From 00093fab980d0a8950a64bdf9e346d0497b9a7e4 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 14 Aug 2010 11:09:49 +0000 Subject: net/sched: remove unneeded NULL check There is no need to check "s". nla_data() doesn't return NULL. Also we already dereferenced "s" at this point so it would have oopsed ealier if it were NULL. Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/sched/sch_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/sched') diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 408eea7086aa..6fb3d41c0e41 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -360,7 +360,7 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) tsize = nla_len(tb[TCA_STAB_DATA]) / sizeof(u16); } - if (!s || tsize != s->tsize || (!tab && tsize > 0)) + if (tsize != s->tsize || (!tab && tsize > 0)) return ERR_PTR(-EINVAL); spin_lock(&qdisc_stab_lock); -- cgit v1.2.3 From 78d3307eded853f01c5e9aaa8c0768c2f75825a3 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 17 Aug 2010 19:05:08 +0000 Subject: net_sched: cls_flow: use proto_ports_offset() to support AH message Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- net/sched/cls_flow.c | 67 +++++++++++++++++++++++++++++----------------------- 1 file changed, 38 insertions(+), 29 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index e17096e3913c..cd709f1294df 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -111,44 +111,41 @@ static u32 flow_get_proto(struct sk_buff *skb) } } -static int has_ports(u8 protocol) -{ - switch (protocol) { - case IPPROTO_TCP: - case IPPROTO_UDP: - case IPPROTO_UDPLITE: - case IPPROTO_SCTP: - case IPPROTO_DCCP: - case IPPROTO_ESP: - return 1; - default: - return 0; - } -} - static u32 flow_get_proto_src(struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): { struct iphdr *iph; + int poff; if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) && - has_ports(iph->protocol) && - pskb_network_may_pull(skb, iph->ihl * 4 + 2)) - return ntohs(*(__be16 *)((void *)iph + iph->ihl * 4)); + if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + break; + poff = proto_ports_offset(iph->protocol); + if (poff >= 0 && + pskb_network_may_pull(skb, iph->ihl * 4 + 2 + poff)) { + iph = ip_hdr(skb); + return ntohs(*(__be16 *)((void *)iph + iph->ihl * 4 + + poff)); + } break; } case htons(ETH_P_IPV6): { struct ipv6hdr *iph; + int poff; - if (!pskb_network_may_pull(skb, sizeof(*iph) + 2)) + if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ipv6_hdr(skb); - if (has_ports(iph->nexthdr)) - return ntohs(*(__be16 *)&iph[1]); + poff = proto_ports_offset(iph->nexthdr); + if (poff >= 0 && + pskb_network_may_pull(skb, sizeof(*iph) + poff + 2)) { + iph = ipv6_hdr(skb); + return ntohs(*(__be16 *)((void *)iph + sizeof(*iph) + + poff)); + } break; } } @@ -161,24 +158,36 @@ static u32 flow_get_proto_dst(struct sk_buff *skb) switch (skb->protocol) { case htons(ETH_P_IP): { struct iphdr *iph; + int poff; if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) && - has_ports(iph->protocol) && - pskb_network_may_pull(skb, iph->ihl * 4 + 4)) - return ntohs(*(__be16 *)((void *)iph + iph->ihl * 4 + 2)); + if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + break; + poff = proto_ports_offset(iph->protocol); + if (poff >= 0 && + pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) { + iph = ip_hdr(skb); + return ntohs(*(__be16 *)((void *)iph + iph->ihl * 4 + + 2 + poff)); + } break; } case htons(ETH_P_IPV6): { struct ipv6hdr *iph; + int poff; - if (!pskb_network_may_pull(skb, sizeof(*iph) + 4)) + if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ipv6_hdr(skb); - if (has_ports(iph->nexthdr)) - return ntohs(*(__be16 *)((void *)&iph[1] + 2)); + poff = proto_ports_offset(iph->nexthdr); + if (poff >= 0 && + pskb_network_may_pull(skb, sizeof(*iph) + poff + 4)) { + iph = ipv6_hdr(skb); + return ntohs(*(__be16 *)((void *)iph + sizeof(*iph) + + poff + 2)); + } break; } } -- cgit v1.2.3 From b9959c2e4460b1df1d113d829180398588bb04b4 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 17 Aug 2010 19:07:35 +0000 Subject: net_sched: sch_sfq: use proto_ports_offset() to support AH message Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- net/sched/sch_sfq.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 201cbac2b32c..3cf478d012dd 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -123,40 +123,39 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) case htons(ETH_P_IP): { const struct iphdr *iph; + int poff; if (!pskb_network_may_pull(skb, sizeof(*iph))) goto err; iph = ip_hdr(skb); h = (__force u32)iph->daddr; h2 = (__force u32)iph->saddr ^ iph->protocol; - if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) && - (iph->protocol == IPPROTO_TCP || - iph->protocol == IPPROTO_UDP || - iph->protocol == IPPROTO_UDPLITE || - iph->protocol == IPPROTO_SCTP || - iph->protocol == IPPROTO_DCCP || - iph->protocol == IPPROTO_ESP) && - pskb_network_may_pull(skb, iph->ihl * 4 + 4)) - h2 ^= *(((u32*)iph) + iph->ihl); + if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + break; + poff = proto_ports_offset(iph->protocol); + if (poff >= 0 && + pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) { + iph = ip_hdr(skb); + h2 ^= *(u32*)((void *)iph + iph->ihl * 4 + poff); + } break; } case htons(ETH_P_IPV6): { struct ipv6hdr *iph; + int poff; if (!pskb_network_may_pull(skb, sizeof(*iph))) goto err; iph = ipv6_hdr(skb); h = (__force u32)iph->daddr.s6_addr32[3]; h2 = (__force u32)iph->saddr.s6_addr32[3] ^ iph->nexthdr; - if ((iph->nexthdr == IPPROTO_TCP || - iph->nexthdr == IPPROTO_UDP || - iph->nexthdr == IPPROTO_UDPLITE || - iph->nexthdr == IPPROTO_SCTP || - iph->nexthdr == IPPROTO_DCCP || - iph->nexthdr == IPPROTO_ESP) && - pskb_network_may_pull(skb, sizeof(*iph) + 4)) - h2 ^= *(u32*)&iph[1]; + poff = proto_ports_offset(iph->nexthdr); + if (poff >= 0 && + pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) { + iph = ipv6_hdr(skb); + h2 ^= *(u32*)((void *)iph + sizeof(*iph) + poff); + } break; } default: -- cgit v1.2.3 From eb4d40654505e47aa9d2035bb97f631fa61d14b4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Gr=C3=A9goire=20Baron?