From: Gabor Juhos Date: Thu, 29 Nov 2012 17:37:18 +0000 (+0000) Subject: kernel: Add ATM fixes pending upstream merge (queue reduction, race fixes) X-Git-Url: https://git.librecmc.org/?a=commitdiff_plain;h=543c2c27d1dd16ad0025ecd54b543b1187d5609c;p=librecmc%2Flibrecmc.git kernel: Add ATM fixes pending upstream merge (queue reduction, race fixes) Patches about to go into net-next.git Signed-off-by: David Woodhouse Signed-off-by: Gabor Juhos SVN-Revision: 34410 --- diff --git a/target/linux/generic/patches-3.3/080-prot-release-cb.patch b/target/linux/generic/patches-3.3/080-prot-release-cb.patch new file mode 100644 index 0000000000..8af8a198f1 --- /dev/null +++ b/target/linux/generic/patches-3.3/080-prot-release-cb.patch @@ -0,0 +1,27 @@ +This was added in commit 46d3ceabd8d98ed0ad10f20c595ca784e34786c5 (tcp: +TCP Small Queues) but we need it for pppoatm too. + +--- a/include/net/sock.h ++++ b/include/net/sock.h +@@ -858,6 +858,8 @@ struct proto { + int (*backlog_rcv) (struct sock *sk, + struct sk_buff *skb); + ++ void (*release_cb)(struct sock *sk); ++ + /* Keeping track of sk's, looking them up, and port selection methods. */ + void (*hash)(struct sock *sk); + void (*unhash)(struct sock *sk); +--- a/net/core/sock.c ++++ b/net/core/sock.c +@@ -2159,6 +2159,10 @@ void release_sock(struct sock *sk) + spin_lock_bh(&sk->sk_lock.slock); + if (sk->sk_backlog.tail) + __release_sock(sk); ++ ++ if (sk->sk_prot->release_cb) ++ sk->sk_prot->release_cb(sk); ++ + sk->sk_lock.owned = 0; + if (waitqueue_active(&sk->sk_lock.wq)) + wake_up(&sk->sk_lock.wq); diff --git a/target/linux/generic/patches-3.3/131-atm-fixes.patch b/target/linux/generic/patches-3.3/131-atm-fixes.patch new file mode 100644 index 0000000000..734657a23b --- /dev/null +++ b/target/linux/generic/patches-3.3/131-atm-fixes.patch @@ -0,0 +1,709 @@ +commit 86768086727a60335b08c34b2966c784029a24cf +Author: David Woodhouse +Date: Wed Nov 28 10:15:05 2012 +0000 + + pppoatm: optimise PPP channel wakeups after sock_owned_by_user() + + We don't need to schedule the wakeup tasklet on *every* unlock; only if we + actually blocked the channel in the first place. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit a009aa5fde926350f7a7e558a3ac0180e10eb24a +Author: Krzysztof Mazur +Date: Wed Nov 28 09:08:04 2012 +0100 + + br2684: allow assign only on a connected socket + + The br2684 does not check if used vcc is in connected state, + causing potential Oops in pppoatm_send() when vcc->send() is called + on not fully connected socket. + + Now br2684 can be assigned only on connected sockets; otherwise + -EINVAL error is returned. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit ae2169bcb6375fb214cadd0ea50ac54bcf39b0d6 +Author: Nathan Williams +Date: Tue Nov 27 17:34:09 2012 +1100 + + solos-pci: Fix leak of skb received for unknown vcc + + ... and ensure that the next skb is set up for RX in the DMA case. + + Signed-off-by: Nathan Williams + Signed-off-by: David Woodhouse + +commit 6227612becaebe2f9f4ad7d0cdf27e298bb56687 +Author: David Woodhouse +Date: Wed Nov 28 00:46:45 2012 +0000 + + br2684: fix module_put() race + + The br2684 code used module_put() during unassignment from vcc with + hope that we have BKL. This assumption is no longer true. + + Now owner field in atmvcc is used to move this module_put() + to vcc_destroy_socket(). + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 44abbb464896dc2270716d25e12fe47e57eeb1d3 +Author: David Woodhouse +Date: Wed Nov 28 00:05:52 2012 +0000 + + pppoatm: fix missing wakeup in pppoatm_send() + + Now that we can return zero from pppoatm_send() for reasons *other* than + the queue being full, that means we can't depend on a subsequent call to + pppoatm_pop() waking the queue, and we might leave it stalled + indefinitely. + + Use the ->release_cb() callback to wake the queue after the sock is + unlocked. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit c93eeac2ebee497dbc9b6ad39c235ff3061be141 +Author: David Woodhouse +Date: Wed Nov 28 00:03:11 2012 +0000 + + atm: Add release_cb() callback to vcc + + The immediate use case for this is that it will allow us to ensure that a + pppoatm queue is woken after it has to drop a packet due to the sock being + locked. + + Note that 'release_cb' is called when the socket is *unlocked*. This is + not to be confused with vcc_release() — which probably ought to be called + vcc_close(). + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 9b3e2e224cc4326d8897243b24d778abf9098a8d +Author: David Woodhouse +Date: Tue Nov 27 23:28:36 2012 +0000 + + br2684: don't send frames on not-ready vcc + + Avoid submitting packets to a vcc which is being closed. Things go badly + wrong when the ->pop method gets later called after everything's been + torn down. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 26c7c53318cf56a690ae553104f4a60181734fb5 +Author: David Woodhouse +Date: Tue Nov 27 23:49:24 2012 +0000 + + solos-pci: Wait for pending TX to complete when releasing vcc + + We should no longer be calling the old pop routine for the vcc, after + vcc_release() has completed. Make sure we wait for any pending TX skbs + to complete, by waiting for our own PKT_PCLOSE control skb to be sent. + + Signed-off-by: David Woodhouse + +commit 1a3304e89b9ba168340a37926014be11c3ad110e +Author: Krzysztof Mazur +Date: Tue Nov 6 23:17:02 2012 +0100 + + pppoatm: do not inline pppoatm_may_send() + + The pppoatm_may_send() is quite heavy and it's called three times + in pppoatm_send() and inlining costs more than 200 bytes of code + (more than 10% of total pppoatm driver code size). + + add/remove: 1/0 grow/shrink: 0/1 up/down: 132/-367 (-235) + function old new delta + pppoatm_may_send - 132 +132 + pppoatm_send 900 533 -367 + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 294398bcd0fe26335059a185b59cfb5de1fc4c71 +Author: Krzysztof Mazur +Date: Sat Nov 10 23:33:19 2012 +0100 + + pppoatm: drop frames to not-ready vcc + + Patches "atm: detach protocol before closing vcc" + and "pppoatm: allow assign only on a connected socket" fixed + common cases where the pppoatm_send() crashes while sending + frame to not-ready vcc. However there are still some other cases + where we can send frames to vcc, which is flagged as ATM_VF_CLOSE + (for instance after vcc_release_async()) or it's opened but not + ready yet. + + Now pppoatm_send(), like vcc_sendmsg(), checks for vcc flags that + indicate that vcc is not ready. If the vcc is not ready we just + drop frame. Queueing frames is much more complicated because we + don't have callbacks that inform us about vcc flags changes. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 3ac108006fd7f20cb8fc8ea2287f1497bcda00a1 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:17:00 2012 +0100 + + pppoatm: take ATM socket lock in pppoatm_send() + + The pppoatm_send() does not take any lock that will prevent concurrent + vcc_sendmsg(). This causes two problems: + + - there is no locking between checking the send queue size + with atm_may_send() and incrementing sk_wmem_alloc, + and the real queue size can be a little higher than sk_sndbuf + + - the vcc->sendmsg() can be called concurrently. I'm not sure + if it's allowed. Some drivers (eni, nicstar, ...) seem + to assume it will never happen. + + Now pppoatm_send() takes ATM socket lock, the same that is used + in vcc_sendmsg() and other ATM socket functions. The pppoatm_send() + is called with BH disabled, so bh_lock_sock() is used instead + of lock_sock(). + + Signed-off-by: Krzysztof Mazur + Cc: Chas Williams - CONTRACTOR + Signed-off-by: David Woodhouse + +commit e41faed9cde1acce657f75a0b19a1787e9850d3f +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:59 2012 +0100 + + pppoatm: fix module_put() race + + The pppoatm used module_put() during unassignment from vcc with + hope that we have BKL. This assumption is no longer true. + + Now owner field in atmvcc is used to move this module_put() + to vcc_destroy_socket(). + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 3b1a914595f3f9beb9e38ff3ddc7bdafa092ba22 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:58 2012 +0100 + + pppoatm: allow assign only on a connected socket + + The pppoatm does not check if used vcc is in connected state, + causing an Oops in pppoatm_send() when vcc->send() is called + on not fully connected socket. + + Now pppoatm can be assigned only on connected sockets; otherwise + -EINVAL error is returned. + + Signed-off-by: Krzysztof Mazur + Cc: Chas Williams - CONTRACTOR + Signed-off-by: David Woodhouse + +commit ec809bd817dfa1905283468e4c813684ed4efe78 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:57 2012 +0100 + + atm: add owner of push() callback to atmvcc + + The atm is using atmvcc->push(vcc, NULL) callback to notify protocol + that vcc will be closed and protocol must detach from it. This callback + is usually used by protocol to decrement module usage count by module_put(), + but it leaves small window then module is still used after module_put(). + + Now the owner of push() callback is kept in atmvcc and + module_put(atmvcc->owner) is called after the protocol is detached from vcc. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + Acked-by: Chas Williams + +commit ae088d663beebb3cad0e7abaac67ee61a7c578d5 +Author: David Woodhouse +Date: Sun Nov 25 12:06:52 2012 +0000 + + atm: br2684: Fix excessive queue bloat + + There's really no excuse for an additional wmem_default of buffering + between the netdev queue and the ATM device. Two packets (one in-flight, + and one ready to send) ought to be fine. It's not as if it should take + long to get another from the netdev queue when we need it. + + If necessary we can make the queue space configurable later, but I don't + think it's likely to be necessary. + + cf. commit 9d02daf754238adac48fa075ee79e7edd3d79ed3 (pppoatm: Fix + excessive queue bloat) which did something very similar for PPPoATM. + + Note that there is a tremendously unlikely race condition which may + result in qspace temporarily going negative. If a CPU running the + br2684_pop() function goes off into the weeds for a long period of time + after incrementing qspace to 1, but before calling netdev_wake_queue()... + and another CPU ends up calling br2684_start_xmit() and *stopping* the + queue again before the first CPU comes back, the netdev queue could + end up being woken when qspace has already reached zero. + + An alternative approach to coping with this race would be to check in + br2684_start_xmit() for qspace==0 and return NETDEV_TX_BUSY, but just + using '> 0' and '< 1' for comparison instead of '== 0' and '!= 0' is + simpler. It just warranted a mention of *why* we do it that way... + + Move the call to atmvcc->send() to happen *after* the accounting and + potentially stopping the netdev queue, in br2684_xmit_vcc(). This matters + if the ->send() call suffers an immediate failure, because it'll call + br2684_pop() with the offending skb before returning. We want that to + happen *after* we've done the initial accounting for the packet in + question. Also make it return an appropriate success/failure indication + while we're at it. + + Tested by running 'ping -l 1000 bottomless.aaisp.net.uk' from within my + network, with only a single PPPoE-over-BR2684 link running. And after + setting txqueuelen on the nas0 interface to something low (5, in fact). + Before the patch, we'd see about 15 packets being queued and a resulting + latency of ~56ms being reached. After the patch, we see only about 8, + which is fairly much what we expect. And a max latency of ~36ms. On this + OpenWRT box, wmem_default is 163840. + + Signed-off-by: David Woodhouse + Reviewed-by: Krzysztof Mazur + Signed-off-by: David S. Miller + +diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c +index 9851093..6258961 100644 +--- a/drivers/atm/solos-pci.c ++++ b/drivers/atm/solos-pci.c +@@ -92,6 +92,7 @@ struct pkt_hdr { + }; + + struct solos_skb_cb { ++ struct completion c; + struct atm_vcc *vcc; + uint32_t dma_addr; + }; +@@ -710,7 +711,8 @@ void solos_bh(unsigned long card_arg) + dev_warn(&card->dev->dev, "Received packet for unknown VPI.VCI %d.