aboutsummaryrefslogtreecommitdiffstats
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/Kconfig39
-rw-r--r--net/sched/Makefile3
-rw-r--r--net/sched/act_mirred.c2
-rw-r--r--net/sched/act_pedit.c1
-rw-r--r--net/sched/cls_api.c3
-rw-r--r--net/sched/cls_flow.c2
-rw-r--r--net/sched/cls_flower.c3
-rw-r--r--net/sched/cls_fw.c11
-rw-r--r--net/sched/cls_route.c1
-rw-r--r--net/sched/cls_rsvp.c28
-rw-r--r--net/sched/cls_rsvp.h775
-rw-r--r--net/sched/cls_rsvp6.c28
-rw-r--r--net/sched/cls_tcindex.c698
-rw-r--r--net/sched/cls_u32.c77
-rw-r--r--net/sched/em_text.c4
-rw-r--r--net/sched/ematch.c2
-rw-r--r--net/sched/sch_api.c82
-rw-r--r--net/sched/sch_atm.c5
-rw-r--r--net/sched/sch_cake.c2
-rw-r--r--net/sched/sch_cbq.c6
-rw-r--r--net/sched/sch_fq_codel.c2
-rw-r--r--net/sched/sch_hfsc.c14
-rw-r--r--net/sched/sch_ingress.c16
-rw-r--r--net/sched/sch_mqprio.c144
-rw-r--r--net/sched/sch_netem.c61
-rw-r--r--net/sched/sch_plug.c2
-rw-r--r--net/sched/sch_qfq.c42
-rw-r--r--net/sched/sch_sfq.c2
28 files changed, 334 insertions, 1721 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index e95741388311..7698a8974a47 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -458,17 +458,6 @@ config NET_CLS_BASIC
To compile this code as a module, choose M here: the
module will be called cls_basic.
-config NET_CLS_TCINDEX
- tristate "Traffic-Control Index (TCINDEX)"
- select NET_CLS
- ---help---
- Say Y here if you want to be able to classify packets based on
- traffic control indices. You will want this feature if you want
- to implement Differentiated Services together with DSMARK.
-
- To compile this code as a module, choose M here: the
- module will be called cls_tcindex.
-
config NET_CLS_ROUTE4
tristate "Routing decision (ROUTE)"
depends on INET
@@ -514,34 +503,6 @@ config CLS_U32_MARK
---help---
Say Y here to be able to use netfilter marks as u32 key.
-config NET_CLS_RSVP
- tristate "IPv4 Resource Reservation Protocol (RSVP)"
- select NET_CLS
- ---help---
- The Resource Reservation Protocol (RSVP) permits end systems to
- request a minimum and maximum data flow rate for a connection; this
- is important for real time data such as streaming sound or video.
-
- Say Y here if you want to be able to classify outgoing packets based
- on their RSVP requests.
-
- To compile this code as a module, choose M here: the
- module will be called cls_rsvp.
-
-config NET_CLS_RSVP6
- tristate "IPv6 Resource Reservation Protocol (RSVP6)"
- select NET_CLS
- ---help---
- The Resource Reservation Protocol (RSVP) permits end systems to
- request a minimum and maximum data flow rate for a connection; this
- is important for real time data such as streaming sound or video.
-
- Say Y here if you want to be able to classify outgoing packets based
- on their RSVP requests and you are using the IPv6 protocol.
-
- To compile this code as a module, choose M here: the
- module will be called cls_rsvp6.
-
config NET_CLS_FLOW
tristate "Flow classifier"
select NET_CLS
diff --git a/net/sched/Makefile b/net/sched/Makefile
index f0403f49edcb..3139c32e1947 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -61,9 +61,6 @@ obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o
obj-$(CONFIG_NET_CLS_U32) += cls_u32.o
obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o
obj-$(CONFIG_NET_CLS_FW) += cls_fw.o
-obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o
-obj-$(CONFIG_NET_CLS_TCINDEX) += cls_tcindex.o
-obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o
obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o
obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o
obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a30c17a28281..9aad86e4a0fb 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -220,7 +220,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
goto out;
}
- if (unlikely(!(dev->flags & IFF_UP))) {
+ if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) {
net_notice_ratelimited("tc mirred to Houston: device %s is down\n",
dev->name);
goto out;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index aeb8f84cbd9e..255d4ecf6252 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -29,6 +29,7 @@ static struct tc_action_ops act_pedit_ops;
static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
[TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) },
+ [TCA_PEDIT_PARMS_EX] = { .len = sizeof(struct tc_pedit) },
[TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED },
};
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 435911dc9f16..6166bbad9753 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -31,8 +31,6 @@
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
-extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
-
/* The list of all installed classifier types */
static LIST_HEAD(tcf_proto_base);
@@ -1840,6 +1838,7 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
return PTR_ERR(ops);
if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier");
+ module_put(ops->owner);
return -EOPNOTSUPP;
}
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 55bf75cb1f16..164049d20f4d 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -229,7 +229,7 @@ static u32 flow_get_skgid(const struct sk_buff *skb)
static u32 flow_get_vlan_tag(const struct sk_buff *skb)
{
- u16 uninitialized_var(tag);
+ u16 tag;
if (vlan_get_tag(skb, &tag) < 0)
return 0;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 6163648145c1..7ffa28a98d74 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -640,6 +640,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
if (option_len > sizeof(struct geneve_opt))
data_len = option_len - sizeof(struct geneve_opt);
+ if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4)
+ return -ERANGE;
+
opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len];
memset(opt, 0xff, option_len);
opt->length = data_len / 4;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index cb2c62605fc7..f15089c24a32 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -221,11 +221,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
if (err < 0)
return err;
- if (tb[TCA_FW_CLASSID]) {
- f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]);
- tcf_bind_filter(tp, &f->res, base);
- }
-
#ifdef CONFIG_NET_CLS_IND
if (tb[TCA_FW_INDEV]) {
int ret;
@@ -244,6 +239,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
} else if (head->mask != 0xFFFFFFFF)
return err;
+ if (tb[TCA_FW_CLASSID]) {
+ f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]);
+ tcf_bind_filter(tp, &f->res, base);
+ }
+
return 0;
}
@@ -277,7 +277,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
return -ENOBUFS;
fnew->id = f->id;
- fnew->res = f->res;
#ifdef CONFIG_NET_CLS_IND
fnew->ifindex = f->ifindex;
#endif /* CONFIG_NET_CLS_IND */
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 4c7fa1cfd8e3..a924292623ec 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -513,7 +513,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
if (fold) {
f->id = fold->id;
f->iif = fold->iif;
- f->res = fold->res;
f->handle = fold->handle;
f->tp = fold->tp;
diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c
deleted file mode 100644
index cbb5e0d600f3..000000000000
--- a/net/sched/cls_rsvp.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4.
- *
- * 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.
- *
- * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/skbuff.h>
-#include <net/ip.h>
-#include <net/netlink.h>
-#include <net/act_api.h>
-#include <net/pkt_cls.h>
-
-#define RSVP_DST_LEN 1
-#define RSVP_ID "rsvp"
-#define RSVP_OPS cls_rsvp_ops
-
-#include "cls_rsvp.h"
-MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
deleted file mode 100644
index eb1dd2afc5a1..000000000000
--- a/net/sched/cls_rsvp.h
+++ /dev/null
@@ -1,775 +0,0 @@
-/*
- * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers.
- *
- * 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.
- *
- * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- */
-
-/*
- Comparing to general packet classification problem,
- RSVP needs only sevaral relatively simple rules:
-
- * (dst, protocol) are always specified,
- so that we are able to hash them.
- * src may be exact, or may be wildcard, so that
- we can keep a hash table plus one wildcard entry.
- * source port (or flow label) is important only if src is given.
-
- IMPLEMENTATION.
-
- We use a two level hash table: The top level is keyed by
- destination address and protocol ID, every bucket contains a list
- of "rsvp sessions", identified by destination address, protocol and
- DPI(="Destination Port ID"): triple (key, mask, offset).
-
- Every bucket has a smaller hash table keyed by source address
- (cf. RSVP flowspec) and one wildcard entry for wildcard reservations.
- Every bucket is again a list of "RSVP flows", selected by
- source address and SPI(="Source Port ID" here rather than
- "security parameter index"): triple (key, mask, offset).
-
-
- NOTE 1. All the packets with IPv6 extension headers (but AH and ESP)
- and all fragmented packets go to the best-effort traffic class.
-
-
- NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires
- only one "Generalized Port Identifier". So that for classic
- ah, esp (and udp,tcp) both *pi should coincide or one of them
- should be wildcard.
-
- At first sight, this redundancy is just a waste of CPU
- resources. But DPI and SPI add the possibility to assign different
- priorities to GPIs. Look also at note 4 about tunnels below.
-
-
- NOTE 3. One complication is the case of tunneled packets.
- We implement it as following: if the first lookup
- matches a special session with "tunnelhdr" value not zero,
- flowid doesn't contain the true flow ID, but the tunnel ID (1...255).
- In this case, we pull tunnelhdr bytes and restart lookup
- with tunnel ID added to the list of keys. Simple and stupid 8)8)
- It's enough for PIMREG and IPIP.
