From d145f7ec23b6366e2b75442eaefafa11077ed568 Mon Sep 17 00:00:00 2001 From: Xiaotian Feng Date: Tue, 30 Oct 2012 22:06:01 +0000 Subject: tipc: do not use tasklet_disable before tasklet_kill If tasklet_disable() is called before related tasklet handled, tasklet_kill will never be finished. tasklet_kill is enough. Signed-off-by: Xiaotian Feng Cc: Jon Maloy Cc: Allan Stephens Cc: "David S. Miller" Cc: netdev@vger.kernel.org Cc: tipc-discussion@lists.sourceforge.net Signed-off-by: David S. Miller --- net/tipc/handler.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/tipc/handler.c b/net/tipc/handler.c index 111ff8300ae5..b36f0fcd9bdf 100644 --- a/net/tipc/handler.c +++ b/net/tipc/handler.c @@ -116,7 +116,6 @@ void tipc_handler_stop(void) return; handler_enabled = 0; - tasklet_disable(&tipc_tasklet); tasklet_kill(&tipc_tasklet); spin_lock_bh(&qitem_lock); -- cgit v1.2.2 From a7a558fe426adf22b0b979705167146bf16c37fa Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 1 Nov 2012 16:23:10 +0000 Subject: rtnetlink: Use nlmsg type RTM_NEWNEIGH from dflt fdb dump Change the dflt fdb dump handler to use RTM_NEWNEIGH to be compatible with bridge dump routines. The dump reply from the network driver handlers should match the reply from bridge handler. The fact they were not in the ixgbe case was effectively a bug. This patch resolves it. Applications that were not checking the nlmsg type will continue to work. And now applications that do check the type will work as expected. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 76d4c2c3c89b..fad649ae4dec 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2192,7 +2192,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, - portid, seq, 0, NTF_SELF); + portid, seq, + RTM_NEWNEIGH, NTF_SELF); if (err < 0) return err; skip: -- cgit v1.2.2 From cacb6ba0f36ab14a507f4ee7697e8332899015d2 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Sat, 3 Nov 2012 09:30:34 +0000 Subject: net: inet_diag -- Return error code if protocol handler is missed We've observed that in case if UDP diag module is not supported in kernel the netlink returns NLMSG_DONE without notifying a caller that handler is missed. This patch makes __inet_diag_dump to return error code instead. So as example it become possible to detect such situation and handle it gracefully on userspace level. Signed-off-by: Cyrill Gorcunov CC: David Miller CC: Eric Dumazet CC: Pavel Emelyanov Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/ipv4/inet_diag.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 535584c00f91..0c34bfabc11f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -892,13 +892,16 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct inet_diag_req_v2 *r, struct nlattr *bc) { const struct inet_diag_handler *handler; + int err = 0; handler = inet_diag_lock_handler(r->sdiag_protocol); if (!IS_ERR(handler)) handler->dump(skb, cb, r, bc); + else + err = PTR_ERR(handler); inet_diag_unlock_handler(handler); - return skb->len; + return err ? : skb->len; } static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) -- cgit v1.2.2 From 3015f3d2a3cd9614294025849d3ed89fd2f3a7f5 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Mon, 5 Nov 2012 20:29:24 +0000 Subject: pkt_sched: enable QFQ to support TSO/GSO If the max packet size for some class (configured through tc) is violated by the actual size of the packets of that class, then QFQ would not schedule classes correctly, and the data structures implementing the bucket lists may get corrupted. This problem occurs with TSO/GSO even if the max packet size is set to the MTU, and is, e.g., the cause of the failure reported in [1]. Two patches have been proposed to solve this problem in [2], one of them is a preliminary version of this patch. This patch addresses the above issues by: 1) setting QFQ parameters to proper values for supporting TSO/GSO (in particular, setting the maximum possible packet size to 64KB), 2) automatically increasing the max packet size for a class, lmax, when a packet with a larger size than the current value of lmax arrives. The drawback of the first point is that the maximum weight for a class is now limited to 4096, which is equal to 1/16 of the maximum weight sum. Finally, this patch also forcibly caps the timestamps of a class if they are too high to be stored in the bucket list. This capping, taken from QFQ+ [3], handles the unfrequent case described in the comment to the function slot_insert. [1] http://marc.info/?l=linux-netdev&m=134968777902077&w=2 [2] http://marc.info/?l=linux-netdev&m=135096573507936&w=2 [3] http://marc.info/?l=linux-netdev&m=134902691421670&w=2 Signed-off-by: Paolo Valente Tested-by: Cong Wang Acked-by: Stephen Hemminger Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/sched/sch_qfq.c | 109 +++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 79 insertions(+), 30 deletions(-) (limited to 'net') diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f0dd83cff906..9687fa1c2275 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -84,18 +84,19 @@ * grp->index is the index of the group; and grp->slot_shift * is the shift for the corresponding (scaled) sigma_i. */ -#define QFQ_MAX_INDEX 19 -#define QFQ_MAX_WSHIFT 16 +#define QFQ_MAX_INDEX 24 +#define QFQ_MAX_WSHIFT 12 #define QFQ_MAX_WEIGHT (1<wsum += delta_w; } +static void qfq_update_reactivate_class(struct qfq_sched *q, + struct qfq_class *cl, + u32 inv_w, u32 lmax, int delta_w) +{ + bool need_reactivation = false; + int i = qfq_calc_index(inv_w, lmax); + + if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { + /* + * shift cl->F back, to not charge the + * class for the not-yet-served head + * packet + */ + cl->F = cl->S; + /* remove class from its slot in the old group */ + qfq_deactivate_class(q, cl); + need_reactivation = true; + } + + qfq_update_class_params(q, cl, lmax, inv_w, delta_w); + + if (need_reactivation) /* activate in new group */ + qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); +} + + static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg) { @@ -238,7 +265,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct qfq_class *cl = (struct qfq_class *)*arg; struct nlattr *tb[TCA_QFQ_MAX + 1]; u32 weight, lmax, inv_w; - int i, err; + int err; int delta_w; if (tca[TCA_OPTIONS] == NULL) { @@ -270,16 +297,14 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) { + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { pr_notice("qfq: invalid max length %u\n", lmax); return -EINVAL; } } else - lmax = 1UL << QFQ_MTU_SHIFT; + lmax = psched_mtu(qdisc_dev(sch)); if (cl != NULL) { - bool need_reactivation = false; - if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, &cl->rate_est, qdisc_root_sleeping_lock(sch), @@ -291,24 +316,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (lmax == cl->lmax && inv_w == cl->inv_w) return 0; /* nothing to update */ - i = qfq_calc_index(inv_w, lmax); sch_tree_lock(sch); - if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) { - /* - * shift cl->F back, to not charge the - * class for the not-yet-served head - * packet - */ - cl->F = cl->S; - /* remove class from its slot in the old group */ - qfq_deactivate_class(q, cl); - need_reactivation = true; - } - - qfq_update_class_params(q, cl, lmax, inv_w, delta_w); - - if (need_reactivation) /* activate in new group */ - qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc)); + qfq_update_reactivate_class(q, cl, inv_w, lmax, delta_w); sch_tree_unlock(sch); return 0; @@ -663,15 +672,48 @@ static void qfq_make_eligible(struct qfq_sched *q, u64 old_V) /* - * XXX we should make sure that slot becomes less than 32. - * This is guaranteed by the input values. - * roundedS is always cl->S rounded on grp->slot_shift bits. + * If the weight and lmax (max_pkt_size) of the classes do not change, + * then QFQ guarantees that the slot index is never higher than + * 2 + ((1<S) >> grp->slot_shift; - unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS; + unsigned int i; /* slot index in the bucket list */ + + if (unlikely(slot > QFQ_MAX_SLOTS - 2)) { + u64 deltaS = roundedS - grp->S - + ((u64)(QFQ_MAX_SLOTS - 2)<slot_shift); + cl->S -= deltaS; + cl->F -= deltaS; + slot = QFQ_MAX_SLOTS - 2; + } + + i = (grp->front + slot) % QFQ_MAX_SLOTS; hlist_add_head(&cl->next, &grp->slots[i]); __set_bit(slot, &grp->full_slots); @@ -892,6 +934,13 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) } pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); + if (unlikely(cl->lmax < qdisc_pkt_len(skb))) { + pr_debug("qfq: increasing maxpkt from %u to %u for class %u", + cl->lmax, qdisc_pkt_len(skb), cl->common.classid); + qfq_update_reactivate_class(q, cl, cl->inv_w, + qdisc_pkt_len(skb), 0); + } + err = qdisc_enqueue(skb, cl->qdisc); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); -- cgit v1.2.2 From a3d744e995d2b936c500585ae39d99ee251c89b4 Mon Sep 17 00:00:00 2001 From: Eric Leblond Date: Tue, 6 Nov 2012 02:10:10 +0000 Subject: af-packet: fix oops when socket is not present MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Due to a NULL dereference, the following patch is causing oops in normal trafic condition: commit c0de08d04215031d68fa13af36f347a6cfa252ca Author: Eric Leblond Date:   Thu Aug 16 22:02:58 2012 +0000     af_packet: don't emit packet on orig fanout group This buggy patch was a feature fix and has reached most stable branches. When skb->sk is NULL and when packet fanout is used, there is a crash in match_fanout_group where skb->sk is accessed. This patch fixes the issue by returning false as soon as the socket is NULL: this correspond to the wanted behavior because the kernel as to resend the skb to all the listening socket in this case. Signed-off-by: Eric Leblond Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 09cb3f6dc40c..bda6d004f9f0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1666,7 +1666,7 @@ static inline int deliver_skb(struct sk_buff *skb, static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { - if (ptype->af_packet_priv == NULL) + if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) -- cgit v1.2.2 From 60713a0ca7fd6651b951cc1b4dbd528d1fc0281b Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Tue, 6 Nov 2012 16:18:41 +0000 Subject: ipv6: send unsolicited neighbour advertisements to all-nodes As documented in RFC4861 (Neighbor Discovery for IP version 6) 7.2.6., unsolicited neighbour advertisements should be sent to the all-nodes multicast address. Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ndisc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ff36194a71aa..2edce30ef733 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -535,7 +535,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; - struct in6_addr mcaddr; + struct in6_addr mcaddr = IN6ADDR_LINKLOCAL_ALLNODES_INIT; idev = in6_dev_get(dev); if (!idev) @@ -543,7 +543,6 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - addrconf_addr_solict_mult(&ifa->addr, &mcaddr); ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, -- cgit v1.2.2 From a375413311b39005ef281bfd71ae8f4e3df22e97 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 9 Nov 2012 05:34:56 +0000 Subject: gre6: fix rtnl dump messages Spotted after a code review. Introduced by c12b395a46646bab69089ce7016ac78177f6001f (gre: Support GRE over IPv6). Signed-off-by: Nicolas Dichtel Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 0185679c5f53..d5cb3c4e66f8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1633,9 +1633,9 @@ static size_t ip6gre_get_size(const struct net_device *dev) /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_REMOTE */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ @@ -1659,8 +1659,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || - nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) || - nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || -- cgit v1.2.2