Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Several cases of overlapping changes, except the packet scheduler
conflicts which deal with the addition of the free list parameter
to qdisc_enqueue().

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 73 insertions, 74 deletions

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f8c61d2a7963..47ec2305f920 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1122,7 +1122,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
                 nla_nest_end(skb, nest);
                 ret = skb->len;
         } else
-                nla_nest_cancel(skb, nest);
+                nlmsg_trim(skb, b);
 
         nlh->nlmsg_len = skb_tail_pointer(skb) - b;
         if (NETLINK_CB(cb->skb).portid && ret)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index b7fa96926c90..845ab5119c05 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -106,9 +106,9 @@ int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi)
 }
 EXPORT_SYMBOL_GPL(ife_get_meta_u16);
 
-int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval)
+int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
 {
-        mi->metaval = kmemdup(metaval, sizeof(u32), GFP_KERNEL);
+        mi->metaval = kmemdup(metaval, sizeof(u32), gfp);
         if (!mi->metaval)
                 return -ENOMEM;
 
@@ -116,9 +116,9 @@ int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval)
 }
 EXPORT_SYMBOL_GPL(ife_alloc_meta_u32);
 
-int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval)
+int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp)
 {
-        mi->metaval = kmemdup(metaval, sizeof(u16), GFP_KERNEL);
+        mi->metaval = kmemdup(metaval, sizeof(u16), gfp);
         if (!mi->metaval)
                 return -ENOMEM;
 
@@ -240,10 +240,10 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len)
 }
 
 /* called when adding new meta information
- * under ife->tcf_lock
+ * under ife->tcf_lock for existing action
 */
 static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
-                                void *val, int len)
+                                void *val, int len, bool exists)
 {
         struct tcf_meta_ops *ops = find_ife_oplist(metaid);
         int ret = 0;
@@ -251,11 +251,13 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
         if (!ops) {
                 ret = -ENOENT;
 #ifdef CONFIG_MODULES
-                spin_unlock_bh(&ife->tcf_lock);
+                if (exists)
+                        spin_unlock_bh(&ife->tcf_lock);
                 rtnl_unlock();
                 request_module("ifemeta%u", metaid);
                 rtnl_lock();
-                spin_lock_bh(&ife->tcf_lock);
+                if (exists)
+                        spin_lock_bh(&ife->tcf_lock);
                 ops = find_ife_oplist(metaid);
 #endif
         }
@@ -272,10 +274,10 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 }
 
 /* called when adding new meta information
- * under ife->tcf_lock
+ * under ife->tcf_lock for existing action
 */
 static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-                        int len)
+                        int len, bool atomic)
 {
         struct tcf_meta_info *mi = NULL;
         struct tcf_meta_ops *ops = find_ife_oplist(metaid);
@@ -284,7 +286,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
         if (!ops)
                 return -ENOENT;
 
-        mi = kzalloc(sizeof(*mi), GFP_KERNEL);
+        mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL);
         if (!mi) {
                 /*put back what find_ife_oplist took */
                 module_put(ops->owner);
@@ -294,7 +296,7 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
         mi->metaid = metaid;
         mi->ops = ops;
         if (len > 0) {
-                ret = ops->alloc(mi, metaval);
+                ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL);
                 if (ret != 0) {
                         kfree(mi);
                         module_put(ops->owner);
@@ -313,11 +315,13 @@ static int use_all_metadata(struct tcf_ife_info *ife)
         int rc = 0;
         int installed = 0;
 
+        read_lock(&ife_mod_lock);
         list_for_each_entry(o, &ifeoplist, list) {
-                rc = add_metainfo(ife, o->metaid, NULL, 0);
+                rc = add_metainfo(ife, o->metaid, NULL, 0, true);
                 if (rc == 0)
                         installed += 1;
         }
+        read_unlock(&ife_mod_lock);
 
         if (installed)
                 return 0;
@@ -385,8 +389,9 @@ static void tcf_ife_cleanup(struct tc_action *a, int bind)
         spin_unlock_bh(&ife->tcf_lock);
 }
 
