* [PATCH 4.4 stable 01/10] netfilter: ipv6: nf_defrag: avoid/free clone operations
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 02/10] netfilter: ipv6: avoid nf_iterate recursion Georg Kohmann
` (9 subsequent siblings)
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev; +Cc: Georg Kohmann, Joe Stringer, Florian Westphal, Pablo Neira Ayuso
commit 029f7f3b8701 ("netfilter: ipv6: nf_defrag: avoid/free clone
operations")
Author: Florian Westphal <fw@strlen.de>
Date: Wed Nov 18 23:32:39 2015 +0100
commit 6aafeef03b9d9ecf
("netfilter: push reasm skb through instead of original frag skbs")
changed ipv6 defrag to not use the original skbs anymore.
So rather than keeping the original skbs around just to discard them
afterwards just use the original skbs directly for the fraglist of
the newly assembled skb and remove the extra clone/free operations.
The skb that completes the fragment queue is morphed into a the
reassembled one instead, just like ipv4 defrag.
openvswitch doesn't need any additional skb_morph magic anymore to deal
with this situation so just remove that.
A followup patch can then also remove the NF_HOOK (re)invocation in
the ipv6 netfilter defrag hook.
Cc: Joe Stringer <joestringer@nicira.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/ipv6/nf_defrag_ipv6.h | 1 -
net/ipv6/netfilter/nf_conntrack_reasm.c | 106 +++++++++++-----------------
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 6 --
net/openvswitch/conntrack.c | 14 ----
4 files changed, 40 insertions(+), 87 deletions(-)
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index fb7da5b..fcd20cf 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -6,7 +6,6 @@ void nf_defrag_ipv6_enable(void);
int nf_ct_frag6_init(void);
void nf_ct_frag6_cleanup(void);
struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user);
-void nf_ct_frag6_consume_orig(struct sk_buff *skb);
struct inet_frags_ctl;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 664c84e..58dd6f6 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -56,7 +56,6 @@ struct nf_ct_frag6_skb_cb
{
struct inet6_skb_parm h;
int offset;
- struct sk_buff *orig;
};
#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb))
@@ -151,12 +150,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
-static void nf_skb_free(struct sk_buff *skb)
-{
- if (NFCT_FRAG6_CB(skb)->orig)
- kfree_skb(NFCT_FRAG6_CB(skb)->orig);
-}
-
static void nf_ct_frag6_expire(unsigned long data)
{
struct frag_queue *fq;
@@ -350,9 +343,9 @@ err:
* the last and the first frames arrived and all the bits are here.
*/
static struct sk_buff *
-nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
+nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev)
{
- struct sk_buff *fp, *op, *head = fq->q.fragments;
+ struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
u8 ecn;
@@ -403,10 +396,38 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
clone->csum = 0;
clone->ip_summed = head->ip_summed;
- NFCT_FRAG6_CB(clone)->orig = NULL;
add_frag_mem_limit(fq->q.net, clone->truesize);
}
+ /* morph head into last received skb: prev.
+ *
+ * This allows callers of ipv6 conntrack defrag to continue
+ * to use the last skb(frag) passed into the reasm engine.
+ * The last skb frag 'silently' turns into the full reassembled skb.
+ *
+ * Since prev is also part of q->fragments we have to clone it first.
+ */
+ if (head != prev) {
+ struct sk_buff *iter;
+
+ fp = skb_clone(prev, GFP_ATOMIC);
+ if (!fp)
+ goto out_oom;
+
+ fp->next = prev->next;
+ skb_queue_walk(head, iter) {
+ if (iter->next != prev)
+ continue;
+ iter->next = fp;
+ break;
+ }
+
+ skb_morph(prev, head);
+ prev->next = head->next;
+ consume_skb(head);
+ head = prev;
+ }
+
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0];
@@ -449,21 +470,6 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
- /* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */
- fp = skb_shinfo(head)->frag_list;
- if (fp && NFCT_FRAG6_CB(fp)->orig == NULL)
- /* at above code, head skb is divided into two skbs. */
- fp = fp->next;
-
- op = NFCT_FRAG6_CB(head)->orig;
- for (; fp; fp = fp->next) {
- struct sk_buff *orig = NFCT_FRAG6_CB(fp)->orig;
-
- op->next = orig;
- op = orig;
- NFCT_FRAG6_CB(fp)->orig = NULL;
- }
-
return head;
out_oversize:
@@ -541,7 +547,6 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
- struct sk_buff *clone;
struct net_device *dev = skb->dev;
struct frag_hdr *fhdr;
struct frag_queue *fq;
@@ -559,22 +564,12 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
return skb;
- clone = skb_clone(skb, GFP_ATOMIC);
- if (clone == NULL) {
- pr_debug("Can't clone skb\n");
+ if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
return skb;
- }
- NFCT_FRAG6_CB(clone)->orig = skb;
-
- if (!pskb_may_pull(clone, fhoff + sizeof(*fhdr))) {
- pr_debug("message is too short.\n");
- goto ret_orig;
- }
-
- skb_set_transport_header(clone, fhoff);
- hdr = ipv6_hdr(clone);
- fhdr = (struct frag_hdr *)skb_transport_header(clone);
+ skb_set_transport_header(skb, fhoff);
+ hdr = ipv6_hdr(skb);
+ fhdr = (struct frag_hdr *)skb_transport_header(skb);
if (clone->len - skb_network_offset(clone) < IPV6_MIN_MTU &&
fhdr->frag_off & htons(IP6_MF))
@@ -583,23 +578,20 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
skb_orphan(skb);
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
- if (fq == NULL) {
- pr_debug("Can't find and can't create new queue\n");
- goto ret_orig;
- }
-
+ if (fq == NULL)
+ return skb;
spin_lock_bh(&fq->q.lock);
- if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) {
+ if (nf_ct_frag6_queue(fq, skb, fhdr, nhoff) < 0) {
spin_unlock_bh(&fq->q.lock);
pr_debug("Can't insert skb to queue\n");
inet_frag_put(&fq->q);
- goto ret_orig;
+ return skb;
}
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
- ret_skb = nf_ct_frag6_reasm(fq, dev);
+ ret_skb = nf_ct_frag6_reasm(fq, skb, dev);
if (ret_skb == NULL)
pr_debug("Can't reassemble fragmented packets\n");
}
@@ -607,26 +599,9 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
inet_frag_put(&fq->q);
return ret_skb;
-
-ret_orig:
- kfree_skb(clone);
- return skb;
}
EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
-void nf_ct_frag6_consume_orig(struct sk_buff *skb)
-{
- struct sk_buff *s, *s2;
-
- for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
- s2 = s->next;
- s->next = NULL;
- consume_skb(s);
- s = s2;
- }
-}
-EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_orig);
-
static int nf_ct_net_init(struct net *net)
{
int res;
@@ -662,7 +637,6 @@ int nf_ct_frag6_init(void)
nf_frags.constructor = ip6_frag_init;
nf_frags.destructor = NULL;
- nf_frags.skb_free = nf_skb_free;
nf_frags.qsize = sizeof(struct frag_queue);
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index 4fdbed5e..fb96b10 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -69,12 +69,6 @@ static unsigned int ipv6_defrag(void *priv,
if (reasm == NULL)
return NF_STOLEN;
- /* error occurred or not fragmented */
- if (reasm == skb)
- return NF_ACCEPT;
-
- nf_ct_frag6_consume_orig(reasm);
-
NF_HOOK_THRESH(NFPROTO_IPV6, state->hook, state->net, state->sk, reasm,
state->in, state->out,
state->okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 1829adb..6f5cbb7 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -326,21 +326,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
if (!reasm)
return -EINPROGRESS;
- if (skb == reasm) {
- kfree_skb(skb);
- return -EINVAL;
- }
-
- /* Don't free 'skb' even though it is one of the original
- * fragments, as we're going to morph it into the head.
- */
- skb_get(skb);
- nf_ct_frag6_consume_orig(reasm);
-
key->ip.proto = ipv6_hdr(reasm)->nexthdr;
- skb_morph(skb, reasm);
- skb->next = reasm->next;
- consume_skb(reasm);
ovs_cb.mru = IP6CB(skb)->frag_max_size;
#endif
} else {
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 02/10] netfilter: ipv6: avoid nf_iterate recursion
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 01/10] netfilter: ipv6: nf_defrag: avoid/free clone operations Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 03/10] ipv6: do not increment mac header when it's unset Georg Kohmann
` (8 subsequent siblings)
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev; +Cc: Georg Kohmann, Florian Westphal, Pablo Neira Ayuso
commit daaa7d647f81 ("netfilter: ipv6: avoid nf_iterate recursion")
Author: Florian Westphal <fw@strlen.de>
Date: Wed Nov 18 23:32:40 2015 +0100
The previous patch changed nf_ct_frag6_gather() to morph reassembled skb
with the previous one.
This means that the return value is always NULL or the skb argument.
So change it to an err value.
Instead of invoking NF_HOOK recursively with threshold to skip already-called hooks
we can now just return NF_ACCEPT to move on to the next hook except for
-EINPROGRESS (which means skb has been queued for reassembly), in which case we
return NF_STOLEN.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/ipv6/nf_defrag_ipv6.h | 2 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 71 +++++++++++++----------------
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 14 ++----
net/openvswitch/conntrack.c | 11 ++---
4 files changed, 42 insertions(+), 56 deletions(-)
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index fcd20cf..ddf162f 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -5,7 +5,7 @@ void nf_defrag_ipv6_enable(void);
int nf_ct_frag6_init(void);
void nf_ct_frag6_cleanup(void);
-struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user);
+int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user);
struct inet_frags_ctl;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 58dd6f6..0a85de9 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -335,14 +335,15 @@ err:
/*
* Check if this packet is complete.
- * Returns NULL on failure by any reason, and pointer
- * to current nexthdr field in reassembled frame.
*
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
+ *
+ * returns true if *prev skb has been transformed into the reassembled
+ * skb, false otherwise.
*/
-static struct sk_buff *
+static bool
nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev)
{
struct sk_buff *fp, *head = fq->q.fragments;
@@ -356,22 +357,21 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
- goto out_fail;
+ return false;
/* Unfragmented part is taken from the first segment. */
payload_len = ((head->data - skb_network_header(head)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN) {
- pr_debug("payload len is too large.\n");
- goto out_oversize;
+ net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n",
+ payload_len);
+ return false;
}
/* Head of list must not be cloned. */
- if (skb_unclone(head, GFP_ATOMIC)) {
- pr_debug("skb is cloned but can't expand head");
- goto out_oom;
- }
+ if (skb_unclone(head, GFP_ATOMIC))
+ return false;
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
@@ -382,7 +382,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
clone = alloc_skb(0, GFP_ATOMIC);
if (clone == NULL)
- goto out_oom;
+ return false;
clone->next = head->next;
head->next = clone;
@@ -412,7 +412,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
fp = skb_clone(prev, GFP_ATOMIC);
if (!fp)
- goto out_oom;
+ return false;
fp->next = prev->next;
skb_queue_walk(head, iter) {
@@ -470,16 +470,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
- return head;
-
-out_oversize:
- net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n",
- payload_len);
- goto out_fail;
-out_oom:
- net_dbg_ratelimited("nf_ct_frag6_reasm: no memory for reassembly\n");
-out_fail:
- return NULL;
+ return true;
}
/*
@@ -545,27 +536,26 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
return 0;
}
-struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
+int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
struct net_device *dev = skb->dev;
+ int fhoff, nhoff, ret;
struct frag_hdr *fhdr;
struct frag_queue *fq;
struct ipv6hdr *hdr;
- int fhoff, nhoff;
u8 prevhdr;
- struct sk_buff *ret_skb = NULL;
/* Jumbo payload inhibits frag. header */
if (ipv6_hdr(skb)->payload_len == 0) {
pr_debug("payload len = 0\n");
- return skb;
+ return -EINVAL;
}
if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
- return skb;
+ return -EINVAL;
if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
- return skb;
+ return -ENOMEM;
skb_set_transport_header(skb, fhoff);
hdr = ipv6_hdr(skb);
@@ -579,26 +569,27 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL)
- return skb;
+ return -ENOMEM;
spin_lock_bh(&fq->q.lock);
if (nf_ct_frag6_queue(fq, skb, fhdr, nhoff) < 0) {
- spin_unlock_bh(&fq->q.lock);
- pr_debug("Can't insert skb to queue\n");
- inet_frag_put(&fq->q);
- return skb;
+ ret = -EINVAL;
+ goto out_unlock;
}
+ /* after queue has assumed skb ownership, only 0 or -EINPROGRESS
+ * must be returned.
+ */
+ ret = -EINPROGRESS;
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- fq->q.meat == fq->q.len) {
- ret_skb = nf_ct_frag6_reasm(fq, skb, dev);
- if (ret_skb == NULL)
- pr_debug("Can't reassemble fragmented packets\n");
- }
- spin_unlock_bh(&fq->q.lock);
+ fq->q.meat == fq->q.len &&
+ nf_ct_frag6_reasm(fq, skb, dev))
+ ret = 0;
+out_unlock:
+ spin_unlock_bh(&fq->q.lock);
inet_frag_put(&fq->q);
- return ret_skb;
+ return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index fb96b10..f7aab5a 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -55,7 +55,7 @@ static unsigned int ipv6_defrag(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- struct sk_buff *reasm;
+ int err;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* Previously seen (loopback)? */
@@ -63,17 +63,13 @@ static unsigned int ipv6_defrag(void *priv,
return NF_ACCEPT;
#endif
- reasm = nf_ct_frag6_gather(state->net, skb,
- nf_ct6_defrag_user(state->hook, skb));
+ err = nf_ct_frag6_gather(state->net, skb,
+ nf_ct6_defrag_user(state->hook, skb));
/* queued */
- if (reasm == NULL)
+ if (err == -EINPROGRESS)
return NF_STOLEN;
- NF_HOOK_THRESH(NFPROTO_IPV6, state->hook, state->net, state->sk, reasm,
- state->in, state->out,
- state->okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
-
- return NF_STOLEN;
+ return NF_ACCEPT;
}
static struct nf_hook_ops ipv6_defrag_ops[] = {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 6f5cbb7..3ed0331 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -305,10 +305,10 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
u16 zone, struct sk_buff *skb)
{
struct ovs_skb_cb ovs_cb = *OVS_CB(skb);
+ int err;
if (key->eth.type == htons(ETH_P_IP)) {
enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
- int err;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
err = ip_defrag(net, skb, user);
@@ -319,14 +319,13 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
} else if (key->eth.type == htons(ETH_P_IPV6)) {
enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
- struct sk_buff *reasm;
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
- reasm = nf_ct_frag6_gather(net, skb, user);
- if (!reasm)
- return -EINPROGRESS;
+ err = nf_ct_frag6_gather(net, skb, user);
+ if (err)
+ return err;
- key->ip.proto = ipv6_hdr(reasm)->nexthdr;
+ key->ip.proto = ipv6_hdr(skb)->nexthdr;
ovs_cb.mru = IP6CB(skb)->frag_max_size;
#endif
} else {
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 03/10] ipv6: do not increment mac header when it's unset
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 01/10] netfilter: ipv6: nf_defrag: avoid/free clone operations Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 02/10] netfilter: ipv6: avoid nf_iterate recursion Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 04/10] netfilter: ipv6: nf_defrag: Pass on packets to stack per RFC2460 Georg Kohmann
` (7 subsequent siblings)
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev; +Cc: Georg Kohmann, Jason A . Donenfeld, David S . Miller
commit b678aa578c9e ("ipv6: do not increment mac header when it's unset")
Author: Jason A. Donenfeld <Jason@zx2c4.com>
Date: Fri Oct 21 18:28:25 2016 +0900
Otherwise we'll overflow the integer. This occurs when layer 3 tunneled
packets are handed off to the IPv6 layer.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/reassembly.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index ec917f5..2842ccf 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -418,7 +418,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
memmove(head->head + sizeof(struct frag_hdr), head->head,
(head->data - head->head) - sizeof(struct frag_hdr));
- head->mac_header += sizeof(struct frag_hdr);
+ if (skb_mac_header_was_set(head))
+ head->mac_header += sizeof(struct frag_hdr);
head->network_header += sizeof(struct frag_hdr);
skb_reset_transport_header(head);
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 04/10] netfilter: ipv6: nf_defrag: Pass on packets to stack per RFC2460
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (2 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 03/10] ipv6: do not increment mac header when it's unset Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 12:04 ` Greg Kroah-Hartman
2019-10-08 11:23 ` [PATCH 4.4 stable 05/10] netfilter: ipv6: nf_defrag: fix NULL deref panic Georg Kohmann
` (6 subsequent siblings)
10 siblings, 1 reply; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev
Cc: Georg Kohmann, Subash Abhinov Kasiviswanathan, Pablo Neira Ayuso,
Sasha Levin, Greg Kroah-Hartman
commit d65bc9545fd3 ("netfilter: ipv6: nf_defrag: Pass on packets to stack
per RFC2460")
Author: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Fri Jan 12 17:36:27 2018 -0700
[ Upstream commit 83f1999caeb14e15df205e80d210699951733287 ]
ipv6_defrag pulls network headers before fragment header. In case of
an error, the netfilter layer is currently dropping these packets.
This results in failure of some IPv6 standards tests which passed on
older kernels due to the netfilter framework using cloning.
The test case run here is a check for ICMPv6 error message replies
when some invalid IPv6 fragments are sent. This specific test case is
listed in https://www.ipv6ready.org/docs/Core_Conformance_Latest.pdf
in the Extension Header Processing Order section.
A packet with unrecognized option Type 11 is sent and the test expects
an ICMP error in line with RFC2460 section 4.2 -
11 - discard the packet and, only if the packet's Destination
Address was not a multicast address, send an ICMP Parameter
Problem, Code 2, message to the packet's Source Address,
pointing to the unrecognized Option Type.
Since netfilter layer now drops all invalid IPv6 frag packets, we no
longer see the ICMP error message and fail the test case.
To fix this, save the transport header. If defrag is unable to process
the packet due to RFC2460, restore the transport header and allow packet
to be processed by stack. There is no change for other packet
processing paths.
Tested by confirming that stack sends an ICMP error when it receives
these packets. Also tested that fragmented ICMP pings succeed.
v1->v2: Instead of cloning always, save the transport_header and
restore it in case of this specific error. Update the title and
commit message accordingly.
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv6/netfilter/nf_conntrack_reasm.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 0a85de9..394aeb1 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -203,7 +203,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
if ((unsigned int)end > IPV6_MAXPLEN) {
pr_debug("offset is too large.\n");
- return -1;
+ return -EINVAL;
}
ecn = ip6_frag_ecn(ipv6_hdr(skb));
@@ -236,7 +236,7 @@ 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");
- return -1;
+ return -EPROTO;
}
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
@@ -330,7 +330,7 @@ found:
discard_fq:
inet_frag_kill(&fq->q);
err:
- return -1;
+ return -EINVAL;
}
/*
@@ -538,6 +538,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
+ u16 savethdr = skb->transport_header;
struct net_device *dev = skb->dev;
int fhoff, nhoff, ret;
struct frag_hdr *fhdr;
@@ -572,8 +573,12 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
return -ENOMEM;
spin_lock_bh(&fq->q.lock);
- if (nf_ct_frag6_queue(fq, skb, fhdr, nhoff) < 0) {
- ret = -EINVAL;
+ ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff);
+ if (ret < 0) {
+ if (ret == -EPROTO) {
+ skb->transport_header = savethdr;
+ ret = 0;
+ }
goto out_unlock;
}
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 05/10] netfilter: ipv6: nf_defrag: fix NULL deref panic
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (3 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 04/10] netfilter: ipv6: nf_defrag: Pass on packets to stack per RFC2460 Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 06/10] ipv6: frags: fix a lockdep false positive Georg Kohmann
` (5 subsequent siblings)
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev; +Cc: Georg Kohmann, Florian Westphal, Pablo Neira Ayuso
commit e97ac12859db ("netfilter: ipv6: nf_defrag: fix NULL deref panic")
Author: Florian Westphal <fw@strlen.de>
Date: Tue Dec 8 23:35:19 2015 +0100
Valdis reports NULL deref in nf_ct_frag6_gather.
Problem is bogus use of skb_queue_walk() -- we miss first skb in the list
since we start with head->next instead of head.
In case the element we're looking for was head->next we won't find
a result and then trip over NULL iter.
(defrag uses plain NULL-terminated list rather than one terminated by
head-of-list-pointer, which is what skb_queue_walk expects).
Fixes: 029f7f3b8701cc7a ("netfilter: ipv6: nf_defrag: avoid/free clone operations")
Reported-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/ipv6/netfilter/nf_conntrack_reasm.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 394aeb1..5640e041 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -415,11 +415,14 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
return false;
fp->next = prev->next;
- skb_queue_walk(head, iter) {
- if (iter->next != prev)
- continue;
- iter->next = fp;
- break;
+
+ iter = head;
+ while (iter) {
+ if (iter->next == prev) {
+ iter->next = fp;
+ break;
+ }
+ iter = iter->next;
}
skb_morph(prev, head);
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 06/10] ipv6: frags: fix a lockdep false positive
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (4 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 05/10] netfilter: ipv6: nf_defrag: fix NULL deref panic Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 07/10] net: IP defrag: encapsulate rbtree defrag code into callable functions Georg Kohmann
` (4 subsequent siblings)
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev; +Cc: Georg Kohmann, Eric Dumazet, David S . Miller
commit 415787d7799f ("ipv6: frags: fix a lockdep false positive")
From: Eric Dumazet <edumazet@google.com>
lockdep does not know that the locks used by IPv4 defrag
and IPv6 reassembly units are of different classes.
It complains because of following chains :
1) sch_direct_xmit() (lock txq->_xmit_lock)
dev_hard_start_xmit()
xmit_one()
dev_queue_xmit_nit()
packet_rcv_fanout()
ip_check_defrag()
ip_defrag()
spin_lock() (lock frag queue spinlock)
2) ip6_input_finish()
ipv6_frag_rcv() (lock frag queue spinlock)
ip6_frag_queue()
icmpv6_param_prob() (lock txq->_xmit_lock at some point)
We could add lockdep annotations, but we also can make sure IPv6
calls icmpv6_param_prob() only after the release of the frag queue spinlock,
since this naturally makes frag queue spinlock a leaf in lock hierarchy.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/reassembly.c | 23 ++++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2842ccf..c708fc5 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -169,7 +169,8 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
}
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
- struct frag_hdr *fhdr, int nhoff)
+ struct frag_hdr *fhdr, int nhoff,
+ u32 *prob_offset)
{
struct sk_buff *prev, *next;
struct net_device *dev;
@@ -185,11 +186,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
if ((unsigned int)end > IPV6_MAXPLEN) {
- IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
- ((u8 *)&fhdr->frag_off -
- skb_network_header(skb)));
+ *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
return -1;
}
@@ -220,10 +217,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
/* RFC2460 says always send parameter problem in
* this case. -DaveM
*/
- IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
- offsetof(struct ipv6hdr, payload_len));
+ *prob_offset = offsetof(struct ipv6hdr, payload_len);
return -1;
}
if (end > fq->q.len) {
@@ -524,15 +518,22 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
+ u32 prob_offset = 0;
int ret;
spin_lock(&fq->q.lock);
fq->iif = iif;
- ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
+ ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff,
+ &prob_offset);
spin_unlock(&fq->q.lock);
inet_frag_put(&fq->q);
+ if (prob_offset) {
+ IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset);
+ }
return ret;
}
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 07/10] net: IP defrag: encapsulate rbtree defrag code into callable functions
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (5 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 06/10] ipv6: frags: fix a lockdep false positive Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 08/10] ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module Georg Kohmann
` (3 subsequent siblings)
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev
Cc: Georg Kohmann, Peter Oskolkov, Eric Dumazet, Florian Westphal,
Tom Herbert, David S . Miller
commit c23f35d19db3 ("net: IP defrag: encapsulate rbtree defrag code into
callable functions")
This is a refactoring patch: without changing runtime behavior,
it moves rbtree-related code from IPv4-specific files/functions
into .h/.c defrag files shared with IPv6 defragmentation code.
Signed-off-by: Peter Oskolkov <posk@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/inet_frag.h | 16 ++-
net/ipv4/inet_fragment.c | 293 ++++++++++++++++++++++++++++++++++++++++++++++
net/ipv4/ip_fragment.c | 295 ++++++-----------------------------------------
3 files changed, 342 insertions(+), 262 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 6260ec1..7c8b063 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -75,8 +75,8 @@ struct inet_frag_queue {
struct timer_list timer;
spinlock_t lock;
atomic_t refcnt;
- struct sk_buff *fragments; /* Used in IPv6. */
- struct rb_root rb_fragments; /* Used in IPv4. */
+ struct sk_buff *fragments; /* used in 6lopwpan IPv6. */
+ struct rb_root rb_fragments; /* Used in IPv4/IPv6. */
struct sk_buff *fragments_tail;
struct sk_buff *last_run_head;
ktime_t stamp;
@@ -152,4 +152,16 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
extern const u8 ip_frag_ecn_table[16];
+/* Return values of inet_frag_queue_insert() */
+#define IPFRAG_OK 0
+#define IPFRAG_DUP 1
+#define IPFRAG_OVERLAP 2
+int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
+ int offset, int end);
+void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
+ struct sk_buff *parent);
+void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
+ void *reasm_data);
+struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q);
+
#endif
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c03e5f5..5c167ef 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -24,6 +24,62 @@
#include <net/sock.h>
#include <net/inet_frag.h>
#include <net/inet_ecn.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+
+/* Use skb->cb to track consecutive/adjacent fragments coming at
+ * the end of the queue. Nodes in the rb-tree queue will
+ * contain "runs" of one or more adjacent fragments.
+ *
+ * Invariants:
+ * - next_frag is NULL at the tail of a "run";
+ * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
+ */
+struct ipfrag_skb_cb {
+ union {
+ struct inet_skb_parm h4;
+ struct inet6_skb_parm h6;
+ };
+ struct sk_buff *next_frag;
+ int frag_run_len;
+};
+
+#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
+
+static void fragcb_clear(struct sk_buff *skb)
+{
+ RB_CLEAR_NODE(&skb->rbnode);
+ FRAG_CB(skb)->next_frag = NULL;
+ FRAG_CB(skb)->frag_run_len = skb->len;
+}
+
+/* Append skb to the last "run". */
+static void fragrun_append_to_last(struct inet_frag_queue *q,
+ struct sk_buff *skb)
+{
+ fragcb_clear(skb);
+
+ FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
+ FRAG_CB(q->fragments_tail)->next_frag = skb;
+ q->fragments_tail = skb;
+}
+
+/* Create a new "run" with the skb. */
+static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb)
+{
+ BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
+ fragcb_clear(skb);
+
+ if (q->last_run_head)
+ rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
+ &q->last_run_head->rbnode.rb_right);
+ else
+ rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
+ rb_insert_color(&skb->rbnode, &q->rb_fragments);
+
+ q->fragments_tail = skb;
+ q->last_run_head = skb;
+}
/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
* Value : 0xff if frame should be dropped.
@@ -130,6 +186,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head)
kmem_cache_free(f->frags_cachep, q);
}
+unsigned int inet_frag_rbtree_purge(struct rb_root *root)
+{
+ struct rb_node *p = rb_first(root);
+ unsigned int sum = 0;
+
+ while (p) {
+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
+
+ p = rb_next(p);
+ rb_erase(&skb->rbnode, root);
+ while (skb) {
+ struct sk_buff *next = FRAG_CB(skb)->next_frag;
+
+ sum += skb->truesize;
+ kfree_skb(skb);
+ skb = next;
+ }
+ }
+ return sum;
+}
+EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
@@ -231,3 +309,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
return fq;
}
EXPORT_SYMBOL(inet_frag_find);
+
+int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
+ int offset, int end)
+{
+ struct sk_buff *last = q->fragments_tail;
+
+ /* RFC5722, Section 4, amended by Errata ID : 3089
+ * When reassembling an IPv6 datagram, if
+ * one or more its constituent fragments is determined to be an
+ * overlapping fragment, the entire datagram (and any constituent
+ * fragments) MUST be silently discarded.
+ *
+ * Duplicates, however, should be ignored (i.e. skb dropped, but the
+ * queue/fragments kept for later reassembly).
+ */
+ if (!last)
+ fragrun_create(q, skb); /* First fragment. */
+ else if (last->ip_defrag_offset + last->len < end) {
+ /* This is the common case: skb goes to the end. */
+ /* Detect and discard overlaps. */
+ if (offset < last->ip_defrag_offset + last->len)
+ return IPFRAG_OVERLAP;
+ if (offset == last->ip_defrag_offset + last->len)
+ fragrun_append_to_last(q, skb);
+ else
+ fragrun_create(q, skb);
+ } else {
+ /* Binary search. Note that skb can become the first fragment,
+ * but not the last (covered above).
+ */
+ struct rb_node **rbn, *parent;
+
+ rbn = &q->rb_fragments.rb_node;
+ do {
+ struct sk_buff *curr;
+ int curr_run_end;
+
+ parent = *rbn;
+ curr = rb_to_skb(parent);
+ curr_run_end = curr->ip_defrag_offset +
+ FRAG_CB(curr)->frag_run_len;
+ if (end <= curr->ip_defrag_offset)
+ rbn = &parent->rb_left;
+ else if (offset >= curr_run_end)
+ rbn = &parent->rb_right;
+ else if (offset >= curr->ip_defrag_offset &&
+ end <= curr_run_end)
+ return IPFRAG_DUP;
+ else
+ return IPFRAG_OVERLAP;
+ } while (*rbn);
+ /* Here we have parent properly set, and rbn pointing to
+ * one of its NULL left/right children. Insert skb.
+ */
+ fragcb_clear(skb);
+ rb_link_node(&skb->rbnode, parent, rbn);
+ rb_insert_color(&skb->rbnode, &q->rb_fragments);
+ }
+
+ skb->ip_defrag_offset = offset;
+
+ return IPFRAG_OK;
+}
+EXPORT_SYMBOL(inet_frag_queue_insert);
+
+void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
+ struct sk_buff *parent)
+{
+ struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
+ struct sk_buff **nextp;
+ int delta;
+
+ if (head != skb) {
+ fp = skb_clone(skb, GFP_ATOMIC);
+ if (!fp)
+ return NULL;
+ FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
+ if (RB_EMPTY_NODE(&skb->rbnode))
+ FRAG_CB(parent)->next_frag = fp;
+ else
+ rb_replace_node(&skb->rbnode, &fp->rbnode,
+ &q->rb_fragments);
+ if (q->fragments_tail == skb)
+ q->fragments_tail = fp;
+ skb_morph(skb, head);
+ FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
+ rb_replace_node(&head->rbnode, &skb->rbnode,
+ &q->rb_fragments);
+ consume_skb(head);
+ head = skb;
+ }
+ WARN_ON(head->ip_defrag_offset != 0);
+
+ delta = -head->truesize;
+
+ /* Head of list must not be cloned. */
+ if (skb_unclone(head, GFP_ATOMIC))
+ return NULL;
+
+ delta += head->truesize;
+ if (delta)
+ add_frag_mem_limit(q->net, delta);
+
+ /* If the first fragment is fragmented itself, we split
+ * it to two chunks: the first with data and paged part
+ * and the second, holding only fragments.
+ */
+ if (skb_has_frag_list(head)) {
+ struct sk_buff *clone;
+ int i, plen = 0;
+
+ clone = alloc_skb(0, GFP_ATOMIC);
+ if (!clone)
+ return NULL;
+ skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
+ skb_frag_list_init(head);
+ for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
+ plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
+ clone->data_len = head->data_len - plen;
+ clone->len = clone->data_len;
+ head->truesize += clone->truesize;
+ clone->csum = 0;
+ clone->ip_summed = head->ip_summed;
+ add_frag_mem_limit(q->net, clone->truesize);
+ skb_shinfo(head)->frag_list = clone;
+ nextp = &clone->next;
+ } else {
+ nextp = &skb_shinfo(head)->frag_list;
+ }
+
+ return nextp;
+}
+EXPORT_SYMBOL(inet_frag_reasm_prepare);
+
+void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
+ void *reasm_data)
+{
+ struct sk_buff **nextp = (struct sk_buff **)reasm_data;
+ struct rb_node *rbn;
+ struct sk_buff *fp;
+
+ skb_push(head, head->data - skb_network_header(head));
+
+ /* Traverse the tree in order, to build frag_list. */
+ fp = FRAG_CB(head)->next_frag;
+ rbn = rb_next(&head->rbnode);
+ rb_erase(&head->rbnode, &q->rb_fragments);
+ while (rbn || fp) {
+ /* fp points to the next sk_buff in the current run;
+ * rbn points to the next run.
+ */
+ /* Go through the current run. */
+ while (fp) {
+ *nextp = fp;
+ nextp = &fp->next;
+ fp->prev = NULL;
+ memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+ fp->sk = NULL;
+ head->data_len += fp->len;
+ head->len += fp->len;
+ if (head->ip_summed != fp->ip_summed)
+ head->ip_summed = CHECKSUM_NONE;
+ else if (head->ip_summed == CHECKSUM_COMPLETE)
+ head->csum = csum_add(head->csum, fp->csum);
+ head->truesize += fp->truesize;
+ fp = FRAG_CB(fp)->next_frag;
+ }
+ /* Move to the next run. */
+ if (rbn) {
+ struct rb_node *rbnext = rb_next(rbn);
+
+ fp = rb_to_skb(rbn);
+ rb_erase(rbn, &q->rb_fragments);
+ rbn = rbnext;
+ }
+ }
+ sub_frag_mem_limit(q->net, head->truesize);
+
+ *nextp = NULL;
+ head->next = NULL;
+ head->prev = NULL;
+ head->tstamp = q->stamp;
+}
+EXPORT_SYMBOL(inet_frag_reasm_finish);
+
+struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q)
+{
+ struct sk_buff *head;
+
+ if (q->fragments) {
+ head = q->fragments;
+ q->fragments = head->next;
+ } else {
+ struct sk_buff *skb;
+
+ head = skb_rb_first(&q->rb_fragments);
+ if (!head)
+ return NULL;
+ skb = FRAG_CB(head)->next_frag;
+ if (skb)
+ rb_replace_node(&head->rbnode, &skb->rbnode,
+ &q->rb_fragments);
+ else
+ rb_erase(&head->rbnode, &q->rb_fragments);
+ memset(&head->rbnode, 0, sizeof(head->rbnode));
+ barrier();
+ }
+ if (head == q->fragments_tail)
+ q->fragments_tail = NULL;
+
+ sub_frag_mem_limit(q->net, head->truesize);
+
+ return head;
+}
+EXPORT_SYMBOL(inet_frag_pull_head);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9b09a9b..bbd9940 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -58,57 +58,6 @@
static int sysctl_ipfrag_max_dist __read_mostly = 64;
static const char ip_frag_cache_name[] = "ip4-frags";
-/* Use skb->cb to track consecutive/adjacent fragments coming at
- * the end of the queue. Nodes in the rb-tree queue will
- * contain "runs" of one or more adjacent fragments.
- *
- * Invariants:
- * - next_frag is NULL at the tail of a "run";
- * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
- */
-struct ipfrag_skb_cb {
- struct inet_skb_parm h;
- struct sk_buff *next_frag;
- int frag_run_len;
-};
-
-#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
-
-static void ip4_frag_init_run(struct sk_buff *skb)
-{
- BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
-
- FRAG_CB(skb)->next_frag = NULL;
- FRAG_CB(skb)->frag_run_len = skb->len;
-}
-
-/* Append skb to the last "run". */
-static void ip4_frag_append_to_last_run(struct inet_frag_queue *q,
- struct sk_buff *skb)
-{
- RB_CLEAR_NODE(&skb->rbnode);
- FRAG_CB(skb)->next_frag = NULL;
-
- FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
- FRAG_CB(q->fragments_tail)->next_frag = skb;
- q->fragments_tail = skb;
-}
-
-/* Create a new "run" with the skb. */
-static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb)
-{
- if (q->last_run_head)
- rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
- &q->last_run_head->rbnode.rb_right);
- else
- rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
- rb_insert_color(&skb->rbnode, &q->rb_fragments);
-
- ip4_frag_init_run(skb);
- q->fragments_tail = skb;
- q->last_run_head = skb;
-}
-
/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
struct inet_frag_queue q;
@@ -212,27 +161,9 @@ static void ip_expire(unsigned long arg)
* pull the head out of the tree in order to be able to
* deal with head->dev.
*/
- if (qp->q.fragments) {
- head = qp->q.fragments;
- qp->q.fragments = head->next;
- } else {
- head = skb_rb_first(&qp->q.rb_fragments);
- if (!head)
- goto out;
- if (FRAG_CB(head)->next_frag)
- rb_replace_node(&head->rbnode,
- &FRAG_CB(head)->next_frag->rbnode,
- &qp->q.rb_fragments);
- else
- rb_erase(&head->rbnode, &qp->q.rb_fragments);
- memset(&head->rbnode, 0, sizeof(head->rbnode));
- barrier();
- }
- if (head == qp->q.fragments_tail)
- qp->q.fragments_tail = NULL;
-
- sub_frag_mem_limit(qp->q.net, head->truesize);
-
+ head = inet_frag_pull_head(&qp->q);
+ if (!head)
+ goto out;
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out;
@@ -345,12 +276,10 @@ static int ip_frag_reinit(struct ipq *qp)
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
- struct rb_node **rbn, *parent;
- struct sk_buff *skb1, *prev_tail;
- int ihl, end, skb1_run_end;
+ int ihl, end, flags, offset;
+ struct sk_buff *prev_tail;
struct net_device *dev;
unsigned int fragsize;
- int flags, offset;
int err = -ENOENT;
u8 ecn;
@@ -382,7 +311,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
*/
if (end < qp->q.len ||
((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
- goto err;
+ goto discard_qp;
qp->q.flags |= INET_FRAG_LAST_IN;
qp->q.len = end;
} else {
@@ -394,82 +323,33 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
if (end > qp->q.len) {
/* Some bits beyond end -> corruption. */
if (qp->q.flags & INET_FRAG_LAST_IN)
- goto err;
+ goto discard_qp;
qp->q.len = end;
}
}
if (end == offset)
- goto err;
+ goto discard_qp;
err = -ENOMEM;
if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
- goto err;
+ goto discard_qp;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
- goto err;
+ goto discard_qp;
/* Note : skb->rbnode and skb->dev share the same location. */
dev = skb->dev;
/* Makes sure compiler wont do silly aliasing games */
barrier();
- /* RFC5722, Section 4, amended by Errata ID : 3089
- * When reassembling an IPv6 datagram, if
- * one or more its constituent fragments is determined to be an
- * overlapping fragment, the entire datagram (and any constituent
- * fragments) MUST be silently discarded.
- *
- * We do the same here for IPv4 (and increment an snmp counter) but
- * we do not want to drop the whole queue in response to a duplicate
- * fragment.
- */
-
- err = -EINVAL;
- /* Find out where to put this fragment. */
prev_tail = qp->q.fragments_tail;
- if (!prev_tail)
- ip4_frag_create_run(&qp->q, skb); /* First fragment. */
- else if (prev_tail->ip_defrag_offset + prev_tail->len < end) {
- /* This is the common case: skb goes to the end. */
- /* Detect and discard overlaps. */
- if (offset < prev_tail->ip_defrag_offset + prev_tail->len)
- goto discard_qp;
- if (offset == prev_tail->ip_defrag_offset + prev_tail->len)
- ip4_frag_append_to_last_run(&qp->q, skb);
- else
- ip4_frag_create_run(&qp->q, skb);
- } else {
- /* Binary search. Note that skb can become the first fragment,
- * but not the last (covered above).
- */
- rbn = &qp->q.rb_fragments.rb_node;
- do {
- parent = *rbn;
- skb1 = rb_to_skb(parent);
- skb1_run_end = skb1->ip_defrag_offset +
- FRAG_CB(skb1)->frag_run_len;
- if (end <= skb1->ip_defrag_offset)
- rbn = &parent->rb_left;
- else if (offset >= skb1_run_end)
- rbn = &parent->rb_right;
- else if (offset >= skb1->ip_defrag_offset &&
- end <= skb1_run_end)
- goto err; /* No new data, potential duplicate */
- else
- goto discard_qp; /* Found an overlap */
- } while (*rbn);
- /* Here we have parent properly set, and rbn pointing to
- * one of its NULL left/right children. Insert skb.
- */
- ip4_frag_init_run(skb);
- rb_link_node(&skb->rbnode, parent, rbn);
- rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
- }
+ err = inet_frag_queue_insert(&qp->q, skb, offset, end);
+ if (err)
+ goto insert_error;
if (dev)
qp->iif = dev->ifindex;
- skb->ip_defrag_offset = offset;
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
@@ -494,15 +374,24 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
skb->_skb_refdst = 0UL;
err = ip_frag_reasm(qp, skb, prev_tail, dev);
skb->_skb_refdst = orefdst;
+ if (err)
+ inet_frag_kill(&qp->q);
return err;
}
skb_dst_drop(skb);
return -EINPROGRESS;
+insert_error:
+ if (err == IPFRAG_DUP) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+ err = -EINVAL;
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASM_OVERLAPS);
discard_qp:
inet_frag_kill(&qp->q);
- IP_INC_STATS_BH(net, IPSTATS_MIB_REASM_OVERLAPS);
+ IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
err:
kfree_skb(skb);
return err;
@@ -514,12 +403,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
- struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments);
- struct sk_buff **nextp; /* To build frag_list. */
- struct rb_node *rbn;
- int len;
- int ihlen;
- int err;
+ void *reasm_data;
+ int len, err;
u8 ecn;
ipq_kill(qp);
@@ -529,111 +414,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
err = -EINVAL;
goto out_fail;
}
- /* Make the one we just received the head. */
- if (head != skb) {
- fp = skb_clone(skb, GFP_ATOMIC);
- if (!fp)
- goto out_nomem;
- FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
- if (RB_EMPTY_NODE(&skb->rbnode))
- FRAG_CB(prev_tail)->next_frag = fp;
- else
- rb_replace_node(&skb->rbnode, &fp->rbnode,
- &qp->q.rb_fragments);
- if (qp->q.fragments_tail == skb)
- qp->q.fragments_tail = fp;
- skb_morph(skb, head);
- FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
- rb_replace_node(&head->rbnode, &skb->rbnode,
- &qp->q.rb_fragments);
- consume_skb(head);
- head = skb;
- }
-
- WARN_ON(head->ip_defrag_offset != 0);
- /* Allocate a new buffer for the datagram. */
- ihlen = ip_hdrlen(head);
- len = ihlen + qp->q.len;
+ /* Make the one we just received the head. */
+ reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail);
+ if (!reasm_data)
+ goto out_nomem;
+ len = ip_hdrlen(skb) + qp->q.len;
err = -E2BIG;
if (len > 65535)
goto out_oversize;
- /* Head of list must not be cloned. */
- if (skb_unclone(head, GFP_ATOMIC))
- goto out_nomem;
-
- /* If the first fragment is fragmented itself, we split
- * it to two chunks: the first with data and paged part
- * and the second, holding only fragments. */
- if (skb_has_frag_list(head)) {
- struct sk_buff *clone;
- int i, plen = 0;
-
- clone = alloc_skb(0, GFP_ATOMIC);
- if (!clone)
- goto out_nomem;
- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
- skb_frag_list_init(head);
- for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
- plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
- clone->len = clone->data_len = head->data_len - plen;
- head->truesize += clone->truesize;
- clone->csum = 0;
- clone->ip_summed = head->ip_summed;
- add_frag_mem_limit(qp->q.net, clone->truesize);
- skb_shinfo(head)->frag_list = clone;
- nextp = &clone->next;
- } else {
- nextp = &skb_shinfo(head)->frag_list;
- }
+ inet_frag_reasm_finish(&qp->q, skb, reasm_data);
- skb_push(head, head->data - skb_network_header(head));
+ skb->dev = dev;
+ IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
- /* Traverse the tree in order, to build frag_list. */
- fp = FRAG_CB(head)->next_frag;
- rbn = rb_next(&head->rbnode);
- rb_erase(&head->rbnode, &qp->q.rb_fragments);
- while (rbn || fp) {
- /* fp points to the next sk_buff in the current run;
- * rbn points to the next run.
- */
- /* Go through the current run. */
- while (fp) {
- *nextp = fp;
- nextp = &fp->next;
- fp->prev = NULL;
- memset(&fp->rbnode, 0, sizeof(fp->rbnode));
- fp->sk = NULL;
- head->data_len += fp->len;
- head->len += fp->len;
- if (head->ip_summed != fp->ip_summed)
- head->ip_summed = CHECKSUM_NONE;
- else if (head->ip_summed == CHECKSUM_COMPLETE)
- head->csum = csum_add(head->csum, fp->csum);
- head->truesize += fp->truesize;
- fp = FRAG_CB(fp)->next_frag;
- }
- /* Move to the next run. */
- if (rbn) {
- struct rb_node *rbnext = rb_next(rbn);
-
- fp = rb_to_skb(rbn);
- rb_erase(rbn, &qp->q.rb_fragments);
- rbn = rbnext;
- }
- }
- sub_frag_mem_limit(qp->q.net, head->truesize);
-
- *nextp = NULL;
- head->next = NULL;
- head->prev = NULL;
- head->dev = dev;
- head->tstamp = qp->q.stamp;
- IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
-
- iph = ip_hdr(head);
+ iph = ip_hdr(skb);
iph->tot_len = htons(len);
iph->tos |= ecn;
@@ -646,7 +443,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
* from one very small df-fragment and one large non-df frag.
*/
if (qp->max_df_size == qp->q.max_size) {
- IPCB(head)->flags |= IPSKB_FRAG_PMTU;
+ IPCB(skb)->flags |= IPSKB_FRAG_PMTU;
iph->frag_off = htons(IP_DF);
} else {
iph->frag_off = 0;
@@ -744,28 +541,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
}
EXPORT_SYMBOL(ip_check_defrag);
-unsigned int inet_frag_rbtree_purge(struct rb_root *root)
-{
- struct rb_node *p = rb_first(root);
- unsigned int sum = 0;
-
- while (p) {
- struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
-
- p = rb_next(p);
- rb_erase(&skb->rbnode, root);
- while (skb) {
- struct sk_buff *next = FRAG_CB(skb)->next_frag;
-
- sum += skb->truesize;
- kfree_skb(skb);
- skb = next;
- }
- }
- return sum;
-}
-EXPORT_SYMBOL(inet_frag_rbtree_purge);
-
#ifdef CONFIG_SYSCTL
static int dist_min;
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 08/10] ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (6 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 07/10] net: IP defrag: encapsulate rbtree defrag code into callable functions Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 09/10] net: IP6 defrag: use rbtrees for IPv6 defrag Georg Kohmann
` (2 subsequent siblings)
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev; +Cc: Georg Kohmann, Florian Westphal, Pablo Neira Ayuso
commit 70b095c84326 ("ipv6: remove dependency of nf_defrag_ipv6 on ipv6
module")
From: Florian Westphal <fw@strlen.de>
IPV6=m
DEFRAG_IPV6=m
CONNTRACK=y yields:
net/netfilter/nf_conntrack_proto.o: In function `nf_ct_netns_do_get':
net/netfilter/nf_conntrack_proto.c:802: undefined reference to `nf_defrag_ipv6_enable'
net/netfilter/nf_conntrack_proto.o:(.rodata+0x640): undefined reference to `nf_conntrack_l4proto_icmpv6'
Setting DEFRAG_IPV6=y causes undefined references to ip6_rhash_params
ip6_frag_init and ip6_expire_frag_queue so it would be needed to force
IPV6=y too.
This patch gets rid of the 'followup linker error' by removing
the dependency of ipv6.ko symbols from netfilter ipv6 defrag.
Shared code is placed into a header, then used from both.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/ipv6.h | 29 ---------
include/net/ipv6_frag.h | 104 ++++++++++++++++++++++++++++++
net/ieee802154/6lowpan/reassembly.c | 2 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 17 +++--
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 3 +-
net/ipv6/reassembly.c | 92 ++------------------------
net/openvswitch/conntrack.c | 1 +
7 files changed, 126 insertions(+), 122 deletions(-)
create mode 100644 include/net/ipv6_frag.h
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index c07cf95..bd7c2ab 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -486,35 +486,6 @@ static inline bool ipv6_prefix_equal(const struct in6_addr *addr1,
}
#endif
-struct inet_frag_queue;
-
-enum ip6_defrag_users {
- IP6_DEFRAG_LOCAL_DELIVER,
- IP6_DEFRAG_CONNTRACK_IN,
- __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
- IP6_DEFRAG_CONNTRACK_OUT,
- __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
- IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
- __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
-};
-
-void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-extern const struct rhashtable_params ip6_rhash_params;
-
-/*
- * Equivalent of ipv4 struct ip
- */
-struct frag_queue {
- struct inet_frag_queue q;
-
- int iif;
- unsigned int csum;
- __u16 nhoffset;
- u8 ecn;
-};
-
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
-
static inline bool ipv6_addr_any(const struct in6_addr *a)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
new file mode 100644
index 00000000..749e1dc
--- /dev/null
+++ b/include/net/ipv6_frag.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _IPV6_FRAG_H
+#define _IPV6_FRAG_H
+#include <linux/kernel.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+enum ip6_defrag_users {
+ IP6_DEFRAG_LOCAL_DELIVER,
+ IP6_DEFRAG_CONNTRACK_IN,
+ __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
+ IP6_DEFRAG_CONNTRACK_OUT,
+ __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
+ IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
+ __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
+};
+
+/*
+ * Equivalent of ipv4 struct ip
+ */
+struct frag_queue {
+ struct inet_frag_queue q;
+
+ int iif;
+ __u16 nhoffset;
+ u8 ecn;
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline void ip6frag_init(struct inet_frag_queue *q, const void *a)
+{
+ struct frag_queue *fq = container_of(q, struct frag_queue, q);
+ const struct frag_v6_compare_key *key = a;
+
+ q->key.v6 = *key;
+ fq->ecn = 0;
+}
+
+static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v6,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline int
+ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v6_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static inline void
+ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
+{
+ struct net_device *dev = NULL;
+ struct sk_buff *head;
+
+ rcu_read_lock();
+ spin_lock(&fq->q.lock);
+
+ if (fq->q.flags & INET_FRAG_COMPLETE)
+ goto out;
+
+ inet_frag_kill(&fq->q);
+
+ dev = dev_get_by_index_rcu(net, fq->iif);
+ if (!dev)
+ goto out;
+
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+ IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+
+ /* Don't send error if the first segment did not arrive. */
+ head = fq->q.fragments;
+ if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;
+
+ head->dev = dev;
+ skb_get(head);
+ spin_unlock(&fq->q.lock);
+
+ icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+ kfree_skb(head);
+ goto out_rcu_unlock;
+
+out:
+ spin_unlock(&fq->q.lock);
+out_rcu_unlock:
+ rcu_read_unlock();
+ inet_frag_put(&fq->q);
+}
+#endif
+#endif
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 6183730..a67ef73 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -25,7 +25,7 @@
#include <net/ieee802154_netdev.h>
#include <net/6lowpan.h>
-#include <net/ipv6.h>
+#include <net/ipv6_frag.h>
#include <net/inet_frag.h>
#include "6lowpan_i.h"
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 5640e041..49fd3c6 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -33,9 +33,8 @@
#include <net/sock.h>
#include <net/snmp.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
-#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
@@ -158,7 +157,7 @@ static void nf_ct_frag6_expire(unsigned long data)
fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
net = container_of(fq->q.net, struct net, nf_frag.frags);
- ip6_expire_frag_queue(net, fq);
+ ip6frag_expire_frag_queue(net, fq);
}
/* Creation primitives. */
@@ -630,16 +629,24 @@ static struct pernet_operations nf_ct_net_ops = {
.exit = nf_ct_net_exit,
};
+static const struct rhashtable_params nfct_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = ip6frag_key_hashfn,
+ .obj_hashfn = ip6frag_obj_hashfn,
+ .obj_cmpfn = ip6frag_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
int nf_ct_frag6_init(void)
{
int ret = 0;
- nf_frags.constructor = ip6_frag_init;
+ nf_frags.constructor = ip6frag_init;
nf_frags.destructor = NULL;
nf_frags.qsize = sizeof(struct frag_queue);
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
- nf_frags.rhash_params = ip6_rhash_params;
+ nf_frags.rhash_params = nfct_rhash_params;
ret = inet_frags_init(&nf_frags);
if (ret)
goto out;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index f7aab5a..169bed9 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -14,8 +14,7 @@
#include <linux/skbuff.h>
#include <linux/icmp.h>
#include <linux/sysctl.h>
-#include <net/ipv6.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index c708fc5..ec90b84 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -57,7 +57,7 @@
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
#include <net/inet_ecn.h>
static const char ip6_frag_cache_name[] = "ip6-frags";
@@ -79,61 +79,6 @@ static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
-void ip6_frag_init(struct inet_frag_queue *q, const void *a)
-{
- struct frag_queue *fq = container_of(q, struct frag_queue, q);
- const struct frag_v6_compare_key *key = a;
-
- q->key.v6 = *key;
- fq->ecn = 0;
-}
-EXPORT_SYMBOL(ip6_frag_init);
-
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
-{
- struct net_device *dev = NULL;
- struct sk_buff *head;
-
- rcu_read_lock();
- spin_lock(&fq->q.lock);
-
- if (fq->q.flags & INET_FRAG_COMPLETE)
- goto out;
-
- inet_frag_kill(&fq->q);
-
- dev = dev_get_by_index_rcu(net, fq->iif);
- if (!dev)
- goto out;
-
- IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
- IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
-
- /* Don't send error if the first segment did not arrive. */
- head = fq->q.fragments;
- if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
- goto out;
-
- /* But use as source device on which LAST ARRIVED
- * segment was received. And do not use fq->dev
- * pointer directly, device might already disappeared.
- */
- head->dev = dev;
- skb_get(head);
- spin_unlock(&fq->q.lock);
-
- icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
- kfree_skb(head);
- goto out_rcu_unlock;
-
-out:
- spin_unlock(&fq->q.lock);
-out_rcu_unlock:
- rcu_read_unlock();
- inet_frag_put(&fq->q);
-}
-EXPORT_SYMBOL(ip6_expire_frag_queue);
-
static void ip6_frag_expire(unsigned long data)
{
struct frag_queue *fq;
@@ -142,7 +87,7 @@ static void ip6_frag_expire(unsigned long data)
fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ipv6.frags);
- ip6_expire_frag_queue(net, fq);
+ ip6frag_expire_frag_queue(net, fq);
}
static struct frag_queue *
@@ -705,42 +650,19 @@ static struct pernet_operations ip6_frags_ops = {
.exit = ipv6_frags_exit_net,
};
-static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
-{
- return jhash2(data,
- sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
-}
-
-static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
-{
- const struct inet_frag_queue *fq = data;
-
- return jhash2((const u32 *)&fq->key.v6,
- sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
-}
-
-static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
-{
- const struct frag_v6_compare_key *key = arg->key;
- const struct inet_frag_queue *fq = ptr;
-
- return !!memcmp(&fq->key, key, sizeof(*key));
-}
-
-const struct rhashtable_params ip6_rhash_params = {
+static const struct rhashtable_params ip6_rhash_params = {
.head_offset = offsetof(struct inet_frag_queue, node),
- .hashfn = ip6_key_hashfn,
- .obj_hashfn = ip6_obj_hashfn,
- .obj_cmpfn = ip6_obj_cmpfn,
+ .hashfn = ip6frag_key_hashfn,
+ .obj_hashfn = ip6frag_obj_hashfn,
+ .obj_cmpfn = ip6frag_obj_cmpfn,
.automatic_shrinking = true,
};
-EXPORT_SYMBOL(ip6_rhash_params);
int __init ipv6_frag_init(void)
{
int ret;
- ip6_frags.constructor = ip6_frag_init;
+ ip6_frags.constructor = ip6frag_init;
ip6_frags.destructor = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
ip6_frags.frag_expire = ip6_frag_expire;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 3ed0331..9b74e72 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -19,6 +19,7 @@
#include <net/netfilter/nf_conntrack_labels.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/ipv6_frag.h>
#include "datapath.h"
#include "conntrack.h"
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 09/10] net: IP6 defrag: use rbtrees for IPv6 defrag
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (7 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 08/10] ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2019-10-08 11:23 ` [PATCH 4.4 stable 10/10] net: IP6 defrag: use rbtrees in nf_conntrack_reasm.c Georg Kohmann
2020-02-05 3:40 ` [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Nobuhiro Iwamatsu
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev
Cc: Georg Kohmann, Peter Oskolkov, Eric Dumazet, Florian Westphal,
David S . Miller
commit d4289fcc9b16 ("net: IP6 defrag: use rbtrees for IPv6 defrag")
Currently, IPv6 defragmentation code drops non-last fragments that
are smaller than 1280 bytes: see
commit 0ed4229b08c1 ("ipv6: defrag: drop non-last frags smaller than min mtu")
This behavior is not specified in IPv6 RFCs and appears to break
compatibility with some IPv6 implemenations, as reported here:
https://www.spinics.net/lists/netdev/msg543846.html
This patch re-uses common IP defragmentation queueing and reassembly
code in IPv6, removing the 1280 byte restriction.
Signed-off-by: Peter Oskolkov <posk@google.com>
Reported-by: Tom Herbert <tom@herbertland.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/ipv6_frag.h | 11 ++-
net/ipv6/reassembly.c | 246 ++++++++++++++----------------------------------
2 files changed, 81 insertions(+), 176 deletions(-)
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index 749e1dc..67718f2 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -82,8 +82,15 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
/* Don't send error if the first segment did not arrive. */
- head = fq->q.fragments;
- if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+ if (!(fq->q.flags & INET_FRAG_FIRST_IN))
+ goto out;
+
+ /* sk_buff::dev and sk_buff::rbnode are unionized. So we
+ * pull the head out of the tree in order to be able to
+ * deal with head->dev.
+ */
+ head = inet_frag_pull_head(&fq->q);
+ if (!head)
goto out;
head->dev = dev;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index ec90b84..8bb8f5b 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -62,13 +62,6 @@
static const char ip6_frag_cache_name[] = "ip6-frags";
-struct ip6frag_skb_cb {
- struct inet6_skb_parm h;
- int offset;
-};
-
-#define FRAG6_CB(skb) ((struct ip6frag_skb_cb *)((skb)->cb))
-
static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
@@ -76,8 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
static struct inet_frags ip6_frags;
-static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
- struct net_device *dev);
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev);
static void ip6_frag_expire(unsigned long data)
{
@@ -117,21 +110,26 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff,
u32 *prob_offset)
{
- struct sk_buff *prev, *next;
- struct net_device *dev;
- int offset, end;
struct net *net = dev_net(skb_dst(skb)->dev);
+ int offset, end, fragsize;
+ struct sk_buff *prev_tail;
+ struct net_device *dev;
+ int err = -ENOENT;
u8 ecn;
if (fq->q.flags & INET_FRAG_COMPLETE)
goto err;
+ err = -EINVAL;
offset = ntohs(fhdr->frag_off) & ~0x7;
end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
if ((unsigned int)end > IPV6_MAXPLEN) {
*prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
+ /* note that if prob_offset is set, the skb is freed elsewhere,
+ * we do not free it here.
+ */
return -1;
}
@@ -151,7 +149,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
*/
if (end < fq->q.len ||
((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
- goto err;
+ goto discard_fq;
fq->q.flags |= INET_FRAG_LAST_IN;
fq->q.len = end;
} else {
@@ -168,75 +166,45 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.flags & INET_FRAG_LAST_IN)
- goto err;
+ goto discard_fq;
fq->q.len = end;
}
}
if (end == offset)
- goto err;
+ goto discard_fq;
+ err = -ENOMEM;
/* Point into the IP datagram 'data' part. */
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
- goto err;
-
- if (pskb_trim_rcsum(skb, end - offset))
- goto err;
-
- /* Find out which fragments are in front and at the back of us
- * in the chain of fragments so far. We must know where to put
- * this fragment, right?
- */
- prev = fq->q.fragments_tail;
- if (!prev || FRAG6_CB(prev)->offset < offset) {
- next = NULL;
- goto found;
- }
- prev = NULL;
- for (next = fq->q.fragments; next != NULL; next = next->next) {
- if (FRAG6_CB(next)->offset >= offset)
- break; /* bingo! */
- prev = next;
- }
-
-found:
- /* RFC5722, Section 4, amended by Errata ID : 3089
- * When reassembling an IPv6 datagram, if
- * one or more its constituent fragments is determined to be an
- * overlapping fragment, the entire datagram (and any constituent
- * fragments) MUST be silently discarded.
- */
-
- /* Check for overlap with preceding fragment. */
- if (prev &&
- (FRAG6_CB(prev)->offset + prev->len) > offset)
goto discard_fq;
- /* Look for overlap with succeeding segment. */
- if (next && FRAG6_CB(next)->offset < end)
+ err = pskb_trim_rcsum(skb, end - offset);
+ if (err)
goto discard_fq;
- FRAG6_CB(skb)->offset = offset;
+ /* Note : skb->rbnode and skb->dev share the same location. */
+ dev = skb->dev;
+ /* Makes sure compiler wont do silly aliasing games */
+ barrier();
- /* Insert this fragment in the chain of fragments. */
- skb->next = next;
- if (!next)
- fq->q.fragments_tail = skb;
- if (prev)
- prev->next = skb;
- else
- fq->q.fragments = skb;
+ prev_tail = fq->q.fragments_tail;
+ err = inet_frag_queue_insert(&fq->q, skb, offset, end);
+ if (err)
+ goto insert_error;
- dev = skb->dev;
- if (dev) {
+ if (dev)
fq->iif = dev->ifindex;
- skb->dev = NULL;
- }
+
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
add_frag_mem_limit(fq->q.net, skb->truesize);
+ fragsize = -skb_network_offset(skb) + skb->len;
+ if (fragsize > fq->q.max_size)
+ fq->q.max_size = fragsize;
+
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
@@ -247,44 +215,48 @@ found:
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
- int res;
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
- res = ip6_frag_reasm(fq, prev, dev);
+ err = ip6_frag_reasm(fq, skb, prev_tail, dev);
skb->_skb_refdst = orefdst;
- return res;
+ return err;
}
skb_dst_drop(skb);
- return -1;
+ return -EINPROGRESS;
+insert_error:
+ if (err == IPFRAG_DUP) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+ err = -EINVAL;
+ IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_REASM_OVERLAPS);
discard_fq:
inet_frag_kill(&fq->q);
-err:
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
+err:
kfree_skb(skb);
- return -1;
+ return err;
}
/*
* Check if this packet is complete.
- * Returns NULL on failure by any reason, and pointer
- * to current nexthdr field in reassembled frame.
*
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
*/
-static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
- struct net_device *dev)
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev)
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
- struct sk_buff *fp, *head = fq->q.fragments;
- int payload_len;
unsigned int nhoff;
- int sum_truesize;
+ void *reasm_data;
+ int payload_len;
u8 ecn;
inet_frag_kill(&fq->q);
@@ -293,113 +265,40 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
if (unlikely(ecn == 0xff))
goto out_fail;
- /* Make the one we just received the head. */
- if (prev) {
- head = prev->next;
- fp = skb_clone(head, GFP_ATOMIC);
-
- if (!fp)
- goto out_oom;
-
- fp->next = head->next;
- if (!fp->next)
- fq->q.fragments_tail = fp;
- prev->next = fp;
-
- skb_morph(head, fq->q.fragments);
- head->next = fq->q.fragments->next;
-
- consume_skb(fq->q.fragments);
- fq->q.fragments = head;
- }
-
- WARN_ON(head == NULL);
- WARN_ON(FRAG6_CB(head)->offset != 0);
+ reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
+ if (!reasm_data)
+ goto out_oom;
- /* Unfragmented part is taken from the first segment. */
- payload_len = ((head->data - skb_network_header(head)) -
+ payload_len = ((skb->data - skb_network_header(skb)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
- /* Head of list must not be cloned. */
- if (skb_unclone(head, GFP_ATOMIC))
- goto out_oom;
-
- /* If the first fragment is fragmented itself, we split
- * it to two chunks: the first with data and paged part
- * and the second, holding only fragments. */
- if (skb_has_frag_list(head)) {
- struct sk_buff *clone;
- int i, plen = 0;
-
- clone = alloc_skb(0, GFP_ATOMIC);
- if (!clone)
- goto out_oom;
- clone->next = head->next;
- head->next = clone;
- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
- skb_frag_list_init(head);
- for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
- plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
- clone->len = clone->data_len = head->data_len - plen;
- head->data_len -= clone->len;
- head->len -= clone->len;
- clone->csum = 0;
- clone->ip_summed = head->ip_summed;
- add_frag_mem_limit(fq->q.net, clone->truesize);
- }
-
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
nhoff = fq->nhoffset;
- skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
- memmove(head->head + sizeof(struct frag_hdr), head->head,
- (head->data - head->head) - sizeof(struct frag_hdr));
- if (skb_mac_header_was_set(head))
- head->mac_header += sizeof(struct frag_hdr);
- head->network_header += sizeof(struct frag_hdr);
-
- skb_reset_transport_header(head);
- skb_push(head, head->data - skb_network_header(head));
-
- sum_truesize = head->truesize;
- for (fp = head->next; fp;) {
- bool headstolen;
- int delta;
- struct sk_buff *next = fp->next;
-
- sum_truesize += fp->truesize;
- if (head->ip_summed != fp->ip_summed)
- head->ip_summed = CHECKSUM_NONE;
- else if (head->ip_summed == CHECKSUM_COMPLETE)
- head->csum = csum_add(head->csum, fp->csum);
-
- if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
- kfree_skb_partial(fp, headstolen);
- } else {
- if (!skb_shinfo(head)->frag_list)
- skb_shinfo(head)->frag_list = fp;
- head->data_len += fp->len;
- head->len += fp->len;
- head->truesize += fp->truesize;
- }
- fp = next;
- }
- sub_frag_mem_limit(fq->q.net, sum_truesize);
+ skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0];
+ memmove(skb->head + sizeof(struct frag_hdr), skb->head,
+ (skb->data - skb->head) - sizeof(struct frag_hdr));
+ if (skb_mac_header_was_set(skb))
+ skb->mac_header += sizeof(struct frag_hdr);
+ skb->network_header += sizeof(struct frag_hdr);
- head->next = NULL;
- head->dev = dev;
- head->tstamp = fq->q.stamp;
- ipv6_hdr(head)->payload_len = htons(payload_len);
- ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
- IP6CB(head)->nhoff = nhoff;
- IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
+ skb_reset_transport_header(skb);
+
+ inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+
+ skb->dev = dev;
+ ipv6_hdr(skb)->payload_len = htons(payload_len);
+ ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
+ IP6CB(skb)->nhoff = nhoff;
+ IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
+ IP6CB(skb)->frag_max_size = fq->q.max_size;
/* Yes, and fold redundant checksum back. 8) */
- skb_postpush_rcsum(head, skb_network_header(head),
- skb_network_header_len(head));
+ skb_postpush_rcsum(skb, skb_network_header(skb),
+ skb_network_header_len(skb));
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
@@ -407,6 +306,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
fq->q.fragments = NULL;
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
+ fq->q.last_run_head = NULL;
return 1;
out_oversize:
@@ -418,6 +318,7 @@ out_fail:
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
+ inet_frag_kill(&fq->q);
return -1;
}
@@ -456,10 +357,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
return 1;
}
- if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
- fhdr->frag_off & htons(IP6_MF))
- goto fail_hdr;
-
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
@@ -477,6 +374,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
if (prob_offset) {
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_INHDRERRORS);
+ /* icmpv6_param_prob() calls kfree_skb(skb) */
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset);
}
return ret;
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 4.4 stable 10/10] net: IP6 defrag: use rbtrees in nf_conntrack_reasm.c
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (8 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 09/10] net: IP6 defrag: use rbtrees for IPv6 defrag Georg Kohmann
@ 2019-10-08 11:23 ` Georg Kohmann
2020-02-05 3:40 ` [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Nobuhiro Iwamatsu
10 siblings, 0 replies; 13+ messages in thread
From: Georg Kohmann @ 2019-10-08 11:23 UTC (permalink / raw)
To: netdev
Cc: Georg Kohmann, Peter Oskolkov, Eric Dumazet, Florian Westphal,
David S . Miller
commit 997dd9647164 ("net: IP6 defrag: use rbtrees in
nf_conntrack_reasm.c")
Currently, IPv6 defragmentation code drops non-last fragments that
are smaller than 1280 bytes: see
commit 0ed4229b08c1 ("ipv6: defrag: drop non-last frags smaller than min mtu")
This behavior is not specified in IPv6 RFCs and appears to break
compatibility with some IPv6 implemenations, as reported here:
https://www.spinics.net/lists/netdev/msg543846.html
This patch re-uses common IP defragmentation queueing and reassembly
code in IP6 defragmentation in nf_conntrack, removing the 1280 byte
restriction.
Signed-off-by: Peter Oskolkov <posk@google.com>
Reported-by: Tom Herbert <tom@herbertland.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/netfilter/nf_conntrack_reasm.c | 256 +++++++++-----------------------
1 file changed, 72 insertions(+), 184 deletions(-)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 49fd3c6..31b7745 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -51,14 +51,6 @@
static const char nf_frags_cache_name[] = "nf-frags";
-struct nf_ct_frag6_skb_cb
-{
- struct inet6_skb_parm h;
- int offset;
-};
-
-#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb))
-
static struct inet_frags nf_frags;
#ifdef CONFIG_SYSCTL
@@ -144,6 +136,9 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
}
#endif
+static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev);
+
static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
@@ -184,9 +179,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
const struct frag_hdr *fhdr, int nhoff)
{
- struct sk_buff *prev, *next;
unsigned int payload_len;
- int offset, end;
+ struct net_device *dev;
+ struct sk_buff *prev;
+ int offset, end, err;
u8 ecn;
if (fq->q.flags & INET_FRAG_COMPLETE) {
@@ -260,55 +256,19 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
goto err;
}
- /* Find out which fragments are in front and at the back of us
- * in the chain of fragments so far. We must know where to put
- * this fragment, right?
- */
+ /* Note : skb->rbnode and skb->dev share the same location. */
+ dev = skb->dev;
+ /* Makes sure compiler wont do silly aliasing games */
+ barrier();
+
prev = fq->q.fragments_tail;
- if (!prev || NFCT_FRAG6_CB(prev)->offset < offset) {
- next = NULL;
- goto found;
- }
- prev = NULL;
- for (next = fq->q.fragments; next != NULL; next = next->next) {
- if (NFCT_FRAG6_CB(next)->offset >= offset)
- break; /* bingo! */
- prev = next;
- }
+ err = inet_frag_queue_insert(&fq->q, skb, offset, end);
+ if (err)
+ goto insert_error;
-found:
- /* RFC5722, Section 4:
- * When reassembling an IPv6 datagram, if
- * one or more its constituent fragments is determined to be an
- * overlapping fragment, the entire datagram (and any constituent
- * fragments, including those not yet received) MUST be silently
- * discarded.
- */
+ if (dev)
+ fq->iif = dev->ifindex;
- /* Check for overlap with preceding fragment. */
- if (prev &&
- (NFCT_FRAG6_CB(prev)->offset + prev->len) > offset)
- goto discard_fq;
-
- /* Look for overlap with succeeding segment. */
- if (next && NFCT_FRAG6_CB(next)->offset < end)
- goto discard_fq;
-
- NFCT_FRAG6_CB(skb)->offset = offset;
-
- /* Insert this fragment in the chain of fragments. */
- skb->next = next;
- if (!next)
- fq->q.fragments_tail = skb;
- if (prev)
- prev->next = skb;
- else
- fq->q.fragments = skb;
-
- if (skb->dev) {
- fq->iif = skb->dev->ifindex;
- skb->dev = NULL;
- }
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
fq->ecn |= ecn;
@@ -324,11 +284,25 @@ found:
fq->q.flags |= INET_FRAG_FIRST_IN;
}
- return 0;
+ if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+ fq->q.meat == fq->q.len) {
+ unsigned long orefdst = skb->_skb_refdst;
+
+ skb->_skb_refdst = 0UL;
+ err = nf_ct_frag6_reasm(fq, skb, prev, dev);
+ skb->_skb_refdst = orefdst;
+ return err;
+ }
-discard_fq:
+ skb_dst_drop(skb);
+ return -EINPROGRESS;
+
+insert_error:
+ if (err == IPFRAG_DUP)
+ goto err;
inet_frag_kill(&fq->q);
err:
+ skb_dst_drop(skb);
return -EINVAL;
}
@@ -338,141 +312,67 @@ err:
* It is called with locked fq, and caller must check that
* queue is eligible for reassembly i.e. it is not COMPLETE,
* the last and the first frames arrived and all the bits are here.
- *
- * returns true if *prev skb has been transformed into the reassembled
- * skb, false otherwise.
*/
-static bool
-nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev)
+static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
+ struct sk_buff *prev_tail, struct net_device *dev)
{
- struct sk_buff *fp, *head = fq->q.fragments;
- int payload_len;
+ void *reasm_data;
+ int payload_len;
u8 ecn;
inet_frag_kill(&fq->q);
- WARN_ON(head == NULL);
- WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
-
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
- return false;
+ goto err;
+
+ reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
+ if (!reasm_data)
+ goto err;
- /* Unfragmented part is taken from the first segment. */
- payload_len = ((head->data - skb_network_header(head)) -
+ payload_len = ((skb->data - skb_network_header(skb)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN) {
net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n",
payload_len);
- return false;
- }
-
- /* Head of list must not be cloned. */
- if (skb_unclone(head, GFP_ATOMIC))
- return false;
-
- /* If the first fragment is fragmented itself, we split
- * it to two chunks: the first with data and paged part
- * and the second, holding only fragments. */
- if (skb_has_frag_list(head)) {
- struct sk_buff *clone;
- int i, plen = 0;
-
- clone = alloc_skb(0, GFP_ATOMIC);
- if (clone == NULL)
- return false;
-
- clone->next = head->next;
- head->next = clone;
- skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
- skb_frag_list_init(head);
- for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
- plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
- clone->len = clone->data_len = head->data_len - plen;
- head->data_len -= clone->len;
- head->len -= clone->len;
- clone->csum = 0;
- clone->ip_summed = head->ip_summed;
-
- add_frag_mem_limit(fq->q.net, clone->truesize);
- }
-
- /* morph head into last received skb: prev.
- *
- * This allows callers of ipv6 conntrack defrag to continue
- * to use the last skb(frag) passed into the reasm engine.
- * The last skb frag 'silently' turns into the full reassembled skb.
- *
- * Since prev is also part of q->fragments we have to clone it first.
- */
- if (head != prev) {
- struct sk_buff *iter;
-
- fp = skb_clone(prev, GFP_ATOMIC);
- if (!fp)
- return false;
-
- fp->next = prev->next;
-
- iter = head;
- while (iter) {
- if (iter->next == prev) {
- iter->next = fp;
- break;
- }
- iter = iter->next;
- }
-
- skb_morph(prev, head);
- prev->next = head->next;
- consume_skb(head);
- head = prev;
+ goto err;
}
/* We have to remove fragment header from datagram and to relocate
* header in order to calculate ICV correctly. */
- skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0];
- memmove(head->head + sizeof(struct frag_hdr), head->head,
- (head->data - head->head) - sizeof(struct frag_hdr));
- head->mac_header += sizeof(struct frag_hdr);
- head->network_header += sizeof(struct frag_hdr);
-
- skb_shinfo(head)->frag_list = head->next;
- skb_reset_transport_header(head);
- skb_push(head, head->data - skb_network_header(head));
-
- for (fp = head->next; fp; fp = fp->next) {
- head->data_len += fp->len;
- head->len += fp->len;
- if (head->ip_summed != fp->ip_summed)
- head->ip_summed = CHECKSUM_NONE;
- else if (head->ip_summed == CHECKSUM_COMPLETE)
- head->csum = csum_add(head->csum, fp->csum);
- head->truesize += fp->truesize;
- fp->sk = NULL;
- }
- sub_frag_mem_limit(fq->q.net, head->truesize);
+ skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0];
+ memmove(skb->head + sizeof(struct frag_hdr), skb->head,
+ (skb->data - skb->head) - sizeof(struct frag_hdr));
+ skb->mac_header += sizeof(struct frag_hdr);
+ skb->network_header += sizeof(struct frag_hdr);
+
+ skb_reset_transport_header(skb);
- head->ignore_df = 1;
- head->next = NULL;
- head->dev = dev;
- head->tstamp = fq->q.stamp;
- ipv6_hdr(head)->payload_len = htons(payload_len);
- ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
- IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
+ inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+
+ skb->ignore_df = 1;
+ skb->dev = dev;
+ ipv6_hdr(skb)->payload_len = htons(payload_len);
+ ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
+ IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
/* Yes, and fold redundant checksum back. 8) */
- if (head->ip_summed == CHECKSUM_COMPLETE)
- head->csum = csum_partial(skb_network_header(head),
- skb_network_header_len(head),
- head->csum);
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_partial(skb_network_header(skb),
+ skb_network_header_len(skb),
+ skb->csum);
fq->q.fragments = NULL;
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
+ fq->q.last_run_head = NULL;
+
+ return 0;
- return true;
+err:
+ inet_frag_kill(&fq->q);
+ return -EINVAL;
}
/*
@@ -541,7 +441,6 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
u16 savethdr = skb->transport_header;
- struct net_device *dev = skb->dev;
int fhoff, nhoff, ret;
struct frag_hdr *fhdr;
struct frag_queue *fq;
@@ -564,10 +463,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
hdr = ipv6_hdr(skb);
fhdr = (struct frag_hdr *)skb_transport_header(skb);
- if (clone->len - skb_network_offset(clone) < IPV6_MIN_MTU &&
- fhdr->frag_off & htons(IP6_MF))
- goto ret_orig;
-
skb_orphan(skb);
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
@@ -576,24 +471,17 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
spin_lock_bh(&fq->q.lock);
ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff);
- if (ret < 0) {
- if (ret == -EPROTO) {
- skb->transport_header = savethdr;
- ret = 0;
- }
- goto out_unlock;
+ if (ret == -EPROTO) {
+ skb->transport_header = savethdr;
+ ret = 0;
}
/* after queue has assumed skb ownership, only 0 or -EINPROGRESS
* must be returned.
*/
- ret = -EINPROGRESS;
- if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- fq->q.meat == fq->q.len &&
- nf_ct_frag6_reasm(fq, skb, dev))
- ret = 0;
+ if (ret)
+ ret = -EINPROGRESS;
-out_unlock:
spin_unlock_bh(&fq->q.lock);
inet_frag_put(&fq->q);
return ret;
--
2.10.2
^ permalink raw reply related [flat|nested] 13+ messages in thread* Re: [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes
2019-10-08 11:22 [PATCH 4.4 stable 00/10] net: ip6 defrag: backport fixes Georg Kohmann
` (9 preceding siblings ...)
2019-10-08 11:23 ` [PATCH 4.4 stable 10/10] net: IP6 defrag: use rbtrees in nf_conntrack_reasm.c Georg Kohmann
@ 2020-02-05 3:40 ` Nobuhiro Iwamatsu
10 siblings, 0 replies; 13+ messages in thread
From: Nobuhiro Iwamatsu @ 2020-02-05 3:40 UTC (permalink / raw)
To: Georg Kohmann; +Cc: netdev
Hi,
Could you tell me about the status of this patch series?
I think you need to respond to Greg's comments.
Best regards,
Nobuhiro
On Tue, Oct 08, 2019 at 01:22:59PM +0200, Georg Kohmann wrote:
> This is a backport of a 5.1rc patchset:
> https://patchwork.ozlabs.org/cover/1029418/
>
> Which was backported into 4.19:
> https://patchwork.ozlabs.org/cover/1081619/
>
> and into 4.14:
> https://patchwork.ozlabs.org/cover/1089651/
>
> and into 4.9:
> https://www.spinics.net/lists/netdev/msg567087.html
>
> This patchset for 4.4 is based on Peter Oskolkov's patchsets above.
> 5 additional patches has been added to make it all apply, build
> and pass TAHI IPv6 Ready test with the IOL INTACT test tool.
> Without this patchset 2 extension header tests and 12 fragmentation
> tests fail to pass. The previous attempt to fix this seamed to end
> here: https://www.spinics.net/lists/netdev/msg567728.html
> It would be nice if someone with more netfilter
> and fragmentation knowledge than me could review it.
>
> Florian Westphal (3):
> netfilter: ipv6: nf_defrag: avoid/free clone operations
> netfilter: ipv6: avoid nf_iterate recursion
> netfilter: ipv6: nf_defrag: fix NULL deref panic
> ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module
>
> Jason A. Donenfeld (1):
> ipv6: do not increment mac header when it's unset
>
> Subash Abhinov Kasiviswanathan (1):
> netfilter: ipv6: nf_defrag: Pass on packets to stack per RFC2460
>
> Eric Dumazet (1):
> ipv6: frags: fix a lockdep false positive
>
> Peter Oskolkov (3):
> net: IP defrag: encapsulate rbtree defrag code into callable functions
> net: IP6 defrag: use rbtrees for IPv6 defrag
> net: IP6 defrag: use rbtrees in nf_conntrack_reasm.c
>
> include/net/inet_frag.h | 16 +-
> include/net/ipv6.h | 29 ---
> include/net/ipv6_frag.h | 111 +++++++++
> include/net/netfilter/ipv6/nf_defrag_ipv6.h | 3 +-
> net/ieee802154/6lowpan/reassembly.c | 2 +-
> net/ipv4/inet_fragment.c | 293 ++++++++++++++++++++++
> net/ipv4/ip_fragment.c | 295 +++--------------------
> net/ipv6/netfilter/nf_conntrack_reasm.c | 344 ++++++++------------------
> net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 23 +-
> net/ipv6/reassembly.c | 360 +++++++---------------------
> net/openvswitch/conntrack.c | 26 +-
> 11 files changed, 664 insertions(+), 838 deletions(-)
> create mode 100644 include/net/ipv6_frag.h
>
> --
> 2.10.2
>
>
^ permalink raw reply [flat|nested] 13+ messages in thread