1__SKB_TRY_RECV_DATAG(9)        Linux Networking        __SKB_TRY_RECV_DATAG(9)
2
3
4

NAME

6       __skb_try_recv_datagram - Receive a datagram skbuff
7

SYNOPSIS

9       struct sk_buff * __skb_try_recv_datagram(struct sock * sk,
10                                                unsigned int flags,
11                                                void (*destructor) (struct sock *sk, struct sk_buff *skb),
12                                                int * peeked, int * off,
13                                                int * err,
14                                                struct sk_buff ** last);
15

ARGUMENTS

17       sk
18           socket
19
20       flags
21           MSG_ flags
22
23       destructor
24           invoked under the receive lock on successful dequeue
25
26       peeked
27           returns non-zero if this packet has been seen before
28
29       off
30           an offset in bytes to peek skb from. Returns an offset within an
31           skb where data actually starts
32
33       err
34           error code returned
35
36       last
37           set to last peeked message to inform the wait function what to look
38           for when peeking
39

DESCRIPTION

41       Get a datagram skbuff, understands the peeking, nonblocking wakeups and
42       possible races. This replaces identical code in packet, raw and udp, as
43       well as the IPX AX.25 and Appletalk. It also finally fixes the long
44       standing peek and read race for datagram sockets. If you alter this
45       routine remember it must be re-entrant.
46
47       This function will lock the socket if a skb is returned, so the caller
48       needs to unlock the socket in that case (usually by calling
49       skb_free_datagram). Returns NULL with *err set to -EAGAIN if no data
50       was available or to some other value if an error was detected.
51
52       * It does not lock socket since today. This function is * free of race
53       conditions. This measure should/can improve * significantly datagram
54       socket latencies at high loads, * when data copying to user space takes
55       lots of time. * (BTW I've just killed the last cli in
56       IP/IPv6/core/netlink/packet * 8) Great win.) * --ANK (980729)
57
58       The order of the tests when we find no data waiting are specified quite
59       explicitly by POSIX 1003.1g, don't change them without having the
60       standard around please.
61

63Kernel Hackers Manual 3.10         June 2019           __SKB_TRY_RECV_DATAG(9)
Impressum