-/* under ife->tcf_lock */
-static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb)
+/* under ife->tcf_lock for existing action */
+static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
+                             bool exists)
 {
         int len = 0;
         int rc = 0;
@@ -398,11 +403,11 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb)
                         val = nla_data(tb[i]);
                         len = nla_len(tb[i]);
 
-                        rc = load_metaops_and_vet(ife, i, val, len);
+                        rc = load_metaops_and_vet(ife, i, val, len, exists);
                         if (rc != 0)
                                 return rc;
 
-                        rc = add_metainfo(ife, i, val, len);
+                        rc = add_metainfo(ife, i, val, len, exists);
                         if (rc)
                                 return rc;
                 }
@@ -475,7 +480,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
                         saddr = nla_data(tb[TCA_IFE_SMAC]);
         }
 
-        spin_lock_bh(&ife->tcf_lock);
+        if (exists)
+                spin_lock_bh(&ife->tcf_lock);
         ife->tcf_action = parm->action;
 
         if (parm->flags & IFE_ENCODE) {
@@ -505,11 +511,12 @@ metadata_parse_err:
                         if (ret == ACT_P_CREATED)
                                 _tcf_ife_cleanup(a, bind);
 
-                        spin_unlock_bh(&ife->tcf_lock);
+                        if (exists)
+                                spin_unlock_bh(&ife->tcf_lock);
                         return err;
                 }
 
-                err = populate_metalist(ife, tb2);
+                err = populate_metalist(ife, tb2, exists);
                 if (err)
                         goto metadata_parse_err;
 
@@ -524,12 +531,14 @@ metadata_parse_err:
                         if (ret == ACT_P_CREATED)
                                 _tcf_ife_cleanup(a, bind);
 
-                        spin_unlock_bh(&ife->tcf_lock);
+                        if (exists)
+                                spin_unlock_bh(&ife->tcf_lock);
                         return err;
                 }
         }
 
-        spin_unlock_bh(&ife->tcf_lock);
+        if (exists)
+                spin_unlock_bh(&ife->tcf_lock);
 
         if (ret == ACT_P_CREATED)
                 tcf_hash_insert(tn, a);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 6148e323ed93..b8c50600697a 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -123,10 +123,13 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
         }
 
         td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
-        if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size)
+        if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
+                if (exists)
+                        tcf_hash_release(a, bind);
                 return -EINVAL;
+        }
 
-        if (!tcf_hash_check(tn, index, a, bind)) {
+        if (!exists) {
                 ret = tcf_hash_create(tn, index, est, a, sizeof(*ipt), bind,
                                       false);
                 if (ret)
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 6ea0db427f91..baeed6a78d28 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -40,14 +40,18 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
                               struct sk_buff **to_free)
 {
+        unsigned int prev_backlog;
+
         if (likely(skb_queue_len(&sch->q) < sch->limit))
                 return qdisc_enqueue_tail(skb, sch);
 
+        prev_backlog = sch->qstats.backlog;
         /* queue full, remove one skb to fulfill the limit */
         __qdisc_queue_drop_head(sch, &sch->q, to_free);
         qdisc_qstats_drop(sch);
         qdisc_enqueue_tail(skb, sch);
 
+        qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog);
         return NET_XMIT_CN;
 }
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index ba098f2654b4..91982d9784b3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -984,7 +984,9 @@ static void htb_work_func(struct work_struct *work)
         struct htb_sched *q = container_of(work, struct htb_sched, work);
         struct Qdisc *sch = q->watchdog.qdisc;
 
+        rcu_read_lock();
         __netif_schedule(qdisc_root(sch));
+        rcu_read_unlock();
 }
 
 static int htb_init(struct Qdisc *sch, struct nlattr *opt)
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 6eac3d880048..aaaf02175338 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -621,17 +621,17 @@ deliver:
 #endif
 
                         if (q->qdisc) {
+                                unsigned int pkt_len = qdisc_pkt_len(skb);
                                 struct sk_buff *to_free = NULL;
                                 int err;
 
