| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20140110094241.7193.14386.stgit@nitbit.x32>
Date: Fri, 10 Jan 2014 01:42:43 -0800
From: John Fastabend <john.fastabend@...il.com>
To: xiyou.wangcong@...il.com, jhs@...atatu.com, eric.dumazet@...il.com
Cc: netdev@...r.kernel.org, davem@...emloft.net
Subject: [RFC PATCH 09/12] net: sched: make cls_u32 lockless
Make cls_u32 classifier safe to run without holding lock. This patch
converts statistics that are kept in read section u32_classify into
per cpu counters.
This patch needs careful review to be sure the internal data
structures are being handled. With regards to testing simply creating
a u32 filter is not enough the actual structure need to be created
and destroyed under stress for a valid test case.
Signed-off-by: John Fastabend <john.r.fastabend@...el.com>
---
net/sched/cls_u32.c | 258 +++++++++++++++++++++++++++++++++------------------
1 file changed, 169 insertions(+), 89 deletions(-)
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 20f2fb7..1d68d08 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -36,6 +36,7 @@
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
+#include <linux/percpu.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
@@ -43,40 +44,46 @@
#include <net/pkt_cls.h>
struct tc_u_knode {
- struct tc_u_knode *next;
+ struct tc_u_knode __rcu *next;
u32 handle;
- struct tc_u_hnode *ht_up;
+ struct tc_u_hnode __rcu *ht_up;
struct tcf_exts exts;
#ifdef CONFIG_NET_CLS_IND
char indev[IFNAMSIZ];
#endif
u8 fshift;
struct tcf_result res;
- struct tc_u_hnode *ht_down;
+ struct tc_u_hnode __rcu *ht_down;
#ifdef CONFIG_CLS_U32_PERF
- struct tc_u32_pcnt *pf;
+ struct tc_u32_pcnt __percpu *pf;
#endif
#ifdef CONFIG_CLS_U32_MARK
- struct tc_u32_mark mark;
+ u32 val;
+ u32 mask;
+ u32 __percpu *pcpu_success;
#endif
+ struct tcf_proto *tp;
+ struct rcu_head rcu;
struct tc_u32_sel sel;
};
struct tc_u_hnode {
- struct tc_u_hnode *next;
+ struct tc_u_hnode __rcu *next;
u32 handle;
u32 prio;
struct tc_u_common *tp_c;
int refcnt;
unsigned int divisor;
- struct tc_u_knode *ht[1];
+ struct tc_u_knode __rcu *ht[1];
+ struct rcu_head rcu;
};
struct tc_u_common {
- struct tc_u_hnode *hlist;
+ struct tc_u_hnode __rcu *hlist;
struct Qdisc *q;
int refcnt;
u32 hgenerator;
+ struct rcu_head rcu;
};
static inline unsigned int u32_hash_fold(__be32 key,
@@ -95,7 +102,7 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct
unsigned int off;
} stack[TC_U32_MAXDEPTH];
- struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root;
+ struct tc_u_hnode *ht = (struct tc_u_hnode *) rcu_dereference_bh(tp->root);
unsigned int off = skb_network_offset(skb);
struct tc_u_knode *n;
int sdepth = 0;
@@ -103,27 +110,31 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct
int sel = 0;
#ifdef CONFIG_CLS_U32_PERF
int j;
+ struct tc_u32_pcnt *pf;
#endif
int i, r;
next_ht:
- n = ht->ht[sel];
+ n = rcu_dereference_bh(ht->ht[sel]);
next_knode:
if (n) {
struct tc_u32_key *key = n->sel.keys;
#ifdef CONFIG_CLS_U32_PERF
- n->pf->rcnt += 1;
+ pf = this_cpu_ptr(n->pf);
+ pf->rcnt += 1;
j = 0;
#endif
#ifdef CONFIG_CLS_U32_MARK