-
-
- NOTE 4. Two GPIs make it possible to parse even GRE packets.
- F.e. DPI can select ETH_P_IP (and necessary flags to make
- tunnelhdr correct) in GRE protocol field and SPI matches
- GRE key. Is it not nice? 8)8)
-
-
- Well, as result, despite its simplicity, we get a pretty
- powerful classification engine. */
-
-
-struct rsvp_head {
- u32 tmap[256/32];
- u32 hgenerator;
- u8 tgenerator;
- struct rsvp_session __rcu *ht[256];
- struct rcu_head rcu;
-};
-
-struct rsvp_session {
- struct rsvp_session __rcu *next;
- __be32 dst[RSVP_DST_LEN];
- struct tc_rsvp_gpi dpi;
- u8 protocol;
- u8 tunnelid;
- /* 16 (src,sport) hash slots, and one wildcard source slot */
- struct rsvp_filter __rcu *ht[16 + 1];
- struct rcu_head rcu;
-};
-
-
-struct rsvp_filter {
- struct rsvp_filter __rcu *next;
- __be32 src[RSVP_DST_LEN];
- struct tc_rsvp_gpi spi;
- u8 tunnelhdr;
-
- struct tcf_result res;
- struct tcf_exts exts;
-
- u32 handle;
- struct rsvp_session *sess;
- struct rcu_work rwork;
-};
-
-static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid)
-{
- unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1];
-
- h ^= h>>16;
- h ^= h>>8;
- return (h ^ protocol ^ tunnelid) & 0xFF;
-}
-
-static inline unsigned int hash_src(__be32 *src)
-{
- unsigned int h = (__force __u32)src[RSVP_DST_LEN-1];
-
- h ^= h>>16;
- h ^= h>>8;
- h ^= h>>4;
- return h & 0xF;
-}
-
-#define RSVP_APPLY_RESULT() \
-{ \
- int r = tcf_exts_exec(skb, &f->exts, res); \
- if (r < 0) \
- continue; \
- else if (r > 0) \
- return r; \
-}
-
-static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp,
- struct tcf_result *res)
-{
- struct rsvp_head *head = rcu_dereference_bh(tp->root);
- struct rsvp_session *s;
- struct rsvp_filter *f;
- unsigned int h1, h2;
- __be32 *dst, *src;
- u8 protocol;
- u8 tunnelid = 0;
- u8 *xprt;
-#if RSVP_DST_LEN == 4
- struct ipv6hdr *nhptr;
-
- if (!pskb_network_may_pull(skb, sizeof(*nhptr)))
- return -1;
- nhptr = ipv6_hdr(skb);
-#else
- struct iphdr *nhptr;
-
- if (!pskb_network_may_pull(skb, sizeof(*nhptr)))
- return -1;
- nhptr = ip_hdr(skb);
-#endif
-restart:
-
-#if RSVP_DST_LEN == 4
- src = &nhptr->saddr.s6_addr32[0];
- dst = &nhptr->daddr.s6_addr32[0];
- protocol = nhptr->nexthdr;
- xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr);
-#else
- src = &nhptr->saddr;
- dst = &nhptr->daddr;
- protocol = nhptr->protocol;
- xprt = ((u8 *)nhptr) + (nhptr->ihl<<2);
- if (ip_is_fragment(nhptr))
- return -1;
-#endif
-
- h1 = hash_dst(dst, protocol, tunnelid);
- h2 = hash_src(src);
-
- for (s = rcu_dereference_bh(head->ht[h1]); s;
- s = rcu_dereference_bh(s->next)) {
- if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] &&
- protocol == s->protocol &&
- !(s->dpi.mask &
- (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) &&
-#if RSVP_DST_LEN == 4
- dst[0] == s->dst[0] &&
- dst[1] == s->dst[1] &&
- dst[2] == s->dst[2] &&
-#endif
- tunnelid == s->tunnelid) {
-
- for (f = rcu_dereference_bh(s->ht[h2]); f;
- f = rcu_dereference_bh(f->next)) {
- if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] &&
- !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key))
-#if RSVP_DST_LEN == 4
- &&
- src[0] == f->src[0] &&
- src[1] == f->src[1] &&
- src[2] == f->src[2]
-#endif
- ) {
- *res = f->res;
- RSVP_APPLY_RESULT();
-
-matched:
- if (f->tunnelhdr == 0)
- return 0;
-
- tunnelid = f->res.classid;
- nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr));
- goto restart;
- }
- }
-
- /* And wildcard bucket... */
- for (f = rcu_dereference_bh(s->ht[16]); f;
- f = rcu_dereference_bh(f->next)) {
- *res = f->res;
- RSVP_APPLY_RESULT();
- goto matched;
- }
- return -1;
- }
- }
- return -1;
-}
-
-static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- struct rsvp_session *s;
- struct rsvp_filter __rcu **ins;
- struct rsvp_filter *pins;
- unsigned int h1 = h & 0xFF;
- unsigned int h2 = (h >> 8) & 0xFF;
-
- for (s = rtnl_dereference(head->ht[h1]); s;
- s = rtnl_dereference(s->next)) {
- for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ;
- ins = &pins->next, pins = rtnl_dereference(*ins)) {
- if (pins->handle == h) {
- RCU_INIT_POINTER(n->next, pins->next);
- rcu_assign_pointer(*ins, n);
- return;
- }
- }
- }
-
- /* Something went wrong if we are trying to replace a non-existant
- * node. Mind as well halt instead of silently failing.
- */
- BUG_ON(1);
-}
-
-static void *rsvp_get(struct tcf_proto *tp, u32 handle)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- struct rsvp_session *s;
- struct rsvp_filter *f;
- unsigned int h1 = handle & 0xFF;
- unsigned int h2 = (handle >> 8) & 0xFF;
-
- if (h2 > 16)
- return NULL;
-
- for (s = rtnl_dereference(head->ht[h1]); s;
- s = rtnl_dereference(s->next)) {
- for (f = rtnl_dereference(s->ht[h2]); f;
- f = rtnl_dereference(f->next)) {
- if (f->handle == handle)
- return f;
- }
- }
- return NULL;
-}
-
-static int rsvp_init(struct tcf_proto *tp)
-{
- struct rsvp_head *data;
-
- data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL);
- if (data) {
- rcu_assign_pointer(tp->root, data);
- return 0;
- }
- return -ENOBUFS;
-}
-
-static void __rsvp_delete_filter(struct rsvp_filter *f)
-{
- tcf_exts_destroy(&f->exts);
- tcf_exts_put_net(&f->exts);
- kfree(f);
-}
-
-static void rsvp_delete_filter_work(struct work_struct *work)
-{
- struct rsvp_filter *f = container_of(to_rcu_work(work),
- struct rsvp_filter,
- rwork);
- rtnl_lock();
- __rsvp_delete_filter(f);
- rtnl_unlock();
-}
-
-static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
-{
- tcf_unbind_filter(tp, &f->res);
- /* all classifiers are required to call tcf_exts_destroy() after rcu
- * grace period, since converted-to-rcu actions are relying on that
- * in cleanup() callback
- */
- if (tcf_exts_get_net(&f->exts))
- tcf_queue_work(&f->rwork, rsvp_delete_filter_work);
- else
- __rsvp_delete_filter(f);
-}
-
-static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
-{
- struct rsvp_head *data = rtnl_dereference(tp->root);
- int h1, h2;
-
- if (data == NULL)
- return;
-
- for (h1 = 0; h1 < 256; h1++) {
- struct rsvp_session *s;
-
- while ((s = rtnl_dereference(data->ht[h1])) != NULL) {
- RCU_INIT_POINTER(data->ht[h1], s->next);
-
- for (h2 = 0; h2 <= 16; h2++) {
- struct rsvp_filter *f;
-
- while ((f = rtnl_dereference(s->ht[h2])) != NULL) {
- rcu_assign_pointer(s->ht[h2], f->next);
- rsvp_delete_filter(tp, f);
- }
- }
- kfree_rcu(s, rcu);
- }
- }
- kfree_rcu(data, rcu);
-}
-
-static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- struct rsvp_filter *nfp, *f = arg;
- struct rsvp_filter __rcu **fp;
- unsigned int h = f->handle;
- struct rsvp_session __rcu **sp;
- struct rsvp_session *nsp, *s = f->sess;
- int i, h1;
-
- fp = &s->ht[(h >> 8) & 0xFF];
- for (nfp = rtnl_dereference(*fp); nfp;
- fp = &nfp->next, nfp = rtnl_dereference(*fp)) {
- if (nfp == f) {
- RCU_INIT_POINTER(*fp, f->next);
- rsvp_delete_filter(tp, f);
-
- /* Strip tree */
-
- for (i = 0; i <= 16; i++)
- if (s->ht[i])
- goto out;
-
- /* OK, session has no flows */
- sp = &head->ht[h & 0xFF];
- for (nsp = rtnl_dereference(*sp); nsp;
- sp = &nsp->next, nsp = rtnl_dereference(*sp)) {
- if (nsp == s) {
- RCU_INIT_POINTER(*sp, s->next);
- kfree_rcu(s, rcu);
- goto out;
- }
- }
-
- break;
- }
- }
-
-out:
- *last = true;
- for (h1 = 0; h1 < 256; h1++) {
- if (rcu_access_pointer(head->ht[h1])) {
- *last = false;
- break;
- }
- }
-
- return 0;
-}
-
-static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt)
-{
- struct rsvp_head *data = rtnl_dereference(tp->root);
- int i = 0xFFFF;
-
- while (i-- > 0) {
- u32 h;
-
- if ((data->hgenerator += 0x10000) == 0)
- data->hgenerator = 0x10000;
- h = data->hgenerator|salt;
- if (!rsvp_get(tp, h))
- return h;
- }
- return 0;
-}
-
-static int tunnel_bts(struct rsvp_head *data)
-{
- int n = data->tgenerator >> 5;
- u32 b = 1 << (data->tgenerator & 0x1F);
-
- if (data->tmap[n] & b)
- return 0;
- data->tmap[n] |= b;
- return 1;
-}
-
-static void tunnel_recycle(struct rsvp_head *data)
-{
- struct rsvp_session __rcu **sht = data->ht;
- u32 tmap[256/32];
- int h1, h2;
-
- memset(tmap, 0, sizeof(tmap));
-
- for (h1 = 0; h1 < 256; h1++) {
- struct rsvp_session *s;
- for (s = rtnl_dereference(sht[h1]); s;
- s = rtnl_dereference(s->next)) {
- for (h2 = 0; h2 <= 16; h2++) {
- struct rsvp_filter *f;
-
- for (f = rtnl_dereference(s->ht[h2]); f;
- f = rtnl_dereference(f->next)) {
- if (f->tunnelhdr == 0)
- continue;
- data->tgenerator = f->res.classid;
- tunnel_bts(data);
- }
- }
- }
- }
-
- memcpy(data->tmap, tmap, sizeof(tmap));
-}
-
-static u32 gen_tunnel(struct rsvp_head *data)
-{
- int i, k;
-
- for (k = 0; k < 2; k++) {
- for (i = 255; i > 0; i--) {
- if (++data->tgenerator == 0)
- data->tgenerator = 1;
- if (tunnel_bts(data))
- return data->tgenerator;
- }
- tunnel_recycle(data);
- }
- return 0;
-}
-
-static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = {
- [TCA_RSVP_CLASSID] = { .type = NLA_U32 },
- [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) },
- [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) },
- [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) },
-};
-
-static int rsvp_change(struct net *net, struct sk_buff *in_skb,
- struct tcf_proto *tp, unsigned long base,
- u32 handle,
- struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
-{
- struct rsvp_head *data = rtnl_dereference(tp->root);
- struct rsvp_filter *f, *nfp;
- struct rsvp_filter __rcu **fp;
- struct rsvp_session *nsp, *s;
- struct rsvp_session __rcu **sp;
- struct tc_rsvp_pinfo *pinfo = NULL;
- struct nlattr *opt = tca[TCA_OPTIONS];
- struct nlattr *tb[TCA_RSVP_MAX + 1];
- struct tcf_exts e;
- unsigned int h1, h2;
- __be32 *dst;
- int err;
-
- if (opt == NULL)
- return handle ? -EINVAL : 0;
-
- err = nla_parse_nested(tb, TCA_RSVP_MAX, opt, rsvp_policy, NULL);
- if (err < 0)
- return err;
-
- err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE);
- if (err < 0)
- return err;
- err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, extack);
- if (err < 0)
- goto errout2;
-
- f = *arg;
- if (f) {
- /* Node exists: adjust only classid */
- struct rsvp_filter *n;
-
- if (f->handle != handle && handle)
- goto errout2;
-
- n = kmemdup(f, sizeof(*f), GFP_KERNEL);
- if (!n) {
- err = -ENOMEM;
- goto errout2;
- }
-
- err = tcf_exts_init(&n->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE);
- if (err < 0) {
- kfree(n);
- goto errout2;
- }
-
- if (tb[TCA_RSVP_CLASSID]) {
- n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]);
- tcf_bind_filter(tp, &n->res, base);
- }
-
- tcf_exts_change(&n->exts, &e);
- rsvp_replace(tp, n, handle);
- return 0;
- }
-
- /* Now more serious part... */
- err = -EINVAL;
- if (handle)
- goto errout2;
- if (tb[TCA_RSVP_DST] == NULL)
- goto errout2;
-
- err = -ENOBUFS;
- f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL);
- if (f == NULL)
- goto errout2;
-
- err = tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE);
- if (err < 0)
- goto errout;
- h2 = 16;
- if (tb[TCA_RSVP_SRC]) {
- memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src));
- h2 = hash_src(f->src);
- }
- if (tb[TCA_RSVP_PINFO]) {
- pinfo = nla_data(tb[TCA_RSVP_PINFO]);
- f->spi = pinfo->spi;
- f->tunnelhdr = pinfo->tunnelhdr;
- }
- if (tb[TCA_RSVP_CLASSID])
- f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]);
-
- dst = nla_data(tb[TCA_RSVP_DST]);
- h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0);
-
- err = -ENOMEM;
- if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0)
- goto errout;
-
- if (f->tunnelhdr) {
- err = -EINVAL;
- if (f->res.classid > 255)
- goto errout;
-
- err = -ENOMEM;
- if (f->res.classid == 0 &&
- (f->res.classid = gen_tunnel(data)) == 0)
- goto errout;
- }
-
- for (sp = &data->ht[h1];
- (s = rtnl_dereference(*sp)) != NULL;
- sp = &s->next) {
- if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] &&
- pinfo && pinfo->protocol == s->protocol &&
- memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 &&
-#if RSVP_DST_LEN == 4
- dst[0] == s->dst[0] &&
- dst[1] == s->dst[1] &&
- dst[2] == s->dst[2] &&
-#endif
- pinfo->tunnelid == s->tunnelid) {
-
-insert:
- /* OK, we found appropriate session */
-
- fp = &s->ht[h2];
-
- f->sess = s;
- if (f->tunnelhdr == 0)
- tcf_bind_filter(tp, &f->res, base);
-
- tcf_exts_change(&f->exts, &e);
-
- fp = &s->ht[h2];
- for (nfp = rtnl_dereference(*fp); nfp;
- fp = &nfp->next, nfp = rtnl_dereference(*fp)) {
- __u32 mask = nfp->spi.mask & f->spi.mask;
-
- if (mask != f->spi.mask)
- break;
- }
- RCU_INIT_POINTER(f->next, nfp);
- rcu_assign_pointer(*fp, f);
-
- *arg = f;
- return 0;
- }
- }
-
- /* No session found. Create new one. */
-
- err = -ENOBUFS;
- s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL);
- if (s == NULL)
- goto errout;
- memcpy(s->dst, dst, sizeof(s->dst));
-
- if (pinfo) {
- s->dpi = pinfo->dpi;
- s->protocol = pinfo->protocol;
- s->tunnelid = pinfo->tunnelid;
- }
- sp = &data->ht[h1];
- for (nsp = rtnl_dereference(*sp); nsp;
- sp = &nsp->next, nsp = rtnl_dereference(*sp)) {
- if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask)
- break;
- }
- RCU_INIT_POINTER(s->next, nsp);
- rcu_assign_pointer(*sp, s);
-
- goto insert;
-
-errout:
- tcf_exts_destroy(&f->exts);
- kfree(f);
-errout2:
- tcf_exts_destroy(&e);
- return err;
-}
-
-static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- unsigned int h, h1;
-
- if (arg->stop)
- return;
-
- for (h = 0; h < 256; h++) {
- struct rsvp_session *s;
-
- for (s = rtnl_dereference(head->ht[h]); s;
- s = rtnl_dereference(s->next)) {
- for (h1 = 0; h1 <= 16; h1++) {
- struct rsvp_filter *f;
-
- for (f = rtnl_dereference(s->ht[h1]); f;
- f = rtnl_dereference(f->next)) {
- if (arg->count < arg->skip) {
- arg->count++;
- continue;
- }
- if (arg->fn(tp, f, arg) < 0) {
- arg->stop = 1;
- return;
- }
- arg->count++;
- }
- }
- }
- }
-}
-
-static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
-{
- struct rsvp_filter *f = fh;
- struct rsvp_session *s;
- struct nlattr *nest;
- struct tc_rsvp_pinfo pinfo;
-
- if (f == NULL)
- return skb->len;
- s = f->sess;
-
- t->tcm_handle = f->handle;
-
- nest = nla_nest_start(skb, TCA_OPTIONS);
- if (nest == NULL)
- goto nla_put_failure;
-
- if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst))
- goto nla_put_failure;
- pinfo.dpi = s->dpi;
- pinfo.spi = f->spi;
- pinfo.protocol = s->protocol;
- pinfo.tunnelid = s->tunnelid;
- pinfo.tunnelhdr = f->tunnelhdr;
- pinfo.pad = 0;
- if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo))
- goto nla_put_failure;
- if (f->res.classid &&
- nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid))
- goto nla_put_failure;
- if (((f->handle >> 8) & 0xFF) != 16 &&
- nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src))
- goto nla_put_failure;
-
- if (tcf_exts_dump(skb, &f->exts) < 0)
- goto nla_put_failure;
-
- nla_nest_end(skb, nest);
-
- if (tcf_exts_dump_stats(skb, &f->exts) < 0)
- goto nla_put_failure;
- return skb->len;
-
-nla_put_failure:
- nla_nest_cancel(skb, nest);
- return -1;
-}
-
-static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
- unsigned long base)
-{
- struct rsvp_filter *f = fh;
-
- if (f && f->res.classid == classid) {
- if (cl)
- __tcf_bind_filter(q, &f->res, base);
- else
- __tcf_unbind_filter(q, &f->res);
- }
-}
-
-static struct tcf_proto_ops RSVP_OPS __read_mostly = {
- .kind = RSVP_ID,
- .classify = rsvp_classify,
- .init = rsvp_init,
- .destroy = rsvp_destroy,
- .get = rsvp_get,
- .change = rsvp_change,
- .delete = rsvp_delete,
- .walk = rsvp_walk,
- .dump = rsvp_dump,
- .bind_class = rsvp_bind_class,
- .owner = THIS_MODULE,
-};
-
-static int __init init_rsvp(void)
-{
- return register_tcf_proto_ops(&RSVP_OPS);
-}
-
-static void __exit exit_rsvp(void)
-{
- unregister_tcf_proto_ops(&RSVP_OPS);
-}
-
-module_init(init_rsvp)
-module_exit(exit_rsvp)
diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c
deleted file mode 100644
index dd08aea2aee5..000000000000
--- a/net/sched/cls_rsvp6.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6.
