From: John Fastabend <john.fastabend@gmail.com>
To: xiyou.wangcong@gmail.com, davem@davemloft.net,
eric.dumazet@gmail.com, jhs@mojatatu.com
Cc: netdev@vger.kernel.org, paulmck@linux.vnet.ibm.com, brouer@redhat.com
Subject: [net-next PATCH v3 05/15] net: sched: cls_flow use RCU
Date: Mon, 08 Sep 2014 22:56:08 -0700 [thread overview]
Message-ID: <20140909055601.2071.43459.stgit@nitbit.x32> (raw)
In-Reply-To: <20140909055221.2071.99671.stgit@nitbit.x32>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
net/sched/cls_flow.c | 145 +++++++++++++++++++++++++++++---------------------
1 file changed, 84 insertions(+), 61 deletions(-)
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 35be16f..e33560b 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -34,12 +34,15 @@
struct flow_head {
struct list_head filters;
+ struct rcu_head rcu;
};
struct flow_filter {
struct list_head list;
+ struct rcu_head rcu;
struct tcf_exts exts;
struct tcf_ematch_tree ematches;
+ struct tcf_proto *tp;
struct timer_list perturb_timer;
u32 perturb_period;
u32 handle;
@@ -276,14 +279,14 @@ static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow)
static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
- struct flow_head *head = tp->root;
+ struct flow_head *head = rcu_dereference_bh(tp->root);
struct flow_filter *f;
u32 keymask;
u32 classid;
unsigned int n, key;
int r;
- list_for_each_entry(f, &head->filters, list) {
+ list_for_each_entry_rcu(f, &head->filters, list) {
u32 keys[FLOW_KEY_MAX + 1];
struct flow_keys flow_keys;
@@ -346,13 +349,23 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = {
[TCA_FLOW_PERTURB] = { .type = NLA_U32 },
};
+static void flow_destroy_filter(struct rcu_head *head)
+{
+ struct flow_filter *f = container_of(head, struct flow_filter, rcu);
+
+ del_timer_sync(&f->perturb_timer);
+ tcf_exts_destroy(f->tp, &f->exts);
+ tcf_em_tree_destroy(f->tp, &f->ematches);
+ kfree(f);
+}
+
static int flow_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
unsigned long *arg, bool ovr)
{
- struct flow_head *head = tp->root;
- struct flow_filter *f;
+ struct flow_head *head = rtnl_dereference(tp->root);
+ struct flow_filter *fold, *fnew;
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_FLOW_MAX + 1];
struct tcf_exts e;
@@ -401,20 +414,42 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
if (err < 0)
goto err1;
- f = (struct flow_filter *)*arg;
- if (f != NULL) {
+ err = -ENOBUFS;
+ fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
+ if (!fnew)
+ goto err2;
+
+ fold = (struct flow_filter *)*arg;
+ if (fold) {
err = -EINVAL;
- if (f->handle != handle && handle)
+ if (fold->handle != handle && handle)
goto err2;
- mode = f->mode;
+ /* Copy fold into fnew */
+ fnew->handle = fold->handle;
+ fnew->keymask = fold->keymask;
+ fnew->tp = fold->tp;
+
+ fnew->handle = fold->handle;
+ fnew->nkeys = fold->nkeys;
+ fnew->keymask = fold->keymask;
+ fnew->mode = fold->mode;
+ fnew->mask = fold->mask;
+ fnew->xor = fold->xor;
+ fnew->rshift = fold->rshift;
+ fnew->addend = fold->addend;
+ fnew->divisor = fold->divisor;
+ fnew->baseclass = fold->baseclass;
+ fnew->hashrnd = fold->hashrnd;
+
+ mode = fold->mode;
if (tb[TCA_FLOW_MODE])
mode = nla_get_u32(tb[TCA_FLOW_MODE]);
if (mode != FLOW_MODE_HASH && nkeys > 1)
goto err2;
if (mode == FLOW_MODE_HASH)
- perturb_period = f->perturb_period;
+ perturb_period = fold->perturb_period;
if (tb[TCA_FLOW_PERTURB]) {
if (mode != FLOW_MODE_HASH)
goto err2;
@@ -444,83 +479,70 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
if (TC_H_MIN(baseclass) == 0)
baseclass = TC_H_MAKE(baseclass, 1);
- err = -ENOBUFS;
- f = kzalloc(sizeof(*f), GFP_KERNEL);
- if (f == NULL)
- goto err2;
-
- f->handle = handle;
- f->mask = ~0U;
- tcf_exts_init(&f->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
-
- get_random_bytes(&f->hashrnd, 4);
- f->perturb_timer.function = flow_perturbation;
- f->perturb_timer.data = (unsigned long)f;
- init_timer_deferrable(&f->perturb_timer);
+ fnew->handle = handle;
+ fnew->mask = ~0U;
+ fnew->tp = tp;
+ get_random_bytes(&fnew->hashrnd, 4);
+ tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
}
- tcf_exts_change(tp, &f->exts, &e);
- tcf_em_tree_change(tp, &f->ematches, &t);
+ fnew->perturb_timer.function = flow_perturbation;
+ fnew->perturb_timer.data = (unsigned long)fnew;
+ init_timer_deferrable(&fnew->perturb_timer);
- tcf_tree_lock(tp);
+ tcf_exts_change(tp, &fnew->exts, &e);
+ tcf_em_tree_change(tp, &fnew->ematches, &t);
if (tb[TCA_FLOW_KEYS]) {
- f->keymask = keymask;
- f->nkeys = nkeys;
+ fnew->keymask = keymask;
+ fnew->nkeys = nkeys;
}
- f->mode = mode;
+ fnew->mode = mode;
if (tb[TCA_FLOW_MASK])
- f->mask = nla_get_u32(tb[TCA_FLOW_MASK]);
+ fnew->mask = nla_get_u32(tb[TCA_FLOW_MASK]);
if (tb[TCA_FLOW_XOR])
- f->xor = nla_get_u32(tb[TCA_FLOW_XOR]);
+ fnew->xor = nla_get_u32(tb[TCA_FLOW_XOR]);
if (tb[TCA_FLOW_RSHIFT])
- f->rshift = nla_get_u32(tb[TCA_FLOW_RSHIFT]);
+ fnew->rshift = nla_get_u32(tb[TCA_FLOW_RSHIFT]);
if (tb[TCA_FLOW_ADDEND])
- f->addend = nla_get_u32(tb[TCA_FLOW_ADDEND]);
+ fnew->addend = nla_get_u32(tb[TCA_FLOW_ADDEND]);
if (tb[TCA_FLOW_DIVISOR])
- f->divisor = nla_get_u32(tb[TCA_FLOW_DIVISOR]);
+ fnew->divisor = nla_get_u32(tb[TCA_FLOW_DIVISOR]);
if (baseclass)
- f->baseclass = baseclass;
+ fnew->baseclass = baseclass;
- f->perturb_period = perturb_period;
- del_timer(&f->perturb_timer);
+ fnew->perturb_period = perturb_period;
if (perturb_period)
- mod_timer(&f->perturb_timer, jiffies + perturb_period);
+ mod_timer(&fnew->perturb_timer, jiffies + perturb_period);
if (*arg == 0)
- list_add_tail(&f->list, &head->filters);
+ list_add_tail_rcu(&fnew->list, &head->filters);
+ else
+ list_replace_rcu(&fnew->list, &fold->list);
- tcf_tree_unlock(tp);
+ *arg = (unsigned long)fnew;
- *arg = (unsigned long)f;
+ if (fold)
+ call_rcu(&fold->rcu, flow_destroy_filter);
return 0;
err2:
tcf_em_tree_destroy(tp, &t);
+ kfree(fnew);
err1:
tcf_exts_destroy(tp, &e);
return err;
}
-static void flow_destroy_filter(struct tcf_proto *tp, struct flow_filter *f)
-{
- del_timer_sync(&f->perturb_timer);
- tcf_exts_destroy(tp, &f->exts);
- tcf_em_tree_destroy(tp, &f->ematches);
- kfree(f);
-}
-
static int flow_delete(struct tcf_proto *tp, unsigned long arg)
{
struct flow_filter *f = (struct flow_filter *)arg;
- tcf_tree_lock(tp);
- list_del(&f->list);
- tcf_tree_unlock(tp);
- flow_destroy_filter(tp, f);
+ list_del_rcu(&f->list);
+ call_rcu(&f->rcu, flow_destroy_filter);
return 0;
}
@@ -532,28 +554,29 @@ static int flow_init(struct tcf_proto *tp)
if (head == NULL)
return -ENOBUFS;
INIT_LIST_HEAD(&head->filters);
- tp->root = head;
+ rcu_assign_pointer(tp->root, head);
return 0;
}
static void flow_destroy(struct tcf_proto *tp)
{
- struct flow_head *head = tp->root;
+ struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *f, *next;
list_for_each_entry_safe(f, next, &head->filters, list) {
- list_del(&f->list);
- flow_destroy_filter(tp, f);
+ list_del_rcu(&f->list);
+ call_rcu(&f->rcu, flow_destroy_filter);
}
- kfree(head);
+ RCU_INIT_POINTER(tp->root, NULL);
+ kfree_rcu(head, rcu);
}
static unsigned long flow_get(struct tcf_proto *tp, u32 handle)
{
- struct flow_head *head = tp->root;
+ struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *f;
- list_for_each_entry(f, &head->filters, list)
+ list_for_each_entry_rcu(f, &head->filters, list)
if (f->handle == handle)
return (unsigned long)f;
return 0;
@@ -626,10 +649,10 @@ nla_put_failure:
static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
- struct flow_head *head = tp->root;
+ struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *f;
- list_for_each_entry(f, &head->filters, list) {
+ list_for_each_entry_rcu(f, &head->filters, list) {
if (arg->count < arg->skip)
goto skip;
if (arg->fn(tp, (unsigned long)f, arg) < 0) {
next prev parent reply other threads:[~2014-09-09 5:56 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-09 5:53 [net-next PATCH v3 00/15] net/sched use rcu filters John Fastabend
2014-09-09 5:54 ` [net-next PATCH v3 01/15] net: qdisc: use rcu prefix and silence sparse warnings John Fastabend
2014-09-09 12:05 ` Eric Dumazet
2014-09-09 5:54 ` [net-next PATCH v3 02/15] net: rcu-ify tcf_proto John Fastabend
2014-09-09 12:20 ` Eric Dumazet
2014-09-09 15:15 ` John Fastabend
2014-09-09 15:20 ` Eric Dumazet
2014-09-09 5:55 ` [net-next PATCH v3 03/15] net: sched: cls_basic use RCU John Fastabend
2014-09-09 12:29 ` Eric Dumazet
2014-09-09 5:55 ` [net-next PATCH v3 04/15] net: sched: cls_cgroup " John Fastabend
2014-09-09 12:34 ` Eric Dumazet
2014-09-09 5:56 ` John Fastabend [this message]
2014-09-09 12:41 ` [net-next PATCH v3 05/15] net: sched: cls_flow " Eric Dumazet
2014-09-09 16:09 ` John Fastabend
2014-09-09 16:20 ` Eric Dumazet
2014-09-09 5:56 ` [net-next PATCH v3 06/15] net: sched: fw " John Fastabend
2014-09-09 12:48 ` Eric Dumazet
2014-09-09 5:57 ` [net-next PATCH v3 07/15] net: sched: RCU cls_route John Fastabend
2014-09-09 12:59 ` Eric Dumazet
2014-09-09 16:24 ` John Fastabend
2014-09-09 5:57 ` [net-next PATCH v3 08/15] net: sched: RCU cls_tcindex John Fastabend
2014-09-09 5:58 ` [net-next PATCH v3 09/15] net: sched: make cls_u32 lockless John Fastabend
2014-09-09 13:20 ` Eric Dumazet
2014-09-09 16:35 ` John Fastabend
2014-09-09 18:02 ` Cong Wang
2014-09-10 4:53 ` John Fastabend
2014-09-09 5:58 ` [net-next PATCH v3 10/15] net: sched: rcu'ify cls_rsvp John Fastabend
2014-09-09 13:27 ` Eric Dumazet
2014-09-09 16:46 ` John Fastabend
2014-09-09 5:59 ` [net-next PATCH v3 11/15] net: sched: rcu'ify cls_bpf John Fastabend
2014-09-09 5:59 ` [net-next PATCH v3 12/15] net: sched: make tc_action safe to walk under RCU John Fastabend
2014-09-09 6:00 ` [net-next PATCH v3 13/15] net: sched: make bstats per cpu and estimator RCU safe John Fastabend
2014-09-09 6:00 ` [net-next PATCH v3 14/15] net: sched: make qstats per cpu John Fastabend
2014-09-09 6:01 ` [net-next PATCH v3 15/15] net: sched: drop ingress qdisc lock John Fastabend
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140909055601.2071.43459.stgit@nitbit.x32 \
--to=john.fastabend@gmail.com \
--cc=brouer@redhat.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=jhs@mojatatu.com \
--cc=netdev@vger.kernel.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=xiyou.wangcong@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.