【内核源码】linux UDP实现
对于不设置MSG_MORE和UDP_CORK的通常情况， udp_sendmsg查找路由和获取ip选项后，直接调用ip_make_skb()来创建skb，并调用udp_send_skb发送，由ip层来执行分片
对于需要cork的情况，调用ip_append_data()来添加数据到队列
ip_make_skb
struct sk_buff *ip_make_skb(struct sock *sk,
struct flowi4 *fl4,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
unsigned int flags)
{
struct inet_cork cork;
struct sk_buff_head queue;
int err;
if (flags & MSG_PROBE)
return NULL;
__skb_queue_head_init(&queue);
cork.flags = 0;
cork.addr = 0;
cork.opt = NULL;
err = ip_setup_cork(sk, &cork, ipc, rtp);
if (err)
return ERR_PTR(err);
err = __ip_append_data(sk, fl4, &queue, &cork, //创建添加copy数据到skb， 并放入queue中
¤t->task_frag, getfrag,
from, length, transhdrlen, flags);
if (err) {
__ip_flush_pending_frames(sk, &queue, &cork);
return ERR_PTR(err);
}
return __ip_make_skb(sk, fl4, &queue, &cork); //把queue中所有skb都合并到一个skb及其frag_list中， 并设置好ip头
}
ip_append_data
/*
* ip_append_data() and ip_append_page() can make one large IP datagram
* from many pieces of data. Each pieces will be holded on the socket
* until ip_push_pending_frames() is called. Each piece can be a page
* or non-page data.
*
* Not only UDP, other transport protocols - e.g. raw sockets - can use
* this interface potentially.
*
* LATER: length must be adjusted by pad at tail, when it is required.
*/
int ip_append_data(struct sock *sk, struct flowi4 *fl4,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
struct ipcm_cookie *ipc, struct rtable **rtp,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
int err;
if (flags&MSG_PROBE)
return 0;
if (skb_queue_empty(&sk->sk_write_queue)) {
err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp); //sk_write_queue为空，初始化cork
if (err)
return err;
} else {
transhdrlen = 0;
}
return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, //添加skb到sk_write_queue
sk_page_frag(sk), getfrag,
from, length, transhdrlen, flags);
}
__ip_append_data
- 如果支持UFO则调用ip_ufo_append_data
- 尝试添加到队列sk_write_queue尾部skb，如果head空间够则copy到head，否则根据是否支持sg，创建新的skb或者添加到frag中
static int __ip_append_data(struct sock *sk,
struct flowi4 *fl4,
struct sk_buff_head *queue,
struct inet_cork *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)
{
struct inet_sock *inet = inet_sk(sk);
struct sk_buff *skb;
struct ip_options *opt = cork->opt;
int hh_len;
int exthdrlen;
int mtu;
int copy;
int err;
int offset = 0;
unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
int csummode = CHECKSUM_NONE;
struct rtable *rt = (struct rtable *)cork->dst;
u32 tskey = 0;
skb = skb_peek_tail(queue);
exthdrlen = !skb ? rt->dst.header_len : 0;
mtu = cork->fragsize;
if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
tskey = sk->sk_tskey++;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; //ip包长，8对齐
maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
if (cork->length + length > maxnonfragsize - fragheaderlen) { //超过最大包长
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
mtu - (opt ? opt->optlen : 0));
return -EMSGSIZE;
}
/*
* transhdrlen > 0 means that this is the first fragment and we wish
* it won't be fragmented in the future.
*/
if (transhdrlen && // sizeof(struct udphdr)
length + fragheaderlen <= mtu &&
rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) &&
!(flags & MSG_MORE) &&
!exthdrlen)
csummode = CHECKSUM_PARTIAL; //硬件计算校验和
cork->length += length;
if (((length > mtu) || (skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
(sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { //支持ufo
err = ip_ufo_append_data(sk, queue, getfrag, from, length, //创建ufo skb，添加数据到frag中
hh_len, fragheaderlen, transhdrlen,
maxfraglen, flags);
if (err)
goto error;
return 0;
}
/* So, what's going on in the loop below?
*
* We use calculated fragment length to generate chained skb,
* each of segments is IP fragment ready for sending to network after
* adding appropriate IP header.
*/
//下面是不支持gso/ufo的处理
if (!skb) //队列中没有skb，则需要创建新的
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */ //检查当前skb是否还由空间能copy
copy = mtu - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) { //剩余空间不够，创建新的skb插入
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;
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 > mtu - fragheaderlen)
datalen = maxfraglen - fragheaderlen;
fraglen = datalen + fragheaderlen;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = fraglen;
alloclen += exthdrlen;
/* The last fragment gets additional space at tail.
* Note, with MSG_MORE we overallocate on fragments,
* because we have no idea what fragment will be
* the last.
*/
if (datalen == length + fraggap)
alloclen += rt->dst.trailer_len;
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len + 15,
(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 + 15, 1,
sk->sk_allocation);
if (unlikely(!skb))
err = -ENOBUFS;
}
if (!skb)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
skb_reserve(skb, hh_len);
/* only the initial fragment is time stamped */
skb_shinfo(skb)->tx_flags = cork->tx_flags;
cork->tx_flags = 0;
skb_shinfo(skb)->tskey = tskey;
tskey = 0;
/*
* Find where to start putting bytes.
*/
data = skb_put(skb, fraglen + exthdrlen);
skb_set_network_header(skb, exthdrlen);
skb->transport_header = (skb->network_header +
fragheaderlen);
data += fragheaderlen + 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;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
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(queue, skb); //把新的skb插入队列
continue;
}
if (copy > length)
copy = length;
if (!(rt->dst.dev->features&NETIF_F_SG)) { //不支持sg，copy数据到head区
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy), //ip_generic_getfrag
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else { //支持sg，copy数据到frag
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;
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
return err;
}
ip_ufo_append_data
static inline int ip_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 transhdrlen, int maxfraglen, unsigned int flags)
{
struct sk_buff *skb;
int err;
/* There is support for UDP fragmentation 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, //分配skb空间
hh_len + fragheaderlen + transhdrlen + 20, //这部分在skb head区
(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_reset_network_header(skb);
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
skb->csum = 0;
__skb_queue_tail(queue, skb); //把这个不带数据部分的skb，插入队列中
} else if (skb_is_gso(skb)) {
goto append;
}
skb->ip_summed = CHECKSUM_PARTIAL;
/* specify the length of each IP datagram fragment */
skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
append:
return skb_append_datato_frags(sk, skb, getfrag, from, //copy数据部分到frag
(length - transhdrlen));
}
int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
int (*getfrag)(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length)
{
int frg_cnt = skb_shinfo(skb)->nr_frags;
int copy;
int offset = 0;
int ret;
struct page_frag *pfrag = ¤t->task_frag;
do {
/* Return error if we don't have space for new frag */
if (frg_cnt >= MAX_SKB_FRAGS)
return -EMSGSIZE;
if (!sk_page_frag_refill(sk, pfrag))
return -ENOMEM;
/* copy the user data to page */
copy = min_t(int, length, pfrag->size - pfrag->offset);
ret = getfrag(from, page_address(pfrag->page) + pfrag->offset, //ip_generic_getfrag
offset, copy, 0, skb);
if (ret < 0)
return -EFAULT;
/* copy was successful so update the size parameters */
skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset,
copy);
frg_cnt++;
pfrag->offset += copy;
get_page(pfrag->page);
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
skb->len += copy;
skb->data_len += copy;
offset += copy;
length -= copy;
} while (length > 0);
return 0;
}
int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
struct msghdr *msg = from;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (copy_from_iter(to, len, &msg->msg_iter) != len)
return -EFAULT;
} else {
__wsum csum = 0;
if (csum_and_copy_from_iter(to, len, &csum, &msg->msg_iter) != len)
return -EFAULT;
skb->csum = csum_block_add(skb->csum, csum, odd);
}
return 0;
}