/**
* tipc_msg_bundle(): Append contents of a buffer to tail of an existing one
* @list: the buffer chain of the existing buffer ("bundle")
* @skb: buffer to be appended
* @mtu: max allowable size for the bundle buffer
* Consumes buffer if successful
* Returns true if bundling could be performed, otherwise false
*/
bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu)
{
struct sk_buff *bskb = skb_peek_tail(list);
struct tipc_msg *bmsg = buf_msg(bskb);
struct tipc_msg *msg = buf_msg(skb);
unsigned int bsz = msg_size(bmsg);
unsigned int msz = msg_size(msg);
u32 start = align(bsz);
u32 max = mtu - INT_H_SIZE;
u32 pad = start - bsz;
if (likely(msg_user(msg) == MSG_FRAGMENTER))
return false;
if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL))
return false;
if (unlikely(msg_user(msg) == BCAST_PROTOCOL))
return false;
if (likely(msg_user(bmsg) != MSG_BUNDLER))
return false;
if (likely(!TIPC_SKB_CB(bskb)->bundling))
return false;
if (unlikely(skb_tailroom(bskb) < (pad + msz)))
return false;
if (unlikely(max < (start + msz)))
return false;
skb_put(bskb, pad + msz);
skb_copy_to_linear_data_offset(bskb, start, skb->data, msz);
msg_set_size(bmsg, start + msz);
msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1);
kfree_skb(skb);
return true;
}
static inline int ip6_ufo_append_data(struct sock *sk,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
int transhdrlen, int mtu,unsigned int flags)
{
struct sk_buff *skb;
int err;
/* There is support for UDP large send offload by network
* device, so create one single skb packet containing complete
* udp datagram
*/
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
skb = sock_alloc_send_skb(sk,
hh_len + fragheaderlen + transhdrlen + 20,
(flags & MSG_DONTWAIT), &err);
if (skb == NULL)
return -ENOMEM;
/* reserve space for Hardware header */
skb_reserve(skb, hh_len);
/* create space for UDP/IP header */
skb_put(skb,fragheaderlen + transhdrlen);
/* initialize network header pointer */
skb_reset_network_header(skb);
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
sk->sk_sndmsg_off = 0;
}
err = skb_append_datato_frags(sk,skb, getfrag, from,
(length - transhdrlen));
if (!err) {
struct frag_hdr fhdr;
/* specify the length of each IP datagram fragment*/
skb_shinfo(skb)->gso_size = mtu - fragheaderlen -
sizeof(struct frag_hdr);
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
ipv6_select_ident(skb, &fhdr);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
__skb_queue_tail(&sk->sk_write_queue, skb);
return 0;
}
/* There is not enough support do UPD LSO,
* so follow normal path
*/
kfree_skb(skb);
return err;
}
static void ks_netlink_process_backlog(void)
{
int processed;
int err;
do {
struct sk_buff *skb;
struct sk_buff *tail;
tail = skb_peek_tail(&ks_backlog);
processed = FALSE;
while ((skb = skb_dequeue(&ks_backlog))) {
err = ks_netlink_rcv_skb(&ks_netlink_state, skb);
if (err == -EAGAIN)
skb_queue_tail(&ks_backlog, skb);
else {
kfree_skb(skb);
processed = TRUE;
}
if (skb == tail)
break;
}
} while(processed);
}
static void iwl_mvm_release_frames(struct iwl_mvm *mvm,
struct ieee80211_sta *sta,
struct napi_struct *napi,
struct iwl_mvm_reorder_buffer *reorder_buf,
u16 nssn)
{
u16 ssn = reorder_buf->head_sn;
lockdep_assert_held(&reorder_buf->lock);
/* ignore nssn smaller than head sn - this can happen due to timeout */
if (iwl_mvm_is_sn_less(nssn, ssn, reorder_buf->buf_size))
return;
while (iwl_mvm_is_sn_less(ssn, nssn, reorder_buf->buf_size)) {
int index = ssn % reorder_buf->buf_size;
struct sk_buff_head *skb_list = &reorder_buf->entries[index];
struct sk_buff *skb;
ssn = ieee80211_sn_inc(ssn);
/* holes are valid since nssn indicates frames were received. */
if (skb_queue_empty(skb_list) || !skb_peek_tail(skb_list))
continue;
/* Empty the list. Will have more than one frame for A-MSDU */
while ((skb = __skb_dequeue(skb_list))) {
iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb,
reorder_buf->queue,
sta);
reorder_buf->num_stored--;