- if ((skb->mark & n->mark.mask) != n->mark.val) {
- n = n->next;
+ if ((skb->mark & n->mask) != n->val) {
+ n = rcu_dereference_bh(n->next);
goto next_knode;
} else {
- n->mark.success++;
+ u32 *success = this_cpu_ptr(n->pcpu_success);
+
+ *success = *success + 1;
}
#endif
@@ -138,37 +149,41 @@ next_knode:
if (!data)
goto out;
if ((*data ^ key->val) & key->mask) {
- n = n->next;
+ n = rcu_dereference_bh(n->next);
goto next_knode;
}
#ifdef CONFIG_CLS_U32_PERF
- n->pf->kcnts[j] += 1;
+ pf = this_cpu_ptr(n->pf);
+ pf->kcnts[j] += 1;
j++;
#endif
}
- if (n->ht_down == NULL) {
+
+ ht = rcu_dereference_bh(n->ht_down);
+ if (!ht) {
check_terminal:
if (n->sel.flags & TC_U32_TERMINAL) {
*res = n->res;
#ifdef CONFIG_NET_CLS_IND
if (!tcf_match_indev(skb, n->indev)) {
- n = n->next;
+ n = rcu_dereference_bh(n->next);
goto next_knode;
}
#endif
#ifdef CONFIG_CLS_U32_PERF
- n->pf->rhit += 1;
+ pf = this_cpu_ptr(n->pf);
+ pf->rhit += 1;
#endif
r = tcf_exts_exec(skb, &n->exts, res);
if (r < 0) {
- n = n->next;
+ n = rcu_dereference_bh(n->next);
goto next_knode;
}
return r;
}
- n = n->next;
+ n = rcu_dereference_bh(n->next);
goto next_knode;
}
@@ -179,7 +194,7 @@ check_terminal:
stack[sdepth].off = off;
sdepth++;
- ht = n->ht_down;
+ ht = rcu_dereference_bh(n->ht_down);
sel = 0;
if (ht->divisor) {
__be32 *data, hdata;
@@ -221,7 +236,7 @@ check_terminal:
/* POP */
if (sdepth--) {
n = stack[sdepth].knode;
- ht = n->ht_up;
+ ht = rcu_dereference_bh(n->ht_up);
off = stack[sdepth].off;
goto check_terminal;
}
@@ -238,7 +253,9 @@ u32_lookup_ht(struct tc_u_common *tp_c, u32 handle)
{
struct tc_u_hnode *ht;
- for (ht = tp_c->hlist; ht; ht = ht->next)
+ for (ht = rtnl_dereference(tp_c->hlist);
+ ht;
+ ht = rtnl_dereference(ht->next))
if (ht->handle == handle)
break;
@@ -255,7 +272,9 @@ u32_lookup_key(struct tc_u_hnode *ht, u32 handle)
if (sel > ht->divisor)
goto out;
- for (n = ht->ht[sel]; n; n = n->next)
+ for (n = rtnl_dereference(ht->ht[sel]);
+ n;
+ n = rtnl_dereference(n->next))
if (n->handle == handle)
break;
out:
@@ -269,7 +288,7 @@ static unsigned long u32_get(struct tcf_proto *tp, u32 handle)
struct tc_u_common *tp_c = tp->data;
if (TC_U32_HTID(handle) == TC_U32_ROOT)
- ht = tp->root;
+ ht = rtnl_dereference(tp->root);
else
ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle));
@@ -290,6 +309,9 @@ static u32 gen_new_htid(struct tc_u_common *tp_c)
{
int i = 0x800;
+ /* hgenerator only used inside rtnl lock it is safe to increment
+ * without read _copy_ update semantics
+ */
do {
if (++tp_c->hgenerator == 0x7FF)
tp_c->hgenerator = 1;
@@ -325,11 +347,11 @@ static int u32_init(struct tcf_proto *tp)
}
tp_c->refcnt++;
- root_ht->next = tp_c->hlist;
- tp_c->hlist = root_ht;
+ rcu_assign_pointer(root_ht->next, tp_c->hlist);
+ rcu_assign_pointer(tp_c->hlist, root_ht);
root_ht->tp_c = tp_c;
- tp->root = root_ht;
+ rcu_assign_pointer(tp->root, root_ht);
tp->data = tp_c;
return 0;
}
@@ -341,25 +363,33 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n)
if (n->ht_down)
n->ht_down->refcnt--;
#ifdef CONFIG_CLS_U32_PERF
- kfree(n->pf);
+ free_percpu(n->pf);
#endif
kfree(n);
return 0;
}
+void __u32_delete_key(struct rcu_head *rcu)
+{
+ struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu);
+
+ u32_destroy_key(key->tp, key);
+}
+
static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
{
- struct tc_u_knode **kp;
+ struct tc_u_knode __rcu **kp;
+ struct tc_u_knode *pkp;
struct tc_u_hnode *ht = key->ht_up;
if (ht) {
- for (kp = &ht->ht[TC_U32_HASH(key->handle)]; *kp; kp = &(*kp)->next) {
- if (*kp == key) {
- tcf_tree_lock(tp);
- *kp = key->next;
- tcf_tree_unlock(tp);
+ kp = &ht->ht[TC_U32_HASH(key->handle)];
+ for (pkp = rtnl_dereference(*kp); pkp;
+ kp = &pkp->next, pkp = rtnl_dereference(*kp)) {
+ if (pkp == key) {
+ rcu_assign_pointer(*kp, key->next);
- u32_destroy_key(tp, key);
+ call_rcu(&key->rcu, __u32_delete_key);
return 0;
}
}
@@ -368,16 +398,15 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
return 0;
}
-static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
+static void u32_clear_hnode(struct tc_u_hnode *ht)
{
struct tc_u_knode *n;
unsigned int h;
for (h = 0; h <= ht->divisor; h++) {
- while ((n = ht->ht[h]) != NULL) {
- ht->ht[h] = n->next;
-
- u32_destroy_key(tp, n);
+ while ((n = rtnl_dereference(ht->ht[h])) != NULL) {
+ rcu_assign_pointer(ht->ht[h], rtnl_dereference(n->next));
+ call_rcu(&n->rcu, __u32_delete_key);
}
}
}
@@ -385,28 +414,31 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
{
struct tc_u_common *tp_c = tp->data;
- struct tc_u_hnode **hn;
+ struct tc_u_hnode __rcu **hn;
+ struct tc_u_hnode *phn;
WARN_ON(ht->refcnt);
- u32_clear_hnode(tp, ht);
+ u32_clear_hnode(ht);
- for (hn = &tp_c->hlist; *hn; hn = &(*hn)->next) {
- if (*hn == ht) {
- *hn = ht->next;
- kfree(ht);
+ hn = &tp_c->hlist;
+ for (phn = rtnl_dereference(*hn);
+ phn;
+ hn = &phn->next, phn = rtnl_dereference(*hn)) {
+ if (phn == ht) {
+ rcu_assign_pointer(*hn, ht->next);
+ kfree_rcu(ht, rcu);
return 0;
}
}
- WARN_ON(1);
return -ENOENT;
}
static void u32_destroy(struct tcf_proto *tp)
{
struct tc_u_common *tp_c = tp->data;
- struct tc_u_hnode *root_ht = tp->root;
+ struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
WARN_ON(root_ht == NULL);
@@ -418,17 +450,16 @@ static void u32_destroy(struct tcf_proto *tp)
tp->q->u32_node = NULL;
- for (ht = tp_c->hlist; ht; ht = ht->next) {
+ for (ht = rtnl_dereference(tp_c->hlist);
+ ht;
+ ht = rtnl_dereference(ht->next)) {
ht->refcnt--;
- u32_clear_hnode(tp, ht);
+ u32_clear_hnode(ht);
}
- while ((ht = tp_c->hlist) != NULL) {
- tp_c->hlist = ht->next;
-
- WARN_ON(ht->refcnt != 0);
-
- kfree(ht);
+ while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) {
+ rcu_assign_pointer(tp_c->hlist, ht->next);
+ kfree_rcu(ht, rcu);
}
kfree(tp_c);
@@ -440,6 +471,7 @@ static void u32_destroy(struct tcf_proto *tp)
static int u32_delete(struct tcf_proto *tp, unsigned long arg)
{
struct tc_u_hnode *ht = (struct tc_u_hnode *)arg;
+ struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
if (ht == NULL)
return 0;
@@ -447,7 +479,7 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg)
if (TC_U32_KEY(ht->handle))
return u32_delete_key(tp, (struct tc_u_knode *)ht);
- if (tp->root == ht)
+ if (root_ht == ht)
return -EINVAL;
if (ht->refcnt == 1) {
@@ -465,7 +497,9 @@ static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle)
struct tc_u_knode *n;
unsigned int i = 0x7FF;
- for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next)
+ for (n = rtnl_dereference(ht->ht[TC_U32_HASH(handle)]);
+ n;
+ n = rtnl_dereference(n->next))
if (i < TC_U32_NODE(n->handle))
i = TC_U32_NODE(n->handle);
i++;
@@ -512,10 +546,8 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
ht_down->refcnt++;
}
- tcf_tree_lock(tp);
- ht_old = n->ht_down;
- n->ht_down = ht_down;
- tcf_tree_unlock(tp);
+ ht_old = rtnl_dereference(n->ht_down);
+ rcu_assign_pointer(n->ht_down, ht_down);
if (ht_old)
ht_old->refcnt--;
@@ -527,6 +559,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
#ifdef CONFIG_NET_CLS_IND
if (tb[TCA_U32_INDEV]) {
+ /* TODO make this a pointer update */
err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV]);
if (err < 0)
goto errout;
@@ -590,8 +623,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
ht->divisor = divisor;
ht->handle = handle;
ht->prio = tp->prio;
- ht->next = tp_c->hlist;
- tp_c->hlist = ht;
+ rcu_assign_pointer(ht->next, tp_c->hlist);
+ rcu_assign_pointer(tp_c->hlist, ht);
*arg = (unsigned long)ht;
return 0;
}
@@ -599,7 +632,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
if (tb[TCA_U32_HASH]) {
htid = nla_get_u32(tb[TCA_U32_HASH]);
if (TC_U32_HTID(htid) == TC_U32_ROOT) {
- ht = tp->root;
+ ht = rtnl_dereference(tp->root);
htid = ht->handle;
} else {
ht = u32_lookup_ht(tp->data, TC_U32_HTID(htid));
@@ -607,7 +640,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return -EINVAL;
}
} else {
- ht = tp->root;
+ ht = rtnl_dereference(tp->root);
htid = ht->handle;
}
@@ -631,8 +664,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return -ENOBUFS;
#ifdef CONFIG_CLS_U32_PERF
- n->pf = kzalloc(sizeof(struct tc_u32_pcnt) + s->nkeys*sizeof(u64), GFP_KERNEL);
- if (n->pf == NULL) {
+ n->pf = __alloc_percpu(sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64),
+ __alignof__(struct tc_u32_pcnt));
+ if (!n->pf) {
kfree(n);
return -ENOBUFS;
}
@@ -643,34 +677,39 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
n->handle = handle;
n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE);
+ n->tp = tp;
#ifdef CONFIG_CLS_U32_MARK
+ n->pcpu_success = alloc_percpu(u32);
+
if (tb[TCA_U32_MARK]) {
struct tc_u32_mark *mark;
mark = nla_data(tb[TCA_U32_MARK]);
- memcpy(&n->mark, mark, sizeof(struct tc_u32_mark));
- n->mark.success = 0;
+ n->val = mark->val;
+ n->mask = mark->mask;
}
#endif
err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE]);
if (err == 0) {
- struct tc_u_knode **ins;
- for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next)
- if (TC_U32_NODE(handle) < TC_U32_NODE((*ins)->handle))
+ struct tc_u_knode __rcu **ins;
+ struct tc_u_knode *pins;
+
+ ins = &ht->ht[TC_U32_HASH(handle)];
+ for (pins = rtnl_dereference(*ins); pins;
+ ins = &pins->next, pins = rtnl_dereference(*ins))
+ if (TC_U32_NODE(handle) < TC_U32_NODE(pins->handle))
break;
- n->next = *ins;
- tcf_tree_lock(tp);
- *ins = n;
- tcf_tree_unlock(tp);
+ rcu_assign_pointer(n->next, pins);
+ rcu_assign_pointer(*ins, n);
*arg = (unsigned long)n;
return 0;
}
#ifdef CONFIG_CLS_U32_PERF
- kfree(n->pf);
+ free_percpu(n->pf);
#endif
kfree(n);
return err;
@@ -686,7 +725,9 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
if (arg->stop)
return;
- for (ht = tp_c->hlist; ht; ht = ht->next) {
+ for (ht = rtnl_dereference(tp_c->hlist);
+ ht;
+ ht = rtnl_dereference(ht->next)) {
if (ht->prio != tp->prio)
continue;
if (arg->count >= arg->skip) {
@@ -697,7 +738,9 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
}
arg->count++;
for (h = 0; h <= ht->divisor; h++) {
- for (n = ht->ht[h]; n; n = n->next) {
+ for (n = rtnl_dereference(ht->ht[h]);
+ n;
+ n = rtnl_dereference(n->next)) {
if (arg->count < arg->skip) {
arg->count++;
continue;
@@ -716,6 +759,7 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
struct tc_u_knode *n = (struct tc_u_knode *)fh;
+ struct tc_u_hnode *ht_up, *ht_down;
struct nlattr *nest;
if (n == NULL)
@@ -734,11 +778,18 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh,
if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor))
goto nla_put_failure;
} else {
+#ifdef CONFIG_CLS_U32_PERF
+ struct tc_u32_pcnt *gpf;
+#endif
+ int cpu;
+
if (nla_put(skb, TCA_U32_SEL,
sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key),
&n->sel))
goto nla_put_failure;
- if (n->ht_up) {
+
+ ht_up = rtnl_dereference(n->ht_up);
+ if (ht_up) {
u32 htid = n->handle & 0xFFFFF000;
if (nla_put_u32(skb, TCA_U32_HASH, htid))
goto nla_put_failure;
@@ -746,14 +797,24 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh,
if (n->res.classid &&
nla_put_u32(skb, TCA_U32_CLASSID, n->res.classid))
goto nla_put_failure;
- if (n->ht_down &&
- nla_put_u32(skb, TCA_U32_LINK, n->ht_down->handle))
+
+ ht_down = rtnl_dereference(n->ht_down);
+ if (ht_down &&
+ nla_put_u32(skb, TCA_U32_LINK, ht_down->handle))
goto nla_put_failure;
#ifdef CONFIG_CLS_U32_MARK
- if ((n->mark.val || n->mark.mask) &&
- nla_put(skb, TCA_U32_MARK, sizeof(n->mark), &n->mark))
- goto nla_put_failure;
+ if ((n->val || n->mask)) {
+ struct tc_u32_mark mark = {.val = n->val,
+ .mask = n->mask,
+ .success = 0};
+
+ for_each_possible_cpu(cpu)
+ mark.success += *per_cpu_ptr(n->pcpu_success, cpu);
+
+ if (nla_put(skb, TCA_U32_MARK, sizeof(mark), &mark))
+ goto nla_put_failure;
+ }
#endif
if (tcf_exts_dump(skb, &n->exts) < 0)
@@ -765,10 +826,29 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh,
goto nla_put_failure;
#endif
#ifdef CONFIG_CLS_U32_PERF
+ gpf = kzalloc(sizeof(struct tc_u32_pcnt) +
+ n->sel.nkeys * sizeof(u64),
+ GFP_KERNEL);
+ if (!gpf)
+ goto nla_put_failure;
+
+ for_each_possible_cpu(cpu) {
+ int i;
+ struct tc_u32_pcnt *pf = per_cpu_ptr(n->pf, cpu);
+
+ gpf->rcnt += pf->rcnt;
+ gpf->rhit += pf->rhit;
+ for (i = 0; i < n->sel.nkeys; i++)
+ gpf->kcnts[i] += pf->kcnts[i];
+ }
+
if (nla_put(skb, TCA_U32_PCNT,
sizeof(struct tc_u32_pcnt) + n->sel.nkeys*sizeof(u64),
- n->pf))
+ gpf)) {
+ kfree(gpf);
goto nla_put_failure;
+ }
+ kfree(gpf);
#endif
}
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists