From f0f6ee1f70c4eaab9d52cf7d255df4bd89f8d1c2 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Mon, 1 Apr 2013 03:01:32 +0000 Subject: cbq: incorrect processing of high limits currently cbq works incorrectly for limits > 10% real link bandwidth, and practically does not work for limits > 50% real link bandwidth. Below are results of experiments taken on 1 Gbit link In shaper | Actual Result -----------+--------------- 100M | 108 Mbps 200M | 244 Mbps 300M | 412 Mbps 500M | 893 Mbps This happen because of q->now changes incorrectly in cbq_dequeue(): when it is called before real end of packet transmitting, L2T is greater than real time delay, q_now gets an extra boost but never compensate it. To fix this problem we prevent change of q->now until its synchronization with real time. Signed-off-by: Vasily Averin Reviewed-by: Alexey Kuznetsov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/sch_cbq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 13aa47aa2ffb..1bc210ffcba2 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -962,8 +962,11 @@ cbq_dequeue(struct Qdisc *sch) cbq_update(q); if ((incr -= incr2) < 0) incr = 0; + q->now += incr; + } else { + if (now > q->now) + q->now = now; } - q->now += incr; q->now_rt = now; for (;;) { -- cgit v1.2.3-59-g8ed1b From 25fb6ca4ed9cad72f14f61629b68dc03c0d9713f Mon Sep 17 00:00:00 2001 From: Balakumaran Kannan Date: Tue, 2 Apr 2013 16:15:05 +0530 Subject: net IPv6 : Fix broken IPv6 routing table after loopback down-up IPv6 Routing table becomes broken once we do ifdown, ifup of the loopback(lo) interface. After down-up, routes of other interface's IPv6 addresses through 'lo' are lost. IPv6 addresses assigned to all interfaces are routed through 'lo' for internal communication. Once 'lo' is down, those routing entries are removed from routing table. But those removed entries are not being re-created properly when 'lo' is brought up. So IPv6 addresses of other interfaces becomes unreachable from the same machine. Also this breaks communication with other machines because of NDISC packet processing failure. This patch fixes this issue by reading all interface's IPv6 addresses and adding them to IPv6 routing table while bringing up 'lo'. ==Testing== Before applying the patch: $ route -A inet6 Kernel IPv6 routing table Destination Next Hop Flag Met Ref Use If 2000::20/128 :: U 256 0 0 eth0 fe80::/64 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo ::1/128 :: Un 0 1 0 lo 2000::20/128 :: Un 0 1 0 lo fe80::xxxx:xxxx:xxxx:xxxx/128 :: Un 0 1 0 lo ff00::/8 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo $ sudo ifdown lo $ sudo ifup lo $ route -A inet6 Kernel IPv6 routing table Destination Next Hop Flag Met Ref Use If 2000::20/128 :: U 256 0 0 eth0 fe80::/64 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo ::1/128 :: Un 0 1 0 lo ff00::/8 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo $ After applying the patch: $ route -A inet6 Kernel IPv6 routing table Destination Next Hop Flag Met Ref Use If 2000::20/128 :: U 256 0 0 eth0 fe80::/64 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo ::1/128 :: Un 0 1 0 lo 2000::20/128 :: Un 0 1 0 lo fe80::xxxx:xxxx:xxxx:xxxx/128 :: Un 0 1 0 lo ff00::/8 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo $ sudo ifdown lo $ sudo ifup lo $ route -A inet6 Kernel IPv6 routing table Destination Next Hop Flag Met Ref Use If 2000::20/128 :: U 256 0 0 eth0 fe80::/64 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo ::1/128 :: Un 0 1 0 lo 2000::20/128 :: Un 0 1 0 lo fe80::xxxx:xxxx:xxxx:xxxx/128 :: Un 0 1 0 lo ff00::/8 :: U 256 0 0 eth0 ::/0 :: !n -1 1 1 lo $ Signed-off-by: Balakumaran Kannan Signed-off-by: Maruthi Thotad Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'net') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 26512250e095..a459c4f5b769 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2529,6 +2529,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) static void init_loopback(struct net_device *dev) { struct inet6_dev *idev; + struct net_device *sp_dev; + struct inet6_ifaddr *sp_ifa; + struct rt6_info *sp_rt; /* ::1 */ @@ -2540,6 +2543,30 @@ static void init_loopback(struct net_device *dev) } add_addr(idev, &in6addr_loopback, 128, IFA_HOST); + + /* Add routes to other interface's IPv6 addresses */ + for_each_netdev(dev_net(dev), sp_dev) { + if (!strcmp(sp_dev->name, dev->name)) + continue; + + idev = __in6_dev_get(sp_dev); + if (!idev) + continue; + + read_lock_bh(&idev->lock); + list_for_each_entry(sp_ifa, &idev->addr_list, if_list) { + + if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE)) + continue; + + sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0); + + /* Failure cases are ignored */ + if (!IS_ERR(sp_rt)) + ip6_ins_rt(sp_rt); + } + read_unlock_bh(&idev->lock); + } } static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) -- cgit v1.2.3-59-g8ed1b From 990454b5a48babde44a23c0f22bae5523f4fdf13 Mon Sep 17 00:00:00 2001 From: Reilly Grant Date: Mon, 1 Apr 2013 11:41:52 -0700 Subject: VSOCK: Handle changes to the VMCI context ID. The VMCI context ID of a virtual machine may change at any time. There is a VMCI event which signals this but datagrams may be processed before this is handled. It is therefore necessary to be flexible about the destination context ID of any datagrams received. (It can be assumed to be correct because it is provided by the hypervisor.) The context ID on existing sockets should be updated to reflect how the hypervisor is currently referring to the system. Signed-off-by: Reilly Grant Acked-by: Andy King Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 6 +++--- net/vmw_vsock/vmci_transport.c | 31 ++++++++++++++++++++----------- net/vmw_vsock/vsock_addr.c | 10 ---------- net/vmw_vsock/vsock_addr.h | 2 -- 4 files changed, 23 insertions(+), 26 deletions(-) (limited to 'net') diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ca511c4f388a..d8079daf1bde 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -207,7 +207,7 @@ static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) - if (vsock_addr_equals_addr_any(addr, &vsk->local_addr)) + if (addr->svm_port == vsk->local_addr.svm_port) return sk_vsock(vsk); return NULL; @@ -220,8 +220,8 @@ static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { - if (vsock_addr_equals_addr(src, &vsk->remote_addr) - && vsock_addr_equals_addr(dst, &vsk->local_addr)) { + if (vsock_addr_equals_addr(src, &vsk->remote_addr) && + dst->svm_port == vsk->local_addr.svm_port) { return sk_vsock(vsk); } } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index a70ace83a153..1f6508e249ae 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -464,19 +464,16 @@ static struct sock *vmci_transport_get_pending( struct vsock_sock *vlistener; struct vsock_sock *vpending; struct sock *pending; + struct sockaddr_vm src; + + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); vlistener = vsock_sk(listener); list_for_each_entry(vpending, &vlistener->pending_links, pending_links) { - struct sockaddr_vm src; - struct sockaddr_vm dst; - - vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); - vsock_addr_init(&dst, pkt->dg.dst.context, pkt->dst_port); - if (vsock_addr_equals_addr(&src, &vpending->remote_addr) && - vsock_addr_equals_addr(&dst, &vpending->local_addr)) { + pkt->dst_port == vpending->local_addr.svm_port) { pending = sk_vsock(vpending); sock_hold(pending); goto found; @@ -739,10 +736,15 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) */ bh_lock_sock(sk); - if (!sock_owned_by_user(sk) && sk->sk_state == SS_CONNECTED) - vmci_trans(vsk)->notify_ops->handle_notify_pkt( - sk, pkt, true, &dst, &src, - &bh_process_pkt); + if (!sock_owned_by_user(sk)) { + /* The local context ID may be out of date, update it. */ + vsk->local_addr.svm_cid = dst.svm_cid; + + if (sk->sk_state == SS_CONNECTED) + vmci_trans(vsk)->notify_ops->handle_notify_pkt( + sk, pkt, true, &dst, &src, + &bh_process_pkt); + } bh_unlock_sock(sk); @@ -902,6 +904,9 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) lock_sock(sk); + /* The local context ID may be out of date. */ + vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; + switch (sk->sk_state) { case SS_LISTEN: vmci_transport_recv_listen(sk, pkt); @@ -958,6 +963,10 @@ static int vmci_transport_recv_listen(struct sock *sk, pending = vmci_transport_get_pending(sk, pkt); if (pending) { lock_sock(pending); + + /* The local context ID may be out of date. */ + vsock_sk(pending)->local_addr.svm_cid = pkt->dg.dst.context; + switch (pending->sk_state) { case SS_CONNECTING: err = vmci_transport_recv_connecting_server(sk, diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c index b7df1aea7c59..ec2611b4ea0e 100644 --- a/net/vmw_vsock/vsock_addr.c +++ b/net/vmw_vsock/vsock_addr.c @@ -64,16 +64,6 @@ bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, } EXPORT_SYMBOL_GPL(vsock_addr_equals_addr); -bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr, - const struct sockaddr_vm *other) -{ - return (addr->svm_cid == VMADDR_CID_ANY || - other->svm_cid == VMADDR_CID_ANY || - addr->svm_cid == other->svm_cid) && - addr->svm_port == other->svm_port; -} -EXPORT_SYMBOL_GPL(vsock_addr_equals_addr_any); - int vsock_addr_cast(const struct sockaddr *addr, size_t len, struct sockaddr_vm **out_addr) { diff --git a/net/vmw_vsock/vsock_addr.h b/net/vmw_vsock/vsock_addr.h index cdfbcefdf843..9ccd5316eac0 100644 --- a/net/vmw_vsock/vsock_addr.h +++ b/net/vmw_vsock/vsock_addr.h @@ -24,8 +24,6 @@ bool vsock_addr_bound(const struct sockaddr_vm *addr); void vsock_addr_unbind(struct sockaddr_vm *addr); bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, const struct sockaddr_vm *other); -bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr, - const struct sockaddr_vm *other); int vsock_addr_cast(const struct sockaddr *addr, size_t len, struct sockaddr_vm **out_addr); -- cgit v1.2.3-59-g8ed1b