%d on port %d\n", + le16_to_cpu(header->vpi), le16_to_cpu(header->vci), + port); +- continue; ++ dev_kfree_skb_any(skb); ++ break; + } + atm_charge(vcc, skb->truesize); + vcc->push(vcc, skb); +@@ -881,11 +883,18 @@ static void pclose(struct atm_vcc *vcc) + header->vci = cpu_to_le16(vcc->vci); + header->type = cpu_to_le16(PKT_PCLOSE); + ++ init_completion(&SKB_CB(skb)->c); ++ + fpga_queue(card, SOLOS_CHAN(vcc->dev), skb, NULL); + + clear_bit(ATM_VF_ADDR, &vcc->flags); + clear_bit(ATM_VF_READY, &vcc->flags); + ++ if (!wait_for_completion_timeout(&SKB_CB(skb)->c, ++ msecs_to_jiffies(5000))) ++ dev_warn(&card->dev->dev, "Timeout waiting for VCC close on port %d\n", ++ SOLOS_CHAN(vcc->dev)); ++ + /* Hold up vcc_destroy_socket() (our caller) until solos_bh() in the + tasklet has finished processing any incoming packets (and, more to + the point, using the vcc pointer). */ +@@ -1011,9 +1020,12 @@ static uint32_t fpga_tx(struct solos_card *card) + if (vcc) { + atomic_inc(&vcc->stats->tx); + solos_pop(vcc, oldskb); +- } else ++ } else { ++ struct pkt_hdr *header = (void *)oldskb->data; ++ if (le16_to_cpu(header->type) == PKT_PCLOSE) ++ complete(&SKB_CB(oldskb)->c); + dev_kfree_skb_irq(oldskb); +- ++ } + } + } + /* For non-DMA TX, write the 'TX start' bit for all four ports simultaneously */ +@@ -1345,6 +1357,8 @@ static struct pci_driver fpga_driver = { + + static int __init solos_pci_init(void) + { ++ BUILD_BUG_ON(sizeof(struct solos_skb_cb) > sizeof(((struct sk_buff *)0)->cb)); ++ + printk(KERN_INFO "Solos PCI Driver Version %s\n", VERSION); + return pci_register_driver(&fpga_driver); + } +diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h +index 22ef21c..c1da539 100644 +--- a/include/linux/atmdev.h ++++ b/include/linux/atmdev.h +@@ -99,6 +99,7 @@ struct atm_vcc { + struct atm_dev *dev; /* device back pointer */ + struct atm_qos qos; /* QOS */ + struct atm_sap sap; /* SAP */ ++ void (*release_cb)(struct atm_vcc *vcc); /* release_sock callback */ + void (*push)(struct atm_vcc *vcc,struct sk_buff *skb); + void (*pop)(struct atm_vcc *vcc,struct sk_buff *skb); /* optional */ + int (*push_oam)(struct atm_vcc *vcc,void *cell); +@@ -106,6 +107,7 @@ struct atm_vcc { + void *dev_data; /* per-device data */ + void *proto_data; /* per-protocol data */ + struct k_atm_aal_stats *stats; /* pointer to AAL stats group */ ++ struct module *owner; /* owner of ->push function */ + /* SVC part --- may move later ------------------------------------- */ + short itf; /* interface number */ + struct sockaddr_atmsvc local; +diff --git a/net/atm/br2684.c b/net/atm/br2684.c +index 4819d315..a4ee4ad 100644 +--- a/net/atm/br2684.c ++++ b/net/atm/br2684.c +@@ -68,12 +68,14 @@ 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); ++ 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 copies_needed, copies_failed; ++ atomic_t qspace; + }; + + struct br2684_dev { +@@ -181,18 +183,15 @@ 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, +@@ -251,21 +250,30 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, + skb_debug(skb); + + ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; ++ if (test_bit(ATM_VF_RELEASED, &atmvcc->flags) || ++ test_bit(ATM_VF_CLOSE, &atmvcc->flags) || ++ !test_bit(ATM_VF_READY, &atmvcc->flags)) { ++ dev_kfree_skb(skb); ++ return 0; ++ } + pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); + atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); + 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 inline struct br2684_vcc *pick_outgoing_vcc(const struct sk_buff *skb, +@@ -378,8 +386,8 @@ static void br2684_close_vcc(struct br2684_vcc *brvcc) + write_unlock_irq(&devs_lock); + brvcc->atmvcc->user_back = NULL; /* what about vcc->recvq ??? */ + 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 +512,13 @@ 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 +561,11 @@ 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_owner = atmvcc->owner; + barrier(); + atmvcc->push = br2684_push; + atmvcc->pop = br2684_pop; ++ atmvcc->owner = THIS_MODULE; + + /* initialize netdev carrier state */ + if (atmvcc->dev->signal == ATM_PHY_SIG_LOST) +@@ -687,10 +704,13 @@ 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 0c0ad93..806fc0a 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 226dca9..8c93267 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/target/linux/generic/patches-3.6/131-atm-fixes.patch b/target/linux/generic/patches-3.6/131-atm-fixes.patch new file mode 100644 index 0000000000..926956bff3 --- /dev/null +++ b/target/linux/generic/patches-3.6/131-atm-fixes.patch @@ -0,0 +1,709 @@ +commit 86768086727a60335b08c34b2966c784029a24cf +Author: David Woodhouse +Date: Wed Nov 28 10:15:05 2012 +0000 + + pppoatm: optimise PPP channel wakeups after sock_owned_by_user() + + We don't need to schedule the wakeup tasklet on *every* unlock; only if we + actually blocked the channel in the first place. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit a009aa5fde926350f7a7e558a3ac0180e10eb24a +Author: Krzysztof Mazur +Date: Wed Nov 28 09:08:04 2012 +0100 + + br2684: allow assign only on a connected socket + + The br2684 does not check if used vcc is in connected state, + causing potential Oops in pppoatm_send() when vcc->send() is called + on not fully connected socket. + + Now br2684 can be assigned only on connected sockets; otherwise + -EINVAL error is returned. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit ae2169bcb6375fb214cadd0ea50ac54bcf39b0d6 +Author: Nathan Williams +Date: Tue Nov 27 17:34:09 2012 +1100 + + solos-pci: Fix leak of skb received for unknown vcc + + ... and ensure that the next skb is set up for RX in the DMA case. + + Signed-off-by: Nathan Williams + Signed-off-by: David Woodhouse + +commit 6227612becaebe2f9f4ad7d0cdf27e298bb56687 +Author: David Woodhouse +Date: Wed Nov 28 00:46:45 2012 +0000 + + br2684: fix module_put() race + + The br2684 code used module_put() during unassignment from vcc with + hope that we have BKL. This assumption is no longer true. + + Now owner field in atmvcc is used to move this module_put() + to vcc_destroy_socket(). + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 44abbb464896dc2270716d25e12fe47e57eeb1d3 +Author: David Woodhouse +Date: Wed Nov 28 00:05:52 2012 +0000 + + pppoatm: fix missing wakeup in pppoatm_send() + + Now that we can return zero from pppoatm_send() for reasons *other* than + the queue being full, that means we can't depend on a subsequent call to + pppoatm_pop() waking the queue, and we might leave it stalled + indefinitely. + + Use the ->release_cb() callback to wake the queue after the sock is + unlocked. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit c93eeac2ebee497dbc9b6ad39c235ff3061be141 +Author: David Woodhouse +Date: Wed Nov 28 00:03:11 2012 +0000 + + atm: Add release_cb() callback to vcc + + The immediate use case for this is that it will allow us to ensure that a + pppoatm queue is woken after it has to drop a packet due to the sock being + locked. + + Note that 'release_cb' is called when the socket is *unlocked*. This is + not to be confused with vcc_release() — which probably ought to be called + vcc_close(). + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 9b3e2e224cc4326d8897243b24d778abf9098a8d +Author: David Woodhouse +Date: Tue Nov 27 23:28:36 2012 +0000 + + br2684: don't send frames on not-ready vcc + + Avoid submitting packets to a vcc which is being closed. Things go badly + wrong when the ->pop method gets later called after everything's been + torn down. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 26c7c53318cf56a690ae553104f4a60181734fb5 +Author: David Woodhouse +Date: Tue Nov 27 23:49:24 2012 +0000 + + solos-pci: Wait for pending TX to complete when releasing vcc + + We should no longer be calling the old pop routine for the vcc, after + vcc_release() has completed. Make sure we wait for any pending TX skbs + to complete, by waiting for our own PKT_PCLOSE control skb to be sent. + + Signed-off-by: David Woodhouse + +commit 1a3304e89b9ba168340a37926014be11c3ad110e +Author: Krzysztof Mazur +Date: Tue Nov 6 23:17:02 2012 +0100 + + pppoatm: do not inline pppoatm_may_send() + + The pppoatm_may_send() is quite heavy and it's called three times + in pppoatm_send() and inlining costs more than 200 bytes of code + (more than 10% of total pppoatm driver code size). + + add/remove: 1/0 grow/shrink: 0/1 up/down: 132/-367 (-235) + function old new delta + pppoatm_may_send - 132 +132 + pppoatm_send 900 533 -367 + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 294398bcd0fe26335059a185b59cfb5de1fc4c71 +Author: Krzysztof Mazur +Date: Sat Nov 10 23:33:19 2012 +0100 + + pppoatm: drop frames to not-ready vcc + + Patches "atm: detach protocol before closing vcc" + and "pppoatm: allow assign only on a connected socket" fixed + common cases where the pppoatm_send() crashes while sending + frame to not-ready vcc. However there are still some other cases + where we can send frames to vcc, which is flagged as ATM_VF_CLOSE + (for instance after vcc_release_async()) or it's opened but not + ready yet. + + Now pppoatm_send(), like vcc_sendmsg(), checks for vcc flags that + indicate that vcc is not ready. If the vcc is not ready we just + drop frame. Queueing frames is much more complicated because we + don't have callbacks that inform us about vcc flags changes. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 3ac108006fd7f20cb8fc8ea2287f1497bcda00a1 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:17:00 2012 +0100 + + pppoatm: take ATM socket lock in pppoatm_send() + + The pppoatm_send() does not take any lock that will prevent concurrent + vcc_sendmsg(). This causes two problems: + + - there is no locking between checking the send queue size + with atm_may_send() and incrementing sk_wmem_alloc, + and the real queue size can be a little higher than sk_sndbuf + + - the vcc->sendmsg() can be called concurrently. I'm not sure + if it's allowed. Some drivers (eni, nicstar, ...) seem + to assume it will never happen. + + Now pppoatm_send() takes ATM socket lock, the same that is used + in vcc_sendmsg() and other ATM socket functions. The pppoatm_send() + is called with BH disabled, so bh_lock_sock() is used instead + of lock_sock(). + + Signed-off-by: Krzysztof Mazur + Cc: Chas Williams - CONTRACTOR + Signed-off-by: David Woodhouse + +commit e41faed9cde1acce657f75a0b19a1787e9850d3f +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:59 2012 +0100 + + pppoatm: fix module_put() race + + The pppoatm used module_put() during unassignment from vcc with + hope that we have BKL. This assumption is no longer true. + + Now owner field in atmvcc is used to move this module_put() + to vcc_destroy_socket(). + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 3b1a914595f3f9beb9e38ff3ddc7bdafa092ba22 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:58 2012 +0100 + + pppoatm: allow assign only on a connected socket + + The pppoatm does not check if used vcc is in connected state, + causing an Oops in pppoatm_send() when vcc->send() is called + on not fully connected socket. + + Now pppoatm can be assigned only on connected sockets; otherwise + -EINVAL error is returned. + + Signed-off-by: Krzysztof Mazur + Cc: Chas Williams - CONTRACTOR + Signed-off-by: David Woodhouse + +commit ec809bd817dfa1905283468e4c813684ed4efe78 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:57 2012 +0100 + + atm: add owner of push() callback to atmvcc + + The atm is using atmvcc->push(vcc, NULL) callback to notify protocol + that vcc will be closed and protocol must detach from it. This callback + is usually used by protocol to decrement module usage count by module_put(), + but it leaves small window then module is still used after module_put(). + + Now the owner of push() callback is kept in atmvcc and + module_put(atmvcc->owner) is called after the protocol is detached from vcc. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + Acked-by: Chas Williams + +commit ae088d663beebb3cad0e7abaac67ee61a7c578d5 +Author: David Woodhouse +Date: Sun Nov 25 12:06:52 2012 +0000 + + atm: br2684: Fix excessive queue bloat + + There's really no excuse for an additional wmem_default of buffering + between the netdev queue and the ATM device. Two packets (one in-flight, + and one ready to send) ought to be fine. It's not as if it should take + long to get another from the netdev queue when we need it. + + If necessary we can make the queue space configurable later, but I don't + think it's likely to be necessary. + + cf. commit 9d02daf754238adac48fa075ee79e7edd3d79ed3 (pppoatm: Fix + excessive queue bloat) which did something very similar for PPPoATM. + + Note that there is a tremendously unlikely race condition which may + result in qspace temporarily going negative. If a CPU running the + br2684_pop() function goes off into the weeds for a long period of time + after incrementing qspace to 1, but before calling netdev_wake_queue()... + and another CPU ends up calling br2684_start_xmit() and *stopping* the + queue again before the first CPU comes back, the netdev queue could + end up being woken when qspace has already reached zero. + + An alternative approach to coping with this race would be to check in + br2684_start_xmit() for qspace==0 and return NETDEV_TX_BUSY, but just + using '> 0' and '< 1' for comparison instead of '== 0' and '!= 0' is + simpler. It just warranted a mention of *why* we do it that way... + + Move the call to atmvcc->send() to happen *after* the accounting and + potentially stopping the netdev queue, in br2684_xmit_vcc(). This matters + if the ->send() call suffers an immediate failure, because it'll call + br2684_pop() with the offending skb before returning. We want that to + happen *after* we've done the initial accounting for the packet in + question. Also make it return an appropriate success/failure indication + while we're at it. + + Tested by running 'ping -l 1000 bottomless.aaisp.net.uk' from within my + network, with only a single PPPoE-over-BR2684 link running. And after + setting txqueuelen on the nas0 interface to something low (5, in fact). + Before the patch, we'd see about 15 packets being queued and a resulting + latency of ~56ms being reached. After the patch, we see only about 8, + which is fairly much what we expect. And a max latency of ~36ms. On this + OpenWRT box, wmem_default is 163840. + + Signed-off-by: David Woodhouse + Reviewed-by: Krzysztof Mazur + Signed-off-by: David S. Miller + +diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c +index 9851093..6258961 100644 +--- a/drivers/atm/solos-pci.c ++++ b/drivers/atm/solos-pci.c +@@ -92,6 +92,7 @@ struct pkt_hdr { + }; + + struct solos_skb_cb { ++ struct completion c; + struct atm_vcc *vcc; + uint32_t dma_addr; + }; +@@ -710,7 +711,8 @@ void solos_bh(unsigned long card_arg) + dev_warn(&card->dev->dev, "Received packet for unknown VPI.VCI %d.%d on port %d\n", + le16_to_cpu(header->vpi), le16_to_cpu(header->vci), + port); +- continue; ++ dev_kfree_skb_any(skb); ++ break; + } + atm_charge(vcc, skb->truesize); + vcc->push(vcc, skb); +@@ -881,11 +883,18 @@ static void pclose(struct atm_vcc *vcc) + header->vci = cpu_to_le16(vcc->vci); + header->type = cpu_to_le16(PKT_PCLOSE); + ++ init_completion(&SKB_CB(skb)->c); ++ + fpga_queue(card, SOLOS_CHAN(vcc->dev), skb, NULL); + + clear_bit(ATM_VF_ADDR, &vcc->flags); + clear_bit(ATM_VF_READY, &vcc->flags); + ++ if (!wait_for_completion_timeout(&SKB_CB(skb)->c, ++ msecs_to_jiffies(5000))) ++ dev_warn(&card->dev->dev, "Timeout waiting for VCC close on port %d\n", ++ SOLOS_CHAN(vcc->dev)); ++ + /* Hold up vcc_destroy_socket() (our caller) until solos_bh() in the + tasklet has finished processing any incoming packets (and, more to + the point, using the vcc pointer). */ +@@ -1011,9 +1020,12 @@ static uint32_t fpga_tx(struct solos_card *card) + if (vcc) { + atomic_inc(&vcc->stats->tx); + solos_pop(vcc, oldskb); +- } else ++ } else { ++ struct pkt_hdr *header = (void *)oldskb->data; ++ if (le16_to_cpu(header->type) == PKT_PCLOSE) ++ complete(&SKB_CB(oldskb)->c); + dev_kfree_skb_irq(oldskb); +- ++ } + } + } + /* For non-DMA TX, write the 'TX start' bit for all four ports simultaneously */ +@@ -1345,6 +1357,8 @@ static struct pci_driver fpga_driver = { + + static int __init solos_pci_init(void) + { ++ BUILD_BUG_ON(sizeof(struct solos_skb_cb) > sizeof(((struct sk_buff *)0)->cb)); ++ + printk(KERN_INFO "Solos PCI Driver Version %s\n", VERSION); + return pci_register_driver(&fpga_driver); + } +diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h +index 22ef21c..c1da539 100644 +--- a/include/linux/atmdev.h ++++ b/include/linux/atmdev.h +@@ -99,6 +99,7 @@ struct atm_vcc { + struct atm_dev *dev; /* device back pointer */ + struct atm_qos qos; /* QOS */ + struct atm_sap sap; /* SAP */ ++ void (*release_cb)(struct atm_vcc *vcc); /* release_sock callback */ + void (*push)(struct atm_vcc *vcc,struct sk_buff *skb); + void (*pop)(struct atm_vcc *vcc,struct sk_buff *skb); /* optional */ + int (*push_oam)(struct atm_vcc *vcc,void *cell); +@@ -106,6 +107,7 @@ struct atm_vcc { + void *dev_data; /* per-device data */ + void *proto_data; /* per-protocol data */ + struct k_atm_aal_stats *stats; /* pointer to AAL stats group */ ++ struct module *owner; /* owner of ->push function */ + /* SVC part --- may move later ------------------------------------- */ + short itf; /* interface number */ + struct sockaddr_atmsvc local; +diff --git a/net/atm/br2684.c b/net/atm/br2684.c +index 4819d315..a4ee4ad 100644 +--- a/net/atm/br2684.c ++++ b/net/atm/br2684.c +@@ -68,12 +68,14 @@ 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); ++ 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 +183,15 @@ 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, +@@ -251,21 +250,30 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, + skb_debug(skb); + + ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; ++ if (test_bit(ATM_VF_RELEASED, &atmvcc->flags) || ++ test_bit(ATM_VF_CLOSE, &atmvcc->flags) || ++ !test_bit(ATM_VF_READY, &atmvcc->flags)) { ++ dev_kfree_skb(skb); ++ return 0; ++ } + pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); + atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); + 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 inline struct br2684_vcc *pick_outgoing_vcc(const struct sk_buff *skb, +@@ -378,8 +386,8 @@ static void br2684_close_vcc(struct br2684_vcc *brvcc) + write_unlock_irq(&devs_lock); + brvcc->atmvcc->user_back = NULL; /* what about vcc->recvq ??? */ + 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 +512,13 @@ 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 +561,11 @@ 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_owner = atmvcc->owner; + barrier(); + atmvcc->push = br2684_push; + atmvcc->pop = br2684_pop; ++ atmvcc->owner = THIS_MODULE; + + /* initialize netdev carrier state */ + if (atmvcc->dev->signal == ATM_PHY_SIG_LOST) +@@ -687,10 +704,13 @@ 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 0c0ad93..806fc0a 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 226dca9..8c93267 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/target/linux/generic/patches-3.7/131-atm-fixes.patch b/target/linux/generic/patches-3.7/131-atm-fixes.patch new file mode 100644 index 0000000000..926956bff3 --- /dev/null +++ b/target/linux/generic/patches-3.7/131-atm-fixes.patch @@ -0,0 +1,709 @@ +commit 86768086727a60335b08c34b2966c784029a24cf +Author: David Woodhouse +Date: Wed Nov 28 10:15:05 2012 +0000 + + pppoatm: optimise PPP channel wakeups after sock_owned_by_user() + + We don't need to schedule the wakeup tasklet on *every* unlock; only if we + actually blocked the channel in the first place. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit a009aa5fde926350f7a7e558a3ac0180e10eb24a +Author: Krzysztof Mazur +Date: Wed Nov 28 09:08:04 2012 +0100 + + br2684: allow assign only on a connected socket + + The br2684 does not check if used vcc is in connected state, + causing potential Oops in pppoatm_send() when vcc->send() is called + on not fully connected socket. + + Now br2684 can be assigned only on connected sockets; otherwise + -EINVAL error is returned. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit ae2169bcb6375fb214cadd0ea50ac54bcf39b0d6 +Author: Nathan Williams +Date: Tue Nov 27 17:34:09 2012 +1100 + + solos-pci: Fix leak of skb received for unknown vcc + + ... and ensure that the next skb is set up for RX in the DMA case. + + Signed-off-by: Nathan Williams + Signed-off-by: David Woodhouse + +commit 6227612becaebe2f9f4ad7d0cdf27e298bb56687 +Author: David Woodhouse +Date: Wed Nov 28 00:46:45 2012 +0000 + + br2684: fix module_put() race + + The br2684 code used module_put() during unassignment from vcc with + hope that we have BKL. This assumption is no longer true. + + Now owner field in atmvcc is used to move this module_put() + to vcc_destroy_socket(). + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 44abbb464896dc2270716d25e12fe47e57eeb1d3 +Author: David Woodhouse +Date: Wed Nov 28 00:05:52 2012 +0000 + + pppoatm: fix missing wakeup in pppoatm_send() + + Now that we can return zero from pppoatm_send() for reasons *other* than + the queue being full, that means we can't depend on a subsequent call to + pppoatm_pop() waking the queue, and we might leave it stalled + indefinitely. + + Use the ->release_cb() callback to wake the queue after the sock is + unlocked. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit c93eeac2ebee497dbc9b6ad39c235ff3061be141 +Author: David Woodhouse +Date: Wed Nov 28 00:03:11 2012 +0000 + + atm: Add release_cb() callback to vcc + + The immediate use case for this is that it will allow us to ensure that a + pppoatm queue is woken after it has to drop a packet due to the sock being + locked. + + Note that 'release_cb' is called when the socket is *unlocked*. This is + not to be confused with vcc_release() — which probably ought to be called + vcc_close(). + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 9b3e2e224cc4326d8897243b24d778abf9098a8d +Author: David Woodhouse +Date: Tue Nov 27 23:28:36 2012 +0000 + + br2684: don't send frames on not-ready vcc + + Avoid submitting packets to a vcc which is being closed. Things go badly + wrong when the ->pop method gets later called after everything's been + torn down. + + Signed-off-by: David Woodhouse + Acked-by: Krzysztof Mazur + +commit 26c7c53318cf56a690ae553104f4a60181734fb5 +Author: David