED); + + l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_MOVE_CHAN_CFM, + sizeof(cfm), &cfm); } static void l2cap_send_move_chan_cfm_rsp(struct l2cap_conn *conn, u8 ident, @@ -4043,11 +4395,289 @@ static void l2cap_send_move_chan_cfm_rsp(struct l2cap_conn *conn, u8 ident, l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_CFM_RSP, sizeof(rsp), &rsp); } +static void __release_logical_link(struct l2cap_chan *chan) +{ + chan->hs_hchan = NULL; + chan->hs_hcon = NULL; + + /* Placeholder - release the logical link */ +} + +static void l2cap_logical_fail(struct l2cap_chan *chan) +{ + /* Logical link setup failed */ + if (chan->state != BT_CONNECTED) { + /* Create channel failure, disconnect */ + l2cap_send_disconn_req(chan, ECONNRESET); + return; + } + + switch (chan->move_role) { + case L2CAP_MOVE_ROLE_RESPONDER: + l2cap_move_done(chan); + l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_SUPP); + break; + case L2CAP_MOVE_ROLE_INITIATOR: + if (chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_COMP || + chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_CFM) { + /* Remote has only sent pending or + * success responses, clean up + */ + l2cap_move_done(chan); + } + + /* Other amp move states imply that the move + * has already aborted + */ + l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); + break; + } +} + +static void l2cap_logical_finish_create(struct l2cap_chan *chan, + struct hci_chan *hchan) +{ + struct l2cap_conf_rsp rsp; + + chan->hs_hchan = hchan; + chan->hs_hcon->l2cap_data = chan->conn; + + l2cap_send_efs_conf_rsp(chan, &rsp, chan->ident, 0); + + if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { + int err; + + set_default_fcs(chan); + + err = l2cap_ertm_init(chan); + if (err < 0) + l2cap_send_disconn_req(chan, -err); + else + l2cap_chan_ready(chan); + } +} + +static void l2cap_logical_finish_move(struct l2cap_chan *chan, + struct hci_chan *hchan) +{ + chan->hs_hcon = hchan->conn; + chan->hs_hcon->l2cap_data = chan->conn; + + BT_DBG("move_state %d", chan->move_state); + + switch (chan->move_state) { + case L2CAP_MOVE_WAIT_LOGICAL_COMP: + /* Move confirm will be sent after a success + * response is received + */ + chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; + break; + case L2CAP_MOVE_WAIT_LOGICAL_CFM: + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { + chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; + } else if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { + chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; + l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); + } else if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { + chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; + l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); + } + break; + default: + /* Move was not in expected state, free the channel */ + __release_logical_link(chan); + + chan->move_state = L2CAP_MOVE_STABLE; + } +} + +/* Call with chan locked */ +void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, + u8 status) +{ + BT_DBG("chan %p, hchan %p, status %d", chan, hchan, status); + + if (status) { + l2cap_logical_fail(chan); + __release_logical_link(chan); + return; + } + + if (chan->state != BT_CONNECTED) { + /* Ignore logical link if channel is on BR/EDR */ + if (chan->local_amp_id) + l2cap_logical_finish_create(chan, hchan); + } else { + l2cap_logical_finish_move(chan, hchan); + } +} + +void l2cap_move_start(struct l2cap_chan *chan) +{ + BT_DBG("chan %p", chan); + + if (chan->local_amp_id == HCI_BREDR_ID) { + if (chan->chan_policy != BT_CHANNEL_POLICY_AMP_PREFERRED) + return; + chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; + chan->move_state = L2CAP_MOVE_WAIT_PREPARE; + /* Placeholder - start physical link setup */ + } else { + chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; + chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; + chan->move_id = 0; + l2cap_move_setup(chan); + l2cap_send_move_chan_req(chan, 0); + } +} + +static void l2cap_do_create(struct l2cap_chan *chan, int result, + u8 local_amp_id, u8 remote_amp_id) +{ + BT_DBG("chan %p state %s %u -> %u", chan, state_to_string(chan->state), + local_amp_id, remote_amp_id); + + chan->fcs = L2CAP_FCS_NONE; + + /* Outgoing channel on AMP */ + if (chan->state == BT_CONNECT) { + if (result == L2CAP_CR_SUCCESS) { + chan->local_amp_id = local_amp_id; + l2cap_send_create_chan_req(chan, remote_amp_id); + } else { + /* Revert to BR/EDR connect */ + l2cap_send_conn_req(chan); + } + + return; + } + + /* Incoming channel on AMP */ + if (__l2cap_no_conn_pending(chan)) { + struct l2cap_conn_rsp rsp; + char buf[128]; + rsp.scid = cpu_to_le16(chan->dcid); + rsp.dcid = cpu_to_le16(chan->scid); + + if (result == L2CAP_CR_SUCCESS) { + /* Send successful response */ + rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + } else { + /* Send negative response */ + rsp.result = __constant_cpu_to_le16(L2CAP_CR_NO_MEM); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + } + + l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_RSP, + sizeof(rsp), &rsp); + + if (result == L2CAP_CR_SUCCESS) { + __l2cap_state_change(chan, BT_CONFIG); + set_bit(CONF_REQ_SENT, &chan->conf_state); + l2cap_send_cmd(chan->conn, l2cap_get_ident(chan->conn), + L2CAP_CONF_REQ, + l2cap_build_conf_req(chan, buf), buf); + chan->num_conf_req++; + } + } +} + +static void l2cap_do_move_initiate(struct l2cap_chan *chan, u8 local_amp_id, + u8 remote_amp_id) +{ + l2cap_move_setup(chan); + chan->move_id = local_amp_id; + chan->move_state = L2CAP_MOVE_WAIT_RSP; + + l2cap_send_move_chan_req(chan, remote_amp_id); +} + +static void l2cap_do_move_respond(struct l2cap_chan *chan, int result) +{ + struct hci_chan *hchan = NULL; + + /* Placeholder - get hci_chan for logical link */ + + if (hchan) { + if (hchan->state == BT_CONNECTED) { + /* Logical link is ready to go */ + chan->hs_hcon = hchan->conn; + chan->hs_hcon->l2cap_data = chan->conn; + chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; + l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); + + l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); + } else { + /* Wait for logical link to be ready */ + chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; + } + } else { + /* Logical link not available */ + l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_ALLOWED); + } +} + +static void l2cap_do_move_cancel(struct l2cap_chan *chan, int result) +{ + if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { + u8 rsp_result; + if (result == -EINVAL) + rsp_result = L2CAP_MR_BAD_ID; + else + rsp_result = L2CAP_MR_NOT_ALLOWED; + + l2cap_send_move_chan_rsp(chan, rsp_result); + } + + chan->move_role = L2CAP_MOVE_ROLE_NONE; + chan->move_state = L2CAP_MOVE_STABLE; + + /* Restart data transmission */ + l2cap_ertm_send(chan); +} + +/* Invoke with locked chan */ +void __l2cap_physical_cfm(struct l2cap_chan *chan, int result) +{ + u8 local_amp_id = chan->local_amp_id; + u8 remote_amp_id = chan->remote_amp_id; + + BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d", + chan, result, local_amp_id, remote_amp_id); + + if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) { + l2cap_chan_unlock(chan); + return; + } + + if (chan->state != BT_CONNECTED) { + l2cap_do_create(chan, result, local_amp_id, remote_amp_id); + } else if (result != L2CAP_MR_SUCCESS) { + l2cap_do_move_cancel(chan, result); + } else { + switch (chan->move_role) { + case L2CAP_MOVE_ROLE_INITIATOR: + l2cap_do_move_initiate(chan, local_amp_id, + remote_amp_id); + break; + case L2CAP_MOVE_ROLE_RESPONDER: + l2cap_do_move_respond(chan, result); + break; + default: + l2cap_do_move_cancel(chan, result); + break; + } + } +} + static inline int l2cap_move_channel_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, void *data) { struct l2cap_move_chan_req *req = data; + struct l2cap_move_chan_rsp rsp; + struct l2cap_chan *chan; u16 icid = 0; u16 result = L2CAP_MR_NOT_ALLOWED; @@ -4061,15 +4691,206 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn, if (!enable_hs) return -EINVAL; - /* Placeholder: Always refuse */ - l2cap_send_move_chan_rsp(conn, cmd->ident, icid, result); + chan = l2cap_get_chan_by_dcid(conn, icid); + if (!chan) { + rsp.icid = cpu_to_le16(icid); + rsp.result = __constant_cpu_to_le16(L2CAP_MR_NOT_ALLOWED); + l2cap_send_cmd(conn, cmd->ident, L2CAP_MOVE_CHAN_RSP, + sizeof(rsp), &rsp); + return 0; + } + + chan->ident = cmd->ident; + + if (chan->scid < L2CAP_CID_DYN_START || + chan->chan_policy == BT_CHANNEL_POLICY_BREDR_ONLY || + (chan->mode != L2CAP_MODE_ERTM && + chan->mode != L2CAP_MODE_STREAMING)) { + result = L2CAP_MR_NOT_ALLOWED; + goto send_move_response; + } + + if (chan->local_amp_id == req->dest_amp_id) { + result = L2CAP_MR_SAME_ID; + goto send_move_response; + } + + if (req->dest_amp_id) { + struct hci_dev *hdev; + hdev = hci_dev_get(req->dest_amp_id); + if (!hdev || hdev->dev_type != HCI_AMP || + !test_bit(HCI_UP, &hdev->flags)) { + if (hdev) + hci_dev_put(hdev); + + result = L2CAP_MR_BAD_ID; + goto send_move_response; + } + hci_dev_put(hdev); + } + + /* Detect a move collision. Only send a collision response + * if this side has "lost", otherwise proceed with the move. + * The winner has the larger bd_addr. + */ + if ((__chan_is_moving(chan) || + chan->move_role != L2CAP_MOVE_ROLE_NONE) && + bacmp(conn->src, conn->dst) > 0) { + result = L2CAP_MR_COLLISION; + goto send_move_response; + } + + chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; + l2cap_move_setup(chan); + chan->move_id = req->dest_amp_id; + icid = chan->dcid; + + if (!req->dest_amp_id) { + /* Moving to BR/EDR */ + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { + chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; + result = L2CAP_MR_PEND; + } else { + chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; + result = L2CAP_MR_SUCCESS; + } + } else { + chan->move_state = L2CAP_MOVE_WAIT_PREPARE; + /* Placeholder - uncomment when amp functions are available */ + /*amp_accept_physical(chan, req->dest_amp_id);*/ + result = L2CAP_MR_PEND; + } + +send_move_response: + l2cap_send_move_chan_rsp(chan, result); + + l2cap_chan_unlock(chan); return 0; } -static inline int l2cap_move_channel_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) +static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result) +{ + struct l2cap_chan *chan; + struct hci_chan *hchan = NULL; + + chan = l2cap_get_chan_by_scid(conn, icid); + if (!chan) { + l2cap_send_move_chan_cfm_icid(conn, icid); + return; + } + + __clear_chan_timer(chan); + if (result == L2CAP_MR_PEND) + __set_chan_timer(chan, L2CAP_MOVE_ERTX_TIMEOUT); + + switch (chan->move_state) { + case L2CAP_MOVE_WAIT_LOGICAL_COMP: + /* Move confirm will be sent when logical link + * is complete. + */ + chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; + break; + case L2CAP_MOVE_WAIT_RSP_SUCCESS: + if (result == L2CAP_MR_PEND) { + break; + } else if (test_bit(CONN_LOCAL_BUSY, + &chan->conn_state)) { + chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; + } else { + /* Logical link is up or moving to BR/EDR, + * proceed with move + */ + chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; + l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); + } + break; + case L2CAP_MOVE_WAIT_RSP: + /* Moving to AMP */ + if (result == L2CAP_MR_SUCCESS) { + /* Remote is ready, send confirm immediately + * after logical link is ready + */ + chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; + } else { + /* Both logical link and move success + * are required to confirm + */ + chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_COMP; + } + + /* Placeholder - get hci_chan for logical link */ + if (!hchan) { + /* Logical link not available */ + l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); + break; + } + + /* If the logical link is not yet connected, do not + * send confirmation. + */ + if (hchan->state != BT_CONNECTED) + break; + + /* Logical link is already ready to go */ + + chan->hs_hcon = hchan->conn; + chan->hs_hcon->l2cap_data = chan->conn; + + if (result == L2CAP_MR_SUCCESS) { + /* Can confirm now */ + l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); + } else { + /* Now only need move success + * to confirm + */ + chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; + } + + l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); + break; + default: + /* Any other amp move state means the move failed. */ + chan->move_id = chan->local_amp_id; + l2cap_move_done(chan); + l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); + } + + l2cap_chan_unlock(chan); +} + +static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, + u16 result) +{ + struct l2cap_chan *chan; + + chan = l2cap_get_chan_by_ident(conn, ident); + if (!chan) { + /* Could not locate channel, icid is best guess */ + l2cap_send_move_chan_cfm_icid(conn, icid); + return; + } + + __clear_chan_timer(chan); + + if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { + if (result == L2CAP_MR_COLLISION) { + chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; + } else { + /* Cleanup - cancel move */ + chan->move_id = chan->local_amp_id; + l2cap_move_done(chan); + } + } + + l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); + + l2cap_chan_unlock(chan); +} + +static int l2cap_move_channel_rsp(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, void *data) { struct l2cap_move_chan_rsp *rsp = data; u16 icid, result; @@ -4082,17 +4903,20 @@ static inline int l2cap_move_channel_rsp(struct l2cap_conn *conn, BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); - /* Placeholder: Always unconfirmed */ - l2cap_send_move_chan_cfm(conn, NULL, icid, L2CAP_MC_UNCONFIRMED); + if (result == L2CAP_MR_SUCCESS || result == L2CAP_MR_PEND) + l2cap_move_continue(conn, icid, result); + else + l2cap_move_fail(conn, cmd->ident, icid, result); return 0; } -static inline int l2cap_move_channel_confirm(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) +static int l2cap_move_channel_confirm(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, void *data) { struct l2cap_move_chan_cfm *cfm = data; + struct l2cap_chan *chan; u16 icid, result; if (cmd_len != sizeof(*cfm)) @@ -4103,8 +4927,29 @@ static inline int l2cap_move_channel_confirm(struct l2cap_conn *conn, BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); + chan = l2cap_get_chan_by_dcid(conn, icid); + if (!chan) { + /* Spec requires a response even if the icid was not found */ + l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); + return 0; + } + + if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM) { + if (result == L2CAP_MC_CONFIRMED) { + chan->local_amp_id = chan->move_id; + if (!chan->local_amp_id) + __release_logical_link(chan); + } else { + chan->move_id = chan->local_amp_id; + } + + l2cap_move_done(chan); + } + l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); + l2cap_chan_unlock(chan); + return 0; } @@ -4113,6 +4958,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, u16 cmd_len, void *data) { struct l2cap_move_chan_cfm_rsp *rsp = data; + struct l2cap_chan *chan; u16 icid; if (cmd_len != sizeof(*rsp)) @@ -4122,11 +4968,28 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, BT_DBG("icid 0x%4.4x", icid); + chan = l2cap_get_chan_by_scid(conn, icid); + if (!chan) + return 0; + + __clear_chan_timer(chan); + + if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM_RSP) { + chan->local_amp_id = chan->move_id; + + if (!chan->local_amp_id && chan->hs_hchan) + __release_logical_link(chan); + + l2cap_move_done(chan); + } + + l2cap_chan_unlock(chan); + return 0; } static inline int l2cap_check_conn_param(u16 min, u16 max, u16 latency, - u16 to_multiplier) + u16 to_multiplier) { u16 max_latency; @@ -4147,7 +5010,8 @@ static inline int l2cap_check_conn_param(u16 min, u16 max, u16 latency, } static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u8 *data) + struct l2cap_cmd_hdr *cmd, + u8 *data) { struct hci_conn *hcon = conn->hcon; struct l2cap_conn_param_update_req *req; @@ -4169,7 +5033,7 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, to_multiplier = __le16_to_cpu(req->to_multiplier); BT_DBG("min 0x%4.4x max 0x%4.4x latency: 0x%4.4x Timeout: 0x%4.4x", - min, max, latency, to_multiplier); + min, max, latency, to_multiplier); memset(&rsp, 0, sizeof(rsp)); @@ -4180,7 +5044,7 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, rsp.result = __constant_cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED); l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP, - sizeof(rsp), &rsp); + sizeof(rsp), &rsp); if (!err) hci_le_conn_update(hcon, min, max, latency, to_multiplier); @@ -4189,7 +5053,8 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, } static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) { int err = 0; @@ -4203,7 +5068,8 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, break; case L2CAP_CONN_RSP: - err = l2cap_connect_rsp(conn, cmd, data); + case L2CAP_CREATE_CHAN_RSP: + err = l2cap_connect_create_rsp(conn, cmd, data); break; case L2CAP_CONF_REQ: @@ -4241,10 +5107,6 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, err = l2cap_create_channel_req(conn, cmd, cmd_len, data); break; - case L2CAP_CREATE_CHAN_RSP: - err = l2cap_create_channel_rsp(conn, cmd, data); - break; - case L2CAP_MOVE_CHAN_REQ: err = l2cap_move_channel_req(conn, cmd, cmd_len, data); break; @@ -4271,7 +5133,7 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, } static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u8 *data) + struct l2cap_cmd_hdr *cmd, u8 *data) { switch (cmd->code) { case L2CAP_COMMAND_REJ: @@ -4290,7 +5152,7 @@ static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn, } static inline void l2cap_sig_channel(struct l2cap_conn *conn, - struct sk_buff *skb) + struct sk_buff *skb) { u8 *data = skb->data; int len = skb->len; @@ -4307,7 +5169,8 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, cmd_len = le16_to_cpu(cmd.len); - BT_DBG("code 0x%2.2x len %d id 0x%2.2x", cmd.code, cmd_len, cmd.ident); + BT_DBG("code 0x%2.2x len %d id 0x%2.2x", cmd.code, cmd_len, + cmd.ident); if (cmd_len > len || !cmd.ident) { BT_DBG("corrupted command"); @@ -4326,7 +5189,8 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, /* FIXME: Map err to a valid reason */ rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); - l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); + l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ, + sizeof(rej), &rej); } data += cmd_len; @@ -4391,8 +5255,8 @@ static void l2cap_send_i_or_rr_or_rnr(struct l2cap_chan *chan) } } -static void append_skb_frag(struct sk_buff *skb, - struct sk_buff *new_frag, struct sk_buff **last_frag) +static void append_skb_frag(struct sk_buff *skb, struct sk_buff *new_frag, + struct sk_buff **last_frag) { /* skb->len reflects data in skb as well as all fragments * skb->data_len reflects only data in fragments @@ -4492,6 +5356,12 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, return err; } +static int l2cap_resegment(struct l2cap_chan *chan) +{ + /* Placeholder */ + return 0; +} + void l2cap_chan_busy(struct l2cap_chan *chan, int busy) { u8 event; @@ -4546,7 +5416,7 @@ static void l2cap_handle_srej(struct l2cap_chan *chan, if (control->reqseq == chan->next_tx_seq) { BT_DBG("Invalid reqseq %d, disconnecting", control->reqseq); - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); return; } @@ -4560,7 +5430,7 @@ static void l2cap_handle_srej(struct l2cap_chan *chan, if (chan->max_tx != 0 && bt_cb(skb)->control.retries >= chan->max_tx) { BT_DBG("Retry limit exceeded (%d)", chan->max_tx); - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); return; } @@ -4604,7 +5474,7 @@ static void l2cap_handle_rej(struct l2cap_chan *chan, if (control->reqseq == chan->next_tx_seq) { BT_DBG("Invalid reqseq %d, disconnecting", control->reqseq); - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); return; } @@ -4613,7 +5483,7 @@ static void l2cap_handle_rej(struct l2cap_chan *chan, if (chan->max_tx && skb && bt_cb(skb)->control.retries >= chan->max_tx) { BT_DBG("Retry limit exceeded (%d)", chan->max_tx); - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); return; } @@ -4641,7 +5511,7 @@ static u8 l2cap_classify_txseq(struct l2cap_chan *chan, u16 txseq) if (chan->rx_state == L2CAP_RX_STATE_SREJ_SENT) { if (__seq_offset(chan, txseq, chan->last_acked_seq) >= - chan->tx_win) { + chan->tx_win) { /* See notes below regarding "double poll" and * invalid packets. */ @@ -4682,8 +5552,7 @@ static u8 l2cap_classify_txseq(struct l2cap_chan *chan, u16 txseq) } if (__seq_offset(chan, txseq, chan->last_acked_seq) < - __seq_offset(chan, chan->expected_tx_seq, - chan->last_acked_seq)){ + __seq_offset(chan, chan->expected_tx_seq, chan->last_acked_seq)) { BT_DBG("Duplicate - expected_tx_seq later than txseq"); return L2CAP_TXSEQ_DUPLICATE; } @@ -4798,8 +5667,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, break; case L2CAP_TXSEQ_INVALID: default: - l2cap_send_disconn_req(chan->conn, chan, - ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); break; } break; @@ -4808,8 +5676,8 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, if (control->final) { clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - if (!test_and_clear_bit(CONN_REJ_ACT, - &chan->conn_state)) { + if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state) && + !__chan_is_moving(chan)) { control->final = 0; l2cap_retransmit_all(chan, control); } @@ -4932,8 +5800,7 @@ static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan, break; case L2CAP_TXSEQ_INVALID: default: - l2cap_send_disconn_req(chan->conn, chan, - ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); break; } break; @@ -4998,6 +5865,96 @@ static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan, return err; } +static int l2cap_finish_move(struct l2cap_chan *chan) +{ + BT_DBG("chan %p", chan); + + chan->rx_state = L2CAP_RX_STATE_RECV; + + if (chan->hs_hcon) + chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; + else + chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + + return l2cap_resegment(chan); +} + +static int l2cap_rx_state_wait_p(struct l2cap_chan *chan, + struct l2cap_ctrl *control, + struct sk_buff *skb, u8 event) +{ + int err; + + BT_DBG("chan %p, control %p, skb %p, event %d", chan, control, skb, + event); + + if (!control->poll) + return -EPROTO; + + l2cap_process_reqseq(chan, control->reqseq); + + if (!skb_queue_empty(&chan->tx_q)) + chan->tx_send_head = skb_peek(&chan->tx_q); + else + chan->tx_send_head = NULL; + + /* Rewind next_tx_seq to the point expected + * by the receiver. + */ + chan->next_tx_seq = control->reqseq; + chan->unacked_frames = 0; + + err = l2cap_finish_move(chan); + if (err) + return err; + + set_bit(CONN_SEND_FBIT, &chan->conn_state); + l2cap_send_i_or_rr_or_rnr(chan); + + if (event == L2CAP_EV_RECV_IFRAME) + return -EPROTO; + + return l2cap_rx_state_recv(chan, control, NULL, event); +} + +static int l2cap_rx_state_wait_f(struct l2cap_chan *chan, + struct l2cap_ctrl *control, + struct sk_buff *skb, u8 event) +{ + int err; + + if (!control->final) + return -EPROTO; + + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); + + chan->rx_state = L2CAP_RX_STATE_RECV; + l2cap_process_reqseq(chan, control->reqseq); + + if (!skb_queue_empty(&chan->tx_q)) + chan->tx_send_head = skb_peek(&chan->tx_q); + else + chan->tx_send_head = NULL; + + /* Rewind next_tx_seq to the point expected + * by the receiver. + */ + chan->next_tx_seq = control->reqseq; + chan->unacked_frames = 0; + + if (chan->hs_hcon) + chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; + else + chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + + err = l2cap_resegment(chan); + + if (!err) + err = l2cap_rx_state_recv(chan, control, skb, event); + + return err; +} + static bool __valid_reqseq(struct l2cap_chan *chan, u16 reqseq) { /* Make sure reqseq is for a packet that has been sent but not acked */ @@ -5024,6 +5981,12 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, err = l2cap_rx_state_srej_sent(chan, control, skb, event); break; + case L2CAP_RX_STATE_WAIT_P: + err = l2cap_rx_state_wait_p(chan, control, skb, event); + break; + case L2CAP_RX_STATE_WAIT_F: + err = l2cap_rx_state_wait_f(chan, control, skb, event); + break; default: /* shut it down */ break; @@ -5032,7 +5995,7 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, BT_DBG("Invalid reqseq %d (next_tx_seq %d, expected_ack_seq %d", control->reqseq, chan->next_tx_seq, chan->expected_ack_seq); - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); } return err; @@ -5101,7 +6064,7 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) len -= L2CAP_FCS_SIZE; if (len > chan->mps) { - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); goto drop; } @@ -5126,8 +6089,7 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) } if (err) - l2cap_send_disconn_req(chan->conn, chan, - ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); } else { const u8 rx_func_to_event[4] = { L2CAP_EV_RECV_RR, L2CAP_EV_RECV_REJ, @@ -5143,8 +6105,8 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) control->super); if (len != 0) { - BT_ERR("%d", len); - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + BT_ERR("Trailing bytes: %d in sframe", len); + l2cap_send_disconn_req(chan, ECONNRESET); goto drop; } @@ -5155,7 +6117,7 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) event = rx_func_to_event[control->super]; if (l2cap_rx(chan, control, skb, event)) - l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + l2cap_send_disconn_req(chan, ECONNRESET); } return 0; @@ -5323,7 +6285,7 @@ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) int exact = 0, lm1 = 0, lm2 = 0; struct l2cap_chan *c; - BT_DBG("hdev %s, bdaddr %s", hdev->name, batostr(bdaddr)); + BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets and check their link_mode */ read_lock(&chan_list_lock); @@ -5353,15 +6315,15 @@ void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) { struct l2cap_conn *conn; - BT_DBG("hcon %p bdaddr %s status %d", hcon, batostr(&hcon->dst), status); + BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); if (!status) { conn = l2cap_conn_add(hcon, status); if (conn) l2cap_conn_ready(conn); - } else + } else { l2cap_conn_del(hcon, bt_to_errno(status)); - + } } int l2cap_disconn_ind(struct hci_conn *hcon) @@ -5437,13 +6399,13 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) continue; } - if (test_bit(CONF_CONNECT_PEND, &chan->conf_state)) { + if (!__l2cap_no_conn_pending(chan)) { l2cap_chan_unlock(chan); continue; } if (!status && (chan->state == BT_CONNECTED || - chan->state == BT_CONFIG)) { + chan->state == BT_CONFIG)) { struct sock *sk = chan->sk; clear_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags); @@ -5456,7 +6418,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (chan->state == BT_CONNECT) { if (!status) { - l2cap_send_conn_req(chan); + l2cap_start_connection(chan); } else { __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); } @@ -5470,11 +6432,9 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (!status) { if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { - struct sock *parent = bt_sk(sk)->parent; res = L2CAP_CR_PEND; stat = L2CAP_CS_AUTHOR_PEND; - if (parent) - parent->sk_data_ready(parent, 0); + chan->ops->defer(chan); } else { __l2cap_state_change(chan, BT_CONFIG); res = L2CAP_CR_SUCCESS; @@ -5494,7 +6454,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) rsp.result = cpu_to_le16(res); rsp.status = cpu_to_le16(stat); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, - sizeof(rsp), &rsp); + sizeof(rsp), &rsp); if (!test_bit(CONF_REQ_SENT, &chan->conf_state) && res == L2CAP_CR_SUCCESS) { @@ -5519,6 +6479,12 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) { struct l2cap_conn *conn = hcon->l2cap_data; + struct l2cap_hdr *hdr; + int len; + + /* For AMP controller do not create l2cap conn */ + if (!conn && hcon->hdev->dev_type != HCI_BREDR) + goto drop; if (!conn) conn = l2cap_conn_add(hcon, 0); @@ -5528,10 +6494,10 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) BT_DBG("conn %p len %d flags 0x%x", conn, skb->len, flags); - if (!(flags & ACL_CONT)) { - struct l2cap_hdr *hdr; - int len; - + switch (flags) { + case ACL_START: + case ACL_START_NO_FLUSH: + case ACL_COMPLETE: if (conn->rx_len) { BT_ERR("Unexpected start frame (len %d)", skb->len); kfree_skb(conn->rx_skb); @@ -5560,20 +6526,22 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) if (skb->len > len) { BT_ERR("Frame is too long (len %d, expected len %d)", - skb->len, len); + skb->len, len); l2cap_conn_unreliable(conn, ECOMM); goto drop; } /* Allocate skb for the complete frame (with header) */ - conn->rx_skb = bt_skb_alloc(len, GFP_ATOMIC); + conn->rx_skb = bt_skb_alloc(len, GFP_KERNEL); if (!conn->rx_skb) goto drop; skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), - skb->len); + skb->len); conn->rx_len = len - skb->len; - } else { + break; + + case ACL_CONT: BT_DBG("Cont: frag len %d (expecting %d)", skb->len, conn->rx_len); if (!conn->rx_len) { @@ -5584,7 +6552,7 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) if (skb->len > conn->rx_len) { BT_ERR("Fragment is too long (len %d, expected %d)", - skb->len, conn->rx_len); + skb->len, conn->rx_len); kfree_skb(conn->rx_skb); conn->rx_skb = NULL; conn->rx_len = 0; @@ -5593,7 +6561,7 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) } skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), - skb->len); + skb->len); conn->rx_len -= skb->len; if (!conn->rx_len) { @@ -5601,6 +6569,7 @@ int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) l2cap_recv_frame(conn, conn->rx_skb); conn->rx_skb = NULL; } + break; } drop: @@ -5617,12 +6586,11 @@ static int l2cap_debugfs_show(struct seq_file *f, void *p) list_for_each_entry(c, &chan_list, global_l) { struct sock *sk = c->sk; - seq_printf(f, "%s %s %d %d 0x%4.4x 0x%4.4x %d %d %d %d\n", - batostr(&bt_sk(sk)->src), - batostr(&bt_sk(sk)->dst), - c->state, __le16_to_cpu(c->psm), - c->scid, c->dcid, c->imtu, c->omtu, - c->sec_level, c->mode); + seq_printf(f, "%pMR %pMR %d %d 0x%4.4x 0x%4.4x %d %d %d %d\n", + &bt_sk(sk)->src, &bt_sk(sk)->dst, + c->state, __le16_to_cpu(c->psm), + c->scid, c->dcid, c->imtu, c->omtu, + c->sec_level, c->mode); } read_unlock(&chan_list_lock); @@ -5653,8 +6621,8 @@ int __init l2cap_init(void) return err; if (bt_debugfs) { - l2cap_debugfs = debugfs_create_file("l2cap", 0444, - bt_debugfs, NULL, &l2cap_debugfs_fops); + l2cap_debugfs = debugfs_create_file("l2cap", 0444, bt_debugfs, + NULL, &l2cap_debugfs_fops); if (!l2cap_debugfs) BT_ERR("Failed to create L2CAP debug file"); } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 083f2bf065d4..1bcfb8422fdc 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -40,7 +40,8 @@ static struct bt_sock_list l2cap_sk_list = { static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); -static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio); +static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, + int proto, gfp_t prio); static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) { @@ -106,7 +107,8 @@ done: return err; } -static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) +static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -134,7 +136,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, - sock_sndtimeo(sk, flags & O_NONBLOCK)); + sock_sndtimeo(sk, flags & O_NONBLOCK)); release_sock(sk); @@ -185,7 +187,8 @@ done: return err; } -static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int flags) +static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, + int flags) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *nsk; @@ -241,7 +244,8 @@ done: return err; } -static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer) +static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, + int *len, int peer) { struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr; struct sock *sk = sock->sk; @@ -266,7 +270,8 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l return 0; } -static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen) +static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, + char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -309,7 +314,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us break; case BT_SECURITY_HIGH: opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT | - L2CAP_LM_SECURE; + L2CAP_LM_SECURE; break; default: opt = 0; @@ -353,7 +358,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us return err; } -static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) +static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -377,19 +383,20 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch switch (optname) { case BT_SECURITY: if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && - chan->chan_type != L2CAP_CHAN_RAW) { + chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; } memset(&sec, 0, sizeof(sec)); - if (chan->conn) + if (chan->conn) { sec.level = chan->conn->hcon->sec_level; - else - sec.level = chan->sec_level; - if (sk->sk_state == BT_CONNECTED) - sec.key_size = chan->conn->hcon->enc_key_size; + if (sk->sk_state == BT_CONNECTED) + sec.key_size = chan->conn->hcon->enc_key_size; + } else { + sec.level = chan->sec_level; + } len = min_t(unsigned int, len, sizeof(sec)); if (copy_to_user(optval, (char *) &sec, len)) @@ -411,14 +418,14 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch case BT_FLUSHABLE: if (put_user(test_bit(FLAG_FLUSHABLE, &chan->flags), - (u32 __user *) optval)) + (u32 __user *) optval)) err = -EFAULT; break; case BT_POWER: if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM - && sk->sk_type != SOCK_RAW) { + && sk->sk_type != SOCK_RAW) { err = -EINVAL; break; } @@ -466,7 +473,8 @@ static bool l2cap_valid_mtu(struct l2cap_chan *chan, u16 mtu) return true; } -static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) +static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -529,6 +537,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us chan->fcs = opts.fcs; chan->max_tx = opts.max_tx; chan->tx_win = opts.txwin_size; + chan->flush_to = opts.flush_to; break; case L2CAP_LM: @@ -564,7 +573,8 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us return err; } -static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) +static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -587,7 +597,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch switch (optname) { case BT_SECURITY: if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && - chan->chan_type != L2CAP_CHAN_RAW) { + chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; } @@ -601,7 +611,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch } if (sec.level < BT_SECURITY_LOW || - sec.level > BT_SECURITY_HIGH) { + sec.level > BT_SECURITY_HIGH) { err = -EINVAL; break; } @@ -627,7 +637,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch /* or for ACL link */ } else if ((sk->sk_state == BT_CONNECT2 && - test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) || + test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) || sk->sk_state == BT_CONNECTED) { if (!l2cap_chan_check_security(chan)) set_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags); @@ -684,7 +694,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch case BT_POWER: if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && - chan->chan_type != L2CAP_CHAN_RAW) { + chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; } @@ -720,12 +730,17 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch } if (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING) { + chan->mode != L2CAP_MODE_STREAMING) { err = -EOPNOTSUPP; break; } chan->chan_policy = (u8) opt; + + if (sk->sk_state == BT_CONNECTED && + chan->move_role == L2CAP_MOVE_ROLE_NONE) + l2cap_move_start(chan); + break; default: @@ -737,7 +752,8 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch return err; } -static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) +static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -762,7 +778,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms return err; } -static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags) +static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct l2cap_pinfo *pi = l2cap_pi(sk); @@ -866,7 +883,7 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) err = bt_sock_wait_state(sk, BT_CLOSED, - sk->sk_lingertime); + sk->sk_lingertime); } if (!err && sk->sk_err) @@ -930,7 +947,7 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, - GFP_ATOMIC); + GFP_ATOMIC); if (!sk) return NULL; @@ -938,6 +955,8 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) l2cap_sock_init(sk, parent); + bt_accept_enqueue(parent, sk); + return l2cap_pi(sk)->chan; } @@ -1068,6 +1087,15 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan) release_sock(sk); } +static void l2cap_sock_defer_cb(struct l2cap_chan *chan) +{ + struct sock *sk = chan->data; + struct sock *parent = bt_sk(sk)->parent; + + if (parent) + parent->sk_data_ready(parent, 0); +} + static struct l2cap_ops l2cap_chan_ops = { .name = "L2CAP Socket Interface", .new_connection = l2cap_sock_new_connection_cb, @@ -1076,6 +1104,7 @@ static struct l2cap_ops l2cap_chan_ops = { .teardown = l2cap_sock_teardown_cb, .state_change = l2cap_sock_state_change_cb, .ready = l2cap_sock_ready_cb, + .defer = l2cap_sock_defer_cb, .alloc_skb = l2cap_sock_alloc_skb_cb, }; @@ -1083,7 +1112,8 @@ static void l2cap_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); - l2cap_chan_put(l2cap_pi(sk)->chan); + if (l2cap_pi(sk)->chan) + l2cap_chan_put(l2cap_pi(sk)->chan); if (l2cap_pi(sk)->rx_busy_skb) { kfree_skb(l2cap_pi(sk)->rx_busy_skb); l2cap_pi(sk)->rx_busy_skb = NULL; @@ -1159,7 +1189,8 @@ static struct proto l2cap_proto = { .obj_size = sizeof(struct l2cap_pinfo) }; -static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio) +static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, + int proto, gfp_t prio) { struct sock *sk; struct l2cap_chan *chan; @@ -1204,7 +1235,7 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, sock->state = SS_UNCONNECTED; if (sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM && - sock->type != SOCK_DGRAM && sock->type != SOCK_RAW) + sock->type != SOCK_DGRAM && sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) @@ -1261,7 +1292,8 @@ int __init l2cap_init_sockets(void) goto error; } - err = bt_procfs_init(THIS_MODULE, &init_net, "l2cap", &l2cap_sk_list, NULL); + err = bt_procfs_init(THIS_MODULE, &init_net, "l2cap", &l2cap_sk_list, + NULL); if (err < 0) { BT_ERR("Failed to create L2CAP proc file"); bt_sock_unregister(BTPROTO_L2CAP); diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index e1c97527e16c..b3fbc73516c4 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -41,20 +41,6 @@ void baswap(bdaddr_t *dst, bdaddr_t *src) } EXPORT_SYMBOL(baswap); -char *batostr(bdaddr_t *ba) -{ - static char str[2][18]; - static int i = 1; - - i ^= 1; - sprintf(str[i], "%2.2X:%2.2X:%2.2X:%2.2X:%2.2X:%2.2X", - ba->b[5], ba->b[4], ba->b[3], - ba->b[2], ba->b[1], ba->b[0]); - - return str[i]; -} -EXPORT_SYMBOL(batostr); - /* Bluetooth error codes to Unix errno mapping */ int bt_to_errno(__u16 code) { diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index aa2ea0a8142c..f559b966279c 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -222,7 +222,7 @@ static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) hdr = (void *) skb_put(skb, sizeof(*hdr)); - hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS); + hdr->opcode = __constant_cpu_to_le16(MGMT_EV_CMD_STATUS); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(sizeof(*ev)); @@ -253,7 +253,7 @@ static int cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, hdr = (void *) skb_put(skb, sizeof(*hdr)); - hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE); + hdr->opcode = __constant_cpu_to_le16(MGMT_EV_CMD_COMPLETE); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(sizeof(*ev) + rp_len); @@ -326,7 +326,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, struct hci_dev *d; size_t rp_len; u16 count; - int i, err; + int err; BT_DBG("sock %p", sk); @@ -347,9 +347,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, return -ENOMEM; } - rp->num_controllers = cpu_to_le16(count); - - i = 0; + count = 0; list_for_each_entry(d, &hci_dev_list, list) { if (test_bit(HCI_SETUP, &d->dev_flags)) continue; @@ -357,10 +355,13 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, if (!mgmt_valid_hdev(d)) continue; - rp->index[i++] = cpu_to_le16(d->id); + rp->index[count++] = cpu_to_le16(d->id); BT_DBG("Added hci%u", d->id); } + rp->num_controllers = cpu_to_le16(count); + rp_len = sizeof(*rp) + (2 * count); + read_unlock(&hci_dev_list_lock); err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_INDEX_LIST, 0, rp, @@ -376,15 +377,15 @@ static u32 get_supported_settings(struct hci_dev *hdev) u32 settings = 0; settings |= MGMT_SETTING_POWERED; - settings |= MGMT_SETTING_CONNECTABLE; - settings |= MGMT_SETTING_FAST_CONNECTABLE; - settings |= MGMT_SETTING_DISCOVERABLE; settings |= MGMT_SETTING_PAIRABLE; if (lmp_ssp_capable(hdev)) settings |= MGMT_SETTING_SSP; if (lmp_bredr_capable(hdev)) { + settings |= MGMT_SETTING_CONNECTABLE; + settings |= MGMT_SETTING_FAST_CONNECTABLE; + settings |= MGMT_SETTING_DISCOVERABLE; settings |= MGMT_SETTING_BREDR; settings |= MGMT_SETTING_LINK_SECURITY; } @@ -484,7 +485,7 @@ static void create_eir(struct hci_dev *hdev, u8 *data) ptr += (name_len + 2); } - if (hdev->inq_tx_power) { + if (hdev->inq_tx_power != HCI_TX_POWER_INVALID) { ptr[0] = 2; ptr[1] = EIR_TX_POWER; ptr[2] = (u8) hdev->inq_tx_power; @@ -565,7 +566,7 @@ static int update_eir(struct hci_dev *hdev) if (!hdev_is_powered(hdev)) return 0; - if (!(hdev->features[6] & LMP_EXT_INQ)) + if (!lmp_ext_inq_capable(hdev)) return 0; if (!test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) @@ -832,7 +833,7 @@ static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 data_len, if (hdev) hdr->index = cpu_to_le16(hdev->id); else - hdr->index = cpu_to_le16(MGMT_INDEX_NONE); + hdr->index = __constant_cpu_to_le16(MGMT_INDEX_NONE); hdr->len = cpu_to_le16(data_len); if (data) @@ -867,6 +868,10 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("request for %s", hdev->name); + if (!lmp_bredr_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, + MGMT_STATUS_NOT_SUPPORTED); + timeout = __le16_to_cpu(cp->timeout); if (!cp->val && timeout > 0) return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, @@ -962,6 +967,10 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("request for %s", hdev->name); + if (!lmp_bredr_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, + MGMT_STATUS_NOT_SUPPORTED); + hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { @@ -1060,6 +1069,10 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("request for %s", hdev->name); + if (!lmp_bredr_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY, + MGMT_STATUS_NOT_SUPPORTED); + hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { @@ -1213,7 +1226,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) } val = !!cp->val; - enabled = !!(hdev->host_features[0] & LMP_HOST_LE); + enabled = lmp_host_le_capable(hdev); if (!hdev_is_powered(hdev) || val == enabled) { bool changed = false; @@ -1249,7 +1262,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) if (val) { hci_cp.le = val; - hci_cp.simul = !!(hdev->features[6] & LMP_SIMUL_LE_BR); + hci_cp.simul = lmp_le_br_capable(hdev); } err = hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp), @@ -1366,6 +1379,7 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, continue; list_del(&match->list); + kfree(match); found++; } @@ -2594,6 +2608,10 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev, BT_DBG("%s", hdev->name); + if (!lmp_bredr_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, + MGMT_STATUS_NOT_SUPPORTED); + if (!hdev_is_powered(hdev)) return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, MGMT_STATUS_NOT_POWERED); @@ -2871,6 +2889,21 @@ static void settings_rsp(struct pending_cmd *cmd, void *data) mgmt_pending_free(cmd); } +static int set_bredr_scan(struct hci_dev *hdev) +{ + u8 scan = 0; + + if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) + scan |= SCAN_PAGE; + if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) + scan |= SCAN_INQUIRY; + + if (!scan) + return 0; + + return hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); +} + int mgmt_powered(struct hci_dev *hdev, u8 powered) { struct cmd_lookup match = { NULL, hdev }; @@ -2882,17 +2915,8 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); if (powered) { - u8 scan = 0; - - if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) - scan |= SCAN_PAGE; - if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) - scan |= SCAN_INQUIRY; - - if (scan) - hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); - - if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) && + !lmp_host_ssp_capable(hdev)) { u8 ssp = 1; hci_send_cmd(hdev, HCI_OP_WRITE_SSP_MODE, 1, &ssp); @@ -2902,15 +2926,24 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) struct hci_cp_write_le_host_supported cp; cp.le = 1; - cp.simul = !!(hdev->features[6] & LMP_SIMUL_LE_BR); - - hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, - sizeof(cp), &cp); + cp.simul = lmp_le_br_capable(hdev); + + /* Check first if we already have the right + * host state (host features set) + */ + if (cp.le != lmp_host_le_capable(hdev) || + cp.simul != lmp_host_le_br_capable(hdev)) + hci_send_cmd(hdev, + HCI_OP_WRITE_LE_HOST_SUPPORTED, + sizeof(cp), &cp); } - update_class(hdev); - update_name(hdev, hdev->dev_name); - update_eir(hdev); + if (lmp_bredr_capable(hdev)) { + set_bredr_scan(hdev); + update_class(hdev); + update_name(hdev, hdev->dev_name); + update_eir(hdev); + } } else { u8 status = MGMT_STATUS_NOT_POWERED; mgmt_pending_foreach(0, hdev, cmd_status_rsp, &status); @@ -3125,6 +3158,9 @@ int mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, struct pending_cmd *cmd; int err; + mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp, + hdev); + cmd = mgmt_pending_find(MGMT_OP_DISCONNECT, hdev); if (!cmd) return -ENOENT; @@ -3137,8 +3173,6 @@ int mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, mgmt_pending_remove(cmd); - mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp, - hdev); return err; } @@ -3358,7 +3392,7 @@ static int clear_eir(struct hci_dev *hdev) { struct hci_cp_write_eir cp; - if (!(hdev->features[6] & LMP_EXT_INQ)) + if (!lmp_ext_inq_capable(hdev)) return 0; memset(hdev->eir, 0, sizeof(hdev->eir)); @@ -3490,7 +3524,12 @@ send_event: err = mgmt_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev), cmd ? cmd->sk : NULL); - update_eir(hdev); + /* EIR is taken care of separately when powering on the + * adapter so only update them here if this is a name change + * unrelated to power on. + */ + if (!test_bit(HCI_INIT, &hdev->flags)) + update_eir(hdev); failed: if (cmd) @@ -3585,9 +3624,9 @@ int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, ev->addr.type = link_to_bdaddr(link_type, addr_type); ev->rssi = rssi; if (cfm_name) - ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME); + ev->flags |= __constant_cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME); if (!ssp) - ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING); + ev->flags |= __constant_cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING); if (eir_len > 0) memcpy(ev->eir, eir, eir_len); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index c75107ef8920..201fdf737209 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -377,8 +377,8 @@ static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, int err = 0; u8 dlci; - BT_DBG("dlc %p state %ld %s %s channel %d", - d, d->state, batostr(src), batostr(dst), channel); + BT_DBG("dlc %p state %ld %pMR -> %pMR channel %d", + d, d->state, src, dst, channel); if (channel < 1 || channel > 30) return -EINVAL; @@ -676,7 +676,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, struct socket *sock; struct sock *sk; - BT_DBG("%s %s", batostr(src), batostr(dst)); + BT_DBG("%pMR -> %pMR", src, dst); *err = rfcomm_l2sock_create(&sock); if (*err < 0) @@ -709,7 +709,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bacpy(&addr.l2_bdaddr, dst); addr.l2_family = AF_BLUETOOTH; - addr.l2_psm = cpu_to_le16(RFCOMM_PSM); + addr.l2_psm = __constant_cpu_to_le16(RFCOMM_PSM); addr.l2_cid = 0; *err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK); if (*err == 0 || *err == -EINPROGRESS) @@ -1987,7 +1987,7 @@ static int rfcomm_add_listener(bdaddr_t *ba) /* Bind socket */ bacpy(&addr.l2_bdaddr, ba); addr.l2_family = AF_BLUETOOTH; - addr.l2_psm = cpu_to_le16(RFCOMM_PSM); + addr.l2_psm = __constant_cpu_to_le16(RFCOMM_PSM); addr.l2_cid = 0; err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr)); if (err < 0) { @@ -2125,11 +2125,10 @@ static int rfcomm_dlc_debugfs_show(struct seq_file *f, void *x) list_for_each_entry(d, &s->dlcs, list) { struct sock *sk = s->sock->sk; - seq_printf(f, "%s %s %ld %d %d %d %d\n", - batostr(&bt_sk(sk)->src), - batostr(&bt_sk(sk)->dst), - d->state, d->dlci, d->mtu, - d->rx_credits, d->tx_credits); + seq_printf(f, "%pMR %pMR %ld %d %d %d %d\n", + &bt_sk(sk)->src, &bt_sk(sk)->dst, + d->state, d->dlci, d->mtu, + d->rx_credits, d->tx_credits); } } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index b3226f3658cf..ce3f6658f4b2 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -334,7 +334,7 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr struct sock *sk = sock->sk; int err = 0; - BT_DBG("sk %p %s", sk, batostr(&sa->rc_bdaddr)); + BT_DBG("sk %p %pMR", sk, &sa->rc_bdaddr); if (!addr || addr->sa_family != AF_BLUETOOTH) return -EINVAL; @@ -467,7 +467,7 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f long timeo; int err = 0; - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_type != SOCK_STREAM) { err = -EINVAL; @@ -504,7 +504,7 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f release_sock(sk); timeo = schedule_timeout(timeo); - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); @@ -975,10 +975,9 @@ static int rfcomm_sock_debugfs_show(struct seq_file *f, void *p) read_lock(&rfcomm_sk_list.lock); sk_for_each(sk, node, &rfcomm_sk_list.head) { - seq_printf(f, "%s %s %d %d\n", - batostr(&bt_sk(sk)->src), - batostr(&bt_sk(sk)->dst), - sk->sk_state, rfcomm_pi(sk)->channel); + seq_printf(f, "%pMR %pMR %d %d\n", + &bt_sk(sk)->src, &bt_sk(sk)->dst, + sk->sk_state, rfcomm_pi(sk)->channel); } read_unlock(&rfcomm_sk_list.lock); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index ccc248791d50..bd6fd0f43d2b 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -166,7 +166,7 @@ static struct device *rfcomm_get_device(struct rfcomm_dev *dev) static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); - return sprintf(buf, "%s\n", batostr(&dev->dst)); + return sprintf(buf, "%pMR\n", &dev->dst); } static ssize_t show_channel(struct device *tty_dev, struct device_attribute *attr, char *buf) @@ -663,8 +663,8 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) if (!dev) return -ENODEV; - BT_DBG("dev %p dst %s channel %d opened %d", dev, batostr(&dev->dst), - dev->channel, dev->port.count); + BT_DBG("dev %p dst %pMR channel %d opened %d", dev, &dev->dst, + dev->channel, dev->port.count); spin_lock_irqsave(&dev->port.lock, flags); if (++dev->port.count > 1) { diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index dc42b917aaaf..57f250c20e39 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -131,15 +131,6 @@ static int sco_conn_del(struct hci_conn *hcon, int err) sco_sock_clear_timer(sk); sco_chan_del(sk, err); bh_unlock_sock(sk); - - sco_conn_lock(conn); - conn->sk = NULL; - sco_pi(sk)->conn = NULL; - sco_conn_unlock(conn); - - if (conn->hcon) - hci_conn_put(conn->hcon); - sco_sock_kill(sk); } @@ -172,7 +163,7 @@ static int sco_connect(struct sock *sk) struct hci_dev *hdev; int err, type; - BT_DBG("%s -> %s", batostr(src), batostr(dst)); + BT_DBG("%pMR -> %pMR", src, dst); hdev = hci_get_route(dst, src); if (!hdev) @@ -361,7 +352,7 @@ static void __sco_sock_close(struct sock *sk) case BT_CONNECTED: case BT_CONFIG: - if (sco_pi(sk)->conn) { + if (sco_pi(sk)->conn->hcon) { sk->sk_state = BT_DISCONN; sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); hci_conn_put(sco_pi(sk)->conn->hcon); @@ -397,6 +388,7 @@ static void sco_sock_init(struct sock *sk, struct sock *parent) if (parent) { sk->sk_type = parent->sk_type; + bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); } } @@ -460,7 +452,7 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le struct sock *sk = sock->sk; int err = 0; - BT_DBG("sk %p %s", sk, batostr(&sa->sco_bdaddr)); + BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); if (!addr || addr->sa_family != AF_BLUETOOTH) return -EINVAL; @@ -662,16 +654,57 @@ static int sco_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return err; } +static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct sco_pinfo *pi = sco_pi(sk); + + lock_sock(sk); + + if (sk->sk_state == BT_CONNECT2 && + test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + hci_conn_accept(pi->conn->hcon, 0); + sk->sk_state = BT_CONFIG; + + release_sock(sk); + return 0; + } + + release_sock(sk); + + return bt_sock_recvmsg(iocb, sock, msg, len, flags); +} + static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; + u32 opt; BT_DBG("sk %p", sk); lock_sock(sk); switch (optname) { + + case BT_DEFER_SETUP: + if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { + err = -EINVAL; + break; + } + + if (get_user(opt, (u32 __user *) optval)) { + err = -EFAULT; + break; + } + + if (opt) + set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); + else + clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); + break; + default: err = -ENOPROTOOPT; break; @@ -753,6 +786,19 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char lock_sock(sk); switch (optname) { + + case BT_DEFER_SETUP: + if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { + err = -EINVAL; + break; + } + + if (put_user(test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags), + (u32 __user *) optval)) + err = -EFAULT; + + break; + default: err = -ENOPROTOOPT; break; @@ -830,6 +876,16 @@ static void sco_chan_del(struct sock *sk, int err) BT_DBG("sk %p, conn %p, err %d", sk, conn, err); + if (conn) { + sco_conn_lock(conn); + conn->sk = NULL; + sco_pi(sk)->conn = NULL; + sco_conn_unlock(conn); + + if (conn->hcon) + hci_conn_put(conn->hcon); + } + sk->sk_state = BT_CLOSED; sk->sk_err = err; sk->sk_state_change(sk); @@ -874,7 +930,10 @@ static void sco_conn_ready(struct sco_conn *conn) hci_conn_hold(conn->hcon); __sco_chan_add(conn, sk, parent); - sk->sk_state = BT_CONNECTED; + if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) + sk->sk_state = BT_CONNECT2; + else + sk->sk_state = BT_CONNECTED; /* Wake up parent */ parent->sk_data_ready(parent, 1); @@ -887,13 +946,13 @@ done: } /* ----- SCO interface with lower layer (HCI) ----- */ -int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) +int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct sock *sk; struct hlist_node *node; int lm = 0; - BT_DBG("hdev %s, bdaddr %s", hdev->name, batostr(bdaddr)); + BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets */ read_lock(&sco_sk_list.lock); @@ -904,6 +963,9 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr) || !bacmp(&bt_sk(sk)->src, BDADDR_ANY)) { lm |= HCI_LM_ACCEPT; + + if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) + *flags |= HCI_PROTO_DEFER; break; } } @@ -914,7 +976,7 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) void sco_connect_cfm(struct hci_conn *hcon, __u8 status) { - BT_DBG("hcon %p bdaddr %s status %d", hcon, batostr(&hcon->dst), status); + BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; @@ -959,8 +1021,8 @@ static int sco_debugfs_show(struct seq_file *f, void *p) read_lock(&sco_sk_list.lock); sk_for_each(sk, node, &sco_sk_list.head) { - seq_printf(f, "%s %s %d\n", batostr(&bt_sk(sk)->src), - batostr(&bt_sk(sk)->dst), sk->sk_state); + seq_printf(f, "%pMR %pMR %d\n", &bt_sk(sk)->src, + &bt_sk(sk)->dst, sk->sk_state); } read_unlock(&sco_sk_list.lock); @@ -992,7 +1054,7 @@ static const struct proto_ops sco_sock_ops = { .accept = sco_sock_accept, .getname = sco_sock_getname, .sendmsg = sco_sock_sendmsg, - .recvmsg = bt_sock_recvmsg, + .recvmsg = sco_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, .mmap = sock_no_mmap, diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 2ac8d50861e0..68a9587c9694 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -167,7 +167,7 @@ static struct sk_buff *smp_build_cmd(struct l2cap_conn *conn, u8 code, lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); lh->len = cpu_to_le16(sizeof(code) + dlen); - lh->cid = cpu_to_le16(L2CAP_CID_SMP); + lh->cid = __constant_cpu_to_le16(L2CAP_CID_SMP); memcpy(skb_put(skb, sizeof(code)), &code, sizeof(code)); @@ -267,7 +267,7 @@ static void smp_failure(struct l2cap_conn *conn, u8 reason, u8 send) clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->hcon->flags); mgmt_auth_failed(conn->hcon->hdev, conn->dst, hcon->type, - hcon->dst_type, reason); + hcon->dst_type, HCI_ERROR_AUTH_FAILURE); cancel_delayed_work_sync(&conn->security_timer); diff --git a/net/bridge/Makefile b/net/bridge/Makefile index d0359ea8ee79..e859098f5ee9 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -12,6 +12,6 @@ bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o bridge-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o -bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o +bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 070e8a68cfc6..7c78e2640190 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -313,6 +313,8 @@ static const struct net_device_ops br_netdev_ops = { .ndo_fdb_add = br_fdb_add, .ndo_fdb_del = br_fdb_delete, .ndo_fdb_dump = br_fdb_dump, + .ndo_bridge_getlink = br_getlink, + .ndo_bridge_setlink = br_setlink, }; static void br_dev_free(struct net_device *dev) @@ -356,7 +358,7 @@ void br_dev_setup(struct net_device *dev) br->bridge_id.prio[0] = 0x80; br->bridge_id.prio[1] = 0x00; - memcpy(br->group_addr, br_group_address, ETH_ALEN); + memcpy(br->group_addr, eth_reserved_addr_base, ETH_ALEN); br->stp_enabled = BR_NO_STP; br->group_fwd_mask = BR_GROUPFWD_DEFAULT; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 1c8fdc3558cd..37fe693471a8 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -366,11 +366,11 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) err = netdev_set_master(dev, br->dev); if (err) - goto err3; + goto err4; err = netdev_rx_handler_register(dev, br_handle_frame, p); if (err) - goto err4; + goto err5; dev->priv_flags |= IFF_BRIDGE_PORT; @@ -402,8 +402,10 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) return 0; -err4: +err5: netdev_set_master(dev, NULL); +err4: + br_netpoll_disable(p); err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 76f15fda0212..4b34207419b1 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -19,9 +19,6 @@ #include <linux/export.h> #include "br_private.h" -/* Bridge group multicast address 802.1d (pg 51). */ -const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; - /* Hook for brouter */ br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; EXPORT_SYMBOL(br_should_route_hook); @@ -127,18 +124,6 @@ static int br_handle_local_finish(struct sk_buff *skb) return 0; /* process further */ } -/* Does address match the link local multicast address. - * 01:80:c2:00:00:0X - */ -static inline int is_link_local(const unsigned char *dest) -{ - __be16 *a = (__be16 *)dest; - static const __be16 *b = (const __be16 *)br_group_address; - static const __be16 m = cpu_to_be16(0xfff0); - - return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; -} - /* * Return NULL if skb is handled * note: already called with rcu_read_lock @@ -162,7 +147,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) p = br_port_get_rcu(skb->dev); - if (unlikely(is_link_local(dest))) { + if (unlikely(is_link_local_ether_addr(dest))) { /* * See IEEE 802.1D Table 7-10 Reserved addresses * diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 7222fe1d5460..cd8c3a44ab7d 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -85,13 +85,14 @@ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, /* called with RTNL */ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) { + struct net *net = dev_net(br->dev); struct net_device *dev; int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - dev = __dev_get_by_index(dev_net(br->dev), ifindex); + dev = __dev_get_by_index(net, ifindex); if (dev == NULL) return -EINVAL; @@ -178,25 +179,25 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } case BRCTL_SET_BRIDGE_FORWARD_DELAY: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; return br_set_forward_delay(br, args[1]); case BRCTL_SET_BRIDGE_HELLO_TIME: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; return br_set_hello_time(br, args[1]); case BRCTL_SET_BRIDGE_MAX_AGE: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; return br_set_max_age(br, args[1]); case BRCTL_SET_AGEING_TIME: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br->ageing_time = clock_t_to_jiffies(args[1]); @@ -236,14 +237,14 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } case BRCTL_SET_BRIDGE_STP_STATE: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_stp_set_enabled(br, args[1]); return 0; case BRCTL_SET_BRIDGE_PRIORITY: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); @@ -256,7 +257,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) struct net_bridge_port *p; int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); @@ -273,7 +274,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) struct net_bridge_port *p; int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); @@ -330,7 +331,7 @@ static int old_deviceless(struct net *net, void __user *uarg) { char buf[IFNAMSIZ]; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, (void __user *)args[1], IFNAMSIZ)) @@ -360,7 +361,7 @@ int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uar { char buf[IFNAMSIZ]; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, uarg, IFNAMSIZ)) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c new file mode 100644 index 000000000000..acc9f4cc18f7 --- /dev/null +++ b/net/bridge/br_mdb.c @@ -0,0 +1,493 @@ +#include <linux/err.h> +#include <linux/igmp.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/if_ether.h> +#include <net/ip.h> +#include <net/netlink.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#endif + +#include "br_private.h" + +static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + struct net_bridge_port *p; + struct hlist_node *n; + struct nlattr *nest; + + if (!br->multicast_router || hlist_empty(&br->router_list)) + return 0; + + nest = nla_nest_start(skb, MDBA_ROUTER); + if (nest == NULL) + return -EMSGSIZE; + + hlist_for_each_entry_rcu(p, n, &br->router_list, rlist) { + if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex)) + goto fail; + } + + nla_nest_end(skb, nest); + return 0; +fail: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + struct net_bridge_mdb_htable *mdb; + struct nlattr *nest, *nest2; + int i, err = 0; + int idx = 0, s_idx = cb->args[1]; + + if (br->multicast_disabled) + return 0; + + mdb = rcu_dereference(br->mdb); + if (!mdb) + return 0; + + nest = nla_nest_start(skb, MDBA_MDB); + if (nest == NULL) + return -EMSGSIZE; + + for (i = 0; i < mdb->max; i++) { + struct hlist_node *h; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p, **pp; + struct net_bridge_port *port; + + hlist_for_each_entry_rcu(mp, h, &mdb->mhash[i], hlist[mdb->ver]) { + if (idx < s_idx) + goto skip; + + nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY); + if (nest2 == NULL) { + err = -EMSGSIZE; + goto out; + } + + for (pp = &mp->ports; + (p = rcu_dereference(*pp)) != NULL; + pp = &p->next) { + port = p->port; + if (port) { + struct br_mdb_entry e; + e.ifindex = port->dev->ifindex; + e.state = p->state; + if (p->addr.proto == htons(ETH_P_IP)) + e.addr.u.ip4 = p->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + if (p->addr.proto == htons(ETH_P_IPV6)) + e.addr.u.ip6 = p->addr.u.ip6; +#endif + e.addr.proto = p->addr.proto; + if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(e), &e)) { + nla_nest_cancel(skb, nest2); + err = -EMSGSIZE; + goto out; + } + } + } + nla_nest_end(skb, nest2); + skip: + idx++; + } + } + +out: + cb->args[1] = idx; + nla_nest_end(skb, nest); + return err; +} + +static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net_device *dev; + struct net *net = sock_net(skb->sk); + struct nlmsghdr *nlh = NULL; + int idx = 0, s_idx; + + s_idx = cb->args[0]; + + rcu_read_lock(); + + /* In theory this could be wrapped to 0... */ + cb->seq = net->dev_base_seq + br_mdb_rehash_seq; + + for_each_netdev_rcu(net, dev) { + if (dev->priv_flags & IFF_EBRIDGE) { + struct br_port_msg *bpm; + + if (idx < s_idx) + goto skip; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_GETMDB, + sizeof(*bpm), NLM_F_MULTI); + if (nlh == NULL) + break; + + bpm = nlmsg_data(nlh); + bpm->ifindex = dev->ifindex; + if (br_mdb_fill_info(skb, cb, dev) < 0) + goto out; + if (br_rports_fill_info(skb, cb, dev) < 0) + goto out; + + cb->args[1] = 0; + nlmsg_end(skb, nlh); + skip: + idx++; + } + } + +out: + if (nlh) + nlmsg_end(skb, nlh); + rcu_read_unlock(); + cb->args[0] = idx; + return skb->len; +} + +static int nlmsg_populate_mdb_fill(struct sk_buff *skb, + struct net_device *dev, + struct br_mdb_entry *entry, u32 pid, + u32 seq, int type, unsigned int flags) +{ + struct nlmsghdr *nlh; + struct br_port_msg *bpm; + struct nlattr *nest, *nest2; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + bpm = nlmsg_data(nlh); + bpm->family = AF_BRIDGE; + bpm->ifindex = dev->ifindex; + nest = nla_nest_start(skb, MDBA_MDB); + if (nest == NULL) + goto cancel; + nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY); + if (nest2 == NULL) + goto end; + + if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry)) + goto end; + + nla_nest_end(skb, nest2); + nla_nest_end(skb, nest); + return nlmsg_end(skb, nlh); + +end: + nla_nest_end(skb, nest); +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t rtnl_mdb_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct br_port_msg)) + + nla_total_size(sizeof(struct br_mdb_entry)); +} + +static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, + int type) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC); + if (!skb) + goto errout; + + err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_MDB, err); +} + +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type) +{ + struct br_mdb_entry entry; + + entry.ifindex = port->dev->ifindex; + entry.addr.proto = group->proto; + entry.addr.u.ip4 = group->u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + entry.addr.u.ip6 = group->u.ip6; +#endif + __br_mdb_notify(dev, &entry, type); +} + +static bool is_valid_mdb_entry(struct br_mdb_entry *entry) +{ + if (entry->ifindex == 0) + return false; + + if (entry->addr.proto == htons(ETH_P_IP)) { + if (!ipv4_is_multicast(entry->addr.u.ip4)) + return false; + if (ipv4_is_local_multicast(entry->addr.u.ip4)) + return false; +#if IS_ENABLED(CONFIG_IPV6) + } else if (entry->addr.proto == htons(ETH_P_IPV6)) { + if (!ipv6_is_transient_multicast(&entry->addr.u.ip6)) + return false; +#endif + } else + return false; + if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) + return false; + + return true; +} + +static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, + struct net_device **pdev, struct br_mdb_entry **pentry) +{ + struct net *net = sock_net(skb->sk); + struct br_mdb_entry *entry; + struct br_port_msg *bpm; + struct nlattr *tb[MDBA_SET_ENTRY_MAX+1]; + struct net_device *dev; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL); + if (err < 0) + return err; + + bpm = nlmsg_data(nlh); + if (bpm->ifindex == 0) { + pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, bpm->ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n"); + return -ENODEV; + } + + if (!(dev->priv_flags & IFF_EBRIDGE)) { + pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n"); + return -EOPNOTSUPP; + } + + *pdev = dev; + + if (!tb[MDBA_SET_ENTRY] || + nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) { + pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n"); + return -EINVAL; + } + + entry = nla_data(tb[MDBA_SET_ENTRY]); + if (!is_valid_mdb_entry(entry)) { + pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n"); + return -EINVAL; + } + + *pentry = entry; + return 0; +} + +static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, + struct br_ip *group, unsigned char state) +{ + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_mdb_htable *mdb; + int err; + + mdb = mlock_dereference(br->mdb, br); + mp = br_mdb_ip_get(mdb, group); + if (!mp) { + mp = br_multicast_new_group(br, port, group); + err = PTR_ERR(mp); + if (IS_ERR(mp)) + return err; + } + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port == port) + return -EEXIST; + if ((unsigned long)p->port < (unsigned long)port) + break; + } + + p = br_multicast_new_port_group(port, group, *pp, state); + if (unlikely(!p)) + return -ENOMEM; + rcu_assign_pointer(*pp, p); + + br_mdb_notify(br->dev, port, group, RTM_NEWMDB); + return 0; +} + +static int __br_mdb_add(struct net *net, struct net_bridge *br, + struct br_mdb_entry *entry) +{ + struct br_ip ip; + struct net_device *dev; + struct net_bridge_port *p; + int ret; + + if (!netif_running(br->dev) || br->multicast_disabled) + return -EINVAL; + + dev = __dev_get_by_index(net, entry->ifindex); + if (!dev) + return -ENODEV; + + p = br_port_get_rtnl(dev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + + ip.proto = entry->addr.proto; + if (ip.proto == htons(ETH_P_IP)) + ip.u.ip4 = entry->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + else + ip.u.ip6 = entry->addr.u.ip6; +#endif + + spin_lock_bh(&br->multicast_lock); + ret = br_mdb_add_group(br, p, &ip, entry->state); + spin_unlock_bh(&br->multicast_lock); + return ret; +} + +static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct net *net = sock_net(skb->sk); + struct br_mdb_entry *entry; + struct net_device *dev; + struct net_bridge *br; + int err; + + err = br_mdb_parse(skb, nlh, &dev, &entry); + if (err < 0) + return err; + + br = netdev_priv(dev); + + err = __br_mdb_add(net, br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_NEWMDB); + return err; +} + +static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu **pp; + struct br_ip ip; + int err = -EINVAL; + + if (!netif_running(br->dev) || br->multicast_disabled) + return -EINVAL; + + if (timer_pending(&br->multicast_querier_timer)) + return -EBUSY; + + ip.proto = entry->addr.proto; + if (ip.proto == htons(ETH_P_IP)) + ip.u.ip4 = entry->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + else + ip.u.ip6 = entry->addr.u.ip6; +#endif + + spin_lock_bh(&br->multicast_lock); + mdb = mlock_dereference(br->mdb, br); + + mp = br_mdb_ip_get(mdb, &ip); + if (!mp) + goto unlock; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (!p->port || p->port->dev->ifindex != entry->ifindex) + continue; + + if (p->port->state == BR_STATE_DISABLED) + goto unlock; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + err = 0; + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + break; + } + +unlock: + spin_unlock_bh(&br->multicast_lock); + return err; +} + +static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct net_device *dev; + struct br_mdb_entry *entry; + struct net_bridge *br; + int err; + + err = br_mdb_parse(skb, nlh, &dev, &entry); + if (err < 0) + return err; + + br = netdev_priv(dev); + + err = __br_mdb_del(br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_DELMDB); + return err; +} + +void br_mdb_init(void) +{ + rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL); + rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, NULL); +} + +void br_mdb_uninit(void) +{ + rtnl_unregister(PF_BRIDGE, RTM_GETMDB); + rtnl_unregister(PF_BRIDGE, RTM_NEWMDB); + rtnl_unregister(PF_BRIDGE, RTM_DELMDB); +} diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 241743417f49..6d6f26531de2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -27,25 +27,13 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/mld.h> -#include <net/addrconf.h> #include <net/ip6_checksum.h> #endif #include "br_private.h" -#define mlock_dereference(X, br) \ - rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) - static void br_multicast_start_querier(struct net_bridge *br); - -#if IS_ENABLED(CONFIG_IPV6) -static inline int ipv6_is_transient_multicast(const struct in6_addr *addr) -{ - if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr)) - return 1; - return 0; -} -#endif +unsigned int br_mdb_rehash_seq; static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) { @@ -103,8 +91,8 @@ static struct net_bridge_mdb_entry *__br_mdb_ip_get( return NULL; } -static struct net_bridge_mdb_entry *br_mdb_ip_get( - struct net_bridge_mdb_htable *mdb, struct br_ip *dst) +struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, + struct br_ip *dst) { if (!mdb) return NULL; @@ -207,7 +195,7 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, return maxlen > elasticity ? -EINVAL : 0; } -static void br_multicast_free_pg(struct rcu_head *head) +void br_multicast_free_pg(struct rcu_head *head) { struct net_bridge_port_group *p = container_of(head, struct net_bridge_port_group, rcu); @@ -291,7 +279,7 @@ static void br_multicast_port_group_expired(unsigned long data) spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&pg->timer) || - hlist_unhashed(&pg->mglist)) + hlist_unhashed(&pg->mglist) || pg->state & MDB_PERMANENT) goto out; br_multicast_del_pg(br, pg); @@ -338,6 +326,7 @@ static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max, return err; } + br_mdb_rehash_seq++; call_rcu_bh(&mdb->rcu, br_mdb_free); out: @@ -582,9 +571,8 @@ err: return mp; } -static struct net_bridge_mdb_entry *br_multicast_new_group( - struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group) +struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, + struct net_bridge_port *port, struct br_ip *group) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; @@ -631,6 +619,28 @@ out: return mp; } +struct net_bridge_port_group *br_multicast_new_port_group( + struct net_bridge_port *port, + struct br_ip *group, + struct net_bridge_port_group __rcu *next, + unsigned char state) +{ + struct net_bridge_port_group *p; + + p = kzalloc(sizeof(*p), GFP_ATOMIC); + if (unlikely(!p)) + return NULL; + + p->addr = *group; + p->port = port; + p->state = state; + rcu_assign_pointer(p->next, next); + hlist_add_head(&p->mglist, &port->mglist); + setup_timer(&p->timer, br_multicast_port_group_expired, + (unsigned long)p); + return p; +} + static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group) @@ -666,19 +676,11 @@ static int br_multicast_add_group(struct net_bridge *br, break; } - p = kzalloc(sizeof(*p), GFP_ATOMIC); - err = -ENOMEM; + p = br_multicast_new_port_group(port, group, *pp, MDB_TEMPORARY); if (unlikely(!p)) goto err; - - p->addr = *group; - p->port = port; - p->next = *pp; - hlist_add_head(&p->mglist, &port->mglist); - setup_timer(&p->timer, br_multicast_port_group_expired, - (unsigned long)p); - rcu_assign_pointer(*pp, p); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -1138,7 +1140,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct mld_msg *mld = (struct mld_msg *) icmp6_hdr(skb); + struct mld_msg *mld; struct net_bridge_mdb_entry *mp; struct mld2_query *mld2q; struct net_bridge_port_group *p; @@ -1172,7 +1174,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; - max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(mld2q->mld2q_mrc) : 1; + max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(ntohs(mld2q->mld2q_mrc)) : 1; } if (!group) @@ -1225,6 +1227,28 @@ static void br_multicast_leave_group(struct net_bridge *br, if (!mp) goto out; + if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { + struct net_bridge_port_group __rcu **pp; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + + rcu_assign_pointer(*pp, p->next); + hlist_del_init(&p->mglist); + del_timer(&p->timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + br_mdb_notify(br->dev, port, group, RTM_DELMDB); + + if (!mp->ports && !mp->mglist && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + } + goto out; + } + now = jiffies; time = now + br->multicast_last_member_count * br->multicast_last_member_interval; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 093f527276a3..5dc66abcc9e2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -20,16 +20,44 @@ #include "br_private.h" #include "br_private_stp.h" +static inline size_t br_port_info_size(void) +{ + return nla_total_size(1) /* IFLA_BRPORT_STATE */ + + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + + nla_total_size(4) /* IFLA_BRPORT_COST */ + + nla_total_size(1) /* IFLA_BRPORT_MODE */ + + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + + 0; +} + static inline size_t br_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) - + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ - + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ - + nla_total_size(4) /* IFLA_MASTER */ - + nla_total_size(4) /* IFLA_MTU */ - + nla_total_size(4) /* IFLA_LINK */ - + nla_total_size(1) /* IFLA_OPERSTATE */ - + nla_total_size(1); /* IFLA_PROTINFO */ + + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(4) /* IFLA_MTU */ + + nla_total_size(4) /* IFLA_LINK */ + + nla_total_size(1) /* IFLA_OPERSTATE */ + + nla_total_size(br_port_info_size()); /* IFLA_PROTINFO */ +} + +static int br_port_fill_attrs(struct sk_buff *skb, + const struct net_bridge_port *p) +{ + u8 mode = !!(p->flags & BR_HAIRPIN_MODE); + + if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || + nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || + nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || + nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || + nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || + nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) || + nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE))) + return -EMSGSIZE; + + return 0; } /* @@ -67,10 +95,18 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev->iflink && - nla_put_u32(skb, IFLA_LINK, dev->iflink)) || - (event == RTM_NEWLINK && - nla_put_u8(skb, IFLA_PROTINFO, port->state))) + nla_put_u32(skb, IFLA_LINK, dev->iflink))) goto nla_put_failure; + + if (event == RTM_NEWLINK) { + struct nlattr *nest + = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED); + + if (nest == NULL || br_port_fill_attrs(skb, port) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest); + } + return nlmsg_end(skb, nlh); nla_put_failure: @@ -111,89 +147,134 @@ errout: /* * Dump information about all ports, in response to GETLINK */ -static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev) +{ + int err = 0; + struct net_bridge_port *port = br_port_get_rcu(dev); + + /* not a bridge port */ + if (!port) + goto out; + + err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI); +out: + return err; +} + +static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = { + [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, + [IFLA_BRPORT_COST] = { .type = NLA_U32 }, + [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, + [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, + [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, + [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, +}; + +/* Change the state of the port and notify spanning tree */ +static int br_set_port_state(struct net_bridge_port *p, u8 state) +{ + if (state > BR_STATE_BLOCKING) + return -EINVAL; + + /* if kernel STP is running, don't allow changes */ + if (p->br->stp_enabled == BR_KERNEL_STP) + return -EBUSY; + + if (!netif_running(p->dev) || + (!netif_carrier_ok(p->dev) && state != BR_STATE_DISABLED)) + return -ENETDOWN; + + p->state = state; + br_log_state(p); + br_port_state_selection(p->br); + return 0; +} + +/* Set/clear or port flags based on attribute */ +static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], + int attrtype, unsigned long mask) +{ + if (tb[attrtype]) { + u8 flag = nla_get_u8(tb[attrtype]); + if (flag) + p->flags |= mask; + else + p->flags &= ~mask; + } +} + +/* Process bridge protocol info on port */ +static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) { - struct net *net = sock_net(skb->sk); - struct net_device *dev; - int idx; - - idx = 0; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { - struct net_bridge_port *port = br_port_get_rcu(dev); - - /* not a bridge port */ - if (!port || idx < cb->args[0]) - goto skip; - - if (br_fill_ifinfo(skb, port, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWLINK, - NLM_F_MULTI) < 0) - break; -skip: - ++idx; + int err; + + br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); + br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); + br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); + + if (tb[IFLA_BRPORT_COST]) { + err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); + if (err) + return err; + } + + if (tb[IFLA_BRPORT_PRIORITY]) { + err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); + if (err) + return err; } - rcu_read_unlock(); - cb->args[0] = idx; - return skb->len; + if (tb[IFLA_BRPORT_STATE]) { + err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); + if (err) + return err; + } + return 0; } -/* - * Change state of port (ie from forwarding to blocking etc) - * Used by spanning tree in user space. - */ -static int br_rtm_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +/* Change state and parameters on port. */ +int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) { - struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct nlattr *protinfo; - struct net_device *dev; struct net_bridge_port *p; - u8 new_state; - - if (nlmsg_len(nlh) < sizeof(*ifm)) - return -EINVAL; + struct nlattr *tb[IFLA_BRPORT_MAX + 1]; + int err; ifm = nlmsg_data(nlh); - if (ifm->ifi_family != AF_BRIDGE) - return -EPFNOSUPPORT; protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO); - if (!protinfo || nla_len(protinfo) < sizeof(u8)) - return -EINVAL; - - new_state = nla_get_u8(protinfo); - if (new_state > BR_STATE_BLOCKING) - return -EINVAL; - - dev = __dev_get_by_index(net, ifm->ifi_index); - if (!dev) - return -ENODEV; + if (!protinfo) + return 0; p = br_port_get_rtnl(dev); if (!p) return -EINVAL; - /* if kernel STP is running, don't allow changes */ - if (p->br->stp_enabled == BR_KERNEL_STP) - return -EBUSY; - - if (!netif_running(dev) || - (!netif_carrier_ok(dev) && new_state != BR_STATE_DISABLED)) - return -ENETDOWN; - - p->state = new_state; - br_log_state(p); + if (protinfo->nla_type & NLA_F_NESTED) { + err = nla_parse_nested(tb, IFLA_BRPORT_MAX, + protinfo, ifla_brport_policy); + if (err) + return err; + + spin_lock_bh(&p->br->lock); + err = br_setport(p, tb); + spin_unlock_bh(&p->br->lock); + } else { + /* Binary compatability with old RSTP */ + if (nla_len(protinfo) < sizeof(u8)) + return -EINVAL; - spin_lock_bh(&p->br->lock); - br_port_state_selection(p->br); - spin_unlock_bh(&p->br->lock); + spin_lock_bh(&p->br->lock); + err = br_set_port_state(p, nla_get_u8(protinfo)); + spin_unlock_bh(&p->br->lock); + } - br_ifinfo_notify(RTM_NEWLINK, p); + if (err == 0) + br_ifinfo_notify(RTM_NEWLINK, p); - return 0; + return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -220,31 +301,19 @@ int __init br_netlink_init(void) { int err; + br_mdb_init(); err = rtnl_link_register(&br_link_ops); - if (err < 0) - goto err1; - - err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, - br_dump_ifinfo, NULL); - if (err) - goto err2; - err = __rtnl_register(PF_BRIDGE, RTM_SETLINK, - br_rtm_setlink, NULL, NULL); if (err) - goto err3; + goto out; return 0; - -err3: - rtnl_unregister_all(PF_BRIDGE); -err2: - rtnl_link_unregister(&br_link_ops); -err1: +out: + br_mdb_uninit(); return err; } void __exit br_netlink_fini(void) { + br_mdb_uninit(); rtnl_link_unregister(&br_link_ops); - rtnl_unregister_all(PF_BRIDGE); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 9b278c4ebee1..711094aed41a 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -83,6 +83,7 @@ struct net_bridge_port_group { struct rcu_head rcu; struct timer_list timer; struct br_ip addr; + unsigned char state; }; struct net_bridge_mdb_entry @@ -135,6 +136,9 @@ struct net_bridge_port unsigned long flags; #define BR_HAIRPIN_MODE 0x00000001 +#define BR_BPDU_GUARD 0x00000002 +#define BR_ROOT_BLOCK 0x00000004 +#define BR_MULTICAST_FAST_LEAVE 0x00000008 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING u32 multicast_startup_queries_sent; @@ -158,7 +162,9 @@ struct net_bridge_port static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) { - struct net_bridge_port *port = rcu_dereference(dev->rx_handler_data); + struct net_bridge_port *port = + rcu_dereference_rtnl(dev->rx_handler_data); + return br_port_exists(dev) ? port : NULL; } @@ -288,7 +294,6 @@ struct br_input_skb_cb { pr_debug("%s: " format, (br)->dev->name, ##args) extern struct notifier_block br_device_notifier; -extern const u8 br_group_address[ETH_ALEN]; /* called under bridge lock */ static inline int br_is_root_bridge(const struct net_bridge *br) @@ -407,6 +412,7 @@ extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __us /* br_multicast.c */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING +extern unsigned int br_mdb_rehash_seq; extern int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb); @@ -429,6 +435,34 @@ extern int br_multicast_set_port_router(struct net_bridge_port *p, extern int br_multicast_toggle(struct net_bridge *br, unsigned long val); extern int br_multicast_set_querier(struct net_bridge *br, unsigned long val); extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val); +extern struct net_bridge_mdb_entry *br_mdb_ip_get( + struct net_bridge_mdb_htable *mdb, + struct br_ip *dst); +extern struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, + struct net_bridge_port *port, struct br_ip *group); +extern void br_multicast_free_pg(struct rcu_head *head); +extern struct net_bridge_port_group *br_multicast_new_port_group( + struct net_bridge_port *port, + struct br_ip *group, + struct net_bridge_port_group *next, + unsigned char state); +extern void br_mdb_init(void); +extern void br_mdb_uninit(void); +extern void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type); + +#define mlock_dereference(X, br) \ + rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) + +#if IS_ENABLED(CONFIG_IPV6) +#include <net/addrconf.h> +static inline int ipv6_is_transient_multicast(const struct in6_addr *addr) +{ + if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr)) + return 1; + return 0; +} +#endif static inline bool br_multicast_is_router(struct net_bridge *br) { @@ -492,6 +526,12 @@ static inline bool br_multicast_is_router(struct net_bridge *br) { return 0; } +static inline void br_mdb_init(void) +{ +} +static inline void br_mdb_uninit(void) +{ +} #endif /* br_netfilter.c */ @@ -553,6 +593,9 @@ extern struct rtnl_link_ops br_link_ops; extern int br_netlink_init(void); extern void br_netlink_fini(void); extern void br_ifinfo_notify(int event, struct net_bridge_port *port); +extern int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg); +extern int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ @@ -566,10 +609,10 @@ extern void br_sysfs_delbr(struct net_device *dev); #else -#define br_sysfs_addif(p) (0) -#define br_sysfs_renameif(p) (0) -#define br_sysfs_addbr(dev) (0) -#define br_sysfs_delbr(dev) do { } while(0) +static inline int br_sysfs_addif(struct net_bridge_port *p) { return 0; } +static inline int br_sysfs_renameif(struct net_bridge_port *p) { return 0; } +static inline int br_sysfs_addbr(struct net_device *dev) { return 0; } +static inline void br_sysfs_delbr(struct net_device *dev) { return; } #endif /* CONFIG_SYSFS */ #endif diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index af9a12099ba4..b01849a74310 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -100,6 +100,21 @@ static int br_should_become_root_port(const struct net_bridge_port *p, return 0; } +static void br_root_port_block(const struct net_bridge *br, + struct net_bridge_port *p) +{ + + br_notice(br, "port %u(%s) tried to become root port (blocked)", + (unsigned int) p->port_no, p->dev->name); + + p->state = BR_STATE_LISTENING; + br_log_state(p); + br_ifinfo_notify(RTM_NEWLINK, p); + + if (br->forward_delay > 0) + mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); +} + /* called under bridge lock */ static void br_root_selection(struct net_bridge *br) { @@ -107,7 +122,12 @@ static void br_root_selection(struct net_bridge *br) u16 root_port = 0; list_for_each_entry(p, &br->port_list, list) { - if (br_should_become_root_port(p, root_port)) + if (!br_should_become_root_port(p, root_port)) + continue; + + if (p->flags & BR_ROOT_BLOCK) + br_root_port_block(br, p); + else root_port = p->port_no; } diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index fd30a6022dea..7f884e3fb955 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -170,6 +170,13 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (!ether_addr_equal(dest, br->group_addr)) goto out; + if (p->flags & BR_BPDU_GUARD) { + br_notice(br, "BPDU received on blocked port %u(%s)\n", + (unsigned int) p->port_no, p->dev->name); + br_stp_disable_port(p); + goto out; + } + buf = skb_pull(skb, 3); if (buf[0] == BPDU_TYPE_CONFIG) { diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index c5c059333eab..5913a3a0047b 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -14,6 +14,7 @@ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> @@ -36,7 +37,7 @@ static ssize_t store_bridge_parm(struct device *d, unsigned long val; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; val = simple_strtoul(buf, &endp, 0); @@ -132,7 +133,7 @@ static ssize_t store_stp_state(struct device *d, char *endp; unsigned long val; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; val = simple_strtoul(buf, &endp, 0); @@ -165,7 +166,7 @@ static ssize_t store_group_fwd_mask(struct device *d, char *endp; unsigned long val; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; val = simple_strtoul(buf, &endp, 0); @@ -297,23 +298,18 @@ static ssize_t store_group_addr(struct device *d, const char *buf, size_t len) { struct net_bridge *br = to_bridge(d); - unsigned int new_addr[6]; + u8 new_addr[6]; int i; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; - if (sscanf(buf, "%x:%x:%x:%x:%x:%x", + if (sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &new_addr[0], &new_addr[1], &new_addr[2], &new_addr[3], &new_addr[4], &new_addr[5]) != 6) return -EINVAL; - /* Must be 01:80:c2:00:00:0X */ - for (i = 0; i < 5; i++) - if (new_addr[i] != br_group_address[i]) - return -EINVAL; - - if (new_addr[5] & ~0xf) + if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ @@ -337,7 +333,7 @@ static ssize_t store_flush(struct device *d, { struct net_bridge *br = to_bridge(d); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_fdb_flush(br); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 13b36bdc76a7..a1ef1b6e14dc 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -34,6 +34,28 @@ const struct brport_attribute brport_attr_##_name = { \ .store = _store, \ }; +#define BRPORT_ATTR_FLAG(_name, _mask) \ +static ssize_t show_##_name(struct net_bridge_port *p, char *buf) \ +{ \ + return sprintf(buf, "%d\n", !!(p->flags & _mask)); \ +} \ +static int store_##_name(struct net_bridge_port *p, unsigned long v) \ +{ \ + unsigned long flags = p->flags; \ + if (v) \ + flags |= _mask; \ + else \ + flags &= ~_mask; \ + if (flags != p->flags) { \ + p->flags = flags; \ + br_ifinfo_notify(RTM_NEWLINK, p); \ + } \ + return 0; \ +} \ +static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR, \ + show_##_name, store_##_name) + + static ssize_t show_path_cost(struct net_bridge_port *p, char *buf) { return sprintf(buf, "%d\n", p->path_cost); @@ -133,21 +155,9 @@ static int store_flush(struct net_bridge_port *p, unsigned long v) } static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush); -static ssize_t show_hairpin_mode(struct net_bridge_port *p, char *buf) -{ - int hairpin_mode = (p->flags & BR_HAIRPIN_MODE) ? 1 : 0; - return sprintf(buf, "%d\n", hairpin_mode); -} -static int store_hairpin_mode(struct net_bridge_port *p, unsigned long v) -{ - if (v) - p->flags |= BR_HAIRPIN_MODE; - else - p->flags &= ~BR_HAIRPIN_MODE; - return 0; -} -static BRPORT_ATTR(hairpin_mode, S_IRUGO | S_IWUSR, - show_hairpin_mode, store_hairpin_mode); +BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE); +BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD); +BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -162,6 +172,8 @@ static int store_multicast_router(struct net_bridge_port *p, } static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, store_multicast_router); + +BRPORT_ATTR_FLAG(multicast_fast_leave, BR_MULTICAST_FAST_LEAVE); #endif static const struct brport_attribute *brport_attrs[] = { @@ -181,8 +193,11 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_hold_timer, &brport_attr_flush, &brport_attr_hairpin_mode, + &brport_attr_bpdu_guard, + &brport_attr_root_block, #ifdef CONFIG_BRIDGE_IGMP_SNOOPING &brport_attr_multicast_router, + &brport_attr_multicast_fast_leave, #endif NULL }; @@ -209,7 +224,7 @@ static ssize_t brport_store(struct kobject * kobj, char *endp; unsigned long val; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(dev_net(p->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; val = simple_strtoul(buf, &endp, 0); diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index fd7cbf5aa895..3ebc8cbc91ff 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -126,20 +126,16 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, struct net_device *dev = arg; struct caif_dev_common common; struct cflayer *layer, *link_support; - struct usbnet *usbnet = netdev_priv(dev); - struct usb_device *usbdev = usbnet->udev; - struct ethtool_drvinfo drvinfo; + struct usbnet *usbnet; + struct usb_device *usbdev; - /* - * Quirks: High-jack ethtool to find if we have a NCM device, - * and find it's VID/PID. - */ - if (dev->ethtool_ops == NULL || dev->ethtool_ops->get_drvinfo == NULL) + /* Check whether we have a NCM device, and find its VID/PID. */ + if (!(dev->dev.parent && dev->dev.parent->driver && + strcmp(dev->dev.parent->driver->name, "cdc_ncm") == 0)) return 0; - dev->ethtool_ops->get_drvinfo(dev, &drvinfo); - if (strncmp(drvinfo.driver, "cdc_ncm", 7) != 0) - return 0; + usbnet = netdev_priv(dev); + usbdev = usbnet->udev; pr_debug("USB CDC NCM device VID:0x%4x PID:0x%4x\n", le16_to_cpu(usbdev->descriptor.idVendor), diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 44f270fc2d06..a376ec1ac0a7 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -515,8 +515,7 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) client_layer : NULL); } - if (req != NULL) - kfree(req); + kfree(req); spin_unlock_bh(&cfctrl->info_list_lock); } diff --git a/net/can/bcm.c b/net/can/bcm.c index 6f747582718e..969b7cdff59d 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1084,6 +1084,9 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->sk = sk; op->ifindex = ifindex; + /* ifindex for timeout events w/o previous frame reception */ + op->rx_ifindex = ifindex; + /* initialize uninitialized (kzalloc) structure */ hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); op->timer.function = bcm_rx_timeout_handler; diff --git a/net/can/gw.c b/net/can/gw.c index 1f5c9785a262..574dda78eb0f 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -751,6 +751,9 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct cgw_job *gwj; int err = 0; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; @@ -839,6 +842,9 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct can_can_gw ccgw; int err = 0; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index a8020293f342..ee71ea26777a 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -305,7 +305,6 @@ ceph_parse_options(char *options, const char *dev_name, /* start with defaults */ opt->flags = CEPH_OPT_DEFAULT; - opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT; opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */ opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; /* seconds */ @@ -391,7 +390,7 @@ ceph_parse_options(char *options, const char *dev_name, /* misc */ case Opt_osdtimeout: - opt->osd_timeout = intval; + pr_warning("ignoring deprecated osdtimeout option\n"); break; case Opt_osdkeepalivetimeout: opt->osd_keepalive_timeout = intval; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 159aa8bef9e7..5ccf87ed8d68 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -506,6 +506,7 @@ static void reset_connection(struct ceph_connection *con) { /* reset connection, out_queue, msg_ and connect_seq */ /* discard existing out_queue and msg_seq */ + dout("reset_connection %p\n", con); ceph_msg_remove_list(&con->out_queue); ceph_msg_remove_list(&con->out_sent); @@ -561,7 +562,7 @@ void ceph_con_open(struct ceph_connection *con, mutex_lock(&con->mutex); dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr)); - BUG_ON(con->state != CON_STATE_CLOSED); + WARN_ON(con->state != CON_STATE_CLOSED); con->state = CON_STATE_PREOPEN; con->peer_name.type = (__u8) entity_type; @@ -1506,13 +1507,6 @@ static int process_banner(struct ceph_connection *con) return 0; } -static void fail_protocol(struct ceph_connection *con) -{ - reset_connection(con); - BUG_ON(con->state != CON_STATE_NEGOTIATING); - con->state = CON_STATE_CLOSED; -} - static int process_connect(struct ceph_connection *con) { u64 sup_feat = con->msgr->supported_features; @@ -1530,7 +1524,7 @@ static int process_connect(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), sup_feat, server_feat, server_feat & ~sup_feat); con->error_msg = "missing required protocol features"; - fail_protocol(con); + reset_connection(con); return -1; case CEPH_MSGR_TAG_BADPROTOVER: @@ -1541,7 +1535,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->out_connect.protocol_version), le32_to_cpu(con->in_reply.protocol_version)); con->error_msg = "protocol version mismatch"; - fail_protocol(con); + reset_connection(con); return -1; case CEPH_MSGR_TAG_BADAUTHORIZER: @@ -1631,11 +1625,11 @@ static int process_connect(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), req_feat, server_feat, req_feat & ~server_feat); con->error_msg = "missing required protocol features"; - fail_protocol(con); + reset_connection(con); return -1; } - BUG_ON(con->state != CON_STATE_NEGOTIATING); + WARN_ON(con->state != CON_STATE_NEGOTIATING); con->state = CON_STATE_OPEN; con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); @@ -2132,7 +2126,6 @@ more: if (ret < 0) goto out; - BUG_ON(con->state != CON_STATE_CONNECTING); con->state = CON_STATE_NEGOTIATING; /* @@ -2160,7 +2153,7 @@ more: goto more; } - BUG_ON(con->state != CON_STATE_OPEN); + WARN_ON(con->state != CON_STATE_OPEN); if (con->in_base_pos < 0) { /* @@ -2244,22 +2237,62 @@ bad_tag: /* - * Atomically queue work on a connection. Bump @con reference to - * avoid races with connection teardown. + * Atomically queue work on a connection after the specified delay. + * Bump @con reference to avoid races with connection teardown. + * Returns 0 if work was queued, or an error code otherwise. */ -static void queue_con(struct ceph_connection *con) +static int queue_con_delay(struct ceph_connection *con, unsigned long delay) { if (!con->ops->get(con)) { - dout("queue_con %p ref count 0\n", con); - return; + dout("%s %p ref count 0\n", __func__, con); + + return -ENOENT; } - if (!queue_delayed_work(ceph_msgr_wq, &con->work, 0)) { - dout("queue_con %p - already queued\n", con); + if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) { + dout("%s %p - already queued\n", __func__, con); con->ops->put(con); - } else { - dout("queue_con %p\n", con); + + return -EBUSY; + } + + dout("%s %p %lu\n", __func__, con, delay); + + return 0; +} + +static void queue_con(struct ceph_connection *con) +{ + (void) queue_con_delay(con, 0); +} + +static bool con_sock_closed(struct ceph_connection *con) +{ + if (!test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) + return false; + +#define CASE(x) \ + case CON_STATE_ ## x: \ + con->error_msg = "socket closed (con state " #x ")"; \ + break; + + switch (con->state) { + CASE(CLOSED); + CASE(PREOPEN); + CASE(CONNECTING); + CASE(NEGOTIATING); + CASE(OPEN); + CASE(STANDBY); + default: + pr_warning("%s con %p unrecognized state %lu\n", + __func__, con, con->state); + con->error_msg = "unrecognized con state"; + BUG(); + break; } +#undef CASE + + return true; } /* @@ -2273,37 +2306,19 @@ static void con_work(struct work_struct *work) mutex_lock(&con->mutex); restart: - if (test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) { - switch (con->state) { - case CON_STATE_CONNECTING: - con->error_msg = "connection failed"; - break; - case CON_STATE_NEGOTIATING: - con->error_msg = "negotiation failed"; - break; - case CON_STATE_OPEN: - con->error_msg = "socket closed"; - break; - default: - dout("unrecognized con state %d\n", (int)con->state); - con->error_msg = "unrecognized con state"; - BUG(); - } + if (con_sock_closed(con)) goto fault; - } if (test_and_clear_bit(CON_FLAG_BACKOFF, &con->flags)) { dout("con_work %p backing off\n", con); - if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay))) { - dout("con_work %p backoff %lu\n", con, con->delay); - mutex_unlock(&con->mutex); - return; - } else { - con->ops->put(con); + ret = queue_con_delay(con, round_jiffies_relative(con->delay)); + if (ret) { dout("con_work %p FAILED to back off %lu\n", con, con->delay); + BUG_ON(ret == -ENOENT); + set_bit(CON_FLAG_BACKOFF, &con->flags); } + goto done; } if (con->state == CON_STATE_STANDBY) { @@ -2355,12 +2370,12 @@ fault: static void ceph_fault(struct ceph_connection *con) __releases(con->mutex) { - pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), + pr_warning("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); dout("fault %p state %lu to peer %s\n", con, con->state, ceph_pr_addr(&con->peer_addr.in_addr)); - BUG_ON(con->state != CON_STATE_CONNECTING && + WARN_ON(con->state != CON_STATE_CONNECTING && con->state != CON_STATE_NEGOTIATING && con->state != CON_STATE_OPEN); @@ -2397,24 +2412,8 @@ static void ceph_fault(struct ceph_connection *con) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) con->delay *= 2; - con->ops->get(con); - if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay))) { - dout("fault queued %p delay %lu\n", con, con->delay); - } else { - con->ops->put(con); - dout("fault failed to queue %p delay %lu, backoff\n", - con, con->delay); - /* - * In many cases we see a socket state change - * while con_work is running and end up - * queuing (non-delayed) work, such that we - * can't backoff with a delay. Set a flag so - * that when con_work restarts we schedule the - * delay then. - */ - set_bit(CON_FLAG_BACKOFF, &con->flags); - } + set_bit(CON_FLAG_BACKOFF, &con->flags); + queue_con(con); } out_unlock: @@ -2749,7 +2748,8 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) msg = con->ops->alloc_msg(con, hdr, skip); mutex_lock(&con->mutex); if (con->state != CON_STATE_OPEN) { - ceph_msg_put(msg); + if (msg) + ceph_msg_put(msg); return -EAGAIN; } con->in_msg = msg; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index c1d756cc7448..eb9a44478764 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -221,6 +221,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, kref_init(&req->r_kref); init_completion(&req->r_completion); init_completion(&req->r_safe_completion); + RB_CLEAR_NODE(&req->r_node); INIT_LIST_HEAD(&req->r_unsafe_item); INIT_LIST_HEAD(&req->r_linger_item); INIT_LIST_HEAD(&req->r_linger_osd); @@ -580,7 +581,7 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc, dout("__kick_osd_requests osd%d\n", osd->o_osd); err = __reset_osd(osdc, osd); - if (err == -EAGAIN) + if (err) return; list_for_each_entry(req, &osd->o_requests, r_osd_item) { @@ -607,14 +608,6 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc, } } -static void kick_osd_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd) -{ - mutex_lock(&osdc->request_mutex); - __kick_osd_requests(osdc, kickosd); - mutex_unlock(&osdc->request_mutex); -} - /* * If the osd connection drops, we need to resubmit all requests. */ @@ -628,7 +621,9 @@ static void osd_reset(struct ceph_connection *con) dout("osd_reset osd%d\n", osd->o_osd); osdc = osd->o_osdc; down_read(&osdc->map_sem); - kick_osd_requests(osdc, osd); + mutex_lock(&osdc->request_mutex); + __kick_osd_requests(osdc, osd); + mutex_unlock(&osdc->request_mutex); send_queued(osdc); up_read(&osdc->map_sem); } @@ -647,6 +642,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) atomic_set(&osd->o_ref, 1); osd->o_osdc = osdc; osd->o_osd = onum; + RB_CLEAR_NODE(&osd->o_node); INIT_LIST_HEAD(&osd->o_requests); INIT_LIST_HEAD(&osd->o_linger_requests); INIT_LIST_HEAD(&osd->o_osd_lru); @@ -750,6 +746,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) if (list_empty(&osd->o_requests) && list_empty(&osd->o_linger_requests)) { __remove_osd(osdc, osd); + ret = -ENODEV; } else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd], &osd->o_con.peer_addr, sizeof(osd->o_con.peer_addr)) == 0 && @@ -876,9 +873,9 @@ static void __unregister_request(struct ceph_osd_client *osdc, req->r_osd = NULL; } + list_del_init(&req->r_req_lru_item); ceph_osdc_put_request(req); - list_del_init(&req->r_req_lru_item); if (osdc->num_requests == 0) { dout(" no requests, canceling timeout\n"); __cancel_osd_timeout(osdc); @@ -910,8 +907,8 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { dout("__unregister_linger_request %p\n", req); + list_del_init(&req->r_linger_item); if (req->r_osd) { - list_del_init(&req->r_linger_item); list_del_init(&req->r_linger_osd); if (list_empty(&req->r_osd->o_requests) && @@ -1090,12 +1087,10 @@ static void handle_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, timeout_work.work); - struct ceph_osd_request *req, *last_req = NULL; + struct ceph_osd_request *req; struct ceph_osd *osd; - unsigned long timeout = osdc->client->options->osd_timeout * HZ; unsigned long keepalive = osdc->client->options->osd_keepalive_timeout * HZ; - unsigned long last_stamp = 0; struct list_head slow_osds; dout("timeout\n"); down_read(&osdc->map_sem); @@ -1105,37 +1100,6 @@ static void handle_timeout(struct work_struct *work) mutex_lock(&osdc->request_mutex); /* - * reset osds that appear to be _really_ unresponsive. this - * is a failsafe measure.. we really shouldn't be getting to - * this point if the system is working properly. the monitors - * should mark the osd as failed and we should find out about - * it from an updated osd map. - */ - while (timeout && !list_empty(&osdc->req_lru)) { - req = list_entry(osdc->req_lru.next, struct ceph_osd_request, - r_req_lru_item); - - /* hasn't been long enough since we sent it? */ - if (time_before(jiffies, req->r_stamp + timeout)) - break; - - /* hasn't been long enough since it was acked? */ - if (req->r_request->ack_stamp == 0 || - time_before(jiffies, req->r_request->ack_stamp + timeout)) - break; - - BUG_ON(req == last_req && req->r_stamp == last_stamp); - last_req = req; - last_stamp = req->r_stamp; - - osd = req->r_osd; - BUG_ON(!osd); - pr_warning(" tid %llu timed out on osd%d, will reset osd\n", - req->r_tid, osd->o_osd); - __kick_osd_requests(osdc, osd); - } - - /* * ping osds that are a bit slow. this ensures that if there * is a break in the TCP connection we will notice, and reopen * a connection with that osd (from the fault callback). @@ -1306,7 +1270,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) * Requeue requests whose mapping to an OSD has changed. If requests map to * no osd, request a new map. * - * Caller should hold map_sem for read and request_mutex. + * Caller should hold map_sem for read. */ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) { @@ -1320,6 +1284,24 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) for (p = rb_first(&osdc->requests); p; ) { req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); + + /* + * For linger requests that have not yet been + * registered, move them to the linger list; they'll + * be sent to the osd in the loop below. Unregister + * the request before re-registering it as a linger + * request to ensure the __map_request() below + * will decide it needs to be sent. + */ + if (req->r_linger && list_empty(&req->r_linger_item)) { + dout("%p tid %llu restart on osd%d\n", + req, req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); + __unregister_request(osdc, req); + __register_linger_request(osdc, req); + continue; + } + err = __map_request(osdc, req, force_resend); if (err < 0) continue; /* error */ @@ -1334,17 +1316,6 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) req->r_flags |= CEPH_OSD_FLAG_RETRY; } } - if (req->r_linger && list_empty(&req->r_linger_item)) { - /* - * register as a linger so that we will - * re-submit below and get a new tid - */ - dout("%p tid %llu restart on osd%d\n", - req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - __register_linger_request(osdc, req); - __unregister_request(osdc, req); - } } list_for_each_entry_safe(req, nreq, &osdc->req_linger, @@ -1352,6 +1323,7 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("linger req=%p req->r_osd=%p\n", req, req->r_osd); err = __map_request(osdc, req, force_resend); + dout("__map_request returned %d\n", err); if (err == 0) continue; /* no change and no osd was specified */ if (err < 0) @@ -1364,8 +1336,8 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); - __unregister_linger_request(osdc, req); __register_request(osdc, req); + __unregister_linger_request(osdc, req); } mutex_unlock(&osdc->request_mutex); @@ -1373,6 +1345,7 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("%d requests for down osds, need new map\n", needmap); ceph_monc_request_next_osdmap(&osdc->client->monc); } + reset_changed_osds(osdc); } @@ -1429,7 +1402,6 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) osdc->osdmap = newmap; } kick_requests(osdc, 0); - reset_changed_osds(osdc); } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); @@ -1599,6 +1571,7 @@ int ceph_osdc_create_event(struct ceph_osd_client *osdc, event->data = data; event->osdc = osdc; INIT_LIST_HEAD(&event->osd_node); + RB_CLEAR_NODE(&event->node); kref_init(&event->kref); /* one ref for us */ kref_get(&event->kref); /* one ref for the caller */ init_completion(&event->completion); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 5433fb0eb3c6..de73214b5d26 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -469,6 +469,22 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id) return NULL; } +const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id) +{ + struct ceph_pg_pool_info *pi; + + if (id == CEPH_NOPOOL) + return NULL; + + if (WARN_ON_ONCE(id > (u64) INT_MAX)) + return NULL; + + pi = __lookup_pg_pool(&map->pg_pools, (int) id); + + return pi ? pi->name : NULL; +} +EXPORT_SYMBOL(ceph_pg_pool_name_by_id); + int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) { struct rb_node *rbp; @@ -645,10 +661,12 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) ceph_decode_32_safe(p, end, max, bad); while (max--) { ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad); + err = -ENOMEM; pi = kzalloc(sizeof(*pi), GFP_NOFS); if (!pi) goto bad; pi->id = ceph_decode_32(p); + err = -EINVAL; ev = ceph_decode_8(p); /* encoding version */ if (ev > CEPH_PG_POOL_VERSION) { pr_warning("got unknown v %d > %d of ceph_pg_pool\n", @@ -664,8 +682,13 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) __insert_pg_pool(&map->pg_pools, pi); } - if (version >= 5 && __decode_pool_names(p, end, map) < 0) - goto bad; + if (version >= 5) { + err = __decode_pool_names(p, end, map); + if (err < 0) { + dout("fail to decode pool names"); + goto bad; + } + } ceph_decode_32_safe(p, end, map->pool_max, bad); @@ -745,7 +768,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) return map; bad: - dout("osdmap_decode fail\n"); + dout("osdmap_decode fail err %d\n", err); ceph_osdmap_destroy(map); return ERR_PTR(err); } @@ -839,6 +862,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (ev > CEPH_PG_POOL_VERSION) { pr_warning("got unknown v %d > %d of ceph_pg_pool\n", ev, CEPH_PG_POOL_VERSION); + err = -EINVAL; goto bad; } pi = __lookup_pg_pool(&map->pg_pools, pool); @@ -855,8 +879,11 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (err < 0) goto bad; } - if (version >= 5 && __decode_pool_names(p, end, map) < 0) - goto bad; + if (version >= 5) { + err = __decode_pool_names(p, end, map); + if (err < 0) + goto bad; + } /* old_pool */ ceph_decode_32_safe(p, end, len, bad); @@ -932,15 +959,13 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, (void) __remove_pg_mapping(&map->pg_temp, pgid); /* insert */ - if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) { - err = -EINVAL; + err = -EINVAL; + if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) goto bad; - } + err = -ENOMEM; pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); - if (!pg) { - err = -ENOMEM; + if (!pg) goto bad; - } pg->pgid = pgid; pg->len = pglen; for (j = 0; j < pglen; j++) diff --git a/net/core/dev.c b/net/core/dev.c index 09cb3f6dc40c..f64e439b4a00 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -176,8 +176,10 @@ #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) static DEFINE_SPINLOCK(ptype_lock); +static DEFINE_SPINLOCK(offload_lock); static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static struct list_head ptype_all __read_mostly; /* Taps */ +static struct list_head offload_base __read_mostly; /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -201,6 +203,8 @@ static struct list_head ptype_all __read_mostly; /* Taps */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +seqcount_t devnet_rename_seq; + static inline void dev_base_seq_inc(struct net *net) { while (++net->dev_base_seq == 0); @@ -470,6 +474,82 @@ void dev_remove_pack(struct packet_type *pt) } EXPORT_SYMBOL(dev_remove_pack); + +/** + * dev_add_offload - register offload handlers + * @po: protocol offload declaration + * + * Add protocol offload handlers to the networking stack. The passed + * &proto_offload is linked into kernel lists and may not be freed until + * it has been removed from the kernel lists. + * + * This call does not sleep therefore it can not + * guarantee all CPU's that are in middle of receiving packets + * will see the new offload handlers (until the next received packet). + */ +void dev_add_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + + spin_lock(&offload_lock); + list_add_rcu(&po->list, head); + spin_unlock(&offload_lock); +} +EXPORT_SYMBOL(dev_add_offload); + +/** + * __dev_remove_offload - remove offload handler + * @po: packet offload declaration + * + * Remove a protocol offload handler that was previously added to the + * kernel offload handlers by dev_add_offload(). The passed &offload_type + * is removed from the kernel lists and can be freed or reused once this + * function returns. + * + * The packet type might still be in use by receivers + * and must not be freed until after all the CPU's have gone + * through a quiescent state. + */ +void __dev_remove_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + struct packet_offload *po1; + + spin_lock(&offload_lock); + + list_for_each_entry(po1, head, list) { + if (po == po1) { + list_del_rcu(&po->list); + goto out; + } + } + + pr_warn("dev_remove_offload: %p not found\n", po); +out: + spin_unlock(&offload_lock); +} +EXPORT_SYMBOL(__dev_remove_offload); + +/** + * dev_remove_offload - remove packet offload handler + * @po: packet offload declaration + * + * Remove a packet offload handler that was previously added to the kernel + * offload handlers by dev_add_offload(). The passed &offload_type is + * removed from the kernel lists and can be freed or reused once this + * function returns. + * + * This call sleeps to guarantee that no CPU is looking at the packet + * type after return. + */ +void dev_remove_offload(struct packet_offload *po) +{ + __dev_remove_offload(po); + + synchronize_net(); +} +EXPORT_SYMBOL(dev_remove_offload); + /****************************************************************************** Device Boot-time Settings Routines @@ -1013,22 +1093,31 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) + write_seqcount_begin(&devnet_rename_seq); + + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { + write_seqcount_end(&devnet_rename_seq); return 0; + } memcpy(oldname, dev->name, IFNAMSIZ); err = dev_get_valid_name(net, dev, newname); - if (err < 0) + if (err < 0) { + write_seqcount_end(&devnet_rename_seq); return err; + } rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); + write_seqcount_end(&devnet_rename_seq); return ret; } + write_seqcount_end(&devnet_rename_seq); + write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); @@ -1046,6 +1135,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; + write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; } else { @@ -1075,10 +1165,8 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return -EINVAL; if (!len) { - if (dev->ifalias) { - kfree(dev->ifalias); - dev->ifalias = NULL; - } + kfree(dev->ifalias); + dev->ifalias = NULL; return 0; } @@ -1666,7 +1754,7 @@ static inline int deliver_skb(struct sk_buff *skb, static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { - if (ptype->af_packet_priv == NULL) + if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) @@ -1994,7 +2082,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; int vlan_depth = ETH_HLEN; int err; @@ -2023,18 +2111,17 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, } rcu_read_lock(); - list_for_each_entry_rcu(ptype, - &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && !ptype->dev && ptype->gso_segment) { + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->callbacks.gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - err = ptype->gso_send_check(skb); + err = ptype->callbacks.gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) break; __skb_push(skb, (skb->data - skb_network_header(skb))); } - segs = ptype->gso_segment(skb, features); + segs = ptype->callbacks.gso_segment(skb, features); break; } } @@ -2237,6 +2324,13 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb->vlan_tci = 0; } + /* If encapsulation offload request, verify we are testing + * hardware encapsulation features instead of standard + * features for the netdev + */ + if (skb->encapsulation) + features &= dev->hw_enc_features; + if (netif_needs_gso(skb, features)) { if (unlikely(dev_gso_segment(skb, features))) goto out_kfree_skb; @@ -2252,8 +2346,12 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { - skb_set_transport_header(skb, - skb_checksum_start_offset(skb)); + if (skb->encapsulation) + skb_set_inner_transport_header(skb, + skb_checksum_start_offset(skb)); + else + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); if (!(features & NETIF_F_ALL_CSUM) && skb_checksum_help(skb)) goto out_kfree_skb; @@ -2818,8 +2916,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (unlikely(tcpu != next_cpu) && (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - - rflow->last_qtail)) >= 0)) + rflow->last_qtail)) >= 0)) { + tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); + } if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { *rflowp = rflow; @@ -3444,11 +3544,13 @@ static void flush_backlog(void *arg) static int napi_gro_complete(struct sk_buff *skb) { - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + struct list_head *head = &offload_base; int err = -ENOENT; + BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); + if (NAPI_GRO_CB(skb)->count == 1) { skb_shinfo(skb)->gso_size = 0; goto out; @@ -3456,10 +3558,10 @@ static int napi_gro_complete(struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_complete) + if (ptype->type != type || !ptype->callbacks.gro_complete) continue; - err = ptype->gro_complete(skb); + err = ptype->callbacks.gro_complete(skb); break; } rcu_read_unlock(); @@ -3503,12 +3605,34 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old) } EXPORT_SYMBOL(napi_gro_flush); -enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) +{ + struct sk_buff *p; + unsigned int maclen = skb->dev->hard_header_len; + + for (p = napi->gro_list; p; p = p->next) { + unsigned long diffs; + + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= p->vlan_tci ^ skb->vlan_tci; + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_gro_mac_header(skb), + maclen); + NAPI_GRO_CB(p)->same_flow = !diffs; + NAPI_GRO_CB(p)->flush = 0; + } +} + +static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + struct list_head *head = &offload_base; int same_flow; int mac_len; enum gro_result ret; @@ -3519,9 +3643,11 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; + gro_list_prepare(napi, skb); + rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_receive) + if (ptype->type != type || !ptype->callbacks.gro_receive) continue; skb_set_network_header(skb, skb_gro_offset(skb)); @@ -3531,7 +3657,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; - pp = ptype->gro_receive(&napi->gro_list, skb); + pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); break; } rcu_read_unlock(); @@ -3594,34 +3720,9 @@ normal: ret = GRO_NORMAL; goto pull; } -EXPORT_SYMBOL(dev_gro_receive); - -static inline gro_result_t -__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - struct sk_buff *p; - unsigned int maclen = skb->dev->hard_header_len; - - for (p = napi->gro_list; p; p = p->next) { - unsigned long diffs; - - diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= p->vlan_tci ^ skb->vlan_tci; - if (maclen == ETH_HLEN) - diffs |= compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); - else if (!diffs) - diffs = memcmp(skb_mac_header(p), - skb_gro_mac_header(skb), - maclen); - NAPI_GRO_CB(p)->same_flow = !diffs; - NAPI_GRO_CB(p)->flush = 0; - } - return dev_gro_receive(napi, skb); -} -gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { case GRO_NORMAL: @@ -3647,7 +3748,6 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) return ret; } -EXPORT_SYMBOL(napi_skb_finish); static void skb_gro_reset_offset(struct sk_buff *skb) { @@ -3670,7 +3770,7 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { skb_gro_reset_offset(skb); - return napi_skb_finish(__napi_gro_receive(napi, skb), skb); + return napi_skb_finish(dev_gro_receive(napi, skb), skb); } EXPORT_SYMBOL(napi_gro_receive); @@ -3699,7 +3799,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); -gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, +static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) { switch (ret) { @@ -3724,7 +3824,6 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, return ret; } -EXPORT_SYMBOL(napi_frags_finish); static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { @@ -3769,7 +3868,7 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) if (!skb) return GRO_DROP; - return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb)); + return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); } EXPORT_SYMBOL(napi_gro_frags); @@ -4071,6 +4170,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) { struct net_device *dev; struct ifreq ifr; + unsigned seq; /* * Fetch the caller's info block. @@ -4079,6 +4179,8 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; +retry: + seq = read_seqcount_begin(&devnet_rename_seq); rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); if (!dev) { @@ -4088,6 +4190,8 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) strcpy(ifr.ifr_name, dev->name); rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) + goto retry; if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; @@ -4880,7 +4984,7 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) else dev->mtu = new_mtu; - if (!err && dev->flags & IFF_UP) + if (!err) call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); return err; } @@ -5200,7 +5304,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSIFNAME: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; dev_load(net, ifr.ifr_name); rtnl_lock(); @@ -5221,16 +5325,25 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) * - require strict serialization. * - do not return a value */ + case SIOCSIFMAP: + case SIOCSIFTXQLEN: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + /* + * These ioctl calls: + * - require local superuser power. + * - require strict serialization. + * - do not return a value + */ case SIOCSIFFLAGS: case SIOCSIFMETRIC: case SIOCSIFMTU: - case SIOCSIFMAP: case SIOCSIFHWADDR: case SIOCSIFSLAVE: case SIOCADDMULTI: case SIOCDELMULTI: case SIOCSIFHWBROADCAST: - case SIOCSIFTXQLEN: case SIOCSMIIREG: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: @@ -5239,7 +5352,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCBRADDIF: case SIOCBRDELIF: case SIOCSHWTSTAMP: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* fall through */ case SIOCBONDSLAVEINFOQUERY: @@ -6008,6 +6121,14 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) static const struct ethtool_ops default_ethtool_ops; +void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops) +{ + if (dev->ethtool_ops == &default_ethtool_ops) + dev->ethtool_ops = ops; +} +EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); + /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for @@ -6264,7 +6385,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char goto out; /* Ensure the device has been registrered */ - err = -EINVAL; if (dev->reg_state != NETREG_REGISTERED) goto out; @@ -6319,6 +6439,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_uc_flush(dev); dev_mc_flush(dev); + /* Send a netdev-removed uevent to the old namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); + /* Actually switch the network namespace */ dev_net_set(dev, net); @@ -6330,6 +6453,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev->iflink = dev->ifindex; } + /* Send a netdev-add uevent to the new namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); WARN_ON(err); @@ -6662,6 +6788,8 @@ static int __init net_dev_init(void) for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); + INIT_LIST_HEAD(&offload_base); + if (register_pernet_subsys(&netdev_net_ops)) goto out; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 87cc17db2d56..b079c7bbc157 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -319,7 +319,8 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr, */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); - if (ha->addr == dev->dev_addr && ha->refcount == 1) + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4d64cc2e3fa9..a8705432e4b1 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1460,7 +1460,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GEEE: break; default: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; } diff --git a/net/core/filter.c b/net/core/filter.c index 3d92ebb7fbcf..c23543cba132 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -39,6 +39,7 @@ #include <linux/reciprocal_div.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> +#include <linux/if_vlan.h> /* No hurry in this branch * @@ -341,6 +342,12 @@ load_b: case BPF_S_ANC_CPU: A = raw_smp_processor_id(); continue; + case BPF_S_ANC_VLAN_TAG: + A = vlan_tx_tag_get(skb); + continue; + case BPF_S_ANC_VLAN_TAG_PRESENT: + A = !!vlan_tx_tag_present(skb); + continue; case BPF_S_ANC_NLATTR: { struct nlattr *nla; @@ -600,6 +607,8 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) ANCILLARY(RXHASH); ANCILLARY(CPU); ANCILLARY(ALU_XOR_X); + ANCILLARY(VLAN_TAG); + ANCILLARY(VLAN_TAG_PRESENT); } } ftest->code = code; @@ -751,3 +760,133 @@ int sk_detach_filter(struct sock *sk) return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); + +static void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) +{ + static const u16 decodes[] = { + [BPF_S_ALU_ADD_K] = BPF_ALU|BPF_ADD|BPF_K, + [BPF_S_ALU_ADD_X] = BPF_ALU|BPF_ADD|BPF_X, + [BPF_S_ALU_SUB_K] = BPF_ALU|BPF_SUB|BPF_K, + [BPF_S_ALU_SUB_X] = BPF_ALU|BPF_SUB|BPF_X, + [BPF_S_ALU_MUL_K] = BPF_ALU|BPF_MUL|BPF_K, + [BPF_S_ALU_MUL_X] = BPF_ALU|BPF_MUL|BPF_X, + [BPF_S_ALU_DIV_X] = BPF_ALU|BPF_DIV|BPF_X, + [BPF_S_ALU_MOD_K] = BPF_ALU|BPF_MOD|BPF_K, + [BPF_S_ALU_MOD_X] = BPF_ALU|BPF_MOD|BPF_X, + [BPF_S_ALU_AND_K] = BPF_ALU|BPF_AND|BPF_K, + [BPF_S_ALU_AND_X] = BPF_ALU|BPF_AND|BPF_X, + [BPF_S_ALU_OR_K] = BPF_ALU|BPF_OR|BPF_K, + [BPF_S_ALU_OR_X] = BPF_ALU|BPF_OR|BPF_X, + [BPF_S_ALU_XOR_K] = BPF_ALU|BPF_XOR|BPF_K, + [BPF_S_ALU_XOR_X] = BPF_ALU|BPF_XOR|BPF_X, + [BPF_S_ALU_LSH_K] = BPF_ALU|BPF_LSH|BPF_K, + [BPF_S_ALU_LSH_X] = BPF_ALU|BPF_LSH|BPF_X, + [BPF_S_ALU_RSH_K] = BPF_ALU|BPF_RSH|BPF_K, + [BPF_S_ALU_RSH_X] = BPF_ALU|BPF_RSH|BPF_X, + [BPF_S_ALU_NEG] = BPF_ALU|BPF_NEG, + [BPF_S_LD_W_ABS] = BPF_LD|BPF_W|BPF_ABS, + [BPF_S_LD_H_ABS] = BPF_LD|BPF_H|BPF_ABS, + [BPF_S_LD_B_ABS] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_PROTOCOL] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_PKTTYPE] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_IFINDEX] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_NLATTR] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_NLATTR_NEST] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_MARK] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_QUEUE] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_HATYPE] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_RXHASH] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_CPU] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_ALU_XOR_X] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN, + [BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND, + [BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND, + [BPF_S_LD_B_IND] = BPF_LD|BPF_B|BPF_IND, + [BPF_S_LD_IMM] = BPF_LD|BPF_IMM, + [BPF_S_LDX_W_LEN] = BPF_LDX|BPF_W|BPF_LEN, + [BPF_S_LDX_B_MSH] = BPF_LDX|BPF_B|BPF_MSH, + [BPF_S_LDX_IMM] = BPF_LDX|BPF_IMM, + [BPF_S_MISC_TAX] = BPF_MISC|BPF_TAX, + [BPF_S_MISC_TXA] = BPF_MISC|BPF_TXA, + [BPF_S_RET_K] = BPF_RET|BPF_K, + [BPF_S_RET_A] = BPF_RET|BPF_A, + [BPF_S_ALU_DIV_K] = BPF_ALU|BPF_DIV|BPF_K, + [BPF_S_LD_MEM] = BPF_LD|BPF_MEM, + [BPF_S_LDX_MEM] = BPF_LDX|BPF_MEM, + [BPF_S_ST] = BPF_ST, + [BPF_S_STX] = BPF_STX, + [BPF_S_JMP_JA] = BPF_JMP|BPF_JA, + [BPF_S_JMP_JEQ_K] = BPF_JMP|BPF_JEQ|BPF_K, + [BPF_S_JMP_JEQ_X] = BPF_JMP|BPF_JEQ|BPF_X, + [BPF_S_JMP_JGE_K] = BPF_JMP|BPF_JGE|BPF_K, + [BPF_S_JMP_JGE_X] = BPF_JMP|BPF_JGE|BPF_X, + [BPF_S_JMP_JGT_K] = BPF_JMP|BPF_JGT|BPF_K, + [BPF_S_JMP_JGT_X] = BPF_JMP|BPF_JGT|BPF_X, + [BPF_S_JMP_JSET_K] = BPF_JMP|BPF_JSET|BPF_K, + [BPF_S_JMP_JSET_X] = BPF_JMP|BPF_JSET|BPF_X, + }; + u16 code; + + code = filt->code; + + to->code = decodes[code]; + to->jt = filt->jt; + to->jf = filt->jf; + + if (code == BPF_S_ALU_DIV_K) { + /* + * When loaded this rule user gave us X, which was + * translated into R = r(X). Now we calculate the + * RR = r(R) and report it back. If next time this + * value is loaded and RRR = r(RR) is calculated + * then the R == RRR will be true. + * + * One exception. X == 1 translates into R == 0 and + * we can't calculate RR out of it with r(). + */ + + if (filt->k == 0) + to->k = 1; + else + to->k = reciprocal_value(filt->k); + + BUG_ON(reciprocal_value(to->k) != filt->k); + } else + to->k = filt->k; +} + +int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) +{ + struct sk_filter *filter; + int i, ret; + + lock_sock(sk); + filter = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); + ret = 0; + if (!filter) + goto out; + ret = filter->len; + if (!len) + goto out; + ret = -EINVAL; + if (len < filter->len) + goto out; + + ret = -EFAULT; + for (i = 0; i < filter->len; i++) { + struct sock_filter fb; + + sk_decode_filter(&filter->insns[i], &fb); + if (copy_to_user(&ubuf[i], &fb, sizeof(fb))) + goto out; + } + + ret = filter->len; +out: + release_sock(sk); + return ret; +} diff --git a/net/core/flow.c b/net/core/flow.c index e318c7e98042..b0901ee5a002 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -327,11 +327,9 @@ static void flow_cache_flush_tasklet(unsigned long data) static void flow_cache_flush_per_cpu(void *data) { struct flow_flush_info *info = data; - int cpu; struct tasklet_struct *tasklet; - cpu = smp_processor_id(); - tasklet = &per_cpu_ptr(info->cache->percpu, cpu)->flush_tasklet; + tasklet = this_cpu_ptr(&info->cache->percpu->flush_tasklet); tasklet->data = (unsigned long)info; tasklet_schedule(tasklet); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 22571488730a..c815f285e5ab 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1787,8 +1787,7 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes) || /* approximative value for deprecated QUEUE_LEN (in packets) */ nla_put_u32(skb, NDTPA_QUEUE_LEN, - DIV_ROUND_UP(parms->queue_len_bytes, - SKB_TRUESIZE(ETH_FRAME_LEN))) || + parms->queue_len_bytes / SKB_TRUESIZE(ETH_FRAME_LEN)) || nla_put_u32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen) || nla_put_u32(skb, NDTPA_APP_PROBES, parms->app_probes) || nla_put_u32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes) || @@ -2770,6 +2769,8 @@ EXPORT_SYMBOL(neigh_app_ns); #endif /* CONFIG_ARPD */ #ifdef CONFIG_SYSCTL +static int zero; +static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -2777,9 +2778,13 @@ static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer, int size, ret; ctl_table tmp = *ctl; + tmp.extra1 = &zero; + tmp.extra2 = &unres_qlen_max; tmp.data = &size; - size = DIV_ROUND_UP(*(int *)ctl->data, SKB_TRUESIZE(ETH_FRAME_LEN)); - ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + + size = *(int *)ctl->data / SKB_TRUESIZE(ETH_FRAME_LEN); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN); return ret; @@ -2865,7 +2870,8 @@ static struct neigh_sysctl_table { .procname = "unres_qlen_bytes", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_PROXY_QLEN] = { .procname = "proxy_qlen", @@ -2987,6 +2993,10 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev; } + /* Don't export sysctls to unprivileged users */ + if (neigh_parms_net(p)->user_ns != &init_user_ns) + t->neigh_vars[0].procname = NULL; + snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", p_name, dev_name_source); t->sysctl_header = diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index bcf02f608cbf..28c5f5aa7ca7 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -18,11 +18,9 @@ #include <net/sock.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> -#include <linux/wireless.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/jiffies.h> -#include <net/wext.h> #include "net-sysfs.h" @@ -73,11 +71,12 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { - struct net_device *net = to_net_dev(dev); + struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); unsigned long new; int ret = -EINVAL; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); @@ -87,8 +86,8 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, if (!rtnl_trylock()) return restart_syscall(); - if (dev_isalive(net)) { - if ((ret = (*set)(net, new)) == 0) + if (dev_isalive(netdev)) { + if ((ret = (*set)(netdev, new)) == 0) ret = len; } rtnl_unlock(); @@ -264,6 +263,9 @@ static ssize_t store_tx_queue_len(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + return netdev_store(dev, attr, buf, len, change_tx_queue_len); } @@ -271,10 +273,11 @@ static ssize_t store_ifalias(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); size_t count = len; ssize_t ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ @@ -429,6 +432,17 @@ static struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; + +#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) +static struct attribute *wireless_attrs[] = { + NULL +}; + +static struct attribute_group wireless_group = { + .name = "wireless", + .attrs = wireless_attrs, +}; +#endif #endif /* CONFIG_SYSFS */ #ifdef CONFIG_RPS @@ -1320,7 +1334,6 @@ struct kobj_ns_type_operations net_ns_type_operations = { }; EXPORT_SYMBOL_GPL(net_ns_type_operations); -#ifdef CONFIG_HOTPLUG static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) { struct net_device *dev = to_net_dev(d); @@ -1339,7 +1352,6 @@ static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) exit: return retval; } -#endif /* * netdev_release -- destroy and free a dead device. @@ -1368,9 +1380,7 @@ static struct class net_class = { #ifdef CONFIG_SYSFS .dev_attrs = net_class_attributes, #endif /* CONFIG_SYSFS */ -#ifdef CONFIG_HOTPLUG .dev_uevent = netdev_uevent, -#endif .ns_type = &net_ns_type_operations, .namespace = net_namespace, }; @@ -1409,6 +1419,15 @@ int netdev_register_kobject(struct net_device *net) groups++; *groups++ = &netstat_group; + +#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) + if (net->ieee80211_ptr) + *groups++ = &wireless_group; +#if IS_ENABLED(CONFIG_WIRELESS_EXT) + else if (net->wireless_handlers) + *groups++ = &wireless_group; +#endif +#endif #endif /* CONFIG_SYSFS */ error = device_add(dev); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 42f1e1c7514f..8acce01b6dab 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -13,6 +13,7 @@ #include <linux/proc_fs.h> #include <linux/file.h> #include <linux/export.h> +#include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -145,7 +146,7 @@ static void ops_free_list(const struct pernet_operations *ops, /* * setup_net runs the initializers for the network namespace object. */ -static __net_init int setup_net(struct net *net) +static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) { /* Must be called with net_mutex held */ const struct pernet_operations *ops, *saved_ops; @@ -155,6 +156,7 @@ static __net_init int setup_net(struct net *net) atomic_set(&net->count, 1); atomic_set(&net->passive, 1); net->dev_base_seq = 1; + net->user_ns = user_ns; #ifdef NETNS_REFCNT_DEBUG atomic_set(&net->use_count, 0); @@ -232,7 +234,8 @@ void net_drop_ns(void *p) net_free(ns); } -struct net *copy_net_ns(unsigned long flags, struct net *old_net) +struct net *copy_net_ns(unsigned long flags, + struct user_namespace *user_ns, struct net *old_net) { struct net *net; int rv; @@ -243,8 +246,11 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) net = net_alloc(); if (!net) return ERR_PTR(-ENOMEM); + + get_user_ns(user_ns); + mutex_lock(&net_mutex); - rv = setup_net(net); + rv = setup_net(net, user_ns); if (rv == 0) { rtnl_lock(); list_add_tail_rcu(&net->list, &net_namespace_list); @@ -252,6 +258,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) } mutex_unlock(&net_mutex); if (rv < 0) { + put_user_ns(user_ns); net_drop_ns(net); return ERR_PTR(rv); } @@ -308,6 +315,7 @@ static void cleanup_net(struct work_struct *work) /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); + put_user_ns(net->user_ns); net_drop_ns(net); } } @@ -347,13 +355,6 @@ struct net *get_net_ns_by_fd(int fd) } #else -struct net *copy_net_ns(unsigned long flags, struct net *old_net) -{ - if (flags & CLONE_NEWNET) - return ERR_PTR(-EINVAL); - return old_net; -} - struct net *get_net_ns_by_fd(int fd) { return ERR_PTR(-EINVAL); @@ -380,6 +381,21 @@ struct net *get_net_ns_by_pid(pid_t pid) } EXPORT_SYMBOL_GPL(get_net_ns_by_pid); +static __net_init int net_ns_net_init(struct net *net) +{ + return proc_alloc_inum(&net->proc_inum); +} + +static __net_exit void net_ns_net_exit(struct net *net) +{ + proc_free_inum(net->proc_inum); +} + +static struct pernet_operations __net_initdata net_ns_ops = { + .init = net_ns_net_init, + .exit = net_ns_net_exit, +}; + static int __init net_ns_init(void) { struct net_generic *ng; @@ -402,7 +418,7 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); mutex_lock(&net_mutex); - if (setup_net(&init_net)) + if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); rtnl_lock(); @@ -411,6 +427,8 @@ static int __init net_ns_init(void) mutex_unlock(&net_mutex); + register_pernet_subsys(&net_ns_ops); + return 0; } @@ -629,16 +647,29 @@ static void netns_put(void *ns) static int netns_install(struct nsproxy *nsproxy, void *ns) { + struct net *net = ns; + + if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || + !nsown_capable(CAP_SYS_ADMIN)) + return -EPERM; + put_net(nsproxy->net_ns); - nsproxy->net_ns = get_net(ns); + nsproxy->net_ns = get_net(net); return 0; } +static unsigned int netns_inum(void *ns) +{ + struct net *net = ns; + return net->proc_inum; +} + const struct proc_ns_operations netns_operations = { .name = "net", .type = CLONE_NEWNET, .get = netns_get, .put = netns_put, .install = netns_install, + .inum = netns_inum, }; #endif diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 77a0388fc3be..3151acf5ec13 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -674,7 +674,8 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; *delim = 0; - np->local_port = simple_strtol(cur, NULL, 10); + if (kstrtou16(cur, 10, &np->local_port)) + goto parse_failed; cur = delim; } cur++; @@ -705,7 +706,8 @@ int netpoll_parse_options(struct netpoll *np, char *opt) *delim = 0; if (*cur == ' ' || *cur == '\t') np_info(np, "warning: whitespace is not allowed\n"); - np->remote_port = simple_strtol(cur, NULL, 10); + if (kstrtou16(cur, 10, &np->remote_port)) + goto parse_failed; cur = delim; } cur++; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 79285a36035f..5e67defe2cb0 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -27,11 +27,7 @@ #include <linux/fdtable.h> -#define PRIOIDX_SZ 128 - -static unsigned long prioidx_map[PRIOIDX_SZ]; -static DEFINE_SPINLOCK(prioidx_map_lock); -static atomic_t max_prioidx = ATOMIC_INIT(0); +#define PRIOMAP_MIN_SZ 128 static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp) { @@ -39,136 +35,157 @@ static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgr struct cgroup_netprio_state, css); } -static int get_prioidx(u32 *prio) -{ - unsigned long flags; - u32 prioidx; - - spin_lock_irqsave(&prioidx_map_lock, flags); - prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); - if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) { - spin_unlock_irqrestore(&prioidx_map_lock, flags); - return -ENOSPC; - } - set_bit(prioidx, prioidx_map); - if (atomic_read(&max_prioidx) < prioidx) - atomic_set(&max_prioidx, prioidx); - spin_unlock_irqrestore(&prioidx_map_lock, flags); - *prio = prioidx; - return 0; -} - -static void put_prioidx(u32 idx) +/* + * Extend @dev->priomap so that it's large enough to accomodate + * @target_idx. @dev->priomap.priomap_len > @target_idx after successful + * return. Must be called under rtnl lock. + */ +static int extend_netdev_table(struct net_device *dev, u32 target_idx) { - unsigned long flags; - - spin_lock_irqsave(&prioidx_map_lock, flags); - clear_bit(idx, prioidx_map); - spin_unlock_irqrestore(&prioidx_map_lock, flags); -} + struct netprio_map *old, *new; + size_t new_sz, new_len; -static int extend_netdev_table(struct net_device *dev, u32 new_len) -{ - size_t new_size = sizeof(struct netprio_map) + - ((sizeof(u32) * new_len)); - struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL); - struct netprio_map *old_priomap; + /* is the existing priomap large enough? */ + old = rtnl_dereference(dev->priomap); + if (old && old->priomap_len > target_idx) + return 0; - old_priomap = rtnl_dereference(dev->priomap); + /* + * Determine the new size. Let's keep it power-of-two. We start + * from PRIOMAP_MIN_SZ and double it until it's large enough to + * accommodate @target_idx. + */ + new_sz = PRIOMAP_MIN_SZ; + while (true) { + new_len = (new_sz - offsetof(struct netprio_map, priomap)) / + sizeof(new->priomap[0]); + if (new_len > target_idx) + break; + new_sz *= 2; + /* overflowed? */ + if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) + return -ENOSPC; + } - if (!new_priomap) { + /* allocate & copy */ + new = kzalloc(new_sz, GFP_KERNEL); + if (!new) { pr_warn("Unable to alloc new priomap!\n"); return -ENOMEM; } - if (old_priomap) - memcpy(new_priomap->priomap, old_priomap->priomap, - old_priomap->priomap_len * - sizeof(old_priomap->priomap[0])); + if (old) + memcpy(new->priomap, old->priomap, + old->priomap_len * sizeof(old->priomap[0])); - new_priomap->priomap_len = new_len; + new->priomap_len = new_len; - rcu_assign_pointer(dev->priomap, new_priomap); - if (old_priomap) - kfree_rcu(old_priomap, rcu); + /* install the new priomap */ + rcu_assign_pointer(dev->priomap, new); + if (old) + kfree_rcu(old, rcu); return 0; } -static int write_update_netdev_table(struct net_device *dev) +/** + * netprio_prio - return the effective netprio of a cgroup-net_device pair + * @cgrp: cgroup part of the target pair + * @dev: net_device part of the target pair + * + * Should be called under RCU read or rtnl lock. + */ +static u32 netprio_prio(struct cgroup *cgrp, struct net_device *dev) +{ + struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); + + if (map && cgrp->id < map->priomap_len) + return map->priomap[cgrp->id]; + return 0; +} + +/** + * netprio_set_prio - set netprio on a cgroup-net_device pair + * @cgrp: cgroup part of the target pair + * @dev: net_device part of the target pair + * @prio: prio to set + * + * Set netprio to @prio on @cgrp-@dev pair. Should be called under rtnl + * lock and may fail under memory pressure for non-zero @prio. + */ +static int netprio_set_prio(struct cgroup *cgrp, struct net_device *dev, + u32 prio) { - int ret = 0; - u32 max_len; struct netprio_map *map; + int ret; - max_len = atomic_read(&max_prioidx) + 1; + /* avoid extending priomap for zero writes */ map = rtnl_dereference(dev->priomap); - if (!map || map->priomap_len < max_len) - ret = extend_netdev_table(dev, max_len); + if (!prio && (!map || map->priomap_len <= cgrp->id)) + return 0; - return ret; + ret = extend_netdev_table(dev, cgrp->id); + if (ret) + return ret; + + map = rtnl_dereference(dev->priomap); + map->priomap[cgrp->id] = prio; + return 0; } -static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) +static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp) { struct cgroup_netprio_state *cs; - int ret = -EINVAL; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); - if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) - goto out; - - ret = get_prioidx(&cs->prioidx); - if (ret < 0) { - pr_warn("No space in priority index array\n"); - goto out; - } - return &cs->css; -out: - kfree(cs); - return ERR_PTR(ret); } -static void cgrp_destroy(struct cgroup *cgrp) +static int cgrp_css_online(struct cgroup *cgrp) { - struct cgroup_netprio_state *cs; + struct cgroup *parent = cgrp->parent; struct net_device *dev; - struct netprio_map *map; + int ret = 0; + + if (!parent) + return 0; - cs = cgrp_netprio_state(cgrp); rtnl_lock(); + /* + * Inherit prios from the parent. As all prios are set during + * onlining, there is no need to clear them on offline. + */ for_each_netdev(&init_net, dev) { - map = rtnl_dereference(dev->priomap); - if (map && cs->prioidx < map->priomap_len) - map->priomap[cs->prioidx] = 0; + u32 prio = netprio_prio(parent, dev); + + ret = netprio_set_prio(cgrp, dev, prio); + if (ret) + break; } rtnl_unlock(); - put_prioidx(cs->prioidx); - kfree(cs); + return ret; +} + +static void cgrp_css_free(struct cgroup *cgrp) +{ + kfree(cgrp_netprio_state(cgrp)); } static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft) { - return (u64)cgrp_netprio_state(cgrp)->prioidx; + return cgrp->id; } static int read_priomap(struct cgroup *cont, struct cftype *cft, struct cgroup_map_cb *cb) { struct net_device *dev; - u32 prioidx = cgrp_netprio_state(cont)->prioidx; - u32 priority; - struct netprio_map *map; rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - map = rcu_dereference(dev->priomap); - priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0; - cb->fill(cb, dev->name, priority); - } + for_each_netdev_rcu(&init_net, dev) + cb->fill(cb, dev->name, netprio_prio(cont, dev)); rcu_read_unlock(); return 0; } @@ -176,66 +193,24 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft, static int write_priomap(struct cgroup *cgrp, struct cftype *cft, const char *buffer) { - char *devname = kstrdup(buffer, GFP_KERNEL); - int ret = -EINVAL; - u32 prioidx = cgrp_netprio_state(cgrp)->prioidx; - unsigned long priority; - char *priostr; + char devname[IFNAMSIZ + 1]; struct net_device *dev; - struct netprio_map *map; - - if (!devname) - return -ENOMEM; - - /* - * Minimally sized valid priomap string - */ - if (strlen(devname) < 3) - goto out_free_devname; - - priostr = strstr(devname, " "); - if (!priostr) - goto out_free_devname; - - /* - *Separate the devname from the associated priority - *and advance the priostr pointer to the priority value - */ - *priostr = '\0'; - priostr++; - - /* - * If the priostr points to NULL, we're at the end of the passed - * in string, and its not a valid write - */ - if (*priostr == '\0') - goto out_free_devname; - - ret = kstrtoul(priostr, 10, &priority); - if (ret < 0) - goto out_free_devname; + u32 prio; + int ret; - ret = -ENODEV; + if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) + return -EINVAL; dev = dev_get_by_name(&init_net, devname); if (!dev) - goto out_free_devname; + return -ENODEV; rtnl_lock(); - ret = write_update_netdev_table(dev); - if (ret < 0) - goto out_put_dev; - map = rtnl_dereference(dev->priomap); - if (map) - map->priomap[prioidx] = priority; + ret = netprio_set_prio(cgrp, dev, prio); -out_put_dev: rtnl_unlock(); dev_put(dev); - -out_free_devname: - kfree(devname); return ret; } @@ -248,7 +223,7 @@ static int update_netprio(const void *v, struct file *file, unsigned n) return 0; } -void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +static void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct task_struct *p; void *v; @@ -276,22 +251,13 @@ static struct cftype ss_files[] = { struct cgroup_subsys net_prio_subsys = { .name = "net_prio", - .create = cgrp_create, - .destroy = cgrp_destroy, + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, .attach = net_prio_attach, .subsys_id = net_prio_subsys_id, .base_cftypes = ss_files, .module = THIS_MODULE, - - /* - * net_prio has artificial limit on the number of cgroups and - * disallows nesting making it impossible to co-mount it with other - * hierarchical subsystems. Remove the artificially low PRIOIDX_SZ - * limit and properly nest configuration such that children follow - * their parents' configurations by default and are allowed to - * override and remove the following. - */ - .broken_hierarchy = true, }; static int netprio_device_event(struct notifier_block *unused, diff --git a/net/core/pktgen.c b/net/core/pktgen.c index d1dc14c2aac4..b29dacf900f9 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -419,20 +419,6 @@ struct pktgen_thread { #define REMOVE 1 #define FIND 0 -static inline ktime_t ktime_now(void) -{ - struct timespec ts; - ktime_get_ts(&ts); - - return timespec_to_ktime(ts); -} - -/* This works even if 32 bit because of careful byte order choice */ -static inline int ktime_lt(const ktime_t cmp1, const ktime_t cmp2) -{ - return cmp1.tv64 < cmp2.tv64; -} - static const char version[] = "Packet Generator for packet performance testing. " "Version: " VERSION "\n"; @@ -675,7 +661,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_puts(seq, "\n"); /* not really stopped, more like last-running-at */ - stopped = pkt_dev->running ? ktime_now() : pkt_dev->stopped_at; + stopped = pkt_dev->running ? ktime_get() : pkt_dev->stopped_at; idle = pkt_dev->idle_acc; do_div(idle, NSEC_PER_USEC); @@ -2141,12 +2127,12 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) return; } - start_time = ktime_now(); + start_time = ktime_get(); if (remaining < 100000) { /* for small delays (<100us), just loop until limit is reached */ do { - end_time = ktime_now(); - } while (ktime_lt(end_time, spin_until)); + end_time = ktime_get(); + } while (ktime_compare(end_time, spin_until) < 0); } else { /* see do_nanosleep */ hrtimer_init_sleeper(&t, current); @@ -2162,7 +2148,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) hrtimer_cancel(&t.timer); } while (t.task && pkt_dev->running && !signal_pending(current)); __set_current_state(TASK_RUNNING); - end_time = ktime_now(); + end_time = ktime_get(); } pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); @@ -2427,11 +2413,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } } else { /* IPV6 * */ - if (pkt_dev->min_in6_daddr.s6_addr32[0] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[1] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[2] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[3] == 0) ; - else { + if (!ipv6_addr_any(&pkt_dev->min_in6_daddr)) { int i; /* Only random destinations yet */ @@ -2916,8 +2898,7 @@ static void pktgen_run(struct pktgen_thread *t) pktgen_clear_counters(pkt_dev); pkt_dev->running = 1; /* Cranke yeself! */ pkt_dev->skb = NULL; - pkt_dev->started_at = - pkt_dev->next_tx = ktime_now(); + pkt_dev->started_at = pkt_dev->next_tx = ktime_get(); set_pkt_overhead(pkt_dev); @@ -3076,7 +3057,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) kfree_skb(pkt_dev->skb); pkt_dev->skb = NULL; - pkt_dev->stopped_at = ktime_now(); + pkt_dev->stopped_at = ktime_get(); pkt_dev->running = 0; show_results(pkt_dev, nr_frags); @@ -3095,7 +3076,7 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t) continue; if (best == NULL) best = pkt_dev; - else if (ktime_lt(pkt_dev->next_tx, best->next_tx)) + else if (ktime_compare(pkt_dev->next_tx, best->next_tx) < 0) best = pkt_dev; } if_unlock(t); @@ -3180,14 +3161,14 @@ static void pktgen_rem_thread(struct pktgen_thread *t) static void pktgen_resched(struct pktgen_dev *pkt_dev) { - ktime_t idle_start = ktime_now(); + ktime_t idle_start = ktime_get(); schedule(); - pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start)); + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); } static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) { - ktime_t idle_start = ktime_now(); + ktime_t idle_start = ktime_get(); while (atomic_read(&(pkt_dev->skb->users)) != 1) { if (signal_pending(current)) @@ -3198,7 +3179,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) else cpu_relax(); } - pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start)); + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); } static void pktgen_xmit(struct pktgen_dev *pkt_dev) @@ -3220,7 +3201,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) * "never transmit" */ if (unlikely(pkt_dev->delay == ULLONG_MAX)) { - pkt_dev->next_tx = ktime_add_ns(ktime_now(), ULONG_MAX); + pkt_dev->next_tx = ktime_add_ns(ktime_get(), ULONG_MAX); return; } diff --git a/net/core/request_sock.c b/net/core/request_sock.c index c31d9e8668c3..4425148d2b51 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -186,8 +186,6 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, struct fastopen_queue *fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; - BUG_ON(!spin_is_locked(&sk->sk_lock.slock) && !sock_owned_by_user(sk)); - tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 76d4c2c3c89b..1868625af25e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -128,7 +128,7 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) if (tab == NULL || tab[msgindex].doit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; - return tab ? tab[msgindex].doit : NULL; + return tab[msgindex].doit; } static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) @@ -143,7 +143,7 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) if (tab == NULL || tab[msgindex].dumpit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; - return tab ? tab[msgindex].dumpit : NULL; + return tab[msgindex].dumpit; } static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) @@ -158,7 +158,7 @@ static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) if (tab == NULL || tab[msgindex].calcit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; - return tab ? tab[msgindex].calcit : NULL; + return tab[msgindex].calcit; } /** @@ -1316,6 +1316,10 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + err = -EPERM; + goto errout; + } err = dev_change_net_namespace(dev, net, ifname); put_net(net); if (err) @@ -1638,7 +1642,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } EXPORT_SYMBOL(rtnl_configure_link); -struct net_device *rtnl_create_link(struct net *src_net, struct net *net, +struct net_device *rtnl_create_link(struct net *net, char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) { int err; @@ -1836,7 +1840,7 @@ replay: if (IS_ERR(dest_net)) return PTR_ERR(dest_net); - dev = rtnl_create_link(net, dest_net, ifname, ops, tb); + dev = rtnl_create_link(dest_net, ifname, ops, tb); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out; @@ -2057,6 +2061,9 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) u8 *addr; int err; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); if (err < 0) return err; @@ -2123,6 +2130,9 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) int err = -EINVAL; __u8 *addr; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (nlmsg_len(nlh) < sizeof(*ndm)) return -EINVAL; @@ -2192,7 +2202,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, - portid, seq, 0, NTF_SELF); + portid, seq, + RTM_NEWNEIGH, NTF_SELF); if (err < 0) return err; skip: @@ -2252,6 +2263,211 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u16 mode) +{ + struct nlmsghdr *nlh; + struct ifinfomsg *ifm; + struct nlattr *br_afspec; + u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + + nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); + if (nlh == NULL) + return -EMSGSIZE; + + ifm = nlmsg_data(nlh); + ifm->ifi_family = AF_BRIDGE; + ifm->__ifi_pad = 0; + ifm->ifi_type = dev->type; + ifm->ifi_index = dev->ifindex; + ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_change = 0; + + + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u8(skb, IFLA_OPERSTATE, operstate) || + (dev->master && + nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (dev->addr_len && + nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink))) + goto nla_put_failure; + + br_afspec = nla_nest_start(skb, IFLA_AF_SPEC); + if (!br_afspec) + goto nla_put_failure; + + if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) || + nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) { + nla_nest_cancel(skb, br_afspec); + goto nla_put_failure; + } + nla_nest_end(skb, br_afspec); + + return nlmsg_end(skb, nlh); +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} +EXPORT_SYMBOL(ndo_dflt_bridge_getlink); + +static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int idx = 0; + u32 portid = NETLINK_CB(cb->skb).portid; + u32 seq = cb->nlh->nlmsg_seq; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + const struct net_device_ops *ops = dev->netdev_ops; + struct net_device *master = dev->master; + + if (master && master->netdev_ops->ndo_bridge_getlink) { + if (idx >= cb->args[0] && + master->netdev_ops->ndo_bridge_getlink( + skb, portid, seq, dev) < 0) + break; + idx++; + } + + if (ops->ndo_bridge_getlink) { + if (idx >= cb->args[0] && + ops->ndo_bridge_getlink(skb, portid, seq, dev) < 0) + break; + idx++; + } + } + rcu_read_unlock(); + cb->args[0] = idx; + + return skb->len; +} + +static inline size_t bridge_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + + nla_total_size(sizeof(u32)) /* IFLA_MASTER */ + + nla_total_size(sizeof(u32)) /* IFLA_MTU */ + + nla_total_size(sizeof(u32)) /* IFLA_LINK */ + + nla_total_size(sizeof(u32)) /* IFLA_OPERSTATE */ + + nla_total_size(sizeof(u8)) /* IFLA_PROTINFO */ + + nla_total_size(sizeof(struct nlattr)) /* IFLA_AF_SPEC */ + + nla_total_size(sizeof(u16)) /* IFLA_BRIDGE_FLAGS */ + + nla_total_size(sizeof(u16)); /* IFLA_BRIDGE_MODE */ +} + +static int rtnl_bridge_notify(struct net_device *dev, u16 flags) +{ + struct net *net = dev_net(dev); + struct net_device *master = dev->master; + struct sk_buff *skb; + int err = -EOPNOTSUPP; + + skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC); + if (!skb) { + err = -ENOMEM; + goto errout; + } + + if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && + master && master->netdev_ops->ndo_bridge_getlink) { + err = master->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + if (err < 0) + goto errout; + } + + if ((flags & BRIDGE_FLAGS_SELF) && + dev->netdev_ops->ndo_bridge_getlink) { + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + if (err < 0) + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); + return 0; +errout: + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); + return err; +} + +static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, + void *arg) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + struct nlattr *br_spec, *attr = NULL; + int rem, err = -EOPNOTSUPP; + u16 oflags, flags = 0; + bool have_flags = false; + + if (nlmsg_len(nlh) < sizeof(*ifm)) + return -EINVAL; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_family != AF_BRIDGE) + return -EPFNOSUPPORT; + + dev = __dev_get_by_index(net, ifm->ifi_index); + if (!dev) { + pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + return -ENODEV; + } + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (br_spec) { + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + have_flags = true; + flags = nla_get_u16(attr); + break; + } + } + } + + oflags = flags; + + if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { + if (!dev->master || + !dev->master->netdev_ops->ndo_bridge_setlink) { + err = -EOPNOTSUPP; + goto out; + } + + err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh); + if (err) + goto out; + + flags &= ~BRIDGE_FLAGS_MASTER; + } + + if ((flags & BRIDGE_FLAGS_SELF)) { + if (!dev->netdev_ops->ndo_bridge_setlink) + err = -EOPNOTSUPP; + else + err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh); + + if (!err) + flags &= ~BRIDGE_FLAGS_SELF; + } + + if (have_flags) + memcpy(nla_data(attr), &flags, sizeof(flags)); + /* Generate event to notify upper layer of bridge change */ + if (!err) + err = rtnl_bridge_notify(dev, oflags); +out: + return err; +} + /* Protected by RTNL sempahore. */ static struct rtattr **rta_buf; static int rtattr_max; @@ -2282,7 +2498,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !capable(CAP_NET_ADMIN)) + if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { @@ -2433,5 +2649,8 @@ void __init rtnetlink_init(void) rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL); rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL); rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL); + + rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL); + rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); } diff --git a/net/core/scm.c b/net/core/scm.c index ab570841a532..905dcc6ad1e3 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -35,6 +35,7 @@ #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> +#include <net/cls_cgroup.h> /* @@ -51,11 +52,11 @@ static __inline__ int scm_check_creds(struct ucred *creds) if (!uid_valid(uid) || !gid_valid(gid)) return -EINVAL; - if ((creds->pid == task_tgid_vnr(current) || capable(CAP_SYS_ADMIN)) && + if ((creds->pid == task_tgid_vnr(current) || nsown_capable(CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || - uid_eq(uid, cred->suid)) || capable(CAP_SETUID)) && + uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || - gid_eq(gid, cred->sgid)) || capable(CAP_SETGID))) { + gid_eq(gid, cred->sgid)) || nsown_capable(CAP_SETGID))) { return 0; } return -EPERM; @@ -302,8 +303,10 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } /* Bump the usage count and install the file. */ sock = sock_from_file(fp[i], &err); - if (sock) + if (sock) { sock_update_netprioidx(sock->sk, current); + sock_update_classid(sock->sk, current); + } fd_install(new_fd, get_file(fp[i])); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4007c1437fda..a9a2ae3e2213 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -519,7 +519,7 @@ static void skb_release_data(struct sk_buff *skb) uarg = skb_shinfo(skb)->destructor_arg; if (uarg->callback) - uarg->callback(uarg); + uarg->callback(uarg, true); } if (skb_has_frag_list(skb)) @@ -635,6 +635,26 @@ void kfree_skb(struct sk_buff *skb) EXPORT_SYMBOL(kfree_skb); /** + * skb_tx_error - report an sk_buff xmit error + * @skb: buffer that triggered an error + * + * Report xmit error if a device callback is tracking this skb. + * skb must be freed afterwards. + */ +void skb_tx_error(struct sk_buff *skb) +{ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + struct ubuf_info *uarg; + + uarg = skb_shinfo(skb)->destructor_arg; + if (uarg->callback) + uarg->callback(uarg, false); + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + } +} +EXPORT_SYMBOL(skb_tx_error); + +/** * consume_skb - free an skbuff * @skb: buffer to free * @@ -662,11 +682,14 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; + new->inner_transport_header = old->inner_transport_header; + new->inner_network_header = old->inner_transport_header; skb_dst_copy(new, old); new->rxhash = old->rxhash; new->ooo_okay = old->ooo_okay; new->l4_rxhash = old->l4_rxhash; new->no_fcs = old->no_fcs; + new->encapsulation = old->encapsulation; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif @@ -797,7 +820,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); - uarg->callback(uarg); + uarg->callback(uarg, false); /* skb frags point to kernel buffers */ for (i = num_frags - 1; i >= 0; i--) { @@ -872,6 +895,8 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->network_header += offset; if (skb_mac_header_was_set(new)) new->mac_header += offset; + new->inner_transport_header += offset; + new->inner_network_header += offset; #endif skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; @@ -1069,6 +1094,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; + skb->inner_transport_header += off; + skb->inner_network_header += off; /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) skb->csum_start += nhead; @@ -1168,6 +1195,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, n->network_header += off; if (skb_mac_header_was_set(skb)) n->mac_header += off; + n->inner_transport_header += off; + n->inner_network_header += off; #endif return n; @@ -1620,7 +1649,7 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, - struct sk_buff *skb, struct sock *sk) + struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); @@ -1653,14 +1682,14 @@ static bool spd_can_coalesce(const struct splice_pipe_desc *spd, static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, - struct sk_buff *skb, bool linear, + bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { - page = linear_to_page(page, len, &offset, skb, sk); + page = linear_to_page(page, len, &offset, sk); if (!page) return true; } @@ -1677,23 +1706,9 @@ static bool spd_fill_page(struct splice_pipe_desc *spd, return false; } -static inline void __segment_seek(struct page **page, unsigned int *poff, - unsigned int *plen, unsigned int off) -{ - unsigned long n; - - *poff += off; - n = *poff / PAGE_SIZE; - if (n) - *page = nth_page(*page, n); - - *poff = *poff % PAGE_SIZE; - *plen -= off; -} - static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, + unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) @@ -1708,23 +1723,19 @@ static bool __splice_segment(struct page *page, unsigned int poff, } /* ignore any bits we already processed */ - if (*off) { - __segment_seek(&page, &poff, &plen, *off); - *off = 0; - } + poff += *off; + plen -= *off; + *off = 0; do { unsigned int flen = min(*len, plen); - /* the linear region may spread across several pages */ - flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - - if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) + if (spd_fill_page(spd, pipe, page, &flen, poff, + linear, sk)) return true; - - __segment_seek(&page, &poff, &plen, flen); + poff += flen; + plen -= flen; *len -= flen; - } while (*len && plen); return false; @@ -1748,7 +1759,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, + offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; @@ -1761,7 +1772,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(skb_frag_page(f), f->page_offset, skb_frag_size(f), - offset, len, skb, spd, false, sk, pipe)) + offset, len, spd, false, sk, pipe)) return true; } @@ -2999,12 +3010,11 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) memcpy(skb_mac_header(nskb), skb_mac_header(p), p->data - skb_mac_header(p)); - *NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p); skb_shinfo(nskb)->frag_list = p; skb_shinfo(nskb)->gso_size = pinfo->gso_size; pinfo->gso_size = 0; skb_header_release(p); - nskb->prev = p; + NAPI_GRO_CB(nskb)->last = p; nskb->data_len += p->len; nskb->truesize += p->truesize; @@ -3030,8 +3040,8 @@ merge: __skb_pull(skb, offset); - p->prev->next = skb; - p->prev = skb; + NAPI_GRO_CB(p)->last->next = skb; + NAPI_GRO_CB(p)->last = skb; skb_header_release(skb); done: diff --git a/net/core/sock.c b/net/core/sock.c index 8a146cfcc366..bc131d419683 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -505,7 +505,8 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); -static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) +static int sock_setbindtodevice(struct sock *sk, char __user *optval, + int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES @@ -515,7 +516,7 @@ static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) /* Sorry... */ ret = -EPERM; - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; @@ -562,6 +563,59 @@ out: return ret; } +static int sock_getbindtodevice(struct sock *sk, char __user *optval, + int __user *optlen, int len) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + struct net_device *dev; + char devname[IFNAMSIZ]; + unsigned seq; + + if (sk->sk_bound_dev_if == 0) { + len = 0; + goto zero; + } + + ret = -EINVAL; + if (len < IFNAMSIZ) + goto out; + +retry: + seq = read_seqcount_begin(&devnet_rename_seq); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + ret = -ENODEV; + if (!dev) { + rcu_read_unlock(); + goto out; + } + + strcpy(devname, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) + goto retry; + + len = strlen(devname) + 1; + + ret = -EFAULT; + if (copy_to_user(optval, devname, len)) + goto out; + +zero: + ret = -EFAULT; + if (put_user(len, optlen)) + goto out; + + ret = 0; + +out: +#endif + + return ret; +} + static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) { if (valbool) @@ -589,7 +643,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, */ if (optname == SO_BINDTODEVICE) - return sock_bindtodevice(sk, optval, optlen); + return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; @@ -696,7 +750,8 @@ set_rcvbuf: break; case SO_PRIORITY: - if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) + if ((val >= 0 && val <= 6) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) sk->sk_priority = val; else ret = -EPERM; @@ -813,7 +868,7 @@ set_rcvbuf: clear_bit(SOCK_PASSSEC, &sock->flags); break; case SO_MARK: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) ret = -EPERM; else sk->sk_mark = val; @@ -1074,6 +1129,17 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); break; + + case SO_BINDTODEVICE: + return sock_getbindtodevice(sk, optval, optlen, len); + + case SO_GET_FILTER: + len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); + if (len < 0) + return len; + + goto lenout; + default: return -ENOPROTOOPT; } @@ -1214,13 +1280,11 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) #ifdef CONFIG_CGROUPS #if IS_ENABLED(CONFIG_NET_CLS_CGROUP) -void sock_update_classid(struct sock *sk) +void sock_update_classid(struct sock *sk, struct task_struct *task) { u32 classid; - rcu_read_lock(); /* doing current task, which cannot vanish. */ - classid = task_cls_classid(current); - rcu_read_unlock(); + classid = task_cls_classid(task); if (classid != sk->sk_classid) sk->sk_classid = classid; } @@ -1263,7 +1327,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sock_net_set(sk, get_net(net)); atomic_set(&sk->sk_wmem_alloc, 1); - sock_update_classid(sk); + sock_update_classid(sk, current); sock_update_netprioidx(sk, current); } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index a7c36845b123..d1b08045a9df 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -216,6 +216,11 @@ static __net_init int sysctl_core_net_init(struct net *net) goto err_dup; tbl[0].data = &net->core.sysctl_somaxconn; + + /* Don't export any sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) { + tbl[0].procname = NULL; + } } net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 70989e672304..1b588e23cf80 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1662,8 +1662,8 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct nlmsghdr *reply_nlh = NULL; const struct reply_func *fn; - if (!net_eq(net, &init_net)) - return -EINVAL; + if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN)) + return -EPERM; ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, dcbnl_rtnl_policy); @@ -1681,7 +1681,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (!tb[DCB_ATTR_IFNAME]) return -EINVAL; - netdev = dev_get_by_name(&init_net, nla_data(tb[DCB_ATTR_IFNAME])); + netdev = dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME])); if (!netdev) return -ENODEV; @@ -1705,7 +1705,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) nlmsg_end(reply_skb, reply_nlh); - ret = rtnl_unicast(reply_skb, &init_net, portid); + ret = rtnl_unicast(reply_skb, net, portid); out: dev_put(netdev); return ret; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 176ecdba4a22..4f9f5eb478f1 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -439,8 +439,8 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: - bh_unlock_sock(newsk); - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); goto exit; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 56840b249f3b..6e05981f271e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -585,7 +585,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newinet->inet_rcv_saddr = LOOPBACK4_IPV6; if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); goto out; } __inet6_hash(newsk, NULL); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index ea850ce35d4a..662071b249cc 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -174,8 +174,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, * To protect against Request floods, increment retrans * counter (backoff, monitored by dccp_response_timer). */ - req->retrans++; - req->rsk_ops->rtx_syn_ack(sk, req, NULL); + inet_rtx_syn_ack(sk, req); } /* Network Duplicate, discard packet */ return NULL; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 7b7e561412d3..e47ba9fc4a0e 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -573,6 +573,9 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct dn_ifaddr __rcu **ifap; int err = -EINVAL; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!net_eq(net, &init_net)) goto errout; @@ -614,6 +617,9 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct dn_ifaddr *ifa; int err; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!net_eq(net, &init_net)) return -EINVAL; diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 102d6106a942..e36614eccc04 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -520,6 +520,9 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void * struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!net_eq(net, &init_net)) return -EINVAL; @@ -540,6 +543,9 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void * struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!net_eq(net, &init_net)) return -EINVAL; diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 8aa4b1115384..0a69d0757795 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -259,20 +259,16 @@ static int __init init_dns_resolver(void) if (!cred) return -ENOMEM; - keyring = key_alloc(&key_type_keyring, ".dns_resolver", - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, - (KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ, - KEY_ALLOC_NOT_IN_QUOTA); + keyring = keyring_alloc(".dns_resolver", + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ, + KEY_ALLOC_NOT_IN_QUOTA, NULL); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto failed_put_cred; } - ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL); - if (ret < 0) - goto failed_put_key; - ret = register_key_type(&key_type_dns_resolver); if (ret < 0) goto failed_put_key; @@ -304,3 +300,4 @@ static void __exit exit_dns_resolver(void) module_init(init_dns_resolver) module_exit(exit_dns_resolver) MODULE_LICENSE("GPL"); + diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 274791cd7a35..f5eede1d6cb8 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -1,26 +1,24 @@ +config HAVE_NET_DSA + def_bool y + depends on NETDEVICES && !S390 + +# Drivers must select NET_DSA and the appropriate tagging format + config NET_DSA - tristate "Distributed Switch Architecture support" - default n - depends on EXPERIMENTAL && NETDEVICES && !S390 + tristate + depends on HAVE_NET_DSA select PHYLIB - ---help--- - This allows you to use hardware switch chips that use - the Distributed Switch Architecture. - if NET_DSA # tagging formats config NET_DSA_TAG_DSA bool - default n config NET_DSA_TAG_EDSA bool - default n config NET_DSA_TAG_TRAILER bool - default n endif diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 6d42c17af96b..f651da60f161 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -1047,7 +1047,8 @@ static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) goto error; } - if (skb->len <= IEEE802154_MTU) { + /* Send directly if less than the MTU minus the 2 checksum bytes. */ + if (skb->len <= IEEE802154_MTU - IEEE802154_MFR_SIZE) { err = dev_queue_xmit(skb); goto out; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 766c59658563..24b384b7903e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -346,7 +346,8 @@ lookup_protocol: } err = -EPERM; - if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && + !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; err = -EAFNOSUPPORT; @@ -473,6 +474,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; int err; @@ -496,7 +498,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since @@ -516,7 +518,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) snum = ntohs(addr->sin_port); err = -EACCES; - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; /* We keep a pair of addresses. rcv_saddr is the one @@ -1251,7 +1254,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); static int inet_gso_send_check(struct sk_buff *skb) { - const struct net_protocol *ops; + const struct net_offload *ops; const struct iphdr *iph; int proto; int ihl; @@ -1275,9 +1278,9 @@ static int inet_gso_send_check(struct sk_buff *skb) err = -EPROTONOSUPPORT; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (likely(ops && ops->gso_send_check)) - err = ops->gso_send_check(skb); + ops = rcu_dereference(inet_offloads[proto]); + if (likely(ops && ops->callbacks.gso_send_check)) + err = ops->callbacks.gso_send_check(skb); rcu_read_unlock(); out: @@ -1288,7 +1291,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); - const struct net_protocol *ops; + const struct net_offload *ops; struct iphdr *iph; int proto; int ihl; @@ -1325,9 +1328,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (likely(ops && ops->gso_segment)) - segs = ops->gso_segment(skb, features); + ops = rcu_dereference(inet_offloads[proto]); + if (likely(ops && ops->callbacks.gso_segment)) + segs = ops->callbacks.gso_segment(skb, features); rcu_read_unlock(); if (!segs || IS_ERR(segs)) @@ -1356,7 +1359,7 @@ out: static struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - const struct net_protocol *ops; + const struct net_offload *ops; struct sk_buff **pp = NULL; struct sk_buff *p; const struct iphdr *iph; @@ -1378,8 +1381,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, proto = iph->protocol; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (!ops || !ops->gro_receive) + ops = rcu_dereference(inet_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) goto out_unlock; if (*(u8 *)iph != 0x45) @@ -1420,7 +1423,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); - pp = ops->gro_receive(head, skb); + pp = ops->callbacks.gro_receive(head, skb); out_unlock: rcu_read_unlock(); @@ -1435,7 +1438,7 @@ static int inet_gro_complete(struct sk_buff *skb) { __be16 newlen = htons(skb->len - skb_network_offset(skb)); struct iphdr *iph = ip_hdr(skb); - const struct net_protocol *ops; + const struct net_offload *ops; int proto = iph->protocol; int err = -ENOSYS; @@ -1443,11 +1446,11 @@ static int inet_gro_complete(struct sk_buff *skb) iph->tot_len = newlen; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (WARN_ON(!ops || !ops->gro_complete)) + ops = rcu_dereference(inet_offloads[proto]); + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->gro_complete(skb); + err = ops->callbacks.gro_complete(skb); out_unlock: rcu_read_unlock(); @@ -1558,23 +1561,33 @@ static const struct net_protocol tcp_protocol = { .early_demux = tcp_v4_early_demux, .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, - .gso_send_check = tcp_v4_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, .no_policy = 1, .netns_ok = 1, }; +static const struct net_offload tcp_offload = { + .callbacks = { + .gso_send_check = tcp_v4_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, +}; + static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, - .gso_send_check = udp4_ufo_send_check, - .gso_segment = udp4_ufo_fragment, .no_policy = 1, .netns_ok = 1, }; +static const struct net_offload udp_offload = { + .callbacks = { + .gso_send_check = udp4_ufo_send_check, + .gso_segment = udp4_ufo_fragment, + }, +}; + static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = ping_err, @@ -1659,13 +1672,35 @@ static int ipv4_proc_init(void); * IP protocol layer initialiser */ +static struct packet_offload ip_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IP), + .callbacks = { + .gso_send_check = inet_gso_send_check, + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, +}; + +static int __init ipv4_offload_init(void) +{ + /* + * Add offloads + */ + if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0) + pr_crit("%s: Cannot add UDP protocol offload\n", __func__); + if (inet_add_offload(&tcp_offload, IPPROTO_TCP) < 0) + pr_crit("%s: Cannot add TCP protocol offlaod\n", __func__); + + dev_add_offload(&ip_packet_offload); + return 0; +} + +fs_initcall(ipv4_offload_init); + static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, - .gso_send_check = inet_gso_send_check, - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, }; static int __init inet_init(void) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a0d8392491c3..a69b4e4a02b5 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -269,7 +269,11 @@ static void ah_input_done(struct crypto_async_request *base, int err) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -381,7 +385,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr; @@ -413,9 +420,12 @@ static void ah4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 47800459e4cb..9547a273b9e9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -321,7 +321,7 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; - u8 *dst_ha = NULL; + u8 dst_ha[MAX_ADDR_LEN], *dst_hw = NULL; struct net_device *dev = neigh->dev; __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); @@ -363,8 +363,8 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) if (probes < 0) { if (!(neigh->nud_state & NUD_VALID)) pr_debug("trying to ucast probe in NUD_INVALID\n"); - dst_ha = neigh->ha; - read_lock_bh(&neigh->lock); + neigh_ha_snapshot(dst_ha, neigh, dev); + dst_hw = dst_ha; } else { probes -= neigh->parms->app_probes; if (probes < 0) { @@ -376,9 +376,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_ha, dev->dev_addr, NULL); - if (dst_ha) - read_unlock_bh(&neigh->lock); + dst_hw, dev->dev_addr, NULL); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -1161,7 +1159,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch (cmd) { case SIOCDARP: case SIOCSARP: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 424fafbc8cb0..b28e863fe0a7 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -85,3 +85,28 @@ out: return err; } EXPORT_SYMBOL(ip4_datagram_connect); + +void ip4_datagram_release_cb(struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; + struct flowi4 fl4; + struct rtable *rt; + + if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) + return; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_protocol, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + if (!IS_ERR(rt)) + __sk_dst_set(sk, &rt->dst); + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2a6abc163ed2..a8e4f2665d5e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -55,6 +55,7 @@ #include <linux/sysctl.h> #endif #include <linux/kmod.h> +#include <linux/netconf.h> #include <net/arp.h> #include <net/ip.h> @@ -723,7 +724,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSIFFLAGS: ret = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; break; case SIOCSIFADDR: /* Set interface address (and family) */ @@ -731,7 +732,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ ret = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; ret = -EINVAL; if (sin->sin_family != AF_INET) @@ -822,9 +823,9 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!ifa) { ret = -ENOBUFS; ifa = inet_alloc_ifa(); - INIT_HLIST_NODE(&ifa->hash); if (!ifa) break; + INIT_HLIST_NODE(&ifa->hash); if (colon) memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ); else @@ -1442,6 +1443,155 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) return 0; } +static int inet_netconf_msgsize_devconf(int type) +{ + int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + + nla_total_size(4); /* NETCONFA_IFINDEX */ + + /* type -1 is used for ALL */ + if (type == -1 || type == NETCONFA_FORWARDING) + size += nla_total_size(4); + if (type == -1 || type == NETCONFA_RP_FILTER) + size += nla_total_size(4); + if (type == -1 || type == NETCONFA_MC_FORWARDING) + size += nla_total_size(4); + + return size; +} + +static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, + struct ipv4_devconf *devconf, u32 portid, + u32 seq, int event, unsigned int flags, + int type) +{ + struct nlmsghdr *nlh; + struct netconfmsg *ncm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), + flags); + if (nlh == NULL) + return -EMSGSIZE; + + ncm = nlmsg_data(nlh); + ncm->ncm_family = AF_INET; + + if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) + goto nla_put_failure; + + /* type -1 is used for ALL */ + if ((type == -1 || type == NETCONFA_FORWARDING) && + nla_put_s32(skb, NETCONFA_FORWARDING, + IPV4_DEVCONF(*devconf, FORWARDING)) < 0) + goto nla_put_failure; + if ((type == -1 || type == NETCONFA_RP_FILTER) && + nla_put_s32(skb, NETCONFA_RP_FILTER, + IPV4_DEVCONF(*devconf, RP_FILTER)) < 0) + goto nla_put_failure; + if ((type == -1 || type == NETCONFA_MC_FORWARDING) && + nla_put_s32(skb, NETCONFA_MC_FORWARDING, + IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, + struct ipv4_devconf *devconf) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, + RTM_NEWNETCONF, 0, type); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); +} + +static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { + [NETCONFA_IFINDEX] = { .len = sizeof(int) }, + [NETCONFA_FORWARDING] = { .len = sizeof(int) }, + [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, +}; + +static int inet_netconf_get_devconf(struct sk_buff *in_skb, + struct nlmsghdr *nlh, + void *arg) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NETCONFA_MAX+1]; + struct netconfmsg *ncm; + struct sk_buff *skb; + struct ipv4_devconf *devconf; + struct in_device *in_dev; + struct net_device *dev; + int ifindex; + int err; + + err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, + devconf_ipv4_policy); + if (err < 0) + goto errout; + + err = EINVAL; + if (!tb[NETCONFA_IFINDEX]) + goto errout; + + ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); + switch (ifindex) { + case NETCONFA_IFINDEX_ALL: + devconf = net->ipv4.devconf_all; + break; + case NETCONFA_IFINDEX_DEFAULT: + devconf = net->ipv4.devconf_dflt; + break; + default: + dev = __dev_get_by_index(net, ifindex); + if (dev == NULL) + goto errout; + in_dev = __in_dev_get_rtnl(dev); + if (in_dev == NULL) + goto errout; + devconf = &in_dev->cnf; + break; + } + + err = -ENOBUFS; + skb = nlmsg_new(inet_netconf_msgsize_devconf(-1), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet_netconf_fill_devconf(skb, ifindex, devconf, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWNETCONF, 0, + -1); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout: + return err; +} + #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) @@ -1467,6 +1617,12 @@ static void inet_forward_change(struct net *net) IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all); + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; @@ -1474,8 +1630,11 @@ static void inet_forward_change(struct net *net) dev_disable_lro(dev); rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); - if (in_dev) + if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + dev->ifindex, &in_dev->cnf); + } rcu_read_unlock(); } } @@ -1501,6 +1660,23 @@ static int devinet_conf_proc(ctl_table *ctl, int write, i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); + if (i == IPV4_DEVCONF_RP_FILTER - 1 && + new_value != old_value) { + int ifindex; + + if (cnf == net->ipv4.devconf_dflt) + ifindex = NETCONFA_IFINDEX_DEFAULT; + else if (cnf == net->ipv4.devconf_all) + ifindex = NETCONFA_IFINDEX_ALL; + else { + struct in_device *idev = + container_of(cnf, struct in_device, + cnf); + ifindex = idev->dev->ifindex; + } + inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER, + ifindex, cnf); + } } return ret; @@ -1527,15 +1703,23 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, } if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); - } else if (*valp) { + } else { struct ipv4_devconf *cnf = ctl->extra1; struct in_device *idev = container_of(cnf, struct in_device, cnf); - dev_disable_lro(idev->dev); + if (*valp) + dev_disable_lro(idev->dev); + inet_netconf_notify_devconf(net, + NETCONFA_FORWARDING, + idev->dev->ifindex, + cnf); } rtnl_unlock(); rt_cache_flush(net); - } + } else + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt); } return ret; @@ -1809,5 +1993,7 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); + rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, + NULL, NULL); } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b61e9deb7c7e..3b4f0cd2e63e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -346,7 +346,10 @@ static int esp_input_done2(struct sk_buff *skb, int err) pskb_trim(skb, skb->len - alen - padlen - 2); __skb_pull(skb, hlen); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr[1]; @@ -499,9 +502,12 @@ static void esp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 825c608826de..5cd75e2dab2c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -488,7 +488,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&rt, arg, sizeof(rt))) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 71b125cd5db1..4797a800faf8 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -803,7 +803,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) unsigned int bytes; if (!new_size) - new_size = 1; + new_size = 16; bytes = new_size * sizeof(struct hlist_head *); new_info_hash = fib_info_hash_alloc(bytes); new_laddrhash = fib_info_hash_alloc(bytes); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f2eccd531746..17ff9fd7cdda 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -257,7 +257,8 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, struct inet_peer *peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1); rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); - inet_putpeer(peer); + if (peer) + inet_putpeer(peer); } out: return rc; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d34ce2972c8f..d0670f00d524 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -521,21 +521,31 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, int *expire, int *resend) { if (!rskq_defer_accept) { - *expire = req->retrans >= thresh; + *expire = req->num_timeout >= thresh; *resend = 1; return; } - *expire = req->retrans >= thresh && - (!inet_rsk(req)->acked || req->retrans >= max_retries); + *expire = req->num_timeout >= thresh && + (!inet_rsk(req)->acked || req->num_timeout >= max_retries); /* * Do not resend while waiting for data after ACK, * start to resend on end of deferring period to give * last chance for data or ACK to create established socket. */ *resend = !inet_rsk(req)->acked || - req->retrans >= rskq_defer_accept - 1; + req->num_timeout >= rskq_defer_accept - 1; } +int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) +{ + int err = req->rsk_ops->rtx_syn_ack(parent, req, NULL); + + if (!err) + req->num_retrans++; + return err; +} +EXPORT_SYMBOL(inet_rtx_syn_ack); + void inet_csk_reqsk_queue_prune(struct sock *parent, const unsigned long interval, const unsigned long timeout, @@ -599,13 +609,14 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, req->rsk_ops->syn_ack_timeout(parent, req); if (!expire && (!resend || - !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || + !inet_rtx_syn_ack(parent, req) || inet_rsk(req)->acked)) { unsigned long timeo; - if (req->retrans++ == 0) + if (req->num_timeout++ == 0) lopt->qlen_young--; - timeo = min((timeout << req->retrans), max_rto); + timeo = min(timeout << req->num_timeout, + max_rto); req->expires = now + timeo; reqp = &req->dl_next; continue; @@ -699,6 +710,22 @@ void inet_csk_destroy_sock(struct sock *sk) } EXPORT_SYMBOL(inet_csk_destroy_sock); +/* This function allows to force a closure of a socket after the call to + * tcp/dccp_create_openreq_child(). + */ +void inet_csk_prepare_forced_close(struct sock *sk) +{ + /* sk_clone_lock locked the socket and set refcnt to 2 */ + bh_unlock_sock(sk); + sock_put(sk); + + /* The below has to be done to allow calling inet_csk_destroy_sock */ + sock_set_flag(sk, SOCK_DEAD); + percpu_counter_inc(sk->sk_prot->orphan_count); + inet_sk(sk)->inet_num = 0; +} +EXPORT_SYMBOL(inet_csk_prepare_forced_close); + int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) { struct inet_sock *inet = inet_sk(sk); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 535584c00f91..7afa2c3c788f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -44,6 +44,10 @@ struct inet_diag_entry { u16 dport; u16 family; u16 userlocks; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr saddr_storage; /* for IPv4-mapped-IPv6 addresses */ + struct in6_addr daddr_storage; /* for IPv4-mapped-IPv6 addresses */ +#endif }; static DEFINE_MUTEX(inet_diag_table_mutex); @@ -105,6 +109,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; + if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) + goto errout; + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, * hence this needs to be included regardless of socket family. */ @@ -428,25 +435,31 @@ static int inet_diag_bc_run(const struct nlattr *_bc, break; } - if (cond->prefix_len == 0) - break; - if (op->code == INET_DIAG_BC_S_COND) addr = entry->saddr; else addr = entry->daddr; + if (cond->family != AF_UNSPEC && + cond->family != entry->family) { + if (entry->family == AF_INET6 && + cond->family == AF_INET) { + if (addr[0] == 0 && addr[1] == 0 && + addr[2] == htonl(0xffff) && + bitstring_match(addr + 3, + cond->addr, + cond->prefix_len)) + break; + } + yes = 0; + break; + } + + if (cond->prefix_len == 0) + break; if (bitstring_match(addr, cond->addr, cond->prefix_len)) break; - if (entry->family == AF_INET6 && - cond->family == AF_INET) { - if (addr[0] == 0 && addr[1] == 0 && - addr[2] == htonl(0xffff) && - bitstring_match(addr + 3, cond->addr, - cond->prefix_len)) - break; - } yes = 0; break; } @@ -509,6 +522,55 @@ static int valid_cc(const void *bc, int len, int cc) return 0; } +/* Validate an inet_diag_hostcond. */ +static bool valid_hostcond(const struct inet_diag_bc_op *op, int len, + int *min_len) +{ + int addr_len; + struct inet_diag_hostcond *cond; + + /* Check hostcond space. */ + *min_len += sizeof(struct inet_diag_hostcond); + if (len < *min_len) + return false; + cond = (struct inet_diag_hostcond *)(op + 1); + + /* Check address family and address length. */ + switch (cond->family) { + case AF_UNSPEC: + addr_len = 0; + break; + case AF_INET: + addr_len = sizeof(struct in_addr); + break; + case AF_INET6: + addr_len = sizeof(struct in6_addr); + break; + default: + return false; + } + *min_len += addr_len; + if (len < *min_len) + return false; + + /* Check prefix length (in bits) vs address length (in bytes). */ + if (cond->prefix_len > 8 * addr_len) + return false; + + return true; +} + +/* Validate a port comparison operator. */ +static inline bool valid_port_comparison(const struct inet_diag_bc_op *op, + int len, int *min_len) +{ + /* Port comparisons put the port in a follow-on inet_diag_bc_op. */ + *min_len += sizeof(struct inet_diag_bc_op); + if (len < *min_len) + return false; + return true; +} + static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) { const void *bc = bytecode; @@ -516,29 +578,39 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) while (len > 0) { const struct inet_diag_bc_op *op = bc; + int min_len = sizeof(struct inet_diag_bc_op); //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len); switch (op->code) { - case INET_DIAG_BC_AUTO: case INET_DIAG_BC_S_COND: case INET_DIAG_BC_D_COND: + if (!valid_hostcond(bc, len, &min_len)) + return -EINVAL; + break; case INET_DIAG_BC_S_GE: case INET_DIAG_BC_S_LE: case INET_DIAG_BC_D_GE: case INET_DIAG_BC_D_LE: - case INET_DIAG_BC_JMP: - if (op->no < 4 || op->no > len + 4 || op->no & 3) - return -EINVAL; - if (op->no < len && - !valid_cc(bytecode, bytecode_len, len - op->no)) + if (!valid_port_comparison(bc, len, &min_len)) return -EINVAL; break; + case INET_DIAG_BC_AUTO: + case INET_DIAG_BC_JMP: case INET_DIAG_BC_NOP: break; default: return -EINVAL; } - if (op->yes < 4 || op->yes > len + 4 || op->yes & 3) + + if (op->code != INET_DIAG_BC_NOP) { + if (op->no < min_len || op->no > len + 4 || op->no & 3) + return -EINVAL; + if (op->no < len && + !valid_cc(bytecode, bytecode_len, len - op->no)) + return -EINVAL; + } + + if (op->yes < min_len || op->yes > len + 4 || op->yes & 3) return -EINVAL; bc += op->yes; len -= op->yes; @@ -596,6 +668,36 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } +/* Get the IPv4, IPv6, or IPv4-mapped-IPv6 local and remote addresses + * from a request_sock. For IPv4-mapped-IPv6 we must map IPv4 to IPv6. + */ +static inline void inet_diag_req_addrs(const struct sock *sk, + const struct request_sock *req, + struct inet_diag_entry *entry) +{ + struct inet_request_sock *ireq = inet_rsk(req); + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + if (req->rsk_ops->family == AF_INET6) { + entry->saddr = inet6_rsk(req)->loc_addr.s6_addr32; + entry->daddr = inet6_rsk(req)->rmt_addr.s6_addr32; + } else if (req->rsk_ops->family == AF_INET) { + ipv6_addr_set_v4mapped(ireq->loc_addr, + &entry->saddr_storage); + ipv6_addr_set_v4mapped(ireq->rmt_addr, + &entry->daddr_storage); + entry->saddr = entry->saddr_storage.s6_addr32; + entry->daddr = entry->daddr_storage.s6_addr32; + } + } else +#endif + { + entry->saddr = &ireq->loc_addr; + entry->daddr = &ireq->rmt_addr; + } +} + static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, struct request_sock *req, struct user_namespace *user_ns, @@ -617,7 +719,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_family = sk->sk_family; r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; - r->idiag_retrans = req->retrans; + r->idiag_retrans = req->num_retrans; r->id.idiag_if = sk->sk_bound_dev_if; sock_diag_save_cookie(req, r->id.idiag_cookie); @@ -637,8 +739,10 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_inode = 0; #if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { - *(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr; - *(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr; + struct inet_diag_entry entry; + inet_diag_req_addrs(sk, req, &entry); + memcpy(r->id.idiag_src, entry.saddr, sizeof(struct in6_addr)); + memcpy(r->id.idiag_dst, entry.daddr, sizeof(struct in6_addr)); } #endif @@ -691,18 +795,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, continue; if (bc) { - entry.saddr = -#if IS_ENABLED(CONFIG_IPV6) - (entry.family == AF_INET6) ? - inet6_rsk(req)->loc_addr.s6_addr32 : -#endif - &ireq->loc_addr; - entry.daddr = -#if IS_ENABLED(CONFIG_IPV6) - (entry.family == AF_INET6) ? - inet6_rsk(req)->rmt_addr.s6_addr32 : -#endif - &ireq->rmt_addr; + inet_diag_req_addrs(sk, req, &entry); entry.dport = ntohs(ireq->rmt_port); if (!inet_diag_bc_run(bc, &entry)) @@ -892,13 +985,16 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct inet_diag_req_v2 *r, struct nlattr *bc) { const struct inet_diag_handler *handler; + int err = 0; handler = inet_diag_lock_handler(r->sdiag_protocol); if (!IS_ERR(handler)) handler->dump(skb, cb, r, bc); + else + err = PTR_ERR(handler); inet_diag_unlock_handler(handler); - return skb->len; + return err ? : skb->len; } static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7880af970208..fa3ae8148710 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -237,12 +237,14 @@ struct sock *__inet_lookup_established(struct net *net, rcu_read_lock(); begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (INET_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET_MATCH(sk, net, acookie, + saddr, daddr, ports, dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) goto begintw; - if (unlikely(!INET_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif))) { + if (unlikely(!INET_MATCH(sk, net, acookie, + saddr, daddr, ports, dif))) { sock_put(sk); goto begin; } @@ -260,14 +262,18 @@ begin: begintw: /* Must check for a TIME_WAIT'er before going to listener hash. */ sk_nulls_for_each_rcu(sk, node, &head->twchain) { - if (INET_TW_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET_TW_MATCH(sk, net, acookie, + saddr, daddr, ports, + dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { sk = NULL; goto out; } - if (unlikely(!INET_TW_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif))) { + if (unlikely(!INET_TW_MATCH(sk, net, acookie, + saddr, daddr, ports, + dif))) { sock_put(sk); goto begintw; } @@ -314,10 +320,12 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, /* Check TIME-WAIT sockets first. */ sk_nulls_for_each(sk2, node, &head->twchain) { - tw = inet_twsk(sk2); + if (sk2->sk_hash != hash) + continue; - if (INET_TW_MATCH(sk2, net, hash, acookie, - saddr, daddr, ports, dif)) { + if (likely(INET_TW_MATCH(sk2, net, acookie, + saddr, daddr, ports, dif))) { + tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) goto unique; else @@ -328,8 +336,10 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, /* And established part... */ sk_nulls_for_each(sk2, node, &head->chain) { - if (INET_MATCH(sk2, net, hash, acookie, - saddr, daddr, ports, dif)) + if (sk2->sk_hash != hash) + continue; + if (likely(INET_MATCH(sk2, net, acookie, + saddr, daddr, ports, dif))) goto not_unique; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 448e68546827..eb9d63a570cd 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -707,28 +707,27 @@ EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) { - const struct iphdr *iph; + struct iphdr iph; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) + if (!skb_copy_bits(skb, 0, &iph, sizeof(iph))) return skb; - iph = ip_hdr(skb); - if (iph->ihl < 5 || iph->version != 4) + if (iph.ihl < 5 || iph.version != 4) return skb; - if (!pskb_may_pull(skb, iph->ihl*4)) - return skb; - iph = ip_hdr(skb); - len = ntohs(iph->tot_len); - if (skb->len < len || len < (iph->ihl * 4)) + + len = ntohs(iph.tot_len); + if (skb->len < len || len < (iph.ihl * 4)) return skb; - if (ip_is_fragment(ip_hdr(skb))) { + if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { + if (!pskb_may_pull(skb, iph.ihl*4)) + return skb; if (pskb_trim_rcsum(skb, len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); @@ -802,6 +801,10 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table[0].data = &net->ipv4.frags.high_thresh; table[1].data = &net->ipv4.frags.low_thresh; table[2].data = &net->ipv4.frags.timeout; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7240f8e2dd45..e81b1caf2ea2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -164,21 +164,6 @@ struct ipgre_net { #define tunnels_r tunnels[2] #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -250,7 +235,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, ARPHRD_ETHER : ARPHRD_IPGRE; int score, cand_score = 4; - for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) @@ -277,7 +262,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) { if (remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) continue; @@ -303,7 +288,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) { if ((local != t->parms.iph.saddr && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) || @@ -331,7 +316,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) { if (t->parms.i_key != key || !(t->dev->flags & IFF_UP)) continue; @@ -753,7 +738,6 @@ drop: static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; const struct iphdr *old_iph = ip_hdr(skb); const struct iphdr *tiph; struct flowi4 fl4; @@ -766,6 +750,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev int gre_hlen; __be32 dst; int mtu; + u8 ttl; if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) @@ -776,7 +761,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (dev->header_ops && dev->type == ARPHRD_IPGRE) { gre_hlen = 0; - tiph = (const struct iphdr *)skb->data; + if (skb->protocol == htons(ETH_P_IP)) + tiph = (const struct iphdr *)skb->data; + else + tiph = &tunnel->parms.iph; } else { gre_hlen = tunnel->hlen; tiph = &tunnel->parms.iph; @@ -828,6 +816,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } + ttl = tiph->ttl; tos = tiph->tos; if (tos == 1) { tos = 0; @@ -920,11 +909,12 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev dev_kfree_skb(skb); skb = new_skb; old_iph = ip_hdr(skb); + /* Warning : tiph value might point to freed memory */ } - skb_reset_transport_header(skb); skb_push(skb, gre_hlen); skb_reset_network_header(skb); + skb_set_transport_header(skb, sizeof(*iph)); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); @@ -943,8 +933,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb); iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; + iph->ttl = ttl; - if ((iph->ttl = tiph->ttl) == 0) { + if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) @@ -972,14 +963,16 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev ptr--; } if (tunnel->parms.o_flags&GRE_CSUM) { + int offset = skb_transport_offset(skb); + *ptr = 0; - *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, + skb->len - offset, + 0)); } } - nf_reset(skb); - tstats = this_cpu_ptr(dev->tstats); - __IPTUNNEL_XMIT(tstats, &dev->stats); + iptunnel_xmit(skb, dev); return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_IPV6) @@ -1082,7 +1075,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1157,7 +1150,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ign->fb_tunnel_dev) { diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 1dc01f9793d5..f6289bf6f332 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -409,7 +409,7 @@ int ip_options_compile(struct net *net, optptr[2] += 8; break; default: - if (!skb && !capable(CAP_NET_RAW)) { + if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr + 3; goto error; } @@ -445,7 +445,7 @@ int ip_options_compile(struct net *net, opt->router_alert = optptr - iph; break; case IPOPT_CIPSO: - if ((!skb && !capable(CAP_NET_RAW)) || opt->cipso) { + if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) { pp_ptr = optptr; goto error; } @@ -458,7 +458,7 @@ int ip_options_compile(struct net *net, case IPOPT_SEC: case IPOPT_SID: default: - if (!skb && !capable(CAP_NET_RAW)) { + if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr; goto error; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6537a408a4fb..3e98ed2bff55 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -595,6 +595,10 @@ slow_path_clean: } slow_path: + /* for offloaded checksums cleanup checksum before fragmentation */ + if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb)) + goto fail; + left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5eea4a811042..d9c4f113d709 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -457,19 +457,28 @@ static int do_ip_setsockopt(struct sock *sk, int level, struct inet_sock *inet = inet_sk(sk); int val = 0, err; - if (((1<<optname) & ((1<<IP_PKTINFO) | (1<<IP_RECVTTL) | - (1<<IP_RECVOPTS) | (1<<IP_RECVTOS) | - (1<<IP_RETOPTS) | (1<<IP_TOS) | - (1<<IP_TTL) | (1<<IP_HDRINCL) | - (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) | - (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | - (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) | - (1<<IP_MINTTL) | (1<<IP_NODEFRAG))) || - optname == IP_UNICAST_IF || - optname == IP_MULTICAST_TTL || - optname == IP_MULTICAST_ALL || - optname == IP_MULTICAST_LOOP || - optname == IP_RECVORIGDSTADDR) { + switch (optname) { + case IP_PKTINFO: + case IP_RECVTTL: + case IP_RECVOPTS: + case IP_RECVTOS: + case IP_RETOPTS: + case IP_TOS: + case IP_TTL: + case IP_HDRINCL: + case IP_MTU_DISCOVER: + case IP_RECVERR: + case IP_ROUTER_ALERT: + case IP_FREEBIND: + case IP_PASSSEC: + case IP_TRANSPARENT: + case IP_MINTTL: + case IP_NODEFRAG: + case IP_UNICAST_IF: + case IP_MULTICAST_TTL: + case IP_MULTICAST_ALL: + case IP_MULTICAST_LOOP: + case IP_RECVORIGDSTADDR: if (optlen >= sizeof(int)) { if (get_user(val, (int __user *) optval)) return -EFAULT; @@ -581,7 +590,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_TTL: if (optlen < 1) goto e_inval; - if (val != -1 && (val < 0 || val > 255)) + if (val != -1 && (val < 1 || val > 255)) goto e_inval; inet->uc_ttl = val; break; @@ -980,13 +989,14 @@ mc_msf_out: case IP_IPSEC_POLICY: case IP_XFRM_POLICY: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) break; err = xfrm_user_policy(sk, optname, optval, optlen); break; case IP_TRANSPARENT: - if (!!val && !capable(CAP_NET_RAW) && !capable(CAP_NET_ADMIN)) { + if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { err = -EPERM; break; } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1831092f999f..c3a4233c0ac2 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -66,20 +66,6 @@ static void vti_tunnel_setup(struct net_device *dev); static void vti_dev_free(struct net_device *dev); static int vti_tunnel_bind_dev(struct net_device *dev); -/* Locking : hash tables are protected by RCU and RTNL */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; - #define VTI_XMIT(stats1, stats2) do { \ int err; \ int pkt_len = skb->len; \ @@ -142,19 +128,19 @@ static struct ip_tunnel *vti_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct vti_net *ipn = net_generic(net, vti_net_id); - for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1]) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0]) if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1]) if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_wc[0]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_wc[0]) if (t && (t->dev->flags&IFF_UP)) return t; return NULL; @@ -338,12 +324,17 @@ static int vti_rcv(struct sk_buff *skb) if (tunnel != NULL) { struct pcpu_tstats *tstats; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + return -1; + tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); + skb->mark = 0; + secpath_reset(skb); skb->dev = tunnel->dev; return 1; } @@ -497,7 +488,7 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -562,7 +553,7 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ipn->fb_tunnel_dev) { diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index d3ab47e19a89..9a46daed2f3c 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -47,9 +47,12 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 798358b10717..a2e50ae80b53 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -136,6 +136,8 @@ __be32 ic_myaddr = NONE; /* My IP address */ static __be32 ic_netmask = NONE; /* Netmask for local subnet */ __be32 ic_gateway = NONE; /* Gateway IP address */ +__be32 ic_addrservaddr = NONE; /* IP Address of the IP addresses'server */ + __be32 ic_servaddr = NONE; /* Boot server IP address */ __be32 root_server_addr = NONE; /* Address of NFS server */ @@ -558,6 +560,7 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (ic_myaddr == NONE) ic_myaddr = tip; ic_servaddr = sip; + ic_addrservaddr = sip; ic_got_reply = IC_RARP; drop_unlock: @@ -1068,7 +1071,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str ic_servaddr = server_id; #ifdef IPCONFIG_DEBUG printk("DHCP: Offered address %pI4 by server %pI4\n", - &ic_myaddr, &ic_servaddr); + &ic_myaddr, &b->iph.saddr); #endif /* The DHCP indicated server address takes * precedence over the bootp header one if @@ -1113,6 +1116,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str ic_dev = dev; ic_myaddr = b->your_ip; ic_servaddr = b->server_ip; + ic_addrservaddr = b->iph.saddr; if (ic_gateway == NONE && b->relay_ip) ic_gateway = b->relay_ip; if (ic_nameservers[0] == NONE) @@ -1268,7 +1272,7 @@ static int __init ic_dynamic(void) printk("IP-Config: Got %s answer from %pI4, ", ((ic_got_reply & IC_RARP) ? "RARP" : (ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP"), - &ic_servaddr); + &ic_addrservaddr); pr_cont("my address is %pI4\n", &ic_myaddr); return 0; @@ -1500,8 +1504,10 @@ static int __init ip_auto_config(void) * Clue in the operator. */ pr_info("IP-Config: Complete:\n"); - pr_info(" device=%s, addr=%pI4, mask=%pI4, gw=%pI4\n", - ic_dev->name, &ic_myaddr, &ic_netmask, &ic_gateway); + + pr_info(" device=%s, hwaddr=%*phC, ipaddr=%pI4, mask=%pI4, gw=%pI4\n", + ic_dev->name, ic_dev->addr_len, ic_dev->dev_addr, + &ic_myaddr, &ic_netmask, &ic_gateway); pr_info(" host=%s, domain=%s, nis-domain=%s\n", utsname()->nodename, ic_domain, utsname()->domainname); pr_info(" bootserver=%pI4, rootserver=%pI4, rootpath=%s", diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index e15b45297c09..191fc24a745a 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -138,22 +138,7 @@ struct ipip_net { static int ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); static void ipip_dev_free(struct net_device *dev); - -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; +static struct rtnl_link_ops ipip_link_ops __read_mostly; static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -197,16 +182,16 @@ static struct ip_tunnel *ipip_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct ipip_net *ipn = net_generic(net, ipip_net_id); - for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1]) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0]) if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1]) if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) return t; @@ -264,6 +249,32 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) rcu_assign_pointer(*tp, t); } +static int ipip_tunnel_create(struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ipip_net *ipn = net_generic(net, ipip_net_id); + int err; + + err = ipip_tunnel_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &ipip_link_ops; + + dev_hold(dev); + ipip_tunnel_link(ipn, t); + return 0; + +out: + return err; +} + static struct ip_tunnel *ipip_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { @@ -298,16 +309,9 @@ static struct ip_tunnel *ipip_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - if (ipip_tunnel_init(dev) < 0) + if (ipip_tunnel_create(dev) < 0) goto failed_free; - if (register_netdevice(dev) < 0) - goto failed_free; - - strcpy(nt->parms.name, dev->name); - - dev_hold(dev); - ipip_tunnel_link(ipn, nt); return nt; failed_free: @@ -463,7 +467,6 @@ drop: static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; const struct iphdr *tiph = &tunnel->parms.iph; u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; @@ -479,6 +482,10 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->protocol != htons(ETH_P_IP)) goto tx_error; + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + goto tx_error; + if (tos & 1) tos = old_iph->tos; @@ -586,9 +593,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if ((iph->ttl = tiph->ttl) == 0) iph->ttl = old_iph->ttl; - nf_reset(skb); - tstats = this_cpu_ptr(dev->tstats); - __IPTUNNEL_XMIT(tstats, &dev->stats); + iptunnel_xmit(skb, dev); return NETDEV_TX_OK; tx_error_icmp: @@ -635,6 +640,28 @@ static void ipip_tunnel_bind_dev(struct net_device *dev) dev->iflink = tunnel->parms.link; } +static void ipip_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) +{ + struct net *net = dev_net(t->dev); + struct ipip_net *ipn = net_generic(net, ipip_net_id); + + ipip_tunnel_unlink(ipn, t); + synchronize_net(); + t->parms.iph.saddr = p->iph.saddr; + t->parms.iph.daddr = p->iph.daddr; + memcpy(t->dev->dev_addr, &p->iph.saddr, 4); + memcpy(t->dev->broadcast, &p->iph.daddr, 4); + ipip_tunnel_link(ipn, t); + t->parms.iph.ttl = p->iph.ttl; + t->parms.iph.tos = p->iph.tos; + t->parms.iph.frag_off = p->iph.frag_off; + if (t->parms.link != p->link) { + t->parms.link = p->link; + ipip_tunnel_bind_dev(t->dev); + } + netdev_state_change(t->dev); +} + static int ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -664,7 +691,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -693,29 +720,13 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } t = netdev_priv(dev); - ipip_tunnel_unlink(ipn, t); - synchronize_net(); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - ipip_tunnel_link(ipn, t); - netdev_state_change(dev); } + + ipip_tunnel_update(t, &p); } if (t) { err = 0; - if (cmd == SIOCCHGTUNNEL) { - t->parms.iph.ttl = p.iph.ttl; - t->parms.iph.tos = p.iph.tos; - t->parms.iph.frag_off = p.iph.frag_off; - if (t->parms.link != p.link) { - t->parms.link = p.link; - ipip_tunnel_bind_dev(dev); - netdev_state_change(dev); - } - } if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p))) err = -EFAULT; } else @@ -724,7 +735,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ipn->fb_tunnel_dev) { @@ -773,6 +784,11 @@ static void ipip_dev_free(struct net_device *dev) free_netdev(dev); } +#define IPIP_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_HW_CSUM) + static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; @@ -787,6 +803,9 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + + dev->features |= IPIP_FEATURES; + dev->hw_features |= IPIP_FEATURES; } static int ipip_tunnel_init(struct net_device *dev) @@ -829,6 +848,142 @@ static int __net_init ipip_fb_tunnel_init(struct net_device *dev) return 0; } +static void ipip_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.version = 4; + parms->iph.protocol = IPPROTO_IPIP; + parms->iph.ihl = 5; + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); + + if (data[IFLA_IPTUN_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); + + if (data[IFLA_IPTUN_TTL]) { + parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); + if (parms->iph.ttl) + parms->iph.frag_off = htons(IP_DF); + } + + if (data[IFLA_IPTUN_TOS]) + parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); + + if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) + parms->iph.frag_off = htons(IP_DF); +} + +static int ipip_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip_tunnel *nt; + + nt = netdev_priv(dev); + ipip_netlink_parms(data, &nt->parms); + + if (ipip_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + return ipip_tunnel_create(dev); +} + +static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip_tunnel *t; + struct ip_tunnel_parm p; + struct net *net = dev_net(dev); + struct ipip_net *ipn = net_generic(net, ipip_net_id); + + if (dev == ipn->fb_tunnel_dev) + return -EINVAL; + + ipip_netlink_parms(data, &p); + + if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || + (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) + return -EINVAL; + + t = ipip_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + ipip_tunnel_update(t, &p); + return 0; +} + +static size_t ipip_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(4) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(4) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_TOS */ + nla_total_size(1) + + /* IFLA_IPTUN_PMTUDISC */ + nla_total_size(1) + + 0; +} + +static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct ip_tunnel_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || + nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || + nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, + !!(parm->iph.frag_off & htons(IP_DF)))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, + [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, + [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, +}; + +static struct rtnl_link_ops ipip_link_ops __read_mostly = { + .kind = "ipip", + .maxtype = IFLA_IPTUN_MAX, + .policy = ipip_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = ipip_tunnel_setup, + .newlink = ipip_newlink, + .changelink = ipip_changelink, + .get_size = ipip_get_size, + .fill_info = ipip_fill_info, +}; + static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip_err, @@ -925,14 +1080,26 @@ static int __init ipip_init(void) return err; err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { - unregister_pernet_device(&ipip_net_ops); pr_info("%s: can't register tunnel\n", __func__); + goto xfrm_tunnel_failed; } + err = rtnl_link_register(&ipip_link_ops); + if (err < 0) + goto rtnl_link_failed; + +out: return err; + +rtnl_link_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel_failed: + unregister_pernet_device(&ipip_net_ops); + goto out; } static void __exit ipip_fini(void) { + rtnl_link_unregister(&ipip_link_ops); if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) pr_info("%s: can't deregister tunnel\n", __func__); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 6168c4dc58b1..a9454cbd953c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -65,6 +65,7 @@ #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> +#include <linux/netconf.h> #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) #define CONFIG_IP_PIMSM 1 @@ -83,8 +84,8 @@ struct mr_table { struct vif_device vif_table[MAXVIFS]; int maxvif; atomic_t cache_resolve_queue_len; - int mroute_do_assert; - int mroute_do_pim; + bool mroute_do_assert; + bool mroute_do_pim; #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) int mroute_reg_vif_num; #endif @@ -133,6 +134,8 @@ static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); +static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, + int cmd); static void mroute_clean_tables(struct mr_table *mrt); static void ipmr_expire_process(unsigned long arg); @@ -582,6 +585,9 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; + inet_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); } @@ -665,6 +671,7 @@ static void ipmr_expire_process(unsigned long arg) } list_del(&c->list); + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_destroy_unres(mrt, c); } @@ -772,6 +779,8 @@ static int vif_add(struct net *net, struct mr_table *mrt, return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; + inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex, + &in_dev->cnf); ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ @@ -1020,6 +1029,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->list, &mrt->mfc_unres_queue); + mroute_netlink_event(mrt, c, RTM_NEWROUTE); if (atomic_read(&mrt->cache_resolve_queue_len) == 1) mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); @@ -1054,7 +1064,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { list_del_rcu(&c->list); - + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); return 0; } @@ -1089,6 +1099,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1131,6 +1142,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } + mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1159,6 +1171,7 @@ static void mroute_clean_tables(struct mr_table *mrt) if (c->mfc_flags & MFC_STATIC) continue; list_del_rcu(&c->list); + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); } } @@ -1167,6 +1180,7 @@ static void mroute_clean_tables(struct mr_table *mrt) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { list_del(&c->list); + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); @@ -1185,6 +1199,9 @@ static void mrtsock_destruct(struct sock *sk) ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; + inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all); RCU_INIT_POINTER(mrt->mroute_sk, NULL); mroute_clean_tables(mrt); } @@ -1207,23 +1224,24 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi struct net *net = sock_net(sk); struct mr_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_IGMP) + return -EOPNOTSUPP; + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (mrt == NULL) return -ENOENT; if (optname != MRT_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && - !capable(CAP_NET_ADMIN)) + !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } switch (optname) { case MRT_INIT: - if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->inet_num != IPPROTO_IGMP) - return -EOPNOTSUPP; if (optlen != sizeof(int)) - return -ENOPROTOOPT; + return -EINVAL; rtnl_lock(); if (rtnl_dereference(mrt->mroute_sk)) { @@ -1235,6 +1253,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi if (ret == 0) { rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; + inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all); } rtnl_unlock(); return ret; @@ -1284,9 +1305,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi case MRT_ASSERT: { int v; + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; - mrt->mroute_do_assert = (v) ? 1 : 0; + mrt->mroute_do_assert = v; return 0; } #ifdef CONFIG_IP_PIMSM @@ -1294,9 +1317,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi { int v; + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; - v = (v) ? 1 : 0; + v = !!v; rtnl_lock(); ret = 0; @@ -1318,6 +1343,10 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi if (get_user(v, (u32 __user *)optval)) return -EFAULT; + /* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */ + if (v != RT_TABLE_DEFAULT && v >= 1000000000) + return -EINVAL; + rtnl_lock(); ret = 0; if (sk == rtnl_dereference(mrt->mroute_sk)) { @@ -1325,7 +1354,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi } else { if (!ipmr_new_table(net, v)) ret = -ENOMEM; - raw_sk(sk)->ipmr_table = v; + else + raw_sk(sk)->ipmr_table = v; } rtnl_unlock(); return ret; @@ -1351,6 +1381,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int struct net *net = sock_net(sk); struct mr_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_IGMP) + return -EOPNOTSUPP; + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (mrt == NULL) return -ENOENT; @@ -2020,6 +2054,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, int ct; struct rtnexthop *nhp; struct nlattr *mp_attr; + struct rta_mfc_stats mfcs; /* If cache is unresolved, don't try to parse IIF and OIF */ if (c->mfc_parent >= MAXVIFS) @@ -2048,6 +2083,12 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, nla_nest_end(skb, mp_attr); + mfcs.mfcs_packets = c->mfc_un.res.pkt; + mfcs.mfcs_bytes = c->mfc_un.res.bytes; + mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0) + return -EMSGSIZE; + rtm->rtm_type = RTN_MULTICAST; return 1; } @@ -2117,12 +2158,13 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc_cache *c) + u32 portid, u32 seq, struct mfc_cache *c, int cmd) { struct nlmsghdr *nlh; struct rtmsg *rtm; + int err; - nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); if (nlh == NULL) return -EMSGSIZE; @@ -2136,13 +2178,18 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - rtm->rtm_protocol = RTPROT_UNSPEC; + if (c->mfc_flags & MFC_STATIC) + rtm->rtm_protocol = RTPROT_STATIC; + else + rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) || nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; - if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0) + err = __ipmr_fill_mroute(mrt, skb, c, rtm); + /* do not break the dump if cache is unresolved */ + if (err < 0 && err != -ENOENT) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2152,6 +2199,52 @@ nla_put_failure: return -EMSGSIZE; } +static size_t mroute_msgsize(bool unresolved, int maxvif) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(4) /* RTA_TABLE */ + + nla_total_size(4) /* RTA_SRC */ + + nla_total_size(4) /* RTA_DST */ + ; + + if (!unresolved) + len = len + + nla_total_size(4) /* RTA_IIF */ + + nla_total_size(0) /* RTA_MULTIPATH */ + + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) + /* RTA_MFC_STATS */ + + nla_total_size(sizeof(struct rta_mfc_stats)) + ; + + return len; +} + +static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, + int cmd) +{ + struct net *net = read_pnet(&mrt->net); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif), + GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + if (err < 0) + goto errout; + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE, NULL, GFP_ATOMIC); + return; + +errout: + kfree_skb(skb); + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); +} + static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2178,13 +2271,29 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc) < 0) + mfc, RTM_NEWROUTE) < 0) goto done; next_entry: e++; } e = s_e = 0; } + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { + if (e < s_e) + goto next_entry2; + if (ipmr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + mfc, RTM_NEWROUTE) < 0) { + spin_unlock_bh(&mfc_unres_lock); + goto done; + } +next_entry2: + e++; + } + spin_unlock_bh(&mfc_unres_lock); + e = s_e = 0; s_h = 0; next_table: t++; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 97e61eadf580..3ea4127404d6 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1533,7 +1533,7 @@ static int compat_do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1677,7 +1677,7 @@ static int compat_do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1698,7 +1698,7 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1722,7 +1722,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 170b1fdd6b72..17c5e06da662 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1846,7 +1846,7 @@ compat_do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1961,7 +1961,7 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1983,7 +1983,7 @@ do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -2008,7 +2008,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index fe5daea5214d..75e33a7048f8 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -661,6 +661,7 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input, #define PROC_WRITELEN 10 char buffer[PROC_WRITELEN+1]; unsigned long nodenum; + int rc; if (size > PROC_WRITELEN) return -EIO; @@ -669,11 +670,15 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input, buffer[size] = 0; if (*buffer == '+') { - nodenum = simple_strtoul(buffer+1, NULL, 10); + rc = kstrtoul(buffer+1, 10, &nodenum); + if (rc) + return rc; if (clusterip_add_node(c, nodenum)) return -ENOMEM; } else if (*buffer == '-') { - nodenum = simple_strtoul(buffer+1, NULL,10); + rc = kstrtoul(buffer+1, 10, &nodenum); + if (rc) + return rc; if (clusterip_del_node(c, nodenum)) return -ENOENT; } else diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 51f13f8ec724..04b18c1ac345 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -81,6 +81,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) niph->saddr = oiph->daddr; niph->daddr = oiph->saddr; + skb_reset_transport_header(nskb); tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); memset(tcph, 0, sizeof(*tcph)); tcph->source = oth->dest; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 9e0ffaf1d942..eeaff7e4acb5 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -124,19 +124,28 @@ nf_nat_ipv4_fn(unsigned int hooknum, ret = nf_nat_rule_find(skb, hooknum, in, out, ct); if (ret != NF_ACCEPT) return ret; - } else + } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; + } break; default: /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; } return nf_nat_packet(ct, ctinfo, hooknum, skb); + +oif_changed: + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; } static unsigned int @@ -184,7 +193,8 @@ nf_nat_ipv4_out(unsigned int hooknum, if ((ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) || - (ct->tuplehash[dir].tuple.src.u.all != + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && + ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) if (nf_xfrm_me_harder(skb, AF_INET) < 0) ret = NF_DROP; @@ -221,6 +231,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum, } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) if (nf_xfrm_me_harder(skb, AF_INET) < 0) @@ -274,9 +285,7 @@ static int __net_init iptable_nat_net_init(struct net *net) return -ENOMEM; net->ipv4.nat_table = ipt_register_table(net, &nf_nat_ipv4_table, repl); kfree(repl); - if (IS_ERR(net->ipv4.nat_table)) - return PTR_ERR(net->ipv4.nat_table); - return 0; + return PTR_RET(net->ipv4.nat_table); } static void __net_exit iptable_nat_net_exit(struct net *net) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8f3d05424a3e..6f9c07268cf6 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -738,6 +738,7 @@ struct proto ping_prot = { .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = ping_v4_hash, .unhash = ping_v4_unhash, .get_port = ping_v4_get_port, diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 8918eff1426d..0f9d09f54bd9 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -29,6 +29,7 @@ #include <net/protocol.h> const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; +const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; /* * Add a protocol handler to the hash tables @@ -41,6 +42,13 @@ int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) } EXPORT_SYMBOL(inet_add_protocol); +int inet_add_offload(const struct net_offload *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_offload **)&inet_offloads[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet_add_offload); + /* * Remove a protocol from the hash tables. */ @@ -57,3 +65,16 @@ int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol) return ret; } EXPORT_SYMBOL(inet_del_protocol); + +int inet_del_offload(const struct net_offload *prot, unsigned char protocol) +{ + int ret; + + ret = (cmpxchg((const struct net_offload **)&inet_offloads[protocol], + prot, NULL) == prot) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet_del_offload); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 73d1e4df4bf6..6f08991409c3 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -894,6 +894,7 @@ struct proto raw_prot = { .recvmsg = raw_recvmsg, .bind = raw_bind, .backlog_rcv = raw_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw_sock), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a8c651216fa6..a0fcc47fee73 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -912,6 +912,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct dst_entry *dst = &rt->dst; struct fib_result res; + if (dst_metric_locked(dst, RTAX_MTU)) + return; + if (dst->dev->mtu < mtu) return; @@ -962,7 +965,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); -void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; @@ -975,6 +978,53 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) ip_rt_put(rt); } } + +void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; + struct dst_entry *dst; + bool new = false; + + bh_lock_sock(sk); + rt = (struct rtable *) __sk_dst_get(sk); + + if (sock_owned_by_user(sk) || !rt) { + __ipv4_sk_update_pmtu(skb, sk, mtu); + goto out; + } + + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + + if (!__sk_dst_check(sk, 0)) { + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); + + dst = dst_check(&rt->dst, 0); + if (!dst) { + if (new) + dst_release(&rt->dst); + + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + if (new) + __sk_dst_set(sk, &rt->dst); + +out: + bh_unlock_sock(sk); +} EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, @@ -1120,7 +1170,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) if (!mtu || time_after_eq(jiffies, rt->dst.expires)) mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu && rt_is_output_route(rt)) + if (mtu) return mtu; mtu = dst->dev->mtu; @@ -1785,6 +1835,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; + do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; @@ -1793,6 +1844,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; + else + do_cache = false; /* If multicast route do not exist use * default one, but do not gateway in this case. * Yes, it is hack. @@ -1802,8 +1855,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, } fnhe = NULL; - do_cache = fi != NULL; - if (fi) { + do_cache &= fi != NULL; + if (do_cache) { struct rtable __rcu **prth; struct fib_nh *nh = &FIB_RES_NH(*res); @@ -2229,8 +2282,27 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, error = rt->dst.error; if (rt_is_input_route(rt)) { - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) - goto nla_put_failure; +#ifdef CONFIG_IP_MROUTE + if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && + IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { + int err = ipmr_get_route(net, skb, + fl4->saddr, fl4->daddr, + r, nowait); + if (err <= 0) { + if (!nowait) { + if (err == 0) + return 0; + goto nla_put_failure; + } else { + if (err == -EMSGSIZE) + goto nla_put_failure; + error = err; + } + } + } else +#endif + if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + goto nla_put_failure; } if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) @@ -2493,6 +2565,10 @@ static __net_init int sysctl_route_net_init(struct net *net) tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + tbl[0].procname = NULL; } tbl[0].extra1 = net; @@ -2597,7 +2673,7 @@ int __init ip_rt_init(void) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); - xfrm4_init(ip_rt_max_size); + xfrm4_init(); #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index ba48e799b031..b236ef04914f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -340,7 +340,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, } req->expires = 0UL; - req->retrans = 0; + req->num_retrans = 0; /* * We need to lookup the route here to get at the correct diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 63d4eccc674d..d84400b65049 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -883,6 +883,9 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[6].data = &net->ipv4.sysctl_ping_group_range; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } /* diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 197c0008503c..2aa69c8ae60c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -536,13 +536,14 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct tcp_sock *tp = tcp_sk(sk); int answ; + bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; - lock_sock(sk); + slow = lock_sock_fast(sk); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else if (sock_flag(sk, SOCK_URGINLINE) || @@ -557,7 +558,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) answ--; } else answ = tp->urg_seq - tp->copied_seq; - release_sock(sk); + unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = tp->urg_data && tp->urg_seq == tp->copied_seq; @@ -830,8 +831,8 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset, - size_t psize, int flags) +static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, + size_t size, int flags) { struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; @@ -858,12 +859,9 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; - while (psize > 0) { + while (size > 0) { struct sk_buff *skb = tcp_write_queue_tail(sk); - struct page *page = pages[poffset / PAGE_SIZE]; int copy, i; - int offset = poffset % PAGE_SIZE; - int size = min_t(size_t, psize, PAGE_SIZE - offset); bool can_coalesce; if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) { @@ -912,8 +910,8 @@ new_segment: TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; copied += copy; - poffset += copy; - if (!(psize -= copy)) + offset += copy; + if (!(size -= copy)) goto out; if (skb->len < size_goal || (flags & MSG_OOB)) @@ -960,7 +958,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, flags); lock_sock(sk); - res = do_tcp_sendpages(sk, &page, offset, size, flags); + res = do_tcp_sendpages(sk, page, offset, size, flags); release_sock(sk); return res; } @@ -1212,7 +1210,7 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - if (copied && likely(!tp->repair)) + if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) @@ -1223,7 +1221,7 @@ wait_for_memory: } out: - if (copied && likely(!tp->repair)) + if (copied) tcp_push(sk, flags, mss_now, tp->nonagle); release_sock(sk); return copied + copied_syn; @@ -1430,12 +1428,12 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) } #endif -static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) +static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; - skb_queue_walk(&sk->sk_receive_queue, skb) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (tcp_hdr(skb)->syn) offset--; @@ -1443,6 +1441,11 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) *off = offset; return skb; } + /* This looks weird, but this can happen if TCP collapsing + * splitted a fat GRO packet, while we released socket lock + * in skb_splice_bits() + */ + sk_eat_skb(sk, skb, false); } return NULL; } @@ -1484,7 +1487,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, break; } used = recv_actor(desc, skb, offset, len); - if (used < 0) { + if (used <= 0) { if (!copied) copied = used; break; @@ -1493,15 +1496,19 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, copied += used; offset += used; } - /* - * If recv_actor drops the lock (e.g. TCP splice + /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ - skb = tcp_recv_skb(sk, seq-1, &offset); - if (!skb || (offset+1 != skb->len)) + skb = tcp_recv_skb(sk, seq - 1, &offset); + if (!skb) break; + /* TCP coalescing might have appended data to the skb. + * Try to splice more frags + */ + if (offset + 1 != skb->len) + continue; } if (tcp_hdr(skb)->fin) { sk_eat_skb(sk, skb, false); @@ -1518,8 +1525,10 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) + if (copied > 0) { + tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); + } return copied; } EXPORT_SYMBOL(tcp_read_sock); @@ -2303,7 +2312,7 @@ void tcp_sock_destruct(struct sock *sk) static inline bool tcp_can_repair_sock(const struct sock *sk) { - return capable(CAP_NET_ADMIN) && + return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED)); } @@ -3589,8 +3598,7 @@ void __init tcp_init(void) alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, - (totalram_pages >= 128 * 1024) ? - 13 : 15, + 17, /* one slot per 128 KB of memory */ 0, NULL, &tcp_hashinfo.ehash_mask, @@ -3606,8 +3614,7 @@ void __init tcp_init(void) alloc_large_system_hash("TCP bind", sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, - (totalram_pages >= 128 * 1024) ? - 13 : 15, + 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 701a7f6fb9b1..291f2ed7cc31 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -259,7 +259,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) if (!ca) err = -ENOENT; - else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || capable(CAP_NET_ADMIN))) + else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) err = -EPERM; else if (!try_module_get(ca->owner)) diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 813b43a76fec..834857f3c871 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -313,11 +313,13 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, .tcpv_rttcnt = ca->cnt_rtt, .tcpv_minrtt = ca->base_rtt, }; - u64 t = ca->sum_rtt; - do_div(t, ca->cnt_rtt); - info.tcpv_rtt = t; + if (info.tcpv_rttcnt > 0) { + u64 t = ca->sum_rtt; + do_div(t, info.tcpv_rttcnt); + info.tcpv_rtt = t; + } nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); } } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1db663983587..18f97ca76b00 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3552,6 +3552,24 @@ static bool tcp_process_frto(struct sock *sk, int flag) return false; } +/* RFC 5961 7 [ACK Throttling] */ +static void tcp_send_challenge_ack(struct sock *sk) +{ + /* unprotected vars, we dont care of overwrites */ + static u32 challenge_timestamp; + static unsigned int challenge_count; + u32 now = jiffies / HZ; + + if (now != challenge_timestamp) { + challenge_timestamp = now; + challenge_count = 0; + } + if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + tcp_send_ack(sk); + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3571,8 +3589,14 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* If the ack is older than previous acks * then we can probably ignore it. */ - if (before(ack, prior_snd_una)) + if (before(ack, prior_snd_una)) { + /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ + if (before(ack, prior_snd_una - tp->max_window)) { + tcp_send_challenge_ack(sk); + return -1; + } goto old_ack; + } /* If the ack includes data we haven't sent yet, discard * this segment (RFC793 Section 3.9). @@ -4529,6 +4553,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) struct tcphdr *th; bool fragstolen; + if (size == 0) + return 0; + skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); if (!skb) goto err; @@ -5241,23 +5268,6 @@ out: } #endif /* CONFIG_NET_DMA */ -static void tcp_send_challenge_ack(struct sock *sk) -{ - /* unprotected vars, we dont care of overwrites */ - static u32 challenge_timestamp; - static unsigned int challenge_count; - u32 now = jiffies / HZ; - - if (now != challenge_timestamp) { - challenge_timestamp = now; - challenge_count = 0; - } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); - tcp_send_ack(sk); - } -} - /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ @@ -5310,11 +5320,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, goto discard; } - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 3: check security and precedence [ignored] */ /* step 4: Check for a SYN @@ -5538,6 +5543,9 @@ slow_path: if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb)) goto csum_error; + if (!th->ack && !th->rst) + goto discard; + /* * Standard slow path. */ @@ -5546,9 +5554,14 @@ slow_path: return 0; step5: - if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) + if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) goto discard; + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -5642,7 +5655,11 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); if (data) { /* Retransmit unacked data in SYN */ - tcp_retransmit_skb(sk, data); + tcp_for_write_queue_from(data, sk) { + if (data == tcp_send_head(sk) || + __tcp_retransmit_skb(sk, data)) + break; + } tcp_rearm_rto(sk); return true; } @@ -5970,11 +5987,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (tcp_check_req(sk, skb, req, NULL, true) == NULL) goto discard; } + + if (!th->ack && !th->rst) + goto discard; + if (!tcp_validate_incoming(sk, skb, th, 0)) return 0; /* step 5: check the ACK field */ - if (th->ack) { + if (true) { int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0; switch (sk->sk_state) { @@ -5985,7 +6006,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, */ if (req) { tcp_synack_rtt_meas(sk, req); - tp->total_retrans = req->retrans; + tp->total_retrans = req->num_retrans; reqsk_fastopen_remove(sk, req, false); } else { @@ -6124,8 +6145,12 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } break; } - } else - goto discard; + } + + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); /* step 6: check the URG bit */ tcp_urg(sk, skb, th); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0c4a64355603..70b09ef2463b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -138,14 +138,6 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) } EXPORT_SYMBOL_GPL(tcp_twsk_unique); -static int tcp_repair_connect(struct sock *sk) -{ - tcp_connect_init(sk); - tcp_finish_connect(sk, NULL); - - return 0; -} - /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -250,10 +242,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_id = tp->write_seq ^ jiffies; - if (likely(!tp->repair)) - err = tcp_connect(sk); - else - err = tcp_repair_connect(sk); + err = tcp_connect(sk); rt = NULL; if (err) @@ -380,11 +369,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk) && - type != ICMP_DEST_UNREACH && - code != ICMP_FRAG_NEEDED) - NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); - + if (sock_owned_by_user(sk)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); + } if (sk->sk_state == TCP_CLOSE) goto out; @@ -877,10 +865,13 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, } static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp) { - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v4_send_synack(sk, NULL, req, rvp, 0, false); + int res = tcp_v4_send_synack(sk, NULL, req, rvp, 0, false); + + if (!res) + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return res; } /* @@ -1070,7 +1061,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) } EXPORT_SYMBOL(tcp_md5_do_del); -void tcp_clear_md5_list(struct sock *sk) +static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; @@ -1386,7 +1377,8 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk, struct sock *child; int err; - req->retrans = 0; + req->num_retrans = 0; + req->num_timeout = 0; req->sk = NULL; child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); @@ -1741,7 +1733,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_initialize_rcv_mss(newsk); tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->retrans; + newtp->total_retrans = req->num_retrans; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -1774,10 +1766,8 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: - tcp_clear_xmit_timers(newsk); - tcp_cleanup_congestion_control(newsk); - bh_unlock_sock(newsk); - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); goto exit; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); @@ -1919,7 +1909,6 @@ EXPORT_SYMBOL(tcp_v4_do_rcv); void tcp_v4_early_demux(struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; @@ -1927,16 +1916,16 @@ void tcp_v4_early_demux(struct sk_buff *skb) if (skb->pkt_type != PACKET_HOST) return; - if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr))) + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return; iph = ip_hdr(skb); - th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb)); + th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return; - sk = __inet_lookup_established(net, &tcp_hashinfo, + sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif); @@ -2640,7 +2629,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), - req->retrans, + req->num_timeout, from_kuid_munged(seq_user_ns(f), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4c752a6e0bcd..f696d7c2e9fa 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -1,7 +1,6 @@ #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/jiffies.h> -#include <linux/bootmem.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/slab.h> @@ -9,6 +8,7 @@ #include <linux/tcp.h> #include <linux/hash.h> #include <linux/tcp_metrics.h> +#include <linux/vmalloc.h> #include <net/inet_connection_sock.h> #include <net/net_namespace.h> @@ -864,7 +864,7 @@ static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, } a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6]; if (a) { - if (nla_len(a) != sizeof(sizeof(struct in6_addr))) + if (nla_len(a) != sizeof(struct in6_addr)) return -EINVAL; addr->family = AF_INET6; memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6)); @@ -1034,7 +1034,10 @@ static int __net_init tcp_net_metrics_init(struct net *net) net->ipv4.tcp_metrics_hash_log = order_base_2(slots); size = sizeof(struct tcpm_hash_bucket) << net->ipv4.tcp_metrics_hash_log; - net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL); + net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!net->ipv4.tcp_metrics_hash) + net->ipv4.tcp_metrics_hash = vzalloc(size); + if (!net->ipv4.tcp_metrics_hash) return -ENOMEM; @@ -1055,7 +1058,10 @@ static void __net_exit tcp_net_metrics_exit(struct net *net) tm = next; } } - kfree(net->ipv4.tcp_metrics_hash); + if (is_vmalloc_addr(net->ipv4.tcp_metrics_hash)) + vfree(net->ipv4.tcp_metrics_hash); + else + kfree(net->ipv4.tcp_metrics_hash); } static __net_initdata struct pernet_operations tcp_net_metrics_ops = { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a7302d974f32..f35f2dfb6401 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -553,7 +553,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans); + tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout); paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } @@ -582,7 +582,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Note that even if there is new data in the SYN packet * they will be thrown away too. */ - req->rsk_ops->rtx_syn_ack(sk, req, NULL); + inet_rtx_syn_ack(sk, req); return NULL; } @@ -696,7 +696,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* Got ACK for our SYNACK, so update baseline for SYNACK RTT sample. */ if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; - else if (req->retrans) /* don't take RTT sample if retrans && ~TS */ + else if (req->num_retrans) /* don't take RTT sample if retrans && ~TS */ tcp_rsk(req)->snt_synack = 0; /* For Fast Open no more processing is needed (sk is the @@ -706,7 +706,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, return sk; /* While TCP_DEFER_ACCEPT is active, drop bare ACK. */ - if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + if (req->num_timeout < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { inet_rsk(req)->acked = 1; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cfe6ffe1c177..5d451593ef16 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1986,6 +1986,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); + if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) + goto repair; /* Skip network transmission */ + cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) break; @@ -2026,6 +2029,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; +repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ @@ -2305,12 +2309,11 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ -int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) +int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; - int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { @@ -2383,11 +2386,17 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; } else { - err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } +} + +int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + int err = __tcp_retransmit_skb(sk, skb); if (err == 0) { /* Update global TCP statistics. */ @@ -2983,6 +2992,11 @@ int tcp_connect(struct sock *sk) tcp_connect_init(sk); + if (unlikely(tp->repair)) { + tcp_finish_connect(sk, NULL); + return 0; + } + buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); if (unlikely(buff == NULL)) return -ENOBUFS; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d47c1b4421a3..b78aac30c498 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -318,7 +318,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) req = tcp_sk(sk)->fastopen_rsk; req->rsk_ops->syn_ack_timeout(sk, req); - if (req->retrans >= max_retries) { + if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; } @@ -327,10 +327,10 @@ static void tcp_fastopen_synack_timer(struct sock *sk) * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ - req->rsk_ops->rtx_syn_ack(sk, req, NULL); - req->retrans++; + inet_rtx_syn_ack(sk, req); + req->num_timeout++; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - TCP_TIMEOUT_INIT << req->retrans, TCP_RTO_MAX); + TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); } /* diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 79c8dbe59b54..1f4d405eafba 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1952,6 +1952,7 @@ struct proto udp_prot = { .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .backlog_rcv = __udp_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05c5ab8d983c..3be0ac2c1920 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -279,19 +279,8 @@ static void __exit xfrm4_policy_fini(void) xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo); } -void __init xfrm4_init(int rt_max_size) +void __init xfrm4_init(void) { - /* - * Select a default value for the gc_thresh based on the main route - * table hash size. It seems to me the worst case scenario is when - * we have ipsec operating in transport mode, in which we create a - * dst_entry per socket. The xfrm gc algorithm starts trying to remove - * entries at gc_thresh, and prevents new allocations as 2*gc_thresh - * so lets set an initial xfrm gc_thresh value at the rt_max_size/2. - * That will let us store an ipsec connection per route table entry, - * and start cleaning when were 1/2 full - */ - xfrm4_dst_ops.gc_thresh = rt_max_size/2; dst_entries_init(&xfrm4_dst_ops); xfrm4_state_init(); diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index b6d3f79151e2..4ea244891b58 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -7,9 +7,11 @@ obj-$(CONFIG_IPV6) += ipv6.o ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ - raw.o protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ + raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o +ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o + ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o @@ -39,5 +41,6 @@ obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o obj-y += addrconf_core.o exthdrs_core.o +obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0424e4e27414..420e56326384 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -81,6 +81,7 @@ #include <net/pkt_sched.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> +#include <linux/netconf.h> #ifdef CONFIG_IPV6_PRIVACY #include <linux/random.h> @@ -153,6 +154,11 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); +static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, + int plen, + const struct net_device *dev, + u32 flags, u32 noflags); + static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_timer(unsigned long data); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); @@ -249,12 +255,6 @@ static inline bool addrconf_qdisc_ok(const struct net_device *dev) return !qdisc_tx_is_noop(dev); } -/* Check if a route is valid prefix route */ -static inline int addrconf_is_prefix_route(const struct rt6_info *rt) -{ - return (rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0; -} - static void addrconf_del_timer(struct inet6_ifaddr *ifp) { if (del_timer(&ifp->timer)) @@ -401,7 +401,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) ndev->cnf.accept_dad = -1; -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { pr_info("%s: Disabled Multicast RS\n", dev->name); ndev->cnf.rtr_solicits = 0; @@ -460,6 +460,149 @@ static struct inet6_dev *ipv6_find_idev(struct net_device *dev) return idev; } +static int inet6_netconf_msgsize_devconf(int type) +{ + int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + + nla_total_size(4); /* NETCONFA_IFINDEX */ + + /* type -1 is used for ALL */ + if (type == -1 || type == NETCONFA_FORWARDING) + size += nla_total_size(4); +#ifdef CONFIG_IPV6_MROUTE + if (type == -1 || type == NETCONFA_MC_FORWARDING) + size += nla_total_size(4); +#endif + + return size; +} + +static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, + struct ipv6_devconf *devconf, u32 portid, + u32 seq, int event, unsigned int flags, + int type) +{ + struct nlmsghdr *nlh; + struct netconfmsg *ncm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), + flags); + if (nlh == NULL) + return -EMSGSIZE; + + ncm = nlmsg_data(nlh); + ncm->ncm_family = AF_INET6; + + if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) + goto nla_put_failure; + + /* type -1 is used for ALL */ + if ((type == -1 || type == NETCONFA_FORWARDING) && + nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0) + goto nla_put_failure; +#ifdef CONFIG_IPV6_MROUTE + if ((type == -1 || type == NETCONFA_MC_FORWARDING) && + nla_put_s32(skb, NETCONFA_MC_FORWARDING, + devconf->mc_forwarding) < 0) + goto nla_put_failure; +#endif + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, + struct ipv6_devconf *devconf) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, + RTM_NEWNETCONF, 0, type); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err); +} + +static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { + [NETCONFA_IFINDEX] = { .len = sizeof(int) }, + [NETCONFA_FORWARDING] = { .len = sizeof(int) }, +}; + +static int inet6_netconf_get_devconf(struct sk_buff *in_skb, + struct nlmsghdr *nlh, + void *arg) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NETCONFA_MAX+1]; + struct netconfmsg *ncm; + struct sk_buff *skb; + struct ipv6_devconf *devconf; + struct inet6_dev *in6_dev; + struct net_device *dev; + int ifindex; + int err; + + err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, + devconf_ipv6_policy); + if (err < 0) + goto errout; + + err = EINVAL; + if (!tb[NETCONFA_IFINDEX]) + goto errout; + + ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); + switch (ifindex) { + case NETCONFA_IFINDEX_ALL: + devconf = net->ipv6.devconf_all; + break; + case NETCONFA_IFINDEX_DEFAULT: + devconf = net->ipv6.devconf_dflt; + break; + default: + dev = __dev_get_by_index(net, ifindex); + if (dev == NULL) + goto errout; + in6_dev = __in6_dev_get(dev); + if (in6_dev == NULL) + goto errout; + devconf = &in6_dev->cnf; + break; + } + + err = -ENOBUFS; + skb = nlmsg_new(inet6_netconf_msgsize_devconf(-1), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_netconf_fill_devconf(skb, ifindex, devconf, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWNETCONF, 0, + -1); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout: + return err; +} + #ifdef CONFIG_SYSCTL static void dev_forward_change(struct inet6_dev *idev) { @@ -471,7 +614,7 @@ static void dev_forward_change(struct inet6_dev *idev) dev = idev->dev; if (idev->cnf.forwarding) dev_disable_lro(dev); - if (dev && (dev->flags & IFF_MULTICAST)) { + if (dev->flags & IFF_MULTICAST) { if (idev->cnf.forwarding) ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); else @@ -486,6 +629,8 @@ static void dev_forward_change(struct inet6_dev *idev) else addrconf_leave_anycast(ifa); } + inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING, + dev->ifindex, &idev->cnf); } @@ -518,6 +663,10 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) *p = newf; if (p == &net->ipv6.devconf_dflt->forwarding) { + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); rtnl_unlock(); return 0; } @@ -525,6 +674,10 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) if (p == &net->ipv6.devconf_all->forwarding) { net->ipv6.devconf_dflt->forwarding = newf; addrconf_forward_change(net, newf); + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); } else if ((!newf) ^ (!old)) dev_forward_change((struct inet6_dev *)table->extra1); rtnl_unlock(); @@ -553,7 +706,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) pr_warn("Freeing alive inet6 address %p\n", ifp); return; } - dst_release(&ifp->rt->dst); + ip6_rt_put(ifp->rt); kfree_rcu(ifp, rcu); } @@ -787,17 +940,15 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) { struct in6_addr prefix; struct rt6_info *rt; - struct net *net = dev_net(ifp->idev->dev); - struct flowi6 fl6 = {}; ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len); - fl6.flowi6_oif = ifp->idev->dev->ifindex; - fl6.daddr = prefix; - rt = (struct rt6_info *)ip6_route_lookup(net, &fl6, - RT6_LOOKUP_F_IFACE); - if (rt != net->ipv6.ip6_null_entry && - addrconf_is_prefix_route(rt)) { + rt = addrconf_get_prefix_route(&prefix, + ifp->prefix_len, + ifp->idev->dev, + 0, RTF_GATEWAY | RTF_DEFAULT); + + if (rt) { if (onlink == 0) { ip6_del_rt(rt); rt = NULL; @@ -805,7 +956,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) rt6_set_expires(rt, expires); } } - dst_release(&rt->dst); + ip6_rt_put(rt); } /* clean up prefsrc entries */ @@ -1692,7 +1843,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) cfg.fc_flags |= RTF_NONEXTHOP; #endif @@ -1723,7 +1874,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->rt6i_flags & flags) != flags) continue; - if ((noflags != 0) && ((rt->rt6i_flags & flags) != 0)) + if ((rt->rt6i_flags & noflags) != 0) continue; dst_hold(&rt->dst); break; @@ -1752,7 +1903,7 @@ static void addrconf_add_mroute(struct net_device *dev) ip6_route_add(&cfg); } -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) static void sit_route_add(struct net_device *dev) { struct fib6_config cfg = { @@ -1881,8 +2032,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, dev, expires, flags); } - if (rt) - dst_release(&rt->dst); + ip6_rt_put(rt); } /* Try to figure out our local address for this prefix */ @@ -2104,7 +2254,7 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) if (dev == NULL) goto err_exit; -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT) { const struct net_device_ops *ops = dev->netdev_ops; struct ifreq ifr; @@ -2268,7 +2418,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) struct in6_ifreq ireq; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) @@ -2287,7 +2437,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg) struct in6_ifreq ireq; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) @@ -2315,7 +2465,7 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, } } -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) static void sit_add_v4_addrs(struct inet6_dev *idev) { struct in6_addr addr; @@ -2434,7 +2584,7 @@ static void addrconf_dev_config(struct net_device *dev) addrconf_add_linklocal(idev, &addr); } -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) static void addrconf_sit_config(struct net_device *dev) { struct inet6_dev *idev; @@ -2471,7 +2621,7 @@ static void addrconf_sit_config(struct net_device *dev) } #endif -#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE) +#if IS_ENABLED(CONFIG_NET_IPGRE) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; @@ -2601,12 +2751,12 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } switch (dev->type) { -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) +#if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: addrconf_sit_config(dev); break; #endif -#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE) +#if IS_ENABLED(CONFIG_NET_IPGRE) case ARPHRD_IPGRE: addrconf_gre_config(dev); break; @@ -2843,7 +2993,7 @@ static void addrconf_rs_timer(unsigned long data) if (idev->dead || !(idev->if_flags & IF_READY)) goto out; - if (idev->cnf.forwarding) + if (!ipv6_accept_ra(idev)) goto out; /* Announcement received after solicitation was sent */ @@ -3005,8 +3155,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) router advertisements, start sending router solicitations. */ - if (((ifp->idev->cnf.accept_ra == 1 && !ifp->idev->cnf.forwarding) || - ifp->idev->cnf.accept_ra == 2) && + if (ipv6_accept_ra(ifp->idev) && ifp->idev->cnf.rtr_solicits > 0 && (dev->flags&IFF_LOOPBACK) == 0 && (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { @@ -3194,7 +3343,7 @@ void if6_proc_exit(void) } #endif /* CONFIG_PROC_FS */ -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) /* Check if address is a home address configured on any interface. */ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { @@ -3892,6 +4041,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; + array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; } static inline size_t inet6_ifla6_size(void) @@ -4560,6 +4710,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec }, { + .procname = "ndisc_notify", + .data = &ipv6_devconf.ndisc_notify, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { /* sentinel */ } }, @@ -4784,6 +4941,8 @@ int __init addrconf_init(void) inet6_dump_ifmcaddr, NULL); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, + NULL, NULL); ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a974247a9ae4..b043c60429bd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -160,7 +160,8 @@ lookup_protocol: } err = -EPERM; - if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && + !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; @@ -282,7 +283,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; lock_sock(sk); @@ -699,249 +700,9 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ipv6_opt_accepted); -static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) -{ - const struct inet6_protocol *ops = NULL; - - for (;;) { - struct ipv6_opt_hdr *opth; - int len; - - if (proto != NEXTHDR_HOP) { - ops = rcu_dereference(inet6_protos[proto]); - - if (unlikely(!ops)) - break; - - if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) - break; - } - - if (unlikely(!pskb_may_pull(skb, 8))) - break; - - opth = (void *)skb->data; - len = ipv6_optlen(opth); - - if (unlikely(!pskb_may_pull(skb, len))) - break; - - proto = opth->nexthdr; - __skb_pull(skb, len); - } - - return proto; -} - -static int ipv6_gso_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - const struct inet6_protocol *ops; - int err = -EINVAL; - - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - goto out; - - ipv6h = ipv6_hdr(skb); - __skb_pull(skb, sizeof(*ipv6h)); - err = -EPROTONOSUPPORT; - - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[ - ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - - if (likely(ops && ops->gso_send_check)) { - skb_reset_transport_header(skb); - err = ops->gso_send_check(skb); - } - rcu_read_unlock(); - -out: - return err; -} - -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - struct ipv6hdr *ipv6h; - const struct inet6_protocol *ops; - int proto; - struct frag_hdr *fptr; - unsigned int unfrag_ip6hlen; - u8 *prevhdr; - int offset = 0; - - if (!(features & NETIF_F_V6_CSUM)) - features &= ~NETIF_F_SG; - - if (unlikely(skb_shinfo(skb)->gso_type & - ~(SKB_GSO_UDP | - SKB_GSO_DODGY | - SKB_GSO_TCP_ECN | - SKB_GSO_TCPV6 | - 0))) - goto out; - - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - goto out; - - ipv6h = ipv6_hdr(skb); - __skb_pull(skb, sizeof(*ipv6h)); - segs = ERR_PTR(-EPROTONOSUPPORT); - - proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[proto]); - if (likely(ops && ops->gso_segment)) { - skb_reset_transport_header(skb); - segs = ops->gso_segment(skb, features); - } - rcu_read_unlock(); - - if (IS_ERR(segs)) - goto out; - - for (skb = segs; skb; skb = skb->next) { - ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(skb->len - skb->mac_len - - sizeof(*ipv6h)); - if (proto == IPPROTO_UDP) { - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)(skb_network_header(skb) + - unfrag_ip6hlen); - fptr->frag_off = htons(offset); - if (skb->next != NULL) - fptr->frag_off |= htons(IP6_MF); - offset += (ntohs(ipv6h->payload_len) - - sizeof(struct frag_hdr)); - } - } - -out: - return segs; -} - -static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) -{ - const struct inet6_protocol *ops; - struct sk_buff **pp = NULL; - struct sk_buff *p; - struct ipv6hdr *iph; - unsigned int nlen; - unsigned int hlen; - unsigned int off; - int flush = 1; - int proto; - __wsum csum; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*iph); - iph = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - iph = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!iph)) - goto out; - } - - skb_gro_pull(skb, sizeof(*iph)); - skb_set_transport_header(skb, skb_gro_offset(skb)); - - flush += ntohs(iph->payload_len) != skb_gro_len(skb); - - rcu_read_lock(); - proto = iph->nexthdr; - ops = rcu_dereference(inet6_protos[proto]); - if (!ops || !ops->gro_receive) { - __pskb_pull(skb, skb_gro_offset(skb)); - proto = ipv6_gso_pull_exthdrs(skb, proto); - skb_gro_pull(skb, -skb_transport_offset(skb)); - skb_reset_transport_header(skb); - __skb_push(skb, skb_gro_offset(skb)); - - ops = rcu_dereference(inet6_protos[proto]); - if (!ops || !ops->gro_receive) - goto out_unlock; - - iph = ipv6_hdr(skb); - } - - NAPI_GRO_CB(skb)->proto = proto; - - flush--; - nlen = skb_network_header_len(skb); - - for (p = *head; p; p = p->next) { - const struct ipv6hdr *iph2; - __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ - - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - iph2 = ipv6_hdr(p); - first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; - - /* All fields must match except length and Traffic Class. */ - if (nlen != skb_network_header_len(p) || - (first_word & htonl(0xF00FFFFF)) || - memcmp(&iph->nexthdr, &iph2->nexthdr, - nlen - offsetof(struct ipv6hdr, nexthdr))) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - /* flush if Traffic Class fields are different */ - NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); - NAPI_GRO_CB(p)->flush |= flush; - } - - NAPI_GRO_CB(skb)->flush |= flush; - - csum = skb->csum; - skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); - - pp = ops->gro_receive(head, skb); - - skb->csum = csum; - -out_unlock: - rcu_read_unlock(); - -out: - NAPI_GRO_CB(skb)->flush |= flush; - - return pp; -} - -static int ipv6_gro_complete(struct sk_buff *skb) -{ - const struct inet6_protocol *ops; - struct ipv6hdr *iph = ipv6_hdr(skb); - int err = -ENOSYS; - - iph->payload_len = htons(skb->len - skb_network_offset(skb) - - sizeof(*iph)); - - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[NAPI_GRO_CB(skb)->proto]); - if (WARN_ON(!ops || !ops->gro_complete)) - goto out_unlock; - - err = ops->gro_complete(skb); - -out_unlock: - rcu_read_unlock(); - - return err; -} - static struct packet_type ipv6_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .func = ipv6_rcv, - .gso_send_check = ipv6_gso_send_check, - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, }; static int __init ipv6_packet_init(void) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 7e6139508ee7..384233188ac1 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -44,7 +44,7 @@ #define IPV6HDR_BASELEN 8 struct tmp_ext { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) struct in6_addr saddr; #endif struct in6_addr daddr; @@ -152,7 +152,7 @@ bad: return false; } -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) /** * ipv6_rearrange_destopt - rearrange IPv6 destination options header * @iph: IPv6 header @@ -320,7 +320,7 @@ static void ah6_output_done(struct crypto_async_request *base, int err) memcpy(top_iph, iph_base, IPV6HDR_BASELEN); if (extlen) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) memcpy(&top_iph->saddr, iph_ext, extlen); #else memcpy(&top_iph->daddr, iph_ext, extlen); @@ -385,7 +385,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(iph_base, top_iph, IPV6HDR_BASELEN); if (extlen) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) memcpy(iph_ext, &top_iph->saddr, extlen); #else memcpy(iph_ext, &top_iph->daddr, extlen); @@ -434,7 +434,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph, iph_base, IPV6HDR_BASELEN); if (extlen) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) memcpy(&top_iph->saddr, iph_ext, extlen); #else memcpy(&top_iph->daddr, iph_ext, extlen); @@ -472,7 +472,10 @@ static void ah6_input_done(struct crypto_async_request *base, int err) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); __skb_pull(skb, ah_hlen + hdr_len); - skb_set_transport_header(skb, -hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -593,9 +596,13 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); - skb->transport_header = skb->network_header; __skb_pull(skb, ah_hlen + hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); + err = nexthdr; out_free: diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index cdf02be5f191..757a810d8f15 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -64,7 +64,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) return -EINVAL; @@ -84,7 +84,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { dev = rt->dst.dev; - dst_release(&rt->dst); + ip6_rt_put(rt); } else if (ishost) { err = -EADDRNOTAVAIL; goto error; @@ -189,6 +189,9 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; + if (!np->ipv6_ac_list) + return; + write_lock_bh(&ipv6_sk_ac_lock); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index be2b67d631e5..8edf2601065a 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -701,7 +701,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -721,7 +721,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -746,7 +746,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -769,7 +769,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg); switch (rthdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 282f3723ee19..40ffd72243a4 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -300,7 +300,10 @@ static int esp_input_done2(struct sk_buff *skb, int err) pskb_trim(skb, skb->len - alen - padlen - 2); __skb_pull(skb, hlen); - skb_set_transport_header(skb, -hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); err = nexthdr[1]; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index fa3d9c328092..473f628f9f20 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -43,56 +43,12 @@ #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/xfrm.h> #endif #include <asm/uaccess.h> -int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) -{ - const unsigned char *nh = skb_network_header(skb); - int packet_len = skb->tail - skb->network_header; - struct ipv6_opt_hdr *hdr; - int len; - - if (offset + 2 > packet_len) - goto bad; - hdr = (struct ipv6_opt_hdr *)(nh + offset); - len = ((hdr->hdrlen + 1) << 3); - - if (offset + len > packet_len) - goto bad; - - offset += 2; - len -= 2; - - while (len > 0) { - int opttype = nh[offset]; - int optlen; - - if (opttype == type) - return offset; - - switch (opttype) { - case IPV6_TLV_PAD1: - optlen = 1; - break; - default: - optlen = nh[offset + 1] + 2; - if (optlen > len) - goto bad; - break; - } - offset += optlen; - len -= optlen; - } - /* not_found */ - bad: - return -1; -} -EXPORT_SYMBOL_GPL(ipv6_find_tlv); - /* * Parsing tlv encoded headers. * @@ -224,7 +180,7 @@ bad: Destination options header. *****************************/ -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) { struct ipv6_destopt_hao *hao; @@ -288,7 +244,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) #endif static const struct tlvtype_proc tlvprocdestopt_lst[] = { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) { .type = IPV6_TLV_HAO, .func = ipv6_dest_hao, @@ -300,7 +256,7 @@ static const struct tlvtype_proc tlvprocdestopt_lst[] = { static int ipv6_destopt_rcv(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) __u16 dstbuf; #endif struct dst_entry *dst = skb_dst(skb); @@ -315,14 +271,14 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) } opt->lastopt = opt->dst1 = skb_network_header_len(skb); -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) dstbuf = opt->dst1; #endif if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; opt = IP6CB(skb); -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) opt->nhoff = dstbuf; #else opt->nhoff = opt->dst1; @@ -378,7 +334,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) looped_back: if (hdr->segments_left == 0) { switch (hdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: /* Silently discard type 2 header unless it was * processed by own @@ -404,7 +360,7 @@ looped_back: } switch (hdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (accept_source_route < 0) goto unknown_rh; @@ -461,7 +417,7 @@ looped_back: addr += i - 1; switch (hdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, @@ -528,12 +484,12 @@ unknown_rh: static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, + .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol destopt_protocol = { .handler = ipv6_destopt_rcv, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, + .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol nodata_protocol = { @@ -559,10 +515,10 @@ int __init ipv6_exthdrs_init(void) out: return ret; -out_rthdr: - inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); out_destopt: inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); +out_rthdr: + inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); goto out; }; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index f73d59a14131..c5e83fae4df4 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -111,3 +111,171 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, return start; } EXPORT_SYMBOL(ipv6_skip_exthdr); + +int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) +{ + const unsigned char *nh = skb_network_header(skb); + int packet_len = skb->tail - skb->network_header; + struct ipv6_opt_hdr *hdr; + int len; + + if (offset + 2 > packet_len) + goto bad; + hdr = (struct ipv6_opt_hdr *)(nh + offset); + len = ((hdr->hdrlen + 1) << 3); + + if (offset + len > packet_len) + goto bad; + + offset += 2; + len -= 2; + + while (len > 0) { + int opttype = nh[offset]; + int optlen; + + if (opttype == type) + return offset; + + switch (opttype) { + case IPV6_TLV_PAD1: + optlen = 1; + break; + default: + optlen = nh[offset + 1] + 2; + if (optlen > len) + goto bad; + break; + } + offset += optlen; + len -= optlen; + } + /* not_found */ + bad: + return -1; +} +EXPORT_SYMBOL_GPL(ipv6_find_tlv); + +/* + * find the offset to specified header or the protocol number of last header + * if target < 0. "last header" is transport protocol header, ESP, or + * "No next header". + * + * Note that *offset is used as input/output parameter. an if it is not zero, + * then it must be a valid offset to an inner IPv6 header. This can be used + * to explore inner IPv6 header, eg. ICMPv6 error messages. + * + * If target header is found, its offset is set in *offset and return protocol + * number. Otherwise, return -1. + * + * If the first fragment doesn't contain the final protocol header or + * NEXTHDR_NONE it is considered invalid. + * + * Note that non-1st fragment is special case that "the protocol number + * of last header" is "next header" field in Fragment header. In this case, + * *offset is meaningless and fragment offset is stored in *fragoff if fragoff + * isn't NULL. + * + * if flags is not NULL and it's a fragment, then the frag flag + * IP6_FH_F_FRAG will be set. If it's an AH header, the + * IP6_FH_F_AUTH flag is set and target < 0, then this function will + * stop at the AH header. If IP6_FH_F_SKIP_RH flag was passed, then this + * function will skip all those routing headers, where segements_left was 0. + */ +int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, + int target, unsigned short *fragoff, int *flags) +{ + unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + unsigned int len; + bool found; + + if (fragoff) + *fragoff = 0; + + if (*offset) { + struct ipv6hdr _ip6, *ip6; + + ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); + if (!ip6 || (ip6->version != 6)) { + printk(KERN_ERR "IPv6 header not found\n"); + return -EBADMSG; + } + start = *offset + sizeof(struct ipv6hdr); + nexthdr = ip6->nexthdr; + } + len = skb->len - start; + + do { + struct ipv6_opt_hdr _hdr, *hp; + unsigned int hdrlen; + found = (nexthdr == target); + + if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { + if (target < 0) + break; + return -ENOENT; + } + + hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); + if (hp == NULL) + return -EBADMSG; + + if (nexthdr == NEXTHDR_ROUTING) { + struct ipv6_rt_hdr _rh, *rh; + + rh = skb_header_pointer(skb, start, sizeof(_rh), + &_rh); + if (rh == NULL) + return -EBADMSG; + + if (flags && (*flags & IP6_FH_F_SKIP_RH) && + rh->segments_left == 0) + found = false; + } + + if (nexthdr == NEXTHDR_FRAGMENT) { + unsigned short _frag_off; + __be16 *fp; + + if (flags) /* Indicate that this is a fragment */ + *flags |= IP6_FH_F_FRAG; + fp = skb_header_pointer(skb, + start+offsetof(struct frag_hdr, + frag_off), + sizeof(_frag_off), + &_frag_off); + if (fp == NULL) + return -EBADMSG; + + _frag_off = ntohs(*fp) & ~0x7; + if (_frag_off) { + if (target < 0 && + ((!ipv6_ext_hdr(hp->nexthdr)) || + hp->nexthdr == NEXTHDR_NONE)) { + if (fragoff) + *fragoff = _frag_off; + return hp->nexthdr; + } + return -ENOENT; + } + hdrlen = 8; + } else if (nexthdr == NEXTHDR_AUTH) { + if (flags && (*flags & IP6_FH_F_AUTH) && (target < 0)) + break; + hdrlen = (hp->hdrlen + 2) << 2; + } else + hdrlen = ipv6_optlen(hp); + + if (!found) { + nexthdr = hp->nexthdr; + len -= hdrlen; + start += hdrlen; + } + } while (!found); + + *offset = start; + return nexthdr; +} +EXPORT_SYMBOL(ipv6_find_hdr); + diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c new file mode 100644 index 000000000000..cf77f3abfd06 --- /dev/null +++ b/net/ipv6/exthdrs_offload.c @@ -0,0 +1,41 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * IPV6 Extension Header GSO/GRO support + */ +#include <net/protocol.h> +#include "ip6_offload.h" + +static const struct net_offload rthdr_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +static const struct net_offload dstopt_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +int __init ipv6_exthdrs_offload_init(void) +{ + int ret; + + ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); + if (!ret) + goto out; + + ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); + if (!ret) + goto out_rt; + +out: + return ret; + +out_rt: + inet_del_offload(&rthdr_offload, IPPROTO_ROUTING); + goto out; +} diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index d9fb9110f607..2e1a432867c0 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -100,7 +100,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto out; } again: - dst_release(&rt->dst); + ip6_rt_put(rt); rt = NULL; goto out; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 24d69dbca4d6..fff5bdd8b680 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -81,10 +81,22 @@ static inline struct sock *icmpv6_sk(struct net *net) return net->ipv6.icmp_sk[smp_processor_id()]; } +static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct net *net = dev_net(skb->dev); + + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, 0, 0); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); +} + static int icmpv6_rcv(struct sk_buff *skb); static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, + .err_handler = icmpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; @@ -280,7 +292,7 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st return 0; } -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) static void mip6_addr_swap(struct sk_buff *skb) { struct ipv6hdr *iph = ipv6_hdr(skb); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index c4f934176cab..30647857a375 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -252,6 +252,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) return NULL; dst->ops->update_pmtu(dst, sk, NULL, mtu); - return inet6_csk_route_socket(sk, &fl6); + dst = inet6_csk_route_socket(sk, &fl6); + return IS_ERR(dst) ? NULL : dst; } EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 73f1a00a96af..dea17fd28e50 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -87,11 +87,13 @@ struct sock *__inet6_lookup_established(struct net *net, rcu_read_lock(); begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { - /* For IPV6 do the cheaper port and family tests first. */ - if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) goto begintw; - if (!INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, + ports, dif))) { sock_put(sk); goto begin; } @@ -104,12 +106,16 @@ begin: begintw: /* Must check for a TIME_WAIT'er before going to listener hash. */ sk_nulls_for_each_rcu(sk, node, &head->twchain) { - if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET6_TW_MATCH(sk, net, saddr, daddr, + ports, dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { sk = NULL; goto out; } - if (!INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, + ports, dif))) { sock_put(sk); goto begintw; } @@ -236,9 +242,12 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, /* Check TIME-WAIT sockets first. */ sk_nulls_for_each(sk2, node, &head->twchain) { - tw = inet_twsk(sk2); + if (sk2->sk_hash != hash) + continue; - if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) { + if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr, + ports, dif))) { + tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) goto unique; else @@ -249,7 +258,9 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, /* And established part... */ sk_nulls_for_each(sk2, node, &head->chain) { - if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) + if (sk2->sk_hash != hash) + continue; + if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) goto not_unique; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 24995a93ef8c..710cafd2e1a9 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -672,6 +672,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, iter->rt6i_idev == rt->rt6i_idev && ipv6_addr_equal(&iter->rt6i_gateway, &rt->rt6i_gateway)) { + if (rt->rt6i_nsiblings) + rt->rt6i_nsiblings = 0; if (!(iter->rt6i_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->rt6i_flags & RTF_EXPIRES)) @@ -680,6 +682,21 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, rt6_set_expires(iter, rt->dst.expires); return -EEXIST; } + /* If we have the same destination and the same metric, + * but not the same gateway, then the route we try to + * add is sibling to this route, increment our counter + * of siblings, and later we will add our route to the + * list. + * Only static routes (which don't have flag + * RTF_EXPIRES) are used for ECMPv6. + * + * To avoid long list, we only had siblings if the + * route have a gateway. + */ + if (rt->rt6i_flags & RTF_GATEWAY && + !(rt->rt6i_flags & RTF_EXPIRES) && + !(iter->rt6i_flags & RTF_EXPIRES)) + rt->rt6i_nsiblings++; } if (iter->rt6i_metric > rt->rt6i_metric) @@ -692,6 +709,35 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (ins == &fn->leaf) fn->rr_ptr = NULL; + /* Link this route to others same route. */ + if (rt->rt6i_nsiblings) { + unsigned int rt6i_nsiblings; + struct rt6_info *sibling, *temp_sibling; + + /* Find the first route that have the same metric */ + sibling = fn->leaf; + while (sibling) { + if (sibling->rt6i_metric == rt->rt6i_metric) { + list_add_tail(&rt->rt6i_siblings, + &sibling->rt6i_siblings); + break; + } + sibling = sibling->dst.rt6_next; + } + /* For each sibling in the list, increment the counter of + * siblings. BUG() if counters does not match, list of siblings + * is broken! + */ + rt6i_nsiblings = 0; + list_for_each_entry_safe(sibling, temp_sibling, + &rt->rt6i_siblings, rt6i_siblings) { + sibling->rt6i_nsiblings++; + BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings); + rt6i_nsiblings++; + } + BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings); + } + /* * insert node */ @@ -1193,6 +1239,17 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, if (fn->rr_ptr == rt) fn->rr_ptr = NULL; + /* Remove this entry from other siblings */ + if (rt->rt6i_nsiblings) { + struct rt6_info *sibling, *next_sibling; + + list_for_each_entry_safe(sibling, next_sibling, + &rt->rt6i_siblings, rt6i_siblings) + sibling->rt6i_nsiblings--; + rt->rt6i_nsiblings = 0; + list_del_init(&rt->rt6i_siblings); + } + /* Adjust walkers */ read_lock(&fib6_walker_lock); FOR_WALKERS(w) { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 90bbefb57943..29124b7a04c8 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -519,7 +519,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } read_unlock_bh(&ip6_sk_fl_lock); - if (freq.flr_share == IPV6_FL_S_NONE && capable(CAP_NET_ADMIN)) { + if (freq.flr_share == IPV6_FL_S_NONE && + ns_capable(net->user_ns, CAP_NET_ADMIN)) { fl = fl_lookup(net, freq.flr_label); if (fl) { err = fl6_renew(fl, freq.flr_linger, freq.flr_expires); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 0185679c5f53..c727e4712751 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -109,21 +109,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr) #define tunnels_r tunnels[2] #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -181,7 +166,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; - for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || @@ -206,7 +191,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) { if (!ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) @@ -230,7 +215,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) { if ((!ipv6_addr_equal(local, &t->parms.laddr) && (!ipv6_addr_equal(local, &t->parms.raddr) || !ipv6_addr_is_multicast(local))) || @@ -256,7 +241,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) { if (t->parms.i_key != key || !(t->dev->flags & IFF_UP)) continue; @@ -773,8 +758,6 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_dst_set_noref(skb, dst); } - skb->transport_header = skb->network_header; - proto = NEXTHDR_GRE; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); @@ -783,6 +766,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_push(skb, gre_hlen); skb_reset_network_header(skb); + skb_set_transport_header(skb, sizeof(*ipv6h)); /* * Push down and install the IP header. @@ -1069,7 +1053,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) dev->mtu = IPV6_MIN_MTU; } } - dst_release(&rt->dst); + ip6_rt_put(rt); } t->hlen = addend; @@ -1161,7 +1145,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1209,7 +1193,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ign->fb_tunnel_dev) { @@ -1633,9 +1617,9 @@ static size_t ip6gre_get_size(const struct net_device *dev) /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_REMOTE */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ @@ -1659,8 +1643,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || - nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) || - nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c new file mode 100644 index 000000000000..f26f0da7f095 --- /dev/null +++ b/net/ipv6/ip6_offload.c @@ -0,0 +1,282 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/socket.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/printk.h> + +#include <net/protocol.h> +#include <net/ipv6.h> + +#include "ip6_offload.h" + +static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) +{ + const struct net_offload *ops = NULL; + + for (;;) { + struct ipv6_opt_hdr *opth; + int len; + + if (proto != NEXTHDR_HOP) { + ops = rcu_dereference(inet6_offloads[proto]); + + if (unlikely(!ops)) + break; + + if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + + if (unlikely(!pskb_may_pull(skb, 8))) + break; + + opth = (void *)skb->data; + len = ipv6_optlen(opth); + + if (unlikely(!pskb_may_pull(skb, len))) + break; + + proto = opth->nexthdr; + __skb_pull(skb, len); + } + + return proto; +} + +static int ipv6_gso_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + const struct net_offload *ops; + int err = -EINVAL; + + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + ipv6h = ipv6_hdr(skb); + __skb_pull(skb, sizeof(*ipv6h)); + err = -EPROTONOSUPPORT; + + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[ + ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); + + if (likely(ops && ops->callbacks.gso_send_check)) { + skb_reset_transport_header(skb); + err = ops->callbacks.gso_send_check(skb); + } + rcu_read_unlock(); + +out: + return err; +} + +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct ipv6hdr *ipv6h; + const struct net_offload *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; + + if (!