* [PATCH v4 net-next 01/19] ipv6: frag: remove unused field
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 02/19] inet: frags: change inet_frags_init_net() return value Eric Dumazet
` (18 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
csum field in struct frag_queue is not used, remove it.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/ipv6.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 50a6f0ddb8780f6c9169f4ae0b3b35af2d66cd4b..5c18836672e9d1c560cdce15f5b34928c337abfd 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -603,7 +603,6 @@ struct frag_queue {
struct in6_addr daddr;
int iif;
- unsigned int csum;
__u16 nhoffset;
u8 ecn;
};
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 02/19] inet: frags: change inet_frags_init_net() return value
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 01/19] ipv6: frag: remove unused field Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 03/19] inet: frags: add a pointer to struct netns_frags Eric Dumazet
` (17 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
We will soon initialize one rhashtable per struct netns_frags
in inet_frags_init_net().
This patch changes the return value to eventually propagate an
error.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 3 ++-
net/ieee802154/6lowpan/reassembly.c | 11 ++++++++---
net/ipv4/ip_fragment.c | 12 +++++++++---
net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++++++++---
net/ipv6/reassembly.c | 11 +++++++++--
5 files changed, 37 insertions(+), 12 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 351f0c3cdcd9df16078a40f07963fb605eeaa882..b1d62176f3b4fcf100bd263e8eae0db656a3d9b6 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -104,9 +104,10 @@ struct inet_frags {
int inet_frags_init(struct inet_frags *);
void inet_frags_fini(struct inet_frags *);
-static inline void inet_frags_init_net(struct netns_frags *nf)
+static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
+ return 0;
}
void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 85bf86ad6b1801066a4252af18b5b511070a9e08..2aaab4bba42961647a4d3d1c0b8497917d5065ce 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -581,14 +581,19 @@ static int __net_init lowpan_frags_init_net(struct net *net)
{
struct netns_ieee802154_lowpan *ieee802154_lowpan =
net_ieee802154_lowpan(net);
+ int res;
ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&ieee802154_lowpan->frags);
-
- return lowpan_frags_ns_sysctl_register(net);
+ res = inet_frags_init_net(&ieee802154_lowpan->frags);
+ if (res < 0)
+ return res;
+ res = lowpan_frags_ns_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ return res;
}
static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbf1b94942c0ed53d1ddb87e4ee63833c08f2684..e0b39d4ecbd411ff4bb72d1ed973e45bd6da9ef1 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -846,6 +846,8 @@ static void __init ip4_frags_ctl_register(void)
static int __net_init ipv4_frags_init_net(struct net *net)
{
+ int res;
+
/* Fragment cache limits.
*
* The fragment memory accounting code, (tries to) account for
@@ -871,9 +873,13 @@ static int __net_init ipv4_frags_init_net(struct net *net)
net->ipv4.frags.max_dist = 64;
- inet_frags_init_net(&net->ipv4.frags);
-
- return ip4_frags_ns_ctl_register(net);
+ res = inet_frags_init_net(&net->ipv4.frags);
+ if (res < 0)
+ return res;
+ res = ip4_frags_ns_ctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index b84ce3e6d728a5b8af65b91faf42ec640ff03910..6ff41569134ae36809a8b42d8e46d50d19ffde53 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -629,12 +629,18 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
static int nf_ct_net_init(struct net *net)
{
+ int res;
+
net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&net->nf_frag.frags);
-
- return nf_ct_frag6_sysctl_register(net);
+ res = inet_frags_init_net(&net->nf_frag.frags);
+ if (res < 0)
+ return res;
+ res = nf_ct_frag6_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ return res;
}
static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 08a139f14d0f6fa8ca326088cce1144411e09bf5..a8f7a5f0251a7af0b14cc6de5006b924d9d05672 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -711,13 +711,20 @@ static void ip6_frags_sysctl_unregister(void)
static int __net_init ipv6_frags_init_net(struct net *net)
{
+ int res;
+
net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
- inet_frags_init_net(&net->ipv6.frags);
+ res = inet_frags_init_net(&net->ipv6.frags);
+ if (res < 0)
+ return res;
- return ip6_frags_ns_sysctl_register(net);
+ res = ip6_frags_ns_sysctl_register(net);
+ if (res < 0)
+ inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ return res;
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 03/19] inet: frags: add a pointer to struct netns_frags
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 01/19] ipv6: frag: remove unused field Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 02/19] inet: frags: change inet_frags_init_net() return value Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 04/19] inet: frags: refactor ipv6_frag_init() Eric Dumazet
` (16 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In order to simplify the API, add a pointer to struct inet_frags.
This will allow us to make things less complex.
These functions no longer have a struct inet_frags parameter :
inet_frag_destroy(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frag_put(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frag_kill(struct inet_frag_queue *q /*, struct inet_frags *f */)
inet_frags_exit_net(struct netns_frags *nf /*, struct inet_frags *f */)
ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 11 ++++++-----
include/net/ipv6.h | 3 +--
net/ieee802154/6lowpan/reassembly.c | 13 +++++++------
net/ipv4/inet_fragment.c | 17 ++++++++++-------
net/ipv4/ip_fragment.c | 9 +++++----
net/ipv6/netfilter/nf_conntrack_reasm.c | 16 +++++++++-------
net/ipv6/reassembly.c | 20 ++++++++++----------
7 files changed, 48 insertions(+), 41 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index b1d62176f3b4fcf100bd263e8eae0db656a3d9b6..69e531ed81894393e07cac9e953825fcb55ef42a 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -10,6 +10,7 @@ struct netns_frags {
int high_thresh;
int low_thresh;
int max_dist;
+ struct inet_frags *f;
};
/**
@@ -109,20 +110,20 @@ static inline int inet_frags_init_net(struct netns_frags *nf)
atomic_set(&nf->mem, 0);
return 0;
}
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
+void inet_frags_exit_net(struct netns_frags *nf);
-void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f);
+void inet_frag_kill(struct inet_frag_queue *q);
+void inet_frag_destroy(struct inet_frag_queue *q);
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
struct inet_frags *f, void *key, unsigned int hash);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
-static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
+static inline void inet_frag_put(struct inet_frag_queue *q)
{
if (refcount_dec_and_test(&q->refcnt))
- inet_frag_destroy(q, f);
+ inet_frag_destroy(q);
}
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 5c18836672e9d1c560cdce15f5b34928c337abfd..57b7fe43d2ab8e0ef3d663b7a5ee201affd5ca1f 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -607,8 +607,7 @@ struct frag_queue {
u8 ecn;
};
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
- struct inet_frags *frags);
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
static inline bool ipv6_addr_any(const struct in6_addr *a)
{
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 2aaab4bba42961647a4d3d1c0b8497917d5065ce..6badc055555b7baedac2051a1aaea15f9e9b180c 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -94,10 +94,10 @@ static void lowpan_frag_expire(struct timer_list *t)
if (fq->q.flags & INET_FRAG_COMPLETE)
goto out;
- inet_frag_kill(&fq->q, &lowpan_frags);
+ inet_frag_kill(&fq->q);
out:
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &lowpan_frags);
+ inet_frag_put(&fq->q);
}
static inline struct lowpan_frag_queue *
@@ -230,7 +230,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
struct sk_buff *fp, *head = fq->q.fragments;
int sum_truesize;
- inet_frag_kill(&fq->q, &lowpan_frags);
+ inet_frag_kill(&fq->q);
/* Make the one we just received the head. */
if (prev) {
@@ -438,7 +438,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
ret = lowpan_frag_queue(fq, skb, frag_type);
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &lowpan_frags);
+ inet_frag_put(&fq->q);
return ret;
}
@@ -586,13 +586,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+ ieee802154_lowpan->frags.f = &lowpan_frags;
res = inet_frags_init_net(&ieee802154_lowpan->frags);
if (res < 0)
return res;
res = lowpan_frags_ns_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ inet_frags_exit_net(&ieee802154_lowpan->frags);
return res;
}
@@ -602,7 +603,7 @@ static void __net_exit lowpan_frags_exit_net(struct net *net)
net_ieee802154_lowpan(net);
lowpan_frags_ns_sysctl_unregister(net);
- inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+ inet_frags_exit_net(&ieee802154_lowpan->frags);
}
static struct pernet_operations lowpan_frags_ops = {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index e8ec28999f5ce0c5d496e9a97ca1748b18db0cf0..1ac69f65d0dee600d0ab4db20ff5942952932c40 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -219,8 +219,9 @@ void inet_frags_fini(struct inet_frags *f)
}
EXPORT_SYMBOL(inet_frags_fini);
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
+void inet_frags_exit_net(struct netns_frags *nf)
{
+ struct inet_frags *f =nf->f;
unsigned int seq;
int i;
@@ -264,33 +265,34 @@ __acquires(hb->chain_lock)
return hb;
}
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+static inline void fq_unlink(struct inet_frag_queue *fq)
{
struct inet_frag_bucket *hb;
- hb = get_frag_bucket_locked(fq, f);
+ hb = get_frag_bucket_locked(fq, fq->net->f);
hlist_del(&fq->list);
fq->flags |= INET_FRAG_COMPLETE;
spin_unlock(&hb->chain_lock);
}
-void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frag_kill(struct inet_frag_queue *fq)
{
if (del_timer(&fq->timer))
refcount_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq_unlink(fq, f);
+ fq_unlink(fq);
refcount_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
+void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
struct netns_frags *nf;
unsigned int sum, sum_truesize = 0;
+ struct inet_frags *f;
WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
WARN_ON(del_timer(&q->timer) != 0);
@@ -298,6 +300,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
/* Release all fragment data. */
fp = q->fragments;
nf = q->net;
+ f = nf->f;
while (fp) {
struct sk_buff *xp = fp->next;
@@ -333,7 +336,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
refcount_inc(&qp->refcnt);
spin_unlock(&hb->chain_lock);
qp_in->flags |= INET_FRAG_COMPLETE;
- inet_frag_put(qp_in, f);
+ inet_frag_put(qp_in);
return qp;
}
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index e0b39d4ecbd411ff4bb72d1ed973e45bd6da9ef1..cd2b4c9419fc1552d367b572926e314b11cb6c00 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -168,7 +168,7 @@ static void ip4_frag_free(struct inet_frag_queue *q)
static void ipq_put(struct ipq *ipq)
{
- inet_frag_put(&ipq->q, &ip4_frags);
+ inet_frag_put(&ipq->q);
}
/* Kill ipq entry. It is not destroyed immediately,
@@ -176,7 +176,7 @@ static void ipq_put(struct ipq *ipq)
*/
static void ipq_kill(struct ipq *ipq)
{
- inet_frag_kill(&ipq->q, &ip4_frags);
+ inet_frag_kill(&ipq->q);
}
static bool frag_expire_skip_icmp(u32 user)
@@ -872,20 +872,21 @@ static int __net_init ipv4_frags_init_net(struct net *net)
net->ipv4.frags.timeout = IP_FRAG_TIME;
net->ipv4.frags.max_dist = 64;
+ net->ipv4.frags.f = &ip4_frags;
res = inet_frags_init_net(&net->ipv4.frags);
if (res < 0)
return res;
res = ip4_frags_ns_ctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ inet_frags_exit_net(&net->ipv4.frags);
return res;
}
static void __net_exit ipv4_frags_exit_net(struct net *net)
{
ip4_frags_ns_ctl_unregister(net);
- inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+ inet_frags_exit_net(&net->ipv4.frags);
}
static struct pernet_operations ip4_frags_ops = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6ff41569134ae36809a8b42d8e46d50d19ffde53..c4b40fdee838300f3723cece1e6b5b9d03fa9249 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -178,7 +178,7 @@ static void nf_ct_frag6_expire(struct timer_list *t)
fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, nf_frag.frags);
- ip6_expire_frag_queue(net, fq, &nf_frags);
+ ip6_expire_frag_queue(net, fq);
}
/* Creation primitives. */
@@ -264,7 +264,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
* this case. -DaveM
*/
pr_debug("end of fragment not rounded to 8 bytes.\n");
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
return -EPROTO;
}
if (end > fq->q.len) {
@@ -357,7 +357,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
return 0;
discard_fq:
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
err:
return -EINVAL;
}
@@ -379,7 +379,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
int payload_len;
u8 ecn;
- inet_frag_kill(&fq->q, &nf_frags);
+ inet_frag_kill(&fq->q);
WARN_ON(head == NULL);
WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
@@ -622,7 +622,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
out_unlock:
spin_unlock_bh(&fq->q.lock);
- inet_frag_put(&fq->q, &nf_frags);
+ inet_frag_put(&fq->q);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
@@ -634,19 +634,21 @@ static int nf_ct_net_init(struct net *net)
net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
+ net->nf_frag.frags.f = &nf_frags;
+
res = inet_frags_init_net(&net->nf_frag.frags);
if (res < 0)
return res;
res = nf_ct_frag6_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ inet_frags_exit_net(&net->nf_frag.frags);
return res;
}
static void nf_ct_net_exit(struct net *net)
{
nf_ct_frags6_sysctl_unregister(net);
- inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+ inet_frags_exit_net(&net->nf_frag.frags);
}
static struct pernet_operations nf_ct_net_ops = {
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index a8f7a5f0251a7af0b14cc6de5006b924d9d05672..4855de6f673a4753526679ca29dcdaebecb5777f 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -128,8 +128,7 @@ void ip6_frag_init(struct inet_frag_queue *q, const void *a)
}
EXPORT_SYMBOL(ip6_frag_init);
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
- struct inet_frags *frags)
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
{
struct net_device *dev = NULL;
@@ -138,7 +137,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
if (fq->q.flags & INET_FRAG_COMPLETE)
goto out;
- inet_frag_kill(&fq->q, frags);
+ inet_frag_kill(&fq->q);
rcu_read_lock();
dev = dev_get_by_index_rcu(net, fq->iif);
@@ -166,7 +165,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
rcu_read_unlock();
out:
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, frags);
+ inet_frag_put(&fq->q);
}
EXPORT_SYMBOL(ip6_expire_frag_queue);
@@ -179,7 +178,7 @@ static void ip6_frag_expire(struct timer_list *t)
fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ipv6.frags);
- ip6_expire_frag_queue(net, fq, &ip6_frags);
+ ip6_expire_frag_queue(net, fq);
}
static struct frag_queue *
@@ -364,7 +363,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
return -1;
discard_fq:
- inet_frag_kill(&fq->q, &ip6_frags);
+ inet_frag_kill(&fq->q);
err:
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
@@ -391,7 +390,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
int sum_truesize;
u8 ecn;
- inet_frag_kill(&fq->q, &ip6_frags);
+ inet_frag_kill(&fq->q);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
@@ -569,7 +568,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q, &ip6_frags);
+ inet_frag_put(&fq->q);
return ret;
}
@@ -716,6 +715,7 @@ static int __net_init ipv6_frags_init_net(struct net *net)
net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+ net->ipv6.frags.f = &ip6_frags;
res = inet_frags_init_net(&net->ipv6.frags);
if (res < 0)
@@ -723,14 +723,14 @@ static int __net_init ipv6_frags_init_net(struct net *net)
res = ip6_frags_ns_sysctl_register(net);
if (res < 0)
- inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ inet_frags_exit_net(&net->ipv6.frags);
return res;
}
static void __net_exit ipv6_frags_exit_net(struct net *net)
{
ip6_frags_ns_sysctl_unregister(net);
- inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+ inet_frags_exit_net(&net->ipv6.frags);
}
static struct pernet_operations ip6_frags_ops = {
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 04/19] inet: frags: refactor ipv6_frag_init()
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (2 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 03/19] inet: frags: add a pointer to struct netns_frags Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 05/19] inet: frags: refactor lowpan_net_frag_init() Eric Dumazet
` (15 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
We want to call inet_frags_init() earlier.
This is a prereq to "inet: frags: use rhashtables for reassembly units"
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv6/reassembly.c | 27 +++++++++++++++------------
1 file changed, 15 insertions(+), 12 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 4855de6f673a4753526679ca29dcdaebecb5777f..f0071b113a92fcff15ac57610170c12b17cb59ba 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -742,18 +742,6 @@ int __init ipv6_frag_init(void)
{
int ret;
- ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
- if (ret)
- goto out;
-
- ret = ip6_frags_sysctl_register();
- if (ret)
- goto err_sysctl;
-
- ret = register_pernet_subsys(&ip6_frags_ops);
- if (ret)
- goto err_pernet;
-
ip6_frags.hashfn = ip6_hashfn;
ip6_frags.constructor = ip6_frag_init;
ip6_frags.destructor = NULL;
@@ -762,8 +750,21 @@ int __init ipv6_frag_init(void)
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.frags_cache_name = ip6_frag_cache_name;
ret = inet_frags_init(&ip6_frags);
+ if (ret)
+ goto out;
+
+ ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+ if (ret)
+ goto err_protocol;
+
+ ret = ip6_frags_sysctl_register();
+ if (ret)
+ goto err_sysctl;
+
+ ret = register_pernet_subsys(&ip6_frags_ops);
if (ret)
goto err_pernet;
+
out:
return ret;
@@ -771,6 +772,8 @@ int __init ipv6_frag_init(void)
ip6_frags_sysctl_unregister();
err_sysctl:
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+err_protocol:
+ inet_frags_fini(&ip6_frags);
goto out;
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 05/19] inet: frags: refactor lowpan_net_frag_init()
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (3 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 04/19] inet: frags: refactor ipv6_frag_init() Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 06/19] inet: frags: refactor ipfrag_init() Eric Dumazet
` (14 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
We want to call lowpan_net_frag_init() earlier.
