From: Pavel Emelyanov <[EMAIL PROTECTED]>
Date: Fri, 16 Nov 2007 18:06:16 +0300
> Both ipv6/raw.c and ipv4/raw.c use the seq files to walk
> through the raw sockets hash and show them.
>
> The "walking" code is rather huge, but is identical in both
> cases. The difference is the hash table to wal
Both ipv6/raw.c and ipv4/raw.c use the seq files to walk
through the raw sockets hash and show them.
The "walking" code is rather huge, but is identical in both
cases. The difference is the hash table to walk over and
the protocol family to check (this was not in the first
virsion of the patch, wh
YOSHIFUJI Hideaki wrote:
> NAK.
>
> In article <[EMAIL PROTECTED]> (at Fri, 16 Nov 2007 17:19:27 +0300), Pavel
> Emelyanov <[EMAIL PROTECTED]> says:
>
>> @@ -858,7 +852,7 @@ static struct sock *raw_get_first(struct seq_file *seq)
>> ++state->bucket) {
>> struct
NAK.
In article <[EMAIL PROTECTED]> (at Fri, 16 Nov 2007 17:19:27 +0300), Pavel
Emelyanov <[EMAIL PROTECTED]> says:
> @@ -858,7 +852,7 @@ static struct sock *raw_get_first(struct seq_file *seq)
> ++state->bucket) {
> struct hlist_node *node;
>
> -
Both ipv6/raw.c and ipv4/raw.c use the seq files to
walk through the raw sockets hash and show them.
The "walking" code is rather huge, but is identical
in both cases. The difference is the hash table to
walk over.
Make the ->open store the needed hash table on the
allocated raw_iter_state and m
