The network driver uses two virtqueues: one for input packets and one
for output packets. This has nice locking properties (ie. we don't do
any for recv vs send).
TODO:
1) Big packets.
2) Multi-client devices (maybe separate driver?).
3) Resolve freeing of old xmit skbs (C
Ok the rebase is complete and I integrated all of the
"easy" stuff in my backlog. In the usual spot:
kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6.git
John, one patch didn't go in cleanly after I removed the
Z1211 driver. I put it here for your consideration so it
doesn't get lost
From: Vlad Yasevich <[EMAIL PROTECTED]>
Date: Mon, 24 Sep 2007 16:59:25 -0400
> Can you please pull the following changes since commit
> a41d3015c11a4e864b95cb57f579f2d8f40cd41b:
I had to apply this by hand because:
> David S. Miller (1):
> Revert "PCI: disable MSI by default on syste
From: "Ilpo_Järvinen" <[EMAIL PROTECTED]>
Date: Mon, 24 Sep 2007 12:04:08 +0300
> Signed-off-by: Ilpo Järvinen <[EMAIL PROTECTED]>
This also looks fine, applied, thanks!
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordom
From: "Ilpo_Järvinen" <[EMAIL PROTECTED]>
Date: Mon, 24 Sep 2007 12:04:07 +0300
> In case of ACK reordering, the SACK block might be valid in it's
> time but is already obsoleted since we've received another kind
> of confirmation about arrival of the segments through snd_una
> advancement of an e
From: "Ilpo_Järvinen" <[EMAIL PROTECTED]>
Date: Mon, 24 Sep 2007 12:04:06 +0300
> I previously added checking to position that is rather poor as
> state has already been adjusted quite a bit. Re-placing it above
> all state changes should be more robust though the return should
> never ever get ex
From: "John W. Linville" <[EMAIL PROTECTED]>
Date: Sat, 22 Sep 2007 15:54:57 -0400
> The individual patches are available here:
>
>
> http://www.kernel.org/pub/linux/kernel/people/linville/wireless-2.6/upstream-davem/
I sucked these into my net-2.6.24 tree, thanks John.
It may look sligh
On Wed, 26 Sep 2007 11:18:39 +0800
Herbert Xu <[EMAIL PROTECTED]> wrote:
> Stephen Hemminger <[EMAIL PROTECTED]> wrote:
> > The bug http://bugzilla.kernel.org/show_bug.cgi?id=5731
> > describes an issue where write() can't be used to generate a zero-length
> > datagram (but send, and sendto do wor
David Miller wrote:
From: Joe Perches <[EMAIL PROTECTED]>
Date: Tue, 25 Sep 2007 21:36:38 -0700
On Tue, 2007-09-25 at 19:29 -0700, David Miller wrote:
I'm going to hold on this for now, there is no universal
agreement that this is something we want to do and I'd
like to take care of getting th
From: Joe Perches <[EMAIL PROTECTED]>
Date: Tue, 25 Sep 2007 21:36:38 -0700
> On Tue, 2007-09-25 at 19:29 -0700, David Miller wrote:
> > I'm going to hold on this for now, there is no universal
> > agreement that this is something we want to do and I'd
> > like to take care of getting the more cer
On Tue, 2007-09-25 at 19:29 -0700, David Miller wrote:
> I'm going to hold on this for now, there is no universal
> agreement that this is something we want to do and I'd
> like to take care of getting the more certain stuff into
> net-2.6.24 before "iffy" bits like this one.
Here's an argument fo
Stephen Hemminger <[EMAIL PROTECTED]> wrote:
> The bug http://bugzilla.kernel.org/show_bug.cgi?id=5731
> describes an issue where write() can't be used to generate a zero-length
> datagram (but send, and sendto do work).
>
> I think the following is needed:
>
> --- a/net/socket.c 2007-08-20
From: "John W. Linville" <[EMAIL PROTECTED]>
Date: Sat, 22 Sep 2007 11:41:42 -0400
> These are a few more minor fixes that I would like to have in 2.6.23 if
> at all possible.
I've pulled these into my net-2.6 tree and will push to
Linus, thanks!
-
To unsubscribe from this list: send the line "un
From: Herbert Xu <[EMAIL PROTECTED]>
Date: Sat, 22 Sep 2007 08:57:10 +0800
> On Fri, Sep 21, 2007 at 04:59:54PM +0200, Christian Borntraeger wrote:
> >
> > I suggest to document that LLTX is deprecated.
> >
> > Signed-off-by: Christian Borntraeger <[EMAIL PROTECTED]>
>
> This looks good to me.