Similar to commit "inet: frags: refactor ipv6_frag_init()"
This is a prereq to "inet: frags: use rhashtables for reassembly units"
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ieee802154/6lowpan/reassembly.c | 20 +++++++++++---------
1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 6badc055555b7baedac2051a1aaea15f9e9b180c..ddada12a044de293f904a1dc7a5ff398d089d101 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -615,14 +615,6 @@ int __init lowpan_net_frag_init(void)
{
int ret;
- ret = lowpan_frags_sysctl_register();
- if (ret)
- return ret;
-
- ret = register_pernet_subsys(&lowpan_frags_ops);
- if (ret)
- goto err_pernet;
-
lowpan_frags.hashfn = lowpan_hashfn;
lowpan_frags.constructor = lowpan_frag_init;
lowpan_frags.destructor = NULL;
@@ -631,12 +623,22 @@ int __init lowpan_net_frag_init(void)
lowpan_frags.frag_expire = lowpan_frag_expire;
lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
ret = inet_frags_init(&lowpan_frags);
+ if (ret)
+ goto out;
+
+ ret = lowpan_frags_sysctl_register();
+ if (ret)
+ goto err_sysctl;
+
+ ret = register_pernet_subsys(&lowpan_frags_ops);
if (ret)
goto err_pernet;
-
+out:
return ret;
err_pernet:
lowpan_frags_sysctl_unregister();
+err_sysctl:
+ inet_frags_fini(&lowpan_frags);
return ret;
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 06/19] inet: frags: refactor ipfrag_init()
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (4 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 05/19] inet: frags: refactor lowpan_net_frag_init() Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 07/19] rhashtable: add schedule points Eric Dumazet
` (13 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
We need to call inet_frags_init() before register_pernet_subsys(),
as a prereq for following patch ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/ip_fragment.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index cd2b4c9419fc1552d367b572926e314b11cb6c00..1a3bc85d6f5ea8f36b8f3d221cad632906b317a2 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -896,8 +896,6 @@ static struct pernet_operations ip4_frags_ops = {
void __init ipfrag_init(void)
{
- ip4_frags_ctl_register();
- register_pernet_subsys(&ip4_frags_ops);
ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
@@ -907,4 +905,6 @@ void __init ipfrag_init(void)
ip4_frags.frags_cache_name = ip_frag_cache_name;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
+ ip4_frags_ctl_register();
+ register_pernet_subsys(&ip4_frags_ops);
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 07/19] rhashtable: add schedule points
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (5 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 06/19] inet: frags: refactor ipfrag_init() Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 08/19] inet: frags: use rhashtables for reassembly units Eric Dumazet
` (12 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
Rehashing and destroying large hash table takes a lot of time,
and happens in process context. It is safe to add cond_resched()
in rhashtable_rehash_table() and rhashtable_free_and_destroy()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
---
lib/rhashtable.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 47de025b624520f75e521bef46dc9b28baa6a1a0..2b2b79974b614a94e5325e8c2271804cb27069aa 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -333,6 +333,7 @@ static int rhashtable_rehash_table(struct rhashtable *ht)
err = rhashtable_rehash_chain(ht, old_hash);
if (err)
return err;
+ cond_resched();
}
/* Publish the new table pointer. */
@@ -1112,6 +1113,7 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
for (i = 0; i < tbl->size; i++) {
struct rhash_head *pos, *next;
+ cond_resched();
for (pos = rht_dereference(*rht_bucket(tbl, i), ht),
next = !rht_is_a_nulls(pos) ?
rht_dereference(pos->next, ht) : NULL;
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 08/19] inet: frags: use rhashtables for reassembly units
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (6 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 07/19] rhashtable: add schedule points Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-04-16 12:54 ` Stefan Schmidt
2018-03-31 19:58 ` [PATCH v4 net-next 09/19] inet: frags: remove some helpers Eric Dumazet
` (11 subsequent siblings)
19 siblings, 1 reply; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
Some applications still rely on IP fragmentation, and to be fair linux
reassembly unit is not working under any serious load.
It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!)
A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.
This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.
Then there is the problem of sharing this hash table for all netns.
It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.
Lookup is now using RCU. A followup patch will even remove
the refcount hold/release left from prior implementation and save
a couple of atomic operations.
Before this patch, 16 cpus (16 RX queue NIC) could not handle more
than 1 Mpps frags DDOS.
After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB
of storage for the fragments (exact number depends on frags being evicted
after timeout)
$ grep FRAG /proc/net/sockstat
FRAG: inuse 1966916 memory 2140004608
A followup patch will change the limits for 64bit arches.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Florian Westphal <fw@strlen.de>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
---
Documentation/networking/ip-sysctl.txt | 7 +-
include/net/inet_frag.h | 81 +++---
include/net/ipv6.h | 16 +-
net/ieee802154/6lowpan/6lowpan_i.h | 26 +-
net/ieee802154/6lowpan/reassembly.c | 93 +++----
net/ipv4/inet_fragment.c | 354 +++++-------------------
net/ipv4/ip_fragment.c | 112 ++++----
net/ipv6/netfilter/nf_conntrack_reasm.c | 51 +---
net/ipv6/reassembly.c | 110 ++++----
9 files changed, 271 insertions(+), 579 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 33f35f049ad57ad6c06ed6e089966e346d72d108..6f2a3670e44b6662ce53c16cb7ca1e4f61274c15 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -134,13 +134,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
ipfrag_high_thresh - INTEGER
- Maximum memory used to reassemble IP fragments. When
- ipfrag_high_thresh bytes of memory is allocated for this purpose,
- the fragment handler will toss packets until ipfrag_low_thresh
- is reached. This also serves as a maximum limit to namespaces
- different from the initial one.
+ Maximum memory used to reassemble IP fragments.
ipfrag_low_thresh - INTEGER
+ (Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
The kernel still accepts new fragments for defragmentation.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 69e531ed81894393e07cac9e953825fcb55ef42a..3fec0d3a0d0186e98afb951784e1fe7329ba6d77 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -2,7 +2,11 @@
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
+#include <linux/rhashtable.h>
+
struct netns_frags {
+ struct rhashtable rhashtable ____cacheline_aligned_in_smp;
+
/* Keep atomic mem on separate cachelines in structs that include it */
atomic_t mem ____cacheline_aligned_in_smp;
/* sysctls */
@@ -26,12 +30,30 @@ enum {
INET_FRAG_COMPLETE = BIT(2),
};
+struct frag_v4_compare_key {
+ __be32 saddr;
+ __be32 daddr;
+ u32 user;
+ u32 vif;
+ __be16 id;
+ u16 protocol;
+};
+
+struct frag_v6_compare_key {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ u32 user;
+ __be32 id;
+ u32 iif;
+};
+
/**
* struct inet_frag_queue - fragment queue
*
- * @lock: spinlock protecting the queue
+ * @node: rhash node
+ * @key: keys identifying this frag.
* @timer: queue expiration timer
- * @list: hash bucket list
+ * @lock: spinlock protecting this frag
* @refcnt: reference count of the queue
* @fragments: received fragments head
* @fragments_tail: received fragments tail
@@ -41,12 +63,16 @@ enum {
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @net: namespace that this frag belongs to
- * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
+ * @rcu: rcu head for freeing deferall
*/
struct inet_frag_queue {
- spinlock_t lock;
+ struct rhash_head node;
+ union {
+ struct frag_v4_compare_key v4;
+ struct frag_v6_compare_key v6;
+ } key;
struct timer_list timer;
- struct hlist_node list;
+ spinlock_t lock;
refcount_t refcnt;
struct sk_buff *fragments;
struct sk_buff *fragments_tail;
@@ -55,51 +81,20 @@ struct inet_frag_queue {
int meat;
__u8 flags;
u16 max_size;
- struct netns_frags *net;
- struct hlist_node list_evictor;
-};
-
-#define INETFRAGS_HASHSZ 1024
-
-/* averaged:
- * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
- * rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
- * struct frag_queue))
- */
-#define INETFRAGS_MAXDEPTH 128
-
-struct inet_frag_bucket {
- struct hlist_head chain;
- spinlock_t chain_lock;
+ struct netns_frags *net;
+ struct rcu_head rcu;
};
struct inet_frags {
- struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
-
- struct work_struct frags_work;
- unsigned int next_bucket;
- unsigned long last_rebuild_jiffies;
- bool rebuild;
-
- /* The first call to hashfn is responsible to initialize
- * rnd. This is best done with net_get_random_once.
- *
- * rnd_seqlock is used to let hash insertion detect
- * when it needs to re-lookup the hash chain to use.
- */
- u32 rnd;
- seqlock_t rnd_seqlock;
unsigned int qsize;
- unsigned int (*hashfn)(const struct inet_frag_queue *);
- bool (*match)(const struct inet_frag_queue *q,
- const void *arg);
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
void (*frag_expire)(struct timer_list *t);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
+ struct rhashtable_params rhash_params;
};
int inet_frags_init(struct inet_frags *);
@@ -108,15 +103,13 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
- return 0;
+ return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key, unsigned int hash);
-
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
@@ -128,7 +121,7 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
{
- return !hlist_unhashed(&q->list_evictor);
+ return false;
}
/* Memory Tracking Functions. */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 57b7fe43d2ab8e0ef3d663b7a5ee201affd5ca1f..6fa9a2bc589665dfa9ce84813f33e5e86e12fd74 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -579,17 +579,8 @@ enum ip6_defrag_users {
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
};
-struct ip6_create_arg {
- __be32 id;
- u32 user;
- const struct in6_addr *src;
- const struct in6_addr *dst;
- int iif;
- u8 ecn;
-};
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
+extern const struct rhashtable_params ip6_rhash_params;
/*
* Equivalent of ipv4 struct ip
@@ -597,11 +588,6 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
struct frag_queue {
struct inet_frag_queue q;
- __be32 id; /* fragment id */
- u32 user;
- struct in6_addr saddr;
- struct in6_addr daddr;
-
int iif;
__u16 nhoffset;
u8 ecn;
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index d8de3bcfb1032a1133402cb2a4c50a2448133846..b8d95cb71c25dd69c8a88b2c886a3f0d2ce1174f 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -17,37 +17,19 @@ typedef unsigned __bitwise lowpan_rx_result;
#define LOWPAN_DISPATCH_FRAG1 0xc0
#define LOWPAN_DISPATCH_FRAGN 0xe0
-struct lowpan_create_arg {
+struct frag_lowpan_compare_key {
u16 tag;
u16 d_size;
- const struct ieee802154_addr *src;
- const struct ieee802154_addr *dst;
+ const struct ieee802154_addr src;
+ const struct ieee802154_addr dst;
};
-/* Equivalent of ipv4 struct ip
+/* Equivalent of ipv4 struct ipq
*/
struct lowpan_frag_queue {
struct inet_frag_queue q;
-
- u16 tag;
- u16 d_size;
- struct ieee802154_addr saddr;
- struct ieee802154_addr daddr;
};
-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
-{
- switch (a->mode) {
- case IEEE802154_ADDR_LONG:
- return (((__force u64)a->extended_addr) >> 32) ^
- (((__force u64)a->extended_addr) & 0xffffffff);
- case IEEE802154_ADDR_SHORT:
- return (__force u32)(a->short_addr + (a->pan_id << 16));
- default:
- return 0;
- }
-}
-
int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
void lowpan_net_frag_exit(void);
int lowpan_net_frag_init(void);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index ddada12a044de293f904a1dc7a5ff398d089d101..0fa0121f85d4531751566c26e18cc2a23c017da6 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
struct sk_buff *prev, struct net_device *ldev);
-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
- const struct ieee802154_addr *saddr,
- const struct ieee802154_addr *daddr)
-{
- net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
- return jhash_3words(ieee802154_addr_hash(saddr),
- ieee802154_addr_hash(daddr),
- (__force u32)(tag + (d_size << 16)),
- lowpan_frags.rnd);
-}
-
-static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
-{
- const struct lowpan_frag_queue *fq;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
-}
-
-static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct lowpan_frag_queue *fq;
- const struct lowpan_create_arg *arg = a;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return fq->tag == arg->tag && fq->d_size == arg->d_size &&
- ieee802154_addr_equal(&fq->saddr, arg->src) &&
- ieee802154_addr_equal(&fq->daddr, arg->dst);
-}
-
static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
{
- const struct lowpan_create_arg *arg = a;
+ const struct frag_lowpan_compare_key *key = a;
struct lowpan_frag_queue *fq;
fq = container_of(q, struct lowpan_frag_queue, q);
- fq->tag = arg->tag;
- fq->d_size = arg->d_size;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
+ BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
+ memcpy(&q->key, key, sizeof(*key));
}
static void lowpan_frag_expire(struct timer_list *t)
@@ -105,21 +73,17 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
const struct ieee802154_addr *src,
const struct ieee802154_addr *dst)
{
+ struct netns_ieee802154_lowpan *ieee802154_lowpan =
+ net_ieee802154_lowpan(net);
+ struct frag_lowpan_compare_key key = {
+ .tag = cb->d_tag,
+ .d_size = cb->d_size,
+ .src = *src,
+ .dst = *dst,
+ };
struct inet_frag_queue *q;
- struct lowpan_create_arg arg;
- unsigned int hash;
- struct netns_ieee802154_lowpan *ieee802154_lowpan =
- net_ieee802154_lowpan(net);
- arg.tag = cb->d_tag;
- arg.d_size = cb->d_size;
- arg.src = src;
- arg.dst = dst;
-
- hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
-
- q = inet_frag_find(&ieee802154_lowpan->frags,
- &lowpan_frags, &arg, hash);
+ q = inet_frag_find(&ieee802154_lowpan->frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -611,17 +575,46 @@ static struct pernet_operations lowpan_frags_ops = {
.exit = lowpan_frags_exit_net,
};
+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_lowpan_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params lowpan_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = lowpan_key_hashfn,
+ .obj_hashfn = lowpan_obj_hashfn,
+ .obj_cmpfn = lowpan_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
int __init lowpan_net_frag_init(void)
{
int ret;
- lowpan_frags.hashfn = lowpan_hashfn;
lowpan_frags.constructor = lowpan_frag_init;
lowpan_frags.destructor = NULL;
lowpan_frags.qsize = sizeof(struct frag_queue);
- lowpan_frags.match = lowpan_frag_match;
lowpan_frags.frag_expire = lowpan_frag_expire;
lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
+ lowpan_frags.rhash_params = lowpan_rhash_params;
ret = inet_frags_init(&lowpan_frags);
if (ret)
goto out;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 1ac69f65d0dee600d0ab4db20ff5942952932c40..ebb8f411e0db16478e861105b1926e97fbf07b06 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -25,12 +25,6 @@
#include <net/inet_frag.h>
#include <net/inet_ecn.h>
-#define INETFRAGS_EVICT_BUCKETS 128
-#define INETFRAGS_EVICT_MAX 512
-
-/* don't rebuild inetfrag table with new secret more often than this */
-#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
-
/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
* Value : 0xff if frame should be dropped.
* 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = {
};
EXPORT_SYMBOL(ip_frag_ecn_table);
-static unsigned int
-inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
-{
- return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
-}
-
-static bool inet_frag_may_rebuild(struct inet_frags *f)
-{
- return time_after(jiffies,
- f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
-}
-
-static void inet_frag_secret_rebuild(struct inet_frags *f)
-{
- int i;
-
- write_seqlock_bh(&f->rnd_seqlock);
-
- if (!inet_frag_may_rebuild(f))
- goto out;
-
- get_random_bytes(&f->rnd, sizeof(u32));
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- struct hlist_node *n;
-
- hb = &f->hash[i];
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(q, n, &hb->chain, list) {
- unsigned int hval = inet_frag_hashfn(f, q);
-
- if (hval != i) {
- struct inet_frag_bucket *hb_dest;
-
- hlist_del(&q->list);
-
- /* Relink to new hash chain. */
- hb_dest = &f->hash[hval];
-
- /* This is the only place where we take
- * another chain_lock while already holding
- * one. As this will not run concurrently,
- * we cannot deadlock on hb_dest lock below, if its
- * already locked it will be released soon since
- * other caller cannot be waiting for hb lock
- * that we've taken above.