= Date: Wed, 18 Aug 2010 13:10:35 +0000 Subject: net/sched: add ACT_CSUM action to update packets checksums net/sched: add ACT_CSUM action to update packets checksums ACT_CSUM can be called just after ACT_PEDIT in order to re-compute some altered checksums in IPv4 and IPv6 packets. The following checksums are supported by this patch: - IPv4: IPv4 header, ICMP, IGMP, TCP, UDP & UDPLite - IPv6: ICMPv6, TCP, UDP & UDPLite It's possible to request in the same action to update different kind of checksums, if the packets flow mix TCP, UDP and UDPLite, ... An example of usage is done in the associated iproute2 patch. Version 3 changes: - remove useless goto instructions - improve IPv6 hop options decoding Version 2 changes: - coding style correction - remove useless arguments of some functions - use stack in tcf_csum_dump() - add tcf_csum_skb_nextlayer() to factor code Signed-off-by: Gregoire Baron Acked-by: jamal Signed-off-by: David S. Miller --- net/sched/Kconfig | 10 + net/sched/Makefile | 1 + net/sched/act_csum.c | 595 +++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 606 insertions(+) create mode 100644 net/sched/act_csum.c (limited to 'net/sched') diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2f691fb180d1..522d5a9a2825 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -518,6 +518,16 @@ config NET_ACT_SKBEDIT To compile this code as a module, choose M here: the module will be called act_skbedit. +config NET_ACT_CSUM + tristate "Checksum Updating" + depends on NET_CLS_ACT + ---help--- + Say Y here to update some common checksum after some direct + packet alterations. + + To compile this code as a module, choose M here: the + module will be called act_csum. + config NET_CLS_IND bool "Incoming device classification" depends on NET_CLS_U32 || NET_CLS_FW diff --git a/net/sched/Makefile b/net/sched/Makefile index f14e71bfa58f..960f5dba6304 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_NET_ACT_NAT) += act_nat.o obj-$(CONFIG_NET_ACT_PEDIT) += act_pedit.o obj-$(CONFIG_NET_ACT_SIMP) += act_simple.o obj-$(CONFIG_NET_ACT_SKBEDIT) += act_skbedit.o +obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c new file mode 100644 index 000000000000..58d7f36949da --- /dev/null +++ b/net/sched/act_csum.c @@ -0,0 +1,595 @@ +/* + * Checksum updating actions + * + * Copyright (c) 2010 Gregoire Baron + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#include +#include +#include +#include +#include + +#include +#include +#include + +#include + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include + +#define CSUM_TAB_MASK 15 +static struct tcf_common *tcf_csum_ht[CSUM_TAB_MASK + 1]; +static u32 csum_idx_gen; +static DEFINE_RWLOCK(csum_lock); + +static struct tcf_hashinfo csum_hash_info = { + .htab = tcf_csum_ht, + .hmask = CSUM_TAB_MASK, + .lock = &csum_lock, +}; + +static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { + [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, +}; + +static int tcf_csum_init(struct nlattr *nla, struct nlattr *est, + struct tc_action *a, int ovr, int bind) +{ + struct nlattr *tb[TCA_CSUM_MAX + 1]; + struct tc_csum *parm; + struct tcf_common *pc; + struct tcf_csum *p; + int ret = 0, err; + + if (nla == NULL) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_CSUM_MAX, nla,csum_policy); + if (err < 0) + return err; + + if (tb[TCA_CSUM_PARMS] == NULL) + return -EINVAL; + parm = nla_data(tb[TCA_CSUM_PARMS]); + + pc = tcf_hash_check(parm->index, a, bind, &csum_hash_info); + if (!pc) { + pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &csum_idx_gen, &csum_hash_info); + if (IS_ERR(pc)) + return PTR_ERR(pc); + p = to_tcf_csum(pc); + ret = ACT_P_CREATED; + } else { + p = to_tcf_csum(pc); + if (!ovr) { + tcf_hash_release(pc, bind, &csum_hash_info); + return -EEXIST; + } + } + + spin_lock_bh(&p->tcf_lock); + p->tcf_action = parm->action; + p->update_flags = parm->update_flags; + spin_unlock_bh(&p->tcf_lock); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(pc, &csum_hash_info); + + return ret; +} + +static int tcf_csum_cleanup(struct tc_action *a, int bind) +{ + struct tcf_csum *p = a->priv; + return tcf_hash_release(&p->common, bind, &csum_hash_info); +} + +/** + * tcf_csum_skb_nextlayer - Get next layer pointer + * @skb: sk_buff to use + * @ihl: previous summed headers length + * @ipl: complete packet length + * @jhl: next header length + * + * Check the expected next layer availability in the specified sk_buff. + * Return the next layer pointer if pass, NULL otherwise. + */ +static void *tcf_csum_skb_nextlayer(struct sk_buff *skb, + unsigned int ihl, unsigned int ipl, + unsigned int jhl) +{ + int ntkoff = skb_network_offset(skb); + int hl = ihl + jhl; + + if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) || + (skb_cloned(skb) && + !skb_clone_writable(skb, hl + ntkoff) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return NULL; + else + return (void *)(skb_network_header(skb) + ihl); +} + +static int tcf_csum_ipv4_icmp(struct sk_buff *skb, + unsigned int ihl, unsigned int ipl) +{ + struct icmphdr *icmph; + + icmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmph)); + if (icmph == NULL) + return 0; + + icmph->checksum = 0; + skb->csum = csum_partial(icmph, ipl - ihl, 0); + icmph->checksum = csum_fold(skb->csum); + + skb->ip_summed = CHECKSUM_NONE; + + return 1; +} + +static int tcf_csum_ipv4_igmp(struct sk_buff *skb, + unsigned int ihl, unsigned int ipl) +{ + struct igmphdr *igmph; + + igmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*igmph)); + if (igmph == NULL) + return 0; + + igmph->csum = 0; + skb->csum = csum_partial(igmph, ipl - ihl, 0); + igmph->csum = csum_fold(skb->csum); + + skb->ip_summed = CHECKSUM_NONE; + + return 1; +} + +static int tcf_csum_ipv6_icmp(struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int ihl, unsigned int ipl) +{ + struct icmp6hdr *icmp6h; + + icmp6h = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmp6h)); + if (icmp6h == NULL) + return 0; + + icmp6h->icmp6_cksum = 0; + skb->csum = csum_partial(icmp6h, ipl - ihl, 0); + icmp6h->icmp6_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + ipl - ihl, IPPROTO_ICMPV6, + skb->csum); + + skb->ip_summed = CHECKSUM_NONE; + + return 1; +} + +static int tcf_csum_ipv4_tcp(struct sk_buff *skb, struct iphdr *iph, + unsigned int ihl, unsigned int ipl) +{ + struct tcphdr *tcph; + + tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); + if (tcph == NULL) + return 0; + + tcph->check = 0; + skb->csum = csum_partial(tcph, ipl - ihl, 0); + tcph->check = tcp_v4_check(ipl - ihl, + iph->saddr, iph->daddr, skb->csum); + + skb->ip_summed = CHECKSUM_NONE; + + return 1; +} + +static int tcf_csum_ipv6_tcp(struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int ihl, unsigned int ipl) +{ + struct tcphdr *tcph; + + tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); + if (tcph == NULL) + return 0; + + tcph->check = 0; + skb->csum = csum_partial(tcph, ipl - ihl, 0); + tcph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + ipl - ihl, IPPROTO_TCP, + skb->csum); + + skb->ip_summed = CHECKSUM_NONE; + + return 1; +} + +static int tcf_csum_ipv4_udp(struct sk_buff *skb, struct iphdr *iph, + unsigned int ihl, unsigned int ipl, int udplite) +{ + struct udphdr *udph; + u16 ul; + + /* Support both UDP and UDPLITE checksum algorithms, + * Don't use udph->len to get the real length without any protocol check, + * UDPLITE uses udph->len for another thing, + * Use iph->tot_len, or just ipl. + */ + + udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); + if (udph == NULL) + return 0; + + ul = ntohs(udph->len); + + if (udplite || udph->check) { + + udph->check = 0; + + if (udplite) { + if (ul == 0) + skb->csum = csum_partial(udph, ipl - ihl, 0); + + else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) + skb->csum = csum_partial(udph, ul, 0); + + else + goto ignore_obscure_skb; + } else { + if (ul != ipl - ihl) + goto ignore_obscure_skb; + + skb->csum = csum_partial(udph, ul, 0); + } + + udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, + ul, iph->protocol, + skb->csum); + + if (!udph->check) + udph->check = CSUM_MANGLED_0; + } + + skb->ip_summed = CHECKSUM_NONE; + +ignore_obscure_skb: + return 1; +} + +static int tcf_csum_ipv6_udp(struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int ihl, unsigned int ipl, int udplite) +{ + struct udphdr *udph; + u16 ul; + + /* Support both UDP and UDPLITE checksum algorithms, + * Don't use udph->len to get the real length without any protocol check, + * UDPLITE uses udph->len for another thing, + * Use ip6h->payload_len + sizeof(*ip6h) ... , or just ipl. + */ + + udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); + if (udph == NULL) + return 0; + + ul = ntohs(udph->len); + + udph->check = 0; + + if (udplite) { + if (ul == 0) + skb->csum = csum_partial(udph, ipl - ihl, 0); + + else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) + skb->csum = csum_partial(udph, ul, 0); + + else + goto ignore_obscure_skb; + } else { + if (ul != ipl - ihl) + goto ignore_obscure_skb; + + skb->csum = csum_partial(udph, ul, 0); + } + + udph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ul, + udplite ? IPPROTO_UDPLITE : IPPROTO_UDP, + skb->csum); + + if (!udph->check) + udph->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_NONE; + +ignore_obscure_skb: + return 1; +} + +static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) +{ + struct iphdr *iph; + int ntkoff; + + ntkoff = skb_network_offset(skb); + + if (!pskb_may_pull(skb, sizeof(*iph) + ntkoff)) + goto fail; + + iph = ip_hdr(skb); + + switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) { + case IPPROTO_ICMP: + if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) + if (!tcf_csum_ipv4_icmp(skb, + iph->ihl * 4, ntohs(iph->tot_len))) + goto fail; + break; + case IPPROTO_IGMP: + if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP) + if (!tcf_csum_ipv4_igmp(skb, + iph->ihl * 4, ntohs(iph->tot_len))) + goto fail; + break; + case IPPROTO_TCP: + if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) + if (!tcf_csum_ipv4_tcp(skb, iph, + iph->ihl * 4, ntohs(iph->tot_len))) + goto fail; + break; + case IPPROTO_UDP: + if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) + if (!tcf_csum_ipv4_udp(skb, iph, + iph->ihl * 4, ntohs(iph->tot_len), 0)) + goto fail; + break; + case IPPROTO_UDPLITE: + if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) + if (!tcf_csum_ipv4_udp(skb, iph, + iph->ihl * 4, ntohs(iph->tot_len), 1)) + goto fail; + break; + } + + if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) { + if (skb_cloned(skb) && + !skb_clone_writable(skb, sizeof(*iph) + ntkoff) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + goto fail; + + ip_send_check(iph); + } + + return 1; + +fail: + return 0; +} + +static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, + unsigned int ixhl, unsigned int *pl) +{ + int off, len, optlen; + unsigned char *xh = (void *)ip6xh; + + off = sizeof(*ip6xh); + len = ixhl - off; + + while (len > 1) { + switch (xh[off]) + { + case IPV6_TLV_PAD0: + optlen = 1; + break; + case IPV6_TLV_JUMBO: + optlen = xh[off + 1] + 2; + if (optlen != 6 || len < 6 || (off & 3) != 2) + /* wrong jumbo option length/alignment */ + return 0; + *pl = ntohl(*(__be32 *)(xh + off + 2)); + goto done; + default: + optlen = xh[off + 1] + 2; + if (optlen > len) + /* ignore obscure options */ + goto done; + break; + } + off += optlen; + len -= optlen; + } + +done: + return 1; +} + +static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags) +{ + struct ipv6hdr *ip6h; + struct ipv6_opt_hdr *ip6xh; + unsigned int hl, ixhl; + unsigned int pl; + int ntkoff; + u8 nexthdr; + + ntkoff = skb_network_offset(skb); + + hl = sizeof(*ip6h); + + if (!pskb_may_pull(skb, hl + ntkoff)) + goto fail; + + ip6h = ipv6_hdr(skb); + + pl = ntohs(ip6h->payload_len); + nexthdr = ip6h->nexthdr; + + do { + switch (nexthdr) { + case NEXTHDR_FRAGMENT: + goto ignore_skb; + case NEXTHDR_ROUTING: + case NEXTHDR_HOP: + case NEXTHDR_DEST: + if (!pskb_may_pull(skb, hl + sizeof(*ip6xh) + ntkoff)) + goto fail; + ip6xh = (void *)(skb_network_header(skb) + hl); + ixhl = ipv6_optlen(ip6xh); + if (!pskb_may_pull(skb, hl + ixhl + ntkoff)) + goto fail; + if ((nexthdr == NEXTHDR_HOP) && + !(tcf_csum_ipv6_hopopts(ip6xh, ixhl, &pl))) + goto fail; + nexthdr = ip6xh->nexthdr; + hl += ixhl; + break; + case IPPROTO_ICMPV6: + if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) + if (!tcf_csum_ipv6_icmp(skb, ip6h, + hl, pl + sizeof(*ip6h))) + goto fail; + goto done; + case IPPROTO_TCP: + if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) + if (!tcf_csum_ipv6_tcp(skb, ip6h, + hl, pl + sizeof(*ip6h))) + goto fail; + goto done; + case IPPROTO_UDP: + if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) + if (!tcf_csum_ipv6_udp(skb, ip6h, + hl, pl + sizeof(*ip6h), 0)) + goto fail; + goto done; + case IPPROTO_UDPLITE: + if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) + if (!tcf_csum_ipv6_udp(skb, ip6h, + hl, pl + sizeof(*ip6h), 1)) + goto fail; + goto done; + default: + goto ignore_skb; + } + } while (pskb_may_pull(skb, hl + 1 + ntkoff)); + +done: +ignore_skb: + return 1; + +fail: + return 0; +} + +static int tcf_csum(struct sk_buff *skb, + struct tc_action *a, struct tcf_result *res) +{ + struct tcf_csum *p = a->priv; + int action; + u32 update_flags; + + spin_lock(&p->tcf_lock); + p->tcf_tm.lastuse = jiffies; + p->tcf_bstats.bytes += qdisc_pkt_len(skb); + p->tcf_bstats.packets++; + action = p->tcf_action; + update_flags = p->update_flags; + spin_unlock(&p->tcf_lock); + + if (unlikely(action == TC_ACT_SHOT)) + goto drop; + + switch (skb->protocol) { + case cpu_to_be16(ETH_P_IP): + if (!tcf_csum_ipv4(skb, update_flags)) + goto drop; + break; + case cpu_to_be16(ETH_P_IPV6): + if (!tcf_csum_ipv6(skb, update_flags)) + goto drop; + break; + } + + return action; + +drop: + spin_lock(&p->tcf_lock); + p->tcf_qstats.drops++; + spin_unlock(&p->tcf_lock); + return TC_ACT_SHOT; +} + +static int tcf_csum_dump(struct sk_buff *skb, + struct tc_action *a, int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_csum *p = a->priv; + struct tc_csum opt = { + .update_flags = p->update_flags, + + .index = p->tcf_index, + .action = p->tcf_action, + .refcnt = p->tcf_refcnt - ref, + .bindcnt = p->tcf_bindcnt - bind, + }; + struct tcf_t t; + + NLA_PUT(skb, TCA_CSUM_PARMS, sizeof(opt), &opt); + t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(p->tcf_tm.expires); + NLA_PUT(skb, TCA_CSUM_TM, sizeof(t), &t); + + return skb->len; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static struct tc_action_ops act_csum_ops = { + .kind = "csum", + .hinfo = &csum_hash_info, + .type = TCA_ACT_CSUM, + .capab = TCA_CAP_NONE, + .owner = THIS_MODULE, + .act = tcf_csum, + .dump = tcf_csum_dump, + .cleanup = tcf_csum_cleanup, + .lookup = tcf_hash_search, + .init = tcf_csum_init, + .walk = tcf_generic_walker +}; + +MODULE_DESCRIPTION("Checksum updating actions"); +MODULE_LICENSE("GPL"); + +static int __init csum_init_module(void) +{ + return tcf_register_action(&act_csum_ops); +} + +static void __exit csum_cleanup_module(void) +{ + tcf_unregister_action(&act_csum_ops); +} + +module_init(csum_init_module); +module_exit(csum_cleanup_module); -- cgit v1.2.3 From 739a91ef0625e0e4a40b835f4f891313c47915df Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Sat, 21 Aug 2010 06:23:15 +0000 Subject: net_sched: cls_flow: add key rxhash We can use rxhash to classify the traffic into flows. As rxhash maybe supplied by NIC or RPS, it is cheaper. Signed-off-by: Changli Gao Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/cls_flow.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/sched') diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index cd709f1294df..5b271a18bc3a 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -306,6 +306,11 @@ static u32 flow_get_vlan_tag(const struct sk_buff *skb) return tag & VLAN_VID_MASK; } +static u32 flow_get_rxhash(struct sk_buff *skb) +{ + return skb_get_rxhash(skb); +} + static u32 flow_key_get(struct sk_buff *skb, int key) { switch (key) { @@ -343,6 +348,8 @@ static u32 flow_key_get(struct sk_buff *skb, int key) return flow_get_skgid(skb); case FLOW_KEY_VLAN_TAG: return flow_get_vlan_tag(skb); + case FLOW_KEY_RXHASH: + return flow_get_rxhash(skb); default: WARN_ON(1); return 0; -- cgit v1.2.3 From 2436243a39de56f03d38c74139261cc61bea8456 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Sun, 22 Aug 2010 20:31:14 -0700 Subject: net/sched: need to include net/ip6_checksum.h for the declararion of csum_ipv6_magic. Fixes this build error on PowerPC (at least): net/sched/act_csum.c: In function 'tcf_csum_ipv6_icmp': net/sched/act_csum.c:178: error: implicit declaration of function 'csum_ipv6_magic' Signed-off-by: Stephen Rothwell Signed-off-by: David S. Miller --- net/sched/act_csum.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/sched') diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 58d7f36949da..be41f1cc10ee 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -29,6 +29,7 @@ #include #include #include +#include #include -- cgit v1.2.3 From 7abac686026ec1af38f6e766369dbfe4007949b6 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 23 Aug 2010 20:42:11 -0700 Subject: pkt_sched: Make act_csum depend upon INET. It uses ip_send_check() and stuff like that. Reported-by: Randy Dunlap Signed-off-by: David S. Miller --- net/sched/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/sched') diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 522d5a9a2825..a36270a994d7 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -520,7 +520,7 @@ config NET_ACT_SKBEDIT config NET_ACT_CSUM tristate "Checksum Updating" - depends on NET_CLS_ACT + depends on NET_CLS_ACT && INET ---help--- Say Y here to update some common checksum after some direct packet alterations. -- cgit v1.2.3 From 0eec32ff350348e635b3b8d87b989117ce045d25 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Mon, 23 Aug 2010 03:27:58 +0000 Subject: net_sched: act_csum: coding style cleanup Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- net/sched/act_csum.c | 77 ++++++++++++++++++++++++++-------------------------- 1 file changed, 38 insertions(+), 39 deletions(-) (limited to 'net/sched') diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index be41f1cc10ee..67dc7ce9b63a 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -42,9 +42,9 @@ static u32 csum_idx_gen; static DEFINE_RWLOCK(csum_lock); static struct tcf_hashinfo csum_hash_info = { - .htab = tcf_csum_ht, - .hmask = CSUM_TAB_MASK, - .lock = &csum_lock, + .htab = tcf_csum_ht, + .hmask = CSUM_TAB_MASK, + .lock = &csum_lock, }; static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { @@ -73,7 +73,8 @@ static int tcf_csum_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_check(parm->index, a, bind, &csum_hash_info); if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &csum_idx_gen, &csum_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, + &csum_idx_gen, &csum_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); p = to_tcf_csum(pc); @@ -230,8 +231,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, struct iphdr *iph, struct udphdr *udph; u16 ul; - /* Support both UDP and UDPLITE checksum algorithms, - * Don't use udph->len to get the real length without any protocol check, + /* + * Support both UDP and UDPLITE checksum algorithms, Don't use + * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use iph->tot_len, or just ipl. */ @@ -249,10 +251,8 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, struct iphdr *iph, if (udplite) { if (ul == 0) skb->csum = csum_partial(udph, ipl - ihl, 0); - else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) skb->csum = csum_partial(udph, ul, 0); - else goto ignore_obscure_skb; } else { @@ -282,8 +282,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, struct ipv6hdr *ip6h, struct udphdr *udph; u16 ul; - /* Support both UDP and UDPLITE checksum algorithms, - * Don't use udph->len to get the real length without any protocol check, + /* + * Support both UDP and UDPLITE checksum algorithms, Don't use + * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use ip6h->payload_len + sizeof(*ip6h) ... , or just ipl. */ @@ -340,32 +341,32 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) { case IPPROTO_ICMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) - if (!tcf_csum_ipv4_icmp(skb, - iph->ihl * 4, ntohs(iph->tot_len))) + if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4, + ntohs(iph->tot_len))) goto fail; break; case IPPROTO_IGMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP) - if (!tcf_csum_ipv4_igmp(skb, - iph->ihl * 4, ntohs(iph->tot_len))) + if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4, + ntohs(iph->tot_len))) goto fail; break; case IPPROTO_TCP: if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) - if (!tcf_csum_ipv4_tcp(skb, iph, - iph->ihl * 4, ntohs(iph->tot_len))) + if (!tcf_csum_ipv4_tcp(skb, iph, iph->ihl * 4, + ntohs(iph->tot_len))) goto fail; break; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) - if (!tcf_csum_ipv4_udp(skb, iph, - iph->ihl * 4, ntohs(iph->tot_len), 0)) + if (!tcf_csum_ipv4_udp(skb, iph, iph->ihl * 4, + ntohs(iph->tot_len), 0)) goto fail; break; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) - if (!tcf_csum_ipv4_udp(skb, iph, - iph->ihl * 4, ntohs(iph->tot_len), 1)) + if (!tcf_csum_ipv4_udp(skb, iph, iph->ihl * 4, + ntohs(iph->tot_len), 1)) goto fail; break; } @@ -386,7 +387,7 @@ fail: } static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, - unsigned int ixhl, unsigned int *pl) + unsigned int ixhl, unsigned int *pl) { int off, len, optlen; unsigned char *xh = (void *)ip6xh; @@ -395,8 +396,7 @@ static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, len = ixhl - off; while (len > 1) { - switch (xh[off]) - { + switch (xh[off]) { case IPV6_TLV_PAD0: optlen = 1; break; @@ -476,14 +476,14 @@ static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags) goto done; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) - if (!tcf_csum_ipv6_udp(skb, ip6h, - hl, pl + sizeof(*ip6h), 0)) + if (!tcf_csum_ipv6_udp(skb, ip6h, hl, + pl + sizeof(*ip6h), 0)) goto fail; goto done; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) - if (!tcf_csum_ipv6_udp(skb, ip6h, - hl, pl + sizeof(*ip6h), 1)) + if (!tcf_csum_ipv6_udp(skb, ip6h, hl, + pl + sizeof(*ip6h), 1)) goto fail; goto done; default: @@ -544,7 +544,6 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tcf_csum *p = a->priv; struct tc_csum opt = { .update_flags = p->update_flags, - .index = p->tcf_index, .action = p->tcf_action, .refcnt = p->tcf_refcnt - ref, @@ -566,17 +565,17 @@ nla_put_failure: } static struct tc_action_ops act_csum_ops = { - .kind = "csum", - .hinfo = &csum_hash_info, - .type = TCA_ACT_CSUM, - .capab = TCA_CAP_NONE, - .owner = THIS_MODULE, - .act = tcf_csum, - .dump = tcf_csum_dump, - .cleanup = tcf_csum_cleanup, - .lookup = tcf_hash_search, - .init = tcf_csum_init, - .walk = tcf_generic_walker + .kind = "csum", + .hinfo = &csum_hash_info, + .type = TCA_ACT_CSUM, + .capab = TCA_CAP_NONE, + .owner = THIS_MODULE, + .act = tcf_csum, + .dump = tcf_csum_dump, + .cleanup = tcf_csum_cleanup, + .lookup = tcf_hash_search, + .init = tcf_csum_init, + .walk = tcf_generic_walker }; MODULE_DESCRIPTION("Checksum updating actions"); -- cgit v1.2.3 From c2e3143e3c46ede22336316b3ff4746727c0d93a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 24 Aug 2010 14:48:10 -0700 Subject: tc: add meta match on receive hash Trivial extension to existing meta data match rules to allow matching on skb receive hash value. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/sched/em_meta.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/sched') diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 3bcac8aa333c..34da5e29ea1a 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -223,6 +223,11 @@ META_COLLECTOR(int_maclen) dst->value = skb->mac_len; } +META_COLLECTOR(int_rxhash) +{ + dst->value = skb_get_rxhash(skb); +} + /************************************************************************** * Netfilter **************************************************************************/ @@ -541,6 +546,7 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { [META_ID(SK_SENDMSG_OFF)] = META_FUNC(int_sk_sendmsg_off), [META_ID(SK_WRITE_PENDING)] = META_FUNC(int_sk_write_pend), [META_ID(VLAN_TAG)] = META_FUNC(int_vlan_tag), + [META_ID(RXHASH)] = META_FUNC(int_rxhash), } }; -- cgit v1.2.3 From bfa5ae63b823f4ffd3483a05f60a93a4a7b7d680 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Sep 2010 05:58:37 +0000 Subject: net: rename netdev rx_queue to ingress_queue There is some confusion with rx_queue name after RPS, and net drivers private rx_queue fields. I suggest to rename "struct net_device"->rx_queue to ingress_queue. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/sch_api.c | 14 +++++++------- net/sched/sch_generic.c | 8 ++++---- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 6fb3d41c0e41..b8020784d0e9 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -240,7 +240,7 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) if (q) goto out; - q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle); + q = qdisc_match_from_root(dev->ingress_queue.qdisc_sleeping, handle); out: return q; } @@ -701,7 +701,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, } for (i = 0; i < num_q; i++) { - struct netdev_queue *dev_queue = &dev->rx_queue; + struct netdev_queue *dev_queue = &dev->ingress_queue; if (!ingress) dev_queue = netdev_get_tx_queue(dev, i); @@ -979,7 +979,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -ENOENT; q = qdisc_leaf(p, clid); } else { /* ingress */ - q = dev->rx_queue.qdisc_sleeping; + q = dev->ingress_queue.qdisc_sleeping; } } else { q = dev->qdisc; @@ -1044,7 +1044,7 @@ replay: return -ENOENT; q = qdisc_leaf(p, clid); } else { /*ingress */ - q = dev->rx_queue.qdisc_sleeping; + q = dev->ingress_queue.qdisc_sleeping; } } else { q = dev->qdisc; @@ -1124,7 +1124,7 @@ create_n_graft: if (!(n->nlmsg_flags&NLM_F_CREATE)) return -ENOENT; if (clid == TC_H_INGRESS) - q = qdisc_create(dev, &dev->rx_queue, p, + q = qdisc_create(dev, &dev->ingress_queue, p, tcm->tcm_parent, tcm->tcm_parent, tca, &err); else { @@ -1304,7 +1304,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0) goto done; - dev_queue = &dev->rx_queue; + dev_queue = &dev->ingress_queue; if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0) goto done; @@ -1595,7 +1595,7 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) goto done; - dev_queue = &dev->rx_queue; + dev_queue = &dev->ingress_queue; if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) goto done; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 2aeb3a4386a1..545278a1c478 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -753,7 +753,7 @@ void dev_activate(struct net_device *dev) need_watchdog = 0; netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog); - transition_one_qdisc(dev, &dev->rx_queue, NULL); + transition_one_qdisc(dev, &dev->ingress_queue, NULL); if (need_watchdog) { dev->trans_start = jiffies; @@ -812,7 +812,7 @@ static bool some_qdisc_is_busy(struct net_device *dev) void dev_deactivate(struct net_device *dev) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); - dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc); + dev_deactivate_queue(dev, &dev->ingress_queue, &noop_qdisc); dev_watchdog_down(dev); @@ -838,7 +838,7 @@ void dev_init_scheduler(struct