                                 err = qdisc_enqueue(skb, q->qdisc, &to_free);
                                 kfree_skb_list(to_free);
-                                if (unlikely(err != NET_XMIT_SUCCESS)) {
-                                        if (net_xmit_drop_count(err)) {
-                                                qdisc_qstats_drop(sch);
-                                                qdisc_tree_reduce_backlog(sch, 1,
-                                                                          qdisc_pkt_len(skb));
-                                        }
+                                if (err != NET_XMIT_SUCCESS &&
+                                    net_xmit_drop_count(err)) {
+                                        qdisc_qstats_drop(sch);
+                                        qdisc_tree_reduce_backlog(sch, 1,
+                                                                  pkt_len);
                                 }
                                 goto tfifo_dequeue;
                         }
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index f4d443aeae54..8f575899adfa 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -153,8 +153,9 @@ prio_destroy(struct Qdisc *sch)
 static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 {
         struct prio_sched_data *q = qdisc_priv(sch);
+        struct Qdisc *queues[TCQ_PRIO_BANDS];
+        int oldbands = q->bands, i;
         struct tc_prio_qopt *qopt;
-        int i;
 
         if (nla_len(opt) < sizeof(*qopt))
                 return -EINVAL;
@@ -168,62 +169,42 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
                         return -EINVAL;
         }
 
+        /* Before commit, make sure we can allocate all new qdiscs */
+        for (i = oldbands; i < qopt->bands; i++) {
+                queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+                                              TC_H_MAKE(sch->handle, i + 1));
+                if (!queues[i]) {
+                        while (i > oldbands)
+                                qdisc_destroy(queues[--i]);
+                        return -ENOMEM;
+                }
+        }
+
         sch_tree_lock(sch);
         q->bands = qopt->bands;
         memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
 
-        for (i = q->bands; i < TCQ_PRIO_BANDS; i++) {
+        for (i = q->bands; i < oldbands; i++) {
                 struct Qdisc *child = q->queues[i];
-                q->queues[i] = &noop_qdisc;
-                if (child != &noop_qdisc) {
-                        qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
-                        qdisc_destroy(child);
-                }
-        }
-        sch_tree_unlock(sch);
 
-        for (i = 0; i < q->bands; i++) {
-                if (q->queues[i] == &noop_qdisc) {
-                        struct Qdisc *child, *old;
-
-                        child = qdisc_create_dflt(sch->dev_queue,
-                                                  &pfifo_qdisc_ops,
-                                                  TC_H_MAKE(sch->handle, i + 1));
-                        if (child) {
-                                sch_tree_lock(sch);
-                                old = q->queues[i];
-                                q->queues[i] = child;
-
-                                if (old != &noop_qdisc) {
-                                        qdisc_tree_reduce_backlog(old,
-                                                                  old->q.qlen,
-                                                                  old->qstats.backlog);
-                                        qdisc_destroy(old);
-                                }
-                                sch_tree_unlock(sch);
-                        }
-                }
+                qdisc_tree_reduce_backlog(child, child->q.qlen,
+                                          child->qstats.backlog);
+                qdisc_destroy(child);
         }
+
+        for (i = oldbands; i < q->bands; i++)
+                q->queues[i] = queues[i];
+
+        sch_tree_unlock(sch);
         return 0;
 }
 
 static int prio_init(struct Qdisc *sch, struct nlattr *opt)
 {
-        struct prio_sched_data *q = qdisc_priv(sch);
-        int i;
-
-        for (i = 0; i < TCQ_PRIO_BANDS; i++)
-                q->queues[i] = &noop_qdisc;
-
-        if (opt == NULL) {
+        if (!opt)
                 return -EINVAL;
-        } else {
-                int err;
 
-                if ((err = prio_tune(sch, opt)) != 0)
-                        return err;
-        }
-        return 0;
+        return prio_tune(sch, opt);
 }
 
 static int prio_dump(struct Qdisc *sch, struct sk_buff *skb)