- */
- spin_lock_nested(&hb_dest->chain_lock,
- SINGLE_DEPTH_NESTING);
- hlist_add_head(&q->list, &hb_dest->chain);
- spin_unlock(&hb_dest->chain_lock);
- }
- }
- spin_unlock(&hb->chain_lock);
- }
-
- f->rebuild = false;
- f->last_rebuild_jiffies = jiffies;
-out:
- write_sequnlock_bh(&f->rnd_seqlock);
-}
-
-static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
-{
- if (!hlist_unhashed(&q->list_evictor))
- return false;
-
- return q->net->low_thresh == 0 ||
- frag_mem_limit(q->net) >= q->net->low_thresh;
-}
-
-static unsigned int
-inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
-{
- struct inet_frag_queue *fq;
- struct hlist_node *n;
- unsigned int evicted = 0;
- HLIST_HEAD(expired);
-
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
- if (!inet_fragq_should_evict(fq))
- continue;
-
- if (!del_timer(&fq->timer))
- continue;
-
- hlist_add_head(&fq->list_evictor, &expired);
- ++evicted;
- }
-
- spin_unlock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
- f->frag_expire(&fq->timer);
-
- return evicted;
-}
-
-static void inet_frag_worker(struct work_struct *work)
-{
- unsigned int budget = INETFRAGS_EVICT_BUCKETS;
- unsigned int i, evicted = 0;
- struct inet_frags *f;
-
- f = container_of(work, struct inet_frags, frags_work);
-
- BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
-
- local_bh_disable();
-
- for (i = READ_ONCE(f->next_bucket); budget; --budget) {
- evicted += inet_evict_bucket(f, &f->hash[i]);
- i = (i + 1) & (INETFRAGS_HASHSZ - 1);
- if (evicted > INETFRAGS_EVICT_MAX)
- break;
- }
-
- f->next_bucket = i;
-
- local_bh_enable();
-
- if (f->rebuild && inet_frag_may_rebuild(f))
- inet_frag_secret_rebuild(f);
-}
-
-static void inet_frag_schedule_worker(struct inet_frags *f)
-{
- if (unlikely(!work_pending(&f->frags_work)))
- schedule_work(&f->frags_work);
-}
-
int inet_frags_init(struct inet_frags *f)
{
- int i;
-
- INIT_WORK(&f->frags_work, inet_frag_worker);
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb = &f->hash[i];
-
- spin_lock_init(&hb->chain_lock);
- INIT_HLIST_HEAD(&hb->chain);
- }
-
- seqlock_init(&f->rnd_seqlock);
- f->last_rebuild_jiffies = 0;
f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
NULL);
if (!f->frags_cachep)
@@ -214,79 +59,69 @@ EXPORT_SYMBOL(inet_frags_init);
void inet_frags_fini(struct inet_frags *f)
{
- cancel_work_sync(&f->frags_work);
+ /* We must wait that all inet_frag_destroy_rcu() have completed. */
+ rcu_barrier();
+
kmem_cache_destroy(f->frags_cachep);
+ f->frags_cachep = NULL;
}
EXPORT_SYMBOL(inet_frags_fini);
+static void inet_frags_free_cb(void *ptr, void *arg)
+{
+ struct inet_frag_queue *fq = ptr;
+
+ /* If we can not cancel the timer, it means this frag_queue
+ * is already disappearing, we have nothing to do.
+ * Otherwise, we own a refcount until the end of this function.
+ */
+ if (!del_timer(&fq->timer))
+ return;
+
+ spin_lock_bh(&fq->lock);
+ if (!(fq->flags & INET_FRAG_COMPLETE)) {
+ fq->flags |= INET_FRAG_COMPLETE;
+ refcount_dec(&fq->refcnt);
+ }
+ spin_unlock_bh(&fq->lock);
+
+ inet_frag_put(fq);
+}
+
void inet_frags_exit_net(struct netns_frags *nf)
{
- struct inet_frags *f =nf->f;
- unsigned int seq;
- int i;
+ nf->low_thresh = 0; /* prevent creation of new frags */
- nf->low_thresh = 0;
-
-evict_again:
- local_bh_disable();
- seq = read_seqbegin(&f->rnd_seqlock);
-
- for (i = 0; i < INETFRAGS_HASHSZ ; i++)
- inet_evict_bucket(f, &f->hash[i]);
-
- local_bh_enable();
- cond_resched();
-
- if (read_seqretry(&f->rnd_seqlock, seq) ||
- sum_frag_mem_limit(nf))
- goto evict_again;
+ rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
}
EXPORT_SYMBOL(inet_frags_exit_net);
-static struct inet_frag_bucket *
-get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
-__acquires(hb->chain_lock)
-{
- struct inet_frag_bucket *hb;
- unsigned int seq, hash;
-
- restart:
- seq = read_seqbegin(&f->rnd_seqlock);
-
- hash = inet_frag_hashfn(f, fq);
- hb = &f->hash[hash];
-
- spin_lock(&hb->chain_lock);
- if (read_seqretry(&f->rnd_seqlock, seq)) {
- spin_unlock(&hb->chain_lock);
- goto restart;
- }
-
- return hb;
-}
-
-static inline void fq_unlink(struct inet_frag_queue *fq)
-{
- struct inet_frag_bucket *hb;
-
- hb = get_frag_bucket_locked(fq, fq->net->f);
- hlist_del(&fq->list);
- fq->flags |= INET_FRAG_COMPLETE;
- spin_unlock(&hb->chain_lock);
-}
-
void inet_frag_kill(struct inet_frag_queue *fq)
{
if (del_timer(&fq->timer))
refcount_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq_unlink(fq);
+ struct netns_frags *nf = fq->net;
+
+ fq->flags |= INET_FRAG_COMPLETE;
+ rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
refcount_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
+static void inet_frag_destroy_rcu(struct rcu_head *head)
+{
+ struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
+ rcu);
+ struct inet_frags *f = q->net->f;
+
+ if (f->destructor)
+ f->destructor(q);
+ kmem_cache_free(f->frags_cachep, q);
+}
+
void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
@@ -310,59 +145,20 @@ void inet_frag_destroy(struct inet_frag_queue *q)
}
sum = sum_truesize + f->qsize;
- if (f->destructor)
- f->destructor(q);
- kmem_cache_free(f->frags_cachep, q);
+ call_rcu(&q->rcu, inet_frag_destroy_rcu);
sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
-static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
- struct inet_frag_queue *qp_in,
- struct inet_frags *f,
- void *arg)
-{
- struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
- struct inet_frag_queue *qp;
-
-#ifdef CONFIG_SMP
- /* With SMP race we have to recheck hash table, because
- * such entry could have been created on other cpu before
- * we acquired hash bucket lock.
- */
- hlist_for_each_entry(qp, &hb->chain, list) {
- if (qp->net == nf && f->match(qp, arg)) {
- refcount_inc(&qp->refcnt);
- spin_unlock(&hb->chain_lock);
- qp_in->flags |= INET_FRAG_COMPLETE;
- inet_frag_put(qp_in);
- return qp;
- }
- }
-#endif
- qp = qp_in;
- if (!mod_timer(&qp->timer, jiffies + nf->timeout))
- refcount_inc(&qp->refcnt);
-
- refcount_inc(&qp->refcnt);
- hlist_add_head(&qp->list, &hb->chain);
-
- spin_unlock(&hb->chain_lock);
-
- return qp;
-}
-
static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
struct inet_frags *f,
void *arg)
{
struct inet_frag_queue *q;
- if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
- inet_frag_schedule_worker(f);
+ if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
return NULL;
- }
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
@@ -374,59 +170,52 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
timer_setup(&q->timer, f->frag_expire, 0);
spin_lock_init(&q->lock);
- refcount_set(&q->refcnt, 1);
+ refcount_set(&q->refcnt, 3);
return q;
}
static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
- struct inet_frags *f,
void *arg)
{
+ struct inet_frags *f = nf->f;
struct inet_frag_queue *q;
+ int err;
q = inet_frag_alloc(nf, f, arg);
if (!q)
return NULL;
- return inet_frag_intern(nf, q, f, arg);
+ mod_timer(&q->timer, jiffies + nf->timeout);
+
+ err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
+ f->rhash_params);
+ if (err < 0) {
+ q->flags |= INET_FRAG_COMPLETE;
+ inet_frag_kill(q);
+ inet_frag_destroy(q);
+ return NULL;
+ }
+ return q;
}
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key,
- unsigned int hash)
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
{
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- int depth = 0;
+ struct inet_frag_queue *fq;
- if (frag_mem_limit(nf) > nf->low_thresh)
- inet_frag_schedule_worker(f);
+ rcu_read_lock();
- hash &= (INETFRAGS_HASHSZ - 1);
- hb = &f->hash[hash];
-
- spin_lock(&hb->chain_lock);
- hlist_for_each_entry(q, &hb->chain, list) {
- if (q->net == nf && f->match(q, key)) {
- refcount_inc(&q->refcnt);
- spin_unlock(&hb->chain_lock);
- return q;
- }
- depth++;
- }
- spin_unlock(&hb->chain_lock);
-
- if (depth <= INETFRAGS_MAXDEPTH)
- return inet_frag_create(nf, f, key);
-
- if (inet_frag_may_rebuild(f)) {
- if (!f->rebuild)
- f->rebuild = true;
- inet_frag_schedule_worker(f);
+ fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+ if (fq) {
+ if (!refcount_inc_not_zero(&fq->refcnt))
+ fq = NULL;
+ rcu_read_unlock();
+ return fq;
}
+ rcu_read_unlock();
- return ERR_PTR(-ENOBUFS);
+ return inet_frag_create(nf, key);
}
EXPORT_SYMBOL(inet_frag_find);
@@ -434,8 +223,7 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix)
{
static const char msg[] = "inet_frag_find: Fragment hash bucket"
- " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
- ". Dropping fragment.\n";
+ " list length grew over limit. Dropping fragment.\n";
if (PTR_ERR(q) == -ENOBUFS)
net_dbg_ratelimited("%s%s", prefix, msg);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1a3bc85d6f5ea8f36b8f3d221cad632906b317a2..4021820db6f291b255cc53aeca91dd74aef29934 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -69,15 +69,9 @@ struct ipfrag_skb_cb
struct ipq {
struct inet_frag_queue q;
- u32 user;
- __be32 saddr;
- __be32 daddr;
- __be16 id;
- u8 protocol;
u8 ecn; /* RFC3168 support */
u16 max_df_size; /* largest frag with DF set seen */
int iif;
- int vif; /* L3 master device index */
unsigned int rid;
struct inet_peer *peer;
};
@@ -97,41 +91,6 @@ int ip_frag_mem(struct net *net)
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
-struct ip4_create_arg {
- struct iphdr *iph;
- u32 user;
- int vif;
-};
-
-static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
-{
- net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
- return jhash_3words((__force u32)id << 16 | prot,
- (__force u32)saddr, (__force u32)daddr,
- ip4_frags.rnd);
-}
-
-static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
-{
- const struct ipq *ipq;
-
- ipq = container_of(q, struct ipq, q);
- return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
-}
-
-static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct ipq *qp;
- const struct ip4_create_arg *arg = a;
-
- qp = container_of(q, struct ipq, q);
- return qp->id == arg->iph->id &&
- qp->saddr == arg->iph->saddr &&
- qp->daddr == arg->iph->daddr &&
- qp->protocol == arg->iph->protocol &&
- qp->user == arg->user &&
- qp->vif == arg->vif;
-}
static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
@@ -140,17 +99,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
frags);
struct net *net = container_of(ipv4, struct net, ipv4);
- const struct ip4_create_arg *arg = a;
+ const struct frag_v4_compare_key *key = a;
- qp->protocol = arg->iph->protocol;
- qp->id = arg->iph->id;
- qp->ecn = ip4_frag_ecn(arg->iph->tos);
- qp->saddr = arg->iph->saddr;
- qp->daddr = arg->iph->daddr;
- qp->vif = arg->vif;
- qp->user = arg->user;
+ q->key.v4 = *key;
+ qp->ecn = 0;
qp->peer = q->net->max_dist ?
- inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+ inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
NULL;
}
@@ -234,7 +188,7 @@ static void ip_expire(struct timer_list *t)
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
- if (frag_expire_skip_icmp(qp->user) &&
+ if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
@@ -262,17 +216,17 @@ static void ip_expire(struct timer_list *t)
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
u32 user, int vif)
{
+ struct frag_v4_compare_key key = {
+ .saddr = iph->saddr,
+ .daddr = iph->daddr,
+ .user = user,
+ .vif = vif,
+ .id = iph->id,
+ .protocol = iph->protocol,
+ };
struct inet_frag_queue *q;
- struct ip4_create_arg arg;
- unsigned int hash;
- arg.iph = iph;
- arg.user = user;
- arg.vif = vif;
-
- hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
-
- q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv4.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -656,7 +610,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
err = -ENOMEM;
goto out_fail;
out_oversize:
- net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
+ net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
return err;
@@ -894,15 +848,47 @@ static struct pernet_operations ip4_frags_ops = {
.exit = ipv4_frags_exit_net,
};
+
+static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v4,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v4_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params ip4_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .key_offset = offsetof(struct inet_frag_queue, key),
+ .key_len = sizeof(struct frag_v4_compare_key),
+ .hashfn = ip4_key_hashfn,
+ .obj_hashfn = ip4_obj_hashfn,
+ .obj_cmpfn = ip4_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
void __init ipfrag_init(void)
{
- ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
ip4_frags.qsize = sizeof(struct ipq);
- ip4_frags.match = ip4_frag_match;
ip4_frags.frag_expire = ip_expire;
ip4_frags.frags_cache_name = ip_frag_cache_name;
+ ip4_frags.rhash_params = ip4_rhash_params;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
ip4_frags_ctl_register();
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c4b40fdee838300f3723cece1e6b5b9d03fa9249..0ad3df551d9884ba30f2d40658ee81a61720e947 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -152,23 +152,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, nf_frags.rnd);
-}
-
-
-static unsigned int nf_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *nq;
-
- nq = container_of(q, struct frag_queue, q);
- return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
-}
-
static void nf_ct_frag6_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
@@ -182,26 +165,19 @@ static void nf_ct_frag6_expire(struct timer_list *t)
}
/* Creation primitives. */
-static inline struct frag_queue *fq_find(struct net *net, __be32 id,
- u32 user, struct in6_addr *src,
- struct in6_addr *dst, int iif, u8 ecn)
+static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
+ const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = user,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
- arg.id = id;
- arg.user = user;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
-
- local_bh_disable();
- hash = nf_hash_frag(id, src, dst);
-
- q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
- local_bh_enable();
+ q = inet_frag_find(&net->nf_frag.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -593,8 +569,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
fhdr = (struct frag_hdr *)skb_transport_header(skb);
skb_orphan(skb);
- fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ fq = fq_find(net, fhdr->identification, user, hdr,
+ skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
return -ENOMEM;
@@ -660,13 +636,12 @@ int nf_ct_frag6_init(void)
{
int ret = 0;
- nf_frags.hashfn = nf_hashfn;
nf_frags.constructor = ip6_frag_init;
nf_frags.destructor = NULL;
nf_frags.qsize = sizeof(struct frag_queue);
- nf_frags.match = ip6_frag_match;
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
+ nf_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&nf_frags);
if (ret)
goto out;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index f0071b113a92fcff15ac57610170c12b17cb59ba..3fc853e4492abb109062d662296c0b470763042a 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -79,52 +79,13 @@ static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
-/*
- * callers should be careful not to use the hash value outside the ipfrag_lock
- * as doing so could race with ipfrag_hash_rnd being recalculated.
- */
-static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, ip6_frags.rnd);
-}
-
-static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *fq;
-
- fq = container_of(q, struct frag_queue, q);
- return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
-}
-
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct frag_queue *fq;
- const struct ip6_create_arg *arg = a;
-
- fq = container_of(q, struct frag_queue, q);
- return fq->id == arg->id &&
- fq->user == arg->user &&
- ipv6_addr_equal(&fq->saddr, arg->src) &&
- ipv6_addr_equal(&fq->daddr, arg->dst) &&
- (arg->iif == fq->iif ||
- !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
- IPV6_ADDR_LINKLOCAL)));
-}
-EXPORT_SYMBOL(ip6_frag_match);
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
- const struct ip6_create_arg *arg = a;
+ const struct frag_v6_compare_key *key = a;
- fq->id = arg->id;
- fq->user = arg->user;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
- fq->ecn = arg->ecn;
+ q->key.v6 = *key;
+ fq->ecn = 0;
}
EXPORT_SYMBOL(ip6_frag_init);
@@ -182,23 +143,22 @@ static void ip6_frag_expire(struct timer_list *t)
}
static struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
- const struct in6_addr *dst, int iif, u8 ecn)
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = IP6_DEFRAG_LOCAL_DELIVER,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
- arg.id = id;
- arg.user = IP6_DEFRAG_LOCAL_DELIVER;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)))
+ key.iif = 0;
- hash = inet6_hash_frag(id, src, dst);
-
- q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv6.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -530,6 +490,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
+ int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
goto fail_hdr;
@@ -558,13 +519,14 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
return 1;
}
- fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ iif = skb->dev ? skb->dev->ifindex : 0;
+ fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
int ret;
spin_lock(&fq->q.lock);
+ fq->iif = iif;
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
@@ -738,17 +700,47 @@ static struct pernet_operations ip6_frags_ops = {
.exit = ipv6_frags_exit_net,
};
+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v6,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v6_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params ip6_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = ip6_key_hashfn,
+ .obj_hashfn = ip6_obj_hashfn,
+ .obj_cmpfn = ip6_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+EXPORT_SYMBOL(ip6_rhash_params);
+
int __init ipv6_frag_init(void)
{
int ret;
- ip6_frags.hashfn = ip6_hashfn;
ip6_frags.constructor = ip6_frag_init;
ip6_frags.destructor = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
- ip6_frags.match = ip6_frag_match;
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.frags_cache_name = ip6_frag_cache_name;
+ ip6_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&ip6_frags);
if (ret)
goto out;
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 08/19] inet: frags: use rhashtables for reassembly units
2018-03-31 19:58 ` [PATCH v4 net-next 08/19] inet: frags: use rhashtables for reassembly units Eric Dumazet
@ 2018-04-16 12:54 ` Stefan Schmidt
0 siblings, 0 replies; 34+ messages in thread
From: Stefan Schmidt @ 2018-04-16 12:54 UTC (permalink / raw)
To: Eric Dumazet, David S . Miller; +Cc: netdev, Eric Dumazet, Alexander Aring
Hello Eric.