(features & NETIF_F_V6_CSUM)) + features &= ~NETIF_F_SG; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_TCPV6 | + 0))) + goto out; + + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + ipv6h = ipv6_hdr(skb); + __skb_pull(skb, sizeof(*ipv6h)); + segs = ERR_PTR(-EPROTONOSUPPORT); + + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[proto]); + if (likely(ops && ops->callbacks.gso_segment)) { + skb_reset_transport_header(skb); + segs = ops->callbacks.gso_segment(skb, features); + } + rcu_read_unlock(); + + if (IS_ERR(segs)) + goto out; + + for (skb = segs; skb; skb = skb->next) { + ipv6h = ipv6_hdr(skb); + ipv6h->payload_len = htons(skb->len - skb->mac_len - + sizeof(*ipv6h)); + if (proto == IPPROTO_UDP) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)(skb_network_header(skb) + + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } + } + +out: + return segs; +} + +static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct net_offload *ops; + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct ipv6hdr *iph; + unsigned int nlen; + unsigned int hlen; + unsigned int off; + int flush = 1; + int proto; + __wsum csum; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*iph); + iph = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + iph = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!iph)) + goto out; + } + + skb_gro_pull(skb, sizeof(*iph)); + skb_set_transport_header(skb, skb_gro_offset(skb)); + + flush += ntohs(iph->payload_len) != skb_gro_len(skb); + + rcu_read_lock(); + proto = iph->nexthdr; + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) { + __pskb_pull(skb, skb_gro_offset(skb)); + proto = ipv6_gso_pull_exthdrs(skb, proto); + skb_gro_pull(skb, -skb_transport_offset(skb)); + skb_reset_transport_header(skb); + __skb_push(skb, skb_gro_offset(skb)); + + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) + goto out_unlock; + + iph = ipv6_hdr(skb); + } + + NAPI_GRO_CB(skb)->proto = proto; + + flush--; + nlen = skb_network_header_len(skb); + + for (p = *head; p; p = p->next) { + const struct ipv6hdr *iph2; + __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + iph2 = ipv6_hdr(p); + first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; + + /* All fields must match except length and Traffic Class. */ + if (nlen != skb_network_header_len(p) || + (first_word & htonl(0xF00FFFFF)) || + memcmp(&iph->nexthdr, &iph2->nexthdr, + nlen - offsetof(struct ipv6hdr, nexthdr))) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + /* flush if Traffic Class fields are different */ + NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); + NAPI_GRO_CB(p)->flush |= flush; + } + + NAPI_GRO_CB(skb)->flush |= flush; + + csum = skb->csum; + skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + + pp = ops->callbacks.gro_receive(head, skb); + + skb->csum = csum; + +out_unlock: + rcu_read_unlock(); + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int ipv6_gro_complete(struct sk_buff *skb) +{ + const struct net_offload *ops; + struct ipv6hdr *iph = ipv6_hdr(skb); + int err = -ENOSYS; + + iph->payload_len = htons(skb->len - skb_network_offset(skb) - + sizeof(*iph)); + + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]); + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) + goto out_unlock; + + err = ops->callbacks.gro_complete(skb); + +out_unlock: + rcu_read_unlock(); + + return err; +} + +static struct packet_offload ipv6_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IPV6), + .callbacks = { + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, +}; + +static int __init ipv6_offload_init(void) +{ + + if (tcpv6_offload_init() < 0) + pr_crit("%s: Cannot add TCP protocol offload\n", __func__); + if (udp_offload_init() < 0) + pr_crit("%s: Cannot add UDP protocol offload\n", __func__); + if (ipv6_exthdrs_offload_init() < 0) + pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); + + dev_add_offload(&ipv6_packet_offload); + return 0; +} + +fs_initcall(ipv6_offload_init); diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h new file mode 100644 index 000000000000..2e155c651b35 --- /dev/null +++ b/net/ipv6/ip6_offload.h @@ -0,0 +1,18 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef __ip6_offload_h +#define __ip6_offload_h + +int ipv6_exthdrs_offload_init(void); +int udp_offload_init(void); +int tcpv6_offload_init(void); + +#endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index aece3e792f84..0c7c03d50dc0 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -538,78 +538,12 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ - defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) to->nf_trace = from->nf_trace; #endif skb_copy_secmark(to, from); } -int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) -{ - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - unsigned int packet_len = skb->tail - skb->network_header; - int found_rhdr = 0; - *nexthdr = &ipv6_hdr(skb)->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - - case NEXTHDR_HOP: - break; - case NEXTHDR_ROUTING: - found_rhdr = 1; - break; - case NEXTHDR_DEST: -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) - break; -#endif - if (found_rhdr) - return offset; - break; - default : - return offset; - } - - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + - offset); - } - - return offset; -} - -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static atomic_t ipv6_fragmentation_id; - int old, new; - - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } - } - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); -} - int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -756,7 +690,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); - dst_release(&rt->dst); + ip6_rt_put(rt); return 0; } @@ -768,7 +702,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); - dst_release(&rt->dst); + ip6_rt_put(rt); return err; slow_path_clean: @@ -1279,10 +1213,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (dst_allfrag(rt->dst.path)) cork->flags |= IPCORK_ALLFRAG; cork->length = 0; - exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; + exthdrlen = (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; - dst_exthdrlen = rt->dst.header_len; + dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index cb7e2ded6f08..a14f28b280f5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -74,6 +74,10 @@ MODULE_ALIAS_NETDEV("ip6tnl0"); #define HASH_SIZE_SHIFT 5 #define HASH_SIZE (1 << HASH_SIZE_SHIFT) +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); @@ -83,6 +87,7 @@ static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); +static struct rtnl_link_ops ip6_link_ops __read_mostly; static int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { @@ -94,14 +99,6 @@ struct ip6_tnl_net { struct ip6_tnl __rcu **tnls[2]; }; -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -} __attribute__((aligned(4*sizeof(unsigned long)))); - static struct net_device_stats *ip6_get_stats(struct net_device *dev) { struct pcpu_tstats sum = { 0 }; @@ -258,6 +255,33 @@ static void ip6_dev_free(struct net_device *dev) free_netdev(dev); } +static int ip6_tnl_create2(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + t = netdev_priv(dev); + err = ip6_tnl_dev_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &ip6_link_ops; + + dev_hold(dev); + ip6_tnl_link(ip6n, t); + return 0; + +out: + return err; +} + /** * ip6_tnl_create - create a new tunnel * @p: tunnel parameters @@ -276,7 +300,6 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) struct ip6_tnl *t; char name[IFNAMSIZ]; int err; - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); @@ -291,17 +314,10 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) t = netdev_priv(dev); t->parms = *p; - err = ip6_tnl_dev_init(dev); + err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; - if ((err = register_netdevice(dev)) < 0) - goto failed_free; - - strcpy(t->parms.name, dev->name); - - dev_hold(dev); - ip6_tnl_link(ip6n, t); return t; failed_free: @@ -663,8 +679,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, icmpv6_send(skb2, rel_type, rel_code, rel_info); - if (rt) - dst_release(&rt->dst); + ip6_rt_put(rt); kfree_skb(skb2); } @@ -672,28 +687,26 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } -static void ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, - struct sk_buff *skb) +static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); - if (INET_ECN_is_ce(dsfield)) - IP_ECN_set_ce(ip_hdr(skb)); + return IP6_ECN_decapsulate(ipv6h, skb); } -static void ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, - struct sk_buff *skb) +static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); - if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h))) - IP6_ECN_set_ce(ipv6_hdr(skb)); + return IP6_ECN_decapsulate(ipv6h, skb); } __u32 ip6_tnl_get_cap(struct ip6_tnl *t, @@ -757,12 +770,13 @@ EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, __u8 ipproto, - void (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, - struct sk_buff *skb)) + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb)) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + int err; rcu_read_lock(); @@ -792,14 +806,26 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); + __skb_tunnel_rx(skb, t->dev); + + err = dscp_ecn_decapsulate(t, ipv6h, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n", + &ipv6h->saddr, + ipv6_get_dsfield(ipv6h)); + if (err > 1) { + ++t->dev->stats.rx_frame_errors; + ++t->dev->stats.rx_errors; + rcu_read_unlock(); + goto discard; + } + } + tstats = this_cpu_ptr(t->dev->tstats); tstats->rx_packets++; tstats->rx_bytes += skb->len; - __skb_tunnel_rx(skb, t->dev); - - dscp_ecn_decapsulate(t, ipv6h, skb); - netif_rx(skb); rcu_read_unlock(); @@ -1208,7 +1234,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } - dst_release(&rt->dst); + ip6_rt_put(rt); } } @@ -1237,6 +1263,20 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) return 0; } +static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +{ + struct net *net = dev_net(t->dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + ip6_tnl_unlink(ip6n, t); + synchronize_net(); + err = ip6_tnl_change(t, p); + ip6_tnl_link(ip6n, t); + netdev_state_change(t->dev); + return err; +} + static void ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) { @@ -1325,7 +1365,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) @@ -1345,11 +1385,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } else t = netdev_priv(dev); - ip6_tnl_unlink(ip6n, t); - synchronize_net(); - err = ip6_tnl_change(t, &p1); - ip6_tnl_link(ip6n, t); - netdev_state_change(dev); + err = ip6_tnl_update(t, &p1); } if (t) { err = 0; @@ -1362,7 +1398,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { @@ -1505,6 +1541,164 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) return 0; } +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; + + return 0; +} + +static void ip6_tnl_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_IPTUN_LOCAL], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_IPTUN_REMOTE], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_TTL]) + parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); + + if (data[IFLA_IPTUN_ENCAP_LIMIT]) + parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); + + if (data[IFLA_IPTUN_FLOWINFO]) + parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); + + if (data[IFLA_IPTUN_FLAGS]) + parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); +} + +static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *nt; + + nt = netdev_priv(dev); + ip6_tnl_netlink_parms(data, &nt->parms); + + if (ip6_tnl_locate(net, &nt->parms, 0)) + return -EEXIST; + + return ip6_tnl_create2(dev); +} + +static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t; + struct __ip6_tnl_parm p; + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev == ip6n->fb_tnl_dev) + return -EINVAL; + + ip6_tnl_netlink_parms(data, &p); + + t = ip6_tnl_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + return ip6_tnl_update(t, &p); +} + +static size_t ip6_tnl_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_ENCAP_LIMIT */ + nla_total_size(1) + + /* IFLA_IPTUN_FLOWINFO */ + nla_total_size(4) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(4) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + + 0; +} + +static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct __ip6_tnl_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), + &parm->raddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->laddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || + nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || + nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || + nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, +}; + +static struct rtnl_link_ops ip6_link_ops __read_mostly = { + .kind = "ip6tnl", + .maxtype = IFLA_IPTUN_MAX, + .policy = ip6_tnl_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6_tnl_dev_setup, + .validate = ip6_tnl_validate, + .newlink = ip6_tnl_newlink, + .changelink = ip6_tnl_changelink, + .get_size = ip6_tnl_get_size, + .fill_info = ip6_tnl_fill_info, +}; + static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, @@ -1613,9 +1807,14 @@ static int __init ip6_tunnel_init(void) pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } + err = rtnl_link_register(&ip6_link_ops); + if (err < 0) + goto rtnl_link_failed; return 0; +rtnl_link_failed: + xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: @@ -1630,6 +1829,7 @@ out_pernet: static void __exit ip6_tunnel_cleanup(void) { + rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) pr_info("%s: can't deregister ip4ip6\n", __func__); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f7c7c6319720..8fd154e5f079 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -52,6 +52,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/export.h> #include <net/ip6_checksum.h> +#include <linux/netconf.h> struct mr6_table { struct list_head list; @@ -66,8 +67,8 @@ struct mr6_table { struct mif_device vif6_table[MAXMIFS]; int maxvif; atomic_t cache_resolve_queue_len; - int mroute_do_assert; - int mroute_do_pim; + bool mroute_do_assert; + bool mroute_do_pim; #ifdef CONFIG_IPV6_PIMSM_V2 int mroute_reg_vif_num; #endif @@ -115,6 +116,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); +static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, + int cmd); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr6_table *mrt); @@ -805,8 +808,12 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) dev_set_allmulti(dev, -1); in6_dev = __in6_dev_get(dev); - if (in6_dev) + if (in6_dev) { in6_dev->cnf.mc_forwarding--; + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in6_dev->cnf); + } if (v->flags & MIFF_REGISTER) unregister_netdevice_queue(dev, head); @@ -865,6 +872,7 @@ static void ipmr_do_expire_process(struct mr6_table *mrt) } list_del(&c->list); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, c); } @@ -958,8 +966,12 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, } in6_dev = __in6_dev_get(dev); - if (in6_dev) + if (in6_dev) { in6_dev->cnf.mc_forwarding++; + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in6_dev->cnf); + } /* * Fill in the VIF structures @@ -1211,6 +1223,7 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->list, &mrt->mfc6_unres_queue); + mr6_netlink_event(mrt, c, RTM_NEWROUTE); ipmr_do_expire_process(mrt); } @@ -1248,6 +1261,7 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) list_del(&c->list); write_unlock_bh(&mrt_lock); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_cache_free(c); return 0; } @@ -1412,6 +1426,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1456,6 +1471,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } + mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1489,6 +1505,7 @@ static void mroute_clean_tables(struct mr6_table *mrt) list_del(&c->list); write_unlock_bh(&mrt_lock); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_cache_free(c); } } @@ -1497,6 +1514,7 @@ static void mroute_clean_tables(struct mr6_table *mrt) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { list_del(&c->list); + mr6_netlink_event(mrt, c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); @@ -1513,6 +1531,9 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) if (likely(mrt->mroute6_sk == NULL)) { mrt->mroute6_sk = sk; net->ipv6.devconf_all->mc_forwarding++; + inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); } else err = -EADDRINUSE; @@ -1535,6 +1556,10 @@ int ip6mr_sk_done(struct sock *sk) write_lock_bh(&mrt_lock); mrt->mroute6_sk = NULL; net->ipv6.devconf_all->mc_forwarding--; + inet6_netconf_notify_devconf(net, + NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); write_unlock_bh(&mrt_lock); mroute_clean_tables(mrt); @@ -1583,7 +1608,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -ENOENT; if (optname != MRT6_INIT) { - if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute6_sk && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } @@ -1646,9 +1671,12 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ASSERT: { int v; + + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; - mrt->mroute_do_assert = !!v; + mrt->mroute_do_assert = v; return 0; } @@ -1656,6 +1684,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_PIM: { int v; + + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; v = !!v; @@ -1679,6 +1710,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -EINVAL; if (get_user(v, (u32 __user *)optval)) return -EFAULT; + /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ + if (v != RT_TABLE_DEFAULT && v >= 100000000) + return -EINVAL; if (sk == mrt->mroute6_sk) return -EBUSY; @@ -2097,8 +2131,8 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, { int ct; struct rtnexthop *nhp; - u8 *b = skb_tail_pointer(skb); - struct rtattr *mp_head; + struct nlattr *mp_attr; + struct rta_mfc_stats mfcs; /* If cache is unresolved, don't try to parse IIF and OIF */ if (c->mf6c_parent >= MAXMIFS) @@ -2107,28 +2141,35 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (MIF_EXISTS(mrt, c->mf6c_parent) && nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) return -EMSGSIZE; - - mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); + mp_attr = nla_nest_start(skb, RTA_MULTIPATH); + if (mp_attr == NULL) + return -EMSGSIZE; for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { - if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) - goto rtattr_failure; - nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); + nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); + if (nhp == NULL) { + nla_nest_cancel(skb, mp_attr); + return -EMSGSIZE; + } + nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } - mp_head->rta_type = RTA_MULTIPATH; - mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head; + + nla_nest_end(skb, mp_attr); + + mfcs.mfcs_packets = c->mfc_un.res.pkt; + mfcs.mfcs_bytes = c->mfc_un.res.bytes; + mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0) + return -EMSGSIZE; + rtm->rtm_type = RTN_MULTICAST; return 1; - -rtattr_failure: - nlmsg_trim(skb, b); - return -EMSGSIZE; } int ip6mr_get_route(struct net *net, @@ -2202,31 +2243,38 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc6_cache *c) + u32 portid, u32 seq, struct mfc6_cache *c, int cmd) { struct nlmsghdr *nlh; struct rtmsg *rtm; + int err; - nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); if (nlh == NULL) return -EMSGSIZE; rtm = nlmsg_data(nlh); - rtm->rtm_family = RTNL_FAMILY_IPMR; + rtm->rtm_family = RTNL_FAMILY_IP6MR; rtm->rtm_dst_len = 128; rtm->rtm_src_len = 128; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; + rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - rtm->rtm_protocol = RTPROT_UNSPEC; + if (c->mfc_flags & MFC_STATIC) + rtm->rtm_protocol = RTPROT_STATIC; + else + rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) || nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp)) goto nla_put_failure; - if (__ip6mr_fill_mroute(mrt, skb, c, rtm) < 0) + err = __ip6mr_fill_mroute(mrt, skb, c, rtm); + /* do not break the dump if cache is unresolved */ + if (err < 0 && err != -ENOENT) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2236,6 +2284,52 @@ nla_put_failure: return -EMSGSIZE; } +static int mr6_msgsize(bool unresolved, int maxvif) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(4) /* RTA_TABLE */ + + nla_total_size(sizeof(struct in6_addr)) /* RTA_SRC */ + + nla_total_size(sizeof(struct in6_addr)) /* RTA_DST */ + ; + + if (!unresolved) + len = len + + nla_total_size(4) /* RTA_IIF */ + + nla_total_size(0) /* RTA_MULTIPATH */ + + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) + /* RTA_MFC_STATS */ + + nla_total_size(sizeof(struct rta_mfc_stats)) + ; + + return len; +} + +static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, + int cmd) +{ + struct net *net = read_pnet(&mrt->net); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif), + GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + if (err < 0) + goto errout; + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE, NULL, GFP_ATOMIC); + return; + +errout: + kfree_skb(skb); + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); +} + static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2262,13 +2356,29 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc) < 0) + mfc, RTM_NEWROUTE) < 0) goto done; next_entry: e++; } e = s_e = 0; } + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) { + if (e < s_e) + goto next_entry2; + if (ip6mr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + mfc, RTM_NEWROUTE) < 0) { + spin_unlock_bh(&mfc_unres_lock); + goto done; + } +next_entry2: + e++; + } + spin_unlock_bh(&mfc_unres_lock); + e = s_e = 0; s_h = 0; next_table: t++; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ba6d13d1f1e1..ee94d31c9d4d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -343,7 +343,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; case IPV6_TRANSPARENT: - if (valbool && !capable(CAP_NET_ADMIN) && !capable(CAP_NET_RAW)) { + if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) && + !ns_capable(net->user_ns, CAP_NET_RAW)) { retv = -EPERM; break; } @@ -381,7 +382,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, /* hop-by-hop / destination options are privileged option */ retv = -EPERM; - if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW)) + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) break; opt = ipv6_renew_options(sk, np->opt, optname, @@ -397,7 +398,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_RTHDR && opt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = opt->srcrt; switch (rthdr->type) { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) @@ -754,7 +755,7 @@ done: case IPV6_IPSEC_POLICY: case IPV6_XFRM_POLICY: retv = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; retv = xfrm_user_policy(sk, optname, optval, optlen); break; @@ -827,6 +828,7 @@ pref_skip_coa: if (val < 0 || val > 255) goto e_inval; np->min_hopcount = val; + retv = 0; break; case IPV6_DONTFRAG: np->dontfrag = valbool; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 92f8e48e4ba4..28dfa5f3801f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -163,7 +163,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { dev = rt->dst.dev; - dst_release(&rt->dst); + ip6_rt_put(rt); } } else dev = dev_get_by_index_rcu(net, ifindex); @@ -260,7 +260,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, if (rt) { dev = rt->dst.dev; - dst_release(&rt->dst); + ip6_rt_put(rt); } } else dev = dev_get_by_index_rcu(net, ifindex); @@ -284,6 +284,9 @@ void ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); + if (!rcu_access_pointer(np->ipv6_mc_list)) + return; + spin_lock(&ipv6_sk_mc_lock); while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ff36194a71aa..6574175795df 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -151,8 +151,8 @@ static inline int ndisc_opt_addr_space(struct net_device *dev) static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, unsigned short addr_type) { - int space = NDISC_OPT_SPACE(data_len); int pad = ndisc_addr_option_pad(addr_type); + int space = NDISC_OPT_SPACE(data_len + pad); opt[0] = type; opt[1] = space>>3; @@ -370,12 +370,12 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -struct sk_buff *ndisc_build_skb(struct net_device *dev, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, - const struct in6_addr *target, - int llinfo) +static struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; @@ -431,14 +431,11 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, return skb; } -EXPORT_SYMBOL(ndisc_build_skb); - -void ndisc_send_skb(struct sk_buff *skb, - struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h) +static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h) { struct flowi6 fl6; struct dst_entry *dst; @@ -473,8 +470,6 @@ void ndisc_send_skb(struct sk_buff *skb, rcu_read_unlock(); } -EXPORT_SYMBOL(ndisc_send_skb); - /* * Send a Neighbour Discover packet */ @@ -535,7 +530,6 @@ static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; - struct in6_addr mcaddr; idev = in6_dev_get(dev); if (!idev) @@ -543,8 +537,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - addrconf_addr_solict_mult(&ifa->addr, &mcaddr); - ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr, + ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); @@ -906,7 +899,7 @@ static void ndisc_recv_na(struct sk_buff *skb) if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { - /* XXX: idev->cnf.prixy_ndp */ + /* XXX: idev->cnf.proxy_ndp */ goto out; } @@ -1034,18 +1027,6 @@ errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } -static inline int accept_ra(struct inet6_dev *in6_dev) -{ - /* - * If forwarding is enabled, RA are not accepted unless the special - * hybrid mode (accept_ra=2) is enabled. - */ - if (in6_dev->cnf.forwarding && in6_dev->cnf.accept_ra < 2) - return 0; - - return in6_dev->cnf.accept_ra; -} - static void ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); @@ -1093,7 +1074,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - if (!accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) goto skip_linkparms; #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -1145,7 +1126,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - dst_release(&rt->dst); + ip6_rt_put(rt); return; } } @@ -1170,7 +1151,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - dst_release(&rt->dst); + ip6_rt_put(rt); return; } neigh->flags |= NTF_ROUTER; @@ -1249,7 +1230,7 @@ skip_linkparms: NEIGH_UPDATE_F_ISROUTER); } - if (!accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) goto out; #ifdef CONFIG_IPV6_ROUTE_INFO @@ -1326,14 +1307,19 @@ skip_routeinfo: ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: - if (rt) - dst_release(&rt->dst); + ip6_rt_put(rt); if (neigh) neigh_release(neigh); } static void ndisc_redirect_rcv(struct sk_buff *skb) { + u8 *hdr; + struct ndisc_options ndopts; + struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); + u32 ndoptlen = skb->tail - (skb->transport_header + + offsetof(struct rd_msg, opt)); + #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: @@ -1350,6 +1336,17 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) return; } + if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) + return; + + if (!ndopts.nd_opts_rh) + return; + + hdr = (u8 *)ndopts.nd_opts_rh; + hdr += 8; + if (!pskb_pull(skb, hdr - skb_transport_header(skb))) + return; + icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } @@ -1575,11 +1572,18 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct inet6_dev *idev; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(~0UL, net); + idev = in6_dev_get(dev); + if (!idev) + break; + if (idev->cnf.ndisc_notify) + ndisc_send_unsol_na(dev); + in6_dev_put(idev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index d7cb04506c3d..125a90d6a795 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -207,8 +207,7 @@ ip6t_get_target_c(const struct ip6t_entry *e) return ip6t_get_target((struct ip6t_entry *)e); } -#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ - defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* This cries for unification! */ static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", @@ -381,8 +380,7 @@ ip6t_do_table(struct sk_buff *skb, t = ip6t_get_target_c(e); IP_NF_ASSERT(t->u.kernel.target); -#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ - defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(skb, hook, in, out, @@ -1856,7 +1854,7 @@ compat_do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1971,7 +1969,7 @@ compat_do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1993,7 +1991,7 @@ do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -2018,7 +2016,7 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -2273,112 +2271,9 @@ static void __exit ip6_tables_fini(void) unregister_pernet_subsys(&ip6_tables_net_ops); } -/* - * find the offset to specified header or the protocol number of last header - * if target < 0. "last header" is transport protocol header, ESP, or - * "No next header". - * - * Note that *offset is used as input/output parameter. an if it is not zero, - * then it must be a valid offset to an inner IPv6 header. This can be used - * to explore inner IPv6 header, eg. ICMPv6 error messages. - * - * If target header is found, its offset is set in *offset and return protocol - * number. Otherwise, return -1. - * - * If the first fragment doesn't contain the final protocol header or - * NEXTHDR_NONE it is considered invalid. - * - * Note that non-1st fragment is special case that "the protocol number - * of last header" is "next header" field in Fragment header. In this case, - * *offset is meaningless and fragment offset is stored in *fragoff if fragoff - * isn't NULL. - * - * if flags is not NULL and it's a fragment, then the frag flag IP6T_FH_F_FRAG - * will be set. If it's an AH header, the IP6T_FH_F_AUTH flag is set and - * target < 0, then this function will stop at the AH header. - */ -int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, - int target, unsigned short *fragoff, int *flags) -{ - unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - unsigned int len; - - if (fragoff) - *fragoff = 0; - - if (*offset) { - struct ipv6hdr _ip6, *ip6; - - ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); - if (!ip6 || (ip6->version != 6)) { - printk(KERN_ERR "IPv6 header not found\n"); - return -EBADMSG; - } - start = *offset + sizeof(struct ipv6hdr); - nexthdr = ip6->nexthdr; - } - len = skb->len - start; - - while (nexthdr != target) { - struct ipv6_opt_hdr _hdr, *hp; - unsigned int hdrlen; - - if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { - if (target < 0) - break; - return -ENOENT; - } - - hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); - if (hp == NULL) - return -EBADMSG; - if (nexthdr == NEXTHDR_FRAGMENT) { - unsigned short _frag_off; - __be16 *fp; - - if (flags) /* Indicate that this is a fragment */ - *flags |= IP6T_FH_F_FRAG; - fp = skb_header_pointer(skb, - start+offsetof(struct frag_hdr, - frag_off), - sizeof(_frag_off), - &_frag_off); - if (fp == NULL) - return -EBADMSG; - - _frag_off = ntohs(*fp) & ~0x7; - if (_frag_off) { - if (target < 0 && - ((!ipv6_ext_hdr(hp->nexthdr)) || - hp->nexthdr == NEXTHDR_NONE)) { - if (fragoff) - *fragoff = _frag_off; - return hp->nexthdr; - } - return -ENOENT; - } - hdrlen = 8; - } else if (nexthdr == NEXTHDR_AUTH) { - if (flags && (*flags & IP6T_FH_F_AUTH) && (target < 0)) - break; - hdrlen = (hp->hdrlen + 2) << 2; - } else - hdrlen = ipv6_optlen(hp); - - nexthdr = hp->nexthdr; - len -= hdrlen; - start += hdrlen; - } - - *offset = start; - return nexthdr; -} - EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); -EXPORT_SYMBOL(ipv6_find_hdr); module_init(ip6_tables_init); module_exit(ip6_tables_fini); diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c index e9486915eff6..7302b0b7b642 100644 --- a/net/ipv6/netfilter/ip6t_NPT.c +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -14,42 +14,23 @@ #include <linux/netfilter_ipv6/ip6t_NPT.h> #include <linux/netfilter/x_tables.h> -static __sum16 csum16_complement(__sum16 a) -{ - return (__force __sum16)(0xffff - (__force u16)a); -} - -static __sum16 csum16_add(__sum16 a, __sum16 b) -{ - u16 sum; - - sum = (__force u16)a + (__force u16)b; - sum += (__force u16)a < (__force u16)b; - return (__force __sum16)sum; -} - -static __sum16 csum16_sub(__sum16 a, __sum16 b) -{ - return csum16_add(a, csum16_complement(b)); -} - static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) { struct ip6t_npt_tginfo *npt = par->targinfo; - __sum16 src_sum = 0, dst_sum = 0; + __wsum src_sum = 0, dst_sum = 0; unsigned int i; if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64) return -EINVAL; for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) { - src_sum = csum16_add(src_sum, - (__force __sum16)npt->src_pfx.in6.s6_addr16[i]); - dst_sum = csum16_add(dst_sum, - (__force __sum16)npt->dst_pfx.in6.s6_addr16[i]); + src_sum = csum_add(src_sum, + (__force __wsum)npt->src_pfx.in6.s6_addr16[i]); + dst_sum = csum_add(dst_sum, + (__force __wsum)npt->dst_pfx.in6.s6_addr16[i]); } - npt->adjustment = csum16_sub(src_sum, dst_sum); + npt->adjustment = (__force __sum16) csum_sub(src_sum, dst_sum); return 0; } @@ -85,7 +66,7 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, return false; } - sum = csum16_add((__force __sum16)addr->s6_addr16[idx], + sum = (__force __sum16) csum_add((__force __wsum)addr->s6_addr16[idx], npt->adjustment); if (sum == CSUM_MANGLED_0) sum = 0; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index fd4fb34c51c7..029623dbd411 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -132,6 +132,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) ip6h->saddr = oip6h->daddr; ip6h->daddr = oip6h->saddr; + skb_reset_transport_header(nskb); tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ tcph->doff = sizeof(struct tcphdr)/4; diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 5d1d8b04d694..5060d54199ab 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -67,7 +67,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE)) ret = true; out: - dst_release(&rt->dst); + ip6_rt_put(rt); return ret; } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index e418bd6350a4..e0e788d25b14 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -127,19 +127,28 @@ nf_nat_ipv6_fn(unsigned int hooknum, ret = nf_nat_rule_find(skb, hooknum, in, out, ct); if (ret != NF_ACCEPT) return ret; - } else + } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; + } break; default: /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; } return nf_nat_packet(ct, ctinfo, hooknum, skb); + +oif_changed: + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; } static unsigned int @@ -186,7 +195,8 @@ nf_nat_ipv6_out(unsigned int hooknum, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || - (ct->tuplehash[dir].tuple.src.u.all != + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) if (nf_xfrm_me_harder(skb, AF_INET6) < 0) ret = NF_DROP; @@ -222,6 +232,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum, } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) if (nf_xfrm_me_harder(skb, AF_INET6)) @@ -275,9 +286,7 @@ static int __net_init ip6table_nat_net_init(struct net *net) return -ENOMEM; net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_nat)) - return PTR_ERR(net->ipv6.ip6table_nat); - return 0; + return PTR_RET(net->ipv6.ip6table_nat); } static void __net_exit ip6table_nat_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 8860d23e61cf..137e245860ab 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -21,6 +21,7 @@ #include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> @@ -80,8 +81,8 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, } protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off); /* - * (protoff == skb->len) mean that the packet doesn't have no data - * except of IPv6 & ext headers. but it's tracked anyway. - YK + * (protoff == skb->len) means the packet has not data, just + * IPv6 and possibly extensions headers, but it is tracked anyway */ if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("ip6_conntrack_core: can't find proto in pkt\n"); @@ -295,7 +296,56 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { }, }; -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +static int +ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *inet6 = inet6_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct sockaddr_in6 sin6; + struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; + struct nf_conn *ct; + + tuple.src.u3.in6 = inet6->rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.in6 = inet6->daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.dst.protonum = sk->sk_protocol; + + if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP) + return -ENOPROTOOPT; + + if (*len < 0 || (unsigned int) *len < sizeof(sin6)) + return -EINVAL; + + h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); + if (!h) { + pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", + &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; + } + + ct = nf_ct_tuplehash_to_ctrack(h); + + sin6.sin6_family = AF_INET6; + sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; + sin6.sin6_flowinfo = inet6->flow_label & IPV6_FLOWINFO_MASK; + memcpy(&sin6.sin6_addr, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, + sizeof(sin6.sin6_addr)); + + nf_ct_put(ct); + + if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) + sin6.sin6_scope_id = sk->sk_bound_dev_if; + else + sin6.sin6_scope_id = 0; + + return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> @@ -346,7 +396,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { .invert_tuple = ipv6_invert_tuple, .print_tuple = ipv6_print_tuple, .get_l4proto = ipv6_get_l4proto, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = ipv6_tuple_to_nlattr, .nlattr_tuple_size = ipv6_nlattr_tuple_size, .nlattr_to_tuple = ipv6_nlattr_to_tuple, @@ -359,6 +409,14 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); +static struct nf_sockopt_ops so_getorigdst6 = { + .pf = NFPROTO_IPV6, + .get_optmin = IP6T_SO_ORIGINAL_DST, + .get_optmax = IP6T_SO_ORIGINAL_DST + 1, + .get = ipv6_getorigdst, + .owner = THIS_MODULE, +}; + static int ipv6_net_init(struct net *net) { int ret = 0; @@ -425,6 +483,12 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) need_conntrack(); nf_defrag_ipv6_enable(); + ret = nf_register_sockopt(&so_getorigdst6); + if (ret < 0) { + pr_err("Unable to register netfilter socket option\n"); + return ret; + } + ret = register_pernet_subsys(&ipv6_net_ops); if (ret < 0) goto cleanup_pernet; @@ -440,6 +504,7 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) cleanup_ipv6: unregister_pernet_subsys(&ipv6_net_ops); cleanup_pernet: + nf_unregister_sockopt(&so_getorigdst6); return ret; } @@ -448,6 +513,7 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void) synchronize_net(); nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); unregister_pernet_subsys(&ipv6_net_ops); + nf_unregister_sockopt(&so_getorigdst6); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 2d54b2061d68..24df3dde0076 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -232,7 +232,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum); } -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> @@ -375,7 +375,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = .get_timeouts = icmpv6_get_timeouts, .new = icmpv6_new, .error = icmpv6_error, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, .nlattr_tuple_size = icmpv6_nlattr_tuple_size, .nlattr_to_tuple = icmpv6_nlattr_to_tuple, diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 18bd9bbbd1c6..3dacecc99065 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -85,7 +85,7 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { { } }; -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -127,7 +127,7 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) } #else -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { return 0; } @@ -311,7 +311,10 @@ found: else fq->q.fragments = skb; - skb->dev = NULL; + if (skb->dev) { + fq->iif = skb->dev->ifindex; + skb->dev = NULL; + } fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; if (payload_len > fq->q.max_size) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index cdd6d045e42e..aacd121fe8c5 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -19,7 +19,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> @@ -35,7 +35,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, { u16 zone = NF_CT_DEFAULT_ZONE; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) if (skb->nfct) zone = nf_ct_zone((struct nf_conn *)skb->nfct); #endif @@ -60,7 +60,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, { struct sk_buff *reasm; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Previously seen (loopback)? */ if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) return NF_ACCEPT; diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 5d6da784305b..61aaf70f376e 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -84,7 +84,7 @@ const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = { .manip_pkt = icmpv6_manip_pkt, .in_range = icmpv6_in_range, .unique_tuple = icmpv6_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c new file mode 100644 index 000000000000..c2e73e647e44 --- /dev/null +++ b/net/ipv6/output_core.c @@ -0,0 +1,76 @@ +/* + * IPv6 library code, needed by static components when full IPv6 support is + * not configured or static. These functions are needed by GSO/GRO implementation. + */ +#include <linux/export.h> +#include <net/ipv6.h> +#include <net/ip6_fib.h> + +void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static atomic_t ipv6_fragmentation_id; + int old, new; + +#if IS_ENABLED(CONFIG_IPV6) + if (rt && !(rt->dst.flags & DST_NOPEER)) { + struct inet_peer *peer; + struct net *net; + + net = dev_net(rt->dst.dev); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + if (peer) { + fhdr->identification = htonl(inet_getid(peer, 0)); + inet_putpeer(peer); + return; + } + } +#endif + do { + old = atomic_read(&ipv6_fragmentation_id); + new = old + 1; + if (!new) + new = 1; + } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); + fhdr->identification = htonl(new); +} +EXPORT_SYMBOL(ipv6_select_ident); + +int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = + (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + unsigned int packet_len = skb->tail - skb->network_header; + int found_rhdr = 0; + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + found_rhdr = 1; + break; + case NEXTHDR_DEST: +#if IS_ENABLED(CONFIG_IPV6_MIP6) + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) + break; +#endif + if (found_rhdr) + return offset; + break; + default : + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); + } + + return offset; +} +EXPORT_SYMBOL(ip6_find_1stfragopt); diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 053082dfc93e..22d1bd4670da 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -25,7 +25,9 @@ #include <linux/spinlock.h> #include <net/protocol.h> +#if IS_ENABLED(CONFIG_IPV6) const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; +EXPORT_SYMBOL(inet6_protos); int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { @@ -50,3 +52,26 @@ int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol return ret; } EXPORT_SYMBOL(inet6_del_protocol); +#endif + +const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly; + +int inet6_add_offload(const struct net_offload *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet6_add_offload); + +int inet6_del_offload(const struct net_offload *prot, unsigned char protocol) +{ + int ret; + + ret = (cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + prot, NULL) == prot) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet6_del_offload); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d8e95c77db99..6cd29b1e8b92 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -50,7 +50,7 @@ #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> @@ -123,7 +123,7 @@ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) return 1; } -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; @@ -184,7 +184,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) filtered = icmpv6_filter(sk, skb); break; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index da8a4e301b1b..e5253ec9e0fc 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -616,6 +616,10 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) table[0].data = &net->ipv6.frags.high_thresh; table[1].data = &net->ipv6.frags.low_thresh; table[2].data = &net->ipv6.frags.timeout; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } hdr = register_net_sysctl(net, "net/ipv6", table); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b1e6cf0b95fd..e229a3bc345d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -57,6 +57,7 @@ #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> +#include <net/nexthop.h> #include <asm/uaccess.h> @@ -289,6 +290,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); rt->rt6i_genid = rt_genid(net); + INIT_LIST_HEAD(&rt->rt6i_siblings); + rt->rt6i_nsiblings = 0; } return rt; } @@ -318,13 +321,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } -static atomic_t __rt6_peer_genid = ATOMIC_INIT(0); - -static u32 rt6_peer_genid(void) -{ - return atomic_read(&__rt6_peer_genid); -} - void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer_base *base; @@ -338,8 +334,6 @@ void rt6_bind_peer(struct rt6_info *rt, int create) if (peer) { if (!rt6_set_peer(rt, peer)) inet_putpeer(peer); - else - rt->rt6i_peer_genid = rt6_peer_genid(); } } @@ -385,6 +379,69 @@ static bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +/* Multipath route selection: + * Hash based function using packet header and flowlabel. + * Adapted from fib_info_hashfn() + */ +static int rt6_info_hash_nhsfn(unsigned int candidate_count, + const struct flowi6 *fl6) +{ + unsigned int val = fl6->flowi6_proto; + + val ^= (__force u32)fl6->daddr.s6_addr32[0]; + val ^= (__force u32)fl6->daddr.s6_addr32[1]; + val ^= (__force u32)fl6->daddr.s6_addr32[2]; + val ^= (__force u32)fl6->daddr.s6_addr32[3]; + + val ^= (__force u32)fl6->saddr.s6_addr32[0]; + val ^= (__force u32)fl6->saddr.s6_addr32[1]; + val ^= (__force u32)fl6->saddr.s6_addr32[2]; + val ^= (__force u32)fl6->saddr.s6_addr32[3]; + + /* Work only if this not encapsulated */ + switch (fl6->flowi6_proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_SCTP: + val ^= (__force u16)fl6->fl6_sport; + val ^= (__force u16)fl6->fl6_dport; + break; + + case IPPROTO_ICMPV6: + val ^= (__force u16)fl6->fl6_icmp_type; + val ^= (__force u16)fl6->fl6_icmp_code; + break; + } + /* RFC6438 recommands to use flowlabel */ + val ^= (__force u32)fl6->flowlabel; + + /* Perhaps, we need to tune, this function? */ + val = val ^ (val >> 7) ^ (val >> 12); + return val % candidate_count; +} + +static struct rt6_info *rt6_multipath_select(struct rt6_info *match, + struct flowi6 *fl6) +{ + struct rt6_info *sibling, *next_sibling; + int route_choosen; + + route_choosen = rt6_info_hash_nhsfn(match->rt6i_nsiblings + 1, fl6); + /* Don't change the route, if route_choosen == 0 + * (siblings does not include ourself) + */ + if (route_choosen) + list_for_each_entry_safe(sibling, next_sibling, + &match->rt6i_siblings, rt6i_siblings) { + route_choosen--; + if (route_choosen == 0) { + match = sibling; + break; + } + } + return match; +} + /* * Route lookup. Any table->tb6_lock is implied. */ @@ -487,35 +544,32 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) return 0; } -static inline int rt6_check_neigh(struct rt6_info *rt) +static inline bool rt6_check_neigh(struct rt6_info *rt) { struct neighbour *neigh; - int m; + bool ret = false; neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - m = 1; + ret = true; else if (neigh) { read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) - m = 2; + ret = true; #ifdef CONFIG_IPV6_ROUTER_PREF - else if (neigh->nud_state & NUD_FAILED) - m = 0; + else if (!(neigh->nud_state & NUD_FAILED)) + ret = true; #endif - else - m = 1; read_unlock_bh(&neigh->lock); - } else - m = 0; - return m; + } + return ret; } static int rt6_score_route(struct rt6_info *rt, int oif, int strict) { - int m, n; + int m; m = rt6_check_dev(rt, oif); if (!m && (strict & RT6_LOOKUP_F_IFACE)) @@ -523,8 +577,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif - n = rt6_check_neigh(rt); - if (!n && (strict & RT6_LOOKUP_F_REACHABLE)) + if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE)) return -1; return m; } @@ -666,7 +719,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, else rt6_set_expires(rt, jiffies + HZ * lifetime); - dst_release(&rt->dst); + ip6_rt_put(rt); } return 0; } @@ -702,6 +755,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, restart: rt = fn->leaf; rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); + if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) + rt = rt6_multipath_select(rt, fl6); BACKTRACK(net, &fl6->saddr); out: dst_use(&rt->dst, jiffies); @@ -863,7 +918,8 @@ restart_2: restart: rt = rt6_select(fn, oif, strict | reachable); - + if (rt->rt6i_nsiblings && oif == 0) + rt = rt6_multipath_select(rt, fl6); BACKTRACK(net, &fl6->saddr); if (rt == net->ipv6.ip6_null_entry || rt->rt6i_flags & RTF_CACHE) @@ -879,7 +935,7 @@ restart: else goto out2; - dst_release(&rt->dst); + ip6_rt_put(rt); rt = nrt ? : net->ipv6.ip6_null_entry; dst_hold(&rt->dst); @@ -896,7 +952,7 @@ restart: * Race condition! In the gap, when table->tb6_lock was * released someone could insert this route. Relookup. */ - dst_release(&rt->dst); + ip6_rt_put(rt); goto relookup; out: @@ -1030,14 +1086,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { - if (rt->rt6i_peer_genid != rt6_peer_genid()) { - if (!rt6_has_peer(rt)) - rt6_bind_peer(rt, 0); - rt->rt6i_peer_genid = rt6_peer_genid(); - } + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) return dst; - } + return NULL; } @@ -1316,12 +1367,6 @@ out: return entries > rt_max_size; } -/* Clean host part of a prefix. Not necessary in radix tree, - but results in cleaner routing tables. - - Remove it only when all the things will work! - */ - int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); @@ -1507,7 +1552,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; if (dev) { if (dev != grt->dst.dev) { - dst_release(&grt->dst); + ip6_rt_put(grt); goto out; } } else { @@ -1518,7 +1563,7 @@ int ip6_route_add(struct fib6_config *cfg) } if (!(grt->rt6i_flags & RTF_GATEWAY)) err = 0; - dst_release(&grt->dst); + ip6_rt_put(grt); if (err) goto out; @@ -1604,7 +1649,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) write_unlock_bh(&table->tb6_lock); out: - dst_release(&rt->dst); + ip6_rt_put(rt); return err; } @@ -1987,7 +2032,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch(cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = copy_from_user(&rtmsg, arg, sizeof(struct in6_rtmsg)); @@ -2249,6 +2294,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2326,11 +2372,71 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); + if (tb[RTA_MULTIPATH]) { + cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); + cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); + } + err = 0; errout: return err; } +static int ip6_route_multipath(struct fib6_config *cfg, int add) +{ + struct fib6_config r_cfg; + struct rtnexthop *rtnh; + int remaining; + int attrlen; + int err = 0, last_err = 0; + +beginning: + rtnh = (struct rtnexthop *)cfg->fc_mp; + remaining = cfg->fc_mp_len; + + /* Parse a Multipath Entry */ + while (rtnh_ok(rtnh, remaining)) { + memcpy(&r_cfg, cfg, sizeof(*cfg)); + if (rtnh->rtnh_ifindex) + r_cfg.fc_ifindex = rtnh->rtnh_ifindex; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla) { + nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_flags |= RTF_GATEWAY; + } + } + err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); + if (err) { + last_err = err; + /* If we are trying to remove a route, do not stop the + * loop when ip6_route_del() fails (because next hop is + * already gone), we should try to remove all next hops. + */ + if (add) { + /* If add fails, we should try to delete all + * next hops that have been already added. + */ + add = 0; + goto beginning; + } + } + /* Because each route is added like a single route we remove + * this flag after the first nexthop (if there is a collision, + * we have already fail to add the first nexthop: + * fib6_add_rt2node() has reject it). + */ + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL; + rtnh = rtnh_next(rtnh, &remaining); + } + + return last_err; +} + static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct fib6_config cfg; @@ -2340,7 +2446,10 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a if (err < 0) return err; - return ip6_route_del(&cfg); + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 0); + else + return ip6_route_del(&cfg); } static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) @@ -2352,7 +2461,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a if (err < 0) return err; - return ip6_route_add(&cfg); + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 1); + else + return ip6_route_add(&cfg); } static inline size_t rt6_nlmsg_size(void) @@ -2596,7 +2708,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { - dst_release(&rt->dst); + ip6_rt_put(rt); err = -ENOBUFS; goto errout; } @@ -2873,6 +2985,10 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } return table; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3ed54ffd8d50..cfba99b2c2a4 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -65,9 +65,14 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); +static struct rtnl_link_ops sit_link_ops __read_mostly; static int sit_net_id __read_mostly; struct sit_net { @@ -80,22 +85,6 @@ struct sit_net { struct net_device *fb_tunnel_dev; }; -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; - static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) { @@ -121,6 +110,7 @@ static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev, } tot->rx_errors = dev->stats.rx_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; tot->tx_fifo_errors = dev->stats.tx_fifo_errors; tot->tx_carrier_errors = dev->stats.tx_carrier_errors; tot->tx_dropped = dev->stats.tx_dropped; @@ -141,20 +131,20 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); - for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) @@ -231,6 +221,37 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) #endif } +static int ipip6_tunnel_create(struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + int err; + + err = ipip6_tunnel_init(dev); + if (err < 0) + goto out; + ipip6_tunnel_clone_6rd(dev, sitn); + + if ((__force u16)t->parms.i_flags & SIT_ISATAP) + dev->priv_flags |= IFF_ISATAP; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &sit_link_ops; + + dev_hold(dev); + + ipip6_tunnel_link(sitn, t); + return 0; + +out: + return err; +} + static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { @@ -271,21 +292,9 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - if (ipip6_tunnel_init(dev) < 0) + if (ipip6_tunnel_create(dev) < 0) goto failed_free; - ipip6_tunnel_clone_6rd(dev, sitn); - if (parms->i_flags & SIT_ISATAP) - dev->priv_flags |= IFF_ISATAP; - - if (register_netdevice(dev) < 0) - goto failed_free; - - strcpy(nt->parms.name, dev->name); - - dev_hold(dev); - - ipip6_tunnel_link(sitn, nt); return nt; failed_free: @@ -581,16 +590,11 @@ out: return err; } -static inline void ipip6_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb) -{ - if (INET_ECN_is_ce(iph->tos)) - IP6_ECN_set_ce(ipv6_hdr(skb)); -} - static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph; struct ip_tunnel *tunnel; + int err; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; @@ -612,18 +616,27 @@ static int ipip6_rcv(struct sk_buff *skb) if ((tunnel->dev->priv_flags & IFF_ISATAP) && !isatap_chksrc(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; - kfree_skb(skb); - return 0; + goto out; + } + + __skb_tunnel_rx(skb, tunnel->dev); + + err = IP_ECN_decapsulate(iph, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &iph->saddr, iph->tos); + if (err > 1) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto out; + } } tstats = this_cpu_ptr(tunnel->dev->tstats); tstats->rx_packets++; tstats->rx_bytes += skb->len; - __skb_tunnel_rx(skb, tunnel->dev); - - ipip6_ecn_decapsulate(iph, skb); - netif_rx(skb); return 0; @@ -683,7 +696,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; const struct iphdr *tiph = &tunnel->parms.iph; const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; @@ -864,9 +876,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if ((iph->ttl = tiph->ttl) == 0) iph->ttl = iph6->hop_limit; - nf_reset(skb); - tstats = this_cpu_ptr(dev->tstats); - __IPTUNNEL_XMIT(tstats, &dev->stats); + iptunnel_xmit(skb, dev); return NETDEV_TX_OK; tx_error_icmp: @@ -914,6 +924,59 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) dev->iflink = tunnel->parms.link; } +static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) +{ + struct net *net = dev_net(t->dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + ipip6_tunnel_unlink(sitn, t); + synchronize_net(); + t->parms.iph.saddr = p->iph.saddr; + t->parms.iph.daddr = p->iph.daddr; + memcpy(t->dev->dev_addr, &p->iph.saddr, 4); + memcpy(t->dev->broadcast, &p->iph.daddr, 4); + ipip6_tunnel_link(sitn, t); + t->parms.iph.ttl = p->iph.ttl; + t->parms.iph.tos = p->iph.tos; + if (t->parms.link != p->link) { + t->parms.link = p->link; + ipip6_tunnel_bind_dev(t->dev); + } + netdev_state_change(t->dev); +} + +#ifdef CONFIG_IPV6_SIT_6RD +static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, + struct ip_tunnel_6rd *ip6rd) +{ + struct in6_addr prefix; + __be32 relay_prefix; + + if (ip6rd->relay_prefixlen > 32 || + ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) + return -EINVAL; + + ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); + if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) + return -EINVAL; + if (ip6rd->relay_prefixlen) + relay_prefix = ip6rd->relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd->relay_prefixlen)); + else + relay_prefix = 0; + if (relay_prefix != ip6rd->relay_prefix) + return -EINVAL; + + t->ip6rd.prefix = prefix; + t->ip6rd.relay_prefix = relay_prefix; + t->ip6rd.prefixlen = ip6rd->prefixlen; + t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + netdev_state_change(t->dev); + return 0; +} +#endif + static int ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -966,7 +1029,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -995,28 +1058,13 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } t = netdev_priv(dev); - ipip6_tunnel_unlink(sitn, t); - synchronize_net(); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - ipip6_tunnel_link(sitn, t); - netdev_state_change(dev); } + + ipip6_tunnel_update(t, &p); } if (t) { err = 0; - if (cmd == SIOCCHGTUNNEL) { - t->parms.iph.ttl = p.iph.ttl; - t->parms.iph.tos = p.iph.tos; - if (t->parms.link != p.link) { - t->parms.link = p.link; - ipip6_tunnel_bind_dev(dev); - netdev_state_change(dev); - } - } if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p))) err = -EFAULT; } else @@ -1025,7 +1073,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == sitn->fb_tunnel_dev) { @@ -1058,7 +1106,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELPRL: case SIOCCHGPRL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EINVAL; if (dev == sitn->fb_tunnel_dev) @@ -1087,7 +1135,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCCHG6RD: case SIOCDEL6RD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1098,31 +1146,9 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) t = netdev_priv(dev); if (cmd != SIOCDEL6RD) { - struct in6_addr prefix; - __be32 relay_prefix; - - err = -EINVAL; - if (ip6rd.relay_prefixlen > 32 || - ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64) - goto done; - - ipv6_addr_prefix(&prefix, &ip6rd.prefix, - ip6rd.prefixlen); - if (!ipv6_addr_equal(&prefix, &ip6rd.prefix)) - goto done; - if (ip6rd.relay_prefixlen) - relay_prefix = ip6rd.relay_prefix & - htonl(0xffffffffUL << - (32 - ip6rd.relay_prefixlen)); - else - relay_prefix = 0; - if (relay_prefix != ip6rd.relay_prefix) + err = ipip6_tunnel_update_6rd(t, &ip6rd); + if (err < 0) goto done; - - t->ip6rd.prefix = prefix; - t->ip6rd.relay_prefix = relay_prefix; - t->ip6rd.prefixlen = ip6rd.prefixlen; - t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; } else ipip6_tunnel_clone_6rd(dev, sitn); @@ -1216,6 +1242,239 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) return 0; } +static void ipip6_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.version = 4; + parms->iph.protocol = IPPROTO_IPV6; + parms->iph.ihl = 5; + parms->iph.ttl = 64; + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); + + if (data[IFLA_IPTUN_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); + + if (data[IFLA_IPTUN_TTL]) { + parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); + if (parms->iph.ttl) + parms->iph.frag_off = htons(IP_DF); + } + + if (data[IFLA_IPTUN_TOS]) + parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); + + if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) + parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_IPTUN_FLAGS]) + parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); +} + +#ifdef CONFIG_IPV6_SIT_6RD +/* This function returns true when 6RD attributes are present in the nl msg */ +static bool ipip6_netlink_6rd_parms(struct nlattr *data[], + struct ip_tunnel_6rd *ip6rd) +{ + bool ret = false; + memset(ip6rd, 0, sizeof(*ip6rd)); + + if (!data) + return ret; + + if (data[IFLA_IPTUN_6RD_PREFIX]) { + ret = true; + nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX], + sizeof(struct in6_addr)); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { + ret = true; + ip6rd->relay_prefix = + nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); + } + + if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { + ret = true; + ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { + ret = true; + ip6rd->relay_prefixlen = + nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); + } + + return ret; +} +#endif + +static int ipip6_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip_tunnel *nt; +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + int err; + + nt = netdev_priv(dev); + ipip6_netlink_parms(data, &nt->parms); + + if (ipip6_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + err = ipip6_tunnel_create(dev); + if (err < 0) + return err; + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + err = ipip6_tunnel_update_6rd(nt, &ip6rd); +#endif + + return err; +} + +static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip_tunnel *t; + struct ip_tunnel_parm p; + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + + if (dev == sitn->fb_tunnel_dev) + return -EINVAL; + + ipip6_netlink_parms(data, &p); + + if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || + (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) + return -EINVAL; + + t = ipip6_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + ipip6_tunnel_update(t, &p); + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + return ipip6_tunnel_update_6rd(t, &ip6rd); +#endif + + return 0; +} + +static size_t ipip6_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(4) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(4) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_TOS */ + nla_total_size(1) + + /* IFLA_IPTUN_PMTUDISC */ + nla_total_size(1) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(2) + +#ifdef CONFIG_IPV6_SIT_6RD + /* IFLA_IPTUN_6RD_PREFIX */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ + nla_total_size(4) + + /* IFLA_IPTUN_6RD_PREFIXLEN */ + nla_total_size(2) + + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ + nla_total_size(2) + +#endif + 0; +} + +static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct ip_tunnel_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || + nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || + nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, + !!(parm->iph.frag_off & htons(IP_DF))) || + nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags)) + goto nla_put_failure; + +#ifdef CONFIG_IPV6_SIT_6RD + if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr), + &tunnel->ip6rd.prefix) || + nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, + tunnel->ip6rd.relay_prefix) || + nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, + tunnel->ip6rd.prefixlen) || + nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, + tunnel->ip6rd.relay_prefixlen)) + goto nla_put_failure; +#endif + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, + [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, + [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, +#ifdef CONFIG_IPV6_SIT_6RD + [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, + [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, + [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, +#endif +}; + +static struct rtnl_link_ops sit_link_ops __read_mostly = { + .kind = "sit", + .maxtype = IFLA_IPTUN_MAX, + .policy = ipip6_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = ipip6_tunnel_setup, + .newlink = ipip6_newlink, + .changelink = ipip6_changelink, + .get_size = ipip6_get_size, + .fill_info = ipip6_fill_info, +}; + static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, @@ -1302,6 +1561,7 @@ static struct pernet_operations sit_net_ops = { static void __exit sit_cleanup(void) { + rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); unregister_pernet_device(&sit_net_ops); @@ -1319,10 +1579,21 @@ static int __init sit_init(void) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { - unregister_pernet_device(&sit_net_ops); pr_info("%s: can't add protocol\n", __func__); + goto xfrm_tunnel_failed; } + err = rtnl_link_register(&sit_link_ops); + if (err < 0) + goto rtnl_link_failed; + +out: return err; + +rtnl_link_failed: + xfrm4_tunnel_deregister(&sit_handler, AF_INET6); +xfrm_tunnel_failed: + unregister_pernet_device(&sit_net_ops); + goto out; } module_init(sit_init); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 182ab9a85d6c..40161977f7cf 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -214,7 +214,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq6->iif = inet6_iif(skb); req->expires = 0UL; - req->retrans = 0; + req->num_retrans = 0; ireq->ecn_ok = ecn_ok; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 26175bffbaa0..93825dd3a7c0 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -77,9 +77,6 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -static void __tcp_v6_send_check(struct sk_buff *skb, - const struct in6_addr *saddr, - const struct in6_addr *daddr); static const struct inet_connection_sock_af_ops ipv6_mapped; static const struct inet_connection_sock_af_ops ipv6_specific; @@ -119,14 +116,6 @@ static void tcp_v6_hash(struct sock *sk) } } -static __inline__ __sum16 tcp_v6_check(int len, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - __wsum base) -{ - return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); -} - static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, @@ -306,7 +295,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (err) goto late_failure; - if (!tp->write_seq) + if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, np->daddr.s6_addr32, inet->inet_sport, @@ -495,9 +484,12 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { struct flowi6 fl6; + int res; - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0); + res = tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0); + if (!res) + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return res; } static void tcp_v6_reqsk_destructor(struct request_sock *req) @@ -719,94 +711,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { }; #endif -static void __tcp_v6_send_check(struct sk_buff *skb, - const struct in6_addr *saddr, const struct in6_addr *daddr) -{ - struct tcphdr *th = tcp_hdr(skb); - - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = tcp_v6_check(skb->len, saddr, daddr, - csum_partial(th, th->doff << 2, - skb->csum)); - } -} - -static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - - __tcp_v6_send_check(skb, &np->saddr, &np->daddr); -} - -static int tcp_v6_gso_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct tcphdr *th; - - if (!pskb_may_pull(skb, sizeof(*th))) - return -EINVAL; - - ipv6h = ipv6_hdr(skb); - th = tcp_hdr(skb); - - th->check = 0; - skb->ip_summed = CHECKSUM_PARTIAL; - __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); - return 0; -} - -static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) -{ - const struct ipv6hdr *iph = skb_gro_network_header(skb); - __wsum wsum; - __sum16 sum; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } -flush: - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - - case CHECKSUM_NONE: - wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), - IPPROTO_TCP, 0)); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } - - return tcp_gro_receive(head, skb); -} - -static int tcp6_gro_complete(struct sk_buff *skb) -{ - const struct ipv6hdr *iph = ipv6_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); - - th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), - &iph->saddr, &iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - - return tcp_gro_complete(skb); -} - static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, struct tcp_md5sig_key *key, int rst, u8 tclass) { @@ -1364,7 +1268,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_initialize_rcv_mss(newsk); tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->retrans; + newtp->total_retrans = req->num_retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; @@ -1384,7 +1288,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #endif if (__inet_inherit_port(sk, newsk) < 0) { - sock_put(newsk); + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); goto out; } __inet6_hash(newsk, NULL); @@ -1741,11 +1646,11 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { struct dst_entry *dst = sk->sk_rx_dst; - struct inet_sock *icsk = inet_sk(sk); + if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); if (dst && - icsk->rx_dst_ifindex == skb->skb_iif) + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } @@ -1866,7 +1771,7 @@ static void get_openreq6(struct seq_file *seq, 0,0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), - req->retrans, + req->num_timeout, from_kuid_munged(seq_user_ns(seq), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ @@ -2063,10 +1968,6 @@ static const struct inet6_protocol tcpv6_protocol = { .early_demux = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, - .gso_send_check = tcp_v6_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; @@ -2121,10 +2022,10 @@ int __init tcpv6_init(void) out: return ret; -out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); +out_tcpv6_protocol: + inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); goto out; } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c new file mode 100644 index 000000000000..2ec6bf6a0aa0 --- /dev/null +++ b/net/ipv6/tcpv6_offload.c @@ -0,0 +1,95 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * TCPv6 GSO/GRO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/tcp.h> +#include <net/ip6_checksum.h> +#include "ip6_offload.h" + +static int tcp_v6_gso_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + struct tcphdr *th; + + if (!pskb_may_pull(skb, sizeof(*th))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + th = tcp_hdr(skb); + + th->check = 0; + skb->ip_summed = CHECKSUM_PARTIAL; + __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); + return 0; +} + +static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + __wsum wsum; + __sum16 sum; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, + skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } +flush: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + + case CHECKSUM_NONE: + wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), + IPPROTO_TCP, 0)); + sum = csum_fold(skb_checksum(skb, + skb_gro_offset(skb), + skb_gro_len(skb), + wsum)); + if (sum) + goto flush; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + + return tcp_gro_receive(head, skb); +} + +static int tcp6_gro_complete(struct sk_buff *skb) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), + &iph->saddr, &iph->daddr, 0); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + + return tcp_gro_complete(skb); +} + +static const struct net_offload tcpv6_offload = { + .callbacks = { + .gso_send_check = tcp_v6_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, +}; + +int __init tcpv6_offload_init(void) +{ + return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); +} diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fc9997260a6b..dfaa29b8b293 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1343,103 +1343,9 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif -static int udp6_ufo_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct udphdr *uh; - - if (!pskb_may_pull(skb, sizeof(*uh))) - return -EINVAL; - - ipv6h = ipv6_hdr(skb); - uh = udp_hdr(skb); - - uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, - IPPROTO_UDP, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct udphdr, check); - skb->ip_summed = CHECKSUM_PARTIAL; - return 0; -} - -static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - unsigned int mss; - unsigned int unfrag_ip6hlen, unfrag_len; - struct frag_hdr *fptr; - u8 *mac_start, *prevhdr; - u8 nexthdr; - u8 frag_hdr_sz = sizeof(struct frag_hdr); - int offset; - __wsum csum; - - mss = skb_shinfo(skb)->gso_size; - if (unlikely(skb->len <= mss)) - goto out; - - if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { - /* Packet is from an untrusted source, reset gso_segs. */ - int type = skb_shinfo(skb)->gso_type; - - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || - !(type & (SKB_GSO_UDP)))) - goto out; - - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); - - segs = NULL; - goto out; - } - - /* Do software UFO. Complete and fill in the UDP checksum as HW cannot - * do checksum of UDP packets sent as multiple IP fragments. - */ - offset = skb_checksum_start_offset(skb); - csum = skb_checksum(skb, offset, skb->len - offset, 0); - offset += skb->csum_offset; - *(__sum16 *)(skb->data + offset) = csum_fold(csum); - skb->ip_summed = CHECKSUM_NONE; - - /* Check if there is enough headroom to insert fragment header. */ - if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && - pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) - goto out; - - /* Find the unfragmentable header and shift it left by frag_hdr_sz - * bytes to insert fragment header. - */ - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - nexthdr = *prevhdr; - *prevhdr = NEXTHDR_FRAGMENT; - unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + - unfrag_ip6hlen; - mac_start = skb_mac_header(skb); - memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); - - skb->mac_header -= frag_hdr_sz; - skb->network_header -= frag_hdr_sz; - - fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); - fptr->nexthdr = nexthdr; - fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); - - /* Fragment the skb. ipv6 header and the remaining fields of the - * fragment header are updated in ipv6_gso_segment() - */ - segs = skb_segment(skb, features); - -out: - return segs; -} - static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, - .gso_send_check = udp6_ufo_send_check, - .gso_segment = udp6_ufo_fragment, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c new file mode 100644 index 000000000000..0c8934a317c2 --- /dev/null +++ b/net/ipv6/udp_offload.c @@ -0,0 +1,120 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * UDPv6 GSO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> +#include "ip6_offload.h" + +static int udp6_ufo_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(*uh))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + return 0; +} + +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *mac_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + int offset; + __wsum csum; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + goto out; + } + + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb_checksum_start_offset(skb); + csum = skb_checksum(skb, offset, skb->len - offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && + pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) + goto out; + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + + unfrag_ip6hlen; + mac_start = skb_mac_header(skb); + memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); + + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + +out: + return segs; +} +static const struct net_offload udpv6_offload = { + .callbacks = { + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, + }, +}; + +int __init udp_offload_init(void) +{ + return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); +} diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f8c4c08ffb60..c9844135c9ca 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -20,7 +20,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif @@ -182,7 +182,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) fl6->flowi6_proto = nexthdr; return; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { struct ip6_mh *mh; @@ -327,21 +327,7 @@ static struct ctl_table_header *sysctl_hdr; int __init xfrm6_init(void) { int ret; - unsigned int gc_thresh; - - /* - * We need a good default value for the xfrm6 gc threshold. - * In ipv4 we set it to the route hash table size * 8, which - * is half the size of the maximaum route cache for ipv4. It - * would be good to do the same thing for v6, except the table is - * constructed differently here. Here each table for a net namespace - * can have FIB_TABLE_HASHSZ entries, so lets go with the same - * computation that we used for ipv4 here. Also, lets keep the initial - * gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults - * to that as a minimum as well - */ - gc_thresh = FIB6_TABLE_HASHSZ * 8; - xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; + dst_entries_init(&xfrm6_dst_ops); ret = xfrm6_policy_init(); @@ -370,7 +356,6 @@ void xfrm6_fini(void) if (sysctl_hdr) unregister_net_sysctl_table(sysctl_hdr); #endif - //xfrm6_input_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); dst_entries_destroy(&xfrm6_dst_ops); diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 3f2f7c4ab721..d8c70b8efc24 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -101,7 +101,7 @@ static int __xfrm6_state_sort_cmp(void *p) return 1; else return 3; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; @@ -134,7 +134,7 @@ static int __xfrm6_tmpl_sort_cmp(void *p) switch (v->mode) { case XFRM_MODE_TRANSPORT: return 1; -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) +#if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 496ce2cebcd7..a68c88cdec6e 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -183,6 +183,7 @@ static void __exit __ircomm_tty_cleanup(struct ircomm_tty_cb *self) ircomm_tty_shutdown(self); self->magic = 0; + tty_port_destroy(&self->port); kfree(self); } diff --git a/net/irda/irttp.c b/net/irda/irttp.c index 1002e3396f72..ae43c62f9045 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -441,6 +441,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify) lsap = irlmp_open_lsap(stsap_sel, &ttp_notify, 0); if (lsap == NULL) { IRDA_DEBUG(0, "%s: unable to allocate LSAP!!\n", __func__); + __irttp_close_tsap(self); return NULL; } diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 3ad1f9db5f8b..df082508362d 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1806,7 +1806,7 @@ static void iucv_external_interrupt(struct ext_code ext_code, struct iucv_irq_data *p; struct iucv_irq_list *work; - kstat_cpu(smp_processor_id()).irqs[EXTINT_IUC]++; + inc_irq_stat(IRQEXT_IUC); p = iucv_irq_data[smp_processor_id()]; if (p->ippathid >= iucv_max_pathid) { WARN_ON(p->ippathid >= iucv_max_pathid); diff --git a/net/key/af_key.c b/net/key/af_key.c index 08897a3c7ec7..5b426a646544 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -141,7 +141,7 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 37b8b8ba31f7..76125c57ee6d 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -291,6 +291,7 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p out_del_dev: free_netdev(dev); + spriv->dev = NULL; out_del_session: l2tp_session_delete(session); out: diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 6c4cc12c7414..bbba3a19e944 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -632,7 +632,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl nla_put_u16(skb, L2TP_ATTR_MRU, session->mru))) goto nla_put_failure; - if ((session->ifname && session->ifname[0] && + if ((session->ifname[0] && nla_put_string(skb, L2TP_ATTR_IFNAME, session->ifname)) || (session->cookie_len && nla_put(skb, L2TP_ATTR_COOKIE, session->cookie_len, diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c2190005a114..88709882c464 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -160,7 +160,7 @@ static int llc_ui_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; int rc = -ESOCKTNOSUPPORT; - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 63af25458fda..b4ecf267a34b 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -248,7 +248,7 @@ config MAC80211_MHWMP_DEBUG Do not select this option. config MAC80211_MESH_SYNC_DEBUG - bool "Verbose mesh mesh synchronization debugging" + bool "Verbose mesh synchronization debugging" depends on MAC80211_DEBUG_MENU depends on MAC80211_MESH ---help--- diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index a7dd110faafa..4911202334d9 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -8,6 +8,7 @@ mac80211-y := \ wpa.o \ scan.o offchannel.o \ ht.o agg-tx.o agg-rx.o \ + vht.o \ ibss.o \ iface.o \ rate.o \ diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index a04752e91023..537488cbf941 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/crypto.h> +#include <linux/export.h> #include <linux/err.h> #include <crypto/aes.h> @@ -126,3 +127,20 @@ void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm) { crypto_free_cipher(tfm); } + +void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf, + u8 *k1, u8 *k2) +{ + u8 l[AES_BLOCK_SIZE] = {}; + struct ieee80211_key *key = + container_of(keyconf, struct ieee80211_key, conf); + + crypto_cipher_encrypt_one(key->u.aes_cmac.tfm, l, l); + + memcpy(k1, l, AES_BLOCK_SIZE); + gf_mulx(k1); + + memcpy(k2, k1, AES_BLOCK_SIZE); + gf_mulx(k2); +} +EXPORT_SYMBOL(ieee80211_aes_cmac_calculate_k1_k2); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 186d9919b043..808338a1bce5 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -118,7 +118,7 @@ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, return; } - for (i = 0; i < STA_TID_NUM; i++) + for (i = 0; i < IEEE80211_NUM_TIDS; i++) if (ba_rx_bitmap & BIT(i)) set_bit(i, sta->ampdu_mlme.tid_rx_stop_requested); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 3195a6307f50..eb9df22418f0 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -445,10 +445,10 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, trace_api_start_tx_ba_session(pubsta, tid); - if (WARN_ON(!local->ops->ampdu_action)) + if (WARN_ON_ONCE(!local->ops->ampdu_action)) return -EINVAL; - if ((tid >= STA_TID_NUM) || + if ((tid >= IEEE80211_NUM_TIDS) || !(local->hw.flags & IEEE80211_HW_AMPDU_AGGREGATION) || (local->hw.flags & IEEE80211_HW_TX_AMPDU_SETUP_IN_HW)) return -EINVAL; @@ -605,9 +605,9 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid) trace_api_start_tx_ba_cb(sdata, ra, tid); - if (tid >= STA_TID_NUM) { + if (tid >= IEEE80211_NUM_TIDS) { ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", - tid, STA_TID_NUM); + tid, IEEE80211_NUM_TIDS); return; } @@ -687,7 +687,7 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid) if (!local->ops->ampdu_action) return -EINVAL; - if (tid >= STA_TID_NUM) + if (tid >= IEEE80211_NUM_TIDS) return -EINVAL; spin_lock_bh(&sta->lock); @@ -722,9 +722,9 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) trace_api_stop_tx_ba_cb(sdata, ra, tid); - if (tid >= STA_TID_NUM) { + if (tid >= IEEE80211_NUM_TIDS) { ht_dbg(sdata, "Bad TID value: tid = %d (>= %d)\n", - tid, STA_TID_NUM); + tid, IEEE80211_NUM_TIDS); return; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 05f3a313db88..516fbc96feff 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -164,7 +164,17 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, sta = sta_info_get(sdata, mac_addr); else sta = sta_info_get_bss(sdata, mac_addr); - if (!sta) { + /* + * The ASSOC test makes sure the driver is ready to + * receive the key. When wpa_supplicant has roamed + * using FT, it attempts to set the key before + * association has completed, this rejects that attempt + * so it will set the key again after assocation. + * + * TODO: accept the key if we have a station entry and + * add it to the device after the station. + */ + if (!sta || !test_sta_flag(sta, WLAN_STA_ASSOC)) { ieee80211_key_free(sdata->local, key); err = -ENOENT; goto out_unlock; @@ -370,29 +380,64 @@ static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, return 0; } -static void rate_idx_to_bitrate(struct rate_info *rate, struct sta_info *sta, int idx) -{ - if (!(rate->flags & RATE_INFO_FLAGS_MCS)) { - struct ieee80211_supported_band *sband; - sband = sta->local->hw.wiphy->bands[ - sta->local->oper_channel->band]; - rate->legacy = sband->bitrates[idx].bitrate; - } else - rate->mcs = idx; -} - void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo) { rinfo->flags = 0; - if (rate->flags & IEEE80211_TX_RC_MCS) + if (rate->flags & IEEE80211_TX_RC_MCS) { rinfo->flags |= RATE_INFO_FLAGS_MCS; + rinfo->mcs = rate->idx; + } else if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { + rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; + rinfo->mcs = ieee80211_rate_get_vht_mcs(rate); + rinfo->nss = ieee80211_rate_get_vht_nss(rate); + } else { + struct ieee80211_supported_band *sband; + sband = sta->local->hw.wiphy->bands[ + ieee80211_get_sdata_band(sta->sdata)]; + rinfo->legacy = sband->bitrates[rate->idx].bitrate; + } if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH; + if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) + rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH; + if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) + rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; - rate_idx_to_bitrate(rinfo, sta, rate->idx); +} + +void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) +{ + rinfo->flags = 0; + + if (sta->last_rx_rate_flag & RX_FLAG_HT) { + rinfo->flags |= RATE_INFO_FLAGS_MCS; + rinfo->mcs = sta->last_rx_rate_idx; + } else if (sta->last_rx_rate_flag & RX_FLAG_VHT) { + rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; + rinfo->nss = sta->last_rx_rate_vht_nss; + rinfo->mcs = sta->last_rx_rate_idx; + } else { + struct ieee80211_supported_band *sband; + + sband = sta->local->hw.wiphy->bands[ + ieee80211_get_sdata_band(sta->sdata)]; + rinfo->legacy = + sband->bitrates[sta->last_rx_rate_idx].bitrate; + } + + if (sta->last_rx_rate_flag & RX_FLAG_40MHZ) + rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH; + if (sta->last_rx_rate_flag & RX_FLAG_SHORT_GI) + rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; + if (sta->last_rx_rate_flag & RX_FLAG_80MHZ) + rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH; + if (sta->last_rx_rate_flag & RX_FLAG_80P80MHZ) + rinfo->flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH; + if (sta->last_rx_rate_flag & RX_FLAG_160MHZ) + rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH; } static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) @@ -441,15 +486,7 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) } sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate); - - sinfo->rxrate.flags = 0; - if (sta->last_rx_rate_flag & RX_FLAG_HT) - sinfo->rxrate.flags |= RATE_INFO_FLAGS_MCS; - if (sta->last_rx_rate_flag & RX_FLAG_40MHZ) - sinfo->rxrate.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH; - if (sta->last_rx_rate_flag & RX_FLAG_SHORT_GI) - sinfo->rxrate.flags |= RATE_INFO_FLAGS_SHORT_GI; - rate_idx_to_bitrate(&sinfo->rxrate, sta, sta->last_rx_rate_idx); + sta_set_rate_info_rx(sta, &sinfo->rxrate); if (ieee80211_vif_is_mesh(&sdata->vif)) { #ifdef CONFIG_MAC80211_MESH @@ -532,6 +569,8 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, u64 *data) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *channel; struct sta_info *sta; struct ieee80211_local *local = sdata->local; struct station_info sinfo; @@ -607,19 +646,26 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, do_survey: i = STA_STATS_LEN - STA_STATS_SURVEY_LEN; /* Get survey stats for current channel */ - q = 0; - while (true) { - survey.filled = 0; - if (drv_get_survey(local, q, &survey) != 0) { - survey.filled = 0; - break; - } + survey.filled = 0; - if (survey.channel && - (local->oper_channel->center_freq == - survey.channel->center_freq)) - break; - q++; + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (chanctx_conf) + channel = chanctx_conf->def.chan; + else + channel = NULL; + rcu_read_unlock(); + + if (channel) { + q = 0; + do { + survey.filled = 0; + if (drv_get_survey(local, q, &survey) != 0) { + survey.filled = 0; + break; + } + q++; + } while (channel != survey.channel); } if (survey.filled) @@ -724,47 +770,37 @@ static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, return ret; } -static int ieee80211_set_channel(struct wiphy *wiphy, - struct net_device *netdev, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type) +static int ieee80211_set_monitor_channel(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = wiphy_priv(wiphy); - struct ieee80211_sub_if_data *sdata = NULL; - - if (netdev) - sdata = IEEE80211_DEV_TO_SUB_IF(netdev); - - switch (ieee80211_get_channel_mode(local, NULL)) { - case CHAN_MODE_HOPPING: - return -EBUSY; - case CHAN_MODE_FIXED: - if (local->oper_channel != chan || - (!sdata && local->_oper_channel_type != channel_type)) - return -EBUSY; - if (!sdata && local->_oper_channel_type == channel_type) - return 0; - break; - case CHAN_MODE_UNDEFINED: - break; - } - - if (!ieee80211_set_channel_type(local, sdata, channel_type)) - return -EBUSY; + struct ieee80211_sub_if_data *sdata; + int ret = 0; - local->oper_channel = chan; + if (cfg80211_chandef_identical(&local->monitor_chandef, chandef)) + return 0; - /* auto-detects changes */ - ieee80211_hw_config(local, 0); + mutex_lock(&local->iflist_mtx); + if (local->use_chanctx) { + sdata = rcu_dereference_protected( + local->monitor_sdata, + lockdep_is_held(&local->iflist_mtx)); + if (sdata) { + ieee80211_vif_release_channel(sdata); + ret = ieee80211_vif_use_channel(sdata, chandef, + IEEE80211_CHANCTX_EXCLUSIVE); + } + } else if (local->open_count == local->monitors) { + local->_oper_channel = chandef->chan; + local->_oper_channel_type = cfg80211_get_chandef_type(chandef); + ieee80211_hw_config(local, 0); + } - return 0; -} + if (ret == 0) + local->monitor_chandef = *chandef; + mutex_unlock(&local->iflist_mtx); -static int ieee80211_set_monitor_channel(struct wiphy *wiphy, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type) -{ - return ieee80211_set_channel(wiphy, NULL, chan, channel_type); + return ret; } static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, @@ -872,15 +908,20 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, u32 changed = BSS_CHANGED_BEACON_INT | BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_BEACON | - BSS_CHANGED_SSID; + BSS_CHANGED_SSID | + BSS_CHANGED_P2P_PS; int err; old = rtnl_dereference(sdata->u.ap.beacon); if (old) return -EALREADY; - err = ieee80211_set_channel(wiphy, dev, params->channel, - params->channel_type); + /* TODO: make hostapd tell us what it wants */ + sdata->smps_mode = IEEE80211_SMPS_OFF; + sdata->needed_rx_chains = sdata->local->rx_chains; + + err = ieee80211_vif_use_channel(sdata, ¶ms->chandef, + IEEE80211_CHANCTX_SHARED); if (err) return err; @@ -907,11 +948,23 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.hidden_ssid = (params->hidden_ssid != NL80211_HIDDEN_SSID_NOT_IN_USE); + sdata->vif.bss_conf.p2p_ctwindow = params->p2p_ctwindow; + sdata->vif.bss_conf.p2p_oppps = params->p2p_opp_ps; + err = ieee80211_assign_beacon(sdata, ¶ms->beacon); if (err < 0) return err; changed |= err; + err = drv_start_ap(sdata->local, sdata); + if (err) { + old = rtnl_dereference(sdata->u.ap.beacon); + if (old) + kfree_rcu(old, rcu_head); + RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); + return err; + } + ieee80211_bss_info_change_notify(sdata, changed); netif_carrier_on(dev); @@ -943,26 +996,42 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) { - struct ieee80211_sub_if_data *sdata, *vlan; - struct beacon_data *old; - - sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_sub_if_data *vlan; + struct ieee80211_local *local = sdata->local; + struct beacon_data *old_beacon; + struct probe_resp *old_probe_resp; - old = rtnl_dereference(sdata->u.ap.beacon); - if (!old) + old_beacon = rtnl_dereference(sdata->u.ap.beacon); + if (!old_beacon) return -ENOENT; + old_probe_resp = rtnl_dereference(sdata->u.ap.probe_resp); + /* turn off carrier for this interface and dependent VLANs */ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_off(vlan->dev); netif_carrier_off(dev); + /* remove beacon and probe response */ RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); + RCU_INIT_POINTER(sdata->u.ap.probe_resp, NULL); + kfree_rcu(old_beacon, rcu_head); + if (old_probe_resp) + kfree_rcu(old_probe_resp, rcu_head); - kfree_rcu(old, rcu_head); - - sta_info_flush(sdata->local, sdata); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + sta_info_flush(local, vlan); + sta_info_flush(local, sdata); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + drv_stop_ap(sdata->local, sdata); + + /* free all potentially still buffered bcast frames */ + local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf); + skb_queue_purge(&sdata->u.ap.ps.bc_buf); + + ieee80211_vif_release_channel(sdata); + return 0; } @@ -1019,9 +1088,10 @@ static int sta_apply_parameters(struct ieee80211_local *local, int i, j; struct ieee80211_supported_band *sband; struct ieee80211_sub_if_data *sdata = sta->sdata; + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); u32 mask, set; - sband = local->hw.wiphy->bands[local->oper_channel->band]; + sband = local->hw.wiphy->bands[band]; mask = params->sta_flags_mask; set = params->sta_flags_set; @@ -1136,7 +1206,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, rates |= BIT(j); } } - sta->sta.supp_rates[local->oper_channel->band] = rates; + sta->sta.supp_rates[band] = rates; } if (params->ht_capa) @@ -1144,6 +1214,11 @@ static int sta_apply_parameters(struct ieee80211_local *local, params->ht_capa, &sta->sta.ht_cap); + if (params->vht_capa) + ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, + params->vht_capa, + &sta->sta.vht_cap); + if (ieee80211_vif_is_mesh(&sdata->vif)) { #ifdef CONFIG_MAC80211_MESH if (sdata->u.mesh.security & IEEE80211_MESH_SEC_SECURED) @@ -1664,8 +1739,12 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, if (err) return err; - err = ieee80211_set_channel(wiphy, dev, setup->channel, - setup->channel_type); + /* can mesh use other SMPS modes? */ + sdata->smps_mode = IEEE80211_SMPS_OFF; + sdata->needed_rx_chains = sdata->local->rx_chains; + + err = ieee80211_vif_use_channel(sdata, &setup->chandef, + IEEE80211_CHANCTX_SHARED); if (err) return err; @@ -1679,6 +1758,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); ieee80211_stop_mesh(sdata); + ieee80211_vif_release_channel(sdata); return 0; } @@ -1688,10 +1768,14 @@ static int ieee80211_change_bss(struct wiphy *wiphy, struct net_device *dev, struct bss_parameters *params) { - struct ieee80211_sub_if_data *sdata; + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + enum ieee80211_band band; u32 changed = 0; - sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (!rtnl_dereference(sdata->u.ap.beacon)) + return -ENOENT; + + band = ieee80211_get_sdata_band(sdata); if (params->use_cts_prot >= 0) { sdata->vif.bss_conf.use_cts_prot = params->use_cts_prot; @@ -1704,7 +1788,7 @@ static int ieee80211_change_bss(struct wiphy *wiphy, } if (!sdata->vif.bss_conf.use_short_slot && - sdata->local->oper_channel->band == IEEE80211_BAND_5GHZ) { + band == IEEE80211_BAND_5GHZ) { sdata->vif.bss_conf.use_short_slot = true; changed |= BSS_CHANGED_ERP_SLOT; } @@ -1718,9 +1802,7 @@ static int ieee80211_change_bss(struct wiphy *wiphy, if (params->basic_rates) { int i, j; u32 rates = 0; - struct ieee80211_local *local = wiphy_priv(wiphy); - struct ieee80211_supported_band *sband = - wiphy->bands[local->oper_channel->band]; + struct ieee80211_supported_band *sband = wiphy->bands[band]; for (i = 0; i < params->basic_rates_len; i++) { int rate = (params->basic_rates[i] & 0x7f) * 5; @@ -1746,6 +1828,16 @@ static int ieee80211_change_bss(struct wiphy *wiphy, changed |= BSS_CHANGED_HT; } + if (params->p2p_ctwindow >= 0) { + sdata->vif.bss_conf.p2p_ctwindow = params->p2p_ctwindow; + changed |= BSS_CHANGED_P2P_PS; + } + + if (params->p2p_opp_ps >= 0) { + sdata->vif.bss_conf.p2p_oppps = params->p2p_opp_ps; + changed |= BSS_CHANGED_P2P_PS; + } + ieee80211_bss_info_change_notify(sdata, changed); return 0; @@ -1829,7 +1921,16 @@ static int ieee80211_scan(struct wiphy *wiphy, * beaconing hasn't been configured yet */ case NL80211_IFTYPE_AP: - if (sdata->u.ap.beacon) + /* + * If the scan has been forced (and the driver supports + * forcing), don't care about being beaconing already. + * This will create problems to the attached stations (e.g. all + * the frames sent while scanning on other channel will be + * lost) + */ + if (sdata->u.ap.beacon && + (!(wiphy->features & NL80211_FEATURE_AP_SCAN) || + !(req->flags & NL80211_SCAN_FLAG_AP))) return -EOPNOTSUPP; break; default: @@ -1872,20 +1973,6 @@ static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req) { - struct ieee80211_local *local = wiphy_priv(wiphy); - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - switch (ieee80211_get_channel_mode(local, sdata)) { - case CHAN_MODE_HOPPING: - return -EBUSY; - case CHAN_MODE_FIXED: - if (local->oper_channel == req->bss->channel) - break; - return -EBUSY; - case CHAN_MODE_UNDEFINED: - break; - } - return ieee80211_mgd_assoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } @@ -1904,30 +1991,22 @@ static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ibss_params *params) { - struct ieee80211_local *local = wiphy_priv(wiphy); - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - switch (ieee80211_get_channel_mode(local, sdata)) { - case CHAN_MODE_HOPPING: - return -EBUSY; - case CHAN_MODE_FIXED: - if (!params->channel_fixed) - return -EBUSY; - if (local->oper_channel == params->channel) - break; - return -EBUSY; - case CHAN_MODE_UNDEFINED: - break; - } - - return ieee80211_ibss_join(sdata, params); + return ieee80211_ibss_join(IEEE80211_DEV_TO_SUB_IF(dev), params); } static int ieee80211_leave_ibss(struct wiphy *wiphy, struct net_device *dev) { + return ieee80211_ibss_leave(IEEE80211_DEV_TO_SUB_IF(dev)); +} + +static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev, + int rate[IEEE80211_NUM_BANDS]) +{ struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - return ieee80211_ibss_leave(sdata); + memcpy(sdata->vif.bss_conf.mcast_rate, rate, sizeof(rate)); + + return 0; } static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) @@ -1956,10 +2035,16 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) return err; } - if (changed & WIPHY_PARAM_RETRY_SHORT) + if (changed & WIPHY_PARAM_RETRY_SHORT) { + if (wiphy->retry_short > IEEE80211_MAX_TX_RETRY) + return -EINVAL; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; - if (changed & WIPHY_PARAM_RETRY_LONG) + } + if (changed & WIPHY_PARAM_RETRY_LONG) { + if (wiphy->retry_long > IEEE80211_MAX_TX_RETRY) + return -EINVAL; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; + } if (changed & (WIPHY_PARAM_RETRY_SHORT | WIPHY_PARAM_RETRY_LONG)) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_RETRY_LIMITS); @@ -1968,41 +2053,65 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) } static int ieee80211_set_tx_power(struct wiphy *wiphy, + struct wireless_dev *wdev, enum nl80211_tx_power_setting type, int mbm) { struct ieee80211_local *local = wiphy_priv(wiphy); - struct ieee80211_channel *chan = local->oper_channel; - u32 changes = 0; + struct ieee80211_sub_if_data *sdata; + + if (wdev) { + sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + + switch (type) { + case NL80211_TX_POWER_AUTOMATIC: + sdata->user_power_level = IEEE80211_UNSET_POWER_LEVEL; + break; + case NL80211_TX_POWER_LIMITED: + case NL80211_TX_POWER_FIXED: + if (mbm < 0 || (mbm % 100)) + return -EOPNOTSUPP; + sdata->user_power_level = MBM_TO_DBM(mbm); + break; + } + + ieee80211_recalc_txpower(sdata); + + return 0; + } switch (type) { case NL80211_TX_POWER_AUTOMATIC: - local->user_power_level = -1; + local->user_power_level = IEEE80211_UNSET_POWER_LEVEL; break; case NL80211_TX_POWER_LIMITED: - if (mbm < 0 || (mbm % 100)) - return -EOPNOTSUPP; - local->user_power_level = MBM_TO_DBM(mbm); - break; case NL80211_TX_POWER_FIXED: if (mbm < 0 || (mbm % 100)) return -EOPNOTSUPP; - /* TODO: move to cfg80211 when it knows the channel */ - if (MBM_TO_DBM(mbm) > chan->max_power) - return -EINVAL; local->user_power_level = MBM_TO_DBM(mbm); break; } - ieee80211_hw_config(local, changes); + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata, &local->interfaces, list) + sdata->user_power_level = local->user_power_level; + list_for_each_entry(sdata, &local->interfaces, list) + ieee80211_recalc_txpower(sdata); + mutex_unlock(&local->iflist_mtx); return 0; } -static int ieee80211_get_tx_power(struct wiphy *wiphy, int *dbm) +static int ieee80211_get_tx_power(struct wiphy *wiphy, + struct wireless_dev *wdev, + int *dbm) { struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); - *dbm = local->hw.conf.power_level; + if (!local->use_chanctx) + *dbm = local->hw.conf.power_level; + else + *dbm = sdata->vif.bss_conf.txpower; return 0; } @@ -2067,13 +2176,12 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, /* * If not associated, or current association is not an HT - * association, there's no need to send an action frame. + * association, there's no need to do anything, just store + * the new value until we associate. */ if (!sdata->u.mgd.associated || - sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT) { - ieee80211_recalc_smps(sdata->local); + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT) return 0; - } ap = sdata->u.mgd.associated->bssid; @@ -2179,7 +2287,6 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, static int ieee80211_start_roc_work(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel, - enum nl80211_channel_type channel_type, unsigned int duration, u64 *cookie, struct sk_buff *txskb) { @@ -2189,12 +2296,14 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, lockdep_assert_held(&local->mtx); + if (local->use_chanctx && !local->ops->remain_on_channel) + return -EOPNOTSUPP; + roc = kzalloc(sizeof(*roc), GFP_KERNEL); if (!roc) return -ENOMEM; roc->chan = channel; - roc->chan_type = channel_type; roc->duration = duration; roc->req_duration = duration; roc->frame = txskb; @@ -2227,7 +2336,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, if (!duration) duration = 10; - ret = drv_remain_on_channel(local, channel, channel_type, duration); + ret = drv_remain_on_channel(local, sdata, channel, duration); if (ret) { kfree(roc); return ret; @@ -2238,7 +2347,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, out_check_combine: list_for_each_entry(tmp, &local->roc_list, list) { - if (tmp->chan != channel || tmp->chan_type != channel_type) + if (tmp->chan != channel || tmp->sdata != sdata) continue; /* @@ -2332,13 +2441,22 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, list_add_tail(&roc->list, &local->roc_list); /* - * cookie is either the roc (for normal roc) + * cookie is either the roc cookie (for normal roc) * or the SKB (for mgmt TX) */ - if (txskb) + if (!txskb) { + /* local->mtx protects this */ + local->roc_cookie_counter++; + roc->cookie = local->roc_cookie_counter; + /* wow, you wrapped 64 bits ... more likely a bug */ + if (WARN_ON(roc->cookie == 0)) { + roc->cookie = 1; + local->roc_cookie_counter++; + } + *cookie = roc->cookie; + } else { *cookie = (unsigned long)txskb; - else - *cookie = (unsigned long)roc; + } return 0; } @@ -2346,7 +2464,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, static int ieee80211_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, unsigned int duration, u64 *cookie) { @@ -2355,7 +2472,7 @@ static int ieee80211_remain_on_channel(struct wiphy *wiphy, int ret; mutex_lock(&local->mtx); - ret = ieee80211_start_roc_work(local, sdata, chan, channel_type, + ret = ieee80211_start_roc_work(local, sdata, chan, duration, cookie, NULL); mutex_unlock(&local->mtx); @@ -2373,7 +2490,7 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local, struct ieee80211_roc_work *dep, *tmp2; list_for_each_entry_safe(dep, tmp2, &roc->dependents, list) { - if (!mgmt_tx && (unsigned long)dep != cookie) + if (!mgmt_tx && dep->cookie != cookie) continue; else if (mgmt_tx && dep->mgmt_tx_cookie != cookie) continue; @@ -2385,7 +2502,7 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local, return 0; } - if (!mgmt_tx && (unsigned long)roc != cookie) + if (!mgmt_tx && roc->cookie != cookie) continue; else if (mgmt_tx && roc->mgmt_tx_cookie != cookie) continue; @@ -2448,10 +2565,8 @@ static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy, static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, bool offchan, - enum nl80211_channel_type channel_type, - bool channel_type_valid, unsigned int wait, - const u8 *buf, size_t len, bool no_cck, - bool dont_wait_for_ack, u64 *cookie) + unsigned int wait, const u8 *buf, size_t len, + bool no_cck, bool dont_wait_for_ack, u64 *cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_local *local = sdata->local; @@ -2515,10 +2630,16 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, /* Check if the operating channel is the requested channel */ if (!need_offchan) { - need_offchan = chan != local->oper_channel; - if (channel_type_valid && - channel_type != local->_oper_channel_type) + struct ieee80211_chanctx_conf *chanctx_conf; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + + if (chanctx_conf) + need_offchan = chan != chanctx_conf->def.chan; + else need_offchan = true; + rcu_read_unlock(); } if (need_offchan && !offchan) { @@ -2552,7 +2673,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, local->hw.offchannel_tx_hw_queue; /* This will handle all kinds of coalescing and immediate TX */ - ret = ieee80211_start_roc_work(local, sdata, chan, channel_type, + ret = ieee80211_start_roc_work(local, sdata, chan, wait, cookie, skb); if (ret) kfree_skb(skb); @@ -2594,6 +2715,9 @@ static void ieee80211_mgmt_frame_register(struct wiphy *wiphy, else local->probe_req_reg--; + if (!local->open_count) + break; + ieee80211_queue_work(&local->hw, &local->reconfig_filter); break; default: @@ -2667,7 +2791,7 @@ static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata) u16 capab; capab = 0; - if (local->oper_channel->band != IEEE80211_BAND_2GHZ) + if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ) return capab; if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE)) @@ -2699,7 +2823,7 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, u16 status_code, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); struct ieee80211_tdls_data *tf; tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); @@ -2719,10 +2843,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, tf->u.setup_req.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(sdata, skb, false, - local->oper_channel->band); - ieee80211_add_ext_srates_ie(sdata, skb, false, - local->oper_channel->band); + ieee80211_add_srates_ie(sdata, skb, false, band); + ieee80211_add_ext_srates_ie(sdata, skb, false, band); ieee80211_tdls_add_ext_capab(skb); break; case WLAN_TDLS_SETUP_RESPONSE: @@ -2735,10 +2857,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, tf->u.setup_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(sdata, skb, false, - local->oper_channel->band); - ieee80211_add_ext_srates_ie(sdata, skb, false, - local->oper_channel->band); + ieee80211_add_srates_ie(sdata, skb, false, band); + ieee80211_add_ext_srates_ie(sdata, skb, false, band); ieee80211_tdls_add_ext_capab(skb); break; case WLAN_TDLS_SETUP_CONFIRM: @@ -2776,7 +2896,7 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, u16 status_code, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); struct ieee80211_mgmt *mgmt; mgmt = (void *)skb_put(skb, 24); @@ -2799,10 +2919,8 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, mgmt->u.action.u.tdls_discover_resp.capability = cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - ieee80211_add_srates_ie(sdata, skb, false, - local->oper_channel->band); - ieee80211_add_ext_srates_ie(sdata, skb, false, - local->oper_channel->band); + ieee80211_add_srates_ie(sdata, skb, false, band); + ieee80211_add_ext_srates_ie(sdata, skb, false, band); ieee80211_tdls_add_ext_capab(skb); break; default: @@ -2819,7 +2937,6 @@ static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; - struct ieee80211_tx_info *info; struct sk_buff *skb = NULL; bool send_direct; int ret; @@ -2845,7 +2962,6 @@ static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, if (!skb) return -ENOMEM; - info = IEEE80211_SKB_CB(skb); skb_reserve(skb, local->hw.extra_tx_headroom); switch (action_code) { @@ -2982,12 +3098,19 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, bool qos; struct ieee80211_tx_info *info; struct sta_info *sta; + struct ieee80211_chanctx_conf *chanctx_conf; + enum ieee80211_band band; rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return -EINVAL; + } + band = chanctx_conf->def.chan->band; sta = sta_info_get(sdata, peer); if (sta) { qos = test_sta_flag(sta, WLAN_STA_WME); - rcu_read_unlock(); } else { rcu_read_unlock(); return -ENOLINK; @@ -3005,8 +3128,10 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, } skb = dev_alloc_skb(local->hw.extra_tx_headroom + size); - if (!skb) + if (!skb) { + rcu_read_unlock(); return -ENOMEM; + } skb->dev = dev; @@ -3031,21 +3156,31 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, nullfunc->qos_ctrl = cpu_to_le16(7); local_bh_disable(); - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, skb, band); local_bh_enable(); + rcu_read_unlock(); *cookie = (unsigned long) skb; return 0; } -static struct ieee80211_channel * -ieee80211_cfg_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, - enum nl80211_channel_type *type) +static int ieee80211_cfg_get_channel(struct wiphy *wiphy, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef) { - struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + struct ieee80211_chanctx_conf *chanctx_conf; + int ret = -ENODATA; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (chanctx_conf) { + *chandef = chanctx_conf->def; + ret = 0; + } + rcu_read_unlock(); - *type = local->_oper_channel_type; - return local->oper_channel; + return ret; } #ifdef CONFIG_PM @@ -3100,6 +3235,7 @@ struct cfg80211_ops mac80211_config_ops = { .disassoc = ieee80211_disassoc, .join_ibss = ieee80211_join_ibss, .leave_ibss = ieee80211_leave_ibss, + .set_mcast_rate = ieee80211_set_mcast_rate, .set_wiphy_params = ieee80211_set_wiphy_params, .set_tx_power = ieee80211_set_tx_power, .get_tx_power = ieee80211_get_tx_power, diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 0bfc914ddd15..80e55527504b 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -3,168 +3,385 @@ */ #include <linux/nl80211.h> +#include <linux/export.h> +#include <linux/rtnetlink.h> #include <net/cfg80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" -static enum ieee80211_chan_mode -__ieee80211_get_channel_mode(struct ieee80211_local *local, - struct ieee80211_sub_if_data *ignore) +static void ieee80211_change_chandef(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + const struct cfg80211_chan_def *chandef) { + if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) + return; + + WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); + + ctx->conf.def = *chandef; + drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_WIDTH); + + if (!local->use_chanctx) { + local->_oper_channel_type = cfg80211_get_chandef_type(chandef); + ieee80211_hw_config(local, 0); + } +} + +static struct ieee80211_chanctx * +ieee80211_find_chanctx(struct ieee80211_local *local, + const struct cfg80211_chan_def *chandef, + enum ieee80211_chanctx_mode mode) +{ + struct ieee80211_chanctx *ctx; + + lockdep_assert_held(&local->chanctx_mtx); + + if (mode == IEEE80211_CHANCTX_EXCLUSIVE) + return NULL; + + list_for_each_entry(ctx, &local->chanctx_list, list) { + const struct cfg80211_chan_def *compat; + + if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) + continue; + + compat = cfg80211_chandef_compatible(&ctx->conf.def, chandef); + if (!compat) + continue; + + ieee80211_change_chandef(local, ctx, compat); + + return ctx; + } + + return NULL; +} + +static struct ieee80211_chanctx * +ieee80211_new_chanctx(struct ieee80211_local *local, + const struct cfg80211_chan_def *chandef, + enum ieee80211_chanctx_mode mode) +{ + struct ieee80211_chanctx *ctx; + int err; + + lockdep_assert_held(&local->chanctx_mtx); + + ctx = kzalloc(sizeof(*ctx) + local->hw.chanctx_data_size, GFP_KERNEL); + if (!ctx) + return ERR_PTR(-ENOMEM); + + ctx->conf.def = *chandef; + ctx->conf.rx_chains_static = 1; + ctx->conf.rx_chains_dynamic = 1; + ctx->mode = mode; + + if (!local->use_chanctx) { + local->_oper_channel_type = + cfg80211_get_chandef_type(chandef); + local->_oper_channel = chandef->chan; + ieee80211_hw_config(local, 0); + } else { + err = drv_add_chanctx(local, ctx); + if (err) { + kfree(ctx); + return ERR_PTR(err); + } + } + + list_add_rcu(&ctx->list, &local->chanctx_list); + + return ctx; +} + +static void ieee80211_free_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + lockdep_assert_held(&local->chanctx_mtx); + + WARN_ON_ONCE(ctx->refcount != 0); + + if (!local->use_chanctx) { + local->_oper_channel_type = NL80211_CHAN_NO_HT; + ieee80211_hw_config(local, 0); + } else { + drv_remove_chanctx(local, ctx); + } + + list_del_rcu(&ctx->list); + kfree_rcu(ctx, rcu_head); +} + +static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata, + struct ieee80211_chanctx *ctx) +{ + struct ieee80211_local *local = sdata->local; + int ret; + + lockdep_assert_held(&local->chanctx_mtx); + + ret = drv_assign_vif_chanctx(local, sdata, ctx); + if (ret) + return ret; + + rcu_assign_pointer(sdata->vif.chanctx_conf, &ctx->conf); + ctx->refcount++; + + ieee80211_recalc_txpower(sdata); + + return 0; +} + +static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + struct ieee80211_chanctx_conf *conf = &ctx->conf; struct ieee80211_sub_if_data *sdata; + const struct cfg80211_chan_def *compat = NULL; + + lockdep_assert_held(&local->chanctx_mtx); - lockdep_assert_held(&local->iflist_mtx); + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { - list_for_each_entry(sdata, &local->interfaces, list) { - if (sdata == ignore) + if (!ieee80211_sdata_running(sdata)) + continue; + if (rcu_access_pointer(sdata->vif.chanctx_conf) != conf) continue; + if (!compat) + compat = &sdata->vif.bss_conf.chandef; + + compat = cfg80211_chandef_compatible( + &sdata->vif.bss_conf.chandef, compat); + if (!compat) + break; + } + rcu_read_unlock(); + + if (WARN_ON_ONCE(!compat)) + return; + + ieee80211_change_chandef(local, ctx, compat); +} + +static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata, + struct ieee80211_chanctx *ctx) +{ + struct ieee80211_local *local = sdata->local; + + lockdep_assert_held(&local->chanctx_mtx); + + ctx->refcount--; + rcu_assign_pointer(sdata->vif.chanctx_conf, NULL); + + drv_unassign_vif_chanctx(local, sdata, ctx); + + if (ctx->refcount > 0) { + ieee80211_recalc_chanctx_chantype(sdata->local, ctx); + ieee80211_recalc_smps_chanctx(local, ctx); + } +} + +static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx_conf *conf; + struct ieee80211_chanctx *ctx; + + lockdep_assert_held(&local->chanctx_mtx); + + conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (!conf) + return; + + ctx = container_of(conf, struct ieee80211_chanctx, conf); + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + struct ieee80211_sub_if_data *vlan; + + /* for the VLAN list */ + ASSERT_RTNL(); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + rcu_assign_pointer(vlan->vif.chanctx_conf, NULL); + } + + ieee80211_unassign_vif_chanctx(sdata, ctx); + if (ctx->refcount == 0) + ieee80211_free_chanctx(local, ctx); +} + +void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *chanctx) +{ + struct ieee80211_sub_if_data *sdata; + u8 rx_chains_static, rx_chains_dynamic; + + lockdep_assert_held(&local->chanctx_mtx); + + rx_chains_static = 1; + rx_chains_dynamic = 1; + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + u8 needed_static, needed_dynamic; + if (!ieee80211_sdata_running(sdata)) continue; + if (rcu_access_pointer(sdata->vif.chanctx_conf) != + &chanctx->conf) + continue; + switch (sdata->vif.type) { - case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_P2P_DEVICE: continue; case NL80211_IFTYPE_STATION: if (!sdata->u.mgd.associated) continue; break; - case NL80211_IFTYPE_ADHOC: - if (!sdata->u.ibss.ssid_len) - continue; - if (!sdata->u.ibss.fixed_channel) - return CHAN_MODE_HOPPING; - break; case NL80211_IFTYPE_AP_VLAN: - /* will also have _AP interface */ continue; case NL80211_IFTYPE_AP: - if (!sdata->u.ap.beacon) - continue; - break; + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MESH_POINT: - if (!sdata->wdev.mesh_id_len) - continue; break; default: + WARN_ON_ONCE(1); + } + + switch (sdata->smps_mode) { + default: + WARN_ONCE(1, "Invalid SMPS mode %d\n", + sdata->smps_mode); + /* fall through */ + case IEEE80211_SMPS_OFF: + needed_static = sdata->needed_rx_chains; + needed_dynamic = sdata->needed_rx_chains; + break; + case IEEE80211_SMPS_DYNAMIC: + needed_static = 1; + needed_dynamic = sdata->needed_rx_chains; + break; + case IEEE80211_SMPS_STATIC: + needed_static = 1; + needed_dynamic = 1; break; } - return CHAN_MODE_FIXED; + rx_chains_static = max(rx_chains_static, needed_static); + rx_chains_dynamic = max(rx_chains_dynamic, needed_dynamic); } + rcu_read_unlock(); - return CHAN_MODE_UNDEFINED; + if (!local->use_chanctx) { + if (rx_chains_static > 1) + local->smps_mode = IEEE80211_SMPS_OFF; + else if (rx_chains_dynamic > 1) + local->smps_mode = IEEE80211_SMPS_DYNAMIC; + else + local->smps_mode = IEEE80211_SMPS_STATIC; + ieee80211_hw_config(local, 0); + } + + if (rx_chains_static == chanctx->conf.rx_chains_static && + rx_chains_dynamic == chanctx->conf.rx_chains_dynamic) + return; + + chanctx->conf.rx_chains_static = rx_chains_static; + chanctx->conf.rx_chains_dynamic = rx_chains_dynamic; + drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RX_CHAINS); } -enum ieee80211_chan_mode -ieee80211_get_channel_mode(struct ieee80211_local *local, - struct ieee80211_sub_if_data *ignore) +int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata, + const struct cfg80211_chan_def *chandef, + enum ieee80211_chanctx_mode mode) { - enum ieee80211_chan_mode mode; + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx *ctx; + int ret; - mutex_lock(&local->iflist_mtx); - mode = __ieee80211_get_channel_mode(local, ignore); - mutex_unlock(&local->iflist_mtx); + WARN_ON(sdata->dev && netif_carrier_ok(sdata->dev)); - return mode; -} + mutex_lock(&local->chanctx_mtx); + __ieee80211_vif_release_channel(sdata); -static enum nl80211_channel_type -ieee80211_get_superchan(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) -{ - enum nl80211_channel_type superchan = NL80211_CHAN_NO_HT; - struct ieee80211_sub_if_data *tmp; + ctx = ieee80211_find_chanctx(local, chandef, mode); + if (!ctx) + ctx = ieee80211_new_chanctx(local, chandef, mode); + if (IS_ERR(ctx)) { + ret = PTR_ERR(ctx); + goto out; + } - mutex_lock(&local->iflist_mtx); - list_for_each_entry(tmp, &local->interfaces, list) { - if (tmp == sdata) - continue; + sdata->vif.bss_conf.chandef = *chandef; - if (!ieee80211_sdata_running(tmp)) - continue; + ret = ieee80211_assign_vif_chanctx(sdata, ctx); + if (ret) { + /* if assign fails refcount stays the same */ + if (ctx->refcount == 0) + ieee80211_free_chanctx(local, ctx); + goto out; + } - switch (tmp->vif.bss_conf.channel_type) { - case NL80211_CHAN_NO_HT: - case NL80211_CHAN_HT20: - if (superchan > tmp->vif.bss_conf.channel_type) - break; + if (sdata->vif.type == NL80211_IFTYPE_AP) { + struct ieee80211_sub_if_data *vlan; - superchan = tmp->vif.bss_conf.channel_type; - break; - case NL80211_CHAN_HT40PLUS: - WARN_ON(superchan == NL80211_CHAN_HT40MINUS); - superchan = NL80211_CHAN_HT40PLUS; - break; - case NL80211_CHAN_HT40MINUS: - WARN_ON(superchan == NL80211_CHAN_HT40PLUS); - superchan = NL80211_CHAN_HT40MINUS; - break; - } + /* for the VLAN list */ + ASSERT_RTNL(); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + rcu_assign_pointer(vlan->vif.chanctx_conf, &ctx->conf); } - mutex_unlock(&local->iflist_mtx); - return superchan; + ieee80211_recalc_smps_chanctx(local, ctx); + out: + mutex_unlock(&local->chanctx_mtx); + return ret; } -static bool -ieee80211_channel_types_are_compatible(enum nl80211_channel_type chantype1, - enum nl80211_channel_type chantype2, - enum nl80211_channel_type *compat) +void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata) { - /* - * start out with chantype1 being the result, - * overwriting later if needed - */ - if (compat) - *compat = chantype1; - - switch (chantype1) { - case NL80211_CHAN_NO_HT: - if (compat) - *compat = chantype2; - break; - case NL80211_CHAN_HT20: - /* - * allow any change that doesn't go to no-HT - * (if it already is no-HT no change is needed) - */ - if (chantype2 == NL80211_CHAN_NO_HT) - break; - if (compat) - *compat = chantype2; - break; - case NL80211_CHAN_HT40PLUS: - case NL80211_CHAN_HT40MINUS: - /* allow smaller bandwidth and same */ - if (chantype2 == NL80211_CHAN_NO_HT) - break; - if (chantype2 == NL80211_CHAN_HT20) - break; - if (chantype2 == chantype1) - break; - return false; - } + WARN_ON(sdata->dev && netif_carrier_ok(sdata->dev)); - return true; + mutex_lock(&sdata->local->chanctx_mtx); + __ieee80211_vif_release_channel(sdata); + mutex_unlock(&sdata->local->chanctx_mtx); } -bool ieee80211_set_channel_type(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum nl80211_channel_type chantype) +void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata) { - enum nl80211_channel_type superchan; - enum nl80211_channel_type compatchan; + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *ap; + struct ieee80211_chanctx_conf *conf; - superchan = ieee80211_get_superchan(local, sdata); - if (!ieee80211_channel_types_are_compatible(superchan, chantype, - &compatchan)) - return false; + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->bss)) + return; - local->_oper_channel_type = compatchan; + ap = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); - if (sdata) - sdata->vif.bss_conf.channel_type = chantype; + mutex_lock(&local->chanctx_mtx); - return true; + conf = rcu_dereference_protected(ap->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + rcu_assign_pointer(sdata->vif.chanctx_conf, conf); + mutex_unlock(&local->chanctx_mtx); +} + +void ieee80211_iter_chan_contexts_atomic( + struct ieee80211_hw *hw, + void (*iter)(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *chanctx_conf, + void *data), + void *iter_data) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_chanctx *ctx; + rcu_read_lock(); + list_for_each_entry_rcu(ctx, &local->chanctx_list, list) + iter(hw, &ctx->conf, iter_data); + rcu_read_unlock(); } +EXPORT_SYMBOL_GPL(ieee80211_iter_chan_contexts_atomic); diff --git a/net/mac80211/debugfs.h b/net/mac80211/debugfs.h index 9be4e6d71d00..214ed4ecd739 100644 --- a/net/mac80211/debugfs.h +++ b/net/mac80211/debugfs.h @@ -2,9 +2,9 @@ #define __MAC80211_DEBUGFS_H #ifdef CONFIG_MAC80211_DEBUGFS -extern void debugfs_hw_add(struct ieee80211_local *local); -extern int mac80211_format_buffer(char __user *userbuf, size_t count, - loff_t *ppos, char *fmt, ...); +void debugfs_hw_add(struct ieee80211_local *local); +int __printf(4, 5) mac80211_format_buffer(char __user *userbuf, size_t count, + loff_t *ppos, char *fmt, ...); #else static inline void debugfs_hw_add(struct ieee80211_local *local) { diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 090d08ff22c4..c3a3082b72e5 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -116,7 +116,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; - char buf[14*NUM_RX_DATA_QUEUES+1], *p = buf; + char buf[14*IEEE80211_NUM_TIDS+1], *p = buf; int i, len; const u8 *rpn; @@ -126,7 +126,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, len = scnprintf(buf, sizeof(buf), "\n"); break; case WLAN_CIPHER_SUITE_TKIP: - for (i = 0; i < NUM_RX_DATA_QUEUES; i++) + for (i = 0; i < IEEE80211_NUM_TIDS; i++) p += scnprintf(p, sizeof(buf)+buf-p, "%08x %04x\n", key->u.tkip.rx[i].iv32, @@ -134,7 +134,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, len = p - buf; break; case WLAN_CIPHER_SUITE_CCMP: - for (i = 0; i < NUM_RX_DATA_QUEUES + 1; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { rpn = key->u.ccmp.rx_pn[i]; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", @@ -199,6 +199,22 @@ static ssize_t key_icverrors_read(struct file *file, char __user *userbuf, } KEY_OPS(icverrors); +static ssize_t key_mic_failures_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct ieee80211_key *key = file->private_data; + char buf[20]; + int len; + + if (key->conf.cipher != WLAN_CIPHER_SUITE_TKIP) + return -EINVAL; + + len = scnprintf(buf, sizeof(buf), "%u\n", key->u.tkip.mic_failures); + + return simple_read_from_buffer(userbuf, count, ppos, buf, len); +} +KEY_OPS(mic_failures); + static ssize_t key_key_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -260,6 +276,7 @@ void ieee80211_debugfs_key_add(struct ieee80211_key *key) DEBUGFS_ADD(rx_spec); DEBUGFS_ADD(replays); DEBUGFS_ADD(icverrors); + DEBUGFS_ADD(mic_failures); DEBUGFS_ADD(key); DEBUGFS_ADD(ifindex); }; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 6d5aec9418ee..cbde5cc49a40 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/device.h> #include <linux/if.h> +#include <linux/if_ether.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> @@ -167,7 +168,29 @@ IEEE80211_IF_FILE(rc_rateidx_mcs_mask_5ghz, IEEE80211_IF_FILE(flags, flags, HEX); IEEE80211_IF_FILE(state, state, LHEX); -IEEE80211_IF_FILE(channel_type, vif.bss_conf.channel_type, DEC); +IEEE80211_IF_FILE(txpower, vif.bss_conf.txpower, DEC); +IEEE80211_IF_FILE(ap_power_level, ap_power_level, DEC); +IEEE80211_IF_FILE(user_power_level, user_power_level, DEC); + +static ssize_t +ieee80211_if_fmt_hw_queues(const struct ieee80211_sub_if_data *sdata, + char *buf, int buflen) +{ + int len; + + len = scnprintf(buf, buflen, "AC queues: VO:%d VI:%d BE:%d BK:%d\n", + sdata->vif.hw_queue[IEEE80211_AC_VO], + sdata->vif.hw_queue[IEEE80211_AC_VI], + sdata->vif.hw_queue[IEEE80211_AC_BE], + sdata->vif.hw_queue[IEEE80211_AC_BK]); + + if (sdata->vif.type == NL80211_IFTYPE_AP) + len += scnprintf(buf + len, buflen - len, "cab queue: %d\n", + sdata->vif.cab_queue); + + return len; +} +__IEEE80211_IF_FILE(hw_queues, NULL); /* STA attributes */ IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC); @@ -217,7 +240,7 @@ static ssize_t ieee80211_if_fmt_smps(const struct ieee80211_sub_if_data *sdata, return snprintf(buf, buflen, "request: %s\nused: %s\n", smps_modes[sdata->u.mgd.req_smps], - smps_modes[sdata->u.mgd.ap_smps]); + smps_modes[sdata->smps_mode]); } static ssize_t ieee80211_if_parse_smps(struct ieee80211_sub_if_data *sdata, @@ -245,27 +268,6 @@ static ssize_t ieee80211_if_fmt_tkip_mic_test( return -EOPNOTSUPP; } -static int hwaddr_aton(const char *txt, u8 *addr) -{ - int i; - - for (i = 0; i < ETH_ALEN; i++) { - int a, b; - - a = hex_to_bin(*txt++); - if (a < 0) - return -1; - b = hex_to_bin(*txt++); - if (b < 0) - return -1; - *addr++ = (a << 4) | b; - if (i < 5 && *txt++ != ':') - return -1; - } - - return 0; -} - static ssize_t ieee80211_if_parse_tkip_mic_test( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { @@ -275,13 +277,7 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( struct ieee80211_hdr *hdr; __le16 fc; - /* - * Assume colon-delimited MAC address with possible white space - * following. - */ - if (buflen < 3 * ETH_ALEN - 1) - return -EINVAL; - if (hwaddr_aton(buf, addr) < 0) + if (!mac_pton(buf, addr)) return -EINVAL; if (!ieee80211_sdata_running(sdata)) @@ -307,13 +303,16 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( case NL80211_IFTYPE_STATION: fc |= cpu_to_le16(IEEE80211_FCTL_TODS); /* BSSID SA DA */ - if (sdata->vif.bss_conf.bssid == NULL) { + mutex_lock(&sdata->u.mgd.mtx); + if (!sdata->u.mgd.associated) { + mutex_unlock(&sdata->u.mgd.mtx); dev_kfree_skb(skb); return -ENOTCONN; } - memcpy(hdr->addr1, sdata->vif.bss_conf.bssid, ETH_ALEN); + memcpy(hdr->addr1, sdata->u.mgd.associated->bssid, ETH_ALEN); memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr->addr3, addr, ETH_ALEN); + mutex_unlock(&sdata->u.mgd.mtx); break; default: dev_kfree_skb(skb); @@ -395,14 +394,14 @@ __IEEE80211_IF_FILE_W(uapsd_max_sp_len); /* AP attributes */ IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC); -IEEE80211_IF_FILE(num_sta_ps, u.ap.num_sta_ps, ATOMIC); -IEEE80211_IF_FILE(dtim_count, u.ap.dtim_count, DEC); +IEEE80211_IF_FILE(num_sta_ps, u.ap.ps.num_sta_ps, ATOMIC); +IEEE80211_IF_FILE(dtim_count, u.ap.ps.dtim_count, DEC); static ssize_t ieee80211_if_fmt_num_buffered_multicast( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { return scnprintf(buf, buflen, "%u\n", - skb_queue_len(&sdata->u.ap.ps_bc_buf)); + skb_queue_len(&sdata->u.ap.ps.bc_buf)); } __IEEE80211_IF_FILE(num_buffered_multicast, NULL); @@ -443,7 +442,7 @@ static ssize_t ieee80211_if_parse_tsf( } ret = kstrtoull(buf, 10, &tsf); if (ret < 0) - return -EINVAL; + return ret; if (tsf_is_delta) tsf = drv_get_tsf(local, sdata) + tsf_is_delta * tsf; if (local->ops->set_tsf) { @@ -471,7 +470,7 @@ IEEE80211_IF_FILE(dropped_frames_congestion, u.mesh.mshstats.dropped_frames_congestion, DEC); IEEE80211_IF_FILE(dropped_frames_no_route, u.mesh.mshstats.dropped_frames_no_route, DEC); -IEEE80211_IF_FILE(estab_plinks, u.mesh.mshstats.estab_plinks, ATOMIC); +IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC); /* Mesh parameters */ IEEE80211_IF_FILE(dot11MeshMaxRetries, @@ -531,6 +530,7 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(rc_rateidx_mask_5ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); + DEBUGFS_ADD(hw_queues); } static void add_sta_files(struct ieee80211_sub_if_data *sdata) @@ -631,7 +631,9 @@ static void add_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(flags); DEBUGFS_ADD(state); - DEBUGFS_ADD(channel_type); + DEBUGFS_ADD(txpower); + DEBUGFS_ADD(user_power_level); + DEBUGFS_ADD(ap_power_level); if (sdata->vif.type != NL80211_IFTYPE_MONITOR) add_common_files(sdata); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 5ccec2c1e9f6..6fb1168b9f16 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -14,6 +14,7 @@ #include "debugfs.h" #include "debugfs_sta.h" #include "sta_info.h" +#include "driver-ops.h" /* sta attributtes */ @@ -52,6 +53,7 @@ static const struct file_operations sta_ ##name## _ops = { \ STA_FILE(aid, sta.aid, D); STA_FILE(dev, sdata->name, S); STA_FILE(last_signal, last_signal, D); +STA_FILE(last_ack_signal, last_ack_signal, D); static ssize_t sta_flags_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -131,10 +133,10 @@ STA_OPS(connected_time); static ssize_t sta_last_seq_ctrl_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - char buf[15*NUM_RX_DATA_QUEUES], *p = buf; + char buf[15*IEEE80211_NUM_TIDS], *p = buf; int i; struct sta_info *sta = file->private_data; - for (i = 0; i < NUM_RX_DATA_QUEUES; i++) + for (i = 0; i < IEEE80211_NUM_TIDS; i++) p += scnprintf(p, sizeof(buf)+buf-p, "%x ", le16_to_cpu(sta->last_seq_ctrl[i])); p += scnprintf(p, sizeof(buf)+buf-p, "\n"); @@ -145,7 +147,7 @@ STA_OPS(last_seq_ctrl); static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - char buf[71 + STA_TID_NUM * 40], *p = buf; + char buf[71 + IEEE80211_NUM_TIDS * 40], *p = buf; int i; struct sta_info *sta = file->private_data; struct tid_ampdu_rx *tid_rx; @@ -158,7 +160,7 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, p += scnprintf(p, sizeof(buf) + buf - p, "TID\t\tRX active\tDTKN\tSSN\t\tTX\tDTKN\tpending\n"); - for (i = 0; i < STA_TID_NUM; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[i]); tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[i]); @@ -218,9 +220,11 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu } else return -EINVAL; - tid = simple_strtoul(buf, NULL, 0); + ret = kstrtoul(buf, 0, &tid); + if (ret) + return ret; - if (tid >= STA_TID_NUM) + if (tid >= IEEE80211_NUM_TIDS) return -EINVAL; if (tx) { @@ -320,6 +324,38 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, } STA_OPS(ht_capa); +static ssize_t sta_current_tx_rate_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct rate_info rinfo; + u16 rate; + sta_set_rate_info_tx(sta, &sta->last_tx_rate, &rinfo); + rate = cfg80211_calculate_bitrate(&rinfo); + + return mac80211_format_buffer(userbuf, count, ppos, + "%d.%d MBit/s\n", + rate/10, rate%10); +} +STA_OPS(current_tx_rate); + +static ssize_t sta_last_rx_rate_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct rate_info rinfo; + u16 rate; + + sta_set_rate_info_rx(sta, &rinfo); + + rate = cfg80211_calculate_bitrate(&rinfo); + + return mac80211_format_buffer(userbuf, count, ppos, + "%d.%d MBit/s\n", + rate/10, rate%10); +} +STA_OPS(last_rx_rate); + #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ sta->debugfs.dir, sta, &sta_ ##name## _ops); @@ -334,6 +370,8 @@ STA_OPS(ht_capa); void ieee80211_sta_debugfs_add(struct sta_info *sta) { + struct ieee80211_local *local = sta->local; + struct ieee80211_sub_if_data *sdata = sta->sdata; struct dentry *stations_dir = sta->sdata->debugfs.subdir_stations; u8 mac[3*ETH_ALEN]; @@ -366,6 +404,9 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(dev); DEBUGFS_ADD(last_signal); DEBUGFS_ADD(ht_capa); + DEBUGFS_ADD(last_ack_signal); + DEBUGFS_ADD(current_tx_rate); + DEBUGFS_ADD(last_rx_rate); DEBUGFS_ADD_COUNTER(rx_packets, rx_packets); DEBUGFS_ADD_COUNTER(tx_packets, tx_packets); @@ -379,10 +420,16 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD_COUNTER(tx_retry_failed, tx_retry_failed); DEBUGFS_ADD_COUNTER(tx_retry_count, tx_retry_count); DEBUGFS_ADD_COUNTER(wep_weak_iv_count, wep_weak_iv_count); + + drv_sta_add_debugfs(local, sdata, &sta->sta, sta->debugfs.dir); } void ieee80211_sta_debugfs_remove(struct sta_info *sta) { + struct ieee80211_local *local = sta->local; + struct ieee80211_sub_if_data *sdata = sta->sdata; + + drv_sta_remove_debugfs(local, sdata, &sta->sta, sta->debugfs.dir); debugfs_remove_recursive(sta->debugfs.dir); sta->debugfs.dir = NULL; } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index f28772443bd3..698dc7e6f309 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -490,6 +490,38 @@ static inline void drv_sta_remove(struct ieee80211_local *local, trace_drv_return_void(local); } +#ifdef CONFIG_MAC80211_DEBUGFS +static inline void drv_sta_add_debugfs(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + struct dentry *dir) +{ + might_sleep(); + + sdata = get_bss_sdata(sdata); + check_sdata_in_driver(sdata); + + if (local->ops->sta_add_debugfs) + local->ops->sta_add_debugfs(&local->hw, &sdata->vif, + sta, dir); +} + +static inline void drv_sta_remove_debugfs(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + struct dentry *dir) +{ + might_sleep(); + + sdata = get_bss_sdata(sdata); + check_sdata_in_driver(sdata); + + if (local->ops->sta_remove_debugfs) + local->ops->sta_remove_debugfs(&local->hw, &sdata->vif, + sta, dir); +} +#endif + static inline __must_check int drv_sta_state(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, @@ -704,17 +736,17 @@ static inline int drv_get_antenna(struct ieee80211_local *local, } static inline int drv_remain_on_channel(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *chan, - enum nl80211_channel_type chantype, unsigned int duration) { int ret; might_sleep(); - trace_drv_remain_on_channel(local, chan, chantype, duration); - ret = local->ops->remain_on_channel(&local->hw, chan, chantype, - duration); + trace_drv_remain_on_channel(local, sdata, chan, duration); + ret = local->ops->remain_on_channel(&local->hw, &sdata->vif, + chan, duration); trace_drv_return_int(local, ret); return ret; @@ -871,4 +903,104 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, local->ops->mgd_prepare_tx(&local->hw, &sdata->vif); trace_drv_return_void(local); } + +static inline int drv_add_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + int ret = -EOPNOTSUPP; + + trace_drv_add_chanctx(local, ctx); + if (local->ops->add_chanctx) + ret = local->ops->add_chanctx(&local->hw, &ctx->conf); + trace_drv_return_int(local, ret); + + return ret; +} + +static inline void drv_remove_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + trace_drv_remove_chanctx(local, ctx); + if (local->ops->remove_chanctx) + local->ops->remove_chanctx(&local->hw, &ctx->conf); + trace_drv_return_void(local); +} + +static inline void drv_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + u32 changed) +{ + trace_drv_change_chanctx(local, ctx, changed); + if (local->ops->change_chanctx) + local->ops->change_chanctx(&local->hw, &ctx->conf, changed); + trace_drv_return_void(local); +} + +static inline int drv_assign_vif_chanctx(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_chanctx *ctx) +{ + int ret = 0; + + check_sdata_in_driver(sdata); + + trace_drv_assign_vif_chanctx(local, sdata, ctx); + if (local->ops->assign_vif_chanctx) + ret = local->ops->assign_vif_chanctx(&local->hw, + &sdata->vif, + &ctx->conf); + trace_drv_return_int(local, ret); + + return ret; +} + +static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_chanctx *ctx) +{ + check_sdata_in_driver(sdata); + + trace_drv_unassign_vif_chanctx(local, sdata, ctx); + if (local->ops->unassign_vif_chanctx) + local->ops->unassign_vif_chanctx(&local->hw, + &sdata->vif, + &ctx->conf); + trace_drv_return_void(local); +} + +static inline int drv_start_ap(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + int ret = 0; + + check_sdata_in_driver(sdata); + + trace_drv_start_ap(local, sdata, &sdata->vif.bss_conf); + if (local->ops->start_ap) + ret = local->ops->start_ap(&local->hw, &sdata->vif); + trace_drv_return_int(local, ret); + return ret; +} + +static inline void drv_stop_ap(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + check_sdata_in_driver(sdata); + + trace_drv_stop_ap(local, sdata); + if (local->ops->stop_ap) + local->ops->stop_ap(&local->hw, &sdata->vif); + trace_drv_return_void(local); +} + +static inline void drv_restart_complete(struct ieee80211_local *local) +{ + might_sleep(); + + trace_drv_restart_complete(local); + if (local->ops->restart_complete) + local->ops->restart_complete(&local->hw); + trace_drv_return_void(local); +} + #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 4b4538d63925..a71d891794a4 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -185,7 +185,7 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, bool tx) cancel_work_sync(&sta->ampdu_mlme.work); - for (i = 0; i < STA_TID_NUM; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { __ieee80211_stop_tx_ba_session(sta, i, WLAN_BACK_INITIATOR, tx); __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, WLAN_REASON_QSTA_LEAVE_QBSS, tx); @@ -209,7 +209,7 @@ void ieee80211_ba_session_work(struct work_struct *work) return; mutex_lock(&sta->ampdu_mlme.mtx); - for (tid = 0; tid < STA_TID_NUM; tid++) { + for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { if (test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_timer_expired)) ___ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 5f3620f0bc0a..6b7644e818d8 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -26,7 +26,6 @@ #include "rate.h" #define IEEE80211_SCAN_INTERVAL (2 * HZ) -#define IEEE80211_SCAN_INTERVAL_SLOW (15 * HZ) #define IEEE80211_IBSS_JOIN_TIMEOUT (7 * HZ) #define IEEE80211_IBSS_MERGE_INTERVAL (30 * HZ) @@ -39,7 +38,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, const u8 *bssid, const int beacon_int, struct ieee80211_channel *chan, const u32 basic_rates, - const u16 capability, u64 tsf) + const u16 capability, u64 tsf, + bool creator) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; @@ -51,7 +51,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *bss; u32 bss_change; u8 supp_rates[IEEE80211_MAX_SUPP_RATES]; - enum nl80211_channel_type channel_type; + struct cfg80211_chan_def chandef; lockdep_assert_held(&ifibss->mtx); @@ -72,25 +72,29 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, /* if merging, indicate to driver that we leave the old IBSS */ if (sdata->vif.bss_conf.ibss_joined) { sdata->vif.bss_conf.ibss_joined = false; + sdata->vif.bss_conf.ibss_creator = false; netif_carrier_off(sdata->dev); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IBSS); } - memcpy(ifibss->bssid, bssid, ETH_ALEN); - sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; - local->oper_channel = chan; - channel_type = ifibss->channel_type; - if (!cfg80211_can_beacon_sec_chan(local->hw.wiphy, chan, channel_type)) - channel_type = NL80211_CHAN_HT20; - if (!ieee80211_set_channel_type(local, sdata, channel_type)) { - /* can only fail due to HT40+/- mismatch */ - channel_type = NL80211_CHAN_HT20; - WARN_ON(!ieee80211_set_channel_type(local, sdata, - NL80211_CHAN_HT20)); + cfg80211_chandef_create(&chandef, chan, ifibss->channel_type); + if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef)) { + chandef.width = NL80211_CHAN_WIDTH_20; + chandef.center_freq1 = chan->center_freq; + } + + ieee80211_vif_release_channel(sdata); + if (ieee80211_vif_use_channel(sdata, &chandef, + ifibss->fixed_channel ? + IEEE80211_CHANCTX_SHARED : + IEEE80211_CHANCTX_EXCLUSIVE)) { + sdata_info(sdata, "Failed to join IBSS, no channel context\n"); + return; } - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + + memcpy(ifibss->bssid, bssid, ETH_ALEN); sband = local->hw.wiphy->bands[chan->band]; @@ -156,7 +160,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, ifibss->ie, ifibss->ie_len); /* add HT capability and information IEs */ - if (channel_type && sband->ht_cap.ht_supported) { + if (chandef.width != NL80211_CHAN_WIDTH_20_NOHT && + sband->ht_cap.ht_supported) { pos = skb_put(skb, 4 + sizeof(struct ieee80211_ht_cap) + sizeof(struct ieee80211_ht_operation)); @@ -168,7 +173,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, * keep them at 0 */ pos = ieee80211_ie_build_ht_oper(pos, &sband->ht_cap, - chan, channel_type, 0); + &chandef, 0); } if (local->hw.queues >= IEEE80211_NUM_ACS) { @@ -196,7 +201,22 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, bss_change |= BSS_CHANGED_BASIC_RATES; bss_change |= BSS_CHANGED_HT; bss_change |= BSS_CHANGED_IBSS; + + /* + * In 5 GHz/802.11a, we can always use short slot time. + * (IEEE 802.11-2012 18.3.8.7) + * + * In 2.4GHz, we must always use long slots in IBSS for compatibility + * reasons. + * (IEEE 802.11-2012 19.4.5) + * + * HT follows these specifications (IEEE 802.11-2012 20.3.18) + */ + sdata->vif.bss_conf.use_short_slot = chan->band == IEEE80211_BAND_5GHZ; + bss_change |= BSS_CHANGED_ERP_SLOT; + sdata->vif.bss_conf.ibss_joined = true; + sdata->vif.bss_conf.ibss_creator = creator; ieee80211_bss_info_change_notify(sdata, bss_change); ieee80211_sta_def_wmm_params(sdata, sband->n_bitrates, supp_rates); @@ -249,7 +269,8 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, cbss->channel, basic_rates, cbss->capability, - cbss->tsf); + cbss->tsf, + false); } static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta, @@ -279,7 +300,7 @@ static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta, ibss_dbg(sdata, "TX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=1)\n", sdata->vif.addr, addr, sdata->u.ibss.bssid); - ieee80211_send_auth(sdata, 1, WLAN_AUTH_OPEN, NULL, 0, + ieee80211_send_auth(sdata, 1, WLAN_AUTH_OPEN, 0, NULL, 0, addr, sdata->u.ibss.bssid, NULL, 0, 0); } return sta; @@ -294,7 +315,8 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; struct sta_info *sta; - int band = local->oper_channel->band; + struct ieee80211_chanctx_conf *chanctx_conf; + int band; /* * XXX: Consider removing the least recently used entry and @@ -317,6 +339,13 @@ ieee80211_ibss_add_sta(struct ieee80211_sub_if_data *sdata, return NULL; } + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON_ONCE(!chanctx_conf)) + return NULL; + band = chanctx_conf->def.chan->band; + rcu_read_unlock(); + sta = sta_info_alloc(sdata, addr, GFP_KERNEL); if (!sta) { rcu_read_lock(); @@ -362,11 +391,13 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg); auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction); - if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1) - return; ibss_dbg(sdata, "RX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=%d)\n", mgmt->sa, mgmt->da, mgmt->bssid, auth_transaction); + + if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1) + return; + sta_info_destroy_addr(sdata, mgmt->sa); sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid, mgmt->sa, 0, false); rcu_read_unlock(); @@ -389,7 +420,7 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, * However, try to reply to authentication attempts if someone * has actually implemented this. */ - ieee80211_send_auth(sdata, 2, WLAN_AUTH_OPEN, NULL, 0, + ieee80211_send_auth(sdata, 2, WLAN_AUTH_OPEN, 0, NULL, 0, mgmt->sa, sdata->u.ibss.bssid, NULL, 0, 0); } @@ -461,9 +492,11 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, sdata->u.ibss.channel_type != NL80211_CHAN_NO_HT) { /* we both use HT */ struct ieee80211_sta_ht_cap sta_ht_cap_new; - enum nl80211_channel_type channel_type = - ieee80211_ht_oper_to_channel_type( - elems->ht_operation); + struct cfg80211_chan_def chandef; + + ieee80211_ht_oper_to_chandef(channel, + elems->ht_operation, + &chandef); ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, elems->ht_cap_elem, @@ -473,9 +506,9 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, * fall back to HT20 if we don't use or use * the other extension channel */ - if (!(channel_type == NL80211_CHAN_HT40MINUS || - channel_type == NL80211_CHAN_HT40PLUS) || - channel_type != sdata->u.ibss.channel_type) + if (chandef.width != NL80211_CHAN_WIDTH_40 || + cfg80211_get_chandef_type(&chandef) != + sdata->u.ibss.channel_type) sta_ht_cap_new.cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; @@ -517,7 +550,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, goto put_bss; /* different channel */ - if (cbss->channel != local->oper_channel) + if (sdata->u.ibss.fixed_channel && + sdata->u.ibss.channel != cbss->channel) goto put_bss; /* different SSID */ @@ -530,30 +564,11 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, if (ether_addr_equal(cbss->bssid, sdata->u.ibss.bssid)) goto put_bss; - if (rx_status->flag & RX_FLAG_MACTIME_MPDU) { - /* - * For correct IBSS merging we need mactime; since mactime is - * defined as the time the first data symbol of the frame hits - * the PHY, and the timestamp of the beacon is defined as "the - * time that the data symbol containing the first bit of the - * timestamp is transmitted to the PHY plus the transmitting - * STA's delays through its local PHY from the MAC-PHY - * interface to its interface with the WM" (802.11 11.1.2) - * - equals the time this bit arrives at the receiver - we have - * to take into account the offset between the two. - * - * E.g. at 1 MBit that means mactime is 192 usec earlier - * (=24 bytes * 8 usecs/byte) than the beacon timestamp. - */ - int rate; - - if (rx_status->flag & RX_FLAG_HT) - rate = 65; /* TODO: HT rates */ - else - rate = local->hw.wiphy->bands[band]-> - bitrates[rx_status->rate_idx].bitrate; - - rx_timestamp = rx_status->mactime + (24 * 8 * 10 / rate); + if (ieee80211_have_rx_timestamp(rx_status)) { + /* time when timestamp field was received */ + rx_timestamp = + ieee80211_calculate_rx_timestamp(local, rx_status, + len + FCS_LEN, 24); } else { /* * second best option: get current TSF @@ -592,7 +607,8 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; struct sta_info *sta; - int band = local->oper_channel->band; + struct ieee80211_chanctx_conf *chanctx_conf; + int band; /* * XXX: Consider removing the least recently used entry and @@ -610,6 +626,15 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata, if (!ether_addr_equal(bssid, sdata->u.ibss.bssid)) return; + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON_ONCE(!chanctx_conf)) { + rcu_read_unlock(); + return; + } + band = chanctx_conf->def.chan->band; + rcu_read_unlock(); + sta = sta_info_alloc(sdata, addr, GFP_ATOMIC); if (!sta) return; @@ -678,8 +703,8 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata) sdata_info(sdata, "No active IBSS STAs - trying to scan for other IBSS networks with same SSID (merge)\n"); - ieee80211_request_internal_scan(sdata, - ifibss->ssid, ifibss->ssid_len, NULL); + ieee80211_request_ibss_scan(sdata, ifibss->ssid, ifibss->ssid_len, + NULL); } static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) @@ -715,7 +740,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) __ieee80211_sta_join_ibss(sdata, bssid, sdata->vif.bss_conf.beacon_int, ifibss->channel, ifibss->basic_rates, - capability, 0); + capability, 0, true); } /* @@ -777,25 +802,14 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) IEEE80211_SCAN_INTERVAL)) { sdata_info(sdata, "Trigger new scan to find an IBSS to join\n"); - ieee80211_request_internal_scan(sdata, - ifibss->ssid, ifibss->ssid_len, - ifibss->fixed_channel ? ifibss->channel : NULL); + ieee80211_request_ibss_scan(sdata, ifibss->ssid, + ifibss->ssid_len, chan); } else { int interval = IEEE80211_SCAN_INTERVAL; if (time_after(jiffies, ifibss->ibss_join_req + - IEEE80211_IBSS_JOIN_TIMEOUT)) { - if (!(local->oper_channel->flags & IEEE80211_CHAN_NO_IBSS)) { - ieee80211_sta_create_ibss(sdata); - return; - } - sdata_info(sdata, "IBSS not allowed on %d MHz\n", - local->oper_channel->center_freq); - - /* No IBSS found - decrease scan interval and continue - * scanning. */ - interval = IEEE80211_SCAN_INTERVAL_SLOW; - } + IEEE80211_IBSS_JOIN_TIMEOUT)) + ieee80211_sta_create_ibss(sdata); mod_timer(&ifibss->timer, round_jiffies(jiffies + interval)); @@ -1082,21 +1096,11 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.beacon_int = params->beacon_interval; - sdata->u.ibss.channel = params->channel; - sdata->u.ibss.channel_type = params->channel_type; + sdata->u.ibss.channel = params->chandef.chan; + sdata->u.ibss.channel_type = + cfg80211_get_chandef_type(¶ms->chandef); sdata->u.ibss.fixed_channel = params->channel_fixed; - /* fix ourselves to that channel now already */ - if (params->channel_fixed) { - sdata->local->oper_channel = params->channel; - if (!ieee80211_set_channel_type(sdata->local, sdata, - params->channel_type)) { - mutex_unlock(&sdata->u.ibss.mtx); - kfree_skb(skb); - return -EINVAL; - } - } - if (params->ie) { sdata->u.ibss.ie = kmemdup(params->ie, params->ie_len, GFP_KERNEL); @@ -1108,7 +1112,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, sdata->u.ibss.state = IEEE80211_IBSS_MLME_SEARCH; sdata->u.ibss.ibss_join_req = jiffies; - memcpy(sdata->u.ibss.ssid, params->ssid, IEEE80211_MAX_SSID_LEN); + memcpy(sdata->u.ibss.ssid, params->ssid, params->ssid_len); sdata->u.ibss.ssid_len = params->ssid_len; mutex_unlock(&sdata->u.ibss.mtx); @@ -1134,6 +1138,9 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, changed |= BSS_CHANGED_HT; ieee80211_bss_info_change_notify(sdata, changed); + sdata->smps_mode = IEEE80211_SMPS_OFF; + sdata->needed_rx_chains = sdata->local->rx_chains; + ieee80211_queue_work(&sdata->local->hw, &sdata->work); return 0; @@ -1151,10 +1158,6 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->u.ibss.mtx); - sdata->u.ibss.state = IEEE80211_IBSS_MLME_SEARCH; - memset(sdata->u.ibss.bssid, 0, ETH_ALEN); - sdata->u.ibss.ssid_len = 0; - active_ibss = ieee80211_sta_active_ibss(sdata); if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) { @@ -1175,6 +1178,10 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) } } + ifibss->state = IEEE80211_IBSS_MLME_SEARCH; + memset(ifibss->bssid, 0, ETH_ALEN); + ifibss->ssid_len = 0; + sta_info_flush(sdata->local, sdata); spin_lock_bh(&ifibss->incomplete_lock); @@ -1197,6 +1204,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) lockdep_is_held(&sdata->u.ibss.mtx)); RCU_INIT_POINTER(sdata->u.ibss.presp, NULL); sdata->vif.bss_conf.ibss_joined = false; + sdata->vif.bss_conf.ibss_creator = false; ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_IBSS); synchronize_rcu(); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8c804550465b..2ed065c09562 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -56,6 +56,9 @@ struct ieee80211_local; #define TU_TO_JIFFIES(x) (usecs_to_jiffies((x) * 1024)) #define TU_TO_EXP_TIME(x) (jiffies + TU_TO_JIFFIES(x)) +/* power level hasn't been configured (or set to automatic) */ +#define IEEE80211_UNSET_POWER_LEVEL INT_MIN + /* * Some APs experience problems when working with U-APSD. Decrease the * probability of that happening by using legacy mode for all ACs but VO. @@ -89,8 +92,6 @@ struct ieee80211_bss { u32 device_ts; - u8 dtim_period; - bool wmm_used; bool uapsd_supported; @@ -137,7 +138,6 @@ enum ieee80211_bss_corrupt_data_flags { /** * enum ieee80211_valid_data_flags - BSS valid data flags - * @IEEE80211_BSS_VALID_DTIM: DTIM data was gathered from non-corrupt IE * @IEEE80211_BSS_VALID_WMM: WMM/UAPSD data was gathered from non-corrupt IE * @IEEE80211_BSS_VALID_RATES: Supported rates were gathered from non-corrupt IE * @IEEE80211_BSS_VALID_ERP: ERP flag was gathered from non-corrupt IE @@ -148,7 +148,6 @@ enum ieee80211_bss_corrupt_data_flags { * beacon/probe response. */ enum ieee80211_bss_valid_data_flags { - IEEE80211_BSS_VALID_DTIM = BIT(0), IEEE80211_BSS_VALID_WMM = BIT(1), IEEE80211_BSS_VALID_RATES = BIT(2), IEEE80211_BSS_VALID_ERP = BIT(3) @@ -280,23 +279,27 @@ struct probe_resp { u8 data[0]; }; -struct ieee80211_if_ap { - struct beacon_data __rcu *beacon; - struct probe_resp __rcu *probe_resp; - - struct list_head vlans; - +struct ps_data { /* yes, this looks ugly, but guarantees that we can later use * bitmap_empty :) * NB: don't touch this bitmap, use sta_info_{set,clear}_tim_bit */ u8 tim[sizeof(unsigned long) * BITS_TO_LONGS(IEEE80211_MAX_AID + 1)]; - struct sk_buff_head ps_bc_buf; + struct sk_buff_head bc_buf; atomic_t num_sta_ps; /* number of stations in PS mode */ - atomic_t num_mcast_sta; /* number of stations receiving multicast */ int dtim_count; bool dtim_bc_mc; }; +struct ieee80211_if_ap { + struct beacon_data __rcu *beacon; + struct probe_resp __rcu *probe_resp; + + struct list_head vlans; + + struct ps_data ps; + atomic_t num_mcast_sta; /* number of stations receiving multicast */ +}; + struct ieee80211_if_wds { struct sta_info *sta; u8 remote_addr[ETH_ALEN]; @@ -316,7 +319,6 @@ struct mesh_stats { __u32 dropped_frames_ttl; /* Not transmitted since mesh_ttl == 0*/ __u32 dropped_frames_no_route; /* Not transmitted, no route found */ __u32 dropped_frames_congestion;/* Not forwarded due to congestion */ - atomic_t estab_plinks; }; #define PREQ_Q_F_START 0x1 @@ -342,7 +344,6 @@ struct ieee80211_roc_work { struct ieee80211_sub_if_data *sdata; struct ieee80211_channel *chan; - enum nl80211_channel_type chan_type; bool started, abort, hw_begun, notified; @@ -350,7 +351,7 @@ struct ieee80211_roc_work { u32 duration, req_duration; struct sk_buff *frame; - u64 mgmt_tx_cookie; + u64 cookie, mgmt_tx_cookie; }; /* flags used in struct ieee80211_if_managed.flags */ @@ -358,7 +359,7 @@ enum ieee80211_sta_flags { IEEE80211_STA_BEACON_POLL = BIT(0), IEEE80211_STA_CONNECTION_POLL = BIT(1), IEEE80211_STA_CONTROL_PORT = BIT(2), - IEEE80211_STA_DISABLE_11N = BIT(4), + IEEE80211_STA_DISABLE_HT = BIT(4), IEEE80211_STA_CSA_RECEIVED = BIT(5), IEEE80211_STA_MFP_ENABLED = BIT(6), IEEE80211_STA_UAPSD_ENABLED = BIT(7), @@ -366,6 +367,8 @@ enum ieee80211_sta_flags { IEEE80211_STA_RESET_SIGNAL_AVE = BIT(9), IEEE80211_STA_DISABLE_40MHZ = BIT(10), IEEE80211_STA_DISABLE_VHT = BIT(11), + IEEE80211_STA_DISABLE_80P80MHZ = BIT(12), + IEEE80211_STA_DISABLE_160MHZ = BIT(13), }; struct ieee80211_mgd_auth_data { @@ -378,8 +381,9 @@ struct ieee80211_mgd_auth_data { u8 key_len, key_idx; bool done; - size_t ie_len; - u8 ie[]; + u16 sae_trans, sae_status; + size_t data_len; + u8 data[]; }; struct ieee80211_mgd_assoc_data { @@ -432,8 +436,8 @@ struct ieee80211_if_managed { unsigned long timers_running; /* used for quiesce/restart */ bool powersave; /* powersave requested for this iface */ bool broken_ap; /* AP is broken -- turn off powersave */ + u8 dtim_period; enum ieee80211_smps_mode req_smps, /* requested smps mode */ - ap_smps, /* smps mode AP thinks we're in */ driver_smps_mode; /* smps mode request */ struct work_struct request_smps_work; @@ -467,6 +471,8 @@ struct ieee80211_if_managed { u8 use_4addr; + u8 p2p_noa_index; + /* Signal strength from the last Beacon frame in the current BSS. */ int last_beacon_signal; @@ -599,6 +605,7 @@ struct ieee80211_if_mesh { int preq_queue_len; struct mesh_stats mshstats; struct mesh_config mshcfg; + atomic_t estab_plinks; u32 mesh_seqnum; bool accepting_plinks; int num_gates; @@ -610,7 +617,7 @@ struct ieee80211_if_mesh { IEEE80211_MESH_SEC_SECURED = 0x2, } security; /* Extensible Synchronization Framework */ - struct ieee80211_mesh_sync_ops *sync_ops; + const struct ieee80211_mesh_sync_ops *sync_ops; s64 sync_offset_clockdrift_max; spinlock_t sync_offset_lock; bool adjusting_tbtt; @@ -658,6 +665,30 @@ enum ieee80211_sdata_state_bits { SDATA_STATE_OFFCHANNEL, }; +/** + * enum ieee80211_chanctx_mode - channel context configuration mode + * + * @IEEE80211_CHANCTX_SHARED: channel context may be used by + * multiple interfaces + * @IEEE80211_CHANCTX_EXCLUSIVE: channel context can be used + * only by a single interface. This can be used for example for + * non-fixed channel IBSS. + */ +enum ieee80211_chanctx_mode { + IEEE80211_CHANCTX_SHARED, + IEEE80211_CHANCTX_EXCLUSIVE +}; + +struct ieee80211_chanctx { + struct list_head list; + struct rcu_head rcu_head; + + enum ieee80211_chanctx_mode mode; + int refcount; + + struct ieee80211_chanctx_conf conf; +}; + struct ieee80211_sub_if_data { struct list_head list; @@ -704,11 +735,20 @@ struct ieee80211_sub_if_data { struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS]; + /* used to reconfigure hardware SM PS */ + struct work_struct recalc_smps; + struct work_struct work; struct sk_buff_head skb_queue; bool arp_filter_state; + u8 needed_rx_chains; + enum ieee80211_smps_mode smps_mode; + + int user_power_level; /* in dBm */ + int ap_power_level; /* in dBm */ + /* * AP this belongs to: self in AP mode and * corresponding AP in VLAN mode, NULL for @@ -730,6 +770,10 @@ struct ieee80211_sub_if_data { u32 mntr_flags; } u; + spinlock_t cleanup_stations_lock; + struct list_head cleanup_stations; + struct work_struct cleanup_stations_wk; + #ifdef CONFIG_MAC80211_DEBUGFS struct { struct dentry *dir; @@ -749,6 +793,21 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p) return container_of(p, struct ieee80211_sub_if_data, vif); } +static inline enum ieee80211_band +ieee80211_get_sdata_band(struct ieee80211_sub_if_data *sdata) +{ + enum ieee80211_band band = IEEE80211_BAND_2GHZ; + struct ieee80211_chanctx_conf *chanctx_conf; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!WARN_ON(!chanctx_conf)) + band = chanctx_conf->def.chan->band; + rcu_read_unlock(); + + return band; +} + enum sdata_queue_type { IEEE80211_SDATA_QUEUE_TYPE_FRAME = 0, IEEE80211_SDATA_QUEUE_AGG_START = 1, @@ -821,6 +880,7 @@ enum { * @SCAN_SUSPEND: Suspend the scan and go back to operating channel to * send out data * @SCAN_RESUME: Resume the scan and scan the next channel + * @SCAN_ABORT: Abort the scan and go back to operating channel */ enum mac80211_scan_state { SCAN_DECISION, @@ -828,6 +888,7 @@ enum mac80211_scan_state { SCAN_SEND_PROBE, SCAN_SUSPEND, SCAN_RESUME, + SCAN_ABORT, }; struct ieee80211_local { @@ -858,15 +919,14 @@ struct ieee80211_local { bool wiphy_ciphers_allocated; + bool use_chanctx; + /* protects the aggregated multicast list and filter calls */ spinlock_t filter_lock; /* used for uploading changed mc list */ struct work_struct reconfig_filter; - /* used to reconfigure hardware SM PS */ - struct work_struct recalc_smps; - /* aggregated multicast list */ struct netdev_hw_addr_list mc_list; @@ -903,6 +963,9 @@ struct ieee80211_local { /* wowlan is enabled -- don't reconfig on resume */ bool wowlan; + /* number of RX chains the hardware has */ + u8 rx_chains; + int tx_headroom; /* required headroom for hardware/radiotap */ /* Tasklet and skb queue to process calls from IRQ mode. All frames @@ -972,6 +1035,7 @@ struct ieee80211_local { enum ieee80211_band hw_scan_band; int scan_channel_idx; int scan_ies_len; + int hw_scan_ies_bufsize; struct work_struct sched_scan_stopped_work; struct ieee80211_sub_if_data __rcu *sched_scan_sdata; @@ -980,12 +1044,17 @@ struct ieee80211_local { enum mac80211_scan_state next_scan_state; struct delayed_work scan_work; struct ieee80211_sub_if_data __rcu *scan_sdata; + struct ieee80211_channel *csa_channel; + /* For backward compatibility only -- do not use */ + struct ieee80211_channel *_oper_channel; enum nl80211_channel_type _oper_channel_type; - struct ieee80211_channel *oper_channel, *csa_channel; /* Temporary remain-on-channel for off-channel operations */ struct ieee80211_channel *tmp_channel; - enum nl80211_channel_type tmp_channel_type; + + /* channel contexts */ + struct list_head chanctx_list; + struct mutex chanctx_mtx; /* SNMP counters */ /* dot11CountersTable */ @@ -1058,8 +1127,7 @@ struct ieee80211_local { int dynamic_ps_user_timeout; bool disable_dynamic_ps; - int user_power_level; /* in dBm */ - int ap_power_level; /* in dBm */ + int user_power_level; /* in dBm, for all interfaces */ enum ieee80211_smps_mode smps_mode; @@ -1078,6 +1146,7 @@ struct ieee80211_local { struct list_head roc_list; struct work_struct hw_roc_start, hw_roc_done; unsigned long hw_roc_start_time; + u64 roc_cookie_counter; struct idr ack_status_frames; spinlock_t ack_status_lock; @@ -1091,6 +1160,7 @@ struct ieee80211_local { /* virtual monitor interface */ struct ieee80211_sub_if_data __rcu *monitor_sdata; + struct cfg80211_chan_def monitor_chandef; }; static inline struct ieee80211_sub_if_data * @@ -1133,6 +1203,8 @@ struct ieee802_11_elems { u8 *wmm_param; struct ieee80211_ht_cap *ht_cap_elem; struct ieee80211_ht_operation *ht_operation; + struct ieee80211_vht_cap *vht_cap_elem; + struct ieee80211_vht_operation *vht_operation; struct ieee80211_meshconf_ie *mesh_config; u8 *mesh_id; u8 *peering; @@ -1188,7 +1260,18 @@ static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr) is_broadcast_ether_addr(raddr); } +static inline bool +ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status) +{ + WARN_ON_ONCE(status->flag & RX_FLAG_MACTIME_START && + status->flag & RX_FLAG_MACTIME_END); + return status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END); +} +u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, + struct ieee80211_rx_status *status, + unsigned int mpdu_len, + unsigned int mpdu_offset); int ieee80211_hw_config(struct ieee80211_local *local, u32 changed); void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx); void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, @@ -1247,9 +1330,9 @@ void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, /* scan/BSS handling */ void ieee80211_scan_work(struct work_struct *work); -int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, - const u8 *ssid, u8 ssid_len, - struct ieee80211_channel *chan); +int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, + const u8 *ssid, u8 ssid_len, + struct ieee80211_channel *chan); int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req); void ieee80211_scan_cancel(struct ieee80211_local *local); @@ -1275,10 +1358,8 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata); void ieee80211_sched_scan_stopped_work(struct work_struct *work); /* off-channel helpers */ -void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, - bool offchannel_ps_enable); -void ieee80211_offchannel_return(struct ieee80211_local *local, - bool offchannel_ps_disable); +void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local); +void ieee80211_offchannel_return(struct ieee80211_local *local); void ieee80211_roc_setup(struct ieee80211_local *local); void ieee80211_start_next_roc(struct ieee80211_local *local); void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata); @@ -1302,6 +1383,9 @@ void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up); void ieee80211_sdata_stop(struct ieee80211_sub_if_data *sdata); +bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata); +void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata); + static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata) { return test_bit(SDATA_STATE_RUNNING, &sdata->state); @@ -1314,6 +1398,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs); /* HT */ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, @@ -1359,6 +1445,13 @@ void ieee80211_ba_session_work(struct work_struct *work); void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid); void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid); +u8 ieee80211_mcs_to_chains(const struct ieee80211_mcs_info *mcs); + +/* VHT */ +void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct ieee80211_vht_cap *vht_cap_ie, + struct ieee80211_sta_vht_cap *vht_cap); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, @@ -1393,11 +1486,42 @@ void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int ke gfp_t gfp); void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, bool bss_notify); -void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); +void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, + enum ieee80211_band band); + +void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, int tid, + enum ieee80211_band band); -void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, int tid); -static void inline ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, +static inline void +ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, int tid, + enum ieee80211_band band) +{ + rcu_read_lock(); + __ieee80211_tx_skb_tid_band(sdata, skb, tid, band); + rcu_read_unlock(); +} + +static inline void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, int tid) +{ + struct ieee80211_chanctx_conf *chanctx_conf; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + kfree_skb(skb); + return; + } + + __ieee80211_tx_skb_tid_band(sdata, skb, tid, + chanctx_conf->def.chan->band); + rcu_read_unlock(); +} + +static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { /* Send all internal mgmt frames on VO. Accordingly set TID to 7. */ @@ -1444,14 +1568,14 @@ static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local, } void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, - u16 transaction, u16 auth_alg, + u16 transaction, u16 auth_alg, u16 status, u8 *extra, size_t extra_len, const u8 *bssid, const u8 *da, const u8 *key, u8 key_len, u8 key_idx); void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, const u8 *bssid, u16 stype, u16 reason, bool send_frame, u8 *frame_buf); int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, - const u8 *ie, size_t ie_len, + size_t buffer_len, const u8 *ie, size_t ie_len, enum ieee80211_band band, u32 rate_mask, u8 channel); struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, @@ -1464,7 +1588,7 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, u32 ratemask, bool directed, bool no_cck, - struct ieee80211_channel *channel); + struct ieee80211_channel *channel, bool scan); void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, const size_t supp_rates_len, @@ -1474,7 +1598,7 @@ u32 ieee80211_sta_get_rates(struct ieee80211_local *local, enum ieee80211_band band, u32 *basic_rates); int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode); -void ieee80211_recalc_smps(struct ieee80211_local *local); +void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata); size_t ieee80211_ie_split(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, size_t offset); @@ -1482,8 +1606,7 @@ size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset); u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, u16 cap); u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, - struct ieee80211_channel *channel, - enum nl80211_channel_type channel_type, + const struct cfg80211_chan_def *chandef, u16 prot_mode); u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); @@ -1495,20 +1618,19 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band); /* channel management */ -enum ieee80211_chan_mode { - CHAN_MODE_UNDEFINED, - CHAN_MODE_HOPPING, - CHAN_MODE_FIXED, -}; - -enum ieee80211_chan_mode -ieee80211_get_channel_mode(struct ieee80211_local *local, - struct ieee80211_sub_if_data *ignore); -bool ieee80211_set_channel_type(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum nl80211_channel_type chantype); -enum nl80211_channel_type -ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper); +void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan, + struct ieee80211_ht_operation *ht_oper, + struct cfg80211_chan_def *chandef); + +int __must_check +ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata, + const struct cfg80211_chan_def *chandef, + enum ieee80211_chanctx_mode mode); +void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata); +void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata); + +void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *chanctx); #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7de7717ad67d..8be854e86cd9 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -42,6 +42,41 @@ * by either the RTNL, the iflist_mtx or RCU. */ +bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_chanctx_conf *chanctx_conf; + int power; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) { + rcu_read_unlock(); + return false; + } + + power = chanctx_conf->def.chan->max_power; + rcu_read_unlock(); + + if (sdata->user_power_level != IEEE80211_UNSET_POWER_LEVEL) + power = min(power, sdata->user_power_level); + + if (sdata->ap_power_level != IEEE80211_UNSET_POWER_LEVEL) + power = min(power, sdata->ap_power_level); + + if (power != sdata->vif.bss_conf.txpower) { + sdata->vif.bss_conf.txpower = power; + ieee80211_hw_config(sdata->local, 0); + return true; + } + + return false; +} + +void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata) +{ + if (__ieee80211_recalc_txpower(sdata)) + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER); +} static u32 ieee80211_idle_off(struct ieee80211_local *local, const char *reason) @@ -172,22 +207,54 @@ void ieee80211_recalc_idle(struct ieee80211_local *local) static int ieee80211_change_mtu(struct net_device *dev, int new_mtu) { - int meshhdrlen; - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - meshhdrlen = (sdata->vif.type == NL80211_IFTYPE_MESH_POINT) ? 5 : 0; - - /* FIX: what would be proper limits for MTU? - * This interface uses 802.3 frames. */ - if (new_mtu < 256 || - new_mtu > IEEE80211_MAX_DATA_LEN - 24 - 6 - meshhdrlen) { + if (new_mtu < 256 || new_mtu > IEEE80211_MAX_DATA_LEN) return -EINVAL; - } dev->mtu = new_mtu; return 0; } +static int ieee80211_verify_mac(struct ieee80211_local *local, u8 *addr) +{ + struct ieee80211_sub_if_data *sdata; + u64 new, mask, tmp; + u8 *m; + int ret = 0; + + if (is_zero_ether_addr(local->hw.wiphy->addr_mask)) + return 0; + + m = addr; + new = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | + ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | + ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); + + m = local->hw.wiphy->addr_mask; + mask = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | + ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | + ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); + + + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->vif.type == NL80211_IFTYPE_MONITOR) + continue; + + m = sdata->vif.addr; + tmp = ((u64)m[0] << 5*8) | ((u64)m[1] << 4*8) | + ((u64)m[2] << 3*8) | ((u64)m[3] << 2*8) | + ((u64)m[4] << 1*8) | ((u64)m[5] << 0*8); + + if ((new & ~mask) != (tmp & ~mask)) { + ret = -EINVAL; + break; + } + } + mutex_unlock(&local->iflist_mtx); + + return ret; +} + static int ieee80211_change_mac(struct net_device *dev, void *addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -197,6 +264,10 @@ static int ieee80211_change_mac(struct net_device *dev, void *addr) if (ieee80211_sdata_running(sdata)) return -EBUSY; + ret = ieee80211_verify_mac(sdata->local, sa->sa_data); + if (ret) + return ret; + ret = eth_mac_addr(dev, sa); if (ret == 0) @@ -380,6 +451,14 @@ static int ieee80211_add_virtual_monitor(struct ieee80211_local *local) goto out_unlock; } + ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef, + IEEE80211_CHANCTX_EXCLUSIVE); + if (ret) { + drv_remove_interface(local, sdata); + kfree(sdata); + goto out_unlock; + } + rcu_assign_pointer(local->monitor_sdata, sdata); out_unlock: mutex_unlock(&local->iflist_mtx); @@ -403,6 +482,8 @@ static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) rcu_assign_pointer(local->monitor_sdata, NULL); synchronize_net(); + ieee80211_vif_release_channel(sdata); + drv_remove_interface(local, sdata); kfree(sdata); @@ -496,11 +577,13 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: - /* no need to tell driver, but set carrier */ - if (rtnl_dereference(sdata->bss->beacon)) + /* no need to tell driver, but set carrier and chanctx */ + if (rtnl_dereference(sdata->bss->beacon)) { + ieee80211_vif_vlan_copy_chanctx(sdata); netif_carrier_on(dev); - else + } else { netif_carrier_off(dev); + } break; case NL80211_IFTYPE_MONITOR: if (sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) { @@ -665,7 +748,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; int i; - enum nl80211_channel_type orig_ct; clear_bit(SDATA_STATE_RUNNING, &sdata->state); @@ -729,34 +811,17 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, del_timer_sync(&local->dynamic_ps_timer); cancel_work_sync(&local->dynamic_ps_enable_work); + cancel_work_sync(&sdata->recalc_smps); + /* APs need special treatment */ if (sdata->vif.type == NL80211_IFTYPE_AP) { struct ieee80211_sub_if_data *vlan, *tmpsdata; - struct beacon_data *old_beacon = - rtnl_dereference(sdata->u.ap.beacon); - struct probe_resp *old_probe_resp = - rtnl_dereference(sdata->u.ap.probe_resp); - - /* sdata_running will return false, so this will disable */ - ieee80211_bss_info_change_notify(sdata, - BSS_CHANGED_BEACON_ENABLED); - - /* remove beacon and probe response */ - RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); - RCU_INIT_POINTER(sdata->u.ap.probe_resp, NULL); - synchronize_rcu(); - kfree(old_beacon); - kfree(old_probe_resp); /* down all dependent devices, that is VLANs */ list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, u.vlan.list) dev_close(vlan->dev); WARN_ON(!list_empty(&sdata->u.ap.vlans)); - - /* free all potentially still buffered bcast frames */ - local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps_bc_buf); - skb_queue_purge(&sdata->u.ap.ps_bc_buf); } else if (sdata->vif.type == NL80211_IFTYPE_STATION) { ieee80211_mgd_stop(sdata); } @@ -767,6 +832,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: list_del(&sdata->u.vlan.list); + rcu_assign_pointer(sdata->vif.chanctx_conf, NULL); /* no need to tell driver */ break; case NL80211_IFTYPE_MONITOR: @@ -790,23 +856,14 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, rcu_assign_pointer(local->p2p_sdata, NULL); /* fall through */ default: - flush_work(&sdata->work); + cancel_work_sync(&sdata->work); /* * When we get here, the interface is marked down. - * Call rcu_barrier() to wait both for the RX path + * Call synchronize_rcu() to wait for the RX path * should it be using the interface and enqueuing - * frames at this very time on another CPU, and - * for the sta free call_rcu callbacks. - */ - rcu_barrier(); - - /* - * free_sta_rcu() enqueues a work for the actual - * sta cleanup, so we need to flush it while - * sdata is still valid. + * frames at this very time on another CPU. */ - flush_workqueue(local->workqueue); - + synchronize_rcu(); skb_queue_purge(&sdata->skb_queue); /* @@ -837,14 +894,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, hw_reconf_flags = 0; } - /* Re-calculate channel-type, in case there are multiple vifs - * on different channel types. - */ - orig_ct = local->_oper_channel_type; - ieee80211_set_channel_type(local, NULL, NL80211_CHAN_NO_HT); - /* do after stop to avoid reconfiguring when we stop anyway */ - if (hw_reconf_flags || (orig_ct != local->_oper_channel_type)) + if (hw_reconf_flags) ieee80211_hw_config(local, hw_reconf_flags); spin_lock_irqsave(&local->queue_stop_reason_lock, flags); @@ -1121,6 +1172,13 @@ static void ieee80211_iface_work(struct work_struct *work) } } +static void ieee80211_recalc_smps_work(struct work_struct *work) +{ + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, recalc_smps); + + ieee80211_recalc_smps(sdata); +} /* * Helper function to initialise an interface to a specific type. @@ -1149,6 +1207,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, skb_queue_head_init(&sdata->skb_queue); INIT_WORK(&sdata->work, ieee80211_iface_work); + INIT_WORK(&sdata->recalc_smps, ieee80211_recalc_smps_work); switch (type) { case NL80211_IFTYPE_P2P_GO: @@ -1157,7 +1216,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->vif.p2p = true; /* fall through */ case NL80211_IFTYPE_AP: - skb_queue_head_init(&sdata->u.ap.ps_bc_buf); + skb_queue_head_init(&sdata->u.ap.ps.bc_buf); INIT_LIST_HEAD(&sdata->u.ap.vlans); break; case NL80211_IFTYPE_P2P_CLIENT: @@ -1282,11 +1341,6 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, if (type == ieee80211_vif_type_p2p(&sdata->vif)) return 0; - /* Setting ad-hoc mode on non-IBSS channel is not supported. */ - if (sdata->local->oper_channel->flags & IEEE80211_CHAN_NO_IBSS && - type == NL80211_IFTYPE_ADHOC) - return -EOPNOTSUPP; - if (ieee80211_sdata_running(sdata)) { ret = ieee80211_runtime_change_iftype(sdata, type); if (ret) @@ -1298,9 +1352,6 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, } /* reset some values that shouldn't be kept across type changes */ - sdata->vif.bss_conf.basic_rates = - ieee80211_mandatory_rates(sdata->local, - sdata->local->oper_channel->band); sdata->drop_unencrypted = 0; if (type == NL80211_IFTYPE_STATION) sdata->u.mgd.use_4addr = false; @@ -1432,6 +1483,15 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, mutex_unlock(&local->iflist_mtx); } +static void ieee80211_cleanup_sdata_stas_wk(struct work_struct *wk) +{ + struct ieee80211_sub_if_data *sdata; + + sdata = container_of(wk, struct ieee80211_sub_if_data, cleanup_stations_wk); + + ieee80211_cleanup_sdata_stas(sdata); +} + int ieee80211_if_add(struct ieee80211_local *local, const char *name, struct wireless_dev **new_wdev, enum nl80211_iftype type, struct vif_params *params) @@ -1507,6 +1567,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, INIT_LIST_HEAD(&sdata->key_list); + spin_lock_init(&sdata->cleanup_stations_lock); + INIT_LIST_HEAD(&sdata->cleanup_stations); + INIT_WORK(&sdata->cleanup_stations_wk, ieee80211_cleanup_sdata_stas_wk); + for (i = 0; i < IEEE80211_NUM_BANDS; i++) { struct ieee80211_supported_band *sband; sband = local->hw.wiphy->bands[i]; @@ -1523,6 +1587,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ieee80211_set_default_queues(sdata); + sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; + sdata->user_power_level = local->user_power_level; + /* setup type-dependent data */ ieee80211_setup_sdata(sdata, type); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index d27e61aaa71b..619c5d697999 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -339,7 +339,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, key->conf.iv_len = TKIP_IV_LEN; key->conf.icv_len = TKIP_ICV_LEN; if (seq) { - for (i = 0; i < NUM_RX_DATA_QUEUES; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { key->u.tkip.rx[i].iv32 = get_unaligned_le32(&seq[2]); key->u.tkip.rx[i].iv16 = @@ -352,7 +352,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, key->conf.iv_len = CCMP_HDR_LEN; key->conf.icv_len = CCMP_MIC_LEN; if (seq) { - for (i = 0; i < NUM_RX_DATA_QUEUES + 1; i++) + for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) for (j = 0; j < CCMP_PN_LEN; j++) key->u.ccmp.rx_pn[i][j] = seq[CCMP_PN_LEN - j - 1]; @@ -372,8 +372,9 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, key->conf.iv_len = 0; key->conf.icv_len = sizeof(struct ieee80211_mmie); if (seq) - for (j = 0; j < 6; j++) - key->u.aes_cmac.rx_pn[j] = seq[6 - j - 1]; + for (j = 0; j < CMAC_PN_LEN; j++) + key->u.aes_cmac.rx_pn[j] = + seq[CMAC_PN_LEN - j - 1]; /* * Initialize AES key state here as an optimization so that * it does not need to be initialized for every packet. @@ -654,16 +655,16 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: - if (WARN_ON(tid < 0 || tid >= NUM_RX_DATA_QUEUES)) + if (WARN_ON(tid < 0 || tid >= IEEE80211_NUM_TIDS)) return; seq->tkip.iv32 = key->u.tkip.rx[tid].iv32; seq->tkip.iv16 = key->u.tkip.rx[tid].iv16; break; case WLAN_CIPHER_SUITE_CCMP: - if (WARN_ON(tid < -1 || tid >= NUM_RX_DATA_QUEUES)) + if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS)) return; if (tid < 0) - pn = key->u.ccmp.rx_pn[NUM_RX_DATA_QUEUES]; + pn = key->u.ccmp.rx_pn[IEEE80211_NUM_TIDS]; else pn = key->u.ccmp.rx_pn[tid]; memcpy(seq->ccmp.pn, pn, CCMP_PN_LEN); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 7d4e31f037d7..382dc44ed330 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -30,8 +30,6 @@ #define TKIP_ICV_LEN 4 #define CMAC_PN_LEN 6 -#define NUM_RX_DATA_QUEUES 16 - struct ieee80211_local; struct ieee80211_sub_if_data; struct sta_info; @@ -82,17 +80,20 @@ struct ieee80211_key { struct tkip_ctx tx; /* last received RSC */ - struct tkip_ctx rx[NUM_RX_DATA_QUEUES]; + struct tkip_ctx rx[IEEE80211_NUM_TIDS]; + + /* number of mic failures */ + u32 mic_failures; } tkip; struct { atomic64_t tx_pn; /* * Last received packet number. The first - * NUM_RX_DATA_QUEUES counters are used with Data + * IEEE80211_NUM_TIDS counters are used with Data * frames and the last counter is used with Robust * Management frames. */ - u8 rx_pn[NUM_RX_DATA_QUEUES + 1][CCMP_PN_LEN]; + u8 rx_pn[IEEE80211_NUM_TIDS + 1][CCMP_PN_LEN]; struct crypto_cipher *tfm; u32 replays; /* dot11RSNAStatsCCMPReplays */ } ccmp; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index c80c4490351c..1b087fff93e7 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -93,15 +93,15 @@ static void ieee80211_reconfig_filter(struct work_struct *work) ieee80211_configure_filter(local); } -int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) +static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) { + struct ieee80211_sub_if_data *sdata; struct ieee80211_channel *chan; - int ret = 0; + u32 changed = 0; int power; enum nl80211_channel_type channel_type; u32 offchannel_flag; - - might_sleep(); + bool scanning = false; offchannel_flag = local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; if (local->scan_channel) { @@ -109,19 +109,19 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) /* If scanning on oper channel, use whatever channel-type * is currently in use. */ - if (chan == local->oper_channel) + if (chan == local->_oper_channel) channel_type = local->_oper_channel_type; else channel_type = NL80211_CHAN_NO_HT; } else if (local->tmp_channel) { chan = local->tmp_channel; - channel_type = local->tmp_channel_type; + channel_type = NL80211_CHAN_NO_HT; } else { - chan = local->oper_channel; + chan = local->_oper_channel; channel_type = local->_oper_channel_type; } - if (chan != local->oper_channel || + if (chan != local->_oper_channel || channel_type != local->_oper_channel_type) local->hw.conf.flags |= IEEE80211_CONF_OFFCHANNEL; else @@ -148,22 +148,39 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) changed |= IEEE80211_CONF_CHANGE_SMPS; } - if (test_bit(SCAN_SW_SCANNING, &local->scanning) || - test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) || - test_bit(SCAN_HW_SCANNING, &local->scanning) || - !local->ap_power_level) - power = chan->max_power; - else - power = min(chan->max_power, local->ap_power_level); + scanning = test_bit(SCAN_SW_SCANNING, &local->scanning) || + test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning) || + test_bit(SCAN_HW_SCANNING, &local->scanning); + power = chan->max_power; - if (local->user_power_level >= 0) - power = min(power, local->user_power_level); + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (!rcu_access_pointer(sdata->vif.chanctx_conf)) + continue; + power = min(power, sdata->vif.bss_conf.txpower); + } + rcu_read_unlock(); if (local->hw.conf.power_level != power) { changed |= IEEE80211_CONF_CHANGE_POWER; local->hw.conf.power_level = power; } + return changed; +} + +int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) +{ + int ret = 0; + + might_sleep(); + + if (!local->use_chanctx) + changed |= ieee80211_hw_conf_chan(local); + else + changed &= ~(IEEE80211_CONF_CHANGE_CHANNEL | + IEEE80211_CONF_CHANGE_POWER); + if (changed && local->open_count) { ret = drv_config(local, changed); /* @@ -359,14 +376,6 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_restart_hw); -static void ieee80211_recalc_smps_work(struct work_struct *work) -{ - struct ieee80211_local *local = - container_of(work, struct ieee80211_local, recalc_smps); - - ieee80211_recalc_smps(local); -} - #ifdef CONFIG_INET static int ieee80211_ifa_changed(struct notifier_block *nb, unsigned long data, void *arg) @@ -465,7 +474,8 @@ ieee80211_default_mgmt_stypes[NUM_NL80211_IFTYPES] = { .tx = 0xffff, .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | BIT(IEEE80211_STYPE_AUTH >> 4) | - BIT(IEEE80211_STYPE_DEAUTH >> 4), + BIT(IEEE80211_STYPE_DEAUTH >> 4) | + BIT(IEEE80211_STYPE_PROBE_REQ >> 4), }, [NL80211_IFTYPE_STATION] = { .tx = 0xffff, @@ -540,6 +550,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, struct ieee80211_local *local; int priv_size, i; struct wiphy *wiphy; + bool use_chanctx; if (WARN_ON(!ops->tx || !ops->start || !ops->stop || !ops->config || !ops->add_interface || !ops->remove_interface || @@ -549,6 +560,14 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, if (WARN_ON(ops->sta_state && (ops->sta_add || ops->sta_remove))) return NULL; + /* check all or no channel context operations exist */ + i = !!ops->add_chanctx + !!ops->remove_chanctx + + !!ops->change_chanctx + !!ops->assign_vif_chanctx + + !!ops->unassign_vif_chanctx; + if (WARN_ON(i != 0 && i != 5)) + return NULL; + use_chanctx = i == 5; + /* Ensure 32-byte alignment of our private data and hw private data. * We use the wiphy priv data for both our ieee80211_local and for * the driver's private data @@ -584,8 +603,15 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, if (ops->remain_on_channel) wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL; - wiphy->features = NL80211_FEATURE_SK_TX_STATUS | - NL80211_FEATURE_HT_IBSS; + wiphy->features |= NL80211_FEATURE_SK_TX_STATUS | + NL80211_FEATURE_SAE | + NL80211_FEATURE_HT_IBSS | + NL80211_FEATURE_VIF_TXPOWER; + + if (!ops->hw_scan) + wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN | + NL80211_FEATURE_AP_SCAN; + if (!ops->set_key) wiphy->flags |= WIPHY_FLAG_IBSS_RSN; @@ -599,6 +625,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN); local->ops = ops; + local->use_chanctx = use_chanctx; /* set up some defaults */ local->hw.queues = 1; @@ -612,7 +639,9 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.radiotap_mcs_details = IEEE80211_RADIOTAP_MCS_HAVE_MCS | IEEE80211_RADIOTAP_MCS_HAVE_GI | IEEE80211_RADIOTAP_MCS_HAVE_BW; - local->user_power_level = -1; + local->hw.radiotap_vht_details = IEEE80211_RADIOTAP_VHT_KNOWN_GI | + IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH; + local->user_power_level = IEEE80211_UNSET_POWER_LEVEL; wiphy->ht_capa_mod_mask = &mac80211_ht_capa_mod_mask; INIT_LIST_HEAD(&local->interfaces); @@ -626,6 +655,9 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, spin_lock_init(&local->filter_lock); spin_lock_init(&local->queue_stop_reason_lock); + INIT_LIST_HEAD(&local->chanctx_list); + mutex_init(&local->chanctx_mtx); + /* * The rx_skb_queue is only accessed from tasklets, * but other SKB queues are used from within IRQ @@ -641,7 +673,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, INIT_WORK(&local->restart_work, ieee80211_restart_work); INIT_WORK(&local->reconfig_filter, ieee80211_reconfig_filter); - INIT_WORK(&local->recalc_smps, ieee80211_recalc_smps_work); local->smps_mode = IEEE80211_SMPS_OFF; INIT_WORK(&local->dynamic_ps_enable_work, @@ -719,6 +750,25 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if ((hw->flags & IEEE80211_HW_SCAN_WHILE_IDLE) && !local->ops->hw_scan) return -EINVAL; + if (!local->use_chanctx) { + for (i = 0; i < local->hw.wiphy->n_iface_combinations; i++) { + const struct ieee80211_iface_combination *comb; + + comb = &local->hw.wiphy->iface_combinations[i]; + + if (comb->num_different_channels > 1) + return -EINVAL; + } + } else { + /* + * WDS is currently prohibited when channel contexts are used + * because there's no clear definition of which channel WDS + * type interfaces use + */ + if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS)) + return -EINVAL; + } + /* Only HW csum features are currently compatible with mac80211 */ feature_whitelist = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM; @@ -728,6 +778,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (hw->max_report_rates == 0) hw->max_report_rates = hw->max_rates; + local->rx_chains = 1; + /* * generic code guarantees at least one band, * set this very early because much code assumes @@ -743,18 +795,28 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) sband = local->hw.wiphy->bands[band]; if (!sband) continue; - if (!local->oper_channel) { + if (!local->use_chanctx && !local->_oper_channel) { /* init channel we're on */ local->hw.conf.channel = - local->oper_channel = &sband->channels[0]; + local->_oper_channel = &sband->channels[0]; local->hw.conf.channel_type = NL80211_CHAN_NO_HT; } + cfg80211_chandef_create(&local->monitor_chandef, + &sband->channels[0], + NL80211_CHAN_NO_HT); channels += sband->n_channels; if (max_bitrates < sband->n_bitrates) max_bitrates = sband->n_bitrates; supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; + + if (sband->ht_cap.ht_supported) + local->rx_chains = + max(ieee80211_mcs_to_chains(&sband->ht_cap.mcs), + local->rx_chains); + + /* TODO: consider VHT for RX chains, hopefully it's the same */ } local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + @@ -778,19 +840,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_MONITOR); hw->wiphy->software_iftypes |= BIT(NL80211_IFTYPE_MONITOR); - /* - * mac80211 doesn't support more than 1 channel, and also not more - * than one IBSS interface - */ + /* mac80211 doesn't support more than one IBSS interface right now */ for (i = 0; i < hw->wiphy->n_iface_combinations; i++) { const struct ieee80211_iface_combination *c; int j; c = &hw->wiphy->iface_combinations[i]; - if (c->num_different_channels > 1) - return -EINVAL; - for (j = 0; j < c->n_limits; j++) if ((c->limits[j].types & BIT(NL80211_IFTYPE_ADHOC)) && c->limits[j].max > 1) @@ -830,9 +886,21 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (supp_ht) local->scan_ies_len += 2 + sizeof(struct ieee80211_ht_cap); - if (supp_vht) + if (supp_vht) { local->scan_ies_len += - 2 + sizeof(struct ieee80211_vht_capabilities); + 2 + sizeof(struct ieee80211_vht_cap); + + /* + * (for now at least), drivers wanting to use VHT must + * support channel contexts, as they contain all the + * necessary VHT information and the global hw config + * doesn't (yet) + */ + if (WARN_ON(!local->use_chanctx)) { + result = -EINVAL; + goto fail_wiphy_register; + } + } if (!local->ops->hw_scan) { /* For hw_scan, driver needs to set these up. */ @@ -871,8 +939,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->cipher_suites, sizeof(u32) * local->hw.wiphy->n_cipher_suites, GFP_KERNEL); - if (!suites) - return -ENOMEM; + if (!suites) { + result = -ENOMEM; + goto fail_wiphy_register; + } for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) { u32 suite = local->hw.wiphy->cipher_suites[r]; if (suite == WLAN_CIPHER_SUITE_WEP40 || diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index ff0296c7bab8..649ad513547f 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -76,7 +76,7 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; u32 basic_rates = 0; - enum nl80211_channel_type sta_channel_type = NL80211_CHAN_NO_HT; + struct cfg80211_chan_def sta_chan_def; /* * As support for each feature is added, check for matching @@ -97,23 +97,17 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, (ifmsh->mesh_auth_id == ie->mesh_config->meshconf_auth))) goto mismatch; - ieee80211_sta_get_rates(local, ie, local->oper_channel->band, + ieee80211_sta_get_rates(local, ie, ieee80211_get_sdata_band(sdata), &basic_rates); if (sdata->vif.bss_conf.basic_rates != basic_rates) goto mismatch; - if (ie->ht_operation) - sta_channel_type = - ieee80211_ht_oper_to_channel_type(ie->ht_operation); - - /* Disallow HT40+/- mismatch */ - if (ie->ht_operation && - (sdata->vif.bss_conf.channel_type == NL80211_CHAN_HT40MINUS || - sdata->vif.bss_conf.channel_type == NL80211_CHAN_HT40PLUS) && - (sta_channel_type == NL80211_CHAN_HT40MINUS || - sta_channel_type == NL80211_CHAN_HT40PLUS) && - sdata->vif.bss_conf.channel_type != sta_channel_type) + ieee80211_ht_oper_to_chandef(sdata->vif.bss_conf.chandef.chan, + ie->ht_operation, &sta_chan_def); + + if (!cfg80211_chandef_compatible(&sdata->vif.bss_conf.chandef, + &sta_chan_def)) goto mismatch; return true; @@ -129,7 +123,7 @@ mismatch: bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie) { return (ie->mesh_config->meshconf_cap & - MESHCONF_CAPAB_ACCEPT_PLINKS) != 0; + IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS) != 0; } /** @@ -169,7 +163,7 @@ int mesh_rmc_init(struct ieee80211_sub_if_data *sdata) return -ENOMEM; sdata->u.mesh.rmc->idx_mask = RMC_BUCKETS - 1; for (i = 0; i < RMC_BUCKETS; i++) - INIT_LIST_HEAD(&sdata->u.mesh.rmc->bucket[i].list); + INIT_LIST_HEAD(&sdata->u.mesh.rmc->bucket[i]); return 0; } @@ -183,7 +177,7 @@ void mesh_rmc_free(struct ieee80211_sub_if_data *sdata) return; for (i = 0; i < RMC_BUCKETS; i++) - list_for_each_entry_safe(p, n, &rmc->bucket[i].list, list) { + list_for_each_entry_safe(p, n, &rmc->bucket[i], list) { list_del(&p->list); kmem_cache_free(rm_cache, p); } @@ -216,7 +210,7 @@ int mesh_rmc_check(u8 *sa, struct ieee80211s_hdr *mesh_hdr, /* Don't care about endianness since only match matters */ memcpy(&seqnum, &mesh_hdr->seqnum, sizeof(mesh_hdr->seqnum)); idx = le32_to_cpu(mesh_hdr->seqnum) & rmc->idx_mask; - list_for_each_entry_safe(p, n, &rmc->bucket[idx].list, list) { + list_for_each_entry_safe(p, n, &rmc->bucket[idx], list) { ++entries; if (time_after(jiffies, p->exp_time) || (entries == RMC_QUEUE_MAX_LEN)) { @@ -235,7 +229,7 @@ int mesh_rmc_check(u8 *sa, struct ieee80211s_hdr *mesh_hdr, p->seqnum = seqnum; p->exp_time = jiffies + RMC_TIMEOUT; memcpy(p->sa, sa, ETH_ALEN); - list_add(&p->list, &rmc->bucket[idx].list); + list_add(&p->list, &rmc->bucket[idx]); return 0; } @@ -264,16 +258,16 @@ mesh_add_meshconf_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) /* Authentication Protocol identifier */ *pos++ = ifmsh->mesh_auth_id; /* Mesh Formation Info - number of neighbors */ - neighbors = atomic_read(&ifmsh->mshstats.estab_plinks); + neighbors = atomic_read(&ifmsh->estab_plinks); /* Number of neighbor mesh STAs or 15 whichever is smaller */ neighbors = (neighbors > 15) ? 15 : neighbors; *pos++ = neighbors << 1; /* Mesh capability */ - *pos = MESHCONF_CAPAB_FORWARDING; + *pos = IEEE80211_MESHCONF_CAPAB_FORWARDING; *pos |= ifmsh->accepting_plinks ? - MESHCONF_CAPAB_ACCEPT_PLINKS : 0x00; + IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS : 0x00; *pos++ |= ifmsh->adjusting_tbtt ? - MESHCONF_CAPAB_TBTT_ADJUSTING : 0x00; + IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING : 0x00; *pos++ = 0x00; return 0; @@ -355,12 +349,22 @@ int mesh_add_ds_params_ie(struct sk_buff *skb, { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; - struct ieee80211_channel *chan = local->oper_channel; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *chan; u8 *pos; if (skb_tailroom(skb) < 3) return -ENOMEM; + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return -EINVAL; + } + chan = chanctx_conf->def.chan; + rcu_read_unlock(); + sband = local->hw.wiphy->bands[chan->band]; if (sband->band == IEEE80211_BAND_2GHZ) { pos = skb_put(skb, 2 + 1); @@ -376,12 +380,13 @@ int mesh_add_ht_cap_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); struct ieee80211_supported_band *sband; u8 *pos; - sband = local->hw.wiphy->bands[local->oper_channel->band]; + sband = local->hw.wiphy->bands[band]; if (!sband->ht_cap.ht_supported || - sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT) + sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT) return 0; if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_cap)) @@ -397,14 +402,26 @@ int mesh_add_ht_oper_ie(struct sk_buff *skb, struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; - struct ieee80211_channel *channel = local->oper_channel; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *channel; enum nl80211_channel_type channel_type = - sdata->vif.bss_conf.channel_type; - struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[channel->band]; - struct ieee80211_sta_ht_cap *ht_cap = &sband->ht_cap; + cfg80211_get_chandef_type(&sdata->vif.bss_conf.chandef); + struct ieee80211_supported_band *sband; + struct ieee80211_sta_ht_cap *ht_cap; u8 *pos; + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return -EINVAL; + } + channel = chanctx_conf->def.chan; + rcu_read_unlock(); + + sband = local->hw.wiphy->bands[channel->band]; + ht_cap = &sband->ht_cap; + if (!ht_cap->ht_supported || channel_type == NL80211_CHAN_NO_HT) return 0; @@ -412,7 +429,7 @@ int mesh_add_ht_oper_ie(struct sk_buff *skb, return -ENOMEM; pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation)); - ieee80211_ie_build_ht_oper(pos, ht_cap, channel, channel_type, + ieee80211_ie_build_ht_oper(pos, ht_cap, &sdata->vif.bss_conf.chandef, sdata->vif.bss_conf.ht_operation_mode); return 0; @@ -610,7 +627,7 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) sdata->vif.bss_conf.beacon_int = MESH_DEFAULT_BEACON_INTERVAL; sdata->vif.bss_conf.basic_rates = ieee80211_mandatory_rates(sdata->local, - sdata->local->oper_channel->band); + ieee80211_get_sdata_band(sdata)); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON | BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_HT | @@ -680,8 +697,10 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(mgmt->u.probe_resp.variable, len - baselen, &elems); - /* ignore beacons from secure mesh peers if our security is off */ - if (elems.rsn_len && sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) + /* ignore non-mesh or secure / unsecure mismatch */ + if ((!elems.mesh_id || !elems.mesh_config) || + (elems.rsn && sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) || + (!elems.rsn && sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE)) return; if (elems.ds_params && elems.ds_params_len == 1) @@ -694,8 +713,7 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) return; - if (elems.mesh_id && elems.mesh_config && - mesh_matches_local(sdata, &elems)) + if (mesh_matches_local(sdata, &elems)) mesh_neighbour_update(sdata, mgmt->sa, &elems); if (ifmsh->sync_ops) diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 25d0f17dec71..84c28c6101cd 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -19,20 +19,6 @@ /* Data structures */ /** - * enum mesh_config_capab_flags - mesh config IE capability flags - * - * @MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish - * additional mesh peerings with other mesh STAs - * @MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs - * @MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure is ongoing - */ -enum mesh_config_capab_flags { - MESHCONF_CAPAB_ACCEPT_PLINKS = BIT(0), - MESHCONF_CAPAB_FORWARDING = BIT(3), - MESHCONF_CAPAB_TBTT_ADJUSTING = BIT(5), -}; - -/** * enum mesh_path_flags - mac80211 mesh path flags * * @@ -198,7 +184,7 @@ struct rmc_entry { }; struct mesh_rmc { - struct rmc_entry bucket[RMC_BUCKETS]; + struct list_head bucket[RMC_BUCKETS]; u32 idx_mask; }; @@ -256,7 +242,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh); -struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method); +const struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method); /* Mesh paths */ int mesh_nexthop_lookup(struct sk_buff *skb, @@ -324,7 +310,7 @@ extern int mesh_allocated; static inline int mesh_plink_free_count(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mshcfg.dot11MeshMaxPeerLinks - - atomic_read(&sdata->u.mesh.mshstats.estab_plinks); + atomic_read(&sdata->u.mesh.estab_plinks); } static inline bool mesh_plink_availables(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 47aeee2d8db1..2659e428b80c 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -215,6 +215,7 @@ static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata, skb->priority = 7; info->control.vif = &sdata->vif; + info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; ieee80211_set_qos_hdr(sdata, skb); } @@ -246,11 +247,13 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, return -EAGAIN; skb = dev_alloc_skb(local->tx_headroom + + IEEE80211_ENCRYPT_HEADROOM + + IEEE80211_ENCRYPT_TAILROOM + hdr_len + 2 + 15 /* PERR IE */); if (!skb) return -1; - skb_reserve(skb, local->tx_headroom); + skb_reserve(skb, local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM); mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); memset(mgmt, 0, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 3ab34d816897..4b274e9c91a5 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -19,12 +19,6 @@ #define mod_plink_timer(s, t) (mod_timer(&s->plink_timer, \ jiffies + HZ * t / 1000)) -#define dot11MeshMaxRetries(s) (s->u.mesh.mshcfg.dot11MeshMaxRetries) -#define dot11MeshRetryTimeout(s) (s->u.mesh.mshcfg.dot11MeshRetryTimeout) -#define dot11MeshConfirmTimeout(s) (s->u.mesh.mshcfg.dot11MeshConfirmTimeout) -#define dot11MeshHoldingTimeout(s) (s->u.mesh.mshcfg.dot11MeshHoldingTimeout) -#define dot11MeshMaxPeerLinks(s) (s->u.mesh.mshcfg.dot11MeshMaxPeerLinks) - /* We only need a valid sta if user configured a minimum rssi_threshold. */ #define rssi_threshold_check(sta, sdata) \ (sdata->u.mesh.mshcfg.rssi_threshold == 0 ||\ @@ -50,14 +44,14 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, static inline u32 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata) { - atomic_inc(&sdata->u.mesh.mshstats.estab_plinks); + atomic_inc(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata); } static inline u32 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata) { - atomic_dec(&sdata->u.mesh.mshstats.estab_plinks); + atomic_dec(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata); } @@ -117,7 +111,7 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) u16 ht_opmode; bool non_ht_sta = false, ht20_sta = false; - if (sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT) + if (sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT) return 0; rcu_read_lock(); @@ -126,14 +120,14 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) sta->plink_state != NL80211_PLINK_ESTAB) continue; - switch (sta->ch_type) { - case NL80211_CHAN_NO_HT: + switch (sta->ch_width) { + case NL80211_CHAN_WIDTH_20_NOHT: mpl_dbg(sdata, "mesh_plink %pM: nonHT sta (%pM) is present\n", sdata->vif.addr, sta->sta.addr); non_ht_sta = true; goto out; - case NL80211_CHAN_HT20: + case NL80211_CHAN_WIDTH_20: mpl_dbg(sdata, "mesh_plink %pM: HT20 sta (%pM) is present\n", sdata->vif.addr, sta->sta.addr); @@ -148,7 +142,7 @@ out: if (non_ht_sta) ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED; else if (ht20_sta && - sdata->vif.bss_conf.channel_type > NL80211_CHAN_HT20) + sdata->vif.bss_conf.chandef.width > NL80211_CHAN_WIDTH_20) ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_20MHZ; else ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONE; @@ -252,6 +246,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.self_prot.action_code = action; if (action != WLAN_SP_MESH_PEERING_CLOSE) { + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); + /* capability info */ pos = skb_put(skb, 2); memset(pos, 0, 2); @@ -260,10 +256,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, 2); memcpy(pos + 2, &plid, 2); } - if (ieee80211_add_srates_ie(sdata, skb, true, - local->oper_channel->band) || - ieee80211_add_ext_srates_ie(sdata, skb, true, - local->oper_channel->band) || + if (ieee80211_add_srates_ie(sdata, skb, true, band) || + ieee80211_add_ext_srates_ie(sdata, skb, true, band) || mesh_add_rsn_ie(skb, sdata) || mesh_add_meshid_ie(skb, sdata) || mesh_add_meshconf_ie(skb, sdata)) @@ -343,7 +337,7 @@ static struct sta_info *mesh_peer_init(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems) { struct ieee80211_local *local = sdata->local; - enum ieee80211_band band = local->oper_channel->band; + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); struct ieee80211_supported_band *sband; u32 rates, basic_rates = 0; struct sta_info *sta; @@ -378,7 +372,7 @@ static struct sta_info *mesh_peer_init(struct ieee80211_sub_if_data *sdata, sta->sta.supp_rates[band] = rates; if (elems->ht_cap_elem && - sdata->vif.bss_conf.channel_type != NL80211_CHAN_NO_HT) + sdata->vif.bss_conf.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, elems->ht_cap_elem, &sta->sta.ht_cap); @@ -386,15 +380,19 @@ static struct sta_info *mesh_peer_init(struct ieee80211_sub_if_data *sdata, memset(&sta->sta.ht_cap, 0, sizeof(sta->sta.ht_cap)); if (elems->ht_operation) { + struct cfg80211_chan_def chandef; + if (!(elems->ht_operation->ht_param & IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)) sta->sta.ht_cap.cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; - sta->ch_type = - ieee80211_ht_oper_to_channel_type(elems->ht_operation); + ieee80211_ht_oper_to_chandef(sdata->vif.bss_conf.chandef.chan, + elems->ht_operation, &chandef); + sta->ch_width = chandef.width; } - rate_control_rate_init(sta); + if (insert) + rate_control_rate_init(sta); spin_unlock_bh(&sta->lock); if (insert && sta_info_insert(sta)) @@ -430,6 +428,7 @@ static void mesh_plink_timer(unsigned long data) struct sta_info *sta; __le16 llid, plid, reason; struct ieee80211_sub_if_data *sdata; + struct mesh_config *mshcfg; /* * This STA is valid because sta_info_destroy() will @@ -456,12 +455,13 @@ static void mesh_plink_timer(unsigned long data) llid = sta->llid; plid = sta->plid; sdata = sta->sdata; + mshcfg = &sdata->u.mesh.mshcfg; switch (sta->plink_state) { case NL80211_PLINK_OPN_RCVD: case NL80211_PLINK_OPN_SNT: /* retry timer */ - if (sta->plink_retries < dot11MeshMaxRetries(sdata)) { + if (sta->plink_retries < mshcfg->dot11MeshMaxRetries) { u32 rand; mpl_dbg(sta->sdata, "Mesh plink for %pM (retry, timeout): %d %d\n", @@ -484,7 +484,7 @@ static void mesh_plink_timer(unsigned long data) if (!reason) reason = cpu_to_le16(WLAN_REASON_MESH_CONFIRM_TIMEOUT); sta->plink_state = NL80211_PLINK_HOLDING; - mod_plink_timer(sta, dot11MeshHoldingTimeout(sdata)); + mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout); spin_unlock_bh(&sta->lock); mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, sta->sta.addr, llid, plid, reason); @@ -543,7 +543,7 @@ int mesh_plink_open(struct sta_info *sta) return -EBUSY; } sta->plink_state = NL80211_PLINK_OPN_SNT; - mesh_plink_timer_set(sta, dot11MeshRetryTimeout(sdata)); + mesh_plink_timer_set(sta, sdata->u.mesh.mshcfg.dot11MeshRetryTimeout); spin_unlock_bh(&sta->lock); mpl_dbg(sdata, "Mesh plink: starting establishment with %pM\n", @@ -570,6 +570,7 @@ void mesh_plink_block(struct sta_info *sta) void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status) { + struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg; struct ieee802_11_elems elems; struct sta_info *sta; enum plink_event event; @@ -777,7 +778,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->plid = plid; get_random_bytes(&llid, 2); sta->llid = llid; - mesh_plink_timer_set(sta, dot11MeshRetryTimeout(sdata)); + mesh_plink_timer_set(sta, + mshcfg->dot11MeshRetryTimeout); spin_unlock_bh(&sta->lock); mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_OPEN, @@ -803,7 +805,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->reason = reason; sta->plink_state = NL80211_PLINK_HOLDING; if (!mod_plink_timer(sta, - dot11MeshHoldingTimeout(sdata))) + mshcfg->dot11MeshHoldingTimeout)) sta->ignore_plink_timer = true; llid = sta->llid; @@ -825,7 +827,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m case CNF_ACPT: sta->plink_state = NL80211_PLINK_CNF_RCVD; if (!mod_plink_timer(sta, - dot11MeshConfirmTimeout(sdata))) + mshcfg->dot11MeshConfirmTimeout)) sta->ignore_plink_timer = true; spin_unlock_bh(&sta->lock); @@ -847,7 +849,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->reason = reason; sta->plink_state = NL80211_PLINK_HOLDING; if (!mod_plink_timer(sta, - dot11MeshHoldingTimeout(sdata))) + mshcfg->dot11MeshHoldingTimeout)) sta->ignore_plink_timer = true; llid = sta->llid; @@ -888,7 +890,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m sta->reason = reason; sta->plink_state = NL80211_PLINK_HOLDING; if (!mod_plink_timer(sta, - dot11MeshHoldingTimeout(sdata))) + mshcfg->dot11MeshHoldingTimeout)) sta->ignore_plink_timer = true; llid = sta->llid; @@ -923,7 +925,7 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_m changed |= __mesh_plink_deactivate(sta); sta->plink_state = NL80211_PLINK_HOLDING; llid = sta->llid; - mod_plink_timer(sta, dot11MeshHoldingTimeout(sdata)); + mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout); spin_unlock_bh(&sta->lock); changed |= mesh_set_ht_prot_mode(sdata); mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c index a16b7b4b1e02..aa8d1e437385 100644 --- a/net/mac80211/mesh_sync.c +++ b/net/mac80211/mesh_sync.c @@ -43,7 +43,7 @@ struct sync_method { static bool mesh_peer_tbtt_adjusting(struct ieee802_11_elems *ie) { return (ie->mesh_config->meshconf_cap & - MESHCONF_CAPAB_TBTT_ADJUSTING) != 0; + IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING) != 0; } void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata) @@ -116,43 +116,13 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, goto no_sync; } - if (rx_status->flag & RX_FLAG_MACTIME_MPDU && rx_status->mactime) { - /* - * The mactime is defined as the time the first data symbol - * of the frame hits the PHY, and the timestamp of the beacon - * is defined as "the time that the data symbol containing the - * first bit of the timestamp is transmitted to the PHY plus - * the transmitting STA's delays through its local PHY from the - * MAC-PHY interface to its interface with the WM" (802.11 - * 11.1.2) - * - * T_r, in 13.13.2.2.2, is just defined as "the frame reception - * time" but we unless we interpret that time to be the same - * time of the beacon timestamp, the offset calculation will be - * off. Below we adjust t_r to be "the time at which the first - * symbol of the timestamp element in the beacon is received". - * This correction depends on the rate. - * - * Based on similar code in ibss.c - */ - int rate; - - if (rx_status->flag & RX_FLAG_HT) { - /* TODO: - * In principle there could be HT-beacons (Dual Beacon - * HT Operation options), but for now ignore them and - * just use the primary (i.e. non-HT) beacons for - * synchronization. - * */ - goto no_sync; - } else - rate = local->hw.wiphy->bands[rx_status->band]-> - bitrates[rx_status->rate_idx].bitrate; - - /* 24 bytes of header * 8 bits/byte * - * 10*(100 Kbps)/Mbps / rate (100 Kbps)*/ - t_r = rx_status->mactime + (24 * 8 * 10 / rate); - } + if (ieee80211_have_rx_timestamp(rx_status)) + /* time when timestamp field was received */ + t_r = ieee80211_calculate_rx_timestamp(local, rx_status, + 24 + 12 + + elems->total_len + + FCS_LEN, + 24); /* Timing offset calculation (see 13.13.2.2.2) */ t_t = le64_to_cpu(mgmt->u.beacon.timestamp); @@ -225,58 +195,20 @@ static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata) ifmsh->sync_offset_clockdrift_max); set_bit(MESH_WORK_DRIFT_ADJUST, &ifmsh->wrkq_flags); + + ifmsh->adjusting_tbtt = true; } else { msync_dbg(sdata, "TBTT : max clockdrift=%lld; too small to adjust\n", (long long)ifmsh->sync_offset_clockdrift_max); ifmsh->sync_offset_clockdrift_max = 0; + + ifmsh->adjusting_tbtt = false; } spin_unlock_bh(&ifmsh->sync_offset_lock); } -static const u8 *mesh_get_vendor_oui(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - u8 offset; - - if (!ifmsh->ie || !ifmsh->ie_len) - return NULL; - - offset = ieee80211_ie_split_vendor(ifmsh->ie, - ifmsh->ie_len, 0); - - if (!offset) - return NULL; - - return ifmsh->ie + offset + 2; -} - -static void mesh_sync_vendor_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, - u16 stype, - struct ieee80211_mgmt *mgmt, - struct ieee802_11_elems *elems, - struct ieee80211_rx_status *rx_status) -{ - const u8 *oui; - - WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR); - msync_dbg(sdata, "called mesh_sync_vendor_rx_bcn_presp\n"); - oui = mesh_get_vendor_oui(sdata); - /* here you would implement the vendor offset tracking for this oui */ -} - -static void mesh_sync_vendor_adjust_tbtt(struct ieee80211_sub_if_data *sdata) -{ - const u8 *oui; - - WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR); - msync_dbg(sdata, "called mesh_sync_vendor_adjust_tbtt\n"); - oui = mesh_get_vendor_oui(sdata); - /* here you would implement the vendor tsf adjustment for this oui */ -} - -/* global variable */ -static struct sync_method sync_methods[] = { +static const struct sync_method sync_methods[] = { { .method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET, .ops = { @@ -284,18 +216,11 @@ static struct sync_method sync_methods[] = { .adjust_tbtt = &mesh_sync_offset_adjust_tbtt, } }, - { - .method = IEEE80211_SYNC_METHOD_VENDOR, - .ops = { - .rx_bcn_presp = &mesh_sync_vendor_rx_bcn_presp, - .adjust_tbtt = &mesh_sync_vendor_adjust_tbtt, - } - }, }; -struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method) +const struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method) { - struct ieee80211_mesh_sync_ops *ops = NULL; + const struct ieee80211_mesh_sync_ops *ops = NULL; u8 i; for (i = 0 ; i < ARRAY_SIZE(sync_methods); ++i) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1b7eed252fe9..a3552929a21d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -178,20 +178,32 @@ static u32 ieee80211_config_ht_tx(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *chan; struct sta_info *sta; u32 changed = 0; u16 ht_opmode; bool disable_40 = false; - sband = local->hw.wiphy->bands[local->oper_channel->band]; + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return 0; + } + chan = chanctx_conf->def.chan; + rcu_read_unlock(); + sband = local->hw.wiphy->bands[chan->band]; - switch (sdata->vif.bss_conf.channel_type) { - case NL80211_CHAN_HT40PLUS: - if (local->oper_channel->flags & IEEE80211_CHAN_NO_HT40PLUS) + switch (sdata->vif.bss_conf.chandef.width) { + case NL80211_CHAN_WIDTH_40: + if (sdata->vif.bss_conf.chandef.chan->center_freq > + sdata->vif.bss_conf.chandef.center_freq1 && + chan->flags & IEEE80211_CHAN_NO_HT40PLUS) disable_40 = true; - break; - case NL80211_CHAN_HT40MINUS: - if (local->oper_channel->flags & IEEE80211_CHAN_NO_HT40MINUS) + if (sdata->vif.bss_conf.chandef.chan->center_freq < + sdata->vif.bss_conf.chandef.center_freq1 && + chan->flags & IEEE80211_CHAN_NO_HT40MINUS) disable_40 = true; break; default: @@ -342,8 +354,18 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, /* determine capability flags */ cap = vht_cap.cap; + if (sdata->u.mgd.flags & IEEE80211_STA_DISABLE_80P80MHZ) { + cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ; + cap |= IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; + } + + if (sdata->u.mgd.flags & IEEE80211_STA_DISABLE_160MHZ) { + cap &= ~IEEE80211_VHT_CAP_SHORT_GI_160; + cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; + } + /* reserve and fill IE */ - pos = skb_put(skb, sizeof(struct ieee80211_vht_capabilities) + 2); + pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); ieee80211_ie_build_vht_cap(pos, &vht_cap, cap); } @@ -359,11 +381,21 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) int i, count, rates_len, supp_rates_len; u16 capab; struct ieee80211_supported_band *sband; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *chan; u32 rates = 0; lockdep_assert_held(&ifmgd->mtx); - sband = local->hw.wiphy->bands[local->oper_channel->band]; + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return; + } + chan = chanctx_conf->def.chan; + rcu_read_unlock(); + sband = local->hw.wiphy->bands[chan->band]; if (assoc_data->supp_rates_len) { /* @@ -392,7 +424,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) 4 + /* power capability */ 2 + 2 * sband->n_channels + /* supported channels */ 2 + sizeof(struct ieee80211_ht_cap) + /* HT */ - 2 + sizeof(struct ieee80211_vht_capabilities) + /* VHT */ + 2 + sizeof(struct ieee80211_vht_cap) + /* VHT */ assoc_data->ie_len + /* extra IEs */ 9, /* WMM */ GFP_KERNEL); @@ -485,7 +517,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) *pos++ = WLAN_EID_PWR_CAPABILITY; *pos++ = 2; *pos++ = 0; /* min tx power */ - *pos++ = local->oper_channel->max_power; /* max tx power */ + *pos++ = chan->max_power; /* max tx power */ /* 2. supported channels */ /* TODO: get this in reg domain format */ @@ -521,9 +553,13 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) offset = noffset; } - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) + if (WARN_ON_ONCE((ifmgd->flags & IEEE80211_STA_DISABLE_HT) && + !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))) + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) ieee80211_add_ht_ie(sdata, skb, assoc_data->ap_ht_param, - sband, local->oper_channel, ifmgd->ap_smps); + sband, chan, sdata->smps_mode); if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) ieee80211_add_vht_ie(sdata, skb, sband); @@ -657,18 +693,18 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (!ifmgd->associated) goto out; - sdata->local->oper_channel = sdata->local->csa_channel; + sdata->local->_oper_channel = sdata->local->csa_channel; if (!sdata->local->ops->channel_switch) { /* call "hw_config" only if doing sw channel switch */ ieee80211_hw_config(sdata->local, IEEE80211_CONF_CHANGE_CHANNEL); } else { /* update the device channel directly */ - sdata->local->hw.conf.channel = sdata->local->oper_channel; + sdata->local->hw.conf.channel = sdata->local->_oper_channel; } /* XXX: shouldn't really modify cfg80211-owned data! */ - ifmgd->associated->channel = sdata->local->oper_channel; + ifmgd->associated->channel = sdata->local->_oper_channel; /* XXX: wait for a beacon first? */ ieee80211_wake_queues_by_reason(&sdata->local->hw, @@ -680,11 +716,8 @@ static void ieee80211_chswitch_work(struct work_struct *work) void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success) { - struct ieee80211_sub_if_data *sdata; - struct ieee80211_if_managed *ifmgd; - - sdata = vif_to_sdata(vif); - ifmgd = &sdata->u.mgd; + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; trace_api_chswitch_done(sdata, success); if (!success) { @@ -723,6 +756,7 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num, cbss->channel->band); + struct ieee80211_chanctx *chanctx; ASSERT_MGD_MTX(ifmgd); @@ -748,10 +782,35 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; } - sdata->local->csa_channel = new_ch; - ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED; + if (sdata->local->use_chanctx) { + sdata_info(sdata, + "not handling channel switch with channel contexts\n"); + ieee80211_queue_work(&sdata->local->hw, + &ifmgd->csa_connection_drop_work); + return; + } + + mutex_lock(&sdata->local->chanctx_mtx); + if (WARN_ON(!rcu_access_pointer(sdata->vif.chanctx_conf))) { + mutex_unlock(&sdata->local->chanctx_mtx); + return; + } + chanctx = container_of(rcu_access_pointer(sdata->vif.chanctx_conf), + struct ieee80211_chanctx, conf); + if (chanctx->refcount > 1) { + sdata_info(sdata, + "channel switch with multiple interfaces on the same channel, disconnecting\n"); + ieee80211_queue_work(&sdata->local->hw, + &ifmgd->csa_connection_drop_work); + mutex_unlock(&sdata->local->chanctx_mtx); + return; + } + mutex_unlock(&sdata->local->chanctx_mtx); + + sdata->local->csa_channel = new_ch; + if (sw_elem->mode) ieee80211_stop_queues_by_reason(&sdata->local->hw, IEEE80211_QUEUE_STOP_REASON_CSA); @@ -778,10 +837,10 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, cbss->beacon_interval)); } -static void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, - struct ieee80211_channel *channel, - const u8 *country_ie, u8 country_ie_len, - const u8 *pwr_constr_elem) +static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel *channel, + const u8 *country_ie, u8 country_ie_len, + const u8 *pwr_constr_elem) { struct ieee80211_country_ie_triplet *triplet; int chan = ieee80211_frequency_to_channel(channel->center_freq); @@ -790,7 +849,7 @@ static void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, /* Invalid IE */ if (country_ie_len % 2 || country_ie_len < IEEE80211_COUNTRY_IE_MIN_LEN) - return; + return 0; triplet = (void *)(country_ie + 3); country_ie_len -= 3; @@ -831,19 +890,21 @@ static void ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, } if (!have_chan_pwr) - return; + return 0; new_ap_level = max_t(int, 0, chan_pwr - *pwr_constr_elem); - if (sdata->local->ap_power_level == new_ap_level) - return; + if (sdata->ap_power_level == new_ap_level) + return 0; sdata_info(sdata, "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n", new_ap_level, chan_pwr, *pwr_constr_elem, sdata->u.mgd.bssid); - sdata->local->ap_power_level = new_ap_level; - ieee80211_hw_config(sdata->local, 0); + sdata->ap_power_level = new_ap_level; + if (__ieee80211_recalc_txpower(sdata)) + return BSS_CHANGED_TXPOWER; + return 0; } void ieee80211_enable_dyn_ps(struct ieee80211_vif *vif) @@ -1013,12 +1074,8 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) if (beaconint_us > latency) { local->ps_sdata = NULL; } else { - struct ieee80211_bss *bss; int maxslp = 1; - u8 dtimper; - - bss = (void *)found->u.mgd.associated->priv; - dtimper = bss->dtim_period; + u8 dtimper = found->u.mgd.dtim_period; /* If the TIM IE is invalid, pretend the value is 1 */ if (!dtimper) @@ -1280,7 +1337,7 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, } use_short_slot = !!(capab & WLAN_CAPABILITY_SHORT_SLOT_TIME); - if (sdata->local->oper_channel->band == IEEE80211_BAND_5GHZ) + if (ieee80211_get_sdata_band(sdata) == IEEE80211_BAND_5GHZ) use_short_slot = true; if (use_protection != bss_conf->use_cts_prot) { @@ -1321,15 +1378,45 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, sdata->u.mgd.flags |= IEEE80211_STA_RESET_SIGNAL_AVE; + if (sdata->vif.p2p) { + const struct cfg80211_bss_ies *ies; + + rcu_read_lock(); + ies = rcu_dereference(cbss->ies); + if (ies) { + u8 noa[2]; + int ret; + + ret = cfg80211_get_p2p_attr( + ies->data, ies->len, + IEEE80211_P2P_ATTR_ABSENCE_NOTICE, + noa, sizeof(noa)); + if (ret >= 2) { + bss_conf->p2p_oppps = noa[1] & 0x80; + bss_conf->p2p_ctwindow = noa[1] & 0x7f; + bss_info_changed |= BSS_CHANGED_P2P_PS; + sdata->u.mgd.p2p_noa_index = noa[0]; + } + } + rcu_read_unlock(); + } + /* just to be sure */ ieee80211_stop_poll(sdata); ieee80211_led_assoc(local, 1); - if (local->hw.flags & IEEE80211_HW_NEED_DTIM_PERIOD) - bss_conf->dtim_period = bss->dtim_period; - else + if (local->hw.flags & IEEE80211_HW_NEED_DTIM_PERIOD) { + /* + * If the AP is buggy we may get here with no DTIM period + * known, so assume it's 1 which is the only safe assumption + * in that case, although if the TIM IE is broken powersave + * probably just won't work at all. + */ + bss_conf->dtim_period = sdata->u.mgd.dtim_period ?: 1; + } else { bss_conf->dtim_period = 0; + } bss_conf->assoc = 1; @@ -1350,7 +1437,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_ps(local, -1); mutex_unlock(&local->iflist_mtx); - ieee80211_recalc_smps(local); + ieee80211_recalc_smps(sdata); ieee80211_recalc_ps_vif(sdata); netif_tx_start_all_queues(sdata->dev); @@ -1443,11 +1530,14 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, changed |= BSS_CHANGED_ASSOC; sdata->vif.bss_conf.assoc = false; + sdata->vif.bss_conf.p2p_ctwindow = 0; + sdata->vif.bss_conf.p2p_oppps = false; + /* on the next assoc, re-program HT parameters */ memset(&ifmgd->ht_capa, 0, sizeof(ifmgd->ht_capa)); memset(&ifmgd->ht_capa_mask, 0, sizeof(ifmgd->ht_capa_mask)); - local->ap_power_level = 0; + sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; del_timer_sync(&local->dynamic_ps_timer); cancel_work_sync(&local->dynamic_ps_enable_work); @@ -1465,10 +1555,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, changed |= BSS_CHANGED_BSSID | BSS_CHANGED_HT; ieee80211_bss_info_change_notify(sdata, changed); - /* channel(_type) changes are handled by ieee80211_hw_config */ - WARN_ON(!ieee80211_set_channel_type(local, sdata, NL80211_CHAN_NO_HT)); - ieee80211_hw_config(local, 0); - /* disassociated - set to defaults now */ ieee80211_set_wmm_default(sdata, false); @@ -1478,6 +1564,11 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, del_timer_sync(&sdata->u.mgd.chswitch_timer); sdata->u.mgd.timers_running = 0; + + sdata->vif.bss_conf.dtim_period = 0; + + ifmgd->flags = 0; + ieee80211_vif_release_channel(sdata); } void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, @@ -1581,6 +1672,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) } else { int ssid_len; + rcu_read_lock(); ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); if (WARN_ON_ONCE(ssid == NULL)) ssid_len = 0; @@ -1589,7 +1681,8 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid_len, NULL, 0, (u32) -1, true, false, - ifmgd->associated->channel); + ifmgd->associated->channel, false); + rcu_read_unlock(); } ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms); @@ -1685,6 +1778,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, else return NULL; + rcu_read_lock(); ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID); if (WARN_ON_ONCE(ssid == NULL)) ssid_len = 0; @@ -1692,10 +1786,10 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, ssid_len = ssid[1]; skb = ieee80211_build_probe_req(sdata, cbss->bssid, - (u32) -1, - sdata->local->oper_channel, + (u32) -1, cbss->channel, ssid + 2, ssid_len, NULL, 0, true); + rcu_read_unlock(); return skb; } @@ -1804,6 +1898,8 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata, memset(sdata->u.mgd.bssid, 0, ETH_ALEN); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); + sdata->u.mgd.flags = 0; + ieee80211_vif_release_channel(sdata); } cfg80211_put_bss(auth_data->bss); @@ -1824,7 +1920,7 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, return; auth_data->expected_transaction = 4; drv_mgd_prepare_tx(sdata->local, sdata); - ieee80211_send_auth(sdata, 3, auth_data->algorithm, + ieee80211_send_auth(sdata, 3, auth_data->algorithm, 0, elems.challenge - 2, elems.challenge_len + 2, auth_data->bss->bssid, auth_data->bss->bssid, auth_data->key, auth_data->key_len, @@ -1858,8 +1954,13 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, status_code = le16_to_cpu(mgmt->u.auth.status_code); if (auth_alg != ifmgd->auth_data->algorithm || - auth_transaction != ifmgd->auth_data->expected_transaction) + auth_transaction != ifmgd->auth_data->expected_transaction) { + sdata_info(sdata, "%pM unexpected authentication state: alg %d (expected %d) transact %d (expected %d)\n", + mgmt->sa, auth_alg, ifmgd->auth_data->algorithm, + auth_transaction, + ifmgd->auth_data->expected_transaction); return RX_MGMT_NONE; + } if (status_code != WLAN_STATUS_SUCCESS) { sdata_info(sdata, "%pM denied authentication (status %d)\n", @@ -1872,6 +1973,7 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, case WLAN_AUTH_OPEN: case WLAN_AUTH_LEAP: case WLAN_AUTH_FT: + case WLAN_AUTH_SAE: break; case WLAN_AUTH_SHARED_KEY: if (ifmgd->auth_data->expected_transaction != 4) { @@ -1891,6 +1993,15 @@ ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, ifmgd->auth_data->timeout = jiffies + IEEE80211_AUTH_WAIT_ASSOC; run_again(ifmgd, ifmgd->auth_data->timeout); + if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && + ifmgd->auth_data->expected_transaction != 2) { + /* + * Report auth frame to user space for processing since another + * round of Authentication frames is still needed. + */ + return RX_MGMT_CFG80211_RX_AUTH; + } + /* move station state to auth */ mutex_lock(&sdata->local->sta_mtx); sta = sta_info_get(sdata, bssid); @@ -2030,6 +2141,8 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, memset(sdata->u.mgd.bssid, 0, ETH_ALEN); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); + sdata->u.mgd.flags = 0; + ieee80211_vif_release_channel(sdata); } kfree(assoc_data); @@ -2091,15 +2204,20 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, return false; } - sband = local->hw.wiphy->bands[local->oper_channel->band]; + sband = local->hw.wiphy->bands[ieee80211_get_sdata_band(sdata)]; - if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) + if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, elems.ht_cap_elem, &sta->sta.ht_cap); sta->supports_40mhz = sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40; + if (elems.vht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) + ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, + elems.vht_cap_elem, + &sta->sta.vht_cap); + rate_control_rate_init(sta); if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) @@ -2140,7 +2258,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, changed |= BSS_CHANGED_QOS; if (elems.ht_operation && elems.wmm_param && - !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) + !(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) changed |= ieee80211_config_ht_tx(sdata, elems.ht_operation, cbss->bssid, false); @@ -2247,9 +2365,9 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, return RX_MGMT_CFG80211_RX_ASSOC; } + static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len, + struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status, struct ieee802_11_elems *elems, bool beacon) @@ -2260,11 +2378,18 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel; bool need_ps = false; - if (sdata->u.mgd.associated && - ether_addr_equal(mgmt->bssid, sdata->u.mgd.associated->bssid)) { - bss = (void *)sdata->u.mgd.associated->priv; + if ((sdata->u.mgd.associated && + ether_addr_equal(mgmt->bssid, sdata->u.mgd.associated->bssid)) || + (sdata->u.mgd.assoc_data && + ether_addr_equal(mgmt->bssid, + sdata->u.mgd.assoc_data->bss->bssid))) { /* not previously set so we may need to recalc */ - need_ps = !bss->dtim_period; + need_ps = sdata->u.mgd.associated && !sdata->u.mgd.dtim_period; + + if (elems->tim && !elems->parse_error) { + struct ieee80211_tim_ie *tim_ie = elems->tim; + sdata->u.mgd.dtim_period = tim_ie->dtim_period; + } } if (elems->ds_params && elems->ds_params_len == 1) @@ -2369,8 +2494,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, size_t baselen; struct ieee802_11_elems elems; struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *chan; u32 changed = 0; - bool erp_valid, directed_tim = false; + bool erp_valid; u8 erp_value = 0; u32 ncrc; u8 *bssid; @@ -2382,8 +2509,19 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; - if (rx_status->freq != local->oper_channel->center_freq) + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) { + rcu_read_unlock(); return; + } + + if (rx_status->freq != chanctx_conf->def.chan->center_freq) { + rcu_read_unlock(); + return; + } + chan = chanctx_conf->def.chan; + rcu_read_unlock(); if (ifmgd->assoc_data && !ifmgd->assoc_data->have_beacon && ether_addr_equal(mgmt->bssid, ifmgd->assoc_data->bss->bssid)) { @@ -2490,11 +2628,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, len - baselen, &elems, care_about_ies, ncrc); - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) - directed_tim = ieee80211_check_tim(elems.tim, elems.tim_len, - ifmgd->aid); - if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) { + bool directed_tim = ieee80211_check_tim(elems.tim, + elems.tim_len, + ifmgd->aid); if (directed_tim) { if (local->hw.conf.dynamic_ps_timeout > 0) { if (local->hw.conf.flags & IEEE80211_CONF_PS) { @@ -2519,6 +2656,27 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } } + if (sdata->vif.p2p) { + u8 noa[2]; + int ret; + + ret = cfg80211_get_p2p_attr(mgmt->u.beacon.variable, + len - baselen, + IEEE80211_P2P_ATTR_ABSENCE_NOTICE, + noa, sizeof(noa)); + if (ret >= 2 && sdata->u.mgd.p2p_noa_index != noa[0]) { + bss_conf->p2p_oppps = noa[1] & 0x80; + bss_conf->p2p_ctwindow = noa[1] & 0x7f; + changed |= BSS_CHANGED_P2P_PS; + sdata->u.mgd.p2p_noa_index = noa[0]; + /* + * make sure we update all information, the CRC + * mechanism doesn't look at P2P attributes. + */ + ifmgd->beacon_crc_valid = false; + } + } + if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) return; ifmgd->beacon_crc = ncrc; @@ -2543,22 +2701,17 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (elems.ht_cap_elem && elems.ht_operation && elems.wmm_param && - !(ifmgd->flags & IEEE80211_STA_DISABLE_11N)) { - struct ieee80211_supported_band *sband; - - sband = local->hw.wiphy->bands[local->oper_channel->band]; - + !(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) changed |= ieee80211_config_ht_tx(sdata, elems.ht_operation, bssid, true); - } if (elems.country_elem && elems.pwr_constr_elem && mgmt->u.probe_resp.capab_info & cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT)) - ieee80211_handle_pwr_constr(sdata, local->oper_channel, - elems.country_elem, - elems.country_elem_len, - elems.pwr_constr_elem); + changed |= ieee80211_handle_pwr_constr(sdata, chan, + elems.country_elem, + elems.country_elem_len, + elems.pwr_constr_elem); ieee80211_bss_info_change_notify(sdata, changed); } @@ -2703,13 +2856,23 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) drv_mgd_prepare_tx(local, sdata); if (auth_data->bss->proberesp_ies) { + u16 trans = 1; + u16 status = 0; + sdata_info(sdata, "send auth to %pM (try %d/%d)\n", auth_data->bss->bssid, auth_data->tries, IEEE80211_AUTH_MAX_TRIES); auth_data->expected_transaction = 2; - ieee80211_send_auth(sdata, 1, auth_data->algorithm, - auth_data->ie, auth_data->ie_len, + + if (auth_data->algorithm == WLAN_AUTH_SAE) { + trans = auth_data->sae_trans; + status = auth_data->sae_status; + auth_data->expected_transaction = trans; + } + + ieee80211_send_auth(sdata, trans, auth_data->algorithm, status, + auth_data->data, auth_data->data_len, auth_data->bss->bssid, auth_data->bss->bssid, NULL, 0, 0); } else { @@ -2719,16 +2882,20 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) auth_data->bss->bssid, auth_data->tries, IEEE80211_AUTH_MAX_TRIES); + rcu_read_lock(); ssidie = ieee80211_bss_get_ie(auth_data->bss, WLAN_EID_SSID); - if (!ssidie) + if (!ssidie) { + rcu_read_unlock(); return -EINVAL; + } /* * Direct probe is sent to broadcast address as some APs * will not answer to direct packet in unassociated state. */ ieee80211_send_probe_req(sdata, NULL, ssidie + 2, ssidie[1], NULL, 0, (u32) -1, true, false, - auth_data->bss->channel); + auth_data->bss->channel, false); + rcu_read_unlock(); } auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; @@ -3058,90 +3225,313 @@ int ieee80211_max_network_latency(struct notifier_block *nb, return 0; } +static u32 chandef_downgrade(struct cfg80211_chan_def *c) +{ + u32 ret; + int tmp; + + switch (c->width) { + case NL80211_CHAN_WIDTH_20: + c->width = NL80211_CHAN_WIDTH_20_NOHT; + ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + break; + case NL80211_CHAN_WIDTH_40: + c->width = NL80211_CHAN_WIDTH_20; + c->center_freq1 = c->chan->center_freq; + ret = IEEE80211_STA_DISABLE_40MHZ | + IEEE80211_STA_DISABLE_VHT; + break; + case NL80211_CHAN_WIDTH_80: + tmp = (30 + c->chan->center_freq - c->center_freq1)/20; + /* n_P40 */ + tmp /= 2; + /* freq_P40 */ + c->center_freq1 = c->center_freq1 - 20 + 40 * tmp; + c->width = NL80211_CHAN_WIDTH_40; + ret = IEEE80211_STA_DISABLE_VHT; + break; + case NL80211_CHAN_WIDTH_80P80: + c->center_freq2 = 0; + c->width = NL80211_CHAN_WIDTH_80; + ret = IEEE80211_STA_DISABLE_80P80MHZ | + IEEE80211_STA_DISABLE_160MHZ; + break; + case NL80211_CHAN_WIDTH_160: + /* n_P20 */ + tmp = (70 + c->chan->center_freq - c->center_freq1)/20; + /* n_P80 */ + tmp /= 4; + c->center_freq1 = c->center_freq1 - 40 + 80 * tmp; + c->width = NL80211_CHAN_WIDTH_80; + ret = IEEE80211_STA_DISABLE_80P80MHZ | + IEEE80211_STA_DISABLE_160MHZ; + break; + default: + case NL80211_CHAN_WIDTH_20_NOHT: + WARN_ON_ONCE(1); + c->width = NL80211_CHAN_WIDTH_20_NOHT; + ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + break; + } + + WARN_ON_ONCE(!cfg80211_chandef_valid(c)); + + return ret; +} + +static u32 +ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct ieee80211_channel *channel, + const struct ieee80211_ht_operation *ht_oper, + const struct ieee80211_vht_operation *vht_oper, + struct cfg80211_chan_def *chandef) +{ + struct cfg80211_chan_def vht_chandef; + u32 ht_cfreq, ret; + + chandef->chan = channel; + chandef->width = NL80211_CHAN_WIDTH_20_NOHT; + chandef->center_freq1 = channel->center_freq; + chandef->center_freq2 = 0; + + if (!ht_oper || !sband->ht_cap.ht_supported) { + ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + goto out; + } + + chandef->width = NL80211_CHAN_WIDTH_20; + + ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, + channel->band); + /* check that channel matches the right operating channel */ + if (channel->center_freq != ht_cfreq) { + /* + * It's possible that some APs are confused here; + * Netgear WNDR3700 sometimes reports 4 higher than + * the actual channel in association responses, but + * since we look at probe response/beacon data here + * it should be OK. + */ + sdata_info(sdata, + "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", + channel->center_freq, ht_cfreq, + ht_oper->primary_chan, channel->band); + ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + goto out; + } + + /* check 40 MHz support, if we have it */ + if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { + switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { + case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: + chandef->width = NL80211_CHAN_WIDTH_40; + chandef->center_freq1 += 10; + break; + case IEEE80211_HT_PARAM_CHA_SEC_BELOW: + chandef->width = NL80211_CHAN_WIDTH_40; + chandef->center_freq1 -= 10; + break; + } + } else { + /* 40 MHz (and 80 MHz) must be supported for VHT */ + ret = IEEE80211_STA_DISABLE_VHT; + goto out; + } + + if (!vht_oper || !sband->vht_cap.vht_supported) { + ret = IEEE80211_STA_DISABLE_VHT; + goto out; + } + + vht_chandef.chan = channel; + vht_chandef.center_freq1 = + ieee80211_channel_to_frequency(vht_oper->center_freq_seg1_idx, + channel->band); + vht_chandef.center_freq2 = 0; + + if (vht_oper->center_freq_seg2_idx) + vht_chandef.center_freq2 = + ieee80211_channel_to_frequency( + vht_oper->center_freq_seg2_idx, + channel->band); + + switch (vht_oper->chan_width) { + case IEEE80211_VHT_CHANWIDTH_USE_HT: + vht_chandef.width = chandef->width; + break; + case IEEE80211_VHT_CHANWIDTH_80MHZ: + vht_chandef.width = NL80211_CHAN_WIDTH_80; + break; + case IEEE80211_VHT_CHANWIDTH_160MHZ: + vht_chandef.width = NL80211_CHAN_WIDTH_160; + break; + case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + vht_chandef.width = NL80211_CHAN_WIDTH_80P80; + break; + default: + sdata_info(sdata, + "AP VHT operation IE has invalid channel width (%d), disable VHT\n", + vht_oper->chan_width); + ret = IEEE80211_STA_DISABLE_VHT; + goto out; + } + + if (!cfg80211_chandef_valid(&vht_chandef)) { + sdata_info(sdata, + "AP VHT information is invalid, disable VHT\n"); + ret = IEEE80211_STA_DISABLE_VHT; + goto out; + } + + if (cfg80211_chandef_identical(chandef, &vht_chandef)) { + ret = 0; + goto out; + } + + if (!cfg80211_chandef_compatible(chandef, &vht_chandef)) { + sdata_info(sdata, + "AP VHT information doesn't match HT, disable VHT\n"); + ret = IEEE80211_STA_DISABLE_VHT; + goto out; + } + + *chandef = vht_chandef; + + ret = 0; + + while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef, + IEEE80211_CHAN_DISABLED)) { + if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) { + ret = IEEE80211_STA_DISABLE_HT | + IEEE80211_STA_DISABLE_VHT; + goto out; + } + + ret = chandef_downgrade(chandef); + } + + if (chandef->width != vht_chandef.width) + sdata_info(sdata, + "local regulatory prevented using AP HT/VHT configuration, downgraded\n"); + +out: + WARN_ON_ONCE(!cfg80211_chandef_valid(chandef)); + return ret; +} + +static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, + struct cfg80211_bss *cbss) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + const u8 *ht_cap_ie, *vht_cap_ie; + const struct ieee80211_ht_cap *ht_cap; + const struct ieee80211_vht_cap *vht_cap; + u8 chains = 1; + + if (ifmgd->flags & IEEE80211_STA_DISABLE_HT) + return chains; + + ht_cap_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_CAPABILITY); + if (ht_cap_ie && ht_cap_ie[1] >= sizeof(*ht_cap)) { + ht_cap = (void *)(ht_cap_ie + 2); + chains = ieee80211_mcs_to_chains(&ht_cap->mcs); + /* + * TODO: use "Tx Maximum Number Spatial Streams Supported" and + * "Tx Unequal Modulation Supported" fields. + */ + } + + if (ifmgd->flags & IEEE80211_STA_DISABLE_VHT) + return chains; + + vht_cap_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_VHT_CAPABILITY); + if (vht_cap_ie && vht_cap_ie[1] >= sizeof(*vht_cap)) { + u8 nss; + u16 tx_mcs_map; + + vht_cap = (void *)(vht_cap_ie + 2); + tx_mcs_map = le16_to_cpu(vht_cap->supp_mcs.tx_mcs_map); + for (nss = 8; nss > 0; nss--) { + if (((tx_mcs_map >> (2 * (nss - 1))) & 3) != + IEEE80211_VHT_MCS_NOT_SUPPORTED) + break; + } + /* TODO: use "Tx Highest Supported Long GI Data Rate" field? */ + chains = max(chains, nss); + } + + return chains; +} + static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - int ht_cfreq; - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - const u8 *ht_oper_ie; const struct ieee80211_ht_operation *ht_oper = NULL; + const struct ieee80211_vht_operation *vht_oper = NULL; struct ieee80211_supported_band *sband; + struct cfg80211_chan_def chandef; + int ret; sband = local->hw.wiphy->bands[cbss->channel->band]; - ifmgd->flags &= ~IEEE80211_STA_DISABLE_40MHZ; + ifmgd->flags &= ~(IEEE80211_STA_DISABLE_40MHZ | + IEEE80211_STA_DISABLE_80P80MHZ | + IEEE80211_STA_DISABLE_160MHZ); - if (sband->ht_cap.ht_supported) { - ht_oper_ie = cfg80211_find_ie(WLAN_EID_HT_OPERATION, - cbss->information_elements, - cbss->len_information_elements); + rcu_read_lock(); + + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) && + sband->ht_cap.ht_supported) { + const u8 *ht_oper_ie; + + ht_oper_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_OPERATION); if (ht_oper_ie && ht_oper_ie[1] >= sizeof(*ht_oper)) ht_oper = (void *)(ht_oper_ie + 2); } - if (ht_oper) { - ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, - cbss->channel->band); - /* check that channel matches the right operating channel */ - if (cbss->channel->center_freq != ht_cfreq) { - /* - * It's possible that some APs are confused here; - * Netgear WNDR3700 sometimes reports 4 higher than - * the actual channel in association responses, but - * since we look at probe response/beacon data here - * it should be OK. - */ + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) && + sband->vht_cap.vht_supported) { + const u8 *vht_oper_ie; + + vht_oper_ie = ieee80211_bss_get_ie(cbss, + WLAN_EID_VHT_OPERATION); + if (vht_oper_ie && vht_oper_ie[1] >= sizeof(*vht_oper)) + vht_oper = (void *)(vht_oper_ie + 2); + if (vht_oper && !ht_oper) { + vht_oper = NULL; sdata_info(sdata, - "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", - cbss->channel->center_freq, - ht_cfreq, ht_oper->primary_chan, - cbss->channel->band); - ht_oper = NULL; - } else { - channel_type = NL80211_CHAN_HT20; + "AP advertised VHT without HT, disabling both\n"); + sdata->flags |= IEEE80211_STA_DISABLE_HT; + sdata->flags |= IEEE80211_STA_DISABLE_VHT; } } - if (ht_oper && sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { - /* - * cfg80211 already verified that the channel itself can - * be used, but it didn't check that we can do the right - * HT type, so do that here as well. If HT40 isn't allowed - * on this channel, disable 40 MHz operation. - */ + ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, + cbss->channel, + ht_oper, vht_oper, + &chandef); - switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { - case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: - if (cbss->channel->flags & IEEE80211_CHAN_NO_HT40PLUS) - ifmgd->flags |= IEEE80211_STA_DISABLE_40MHZ; - else - channel_type = NL80211_CHAN_HT40PLUS; - break; - case IEEE80211_HT_PARAM_CHA_SEC_BELOW: - if (cbss->channel->flags & IEEE80211_CHAN_NO_HT40MINUS) - ifmgd->flags |= IEEE80211_STA_DISABLE_40MHZ; - else - channel_type = NL80211_CHAN_HT40MINUS; - break; - } - } + sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), + local->rx_chains); - if (!ieee80211_set_channel_type(local, sdata, channel_type)) { - /* can only fail due to HT40+/- mismatch */ - channel_type = NL80211_CHAN_HT20; - sdata_info(sdata, - "disabling 40 MHz due to multi-vif mismatch\n"); - ifmgd->flags |= IEEE80211_STA_DISABLE_40MHZ; - WARN_ON(!ieee80211_set_channel_type(local, sdata, - channel_type)); - } + rcu_read_unlock(); - local->oper_channel = cbss->channel; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + /* will change later if needed */ + sdata->smps_mode = IEEE80211_SMPS_OFF; - return 0; + /* + * If this fails (possibly due to channel context sharing + * on incompatible channels, e.g. 80+80 and 160 sharing the + * same control channel) try to use a smaller bandwidth. + */ + ret = ieee80211_vif_use_channel(sdata, &chandef, + IEEE80211_CHANCTX_SHARED); + while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT) + ifmgd->flags |= chandef_downgrade(&chandef); + return ret; } static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, @@ -3211,7 +3601,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.basic_rates = basic_rates; /* cf. IEEE 802.11 9.2.12 */ - if (local->oper_channel->band == IEEE80211_BAND_2GHZ && + if (cbss->channel->band == IEEE80211_BAND_2GHZ && have_higher_than_11mbit) sdata->flags |= IEEE80211_SDATA_OPERATING_GMODE; else @@ -3273,19 +3663,33 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, case NL80211_AUTHTYPE_NETWORK_EAP: auth_alg = WLAN_AUTH_LEAP; break; + case NL80211_AUTHTYPE_SAE: + auth_alg = WLAN_AUTH_SAE; + break; default: return -EOPNOTSUPP; } - auth_data = kzalloc(sizeof(*auth_data) + req->ie_len, GFP_KERNEL); + auth_data = kzalloc(sizeof(*auth_data) + req->sae_data_len + + req->ie_len, GFP_KERNEL); if (!auth_data) return -ENOMEM; auth_data->bss = req->bss; + if (req->sae_data_len >= 4) { + __le16 *pos = (__le16 *) req->sae_data; + auth_data->sae_trans = le16_to_cpu(pos[0]); + auth_data->sae_status = le16_to_cpu(pos[1]); + memcpy(auth_data->data, req->sae_data + 4, + req->sae_data_len - 4); + auth_data->data_len += req->sae_data_len - 4; + } + if (req->ie && req->ie_len) { - memcpy(auth_data->ie, req->ie, req->ie_len); - auth_data->ie_len = req->ie_len; + memcpy(&auth_data->data[auth_data->data_len], + req->ie, req->ie_len); + auth_data->data_len += req->ie_len; } if (req->key && req->key_len) { @@ -3355,14 +3759,21 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, const u8 *ssidie, *ht_ie; int i, err; - ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); - if (!ssidie) - return -EINVAL; - assoc_data = kzalloc(sizeof(*assoc_data) + req->ie_len, GFP_KERNEL); if (!assoc_data) return -ENOMEM; + rcu_read_lock(); + ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); + if (!ssidie) { + rcu_read_unlock(); + kfree(assoc_data); + return -EINVAL; + } + memcpy(assoc_data->ssid, ssidie + 2, ssidie[1]); + assoc_data->ssid_len = ssidie[1]; + rcu_read_unlock(); + mutex_lock(&ifmgd->mtx); if (ifmgd->associated) @@ -3388,13 +3799,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, /* prepare assoc data */ - /* - * keep only the 40 MHz disable bit set as it might have - * been set during authentication already, all other bits - * should be reset for a new connection - */ - ifmgd->flags &= IEEE80211_STA_DISABLE_40MHZ; - ifmgd->beacon_crc_valid = false; /* @@ -3408,7 +3812,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP40 || req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_TKIP || req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) { - ifmgd->flags |= IEEE80211_STA_DISABLE_11N; + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; netdev_info(sdata->dev, "disabling HT/VHT due to WEP/TKIP use\n"); @@ -3416,7 +3820,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, } if (req->flags & ASSOC_REQ_DISABLE_HT) { - ifmgd->flags |= IEEE80211_STA_DISABLE_11N; + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; } @@ -3424,7 +3828,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, sband = local->hw.wiphy->bands[req->bss->channel->band]; if (!sband->ht_cap.ht_supported || local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used) { - ifmgd->flags |= IEEE80211_STA_DISABLE_11N; + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; if (!bss->wmm_used) netdev_info(sdata->dev, "disabling HT as WMM/QoS is not supported by the AP\n"); @@ -3452,11 +3856,11 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (ifmgd->req_smps == IEEE80211_SMPS_AUTOMATIC) { if (ifmgd->powersave) - ifmgd->ap_smps = IEEE80211_SMPS_DYNAMIC; + sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; else - ifmgd->ap_smps = IEEE80211_SMPS_OFF; + sdata->smps_mode = IEEE80211_SMPS_OFF; } else - ifmgd->ap_smps = ifmgd->req_smps; + sdata->smps_mode = ifmgd->req_smps; assoc_data->capability = req->bss->capability; assoc_data->wmm = bss->wmm_used && @@ -3464,12 +3868,14 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, assoc_data->supp_rates = bss->supp_rates; assoc_data->supp_rates_len = bss->supp_rates_len; + rcu_read_lock(); ht_ie = ieee80211_bss_get_ie(req->bss, WLAN_EID_HT_OPERATION); if (ht_ie && ht_ie[1] >= sizeof(struct ieee80211_ht_operation)) assoc_data->ap_ht_param = ((struct ieee80211_ht_operation *)(ht_ie + 2))->ht_param; else - ifmgd->flags |= IEEE80211_STA_DISABLE_11N; + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; + rcu_read_unlock(); if (bss->wmm_used && bss->uapsd_supported && (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { @@ -3480,9 +3886,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, ifmgd->flags &= ~IEEE80211_STA_UAPSD_ENABLED; } - memcpy(assoc_data->ssid, ssidie + 2, ssidie[1]); - assoc_data->ssid_len = ssidie[1]; - if (req->prev_bssid) memcpy(assoc_data->prev_bssid, req->prev_bssid, ETH_ALEN); @@ -3505,20 +3908,41 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, /* kick off associate process */ ifmgd->assoc_data = assoc_data; + ifmgd->dtim_period = 0; err = ieee80211_prep_connection(sdata, req->bss, true); if (err) goto err_clear; - if (!bss->dtim_period && - sdata->local->hw.flags & IEEE80211_HW_NEED_DTIM_PERIOD) { - /* - * Wait up to one beacon interval ... - * should this be more if we miss one? - */ - sdata_info(sdata, "waiting for beacon from %pM\n", - ifmgd->bssid); - assoc_data->timeout = TU_TO_EXP_TIME(req->bss->beacon_interval); + if (sdata->local->hw.flags & IEEE80211_HW_NEED_DTIM_PERIOD) { + const struct cfg80211_bss_ies *beacon_ies; + + rcu_read_lock(); + beacon_ies = rcu_dereference(req->bss->beacon_ies); + if (!beacon_ies) { + /* + * Wait up to one beacon interval ... + * should this be more if we miss one? + */ + sdata_info(sdata, "waiting for beacon from %pM\n", + ifmgd->bssid); + assoc_data->timeout = + TU_TO_EXP_TIME(req->bss->beacon_interval); + } else { + const u8 *tim_ie = cfg80211_find_ie(WLAN_EID_TIM, + beacon_ies->data, + beacon_ies->len); + if (tim_ie && tim_ie[1] >= + sizeof(struct ieee80211_tim_ie)) { + const struct ieee80211_tim_ie *tim; + tim = (void *)(tim_ie + 2); + ifmgd->dtim_period = tim->dtim_period; + } + assoc_data->have_beacon = true; + assoc_data->sent_assoc = false; + assoc_data->timeout = jiffies; + } + rcu_read_unlock(); } else { assoc_data->have_beacon = true; assoc_data->sent_assoc = false; @@ -3560,40 +3984,44 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; bool tx = !req->local_state_change; + bool sent_frame = false; mutex_lock(&ifmgd->mtx); - if (ifmgd->auth_data) { - ieee80211_destroy_auth_data(sdata, false); - mutex_unlock(&ifmgd->mtx); - return 0; - } - sdata_info(sdata, "deauthenticating from %pM by local choice (reason=%d)\n", req->bssid, req->reason_code); - if (ifmgd->associated && - ether_addr_equal(ifmgd->associated->bssid, req->bssid)) { - ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, - req->reason_code, tx, frame_buf); - } else { + if (ifmgd->auth_data) { drv_mgd_prepare_tx(sdata->local, sdata); ieee80211_send_deauth_disassoc(sdata, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, frame_buf); + ieee80211_destroy_auth_data(sdata, false); + mutex_unlock(&ifmgd->mtx); + + sent_frame = tx; + goto out; } + if (ifmgd->associated && + ether_addr_equal(ifmgd->associated->bssid, req->bssid)) { + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, + req->reason_code, tx, frame_buf); + sent_frame = tx; + } mutex_unlock(&ifmgd->mtx); - __cfg80211_send_deauth(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); - + out: mutex_lock(&sdata->local->mtx); ieee80211_recalc_idle(sdata->local); mutex_unlock(&sdata->local->mtx); + if (sent_frame) + __cfg80211_send_deauth(sdata->dev, frame_buf, + IEEE80211_DEAUTH_FRAME_LEN); + return 0; } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 83608ac16780..a3ad4c3c80a3 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -102,11 +102,13 @@ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata) ieee80211_sta_reset_conn_monitor(sdata); } -void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, - bool offchannel_ps_enable) +void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; + if (WARN_ON(local->use_chanctx)) + return; + /* * notify the AP about us leaving the channel and stop all * STA interfaces. @@ -131,8 +133,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, if (sdata->vif.type != NL80211_IFTYPE_MONITOR) { netif_tx_stop_all_queues(sdata->dev); - if (offchannel_ps_enable && - (sdata->vif.type == NL80211_IFTYPE_STATION) && + if (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.associated) ieee80211_offchannel_ps_enable(sdata); } @@ -140,11 +141,13 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, mutex_unlock(&local->iflist_mtx); } -void ieee80211_offchannel_return(struct ieee80211_local *local, - bool offchannel_ps_disable) +void ieee80211_offchannel_return(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; + if (WARN_ON(local->use_chanctx)) + return; + mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE) @@ -157,11 +160,9 @@ void ieee80211_offchannel_return(struct ieee80211_local *local, continue; /* Tell AP we're back */ - if (offchannel_ps_disable && - sdata->vif.type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.associated) - ieee80211_offchannel_ps_disable(sdata); - } + if (sdata->vif.type == NL80211_IFTYPE_STATION && + sdata->u.mgd.associated) + ieee80211_offchannel_ps_disable(sdata); if (sdata->vif.type != NL80211_IFTYPE_MONITOR) { /* @@ -193,13 +194,14 @@ void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc) if (roc->mgmt_tx_cookie) { if (!WARN_ON(!roc->frame)) { - ieee80211_tx_skb(roc->sdata, roc->frame); + ieee80211_tx_skb_tid_band(roc->sdata, roc->frame, 7, + roc->chan->band); roc->frame = NULL; } } else { - cfg80211_ready_on_channel(&roc->sdata->wdev, (unsigned long)roc, - roc->chan, roc->chan_type, - roc->req_duration, GFP_KERNEL); + cfg80211_ready_on_channel(&roc->sdata->wdev, roc->cookie, + roc->chan, roc->req_duration, + GFP_KERNEL); } roc->notified = true; @@ -276,8 +278,7 @@ void ieee80211_start_next_roc(struct ieee80211_local *local) if (!duration) duration = 10; - ret = drv_remain_on_channel(local, roc->chan, - roc->chan_type, + ret = drv_remain_on_channel(local, roc->sdata, roc->chan, duration); roc->started = true; @@ -313,8 +314,7 @@ void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc) if (!roc->mgmt_tx_cookie) cfg80211_remain_on_channel_expired(&roc->sdata->wdev, - (unsigned long)roc, - roc->chan, roc->chan_type, + roc->cookie, roc->chan, GFP_KERNEL); list_for_each_entry_safe(dep, tmp, &roc->dependents, list) @@ -353,7 +353,6 @@ void ieee80211_sw_roc_work(struct work_struct *work) ieee80211_recalc_idle(local); local->tmp_channel = roc->chan; - local->tmp_channel_type = roc->chan_type; ieee80211_hw_config(local, 0); /* tell userspace or send frame */ @@ -381,7 +380,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) local->tmp_channel = NULL; ieee80211_hw_config(local, 0); - ieee80211_offchannel_return(local, true); + ieee80211_offchannel_return(local); } ieee80211_recalc_idle(local); @@ -458,8 +457,6 @@ void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata) list_move_tail(&roc->list, &tmp_list); roc->abort = true; } - - ieee80211_start_next_roc(local); mutex_unlock(&local->mtx); list_for_each_entry_safe(roc, tmp, &tmp_list, list) { diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 5c572e7a1a71..79a48f37d409 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -33,6 +33,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; struct sta_info *sta; + struct ieee80211_chanctx *ctx; if (!local->open_count) goto suspend; @@ -135,12 +136,55 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + if (sdata->vif.type == NL80211_IFTYPE_AP && + rcu_access_pointer(sdata->u.ap.beacon)) + drv_stop_ap(local, sdata); + + if (local->use_chanctx) { + struct ieee80211_chanctx_conf *conf; + + mutex_lock(&local->chanctx_mtx); + conf = rcu_dereference_protected( + sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (conf) { + ctx = container_of(conf, + struct ieee80211_chanctx, + conf); + drv_unassign_vif_chanctx(local, sdata, ctx); + } + + mutex_unlock(&local->chanctx_mtx); + } drv_remove_interface(local, sdata); } sdata = rtnl_dereference(local->monitor_sdata); - if (sdata) + if (sdata) { + if (local->use_chanctx) { + struct ieee80211_chanctx_conf *conf; + + mutex_lock(&local->chanctx_mtx); + conf = rcu_dereference_protected( + sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (conf) { + ctx = container_of(conf, + struct ieee80211_chanctx, + conf); + drv_unassign_vif_chanctx(local, sdata, ctx); + } + + mutex_unlock(&local->chanctx_mtx); + } + drv_remove_interface(local, sdata); + } + + mutex_lock(&local->chanctx_mtx); + list_for_each_entry(ctx, &local->chanctx_list, list) + drv_remove_chanctx(local, ctx); + mutex_unlock(&local->chanctx_mtx); /* stop hardware - this must stop RX */ if (local->open_count) diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 3313c117b322..dd88381c53b7 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -391,7 +391,7 @@ static void rate_idx_match_mask(struct ieee80211_tx_rate *rate, return; /* if HT BSS, and we handle a data frame, also try HT rates */ - if (txrc->bss_conf->channel_type == NL80211_CHAN_NO_HT) + if (txrc->bss_conf->chandef.width == NL80211_CHAN_WIDTH_20_NOHT) return; fc = hdr->frame_control; @@ -408,8 +408,7 @@ static void rate_idx_match_mask(struct ieee80211_tx_rate *rate, alt_rate.flags |= IEEE80211_TX_RC_MCS; - if ((txrc->bss_conf->channel_type == NL80211_CHAN_HT40MINUS) || - (txrc->bss_conf->channel_type == NL80211_CHAN_HT40PLUS)) + if (txrc->bss_conf->chandef.width == NL80211_CHAN_WIDTH_40) alt_rate.flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; if (rate_idx_match_mcs_mask(&alt_rate, mcs_mask)) { diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 10de668eb9f6..301386dabf88 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -52,11 +52,21 @@ static inline void rate_control_rate_init(struct sta_info *sta) struct ieee80211_sta *ista = &sta->sta; void *priv_sta = sta->rate_ctrl_priv; struct ieee80211_supported_band *sband; + struct ieee80211_chanctx_conf *chanctx_conf; if (!ref) return; - sband = local->hw.wiphy->bands[local->oper_channel->band]; + rcu_read_lock(); + + chanctx_conf = rcu_dereference(sta->sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return; + } + + sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band]; + rcu_read_unlock(); ref->ops->rate_init(ref->priv, sband, ista, priv_sta); set_sta_flag(sta, WLAN_STA_RATE_CONTROL); diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 79633ae06fd6..8c5acdc06226 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -154,6 +154,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, void *priv_sta, struct sk_buff *skb) { + struct minstrel_priv *mp = priv; struct minstrel_sta_info *mi = priv_sta; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_tx_rate *ar = info->status.rates; @@ -181,6 +182,10 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, if (mi->sample_deferred > 0) mi->sample_deferred--; + + if (time_after(jiffies, mi->stats_update + + (mp->update_interval * HZ) / 1000)) + minstrel_update_stats(mp, mi); } @@ -235,10 +240,6 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, mrr = mp->has_mrr && !txrc->rts && !txrc->bss_conf->use_cts_prot; - if (time_after(jiffies, mi->stats_update + (mp->update_interval * - HZ) / 1000)) - minstrel_update_stats(mp, mi); - ndx = mi->max_tp_rate; if (mrr) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index fb1d4aa65e8c..9f9c453bc45d 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -389,9 +389,9 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, struct ieee80211_tx_rate *ar = info->status.rates; struct minstrel_rate_stats *rate, *rate2; struct minstrel_priv *mp = priv; - bool last = false; + bool last; int group; - int i = 0; + int i; if (!msp->is_ht) return mac80211_minstrel.tx_status(priv, sband, sta, &msp->legacy, skb); @@ -419,13 +419,11 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) mi->sample_packets += info->status.ampdu_len; + last = !minstrel_ht_txstat_valid(&ar[0]); for (i = 0; !last; i++) { last = (i == IEEE80211_TX_MAX_RATES - 1) || !minstrel_ht_txstat_valid(&ar[i + 1]); - if (!minstrel_ht_txstat_valid(&ar[i])) - break; - group = minstrel_ht_get_group_idx(&ar[i]); rate = &mi->groups[group].rates[ar[i].idx % 8]; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 61c621e9273f..580704eba8b8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -40,6 +40,8 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local, struct sk_buff *skb) { + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) { if (likely(skb->len > FCS_LEN)) __pskb_trim(skb, skb->len - FCS_LEN); @@ -47,24 +49,29 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local, /* driver bug */ WARN_ON(1); dev_kfree_skb(skb); - skb = NULL; + return NULL; } } + if (status->vendor_radiotap_len) + __pskb_pull(skb, status->vendor_radiotap_len); + return skb; } -static inline int should_drop_frame(struct sk_buff *skb, - int present_fcs_len) +static inline int should_drop_frame(struct sk_buff *skb, int present_fcs_len) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct ieee80211_hdr *hdr; + + hdr = (void *)(skb->data + status->vendor_radiotap_len); if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC | RX_FLAG_AMPDU_IS_ZEROLEN)) return 1; - if (unlikely(skb->len < 16 + present_fcs_len)) + if (unlikely(skb->len < 16 + present_fcs_len + + status->vendor_radiotap_len)) return 1; if (ieee80211_is_ctl(hdr->frame_control) && !ieee80211_is_pspoll(hdr->frame_control) && @@ -74,32 +81,53 @@ static inline int should_drop_frame(struct sk_buff *skb, } static int -ieee80211_rx_radiotap_len(struct ieee80211_local *local, - struct ieee80211_rx_status *status) +ieee80211_rx_radiotap_space(struct ieee80211_local *local, + struct ieee80211_rx_status *status) { int len; /* always present fields */ len = sizeof(struct ieee80211_radiotap_header) + 9; - if (status->flag & RX_FLAG_MACTIME_MPDU) + /* allocate extra bitmap */ + if (status->vendor_radiotap_len) + len += 4; + + if (ieee80211_have_rx_timestamp(status)) { + len = ALIGN(len, 8); len += 8; + } if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM) len += 1; - if (len & 1) /* padding for RX_FLAGS if necessary */ - len++; + /* padding for RX_FLAGS if necessary */ + len = ALIGN(len, 2); if (status->flag & RX_FLAG_HT) /* HT info */ len += 3; if (status->flag & RX_FLAG_AMPDU_DETAILS) { - /* padding */ - while (len & 3) - len++; + len = ALIGN(len, 4); len += 8; } + if (status->flag & RX_FLAG_VHT) { + len = ALIGN(len, 2); + len += 12; + } + + if (status->vendor_radiotap_len) { + if (WARN_ON_ONCE(status->vendor_radiotap_align == 0)) + status->vendor_radiotap_align = 1; + /* align standard part of vendor namespace */ + len = ALIGN(len, 2); + /* allocate standard part of vendor namespace */ + len += 6; + /* align vendor-defined part */ + len = ALIGN(len, status->vendor_radiotap_align); + /* vendor-defined part is already in skb */ + } + return len; } @@ -118,6 +146,11 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, struct ieee80211_radiotap_header *rthdr; unsigned char *pos; u16 rx_flags = 0; + int mpdulen; + + mpdulen = skb->len; + if (!(has_fcs && (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS))) + mpdulen += FCS_LEN; rthdr = (struct ieee80211_radiotap_header *)skb_push(skb, rtap_len); memset(rthdr, 0, rtap_len); @@ -128,17 +161,30 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, (1 << IEEE80211_RADIOTAP_CHANNEL) | (1 << IEEE80211_RADIOTAP_ANTENNA) | (1 << IEEE80211_RADIOTAP_RX_FLAGS)); - rthdr->it_len = cpu_to_le16(rtap_len); + rthdr->it_len = cpu_to_le16(rtap_len + status->vendor_radiotap_len); - pos = (unsigned char *)(rthdr+1); + pos = (unsigned char *)(rthdr + 1); + + if (status->vendor_radiotap_len) { + rthdr->it_present |= + cpu_to_le32(BIT(IEEE80211_RADIOTAP_VENDOR_NAMESPACE)) | + cpu_to_le32(BIT(IEEE80211_RADIOTAP_EXT)); + put_unaligned_le32(status->vendor_radiotap_bitmap, pos); + pos += 4; + } /* the order of the following fields is important */ /* IEEE80211_RADIOTAP_TSFT */ - if (status->flag & RX_FLAG_MACTIME_MPDU) { - put_unaligned_le64(status->mactime, pos); - rthdr->it_present |= - cpu_to_le32(1 << IEEE80211_RADIOTAP_TSFT); + if (ieee80211_have_rx_timestamp(status)) { + /* padding */ + while ((pos - (u8 *)rthdr) & 7) + *pos++ = 0; + put_unaligned_le64( + ieee80211_calculate_rx_timestamp(local, status, + mpdulen, 0), + pos); + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_TSFT); pos += 8; } @@ -152,7 +198,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, pos++; /* IEEE80211_RADIOTAP_RATE */ - if (!rate || status->flag & RX_FLAG_HT) { + if (!rate || status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) { /* * Without rate information don't add it. If we have, * MCS information is a separate field in radiotap, @@ -172,7 +218,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, if (status->band == IEEE80211_BAND_5GHZ) put_unaligned_le16(IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ, pos); - else if (status->flag & RX_FLAG_HT) + else if (status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) put_unaligned_le16(IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ, pos); else if (rate && rate->flags & IEEE80211_RATE_ERP_G) @@ -205,7 +251,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, /* IEEE80211_RADIOTAP_RX_FLAGS */ /* ensure 2 byte alignment for the 2 byte field as required */ if ((pos - (u8 *)rthdr) & 1) - pos++; + *pos++ = 0; if (status->flag & RX_FLAG_FAILED_PLCP_CRC) rx_flags |= IEEE80211_RADIOTAP_F_RX_BADPLCP; put_unaligned_le16(rx_flags, pos); @@ -255,6 +301,56 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, *pos++ = 0; *pos++ = 0; } + + if (status->flag & RX_FLAG_VHT) { + u16 known = local->hw.radiotap_vht_details; + + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT); + /* known field - how to handle 80+80? */ + if (status->flag & RX_FLAG_80P80MHZ) + known &= ~IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH; + put_unaligned_le16(known, pos); + pos += 2; + /* flags */ + if (status->flag & RX_FLAG_SHORT_GI) + *pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; + pos++; + /* bandwidth */ + if (status->flag & RX_FLAG_80MHZ) + *pos++ = 4; + else if (status->flag & RX_FLAG_80P80MHZ) + *pos++ = 0; /* marked not known above */ + else if (status->flag & RX_FLAG_160MHZ) + *pos++ = 11; + else if (status->flag & RX_FLAG_40MHZ) + *pos++ = 1; + else /* 20 MHz */ + *pos++ = 0; + /* MCS/NSS */ + *pos = (status->rate_idx << 4) | status->vht_nss; + pos += 4; + /* coding field */ + pos++; + /* group ID */ + pos++; + /* partial_aid */ + pos += 2; + } + + if (status->vendor_radiotap_len) { + /* ensure 2 byte alignment for the vendor field as required */ + if ((pos - (u8 *)rthdr) & 1) + *pos++ = 0; + *pos++ = status->vendor_radiotap_oui[0]; + *pos++ = status->vendor_radiotap_oui[1]; + *pos++ = status->vendor_radiotap_oui[2]; + *pos++ = status->vendor_radiotap_subns; + put_unaligned_le16(status->vendor_radiotap_len, pos); + pos += 2; + /* align the actual payload as requested */ + while ((pos - (u8 *)rthdr) & (status->vendor_radiotap_align - 1)) + *pos++ = 0; + } } /* @@ -282,14 +378,11 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, * the SKB because it has a bad FCS/PLCP checksum. */ - /* room for the radiotap header based on driver features */ - needed_headroom = ieee80211_rx_radiotap_len(local, status); - if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) present_fcs_len = FCS_LEN; - /* make sure hdr->frame_control is on the linear part */ - if (!pskb_may_pull(origskb, 2)) { + /* ensure hdr->frame_control and vendor radiotap data are in skb head */ + if (!pskb_may_pull(origskb, 2 + status->vendor_radiotap_len)) { dev_kfree_skb(origskb); return NULL; } @@ -303,6 +396,9 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return remove_monitor_info(local, origskb); } + /* room for the radiotap header based on driver features */ + needed_headroom = ieee80211_rx_radiotap_space(local, status); + if (should_drop_frame(origskb, present_fcs_len)) { /* only need to expand headroom if necessary */ skb = origskb; @@ -374,7 +470,6 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return origskb; } - static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; @@ -403,10 +498,10 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) * * We also use that counter for non-QoS STAs. */ - seqno_idx = NUM_RX_DATA_QUEUES; + seqno_idx = IEEE80211_NUM_TIDS; security_idx = 0; if (ieee80211_is_mgmt(hdr->frame_control)) - security_idx = NUM_RX_DATA_QUEUES; + security_idx = IEEE80211_NUM_TIDS; tid = 0; } @@ -481,8 +576,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) struct ieee80211_mgmt *hdr = (struct ieee80211_mgmt *) skb->data; struct ieee80211_mmie *mmie; - if (skb->len < 24 + sizeof(*mmie) || - !is_multicast_ether_addr(hdr->da)) + if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da)) return -1; if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *) hdr)) @@ -497,9 +591,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) return le16_to_cpu(mmie->key_id); } - -static ieee80211_rx_result -ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) +static ieee80211_rx_result ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; char *dev_addr = rx->sdata->vif.addr; @@ -507,7 +599,7 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) if (ieee80211_is_data(hdr->frame_control)) { if (is_multicast_ether_addr(hdr->addr1)) { if (ieee80211_has_tods(hdr->frame_control) || - !ieee80211_has_fromds(hdr->frame_control)) + !ieee80211_has_fromds(hdr->frame_control)) return RX_DROP_MONITOR; if (ether_addr_equal(hdr->addr3, dev_addr)) return RX_DROP_MONITOR; @@ -531,10 +623,15 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) if (ieee80211_is_action(hdr->frame_control)) { u8 category; + + /* make sure category field is present */ + if (rx->skb->len < IEEE80211_MIN_ACTION_SIZE) + return RX_DROP_MONITOR; + mgmt = (struct ieee80211_mgmt *)hdr; category = mgmt->u.action.category; if (category != WLAN_CATEGORY_MESH_ACTION && - category != WLAN_CATEGORY_SELF_PROTECTED) + category != WLAN_CATEGORY_SELF_PROTECTED) return RX_DROP_MONITOR; return RX_CONTINUE; } @@ -546,7 +643,6 @@ ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) return RX_CONTINUE; return RX_DROP_MONITOR; - } return RX_CONTINUE; @@ -570,7 +666,6 @@ static inline u16 seq_sub(u16 sq1, u16 sq2) return (sq1 - sq2) & SEQ_MASK; } - static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_rx *tid_agg_rx, int index) @@ -883,14 +978,16 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) */ if (rx->sta && rx->sdata->vif.type == NL80211_IFTYPE_STATION && ieee80211_is_data_present(hdr->frame_control)) { - u16 ethertype; - u8 *payload; - - payload = rx->skb->data + - ieee80211_hdrlen(hdr->frame_control); - ethertype = (payload[6] << 8) | payload[7]; - if (cpu_to_be16(ethertype) == - rx->sdata->control_port_protocol) + unsigned int hdrlen; + __be16 ethertype; + + hdrlen = ieee80211_hdrlen(hdr->frame_control); + + if (rx->skb->len < hdrlen + 8) + return RX_DROP_MONITOR; + + skb_copy_bits(rx->skb, hdrlen + 6, ðertype, 2); + if (ethertype == rx->sdata->control_port_protocol) return RX_CONTINUE; } @@ -1141,12 +1238,19 @@ ieee80211_rx_h_check_more_data(struct ieee80211_rx_data *rx) return RX_CONTINUE; } -static void ap_sta_ps_start(struct sta_info *sta) +static void sta_ps_start(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; + struct ps_data *ps; + + if (sta->sdata->vif.type == NL80211_IFTYPE_AP || + sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + ps = &sdata->bss->ps; + else + return; - atomic_inc(&sdata->bss->num_sta_ps); + atomic_inc(&ps->num_sta_ps); set_sta_flag(sta, WLAN_STA_PS_STA); if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta); @@ -1154,7 +1258,7 @@ static void ap_sta_ps_start(struct sta_info *sta) sta->sta.addr, sta->sta.aid); } -static void ap_sta_ps_end(struct sta_info *sta) +static void sta_ps_end(struct sta_info *sta) { ps_dbg(sta->sdata, "STA %pM aid %d exits power save mode\n", sta->sta.addr, sta->sta.aid); @@ -1181,9 +1285,9 @@ int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start) return -EINVAL; if (start) - ap_sta_ps_start(sta_inf); + sta_ps_start(sta_inf); else - ap_sta_ps_end(sta_inf); + sta_ps_end(sta_inf); return 0; } @@ -1277,17 +1381,22 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) /* * Update last_rx only for IBSS packets which are for the current - * BSSID to avoid keeping the current IBSS network alive in cases - * where other STAs start using different BSSID. + * BSSID and for station already AUTHORIZED to avoid keeping the + * current IBSS network alive in cases where other STAs start + * using different BSSID. This will also give the station another + * chance to restart the authentication/authorization in case + * something went wrong the first time. */ if (rx->sdata->vif.type == NL80211_IFTYPE_ADHOC) { u8 *bssid = ieee80211_get_bssid(hdr, rx->skb->len, NL80211_IFTYPE_ADHOC); - if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid)) { + if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid) && + test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { sta->last_rx = jiffies; if (ieee80211_is_data(hdr->frame_control)) { sta->last_rx_rate_idx = status->rate_idx; sta->last_rx_rate_flag = status->flag; + sta->last_rx_rate_vht_nss = status->vht_nss; } } } else if (!is_multicast_ether_addr(hdr->addr1)) { @@ -1299,6 +1408,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) if (ieee80211_is_data(hdr->frame_control)) { sta->last_rx_rate_idx = status->rate_idx; sta->last_rx_rate_flag = status->flag; + sta->last_rx_rate_vht_nss = status->vht_nss; } } @@ -1335,10 +1445,10 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) */ if (ieee80211_is_data(hdr->frame_control) && !ieee80211_has_pm(hdr->frame_control)) - ap_sta_ps_end(sta); + sta_ps_end(sta); } else { if (ieee80211_has_pm(hdr->frame_control)) - ap_sta_ps_start(sta); + sta_ps_start(sta); } } @@ -1384,9 +1494,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, struct sk_buff **skb) { struct ieee80211_fragment_entry *entry; - int idx; - idx = sdata->fragment_next; entry = &sdata->fragments[sdata->fragment_next++]; if (sdata->fragment_next >= IEEE80211_FRAGMENT_MAX) sdata->fragment_next = 0; @@ -1462,11 +1570,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; + + if (ieee80211_is_ctl(fc)) + return RX_CONTINUE; + sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; if (likely((!ieee80211_has_morefrags(fc) && frag == 0) || - (rx->skb)->len < 24 || is_multicast_ether_addr(hdr->addr1))) { /* not fragmented */ goto out; @@ -1570,18 +1681,15 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) return RX_CONTINUE; } -static int -ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) +static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) { - if (unlikely(!rx->sta || - !test_sta_flag(rx->sta, WLAN_STA_AUTHORIZED))) + if (unlikely(!rx->sta || !test_sta_flag(rx->sta, WLAN_STA_AUTHORIZED))) return -EACCES; return 0; } -static int -ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) +static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) { struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); @@ -1603,8 +1711,7 @@ ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) return 0; } -static int -ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) +static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); @@ -1889,6 +1996,20 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); + + /* make sure fixed part of mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, hdrlen + 6)) + return RX_DROP_MONITOR; + + mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + + /* make sure full mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, + hdrlen + ieee80211_get_mesh_hdrlen(mesh_hdr))) + return RX_DROP_MONITOR; + + /* reload pointers */ + hdr = (struct ieee80211_hdr *) skb->data; mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); /* frame is in RMC, don't forward */ @@ -1897,7 +2018,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) mesh_rmc_check(hdr->addr3, mesh_hdr, rx->sdata)) return RX_DROP_MONITOR; - if (!ieee80211_is_data(hdr->frame_control)) + if (!ieee80211_is_data(hdr->frame_control) || + !(status->rx_flags & IEEE80211_RX_RA_MATCH)) return RX_CONTINUE; if (!mesh_hdr->ttl) @@ -1911,9 +2033,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (is_multicast_ether_addr(hdr->addr1)) { mpp_addr = hdr->addr3; proxied_addr = mesh_hdr->eaddr1; - } else { + } else if (mesh_hdr->flags & MESH_FLAGS_AE_A5_A6) { + /* has_a4 already checked in ieee80211_rx_mesh_check */ mpp_addr = hdr->addr4; proxied_addr = mesh_hdr->eaddr2; + } else { + return RX_DROP_MONITOR; } rcu_read_lock(); @@ -1941,12 +2066,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) } skb_set_queue_mapping(skb, q); - if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) - goto out; - if (!--mesh_hdr->ttl) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); - return RX_DROP_MONITOR; + goto out; } if (!ifmsh->mshcfg.dot11MeshForwarding) @@ -1973,7 +2095,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) } else { /* unable to resolve next hop */ mesh_path_error_tx(ifmsh->mshcfg.element_ttl, fwd_hdr->addr3, - 0, reason, fwd_hdr->addr2, sdata); + 0, reason, fwd_hdr->addr2, sdata); IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_no_route); kfree_skb(fwd_skb); return RX_DROP_MONITOR; @@ -2182,7 +2304,7 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx) cfg80211_report_obss_beacon(rx->local->hw.wiphy, rx->skb->data, rx->skb->len, - status->freq, sig, GFP_ATOMIC); + status->freq, sig); rx->flags |= IEEE80211_RX_BEACON_REPORTED; } @@ -2211,7 +2333,8 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) if (len < IEEE80211_MIN_ACTION_SIZE) return RX_DROP_UNUSABLE; - if (!rx->sta && mgmt->u.action.category != WLAN_CATEGORY_PUBLIC) + if (!rx->sta && mgmt->u.action.category != WLAN_CATEGORY_PUBLIC && + mgmt->u.action.category != WLAN_CATEGORY_SELF_PROTECTED) return RX_DROP_UNUSABLE; if (!(status->rx_flags & IEEE80211_RX_RA_MATCH)) @@ -2353,6 +2476,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) } break; case WLAN_CATEGORY_SELF_PROTECTED: + if (len < (IEEE80211_MIN_ACTION_SIZE + + sizeof(mgmt->u.action.u.self_prot.action_code))) + break; + switch (mgmt->u.action.u.self_prot.action_code) { case WLAN_SP_MESH_PEERING_OPEN: case WLAN_SP_MESH_PEERING_CLOSE: @@ -2371,10 +2498,14 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) } break; case WLAN_CATEGORY_MESH_ACTION: + if (len < (IEEE80211_MIN_ACTION_SIZE + + sizeof(mgmt->u.action.u.mesh_action.action_code))) + break; + if (!ieee80211_vif_is_mesh(&sdata->vif)) break; if (mesh_action_is_path_sel(mgmt) && - (!mesh_path_sel_is_hwmp(sdata))) + !mesh_path_sel_is_hwmp(sdata)) break; goto queue; } @@ -2430,7 +2561,6 @@ ieee80211_rx_h_userspace_mgmt(struct ieee80211_rx_data *rx) return RX_QUEUED; } - return RX_CONTINUE; } @@ -2560,7 +2690,7 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, goto out_free_skb; /* room for the radiotap header based on driver features */ - needed_headroom = ieee80211_rx_radiotap_len(local, status); + needed_headroom = ieee80211_rx_radiotap_space(local, status); if (skb_headroom(skb) < needed_headroom && pskb_expand_head(skb, needed_headroom, 0, GFP_ATOMIC)) @@ -2623,7 +2753,8 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx, status = IEEE80211_SKB_RXCB((rx->skb)); sband = rx->local->hw.wiphy->bands[status->band]; - if (!(status->flag & RX_FLAG_HT)) + if (!(status->flag & RX_FLAG_HT) && + !(status->flag & RX_FLAG_VHT)) rate = &sband->bitrates[status->rate_idx]; ieee80211_rx_cooked_monitor(rx, rate); @@ -2790,8 +2921,8 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } else if (!rx->sta) { int rate_idx; - if (status->flag & RX_FLAG_HT) - rate_idx = 0; /* TODO: HT rates */ + if (status->flag & (RX_FLAG_HT | RX_FLAG_VHT)) + rate_idx = 0; /* TODO: HT/VHT rates */ else rate_idx = status->rate_idx; ieee80211_ibss_rx_no_sta(sdata, bssid, hdr->addr2, @@ -2913,10 +3044,15 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) local->dot11ReceivedFragmentCount++; - if (ieee80211_is_mgmt(fc)) - err = skb_linearize(skb); - else + if (ieee80211_is_mgmt(fc)) { + /* drop frame if too short for header */ + if (skb->len < ieee80211_hdrlen(fc)) + err = -ENOBUFS; + else + err = skb_linearize(skb); + } else { err = !pskb_may_pull(skb, ieee80211_hdrlen(fc)); + } if (err) { dev_kfree_skb(skb); @@ -3010,8 +3146,7 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) WARN_ON_ONCE(softirq_count() == 0); - if (WARN_ON(status->band < 0 || - status->band >= IEEE80211_NUM_BANDS)) + if (WARN_ON(status->band >= IEEE80211_NUM_BANDS)) goto drop; sband = local->hw.wiphy->bands[status->band]; @@ -3056,17 +3191,22 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) * hardware error. The driver should catch hardware * errors. */ - if (WARN((status->rate_idx < 0 || - status->rate_idx > 76), + if (WARN(status->rate_idx > 76, "Rate marked as an HT rate but passed " "status->rate_idx is not " "an MCS index [0-76]: %d (0x%02x)\n", status->rate_idx, status->rate_idx)) goto drop; + } else if (status->flag & RX_FLAG_VHT) { + if (WARN_ONCE(status->rate_idx > 9 || + !status->vht_nss || + status->vht_nss > 8, + "Rate marked as a VHT rate but data is invalid: MCS: %d, NSS: %d\n", + status->rate_idx, status->vht_nss)) + goto drop; } else { - if (WARN_ON(status->rate_idx < 0 || - status->rate_idx >= sband->n_bitrates)) + if (WARN_ON(status->rate_idx >= sband->n_bitrates)) goto drop; rate = &sband->bitrates[status->rate_idx]; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index c4cdbde24fd3..bf82e69d0601 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -113,18 +113,6 @@ ieee80211_bss_info_update(struct ieee80211_local *local, bss->valid_data |= IEEE80211_BSS_VALID_ERP; } - if (elems->tim && (!elems->parse_error || - !(bss->valid_data & IEEE80211_BSS_VALID_DTIM))) { - struct ieee80211_tim_ie *tim_ie = elems->tim; - bss->dtim_period = tim_ie->dtim_period; - if (!elems->parse_error) - bss->valid_data |= IEEE80211_BSS_VALID_DTIM; - } - - /* If the beacon had no TIM IE, or it was invalid, use 1 */ - if (beacon && !bss->dtim_period) - bss->dtim_period = 1; - /* replace old supported rates if we get new values */ if (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_RATES)) { @@ -174,7 +162,6 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) u8 *elements; struct ieee80211_channel *channel; size_t baselen; - int freq; bool beacon; struct ieee802_11_elems elems; @@ -209,13 +196,7 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) ieee802_11_parse_elems(elements, skb->len - baselen, &elems); - if (elems.ds_params && elems.ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems.ds_params[0], - rx_status->band); - else - freq = rx_status->freq; - - channel = ieee80211_get_channel(local->hw.wiphy, freq); + channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq); if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) return; @@ -254,6 +235,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) local->hw_scan_req->n_channels = n_chans; ielen = ieee80211_build_preq_ies(local, (u8 *)local->hw_scan_req->ie, + local->hw_scan_ies_bufsize, req->ie, req->ie_len, band, req->rates[band], 0); local->hw_scan_req->ie_len = ielen; @@ -310,7 +292,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, if (!was_hw_scan) { ieee80211_configure_filter(local); drv_sw_scan_complete(local); - ieee80211_offchannel_return(local, true); + ieee80211_offchannel_return(local); } ieee80211_recalc_idle(local); @@ -336,6 +318,10 @@ EXPORT_SYMBOL(ieee80211_scan_completed); static int ieee80211_start_sw_scan(struct ieee80211_local *local) { + /* Software scan is not supported in multi-channel cases */ + if (local->use_chanctx) + return -EOPNOTSUPP; + /* * Hardware/driver doesn't support hw_scan, so use software * scanning instead. First send a nullfunc frame with power save @@ -355,7 +341,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; - ieee80211_offchannel_stop_vifs(local, true); + ieee80211_offchannel_stop_vifs(local); ieee80211_configure_filter(local); @@ -417,7 +403,7 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, local->scan_req->ie, local->scan_req->ie_len, local->scan_req->rates[band], false, local->scan_req->no_cck, - local->hw.conf.channel); + local->hw.conf.channel, true); /* * After sending probe requests, wait for probe responses @@ -448,11 +434,13 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (local->ops->hw_scan) { u8 *ies; + local->hw_scan_ies_bufsize = 2 + IEEE80211_MAX_SSID_LEN + + local->scan_ies_len + + req->ie_len; local->hw_scan_req = kmalloc( sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]) + - 2 + IEEE80211_MAX_SSID_LEN + local->scan_ies_len + - req->ie_len, GFP_KERNEL); + local->hw_scan_ies_bufsize, GFP_KERNEL); if (!local->hw_scan_req) return -ENOMEM; @@ -462,6 +450,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]); local->hw_scan_req->ie = ies; + local->hw_scan_req->flags = req->flags; local->hw_scan_band = 0; @@ -480,7 +469,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (local->ops->hw_scan) { __set_bit(SCAN_HW_SCANNING, &local->scanning); } else if ((req->n_channels == 1) && - (req->channels[0] == local->oper_channel)) { + (req->channels[0] == local->_oper_channel)) { /* * If we are scanning only on the operating channel * then we do not need to stop normal activities @@ -562,6 +551,7 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local, unsigned long min_beacon_int = 0; struct ieee80211_sub_if_data *sdata; struct ieee80211_channel *next_chan; + enum mac80211_scan_state next_scan_state; /* * check if at least one STA interface is associated, @@ -620,10 +610,18 @@ static void ieee80211_scan_state_decision(struct ieee80211_local *local, usecs_to_jiffies(min_beacon_int * 1024) * local->hw.conf.listen_interval); - if (associated && (!tx_empty || bad_latency || listen_int_exceeded)) - local->next_scan_state = SCAN_SUSPEND; - else - local->next_scan_state = SCAN_SET_CHANNEL; + if (associated && !tx_empty) { + if (local->scan_req->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) + next_scan_state = SCAN_ABORT; + else + next_scan_state = SCAN_SUSPEND; + } else if (associated && (bad_latency || listen_int_exceeded)) { + next_scan_state = SCAN_SUSPEND; + } else { + next_scan_state = SCAN_SET_CHANNEL; + } + + local->next_scan_state = next_scan_state; *next_delay = 0; } @@ -680,12 +678,8 @@ static void ieee80211_scan_state_suspend(struct ieee80211_local *local, local->scan_channel = NULL; ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - /* - * Re-enable vifs and beaconing. Leave PS - * in off-channel state..will put that back - * on-channel at the end of scanning. - */ - ieee80211_offchannel_return(local, false); + /* disable PS */ + ieee80211_offchannel_return(local); *next_delay = HZ / 5; /* afterwards, resume scan & go to next channel */ @@ -695,8 +689,7 @@ static void ieee80211_scan_state_suspend(struct ieee80211_local *local, static void ieee80211_scan_state_resume(struct ieee80211_local *local, unsigned long *next_delay) { - /* PS already is in off-channel mode */ - ieee80211_offchannel_stop_vifs(local, false); + ieee80211_offchannel_stop_vifs(local); if (local->ops->flush) { drv_flush(local, false); @@ -794,6 +787,9 @@ void ieee80211_scan_work(struct work_struct *work) case SCAN_RESUME: ieee80211_scan_state_resume(local, &next_delay); break; + case SCAN_ABORT: + aborted = true; + goto out_complete; } } while (next_delay == 0); @@ -819,9 +815,9 @@ int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, return res; } -int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, - const u8 *ssid, u8 ssid_len, - struct ieee80211_channel *chan) +int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, + const u8 *ssid, u8 ssid_len, + struct ieee80211_channel *chan) { struct ieee80211_local *local = sdata->local; int ret = -EBUSY; @@ -835,22 +831,36 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, /* fill internal scan request */ if (!chan) { - int i, nchan = 0; + int i, max_n; + int n_ch = 0; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (!local->hw.wiphy->bands[band]) continue; - for (i = 0; - i < local->hw.wiphy->bands[band]->n_channels; - i++) { - local->int_scan_req->channels[nchan] = + + max_n = local->hw.wiphy->bands[band]->n_channels; + for (i = 0; i < max_n; i++) { + struct ieee80211_channel *tmp_ch = &local->hw.wiphy->bands[band]->channels[i]; - nchan++; + + if (tmp_ch->flags & (IEEE80211_CHAN_NO_IBSS | + IEEE80211_CHAN_DISABLED)) + continue; + + local->int_scan_req->channels[n_ch] = tmp_ch; + n_ch++; } } - local->int_scan_req->n_channels = nchan; + if (WARN_ON_ONCE(n_ch == 0)) + goto unlock; + + local->int_scan_req->n_channels = n_ch; } else { + if (WARN_ON_ONCE(chan->flags & (IEEE80211_CHAN_NO_IBSS | + IEEE80211_CHAN_DISABLED))) + goto unlock; + local->int_scan_req->channels[0] = chan; local->int_scan_req->n_channels = 1; } @@ -917,8 +927,11 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; - struct ieee80211_sched_scan_ies sched_scan_ies; - int ret, i; + struct ieee80211_sched_scan_ies sched_scan_ies = {}; + int ret, i, iebufsz; + + iebufsz = 2 + IEEE80211_MAX_SSID_LEN + + local->scan_ies_len + req->ie_len; mutex_lock(&local->mtx); @@ -936,10 +949,7 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, if (!local->hw.wiphy->bands[i]) continue; - sched_scan_ies.ie[i] = kzalloc(2 + IEEE80211_MAX_SSID_LEN + - local->scan_ies_len + - req->ie_len, - GFP_KERNEL); + sched_scan_ies.ie[i] = kzalloc(iebufsz, GFP_KERNEL); if (!sched_scan_ies.ie[i]) { ret = -ENOMEM; goto out_free; @@ -947,8 +957,8 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, sched_scan_ies.len[i] = ieee80211_build_preq_ies(local, sched_scan_ies.ie[i], - req->ie, req->ie_len, i, - (u32) -1, 0); + iebufsz, req->ie, req->ie_len, + i, (u32) -1, 0); } ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 0a4e4c04db89..ca9fde198188 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -91,13 +91,13 @@ static int sta_info_hash_del(struct ieee80211_local *local, return -ENOENT; } -static void free_sta_work(struct work_struct *wk) +static void cleanup_single_sta(struct sta_info *sta) { - struct sta_info *sta = container_of(wk, struct sta_info, free_sta_wk); int ac, i; struct tid_ampdu_tx *tid_tx; struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; + struct ps_data *ps; /* * At this point, when being called as call_rcu callback, @@ -107,18 +107,22 @@ static void free_sta_work(struct work_struct *wk) */ if (test_sta_flag(sta, WLAN_STA_PS_STA)) { - BUG_ON(!sdata->bss); + if (sta->sdata->vif.type == NL80211_IFTYPE_AP || + sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + ps = &sdata->bss->ps; + else + return; clear_sta_flag(sta, WLAN_STA_PS_STA); - atomic_dec(&sdata->bss->num_sta_ps); + atomic_dec(&ps->num_sta_ps); sta_info_recalc_tim(sta); } for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { local->total_ps_buffered -= skb_queue_len(&sta->ps_tx_buf[ac]); - __skb_queue_purge(&sta->ps_tx_buf[ac]); - __skb_queue_purge(&sta->tx_filtered[ac]); + ieee80211_purge_tx_queue(&local->hw, &sta->ps_tx_buf[ac]); + ieee80211_purge_tx_queue(&local->hw, &sta->tx_filtered[ac]); } #ifdef CONFIG_MAC80211_MESH @@ -137,22 +141,46 @@ static void free_sta_work(struct work_struct *wk) * drivers have to handle aggregation stop being requested, followed * directly by station destruction. */ - for (i = 0; i < STA_TID_NUM; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { tid_tx = rcu_dereference_raw(sta->ampdu_mlme.tid_tx[i]); if (!tid_tx) continue; - __skb_queue_purge(&tid_tx->pending); + ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending); kfree(tid_tx); } sta_info_free(local, sta); } +void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata) +{ + struct sta_info *sta; + + spin_lock_bh(&sdata->cleanup_stations_lock); + while (!list_empty(&sdata->cleanup_stations)) { + sta = list_first_entry(&sdata->cleanup_stations, + struct sta_info, list); + list_del(&sta->list); + spin_unlock_bh(&sdata->cleanup_stations_lock); + + cleanup_single_sta(sta); + + spin_lock_bh(&sdata->cleanup_stations_lock); + } + + spin_unlock_bh(&sdata->cleanup_stations_lock); +} + static void free_sta_rcu(struct rcu_head *h) { struct sta_info *sta = container_of(h, struct sta_info, rcu_head); + struct ieee80211_sub_if_data *sdata = sta->sdata; - ieee80211_queue_work(&sta->local->hw, &sta->free_sta_wk); + spin_lock(&sdata->cleanup_stations_lock); + list_add_tail(&sta->list, &sdata->cleanup_stations); + spin_unlock(&sdata->cleanup_stations_lock); + + ieee80211_queue_work(&sdata->local->hw, &sdata->cleanup_stations_wk); } /* protected by RCU */ @@ -305,7 +333,6 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, spin_lock_init(&sta->lock); INIT_WORK(&sta->drv_unblock_wk, sta_unblock); - INIT_WORK(&sta->free_sta_wk, free_sta_work); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); @@ -325,7 +352,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, return NULL; } - for (i = 0; i < STA_TID_NUM; i++) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { /* * timer_to_tid must be initialized with identity mapping * to enable session_timer's data differentiation. See @@ -338,7 +365,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, skb_queue_head_init(&sta->tx_filtered[i]); } - for (i = 0; i < NUM_RX_DATA_QUEUES; i++) + for (i = 0; i < IEEE80211_NUM_TIDS; i++) sta->last_seq_ctrl[i] = cpu_to_le16(USHRT_MAX); sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); @@ -502,22 +529,22 @@ int sta_info_insert(struct sta_info *sta) return err; } -static inline void __bss_tim_set(struct ieee80211_if_ap *bss, u16 aid) +static inline void __bss_tim_set(u8 *tim, u16 id) { /* * This format has been mandated by the IEEE specifications, * so this line may not be changed to use the __set_bit() format. */ - bss->tim[aid / 8] |= (1 << (aid % 8)); + tim[id / 8] |= (1 << (id % 8)); } -static inline void __bss_tim_clear(struct ieee80211_if_ap *bss, u16 aid) +static inline void __bss_tim_clear(u8 *tim, u16 id) { /* * This format has been mandated by the IEEE specifications, * so this line may not be changed to use the __clear_bit() format. */ - bss->tim[aid / 8] &= ~(1 << (aid % 8)); + tim[id / 8] &= ~(1 << (id % 8)); } static unsigned long ieee80211_tids_for_ac(int ac) @@ -541,14 +568,23 @@ static unsigned long ieee80211_tids_for_ac(int ac) void sta_info_recalc_tim(struct sta_info *sta) { struct ieee80211_local *local = sta->local; - struct ieee80211_if_ap *bss = sta->sdata->bss; + struct ps_data *ps; unsigned long flags; bool indicate_tim = false; u8 ignore_for_tim = sta->sta.uapsd_queues; int ac; + u16 id; + + if (sta->sdata->vif.type == NL80211_IFTYPE_AP || + sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + if (WARN_ON_ONCE(!sta->sdata->bss)) + return; - if (WARN_ON_ONCE(!sta->sdata->bss)) + ps = &sta->sdata->bss->ps; + id = sta->sta.aid; + } else { return; + } /* No need to do anything if the driver does all */ if (local->hw.flags & IEEE80211_HW_AP_LINK_PS) @@ -587,9 +623,9 @@ void sta_info_recalc_tim(struct sta_info *sta) spin_lock_irqsave(&local->tim_lock, flags); if (indicate_tim) - __bss_tim_set(bss, sta->sta.aid); + __bss_tim_set(ps->tim, id); else - __bss_tim_clear(bss, sta->sta.aid); + __bss_tim_clear(ps->tim, id); if (local->ops->set_tim) { local->tim_in_locked_section = true; @@ -848,7 +884,7 @@ void sta_info_init(struct ieee80211_local *local) void sta_info_stop(struct ieee80211_local *local) { - del_timer(&local->sta_cleanup); + del_timer_sync(&local->sta_cleanup); sta_info_flush(local, NULL); } @@ -877,6 +913,20 @@ int sta_info_flush(struct ieee80211_local *local, } mutex_unlock(&local->sta_mtx); + rcu_barrier(); + + if (sdata) { + ieee80211_cleanup_sdata_stas(sdata); + cancel_work_sync(&sdata->cleanup_stations_wk); + } else { + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + ieee80211_cleanup_sdata_stas(sdata); + cancel_work_sync(&sdata->cleanup_stations_wk); + } + mutex_unlock(&local->iflist_mtx); + } + return ret; } @@ -893,8 +943,8 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, continue; if (time_after(jiffies, sta->last_rx + exp_time)) { - ibss_dbg(sdata, "expiring inactive STA %pM\n", - sta->sta.addr); + sta_dbg(sta->sdata, "expiring inactive STA %pM\n", + sta->sta.addr); WARN_ON(__sta_info_destroy(sta)); } } @@ -948,10 +998,17 @@ static void clear_sta_ps_flags(void *_sta) { struct sta_info *sta = _sta; struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ps_data *ps; + + if (sdata->vif.type == NL80211_IFTYPE_AP || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + ps = &sdata->bss->ps; + else + return; clear_sta_flag(sta, WLAN_STA_PS_DRIVER); if (test_and_clear_sta_flag(sta, WLAN_STA_PS_STA)) - atomic_dec(&sdata->bss->num_sta_ps); + atomic_dec(&ps->num_sta_ps); } /* powersave support code */ @@ -961,10 +1018,11 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) struct ieee80211_local *local = sdata->local; struct sk_buff_head pending; int filtered = 0, buffered = 0, ac; + unsigned long flags; clear_sta_flag(sta, WLAN_STA_SP); - BUILD_BUG_ON(BITS_TO_LONGS(STA_TID_NUM) > 1); + BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1); sta->driver_buffered_tids = 0; if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) @@ -976,12 +1034,16 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; + spin_lock_irqsave(&sta->tx_filtered[ac].lock, flags); skb_queue_splice_tail_init(&sta->tx_filtered[ac], &pending); + spin_unlock_irqrestore(&sta->tx_filtered[ac].lock, flags); tmp = skb_queue_len(&pending); filtered += tmp - count; count = tmp; + spin_lock_irqsave(&sta->ps_tx_buf[ac].lock, flags); skb_queue_splice_tail_init(&sta->ps_tx_buf[ac], &pending); + spin_unlock_irqrestore(&sta->ps_tx_buf[ac].lock, flags); tmp = skb_queue_len(&pending); buffered += tmp - count; } @@ -1008,6 +1070,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, __le16 fc; bool qos = test_sta_flag(sta, WLAN_STA_WME); struct ieee80211_tx_info *info; + struct ieee80211_chanctx_conf *chanctx_conf; if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | @@ -1057,7 +1120,16 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, drv_allow_buffered_frames(local, sta, BIT(tid), 1, reason, false); - ieee80211_xmit(sdata, skb); + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + kfree_skb(skb); + return; + } + + ieee80211_xmit(sdata, skb, chanctx_conf->def.chan->band); + rcu_read_unlock(); } static void @@ -1338,7 +1410,7 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); - if (WARN_ON(tid >= STA_TID_NUM)) + if (WARN_ON(tid >= IEEE80211_NUM_TIDS)) return; if (buffered) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index c88f161f8118..37c1889afd3a 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -80,7 +80,6 @@ enum ieee80211_sta_info_flags { WLAN_STA_TOFFSET_KNOWN, }; -#define STA_TID_NUM 16 #define ADDBA_RESP_INTERVAL HZ #define HT_AGG_MAX_RETRIES 15 #define HT_AGG_BURST_RETRIES 3 @@ -197,15 +196,15 @@ struct tid_ampdu_rx { struct sta_ampdu_mlme { struct mutex mtx; /* rx */ - struct tid_ampdu_rx __rcu *tid_rx[STA_TID_NUM]; - unsigned long tid_rx_timer_expired[BITS_TO_LONGS(STA_TID_NUM)]; - unsigned long tid_rx_stop_requested[BITS_TO_LONGS(STA_TID_NUM)]; + struct tid_ampdu_rx __rcu *tid_rx[IEEE80211_NUM_TIDS]; + unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; + unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; /* tx */ struct work_struct work; - struct tid_ampdu_tx __rcu *tid_tx[STA_TID_NUM]; - struct tid_ampdu_tx *tid_start_tx[STA_TID_NUM]; - unsigned long last_addba_req_time[STA_TID_NUM]; - u8 addba_req_num[STA_TID_NUM]; + struct tid_ampdu_tx __rcu *tid_tx[IEEE80211_NUM_TIDS]; + struct tid_ampdu_tx *tid_start_tx[IEEE80211_NUM_TIDS]; + unsigned long last_addba_req_time[IEEE80211_NUM_TIDS]; + u8 addba_req_num[IEEE80211_NUM_TIDS]; u8 dialog_token_allocator; }; @@ -228,6 +227,7 @@ struct sta_ampdu_mlme { * "the" transmit rate * @last_rx_rate_idx: rx status rate index of the last data packet * @last_rx_rate_flag: rx status flag of the last data packet + * @last_rx_rate_vht_nss: rx status nss of last data packet * @lock: used for locking all fields that require locking, see comments * in the header file. * @drv_unblock_wk: used for driver PS unblocking @@ -250,6 +250,7 @@ struct sta_ampdu_mlme { * @rx_dropped: number of dropped MPDUs from this STA * @last_signal: signal of last received frame from this STA * @avg_signal: moving average of signal of received frames from this STA + * @last_ack_signal: signal of last received Ack frame from this STA * @last_seq_ctrl: last received seq/frag number from this STA (per RX queue) * @tx_filtered_count: number of frames the hardware filtered for this STA * @tx_retry_failed: number of frames that failed retry @@ -273,7 +274,7 @@ struct sta_ampdu_mlme { * @t_offset: timing offset relative to this host * @t_offset_setpoint: reference timing offset of this sta to be used when * calculating clockdrift - * @ch_type: peer's channel type + * @ch_width: peer's channel width * @debugfs: debug filesystem info * @dead: set to true when sta is unlinked * @uploaded: set to true when sta is uploaded to the driver @@ -298,7 +299,6 @@ struct sta_info { spinlock_t lock; struct work_struct drv_unblock_wk; - struct work_struct free_sta_wk; u16 listen_interval; @@ -329,8 +329,9 @@ struct sta_info { unsigned long rx_dropped; int last_signal; struct ewma avg_signal; + int last_ack_signal; /* Plus 1 for non-QoS frames */ - __le16 last_seq_ctrl[NUM_RX_DATA_QUEUES + 1]; + __le16 last_seq_ctrl[IEEE80211_NUM_TIDS + 1]; /* Updated from TX status path only, no locking requirements */ unsigned long tx_filtered_count; @@ -344,14 +345,15 @@ struct sta_info { unsigned long tx_fragments; struct ieee80211_tx_rate last_tx_rate; int last_rx_rate_idx; - int last_rx_rate_flag; + u32 last_rx_rate_flag; + u8 last_rx_rate_vht_nss; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; /* * Aggregation information, locked with lock. */ struct sta_ampdu_mlme ampdu_mlme; - u8 timer_to_tid[STA_TID_NUM]; + u8 timer_to_tid[IEEE80211_NUM_TIDS]; #ifdef CONFIG_MAC80211_MESH /* @@ -369,7 +371,7 @@ struct sta_info { struct timer_list plink_timer; s64 t_offset; s64 t_offset_setpoint; - enum nl80211_channel_type ch_type; + enum nl80211_chan_width ch_width; #endif #ifdef CONFIG_MAC80211_DEBUGFS @@ -551,6 +553,8 @@ int sta_info_flush(struct ieee80211_local *local, void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo); +void sta_set_rate_info_rx(struct sta_info *sta, + struct rate_info *rinfo); void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time); @@ -558,4 +562,6 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta); void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta); void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta); +void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata); + #endif /* STA_INFO_H */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 3af0cc4130f1..07d99578a2b1 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -189,30 +189,31 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) } if (ieee80211_is_action(mgmt->frame_control) && - sdata->vif.type == NL80211_IFTYPE_STATION && mgmt->u.action.category == WLAN_CATEGORY_HT && - mgmt->u.action.u.ht_smps.action == WLAN_HT_ACTION_SMPS) { + mgmt->u.action.u.ht_smps.action == WLAN_HT_ACTION_SMPS && + sdata->vif.type == NL80211_IFTYPE_STATION && + ieee80211_sdata_running(sdata)) { /* * This update looks racy, but isn't -- if we come * here we've definitely got a station that we're * talking to, and on a managed interface that can * only be the AP. And the only other place updating - * this variable is before we're associated. + * this variable in managed mode is before association. */ switch (mgmt->u.action.u.ht_smps.smps_control) { case WLAN_HT_SMPS_CONTROL_DYNAMIC: - sta->sdata->u.mgd.ap_smps = IEEE80211_SMPS_DYNAMIC; + sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; break; case WLAN_HT_SMPS_CONTROL_STATIC: - sta->sdata->u.mgd.ap_smps = IEEE80211_SMPS_STATIC; + sdata->smps_mode = IEEE80211_SMPS_STATIC; break; case WLAN_HT_SMPS_CONTROL_DISABLED: default: /* shouldn't happen since we don't send that */ - sta->sdata->u.mgd.ap_smps = IEEE80211_SMPS_OFF; + sdata->smps_mode = IEEE80211_SMPS_OFF; break; } - ieee80211_queue_work(&local->hw, &local->recalc_smps); + ieee80211_queue_work(&local->hw, &sdata->recalc_smps); } } @@ -324,6 +325,75 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band } +static void ieee80211_report_used_skb(struct ieee80211_local *local, + struct sk_buff *skb, bool dropped) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (void *)skb->data; + bool acked = info->flags & IEEE80211_TX_STAT_ACK; + + if (dropped) + acked = false; + + if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { + struct ieee80211_sub_if_data *sdata = NULL; + struct ieee80211_sub_if_data *iter_sdata; + u64 cookie = (unsigned long)skb; + + rcu_read_lock(); + + if (skb->dev) { + list_for_each_entry_rcu(iter_sdata, &local->interfaces, + list) { + if (!iter_sdata->dev) + continue; + + if (skb->dev == iter_sdata->dev) { + sdata = iter_sdata; + break; + } + } + } else { + sdata = rcu_dereference(local->p2p_sdata); + } + + if (!sdata) + skb->dev = NULL; + else if (ieee80211_is_nullfunc(hdr->frame_control) || + ieee80211_is_qos_nullfunc(hdr->frame_control)) { + cfg80211_probe_status(sdata->dev, hdr->addr1, + cookie, acked, GFP_ATOMIC); + } else { + cfg80211_mgmt_tx_status(&sdata->wdev, cookie, skb->data, + skb->len, acked, GFP_ATOMIC); + } + + rcu_read_unlock(); + } + + if (unlikely(info->ack_frame_id)) { + struct sk_buff *ack_skb; + unsigned long flags; + + spin_lock_irqsave(&local->ack_status_lock, flags); + ack_skb = idr_find(&local->ack_status_frames, + info->ack_frame_id); + if (ack_skb) + idr_remove(&local->ack_status_frames, + info->ack_frame_id); + spin_unlock_irqrestore(&local->ack_status_lock, flags); + + if (ack_skb) { + if (!dropped) { + /* consumes ack_skb */ + skb_complete_wifi_ack(ack_skb, acked); + } else { + dev_kfree_skb_any(ack_skb); + } + } + } +} + /* * Use a static threshold for now, best value to be determined * by testing ... @@ -432,7 +502,11 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) IEEE80211_BAR_CTRL_TID_INFO_MASK) >> IEEE80211_BAR_CTRL_TID_INFO_SHIFT; - ieee80211_set_bar_pending(sta, tid, ssn); + if (local->hw.flags & + IEEE80211_HW_TEARDOWN_AGGR_ON_BAR_FAIL) + ieee80211_stop_tx_ba_session(&sta->sta, tid); + else + ieee80211_set_bar_pending(sta, tid, ssn); } } @@ -469,6 +543,9 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) sta->lost_packets = 0; } } + + if (acked) + sta->last_ack_signal = info->status.ack_signal; } rcu_read_unlock(); @@ -515,62 +592,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) msecs_to_jiffies(10)); } - if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { - u64 cookie = (unsigned long)skb; - bool found = false; - - acked = info->flags & IEEE80211_TX_STAT_ACK; - - rcu_read_lock(); - - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - if (!sdata->dev) - continue; - - if (skb->dev != sdata->dev) - continue; - - found = true; - break; - } - - if (!skb->dev) { - sdata = rcu_dereference(local->p2p_sdata); - if (sdata) - found = true; - } - - if (!found) - skb->dev = NULL; - else if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) { - cfg80211_probe_status(sdata->dev, hdr->addr1, - cookie, acked, GFP_ATOMIC); - } else { - cfg80211_mgmt_tx_status(&sdata->wdev, cookie, skb->data, - skb->len, acked, GFP_ATOMIC); - } - - rcu_read_unlock(); - } - - if (unlikely(info->ack_frame_id)) { - struct sk_buff *ack_skb; - unsigned long flags; - - spin_lock_irqsave(&local->ack_status_lock, flags); - ack_skb = idr_find(&local->ack_status_frames, - info->ack_frame_id); - if (ack_skb) - idr_remove(&local->ack_status_frames, - info->ack_frame_id); - spin_unlock_irqrestore(&local->ack_status_lock, flags); - - /* consumes ack_skb */ - if (ack_skb) - skb_complete_wifi_ack(ack_skb, - info->flags & IEEE80211_TX_STAT_ACK); - } + ieee80211_report_used_skb(local, skb, false); /* this was a transmitted frame, but now we want to reuse it */ skb_orphan(skb); @@ -646,25 +668,17 @@ EXPORT_SYMBOL(ieee80211_report_low_ack); void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb) { struct ieee80211_local *local = hw_to_local(hw); - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - - if (unlikely(info->ack_frame_id)) { - struct sk_buff *ack_skb; - unsigned long flags; - - spin_lock_irqsave(&local->ack_status_lock, flags); - ack_skb = idr_find(&local->ack_status_frames, - info->ack_frame_id); - if (ack_skb) - idr_remove(&local->ack_status_frames, - info->ack_frame_id); - spin_unlock_irqrestore(&local->ack_status_lock, flags); - - /* consumes ack_skb */ - if (ack_skb) - dev_kfree_skb_any(ack_skb); - } + ieee80211_report_used_skb(local, skb, true); dev_kfree_skb_any(skb); } EXPORT_SYMBOL(ieee80211_free_txskb); + +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs) +{ + struct sk_buff *skb; + + while ((skb = __skb_dequeue(skbs))) + ieee80211_free_txskb(hw, skb); +} diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 18d9c8a52e9e..a8270b441a6f 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -28,6 +28,25 @@ #define VIF_PR_FMT " vif:%s(%d%s)" #define VIF_PR_ARG __get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : "" +#define CHANCTX_ENTRY __field(u32, control_freq) \ + __field(u32, chan_width) \ + __field(u32, center_freq1) \ + __field(u32, center_freq2) \ + __field(u8, rx_chains_static) \ + __field(u8, rx_chains_dynamic) +#define CHANCTX_ASSIGN __entry->control_freq = ctx->conf.def.chan->center_freq;\ + __entry->chan_width = ctx->conf.def.width; \ + __entry->center_freq1 = ctx->conf.def.center_freq1; \ + __entry->center_freq2 = ctx->conf.def.center_freq2; \ + __entry->rx_chains_static = ctx->conf.rx_chains_static; \ + __entry->rx_chains_dynamic = ctx->conf.rx_chains_dynamic +#define CHANCTX_PR_FMT " control:%d MHz width:%d center: %d/%d MHz chains:%d/%d" +#define CHANCTX_PR_ARG __entry->control_freq, __entry->chan_width, \ + __entry->center_freq1, __entry->center_freq2, \ + __entry->rx_chains_static, __entry->rx_chains_dynamic + + + /* * Tracing for driver callbacks. */ @@ -301,20 +320,37 @@ TRACE_EVENT(drv_bss_info_changed, TP_STRUCT__entry( LOCAL_ENTRY VIF_ENTRY + __field(u32, changed) __field(bool, assoc) + __field(bool, ibss_joined) + __field(bool, ibss_creator) __field(u16, aid) __field(bool, cts) __field(bool, shortpre) __field(bool, shortslot) + __field(bool, enable_beacon) __field(u8, dtimper) __field(u16, bcnint) __field(u16, assoc_cap) __field(u64, sync_tsf) __field(u32, sync_device_ts) __field(u32, basic_rates) - __field(u32, changed) - __field(bool, enable_beacon) + __array(int, mcast_rate, IEEE80211_NUM_BANDS) __field(u16, ht_operation_mode) + __field(s32, cqm_rssi_thold); + __field(s32, cqm_rssi_hyst); + __field(u32, channel_width); + __field(u32, channel_cfreq1); + __dynamic_array(u32, arp_addr_list, info->arp_addr_cnt); + __field(bool, arp_filter_enabled); + __field(bool, qos); + __field(bool, idle); + __field(bool, ps); + __dynamic_array(u8, ssid, info->ssid_len); + __field(bool, hidden_ssid); + __field(int, txpower) + __field(u8, p2p_ctwindow) + __field(bool, p2p_oppps) ), TP_fast_assign( @@ -323,17 +359,36 @@ TRACE_EVENT(drv_bss_info_changed, __entry->changed = changed; __entry->aid = info->aid; __entry->assoc = info->assoc; + __entry->ibss_joined = info->ibss_joined; + __entry->ibss_creator = info->ibss_creator; __entry->shortpre = info->use_short_preamble; __entry->cts = info->use_cts_prot; __entry->shortslot = info->use_short_slot; + __entry->enable_beacon = info->enable_beacon; __entry->dtimper = info->dtim_period; __entry->bcnint = info->beacon_int; __entry->assoc_cap = info->assoc_capability; __entry->sync_tsf = info->sync_tsf; __entry->sync_device_ts = info->sync_device_ts; __entry->basic_rates = info->basic_rates; - __entry->enable_beacon = info->enable_beacon; + memcpy(__entry->mcast_rate, info->mcast_rate, + sizeof(__entry->mcast_rate)); __entry->ht_operation_mode = info->ht_operation_mode; + __entry->cqm_rssi_thold = info->cqm_rssi_thold; + __entry->cqm_rssi_hyst = info->cqm_rssi_hyst; + __entry->channel_width = info->chandef.width; + __entry->channel_cfreq1 = info->chandef.center_freq1; + memcpy(__get_dynamic_array(arp_addr_list), info->arp_addr_list, + sizeof(u32) * info->arp_addr_cnt); + __entry->arp_filter_enabled = info->arp_filter_enabled; + __entry->qos = info->qos; + __entry->idle = info->idle; + __entry->ps = info->ps; + memcpy(__get_dynamic_array(ssid), info->ssid, info->ssid_len); + __entry->hidden_ssid = info->hidden_ssid; + __entry->txpower = info->txpower; + __entry->p2p_ctwindow = info->p2p_ctwindow; + __entry->p2p_oppps = info->p2p_oppps; ), TP_printk( @@ -971,28 +1026,31 @@ TRACE_EVENT(drv_get_antenna, ); TRACE_EVENT(drv_remain_on_channel, - TP_PROTO(struct ieee80211_local *local, struct ieee80211_channel *chan, - enum nl80211_channel_type chantype, unsigned int duration), + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel *chan, + unsigned int duration), - TP_ARGS(local, chan, chantype, duration), + TP_ARGS(local, sdata, chan, duration), TP_STRUCT__entry( LOCAL_ENTRY + VIF_ENTRY __field(int, center_freq) - __field(int, channel_type) __field(unsigned int, duration) ), TP_fast_assign( LOCAL_ASSIGN; + VIF_ASSIGN; __entry->center_freq = chan->center_freq; - __entry->channel_type = chantype; __entry->duration = duration; ), TP_printk( - LOCAL_PR_FMT " freq:%dMHz duration:%dms", - LOCAL_PR_ARG, __entry->center_freq, __entry->duration + LOCAL_PR_FMT VIF_PR_FMT " freq:%dMHz duration:%dms", + LOCAL_PR_ARG, VIF_PR_ARG, + __entry->center_freq, __entry->duration ) ); @@ -1001,34 +1059,6 @@ DEFINE_EVENT(local_only_evt, drv_cancel_remain_on_channel, TP_ARGS(local) ); -TRACE_EVENT(drv_offchannel_tx, - TP_PROTO(struct ieee80211_local *local, struct sk_buff *skb, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, - unsigned int wait), - - TP_ARGS(local, skb, chan, channel_type, wait), - - TP_STRUCT__entry( - LOCAL_ENTRY - __field(int, center_freq) - __field(int, channel_type) - __field(unsigned int, wait) - ), - - TP_fast_assign( - LOCAL_ASSIGN; - __entry->center_freq = chan->center_freq; - __entry->channel_type = channel_type; - __entry->wait = wait; - ), - - TP_printk( - LOCAL_PR_FMT " freq:%dMHz, wait:%dms", - LOCAL_PR_ARG, __entry->center_freq, __entry->wait - ) -); - TRACE_EVENT(drv_set_ringparam, TP_PROTO(struct ieee80211_local *local, u32 tx, u32 rx), @@ -1256,6 +1286,146 @@ DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx, TP_ARGS(local, sdata) ); +DECLARE_EVENT_CLASS(local_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx), + + TP_ARGS(local, ctx), + + TP_STRUCT__entry( + LOCAL_ENTRY + CHANCTX_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + CHANCTX_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT CHANCTX_PR_FMT, + LOCAL_PR_ARG, CHANCTX_PR_ARG + ) +); + +DEFINE_EVENT(local_chanctx, drv_add_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx), + TP_ARGS(local, ctx) +); + +DEFINE_EVENT(local_chanctx, drv_remove_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx), + TP_ARGS(local, ctx) +); + +TRACE_EVENT(drv_change_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + u32 changed), + + TP_ARGS(local, ctx, changed), + + TP_STRUCT__entry( + LOCAL_ENTRY + CHANCTX_ENTRY + __field(u32, changed) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + CHANCTX_ASSIGN; + __entry->changed = changed; + ), + + TP_printk( + LOCAL_PR_FMT CHANCTX_PR_FMT " changed:%#x", + LOCAL_PR_ARG, CHANCTX_PR_ARG, __entry->changed + ) +); + +DECLARE_EVENT_CLASS(local_sdata_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_chanctx *ctx), + + TP_ARGS(local, sdata, ctx), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + CHANCTX_ENTRY + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + CHANCTX_ASSIGN; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT CHANCTX_PR_FMT, + LOCAL_PR_ARG, VIF_PR_ARG, CHANCTX_PR_ARG + ) +); + +DEFINE_EVENT(local_sdata_chanctx, drv_assign_vif_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_chanctx *ctx), + TP_ARGS(local, sdata, ctx) +); + +DEFINE_EVENT(local_sdata_chanctx, drv_unassign_vif_chanctx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_chanctx *ctx), + TP_ARGS(local, sdata, ctx) +); + +TRACE_EVENT(drv_start_ap, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_bss_conf *info), + + TP_ARGS(local, sdata, info), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __field(u8, dtimper) + __field(u16, bcnint) + __dynamic_array(u8, ssid, info->ssid_len); + __field(bool, hidden_ssid); + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + __entry->dtimper = info->dtim_period; + __entry->bcnint = info->beacon_int; + memcpy(__get_dynamic_array(ssid), info->ssid, info->ssid_len); + __entry->hidden_ssid = info->hidden_ssid; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT, + LOCAL_PR_ARG, VIF_PR_ARG + ) +); + +DEFINE_EVENT(local_sdata_evt, drv_stop_ap, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + TP_ARGS(local, sdata) +); + +DEFINE_EVENT(local_only_evt, drv_restart_complete, + TP_PROTO(struct ieee80211_local *local), + TP_ARGS(local) +); + /* * Tracing for API calls that drivers call. */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index c9bf83f36657..467c1d1b66f2 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -324,22 +324,20 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) struct ieee80211_sub_if_data *sdata; struct sta_info *sta; - /* - * virtual interfaces are protected by RCU - */ - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - struct ieee80211_if_ap *ap; - if (sdata->vif.type != NL80211_IFTYPE_AP) + struct ps_data *ps; + + if (sdata->vif.type == NL80211_IFTYPE_AP) + ps = &sdata->u.ap.ps; + else continue; - ap = &sdata->u.ap; - skb = skb_dequeue(&ap->ps_bc_buf); + + skb = skb_dequeue(&ps->bc_buf); if (skb) { purged++; dev_kfree_skb(skb); } - total += skb_queue_len(&ap->ps_bc_buf); + total += skb_queue_len(&ps->bc_buf); } /* @@ -360,8 +358,6 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) } } - rcu_read_unlock(); - local->total_ps_buffered = total; ps_dbg_hw(&local->hw, "PS buffers full - purged %d frames\n", purged); } @@ -371,6 +367,7 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; + struct ps_data *ps; /* * broadcast/multicast frame @@ -380,16 +377,24 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) * This is done either by the hardware or us. */ - /* powersaving STAs only in AP/VLAN mode */ - if (!tx->sdata->bss) + /* powersaving STAs currently only in AP/VLAN mode */ + if (tx->sdata->vif.type == NL80211_IFTYPE_AP || + tx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + if (!tx->sdata->bss) + return TX_CONTINUE; + + ps = &tx->sdata->bss->ps; + } else { return TX_CONTINUE; + } + /* no buffering for ordered frames */ if (ieee80211_has_order(hdr->frame_control)) return TX_CONTINUE; /* no stations in PS mode */ - if (!atomic_read(&tx->sdata->bss->num_sta_ps)) + if (!atomic_read(&ps->num_sta_ps)) return TX_CONTINUE; info->flags |= IEEE80211_TX_CTL_SEND_AFTER_DTIM; @@ -404,14 +409,14 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) purge_old_ps_buffers(tx->local); - if (skb_queue_len(&tx->sdata->bss->ps_bc_buf) >= AP_MAX_BC_BUFFER) { + if (skb_queue_len(&ps->bc_buf) >= AP_MAX_BC_BUFFER) { ps_dbg(tx->sdata, "BC TX buffer full - dropping the oldest frame\n"); - dev_kfree_skb(skb_dequeue(&tx->sdata->bss->ps_bc_buf)); + dev_kfree_skb(skb_dequeue(&ps->bc_buf)); } else tx->local->total_ps_buffered++; - skb_queue_tail(&tx->sdata->bss->ps_bc_buf, tx->skb); + skb_queue_tail(&ps->bc_buf, tx->skb); return TX_QUEUED; } @@ -951,7 +956,6 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) fragnum = 0; skb_queue_walk(&tx->skbs, skb) { - int next_len; const __le16 morefrags = cpu_to_le16(IEEE80211_FCTL_MOREFRAGS); hdr = (void *)skb->data; @@ -970,7 +974,6 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) info->flags &= ~IEEE80211_TX_CTL_RATE_CTRL_PROBE; } else { hdr->frame_control &= ~morefrags; - next_len = 0; } hdr->seq_ctrl |= cpu_to_le16(fragnum & IEEE80211_SCTL_FRAG); fragnum++; @@ -1358,7 +1361,7 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx) if (tx->skb) ieee80211_free_txskb(&tx->local->hw, tx->skb); else - __skb_queue_purge(&tx->skbs); + ieee80211_purge_tx_queue(&tx->local->hw, &tx->skbs); return -1; } else if (unlikely(res == TX_QUEUED)) { I802_DEBUG_INC(tx->local->tx_handlers_queued); @@ -1372,7 +1375,8 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx) * Returns false if the frame couldn't be transmitted but was queued instead. */ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, bool txpending) + struct sk_buff *skb, bool txpending, + enum ieee80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_data tx; @@ -1386,20 +1390,18 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, return true; } - rcu_read_lock(); - /* initialises tx */ led_len = skb->len; res_prepare = ieee80211_tx_prepare(sdata, &tx, skb); if (unlikely(res_prepare == TX_DROP)) { ieee80211_free_txskb(&local->hw, skb); - goto out; + return true; } else if (unlikely(res_prepare == TX_QUEUED)) { - goto out; + return true; } - info->band = local->hw.conf.channel->band; + info->band = band; /* set up hw_queue value early */ if (!