net_device *dev) { dev->qdisc = &noop_qdisc; netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); - dev_init_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); + dev_init_scheduler_queue(dev, &dev->ingress_queue, &noop_qdisc); setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); } @@ -861,7 +861,7 @@ static void shutdown_scheduler_queue(struct net_device *dev, void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); - shutdown_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); + shutdown_scheduler_queue(dev, &dev->ingress_queue, &noop_qdisc); qdisc_destroy(dev->qdisc); dev->qdisc = &noop_qdisc; -- cgit v1.2.3 From 24824a09e35402b8d58dcc5be803a5ad3937bdba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 2 Oct 2010 06:11:55 +0000 Subject: net: dynamic ingress_queue allocation ingress being not used very much, and net_device->ingress_queue being quite a big object (128 or 256 bytes), use a dynamic allocation if needed (tc qdisc add dev eth0 ingress ...) dev_ingress_queue(dev) helper should be used only with RTNL taken. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/sch_api.c | 42 ++++++++++++++++++++++++++++-------------- net/sched/sch_generic.c | 12 ++++++++---- 2 files changed, 36 insertions(+), 18 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b8020784d0e9..b22ca2d1cebc 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -240,7 +240,10 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) if (q) goto out; - q = qdisc_match_from_root(dev->ingress_queue.qdisc_sleeping, handle); + if (dev_ingress_queue(dev)) + q = qdisc_match_from_root( + dev_ingress_queue(dev)->qdisc_sleeping, + handle); out: return q; } @@ -690,6 +693,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, (new && new->flags & TCQ_F_INGRESS)) { num_q = 1; ingress = 1; + if (!dev_ingress_queue(dev)) + return -ENOENT; } if (dev->flags & IFF_UP) @@ -701,7 +706,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, } for (i = 0; i < num_q; i++) { - struct netdev_queue *dev_queue = &dev->ingress_queue; + struct netdev_queue *dev_queue = dev_ingress_queue(dev); if (!ingress) dev_queue = netdev_get_tx_queue(dev, i); @@ -979,7 +984,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -ENOENT; q = qdisc_leaf(p, clid); } else { /* ingress */ - q = dev->ingress_queue.qdisc_sleeping; + if (dev_ingress_queue(dev)) + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -1043,8 +1049,9 @@ replay: if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /*ingress */ - q = dev->ingress_queue.qdisc_sleeping; + } else { /* ingress */ + if (dev_ingress_queue_create(dev)) + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -1123,11 +1130,14 @@ replay: create_n_graft: if (!(n->nlmsg_flags&NLM_F_CREATE)) return -ENOENT; - if (clid == TC_H_INGRESS) - q = qdisc_create(dev, &dev->ingress_queue, p, - tcm->tcm_parent, tcm->tcm_parent, - tca, &err); - else { + if (clid == TC_H_INGRESS) { + if (dev_ingress_queue(dev)) + q = qdisc_create(dev, dev_ingress_queue(dev), p, + tcm->tcm_parent, tcm->tcm_parent, + tca, &err); + else + err = -ENOENT; + } else { struct netdev_queue *dev_queue; if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue) @@ -1304,8 +1314,10 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0) goto done; - dev_queue = &dev->ingress_queue; - if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0) + dev_queue = dev_ingress_queue(dev); + if (dev_queue && + tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, + &q_idx, s_q_idx) < 0) goto done; cont: @@ -1595,8 +1607,10 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) goto done; - dev_queue = &dev->ingress_queue; - if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) + dev_queue = dev_ingress_queue(dev); + if (dev_queue && + tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, + &t, s_t) < 0) goto done; done: diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 545278a1c478..3d57681bdb76 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -753,7 +753,8 @@ void dev_activate(struct net_device *dev) need_watchdog = 0; netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog); - transition_one_qdisc(dev, &dev->ingress_queue, NULL); + if (dev_ingress_queue(dev)) + transition_one_qdisc(dev, dev_ingress_queue(dev), NULL); if (need_watchdog) { dev->trans_start = jiffies; @@ -812,7 +813,8 @@ static bool some_qdisc_is_busy(struct net_device *dev) void dev_deactivate(struct net_device *dev) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); - dev_deactivate_queue(dev, &dev->ingress_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + dev_deactivate_queue(dev, dev_ingress_queue(dev), &noop_qdisc); dev_watchdog_down(dev); @@ -838,7 +840,8 @@ void dev_init_scheduler(struct net_device *dev) { dev->qdisc = &noop_qdisc; netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); - dev_init_scheduler_queue(dev, &dev->ingress_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); } @@ -861,7 +864,8 @@ static void shutdown_scheduler_queue(struct net_device *dev, void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); - shutdown_scheduler_queue(dev, &dev->ingress_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); qdisc_destroy(dev->qdisc); dev->qdisc = &noop_qdisc; -- cgit v1.2.3 From e18434c45765cfc4a74b5c61da9e9fbc6ddd3d5f Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 30 Sep 2010 06:17:44 +0000 Subject: net_sched: use __TCA_HTB_MAX and TCA_HTB_MAX Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- net/sched/sch_htb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 4be8d04b262d..87d944941867 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1302,14 +1302,14 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; struct qdisc_rate_table *rtab = NULL, *ctab = NULL; - struct nlattr *tb[TCA_HTB_RTAB + 1]; + struct nlattr *tb[__TCA_HTB_MAX]; struct tc_htb_opt *hopt; /* extract all subattrs from opt attr */ if (!opt) goto failure; - err = nla_parse_nested(tb, TCA_HTB_RTAB, opt, htb_policy); + err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy); if (err < 0) goto failure; -- cgit v1.2.3 From 0ed8ddf4045fcfcac36bad753dc4046118c603ec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Oct 2010 10:44:07 +0000 Subject: neigh: Protect neigh->ha[] with a seqlock Add a seqlock in struct neighbour to protect neigh->ha[], and avoid dirtying neighbour in stress situation (many different flows / dsts) Dirtying takes place because of read_lock(&n->lock) and n->used writes. Switching to a seqlock, and writing n->used only on jiffies changes permits less dirtying. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/sch_teql.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index feaabc103ce6..401af9596709 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -241,11 +241,11 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * } if (neigh_event_send(n, skb_res) == 0) { int err; + char haddr[MAX_ADDR_LEN]; - read_lock(&n->lock); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - n->ha, NULL, skb->len); - read_unlock(&n->lock); + neigh_ha_snapshot(haddr, n, dev); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), haddr, + NULL, skb->len); if (err < 0) { neigh_release(n); -- cgit v1.2.3 From 87a2e70db62fec7348c6e5545eb7b7650c33d81b Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 13 Oct 2010 16:11:22 +0200 Subject: netfilter: xtables: resolve indirect macros 2/3 Signed-off-by: Jan Engelhardt --- net/sched/act_ipt.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net/sched') diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index c7e59e6ec349..f6d464f993ef 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -39,7 +39,7 @@ static struct tcf_hashinfo ipt_hash_info = { .lock = &ipt_lock, }; -static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) +static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) { struct xt_tgchk_param par; struct xt_target *target; @@ -66,7 +66,7 @@ static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int return 0; } -static void ipt_destroy_target(struct ipt_entry_target *t) +static void ipt_destroy_target(struct xt_entry_target *t) { struct xt_tgdtor_param par = { .target = t->u.kernel.target, @@ -99,7 +99,7 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TABLE] = { .type = NLA_STRING, .len = IFNAMSIZ }, [TCA_IPT_HOOK] = { .type = NLA_U32 }, [TCA_IPT_INDEX] = { .type = NLA_U32 }, - [TCA_IPT_TARG] = { .len = sizeof(struct ipt_entry_target) }, + [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, @@ -108,7 +108,7 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; struct tcf_common *pc; - struct ipt_entry_target *td, *t; + struct xt_entry_target *td, *t; char *tname; int ret = 0, err; u32 hook = 0; @@ -126,7 +126,7 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, if (tb[TCA_IPT_TARG] == NULL) return -EINVAL; - td = (struct ipt_entry_target *)nla_data(tb[TCA_IPT_TARG]); + td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) return -EINVAL; @@ -249,7 +249,7 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int { unsigned char *b = skb_tail_pointer(skb); struct tcf_ipt *ipt = a->priv; - struct ipt_entry_target *t; + struct xt_entry_target *t; struct tcf_t tm; struct tc_cnt c; -- cgit v1.2.3 From 243bf6e29eef642de0ff62f1ebf58bc2396d6d6e Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 13 Oct 2010 16:28:00 +0200 Subject: netfilter: xtables: resolve indirect macros 3/3 --- net/sched/act_ipt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/sched') diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index f6d464f993ef..8daef9632255 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -230,7 +230,7 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, result = TC_ACT_SHOT; ipt->tcf_qstats.drops++; break; - case IPT_CONTINUE: + case XT_CONTINUE: result = TC_ACT_PIPE; break; default: -- cgit v1.2.3 From 7b5edbc4cfe2297b0915adea5aa1eafcafadbf06 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Oct 2010 19:22:34 +0000 Subject: net/sched: fix missing spinlock init Under network load, doing : tc qdisc del dev eth0 root triggers : [ 167.193087] BUG: spinlock bad magic on CPU#3, udpflood/4928 [ 167.193139] lock: c15bc324, .magic: 00000000, .owner: /-1, .owner_cpu: -1 [ 167.193193] Pid: 4928, comm: udpflood Not tainted 2.6.36-rc7-11417-g215340c-dirty #323 [ 167.193245] Call Trace: [ 167.193292] [] ? printk+0x18/0x20 [ 167.193342] [] spin_bug+0xa3/0xf0 [ 167.193389] [] do_raw_spin_lock+0x7d/0x160 [ 167.193440] [] ? __dev_xmit_skb+0x27e/0x2b0 [ 167.193496] [] ? trace_hardirqs_on+0xb/0x10 [ 167.193545] [] _raw_spin_lock+0x3a/0x40 [ 167.193593] [] ? __dev_xmit_skb+0x27e/0x2b0 [ 167.193641] [] __dev_xmit_skb+0x27e/0x2b0 commit 79640a4ca695 (add additional lock to qdisc to increase throughput) forgot to initialize noop_qdisc and noqueue_qdisc busylock Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/sched') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 3d57681bdb76..0abcc492fbf9 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -383,6 +383,7 @@ struct Qdisc noop_qdisc = { .list = LIST_HEAD_INIT(noop_qdisc.list), .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, + .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), }; EXPORT_SYMBOL(noop_qdisc); @@ -409,6 +410,7 @@ static struct Qdisc noqueue_qdisc = { .list = LIST_HEAD_INIT(noqueue_qdisc.list), .q.lock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock), .dev_queue = &noqueue_netdev_queue, + .busylock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.busylock), }; -- cgit v1.2.3 From 3511c9132f8b1e1b5634e41a3331c44b0c13be70 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Sat, 16 Oct 2010 13:04:08 +0000 Subject: net_sched: remove the unused parameter of qdisc_create_dflt() The first parameter dev isn't in use in qdisc_create_dflt(). Signed-off-by: Changli Gao Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/sch_atm.c | 5 ++--- net/sched/sch_cbq.c | 12 ++++++------ net/sched/sch_drr.c | 4 ++-- net/sched/sch_dsmark.c | 6 ++---- net/sched/sch_fifo.c | 3 +-- net/sched/sch_generic.c | 10 ++++------ net/sched/sch_hfsc.c | 8 +++----- net/sched/sch_htb.c | 8 +++----- net/sched/sch_mq.c | 2 +- net/sched/sch_multiq.c | 3 +-- net/sched/sch_netem.c | 3 +-- net/sched/sch_prio.c | 2 +- 12 files changed, 27 insertions(+), 39 deletions(-) (limited to 'net/sched') diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 6318e1136b83..282540778aa8 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -275,8 +275,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, goto err_out; } flow->filter_list = NULL; - flow->q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, classid); + flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!flow->q) flow->q = &noop_qdisc; pr_debug("atm_tc_change: qdisc %p\n", flow->q); @@ -543,7 +542,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) INIT_LIST_HEAD(&p->flows); INIT_LIST_HEAD(&p->link.list); list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + p->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (!p->link.q) p->link.q = &noop_qdisc; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 28c01ef5abc8..eb7631590865 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1379,9 +1379,9 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) q->link.sibling = &q->link; q->link.common.classid = sch->handle; q->link.qdisc = sch; - if (!(q->link.q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, - sch->handle))) + q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + sch->handle); + if (!q->link.q) q->link.q = &noop_qdisc; q->link.priority = TC_CBQ_MAXPRIO-1; @@ -1623,7 +1623,7 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct cbq_class *cl = (struct cbq_class*)arg; if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->common.classid); if (new == NULL) return -ENOBUFS; @@ -1874,8 +1874,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->R_tab = rtab; rtab = NULL; cl->refcnt = 1; - if (!(cl->q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, classid))) + cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); + if (!cl->q) cl->q = &noop_qdisc; cl->common.classid = classid; cl->tparent = parent; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index b74046a95397..aa8b5313f8cf 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -110,7 +110,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->refcnt = 1; cl->common.classid = classid; cl->quantum = quantum; - cl->qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; @@ -218,7 +218,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg, struct drr_class *cl = (struct drr_class *)arg; if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->common.classid); if (new == NULL) new = &noop_qdisc; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 63d41f86679c..1d295d62bb5c 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -61,8 +61,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, sch, p, new, old); if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (new == NULL) new = &noop_qdisc; @@ -384,8 +383,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) p->default_index = default_index; p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - p->q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, sch->handle); + p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (p->q == NULL) p->q = &noop_qdisc; diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 5948bafa8ce2..4dfecb0cba37 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -172,8 +172,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, struct Qdisc *q; int err = -ENOMEM; - q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - ops, TC_H_MAKE(sch->handle, 1)); + q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1)); if (q) { err = fifo_set_limit(q, limit); if (err < 0) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 0abcc492fbf9..5dbb3cd96e59 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -576,10 +576,8 @@ errout: return ERR_PTR(err); } -struct Qdisc * qdisc_create_dflt(struct net_device *dev, - struct netdev_queue *dev_queue, - struct Qdisc_ops *ops, - unsigned int parentid) +struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, + struct Qdisc_ops *ops, unsigned int parentid) { struct Qdisc *sch; @@ -684,7 +682,7 @@ static void attach_one_default_qdisc(struct net_device *dev, struct Qdisc *qdisc; if (dev->tx_queue_len) { - qdisc = qdisc_create_dflt(dev, dev_queue, + qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, TC_H_ROOT); if (!qdisc) { printk(KERN_INFO "%s: activation failed\n", dev->name); @@ -711,7 +709,7 @@ static void attach_default_qdiscs(struct net_device *dev) dev->qdisc = txq->qdisc_sleeping; atomic_inc(&dev->qdisc->refcnt); } else { - qdisc = qdisc_create_dflt(dev, txq, &mq_qdisc_ops, TC_H_ROOT); + qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); if (qdisc) { qdisc->ops->attach(qdisc); dev->qdisc = qdisc; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 47496098d35c..069c62b7bb36 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1088,7 +1088,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->refcnt = 1; cl->sched = q; cl->cl_parent = parent; - cl->qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; @@ -1209,8 +1209,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (cl->level > 0) return -EINVAL; if (new == NULL) { - new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->cl_common.classid); if (new == NULL) new = &noop_qdisc; @@ -1452,8 +1451,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) q->root.cl_common.classid = sch->handle; q->root.refcnt = 1; q->root.sched = q; - q->root.qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 87d944941867..01b519d6c52d 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1121,8 +1121,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (cl->level) return -EINVAL; if (new == NULL && - (new = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + (new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->common.classid)) == NULL) return -ENOBUFS; @@ -1247,8 +1246,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) return -EBUSY; if (!cl->level && htb_parent_last_child(cl)) { - new_q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &pfifo_qdisc_ops, + new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->parent->common.classid); last_child = 1; } @@ -1377,7 +1375,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) so that can't be used inside of sch_tree_lock -- thanks to Karlis Peisenieks */ - new_q = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); sch_tree_lock(sch); if (parent && !parent->level) { diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index fe91e50f9d98..ecc302f4d2a1 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -56,7 +56,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { dev_queue = netdev_get_tx_queue(dev, ntx); - qdisc = qdisc_create_dflt(dev, dev_queue, &pfifo_fast_ops, + qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(ntx + 1))); if (qdisc == NULL) diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 6ae251279fc2..32690deab5d0 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -227,8 +227,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; - child = qdisc_create_dflt(qdisc_dev(sch), - sch->dev_queue, + child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1)); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 4714ff162bbd..e5593c083a78 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -538,8 +538,7 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); - q->qdisc = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, - &tfifo_qdisc_ops, + q->qdisc = qdisc_create_dflt(sch->dev_queue, &tfifo_qdisc_ops, TC_H_MAKE(sch->handle, 1)); if (!q->qdisc) { pr_debug("netem: qdisc create failed\n"); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 0748fb1e3a49..b1c95bce33ce 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -200,7 +200,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) for (i=0; ibands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; - child = qdisc_create_dflt(qdisc_dev(sch), sch->dev_queue, + child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1)); if (child) { -- cgit v1.2.3