Woodhouse +Date: Tue Nov 27 23:49:24 2012 +0000 + + solos-pci: Wait for pending TX to complete when releasing vcc + + We should no longer be calling the old pop routine for the vcc, after + vcc_release() has completed. Make sure we wait for any pending TX skbs + to complete, by waiting for our own PKT_PCLOSE control skb to be sent. + + Signed-off-by: David Woodhouse + +commit 1a3304e89b9ba168340a37926014be11c3ad110e +Author: Krzysztof Mazur +Date: Tue Nov 6 23:17:02 2012 +0100 + + pppoatm: do not inline pppoatm_may_send() + + The pppoatm_may_send() is quite heavy and it's called three times + in pppoatm_send() and inlining costs more than 200 bytes of code + (more than 10% of total pppoatm driver code size). + + add/remove: 1/0 grow/shrink: 0/1 up/down: 132/-367 (-235) + function old new delta + pppoatm_may_send - 132 +132 + pppoatm_send 900 533 -367 + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 294398bcd0fe26335059a185b59cfb5de1fc4c71 +Author: Krzysztof Mazur +Date: Sat Nov 10 23:33:19 2012 +0100 + + pppoatm: drop frames to not-ready vcc + + Patches "atm: detach protocol before closing vcc" + and "pppoatm: allow assign only on a connected socket" fixed + common cases where the pppoatm_send() crashes while sending + frame to not-ready vcc. However there are still some other cases + where we can send frames to vcc, which is flagged as ATM_VF_CLOSE + (for instance after vcc_release_async()) or it's opened but not + ready yet. + + Now pppoatm_send(), like vcc_sendmsg(), checks for vcc flags that + indicate that vcc is not ready. If the vcc is not ready we just + drop frame. Queueing frames is much more complicated because we + don't have callbacks that inform us about vcc flags changes. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 3ac108006fd7f20cb8fc8ea2287f1497bcda00a1 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:17:00 2012 +0100 + + pppoatm: take ATM socket lock in pppoatm_send() + + The pppoatm_send() does not take any lock that will prevent concurrent + vcc_sendmsg(). This causes two problems: + + - there is no locking between checking the send queue size + with atm_may_send() and incrementing sk_wmem_alloc, + and the real queue size can be a little higher than sk_sndbuf + + - the vcc->sendmsg() can be called concurrently. I'm not sure + if it's allowed. Some drivers (eni, nicstar, ...) seem + to assume it will never happen. + + Now pppoatm_send() takes ATM socket lock, the same that is used + in vcc_sendmsg() and other ATM socket functions. The pppoatm_send() + is called with BH disabled, so bh_lock_sock() is used instead + of lock_sock(). + + Signed-off-by: Krzysztof Mazur + Cc: Chas Williams - CONTRACTOR + Signed-off-by: David Woodhouse + +commit e41faed9cde1acce657f75a0b19a1787e9850d3f +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:59 2012 +0100 + + pppoatm: fix module_put() race + + The pppoatm used module_put() during unassignment from vcc with + hope that we have BKL. This assumption is no longer true. + + Now owner field in atmvcc is used to move this module_put() + to vcc_destroy_socket(). + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + +commit 3b1a914595f3f9beb9e38ff3ddc7bdafa092ba22 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:58 2012 +0100 + + pppoatm: allow assign only on a connected socket + + The pppoatm does not check if used vcc is in connected state, + causing an Oops in pppoatm_send() when vcc->send() is called + on not fully connected socket. + + Now pppoatm can be assigned only on connected sockets; otherwise + -EINVAL error is returned. + + Signed-off-by: Krzysztof Mazur + Cc: Chas Williams - CONTRACTOR + Signed-off-by: David Woodhouse + +commit ec809bd817dfa1905283468e4c813684ed4efe78 +Author: Krzysztof Mazur +Date: Tue Nov 6 23:16:57 2012 +0100 + + atm: add owner of push() callback to atmvcc + + The atm is using atmvcc->push(vcc, NULL) callback to notify protocol + that vcc will be closed and protocol must detach from it. This callback + is usually used by protocol to decrement module usage count by module_put(), + but it leaves small window then module is still used after module_put(). + + Now the owner of push() callback is kept in atmvcc and + module_put(atmvcc->owner) is called after the protocol is detached from vcc. + + Signed-off-by: Krzysztof Mazur + Signed-off-by: David Woodhouse + Acked-by: Chas Williams + +commit ae088d663beebb3cad0e7abaac67ee61a7c578d5 +Author: David Woodhouse +Date: Sun Nov 25 12:06:52 2012 +0000 + + atm: br2684: Fix excessive queue bloat + + There's really no excuse for an additional wmem_default of buffering + between the netdev queue and the ATM device. Two packets (one in-flight, + and one ready to send) ought to be fine. It's not as if it should take + long to get another from the netdev queue when we need it. + + If necessary we can make the queue space configurable later, but I don't + think it's likely to be necessary. + + cf. commit 9d02daf754238adac48fa075ee79e7edd3d79ed3 (pppoatm: Fix + excessive queue bloat) which did something very similar for PPPoATM. + + Note that there is a tremendously unlikely race condition which may + result in qspace temporarily going negative. If a CPU running the + br2684_pop() function goes off into the weeds for a long period of time + after incrementing qspace to 1, but before calling netdev_wake_queue()... + and another CPU ends up calling br2684_start_xmit() and *stopping* the + queue again before the first CPU comes back, the netdev queue could + end up being woken when qspace has already reached zero. + + An alternative approach to coping with this race would be to check in + br2684_start_xmit() for qspace==0 and return NETDEV_TX_BUSY, but just + using '> 0' and '< 1' for comparison instead of '== 0' and '!