(info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) || @@ -1410,8 +1412,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, if (!invoke_tx_handlers(&tx)) result = __ieee80211_tx(local, &tx.skbs, led_len, tx.sta, txpending); - out: - rcu_read_unlock(); + return result; } @@ -1446,7 +1447,8 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, return 0; } -void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) +void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, + enum ieee80211_band band) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -1454,8 +1456,6 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) int headroom; bool may_encrypt; - rcu_read_lock(); - may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT); headroom = local->tx_headroom; @@ -1466,7 +1466,6 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) { ieee80211_free_txskb(&local->hw, skb); - rcu_read_unlock(); return; } @@ -1478,13 +1477,11 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) !is_multicast_ether_addr(hdr->addr1) && mesh_nexthop_resolve(skb, sdata)) { /* skb queued: don't free */ - rcu_read_unlock(); return; } ieee80211_set_qos_hdr(sdata, skb); - ieee80211_tx(sdata, skb, false); - rcu_read_unlock(); + ieee80211_tx(sdata, skb, false, band); } static bool ieee80211_parse_tx_radiotap(struct sk_buff *skb) @@ -1574,7 +1571,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_channel *chan = local->hw.conf.channel; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *chan; struct ieee80211_radiotap_header *prthdr = (struct ieee80211_radiotap_header *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -1583,26 +1581,6 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, u16 len_rthdr; int hdrlen; - /* - * Frame injection is not allowed if beaconing is not allowed - * or if we need radar detection. Beaconing is usually not allowed when - * the mode or operation (Adhoc, AP, Mesh) does not support DFS. - * Passive scan is also used in world regulatory domains where - * your country is not known and as such it should be treated as - * NO TX unless the channel is explicitly allowed in which case - * your current regulatory domain would not have the passive scan - * flag. - * - * Since AP mode uses monitor interfaces to inject/TX management - * frames we can make AP mode the exception to this rule once it - * supports radar detection as its implementation can deal with - * radar detection by itself. We can do that later by adding a - * monitor flag interfaces used for AP support. - */ - if ((chan->flags & (IEEE80211_CHAN_NO_IBSS | IEEE80211_CHAN_RADAR | - IEEE80211_CHAN_PASSIVE_SCAN))) - goto fail; - /* check for not even having the fixed radiotap header part */ if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) goto fail; /* too short to be possibly valid */ @@ -1688,11 +1666,48 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, } } - ieee80211_xmit(sdata, skb); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) { + tmp_sdata = rcu_dereference(local->monitor_sdata); + if (tmp_sdata) + chanctx_conf = + rcu_dereference(tmp_sdata->vif.chanctx_conf); + } + + if (chanctx_conf) + chan = chanctx_conf->def.chan; + else if (!local->use_chanctx) + chan = local->_oper_channel; + else + goto fail_rcu; + + /* + * Frame injection is not allowed if beaconing is not allowed + * or if we need radar detection. Beaconing is usually not allowed when + * the mode or operation (Adhoc, AP, Mesh) does not support DFS. + * Passive scan is also used in world regulatory domains where + * your country is not known and as such it should be treated as + * NO TX unless the channel is explicitly allowed in which case + * your current regulatory domain would not have the passive scan + * flag. + * + * Since AP mode uses monitor interfaces to inject/TX management + * frames we can make AP mode the exception to this rule once it + * supports radar detection as its implementation can deal with + * radar detection by itself. We can do that later by adding a + * monitor flag interfaces used for AP support. + */ + if ((chan->flags & (IEEE80211_CHAN_NO_IBSS | IEEE80211_CHAN_RADAR | + IEEE80211_CHAN_PASSIVE_SCAN))) + goto fail_rcu; + + ieee80211_xmit(sdata, skb, chan->band); rcu_read_unlock(); return NETDEV_TX_OK; +fail_rcu: + rcu_read_unlock(); fail: dev_kfree_skb(skb); return NETDEV_TX_OK; /* meaning, we dealt with the skb */ @@ -1734,6 +1749,9 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, bool multicast; u32 info_flags = 0; u16 info_id = 0; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_sub_if_data *ap_sdata; + enum ieee80211_band band; if (unlikely(skb->len < ETH_HLEN)) goto fail; @@ -1743,9 +1761,10 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, ethertype = (skb->data[12] << 8) | skb->data[13]; fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); + rcu_read_lock(); + switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: - rcu_read_lock(); sta = rcu_dereference(sdata->u.vlan.sta); if (sta) { fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); @@ -1758,7 +1777,12 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); wme_sta = test_sta_flag(sta, WLAN_STA_WME); } - rcu_read_unlock(); + ap_sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, + u.ap); + chanctx_conf = rcu_dereference(ap_sdata->vif.chanctx_conf); + if (!chanctx_conf) + goto fail_rcu; + band = chanctx_conf->def.chan->band; if (sta) break; /* fall through */ @@ -1769,6 +1793,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr.addr3, skb->data + ETH_ALEN, ETH_ALEN); hdrlen = 24; + if (sdata->vif.type == NL80211_IFTYPE_AP) + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) + goto fail_rcu; + band = chanctx_conf->def.chan->band; break; case NL80211_IFTYPE_WDS: fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); @@ -1778,15 +1807,20 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, memcpy(hdr.addr3, skb->data, ETH_ALEN); memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN); hdrlen = 30; + /* + * This is the exception! WDS style interfaces are prohibited + * when channel contexts are in used so this must be valid + */ + band = local->hw.conf.channel->band; break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: if (!sdata->u.mesh.mshcfg.dot11MeshTTL) { /* Do not send frames with mesh_ttl == 0 */ sdata->u.mesh.mshstats.dropped_frames_ttl++; - goto fail; + goto fail_rcu; } - rcu_read_lock(); + if (!is_multicast_ether_addr(skb->data)) { mpath = mesh_path_lookup(skb->data, sdata); if (!mpath) @@ -1803,7 +1837,6 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, !(mppath && !ether_addr_equal(mppath->mpp, skb->data))) { hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, skb->data, skb->data + ETH_ALEN); - rcu_read_unlock(); meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata, NULL, NULL); } else { @@ -1819,7 +1852,6 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, mesh_da = mppath->mpp; else if (mpath) mesh_da = mpath->dst; - rcu_read_unlock(); hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, mesh_da, sdata->vif.addr); @@ -1839,13 +1871,16 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, skb->data + ETH_ALEN); } + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) + goto fail_rcu; + band = chanctx_conf->def.chan->band; break; #endif case NL80211_IFTYPE_STATION: if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) { bool tdls_peer = false; - rcu_read_lock(); sta = sta_info_get(sdata, skb->data); if (sta) { authorized = test_sta_flag(sta, @@ -1856,7 +1891,6 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, tdls_auth = test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); } - rcu_read_unlock(); /* * If the TDLS link is enabled, send everything @@ -1871,7 +1905,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, if (tdls_direct) { /* link during setup - throw out frames to peer */ if (!tdls_auth) - goto fail; + goto fail_rcu; /* DA SA BSSID */ memcpy(hdr.addr1, skb->data, ETH_ALEN); @@ -1896,6 +1930,10 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, memcpy(hdr.addr3, skb->data, ETH_ALEN); hdrlen = 24; } + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) + goto fail_rcu; + band = chanctx_conf->def.chan->band; break; case NL80211_IFTYPE_ADHOC: /* DA SA BSSID */ @@ -1903,9 +1941,13 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); memcpy(hdr.addr3, sdata->u.ibss.bssid, ETH_ALEN); hdrlen = 24; + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) + goto fail_rcu; + band = chanctx_conf->def.chan->band; break; default: - goto fail; + goto fail_rcu; } /* @@ -1915,13 +1957,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, */ multicast = is_multicast_ether_addr(hdr.addr1); if (!multicast) { - rcu_read_lock(); sta = sta_info_get(sdata, hdr.addr1); if (sta) { authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); wme_sta = test_sta_flag(sta, WLAN_STA_WME); } - rcu_read_unlock(); } /* For mesh, the use of the QoS header is mandatory */ @@ -1949,7 +1989,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, I802_DEBUG_INC(local->tx_handlers_drop_unauth_port); - goto fail; + goto fail_rcu; } if (unlikely(!multicast && skb->sk && @@ -2004,7 +2044,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, kfree_skb(tmp_skb); if (!skb) - goto fail; + goto fail_rcu; } hdr.frame_control = fc; @@ -2052,7 +2092,8 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, head_need = max_t(int, 0, head_need); if (ieee80211_skb_resize(sdata, skb, head_need, true)) { ieee80211_free_txskb(&local->hw, skb); - return NETDEV_TX_OK; + skb = NULL; + goto fail_rcu; } } @@ -2104,10 +2145,13 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, info->flags = info_flags; info->ack_frame_id = info_id; - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, skb, band); + rcu_read_unlock(); return NETDEV_TX_OK; + fail_rcu: + rcu_read_unlock(); fail: dev_kfree_skb(skb); return NETDEV_TX_OK; @@ -2120,10 +2164,13 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, */ void ieee80211_clear_tx_pending(struct ieee80211_local *local) { + struct sk_buff *skb; int i; - for (i = 0; i < local->hw.queues; i++) - skb_queue_purge(&local->pending[i]); + for (i = 0; i < local->hw.queues; i++) { + while ((skb = skb_dequeue(&local->pending[i])) != NULL) + ieee80211_free_txskb(&local->hw, skb); + } } /* @@ -2139,11 +2186,18 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, struct sta_info *sta; struct ieee80211_hdr *hdr; bool result; + struct ieee80211_chanctx_conf *chanctx_conf; sdata = vif_to_sdata(info->control.vif); if (info->flags & IEEE80211_TX_INTFL_NEED_TXPROCESSING) { - result = ieee80211_tx(sdata, skb, true); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (unlikely(!chanctx_conf)) { + dev_kfree_skb(skb); + return true; + } + result = ieee80211_tx(sdata, skb, true, + chanctx_conf->def.chan->band); } else { struct sk_buff_head skbs; @@ -2211,9 +2265,8 @@ void ieee80211_tx_pending(unsigned long data) /* functions for drivers to get certain frames */ static void ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, - struct ieee80211_if_ap *bss, - struct sk_buff *skb, - struct beacon_data *beacon) + struct ps_data *ps, + struct sk_buff *skb) { u8 *pos, *tim; int aid0 = 0; @@ -2221,27 +2274,27 @@ static void ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, /* Generate bitmap for TIM only if there are any STAs in power save * mode. */ - if (atomic_read(&bss->num_sta_ps) > 0) + if (atomic_read(&ps->num_sta_ps) > 0) /* in the hope that this is faster than * checking byte-for-byte */ - have_bits = !bitmap_empty((unsigned long*)bss->tim, + have_bits = !bitmap_empty((unsigned long*)ps->tim, IEEE80211_MAX_AID+1); - if (bss->dtim_count == 0) - bss->dtim_count = sdata->vif.bss_conf.dtim_period - 1; + if (ps->dtim_count == 0) + ps->dtim_count = sdata->vif.bss_conf.dtim_period - 1; else - bss->dtim_count--; + ps->dtim_count--; tim = pos = (u8 *) skb_put(skb, 6); *pos++ = WLAN_EID_TIM; *pos++ = 4; - *pos++ = bss->dtim_count; + *pos++ = ps->dtim_count; *pos++ = sdata->vif.bss_conf.dtim_period; - if (bss->dtim_count == 0 && !skb_queue_empty(&bss->ps_bc_buf)) + if (ps->dtim_count == 0 && !skb_queue_empty(&ps->bc_buf)) aid0 = 1; - bss->dtim_bc_mc = aid0 == 1; + ps->dtim_bc_mc = aid0 == 1; if (have_bits) { /* Find largest even number N1 so that bits numbered 1 through @@ -2249,14 +2302,14 @@ static void ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, * (N2 + 1) x 8 through 2007 are 0. */ n1 = 0; for (i = 0; i < IEEE80211_MAX_TIM_LEN; i++) { - if (bss->tim[i]) { + if (ps->tim[i]) { n1 = i & 0xfe; break; } } n2 = n1; for (i = IEEE80211_MAX_TIM_LEN - 1; i >= n1; i--) { - if (bss->tim[i]) { + if (ps->tim[i]) { n2 = i; break; } @@ -2266,7 +2319,7 @@ static void ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, *pos++ = n1 | aid0; /* Part Virt Bitmap */ skb_put(skb, n2 - n1); - memcpy(pos, bss->tim + n1, n2 - n1 + 1); + memcpy(pos, ps->tim + n1, n2 - n1 + 1); tim[1] = n2 - n1 + 4; } else { @@ -2283,16 +2336,16 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, struct sk_buff *skb = NULL; struct ieee80211_tx_info *info; struct ieee80211_sub_if_data *sdata = NULL; - struct ieee80211_if_ap *ap = NULL; - struct beacon_data *beacon; - enum ieee80211_band band = local->oper_channel->band; + enum ieee80211_band band; struct ieee80211_tx_rate_control txrc; + struct ieee80211_chanctx_conf *chanctx_conf; rcu_read_lock(); sdata = vif_to_sdata(vif); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (!ieee80211_sdata_running(sdata)) + if (!ieee80211_sdata_running(sdata) || !chanctx_conf) goto out; if (tim_offset) @@ -2301,8 +2354,9 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, *tim_length = 0; if (sdata->vif.type == NL80211_IFTYPE_AP) { - ap = &sdata->u.ap; - beacon = rcu_dereference(ap->beacon); + struct ieee80211_if_ap *ap = &sdata->u.ap; + struct beacon_data *beacon = rcu_dereference(ap->beacon); + if (beacon) { /* * headroom, head length, @@ -2326,14 +2380,12 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, * of the tim bitmap in mac80211 and the driver. */ if (local->tim_in_locked_section) { - ieee80211_beacon_add_tim(sdata, ap, skb, - beacon); + ieee80211_beacon_add_tim(sdata, &ap->ps, skb); } else { unsigned long flags; spin_lock_irqsave(&local->tim_lock, flags); - ieee80211_beacon_add_tim(sdata, ap, skb, - beacon); + ieee80211_beacon_add_tim(sdata, &ap->ps, skb); spin_unlock_irqrestore(&local->tim_lock, flags); } @@ -2409,6 +2461,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, *pos++ = WLAN_EID_SSID; *pos++ = 0x0; + band = chanctx_conf->def.chan->band; + if (ieee80211_add_srates_ie(sdata, skb, true, band) || mesh_add_ds_params_ie(skb, sdata) || ieee80211_add_ext_srates_ie(sdata, skb, true, band) || @@ -2426,6 +2480,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, goto out; } + band = chanctx_conf->def.chan->band; + info = IEEE80211_SKB_CB(skb); info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; @@ -2570,7 +2626,7 @@ EXPORT_SYMBOL(ieee80211_nullfunc_get); struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *ssid, size_t ssid_len, - const u8 *ie, size_t ie_len) + size_t tailroom) { struct ieee80211_sub_if_data *sdata; struct ieee80211_local *local; @@ -2584,7 +2640,7 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, ie_ssid_len = 2 + ssid_len; skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(*hdr) + - ie_ssid_len + ie_len); + ie_ssid_len + tailroom); if (!skb) return NULL; @@ -2605,11 +2661,6 @@ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, memcpy(pos, ssid, ssid_len); pos += ssid_len; - if (ie) { - pos = skb_put(skb, ie_len); - memcpy(pos, ie, ie_len); - } - return skb; } EXPORT_SYMBOL(ieee80211_probereq_get); @@ -2653,29 +2704,40 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, struct sk_buff *skb = NULL; struct ieee80211_tx_data tx; struct ieee80211_sub_if_data *sdata; - struct ieee80211_if_ap *bss = NULL; - struct beacon_data *beacon; + struct ps_data *ps; struct ieee80211_tx_info *info; + struct ieee80211_chanctx_conf *chanctx_conf; sdata = vif_to_sdata(vif); - bss = &sdata->u.ap; rcu_read_lock(); - beacon = rcu_dereference(bss->beacon); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + + if (!chanctx_conf) + goto out; - if (sdata->vif.type != NL80211_IFTYPE_AP || !beacon || !beacon->head) + if (sdata->vif.type == NL80211_IFTYPE_AP) { + struct beacon_data *beacon = + rcu_dereference(sdata->u.ap.beacon); + + if (!beacon || !beacon->head) + goto out; + + ps = &sdata->u.ap.ps; + } else { goto out; + } - if (bss->dtim_count != 0 || !bss->dtim_bc_mc) + if (ps->dtim_count != 0 || !ps->dtim_bc_mc) goto out; /* send buffered bc/mc only after DTIM beacon */ while (1) { - skb = skb_dequeue(&bss->ps_bc_buf); + skb = skb_dequeue(&ps->bc_buf); if (!skb) goto out; local->total_ps_buffered--; - if (!skb_queue_empty(&bss->ps_bc_buf) && skb->len >= 2) { + if (!skb_queue_empty(&ps->bc_buf) && skb->len >= 2) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; /* more buffered multicast/broadcast frames ==> set @@ -2693,7 +2755,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, info = IEEE80211_SKB_CB(skb); tx.flags |= IEEE80211_TX_PS_BUFFERED; - info->band = local->oper_channel->band; + info->band = chanctx_conf->def.chan->band; if (invoke_tx_handlers(&tx)) skb = NULL; @@ -2704,8 +2766,9 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_get_buffered_bc); -void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, int tid) +void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, int tid, + enum ieee80211_band band) { int ac = ieee802_1d_to_ac[tid & 7]; @@ -2722,6 +2785,6 @@ void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, * requirements are that we do not come into tx with bhs on. */ local_bh_disable(); - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, skb, band); local_bh_enable(); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 94e586873979..f11e8c540db4 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -512,7 +512,7 @@ void ieee80211_wake_queues(struct ieee80211_hw *hw) EXPORT_SYMBOL(ieee80211_wake_queues); void ieee80211_iterate_active_interfaces( - struct ieee80211_hw *hw, + struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data) @@ -530,6 +530,9 @@ void ieee80211_iterate_active_interfaces( default: break; } + if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) && + !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) + continue; if (ieee80211_sdata_running(sdata)) iterator(data, sdata->vif.addr, &sdata->vif); @@ -537,7 +540,9 @@ void ieee80211_iterate_active_interfaces( sdata = rcu_dereference_protected(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx)); - if (sdata) + if (sdata && + (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || + sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); mutex_unlock(&local->iflist_mtx); @@ -545,7 +550,7 @@ void ieee80211_iterate_active_interfaces( EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces); void ieee80211_iterate_active_interfaces_atomic( - struct ieee80211_hw *hw, + struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data) @@ -563,13 +568,18 @@ void ieee80211_iterate_active_interfaces_atomic( default: break; } + if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) && + !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) + continue; if (ieee80211_sdata_running(sdata)) iterator(data, sdata->vif.addr, &sdata->vif); } sdata = rcu_dereference(local->monitor_sdata); - if (sdata) + if (sdata && + (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || + sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); rcu_read_unlock(); @@ -643,13 +653,41 @@ u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, break; } - if (id != WLAN_EID_VENDOR_SPECIFIC && - id != WLAN_EID_QUIET && - test_bit(id, seen_elems)) { - elems->parse_error = true; - left -= elen; - pos += elen; - continue; + switch (id) { + case WLAN_EID_SSID: + case WLAN_EID_SUPP_RATES: + case WLAN_EID_FH_PARAMS: + case WLAN_EID_DS_PARAMS: + case WLAN_EID_CF_PARAMS: + case WLAN_EID_TIM: + case WLAN_EID_IBSS_PARAMS: + case WLAN_EID_CHALLENGE: + case WLAN_EID_RSN: + case WLAN_EID_ERP_INFO: + case WLAN_EID_EXT_SUPP_RATES: + case WLAN_EID_HT_CAPABILITY: + case WLAN_EID_HT_OPERATION: + case WLAN_EID_VHT_CAPABILITY: + case WLAN_EID_VHT_OPERATION: + case WLAN_EID_MESH_ID: + case WLAN_EID_MESH_CONFIG: + case WLAN_EID_PEER_MGMT: + case WLAN_EID_PREQ: + case WLAN_EID_PREP: + case WLAN_EID_PERR: + case WLAN_EID_RANN: + case WLAN_EID_CHANNEL_SWITCH: + case WLAN_EID_EXT_CHANSWITCH_ANN: + case WLAN_EID_COUNTRY: + case WLAN_EID_PWR_CONSTRAINT: + case WLAN_EID_TIMEOUT_INTERVAL: + if (test_bit(id, seen_elems)) { + elems->parse_error = true; + left -= elen; + pos += elen; + continue; + } + break; } if (calc_crc && id < 64 && (filter & (1ULL << id))) @@ -741,6 +779,18 @@ u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, else elem_parse_failed = true; break; + case WLAN_EID_VHT_CAPABILITY: + if (elen >= sizeof(struct ieee80211_vht_cap)) + elems->vht_cap_elem = (void *)pos; + else + elem_parse_failed = true; + break; + case WLAN_EID_VHT_OPERATION: + if (elen >= sizeof(struct ieee80211_vht_operation)) + elems->vht_operation = (void *)pos; + else + elem_parse_failed = true; + break; case WLAN_EID_MESH_ID: elems->mesh_id = pos; elems->mesh_id_len = elen; @@ -809,7 +859,7 @@ u32 ieee802_11_parse_elems_crc(u8 *start, size_t len, if (elem_parse_failed) elems->parse_error = true; else - set_bit(id, seen_elems); + __set_bit(id, seen_elems); left -= elen; pos += elen; @@ -832,6 +882,7 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_queue_params qparam; + struct ieee80211_chanctx_conf *chanctx_conf; int ac; bool use_11b, enable_qos; int aCWmin, aCWmax; @@ -844,8 +895,12 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, memset(&qparam, 0, sizeof(qparam)); - use_11b = (local->oper_channel->band == IEEE80211_BAND_2GHZ) && + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + use_11b = (chanctx_conf && + chanctx_conf->def.chan->band == IEEE80211_BAND_2GHZ) && !(sdata->flags & IEEE80211_SDATA_OPERATING_GMODE); + rcu_read_unlock(); /* * By default disable QoS in STA mode for old access points, which do @@ -924,7 +979,7 @@ void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, const size_t supp_rates_len, const u8 *supp_rates) { - struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx_conf *chanctx_conf; int i, have_higher_than_11mbit = 0; /* cf. IEEE 802.11 9.2.12 */ @@ -932,11 +987,16 @@ void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, if ((supp_rates[i] & 0x7f) * 5 > 110) have_higher_than_11mbit = 1; - if (local->oper_channel->band == IEEE80211_BAND_2GHZ && + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + + if (chanctx_conf && + chanctx_conf->def.chan->band == IEEE80211_BAND_2GHZ && have_higher_than_11mbit) sdata->flags |= IEEE80211_SDATA_OPERATING_GMODE; else sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE; + rcu_read_unlock(); ieee80211_set_wmm_default(sdata, true); } @@ -968,7 +1028,7 @@ u32 ieee80211_mandatory_rates(struct ieee80211_local *local, } void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, - u16 transaction, u16 auth_alg, + u16 transaction, u16 auth_alg, u16 status, u8 *extra, size_t extra_len, const u8 *da, const u8 *bssid, const u8 *key, u8 key_len, u8 key_idx) { @@ -993,7 +1053,7 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, memcpy(mgmt->bssid, bssid, ETH_ALEN); mgmt->u.auth.auth_alg = cpu_to_le16(auth_alg); mgmt->u.auth.auth_transaction = cpu_to_le16(transaction); - mgmt->u.auth.status_code = cpu_to_le16(0); + mgmt->u.auth.status_code = cpu_to_le16(status); if (extra) memcpy(skb_put(skb, extra_len), extra, extra_len); @@ -1047,12 +1107,12 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, } int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, - const u8 *ie, size_t ie_len, + size_t buffer_len, const u8 *ie, size_t ie_len, enum ieee80211_band band, u32 rate_mask, u8 channel) { struct ieee80211_supported_band *sband; - u8 *pos; + u8 *pos = buffer, *end = buffer + buffer_len; size_t offset = 0, noffset; int supp_rates_len, i; u8 rates[32]; @@ -1063,8 +1123,6 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, if (WARN_ON_ONCE(!sband)) return 0; - pos = buffer; - num_rates = 0; for (i = 0; i < sband->n_bitrates; i++) { if ((BIT(i) & rate_mask) == 0) @@ -1074,6 +1132,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, supp_rates_len = min_t(int, num_rates, 8); + if (end - pos < 2 + supp_rates_len) + goto out_err; *pos++ = WLAN_EID_SUPP_RATES; *pos++ = supp_rates_len; memcpy(pos, rates, supp_rates_len); @@ -1090,6 +1150,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, before_extrates, ARRAY_SIZE(before_extrates), offset); + if (end - pos < noffset - offset) + goto out_err; memcpy(pos, ie + offset, noffset - offset); pos += noffset - offset; offset = noffset; @@ -1097,6 +1159,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, ext_rates_len = num_rates - supp_rates_len; if (ext_rates_len > 0) { + if (end - pos < 2 + ext_rates_len) + goto out_err; *pos++ = WLAN_EID_EXT_SUPP_RATES; *pos++ = ext_rates_len; memcpy(pos, rates + supp_rates_len, ext_rates_len); @@ -1104,6 +1168,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, } if (channel && sband->band == IEEE80211_BAND_2GHZ) { + if (end - pos < 3) + goto out_err; *pos++ = WLAN_EID_DS_PARAMS; *pos++ = 1; *pos++ = channel; @@ -1122,14 +1188,19 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, noffset = ieee80211_ie_split(ie, ie_len, before_ht, ARRAY_SIZE(before_ht), offset); + if (end - pos < noffset - offset) + goto out_err; memcpy(pos, ie + offset, noffset - offset); pos += noffset - offset; offset = noffset; } - if (sband->ht_cap.ht_supported) + if (sband->ht_cap.ht_supported) { + if (end - pos < 2 + sizeof(struct ieee80211_ht_cap)) + goto out_err; pos = ieee80211_ie_build_ht_cap(pos, &sband->ht_cap, sband->ht_cap.cap); + } /* * If adding more here, adjust code in main.c @@ -1139,15 +1210,23 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, /* add any remaining custom IEs */ if (ie && ie_len) { noffset = ie_len; + if (end - pos < noffset - offset) + goto out_err; memcpy(pos, ie + offset, noffset - offset); pos += noffset - offset; } - if (sband->vht_cap.vht_supported) + if (sband->vht_cap.vht_supported) { + if (end - pos < 2 + sizeof(struct ieee80211_vht_cap)) + goto out_err; pos = ieee80211_ie_build_vht_cap(pos, &sband->vht_cap, sband->vht_cap.cap); + } return pos - buffer; + out_err: + WARN_ONCE(1, "not enough space for preq IEs\n"); + return pos - buffer; } struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, @@ -1160,14 +1239,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; - size_t buf_len; - u8 *buf; u8 chan_no; - - /* FIXME: come up with a proper value */ - buf = kmalloc(200 + ie_len, GFP_KERNEL); - if (!buf) - return NULL; + int ies_len; /* * Do not send DS Channel parameter for directed probe requests @@ -1179,14 +1252,16 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, else chan_no = ieee80211_frequency_to_channel(chan->center_freq); - buf_len = ieee80211_build_preq_ies(local, buf, ie, ie_len, chan->band, - ratemask, chan_no); - skb = ieee80211_probereq_get(&local->hw, &sdata->vif, - ssid, ssid_len, - buf, buf_len); + ssid, ssid_len, 100 + ie_len); if (!skb) - goto out; + return NULL; + + ies_len = ieee80211_build_preq_ies(local, skb_tail_pointer(skb), + skb_tailroom(skb), + ie, ie_len, chan->band, + ratemask, chan_no); + skb_put(skb, ies_len); if (dst) { mgmt = (struct ieee80211_mgmt *) skb->data; @@ -1196,9 +1271,6 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; - out: - kfree(buf); - return skb; } @@ -1206,7 +1278,7 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, u32 ratemask, bool directed, bool no_cck, - struct ieee80211_channel *channel) + struct ieee80211_channel *channel, bool scan) { struct sk_buff *skb; @@ -1217,7 +1289,10 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, if (no_cck) IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_NO_CCK_RATE; - ieee80211_tx_skb(sdata, skb); + if (scan) + ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); + else + ieee80211_tx_skb(sdata, skb); } } @@ -1280,6 +1355,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) { struct ieee80211_hw *hw = &local->hw; struct ieee80211_sub_if_data *sdata; + struct ieee80211_chanctx *ctx; struct sta_info *sta; int res, i; @@ -1352,6 +1428,46 @@ int ieee80211_reconfig(struct ieee80211_local *local) res = drv_add_interface(local, sdata); } + /* add channel contexts */ + if (local->use_chanctx) { + mutex_lock(&local->chanctx_mtx); + list_for_each_entry(ctx, &local->chanctx_list, list) + WARN_ON(drv_add_chanctx(local, ctx)); + mutex_unlock(&local->chanctx_mtx); + } + + list_for_each_entry(sdata, &local->interfaces, list) { + struct ieee80211_chanctx_conf *ctx_conf; + + if (!ieee80211_sdata_running(sdata)) + continue; + + mutex_lock(&local->chanctx_mtx); + ctx_conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (ctx_conf) { + ctx = container_of(ctx_conf, struct ieee80211_chanctx, + conf); + drv_assign_vif_chanctx(local, sdata, ctx); + } + mutex_unlock(&local->chanctx_mtx); + } + + sdata = rtnl_dereference(local->monitor_sdata); + if (sdata && local->use_chanctx && ieee80211_sdata_running(sdata)) { + struct ieee80211_chanctx_conf *ctx_conf; + + mutex_lock(&local->chanctx_mtx); + ctx_conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (ctx_conf) { + ctx = container_of(ctx_conf, struct ieee80211_chanctx, + conf); + drv_assign_vif_chanctx(local, sdata, ctx); + } + mutex_unlock(&local->chanctx_mtx); + } + /* add STAs back */ mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { @@ -1407,7 +1523,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) BSS_CHANGED_BSSID | BSS_CHANGED_CQM | BSS_CHANGED_QOS | - BSS_CHANGED_IDLE; + BSS_CHANGED_IDLE | + BSS_CHANGED_TXPOWER; switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: @@ -1422,11 +1539,15 @@ int ieee80211_reconfig(struct ieee80211_local *local) changed |= BSS_CHANGED_IBSS; /* fall through */ case NL80211_IFTYPE_AP: - changed |= BSS_CHANGED_SSID; + changed |= BSS_CHANGED_SSID | BSS_CHANGED_P2P_PS; - if (sdata->vif.type == NL80211_IFTYPE_AP) + if (sdata->vif.type == NL80211_IFTYPE_AP) { changed |= BSS_CHANGED_AP_PROBE_RESP; + if (rcu_access_pointer(sdata->u.ap.beacon)) + drv_start_ap(local, sdata); + } + /* fall through */ case NL80211_IFTYPE_MESH_POINT: changed |= BSS_CHANGED_BEACON | @@ -1463,6 +1584,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_STATION) continue; + if (!sdata->u.mgd.associated) + continue; ieee80211_send_nullfunc(local, sdata, 0); } @@ -1523,8 +1646,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) * If this is for hw restart things are still running. * We may want to change that later, however. */ - if (!local->suspended) + if (!local->suspended) { + drv_restart_complete(local); return 0; + } #ifdef CONFIG_PM /* first set suspended false, then resuming */ @@ -1587,68 +1712,24 @@ void ieee80211_resume_disconnect(struct ieee80211_vif *vif) } EXPORT_SYMBOL_GPL(ieee80211_resume_disconnect); -static int check_mgd_smps(struct ieee80211_if_managed *ifmgd, - enum ieee80211_smps_mode *smps_mode) -{ - if (ifmgd->associated) { - *smps_mode = ifmgd->ap_smps; - - if (*smps_mode == IEEE80211_SMPS_AUTOMATIC) { - if (ifmgd->powersave) - *smps_mode = IEEE80211_SMPS_DYNAMIC; - else - *smps_mode = IEEE80211_SMPS_OFF; - } - - return 1; - } - - return 0; -} - -void ieee80211_recalc_smps(struct ieee80211_local *local) +void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata) { - struct ieee80211_sub_if_data *sdata; - enum ieee80211_smps_mode smps_mode = IEEE80211_SMPS_OFF; - int count = 0; - - mutex_lock(&local->iflist_mtx); - - /* - * This function could be improved to handle multiple - * interfaces better, but right now it makes any - * non-station interfaces force SM PS to be turned - * off. If there are multiple station interfaces it - * could also use the best possible mode, e.g. if - * one is in static and the other in dynamic then - * dynamic is ok. - */ - - list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata)) - continue; - if (sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE) - continue; - if (sdata->vif.type != NL80211_IFTYPE_STATION) - goto set; + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_chanctx *chanctx; - count += check_mgd_smps(&sdata->u.mgd, &smps_mode); + mutex_lock(&local->chanctx_mtx); - if (count > 1) { - smps_mode = IEEE80211_SMPS_OFF; - break; - } - } + chanctx_conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); - if (smps_mode == local->smps_mode) + if (WARN_ON_ONCE(!chanctx_conf)) goto unlock; - set: - local->smps_mode = smps_mode; - /* changed flag is auto-detected for this */ - ieee80211_hw_config(local, 0); + chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); + ieee80211_recalc_smps_chanctx(local, chanctx); unlock: - mutex_unlock(&local->iflist_mtx); + mutex_unlock(&local->chanctx_mtx); } static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id) @@ -1788,8 +1869,8 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, __le32 tmp; *pos++ = WLAN_EID_VHT_CAPABILITY; - *pos++ = sizeof(struct ieee80211_vht_capabilities); - memset(pos, 0, sizeof(struct ieee80211_vht_capabilities)); + *pos++ = sizeof(struct ieee80211_vht_cap); + memset(pos, 0, sizeof(struct ieee80211_vht_cap)); /* capability flags */ tmp = cpu_to_le32(cap); @@ -1804,8 +1885,7 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, } u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, - struct ieee80211_channel *channel, - enum nl80211_channel_type channel_type, + const struct cfg80211_chan_def *chandef, u16 prot_mode) { struct ieee80211_ht_operation *ht_oper; @@ -1813,23 +1893,25 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, *pos++ = WLAN_EID_HT_OPERATION; *pos++ = sizeof(struct ieee80211_ht_operation); ht_oper = (struct ieee80211_ht_operation *)pos; - ht_oper->primary_chan = - ieee80211_frequency_to_channel(channel->center_freq); - switch (channel_type) { - case NL80211_CHAN_HT40MINUS: - ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_BELOW; - break; - case NL80211_CHAN_HT40PLUS: - ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_ABOVE; + ht_oper->primary_chan = ieee80211_frequency_to_channel( + chandef->chan->center_freq); + switch (chandef->width) { + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_40: + if (chandef->center_freq1 > chandef->chan->center_freq) + ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_ABOVE; + else + ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_BELOW; break; - case NL80211_CHAN_HT20: default: ht_oper->ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE; break; } if (ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 && - channel_type != NL80211_CHAN_NO_HT && - channel_type != NL80211_CHAN_HT20) + chandef->width != NL80211_CHAN_WIDTH_20_NOHT && + chandef->width != NL80211_CHAN_WIDTH_20) ht_oper->ht_param |= IEEE80211_HT_PARAM_CHAN_WIDTH_ANY; ht_oper->operation_mode = cpu_to_le16(prot_mode); @@ -1843,13 +1925,17 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, return pos + sizeof(struct ieee80211_ht_operation); } -enum nl80211_channel_type -ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper) +void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan, + struct ieee80211_ht_operation *ht_oper, + struct cfg80211_chan_def *chandef) { enum nl80211_channel_type channel_type; - if (!ht_oper) - return NL80211_CHAN_NO_HT; + if (!ht_oper) { + cfg80211_chandef_create(chandef, control_chan, + NL80211_CHAN_NO_HT); + return; + } switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { case IEEE80211_HT_PARAM_CHA_SEC_NONE: @@ -1865,7 +1951,7 @@ ieee80211_ht_oper_to_channel_type(struct ieee80211_ht_operation *ht_oper) channel_type = NL80211_CHAN_NO_HT; } - return channel_type; + cfg80211_chandef_create(chandef, control_chan, channel_type); } int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, @@ -1947,3 +2033,84 @@ int ieee80211_ave_rssi(struct ieee80211_vif *vif) return ifmgd->ave_beacon_signal; } EXPORT_SYMBOL_GPL(ieee80211_ave_rssi); + +u8 ieee80211_mcs_to_chains(const struct ieee80211_mcs_info *mcs) +{ + if (!mcs) + return 1; + + /* TODO: consider rx_highest */ + + if (mcs->rx_mask[3]) + return 4; + if (mcs->rx_mask[2]) + return 3; + if (mcs->rx_mask[1]) + return 2; + return 1; +} + +/** + * ieee80211_calculate_rx_timestamp - calculate timestamp in frame + * @local: mac80211 hw info struct + * @status: RX status + * @mpdu_len: total MPDU length (including FCS) + * @mpdu_offset: offset into MPDU to calculate timestamp at + * + * This function calculates the RX timestamp at the given MPDU offset, taking + * into account what the RX timestamp was. An offset of 0 will just normalize + * the timestamp to TSF at beginning of MPDU reception. + */ +u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, + struct ieee80211_rx_status *status, + unsigned int mpdu_len, + unsigned int mpdu_offset) +{ + u64 ts = status->mactime; + struct rate_info ri; + u16 rate; + + if (WARN_ON(!ieee80211_have_rx_timestamp(status))) + return 0; + + memset(&ri, 0, sizeof(ri)); + + /* Fill cfg80211 rate info */ + if (status->flag & RX_FLAG_HT) { + ri.mcs = status->rate_idx; + ri.flags |= RATE_INFO_FLAGS_MCS; + if (status->flag & RX_FLAG_40MHZ) + ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH; + if (status->flag & RX_FLAG_SHORT_GI) + ri.flags |= RATE_INFO_FLAGS_SHORT_GI; + } else if (status->flag & RX_FLAG_VHT) { + ri.flags |= RATE_INFO_FLAGS_VHT_MCS; + ri.mcs = status->rate_idx; + ri.nss = status->vht_nss; + if (status->flag & RX_FLAG_40MHZ) + ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH; + if (status->flag & RX_FLAG_80MHZ) + ri.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH; + if (status->flag & RX_FLAG_80P80MHZ) + ri.flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH; + if (status->flag & RX_FLAG_160MHZ) + ri.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH; + if (status->flag & RX_FLAG_SHORT_GI) + ri.flags |= RATE_INFO_FLAGS_SHORT_GI; + } else { + struct ieee80211_supported_band *sband; + + sband = local->hw.wiphy->bands[status->band]; + ri.legacy = sband->bitrates[status->rate_idx].bitrate; + } + + rate = cfg80211_calculate_bitrate(&ri); + + /* rewind from end of MPDU */ + if (status->flag & RX_FLAG_MACTIME_END) + ts -= mpdu_len * 8 * 10 / rate; + + ts += mpdu_offset * 8 * 10 / rate; + + return ts; +} diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c new file mode 100644 index 000000000000..f311388aeedf --- /dev/null +++ b/net/mac80211/vht.c @@ -0,0 +1,35 @@ +/* + * VHT handling + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/ieee80211.h> +#include <linux/export.h> +#include <net/mac80211.h> +#include "ieee80211_i.h" + + +void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct ieee80211_vht_cap *vht_cap_ie, + struct ieee80211_sta_vht_cap *vht_cap) +{ + if (WARN_ON_ONCE(!vht_cap)) + return; + + memset(vht_cap, 0, sizeof(*vht_cap)); + + if (!vht_cap_ie || !sband->vht_cap.vht_supported) + return; + + vht_cap->vht_supported = true; + + vht_cap->cap = le32_to_cpu(vht_cap_ie->vht_cap_info); + + /* Copy peer MCS info, the driver might need them. */ + memcpy(&vht_cap->vht_mcs, &vht_cap_ie->supp_mcs, + sizeof(struct ieee80211_vht_mcs_info)); +} diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index cea06e9f26f4..906f00cd6d2f 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -160,31 +160,37 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, return ieee80211_downgrade_queue(sdata, skb); } +/** + * ieee80211_set_qos_hdr - Fill in the QoS header if there is one. + * + * @sdata: local subif + * @skb: packet to be updated + */ void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + u8 *p; + u8 ack_policy, tid; - /* Fill in the QoS header if there is one. */ - if (ieee80211_is_data_qos(hdr->frame_control)) { - u8 *p = ieee80211_get_qos_ctl(hdr); - u8 ack_policy, tid; - - tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + if (!ieee80211_is_data_qos(hdr->frame_control)) + return; - /* preserve EOSP bit */ - ack_policy = *p & IEEE80211_QOS_CTL_EOSP; + p = ieee80211_get_qos_ctl(hdr); + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; - if (is_multicast_ether_addr(hdr->addr1) || - sdata->noack_map & BIT(tid)) { - ack_policy |= IEEE80211_QOS_CTL_ACK_POLICY_NOACK; - info->flags |= IEEE80211_TX_CTL_NO_ACK; - } + /* preserve EOSP bit */ + ack_policy = *p & IEEE80211_QOS_CTL_EOSP; - /* qos header is 2 bytes */ - *p++ = ack_policy | tid; - *p = ieee80211_vif_is_mesh(&sdata->vif) ? - (IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT >> 8) : 0; + if (is_multicast_ether_addr(hdr->addr1) || + sdata->noack_map & BIT(tid)) { + ack_policy |= IEEE80211_QOS_CTL_ACK_POLICY_NOACK; + info->flags |= IEEE80211_TX_CTL_NO_ACK; } + + /* qos header is 2 bytes */ + *p++ = ack_policy | tid; + *p = ieee80211_vif_is_mesh(&sdata->vif) ? + (IEEE80211_QOS_CTL_MESH_CONTROL_PRESENT >> 8) : 0; } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 8bd2f5c6a56e..c175ee866ff4 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -104,7 +104,7 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) */ if (status->flag & (RX_FLAG_MMIC_STRIPPED | RX_FLAG_IV_STRIPPED)) { if (status->flag & RX_FLAG_MMIC_ERROR) - goto mic_fail; + goto mic_fail_no_key; if (!(status->flag & RX_FLAG_IV_STRIPPED) && rx->key && rx->key->conf.cipher == WLAN_CIPHER_SUITE_TKIP) @@ -161,6 +161,9 @@ update_iv: return RX_CONTINUE; mic_fail: + rx->key->u.tkip.mic_failures++; + +mic_fail_no_key: /* * In some cases the key can be unset - e.g. a multicast packet, in * a driver that supports HW encryption. Send up the key idx only if diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index e748aed290aa..b7c7f815deae 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -224,9 +224,9 @@ void ieee802154_free_device(struct ieee802154_dev *hw) BUG_ON(!list_empty(&priv->slaves)); - wpan_phy_free(priv->phy); - mutex_destroy(&priv->slaves_mtx); + + wpan_phy_free(priv->phy); } EXPORT_SYMBOL(ieee802154_free_device); diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 1a4df39c722e..4e09d070995a 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -85,6 +85,7 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, if (!(priv->phy->channels_supported[page] & (1 << chan))) { WARN_ON(1); + kfree_skb(skb); return NETDEV_TX_OK; } @@ -98,13 +99,15 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, } if (skb_cow_head(skb, priv->hw.extra_tx_headroom)) { - dev_kfree_skb(skb); + kfree_skb(skb); return NETDEV_TX_OK; } work = kzalloc(sizeof(struct xmit_work), GFP_ATOMIC); - if (!work) + if (!work) { + kfree_skb(skb); return NETDEV_TX_BUSY; + } INIT_WORK(&work->work, mac802154_xmit_worker); work->skb = skb; diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index f30f6d4beea1..199b92261e94 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -327,8 +327,10 @@ mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev) if (chan == MAC802154_CHAN_NONE || page >= WPAN_NUM_PAGES || - chan >= WPAN_NUM_CHANNELS) + chan >= WPAN_NUM_CHANNELS) { + kfree_skb(skb); return NETDEV_TX_OK; + } skb->skb_iif = dev->ifindex; dev->stats.tx_packets++; @@ -387,7 +389,7 @@ void mac802154_wpan_setup(struct net_device *dev) static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) { - return netif_rx(skb); + return netif_rx_ni(skb); } static int diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index fefa514b9917..49e96df5fbc4 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -680,6 +680,13 @@ config NETFILTER_XT_TARGET_NFQUEUE To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_TARGET_NOTRACK + tristate '"NOTRACK" target support (DEPRECATED)' + depends on NF_CONNTRACK + depends on IP_NF_RAW || IP6_NF_RAW + depends on NETFILTER_ADVANCED + select NETFILTER_XT_TARGET_CT + config NETFILTER_XT_TARGET_RATEEST tristate '"RATEEST" target support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 68912dadf13d..a9c488b6c50d 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -295,8 +295,6 @@ void __init netfilter_init(void) panic("cannot create netfilter proc entry"); #endif - if (netfilter_queue_init() < 0) - panic("cannot initialize nf_queue"); if (netfilter_log_init() < 0) panic("cannot initialize nf_log"); } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 778465f217fa..6d6d8f2b033e 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -28,9 +28,10 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */ static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */ static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */ -static struct ip_set **ip_set_list; /* all individual sets */ +static struct ip_set * __rcu *ip_set_list; /* all individual sets */ static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */ +#define IP_SET_INC 64 #define STREQ(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0) static unsigned int max_sets; @@ -42,6 +43,12 @@ MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); +/* When the nfnl mutex is held: */ +#define nfnl_dereference(p) \ + rcu_dereference_protected(p, 1) +#define nfnl_set(id) \ + nfnl_dereference(ip_set_list)[id] + /* * The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -321,19 +328,19 @@ EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); */ static inline void -__ip_set_get(ip_set_id_t index) +__ip_set_get(struct ip_set *set) { write_lock_bh(&ip_set_ref_lock); - ip_set_list[index]->ref++; + set->ref++; write_unlock_bh(&ip_set_ref_lock); } static inline void -__ip_set_put(ip_set_id_t index) +__ip_set_put(struct ip_set *set) { write_lock_bh(&ip_set_ref_lock); - BUG_ON(ip_set_list[index]->ref == 0); - ip_set_list[index]->ref--; + BUG_ON(set->ref == 0); + set->ref--; write_unlock_bh(&ip_set_ref_lock); } @@ -344,12 +351,25 @@ __ip_set_put(ip_set_id_t index) * so it can't be destroyed (or changed) under our foot. */ +static inline struct ip_set * +ip_set_rcu_get(ip_set_id_t index) +{ + struct ip_set *set; + + rcu_read_lock(); + /* ip_set_list itself needs to be protected */ + set = rcu_dereference(ip_set_list)[index]; + rcu_read_unlock(); + + return set; +} + int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, const struct ip_set_adt_opt *opt) { - struct ip_set *set = ip_set_list[index]; + struct ip_set *set = ip_set_rcu_get(index); int ret = 0; BUG_ON(set == NULL); @@ -388,7 +408,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, const struct ip_set_adt_opt *opt) { - struct ip_set *set = ip_set_list[index]; + struct ip_set *set = ip_set_rcu_get(index); int ret; BUG_ON(set == NULL); @@ -411,7 +431,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, const struct ip_set_adt_opt *opt) { - struct ip_set *set = ip_set_list[index]; + struct ip_set *set = ip_set_rcu_get(index); int ret = 0; BUG_ON(set == NULL); @@ -440,14 +460,17 @@ ip_set_get_byname(const char *name, struct ip_set **set) ip_set_id_t i, index = IPSET_INVALID_ID; struct ip_set *s; + rcu_read_lock(); for (i = 0; i < ip_set_max; i++) { - s = ip_set_list[i]; + s = rcu_dereference(ip_set_list)[i]; if (s != NULL && STREQ(s->name, name)) { - __ip_set_get(i); + __ip_set_get(s); index = i; *set = s; + break; } } + rcu_read_unlock(); return index; } @@ -462,8 +485,13 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname); void ip_set_put_byindex(ip_set_id_t index) { - if (ip_set_list[index] != NULL) - __ip_set_put(index); + struct ip_set *set; + + rcu_read_lock(); + set = rcu_dereference(ip_set_list)[index]; + if (set != NULL) + __ip_set_put(set); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ip_set_put_byindex); @@ -477,7 +505,7 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex); const char * ip_set_name_byindex(ip_set_id_t index) { - const struct ip_set *set = ip_set_list[index]; + const struct ip_set *set = ip_set_rcu_get(index); BUG_ON(set == NULL); BUG_ON(set->ref == 0); @@ -501,11 +529,18 @@ EXPORT_SYMBOL_GPL(ip_set_name_byindex); ip_set_id_t ip_set_nfnl_get(const char *name) { + ip_set_id_t i, index = IPSET_INVALID_ID; struct ip_set *s; - ip_set_id_t index; nfnl_lock(); - index = ip_set_get_byname(name, &s); + for (i = 0; i < ip_set_max; i++) { + s = nfnl_set(i); + if (s != NULL && STREQ(s->name, name)) { + __ip_set_get(s); + index = i; + break; + } + } nfnl_unlock(); return index; @@ -521,12 +556,15 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_get); ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index) { + struct ip_set *set; + if (index > ip_set_max) return IPSET_INVALID_ID; nfnl_lock(); - if (ip_set_list[index]) - __ip_set_get(index); + set = nfnl_set(index); + if (set) + __ip_set_get(set); else index = IPSET_INVALID_ID; nfnl_unlock(); @@ -545,8 +583,11 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_get_byindex); void ip_set_nfnl_put(ip_set_id_t index) { + struct ip_set *set; nfnl_lock(); - ip_set_put_byindex(index); + set = nfnl_set(index); + if (set != NULL) + __ip_set_put(set); nfnl_unlock(); } EXPORT_SYMBOL_GPL(ip_set_nfnl_put); @@ -603,41 +644,46 @@ static const struct nla_policy ip_set_create_policy[IPSET_ATTR_CMD_MAX + 1] = { [IPSET_ATTR_DATA] = { .type = NLA_NESTED }, }; -static ip_set_id_t -find_set_id(const char *name) +static struct ip_set * +find_set_and_id(const char *name, ip_set_id_t *id) { - ip_set_id_t i, index = IPSET_INVALID_ID; - const struct ip_set *set; + struct ip_set *set = NULL; + ip_set_id_t i; - for (i = 0; index == IPSET_INVALID_ID && i < ip_set_max; i++) { - set = ip_set_list[i]; - if (set != NULL && STREQ(set->name, name)) - index = i; + *id = IPSET_INVALID_ID; + for (i = 0; i < ip_set_max; i++) { + set = nfnl_set(i); + if (set != NULL && STREQ(set->name, name)) { + *id = i; + break; + } } - return index; + return (*id == IPSET_INVALID_ID ? NULL : set); } static inline struct ip_set * find_set(const char *name) { - ip_set_id_t index = find_set_id(name); + ip_set_id_t id; - return index == IPSET_INVALID_ID ? NULL : ip_set_list[index]; + return find_set_and_id(name, &id); } static int find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set) { + struct ip_set *s; ip_set_id_t i; *index = IPSET_INVALID_ID; for (i = 0; i < ip_set_max; i++) { - if (ip_set_list[i] == NULL) { + s = nfnl_set(i); + if (s == NULL) { if (*index == IPSET_INVALID_ID) *index = i; - } else if (STREQ(name, ip_set_list[i]->name)) { + } else if (STREQ(name, s->name)) { /* Name clash */ - *set = ip_set_list[i]; + *set = s; return -EEXIST; } } @@ -730,10 +776,9 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, * and check clashing. */ ret = find_free_id(set->name, &index, &clash); - if (ret != 0) { + if (ret == -EEXIST) { /* If this is the same set and requested, ignore error */ - if (ret == -EEXIST && - (flags & IPSET_FLAG_EXIST) && + if ((flags & IPSET_FLAG_EXIST) && STREQ(set->type->name, clash->type->name) && set->type->family == clash->type->family && set->type->revision_min == clash->type->revision_min && @@ -741,13 +786,36 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, set->variant->same_set(set, clash)) ret = 0; goto cleanup; - } + } else if (ret == -IPSET_ERR_MAX_SETS) { + struct ip_set **list, **tmp; + ip_set_id_t i = ip_set_max + IP_SET_INC; + + if (i < ip_set_max || i == IPSET_INVALID_ID) + /* Wraparound */ + goto cleanup; + + list = kzalloc(sizeof(struct ip_set *) * i, GFP_KERNEL); + if (!list) + goto cleanup; + /* nfnl mutex is held, both lists are valid */ + tmp = nfnl_dereference(ip_set_list); + memcpy(list, tmp, sizeof(struct ip_set *) * ip_set_max); + rcu_assign_pointer(ip_set_list, list); + /* Make sure all current packets have passed through */ + synchronize_net(); + /* Use new list */ + index = ip_set_max; + ip_set_max = i; + kfree(tmp); + ret = 0; + } else if (ret) + goto cleanup; /* * Finally! Add our shiny new set to the list, and be done. */ pr_debug("create: '%s' created with index %u!\n", set->name, index); - ip_set_list[index] = set; + nfnl_set(index) = set; return ret; @@ -772,10 +840,10 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { static void ip_set_destroy_set(ip_set_id_t index) { - struct ip_set *set = ip_set_list[index]; + struct ip_set *set = nfnl_set(index); pr_debug("set: %s\n", set->name); - ip_set_list[index] = NULL; + nfnl_set(index) = NULL; /* Must call it without holding any lock */ set->variant->destroy(set); @@ -788,6 +856,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[]) { + struct ip_set *s; ip_set_id_t i; int ret = 0; @@ -807,22 +876,24 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) { - if (ip_set_list[i] != NULL && ip_set_list[i]->ref) { + s = nfnl_set(i); + if (s != NULL && s->ref) { ret = -IPSET_ERR_BUSY; goto out; } } read_unlock_bh(&ip_set_ref_lock); for (i = 0; i < ip_set_max; i++) { - if (ip_set_list[i] != NULL) + s = nfnl_set(i); + if (s != NULL) ip_set_destroy_set(i); } } else { - i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); - if (i == IPSET_INVALID_ID) { + s = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &i); + if (s == NULL) { ret = -ENOENT; goto out; - } else if (ip_set_list[i]->ref) { + } else if (s->ref) { ret = -IPSET_ERR_BUSY; goto out; } @@ -853,21 +924,24 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[]) { + struct ip_set *s; ip_set_id_t i; if (unlikely(protocol_failed(attr))) return -IPSET_ERR_PROTOCOL; if (!attr[IPSET_ATTR_SETNAME]) { - for (i = 0; i < ip_set_max; i++) - if (ip_set_list[i] != NULL) - ip_set_flush_set(ip_set_list[i]); + for (i = 0; i < ip_set_max; i++) { + s = nfnl_set(i); + if (s != NULL) + ip_set_flush_set(s); + } } else { - i = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); - if (i == IPSET_INVALID_ID) + s = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); + if (s == NULL) return -ENOENT; - ip_set_flush_set(ip_set_list[i]); + ip_set_flush_set(s); } return 0; @@ -889,7 +963,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[]) { - struct ip_set *set; + struct ip_set *set, *s; const char *name2; ip_set_id_t i; int ret = 0; @@ -911,8 +985,8 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < ip_set_max; i++) { - if (ip_set_list[i] != NULL && - STREQ(ip_set_list[i]->name, name2)) { + s = nfnl_set(i); + if (s != NULL && STREQ(s->name, name2)) { ret = -IPSET_ERR_EXIST_SETNAME2; goto out; } @@ -947,17 +1021,14 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, attr[IPSET_ATTR_SETNAME2] == NULL)) return -IPSET_ERR_PROTOCOL; - from_id = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); - if (from_id == IPSET_INVALID_ID) + from = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &from_id); + if (from == NULL) return -ENOENT; - to_id = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME2])); - if (to_id == IPSET_INVALID_ID) + to = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME2]), &to_id); + if (to == NULL) return -IPSET_ERR_EXIST_SETNAME2; - from = ip_set_list[from_id]; - to = ip_set_list[to_id]; - /* Features must not change. * Not an artificial restriction anymore, as we must prevent * possible loops created by swapping in setlist type of sets. */ @@ -971,8 +1042,8 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, write_lock_bh(&ip_set_ref_lock); swap(from->ref, to->ref); - ip_set_list[from_id] = to; - ip_set_list[to_id] = from; + nfnl_set(from_id) = to; + nfnl_set(to_id) = from; write_unlock_bh(&ip_set_ref_lock); return 0; @@ -992,7 +1063,7 @@ static int ip_set_dump_done(struct netlink_callback *cb) { if (cb->args[2]) { - pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name); + pr_debug("release set %s\n", nfnl_set(cb->args[1])->name); ip_set_put_byindex((ip_set_id_t) cb->args[1]); } return 0; @@ -1030,8 +1101,11 @@ dump_init(struct netlink_callback *cb) */ if (cda[IPSET_ATTR_SETNAME]) { - index = find_set_id(nla_data(cda[IPSET_ATTR_SETNAME])); - if (index == IPSET_INVALID_ID) + struct ip_set *set; + + set = find_set_and_id(nla_data(cda[IPSET_ATTR_SETNAME]), + &index); + if (set == NULL) return -ENOENT; dump_type = DUMP_ONE; @@ -1081,7 +1155,7 @@ dump_last: dump_type, dump_flags, cb->args[1]); for (; cb->args[1] < max; cb->args[1]++) { index = (ip_set_id_t) cb->args[1]; - set = ip_set_list[index]; + set = nfnl_set(index); if (set == NULL) { if (dump_type == DUMP_ONE) { ret = -ENOENT; @@ -1100,7 +1174,7 @@ dump_last: if (!cb->args[2]) { /* Start listing: make sure set won't be destroyed */ pr_debug("reference set\n"); - __ip_set_get(index); + __ip_set_get(set); } nlh = start_msg(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, @@ -1159,7 +1233,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[2]) { - pr_debug("release set %s\n", ip_set_list[index]->name); + pr_debug("release set %s\n", nfnl_set(index)->name); ip_set_put_byindex(index); cb->args[2] = 0; } @@ -1409,17 +1483,15 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, const struct ip_set *set; struct sk_buff *skb2; struct nlmsghdr *nlh2; - ip_set_id_t index; int ret = 0; if (unlikely(protocol_failed(attr) || attr[IPSET_ATTR_SETNAME] == NULL)) return -IPSET_ERR_PROTOCOL; - index = find_set_id(nla_data(attr[IPSET_ATTR_SETNAME])); - if (index == IPSET_INVALID_ID) + set = find_set(nla_data(attr[IPSET_ATTR_SETNAME])); + if (set == NULL) return -ENOENT; - set = ip_set_list[index]; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) @@ -1643,7 +1715,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) void *data; int copylen = *len, ret = 0; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (optval != SO_IP_SET) return -EBADF; @@ -1684,6 +1756,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } case IP_SET_OP_GET_BYNAME: { struct ip_set_req_get_set *req_get = data; + ip_set_id_t id; if (*len != sizeof(struct ip_set_req_get_set)) { ret = -EINVAL; @@ -1691,12 +1764,14 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0'; nfnl_lock(); - req_get->set.index = find_set_id(req_get->set.name); + find_set_and_id(req_get->set.name, &id); + req_get->set.index = id; nfnl_unlock(); goto copy; } case IP_SET_OP_GET_BYINDEX: { struct ip_set_req_get_set *req_get = data; + struct ip_set *set; if (*len != sizeof(struct ip_set_req_get_set) || req_get->set.index >= ip_set_max) { @@ -1704,9 +1779,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) goto done; } nfnl_lock(); - strncpy(req_get->set.name, - ip_set_list[req_get->set.index] - ? ip_set_list[req_get->set.index]->name : "", + set = nfnl_set(req_get->set.index); + strncpy(req_get->set.name, set ? set->name : "", IPSET_MAXNAMELEN); nfnl_unlock(); goto copy; @@ -1737,6 +1811,7 @@ static struct nf_sockopt_ops so_set __read_mostly = { static int __init ip_set_init(void) { + struct ip_set **list; int ret; if (max_sets) @@ -1744,22 +1819,22 @@ ip_set_init(void) if (ip_set_max >= IPSET_INVALID_ID) ip_set_max = IPSET_INVALID_ID - 1; - ip_set_list = kzalloc(sizeof(struct ip_set *) * ip_set_max, - GFP_KERNEL); - if (!ip_set_list) + list = kzalloc(sizeof(struct ip_set *) * ip_set_max, GFP_KERNEL); + if (!list) return -ENOMEM; + rcu_assign_pointer(ip_set_list, list); ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); if (ret != 0) { pr_err("ip_set: cannot register with nfnetlink.\n"); - kfree(ip_set_list); + kfree(list); return ret; } ret = nf_register_sockopt(&so_set); if (ret != 0) { pr_err("SO_SET registry failed: %d\n", ret); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - kfree(ip_set_list); + kfree(list); return ret; } @@ -1770,10 +1845,12 @@ ip_set_init(void) static void __exit ip_set_fini(void) { + struct ip_set **list = rcu_dereference_protected(ip_set_list, 1); + /* There can't be any existing set */ nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - kfree(ip_set_list); + kfree(list); pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index ec3dba5dcd62..5c0b78528e55 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -173,6 +173,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], return adtfn(set, &nip, timeout, flags); } + ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) @@ -185,8 +186,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); - } else - ip_to = ip; + } hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 0171f7502fa5..6283351f4eeb 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -162,7 +162,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem data = { }; - u32 ip, ip_to = 0, p = 0, port, port_to; + u32 ip, ip_to, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; @@ -210,7 +210,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], return ip_set_eexist(ret, flags) ? 0 : ret; } - ip = ntohl(data.ip); + ip_to = ip = ntohl(data.ip); if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) @@ -223,8 +223,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); - } else - ip_to = ip; + } port_to = port = ntohs(data.port); if (with_ports && tb[IPSET_ATTR_PORT_TO]) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 6344ef551ec8..6a21271c8d5a 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -166,7 +166,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem data = { }; - u32 ip, ip_to = 0, p = 0, port, port_to; + u32 ip, ip_to, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; @@ -218,7 +218,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], return ip_set_eexist(ret, flags) ? 0 : ret; } - ip = ntohl(data.ip); + ip_to = ip = ntohl(data.ip); if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) @@ -231,8 +231,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (!cidr || cidr > 32) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); - } else - ip_to = ip; + } port_to = port = ntohs(data.port); if (with_ports && tb[IPSET_ATTR_PORT_TO]) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index cb71f9a774e7..2d5cd4ee30eb 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -215,8 +215,8 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem data = { .cidr = HOST_MASK - 1 }; - u32 ip, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to, ip2_last, ip2; + u32 ip, ip_to, p = 0, port, port_to; + u32 ip2_from, ip2_to, ip2_last, ip2; u32 timeout = h->timeout; bool with_ports = false; u8 cidr; @@ -286,6 +286,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], return ip_set_eexist(ret, flags) ? 0 : ret; } + ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) @@ -306,6 +307,8 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (port > port_to) swap(port, port_to); } + + ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); if (ret) diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index b9a63381e349..45a101439bc5 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -793,7 +793,7 @@ static struct ip_set_type hash_netiface_type __read_mostly = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_IFACE] = { .type = NLA_NUL_STRING, - .len = IPSET_MAXNAMELEN - 1 }, + .len = IFNAMSIZ - 1 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 8b2cffdfdd99..0c3b1670b0d1 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -28,12 +28,11 @@ if IP_VS config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 + select IP6_NF_IPTABLES ---help--- - Add IPv6 support to IPVS. This is incomplete and might be dangerous. + Add IPv6 support to IPVS. - See http://www.mindbasket.com/ipvs for more information. - - Say N if unsure. + Say Y if unsure. config IP_VS_DEBUG bool "IP virtual server debugging" diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 1548df9a7524..30e764ad021f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -308,13 +308,12 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p) static int ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, - unsigned int proto_off, int inverse, - struct ip_vs_conn_param *p) + int inverse, struct ip_vs_conn_param *p) { __be16 _ports[2], *pptr; struct net *net = skb_net(skb); - pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); + pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph); if (pptr == NULL) return 1; @@ -329,12 +328,11 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - unsigned int proto_off, int inverse) + const struct ip_vs_iphdr *iph, int inverse) { struct ip_vs_conn_param p; - if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p)) + if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p)) return NULL; return ip_vs_conn_in_get(&p); @@ -432,12 +430,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - unsigned int proto_off, int inverse) + const struct ip_vs_iphdr *iph, int inverse) { struct ip_vs_conn_param p; - if (ip_vs_conn_fill_param_proto(af, skb, iph, proto_off, inverse, &p)) + if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p)) return NULL; return ip_vs_conn_out_get(&p); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 58918e20f9d5..47edf5a40a59 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -222,11 +222,10 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, */ static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, - struct sk_buff *skb, - __be16 src_port, __be16 dst_port, int *ignored) + struct sk_buff *skb, __be16 src_port, __be16 dst_port, + int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp = NULL; - struct ip_vs_iphdr iph; struct ip_vs_dest *dest; struct ip_vs_conn *ct; __be16 dport = 0; /* destination port to forward */ @@ -236,20 +235,18 @@ ip_vs_sched_persist(struct ip_vs_service *svc, union nf_inet_addr snet; /* source network of the client, after masking */ - ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); - /* Mask saddr with the netmask to adjust template granularity */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) - ipv6_addr_prefix(&snet.in6, &iph.saddr.in6, svc->netmask); + ipv6_addr_prefix(&snet.in6, &iph->saddr.in6, svc->netmask); else #endif - snet.ip = iph.saddr.ip & svc->netmask; + snet.ip = iph->saddr.ip & svc->netmask; IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", - IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port), - IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port), + IP_VS_DBG_ADDR(svc->af, &iph->saddr), ntohs(src_port), + IP_VS_DBG_ADDR(svc->af, &iph->daddr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* @@ -266,8 +263,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * is created for other persistent services. */ { - int protocol = iph.protocol; - const union nf_inet_addr *vaddr = &iph.daddr; + int protocol = iph->protocol; + const union nf_inet_addr *vaddr = &iph->daddr; __be16 vport = 0; if (dst_port == svc->port) { @@ -342,14 +339,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc, dport = dest->port; flags = (svc->flags & IP_VS_SVC_F_ONEPACKET - && iph.protocol == IPPROTO_UDP)? + && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a new connection according to the template */ - ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr, - src_port, &iph.daddr, dst_port, ¶m); + ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr, + src_port, &iph->daddr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { @@ -392,18 +389,20 @@ ip_vs_sched_persist(struct ip_vs_service *svc, */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_proto_data *pd, int *ignored) + struct ip_vs_proto_data *pd, int *ignored, + struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; - struct ip_vs_iphdr iph; struct ip_vs_dest *dest; __be16 _ports[2], *pptr; unsigned int flags; *ignored = 1; - ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); - pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); + /* + * IPv6 frags, only the first hit here. + */ + pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph); if (pptr == NULL) return NULL; @@ -423,7 +422,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && - (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) { + (cp = pp->conn_in_get(svc->af, skb, iph, 1))) { IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, "Not scheduling reply for existing connection"); __ip_vs_conn_put(cp); @@ -434,7 +433,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, * Persistent service */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) - return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored); + return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored, + iph); *ignored = 0; @@ -456,7 +456,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } flags = (svc->flags & IP_VS_SVC_F_ONEPACKET - && iph.protocol == IPPROTO_UDP)? + && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* @@ -465,9 +465,9 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, - &iph.saddr, pptr[0], &iph.daddr, pptr[1], - &p); + ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, + &iph->saddr, pptr[0], &iph->daddr, + pptr[1], &p); cp = ip_vs_conn_new(&p, &dest->addr, dest->port ? dest->port : pptr[1], flags, dest, skb->mark); @@ -496,19 +496,16 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { __be16 _ports[2], *pptr; - struct ip_vs_iphdr iph; #ifdef CONFIG_SYSCTL struct net *net; struct netns_ipvs *ipvs; int unicast; #endif - ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); - - pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); + pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph); if (pptr == NULL) { ip_vs_service_put(svc); return NF_DROP; @@ -519,10 +516,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) - unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST; + unicast = ipv6_addr_type(&iph->daddr.in6) & IPV6_ADDR_UNICAST; else #endif - unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST); + unicast = (inet_addr_type(net, iph->daddr.ip) == RTN_UNICAST); /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create @@ -532,7 +529,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && - iph.protocol == IPPROTO_UDP)? + iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; @@ -542,9 +539,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, - &iph.saddr, pptr[0], - &iph.daddr, pptr[1], &p); + ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, + &iph->saddr, pptr[0], + &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, NULL, skb->mark); @@ -559,7 +556,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ - ret = cp->packet_xmit(skb, cp, pd->pp); + ret = cp->packet_xmit(skb, cp, pd->pp, iph); /* do not touch skb anymore */ atomic_inc(&cp->in_pkts); @@ -654,14 +651,6 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } -#ifdef CONFIG_IP_VS_IPV6 -static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user) -{ - /* TODO IPv6: Find out what to do here for IPv6 */ - return 0; -} -#endif - static int ip_vs_route_me_harder(int af, struct sk_buff *skb) { #ifdef CONFIG_IP_VS_IPV6 @@ -732,10 +721,19 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct ipv6hdr *iph = ipv6_hdr(skb); - unsigned int icmp_offset = sizeof(struct ipv6hdr); - struct icmp6hdr *icmph = (struct icmp6hdr *)(skb_network_header(skb) + - icmp_offset); - struct ipv6hdr *ciph = (struct ipv6hdr *)(icmph + 1); + unsigned int icmp_offset = 0; + unsigned int offs = 0; /* header offset*/ + int protocol; + struct icmp6hdr *icmph; + struct ipv6hdr *ciph; + unsigned short fragoffs; + + ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); + icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); + offs = icmp_offset + sizeof(struct icmp6hdr); + ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); + + protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); if (inout) { iph->saddr = cp->vaddr.in6; @@ -746,10 +744,13 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, } /* the TCP/UDP/SCTP port */ - if (IPPROTO_TCP == ciph->nexthdr || IPPROTO_UDP == ciph->nexthdr || - IPPROTO_SCTP == ciph->nexthdr) { - __be16 *ports = (void *)ciph + sizeof(struct ipv6hdr); + if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || + IPPROTO_SCTP == protocol)) { + __be16 *ports = (void *)(skb_network_header(skb) + offs); + IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, + ntohs(inout ? ports[1] : ports[0]), + ntohs(inout ? cp->vport : cp->dport)); if (inout) ports[1] = cp->vport; else @@ -898,51 +899,35 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - offset += cih->ihl * 4; - - ip_vs_fill_iphdr(AF_INET, cih, &ciph); + ip_vs_fill_ip4hdr(cih, &ciph); + ciph.len += offset; /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET, skb, &ciph, 1); if (!cp) return NF_ACCEPT; snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, offset, ihl); + pp, ciph.len, ihl); } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, - unsigned int hooknum) + unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { - struct ipv6hdr *iph; struct icmp6hdr _icmph, *ic; - struct ipv6hdr _ciph, *cih; /* The ip header contained - within the ICMP */ - struct ip_vs_iphdr ciph; + struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */ + struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; - unsigned int offset; union nf_inet_addr snet; + unsigned int writable; *related = 1; - - /* reassemble IP fragments */ - if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { - if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum))) - return NF_STOLEN; - } - - iph = ipv6_hdr(skb); - offset = sizeof(struct ipv6hdr); - ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); + ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh); if (ic == NULL) return NF_DROP; - IP_VS_DBG(12, "Outgoing ICMPv6 (%d,%d) %pI6->%pI6\n", - ic->icmp6_type, ntohs(icmpv6_id(ic)), - &iph->saddr, &iph->daddr); - /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy @@ -950,42 +935,45 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ - if ((ic->icmp6_type != ICMPV6_DEST_UNREACH) && - (ic->icmp6_type != ICMPV6_PKT_TOOBIG) && - (ic->icmp6_type != ICMPV6_TIME_EXCEED)) { + if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } + /* Fragment header that is before ICMP header tells us that: + * it's not an error message since they can't be fragmented. + */ + if (ipvsh->flags & IP6_FH_F_FRAG) + return NF_DROP; + + IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n", + ic->icmp6_type, ntohs(icmpv6_id(ic)), + &ipvsh->saddr, &ipvsh->daddr); /* Now find the contained IP header */ - offset += sizeof(_icmph); - cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + ciph.len = ipvsh->len + sizeof(_icmph); + ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h); + if (ip6h == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ - - pp = ip_vs_proto_get(cih->nexthdr); + ciph.saddr.in6 = ip6h->saddr; /* conn_out_get() handles reverse order */ + ciph.daddr.in6 = ip6h->daddr; + /* skip possible IPv6 exthdrs of contained IPv6 packet */ + ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL); + if (ciph.protocol < 0) + return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */ + + pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; - /* Is the embedded protocol header present? */ - /* TODO: we don't support fragmentation at the moment anyways */ - if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag)) - return NF_ACCEPT; - - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, - "Checking outgoing ICMPv6 for"); - - offset += sizeof(struct ipv6hdr); - - ip_vs_fill_iphdr(AF_INET6, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET6, skb, &ciph, 1); if (!cp) return NF_ACCEPT; - snet.in6 = iph->saddr; - return handle_response_icmp(AF_INET6, skb, &snet, cih->nexthdr, cp, - pp, offset, sizeof(struct ipv6hdr)); + snet.in6 = ciph.saddr.in6; + writable = ciph.len; + return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, + pp, writable, sizeof(struct ipv6hdr)); } #endif @@ -1018,17 +1006,17 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - struct ip_vs_conn *cp, int ihl) + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet"); - if (!skb_make_writable(skb, ihl)) + if (!skb_make_writable(skb, iph->len)) goto drop; /* mangle the packet */ - if (pp->snat_handler && !pp->snat_handler(skb, pp, cp)) + if (pp->snat_handler && !pp->snat_handler(skb, pp, cp, iph)) goto drop; #ifdef CONFIG_IP_VS_IPV6 @@ -1115,17 +1103,22 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) if (!net_ipvs(net)->enable) return NF_ACCEPT; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + ip_vs_fill_iph_skb(af, skb, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { + if (!iph.fragoffs && skb_nfct_reasm(skb)) { + struct sk_buff *reasm = skb_nfct_reasm(skb); + /* Save fw mark for coming frags */ + reasm->ipvs_property = 1; + reasm->mark = skb->mark; + } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(skb, &related, - hooknum); + hooknum, &iph); if (related) return verdict; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } } else #endif @@ -1135,7 +1128,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) if (related) return verdict; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } pd = ip_vs_proto_data_get(net, iph.protocol); @@ -1145,39 +1137,31 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { - if (ip_vs_gather_frags_v6(skb, - ip_vs_defrag_user(hooknum))) - return NF_STOLEN; - } - - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); - } else + if (af == AF_INET) #endif if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + ip_vs_fill_ip4hdr(skb_network_header(skb), &iph); } /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(af, skb, &iph, iph.len, 0); + cp = pp->conn_out_get(af, skb, &iph, 0); if (likely(cp)) - return handle_response(af, skb, pd, cp, iph.len); + return handle_response(af, skb, pd, cp, &iph); if (sysctl_nat_icmp_send(net) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { __be16 _ports[2], *pptr; - pptr = skb_header_pointer(skb, iph.len, - sizeof(_ports), _ports); + pptr = frag_safe_skb_hp(skb, iph.len, + sizeof(_ports), _ports, &iph); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ if (ip_vs_lookup_real_service(net, af, iph.protocol, @@ -1375,13 +1359,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) "Checking incoming ICMP for"); offset2 = offset; - offset += cih->ihl * 4; - - ip_vs_fill_iphdr(AF_INET, cih, &ciph); + ip_vs_fill_ip4hdr(cih, &ciph); + ciph.len += offset; + offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP this is error for request, not for reply. */ - cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1); + cp = pp->conn_in_get(AF_INET, skb, &ciph, ipip ? 0 : 1); if (!cp) return NF_ACCEPT; @@ -1450,7 +1434,7 @@ ignore_ipip: ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol) offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum); + verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); out: __ip_vs_conn_put(cp); @@ -1459,38 +1443,24 @@ out: } #ifdef CONFIG_IP_VS_IPV6 -static int -ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) +static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, + unsigned int hooknum, struct ip_vs_iphdr *iph) { struct net *net = NULL; - struct ipv6hdr *iph; + struct ipv6hdr _ip6h, *ip6h; struct icmp6hdr _icmph, *ic; - struct ipv6hdr _ciph, *cih; /* The ip header contained - within the ICMP */ - struct ip_vs_iphdr ciph; + struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; - unsigned int offset, verdict; + unsigned int offs_ciph, writable, verdict; *related = 1; - /* reassemble IP fragments */ - if (ipv6_hdr(skb)->nexthdr == IPPROTO_FRAGMENT) { - if (ip_vs_gather_frags_v6(skb, ip_vs_defrag_user(hooknum))) - return NF_STOLEN; - } - - iph = ipv6_hdr(skb); - offset = sizeof(struct ipv6hdr); - ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); + ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph, iph); if (ic == NULL) return NF_DROP; - IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) %pI6->%pI6\n", - ic->icmp6_type, ntohs(icmpv6_id(ic)), - &iph->saddr, &iph->daddr); - /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy @@ -1498,47 +1468,71 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ - if ((ic->icmp6_type != ICMPV6_DEST_UNREACH) && - (ic->icmp6_type != ICMPV6_PKT_TOOBIG) && - (ic->icmp6_type != ICMPV6_TIME_EXCEED)) { + if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } + /* Fragment header that is before ICMP header tells us that: + * it's not an error message since they can't be fragmented. + */ + if (iph->flags & IP6_FH_F_FRAG) + return NF_DROP; + + IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n", + ic->icmp6_type, ntohs(icmpv6_id(ic)), + &iph->saddr, &iph->daddr); /* Now find the contained IP header */ - offset += sizeof(_icmph); - cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + ciph.len = iph->len + sizeof(_icmph); + offs_ciph = ciph.len; /* Save ip header offset */ + ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h); + if (ip6h == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ + ciph.saddr.in6 = ip6h->saddr; /* conn_in_get() handles reverse order */ + ciph.daddr.in6 = ip6h->daddr; + /* skip possible IPv6 exthdrs of contained IPv6 packet */ + ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL); + if (ciph.protocol < 0) + return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */ net = skb_net(skb); - pd = ip_vs_proto_data_get(net, cih->nexthdr); + pd = ip_vs_proto_data_get(net, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; - /* Is the embedded protocol header present? */ - /* TODO: we don't support fragmentation at the moment anyways */ - if (unlikely(cih->nexthdr == IPPROTO_FRAGMENT && pp->dont_defrag)) + /* Cannot handle fragmented embedded protocol */ + if (ciph.fragoffs) return NF_ACCEPT; - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph, "Checking incoming ICMPv6 for"); - offset += sizeof(struct ipv6hdr); + /* The embedded headers contain source and dest in reverse order + * if not from localhost + */ + cp = pp->conn_in_get(AF_INET6, skb, &ciph, + (hooknum == NF_INET_LOCAL_OUT) ? 0 : 1); - ip_vs_fill_iphdr(AF_INET6, cih, &ciph); - /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1); if (!cp) return NF_ACCEPT; + /* VS/TUN, VS/DR and LOCALNODE just let it go */ + if ((hooknum == NF_INET_LOCAL_OUT) && + (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { + __ip_vs_conn_put(cp); + return NF_ACCEPT; + } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - if (IPPROTO_TCP == cih->nexthdr || IPPROTO_UDP == cih->nexthdr || - IPPROTO_SCTP == cih->nexthdr) - offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum); + + /* Need to mangle contained IPv6 header in ICMPv6 packet */ + writable = ciph.len; + if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || + IPPROTO_SCTP == ciph.protocol) + writable += 2 * sizeof(__u16); /* Also mangle ports */ + + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum, &ciph); __ip_vs_conn_put(cp); @@ -1574,7 +1568,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + ip_vs_fill_iph_skb(af, skb, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, @@ -1586,7 +1580,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (!net_ipvs(net)->enable) return NF_ACCEPT; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); + ip_vs_fill_iph_skb(af, skb, &iph); /* Bad... Do not break raw sockets */ if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && @@ -1600,13 +1594,19 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { + if (!iph.fragoffs && skb_nfct_reasm(skb)) { + struct sk_buff *reasm = skb_nfct_reasm(skb); + /* Save fw mark for coming frags. */ + reasm->ipvs_property = 1; + reasm->mark = skb->mark; + } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; - int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum); + int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum, + &iph); if (related) return verdict; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } } else #endif @@ -1616,7 +1616,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (related) return verdict; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } /* Protocol supported? */ @@ -1627,12 +1626,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(af, skb, &iph, iph.len, 0); - - if (unlikely(!cp)) { + cp = pp->conn_in_get(af, skb, &iph, 0); + if (unlikely(!cp) && !iph.fragoffs) { + /* No (second) fragments need to enter here, as nf_defrag_ipv6 + * replayed fragment zero will already have created the cp + */ int v; - if (!pp->conn_schedule(af, skb, pd, &v, &cp)) + /* Schedule and create new connection entry into &cp */ + if (!pp->conn_schedule(af, skb, pd, &v, &cp, &iph)) return v; } @@ -1640,6 +1642,14 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, 0, "ip_vs_in: packet continues traversal as normal"); + if (iph.fragoffs && !skb_nfct_reasm(skb)) { + /* Fragment that couldn't be mapped to a conn entry + * and don't have any pointer to a reasm skb + * is missing module nf_defrag_ipv6 + */ + IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); + IP_VS_DBG_PKT(7, af, pp, skb, 0, "unhandled fragment"); + } return NF_ACCEPT; } @@ -1662,7 +1672,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_in_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) - ret = cp->packet_xmit(skb, cp, pp); + ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ else { IP_VS_DBG_RL("warning: packet_xmit is null"); @@ -1724,6 +1734,38 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 /* + * AF_INET6 fragment handling + * Copy info from first fragment, to the rest of them. + */ +static unsigned int +ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct sk_buff *reasm = skb_nfct_reasm(skb); + struct net *net; + + /* Skip if not a "replay" from nf_ct_frag6_output or first fragment. + * ipvs_property is set when checking first fragment + * in ip_vs_in() and ip_vs_out(). + */ + if (reasm) + IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property); + if (!reasm || !reasm->ipvs_property) + return NF_ACCEPT; + + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + + /* Copy stored fw mark, saved in ip_vs_{in,out} */ + skb->mark = reasm->mark; + + return NF_ACCEPT; +} + +/* * AF_INET6 handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ @@ -1793,8 +1835,10 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, { int r; struct net *net; + struct ip_vs_iphdr iphdr; - if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) + ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr); + if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; /* ipvs enabled in this netns ? */ @@ -1802,7 +1846,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, if (!net_ipvs(net)->enable) return NF_ACCEPT; - return ip_vs_in_icmp_v6(skb, &r, hooknum); + return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr); } #endif @@ -1860,6 +1904,14 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .priority = 100, }, #ifdef CONFIG_IP_VS_IPV6 + /* After mangle & nat fetch 2:nd fragment and following */ + { + .hook = ip_vs_preroute_frag6, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_NAT_DST + 1, + }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c4ee43710aab..ec664cbb119f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2339,7 +2339,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) struct ip_vs_dest_user_kern udest; struct netns_ipvs *ipvs = net_ipvs(net); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_SET_MAX) @@ -2632,7 +2632,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) struct netns_ipvs *ipvs = net_ipvs(net); BUG_ON(!net); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_GET_MAX) @@ -3699,6 +3699,10 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); if (tbl == NULL) return -ENOMEM; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + tbl[0].procname = NULL; } else tbl = vs_vars; /* Initialize sysctl defaults */ diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index 8b7dca9ea422..7f3b0cc00b7a 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -215,7 +215,7 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_dh_bucket *tbl; struct ip_vs_iphdr iph; - ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); + ip_vs_fill_iph_addr_only(svc->af, skb, &iph); IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index df646ccf08a7..fdd89b9564ea 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -479,7 +479,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_dest *dest = NULL; struct ip_vs_lblc_entry *en; - ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); + ip_vs_fill_iph_addr_only(svc->af, skb, &iph); IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -560,6 +560,11 @@ static int __net_init __ip_vs_lblc_init(struct net *net) GFP_KERNEL); if (ipvs->lblc_ctl_table == NULL) return -ENOMEM; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + ipvs->lblc_ctl_table[0].procname = NULL; + } else ipvs->lblc_ctl_table = vs_vars_table; ipvs->sysctl_lblc_expiration = DEFAULT_EXPIRATION; diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 570e31ea427a..c03b6a3ade2f 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -649,7 +649,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_dest *dest = NULL; struct ip_vs_lblcr_entry *en; - ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); + ip_vs_fill_iph_addr_only(svc->af, skb, &iph); IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); @@ -754,6 +754,10 @@ static int __net_init __ip_vs_lblcr_init(struct net *net) GFP_KERNEL); if (ipvs->lblcr_ctl_table == NULL) return -ENOMEM; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + ipvs->lblcr_ctl_table[0].procname = NULL; } else ipvs->lblcr_ctl_table = vs_vars_table; ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION; diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 022e77e1e766..c8beafd401aa 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -82,7 +82,7 @@ void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) { enum ip_conntrack_info ctinfo; - struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); struct nf_conntrack_tuple new_tuple; if (ct == NULL || nf_ct_is_confirmed(ct) || nf_ct_is_untracked(ct) || diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index 1aa5cac748c4..12475ef88daf 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -68,23 +68,31 @@ static int get_callid(const char *dptr, unsigned int dataoff, static int ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) { + struct sk_buff *reasm = skb_nfct_reasm(skb); struct ip_vs_iphdr iph; unsigned int dataoff, datalen, matchoff, matchlen; const char *dptr; int retc; - ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph); + ip_vs_fill_iph_skb(p->af, skb, &iph); /* Only useful with UDP */ if (iph.protocol != IPPROTO_UDP) return -EINVAL; + /* todo: IPv6 fragments: + * I think this only should be done for the first fragment. /HS + */ + if (reasm) { + skb = reasm; + dataoff = iph.thoff_reasm + sizeof(struct udphdr); + } else + dataoff = iph.len + sizeof(struct udphdr); - /* No Data ? */ - dataoff = iph.len + sizeof(struct udphdr); if (dataoff >= skb->len) return -EINVAL; - - if ((retc=skb_linearize(skb)) < 0) + /* todo: Check if this will mess-up the reasm skb !!! /HS */ + retc = skb_linearize(skb); + if (retc < 0) return retc; dptr = skb->data + dataoff; datalen = skb->len - dataoff; diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 50d82186da87..939f7fbe9b46 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -280,17 +280,17 @@ ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp, if (ih == NULL) sprintf(buf, "TRUNCATED"); else if (ih->nexthdr == IPPROTO_FRAGMENT) - sprintf(buf, "%pI6->%pI6 frag", &ih->saddr, &ih->daddr); + sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr); else { __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr), sizeof(_ports), _ports); if (pptr == NULL) - sprintf(buf, "TRUNCATED %pI6->%pI6", + sprintf(buf, "TRUNCATED %pI6c->%pI6c", &ih->saddr, &ih->daddr); else - sprintf(buf, "%pI6:%u->%pI6:%u", + sprintf(buf, "%pI6c:%u->%pI6c:%u", &ih->saddr, ntohs(pptr[0]), &ih->daddr, ntohs(pptr[1])); } diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 5b8eb8b12c3e..5de3dd312c0f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -57,7 +57,7 @@ ah_esp_conn_fill_param_proto(struct net *net, int af, static struct ip_vs_conn * ah_esp_conn_in_get(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, unsigned int proto_off, + const struct ip_vs_iphdr *iph, int inverse) { struct ip_vs_conn *cp; @@ -85,9 +85,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, static struct ip_vs_conn * ah_esp_conn_out_get(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - unsigned int proto_off, - int inverse) + const struct ip_vs_iphdr *iph, int inverse) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; @@ -110,7 +108,8 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb, static int ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - int *verdict, struct ip_vs_conn **cpp) + int *verdict, struct ip_vs_conn **cpp, + struct ip_vs_iphdr *iph) { /* * AH/ESP is only related traffic. Pass the packet to IP stack. diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 9f3fb751c491..746048b13ef3 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -10,28 +10,26 @@ static int sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - int *verdict, struct ip_vs_conn **cpp) + int *verdict, struct ip_vs_conn **cpp, + struct ip_vs_iphdr *iph) { struct net *net; struct ip_vs_service *svc; sctp_chunkhdr_t _schunkh, *sch; sctp_sctphdr_t *sh, _sctph; - struct ip_vs_iphdr iph; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); - - sh = skb_header_pointer(skb, iph.len, sizeof(_sctph), &_sctph); + sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); if (sh == NULL) return 0; - sch = skb_header_pointer(skb, iph.len + sizeof(sctp_sctphdr_t), + sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t), sizeof(_schunkh), &_schunkh); if (sch == NULL) return 0; net = skb_net(skb); if ((sch->type == SCTP_CID_INIT) && - (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, - &iph.daddr, sh->dest))) { + (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol, + &iph->daddr, sh->dest))) { int ignored; if (ip_vs_todrop(net_ipvs(net))) { @@ -47,10 +45,10 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) - *verdict = ip_vs_leave(svc, skb, pd); + *verdict = ip_vs_leave(svc, skb, pd, iph); else { ip_vs_service_put(svc); *verdict = NF_DROP; @@ -64,20 +62,18 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, } static int -sctp_snat_handler(struct sk_buff *skb, - struct ip_vs_protocol *pp, struct ip_vs_conn *cp) +sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { sctp_sctphdr_t *sctph; - unsigned int sctphoff; + unsigned int sctphoff = iph->len; struct sk_buff *iter; __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 - if (cp->af == AF_INET6) - sctphoff = sizeof(struct ipv6hdr); - else + if (cp->af == AF_INET6 && iph->fragoffs) + return 1; #endif - sctphoff = ip_hdrlen(skb); /* csum_check requires unshared skb */ if (!skb_make_writable(skb, sctphoff + sizeof(*sctph))) @@ -108,20 +104,18 @@ sctp_snat_handler(struct sk_buff *skb, } static int -sctp_dnat_handler(struct sk_buff *skb, - struct ip_vs_protocol *pp, struct ip_vs_conn *cp) +sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { sctp_sctphdr_t *sctph; - unsigned int sctphoff; + unsigned int sctphoff = iph->len; struct sk_buff *iter; __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 - if (cp->af == AF_INET6) - sctphoff = sizeof(struct ipv6hdr); - else + if (cp->af == AF_INET6 && iph->fragoffs) + return 1; #endif - sctphoff = ip_hdrlen(skb); /* csum_check requires unshared skb */ if (!skb_make_writable(skb, sctphoff + sizeof(*sctph))) diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index cd609cc62721..9af653a75825 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -33,16 +33,14 @@ static int tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - int *verdict, struct ip_vs_conn **cpp) + int *verdict, struct ip_vs_conn **cpp, + struct ip_vs_iphdr *iph) { struct net *net; struct ip_vs_service *svc; struct tcphdr _tcph, *th; - struct ip_vs_iphdr iph; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); - - th = skb_header_pointer(skb, iph.len, sizeof(_tcph), &_tcph); + th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th == NULL) { *verdict = NF_DROP; return 0; @@ -50,8 +48,8 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, net = skb_net(skb); /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ if (th->syn && - (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, - &iph.daddr, th->dest))) { + (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol, + &iph->daddr, th->dest))) { int ignored; if (ip_vs_todrop(net_ipvs(net))) { @@ -68,10 +66,10 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) - *verdict = ip_vs_leave(svc, skb, pd); + *verdict = ip_vs_leave(svc, skb, pd, iph); else { ip_vs_service_put(svc); *verdict = NF_DROP; @@ -128,20 +126,18 @@ tcp_partial_csum_update(int af, struct tcphdr *tcph, static int -tcp_snat_handler(struct sk_buff *skb, - struct ip_vs_protocol *pp, struct ip_vs_conn *cp) +tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; - unsigned int tcphoff; + unsigned int tcphoff = iph->len; int oldlen; int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 - if (cp->af == AF_INET6) - tcphoff = sizeof(struct ipv6hdr); - else + if (cp->af == AF_INET6 && iph->fragoffs) + return 1; #endif - tcphoff = ip_hdrlen(skb); oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ @@ -208,20 +204,18 @@ tcp_snat_handler(struct sk_buff *skb, static int -tcp_dnat_handler(struct sk_buff *skb, - struct ip_vs_protocol *pp, struct ip_vs_conn *cp) +tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; - unsigned int tcphoff; + unsigned int tcphoff = iph->len; int oldlen; int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 - if (cp->af == AF_INET6) - tcphoff = sizeof(struct ipv6hdr); - else + if (cp->af == AF_INET6 && iph->fragoffs) + return 1; #endif - tcphoff = ip_hdrlen(skb); oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 2fedb2dcb3d1..503a842c90d2 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -30,23 +30,22 @@ static int udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - int *verdict, struct ip_vs_conn **cpp) + int *verdict, struct ip_vs_conn **cpp, + struct ip_vs_iphdr *iph) { struct net *net; struct ip_vs_service *svc; struct udphdr _udph, *uh; - struct ip_vs_iphdr iph; - ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); - - uh = skb_header_pointer(skb, iph.len, sizeof(_udph), &_udph); + /* IPv6 fragments, only first fragment will hit this */ + uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); if (uh == NULL) { *verdict = NF_DROP; return 0; } net = skb_net(skb); - svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, - &iph.daddr, uh->dest); + svc = ip_vs_service_get(net, af, skb->mark, iph->protocol, + &iph->daddr, uh->dest); if (svc) { int ignored; @@ -64,10 +63,10 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) - *verdict = ip_vs_leave(svc, skb, pd); + *verdict = ip_vs_leave(svc, skb, pd, iph); else { ip_vs_service_put(svc); *verdict = NF_DROP; @@ -125,20 +124,18 @@ udp_partial_csum_update(int af, struct udphdr *uhdr, static int -udp_snat_handler(struct sk_buff *skb, - struct ip_vs_protocol *pp, struct ip_vs_conn *cp) +udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct udphdr *udph; - unsigned int udphoff; + unsigned int udphoff = iph->len; int oldlen; int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 - if (cp->af == AF_INET6) - udphoff = sizeof(struct ipv6hdr); - else + if (cp->af == AF_INET6 && iph->fragoffs) + return 1; #endif - udphoff = ip_hdrlen(skb); oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ @@ -210,20 +207,18 @@ udp_snat_handler(struct sk_buff *skb, static int -udp_dnat_handler(struct sk_buff *skb, - struct ip_vs_protocol *pp, struct ip_vs_conn *cp) +udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct udphdr *udph; - unsigned int udphoff; + unsigned int udphoff = iph->len; int oldlen; int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 - if (cp->af == AF_INET6) - udphoff = sizeof(struct ipv6hdr); - else + if (cp->af == AF_INET6 && iph->fragoffs) + return 1; #endif - udphoff = ip_hdrlen(skb); oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 08dbdd5bc18f..d6bf20d6cdbe 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -159,7 +159,7 @@ void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg) svc->fwmark, msg); #ifdef CONFIG_IP_VS_IPV6 } else if (svc->af == AF_INET6) { - IP_VS_ERR_RL("%s: %s [%pI6]:%d - %s\n", + IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n", svc->scheduler->name, ip_vs_proto_name(svc->protocol), &svc->addr.in6, ntohs(svc->port), msg); diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index 05126521743e..e33126994628 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -228,7 +228,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) struct ip_vs_sh_bucket *tbl; struct ip_vs_iphdr iph; - ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); + ip_vs_fill_iph_addr_only(svc->af, skb, &iph); IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n"); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index cc4c8095681a..ee6b7a9f1ec2 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -338,7 +338,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, local = __ip_vs_is_local_route6(rt); if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) & rt_mode)) { - IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n", + IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6c\n", local ? "local":"non-local", daddr); dst_release(&rt->dst); return NULL; @@ -346,8 +346,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, if (local && !(rt_mode & IP_VS_RT_MODE_RDR) && !((ort = (struct rt6_info *) skb_dst(skb)) && __ip_vs_is_local_route6(ort))) { - IP_VS_DBG_RL("Redirect from non-local address %pI6 to local " - "requires NAT method, dest: %pI6\n", + IP_VS_DBG_RL("Redirect from non-local address %pI6c to local " + "requires NAT method, dest: %pI6c\n", &ipv6_hdr(skb)->daddr, daddr); dst_release(&rt->dst); return NULL; @@ -355,8 +355,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) && ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LOOPBACK)) { - IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 " - "to non-local address, dest: %pI6\n", + IP_VS_DBG_RL("Stopping traffic from loopback address %pI6c " + "to non-local address, dest: %pI6c\n", &ipv6_hdr(skb)->saddr, daddr); dst_release(&rt->dst); return NULL; @@ -427,7 +427,7 @@ do { \ */ int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { /* we do not touch skb and do not need pskb ptr */ IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1); @@ -441,7 +441,7 @@ ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, */ int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { struct rtable *rt; /* Route to the other host */ struct iphdr *iph = ip_hdr(skb); @@ -496,16 +496,16 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph) { struct rt6_info *rt; /* Route to the other host */ - struct ipv6hdr *iph = ipv6_hdr(skb); int mtu; EnterFunction(10); - if (!(rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr, NULL, 0, - IP_VS_RT_MODE_NON_LOCAL))) + rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr.in6, NULL, 0, + IP_VS_RT_MODE_NON_LOCAL); + if (!rt) goto tx_error_icmp; /* MTU checking */ @@ -516,7 +516,9 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->dev = net->loopback_dev; } - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + /* only send ICMP too big on first fragment */ + if (!iph->fragoffs) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); dst_release(&rt->dst); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; @@ -559,7 +561,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, */ int ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { struct rtable *rt; /* Route to the other host */ int mtu; @@ -592,7 +594,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; - struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0, @@ -629,7 +631,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* mangle the packet */ - if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) + if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh)) goto tx_error_put; ip_hdr(skb)->daddr = cp->daddr.ip; ip_send_check(ip_hdr(skb)); @@ -677,7 +679,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph) { struct rt6_info *rt; /* Route to the other host */ int mtu; @@ -686,10 +688,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); /* check if it is a connection of no-client-port */ - if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) { + if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !iph->fragoffs)) { __be16 _pt, *p; - p = skb_header_pointer(skb, sizeof(struct ipv6hdr), - sizeof(_pt), &_pt); + p = skb_header_pointer(skb, iph->len, sizeof(_pt), &_pt); if (p == NULL) goto tx_error; ip_vs_conn_fill_cport(cp, *p); @@ -709,7 +710,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; - struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0, @@ -737,7 +738,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->dev = net->loopback_dev; } - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + /* only send ICMP too big on first fragment */ + if (!iph->fragoffs) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): frag needed for"); goto tx_error_put; @@ -751,7 +754,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; /* mangle the packet */ - if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) + if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, iph)) goto tx_error; ipv6_hdr(skb)->daddr = cp->daddr.in6; @@ -812,7 +815,7 @@ tx_error_put: */ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); struct rtable *rt; /* Route to the other host */ @@ -932,7 +935,7 @@ tx_error_put: #ifdef CONFIG_IP_VS_IPV6 int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { struct rt6_info *rt; /* Route to the other host */ struct in6_addr saddr; /* Source for tunnel */ @@ -972,7 +975,9 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->dev = net->loopback_dev; } - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + /* only send ICMP too big on first fragment */ + if (!ipvsh->fragoffs) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } @@ -1053,7 +1058,7 @@ tx_error_put: */ int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { struct rtable *rt; /* Route to the other host */ struct iphdr *iph = ip_hdr(skb); @@ -1115,7 +1120,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp) + struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph) { struct rt6_info *rt; /* Route to the other host */ int mtu; @@ -1139,7 +1144,9 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->dev = net->loopback_dev; } - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + /* only send ICMP too big on first fragment */ + if (!iph->fragoffs) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); dst_release(&rt->dst); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; @@ -1183,7 +1190,8 @@ tx_error: */ int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum) + struct ip_vs_protocol *pp, int offset, unsigned int hooknum, + struct ip_vs_iphdr *iph) { struct rtable *rt; /* Route to the other host */ int mtu; @@ -1198,7 +1206,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp); + rc = cp->packet_xmit(skb, cp, pp, iph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1227,7 +1235,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; - struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG(10, "%s(): " @@ -1304,7 +1312,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum) + struct ip_vs_protocol *pp, int offset, unsigned int hooknum, + struct ip_vs_iphdr *iph) { struct rt6_info *rt; /* Route to the other host */ int mtu; @@ -1319,7 +1328,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp); + rc = cp->packet_xmit(skb, cp, pp, iph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1347,7 +1356,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; - struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG(10, "%s(): " @@ -1375,7 +1384,9 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->dev = net->loopback_dev; } - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + /* only send ICMP too big on first fragment */ + if (!iph->fragoffs) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index d61e0782a797..7df424e2d10c 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -69,6 +69,10 @@ static int nf_conntrack_acct_init_sysctl(struct net *net) table[0].data = &net->ct.sysctl_acct; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + net->ct.acct_sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.acct_sysctl_header) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0f241be28f9e..e4a0c4fb3a7c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -221,11 +221,9 @@ destroy_conntrack(struct nf_conntrack *nfct) * too. */ nf_ct_remove_expectations(ct); - /* We overload first tuple to link into unconfirmed list. */ - if (!nf_ct_is_confirmed(ct)) { - BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); - hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); - } + /* We overload first tuple to link into unconfirmed or dying list.*/ + BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); + hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); NF_CT_STAT_INC(net, delete); spin_unlock_bh(&nf_conntrack_lock); @@ -247,6 +245,9 @@ void nf_ct_delete_from_lists(struct nf_conn *ct) * Otherwise we can get spurious warnings. */ NF_CT_STAT_INC(net, delete_list); clean_from_lists(ct); + /* add this conntrack to the dying list */ + hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &net->ct.dying); spin_unlock_bh(&nf_conntrack_lock); } EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists); @@ -268,31 +269,23 @@ static void death_by_event(unsigned long ul_conntrack) } /* we've got the event delivered, now it's dying */ set_bit(IPS_DYING_BIT, &ct->status); - spin_lock(&nf_conntrack_lock); - hlist_nulls_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); - spin_unlock(&nf_conntrack_lock); nf_ct_put(ct); } -void nf_ct_insert_dying_list(struct nf_conn *ct) +void nf_ct_dying_timeout(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct); BUG_ON(ecache == NULL); - /* add this conntrack to the dying list */ - spin_lock_bh(&nf_conntrack_lock); - hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &net->ct.dying); - spin_unlock_bh(&nf_conntrack_lock); /* set a new timer to retry event delivery */ setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct); ecache->timeout.expires = jiffies + (random32() % net->ct.sysctl_events_retry_timeout); add_timer(&ecache->timeout); } -EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list); +EXPORT_SYMBOL_GPL(nf_ct_dying_timeout); static void death_by_timeout(unsigned long ul_conntrack) { @@ -307,7 +300,7 @@ static void death_by_timeout(unsigned long ul_conntrack) unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) { /* destroy event was not delivered */ nf_ct_delete_from_lists(ct); - nf_ct_insert_dying_list(ct); + nf_ct_dying_timeout(ct); return; } set_bit(IPS_DYING_BIT, &ct->status); @@ -1383,11 +1376,12 @@ void nf_conntrack_cleanup(struct net *net) synchronize_net(); nf_conntrack_proto_fini(net); nf_conntrack_cleanup_net(net); +} - if (net_eq(net, &init_net)) { - RCU_INIT_POINTER(nf_ct_destroy, NULL); - nf_conntrack_cleanup_init_net(); - } +void nf_conntrack_cleanup_end(void) +{ + RCU_INIT_POINTER(nf_ct_destroy, NULL); + nf_conntrack_cleanup_init_net(); } void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) @@ -1416,7 +1410,7 @@ EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable); int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) { - int i, bucket; + int i, bucket, rc; unsigned int hashsize, old_size; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; @@ -1429,7 +1423,9 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!nf_conntrack_htable_size) return param_set_uint(val, kp); - hashsize = simple_strtoul(val, NULL, 0); + rc = kstrtouint(val, 0, &hashsize); + if (rc) + return rc; if (!hashsize) return -EINVAL; @@ -1531,6 +1527,7 @@ err_extend: */ #define UNCONFIRMED_NULLS_VAL ((1<<30)+0) #define DYING_NULLS_VAL ((1<<30)+1) +#define TEMPLATE_NULLS_VAL ((1<<30)+2) static int nf_conntrack_init_net(struct net *net) { @@ -1539,6 +1536,7 @@ static int nf_conntrack_init_net(struct net *net) atomic_set(&net->ct.count, 0); INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL); net->ct.stat = alloc_percpu(struct ip_conntrack_stat); if (!net->ct.stat) { ret = -ENOMEM; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index de9781b6464f..faa978f1714b 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -196,6 +196,10 @@ static int nf_conntrack_event_init_sysctl(struct net *net) table[0].data = &net->ct.sysctl_events; table[1].data = &net->ct.sysctl_events_retry_timeout; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + net->ct.event_sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.event_sysctl_header) { diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 1b30b0dee708..962795e839ab 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -753,7 +753,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi4_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi4_to_flowi(&fl2), false)) { - if (rt1->rt_gateway == rt2->rt_gateway && + if (rt_nexthop(rt1, fl1.daddr) == + rt_nexthop(rt2, fl2.daddr) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index c4bc637feb76..884f2b39319a 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -64,6 +64,10 @@ static int nf_conntrack_helper_init_sysctl(struct net *net) table[0].data = &net->ct.sysctl_auto_assign_helper; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + net->ct.helper_sysctl_header = register_net_sysctl(net, "net/netfilter", table); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7bbfb3deea30..627b0e50b238 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -898,7 +898,8 @@ ctnetlink_parse_zone(const struct nlattr *attr, u16 *zone) } static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { - [CTA_HELP_NAME] = { .type = NLA_NUL_STRING }, + [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN - 1 }, }; static inline int @@ -932,6 +933,8 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_ID] = { .type = NLA_U32 }, [CTA_NAT_DST] = { .type = NLA_NESTED }, [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, + [CTA_NAT_SEQ_ADJ_ORIG] = { .type = NLA_NESTED }, + [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, }; @@ -989,7 +992,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, nlmsg_report(nlh)) < 0) { nf_ct_delete_from_lists(ct); /* we failed to report the event, try later */ - nf_ct_insert_dying_list(ct); + nf_ct_dying_timeout(ct); nf_ct_put(ct); return 0; } @@ -1089,6 +1092,112 @@ out: return err == -EAGAIN ? -ENOBUFS : err; } +static int ctnetlink_done_list(struct netlink_callback *cb) +{ + if (cb->args[1]) + nf_ct_put((struct nf_conn *)cb->args[1]); + return 0; +} + +static int +ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, + struct hlist_nulls_head *list) +{ + struct nf_conn *ct, *last; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + u_int8_t l3proto = nfmsg->nfgen_family; + int res; + + if (cb->args[2]) + return 0; + + spin_lock_bh(&nf_conntrack_lock); + last = (struct nf_conn *)cb->args[1]; +restart: + hlist_nulls_for_each_entry(h, n, list, hnnode) { + ct = nf_ct_tuplehash_to_ctrack(h); + if (l3proto && nf_ct_l3num(ct) != l3proto) + continue; + if (cb->args[1]) { + if (ct != last) + continue; + cb->args[1] = 0; + } + rcu_read_lock(); + res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + ct); + rcu_read_unlock(); + if (res < 0) { + nf_conntrack_get(&ct->ct_general); + cb->args[1] = (unsigned long)ct; + goto out; + } + } + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } else + cb->args[2] = 1; +out: + spin_unlock_bh(&nf_conntrack_lock); + if (last) + nf_ct_put(last); + + return skb->len; +} + +static int +ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + + return ctnetlink_dump_list(skb, cb, &net->ct.dying); +} + +static int +ctnetlink_get_ct_dying(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnetlink_dump_dying, + .done = ctnetlink_done_list, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + return -EOPNOTSUPP; +} + +static int +ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + + return ctnetlink_dump_list(skb, cb, &net->ct.unconfirmed); +} + +static int +ctnetlink_get_ct_unconfirmed(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]) +{ + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnetlink_dump_unconfirmed, + .done = ctnetlink_done_list, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } + + return -EOPNOTSUPP; +} + #ifdef CONFIG_NF_NAT_NEEDED static int ctnetlink_parse_nat_setup(struct nf_conn *ct, @@ -2216,7 +2325,8 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, [CTA_EXPECT_ID] = { .type = NLA_U32 }, - [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING }, + [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, + .len = NF_CT_HELPER_NAME_LEN - 1 }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, @@ -2514,7 +2624,7 @@ ctnetlink_create_expect(struct net *net, u16 zone, if (!help) { if (!cda[CTA_EXPECT_TIMEOUT]) { err = -EINVAL; - goto out; + goto err_out; } exp->timeout.expires = jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; @@ -2712,6 +2822,8 @@ static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu }, [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct }, + [IPCTNL_MSG_CT_GET_DYING] = { .call = ctnetlink_get_ct_dying }, + [IPCTNL_MSG_CT_GET_UNCONFIRMED] = { .call = ctnetlink_get_ct_unconfirmed }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 6535326cf07c..a8ae287bc7af 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -815,7 +815,7 @@ static struct ctl_table dccp_sysctl_table[] = { }; #endif /* CONFIG_SYSCTL */ -static int dccp_kmemdup_sysctl_table(struct nf_proto_net *pn, +static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn, struct dccp_net *dn) { #ifdef CONFIG_SYSCTL @@ -836,6 +836,10 @@ static int dccp_kmemdup_sysctl_table(struct nf_proto_net *pn, pn->ctl_table[5].data = &dn->dccp_timeout[CT_DCCP_CLOSING]; pn->ctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT]; pn->ctl_table[7].data = &dn->dccp_loose; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + pn->ctl_table[0].procname = NULL; #endif return 0; } @@ -857,7 +861,7 @@ static int dccp_init_net(struct net *net, u_int16_t proto) dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; } - return dccp_kmemdup_sysctl_table(pn, dn); + return dccp_kmemdup_sysctl_table(net, pn, dn); } static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 61f9285111d1..83876e9877f1 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1353,6 +1353,8 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { [CTA_TIMEOUT_TCP_TIME_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_CLOSE] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_SYN_SENT2] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_RETRANS] = { .type = NLA_U32 }, + [CTA_TIMEOUT_TCP_UNACK] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b3943252a5e..e7185c684816 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -489,6 +489,10 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[3].data = &net->ct.sysctl_checksum; table[4].data = &net->ct.sysctl_log_invalid; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + net->ct.sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.sysctl_header) goto out_unregister_netfilter; @@ -571,6 +575,7 @@ static int __init nf_conntrack_standalone_init(void) static void __exit nf_conntrack_standalone_fini(void) { unregister_pernet_subsys(&nf_conntrack_net_ops); + nf_conntrack_cleanup_end(); } module_init(nf_conntrack_standalone_init); diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c index dbb364f62d6f..7ea8026f07c9 100644 --- a/net/netfilter/nf_conntrack_timestamp.c +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -51,6 +51,10 @@ static int nf_conntrack_tstamp_init_sysctl(struct net *net) table[0].data = &net->ct.sysctl_tstamp; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + net->ct.tstamp_sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.tstamp_sysctl_header) { diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 8d2cf9ec37a8..d812c1235b30 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -14,84 +14,32 @@ #include "nf_internals.h" /* - * A queue handler may be registered for each protocol. Each is protected by - * long term mutex. The handler must provide an an outfn() to accept packets - * for queueing and must reinject all packets it receives, no matter what. + * Hook for nfnetlink_queue to register its queue handler. + * We do this so that most of the NFQUEUE code can be modular. + * + * Once the queue is registered it must reinject all packets it + * receives, no matter what. */ -static const struct nf_queue_handler __rcu *queue_handler[NFPROTO_NUMPROTO] __read_mostly; - -static DEFINE_MUTEX(queue_handler_mutex); +static const struct nf_queue_handler __rcu *queue_handler __read_mostly; /* return EBUSY when somebody else is registered, return EEXIST if the * same handler is registered, return 0 in case of success. */ -int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) +void nf_register_queue_handler(const struct nf_queue_handler *qh) { - int ret; - const struct nf_queue_handler *old; - - if (pf >= ARRAY_SIZE(queue_handler)) - return -EINVAL; - - mutex_lock(&queue_handler_mutex); - old = rcu_dereference_protected(queue_handler[pf], - lockdep_is_held(&queue_handler_mutex)); - if (old == qh) - ret = -EEXIST; - else if (old) - ret = -EBUSY; - else { - rcu_assign_pointer(queue_handler[pf], qh); - ret = 0; - } - mutex_unlock(&queue_handler_mutex); - - return ret; + /* should never happen, we only have one queueing backend in kernel */ + WARN_ON(rcu_access_pointer(queue_handler)); + rcu_assign_pointer(queue_handler, qh); } EXPORT_SYMBOL(nf_register_queue_handler); /* The caller must flush their queue before this */ -int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) +void nf_unregister_queue_handler(void) { - const struct nf_queue_handler *old; - - if (pf >= ARRAY_SIZE(queue_handler)) - return -EINVAL; - - mutex_lock(&queue_handler_mutex); - old = rcu_dereference_protected(queue_handler[pf], - lockdep_is_held(&queue_handler_mutex)); - if (old && old != qh) { - mutex_unlock(&queue_handler_mutex); - return -EINVAL; - } - - RCU_INIT_POINTER(queue_handler[pf], NULL); - mutex_unlock(&queue_handler_mutex); - + RCU_INIT_POINTER(queue_handler, NULL); synchronize_rcu(); - - return 0; } EXPORT_SYMBOL(nf_unregister_queue_handler); -void nf_unregister_queue_handlers(const struct nf_queue_handler *qh) -{ - u_int8_t pf; - - mutex_lock(&queue_handler_mutex); - for (pf = 0; pf < ARRAY_SIZE(queue_handler); pf++) { - if (rcu_dereference_protected( - queue_handler[pf], - lockdep_is_held(&queue_handler_mutex) - ) == qh) - RCU_INIT_POINTER(queue_handler[pf], NULL); - } - mutex_unlock(&queue_handler_mutex); - - synchronize_rcu(); -} -EXPORT_SYMBOL_GPL(nf_unregister_queue_handlers); - static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) { /* Release those devices we held, or Alexey will kill me. */ @@ -137,7 +85,7 @@ static int __nf_queue(struct sk_buff *skb, /* QUEUE == DROP if no one is waiting, to be safe. */ rcu_read_lock(); - qh = rcu_dereference(queue_handler[pf]); + qh = rcu_dereference(queue_handler); if (!qh) { status = -ESRCH; goto err_unlock; @@ -344,77 +292,3 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) kfree(entry); } EXPORT_SYMBOL(nf_reinject); - -#ifdef CONFIG_PROC_FS -static void *seq_start(struct seq_file *seq, loff_t *pos) -{ - if (*pos >= ARRAY_SIZE(queue_handler)) - return NULL; - - return pos; -} - -static void *seq_next(struct seq_file *s, void *v, loff_t *pos) -{ - (*pos)++; - - if (*pos >= ARRAY_SIZE(queue_handler)) - return NULL; - - return pos; -} - -static void seq_stop(struct seq_file *s, void *v) -{ - -} - -static int seq_show(struct seq_file *s, void *v) -{ - int ret; - loff_t *pos = v; - const struct nf_queue_handler *qh; - - rcu_read_lock(); - qh = rcu_dereference(queue_handler[*pos]); - if (!qh) - ret = seq_printf(s, "%2lld NONE\n", *pos); - else - ret = seq_printf(s, "%2lld %s\n", *pos, qh->name); - rcu_read_unlock(); - - return ret; -} - -static const struct seq_operations nfqueue_seq_ops = { - .start = seq_start, - .next = seq_next, - .stop = seq_stop, - .show = seq_show, -}; - -static int nfqueue_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &nfqueue_seq_ops); -} - -static const struct file_operations nfqueue_file_ops = { - .owner = THIS_MODULE, - .open = nfqueue_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif /* PROC_FS */ - - -int __init netfilter_queue_init(void) -{ -#ifdef CONFIG_PROC_FS - if (!proc_create("nf_queue", S_IRUGO, - proc_net_netfilter, &nfqueue_file_ops)) - return -1; -#endif - return 0; -} - diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index ffb92c03a358..58a09b7c3f6d 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -138,7 +138,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) const struct nfnetlink_subsystem *ss; int type, err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* All the messages must at least contain nfgenmsg */ diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 8847b4d8be06..701c88a20fea 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -41,7 +41,8 @@ MODULE_DESCRIPTION("cttimeout: Extended Netfilter Connection Tracking timeout tu static LIST_HEAD(cttimeout_list); static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { - [CTA_TIMEOUT_NAME] = { .type = NLA_NUL_STRING }, + [CTA_TIMEOUT_NAME] = { .type = NLA_NUL_STRING, + .len = CTNL_TIMEOUT_NAME_MAX - 1}, [CTA_TIMEOUT_L3PROTO] = { .type = NLA_U16 }, [CTA_TIMEOUT_L4PROTO] = { .type = NLA_U8 }, [CTA_TIMEOUT_DATA] = { .type = NLA_NESTED }, diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 9f199f2e31fa..92fd8eca0d31 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -13,6 +13,7 @@ */ #include <linux/module.h> #include <linux/skbuff.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -384,6 +385,7 @@ __build_packet_message(struct nfulnl_instance *inst, struct nfgenmsg *nfmsg; sk_buff_data_t old_tail = inst->skb->tail; struct sock *sk; + const unsigned char *hwhdrp; nlh = nlmsg_put(inst->skb, 0, 0, NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET, @@ -485,9 +487,17 @@ __build_packet_message(struct nfulnl_instance *inst, if (indev && skb_mac_header_was_set(skb)) { if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || nla_put_be16(inst->skb, NFULA_HWLEN, - htons(skb->dev->hard_header_len)) || - nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, - skb_mac_header(skb))) + htons(skb->dev->hard_header_len))) + goto nla_put_failure; + + hwhdrp = skb_mac_header(skb); + + if (skb->dev->type == ARPHRD_SIT) + hwhdrp -= ETH_HLEN; + + if (hwhdrp >= skb->head && + nla_put(inst->skb, NFULA_HWHEADER, + skb->dev->hard_header_len, hwhdrp)) goto nla_put_failure; } diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index e12d44e75b21..3158d87b56a8 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -809,7 +809,6 @@ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { }; static const struct nf_queue_handler nfqh = { - .name = "nf_queue", .outfn = &nfqnl_enqueue_packet, }; @@ -827,14 +826,10 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, if (nfqa[NFQA_CFG_CMD]) { cmd = nla_data(nfqa[NFQA_CFG_CMD]); - /* Commands without queue context - might sleep */ + /* Obsolete commands without queue context */ switch (cmd->command) { - case NFQNL_CFG_CMD_PF_BIND: - return nf_register_queue_handler(ntohs(cmd->pf), - &nfqh); - case NFQNL_CFG_CMD_PF_UNBIND: - return nf_unregister_queue_handler(ntohs(cmd->pf), - &nfqh); + case NFQNL_CFG_CMD_PF_BIND: return 0; + case NFQNL_CFG_CMD_PF_UNBIND: return 0; } } @@ -1074,6 +1069,7 @@ static int __init nfnetlink_queue_init(void) #endif register_netdevice_notifier(&nfqnl_dev_notifier); + nf_register_queue_handler(&nfqh); return status; #ifdef CONFIG_PROC_FS @@ -1087,7 +1083,7 @@ cleanup_netlink_notifier: static void __exit nfnetlink_queue_fini(void) { - nf_unregister_queue_handlers(&nfqh); + nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_queue", proc_net_netfilter); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8d987c3573fd..7b3a9e5999c0 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -345,19 +345,27 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, } EXPORT_SYMBOL_GPL(xt_find_revision); -static char *textify_hooks(char *buf, size_t size, unsigned int mask) +static char * +textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { - static const char *const names[] = { + static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; - unsigned int i; + static const char *const arp_names[] = { + "INPUT", "FORWARD", "OUTPUT", + }; + const char *const *names; + unsigned int i, max; char *p = buf; bool np = false; int res; + names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; + max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : + ARRAY_SIZE(inetbr_names); *p = '\0'; - for (i = 0; i < ARRAY_SIZE(names); ++i) { + for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); @@ -402,8 +410,10 @@ int xt_check_match(struct xt_mtchk_param *par, pr_err("%s_tables: %s match: used from hooks %s, but only " "valid from %s\n", xt_prefix[par->family], par->match->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->match->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->match->hooks, + par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { @@ -575,8 +585,10 @@ int xt_check_target(struct xt_tgchk_param *par, pr_err("%s_tables: %s target: used from hooks %s, but only " "usable from %s\n", xt_prefix[par->family], par->target->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->target->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->target->hooks, + par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index ae7f5daeee43..bde009ed8d3b 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -109,7 +109,7 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) struct xt_ct_target_info *info = par->targinfo; struct nf_conntrack_tuple t; struct nf_conn *ct; - int ret; + int ret = -EOPNOTSUPP; if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -149,6 +149,10 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) __set_bit(IPS_TEMPLATE_BIT, &ct->status); __set_bit(IPS_CONFIRMED_BIT, &ct->status); + + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &par->net->ct.tmpl); out: info->ct = ct; return 0; @@ -243,7 +247,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) struct xt_ct_target_info_v1 *info = par->targinfo; struct nf_conntrack_tuple t; struct nf_conn *ct; - int ret; + int ret = -EOPNOTSUPP; if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -289,6 +293,10 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) __set_bit(IPS_TEMPLATE_BIT, &ct->status); __set_bit(IPS_CONFIRMED_BIT, &ct->status); + + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &par->net->ct.tmpl); out: info->ct = ct; return 0; @@ -377,14 +385,60 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { }, }; +static unsigned int +notrack_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + /* Previously seen (loopback)? Ignore. */ + if (skb->nfct != NULL) + return XT_CONTINUE; + + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); + + return XT_CONTINUE; +} + +static int notrack_chk(const struct xt_tgchk_param *par) +{ + if (!par->net->xt.notrack_deprecated_warning) { + pr_info("netfilter: NOTRACK target is deprecated, " + "use CT instead or upgrade iptables\n"); + par->net->xt.notrack_deprecated_warning = true; + } + return 0; +} + +static struct xt_target notrack_tg_reg __read_mostly = { + .name = "NOTRACK", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = notrack_chk, + .target = notrack_tg, + .table = "raw", + .me = THIS_MODULE, +}; + static int __init xt_ct_tg_init(void) { - return xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + int ret; + + ret = xt_register_target(¬rack_tg_reg); + if (ret < 0) + return ret; + + ret = xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + if (ret < 0) { + xt_unregister_target(¬rack_tg_reg); + return ret; + } + return 0; } static void __exit xt_ct_tg_exit(void) { xt_unregister_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + xt_unregister_target(¬rack_tg_reg); } module_init(xt_ct_tg_init); @@ -394,3 +448,5 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: connection tracking target"); MODULE_ALIAS("ipt_CT"); MODULE_ALIAS("ip6t_CT"); +MODULE_ALIAS("ipt_NOTRACK"); +MODULE_ALIAS("ip6t_NOTRACK"); diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c index 1686ca1b53a1..73b73f687c58 100644 --- a/net/netfilter/xt_HMARK.c +++ b/net/netfilter/xt_HMARK.c @@ -167,7 +167,7 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t, const struct xt_hmark_info *info) { struct ipv6hdr *ip6, _ip6; - int flag = IP6T_FH_F_AUTH; + int flag = IP6_FH_F_AUTH; unsigned int nhoff = 0; u16 fragoff = 0; int nexthdr; @@ -177,7 +177,7 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t, if (nexthdr < 0) return 0; /* No need to check for icmp errors on fragments */ - if ((flag & IP6T_FH_F_FRAG) || (nexthdr != IPPROTO_ICMPV6)) + if ((flag & IP6_FH_F_FRAG) || (nexthdr != IPPROTO_ICMPV6)) goto noicmp; /* Use inner header in case of ICMP errors */ if (get_inner6_hdr(skb, &nhoff)) { @@ -185,7 +185,7 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t, if (ip6 == NULL) return -1; /* If AH present, use SPI like in ESP. */ - flag = IP6T_FH_F_AUTH; + flag = IP6_FH_F_AUTH; nexthdr = ipv6_find_hdr(skb, &nhoff, -1, &fragoff, &flag); if (nexthdr < 0) return -1; @@ -201,7 +201,7 @@ noicmp: if (t->proto == IPPROTO_ICMPV6) return 0; - if (flag & IP6T_FH_F_FRAG) + if (flag & IP6_FH_F_FRAG) return 0; hmark_set_tuple_ports(skb, nhoff, t, info); diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 26a668a84aa2..a9d7af953ceb 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -157,11 +157,22 @@ dsthash_find(const struct xt_hashlimit_htable *ht, /* allocate dsthash_ent, initialize dst, put in htable and lock it */ static struct dsthash_ent * dsthash_alloc_init(struct xt_hashlimit_htable *ht, - const struct dsthash_dst *dst) + const struct dsthash_dst *dst, bool *race) { struct dsthash_ent *ent; spin_lock(&ht->lock); + + /* Two or more packets may race to create the same entry in the + * hashtable, double check if this packet lost race. + */ + ent = dsthash_find(ht, dst); + if (ent != NULL) { + spin_unlock(&ht->lock); + *race = true; + return ent; + } + /* initialize hash with random val at the time we allocate * the first hashtable entry */ if (unlikely(!ht->rnd_initialized)) { @@ -318,7 +329,10 @@ static void htable_destroy(struct xt_hashlimit_htable *hinfo) parent = hashlimit_net->ipt_hashlimit; else parent = hashlimit_net->ip6t_hashlimit; - remove_proc_entry(hinfo->pde->name, parent); + + if(parent != NULL) + remove_proc_entry(hinfo->pde->name, parent); + htable_selective_cleanup(hinfo, select_all); vfree(hinfo); } @@ -585,6 +599,7 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; + bool race = false; u32 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) @@ -593,13 +608,18 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) rcu_read_lock_bh(); dh = dsthash_find(hinfo, &dst); if (dh == NULL) { - dh = dsthash_alloc_init(hinfo, &dst); + dh = dsthash_alloc_init(hinfo, &dst, &race); if (dh == NULL) { rcu_read_unlock_bh(); goto hotdrop; + } else if (race) { + /* Already got an entry, update expiration timeout */ + dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); + rateinfo_recalc(dh, now, hinfo->cfg.mode); + } else { + dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); + rateinfo_init(dh, hinfo); } - dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_init(dh, hinfo); } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); @@ -856,6 +876,27 @@ static int __net_init hashlimit_proc_net_init(struct net *net) static void __net_exit hashlimit_proc_net_exit(struct net *net) { + struct xt_hashlimit_htable *hinfo; + struct hlist_node *pos; + struct proc_dir_entry *pde; + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); + + /* recent_net_exit() is called before recent_mt_destroy(). Make sure + * that the parent xt_recent proc entry is is empty before trying to + * remove it. + */ + mutex_lock(&hashlimit_mutex); + pde = hashlimit_net->ipt_hashlimit; + if (pde == NULL) + pde = hashlimit_net->ip6t_hashlimit; + + hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) + remove_proc_entry(hinfo->pde->name, pde); + + hashlimit_net->ipt_hashlimit = NULL; + hashlimit_net->ip6t_hashlimit = NULL; + mutex_unlock(&hashlimit_mutex); + proc_net_remove(net, "ipt_hashlimit"); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) proc_net_remove(net, "ip6t_hashlimit"); @@ -872,9 +913,6 @@ static int __net_init hashlimit_net_init(struct net *net) static void __net_exit hashlimit_net_exit(struct net *net) { - struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); - - BUG_ON(!hlist_empty(&hashlimit_net->htables)); hashlimit_proc_net_exit(net); } diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index bb10b0717f1b..8d47c3780fda 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -67,7 +67,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) goto out; } - ip_vs_fill_iphdr(family, skb_network_header(skb), &iph); + ip_vs_fill_iph_skb(family, skb, &iph); if (data->bitmask & XT_IPVS_PROTO) if ((iph.protocol == data->l4proto) ^ @@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(family, skb, &iph, iph.len, 1 /* inverse */); + cp = pp->conn_out_get(family, skb, &iph, 1 /* inverse */); if (unlikely(cp == NULL)) { match = false; goto out; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 4635c9b00459..978efc9b555a 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -29,6 +29,7 @@ #include <linux/skbuff.h> #include <linux/inet.