From: "John W. Linville" <[EMAIL PROTECTED]>
Date: Thu, 20 Sep 2007 21:34:03 -0400
> On Fri, Sep 21, 2007 at 09:20:30AM +0800, Zhu Yi wrote:
> > On Wed, 2007-09-19 at 11:13 +0100, Christoph Hellwig wrote:
> > > it really needs to be moved into a directory of it's own.
> >
> > It used to be... Joh
From: Jeff Garzik <[EMAIL PROTECTED]>
Date: Thu, 20 Sep 2007 16:58:43 -0400
> [EMAIL PROTECTED] wrote:
> > From: Andrew Morton <[EMAIL PROTECTED]>
> >
> > Revert git-netdev-all's 9ee6b32a47b9abc565466a9c3b127a5246b452e5. Michal
> > was
> > getting oopses.
> >
> > Cc: Michal Piotrowski <[EMAIL
From: jamal <[EMAIL PROTECTED]>
Date: Wed, 19 Sep 2007 22:43:03 -0400
> [NET_SCHED] explict hold dev tx lock
>
> For N cpus, with full throttle traffic on all N CPUs, funneling traffic
> to the same ethernet device, the devices queue lock is contended by all
> N CPUs constantly. The TX lock is on
From: Joe Perches <[EMAIL PROTECTED]>
Date: Wed, 19 Sep 2007 23:53:31 -0700
> In the same vein as print_mac, the implementations
> introduce declaration macros:
I'm going to hold on this for now, there is no universal
agreement that this is something we want to do and I'd
like to take care of get
From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Fri, 24 Aug 2007 13:43:10 -0700
> The follow patches series starts the process of moving function
> pointers out of network device structure. This saves space and
> separates code from data.
>
> The first step is moving the functions dealing with
From: [EMAIL PROTECTED] (Eric W. Biederman)
Date: Mon, 17 Sep 2007 20:44:14 -0600
> David Miller <[EMAIL PROTECTED]> writes:
>
> > From: "Peter Waskiewicz" <[EMAIL PROTECTED]>
> > Date: Mon, 17 Sep 2007 12:12:24 -0700
> >
> >> This would be a good opportunity to remove the single-allocated queue
Jamal & Stephen,
I found BSS-hash paper you mentioned and have browsed it briefly.
The issue "may end sending all your packets to one cpu" might be dealt with
by
cpu hash (srcip + dstip) % nr_cpus, plus checking cpu balance periodically,
shift cpu by an extra seed value?
Any way, the cpu hash cod
Signed-off-by: Al Viro <[EMAIL PROTECTED]>
---
drivers/net/mv643xx_eth.c |2 --
1 files changed, 0 insertions(+), 2 deletions(-)
diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c
index 6a117e9..456d1e1 100644
--- a/drivers/net/mv643xx_eth.c
+++ b/drivers/net/mv643xx_eth.c
@@
On Tue, 2007-25-09 at 18:15 -0400, jamal wrote:
> A further optimization i made was to reduce the time it takes to hold
> the tx lock at the driver by moving gunk that doesnt need lock-holding
> into the new method dev->hard_end_xmit() (refer to patch #2)
Sorry, that should have read dev->hard_pr
On Tue, 2007-25-09 at 13:16 -0700, Randy Dunlap wrote:
> On Mon, 24 Sep 2007 18:54:19 -0400 jamal wrote:
>
> > I have updated the driver howto to match the patches i posted yesterday.
> > attached.
>
> Thanks for sending this.
Thank you for reading it Randy.
> This is an early draft, right?
On Tue, 2007-25-09 at 09:03 -0700, Stephen Hemminger wrote:
> There is a standard hash called RSS, that many drivers support because it is
> used by other operating systems.
I think any stateless/simple thing will do (something along the lines
what 802.1ad does for trunk, a 5 classical five tupl
On Tue, 2007-25-09 at 08:24 -0700, Stephen Hemminger wrote:
> The transmit code path is locked as a code region, rather than just object
> locking
> on the transmit queue or other fine grained object. This leads to moderately
> long
> lock hold times when multiple qdisc's and classification is b
From: Urs Thuermann <[EMAIL PROTECTED]>
Date: 25 Sep 2007 23:00:15 +0200
> Stephen Hemminger <[EMAIL PROTECTED]> writes:
>
> > Then please make all exported symbols marked EXPORT_SYMBOL_GPL to make
> > sure that the other CAN protocol can not reuse your infrastructure.
>
> We don't want to force
I just got back from some travelling this past weekend, so
what I'm going to do today is:
1) Rebase net-2.6.24, that's what I'm doing right now.
I'll be combining bug fixes for feature patches as
much as possible, so this might take most if not all
of this afternoon.
2) After the rebase
On 25 Sep 2007 23:00:15 +0200
Urs Thuermann <[EMAIL PROTECTED]> wrote:
> Stephen Hemminger <[EMAIL PROTECTED]> writes:
>
> > Then please make all exported symbols marked EXPORT_SYMBOL_GPL to
> > make sure that the other CAN protocol can not reuse your
> > infrastructure.
>
> We don't want to for
Stephen Hemminger <[EMAIL PROTECTED]> writes:
> Then please make all exported symbols marked EXPORT_SYMBOL_GPL to make
> sure that the other CAN protocol can not reuse your infrastructure.
We don't want to force other CAN protocol implementations to be GPL
also. AFAIR from discussions on LKML, i
On Mon, 24 Sep 2007 18:54:19 -0400 jamal wrote:
> I have updated the driver howto to match the patches i posted yesterday.
> attached.
Thanks for sending this.
This is an early draft, right?
I'll fix some typos etc. in it (patch attached) and add some whitespace.
Please see RD: in the patch fo
These two wireless fixes are IN ADDITION to the previously submitted
fixes. Same linear history. In other words, if you pull
"upstream-linus", you will get both the changes below, _and_ the changes
I submitted yesterday. If you have already pulled yesterday's fixes,
then you will only receive t
On Tue, 25 Sep 2007 22:00:48 +0400
Evgeniy Polyakov <[EMAIL PROTECTED]> wrote:
> Hi.
>
> I've released new version of the extremely small
> userspace netowork stack [1] implementation.
> Stack supports TCP and UDP over IP.
> It works on top of netchannels [2] or packet socket
> (returned back i
Evgeniy,
On 9/25/07, Evgeniy Polyakov <[EMAIL PROTECTED]> wrote:
> I've released new version of the extremely small
> userspace netowork stack [1] implementation.
>
> 1. Userspace network stack.
> http://tservice.net.ru/~s0mbre/old/?section=projects&item=unetstack
>
> 2. Netchannel subsystem.
>
Patrick McHardy wrote:
>
> Yoshifuji's point was that the license seems to contradict itself,
> it says you may choose GPL, but have to retain BSD. And that is
> not about Dual BSD/GPL but about the specific wording.
>
Got it (finally)!
Trying to specify the GPL Version (and the reference to t
Oliver Hartkopp wrote:
I do think you need to allow people to select GPLv2 only.
>>>
> The Linux Kernel is currently under GPLv2 and we just wanted to follow
> Linus' mind and so we referenced the COPYING file which many other
> source does as well. Indeed it was a hard thing to make
Hi.
I've released new version of the extremely small
userspace netowork stack [1] implementation.
Stack supports TCP and UDP over IP.
It works on top of netchannels [2] or packet socket
(returned back in this release).
Supported features:
* TCP/UDP sending and receiving.
* Times
Patrick McHardy wrote:
> Urs Thuermann wrote:
>
>> YOSHIFUJI Hideaki / È£ÑÀ <[EMAIL PROTECTED]> writes:
>>
>>
>>
>>> I'm not a lawyer, but the following lines:
>>>
>>> | + * Alternatively, provided that this notice is retained in full, this
>>> ~
Stephen Hemminger wrote:
On Tue, 25 Sep 2007 06:07:24 +0200
Patrick McHardy <[EMAIL PROTECTED]> wrote:
I meant removing brnf_sysctl_call_tables function, not the sysctls
themselves, all it does is change values != 0 to 1. Or did you
actually mean that something in userspace might depend on r
On Tue, 25 Sep 2007 14:18:17 +0100 Ralf Baechle <[EMAIL PROTECTED]> wrote:
> On Fri, Sep 21, 2007 at 12:44:09PM -0700, Andrew Morton wrote:
>
> > > A driver model and phylib update.
