diff options
Diffstat (limited to 'net/atm/pppoatm.c')
| -rw-r--r-- | net/atm/pppoatm.c | 165 |
1 files changed, 149 insertions, 16 deletions
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index df35d9a3b5f..c4e09846d1d 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -44,7 +44,7 @@ #include <linux/atmdev.h> #include <linux/capability.h> #include <linux/ppp_defs.h> -#include <linux/if_ppp.h> +#include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/atmppp.h> @@ -60,14 +60,29 @@ 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; + unsigned long blocked; int flags; /* SC_COMP_PROT - compress protocol */ struct ppp_channel chan; /* interface to generic ppp layer */ struct tasklet_struct wakeup_tasklet; }; /* + * We want to allow two packets in the queue. The one that's currently in + * flight, and *one* queued up ready for the ATM device to send immediately + * from its TX done IRQ. We want to be able to use atomic_inc_not_zero(), so + * inflight == -2 represents an empty queue, -1 one packet, and zero means + * there are two packets in the queue. + */ +#define NONE_INFLIGHT -2 + +#define BLOCKED 0 + +/* * Header used for LLC Encapsulated PPP (4 bytes) followed by the LCP protocol * ID (0xC021) used in autodetection */ @@ -94,6 +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, @@ -102,16 +135,30 @@ static void pppoatm_wakeup_sender(unsigned long arg) static void pppoatm_pop(struct atm_vcc *atmvcc, struct sk_buff *skb) { struct pppoatm_vcc *pvcc = atmvcc_to_pvcc(atmvcc); + pvcc->old_pop(atmvcc, skb); + atomic_dec(&pvcc->inflight); + /* - * We don't really always want to do this since it's - * really inefficient - it would be much better if we could - * test if we had actually throttled the generic layer. - * Unfortunately then there would be a nasty SMP race where - * we could clear that flag just as we refuse another packet. - * For now we do the safe thing. + * We always used to run the wakeup tasklet unconditionally here, for + * fear of race conditions where we clear the BLOCKED flag just as we + * refuse another packet in pppoatm_send(). This was quite inefficient. + * + * In fact it's OK. The PPP core will only ever call pppoatm_send() + * while holding the channel->downl lock. And ppp_output_wakeup() as + * called by the tasklet will *also* grab that lock. So even if another + * CPU is in pppoatm_send() right now, the tasklet isn't going to race + * with it. The wakeup *will* happen after the other CPU is safely out + * of pppoatm_send() again. + * + * So if the CPU in pppoatm_send() has already set the BLOCKED bit and + * it about to return, that's fine. We trigger a wakeup which will + * happen later. And if the CPU in pppoatm_send() *hasn't* set the + * BLOCKED bit yet, that's fine too because of the double check in + * pppoatm_may_send() which is commented there. */ - tasklet_schedule(&pvcc->wakeup_tasklet); + if (test_and_clear_bit(BLOCKED, &pvcc->blocked)) + tasklet_schedule(&pvcc->wakeup_tasklet); } /* @@ -124,12 +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 */ @@ -138,9 +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); @@ -184,6 +234,51 @@ error: ppp_input_error(&pvcc->chan, 0); } +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() + * to check we don't exceed sk->sk_sndbuf. If userspace sets a + * value of sk_sndbuf which is lower than the MTU, we're going to + * block for ever. But the code always did that before we introduced + * the packet count limit, so... + */ + if (atm_may_send(pvcc->atmvcc, size) && + atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT)) + return 1; + + /* + * We use test_and_set_bit() rather than set_bit() here because + * we need to ensure there's a memory barrier after it. The bit + * *must* be set before we do the atomic_inc() on pvcc->inflight. + * There's no smp_mb__after_set_bit(), so it's this or abuse + * smp_mb__after_atomic(). + */ + test_and_set_bit(BLOCKED, &pvcc->blocked); + + /* + * We may have raced with pppoatm_pop(). If it ran for the + * last packet in the queue, *just* before we set the BLOCKED + * bit, then it might never run again and the channel could + * remain permanently blocked. Cope with that race by checking + * *again*. If it did run in that window, we'll have space on + * the queue now and can return success. It's harmless to leave + * the BLOCKED flag set, since it's only used as a trigger to + * run the wakeup tasklet. Another wakeup will never hurt. + * If pppoatm_pop() is running but hasn't got as far as making + * space on the queue yet, then it hasn't checked the BLOCKED + * flag yet either, so we're safe in that case too. It'll issue + * an "immediate" wakeup... where "immediate" actually involves + * taking the PPP channel's ->downl lock, which is held by the + * code path that calls pppoatm_send(), and is thus going to + * wait for us to finish. + */ + if (atm_may_send(pvcc->atmvcc, size) && + atomic_inc_not_zero(&pvcc->inflight)) + return 1; + + return 0; +} /* * Called by the ppp_generic.c to send a packet - returns true if packet * was accepted. If we return false, then it's our job to call @@ -197,33 +292,59 @@ error: 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) { struct sk_buff *n; n = skb_realloc_headroom(skb, LLC_LEN); if (n != NULL && - !atm_may_send(pvcc->atmvcc, n->truesize)) { + !pppoatm_may_send(pvcc, n->truesize)) { kfree_skb(n); goto nospace; } - kfree_skb(skb); + consume_skb(skb); skb = n; - if (skb == NULL) + if (skb == NULL) { + bh_unlock_sock(sk_atm(vcc)); return DROP_PACKET; - } else if (!atm_may_send(pvcc->atmvcc, skb->truesize)) + } + } else if (!pppoatm_may_send(pvcc, skb->truesize)) goto nospace; memcpy(skb_push(skb, LLC_LEN), pppllc, LLC_LEN); break; case e_vc: - if (!atm_may_send(pvcc->atmvcc, skb->truesize)) + if (!pppoatm_may_send(pvcc, skb->truesize)) 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; @@ -233,9 +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 @@ -285,8 +409,13 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) if (pvcc == NULL) return -ENOMEM; pvcc->atmvcc = atmvcc; + + /* Maximum is zero, so that we can use atomic_inc_not_zero() */ + 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; @@ -302,7 +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 */ @@ -331,6 +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: |