Zhao Xiaoming wrote:
The latest update:
It seems that Linux kernel memory management mechanisms including
buddy and slab algorisms are not very efficient under my test
conditions that tcp stack requires a lot of (hundreds of MB) packet
buffers and release them very frequently.
Here
The way to get the next protocol number of an IPv6 tunnel changes
after introducing IP6CB, but I think we should go back to the
previous version here.
In our case I think there was a confusion between the pointer
on the first byte of the next header and the value of the next
header field.
Vitaly Wool wrote:
The patch inlined below adds NET_POLL_CONTROLLER support for gianfar network
driver.
As noted, this patch is out of date. 2.6.19-rc kernels removed the
pt_regs argument from all irq handlers.
Jeff
-
To unsubscribe from this list: send the line unsubscribe
Stephen Hemminger wrote:
This is a consolidation of earlier marvell register decode patches to ethtool.
Signed-off-by: Stephen Hemminger [EMAIL PROTECTED]
applied patch 1 of 3
patches 2 and 3 still in the queue under consideration.
-
To unsubscribe from this list: send the line unsubscribe
Andy Fleming wrote:
* genphy_update_link is now exported
* Added a fix from [EMAIL PROTECTED] which changes forcing so it
only updates the link. Otherwise, it never tries the lower
values, since it is always overwriting the speed/duplex values
with the current ones, rather than the
[EMAIL PROTECTED] wrote:
From: Jesse Huang [EMAIL PROTECTED]
Fix TX Pause bug (reset_tx, intr_handler). When MaxCollisions occurred, need
to re-enable Tx. But just after re-enable, MaxCollisions maybe occurred again
and with TxStatusOverflow. This will cause driver can't check new
[EMAIL PROTECTED] wrote:
From: Jesse Huang [EMAIL PROTECTED]
For patent issue need to remove TxStartThresh and RxEarlyThresh. This patent
is cut-through patent. If use this function, Tx will start to transmit after
few data be move in to Tx FIFO. We are not allow to use those function in
[EMAIL PROTECTED] wrote:
From: Jesse Huang [EMAIL PROTECTED]
Correct initial and close hardware step. In some embedded system down and up
IP100A will cause DMA crash. We add some for safe down and up IP100A.
Signed-off-by: Jesse Huang [EMAIL PROTECTED]
Signed-off-by: Andrew Morton [EMAIL
In article [EMAIL PROTECTED] (at Tue, 7 Nov 2006 10:30:02 +0100),
Jean-Philippe Andriot [EMAIL PROTECTED] says:
The way to get the next protocol number of an IPv6 tunnel changes
after introducing IP6CB, but I think we should go back to the
previous version here.
:
struct ipv6_opt_hdr
Quoting Chris Lalancette:
| Hello,
| I realized that all of the packets that go from the crashing machine to
the netdump server have a zero checksum.
snip
| Assuming that this is just an oversight, attached is a simple patch to
compute the UDP checksum in netpoll_send_udp.
|
|
On Mon, 6 Nov 2006 15:26:33 -0600
Andy Fleming [EMAIL PROTECTED] wrote:
You are passing extra arguments, here
Oh yes, thanks. I was out of sync here.
1) Do we need the disable/enable irq stuff? It seems like we should
be able to either just *mask* the interrupts at the controller, or
The patch inlined below adds NET_POLL_CONTROLLER support for gianfar network
driver, slightly modified wrt the comments from Andy Fleming.
drivers/net/gianfar.c | 33 +
1 file changed, 33 insertions(+)
Signed-off-by: Vitaly Wool [EMAIL PROTECTED]
Index:
On Mon, Nov 06, 2006 at 10:25:36PM -0800, Ravikiran G Thirumalai wrote:
On Sun, Nov 05, 2006 at 12:53:23AM +0100, Christoph Hellwig wrote:
On Sat, Nov 04, 2006 at 06:06:48PM -0500, Dave Jones wrote:
On Sat, Nov 04, 2006 at 11:56:29PM +0100, Christoph Hellwig wrote:
This will break the
Please pull from 'upstream-linus' branch of
master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
upstream-linus
to receive the following updates:
drivers/net/b44.c |5 +++--
drivers/net/e1000/e1000_main.c |7 +++
2 files changed, 10 insertions(+), 2
Evgeniy Polyakov wrote:
Generic event handling mechanism.
Consider for inclusion.
Changes from 'take20' patchset:
* new ring buffer implementation
* removed artificial limit on possible number of kevents
With this release and fixed userspace web server it was possible to
achive 3960+ req/s
On Tue, 7 Nov 2006, Gerrit Renker wrote:
Quoting Chris Lalancette:
| Hello,
| I realized that all of the packets that go from the crashing machine to
the netdump server have a zero checksum.
snip
| Assuming that this is just an oversight, attached is a simple patch to
compute
The skge 1.9 patch is looking good on older syskonnect fiber cards.
Stability issues seem to be taken care of and performance is good. There
are some strange interactions with bonding, however. If I try to put
both interfaces of an sk-9844 into a bonded interface, I only see
traffic from one
David Miller wrote:
From: Chris Lalancette [EMAIL PROTECTED]
Date: Mon, 06 Nov 2006 18:40:59 -0500
Assuming that this is just an oversight, attached is a simple
patch to compute the UDP checksum in netpoll_send_udp.
If the resulting checksum is zero, you should set it to
all 1's,
At an aside... This may be useful. Or not.
Al Viro had an interesting idea about kernel-userspace data passing
interfaces. He had suggested creating a task-specific filesystem
derived from ramfs. Through the normal VFS/VM codepaths, the user can
easily create [subject to resource/priv
On Tue, Nov 07, 2006 at 06:46:58AM -0500, Jeff Garzik ([EMAIL PROTECTED]) wrote:
At an aside... This may be useful. Or not.
Al Viro had an interesting idea about kernel-userspace data passing
interfaces. He had suggested creating a task-specific filesystem
derived from ramfs. Through
On Tue, Nov 07, 2006 at 06:26:09AM -0500, Jeff Garzik ([EMAIL PROTECTED]) wrote:
Evgeniy Polyakov wrote:
Generic event handling mechanism.
Consider for inclusion.
Changes from 'take20' patchset:
* new ring buffer implementation
* removed artificial limit on possible number of kevents
Nate Diller wrote:
Indesiciveness has certainly been an issue here, but I remember akpm
and Ulrich both giving concrete suggestions. I was particularly
interested in Andrew's request to explain and justify the differences
between kevent and BSD's kqueue interface. Was there a discussion
that I
David Miller wrote:
From: Pavel Machek [EMAIL PROTECTED]
Date: Fri, 3 Nov 2006 09:57:12 +0100
Not sure what you are smoking, but there's unsigned long in *bsd
version, lets rewrite it from scratch sounds like very bad idea. What
about fixing that one bit you don't like?
I disagree, it's more
Evgeniy Polyakov wrote:
Well, kevent network and FS AIO are suspended for now (although first
Why?
IMO, getting async event submission right is important. It should be
designed in parallel with async event reception.
Jeff
-
To unsubscribe from this list: send the line
Evgeniy Polyakov wrote:
Mmap ring buffer implementation was stopped by Andrew Morton and Ulrich
Drepper, process' memory is used instead. copy_to_user() is slower (and
some times noticebly), but there are major advantages of such approach.
h. I say there are advantages to both.
Perhaps
On Tue, Nov 07, 2006 at 07:17:03AM -0500, Jeff Garzik ([EMAIL PROTECTED]) wrote:
Evgeniy Polyakov wrote:
Well, kevent network and FS AIO are suspended for now (although first
Why?
IMO, getting async event submission right is important. It should be
designed in parallel with async event
Hi All,
I will be sending NetXen 1G/10G ethernet driver updates in subsequent
emails. Kindly review it and feel free to send feedback.
Thanks,
--Amit
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
Hi Amit,
one minor nitpick:
You wrote:
diff --git a/drivers/net/netxen/netxen_nic_main.c
b/drivers/net/netxen/netxen_nic_main.c
index b54ea16..4effb87 100644
--- a/drivers/net/netxen/netxen_nic_main.c
+++ b/drivers/net/netxen/netxen_nic_main.c
[...]
@@ -1040,7 +1041,7 @@ static int
NetXen: 1G/10G Ethernet Driver updates
- Driver cleanup
- These fixes take care of driver on machines with 4G memory
Signed-off-by: Amit S. Kale [EMAIL PROTECTED]
netxen_nic.h | 41 ++
netxen_nic_ethtool.c | 19 ++--
netxen_nic_hdr.h |0
Fix the selection of an SA for an outgoing packet to be at the same
context as the originating socket/flow. This eliminates the SELinux
policy's ability to use/sendto SAs with contexts other than the socket's.
With this patch applied, the SELinux policy will require one or more of the
following
On Tue, 07 Nov 2006 08:25:07 -0500
Michael Stone [EMAIL PROTECTED] wrote:
The skge 1.9 patch is looking good on older syskonnect fiber cards.
Stability issues seem to be taken care of and performance is good. There
are some strange interactions with bonding, however. If I try to put
both
On Tue, 7 Nov 2006 07:49:43 +0100
Jarek Poplawski [EMAIL PROTECTED] wrote:
On Mon, Nov 06, 2006 at 09:44:49AM -0800, Stephen Hemminger wrote:
On Mon, 6 Nov 2006 12:33:53 +0100
Jarek Poplawski [EMAIL PROTECTED] wrote:
After hlist_del() next and pprev pointers are not NULL
so
Matthew Wilcox wrote:
The motivator for this was to fix the sparse warning:
drivers/net/e100.c:2418:48: warning: cast truncates bits from constant
value (83126e978d4fdf becomes 978d4fdf)
drivers/net/e100.c:2419:37: warning: cast truncates bits from constant
value (83126e978d4fdf becomes
I've put a new patchset up at
http://johannes.sipsolutions.net/files/d80211-cleanup/
It now contains:
001-cfg80211-fix-Makefile.patch
002-cfg80211-wext-compat.patch
as before.
003-d80211-reduce-mdev-1.patch
004-d80211-reduce-mdev-2.patch
005-d80211-cleanup-rxmgmt.patch
Hi,
http://johannes.sipsolutions.net/files/d80211-cleanup/
You might want to fix the rights to the folder again ;)
Ivo
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
On Tue, Nov 07, 2006 at 10:33:14AM -0800, Auke Kok wrote:
Matthew Wilcox wrote:
Tested on the internal interface of an HP Integrity rx2600.
bad news, it's completely hosed. The adapter does some indistinguishable
blinking for a second, then stops blinking alltogether.
Weird. I tested it
On Tue, Nov 07, 2006 at 09:51:04AM -0800, Stephen Hemminger wrote:
Which form of bonding link checking are you using. It could be that
bonding MII checking is confused.
I'm not specifying anything, just ifenslave bond0 eth2 eth3
Mike Stone
-
To unsubscribe from this list: send the line
On Tue, 2006-11-07 at 11:17 -0600, Venkat Yekkirala wrote:
int selinux_xfrm_policy_alloc(struct xfrm_policy *xp,
- struct xfrm_user_sec_ctx *uctx, struct sock *sk)
+ struct xfrm_user_sec_ctx *uctx)
{
int err;
- u32 sid;
- BUG_ON(!xp);
-
On Tue, 07 Nov 2006 13:58:31 -0500
Michael Stone [EMAIL PROTECTED] wrote:
On Tue, Nov 07, 2006 at 09:51:04AM -0800, Stephen Hemminger wrote:
Which form of bonding link checking are you using. It could be that
bonding MII checking is confused.
I'm not specifying anything, just ifenslave
Begin forwarded message:
Date: Tue, 07 Nov 2006 10:32:34 -0800
From: Tim Chen [EMAIL PROTECTED]
Newsgroups: linux.dev.kernel
Subject: 2.6.19-rc1: Volanomark slowdown
The patch
[TCP]: Send ACKs each 2nd received segment
commit: 1ef9696c909060ccdae3ade245ca88692b49285b
http://kernel.org/git/?
On Tue, Nov 07, 2006 at 11:18:07AM -0800, Stephen Hemminger wrote:
Do both ports report carrier present?
ethtool eth2
ethtool eth3
Link detected? yes
Mike Stone
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to [EMAIL PROTECTED]
More
Core files.
This patch includes core kevent files:
* userspace controlling
* kernelspace interfaces
* initialization
* notification state machines
Some bits of documentation can be found on project's homepage (and links from
there):
Description.
int kevent_ctl(int fd, unsigned int cmd, unsigned int num, struct ukevent *arg);
fd - is the file descriptor referring to the kevent queue to manipulate.
It is created by opening /dev/kevent char device, which is created with
dynamic
minor number and major number assigned for
poll/select() notifications.
This patch includes generic poll/select notifications.
kevent_poll works simialr to epoll and has the same issues (callback
is invoked not from internal state machine of the caller, but through
process awake, a lot of allocations and so on).
Signed-off-by: Evgeniy
Socket notifications.
This patch includes socket send/recv/accept notifications.
Using trivial web server based on kevent and this features
instead of epoll it's performance increased more than noticebly.
More details about various benchmarks and server itself
(evserver_kevent.c) can be found
Timer notifications.
Timer notifications can be used for fine grained per-process time
management, since interval timers are very inconvenient to use,
and they are limited.
This subsystem uses high-resolution timers.
id.raw[0] is used as number of seconds
id.raw[1] is used as number of
Generic event handling mechanism.
Kevent is a generic subsytem which allows to handle event notifications.
It supports both level and edge triggered events. It is similar to
poll/epoll in some cases, but it is more scalable, it is faster and
allows to work with essentially eny kind of events.
On Tue, 07 Nov 2006 07:32:20 -0500
Jeff Garzik [EMAIL PROTECTED] wrote:
Evgeniy Polyakov wrote:
Mmap ring buffer implementation was stopped by Andrew Morton and Ulrich
Drepper, process' memory is used instead. copy_to_user() is slower (and
some times noticebly), but there are major
Michael Stone [EMAIL PROTECTED] wrote:
The skge 1.9 patch is looking good on older syskonnect fiber cards.
Stability issues seem to be taken care of and performance is good. There
are some strange interactions with bonding, however. If I try to put both
interfaces of an sk-9844 into a bonded
From: Tim Chen [EMAIL PROTECTED]
Date: Tue, 07 Nov 2006 10:32:34 -0800
[ Please bring up networking questions on netdev@vger.kernel.org
as that is the place where networking developers read bug reports
and questions, they by-in-large do not read linux-kernel at all. ]
[TCP]: Send ACKs each
On Tue, 2006-11-07 at 15:29 -0500, Paul Moore wrote:
Venkat Yekkirala wrote:
+/*
+ * security_sid_compare() - compares two given sid contexts.
+ * Returns 1 if they are equal, 0 otherwise.
+ */
+int security_sid_compare(u32 sid1, u32 sid2)
+{
+ struct context *context1;
+
David Miller wrote:
If we don't ACK every two segments, stacks which grow the congestion
window based upon packet counting will not grow the congestion window
properly when they are sending smaller than MSS sized segments.
The only stack I know of that does this currently is linux, and in
From: John Heffner [EMAIL PROTECTED]
Date: Tue, 07 Nov 2006 16:50:33 -0500
The only stack I know of that does this currently is linux, and in doing
so does not conform to the spec. ;) Sending to a BSD receiver will
result in the same behavior, so the right place to fix this is on the
David Miller wrote:
From: John Heffner [EMAIL PROTECTED]
Date: Tue, 07 Nov 2006 16:50:33 -0500
The only stack I know of that does this currently is linux, and in doing
so does not conform to the spec. ;) Sending to a BSD receiver will
result in the same behavior, so the right place to fix
Matthew Wilcox wrote:
On Tue, Nov 07, 2006 at 10:33:14AM -0800, Auke Kok wrote:
Matthew Wilcox wrote:
Tested on the internal interface of an HP Integrity rx2600.
bad news, it's completely hosed. The adapter does some indistinguishable
blinking for a second, then stops blinking alltogether.
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 7 Nov 2006 09:50:07 -0800
Your patch duplicated the code in hlist_del_init(). Why not do:
Indeed, this is the patch I will apply.
Thanks Stephen.
-
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to
On Tue, 7 Nov 2006, Evgeniy Polyakov wrote:
+static int kevent_poll_wait_callback(wait_queue_t *wait,
+ unsigned mode, int sync, void *key)
+{
+ struct kevent_poll_wait_container *cont =
+ container_of(wait, struct kevent_poll_wait_container, wait);
+ struct
From: Michael Chan [EMAIL PROTECTED]
Date: Mon, 06 Nov 2006 12:07:31 -0800
On Mon, 2006-11-06 at 10:45 +0100, Adrian Bunk wrote:
The Coverity checker noted the following in drivers/net/tg3.c:
-- snip --
The problem is that vpd_data[i + 2] could be vpd_data[255 + 2].
Thanks.
On Fri, Nov 03, 2006 at 01:41:46PM -0500, Luis R. Rodriguez wrote:
On 11/3/06, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote:
yes, especially mgt_commit_list caused alot headaches, until I removed
DOT11_OID_PSM from the cache list.
Now, I can hammer it with ping -f for hours.
nice, perhaps
The following changes since commit edd106fc8ac1826dbe231b70ce0762db24133e5c:
Auke Kok:
e1000: Fix regression: garbled stats and irq allocation during swsusp
are found in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-2.6.git
upstream-fixes
The following changes since commit d4f748365129ccfc9dadf6fb14331e45e33cc4ed:
John W. Linville:
Merge branch 'upstream-fixes' into upstream
are found in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-2.6.git
upstream
John W. Linville:
Hi Ingo,
Will do.
Thanks for reviewing it.
-Amit
On Tuesday 07 November 2006 22:19, Ingo Oeser wrote:
Hi Amit,
one minor nitpick:
You wrote:
diff --git a/drivers/net/netxen/netxen_nic_main.c
b/drivers/net/netxen/netxen_nic_main.c index b54ea16..4effb87 100644
---
Most PHYs connect to an ethernet controller over a GMII or MII
interface. However, a growing number are connected over
different interfaces, such as RGMII or SGMII.
The ethernet driver will tell the PHY what type of connection it
is by setting it manually, or passing it in through phy_connect
This patch requires the new support for configurable PHY
interfaces.
Changes include:
* New support for 88e1145
* New support for 88e111s
* Fixing 88e1101 driver to not match non-88e1101 PHYs
* Increases in feature support across Marvell PHY product line
* Fixes a bunch of whitespace issues found
On Nov 8, 2006, at 12:10 AM, Andy Fleming wrote:
Most PHYs connect to an ethernet controller over a GMII or MII
interface. However, a growing number are connected over
different interfaces, such as RGMII or SGMII.
The ethernet driver will tell the PHY what type of connection it
is by setting
On Nov 8, 2006, at 00:16, Kumar Gala wrote:
On Nov 8, 2006, at 12:10 AM, Andy Fleming wrote:
Most PHYs connect to an ethernet controller over a GMII or MII
interface. However, a growing number are connected over
different interfaces, such as RGMII or SGMII.
The ethernet driver will tell
On Tue, Nov 07, 2006 at 09:50:07AM -0800, Stephen Hemminger wrote:
On Tue, 7 Nov 2006 07:49:43 +0100
Jarek Poplawski [EMAIL PROTECTED] wrote:
...
Your patch duplicated the code in hlist_del_init(). Why not do:
--- a/net/sched/sch_htb.c 2006-11-07 09:48:22.0 -0800
+++
On Wed, 8 Nov 2006 15:01:41 +0900
KAMEZAWA Hiroyuki [EMAIL PROTECTED] wrote:
While compiling 2.6.19-rc4-mm2 on ia64, I met this compile error.
==
CC [M] drivers/acpi/processor_idle.o
drivers/acpi/processor_idle.c:43:22: asm/apic.h: No such file or directory
From: Andrew Morton [EMAIL PROTECTED]
Date: Tue, 7 Nov 2006 22:52:59 -0800
Also,
drivers/built-in.o(.text+0xd9a72): In function `e1000_xmit_frame':
: undefined reference to `csum_ipv6_magic'
I don't know how this got broken. ia64 seems to be the only architecture
which doesn't have an
On Tue, 7 Nov 2006 22:52:59 -0800
Andrew Morton [EMAIL PROTECTED] wrote:
On Wed, 8 Nov 2006 15:01:41 +0900
KAMEZAWA Hiroyuki [EMAIL PROTECTED] wrote:
While compiling 2.6.19-rc4-mm2 on ia64, I met this compile error.
==
CC [M] drivers/acpi/processor_idle.o
70 matches
Mail list logo