- *
- * 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.
- *
- * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/ipv6.h>
-#include <linux/skbuff.h>
-#include <net/act_api.h>
-#include <net/pkt_cls.h>
-#include <net/netlink.h>
-
-#define RSVP_DST_LEN 4
-#define RSVP_ID "rsvp6"
-#define RSVP_OPS cls_rsvp6_ops
-
-#include "cls_rsvp.h"
-MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
deleted file mode 100644
index 4070197f9543..000000000000
--- a/net/sched/cls_tcindex.c
+++ /dev/null
@@ -1,698 +0,0 @@
-/*
- * net/sched/cls_tcindex.c Packet classifier for skb->tc_index
- *
- * Written 1998,1999 by Werner Almesberger, EPFL ICA
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/skbuff.h>
-#include <linux/errno.h>
-#include <linux/slab.h>
-#include <net/act_api.h>
-#include <net/netlink.h>
-#include <net/pkt_cls.h>
-#include <net/sch_generic.h>
-
-/*
- * Passing parameters to the root seems to be done more awkwardly than really
- * necessary. At least, u32 doesn't seem to use such dirty hacks. To be
- * verified. FIXME.
- */
-
-#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */
-#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */
-
-
-struct tcindex_filter_result {
- struct tcf_exts exts;
- struct tcf_result res;
- struct rcu_work rwork;
-};
-
-struct tcindex_filter {
- u16 key;
- struct tcindex_filter_result result;
- struct tcindex_filter __rcu *next;
- struct rcu_work rwork;
-};
-
-
-struct tcindex_data {
- struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */
- struct tcindex_filter __rcu **h; /* imperfect hash; */
- struct tcf_proto *tp;
- u16 mask; /* AND key with mask */
- u32 shift; /* shift ANDed key to the right */
- u32 hash; /* hash table size; 0 if undefined */
- u32 alloc_hash; /* allocated size */
- u32 fall_through; /* 0: only classify if explicit match */
- struct rcu_work rwork;
-};
-
-static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
-{
- return tcf_exts_has_actions(&r->exts) || r->res.classid;
-}
-
-static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
- u16 key)
-{
- if (p->perfect) {
- struct tcindex_filter_result *f = p->perfect + key;
-
- return tcindex_filter_is_set(f) ? f : NULL;
- } else if (p->h) {
- struct tcindex_filter __rcu **fp;
- struct tcindex_filter *f;
-
- fp = &p->h[key % p->hash];
- for (f = rcu_dereference_bh_rtnl(*fp);
- f;
- fp = &f->next, f = rcu_dereference_bh_rtnl(*fp))
- if (f->key == key)
- return &f->result;
- }
-
- return NULL;
-}
-
-
-static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
- struct tcf_result *res)
-{
- struct tcindex_data *p = rcu_dereference_bh(tp->root);
- struct tcindex_filter_result *f;
- int key = (skb->tc_index & p->mask) >> p->shift;
-
- pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n",
- skb, tp, res, p);
-
- f = tcindex_lookup(p, key);
- if (!f) {
- struct Qdisc *q = tcf_block_q(tp->chain->block);
-
- if (!p->fall_through)
- return -1;
- res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key);
- res->class = 0;
- pr_debug("alg 0x%x\n", res->classid);
- return 0;
- }
- *res = f->res;
- pr_debug("map 0x%x\n", res->classid);
-
- return tcf_exts_exec(skb, &f->exts, res);
-}
-
-
-static void *tcindex_get(struct tcf_proto *tp, u32 handle)
-{
- struct tcindex_data *p = rtnl_dereference(tp->root);
- struct tcindex_filter_result *r;
-
- pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle);
- if (p->perfect && handle >= p->alloc_hash)
- return NULL;
- r = tcindex_lookup(p, handle);
- return r && tcindex_filter_is_set(r) ? r : NULL;
-}
-
-static int tcindex_init(struct tcf_proto *tp)
-{
- struct tcindex_data *p;
-
- pr_debug("tcindex_init(tp %p)\n", tp);
- p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL);
- if (!p)
- return -ENOMEM;
-
- p->mask = 0xffff;
- p->hash = DEFAULT_HASH_SIZE;
- p->fall_through = 1;
-
- rcu_assign_pointer(tp->root, p);
- return 0;
-}
-
-static void __tcindex_destroy_rexts(struct tcindex_filter_result *r)
-{
- tcf_exts_destroy(&r->exts);
- tcf_exts_put_net(&r->exts);
-}
-
-static void tcindex_destroy_rexts_work(struct work_struct *work)
-{
- struct tcindex_filter_result *r;
-
- r = container_of(to_rcu_work(work),
- struct tcindex_filter_result,
- rwork);
- rtnl_lock();
- __tcindex_destroy_rexts(r);
- rtnl_unlock();
-}
-
-static void __tcindex_destroy_fexts(struct tcindex_filter *f)
-{
- tcf_exts_destroy(&f->result.exts);
- tcf_exts_put_net(&f->result.exts);
- kfree(f);
-}
-
-static void tcindex_destroy_fexts_work(struct work_struct *work)
-{
- struct tcindex_filter *f = container_of(to_rcu_work(work),
- struct tcindex_filter,
- rwork);
-
- rtnl_lock();
- __tcindex_destroy_fexts(f);
- rtnl_unlock();
-}
-
-static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
-{
- struct tcindex_data *p = rtnl_dereference(tp->root);
- struct tcindex_filter_result *r = arg;
- struct tcindex_filter __rcu **walk;
- struct tcindex_filter *f = NULL;
-
- pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p);
- if (p->perfect) {
- if (!r->res.class)
- return -ENOENT;
- } else {
- int i;
-
- for (i = 0; i < p->hash; i++) {
- walk = p->h + i;
- for (f = rtnl_dereference(*walk); f;
- walk = &f->next, f = rtnl_dereference(*walk)) {
- if (&f->result == r)
- goto found;
- }
- }
- return -ENOENT;
-
-found:
- rcu_assign_pointer(*walk, rtnl_dereference(f->next));
- }
- tcf_unbind_filter(tp, &r->res);
- /* all classifiers are required to call tcf_exts_destroy() after rcu
- * grace period, since converted-to-rcu actions are relying on that
- * in cleanup() callback
- */
- if (f) {
- if (tcf_exts_get_net(&f->result.exts))
- tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work);
- else
- __tcindex_destroy_fexts(f);
- } else {
- if (tcf_exts_get_net(&r->exts))
- tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);
- else
- __tcindex_destroy_rexts(r);
- }
-
- *last = false;
- return 0;
-}
-
-static void tcindex_destroy_work(struct work_struct *work)
-{
- struct tcindex_data *p = container_of(to_rcu_work(work),
- struct tcindex_data,
- rwork);
-
- kfree(p->perfect);
- kfree(p->h);
- kfree(p);
-}
-
-static inline int
-valid_perfect_hash(struct tcindex_data *p)
-{
- return p->hash > (p->mask >> p->shift);
-}
-
-static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
- [TCA_TCINDEX_HASH] = { .type = NLA_U32 },
- [TCA_TCINDEX_MASK] = { .type = NLA_U16 },
- [TCA_TCINDEX_SHIFT] = { .type = NLA_U32 },
- [TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 },
- [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 },
-};
-
-static int tcindex_filter_result_init(struct tcindex_filter_result *r)
-{
- memset(r, 0, sizeof(*r));
- return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-}
-
-static void tcindex_partial_destroy_work(struct work_struct *work)
-{
- struct tcindex_data *p = container_of(to_rcu_work(work),
- struct tcindex_data,
- rwork);
-
- kfree(p->perfect);
- kfree(p);
-}
-
-static void tcindex_free_perfect_hash(struct tcindex_data *cp)
-{
- int i;
-
- for (i = 0; i < cp->hash; i++)
- tcf_exts_destroy(&cp->perfect[i].exts);
- kfree(cp->perfect);
-}
-
-static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
-{
- int i, err = 0;
-
- cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result),
- GFP_KERNEL | __GFP_NOWARN);
- if (!cp->perfect)
- return -ENOMEM;
-
- for (i = 0; i < cp->hash; i++) {
- err = tcf_exts_init(&cp->perfect[i].exts,
- TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
- if (err < 0)
- goto errout;
-#ifdef CONFIG_NET_CLS_ACT
- cp->perfect[i].exts.net = net;
-#endif
- }
-
- return 0;
-
-errout:
- tcindex_free_perfect_hash(cp);
- return err;
-}
-
-static int
-tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
- u32 handle, struct tcindex_data *p,
- struct tcindex_filter_result *r, struct nlattr **tb,
- struct nlattr *est, bool ovr, struct netlink_ext_ack *extack)
-{
- struct tcindex_filter_result new_filter_result, *old_r = r;
- struct tcindex_data *cp = NULL, *oldp;
- struct tcindex_filter *f = NULL; /* make gcc behave */
- struct tcf_result cr = {};
- int err, balloc = 0;
- struct tcf_exts e;
-
- err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
- if (err < 0)
- return err;
- err = tcf_exts_validate(net, tp, tb, est, &e, ovr, extack);
- if (err < 0)
- goto errout;
-
- err = -ENOMEM;
- /* tcindex_data attributes must look atomic to classifier/lookup so
- * allocate new tcindex data and RCU assign it onto root. Keeping
- * perfect hash and hash pointers from old data.