> >
> > akpm:/usr/src/25> diffstat patches/git-net.patch | tail -n 1
> > 1013 files changed, 187667 insertions(+
On Tue, 25 Sep 2007 18:23:58 +0530 Kamalesh Babulal <[EMAIL PROTECTED]> wrote:
> Hi Andrew,
>
> The drivers/net/ibm_newemac/mal seems to be broken, which stop with
> build error
(please cc netdev@vger.kernel.org on networking things)
> CC drivers/net/ibm_newemac/mal.o
> drivers/net/ibm_new
On Tue, 25 Sep 2007 06:07:24 +0200
Patrick McHardy <[EMAIL PROTECTED]> wrote:
> Stephen Hemminger wrote:
> > On Mon, 24 Sep 2007 18:55:38 +0200
> > Patrick McHardy <[EMAIL PROTECTED]> wrote:
> >
> >>Eric W. Biederman wrote:
> >>
> >>>A really good fix would be to remove the binary side and then t
On Tue, 25 Sep 2007 23:36:25 +0800
"john ye" <[EMAIL PROTECTED]> wrote:
> Jamal,
>
> You pointed out a key point: it's NOT acceptable if massive packet
> re-ordering couldn¡¯t be avoided.
> I debugged function tcp_ofo_queue in net/ipv4/tcp_input.c & monitored
> out_of_order_queue, found that re
> Roland, are you comfortable with the IB changes in patches 1 and 2?
Yes, they look fine to me. Feel free to apply, with
Acked-by: Roland Dreier <[EMAIL PROTECTED]>
- R.
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
Mor
Jamal,
You pointed out a key point: it's NOT acceptable if massive packet re-ordering
couldn¡¯t be avoided.
I debugged function tcp_ofo_queue in net/ipv4/tcp_input.c & monitored
out_of_order_queue, found that re-ordering
becomes unacceptable with the softirq load grows.
It's simple to avoid out
On 25 Sep 2007 15:24:33 +0200
Urs Thuermann <[EMAIL PROTECTED]> wrote:
> Arnaldo Carvalho de Melo <[EMAIL PROTECTED]> writes:
>
> > > + skb_queue_purge(&sk->sk_receive_queue);
> > > + if (sk->sk_protinfo)
> > > + kfree(sk->sk_protinfo);
> > > +}
> >
> > Is it really needed to do this sk_
On Tue, 25 Sep 2007 09:15:38 -0400
jamal <[EMAIL PROTECTED]> wrote:
> On Mon, 2007-24-09 at 17:14 -0700, Stephen Hemminger wrote:
>
> > Since we are redoing this,
> > is there any way to make the whole TX path
> > more lockless? The existing model seems to be more of a monitor than
> > a real l
ACK patches 3 - 9.
Roland, are you comfortable with the IB changes in patches 1 and 2?
Jeff, when Roland acks patches 1 and 2, please apply all 9.
-J
---
-Jay Vosburgh, IBM Linux Technology Center, [EMAIL PROTECTED]
Moni Shoua <[EMAIL PROTECTED]> wrote:
>This
Urs Thuermann wrote:
> YOSHIFUJI Hideaki / È£ÑÀ <[EMAIL PROTECTED]> writes:
>
>
>>I'm not a lawyer, but the following lines:
>>
>>| + * Alternatively, provided that this notice is retained in full, this
>> ~~
>>| + * software may be
YOSHIFUJI Hideaki / È£ÑÀ <[EMAIL PROTECTED]> writes:
> I'm not a lawyer, but the following lines:
>
> | + * Alternatively, provided that this notice is retained in full, this
> ~~
> | + * software may be distributed under the terms
Arnaldo Carvalho de Melo <[EMAIL PROTECTED]> writes:
> > + skb = alloc_skb(CFSIZ,
> > + in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
>
> We have gfp_any() for this:
Ah, ok. That looks better. Applied.
urs
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
Arnaldo Carvalho de Melo <[EMAIL PROTECTED]> writes:
> > + skb_queue_purge(&sk->sk_receive_queue);
> > + if (sk->sk_protinfo)
> > + kfree(sk->sk_protinfo);
> > +}
>
> Is it really needed to do this sk_protinfo check?
Thanks for finding this. This is from 2.6.12 times or so. We ha
Hello.
In article <[EMAIL PROTECTED]> (at Tue, 25 Sep 2007 14:20:34 +0200), Urs
Thuermann <[EMAIL PROTECTED]> says:
> Index: net-2.6.24/drivers/net/can/vcan.c
> ===
> --- /dev/null 1970-01-01 00:00:00.0 +
> +++ net-2.6.2
On Fri, Sep 21, 2007 at 12:44:09PM -0700, Andrew Morton wrote:
> > A driver model and phylib update.
>
> akpm:/usr/src/25> diffstat patches/git-net.patch | tail -n 1
> 1013 files changed, 187667 insertions(+), 23587 deletions(-)
>
> Sorry, but raising networking patches against Linus's crufty
On Mon, 2007-24-09 at 17:14 -0700, Stephen Hemminger wrote:
> Since we are redoing this,
> is there any way to make the whole TX path
> more lockless? The existing model seems to be more of a monitor than
> a real locking model.
What do you mean it is "more of a monitor"?
On the challenge of m
On Mon, 2007-24-09 at 16:47 -0700, Waskiewicz Jr, Peter P wrote:
> We should make sure we're symmetric with the locking on enqueue to
> dequeue. If we use the single device queue lock on enqueue, then
> dequeue will also need to check that lock in addition to the individual
> queue lock. The det
Em Tue, Sep 25, 2007 at 02:20:33PM +0200, Urs Thuermann escreveu:
> This patch adds the CAN broadcast manager (bcm) protocol.
>
> +static void bcm_can_tx(struct bcm_op *op)
> +{
> + skb = alloc_skb(CFSIZ,
> + in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
We have gfp_any() for
Em Tue, Sep 25, 2007 at 02:20:31PM +0200, Urs Thuermann escreveu:
> +
> +static void can_sock_destruct(struct sock *sk)
> +{
> + DBG("called for sock %p\n", sk);
> +
> + skb_queue_purge(&sk->sk_receive_queue);
> + if (sk->sk_protinfo)
> + kfree(sk->sk_protinfo);
> +}
Is it
This patch adds documentation for the PF_CAN protocol family.
Signed-off-by: Oliver Hartkopp <[EMAIL PROTECTED]>
Signed-off-by: Urs Thuermann <[EMAIL PROTECTED]>
---
Documentation/networking/00-INDEX |2
Documentation/networking/can.txt | 634 ++
2 file
This patch adds a protocol/address family number, ARP hardware type,
ethernet packet type, and a line discipline number for the SocketCAN
implementation.
Signed-off-by: Oliver Hartkopp <[EMAIL PROTECTED]>
Signed-off-by: Urs Thuermann <[EMAIL PROTECTED]>
---
include/linux/if_arp.h |1 +
inc
This patch adds the CAN broadcast manager (bcm) protocol.
Signed-off-by: Oliver Hartkopp <[EMAIL PROTECTED]>
Signed-off-by: Urs Thuermann <[EMAIL PROTECTED]>
---
include/linux/can/bcm.h | 65 +
net/can/Kconfig | 13
net/can/Makefile|3
net/can/bcm.c | 1778 +++
This patch adds the virtual CAN bus (vcan) network driver.
The vcan device is just a loopback device for CAN frames, no
real CAN hardware is involved.
Signed-off-by: Oliver Hartkopp <[EMAIL PROTECTED]>
Signed-off-by: Urs Thuermann <[EMAIL PROTECTED]>
---
drivers/net/Makefile |1
drivers
This patch adds the CAN raw protocol.
Signed-off-by: Oliver Hartkopp <[EMAIL PROTECTED]>
Signed-off-by: Urs Thuermann <[EMAIL PROTECTED]>
---
include/linux/can/raw.h | 31 +
net/can/Kconfig | 11
net/can/Makefile|3
net/can/raw.c | 822 +++
This patch adds entries in the CREDITS and MAINTAINERS file for CAN.
Signed-off-by: Oliver Hartkopp <[EMAIL PROTECTED]>
Signed-off-by: Urs Thuermann <[EMAIL PROTECTED]>
---
CREDITS | 16
MAINTAINERS |9 +
2 files changed, 25 insertions(+)
Index: net-2.6.24/CRE
Hello Dave, hello Patrick,
this is the eigth post of the patch series that adds the PF_CAN
protocol family for the Controller Area Network.
Since our last post we have changed the following:
* Some changes in debug code, following suggestions from Joe Perches:
- Remove dynamically allocated bu
Jay,
I think that all comments to the patches were discussed and handled.
If you agree, can you please push then to the networking tree so they will be
merged into 2.6.24?
This includes the IPoIB patches (agreed with Roland).
Note that there are *no* patches to net/core (like in V5).
thanks
Moni
>
> Please get rid of the warning. Make bonding work correctly and allow
> enslave/remove
> of device when bonding is down.
> -
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to [EMAIL PROTECTED]
> More majordomo info at http://vger.kernel.org/maj
Hi Tomo,
FUJITA Tomonori wrote:
> On Sat, 8 Sep 2007 13:00:36 +0100
> Christoph Hellwig <[EMAIL PROTECTED]> wrote:
>
>> On Sat, Sep 08, 2007 at 07:32:27AM -0400, Jeff Garzik wrote:
>>> FUJITA Tomonori wrote:
Yeah, iommu code ignores the lld limitations (the problem is that the
lld limit
68 matches
Mail list logo