}
}
reorder_buf->head_sn = nssn;
if (reorder_buf->num_stored && !reorder_buf->removed) {
u16 index = reorder_buf->head_sn % reorder_buf->buf_size;
while (!skb_peek_tail(&reorder_buf->entries[index]))
index = (index + 1) % reorder_buf->buf_size;
/* modify timer to match next frame's expiration time */
mod_timer(&reorder_buf->reorder_timer,
reorder_buf->reorder_time[index] + 1 +
RX_REORDER_BUF_TIMEOUT_MQ);
} else {
del_timer(&reorder_buf->reorder_timer);
}
}
static inline int ip6_ufo_append_data(struct sock *sk,
struct sk_buff_head *queue,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
int exthdrlen, int transhdrlen, int mtu,
unsigned int flags, const struct flowi6 *fl6)
{
struct sk_buff *skb;
int err;
/* There is support for UDP large send offload by network
* device, so create one single skb packet containing complete
* udp datagram
*/
skb = skb_peek_tail(queue);
if (!skb) {
skb = sock_alloc_send_skb(sk,
hh_len + fragheaderlen + transhdrlen + 20,
(flags & MSG_DONTWAIT), &err);
if (!skb)
return err;
/* reserve space for Hardware header */
skb_reserve(skb, hh_len);
/* create space for UDP/IP header */
skb_put(skb, fragheaderlen + transhdrlen);
/* initialize network header pointer */
skb_set_network_header(skb, exthdrlen);
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
skb->protocol = htons(ETH_P_IPV6);
skb->csum = 0;
__skb_queue_tail(queue, skb);
} else if (skb_is_gso(skb)) {
goto append;
}
skb->ip_summed = CHECKSUM_PARTIAL;
/* Specify the length of each IPv6 datagram fragment.
* It has to be a multiple of 8.
*/
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk),
&fl6->daddr,
&fl6->saddr);
append:
return skb_append_datato_frags(sk, skb, getfrag, from,
(length - transhdrlen));
}
static inline int ip6_ufo_append_data(struct sock *sk,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
int transhdrlen, int mtu,unsigned int flags,
struct rt6_info *rt)
{
struct sk_buff *skb;
int err;
/* There is support for UDP large send offload by network
* device, so create one single skb packet containing complete
* udp datagram
*/
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
struct frag_hdr fhdr;
skb = sock_alloc_send_skb(sk,
hh_len + fragheaderlen + transhdrlen + 20,
(flags & MSG_DONTWAIT), &err);
if (skb == NULL)
return err;
/* reserve space for Hardware header */
skb_reserve(skb, hh_len);
/* create space for UDP/IP header */
skb_put(skb,fragheaderlen + transhdrlen);
/* initialize network header pointer */
skb_reset_network_header(skb);
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
/* Specify the length of each IPv6 datagram fragment.
* It has to be a multiple of 8.
*/
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
ipv6_select_ident(&fhdr, rt);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
__skb_queue_tail(&sk->sk_write_queue, skb);
}
return skb_append_datato_frags(sk, skb, getfrag, from,
(length - transhdrlen));
}
void iwl_mvm_reorder_timer_expired(unsigned long data)
{
struct iwl_mvm_reorder_buffer *buf = (void *)data;
int i;
u16 sn = 0, index = 0;
bool expired = false;
spin_lock_bh(&buf->lock);
if (!buf->num_stored || buf->removed) {
spin_unlock_bh(&buf->lock);
return;
}
for (i = 0; i < buf->buf_size ; i++) {
index = (buf->head_sn + i) % buf->buf_size;
if (!skb_peek_tail(&buf->entries[index]))
continue;
if (!time_after(jiffies, buf->reorder_time[index] +
RX_REORDER_BUF_TIMEOUT_MQ))
break;
expired = true;
sn = ieee80211_sn_add(buf->head_sn, i + 1);
}
if (expired) {
struct ieee80211_sta *sta;
rcu_read_lock();
sta = rcu_dereference(buf->mvm->fw_id_to_mac_id[buf->sta_id]);
/* SN is set to the last expired frame + 1 */
IWL_DEBUG_HT(buf->mvm,
"Releasing expired frames for sta %u, sn %d\n",
buf->sta_id, sn);
iwl_mvm_release_frames(buf->mvm, sta, NULL, buf, sn);
rcu_read_unlock();
} else if (buf->num_stored) {
/*
* If no frame expired and there are stored frames, index is now
* pointing to the first unexpired frame - modify timer
* accordingly to this frame.