- */
- cp = kzalloc(sizeof(*cp), GFP_KERNEL);
- if (!cp)
- goto errout;
-
- cp->mask = p->mask;
- cp->shift = p->shift;
- cp->hash = p->hash;
- cp->alloc_hash = p->alloc_hash;
- cp->fall_through = p->fall_through;
- cp->tp = tp;
-
- if (tb[TCA_TCINDEX_HASH])
- cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
-
- if (tb[TCA_TCINDEX_MASK])
- cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
-
- if (tb[TCA_TCINDEX_SHIFT]) {
- cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
- if (cp->shift > 16) {
- err = -EINVAL;
- goto errout;
- }
- }
- if (!cp->hash) {
- /* Hash not specified, use perfect hash if the upper limit
- * of the hashing index is below the threshold.
- */
- if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
- cp->hash = (cp->mask >> cp->shift) + 1;
- else
- cp->hash = DEFAULT_HASH_SIZE;
- }
-
- if (p->perfect) {
- int i;
-
- if (tcindex_alloc_perfect_hash(net, cp) < 0)
- goto errout;
- cp->alloc_hash = cp->hash;
- for (i = 0; i < min(cp->hash, p->hash); i++)
- cp->perfect[i].res = p->perfect[i].res;
- balloc = 1;
- }
- cp->h = p->h;
-
- err = tcindex_filter_result_init(&new_filter_result);
- if (err < 0)
- goto errout_alloc;
- if (old_r)
- cr = r->res;
-
- err = -EBUSY;
-
- /* Hash already allocated, make sure that we still meet the
- * requirements for the allocated hash.
- */
- if (cp->perfect) {
- if (!valid_perfect_hash(cp) ||
- cp->hash > cp->alloc_hash)
- goto errout_alloc;
- } else if (cp->h && cp->hash != cp->alloc_hash) {
- goto errout_alloc;
- }
-
- err = -EINVAL;
- if (tb[TCA_TCINDEX_FALL_THROUGH])
- cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
-
- if (!cp->perfect && !cp->h)
- cp->alloc_hash = cp->hash;
-
- /* Note: this could be as restrictive as if (handle & ~(mask >> shift))
- * but then, we'd fail handles that may become valid after some future
- * mask change. While this is extremely unlikely to ever matter,
- * the check below is safer (and also more backwards-compatible).
- */
- if (cp->perfect || valid_perfect_hash(cp))
- if (handle >= cp->alloc_hash)
- goto errout_alloc;
-
-
- err = -ENOMEM;
- if (!cp->perfect && !cp->h) {
- if (valid_perfect_hash(cp)) {
- if (tcindex_alloc_perfect_hash(net, cp) < 0)
- goto errout_alloc;
- balloc = 1;
- } else {
- struct tcindex_filter __rcu **hash;
-
- hash = kcalloc(cp->hash,
- sizeof(struct tcindex_filter *),
- GFP_KERNEL);
-
- if (!hash)
- goto errout_alloc;
-
- cp->h = hash;
- balloc = 2;
- }
- }
-
- if (cp->perfect)
- r = cp->perfect + handle;
- else
- r = tcindex_lookup(cp, handle) ? : &new_filter_result;
-
- if (r == &new_filter_result) {
- f = kzalloc(sizeof(*f), GFP_KERNEL);
- if (!f)
- goto errout_alloc;
- f->key = handle;
- f->next = NULL;
- err = tcindex_filter_result_init(&f->result);
- if (err < 0) {
- kfree(f);
- goto errout_alloc;
- }
- }
-
- if (tb[TCA_TCINDEX_CLASSID]) {
- cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
- tcf_bind_filter(tp, &cr, base);
- }
-
- if (old_r && old_r != r) {
- err = tcindex_filter_result_init(old_r);
- if (err < 0) {
- kfree(f);
- goto errout_alloc;
- }
- }
-
- oldp = p;
- r->res = cr;
- tcf_exts_change(&r->exts, &e);
-
- rcu_assign_pointer(tp->root, cp);
-
- if (r == &new_filter_result) {
- struct tcindex_filter *nfp;
- struct tcindex_filter __rcu **fp;
-
- f->result.res = r->res;
- tcf_exts_change(&f->result.exts, &r->exts);
-
- fp = cp->h + (handle % cp->hash);
- for (nfp = rtnl_dereference(*fp);
- nfp;
- fp = &nfp->next, nfp = rtnl_dereference(*fp))
- ; /* nothing */
-
- rcu_assign_pointer(*fp, f);
- } else {
- tcf_exts_destroy(&new_filter_result.exts);
- }
-
- if (oldp)
- tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
- return 0;
-
-errout_alloc:
- if (balloc == 1)
- tcindex_free_perfect_hash(cp);
- else if (balloc == 2)
- kfree(cp->h);
- tcf_exts_destroy(&new_filter_result.exts);
-errout:
- kfree(cp);
- tcf_exts_destroy(&e);
- return err;
-}
-
-static int
-tcindex_change(struct net *net, struct sk_buff *in_skb,
- struct tcf_proto *tp, unsigned long base, u32 handle,
- struct nlattr **tca, void **arg, bool ovr,
- struct netlink_ext_ack *extack)
-{
- struct nlattr *opt = tca[TCA_OPTIONS];
- struct nlattr *tb[TCA_TCINDEX_MAX + 1];
- struct tcindex_data *p = rtnl_dereference(tp->root);
- struct tcindex_filter_result *r = *arg;
- int err;
-
- pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p,"
- "p %p,r %p,*arg %p\n",
- tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL);
-
- if (!opt)
- return 0;
-
- err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL);
- if (err < 0)
- return err;
-
- return tcindex_set_parms(net, tp, base, handle, p, r, tb,
- tca[TCA_RATE], ovr, extack);
-}
-
-static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
-{
- struct tcindex_data *p = rtnl_dereference(tp->root);
- struct tcindex_filter *f, *next;
- int i;
-
- pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p);
- if (p->perfect) {
- for (i = 0; i < p->hash; i++) {
- if (!p->perfect[i].res.class)
- continue;
- if (walker->count >= walker->skip) {
- if (walker->fn(tp, p->perfect + i, walker) < 0) {
- walker->stop = 1;
- return;
- }
- }
- walker->count++;
- }
- }
- if (!p->h)
- return;
- for (i = 0; i < p->hash; i++) {
- for (f = rtnl_dereference(p->h[i]); f; f = next) {
- next = rtnl_dereference(f->next);
- if (walker->count >= walker->skip) {
- if (walker->fn(tp, &f->result, walker) < 0) {
- walker->stop = 1;
- return;
- }
- }
- walker->count++;
- }
- }
-}
-
-static void tcindex_destroy(struct tcf_proto *tp,
- struct netlink_ext_ack *extack)
-{
- struct tcindex_data *p = rtnl_dereference(tp->root);
- int i;
-
- pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
-
- if (p->perfect) {
- for (i = 0; i < p->hash; i++) {
- struct tcindex_filter_result *r = p->perfect + i;
-
- tcf_unbind_filter(tp, &r->res);
- if (tcf_exts_get_net(&r->exts))
- tcf_queue_work(&r->rwork,
- tcindex_destroy_rexts_work);
- else
- __tcindex_destroy_rexts(r);
- }
- }
-
- for (i = 0; p->h && i < p->hash; i++) {
- struct tcindex_filter *f, *next;
- bool last;
-
- for (f = rtnl_dereference(p->h[i]); f; f = next) {
- next = rtnl_dereference(f->next);
- tcindex_delete(tp, &f->result, &last, NULL);
- }
- }
-
- tcf_queue_work(&p->rwork, tcindex_destroy_work);
-}
-
-
-static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
-{
- struct tcindex_data *p = rtnl_dereference(tp->root);
- struct tcindex_filter_result *r = fh;
- struct nlattr *nest;
-
- pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n",
- tp, fh, skb, t, p, r);
- pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h);
-
- nest = nla_nest_start(skb, TCA_OPTIONS);
- if (nest == NULL)
- goto nla_put_failure;
-
- if (!fh) {
- t->tcm_handle = ~0; /* whatever ... */
- if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) ||
- nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) ||
- nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) ||
- nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through))
- goto nla_put_failure;
- nla_nest_end(skb, nest);
- } else {
- if (p->perfect) {
- t->tcm_handle = r - p->perfect;
- } else {
- struct tcindex_filter *f;
- struct tcindex_filter __rcu **fp;
- int i;
-
- t->tcm_handle = 0;
- for (i = 0; !t->tcm_handle && i < p->hash; i++) {
- fp = &p->h[i];
- for (f = rtnl_dereference(*fp);
- !t->tcm_handle && f;
- fp = &f->next, f = rtnl_dereference(*fp)) {
- if (&f->result == r)
- t->tcm_handle = f->key;
- }
- }
- }
- pr_debug("handle = %d\n", t->tcm_handle);
- if (r->res.class &&
- nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid))
- goto nla_put_failure;
-
- if (tcf_exts_dump(skb, &r->exts) < 0)
- goto nla_put_failure;
- nla_nest_end(skb, nest);
-
- if (tcf_exts_dump_stats(skb, &r->exts) < 0)
- goto nla_put_failure;
- }
-
- return skb->len;
-
-nla_put_failure:
- nla_nest_cancel(skb, nest);
- return -1;
-}
-
-static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl,
- void *q, unsigned long base)
-{
- struct tcindex_filter_result *r = fh;
-
- if (r && r->res.classid == classid) {
- if (cl)
- __tcf_bind_filter(q, &r->res, base);
- else
- __tcf_unbind_filter(q, &r->res);
- }
-}
-
-static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
- .kind = "tcindex",
- .classify = tcindex_classify,
- .init = tcindex_init,
- .destroy = tcindex_destroy,
- .get = tcindex_get,
- .change = tcindex_change,
- .delete = tcindex_delete,
- .walk = tcindex_walk,
- .dump = tcindex_dump,
- .bind_class = tcindex_bind_class,
- .owner = THIS_MODULE,
-};
-
-static int __init init_tcindex(void)
-{
- return register_tcf_proto_ops(&cls_tcindex_ops);
-}
-
-static void __exit exit_tcindex(void)
-{
- unregister_tcf_proto_ops(&cls_tcindex_ops);
-}
-
-module_init(init_tcindex)
-module_exit(exit_tcindex)
-MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index d30256ac3537..1e71ff093c91 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -778,11 +778,22 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
int err;
+#ifdef CONFIG_NET_CLS_IND
+ int ifindex = -1;
+#endif
err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, extack);
if (err < 0)
return err;
+#ifdef CONFIG_NET_CLS_IND
+ if (tb[TCA_U32_INDEV]) {
+ ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack);
+ if (ifindex < 0)
+ return -EINVAL;
+ }
+#endif
+
if (tb[TCA_U32_LINK]) {
u32 handle = nla_get_u32(tb[TCA_U32_LINK]);
struct tc_u_hnode *ht_down = NULL, *ht_old;
@@ -814,13 +825,8 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
}
#ifdef CONFIG_NET_CLS_IND
- if (tb[TCA_U32_INDEV]) {
- int ret;
- ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack);
- if (ret < 0)
- return -EINVAL;
- n->ifindex = ret;
- }
+ if (ifindex >= 0)
+ n->ifindex = ifindex;
#endif
return 0;
}
@@ -873,7 +879,6 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
new->ifindex = n->ifindex;
#endif
new->fshift = n->fshift;
- new->res = n->res;
new->flags = n->flags;
RCU_INIT_POINTER(new->ht_down, ht);
@@ -1061,18 +1066,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return -EINVAL;
}
+ /* At this point, we need to derive the new handle that will be used to
+ * uniquely map the identity of this table match entry. The
+ * identity of the entry that we need to construct is 32 bits made of:
+ * htid(12b):bucketid(8b):node/entryid(12b)
+ *
+ * At this point _we have the table(ht)_ in which we will insert this
+ * entry. We carry the table's id in variable "htid".
+ * Note that earlier code picked the ht selection either by a) the user
+ * providing the htid specified via TCA_U32_HASH attribute or b) when
+ * no such attribute is passed then the root ht, is default to at ID
+ * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0.
+ * If OTOH the user passed us the htid, they may also pass a bucketid of
+ * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is
+ * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be
+ * passed via the htid, so even if it was non-zero it will be ignored.
+ *
+ * We may also have a handle, if the user passed one. The handle also
+ * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b).
+ * Rule: the bucketid on the handle is ignored even if one was passed;
+ * rather the value on "htid" is always assumed to be the bucketid.
+ */
if (handle) {
+ /* Rule: The htid from handle and tableid from htid must match */
if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) {
NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch");
return -EINVAL;
}
- handle = htid | TC_U32_NODE(handle);
- err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle,
- GFP_KERNEL);
- if (err)
- return err;
- } else
+ /* Ok, so far we have a valid htid(12b):bucketid(8b) but we
+ * need to finalize the table entry identification with the last
+ * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for
+ * entries. Rule: nodeid of 0 is reserved only for tables(see
+ * earlier code which processes TC_U32_DIVISOR attribute).
+ * Rule: The nodeid can only be derived from the handle (and not
+ * htid).
+ * Rule: if the handle specified zero for the node id example
+ * 0x60000000, then pick a new nodeid from the pool of IDs
+ * this hash table has been allocating from.
+ * If OTOH it is specified (i.e for example the user passed a
+ * handle such as 0x60000123), then we use it generate our final
+ * handle which is used to uniquely identify the match entry.
+ */
+ if (!TC_U32_NODE(handle)) {
+ handle = gen_new_kid(ht, htid);
+ } else {
+ handle = htid | TC_U32_NODE(handle);
+ err = idr_alloc_u32(&ht->handle_idr, NULL, &handle,
+ handle, GFP_KERNEL);
+ if (err)
+ return err;
+ }
+ } else {
+ /* The user did not give us a handle; lets just generate one
+ * from the table's pool of nodeids.
+ */
handle = gen_new_kid(ht, htid);
+ }
if (tb[TCA_U32_SEL] == NULL) {
NL_SET_ERR_MSG_MOD(extack, "Selector not specified");
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index 73e2ed576ceb..cbf44783024f 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -101,8 +101,10 @@ retry:
static void em_text_destroy(struct tcf_ematch *m)
{
- if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config)
+ if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) {
textsearch_destroy(EM_TEXT_PRIV(m)->config);
+ kfree(EM_TEXT_PRIV(m));
+ }
}
static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m)
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 113a133ee544..5ba3548d2eb7 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -259,6 +259,8 @@ static int tcf_em_validate(struct tcf_proto *tp,
* the value carried.
*/
if (em_hdr->flags & TCF_EM_SIMPLE) {
+ if (em->ops->datalen > 0)
+ goto errout;
if (data_len < sizeof(u32))
goto errout;
em->data = *(u32 *) data;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 424e70907b96..ab57c0ee9923 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1004,12 +1004,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
skip:
if (!ingress) {
- notify_and_destroy(net, skb, n, classid,
- dev->qdisc, new);
+ old = dev->qdisc;
if (new && !new->ops->attach)
qdisc_refcount_inc(new);
dev->qdisc = new ? : &noop_qdisc;
+ notify_and_destroy(net, skb, n, classid, old, new);
+
if (new && new->ops->attach)
new->ops->attach(new);
} else {
@@ -1031,8 +1032,12 @@ skip:
unsigned long cl = cops->find(parent, classid);
if (cl) {
- err = cops->graft(parent, cl, new, &old,
- extack);
+ if (new && new->ops == &noqueue_qdisc_ops) {
+ NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class");
+ err = -EINVAL;
+ } else {
+ err = cops->graft(parent, cl, new, &old, extack);
+ }
} else {
NL_SET_ERR_MSG(extack, "Specified class not found");
err = -ENOENT;
@@ -1144,7 +1149,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
sch->parent = parent;
if (handle == TC_H_INGRESS) {
- sch->flags |= TCQ_F_INGRESS;
+ if (!(sch->flags & TCQ_F_INGRESS)) {
+ NL_SET_ERR_MSG(extack,
+ "Specified parent ID is reserved for ingress and clsact Qdiscs");
+ err = -EINVAL;
+ goto err_out3;
+ }
handle = TC_H_MAKE(TC_H_INGRESS, 0);
lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock);
} else {
@@ -1429,10 +1439,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
return 0;
}
+static bool req_create_or_replace(struct nlmsghdr *n)
+{
+ return (n->nlmsg_flags & NLM_F_CREATE &&
+ n->nlmsg_flags & NLM_F_REPLACE);
+}
+
+static bool req_create_exclusive(struct nlmsghdr *n)
+{
+ return (n->nlmsg_flags & NLM_F_CREATE &&
+ n->nlmsg_flags & NLM_F_EXCL);
+}
+
+static bool req_change(struct nlmsghdr *n)
+{
+ return (!(n->nlmsg_flags & NLM_F_CREATE) &&
+ !(n->nlmsg_flags & NLM_F_REPLACE) &&
+ !(n->nlmsg_flags & NLM_F_EXCL));
+}
+
/*
* Create/change qdisc.
*/
-
static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
{
@@ -1505,11 +1533,20 @@ replay:
NL_SET_ERR_MSG(extack, "Invalid qdisc name");
return -EINVAL;
}
+ if (q->flags & TCQ_F_INGRESS) {
+ NL_SET_ERR_MSG(extack,
+ "Cannot regraft ingress or clsact Qdiscs");
+ return -EINVAL;
+ }
if (q == p ||
(p && check_loop(q, p, 0))) {
NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected");
return -ELOOP;
}
+ if (clid == TC_H_INGRESS) {
+ NL_SET_ERR_MSG(extack, "Ingress cannot graft directly");
+ return -EINVAL;
+ }
qdisc_refcount_inc(q);
goto graft;
} else {
@@ -1520,27 +1557,35 @@ replay:
*
* We know, that some child q is already
* attached to this parent and have choice:
- * either to change it or to create/graft new one.
+ * 1) change it or 2) create/graft new one.
+ * If the requested qdisc kind is different
+ * than the existing one, then we choose graft.
+ * If they are the same then this is "change"
+ * operation - just let it fallthrough..
*
* 1. We are allowed to create/graft only
- * if CREATE and REPLACE flags are set.
+ * if the request is explicitly stating
+ * "please create if it doesn't exist".
*
- * 2. If EXCL is set, requestor wanted to say,
- * that qdisc tcm_handle is not expected
+ * 2. If the request is to exclusive create
+ * then the qdisc tcm_handle is not expected
* to exist, so that we choose create/graft too.
*
* 3. The last case is when no flags are set.
+ * This will happen when for example tc
+ * utility issues a "change" command.
* Alas, it is sort of hole in API, we
* cannot decide what to do unambiguously.
- * For now we select create/graft, if
- * user gave KIND, which does not match existing.
+ * For now we select create/graft.
*/
- if ((n->nlmsg_flags & NLM_F_CREATE) &&
- (n->nlmsg_flags & NLM_F_REPLACE) &&
- ((n->nlmsg_flags & NLM_F_EXCL) ||
- (tca[TCA_KIND] &&
- nla_strcmp(tca[TCA_KIND], q->ops->id))))
- goto create_n_graft;
+ if (tca[TCA_KIND] &&
+ nla_strcmp(tca[TCA_KIND], q->ops->id)) {
+ if (req_create_or_replace(n) ||
+ req_create_exclusive(n))
+ goto create_n_graft;
+ else if (req_change(n))
+ goto create_n_graft2;
+ }
}
}
} else {
@@ -1574,6 +1619,7 @@ create_n_graft:
NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag");
return -ENOENT;
}
+create_n_graft2:
if (clid == TC_H_INGRESS) {
if (dev_ingress_queue(dev)) {
q = qdisc_create(dev, dev_ingress_queue(dev), p,
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 9a1bfa13a6cd..ff825f40ea04 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -394,10 +394,13 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
result = tcf_classify(skb, fl, &res, true);
if (result < 0)
continue;
+ if (result == TC_ACT_SHOT)
+ goto done;
+
flow = (struct atm_flow_data *)res.class;
if (!flow)
flow = lookup_flow(sch, res.classid);
- goto done;
+ goto drop;
}
}
flow = NULL;
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 01a177cfa533..d91665ea7b14 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1649,7 +1649,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
{
struct cake_sched_data *q = qdisc_priv(sch);
int len = qdisc_pkt_len(skb);
- int uninitialized_var(ret);
+ int ret;
struct sk_buff *ack = NULL;
ktime_t now = ktime_get();
struct cake_tin_data *b;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 0a76ad05e5ae..7f0a5d22deaf 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -236,6 +236,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
result = tcf_classify(skb, fl, &res, true);
if (!fl || result < 0)
goto fallback;
+ if (result == TC_ACT_SHOT)
+ return NULL;
cl = (void *)res.class;
if (!cl) {
@@ -256,8 +258,6 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
/* fall through */
- case TC_ACT_SHOT:
- return NULL;
case TC_ACT_RECLASSIFY:
return cbq_reclassify(skb, cl);
}
@@ -365,7 +365,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct cbq_sched_data *q = qdisc_priv(sch);
- int uninitialized_var(ret);
+ int ret;
struct cbq_class *cl = cbq_classify(skb, sch, &ret);
#ifdef CONFIG_NET_CLS_ACT
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index e4f69c779b8c..7a4777ee0536 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -192,7 +192,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct fq_codel_sched_data *q = qdisc_priv(sch);
unsigned int idx, prev_backlog, prev_qlen;
struct fq_codel_flow *flow;
- int uninitialized_var(ret);
+ int ret;
unsigned int pkt_len;
bool memory_limited;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index b18ec1f6de60..e71443623d67 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -913,6 +913,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc,
cl->cl_flags |= HFSC_USC;
}
+static void
+hfsc_upgrade_rt(struct hfsc_class *cl)
+{
+ cl->cl_fsc = cl->cl_rsc;
+ rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total);
+ cl->cl_flags |= HFSC_FSC;
+}
+
static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = {
[TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) },
[TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) },
@@ -1073,6 +1081,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cl->cf_tree = RB_ROOT;
sch_tree_lock(sch);
+ /* Check if the inner class is a misconfigured 'rt' */
+ if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
+ NL_SET_ERR_MSG(extack,
+ "Forced curve change on parent 'rt' to 'sc'");
+ hfsc_upgrade_rt(parent);
+ }
qdisc_class_hash_insert(&q->clhash, &cl->cl_common);
list_add_tail(&cl->siblings, &parent->children);
if (parent->level == 0)
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index ce3f55259d0d..834960cc755e 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -83,6 +83,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
struct ingress_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
+ if (sch->parent != TC_H_INGRESS)
+ return -EOPNOTSUPP;
+
net_inc_ingress_queue();
mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
@@ -98,6 +101,9 @@ static void ingress_destroy(struct Qdisc *sch)
{
struct ingress_sched_data *q = qdisc_priv(sch);
+ if (sch->parent != TC_H_INGRESS)
+ return;
+
tcf_block_put_ext(q->block, sch, &q->block_info);
net_dec_ingress_queue();
}
@@ -130,7 +136,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
.cl_ops = &ingress_class_ops,
.id = "ingress",
.priv_size = sizeof(struct ingress_sched_data),
- .static_flags = TCQ_F_CPUSTATS,
+ .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS,
.init = ingress_init,
.destroy = ingress_destroy,
.dump = ingress_dump,
@@ -215,6 +221,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
struct net_device *dev = qdisc_dev(sch);
int err;
+ if (sch->parent != TC_H_CLSACT)
+ return -EOPNOTSUPP;
+
net_inc_ingress_queue();
net_inc_egress_queue();
@@ -242,6 +251,9 @@ static void clsact_destroy(struct Qdisc *sch)
{
struct clsact_sched_data *q = qdisc_priv(sch);
+ if (sch->parent != TC_H_CLSACT)
+ return;
+
tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
@@ -262,7 +274,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = {
.cl_ops = &clsact_class_ops,
.id = "clsact",
.priv_size = sizeof(struct clsact_sched_data),
- .static_flags = TCQ_F_CPUSTATS,
+ .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS,
.init = clsact_init,
.destroy = clsact_destroy,
.dump = ingress_dump,
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 64d7f876d7de..c0ab1e38e80c 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,6 +132,97 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
return 0;
}
+static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt,
+ struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct mqprio_sched *priv = qdisc_priv(sch);
+ struct nlattr *tb[TCA_MQPRIO_MAX + 1];
+ struct nlattr *attr;
+ int i, rem, err;
+
+ err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
+ sizeof(*qopt));
+ if (err < 0)
+ return err;
+
+ if (!qopt->hw) {
+ NL_SET_ERR_MSG(extack,
+ "mqprio TCA_OPTIONS can only contain netlink attributes in hardware mode");
+ return -EINVAL;
+ }
+
+ if (tb[TCA_MQPRIO_MODE]) {
+ priv->flags |= TC_MQPRIO_F_MODE;
+ priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
+ }
+
+ if (tb[TCA_MQPRIO_SHAPER]) {
+ priv->flags |= TC_MQPRIO_F_SHAPER;
+ priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
+ }
+
+ if (tb[TCA_MQPRIO_MIN_RATE64]) {
+ if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MIN_RATE64],
+ "min_rate accepted only when shaper is in bw_rlimit mode");
+ return -EINVAL;
+ }
+ i = 0;
+ nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
+ rem) {
+ if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute type expected to be TCA_MQPRIO_MIN_RATE64");
+ return -EINVAL;
+ }
+
+ if (nla_len(attr) != sizeof(u64)) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute TCA_MQPRIO_MIN_RATE64 expected to have 8 bytes length");
+ return -EINVAL;
+ }
+
+ if (i >= qopt->num_tc)
+ break;
+ priv->min_rate[i] = *(u64 *)nla_data(attr);
+ i++;
+ }
+ priv->flags |= TC_MQPRIO_F_MIN_RATE;
+ }
+
+ if (tb[TCA_MQPRIO_MAX_RATE64]) {
+ if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MAX_RATE64],
+ "max_rate accepted only when shaper is in bw_rlimit mode");
+ return -EINVAL;
+ }
+ i = 0;
+ nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
+ rem) {
+ if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute type expected to be TCA_MQPRIO_MAX_RATE64");
+ return -EINVAL;
+ }
+
+ if (nla_len(attr) != sizeof(u64)) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute TCA_MQPRIO_MAX_RATE64 expected to have 8 bytes length");
+ return -EINVAL;
+ }
+
+ if (i >= qopt->num_tc)
+ break;
+ priv->max_rate[i] = *(u64 *)nla_data(attr);
+ i++;
+ }
+ priv->flags |= TC_MQPRIO_F_MAX_RATE;
+ }
+
+ return 0;
+}
+
static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
@@ -141,9 +232,6 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
struct Qdisc *qdisc;
int i, err = -EOPNOTSUPP;
struct tc_mqprio_qopt *qopt = NULL;
- struct nlattr *tb[TCA_MQPRIO_MAX + 1];
- struct nlattr *attr;
- int rem;
int len;
BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
@@ -168,55 +256,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt));
if (len > 0) {
- err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
- sizeof(*qopt));
- if (err < 0)
+ err = mqprio_parse_nlattr(sch, qopt, opt, extack);
+ if (err)
return err;
-
- if (!qopt->hw)
- return -EINVAL;
-
- if (tb[TCA_MQPRIO_MODE]) {
- priv->flags |= TC_MQPRIO_F_MODE;
- priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
- }
-
- if (tb[TCA_MQPRIO_SHAPER]) {
- priv->flags |= TC_MQPRIO_F_SHAPER;
- priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
- }
-
- if (tb[TCA_MQPRIO_MIN_RATE64]) {
- if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
- return -EINVAL;
- i = 0;
- nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
- rem) {
- if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64)
- return -EINVAL;
- if (i >= qopt->num_tc)
- break;
- priv->min_rate[i] = *(u64 *)nla_data(attr);
- i++;
- }
- priv->flags |= TC_MQPRIO_F_MIN_RATE;
- }
-
- if (tb[TCA_MQPRIO_MAX_RATE64]) {
- if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
- return -EINVAL;
- i = 0;
- nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
- rem) {
- if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64)
- return -EINVAL;
- if (i >= qopt->num_tc)
- break;
- priv->max_rate[i] = *(u64 *)nla_data(attr);
- i++;
- }
- priv->flags |= TC_MQPRIO_F_MAX_RATE;
- }
}
/* pre-allocate qdisc, attachment can't fail */
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 31793af1a77b..cf93dbe3d040 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -748,12 +748,10 @@ static void dist_free(struct disttable *d)
* signed 16 bit values.
*/
-static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
- const struct nlattr *attr)
+static int get_dist_table(struct disttable **tbl, const struct nlattr *attr)
{
size_t n = nla_len(attr)/sizeof(__s16);
const __s16 *data = nla_data(attr);
- spinlock_t *root_lock;
struct disttable *d;
int i;
@@ -768,13 +766,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
for (i = 0; i < n; i++)
d->table[i] = data[i];
- root_lock = qdisc_root_sleeping_lock(sch);
-
- spin_lock_bh(root_lock);
- swap(*tbl, d);
- spin_unlock_bh(root_lock);
-
- dist_free(d);
+ *tbl = d;
return 0;
}
@@ -930,6 +922,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
{
struct netem_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_NETEM_MAX + 1];
+ struct disttable *delay_dist = NULL;
+ struct disttable *slot_dist = NULL;
struct tc_netem_qopt *qopt;
struct clgstate old_clg;
int old_loss_model = CLG_RANDOM;
@@ -943,6 +937,19 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
if (ret < 0)
return ret;
+ if (tb[TCA_NETEM_DELAY_DIST]) {
+ ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]);
+ if (ret)
+ goto table_free;
+ }
+
+ if (tb[TCA_NETEM_SLOT_DIST]) {
+ ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]);
+ if (ret)
+ goto table_free;
+ }
+
+ sch_tree_lock(sch);
/* backup q->clg and q->loss_model */
old_clg = q->clg;
old_loss_model = q->loss_model;
@@ -951,26 +958,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
if (ret) {
q->loss_model = old_loss_model;
- return ret;
+ q->clg = old_clg;
+ goto unlock;
}
} else {
q->loss_model = CLG_RANDOM;
}
- if (tb[TCA_NETEM_DELAY_DIST]) {
- ret = get_dist_table(sch, &q->delay_dist,
- tb[TCA_NETEM_DELAY_DIST]);
- if (ret)
- goto get_table_failure;
- }
-
- if (tb[TCA_NETEM_SLOT_DIST]) {
- ret = get_dist_table(sch, &q->slot_dist,
- tb[TCA_NETEM_SLOT_DIST]);
- if (ret)
- goto get_table_failure;
- }
-
+ if (delay_dist)
+ swap(q->delay_dist, delay_dist);
+ if (slot_dist)
+ swap(q->slot_dist, slot_dist);
sch->limit = qopt->limit;
q->latency = PSCHED_TICKS2NS(qopt->latency);
@@ -1018,15 +1016,12 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
/* capping jitter to the range acceptable by tabledist() */
q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
- return ret;
+unlock:
+ sch_tree_unlock(sch);
-get_table_failure:
- /* recover clg and loss_model, in case of
- * q->clg and q->loss_model were modified
- * in get_loss_clg()
- */
- q->clg = old_clg;
- q->loss_model = old_loss_model;
+table_free:
+ dist_free(delay_dist);
+ dist_free(slot_dist);
return ret;
}
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index 5619d2eb17b6..4ddb4af61d10 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -214,7 +214,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct plug_sched_data),
.enqueue = plug_enqueue,
.dequeue = plug_dequeue,
- .peek = qdisc_peek_head,
+ .peek = qdisc_peek_dequeued,
.init = plug_init,
.change = plug_change,
.reset = qdisc_reset_queue,
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 20dc1851d4ff..4f246599734e 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -387,8 +387,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight,
u32 lmax)
{
struct qfq_sched *q = qdisc_priv(sch);
- struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight);
+ struct qfq_aggregate *new_agg;
+ /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */
+ if (lmax > (1UL << QFQ_MTU_SHIFT))
+ return -EINVAL;
+
+ new_agg = qfq_find_agg(q, lmax, weight);
if (new_agg == NULL) { /* create new aggregate */
new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC);
if (new_agg == NULL)
@@ -433,15 +438,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
} else
weight = 1;
- if (tb[TCA_QFQ_LMAX]) {
+ if (tb[TCA_QFQ_LMAX])
lmax = nla_get_u32(tb[TCA_QFQ_LMAX]);
- if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) {
- pr_notice("qfq: invalid max length %u\n", lmax);
- return -EINVAL;
- }
- } else
+ else
lmax = psched_mtu(qdisc_dev(sch));
+ if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) {
+ pr_notice("qfq: invalid max length %u\n", lmax);
+ return -EINVAL;
+ }
+
inv_w = ONE_FP / weight;
weight = ONE_FP / inv_w;
@@ -982,10 +988,13 @@ static void qfq_update_eligible(struct qfq_sched *q)
}
/* Dequeue head packet of the head class in the DRR queue of the aggregate. */
-static void agg_dequeue(struct qfq_aggregate *agg,
- struct qfq_class *cl, unsigned int len)
+static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
+ struct qfq_class *cl, unsigned int len)
{
- qdisc_dequeue_peeked(cl->qdisc);
+ struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc);
+
+ if (!skb)
+ return NULL;
cl->deficit -= (int) len;
@@ -995,6 +1004,8 @@ static void agg_dequeue(struct qfq_aggregate *agg,
cl->deficit += agg->lmax;
list_move_tail(&cl->alist, &agg->active);
}
+
+ return skb;
}
static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
@@ -1140,11 +1151,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
if (!skb)
return NULL;
- qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
+
+ skb = agg_dequeue(in_serv_agg, cl, len);
+
+ if (!skb) {
+ sch->q.qlen++;
+ return NULL;
+ }
+
+ qdisc_qstats_backlog_dec(sch, skb);
qdisc_bstats_update(sch, skb);
- agg_dequeue(in_serv_agg, cl, len);
/* If lmax is lowered, through qfq_change_class, for a class
* owning pending packets with larger size than the new value
* of lmax, then the following condition may hold.
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 1bfdf90fa0cc..07721a1e98d8 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -353,7 +353,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
unsigned int hash, dropped;
sfq_index x, qlen;
struct sfq_slot *slot;
- int uninitialized_var(ret);
+ int ret;
struct sk_buff *head;
int delta;
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-30 17:35:41 +0000