From: Eric Dumazet edumazet@google.com

[ Upstream commit 415787d7799f4fccbe8d49cb0b8e5811be6b0389 ]

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 2a8c680b67cd..f75e9e711c31 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -170,7 +170,8 @@ 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; @@ -186,11 +187,7 @@ 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(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; }

@@ -221,10 +218,7 @@ 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(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) { @@ -536,15 +530,22 @@ 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(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); + } return ret; }

[ Upstream commit c23f35d19db3b36ffb9e04b08f1d91565d15f84f ]

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.

v2: make handling of overlapping packets match upstream.

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 | 302 +++++---------------------------------- 3 files changed, 342 insertions(+), 269 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 335cf7851f12..008f64823c41 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -77,8 +77,8 @@ struct inet_frag_queue { struct timer_list timer; spinlock_t lock; refcount_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; @@ -153,4 +153,16 @@ 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 6ffee9d2b0e5..481cded81b2d 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. @@ -122,6 +178,28 @@ 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; @@ -224,3 +302,218 @@ 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 d95b32af4a0e..5a1d39e32196 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -57,57 +57,6 @@ */ 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(struct timer_list *t) * 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(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); - __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; @@ -514,13 +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 delta; - int err; + void *reasm_data; + int len, err; u8 ecn;

ipq_kill(qp); @@ -530,117 +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;

- delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_nomem; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(qp->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) - 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;

@@ -653,7 +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; @@ -751,28 +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;

[ Upstream commit d4289fcc9b16b89619ee1c54f829e05e56de8b9a ]

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.

v2: change handling of overlaps to match that of upstream.

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 | 249 +++++++++++----------------------------- 2 files changed, 77 insertions(+), 183 deletions(-)

diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 6ced1e6899b6..28aa9b30aece 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(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 e5ab3b7813d6..fe797b29ca89 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(struct timer_list *t) { @@ -118,21 +111,26 @@ 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, fragsize; 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; }

@@ -152,7 +150,7 @@ 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 { @@ -169,70 +167,36 @@ 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; @@ -252,44 +216,48 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,

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(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASM_OVERLAPS); discard_fq: inet_frag_kill(&fq->q); -err: __IP6_INC_STATS(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, delta; unsigned int nhoff; - int sum_truesize; + void *reasm_data; + int payload_len; u8 ecn;

inet_frag_kill(&fq->q); @@ -298,120 +266,40 @@ 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;

- delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_oom; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->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) - 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); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data);

- 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; - IP6CB(head)->frag_max_size = fq->q.max_size; + 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(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); @@ -419,6 +307,7 @@ 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: @@ -430,6 +319,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); rcu_read_unlock(); + inet_frag_kill(&fq->q); return -1; }

@@ -468,10 +358,6 @@ 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) { @@ -489,6 +375,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) if (prob_offset) { __IP6_INC_STATS(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;