GitHub-Mirror/linux-bl808
2
0
Fork 0
mirror of https://github.com/Fishwaldo/linux-bl808.git synced 2025-03-17 12:34:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'ip-Use-rb-trees-for-IP-frag-queue'

Browse source 
Peter Oskolkov says:

====================
ip: Use rb trees for IP frag queue.

This patchset
 * changes IPv4 defrag behavior to match that of IPv6: overlapping
   fragments now cause the whole IP datagram to be discarded (suggested
   by David Miller): there are no legitimate use cases for overlapping
   fragments;
 * changes IPv4 defrag queue from a list to a rb tree (suggested
   by Eric Dumazet): this change removes a potential attach vector.

Upcoming patches will contain similar changes for IPv6 frag queue,
as well as a comprehensive IP defrag self-test (temporarily delayed).
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2018-08-05 17:16:46 -07:00
commit c30f1fc041
9 changed files with 141 additions and 142 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
include/linux/skbuff.h
View file

@ -676,13 +676,16 @@ struct sk_buff {
* UDP receive path is one user.
*/
unsigned long dev_scratch;
int ip_defrag_offset;
};
};
struct rb_node rbnode; /* used in netem & tcp stack */
struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */
struct list_head list;
};
struct sock *sk;
union {
struct sock *sk;
int ip_defrag_offset;
};
union {
ktime_t tstamp;
@ -2585,7 +2588,7 @@ static inline void __skb_queue_purge(struct sk_buff_head *list)
kfree_skb(skb);
}
void skb_rbtree_purge(struct rb_root *root);
unsigned int skb_rbtree_purge(struct rb_root *root);
void *netdev_alloc_frag(unsigned int fragsz);

3
include/net/inet_frag.h
View file

@ -75,7 +75,8 @@ struct inet_frag_queue {
struct timer_list timer;
spinlock_t lock;
refcount_t refcnt;
struct sk_buff *fragments;
struct sk_buff *fragments; /* Used in IPv6. */
struct rb_root rb_fragments; /* Used in IPv4. */
struct sk_buff *fragments_tail;
ktime_t stamp;
int len;

1
include/uapi/linux/snmp.h
View file

@ -56,6 +56,7 @@ enum
IPSTATS_MIB_ECT1PKTS, /* InECT1Pkts */
IPSTATS_MIB_ECT0PKTS, /* InECT0Pkts */
IPSTATS_MIB_CEPKTS, /* InCEPkts */
IPSTATS_MIB_REASM_OVERLAPS, /* ReasmOverlaps */
__IPSTATS_MIB_MAX
};

6
net/core/skbuff.c
View file

@ -2858,23 +2858,27 @@ EXPORT_SYMBOL(skb_queue_purge);
/**
* skb_rbtree_purge - empty a skb rbtree
* @root: root of the rbtree to empty
* Return value: the sum of truesizes of all purged skbs.
*
* Delete all buffers on an &sk_buff rbtree. Each buffer is removed from
* the list and one reference dropped. This function does not take
* any lock. Synchronization should be handled by the caller (e.g., TCP
* out-of-order queue is protected by the socket lock).
*/
void skb_rbtree_purge(struct rb_root *root)
unsigned int skb_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);
sum += skb->truesize;
kfree_skb(skb);
}
return sum;
}
/**

14
net/ipv4/inet_fragment.c
View file

@ -137,12 +137,16 @@ void inet_frag_destroy(struct inet_frag_queue *q)
fp = q->fragments;
nf = q->net;
f = nf->f;
while (fp) {
struct sk_buff *xp = fp->next;
if (fp) {
do {
struct sk_buff *xp = fp->next;
sum_truesize += fp->truesize;
kfree_skb(fp);
fp = xp;
sum_truesize += fp->truesize;
kfree_skb(fp);
fp = xp;
} while (fp);
} else {
sum_truesize = skb_rbtree_purge(&q->rb_fragments);
}
sum = sum_truesize + f->qsize;

245
net/ipv4/ip_fragment.c
View file

@ -136,7 +136,7 @@ static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
const struct iphdr *iph;
struct sk_buff *head;
struct sk_buff *head = NULL;
struct net *net;
struct ipq *qp;
int err;
@ -152,14 +152,31 @@ static void ip_expire(struct timer_list *t)
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
head = qp->q.fragments;
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
if (!qp->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.
*/
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;
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->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out;
@ -179,16 +196,16 @@ static void ip_expire(struct timer_list *t)
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
skb_get(head);
spin_unlock(&qp->q.lock);
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
kfree_skb(head);
goto out_rcu_unlock;
out:
spin_unlock(&qp->q.lock);
out_rcu_unlock:
rcu_read_unlock();
if (head)
kfree_skb(head);
ipq_put(qp);
}
@ -231,7 +248,7 @@ static int ip_frag_too_far(struct ipq *qp)
end = atomic_inc_return(&peer->rid);
qp->rid = end;
rc = qp->q.fragments && (end - start) > max;
rc = qp->q.fragments_tail && (end - start) > max;
if (rc) {
struct net *net;
@ -245,7 +262,6 @@ static int ip_frag_too_far(struct ipq *qp)
static int ip_frag_reinit(struct ipq *qp)
{
struct sk_buff *fp;
unsigned int sum_truesize = 0;
if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
@ -253,20 +269,14 @@ static int ip_frag_reinit(struct ipq *qp)
return -ETIMEDOUT;
}
fp = qp->q.fragments;
do {
struct sk_buff *xp = fp->next;
sum_truesize += fp->truesize;
kfree_skb(fp);
fp = xp;
} while (fp);
sum_truesize = skb_rbtree_purge(&qp->q.rb_fragments);
sub_frag_mem_limit(qp->q.net, sum_truesize);
qp->q.flags = 0;
qp->q.len = 0;
qp->q.meat = 0;
qp->q.fragments = NULL;
qp->q.rb_fragments = RB_ROOT;
qp->q.fragments_tail = NULL;
qp->iif = 0;
qp->ecn = 0;
@ -277,7 +287,9 @@ static int ip_frag_reinit(struct ipq *qp)
/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct sk_buff *prev, *next;
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct rb_node **rbn, *parent;
struct sk_buff *skb1;
struct net_device *dev;
unsigned int fragsize;
int flags, offset;
@ -340,99 +352,57 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
if (err)
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 = qp->q.fragments_tail;
if (!prev || prev->ip_defrag_offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = qp->q.fragments; next != NULL; next = next->next) {
if (next->ip_defrag_offset >= offset)
break; /* bingo! */
prev = next;
}
found:
/* We found where to put this one. Check for overlap with
* preceding fragment, and, if needed, align things so that
* any overlaps are eliminated.
*/
if (prev) {
int i = (prev->ip_defrag_offset + prev->len) - offset;
if (i > 0) {
offset += i;
err = -EINVAL;
if (end <= offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, i))
goto err;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
}
err = -ENOMEM;
while (next && next->ip_defrag_offset < end) {
int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
if (i < next->len) {
int delta = -next->truesize;
/* Eat head of the next overlapped fragment
* and leave the loop. The next ones cannot overlap.
*/
if (!pskb_pull(next, i))
goto err;
delta += next->truesize;
if (delta)
add_frag_mem_limit(qp->q.net, delta);
next->ip_defrag_offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
next->ip_summed = CHECKSUM_NONE;
break;
} else {
struct sk_buff *free_it = next;
/* Old fragment is completely overridden with
* new one drop it.
*/
next = next->next;
if (prev)
prev->next = next;
else
qp->q.fragments = next;
qp->q.meat -= free_it->len;
sub_frag_mem_limit(qp->q.net, free_it->truesize);
kfree_skb(free_it);
}
}
/* Note : skb->ip_defrag_offset and skb->dev share the same location */
/* Note : skb->rbnode and skb->dev share the same location. */
dev = skb->dev;
if (dev)
qp->iif = dev->ifindex;
/* Makes sure compiler wont do silly aliasing games */
barrier();
skb->ip_defrag_offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
/* 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).
*/
/* Find out where to put this fragment. */
skb1 = qp->q.fragments_tail;
if (!skb1) {
/* This is the first fragment we've received. */
rb_link_node(&skb->rbnode, NULL, &qp->q.rb_fragments.rb_node);
qp->q.fragments_tail = skb;
if (prev)
prev->next = skb;
else
qp->q.fragments = skb;
} else if ((skb1->ip_defrag_offset + skb1->len) < end) {
/* This is the common/special case: skb goes to the end. */
/* Detect and discard overlaps. */
if (offset < (skb1->ip_defrag_offset + skb1->len))
goto discard_qp;
/* Insert after skb1. */
rb_link_node(&skb->rbnode, &skb1->rbnode, &skb1->rbnode.rb_right);
qp->q.fragments_tail = 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);
if (end <= skb1->ip_defrag_offset)
rbn = &parent->rb_left;
else if (offset >= skb1->ip_defrag_offset + skb1->len)
rbn = &parent->rb_right;
else /* Found an overlap with skb1. */
goto discard_qp;
} while (*rbn);
/* Here we have parent properly set, and rbn pointing to
* one of its NULL left/right children. Insert skb. */
rb_link_node(&skb->rbnode, parent, rbn);
}
rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
if (dev)
qp->iif = dev->ifindex;
skb->ip_defrag_offset = offset;
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
@ -455,7 +425,7 @@ found:
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip_frag_reasm(qp, prev, dev);
err = ip_frag_reasm(qp, skb, dev);
skb->_skb_refdst = orefdst;
return err;
}
@ -463,20 +433,24 @@ found:
skb_dst_drop(skb);
return -EINPROGRESS;
discard_qp:
inet_frag_kill(&qp->q);
err = -EINVAL;
__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
err:
kfree_skb(skb);
return err;
}
/* Build a new IP datagram from all its fragments. */
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
struct net_device *dev)
{
struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
struct iphdr *iph;
struct sk_buff *fp, *head = qp->q.fragments;
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;
@ -490,25 +464,20 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
goto out_fail;
}
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (head != skb) {
fp = skb_clone(skb, GFP_ATOMIC);
if (!fp)
goto out_nomem;
fp->next = head->next;
if (!fp->next)
rb_replace_node(&skb->rbnode, &fp->rbnode, &qp->q.rb_fragments);
if (qp->q.fragments_tail == skb)
qp->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, qp->q.fragments);
head->next = qp->q.fragments->next;
consume_skb(qp->q.fragments);
qp->q.fragments = head;
skb_morph(skb, head);
rb_replace_node(&head->rbnode, &skb->rbnode,
&qp->q.rb_fragments);
consume_skb(head);
head = skb;
}
WARN_ON(!head);
WARN_ON(head->ip_defrag_offset != 0);
/* Allocate a new buffer for the datagram. */
@ -533,24 +502,35 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
clone = alloc_skb(0, GFP_ATOMIC);
if (!clone)
goto out_nomem;
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;
skb->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;
}
skb_shinfo(head)->frag_list = head->next;
skb_push(head, head->data - skb_network_header(head));
for (fp=head->next; fp; fp = fp->next) {
/* Traverse the tree in order, to build frag_list. */
rbn = rb_next(&head->rbnode);
rb_erase(&head->rbnode, &qp->q.rb_fragments);
while (rbn) {
struct rb_node *rbnext = rb_next(rbn);
fp = rb_to_skb(rbn);
rb_erase(rbn, &qp->q.rb_fragments);
rbn = rbnext;
*nextp = fp;
nextp = &fp->next;
fp->prev = NULL;
memset(&fp->rbnode, 0, sizeof(fp->rbnode));
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
@ -561,7 +541,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
}
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);
@ -589,6 +571,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.rb_fragments = RB_ROOT;
qp->q.fragments_tail = NULL;
return 0;

1
net/ipv4/proc.c
View file

@ -119,6 +119,7 @@ static const struct snmp_mib snmp4_ipextstats_list[] = {
SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS),
SNMP_MIB_SENTINEL
};

1
net/ipv6/netfilter/nf_conntrack_reasm.c
View file

@ -463,6 +463,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
head->csum);
fq->q.fragments = NULL;
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
return true;

1
net/ipv6/reassembly.c
View file

@ -405,6 +405,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
return 1;