* [PATCH v2 net-next 05/12] inet: frags: refactor lowpan_net_frag_init()
From: Eric Dumazet @ 2018-03-30 20:42 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-Reply-To: <20180330204236.43675-1-edumazet@google.com>
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
* [PATCH v2 net-next 04/12] inet: frags: refactor ipv6_frag_init()
From: Eric Dumazet @ 2018-03-30 20:42 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-Reply-To: <20180330204236.43675-1-edumazet@google.com>
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
* [PATCH v2 net-next 03/12] inet: frags: add a pointer to struct netns_frags
From: Eric Dumazet @ 2018-03-30 20:42 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-Reply-To: <20180330204236.43675-1-edumazet@google.com>
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
* [PATCH v2 net-next 02/12] inet: frags: change inet_frags_init_net() return value
From: Eric Dumazet @ 2018-03-30 20:42 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-Reply-To: <20180330204236.43675-1-edumazet@google.com>
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
* [PATCH v2 net-next 01/12] ipv6: frag: remove unused field
From: Eric Dumazet @ 2018-03-30 20:42 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-Reply-To: <20180330204236.43675-1-edumazet@google.com>
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
* [PATCH v2 net-next 00/12] inet: frags: bring rhashtables to IP defrag
From: Eric Dumazet @ 2018-03-30 20:42 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 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.
v2: Addressed Herbert and Kirill feedbacks
Eric Dumazet (12):
ipv6: frag: remove unused field
inet: frags: change inet_frags_init_net() return value
inet: frags: add a pointer to struct netns_frags
inet: frags: refactor ipv6_frag_init()
inet: frags: refactor lowpan_net_frag_init()
inet: frags: refactor ipfrag_init()
rhashtable: add schedule points
inet: frags: use rhashtables for reassembly units
inet: frags: remove some helpers
inet: frags: get rif of inet_frag_evicting()
inet: frags: remove inet_frag_maybe_warn_overflow()
inet: frags: break the 2GB limit for frags storage
Documentation/networking/ip-sysctl.txt | 11 +-
include/net/inet_frag.h | 123 ++++----
include/net/ip.h | 1 -
include/net/ipv6.h | 27 +-
lib/rhashtable.c | 2 +
net/ieee802154/6lowpan/6lowpan_i.h | 26 +-
net/ieee802154/6lowpan/reassembly.c | 150 +++++-----
net/ipv4/inet_fragment.c | 362 +++++-------------------
net/ipv4/ip_fragment.c | 214 +++++++-------
net/ipv4/proc.c | 6 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 90 +++---
net/ipv6/proc.c | 5 +-
net/ipv6/reassembly.c | 181 ++++++------
13 files changed, 441 insertions(+), 757 deletions(-)
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply
* [GIT] Networking
From: David Miller @ 2018-03-30 20:28 UTC (permalink / raw)
To: torvalds; +Cc: akpm, netdev, linux-kernel
1) Fix RCU locking in xfrm_local_error(), from Taehee Yoo.
2) Fix return value assignments and thus error checking in
iwl_mvm_start_ap_ibss(), from Johannes Berg.
3) Don't count header length twice in vti4, from Stefano Brivio.
4) Fix deadlock in rt6_age_examine_exception, from Eric Dumazet.
5) Fix out-of-bounds access in nf_sk_lookup_slow{v4,v6}() from
Subash Abhinov.
6) Check nladdr size in netlink_connect(), from Alexander
Potapenko.
7) VF representor SQ numbers are 32 not 16 bits, in mlx5 driver,
from Or Gerlitz.
8) Out of bounds read in skb_network_protocol(), from Eric Dumazet.
9) r8169 driver sets driver data pointer after register_netdev() which
is too late. Fix from Heiner Kallweit.
10) Fix memory leak in mlx4 driver, from Moshe Shemesh.
11) The multi-VLAN decap fix added a regression when dealing with
device that lack a MAC header, such as tun. Fix from Toshiaki
Makita.
12) Fix integer overflow in dynamic interrupt coalescing code. From Tal
Gilboa.
13) Use after free in vrf code, from David Ahern.
14) IPV6 route leak between VRFs fix, also from David Ahern.
Please pull, thanks a lot!
The following changes since commit f36b7534b83357cf52e747905de6d65b4f7c2512:
Merge branch 'akpm' (patches from Andrew) (2018-03-22 18:48:43 -0700)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
for you to fetch changes up to e81b5e01c14add8395dfba7130f8829206bb507d:
net: mvneta: fix enable of all initialized RXQs (2018-03-30 14:27:47 -0400)
----------------------------------------------------------------
Alexander Potapenko (1):
netlink: make sure nladdr has correct size in netlink_connect()
Andrei Otcheretianski (2):
iwlwifi: mvm: Increase session protection time after CS
iwlwifi: mvm: Move unused phy's to a default channel
Avraham Stern (3):
iwlwifi: mvm: clear tx queue id when unreserving aggregation queue
iwlwifi: mvm: make sure internal station has a valid id
iwlwifi: mvm: fix array out of bounds reference
Beni Lev (1):
iwlwifi: mvm: Correctly set IGTK for AP
Colin Ian King (1):
atm: iphase: fix spelling mistake: "Receiverd" -> "Received"
Cong Wang (1):
llc: properly handle dev_queue_xmit() return value
Craig Dillabaugh (1):
net sched actions: fix dumping which requires several messages to user space
Dave Watson (1):
strparser: Fix sign of err codes
David Ahern (2):
vrf: Fix use after free and double free in vrf_finish_output
net/ipv6: Fix route leaking between VRFs
David Lebrun (1):
ipv6: sr: fix seg6 encap performances with TSO enabled
David S. Miller (11):
Merge branch 'mlxsw-GRE-mtu-changes'
Merge git://git.kernel.org/.../pablo/nf
Merge tag 'wireless-drivers-for-davem-2018-03-24' of git://git.kernel.org/.../kvalo/wireless-drivers
Merge branch 'bond-hwaddr-sync-fixes'
Merge tag 'batadv-net-for-davem-20180326' of git://git.open-mesh.org/linux-merge
Merge tag 'mlx5-fixes-2018-03-23' of git://git.kernel.org/.../saeed/linux
Merge branch 'mlx4-misc-fixes-for-4.16'
Merge branch 'master' of git://git.kernel.org/.../klassert/ipsec
ip_tunnel: Resolve ipsec merge conflict properly.
Merge git://git.kernel.org/.../bpf/bpf
Merge branch 'vlan-fix'
Emmanuel Grumbach (1):
iwlwifi: mvm: set the correct tid when we flush the MCAST sta
Eran Ben Elisha (1):
net/mlx4_en: Fix mixed PFC and Global pause user control requests
Eric Dumazet (2):
ipv6: fix possible deadlock in rt6_age_examine_exception()
net: fix possible out-of-bound read in skb_network_protocol()
Florian Westphal (3):
netfilter: nf_tables: meter: pick a set backend that supports updates
netfilter: nf_tables: permit second nat hook if colliding hook is going away
netfilter: nf_tables: add missing netlink attrs to policies
Giuseppe Lippolis (1):
net-usb: add qmi_wwan if on lte modem wistron neweb d18q1
Hans Wippel (1):
net/ipv4: disable SMC TCP option with SYN Cookies
Heiner Kallweit (1):
r8169: fix setting driver_data after register_netdev
Jakub Kicinski (2):
tools: bpftool: don't use hex numbers in JSON output
nfp: bpf: fix check of program max insn count
Jason Wang (3):
vhost_net: add missing lock nesting notation
vhost: correctly remove wait queue during poll failure
vhost: validate log when IOTLB is enabled
Jianbo Liu (2):
net/mlx5e: Don't override vport admin link state in switchdev mode
net/mlx5e: Fix memory usage issues in offloading TC flows
Johannes Berg (1):
iwlwifi: mvm: fix error checking for multi/broadcast sta
John Fastabend (1):
net: sched, fix OOO packets with pfifo_fast
Kalle Valo (2):
Merge tag 'iwlwifi-for-kalle-2018-03-16' of git://git.kernel.org/.../iwlwifi/iwlwifi-fixes
Merge tag 'iwlwifi-for-kalle-2018-03-19' of git://git.kernel.org/.../iwlwifi/iwlwifi-fixes
Linus Lüssing (2):
batman-adv: fix multicast-via-unicast transmission with AP isolation
batman-adv: fix packet loss for broadcasted DHCP packets to a server
Luca Coelho (1):
iwlwifi: add shared clock PHY config flag for some devices
Manish Chopra (2):
qede: Fix barrier usage after tx doorbell write.
qede: Do not drop rx-checksum invalidated packets.
Moshe Shemesh (2):
net/mlx5e: Verify coalescing parameters in range
net/mlx4_core: Fix memory leak while delete slave's resources
Or Gerlitz (3):
net/mlx5e: Use 32 bits to store VF representor SQ number
net/mlx5: Make eswitch support to depend on switchdev
net/mlx5e: Avoid using the ipv6 stub in the TC offload neigh update path
Pablo Neira Ayuso (2):
netfilter: nf_tables: cache device name in flowtable object
netfilter: nf_tables: do not hold reference on netdevice from preparation phase
Paolo Abeni (2):
netfilter: drop template ct when conntrack is skipped.
ipv6: the entire IPv6 header chain must fit the first fragment
Pawel Dembicki (1):
net: qmi_wwan: add BroadMobi BM806U 2020:2033
Petr Machata (3):
ip_tunnel: Emit events for post-register MTU changes
mlxsw: spectrum_router: Move mlxsw_sp_rif_ipip_lb_op()
mlxsw: spectrum_router: Handle MTU change of GRE netdevs
Rafał Miłecki (1):
brcmfmac: drop Inter-Access Point Protocol packets by default
Raghuram Chary J (2):
lan78xx: Set ASD in MAC_CR when EEE is enabled.
lan78xx: Crash in lan78xx_writ_reg (Workqueue: events lan78xx_deferred_multicast_write)
Roi Dayan (1):
net/mlx5e: Fix traffic being dropped on VF representor
Sanjeev Gupta (1):
Documentation/isdn: check and fix dead links ...
Sean Wang (2):
net: dsa: mt7530: remove redundant MODULE_ALIAS entries
net: dsa: mt7530: fix module autoloading for OF platform drivers
Shahar Klein (1):
net/mlx5e: Sync netdev vxlan ports at open
Stefan Wahren (1):
brcmfmac: Fix check for ISO3166 code
Stefano Brivio (6):
vti4: Don't count header length twice on tunnel setup
ip_tunnel: Clamp MTU to bounds on new link
vti4: Don't override MTU passed on link creation via IFLA_MTU
vti6: Properly adjust vti6 MTU from MTU of lower device
vti6: Keep set MTU on link creation or change, validate it
vti6: Fix dev->max_mtu setting
Steffen Klassert (1):
xfrm: Fix transport mode skb control buffer usage.
Stephen Hemminger (1):
hv_netvsc: enable multicast if necessary
Subash Abhinov Kasiviswanathan (1):
netfilter: nf_socket: Fix out of bounds access in nf_sk_lookup_slow_v{4,6}
Taehee Yoo (1):
xfrm: fix rcu_read_unlock usage in xfrm_local_error
Tal Gilboa (1):
net/dim: Fix int overflow
Torsten Hilbrich (1):
net/usb/qmi_wwan.c: Add USB id for lt4120 modem
Toshiaki Makita (2):
net: Fix untag for vlan packets without ethernet header
vlan: Fix vlan insertion for packets without ethernet header
Ursula Braun (1):
net/smc: use announced length in sock_recvmsg()
Xin Long (4):
bonding: fix the err path for dev hwaddr sync in bond_enslave
bonding: move dev_mc_sync after master_upper_dev_link in bond_enslave
bonding: process the err returned by dev_set_allmulti properly in bond_enslave
team: move dev_mc_sync after master_upper_dev_link in team_port_add
Yelena Krivosheev (1):
net: mvneta: fix enable of all initialized RXQs
Documentation/isdn/INTERFACE.CAPI | 2 +-
Documentation/isdn/README | 4 ++--
Documentation/isdn/README.FAQ | 4 ++--
Documentation/isdn/README.gigaset | 16 ++++++++------
drivers/atm/iphase.c | 2 +-
drivers/net/bonding/bond_main.c | 73 +++++++++++++++++++++++++++++++------------------------------
drivers/net/dsa/mt7530.c | 2 +-
drivers/net/ethernet/marvell/mvneta.c | 1 +
drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c | 72 ++++++++++++++++++++++++++++++++++--------------------------
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 33 ++++++++++++++++------------
drivers/net/ethernet/mellanox/mlx4/en_main.c | 4 ++--
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 1 +
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 17 +++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 13 +++++------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 34 ++++++++++++++++-------------
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 18 +++++++--------
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 78 ++++++++++++++++++++++++++++++++++++++++++-----------------------
drivers/net/ethernet/netronome/nfp/bpf/jit.c | 6 ++++-
drivers/net/ethernet/qlogic/qede/qede_fp.c | 20 +++++------------
drivers/net/ethernet/realtek/r8169.c | 4 ++--
drivers/net/hyperv/rndis_filter.c | 2 +-
drivers/net/team/team.c | 12 +++++-----
drivers/net/usb/lan78xx.c | 33 ++++++++++++++++++++++++++--
drivers/net/usb/qmi_wwan.c | 5 +++++
drivers/net/vrf.c | 5 +++--
drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 2 +-
drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c | 5 +++++
drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h | 1 +
drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++
drivers/net/wireless/intel/iwlwifi/cfg/9000.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++++
drivers/net/wireless/intel/iwlwifi/fw/file.h | 1 +
drivers/net/wireless/intel/iwlwifi/iwl-config.h | 5 +++++
drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 4 ++++
drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 9 +++++---
drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 3 +++
drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c | 21 +++++++++++++-----
drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 74 ++++++++++++++++++++++++++++----------------------------------
drivers/net/wireless/intel/iwlwifi/mvm/time-event.c | 15 +++++++------
drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 10 ++++-----
drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 38 ++++++++++++++++----------------
drivers/vhost/net.c | 4 ++--
drivers/vhost/vhost.c | 17 ++++++---------
include/linux/if_vlan.h | 15 +++++++++++--
include/linux/net_dim.h | 2 +-
include/net/llc_conn.h | 2 +-
include/net/netfilter/nf_tables.h | 4 ++++
include/net/sch_generic.h | 1 +
net/batman-adv/gateway_client.c | 5 ++++-
net/batman-adv/multicast.c | 4 ++--
net/core/dev.c | 2 +-
net/core/skbuff.c | 6 +++--
net/ipv4/ip_tunnel.c | 31 +++++++++++++++++++++-----
net/ipv4/ip_vti.c | 2 --
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 14 +++++++++++-
net/ipv4/netfilter/nf_socket_ipv4.c | 6 +++--
net/ipv4/syncookies.c | 2 ++
net/ipv4/tcp_input.c | 3 +++
net/ipv6/ip6_output.c | 13 +++++++----
net/ipv6/ip6_vti.c | 36 +++++++++++++++++++-----------
net/ipv6/netfilter/nf_socket_ipv6.c | 6 +++--
net/ipv6/route.c | 16 +++++++++-----
net/ipv6/seg6_iptunnel.c | 16 ++++++--------
net/ipv6/syncookies.c | 2 ++
net/llc/llc_c_ac.c | 15 ++++++++-----
net/llc/llc_conn.c | 32 +++++++++++++++++++--------
net/netfilter/nf_tables_api.c | 106 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--------------------
net/netfilter/nft_set_hash.c | 2 +-
net/netlink/af_netlink.c | 3 +++
net/sched/act_api.c | 4 +++-
net/sched/sch_generic.c | 17 +++++++++++----
net/smc/smc_clc.c | 2 +-
net/strparser/strparser.c | 4 ++--
net/xfrm/xfrm_input.c | 6 +++++
net/xfrm/xfrm_output.c | 5 +++--
tools/bpf/bpftool/map.c | 2 +-
76 files changed, 793 insertions(+), 384 deletions(-)
^ permalink raw reply
* [Patch nf] nf_conntrack_extend: silent a memory leak warning
From: Cong Wang @ 2018-03-30 20:22 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, Cong Wang, Pablo Neira Ayuso, Jozsef Kadlecsik,
Florian Westphal
The following memory leak is false postive:
unreferenced object 0xffff8f37f156fb38 (size 128):
comm "softirq", pid 0, jiffies 4294899665 (age 11.292s)
hex dump (first 32 bytes):
6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk
00 00 00 00 30 00 20 00 48 6b 6b 6b 6b 6b 6b 6b ....0. .Hkkkkkkk
backtrace:
[<000000004fda266a>] __kmalloc_track_caller+0x10d/0x141
[<000000007b0a7e3c>] __krealloc+0x45/0x62
[<00000000d08e0bfb>] nf_ct_ext_add+0xdc/0x133
[<0000000099b47fd8>] init_conntrack+0x1b1/0x392
[<0000000086dc36ec>] nf_conntrack_in+0x1ee/0x34b
[<00000000940592de>] nf_hook_slow+0x36/0x95
[<00000000d1bd4da7>] nf_hook.constprop.43+0x1c3/0x1dd
[<00000000c3673266>] __ip_local_out+0xae/0xb4
[<000000003e4192a6>] ip_local_out+0x17/0x33
[<00000000b64356de>] igmp_ifc_timer_expire+0x23e/0x26f
[<000000006a8f3032>] call_timer_fn+0x14c/0x2a5
[<00000000650c1725>] __run_timers.part.34+0x150/0x182
[<0000000090e6946e>] run_timer_softirq+0x2a/0x4c
[<000000004d1e7293>] __do_softirq+0x1d1/0x3c2
[<000000004643557d>] irq_exit+0x53/0xa2
[<0000000029ddee8f>] smp_apic_timer_interrupt+0x22a/0x235
because __krealloc() is not supposed to release the old
memory and it is released later via kfree_rcu(). Since this is
the only external user of __krealloc(), just mark it as not leak
here.
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
---
net/netfilter/nf_conntrack_extend.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 9fe0ddc333fb..bd71a828ebde 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -71,6 +71,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
rcu_read_unlock();
alloc = max(newlen, NF_CT_EXT_PREALLOC);
+ kmemleak_not_leak(old);
new = __krealloc(old, alloc, gfp);
if (!new)
return NULL;
--
2.13.0
^ permalink raw reply related
* Re: Donation
From: M. M. Fridman @ 2018-03-30 19:47 UTC (permalink / raw)
To: Recipients
I Mikhail Fridman. has selected you specially as one of my beneficiaries
for my Charitable Donation, Just as I have declared on May 23, 2016 to give
my fortune as charity.
Check the link below for confirmation:
http://www.ibtimes.co.uk/russias-second-wealthiest-man-mikhail-fridman-plans-leaving-14-2bn-fortune-charity-1561604
Reply as soon as possible with further directives.
Best Regards,
Mikhail Fridman.
^ permalink raw reply
* Re: [net-next V7 PATCH 12/16] page_pool: refurbish version of page_pool code
From: kbuild test robot @ 2018-03-30 19:58 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: kbuild-all, netdev, BjörnTöpel, magnus.karlsson,
eugenia, Jason Wang, John Fastabend, Eran Ben Elisha,
Saeed Mahameed, galp, Jesper Dangaard Brouer, Daniel Borkmann,
Alexei Starovoitov, Tariq Toukan
In-Reply-To: <152234291739.17048.7135649249513438321.stgit@firesoul>
Hi Jesper,
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/Jesper-Dangaard-Brouer/XDP-redirect-memory-return-API/20180330-203122
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
>> net/core/page_pool.c:17:5: sparse: symbol 'page_pool_init' was not declared. Should it be static?
>> net/core/page_pool.c:198:6: sparse: symbol '__page_pool_recycle_into_ring' was not declared. Should it be static?
>> net/core/page_pool.c:267:6: sparse: symbol '__page_pool_empty_ring' was not declared. Should it be static?
>> net/core/page_pool.c:282:6: sparse: symbol '__page_pool_destroy_rcu' was not declared. Should it be static?
Please review and possibly fold the followup patch.
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* [RFC PATCH] page_pool: page_pool_init() can be static
From: kbuild test robot @ 2018-03-30 19:58 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: kbuild-all, netdev, BjörnTöpel, magnus.karlsson,
eugenia, Jason Wang, John Fastabend, Eran Ben Elisha,
Saeed Mahameed, galp, Jesper Dangaard Brouer, Daniel Borkmann,
Alexei Starovoitov, Tariq Toukan
In-Reply-To: <152234291739.17048.7135649249513438321.stgit@firesoul>
Fixes: 7ec72cfedf20 ("page_pool: refurbish version of page_pool code")
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
---
page_pool.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 1bf4e17..ec1b010 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -14,8 +14,8 @@
#include <linux/page-flags.h>
#include <linux/mm.h> /* for __put_page() */
-int page_pool_init(struct page_pool *pool,
- const struct page_pool_params *params)
+static int page_pool_init(struct page_pool *pool,
+ const struct page_pool_params *params)
{
unsigned int ring_qsize = 1024; /* Default */
@@ -195,8 +195,8 @@ static void __page_pool_return_page(struct page_pool *pool, struct page *page)
*/
}
-bool __page_pool_recycle_into_ring(struct page_pool *pool,
- struct page *page)
+static bool __page_pool_recycle_into_ring(struct page_pool *pool,
+ struct page *page)
{
int ret;
/* BH protection not needed if current is serving softirq */
@@ -264,7 +264,7 @@ void __page_pool_put_page(struct page_pool *pool,
}
EXPORT_SYMBOL(__page_pool_put_page);
-void __page_pool_empty_ring(struct page_pool *pool)
+static void __page_pool_empty_ring(struct page_pool *pool)
{
struct page *page;
@@ -279,7 +279,7 @@ void __page_pool_empty_ring(struct page_pool *pool)
}
}
-void __page_pool_destroy_rcu(struct rcu_head *rcu)
+static void __page_pool_destroy_rcu(struct rcu_head *rcu)
{
struct page_pool *pool;
^ permalink raw reply related
* Re: [PATCH net-next] bridge: Allow max MTU when multiple VLANs present
From: Chas Williams @ 2018-03-30 19:54 UTC (permalink / raw)
To: Toshiaki Makita
Cc: Roopa Prabhu, David Miller, netdev, Stephen Hemminger,
Nikolay Aleksandrov
In-Reply-To: <9034b7d8-dfb7-f1fa-44b1-d5dc95653724@lab.ntt.co.jp>
On Thu, Mar 29, 2018 at 9:02 PM, Toshiaki Makita
<makita.toshiaki@lab.ntt.co.jp> wrote:
> On 2018/03/30 1:49, Roopa Prabhu wrote:
>> On Thu, Mar 22, 2018 at 9:53 PM, Roopa Prabhu <roopa@cumulusnetworks.com> wrote:
>>> On Thu, Mar 22, 2018 at 8:34 AM, Chas Williams <3chas3@gmail.com> wrote:
>>>> If the bridge is allowing multiple VLANs, some VLANs may have
>>>> different MTUs. Instead of choosing the minimum MTU for the
>>>> bridge interface, choose the maximum MTU of the bridge members.
>>>> With this the user only needs to set a larger MTU on the member
>>>> ports that are participating in the large MTU VLANS.
>>>>
>>>> Signed-off-by: Chas Williams <3chas3@gmail.com>
>>>> ---
>>>
>>> Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
>>>
>>> This or an equivalent fix is necessary: as stated above, today the
>>> bridge mtu capped at min port mtu limits all
>>> vlan devices on top of the vlan filtering bridge to min port mtu.
>>
>>
>> On further thought, since this patch changes default behavior, it may
>> upset people. ie with this patch, a vlan device
>> on the bridge by default will now use the bridge max mtu and that
>> could cause unexpected drops in the bridge driver
>> if the xmit port had a lower mtu. This may surprise users.
It only changes the default behavior when you are using VLAN aware bridges.
The behavior remains the same otherwise. I don't know if VLAN aware bridges
are that popular yet so there probably isn't any particular
expectation from those
bridges.
I don't think those drops are unexpected. If a user has misconfigured
the bridge
we can't be expected to fix that for them. It is the user's
responsbility to ensure
that the ports on the VLAN have a size consistent with the traffic
they expect to
pass.
>>
>> The other equivalent fix i was thinking about is to keep the default
>> behavior as is, and allow a max mtu to be
>> configured on the bridge. This will allow a sys admin to fix the
>> current mtu limitations if
>> deployments require it.
>>
>> we will submit an incremental patch to re-work this patch to restore
>> default behavior.
>
> +1
>
> This makes sense to me.
>
> --
> Toshiaki Makita
>
^ permalink raw reply
* Re: [PATCH net-next 0/9] devlink: Add support for region access
From: Alex Vesker @ 2018-03-30 19:39 UTC (permalink / raw)
To: David Ahern, Andrew Lunn
Cc: David S. Miller, netdev, Tariq Toukan, Jiri Pirko
In-Reply-To: <6d55f271-18f9-9ca5-0dbf-24951dd09978@gmail.com>
On 3/30/2018 7:57 PM, David Ahern wrote:
> On 3/30/18 8:34 AM, Andrew Lunn wrote:
>>>> And it seems to want contiguous pages. How well does that work after
>>>> the system has been running for a while and memory is fragmented?
>>> The allocation can be changed, there is no read need for contiguous pages.
>>> It is important to note that we the amount of snapshots is limited by the
>>> driver
>>> this can be based on the dump size or expected frequency of collection.
>>> I also prefer not to pre-allocate this memory.
>> The driver code also asks for a 1MB contiguous chunk of memory! You
>> really should think about this API, how can you avoid double memory
>> allocations. And can kvmalloc be used. But then you get into the
>> problem for DMA'ing the memory from the device...
>>
>> This API also does not scale. 1MB is actually quite small. I'm sure
>> there is firmware running on CPUs with a lot more than 1MB of RAM.
>> How well does with API work with 64MB? Say i wanted to snapshot my
>> GPU? Or the MC/BMC?
>>
> That and the drivers control the number of snapshots. The user should be
> able to control the number of snapshots, and an option to remove all
> snapshots to free up that memory.
There is an option to free up this memory, using a delete command.
The reason I added the option to control the number of snapshots from
the driver side only is because the driver knows the size of the snapshots
and when/why they will be taken.
For example in our mlx4 driver the snapshots are taken on rare failures,
the snapshot is quite large and from past analyses the first dump is usually
the important one, this means that 8 is more than enough in my case.
If a user wants more than that he can always monitor notification read
the snapshot and delete once backup-ed, there is no reason for keeping
all of this data in the kernel.
^ permalink raw reply
* [PATCH] ethernet: hisilicon: hns: hns_dsaf_mac: Use generic eth_broadcast_addr
From: Joe Perches @ 2018-03-30 19:37 UTC (permalink / raw)
To: linux-kernel; +Cc: Yisen Zhuang, Salil Mehta, netdev
Rather than use an on-stack array to copy a broadcast address, use
the generic eth_broadcast_addr function to save a trivial amount of
object code.
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index cac86e9ae0dd..9dcc5765f11f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -369,7 +369,6 @@ static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb,
{
int ret;
struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
- u8 addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
struct dsaf_drv_mac_single_dest_entry mac_entry;
/* directy return ok in debug network mode */
@@ -377,7 +376,7 @@ static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb,
return 0;
if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
- memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr));
+ eth_broadcast_addr(mac_entry.addr);
mac_entry.in_vlan_id = vlan_id;
mac_entry.in_port_num = mac_cb->mac_id;
mac_entry.port_num = port_num;
@@ -404,7 +403,6 @@ int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable)
int ret;
struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
u8 port_num;
- u8 addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
struct mac_entry_idx *uc_mac_entry;
struct dsaf_drv_mac_single_dest_entry mac_entry;
@@ -414,7 +412,7 @@ int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable)
uc_mac_entry = &mac_cb->addr_entry_idx[vmid];
if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
- memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr));
+ eth_broadcast_addr(mac_entry.addr);
mac_entry.in_vlan_id = uc_mac_entry->vlan_id;
mac_entry.in_port_num = mac_cb->mac_id;
ret = hns_mac_get_inner_port_num(mac_cb, vmid, &port_num);
--
2.15.0
^ permalink raw reply related
* Re: [net-next V7 PATCH 11/16] xdp: rhashtable with allocator ID to pointer mapping
From: kbuild test robot @ 2018-03-30 19:07 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: kbuild-all, netdev, BjörnTöpel, magnus.karlsson,
eugenia, Jason Wang, John Fastabend, Eran Ben Elisha,
Saeed Mahameed, galp, Jesper Dangaard Brouer, Daniel Borkmann,
Alexei Starovoitov, Tariq Toukan
In-Reply-To: <152234291230.17048.17742948504401359444.stgit@firesoul>
Hi Jesper,
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/Jesper-Dangaard-Brouer/XDP-redirect-memory-return-API/20180330-203122
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
>> net/core/xdp.c:19:1: sparse: symbol 'mem_id_pool' was not declared. Should it be static?
>> net/core/xdp.c:68:6: sparse: symbol '__xdp_mem_allocator_rcu_free' was not declared. Should it be static?
>> net/core/xdp.c:87:6: sparse: symbol '__xdp_rxq_info_unreg_mem_model' was not declared. Should it be static?
>> net/core/xdp.c:177:5: sparse: symbol '__mem_id_init_hash_table' was not declared. Should it be static?
Please review and possibly fold the followup patch.
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* [RFC PATCH] xdp: mem_id_pool can be static
From: kbuild test robot @ 2018-03-30 19:07 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: kbuild-all, netdev, BjörnTöpel, magnus.karlsson,
eugenia, Jason Wang, John Fastabend, Eran Ben Elisha,
Saeed Mahameed, galp, Jesper Dangaard Brouer, Daniel Borkmann,
Alexei Starovoitov, Tariq Toukan
In-Reply-To: <152234291230.17048.17742948504401359444.stgit@firesoul>
Fixes: a5c71e7a9fe0 ("xdp: rhashtable with allocator ID to pointer mapping")
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
---
xdp.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index e7f11f0..6697900 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -16,7 +16,7 @@
#define REG_STATE_UNREGISTERED 0x2
#define REG_STATE_UNUSED 0x3
-DEFINE_IDA(mem_id_pool);
+static DEFINE_IDA(mem_id_pool);
static DEFINE_MUTEX(mem_id_lock);
#define MEM_ID_MAX 0xFFFE
#define MEM_ID_MIN 1
@@ -65,7 +65,7 @@ static const struct rhashtable_params mem_id_rht_params = {
.obj_cmpfn = xdp_mem_id_cmp,
};
-void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
+static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
{
struct xdp_mem_allocator *xa;
@@ -84,7 +84,7 @@ void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
kfree(xa);
}
-void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
+static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
{
struct xdp_mem_allocator *xa;
int id = xdp_rxq->mem.id;
@@ -174,7 +174,7 @@ bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq)
}
EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg);
-int __mem_id_init_hash_table(void)
+static int __mem_id_init_hash_table(void)
{
struct rhashtable *rht;
int ret;
^ permalink raw reply related
* KASAN: use-after-free Read in _decode_session4
From: syzbot @ 2018-03-30 19:01 UTC (permalink / raw)
To: davem, herbert, kuznet, linux-kernel, netdev, steffen.klassert,
syzkaller-bugs, yoshfuji
Hello,
syzbot hit the following crash on upstream commit
0b412605ef5f5c64b31f19e2910b1d5eba9929c3 (Thu Mar 29 01:07:23 2018 +0000)
Merge tag 'drm-fixes-for-v4.16-rc8' of
git://people.freedesktop.org/~airlied/linux
syzbot dashboard link:
https://syzkaller.appspot.com/bug?extid=a7db9083ed4017ba4423
So far this crash happened 3 times on upstream.
C reproducer: https://syzkaller.appspot.com/x/repro.c?id=4908519807516672
syzkaller reproducer:
https://syzkaller.appspot.com/x/repro.syz?id=5839674757087232
Raw console output:
https://syzkaller.appspot.com/x/log.txt?id=6305464228773888
Kernel config:
https://syzkaller.appspot.com/x/.config?id=-8440362230543204781
compiler: gcc (GCC) 7.1.1 20170620
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+a7db9083ed4017ba4423@syzkaller.appspotmail.com
It will help syzbot understand when the bug is fixed. See footer for
details.
If you forward the report, please keep this part and the footer.
IPv6: ADDRCONF(NETDEV_UP): veth1: link is not ready
IPv6: ADDRCONF(NETDEV_CHANGE): veth1: link becomes ready
IPv6: ADDRCONF(NETDEV_CHANGE): veth0: link becomes ready
protocol 0800 is buggy, dev ip6_vti0
==================================================================
BUG: KASAN: use-after-free in _decode_session4+0x15f0/0x1990
net/ipv4/xfrm4_policy.c:115
Read of size 1 at addr ffff8801b4117398 by task syzkaller030703/4418
CPU: 1 PID: 4418 Comm: syzkaller030703 Not tainted 4.16.0-rc7+ #5
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
IPv6: ADDRCONF(NETDEV_UP): veth1: link is not ready
Call Trace:
__dump_stack lib/dump_stack.c:17 [inline]
dump_stack+0x194/0x24d lib/dump_stack.c:53
print_address_description+0x73/0x250 mm/kasan/report.c:256
kasan_report_error mm/kasan/report.c:354 [inline]
kasan_report+0x23c/0x360 mm/kasan/report.c:412
__asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430
_decode_session4+0x15f0/0x1990 net/ipv4/xfrm4_policy.c:115
__xfrm_decode_session+0x68/0x110 net/xfrm/xfrm_policy.c:2368
xfrm_decode_session include/net/xfrm.h:1206 [inline]
vti6_tnl_xmit+0x36d/0x1820 net/ipv6/ip6_vti.c:546
__netdev_start_xmit include/linux/netdevice.h:4066 [inline]
netdev_start_xmit include/linux/netdevice.h:4075 [inline]
xmit_one net/core/dev.c:3026 [inline]
dev_hard_start_xmit+0x24e/0xac0 net/core/dev.c:3042
protocol 0800 is buggy, dev ip6_vti0
protocol 0800 is buggy, dev ip6_vti0
protocol 0800 is buggy, dev ip6_vti0
__dev_queue_xmit+0x26bf/0x2fc0 net/core/dev.c:3557
protocol 0800 is buggy, dev ip6_vti0
protocol 0800 is buggy, dev ip6_vti0
protocol 0800 is buggy, dev ip6_vti0
protocol 0800 is buggy, dev ip6_vti0
protocol 0800 is buggy, dev ip6_vti0
protocol 0800 is buggy, dev ip6_vti0
dev_queue_xmit+0x17/0x20 net/core/dev.c:3590
packet_snd net/packet/af_packet.c:2944 [inline]
packet_sendmsg+0x3aed/0x60b0 net/packet/af_packet.c:2969
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg+0xca/0x110 net/socket.c:640
SYSC_sendto+0x361/0x5c0 net/socket.c:1747
SyS_sendto+0x40/0x50 net/socket.c:1715
do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4417e9
RSP: 002b:00007ffd4f154978 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 1650e23d775d273d RCX: 00000000004417e9
RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000004
RBP: 00000000004a335c R08: 0000000020000000 R09: 000000000000001c
R10: 0000000000000000 R11: 0000000000000216 R12: 00007ffd4f154a50
R13: 00000000004024c0 R14: 0000000000000000 R15: 0000000000000000
Allocated by task 4418:
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:552
__do_kmalloc_node mm/slab.c:3670 [inline]
__kmalloc_node_track_caller+0x47/0x70 mm/slab.c:3684
__kmalloc_reserve.isra.39+0x41/0xd0 net/core/skbuff.c:137
__alloc_skb+0x13b/0x780 net/core/skbuff.c:205
alloc_skb include/linux/skbuff.h:983 [inline]
alloc_skb_with_frags+0x10d/0x750 net/core/skbuff.c:5227
sock_alloc_send_pskb+0x787/0x9b0 net/core/sock.c:2085
packet_alloc_skb net/packet/af_packet.c:2803 [inline]
packet_snd net/packet/af_packet.c:2894 [inline]
packet_sendmsg+0x1ece/0x60b0 net/packet/af_packet.c:2969
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg+0xca/0x110 net/socket.c:640
SYSC_sendto+0x361/0x5c0 net/socket.c:1747
SyS_sendto+0x40/0x50 net/socket.c:1715
do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
Freed by task 4418:
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
__kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:520
kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:527
__cache_free mm/slab.c:3486 [inline]
kfree+0xd9/0x260 mm/slab.c:3801
skb_free_head+0x74/0xb0 net/core/skbuff.c:550
skb_release_data+0x58c/0x790 net/core/skbuff.c:570
skb_release_all+0x4a/0x60 net/core/skbuff.c:627
__kfree_skb net/core/skbuff.c:641 [inline]
consume_skb+0x153/0x490 net/core/skbuff.c:701
packet_rcv+0x15b/0x16c0 net/packet/af_packet.c:2162
dev_queue_xmit_nit+0x866/0xc40 net/core/dev.c:1991
xmit_one net/core/dev.c:3022 [inline]
dev_hard_start_xmit+0x16b/0xac0 net/core/dev.c:3042
__dev_queue_xmit+0x26bf/0x2fc0 net/core/dev.c:3557
dev_queue_xmit+0x17/0x20 net/core/dev.c:3590
packet_snd net/packet/af_packet.c:2944 [inline]
packet_sendmsg+0x3aed/0x60b0 net/packet/af_packet.c:2969
sock_sendmsg_nosec net/socket.c:630 [inline]
sock_sendmsg+0xca/0x110 net/socket.c:640
SYSC_sendto+0x361/0x5c0 net/socket.c:1747
SyS_sendto+0x40/0x50 net/socket.c:1715
do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
The buggy address belongs to the object at ffff8801b4117280
which belongs to the cache kmalloc-512 of size 512
The buggy address is located 280 bytes inside of
512-byte region [ffff8801b4117280, ffff8801b4117480)
The buggy address belongs to the page:
page:ffffea0006d045c0 count:1 mapcount:0 mapping:ffff8801b4117000 index:0x0
IPv6: ADDRCONF(NETDEV_UP): bond0: link is not ready
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffff8801b4117000 0000000000000000 0000000100000006
raw: ffffea0007243760 ffffea0007246a20 ffff8801dac00940 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
8021q: adding VLAN 0 to HW filter on device bond0
ffff8801b4117280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8801b4117300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ffff8801b4117380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff8801b4117400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8801b4117480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================
---
This bug is generated by a dumb bot. It may contain errors.
See https://goo.gl/tpsmEJ for details.
Direct all questions to syzkaller@googlegroups.com.
syzbot will keep track of this bug report.
If you forgot to add the Reported-by tag, once the fix for this bug is
merged
into any tree, please reply to this email with:
#syz fix: exact-commit-title
If you want to test a patch for this bug, please reply with:
#syz test: git://repo/address.git branch
and provide the patch inline or as an attachment.
To mark this as a duplicate of another syzbot report, please reply with:
#syz dup: exact-subject-of-another-report
If it's a one-off invalid bug report, please reply with:
#syz invalid
Note: if the crash happens again, it will cause creation of a new bug
report.
Note: all commands must start from beginning of the line in the email body.
^ permalink raw reply
* [PATCH net] ibmvnic: Disable irqs before exiting reset from closed state
From: John Allen @ 2018-03-30 18:44 UTC (permalink / raw)
To: netdev; +Cc: Thomas Falcon, Nathan Fontenot
When the driver is closed, all the associated irqs are disabled. In the
event that the driver exits a reset in the closed state, we should be
consistent with the state we are in directly after a close. So before we
exit the reset routine, all irqs should be disabled as well. This will
prevent the irqs from being enabled twice in this case and reporting a
number of noisy warning traces.
Signed-off-by: John Allen <jallen@linux.vnet.ibm.com>
---
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 0389a7a..b492af6 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1167,19 +1167,11 @@ static void clean_tx_pools(struct ibmvnic_adapter *adapter)
}
}
-static void ibmvnic_cleanup(struct net_device *netdev)
+static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
{
- struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+ struct net_device *netdev = adapter->netdev;
int i;
- /* ensure that transmissions are stopped if called by do_reset */
- if (adapter->resetting)
- netif_tx_disable(netdev);
- else
- netif_tx_stop_all_queues(netdev);
-
- ibmvnic_napi_disable(adapter);
-
if (adapter->tx_scrq) {
for (i = 0; i < adapter->req_tx_queues; i++)
if (adapter->tx_scrq[i]->irq) {
@@ -1198,6 +1190,21 @@ static void ibmvnic_cleanup(struct net_device *netdev)
}
}
}
+}
+
+static void ibmvnic_cleanup(struct net_device *netdev)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+
+ /* ensure that transmissions are stopped if called by do_reset */
+ if (adapter->resetting)
+ netif_tx_disable(netdev);
+ else
+ netif_tx_stop_all_queues(netdev);
+
+ ibmvnic_napi_disable(adapter);
+ ibmvnic_disable_irqs(adapter);
+
clean_rx_pools(adapter);
clean_tx_pools(adapter);
}
@@ -1772,6 +1779,7 @@ static int do_reset(struct ibmvnic_adapter *adapter,
}
}
+ ibmvnic_disable_irqs(adapter);
adapter->state = VNIC_CLOSED;
if (reset_state == VNIC_CLOSED)
^ permalink raw reply related
* Re: [PATCH net-next v2 1/2] fs/crashdd: add API to collect hardware dump in second kernel
From: Eric W. Biederman @ 2018-03-30 18:42 UTC (permalink / raw)
To: Rahul Lakkireddy
Cc: Jiri Pirko, netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
kexec@lists.infradead.org, linux-kernel@vger.kernel.org,
davem@davemloft.net, viro@zeniv.linux.org.uk,
stephen@networkplumber.org, akpm@linux-foundation.org,
torvalds@linux-foundation.org, Ganesh GR, Nirranjan Kirubaharan,
Indranil Choudhury
In-Reply-To: <20180330105156.GA24344@chelsio.com>
Rahul Lakkireddy <rahul.lakkireddy@chelsio.com> writes:
> On Friday, March 03/30/18, 2018 at 16:09:07 +0530, Jiri Pirko wrote:
>> Sat, Mar 24, 2018 at 11:56:33AM CET, rahul.lakkireddy@chelsio.com wrote:
>> >Add a new module crashdd that exports the /sys/kernel/crashdd/
>> >directory in second kernel, containing collected hardware/firmware
>> >dumps.
>> >
>> >The sequence of actions done by device drivers to append their device
>> >specific hardware/firmware logs to /sys/kernel/crashdd/ directory are
>> >as follows:
>> >
>> >1. During probe (before hardware is initialized), device drivers
>> >register to the crashdd module (via crashdd_add_dump()), with
>> >callback function, along with buffer size and log name needed for
>> >firmware/hardware log collection.
>> >
>> >2. Crashdd creates a driver's directory under
>> >/sys/kernel/crashdd/<driver>. Then, it allocates the buffer with
>>
>> This smells. I need to identify the exact ASIC instance that produced
>> the dump. To identify by driver name does not help me if I have multiple
>> instances of the same driver. This looks wrong to me. This looks like
>> a job for devlink where you have 1 devlink instance per 1 ASIC instance.
>>
>> Please see:
>> http://patchwork.ozlabs.org/project/netdev/list/?series=36524
>>
>> I bevieve that the solution in the patchset could be used for
>> your usecase too.
>>
>>
>
> The sysfs approach proposed here had been dropped in favour exporting
> the dumps as ELF notes in /proc/vmcore.
>
> Will be posting the new patches soon.
The concern was actually how you identify which device that came from.
Where you read the identifier changes but sysfs or /proc/vmcore the
change remains valid.
Eric
^ permalink raw reply
* [PATCH] ath9k: dfs: remove accidental use of stack VLA
From: Gustavo A. R. Silva @ 2018-03-30 18:34 UTC (permalink / raw)
To: QCA ath9k Development, Kalle Valo
Cc: linux-wireless, netdev, linux-kernel, Gustavo A. R. Silva
In preparation to enabling -Wvla, remove accidental use of stack VLA.
This avoids an accidental stack VLA (since the compiler thinks
the value of FFT_NUM_SAMPLES can change, even when marked
"const"). This just replaces it with a #define.
Also, fixed as part of the directive to remove all VLAs from
the kernel: https://lkml.org/lkml/2018/3/7/621
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
---
drivers/net/wireless/ath/ath9k/dfs.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/ath/ath9k/dfs.c b/drivers/net/wireless/ath/ath9k/dfs.c
index 6fee9a4..c8844f5 100644
--- a/drivers/net/wireless/ath/ath9k/dfs.c
+++ b/drivers/net/wireless/ath/ath9k/dfs.c
@@ -41,7 +41,7 @@ static const int BIN_DELTA_MAX = 10;
/* we need at least 3 deltas / 4 samples for a reliable chirp detection */
#define NUM_DIFFS 3
-static const int FFT_NUM_SAMPLES = (NUM_DIFFS + 1);
+#define FFT_NUM_SAMPLES (NUM_DIFFS + 1)
/* Threshold for difference of delta peaks */
static const int MAX_DIFF = 2;
@@ -114,7 +114,7 @@ static bool ath9k_check_chirping(struct ath_softc *sc, u8 *data,
ath_dbg(common, DFS, "HT40: datalen=%d, num_fft_packets=%d\n",
datalen, num_fft_packets);
- if (num_fft_packets < (FFT_NUM_SAMPLES)) {
+ if (num_fft_packets < FFT_NUM_SAMPLES) {
ath_dbg(common, DFS, "not enough packets for chirp\n");
return false;
}
@@ -136,7 +136,7 @@ static bool ath9k_check_chirping(struct ath_softc *sc, u8 *data,
return false;
ath_dbg(common, DFS, "HT20: datalen=%d, num_fft_packets=%d\n",
datalen, num_fft_packets);
- if (num_fft_packets < (FFT_NUM_SAMPLES)) {
+ if (num_fft_packets < FFT_NUM_SAMPLES) {
ath_dbg(common, DFS, "not enough packets for chirp\n");
return false;
}
--
2.7.4
^ permalink raw reply related
* Re: [PATCH] net: mvneta: fix enable of all initialized RXQs
From: David Miller @ 2018-03-30 18:28 UTC (permalink / raw)
To: gregory.clement
Cc: linux-kernel, netdev, thomas.petazzoni, antoine.tenart,
miquel.raynal, maxime.chevallier, stefanc, ymarkman, yelena
In-Reply-To: <20180330100531.5995-1-gregory.clement@bootlin.com>
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Fri, 30 Mar 2018 12:05:31 +0200
> From: Yelena Krivosheev <yelena@marvell.com>
>
> In mvneta_port_up() we enable relevant RX and TX port queues by write
> queues bit map to an appropriate register.
>
> q_map must be ZERO in the beginning of this process.
>
> Signed-off-by: Yelena Krivosheev <yelena@marvell.com>
> Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Applied, thank you.
^ permalink raw reply
* [PATCH bpf-next 02/10] bpf: btf: Validate type reference
From: Martin KaFai Lau @ 2018-03-30 18:26 UTC (permalink / raw)
To: netdev; +Cc: Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <20180330182643.3539371-1-kafai@fb.com>
After collecting all btf_type in the first pass in an earlier patch,
the second pass (in this patch) can validate the reference types
(e.g. the referring type does exist and it does not refer to itself).
While checking the reference type, it also gathers other information (e.g.
the size of an array). This info will be useful in checking the
struct's members in a later patch. They will also be useful in doing
pretty print later.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
---
include/linux/btf.h | 37 +++
kernel/bpf/btf.c | 666 +++++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 702 insertions(+), 1 deletion(-)
create mode 100644 include/linux/btf.h
diff --git a/include/linux/btf.h b/include/linux/btf.h
new file mode 100644
index 000000000000..f14b60368753
--- /dev/null
+++ b/include/linux/btf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#ifndef _LINUX_BTF_H
+#define _LINUX_BTF_H 1
+
+#include <linux/types.h>
+
+struct btf;
+struct btf_type;
+
+/* Figure out the size of a type_id. If type_id is a modifier
+ * (e.g. const), it will be resolved to find out the type with size.
+ *
+ * For example:
+ * In describing "const void *", type_id is "const" and "const"
+ * refers to "void *". The return type will be "void *".
+ *
+ * If type_id is a simple "int", then return type will be "int".
+ *
+ * @btf: struct btf object
+ * @type_id: Find out the size of type_id. The type_id of the return
+ * type is set to *type_id.
+ * @ret_size: It can be NULL. If not NULL, the size of the return
+ * type is set to *ret_size.
+ * Return: The btf_type (resolved to another type with size info if needed).
+ * NULL is returned if type_id itself does not have size info
+ * (e.g. void) or it cannot be resolved to another type that
+ * has size info.
+ * *type_id and *ret_size will not be changed in the
+ * NULL return case.
+ */
+const struct btf_type *btf_type_id_size(const struct btf *btf,
+ u32 *type_id,
+ u32 *ret_size);
+
+#endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3454e729e8fd..f0147dd9a3aa 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -105,6 +105,50 @@
*
* In the first pass, it still does some verifications (e.g.
* checking the name is a valid offset to the string section).
+ *
+ * Pass #2
+ * ~~~~~~~
+ * The main focus is to resolve a btf_type that is referring
+ * to another type.
+ *
+ * We have to ensure the referring type:
+ * 1) does exist in the BTF (i.e. in btf->types[])
+ * 2) does not cause a loop:
+ * struct A {
+ * struct B b;
+ * };
+ *
+ * struct B {
+ * struct A a;
+ * };
+ *
+ * btf_type_needs_resolve() decides if a btf_type needs
+ * to be resolved.
+ *
+ * The needs_resolve type implements the "resolve()" ops which
+ * essentially does a DFS and detects backedge.
+ *
+ * During resolve (or DFS), different C types have different
+ * "RESOLVED" conditions.
+ *
+ * When resolving a BTF_KIND_STRUCT, we need to resolve all its
+ * members because a member is always referring to another
+ * type. A struct's member can be treated as "RESOLVED" if
+ * it is referring to a BTF_KIND_PTR. Otherwise, the
+ * following valid C struct would be rejected:
+ *
+ * struct A {
+ * int m;
+ * struct A *a;
+ * };
+ *
+ * When resolving a BTF_KIND_PTR, it needs to keep resolving if
+ * it is referring to another BTF_KIND_PTR. Otherwise, we cannot
+ * detect a pointer loop, e.g.:
+ * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR +
+ * ^ |
+ * +-----------------------------------------+
+ *
*/
#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE)
@@ -123,12 +167,19 @@
i < btf_type_vlen(struct_type); \
i++, member++)
+#define for_each_member_from(i, from, struct_type, member) \
+ for (i = from, member = btf_type_member(struct_type) + from; \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
+
struct btf {
union {
struct btf_header *hdr;
void *data;
};
struct btf_type **types;
+ u32 *resolved_ids;
+ u32 *resolved_sizes;
const char *strings;
void *nohdr_data;
u32 nr_types;
@@ -136,10 +187,42 @@ struct btf {
u32 data_size;
};
+enum verifier_phase {
+ CHECK_META,
+ CHECK_TYPE,
+};
+
+struct resolve_vertex {
+ const struct btf_type *t;
+ u32 type_id;
+ u16 next_member;
+};
+
+enum visit_state {
+ NOT_VISITED,
+ VISITED,
+ RESOLVED,
+};
+
+enum resolve_mode {
+ RESOLVE_TBD, /* To Be Determined */
+ RESOLVE_PTR, /* Resolving for Pointer */
+ RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union
+ * or array
+ */
+};
+
+#define MAX_RESOLVE_DEPTH 32
+
struct btf_verifier_env {
struct btf *btf;
+ u8 *visit_states;
+ struct resolve_vertex stack[MAX_RESOLVE_DEPTH];
struct bpf_verifier_log log;
u32 log_type_id;
+ u32 top_stack;
+ enum verifier_phase phase;
+ enum resolve_mode resolve_mode;
};
static const char * const btf_kind_str[NR_BTF_KINDS] = {
@@ -163,6 +246,8 @@ struct btf_kind_operations {
s32 (*check_meta)(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left);
+ int (*resolve)(struct btf_verifier_env *env,
+ const struct resolve_vertex *v);
void (*log_details)(struct btf_verifier_env *env,
const struct btf_type *t);
};
@@ -170,6 +255,102 @@ struct btf_kind_operations {
static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
static struct btf_type btf_void;
+static bool btf_type_is_modifier(const struct btf_type *t)
+{
+ /* Some of them is not strictly a C modifier
+ * but they are grouped into the same bucket
+ * for BTF concern:
+ * A type (t) that refers to another
+ * type through t->type AND its size cannot
+ * be determined without following the t->type.
+ *
+ * ptr does not fall into this bucket
+ * because its size is always sizeof(void *).
+ */
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return true;
+ };
+
+ return false;
+}
+
+static bool btf_type_is_void(const struct btf_type *t)
+{
+ /* void => no type and size info.
+ * Hence, FWD is also treated as void.
+ */
+ return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+}
+
+static bool btf_type_is_void_or_null(const struct btf_type *t)
+{
+ return !t || btf_type_is_void(t);
+}
+
+/* union is only a special case of struct:
+ * all its offsetof(member) == 0
+ */
+static bool btf_type_is_struct(const struct btf_type *t)
+{
+ u8 kind = BTF_INFO_KIND(t->info);
+
+ return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static bool btf_type_is_array(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
+}
+
+static bool btf_type_is_ptr(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
+}
+
+static bool btf_type_is_int(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
+}
+
+/* What types need to be resolved?
+ *
+ * btf_type_is_modifier() is an obvious one.
+ *
+ * btf_type_is_struct() because its member refers to
+ * another type (through member->type).
+
+ * btf_type_is_array() because its element (array->type)
+ * refers to another type. Array can be thought of a
+ * special case of struct while array just has the same
+ * member-type repeated by array->nelems of times.
+ */
+static bool btf_type_needs_resolve(const struct btf_type *t)
+{
+ return btf_type_is_modifier(t) ||
+ btf_type_is_ptr(t) ||
+ btf_type_is_struct(t) ||
+ btf_type_is_array(t);
+}
+
+/* t->size can be used */
+static bool btf_type_has_size(const struct btf_type *t)
+{
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_INT:
+ case BTF_KIND_FLOAT:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_ENUM:
+ return true;
+ };
+
+ return false;
+}
+
static const char *btf_int_encoding_str(u8 encoding)
{
if (encoding == 0)
@@ -232,6 +413,14 @@ static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
return "(invalid-name-offset)";
}
+static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
+{
+ if (type_id > btf->nr_types)
+ return NULL;
+
+ return btf->types[type_id];
+}
+
__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
const char *fmt, ...)
{
@@ -306,6 +495,15 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
if (!bpf_verifier_log_needed(log))
return;
+ /* The CHECK_META phase already did a btf dump.
+ *
+ * If member is logged again, it must hit an error in
+ * parsing this member. It is useful to print out which
+ * struct this member belongs to.
+ */
+ if (env->phase != CHECK_META)
+ btf_verifier_log_type(env, struct_type, NULL);
+
__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
btf_name_by_offset(btf, member->name),
member->type, member->offset);
@@ -367,15 +565,176 @@ static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t)
static void btf_free(struct btf *btf)
{
kfree(btf->types);
+ kfree(btf->resolved_sizes);
+ kfree(btf->resolved_ids);
kfree(btf->data);
kfree(btf);
}
+static int env_resolve_init(struct btf_verifier_env *env)
+{
+ struct btf *btf = env->btf;
+ u32 nr_types = btf->nr_types;
+ u32 *resolved_sizes = NULL;
+ u32 *resolved_ids = NULL;
+ u8 *visit_states = NULL;
+
+ /* +1 for btf_void */
+ resolved_sizes = kvzalloc((nr_types + 1) * sizeof(*resolved_sizes),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!resolved_sizes)
+ goto nomem;
+
+ resolved_ids = kvzalloc((nr_types + 1) * sizeof(*resolved_ids),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!resolved_ids)
+ goto nomem;
+
+ visit_states = kvzalloc((nr_types + 1) * sizeof(*visit_states),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!visit_states)
+ goto nomem;
+
+ btf->resolved_sizes = resolved_sizes;
+ btf->resolved_ids = resolved_ids;
+ env->visit_states = visit_states;
+
+ return 0;
+
+nomem:
+ kfree(resolved_sizes);
+ kfree(resolved_ids);
+ kfree(visit_states);
+ return -ENOMEM;
+}
+
static void btf_verifier_env_free(struct btf_verifier_env *env)
{
+ kfree(env->visit_states);
kfree(env);
}
+static bool env_type_is_resolve_sink(const struct btf_verifier_env *env,
+ const struct btf_type *next_type)
+{
+ switch (env->resolve_mode) {
+ case RESOLVE_TBD:
+ /* int, enum or void is a sink */
+ return !btf_type_needs_resolve(next_type);
+ case RESOLVE_PTR:
+ /* int, enum, void, struct or array is a sink for ptr */
+ return !btf_type_is_modifier(next_type) &&
+ !btf_type_is_ptr(next_type);
+ case RESOLVE_STRUCT_OR_ARRAY:
+ /* int, enum, void or ptr is a sink for struct and array */
+ return !btf_type_is_modifier(next_type) &&
+ !btf_type_is_array(next_type) &&
+ !btf_type_is_struct(next_type);
+ default:
+ BUG_ON(1);
+ };
+}
+
+static bool env_type_is_resolved(const struct btf_verifier_env *env,
+ u32 type_id)
+{
+ return env->visit_states[type_id] == RESOLVED;
+}
+
+static int env_stack_push(struct btf_verifier_env *env,
+ const struct btf_type *t, u32 type_id)
+{
+ struct resolve_vertex *v;
+
+ if (env->top_stack == MAX_RESOLVE_DEPTH)
+ return -E2BIG;
+
+ if (env->visit_states[type_id] != NOT_VISITED)
+ return -EEXIST;
+
+ env->visit_states[type_id] = VISITED;
+
+ v = &env->stack[env->top_stack++];
+ v->t = t;
+ v->type_id = type_id;
+ v->next_member = 0;
+
+ if (env->resolve_mode == RESOLVE_TBD) {
+ if (btf_type_is_ptr(t))
+ env->resolve_mode = RESOLVE_PTR;
+ else if (btf_type_is_struct(t) || btf_type_is_array(t))
+ env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY;
+ }
+
+ return 0;
+}
+
+static void env_stack_set_next_member(struct btf_verifier_env *env,
+ u16 next_member)
+{
+ env->stack[env->top_stack - 1].next_member = next_member;
+}
+
+static void env_stack_pop_resolved(struct btf_verifier_env *env,
+ u32 resolved_type_id,
+ u32 resolved_size)
+{
+ u32 type_id = env->stack[--(env->top_stack)].type_id;
+ struct btf *btf = env->btf;
+
+ btf->resolved_sizes[type_id] = resolved_size;
+ btf->resolved_ids[type_id] = resolved_type_id;
+ env->visit_states[type_id] = RESOLVED;
+}
+
+static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
+{
+ return env->top_stack ? &env->stack[env->top_stack - 1] : NULL;
+}
+
+/* The input param "type_id" must point to a needs_resolve type */
+static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
+ u32 *type_id)
+{
+ *type_id = btf->resolved_ids[*type_id];
+ return btf_type_by_id(btf, *type_id);
+}
+
+const struct btf_type *btf_type_id_size(const struct btf *btf,
+ u32 *type_id, u32 *ret_size)
+{
+ const struct btf_type *size_type;
+ u32 size_type_id = *type_id;
+ u32 size = 0;
+
+ size_type = btf_type_by_id(btf, size_type_id);
+ if (btf_type_is_void_or_null(size_type))
+ return NULL;
+
+ if (btf_type_has_size(size_type)) {
+ size = size_type->size;
+ } else if (btf_type_is_array(size_type)) {
+ size = btf->resolved_sizes[size_type_id];
+ } else if (btf_type_is_ptr(size_type)) {
+ size = sizeof(void *);
+ } else {
+ if (WARN_ON_ONCE(!btf_type_is_modifier(size_type)))
+ return NULL;
+
+ size = btf->resolved_sizes[size_type_id];
+ size_type_id = btf->resolved_ids[size_type_id];
+ size_type = btf_type_by_id(btf, size_type_id);
+ if (btf_type_is_void(size_type))
+ return NULL;
+ }
+
+ *type_id = size_type_id;
+ if (ret_size)
+ *ret_size = size;
+
+ return size_type;
+}
+
static int btf_df_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
@@ -384,6 +743,13 @@ static int btf_df_check_meta(struct btf_verifier_env *env,
return -ENOTSUPP;
}
+static int btf_df_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ btf_verifier_log_basic(env, v->t, "Unsupported resolve");
+ return -EINVAL;
+}
+
static void btf_df_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
@@ -392,6 +758,7 @@ static void btf_df_log(struct btf_verifier_env *env,
static struct btf_kind_operations df_ops = {
.check_meta = btf_df_check_meta,
+ .resolve = btf_df_resolve,
.log_details = btf_df_log,
};
@@ -459,6 +826,7 @@ static void btf_int_log(struct btf_verifier_env *env,
const struct btf_kind_operations int_ops = {
.check_meta = btf_int_check_meta,
+ .resolve = btf_df_resolve,
.log_details = btf_int_log,
};
@@ -481,6 +849,102 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
return 0;
}
+static int btf_modifier_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_type *t = v->t;
+ u32 next_type_id = t->type;
+ struct btf *btf = env->btf;
+ const struct btf_type *next_type = btf_type_by_id(btf, next_type_id);
+ u32 next_type_size = 0;
+
+ if (!next_type) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ /* "typedef void new_void", "const void"...etc */
+ if (btf_type_is_void(next_type))
+ goto resolved;
+
+ if (!env_type_is_resolve_sink(env, next_type) &&
+ !env_type_is_resolved(env, next_type_id))
+ return env_stack_push(env, next_type, next_type_id);
+
+ /* Figure out the resolved next_type_id with size.
+ * They will be stored in the current modifier's
+ * resolved_ids and resolved_sizes such that it can
+ * save us a few type-following when we use it later (e.g. in
+ * pretty print).
+ */
+ if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
+ !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+resolved:
+ env_stack_pop_resolved(env, next_type_id, next_type_size);
+
+ return 0;
+}
+
+static int btf_ptr_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_type *t = v->t;
+ u32 next_type_id = t->type;
+ struct btf *btf = env->btf;
+ const struct btf_type *next_type = btf_type_by_id(btf, next_type_id);
+ u32 next_type_size = 0;
+
+ if (!next_type) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ /* "void *" */
+ if (btf_type_is_void(next_type))
+ goto resolved;
+
+ if (!env_type_is_resolve_sink(env, next_type) &&
+ !env_type_is_resolved(env, next_type_id))
+ return env_stack_push(env, next_type, next_type_id);
+
+ /* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY,
+ * the modifier may have stopped resolving when it was resolved
+ * to a ptr (last-resolved-ptr).
+ *
+ * We now need to continue from the last-resolved-ptr to
+ * ensure the last-resolved-ptr will not referring back to
+ * the currenct ptr (t).
+ */
+ if (btf_type_is_modifier(next_type)) {
+ const struct btf_type *resolved_type;
+ u32 resolved_type_id;
+
+ resolved_type_id = next_type_id;
+ resolved_type = btf_type_id_resolve(btf, &resolved_type_id);
+
+ if (btf_type_is_ptr(resolved_type) &&
+ !env_type_is_resolve_sink(env, resolved_type) &&
+ !env_type_is_resolved(env, resolved_type_id))
+ return env_stack_push(env, resolved_type,
+ resolved_type_id);
+ }
+
+ if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
+ !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+resolved:
+ env_stack_pop_resolved(env, next_type_id, 0);
+
+ return 0;
+}
+
static void btf_ref_type_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
@@ -489,16 +953,19 @@ static void btf_ref_type_log(struct btf_verifier_env *env,
static struct btf_kind_operations modifier_ops = {
.check_meta = btf_ref_type_check_meta,
+ .resolve = btf_modifier_resolve,
.log_details = btf_ref_type_log,
};
static struct btf_kind_operations ptr_ops = {
.check_meta = btf_ref_type_check_meta,
+ .resolve = btf_ptr_resolve,
.log_details = btf_ref_type_log,
};
static struct btf_kind_operations fwd_ops = {
.check_meta = btf_ref_type_check_meta,
+ .resolve = btf_df_resolve,
.log_details = btf_ref_type_log,
};
@@ -537,6 +1004,61 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env,
return meta_needed;
}
+static int btf_array_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_array *array = btf_type_array(v->t);
+ u32 elem_type_id = array->type;
+ struct btf *btf = env->btf;
+ const struct btf_type *elem_type;
+ u32 elem_size;
+
+ elem_type = btf_type_by_id(btf, elem_type_id);
+ if (btf_type_is_void_or_null(elem_type)) {
+ btf_verifier_log_type(env, v->t,
+ "Invalid elem");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, elem_type) &&
+ !env_type_is_resolved(env, elem_type_id))
+ return env_stack_push(env, elem_type, elem_type_id);
+
+ elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+ if (!elem_type) {
+ btf_verifier_log_type(env, v->t, "Invalid elem");
+ return -EINVAL;
+ }
+
+ if (btf_type_is_int(elem_type)) {
+ int int_type_data = btf_type_int(elem_type);
+ u16 nr_bits = BTF_INT_BITS(int_type_data);
+ u16 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+
+ /* Put more restriction on array of int. The int cannot
+ * be a bit field and it must be either u8/u16/u32/u64.
+ */
+ if (BITS_PER_BYTE_MASKED(nr_bits) ||
+ BTF_INT_OFFSET(int_type_data) ||
+ (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
+ nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) {
+ btf_verifier_log_type(env, v->t,
+ "Invalid array of int");
+ return -EINVAL;
+ }
+ }
+
+ if (array->nelems && elem_size > U32_MAX / array->nelems) {
+ btf_verifier_log_type(env, v->t,
+ "Array size overflows U32_MAX");
+ return -EINVAL;
+ }
+
+ env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems);
+
+ return 0;
+}
+
static void btf_array_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
@@ -548,6 +1070,7 @@ static void btf_array_log(struct btf_verifier_env *env,
static struct btf_kind_operations array_ops = {
.check_meta = btf_array_check_meta,
+ .resolve = btf_array_resolve,
.log_details = btf_array_log,
};
@@ -607,6 +1130,50 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return meta_needed;
}
+static int btf_struct_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_member *member;
+ u16 i;
+
+ /* Before continue resolving the next_member,
+ * ensure the last member is indeed resolved to a
+ * type with size info.
+ */
+ if (v->next_member) {
+ const struct btf_member *last_member;
+ u16 last_member_type_id;
+
+ last_member = btf_type_member(v->t) + v->next_member - 1;
+ last_member_type_id = last_member->type;
+ if (WARN_ON_ONCE(!env_type_is_resolved(env,
+ last_member_type_id)))
+ return -EINVAL;
+ }
+
+ for_each_member_from(i, v->next_member, v->t, member) {
+ u32 member_type_id = member->type;
+ const struct btf_type *member_type = btf_type_by_id(env->btf,
+ member_type_id);
+
+ if (btf_type_is_void_or_null(member_type)) {
+ btf_verifier_log_member(env, v->t, member,
+ "Invalid member");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, member_type) &&
+ !env_type_is_resolved(env, member_type_id)) {
+ env_stack_set_next_member(env, i + 1);
+ return env_stack_push(env, member_type, member_type_id);
+ }
+ }
+
+ env_stack_pop_resolved(env, 0, 0);
+
+ return 0;
+}
+
static void btf_struct_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
@@ -615,6 +1182,7 @@ static void btf_struct_log(struct btf_verifier_env *env,
static struct btf_kind_operations struct_ops = {
.check_meta = btf_struct_check_meta,
+ .resolve = btf_struct_resolve,
.log_details = btf_struct_log,
};
@@ -665,6 +1233,7 @@ static void btf_enum_log(struct btf_verifier_env *env,
struct btf_kind_operations enum_ops = {
.check_meta = btf_enum_check_meta,
+ .resolve = btf_df_resolve,
.log_details = btf_enum_log,
};
@@ -743,9 +1312,104 @@ static int btf_check_all_metas(struct btf_verifier_env *env)
return 0;
}
+static int btf_resolve(struct btf_verifier_env *env,
+ const struct btf_type *t, u32 type_id)
+{
+ const struct resolve_vertex *v;
+ int err = 0;
+
+ env->resolve_mode = RESOLVE_TBD;
+ env_stack_push(env, t, type_id);
+ while (!err && (v = env_stack_peak(env))) {
+ env->log_type_id = v->type_id;
+ err = btf_type_ops(v->t)->resolve(env, v);
+ }
+
+ env->log_type_id = type_id;
+ if (err == -E2BIG)
+ btf_verifier_log_type(env, t,
+ "Exceeded max resolving depth:%u",
+ MAX_RESOLVE_DEPTH);
+ else if (err == -EEXIST)
+ btf_verifier_log_type(env, t, "Loop detected");
+
+ return err;
+}
+
+static bool btf_resolve_valid(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 type_id)
+{
+ struct btf *btf = env->btf;
+
+ if (!env_type_is_resolved(env, type_id))
+ return false;
+
+ if (btf_type_is_struct(t))
+ return !btf->resolved_ids[type_id] &&
+ !btf->resolved_sizes[type_id];
+
+ if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) {
+ t = btf_type_id_resolve(btf, &type_id);
+ return t && !btf_type_is_modifier(t);
+ }
+
+ if (btf_type_is_array(t)) {
+ const struct btf_array *array = btf_type_array(t);
+ const struct btf_type *elem_type;
+ u32 elem_type_id = array->type;
+ u32 elem_size;
+
+ elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+ return elem_type && !btf_type_is_modifier(elem_type) &&
+ (array->nelems * elem_size ==
+ btf->resolved_sizes[type_id]);
+ }
+
+ return false;
+}
+
+static int btf_check_all_types(struct btf_verifier_env *env)
+{
+ struct btf *btf = env->btf;
+ u32 type_id;
+ int err;
+
+ err = env_resolve_init(env);
+ if (err)
+ return err;
+
+ env->phase++;
+ for (type_id = 1; type_id <= btf->nr_types; type_id++) {
+ const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+ env->log_type_id = type_id;
+ if (btf_type_needs_resolve(t) &&
+ !env_type_is_resolved(env, type_id)) {
+ err = btf_resolve(env, t, type_id);
+ if (err)
+ return err;
+ }
+
+ if (btf_type_needs_resolve(t) &&
+ !btf_resolve_valid(env, t, type_id)) {
+ btf_verifier_log_type(env, t, "Invalid resolve state");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int btf_parse_type_sec(struct btf_verifier_env *env)
{
- return btf_check_all_metas(env);
+ int err;
+
+ err = btf_check_all_metas(env);
+ if (err)
+ return err;
+
+ return btf_check_all_types(env);
}
static int btf_parse_str_sec(struct btf_verifier_env *env)
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next 04/10] bpf: btf: Add pretty print capability for data with BTF type info
From: Martin KaFai Lau @ 2018-03-30 18:26 UTC (permalink / raw)
To: netdev; +Cc: Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <20180330182643.3539371-1-kafai@fb.com>
This patch adds pretty print capability for data with BTF type info.
The current usage is to allow pretty print of a BPF map.
The next few patches will allow a read() on a pinned map with BTF
type info for its key and value.
This patch uses the seq_printf() infra.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
---
include/linux/btf.h | 2 +
kernel/bpf/btf.c | 199 ++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 201 insertions(+)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index f14b60368753..d8bdab0280ba 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -33,5 +33,7 @@ struct btf_type;
const struct btf_type *btf_type_id_size(const struct btf *btf,
u32 *type_id,
u32 *ret_size);
+void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
+ struct seq_file *m);
#endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 61cdca1700ec..db3082437676 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3,6 +3,7 @@
#include <uapi/linux/btf.h>
#include <uapi/linux/types.h>
+#include <linux/seq_file.h>
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/slab.h>
@@ -254,6 +255,9 @@ struct btf_kind_operations {
const struct btf_type *member_type);
void (*log_details)(struct btf_verifier_env *env,
const struct btf_type *t);
+ void (*seq_show)(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offsets,
+ struct seq_file *m);
};
static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
@@ -770,11 +774,19 @@ static void btf_df_log(struct btf_verifier_env *env,
btf_verifier_log_basic(env, t, "Unsupported log_details");
}
+static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offsets,
+ struct seq_file *m)
+{
+ seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
+}
+
static struct btf_kind_operations df_ops = {
.check_meta = btf_df_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_df_check_member,
.log_details = btf_df_log,
+ .seq_show = btf_df_seq_show,
};
static int btf_int_check_member(struct btf_verifier_env *env,
@@ -877,11 +889,96 @@ static void btf_int_log(struct btf_verifier_env *env,
btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
}
+static void btf_int_bits_seq_show(const struct btf *btf,
+ const struct btf_type *t,
+ void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ u32 int_data = btf_type_int(t);
+ u16 nr_bits = BTF_INT_BITS(int_data);
+ u16 total_bits_offset;
+ u16 nr_copy_bytes;
+ u16 nr_copy_bits;
+ u8 nr_upper_bits;
+ union {
+ u64 u64_num;
+ u8 u8_nums[8];
+ } print_num;
+
+ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
+ data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+ bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+ nr_copy_bits = nr_bits + bits_offset;
+ nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
+
+ print_num.u64_num = 0;
+ memcpy(&print_num.u64_num, data, nr_copy_bytes);
+
+ /* Ditch the higher order bits */
+ nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
+ if (nr_upper_bits) {
+ /* We need to mask out some bits of the upper byte. */
+ u8 mask = (1 << nr_upper_bits) - 1;
+
+ print_num.u8_nums[nr_copy_bytes - 1] &= mask;
+ }
+
+ print_num.u64_num >>= bits_offset;
+
+ seq_printf(m, "0x%llx", print_num.u64_num);
+}
+
+static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ u32 int_data = btf_type_int(t);
+ u32 nr_bits = BTF_INT_BITS(int_data);
+ u8 encoding = BTF_INT_ENCODING(int_data);
+ bool sign = encoding & BTF_INT_SIGNED;
+
+ if (bits_offset || BTF_INT_OFFSET(int_data) ||
+ BITS_PER_BYTE_MASKED(nr_bits)) {
+ btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+ return;
+ }
+
+ switch (nr_bits) {
+ case 64:
+ if (sign)
+ seq_printf(m, "%lld", *(s64 *)data);
+ else
+ seq_printf(m, "%llu", *(u64 *)data);
+ break;
+ case 32:
+ if (sign)
+ seq_printf(m, "%d", *(s32 *)data);
+ else
+ seq_printf(m, "%u", *(u32 *)data);
+ break;
+ case 16:
+ if (sign)
+ seq_printf(m, "%d", *(s16 *)data);
+ else
+ seq_printf(m, "%u", *(u16 *)data);
+ break;
+ case 8:
+ if (sign)
+ seq_printf(m, "%d", *(s8 *)data);
+ else
+ seq_printf(m, "%u", *(u8 *)data);
+ break;
+ default:
+ btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+ }
+}
+
const struct btf_kind_operations int_ops = {
.check_meta = btf_int_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_int_check_member,
.log_details = btf_int_log,
+ .seq_show = btf_int_seq_show,
};
static int btf_modifier_check_member(struct btf_verifier_env *env,
@@ -1050,6 +1147,24 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
return 0;
}
+static void btf_modifier_seq_show(const struct btf *btf,
+ const struct btf_type *t,
+ u32 type_id, void *data,
+ u8 bits_offset, struct seq_file *m)
+{
+ t = btf_type_id_resolve(btf, &type_id);
+
+ btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+}
+
+static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ /* It is a hashed value */
+ seq_printf(m, "%p", *(void **)data);
+}
+
static void btf_ref_type_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
@@ -1061,6 +1176,7 @@ static struct btf_kind_operations modifier_ops = {
.resolve = btf_modifier_resolve,
.check_member = btf_modifier_check_member,
.log_details = btf_ref_type_log,
+ .seq_show = btf_modifier_seq_show,
};
static struct btf_kind_operations ptr_ops = {
@@ -1068,6 +1184,7 @@ static struct btf_kind_operations ptr_ops = {
.resolve = btf_ptr_resolve,
.check_member = btf_ptr_check_member,
.log_details = btf_ref_type_log,
+ .seq_show = btf_ptr_seq_show,
};
static struct btf_kind_operations fwd_ops = {
@@ -1075,6 +1192,7 @@ static struct btf_kind_operations fwd_ops = {
.resolve = btf_df_resolve,
.check_member = btf_df_check_member,
.log_details = btf_ref_type_log,
+ .seq_show = btf_df_seq_show,
};
static int btf_array_check_member(struct btf_verifier_env *env,
@@ -1205,11 +1323,36 @@ static void btf_array_log(struct btf_verifier_env *env,
array->type, array->index_type, array->nelems);
}
+static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const struct btf_array *array = btf_type_array(t);
+ const struct btf_kind_operations *elem_ops;
+ const struct btf_type *elem_type;
+ u32 i, elem_size, elem_type_id;
+
+ elem_type_id = array->type;
+ elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+ elem_ops = btf_type_ops(elem_type);
+ seq_puts(m, "[");
+ for (i = 0; i < array->nelems; i++) {
+ if (i)
+ seq_puts(m, ",");
+
+ elem_ops->seq_show(btf, elem_type, elem_type_id, data,
+ bits_offset, m);
+ data += elem_size;
+ }
+ seq_puts(m, "]");
+}
+
static struct btf_kind_operations array_ops = {
.check_meta = btf_array_check_meta,
.resolve = btf_array_resolve,
.check_member = btf_array_check_member,
.log_details = btf_array_log,
+ .seq_show = btf_array_seq_show,
};
static int btf_struct_check_member(struct btf_verifier_env *env,
@@ -1358,11 +1501,39 @@ static void btf_struct_log(struct btf_verifier_env *env,
btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
}
+static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ",";
+ const struct btf_member *member;
+ u32 i;
+
+ seq_puts(m, "{");
+ for_each_member(i, t, member) {
+ const struct btf_type *member_type = btf_type_by_id(btf,
+ member->type);
+ u32 member_offset = member->offset;
+ u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
+ u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
+ const struct btf_kind_operations *ops;
+
+ if (i)
+ seq_puts(m, seq);
+
+ ops = btf_type_ops(member_type);
+ ops->seq_show(btf, member_type, member->type,
+ data + bytes_offset, bits8_offset, m);
+ }
+ seq_puts(m, "}");
+}
+
static struct btf_kind_operations struct_ops = {
.check_meta = btf_struct_check_meta,
.resolve = btf_struct_resolve,
.check_member = btf_struct_check_member,
.log_details = btf_struct_log,
+ .seq_show = btf_struct_seq_show,
};
static int btf_enum_check_member(struct btf_verifier_env *env,
@@ -1434,11 +1605,31 @@ static void btf_enum_log(struct btf_verifier_env *env,
btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
}
+static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const struct btf_enum *enums = btf_type_enum(t);
+ u32 i, nr_enums = btf_type_vlen(t);
+ int v = *(int *)data;
+
+ for (i = 0; i < nr_enums; i++) {
+ if (v == enums[i].val) {
+ seq_printf(m, "%s",
+ btf_name_by_offset(btf, enums[i].name));
+ return;
+ }
+ }
+
+ seq_printf(m, "%d", v);
+}
+
struct btf_kind_operations enum_ops = {
.check_meta = btf_enum_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_enum_check_member,
.log_details = btf_enum_log,
+ .seq_show = btf_enum_seq_show,
};
static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
@@ -1781,3 +1972,11 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
btf_free(btf);
return ERR_PTR(err);
}
+
+void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
+ struct seq_file *m)
+{
+ const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+ btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
+}
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next 08/10] bpf: btf: Sync bpf.h and btf.h to tools/
From: Martin KaFai Lau @ 2018-03-30 18:26 UTC (permalink / raw)
To: netdev; +Cc: Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <20180330182643.3539371-1-kafai@fb.com>
This patch sync up the bpf.h and btf.h to tools/
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
---
tools/include/uapi/linux/bpf.h | 13 ++++
tools/include/uapi/linux/btf.h | 132 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 145 insertions(+)
create mode 100644 tools/include/uapi/linux/btf.h
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 58060bec999d..9c0d5cfbcb19 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -95,6 +95,7 @@ enum bpf_cmd {
BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
BPF_RAW_TRACEPOINT_OPEN,
+ BPF_BTF_LOAD,
};
enum bpf_map_type {
@@ -272,6 +273,9 @@ union bpf_attr {
*/
char map_name[BPF_OBJ_NAME_LEN];
__u32 map_ifindex; /* ifindex of netdev to create on */
+ __u32 btf_fd; /* fd pointing to a BTF type data */
+ __u32 btf_key_id; /* BTF type_id of the key */
+ __u32 btf_value_id; /* BTF type_id of the value */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -351,6 +355,14 @@ union bpf_attr {
__u64 name;
__u32 prog_fd;
} raw_tracepoint;
+
+ struct { /* anonymous struct for BPF_BTF_LOAD */
+ __aligned_u64 btf;
+ __aligned_u64 btf_log_buf;
+ __u32 btf_size;
+ __u32 btf_log_size;
+ __u32 btf_log_level;
+ };
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -844,6 +856,7 @@ enum bpf_func_id {
/* BPF_FUNC_skb_set_tunnel_key flags. */
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2)
+#define BPF_F_SEQ_NUMBER (1ULL << 3)
/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
* BPF_FUNC_perf_event_read_value flags.
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
new file mode 100644
index 000000000000..45cbebf25b6f
--- /dev/null
+++ b/tools/include/uapi/linux/btf.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2018 Facebook */
+#ifndef _UAPI__LINUX_BTF_H__
+#define _UAPI__LINUX_BTF_H__
+
+#include <linux/types.h>
+
+#define BTF_MAGIC 0xeB9F
+#define BTF_MAGIC_SWAP 0x9FeB
+#define BTF_VERSION 1
+#define BTF_FLAGS_COMPR 0x01
+
+struct btf_header {
+ __u16 magic;
+ __u8 version;
+ __u8 flags;
+
+ __u32 parent_label;
+ __u32 parent_name;
+
+ /* All offsets are in bytes relative to the end of this header */
+ __u32 label_off; /* offset of label section */
+ __u32 object_off; /* offset of data object section*/
+ __u32 func_off; /* offset of function section */
+ __u32 type_off; /* offset of type section */
+ __u32 str_off; /* offset of string section */
+ __u32 str_len; /* length of string section */
+};
+
+/* Max # of type identifier */
+#define BTF_MAX_TYPE 0x7fffffff
+/* Max offset into the string section */
+#define BTF_MAX_NAME_OFFSET 0x7fffffff
+/* Max # of struct/union/enum members or func args */
+#define BTF_MAX_VLEN 0xffff
+
+/* The type id is referring to a parent BTF */
+#define BTF_TYPE_PARENT(id) (((id) >> 31) & 0x1)
+#define BTF_TYPE_ID(id) ((id) & BTF_MAX_TYPE)
+
+/* String is in the ELF string section */
+#define BTF_STR_TBL_ELF_ID(ref) (((ref) >> 31) & 0x1)
+#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET)
+
+struct btf_type {
+ __u32 name;
+ /* "info" bits arrangement
+ * bits 0-15: vlen (e.g. # of struct's members)
+ * bits 16-23: unused
+ * bits 24-28: kind (e.g. int, ptr, array...etc)
+ * bits 29-30: unused
+ * bits 31: root
+ */
+ __u32 info;
+ /* "size" is used by INT, ENUM, STRUCT and UNION.
+ * "size" tells the size of the type it is describing.
+ *
+ * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+ * "type" is a type_id referring to another type.
+ */
+ union {
+ __u32 size;
+ __u32 type;
+ };
+};
+
+#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
+#define BTF_INFO_ISROOT(info) (!!(((info) >> 24) & 0x80))
+#define BTF_INFO_VLEN(info) ((info) & 0xffff)
+
+#define BTF_KIND_UNKN 0 /* Unknown */
+#define BTF_KIND_INT 1 /* Integer */
+#define BTF_KIND_FLOAT 2 /* Float */
+#define BTF_KIND_PTR 3 /* Pointer */
+#define BTF_KIND_ARRAY 4 /* Array */
+#define BTF_KIND_FUNC 5 /* Function */
+#define BTF_KIND_STRUCT 6 /* Struct */
+#define BTF_KIND_UNION 7 /* Union */
+#define BTF_KIND_ENUM 8 /* Enumeration */
+#define BTF_KIND_FWD 9 /* Forward */
+#define BTF_KIND_TYPEDEF 10 /* Typedef */
+#define BTF_KIND_VOLATILE 11 /* Volatile */
+#define BTF_KIND_CONST 12 /* Const */
+#define BTF_KIND_RESTRICT 13 /* Restrict */
+#define BTF_KIND_MAX 13
+#define NR_BTF_KINDS 14
+
+/* For some specific BTF_KIND, "struct btf_type" is immediately
+ * followed by extra data.
+ */
+
+/* BTF_KIND_INT is followed by a u32 and the following
+ * is the 32 bits arrangement:
+ */
+#define BTF_INT_ENCODING(VAL) (((VAL) & 0xff000000) >> 24)
+#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16)
+#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff)
+
+/* Attributes stored in the BTF_INT_ENCODING */
+#define BTF_INT_SIGNED 0x1
+#define BTF_INT_CHAR 0x2
+#define BTF_INT_BOOL 0x4
+#define BTF_INT_VARARGS 0x8
+
+/* BTF_KIND_ENUM is followed by multiple "struct btf_enum".
+ * The exact number of btf_enum is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum {
+ __u32 name;
+ __s32 val;
+};
+
+/* BTF_KIND_ARRAY is followed by one "struct btf_array" */
+struct btf_array {
+ __u32 type;
+ __u32 index_type;
+ __u32 nelems;
+};
+
+/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed
+ * by multiple "struct btf_member". The exact number
+ * of btf_member is stored in the vlen (of the info in
+ * "struct btf_type").
+*/
+struct btf_member {
+ __u32 name;
+ __u32 type;
+ __u32 offset; /* offset in bits */
+};
+
+#endif /* _UAPI__LINUX_BTF_H__ */
--
2.9.5
^ permalink raw reply related
* [PATCH bpf-next 09/10] bpf: btf: Add BTF support to libbpf
From: Martin KaFai Lau @ 2018-03-30 18:26 UTC (permalink / raw)
To: netdev; +Cc: Alexei Starovoitov, Daniel Borkmann, kernel-team
In-Reply-To: <20180330182643.3539371-1-kafai@fb.com>
If the ".BTF" elf section exists, libbpf will try to create
a btf_fd (through BPF_BTF_LOAD). If that fails, it will still
continue loading the bpf prog/map without the BTF.
If the bpf_object has a BTF loaded, it will create a map with the btf_fd.
libbpf will try to figure out the btf_key_id and btf_value_id of a map by
finding the BTF type with name "<map_name>_key" and "<map_name>_name".
If they cannot be found, it will continue without using the BTF.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@fb.com>
---
tools/lib/bpf/Build | 2 +-
tools/lib/bpf/bpf.c | 92 +++++++++---
tools/lib/bpf/bpf.h | 16 +++
tools/lib/bpf/btf.c | 377 +++++++++++++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/btf.h | 22 +++
tools/lib/bpf/libbpf.c | 148 +++++++++++++++++--
tools/lib/bpf/libbpf.h | 3 +
7 files changed, 629 insertions(+), 31 deletions(-)
create mode 100644 tools/lib/bpf/btf.c
create mode 100644 tools/lib/bpf/btf.h
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 64c679d67109..6070e655042d 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index e0500055f1a6..3768f2a699e5 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -73,43 +73,76 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
return syscall(__NR_bpf, cmd, attr, size);
}
-int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
- int key_size, int value_size, int max_entries,
- __u32 map_flags, int node)
+int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
{
- __u32 name_len = name ? strlen(name) : 0;
+ __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
union bpf_attr attr;
memset(&attr, '\0', sizeof(attr));
- attr.map_type = map_type;
- attr.key_size = key_size;
- attr.value_size = value_size;
- attr.max_entries = max_entries;
- attr.map_flags = map_flags;
- memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+ attr.map_type = create_attr->map_type;
+ attr.key_size = create_attr->key_size;
+ attr.value_size = create_attr->value_size;
+ attr.max_entries = create_attr->max_entries;
+ attr.map_flags = create_attr->map_flags;
+ memcpy(attr.map_name, create_attr->name,
+ min(name_len, BPF_OBJ_NAME_LEN - 1));
+ attr.numa_node = create_attr->numa_node;
+ attr.btf_fd = create_attr->btf_fd;
+ attr.btf_key_id = create_attr->btf_key_id;
+ attr.btf_value_id = create_attr->btf_value_id;
+ return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
+int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+ int key_size, int value_size, int max_entries,
+ __u32 map_flags, int node)
+{
+ struct bpf_create_map_attr map_attr = {};
+
+ map_attr.name = name;
+ map_attr.map_type = map_type;
+ map_attr.map_flags = map_flags;
+ map_attr.key_size = key_size;
+ map_attr.value_size = value_size;
+ map_attr.max_entries = max_entries;
if (node >= 0) {
- attr.map_flags |= BPF_F_NUMA_NODE;
- attr.numa_node = node;
+ map_attr.numa_node = node;
+ map_attr.map_flags |= BPF_F_NUMA_NODE;
}
- return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+ return bpf_create_map_xattr(&map_attr);
}
int bpf_create_map(enum bpf_map_type map_type, int key_size,
int value_size, int max_entries, __u32 map_flags)
{
- return bpf_create_map_node(map_type, NULL, key_size, value_size,
- max_entries, map_flags, -1);
+ struct bpf_create_map_attr map_attr = {};
+
+ map_attr.map_type = map_type;
+ map_attr.map_flags = map_flags;
+ map_attr.key_size = key_size;
+ map_attr.value_size = value_size;
+ map_attr.max_entries = max_entries;
+
+ return bpf_create_map_xattr(&map_attr);
}
int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
int key_size, int value_size, int max_entries,
__u32 map_flags)
{
- return bpf_create_map_node(map_type, name, key_size, value_size,
- max_entries, map_flags, -1);
+ struct bpf_create_map_attr map_attr = {};
+
+ map_attr.name = name;
+ map_attr.map_type = map_type;
+ map_attr.map_flags = map_flags;
+ map_attr.key_size = key_size;
+ map_attr.value_size = value_size;
+ map_attr.max_entries = max_entries;
+
+ return bpf_create_map_xattr(&map_attr);
}
int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
@@ -559,3 +592,28 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
close(sock);
return ret;
}
+
+int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
+ bool do_log)
+{
+ union bpf_attr attr = {};
+ int fd;
+
+ attr.btf = ptr_to_u64(btf);
+ attr.btf_size = btf_size;
+
+retry:
+ if (do_log && log_buf && log_buf_size) {
+ attr.btf_log_level = 1;
+ attr.btf_log_size = log_buf_size;
+ attr.btf_log_buf = ptr_to_u64(log_buf);
+ }
+
+ fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
+ if (fd == -1 && !do_log && log_buf && log_buf_size) {
+ do_log = true;
+ goto retry;
+ }
+
+ return fd;
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index ee59342c6f42..f85817688615 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -26,6 +26,20 @@
#include <linux/bpf.h>
#include <stddef.h>
+struct bpf_create_map_attr {
+ const char *name;
+ enum bpf_map_type map_type;
+ __u32 map_flags;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 max_entries;
+ __u32 numa_node;
+ __u32 btf_fd;
+ __u32 btf_key_id;
+ __u32 btf_value_id;
+};
+
+int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
int key_size, int value_size, int max_entries,
__u32 map_flags, int node);
@@ -80,4 +94,6 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
__u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
int bpf_raw_tracepoint_open(const char *name, int prog_fd);
+int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
+ bool do_log);
#endif
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
new file mode 100644
index 000000000000..b6e13e83dded
--- /dev/null
+++ b/tools/lib/bpf/btf.c
@@ -0,0 +1,377 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <linux/btf.h>
+#include "btf.h"
+#include "bpf.h"
+
+#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); }
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+#define BTF_MAX_NR_TYPES 65535
+
+static struct btf_type btf_void;
+
+struct btf {
+ union {
+ struct btf_header *hdr;
+ void *data;
+ };
+ struct btf_type **types;
+ const char *strings;
+ void *nohdr_data;
+ uint32_t nr_types;
+ uint32_t types_size;
+ uint32_t data_size;
+ int fd;
+};
+
+static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
+{
+ if (!BTF_STR_TBL_ELF_ID(offset) &&
+ BTF_STR_OFFSET(offset) < btf->hdr->str_len)
+ return &btf->strings[BTF_STR_OFFSET(offset)];
+ else
+ return NULL;
+}
+
+static int btf_add_type(struct btf *btf, struct btf_type *t)
+{
+ if (btf->types_size - btf->nr_types < 2) {
+ struct btf_type **new_types;
+ u32 expand_by, new_size;
+
+ if (btf->types_size == BTF_MAX_NR_TYPES)
+ return -E2BIG;
+
+ expand_by = max(btf->types_size >> 2, 16);
+ new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
+
+ new_types = realloc(btf->types, sizeof(*new_types) * new_size);
+ if (!new_types)
+ return -ENOMEM;
+
+ if (btf->nr_types == 0)
+ new_types[0] = &btf_void;
+
+ btf->types = new_types;
+ btf->types_size = new_size;
+ }
+
+ btf->types[++(btf->nr_types)] = t;
+
+ return 0;
+}
+
+static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
+{
+ const struct btf_header *hdr = btf->hdr;
+ u32 meta_left;
+
+ if (btf->data_size < sizeof(struct btf_header)) {
+ elog("BTF header not found\n");
+ return -EINVAL;
+ }
+
+ if (hdr->magic != BTF_MAGIC) {
+ elog("Invalid BTF magic:%x\n", hdr->magic);
+ return -EINVAL;
+ }
+
+ if (hdr->version != BTF_VERSION) {
+ elog("Unsupported BTF version:%u\n", hdr->version);
+ return -ENOTSUP;
+ }
+
+ if (hdr->flags) {
+ elog("Unsupported BTF flags:%x\n", hdr->flags);
+ return -ENOTSUP;
+ }
+
+ meta_left = btf->data_size - sizeof(*hdr);
+ if (!meta_left) {
+ elog("BTF has no data\n");
+ return -EINVAL;
+ }
+
+ if (meta_left < hdr->type_off) {
+ elog("Invalid BTF type section offset:%u\n", hdr->type_off);
+ return -EINVAL;
+ }
+
+ if (meta_left < hdr->str_off) {
+ elog("Invalid BTF string section offset:%u\n", hdr->str_off);
+ return -EINVAL;
+ }
+
+ if (hdr->type_off >= hdr->str_off) {
+ elog("BTF type section offset >= string section offset. No type?\n");
+ return -EINVAL;
+ }
+
+ if (hdr->type_off & 0x02) {
+ elog("BTF type section is not aligned to 4 bytes\n");
+ return -EINVAL;
+ }
+
+ btf->nohdr_data = btf->hdr + 1;
+
+ return 0;
+}
+
+static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log)
+{
+ const struct btf_header *hdr = btf->hdr;
+ const char *start = btf->nohdr_data + hdr->str_off;
+ const char *end = start + btf->hdr->str_len;
+
+ if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
+ start[0] || end[-1]) {
+ elog("Invalid BTF string section\n");
+ return -EINVAL;
+ }
+
+ btf->strings = start;
+
+ return 0;
+}
+
+static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
+{
+ struct btf_header *hdr = btf->hdr;
+ void *nohdr_data = btf->nohdr_data;
+ void *next_type = nohdr_data + hdr->type_off;
+ void *end_type = nohdr_data + hdr->str_off;
+
+ while (next_type < end_type) {
+ struct btf_type *t = next_type;
+ uint16_t vlen = BTF_INFO_VLEN(t->info);
+ int err;
+
+ next_type += sizeof(*t);
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_INT:
+ next_type += sizeof(int);
+ break;
+ case BTF_KIND_ARRAY:
+ next_type += sizeof(struct btf_array);
+ break;
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ next_type += vlen * sizeof(struct btf_member);
+ break;
+ case BTF_KIND_ENUM:
+ next_type += vlen * sizeof(struct btf_enum);
+ break;
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_PTR:
+ case BTF_KIND_FWD:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ break;
+ case BTF_KIND_FLOAT:
+ case BTF_KIND_FUNC:
+ default:
+ elog("Unsupported BTF_KIND:%u\n",
+ BTF_INFO_KIND(t->info));
+ return -EINVAL;
+ }
+
+ err = btf_add_type(btf, t);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static const struct btf_type *btf_type_by_id(const struct btf *btf,
+ uint32_t type_id)
+{
+ if (type_id > btf->nr_types)
+ return NULL;
+
+ return btf->types[type_id];
+}
+
+static bool btf_type_is_void(const struct btf_type *t)
+{
+ return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+}
+
+static bool btf_type_is_void_or_null(const struct btf_type *t)
+{
+ return !t || btf_type_is_void(t);
+}
+
+static int64_t btf_type_size(const struct btf_type *t)
+{
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_INT:
+ case BTF_KIND_FLOAT:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_ENUM:
+ return t->size;
+ case BTF_KIND_PTR:
+ return sizeof(void *);
+ default:
+ return -EINVAL;
+ };
+}
+
+#define MAX_RESOLVE_DEPTH 32
+
+int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
+{
+ const struct btf_array *array;
+ const struct btf_type *t;
+ uint32_t nelems = 1;
+ int64_t size = -1;
+ int i;
+
+ t = btf_type_by_id(btf, type_id);
+ for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
+ i++) {
+ size = btf_type_size(t);
+ if (size >= 0)
+ break;
+
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ type_id = t->type;
+ break;
+ case BTF_KIND_ARRAY:
+ array = (const struct btf_array *)(t + 1);
+ if (nelems && array->nelems > UINT32_MAX / nelems)
+ return -E2BIG;
+ nelems *= array->nelems;
+ type_id = array->type;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ t = btf_type_by_id(btf, type_id);
+ }
+
+ if (size < 0)
+ return -EINVAL;
+
+ if (nelems && size > UINT32_MAX / nelems)
+ return -E2BIG;
+
+ return nelems * size;
+}
+
+int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
+{
+ uint32_t i;
+
+ if (!strcmp(type_name, "void"))
+ return 0;
+
+ for (i = 1; i <= btf->nr_types; i++) {
+ const struct btf_type *t = btf->types[i];
+ const char *name = btf_name_by_offset(btf, t->name);
+
+ if (name && !strcmp(type_name, name))
+ return i;
+ }
+
+ return -ENOENT;
+}
+
+void btf__free(struct btf *btf)
+{
+ if (!btf)
+ return;
+
+ if (btf->fd != -1)
+ close(btf->fd);
+
+ free(btf->data);
+ free(btf->types);
+ free(btf);
+}
+
+struct btf *btf__new(uint8_t *data, uint32_t size,
+ btf_print_fn_t err_log)
+{
+ uint32_t log_buf_size = 0;
+ char *log_buf = NULL;
+ struct btf *btf;
+ int err;
+
+ btf = calloc(1, sizeof(struct btf));
+ if (!btf)
+ return ERR_PTR(-ENOMEM);
+
+ btf->fd = -1;
+
+ if (err_log) {
+ log_buf = malloc(BPF_LOG_BUF_SIZE);
+ if (!log_buf) {
+ err = -ENOMEM;
+ goto done;
+ }
+ *log_buf = 0;
+ log_buf_size = BPF_LOG_BUF_SIZE;
+ }
+
+ btf->data = malloc(size);
+ if (!btf->data) {
+ err = -ENOMEM;
+ goto done;
+ }
+
+ memcpy(btf->data, data, size);
+ btf->data_size = size;
+
+ btf->fd = bpf_load_btf(btf->data, btf->data_size,
+ log_buf, log_buf_size, false);
+
+ if (btf->fd == -1) {
+ err = -errno;
+ elog("Error loading BTF: %s(%d)\n", strerror(errno), errno);
+ if (log_buf && *log_buf)
+ elog("%s\n", log_buf);
+ goto done;
+ }
+
+ err = btf_parse_hdr(btf, err_log);
+ if (err)
+ goto done;
+
+ err = btf_parse_str_sec(btf, err_log);
+ if (err)
+ goto done;
+
+ err = btf_parse_type_sec(btf, err_log);
+
+done:
+ free(log_buf);
+
+ if (err) {
+ btf__free(btf);
+ return ERR_PTR(err);
+ }
+
+ return btf;
+}
+
+int btf__fd(const struct btf *btf)
+{
+ return btf->fd;
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
new file mode 100644
index 000000000000..74bb344035bb
--- /dev/null
+++ b/tools/lib/bpf/btf.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#ifndef __BPF_BTF_H
+#define __BPF_BTF_H
+
+#include <stdint.h>
+
+#define BTF_ELF_SEC ".BTF"
+
+struct btf;
+
+typedef int (*btf_print_fn_t)(const char *, ...)
+ __attribute__((format(printf, 1, 2)));
+
+void btf__free(struct btf *btf);
+struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log);
+int32_t btf__find_by_name(const struct btf *btf, const char *type_name);
+int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id);
+int btf__fd(const struct btf *btf);
+
+#endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 64a8fc384186..5cc6d20d7448 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -45,6 +45,7 @@
#include "libbpf.h"
#include "bpf.h"
+#include "btf.h"
#ifndef EM_BPF
#define EM_BPF 247
@@ -210,6 +211,8 @@ struct bpf_map {
char *name;
size_t offset;
struct bpf_map_def def;
+ uint32_t btf_key_id;
+ uint32_t btf_value_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
};
@@ -254,6 +257,8 @@ struct bpf_object {
*/
struct list_head list;
+ struct btf *btf;
+
void *priv;
bpf_object_clear_priv_t clear_priv;
@@ -817,7 +822,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
data->d_size);
else if (strcmp(name, "maps") == 0)
obj->efile.maps_shndx = idx;
- else if (sh.sh_type == SHT_SYMTAB) {
+ else if (strcmp(name, BTF_ELF_SEC) == 0) {
+ obj->btf = btf__new(data->d_buf, data->d_size,
+ __pr_debug);
+ if (IS_ERR(obj->btf)) {
+ pr_debug("Error loading ELF section %s: %ld. Ignored and continue.\n",
+ BTF_ELF_SEC, PTR_ERR(obj->btf));
+ obj->btf = NULL;
+ }
+ } else if (sh.sh_type == SHT_SYMTAB) {
if (obj->efile.symbols) {
pr_warning("bpf: multiple SYMTAB in %s\n",
obj->path);
@@ -994,33 +1007,126 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
return 0;
}
+static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
+{
+ struct bpf_map_def *def = &map->def;
+ const size_t max_name = 256;
+ int64_t key_size, value_size;
+ int32_t key_id, value_id;
+ char name[max_name];
+
+ /* Find key type by name from BTF */
+ if (snprintf(name, max_name, "%s_key", map->name) == max_name) {
+ pr_warning("map:%s length of BTF key_type:%s_key is too long\n",
+ map->name, map->name);
+ return -EINVAL;
+ }
+
+ key_id = btf__find_by_name(btf, name);
+ if (key_id < 0) {
+ pr_debug("map:%s key_type:%s cannot be found in BTF\n",
+ map->name, name);
+ return key_id;
+ }
+
+ key_size = btf__resolve_size(btf, key_id);
+ if (key_size < 0) {
+ pr_warning("map:%s key_type:%s cannot get the BTF type_size\n",
+ map->name, name);
+ return key_size;
+ }
+
+ if (def->key_size != key_size) {
+ pr_warning("map:%s key_type:%s has BTF type_size:%ld != key_size:%u\n",
+ map->name, name, key_size, def->key_size);
+ return -EINVAL;
+ }
+
+ /* Find value type from BTF */
+ if (snprintf(name, max_name, "%s_value", map->name) == max_name) {
+ pr_warning("map:%s length of BTF value_type:%s_value is too long\n",
+ map->name, map->name);
+ return -EINVAL;
+ }
+
+ value_id = btf__find_by_name(btf, name);
+ if (value_id < 0) {
+ pr_debug("map:%s value_type:%s cannot be found in BTF\n",
+ map->name, name);
+ return value_id;
+ }
+
+ value_size = btf__resolve_size(btf, value_id);
+ if (value_size < 0) {
+ pr_warning("map:%s value_type:%s cannot get the BTF type_size\n",
+ map->name, name);
+ return value_size;
+ }
+
+ if (def->value_size != value_size) {
+ pr_warning("map:%s value_type:%s has BTF type_size:%ld != value_size:%u\n",
+ map->name, name, value_size, def->value_size);
+ return -EINVAL;
+ }
+
+ map->btf_key_id = key_id;
+ map->btf_value_id = value_id;
+
+ return 0;
+}
+
static int
bpf_object__create_maps(struct bpf_object *obj)
{
+ struct bpf_create_map_attr create_attr = {};
unsigned int i;
+ int err;
for (i = 0; i < obj->nr_maps; i++) {
- struct bpf_map_def *def = &obj->maps[i].def;
- int *pfd = &obj->maps[i].fd;
-
- *pfd = bpf_create_map_name(def->type,
- obj->maps[i].name,
- def->key_size,
- def->value_size,
- def->max_entries,
- def->map_flags);
+ struct bpf_map *map = &obj->maps[i];
+ struct bpf_map_def *def = &map->def;
+ int *pfd = &map->fd;
+
+ create_attr.name = map->name;
+ create_attr.map_type = def->type;
+ create_attr.map_flags = def->map_flags;
+ create_attr.key_size = def->key_size;
+ create_attr.value_size = def->value_size;
+ create_attr.max_entries = def->max_entries;
+ create_attr.btf_fd = 0;
+ create_attr.btf_key_id = 0;
+ create_attr.btf_value_id = 0;
+
+ if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
+ create_attr.btf_fd = btf__fd(obj->btf);
+ create_attr.btf_key_id = map->btf_key_id;
+ create_attr.btf_value_id = map->btf_value_id;
+ }
+
+ *pfd = bpf_create_map_xattr(&create_attr);
+ if (*pfd < 0 && create_attr.btf_key_id) {
+ pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
+ map->name, strerror(errno), errno);
+ create_attr.btf_fd = 0;
+ create_attr.btf_key_id = 0;
+ create_attr.btf_value_id = 0;
+ map->btf_key_id = 0;
+ map->btf_value_id = 0;
+ *pfd = bpf_create_map_xattr(&create_attr);
+ }
+
if (*pfd < 0) {
size_t j;
- int err = *pfd;
+ err = *pfd;
pr_warning("failed to create map (name: '%s'): %s\n",
- obj->maps[i].name,
+ map->name,
strerror(errno));
for (j = 0; j < i; j++)
zclose(obj->maps[j].fd);
return err;
}
- pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd);
+ pr_debug("create map %s: fd=%d\n", map->name, *pfd);
}
return 0;
@@ -1628,6 +1734,7 @@ void bpf_object__close(struct bpf_object *obj)
bpf_object__elf_finish(obj);
bpf_object__unload(obj);
+ btf__free(obj->btf);
for (i = 0; i < obj->nr_maps; i++) {
zfree(&obj->maps[i].name);
@@ -1679,6 +1786,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj)
return obj ? obj->kern_version : 0;
}
+int bpf_object__btf_fd(const struct bpf_object *obj)
+{
+ return obj->btf ? btf__fd(obj->btf) : -1;
+}
+
int bpf_object__set_priv(struct bpf_object *obj, void *priv,
bpf_object_clear_priv_t clear_priv)
{
@@ -1895,6 +2007,16 @@ const char *bpf_map__name(struct bpf_map *map)
return map ? map->name : NULL;
}
+uint32_t bpf_map__btf_key_id(const struct bpf_map *map)
+{
+ return map ? map->btf_key_id : 0;
+}
+
+uint32_t bpf_map__btf_value_id(const struct bpf_map *map)
+{
+ return map ? map->btf_value_id : 0;
+}
+
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv)
{
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f85906533cdd..6f5364469c97 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -78,6 +78,7 @@ int bpf_object__load(struct bpf_object *obj);
int bpf_object__unload(struct bpf_object *obj);
const char *bpf_object__name(struct bpf_object *obj);
unsigned int bpf_object__kversion(struct bpf_object *obj);
+int bpf_object__btf_fd(const struct bpf_object *obj);
struct bpf_object *bpf_object__next(struct bpf_object *prev);
#define bpf_object__for_each_safe(pos, tmp) \
@@ -239,6 +240,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
int bpf_map__fd(struct bpf_map *map);
const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
const char *bpf_map__name(struct bpf_map *map);
+uint32_t bpf_map__btf_key_id(const struct bpf_map *map);
+uint32_t bpf_map__btf_value_id(const struct bpf_map *map);
typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
--
2.9.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox