aboutsummaryrefslogtreecommitdiff
path: root/net/sched/sch_api.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched/sch_api.c')
-rw-r--r--net/sched/sch_api.c459
1 files changed, 305 insertions, 154 deletions
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index b22ca2d1ceb..58bed7599db 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -135,7 +135,7 @@ static DEFINE_RWLOCK(qdisc_mod_lock);
static struct Qdisc_ops *qdisc_base;
-/* Register/uregister queueing discipline */
+/* Register/unregister queueing discipline */
int register_qdisc(struct Qdisc_ops *qops)
{
@@ -187,7 +187,7 @@ int unregister_qdisc(struct Qdisc_ops *qops)
int err = -ENOENT;
write_lock(&qdisc_mod_lock);
- for (qp = &qdisc_base; (q=*qp)!=NULL; qp = &q->next)
+ for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next)
if (q == qops)
break;
if (q) {
@@ -200,6 +200,58 @@ int unregister_qdisc(struct Qdisc_ops *qops)
}
EXPORT_SYMBOL(unregister_qdisc);
+/* Get default qdisc if not otherwise specified */
+void qdisc_get_default(char *name, size_t len)
+{
+ read_lock(&qdisc_mod_lock);
+ strlcpy(name, default_qdisc_ops->id, len);
+ read_unlock(&qdisc_mod_lock);
+}
+
+static struct Qdisc_ops *qdisc_lookup_default(const char *name)
+{
+ struct Qdisc_ops *q = NULL;
+
+ for (q = qdisc_base; q; q = q->next) {
+ if (!strcmp(name, q->id)) {
+ if (!try_module_get(q->owner))
+ q = NULL;
+ break;
+ }
+ }
+
+ return q;
+}
+
+/* Set new default qdisc to use */
+int qdisc_set_default(const char *name)
+{
+ const struct Qdisc_ops *ops;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ write_lock(&qdisc_mod_lock);
+ ops = qdisc_lookup_default(name);
+ if (!ops) {
+ /* Not found, drop lock and try to load module */
+ write_unlock(&qdisc_mod_lock);
+ request_module("sch_%s", name);
+ write_lock(&qdisc_mod_lock);
+
+ ops = qdisc_lookup_default(name);
+ }
+
+ if (ops) {
+ /* Set new default */
+ module_put(default_qdisc_ops->owner);
+ default_qdisc_ops = ops;
+ }
+ write_unlock(&qdisc_mod_lock);
+
+ return ops ? 0 : -ENOENT;
+}
+
/* We know handle. Find qdisc among all qdisc's attached to device
(root qdisc, all its children, children of children etc.)
*/
@@ -219,11 +271,16 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
return NULL;
}
-static void qdisc_list_add(struct Qdisc *q)
+void qdisc_list_add(struct Qdisc *q)
{
- if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
- list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list);
+ if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+ struct Qdisc *root = qdisc_dev(q)->qdisc;
+
+ WARN_ON_ONCE(root == &noop_qdisc);
+ list_add_tail(&q->list, &root->list);
+ }
}
+EXPORT_SYMBOL(qdisc_list_add);
void qdisc_list_del(struct Qdisc *q)
{
@@ -285,28 +342,70 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind)
return q;
}
+/* The linklayer setting were not transferred from iproute2, in older
+ * versions, and the rate tables lookup systems have been dropped in
+ * the kernel. To keep backward compatible with older iproute2 tc
+ * utils, we detect the linklayer setting by detecting if the rate
+ * table were modified.
+ *
+ * For linklayer ATM table entries, the rate table will be aligned to
+ * 48 bytes, thus some table entries will contain the same value. The
+ * mpu (min packet unit) is also encoded into the old rate table, thus
+ * starting from the mpu, we find low and high table entries for
+ * mapping this cell. If these entries contain the same value, when
+ * the rate tables have been modified for linklayer ATM.
+ *
+ * This is done by rounding mpu to the nearest 48 bytes cell/entry,
+ * and then roundup to the next cell, calc the table entry one below,
+ * and compare.