On 03/31/2018 09:58 PM, Eric Dumazet wrote:
> Some applications still rely on IP fragmentation, and to be fair linux
> reassembly unit is not working under any serious load.
[...]
> ---
> Documentation/networking/ip-sysctl.txt | 7 +-
> include/net/inet_frag.h | 81 +++---
> include/net/ipv6.h | 16 +-
> net/ieee802154/6lowpan/6lowpan_i.h | 26 +-
> net/ieee802154/6lowpan/reassembly.c | 93 +++----
> net/ipv4/inet_fragment.c | 354 +++++-------------------
> net/ipv4/ip_fragment.c | 112 ++++----
> net/ipv6/netfilter/nf_conntrack_reasm.c | 51 +---
> net/ipv6/reassembly.c | 110 ++++----
> 9 files changed, 271 insertions(+), 579 deletions(-)
>
Just a heads up to let you know that this patch broke the 6LoWPAN fragmentation/reassembly
for 802.15.4
Simply initiating a ssh session will fail. After a 1.5 days git bisect session it pointed me to this
commit. :-) After reverting it (and some other patches of this series due to inter dependencies)
it started working again.
No further debugging on this from my side yet, as I just found it and wanted to let you know in
case you have an idea what's going on.
I will try to make some room this week to help with debugging and fixing.
regards
Stefan Schmidt
^ permalink raw reply [flat|nested] 34+ messages in thread
* [PATCH v4 net-next 09/19] inet: frags: remove some helpers
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (7 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 08/19] inet: frags: use rhashtables for reassembly units Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 10/19] inet: frags: get rif of inet_frag_evicting() Eric Dumazet
` (10 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
Remove sum_frag_mem_limit(), ip_frag_mem() & ip6_frag_mem()
Also since we use rhashtable we can bring back the number of fragments
in "grep FRAG /proc/net/sockstat /proc/net/sockstat6" that was
removed in commit 434d305405ab ("inet: frag: don't account number
of fragment queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 5 -----
include/net/ip.h | 1 -
include/net/ipv6.h | 7 -------
net/ipv4/ip_fragment.c | 5 -----
net/ipv4/proc.c | 6 +++---
net/ipv6/proc.c | 5 +++--
6 files changed, 6 insertions(+), 23 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 3fec0d3a0d0186e98afb951784e1fe7329ba6d77..4b5449df0aadf1f75144c98317bf5305ec91d88b 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -141,11 +141,6 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
atomic_add(i, &nf->mem);
}
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
-{
- return atomic_read(&nf->mem);
-}
-
/* RFC 3168 support :
* We want to check ECN values of all fragments, do detect invalid combinations.
* In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
diff --git a/include/net/ip.h b/include/net/ip.h
index 36f8f7811093c37de06194dc7410b7596f8bf9fa..ecffd843e7b896a83416847fdaa452be6223f3dc 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -588,7 +588,6 @@ static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *s
return skb;
}
#endif
-int ip_frag_mem(struct net *net);
/*
* Functions provided by ip_forward.c
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6fa9a2bc589665dfa9ce84813f33e5e86e12fd74..37455e84034779fab96c231fa069957a6dcf2b42 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -379,13 +379,6 @@ static inline bool ipv6_accept_ra(struct inet6_dev *idev)
idev->cnf.accept_ra;
}
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int ip6_frag_mem(struct net *net)
-{
- return sum_frag_mem_limit(&net->ipv6.frags);
-}
-#endif
-
#define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */
#define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */
#define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 4021820db6f291b255cc53aeca91dd74aef29934..44f4fa306e224a6f76183b1c04935f01ceb4fe2b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -83,11 +83,6 @@ static u8 ip4_frag_ecn(u8 tos)
static struct inet_frags ip4_frags;
-int ip_frag_mem(struct net *net)
-{
- return sum_frag_mem_limit(&net->ipv4.frags);
-}
-
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index adfb75340275d240487574257c10feb295df44fe..aacfce0d7d82cf59269a69ef4d6ac8d9955b0bdc 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,6 @@
static int sockstat_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
- unsigned int frag_mem;
int orphans, sockets;
orphans = percpu_counter_sum_positive(&tcp_orphan_count);
@@ -72,8 +71,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
- frag_mem = ip_frag_mem(net);
- seq_printf(seq, "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
+ seq_printf(seq, "FRAG: inuse %u memory %u\n",
+ atomic_read(&net->ipv4.frags.rhashtable.nelems),
+ frag_mem_limit(&net->ipv4.frags));
return 0;
}
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 6e57028d2e9160be264d07f9312658fcb677a568..8befeb91e0712ecc4d05c4c0a6ecca1808dcbcac 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -38,7 +38,6 @@
static int sockstat6_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
- unsigned int frag_mem = ip6_frag_mem(net);
seq_printf(seq, "TCP6: inuse %d\n",
sock_prot_inuse_get(net, &tcpv6_prot));
@@ -48,7 +47,9 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplitev6_prot));
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(net, &rawv6_prot));
- seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem);
+ seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+ atomic_read(&net->ipv6.frags.rhashtable.nelems),
+ frag_mem_limit(&net->ipv6.frags));
return 0;
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 10/19] inet: frags: get rif of inet_frag_evicting()
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (8 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 09/19] inet: frags: remove some helpers Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 11/19] inet: frags: remove inet_frag_maybe_warn_overflow() Eric Dumazet
` (9 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
This refactors ip_expire() since one indentation level is removed.
Note: in the future, we should try hard to avoid the skb_clone()
since this is a serious performance cost.
Under DDOS, the ICMP message wont be sent because of rate limits.
Fact that ip6_expire_frag_queue() does not use skb_clone() is
disturbing too. Presumably IPv6 should have the same
issue than the one we fixed in commit ec4fbd64751d
("inet: frag: release spinlock before calling icmp_send()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 5 ----
net/ipv4/ip_fragment.c | 61 ++++++++++++++++++++---------------------
net/ipv6/reassembly.c | 4 ---
3 files changed, 30 insertions(+), 40 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 4b5449df0aadf1f75144c98317bf5305ec91d88b..0e8e159d88f7f77254fae5a49f1c7ba07b967e11 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -119,11 +119,6 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
inet_frag_destroy(q);
}
-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
- return false;
-}
-
/* Memory Tracking Functions. */
static inline int frag_mem_limit(struct netns_frags *nf)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 44f4fa306e224a6f76183b1c04935f01ceb4fe2b..b844f517b75bd6a52538e9f7687e039e22c93bc7 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -143,8 +143,11 @@ static bool frag_expire_skip_icmp(u32 user)
static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
- struct ipq *qp;
+ struct sk_buff *clone, *head;
+ const struct iphdr *iph;
struct net *net;
+ struct ipq *qp;
+ int err;
qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -158,45 +161,41 @@ static void ip_expire(struct timer_list *t)
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
- if (!inet_frag_evicting(&qp->q)) {
- struct sk_buff *clone, *head = qp->q.fragments;
- const struct iphdr *iph;
- int err;
+ head = qp->q.fragments;
- __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
+ __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
- if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
- goto out;
+ if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;
- head->dev = dev_get_by_index_rcu(net, qp->iif);
- if (!head->dev)
- goto out;
+ head->dev = dev_get_by_index_rcu(net, qp->iif);
+ if (!head->dev)
+ goto out;
- /* skb has no dst, perform route lookup again */
- iph = ip_hdr(head);
- err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+ /* skb has no dst, perform route lookup again */
+ iph = ip_hdr(head);
+ err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
- if (err)
- goto out;
+ if (err)
+ goto out;
- /* Only an end host needs to send an ICMP
- * "Fragment Reassembly Timeout" message, per RFC792.
- */
- if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
- (skb_rtable(head)->rt_type != RTN_LOCAL))
- goto out;
+ /* Only an end host needs to send an ICMP
+ * "Fragment Reassembly Timeout" message, per RFC792.
+ */
+ if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
+ (skb_rtable(head)->rt_type != RTN_LOCAL))
+ goto out;
- clone = skb_clone(head, GFP_ATOMIC);
+ clone = skb_clone(head, GFP_ATOMIC);
- /* Send an ICMP "Fragment Reassembly Timeout" message. */
- if (clone) {
- spin_unlock(&qp->q.lock);
- icmp_send(clone, ICMP_TIME_EXCEEDED,
- ICMP_EXC_FRAGTIME, 0);
- consume_skb(clone);
- goto out_rcu_unlock;
- }
+ /* Send an ICMP "Fragment Reassembly Timeout" message. */
+ if (clone) {
+ spin_unlock(&qp->q.lock);
+ icmp_send(clone, ICMP_TIME_EXCEEDED,
+ ICMP_EXC_FRAGTIME, 0);
+ consume_skb(clone);
+ goto out_rcu_unlock;
}
out:
spin_unlock(&qp->q.lock);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3fc853e4492abb109062d662296c0b470763042a..70acad126d044a0f6a1efc63f307805fcf7b1df9 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -106,10 +106,6 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
goto out_rcu_unlock;
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
- if (inet_frag_evicting(&fq->q))
- goto out_rcu_unlock;
-
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
/* Don't send error if the first segment did not arrive. */
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 11/19] inet: frags: remove inet_frag_maybe_warn_overflow()
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (9 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 10/19] inet: frags: get rif of inet_frag_evicting() Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 12/19] inet: frags: break the 2GB limit for frags storage Eric Dumazet
` (8 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
This function is obsolete, after rhashtable addition to inet defrag.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 2 --
net/ieee802154/6lowpan/reassembly.c | 5 ++---
net/ipv4/inet_fragment.c | 11 -----------
net/ipv4/ip_fragment.c | 5 ++---
net/ipv6/netfilter/nf_conntrack_reasm.c | 5 ++---
net/ipv6/reassembly.c | 5 ++---
6 files changed, 8 insertions(+), 25 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 0e8e159d88f7f77254fae5a49f1c7ba07b967e11..95e353e3305b43253084d972e32538138bcc5454 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -110,8 +110,6 @@ void inet_frags_exit_net(struct netns_frags *nf);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
- const char *prefix);
static inline void inet_frag_put(struct inet_frag_queue *q)
{
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 0fa0121f85d4531751566c26e18cc2a23c017da6..1aec71a3f90478a29065e6559a78aec2e930ceab 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -84,10 +84,9 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
struct inet_frag_queue *q;
q = inet_frag_find(&ieee802154_lowpan->frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct lowpan_frag_queue, q);
}
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index ebb8f411e0db16478e861105b1926e97fbf07b06..c9e35b81d0931df8429a33e8d03e719b87da0747 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -218,14 +218,3 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
return inet_frag_create(nf, key);
}
EXPORT_SYMBOL(inet_frag_find);
-
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
- const char *prefix)
-{
- static const char msg[] = "inet_frag_find: Fragment hash bucket"
- " list length grew over limit. Dropping fragment.\n";
-
- if (PTR_ERR(q) == -ENOBUFS)
- net_dbg_ratelimited("%s%s", prefix, msg);
-}
-EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b844f517b75bd6a52538e9f7687e039e22c93bc7..b0366224f314ae521d8c1f8fe04c53e419292b4c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -221,10 +221,9 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph,
struct inet_frag_queue *q;
q = inet_frag_find(&net->ipv4.frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct ipq, q);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 0ad3df551d9884ba30f2d40658ee81a61720e947..d866412b8f6c432f04c0968f08f820fdc561262b 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -178,10 +178,9 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
struct inet_frag_queue *q;
q = inet_frag_find(&net->nf_frag.frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct frag_queue, q);
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 70acad126d044a0f6a1efc63f307805fcf7b1df9..2a77fda5e3bca1b6ce8c24df11e741653a15c665 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -155,10 +155,9 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
key.iif = 0;
q = inet_frag_find(&net->ipv6.frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct frag_queue, q);
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 12/19] inet: frags: break the 2GB limit for frags storage
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (10 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 11/19] inet: frags: remove inet_frag_maybe_warn_overflow() Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 13/19] inet: frags: do not clone skb in ip_expire() Eric Dumazet
` (7 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
Some users are willing to provision huge amounts of memory to be able
to perform reassembly reasonnably well under pressure.
Current memory tracking is using one atomic_t and integers.
Switch to atomic_long_t so that 64bit arches can use more than 2GB,
without any cost for 32bit arches.
Note that this patch avoids an overflow error, if high_thresh was set
to ~2GB, since this test in inet_frag_alloc() was never true :
if (... || frag_mem_limit(nf) > nf->high_thresh)
Tested:
$ echo 16000000000 >/proc/sys/net/ipv4/ipfrag_high_thresh
<frag DDOS>
$ grep FRAG /proc/net/sockstat
FRAG: inuse 14705885 memory 16000002880
$ nstat -n ; sleep 1 ; nstat | grep Reas
IpReasmReqds 3317150 0.0
IpReasmFails 3317112 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
Documentation/networking/ip-sysctl.txt | 4 ++--
include/net/inet_frag.h | 20 ++++++++++----------
net/ieee802154/6lowpan/reassembly.c | 10 +++++-----
net/ipv4/ip_fragment.c | 10 +++++-----
net/ipv4/proc.c | 2 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 10 +++++-----
net/ipv6/proc.c | 2 +-
net/ipv6/reassembly.c | 6 +++---
8 files changed, 32 insertions(+), 32 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6f2a3670e44b6662ce53c16cb7ca1e4f61274c15..5dc1a040a2f1db610873de26c2d79bc57ac5a1a2 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -133,10 +133,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
-ipfrag_high_thresh - INTEGER
+ipfrag_high_thresh - LONG INTEGER
Maximum memory used to reassemble IP fragments.