*/
mod_timer(&buf->reorder_timer,
buf->reorder_time[index] +
1 + RX_REORDER_BUF_TIMEOUT_MQ);
}
spin_unlock_bh(&buf->lock);
}
struct sk_buff *xip_finish_skb(struct sock *sk)
{
struct sk_buff_head *queue;
struct sk_buff *skb;
queue = &sk->sk_write_queue;
skb = __skb_dequeue(queue);
if (!skb)
return NULL;
/* XIP, by design, does not support fragmentation. */
BUG_ON(skb_peek_tail(queue));
return skb;
}
int xip_append_data(struct sock *sk,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
struct msghdr *from, int length, unsigned int flags)
{
struct sk_buff *skb;
if (flags & MSG_PROBE)
return 0;
skb = skb_peek_tail(&sk->sk_write_queue);
BUG_ON(!skb);
return __xip_append_data(skb, getfrag, from, length);
}
struct sk_buff *brcmu_pktq_peek_tail(struct pktq *pq, int *prec_out)
{
int prec;
if (pq->len == 0)
return NULL;
for (prec = 0; prec < pq->hi_prec; prec++)
if (!skb_queue_empty(&pq->q[prec].skblist))
break;
if (prec_out)
*prec_out = prec;
return skb_peek_tail(&pq->q[prec].skblist);
}
static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
{
struct sk_buff_head *list = &sch->q;
psched_time_t tnext = netem_skb_cb(nskb)->time_to_send;
struct sk_buff *skb = skb_peek_tail(list);
/* Optimize for add at tail */
if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send))
return __skb_queue_tail(list, nskb);
skb_queue_reverse_walk(list, skb) {
if (tnext >= netem_skb_cb(skb)->time_to_send)
break;
}
__skb_queue_after(list, skb, nskb);
}
static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
{
struct sk_buff_head *list = &sch->q;
psched_time_t tnext = netem_skb_cb(nskb)->time_to_send;
struct sk_buff *skb;
if (likely(skb_queue_len(list) < sch->limit)) {
skb = skb_peek_tail(list);
/* Optimize for add at tail */
if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send))
return qdisc_enqueue_tail(nskb, sch);
skb_queue_reverse_walk(list, skb) {
if (tnext >= netem_skb_cb(skb)->time_to_send)
break;
}
__skb_queue_after(list, skb, nskb);
sch->qstats.backlog += qdisc_pkt_len(nskb);
return NET_XMIT_SUCCESS;
}
/**
* llc_util_nr_inside_tx_window - check if sequence number is in tx window
* @sk: current connection.
* @nr: N(R) of received PDU.
*
* This routine checks if N(R) of received PDU is in range of transmit
* window; on the other hand checks if received PDU acknowledges some
* outstanding PDUs that are in transmit window. Returns 0 for success, 1
* otherwise.
*/
static u16 llc_util_nr_inside_tx_window(struct sock *sk, u8 nr)
{
u8 nr1, nr2;
struct sk_buff *skb;
struct llc_pdu_sn *pdu;
struct llc_opt *llc = llc_sk(sk);
int rc = 0;
if (llc->dev->flags & IFF_LOOPBACK)
goto out;
rc = 1;
if (!skb_queue_len(&llc->pdu_unack_q))
goto out;
skb = skb_peek(&llc->pdu_unack_q);
pdu = llc_pdu_sn_hdr(skb);
nr1 = LLC_I_GET_NS(pdu);
skb = skb_peek_tail(&llc->pdu_unack_q);
pdu = llc_pdu_sn_hdr(skb);
nr2 = LLC_I_GET_NS(pdu);
rc = !llc_circular_between(nr1, nr, (nr2 + 1) % LLC_2_SEQ_NBR_MODULO);
out:
return rc;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen;
int exthdrlen;
int hh_len;
int mtu;
int copy;
int err;
int offset = 0;
int csummode = CHECKSUM_NONE;
__u8 tx_flags = 0;
if (flags&MSG_PROBE)
return 0;
cork = &inet->cork.base;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (WARN_ON(np->cork.opt))
return -EINVAL;
np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
np->cork.opt->tot_len = opt->tot_len;
np->cork.opt->opt_flen = opt->opt_flen;
np->cork.opt->opt_nflen = opt->opt_nflen;
np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
sk->sk_allocation);
if (opt->dst0opt && !np->cork.opt->dst0opt)
return -ENOBUFS;
np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
sk->sk_allocation);
if (opt->dst1opt && !np->cork.opt->dst1opt)
return -ENOBUFS;
np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
sk->sk_allocation);
if (opt->hopopt && !np->cork.opt->hopopt)
return -ENOBUFS;
np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
sk->sk_allocation);
if (opt->srcrt && !np->cork.opt->srcrt)
return -ENOBUFS;
/* need source address above miyazawa*/
}
dst_hold(&rt->dst);
cork->dst = &rt->dst;
inet->cork.fl.u.ip6 = *fl6;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(&rt->dst);
else
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
cork->fragsize = mtu;
if (dst_allfrag(rt->dst.path))
cork->flags |= IPCORK_ALLFRAG;
cork->length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) -
rt->rt6i_nfheader_len;
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
rt = (struct rt6_info *)cork->dst;
fl6 = &inet->cork.fl.u.ip6;
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
mtu = cork->fragsize;
}
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/* For UDP, check if TX timestamp is enabled */
if (sk->sk_type == SOCK_DGRAM) {
err = sock_tx_timestamp(sk, &tx_flags);
if (err)
goto error;
}
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
cork->length += length;
if (length > mtu) {
int proto = sk->sk_protocol;
if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
if (proto == IPPROTO_UDP &&
(rt->dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length,
hh_len, fragheaderlen,
transhdrlen, mtu, flags, rt);
if (err)
goto error;
return 0;
}
}
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
fraggap = skb->len - maxfraglen;
else
fraggap = 0;
/* update mtu and maxfraglen if necessary */
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt);
skb_prev = skb;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
if (datalen != length + fraggap) {
/*
* this is not the last fragment, the trailer
* space is regarded as data space.
*/
datalen += rt->dst.trailer_len;
}
alloclen += rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
else {
/* Only the initial fragment
* is time stamped.
*/
tx_flags = 0;
}
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve for fragmentation */
skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
if (sk->sk_type == SOCK_DGRAM)
skb_shinfo(skb)->tx_flags = tx_flags;
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
struct page *page = sk->sk_sndmsg_page;
int off = sk->sk_sndmsg_off;
unsigned int left;
if (page && (left = PAGE_SIZE - off) > 0) {
if (copy >= left)
copy = left;
if (page != frag->page) {
if (i == MAX_SKB_FRAGS) {
err = -EMSGSIZE;
goto error;
}
get_page(page);
skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
frag = &skb_shinfo(skb)->frags[i];
}
} else if(i < MAX_SKB_FRAGS) {
if (copy > PAGE_SIZE)
copy = PAGE_SIZE;
page = alloc_pages(sk->sk_allocation, 0);
if (page == NULL) {
err = -ENOMEM;
goto error;
}
sk->sk_sndmsg_page = page;
sk->sk_sndmsg_off = 0;
skb_fill_page_desc(skb, i, page, 0, 0);
frag = &skb_shinfo(skb)->frags[i];
} else {
err = -EMSGSIZE;
goto error;
}
if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
err = -EFAULT;
goto error;
}
sk->sk_sndmsg_off += copy;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
}
return 0;
error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
static int __ip6_append_data(struct sock *sk,
struct flowi6 *fl6,
struct sk_buff_head *queue,
struct inet_cork *cork,
struct inet6_cork *v6_cork,
struct page_frag *pfrag,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
unsigned int flags, int dontfrag)
{
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
int exthdrlen = 0;
int dst_exthdrlen = 0;
int hh_len;
int copy;
int err;
int offset = 0;
__u8 tx_flags = 0;
u32 tskey = 0;
struct rt6_info *rt = (struct rt6_info *)cork->dst;
struct ipv6_txoptions *opt = v6_cork->opt;
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
skb = skb_peek_tail(queue);
if (!skb) {
exthdrlen = opt ? opt->opt_flen : 0;
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
}
mtu = cork->fragsize;
orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
sizeof(struct frag_hdr);
headersize = sizeof(struct ipv6hdr) +
(opt ? opt->opt_flen + opt->opt_nflen : 0) +
(dst_allfrag(&rt->dst) ?
sizeof(struct frag_hdr) : 0) +
rt->rt6i_nfheader_len;
if (cork->length + length > mtu - headersize && dontfrag &&
(sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_RAW)) {
ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
sizeof(struct ipv6hdr));
goto emsgsize;
}
if (ip6_sk_ignore_df(sk))
maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
else
maxnonfragsize = mtu;
if (cork->length + length > maxnonfragsize - headersize) {
emsgsize:
ipv6_local_error(sk, EMSGSIZE, fl6,
mtu - headersize +
sizeof(struct ipv6hdr));
return -EMSGSIZE;
}
/* CHECKSUM_PARTIAL only with no extension headers and when
* we are not going to fragment
*/
if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
headersize == sizeof(struct ipv6hdr) &&
length < mtu - headersize &&
!(flags & MSG_MORE) &&
rt->dst.dev->features & NETIF_F_V6_CSUM)
csummode = CHECKSUM_PARTIAL;
if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
sock_tx_timestamp(sk, &tx_flags);
if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
tskey = sk->sk_tskey++;
}
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
cork->length += length;
if (((length > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO) &&
(sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, exthdrlen,
transhdrlen, mtu, flags, fl6);
if (err)
goto error;
return 0;
}
if (!skb)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
fraggap = skb->len - maxfraglen;
else
fraggap = 0;
/* update mtu and maxfraglen if necessary */
if (!skb || !skb_prev)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt,
orig_mtu);
skb_prev = skb;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
alloclen += dst_exthdrlen;
if (datalen != length + fraggap) {
/*
* this is not the last fragment, the trailer
* space is regarded as data space.
*/
datalen += rt->dst.trailer_len;
}
alloclen += rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(!skb))
err = -ENOBUFS;
}
if (!skb)
goto error;
/*
* Fill in the control structures
*/
skb->protocol = htons(ETH_P_IPV6);
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve for fragmentation and ipsec header */
skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
dst_exthdrlen);
/* Only the initial fragment is time stamped */
skb_shinfo(skb)->tx_flags = tx_flags;
tx_flags = 0;
skb_shinfo(skb)->tskey = tskey;
tskey = 0;
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
err = -ENOMEM;
if (!sk_page_frag_refill(sk, pfrag))
goto error;
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
err = -EMSGSIZE;
if (i == MAX_SKB_FRAGS)
goto error;
__skb_fill_page_desc(skb, i, pfrag->page,
pfrag->offset, 0);
skb_shinfo(skb)->nr_frags = ++i;
get_page(pfrag->page);
}
copy = min_t(int, copy, pfrag->size - pfrag->offset);
if (getfrag(from,
page_address(pfrag->page) + pfrag->offset,
offset, copy, skb->len, skb) < 0)
goto error_efault;
pfrag->offset += copy;
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
}
return 0;
error_efault:
err = -EFAULT;
error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
/*
* Returns true if the MPDU was buffered\dropped, false if it should be passed
* to upper layer.
*/
static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
struct napi_struct *napi,
int queue,
struct ieee80211_sta *sta,
struct sk_buff *skb,
struct iwl_rx_mpdu_desc *desc)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
struct iwl_mvm_baid_data *baid_data;
struct iwl_mvm_reorder_buffer *buffer;
struct sk_buff *tail;
u32 reorder = le32_to_cpu(desc->reorder_data);
bool amsdu = desc->mac_flags2 & IWL_RX_MPDU_MFLG2_AMSDU;
u8 tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK;
u8 sub_frame_idx = desc->amsdu_info &
IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
int index;
u16 nssn, sn;
u8 baid;
baid = (reorder & IWL_RX_MPDU_REORDER_BAID_MASK) >>
IWL_RX_MPDU_REORDER_BAID_SHIFT;
if (baid == IWL_RX_REORDER_DATA_INVALID_BAID)
return false;
/* no sta yet */
if (WARN_ON(IS_ERR_OR_NULL(sta)))
return false;
/* not a data packet */
if (!ieee80211_is_data_qos(hdr->frame_control) ||
is_multicast_ether_addr(hdr->addr1))
return false;
if (unlikely(!ieee80211_is_data_present(hdr->frame_control)))
return false;
baid_data = rcu_dereference(mvm->baid_map[baid]);
if (WARN(!baid_data,
"Received baid %d, but no data exists for this BAID\n", baid))
return false;
if (WARN(tid != baid_data->tid || mvm_sta->sta_id != baid_data->sta_id,
"baid 0x%x is mapped to sta:%d tid:%d, but was received for sta:%d tid:%d\n",
baid, baid_data->sta_id, baid_data->tid, mvm_sta->sta_id,
tid))
return false;
nssn = reorder & IWL_RX_MPDU_REORDER_NSSN_MASK;
sn = (reorder & IWL_RX_MPDU_REORDER_SN_MASK) >>
IWL_RX_MPDU_REORDER_SN_SHIFT;
buffer = &baid_data->reorder_buf[queue];
spin_lock_bh(&buffer->lock);
/*
* If there was a significant jump in the nssn - adjust.
* If the SN is smaller than the NSSN it might need to first go into
* the reorder buffer, in which case we just release up to it and the
* rest of the function will take of storing it and releasing up to the
* nssn
*/
if (!iwl_mvm_is_sn_less(nssn, buffer->head_sn + buffer->buf_size,
buffer->buf_size)) {
u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn;
iwl_mvm_release_frames(mvm, sta, napi, buffer, min_sn);
}
/* drop any oudated packets */
if (ieee80211_sn_less(sn, buffer->head_sn))
goto drop;
/* release immediately if allowed by nssn and no stored frames */
if (!buffer->num_stored && ieee80211_sn_less(sn, nssn)) {
if (iwl_mvm_is_sn_less(buffer->head_sn, nssn,
buffer->buf_size))
buffer->head_sn = nssn;
/* No need to update AMSDU last SN - we are moving the head */
spin_unlock_bh(&buffer->lock);
return false;
}
index = sn % buffer->buf_size;
/*
* Check if we already stored this frame
* As AMSDU is either received or not as whole, logic is simple:
* If we have frames in that position in the buffer and the last frame
* originated from AMSDU had a different SN then it is a retransmission.
* If it is the same SN then if the subframe index is incrementing it
* is the same AMSDU - otherwise it is a retransmission.
*/
tail = skb_peek_tail(&buffer->entries[index]);
if (tail && !amsdu)
goto drop;
else if (tail && (sn != buffer->last_amsdu ||
buffer->last_sub_index >= sub_frame_idx))
goto drop;
/* put in reorder buffer */
__skb_queue_tail(&buffer->entries[index], skb);
buffer->num_stored++;
buffer->reorder_time[index] = jiffies;
if (amsdu) {
buffer->last_amsdu = sn;
buffer->last_sub_index = sub_frame_idx;
}
iwl_mvm_release_frames(mvm, sta, napi, buffer, nssn);
spin_unlock_bh(&buffer->lock);
return true;
drop:
kfree_skb(skb);
spin_unlock_bh(&buffer->lock);
return true;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, struct ipv6_txoptions *opt, struct flowi *fl, struct rt6_info *rt,
unsigned int flags)
{
struct inet_opt *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
unsigned int maxfraglen, fragheaderlen;
int exthdrlen;
int hh_len;
int mtu;
int copy = 0;
int err;
int offset = 0;
int csummode = CHECKSUM_NONE;
if (flags&MSG_PROBE)
return 0;
if (skb_queue_empty(&sk->write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (np->cork.opt == NULL)
np->cork.opt = kmalloc(opt->tot_len, sk->allocation);
memcpy(np->cork.opt, opt, opt->tot_len);
inet->cork.flags |= IPCORK_OPT;
/* need source address above miyazawa*/
}
dst_hold(&rt->u.dst);
np->cork.rt = rt;
np->cork.fl = fl;
np->cork.hop_limit = hlimit;
inet->cork.fragsize = mtu = dst_pmtu(&rt->u.dst);
inet->cork.length = 0;
inet->sndmsg_page = NULL;
inet->sndmsg_off = 0;
exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
rt = np->cork.rt;
if (inet->cork.flags & IPCORK_OPT)
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
mtu = inet->cork.fragsize;
}
hh_len = (rt->u.dst.dev->hard_header_len&~15) + 16;
fragheaderlen = sizeof(struct ipv6hdr) + (opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen);
return -EMSGSIZE;
}
}
inet->cork.length += length;
if ((skb = skb_peek_tail(&sk->write_queue)) == NULL)
goto alloc_new_skb;
while (length > 0) {
if ((copy = maxfraglen - skb->len) <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int alloclen;
BUG_TRAP(copy == 0);
alloc_new_skb:
datalen = maxfraglen - fragheaderlen;
if (datalen > length)
datalen = length;
fraglen = datalen + fragheaderlen;
if ((flags & MSG_MORE) &&
!(rt->u.dst.dev->features&NETIF_F_SG))
alloclen = maxfraglen;
else
alloclen = fraglen;
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len + 15,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->wmem_alloc) <= 2*sk->sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len + 15, 1,
sk->allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve 8 byte for fragmentation */
skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb->nh.raw = data + exthdrlen;
data += fragheaderlen;
skb->h.raw = data + exthdrlen;
copy = datalen - transhdrlen;
if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, 0, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
struct page *page = inet->sndmsg_page;
int off = inet->sndmsg_off;
unsigned int left;
if (page && (left = PAGE_SIZE - off) > 0) {
if (copy >= left)
copy = left;
if (page != frag->page) {
if (i == MAX_SKB_FRAGS) {
err = -EMSGSIZE;
goto error;
}
get_page(page);
skb_fill_page_desc(skb, i, page, inet->sndmsg_off, 0);
frag = &skb_shinfo(skb)->frags[i];
}
} else if(i < MAX_SKB_FRAGS) {
if (copy > PAGE_SIZE)
copy = PAGE_SIZE;
page = alloc_pages(sk->allocation, 0);
if (page == NULL) {
err = -ENOMEM;
goto error;
}
inet->sndmsg_page = page;
inet->sndmsg_off = 0;
skb_fill_page_desc(skb, i, page, 0, 0);
frag = &skb_shinfo(skb)->frags[i];
skb->truesize += PAGE_SIZE;
atomic_add(PAGE_SIZE, &sk->wmem_alloc);
} else {
err = -EMSGSIZE;
goto error;
}
if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
err = -EFAULT;
goto error;
}
inet->sndmsg_off += copy;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
}
offset += copy;
length -= copy;
}
return 0;
error:
inet->cork.length -= length;
IP6_INC_STATS(Ip6OutDiscards);
return err;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, struct ipv6_txoptions *opt, struct flowi *fl, struct rt6_info *rt,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
unsigned int maxfraglen, fragheaderlen;
int exthdrlen;
int hh_len;
int mtu;
int copy;
int err;
int offset = 0;
int csummode = CHECKSUM_NONE;
if (flags&MSG_PROBE)
return 0;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (np->cork.opt == NULL) {
np->cork.opt = kmalloc(opt->tot_len,
sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
} else if (np->cork.opt->tot_len < opt->tot_len) {
printk(KERN_DEBUG "ip6_append_data: invalid option length\n");
return -EINVAL;
}
memcpy(np->cork.opt, opt, opt->tot_len);
inet->cork.flags |= IPCORK_OPT;
/* need source address above miyazawa*/
}
dst_hold(&rt->u.dst);
np->cork.rt = rt;
inet->cork.fl = *fl;
np->cork.hop_limit = hlimit;
inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
if (dst_allfrag(rt->u.dst.path))
inet->cork.flags |= IPCORK_ALLFRAG;
inet->cork.length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
rt = np->cork.rt;
fl = &inet->cork.fl;
if (inet->cork.flags & IPCORK_OPT)
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
mtu = inet->cork.fragsize;
}
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + (opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
inet->cork.length += length;
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
/* There's no room in the current skb */
if (skb_prev)
fraggap = skb_prev->len - maxfraglen;
else
fraggap = 0;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen;
fraglen = datalen + fragheaderlen;
if ((flags & MSG_MORE) &&
!(rt->u.dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
/*
* The last fragment gets additional space at tail.
* Note: we overallocate on fragments with MSG_MODE
* because we have no idea if we're the last one.
*/
if (datalen == length + fraggap)
alloclen += rt->u.dst.trailer_len;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve for fragmentation */
skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb->nh.raw = data + exthdrlen;
data += fragheaderlen;
skb->h.raw = data + exthdrlen;
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
skb_trim(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
struct page *page = sk->sk_sndmsg_page;
int off = sk->sk_sndmsg_off;
unsigned int left;
if (page && (left = PAGE_SIZE - off) > 0) {
if (copy >= left)
copy = left;
if (page != frag->page) {
if (i == MAX_SKB_FRAGS) {
err = -EMSGSIZE;
goto error;
}
get_page(page);
skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
frag = &skb_shinfo(skb)->frags[i];
}
} else if(i < MAX_SKB_FRAGS) {
if (copy > PAGE_SIZE)
copy = PAGE_SIZE;
page = alloc_pages(sk->sk_allocation, 0);
if (page == NULL) {
err = -ENOMEM;
goto error;
}
sk->sk_sndmsg_page = page;
sk->sk_sndmsg_off = 0;
skb_fill_page_desc(skb, i, page, 0, 0);
frag = &skb_shinfo(skb)->frags[i];
skb->truesize += PAGE_SIZE;
atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
} else {
err = -EMSGSIZE;
goto error;
}
if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
err = -EFAULT;
goto error;
}
sk->sk_sndmsg_off += copy;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
}
offset += copy;
length -= copy;
}
return 0;
error:
inet->cork.length -= length;
IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
return err;
}
/*
* Insert one skb into qdisc.
* Note: parent depends on return value to account for queue length.
* NET_XMIT_DROP: queue length didn't change.
* NET_XMIT_SUCCESS: one skb was queued.
*/
static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
/* We don't fill cb now as skb_unshare() may invalidate it */
struct netem_skb_cb *cb;
struct sk_buff *skb2;
int count = 1;
/* Random duplication */
if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
++count;
/* Drop packet? */
if (loss_event(q))
--count;
if (count == 0) {
sch->qstats.drops++;
kfree_skb(skb);
return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
}
skb_orphan(skb);
/*
* If we need to duplicate packet, then re-insert at top of the
* qdisc tree, since parent queuer expects that only one
* skb will be queued.
*/
if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
struct Qdisc *rootq = qdisc_root(sch);
u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
q->duplicate = 0;
qdisc_enqueue_root(skb2, rootq);
q->duplicate = dupsave;
}
/*
* Randomized packet corruption.
* Make copy if needed since we are modifying
* If packet is going to be hardware checksummed, then
* do it now in software before we mangle it.
*/
if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
(skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_help(skb)))
return qdisc_drop(skb, sch);
skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8);
}
if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
return qdisc_reshape_fail(skb, sch);
sch->qstats.backlog += qdisc_pkt_len(skb);
cb = netem_skb_cb(skb);
if (q->gap == 0 || /* not doing reordering */
q->counter < q->gap - 1 || /* inside last reordering gap */
q->reorder < get_crandom(&q->reorder_cor)) {
psched_time_t now;
psched_tdiff_t delay;
delay = tabledist(q->latency, q->jitter,
&q->delay_cor, q->delay_dist);
now = psched_get_time();
if (q->rate) {
struct sk_buff_head *list = &sch->q;
delay += packet_len_2_sched_time(skb->len, q);
if (!skb_queue_empty(list)) {
/*
* Last packet in queue is reference point (now).
* First packet in queue is already in flight,
* calculate this time bonus and substract
* from delay.
*/
delay -= now - netem_skb_cb(skb_peek(list))->time_to_send;
now = netem_skb_cb(skb_peek_tail(list))->time_to_send;
}
}
cb->time_to_send = now + delay;
++q->counter;
tfifo_enqueue(skb, sch);
} else {
/*
* Do re-ordering by putting one out of N packets at the front
* of the queue.
*/
cb->time_to_send = psched_get_time();
q->counter = 0;
__skb_queue_head(&sch->q, skb);
sch->qstats.requeues++;
}
return NET_XMIT_SUCCESS;
}