+ */
+static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab)
+{
+ int low = roundup(r->mpu, 48);
+ int high = roundup(low+1, 48);
+ int cell_low = low >> r->cell_log;
+ int cell_high = (high >> r->cell_log) - 1;
+
+ /* rtab is too inaccurate at rates > 100Mbit/s */
+ if ((r->rate > (100000000/8)) || (rtab[0] == 0)) {
+ pr_debug("TC linklayer: Giving up ATM detection\n");
+ return TC_LINKLAYER_ETHERNET;
+ }
+
+ if ((cell_high > cell_low) && (cell_high < 256)
+ && (rtab[cell_low] == rtab[cell_high])) {
+ pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n",
+ cell_low, cell_high, rtab[cell_high]);
+ return TC_LINKLAYER_ATM;
+ }
+ return TC_LINKLAYER_ETHERNET;
+}
+
static struct qdisc_rate_table *qdisc_rtab_list;
struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab)
{
struct qdisc_rate_table *rtab;
+ if (tab == NULL || r->rate == 0 || r->cell_log == 0 ||
+ nla_len(tab) != TC_RTAB_SIZE)
+ return NULL;
+
for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) {
- if (memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) == 0) {
+ if (!memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) &&
+ !memcmp(&rtab->data, nla_data(tab), 1024)) {
rtab->refcnt++;
return rtab;
}
}
- if (tab == NULL || r->rate == 0 || r->cell_log == 0 ||
- nla_len(tab) != TC_RTAB_SIZE)
- return NULL;
-
rtab = kmalloc(sizeof(*rtab), GFP_KERNEL);
if (rtab) {
rtab->rate = *r;
rtab->refcnt = 1;
memcpy(rtab->data, nla_data(tab), 1024);
+ if (r->linklayer == TC_LINKLAYER_UNAWARE)
+ r->linklayer = __detect_linklayer(r, rtab->data);
rtab->next = qdisc_rtab_list;
qdisc_rtab_list = rtab;
}
@@ -321,7 +420,9 @@ void qdisc_put_rtab(struct qdisc_rate_table *tab)
if (!tab || --tab->refcnt)
return;
- for (rtabp = &qdisc_rtab_list; (rtab=*rtabp) != NULL; rtabp = &rtab->next) {
+ for (rtabp = &qdisc_rtab_list;
+ (rtab = *rtabp) != NULL;
+ rtabp = &rtab->next) {
if (rtab == tab) {
*rtabp = rtab->next;
kfree(rtab);
@@ -396,6 +497,11 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt)
return stab;
}
+static void stab_kfree_rcu(struct rcu_head *head)
+{
+ kfree(container_of(head, struct qdisc_size_table, rcu));
+}
+
void qdisc_put_stab(struct qdisc_size_table *tab)
{
if (!tab)
@@ -405,7 +511,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab)
if (--tab->refcnt == 0) {
list_del(&tab->list);
- kfree(tab);
+ call_rcu_bh(&tab->rcu, stab_kfree_rcu);
}
spin_unlock(&qdisc_stab_lock);
@@ -419,7 +525,8 @@ static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab)
nest = nla_nest_start(skb, TCA_STAB);
if (nest == NULL)
goto nla_put_failure;
- NLA_PUT(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts);
+ if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts))
+ goto nla_put_failure;
nla_nest_end(skb, nest);
return skb->len;
@@ -428,7 +535,7 @@ nla_put_failure:
return -1;
}
-void qdisc_calculate_pkt_len(struct sk_buff *skb, struct qdisc_size_table *stab)
+void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab)
{
int pkt_len, slot;
@@ -454,14 +561,13 @@ out:
pkt_len = 1;
qdisc_skb_cb(skb)->pkt_len = pkt_len;
}
-EXPORT_SYMBOL(qdisc_calculate_pkt_len);
+EXPORT_SYMBOL(__qdisc_calculate_pkt_len);
-void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc)
+void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
{
if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
- printk(KERN_WARNING
- "%s: %s qdisc %X: is non-work-conserving?\n",
- txt, qdisc->ops->id, qdisc->handle >> 16);
+ pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
+ txt, qdisc->ops->id, qdisc->handle >> 16);
qdisc->flags |= TCQ_F_WARN_NONWC;
}
}
@@ -472,7 +578,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
timer);
- wd->qdisc->flags &= ~TCQ_F_THROTTLED;
+ qdisc_unthrottled(wd->qdisc);
__netif_schedule(qdisc_root(wd->qdisc));
return HRTIMER_NORESTART;
@@ -486,25 +592,24 @@ void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
}
EXPORT_SYMBOL(qdisc_watchdog_init);
-void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires)
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
{
- ktime_t time;
-
if (test_bit(__QDISC_STATE_DEACTIVATED,
&qdisc_root_sleeping(wd->qdisc)->state))
return;
- wd->qdisc->flags |= TCQ_F_THROTTLED;
- time = ktime_set(0, 0);
- time = ktime_add_ns(time, PSCHED_TICKS2NS(expires));
- hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS);
+ qdisc_throttled(wd->qdisc);
+
+ hrtimer_start(&wd->timer,
+ ns_to_ktime(expires),
+ HRTIMER_MODE_ABS);
}
-EXPORT_SYMBOL(qdisc_watchdog_schedule);
+EXPORT_SYMBOL(qdisc_watchdog_schedule_ns);
void qdisc_watchdog_cancel(struct qdisc_watchdog *wd)
{
hrtimer_cancel(&wd->timer);
- wd->qdisc->flags &= ~TCQ_F_THROTTLED;
+ qdisc_unthrottled(wd->qdisc);
}
EXPORT_SYMBOL(qdisc_watchdog_cancel);
@@ -539,7 +644,7 @@ static void qdisc_class_hash_free(struct hlist_head *h, unsigned int n)
void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash)
{
struct Qdisc_class_common *cl;
- struct hlist_node *n, *next;
+ struct hlist_node *next;
struct hlist_head *nhash, *ohash;
unsigned int nsize, nmask, osize;
unsigned int i, h;
@@ -558,7 +663,7 @@ void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash)
sch_tree_lock(sch);
for (i = 0; i < osize; i++) {
- hlist_for_each_entry_safe(cl, n, next, &ohash[i], hnode) {
+ hlist_for_each_entry_safe(cl, next, &ohash[i], hnode) {
h = qdisc_class_hash(cl->classid, nmask);
hlist_add_head(&cl->hnode, &nhash[h]);
}
@@ -612,20 +717,24 @@ void qdisc_class_hash_remove(struct Qdisc_class_hash *clhash,
}
EXPORT_SYMBOL(qdisc_class_hash_remove);
-/* Allocate an unique handle from space managed by kernel */
-
+/* Allocate an unique handle from space managed by kernel
+ * Possible range is [8000-FFFF]:0000 (0x8000 values)
+ */
static u32 qdisc_alloc_handle(struct net_device *dev)
{
- int i = 0x10000;
+ int i = 0x8000;
static u32 autohandle = TC_H_MAKE(0x80000000U, 0);
do {
autohandle += TC_H_MAKE(0x10000U, 0);
if (autohandle == TC_H_MAKE(TC_H_ROOT, 0))
autohandle = TC_H_MAKE(0x80000000U, 0);
- } while (qdisc_lookup(dev, autohandle) && --i > 0);
+ if (!qdisc_lookup(dev, autohandle))
+ return autohandle;
+ cond_resched();
+ } while (--i > 0);
- return i>0 ? autohandle : 0;
+ return 0;
}
void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
@@ -633,9 +742,11 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
const struct Qdisc_class_ops *cops;
unsigned long cl;
u32 parentid;
+ int drops;
if (n == 0)
return;
+ drops = max_t(int, n, 0);
while ((parentid = sch->parent)) {
if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
return;
@@ -652,6 +763,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
cops->put(sch, cl);
}
sch->q.qlen -= n;
+ sch->qstats.drops += drops;
}
}
EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
@@ -823,6 +935,8 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
goto err_out3;
}
lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
+ if (!netif_is_multiqueue(dev))
+ sch->flags |= TCQ_F_ONETXQUEUE;
}
sch->handle = handle;
@@ -834,7 +948,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
err = PTR_ERR(stab);
goto err_out4;
}
- sch->stab = stab;
+ rcu_assign_pointer(sch->stab, stab);
}
if (tca[TCA_RATE]) {
spinlock_t *root_lock;
@@ -874,7 +988,7 @@ err_out4:
* Any broken qdiscs that would require a ops->reset() here?
