This patch properly defines the maximum values for rx/tx coalescing timeouts. Signed-off-by: Vlad Zolotarov <vladz@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> --- drivers/net/bnx2x.h | 2 ++ drivers/net/bnx2x_main.c | 8 ++++---- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h index 8678457..85a737c 100644 --- a/drivers/net/bnx2x.h +++ b/drivers/net/bnx2x.h @@ -902,6 +902,8 @@ struct bnx2x ...

yYETKg http://love22.nm.ru --

> From: Yeasah Pell <yeasah@comrex.com> Add checksum offload support for DM9000A and DM9000B chips. -- v2 changes: added a local copy of ip_summed to save IO cycles in dm9000_send_packet Signed-off-by: Yeasah Pell <yeasah@comrex.com> Signed-off-by: Mike Rapoport <mike@compulab.co.il> --- drivers/net/dm9000.c | 109 ++++++++++++++++++++++++++++++++++++++++++-------- drivers/net/dm9000.h | 18 ++++++++ 2 files changed, 110 insertions(+), 17 deletions(-) diff --git a/...

Not really. For now the best thing to do is to pin everything down and not move at all, because we can't afford to move. The only way for moving to work is if we had the ability to get the sockets to follow the processes. That means, we must have one RX queue per socket. Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: [ message continues ]

Maybe not one RX queue per socket -- sockets belonging to the same thread could share the same RX queue. I'm fairly ignorant of the way networking works these days; is it possible to dynamically reassign a socket between RX queues, so we'd only need one RX queue per CPU? It seems the 82575 device has four queues per port, and it's a dual-port card, so that's eight queues in the system. We'd need hundreds of queues to get one queue per client process. The 82576 has sixteen queues per port, but ...

I understand that most drivers use request_firmware() to load volatile firmware. I do see that there are other nic drivers that use this inferface to flash persistent firmware. We have other tools for offline flashing; but there is requirement to flash f/w through driver without having to use other proprietary tools. Since the firmware load happens only when there is a version mismatch with f/w in /lib/firmware, Users who want to avoid automatic flashing at boot time can choose not to copy the ...

I don't know about the DMA error but this is perfectly normal. You're invoking netpoll from within the NIC's xmit routine, that's why the trylock fails. So I guess you should fix spinlock debugging instead :) Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt --

(Take 2: Changelog spelling fixes, sorry.) David & Robert, below are my recommendations for -stable plus one more patch: On Sun, Jul 05, 2009 at 02:26:54AM +0200, Paweł Staszewski wrote: So after these patches from net-2.6 are tested both for PREEMPT and PREEMPT_NONE I think they should go to -stable: 2.6.30 needs: ------------- commit e0f7cb8c8cc6cccce28d2ce39ad8c60d23c3799f Author: Jarek Poplawski <jarkao2@gmail.com> Date: Mon Jun 15 02:31:29 2009 -0700 ipv4: Fix fi...

Sorry again no attachement. Pawe

Probably non-preempt kernel might need something like this more, but comparing is always interesting. This patch is based on Paul's suggestion (I hope). Thanks, Jarek P. ---> (synchronize take 7; apply on top of the 2.6.29.x with the last all-in-one patch, or net-2.6) net/ipv4/fib_trie.c | 8 ++++++++ 1 files changed, 8 insertions(+), 0 deletions(-) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 00a54b2..fce8238 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_tr...

Looks like a promising approach to me! --

kernel 2.6.29.5 preempt bgp starts normal and kernel know routes normaly like without patch Here are some fib_triestats cat /proc/net/fib_triestat Basic info: size of leaf: 20 bytes, size of tnode: 36 bytes. Main: Aver depth: 2.44 Max depth: 6 Leaves: 277888 Prefixes: 291399 Internal nodes: 66818 1: 33080 2: 14584 3: 10788 4: 4911 5: 2185 6: 900 7: 366 8: 3 17: 1 Pointers: 595584 Null ptrs: 250879 To...

What uses skb_mac_header_was_set apart from a debugging printk in route.c and nfnetlink_log (which is also essentially a debugging printk)? This seems to be a bit much just to make a couple printks work? What about using mac_len instead to figure out whether the MAC header is there? Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: [ message continues ]

From: Herbert Xu <herbert@gondor.apana.org.au> type and code should both be "u8"'s, we made a similar conversio of a family of ipv6 function arguments recently. Actually, it's already there and done to this very function. Herbert, this is just an ancient patch that has been superceded by the very change you are suggestions :-) --

Methinks this whole idea is doomed. The fact is as long as there are more sockets than queues, then you can have two sockets pull the same queue in different directions and there's nothing you can do about that. That's my bit of uncertainty for you :) Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt --

Here's a another crazy idea: Let's use dummy TX descriptors to generate an interrupt, either with or without transmitting an actual packet on the wire depending on the NIC. xmit(skb) if (TX queue contains no interrupting descriptor && qdisc is empty) mark TX descriptor as interrupting clean() do work if (TX queue contains no interrupting descriptor && TX queue non-empty && qdisc is empty) send dummy TX descriptor This is based on the ...

Signed-off-by: Ken Kawasaki <ken_kawasaki@spring.nifty.jp> --- --- linux-2.6.31-rc1/drivers/net/pcmcia/pcnet_cs.c.orig 2009-06-27 10:15:47.000000000 +0900 +++ linux-2.6.31-rc1/drivers/net/pcmcia/pcnet_cs.c 2009-07-04 10:32:44.000000000 +0900 @@ -886,9 +886,10 @@ static void write_asic(unsigned int ioad outb_p(EE_ASIC|EE_CS|EE_DI|dataval, ee_addr); } // sync - outb(EE_ASIC|EE_CS, ee_addr); - outb(EE_ASIC|EE_CS|EE_CK, ee_addr); - outb(EE_ASIC|EE_CS, ee_addr); + dataval = (locat...

On Tue, 30 Jun 2009 07:19:55 -0700 (PDT) Sorry, I cancel the use_shmem patch. (for re-test). Ken. --

On Sat, 04 Jul 2009 17:07:11 -0700 A misconfiguration if you don't intend it, otherwise, isolation between subnets on a common link can be useful. I've taken advantage of it in networking test labs. It can also be useful for basic traffic engineering. You set up two routers attached to the same link, but both with different configured prefixes. Nodes are assigned adresses out of one or the other prefix, to influence which outbound (and inbound) path their traffic takes. Leaving it like that wou...