Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[IPV4\/IPV6\]\s+Keep\s+wmem\s+accounting\s+separate\s+in\s+ip\*_push_pending

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[IPV4\/IPV6\]\s+Keep\s+wmem\s+accounting\s+separate\s+in\s+ip\*_push_pending_frames\s*$/: 20 ]

Total 20 documents matching your query.

1. [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: x>; Date: Sun, 15 May 2005 20:40:16 +1000; Here is a patch that addresses the first issue. Since frag_list skb's constructed by ip*_push_pending_frames are usually going to be fragmented in ip*_fragment and sent separately, it makes no sense; /archives/netdev/2005-05/msg00538.html (11,417 bytes)
2. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: u <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Sun, 15 May 2005 21:41:21 +1000; Please discard this patch. Unfortunately this leads to nightmares with partially cloned frag skb's. The reason is that once you unleash a skb with a frag_list that has individual sk ownerships into t; /archives/netdev/2005-05/msg00539.html (11,591 bytes)
3. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Jeff Garzik <jgarzik@xxxxxxxxx>; Date: Sun, 15 May 2005 15:24:41 -0700 (PDT); Yes, I was just about to inform you that when SKBs are free'd up, only the head SKB's sk gets the destructor run on it. Please refer to this patch from July of 2004: [IPV4]: Fix multicast socket hang; /archives/netdev/2005-05/msg00559.html (12,102 bytes)
4. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Jeff Garzik <jgarzik@xxxxxxxxx>; Date: Mon, 16 May 2005 09:20:20 +1000; Dave, I'm actually agreeing with you :) My patch does these two things: 1) Do what you did below for IPv4 to IPv6 as well. 2) Do what the comment (the one that you removed below) said and actually un; /archives/netdev/2005-05/msg00562.html (12,623 bytes)
5. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: u <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Mon, 16 May 2005 09:59:13 +1000; Actually that turns out to be OK since ip_ct_gather_frags zeros the been reassembled it tries to put the sk back which fails unless the head skb comes in last which is never the case on the output pa; /archives/netdev/2005-05/msg00563.html (11,349 bytes)
6. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: u <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Sun, 15 May 2005 17:32:42 -0700 (PDT); No objections, I see what you are doing now. It is basically the inverse of the case where we hold the frag truesizes in the head SKB. Once we rip apart the fraglist, we have to repropagate the trues; /archives/netdev/2005-05/msg00564.html (10,416 bytes)
7. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: . Miller" <davem@xxxxxxxxxxxxx>; Date: Sun, 15 May 2005 17:39:44 -0700 (PDT); This code should therefore just skb_orphan(), and nothing more. Right?; /archives/netdev/2005-05/msg00565.html (10,484 bytes)
8. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: . Miller" <davem@xxxxxxxxxxxxx>; Date: Mon, 16 May 2005 11:00:58 +1000; Ideally we should move the ownership to the head skb here as well. However, doing this would cause havoc when you have nasty users sending fragments from two different sockets :) So let's stick with; /archives/netdev/2005-05/msg00566.html (10,806 bytes)
9. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 19 May 2005 12:35:30 -0700 (PDT); [ For other readers, Herbert and I are discussing ip_ct_gather_frags(). ] Ok, based upon this I am adding the following patch to my tree. Thanks. -- 1/net/ipv4/netfilter/ip_conntrack_core.c.~1~ 2005-; /archives/netdev/2005-05/msg00777.html (11,578 bytes)
10. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: xxxxxxx>; Date: Fri, 20 May 2005 07:48:38 +1000; Thanks Dave, this looks good to me. -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@xxxxxxxxxxxxxxxxxxx> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: h; /archives/netdev/2005-05/msg00794.html (12,097 bytes)
11. [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Sun, 15 May 2005 20:40:16 +1000; Here is a patch that addresses the first issue. Since frag_list skb's constructed by ip*_push_pending_frames are usually going to be fragmented in ip*_fragment and sent separately, it makes no sense; /archives/netdev/2005-05/msg01827.html (11,541 bytes)
12. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Sun, 15 May 2005 21:41:21 +1000; Please discard this patch. Unfortunately this leads to nightmares with partially cloned frag skb's. The reason is that once you unleash a skb with a frag_list that has individual sk ownerships into t; /archives/netdev/2005-05/msg01828.html (11,750 bytes)
13. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Sun, 15 May 2005 15:24:41 -0700 (PDT); Yes, I was just about to inform you that when SKBs are free'd up, only the head SKB's sk gets the destructor run on it. Please refer to this patch from July of 2004: [IPV4]: Fix multicast socket hang; /archives/netdev/2005-05/msg01848.html (12,215 bytes)
14. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Mon, 16 May 2005 09:20:20 +1000; Dave, I'm actually agreeing with you :) My patch does these two things: 1) Do what you did below for IPv4 to IPv6 as well. 2) Do what the comment (the one that you removed below) said and actually un; /archives/netdev/2005-05/msg01851.html (12,830 bytes)
15. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Mon, 16 May 2005 09:59:13 +1000; Actually that turns out to be OK since ip_ct_gather_frags zeros the been reassembled it tries to put the sk back which fails unless the head skb comes in last which is never the case on the output pa; /archives/netdev/2005-05/msg01852.html (11,577 bytes)
16. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Sun, 15 May 2005 17:32:42 -0700 (PDT); No objections, I see what you are doing now. It is basically the inverse of the case where we hold the frag truesizes in the head SKB. Once we rip apart the fraglist, we have to repropagate the trues; /archives/netdev/2005-05/msg01853.html (10,545 bytes)
17. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Sun, 15 May 2005 17:39:44 -0700 (PDT); This code should therefore just skb_orphan(), and nothing more. Right?; /archives/netdev/2005-05/msg01854.html (10,613 bytes)
18. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Mon, 16 May 2005 11:00:58 +1000; Ideally we should move the ownership to the head skb here as well. However, doing this would cause havoc when you have nasty users sending fragments from two different sockets :) So let's stick with; /archives/netdev/2005-05/msg01855.html (11,028 bytes)
19. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 19 May 2005 12:35:30 -0700 (PDT); [ For other readers, Herbert and I are discussing ip_ct_gather_frags(). ] Ok, based upon this I am adding the following patch to my tree. Thanks. -- 1/net/ipv4/netfilter/ip_conntrack_core.c.~1~ 2005-; /archives/netdev/2005-05/msg02066.html (11,707 bytes)
20. Re: [IPV4/IPV6] Keep wmem accounting separate in ip*_push_pending_frames (score: 1): Author: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Fri, 20 May 2005 07:48:38 +1000; Thanks Dave, this looks good to me. -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@xxxxxxxxxxxxxxxxxxx> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: h; /archives/netdev/2005-05/msg02083.html (12,317 bytes)

Current List: 1 - 20
Page: [1]