-ipfrag_low_thresh - INTEGER
+ipfrag_low_thresh - LONG INTEGER
(Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 95e353e3305b43253084d972e32538138bcc5454..a52e7273e7a59bc8ce47b21d29235a740add8db0 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -8,11 +8,11 @@ struct netns_frags {
struct rhashtable rhashtable ____cacheline_aligned_in_smp;
/* Keep atomic mem on separate cachelines in structs that include it */
- atomic_t mem ____cacheline_aligned_in_smp;
+ atomic_long_t mem ____cacheline_aligned_in_smp;
/* sysctls */
+ long high_thresh;
+ long low_thresh;
int timeout;
- int high_thresh;
- int low_thresh;
int max_dist;
struct inet_frags *f;
};
@@ -102,7 +102,7 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
- atomic_set(&nf->mem, 0);
+ atomic_long_set(&nf->mem, 0);
return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
@@ -119,19 +119,19 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
/* Memory Tracking Functions. */
-static inline int frag_mem_limit(struct netns_frags *nf)
+static inline long frag_mem_limit(const struct netns_frags *nf)
{
- return atomic_read(&nf->mem);
+ return atomic_long_read(&nf->mem);
}
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
{
- atomic_sub(i, &nf->mem);
+ atomic_long_sub(val, &nf->mem);
}
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
{
- atomic_add(i, &nf->mem);
+ atomic_long_add(val, &nf->mem);
}
/* RFC 3168 support :
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 1aec71a3f90478a29065e6559a78aec2e930ceab..44f148a6bb57bb737c35a07e3f070472e209ea23 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -411,23 +411,23 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
}
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table lowpan_frags_ns_ctl_table[] = {
{
.procname = "6lowpanfrag_high_thresh",
.data = &init_net.ieee802154_lowpan.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ieee802154_lowpan.frags.low_thresh
},
{
.procname = "6lowpanfrag_low_thresh",
.data = &init_net.ieee802154_lowpan.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.ieee802154_lowpan.frags.high_thresh
},
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b0366224f314ae521d8c1f8fe04c53e419292b4c..053869f2c49b9fd7a87316f1ef1416568b1bf508 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -678,23 +678,23 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
EXPORT_SYMBOL(ip_check_defrag);
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
.procname = "ipfrag_high_thresh",
.data = &init_net.ipv4.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ipv4.frags.low_thresh
},
{
.procname = "ipfrag_low_thresh",
.data = &init_net.ipv4.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.ipv4.frags.high_thresh
},
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index aacfce0d7d82cf59269a69ef4d6ac8d9955b0bdc..a058de677e947846eb93020e0788148827c8f3cd 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -71,7 +71,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
- seq_printf(seq, "FRAG: inuse %u memory %u\n",
+ seq_printf(seq, "FRAG: inuse %u memory %lu\n",
atomic_read(&net->ipv4.frags.rhashtable.nelems),
frag_mem_limit(&net->ipv4.frags));
return 0;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index d866412b8f6c432f04c0968f08f820fdc561262b..603a395928593a071aff28105578d3bfdbf1b31e 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -63,7 +63,7 @@ struct nf_ct_frag6_skb_cb
static struct inet_frags nf_frags;
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
@@ -76,18 +76,18 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
.procname = "nf_conntrack_frag6_low_thresh",
.data = &init_net.nf_frag.frags.low_thresh,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.nf_frag.frags.high_thresh
},
{
.procname = "nf_conntrack_frag6_high_thresh",
.data = &init_net.nf_frag.frags.high_thresh,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.nf_frag.frags.low_thresh
},
{ }
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 8befeb91e0712ecc4d05c4c0a6ecca1808dcbcac..a85f7e0b14b10f59fdd2ea6901f8e9a95c13654f 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -47,7 +47,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplitev6_prot));
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(net, &rawv6_prot));
- seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+ seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
atomic_read(&net->ipv6.frags.rhashtable.nelems),
frag_mem_limit(&net->ipv6.frags));
return 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2a77fda5e3bca1b6ce8c24df11e741653a15c665..905a8aee2671fd76b47d9cc6b6b0c17c9691d224 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -552,15 +552,15 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = {
{
.procname = "ip6frag_high_thresh",
.data = &init_net.ipv6.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ipv6.frags.low_thresh
},
{
.procname = "ip6frag_low_thresh",
.data = &init_net.ipv6.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 13/19] inet: frags: do not clone skb in ip_expire()
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (11 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 12/19] inet: frags: break the 2GB limit for frags storage Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 14/19] ipv6: frags: rewrite ip6_expire_frag_queue() Eric Dumazet
` (6 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
An skb_clone() was added in commit ec4fbd64751d ("inet: frag: release
spinlock before calling icmp_send()")
While fixing the bug at that time, it also added a very high cost
for DDOS frags, as the ICMP rate limit is applied after this
expensive operation (skb_clone() + consume_skb(), implying memory
allocations, copy, and freeing)
We can use skb_get(head) here, all we want is to make sure skb wont
be freed by another cpu.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/ip_fragment.c | 16 ++++++----------
1 file changed, 6 insertions(+), 10 deletions(-)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 053869f2c49b9fd7a87316f1ef1416568b1bf508..fb185d9a5cc771778fb650695e2d9894724efc23 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -143,8 +143,8 @@ static bool frag_expire_skip_icmp(u32 user)
static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
- struct sk_buff *clone, *head;
const struct iphdr *iph;
+ struct sk_buff *head;
struct net *net;
struct ipq *qp;
int err;
@@ -187,16 +187,12 @@ static void ip_expire(struct timer_list *t)
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
- clone = skb_clone(head, GFP_ATOMIC);
+ skb_get(head);
+ spin_unlock(&qp->q.lock);
+ icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
+ kfree_skb(head);
+ goto out_rcu_unlock;
- /* Send an ICMP "Fragment Reassembly Timeout" message. */
- if (clone) {
- spin_unlock(&qp->q.lock);
- icmp_send(clone, ICMP_TIME_EXCEEDED,
- ICMP_EXC_FRAGTIME, 0);
- consume_skb(clone);
- goto out_rcu_unlock;
- }
out:
spin_unlock(&qp->q.lock);
out_rcu_unlock:
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 14/19] ipv6: frags: rewrite ip6_expire_frag_queue()
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (12 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 13/19] inet: frags: do not clone skb in ip_expire() Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 15/19] rhashtable: reorganize struct rhashtable layout Eric Dumazet
` (5 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
Make it similar to IPv4 ip_expire(), and release the lock
before calling icmp functions.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv6/reassembly.c | 24 ++++++++++++++++--------
1 file changed, 16 insertions(+), 8 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 905a8aee2671fd76b47d9cc6b6b0c17c9691d224..2127da130dc2cee677059247d5e079a8afbca13d 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -92,7 +92,9 @@ EXPORT_SYMBOL(ip6_frag_init);
void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
{
struct net_device *dev = NULL;
+ struct sk_buff *head;
+ rcu_read_lock();
spin_lock(&fq->q.lock);
if (fq->q.flags & INET_FRAG_COMPLETE)
@@ -100,28 +102,34 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
inet_frag_kill(&fq->q);
- rcu_read_lock();
dev = dev_get_by_index_rcu(net, fq->iif);
if (!dev)
- goto out_rcu_unlock;
+ goto out;
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
/* Don't send error if the first segment did not arrive. */
- if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments)
- goto out_rcu_unlock;
+ head = fq->q.fragments;
+ if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;
/* But use as source device on which LAST ARRIVED
* segment was received. And do not use fq->dev
* pointer directly, device might already disappeared.
*/
- fq->q.fragments->dev = dev;
- icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+ head->dev = dev;
+ skb_get(head);
+ spin_unlock(&fq->q.lock);
+
+ icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+ kfree_skb(head);
+ goto out_rcu_unlock;
+
+out:
+ spin_unlock(&fq->q.lock);
out_rcu_unlock:
rcu_read_unlock();
-out:
- spin_unlock(&fq->q.lock);
inet_frag_put(&fq->q);
}
EXPORT_SYMBOL(ip6_expire_frag_queue);
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 15/19] rhashtable: reorganize struct rhashtable layout
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (13 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 14/19] ipv6: frags: rewrite ip6_expire_frag_queue() Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 16/19] inet: frags: reorganize struct netns_frags Eric Dumazet
` (4 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
While under frags DDOS I noticed unfortunate false sharing between
@nelems and @params.automatic_shrinking
Move @nelems at the end of struct rhashtable so that first cache line
is shared between all cpus, because almost never dirtied.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/linux/rhashtable.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 668a21f04b09665018ffaf91989f32995fbbdfc4..1f8ad121eb4346ed06195661dc2327d17be4de49 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -152,25 +152,25 @@ struct rhashtable_params {
/**
* struct rhashtable - Hash table handle
* @tbl: Bucket table
- * @nelems: Number of elements in table
* @key_len: Key length for hashfn
- * @p: Configuration parameters
* @max_elems: Maximum number of elements in table
+ * @p: Configuration parameters
* @rhlist: True if this is an rhltable
* @run_work: Deferred worker to expand/shrink asynchronously
* @mutex: Mutex to protect current/future table swapping
* @lock: Spin lock to protect walker list
+ * @nelems: Number of elements in table
*/
struct rhashtable {
struct bucket_table __rcu *tbl;
- atomic_t nelems;
unsigned int key_len;
- struct rhashtable_params p;
unsigned int max_elems;
+ struct rhashtable_params p;
bool rhlist;
struct work_struct run_work;
struct mutex mutex;
spinlock_t lock;
+ atomic_t nelems;
};
/**
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 16/19] inet: frags: reorganize struct netns_frags
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (14 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 15/19] rhashtable: reorganize struct rhashtable layout Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 17/19] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB Eric Dumazet
` (3 subsequent siblings)
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
Put the read-mostly fields in a separate cache line
at the beginning of struct netns_frags, to reduce
false sharing noticed in inet_frag_kill()
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index a52e7273e7a59bc8ce47b21d29235a740add8db0..ed07e3786d98614898bd5ec9804afb425ba82cec 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -5,16 +5,17 @@
#include <linux/rhashtable.h>
struct netns_frags {
- struct rhashtable rhashtable ____cacheline_aligned_in_smp;
-
- /* Keep atomic mem on separate cachelines in structs that include it */
- atomic_long_t mem ____cacheline_aligned_in_smp;
/* sysctls */
long high_thresh;
long low_thresh;
int timeout;
int max_dist;
struct inet_frags *f;
+
+ struct rhashtable rhashtable ____cacheline_aligned_in_smp;
+
+ /* Keep atomic mem on separate cachelines in structs that include it */
+ atomic_long_t mem ____cacheline_aligned_in_smp;
};
/**
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 17/19] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (15 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 16/19] inet: frags: reorganize struct netns_frags Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-04-01 3:02 ` kbuild test robot
2018-03-31 19:58 ` [PATCH v4 net-next 18/19] ipv6: frags: get rid of ip6frag_skb_cb/FRAG6_CB Eric Dumazet
` (2 subsequent siblings)
19 siblings, 1 reply; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
ip_defrag uses skb->cb[] to store the fragment offset, and unfortunately
this integer is currently in a different cache line than skb->next,
meaning that we use two cache lines per skb when finding the insertion point.
By aliasing skb->ip_defrag_offset and skb->dev, we pack all the fields
in a single cache line and save precious memory bandwidth.
Note that after the fast path added by Changli Gao in commit
d6bebca92c66 ("fragment: add fast path for in-order fragments")
this change wont help the fast path, since we still need
to access prev->len (2nd cache line), but will show great
benefits when slow path is entered, since we perform
a linear scan of a potentially long list.
Also, note that this potential long list is an attack vector,
we might consider also using an rb-tree there eventually.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/linux/skbuff.h | 1 +
net/ipv4/ip_fragment.c | 35 ++++++++++++++---------------------
2 files changed, 15 insertions(+), 21 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 47082f54ec1f645bed95a37d8c101efd160c60dc..9065477ed255a48f7e01b8a28ea6321cce9127f5 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -672,6 +672,7 @@ struct sk_buff {
* UDP receive path is one user.
*/
unsigned long dev_scratch;
+ int ip_defrag_offset;
};
};
struct rb_node rbnode; /* used in netem & tcp stack */
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index fb185d9a5cc771778fb650695e2d9894724efc23..994fa70a910f472ebecc336ddd62d1442014eaba 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -57,14 +57,6 @@
*/
static const char ip_frag_cache_name[] = "ip4-frags";
-struct ipfrag_skb_cb
-{
- struct inet_skb_parm h;
- int offset;
-};
-
-#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
-
/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
struct inet_frag_queue q;
@@ -353,13 +345,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
* this fragment, right?
*/
prev = qp->q.fragments_tail;
- if (!prev || FRAG_CB(prev)->offset < offset) {
+ if (!prev || prev->ip_defrag_offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = qp->q.fragments; next != NULL; next = next->next) {
- if (FRAG_CB(next)->offset >= offset)
+ if (next->ip_defrag_offset >= offset)
break; /* bingo! */
prev = next;
}
@@ -370,7 +362,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
* any overlaps are eliminated.
*/
if (prev) {
- int i = (FRAG_CB(prev)->offset + prev->len) - offset;
+ int i = (prev->ip_defrag_offset + prev->len) - offset;
if (i > 0) {
offset += i;
@@ -387,8 +379,8 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
err = -ENOMEM;
- while (next && FRAG_CB(next)->offset < end) {
- int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
+ while (next && next->ip_defrag_offset < end) {
+ int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
if (i < next->len) {
/* Eat head of the next overlapped fragment
@@ -396,7 +388,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
*/
if (!pskb_pull(next, i))
goto err;
- FRAG_CB(next)->offset += i;
+ next->ip_defrag_offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
next->ip_summed = CHECKSUM_NONE;
@@ -420,7 +412,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
}
}
- FRAG_CB(skb)->offset = offset;
+ /* Note : skb->ip_defrag_offset and skb->dev share the same location */
+ dev = skb->dev;
+ if (dev)
+ qp->iif = dev->ifindex;
+ /* Makes sure compiler wont do silly aliasing games */
+ barrier();
+ skb->ip_defrag_offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
@@ -431,11 +429,6 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
else
qp->q.fragments = skb;
- dev = skb->dev;
- if (dev) {
- qp->iif = dev->ifindex;
- skb->dev = NULL;
- }
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
@@ -511,7 +504,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
}
WARN_ON(!head);
- WARN_ON(FRAG_CB(head)->offset != 0);
+ WARN_ON(head->ip_defrag_offset != 0);
/* Allocate a new buffer for the datagram. */
ihlen = ip_hdrlen(head);
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 17/19] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB
2018-03-31 19:58 ` [PATCH v4 net-next 17/19] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB Eric Dumazet
@ 2018-04-01 3:02 ` kbuild test robot
0 siblings, 0 replies; 34+ messages in thread
From: kbuild test robot @ 2018-04-01 3:02 UTC (permalink / raw)
To: Eric Dumazet
Cc: kbuild-all, David S . Miller, netdev, Florian Westphal,
Herbert Xu, Thomas Graf, Jesper Dangaard Brouer, Alexander Aring,
Stefan Schmidt, Kirill Tkhai, Eric Dumazet, Eric Dumazet
[-- Attachment #1: Type: text/plain, Size: 19352 bytes --]
Hi Eric,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
url: https://github.com/0day-ci/linux/commits/Eric-Dumazet/inet-frags-bring-rhashtables-to-IP-defrag/20180401-053614
reproduce: make htmldocs
All warnings (new ones prefixed by >>):
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
include/net/mac80211.h:2080: warning: bad line: >
net/mac80211/sta_info.h:586: warning: Function parameter or member 'rx_stats_avg' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'rx_stats_avg.signal' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'rx_stats_avg.chain_signal' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.filtered' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.retry_failed' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.retry_count' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.lost_packets' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.last_tdls_pkt_time' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'msdu_retries' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'msdu_failed' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.last_ack' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.last_ack_signal' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'status_stats.ack_signal_filled' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'tx_stats.packets' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'tx_stats.bytes' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'tx_stats.last_rate' not described in 'sta_info'
net/mac80211/sta_info.h:586: warning: Function parameter or member 'msdu' not described in 'sta_info'
include/linux/dma-buf.h:307: warning: Function parameter or member 'cb_excl.cb' not described in 'dma_buf'
include/linux/dma-buf.h:307: warning: Function parameter or member 'cb_excl.poll' not described in 'dma_buf'
include/linux/dma-buf.h:307: warning: Function parameter or member 'cb_excl.active' not described in 'dma_buf'
include/linux/dma-buf.h:307: warning: Function parameter or member 'cb_shared.cb' not described in 'dma_buf'
include/linux/dma-buf.h:307: warning: Function parameter or member 'cb_shared.poll' not described in 'dma_buf'
include/linux/dma-buf.h:307: warning: Function parameter or member 'cb_shared.active' not described in 'dma_buf'
include/linux/dma-fence-array.h:54: warning: Function parameter or member 'work' not described in 'dma_fence_array'
include/linux/gpio/driver.h:142: warning: Function parameter or member 'request_key' not described in 'gpio_irq_chip'
include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.sign' not described in 'iio_chan_spec'
include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.realbits' not described in 'iio_chan_spec'
include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.storagebits' not described in 'iio_chan_spec'
include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.shift' not described in 'iio_chan_spec'
include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.repeat' not described in 'iio_chan_spec'
include/linux/iio/iio.h:270: warning: Function parameter or member 'scan_type.endianness' not described in 'iio_chan_spec'
include/linux/iio/hw-consumer.h:1: warning: no structured comments found
include/linux/device.h:294: warning: Function parameter or member 'coredump' not described in 'device_driver'
include/linux/input/sparse-keymap.h:46: warning: Function parameter or member 'sw' not described in 'key_entry'
include/linux/mtd/rawnand.h:709: warning: Function parameter or member 'timings.sdr' not described in 'nand_data_interface'
include/linux/mtd/rawnand.h:774: warning: Function parameter or member 'buf' not described in 'nand_op_data_instr'
include/linux/mtd/rawnand.h:774: warning: Function parameter or member 'buf.in' not described in 'nand_op_data_instr'
include/linux/mtd/rawnand.h:774: warning: Function parameter or member 'buf.out' not described in 'nand_op_data_instr'
include/linux/mtd/rawnand.h:820: warning: Function parameter or member 'ctx' not described in 'nand_op_instr'
include/linux/mtd/rawnand.h:820: warning: Function parameter or member 'ctx.cmd' not described in 'nand_op_instr'
include/linux/mtd/rawnand.h:820: warning: Function parameter or member 'ctx.addr' not described in 'nand_op_instr'
include/linux/mtd/rawnand.h:820: warning: Function parameter or member 'ctx.data' not described in 'nand_op_instr'
include/linux/mtd/rawnand.h:820: warning: Function parameter or member 'ctx.waitrdy' not described in 'nand_op_instr'
include/linux/mtd/rawnand.h:967: warning: Function parameter or member 'ctx' not described in 'nand_op_parser_pattern_elem'
include/linux/mtd/rawnand.h:967: warning: Function parameter or member 'ctx.addr' not described in 'nand_op_parser_pattern_elem'
include/linux/mtd/rawnand.h:967: warning: Function parameter or member 'ctx.data' not described in 'nand_op_parser_pattern_elem'
include/linux/mtd/rawnand.h:1281: warning: Function parameter or member 'manufacturer.desc' not described in 'nand_chip'
include/linux/mtd/rawnand.h:1281: warning: Function parameter or member 'manufacturer.priv' not described in 'nand_chip'
include/linux/regulator/driver.h:221: warning: Function parameter or member 'resume_early' not described in 'regulator_ops'
drivers/regulator/core.c:4299: warning: Excess function parameter 'state' description in 'regulator_suspend_late'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw0' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw1' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw2' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.esw3' not described in 'irb'
arch/s390/include/asm/cio.h:245: warning: Function parameter or member 'esw.eadm' not described in 'irb'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_pin' not described in 'drm_driver'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_unpin' not described in 'drm_driver'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_res_obj' not described in 'drm_driver'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_get_sg_table' not described in 'drm_driver'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_import_sg_table' not described in 'drm_driver'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_vmap' not described in 'drm_driver'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_vunmap' not described in 'drm_driver'
include/drm/drm_drv.h:610: warning: Function parameter or member 'gem_prime_mmap' not described in 'drm_driver'
include/drm/drm_connector.h:370: warning: Function parameter or member 'margins.left' not described in 'drm_tv_connector_state'
include/drm/drm_connector.h:370: warning: Function parameter or member 'margins.right' not described in 'drm_tv_connector_state'
include/drm/drm_connector.h:370: warning: Function parameter or member 'margins.top' not described in 'drm_tv_connector_state'
include/drm/drm_connector.h:370: warning: Function parameter or member 'margins.bottom' not described in 'drm_tv_connector_state'
include/drm/drm_vblank.h:63: warning: Function parameter or member 'event.base' not described in 'drm_pending_vblank_event'
include/drm/drm_vblank.h:63: warning: Function parameter or member 'event.vbl' not described in 'drm_pending_vblank_event'
include/drm/drm_vblank.h:63: warning: Function parameter or member 'event.seq' not described in 'drm_pending_vblank_event'
include/linux/skbuff.h:850: warning: Function parameter or member 'dev_scratch' not described in 'sk_buff'
>> include/linux/skbuff.h:850: warning: Function parameter or member 'ip_defrag_offset' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'skb_mstamp' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member '__cloned_offset' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'head_frag' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member '__unused' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member '__pkt_type_offset' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'pfmemalloc' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'encapsulation' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'encap_hdr_csum' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'csum_valid' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'csum_complete_sw' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'csum_level' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'inner_protocol_type' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'remcsum_offload' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'offload_fwd_mark' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'offload_mr_fwd_mark' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'sender_cpu' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'reserved_tailroom' not described in 'sk_buff'
include/linux/skbuff.h:850: warning: Function parameter or member 'inner_ipproto' not described in 'sk_buff'
include/net/sock.h:234: warning: Function parameter or member 'skc_addrpair' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_portpair' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_ipv6only' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_net_refcnt' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_v6_daddr' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_v6_rcv_saddr' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_cookie' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_listener' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_tw_dr' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_rcv_wnd' not described in 'sock_common'
include/net/sock.h:234: warning: Function parameter or member 'skc_tw_rcv_nxt' not described in 'sock_common'
include/net/sock.h:488: warning: Function parameter or member 'sk_backlog.rmem_alloc' not described in 'sock'
include/net/sock.h:488: warning: Function parameter or member 'sk_backlog.len' not described in 'sock'
include/net/sock.h:488: warning: Function parameter or member 'sk_backlog.head' not described in 'sock'
include/net/sock.h:488: warning: Function parameter or member 'sk_backlog.tail' not described in 'sock'
include/net/sock.h:488: warning: Function parameter or member 'sk_wq_raw' not described in 'sock'
include/net/sock.h:488: warning: Function parameter or member 'tcp_rtx_queue' not described in 'sock'
include/net/sock.h:488: warning: Function parameter or member 'sk_route_forced_caps' not described in 'sock'
include/linux/netdevice.h:1952: warning: Function parameter or member 'adj_list.upper' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'adj_list.lower' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'gso_partial_features' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'switchdev_ops' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'l3mdev_ops' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'xfrmdev_ops' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'name_assign_type' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'ieee802154_ptr' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'mpls_ptr' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'xdp_prog' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'gro_flush_timeout' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'nf_hooks_ingress' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member '____cacheline_aligned_in_smp' not described in 'net_device'
include/linux/netdevice.h:1952: warning: Function parameter or member 'qdisc_hash' not described in 'net_device'
include/linux/phylink.h:56: warning: Function parameter or member '__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising' not described in 'phylink_link_state'
include/linux/phylink.h:56: warning: Function parameter or member '__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising' not described in 'phylink_link_state'
include/linux/rcupdate.h:570: ERROR: Unexpected indentation.
include/linux/rcupdate.h:574: ERROR: Unexpected indentation.
include/linux/rcupdate.h:578: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/rcupdate.h:580: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/rcupdate.h:580: WARNING: Inline literal start-string without end-string.
kernel/time/timer.c:1259: ERROR: Unexpected indentation.
kernel/time/timer.c:1261: ERROR: Unexpected indentation.
kernel/time/timer.c:1262: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/wait.h:110: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/wait.h:113: ERROR: Unexpected indentation.
include/linux/wait.h:115: WARNING: Block quote ends without a blank line; unexpected unindent.
kernel/time/hrtimer.c:1113: WARNING: Block quote ends without a blank line; unexpected unindent.
kernel/signal.c:327: WARNING: Inline literal start-string without end-string.
drivers/video/fbdev/core/modedb.c:647: WARNING: Inline strong start-string without end-string.
drivers/video/fbdev/core/modedb.c:647: WARNING: Inline strong start-string without end-string.
drivers/video/fbdev/core/modedb.c:647: WARNING: Inline strong start-string without end-string.
drivers/video/fbdev/core/modedb.c:647: WARNING: Inline strong start-string without end-string.
include/linux/iio/iio.h:191: ERROR: Unexpected indentation.
include/linux/iio/iio.h:192: WARNING: Block quote ends without a blank line; unexpected unindent.
include/linux/iio/iio.h:198: WARNING: Definition list ends without a blank line; unexpected unindent.
drivers/ata/libata-core.c:5940: ERROR: Unknown target name: "hw".
drivers/message/fusion/mptbase.c:5052: WARNING: Definition list ends without a blank line; unexpected unindent.
drivers/tty/serial/serial_core.c:1903: WARNING: Definition list ends without a blank line; unexpected unindent.
include/linux/mtd/rawnand.h:805: ERROR: Unexpected indentation.
include/linux/mtd/rawnand.h:1391: WARNING: Inline strong start-string without end-string.
include/linux/mtd/rawnand.h:1393: WARNING: Inline strong start-string without end-string.
include/linux/regulator/driver.h:273: ERROR: Unknown target name: "regulator_regmap_x_voltage".
Documentation/driver-api/slimbus.rst:93: WARNING: Title underline too short.
vim +850 include/linux/skbuff.h
^1da177e Linus Torvalds 2005-04-16 @850
:::::: The code at line 850 was first introduced by commit
:::::: 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 Linux-2.6.12-rc2
:::::: TO: Linus Torvalds <torvalds@ppc970.osdl.org>
:::::: CC: Linus Torvalds <torvalds@ppc970.osdl.org>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 6801 bytes --]
^ permalink raw reply [flat|nested] 34+ messages in thread
* [PATCH v4 net-next 18/19] ipv6: frags: get rid of ip6frag_skb_cb/FRAG6_CB
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (16 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 17/19] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB Eric Dumazet
@ 2018-03-31 19:58 ` Eric Dumazet
2018-03-31 19:59 ` [PATCH v4 net-next 19/19] inet: frags: get rid of nf_ct_frag6_skb_cb/NFCT_FRAG6_CB Eric Dumazet
2018-04-01 3:25 ` [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag David Miller
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:58 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
ip6_frag_queue uses skb->cb[] to store the fragment offset, meaning that
we could use two cache lines per skb when finding the insertion point,
if for some reason inet6_skb_parm size is increased in the future.
By using skb->ip_defrag_offset instead of skb->cb[], we pack all
the fields in a single cache line, matching what we did for IPv4.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv6/reassembly.c | 30 ++++++++++++------------------
1 file changed, 12 insertions(+), 18 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2127da130dc2cee677059247d5e079a8afbca13d..7b52efc63f6adad2c242ae1171e5b7b27b40f0bf 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -62,13 +62,6 @@
static const char ip6_frag_cache_name[] = "ip6-frags";
-struct ip6frag_skb_cb {
- struct inet6_skb_parm h;
- int offset;
-};
-
-#define FRAG6_CB(skb) ((struct ip6frag_skb_cb *)((skb)->cb))
-
static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
@@ -250,13 +243,13 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
* this fragment, right?
*/
prev = fq->q.fragments_tail;
- if (!prev || FRAG6_CB(prev)->offset < offset) {
+ if (!prev || prev->ip_defrag_offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = fq->q.fragments; next != NULL; next = next->next) {
- if (FRAG6_CB(next)->offset >= offset)
+ if (next->ip_defrag_offset >= offset)
break; /* bingo! */
prev = next;
}
@@ -271,14 +264,20 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
/* Check for overlap with preceding fragment. */
if (prev &&
- (FRAG6_CB(prev)->offset + prev->len) > offset)
+ (prev->ip_defrag_offset + prev->len) > offset)
goto discard_fq;
/* Look for overlap with succeeding segment. */
- if (next && FRAG6_CB(next)->offset < end)
+ if (next && next->ip_defrag_offset < end)
goto discard_fq;
- FRAG6_CB(skb)->offset = offset;
+ /* Note : skb->ip_defrag_offset and skb->dev share the same location */
+ dev = skb->dev;
+ if (dev)
+ fq->iif = dev->ifindex;
+ /* Makes sure compiler wont do silly aliasing games */
+ barrier();
+ skb->ip_defrag_offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
@@ -289,11 +288,6 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
else
fq->q.fragments = skb;
- dev = skb->dev;
- if (dev) {
- fq->iif = dev->ifindex;
- skb->dev = NULL;
- }
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
@@ -380,7 +374,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
}
WARN_ON(head == NULL);
- WARN_ON(FRAG6_CB(head)->offset != 0);
+ WARN_ON(head->ip_defrag_offset != 0);
/* Unfragmented part is taken from the first segment. */
payload_len = ((head->data - skb_network_header(head)) -
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* [PATCH v4 net-next 19/19] inet: frags: get rid of nf_ct_frag6_skb_cb/NFCT_FRAG6_CB
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (17 preceding siblings ...)
2018-03-31 19:58 ` [PATCH v4 net-next 18/19] ipv6: frags: get rid of ip6frag_skb_cb/FRAG6_CB Eric Dumazet
@ 2018-03-31 19:59 ` Eric Dumazet
2018-04-01 3:25 ` [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag David Miller
19 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-03-31 19:59 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
nf_ct_frag6_queue() uses skb->cb[] to store the fragment offset,
meaning that we could use two cache lines per skb when finding
the insertion point, if for some reason inet6_skb_parm size
is increased in the future.
By using skb->ip_defrag_offset instead of skb->cb[] we pack all the fields
in a single cache line, matching what we did for IPv4.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv6/netfilter/nf_conntrack_reasm.c | 29 ++++++++++---------------
1 file changed, 11 insertions(+), 18 deletions(-)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 603a395928593a071aff28105578d3bfdbf1b31e..3622aac343aea3cd0d8165d8681f42595735cd90 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -52,14 +52,6 @@
static const char nf_frags_cache_name[] = "nf-frags";
-struct nf_ct_frag6_skb_cb
-{
- struct inet6_skb_parm h;
- int offset;
-};
-
-#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb))
-
static struct inet_frags nf_frags;
#ifdef CONFIG_SYSCTL
@@ -270,13 +262,13 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
* this fragment, right?
*/
prev = fq->q.fragments_tail;
- if (!prev || NFCT_FRAG6_CB(prev)->offset < offset) {
+ if (!prev || prev->ip_defrag_offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = fq->q.fragments; next != NULL; next = next->next) {
- if (NFCT_FRAG6_CB(next)->offset >= offset)
+ if (next->ip_defrag_offset >= offset)
break; /* bingo! */
prev = next;
}
@@ -292,14 +284,19 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
/* Check for overlap with preceding fragment. */
if (prev &&
- (NFCT_FRAG6_CB(prev)->offset + prev->len) > offset)
+ (prev->ip_defrag_offset + prev->len) > offset)
goto discard_fq;
/* Look for overlap with succeeding segment. */
- if (next && NFCT_FRAG6_CB(next)->offset < end)
+ if (next && next->ip_defrag_offset < end)
goto discard_fq;
- NFCT_FRAG6_CB(skb)->offset = offset;
+ /* Note : skb->ip_defrag_offset and skb->dev share the same location */
+ if (skb->dev)
+ fq->iif = skb->dev->ifindex;
+ /* Makes sure compiler wont do silly aliasing games */
+ barrier();
+ skb->ip_defrag_offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
@@ -310,10 +307,6 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
else
fq->q.fragments = skb;
- if (skb->dev) {
- fq->iif = skb->dev->ifindex;
- skb->dev = NULL;
- }
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
@@ -357,7 +350,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
inet_frag_kill(&fq->q);
WARN_ON(head == NULL);
- WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
+ WARN_ON(head->ip_defrag_offset != 0);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
` (18 preceding siblings ...)
2018-03-31 19:59 ` [PATCH v4 net-next 19/19] inet: frags: get rid of nf_ct_frag6_skb_cb/NFCT_FRAG6_CB Eric Dumazet
@ 2018-04-01 3:25 ` David Miller
2018-05-28 9:12 ` Tariq Toukan
19 siblings, 1 reply; 34+ messages in thread
From: David Miller @ 2018-04-01 3:25 UTC (permalink / raw)
To: edumazet
Cc: netdev, fw, herbert, tgraf, brouer, alex.aring, stefan, ktkhai,
eric.dumazet
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 31 Mar 2018 12:58:41 -0700
> IP defrag processing is one of the remaining problematic layer in linux.
>
> It uses static hash tables of 1024 buckets, and up to 128 items per bucket.
>
> A work queue is supposed to garbage collect items when host is under memory
> pressure, and doing a hash rebuild, changing seed used in hash computations.
>
> This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
> occurring every 5 seconds if host is under fire.
>
> Then there is the problem of sharing this hash table for all netns.
>
> It is time to switch to rhashtables, and allocate one of them per netns
> to speedup netns dismantle, since this is a critical metric these days.
>
> Lookup is now using RCU, and 64bit hosts can now provision whatever amount
> of memory needed to handle the expected workloads.
...
Series applied, thanks Eric.
^ permalink raw reply [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-04-01 3:25 ` [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag David Miller
@ 2018-05-28 9:12 ` Tariq Toukan
2018-05-28 14:52 ` Alexander Aring
0 siblings, 1 reply; 34+ messages in thread
From: Tariq Toukan @ 2018-05-28 9:12 UTC (permalink / raw)
To: David Miller, edumazet
Cc: netdev, fw, herbert, tgraf, brouer, alex.aring, stefan, ktkhai,
eric.dumazet, Moshe Shemesh, Eran Ben Elisha
On 01/04/2018 6:25 AM, David Miller wrote:
> From: Eric Dumazet <edumazet@google.com>
> Date: Sat, 31 Mar 2018 12:58:41 -0700
>
>> IP defrag processing is one of the remaining problematic layer in linux.
>>
>> It uses static hash tables of 1024 buckets, and up to 128 items per bucket.
>>
>> A work queue is supposed to garbage collect items when host is under memory
>> pressure, and doing a hash rebuild, changing seed used in hash computations.
>>
>> This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
>> occurring every 5 seconds if host is under fire.
>>
>> Then there is the problem of sharing this hash table for all netns.
>>
>> It is time to switch to rhashtables, and allocate one of them per netns
>> to speedup netns dismantle, since this is a critical metric these days.
>>
>> Lookup is now using RCU, and 64bit hosts can now provision whatever amount
>> of memory needed to handle the expected workloads.
> ...
>
> Series applied, thanks Eric.
>
Hi Eric,
Recently my colleague (Moshe Shemesh) got a failure in upstream
regression, which is related to this patchset. We don’t see the failure
before it was merged.
We checked again on net-next (from May 24th), it still reproduces.
The test case runs netperf with ipv6 udp single stream (64K message size).
After the change we see huge packet loss:
145,134 messages failed out of 145,419 (only 285 fully received)
[root@reg-l-vrt-67100-104 ~]# netperf -H
fe80::e61d:2dff:feca:c7c3%ens9,inet6 -t udp_stream --
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
fe80::e61d:2dff:feca:c7c3%ens9 () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 145419 0 7620.35
212992 10.00 285 14.93
By checking nstat counters we see that Ip6ReasmFails got very high:
#kernel
...
Ip6InReceives 6665965 0.0
Ip6InDelivers 300 0.0
Ip6OutRequests 9 0.0
Ip6ReasmReqds 6665950 0.0
Ip6ReasmOKs 285 0.0
Ip6ReasmFails 6650890 0.0
Ip6InOctets 9813929354 0.0
Ip6OutOctets 2608 0.0
Ip6InNoECTPkts 6665965 0.0
...
Udp6InDatagrams 286 0.0
...
Same test on kernel without the patchset got low failure rate:
Only 810 messages failed out of 114,112 (113,302 fully received)
[root@reg-l-vrt-67100-104 ~]# netperf -H
fe80::e61d:2dff:feca:c7c3%ens9,inet6 -t udp_stream --
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
fe80::e61d:2dff:feca:c7c3%ens9 () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 114112 0 5979.69
212992 10.00 113302 5937.24
nstat counters to compare:
#kernel
...
Ip6InReceives 5249166 0.0
Ip6InDelivers 114126 0.0
Ip6OutRequests 8 0.0
Ip6ReasmReqds 5249152 0.0
Ip6ReasmOKs 114112 0.0
Ip6InOctets 7728009224 0.0
Ip6OutOctets 2544 0.0
Ip6InNoECTPkts 5249166 0.0
...
Udp6InDatagrams 113303 0.0
Udp6InErrors 810 0.0
Udp6RcvbufErrors 810 0.0
...
We did not get to bisect within the patchset yet.
Regards,
Tariq and Moshe
^ permalink raw reply [flat|nested] 34+ messages in thread
* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-28 9:12 ` Tariq Toukan
@ 2018-05-28 14:52 ` Alexander Aring
2018-05-28 16:09 ` Eric Dumazet
0 siblings, 1 reply; 34+ messages in thread
From: Alexander Aring @ 2018-05-28 14:52 UTC (permalink / raw)
To: Tariq Toukan
Cc: David Miller, edumazet, netdev, fw, herbert, tgraf, brouer,
alex.aring, stefan, ktkhai, eric.dumazet, Moshe Shemesh,
Eran Ben Elisha
Hi,
On Mon, May 28, 2018 at 12:12:42PM +0300, Tariq Toukan wrote:
>
>
> On 01/04/2018 6:25 AM, David Miller wrote:
> > From: Eric Dumazet <edumazet@google.com>
> > Date: Sat, 31 Mar 2018 12:58:41 -0700
> >
> > > IP defrag processing is one of the remaining problematic layer in linux.
> > >
> > > It uses static hash tables of 1024 buckets, and up to 128 items per bucket.
> > >
> > > A work queue is supposed to garbage collect items when host is under memory
> > > pressure, and doing a hash rebuild, changing seed used in hash computations.
> > >
> > > This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
> > > occurring every 5 seconds if host is under fire.
> > >
> > > Then there is the problem of sharing this hash table for all netns.
> > >
> > > It is time to switch to rhashtables, and allocate one of them per netns
> > > to speedup netns dismantle, since this is a critical metric these days.
> > >
> > > Lookup is now using RCU, and 64bit hosts can now provision whatever amount
> > > of memory needed to handle the expected workloads.
> > ...
> >
> > Series applied, thanks Eric.
> >
>
> Hi Eric,
>
> Recently my colleague (Moshe Shemesh) got a failure in upstream regression,
> which is related to this patchset. We don’t see the failure before it was
> merged.
> We checked again on net-next (from May 24th), it still reproduces.
>
> The test case runs netperf with ipv6 udp single stream (64K message size).
> After the change we see huge packet loss:
> 145,134 messages failed out of 145,419 (only 285 fully received)
>
as somebody who had similar issues with this patch series I can tell you
about what happened for the 6LoWPAN fragmentation.
The issue sounds similar, but there is too much missing information here
to say something about if you have exactly the issue which we had.
Our problem:
The patch series uses memcmp() to compare hash keys, we had some padding
bytes in our hash key and it occurs that we had sometimes random bytes
in this structure when it's put on stack. We solved it by a struct
foo_key bar = {}, which in case of gcc it _seems_ it makes a whole
memset(bar, 0, ..) on the structure.
I asked on the netdev mailinglist how to deal with this problem in
general, because = {} works in case of gcc, others compilers may have a
different handling or even gcc will changes this behaviour in future.
I got no reply so I did what it works for me. :-)
At least maybe a memcmp() on structures should never be used, it should
be compared by field. I would recommend this way when the compiler is
always clever enough to optimize it in some cases, but I am not so a
compiler expert to say anything about that.
I checked the hash key structures for x86_64 and pahole, so far I didn't
find any padding bytes there, but it might be different on
architectures or ?compiler?.
Additional useful information to check if you running into the same problem
would be:
- Which architecture do you use?
- Do you have similar problems with a veth setup?
You could also try this:
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index b939b94e7e91..40ece9ab8b12 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -142,19 +142,19 @@ static void ip6_frag_expire(struct timer_list *t)
static struct frag_queue *
fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
{
- struct frag_v6_compare_key key = {
- .id = id,
- .saddr = hdr->saddr,
- .daddr = hdr->daddr,
- .user = IP6_DEFRAG_LOCAL_DELIVER,
- .iif = iif,
- };
+ struct frag_v6_compare_key key = {};
struct inet_frag_queue *q;
if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
IPV6_ADDR_LINKLOCAL)))
key.iif = 0;
+ key.id = id;
+ key.saddr = hdr->saddr;
+ key.daddr = hdr->daddr;
+ key.user = IP6_DEFRAG_LOCAL_DELIVER;
+ key.iif = iif;
+
q = inet_frag_find(&net->ipv6.frags, &key);
if (!q)
return NULL;
- Alex
^ permalink raw reply related [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-28 14:52 ` Alexander Aring
@ 2018-05-28 16:09 ` Eric Dumazet
2018-05-30 7:20 ` Tariq Toukan
2018-05-30 9:20 ` Jesper Dangaard Brouer
0 siblings, 2 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-05-28 16:09 UTC (permalink / raw)
To: Alexander Aring, Tariq Toukan
Cc: David Miller, edumazet, netdev, fw, herbert, tgraf, brouer,
alex.aring, stefan, ktkhai, eric.dumazet, Moshe Shemesh,
Eran Ben Elisha
On 05/28/2018 07:52 AM, Alexander Aring wrote:
> as somebody who had similar issues with this patch series I can tell you
> about what happened for the 6LoWPAN fragmentation.
>
> The issue sounds similar, but there is too much missing information here
> to say something about if you have exactly the issue which we had.
>
> Our problem:
>
> The patch series uses memcmp() to compare hash keys, we had some padding
> bytes in our hash key and it occurs that we had sometimes random bytes
> in this structure when it's put on stack. We solved it by a struct
> foo_key bar = {}, which in case of gcc it _seems_ it makes a whole
> memset(bar, 0, ..) on the structure.
>
> I asked on the netdev mailinglist how to deal with this problem in
> general, because = {} works in case of gcc, others compilers may have a
> different handling or even gcc will changes this behaviour in future.
> I got no reply so I did what it works for me. :-)
>
> At least maybe a memcmp() on structures should never be used, it should
> be compared by field. I would recommend this way when the compiler is
> always clever enough to optimize it in some cases, but I am not so a
> compiler expert to say anything about that.
>
> I checked the hash key structures for x86_64 and pahole, so far I didn't
> find any padding bytes there, but it might be different on
> architectures or ?compiler?.
>
> Additional useful information to check if you running into the same problem
> would be:
>
> - Which architecture do you use?
>
> - Do you have similar problems with a veth setup?
>
> You could also try this:
>
> diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
> index b939b94e7e91..40ece9ab8b12 100644
> --- a/net/ipv6/reassembly.c
> +++ b/net/ipv6/reassembly.c
> @@ -142,19 +142,19 @@ static void ip6_frag_expire(struct timer_list *t)
> static struct frag_queue *
> fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
> {
> - struct frag_v6_compare_key key = {
> - .id = id,
> - .saddr = hdr->saddr,
> - .daddr = hdr->daddr,
> - .user = IP6_DEFRAG_LOCAL_DELIVER,
> - .iif = iif,
> - };
> + struct frag_v6_compare_key key = {};
> struct inet_frag_queue *q;
>
> if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
> IPV6_ADDR_LINKLOCAL)))
> key.iif = 0;
>
> + key.id = id;
> + key.saddr = hdr->saddr;
> + key.daddr = hdr->daddr;
> + key.user = IP6_DEFRAG_LOCAL_DELIVER;
> + key.iif = iif;
> +
> q = inet_frag_find(&net->ipv6.frags, &key);
> if (!q)
> return NULL;
>
> - Alex
>
Hi Alex.
This patch makes no sense, since struct frag_v6_compare_key has no hole.
Only 6LoWPAN had a problem really, because of its way of having unions (and holes).
Also note that your patch would break the case when we force key.iif to be zero.
Tariq, here are my test results : No drops for me.
# ./netperf -H 2607:f8b0:8099:e18:: -t UDP_STREAM
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to 2607:f8b0:8099:e18:: () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 202117 0 10592.00
212992 10.00 0 0.00
Somehow, you might send packets too fast and receiver has a problem with that ?
For particular needs, you might need to adjust :
/proc/sys/net/ipv6/ip6frag_time (to 2 seconds instead of the default of 60)
/proc/sys/net/ipv6/ip6frag_low_thresh
/proc/sys/net/ipv6/ip6frag_high_thresh
Once your receiver has filled its capacity with frags, the default of 60 seconds to garbage collect
might be the reason you notice a problem.
Check :
grep FRAG6 /proc/net/sockstat6
On Google servers we multiply by 25 the limits for ipv6 frags memory usage :
/proc/sys/net/ipv6/ip6frag_high_thresh:104857600 (instead of 4MB)
/proc/sys/net/ipv6/ip6frag_low_thresh:78643200 (instead of 3 MB)
When using 64KB datagrams, note that the truesize of the datagram would be about 44 * 2 = 88 KB,
so after ~40 lost packets in the network, you no longer can accept ipv6 fragments, until garbage
collector evicted old datagrams.
^ permalink raw reply [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-28 16:09 ` Eric Dumazet
@ 2018-05-30 7:20 ` Tariq Toukan
2018-05-30 7:36 ` Eric Dumazet
2018-05-31 12:18 ` Moshe Shemesh
2018-05-30 9:20 ` Jesper Dangaard Brouer
1 sibling, 2 replies; 34+ messages in thread
From: Tariq Toukan @ 2018-05-30 7:20 UTC (permalink / raw)
To: Eric Dumazet, Alexander Aring, Tariq Toukan, Moshe Shemesh
Cc: David Miller, edumazet, netdev, fw, herbert, tgraf, brouer,
alex.aring, stefan, ktkhai, Eran Ben Elisha
On 28/05/2018 7:09 PM, Eric Dumazet wrote:
>
>
> On 05/28/2018 07:52 AM, Alexander Aring wrote:
>
>> as somebody who had similar issues with this patch series I can tell you
>> about what happened for the 6LoWPAN fragmentation.
>>
>> The issue sounds similar, but there is too much missing information here
>> to say something about if you have exactly the issue which we had.
>>
>> Our problem:
>>
>> The patch series uses memcmp() to compare hash keys, we had some padding
>> bytes in our hash key and it occurs that we had sometimes random bytes
>> in this structure when it's put on stack. We solved it by a struct
>> foo_key bar = {}, which in case of gcc it _seems_ it makes a whole
>> memset(bar, 0, ..) on the structure.
>>
>> I asked on the netdev mailinglist how to deal with this problem in
>> general, because = {} works in case of gcc, others compilers may have a
>> different handling or even gcc will changes this behaviour in future.
>> I got no reply so I did what it works for me. :-)
>>
>> At least maybe a memcmp() on structures should never be used, it should
>> be compared by field. I would recommend this way when the compiler is
>> always clever enough to optimize it in some cases, but I am not so a
>> compiler expert to say anything about that.
>>
>> I checked the hash key structures for x86_64 and pahole, so far I didn't
>> find any padding bytes there, but it might be different on
>> architectures or ?compiler?.
>>
>> Additional useful information to check if you running into the same problem
>> would be:
>>
>> - Which architecture do you use?
>>
>> - Do you have similar problems with a veth setup?
>>
>> You could also try this:
>>
>> diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
>> index b939b94e7e91..40ece9ab8b12 100644
>> --- a/net/ipv6/reassembly.c
>> +++ b/net/ipv6/reassembly.c
>> @@ -142,19 +142,19 @@ static void ip6_frag_expire(struct timer_list *t)
>> static struct frag_queue *
>> fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
>> {
>> - struct frag_v6_compare_key key = {
>> - .id = id,
>> - .saddr = hdr->saddr,
>> - .daddr = hdr->daddr,
>> - .user = IP6_DEFRAG_LOCAL_DELIVER,
>> - .iif = iif,
>> - };
>> + struct frag_v6_compare_key key = {};
>> struct inet_frag_queue *q;
>>
>> if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
>> IPV6_ADDR_LINKLOCAL)))
>> key.iif = 0;
>>
>> + key.id = id;
>> + key.saddr = hdr->saddr;
>> + key.daddr = hdr->daddr;
>> + key.user = IP6_DEFRAG_LOCAL_DELIVER;
>> + key.iif = iif;
>> +
>> q = inet_frag_find(&net->ipv6.frags, &key);
>> if (!q)
>> return NULL;
>>
>> - Alex
>>
>
> Hi Alex.
>
> This patch makes no sense, since struct frag_v6_compare_key has no hole.
>
> Only 6LoWPAN had a problem really, because of its way of having unions (and holes).
>
> Also note that your patch would break the case when we force key.iif to be zero.
>
>
> Tariq, here are my test results : No drops for me.
>
> # ./netperf -H 2607:f8b0:8099:e18:: -t UDP_STREAM
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to 2607:f8b0:8099:e18:: () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 202117 0 10592.00
> 212992 10.00 0 0.00
>
> Somehow, you might send packets too fast and receiver has a problem with that ?
Not sure, the transmit BW you get is higher than what we saw.
Anyway, we'll check this.
> For particular needs, you might need to adjust :
>
> /proc/sys/net/ipv6/ip6frag_time (to 2 seconds instead of the default of 60)
> /proc/sys/net/ipv6/ip6frag_low_thresh
> /proc/sys/net/ipv6/ip6frag_high_thresh
>
> Once your receiver has filled its capacity with frags, the default of 60 seconds to garbage collect
> might be the reason you notice a problem.
>
> Check :
> grep FRAG6 /proc/net/sockstat6
>
> On Google servers we multiply by 25 the limits for ipv6 frags memory usage :
>
> /proc/sys/net/ipv6/ip6frag_high_thresh:104857600 (instead of 4MB)
> /proc/sys/net/ipv6/ip6frag_low_thresh:78643200 (instead of 3 MB)
>
> When using 64KB datagrams, note that the truesize of the datagram would be about 44 * 2 = 88 KB,
> so after ~40 lost packets in the network, you no longer can accept ipv6 fragments, until garbage
> collector evicted old datagrams.
>
Great.
Moshe, please try the suggested above.
In case these values dramatically improve performance, maybe its time to
change the default.
Thanks,
Tariq
>
>
>
>
>
>
^ permalink raw reply [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-30 7:20 ` Tariq Toukan
@ 2018-05-30 7:36 ` Eric Dumazet
2018-05-30 14:42 ` Tariq Toukan
2018-05-31 12:18 ` Moshe Shemesh
1 sibling, 1 reply; 34+ messages in thread
From: Eric Dumazet @ 2018-05-30 7:36 UTC (permalink / raw)
To: Tariq Toukan
Cc: Eric Dumazet, aring, moshe, David Miller, netdev,
Florian Westphal, Herbert Xu, Thomas Graf, Jesper Dangaard Brouer,
Alexander Aring, Stefan Schmidt, Kirill Tkhai, Eran Ben Elisha
On Wed, May 30, 2018 at 3:20 AM Tariq Toukan <tariqt@mellanox.com> wrote:
> Not sure, the transmit BW you get is higher than what we saw.
> Anyway, we'll check this.
That is on a 40Gbit test bed (mlx4 cx/3), maybe you were using a 10Gbit NIC
?
^ permalink raw reply [flat|nested] 34+ messages in thread
* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-30 7:36 ` Eric Dumazet
@ 2018-05-30 14:42 ` Tariq Toukan
0 siblings, 0 replies; 34+ messages in thread
From: Tariq Toukan @ 2018-05-30 14:42 UTC (permalink / raw)
To: Eric Dumazet, Tariq Toukan, moshe
Cc: Eric Dumazet, aring, David Miller, netdev, Florian Westphal,
Herbert Xu, Thomas Graf, Jesper Dangaard Brouer, Alexander Aring,
Stefan Schmidt, Kirill Tkhai, Eran Ben Elisha
On 30/05/2018 10:36 AM, Eric Dumazet wrote:
> On Wed, May 30, 2018 at 3:20 AM Tariq Toukan <tariqt@mellanox.com> wrote:
>
>> Not sure, the transmit BW you get is higher than what we saw.
>> Anyway, we'll check this.
>
> That is on a 40Gbit test bed (mlx4 cx/3), maybe you were using a 10Gbit NIC
> ?
>
It is a ConnectX-4 50G (mlx5).
Moshe is trying out the tuning you suggested.
He'll update once he's done.
^ permalink raw reply [flat|nested] 34+ messages in thread
* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-30 7:20 ` Tariq Toukan
2018-05-30 7:36 ` Eric Dumazet
@ 2018-05-31 12:18 ` Moshe Shemesh
2018-05-31 14:05 ` Eric Dumazet
1 sibling, 1 reply; 34+ messages in thread
From: Moshe Shemesh @ 2018-05-31 12:18 UTC (permalink / raw)
To: Tariq Toukan, Eric Dumazet, Alexander Aring
Cc: David Miller, edumazet, netdev, fw, herbert, tgraf, brouer,
alex.aring, stefan, ktkhai, Eran Ben Elisha
On 5/30/2018 10:20 AM, Tariq Toukan wrote:
>
>
> On 28/05/2018 7:09 PM, Eric Dumazet wrote:
>>
>>
>> On 05/28/2018 07:52 AM, Alexander Aring wrote:
>>
>>> as somebody who had similar issues with this patch series I can tell you
>>> about what happened for the 6LoWPAN fragmentation.
>>>
>>> The issue sounds similar, but there is too much missing information here
>>> to say something about if you have exactly the issue which we had.
>>>
>>> Our problem:
>>>
>>> The patch series uses memcmp() to compare hash keys, we had some padding
>>> bytes in our hash key and it occurs that we had sometimes random bytes
>>> in this structure when it's put on stack. We solved it by a struct
>>> foo_key bar = {}, which in case of gcc it _seems_ it makes a whole
>>> memset(bar, 0, ..) on the structure.
>>>
>>> I asked on the netdev mailinglist how to deal with this problem in
>>> general, because = {} works in case of gcc, others compilers may have a
>>> different handling or even gcc will changes this behaviour in future.
>>> I got no reply so I did what it works for me. :-)
>>>
>>> At least maybe a memcmp() on structures should never be used, it should
>>> be compared by field. I would recommend this way when the compiler is
>>> always clever enough to optimize it in some cases, but I am not so a
>>> compiler expert to say anything about that.
>>>
>>> I checked the hash key structures for x86_64 and pahole, so far I didn't
>>> find any padding bytes there, but it might be different on
>>> architectures or ?compiler?.
>>>
>>> Additional useful information to check if you running into the same
>>> problem
>>> would be:
>>>
>>> - Which architecture do you use?
>>>
>>> - Do you have similar problems with a veth setup?
>>>
>>> You could also try this:
>>>
>>> diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
>>> index b939b94e7e91..40ece9ab8b12 100644
>>> --- a/net/ipv6/reassembly.c
>>> +++ b/net/ipv6/reassembly.c
>>> @@ -142,19 +142,19 @@ static void ip6_frag_expire(struct timer_list *t)
>>> static struct frag_queue *
>>> fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int
>>> iif)
>>> {
>>> - struct frag_v6_compare_key key = {
>>> - .id = id,
>>> - .saddr = hdr->saddr,
>>> - .daddr = hdr->daddr,
>>> - .user = IP6_DEFRAG_LOCAL_DELIVER,
>>> - .iif = iif,
>>> - };
>>> + struct frag_v6_compare_key key = {};
>>> struct inet_frag_queue *q;
>>> if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
>>> IPV6_ADDR_LINKLOCAL)))
>>> key.iif = 0;
>>> + key.id = id;
>>> + key.saddr = hdr->saddr;
>>> + key.daddr = hdr->daddr;
>>> + key.user = IP6_DEFRAG_LOCAL_DELIVER;
>>> + key.iif = iif;
>>> +
>>> q = inet_frag_find(&net->ipv6.frags, &key);
>>> if (!q)
>>> return NULL;
>>>
>>> - Alex
>>>
>>
>> Hi Alex.
>>
>> This patch makes no sense, since struct frag_v6_compare_key has no hole.
>>
>> Only 6LoWPAN had a problem really, because of its way of having unions
>> (and holes).
>>
>> Also note that your patch would break the case when we force key.iif
>> to be zero.
>>
>>
>> Tariq, here are my test results : No drops for me.
>>
>> # ./netperf -H 2607:f8b0:8099:e18:: -t UDP_STREAM
>> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
>> 2607:f8b0:8099:e18:: () port 0 AF_INET6
>> Socket Message Elapsed Messages
>> Size Size Time Okay Errors Throughput
>> bytes bytes secs # # 10^6bits/sec
>>
>> 212992 65507 10.00 202117 0 10592.00
>> 212992 10.00 0 0.00
>>
>> Somehow, you might send packets too fast and receiver has a problem
>> with that ?
>
> Not sure, the transmit BW you get is higher than what we saw.
> Anyway, we'll check this.
>
>> For particular needs, you might need to adjust :
>>
>> /proc/sys/net/ipv6/ip6frag_time (to 2 seconds instead of the default
>> of 60)
>> /proc/sys/net/ipv6/ip6frag_low_thresh
>> /proc/sys/net/ipv6/ip6frag_high_thresh
>>
>> Once your receiver has filled its capacity with frags, the default of
>> 60 seconds to garbage collect
>> might be the reason you notice a problem.
>>
>> Check :
>> grep FRAG6 /proc/net/sockstat6
>>
>> On Google servers we multiply by 25 the limits for ipv6 frags memory
>> usage :
>>
>> /proc/sys/net/ipv6/ip6frag_high_thresh:104857600 (instead of 4MB)
>> /proc/sys/net/ipv6/ip6frag_low_thresh:78643200 (instead of 3 MB)
>>
>> When using 64KB datagrams, note that the truesize of the datagram
>> would be about 44 * 2 = 88 KB,
>> so after ~40 lost packets in the network, you no longer can accept
>> ipv6 fragments, until garbage
>> collector evicted old datagrams.
>>
>
> Great.
> Moshe, please try the suggested above.
I do see big improvement after changing the 3 parameters as Eric suggested:
/proc/sys/net/ipv6/ip6frag_time set to 2
/proc/sys/net/ipv6/ip6frag_low_thresh set to 104857600
/proc/sys/net/ipv6/ip6frag_high_thresh set to 78643200
[root@reg-l-vrt-67100-104 linux-stable]# netperf -H
fe80::7efe:90ff:fed5:bb48%ens9,inet6 -t udp_stream --
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
fe80::7efe:90ff:fed5:bb48%ens9 () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 156387 0 8194.60
212992 10.00 76901 4029.57
#kernel
Ip6InReceives 7107999 0.0
Ip6InDelivers 114126 0.0
Ip6OutRequests 47 0.0
Ip6ReasmTimeout 5115 0.0
Ip6ReasmReqds 7107987 0.0
Ip6ReasmOKs 114114 0.0
Ip6ReasmFails 1714146 0.0
...
Udp6InDatagrams 112486 0.0
Udp6InErrors 1629 0.0
Udp6RcvbufErrors 1629 0.0
...
While before these parameters settings I got:
[root@reg-l-vrt-67100-104 ~]# netperf -H
fe80::e61d:2dff:feca:c7c3%ens9,inet6 -t udp_stream --
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
fe80::e61d:2dff:feca:c7c3%ens9 () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 145419 0 7620.35
212992 10.00 285 14.93
#kernel
Ip6InReceives 6665965 0.0
Ip6InDelivers 300 0.0
Ip6OutRequests 9 0.0
Ip6ReasmReqds 6665950 0.0
Ip6ReasmOKs 285 0.0
Ip6ReasmFails 6650890 0.0
...
Udp6InDatagrams 286 0.0
however, before the patchset, I got much better results:
[root@reg-l-vrt-67100-104 linux-stable]# netperf -H
fe80::7efe:90ff:fed5:bb48%ens9,inet6 -t udp_stream --
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
fe80::7efe:90ff:fed5:bb48%ens9 () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 158935 0 8328.32
212992 10.00 144652 7579.88
#kernel
Ip6InReceives 7088903 0.0
Ip6InDelivers 154117 0.0
Ip6OutRequests 9 0.0
Ip6ReasmReqds 7088889 0.0
Ip6ReasmOKs 154103 0.0
...
Udp6InDatagrams 144653 0.0
Udp6InErrors 9451 0.0
Udp6RcvbufErrors 9451 0.0
>
> In case these values dramatically improve performance, maybe its time to
> change the default.
>
> Thanks,
> Tariq
>
>>
>>
>>
>>
>>
>>
^ permalink raw reply [flat|nested] 34+ messages in thread* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-31 12:18 ` Moshe Shemesh
@ 2018-05-31 14:05 ` Eric Dumazet
0 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-05-31 14:05 UTC (permalink / raw)
To: moshe
Cc: Tariq Toukan, Eric Dumazet, aring, David Miller, netdev,
Florian Westphal, Herbert Xu, Thomas Graf, Jesper Dangaard Brouer,
Alexander Aring, Stefan Schmidt, Kirill Tkhai, Eran Ben Elisha
On Thu, May 31, 2018 at 8:18 AM Moshe Shemesh <moshe@mellanox.com> wrote:
>
>
>
> I do see big improvement after changing the 3 parameters as Eric suggested:
> /proc/sys/net/ipv6/ip6frag_time set to 2
> /proc/sys/net/ipv6/ip6frag_low_thresh set to 104857600
> /proc/sys/net/ipv6/ip6frag_high_thresh set to 78643200
>
>
> [root@reg-l-vrt-67100-104 linux-stable]# netperf -H
> fe80::7efe:90ff:fed5:bb48%ens9,inet6 -t udp_stream --
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> fe80::7efe:90ff:fed5:bb48%ens9 () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 156387 0 8194.60
> 212992 10.00 76901 4029.57
>
> #kernel
> Ip6InReceives 7107999 0.0
> Ip6InDelivers 114126 0.0
> Ip6OutRequests 47 0.0
> Ip6ReasmTimeout 5115 0.0
> Ip6ReasmReqds 7107987 0.0
> Ip6ReasmOKs 114114 0.0
> Ip6ReasmFails 1714146 0.0
> ...
> Udp6InDatagrams 112486 0.0
> Udp6InErrors 1629 0.0
> Udp6RcvbufErrors 1629 0.0
> ...
>
> While before these parameters settings I got:
> [root@reg-l-vrt-67100-104 ~]# netperf -H
> fe80::e61d:2dff:feca:c7c3%ens9,inet6 -t udp_stream --
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> fe80::e61d:2dff:feca:c7c3%ens9 () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 145419 0 7620.35
> 212992 10.00 285 14.93
>
> #kernel
> Ip6InReceives 6665965 0.0
> Ip6InDelivers 300 0.0
> Ip6OutRequests 9 0.0
> Ip6ReasmReqds 6665950 0.0
> Ip6ReasmOKs 285 0.0
> Ip6ReasmFails 6650890 0.0
> ...
> Udp6InDatagrams 286 0.0
>
>
> however, before the patchset, I got much better results:
> [root@reg-l-vrt-67100-104 linux-stable]# netperf -H
> fe80::7efe:90ff:fed5:bb48%ens9,inet6 -t udp_stream --
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> fe80::7efe:90ff:fed5:bb48%ens9 () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 158935 0 8328.32
> 212992 10.00 144652 7579.88
>
>
> #kernel
> Ip6InReceives 7088903 0.0
> Ip6InDelivers 154117 0.0
> Ip6OutRequests 9 0.0
> Ip6ReasmReqds 7088889 0.0
> Ip6ReasmOKs 154103 0.0
> ...
> Udp6InDatagrams 144653 0.0
> Udp6InErrors 9451 0.0
> Udp6RcvbufErrors 9451 0.0
>
>
Hi Moshe
Your environment seems to be very lossy.
Frags and packets losses do not mix well, there is nothing really
magic we can do with that,
unless we can reserve GB of memory for frags.
Which is exactly was the reason for my patches in the first place.
Thanks.
^ permalink raw reply [flat|nested] 34+ messages in thread
* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-28 16:09 ` Eric Dumazet
2018-05-30 7:20 ` Tariq Toukan
@ 2018-05-30 9:20 ` Jesper Dangaard Brouer
2018-05-30 10:36 ` Eric Dumazet
1 sibling, 1 reply; 34+ messages in thread
From: Jesper Dangaard Brouer @ 2018-05-30 9:20 UTC (permalink / raw)
To: Eric Dumazet
Cc: Alexander Aring, Tariq Toukan, David Miller, edumazet, netdev, fw,
herbert, tgraf, alex.aring, stefan, ktkhai, Moshe Shemesh,
Eran Ben Elisha, brouer, Rick Jones
On Mon, 28 May 2018 09:09:17 -0700
Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Tariq, here are my test results : No drops for me.
>
> # ./netperf -H 2607:f8b0:8099:e18:: -t UDP_STREAM
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to 2607:f8b0:8099:e18:: () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 202117 0 10592.00
> 212992 10.00 0 0.00
Hmm... Eric the above result show that ALL your UDP packets were dropped!
You have 0 okay messages and 0.00 Mbit/s throughput.
It needs to look like below (test on i40e NIC):
$ netperf -t UDP_STREAM -H fee0:cafe::1
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to fee0:cafe::1 () port 0 AF_INET6 : histogram : demo
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 186385 0 9767.08
212992 10.00 186385 9767.08
If I manually instruct ip6tables to drop all UDP packets, then I get
what you see... so, something on your test system are likely dropping
your UDP packets, but letting regular netperf (TCP) control
communication through.
# ip6tables -I INPUT -p udp -j DROP
$ netperf -t UDP_STREAM -H fee0:cafe::1
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to fee0:cafe::1 () port 0 AF_INET6 : histogram : demo
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 182095 0 9542.41
212992 10.00 0 0.00
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply [flat|nested] 34+ messages in thread
* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-30 9:20 ` Jesper Dangaard Brouer
@ 2018-05-30 10:36 ` Eric Dumazet
2018-05-30 10:56 ` Eric Dumazet
0 siblings, 1 reply; 34+ messages in thread
From: Eric Dumazet @ 2018-05-30 10:36 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Eric Dumazet, aring, Tariq Toukan, David Miller, netdev,
Florian Westphal, Herbert Xu, Thomas Graf, Alexander Aring,
Stefan Schmidt, Kirill Tkhai, moshe, Eran Ben Elisha, Rick Jones
On Wed, May 30, 2018 at 5:20 AM Jesper Dangaard Brouer <brouer@redhat.com>
wrote:
> On Mon, 28 May 2018 09:09:17 -0700
> Eric Dumazet <eric.dumazet@gmail.com> wrote:
> > Tariq, here are my test results : No drops for me.
> >
> > # ./netperf -H 2607:f8b0:8099:e18:: -t UDP_STREAM
> > MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
2607:f8b0:8099:e18:: () port 0 AF_INET6
> > Socket Message Elapsed Messages
> > Size Size Time Okay Errors Throughput
> > bytes bytes secs # # 10^6bits/sec
> >
> > 212992 65507 10.00 202117 0 10592.00
> > 212992 10.00 0 0.00
> Hmm... Eric the above result show that ALL your UDP packets were dropped!
> You have 0 okay messages and 0.00 Mbit/s throughput.
> It needs to look like below (test on i40e NIC):
> $ netperf -t UDP_STREAM -H fee0:cafe::1
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to fee0:cafe::1 ()
port 0 AF_INET6 : histogram : demo
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
> 212992 65507 10.00 186385 0 9767.08
> 212992 10.00 186385 9767.08
> If I manually instruct ip6tables to drop all UDP packets, then I get
> what you see... so, something on your test system are likely dropping
> your UDP packets, but letting regular netperf (TCP) control
> communication through.
> # ip6tables -I INPUT -p udp -j DROP
> $ netperf -t UDP_STREAM -H fee0:cafe::1
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to fee0:cafe::1 ()
port 0 AF_INET6 : histogram : demo
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
> 212992 65507 10.00 182095 0 9542.41
> 212992 10.00 0 0.00
Right you are, for some reason I copied/pasted wrong results,
after _specifically_ filling up the frags to the memory limits,
when trying to reproduce 'bad numbers '
Here are the good ones, using latest David Miller net tree. ( plus
https://patchwork.ozlabs.org/patch/922528/ but that should not matter here)
llpaa23:/export/hda3/google/edumazet# ./netperf -H 2607:f8b0:8099:e18:: -t
UDP_STREAM
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
2607:f8b0:8099:e18:: () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 216236 0 11331.89
212992 10.00 215068 11270.68
There are few drops because of the too small
/proc/sys/net/core/rmem_default ( 212992 as seen in netperf output) for
these kind of stress.
( each 64KB datagram actually consumes half the budget ...)
^ permalink raw reply [flat|nested] 34+ messages in thread
* Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
2018-05-30 10:36 ` Eric Dumazet
@ 2018-05-30 10:56 ` Eric Dumazet
0 siblings, 0 replies; 34+ messages in thread
From: Eric Dumazet @ 2018-05-30 10:56 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Eric Dumazet, aring, Tariq Toukan, David Miller, netdev,
Florian Westphal, Herbert Xu, Thomas Graf, Alexander Aring,
Stefan Schmidt, Kirill Tkhai, moshe, Eran Ben Elisha, Rick Jones
On Wed, May 30, 2018 at 6:36 AM Eric Dumazet <edumazet@google.com> wrote:
> Here are the good ones, using latest David Miller net tree. ( plus
> https://patchwork.ozlabs.org/patch/922528/ but that should not matter
here)
> llpaa23:/export/hda3/google/edumazet# ./netperf -H 2607:f8b0:8099:e18:: -t
> UDP_STREAM
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> 2607:f8b0:8099:e18:: () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
> 212992 65507 10.00 216236 0 11331.89
> 212992 10.00 215068 11270.68
> There are few drops because of the too small
> /proc/sys/net/core/rmem_default ( 212992 as seen in netperf output) for
> these kind of stress.
> ( each 64KB datagram actually consumes half the budget ...)
Once rmem_default is set to 1,000,000 and mtu set back to 1500 (instead of
5102 on my testbed)
results are indeed better.
lpaa23:/export/hda3/google/edumazet# ./netperf -H 2607:f8b0:8099:e18:: -t
UDP_STREAM -l 10
MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
2607:f8b0:8099:e18:: () port 0 AF_INET6
Socket Message Elapsed Messages
Size Size Time Okay Errors Throughput
bytes bytes secs # # 10^6bits/sec
212992 65507 10.00 231457 0 12129.56
1000000 10.00 231457 12129.56
^ permalink raw reply [flat|nested] 34+ messages in thread