* The qdisc was never in action so it shouldn't be necessary.
*/
- qdisc_put_stab(sch->stab);
+ qdisc_put_stab(rtnl_dereference(sch->stab));
if (ops->destroy)
ops->destroy(sch);
goto err_out3;
@@ -882,7 +996,7 @@ err_out4:
static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
{
- struct qdisc_size_table *stab = NULL;
+ struct qdisc_size_table *ostab, *stab = NULL;
int err = 0;
if (tca[TCA_OPTIONS]) {
@@ -899,8 +1013,9 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
return PTR_ERR(stab);
}
- qdisc_put_stab(sch->stab);
- sch->stab = stab;
+ ostab = rtnl_dereference(sch->stab);
+ rcu_assign_pointer(sch->stab, stab);
+ qdisc_put_stab(ostab);
if (tca[TCA_RATE]) {
/* NB: ignores errors from replace_estimator
@@ -915,9 +1030,8 @@ out:
return 0;
}
-struct check_loop_arg
-{
- struct qdisc_walker w;
+struct check_loop_arg {
+ struct qdisc_walker w;
struct Qdisc *p;
int depth;
};
@@ -959,33 +1073,39 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
* Delete/get qdisc.
*/
-static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
{
struct net *net = sock_net(skb->sk);
- struct tcmsg *tcm = NLMSG_DATA(n);
+ struct tcmsg *tcm = nlmsg_data(n);
struct nlattr *tca[TCA_MAX + 1];
struct net_device *dev;
- u32 clid = tcm->tcm_parent;
+ u32 clid;
struct Qdisc *q = NULL;
struct Qdisc *p = NULL;
int err;
- if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL)
- return -ENODEV;
+ if ((n->nlmsg_type != RTM_GETQDISC) &&
+ !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
if (err < 0)
return err;
+ dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+ if (!dev)
+ return -ENODEV;
+
+ clid = tcm->tcm_parent;
if (clid) {
if (clid != TC_H_ROOT) {
if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) {
- if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL)
+ p = qdisc_lookup(dev, TC_H_MAJ(clid));
+ if (!p)
return -ENOENT;
q = qdisc_leaf(p, clid);
- } else { /* ingress */
- if (dev_ingress_queue(dev))
- q = dev_ingress_queue(dev)->qdisc_sleeping;
+ } else if (dev_ingress_queue(dev)) {
+ q = dev_ingress_queue(dev)->qdisc_sleeping;
}
} else {
q = dev->qdisc;
@@ -996,7 +1116,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
if (tcm->tcm_handle && q->handle != tcm->tcm_handle)
return -EINVAL;
} else {
- if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL)
+ q = qdisc_lookup(dev, tcm->tcm_handle);
+ if (!q)
return -ENOENT;
}
@@ -1008,7 +1129,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
return -EINVAL;
if (q->handle == 0)
return -ENOENT;
- if ((err = qdisc_graft(dev, p, skb, n, clid, NULL, q)) != 0)
+ err = qdisc_graft(dev, p, skb, n, clid, NULL, q);
+ if (err != 0)
return err;
} else {
qdisc_notify(net, skb, n, clid, NULL, q);
@@ -1017,10 +1139,10 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
}
/*
- Create/change qdisc.
+ * Create/change qdisc.
*/
-static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
{
struct net *net = sock_net(skb->sk);
struct tcmsg *tcm;
@@ -1030,28 +1152,33 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
struct Qdisc *q, *p;
int err;
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
replay:
/* Reinit, just in case something touches this. */
- tcm = NLMSG_DATA(n);
+ err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
+ if (err < 0)
+ return err;
+
+ tcm = nlmsg_data(n);
clid = tcm->tcm_parent;
q = p = NULL;
- if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL)
+ dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+ if (!dev)
return -ENODEV;
- err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
- if (err < 0)
- return err;
if (clid) {
if (clid != TC_H_ROOT) {
if (clid != TC_H_INGRESS) {
- if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL)
+ p = qdisc_lookup(dev, TC_H_MAJ(clid));
+ if (!p)
return -ENOENT;
q = qdisc_leaf(p, clid);
- } else { /* ingress */
- if (dev_ingress_queue_create(dev))
- q = dev_ingress_queue(dev)->qdisc_sleeping;
+ } else if (dev_ingress_queue_create(dev)) {
+ q = dev_ingress_queue(dev)->qdisc_sleeping;
}
} else {
q = dev->qdisc;
@@ -1063,13 +1190,14 @@ replay:
if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) {
if (tcm->tcm_handle) {
- if (q && !(n->nlmsg_flags&NLM_F_REPLACE))
+ if (q && !(n->nlmsg_flags & NLM_F_REPLACE))
return -EEXIST;
if (TC_H_MIN(tcm->tcm_handle))
return -EINVAL;
- if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL)
+ q = qdisc_lookup(dev, tcm->tcm_handle);
+ if (!q)
goto create_n_graft;
- if (n->nlmsg_flags&NLM_F_EXCL)
+ if (n->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id))
return -EINVAL;
@@ -1079,7 +1207,7 @@ replay:
atomic_inc(&q->refcnt);
goto graft;
} else {
- if (q == NULL)
+ if (!q)
goto create_n_graft;
/* This magic test requires explanation.
@@ -1101,9 +1229,9 @@ replay:
* For now we select create/graft, if
* user gave KIND, which does not match existing.
*/
- if ((n->nlmsg_flags&NLM_F_CREATE) &&
- (n->nlmsg_flags&NLM_F_REPLACE) &&
- ((n->nlmsg_flags&NLM_F_EXCL) ||
+ 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;
@@ -1118,7 +1246,7 @@ replay:
/* Change qdisc parameters */
if (q == NULL)
return -ENOENT;
- if (n->nlmsg_flags&NLM_F_EXCL)
+ if (n->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id))
return -EINVAL;
@@ -1128,7 +1256,7 @@ replay:
return err;
create_n_graft:
- if (!(n->nlmsg_flags&NLM_F_CREATE))
+ if (!(n->nlmsg_flags & NLM_F_CREATE))
return -ENOENT;
if (clid == TC_H_INGRESS) {
if (dev_ingress_queue(dev))
@@ -1169,15 +1297,19 @@ graft:
}
static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
- u32 pid, u32 seq, u16 flags, int event)
+ u32 portid, u32 seq, u16 flags, int event)
{
struct tcmsg *tcm;
struct nlmsghdr *nlh;
unsigned char *b = skb_tail_pointer(skb);
struct gnet_dump d;
+ struct qdisc_size_table *stab;
- nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
- tcm = NLMSG_DATA(nlh);
+ cond_resched();
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
+ if (!nlh)
+ goto out_nlmsg_trim;
+ tcm = nlmsg_data(nlh);
tcm->tcm_family = AF_UNSPEC;
tcm->tcm__pad1 = 0;
tcm->tcm__pad2 = 0;
@@ -1185,12 +1317,14 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
tcm->tcm_parent = clid;
tcm->tcm_handle = q->handle;
tcm->tcm_info = atomic_read(&q->refcnt);
- NLA_PUT_STRING(skb, TCA_KIND, q->ops->id);
+ if (nla_put_string(skb, TCA_KIND, q->ops->id))
+ goto nla_put_failure;
if (q->ops->dump && q->ops->dump(q, skb) < 0)
goto nla_put_failure;
q->qstats.qlen = q->q.qlen;
- if (q->stab && qdisc_dump_stab(skb, q->stab) < 0)
+ stab = rtnl_dereference(q->stab);
+ if (stab && qdisc_dump_stab(skb, stab) < 0)
goto nla_put_failure;
if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
@@ -1211,7 +1345,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
-nlmsg_failure:
+out_nlmsg_trim:
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
@@ -1227,23 +1361,26 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
struct Qdisc *old, struct Qdisc *new)
{
struct sk_buff *skb;
- u32 pid = oskb ? NETLINK_CB(oskb).pid : 0;
+ u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
if (old && !tc_qdisc_dump_ignore(old)) {
- if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0)
+ if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq,
+ 0, RTM_DELQDISC) < 0)
goto err_out;
}
if (new && !tc_qdisc_dump_ignore(new)) {
- if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0)
+ if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq,
+ old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0)
goto err_out;
}
if (skb->len)
- return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO);
+ return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+ n->nlmsg_flags & NLM_F_ECHO);
err_out:
kfree_skb(skb);
@@ -1265,7 +1402,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
q_idx++;
} else {
if (!tc_qdisc_dump_ignore(q) &&
- tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid,
+ tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0)
goto done;
q_idx++;
@@ -1275,8 +1412,8 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
q_idx++;
continue;
}
- if (!tc_qdisc_dump_ignore(q) &&
- tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid,
+ if (!tc_qdisc_dump_ignore(q) &&
+ tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0)
goto done;
q_idx++;
@@ -1300,9 +1437,9 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
s_idx = cb->args[0];
s_q_idx = q_idx = cb->args[1];
- rcu_read_lock();
idx = 0;
- for_each_netdev_rcu(net, dev) {
+ ASSERT_RTNL();
+ for_each_netdev(net, dev) {
struct netdev_queue *dev_queue;
if (idx < s_idx)
@@ -1325,8 +1462,6 @@ cont:
}
done:
- rcu_read_unlock();
-
cb->args[0] = idx;
cb->args[1] = q_idx;
@@ -1341,28 +1476,33 @@ done:
-static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
+static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
{
struct net *net = sock_net(skb->sk);
- struct tcmsg *tcm = NLMSG_DATA(n);
+ struct tcmsg *tcm = nlmsg_data(n);
struct nlattr *tca[TCA_MAX + 1];
struct net_device *dev;
struct Qdisc *q = NULL;
const struct Qdisc_class_ops *cops;
unsigned long cl = 0;
unsigned long new_cl;
- u32 pid = tcm->tcm_parent;
- u32 clid = tcm->tcm_handle;
- u32 qid = TC_H_MAJ(clid);
+ u32 portid;
+ u32 clid;
+ u32 qid;
int err;
- if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL)
- return -ENODEV;
+ if ((n->nlmsg_type != RTM_GETTCLASS) &&
+ !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
if (err < 0)
return err;
+ dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+ if (!dev)
+ return -ENODEV;
+
/*
parent == TC_H_UNSPEC - unspecified parent.
parent == TC_H_ROOT - class is root, which has no parent.
@@ -1378,8 +1518,12 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
/* Step 1. Determine qdisc handle X:0 */
- if (pid != TC_H_ROOT) {
- u32 qid1 = TC_H_MAJ(pid);
+ portid = tcm->tcm_parent;
+ clid = tcm->tcm_handle;
+ qid = TC_H_MAJ(clid);
+
+ if (portid != TC_H_ROOT) {
+ u32 qid1 = TC_H_MAJ(portid);
if (qid && qid1) {
/* If both majors are known, they must be identical. */
@@ -1391,19 +1535,20 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
qid = dev->qdisc->handle;
/* Now qid is genuine qdisc handle consistent
- both with parent and child.
-
- TC_H_MAJ(pid) still may be unspecified, complete it now.
+ * both with parent and child.
+ *
+ * TC_H_MAJ(portid) still may be unspecified, complete it now.
*/
- if (pid)
- pid = TC_H_MAKE(qid, pid);
+ if (portid)
+ portid = TC_H_MAKE(qid, portid);
} else {
if (qid == 0)
qid = dev->qdisc->handle;
}
/* OK. Locate qdisc */
- if ((q = qdisc_lookup(dev, qid)) == NULL)
+ q = qdisc_lookup(dev, qid);
+ if (!q)
return -ENOENT;
/* An check that it supports classes */
@@ -1413,7 +1558,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
/* Now try to get class */
if (clid == 0) {
- if (pid == TC_H_ROOT)
+ if (portid == TC_H_ROOT)
clid = qid;
} else
clid = TC_H_MAKE(qid, clid);
@@ -1423,13 +1568,14 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
if (cl == 0) {
err = -ENOENT;
- if (n->nlmsg_type != RTM_NEWTCLASS || !(n->nlmsg_flags&NLM_F_CREATE))
+ if (n->nlmsg_type != RTM_NEWTCLASS ||
+ !(n->nlmsg_flags & NLM_F_CREATE))
goto out;
} else {
switch (n->nlmsg_type) {
case RTM_NEWTCLASS:
err = -EEXIST;
- if (n->nlmsg_flags&NLM_F_EXCL)
+ if (n->nlmsg_flags & NLM_F_EXCL)
goto out;
break;
case RTM_DELTCLASS:
@@ -1451,7 +1597,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
new_cl = cl;
err = -EOPNOTSUPP;
if (cops->change)
- err = cops->change(q, clid, pid, tca, &new_cl);
+ err = cops->change(q, clid, portid, tca, &new_cl);
if (err == 0)
tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS);
@@ -1465,7 +1611,7 @@ out:
static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
unsigned long cl,
- u32 pid, u32 seq, u16 flags, int event)
+ u32 portid, u32 seq, u16 flags, int event)
{
struct tcmsg *tcm;
struct nlmsghdr *nlh;
@@ -1473,8 +1619,11 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
struct gnet_dump d;
const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops;
- nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
- tcm = NLMSG_DATA(nlh);
+ cond_resched();
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
+ if (!nlh)
+ goto out_nlmsg_trim;
+ tcm = nlmsg_data(nlh);
tcm->tcm_family = AF_UNSPEC;
tcm->tcm__pad1 = 0;
tcm->tcm__pad2 = 0;
@@ -1482,7 +1631,8 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
tcm->tcm_parent = q->handle;
tcm->tcm_handle = q->handle;
tcm->tcm_info = 0;
- NLA_PUT_STRING(skb, TCA_KIND, q->ops->id);
+ if (nla_put_string(skb, TCA_KIND, q->ops->id))
+ goto nla_put_failure;
if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0)
goto nla_put_failure;
@@ -1499,7 +1649,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
-nlmsg_failure:
+out_nlmsg_trim:
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
@@ -1510,32 +1660,32 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb,
unsigned long cl, int event)
{
struct sk_buff *skb;
- u32 pid = oskb ? NETLINK_CB(oskb).pid : 0;
+ u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
- if (tc_fill_tclass(skb, q, cl, pid, n->nlmsg_seq, 0, event) < 0) {
+ if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event) < 0) {
kfree_skb(skb);
return -EINVAL;
}
- return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO);
+ return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+ n->nlmsg_flags & NLM_F_ECHO);
}
-struct qdisc_dump_args
-{
- struct qdisc_walker w;
- struct sk_buff *skb;
- struct netlink_callback *cb;
+struct qdisc_dump_args {
+ struct qdisc_walker w;
+ struct sk_buff *skb;
+ struct netlink_callback *cb;
};
static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg)
{
struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg;
- return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).pid,
+ return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid,
a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS);
}
@@ -1590,15 +1740,16 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb,
static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct tcmsg *tcm = (struct tcmsg*)NLMSG_DATA(cb->nlh);
+ struct tcmsg *tcm = nlmsg_data(cb->nlh);
struct net *net = sock_net(skb->sk);
struct netdev_queue *dev_queue;
struct net_device *dev;
int t, s_t;
- if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm)))
+ if (nlmsg_len(cb->nlh) < sizeof(*tcm))
return 0;
- if ((dev = dev_get_by_index(net, tcm->tcm_ifindex)) == NULL)
+ dev = dev_get_by_index(net, tcm->tcm_ifindex);
+ if (!dev)
return 0;
s_t = cb->args[0];
@@ -1621,19 +1772,22 @@ done:
}
/* Main classifier routine: scans classifier chain attached
- to this qdisc, (optionally) tests for protocol and asks
- specific classifiers.
+ * to this qdisc, (optionally) tests for protocol and asks
+ * specific classifiers.
*/
-int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp,
+int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
__be16 protocol = skb->protocol;
- int err = 0;
+ int err;
for (; tp; tp = tp->next) {
- if ((tp->protocol == protocol ||
- tp->protocol == htons(ETH_P_ALL)) &&
- (err = tp->classify(skb, tp, res)) >= 0) {
+ if (tp->protocol != protocol &&
+ tp->protocol != htons(ETH_P_ALL))
+ continue;
+ err = tp->classify(skb, tp, res);
+
+ if (err >= 0) {
#ifdef CONFIG_NET_CLS_ACT
if (err != TC_ACT_RECLASSIFY && skb->tc_verd)
skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0);
@@ -1645,16 +1799,14 @@ int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp,
}
EXPORT_SYMBOL(tc_classify_compat);
-int tc_classify(struct sk_buff *skb, struct tcf_proto *tp,
+int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
int err = 0;
- __be16 protocol;
#ifdef CONFIG_NET_CLS_ACT
- struct tcf_proto *otp = tp;
+ const struct tcf_proto *otp = tp;
reclassify:
#endif
- protocol = skb->protocol;
err = tc_classify_compat(skb, tp, res);
#ifdef CONFIG_NET_CLS_ACT
@@ -1663,12 +1815,10 @@ reclassify:
tp = otp;
if (verd++ >= MAX_REC_LOOP) {
- if (net_ratelimit())
- printk(KERN_NOTICE
- "%s: packet reclassify loop"
- " rule prio %u protocol %02x\n",
- tp->q->ops->id,
- tp->prio & 0xffff, ntohs(tp->protocol));
+ net_notice_ratelimited("%s: packet reclassify loop rule prio %u protocol %02x\n",
+ tp->q->ops->id,
+ tp->prio & 0xffff,
+ ntohs(tp->protocol));
return TC_ACT_SHOT;
}
skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd);
@@ -1728,7 +1878,7 @@ static int __net_init psched_net_init(struct net *net)
{
struct proc_dir_entry *e;
- e = proc_net_fops_create(net, "psched", 0, &psched_fops);
+ e = proc_create("psched", 0, net->proc_net, &psched_fops);
if (e == NULL)
return -ENOMEM;
@@ -1737,7 +1887,7 @@ static int __net_init psched_net_init(struct net *net)
static void __net_exit psched_net_exit(struct net *net)
{
- proc_net_remove(net, "psched");
+ remove_proc_entry("psched", net->proc_net);
}
#else
static int __net_init psched_net_init(struct net *net)
@@ -1761,22 +1911,23 @@ static int __init pktsched_init(void)
err = register_pernet_subsys(&psched_net_ops);
if (err) {
- printk(KERN_ERR "pktsched_init: "
+ pr_err("pktsched_init: "
"cannot initialize per netns operations\n");
return err;
}
+ register_qdisc(&pfifo_fast_ops);
register_qdisc(&pfifo_qdisc_ops);
register_qdisc(&bfifo_qdisc_ops);
register_qdisc(&pfifo_head_drop_qdisc_ops);
register_qdisc(&mq_qdisc_ops);
- rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL);
- rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc);
- rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL);
- rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL);
- rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass);
+ rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, NULL);
+ rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, NULL);
+ rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, NULL);
return 0;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 21:53:09 +0000