= 0' is + simpler. It just warranted a mention of *why* we do it that way... + + Move the call to atmvcc->send() to happen *after* the accounting and + potentially stopping the netdev queue, in br2684_xmit_vcc(). This matters + if the ->send() call suffers an immediate failure, because it'll call + br2684_pop() with the offending skb before returning. We want that to + happen *after* we've done the initial accounting for the packet in + question. Also make it return an appropriate success/failure indication + while we're at it. + + Tested by running 'ping -l 1000 bottomless.aaisp.net.uk' from within my + network, with only a single PPPoE-over-BR2684 link running. And after + setting txqueuelen on the nas0 interface to something low (5, in fact). + Before the patch, we'd see about 15 packets being queued and a resulting + latency of ~56ms being reached. After the patch, we see only about 8, + which is fairly much what we expect. And a max latency of ~36ms. On this + OpenWRT box, wmem_default is 163840. + + Signed-off-by: David Woodhouse + Reviewed-by: Krzysztof Mazur + Signed-off-by: David S. Miller + +diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c +index 9851093..6258961 100644 +--- a/drivers/atm/solos-pci.c ++++ b/drivers/atm/solos-pci.c +@@ -92,6 +92,7 @@ struct pkt_hdr { + }; + + struct solos_skb_cb { ++ struct completion c; + struct atm_vcc *vcc; + uint32_t dma_addr; + }; +@@ -710,7 +711,8 @@ void solos_bh(unsigned long card_arg) + dev_warn(&card->dev->dev, "Received packet for unknown VPI.VCI %d.%d on port %d\n", + le16_to_cpu(header->vpi), le16_to_cpu(header->vci), + port); +- continue; ++ dev_kfree_skb_any(skb); ++ break; + } + atm_charge(vcc, skb->truesize); + vcc->push(vcc, skb); +@@ -881,11 +883,18 @@ static void pclose(struct atm_vcc *vcc) + header->vci = cpu_to_le16(vcc->vci); + header->type = cpu_to_le16(PKT_PCLOSE); + ++ init_completion(&SKB_CB(skb)->c); ++ + fpga_queue(card, SOLOS_CHAN(vcc->dev), skb, NULL); + + clear_bit(ATM_VF_ADDR, &vcc->flags); + clear_bit(ATM_VF_READY, &vcc->flags); + ++ if (!wait_for_completion_timeout(&SKB_CB(skb)->c, ++ msecs_to_jiffies(5000))) ++ dev_warn(&card->dev->dev, "Timeout waiting for VCC close on port %d\n", ++ SOLOS_CHAN(vcc->dev)); ++ + /* Hold up vcc_destroy_socket() (our caller) until solos_bh() in the + tasklet has finished processing any incoming packets (and, more to + the point, using the vcc pointer). */ +@@ -1011,9 +1020,12 @@ static uint32_t fpga_tx(struct solos_card *card) + if (vcc) { + atomic_inc(&vcc->stats->tx); + solos_pop(vcc, oldskb); +- } else ++ } else { ++ struct pkt_hdr *header = (void *)oldskb->data; ++ if (le16_to_cpu(header->type) == PKT_PCLOSE) ++ complete(&SKB_CB(oldskb)->c); + dev_kfree_skb_irq(oldskb); +- ++ } + } + } + /* For non-DMA TX, write the 'TX start' bit for all four ports simultaneously */ +@@ -1345,6 +1357,8 @@ static struct pci_driver fpga_driver = { + + static int __init solos_pci_init(void) + { ++ BUILD_BUG_ON(sizeof(struct solos_skb_cb) > sizeof(((struct sk_buff *)0)->cb)); ++ + printk(KERN_INFO "Solos PCI Driver Version %s\n", VERSION); + return pci_register_driver(&fpga_driver); + } +diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h +index 22ef21c..c1da539 100644 +--- a/include/linux/atmdev.h ++++ b/include/linux/atmdev.h +@@ -99,6 +99,7 @@ struct atm_vcc { + struct atm_dev *dev; /* device back pointer */ + struct atm_qos qos; /* QOS */ + struct atm_sap sap; /* SAP */ ++ void (*release_cb)(struct atm_vcc *vcc); /* release_sock callback */ + void (*push)(struct atm_vcc *vcc,struct sk_buff *skb); + void (*pop)(struct atm_vcc *vcc,struct sk_buff *skb); /* optional */ + int (*push_oam)(struct atm_vcc *vcc,void *cell); +@@ -106,6 +107,7 @@ struct atm_vcc { + void *dev_data; /* per-device data */ + void *proto_data; /* per-protocol data */ + struct k_atm_aal_stats *stats; /* pointer to AAL stats group */ ++ struct module *owner; /* owner of ->push function */ + /* SVC part --- may move later ------------------------------------- */ + short itf; /* interface number */ + struct sockaddr_atmsvc local; +diff --git a/net/atm/br2684.c b/net/atm/br2684.c +index 4819d315..a4ee4ad 100644 +--- a/net/atm/br2684.c ++++ b/net/atm/br2684.c +@@ -68,12 +68,14 @@ 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); ++ 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 +183,15 @@ 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, +@@ -251,21 +250,30 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, + skb_debug(skb); + + ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; ++ if (test_bit(ATM_VF_RELEASED, &atmvcc->flags) || ++ test_bit(ATM_VF_CLOSE, &atmvcc->flags) || ++ !test_bit(ATM_VF_READY, &atmvcc->flags)) { ++ dev_kfree_skb(skb); ++ return 0; ++ } + pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); + atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); + 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 inline struct br2684_vcc *pick_outgoing_vcc(const struct sk_buff *skb, +@@ -378,8 +386,8 @@ static void br2684_close_vcc(struct br2684_vcc *brvcc) + write_unlock_irq(&devs_lock); + brvcc->atmvcc->user_back = NULL; /* what about vcc->recvq ??? */ + 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 +512,13 @@ 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 +561,11 @@ 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_owner = atmvcc->owner; + barrier(); + atmvcc->push = br2684_push; + atmvcc->pop = br2684_pop; ++ atmvcc->owner = THIS_MODULE; + + /* initialize netdev carrier state */ + if (atmvcc->dev->signal == ATM_PHY_SIG_LOST) +@@ -687,10 +704,13 @@ 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 0c0ad93..806fc0a 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 226dca9..8c93267 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: