diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0c7c67b3a87b2351a3a65408c6d00b6eadf583bb..9d24aec064e888316b5a5cf450cf25ffdd391183 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -753,8 +753,6 @@ typedef unsigned char *sk_buff_data_t;
* @list: queue head
* @ll_node: anchor in an llist (eg socket defer_list)
* @sk: Socket we are owned by
- * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in
- * fragmentation management
* @dev: Device we arrived on/are leaving by
* @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
* @cb: Control buffer. Free for use by every layer. Put private vars here
@@ -875,10 +873,7 @@ struct sk_buff {
struct llist_node ll_node;
};
- union {
- struct sock *sk;
- int ip_defrag_offset;
- };
+ struct sock *sk;
union {
ktime_t tstamp;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 7072fc0783ef56e59c886a2f2516e7db7d10c942..c88c9034d63004e7763f60b3211dc319172c8d06 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -24,6 +24,8 @@
#include <net/ip.h>
#include <net/ipv6.h>
+#include "../core/sock_destructor.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.
@@ -39,6 +41,7 @@ struct ipfrag_skb_cb {
};
struct sk_buff *next_frag;
int frag_run_len;
+ int ip_defrag_offset;
};
#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb))
@@ -396,12 +399,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
*/
if (!last)
fragrun_create(q, skb); /* First fragment. */
- else if (last->ip_defrag_offset + last->len < end) {
+ else if (FRAG_CB(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)
+ if (offset < FRAG_CB(last)->ip_defrag_offset + last->len)
return IPFRAG_OVERLAP;
- if (offset == last->ip_defrag_offset + last->len)
+ if (offset == FRAG_CB(last)->ip_defrag_offset + last->len)
fragrun_append_to_last(q, skb);
else
fragrun_create(q, skb);
@@ -418,13 +421,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
parent = *rbn;
curr = rb_to_skb(parent);
- curr_run_end = curr->ip_defrag_offset +
+ curr_run_end = FRAG_CB(curr)->ip_defrag_offset +
FRAG_CB(curr)->frag_run_len;
- if (end <= curr->ip_defrag_offset)
+ if (end <= FRAG_CB(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 &&
+ else if (offset >= FRAG_CB(curr)->ip_defrag_offset &&
end <= curr_run_end)
return IPFRAG_DUP;
else
@@ -438,7 +441,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
rb_insert_color(&skb->rbnode, &q->rb_fragments);
}
- skb->ip_defrag_offset = offset;
+ FRAG_CB(skb)->ip_defrag_offset = offset;
return IPFRAG_OK;
}
@@ -448,13 +451,28 @@ 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;
+ void (*destructor)(struct sk_buff *);
+ unsigned int orig_truesize = 0;
+ struct sk_buff **nextp = NULL;
+ struct sock *sk = skb->sk;
int delta;
+ if (sk && is_skb_wmem(skb)) {
+ /* TX: skb->sk might have been passed as argument to
+ * dst->output and must remain valid until tx completes.
+ *
+ * Move sk to reassembled skb and fix up wmem accounting.
+ */
+ orig_truesize = skb->truesize;
+ destructor = skb->destructor;
+ }
+
if (head != skb) {
fp = skb_clone(skb, GFP_ATOMIC);
- if (!fp)
- return NULL;
+ if (!fp) {
+ head = skb;
+ goto out_restore_sk;
+ }
FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
if (RB_EMPTY_NODE(&skb->rbnode))
FRAG_CB(parent)->next_frag = fp;
@@ -463,6 +481,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
&q->rb_fragments);
if (q->fragments_tail == skb)
q->fragments_tail = fp;
+
+ if (orig_truesize) {
+ /* prevent skb_morph from releasing sk */
+ skb->sk = NULL;
+ skb->destructor = NULL;
+ }
skb_morph(skb, head);
FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
rb_replace_node(&head->rbnode, &skb->rbnode,
@@ -470,13 +494,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
consume_skb(head);
head = skb;
}
- WARN_ON(head->ip_defrag_offset != 0);
+ WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0);
delta = -head->truesize;
/* Head of list must not be cloned. */
if (skb_unclone(head, GFP_ATOMIC))
- return NULL;
+ goto out_restore_sk;
delta += head->truesize;
if (delta)
@@ -492,7 +516,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
- return NULL;
+ goto out_restore_sk;
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++)
@@ -509,6 +533,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
nextp = &skb_shinfo(head)->frag_list;
}
+out_restore_sk:
+ if (orig_truesize) {
+ int ts_delta = head->truesize - orig_truesize;
+
+ /* if this reassembled skb is fragmented later,
+ * fraglist skbs will get skb->sk assigned from head->sk,
+ * and each frag skb will be released via sock_wfree.
+ *
+ * Update sk_wmem_alloc.
+ */
+ head->sk = sk;
+ head->destructor = destructor;
+ refcount_add(ts_delta, &sk->sk_wmem_alloc);
+ }
+
return nextp;
}
EXPORT_SYMBOL(inet_frag_reasm_prepare);
@@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare);
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
void *reasm_data, bool try_coalesce)
{
+ struct sock *sk = is_skb_wmem(head) ? head->sk : NULL;
+ const unsigned int head_truesize = head->truesize;
struct sk_buff **nextp = reasm_data;
struct rb_node *rbn;
struct sk_buff *fp;
@@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
head->prev = NULL;
head->tstamp = q->stamp;
head->mono_delivery_time = q->mono_delivery_time;
+
+ if (sk)
+ refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc);
}
EXPORT_SYMBOL(inet_frag_reasm_finish);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a4941f53b523725cd777d213500b8f6918287920..fb947d1613fe2b8b5262ff809255d3b754b57e59 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
}
skb_dst_drop(skb);
+ skb_orphan(skb);
return -EINPROGRESS;
insert_error:
@@ -487,7 +488,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
struct ipq *qp;
__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
- skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 1a51a44571c372184fb4dabc967dedb44cde976b..d0dcbaca19943a2170f1ea6c621168f4eb8aeb67 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -294,6 +294,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
}
skb_dst_drop(skb);
+ skb_orphan(skb);
return -EINPROGRESS;
insert_error:
@@ -469,7 +470,6 @@ 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);
- skb_orphan(skb);
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {