X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=net%2Fpacket%2Faf_packet.c;h=146b2d7567c0625909e4f5fe60a091c83fdd3240;hb=382299a020add34cc75ac501bbcb655195c123b8;hp=82a6f34d39d012fb35d9a0d490503fcc2048e6e2;hpb=80f01ca1fce2d5045b98f01989017767339b8700;p=pandora-kernel.git

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 82a6f34d39d0..146b2d7567c0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -295,6 +295,7 @@ struct packet_sock {
 	unsigned int		tp_reserve;
 	unsigned int		tp_loss:1;
 	unsigned int		tp_tstamp;
+	struct net_device __rcu	*cached_dev;
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
 };
 
@@ -350,11 +351,15 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static void register_prot_hook(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
+
 	if (!po->running) {
-		if (po->fanout)
+		if (po->fanout) {
 			__fanout_link(sk, po);
-		else
+		} else {
 			dev_add_pack(&po->prot_hook);
+			rcu_assign_pointer(po->cached_dev, po->prot_hook.dev);
+		}
+
 		sock_hold(sk);
 		po->running = 1;
 	}
@@ -372,10 +377,13 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
 	struct packet_sock *po = pkt_sk(sk);
 
 	po->running = 0;
-	if (po->fanout)
+	if (po->fanout) {
 		__fanout_unlink(sk, po);
-	else
+	} else {
 		__dev_remove_pack(&po->prot_hook);
+		RCU_INIT_POINTER(po->cached_dev, NULL);
+	}
+
 	__sock_put(sk);
 
 	if (sync) {
@@ -497,9 +505,9 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
 
 	pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
 
-	spin_lock(&rb_queue->lock);
+	spin_lock_bh(&rb_queue->lock);
 	pkc->delete_blk_timer = 1;
-	spin_unlock(&rb_queue->lock);
+	spin_unlock_bh(&rb_queue->lock);
 
 	prb_del_retire_blk_timer(pkc);
 }
@@ -813,37 +821,27 @@ static void prb_open_block(struct tpacket_kbdq_core *pkc1,
 
 	smp_rmb();
 
-	if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd1))) {
-
-		/* We could have just memset this but we will lose the
-		 * flexibility of making the priv area sticky
-		 */
-		BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++;
-		BLOCK_NUM_PKTS(pbd1) = 0;
-		BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
-		getnstimeofday(&ts);
-		h1->ts_first_pkt.ts_sec = ts.tv_sec;
-		h1->ts_first_pkt.ts_nsec = ts.tv_nsec;
-		pkc1->pkblk_start = (char *)pbd1;
-		pkc1->nxt_offset = (char *)(pkc1->pkblk_start +
-		BLK_PLUS_PRIV(pkc1->blk_sizeof_priv));
-		BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
-		BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN;
-		pbd1->version = pkc1->version;
-		pkc1->prev = pkc1->nxt_offset;
-		pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size;
-		prb_thaw_queue(pkc1);
-		_prb_refresh_rx_retire_blk_timer(pkc1);
-
-		smp_wmb();
-
-		return;
-	}
+	/* We could have just memset this but we will lose the
+	 * flexibility of making the priv area sticky
+	 */
+	BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++;
+	BLOCK_NUM_PKTS(pbd1) = 0;
+	BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
+	getnstimeofday(&ts);
+	h1->ts_first_pkt.ts_sec = ts.tv_sec;
+	h1->ts_first_pkt.ts_nsec = ts.tv_nsec;
+	pkc1->pkblk_start = (char *)pbd1;
+	pkc1->nxt_offset = (char *)(pkc1->pkblk_start +
+				    BLK_PLUS_PRIV(pkc1->blk_sizeof_priv));
+	BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
+	BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN;
+	pbd1->version = pkc1->version;
+	pkc1->prev = pkc1->nxt_offset;
+	pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size;
+	prb_thaw_queue(pkc1);
+	_prb_refresh_rx_retire_blk_timer(pkc1);
 
-	WARN(1, "ERROR block:%p is NOT FREE status:%d kactive_blk_num:%d\n",
-		pbd1, BLOCK_STATUS(pbd1), pkc1->kactive_blk_num);
-	dump_stack();
-	BUG();
+	smp_wmb();
 }
 
 /*
@@ -934,10 +932,6 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc,
 		prb_close_block(pkc, pbd, po, status);
 		return;
 	}
-
-	WARN(1, "ERROR-pbd[%d]:%p\n", pkc->kactive_blk_num, pbd);
-	dump_stack();
-	BUG();
 }
 
 static int prb_curr_blk_in_use(struct tpacket_kbdq_core *pkc,
@@ -1176,16 +1170,6 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
-	int x = atomic_read(&f->rr_cur) + 1;
-
-	if (x >= num)
-		x = 0;
-
-	return x;
-}
-
 static struct sock *fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
 {
 	u32 idx, hash = skb->rxhash;
@@ -1197,13 +1181,9 @@ static struct sock *fanout_demux_hash(struct packet_fanout *f, struct sk_buff *s
 
 static struct sock *fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return f->arr[cur];
+	return f->arr[val % num];
 }
 
 static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
@@ -1217,7 +1197,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = ACCESS_ONCE(f->num_members);
 	struct packet_sock *po;
 	struct sock *sk;
 
@@ -1281,6 +1261,14 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	spin_unlock(&f->lock);
 }
 
+bool match_fanout_group(struct packet_type *ptype, struct sock * sk)
+{
+	if (sk->sk_family != PF_PACKET)
+		return false;
+
+	return ptype->af_packet_priv == pkt_sk(sk)->fanout;
+}
+
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
 	struct packet_sock *po = pkt_sk(sk);
@@ -1298,13 +1286,16 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		return -EINVAL;
 	}
 
+	mutex_lock(&fanout_mutex);
+
+	err = -EINVAL;
 	if (!po->running)
-		return -EINVAL;
+		goto out;
 
+	err = -EALREADY;
 	if (po->fanout)
-		return -EALREADY;
+		goto out;
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1333,6 +1324,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->prot_hook.dev = po->prot_hook.dev;
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
+		match->prot_hook.id_match = match_fanout_group;
 		dev_add_pack(&match->prot_hook);
 		list_add(&match->list, &fanout_list);
 	}
@@ -1359,17 +1351,16 @@ static void fanout_release(struct sock *sk)
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
 
+	mutex_lock(&fanout_mutex);
 	f = po->fanout;
-	if (!f)
-		return;
-
-	po->fanout = NULL;
+	if (f) {
+		po->fanout = NULL;
 
-	mutex_lock(&fanout_mutex);
-	if (atomic_dec_and_test(&f->sk_ref)) {
-		list_del(&f->list);
-		dev_remove_pack(&f->prot_hook);
-		kfree(f);
+		if (atomic_dec_and_test(&f->sk_ref)) {
+			list_del(&f->list);
+			dev_remove_pack(&f->prot_hook);
+			kfree(f);
+		}
 	}
 	mutex_unlock(&fanout_mutex);
 }
@@ -1630,8 +1621,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (snaplen > res)
 		snaplen = res;
 
-	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
-	    (unsigned)sk->sk_rcvbuf)
+	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto drop_n_acct;
 
 	if (skb_shared(skb)) {
@@ -1762,8 +1752,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (po->tp_version <= TPACKET_V2) {
 		if (macoff + snaplen > po->rx_ring.frame_size) {
 			if (po->copy_thresh &&
-				atomic_read(&sk->sk_rmem_alloc) + skb->truesize
-				< (unsigned)sk->sk_rcvbuf) {
+			    atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
 				if (skb_shared(skb)) {
 					copy_skb = skb_clone(skb, GFP_ATOMIC);
 				} else {
@@ -1933,7 +1922,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 
 	if (likely(po->tx_ring.pg_vec)) {
 		ph = skb_shinfo(skb)->destructor_arg;
-		BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING);
 		BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
 		atomic_dec(&po->tx_ring.pending);
 		__packet_set_status(po, ph, TP_STATUS_AVAILABLE);
@@ -2040,12 +2028,24 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	return tp_len;
 }
 
+static struct net_device *packet_cached_dev_get(struct packet_sock *po)
+{
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = rcu_dereference(po->cached_dev);
+	if (dev)
+		dev_hold(dev);
+	rcu_read_unlock();
+
+	return dev;
+}
+
 static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	bool need_rls_dev = false;
 	int err, reserve = 0;
 	void *ph;
 	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
@@ -2058,7 +2058,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 	err = -EBUSY;
 	if (saddr == NULL) {
-		dev = po->prot_hook.dev;
+		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
 		addr	= NULL;
 	} else {
@@ -2072,19 +2072,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
-		need_rls_dev = true;
 	}
 
 	err = -ENXIO;
 	if (unlikely(dev == NULL))
 		goto out;
-
-	reserve = dev->hard_header_len;
-
 	err = -ENETDOWN;
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	reserve = dev->hard_header_len;
+
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
@@ -2160,8 +2158,7 @@ out_status:
 	__packet_set_status(po, ph, status);
 	kfree_skb(skb);
 out_put:
-	if (need_rls_dev)
-		dev_put(dev);
+	dev_put(dev);
 out:
 	mutex_unlock(&po->pg_vec_lock);
 	return err;
@@ -2199,7 +2196,6 @@ static int packet_snd(struct socket *sock,
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	bool need_rls_dev = false;
 	unsigned char *addr;
 	int err, reserve = 0;
 	struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2213,7 +2209,7 @@ static int packet_snd(struct socket *sock,
 	 */
 
 	if (saddr == NULL) {
-		dev = po->prot_hook.dev;
+		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
 		addr	= NULL;
 	} else {
@@ -2225,19 +2221,17 @@ static int packet_snd(struct socket *sock,
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
-		need_rls_dev = true;
 	}
 
 	err = -ENXIO;
-	if (dev == NULL)
+	if (unlikely(dev == NULL))
 		goto out_unlock;
-	if (sock->type == SOCK_RAW)
-		reserve = dev->hard_header_len;
-
 	err = -ENETDOWN;
-	if (!(dev->flags & IFF_UP))
+	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
+	if (sock->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	if (po->has_vnet_hdr) {
 		vnet_hdr_len = sizeof(vnet_hdr);
 
@@ -2358,15 +2352,14 @@ static int packet_snd(struct socket *sock,
 	if (err > 0 && (err = net_xmit_errno(err)) != 0)
 		goto out_unlock;
 
-	if (need_rls_dev)
-		dev_put(dev);
+	dev_put(dev);
 
 	return len;
 
 out_free:
 	kfree_skb(skb);
 out_unlock:
-	if (dev && need_rls_dev)
+	if (dev)
 		dev_put(dev);
 out:
 	return err;
@@ -2416,13 +2409,15 @@ static int packet_release(struct socket *sock)
 
 	packet_flush_mclist(sk);
 
-	memset(&req_u, 0, sizeof(req_u));
-
-	if (po->rx_ring.pg_vec)
+	if (po->rx_ring.pg_vec) {
+		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 0);
+	}
 
-	if (po->tx_ring.pg_vec)
+	if (po->tx_ring.pg_vec) {
+		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 1);
+	}
 
 	fanout_release(sk);
 
@@ -2450,8 +2445,12 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc
 {
 	struct packet_sock *po = pkt_sk(sk);
 
-	if (po->fanout)
+	if (po->fanout) {
+		if (dev)
+			dev_put(dev);
+
 		return -EINVAL;
+	}
 
 	lock_sock(sk);
 
@@ -2577,6 +2576,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	po = pkt_sk(sk);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
+	RCU_INIT_POINTER(po->cached_dev, NULL);
 
 	sk->sk_destruct = packet_sock_destruct;
 	sk_refcnt_debug_inc(sk);
@@ -2665,7 +2665,6 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
-	struct sockaddr_ll *sll;
 	int vnet_hdr_len = 0;
 
 	err = -EINVAL;
@@ -2748,22 +2747,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 			goto out_free;
 	}
 
-	/*
-	 *	If the address length field is there to be filled in, we fill
-	 *	it in now.
-	 */
-
-	sll = &PACKET_SKB_CB(skb)->sa.ll;
-	if (sock->type == SOCK_PACKET)
-		msg->msg_namelen = sizeof(struct sockaddr_pkt);
-	else
-		msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
-	/*
-	 *	You lose any data beyond the buffer you gave. If it worries a
-	 *	user program they can ask the device for its MTU anyway.
+	/* You lose any data beyond the buffer you gave. If it worries
+	 * a user program they can ask the device for its MTU
+	 * anyway.
 	 */
-
 	copied = skb->len;
 	if (copied > len) {
 		copied = len;
@@ -2776,9 +2763,20 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	sock_recv_ts_and_drops(msg, sk, skb);
 
-	if (msg->msg_name)
+	if (msg->msg_name) {
+		/* If the address length field is there to be filled
+		 * in, we fill it in now.
+		 */
+		if (sock->type == SOCK_PACKET) {
+			msg->msg_namelen = sizeof(struct sockaddr_pkt);
+		} else {
+			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+			msg->msg_namelen = sll->sll_halen +
+				offsetof(struct sockaddr_ll, sll_addr);
+		}
 		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
 		       msg->msg_namelen);
+	}
 
 	if (pkt_sk(sk)->auxdata) {
 		struct tpacket_auxdata aux;
@@ -2822,12 +2820,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
 		return -EOPNOTSUPP;
 
 	uaddr->sa_family = AF_PACKET;
+	memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data));
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex);
 	if (dev)
-		strncpy(uaddr->sa_data, dev->name, 14);
-	else
-		memset(uaddr->sa_data, 0, 14);
+		strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data));
 	rcu_read_unlock();
 	*uaddr_len = sizeof(*uaddr);
 
@@ -3082,19 +3079,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		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;
 		switch (val) {
 		case TPACKET_V1:
 		case TPACKET_V2:
 		case TPACKET_V3:
-			po->tp_version = val;
-			return 0;
+			break;
 		default:
 			return -EINVAL;
 		}
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_version = val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_RESERVE:
 	{
@@ -3565,6 +3568,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	/* Added to avoid minimal code churn */
 	struct tpacket_req *req = &req_u->req;
 
+	lock_sock(sk);
 	/* Opening a Tx-ring is NOT supported in TPACKET_V3 */
 	if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) {
 		WARN(1, "Tx-ring is not supported.\n");
@@ -3642,7 +3646,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 	}
 
-	lock_sock(sk);
 
 	/* Detach socket from network */
 	spin_lock(&po->bind_lock);
@@ -3691,11 +3694,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue);
 	}
-	release_sock(sk);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
+	release_sock(sk);
 	return err;
 }