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -310,6 +311,14 @@ out: return ret; } +static void recent_table_free(void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} + static int recent_mt_check(const struct xt_mtchk_param *par, const struct xt_recent_mtinfo_v1 *info) { @@ -322,6 +331,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par, #endif unsigned int i; int ret = -EINVAL; + size_t sz; if (unlikely(!hash_rnd_inited)) { get_random_bytes(&hash_rnd, sizeof(hash_rnd)); @@ -360,8 +370,11 @@ static int recent_mt_check(const struct xt_mtchk_param *par, goto out; } - t = kzalloc(sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size, - GFP_KERNEL); + sz = sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size; + if (sz <= PAGE_SIZE) + t = kzalloc(sz, GFP_KERNEL); + else + t = vzalloc(sz); if (t == NULL) { ret = -ENOMEM; goto out; @@ -377,14 +390,14 @@ static int recent_mt_check(const struct xt_mtchk_param *par, uid = make_kuid(&init_user_ns, ip_list_uid); gid = make_kgid(&init_user_ns, ip_list_gid); if (!uid_valid(uid) || !gid_valid(gid)) { - kfree(t); + recent_table_free(t); ret = -EINVAL; goto out; } pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent, &recent_mt_fops, t); if (pde == NULL) { - kfree(t); + recent_table_free(t); ret = -ENOMEM; goto out; } @@ -431,10 +444,11 @@ static void recent_mt_destroy(const struct xt_mtdtor_param *par) list_del(&t->list); spin_unlock_bh(&recent_lock); #ifdef CONFIG_PROC_FS - remove_proc_entry(t->name, recent_net->xt_recent); + if (recent_net->xt_recent != NULL) + remove_proc_entry(t->name, recent_net->xt_recent); #endif recent_table_flush(t); - kfree(t); + recent_table_free(t); } mutex_unlock(&recent_mutex); } @@ -615,6 +629,20 @@ static int __net_init recent_proc_net_init(struct net *net) static void __net_exit recent_proc_net_exit(struct net *net) { + struct recent_net *recent_net = recent_pernet(net); + struct recent_table *t; + + /* recent_net_exit() is called before recent_mt_destroy(). Make sure + * that the parent xt_recent proc entry is is empty before trying to + * remove it. + */ + spin_lock_bh(&recent_lock); + list_for_each_entry(t, &recent_net->tables, list) + remove_proc_entry(t->name, recent_net->xt_recent); + + recent_net->xt_recent = NULL; + spin_unlock_bh(&recent_lock); + proc_net_remove(net, "xt_recent"); } #else @@ -638,9 +666,6 @@ static int __net_init recent_net_init(struct net *net) static void __net_exit recent_net_exit(struct net *net) { - struct recent_net *recent_net = recent_pernet(net); - - BUG_ON(!list_empty(&recent_net->tables)); recent_proc_net_exit(net); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4da797fa5ec5..c0353d55d56f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -612,7 +612,7 @@ retry: static inline int netlink_capable(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || - capable(CAP_NET_ADMIN); + ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); } static void @@ -669,6 +669,9 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err; + if (addr_len < sizeof(struct sockaddr_nl)) + return -EINVAL; + if (nladdr->nl_family != AF_NETLINK) return -EINVAL; @@ -2059,7 +2062,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v) struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); - seq_printf(seq, "%pK %-3d %-6d %08x %-8d %-8d %pK %-8d %-8d %-8lu\n", + seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %pK %-8d %-8d %-8lu\n", s, s->sk_protocol, nlk->portid, diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig index 8d8d9bc4b6ff..60c3bbb63e8e 100644 --- a/net/nfc/Kconfig +++ b/net/nfc/Kconfig @@ -3,8 +3,8 @@ # menuconfig NFC - depends on NET && EXPERIMENTAL - tristate "NFC subsystem support (EXPERIMENTAL)" + depends on NET + tristate "NFC subsystem support" default n help Say Y here if you want to build support for NFC (Near field diff --git a/net/nfc/core.c b/net/nfc/core.c index 479bee36dc3e..aa64ea441676 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -40,6 +40,9 @@ int nfc_devlist_generation; DEFINE_MUTEX(nfc_devlist_mutex); +/* NFC device ID bitmap */ +static DEFINE_IDA(nfc_index_ida); + /** * nfc_dev_up - turn on the NFC device * @@ -181,6 +184,7 @@ int nfc_stop_poll(struct nfc_dev *dev) dev->ops->stop_poll(dev); dev->polling = false; + dev->rf_mode = NFC_RF_NONE; error: device_unlock(&dev->dev); @@ -194,7 +198,7 @@ static struct nfc_target *nfc_find_target(struct nfc_dev *dev, u32 target_idx) if (dev->n_targets == 0) return NULL; - for (i = 0; i < dev->n_targets ; i++) { + for (i = 0; i < dev->n_targets; i++) { if (dev->targets[i].idx == target_idx) return &dev->targets[i]; } @@ -274,12 +278,14 @@ int nfc_dep_link_down(struct nfc_dev *dev) if (!rc) { dev->dep_link_up = false; dev->active_target = NULL; + dev->rf_mode = NFC_RF_NONE; nfc_llcp_mac_is_down(dev); nfc_genl_dep_link_down_event(dev); } error: device_unlock(&dev->dev); + return rc; } @@ -503,6 +509,7 @@ EXPORT_SYMBOL(nfc_tm_activated); int nfc_tm_deactivated(struct nfc_dev *dev) { dev->dep_link_up = false; + dev->rf_mode = NFC_RF_NONE; return nfc_genl_tm_deactivated(dev); } @@ -697,6 +704,8 @@ static void nfc_check_pres_work(struct work_struct *work) if (dev->active_target && timer_pending(&dev->check_pres_timer) == 0) { rc = dev->ops->check_presence(dev, dev->active_target); + if (rc == -EOPNOTSUPP) + goto exit; if (!rc) { mod_timer(&dev->check_pres_timer, jiffies + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); @@ -708,6 +717,7 @@ static void nfc_check_pres_work(struct work_struct *work) } } +exit: device_unlock(&dev->dev); } @@ -753,7 +763,6 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom) { - static atomic_t dev_no = ATOMIC_INIT(0); struct nfc_dev *dev; if (!ops->start_poll || !ops->stop_poll || !ops->activate_target || @@ -767,11 +776,6 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, if (!dev) return NULL; - dev->dev.class = &nfc_class; - dev->idx = atomic_inc_return(&dev_no) - 1; - dev_set_name(&dev->dev, "nfc%d", dev->idx); - device_initialize(&dev->dev); - dev->ops = ops; dev->supported_protocols = supported_protocols; dev->tx_headroom = tx_headroom; @@ -779,6 +783,7 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, nfc_genl_data_init(&dev->genl_data); + dev->rf_mode = NFC_RF_NONE; /* first generation must not be 0 */ dev->targets_generation = 1; @@ -806,6 +811,14 @@ int nfc_register_device(struct nfc_dev *dev) pr_debug("dev_name=%s\n", dev_name(&dev->dev)); + dev->idx = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL); + if (dev->idx < 0) + return dev->idx; + + dev->dev.class = &nfc_class; + dev_set_name(&dev->dev, "nfc%d", dev->idx); + device_initialize(&dev->dev); + mutex_lock(&nfc_devlist_mutex); nfc_devlist_generation++; rc = device_add(&dev->dev); @@ -834,10 +847,12 @@ EXPORT_SYMBOL(nfc_register_device); */ void nfc_unregister_device(struct nfc_dev *dev) { - int rc; + int rc, id; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); + id = dev->idx; + mutex_lock(&nfc_devlist_mutex); nfc_devlist_generation++; @@ -856,6 +871,8 @@ void nfc_unregister_device(struct nfc_dev *dev) pr_debug("The userspace won't be notified that the device %s was removed\n", dev_name(&dev->dev)); + ida_simple_remove(&nfc_index_ida, id); + } EXPORT_SYMBOL(nfc_unregister_device); diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index 71c6a7086b8f..7d99410e6c1a 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -257,16 +257,16 @@ static u8 nfc_hci_create_pipe(struct nfc_hci_dev *hdev, u8 dest_host, *result = nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, NFC_HCI_ADM_CREATE_PIPE, (u8 *) ¶ms, sizeof(params), &skb); - if (*result == 0) { - resp = (struct hci_create_pipe_resp *)skb->data; - pipe = resp->pipe; - kfree_skb(skb); + if (*result < 0) + return NFC_HCI_INVALID_PIPE; - pr_debug("pipe created=%d\n", pipe); + resp = (struct hci_create_pipe_resp *)skb->data; + pipe = resp->pipe; + kfree_skb(skb); - return pipe; - } else - return NFC_HCI_INVALID_PIPE; + pr_debug("pipe created=%d\n", pipe); + + return pipe; } static int nfc_hci_delete_pipe(struct nfc_hci_dev *hdev, u8 pipe) @@ -279,8 +279,6 @@ static int nfc_hci_delete_pipe(struct nfc_hci_dev *hdev, u8 pipe) static int nfc_hci_clear_all_pipes(struct nfc_hci_dev *hdev) { - int r; - u8 param[2]; /* TODO: Find out what the identity reference data is @@ -288,10 +286,8 @@ static int nfc_hci_clear_all_pipes(struct nfc_hci_dev *hdev) pr_debug("\n"); - r = nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, - NFC_HCI_ADM_CLEAR_ALL_PIPE, param, 2, NULL); - - return 0; + return nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, + NFC_HCI_ADM_CLEAR_ALL_PIPE, param, 2, NULL); } int nfc_hci_disconnect_gate(struct nfc_hci_dev *hdev, u8 gate) @@ -348,7 +344,7 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate, return -EADDRINUSE; if (pipe != NFC_HCI_INVALID_PIPE) - goto pipe_is_open; + goto open_pipe; switch (dest_gate) { case NFC_HCI_LINK_MGMT_GATE: @@ -365,6 +361,7 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate, break; } +open_pipe: r = nfc_hci_open_pipe(hdev, pipe); if (r < 0) { if (pipe_created) @@ -375,7 +372,6 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate, return r; } -pipe_is_open: hdev->gate2pipe[dest_gate] = pipe; return 0; diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 5fbb6e40793e..7bea574d5934 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -33,17 +33,20 @@ /* Largest headroom needed for outgoing HCI commands */ #define HCI_CMDS_HEADROOM 1 -static int nfc_hci_result_to_errno(u8 result) +int nfc_hci_result_to_errno(u8 result) { switch (result) { case NFC_HCI_ANY_OK: return 0; + case NFC_HCI_ANY_E_REG_PAR_UNKNOWN: + return -EOPNOTSUPP; case NFC_HCI_ANY_E_TIMEOUT: return -ETIME; default: return -1; } } +EXPORT_SYMBOL(nfc_hci_result_to_errno); static void nfc_hci_msg_tx_work(struct work_struct *work) { @@ -65,8 +68,9 @@ static void nfc_hci_msg_tx_work(struct work_struct *work) -ETIME); kfree(hdev->cmd_pending_msg); hdev->cmd_pending_msg = NULL; - } else + } else { goto exit; + } } next_msg: @@ -166,7 +170,7 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, kfree_skb(skb); } -static u32 nfc_hci_sak_to_protocol(u8 sak) +u32 nfc_hci_sak_to_protocol(u8 sak) { switch (NFC_HCI_TYPE_A_SEL_PROT(sak)) { case NFC_HCI_TYPE_A_SEL_PROT_MIFARE: @@ -181,8 +185,9 @@ static u32 nfc_hci_sak_to_protocol(u8 sak) return 0xffffffff; } } +EXPORT_SYMBOL(nfc_hci_sak_to_protocol); -static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) +int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) { struct nfc_target *targets; struct sk_buff *atqa_skb = NULL; @@ -263,7 +268,9 @@ static int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate) break; } - targets->hci_reader_gate = gate; + /* if driver set the new gate, we will skip the old one */ + if (targets->hci_reader_gate == 0x00) + targets->hci_reader_gate = gate; r = nfc_targets_found(hdev->ndev, targets, 1); @@ -275,11 +282,18 @@ exit: return r; } +EXPORT_SYMBOL(nfc_hci_target_discovered); void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, struct sk_buff *skb) { int r = 0; + u8 gate = nfc_hci_pipe2gate(hdev, pipe); + + if (gate == 0xff) { + pr_err("Discarded event %x to unopened pipe %x\n", event, pipe); + goto exit; + } switch (event) { case NFC_HCI_EVT_TARGET_DISCOVERED: @@ -303,12 +317,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, goto exit; } - r = nfc_hci_target_discovered(hdev, - nfc_hci_pipe2gate(hdev, pipe)); + r = nfc_hci_target_discovered(hdev, gate); break; default: - /* TODO: Unknown events are hardware specific - * pass them to the driver (needs a new hci_ops) */ + if (hdev->ops->event_received) { + hdev->ops->event_received(hdev, gate, event, skb); + return; + } + break; } @@ -410,6 +426,10 @@ static int hci_dev_version(struct nfc_hci_dev *hdev) r = nfc_hci_get_param(hdev, NFC_HCI_ID_MGMT_GATE, NFC_HCI_ID_MGMT_VERSION_SW, &skb); + if (r == -EOPNOTSUPP) { + pr_info("Software/Hardware info not available\n"); + return 0; + } if (r < 0) return r; @@ -527,7 +547,8 @@ static int hci_start_poll(struct nfc_dev *nfc_dev, return hdev->ops->start_poll(hdev, im_protocols, tm_protocols); else return nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, - NFC_HCI_EVT_READER_REQUESTED, NULL, 0); + NFC_HCI_EVT_READER_REQUESTED, + NULL, 0); } static void hci_stop_poll(struct nfc_dev *nfc_dev) @@ -538,6 +559,28 @@ static void hci_stop_poll(struct nfc_dev *nfc_dev) NFC_HCI_EVT_END_OPERATION, NULL, 0); } +static int hci_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target, + __u8 comm_mode, __u8 *gb, size_t gb_len) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + + if (hdev->ops->dep_link_up) + return hdev->ops->dep_link_up(hdev, target, comm_mode, + gb, gb_len); + + return 0; +} + +static int hci_dep_link_down(struct nfc_dev *nfc_dev) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + + if (hdev->ops->dep_link_down) + return hdev->ops->dep_link_down(hdev); + + return 0; +} + static int hci_activate_target(struct nfc_dev *nfc_dev, struct nfc_target *target, u32 protocol) { @@ -586,8 +629,8 @@ static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, switch (target->hci_reader_gate) { case NFC_HCI_RF_READER_A_GATE: case NFC_HCI_RF_READER_B_GATE: - if (hdev->ops->data_exchange) { - r = hdev->ops->data_exchange(hdev, target, skb, cb, + if (hdev->ops->im_transceive) { + r = hdev->ops->im_transceive(hdev, target, skb, cb, cb_context); if (r <= 0) /* handled */ break; @@ -604,14 +647,14 @@ static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, skb->len, hci_transceive_cb, hdev); break; default: - if (hdev->ops->data_exchange) { - r = hdev->ops->data_exchange(hdev, target, skb, cb, + if (hdev->ops->im_transceive) { + r = hdev->ops->im_transceive(hdev, target, skb, cb, cb_context); if (r == 1) r = -ENOTSUPP; - } - else + } else { r = -ENOTSUPP; + } break; } @@ -620,6 +663,16 @@ static int hci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, return r; } +static int hci_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb) +{ + struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); + + if (hdev->ops->tm_send) + return hdev->ops->tm_send(hdev, skb); + else + return -ENOTSUPP; +} + static int hci_check_presence(struct nfc_dev *nfc_dev, struct nfc_target *target) { @@ -723,9 +776,12 @@ static struct nfc_ops hci_nfc_ops = { .dev_down = hci_dev_down, .start_poll = hci_start_poll, .stop_poll = hci_stop_poll, + .dep_link_up = hci_dep_link_up, + .dep_link_down = hci_dep_link_down, .activate_target = hci_activate_target, .deactivate_target = hci_deactivate_target, .im_transceive = hci_transceive, + .tm_send = hci_tm_send, .check_presence = hci_check_presence, }; @@ -848,7 +904,7 @@ void nfc_hci_driver_failure(struct nfc_hci_dev *hdev, int err) } EXPORT_SYMBOL(nfc_hci_driver_failure); -void inline nfc_hci_recv_frame(struct nfc_hci_dev *hdev, struct sk_buff *skb) +void nfc_hci_recv_frame(struct nfc_hci_dev *hdev, struct sk_buff *skb) { nfc_llc_rcv_from_drv(hdev->llc, skb); } diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index ae1205ded87f..fe5e966e5b88 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -72,7 +72,7 @@ int nfc_llc_register(const char *name, struct nfc_llc_ops *ops) llc_engine->ops = ops; INIT_LIST_HEAD(&llc_engine->entry); - list_add_tail (&llc_engine->entry, &llc_engines); + list_add_tail(&llc_engine->entry, &llc_engines); return 0; } diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 01cbc72943cd..27b313befc35 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -634,9 +634,9 @@ static void llc_shdlc_sm_work(struct work_struct *work) r = llc_shdlc_connect_initiate(shdlc); else r = -ETIME; - if (r < 0) + if (r < 0) { llc_shdlc_connect_complete(shdlc, r); - else { + } else { mod_timer(&shdlc->connect_timer, jiffies + msecs_to_jiffies(SHDLC_CONNECT_VALUE_MS)); @@ -682,9 +682,8 @@ static void llc_shdlc_sm_work(struct work_struct *work) llc_shdlc_handle_send_queue(shdlc); } - if (shdlc->hard_fault) { + if (shdlc->hard_fault) shdlc->llc_failure(shdlc->hdev, shdlc->hard_fault); - } break; default: break; diff --git a/net/nfc/llcp/Kconfig b/net/nfc/llcp/Kconfig index fbf5e8150908..a1a41cd68255 100644 --- a/net/nfc/llcp/Kconfig +++ b/net/nfc/llcp/Kconfig @@ -1,6 +1,6 @@ config NFC_LLCP - depends on NFC && EXPERIMENTAL - bool "NFC LLCP support (EXPERIMENTAL)" + depends on NFC + bool "NFC LLCP support" default n help Say Y here if you want to build support for a kernel NFC LLCP diff --git a/net/nfc/llcp/commands.c b/net/nfc/llcp/commands.c index c45ccd6c094c..df24be48d4da 100644 --- a/net/nfc/llcp/commands.c +++ b/net/nfc/llcp/commands.c @@ -261,7 +261,6 @@ int nfc_llcp_disconnect(struct nfc_llcp_sock *sock) struct sk_buff *skb; struct nfc_dev *dev; struct nfc_llcp_local *local; - u16 size = 0; pr_debug("Sending DISC\n"); @@ -273,17 +272,10 @@ int nfc_llcp_disconnect(struct nfc_llcp_sock *sock) if (dev == NULL) return -ENODEV; - size += LLCP_HEADER_SIZE; - size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; - - skb = alloc_skb(size, GFP_ATOMIC); + skb = llcp_allocate_pdu(sock, LLCP_PDU_DISC, 0); if (skb == NULL) return -ENOMEM; - skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); - - skb = llcp_add_header(skb, sock->dsap, sock->ssap, LLCP_PDU_DISC); - skb_queue_tail(&local->tx_queue, skb); return 0; @@ -324,8 +316,7 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) struct sk_buff *skb; u8 *service_name_tlv = NULL, service_name_tlv_length; u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; - __be16 miux; + u8 *rw_tlv = NULL, rw_tlv_length; int err; u16 size = 0; @@ -343,13 +334,11 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) size += service_name_tlv_length; } - miux = cpu_to_be16(LLCP_MAX_MIUX); - miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, + miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_tlv_length); size += miux_tlv_length; - rw = LLCP_MAX_RW; - rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &local->rw, 0, &rw_tlv_length); size += rw_tlv_length; pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len); @@ -386,8 +375,7 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) struct nfc_llcp_local *local; struct sk_buff *skb; u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; - __be16 miux; + u8 *rw_tlv = NULL, rw_tlv_length; int err; u16 size = 0; @@ -397,13 +385,11 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) if (local == NULL) return -ENODEV; - miux = cpu_to_be16(LLCP_MAX_MIUX); - miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, + miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_tlv_length); size += miux_tlv_length; - rw = LLCP_MAX_RW; - rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &local->rw, 0, &rw_tlv_length); size += rw_tlv_length; skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size); @@ -428,6 +414,52 @@ error_tlv: return err; } +int nfc_llcp_send_snl(struct nfc_llcp_local *local, u8 tid, u8 sap) +{ + struct sk_buff *skb; + struct nfc_dev *dev; + u8 *sdres_tlv = NULL, sdres_tlv_length, sdres[2]; + u16 size = 0; + + pr_debug("Sending SNL tid 0x%x sap 0x%x\n", tid, sap); + + if (local == NULL) + return -ENODEV; + + dev = local->dev; + if (dev == NULL) + return -ENODEV; + + sdres[0] = tid; + sdres[1] = sap; + sdres_tlv = nfc_llcp_build_tlv(LLCP_TLV_SDRES, sdres, 0, + &sdres_tlv_length); + if (sdres_tlv == NULL) + return -ENOMEM; + + size += LLCP_HEADER_SIZE; + size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; + size += sdres_tlv_length; + + skb = alloc_skb(size, GFP_KERNEL); + if (skb == NULL) { + kfree(sdres_tlv); + return -ENOMEM; + } + + skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); + + skb = llcp_add_header(skb, LLCP_SAP_SDP, LLCP_SAP_SDP, LLCP_PDU_SNL); + + memcpy(skb_put(skb, sdres_tlv_length), sdres_tlv, sdres_tlv_length); + + skb_queue_tail(&local->tx_queue, skb); + + kfree(sdres_tlv); + + return 0; +} + int nfc_llcp_send_dm(struct nfc_llcp_local *local, u8 ssap, u8 dsap, u8 reason) { struct sk_buff *skb; @@ -496,6 +528,23 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, if (local == NULL) return -ENODEV; + /* Remote is ready but has not acknowledged our frames */ + if((sock->remote_ready && + skb_queue_len(&sock->tx_pending_queue) >= sock->rw && + skb_queue_len(&sock->tx_queue) >= 2 * sock->rw)) { + pr_err("Pending queue is full %d frames\n", + skb_queue_len(&sock->tx_pending_queue)); + return -ENOBUFS; + } + + /* Remote is not ready and we've been queueing enough frames */ + if ((!sock->remote_ready && + skb_queue_len(&sock->tx_queue) >= 2 * sock->rw)) { + pr_err("Tx queue is full %d frames\n", + skb_queue_len(&sock->tx_queue)); + return -ENOBUFS; + } + msg_data = kzalloc(len, GFP_KERNEL); if (msg_data == NULL) return -ENOMEM; @@ -541,6 +590,63 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, return len; } +int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, + struct msghdr *msg, size_t len) +{ + struct sk_buff *pdu; + struct nfc_llcp_local *local; + size_t frag_len = 0, remaining_len; + u8 *msg_ptr, *msg_data; + int err; + + pr_debug("Send UI frame len %zd\n", len); + + local = sock->local; + if (local == NULL) + return -ENODEV; + + msg_data = kzalloc(len, GFP_KERNEL); + if (msg_data == NULL) + return -ENOMEM; + + if (memcpy_fromiovec(msg_data, msg->msg_iov, len)) { + kfree(msg_data); + return -EFAULT; + } + + remaining_len = len; + msg_ptr = msg_data; + + while (remaining_len > 0) { + + frag_len = min_t(size_t, sock->miu, remaining_len); + + pr_debug("Fragment %zd bytes remaining %zd", + frag_len, remaining_len); + + pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, + frag_len + LLCP_HEADER_SIZE, &err); + if (pdu == NULL) { + pr_err("Could not allocate PDU\n"); + continue; + } + + pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); + + memcpy(skb_put(pdu, frag_len), msg_ptr, frag_len); + + /* No need to check for the peer RW for UI frames */ + skb_queue_tail(&local->tx_queue, pdu); + + remaining_len -= frag_len; + msg_ptr += frag_len; + } + + kfree(msg_data); + + return len; +} + int nfc_llcp_send_rr(struct nfc_llcp_sock *sock) { struct sk_buff *skb; diff --git a/net/nfc/llcp/llcp.c b/net/nfc/llcp/llcp.c index cc10d073c338..ec43914c92a9 100644 --- a/net/nfc/llcp/llcp.c +++ b/net/nfc/llcp/llcp.c @@ -45,12 +45,38 @@ void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *sk) write_unlock(&l->lock); } +static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock) +{ + struct nfc_llcp_local *local = sock->local; + struct sk_buff *s, *tmp; + + pr_debug("%p\n", &sock->sk); + + skb_queue_purge(&sock->tx_queue); + skb_queue_purge(&sock->tx_pending_queue); + skb_queue_purge(&sock->tx_backlog_queue); + + if (local == NULL) + return; + + /* Search for local pending SKBs that are related to this socket */ + skb_queue_walk_safe(&local->tx_queue, s, tmp) { + if (s->sk != &sock->sk) + continue; + + skb_unlink(s, &local->tx_queue); + kfree_skb(s); + } +} + static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) { struct sock *sk; struct hlist_node *node, *tmp; struct nfc_llcp_sock *llcp_sock; + skb_queue_purge(&local->tx_queue); + write_lock(&local->sockets.lock); sk_for_each_safe(sk, node, tmp, &local->sockets.head) { @@ -58,6 +84,8 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) bh_lock_sock(sk); + nfc_llcp_socket_purge(llcp_sock); + if (sk->sk_state == LLCP_CONNECTED) nfc_put_device(llcp_sock->dev); @@ -65,7 +93,8 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) struct nfc_llcp_sock *lsk, *n; struct sock *accept_sk; - list_for_each_entry_safe(lsk, n, &llcp_sock->accept_queue, + list_for_each_entry_safe(lsk, n, + &llcp_sock->accept_queue, accept_queue) { accept_sk = &lsk->sk; bh_lock_sock(accept_sk); @@ -85,6 +114,16 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) } } + /* + * If we have a connection less socket bound, we keep it alive + * if the device is still present. + */ + if (sk->sk_state == LLCP_BOUND && sk->sk_type == SOCK_DGRAM && + listen == true) { + bh_unlock_sock(sk); + continue; + } + sk->sk_state = LLCP_CLOSED; bh_unlock_sock(sk); @@ -134,7 +173,7 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, { struct sock *sk; struct hlist_node *node; - struct nfc_llcp_sock *llcp_sock; + struct nfc_llcp_sock *llcp_sock, *tmp_sock; pr_debug("ssap dsap %d %d\n", ssap, dsap); @@ -146,10 +185,12 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, llcp_sock = NULL; sk_for_each(sk, node, &local->sockets.head) { - llcp_sock = nfc_llcp_sock(sk); + tmp_sock = nfc_llcp_sock(sk); - if (llcp_sock->ssap == ssap && llcp_sock->dsap == dsap) + if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) { + llcp_sock = tmp_sock; break; + } } read_unlock(&local->sockets.lock); @@ -249,7 +290,12 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, pr_debug("llcp sock %p\n", tmp_sock); - if (tmp_sock->sk.sk_state != LLCP_LISTEN) + if (tmp_sock->sk.sk_type == SOCK_STREAM && + tmp_sock->sk.sk_state != LLCP_LISTEN) + continue; + + if (tmp_sock->sk.sk_type == SOCK_DGRAM && + tmp_sock->sk.sk_state != LLCP_BOUND) continue; if (tmp_sock->service_name == NULL || @@ -421,10 +467,9 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local) static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { u8 *gb_cur, *version_tlv, version, version_length; - u8 *lto_tlv, lto, lto_length; + u8 *lto_tlv, lto_length; u8 *wks_tlv, wks_length; u8 *miux_tlv, miux_length; - __be16 miux; u8 gb_len = 0; int ret = 0; @@ -433,9 +478,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) 1, &version_length); gb_len += version_length; - /* 1500 ms */ - lto = 150; - lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, <o, 1, <o_length); + lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, <o_length); gb_len += lto_length; pr_debug("Local wks 0x%lx\n", local->local_wks); @@ -443,8 +486,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) &wks_length); gb_len += wks_length; - miux = cpu_to_be16(LLCP_MAX_MIUX); - miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, + miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_length); gb_len += miux_length; @@ -610,7 +652,12 @@ static void nfc_llcp_tx_work(struct work_struct *work) if (skb != NULL) { sk = skb->sk; llcp_sock = nfc_llcp_sock(sk); - if (llcp_sock != NULL) { + + if (llcp_sock == NULL && nfc_llcp_ptype(skb) == LLCP_PDU_I) { + nfc_llcp_send_symm(local->dev); + } else { + struct sk_buff *copy_skb = NULL; + u8 ptype = nfc_llcp_ptype(skb); int ret; pr_debug("Sending pending skb\n"); @@ -618,24 +665,29 @@ static void nfc_llcp_tx_work(struct work_struct *work) DUMP_PREFIX_OFFSET, 16, 1, skb->data, skb->len, true); + if (ptype == LLCP_PDU_I) + copy_skb = skb_copy(skb, GFP_ATOMIC); + nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_TX); ret = nfc_data_exchange(local->dev, local->target_idx, skb, nfc_llcp_recv, local); - if (!ret && nfc_llcp_ptype(skb) == LLCP_PDU_I) { - skb = skb_get(skb); - skb_queue_tail(&llcp_sock->tx_pending_queue, - skb); + if (ret) { + kfree_skb(copy_skb); + goto out; } - } else { - nfc_llcp_send_symm(local->dev); + + if (ptype == LLCP_PDU_I && copy_skb) + skb_queue_tail(&llcp_sock->tx_pending_queue, + copy_skb); } } else { nfc_llcp_send_symm(local->dev); } +out: mod_timer(&local->link_timer, jiffies + msecs_to_jiffies(2 * local->remote_lto)); } @@ -704,6 +756,39 @@ static u8 *nfc_llcp_connect_sn(struct sk_buff *skb, size_t *sn_len) return NULL; } +static void nfc_llcp_recv_ui(struct nfc_llcp_local *local, + struct sk_buff *skb) +{ + struct nfc_llcp_sock *llcp_sock; + struct nfc_llcp_ui_cb *ui_cb; + u8 dsap, ssap; + + dsap = nfc_llcp_dsap(skb); + ssap = nfc_llcp_ssap(skb); + + ui_cb = nfc_llcp_ui_skb_cb(skb); + ui_cb->dsap = dsap; + ui_cb->ssap = ssap; + + printk("%s %d %d\n", __func__, dsap, ssap); + + pr_debug("%d %d\n", dsap, ssap); + + /* We're looking for a bound socket, not a client one */ + llcp_sock = nfc_llcp_sock_get(local, dsap, LLCP_SAP_SDP); + if (llcp_sock == NULL || llcp_sock->sk.sk_type != SOCK_DGRAM) + return; + + /* There is no sequence with UI frames */ + skb_pull(skb, LLCP_HEADER_SIZE); + if (sock_queue_rcv_skb(&llcp_sock->sk, skb)) { + pr_err("receive queue is full\n"); + skb_queue_head(&llcp_sock->tx_backlog_queue, skb); + } + + nfc_llcp_sock_put(llcp_sock); +} + static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, struct sk_buff *skb) { @@ -823,9 +908,6 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, fail: /* Send DM */ nfc_llcp_send_dm(local, dsap, ssap, reason); - - return; - } int nfc_llcp_queue_i_frames(struct nfc_llcp_sock *sock) @@ -903,15 +985,18 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, /* Remove skbs from the pending queue */ if (llcp_sock->send_ack_n != nr) { struct sk_buff *s, *tmp; + u8 n; llcp_sock->send_ack_n = nr; /* Remove and free all skbs until ns == nr */ skb_queue_walk_safe(&llcp_sock->tx_pending_queue, s, tmp) { + n = nfc_llcp_ns(s); + skb_unlink(s, &llcp_sock->tx_pending_queue); kfree_skb(s); - if (nfc_llcp_ns(s) == nr) + if (n == nr) break; } @@ -953,6 +1038,9 @@ static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, sk = &llcp_sock->sk; lock_sock(sk); + + nfc_llcp_socket_purge(llcp_sock); + if (sk->sk_state == LLCP_CLOSED) { release_sock(sk); nfc_llcp_sock_put(llcp_sock); @@ -1027,7 +1115,7 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) } if (llcp_sock == NULL) { - pr_err("Invalid DM\n"); + pr_debug("Already closed\n"); return; } @@ -1038,8 +1126,100 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) sk->sk_state_change(sk); nfc_llcp_sock_put(llcp_sock); +} - return; +static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, + struct sk_buff *skb) +{ + struct nfc_llcp_sock *llcp_sock; + u8 dsap, ssap, *tlv, type, length, tid, sap; + u16 tlv_len, offset; + char *service_name; + size_t service_name_len; + + dsap = nfc_llcp_dsap(skb); + ssap = nfc_llcp_ssap(skb); + + pr_debug("%d %d\n", dsap, ssap); + + if (dsap != LLCP_SAP_SDP || ssap != LLCP_SAP_SDP) { + pr_err("Wrong SNL SAP\n"); + return; + } + + tlv = &skb->data[LLCP_HEADER_SIZE]; + tlv_len = skb->len - LLCP_HEADER_SIZE; + offset = 0; + + while (offset < tlv_len) { + type = tlv[0]; + length = tlv[1]; + + switch (type) { + case LLCP_TLV_SDREQ: + tid = tlv[2]; + service_name = (char *) &tlv[3]; + service_name_len = length - 1; + + pr_debug("Looking for %.16s\n", service_name); + + if (service_name_len == strlen("urn:nfc:sn:sdp") && + !strncmp(service_name, "urn:nfc:sn:sdp", + service_name_len)) { + sap = 1; + goto send_snl; + } + + llcp_sock = nfc_llcp_sock_from_sn(local, service_name, + service_name_len); + if (!llcp_sock) { + sap = 0; + goto send_snl; + } + + /* + * We found a socket but its ssap has not been reserved + * yet. We need to assign it for good and send a reply. + * The ssap will be freed when the socket is closed. + */ + if (llcp_sock->ssap == LLCP_SDP_UNBOUND) { + atomic_t *client_count; + + sap = nfc_llcp_reserve_sdp_ssap(local); + + pr_debug("Reserving %d\n", sap); + + if (sap == LLCP_SAP_MAX) { + sap = 0; + goto send_snl; + } + + client_count = + &local->local_sdp_cnt[sap - + LLCP_WKS_NUM_SAP]; + + atomic_inc(client_count); + + llcp_sock->ssap = sap; + llcp_sock->reserved_ssap = sap; + } else { + sap = llcp_sock->ssap; + } + + pr_debug("%p %d\n", llcp_sock, sap); + +send_snl: + nfc_llcp_send_snl(local, tid, sap); + break; + + default: + pr_err("Invalid SNL tlv value 0x%x\n", type); + break; + } + + offset += length + 2; + tlv += length + 2; + } } static void nfc_llcp_rx_work(struct work_struct *work) @@ -1072,6 +1252,11 @@ static void nfc_llcp_rx_work(struct work_struct *work) pr_debug("SYMM\n"); break; + case LLCP_PDU_UI: + pr_debug("UI\n"); + nfc_llcp_recv_ui(local, skb); + break; + case LLCP_PDU_CONNECT: pr_debug("CONNECT\n"); nfc_llcp_recv_connect(local, skb); @@ -1092,6 +1277,11 @@ static void nfc_llcp_rx_work(struct work_struct *work) nfc_llcp_recv_dm(local, skb); break; + case LLCP_PDU_SNL: + pr_debug("SNL\n"); + nfc_llcp_recv_snl(local, skb); + break; + case LLCP_PDU_I: case LLCP_PDU_RR: case LLCP_PDU_RNR: @@ -1104,8 +1294,6 @@ static void nfc_llcp_rx_work(struct work_struct *work) schedule_work(&local->tx_work); kfree_skb(local->rx_pending); local->rx_pending = NULL; - - return; } void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) @@ -1121,8 +1309,6 @@ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) local->rx_pending = skb_get(skb); del_timer(&local->link_timer); schedule_work(&local->rx_work); - - return; } int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) @@ -1205,12 +1391,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) rwlock_init(&local->connecting_sockets.lock); rwlock_init(&local->raw_sockets.lock); + local->lto = 150; /* 1500 ms */ + local->rw = LLCP_MAX_RW; + local->miux = cpu_to_be16(LLCP_MAX_MIUX); + nfc_llcp_build_gb(local); local->remote_miu = LLCP_DEFAULT_MIU; local->remote_lto = LLCP_DEFAULT_LTO; - list_add(&llcp_devices, &local->list); + list_add(&local->list, &llcp_devices); return 0; } diff --git a/net/nfc/llcp/llcp.h b/net/nfc/llcp/llcp.h index fdb2d24e60bd..0d62366f8cc3 100644 --- a/net/nfc/llcp/llcp.h +++ b/net/nfc/llcp/llcp.h @@ -64,6 +64,9 @@ struct nfc_llcp_local { u32 target_idx; u8 rf_mode; u8 comm_mode; + u8 lto; + u8 rw; + __be16 miux; unsigned long local_wks; /* Well known services */ unsigned long local_sdp; /* Local services */ unsigned long local_sap; /* Local SAPs, not available for discovery */ @@ -124,6 +127,13 @@ struct nfc_llcp_sock { struct sock *parent; }; +struct nfc_llcp_ui_cb { + __u8 dsap; + __u8 ssap; +}; + +#define nfc_llcp_ui_skb_cb(__skb) ((struct nfc_llcp_ui_cb *)&((__skb)->cb[0])) + #define nfc_llcp_sock(sk) ((struct nfc_llcp_sock *) (sk)) #define nfc_llcp_dev(sk) (nfc_llcp_sock((sk))->dev) @@ -209,10 +219,13 @@ int nfc_llcp_disconnect(struct nfc_llcp_sock *sock); int nfc_llcp_send_symm(struct nfc_dev *dev); int nfc_llcp_send_connect(struct nfc_llcp_sock *sock); int nfc_llcp_send_cc(struct nfc_llcp_sock *sock); +int nfc_llcp_send_snl(struct nfc_llcp_local *local, u8 tid, u8 sap); int nfc_llcp_send_dm(struct nfc_llcp_local *local, u8 ssap, u8 dsap, u8 reason); int nfc_llcp_send_disconnect(struct nfc_llcp_sock *sock); int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, struct msghdr *msg, size_t len); +int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, + struct msghdr *msg, size_t len); int nfc_llcp_send_rr(struct nfc_llcp_sock *sock); /* Socket API */ diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index 63e4cdc92376..fea22eb41b82 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -205,8 +205,8 @@ static int llcp_sock_listen(struct socket *sock, int backlog) lock_sock(sk); - if ((sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM) - || sk->sk_state != LLCP_BOUND) { + if ((sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM) || + sk->sk_state != LLCP_BOUND) { ret = -EBADFD; goto error; } @@ -608,6 +608,21 @@ static int llcp_sock_sendmsg(struct kiocb *iocb, struct socket *sock, lock_sock(sk); + if (sk->sk_type == SOCK_DGRAM) { + struct sockaddr_nfc_llcp *addr = + (struct sockaddr_nfc_llcp *)msg->msg_name; + + if (msg->msg_namelen < sizeof(*addr)) { + release_sock(sk); + return -EINVAL; + } + + release_sock(sk); + + return nfc_llcp_send_ui_frame(llcp_sock, addr->dsap, addr->ssap, + msg, len); + } + if (sk->sk_state != LLCP_CONNECTED) { release_sock(sk); return -ENOTCONN; @@ -663,11 +678,28 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return -EFAULT; } + if (sk->sk_type == SOCK_DGRAM && msg->msg_name) { + struct nfc_llcp_ui_cb *ui_cb = nfc_llcp_ui_skb_cb(skb); + struct sockaddr_nfc_llcp sockaddr; + + pr_debug("Datagram socket %d %d\n", ui_cb->dsap, ui_cb->ssap); + + sockaddr.sa_family = AF_NFC; + sockaddr.nfc_protocol = NFC_PROTO_NFC_DEP; + sockaddr.dsap = ui_cb->dsap; + sockaddr.ssap = ui_cb->ssap; + + memcpy(msg->msg_name, &sockaddr, sizeof(sockaddr)); + msg->msg_namelen = sizeof(sockaddr); + } + /* Mark read part of skb as used */ if (!(flags & MSG_PEEK)) { /* SOCK_STREAM: re-queue skb if it contains unreceived data */ - if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_RAW) { + if (sk->sk_type == SOCK_STREAM || + sk->sk_type == SOCK_DGRAM || + sk->sk_type == SOCK_RAW) { skb_pull(skb, copied); if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); diff --git a/net/nfc/nci/Kconfig b/net/nfc/nci/Kconfig index decdc49b26d8..6d69b5f0f19b 100644 --- a/net/nfc/nci/Kconfig +++ b/net/nfc/nci/Kconfig @@ -1,6 +1,6 @@ config NFC_NCI - depends on NFC && EXPERIMENTAL - tristate "NCI protocol support (EXPERIMENTAL)" + depends on NFC + tristate "NCI protocol support" default n help NCI (NFC Controller Interface) is a communication protocol between diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index acf9abb7d99b..5f98dc1bf039 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -205,10 +205,10 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt) cmd.num_disc_configs = 0; if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && - (protocols & NFC_PROTO_JEWEL_MASK - || protocols & NFC_PROTO_MIFARE_MASK - || protocols & NFC_PROTO_ISO14443_MASK - || protocols & NFC_PROTO_NFC_DEP_MASK)) { + (protocols & NFC_PROTO_JEWEL_MASK || + protocols & NFC_PROTO_MIFARE_MASK || + protocols & NFC_PROTO_ISO14443_MASK || + protocols & NFC_PROTO_NFC_DEP_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_A_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; @@ -224,8 +224,8 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt) } if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) && - (protocols & NFC_PROTO_FELICA_MASK - || protocols & NFC_PROTO_NFC_DEP_MASK)) { + (protocols & NFC_PROTO_FELICA_MASK || + protocols & NFC_PROTO_NFC_DEP_MASK)) { cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode = NCI_NFC_F_PASSIVE_POLL_MODE; cmd.disc_configs[cmd.num_disc_configs].frequency = 1; @@ -414,13 +414,13 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev) struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); struct nci_set_config_param param; __u8 local_gb[NFC_MAX_GT_LEN]; - int i, rc = 0; + int i; param.val = nfc_get_local_general_bytes(nfc_dev, ¶m.len); if ((param.val == NULL) || (param.len == 0)) - return rc; + return 0; - if (param.len > NCI_MAX_PARAM_LEN) + if (param.len > NFC_MAX_GT_LEN) return -EINVAL; for (i = 0; i < param.len; i++) @@ -429,10 +429,8 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev) param.id = NCI_PN_ATR_REQ_GEN_BYTES; param.val = local_gb; - rc = nci_request(ndev, nci_set_config_req, (unsigned long)¶m, - msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); - - return rc; + return nci_request(ndev, nci_set_config_req, (unsigned long)¶m, + msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); } static int nci_start_poll(struct nfc_dev *nfc_dev, @@ -579,7 +577,6 @@ static void nci_deactivate_target(struct nfc_dev *nfc_dev, } } - static int nci_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target, __u8 comm_mode, __u8 *gb, size_t gb_len) { @@ -806,8 +803,8 @@ int nci_recv_frame(struct sk_buff *skb) pr_debug("len %d\n", skb->len); - if (!ndev || (!test_bit(NCI_UP, &ndev->flags) - && !test_bit(NCI_INIT, &ndev->flags))) { + if (!ndev || (!test_bit(NCI_UP, &ndev->flags) && + !test_bit(NCI_INIT, &ndev->flags))) { kfree_skb(skb); return -ENXIO; } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index c1b5285cbde7..3568ae16786d 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -29,6 +29,8 @@ #include "nfc.h" +#include "llcp/llcp.h" + static struct genl_multicast_group nfc_genl_event_mcgrp = { .name = NFC_GENL_MCAST_EVENT_NAME, }; @@ -364,7 +366,8 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) || - nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up)) + nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up) || + nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode)) goto nla_put_failure; return genlmsg_end(msg, hdr); @@ -590,7 +593,7 @@ static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || ((!info->attrs[NFC_ATTR_IM_PROTOCOLS] && !info->attrs[NFC_ATTR_PROTOCOLS]) && - !info->attrs[NFC_ATTR_TM_PROTOCOLS])) + !info->attrs[NFC_ATTR_TM_PROTOCOLS])) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); @@ -715,6 +718,146 @@ static int nfc_genl_dep_link_down(struct sk_buff *skb, struct genl_info *info) return rc; } +static int nfc_genl_send_params(struct sk_buff *msg, + struct nfc_llcp_local *local, + u32 portid, u32 seq) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, 0, + NFC_CMD_LLC_GET_PARAMS); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, local->dev->idx) || + nla_put_u8(msg, NFC_ATTR_LLC_PARAM_LTO, local->lto) || + nla_put_u8(msg, NFC_ATTR_LLC_PARAM_RW, local->rw) || + nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux))) + goto nla_put_failure; + + return genlmsg_end(msg, hdr); + +nla_put_failure: + + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) +{ + struct nfc_dev *dev; + struct nfc_llcp_local *local; + int rc = 0; + struct sk_buff *msg = NULL; + u32 idx; + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + return -EINVAL; + + idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(idx); + if (!dev) + return -ENODEV; + + device_lock(&dev->dev); + + local = nfc_llcp_find_local(dev); + if (!local) { + rc = -ENODEV; + goto exit; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + rc = -ENOMEM; + goto exit; + } + + rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq); + +exit: + device_unlock(&dev->dev); + + nfc_put_device(dev); + + if (rc < 0) { + if (msg) + nlmsg_free(msg); + + return rc; + } + + return genlmsg_reply(msg, info); +} + +static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) +{ + struct nfc_dev *dev; + struct nfc_llcp_local *local; + u8 rw = 0; + u16 miux = 0; + u32 idx; + int rc = 0; + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + (!info->attrs[NFC_ATTR_LLC_PARAM_LTO] && + !info->attrs[NFC_ATTR_LLC_PARAM_RW] && + !info->attrs[NFC_ATTR_LLC_PARAM_MIUX])) + return -EINVAL; + + if (info->attrs[NFC_ATTR_LLC_PARAM_RW]) { + rw = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_RW]); + + if (rw > LLCP_MAX_RW) + return -EINVAL; + } + + if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) { + miux = nla_get_u16(info->attrs[NFC_ATTR_LLC_PARAM_MIUX]); + + if (miux > LLCP_MAX_MIUX) + return -EINVAL; + } + + idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(idx); + if (!dev) + return -ENODEV; + + device_lock(&dev->dev); + + local = nfc_llcp_find_local(dev); + if (!local) { + nfc_put_device(dev); + rc = -ENODEV; + goto exit; + } + + if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) { + if (dev->dep_link_up) { + rc = -EINPROGRESS; + goto exit; + } + + local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]); + } + + if (info->attrs[NFC_ATTR_LLC_PARAM_RW]) + local->rw = rw; + + if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) + local->miux = cpu_to_be16(miux); + +exit: + device_unlock(&dev->dev); + + nfc_put_device(dev); + + return rc; +} + static struct genl_ops nfc_genl_ops[] = { { .cmd = NFC_CMD_GET_DEVICE, @@ -759,6 +902,16 @@ static struct genl_ops nfc_genl_ops[] = { .done = nfc_genl_dump_targets_done, .policy = nfc_genl_policy, }, + { + .cmd = NFC_CMD_LLC_GET_PARAMS, + .doit = nfc_genl_llc_get_params, + .policy = nfc_genl_policy, + }, + { + .cmd = NFC_CMD_LLC_SET_PARAMS, + .doit = nfc_genl_llc_set_params, + .policy = nfc_genl_policy, + }, }; diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index c5e42b79a418..87d914d2876a 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -56,6 +56,7 @@ void nfc_llcp_unregister_device(struct nfc_dev *dev); int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); +struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); int __init nfc_llcp_init(void); void nfc_llcp_exit(void); @@ -97,6 +98,11 @@ static inline int nfc_llcp_data_received(struct nfc_dev *dev, return 0; } +static inline struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev) +{ + return NULL; +} + static inline int nfc_llcp_init(void) { return 0; diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 8b8a6a2b2bad..313bf1bc848a 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -256,7 +256,6 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock, return rc ? : copied; } - static const struct proto_ops rawsock_ops = { .family = PF_NFC, .owner = THIS_MODULE, diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 08114478cb85..ac2defeeba83 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -28,6 +28,7 @@ #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <net/ip.h> +#include <net/ipv6.h> #include <net/checksum.h> #include <net/dsfield.h> @@ -162,6 +163,53 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, *addr = new_addr; } +static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, + __be32 addr[4], const __be32 new_addr[4]) +{ + int transport_len = skb->len - skb_transport_offset(skb); + + if (l4_proto == IPPROTO_TCP) { + if (likely(transport_len >= sizeof(struct tcphdr))) + inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb, + addr, new_addr, 1); + } else if (l4_proto == IPPROTO_UDP) { + if (likely(transport_len >= sizeof(struct udphdr))) { + struct udphdr *uh = udp_hdr(skb); + + if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { + inet_proto_csum_replace16(&uh->check, skb, + addr, new_addr, 1); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + } + } +} + +static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, + __be32 addr[4], const __be32 new_addr[4], + bool recalculate_csum) +{ + if (recalculate_csum) + update_ipv6_checksum(skb, l4_proto, addr, new_addr); + + skb->rxhash = 0; + memcpy(addr, new_addr, sizeof(__be32[4])); +} + +static void set_ipv6_tc(struct ipv6hdr *nh, u8 tc) +{ + nh->priority = tc >> 4; + nh->flow_lbl[0] = (nh->flow_lbl[0] & 0x0F) | ((tc & 0x0F) << 4); +} + +static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl) +{ + nh->flow_lbl[0] = (nh->flow_lbl[0] & 0xF0) | (fl & 0x000F0000) >> 16; + nh->flow_lbl[1] = (fl & 0x0000FF00) >> 8; + nh->flow_lbl[2] = fl & 0x000000FF; +} + static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl) { csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8)); @@ -195,6 +243,47 @@ static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key) return 0; } +static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key) +{ + struct ipv6hdr *nh; + int err; + __be32 *saddr; + __be32 *daddr; + + err = make_writable(skb, skb_network_offset(skb) + + sizeof(struct ipv6hdr)); + if (unlikely(err)) + return err; + + nh = ipv6_hdr(skb); + saddr = (__be32 *)&nh->saddr; + daddr = (__be32 *)&nh->daddr; + + if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src))) + set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr, + ipv6_key->ipv6_src, true); + + if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) { + unsigned int offset = 0; + int flags = IP6_FH_F_SKIP_RH; + bool recalc_csum = true; + + if (ipv6_ext_hdr(nh->nexthdr)) + recalc_csum = ipv6_find_hdr(skb, &offset, + NEXTHDR_ROUTING, NULL, + &flags) != NEXTHDR_ROUTING; + + set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr, + ipv6_key->ipv6_dst, recalc_csum); + } + + set_ipv6_tc(nh, ipv6_key->ipv6_tclass); + set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label)); + nh->hop_limit = ipv6_key->ipv6_hlimit; + + return 0; +} + /* Must follow make_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -339,6 +428,10 @@ static int execute_set_action(struct sk_buff *skb, skb->priority = nla_get_u32(nested_attr); break; + case OVS_KEY_ATTR_SKB_MARK: + skb->mark = nla_get_u32(nested_attr); + break; + case OVS_KEY_ATTR_ETHERNET: err = set_eth_addr(skb, nla_data(nested_attr)); break; @@ -347,6 +440,10 @@ static int execute_set_action(struct sk_buff *skb, err = set_ipv4(skb, nla_data(nested_attr)); break; + case OVS_KEY_ATTR_IPV6: + err = set_ipv6(skb, nla_data(nested_attr)); + break; + case OVS_KEY_ATTR_TCP: err = set_tcp(skb, nla_data(nested_attr)); break; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 4c4b62ccc7d7..f996db343247 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -208,7 +208,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) int error; int key_len; - stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id()); + stats = this_cpu_ptr(dp->stats_percpu); /* Extract flow from 'skb' into 'key'. */ error = ovs_flow_extract(skb, p->port_no, &key, &key_len); @@ -282,7 +282,7 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, return 0; err: - stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id()); + stats = this_cpu_ptr(dp->stats_percpu); u64_stats_update_begin(&stats->sync); stats->n_lost++; @@ -479,8 +479,10 @@ static int validate_set(const struct nlattr *a, switch (key_type) { const struct ovs_key_ipv4 *ipv4_key; + const struct ovs_key_ipv6 *ipv6_key; case OVS_KEY_ATTR_PRIORITY: + case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_ETHERNET: break; @@ -500,6 +502,25 @@ static int validate_set(const struct nlattr *a, break; + case OVS_KEY_ATTR_IPV6: + if (flow_key->eth.type != htons(ETH_P_IPV6)) + return -EINVAL; + + if (!flow_key->ip.proto) + return -EINVAL; + + ipv6_key = nla_data(ovs_key); + if (ipv6_key->ipv6_proto != flow_key->ip.proto) + return -EINVAL; + + if (ipv6_key->ipv6_frag != flow_key->ip.frag) + return -EINVAL; + + if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000) + return -EINVAL; + + break; + case OVS_KEY_ATTR_TCP: if (flow_key->ip.proto != IPPROTO_TCP) return -EINVAL; @@ -675,6 +696,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) goto err_flow_free; err = ovs_flow_metadata_from_nlattrs(&flow->key.phy.priority, + &flow->key.phy.skb_mark, &flow->key.phy.in_port, a[OVS_PACKET_ATTR_KEY]); if (err) @@ -694,6 +716,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) OVS_CB(packet)->flow = flow; packet->priority = flow->key.phy.priority; + packet->mark = flow->key.phy.skb_mark; rcu_read_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 98c70630ad06..c3294cebc4f2 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -604,6 +604,7 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key, key->phy.priority = skb->priority; key->phy.in_port = in_port; + key->phy.skb_mark = skb->mark; skb_reset_mac_header(skb); @@ -689,7 +690,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key, } } - } else if (key->eth.type == htons(ETH_P_ARP) && arphdr_ok(skb)) { + } else if ((key->eth.type == htons(ETH_P_ARP) || + key->eth.type == htons(ETH_P_RARP)) && arphdr_ok(skb)) { struct arp_eth_header *arp; arp = (struct arp_eth_header *)skb_network_header(skb); @@ -702,15 +704,11 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key, /* We only match on the lower 8 bits of the opcode. */ if (ntohs(arp->ar_op) <= 0xff) key->ip.proto = ntohs(arp->ar_op); - - if (key->ip.proto == ARPOP_REQUEST - || key->ip.proto == ARPOP_REPLY) { - memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src)); - memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst)); - memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN); - memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN); - key_len = SW_FLOW_KEY_OFFSET(ipv4.arp); - } + memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src)); + memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst)); + memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN); + memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN); + key_len = SW_FLOW_KEY_OFFSET(ipv4.arp); } } else if (key->eth.type == htons(ETH_P_IPV6)) { int nh_len; /* IPv6 Header + Extensions */ @@ -806,6 +804,7 @@ const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_ENCAP] = -1, [OVS_KEY_ATTR_PRIORITY] = sizeof(u32), [OVS_KEY_ATTR_IN_PORT] = sizeof(u32), + [OVS_KEY_ATTR_SKB_MARK] = sizeof(u32), [OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet), [OVS_KEY_ATTR_VLAN] = sizeof(__be16), [OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16), @@ -991,6 +990,10 @@ int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp, } else { swkey->phy.in_port = DP_MAX_PORTS; } + if (attrs & (1 << OVS_KEY_ATTR_SKB_MARK)) { + swkey->phy.skb_mark = nla_get_u32(a[OVS_KEY_ATTR_SKB_MARK]); + attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK); + } /* Data attributes. */ if (!(attrs & (1 << OVS_KEY_ATTR_ETHERNET))) @@ -1090,7 +1093,8 @@ int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp, if (err) return err; } - } else if (swkey->eth.type == htons(ETH_P_ARP)) { + } else if (swkey->eth.type == htons(ETH_P_ARP) || + swkey->eth.type == htons(ETH_P_RARP)) { const struct ovs_key_arp *arp_key; if (!(attrs & (1 << OVS_KEY_ATTR_ARP))) @@ -1117,6 +1121,8 @@ int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp, /** * ovs_flow_metadata_from_nlattrs - parses Netlink attributes into a flow key. + * @priority: receives the skb priority + * @mark: receives the skb mark * @in_port: receives the extracted input port. * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute * sequence. @@ -1126,7 +1132,7 @@ int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp, * get the metadata, that is, the parts of the flow key that cannot be * extracted from the packet itself. */ -int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port, +int ovs_flow_metadata_from_nlattrs(u32 *priority, u32 *mark, u16 *in_port, const struct nlattr *attr) { const struct nlattr *nla; @@ -1134,6 +1140,7 @@ int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port, *in_port = DP_MAX_PORTS; *priority = 0; + *mark = 0; nla_for_each_nested(nla, attr, rem) { int type = nla_type(nla); @@ -1152,6 +1159,10 @@ int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port, return -EINVAL; *in_port = nla_get_u32(nla); break; + + case OVS_KEY_ATTR_SKB_MARK: + *mark = nla_get_u32(nla); + break; } } } @@ -1173,6 +1184,10 @@ int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb) nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, swkey->phy.in_port)) goto nla_put_failure; + if (swkey->phy.skb_mark && + nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, swkey->phy.skb_mark)) + goto nla_put_failure; + nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key)); if (!nla) goto nla_put_failure; @@ -1226,7 +1241,8 @@ int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb) ipv6_key->ipv6_tclass = swkey->ip.tos; ipv6_key->ipv6_hlimit = swkey->ip.ttl; ipv6_key->ipv6_frag = swkey->ip.frag; - } else if (swkey->eth.type == htons(ETH_P_ARP)) { + } else if (swkey->eth.type == htons(ETH_P_ARP) || + swkey->eth.type == htons(ETH_P_RARP)) { struct ovs_key_arp *arp_key; nla = nla_reserve(skb, OVS_KEY_ATTR_ARP, sizeof(*arp_key)); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 14a324eb017b..a7bb60ff3b5b 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -43,6 +43,7 @@ struct sw_flow_actions { struct sw_flow_key { struct { u32 priority; /* Packet QoS priority. */ + u32 skb_mark; /* SKB mark. */ u16 in_port; /* Input switch port (or DP_MAX_PORTS). */ } phy; struct { @@ -144,6 +145,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies); * ------ --- ------ ----- * OVS_KEY_ATTR_PRIORITY 4 -- 4 8 * OVS_KEY_ATTR_IN_PORT 4 -- 4 8 + * OVS_KEY_ATTR_SKB_MARK 4 -- 4 8 * OVS_KEY_ATTR_ETHERNET 12 -- 4 16 * OVS_KEY_ATTR_ETHERTYPE 2 2 4 8 (outer VLAN ethertype) * OVS_KEY_ATTR_8021Q 4 -- 4 8 @@ -153,14 +155,14 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies); * OVS_KEY_ATTR_ICMPV6 2 2 4 8 * OVS_KEY_ATTR_ND 28 -- 4 32 * ------------------------------------------------- - * total 144 + * total 152 */ -#define FLOW_BUFSIZE 144 +#define FLOW_BUFSIZE 152 int ovs_flow_to_nlattrs(const struct sw_flow_key *, struct sk_buff *); int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp, const struct nlattr *); -int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port, +int ovs_flow_metadata_from_nlattrs(u32 *priority, u32 *mark, u16 *in_port, const struct nlattr *); #define MAX_ACTIONS_BUFSIZE (16 * 1024) diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 3c1e58ba714b..a9327e2e48ce 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -114,6 +114,15 @@ error: return ERR_PTR(err); } +static void free_port_rcu(struct rcu_head *rcu) +{ + struct netdev_vport *netdev_vport = container_of(rcu, + struct netdev_vport, rcu); + + dev_put(netdev_vport->dev); + ovs_vport_free(vport_from_priv(netdev_vport)); +} + static void netdev_destroy(struct vport *vport) { struct netdev_vport *netdev_vport = netdev_vport_priv(vport); @@ -122,10 +131,7 @@ static void netdev_destroy(struct vport *vport) netdev_rx_handler_unregister(netdev_vport->dev); dev_set_promiscuity(netdev_vport->dev, -1); - synchronize_rcu(); - - dev_put(netdev_vport->dev); - ovs_vport_free(vport); + call_rcu(&netdev_vport->rcu, free_port_rcu); } const char *ovs_netdev_get_name(const struct vport *vport) @@ -158,7 +164,7 @@ static int netdev_send(struct vport *vport, struct sk_buff *skb) if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", - ovs_dp_name(vport->dp), + netdev_vport->dev->name, packet_length(skb), mtu); goto error; } diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index f7072a25c604..6478079b3417 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -20,12 +20,15 @@ #define VPORT_NETDEV_H 1 #include <linux/netdevice.h> +#include <linux/rcupdate.h> #include "vport.h" struct vport *ovs_netdev_get_vport(struct net_device *dev); struct netdev_vport { + struct rcu_head rcu; + struct net_device *dev; }; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 03779e8a2622..70af0bedbac4 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -333,8 +333,7 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb) { struct vport_percpu_stats *stats; - stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id()); - + stats = this_cpu_ptr(vport->percpu_stats); u64_stats_update_begin(&stats->sync); stats->rx_packets++; stats->rx_bytes += skb->len; @@ -359,7 +358,7 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb) if (likely(sent)) { struct vport_percpu_stats *stats; - stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id()); + stats = this_cpu_ptr(vport->percpu_stats); u64_stats_update_begin(&stats->sync); stats->tx_packets++; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 94060edbbd70..e639645e8fec 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1881,7 +1881,35 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb_reserve(skb, hlen); skb_reset_network_header(skb); - data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll); + if (po->tp_tx_has_off) { + int off_min, off_max, off; + off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); + off_max = po->tx_ring.frame_size - tp_len; + if (sock->type == SOCK_DGRAM) { + switch (po->tp_version) { + case TPACKET_V2: + off = ph.h2->tp_net; + break; + default: + off = ph.h1->tp_net; + break; + } + } else { + switch (po->tp_version) { + case TPACKET_V2: + off = ph.h2->tp_mac; + break; + default: + off = ph.h1->tp_mac; + break; + } + } + if (unlikely((off < off_min) || (off_max < off))) + return -EINVAL; + data = ph.raw + off; + } else { + data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll); + } to_write = tp_len; if (sock->type == SOCK_DGRAM) { @@ -1907,7 +1935,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, to_write -= dev->hard_header_len; } - err = -EFAULT; offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); @@ -1957,7 +1984,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) mutex_lock(&po->pg_vec_lock); - err = -EBUSY; if (saddr == NULL) { dev = po->prot_hook.dev; proto = po->num; @@ -2478,7 +2504,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) @@ -3111,6 +3137,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return fanout_add(sk, val & 0xffff, val >> 16); } + case PACKET_TX_HAS_OFF: + { + unsigned int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) + return -EBUSY; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + po->tp_tx_has_off = !!val; + return 0; + } default: return -ENOPROTOOPT; } @@ -3202,6 +3241,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, ((u32)po->fanout->type << 16)) : 0); break; + case PACKET_TX_HAS_OFF: + val = po->tp_tx_has_off; + break; default: return -ENOPROTOOPT; } diff --git a/net/packet/internal.h b/net/packet/internal.h index 44945f6b7252..e84cab8cb7a9 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -109,6 +109,7 @@ struct packet_sock { unsigned int tp_hdrlen; unsigned int tp_reserve; unsigned int tp_loss:1; + unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; struct packet_type prot_hook ____cacheline_aligned_in_smp; }; diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 83a8389619aa..0193630d3061 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -70,6 +70,9 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr) int err; u8 pnaddr; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -230,6 +233,9 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr) int err; u8 dst; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/net/rds/ib.h b/net/rds/ib.h index 8d2b3d5a7c21..7280ab8810c2 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -50,7 +50,7 @@ struct rds_ib_cache_head { }; struct rds_ib_refill_cache { - struct rds_ib_cache_head *percpu; + struct rds_ib_cache_head __percpu *percpu; struct list_head *xfer; struct list_head *ready; }; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index a1e116277477..31b74f5e61ad 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -434,12 +434,11 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) version = RDS_PROTOCOL_3_0; while ((common >>= 1) != 0) version++; - } - printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using " - "incompatible protocol version %u.%u\n", - &dp->dp_saddr, - dp->dp_protocol_major, - dp->dp_protocol_minor); + } else + printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n", + &dp->dp_saddr, + dp->dp_protocol_major, + dp->dp_protocol_minor); return version; } diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 8d194912c695..8eb9501e3d60 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -339,8 +339,8 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn, sge->length = sizeof(struct rds_header); sge = &recv->r_sge[1]; - sge->addr = sg_dma_address(&recv->r_frag->f_sg); - sge->length = sg_dma_len(&recv->r_frag->f_sg); + sge->addr = ib_sg_dma_address(ic->i_cm_id->device, &recv->r_frag->f_sg); + sge->length = ib_sg_dma_len(ic->i_cm_id->device, &recv->r_frag->f_sg); ret = 0; out: @@ -381,7 +381,10 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill) ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr); rdsdebug("recv %p ibinc %p page %p addr %lu ret %d\n", recv, recv->r_ibinc, sg_page(&recv->r_frag->f_sg), - (long) sg_dma_address(&recv->r_frag->f_sg), ret); + (long) ib_sg_dma_address( + ic->i_cm_id->device, + &recv->r_frag->f_sg), + ret); if (ret) { rds_ib_conn_error(conn, "recv post on " "%pI4 returned %d, disconnecting and " @@ -418,20 +421,21 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, struct rds_ib_refill_cache *cache) { unsigned long flags; - struct rds_ib_cache_head *chp; struct list_head *old; + struct list_head __percpu *chpfirst; local_irq_save(flags); - chp = per_cpu_ptr(cache->percpu, smp_processor_id()); - if (!chp->first) + chpfirst = __this_cpu_read(cache->percpu->first); + if (!chpfirst) INIT_LIST_HEAD(new_item); else /* put on front */ - list_add_tail(new_item, chp->first); - chp->first = new_item; - chp->count++; + list_add_tail(new_item, chpfirst); - if (chp->count < RDS_IB_RECYCLE_BATCH_COUNT) + __this_cpu_write(chpfirst, new_item); + __this_cpu_inc(cache->percpu->count); + + if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT) goto end; /* @@ -443,12 +447,13 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, do { old = xchg(&cache->xfer, NULL); if (old) - list_splice_entire_tail(old, chp->first); - old = cmpxchg(&cache->xfer, NULL, chp->first); + list_splice_entire_tail(old, chpfirst); + old = cmpxchg(&cache->xfer, NULL, chpfirst); } while (old); - chp->first = NULL; - chp->count = 0; + + __this_cpu_write(chpfirst, NULL); + __this_cpu_write(cache->percpu->count, 0); end: local_irq_restore(flags); } diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 865adb61685a..78fc0937948d 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -213,7 +213,7 @@ static int rfkill_gpio_remove(struct platform_device *pdev) static struct platform_driver rfkill_gpio_driver = { .probe = rfkill_gpio_probe, - .remove = __devexit_p(rfkill_gpio_remove), + .remove = rfkill_gpio_remove, .driver = { .name = "rfkill_gpio", .owner = THIS_MODULE, diff --git a/net/rfkill/rfkill-regulator.c b/net/rfkill/rfkill-regulator.c index 11da3018a853..4b5ab21ecb24 100644 --- a/net/rfkill/rfkill-regulator.c +++ b/net/rfkill/rfkill-regulator.c @@ -55,7 +55,7 @@ struct rfkill_ops rfkill_regulator_ops = { .set_block = rfkill_regulator_set_block, }; -static int __devinit rfkill_regulator_probe(struct platform_device *pdev) +static int rfkill_regulator_probe(struct platform_device *pdev) { struct rfkill_regulator_platform_data *pdata = pdev->dev.platform_data; struct rfkill_regulator_data *rfkill_data; @@ -122,7 +122,7 @@ out: return ret; } -static int __devexit rfkill_regulator_remove(struct platform_device *pdev) +static int rfkill_regulator_remove(struct platform_device *pdev) { struct rfkill_regulator_data *rfkill_data = platform_get_drvdata(pdev); struct rfkill *rf_kill = rfkill_data->rf_kill; @@ -137,7 +137,7 @@ static int __devexit rfkill_regulator_remove(struct platform_device *pdev) static struct platform_driver rfkill_regulator_driver = { .probe = rfkill_regulator_probe, - .remove = __devexit_p(rfkill_regulator_remove), + .remove = rfkill_regulator_remove, .driver = { .name = "rfkill-regulator", .owner = THIS_MODULE, diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 62fb51face8a..235e01acac51 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -509,7 +509,7 @@ config NET_EMATCH_TEXT config NET_EMATCH_CANID tristate "CAN Identifier" - depends on NET_EMATCH && CAN + depends on NET_EMATCH && (CAN=y || CAN=m) ---help--- Say Y here if you want to be able to classify CAN frames based on CAN Identifier. diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 102761d294cb..65d240cbf74b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -987,6 +987,9 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; + if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN)) + return -EPERM; + ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); if (ret < 0) return ret; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 7ae02892437c..ff55ed6c49b2 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -139,6 +139,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg) int err; int tp_created = 0; + if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN)) + return -EPERM; replay: t = nlmsg_data(n); protocol = TC_H_MIN(t->tcm_info); diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 2ecde225ae60..6db7855b9029 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -17,6 +17,7 @@ #include <linux/skbuff.h> #include <linux/cgroup.h> #include <linux/rcupdate.h> +#include <linux/fdtable.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> @@ -34,25 +35,51 @@ static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p) struct cgroup_cls_state, css); } -static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) +static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp) { struct cgroup_cls_state *cs; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); + return &cs->css; +} +static int cgrp_css_online(struct cgroup *cgrp) +{ if (cgrp->parent) - cs->classid = cgrp_cls_state(cgrp->parent)->classid; - - return &cs->css; + cgrp_cls_state(cgrp)->classid = + cgrp_cls_state(cgrp->parent)->classid; + return 0; } -static void cgrp_destroy(struct cgroup *cgrp) +static void cgrp_css_free(struct cgroup *cgrp) { kfree(cgrp_cls_state(cgrp)); } +static int update_classid(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + if (sock) + sock->sk->sk_classid = (u32)(unsigned long)v; + return 0; +} + +static void cgrp_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +{ + struct task_struct *p; + void *v; + + cgroup_taskset_for_each(p, cgrp, tset) { + task_lock(p); + v = (void *)(unsigned long)task_cls_classid(p); + iterate_fd(p->files, 0, update_classid, v); + task_unlock(p); + } +} + static u64 read_classid(struct cgroup *cgrp, struct cftype *cft) { return cgrp_cls_state(cgrp)->classid; @@ -75,20 +102,13 @@ static struct cftype ss_files[] = { struct cgroup_subsys net_cls_subsys = { .name = "net_cls", - .create = cgrp_create, - .destroy = cgrp_destroy, + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = cgrp_attach, .subsys_id = net_cls_subsys_id, .base_cftypes = ss_files, .module = THIS_MODULE, - - /* - * While net_cls cgroup has the rudimentary hierarchy support of - * inheriting the parent's classid on cgroup creation, it doesn't - * properly propagates config changes in ancestors to their - * descendents. A child should follow the parent's configuration - * but be allowed to override it. Fix it and remove the following. - */ - .broken_hierarchy = true, }; struct cls_cgroup_head { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a18d975db59c..d84f7e734cd7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -495,16 +495,15 @@ EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) { - ktime_t time; - if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc_root_sleeping(wd->qdisc)->state)) return; qdisc_throttled(wd->qdisc); - time = ktime_set(0, 0); - time = ktime_add_ns(time, PSCHED_TICKS2NS(expires)); - hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); + + hrtimer_start(&wd->timer, + ns_to_ktime(PSCHED_TICKS2NS(expires)), + HRTIMER_MODE_ABS); } EXPORT_SYMBOL(qdisc_watchdog_schedule); @@ -834,6 +833,8 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, goto err_out3; } lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); + if (!netif_is_multiqueue(dev)) + sch->flags |= TCQ_F_ONETXQUEUE; } sch->handle = handle; @@ -981,6 +982,9 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *p = NULL; int err; + if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN)) + return -EPERM; + dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; @@ -1044,6 +1048,9 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *q, *p; int err; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + replay: /* Reinit, just in case something touches this. */ tcm = nlmsg_data(n); @@ -1380,6 +1387,9 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) u32 qid = TC_H_MAJ(clid); int err; + if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN)) + return -EPERM; + dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 564b9fc8efd3..0e19948470b8 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -509,8 +509,7 @@ static void cbq_ovl_delay(struct cbq_class *cl) cl->cpriority = TC_CBQ_MAXPRIO; q->pmask |= (1<<TC_CBQ_MAXPRIO); - expires = ktime_set(0, 0); - expires = ktime_add_ns(expires, PSCHED_TICKS2NS(sched)); + expires = ns_to_ktime(PSCHED_TICKS2NS(sched)); if (hrtimer_try_to_cancel(&q->delay_timer) && ktime_to_ns(ktime_sub( hrtimer_get_expires(&q->delay_timer), diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index aefc1504dc88..5d81a4478514 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -53,20 +53,19 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) static inline struct sk_buff *dequeue_skb(struct Qdisc *q) { struct sk_buff *skb = q->gso_skb; + const struct netdev_queue *txq = q->dev_queue; if (unlikely(skb)) { - struct net_device *dev = qdisc_dev(q); - struct netdev_queue *txq; - /* check the reason of requeuing without tx lock first */ - txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); + txq = netdev_get_tx_queue(txq->dev, skb_get_queue_mapping(skb)); if (!netif_xmit_frozen_or_stopped(txq)) { q->gso_skb = NULL; q->q.qlen--; } else skb = NULL; } else { - skb = q->dequeue(q); + if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) + skb = q->dequeue(q); } return skb; @@ -686,6 +685,8 @@ static void attach_one_default_qdisc(struct net_device *dev, netdev_info(dev, "activation failed\n"); return; } + if (!netif_is_multiqueue(dev)) + qdisc->flags |= TCQ_F_ONETXQUEUE; } dev_queue->qdisc_sleeping = qdisc; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 9d75b7761313..51561eafcb72 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -71,6 +71,12 @@ enum htb_cmode { HTB_CAN_SEND /* class can send */ }; +struct htb_rate_cfg { + u64 rate_bps; + u32 mult; + u32 shift; +}; + /* interior & leaf nodes; props specific to leaves are marked L: */ struct htb_class { struct Qdisc_class_common common; @@ -118,11 +124,11 @@ struct htb_class { int filter_cnt; /* token bucket parameters */ - struct qdisc_rate_table *rate; /* rate table of the class itself */ - struct qdisc_rate_table *ceil; /* ceiling rate (limits borrows too) */ - long buffer, cbuffer; /* token bucket depth/rate */ + struct htb_rate_cfg rate; + struct htb_rate_cfg ceil; + s64 buffer, cbuffer; /* token bucket depth/rate */ psched_tdiff_t mbuffer; /* max wait time */ - long tokens, ctokens; /* current number of tokens */ + s64 tokens, ctokens; /* current number of tokens */ psched_time_t t_c; /* checkpoint time */ }; @@ -162,6 +168,45 @@ struct htb_sched { struct work_struct work; }; +static u64 l2t_ns(struct htb_rate_cfg *r, unsigned int len) +{ + return ((u64)len * r->mult) >> r->shift; +} + +static void htb_precompute_ratedata(struct htb_rate_cfg *r) +{ + u64 factor; + u64 mult; + int shift; + + r->shift = 0; + r->mult = 1; + /* + * Calibrate mult, shift so that token counting is accurate + * for smallest packet size (64 bytes). Token (time in ns) is + * computed as (bytes * 8) * NSEC_PER_SEC / rate_bps. It will + * work as long as the smallest packet transfer time can be + * accurately represented in nanosec. + */ + if (r->rate_bps > 0) { + /* + * Higher shift gives better accuracy. Find the largest + * shift such that mult fits in 32 bits. + */ + for (shift = 0; shift < 16; shift++) { + r->shift = shift; + factor = 8LLU * NSEC_PER_SEC * (1 << r->shift); + mult = div64_u64(factor, r->rate_bps); + if (mult > UINT_MAX) + break; + } + + r->shift = shift - 1; + factor = 8LLU * NSEC_PER_SEC * (1 << r->shift); + r->mult = div64_u64(factor, r->rate_bps); + } +} + /* find class in global hash table using given handle */ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) { @@ -273,7 +318,7 @@ static void htb_add_to_id_tree(struct rb_root *root, * already in the queue. */ static void htb_add_to_wait_tree(struct htb_sched *q, - struct htb_class *cl, long delay) + struct htb_class *cl, s64 delay) { struct rb_node **p = &q->wait_pq[cl->level].rb_node, *parent = NULL; @@ -441,14 +486,14 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) htb_remove_class_from_row(q, cl, mask); } -static inline long htb_lowater(const struct htb_class *cl) +static inline s64 htb_lowater(const struct htb_class *cl) { if (htb_hysteresis) return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0; else return 0; } -static inline long htb_hiwater(const struct htb_class *cl) +static inline s64 htb_hiwater(const struct htb_class *cl) { if (htb_hysteresis) return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0; @@ -469,9 +514,9 @@ static inline long htb_hiwater(const struct htb_class *cl) * mode transitions per time unit. The speed gain is about 1/6. */ static inline enum htb_cmode -htb_class_mode(struct htb_class *cl, long *diff) +htb_class_mode(struct htb_class *cl, s64 *diff) { - long toks; + s64 toks; if ((toks = (cl->ctokens + *diff)) < htb_lowater(cl)) { *diff = -toks; @@ -495,7 +540,7 @@ htb_class_mode(struct htb_class *cl, long *diff) * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree). */ static void -htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, long *diff) +htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) { enum htb_cmode new_mode = htb_class_mode(cl, diff); @@ -581,26 +626,26 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_SUCCESS; } -static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, long diff) +static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, s64 diff) { - long toks = diff + cl->tokens; + s64 toks = diff + cl->tokens; if (toks > cl->buffer) toks = cl->buffer; - toks -= (long) qdisc_l2t(cl->rate, bytes); + toks -= (s64) l2t_ns(&cl->rate, bytes); if (toks <= -cl->mbuffer) toks = 1 - cl->mbuffer; cl->tokens = toks; } -static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, long diff) +static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff) { - long toks = diff + cl->ctokens; + s64 toks = diff + cl->ctokens; if (toks > cl->cbuffer) toks = cl->cbuffer; - toks -= (long) qdisc_l2t(cl->ceil, bytes); + toks -= (s64) l2t_ns(&cl->ceil, bytes); if (toks <= -cl->mbuffer) toks = 1 - cl->mbuffer; @@ -623,10 +668,10 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, { int bytes = qdisc_pkt_len(skb); enum htb_cmode old_mode; - long diff; + s64 diff; while (cl) { - diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer); + diff = min_t(s64, q->now - cl->t_c, cl->mbuffer); if (cl->level >= level) { if (cl->level == level) cl->xstats.lends++; @@ -673,7 +718,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, unsigned long stop_at = start + 2; while (time_before(jiffies, stop_at)) { struct htb_class *cl; - long diff; + s64 diff; struct rb_node *p = rb_first(&q->wait_pq[level]); if (!p) @@ -684,7 +729,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, return cl->pq_key; htb_safe_rb_erase(p, q->wait_pq + level); - diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer); + diff = min_t(s64, q->now - cl->t_c, cl->mbuffer); htb_change_class_mode(q, cl, &diff); if (cl->cmode != HTB_CAN_SEND) htb_add_to_wait_tree(q, cl, diff); @@ -871,10 +916,10 @@ ok: if (!sch->q.qlen) goto fin; - q->now = psched_get_time(); + q->now = ktime_to_ns(ktime_get()); start_at = jiffies; - next_event = q->now + 5 * PSCHED_TICKS_PER_SEC; + next_event = q->now + 5LLU * NSEC_PER_SEC; for (level = 0; level < TC_HTB_MAXDEPTH; level++) { /* common case optimization - skip event handler quickly */ @@ -884,7 +929,7 @@ ok: if (q->now >= q->near_ev_cache[level]) { event = htb_do_events(q, level, start_at); if (!event) - event = q->now + PSCHED_TICKS_PER_SEC; + event = q->now + NSEC_PER_SEC; q->near_ev_cache[level] = event; } else event = q->near_ev_cache[level]; @@ -903,10 +948,17 @@ ok: } } sch->qstats.overlimits++; - if (likely(next_event > q->now)) - qdisc_watchdog_schedule(&q->watchdog, next_event); - else + if (likely(next_event > q->now)) { + if (!test_bit(__QDISC_STATE_DEACTIVATED, + &qdisc_root_sleeping(q->watchdog.qdisc)->state)) { + ktime_t time = ns_to_ktime(next_event); + qdisc_throttled(q->watchdog.qdisc); + hrtimer_start(&q->watchdog.timer, time, + HRTIMER_MODE_ABS); + } + } else { schedule_work(&q->work); + } fin: return skb; } @@ -1082,9 +1134,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, memset(&opt, 0, sizeof(opt)); - opt.rate = cl->rate->rate; + opt.rate.rate = cl->rate.rate_bps >> 3; opt.buffer = cl->buffer; - opt.ceil = cl->ceil->rate; + opt.ceil.rate = cl->ceil.rate_bps >> 3; opt.cbuffer = cl->cbuffer; opt.quantum = cl->quantum; opt.prio = cl->prio; @@ -1203,9 +1255,6 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) qdisc_destroy(cl->un.leaf.q); } gen_kill_estimator(&cl->bstats, &cl->rate_est); - qdisc_put_rtab(cl->rate); - qdisc_put_rtab(cl->ceil); - tcf_destroy_chain(&cl->filter_list); kfree(cl); } @@ -1307,7 +1356,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; - struct qdisc_rate_table *rtab = NULL, *ctab = NULL; struct nlattr *tb[__TCA_HTB_MAX]; struct tc_htb_opt *hopt; @@ -1326,10 +1374,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, parent = parentid == TC_H_ROOT ? NULL : htb_find(parentid, sch); hopt = nla_data(tb[TCA_HTB_PARMS]); - - rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]); - ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]); - if (!rtab || !ctab) + if (!hopt->rate.rate || !hopt->ceil.rate) goto failure; if (!cl) { /* new class */ @@ -1439,7 +1484,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, * is really leaf before changing cl->un.leaf ! */ if (!cl->level) { - cl->quantum = rtab->rate.rate / q->rate2quantum; + cl->quantum = hopt->rate.rate / q->rate2quantum; if (!hopt->quantum && cl->quantum < 1000) { pr_warning( "HTB: quantum of class %X is small. Consider r2q change.\n", @@ -1460,12 +1505,16 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->buffer = hopt->buffer; cl->cbuffer = hopt->cbuffer; - if (cl->rate) - qdisc_put_rtab(cl->rate); - cl->rate = rtab; - if (cl->ceil) - qdisc_put_rtab(cl->ceil); - cl->ceil = ctab; + + cl->rate.rate_bps = (u64)hopt->rate.rate << 3; + cl->ceil.rate_bps = (u64)hopt->ceil.rate << 3; + + htb_precompute_ratedata(&cl->rate); + htb_precompute_ratedata(&cl->ceil); + + cl->buffer = hopt->buffer << PSCHED_SHIFT; + cl->cbuffer = hopt->buffer << PSCHED_SHIFT; + sch_tree_unlock(sch); qdisc_class_hash_grow(sch, &q->clhash); @@ -1474,10 +1523,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, return 0; failure: - if (rtab) - qdisc_put_rtab(rtab); - if (ctab) - qdisc_put_rtab(ctab); return err; } diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 0a4b2f9a0094..5da78a19ac9a 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -63,6 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) if (qdisc == NULL) goto err; priv->qdiscs[ntx] = qdisc; + qdisc->flags |= TCQ_F_ONETXQUEUE; } sch->flags |= TCQ_F_MQROOT; @@ -150,7 +151,8 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, dev_deactivate(dev); *old = dev_graft_qdisc(dev_queue, new); - + if (new) + new->flags |= TCQ_F_ONETXQUEUE; if (dev->flags & IFF_UP) dev_activate(dev); return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index d1831ca966d4..accec33c454c 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -132,6 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) goto err; } priv->qdiscs[i] = qdisc; + qdisc->flags |= TCQ_F_ONETXQUEUE; } /* If the mqprio options indicate that hardware should own @@ -205,6 +206,9 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, *old = dev_graft_qdisc(dev_queue, new); + if (new) + new->flags |= TCQ_F_ONETXQUEUE; + if (dev->flags & IFF_UP) dev_activate(dev); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f0dd83cff906..6ed37652a4c3 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1,7 +1,8 @@ /* - * net/sched/sch_qfq.c Quick Fair Queueing Scheduler. + * net/sched/sch_qfq.c Quick Fair Queueing Plus Scheduler. * * Copyright (c) 2009 Fabio Checconi, Luigi Rizzo, and Paolo Valente. + * Copyright (c) 2012 Paolo Valente. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -19,12 +20,18 @@ #include <net/pkt_cls.h> -/* Quick Fair Queueing - =================== +/* Quick Fair Queueing Plus + ======================== Sources: - Fabio Checconi, Luigi Rizzo, and Paolo Valente: "QFQ: Efficient + [1] Paolo Valente, + "Reducing the Execution Time of Fair-Queueing Schedulers." + http://algo.ing.unimo.it/people/paolo/agg-sched/agg-sched.pdf + + Sources for QFQ: + + [2] Fabio Checconi, Luigi Rizzo, and Paolo Valente: "QFQ: Efficient Packet Scheduling with Tight Bandwidth Distribution Guarantees." See also: @@ -33,6 +40,20 @@ /* + QFQ+ divides classes into aggregates of at most MAX_AGG_CLASSES + classes. Each aggregate is timestamped with a virtual start time S + and a virtual finish time F, and scheduled according to its + timestamps. S and F are computed as a function of a system virtual + time function V. The classes within each aggregate are instead + scheduled with DRR. + + To speed up operations, QFQ+ divides also aggregates into a limited + number of groups. Which group a class belongs to depends on the + ratio between the maximum packet length for the class and the weight + of the class. Groups have their own S and F. In the end, QFQ+ + schedules groups, then aggregates within groups, then classes within + aggregates. See [1] and [2] for a full description. + Virtual time computations. S, F and V are all computed in fixed point arithmetic with @@ -76,26 +97,28 @@ #define QFQ_MAX_SLOTS 32 /* - * Shifts used for class<->group mapping. We allow class weights that are - * in the range [1, 2^MAX_WSHIFT], and we try to map each class i to the + * Shifts used for aggregate<->group mapping. We allow class weights that are + * in the range [1, 2^MAX_WSHIFT], and we try to map each aggregate i to the * group with the smallest index that can support the L_i / r_i configured - * for the class. + * for the classes in the aggregate. * * grp->index is the index of the group; and grp->slot_shift * is the shift for the corresponding (scaled) sigma_i. */ -#define QFQ_MAX_INDEX 19 -#define QFQ_MAX_WSHIFT 16 +#define QFQ_MAX_INDEX 24 +#define QFQ_MAX_WSHIFT 10 -#define QFQ_MAX_WEIGHT (1<<QFQ_MAX_WSHIFT) -#define QFQ_MAX_WSUM (2*QFQ_MAX_WEIGHT) +#define QFQ_MAX_WEIGHT (1<<QFQ_MAX_WSHIFT) /* see qfq_slot_insert */ +#define QFQ_MAX_WSUM (64*QFQ_MAX_WEIGHT) #define FRAC_BITS 30 /* fixed point arithmetic */ #define ONE_FP (1UL << FRAC_BITS) #define IWSUM (ONE_FP/QFQ_MAX_WSUM) -#define QFQ_MTU_SHIFT 11 -#define QFQ_MIN_SLOT_SHIFT (FRAC_BITS + QFQ_MTU_SHIFT - QFQ_MAX_INDEX) +#define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ +#define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ + +#define QFQ_MAX_AGG_CLASSES 8 /* max num classes per aggregate allowed */ /* * Possible group states. These values are used as indexes for the bitmaps @@ -105,6 +128,8 @@ enum qfq_state { ER, IR, EB, IB, QFQ_MAX_STATE }; struct qfq_group; +struct qfq_aggregate; + struct qfq_class { struct Qdisc_class_common common; @@ -115,7 +140,12 @@ struct qfq_class { struct gnet_stats_queue qstats; struct gnet_stats_rate_est rate_est; struct Qdisc *qdisc; + struct list_head alist; /* Link for active-classes list. */ + struct qfq_aggregate *agg; /* Parent aggregate. */ + int deficit; /* DRR deficit counter. */ +}; +struct qfq_aggregate { struct hlist_node next; /* Link for the slot list. */ u64 S, F; /* flow timestamps (exact) */ @@ -126,8 +156,18 @@ struct qfq_class { struct qfq_group *grp; /* these are copied from the flowset. */ - u32 inv_w; /* ONE_FP/weight */ - u32 lmax; /* Max packet size for this flow. */ + u32 class_weight; /* Weight of each class in this aggregate. */ + /* Max pkt size for the classes in this aggregate, DRR quantum. */ + int lmax; + + u32 inv_w; /* ONE_FP/(sum of weights of classes in aggr.). */ + u32 budgetmax; /* Max budget for this aggregate. */ + u32 initial_budget, budget; /* Initial and current budget. */ + + int num_classes; /* Number of classes in this aggr. */ + struct list_head active; /* DRR queue of active classes. */ + + struct hlist_node nonfull_next; /* See nonfull_aggs in qfq_sched. */ }; struct qfq_group { @@ -137,7 +177,7 @@ struct qfq_group { unsigned int front; /* Index of the front slot. */ unsigned long full_slots; /* non-empty slots */ - /* Array of RR lists of active classes. */ + /* Array of RR lists of active aggregates. */ struct hlist_head slots[QFQ_MAX_SLOTS]; }; @@ -145,13 +185,28 @@ struct qfq_sched { struct tcf_proto *filter_list; struct Qdisc_class_hash clhash; - u64 V; /* Precise virtual time. */ - u32 wsum; /* weight sum */ + u64 oldV, V; /* Precise virtual times. */ + struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ + u32 num_active_agg; /* Num. of active aggregates */ + u32 wsum; /* weight sum */ unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */ struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */ + u32 min_slot_shift; /* Index of the group-0 bit in the bitmaps. */ + + u32 max_agg_classes; /* Max number of classes per aggr. */ + struct hlist_head nonfull_aggs; /* Aggs with room for more classes. */ }; +/* + * Possible reasons why the timestamps of an aggregate are updated + * enqueue: the aggregate switches from idle to active and must scheduled + * for service + * requeue: the aggregate finishes its budget, so it stops being served and + * must be rescheduled for service + */ +enum update_reason {enqueue, requeue}; + static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) { struct qfq_sched *q = qdisc_priv(sch); @@ -181,18 +236,18 @@ static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { * index = log_2(maxlen/weight) but we need to apply the scaling. * This is used only once at flow creation. */ -static int qfq_calc_index(u32 inv_w, unsigned int maxlen) +static int qfq_calc_index(u32 inv_w, unsigned int maxlen, u32 min_slot_shift) { u64 slot_size = (u64)maxlen * inv_w; unsigned long size_map; int index = 0; - size_map = slot_size >> QFQ_MIN_SLOT_SHIFT; + size_map = slot_size >> min_slot_shift; if (!size_map) goto out; index = __fls(size_map) + 1; /* basically a log_2 */ - index -= !(slot_size - (1ULL << (index + QFQ_MIN_SLOT_SHIFT - 1))); + index -= !(slot_size - (1ULL << (index + min_slot_shift - 1))); if (index < 0) index = 0; @@ -203,32 +258,140 @@ out: return index; } -/* Length of the next packet (0 if the queue is empty). */ -static unsigned int qdisc_peek_len(struct Qdisc *sch) +static void qfq_deactivate_agg(struct qfq_sched *, struct qfq_aggregate *); +static void qfq_activate_agg(struct qfq_sched *, struct qfq_aggregate *, + enum update_reason); + +static void qfq_init_agg(struct qfq_sched *q, struct qfq_aggregate *agg, + u32 lmax, u32 weight) { - struct sk_buff *skb; + INIT_LIST_HEAD(&agg->active); + hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs); + + agg->lmax = lmax; + agg->class_weight = weight; +} + +static struct qfq_aggregate *qfq_find_agg(struct qfq_sched *q, + u32 lmax, u32 weight) +{ + struct qfq_aggregate *agg; + struct hlist_node *n; + + hlist_for_each_entry(agg, n, &q->nonfull_aggs, nonfull_next) + if (agg->lmax == lmax && agg->class_weight == weight) + return agg; + + return NULL; +} + + +/* Update aggregate as a function of the new number of classes. */ +static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg, + int new_num_classes) +{ + u32 new_agg_weight; - skb = sch->ops->peek(sch); - return skb ? qdisc_pkt_len(skb) : 0; + if (new_num_classes == q->max_agg_classes) + hlist_del_init(&agg->nonfull_next); + + if (agg->num_classes > new_num_classes && + new_num_classes == q->max_agg_classes - 1) /* agg no more full */ + hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs); + + agg->budgetmax = new_num_classes * agg->lmax; + new_agg_weight = agg->class_weight * new_num_classes; + agg->inv_w = ONE_FP/new_agg_weight; + + if (agg->grp == NULL) { + int i = qfq_calc_index(agg->inv_w, agg->budgetmax, + q->min_slot_shift); + agg->grp = &q->groups[i]; + } + + q->wsum += + (int) agg->class_weight * (new_num_classes - agg->num_classes); + + agg->num_classes = new_num_classes; +} + +/* Add class to aggregate. */ +static void qfq_add_to_agg(struct qfq_sched *q, + struct qfq_aggregate *agg, + struct qfq_class *cl) +{ + cl->agg = agg; + + qfq_update_agg(q, agg, agg->num_classes+1); + if (cl->qdisc->q.qlen > 0) { /* adding an active class */ + list_add_tail(&cl->alist, &agg->active); + if (list_first_entry(&agg->active, struct qfq_class, alist) == + cl && q->in_serv_agg != agg) /* agg was inactive */ + qfq_activate_agg(q, agg, enqueue); /* schedule agg */ + } +} + +static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *); + +static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg) +{ + if (!hlist_unhashed(&agg->nonfull_next)) + hlist_del_init(&agg->nonfull_next); + if (q->in_serv_agg == agg) + q->in_serv_agg = qfq_choose_next_agg(q); + kfree(agg); } -static void qfq_deactivate_class(struct qfq_sched *, struct qfq_class *); -static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl, - unsigned int len); +/* Deschedule class from within its parent aggregate. */ +static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) +{ + struct qfq_aggregate *agg = cl->agg; -static void qfq_update_class_params(struct qfq_sched *q, struct qfq_class *cl, - u32 lmax, u32 inv_w, int delta_w) + + list_del(&cl->alist); /* remove from RR queue of the aggregate */ + if (list_empty(&agg->active)) /* agg is now inactive */ + qfq_deactivate_agg(q, agg); +} + +/* Remove class from its parent aggregate. */ +static void qfq_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) { - int i; + struct qfq_aggregate *agg = cl->agg; - /* update qfq-specific data */ - cl->lmax = lmax; - cl->inv_w = inv_w; - i = qfq_calc_index(cl->inv_w, cl->lmax); + cl->agg = NULL; + if (agg->num_classes == 1) { /* agg being emptied, destroy it */ + qfq_destroy_agg(q, agg); + return; + } + qfq_update_agg(q, agg, agg->num_classes-1); +} - cl->grp = &q->groups[i]; +/* Deschedule class and remove it from its parent aggregate. */ +static void qfq_deact_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) +{ + if (cl->qdisc->q.qlen > 0) /* class is active */ + qfq_deactivate_class(q, cl); - q->wsum += delta_w; + qfq_rm_from_agg(q, cl); +} + +/* Move class to a new aggregate, matching the new class weight and/or lmax */ +static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, + u32 lmax) +{ + struct qfq_sched *q = qdisc_priv(sch); + struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight); + + if (new_agg == NULL) { /* create new aggregate */ + new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC); + if (new_agg == NULL) + return -ENOBUFS; + qfq_init_agg(q, new_agg, lmax, weight); + } + qfq_deact_rm_from_agg(q, cl); + qfq_add_to_agg(q, new_agg, cl); + + return 0; } static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, @@ -236,9 +399,11 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)*arg; + bool existing = false; struct nlattr *tb[TCA_QFQ_MAX + 1]; + struct qfq_aggregate *new_agg = NULL; u32 weight, lmax, inv_w; - int i, err; + int err; int delta_w; if (tca[TCA_OPTIONS] == NULL) { @@ -259,27 +424,32 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } else weight = 1; - inv_w = ONE_FP / weight; - weight = ONE_FP / inv_w; - delta_w = weight - (cl ? ONE_FP / cl->inv_w : 0); - if (q->wsum + delta_w > QFQ_MAX_WSUM) { - pr_notice("qfq: total weight out of range (%u + %u)\n", - delta_w, q->wsum); - return -EINVAL; - } - if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) { + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { pr_notice("qfq: invalid max length %u\n", lmax); return -EINVAL; } } else - lmax = 1UL << QFQ_MTU_SHIFT; + lmax = psched_mtu(qdisc_dev(sch)); + + inv_w = ONE_FP / weight; + weight = ONE_FP / inv_w; - if (cl != NULL) { - bool need_reactivation = false; + if (cl != NULL && + lmax == cl->agg->lmax && + weight == cl->agg->class_weight) + return 0; /* nothing to change */ + delta_w = weight - (cl ? cl->agg->class_weight : 0); + + if (q->wsum + delta_w > QFQ_MAX_WSUM) { + pr_notice("qfq: total weight out of range (%d + %u)\n", + delta_w, q->wsum); + return -EINVAL; + } + + if (cl != NULL) { /* modify existing class */ if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, &cl->rate_est, qdisc_root_sleeping_lock(sch), @@ -287,41 +457,18 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (err) return err; } - - if (lmax == cl->lmax && inv_w == cl->inv_w) - return 0; /* nothing to update */ - - i = qfq_calc_index(inv_w, lmax); - sch_tree_lock(sch); - if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { - /* - * shift cl->F back, to not charge the - * class for the not-yet-served head - * packet - */ - cl->F = cl->S; - /* remove class from its slot in the old group */ - qfq_deactivate_class(q, cl); - need_reactivation = true; - } - - qfq_update_class_params(q, cl, lmax, inv_w, delta_w); - - if (need_reactivation) /* activate in new group */ - qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); - sch_tree_unlock(sch); - - return 0; + existing = true; + goto set_change_agg; } + /* create and init new class */ cl = kzalloc(sizeof(struct qfq_class), GFP_KERNEL); if (cl == NULL) return -ENOBUFS; cl->refcnt = 1; cl->common.classid = classid; - - qfq_update_class_params(q, cl, lmax, inv_w, delta_w); + cl->deficit = lmax; cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); @@ -332,11 +479,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_new_estimator(&cl->bstats, &cl->rate_est, qdisc_root_sleeping_lock(sch), tca[TCA_RATE]); - if (err) { - qdisc_destroy(cl->qdisc); - kfree(cl); - return err; - } + if (err) + goto destroy_class; } sch_tree_lock(sch); @@ -345,19 +489,39 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, qdisc_class_hash_grow(sch, &q->clhash); +set_change_agg: + sch_tree_lock(sch); + new_agg = qfq_find_agg(q, lmax, weight); + if (new_agg == NULL) { /* create new aggregate */ + sch_tree_unlock(sch); + new_agg = kzalloc(sizeof(*new_agg), GFP_KERNEL); + if (new_agg == NULL) { + err = -ENOBUFS; + gen_kill_estimator(&cl->bstats, &cl->rate_est); + goto destroy_class; + } + sch_tree_lock(sch); + qfq_init_agg(q, new_agg, lmax, weight); + } + if (existing) + qfq_deact_rm_from_agg(q, cl); + qfq_add_to_agg(q, new_agg, cl); + sch_tree_unlock(sch); + *arg = (unsigned long)cl; return 0; + +destroy_class: + qdisc_destroy(cl->qdisc); + kfree(cl); + return err; } static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { struct qfq_sched *q = qdisc_priv(sch); - if (cl->inv_w) { - q->wsum -= ONE_FP / cl->inv_w; - cl->inv_w = 0; - } - + qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->bstats, &cl->rate_est); qdisc_destroy(cl->qdisc); kfree(cl); @@ -472,8 +636,8 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_QFQ_WEIGHT, ONE_FP/cl->inv_w) || - nla_put_u32(skb, TCA_QFQ_LMAX, cl->lmax)) + if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) || + nla_put_u32(skb, TCA_QFQ_LMAX, cl->agg->lmax)) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -491,8 +655,8 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, memset(&xstats, 0, sizeof(xstats)); cl->qdisc->qstats.qlen = cl->qdisc->q.qlen; - xstats.weight = ONE_FP/cl->inv_w; - xstats.lmax = cl->lmax; + xstats.weight = cl->agg->class_weight; + xstats.lmax = cl->agg->lmax; if (gnet_stats_copy_basic(d, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || @@ -643,16 +807,16 @@ static void qfq_unblock_groups(struct qfq_sched *q, int index, u64 old_F) * perhaps * old_V ^= q->V; - old_V >>= QFQ_MIN_SLOT_SHIFT; + old_V >>= q->min_slot_shift; if (old_V) { ... } * */ -static void qfq_make_eligible(struct qfq_sched *q, u64 old_V) +static void qfq_make_eligible(struct qfq_sched *q) { - unsigned long vslot = q->V >> QFQ_MIN_SLOT_SHIFT; - unsigned long old_vslot = old_V >> QFQ_MIN_SLOT_SHIFT; + unsigned long vslot = q->V >> q->min_slot_shift; + unsigned long old_vslot = q->oldV >> q->min_slot_shift; if (vslot != old_vslot) { unsigned long mask = (1UL << fls(vslot ^ old_vslot)) - 1; @@ -663,25 +827,62 @@ static void qfq_make_eligible(struct qfq_sched *q, u64 old_V) /* - * XXX we should make sure that slot becomes less than 32. - * This is guaranteed by the input values. - * roundedS is always cl->S rounded on grp->slot_shift bits. + * The index of the slot in which the aggregate is to be inserted must + * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1' + * because the start time of the group may be moved backward by one + * slot after the aggregate has been inserted, and this would cause + * non-empty slots to be right-shifted by one position. + * + * If the weight and lmax (max_pkt_size) of the classes do not change, + * then QFQ+ does meet the above contraint according to the current + * values of its parameters. In fact, if the weight and lmax of the + * classes do not change, then, from the theory, QFQ+ guarantees that + * the slot index is never higher than + * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * + * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18 + * + * When the weight of a class is increased or the lmax of the class is + * decreased, a new aggregate with smaller slot size than the original + * parent aggregate of the class may happen to be activated. The + * activation of this aggregate should be properly delayed to when the + * service of the class has finished in the ideal system tracked by + * QFQ+. If the activation of the aggregate is not delayed to this + * reference time instant, then this aggregate may be unjustly served + * before other aggregates waiting for service. This may cause the + * above bound to the slot index to be violated for some of these + * unlucky aggregates. + * + * Instead of delaying the activation of the new aggregate, which is + * quite complex, the following inaccurate but simple solution is used: + * if the slot index is higher than QFQ_MAX_SLOTS-2, then the + * timestamps of the aggregate are shifted backward so as to let the + * slot index become equal to QFQ_MAX_SLOTS-2. */ -static void qfq_slot_insert(struct qfq_group *grp, struct qfq_class *cl, +static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg, u64 roundedS) { u64 slot = (roundedS - grp->S) >> grp->slot_shift; - unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS; + unsigned int i; /* slot index in the bucket list */ + + if (unlikely(slot > QFQ_MAX_SLOTS - 2)) { + u64 deltaS = roundedS - grp->S - + ((u64)(QFQ_MAX_SLOTS - 2)<<grp->slot_shift); + agg->S -= deltaS; + agg->F -= deltaS; + slot = QFQ_MAX_SLOTS - 2; + } - hlist_add_head(&cl->next, &grp->slots[i]); + i = (grp->front + slot) % QFQ_MAX_SLOTS; + + hlist_add_head(&agg->next, &grp->slots[i]); __set_bit(slot, &grp->full_slots); } /* Maybe introduce hlist_first_entry?? */ -static struct qfq_class *qfq_slot_head(struct qfq_group *grp) +static struct qfq_aggregate *qfq_slot_head(struct qfq_group *grp) { return hlist_entry(grp->slots[grp->front].first, - struct qfq_class, next); + struct qfq_aggregate, next); } /* @@ -689,20 +890,20 @@ static struct qfq_class *qfq_slot_head(struct qfq_group *grp) */ static void qfq_front_slot_remove(struct qfq_group *grp) { - struct qfq_class *cl = qfq_slot_head(grp); + struct qfq_aggregate *agg = qfq_slot_head(grp); - BUG_ON(!cl); - hlist_del(&cl->next); + BUG_ON(!agg); + hlist_del(&agg->next); if (hlist_empty(&grp->slots[grp->front])) __clear_bit(0, &grp->full_slots); } /* - * Returns the first full queue in a group. As a side effect, - * adjust the bucket list so the first non-empty bucket is at - * position 0 in full_slots. + * Returns the first aggregate in the first non-empty bucket of the + * group. As a side effect, adjusts the bucket list so the first + * non-empty bucket is at position 0 in full_slots. */ -static struct qfq_class *qfq_slot_scan(struct qfq_group *grp) +static struct qfq_aggregate *qfq_slot_scan(struct qfq_group *grp) { unsigned int i; @@ -738,7 +939,7 @@ static void qfq_slot_rotate(struct qfq_group *grp, u64 roundedS) grp->front = (grp->front - i) % QFQ_MAX_SLOTS; } -static void qfq_update_eligible(struct qfq_sched *q, u64 old_V) +static void qfq_update_eligible(struct qfq_sched *q) { struct qfq_group *grp; unsigned long ineligible; @@ -750,137 +951,226 @@ static void qfq_update_eligible(struct qfq_sched *q, u64 old_V) if (qfq_gt(grp->S, q->V)) q->V = grp->S; } - qfq_make_eligible(q, old_V); + qfq_make_eligible(q); } } -/* - * Updates the class, returns true if also the group needs to be updated. - */ -static bool qfq_update_class(struct qfq_group *grp, struct qfq_class *cl) +/* Dequeue head packet of the head class in the DRR queue of the aggregate. */ +static void agg_dequeue(struct qfq_aggregate *agg, + struct qfq_class *cl, unsigned int len) { - unsigned int len = qdisc_peek_len(cl->qdisc); + qdisc_dequeue_peeked(cl->qdisc); - cl->S = cl->F; - if (!len) - qfq_front_slot_remove(grp); /* queue is empty */ - else { - u64 roundedS; - - cl->F = cl->S + (u64)len * cl->inv_w; - roundedS = qfq_round_down(cl->S, grp->slot_shift); - if (roundedS == grp->S) - return false; + cl->deficit -= (int) len; - qfq_front_slot_remove(grp); - qfq_slot_insert(grp, cl, roundedS); + if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */ + list_del(&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); } +} - return true; +static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, + struct qfq_class **cl, + unsigned int *len) +{ + struct sk_buff *skb; + + *cl = list_first_entry(&agg->active, struct qfq_class, alist); + skb = (*cl)->qdisc->ops->peek((*cl)->qdisc); + if (skb == NULL) + WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n"); + else + *len = qdisc_pkt_len(skb); + + return skb; +} + +/* Update F according to the actual service received by the aggregate. */ +static inline void charge_actual_service(struct qfq_aggregate *agg) +{ + /* compute the service received by the aggregate */ + u32 service_received = agg->initial_budget - agg->budget; + + agg->F = agg->S + (u64)service_received * agg->inv_w; } static struct sk_buff *qfq_dequeue(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_group *grp; + struct qfq_aggregate *in_serv_agg = q->in_serv_agg; struct qfq_class *cl; - struct sk_buff *skb; - unsigned int len; - u64 old_V; + struct sk_buff *skb = NULL; + /* next-packet len, 0 means no more active classes in in-service agg */ + unsigned int len = 0; - if (!q->bitmaps[ER]) + if (in_serv_agg == NULL) return NULL; - grp = qfq_ffs(q, q->bitmaps[ER]); + if (!list_empty(&in_serv_agg->active)) + skb = qfq_peek_skb(in_serv_agg, &cl, &len); - cl = qfq_slot_head(grp); - skb = qdisc_dequeue_peeked(cl->qdisc); - if (!skb) { - WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n"); - return NULL; + /* + * If there are no active classes in the in-service aggregate, + * or if the aggregate has not enough budget to serve its next + * class, then choose the next aggregate to serve. + */ + if (len == 0 || in_serv_agg->budget < len) { + charge_actual_service(in_serv_agg); + + /* recharge the budget of the aggregate */ + in_serv_agg->initial_budget = in_serv_agg->budget = + in_serv_agg->budgetmax; + + if (!list_empty(&in_serv_agg->active)) + /* + * Still active: reschedule for + * service. Possible optimization: if no other + * aggregate is active, then there is no point + * in rescheduling this aggregate, and we can + * just keep it as the in-service one. This + * should be however a corner case, and to + * handle it, we would need to maintain an + * extra num_active_aggs field. + */ + qfq_activate_agg(q, in_serv_agg, requeue); + else if (sch->q.qlen == 0) { /* no aggregate to serve */ + q->in_serv_agg = NULL; + return NULL; + } + + /* + * If we get here, there are other aggregates queued: + * choose the new aggregate to serve. + */ + in_serv_agg = q->in_serv_agg = qfq_choose_next_agg(q); + skb = qfq_peek_skb(in_serv_agg, &cl, &len); } + if (!skb) + return NULL; sch->q.qlen--; qdisc_bstats_update(sch, skb); - old_V = q->V; - len = qdisc_pkt_len(skb); + agg_dequeue(in_serv_agg, cl, len); + in_serv_agg->budget -= len; q->V += (u64)len * IWSUM; pr_debug("qfq dequeue: len %u F %lld now %lld\n", - len, (unsigned long long) cl->F, (unsigned long long) q->V); + len, (unsigned long long) in_serv_agg->F, + (unsigned long long) q->V); - if (qfq_update_class(grp, cl)) { - u64 old_F = grp->F; + return skb; +} - cl = qfq_slot_scan(grp); - if (!cl) - __clear_bit(grp->index, &q->bitmaps[ER]); - else { - u64 roundedS = qfq_round_down(cl->S, grp->slot_shift); - unsigned int s; +static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q) +{ + struct qfq_group *grp; + struct qfq_aggregate *agg, *new_front_agg; + u64 old_F; - if (grp->S == roundedS) - goto skip_unblock; - grp->S = roundedS; - grp->F = roundedS + (2ULL << grp->slot_shift); - __clear_bit(grp->index, &q->bitmaps[ER]); - s = qfq_calc_state(q, grp); - __set_bit(grp->index, &q->bitmaps[s]); - } + qfq_update_eligible(q); + q->oldV = q->V; - qfq_unblock_groups(q, grp->index, old_F); + if (!q->bitmaps[ER]) + return NULL; + + grp = qfq_ffs(q, q->bitmaps[ER]); + old_F = grp->F; + + agg = qfq_slot_head(grp); + + /* agg starts to be served, remove it from schedule */ + qfq_front_slot_remove(grp); + + new_front_agg = qfq_slot_scan(grp); + + if (new_front_agg == NULL) /* group is now inactive, remove from ER */ + __clear_bit(grp->index, &q->bitmaps[ER]); + else { + u64 roundedS = qfq_round_down(new_front_agg->S, + grp->slot_shift); + unsigned int s; + + if (grp->S == roundedS) + return agg; + grp->S = roundedS; + grp->F = roundedS + (2ULL << grp->slot_shift); + __clear_bit(grp->index, &q->bitmaps[ER]); + s = qfq_calc_state(q, grp); + __set_bit(grp->index, &q->bitmaps[s]); } -skip_unblock: - qfq_update_eligible(q, old_V); + qfq_unblock_groups(q, grp->index, old_F); - return skb; + return agg; } /* - * Assign a reasonable start time for a new flow k in group i. + * Assign a reasonable start time for a new aggregate in group i. * Admissible values for \hat(F) are multiples of \sigma_i * no greater than V+\sigma_i . Larger values mean that * we had a wraparound so we consider the timestamp to be stale. * * If F is not stale and F >= V then we set S = F. * Otherwise we should assign S = V, but this may violate - * the ordering in ER. So, if we have groups in ER, set S to - * the F_j of the first group j which would be blocking us. + * the ordering in EB (see [2]). So, if we have groups in ER, + * set S to the F_j of the first group j which would be blocking us. * We are guaranteed not to move S backward because * otherwise our group i would still be blocked. */ -static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl) +static void qfq_update_start(struct qfq_sched *q, struct qfq_aggregate *agg) { unsigned long mask; u64 limit, roundedF; - int slot_shift = cl->grp->slot_shift; + int slot_shift = agg->grp->slot_shift; - roundedF = qfq_round_down(cl->F, slot_shift); + roundedF = qfq_round_down(agg->F, slot_shift); limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift); - if (!qfq_gt(cl->F, q->V) || qfq_gt(roundedF, limit)) { + if (!qfq_gt(agg->F, q->V) || qfq_gt(roundedF, limit)) { /* timestamp was stale */ - mask = mask_from(q->bitmaps[ER], cl->grp->index); + mask = mask_from(q->bitmaps[ER], agg->grp->index); if (mask) { struct qfq_group *next = qfq_ffs(q, mask); if (qfq_gt(roundedF, next->F)) { if (qfq_gt(limit, next->F)) - cl->S = next->F; + agg->S = next->F; else /* preserve timestamp correctness */ - cl->S = limit; + agg->S = limit; return; } } - cl->S = q->V; + agg->S = q->V; } else /* timestamp is not stale */ - cl->S = cl->F; + agg->S = agg->F; +} + +/* + * Update the timestamps of agg before scheduling/rescheduling it for + * service. In particular, assign to agg->F its maximum possible + * value, i.e., the virtual finish time with which the aggregate + * should be labeled if it used all its budget once in service. + */ +static inline void +qfq_update_agg_ts(struct qfq_sched *q, + struct qfq_aggregate *agg, enum update_reason reason) +{ + if (reason != requeue) + qfq_update_start(q, agg); + else /* just charge agg for the service received */ + agg->S = agg->F; + + agg->F = agg->S + (u64)agg->budgetmax * agg->inv_w; } +static void qfq_schedule_agg(struct qfq_sched *, struct qfq_aggregate *); + static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; + struct qfq_aggregate *agg; int err = 0; cl = qfq_classify(skb, sch, &err); @@ -892,6 +1182,15 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) } pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); + if (unlikely(cl->agg->lmax < qdisc_pkt_len(skb))) { + pr_debug("qfq: increasing maxpkt from %u to %u for class %u", + cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid); + err = qfq_change_agg(sch, cl, cl->agg->class_weight, + qdisc_pkt_len(skb)); + if (err) + return err; + } + err = qdisc_enqueue(skb, cl->qdisc); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); @@ -905,35 +1204,50 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) bstats_update(&cl->bstats, skb); ++sch->q.qlen; - /* If the new skb is not the head of queue, then done here. */ - if (cl->qdisc->q.qlen != 1) + agg = cl->agg; + /* if the queue was not empty, then done here */ + if (cl->qdisc->q.qlen != 1) { + if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) && + list_first_entry(&agg->active, struct qfq_class, alist) + == cl && cl->deficit < qdisc_pkt_len(skb)) + list_move_tail(&cl->alist, &agg->active); + return err; + } - /* If reach this point, queue q was idle */ - qfq_activate_class(q, cl, qdisc_pkt_len(skb)); + /* schedule class for service within the aggregate */ + cl->deficit = agg->lmax; + list_add_tail(&cl->alist, &agg->active); + + if (list_first_entry(&agg->active, struct qfq_class, alist) != cl) + return err; /* aggregate was not empty, nothing else to do */ + + /* recharge budget */ + agg->initial_budget = agg->budget = agg->budgetmax; + + qfq_update_agg_ts(q, agg, enqueue); + if (q->in_serv_agg == NULL) + q->in_serv_agg = agg; + else if (agg != q->in_serv_agg) + qfq_schedule_agg(q, agg); return err; } /* - * Handle class switch from idle to backlogged. + * Schedule aggregate according to its timestamps. */ -static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl, - unsigned int pkt_len) +static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { - struct qfq_group *grp = cl->grp; + struct qfq_group *grp = agg->grp; u64 roundedS; int s; - qfq_update_start(q, cl); - - /* compute new finish time and rounded start. */ - cl->F = cl->S + (u64)pkt_len * cl->inv_w; - roundedS = qfq_round_down(cl->S, grp->slot_shift); + roundedS = qfq_round_down(agg->S, grp->slot_shift); /* - * insert cl in the correct bucket. - * If cl->S >= grp->S we don't need to adjust the + * Insert agg in the correct bucket. + * If agg->S >= grp->S we don't need to adjust the * bucket list and simply go to the insertion phase. * Otherwise grp->S is decreasing, we must make room * in the bucket list, and also recompute the group state. @@ -941,10 +1255,10 @@ static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl, * was in ER make sure to adjust V. */ if (grp->full_slots) { - if (!qfq_gt(grp->S, cl->S)) + if (!qfq_gt(grp->S, agg->S)) goto skip_update; - /* create a slot for this cl->S */ + /* create a slot for this agg->S */ qfq_slot_rotate(grp, roundedS); /* group was surely ineligible, remove */ __clear_bit(grp->index, &q->bitmaps[IR]); @@ -959,46 +1273,61 @@ static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl, pr_debug("qfq enqueue: new state %d %#lx S %lld F %lld V %lld\n", s, q->bitmaps[s], - (unsigned long long) cl->S, - (unsigned long long) cl->F, + (unsigned long long) agg->S, + (unsigned long long) agg->F, (unsigned long long) q->V); skip_update: - qfq_slot_insert(grp, cl, roundedS); + qfq_slot_insert(grp, agg, roundedS); } +/* Update agg ts and schedule agg for service */ +static void qfq_activate_agg(struct qfq_sched *q, struct qfq_aggregate *agg, + enum update_reason reason) +{ + qfq_update_agg_ts(q, agg, reason); + qfq_schedule_agg(q, agg); +} + static void qfq_slot_remove(struct qfq_sched *q, struct qfq_group *grp, - struct qfq_class *cl) + struct qfq_aggregate *agg) { unsigned int i, offset; u64 roundedS; - roundedS = qfq_round_down(cl->S, grp->slot_shift); + roundedS = qfq_round_down(agg->S, grp->slot_shift); offset = (roundedS - grp->S) >> grp->slot_shift; + i = (grp->front + offset) % QFQ_MAX_SLOTS; - hlist_del(&cl->next); + hlist_del(&agg->next); if (hlist_empty(&grp->slots[i])) __clear_bit(offset, &grp->full_slots); } /* - * called to forcibly destroy a queue. - * If the queue is not in the front bucket, or if it has - * other queues in the front bucket, we can simply remove - * the queue with no other side effects. + * Called to forcibly deschedule an aggregate. If the aggregate is + * not in the front bucket, or if the latter has other aggregates in + * the front bucket, we can simply remove the aggregate with no other + * side effects. * Otherwise we must propagate the event up. */ -static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) +static void qfq_deactivate_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { - struct qfq_group *grp = cl->grp; + struct qfq_group *grp = agg->grp; unsigned long mask; u64 roundedS; int s; - cl->F = cl->S; - qfq_slot_remove(q, grp, cl); + if (agg == q->in_serv_agg) { + charge_actual_service(agg); + q->in_serv_agg = qfq_choose_next_agg(q); + return; + } + + agg->F = agg->S; + qfq_slot_remove(q, grp, agg); if (!grp->full_slots) { __clear_bit(grp->index, &q->bitmaps[IR]); @@ -1017,8 +1346,8 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) } __clear_bit(grp->index, &q->bitmaps[ER]); } else if (hlist_empty(&grp->slots[grp->front])) { - cl = qfq_slot_scan(grp); - roundedS = qfq_round_down(cl->S, grp->slot_shift); + agg = qfq_slot_scan(grp); + roundedS = qfq_round_down(agg->S, grp->slot_shift); if (grp->S != roundedS) { __clear_bit(grp->index, &q->bitmaps[ER]); __clear_bit(grp->index, &q->bitmaps[IR]); @@ -1031,7 +1360,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) } } - qfq_update_eligible(q, q->V); + qfq_update_eligible(q); } static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) @@ -1043,6 +1372,32 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) qfq_deactivate_class(q, cl); } +static unsigned int qfq_drop_from_slot(struct qfq_sched *q, + struct hlist_head *slot) +{ + struct qfq_aggregate *agg; + struct hlist_node *n; + struct qfq_class *cl; + unsigned int len; + + hlist_for_each_entry(agg, n, slot, next) { + list_for_each_entry(cl, &agg->active, alist) { + + if (!cl->qdisc->ops->drop) + continue; + + len = cl->qdisc->ops->drop(cl->qdisc); + if (len > 0) { + if (cl->qdisc->q.qlen == 0) + qfq_deactivate_class(q, cl); + + return len; + } + } + } + return 0; +} + static unsigned int qfq_drop(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); @@ -1052,24 +1407,13 @@ static unsigned int qfq_drop(struct Qdisc *sch) for (i = 0; i <= QFQ_MAX_INDEX; i++) { grp = &q->groups[i]; for (j = 0; j < QFQ_MAX_SLOTS; j++) { - struct qfq_class *cl; - struct hlist_node *n; - - hlist_for_each_entry(cl, n, &grp->slots[j], next) { - - if (!cl->qdisc->ops->drop) - continue; - - len = cl->qdisc->ops->drop(cl->qdisc); - if (len > 0) { - sch->q.qlen--; - if (!cl->qdisc->q.qlen) - qfq_deactivate_class(q, cl); - - return len; - } + len = qfq_drop_from_slot(q, &grp->slots[j]); + if (len > 0) { + sch->q.qlen--; + return len; } } + } return 0; @@ -1080,44 +1424,51 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct qfq_sched *q = qdisc_priv(sch); struct qfq_group *grp; int i, j, err; + u32 max_cl_shift, maxbudg_shift, max_classes; err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; + if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES) + max_classes = QFQ_MAX_AGG_CLASSES; + else + max_classes = qdisc_dev(sch)->tx_queue_len + 1; + /* max_cl_shift = floor(log_2(max_classes)) */ + max_cl_shift = __fls(max_classes); + q->max_agg_classes = 1<<max_cl_shift; + + /* maxbudg_shift = log2(max_len * max_classes_per_agg) */ + maxbudg_shift = QFQ_MTU_SHIFT + max_cl_shift; + q->min_slot_shift = FRAC_BITS + maxbudg_shift - QFQ_MAX_INDEX; + for (i = 0; i <= QFQ_MAX_INDEX; i++) { grp = &q->groups[i]; grp->index = i; - grp->slot_shift = QFQ_MTU_SHIFT + FRAC_BITS - - (QFQ_MAX_INDEX - i); + grp->slot_shift = q->min_slot_shift + i; for (j = 0; j < QFQ_MAX_SLOTS; j++) INIT_HLIST_HEAD(&grp->slots[j]); } + INIT_HLIST_HEAD(&q->nonfull_aggs); + return 0; } static void qfq_reset_qdisc(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_group *grp; struct qfq_class *cl; - struct hlist_node *n, *tmp; - unsigned int i, j; + struct hlist_node *n; + unsigned int i; - for (i = 0; i <= QFQ_MAX_INDEX; i++) { - grp = &q->groups[i]; - for (j = 0; j < QFQ_MAX_SLOTS; j++) { - hlist_for_each_entry_safe(cl, n, tmp, - &grp->slots[j], next) { + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + if (cl->qdisc->q.qlen > 0) qfq_deactivate_class(q, cl); - } - } - } - for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) qdisc_reset(cl->qdisc); + } } sch->q.qlen = 0; } diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig index 126b014eb79b..7521d944c0fb 100644 --- a/net/sctp/Kconfig +++ b/net/sctp/Kconfig @@ -9,7 +9,6 @@ menuconfig IP_SCTP select CRYPTO select CRYPTO_HMAC select CRYPTO_SHA1 - select CRYPTO_MD5 if SCTP_HMAC_MD5 select LIBCRC32C ---help--- Stream Control Transmission Protocol @@ -67,34 +66,45 @@ config SCTP_DBG_OBJCNT 'cat /proc/net/sctp/sctp_dbg_objcnt' If unsure, say N - choice - prompt "SCTP: Cookie HMAC Algorithm" - default SCTP_HMAC_MD5 + prompt "Default SCTP cookie HMAC encoding" + default SCTP_DEFAULT_COOKIE_HMAC_MD5 + help + This option sets the default sctp cookie hmac algorithm + when in doubt select 'md5' + +config SCTP_DEFAULT_COOKIE_HMAC_MD5 + bool "Enable optional MD5 hmac cookie generation" help - HMAC algorithm to be used during association initialization. It - is strongly recommended to use HMAC-SHA1 or HMAC-MD5. See - configuration for Cryptographic API and enable those algorithms - to make usable by SCTP. - -config SCTP_HMAC_NONE - bool "None" - help - Choosing this disables the use of an HMAC during association - establishment. It is advised to use either HMAC-MD5 or HMAC-SHA1. - -config SCTP_HMAC_SHA1 - bool "HMAC-SHA1" - help - Enable the use of HMAC-SHA1 during association establishment. It - is advised to use either HMAC-MD5 or HMAC-SHA1. - -config SCTP_HMAC_MD5 - bool "HMAC-MD5" + Enable optional MD5 hmac based SCTP cookie generation + select SCTP_COOKIE_HMAC_MD5 + +config SCTP_DEFAULT_COOKIE_HMAC_SHA1 + bool "Enable optional SHA1 hmac cookie generation" + help + Enable optional SHA1 hmac based SCTP cookie generation + select SCTP_COOKIE_HMAC_SHA1 + +config SCTP_DEFAULT_COOKIE_HMAC_NONE + bool "Use no hmac alg in SCTP cookie generation" help - Enable the use of HMAC-MD5 during association establishment. It is - advised to use either HMAC-MD5 or HMAC-SHA1. + Use no hmac algorithm in SCTP cookie generation endchoice +config SCTP_COOKIE_HMAC_MD5 + bool "Enable optional MD5 hmac cookie generation" + help + Enable optional MD5 hmac based SCTP cookie generation + select CRYPTO_HMAC if SCTP_COOKIE_HMAC_MD5 + select CRYPTO_MD5 if SCTP_COOKIE_HMAC_MD5 + +config SCTP_COOKIE_HMAC_SHA1 + bool "Enable optional SHA1 hmac cookie generation" + help + Enable optional SHA1 hmac based SCTP cookie generation + select CRYPTO_HMAC if SCTP_COOKIE_HMAC_SHA1 + select CRYPTO_SHA1 if SCTP_COOKIE_HMAC_SHA1 + + endif # IP_SCTP diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b1ef3bc301a5..b45ed1f96921 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -321,6 +321,9 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->default_timetolive = sp->default_timetolive; asoc->default_rcv_context = sp->default_rcv_context; + /* SCTP_GET_ASSOC_STATS COUNTERS */ + memset(&asoc->stats, 0, sizeof(struct sctp_priv_assoc_stats)); + /* AUTH related initializations */ INIT_LIST_HEAD(&asoc->endpoint_shared_keys); err = sctp_auth_asoc_copy_shkeys(ep, asoc, gfp); @@ -445,7 +448,7 @@ void sctp_association_free(struct sctp_association *asoc) /* Release the transport structures. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); - list_del(pos); + list_del_rcu(pos); sctp_transport_free(transport); } @@ -565,7 +568,7 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, sctp_assoc_update_retran_path(asoc); /* Remove this peer from the list. */ - list_del(&peer->transports); + list_del_rcu(&peer->transports); /* Get the first transport of asoc. */ pos = asoc->peer.transport_addr_list.next; @@ -760,12 +763,13 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, /* Set the transport's RTO.initial value */ peer->rto = asoc->rto_initial; + sctp_max_rto(asoc, peer); /* Set the peer's active state. */ peer->state = peer_state; /* Attach the remote transport to our asoc. */ - list_add_tail(&peer->transports, &asoc->peer.transport_addr_list); + list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; /* If we do not yet have a primary path, set one. */ @@ -1152,8 +1156,12 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) */ if (sctp_chunk_is_data(chunk)) asoc->peer.last_data_from = chunk->transport; - else + else { SCTP_INC_STATS(net, SCTP_MIB_INCTRLCHUNKS); + asoc->stats.ictrlchunks++; + if (chunk->chunk_hdr->type == SCTP_CID_SACK) + asoc->stats.isacks++; + } if (chunk->transport) chunk->transport->last_time_heard = jiffies; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 7c2df9c33df3..69ce21e3716f 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -183,7 +183,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, msg = sctp_datamsg_new(GFP_KERNEL); if (!msg) - return NULL; + return ERR_PTR(-ENOMEM); /* Note: Calculate this outside of the loop, so that all fragments * have the same expiration. @@ -280,11 +280,14 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, chunk = sctp_make_datafrag_empty(asoc, sinfo, len, frag, 0); - if (!chunk) + if (!chunk) { + err = -ENOMEM; goto errout; + } + err = sctp_user_addto_chunk(chunk, offset, len, msgh->msg_iov); if (err < 0) - goto errout; + goto errout_chunk_free; offset += len; @@ -315,8 +318,10 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, chunk = sctp_make_datafrag_empty(asoc, sinfo, over, frag, 0); - if (!chunk) + if (!chunk) { + err = -ENOMEM; goto errout; + } err = sctp_user_addto_chunk(chunk, offset, over,msgh->msg_iov); @@ -324,7 +329,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, __skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr - (__u8 *)chunk->skb->data); if (err < 0) - goto errout; + goto errout_chunk_free; sctp_datamsg_assign(msg, chunk); list_add_tail(&chunk->frag_list, &msg->chunks); @@ -332,6 +337,9 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, return msg; +errout_chunk_free: + sctp_chunk_free(chunk); + errout: list_for_each_safe(pos, temp, &msg->chunks) { list_del_init(pos); @@ -339,7 +347,7 @@ errout: sctp_chunk_free(chunk); } sctp_datamsg_put(msg); - return NULL; + return ERR_PTR(err); } /* Check whether this message has expired. */ diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index bd7e6a6a815a..17a001bac2cc 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -480,8 +480,11 @@ normal: */ if (asoc && sctp_chunk_is_data(chunk)) asoc->peer.last_data_from = chunk->transport; - else + else { SCTP_INC_STATS(sock_net(ep->base.sk), SCTP_MIB_INCTRLCHUNKS); + if (asoc) + asoc->stats.ictrlchunks++; + } if (chunk->transport) chunk->transport->last_time_heard = jiffies; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 397296fb156f..2d5ad280de38 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -104,6 +104,8 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) * on the BH related data structures. */ list_add_tail(&chunk->list, &q->in_chunk_list); + if (chunk->asoc) + chunk->asoc->stats.ipackets++; q->immediate.func(&q->immediate); } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ea14cb445295..f3f0f4dc31dd 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -345,7 +345,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } out: - if (!IS_ERR(dst)) { + if (!IS_ERR_OR_NULL(dst)) { struct rt6_info *rt; rt = (struct rt6_info *)dst; t->dst = dst; diff --git a/net/sctp/output.c b/net/sctp/output.c index 4e90188bf489..f5200a2ad852 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -311,6 +311,8 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, case SCTP_CID_SACK: packet->has_sack = 1; + if (chunk->asoc) + chunk->asoc->stats.osacks++; break; case SCTP_CID_AUTH: @@ -584,11 +586,13 @@ int sctp_packet_transmit(struct sctp_packet *packet) */ /* Dump that on IP! */ - if (asoc && asoc->peer.last_sent_to != tp) { - /* Considering the multiple CPU scenario, this is a - * "correcter" place for last_sent_to. --xguo - */ - asoc->peer.last_sent_to = tp; + if (asoc) { + asoc->stats.opackets++; + if (asoc->peer.last_sent_to != tp) + /* Considering the multiple CPU scenario, this is a + * "correcter" place for last_sent_to. --xguo + */ + asoc->peer.last_sent_to = tp; } if (has_data) { diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 1b4a7f8ec3fd..9bcdbd02d777 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -224,7 +224,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) /* Free the outqueue structure and any related pending chunks. */ -void sctp_outq_teardown(struct sctp_outq *q) +static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; @@ -277,8 +277,6 @@ void sctp_outq_teardown(struct sctp_outq *q) sctp_chunk_free(chunk); } - q->error = 0; - /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); @@ -286,11 +284,17 @@ void sctp_outq_teardown(struct sctp_outq *q) } } +void sctp_outq_teardown(struct sctp_outq *q) +{ + __sctp_outq_teardown(q); + sctp_outq_init(q->asoc, q); +} + /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ - sctp_outq_teardown(q); + __sctp_outq_teardown(q); /* If we were kmalloc()'d, free the memory. */ if (q->malloced) @@ -667,6 +671,7 @@ redo: chunk->fast_retransmit = SCTP_DONT_FRTX; q->empty = 0; + q->asoc->stats.rtxchunks++; break; } @@ -876,12 +881,14 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) if (status != SCTP_XMIT_OK) { /* put the chunk back */ list_add(&chunk->list, &q->control_chunk_list); - } else if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) { + } else { + asoc->stats.octrlchunks++; /* PR-SCTP C5) If a FORWARD TSN is sent, the * sender MUST assure that at least one T3-rtx * timer is running. */ - sctp_transport_reset_timers(transport); + if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) + sctp_transport_reset_timers(transport); } break; @@ -1055,6 +1062,10 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) */ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; + if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) + asoc->stats.ouodchunks++; + else + asoc->stats.oodchunks++; break; @@ -1162,6 +1173,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); + asoc->stats.gapcnt += gap_ack_blocks; /* * SFR-CACC algorithm: * On receipt of a SACK the sender SHOULD execute the diff --git a/net/sctp/probe.c b/net/sctp/probe.c index bc6cd75cc1dc..5f7518de2fd1 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -122,7 +122,8 @@ static const struct file_operations sctpprobe_fops = { .llseek = noop_llseek, }; -sctp_disposition_t jsctp_sf_eat_sack(const struct sctp_endpoint *ep, +sctp_disposition_t jsctp_sf_eat_sack(struct net *net, + const struct sctp_endpoint *ep, const struct sctp_association *asoc, const sctp_subtype_t type, void *arg, diff --git a/net/sctp/proc.c b/net/sctp/proc.c index c3bea269faf4..8c19e97262ca 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -102,7 +102,7 @@ static const struct file_operations sctp_snmp_seq_fops = { .open = sctp_snmp_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; /* Set up the proc fs entry for 'snmp' object. */ @@ -139,7 +139,11 @@ static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_commo primary = &peer->saddr; } - list_for_each_entry(laddr, &epb->bind_addr.address_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &epb->bind_addr.address_list, list) { + if (!laddr->valid) + continue; + addr = &laddr->a; af = sctp_get_af_specific(addr->sa.sa_family); if (primary && af->cmp_addr(addr, primary)) { @@ -147,6 +151,7 @@ static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_commo } af->seq_dump_addr(seq, addr); } + rcu_read_unlock(); } /* Dump remote addresses of an association. */ @@ -157,15 +162,20 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa struct sctp_af *af; primary = &assoc->peer.primary_addr; - list_for_each_entry(transport, &assoc->peer.transport_addr_list, + rcu_read_lock(); + list_for_each_entry_rcu(transport, &assoc->peer.transport_addr_list, transports) { addr = &transport->ipaddr; + if (transport->dead) + continue; + af = sctp_get_af_specific(addr->sa.sa_family); if (af->cmp_addr(addr, primary)) { seq_printf(seq, "*"); } af->seq_dump_addr(seq, addr); } + rcu_read_unlock(); } static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) @@ -251,7 +261,7 @@ static const struct file_operations sctp_eps_seq_fops = { .open = sctp_eps_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; /* Set up the proc fs entry for 'eps' object. */ @@ -372,7 +382,7 @@ static const struct file_operations sctp_assocs_seq_fops = { .open = sctp_assocs_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; /* Set up the proc fs entry for 'assocs' object. */ @@ -436,12 +446,16 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) head = &sctp_assoc_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); + rcu_read_lock(); sctp_for_each_hentry(epb, node, &head->chain) { if (!net_eq(sock_net(epb->sk), seq_file_net(seq))) continue; assoc = sctp_assoc(epb); - list_for_each_entry(tsp, &assoc->peer.transport_addr_list, + list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { + if (tsp->dead) + continue; + /* * The remote address (ADDR) */ @@ -487,6 +501,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) } } + rcu_read_unlock(); read_unlock(&head->lock); sctp_local_bh_enable(); @@ -517,7 +532,7 @@ static const struct file_operations sctp_remaddr_seq_fops = { .open = sctp_remaddr_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, }; int __net_init sctp_remaddr_proc_init(struct net *net) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 2d518425d598..f898b1c58bd2 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -86,7 +86,7 @@ int sysctl_sctp_rmem[3]; int sysctl_sctp_wmem[3]; /* Set up the proc fs entry for the SCTP protocol. */ -static __net_init int sctp_proc_init(struct net *net) +static int __net_init sctp_proc_init(struct net *net) { #ifdef CONFIG_PROC_FS net->sctp.proc_net_sctp = proc_net_mkdir(net, "sctp", net->proc_net); @@ -1165,7 +1165,7 @@ static void sctp_v4_del_protocol(void) unregister_inetaddr_notifier(&sctp_inetaddr_notifier); } -static int sctp_net_init(struct net *net) +static int __net_init sctp_net_init(struct net *net) { int status; @@ -1190,6 +1190,15 @@ static int sctp_net_init(struct net *net) /* Whether Cookie Preservative is enabled(1) or not(0) */ net->sctp.cookie_preserve_enable = 1; + /* Default sctp sockets to use md5 as their hmac alg */ +#if defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5) + net->sctp.sctp_hmac_alg = "md5"; +#elif defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1) + net->sctp.sctp_hmac_alg = "sha1"; +#else + net->sctp.sctp_hmac_alg = NULL; +#endif + /* Max.Burst - 4 */ net->sctp.max_burst = SCTP_DEFAULT_MAX_BURST; @@ -1281,7 +1290,7 @@ err_sysctl_register: return status; } -static void sctp_net_exit(struct net *net) +static void __net_exit sctp_net_exit(struct net *net) { /* Free the local address list */ sctp_free_addr_wq(net); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 16a10850ed39..04df5301df04 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -804,10 +804,11 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) gabs); /* Add the duplicate TSN information. */ - if (num_dup_tsns) + if (num_dup_tsns) { + aptr->stats.idupchunks += num_dup_tsns; sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); - + } /* Once we have a sack generated, check to see what our sack * generation is, if its 0, reset the transports to 0, and reset * the association generation to 1 @@ -1090,6 +1091,25 @@ nodata: return retval; } +struct sctp_chunk *sctp_make_violation_max_retrans( + const struct sctp_association *asoc, + const struct sctp_chunk *chunk) +{ + struct sctp_chunk *retval; + static const char error[] = "Association exceeded its max_retans count"; + size_t payload_len = sizeof(error) + sizeof(sctp_errhdr_t); + + retval = sctp_make_abort(asoc, chunk, payload_len); + if (!retval) + goto nodata; + + sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, sizeof(error)); + sctp_addto_chunk(retval, sizeof(error), error); + +nodata: + return retval; +} + /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 6773d7803627..c9577754a708 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -542,6 +542,7 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, */ if (!is_hb || transport->hb_sent) { transport->rto = min((transport->rto * 2), transport->asoc->rto_max); + sctp_max_rto(asoc, transport); } } @@ -577,7 +578,7 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, unsigned int error) { struct sctp_ulpevent *event; - + struct sctp_chunk *abort; /* Cancel any partial delivery in progress. */ sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); @@ -593,6 +594,13 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(event)); + if (asoc->overall_error_count >= asoc->max_retrans) { + abort = sctp_make_violation_max_retrans(asoc, chunk); + if (abort) + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, + SCTP_CHUNK(abort)); + } + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); @@ -1268,14 +1276,14 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, sctp_outq_uncork(&asoc->outqueue); local_cork = 0; } - asoc = cmd->obj.ptr; + asoc = cmd->obj.asoc; /* Register with the endpoint. */ sctp_endpoint_add_asoc(ep, asoc); sctp_hash_established(asoc); break; case SCTP_CMD_UPDATE_ASSOC: - sctp_assoc_update(asoc, cmd->obj.ptr); + sctp_assoc_update(asoc, cmd->obj.asoc); break; case SCTP_CMD_PURGE_OUTQUEUE: @@ -1315,7 +1323,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; case SCTP_CMD_PROCESS_FWDTSN: - sctp_cmd_process_fwdtsn(&asoc->ulpq, cmd->obj.ptr); + sctp_cmd_process_fwdtsn(&asoc->ulpq, cmd->obj.chunk); break; case SCTP_CMD_GEN_SACK: @@ -1331,7 +1339,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_PROCESS_SACK: /* Process an inbound SACK. */ error = sctp_cmd_process_sack(commands, asoc, - cmd->obj.ptr); + cmd->obj.chunk); break; case SCTP_CMD_GEN_INIT_ACK: @@ -1352,15 +1360,15 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, * layer which will bail. */ error = sctp_cmd_process_init(commands, asoc, chunk, - cmd->obj.ptr, gfp); + cmd->obj.init, gfp); break; case SCTP_CMD_GEN_COOKIE_ECHO: /* Generate a COOKIE ECHO chunk. */ new_obj = sctp_make_cookie_echo(asoc, chunk); if (!new_obj) { - if (cmd->obj.ptr) - sctp_chunk_free(cmd->obj.ptr); + if (cmd->obj.chunk) + sctp_chunk_free(cmd->obj.chunk); goto nomem; } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, @@ -1369,9 +1377,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, /* If there is an ERROR chunk to be sent along with * the COOKIE_ECHO, send it, too. */ - if (cmd->obj.ptr) + if (cmd->obj.chunk) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, - SCTP_CHUNK(cmd->obj.ptr)); + SCTP_CHUNK(cmd->obj.chunk)); if (new_obj->transport) { new_obj->transport->init_sent_count++; @@ -1417,18 +1425,18 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_CHUNK_ULP: /* Send a chunk to the sockets layer. */ SCTP_DEBUG_PRINTK("sm_sideff: %s %p, %s %p.\n", - "chunk_up:", cmd->obj.ptr, + "chunk_up:", cmd->obj.chunk, "ulpq:", &asoc->ulpq); - sctp_ulpq_tail_data(&asoc->ulpq, cmd->obj.ptr, + sctp_ulpq_tail_data(&asoc->ulpq, cmd->obj.chunk, GFP_ATOMIC); break; case SCTP_CMD_EVENT_ULP: /* Send a notification to the sockets layer. */ SCTP_DEBUG_PRINTK("sm_sideff: %s %p, %s %p.\n", - "event_up:",cmd->obj.ptr, + "event_up:",cmd->obj.ulpevent, "ulpq:",&asoc->ulpq); - sctp_ulpq_tail_event(&asoc->ulpq, cmd->obj.ptr); + sctp_ulpq_tail_event(&asoc->ulpq, cmd->obj.ulpevent); break; case SCTP_CMD_REPLY: @@ -1438,12 +1446,12 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, local_cork = 1; } /* Send a chunk to our peer. */ - error = sctp_outq_tail(&asoc->outqueue, cmd->obj.ptr); + error = sctp_outq_tail(&asoc->outqueue, cmd->obj.chunk); break; case SCTP_CMD_SEND_PKT: /* Send a full packet to our peer. */ - packet = cmd->obj.ptr; + packet = cmd->obj.packet; sctp_packet_transmit(packet); sctp_ootb_pkt_free(packet); break; @@ -1480,7 +1488,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; case SCTP_CMD_SETUP_T2: - sctp_cmd_setup_t2(commands, asoc, cmd->obj.ptr); + sctp_cmd_setup_t2(commands, asoc, cmd->obj.chunk); break; case SCTP_CMD_TIMER_START_ONCE: @@ -1514,7 +1522,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; case SCTP_CMD_INIT_CHOOSE_TRANSPORT: - chunk = cmd->obj.ptr; + chunk = cmd->obj.chunk; t = sctp_assoc_choose_alter_transport(asoc, asoc->init_last_sent_to); asoc->init_last_sent_to = t; @@ -1665,17 +1673,16 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; case SCTP_CMD_PART_DELIVER: - sctp_ulpq_partial_delivery(&asoc->ulpq, cmd->obj.ptr, - GFP_ATOMIC); + sctp_ulpq_partial_delivery(&asoc->ulpq, GFP_ATOMIC); break; case SCTP_CMD_RENEGE: - sctp_ulpq_renege(&asoc->ulpq, cmd->obj.ptr, + sctp_ulpq_renege(&asoc->ulpq, cmd->obj.chunk, GFP_ATOMIC); break; case SCTP_CMD_SETUP_T4: - sctp_cmd_setup_t4(commands, asoc, cmd->obj.ptr); + sctp_cmd_setup_t4(commands, asoc, cmd->obj.chunk); break; case SCTP_CMD_PROCESS_OPERR: @@ -1734,8 +1741,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; default: - pr_warn("Impossible command: %u, %p\n", - cmd->verb, cmd->obj.ptr); + pr_warn("Impossible command: %u\n", + cmd->verb); break; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 49493f335861..5131fcfedb03 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1055,6 +1055,7 @@ sctp_disposition_t sctp_sf_beat_8_3(struct net *net, void *arg, sctp_cmd_seq_t *commands) { + sctp_paramhdr_t *param_hdr; struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; size_t paylen = 0; @@ -1072,12 +1073,17 @@ sctp_disposition_t sctp_sf_beat_8_3(struct net *net, * Information field copied from the received HEARTBEAT chunk. */ chunk->subh.hb_hdr = (sctp_heartbeathdr_t *) chunk->skb->data; + param_hdr = (sctp_paramhdr_t *) chunk->subh.hb_hdr; paylen = ntohs(chunk->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); + + if (ntohs(param_hdr->length) > paylen) + return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, + param_hdr, commands); + if (!pskb_pull(chunk->skb, paylen)) goto nomem; - reply = sctp_make_heartbeat_ack(asoc, chunk, - chunk->subh.hb_hdr, paylen); + reply = sctp_make_heartbeat_ack(asoc, chunk, param_hdr, paylen); if (!reply) goto nomem; @@ -1773,8 +1779,10 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return SCTP_DISPOSITION_CONSUME; nomem_ev: @@ -6127,6 +6135,8 @@ static int sctp_eat_data(const struct sctp_association *asoc, /* The TSN is too high--silently discard the chunk and * count on it getting retransmitted later. */ + if (chunk->asoc) + chunk->asoc->stats.outofseqtsns++; return SCTP_IERROR_HIGH_TSN; } else if (tmp > 0) { /* This is a duplicate. Record it. */ @@ -6226,10 +6236,14 @@ static int sctp_eat_data(const struct sctp_association *asoc, /* Note: Some chunks may get overcounted (if we drop) or overcounted * if we renege and the chunk arrives again. */ - if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) + if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) { SCTP_INC_STATS(net, SCTP_MIB_INUNORDERCHUNKS); - else { + if (chunk->asoc) + chunk->asoc->stats.iuodchunks++; + } else { SCTP_INC_STATS(net, SCTP_MIB_INORDERCHUNKS); + if (chunk->asoc) + chunk->asoc->stats.iodchunks++; ordered = 1; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 59d16ea927f0..9e65758cb038 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -110,7 +110,6 @@ static int sctp_do_bind(struct sock *, union sctp_addr *, int); static int sctp_autobind(struct sock *sk); static void sctp_sock_migrate(struct sock *, struct sock *, struct sctp_association *, sctp_socket_type_t); -static char *sctp_hmac_alg = SCTP_COOKIE_HMAC_ALG; extern struct kmem_cache *sctp_bucket_cachep; extern long sysctl_sctp_mem[3]; @@ -336,6 +335,7 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, /* Bind a local address either to an endpoint or to an association. */ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) { + struct net *net = sock_net(sk); struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct sctp_bind_addr *bp = &ep->base.bind_addr; @@ -379,7 +379,8 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) } } - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; /* See if the address matches any of the addresses we may have @@ -610,6 +611,7 @@ static int sctp_send_asconf_add_ip(struct sock *sk, 2*asoc->pathmtu, 4380)); trans->ssthresh = asoc->peer.i.a_rwnd; trans->rto = asoc->rto_initial; + sctp_max_rto(asoc, trans); trans->rtt = trans->srtt = trans->rttvar = 0; sctp_transport_route(trans, NULL, sctp_sk(asoc->base.sk)); @@ -974,7 +976,7 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk, void *addr_buf; struct sctp_af *af; - SCTP_DEBUG_PRINTK("sctp_setsocktopt_bindx: sk %p addrs %p" + SCTP_DEBUG_PRINTK("sctp_setsockopt_bindx: sk %p addrs %p" " addrs_size %d opt %d\n", sk, addrs, addrs_size, op); if (unlikely(addrs_size <= 0)) @@ -1162,7 +1164,7 @@ static int __sctp_connect(struct sock* sk, * be permitted to open new associations. */ if (ep->base.bind_addr.port < PROT_SOCK && - !capable(CAP_NET_BIND_SERVICE)) { + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) { err = -EACCES; goto out_free; } @@ -1791,7 +1793,7 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, * associations. */ if (ep->base.bind_addr.port < PROT_SOCK && - !capable(CAP_NET_BIND_SERVICE)) { + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) { err = -EACCES; goto out_unlock; } @@ -1915,8 +1917,8 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, /* Break the message into multiple chunks of maximum size. */ datamsg = sctp_datamsg_from_user(asoc, sinfo, msg, msg_len); - if (!datamsg) { - err = -ENOMEM; + if (IS_ERR(datamsg)) { + err = PTR_ERR(datamsg); goto out_free; } @@ -3890,6 +3892,8 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->default_rcv_context = 0; sp->max_burst = net->sctp.max_burst; + sp->sctp_hmac_alg = net->sctp.sctp_hmac_alg; + /* Initialize default setup parameters. These parameters * can be modified with the SCTP_INITMSG socket option or * overridden by the SCTP_INIT CMSG. @@ -5632,6 +5636,71 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, return 0; } +/* + * SCTP_GET_ASSOC_STATS + * + * This option retrieves local per endpoint statistics. It is modeled + * after OpenSolaris' implementation + */ +static int sctp_getsockopt_assoc_stats(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_stats sas; + struct sctp_association *asoc = NULL; + + /* User must provide at least the assoc id */ + if (len < sizeof(sctp_assoc_t)) + return -EINVAL; + + if (copy_from_user(&sas, optval, len)) + return -EFAULT; + + asoc = sctp_id2assoc(sk, sas.sas_assoc_id); + if (!asoc) + return -EINVAL; + + sas.sas_rtxchunks = asoc->stats.rtxchunks; + sas.sas_gapcnt = asoc->stats.gapcnt; + sas.sas_outofseqtsns = asoc->stats.outofseqtsns; + sas.sas_osacks = asoc->stats.osacks; + sas.sas_isacks = asoc->stats.isacks; + sas.sas_octrlchunks = asoc->stats.octrlchunks; + sas.sas_ictrlchunks = asoc->stats.ictrlchunks; + sas.sas_oodchunks = asoc->stats.oodchunks; + sas.sas_iodchunks = asoc->stats.iodchunks; + sas.sas_ouodchunks = asoc->stats.ouodchunks; + sas.sas_iuodchunks = asoc->stats.iuodchunks; + sas.sas_idupchunks = asoc->stats.idupchunks; + sas.sas_opackets = asoc->stats.opackets; + sas.sas_ipackets = asoc->stats.ipackets; + + /* New high max rto observed, will return 0 if not a single + * RTO update took place. obs_rto_ipaddr will be bogus + * in such a case + */ + sas.sas_maxrto = asoc->stats.max_obs_rto; + memcpy(&sas.sas_obs_rto_ipaddr, &asoc->stats.obs_rto_ipaddr, + sizeof(struct sockaddr_storage)); + + /* Mark beginning of a new observation period */ + asoc->stats.max_obs_rto = asoc->rto_min; + + /* Allow the struct to grow and fill in as much as possible */ + len = min_t(size_t, len, sizeof(sas)); + + if (put_user(len, optlen)) + return -EFAULT; + + SCTP_DEBUG_PRINTK("sctp_getsockopt_assoc_stat(%d): %d\n", + len, sas.sas_assoc_id); + + if (copy_to_user(optval, &sas, len)) + return -EFAULT; + + return 0; +} + SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -5773,6 +5842,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_PEER_ADDR_THLDS: retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen); break; + case SCTP_GET_ASSOC_STATS: + retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -5981,13 +6053,15 @@ SCTP_STATIC int sctp_listen_start(struct sock *sk, int backlog) struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct crypto_hash *tfm = NULL; + char alg[32]; /* Allocate HMAC for generating cookie. */ - if (!sctp_sk(sk)->hmac && sctp_hmac_alg) { - tfm = crypto_alloc_hash(sctp_hmac_alg, 0, CRYPTO_ALG_ASYNC); + if (!sp->hmac && sp->sctp_hmac_alg) { + sprintf(alg, "hmac(%s)", sp->sctp_hmac_alg); + tfm = crypto_alloc_hash(alg, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) { net_info_ratelimited("failed to load transform for %s: %ld\n", - sctp_hmac_alg, PTR_ERR(tfm)); + sp->sctp_hmac_alg, PTR_ERR(tfm)); return -ENOSYS; } sctp_sk(sk)->hmac = tfm; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 70e3ba5cb50b..bf3c6e8fc401 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -62,6 +62,11 @@ extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; extern int sysctl_sctp_wmem[3]; +static int proc_sctp_do_hmac_alg(ctl_table *ctl, + int write, + void __user *buffer, size_t *lenp, + + loff_t *ppos); static ctl_table sctp_table[] = { { .procname = "sctp_mem", @@ -147,6 +152,12 @@ static ctl_table sctp_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "cookie_hmac_alg", + .maxlen = 8, + .mode = 0644, + .proc_handler = proc_sctp_do_hmac_alg, + }, + { .procname = "valid_cookie_life", .data = &init_net.sctp.valid_cookie_life, .maxlen = sizeof(unsigned int), @@ -289,6 +300,54 @@ static ctl_table sctp_net_table[] = { { /* sentinel */ } }; +static int proc_sctp_do_hmac_alg(ctl_table *ctl, + int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + char tmp[8]; + ctl_table tbl; + int ret; + int changed = 0; + char *none = "none"; + + memset(&tbl, 0, sizeof(struct ctl_table)); + + if (write) { + tbl.data = tmp; + tbl.maxlen = 8; + } else { + tbl.data = net->sctp.sctp_hmac_alg ? : none; + tbl.maxlen = strlen(tbl.data); + } + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + + if (write) { +#ifdef CONFIG_CRYPTO_MD5 + if (!strncmp(tmp, "md5", 3)) { + net->sctp.sctp_hmac_alg = "md5"; + changed = 1; + } +#endif +#ifdef CONFIG_CRYPTO_SHA1 + if (!strncmp(tmp, "sha1", 4)) { + net->sctp.sctp_hmac_alg = "sha1"; + changed = 1; + } +#endif + if (!strncmp(tmp, "none", 4)) { + net->sctp.sctp_hmac_alg = NULL; + changed = 1; + } + + if (!changed) + ret = -EINVAL; + } + + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; @@ -307,7 +366,11 @@ int sctp_sysctl_net_register(struct net *net) void sctp_sysctl_net_unregister(struct net *net) { + struct ctl_table *table; + + table = net->sctp.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->sctp.sysctl_header); + kfree(table); } static struct ctl_table_header * sctp_sysctl_header; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 953c21e4af97..4e45bb68aef0 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -163,13 +163,11 @@ void sctp_transport_free(struct sctp_transport *transport) sctp_transport_put(transport); } -/* Destroy the transport data structure. - * Assumes there are no more users of this structure. - */ -static void sctp_transport_destroy(struct sctp_transport *transport) +static void sctp_transport_destroy_rcu(struct rcu_head *head) { - SCTP_ASSERT(transport->dead, "Transport is not dead", return); + struct sctp_transport *transport; + transport = container_of(head, struct sctp_transport, rcu); if (transport->asoc) sctp_association_put(transport->asoc); @@ -180,6 +178,16 @@ static void sctp_transport_destroy(struct sctp_transport *transport) SCTP_DBG_OBJCNT_DEC(transport); } +/* Destroy the transport data structure. + * Assumes there are no more users of this structure. + */ +static void sctp_transport_destroy(struct sctp_transport *transport) +{ + SCTP_ASSERT(transport->dead, "Transport is not dead", return); + + call_rcu(&transport->rcu, sctp_transport_destroy_rcu); +} + /* Start T3_rtx timer if it is not already running and update the heartbeat * timer. This routine is called every time a DATA chunk is sent. */ @@ -331,7 +339,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) * 1/8, rto_alpha would be expressed as 3. */ tp->rttvar = tp->rttvar - (tp->rttvar >> net->sctp.rto_beta) - + ((abs(tp->srtt - rtt)) >> net->sctp.rto_beta); + + (((__u32)abs64((__s64)tp->srtt - (__s64)rtt)) >> net->sctp.rto_beta); tp->srtt = tp->srtt - (tp->srtt >> net->sctp.rto_alpha) + (rtt >> net->sctp.rto_alpha); } else { @@ -363,6 +371,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) if (tp->rto > tp->asoc->rto_max) tp->rto = tp->asoc->rto_max; + sctp_max_rto(tp->asoc, tp); tp->rtt = rtt; /* Reset rto_pending so that a new RTT measurement is started when a @@ -620,6 +629,7 @@ void sctp_transport_reset(struct sctp_transport *t) t->burst_limited = 0; t->ssthresh = asoc->peer.i.a_rwnd; t->rto = asoc->rto_initial; + sctp_max_rto(asoc, t); t->rtt = 0; t->srtt = 0; t->rttvar = 0; diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index b5fb7c409023..5f25e0c92c31 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -272,7 +272,7 @@ __u16 sctp_tsnmap_pending(struct sctp_tsnmap *map) __u32 max_tsn = map->max_tsn_seen; __u32 base_tsn = map->base_tsn; __u16 pending_data; - u32 gap, i; + u32 gap; pending_data = max_tsn - cum_tsn; gap = max_tsn - base_tsn; @@ -280,11 +280,7 @@ __u16 sctp_tsnmap_pending(struct sctp_tsnmap *map) if (gap == 0 || gap >= map->len) goto out; - for (i = 0; i < gap+1; i++) { - if (test_bit(i, map->tsn_map)) - pending_data--; - } - + pending_data -= bitmap_weight(map->tsn_map, gap + 1); out: return pending_data; } diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 360d8697b95c..ada17464b65b 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -997,7 +997,6 @@ static __u16 sctp_ulpq_renege_frags(struct sctp_ulpq *ulpq, __u16 needed) /* Partial deliver the first message as there is pressure on rwnd. */ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq, - struct sctp_chunk *chunk, gfp_t gfp) { struct sctp_ulpevent *event; @@ -1060,7 +1059,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn, chunk->transport); sctp_ulpq_tail_data(ulpq, chunk, gfp); - sctp_ulpq_partial_delivery(ulpq, chunk, gfp); + sctp_ulpq_partial_delivery(ulpq, gfp); } sk_mem_reclaim(asoc->base.sk); diff --git a/net/socket.c b/net/socket.c index d92c490e66fa..2ca51c719ef9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -620,8 +620,6 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, { struct sock_iocb *si = kiocb_to_siocb(iocb); - sock_update_classid(sock->sk); - si->sock = sock; si->scm = NULL; si->msg = msg; @@ -784,8 +782,6 @@ static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock, { struct sock_iocb *si = kiocb_to_siocb(iocb); - sock_update_classid(sock->sk); - si->sock = sock; si->scm = NULL; si->msg = msg; @@ -896,8 +892,6 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, if (unlikely(!sock->ops->splice_read)) return -EINVAL; - sock_update_classid(sock->sk); - return sock->ops->splice_read(sock, ppos, pipe, len, flags); } @@ -3437,8 +3431,6 @@ EXPORT_SYMBOL(kernel_setsockopt); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { - sock_update_classid(sock->sk); - if (sock->ops->sendpage) return sock->ops->sendpage(sock, page, offset, size, flags); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 909dc0c31aab..6e5c824b040b 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -192,17 +192,23 @@ gss_fill_context(const void *p, const void *end, struct gss_cl_ctx *ctx, struct const void *q; unsigned int seclen; unsigned int timeout; + unsigned long now = jiffies; u32 window_size; int ret; - /* First unsigned int gives the lifetime (in seconds) of the cred */ + /* First unsigned int gives the remaining lifetime in seconds of the + * credential - e.g. the remaining TGT lifetime for Kerberos or + * the -t value passed to GSSD. + */ p = simple_get_bytes(p, end, &timeout, sizeof(timeout)); if (IS_ERR(p)) goto err; if (timeout == 0) timeout = GSSD_MIN_TIMEOUT; - ctx->gc_expiry = jiffies + (unsigned long)timeout * HZ * 3 / 4; - /* Sequence number window. Determines the maximum number of simultaneous requests */ + ctx->gc_expiry = now + ((unsigned long)timeout * HZ); + /* Sequence number window. Determines the maximum number of + * simultaneous requests + */ p = simple_get_bytes(p, end, &window_size, sizeof(window_size)); if (IS_ERR(p)) goto err; @@ -237,9 +243,12 @@ gss_fill_context(const void *p, const void *end, struct gss_cl_ctx *ctx, struct p = ERR_PTR(ret); goto err; } + dprintk("RPC: %s Success. gc_expiry %lu now %lu timeout %u\n", + __func__, ctx->gc_expiry, now, timeout); return q; err: - dprintk("RPC: %s returning %ld\n", __func__, -PTR_ERR(p)); + dprintk("RPC: %s returns %ld gc_expiry %lu now %lu timeout %u\n", + __func__, -PTR_ERR(p), ctx->gc_expiry, now, timeout); return p; } diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 5a3d675d2f2f..890a29912d5a 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -59,7 +59,7 @@ static void xprt_free_allocation(struct rpc_rqst *req) struct xdr_buf *xbufp; dprintk("RPC: free allocations for req= %p\n", req); - BUG_ON(test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); + WARN_ON_ONCE(test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); xbufp = &req->rq_private_buf; free_page((unsigned long)xbufp->head[0].iov_base); xbufp = &req->rq_snd_buf; @@ -172,7 +172,7 @@ out_free: xprt_free_allocation(req); dprintk("RPC: setup backchannel transport failed\n"); - return -1; + return -ENOMEM; } EXPORT_SYMBOL_GPL(xprt_setup_backchannel); @@ -191,7 +191,9 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) dprintk("RPC: destroy backchannel transport\n"); - BUG_ON(max_reqs == 0); + if (max_reqs == 0) + goto out; + spin_lock_bh(&xprt->bc_pa_lock); xprt_dec_alloc_count(xprt, max_reqs); list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) { @@ -202,6 +204,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) } spin_unlock_bh(&xprt->bc_pa_lock); +out: dprintk("RPC: backchannel list empty= %s\n", list_empty(&xprt->bc_pa_list) ? "true" : "false"); } @@ -255,7 +258,7 @@ void xprt_free_bc_request(struct rpc_rqst *req) dprintk("RPC: free backchannel req=%p\n", req); smp_mb__before_clear_bit(); - BUG_ON(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); + WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); smp_mb__after_clear_bit(); diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c index 0b2eb388cbda..15c7a8a1c24f 100644 --- a/net/sunrpc/bc_svc.c +++ b/net/sunrpc/bc_svc.c @@ -53,7 +53,7 @@ int bc_send(struct rpc_rqst *req) if (IS_ERR(task)) ret = PTR_ERR(task); else { - BUG_ON(atomic_read(&task->tk_count) != 1); + WARN_ON_ONCE(atomic_read(&task->tk_count) != 1); ret = task->tk_status; rpc_put_task(task); } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index fc2f7aa4dca7..9afa4393c217 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -775,11 +775,11 @@ static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, if (rp->q.list.next == &cd->queue) { spin_unlock(&queue_lock); mutex_unlock(&inode->i_mutex); - BUG_ON(rp->offset); + WARN_ON_ONCE(rp->offset); return 0; } rq = container_of(rp->q.list.next, struct cache_request, q.list); - BUG_ON(rq->q.reader); + WARN_ON_ONCE(rq->q.reader); if (rp->offset == 0) rq->readers++; spin_unlock(&queue_lock); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cdc7564b4512..507b5e84fbdb 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -132,8 +132,10 @@ static struct dentry *rpc_setup_pipedir_sb(struct super_block *sb, int error; dir = rpc_d_lookup_sb(sb, dir_name); - if (dir == NULL) + if (dir == NULL) { + pr_info("RPC: pipefs directory doesn't exist: %s\n", dir_name); return dir; + } for (;;) { q.len = snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++); name[sizeof(name) - 1] = '\0'; @@ -192,7 +194,8 @@ static int __rpc_clnt_handle_event(struct rpc_clnt *clnt, unsigned long event, case RPC_PIPEFS_MOUNT: dentry = rpc_setup_pipedir_sb(sb, clnt, clnt->cl_program->pipe_dir_name); - BUG_ON(dentry == NULL); + if (!dentry) + return -ENOENT; if (IS_ERR(dentry)) return PTR_ERR(dentry); clnt->cl_dentry = dentry; @@ -234,7 +237,7 @@ static struct rpc_clnt *rpc_get_client_for_event(struct net *net, int event) spin_lock(&sn->rpc_client_lock); list_for_each_entry(clnt, &sn->all_clients, cl_clients) { if (clnt->cl_program->pipe_dir_name == NULL) - break; + continue; if (rpc_clnt_skip_event(clnt, event)) continue; if (atomic_inc_not_zero(&clnt->cl_count) == 0) @@ -552,7 +555,7 @@ EXPORT_SYMBOL_GPL(rpc_clone_client); * rpc_clone_client_set_auth - Clone an RPC client structure and set its auth * * @clnt: RPC client whose parameters are copied - * @auth: security flavor for new client + * @flavor: security flavor for new client * * Returns a fresh RPC client or an ERR_PTR. */ @@ -607,6 +610,8 @@ EXPORT_SYMBOL_GPL(rpc_killall_tasks); */ void rpc_shutdown_client(struct rpc_clnt *clnt) { + might_sleep(); + dprintk_rcu("RPC: shutting down %s client for %s\n", clnt->cl_protname, rcu_dereference(clnt->cl_xprt)->servername); @@ -693,21 +698,19 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old, const struct rpc_program *program, u32 vers) { + struct rpc_create_args args = { + .program = program, + .prognumber = program->number, + .version = vers, + .authflavor = old->cl_auth->au_flavor, + .client_name = old->cl_principal, + }; struct rpc_clnt *clnt; - const struct rpc_version *version; int err; - BUG_ON(vers >= program->nrvers || !program->version[vers]); - version = program->version[vers]; - clnt = rpc_clone_client(old); + clnt = __rpc_clone_client(&args, old); if (IS_ERR(clnt)) goto out; - clnt->cl_procinfo = version->procs; - clnt->cl_maxproc = version->nrprocs; - clnt->cl_protname = program->name; - clnt->cl_prog = program->number; - clnt->cl_vers = version->number; - clnt->cl_stats = program->stats; err = rpc_ping(clnt); if (err != 0) { rpc_shutdown_client(clnt); @@ -832,7 +835,12 @@ int rpc_call_sync(struct rpc_clnt *clnt, const struct rpc_message *msg, int flag }; int status; - BUG_ON(flags & RPC_TASK_ASYNC); + WARN_ON_ONCE(flags & RPC_TASK_ASYNC); + if (flags & RPC_TASK_ASYNC) { + rpc_release_calldata(task_setup_data.callback_ops, + task_setup_data.callback_data); + return -EINVAL; + } task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) @@ -908,7 +916,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, task->tk_action = call_bc_transmit; atomic_inc(&task->tk_count); - BUG_ON(atomic_read(&task->tk_count) != 2); + WARN_ON_ONCE(atomic_read(&task->tk_count) != 2); rpc_execute(task); out: @@ -1368,6 +1376,7 @@ call_refreshresult(struct rpc_task *task) return; case -ETIMEDOUT: rpc_delay(task, 3*HZ); + case -EKEYEXPIRED: case -EAGAIN: status = -EACCES; if (!task->tk_cred_retry) @@ -1654,7 +1663,6 @@ call_transmit(struct rpc_task *task) task->tk_action = call_transmit_status; /* Encode here so that rpcsec_gss can use correct sequence number. */ if (rpc_task_need_encode(task)) { - BUG_ON(task->tk_rqstp->rq_bytes_sent != 0); rpc_xdr_encode(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) { @@ -1738,7 +1746,6 @@ call_bc_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - BUG_ON(task->tk_status != 0); task->tk_status = xprt_prepare_transmit(task); if (task->tk_status == -EAGAIN) { /* @@ -1785,7 +1792,7 @@ call_bc_transmit(struct rpc_task *task) * We were unable to reply and will have to drop the * request. The server should reconnect and retransmit. */ - BUG_ON(task->tk_status == -EAGAIN); + WARN_ON_ONCE(task->tk_status == -EAGAIN); printk(KERN_NOTICE "RPC: Could not send backchannel reply " "error: %d\n", task->tk_status); break; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 80f5dd23417d..fd10981ea792 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1093,7 +1093,7 @@ void rpc_put_sb_net(const struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); - BUG_ON(sn->pipefs_sb == NULL); + WARN_ON(sn->pipefs_sb == NULL); mutex_unlock(&sn->pipefs_sb_lock); } EXPORT_SYMBOL_GPL(rpc_put_sb_net); @@ -1152,14 +1152,19 @@ static void rpc_kill_sb(struct super_block *sb) struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); + if (sn->pipefs_sb != sb) { + mutex_unlock(&sn->pipefs_sb_lock); + goto out; + } sn->pipefs_sb = NULL; mutex_unlock(&sn->pipefs_sb_lock); - put_net(net); dprintk("RPC: sending pipefs UMOUNT notification for net %p%s\n", net, NET_NAME(net)); blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); + put_net(net); +out: kill_litter_super(sb); } diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index a70acae496e4..795a0f4e920b 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -23,7 +23,6 @@ #include <linux/errno.h> #include <linux/mutex.h> #include <linux/slab.h> -#include <linux/nsproxy.h> #include <net/ipv6.h> #include <linux/sunrpc/clnt.h> @@ -884,7 +883,10 @@ static void encode_rpcb_string(struct xdr_stream *xdr, const char *string, u32 len; len = strlen(string); - BUG_ON(len > maxstrlen); + WARN_ON_ONCE(len > maxstrlen); + if (len > maxstrlen) + /* truncate and hope for the best */ + len = maxstrlen; p = xdr_reserve_space(xdr, 4 + len); xdr_encode_opaque(p, string, len); } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6357fcb00c7e..bfa31714581f 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -98,6 +98,23 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task) list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list); } +static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority) +{ + queue->priority = priority; +} + +static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid) +{ + queue->owner = pid; + queue->nr = RPC_BATCH_COUNT; +} + +static void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue) +{ + rpc_set_waitqueue_priority(queue, queue->maxpriority); + rpc_set_waitqueue_owner(queue, 0); +} + /* * Add new request to a priority queue. */ @@ -109,9 +126,11 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, struct rpc_task *t; INIT_LIST_HEAD(&task->u.tk_wait.links); - q = &queue->tasks[queue_priority]; if (unlikely(queue_priority > queue->maxpriority)) - q = &queue->tasks[queue->maxpriority]; + queue_priority = queue->maxpriority; + if (queue_priority > queue->priority) + rpc_set_waitqueue_priority(queue, queue_priority); + q = &queue->tasks[queue_priority]; list_for_each_entry(t, q, u.tk_wait.list) { if (t->tk_owner == task->tk_owner) { list_add_tail(&task->u.tk_wait.list, &t->u.tk_wait.links); @@ -133,7 +152,9 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, struct rpc_task *task, unsigned char queue_priority) { - BUG_ON (RPC_IS_QUEUED(task)); + WARN_ON_ONCE(RPC_IS_QUEUED(task)); + if (RPC_IS_QUEUED(task)) + return; if (RPC_IS_PRIORITY(queue)) __rpc_add_wait_queue_priority(queue, task, queue_priority); @@ -178,24 +199,6 @@ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_tas task->tk_pid, queue, rpc_qname(queue)); } -static inline void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority) -{ - queue->priority = priority; - queue->count = 1 << (priority * 2); -} - -static inline void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid) -{ - queue->owner = pid; - queue->nr = RPC_BATCH_COUNT; -} - -static inline void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue) -{ - rpc_set_waitqueue_priority(queue, queue->maxpriority); - rpc_set_waitqueue_owner(queue, 0); -} - static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname, unsigned char nr_queues) { int i; @@ -334,7 +337,7 @@ static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, __rpc_add_wait_queue(q, task, queue_priority); - BUG_ON(task->tk_callback != NULL); + WARN_ON_ONCE(task->tk_callback != NULL); task->tk_callback = action; __rpc_add_timer(q, task); } @@ -343,7 +346,12 @@ void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task, rpc_action action) { /* We shouldn't ever put an inactive task to sleep */ - BUG_ON(!RPC_IS_ACTIVATED(task)); + WARN_ON_ONCE(!RPC_IS_ACTIVATED(task)); + if (!RPC_IS_ACTIVATED(task)) { + task->tk_status = -EIO; + rpc_put_task_async(task); + return; + } /* * Protect the queue operations. @@ -358,7 +366,12 @@ void rpc_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, rpc_action action, int priority) { /* We shouldn't ever put an inactive task to sleep */ - BUG_ON(!RPC_IS_ACTIVATED(task)); + WARN_ON_ONCE(!RPC_IS_ACTIVATED(task)); + if (!RPC_IS_ACTIVATED(task)) { + task->tk_status = -EIO; + rpc_put_task_async(task); + return; + } /* * Protect the queue operations. @@ -367,6 +380,7 @@ void rpc_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, __rpc_sleep_on_priority(q, task, action, priority - RPC_PRIORITY_LOW); spin_unlock_bh(&q->lock); } +EXPORT_SYMBOL_GPL(rpc_sleep_on_priority); /** * __rpc_do_wake_up_task - wake up a single rpc_task @@ -451,8 +465,7 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q /* * Check if we need to switch queues. */ - if (--queue->count) - goto new_owner; + goto new_owner; } /* @@ -697,7 +710,9 @@ static void __rpc_execute(struct rpc_task *task) dprintk("RPC: %5u __rpc_execute flags=0x%x\n", task->tk_pid, task->tk_flags); - BUG_ON(RPC_IS_QUEUED(task)); + WARN_ON_ONCE(RPC_IS_QUEUED(task)); + if (RPC_IS_QUEUED(task)) + return; for (;;) { void (*do_action)(struct rpc_task *); @@ -919,16 +934,35 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) return task; } +/* + * rpc_free_task - release rpc task and perform cleanups + * + * Note that we free up the rpc_task _after_ rpc_release_calldata() + * in order to work around a workqueue dependency issue. + * + * Tejun Heo states: + * "Workqueue currently considers two work items to be the same if they're + * on the same address and won't execute them concurrently - ie. it + * makes a work item which is queued again while being executed wait + * for the previous execution to complete. + * + * If a work function frees the work item, and then waits for an event + * which should be performed by another work item and *that* work item + * recycles the freed work item, it can create a false dependency loop. + * There really is no reliable way to detect this short of verifying + * every memory free." + * + */ static void rpc_free_task(struct rpc_task *task) { - const struct rpc_call_ops *tk_ops = task->tk_ops; - void *calldata = task->tk_calldata; + unsigned short tk_flags = task->tk_flags; + + rpc_release_calldata(task->tk_ops, task->tk_calldata); - if (task->tk_flags & RPC_TASK_DYNAMIC) { + if (tk_flags & RPC_TASK_DYNAMIC) { dprintk("RPC: %5u freeing task\n", task->tk_pid); mempool_free(task, rpc_task_mempool); } - rpc_release_calldata(tk_ops, calldata); } static void rpc_async_release(struct work_struct *work) @@ -938,8 +972,7 @@ static void rpc_async_release(struct work_struct *work) static void rpc_release_resources_task(struct rpc_task *task) { - if (task->tk_rqstp) - xprt_release(task); + xprt_release(task); if (task->tk_msg.rpc_cred) { put_rpccred(task->tk_msg.rpc_cred); task->tk_msg.rpc_cred = NULL; @@ -981,7 +1014,7 @@ static void rpc_release_task(struct rpc_task *task) { dprintk("RPC: %5u release task\n", task->tk_pid); - BUG_ON (RPC_IS_QUEUED(task)); + WARN_ON_ONCE(RPC_IS_QUEUED(task)); rpc_release_resources_task(task); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 3ee7461926d8..dbf12ac5ecb7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -20,7 +20,6 @@ #include <linux/module.h> #include <linux/kthread.h> #include <linux/slab.h> -#include <linux/nsproxy.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> @@ -324,7 +323,9 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx) * The caller checks for sv_nrpools > 1, which * implies that we've been initialized. */ - BUG_ON(m->count == 0); + WARN_ON_ONCE(m->count == 0); + if (m->count == 0) + return; switch (m->mode) { case SVC_POOL_PERCPU: @@ -585,7 +586,9 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node) * We assume one is at most one page */ arghi = 0; - BUG_ON(pages > RPCSVC_MAXPAGES); + WARN_ON_ONCE(pages > RPCSVC_MAXPAGES); + if (pages > RPCSVC_MAXPAGES) + pages = RPCSVC_MAXPAGES; while (pages) { struct page *p = alloc_pages_node(node, GFP_KERNEL, 0); if (!p) @@ -946,7 +949,9 @@ int svc_register(const struct svc_serv *serv, struct net *net, unsigned int i; int error = 0; - BUG_ON(proto == 0 && port == 0); + WARN_ON_ONCE(proto == 0 && port == 0); + if (proto == 0 && port == 0) + return -EINVAL; for (progp = serv->sv_program; progp; progp = progp->pg_next) { for (i = 0; i < progp->pg_nvers; i++) { @@ -1035,7 +1040,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) } /* - * Printk the given error with the address of the client that caused it. + * dprintk the given error with the address of the client that caused it. */ static __printf(2, 3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) @@ -1049,8 +1054,7 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - net_warn_ratelimited("svc: %s: %pV", - svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); + dprintk("svc: %s: %pV", svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); va_end(args); } @@ -1299,7 +1303,7 @@ svc_process(struct svc_rqst *rqstp) * Setup response xdr_buf. * Initially it has just one page */ - rqstp->rq_resused = 1; + rqstp->rq_next_page = &rqstp->rq_respages[1]; resv->iov_base = page_address(rqstp->rq_respages[0]); resv->iov_len = 0; rqstp->rq_res.pages = rqstp->rq_respages + 1; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 194d865fae72..b8e47fac7315 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -218,7 +218,9 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, */ static void svc_xprt_received(struct svc_xprt *xprt) { - BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags)); + WARN_ON_ONCE(!test_bit(XPT_BUSY, &xprt->xpt_flags)); + if (!test_bit(XPT_BUSY, &xprt->xpt_flags)) + return; /* As soon as we clear busy, the xprt could be closed and * 'put', so we need a reference to call svc_xprt_enqueue with: */ @@ -577,7 +579,10 @@ int svc_alloc_arg(struct svc_rqst *rqstp) /* now allocate needed pages. If we get a failure, sleep briefly */ pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE; - BUG_ON(pages >= RPCSVC_MAXPAGES); + WARN_ON_ONCE(pages >= RPCSVC_MAXPAGES); + if (pages >= RPCSVC_MAXPAGES) + /* use as many pages as possible */ + pages = RPCSVC_MAXPAGES - 1; for (i = 0; i < pages ; i++) while (rqstp->rq_pages[i] == NULL) { struct page *p = alloc_page(GFP_KERNEL); @@ -926,7 +931,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt) spin_lock_bh(&serv->sv_lock); if (!test_and_set_bit(XPT_DETACHED, &xprt->xpt_flags)) list_del_init(&xprt->xpt_list); - BUG_ON(!list_empty(&xprt->xpt_ready)); + WARN_ON_ONCE(!list_empty(&xprt->xpt_ready)); if (test_bit(XPT_TEMP, &xprt->xpt_flags)) serv->sv_tmpcnt--; spin_unlock_bh(&serv->sv_lock); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 03827cef1fa7..0a148c9d2a5c 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -84,7 +84,11 @@ static struct lock_class_key svc_slock_key[2]; static void svc_reclassify_socket(struct socket *sock) { struct sock *sk = sock->sk; - BUG_ON(sock_owned_by_user(sk)); + + WARN_ON_ONCE(sock_owned_by_user(sk)); + if (sock_owned_by_user(sk)) + return; + switch (sk->sk_family) { case AF_INET: sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD", @@ -601,6 +605,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_respages = rqstp->rq_pages + 1 + DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE); } + rqstp->rq_next_page = rqstp->rq_respages+1; if (serv->sv_stats) serv->sv_stats->netudpcnt++; @@ -874,9 +879,9 @@ static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst { unsigned int i, len, npages; - if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + if (svsk->sk_datalen == 0) return 0; - len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { if (rqstp->rq_pages[i] != NULL) @@ -893,9 +898,9 @@ static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp) { unsigned int i, len, npages; - if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + if (svsk->sk_datalen == 0) return; - len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { svsk->sk_pages[i] = rqstp->rq_pages[i]; @@ -907,9 +912,9 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk) { unsigned int i, len, npages; - if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + if (svsk->sk_datalen == 0) goto out; - len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { BUG_ON(svsk->sk_pages[i] == NULL); @@ -918,13 +923,12 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk) } out: svsk->sk_tcplen = 0; + svsk->sk_datalen = 0; } /* - * Receive data. + * Receive fragment record header. * If we haven't gotten the record length yet, get the next four bytes. - * Otherwise try to gobble up as much as possible up to the complete - * record length. */ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) { @@ -950,32 +954,16 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) return -EAGAIN; } - svsk->sk_reclen = ntohl(svsk->sk_reclen); - if (!(svsk->sk_reclen & RPC_LAST_STREAM_FRAGMENT)) { - /* FIXME: technically, a record can be fragmented, - * and non-terminal fragments will not have the top - * bit set in the fragment length header. - * But apparently no known nfs clients send fragmented - * records. */ - net_notice_ratelimited("RPC: multiple fragments per record not supported\n"); - goto err_delete; - } - - svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK; - dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen); - if (svsk->sk_reclen > serv->sv_max_mesg) { - net_notice_ratelimited("RPC: fragment too large: 0x%08lx\n", - (unsigned long)svsk->sk_reclen); + dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk)); + if (svc_sock_reclen(svsk) + svsk->sk_datalen > + serv->sv_max_mesg) { + net_notice_ratelimited("RPC: fragment too large: %d\n", + svc_sock_reclen(svsk)); goto err_delete; } } - if (svsk->sk_reclen < 8) - goto err_delete; /* client is nuts. */ - - len = svsk->sk_reclen; - - return len; + return svc_sock_reclen(svsk); error: dprintk("RPC: TCP recv_record got %d\n", len); return len; @@ -1019,7 +1007,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) if (dst->iov_len < src->iov_len) return -EAGAIN; /* whatever; just giving up. */ memcpy(dst->iov_base, src->iov_base, src->iov_len); - xprt_complete_rqst(req->rq_task, svsk->sk_reclen); + xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len); rqstp->rq_arg.len = 0; return 0; } @@ -1038,6 +1026,17 @@ static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len) return i; } +static void svc_tcp_fragment_received(struct svc_sock *svsk) +{ + /* If we have more data, signal svc_xprt_enqueue() to try again */ + if (svc_recv_available(svsk) > sizeof(rpc_fraghdr)) + set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + dprintk("svc: TCP %s record (%d bytes)\n", + svc_sock_final_rec(svsk) ? "final" : "nonfinal", + svc_sock_reclen(svsk)); + svsk->sk_tcplen = 0; + svsk->sk_reclen = 0; +} /* * Receive data from a TCP socket. @@ -1064,29 +1063,39 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) goto error; base = svc_tcp_restore_pages(svsk, rqstp); - want = svsk->sk_reclen - base; + want = svc_sock_reclen(svsk) - (svsk->sk_tcplen - sizeof(rpc_fraghdr)); vec = rqstp->rq_vec; pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], - svsk->sk_reclen); + svsk->sk_datalen + want); rqstp->rq_respages = &rqstp->rq_pages[pnum]; + rqstp->rq_next_page = rqstp->rq_respages + 1; /* Now receive data */ len = svc_partial_recvfrom(rqstp, vec, pnum, want, base); - if (len >= 0) + if (len >= 0) { svsk->sk_tcplen += len; - if (len != want) { + svsk->sk_datalen += len; + } + if (len != want || !svc_sock_final_rec(svsk)) { svc_tcp_save_pages(svsk, rqstp); if (len < 0 && len != -EAGAIN) - goto err_other; - dprintk("svc: incomplete TCP record (%d of %d)\n", - svsk->sk_tcplen, svsk->sk_reclen); + goto err_delete; + if (len == want) + svc_tcp_fragment_received(svsk); + else + dprintk("svc: incomplete TCP record (%d of %d)\n", + (int)(svsk->sk_tcplen - sizeof(rpc_fraghdr)), + svc_sock_reclen(svsk)); goto err_noclose; } - rqstp->rq_arg.len = svsk->sk_reclen; + if (svc_sock_reclen(svsk) < 8) + goto err_delete; /* client is nuts. */ + + rqstp->rq_arg.len = svsk->sk_datalen; rqstp->rq_arg.page_base = 0; if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) { rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len; @@ -1103,11 +1112,8 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) len = receive_cb_reply(svsk, rqstp); /* Reset TCP read info */ - svsk->sk_reclen = 0; - svsk->sk_tcplen = 0; - /* If we have more data, signal svc_xprt_enqueue() to try again */ - if (svc_recv_available(svsk) > sizeof(rpc_fraghdr)) - set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + svsk->sk_datalen = 0; + svc_tcp_fragment_received(svsk); if (len < 0) goto error; @@ -1116,15 +1122,14 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) if (serv->sv_stats) serv->sv_stats->nettcpcnt++; - dprintk("svc: TCP complete record (%d bytes)\n", rqstp->rq_arg.len); return rqstp->rq_arg.len; error: if (len != -EAGAIN) - goto err_other; + goto err_delete; dprintk("RPC: TCP recvfrom got EAGAIN\n"); return 0; -err_other: +err_delete: printk(KERN_NOTICE "%s: recvfrom returned errno %d\n", svsk->sk_xprt.xpt_server->sv_name, -len); set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); @@ -1301,6 +1306,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) svsk->sk_reclen = 0; svsk->sk_tcplen = 0; + svsk->sk_datalen = 0; memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages)); tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 08f50afd5f2a..56055632f151 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -318,7 +318,10 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len) tail = buf->tail; head = buf->head; - BUG_ON (len > head->iov_len); + + WARN_ON_ONCE(len > head->iov_len); + if (len > head->iov_len) + len = head->iov_len; /* Shift the tail first */ if (tail->iov_len != 0) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index bd462a532acf..33811db8788a 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1136,10 +1136,18 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) void xprt_release(struct rpc_task *task) { struct rpc_xprt *xprt; - struct rpc_rqst *req; + struct rpc_rqst *req = task->tk_rqstp; - if (!(req = task->tk_rqstp)) + if (req == NULL) { + if (task->tk_client) { + rcu_read_lock(); + xprt = rcu_dereference(task->tk_client->cl_xprt); + if (xprt->snd_task == task) + xprt_release_write(xprt, task); + rcu_read_unlock(); + } return; + } xprt = req->rq_xprt; if (task->tk_ops->rpc_count_stats != NULL) diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 41cb63b623df..0ce75524ed21 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -521,11 +521,11 @@ next_sge: rqstp->rq_pages[ch_no] = NULL; /* - * Detach res pages. svc_release must see a resused count of - * zero or it will attempt to put them. + * Detach res pages. If svc_release sees any it will attempt to + * put them. */ - while (rqstp->rq_resused) - rqstp->rq_respages[--rqstp->rq_resused] = NULL; + while (rqstp->rq_next_page != rqstp->rq_respages) + *(--rqstp->rq_next_page) = NULL; return err; } @@ -550,7 +550,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp, /* rq_respages starts after the last arg page */ rqstp->rq_respages = &rqstp->rq_arg.pages[page_no]; - rqstp->rq_resused = 0; + rqstp->rq_next_page = &rqstp->rq_arg.pages[page_no]; /* Rebuild rq_arg head and tail. */ rqstp->rq_arg.head[0] = head->arg.head[0]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 42eb7ba0b903..c1d124dc772b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -548,6 +548,7 @@ static int send_reply(struct svcxprt_rdma *rdma, int sge_no; int sge_bytes; int page_no; + int pages; int ret; /* Post a recv buffer to handle another request. */ @@ -611,7 +612,8 @@ static int send_reply(struct svcxprt_rdma *rdma, * respages array. They are our pages until the I/O * completes. */ - for (page_no = 0; page_no < rqstp->rq_resused; page_no++) { + pages = rqstp->rq_next_page - rqstp->rq_respages; + for (page_no = 0; page_no < pages; page_no++) { ctxt->pages[page_no+1] = rqstp->rq_respages[page_no]; ctxt->count++; rqstp->rq_respages[page_no] = NULL; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 75853cabf4c9..68b0a81c31d5 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1746,7 +1746,6 @@ static inline void xs_reclassify_socketu(struct socket *sock) { struct sock *sk = sock->sk; - BUG_ON(sock_owned_by_user(sk)); sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC", &xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]); } @@ -1755,7 +1754,6 @@ static inline void xs_reclassify_socket4(struct socket *sock) { struct sock *sk = sock->sk; - BUG_ON(sock_owned_by_user(sk)); sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC", &xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]); } @@ -1764,13 +1762,16 @@ static inline void xs_reclassify_socket6(struct socket *sock) { struct sock *sk = sock->sk; - BUG_ON(sock_owned_by_user(sk)); sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC", &xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]); } static inline void xs_reclassify_socket(int family, struct socket *sock) { + WARN_ON_ONCE(sock_owned_by_user(sock->sk)); + if (sock_owned_by_user(sock->sk)) + return; + switch (family) { case AF_LOCAL: xs_reclassify_socketu(sock); @@ -1901,6 +1902,10 @@ static void xs_local_setup_socket(struct work_struct *work) dprintk("RPC: xprt %p: socket %s does not exist\n", xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); break; + case -ECONNREFUSED: + dprintk("RPC: xprt %p: connection refused for %s\n", + xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); + break; default: printk(KERN_ERR "%s: unhandled error (%d) connecting to %s\n", __func__, -status, @@ -2329,9 +2334,11 @@ static void *bc_malloc(struct rpc_task *task, size_t size) struct page *page; struct rpc_buffer *buf; - BUG_ON(size > PAGE_SIZE - sizeof(struct rpc_buffer)); - page = alloc_page(GFP_KERNEL); + WARN_ON_ONCE(size > PAGE_SIZE - sizeof(struct rpc_buffer)); + if (size > PAGE_SIZE - sizeof(struct rpc_buffer)) + return NULL; + page = alloc_page(GFP_KERNEL); if (!page) return NULL; @@ -2393,7 +2400,6 @@ static int bc_send_request(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct svc_xprt *xprt; - struct svc_sock *svsk; u32 len; dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid)); @@ -2401,7 +2407,6 @@ static int bc_send_request(struct rpc_task *task) * Get the server socket associated with this callback xprt */ xprt = req->rq_xprt->bc_xprt; - svsk = container_of(xprt, struct svc_sock, sk_xprt); /* * Grab the mutex to serialize data as the connection is shared diff --git a/net/sysctl_net.c b/net/sysctl_net.c index e3a6e37cd1c5..9bc6db04be3e 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -38,15 +38,24 @@ static int is_seen(struct ctl_table_set *set) } /* Return standard mode bits for table entry. */ -static int net_ctl_permissions(struct ctl_table_root *root, - struct nsproxy *nsproxy, +static int net_ctl_permissions(struct ctl_table_header *head, struct ctl_table *table) { + struct net *net = container_of(head->set, struct net, sysctls); + kuid_t root_uid = make_kuid(net->user_ns, 0); + kgid_t root_gid = make_kgid(net->user_ns, 0); + /* Allow network administrator to have same access as root. */ - if (capable(CAP_NET_ADMIN)) { + if (ns_capable(net->user_ns, CAP_NET_ADMIN) || + uid_eq(root_uid, current_uid())) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } + /* Allow netns root group to have the same access as the root group */ + if (gid_eq(root_gid, current_gid())) { + int mode = (table->mode >> 3) & 7; + return (mode << 3) | mode; + } return table->mode; } diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 585460180ffb..bc41bd31eadc 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -20,18 +20,9 @@ menuconfig TIPC If in doubt, say N. -if TIPC - -config TIPC_ADVANCED - bool "Advanced TIPC configuration" - default n - help - Saying Y here will open some advanced configuration for TIPC. - Most users do not need to bother; if unsure, just say N. - config TIPC_PORTS int "Maximum number of ports in a node" - depends on TIPC_ADVANCED + depends on TIPC range 127 65535 default "8191" help @@ -40,5 +31,3 @@ config TIPC_PORTS Setting this to a smaller value saves some memory, setting it to higher allows for more ports. - -endif # TIPC diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index e4e6d8cd47e6..54f89f90ac33 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -347,7 +347,7 @@ static void bclink_peek_nack(struct tipc_msg *msg) tipc_node_lock(n_ptr); - if (n_ptr->bclink.supported && + if (n_ptr->bclink.recv_permitted && (n_ptr->bclink.last_in != n_ptr->bclink.last_sent) && (n_ptr->bclink.last_in == msg_bcgap_after(msg))) n_ptr->bclink.oos_state = 2; @@ -429,7 +429,7 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) goto exit; tipc_node_lock(node); - if (unlikely(!node->bclink.supported)) + if (unlikely(!node->bclink.recv_permitted)) goto unlock; /* Handle broadcast protocol message */ @@ -564,7 +564,7 @@ exit: u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) { - return (n_ptr->bclink.supported && + return (n_ptr->bclink.recv_permitted && (tipc_bclink_get_last_sent() != n_ptr->bclink.acked)); } @@ -619,16 +619,14 @@ static int tipc_bcbearer_send(struct sk_buff *buf, if (bcbearer->remains_new.count == bcbearer->remains.count) continue; /* bearer pair doesn't add anything */ - if (p->blocked || - p->media->send_msg(buf, p, &p->media->bcast_addr)) { + if (!tipc_bearer_blocked(p)) + tipc_bearer_send(p, buf, &p->media->bcast_addr); + else if (s && !tipc_bearer_blocked(s)) /* unable to send on primary bearer */ - if (!s || s->blocked || - s->media->send_msg(buf, s, - &s->media->bcast_addr)) { - /* unable to send on either bearer */ - continue; - } - } + tipc_bearer_send(s, buf, &s->media->bcast_addr); + else + /* unable to send on either bearer */ + continue; if (s) { bcbearer->bpairs[bp_index].primary = s; @@ -731,8 +729,8 @@ int tipc_bclink_stats(char *buf, const u32 buf_size) " TX naks:%u acks:%u dups:%u\n", s->sent_nacks, s->sent_acks, s->retransmitted); ret += tipc_snprintf(buf + ret, buf_size - ret, - " Congestion bearer:%u link:%u Send queue max:%u avg:%u\n", - s->bearer_congs, s->link_congs, s->max_queue_sz, + " Congestion link:%u Send queue max:%u avg:%u\n", + s->link_congs, s->max_queue_sz, s->queue_sz_counts ? (s->accu_queue_sz / s->queue_sz_counts) : 0); @@ -766,7 +764,6 @@ int tipc_bclink_set_queue_limits(u32 limit) void tipc_bclink_init(void) { - INIT_LIST_HEAD(&bcbearer->bearer.cong_links); bcbearer->bearer.media = &bcbearer->media; bcbearer->media.send_msg = tipc_bcbearer_send; sprintf(bcbearer->media.name, "tipc-broadcast"); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 4ec5c80e8a7c..aa62f93a9127 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -279,116 +279,31 @@ void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest) } /* - * bearer_push(): Resolve bearer congestion. Force the waiting - * links to push out their unsent packets, one packet per link - * per iteration, until all packets are gone or congestion reoccurs. - * 'tipc_net_lock' is read_locked when this function is called - * bearer.lock must be taken before calling - * Returns binary true(1) ore false(0) - */ -static int bearer_push(struct tipc_bearer *b_ptr) -{ - u32 res = 0; - struct tipc_link *ln, *tln; - - if (b_ptr->blocked) - return 0; - - while (!list_empty(&b_ptr->cong_links) && (res != PUSH_FAILED)) { - list_for_each_entry_safe(ln, tln, &b_ptr->cong_links, link_list) { - res = tipc_link_push_packet(ln); - if (res == PUSH_FAILED) - break; - if (res == PUSH_FINISHED) - list_move_tail(&ln->link_list, &b_ptr->links); - } - } - return list_empty(&b_ptr->cong_links); -} - -void tipc_bearer_lock_push(struct tipc_bearer *b_ptr) -{ - spin_lock_bh(&b_ptr->lock); - bearer_push(b_ptr); - spin_unlock_bh(&b_ptr->lock); -} - - -/* - * Interrupt enabling new requests after bearer congestion or blocking: + * Interrupt enabling new requests after bearer blocking: * See bearer_send(). */ -void tipc_continue(struct tipc_bearer *b_ptr) +void tipc_continue(struct tipc_bearer *b) { - spin_lock_bh(&b_ptr->lock); - if (!list_empty(&b_ptr->cong_links)) - tipc_k_signal((Handler)tipc_bearer_lock_push, (unsigned long)b_ptr); - b_ptr->blocked = 0; - spin_unlock_bh(&b_ptr->lock); + spin_lock_bh(&b->lock); + b->blocked = 0; + spin_unlock_bh(&b->lock); } /* - * Schedule link for sending of messages after the bearer - * has been deblocked by 'continue()'. This method is called - * when somebody tries to send a message via this link while - * the bearer is congested. 'tipc_net_lock' is in read_lock here - * bearer.lock is busy + * tipc_bearer_blocked - determines if bearer is currently blocked */ -static void tipc_bearer_schedule_unlocked(struct tipc_bearer *b_ptr, - struct tipc_link *l_ptr) +int tipc_bearer_blocked(struct tipc_bearer *b) { - list_move_tail(&l_ptr->link_list, &b_ptr->cong_links); -} - -/* - * Schedule link for sending of messages after the bearer - * has been deblocked by 'continue()'. This method is called - * when somebody tries to send a message via this link while - * the bearer is congested. 'tipc_net_lock' is in read_lock here, - * bearer.lock is free - */ -void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr) -{ - spin_lock_bh(&b_ptr->lock); - tipc_bearer_schedule_unlocked(b_ptr, l_ptr); - spin_unlock_bh(&b_ptr->lock); -} - + int res; -/* - * tipc_bearer_resolve_congestion(): Check if there is bearer congestion, - * and if there is, try to resolve it before returning. - * 'tipc_net_lock' is read_locked when this function is called - */ -int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr, - struct tipc_link *l_ptr) -{ - int res = 1; + spin_lock_bh(&b->lock); + res = b->blocked; + spin_unlock_bh(&b->lock); - if (list_empty(&b_ptr->cong_links)) - return 1; - spin_lock_bh(&b_ptr->lock); - if (!bearer_push(b_ptr)) { - tipc_bearer_schedule_unlocked(b_ptr, l_ptr); - res = 0; - } - spin_unlock_bh(&b_ptr->lock); return res; } /** - * tipc_bearer_congested - determines if bearer is currently congested - */ -int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr) -{ - if (unlikely(b_ptr->blocked)) - return 1; - if (likely(list_empty(&b_ptr->cong_links))) - return 0; - return !tipc_bearer_resolve_congestion(b_ptr, l_ptr); -} - -/** * tipc_enable_bearer - enable bearer with the given name */ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) @@ -489,7 +404,6 @@ restart: b_ptr->net_plane = bearer_id + 'A'; b_ptr->active = 1; b_ptr->priority = priority; - INIT_LIST_HEAD(&b_ptr->cong_links); INIT_LIST_HEAD(&b_ptr->links); spin_lock_init(&b_ptr->lock); @@ -528,7 +442,6 @@ int tipc_block_bearer(const char *name) pr_info("Blocking bearer <%s>\n", name); spin_lock_bh(&b_ptr->lock); b_ptr->blocked = 1; - list_splice_init(&b_ptr->cong_links, &b_ptr->links); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { struct tipc_node *n_ptr = l_ptr->owner; @@ -555,7 +468,6 @@ static void bearer_disable(struct tipc_bearer *b_ptr) spin_lock_bh(&b_ptr->lock); b_ptr->blocked = 1; b_ptr->media->disable_bearer(b_ptr); - list_splice_init(&b_ptr->cong_links, &b_ptr->links); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); } diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index dd4c2abf08e7..39f1192d04bf 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -120,7 +120,6 @@ struct tipc_media { * @identity: array index of this bearer within TIPC bearer array * @link_req: ptr to (optional) structure making periodic link setup requests * @links: list of non-congested links associated with bearer - * @cong_links: list of congested links associated with bearer * @active: non-zero if bearer structure is represents a bearer * @net_plane: network plane ('A' through 'H') currently associated with bearer * @nodes: indicates which nodes in cluster can be reached through bearer @@ -143,7 +142,6 @@ struct tipc_bearer { u32 identity; struct tipc_link_req *link_req; struct list_head links; - struct list_head cong_links; int active; char net_plane; struct tipc_node_map nodes; @@ -185,39 +183,23 @@ struct sk_buff *tipc_media_get_names(void); struct sk_buff *tipc_bearer_get_names(void); void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest); void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest); -void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr); struct tipc_bearer *tipc_bearer_find(const char *name); struct tipc_bearer *tipc_bearer_find_interface(const char *if_name); struct tipc_media *tipc_media_find(const char *name); -int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr, - struct tipc_link *l_ptr); -int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct tipc_link *l_ptr); +int tipc_bearer_blocked(struct tipc_bearer *b_ptr); void tipc_bearer_stop(void); -void tipc_bearer_lock_push(struct tipc_bearer *b_ptr); - /** * tipc_bearer_send- sends buffer to destination over bearer * - * Returns true (1) if successful, or false (0) if unable to send - * * IMPORTANT: * The media send routine must not alter the buffer being passed in * as it may be needed for later retransmission! - * - * If the media send routine returns a non-zero value (indicating that - * it was unable to send the buffer), it must: - * 1) mark the bearer as blocked, - * 2) call tipc_continue() once the bearer is able to send again. - * Media types that are unable to meet these two critera must ensure their - * send routine always returns success -- even if the buffer was not sent -- - * and let TIPC's link code deal with the undelivered message. */ -static inline int tipc_bearer_send(struct tipc_bearer *b_ptr, - struct sk_buff *buf, +static inline void tipc_bearer_send(struct tipc_bearer *b, struct sk_buff *buf, struct tipc_media_addr *dest) { - return !b_ptr->media->send_msg(buf, b_ptr, dest); + b->media->send_msg(buf, b, dest); } #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.c b/net/tipc/core.c index bfe8af88469a..fc05cecd7481 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -42,11 +42,6 @@ #include <linux/module.h> -#ifndef CONFIG_TIPC_PORTS -#define CONFIG_TIPC_PORTS 8191 -#endif - - /* global variables used by multiple sub-systems within TIPC */ int tipc_random __read_mostly; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 50eaa403eb6e..1074b9587e81 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -243,7 +243,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) if ((type == DSC_REQ_MSG) && !link_fully_up && !b_ptr->blocked) { rbuf = tipc_disc_init_msg(DSC_RESP_MSG, orig, b_ptr); if (rbuf) { - b_ptr->media->send_msg(rbuf, b_ptr, &media_addr); + tipc_bearer_send(b_ptr, rbuf, &media_addr); kfree_skb(rbuf); } } diff --git a/net/tipc/handler.c b/net/tipc/handler.c index 111ff8300ae5..b36f0fcd9bdf 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -116,7 +116,6 @@ void tipc_handler_stop(void) return; handler_enabled = 0; - tasklet_disable(&tipc_tasklet); tasklet_kill(&tipc_tasklet); spin_lock_bh(&qitem_lock); diff --git a/net/tipc/link.c b/net/tipc/link.c index a79c755cb417..daa6080a2a0c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1,7 +1,7 @@ /* * net/tipc/link.c: TIPC link code * - * Copyright (c) 1996-2007, Ericsson AB + * Copyright (c) 1996-2007, 2012, Ericsson AB * Copyright (c) 2004-2007, 2010-2011, Wind River Systems * All rights reserved. * @@ -97,12 +97,13 @@ static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, u32 num_sect, unsigned int total_len, u32 destnode); -static void link_check_defragm_bufs(struct tipc_link *l_ptr); static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); static void link_start(struct tipc_link *l_ptr); static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf); +static void tipc_link_send_sync(struct tipc_link *l); +static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf); /* * Simple link routines @@ -269,7 +270,6 @@ static void link_timeout(struct tipc_link *l_ptr) } /* do all other link processing performed on a periodic basis */ - link_check_defragm_bufs(l_ptr); link_state_event(l_ptr, TIMEOUT_EVT); @@ -712,6 +712,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_activate(l_ptr); tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; + if (l_ptr->owner->working_links == 1) + tipc_link_send_sync(l_ptr); link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: @@ -745,6 +747,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_activate(l_ptr); tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; + if (l_ptr->owner->working_links == 1) + tipc_link_send_sync(l_ptr); link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: @@ -872,17 +876,12 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) return link_send_long_buf(l_ptr, buf); /* Packet can be queued or sent. */ - if (likely(!tipc_bearer_congested(l_ptr->b_ptr, l_ptr) && + if (likely(!tipc_bearer_blocked(l_ptr->b_ptr) && !link_congested(l_ptr))) { link_add_to_outqueue(l_ptr, buf, msg); - if (likely(tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr))) { - l_ptr->unacked_window = 0; - } else { - tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); - l_ptr->stats.bearer_congs++; - l_ptr->next_out = buf; - } + tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); + l_ptr->unacked_window = 0; return dsz; } /* Congestion: can message be bundled ? */ @@ -891,10 +890,8 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) /* Try adding message to an existing bundle */ if (l_ptr->next_out && - link_bundle_buf(l_ptr, l_ptr->last_out, buf)) { - tipc_bearer_resolve_congestion(l_ptr->b_ptr, l_ptr); + link_bundle_buf(l_ptr, l_ptr->last_out, buf)) return dsz; - } /* Try creating a new bundle */ if (size <= max_packet * 2 / 3) { @@ -917,7 +914,6 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) if (!l_ptr->next_out) l_ptr->next_out = buf; link_add_to_outqueue(l_ptr, buf, msg); - tipc_bearer_resolve_congestion(l_ptr->b_ptr, l_ptr); return dsz; } @@ -949,7 +945,48 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) return res; } -/** +/* + * tipc_link_send_sync - synchronize broadcast link endpoints. + * + * Give a newly added peer node the sequence number where it should + * start receiving and acking broadcast packets. + * + * Called with node locked + */ +static void tipc_link_send_sync(struct tipc_link *l) +{ + struct sk_buff *buf; + struct tipc_msg *msg; + + buf = tipc_buf_acquire(INT_H_SIZE); + if (!buf) + return; + + msg = buf_msg(buf); + tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, l->addr); + msg_set_last_bcast(msg, l->owner->bclink.acked); + link_add_chain_to_outqueue(l, buf, 0); + tipc_link_push_queue(l); +} + +/* + * tipc_link_recv_sync - synchronize broadcast link endpoints. + * Receive the sequence number where we should start receiving and + * acking broadcast packets from a newly added peer node, and open + * up for reception of such packets. + * + * Called with node locked + */ +static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + + n->bclink.last_sent = n->bclink.last_in = msg_last_bcast(msg); + n->bclink.recv_permitted = true; + kfree_skb(buf); +} + +/* * tipc_link_send_names - send name table entries to new neighbor * * Send routine for bulk delivery of name table messages when contact @@ -1006,16 +1043,11 @@ static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, if (likely(!link_congested(l_ptr))) { if (likely(msg_size(msg) <= l_ptr->max_pkt)) { - if (likely(list_empty(&l_ptr->b_ptr->cong_links))) { + if (likely(!tipc_bearer_blocked(l_ptr->b_ptr))) { link_add_to_outqueue(l_ptr, buf, msg); - if (likely(tipc_bearer_send(l_ptr->b_ptr, buf, - &l_ptr->media_addr))) { - l_ptr->unacked_window = 0; - return res; - } - tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); - l_ptr->stats.bearer_congs++; - l_ptr->next_out = buf; + tipc_bearer_send(l_ptr->b_ptr, buf, + &l_ptr->media_addr); + l_ptr->unacked_window = 0; return res; } } else @@ -1106,7 +1138,7 @@ exit: /* Exit if link (or bearer) is congested */ if (link_congested(l_ptr) || - !list_empty(&l_ptr->b_ptr->cong_links)) { + tipc_bearer_blocked(l_ptr->b_ptr)) { res = link_schedule_port(l_ptr, sender->ref, res); goto exit; @@ -1329,15 +1361,11 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) if (r_q_size && buf) { msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in); - if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { - l_ptr->retransm_queue_head = mod(++r_q_head); - l_ptr->retransm_queue_size = --r_q_size; - l_ptr->stats.retransmitted++; - return 0; - } else { - l_ptr->stats.bearer_congs++; - return PUSH_FAILED; - } + tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); + l_ptr->retransm_queue_head = mod(++r_q_head); + l_ptr->retransm_queue_size = --r_q_size; + l_ptr->stats.retransmitted++; + return 0; } /* Send deferred protocol message, if any: */ @@ -1345,15 +1373,11 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) if (buf) { msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in); - if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { - l_ptr->unacked_window = 0; - kfree_skb(buf); - l_ptr->proto_msg_queue = NULL; - return 0; - } else { - l_ptr->stats.bearer_congs++; - return PUSH_FAILED; - } + tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); + l_ptr->unacked_window = 0; + kfree_skb(buf); + l_ptr->proto_msg_queue = NULL; + return 0; } /* Send one deferred data message, if send window not full: */ @@ -1366,18 +1390,14 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) if (mod(next - first) < l_ptr->queue_limit[0]) { msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { - if (msg_user(msg) == MSG_BUNDLER) - msg_set_type(msg, CLOSED_MSG); - l_ptr->next_out = buf->next; - return 0; - } else { - l_ptr->stats.bearer_congs++; - return PUSH_FAILED; - } + tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); + if (msg_user(msg) == MSG_BUNDLER) + msg_set_type(msg, CLOSED_MSG); + l_ptr->next_out = buf->next; + return 0; } } - return PUSH_FINISHED; + return 1; } /* @@ -1388,15 +1408,12 @@ void tipc_link_push_queue(struct tipc_link *l_ptr) { u32 res; - if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) + if (tipc_bearer_blocked(l_ptr->b_ptr)) return; do { res = tipc_link_push_packet(l_ptr); } while (!res); - - if (res == PUSH_FAILED) - tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); } static void link_reset_all(unsigned long addr) @@ -1454,9 +1471,8 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, tipc_addr_string_fill(addr_string, n_ptr->addr); pr_info("Broadcast link info for %s\n", addr_string); - pr_info("Supportable: %d, Supported: %d, Acked: %u\n", - n_ptr->bclink.supportable, - n_ptr->bclink.supported, + pr_info("Reception permitted: %d, Acked: %u\n", + n_ptr->bclink.recv_permitted, n_ptr->bclink.acked); pr_info("Last in: %u, Oos state: %u, Last sent: %u\n", n_ptr->bclink.last_in, @@ -1481,7 +1497,7 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf, msg = buf_msg(buf); - if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) { + if (tipc_bearer_blocked(l_ptr->b_ptr)) { if (l_ptr->retransm_queue_size == 0) { l_ptr->retransm_queue_head = msg_seqno(msg); l_ptr->retransm_queue_size = retransmits; @@ -1491,7 +1507,7 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf, } return; } else { - /* Detect repeated retransmit failures on uncongested bearer */ + /* Detect repeated retransmit failures on unblocked bearer */ if (l_ptr->last_retransmitted == msg_seqno(msg)) { if (++l_ptr->stale_count > 100) { link_retransmit_failure(l_ptr, buf); @@ -1507,17 +1523,10 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf, msg = buf_msg(buf); msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { - buf = buf->next; - retransmits--; - l_ptr->stats.retransmitted++; - } else { - tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); - l_ptr->stats.bearer_congs++; - l_ptr->retransm_queue_head = buf_seqno(buf); - l_ptr->retransm_queue_size = retransmits; - return; - } + tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); + buf = buf->next; + retransmits--; + l_ptr->stats.retransmitted++; } l_ptr->retransm_queue_head = l_ptr->retransm_queue_size = 0; @@ -1676,7 +1685,7 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) ackd = msg_ack(msg); /* Release acked messages */ - if (n_ptr->bclink.supported) + if (n_ptr->bclink.recv_permitted) tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); crs = l_ptr->first_out; @@ -1727,9 +1736,14 @@ deliver: tipc_link_recv_bundle(buf); continue; case NAME_DISTRIBUTOR: + n_ptr->bclink.recv_permitted = true; tipc_node_unlock(n_ptr); tipc_named_recv(buf); continue; + case BCAST_PROTOCOL: + tipc_link_recv_sync(n_ptr, buf); + tipc_node_unlock(n_ptr); + continue; case CONN_MANAGER: tipc_node_unlock(n_ptr); tipc_port_recv_proto_msg(buf); @@ -1772,16 +1786,19 @@ deliver: continue; } + /* Link is not in state WORKING_WORKING */ if (msg_user(msg) == LINK_PROTOCOL) { link_recv_proto_msg(l_ptr, buf); head = link_insert_deferred_queue(l_ptr, head); tipc_node_unlock(n_ptr); continue; } + + /* Traffic message. Conditionally activate link */ link_state_event(l_ptr, TRAFFIC_MSG_EVT); if (link_working_working(l_ptr)) { - /* Re-insert in front of queue */ + /* Re-insert buffer in front of queue */ buf->next = head; head = buf; tipc_node_unlock(n_ptr); @@ -1972,21 +1989,13 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); - /* Defer message if bearer is already congested */ - if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) { - l_ptr->proto_msg_queue = buf; - return; - } - - /* Defer message if attempting to send results in bearer congestion */ - if (!tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { - tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); + /* Defer message if bearer is already blocked */ + if (tipc_bearer_blocked(l_ptr->b_ptr)) { l_ptr->proto_msg_queue = buf; - l_ptr->stats.bearer_congs++; return; } - /* Discard message if it was sent successfully */ + tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); l_ptr->unacked_window = 0; kfree_skb(buf); } @@ -2057,7 +2066,6 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) } else { l_ptr->max_pkt = l_ptr->max_pkt_target; } - l_ptr->owner->bclink.supportable = (max_pkt_info != 0); /* Synchronize broadcast link info, if not done previously */ if (!tipc_node_is_up(l_ptr->owner)) { @@ -2112,7 +2120,7 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) } /* Protocol message before retransmits, reduce loss risk */ - if (l_ptr->owner->bclink.supported) + if (l_ptr->owner->bclink.recv_permitted) tipc_bclink_update_link_state(l_ptr->owner, msg_last_bcast(msg)); @@ -2487,16 +2495,6 @@ static void set_expected_frags(struct sk_buff *buf, u32 exp) msg_set_bcast_ack(buf_msg(buf), exp); } -static u32 get_timer_cnt(struct sk_buff *buf) -{ - return msg_reroute_cnt(buf_msg(buf)); -} - -static void incr_timer_cnt(struct sk_buff *buf) -{ - msg_incr_reroute_cnt(buf_msg(buf)); -} - /* * tipc_link_recv_fragment(): Called with node lock on. Returns * the reassembled buffer if message is complete. @@ -2575,38 +2573,6 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, return 0; } -/** - * link_check_defragm_bufs - flush stale incoming message fragments - * @l_ptr: pointer to link - */ -static void link_check_defragm_bufs(struct tipc_link *l_ptr) -{ - struct sk_buff *prev = NULL; - struct sk_buff *next = NULL; - struct sk_buff *buf = l_ptr->defragm_buf; - - if (!buf) - return; - if (!link_working_working(l_ptr)) - return; - while (buf) { - u32 cnt = get_timer_cnt(buf); - - next = buf->next; - if (cnt < 4) { - incr_timer_cnt(buf); - prev = buf; - } else { - if (prev) - prev->next = buf->next; - else - l_ptr->defragm_buf = buf->next; - kfree_skb(buf); - } - buf = next; - } -} - static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance) { if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL)) @@ -2937,8 +2903,8 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) s->sent_nacks, s->sent_acks, s->retransmitted); ret += tipc_snprintf(buf + ret, buf_size - ret, - " Congestion bearer:%u link:%u Send queue" - " max:%u avg:%u\n", s->bearer_congs, s->link_congs, + " Congestion link:%u Send queue" + " max:%u avg:%u\n", s->link_congs, s->max_queue_sz, s->queue_sz_counts ? (s->accu_queue_sz / s->queue_sz_counts) : 0); diff --git a/net/tipc/link.h b/net/tipc/link.h index 6e921121be06..c048ed1cbd76 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -40,9 +40,6 @@ #include "msg.h" #include "node.h" -#define PUSH_FAILED 1 -#define PUSH_FINISHED 2 - /* * Out-of-range value for link sequence numbers */ @@ -82,7 +79,6 @@ struct tipc_stats { u32 recv_fragmented; u32 recv_fragments; u32 link_congs; /* # port sends blocked by congestion */ - u32 bearer_congs; u32 deferred_recv; u32 duplicates; u32 max_queue_sz; /* send queue size high water mark */ diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 55d3928dfd67..e0d08055754e 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -262,7 +262,7 @@ void tipc_named_node_up(unsigned long nodearg) named_distribute(&message_list, node, &publ_zone, max_item_buf); read_unlock_bh(&tipc_nametbl_lock); - tipc_link_send_names(&message_list, (u32)node); + tipc_link_send_names(&message_list, node); } /** diff --git a/net/tipc/node.c b/net/tipc/node.c index d21db204e25a..48f39dd3eae8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1,7 +1,7 @@ /* * net/tipc/node.c: TIPC node management routines * - * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2000-2006, 2012 Ericsson AB * Copyright (c) 2005-2006, 2010-2011, Wind River Systems * All rights reserved. * @@ -263,12 +263,9 @@ void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) static void node_established_contact(struct tipc_node *n_ptr) { tipc_k_signal((Handler)tipc_named_node_up, n_ptr->addr); - - if (n_ptr->bclink.supportable) { - n_ptr->bclink.acked = tipc_bclink_get_last_sent(); - tipc_bclink_add_node(n_ptr->addr); - n_ptr->bclink.supported = 1; - } + n_ptr->bclink.oos_state = 0; + n_ptr->bclink.acked = tipc_bclink_get_last_sent(); + tipc_bclink_add_node(n_ptr->addr); } static void node_name_purge_complete(unsigned long node_addr) @@ -294,7 +291,7 @@ static void node_lost_contact(struct tipc_node *n_ptr) tipc_addr_string_fill(addr_string, n_ptr->addr)); /* Flush broadcast link info associated with lost node */ - if (n_ptr->bclink.supported) { + if (n_ptr->bclink.recv_permitted) { while (n_ptr->bclink.deferred_head) { struct sk_buff *buf = n_ptr->bclink.deferred_head; n_ptr->bclink.deferred_head = buf->next; @@ -310,7 +307,7 @@ static void node_lost_contact(struct tipc_node *n_ptr) tipc_bclink_remove_node(n_ptr->addr); tipc_bclink_acknowledge(n_ptr, INVALID_LINK_SEQ); - n_ptr->bclink.supported = 0; + n_ptr->bclink.recv_permitted = false; } /* Abort link changeover */ diff --git a/net/tipc/node.h b/net/tipc/node.h index cfcaf4d6e480..3c189b35b102 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -67,8 +67,6 @@ * @permit_changeover: non-zero if node has redundant links to this system * @signature: node instance identifier * @bclink: broadcast-related info - * @supportable: non-zero if node supports TIPC b'cast link capability - * @supported: non-zero if node supports TIPC b'cast capability * @acked: sequence # of last outbound b'cast message acknowledged by node * @last_in: sequence # of last in-sequence b'cast message received from node * @last_sent: sequence # of last b'cast message sent by node @@ -77,6 +75,7 @@ * @deferred_head: oldest OOS b'cast message received from node * @deferred_tail: newest OOS b'cast message received from node * @defragm: list of partially reassembled b'cast message fragments from node + * @recv_permitted: true if node is allowed to receive b'cast messages */ struct tipc_node { u32 addr; @@ -92,8 +91,6 @@ struct tipc_node { int permit_changeover; u32 signature; struct { - u8 supportable; - u8 supported; u32 acked; u32 last_in; u32 last_sent; @@ -102,6 +99,7 @@ struct tipc_node { struct sk_buff *deferred_head; struct sk_buff *deferred_tail; struct sk_buff *defragm; + bool recv_permitted; } bclink; }; diff --git a/net/tipc/port.c b/net/tipc/port.c index 07c42fba672b..18098cac62f2 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -726,7 +726,7 @@ static void port_dispatcher_sigh(void *dummy) if (unlikely(!cb)) goto reject; if (unlikely(!connected)) { - if (tipc_connect2port(dref, &orig)) + if (tipc_connect(dref, &orig)) goto reject; } else if (peer_invalid) goto reject; @@ -1036,15 +1036,30 @@ int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) return res; } -int tipc_connect2port(u32 ref, struct tipc_portid const *peer) +int tipc_connect(u32 ref, struct tipc_portid const *peer) { struct tipc_port *p_ptr; - struct tipc_msg *msg; - int res = -EINVAL; + int res; p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; + res = __tipc_connect(ref, p_ptr, peer); + tipc_port_unlock(p_ptr); + return res; +} + +/* + * __tipc_connect - connect to a remote peer + * + * Port must be locked. + */ +int __tipc_connect(u32 ref, struct tipc_port *p_ptr, + struct tipc_portid const *peer) +{ + struct tipc_msg *msg; + int res = -EINVAL; + if (p_ptr->published || p_ptr->connected) goto exit; if (!peer->ref) @@ -1067,17 +1082,16 @@ int tipc_connect2port(u32 ref, struct tipc_portid const *peer) (net_ev_handler)port_handle_node_down); res = 0; exit: - tipc_port_unlock(p_ptr); p_ptr->max_pkt = tipc_link_get_max_pkt(peer->node, ref); return res; } -/** - * tipc_disconnect_port - disconnect port from peer +/* + * __tipc_disconnect - disconnect port from peer * * Port must be locked. */ -int tipc_disconnect_port(struct tipc_port *tp_ptr) +int __tipc_disconnect(struct tipc_port *tp_ptr) { int res; @@ -1104,7 +1118,7 @@ int tipc_disconnect(u32 ref) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - res = tipc_disconnect_port(p_ptr); + res = __tipc_disconnect(p_ptr); tipc_port_unlock(p_ptr); return res; } diff --git a/net/tipc/port.h b/net/tipc/port.h index 4660e3065790..fb66e2e5f4d1 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -190,7 +190,7 @@ int tipc_publish(u32 portref, unsigned int scope, int tipc_withdraw(u32 portref, unsigned int scope, struct tipc_name_seq const *name_seq); -int tipc_connect2port(u32 portref, struct tipc_portid const *port); +int tipc_connect(u32 portref, struct tipc_portid const *port); int tipc_disconnect(u32 portref); @@ -200,7 +200,9 @@ int tipc_shutdown(u32 ref); /* * The following routines require that the port be locked on entry */ -int tipc_disconnect_port(struct tipc_port *tp_ptr); +int __tipc_disconnect(struct tipc_port *tp_ptr); +int __tipc_connect(u32 ref, struct tipc_port *p_ptr, + struct tipc_portid const *peer); int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg); /* diff --git a/net/tipc/socket.c b/net/tipc/socket.c index fd5f042dbff4..9b4e4833a484 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,8 +1,8 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, Ericsson AB - * Copyright (c) 2004-2008, 2010-2011, Wind River Systems + * Copyright (c) 2001-2007, 2012 Ericsson AB + * Copyright (c) 2004-2008, 2010-2012, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -43,7 +43,7 @@ #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ -#define OVERLOAD_LIMIT_BASE 5000 +#define OVERLOAD_LIMIT_BASE 10000 #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ struct tipc_sock { @@ -62,6 +62,8 @@ struct tipc_sock { static int backlog_rcv(struct sock *sk, struct sk_buff *skb); static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf); static void wakeupdispatch(struct tipc_port *tport); +static void tipc_data_ready(struct sock *sk, int len); +static void tipc_write_space(struct sock *sk); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -71,8 +73,6 @@ static struct proto tipc_proto; static int sockets_enabled; -static atomic_t tipc_queue_size = ATOMIC_INIT(0); - /* * Revised TIPC socket locking policy: * @@ -126,7 +126,6 @@ static atomic_t tipc_queue_size = ATOMIC_INIT(0); static void advance_rx_queue(struct sock *sk) { kfree_skb(__skb_dequeue(&sk->sk_receive_queue)); - atomic_dec(&tipc_queue_size); } /** @@ -138,10 +137,8 @@ static void discard_rx_queue(struct sock *sk) { struct sk_buff *buf; - while ((buf = __skb_dequeue(&sk->sk_receive_queue))) { - atomic_dec(&tipc_queue_size); + while ((buf = __skb_dequeue(&sk->sk_receive_queue))) kfree_skb(buf); - } } /** @@ -153,10 +150,8 @@ static void reject_rx_queue(struct sock *sk) { struct sk_buff *buf; - while ((buf = __skb_dequeue(&sk->sk_receive_queue))) { + while ((buf = __skb_dequeue(&sk->sk_receive_queue))) tipc_reject_msg(buf, TIPC_ERR_NO_PORT); - atomic_dec(&tipc_queue_size); - } } /** @@ -221,6 +216,8 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, sock_init_data(sock, sk); sk->sk_backlog_rcv = backlog_rcv; sk->sk_rcvbuf = TIPC_FLOW_CONTROL_WIN * 2 * TIPC_MAX_USER_MSG_SIZE * 2; + sk->sk_data_ready = tipc_data_ready; + sk->sk_write_space = tipc_write_space; tipc_sk(sk)->p = tp_ptr; tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT; @@ -276,7 +273,6 @@ static int release(struct socket *sock) buf = __skb_dequeue(&sk->sk_receive_queue); if (buf == NULL) break; - atomic_dec(&tipc_queue_size); if (TIPC_SKB_CB(buf)->handle != 0) kfree_skb(buf); else { @@ -408,7 +404,7 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, * socket state flags set * ------------ --------- * unconnected no read flags - * no write flags + * POLLOUT if port is not congested * * connecting POLLIN/POLLRDNORM if ACK/NACK in rx queue * no write flags @@ -435,9 +431,13 @@ static unsigned int poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; u32 mask = 0; - poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, sk_sleep(sk), wait); switch ((int)sock->state) { + case SS_UNCONNECTED: + if (!tipc_sk_port(sk)->congested) + mask |= POLLOUT; + break; case SS_READY: case SS_CONNECTED: if (!tipc_sk_port(sk)->congested) @@ -775,16 +775,19 @@ exit: static int auto_connect(struct socket *sock, struct tipc_msg *msg) { struct tipc_sock *tsock = tipc_sk(sock->sk); - - if (msg_errcode(msg)) { - sock->state = SS_DISCONNECTING; - return -ECONNREFUSED; - } + struct tipc_port *p_ptr; tsock->peer_name.ref = msg_origport(msg); tsock->peer_name.node = msg_orignode(msg); - tipc_connect2port(tsock->p->ref, &tsock->peer_name); - tipc_set_portimportance(tsock->p->ref, msg_importance(msg)); + p_ptr = tipc_port_deref(tsock->p->ref); + if (!p_ptr) + return -EINVAL; + + __tipc_connect(tsock->p->ref, p_ptr, &tsock->peer_name); + + if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE) + return -EINVAL; + msg_set_importance(&p_ptr->phdr, (u32)msg_importance(msg)); sock->state = SS_CONNECTED; return 0; } @@ -943,13 +946,6 @@ restart: sz = msg_data_sz(msg); err = msg_errcode(msg); - /* Complete connection setup for an implied connect */ - if (unlikely(sock->state == SS_CONNECTING)) { - res = auto_connect(sock, msg); - if (res) - goto exit; - } - /* Discard an empty non-errored message & try again */ if ((!sz) && (!err)) { advance_rx_queue(sk); @@ -1126,6 +1122,39 @@ exit: } /** + * tipc_write_space - wake up thread if port congestion is released + * @sk: socket + */ +static void tipc_write_space(struct sock *sk) +{ + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | + POLLWRNORM | POLLWRBAND); + rcu_read_unlock(); +} + +/** + * tipc_data_ready - wake up threads to indicate messages have been received + * @sk: socket + * @len: the length of messages + */ +static void tipc_data_ready(struct sock *sk, int len) +{ + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | + POLLRDNORM | POLLRDBAND); + rcu_read_unlock(); +} + +/** * rx_queue_full - determine if receive queue can accept another message * @msg: message to be added to queue * @queue_size: current size of queue @@ -1154,6 +1183,83 @@ static int rx_queue_full(struct tipc_msg *msg, u32 queue_size, u32 base) } /** + * filter_connect - Handle all incoming messages for a connection-based socket + * @tsock: TIPC socket + * @msg: message + * + * Returns TIPC error status code and socket error status code + * once it encounters some errors + */ +static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) +{ + struct socket *sock = tsock->sk.sk_socket; + struct tipc_msg *msg = buf_msg(*buf); + struct sock *sk = &tsock->sk; + u32 retval = TIPC_ERR_NO_PORT; + int res; + + if (msg_mcast(msg)) + return retval; + + switch ((int)sock->state) { + case SS_CONNECTED: + /* Accept only connection-based messages sent by peer */ + if (msg_connected(msg) && tipc_port_peer_msg(tsock->p, msg)) { + if (unlikely(msg_errcode(msg))) { + sock->state = SS_DISCONNECTING; + __tipc_disconnect(tsock->p); + } + retval = TIPC_OK; + } + break; + case SS_CONNECTING: + /* Accept only ACK or NACK message */ + if (unlikely(msg_errcode(msg))) { + sock->state = SS_DISCONNECTING; + sk->sk_err = -ECONNREFUSED; + retval = TIPC_OK; + break; + } + + if (unlikely(!msg_connected(msg))) + break; + + res = auto_connect(sock, msg); + if (res) { + sock->state = SS_DISCONNECTING; + sk->sk_err = res; + retval = TIPC_OK; + break; + } + + /* If an incoming message is an 'ACK-', it should be + * discarded here because it doesn't contain useful + * data. In addition, we should try to wake up + * connect() routine if sleeping. + */ + if (msg_data_sz(msg) == 0) { + kfree_skb(*buf); + *buf = NULL; + if (waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); + } + retval = TIPC_OK; + break; + case SS_LISTENING: + case SS_UNCONNECTED: + /* Accept only SYN message */ + if (!msg_connected(msg) && !(msg_errcode(msg))) + retval = TIPC_OK; + break; + case SS_DISCONNECTING: + break; + default: + pr_err("Unknown socket state %u\n", sock->state); + } + return retval; +} + +/** * filter_rcv - validate incoming message * @sk: socket * @buf: message @@ -1170,6 +1276,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) struct socket *sock = sk->sk_socket; struct tipc_msg *msg = buf_msg(buf); u32 recv_q_len; + u32 res = TIPC_OK; /* Reject message if it is wrong sort of message for socket */ if (msg_type(msg) > TIPC_DIRECT_MSG) @@ -1179,32 +1286,12 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) if (msg_connected(msg)) return TIPC_ERR_NO_PORT; } else { - if (msg_mcast(msg)) - return TIPC_ERR_NO_PORT; - if (sock->state == SS_CONNECTED) { - if (!msg_connected(msg) || - !tipc_port_peer_msg(tipc_sk_port(sk), msg)) - return TIPC_ERR_NO_PORT; - } else if (sock->state == SS_CONNECTING) { - if (!msg_connected(msg) && (msg_errcode(msg) == 0)) - return TIPC_ERR_NO_PORT; - } else if (sock->state == SS_LISTENING) { - if (msg_connected(msg) || msg_errcode(msg)) - return TIPC_ERR_NO_PORT; - } else if (sock->state == SS_DISCONNECTING) { - return TIPC_ERR_NO_PORT; - } else /* (sock->state == SS_UNCONNECTED) */ { - if (msg_connected(msg) || msg_errcode(msg)) - return TIPC_ERR_NO_PORT; - } + res = filter_connect(tipc_sk(sk), &buf); + if (res != TIPC_OK || buf == NULL) + return res; } /* Reject message if there isn't room to queue it */ - recv_q_len = (u32)atomic_read(&tipc_queue_size); - if (unlikely(recv_q_len >= OVERLOAD_LIMIT_BASE)) { - if (rx_queue_full(msg, recv_q_len, OVERLOAD_LIMIT_BASE)) - return TIPC_ERR_OVERLOAD; - } recv_q_len = skb_queue_len(&sk->sk_receive_queue); if (unlikely(recv_q_len >= (OVERLOAD_LIMIT_BASE / 2))) { if (rx_queue_full(msg, recv_q_len, OVERLOAD_LIMIT_BASE / 2)) @@ -1213,17 +1300,9 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) /* Enqueue message (finally!) */ TIPC_SKB_CB(buf)->handle = 0; - atomic_inc(&tipc_queue_size); __skb_queue_tail(&sk->sk_receive_queue, buf); - /* Initiate connection termination for an incoming 'FIN' */ - if (unlikely(msg_errcode(msg) && (sock->state == SS_CONNECTED))) { - sock->state = SS_DISCONNECTING; - tipc_disconnect_port(tipc_sk_port(sk)); - } - - if (waitqueue_active(sk_sleep(sk))) - wake_up_interruptible(sk_sleep(sk)); + sk->sk_data_ready(sk, 0); return TIPC_OK; } @@ -1290,8 +1369,7 @@ static void wakeupdispatch(struct tipc_port *tport) { struct sock *sk = (struct sock *)tport->usr_handle; - if (waitqueue_active(sk_sleep(sk))) - wake_up_interruptible(sk_sleep(sk)); + sk->sk_write_space(sk); } /** @@ -1309,8 +1387,6 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, struct sock *sk = sock->sk; struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; struct msghdr m = {NULL,}; - struct sk_buff *buf; - struct tipc_msg *msg; unsigned int timeout; int res; @@ -1322,26 +1398,6 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, goto exit; } - /* For now, TIPC does not support the non-blocking form of connect() */ - if (flags & O_NONBLOCK) { - res = -EOPNOTSUPP; - goto exit; - } - - /* Issue Posix-compliant error code if socket is in the wrong state */ - if (sock->state == SS_LISTENING) { - res = -EOPNOTSUPP; - goto exit; - } - if (sock->state == SS_CONNECTING) { - res = -EALREADY; - goto exit; - } - if (sock->state != SS_UNCONNECTED) { - res = -EISCONN; - goto exit; - } - /* * Reject connection attempt using multicast address * @@ -1353,49 +1409,66 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, goto exit; } - /* Reject any messages already in receive queue (very unlikely) */ - reject_rx_queue(sk); + timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout; - /* Send a 'SYN-' to destination */ - m.msg_name = dest; - m.msg_namelen = destlen; - res = send_msg(NULL, sock, &m, 0); - if (res < 0) + switch (sock->state) { + case SS_UNCONNECTED: + /* Send a 'SYN-' to destination */ + m.msg_name = dest; + m.msg_namelen = destlen; + + /* If connect is in non-blocking case, set MSG_DONTWAIT to + * indicate send_msg() is never blocked. + */ + if (!timeout) + m.msg_flags = MSG_DONTWAIT; + + res = send_msg(NULL, sock, &m, 0); + if ((res < 0) && (res != -EWOULDBLOCK)) + goto exit; + + /* Just entered SS_CONNECTING state; the only + * difference is that return value in non-blocking + * case is EINPROGRESS, rather than EALREADY. + */ + res = -EINPROGRESS; + break; + case SS_CONNECTING: + res = -EALREADY; + break; + case SS_CONNECTED: + res = -EISCONN; + break; + default: + res = -EINVAL; goto exit; + } - /* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */ - timeout = tipc_sk(sk)->conn_timeout; - release_sock(sk); - res = wait_event_interruptible_timeout(*sk_sleep(sk), - (!skb_queue_empty(&sk->sk_receive_queue) || - (sock->state != SS_CONNECTING)), - timeout ? (long)msecs_to_jiffies(timeout) - : MAX_SCHEDULE_TIMEOUT); - lock_sock(sk); + if (sock->state == SS_CONNECTING) { + if (!timeout) + goto exit; - if (res > 0) { - buf = skb_peek(&sk->sk_receive_queue); - if (buf != NULL) { - msg = buf_msg(buf); - res = auto_connect(sock, msg); - if (!res) { - if (!msg_data_sz(msg)) - advance_rx_queue(sk); - } - } else { - if (sock->state == SS_CONNECTED) - res = -EISCONN; + /* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */ + release_sock(sk); + res = wait_event_interruptible_timeout(*sk_sleep(sk), + sock->state != SS_CONNECTING, + timeout ? (long)msecs_to_jiffies(timeout) + : MAX_SCHEDULE_TIMEOUT); + lock_sock(sk); + if (res <= 0) { + if (res == 0) + res = -ETIMEDOUT; else - res = -ECONNREFUSED; + ; /* leave "res" unchanged */ + goto exit; } - } else { - if (res == 0) - res = -ETIMEDOUT; - else - ; /* leave "res" unchanged */ - sock->state = SS_DISCONNECTING; } + if (unlikely(sock->state == SS_DISCONNECTING)) + res = sock_error(sk); + else + res = 0; + exit: release_sock(sk); return res; @@ -1436,8 +1509,13 @@ static int listen(struct socket *sock, int len) */ static int accept(struct socket *sock, struct socket *new_sock, int flags) { - struct sock *sk = sock->sk; + struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; + struct tipc_sock *new_tsock; + struct tipc_port *new_tport; + struct tipc_msg *msg; + u32 new_ref; + int res; lock_sock(sk); @@ -1463,48 +1541,51 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) buf = skb_peek(&sk->sk_receive_queue); res = tipc_create(sock_net(sock->sk), new_sock, 0, 0); - if (!res) { - struct sock *new_sk = new_sock->sk; - struct tipc_sock *new_tsock = tipc_sk(new_sk); - struct tipc_port *new_tport = new_tsock->p; - u32 new_ref = new_tport->ref; - struct tipc_msg *msg = buf_msg(buf); - - lock_sock(new_sk); - - /* - * Reject any stray messages received by new socket - * before the socket lock was taken (very, very unlikely) - */ - reject_rx_queue(new_sk); - - /* Connect new socket to it's peer */ - new_tsock->peer_name.ref = msg_origport(msg); - new_tsock->peer_name.node = msg_orignode(msg); - tipc_connect2port(new_ref, &new_tsock->peer_name); - new_sock->state = SS_CONNECTED; - - tipc_set_portimportance(new_ref, msg_importance(msg)); - if (msg_named(msg)) { - new_tport->conn_type = msg_nametype(msg); - new_tport->conn_instance = msg_nameinst(msg); - } + if (res) + goto exit; - /* - * Respond to 'SYN-' by discarding it & returning 'ACK'-. - * Respond to 'SYN+' by queuing it on new socket. - */ - if (!msg_data_sz(msg)) { - struct msghdr m = {NULL,}; + new_sk = new_sock->sk; + new_tsock = tipc_sk(new_sk); + new_tport = new_tsock->p; + new_ref = new_tport->ref; + msg = buf_msg(buf); - advance_rx_queue(sk); - send_packet(NULL, new_sock, &m, 0); - } else { - __skb_dequeue(&sk->sk_receive_queue); - __skb_queue_head(&new_sk->sk_receive_queue, buf); - } - release_sock(new_sk); + /* we lock on new_sk; but lockdep sees the lock on sk */ + lock_sock_nested(new_sk, SINGLE_DEPTH_NESTING); + + /* + * Reject any stray messages received by new socket + * before the socket lock was taken (very, very unlikely) + */ + reject_rx_queue(new_sk); + + /* Connect new socket to it's peer */ + new_tsock->peer_name.ref = msg_origport(msg); + new_tsock->peer_name.node = msg_orignode(msg); + tipc_connect(new_ref, &new_tsock->peer_name); + new_sock->state = SS_CONNECTED; + + tipc_set_portimportance(new_ref, msg_importance(msg)); + if (msg_named(msg)) { + new_tport->conn_type = msg_nametype(msg); + new_tport->conn_instance = msg_nameinst(msg); } + + /* + * Respond to 'SYN-' by discarding it & returning 'ACK'-. + * Respond to 'SYN+' by queuing it on new socket. + */ + if (!msg_data_sz(msg)) { + struct msghdr m = {NULL,}; + + advance_rx_queue(sk); + send_packet(NULL, new_sock, &m, 0); + } else { + __skb_dequeue(&sk->sk_receive_queue); + __skb_queue_head(&new_sk->sk_receive_queue, buf); + } + release_sock(new_sk); + exit: release_sock(sk); return res; @@ -1539,7 +1620,6 @@ restart: /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */ buf = __skb_dequeue(&sk->sk_receive_queue); if (buf) { - atomic_dec(&tipc_queue_size); if (TIPC_SKB_CB(buf)->handle != 0) { kfree_skb(buf); goto restart; @@ -1556,10 +1636,11 @@ restart: case SS_DISCONNECTING: - /* Discard any unreceived messages; wake up sleeping tasks */ + /* Discard any unreceived messages */ discard_rx_queue(sk); - if (waitqueue_active(sk_sleep(sk))) - wake_up_interruptible(sk_sleep(sk)); + + /* Wake up anyone sleeping in poll */ + sk->sk_state_change(sk); res = 0; break; @@ -1677,7 +1758,7 @@ static int getsockopt(struct socket *sock, /* no need to set "res", since already 0 at this point */ break; case TIPC_NODE_RECVQ_DEPTH: - value = (u32)atomic_read(&tipc_queue_size); + value = 0; /* was tipc_queue_size, now obsolete */ break; case TIPC_SOCK_RECVQ_DEPTH: value = skb_queue_len(&sk->sk_receive_queue); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 0f7d0d007e22..6b42d47029af 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -462,7 +462,7 @@ static void subscr_named_msg_event(void *usr_handle, kfree(subscriber); return; } - tipc_connect2port(subscriber->port_ref, orig); + tipc_connect(subscriber->port_ref, orig); /* Lock server port (& save lock address for future use) */ subscriber->lock = tipc_port_lock(subscriber->port_ref)->lock; diff --git a/net/unix/diag.c b/net/unix/diag.c index 06748f108a57..5ac19dc1d5e4 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -151,6 +151,9 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO)) goto out_nlmsg_trim; + if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown)) + goto out_nlmsg_trim; + return nlmsg_end(skb, nlh); out_nlmsg_trim: diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c index b34b5b9792f0..8800604c93f4 100644 --- a/net/unix/sysctl_net_unix.c +++ b/net/unix/sysctl_net_unix.c @@ -34,6 +34,10 @@ int __net_init unix_sysctl_register(struct net *net) if (table == NULL) goto err_alloc; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + table[0].data = &net->unx.sysctl_max_dgram_qlen; net->unx.ctl = register_net_sysctl(net, "net/unix", table); if (net->unx.ctl == NULL) diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index fe4adb12b3ef..16d08b399210 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -140,14 +140,13 @@ config CFG80211_WEXT extensions with cfg80211-based drivers. config LIB80211 - tristate "Common routines for IEEE802.11 drivers" + tristate default n help This options enables a library of common routines used by IEEE802.11 wireless LAN drivers. - Drivers should select this themselves if needed. Say Y if - you want this built into your kernel. + Drivers should select this themselves if needed. config LIB80211_CRYPT_WEP tristate diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 0f7e0d621ab0..a761670af31d 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -10,11 +10,13 @@ obj-$(CONFIG_WEXT_SPY) += wext-spy.o obj-$(CONFIG_WEXT_PRIV) += wext-priv.o cfg80211-y += core.o sysfs.o radiotap.o util.o reg.o scan.o nl80211.o -cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o +cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o +CFLAGS_trace.o := -I$(src) + ccflags-y += -D__CHECK_ENDIAN__ $(obj)/regdb.c: $(src)/db.txt $(src)/genregdb.awk diff --git a/net/wireless/ap.c b/net/wireless/ap.c index fcc60d8dbefa..324e8d851dc4 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -3,6 +3,7 @@ #include <net/cfg80211.h> #include "nl80211.h" #include "core.h" +#include "rdev-ops.h" static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, @@ -23,10 +24,11 @@ static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, if (!wdev->beacon_interval) return -ENOENT; - err = rdev->ops->stop_ap(&rdev->wiphy, dev); + err = rdev_stop_ap(rdev, dev); if (!err) { wdev->beacon_interval = 0; wdev->channel = NULL; + wdev->ssid_len = 0; } return err; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 2f876b9ee344..a7990bb16529 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -9,90 +9,303 @@ #include <linux/export.h> #include <net/cfg80211.h> #include "core.h" +#include "rdev-ops.h" -struct ieee80211_channel * -rdev_freq_to_chan(struct cfg80211_registered_device *rdev, - int freq, enum nl80211_channel_type channel_type) +void cfg80211_chandef_create(struct cfg80211_chan_def *chandef, + struct ieee80211_channel *chan, + enum nl80211_channel_type chan_type) { - struct ieee80211_channel *chan; - struct ieee80211_sta_ht_cap *ht_cap; + if (WARN_ON(!chan)) + return; + + chandef->chan = chan; + chandef->center_freq2 = 0; + + switch (chan_type) { + case NL80211_CHAN_NO_HT: + chandef->width = NL80211_CHAN_WIDTH_20_NOHT; + chandef->center_freq1 = chan->center_freq; + break; + case NL80211_CHAN_HT20: + chandef->width = NL80211_CHAN_WIDTH_20; + chandef->center_freq1 = chan->center_freq; + break; + case NL80211_CHAN_HT40PLUS: + chandef->width = NL80211_CHAN_WIDTH_40; + chandef->center_freq1 = chan->center_freq + 10; + break; + case NL80211_CHAN_HT40MINUS: + chandef->width = NL80211_CHAN_WIDTH_40; + chandef->center_freq1 = chan->center_freq - 10; + break; + default: + WARN_ON(1); + } +} +EXPORT_SYMBOL(cfg80211_chandef_create); + +bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) +{ + u32 control_freq; + + if (!chandef->chan) + return false; - chan = ieee80211_get_channel(&rdev->wiphy, freq); + control_freq = chandef->chan->center_freq; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_20_NOHT: + if (chandef->center_freq1 != control_freq) + return false; + if (chandef->center_freq2) + return false; + break; + case NL80211_CHAN_WIDTH_40: + if (chandef->center_freq1 != control_freq + 10 && + chandef->center_freq1 != control_freq - 10) + return false; + if (chandef->center_freq2) + return false; + break; + case NL80211_CHAN_WIDTH_80P80: + if (chandef->center_freq1 != control_freq + 30 && + chandef->center_freq1 != control_freq + 10 && + chandef->center_freq1 != control_freq - 10 && + chandef->center_freq1 != control_freq - 30) + return false; + if (!chandef->center_freq2) + return false; + break; + case NL80211_CHAN_WIDTH_80: + if (chandef->center_freq1 != control_freq + 30 && + chandef->center_freq1 != control_freq + 10 && + chandef->center_freq1 != control_freq - 10 && + chandef->center_freq1 != control_freq - 30) + return false; + if (chandef->center_freq2) + return false; + break; + case NL80211_CHAN_WIDTH_160: + if (chandef->center_freq1 != control_freq + 70 && + chandef->center_freq1 != control_freq + 50 && + chandef->center_freq1 != control_freq + 30 && + chandef->center_freq1 != control_freq + 10 && + chandef->center_freq1 != control_freq - 10 && + chandef->center_freq1 != control_freq - 30 && + chandef->center_freq1 != control_freq - 50 && + chandef->center_freq1 != control_freq - 70) + return false; + if (chandef->center_freq2) + return false; + break; + default: + return false; + } + + return true; +} +EXPORT_SYMBOL(cfg80211_chandef_valid); + +static void chandef_primary_freqs(const struct cfg80211_chan_def *c, + int *pri40, int *pri80) +{ + int tmp; + + switch (c->width) { + case NL80211_CHAN_WIDTH_40: + *pri40 = c->center_freq1; + *pri80 = 0; + break; + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + *pri80 = c->center_freq1; + /* n_P20 */ + tmp = (30 + c->chan->center_freq - c->center_freq1)/20; + /* n_P40 */ + tmp /= 2; + /* freq_P40 */ + *pri40 = c->center_freq1 - 20 + 40 * tmp; + break; + case NL80211_CHAN_WIDTH_160: + /* n_P20 */ + tmp = (70 + c->chan->center_freq - c->center_freq1)/20; + /* n_P40 */ + tmp /= 2; + /* freq_P40 */ + *pri40 = c->center_freq1 - 60 + 40 * tmp; + /* n_P80 */ + tmp /= 2; + *pri80 = c->center_freq1 - 40 + 80 * tmp; + break; + default: + WARN_ON_ONCE(1); + } +} - /* Primary channel not allowed */ - if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) +const struct cfg80211_chan_def * +cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, + const struct cfg80211_chan_def *c2) +{ + u32 c1_pri40, c1_pri80, c2_pri40, c2_pri80; + + /* If they are identical, return */ + if (cfg80211_chandef_identical(c1, c2)) + return c1; + + /* otherwise, must have same control channel */ + if (c1->chan != c2->chan) return NULL; - if (channel_type == NL80211_CHAN_HT40MINUS && - chan->flags & IEEE80211_CHAN_NO_HT40MINUS) + /* + * If they have the same width, but aren't identical, + * then they can't be compatible. + */ + if (c1->width == c2->width) return NULL; - else if (channel_type == NL80211_CHAN_HT40PLUS && - chan->flags & IEEE80211_CHAN_NO_HT40PLUS) + + if (c1->width == NL80211_CHAN_WIDTH_20_NOHT || + c1->width == NL80211_CHAN_WIDTH_20) + return c2; + + if (c2->width == NL80211_CHAN_WIDTH_20_NOHT || + c2->width == NL80211_CHAN_WIDTH_20) + return c1; + + chandef_primary_freqs(c1, &c1_pri40, &c1_pri80); + chandef_primary_freqs(c2, &c2_pri40, &c2_pri80); + + if (c1_pri40 != c2_pri40) return NULL; - ht_cap = &rdev->wiphy.bands[chan->band]->ht_cap; + WARN_ON(!c1_pri80 && !c2_pri80); + if (c1_pri80 && c2_pri80 && c1_pri80 != c2_pri80) + return NULL; - if (channel_type != NL80211_CHAN_NO_HT) { - if (!ht_cap->ht_supported) - return NULL; + if (c1->width > c2->width) + return c1; + return c2; +} +EXPORT_SYMBOL(cfg80211_chandef_compatible); - if (channel_type != NL80211_CHAN_HT20 && - (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) || - ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT)) - return NULL; +static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, + u32 center_freq, u32 bandwidth, + u32 prohibited_flags) +{ + struct ieee80211_channel *c; + u32 freq; + + for (freq = center_freq - bandwidth/2 + 10; + freq <= center_freq + bandwidth/2 - 10; + freq += 20) { + c = ieee80211_get_channel(wiphy, freq); + if (!c || c->flags & prohibited_flags) + return false; } - return chan; + return true; } -bool cfg80211_can_beacon_sec_chan(struct wiphy *wiphy, - struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type) +bool cfg80211_chandef_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags) { - struct ieee80211_channel *sec_chan; - int diff; + struct ieee80211_sta_ht_cap *ht_cap; + struct ieee80211_sta_vht_cap *vht_cap; + u32 width, control_freq; - switch (channel_type) { - case NL80211_CHAN_HT40PLUS: - diff = 20; + if (WARN_ON(!cfg80211_chandef_valid(chandef))) + return false; + + ht_cap = &wiphy->bands[chandef->chan->band]->ht_cap; + vht_cap = &wiphy->bands[chandef->chan->band]->vht_cap; + + control_freq = chandef->chan->center_freq; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_20: + if (!ht_cap->ht_supported) + return false; + case NL80211_CHAN_WIDTH_20_NOHT: + width = 20; break; - case NL80211_CHAN_HT40MINUS: - diff = -20; + case NL80211_CHAN_WIDTH_40: + width = 40; + if (!ht_cap->ht_supported) + return false; + if (!(ht_cap->cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) || + ht_cap->cap & IEEE80211_HT_CAP_40MHZ_INTOLERANT) + return false; + if (chandef->center_freq1 < control_freq && + chandef->chan->flags & IEEE80211_CHAN_NO_HT40MINUS) + return false; + if (chandef->center_freq1 > control_freq && + chandef->chan->flags & IEEE80211_CHAN_NO_HT40PLUS) + return false; + break; + case NL80211_CHAN_WIDTH_80P80: + if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)) + return false; + case NL80211_CHAN_WIDTH_80: + if (!vht_cap->vht_supported) + return false; + width = 80; + break; + case NL80211_CHAN_WIDTH_160: + if (!vht_cap->vht_supported) + return false; + if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ)) + return false; + width = 160; break; default: - return true; + WARN_ON_ONCE(1); + return false; } - sec_chan = ieee80211_get_channel(wiphy, chan->center_freq + diff); - if (!sec_chan) - return false; + /* TODO: missing regulatory check on 80/160 bandwidth */ - /* we'll need a DFS capability later */ - if (sec_chan->flags & (IEEE80211_CHAN_DISABLED | - IEEE80211_CHAN_PASSIVE_SCAN | - IEEE80211_CHAN_NO_IBSS | - IEEE80211_CHAN_RADAR)) + if (width > 20) + prohibited_flags |= IEEE80211_CHAN_NO_OFDM; + + if (!cfg80211_secondary_chans_ok(wiphy, chandef->center_freq1, + width, prohibited_flags)) return false; - return true; + if (!chandef->center_freq2) + return true; + return cfg80211_secondary_chans_ok(wiphy, chandef->center_freq2, + width, prohibited_flags); } -EXPORT_SYMBOL(cfg80211_can_beacon_sec_chan); +EXPORT_SYMBOL(cfg80211_chandef_usable); -int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, - int freq, enum nl80211_channel_type chantype) +bool cfg80211_reg_can_beacon(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef) { - struct ieee80211_channel *chan; + bool res; + + trace_cfg80211_reg_can_beacon(wiphy, chandef); + res = cfg80211_chandef_usable(wiphy, chandef, + IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_PASSIVE_SCAN | + IEEE80211_CHAN_NO_IBSS | + IEEE80211_CHAN_RADAR); + + trace_cfg80211_return_bool(res); + return res; +} +EXPORT_SYMBOL(cfg80211_reg_can_beacon); + +int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, + struct cfg80211_chan_def *chandef) +{ if (!rdev->ops->set_monitor_channel) return -EOPNOTSUPP; if (!cfg80211_has_monitors_only(rdev)) return -EBUSY; - chan = rdev_freq_to_chan(rdev, freq, chantype); - if (!chan) - return -EINVAL; - - return rdev->ops->set_monitor_channel(&rdev->wiphy, chan, chantype); + return rdev_set_monitor_channel(rdev, chandef); } void diff --git a/net/wireless/core.c b/net/wireless/core.c index 443d4d7deea2..b677eab55b68 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -26,6 +26,7 @@ #include "debugfs.h" #include "wext-compat.h" #include "ethtool.h" +#include "rdev-ops.h" /* name for sysfs, %d is appended */ #define PHY_NAME "phy" @@ -216,7 +217,7 @@ static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data) { struct cfg80211_registered_device *rdev = data; - rdev->ops->rfkill_poll(&rdev->wiphy); + rdev_rfkill_poll(rdev); } static int cfg80211_rfkill_set_block(void *data, bool blocked) @@ -240,7 +241,7 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked) case NL80211_IFTYPE_P2P_DEVICE: if (!wdev->p2p_started) break; - rdev->ops->stop_p2p_device(&rdev->wiphy, wdev); + rdev_stop_p2p_device(rdev, wdev); wdev->p2p_started = false; rdev->opencount--; break; @@ -325,6 +326,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) mutex_init(&rdev->devlist_mtx); mutex_init(&rdev->sched_scan_mtx); INIT_LIST_HEAD(&rdev->wdev_list); + INIT_LIST_HEAD(&rdev->beacon_registrations); + spin_lock_init(&rdev->beacon_registrations_lock); spin_lock_init(&rdev->bss_lock); INIT_LIST_HEAD(&rdev->bss_list); INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done); @@ -370,6 +373,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) rdev->wiphy.rts_threshold = (u32) -1; rdev->wiphy.coverage_class = 0; + rdev->wiphy.features = NL80211_FEATURE_SCAN_FLUSH; + return &rdev->wiphy; } EXPORT_SYMBOL(wiphy_new); @@ -526,8 +531,7 @@ int wiphy_register(struct wiphy *wiphy) for (i = 0; i < sband->n_channels; i++) { sband->channels[i].orig_flags = sband->channels[i].flags; - sband->channels[i].orig_mag = - sband->channels[i].max_antenna_gain; + sband->channels[i].orig_mag = INT_MAX; sband->channels[i].orig_mpwr = sband->channels[i].max_power; sband->channels[i].band = band; @@ -688,7 +692,7 @@ void wiphy_unregister(struct wiphy *wiphy) flush_work(&rdev->event_work); if (rdev->wowlan && rdev->ops->set_wakeup) - rdev->ops->set_wakeup(&rdev->wiphy, false); + rdev_set_wakeup(rdev, false); cfg80211_rdev_free_wowlan(rdev); } EXPORT_SYMBOL(wiphy_unregister); @@ -696,10 +700,15 @@ EXPORT_SYMBOL(wiphy_unregister); void cfg80211_dev_free(struct cfg80211_registered_device *rdev) { struct cfg80211_internal_bss *scan, *tmp; + struct cfg80211_beacon_registration *reg, *treg; rfkill_destroy(rdev->rfkill); mutex_destroy(&rdev->mtx); mutex_destroy(&rdev->devlist_mtx); mutex_destroy(&rdev->sched_scan_mtx); + list_for_each_entry_safe(reg, treg, &rdev->beacon_registrations, list) { + list_del(®->list); + kfree(reg); + } list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list) cfg80211_put_bss(&scan->pub); kfree(rdev); @@ -771,7 +780,7 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev) case NL80211_IFTYPE_P2P_DEVICE: if (!wdev->p2p_started) break; - rdev->ops->stop_p2p_device(&rdev->wiphy, wdev); + rdev_stop_p2p_device(rdev, wdev); wdev->p2p_started = false; rdev->opencount--; break; @@ -857,8 +866,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, /* allow mac80211 to determine the timeout */ wdev->ps_timeout = -1; - if (!dev->ethtool_ops) - dev->ethtool_ops = &cfg80211_ethtool_ops; + netdev_set_default_ethtool_ops(dev, &cfg80211_ethtool_ops); if ((wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || @@ -962,9 +970,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, if ((wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) && rdev->ops->set_power_mgmt) - if (rdev->ops->set_power_mgmt(wdev->wiphy, dev, - wdev->ps, - wdev->ps_timeout)) { + if (rdev_set_power_mgmt(rdev, dev, wdev->ps, + wdev->ps_timeout)) { /* assume this means it's off */ wdev->ps = false; } diff --git a/net/wireless/core.h b/net/wireless/core.h index a343be4a52bd..3563097169cb 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -55,7 +55,8 @@ struct cfg80211_registered_device { int opencount; /* also protected by devlist_mtx */ wait_queue_head_t dev_wait; - u32 ap_beacons_nlportid; + struct list_head beacon_registrations; + spinlock_t beacon_registrations_lock; /* protected by RTNL only */ int num_running_ifaces; @@ -137,8 +138,6 @@ struct cfg80211_internal_bss { unsigned long ts; struct kref ref; atomic_t hold; - bool beacon_ies_allocated; - bool proberesp_ies_allocated; /* must be last because of priv member */ struct cfg80211_bss pub; @@ -260,6 +259,10 @@ enum cfg80211_chan_mode { CHAN_MODE_EXCLUSIVE, }; +struct cfg80211_beacon_registration { + struct list_head list; + u32 nlportid; +}; /* free object */ extern void cfg80211_dev_free(struct cfg80211_registered_device *rdev); @@ -304,9 +307,9 @@ int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, const struct mesh_config *conf); int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev); -int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, int freq, - enum nl80211_channel_type channel_type); +int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef); /* AP */ int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, @@ -320,13 +323,15 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx); + const u8 *key, int key_len, int key_idx, + const u8 *sae_data, int sae_data_len); int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_auth_type auth_type, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx); + const u8 *key, int key_len, int key_idx, + const u8 *sae_data, int sae_data_len); int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan, @@ -371,10 +376,8 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct ieee80211_channel *chan, bool offchan, - enum nl80211_channel_type channel_type, - bool channel_type_valid, unsigned int wait, - const u8 *buf, size_t len, bool no_cck, - bool dont_wait_for_ack, u64 *cookie); + unsigned int wait, const u8 *buf, size_t len, + bool no_cck, bool dont_wait_for_ack, u64 *cookie); void cfg80211_oper_and_ht_capa(struct ieee80211_ht_cap *ht_capa, const struct ieee80211_ht_cap *ht_capa_mask); @@ -465,11 +468,8 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, struct ieee80211_channel **chan, enum cfg80211_chan_mode *chanmode); -struct ieee80211_channel * -rdev_freq_to_chan(struct cfg80211_registered_device *rdev, - int freq, enum nl80211_channel_type channel_type); int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, - int freq, enum nl80211_channel_type chantype); + struct cfg80211_chan_def *chandef); int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, const u8 *rates, unsigned int n_rates, diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index 7eecdf40cf80..48c48ffafa1d 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -2,6 +2,7 @@ #include <net/cfg80211.h> #include "core.h" #include "ethtool.h" +#include "rdev-ops.h" static void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) @@ -47,9 +48,8 @@ static void cfg80211_get_ringparam(struct net_device *dev, memset(rp, 0, sizeof(*rp)); if (rdev->ops->get_ringparam) - rdev->ops->get_ringparam(wdev->wiphy, - &rp->tx_pending, &rp->tx_max_pending, - &rp->rx_pending, &rp->rx_max_pending); + rdev_get_ringparam(rdev, &rp->tx_pending, &rp->tx_max_pending, + &rp->rx_pending, &rp->rx_max_pending); } static int cfg80211_set_ringparam(struct net_device *dev, @@ -62,8 +62,7 @@ static int cfg80211_set_ringparam(struct net_device *dev, return -EINVAL; if (rdev->ops->set_ringparam) - return rdev->ops->set_ringparam(wdev->wiphy, - rp->tx_pending, rp->rx_pending); + return rdev_set_ringparam(rdev, rp->tx_pending, rp->rx_pending); return -ENOTSUPP; } @@ -73,7 +72,7 @@ static int cfg80211_get_sset_count(struct net_device *dev, int sset) struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); if (rdev->ops->get_et_sset_count) - return rdev->ops->get_et_sset_count(wdev->wiphy, dev, sset); + return rdev_get_et_sset_count(rdev, dev, sset); return -EOPNOTSUPP; } @@ -83,7 +82,7 @@ static void cfg80211_get_stats(struct net_device *dev, struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); if (rdev->ops->get_et_stats) - rdev->ops->get_et_stats(wdev->wiphy, dev, stats, data); + rdev_get_et_stats(rdev, dev, stats, data); } static void cfg80211_get_strings(struct net_device *dev, u32 sset, u8 *data) @@ -91,7 +90,7 @@ static void cfg80211_get_strings(struct net_device *dev, u32 sset, u8 *data) struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); if (rdev->ops->get_et_strings) - rdev->ops->get_et_strings(wdev->wiphy, dev, sset, data); + rdev_get_et_strings(rdev, dev, sset, data); } const struct ethtool_ops cfg80211_ethtool_ops = { diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index ca5672f6ee2f..9b9551e4a6f9 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -11,6 +11,7 @@ #include <net/cfg80211.h> #include "wext-compat.h" #include "nl80211.h" +#include "rdev-ops.h" void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) @@ -61,6 +62,8 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) struct cfg80211_event *ev; unsigned long flags; + trace_cfg80211_ibss_joined(dev, bssid); + CFG80211_DEV_WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTING); ev = kzalloc(sizeof(*ev), gfp); @@ -97,9 +100,9 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, * 11a for maximum compatibility. */ struct ieee80211_supported_band *sband = - rdev->wiphy.bands[params->channel->band]; + rdev->wiphy.bands[params->chandef.chan->band]; int j; - u32 flag = params->channel->band == IEEE80211_BAND_5GHZ ? + u32 flag = params->chandef.chan->band == IEEE80211_BAND_5GHZ ? IEEE80211_RATE_MANDATORY_A : IEEE80211_RATE_MANDATORY_B; @@ -115,11 +118,11 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, wdev->ibss_fixed = params->channel_fixed; #ifdef CONFIG_CFG80211_WEXT - wdev->wext.ibss.channel = params->channel; + wdev->wext.ibss.chandef = params->chandef; #endif wdev->sme_state = CFG80211_SME_CONNECTING; - err = cfg80211_can_use_chan(rdev, wdev, params->channel, + err = cfg80211_can_use_chan(rdev, wdev, params->chandef.chan, params->channel_fixed ? CHAN_MODE_SHARED : CHAN_MODE_EXCLUSIVE); @@ -128,7 +131,7 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, return err; } - err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); + err = rdev_join_ibss(rdev, dev, params); if (err) { wdev->connect_keys = NULL; wdev->sme_state = CFG80211_SME_IDLE; @@ -175,7 +178,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) */ if (rdev->ops->del_key) for (i = 0; i < 6; i++) - rdev->ops->del_key(wdev->wiphy, dev, i, false, NULL); + rdev_del_key(rdev, dev, i, false, NULL); if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); @@ -211,7 +214,7 @@ int __cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, if (!wdev->ssid_len) return -ENOLINK; - err = rdev->ops->leave_ibss(&rdev->wiphy, dev); + err = rdev_leave_ibss(rdev, dev); if (err) return err; @@ -248,7 +251,9 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, wdev->wext.ibss.beacon_interval = 100; /* try to find an IBSS channel if none requested ... */ - if (!wdev->wext.ibss.channel) { + if (!wdev->wext.ibss.chandef.chan) { + wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT; + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; @@ -263,15 +268,15 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, continue; if (chan->flags & IEEE80211_CHAN_DISABLED) continue; - wdev->wext.ibss.channel = chan; + wdev->wext.ibss.chandef.chan = chan; break; } - if (wdev->wext.ibss.channel) + if (wdev->wext.ibss.chandef.chan) break; } - if (!wdev->wext.ibss.channel) + if (!wdev->wext.ibss.chandef.chan) return -EINVAL; } @@ -333,7 +338,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, return -EINVAL; } - if (wdev->wext.ibss.channel == chan) + if (wdev->wext.ibss.chandef.chan == chan) return 0; wdev_lock(wdev); @@ -346,7 +351,8 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, return err; if (chan) { - wdev->wext.ibss.channel = chan; + wdev->wext.ibss.chandef.chan = chan; + wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT; wdev->wext.ibss.channel_fixed = true; } else { /* cfg80211_ibss_wext_join will pick one if needed */ @@ -376,8 +382,8 @@ int cfg80211_ibss_wext_giwfreq(struct net_device *dev, wdev_lock(wdev); if (wdev->current_bss) chan = wdev->current_bss->pub.channel; - else if (wdev->wext.ibss.channel) - chan = wdev->wext.ibss.channel; + else if (wdev->wext.ibss.chandef.chan) + chan = wdev->wext.ibss.chandef.chan; wdev_unlock(wdev); if (chan) { diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index c384e77ff77a..f9d6ce5cfabb 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -3,6 +3,7 @@ #include <net/cfg80211.h> #include "nl80211.h" #include "core.h" +#include "rdev-ops.h" /* Default values, timeouts in ms */ #define MESH_TTL 31 @@ -72,8 +73,6 @@ const struct mesh_config default_mesh_config = { const struct mesh_setup default_mesh_setup = { /* cfg80211_join_mesh() will pick a channel if needed */ - .channel = NULL, - .channel_type = NL80211_CHAN_NO_HT, .sync_method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET, .path_sel_proto = IEEE80211_PATH_PROTOCOL_HWMP, .path_metric = IEEE80211_PATH_METRIC_AIRTIME, @@ -110,13 +109,12 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, if (!rdev->ops->join_mesh) return -EOPNOTSUPP; - if (!setup->channel) { + if (!setup->chandef.chan) { /* if no channel explicitly given, use preset channel */ - setup->channel = wdev->preset_chan; - setup->channel_type = wdev->preset_chantype; + setup->chandef = wdev->preset_chandef; } - if (!setup->channel) { + if (!setup->chandef.chan) { /* if we don't have that either, use the first usable channel */ enum ieee80211_band band; @@ -136,35 +134,35 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, IEEE80211_CHAN_DISABLED | IEEE80211_CHAN_RADAR)) continue; - setup->channel = chan; + setup->chandef.chan = chan; break; } - if (setup->channel) + if (setup->chandef.chan) break; } /* no usable channel ... */ - if (!setup->channel) + if (!setup->chandef.chan) return -EINVAL; - setup->channel_type = NL80211_CHAN_NO_HT; + setup->chandef.width = NL80211_CHAN_WIDTH_20_NOHT; + setup->chandef.center_freq1 = setup->chandef.chan->center_freq; } - if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, setup->channel, - setup->channel_type)) + if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef)) return -EINVAL; - err = cfg80211_can_use_chan(rdev, wdev, setup->channel, + err = cfg80211_can_use_chan(rdev, wdev, setup->chandef.chan, CHAN_MODE_SHARED); if (err) return err; - err = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, setup); + err = rdev_join_mesh(rdev, dev, conf, setup); if (!err) { memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len); wdev->mesh_id_len = setup->mesh_id_len; - wdev->channel = setup->channel; + wdev->channel = setup->chandef.chan; } return err; @@ -187,20 +185,12 @@ int cfg80211_join_mesh(struct cfg80211_registered_device *rdev, return err; } -int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, int freq, - enum nl80211_channel_type channel_type) +int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef) { - struct ieee80211_channel *channel; int err; - channel = rdev_freq_to_chan(rdev, freq, channel_type); - if (!channel || !cfg80211_can_beacon_sec_chan(&rdev->wiphy, - channel, - channel_type)) { - return -EINVAL; - } - /* * Workaround for libertas (only!), it puts the interface * into mesh mode but doesn't implement join_mesh. Instead, @@ -209,22 +199,21 @@ int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev, * compatible with 802.11 mesh. */ if (rdev->ops->libertas_set_mesh_channel) { - if (channel_type != NL80211_CHAN_NO_HT) + if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT) return -EINVAL; if (!netif_running(wdev->netdev)) return -ENETDOWN; - err = cfg80211_can_use_chan(rdev, wdev, channel, + err = cfg80211_can_use_chan(rdev, wdev, chandef->chan, CHAN_MODE_SHARED); if (err) return err; - err = rdev->ops->libertas_set_mesh_channel(&rdev->wiphy, - wdev->netdev, - channel); + err = rdev_libertas_set_mesh_channel(rdev, wdev->netdev, + chandef->chan); if (!err) - wdev->channel = channel; + wdev->channel = chandef->chan; return err; } @@ -232,8 +221,7 @@ int cfg80211_set_mesh_freq(struct cfg80211_registered_device *rdev, if (wdev->mesh_id_len) return -EBUSY; - wdev->preset_chan = channel; - wdev->preset_chantype = channel_type; + wdev->preset_chandef = *chandef; return 0; } @@ -242,6 +230,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; + trace_cfg80211_notify_new_peer_candidate(dev, macaddr); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_MESH_POINT)) return; @@ -267,7 +256,7 @@ static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, if (!wdev->mesh_id_len) return -ENOTCONN; - err = rdev->ops->leave_mesh(&rdev->wiphy, dev); + err = rdev_leave_mesh(rdev, dev); if (!err) { wdev->mesh_id_len = 0; wdev->channel = NULL; diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 904a7f368325..5e8123ee63fd 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -15,6 +15,8 @@ #include <net/iw_handler.h> #include "core.h" #include "nl80211.h" +#include "rdev-ops.h" + void cfg80211_send_rx_auth(struct net_device *dev, const u8 *buf, size_t len) { @@ -22,6 +24,7 @@ void cfg80211_send_rx_auth(struct net_device *dev, const u8 *buf, size_t len) struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_send_rx_auth(dev); wdev_lock(wdev); nl80211_send_rx_auth(rdev, dev, buf, len, GFP_KERNEL); @@ -42,6 +45,7 @@ void cfg80211_send_rx_assoc(struct net_device *dev, struct cfg80211_bss *bss, u8 *ie = mgmt->u.assoc_resp.variable; int ieoffs = offsetof(struct ieee80211_mgmt, u.assoc_resp.variable); + trace_cfg80211_send_rx_assoc(dev, bss); wdev_lock(wdev); status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code); @@ -98,6 +102,7 @@ void __cfg80211_send_deauth(struct net_device *dev, const u8 *bssid = mgmt->bssid; bool was_current = false; + trace___cfg80211_send_deauth(dev); ASSERT_WDEV_LOCK(wdev); if (wdev->current_bss && @@ -147,6 +152,7 @@ void __cfg80211_send_disassoc(struct net_device *dev, u16 reason_code; bool from_ap; + trace___cfg80211_send_disassoc(dev); ASSERT_WDEV_LOCK(wdev); nl80211_send_disassoc(rdev, dev, buf, len, GFP_KERNEL); @@ -188,6 +194,7 @@ void cfg80211_send_unprot_deauth(struct net_device *dev, const u8 *buf, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_send_unprot_deauth(dev); nl80211_send_unprot_deauth(rdev, dev, buf, len, GFP_ATOMIC); } EXPORT_SYMBOL(cfg80211_send_unprot_deauth); @@ -199,6 +206,7 @@ void cfg80211_send_unprot_disassoc(struct net_device *dev, const u8 *buf, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_send_unprot_disassoc(dev); nl80211_send_unprot_disassoc(rdev, dev, buf, len, GFP_ATOMIC); } EXPORT_SYMBOL(cfg80211_send_unprot_disassoc); @@ -209,6 +217,7 @@ void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr) struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_send_auth_timeout(dev, addr); wdev_lock(wdev); nl80211_send_auth_timeout(rdev, dev, addr, GFP_KERNEL); @@ -227,6 +236,7 @@ void cfg80211_send_assoc_timeout(struct net_device *dev, const u8 *addr) struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_send_assoc_timeout(dev, addr); wdev_lock(wdev); nl80211_send_assoc_timeout(rdev, dev, addr, GFP_KERNEL); @@ -261,6 +271,7 @@ void cfg80211_michael_mic_failure(struct net_device *dev, const u8 *addr, } #endif + trace_cfg80211_michael_mic_failure(dev, addr, key_type, key_id, tsc); nl80211_michael_mic_failure(rdev, dev, addr, key_type, key_id, tsc, gfp); } EXPORT_SYMBOL(cfg80211_michael_mic_failure); @@ -273,7 +284,8 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx) + const u8 *key, int key_len, int key_idx, + const u8 *sae_data, int sae_data_len) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_auth_request req; @@ -293,6 +305,8 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, req.ie = ie; req.ie_len = ie_len; + req.sae_data = sae_data; + req.sae_data_len = sae_data_len; req.auth_type = auth_type; req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS); @@ -307,7 +321,7 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, if (err) goto out; - err = rdev->ops->auth(&rdev->wiphy, dev, &req); + err = rdev_auth(rdev, dev, &req); out: cfg80211_put_bss(req.bss); @@ -319,7 +333,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, enum nl80211_auth_type auth_type, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx) + const u8 *key, int key_len, int key_idx, + const u8 *sae_data, int sae_data_len) { int err; @@ -327,7 +342,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, wdev_lock(dev->ieee80211_ptr); err = __cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, ssid, ssid_len, ie, ie_len, - key, key_len, key_idx); + key, key_len, key_idx, + sae_data, sae_data_len); wdev_unlock(dev->ieee80211_ptr); mutex_unlock(&rdev->devlist_mtx); @@ -410,7 +426,7 @@ int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, if (err) goto out; - err = rdev->ops->assoc(&rdev->wiphy, dev, &req); + err = rdev_assoc(rdev, dev, &req); out: if (err) { @@ -466,7 +482,7 @@ int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, !ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) return 0; - return rdev->ops->deauth(&rdev->wiphy, dev, &req); + return rdev_deauth(rdev, dev, &req); } int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, @@ -511,7 +527,7 @@ static int __cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, else return -ENOTCONN; - return rdev->ops->disassoc(&rdev->wiphy, dev, &req); + return rdev_disassoc(rdev, dev, &req); } int cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, @@ -552,7 +568,7 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN); req.bssid = bssid; - rdev->ops->deauth(&rdev->wiphy, dev, &req); + rdev_deauth(rdev, dev, &req); if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); @@ -563,27 +579,25 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_remain_on_channel(rdev, wdev, cookie, chan, channel_type, - duration, gfp); + trace_cfg80211_ready_on_channel(wdev, cookie, chan, duration); + nl80211_send_remain_on_channel(rdev, wdev, cookie, chan, duration, gfp); } EXPORT_SYMBOL(cfg80211_ready_on_channel); void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, gfp_t gfp) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - nl80211_send_remain_on_channel_cancel(rdev, wdev, cookie, chan, - channel_type, gfp); + trace_cfg80211_ready_on_channel_expired(wdev, cookie, chan); + nl80211_send_remain_on_channel_cancel(rdev, wdev, cookie, chan, gfp); } EXPORT_SYMBOL(cfg80211_remain_on_channel_expired); @@ -593,6 +607,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_new_sta(dev, mac_addr, sinfo); nl80211_send_sta_event(rdev, dev, mac_addr, sinfo, gfp); } EXPORT_SYMBOL(cfg80211_new_sta); @@ -602,6 +617,7 @@ void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp) struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_del_sta(dev, mac_addr); nl80211_send_sta_del_event(rdev, dev, mac_addr, gfp); } EXPORT_SYMBOL(cfg80211_del_sta); @@ -682,7 +698,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, list_add(&nreg->list, &wdev->mgmt_registrations); if (rdev->ops->mgmt_frame_register) - rdev->ops->mgmt_frame_register(wiphy, wdev, frame_type, true); + rdev_mgmt_frame_register(rdev, wdev, frame_type, true); out: spin_unlock_bh(&wdev->mgmt_registrations_lock); @@ -705,8 +721,8 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) if (rdev->ops->mgmt_frame_register) { u16 frame_type = le16_to_cpu(reg->frame_type); - rdev->ops->mgmt_frame_register(wiphy, wdev, - frame_type, false); + rdev_mgmt_frame_register(rdev, wdev, + frame_type, false); } list_del(®->list); @@ -736,10 +752,8 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct ieee80211_channel *chan, bool offchan, - enum nl80211_channel_type channel_type, - bool channel_type_valid, unsigned int wait, - const u8 *buf, size_t len, bool no_cck, - bool dont_wait_for_ack, u64 *cookie) + unsigned int wait, const u8 *buf, size_t len, + bool no_cck, bool dont_wait_for_ack, u64 *cookie) { const struct ieee80211_mgmt *mgmt; u16 stype; @@ -832,10 +846,9 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, return -EINVAL; /* Transmit the Action frame as requested by user space */ - return rdev->ops->mgmt_tx(&rdev->wiphy, wdev, chan, offchan, - channel_type, channel_type_valid, - wait, buf, len, no_cck, dont_wait_for_ack, - cookie); + return rdev_mgmt_tx(rdev, wdev, chan, offchan, + wait, buf, len, no_cck, dont_wait_for_ack, + cookie); } bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm, @@ -854,10 +867,13 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm, cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE); u16 stype; + trace_cfg80211_rx_mgmt(wdev, freq, sig_mbm); stype = (le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_STYPE) >> 4; - if (!(stypes->rx & BIT(stype))) + if (!(stypes->rx & BIT(stype))) { + trace_cfg80211_return_bool(false); return false; + } data = buf + ieee80211_hdrlen(mgmt->frame_control); data_len = len - ieee80211_hdrlen(mgmt->frame_control); @@ -888,6 +904,7 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm, spin_unlock_bh(&wdev->mgmt_registrations_lock); + trace_cfg80211_return_bool(result); return result; } EXPORT_SYMBOL(cfg80211_rx_mgmt); @@ -898,6 +915,8 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_mgmt_tx_status(wdev, cookie, ack); + /* Indicate TX status of the Action frame to user space */ nl80211_send_mgmt_tx_status(rdev, wdev, cookie, buf, len, ack, gfp); } @@ -911,6 +930,8 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_cqm_rssi_notify(dev, rssi_event); + /* Indicate roaming trigger event to user space */ nl80211_send_cqm_rssi_notify(rdev, dev, rssi_event, gfp); } @@ -923,6 +944,8 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_cqm_pktloss_notify(dev, peer, num_packets); + /* Indicate roaming trigger event to user space */ nl80211_send_cqm_pktloss_notify(rdev, dev, peer, num_packets, gfp); } @@ -948,6 +971,7 @@ void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_gtk_rekey_notify(dev, bssid); nl80211_gtk_rekey_notify(rdev, dev, bssid, replay_ctr, gfp); } EXPORT_SYMBOL(cfg80211_gtk_rekey_notify); @@ -959,17 +983,19 @@ void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_pmksa_candidate_notify(dev, index, bssid, preauth); nl80211_pmksa_candidate_notify(rdev, dev, index, bssid, preauth, gfp); } EXPORT_SYMBOL(cfg80211_pmksa_candidate_notify); -void cfg80211_ch_switch_notify(struct net_device *dev, int freq, - enum nl80211_channel_type type) +void cfg80211_ch_switch_notify(struct net_device *dev, + struct cfg80211_chan_def *chandef) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - struct ieee80211_channel *chan; + + trace_cfg80211_ch_switch_notify(dev, chandef); wdev_lock(wdev); @@ -977,12 +1003,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev, int freq, wdev->iftype != NL80211_IFTYPE_P2P_GO)) goto out; - chan = rdev_freq_to_chan(rdev, freq, type); - if (WARN_ON(!chan)) - goto out; - - wdev->channel = chan; - nl80211_ch_switch_notify(rdev, dev, freq, type, GFP_KERNEL); + wdev->channel = chandef->chan; + nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL); out: wdev_unlock(wdev); return; @@ -993,12 +1015,18 @@ bool cfg80211_rx_spurious_frame(struct net_device *dev, const u8 *addr, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; + bool ret; + + trace_cfg80211_rx_spurious_frame(dev, addr); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && - wdev->iftype != NL80211_IFTYPE_P2P_GO)) + wdev->iftype != NL80211_IFTYPE_P2P_GO)) { + trace_cfg80211_return_bool(false); return false; - - return nl80211_unexpected_frame(dev, addr, gfp); + } + ret = nl80211_unexpected_frame(dev, addr, gfp); + trace_cfg80211_return_bool(ret); + return ret; } EXPORT_SYMBOL(cfg80211_rx_spurious_frame); @@ -1006,12 +1034,18 @@ bool cfg80211_rx_unexpected_4addr_frame(struct net_device *dev, const u8 *addr, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; + bool ret; + + trace_cfg80211_rx_unexpected_4addr_frame(dev, addr); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && wdev->iftype != NL80211_IFTYPE_P2P_GO && - wdev->iftype != NL80211_IFTYPE_AP_VLAN)) + wdev->iftype != NL80211_IFTYPE_AP_VLAN)) { + trace_cfg80211_return_bool(false); return false; - - return nl80211_unexpected_4addr_frame(dev, addr, gfp); + } + ret = nl80211_unexpected_4addr_frame(dev, addr, gfp); + trace_cfg80211_return_bool(ret); + return ret; } EXPORT_SYMBOL(cfg80211_rx_unexpected_4addr_frame); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0418a6d5c1a6..f45706adaf34 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -22,8 +22,8 @@ #include "core.h" #include "nl80211.h" #include "reg.h" +#include "rdev-ops.h" -static bool nl80211_valid_auth_type(enum nl80211_auth_type auth_type); static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, struct genl_info *info, struct cfg80211_crypto_settings *settings, @@ -223,8 +223,13 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING, .len = 20-1 }, [NL80211_ATTR_WIPHY_TXQ_PARAMS] = { .type = NLA_NESTED }, + [NL80211_ATTR_WIPHY_FREQ] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_CHANNEL_TYPE] = { .type = NLA_U32 }, + [NL80211_ATTR_CHANNEL_WIDTH] = { .type = NLA_U32 }, + [NL80211_ATTR_CENTER_FREQ1] = { .type = NLA_U32 }, + [NL80211_ATTR_CENTER_FREQ2] = { .type = NLA_U32 }, + [NL80211_ATTR_WIPHY_RETRY_SHORT] = { .type = NLA_U8 }, [NL80211_ATTR_WIPHY_RETRY_LONG] = { .type = NLA_U8 }, [NL80211_ATTR_WIPHY_FRAG_THRESHOLD] = { .type = NLA_U32 }, @@ -355,6 +360,11 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, [NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 }, + [NL80211_ATTR_SAE_DATA] = { .type = NLA_BINARY, }, + [NL80211_ATTR_VHT_CAPABILITY] = { .len = NL80211_VHT_CAPABILITY_LEN }, + [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 }, + [NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 }, + [NL80211_ATTR_P2P_OPPPS] = { .type = NLA_U8 }, }; /* policy for the key attributes */ @@ -690,7 +700,7 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) static struct cfg80211_cached_keys * nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, - struct nlattr *keys) + struct nlattr *keys, bool *no_ht) { struct key_parse parse; struct nlattr *key; @@ -733,6 +743,12 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, result->params[parse.idx].key_len = parse.p.key_len; result->params[parse.idx].key = result->data[parse.idx]; memcpy(result->data[parse.idx], parse.p.key, parse.p.key_len); + + if (parse.p.cipher == WLAN_CIPHER_SUITE_WEP40 || + parse.p.cipher == WLAN_CIPHER_SUITE_WEP104) { + if (no_ht) + *no_ht = true; + } } return result; @@ -943,7 +959,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flag dev->wiphy.available_antennas_rx) && dev->ops->get_antenna) { u32 tx_ant = 0, rx_ant = 0; int res; - res = dev->ops->get_antenna(&dev->wiphy, &tx_ant, &rx_ant); + res = rdev_get_antenna(dev, &tx_ant, &rx_ant); if (!res) { if (nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_TX, tx_ant) || @@ -1101,6 +1117,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flag goto nla_put_failure; } CMD(start_p2p_device, START_P2P_DEVICE); + CMD(set_mcast_rate, SET_MCAST_RATE); #ifdef CONFIG_NL80211_TESTMODE CMD(testmode_cmd, TESTMODE); @@ -1350,51 +1367,83 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) wdev->iftype == NL80211_IFTYPE_P2P_GO; } -static bool nl80211_valid_channel_type(struct genl_info *info, - enum nl80211_channel_type *channel_type) +static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, + struct genl_info *info, + struct cfg80211_chan_def *chandef) { - enum nl80211_channel_type tmp; + u32 control_freq; - if (!info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) - return false; + if (!info->attrs[NL80211_ATTR_WIPHY_FREQ]) + return -EINVAL; - tmp = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]); - if (tmp != NL80211_CHAN_NO_HT && - tmp != NL80211_CHAN_HT20 && - tmp != NL80211_CHAN_HT40PLUS && - tmp != NL80211_CHAN_HT40MINUS) - return false; + control_freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); - if (channel_type) - *channel_type = tmp; + chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq); + chandef->width = NL80211_CHAN_WIDTH_20_NOHT; + chandef->center_freq1 = control_freq; + chandef->center_freq2 = 0; - return true; + /* Primary channel not allowed */ + if (!chandef->chan || chandef->chan->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; + + if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { + enum nl80211_channel_type chantype; + + chantype = nla_get_u32( + info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]); + + switch (chantype) { + case NL80211_CHAN_NO_HT: + case NL80211_CHAN_HT20: + case NL80211_CHAN_HT40PLUS: + case NL80211_CHAN_HT40MINUS: + cfg80211_chandef_create(chandef, chandef->chan, + chantype); + break; + default: + return -EINVAL; + } + } else if (info->attrs[NL80211_ATTR_CHANNEL_WIDTH]) { + chandef->width = + nla_get_u32(info->attrs[NL80211_ATTR_CHANNEL_WIDTH]); + if (info->attrs[NL80211_ATTR_CENTER_FREQ1]) + chandef->center_freq1 = + nla_get_u32( + info->attrs[NL80211_ATTR_CENTER_FREQ1]); + if (info->attrs[NL80211_ATTR_CENTER_FREQ2]) + chandef->center_freq2 = + nla_get_u32( + info->attrs[NL80211_ATTR_CENTER_FREQ2]); + } + + if (!cfg80211_chandef_valid(chandef)) + return -EINVAL; + + if (!cfg80211_chandef_usable(&rdev->wiphy, chandef, + IEEE80211_CHAN_DISABLED)) + return -EINVAL; + + return 0; } static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct genl_info *info) { - struct ieee80211_channel *channel; - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - u32 freq; + struct cfg80211_chan_def chandef; int result; enum nl80211_iftype iftype = NL80211_IFTYPE_MONITOR; if (wdev) iftype = wdev->iftype; - if (!info->attrs[NL80211_ATTR_WIPHY_FREQ]) - return -EINVAL; - if (!nl80211_can_set_dev_channel(wdev)) return -EOPNOTSUPP; - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && - !nl80211_valid_channel_type(info, &channel_type)) - return -EINVAL; - - freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); + result = nl80211_parse_chandef(rdev, info, &chandef); + if (result) + return result; mutex_lock(&rdev->devlist_mtx); switch (iftype) { @@ -1404,22 +1453,18 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, result = -EBUSY; break; } - channel = rdev_freq_to_chan(rdev, freq, channel_type); - if (!channel || !cfg80211_can_beacon_sec_chan(&rdev->wiphy, - channel, - channel_type)) { + if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef)) { result = -EINVAL; break; } - wdev->preset_chan = channel; - wdev->preset_chantype = channel_type; + wdev->preset_chandef = chandef; result = 0; break; case NL80211_IFTYPE_MESH_POINT: - result = cfg80211_set_mesh_freq(rdev, wdev, freq, channel_type); + result = cfg80211_set_mesh_channel(rdev, wdev, &chandef); break; case NL80211_IFTYPE_MONITOR: - result = cfg80211_set_monitor_channel(rdev, freq, channel_type); + result = cfg80211_set_monitor_channel(rdev, &chandef); break; default: result = -EINVAL; @@ -1457,7 +1502,7 @@ static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - return rdev->ops->set_wds_peer(wdev->wiphy, dev, bssid); + return rdev_set_wds_peer(rdev, dev, bssid); } @@ -1507,10 +1552,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) result = 0; mutex_lock(&rdev->mtx); - } else if (nl80211_can_set_dev_channel(netdev->ieee80211_ptr)) + } else wdev = netdev->ieee80211_ptr; - else - wdev = NULL; /* * end workaround code, by now the rdev is available @@ -1562,24 +1605,29 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (result) goto bad_res; - result = rdev->ops->set_txq_params(&rdev->wiphy, - netdev, - &txq_params); + result = rdev_set_txq_params(rdev, netdev, + &txq_params); if (result) goto bad_res; } } if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - result = __nl80211_set_channel(rdev, wdev, info); + result = __nl80211_set_channel(rdev, + nl80211_can_set_dev_channel(wdev) ? wdev : NULL, + info); if (result) goto bad_res; } if (info->attrs[NL80211_ATTR_WIPHY_TX_POWER_SETTING]) { + struct wireless_dev *txp_wdev = wdev; enum nl80211_tx_power_setting type; int idx, mbm = 0; + if (!(rdev->wiphy.features & NL80211_FEATURE_VIF_TXPOWER)) + txp_wdev = NULL; + if (!rdev->ops->set_tx_power) { result = -EOPNOTSUPP; goto bad_res; @@ -1599,7 +1647,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) mbm = nla_get_u32(info->attrs[idx]); } - result = rdev->ops->set_tx_power(&rdev->wiphy, type, mbm); + result = rdev_set_tx_power(rdev, txp_wdev, type, mbm); if (result) goto bad_res; } @@ -1628,7 +1676,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) tx_ant = tx_ant & rdev->wiphy.available_antennas_tx; rx_ant = rx_ant & rdev->wiphy.available_antennas_rx; - result = rdev->ops->set_antenna(&rdev->wiphy, tx_ant, rx_ant); + result = rdev_set_antenna(rdev, tx_ant, rx_ant); if (result) goto bad_res; } @@ -1713,7 +1761,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (changed & WIPHY_PARAM_COVERAGE_CLASS) rdev->wiphy.coverage_class = coverage_class; - result = rdev->ops->set_wiphy_params(&rdev->wiphy, changed); + result = rdev_set_wiphy_params(rdev, changed); if (result) { rdev->wiphy.retry_short = old_retry_short; rdev->wiphy.retry_long = old_retry_long; @@ -1736,6 +1784,35 @@ static inline u64 wdev_id(struct wireless_dev *wdev) ((u64)wiphy_to_dev(wdev->wiphy)->wiphy_idx << 32); } +static int nl80211_send_chandef(struct sk_buff *msg, + struct cfg80211_chan_def *chandef) +{ + WARN_ON(!cfg80211_chandef_valid(chandef)); + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, + chandef->chan->center_freq)) + return -ENOBUFS; + switch (chandef->width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_40: + if (nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, + cfg80211_get_chandef_type(chandef))) + return -ENOBUFS; + break; + default: + break; + } + if (nla_put_u32(msg, NL80211_ATTR_CHANNEL_WIDTH, chandef->width)) + return -ENOBUFS; + if (nla_put_u32(msg, NL80211_ATTR_CENTER_FREQ1, chandef->center_freq1)) + return -ENOBUFS; + if (chandef->center_freq2 && + nla_put_u32(msg, NL80211_ATTR_CENTER_FREQ2, chandef->center_freq2)) + return -ENOBUFS; + return 0; +} + static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) @@ -1762,16 +1839,18 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag goto nla_put_failure; if (rdev->ops->get_channel) { - struct ieee80211_channel *chan; - enum nl80211_channel_type channel_type; - - chan = rdev->ops->get_channel(&rdev->wiphy, wdev, - &channel_type); - if (chan && - (nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, - chan->center_freq) || - nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, - channel_type))) + int ret; + struct cfg80211_chan_def chandef; + + ret = rdev_get_channel(rdev, wdev, &chandef); + if (ret == 0) { + if (nl80211_send_chandef(msg, &chandef)) + goto nla_put_failure; + } + } + + if (wdev->ssid_len) { + if (nla_put(msg, NL80211_ATTR_SSID, wdev->ssid_len, wdev->ssid)) goto nla_put_failure; } @@ -2014,9 +2093,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) err = parse_monitor_flags(type == NL80211_IFTYPE_MONITOR ? info->attrs[NL80211_ATTR_MNTR_FLAGS] : NULL, &flags); - wdev = rdev->ops->add_virtual_intf(&rdev->wiphy, - nla_data(info->attrs[NL80211_ATTR_IFNAME]), - type, err ? NULL : &flags, ¶ms); + wdev = rdev_add_virtual_intf(rdev, + nla_data(info->attrs[NL80211_ATTR_IFNAME]), + type, err ? NULL : &flags, ¶ms); if (IS_ERR(wdev)) { nlmsg_free(msg); return PTR_ERR(wdev); @@ -2083,7 +2162,7 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) if (!wdev->netdev) info->user_ptr[1] = NULL; - return rdev->ops->del_virtual_intf(&rdev->wiphy, wdev); + return rdev_del_virtual_intf(rdev, wdev); } static int nl80211_set_noack_map(struct sk_buff *skb, struct genl_info *info) @@ -2100,7 +2179,7 @@ static int nl80211_set_noack_map(struct sk_buff *skb, struct genl_info *info) noack_map = nla_get_u16(info->attrs[NL80211_ATTR_NOACK_MAP]); - return rdev->ops->set_noack_map(&rdev->wiphy, dev, noack_map); + return rdev_set_noack_map(rdev, dev, noack_map); } struct get_key_cookie { @@ -2210,8 +2289,8 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) return -ENOENT; - err = rdev->ops->get_key(&rdev->wiphy, dev, key_idx, pairwise, - mac_addr, &cookie, get_key_callback); + err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie, + get_key_callback); if (err) goto free_msg; @@ -2259,7 +2338,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) if (err) goto out; - err = rdev->ops->set_default_key(&rdev->wiphy, dev, key.idx, + err = rdev_set_default_key(rdev, dev, key.idx, key.def_uni, key.def_multi); if (err) @@ -2283,8 +2362,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) if (err) goto out; - err = rdev->ops->set_default_mgmt_key(&rdev->wiphy, - dev, key.idx); + err = rdev_set_default_mgmt_key(rdev, dev, key.idx); if (err) goto out; @@ -2340,9 +2418,9 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); if (!err) - err = rdev->ops->add_key(&rdev->wiphy, dev, key.idx, - key.type == NL80211_KEYTYPE_PAIRWISE, - mac_addr, &key.p); + err = rdev_add_key(rdev, dev, key.idx, + key.type == NL80211_KEYTYPE_PAIRWISE, + mac_addr, &key.p); wdev_unlock(dev->ieee80211_ptr); return err; @@ -2386,9 +2464,9 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) err = -ENOENT; if (!err) - err = rdev->ops->del_key(&rdev->wiphy, dev, key.idx, - key.type == NL80211_KEYTYPE_PAIRWISE, - mac_addr); + err = rdev_del_key(rdev, dev, key.idx, + key.type == NL80211_KEYTYPE_PAIRWISE, + mac_addr); #ifdef CONFIG_CFG80211_WEXT if (!err) { @@ -2476,11 +2554,10 @@ static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, wdev->iftype != NL80211_IFTYPE_P2P_GO) continue; - if (!wdev->preset_chan) + if (!wdev->preset_chandef.chan) continue; - params->channel = wdev->preset_chan; - params->channel_type = wdev->preset_chantype; + params->chandef = wdev->preset_chandef; ret = true; break; } @@ -2490,6 +2567,30 @@ static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, return ret; } +static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, + enum nl80211_auth_type auth_type, + enum nl80211_commands cmd) +{ + if (auth_type > NL80211_AUTHTYPE_MAX) + return false; + + switch (cmd) { + case NL80211_CMD_AUTHENTICATE: + if (!(rdev->wiphy.features & NL80211_FEATURE_SAE) && + auth_type == NL80211_AUTHTYPE_SAE) + return false; + return true; + case NL80211_CMD_CONNECT: + case NL80211_CMD_START_AP: + /* SAE not supported yet */ + if (auth_type == NL80211_AUTHTYPE_SAE) + return false; + return true; + default: + return false; + } +} + static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -2559,7 +2660,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_AUTH_TYPE]) { params.auth_type = nla_get_u32( info->attrs[NL80211_ATTR_AUTH_TYPE]); - if (!nl80211_valid_auth_type(params.auth_type)) + if (!nl80211_valid_auth_type(rdev, params.auth_type, + NL80211_CMD_START_AP)) return -EINVAL; } else params.auth_type = NL80211_AUTHTYPE_AUTOMATIC; @@ -2576,43 +2678,59 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) info->attrs[NL80211_ATTR_INACTIVITY_TIMEOUT]); } - if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && - !nl80211_valid_channel_type(info, &channel_type)) + if (info->attrs[NL80211_ATTR_P2P_CTWINDOW]) { + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EINVAL; + params.p2p_ctwindow = + nla_get_u8(info->attrs[NL80211_ATTR_P2P_CTWINDOW]); + if (params.p2p_ctwindow > 127) + return -EINVAL; + if (params.p2p_ctwindow != 0 && + !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_CTWIN)) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_P2P_OPPPS]) { + u8 tmp; - params.channel = rdev_freq_to_chan(rdev, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]), - channel_type); - if (!params.channel) + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EINVAL; - params.channel_type = channel_type; - } else if (wdev->preset_chan) { - params.channel = wdev->preset_chan; - params.channel_type = wdev->preset_chantype; + tmp = nla_get_u8(info->attrs[NL80211_ATTR_P2P_OPPPS]); + if (tmp > 1) + return -EINVAL; + params.p2p_opp_ps = tmp; + if (params.p2p_opp_ps != 0 && + !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_OPPPS)) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { + err = nl80211_parse_chandef(rdev, info, ¶ms.chandef); + if (err) + return err; + } else if (wdev->preset_chandef.chan) { + params.chandef = wdev->preset_chandef; } else if (!nl80211_get_ap_channel(rdev, ¶ms)) return -EINVAL; - if (!cfg80211_can_beacon_sec_chan(&rdev->wiphy, params.channel, - params.channel_type)) + if (!cfg80211_reg_can_beacon(&rdev->wiphy, ¶ms.chandef)) return -EINVAL; mutex_lock(&rdev->devlist_mtx); - err = cfg80211_can_use_chan(rdev, wdev, params.channel, + err = cfg80211_can_use_chan(rdev, wdev, params.chandef.chan, CHAN_MODE_SHARED); mutex_unlock(&rdev->devlist_mtx); if (err) return err; - err = rdev->ops->start_ap(&rdev->wiphy, dev, ¶ms); + err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { - wdev->preset_chan = params.channel; - wdev->preset_chantype = params.channel_type; + wdev->preset_chandef = params.chandef; wdev->beacon_interval = params.beacon_interval; - wdev->channel = params.channel; + wdev->channel = params.chandef.chan; + wdev->ssid_len = params.ssid_len; + memcpy(wdev->ssid, params.ssid, wdev->ssid_len); } return err; } @@ -2639,7 +2757,7 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) if (err) return err; - return rdev->ops->change_beacon(&rdev->wiphy, dev, ¶ms); + return rdev_change_beacon(rdev, dev, ¶ms); } static int nl80211_stop_ap(struct sk_buff *skb, struct genl_info *info) @@ -2744,29 +2862,52 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, rate = nla_nest_start(msg, attr); if (!rate) - goto nla_put_failure; + return false; /* cfg80211_calculate_bitrate will return 0 for mcs >= 32 */ bitrate = cfg80211_calculate_bitrate(info); /* report 16-bit bitrate only if we can */ bitrate_compat = bitrate < (1UL << 16) ? bitrate : 0; - if ((bitrate > 0 && - nla_put_u32(msg, NL80211_RATE_INFO_BITRATE32, bitrate)) || - (bitrate_compat > 0 && - nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat)) || - ((info->flags & RATE_INFO_FLAGS_MCS) && - nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs)) || - ((info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) && - nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH)) || - ((info->flags & RATE_INFO_FLAGS_SHORT_GI) && - nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))) - goto nla_put_failure; + if (bitrate > 0 && + nla_put_u32(msg, NL80211_RATE_INFO_BITRATE32, bitrate)) + return false; + if (bitrate_compat > 0 && + nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat)) + return false; + + if (info->flags & RATE_INFO_FLAGS_MCS) { + if (nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs)) + return false; + if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH && + nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH)) + return false; + if (info->flags & RATE_INFO_FLAGS_SHORT_GI && + nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI)) + return false; + } else if (info->flags & RATE_INFO_FLAGS_VHT_MCS) { + if (nla_put_u8(msg, NL80211_RATE_INFO_VHT_MCS, info->mcs)) + return false; + if (nla_put_u8(msg, NL80211_RATE_INFO_VHT_NSS, info->nss)) + return false; + if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH && + nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH)) + return false; + if (info->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH && + nla_put_flag(msg, NL80211_RATE_INFO_80_MHZ_WIDTH)) + return false; + if (info->flags & RATE_INFO_FLAGS_80P80_MHZ_WIDTH && + nla_put_flag(msg, NL80211_RATE_INFO_80P80_MHZ_WIDTH)) + return false; + if (info->flags & RATE_INFO_FLAGS_160_MHZ_WIDTH && + nla_put_flag(msg, NL80211_RATE_INFO_160_MHZ_WIDTH)) + return false; + if (info->flags & RATE_INFO_FLAGS_SHORT_GI && + nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI)) + return false; + } nla_nest_end(msg, rate); return true; - -nla_put_failure: - return false; } static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, @@ -2923,8 +3064,8 @@ static int nl80211_dump_station(struct sk_buff *skb, while (1) { memset(&sinfo, 0, sizeof(sinfo)); - err = dev->ops->dump_station(&dev->wiphy, netdev, sta_idx, - mac_addr, &sinfo); + err = rdev_dump_station(dev, netdev, sta_idx, + mac_addr, &sinfo); if (err == -ENOENT) break; if (err) @@ -2969,7 +3110,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->get_station) return -EOPNOTSUPP; - err = rdev->ops->get_station(&rdev->wiphy, dev, mac_addr, &sinfo); + err = rdev_get_station(rdev, dev, mac_addr, &sinfo); if (err) return err; @@ -3146,7 +3287,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) /* be aware of params.vlan when changing code here */ - err = rdev->ops->change_station(&rdev->wiphy, dev, mac_addr, ¶ms); + err = rdev_change_station(rdev, dev, mac_addr, ¶ms); if (params.vlan) dev_put(params.vlan); @@ -3198,6 +3339,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.ht_capa = nla_data(info->attrs[NL80211_ATTR_HT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_VHT_CAPABILITY]) + params.vht_capa = + nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_STA_PLINK_ACTION]) params.plink_action = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]); @@ -3275,7 +3420,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) /* be aware of params.vlan when changing code here */ - err = rdev->ops->add_station(&rdev->wiphy, dev, mac_addr, ¶ms); + err = rdev_add_station(rdev, dev, mac_addr, ¶ms); if (params.vlan) dev_put(params.vlan); @@ -3300,7 +3445,7 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->del_station) return -EOPNOTSUPP; - return rdev->ops->del_station(&rdev->wiphy, dev, mac_addr); + return rdev_del_station(rdev, dev, mac_addr); } static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, @@ -3382,8 +3527,8 @@ static int nl80211_dump_mpath(struct sk_buff *skb, } while (1) { - err = dev->ops->dump_mpath(&dev->wiphy, netdev, path_idx, - dst, next_hop, &pinfo); + err = rdev_dump_mpath(dev, netdev, path_idx, dst, next_hop, + &pinfo); if (err == -ENOENT) break; if (err) @@ -3430,7 +3575,7 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) return -EOPNOTSUPP; - err = rdev->ops->get_mpath(&rdev->wiphy, dev, dst, next_hop, &pinfo); + err = rdev_get_mpath(rdev, dev, dst, next_hop, &pinfo); if (err) return err; @@ -3469,7 +3614,7 @@ static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) return -EOPNOTSUPP; - return rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); + return rdev_change_mpath(rdev, dev, dst, next_hop); } static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) @@ -3494,7 +3639,7 @@ static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) return -EOPNOTSUPP; - return rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); + return rdev_add_mpath(rdev, dev, dst, next_hop); } static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) @@ -3509,7 +3654,7 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->del_mpath) return -EOPNOTSUPP; - return rdev->ops->del_mpath(&rdev->wiphy, dev, dst); + return rdev_del_mpath(rdev, dev, dst); } static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) @@ -3525,6 +3670,8 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) params.use_short_slot_time = -1; params.ap_isolate = -1; params.ht_opmode = -1; + params.p2p_ctwindow = -1; + params.p2p_opp_ps = -1; if (info->attrs[NL80211_ATTR_BSS_CTS_PROT]) params.use_cts_prot = @@ -3547,6 +3694,32 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) params.ht_opmode = nla_get_u16(info->attrs[NL80211_ATTR_BSS_HT_OPMODE]); + if (info->attrs[NL80211_ATTR_P2P_CTWINDOW]) { + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EINVAL; + params.p2p_ctwindow = + nla_get_s8(info->attrs[NL80211_ATTR_P2P_CTWINDOW]); + if (params.p2p_ctwindow < 0) + return -EINVAL; + if (params.p2p_ctwindow != 0 && + !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_CTWIN)) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_P2P_OPPPS]) { + u8 tmp; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EINVAL; + tmp = nla_get_u8(info->attrs[NL80211_ATTR_P2P_OPPPS]); + if (tmp > 1) + return -EINVAL; + params.p2p_opp_ps = tmp; + if (params.p2p_opp_ps && + !(rdev->wiphy.features & NL80211_FEATURE_P2P_GO_OPPPS)) + return -EINVAL; + } + if (!rdev->ops->change_bss) return -EOPNOTSUPP; @@ -3554,7 +3727,7 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; - return rdev->ops->change_bss(&rdev->wiphy, dev, ¶ms); + return rdev_change_bss(rdev, dev, ¶ms); } static const struct nla_policy reg_rule_policy[NL80211_REG_RULE_ATTR_MAX + 1] = { @@ -3668,8 +3841,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, if (!wdev->mesh_id_len) memcpy(&cur_params, &default_mesh_config, sizeof(cur_params)); else - err = rdev->ops->get_mesh_config(&rdev->wiphy, dev, - &cur_params); + err = rdev_get_mesh_config(rdev, dev, &cur_params); wdev_unlock(wdev); if (err) @@ -3971,8 +4143,7 @@ static int nl80211_update_mesh_config(struct sk_buff *skb, err = -ENOLINK; if (!err) - err = rdev->ops->update_mesh_config(&rdev->wiphy, dev, - mask, &cfg); + err = rdev_update_mesh_config(rdev, dev, mask, &cfg); wdev_unlock(wdev); @@ -4337,14 +4508,27 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) } } + if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { + request->flags = nla_get_u32( + info->attrs[NL80211_ATTR_SCAN_FLAGS]); + if (((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) || + ((request->flags & NL80211_SCAN_FLAG_FLUSH) && + !(wiphy->features & NL80211_FEATURE_SCAN_FLUSH))) { + err = -EOPNOTSUPP; + goto out_free; + } + } + request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); request->wdev = wdev; request->wiphy = &rdev->wiphy; + request->scan_start = jiffies; rdev->scan_req = request; - err = rdev->ops->scan(&rdev->wiphy, request); + err = rdev_scan(rdev, request); if (!err) { nl80211_send_scan_start(rdev, wdev); @@ -4568,11 +4752,24 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, request->ie_len); } + if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { + request->flags = nla_get_u32( + info->attrs[NL80211_ATTR_SCAN_FLAGS]); + if (((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) || + ((request->flags & NL80211_SCAN_FLAG_FLUSH) && + !(wiphy->features & NL80211_FEATURE_SCAN_FLUSH))) { + err = -EOPNOTSUPP; + goto out_free; + } + } + request->dev = dev; request->wiphy = &rdev->wiphy; request->interval = interval; + request->scan_start = jiffies; - err = rdev->ops->sched_scan_start(&rdev->wiphy, dev, request); + err = rdev_sched_scan_start(rdev, dev, request); if (!err) { rdev->sched_scan_req = request; nl80211_send_sched_scan(rdev, dev, @@ -4611,6 +4808,7 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, struct cfg80211_internal_bss *intbss) { struct cfg80211_bss *res = &intbss->pub; + const struct cfg80211_bss_ies *ies; void *hdr; struct nlattr *bss; @@ -4631,16 +4829,24 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, if (!bss) goto nla_put_failure; if ((!is_zero_ether_addr(res->bssid) && - nla_put(msg, NL80211_BSS_BSSID, ETH_ALEN, res->bssid)) || - (res->information_elements && res->len_information_elements && - nla_put(msg, NL80211_BSS_INFORMATION_ELEMENTS, - res->len_information_elements, - res->information_elements)) || - (res->beacon_ies && res->len_beacon_ies && - res->beacon_ies != res->information_elements && - nla_put(msg, NL80211_BSS_BEACON_IES, - res->len_beacon_ies, res->beacon_ies))) + nla_put(msg, NL80211_BSS_BSSID, ETH_ALEN, res->bssid))) + goto nla_put_failure; + + rcu_read_lock(); + ies = rcu_dereference(res->ies); + if (ies && ies->len && nla_put(msg, NL80211_BSS_INFORMATION_ELEMENTS, + ies->len, ies->data)) { + rcu_read_unlock(); + goto nla_put_failure; + } + ies = rcu_dereference(res->beacon_ies); + if (ies && ies->len && nla_put(msg, NL80211_BSS_BEACON_IES, + ies->len, ies->data)) { + rcu_read_unlock(); goto nla_put_failure; + } + rcu_read_unlock(); + if (res->tsf && nla_put_u64(msg, NL80211_BSS_TSF, res->tsf)) goto nla_put_failure; @@ -4815,8 +5021,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, while (1) { struct ieee80211_channel *chan; - res = dev->ops->dump_survey(&dev->wiphy, netdev, survey_idx, - &survey); + res = rdev_dump_survey(dev, netdev, survey_idx, &survey); if (res == -ENOENT) break; if (res) @@ -4852,11 +5057,6 @@ static int nl80211_dump_survey(struct sk_buff *skb, return res; } -static bool nl80211_valid_auth_type(enum nl80211_auth_type auth_type) -{ - return auth_type <= NL80211_AUTHTYPE_MAX; -} - static bool nl80211_valid_wpa_versions(u32 wpa_versions) { return !(wpa_versions & ~(NL80211_WPA_VERSION_1 | @@ -4868,8 +5068,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct ieee80211_channel *chan; - const u8 *bssid, *ssid, *ie = NULL; - int err, ssid_len, ie_len = 0; + const u8 *bssid, *ssid, *ie = NULL, *sae_data = NULL; + int err, ssid_len, ie_len = 0, sae_data_len = 0; enum nl80211_auth_type auth_type; struct key_parse key; bool local_state_change; @@ -4945,9 +5145,23 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) } auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); - if (!nl80211_valid_auth_type(auth_type)) + if (!nl80211_valid_auth_type(rdev, auth_type, NL80211_CMD_AUTHENTICATE)) + return -EINVAL; + + if (auth_type == NL80211_AUTHTYPE_SAE && + !info->attrs[NL80211_ATTR_SAE_DATA]) return -EINVAL; + if (info->attrs[NL80211_ATTR_SAE_DATA]) { + if (auth_type != NL80211_AUTHTYPE_SAE) + return -EINVAL; + sae_data = nla_data(info->attrs[NL80211_ATTR_SAE_DATA]); + sae_data_len = nla_len(info->attrs[NL80211_ATTR_SAE_DATA]); + /* need to include at least Auth Transaction and Status Code */ + if (sae_data_len < 4) + return -EINVAL; + } + local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; /* @@ -4959,7 +5173,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, ssid, ssid_len, ie, ie_len, - key.p.key, key.p.key_len, key.idx); + key.p.key, key.p.key_len, key.idx, + sae_data, sae_data_len); } static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, @@ -5250,8 +5465,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; - if (!info->attrs[NL80211_ATTR_WIPHY_FREQ] || - !info->attrs[NL80211_ATTR_SSID] || + if (!info->attrs[NL80211_ATTR_SSID] || !nla_len(info->attrs[NL80211_ATTR_SSID])) return -EINVAL; @@ -5286,34 +5500,17 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) ibss.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { - enum nl80211_channel_type channel_type; - - if (!nl80211_valid_channel_type(info, &channel_type)) - return -EINVAL; - - if (channel_type != NL80211_CHAN_NO_HT && - !(wiphy->features & NL80211_FEATURE_HT_IBSS)) - return -EINVAL; - - ibss.channel_type = channel_type; - } else { - ibss.channel_type = NL80211_CHAN_NO_HT; - } + err = nl80211_parse_chandef(rdev, info, &ibss.chandef); + if (err) + return err; - ibss.channel = rdev_freq_to_chan(rdev, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]), - ibss.channel_type); - if (!ibss.channel || - ibss.channel->flags & IEEE80211_CHAN_NO_IBSS || - ibss.channel->flags & IEEE80211_CHAN_DISABLED) + if (!cfg80211_reg_can_beacon(&rdev->wiphy, &ibss.chandef)) return -EINVAL; - /* Both channels should be able to initiate communication */ - if ((ibss.channel_type == NL80211_CHAN_HT40PLUS || - ibss.channel_type == NL80211_CHAN_HT40MINUS) && - !cfg80211_can_beacon_sec_chan(&rdev->wiphy, ibss.channel, - ibss.channel_type)) + if (ibss.chandef.width > NL80211_CHAN_WIDTH_40) + return -EINVAL; + if (ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT && + !(rdev->wiphy.features & NL80211_FEATURE_HT_IBSS)) return -EINVAL; ibss.channel_fixed = !!info->attrs[NL80211_ATTR_FREQ_FIXED]; @@ -5325,7 +5522,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) int n_rates = nla_len(info->attrs[NL80211_ATTR_BSS_BASIC_RATES]); struct ieee80211_supported_band *sband = - wiphy->bands[ibss.channel->band]; + wiphy->bands[ibss.chandef.chan->band]; err = ieee80211_get_ratemask(sband, rates, n_rates, &ibss.basic_rates); @@ -5339,10 +5536,19 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) return -EINVAL; if (ibss.privacy && info->attrs[NL80211_ATTR_KEYS]) { + bool no_ht = false; + connkeys = nl80211_parse_connkeys(rdev, - info->attrs[NL80211_ATTR_KEYS]); + info->attrs[NL80211_ATTR_KEYS], + &no_ht); if (IS_ERR(connkeys)) return PTR_ERR(connkeys); + + if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) && + no_ht) { + kfree(connkeys); + return -EINVAL; + } } ibss.control_port = @@ -5368,6 +5574,36 @@ static int nl80211_leave_ibss(struct sk_buff *skb, struct genl_info *info) return cfg80211_leave_ibss(rdev, dev, false); } +static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + int mcast_rate[IEEE80211_NUM_BANDS]; + u32 nla_rate; + int err; + + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + return -EOPNOTSUPP; + + if (!rdev->ops->set_mcast_rate) + return -EOPNOTSUPP; + + memset(mcast_rate, 0, sizeof(mcast_rate)); + + if (!info->attrs[NL80211_ATTR_MCAST_RATE]) + return -EINVAL; + + nla_rate = nla_get_u32(info->attrs[NL80211_ATTR_MCAST_RATE]); + if (!nl80211_parse_mcast_rate(rdev, mcast_rate, nla_rate)) + return -EINVAL; + + err = rdev->ops->set_mcast_rate(&rdev->wiphy, dev, mcast_rate); + + return err; +} + + #ifdef CONFIG_NL80211_TESTMODE static struct genl_multicast_group nl80211_testmode_mcgrp = { .name = "testmode", @@ -5384,7 +5620,7 @@ static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) err = -EOPNOTSUPP; if (rdev->ops->testmode_cmd) { rdev->testmode_info = info; - err = rdev->ops->testmode_cmd(&rdev->wiphy, + err = rdev_testmode_cmd(rdev, nla_data(info->attrs[NL80211_ATTR_TESTDATA]), nla_len(info->attrs[NL80211_ATTR_TESTDATA])); rdev->testmode_info = NULL; @@ -5466,8 +5702,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, genlmsg_cancel(skb, hdr); break; } - err = rdev->ops->testmode_dump(&rdev->wiphy, skb, cb, - data, data_len); + err = rdev_testmode_dump(rdev, skb, cb, data, data_len); nla_nest_end(skb, tmdata); if (err == -ENOBUFS || err == -ENOENT) { @@ -5596,7 +5831,8 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_AUTH_TYPE]) { connect.auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); - if (!nl80211_valid_auth_type(connect.auth_type)) + if (!nl80211_valid_auth_type(rdev, connect.auth_type, + NL80211_CMD_CONNECT)) return -EINVAL; } else connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; @@ -5642,7 +5878,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (connect.privacy && info->attrs[NL80211_ATTR_KEYS]) { connkeys = nl80211_parse_connkeys(rdev, - info->attrs[NL80211_ATTR_KEYS]); + info->attrs[NL80211_ATTR_KEYS], NULL); if (IS_ERR(connkeys)) return PTR_ERR(connkeys); } @@ -5771,7 +6007,7 @@ static int nl80211_flush_pmksa(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->flush_pmksa) return -EOPNOTSUPP; - return rdev->ops->flush_pmksa(&rdev->wiphy, dev); + return rdev_flush_pmksa(rdev, dev); } static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) @@ -5798,10 +6034,10 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) status_code = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); dialog_token = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_DIALOG_TOKEN]); - return rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code, - dialog_token, status_code, - nla_data(info->attrs[NL80211_ATTR_IE]), - nla_len(info->attrs[NL80211_ATTR_IE])); + return rdev_tdls_mgmt(rdev, dev, peer, action_code, + dialog_token, status_code, + nla_data(info->attrs[NL80211_ATTR_IE]), + nla_len(info->attrs[NL80211_ATTR_IE])); } static int nl80211_tdls_oper(struct sk_buff *skb, struct genl_info *info) @@ -5822,7 +6058,7 @@ static int nl80211_tdls_oper(struct sk_buff *skb, struct genl_info *info) operation = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_OPERATION]); peer = nla_data(info->attrs[NL80211_ATTR_MAC]); - return rdev->ops->tdls_oper(&rdev->wiphy, dev, peer, operation); + return rdev_tdls_oper(rdev, dev, peer, operation); } static int nl80211_remain_on_channel(struct sk_buff *skb, @@ -5830,12 +6066,11 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev = info->user_ptr[1]; - struct ieee80211_channel *chan; + struct cfg80211_chan_def chandef; struct sk_buff *msg; void *hdr; u64 cookie; - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - u32 freq, duration; + u32 duration; int err; if (!info->attrs[NL80211_ATTR_WIPHY_FREQ] || @@ -5856,14 +6091,9 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, duration > rdev->wiphy.max_remain_on_channel_duration) return -EINVAL; - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && - !nl80211_valid_channel_type(info, &channel_type)) - return -EINVAL; - - freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); - chan = rdev_freq_to_chan(rdev, freq, channel_type); - if (chan == NULL) - return -EINVAL; + err = nl80211_parse_chandef(rdev, info, &chandef); + if (err) + return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -5877,8 +6107,8 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, goto free_msg; } - err = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan, - channel_type, duration, &cookie); + err = rdev_remain_on_channel(rdev, wdev, chandef.chan, + duration, &cookie); if (err) goto free_msg; @@ -5912,7 +6142,7 @@ static int nl80211_cancel_remain_on_channel(struct sk_buff *skb, cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); - return rdev->ops->cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); + return rdev_cancel_remain_on_channel(rdev, wdev, cookie); } static u32 rateset_to_mask(struct ieee80211_supported_band *sband, @@ -6055,7 +6285,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, } } - return rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, NULL, &mask); + return rdev_set_bitrate_mask(rdev, dev, NULL, &mask); } static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) @@ -6097,10 +6327,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev = info->user_ptr[1]; - struct ieee80211_channel *chan; - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - bool channel_type_valid = false; - u32 freq; + struct cfg80211_chan_def chandef; int err; void *hdr = NULL; u64 cookie; @@ -6110,8 +6337,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) dont_wait_for_ack = info->attrs[NL80211_ATTR_DONT_WAIT_FOR_ACK]; - if (!info->attrs[NL80211_ATTR_FRAME] || - !info->attrs[NL80211_ATTR_WIPHY_FREQ]) + if (!info->attrs[NL80211_ATTR_FRAME]) return -EINVAL; if (!rdev->ops->mgmt_tx) @@ -6146,12 +6372,6 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) } - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { - if (!nl80211_valid_channel_type(info, &channel_type)) - return -EINVAL; - channel_type_valid = true; - } - offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK]; if (offchan && !(rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX)) @@ -6159,10 +6379,9 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); - freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); - chan = rdev_freq_to_chan(rdev, freq, channel_type); - if (chan == NULL) - return -EINVAL; + err = nl80211_parse_chandef(rdev, info, &chandef); + if (err) + return err; if (!dont_wait_for_ack) { msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); @@ -6178,8 +6397,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) } } - err = cfg80211_mlme_mgmt_tx(rdev, wdev, chan, offchan, channel_type, - channel_type_valid, wait, + err = cfg80211_mlme_mgmt_tx(rdev, wdev, chandef.chan, offchan, wait, nla_data(info->attrs[NL80211_ATTR_FRAME]), nla_len(info->attrs[NL80211_ATTR_FRAME]), no_cck, dont_wait_for_ack, &cookie); @@ -6230,7 +6448,7 @@ static int nl80211_tx_mgmt_cancel_wait(struct sk_buff *skb, struct genl_info *in cookie = nla_get_u64(info->attrs[NL80211_ATTR_COOKIE]); - return rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); + return rdev_mgmt_tx_cancel_wait(rdev, wdev, cookie); } static int nl80211_set_power_save(struct sk_buff *skb, struct genl_info *info) @@ -6260,8 +6478,7 @@ static int nl80211_set_power_save(struct sk_buff *skb, struct genl_info *info) if (state == wdev->ps) return 0; - err = rdev->ops->set_power_mgmt(wdev->wiphy, dev, state, - wdev->ps_timeout); + err = rdev_set_power_mgmt(rdev, dev, state, wdev->ps_timeout); if (!err) wdev->ps = state; return err; @@ -6322,14 +6539,13 @@ nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] __read_mostly = { }; static int nl80211_set_cqm_txe(struct genl_info *info, - u32 rate, u32 pkts, u32 intvl) + u32 rate, u32 pkts, u32 intvl) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev; struct net_device *dev = info->user_ptr[1]; - if ((rate < 0 || rate > 100) || - (intvl < 0 || intvl > NL80211_CQM_TXE_MAX_INTVL)) + if (rate > 100 || intvl > NL80211_CQM_TXE_MAX_INTVL) return -EINVAL; wdev = dev->ieee80211_ptr; @@ -6341,8 +6557,7 @@ static int nl80211_set_cqm_txe(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; - return rdev->ops->set_cqm_txe_config(wdev->wiphy, dev, - rate, pkts, intvl); + return rdev_set_cqm_txe_config(rdev, dev, rate, pkts, intvl); } static int nl80211_set_cqm_rssi(struct genl_info *info, @@ -6364,8 +6579,7 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; - return rdev->ops->set_cqm_rssi_config(wdev->wiphy, dev, - threshold, hysteresis); + return rdev_set_cqm_rssi_config(rdev, dev, threshold, hysteresis); } static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info) @@ -6446,21 +6660,12 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE] && - !nl80211_valid_channel_type(info, &channel_type)) - return -EINVAL; - - setup.channel = rdev_freq_to_chan(rdev, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]), - channel_type); - if (!setup.channel) - return -EINVAL; - setup.channel_type = channel_type; + err = nl80211_parse_chandef(rdev, info, &setup.chandef); + if (err) + return err; } else { /* cfg80211_join_mesh() will sort it out */ - setup.channel = NULL; + setup.chandef.chan = NULL; } return cfg80211_join_mesh(rdev, dev, &setup, &cfg); @@ -6690,7 +6895,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) set_wakeup: if (rdev->ops->set_wakeup && prev_enabled != !!rdev->wowlan) - rdev->ops->set_wakeup(&rdev->wiphy, rdev->wowlan); + rdev_set_wakeup(rdev, rdev->wowlan); return 0; error: @@ -6746,7 +6951,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) goto out; } - err = rdev->ops->set_rekey_data(&rdev->wiphy, dev, &rekey_data); + err = rdev_set_rekey_data(rdev, dev, &rekey_data); out: wdev_unlock(wdev); return err; @@ -6805,7 +7010,7 @@ static int nl80211_probe_client(struct sk_buff *skb, addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - err = rdev->ops->probe_client(&rdev->wiphy, dev, addr, &cookie); + err = rdev_probe_client(rdev, dev, addr, &cookie); if (err) goto free_msg; @@ -6826,16 +7031,35 @@ static int nl80211_probe_client(struct sk_buff *skb, static int nl80211_register_beacons(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_beacon_registration *reg, *nreg; + int rv; if (!(rdev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS)) return -EOPNOTSUPP; - if (rdev->ap_beacons_nlportid) - return -EBUSY; + nreg = kzalloc(sizeof(*nreg), GFP_KERNEL); + if (!nreg) + return -ENOMEM; + + /* First, check if already registered. */ + spin_lock_bh(&rdev->beacon_registrations_lock); + list_for_each_entry(reg, &rdev->beacon_registrations, list) { + if (reg->nlportid == info->snd_portid) { + rv = -EALREADY; + goto out_err; + } + } + /* Add it to the list */ + nreg->nlportid = info->snd_portid; + list_add(&nreg->list, &rdev->beacon_registrations); - rdev->ap_beacons_nlportid = info->snd_portid; + spin_unlock_bh(&rdev->beacon_registrations_lock); return 0; +out_err: + spin_unlock_bh(&rdev->beacon_registrations_lock); + kfree(nreg); + return rv; } static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info) @@ -6859,7 +7083,7 @@ static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info) if (err) return err; - err = rdev->ops->start_p2p_device(&rdev->wiphy, wdev); + err = rdev_start_p2p_device(rdev, wdev); if (err) return err; @@ -6885,7 +7109,7 @@ static int nl80211_stop_p2p_device(struct sk_buff *skb, struct genl_info *info) if (!wdev->p2p_started) return 0; - rdev->ops->stop_p2p_device(&rdev->wiphy, wdev); + rdev_stop_p2p_device(rdev, wdev); wdev->p2p_started = false; mutex_lock(&rdev->devlist_mtx); @@ -7552,6 +7776,14 @@ static struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_WDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_MCAST_RATE, + .doit = nl80211_set_mcast_rate, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { @@ -7622,6 +7854,9 @@ static int nl80211_add_scan_req(struct sk_buff *msg, nla_put(msg, NL80211_ATTR_IE, req->ie_len, req->ie)) goto nla_put_failure; + if (req->flags) + nla_put_u32(msg, NL80211_ATTR_SCAN_FLAGS, req->flags); + return 0; nla_put_failure: return -ENOBUFS; @@ -8250,7 +8485,6 @@ static void nl80211_send_remain_on_chan_event( int cmd, struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp) { struct sk_buff *msg; @@ -8271,7 +8505,8 @@ static void nl80211_send_remain_on_chan_event( wdev->netdev->ifindex)) || nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id(wdev)) || nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, chan->center_freq) || - nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, channel_type) || + nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, + NL80211_CHAN_NO_HT) || nla_put_u64(msg, NL80211_ATTR_COOKIE, cookie)) goto nla_put_failure; @@ -8293,23 +8528,20 @@ static void nl80211_send_remain_on_chan_event( void nl80211_send_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp) { nl80211_send_remain_on_chan_event(NL80211_CMD_REMAIN_ON_CHANNEL, rdev, wdev, cookie, chan, - channel_type, duration, gfp); + duration, gfp); } void nl80211_send_remain_on_channel_cancel( struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, - u64 cookie, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, gfp_t gfp) + u64 cookie, struct ieee80211_channel *chan, gfp_t gfp) { nl80211_send_remain_on_chan_event(NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, - rdev, wdev, cookie, chan, - channel_type, 0, gfp); + rdev, wdev, cookie, chan, 0, gfp); } void nl80211_send_sta_event(struct cfg80211_registered_device *rdev, @@ -8665,8 +8897,8 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, } void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, - struct net_device *netdev, int freq, - enum nl80211_channel_type type, gfp_t gfp) + struct net_device *netdev, + struct cfg80211_chan_def *chandef, gfp_t gfp) { struct sk_buff *msg; void *hdr; @@ -8681,9 +8913,10 @@ void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, return; } - if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || - nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq) || - nla_put_u32(msg, NL80211_ATTR_WIPHY_CHANNEL_TYPE, type)) + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + if (nl80211_send_chandef(msg, chandef)) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -8800,7 +9033,10 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, void *hdr; int err; + trace_cfg80211_probe_status(dev, addr, cookie, acked); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) return; @@ -8835,44 +9071,96 @@ EXPORT_SYMBOL(cfg80211_probe_status); void cfg80211_report_obss_beacon(struct wiphy *wiphy, const u8 *frame, size_t len, - int freq, int sig_dbm, gfp_t gfp) + int freq, int sig_dbm) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); struct sk_buff *msg; void *hdr; - u32 nlportid = ACCESS_ONCE(rdev->ap_beacons_nlportid); + struct cfg80211_beacon_registration *reg; - if (!nlportid) - return; + trace_cfg80211_report_obss_beacon(wiphy, frame, len, freq, sig_dbm); + + spin_lock_bh(&rdev->beacon_registrations_lock); + list_for_each_entry(reg, &rdev->beacon_registrations, list) { + msg = nlmsg_new(len + 100, GFP_ATOMIC); + if (!msg) { + spin_unlock_bh(&rdev->beacon_registrations_lock); + return; + } + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_FRAME); + if (!hdr) + goto nla_put_failure; - msg = nlmsg_new(len + 100, gfp); + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + (freq && + nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq)) || + (sig_dbm && + nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) || + nla_put(msg, NL80211_ATTR_FRAME, len, frame)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, reg->nlportid); + } + spin_unlock_bh(&rdev->beacon_registrations_lock); + return; + + nla_put_failure: + spin_unlock_bh(&rdev->beacon_registrations_lock); + if (hdr) + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_report_obss_beacon); + +void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer, + enum nl80211_tdls_operation oper, + u16 reason_code, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct sk_buff *msg; + void *hdr; + int err; + + trace_cfg80211_tdls_oper_request(wdev->wiphy, dev, peer, oper, + reason_code); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; - hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_FRAME); + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_TDLS_OPER); if (!hdr) { nlmsg_free(msg); return; } if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || - (freq && - nla_put_u32(msg, NL80211_ATTR_WIPHY_FREQ, freq)) || - (sig_dbm && - nla_put_u32(msg, NL80211_ATTR_RX_SIGNAL_DBM, sig_dbm)) || - nla_put(msg, NL80211_ATTR_FRAME, len, frame)) + nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put_u8(msg, NL80211_ATTR_TDLS_OPERATION, oper) || + nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, peer) || + (reason_code > 0 && + nla_put_u16(msg, NL80211_ATTR_REASON_CODE, reason_code))) goto nla_put_failure; - genlmsg_end(msg, hdr); + err = genlmsg_end(msg, hdr); + if (err < 0) { + nlmsg_free(msg); + return; + } - genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); return; nla_put_failure: genlmsg_cancel(msg, hdr); nlmsg_free(msg); } -EXPORT_SYMBOL(cfg80211_report_obss_beacon); +EXPORT_SYMBOL(cfg80211_tdls_oper_request); static int nl80211_netlink_notify(struct notifier_block * nb, unsigned long state, @@ -8881,6 +9169,7 @@ static int nl80211_netlink_notify(struct notifier_block * nb, struct netlink_notify *notify = _notify; struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; + struct cfg80211_beacon_registration *reg, *tmp; if (state != NETLINK_URELEASE) return NOTIFY_DONE; @@ -8890,8 +9179,17 @@ static int nl80211_netlink_notify(struct notifier_block * nb, list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) { list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) cfg80211_mlme_unregister_socket(wdev, notify->portid); - if (rdev->ap_beacons_nlportid == notify->portid) - rdev->ap_beacons_nlportid = 0; + + spin_lock_bh(&rdev->beacon_registrations_lock); + list_for_each_entry_safe(reg, tmp, &rdev->beacon_registrations, + list) { + if (reg->nlportid == notify->portid) { + list_del(®->list); + kfree(reg); + break; + } + } + spin_unlock_bh(&rdev->beacon_registrations_lock); } rcu_read_unlock(); diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index f6153516068c..2acba8477e9d 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -76,13 +76,11 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, void nl80211_send_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, unsigned int duration, gfp_t gfp); void nl80211_send_remain_on_channel_cancel( struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, - u64 cookie, struct ieee80211_channel *chan, - enum nl80211_channel_type channel_type, gfp_t gfp); + u64 cookie, struct ieee80211_channel *chan, gfp_t gfp); void nl80211_send_sta_event(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *mac_addr, @@ -129,8 +127,8 @@ void nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, const u8 *bssid, bool preauth, gfp_t gfp); void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, - struct net_device *dev, int freq, - enum nl80211_channel_type type, gfp_t gfp); + struct net_device *dev, + struct cfg80211_chan_def *chandef, gfp_t gfp); bool nl80211_unexpected_frame(struct net_device *dev, const u8 *addr, gfp_t gfp); diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h new file mode 100644 index 000000000000..6c0c8191f837 --- /dev/null +++ b/net/wireless/rdev-ops.h @@ -0,0 +1,878 @@ +#ifndef __CFG80211_RDEV_OPS +#define __CFG80211_RDEV_OPS + +#include <linux/rtnetlink.h> +#include <net/cfg80211.h> +#include "core.h" +#include "trace.h" + +static inline int rdev_suspend(struct cfg80211_registered_device *rdev) +{ + int ret; + trace_rdev_suspend(&rdev->wiphy, rdev->wowlan); + ret = rdev->ops->suspend(&rdev->wiphy, rdev->wowlan); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_resume(struct cfg80211_registered_device *rdev) +{ + int ret; + trace_rdev_resume(&rdev->wiphy); + ret = rdev->ops->resume(&rdev->wiphy); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_set_wakeup(struct cfg80211_registered_device *rdev, + bool enabled) +{ + trace_rdev_set_wakeup(&rdev->wiphy, enabled); + rdev->ops->set_wakeup(&rdev->wiphy, enabled); + trace_rdev_return_void(&rdev->wiphy); +} + +static inline struct wireless_dev +*rdev_add_virtual_intf(struct cfg80211_registered_device *rdev, char *name, + enum nl80211_iftype type, u32 *flags, + struct vif_params *params) +{ + struct wireless_dev *ret; + trace_rdev_add_virtual_intf(&rdev->wiphy, name, type); + ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, type, flags, + params); + trace_rdev_return_wdev(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_del_virtual_intf(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + int ret; + trace_rdev_del_virtual_intf(&rdev->wiphy, wdev); + ret = rdev->ops->del_virtual_intf(&rdev->wiphy, wdev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_change_virtual_intf(struct cfg80211_registered_device *rdev, + struct net_device *dev, enum nl80211_iftype type, + u32 *flags, struct vif_params *params) +{ + int ret; + trace_rdev_change_virtual_intf(&rdev->wiphy, dev, type); + ret = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, type, flags, + params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_add_key(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u8 key_index, + bool pairwise, const u8 *mac_addr, + struct key_params *params) +{ + int ret; + trace_rdev_add_key(&rdev->wiphy, netdev, key_index, pairwise, mac_addr); + ret = rdev->ops->add_key(&rdev->wiphy, netdev, key_index, pairwise, + mac_addr, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_get_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, + u8 key_index, bool pairwise, const u8 *mac_addr, void *cookie, + void (*callback)(void *cookie, struct key_params*)) +{ + int ret; + trace_rdev_get_key(&rdev->wiphy, netdev, key_index, pairwise, mac_addr); + ret = rdev->ops->get_key(&rdev->wiphy, netdev, key_index, pairwise, + mac_addr, cookie, callback); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_del_key(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u8 key_index, + bool pairwise, const u8 *mac_addr) +{ + int ret; + trace_rdev_del_key(&rdev->wiphy, netdev, key_index, pairwise, mac_addr); + ret = rdev->ops->del_key(&rdev->wiphy, netdev, key_index, pairwise, + mac_addr); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_set_default_key(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u8 key_index, bool unicast, + bool multicast) +{ + int ret; + trace_rdev_set_default_key(&rdev->wiphy, netdev, key_index, + unicast, multicast); + ret = rdev->ops->set_default_key(&rdev->wiphy, netdev, key_index, + unicast, multicast); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_set_default_mgmt_key(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u8 key_index) +{ + int ret; + trace_rdev_set_default_mgmt_key(&rdev->wiphy, netdev, key_index); + ret = rdev->ops->set_default_mgmt_key(&rdev->wiphy, netdev, + key_index); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_start_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ap_settings *settings) +{ + int ret; + trace_rdev_start_ap(&rdev->wiphy, dev, settings); + ret = rdev->ops->start_ap(&rdev->wiphy, dev, settings); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_change_beacon(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_beacon_data *info) +{ + int ret; + trace_rdev_change_beacon(&rdev->wiphy, dev, info); + ret = rdev->ops->change_beacon(&rdev->wiphy, dev, info); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_stop_ap(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + int ret; + trace_rdev_stop_ap(&rdev->wiphy, dev); + ret = rdev->ops->stop_ap(&rdev->wiphy, dev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_add_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *mac, + struct station_parameters *params) +{ + int ret; + trace_rdev_add_station(&rdev->wiphy, dev, mac, params); + ret = rdev->ops->add_station(&rdev->wiphy, dev, mac, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_del_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *mac) +{ + int ret; + trace_rdev_del_station(&rdev->wiphy, dev, mac); + ret = rdev->ops->del_station(&rdev->wiphy, dev, mac); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_change_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *mac, + struct station_parameters *params) +{ + int ret; + trace_rdev_change_station(&rdev->wiphy, dev, mac, params); + ret = rdev->ops->change_station(&rdev->wiphy, dev, mac, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_get_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *mac, + struct station_info *sinfo) +{ + int ret; + trace_rdev_get_station(&rdev->wiphy, dev, mac); + ret = rdev->ops->get_station(&rdev->wiphy, dev, mac, sinfo); + trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); + return ret; +} + +static inline int rdev_dump_station(struct cfg80211_registered_device *rdev, + struct net_device *dev, int idx, u8 *mac, + struct station_info *sinfo) +{ + int ret; + trace_rdev_dump_station(&rdev->wiphy, dev, idx, mac); + ret = rdev->ops->dump_station(&rdev->wiphy, dev, idx, mac, sinfo); + trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); + return ret; +} + +static inline int rdev_add_mpath(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *dst, u8 *next_hop) +{ + int ret; + trace_rdev_add_mpath(&rdev->wiphy, dev, dst, next_hop); + ret = rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_del_mpath(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *dst) +{ + int ret; + trace_rdev_del_mpath(&rdev->wiphy, dev, dst); + ret = rdev->ops->del_mpath(&rdev->wiphy, dev, dst); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_change_mpath(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *dst, + u8 *next_hop) +{ + int ret; + trace_rdev_change_mpath(&rdev->wiphy, dev, dst, next_hop); + ret = rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_get_mpath(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *dst, u8 *next_hop, + struct mpath_info *pinfo) +{ + int ret; + trace_rdev_get_mpath(&rdev->wiphy, dev, dst, next_hop); + ret = rdev->ops->get_mpath(&rdev->wiphy, dev, dst, next_hop, pinfo); + trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); + return ret; + +} + +static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev, + struct net_device *dev, int idx, u8 *dst, + u8 *next_hop, struct mpath_info *pinfo) + +{ + int ret; + trace_rdev_dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop); + ret = rdev->ops->dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop, + pinfo); + trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); + return ret; +} + +static inline int +rdev_get_mesh_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, struct mesh_config *conf) +{ + int ret; + trace_rdev_get_mesh_config(&rdev->wiphy, dev); + ret = rdev->ops->get_mesh_config(&rdev->wiphy, dev, conf); + trace_rdev_return_int_mesh_config(&rdev->wiphy, ret, conf); + return ret; +} + +static inline int +rdev_update_mesh_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, u32 mask, + const struct mesh_config *nconf) +{ + int ret; + trace_rdev_update_mesh_config(&rdev->wiphy, dev, mask, nconf); + ret = rdev->ops->update_mesh_config(&rdev->wiphy, dev, mask, nconf); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_join_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev, + const struct mesh_config *conf, + const struct mesh_setup *setup) +{ + int ret; + trace_rdev_join_mesh(&rdev->wiphy, dev, conf, setup); + ret = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, setup); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + + +static inline int rdev_leave_mesh(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + int ret; + trace_rdev_leave_mesh(&rdev->wiphy, dev); + ret = rdev->ops->leave_mesh(&rdev->wiphy, dev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_change_bss(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct bss_parameters *params) + +{ + int ret; + trace_rdev_change_bss(&rdev->wiphy, dev, params); + ret = rdev->ops->change_bss(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_set_txq_params(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ieee80211_txq_params *params) + +{ + int ret; + trace_rdev_set_txq_params(&rdev->wiphy, dev, params); + ret = rdev->ops->set_txq_params(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_libertas_set_mesh_channel(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ieee80211_channel *chan) +{ + int ret; + trace_rdev_libertas_set_mesh_channel(&rdev->wiphy, dev, chan); + ret = rdev->ops->libertas_set_mesh_channel(&rdev->wiphy, dev, chan); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_set_monitor_channel(struct cfg80211_registered_device *rdev, + struct cfg80211_chan_def *chandef) +{ + int ret; + trace_rdev_set_monitor_channel(&rdev->wiphy, chandef); + ret = rdev->ops->set_monitor_channel(&rdev->wiphy, chandef); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_scan(struct cfg80211_registered_device *rdev, + struct cfg80211_scan_request *request) +{ + int ret; + trace_rdev_scan(&rdev->wiphy, request); + ret = rdev->ops->scan(&rdev->wiphy, request); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_auth(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_auth_request *req) +{ + int ret; + trace_rdev_auth(&rdev->wiphy, dev, req); + ret = rdev->ops->auth(&rdev->wiphy, dev, req); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_assoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_assoc_request *req) +{ + int ret; + trace_rdev_assoc(&rdev->wiphy, dev, req); + ret = rdev->ops->assoc(&rdev->wiphy, dev, req); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_deauth(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_deauth_request *req) +{ + int ret; + trace_rdev_deauth(&rdev->wiphy, dev, req); + ret = rdev->ops->deauth(&rdev->wiphy, dev, req); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_disassoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_disassoc_request *req) +{ + int ret; + trace_rdev_disassoc(&rdev->wiphy, dev, req); + ret = rdev->ops->disassoc(&rdev->wiphy, dev, req); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_connect(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_connect_params *sme) +{ + int ret; + trace_rdev_connect(&rdev->wiphy, dev, sme); + ret = rdev->ops->connect(&rdev->wiphy, dev, sme); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_disconnect(struct cfg80211_registered_device *rdev, + struct net_device *dev, u16 reason_code) +{ + int ret; + trace_rdev_disconnect(&rdev->wiphy, dev, reason_code); + ret = rdev->ops->disconnect(&rdev->wiphy, dev, reason_code); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_join_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ibss_params *params) +{ + int ret; + trace_rdev_join_ibss(&rdev->wiphy, dev, params); + ret = rdev->ops->join_ibss(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_leave_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + int ret; + trace_rdev_leave_ibss(&rdev->wiphy, dev); + ret = rdev->ops->leave_ibss(&rdev->wiphy, dev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, u32 changed) +{ + int ret; + trace_rdev_set_wiphy_params(&rdev->wiphy, changed); + ret = rdev->ops->set_wiphy_params(&rdev->wiphy, changed); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_set_tx_power(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + enum nl80211_tx_power_setting type, int mbm) +{ + int ret; + trace_rdev_set_tx_power(&rdev->wiphy, wdev, type, mbm); + ret = rdev->ops->set_tx_power(&rdev->wiphy, wdev, type, mbm); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, int *dbm) +{ + int ret; + trace_rdev_get_tx_power(&rdev->wiphy, wdev); + ret = rdev->ops->get_tx_power(&rdev->wiphy, wdev, dbm); + trace_rdev_return_int_int(&rdev->wiphy, ret, *dbm); + return ret; +} + +static inline int rdev_set_wds_peer(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *addr) +{ + int ret; + trace_rdev_set_wds_peer(&rdev->wiphy, dev, addr); + ret = rdev->ops->set_wds_peer(&rdev->wiphy, dev, addr); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_rfkill_poll(struct cfg80211_registered_device *rdev) +{ + trace_rdev_rfkill_poll(&rdev->wiphy); + rdev->ops->rfkill_poll(&rdev->wiphy); + trace_rdev_return_void(&rdev->wiphy); +} + + +#ifdef CONFIG_NL80211_TESTMODE +static inline int rdev_testmode_cmd(struct cfg80211_registered_device *rdev, + void *data, int len) +{ + int ret; + trace_rdev_testmode_cmd(&rdev->wiphy); + ret = rdev->ops->testmode_cmd(&rdev->wiphy, data, len); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_testmode_dump(struct cfg80211_registered_device *rdev, + struct sk_buff *skb, + struct netlink_callback *cb, void *data, + int len) +{ + int ret; + trace_rdev_testmode_dump(&rdev->wiphy); + ret = rdev->ops->testmode_dump(&rdev->wiphy, skb, cb, data, len); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} +#endif + +static inline int +rdev_set_bitrate_mask(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *peer, + const struct cfg80211_bitrate_mask *mask) +{ + int ret; + trace_rdev_set_bitrate_mask(&rdev->wiphy, dev, peer, mask); + ret = rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, peer, mask); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_dump_survey(struct cfg80211_registered_device *rdev, + struct net_device *netdev, int idx, + struct survey_info *info) +{ + int ret; + trace_rdev_dump_survey(&rdev->wiphy, netdev, idx); + ret = rdev->ops->dump_survey(&rdev->wiphy, netdev, idx, info); + if (ret < 0) + trace_rdev_return_int(&rdev->wiphy, ret); + else + trace_rdev_return_int_survey_info(&rdev->wiphy, ret, info); + return ret; +} + +static inline int rdev_set_pmksa(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + struct cfg80211_pmksa *pmksa) +{ + int ret; + trace_rdev_set_pmksa(&rdev->wiphy, netdev, pmksa); + ret = rdev->ops->set_pmksa(&rdev->wiphy, netdev, pmksa); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_del_pmksa(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + struct cfg80211_pmksa *pmksa) +{ + int ret; + trace_rdev_del_pmksa(&rdev->wiphy, netdev, pmksa); + ret = rdev->ops->del_pmksa(&rdev->wiphy, netdev, pmksa); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_flush_pmksa(struct cfg80211_registered_device *rdev, + struct net_device *netdev) +{ + int ret; + trace_rdev_flush_pmksa(&rdev->wiphy, netdev); + ret = rdev->ops->flush_pmksa(&rdev->wiphy, netdev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_remain_on_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct ieee80211_channel *chan, + unsigned int duration, u64 *cookie) +{ + int ret; + trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, duration); + ret = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan, + duration, cookie); + trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); + return ret; +} + +static inline int +rdev_cancel_remain_on_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, u64 cookie) +{ + int ret; + trace_rdev_cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); + ret = rdev->ops->cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct ieee80211_channel *chan, bool offchan, + unsigned int wait, const u8 *buf, size_t len, + bool no_cck, bool dont_wait_for_ack, u64 *cookie) +{ + int ret; + trace_rdev_mgmt_tx(&rdev->wiphy, wdev, chan, offchan, + wait, no_cck, dont_wait_for_ack); + ret = rdev->ops->mgmt_tx(&rdev->wiphy, wdev, chan, offchan, + wait, buf, len, no_cck, + dont_wait_for_ack, cookie); + trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); + return ret; +} + +static inline int +rdev_mgmt_tx_cancel_wait(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, u64 cookie) +{ + int ret; + trace_rdev_mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); + ret = rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_set_power_mgmt(struct cfg80211_registered_device *rdev, + struct net_device *dev, bool enabled, + int timeout) +{ + int ret; + trace_rdev_set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); + ret = rdev->ops->set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_set_cqm_rssi_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) +{ + int ret; + trace_rdev_set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, + rssi_hyst); + ret = rdev->ops->set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, + rssi_hyst); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_set_cqm_txe_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, u32 rate, u32 pkts, u32 intvl) +{ + int ret; + trace_rdev_set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, intvl); + ret = rdev->ops->set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, + intvl); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void +rdev_mgmt_frame_register(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, u16 frame_type, bool reg) +{ + trace_rdev_mgmt_frame_register(&rdev->wiphy, wdev , frame_type, reg); + rdev->ops->mgmt_frame_register(&rdev->wiphy, wdev , frame_type, reg); + trace_rdev_return_void(&rdev->wiphy); +} + +static inline int rdev_set_antenna(struct cfg80211_registered_device *rdev, + u32 tx_ant, u32 rx_ant) +{ + int ret; + trace_rdev_set_antenna(&rdev->wiphy, tx_ant, rx_ant); + ret = rdev->ops->set_antenna(&rdev->wiphy, tx_ant, rx_ant); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_get_antenna(struct cfg80211_registered_device *rdev, + u32 *tx_ant, u32 *rx_ant) +{ + int ret; + trace_rdev_get_antenna(&rdev->wiphy); + ret = rdev->ops->get_antenna(&rdev->wiphy, tx_ant, rx_ant); + if (ret) + trace_rdev_return_int(&rdev->wiphy, ret); + else + trace_rdev_return_int_tx_rx(&rdev->wiphy, ret, *tx_ant, + *rx_ant); + return ret; +} + +static inline int rdev_set_ringparam(struct cfg80211_registered_device *rdev, + u32 tx, u32 rx) +{ + int ret; + trace_rdev_set_ringparam(&rdev->wiphy, tx, rx); + ret = rdev->ops->set_ringparam(&rdev->wiphy, tx, rx); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_get_ringparam(struct cfg80211_registered_device *rdev, + u32 *tx, u32 *tx_max, u32 *rx, + u32 *rx_max) +{ + trace_rdev_get_ringparam(&rdev->wiphy); + rdev->ops->get_ringparam(&rdev->wiphy, tx, tx_max, rx, rx_max); + trace_rdev_return_void_tx_rx(&rdev->wiphy, *tx, *tx_max, *rx, *rx_max); +} + +static inline int +rdev_sched_scan_start(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_sched_scan_request *request) +{ + int ret; + trace_rdev_sched_scan_start(&rdev->wiphy, dev, request); + ret = rdev->ops->sched_scan_start(&rdev->wiphy, dev, request); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_sched_scan_stop(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + int ret; + trace_rdev_sched_scan_stop(&rdev->wiphy, dev); + ret = rdev->ops->sched_scan_stop(&rdev->wiphy, dev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_gtk_rekey_data *data) +{ + int ret; + trace_rdev_set_rekey_data(&rdev->wiphy, dev); + ret = rdev->ops->set_rekey_data(&rdev->wiphy, dev, data); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *peer, + u8 action_code, u8 dialog_token, + u16 status_code, const u8 *buf, size_t len) +{ + int ret; + trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, action_code, + dialog_token, status_code, buf, len); + ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code, + dialog_token, status_code, buf, len); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_tdls_oper(struct cfg80211_registered_device *rdev, + struct net_device *dev, u8 *peer, + enum nl80211_tdls_operation oper) +{ + int ret; + trace_rdev_tdls_oper(&rdev->wiphy, dev, peer, oper); + ret = rdev->ops->tdls_oper(&rdev->wiphy, dev, peer, oper); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_probe_client(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *peer, + u64 *cookie) +{ + int ret; + trace_rdev_probe_client(&rdev->wiphy, dev, peer); + ret = rdev->ops->probe_client(&rdev->wiphy, dev, peer, cookie); + trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); + return ret; +} + +static inline int rdev_set_noack_map(struct cfg80211_registered_device *rdev, + struct net_device *dev, u16 noack_map) +{ + int ret; + trace_rdev_set_noack_map(&rdev->wiphy, dev, noack_map); + ret = rdev->ops->set_noack_map(&rdev->wiphy, dev, noack_map); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int +rdev_get_et_sset_count(struct cfg80211_registered_device *rdev, + struct net_device *dev, int sset) +{ + int ret; + trace_rdev_get_et_sset_count(&rdev->wiphy, dev, sset); + ret = rdev->ops->get_et_sset_count(&rdev->wiphy, dev, sset); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_get_et_stats(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + trace_rdev_get_et_stats(&rdev->wiphy, dev); + rdev->ops->get_et_stats(&rdev->wiphy, dev, stats, data); + trace_rdev_return_void(&rdev->wiphy); +} + +static inline void rdev_get_et_strings(struct cfg80211_registered_device *rdev, + struct net_device *dev, u32 sset, + u8 *data) +{ + trace_rdev_get_et_strings(&rdev->wiphy, dev, sset); + rdev->ops->get_et_strings(&rdev->wiphy, dev, sset, data); + trace_rdev_return_void(&rdev->wiphy); +} + +static inline int +rdev_get_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_chan_def *chandef) +{ + int ret; + + trace_rdev_get_channel(&rdev->wiphy, wdev); + ret = rdev->ops->get_channel(&rdev->wiphy, wdev, chandef); + trace_rdev_return_chandef(&rdev->wiphy, ret, chandef); + + return ret; +} + +static inline int rdev_start_p2p_device(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + int ret; + + trace_rdev_start_p2p_device(&rdev->wiphy, wdev); + ret = rdev->ops->start_p2p_device(&rdev->wiphy, wdev); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline void rdev_stop_p2p_device(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + trace_rdev_stop_p2p_device(&rdev->wiphy, wdev); + rdev->ops->stop_p2p_device(&rdev->wiphy, wdev); + trace_rdev_return_void(&rdev->wiphy); +} +#endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3b8cbbc214db..82c4fc7c994c 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -141,9 +141,8 @@ static const struct ieee80211_regdomain world_regdom = { .reg_rules = { /* IEEE 802.11b/g, channels 1..11 */ REG_RULE(2412-10, 2462+10, 40, 6, 20, 0), - /* IEEE 802.11b/g, channels 12..13. No HT40 - * channel fits here. */ - REG_RULE(2467-10, 2472+10, 20, 6, 20, + /* IEEE 802.11b/g, channels 12..13. */ + REG_RULE(2467-10, 2472+10, 40, 6, 20, NL80211_RRF_PASSIVE_SCAN | NL80211_RRF_NO_IBSS), /* IEEE 802.11 channel 14 - Only JP enables @@ -908,7 +907,7 @@ static void handle_channel(struct wiphy *wiphy, map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = chan->orig_mag = (int) MBI_TO_DBI(power_rule->max_antenna_gain); - chan->max_power = chan->orig_mpwr = + chan->max_reg_power = chan->max_power = chan->orig_mpwr = (int) MBM_TO_DBM(power_rule->max_eirp); return; } @@ -1331,7 +1330,8 @@ static void handle_channel_custom(struct wiphy *wiphy, chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = (int) MBI_TO_DBI(power_rule->max_antenna_gain); - chan->max_power = (int) MBM_TO_DBM(power_rule->max_eirp); + chan->max_reg_power = chan->max_power = + (int) MBM_TO_DBM(power_rule->max_eirp); } static void handle_band_custom(struct wiphy *wiphy, enum ieee80211_band band, @@ -1796,7 +1796,7 @@ EXPORT_SYMBOL(regulatory_hint); */ void regulatory_hint_11d(struct wiphy *wiphy, enum ieee80211_band band, - u8 *country_ie, + const u8 *country_ie, u8 country_ie_len) { char alpha2[2]; @@ -2365,7 +2365,6 @@ int set_regdom(const struct ieee80211_regdomain *rd) return r; } -#ifdef CONFIG_HOTPLUG int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) { if (last_request && !last_request->processed) { @@ -2377,12 +2376,6 @@ int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } -#else -int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - return -ENODEV; -} -#endif /* CONFIG_HOTPLUG */ void wiphy_regulatory_register(struct wiphy *wiphy) { diff --git a/net/wireless/reg.h b/net/wireless/reg.h index f023c8a31c60..4c0a32ffd530 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -81,7 +81,7 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy, */ void regulatory_hint_11d(struct wiphy *wiphy, enum ieee80211_band band, - u8 *country_ie, + const u8 *country_ie, u8 country_ie_len); /** diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 9730c9862bdc..01592d7d4789 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -17,9 +17,63 @@ #include "core.h" #include "nl80211.h" #include "wext-compat.h" +#include "rdev-ops.h" #define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) +static void bss_release(struct kref *ref) +{ + struct cfg80211_bss_ies *ies; + struct cfg80211_internal_bss *bss; + + bss = container_of(ref, struct cfg80211_internal_bss, ref); + + if (WARN_ON(atomic_read(&bss->hold))) + return; + + if (bss->pub.free_priv) + bss->pub.free_priv(&bss->pub); + + ies = (void *)rcu_access_pointer(bss->pub.beacon_ies); + if (ies) + kfree_rcu(ies, rcu_head); + ies = (void *)rcu_access_pointer(bss->pub.proberesp_ies); + if (ies) + kfree_rcu(ies, rcu_head); + + kfree(bss); +} + +/* must hold dev->bss_lock! */ +static void __cfg80211_unlink_bss(struct cfg80211_registered_device *dev, + struct cfg80211_internal_bss *bss) +{ + list_del_init(&bss->list); + rb_erase(&bss->rbn, &dev->bss_tree); + kref_put(&bss->ref, bss_release); +} + +/* must hold dev->bss_lock! */ +static void __cfg80211_bss_expire(struct cfg80211_registered_device *dev, + unsigned long expire_time) +{ + struct cfg80211_internal_bss *bss, *tmp; + bool expired = false; + + list_for_each_entry_safe(bss, tmp, &dev->bss_list, list) { + if (atomic_read(&bss->hold)) + continue; + if (!time_after(expire_time, bss->ts)) + continue; + + __cfg80211_unlink_bss(dev, bss); + expired = true; + } + + if (expired) + dev->bss_generation++; +} + void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) { struct cfg80211_scan_request *request; @@ -45,10 +99,17 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) if (wdev->netdev) cfg80211_sme_scan_done(wdev->netdev); - if (request->aborted) + if (request->aborted) { nl80211_send_scan_aborted(rdev, wdev); - else + } else { + if (request->flags & NL80211_SCAN_FLAG_FLUSH) { + /* flush entries from previous scans */ + spin_lock_bh(&rdev->bss_lock); + __cfg80211_bss_expire(rdev, request->scan_start); + spin_unlock_bh(&rdev->bss_lock); + } nl80211_send_scan_done(rdev, wdev); + } #ifdef CONFIG_CFG80211_WEXT if (wdev->netdev && !request->aborted) { @@ -89,6 +150,7 @@ void __cfg80211_scan_done(struct work_struct *wk) void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) { + trace_cfg80211_scan_done(request, aborted); WARN_ON(request != wiphy_to_dev(request->wiphy)->scan_req); request->aborted = aborted; @@ -99,22 +161,34 @@ EXPORT_SYMBOL(cfg80211_scan_done); void __cfg80211_sched_scan_results(struct work_struct *wk) { struct cfg80211_registered_device *rdev; + struct cfg80211_sched_scan_request *request; rdev = container_of(wk, struct cfg80211_registered_device, sched_scan_results_wk); + request = rdev->sched_scan_req; + mutex_lock(&rdev->sched_scan_mtx); /* we don't have sched_scan_req anymore if the scan is stopping */ - if (rdev->sched_scan_req) - nl80211_send_sched_scan_results(rdev, - rdev->sched_scan_req->dev); + if (request) { + if (request->flags & NL80211_SCAN_FLAG_FLUSH) { + /* flush entries from previous scans */ + spin_lock_bh(&rdev->bss_lock); + __cfg80211_bss_expire(rdev, request->scan_start); + spin_unlock_bh(&rdev->bss_lock); + request->scan_start = + jiffies + msecs_to_jiffies(request->interval); + } + nl80211_send_sched_scan_results(rdev, request->dev); + } mutex_unlock(&rdev->sched_scan_mtx); } void cfg80211_sched_scan_results(struct wiphy *wiphy) { + trace_cfg80211_sched_scan_results(wiphy); /* ignore if we're not scanning */ if (wiphy_to_dev(wiphy)->sched_scan_req) queue_work(cfg80211_wq, @@ -126,6 +200,8 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + trace_cfg80211_sched_scan_stopped(wiphy); + mutex_lock(&rdev->sched_scan_mtx); __cfg80211_stop_sched_scan(rdev, true); mutex_unlock(&rdev->sched_scan_mtx); @@ -145,7 +221,7 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, dev = rdev->sched_scan_req->dev; if (!driver_initiated) { - int err = rdev->ops->sched_scan_stop(&rdev->wiphy, dev); + int err = rdev_sched_scan_stop(rdev, dev); if (err) return err; } @@ -158,24 +234,6 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, return 0; } -static void bss_release(struct kref *ref) -{ - struct cfg80211_internal_bss *bss; - - bss = container_of(ref, struct cfg80211_internal_bss, ref); - if (bss->pub.free_priv) - bss->pub.free_priv(&bss->pub); - - if (bss->beacon_ies_allocated) - kfree(bss->pub.beacon_ies); - if (bss->proberesp_ies_allocated) - kfree(bss->pub.proberesp_ies); - - BUG_ON(atomic_read(&bss->hold)); - - kfree(bss); -} - /* must hold dev->bss_lock! */ void cfg80211_bss_age(struct cfg80211_registered_device *dev, unsigned long age_secs) @@ -183,37 +241,13 @@ void cfg80211_bss_age(struct cfg80211_registered_device *dev, struct cfg80211_internal_bss *bss; unsigned long age_jiffies = msecs_to_jiffies(age_secs * MSEC_PER_SEC); - list_for_each_entry(bss, &dev->bss_list, list) { + list_for_each_entry(bss, &dev->bss_list, list) bss->ts -= age_jiffies; - } -} - -/* must hold dev->bss_lock! */ -static void __cfg80211_unlink_bss(struct cfg80211_registered_device *dev, - struct cfg80211_internal_bss *bss) -{ - list_del_init(&bss->list); - rb_erase(&bss->rbn, &dev->bss_tree); - kref_put(&bss->ref, bss_release); } -/* must hold dev->bss_lock! */ void cfg80211_bss_expire(struct cfg80211_registered_device *dev) { - struct cfg80211_internal_bss *bss, *tmp; - bool expired = false; - - list_for_each_entry_safe(bss, tmp, &dev->bss_list, list) { - if (atomic_read(&bss->hold)) - continue; - if (!time_after(jiffies, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE)) - continue; - __cfg80211_unlink_bss(dev, bss); - expired = true; - } - - if (expired) - dev->bss_generation++; + __cfg80211_bss_expire(dev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE); } const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len) @@ -257,7 +291,7 @@ const u8 *cfg80211_find_vendor_ie(unsigned int oui, u8 oui_type, } EXPORT_SYMBOL(cfg80211_find_vendor_ie); -static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) +static int cmp_ies(u8 num, const u8 *ies1, int len1, const u8 *ies2, int len2) { const u8 *ie1 = cfg80211_find_ie(num, ies1, len1); const u8 *ie2 = cfg80211_find_ie(num, ies2, len2); @@ -277,10 +311,10 @@ static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) return memcmp(ie1 + 2, ie2 + 2, ie1[1]); } -static bool is_bss(struct cfg80211_bss *a, - const u8 *bssid, +static bool is_bss(struct cfg80211_bss *a, const u8 *bssid, const u8 *ssid, size_t ssid_len) { + const struct cfg80211_bss_ies *ies; const u8 *ssidie; if (bssid && !ether_addr_equal(a->bssid, bssid)) @@ -289,9 +323,10 @@ static bool is_bss(struct cfg80211_bss *a, if (!ssid) return true; - ssidie = cfg80211_find_ie(WLAN_EID_SSID, - a->information_elements, - a->len_information_elements); + ies = rcu_access_pointer(a->ies); + if (!ies) + return false; + ssidie = cfg80211_find_ie(WLAN_EID_SSID, ies->data, ies->len); if (!ssidie) return false; if (ssidie[1] != ssid_len) @@ -301,20 +336,21 @@ static bool is_bss(struct cfg80211_bss *a, static bool is_mesh_bss(struct cfg80211_bss *a) { + const struct cfg80211_bss_ies *ies; const u8 *ie; if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability)) return false; - ie = cfg80211_find_ie(WLAN_EID_MESH_ID, - a->information_elements, - a->len_information_elements); + ies = rcu_access_pointer(a->ies); + if (!ies) + return false; + + ie = cfg80211_find_ie(WLAN_EID_MESH_ID, ies->data, ies->len); if (!ie) return false; - ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, - a->information_elements, - a->len_information_elements); + ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, ies->data, ies->len); if (!ie) return false; @@ -325,14 +361,17 @@ static bool is_mesh(struct cfg80211_bss *a, const u8 *meshid, size_t meshidlen, const u8 *meshcfg) { + const struct cfg80211_bss_ies *ies; const u8 *ie; if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability)) return false; - ie = cfg80211_find_ie(WLAN_EID_MESH_ID, - a->information_elements, - a->len_information_elements); + ies = rcu_access_pointer(a->ies); + if (!ies) + return false; + + ie = cfg80211_find_ie(WLAN_EID_MESH_ID, ies->data, ies->len); if (!ie) return false; if (ie[1] != meshidlen) @@ -340,9 +379,7 @@ static bool is_mesh(struct cfg80211_bss *a, if (memcmp(ie + 2, meshid, meshidlen)) return false; - ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, - a->information_elements, - a->len_information_elements); + ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, ies->data, ies->len); if (!ie) return false; if (ie[1] != sizeof(struct ieee80211_meshconf_ie)) @@ -354,30 +391,33 @@ static bool is_mesh(struct cfg80211_bss *a, * part in the same mesh. */ return memcmp(ie + 2, meshcfg, - sizeof(struct ieee80211_meshconf_ie) - 2) == 0; + sizeof(struct ieee80211_meshconf_ie) - 2) == 0; } -static int cmp_bss_core(struct cfg80211_bss *a, - struct cfg80211_bss *b) +static int cmp_bss_core(struct cfg80211_bss *a, struct cfg80211_bss *b) { + const struct cfg80211_bss_ies *a_ies, *b_ies; int r; if (a->channel != b->channel) return b->channel->center_freq - a->channel->center_freq; if (is_mesh_bss(a) && is_mesh_bss(b)) { + a_ies = rcu_access_pointer(a->ies); + if (!a_ies) + return -1; + b_ies = rcu_access_pointer(b->ies); + if (!b_ies) + return 1; + r = cmp_ies(WLAN_EID_MESH_ID, - a->information_elements, - a->len_information_elements, - b->information_elements, - b->len_information_elements); + a_ies->data, a_ies->len, + b_ies->data, b_ies->len); if (r) return r; return cmp_ies(WLAN_EID_MESH_CONFIG, - a->information_elements, - a->len_information_elements, - b->information_elements, - b->len_information_elements); + a_ies->data, a_ies->len, + b_ies->data, b_ies->len); } /* @@ -390,22 +430,28 @@ static int cmp_bss_core(struct cfg80211_bss *a, static int cmp_bss(struct cfg80211_bss *a, struct cfg80211_bss *b) { + const struct cfg80211_bss_ies *a_ies, *b_ies; int r; r = cmp_bss_core(a, b); if (r) return r; + a_ies = rcu_access_pointer(a->ies); + if (!a_ies) + return -1; + b_ies = rcu_access_pointer(b->ies); + if (!b_ies) + return 1; + return cmp_ies(WLAN_EID_SSID, - a->information_elements, - a->len_information_elements, - b->information_elements, - b->len_information_elements); + a_ies->data, a_ies->len, + b_ies->data, b_ies->len); } -static int cmp_hidden_bss(struct cfg80211_bss *a, - struct cfg80211_bss *b) +static int cmp_hidden_bss(struct cfg80211_bss *a, struct cfg80211_bss *b) { + const struct cfg80211_bss_ies *a_ies, *b_ies; const u8 *ie1; const u8 *ie2; int i; @@ -415,17 +461,26 @@ static int cmp_hidden_bss(struct cfg80211_bss *a, if (r) return r; - ie1 = cfg80211_find_ie(WLAN_EID_SSID, - a->information_elements, - a->len_information_elements); - ie2 = cfg80211_find_ie(WLAN_EID_SSID, - b->information_elements, - b->len_information_elements); + a_ies = rcu_access_pointer(a->ies); + if (!a_ies) + return -1; + b_ies = rcu_access_pointer(b->ies); + if (!b_ies) + return 1; + + ie1 = cfg80211_find_ie(WLAN_EID_SSID, a_ies->data, a_ies->len); + ie2 = cfg80211_find_ie(WLAN_EID_SSID, b_ies->data, b_ies->len); - /* Key comparator must use same algorithm in any rb-tree + /* + * Key comparator must use same algorithm in any rb-tree * search function (order is important), otherwise ordering * of items in the tree is broken and search gives incorrect - * results. This code uses same order as cmp_ies() does. */ + * results. This code uses same order as cmp_ies() does. + * + * Note that due to the differring behaviour with hidden SSIDs + * this function only works when "b" is the tree element and + * "a" is the key we're looking for. + */ /* sort missing IE before (left of) present IE */ if (!ie1) @@ -441,10 +496,14 @@ static int cmp_hidden_bss(struct cfg80211_bss *a, if (ie1[1] != ie2[1]) return ie2[1] - ie1[1]; - /* zeroed SSID ie is another indication of a hidden bss */ + /* + * zeroed SSID ie is another indication of a hidden bss; + * if it isn't zeroed just return the regular sort value + * to find the next candidate + */ for (i = 0; i < ie2[1]; i++) if (ie2[i + 2]) - return -1; + return memcmp(ie1 + 2, ie2 + 2, ie1[1]); return 0; } @@ -459,6 +518,9 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, struct cfg80211_internal_bss *bss, *res = NULL; unsigned long now = jiffies; + trace_cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, capa_mask, + capa_val); + spin_lock_bh(&dev->bss_lock); list_for_each_entry(bss, &dev->bss_list, list) { @@ -480,6 +542,7 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, spin_unlock_bh(&dev->bss_lock); if (!res) return NULL; + trace_cfg80211_return_bss(&res->pub); return &res->pub; } EXPORT_SYMBOL(cfg80211_get_bss); @@ -566,7 +629,7 @@ rb_find_bss(struct cfg80211_registered_device *dev, static struct cfg80211_internal_bss * rb_find_hidden_bss(struct cfg80211_registered_device *dev, - struct cfg80211_internal_bss *res) + struct cfg80211_internal_bss *res) { struct rb_node *n = dev->bss_tree.rb_node; struct cfg80211_internal_bss *bss; @@ -589,127 +652,86 @@ rb_find_hidden_bss(struct cfg80211_registered_device *dev, static void copy_hidden_ies(struct cfg80211_internal_bss *res, - struct cfg80211_internal_bss *hidden) + struct cfg80211_internal_bss *hidden) { - if (unlikely(res->pub.beacon_ies)) - return; - if (WARN_ON(!hidden->pub.beacon_ies)) + const struct cfg80211_bss_ies *ies; + + if (rcu_access_pointer(res->pub.beacon_ies)) return; - res->pub.beacon_ies = kmalloc(hidden->pub.len_beacon_ies, GFP_ATOMIC); - if (unlikely(!res->pub.beacon_ies)) + ies = rcu_access_pointer(hidden->pub.beacon_ies); + if (WARN_ON(!ies)) return; - res->beacon_ies_allocated = true; - res->pub.len_beacon_ies = hidden->pub.len_beacon_ies; - memcpy(res->pub.beacon_ies, hidden->pub.beacon_ies, - res->pub.len_beacon_ies); + ies = kmemdup(ies, sizeof(*ies) + ies->len, GFP_ATOMIC); + if (unlikely(!ies)) + return; + rcu_assign_pointer(res->pub.beacon_ies, ies); } static struct cfg80211_internal_bss * cfg80211_bss_update(struct cfg80211_registered_device *dev, - struct cfg80211_internal_bss *res) + struct cfg80211_internal_bss *tmp) { struct cfg80211_internal_bss *found = NULL; - /* - * The reference to "res" is donated to this function. - */ - - if (WARN_ON(!res->pub.channel)) { - kref_put(&res->ref, bss_release); + if (WARN_ON(!tmp->pub.channel)) return NULL; - } - res->ts = jiffies; + tmp->ts = jiffies; spin_lock_bh(&dev->bss_lock); - found = rb_find_bss(dev, res); + if (WARN_ON(!rcu_access_pointer(tmp->pub.ies))) { + spin_unlock_bh(&dev->bss_lock); + return NULL; + } + + found = rb_find_bss(dev, tmp); if (found) { - found->pub.beacon_interval = res->pub.beacon_interval; - found->pub.tsf = res->pub.tsf; - found->pub.signal = res->pub.signal; - found->pub.capability = res->pub.capability; - found->ts = res->ts; + found->pub.beacon_interval = tmp->pub.beacon_interval; + found->pub.tsf = tmp->pub.tsf; + found->pub.signal = tmp->pub.signal; + found->pub.capability = tmp->pub.capability; + found->ts = tmp->ts; /* Update IEs */ - if (res->pub.proberesp_ies) { - size_t used = dev->wiphy.bss_priv_size + sizeof(*res); - size_t ielen = res->pub.len_proberesp_ies; - - if (found->pub.proberesp_ies && - !found->proberesp_ies_allocated && - ksize(found) >= used + ielen) { - memcpy(found->pub.proberesp_ies, - res->pub.proberesp_ies, ielen); - found->pub.len_proberesp_ies = ielen; - } else { - u8 *ies = found->pub.proberesp_ies; - - if (found->proberesp_ies_allocated) - ies = krealloc(ies, ielen, GFP_ATOMIC); - else - ies = kmalloc(ielen, GFP_ATOMIC); - - if (ies) { - memcpy(ies, res->pub.proberesp_ies, - ielen); - found->proberesp_ies_allocated = true; - found->pub.proberesp_ies = ies; - found->pub.len_proberesp_ies = ielen; - } - } + if (rcu_access_pointer(tmp->pub.proberesp_ies)) { + const struct cfg80211_bss_ies *old; + + old = rcu_access_pointer(found->pub.proberesp_ies); + rcu_assign_pointer(found->pub.proberesp_ies, + tmp->pub.proberesp_ies); /* Override possible earlier Beacon frame IEs */ - found->pub.information_elements = - found->pub.proberesp_ies; - found->pub.len_information_elements = - found->pub.len_proberesp_ies; - } - if (res->pub.beacon_ies) { - size_t used = dev->wiphy.bss_priv_size + sizeof(*res); - size_t ielen = res->pub.len_beacon_ies; - bool information_elements_is_beacon_ies = - (found->pub.information_elements == - found->pub.beacon_ies); - - if (found->pub.beacon_ies && - !found->beacon_ies_allocated && - ksize(found) >= used + ielen) { - memcpy(found->pub.beacon_ies, - res->pub.beacon_ies, ielen); - found->pub.len_beacon_ies = ielen; - } else { - u8 *ies = found->pub.beacon_ies; - - if (found->beacon_ies_allocated) - ies = krealloc(ies, ielen, GFP_ATOMIC); - else - ies = kmalloc(ielen, GFP_ATOMIC); - - if (ies) { - memcpy(ies, res->pub.beacon_ies, - ielen); - found->beacon_ies_allocated = true; - found->pub.beacon_ies = ies; - found->pub.len_beacon_ies = ielen; - } - } + rcu_assign_pointer(found->pub.ies, + tmp->pub.proberesp_ies); + if (old) + kfree_rcu((struct cfg80211_bss_ies *)old, + rcu_head); + } else if (rcu_access_pointer(tmp->pub.beacon_ies)) { + const struct cfg80211_bss_ies *old, *ies; + + old = rcu_access_pointer(found->pub.beacon_ies); + ies = rcu_access_pointer(found->pub.ies); + + rcu_assign_pointer(found->pub.beacon_ies, + tmp->pub.beacon_ies); /* Override IEs if they were from a beacon before */ - if (information_elements_is_beacon_ies) { - found->pub.information_elements = - found->pub.beacon_ies; - found->pub.len_information_elements = - found->pub.len_beacon_ies; - } - } + if (old == ies) + rcu_assign_pointer(found->pub.ies, + tmp->pub.beacon_ies); - kref_put(&res->ref, bss_release); + if (old) + kfree_rcu((struct cfg80211_bss_ies *)old, + rcu_head); + } } else { + struct cfg80211_internal_bss *new; struct cfg80211_internal_bss *hidden; + struct cfg80211_bss_ies *ies; /* First check if the beacon is a probe response from * a hidden bss. If so, copy beacon ies (with nullified @@ -720,14 +742,32 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, /* TODO: The code is not trying to update existing probe * response bss entries when beacon ies are * getting changed. */ - hidden = rb_find_hidden_bss(dev, res); + hidden = rb_find_hidden_bss(dev, tmp); if (hidden) - copy_hidden_ies(res, hidden); - - /* this "consumes" the reference */ - list_add_tail(&res->list, &dev->bss_list); - rb_insert_bss(dev, res); - found = res; + copy_hidden_ies(tmp, hidden); + + /* + * create a copy -- the "res" variable that is passed in + * is allocated on the stack since it's not needed in the + * more common case of an update + */ + new = kzalloc(sizeof(*new) + dev->wiphy.bss_priv_size, + GFP_ATOMIC); + if (!new) { + ies = (void *)rcu_dereference(tmp->pub.beacon_ies); + if (ies) + kfree_rcu(ies, rcu_head); + ies = (void *)rcu_dereference(tmp->pub.proberesp_ies); + if (ies) + kfree_rcu(ies, rcu_head); + spin_unlock_bh(&dev->bss_lock); + return NULL; + } + memcpy(new, tmp, sizeof(*new)); + kref_init(&new->ref); + list_add_tail(&new->list, &dev->bss_list); + rb_insert_bss(dev, new); + found = new; } dev->bss_generation++; @@ -737,6 +777,38 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, return found; } +static struct ieee80211_channel * +cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, + struct ieee80211_channel *channel) +{ + const u8 *tmp; + u32 freq; + int channel_number = -1; + + tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen); + if (tmp && tmp[1] == 1) { + channel_number = tmp[2]; + } else { + tmp = cfg80211_find_ie(WLAN_EID_HT_OPERATION, ie, ielen); + if (tmp && tmp[1] >= sizeof(struct ieee80211_ht_operation)) { + struct ieee80211_ht_operation *htop = (void *)(tmp + 2); + + channel_number = htop->primary_chan; + } + } + + if (channel_number < 0) + return channel; + + freq = ieee80211_channel_to_frequency(channel_number, channel->band); + channel = ieee80211_get_channel(wiphy, freq); + if (!channel) + return NULL; + if (channel->flags & IEEE80211_CHAN_DISABLED) + return NULL; + return channel; +} + struct cfg80211_bss* cfg80211_inform_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, @@ -744,54 +816,54 @@ cfg80211_inform_bss(struct wiphy *wiphy, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { - struct cfg80211_internal_bss *res; - size_t privsz; + struct cfg80211_bss_ies *ies; + struct cfg80211_internal_bss tmp = {}, *res; if (WARN_ON(!wiphy)) return NULL; - privsz = wiphy->bss_priv_size; - if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && (signal < 0 || signal > 100))) return NULL; - res = kzalloc(sizeof(*res) + privsz + ielen, gfp); - if (!res) + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, channel); + if (!channel) return NULL; - memcpy(res->pub.bssid, bssid, ETH_ALEN); - res->pub.channel = channel; - res->pub.signal = signal; - res->pub.tsf = tsf; - res->pub.beacon_interval = beacon_interval; - res->pub.capability = capability; + memcpy(tmp.pub.bssid, bssid, ETH_ALEN); + tmp.pub.channel = channel; + tmp.pub.signal = signal; + tmp.pub.tsf = tsf; + tmp.pub.beacon_interval = beacon_interval; + tmp.pub.capability = capability; /* * Since we do not know here whether the IEs are from a Beacon or Probe * Response frame, we need to pick one of the options and only use it * with the driver that does not provide the full Beacon/Probe Response * frame. Use Beacon frame pointer to avoid indicating that this should - * override the information_elements pointer should we have received an - * earlier indication of Probe Response data. + * override the iies pointer should we have received an earlier + * indication of Probe Response data. * * The initial buffer for the IEs is allocated with the BSS entry and * is located after the private area. */ - res->pub.beacon_ies = (u8 *)res + sizeof(*res) + privsz; - memcpy(res->pub.beacon_ies, ie, ielen); - res->pub.len_beacon_ies = ielen; - res->pub.information_elements = res->pub.beacon_ies; - res->pub.len_information_elements = res->pub.len_beacon_ies; + ies = kmalloc(sizeof(*ies) + ielen, gfp); + if (!ies) + return NULL; + ies->len = ielen; + memcpy(ies->data, ie, ielen); - kref_init(&res->ref); + rcu_assign_pointer(tmp.pub.beacon_ies, ies); + rcu_assign_pointer(tmp.pub.ies, ies); - res = cfg80211_bss_update(wiphy_to_dev(wiphy), res); + res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp); if (!res) return NULL; if (res->pub.capability & WLAN_CAPABILITY_ESS) regulatory_hint_found_beacon(wiphy, channel, gfp); + trace_cfg80211_return_bss(&res->pub); /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } @@ -803,10 +875,15 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp) { - struct cfg80211_internal_bss *res; + struct cfg80211_internal_bss tmp = {}, *res; + struct cfg80211_bss_ies *ies; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); - size_t privsz; + + BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != + offsetof(struct ieee80211_mgmt, u.beacon.variable)); + + trace_cfg80211_inform_bss_frame(wiphy, channel, mgmt, len, signal); if (WARN_ON(!mgmt)) return NULL; @@ -821,46 +898,38 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable))) return NULL; - privsz = wiphy->bss_priv_size; - - res = kzalloc(sizeof(*res) + privsz + ielen, gfp); - if (!res) + channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, + ielen, channel); + if (!channel) return NULL; - memcpy(res->pub.bssid, mgmt->bssid, ETH_ALEN); - res->pub.channel = channel; - res->pub.signal = signal; - res->pub.tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); - res->pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); - res->pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); - /* - * The initial buffer for the IEs is allocated with the BSS entry and - * is located after the private area. - */ - if (ieee80211_is_probe_resp(mgmt->frame_control)) { - res->pub.proberesp_ies = (u8 *) res + sizeof(*res) + privsz; - memcpy(res->pub.proberesp_ies, mgmt->u.probe_resp.variable, - ielen); - res->pub.len_proberesp_ies = ielen; - res->pub.information_elements = res->pub.proberesp_ies; - res->pub.len_information_elements = res->pub.len_proberesp_ies; - } else { - res->pub.beacon_ies = (u8 *) res + sizeof(*res) + privsz; - memcpy(res->pub.beacon_ies, mgmt->u.beacon.variable, ielen); - res->pub.len_beacon_ies = ielen; - res->pub.information_elements = res->pub.beacon_ies; - res->pub.len_information_elements = res->pub.len_beacon_ies; - } - - kref_init(&res->ref); + ies = kmalloc(sizeof(*ies) + ielen, gfp); + if (!ies) + return NULL; + ies->len = ielen; + memcpy(ies->data, mgmt->u.probe_resp.variable, ielen); - res = cfg80211_bss_update(wiphy_to_dev(wiphy), res); + if (ieee80211_is_probe_resp(mgmt->frame_control)) + rcu_assign_pointer(tmp.pub.proberesp_ies, ies); + else + rcu_assign_pointer(tmp.pub.beacon_ies, ies); + rcu_assign_pointer(tmp.pub.ies, ies); + + memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN); + tmp.pub.channel = channel; + tmp.pub.signal = signal; + tmp.pub.tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); + tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); + tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); + + res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp); if (!res) return NULL; if (res->pub.capability & WLAN_CAPABILITY_ESS) regulatory_hint_found_beacon(wiphy, channel, gfp); + trace_cfg80211_return_bss(&res->pub); /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } @@ -962,6 +1031,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, creq->ssids = (void *)&creq->channels[n_channels]; creq->n_channels = n_channels; creq->n_ssids = 1; + creq->scan_start = jiffies; /* translate "Scan on frequencies" request */ i = 0; @@ -1026,7 +1096,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, creq->rates[i] = (1 << wiphy->bands[i]->n_bitrates) - 1; rdev->scan_req = creq; - err = rdev->ops->scan(wiphy, creq); + err = rdev_scan(rdev, creq); if (err) { rdev->scan_req = NULL; /* creq will be freed below */ @@ -1044,22 +1114,21 @@ int cfg80211_wext_siwscan(struct net_device *dev, EXPORT_SYMBOL_GPL(cfg80211_wext_siwscan); static void ieee80211_scan_add_ies(struct iw_request_info *info, - struct cfg80211_bss *bss, + const struct cfg80211_bss_ies *ies, char **current_ev, char *end_buf) { - u8 *pos, *end, *next; + const u8 *pos, *end, *next; struct iw_event iwe; - if (!bss->information_elements || - !bss->len_information_elements) + if (!ies) return; /* * If needed, fragment the IEs buffer (at IE boundaries) into short * enough fragments to fit into IW_GENERIC_IE_MAX octet messages. */ - pos = bss->information_elements; - end = pos + bss->len_information_elements; + pos = ies->data; + end = pos + ies->len; while (end - pos > IW_GENERIC_IE_MAX) { next = pos + 2 + pos[1]; @@ -1070,7 +1139,8 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info, iwe.cmd = IWEVGENIE; iwe.u.data.length = next - pos; *current_ev = iwe_stream_add_point(info, *current_ev, - end_buf, &iwe, pos); + end_buf, &iwe, + (void *)pos); pos = next; } @@ -1080,7 +1150,8 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info, iwe.cmd = IWEVGENIE; iwe.u.data.length = end - pos; *current_ev = iwe_stream_add_point(info, *current_ev, - end_buf, &iwe, pos); + end_buf, &iwe, + (void *)pos); } } @@ -1099,10 +1170,11 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, struct cfg80211_internal_bss *bss, char *current_ev, char *end_buf) { + const struct cfg80211_bss_ies *ies; struct iw_event iwe; + const u8 *ie; u8 *buf, *cfg, *p; - u8 *ie = bss->pub.information_elements; - int rem = bss->pub.len_information_elements, i, sig; + int rem, i, sig; bool ismesh = false; memset(&iwe, 0, sizeof(iwe)); @@ -1167,7 +1239,17 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, current_ev = iwe_stream_add_point(info, current_ev, end_buf, &iwe, ""); - while (rem >= 2) { + rcu_read_lock(); + ies = rcu_dereference(bss->pub.ies); + if (ies) { + rem = ies->len; + ie = ies->data; + } else { + rem = 0; + ie = NULL; + } + + while (ies && rem >= 2) { /* invalid data */ if (ie[1] > rem - 2) break; @@ -1179,7 +1261,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, iwe.u.data.length = ie[1]; iwe.u.data.flags = 1; current_ev = iwe_stream_add_point(info, current_ev, end_buf, - &iwe, ie + 2); + &iwe, (u8 *)ie + 2); break; case WLAN_EID_MESH_ID: memset(&iwe, 0, sizeof(iwe)); @@ -1187,7 +1269,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, iwe.u.data.length = ie[1]; iwe.u.data.flags = 1; current_ev = iwe_stream_add_point(info, current_ev, end_buf, - &iwe, ie + 2); + &iwe, (u8 *)ie + 2); break; case WLAN_EID_MESH_CONFIG: ismesh = true; @@ -1196,7 +1278,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, buf = kmalloc(50, GFP_ATOMIC); if (!buf) break; - cfg = ie + 2; + cfg = (u8 *)ie + 2; memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVCUSTOM; sprintf(buf, "Mesh Network Path Selection Protocol ID: " @@ -1294,7 +1376,8 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, kfree(buf); } - ieee80211_scan_add_ies(info, &bss->pub, ¤t_ev, end_buf); + ieee80211_scan_add_ies(info, ies, ¤t_ev, end_buf); + rcu_read_unlock(); return current_ev; } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 6f39cb808302..f2431e41a373 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -16,6 +16,7 @@ #include <net/rtnetlink.h> #include "nl80211.h" #include "reg.h" +#include "rdev-ops.h" struct cfg80211_conn { struct cfg80211_connect_params params; @@ -138,10 +139,11 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) request->wdev = wdev; request->wiphy = &rdev->wiphy; + request->scan_start = jiffies; rdev->scan_req = request; - err = rdev->ops->scan(wdev->wiphy, request); + err = rdev_scan(rdev, request); if (!err) { wdev->conn->state = CFG80211_CONN_SCANNING; nl80211_send_scan_start(rdev, wdev); @@ -179,7 +181,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) params->ssid, params->ssid_len, NULL, 0, params->key, params->key_len, - params->key_idx); + params->key_idx, NULL, 0); case CFG80211_CONN_ASSOCIATE_NEXT: BUG_ON(!rdev->ops->assoc); wdev->conn->state = CFG80211_CONN_ASSOCIATING; @@ -415,7 +417,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, struct cfg80211_bss *bss) { struct wireless_dev *wdev = dev->ieee80211_ptr; - u8 *country_ie; + const u8 *country_ie; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif @@ -499,7 +501,15 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, wdev->sme_state = CFG80211_SME_CONNECTED; cfg80211_upload_connect_keys(wdev); - country_ie = (u8 *) ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY); + rcu_read_lock(); + country_ie = ieee80211_bss_get_ie(bss, WLAN_EID_COUNTRY); + if (!country_ie) { + rcu_read_unlock(); + return; + } + + country_ie = kmemdup(country_ie, 2 + country_ie[1], GFP_ATOMIC); + rcu_read_unlock(); if (!country_ie) return; @@ -513,6 +523,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, bss->channel->band, country_ie + 2, country_ie[1]); + kfree(country_ie); } void cfg80211_connect_result(struct net_device *dev, const u8 *bssid, @@ -716,7 +727,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, */ if (rdev->ops->del_key) for (i = 0; i < 6; i++) - rdev->ops->del_key(wdev->wiphy, dev, i, false, NULL); + rdev_del_key(rdev, dev, i, false, NULL); #ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); @@ -892,7 +903,7 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, } else { wdev->sme_state = CFG80211_SME_CONNECTING; wdev->connect_keys = connkeys; - err = rdev->ops->connect(&rdev->wiphy, dev, connect); + err = rdev_connect(rdev, dev, connect); if (err) { wdev->connect_keys = NULL; wdev->sme_state = CFG80211_SME_IDLE; @@ -964,7 +975,7 @@ int __cfg80211_disconnect(struct cfg80211_registered_device *rdev, if (err) return err; } else { - err = rdev->ops->disconnect(&rdev->wiphy, dev, reason); + err = rdev_disconnect(rdev, dev, reason); if (err) return err; } diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index ff574597a854..1f6f01e2dc4c 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -16,6 +16,7 @@ #include <net/cfg80211.h> #include "sysfs.h" #include "core.h" +#include "rdev-ops.h" static inline struct cfg80211_registered_device *dev_to_rdev( struct device *dev) @@ -76,13 +77,11 @@ static void wiphy_dev_release(struct device *dev) cfg80211_dev_free(rdev); } -#ifdef CONFIG_HOTPLUG static int wiphy_uevent(struct device *dev, struct kobj_uevent_env *env) { /* TODO, we probably need stuff here */ return 0; } -#endif static int wiphy_suspend(struct device *dev, pm_message_t state) { @@ -94,7 +93,7 @@ static int wiphy_suspend(struct device *dev, pm_message_t state) if (rdev->ops->suspend) { rtnl_lock(); if (rdev->wiphy.registered) - ret = rdev->ops->suspend(&rdev->wiphy, rdev->wowlan); + ret = rdev_suspend(rdev); rtnl_unlock(); } @@ -114,7 +113,7 @@ static int wiphy_resume(struct device *dev) if (rdev->ops->resume) { rtnl_lock(); if (rdev->wiphy.registered) - ret = rdev->ops->resume(&rdev->wiphy); + ret = rdev_resume(rdev); rtnl_unlock(); } @@ -133,9 +132,7 @@ struct class ieee80211_class = { .owner = THIS_MODULE, .dev_release = wiphy_dev_release, .dev_attrs = ieee80211_dev_attrs, -#ifdef CONFIG_HOTPLUG .dev_uevent = wiphy_uevent, -#endif .suspend = wiphy_suspend, .resume = wiphy_resume, .ns_type = &net_ns_type_operations, diff --git a/net/wireless/trace.c b/net/wireless/trace.c new file mode 100644 index 000000000000..95f997fad755 --- /dev/null +++ b/net/wireless/trace.c @@ -0,0 +1,7 @@ +#include <linux/module.h> + +#ifndef __CHECKER__ +#define CREATE_TRACE_POINTS +#include "trace.h" + +#endif diff --git a/net/wireless/trace.h b/net/wireless/trace.h new file mode 100644 index 000000000000..2134576f426e --- /dev/null +++ b/net/wireless/trace.h @@ -0,0 +1,2324 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM cfg80211 + +#if !defined(__RDEV_OPS_TRACE) || defined(TRACE_HEADER_MULTI_READ) +#define __RDEV_OPS_TRACE + +#include <linux/tracepoint.h> + +#include <linux/rtnetlink.h> +#include <net/cfg80211.h> +#include "core.h" + +#define MAC_ENTRY(entry_mac) __array(u8, entry_mac, ETH_ALEN) +#define MAC_ASSIGN(entry_mac, given_mac) do { \ + if (given_mac) \ + memcpy(__entry->entry_mac, given_mac, ETH_ALEN); \ + else \ + memset(__entry->entry_mac, 0, ETH_ALEN); \ + } while (0) +#define MAC_PR_FMT "%pM" +#define MAC_PR_ARG(entry_mac) (__entry->entry_mac) + +#define MAXNAME 32 +#define WIPHY_ENTRY __array(char, wiphy_name, 32) +#define WIPHY_ASSIGN strlcpy(__entry->wiphy_name, wiphy_name(wiphy), MAXNAME) +#define WIPHY_PR_FMT "%s" +#define WIPHY_PR_ARG __entry->wiphy_name + +#define WDEV_ENTRY __field(u32, id) +#define WDEV_ASSIGN (__entry->id) = (wdev ? wdev->identifier : 0) +#define WDEV_PR_FMT "wdev(%u)" +#define WDEV_PR_ARG (__entry->id) + +#define NETDEV_ENTRY __array(char, name, IFNAMSIZ) \ + __field(int, ifindex) +#define NETDEV_ASSIGN \ + do { \ + memcpy(__entry->name, netdev->name, IFNAMSIZ); \ + (__entry->ifindex) = (netdev->ifindex); \ + } while (0) +#define NETDEV_PR_FMT "netdev:%s(%d)" +#define NETDEV_PR_ARG __entry->name, __entry->ifindex + +#define MESH_CFG_ENTRY __field(u16, dot11MeshRetryTimeout) \ + __field(u16, dot11MeshConfirmTimeout) \ + __field(u16, dot11MeshHoldingTimeout) \ + __field(u16, dot11MeshMaxPeerLinks) \ + __field(u8, dot11MeshMaxRetries) \ + __field(u8, dot11MeshTTL) \ + __field(u8, element_ttl) \ + __field(bool, auto_open_plinks) \ + __field(u32, dot11MeshNbrOffsetMaxNeighbor) \ + __field(u8, dot11MeshHWMPmaxPREQretries) \ + __field(u32, path_refresh_time) \ + __field(u32, dot11MeshHWMPactivePathTimeout) \ + __field(u16, min_discovery_timeout) \ + __field(u16, dot11MeshHWMPpreqMinInterval) \ + __field(u16, dot11MeshHWMPperrMinInterval) \ + __field(u16, dot11MeshHWMPnetDiameterTraversalTime) \ + __field(u8, dot11MeshHWMPRootMode) \ + __field(u16, dot11MeshHWMPRannInterval) \ + __field(bool, dot11MeshGateAnnouncementProtocol) \ + __field(bool, dot11MeshForwarding) \ + __field(s32, rssi_threshold) \ + __field(u16, ht_opmode) \ + __field(u32, dot11MeshHWMPactivePathToRootTimeout) \ + __field(u16, dot11MeshHWMProotInterval) \ + __field(u16, dot11MeshHWMPconfirmationInterval) +#define MESH_CFG_ASSIGN \ + do { \ + __entry->dot11MeshRetryTimeout = conf->dot11MeshRetryTimeout; \ + __entry->dot11MeshConfirmTimeout = \ + conf->dot11MeshConfirmTimeout; \ + __entry->dot11MeshHoldingTimeout = \ + conf->dot11MeshHoldingTimeout; \ + __entry->dot11MeshMaxPeerLinks = conf->dot11MeshMaxPeerLinks; \ + __entry->dot11MeshMaxRetries = conf->dot11MeshMaxRetries; \ + __entry->dot11MeshTTL = conf->dot11MeshTTL; \ + __entry->element_ttl = conf->element_ttl; \ + __entry->auto_open_plinks = conf->auto_open_plinks; \ + __entry->dot11MeshNbrOffsetMaxNeighbor = \ + conf->dot11MeshNbrOffsetMaxNeighbor; \ + __entry->dot11MeshHWMPmaxPREQretries = \ + conf->dot11MeshHWMPmaxPREQretries; \ + __entry->path_refresh_time = conf->path_refresh_time; \ + __entry->dot11MeshHWMPactivePathTimeout = \ + conf->dot11MeshHWMPactivePathTimeout; \ + __entry->min_discovery_timeout = conf->min_discovery_timeout; \ + __entry->dot11MeshHWMPpreqMinInterval = \ + conf->dot11MeshHWMPpreqMinInterval; \ + __entry->dot11MeshHWMPperrMinInterval = \ + conf->dot11MeshHWMPperrMinInterval; \ + __entry->dot11MeshHWMPnetDiameterTraversalTime = \ + conf->dot11MeshHWMPnetDiameterTraversalTime; \ + __entry->dot11MeshHWMPRootMode = conf->dot11MeshHWMPRootMode; \ + __entry->dot11MeshHWMPRannInterval = \ + conf->dot11MeshHWMPRannInterval; \ + __entry->dot11MeshGateAnnouncementProtocol = \ + conf->dot11MeshGateAnnouncementProtocol; \ + __entry->dot11MeshForwarding = conf->dot11MeshForwarding; \ + __entry->rssi_threshold = conf->rssi_threshold; \ + __entry->ht_opmode = conf->ht_opmode; \ + __entry->dot11MeshHWMPactivePathToRootTimeout = \ + conf->dot11MeshHWMPactivePathToRootTimeout; \ + __entry->dot11MeshHWMProotInterval = \ + conf->dot11MeshHWMProotInterval; \ + __entry->dot11MeshHWMPconfirmationInterval = \ + conf->dot11MeshHWMPconfirmationInterval; \ + } while (0) + +#define CHAN_ENTRY __field(enum ieee80211_band, band) \ + __field(u16, center_freq) +#define CHAN_ASSIGN(chan) \ + do { \ + if (chan) { \ + __entry->band = chan->band; \ + __entry->center_freq = chan->center_freq; \ + } else { \ + __entry->band = 0; \ + __entry->center_freq = 0; \ + } \ + } while (0) +#define CHAN_PR_FMT "band: %d, freq: %u" +#define CHAN_PR_ARG __entry->band, __entry->center_freq + +#define CHAN_DEF_ENTRY __field(enum ieee80211_band, band) \ + __field(u32, control_freq) \ + __field(u32, width) \ + __field(u32, center_freq1) \ + __field(u32, center_freq2) +#define CHAN_DEF_ASSIGN(chandef) \ + do { \ + if ((chandef) && (chandef)->chan) { \ + __entry->band = (chandef)->chan->band; \ + __entry->control_freq = \ + (chandef)->chan->center_freq; \ + __entry->width = (chandef)->width; \ + __entry->center_freq1 = (chandef)->center_freq1;\ + __entry->center_freq2 = (chandef)->center_freq2;\ + } else { \ + __entry->band = 0; \ + __entry->control_freq = 0; \ + __entry->width = 0; \ + __entry->center_freq1 = 0; \ + __entry->center_freq2 = 0; \ + } \ + } while (0) +#define CHAN_DEF_PR_FMT \ + "band: %d, control freq: %u, width: %d, cf1: %u, cf2: %u" +#define CHAN_DEF_PR_ARG __entry->band, __entry->control_freq, \ + __entry->width, __entry->center_freq1, \ + __entry->center_freq2 + +#define SINFO_ENTRY __field(int, generation) \ + __field(u32, connected_time) \ + __field(u32, inactive_time) \ + __field(u32, rx_bytes) \ + __field(u32, tx_bytes) \ + __field(u32, rx_packets) \ + __field(u32, tx_packets) \ + __field(u32, tx_retries) \ + __field(u32, tx_failed) \ + __field(u32, rx_dropped_misc) \ + __field(u32, beacon_loss_count) \ + __field(u16, llid) \ + __field(u16, plid) \ + __field(u8, plink_state) +#define SINFO_ASSIGN \ + do { \ + __entry->generation = sinfo->generation; \ + __entry->connected_time = sinfo->connected_time; \ + __entry->inactive_time = sinfo->inactive_time; \ + __entry->rx_bytes = sinfo->rx_bytes; \ + __entry->tx_bytes = sinfo->tx_bytes; \ + __entry->rx_packets = sinfo->rx_packets; \ + __entry->tx_packets = sinfo->tx_packets; \ + __entry->tx_retries = sinfo->tx_retries; \ + __entry->tx_failed = sinfo->tx_failed; \ + __entry->rx_dropped_misc = sinfo->rx_dropped_misc; \ + __entry->beacon_loss_count = sinfo->beacon_loss_count; \ + __entry->llid = sinfo->llid; \ + __entry->plid = sinfo->plid; \ + __entry->plink_state = sinfo->plink_state; \ + } while (0) + +#define BOOL_TO_STR(bo) (bo) ? "true" : "false" + +/************************************************************* + * rdev->ops traces * + *************************************************************/ + +TRACE_EVENT(rdev_suspend, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_wowlan *wow), + TP_ARGS(wiphy, wow), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(bool, any) + __field(bool, disconnect) + __field(bool, magic_pkt) + __field(bool, gtk_rekey_failure) + __field(bool, eap_identity_req) + __field(bool, four_way_handshake) + __field(bool, rfkill_release) + __field(bool, valid_wow) + ), + TP_fast_assign( + WIPHY_ASSIGN; + if (wow) { + __entry->any = wow->any; + __entry->disconnect = wow->disconnect; + __entry->magic_pkt = wow->magic_pkt; + __entry->gtk_rekey_failure = wow->gtk_rekey_failure; + __entry->eap_identity_req = wow->eap_identity_req; + __entry->four_way_handshake = wow->four_way_handshake; + __entry->rfkill_release = wow->rfkill_release; + __entry->valid_wow = true; + } else { + __entry->valid_wow = false; + } + ), + TP_printk(WIPHY_PR_FMT ", wow%s - any: %d, disconnect: %d, " + "magic pkt: %d, gtk rekey failure: %d, eap identify req: %d, " + "four way handshake: %d, rfkill release: %d.", + WIPHY_PR_ARG, __entry->valid_wow ? "" : "(Not configured!)", + __entry->any, __entry->disconnect, __entry->magic_pkt, + __entry->gtk_rekey_failure, __entry->eap_identity_req, + __entry->four_way_handshake, __entry->rfkill_release) +); + +TRACE_EVENT(rdev_return_int, + TP_PROTO(struct wiphy *wiphy, int ret), + TP_ARGS(wiphy, ret), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, ret) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->ret = ret; + ), + TP_printk(WIPHY_PR_FMT ", returned: %d", WIPHY_PR_ARG, __entry->ret) +); + +TRACE_EVENT(rdev_scan, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_scan_request *request), + TP_ARGS(wiphy, request), + TP_STRUCT__entry( + WIPHY_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT, WIPHY_PR_ARG) +); + +DECLARE_EVENT_CLASS(wiphy_only_evt, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy), + TP_STRUCT__entry( + WIPHY_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT, WIPHY_PR_ARG) +); + +DEFINE_EVENT(wiphy_only_evt, rdev_resume, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy) +); + +DEFINE_EVENT(wiphy_only_evt, rdev_return_void, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy) +); + +DEFINE_EVENT(wiphy_only_evt, rdev_get_ringparam, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy) +); + +DEFINE_EVENT(wiphy_only_evt, rdev_get_antenna, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy) +); + +DEFINE_EVENT(wiphy_only_evt, rdev_rfkill_poll, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy) +); + +DECLARE_EVENT_CLASS(wiphy_enabled_evt, + TP_PROTO(struct wiphy *wiphy, bool enabled), + TP_ARGS(wiphy, enabled), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(bool, enabled) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->enabled = enabled; + ), + TP_printk(WIPHY_PR_FMT ", %senabled ", + WIPHY_PR_ARG, __entry->enabled ? "" : "not ") +); + +DEFINE_EVENT(wiphy_enabled_evt, rdev_set_wakeup, + TP_PROTO(struct wiphy *wiphy, bool enabled), + TP_ARGS(wiphy, enabled) +); + +TRACE_EVENT(rdev_add_virtual_intf, + TP_PROTO(struct wiphy *wiphy, char *name, enum nl80211_iftype type), + TP_ARGS(wiphy, name, type), + TP_STRUCT__entry( + WIPHY_ENTRY + __string(vir_intf_name, name ? name : "<noname>") + __field(enum nl80211_iftype, type) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __assign_str(vir_intf_name, name ? name : "<noname>"); + __entry->type = type; + ), + TP_printk(WIPHY_PR_FMT ", virtual intf name: %s, type: %d", + WIPHY_PR_ARG, __get_str(vir_intf_name), __entry->type) +); + +DECLARE_EVENT_CLASS(wiphy_wdev_evt, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT, WIPHY_PR_ARG, WDEV_PR_ARG) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_return_wdev, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_del_virtual_intf, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + +TRACE_EVENT(rdev_change_virtual_intf, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + enum nl80211_iftype type), + TP_ARGS(wiphy, netdev, type), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(enum nl80211_iftype, type) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->type = type; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", type: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->type) +); + +DECLARE_EVENT_CLASS(key_handle, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, + bool pairwise, const u8 *mac_addr), + TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(mac_addr) + __field(u8, key_index) + __field(bool, pairwise) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(mac_addr, mac_addr); + __entry->key_index = key_index; + __entry->pairwise = pairwise; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", key_index: %u, pairwise: %s, mac addr: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index, + BOOL_TO_STR(__entry->pairwise), MAC_PR_ARG(mac_addr)) +); + +DEFINE_EVENT(key_handle, rdev_add_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, + bool pairwise, const u8 *mac_addr), + TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr) +); + +DEFINE_EVENT(key_handle, rdev_get_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, + bool pairwise, const u8 *mac_addr), + TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr) +); + +DEFINE_EVENT(key_handle, rdev_del_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, + bool pairwise, const u8 *mac_addr), + TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr) +); + +TRACE_EVENT(rdev_set_default_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, + bool unicast, bool multicast), + TP_ARGS(wiphy, netdev, key_index, unicast, multicast), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u8, key_index) + __field(bool, unicast) + __field(bool, multicast) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->key_index = key_index; + __entry->unicast = unicast; + __entry->multicast = multicast; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", key index: %u, unicast: %s, multicast: %s", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index, + BOOL_TO_STR(__entry->unicast), + BOOL_TO_STR(__entry->multicast)) +); + +TRACE_EVENT(rdev_set_default_mgmt_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index), + TP_ARGS(wiphy, netdev, key_index), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u8, key_index) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->key_index = key_index; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", key index: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index) +); + +TRACE_EVENT(rdev_start_ap, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_ap_settings *settings), + TP_ARGS(wiphy, netdev, settings), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + CHAN_DEF_ENTRY + __field(int, beacon_interval) + __field(int, dtim_period) + __array(char, ssid, IEEE80211_MAX_SSID_LEN + 1) + __field(enum nl80211_hidden_ssid, hidden_ssid) + __field(u32, wpa_ver) + __field(bool, privacy) + __field(enum nl80211_auth_type, auth_type) + __field(int, inactivity_timeout) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + CHAN_DEF_ASSIGN(&settings->chandef); + __entry->beacon_interval = settings->beacon_interval; + __entry->dtim_period = settings->dtim_period; + __entry->hidden_ssid = settings->hidden_ssid; + __entry->wpa_ver = settings->crypto.wpa_versions; + __entry->privacy = settings->privacy; + __entry->auth_type = settings->auth_type; + __entry->inactivity_timeout = settings->inactivity_timeout; + memset(__entry->ssid, 0, IEEE80211_MAX_SSID_LEN + 1); + memcpy(__entry->ssid, settings->ssid, settings->ssid_len); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", AP settings - ssid: %s, " + CHAN_DEF_PR_FMT ", beacon interval: %d, dtim period: %d, " + "hidden ssid: %d, wpa versions: %u, privacy: %s, " + "auth type: %d, inactivity timeout: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->ssid, CHAN_DEF_PR_ARG, + __entry->beacon_interval, __entry->dtim_period, + __entry->hidden_ssid, __entry->wpa_ver, + BOOL_TO_STR(__entry->privacy), __entry->auth_type, + __entry->inactivity_timeout) +); + +TRACE_EVENT(rdev_change_beacon, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_beacon_data *info), + TP_ARGS(wiphy, netdev, info), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __dynamic_array(u8, head, info ? info->head_len : 0) + __dynamic_array(u8, tail, info ? info->tail_len : 0) + __dynamic_array(u8, beacon_ies, info ? info->beacon_ies_len : 0) + __dynamic_array(u8, proberesp_ies, + info ? info->proberesp_ies_len : 0) + __dynamic_array(u8, assocresp_ies, + info ? info->assocresp_ies_len : 0) + __dynamic_array(u8, probe_resp, info ? info->probe_resp_len : 0) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + if (info) { + if (info->head) + memcpy(__get_dynamic_array(head), info->head, + info->head_len); + if (info->tail) + memcpy(__get_dynamic_array(tail), info->tail, + info->tail_len); + if (info->beacon_ies) + memcpy(__get_dynamic_array(beacon_ies), + info->beacon_ies, info->beacon_ies_len); + if (info->proberesp_ies) + memcpy(__get_dynamic_array(proberesp_ies), + info->proberesp_ies, + info->proberesp_ies_len); + if (info->assocresp_ies) + memcpy(__get_dynamic_array(assocresp_ies), + info->assocresp_ies, + info->assocresp_ies_len); + if (info->probe_resp) + memcpy(__get_dynamic_array(probe_resp), + info->probe_resp, info->probe_resp_len); + } + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG) +); + +DECLARE_EVENT_CLASS(wiphy_netdev_evt, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_stop_ap, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_get_et_stats, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_sched_scan_stop, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_set_rekey_data, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_get_mesh_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_leave_mesh, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_leave_ibss, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + +DECLARE_EVENT_CLASS(station_add_change, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *mac, + struct station_parameters *params), + TP_ARGS(wiphy, netdev, mac, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(sta_mac) + __field(u32, sta_flags_mask) + __field(u32, sta_flags_set) + __field(u32, sta_modify_mask) + __field(int, listen_interval) + __field(u16, aid) + __field(u8, plink_action) + __field(u8, plink_state) + __field(u8, uapsd_queues) + __array(u8, ht_capa, (int)sizeof(struct ieee80211_ht_cap)) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(sta_mac, mac); + __entry->sta_flags_mask = params->sta_flags_mask; + __entry->sta_flags_set = params->sta_flags_set; + __entry->sta_modify_mask = params->sta_modify_mask; + __entry->listen_interval = params->listen_interval; + __entry->aid = params->aid; + __entry->plink_action = params->plink_action; + __entry->plink_state = params->plink_state; + __entry->uapsd_queues = params->uapsd_queues; + memset(__entry->ht_capa, 0, sizeof(struct ieee80211_ht_cap)); + if (params->ht_capa) + memcpy(__entry->ht_capa, params->ht_capa, + sizeof(struct ieee80211_ht_cap)); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT + ", station flags mask: %u, station flags set: %u, " + "station modify mask: %u, listen interval: %d, aid: %u, " + "plink action: %u, plink state: %u, uapsd queues: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac), + __entry->sta_flags_mask, __entry->sta_flags_set, + __entry->sta_modify_mask, __entry->listen_interval, + __entry->aid, __entry->plink_action, __entry->plink_state, + __entry->uapsd_queues) +); + +DEFINE_EVENT(station_add_change, rdev_add_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *mac, + struct station_parameters *params), + TP_ARGS(wiphy, netdev, mac, params) +); + +DEFINE_EVENT(station_add_change, rdev_change_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *mac, + struct station_parameters *params), + TP_ARGS(wiphy, netdev, mac, params) +); + +DECLARE_EVENT_CLASS(wiphy_netdev_mac_evt, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac), + TP_ARGS(wiphy, netdev, mac), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(sta_mac) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(sta_mac, mac); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", mac: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac)) +); + +DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_del_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac), + TP_ARGS(wiphy, netdev, mac) +); + +DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_get_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac), + TP_ARGS(wiphy, netdev, mac) +); + +DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_del_mpath, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac), + TP_ARGS(wiphy, netdev, mac) +); + +DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_set_wds_peer, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac), + TP_ARGS(wiphy, netdev, mac) +); + +TRACE_EVENT(rdev_dump_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx, + u8 *mac), + TP_ARGS(wiphy, netdev, idx, mac), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(sta_mac) + __field(int, idx) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(sta_mac, mac); + __entry->idx = idx; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT ", idx: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac), + __entry->idx) +); + +TRACE_EVENT(rdev_return_int_station_info, + TP_PROTO(struct wiphy *wiphy, int ret, struct station_info *sinfo), + TP_ARGS(wiphy, ret, sinfo), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, ret) + SINFO_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->ret = ret; + SINFO_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT ", returned %d" , + WIPHY_PR_ARG, __entry->ret) +); + +DECLARE_EVENT_CLASS(mpath_evt, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *dst, + u8 *next_hop), + TP_ARGS(wiphy, netdev, dst, next_hop), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(dst) + MAC_ENTRY(next_hop) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(dst, dst); + MAC_ASSIGN(next_hop, next_hop); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", destination: " MAC_PR_FMT ", next hop: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(dst), + MAC_PR_ARG(next_hop)) +); + +DEFINE_EVENT(mpath_evt, rdev_add_mpath, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *dst, + u8 *next_hop), + TP_ARGS(wiphy, netdev, dst, next_hop) +); + +DEFINE_EVENT(mpath_evt, rdev_change_mpath, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *dst, + u8 *next_hop), + TP_ARGS(wiphy, netdev, dst, next_hop) +); + +DEFINE_EVENT(mpath_evt, rdev_get_mpath, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *dst, + u8 *next_hop), + TP_ARGS(wiphy, netdev, dst, next_hop) +); + +TRACE_EVENT(rdev_dump_mpath, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx, + u8 *dst, u8 *next_hop), + TP_ARGS(wiphy, netdev, idx, dst, next_hop), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(dst) + MAC_ENTRY(next_hop) + __field(int, idx) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(dst, dst); + MAC_ASSIGN(next_hop, next_hop); + __entry->idx = idx; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", index: %d, destination: " + MAC_PR_FMT ", next hop: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->idx, MAC_PR_ARG(dst), + MAC_PR_ARG(next_hop)) +); + +TRACE_EVENT(rdev_return_int_mpath_info, + TP_PROTO(struct wiphy *wiphy, int ret, struct mpath_info *pinfo), + TP_ARGS(wiphy, ret, pinfo), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, ret) + __field(int, generation) + __field(u32, filled) + __field(u32, frame_qlen) + __field(u32, sn) + __field(u32, metric) + __field(u32, exptime) + __field(u32, discovery_timeout) + __field(u8, discovery_retries) + __field(u8, flags) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->ret = ret; + __entry->generation = pinfo->generation; + __entry->filled = pinfo->filled; + __entry->frame_qlen = pinfo->frame_qlen; + __entry->sn = pinfo->sn; + __entry->metric = pinfo->metric; + __entry->exptime = pinfo->exptime; + __entry->discovery_timeout = pinfo->discovery_timeout; + __entry->discovery_retries = pinfo->discovery_retries; + __entry->flags = pinfo->flags; + ), + TP_printk(WIPHY_PR_FMT ", returned %d. mpath info - generation: %d, " + "filled: %u, frame qlen: %u, sn: %u, metric: %u, exptime: %u," + " discovery timeout: %u, discovery retries: %u, flags: %u", + WIPHY_PR_ARG, __entry->ret, __entry->generation, + __entry->filled, __entry->frame_qlen, __entry->sn, + __entry->metric, __entry->exptime, __entry->discovery_timeout, + __entry->discovery_retries, __entry->flags) +); + +TRACE_EVENT(rdev_return_int_mesh_config, + TP_PROTO(struct wiphy *wiphy, int ret, struct mesh_config *conf), + TP_ARGS(wiphy, ret, conf), + TP_STRUCT__entry( + WIPHY_ENTRY + MESH_CFG_ENTRY + __field(int, ret) + ), + TP_fast_assign( + WIPHY_ASSIGN; + MESH_CFG_ASSIGN; + __entry->ret = ret; + ), + TP_printk(WIPHY_PR_FMT ", returned: %d", + WIPHY_PR_ARG, __entry->ret) +); + +TRACE_EVENT(rdev_update_mesh_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u32 mask, + const struct mesh_config *conf), + TP_ARGS(wiphy, netdev, mask, conf), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MESH_CFG_ENTRY + __field(u32, mask) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MESH_CFG_ASSIGN; + __entry->mask = mask; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", mask: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->mask) +); + +TRACE_EVENT(rdev_join_mesh, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + const struct mesh_config *conf, + const struct mesh_setup *setup), + TP_ARGS(wiphy, netdev, conf, setup), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MESH_CFG_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MESH_CFG_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG) +); + +TRACE_EVENT(rdev_change_bss, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct bss_parameters *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(int, use_cts_prot) + __field(int, use_short_preamble) + __field(int, use_short_slot_time) + __field(int, ap_isolate) + __field(int, ht_opmode) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->use_cts_prot = params->use_cts_prot; + __entry->use_short_preamble = params->use_short_preamble; + __entry->use_short_slot_time = params->use_short_slot_time; + __entry->ap_isolate = params->ap_isolate; + __entry->ht_opmode = params->ht_opmode; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", use cts prot: %d, " + "use short preamble: %d, use short slot time: %d, " + "ap isolate: %d, ht opmode: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->use_cts_prot, + __entry->use_short_preamble, __entry->use_short_slot_time, + __entry->ap_isolate, __entry->ht_opmode) +); + +TRACE_EVENT(rdev_set_txq_params, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct ieee80211_txq_params *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(enum nl80211_ac, ac) + __field(u16, txop) + __field(u16, cwmin) + __field(u16, cwmax) + __field(u8, aifs) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->ac = params->ac; + __entry->txop = params->txop; + __entry->cwmin = params->cwmin; + __entry->cwmax = params->cwmax; + __entry->aifs = params->aifs; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", ac: %d, txop: %u, cwmin: %u, cwmax: %u, aifs: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->ac, __entry->txop, + __entry->cwmin, __entry->cwmax, __entry->aifs) +); + +TRACE_EVENT(rdev_libertas_set_mesh_channel, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct ieee80211_channel *chan), + TP_ARGS(wiphy, netdev, chan), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + CHAN_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + CHAN_ASSIGN(chan); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_PR_FMT, WIPHY_PR_ARG, + NETDEV_PR_ARG, CHAN_PR_ARG) +); + +TRACE_EVENT(rdev_set_monitor_channel, + TP_PROTO(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef), + TP_ARGS(wiphy, chandef), + TP_STRUCT__entry( + WIPHY_ENTRY + CHAN_DEF_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + CHAN_DEF_ASSIGN(chandef); + ), + TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT, + WIPHY_PR_ARG, CHAN_DEF_PR_ARG) +); + +TRACE_EVENT(rdev_auth, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_auth_request *req), + TP_ARGS(wiphy, netdev, req), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + __field(enum nl80211_auth_type, auth_type) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + if (req->bss) + MAC_ASSIGN(bssid, req->bss->bssid); + else + memset(__entry->bssid, 0, ETH_ALEN); + __entry->auth_type = req->auth_type; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", auth type: %d, bssid: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->auth_type, + MAC_PR_ARG(bssid)) +); + +TRACE_EVENT(rdev_assoc, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_assoc_request *req), + TP_ARGS(wiphy, netdev, req), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + MAC_ENTRY(prev_bssid) + __field(bool, use_mfp) + __field(u32, flags) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + if (req->bss) + MAC_ASSIGN(bssid, req->bss->bssid); + else + memset(__entry->bssid, 0, ETH_ALEN); + MAC_ASSIGN(prev_bssid, req->prev_bssid); + __entry->use_mfp = req->use_mfp; + __entry->flags = req->flags; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT + ", previous bssid: " MAC_PR_FMT ", use mfp: %s, flags: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), + MAC_PR_ARG(prev_bssid), BOOL_TO_STR(__entry->use_mfp), + __entry->flags) +); + +TRACE_EVENT(rdev_deauth, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_deauth_request *req), + TP_ARGS(wiphy, netdev, req), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + __field(u16, reason_code) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, req->bssid); + __entry->reason_code = req->reason_code; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT ", reason: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), + __entry->reason_code) +); + +TRACE_EVENT(rdev_disassoc, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_disassoc_request *req), + TP_ARGS(wiphy, netdev, req), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + __field(u16, reason_code) + __field(bool, local_state_change) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + if (req->bss) + MAC_ASSIGN(bssid, req->bss->bssid); + else + memset(__entry->bssid, 0, ETH_ALEN); + __entry->reason_code = req->reason_code; + __entry->local_state_change = req->local_state_change; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT + ", reason: %u, local state change: %s", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), + __entry->reason_code, + BOOL_TO_STR(__entry->local_state_change)) +); + +TRACE_EVENT(rdev_mgmt_tx_cancel_wait, + TP_PROTO(struct wiphy *wiphy, + struct wireless_dev *wdev, u64 cookie), + TP_ARGS(wiphy, wdev, cookie), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(u64, cookie) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->cookie = cookie; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", cookie: %llu ", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->cookie) +); + +TRACE_EVENT(rdev_set_power_mgmt, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + bool enabled, int timeout), + TP_ARGS(wiphy, netdev, enabled, timeout), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(bool, enabled) + __field(int, timeout) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->enabled = enabled; + __entry->timeout = timeout; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", %senabled, timeout: %d ", + WIPHY_PR_ARG, NETDEV_PR_ARG, + __entry->enabled ? "" : "not ", __entry->timeout) +); + +TRACE_EVENT(rdev_connect, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_connect_params *sme), + TP_ARGS(wiphy, netdev, sme), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + __array(char, ssid, IEEE80211_MAX_SSID_LEN + 1) + __field(enum nl80211_auth_type, auth_type) + __field(bool, privacy) + __field(u32, wpa_versions) + __field(u32, flags) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, sme->bssid); + memset(__entry->ssid, 0, IEEE80211_MAX_SSID_LEN + 1); + memcpy(__entry->ssid, sme->ssid, sme->ssid_len); + __entry->auth_type = sme->auth_type; + __entry->privacy = sme->privacy; + __entry->wpa_versions = sme->crypto.wpa_versions; + __entry->flags = sme->flags; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT + ", ssid: %s, auth type: %d, privacy: %s, wpa versions: %u, " + "flags: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), __entry->ssid, + __entry->auth_type, BOOL_TO_STR(__entry->privacy), + __entry->wpa_versions, __entry->flags) +); + +TRACE_EVENT(rdev_set_cqm_rssi_config, + TP_PROTO(struct wiphy *wiphy, + struct net_device *netdev, s32 rssi_thold, + u32 rssi_hyst), + TP_ARGS(wiphy, netdev, rssi_thold, rssi_hyst), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(s32, rssi_thold) + __field(u32, rssi_hyst) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->rssi_thold = rssi_thold; + __entry->rssi_hyst = rssi_hyst; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT + ", rssi_thold: %d, rssi_hyst: %u ", + WIPHY_PR_ARG, NETDEV_PR_ARG, + __entry->rssi_thold, __entry->rssi_hyst) +); + +TRACE_EVENT(rdev_set_cqm_txe_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u32 rate, + u32 pkts, u32 intvl), + TP_ARGS(wiphy, netdev, rate, pkts, intvl), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u32, rate) + __field(u32, pkts) + __field(u32, intvl) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->rate = rate; + __entry->pkts = pkts; + __entry->intvl = intvl; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", rate: %u, packets: %u, interval: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->rate, __entry->pkts, + __entry->intvl) +); + +TRACE_EVENT(rdev_disconnect, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + u16 reason_code), + TP_ARGS(wiphy, netdev, reason_code), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u16, reason_code) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->reason_code = reason_code; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", reason code: %u", WIPHY_PR_ARG, + NETDEV_PR_ARG, __entry->reason_code) +); + +TRACE_EVENT(rdev_join_ibss, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_ibss_params *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + __array(char, ssid, IEEE80211_MAX_SSID_LEN + 1) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, params->bssid); + memset(__entry->ssid, 0, IEEE80211_MAX_SSID_LEN + 1); + memcpy(__entry->ssid, params->ssid, params->ssid_len); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT ", ssid: %s", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid), __entry->ssid) +); + +TRACE_EVENT(rdev_set_wiphy_params, + TP_PROTO(struct wiphy *wiphy, u32 changed), + TP_ARGS(wiphy, changed), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(u32, changed) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->changed = changed; + ), + TP_printk(WIPHY_PR_FMT ", changed: %u", + WIPHY_PR_ARG, __entry->changed) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_get_tx_power, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + +TRACE_EVENT(rdev_set_tx_power, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + enum nl80211_tx_power_setting type, int mbm), + TP_ARGS(wiphy, wdev, type, mbm), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(enum nl80211_tx_power_setting, type) + __field(int, mbm) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->type = type; + __entry->mbm = mbm; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", type: %u, mbm: %d", + WIPHY_PR_ARG, WDEV_PR_ARG,__entry->type, __entry->mbm) +); + +TRACE_EVENT(rdev_return_int_int, + TP_PROTO(struct wiphy *wiphy, int func_ret, int func_fill), + TP_ARGS(wiphy, func_ret, func_fill), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, func_ret) + __field(int, func_fill) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->func_ret = func_ret; + __entry->func_fill = func_fill; + ), + TP_printk(WIPHY_PR_FMT ", function returns: %d, function filled: %d", + WIPHY_PR_ARG, __entry->func_ret, __entry->func_fill) +); + +#ifdef CONFIG_NL80211_TESTMODE +TRACE_EVENT(rdev_testmode_cmd, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy), + TP_STRUCT__entry( + WIPHY_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT, WIPHY_PR_ARG) +); + +TRACE_EVENT(rdev_testmode_dump, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy), + TP_STRUCT__entry( + WIPHY_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT, WIPHY_PR_ARG) +); +#endif /* CONFIG_NL80211_TESTMODE */ + +TRACE_EVENT(rdev_set_bitrate_mask, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + const u8 *peer, const struct cfg80211_bitrate_mask *mask), + TP_ARGS(wiphy, netdev, peer, mask), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer)) +); + +TRACE_EVENT(rdev_mgmt_frame_register, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + u16 frame_type, bool reg), + TP_ARGS(wiphy, wdev, frame_type, reg), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(u16, frame_type) + __field(bool, reg) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->frame_type = frame_type; + __entry->reg = reg; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", frame_type: 0x%.2x, reg: %s ", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->frame_type, + __entry->reg ? "true" : "false") +); + +TRACE_EVENT(rdev_return_int_tx_rx, + TP_PROTO(struct wiphy *wiphy, int ret, u32 tx, u32 rx), + TP_ARGS(wiphy, ret, tx, rx), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, ret) + __field(u32, tx) + __field(u32, rx) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->ret = ret; + __entry->tx = tx; + __entry->rx = rx; + ), + TP_printk(WIPHY_PR_FMT ", returned %d, tx: %u, rx: %u", + WIPHY_PR_ARG, __entry->ret, __entry->tx, __entry->rx) +); + +TRACE_EVENT(rdev_return_void_tx_rx, + TP_PROTO(struct wiphy *wiphy, u32 tx, u32 tx_max, + u32 rx, u32 rx_max), + TP_ARGS(wiphy, tx, tx_max, rx, rx_max), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(u32, tx) + __field(u32, tx_max) + __field(u32, rx) + __field(u32, rx_max) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->tx = tx; + __entry->tx_max = tx_max; + __entry->rx = rx; + __entry->rx_max = rx_max; + ), + TP_printk(WIPHY_PR_FMT ", tx: %u, tx_max: %u, rx: %u, rx_max: %u ", + WIPHY_PR_ARG, __entry->tx, __entry->tx_max, __entry->rx, + __entry->rx_max) +); + +DECLARE_EVENT_CLASS(tx_rx_evt, + TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx), + TP_ARGS(wiphy, rx, tx), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(u32, tx) + __field(u32, rx) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->tx = tx; + __entry->rx = rx; + ), + TP_printk(WIPHY_PR_FMT ", tx: %u, rx: %u ", + WIPHY_PR_ARG, __entry->tx, __entry->rx) +); + +DEFINE_EVENT(tx_rx_evt, rdev_set_ringparam, + TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx), + TP_ARGS(wiphy, rx, tx) +); + +DEFINE_EVENT(tx_rx_evt, rdev_set_antenna, + TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx), + TP_ARGS(wiphy, rx, tx) +); + +TRACE_EVENT(rdev_sched_scan_start, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_sched_scan_request *request), + TP_ARGS(wiphy, netdev, request), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG) +); + +TRACE_EVENT(rdev_tdls_mgmt, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, const u8 *buf, size_t len), + TP_ARGS(wiphy, netdev, peer, action_code, dialog_token, status_code, + buf, len), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + __field(u8, action_code) + __field(u8, dialog_token) + __field(u16, status_code) + __dynamic_array(u8, buf, len) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + __entry->action_code = action_code; + __entry->dialog_token = dialog_token; + __entry->status_code = status_code; + memcpy(__get_dynamic_array(buf), buf, len); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", action_code: %u, " + "dialog_token: %u, status_code: %u, buf: %#.2x ", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), + __entry->action_code, __entry->dialog_token, + __entry->status_code, ((u8 *)__get_dynamic_array(buf))[0]) +); + +TRACE_EVENT(rdev_dump_survey, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int idx), + TP_ARGS(wiphy, netdev, idx), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(int, idx) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->idx = idx; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", index: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->idx) +); + +TRACE_EVENT(rdev_return_int_survey_info, + TP_PROTO(struct wiphy *wiphy, int ret, struct survey_info *info), + TP_ARGS(wiphy, ret, info), + TP_STRUCT__entry( + WIPHY_ENTRY + CHAN_ENTRY + __field(int, ret) + __field(u64, channel_time) + __field(u64, channel_time_busy) + __field(u64, channel_time_ext_busy) + __field(u64, channel_time_rx) + __field(u64, channel_time_tx) + __field(u32, filled) + __field(s8, noise) + ), + TP_fast_assign( + WIPHY_ASSIGN; + CHAN_ASSIGN(info->channel); + __entry->ret = ret; + __entry->channel_time = info->channel_time; + __entry->channel_time_busy = info->channel_time_busy; + __entry->channel_time_ext_busy = info->channel_time_ext_busy; + __entry->channel_time_rx = info->channel_time_rx; + __entry->channel_time_tx = info->channel_time_tx; + __entry->filled = info->filled; + __entry->noise = info->noise; + ), + TP_printk(WIPHY_PR_FMT ", returned: %d, " CHAN_PR_FMT + ", channel time: %llu, channel time busy: %llu, " + "channel time extension busy: %llu, channel time rx: %llu, " + "channel time tx: %llu, filled: %u, noise: %d", + WIPHY_PR_ARG, __entry->ret, CHAN_PR_ARG, + __entry->channel_time, __entry->channel_time_busy, + __entry->channel_time_ext_busy, __entry->channel_time_rx, + __entry->channel_time_tx, __entry->filled, __entry->noise) +); + +TRACE_EVENT(rdev_tdls_oper, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + u8 *peer, enum nl80211_tdls_operation oper), + TP_ARGS(wiphy, netdev, peer, oper), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + __field(enum nl80211_tdls_operation, oper) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + __entry->oper = oper; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", oper: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->oper) +); + +DECLARE_EVENT_CLASS(rdev_pmksa, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_pmksa *pmksa), + TP_ARGS(wiphy, netdev, pmksa), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, pmksa->bssid); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(bssid)) +); + +TRACE_EVENT(rdev_probe_client, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + const u8 *peer), + TP_ARGS(wiphy, netdev, peer), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer)) +); + +DEFINE_EVENT(rdev_pmksa, rdev_set_pmksa, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_pmksa *pmksa), + TP_ARGS(wiphy, netdev, pmksa) +); + +DEFINE_EVENT(rdev_pmksa, rdev_del_pmksa, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_pmksa *pmksa), + TP_ARGS(wiphy, netdev, pmksa) +); + +TRACE_EVENT(rdev_remain_on_channel, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + struct ieee80211_channel *chan, + unsigned int duration), + TP_ARGS(wiphy, wdev, chan, duration), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + CHAN_ENTRY + __field(unsigned int, duration) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + CHAN_ASSIGN(chan); + __entry->duration = duration; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", " CHAN_PR_FMT ", duration: %u", + WIPHY_PR_ARG, WDEV_PR_ARG, CHAN_PR_ARG, __entry->duration) +); + +TRACE_EVENT(rdev_return_int_cookie, + TP_PROTO(struct wiphy *wiphy, int ret, u64 cookie), + TP_ARGS(wiphy, ret, cookie), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, ret) + __field(u64, cookie) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->ret = ret; + __entry->cookie = cookie; + ), + TP_printk(WIPHY_PR_FMT ", returned %d, cookie: %llu", + WIPHY_PR_ARG, __entry->ret, __entry->cookie) +); + +TRACE_EVENT(rdev_cancel_remain_on_channel, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie), + TP_ARGS(wiphy, wdev, cookie), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + __field(u64, cookie) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + __entry->cookie = cookie; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", cookie: %llu", + WIPHY_PR_ARG, WDEV_PR_ARG, __entry->cookie) +); + +TRACE_EVENT(rdev_mgmt_tx, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, + struct ieee80211_channel *chan, bool offchan, + unsigned int wait, bool no_cck, bool dont_wait_for_ack), + TP_ARGS(wiphy, wdev, chan, offchan, wait, no_cck, dont_wait_for_ack), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + CHAN_ENTRY + __field(bool, offchan) + __field(unsigned int, wait) + __field(bool, no_cck) + __field(bool, dont_wait_for_ack) + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + CHAN_ASSIGN(chan); + __entry->offchan = offchan; + __entry->wait = wait; + __entry->no_cck = no_cck; + __entry->dont_wait_for_ack = dont_wait_for_ack; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", " CHAN_PR_FMT ", offchan: %s," + " wait: %u, no cck: %s, dont wait for ack: %s", + WIPHY_PR_ARG, WDEV_PR_ARG, CHAN_PR_ARG, + BOOL_TO_STR(__entry->offchan), __entry->wait, + BOOL_TO_STR(__entry->no_cck), + BOOL_TO_STR(__entry->dont_wait_for_ack)) +); + +TRACE_EVENT(rdev_set_noack_map, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + u16 noack_map), + TP_ARGS(wiphy, netdev, noack_map), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u16, noack_map) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->noack_map = noack_map; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", noack_map: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->noack_map) +); + +TRACE_EVENT(rdev_get_et_sset_count, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int sset), + TP_ARGS(wiphy, netdev, sset), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(int, sset) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->sset = sset; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", sset: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sset) +); + +TRACE_EVENT(rdev_get_et_strings, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u32 sset), + TP_ARGS(wiphy, netdev, sset), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u32, sset) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->sset = sset; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", sset: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sset) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_get_channel, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + +TRACE_EVENT(rdev_return_chandef, + TP_PROTO(struct wiphy *wiphy, int ret, + struct cfg80211_chan_def *chandef), + TP_ARGS(wiphy, ret, chandef), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, ret) + CHAN_DEF_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + if (ret == 0) + CHAN_DEF_ASSIGN(chandef); + else + CHAN_DEF_ASSIGN((struct cfg80211_chan_def *)NULL); + __entry->ret = ret; + ), + TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", ret: %d", + WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->ret) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_start_p2p_device, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + +DEFINE_EVENT(wiphy_wdev_evt, rdev_stop_p2p_device, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev) +); + +/************************************************************* + * cfg80211 exported functions traces * + *************************************************************/ + +TRACE_EVENT(cfg80211_return_bool, + TP_PROTO(bool ret), + TP_ARGS(ret), + TP_STRUCT__entry( + __field(bool, ret) + ), + TP_fast_assign( + __entry->ret = ret; + ), + TP_printk("returned %s", BOOL_TO_STR(__entry->ret)) +); + +DECLARE_EVENT_CLASS(cfg80211_netdev_mac_evt, + TP_PROTO(struct net_device *netdev, const u8 *macaddr), + TP_ARGS(netdev, macaddr), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(macaddr) + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(macaddr, macaddr); + ), + TP_printk(NETDEV_PR_FMT ", mac: " MAC_PR_FMT, + NETDEV_PR_ARG, MAC_PR_ARG(macaddr)) +); + +DEFINE_EVENT(cfg80211_netdev_mac_evt, cfg80211_notify_new_peer_candidate, + TP_PROTO(struct net_device *netdev, const u8 *macaddr), + TP_ARGS(netdev, macaddr) +); + +DECLARE_EVENT_CLASS(netdev_evt_only, + TP_PROTO(struct net_device *netdev), + TP_ARGS(netdev), + TP_STRUCT__entry( + NETDEV_ENTRY + ), + TP_fast_assign( + NETDEV_ASSIGN; + ), + TP_printk(NETDEV_PR_FMT , NETDEV_PR_ARG) +); + +DEFINE_EVENT(netdev_evt_only, cfg80211_send_rx_auth, + TP_PROTO(struct net_device *netdev), + TP_ARGS(netdev) +); + +TRACE_EVENT(cfg80211_send_rx_assoc, + TP_PROTO(struct net_device *netdev, struct cfg80211_bss *bss), + TP_ARGS(netdev, bss), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(bssid) + CHAN_ENTRY + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, bss->bssid); + CHAN_ASSIGN(bss->channel); + ), + TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", " CHAN_PR_FMT, + NETDEV_PR_ARG, MAC_PR_ARG(bssid), CHAN_PR_ARG) +); + +DEFINE_EVENT(netdev_evt_only, __cfg80211_send_deauth, + TP_PROTO(struct net_device *netdev), + TP_ARGS(netdev) +); + +DEFINE_EVENT(netdev_evt_only, __cfg80211_send_disassoc, + TP_PROTO(struct net_device *netdev), + TP_ARGS(netdev) +); + +DEFINE_EVENT(netdev_evt_only, cfg80211_send_unprot_deauth, + TP_PROTO(struct net_device *netdev), + TP_ARGS(netdev) +); + +DEFINE_EVENT(netdev_evt_only, cfg80211_send_unprot_disassoc, + TP_PROTO(struct net_device *netdev), + TP_ARGS(netdev) +); + +DECLARE_EVENT_CLASS(netdev_mac_evt, + TP_PROTO(struct net_device *netdev, const u8 *mac), + TP_ARGS(netdev, mac), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(mac) + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(mac, mac) + ), + TP_printk(NETDEV_PR_FMT ", mac: " MAC_PR_FMT, + NETDEV_PR_ARG, MAC_PR_ARG(mac)) +); + +DEFINE_EVENT(netdev_mac_evt, cfg80211_send_auth_timeout, + TP_PROTO(struct net_device *netdev, const u8 *mac), + TP_ARGS(netdev, mac) +); + +DEFINE_EVENT(netdev_mac_evt, cfg80211_send_assoc_timeout, + TP_PROTO(struct net_device *netdev, const u8 *mac), + TP_ARGS(netdev, mac) +); + +TRACE_EVENT(cfg80211_michael_mic_failure, + TP_PROTO(struct net_device *netdev, const u8 *addr, + enum nl80211_key_type key_type, int key_id, const u8 *tsc), + TP_ARGS(netdev, addr, key_type, key_id, tsc), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(addr) + __field(enum nl80211_key_type, key_type) + __field(int, key_id) + __array(u8, tsc, 6) + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(addr, addr); + __entry->key_type = key_type; + __entry->key_id = key_id; + memcpy(__entry->tsc, tsc, 6); + ), + TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm", + NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type, + __entry->key_id, __entry->tsc) +); + +TRACE_EVENT(cfg80211_ready_on_channel, + TP_PROTO(struct wireless_dev *wdev, u64 cookie, + struct ieee80211_channel *chan, + unsigned int duration), + TP_ARGS(wdev, cookie, chan, duration), + TP_STRUCT__entry( + WDEV_ENTRY + __field(u64, cookie) + CHAN_ENTRY + __field(unsigned int, duration) + ), + TP_fast_assign( + WDEV_ASSIGN; + __entry->cookie = cookie; + CHAN_ASSIGN(chan); + __entry->duration = duration; + ), + TP_printk(WDEV_PR_FMT ", cookie: %llu, " CHAN_PR_FMT ", duration: %u", + WDEV_PR_ARG, __entry->cookie, CHAN_PR_ARG, + __entry->duration) +); + +TRACE_EVENT(cfg80211_ready_on_channel_expired, + TP_PROTO(struct wireless_dev *wdev, u64 cookie, + struct ieee80211_channel *chan), + TP_ARGS(wdev, cookie, chan), + TP_STRUCT__entry( + WDEV_ENTRY + __field(u64, cookie) + CHAN_ENTRY + ), + TP_fast_assign( + WDEV_ASSIGN; + __entry->cookie = cookie; + CHAN_ASSIGN(chan); + ), + TP_printk(WDEV_PR_FMT ", cookie: %llu, " CHAN_PR_FMT, + WDEV_PR_ARG, __entry->cookie, CHAN_PR_ARG) +); + +TRACE_EVENT(cfg80211_new_sta, + TP_PROTO(struct net_device *netdev, const u8 *mac_addr, + struct station_info *sinfo), + TP_ARGS(netdev, mac_addr, sinfo), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(mac_addr) + SINFO_ENTRY + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(mac_addr, mac_addr); + SINFO_ASSIGN; + ), + TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT, + NETDEV_PR_ARG, MAC_PR_ARG(mac_addr)) +); + +DEFINE_EVENT(cfg80211_netdev_mac_evt, cfg80211_del_sta, + TP_PROTO(struct net_device *netdev, const u8 *macaddr), + TP_ARGS(netdev, macaddr) +); + +TRACE_EVENT(cfg80211_rx_mgmt, + TP_PROTO(struct wireless_dev *wdev, int freq, int sig_mbm), + TP_ARGS(wdev, freq, sig_mbm), + TP_STRUCT__entry( + WDEV_ENTRY + __field(int, freq) + __field(int, sig_mbm) + ), + TP_fast_assign( + WDEV_ASSIGN; + __entry->freq = freq; + __entry->sig_mbm = sig_mbm; + ), + TP_printk(WDEV_PR_FMT ", freq: %d, sig mbm: %d", + WDEV_PR_ARG, __entry->freq, __entry->sig_mbm) +); + +TRACE_EVENT(cfg80211_mgmt_tx_status, + TP_PROTO(struct wireless_dev *wdev, u64 cookie, bool ack), + TP_ARGS(wdev, cookie, ack), + TP_STRUCT__entry( + WDEV_ENTRY + __field(u64, cookie) + __field(bool, ack) + ), + TP_fast_assign( + WDEV_ASSIGN; + __entry->cookie = cookie; + __entry->ack = ack; + ), + TP_printk(WDEV_PR_FMT", cookie: %llu, ack: %s", + WDEV_PR_ARG, __entry->cookie, BOOL_TO_STR(__entry->ack)) +); + +TRACE_EVENT(cfg80211_cqm_rssi_notify, + TP_PROTO(struct net_device *netdev, + enum nl80211_cqm_rssi_threshold_event rssi_event), + TP_ARGS(netdev, rssi_event), + TP_STRUCT__entry( + NETDEV_ENTRY + __field(enum nl80211_cqm_rssi_threshold_event, rssi_event) + ), + TP_fast_assign( + NETDEV_ASSIGN; + __entry->rssi_event = rssi_event; + ), + TP_printk(NETDEV_PR_FMT ", rssi event: %d", + NETDEV_PR_ARG, __entry->rssi_event) +); + +TRACE_EVENT(cfg80211_reg_can_beacon, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef), + TP_ARGS(wiphy, chandef), + TP_STRUCT__entry( + WIPHY_ENTRY + CHAN_DEF_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + CHAN_DEF_ASSIGN(chandef); + ), + TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT, + WIPHY_PR_ARG, CHAN_DEF_PR_ARG) +); + +TRACE_EVENT(cfg80211_ch_switch_notify, + TP_PROTO(struct net_device *netdev, + struct cfg80211_chan_def *chandef), + TP_ARGS(netdev, chandef), + TP_STRUCT__entry( + NETDEV_ENTRY + CHAN_DEF_ENTRY + ), + TP_fast_assign( + NETDEV_ASSIGN; + CHAN_DEF_ASSIGN(chandef); + ), + TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT, + NETDEV_PR_ARG, CHAN_DEF_PR_ARG) +); + +DECLARE_EVENT_CLASS(cfg80211_rx_evt, + TP_PROTO(struct net_device *netdev, const u8 *addr), + TP_ARGS(netdev, addr), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(addr) + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(addr, addr); + ), + TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT, NETDEV_PR_ARG, MAC_PR_ARG(addr)) +); + +DEFINE_EVENT(cfg80211_rx_evt, cfg80211_ibss_joined, + TP_PROTO(struct net_device *netdev, const u8 *addr), + TP_ARGS(netdev, addr) +); + +DEFINE_EVENT(cfg80211_rx_evt, cfg80211_rx_spurious_frame, + TP_PROTO(struct net_device *netdev, const u8 *addr), + TP_ARGS(netdev, addr) +); + +DEFINE_EVENT(cfg80211_rx_evt, cfg80211_rx_unexpected_4addr_frame, + TP_PROTO(struct net_device *netdev, const u8 *addr), + TP_ARGS(netdev, addr) +); + +TRACE_EVENT(cfg80211_probe_status, + TP_PROTO(struct net_device *netdev, const u8 *addr, u64 cookie, + bool acked), + TP_ARGS(netdev, addr, cookie, acked), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(addr) + __field(u64, cookie) + __field(bool, acked) + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(addr, addr); + __entry->cookie = cookie; + __entry->acked = acked; + ), + TP_printk(NETDEV_PR_FMT " addr:" MAC_PR_FMT ", cookie: %llu, acked: %s", + NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->cookie, + BOOL_TO_STR(__entry->acked)) +); + +TRACE_EVENT(cfg80211_cqm_pktloss_notify, + TP_PROTO(struct net_device *netdev, const u8 *peer, u32 num_packets), + TP_ARGS(netdev, peer, num_packets), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(peer) + __field(u32, num_packets) + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + __entry->num_packets = num_packets; + ), + TP_printk(NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", num of lost packets: %u", + NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->num_packets) +); + +DEFINE_EVENT(cfg80211_netdev_mac_evt, cfg80211_gtk_rekey_notify, + TP_PROTO(struct net_device *netdev, const u8 *macaddr), + TP_ARGS(netdev, macaddr) +); + +TRACE_EVENT(cfg80211_pmksa_candidate_notify, + TP_PROTO(struct net_device *netdev, int index, const u8 *bssid, + bool preauth), + TP_ARGS(netdev, index, bssid, preauth), + TP_STRUCT__entry( + NETDEV_ENTRY + __field(int, index) + MAC_ENTRY(bssid) + __field(bool, preauth) + ), + TP_fast_assign( + NETDEV_ASSIGN; + __entry->index = index; + MAC_ASSIGN(bssid, bssid); + __entry->preauth = preauth; + ), + TP_printk(NETDEV_PR_FMT ", index:%d, bssid: " MAC_PR_FMT ", pre auth: %s", + NETDEV_PR_ARG, __entry->index, MAC_PR_ARG(bssid), + BOOL_TO_STR(__entry->preauth)) +); + +TRACE_EVENT(cfg80211_report_obss_beacon, + TP_PROTO(struct wiphy *wiphy, const u8 *frame, size_t len, + int freq, int sig_dbm), + TP_ARGS(wiphy, frame, len, freq, sig_dbm), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(int, freq) + __field(int, sig_dbm) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->freq = freq; + __entry->sig_dbm = sig_dbm; + ), + TP_printk(WIPHY_PR_FMT ", freq: %d, sig_dbm: %d", + WIPHY_PR_ARG, __entry->freq, __entry->sig_dbm) +); + +TRACE_EVENT(cfg80211_tdls_oper_request, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *peer, + enum nl80211_tdls_operation oper, u16 reason_code), + TP_ARGS(wiphy, netdev, peer, oper, reason_code), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + __field(enum nl80211_tdls_operation, oper) + __field(u16, reason_code) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + __entry->oper = oper; + __entry->reason_code = reason_code; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", oper: %d, reason_code %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->oper, + __entry->reason_code) + ); + +TRACE_EVENT(cfg80211_scan_done, + TP_PROTO(struct cfg80211_scan_request *request, bool aborted), + TP_ARGS(request, aborted), + TP_STRUCT__entry( + __field(u32, n_channels) + __dynamic_array(u8, ie, request ? request->ie_len : 0) + __array(u32, rates, IEEE80211_NUM_BANDS) + __field(u32, wdev_id) + MAC_ENTRY(wiphy_mac) + __field(bool, no_cck) + __field(bool, aborted) + ), + TP_fast_assign( + if (request) { + memcpy(__get_dynamic_array(ie), request->ie, + request->ie_len); + memcpy(__entry->rates, request->rates, + IEEE80211_NUM_BANDS); + __entry->wdev_id = request->wdev ? + request->wdev->identifier : 0; + if (request->wiphy) + MAC_ASSIGN(wiphy_mac, + request->wiphy->perm_addr); + __entry->no_cck = request->no_cck; + } + __entry->aborted = aborted; + ), + TP_printk("aborted: %s", BOOL_TO_STR(__entry->aborted)) +); + +DEFINE_EVENT(wiphy_only_evt, cfg80211_sched_scan_results, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy) +); + +DEFINE_EVENT(wiphy_only_evt, cfg80211_sched_scan_stopped, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy) +); + +TRACE_EVENT(cfg80211_get_bss, + TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel, + const u8 *bssid, const u8 *ssid, size_t ssid_len, + u16 capa_mask, u16 capa_val), + TP_ARGS(wiphy, channel, bssid, ssid, ssid_len, capa_mask, capa_val), + TP_STRUCT__entry( + WIPHY_ENTRY + CHAN_ENTRY + MAC_ENTRY(bssid) + __dynamic_array(u8, ssid, ssid_len) + __field(u16, capa_mask) + __field(u16, capa_val) + ), + TP_fast_assign( + WIPHY_ASSIGN; + CHAN_ASSIGN(channel); + MAC_ASSIGN(bssid, bssid); + memcpy(__get_dynamic_array(ssid), ssid, ssid_len); + __entry->capa_mask = capa_mask; + __entry->capa_val = capa_val; + ), + TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT ", " MAC_PR_FMT ", buf: %#.2x, " + "capa_mask: %d, capa_val: %u", WIPHY_PR_ARG, CHAN_PR_ARG, + MAC_PR_ARG(bssid), ((u8 *)__get_dynamic_array(ssid))[0], + __entry->capa_mask, __entry->capa_val) +); + +TRACE_EVENT(cfg80211_inform_bss_frame, + TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel, + struct ieee80211_mgmt *mgmt, size_t len, + s32 signal), + TP_ARGS(wiphy, channel, mgmt, len, signal), + TP_STRUCT__entry( + WIPHY_ENTRY + CHAN_ENTRY + __dynamic_array(u8, mgmt, len) + __field(s32, signal) + ), + TP_fast_assign( + WIPHY_ASSIGN; + CHAN_ASSIGN(channel); + if (mgmt) + memcpy(__get_dynamic_array(mgmt), mgmt, len); + __entry->signal = signal; + ), + TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT "signal: %d", + WIPHY_PR_ARG, CHAN_PR_ARG, __entry->signal) +); + +DECLARE_EVENT_CLASS(cfg80211_bss_evt, + TP_PROTO(struct cfg80211_bss *pub), + TP_ARGS(pub), + TP_STRUCT__entry( + MAC_ENTRY(bssid) + CHAN_ENTRY + ), + TP_fast_assign( + MAC_ASSIGN(bssid, pub->bssid); + CHAN_ASSIGN(pub->channel); + ), + TP_printk(MAC_PR_FMT ", " CHAN_PR_FMT, MAC_PR_ARG(bssid), CHAN_PR_ARG) +); + +DEFINE_EVENT(cfg80211_bss_evt, cfg80211_return_bss, + TP_PROTO(struct cfg80211_bss *pub), + TP_ARGS(pub) +); + +TRACE_EVENT(cfg80211_return_uint, + TP_PROTO(unsigned int ret), + TP_ARGS(ret), + TP_STRUCT__entry( + __field(unsigned int, ret) + ), + TP_fast_assign( + __entry->ret = ret; + ), + TP_printk("ret: %d", __entry->ret) +); + +TRACE_EVENT(cfg80211_return_u32, + TP_PROTO(u32 ret), + TP_ARGS(ret), + TP_STRUCT__entry( + __field(u32, ret) + ), + TP_fast_assign( + __entry->ret = ret; + ), + TP_printk("ret: %u", __entry->ret) +); + +#endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace +#include <trace/define_trace.h> diff --git a/net/wireless/util.c b/net/wireless/util.c index ef35f4ef2aa6..16d76a807c2f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -11,6 +11,8 @@ #include <net/ip.h> #include <net/dsfield.h> #include "core.h" +#include "rdev-ops.h" + struct ieee80211_rate * ieee80211_get_response_rate(struct ieee80211_supported_band *sband, @@ -309,23 +311,21 @@ unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb) } EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); -static int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) +unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) { int ae = meshhdr->flags & MESH_FLAGS_AE; - /* 7.1.3.5a.2 */ + /* 802.11-2012, 8.2.4.7.3 */ switch (ae) { + default: case 0: return 6; case MESH_FLAGS_AE_A4: return 12; case MESH_FLAGS_AE_A5_A6: return 18; - case (MESH_FLAGS_AE_A4 | MESH_FLAGS_AE_A5_A6): - return 24; - default: - return 6; } } +EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype) @@ -373,6 +373,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, /* make sure meshdr->flags is on the linear part */ if (!pskb_may_pull(skb, hdrlen + 1)) return -1; + if (meshdr->flags & MESH_FLAGS_AE_A4) + return -1; if (meshdr->flags & MESH_FLAGS_AE_A5_A6) { skb_copy_bits(skb, hdrlen + offsetof(struct ieee80211s_hdr, eaddr1), @@ -397,6 +399,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, /* make sure meshdr->flags is on the linear part */ if (!pskb_may_pull(skb, hdrlen + 1)) return -1; + if (meshdr->flags & MESH_FLAGS_AE_A5_A6) + return -1; if (meshdr->flags & MESH_FLAGS_AE_A4) skb_copy_bits(skb, hdrlen + offsetof(struct ieee80211s_hdr, eaddr1), @@ -684,10 +688,13 @@ EXPORT_SYMBOL(cfg80211_classify8021d); const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie) { - if (bss->information_elements == NULL) + const struct cfg80211_bss_ies *ies; + + ies = rcu_dereference(bss->ies); + if (!ies) return NULL; - return cfg80211_find_ie(ie, bss->information_elements, - bss->len_information_elements); + + return cfg80211_find_ie(ie, ies->data, ies->len); } EXPORT_SYMBOL(ieee80211_bss_get_ie); @@ -703,19 +710,18 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) for (i = 0; i < 6; i++) { if (!wdev->connect_keys->params[i].cipher) continue; - if (rdev->ops->add_key(wdev->wiphy, dev, i, false, NULL, - &wdev->connect_keys->params[i])) { + if (rdev_add_key(rdev, dev, i, false, NULL, + &wdev->connect_keys->params[i])) { netdev_err(dev, "failed to set key %d\n", i); continue; } if (wdev->connect_keys->def == i) - if (rdev->ops->set_default_key(wdev->wiphy, dev, - i, true, true)) { + if (rdev_set_default_key(rdev, dev, i, true, true)) { netdev_err(dev, "failed to set defkey %d\n", i); continue; } if (wdev->connect_keys->defmgmt == i) - if (rdev->ops->set_default_mgmt_key(wdev->wiphy, dev, i)) + if (rdev_set_default_mgmt_key(rdev, dev, i)) netdev_err(dev, "failed to set mgtdef %d\n", i); } @@ -848,8 +854,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, cfg80211_process_rdev_events(rdev); } - err = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, - ntype, flags, params); + err = rdev_change_virtual_intf(rdev, dev, ntype, flags, params); WARN_ON(!err && dev->ieee80211_ptr->iftype != ntype); @@ -942,14 +947,86 @@ static u32 cfg80211_calculate_bitrate_60g(struct rate_info *rate) return __mcs2bitrate[rate->mcs]; } +static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) +{ + static const u32 base[4][10] = { + { 6500000, + 13000000, + 19500000, + 26000000, + 39000000, + 52000000, + 58500000, + 65000000, + 78000000, + 0, + }, + { 13500000, + 27000000, + 40500000, + 54000000, + 81000000, + 108000000, + 121500000, + 135000000, + 162000000, + 180000000, + }, + { 29300000, + 58500000, + 87800000, + 117000000, + 175500000, + 234000000, + 263300000, + 292500000, + 351000000, + 390000000, + }, + { 58500000, + 117000000, + 175500000, + 234000000, + 351000000, + 468000000, + 526500000, + 585000000, + 702000000, + 780000000, + }, + }; + u32 bitrate; + int idx; + + if (WARN_ON_ONCE(rate->mcs > 9)) + return 0; + + idx = rate->flags & (RATE_INFO_FLAGS_160_MHZ_WIDTH | + RATE_INFO_FLAGS_80P80_MHZ_WIDTH) ? 3 : + rate->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH ? 2 : + rate->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH ? 1 : 0; + + bitrate = base[idx][rate->mcs]; + bitrate *= rate->nss; + + if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) + bitrate = (bitrate / 9) * 10; + + /* do NOT round down here */ + return (bitrate + 50000) / 100000; +} + u32 cfg80211_calculate_bitrate(struct rate_info *rate) { int modulation, streams, bitrate; - if (!(rate->flags & RATE_INFO_FLAGS_MCS)) + if (!(rate->flags & RATE_INFO_FLAGS_MCS) && + !(rate->flags & RATE_INFO_FLAGS_VHT_MCS)) return rate->legacy; if (rate->flags & RATE_INFO_FLAGS_60G) return cfg80211_calculate_bitrate_60g(rate); + if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) + return cfg80211_calculate_bitrate_vht(rate); /* the formula below does only work for MCS values smaller than 32 */ if (WARN_ON_ONCE(rate->mcs >= 32)) @@ -978,6 +1055,106 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate) } EXPORT_SYMBOL(cfg80211_calculate_bitrate); +int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, + enum ieee80211_p2p_attr_id attr, + u8 *buf, unsigned int bufsize) +{ + u8 *out = buf; + u16 attr_remaining = 0; + bool desired_attr = false; + u16 desired_len = 0; + + while (len > 0) { + unsigned int iedatalen; + unsigned int copy; + const u8 *iedata; + + if (len < 2) + return -EILSEQ; + iedatalen = ies[1]; + if (iedatalen + 2 > len) + return -EILSEQ; + + if (ies[0] != WLAN_EID_VENDOR_SPECIFIC) + goto cont; + + if (iedatalen < 4) + goto cont; + + iedata = ies + 2; + + /* check WFA OUI, P2P subtype */ + if (iedata[0] != 0x50 || iedata[1] != 0x6f || + iedata[2] != 0x9a || iedata[3] != 0x09) + goto cont; + + iedatalen -= 4; + iedata += 4; + + /* check attribute continuation into this IE */ + copy = min_t(unsigned int, attr_remaining, iedatalen); + if (copy && desired_attr) { + desired_len += copy; + if (out) { + memcpy(out, iedata, min(bufsize, copy)); + out += min(bufsize, copy); + bufsize -= min(bufsize, copy); + } + + + if (copy == attr_remaining) + return desired_len; + } + + attr_remaining -= copy; + if (attr_remaining) + goto cont; + + iedatalen -= copy; + iedata += copy; + + while (iedatalen > 0) { + u16 attr_len; + + /* P2P attribute ID & size must fit */ + if (iedatalen < 3) + return -EILSEQ; + desired_attr = iedata[0] == attr; + attr_len = get_unaligned_le16(iedata + 1); + iedatalen -= 3; + iedata += 3; + + copy = min_t(unsigned int, attr_len, iedatalen); + + if (desired_attr) { + desired_len += copy; + if (out) { + memcpy(out, iedata, min(bufsize, copy)); + out += min(bufsize, copy); + bufsize -= min(bufsize, copy); + } + + if (copy == attr_len) + return desired_len; + } + + iedata += copy; + iedatalen -= copy; + attr_remaining = attr_len - copy; + } + + cont: + len -= ies[1] + 2; + ies += ies[1] + 2; + } + + if (attr_remaining && desired_attr) + return -EILSEQ; + + return -ENOENT; +} +EXPORT_SYMBOL(cfg80211_get_p2p_attr); + int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, u32 beacon_int) { diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 494379eb464f..d997d0f0c54a 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -19,6 +19,7 @@ #include <net/cfg80211-wext.h> #include "wext-compat.h" #include "core.h" +#include "rdev-ops.h" int cfg80211_wext_giwname(struct net_device *dev, struct iw_request_info *info, @@ -175,7 +176,7 @@ int cfg80211_wext_giwrange(struct net_device *dev, case CFG80211_SIGNAL_TYPE_NONE: break; case CFG80211_SIGNAL_TYPE_MBM: - range->max_qual.level = -110; + range->max_qual.level = (u8)-110; range->max_qual.qual = 70; range->avg_qual.qual = 35; range->max_qual.updated |= IW_QUAL_DBM; @@ -301,8 +302,7 @@ int cfg80211_wext_siwrts(struct net_device *dev, else wdev->wiphy->rts_threshold = rts->value; - err = rdev->ops->set_wiphy_params(wdev->wiphy, - WIPHY_PARAM_RTS_THRESHOLD); + err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_RTS_THRESHOLD); if (err) wdev->wiphy->rts_threshold = orts; @@ -342,8 +342,7 @@ int cfg80211_wext_siwfrag(struct net_device *dev, wdev->wiphy->frag_threshold = frag->value & ~0x1; } - err = rdev->ops->set_wiphy_params(wdev->wiphy, - WIPHY_PARAM_FRAG_THRESHOLD); + err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_FRAG_THRESHOLD); if (err) wdev->wiphy->frag_threshold = ofrag; @@ -396,7 +395,7 @@ static int cfg80211_wext_siwretry(struct net_device *dev, if (!changed) return 0; - err = rdev->ops->set_wiphy_params(wdev->wiphy, changed); + err = rdev_set_wiphy_params(rdev, changed); if (err) { wdev->wiphy->retry_short = oshort; wdev->wiphy->retry_long = olong; @@ -490,8 +489,8 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) err = -ENOENT; else - err = rdev->ops->del_key(&rdev->wiphy, dev, idx, - pairwise, addr); + err = rdev_del_key(rdev, dev, idx, pairwise, + addr); } wdev->wext.connect.privacy = false; /* @@ -525,8 +524,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, err = 0; if (wdev->current_bss) - err = rdev->ops->add_key(&rdev->wiphy, dev, idx, - pairwise, addr, params); + err = rdev_add_key(rdev, dev, idx, pairwise, addr, params); if (err) return err; @@ -552,8 +550,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, __cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } - err = rdev->ops->set_default_key(&rdev->wiphy, dev, - idx, true, true); + err = rdev_set_default_key(rdev, dev, idx, true, true); } if (!err) { wdev->wext.default_key = idx; @@ -566,8 +563,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC && (tx_key || (!addr && wdev->wext.default_mgmt_key == -1))) { if (wdev->current_bss) - err = rdev->ops->set_default_mgmt_key(&rdev->wiphy, - dev, idx); + err = rdev_set_default_mgmt_key(rdev, dev, idx); if (!err) wdev->wext.default_mgmt_key = idx; return err; @@ -631,8 +627,8 @@ static int cfg80211_wext_siwencode(struct net_device *dev, err = 0; wdev_lock(wdev); if (wdev->current_bss) - err = rdev->ops->set_default_key(&rdev->wiphy, dev, - idx, true, true); + err = rdev_set_default_key(rdev, dev, idx, true, + true); if (!err) wdev->wext.default_key = idx; wdev_unlock(wdev); @@ -788,6 +784,9 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); + struct cfg80211_chan_def chandef = { + .width = NL80211_CHAN_WIDTH_20_NOHT, + }; int freq, err; switch (wdev->iftype) { @@ -801,8 +800,12 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, return freq; if (freq == 0) return -EINVAL; + chandef.center_freq1 = freq; + chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); + if (!chandef.chan) + return -EINVAL; mutex_lock(&rdev->devlist_mtx); - err = cfg80211_set_monitor_channel(rdev, freq, NL80211_CHAN_NO_HT); + err = cfg80211_set_monitor_channel(rdev, &chandef); mutex_unlock(&rdev->devlist_mtx); return err; case NL80211_IFTYPE_MESH_POINT: @@ -811,9 +814,12 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, return freq; if (freq == 0) return -EINVAL; + chandef.center_freq1 = freq; + chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); + if (!chandef.chan) + return -EINVAL; mutex_lock(&rdev->devlist_mtx); - err = cfg80211_set_mesh_freq(rdev, wdev, freq, - NL80211_CHAN_NO_HT); + err = cfg80211_set_mesh_channel(rdev, wdev, &chandef); mutex_unlock(&rdev->devlist_mtx); return err; default: @@ -827,8 +833,8 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); - struct ieee80211_channel *chan; - enum nl80211_channel_type channel_type; + struct cfg80211_chan_def chandef; + int ret; switch (wdev->iftype) { case NL80211_IFTYPE_STATION: @@ -839,10 +845,10 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, if (!rdev->ops->get_channel) return -EINVAL; - chan = rdev->ops->get_channel(wdev->wiphy, wdev, &channel_type); - if (!chan) - return -EINVAL; - freq->m = chan->center_freq; + ret = rdev_get_channel(rdev, wdev, &chandef); + if (ret) + return ret; + freq->m = chandef.chan->center_freq; freq->e = 6; return 0; default: @@ -899,7 +905,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, return 0; } - return rdev->ops->set_tx_power(wdev->wiphy, type, DBM_TO_MBM(dbm)); + return rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm)); } static int cfg80211_wext_giwtxpower(struct net_device *dev, @@ -918,7 +924,7 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev, if (!rdev->ops->get_tx_power) return -EOPNOTSUPP; - err = rdev->ops->get_tx_power(wdev->wiphy, &val); + err = rdev_get_tx_power(rdev, wdev, &val); if (err) return err; @@ -1158,7 +1164,7 @@ static int cfg80211_wext_siwpower(struct net_device *dev, timeout = wrq->value / 1000; } - err = rdev->ops->set_power_mgmt(wdev->wiphy, dev, ps, timeout); + err = rdev_set_power_mgmt(rdev, dev, ps, timeout); if (err) return err; @@ -1200,7 +1206,7 @@ static int cfg80211_wds_wext_siwap(struct net_device *dev, if (!rdev->ops->set_wds_peer) return -EOPNOTSUPP; - err = rdev->ops->set_wds_peer(wdev->wiphy, dev, (u8 *) &addr->sa_data); + err = rdev_set_wds_peer(rdev, dev, (u8 *)&addr->sa_data); if (err) return err; @@ -1272,7 +1278,7 @@ static int cfg80211_wext_siwrate(struct net_device *dev, if (!match) return -EINVAL; - return rdev->ops->set_bitrate_mask(wdev->wiphy, dev, NULL, &mask); + return rdev_set_bitrate_mask(rdev, dev, NULL, &mask); } static int cfg80211_wext_giwrate(struct net_device *dev, @@ -1302,7 +1308,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev, if (err) return err; - err = rdev->ops->get_station(&rdev->wiphy, dev, addr, &sinfo); + err = rdev_get_station(rdev, dev, addr, &sinfo); if (err) return err; @@ -1339,7 +1345,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) memcpy(bssid, wdev->current_bss->pub.bssid, ETH_ALEN); wdev_unlock(wdev); - if (rdev->ops->get_station(&rdev->wiphy, dev, bssid, &sinfo)) + if (rdev_get_station(rdev, dev, bssid, &sinfo)) return NULL; memset(&wstats, 0, sizeof(wstats)); @@ -1474,19 +1480,19 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev, if (!rdev->ops->set_pmksa) return -EOPNOTSUPP; - return rdev->ops->set_pmksa(&rdev->wiphy, dev, &cfg_pmksa); + return rdev_set_pmksa(rdev, dev, &cfg_pmksa); case IW_PMKSA_REMOVE: if (!rdev->ops->del_pmksa) return -EOPNOTSUPP; - return rdev->ops->del_pmksa(&rdev->wiphy, dev, &cfg_pmksa); + return rdev_del_pmksa(rdev, dev, &cfg_pmksa); case IW_PMKSA_FLUSH: if (!rdev->ops->flush_pmksa) return -EOPNOTSUPP; - return rdev->ops->flush_pmksa(&rdev->wiphy, dev); + return rdev_flush_pmksa(rdev, dev); default: return -EOPNOTSUPP; diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 1f773f668d1a..fb9622f6d99c 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -119,7 +119,16 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, * channel we disconnected above and reconnect below. */ if (chan && !wdev->wext.connect.ssid_len) { - err = cfg80211_set_monitor_channel(rdev, freq, NL80211_CHAN_NO_HT); + struct cfg80211_chan_def chandef = { + .width = NL80211_CHAN_WIDTH_20_NOHT, + .center_freq1 = freq, + }; + + chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); + if (chandef.chan) + err = cfg80211_set_monitor_channel(rdev, &chandef); + else + err = -EINVAL; goto out; } @@ -233,13 +242,17 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, wdev_lock(wdev); if (wdev->current_bss) { - const u8 *ie = ieee80211_bss_get_ie(&wdev->current_bss->pub, - WLAN_EID_SSID); + const u8 *ie; + + rcu_read_lock(); + ie = ieee80211_bss_get_ie(&wdev->current_bss->pub, + WLAN_EID_SSID); if (ie) { data->flags = 1; data->length = ie[1]; memcpy(ssid, ie + 2, data->length); } + rcu_read_unlock(); } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { data->flags = 1; data->length = wdev->wext.connect.ssid_len; diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index e5246fbe36c4..2906d520eea7 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -276,18 +276,16 @@ static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name) struct crypto_comp * __percpu *tfms; int cpu; - /* This can be any valid CPU ID so we don't need locking. */ - cpu = raw_smp_processor_id(); list_for_each_entry(pos, &ipcomp_tfms_list, list) { struct crypto_comp *tfm; - tfms = pos->tfms; - tfm = *per_cpu_ptr(tfms, cpu); + /* This can be any valid CPU ID so we don't need locking. */ + tfm = __this_cpu_read(*pos->tfms); if (!strcmp(crypto_comp_name(tfm), alg_name)) { pos->users++; - return tfms; + return pos->tfms; } } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 41eabc46f110..07c585756d2a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2656,7 +2656,7 @@ static void xfrm_policy_fini(struct net *net) WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir])); htab = &net->xfrm.policy_bydst[dir]; - sz = (htab->hmask + 1); + sz = (htab->hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(htab->table)); xfrm_hash_free(htab->table, sz); } diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 3efb07d3eb27..35754cc8a9e5 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -242,11 +242,13 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) u32 diff; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; u32 seq = ntohl(net_seq); - u32 pos = (replay_esn->seq - 1) % replay_esn->replay_window; + u32 pos; if (!replay_esn->replay_window) return; + pos = (replay_esn->seq - 1) % replay_esn->replay_window; + if (seq > replay_esn->seq) { diff = seq - replay_esn->seq; @@ -521,13 +523,12 @@ int xfrm_init_replay(struct xfrm_state *x) replay_esn->bmp_len * sizeof(__u32) * 8) return -EINVAL; - if ((x->props.flags & XFRM_STATE_ESN) && replay_esn->replay_window == 0) - return -EINVAL; - - if ((x->props.flags & XFRM_STATE_ESN) && x->replay_esn) - x->repl = &xfrm_replay_esn; - else - x->repl = &xfrm_replay_bmp; + if (x->props.flags & XFRM_STATE_ESN) { + if (replay_esn->replay_window == 0) + return -EINVAL; + x->repl = &xfrm_replay_esn; + } else + x->repl = &xfrm_replay_bmp; } else x->repl = &xfrm_replay_legacy; diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c index 380976f74c4c..05a6e3d9c258 100644 --- a/net/xfrm/xfrm_sysctl.c +++ b/net/xfrm/xfrm_sysctl.c @@ -54,6 +54,10 @@ int __net_init xfrm_sysctl_init(struct net *net) table[2].data = &net->xfrm.sysctl_larval_drop; table[3].data = &net->xfrm.sysctl_acq_expires; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + net->xfrm.sysctl_hdr = register_net_sysctl(net, "net/core", table); if (!net->xfrm.sysctl_hdr) goto out_register; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 421f98444335..eb872b2e366e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2349,7 +2349,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) link = &xfrm_dispatch[type]; /* All operations require privileges, even GET */ - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || |