jamal wrote:
> On Tue, 2007-20-03 at 07:58 +0100, Patrick McHardy wrote:
>
> Ok. It certainly used to matter in the old days.
Actually it has never been used anywhere else but in ing_filter,
it was introduced together with the TC actions.
>>You would need to make qdisc_lock_tree() aware of the
Hi all,
I noticed recently that, in skb_checksum(), "offset" and "start" are
essentially the same thing and have the same value throughout the
function, despite being computed differently. Using a single variable
allows some cleanups and makes the skb_checksum() function smaller,
more readable, an
On Tue, 2007-20-03 at 07:58 +0100, Patrick McHardy wrote:
> jamal wrote:
> > The main idea is to avoid one BigLock for both ingress and egress;
> > Which was/is still useful in the compat mode where netfilter is used
> > instead.
>
>
> In that case is isn't even used.
>
Ok. It certainly used
jamal wrote:
> On Mon, 2007-19-03 at 19:22 -0700, David Miller wrote:
>
>>It looks like the idea might have been to allow more parallelized
>>running of ingress filters, but this is done wrong and leads to
>>the crashes you are seeing.
>
>
> The main idea is to avoid one BigLock for both ingress
On Mon, 2007-19-03 at 19:22 -0700, David Miller wrote:
>
> I think this should use dev->queue_lock.
>
It would slow down things if he is doing both ingress and egress
traffic as well as control changes.
> It looks like the idea might have been to allow more parallelized
> running of ingress fi
Patrick McHardy wrote:
> [NET]: Fix fib_rules compatibility breakage
I forgot to remove FRA_SRC/FRA_DST from fib6_rule_policy.
Updated patch attached.
[NET]: Fix fib_rules compatibility breakage
The fib_rules netlink attribute policy introduced in 2.6.19 broke
userspace compatibilty. When specif
Thomas Graf wrote:
> * Patrick McHardy <[EMAIL PROTECTED]> 2007-03-19 06:54
>
>>Thomas, I can't see a clean way to fix this right now that
>>doesn't either bloat struct nla_policy or removes FRA_SRC/FRA_DST
>>from the policy, could you please look into this? Thanks.
>
>
> I guess the only way is
Zachary Amsden wrote:
> For VMI, the default clobber was "cc", and you need a way to allow at
> least that, because saving and restoring flags is too expensive on x86.
According to lore (Andi, I think), asm() always clobbers cc.
> I still don't think this was a good trade. The primary motivatio
David Miller <[EMAIL PROTECTED]> writes:
> From: Linus Torvalds <[EMAIL PROTECTED]>
> Date: Mon, 19 Mar 2007 20:18:14 -0700 (PDT)
>
>> > > Please don't subject us to another couple months of hair-pulling only
>> > > to have Linus yank the thing out again, there are certainly more
>> > > useful thi
On Mon, 2007-03-19 at 18:00 -0800, Zachary Amsden wrote:
> Rusty Russell wrote:
> > *This* was the reason that the current hand-coded calls only clobber %
> > eax. It was a compromise between native (no clobbers) and others (might
> > need a reg).
>
> I still don't think this was a good trade.
..
From: Linus Torvalds <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 20:18:14 -0700 (PDT)
> > > Please don't subject us to another couple months of hair-pulling only
> > > to have Linus yank the thing out again, there are certainly more
> > > useful things to spend time on :-)
>
> Good call. Dwarf2 un
On Mon, 19 Mar 2007, Andi Kleen wrote:
>
> Initially we had some bugs that accounted for near all failures, but they
> were all fixed in the latest version.
No. The real bugs were that the people involved wouldn't even accept that
unwinding information was inevitably buggy and/or incomplete.
From: Adrian Bunk <[EMAIL PROTECTED]>
Date: Sun, 18 Mar 2007 19:49:38 +0100
> Subject: ipv6 crash
> References : http://lkml.org/lkml/2007/3/10/2
> Submitter : Len Brown <[EMAIL PROTECTED]>
> Status : unknown
This is caused by some problem in the router round-robin code in
net/ipv6/route
From: Chris Madden <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 16:10:29 -0400
> I did some digging, and it appears the filter add isn't mutexed right.
> Inside net/core/dev.c, ing_filter, I see:
>
> spin_lock(&dev->ingress_lock);
> if ((q = dev->qdisc_ingress) != NULL)
>
From: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 22:38:53 -0300
> Hi David,
>
> Please consider pulling from:
>
> master.kernel.org:/pub/scm/linux/kernel/git/acme/net-2.6.22
Pulled, thanks a lot!
-
To unsubscribe from this list: send the line "unsubscribe netdev"
Rusty Russell wrote:
On Mon, 2007-03-19 at 11:38 -0700, Linus Torvalds wrote:
On Mon, 19 Mar 2007, Eric W. Biederman wrote:
True. You can use all of the call clobbered registers.
Quite often, the biggest single win of inlining is not so much the code
size (although if done righ
Zachary Amsden wrote:
> Jeremy Fitzhardinge wrote:
>> If we then work out in each direction and see matched push/pops,
>> then we know what registers can be trashed in the call. This also
>> allows us to determine the callsite size, and therefore how much space
>> we need for inlining.
>>
>
>
From: Joy Latten <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 18:14:59 -0600
> This patch adds a space between printing of the src and dst ipv6 addresses.
> Otherwise, audit or other test tools may fail to process the audit
> record properly because they cannot find the dst address.
>
> Please let
So that we reduce the number of direct accesses to skb->data.
Signed-off-by: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
---
net/ipv6/netfilter/ip6_tables.c |2 +-
net/ipv6/netfilter/nf_conntrack_reasm.c |5 +++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/net
Signed-off-by: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
---
include/net/netlink.h|2 +-
net/core/wireless.c |2 +-
net/decnet/dn_route.c|3 ++-
net/decnet/dn_table.c|3 ++-
net/ipv4/inet_diag.c |
Signed-off-by: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
---
include/linux/skbuff.h |1 -
net/core/skbuff.c | 14 --
2 files changed, 0 insertions(+), 15 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4803e4d..155f0e6 100644
--- a/include
Not used anywhere and defined inside __KERNEL__, Thomas acked this on irc.
Signed-off-by: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
---
include/linux/netlink.h | 12
1 files changed, 0 insertions(+), 12 deletions(-)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
Hi David,
Please consider pulling from:
master.kernel.org:/pub/scm/linux/kernel/git/acme/net-2.6.22
Best Regards,
- Arnaldo
-
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/ma
For the common "(struct nlmsghdr *)skb->data" sequence, so that we reduce the
number of direct accesses to skb->data and for consistency with all the other
cast skb member helpers.
Signed-off-by: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
---
drivers/connector/connector.c |2 +-
drive
Jeremy Fitzhardinge wrote:
For example, say we wanted to put a general call for sti into entry.S,
where its expected it won't touch any registers. In that case, we'd
have a sequence like:
push %eax
push %ecx
push %edx
call paravirt_cli
pop %edx
pop %ecx
pop %eax
On Mon, 19 Mar 2007 15:43:11 -0700, Deepak Saxena <[EMAIL PROTECTED]> wrote:
> NETPOLL support for Sibyte MAC
>
> Signed-off-by: Manish Lachwani <[EMAIL PROTECTED]>
> Signed-off-by: Deepak Saxena <[EMAIL PROTECTED]>
If you added NETPOLL support, do not forget to ensure hard_start_xmit
routine cal
This patch adds a space between printing of the src and dst ipv6 addresses.
Otherwise, audit or other test tools may fail to process the audit
record properly because they cannot find the dst address.
Please let me know if this patch is ok. It is minor fix, but I have
tested it and printing ipsecv
From: Sridhar Samudrala <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 11:38:05 -0700
> [SCTP]: Reset some transport and association variables on restart
>
> If the association has been restarted, we need to reset the
> transport congestion variables as well as accumulated error
> counts and CACC var
From: Adrian Bunk <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 10:24:03 +0100
> This patch fixes two NULL dereferences spotted by the Coverity checker.
>
> For a better understanding, the "diff -uwp" output (that ignores the
> indentation changes) is:
I'll apply this, thanks Adrian.
-
To unsubscr
From: Sridhar Samudrala <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 11:38:02 -0700
> [SCTP]: Clean up stale data during association restart
>
> During association restart we may have stale data sitting
> on the ULP queue waiting for ordering or reassembly. This
> data may cause severe problems if
From: Sridhar Samudrala <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 11:38:10 -0700
> [SCTP]: Increment error counters on user requested HBs.
>
> 2960bis states (Section 8.3):
>
>D) Request an on-demand HEARTBEAT on a specific destination transport
> address of a given association.
>
>
On Mon, 2007-03-19 at 11:38 -0700, Linus Torvalds wrote:
>
> On Mon, 19 Mar 2007, Eric W. Biederman wrote:
> >
> > True. You can use all of the call clobbered registers.
>
> Quite often, the biggest single win of inlining is not so much the code
> size (although if done right, that will be sma
NETPOLL support for Sibyte MAC
Signed-off-by: Manish Lachwani <[EMAIL PROTECTED]>
Signed-off-by: Deepak Saxena <[EMAIL PROTECTED]>
---
Applies cleanly to 2.6.21-rc4
drivers/net/sb1250-mac.c | 23 +++
1 files changed, 23 insertions(+)
Index: linux-2.6.18/drivers/net/sb1
> Possibly not, but I'd like to be able to say with confidence that
> running a PARAVIRT kernel on bare hardware has no performance loss
> compared to running a !PARAVIRT kernel. There's the case of small
> instruction sequences which have been replaced with calls (such as
> sti/cli/push;popf/etc)
Don't feel obligated to resend patches unless you think they
have become a big merge nightmare due to the rebase, and I can't
think of any patches in my backlog which are like that.
Thanks.
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROT
From: Robert Olsson <[EMAIL PROTECTED]>
Date: Fri, 16 Mar 2007 12:21:38 +0100
> The threshold for root node can be more aggressive set to get
> better tree compression. The new setting mekes the root grow
> from 16 to 19 bits and substansial improvemnt in Aver depth
> this with the current table
From: Robert Olsson <[EMAIL PROTECTED]>
Date: Fri, 16 Mar 2007 11:46:41 +0100
>
> Hello.
>
> The patch below adds break condition for the resize operations. If
> we don't achieve the desired fill factor a warning is printed. Trie
> should still be operational but new thresholds should be consi
Hello!
> This might work. Could you post a patch to better show what you mean to do?
Here it is.
->neigh_destructor() is killed (not used), replaced with ->neigh_cleanup(),
which is called when neighbor entry goes to dead state. At this point
everything is still valid: neigh->dev, neigh->parms e
From: Zacco <[EMAIL PROTECTED]>
Date: Tue, 20 Mar 2007 00:10:19 +0100
> As you recommended, I used oprofile and it turned out that the
> __udp4_lib_lookup function spent most of the time. There is a udp hash
> table and the sockets are sought based on the 7 LSBs of the destination
> port number
Hi Baruch and all,
As you recommended, I used oprofile and it turned out that the
__udp4_lib_lookup function spent most of the time. There is a udp hash
table and the sockets are sought based on the 7 LSBs of the destination
port number. So what happened is now quite obvious: I had many thousa
I got it the first time, it's just very low priority and very
deep in my backlog and I'm also about to be away for 3 days.
I have it so you don't need to keep resending it.
Thanks.
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
M
From: "Arnaldo Carvalho de Melo" <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 17:48:02 -0300
> OK, I wasn' t expecting any whitspaces, probably were whitespaces
> already there that were kept,
I am pretty sure this is exactly what happened.
> I'll try and check future patches.
Thanks!
-
To unsubs
-stable review patch. If anyone has any objections, please let us know.
--
From: Samuel Ortiz <[EMAIL PROTECTED]>
Without this initialization one gets
kernel BUG at kernel/rtmutex_common.h:80!
This patch should also be included in the -stable kernel.
Signed-off-by: G. Liakhov
> It's inability to handle sequences like the above sounds to me like
> a very good argument to _not_ merge the unwinder back into the tree.
The unwinder can handle it fine, it is just that gcc right now cannot
be taught to generate correct unwind tables for it. If paravirt ops
is widely used i g
On 3/19/07, David Miller <[EMAIL PROTECTED]> wrote:
From: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 10:50:30 -0300
> Hi David,
>
> Please pull from:
>
> master.kernel.org:/pub/scm/linux/kernel/git/acme/net-2.6.22
Pulled, thanks Arnaldo.
Can you please verify the
David Miller wrote:
> Another point worth making is that for function calls you
> can fix things up lazily if you want.
> [...]
> In fact forget I mentioned this idea :)
>
OK :) I think we'll only ever want to bind to a hypervisor once, since
the underlying hypervisor can't change on the fly (
From: Jeremy Fitzhardinge <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 12:10:08 -0700
> All this is doable; I'd probably end up hacking boot/compressed/relocs.c
> to generate the appropriate reloc table. My main concern is hacking the
> kernel build process itself; I'm unsure of what it would actua
Linus Torvalds wrote:
> On Mon, 19 Mar 2007, Eric W. Biederman wrote:
>
>> True. You can use all of the call clobbered registers.
>>
>
> Quite often, the biggest single win of inlining is not so much the code
> size (although if done right, that will be smaller too), but the fact that
>
From: David Howells <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 15:41:38 +
> Alan Cox <[EMAIL PROTECTED]> wrote:
>
> > So use SOCK_DGRAM, its clearly near enough.
>
> No, it's not. SOCK_DGRAM is an unreliable, unidirectional datagram passing
> service.
David we're not looking for a precise
From: Patrick McHardy <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 16:27:29 +0100
> Mhh actually this looks intentional:
>
> icmpv6_send and some other output functions do:
> int hlimit;
> ...
> if (hlimit < 0)
> hlimit = dst_metric(dst, RTAX_HOPLIMIT);
> if (h
From: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 10:50:30 -0300
> Hi David,
>
> Please pull from:
>
> master.kernel.org:/pub/scm/linux/kernel/git/acme/net-2.6.22
Pulled, thanks Arnaldo.
Can you please verify the white-space in your patches in the future?
I have a
Eric W. Biederman wrote:
> Rusty Russell <[EMAIL PROTECTED]> writes:
>
>
>> On Sun, 2007-03-18 at 13:08 +0100, Andi Kleen wrote:
>>
The idea is _NOT_ that you go look for references to the paravirt_ops
members structure, that would be stupid and you wouldn't be able to
use th
From: Andi Kleen <[EMAIL PROTECTED]>
Date: Mon, 19 Mar 2007 11:57:28 +0100
> On Monday 19 March 2007 00:46, Jeremy Fitzhardinge wrote:
> > Andi Kleen wrote:
> > For example, say we wanted to put a general call for sti into entry.S,
> > where its expected it won't touch any registers. In that case
On Mon, 19 Mar 2007, Linus Torvalds wrote:
>
> So *please* don't believe that you can make it "as cheap" to have some
> automatic fixup of two sequences, one inlined and one as a "call". It may
> look so when you look at the single instruction generated, but you're
> ignoring all the instruc
* Eric W. Biederman ([EMAIL PROTECTED]) wrote:
> Is it truly critical to inline any of these instructions?
I don't have any current measurements. But we'd been aiming
at getting irq_{en,dis}able to a simple memory write to pda.
But simplicity, maintenance, etc. win over trimming a couple
cycles,
[SCTP]: Increment error counters on user requested HBs.
2960bis states (Section 8.3):
D) Request an on-demand HEARTBEAT on a specific destination transport
address of a given association.
The endpoint should increment the respective error counter of the
destination transport addre
Dave,
Please consider the following 3 SCTP bug fix patches for
inclusion in 2.6.21.
Thanks
Sridhar
[SCTP]: Clean up stale data during association restart
During association restart we may have stale data sitting
on the ULP queue waiting for ordering or reassembly. This
data may cause severe pr
On Mon, 19 Mar 2007, Eric W. Biederman wrote:
>
> True. You can use all of the call clobbered registers.
Quite often, the biggest single win of inlining is not so much the code
size (although if done right, that will be smaller too), but the fact that
inlining DOES NOT CLOBBER AS MANY REGIST
[SCTP]: Reset some transport and association variables on restart
If the association has been restarted, we need to reset the
transport congestion variables as well as accumulated error
counts and CACC variables. If we do not, the association
will use the wrong values and may terminate prematurel
Rusty Russell <[EMAIL PROTECTED]> writes:
> On Sun, 2007-03-18 at 13:08 +0100, Andi Kleen wrote:
>> > The idea is _NOT_ that you go look for references to the paravirt_ops
>> > members structure, that would be stupid and you wouldn't be able to
>> > use the most efficient addressing mode on a give
On Sat, Mar 17, 2007 at 10:08:10PM +0900, takada wrote:
> I tested some patterns. just X86_OOSTORE was effective. WBINVD is needless.
>
> --- arch/i386/Kconfig.cpu~2007-02-05 03:44:54.0 +0900
> +++ arch/i386/Kconfig.cpu 2007-02-17 21:25:52.0 +0900
> @@ -322,7 +322,7 @@ conf
O> No, it's not. SOCK_DGRAM is an unreliable, unidirectional datagram passing
> service.
Thats funny UDP receives and sends packets.
-
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/m
Andi Kleen wrote:
>>
>> push %eax
>> push %ecx
>> push %edx
>> call paravirt_cli
>> pop %edx
>> pop %ecx
>> pop %eax
>>
>
> This cannot right now be expressed as inline assembly in the unwinder at all
> because there is no way to inject the push/pops into the compi
Martin Schiller wrote:
> To be more exactly, it's the examination of
> "ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all"
> which is only be done if XFRM is configured. Since I don't need this anyway,
> I deactivated XFRM now and my "ping -I" is working now.
Could you tr
Alan Cox <[EMAIL PROTECTED]> wrote:
> > > Other RPC types use normal socket types.
> >
> > They do? Examples please. I didn't think Linux, at least, has any other
> > RPC socket families, though I could be wrong as I haven't made a thorough
> > study of them.
>
> SunRPC is implemented in user
Patrick McHardy wrote:
> Pekka Savola wrote:
>
>>On kernel based on 2.6.20.3-rc1 (FC6), 'ip -6 r l' shows:
>>
>>default via fe80::212:f0ff:fe5f:c4ec dev eth1 proto kernel metric
>>1024 expires 7191sec mtu 1500 advmss 1440 hoplimit 4294967295
>>
>>(this is the same with iproute2-ss061214 and ipr
* Patrick McHardy <[EMAIL PROTECTED]> 2007-03-19 06:54
> Thomas, I can't see a clean way to fix this right now that
> doesn't either bloat struct nla_policy or removes FRA_SRC/FRA_DST
> from the policy, could you please look into this? Thanks.
I guess the only way is to remove FRA_SRC/FRA_DST from
Pekka Savola wrote:
> On kernel based on 2.6.20.3-rc1 (FC6), 'ip -6 r l' shows:
>
> default via fe80::212:f0ff:fe5f:c4ec dev eth1 proto kernel metric
> 1024 expires 7191sec mtu 1500 advmss 1440 hoplimit 4294967295
>
> (this is the same with iproute2-ss061214 and iproute2-ss070313.)
>
> So, it
> Quoting Alexey Kuznetsov <[EMAIL PROTECTED]>:
> Subject: Re: dst_ifdown breaks infiniband?
>
> Hello!
>
> > infiniband sets parm->neigh_destructor, and I search for a way to prevent
> > this destructor from being called after the module has been unloaded.
> > Ideas?
>
> It must be called in an
Hi,
On kernel based on 2.6.20.3-rc1 (FC6), 'ip -6 r l' shows:
default via fe80::212:f0ff:fe5f:c4ec dev eth1 proto kernel metric 1024
expires 7191sec mtu 1500 advmss 1440 hoplimit 4294967295
(this is the same with iproute2-ss061214 and iproute2-ss070313.)
So, it seems that the data length f
David Miller <[EMAIL PROTECTED]> writes:
> I think the thing to do is to just leave the loopback references
> in place, try to unregister the per-namespace loopback device,
> and that will safely wait for all the references to go away.
Right. The only thing I have found that needs to be changed
> > Other RPC types use normal socket types.
>
> They do? Examples please. I didn't think Linux, at least, has any other RPC
> socket families, though I could be wrong as I haven't made a thorough study of
> them.
SunRPC is implemented in user space and uses the existing TCP/IP layer
and socket
Hi David,
Please pull from:
master.kernel.org:/pub/scm/linux/kernel/git/acme/net-2.6.22
- Arnaldo
---
I did it just in alloc_skb_from_cache, forgot __alloc_skb, fixed now.
Signed-off-by: Arnaldo Carvalho de Melo <[EMAIL PROTECTED]>
---
net/core/skbuff.c |5 -
1 files changed,
Hello!
> infiniband sets parm->neigh_destructor, and I search for a way to prevent
> this destructor from being called after the module has been unloaded.
> Ideas?
It must be called in any case to update/release internal ipoib structures.
The idea is to move call of parm->neigh_destructor from n
Alan Cox <[EMAIL PROTECTED]> wrote:
> > message transmission. You yourself defined RDM to be a datagram service.
> > RxRPC is not, in my opinion, a datagram service, and neither is it a stream
> > service.
>
> Message is what I should have said.
socket(2) also says datagram...
> Which is just
Paul E. McKenney writes:
> > We have two users of trie_leaf_remove, fn_trie_flush and fn_trie_delete
> > both are holding RTNL. So there shouldn't be need for this preempt stuff.
> > This is assumed to a leftover from an older RCU-take.
>
> True enough! One request -- would it be reasona
> Quoting Alexey Kuznetsov <[EMAIL PROTECTED]>:
> Subject: Re: dst_ifdown breaks infiniband?
>
> Hello!
>
> > If a device driver sets neigh_destructor in neigh_params, this could
> > get called after the device has been unregistered and the driver module
> > removed.
>
> It is the same problem:
> Quoting Alexey Kuznetsov <[EMAIL PROTECTED]>:
> Subject: Re: dst_ifdown breaks infiniband?
>
> Hello!
>
> > If a device driver sets neigh_destructor in neigh_params, this could
> > get called after the device has been unregistered and the driver module
> > removed.
>
> It is the same problem:
Hello!
> If a device driver sets neigh_destructor in neigh_params, this could
> get called after the device has been unregistered and the driver module
> removed.
It is the same problem: if dst->neighbour holds neighbour, it should
not hold device. parms->dev is not supposed to be used after
neig
> message transmission. You yourself defined RDM to be a datagram service.
> RxRPC is not, in my opinion, a datagram service, and neither is it a stream
> service.
Message is what I should have said.
> Interestingly, searching for SOCK_RDM definitions with google shows there's
> some disagreemen
Alan Cox <[EMAIL PROTECTED]> wrote:
> > IMHO the problem with classifying RxRPC as a "reliable datagram"
> > socket is that even an atomic unidirectional communication isn't a
> > single datagram, it's at least 3; there is shared connection state
>
> Thats fine. Any *reliable* protocol send
On Monday 19 March 2007 00:46, Jeremy Fitzhardinge wrote:
> Andi Kleen wrote:
> > Yes. All inline assembly tells gcc what registers are clobbered
> > and it fills in the tables. Hand clobbering in inline assembly cannot
> > be expressed with the current toolchain, so we moved all those
> > out of l
> IMHO the problem with classifying RxRPC as a "reliable datagram"
> socket is that even an atomic unidirectional communication isn't a
> single datagram, it's at least 3; there is shared connection state
Thats fine. Any *reliable* protocol sends more than one packet per
message you send. RD
> Quoting Michael S. Tsirkin <[EMAIL PROTECTED]>:
> Subject: Re: dst_ifdown breaks infiniband?
>
> > > Any simpler ideas?
> >
> > Well, if inifiniband destructor really needs to take that lock... no.
> > Right now I do not see.
>
> OK, this is actually not hard to fix - for infiniband, we can ju
> > Any simpler ideas?
>
> Well, if inifiniband destructor really needs to take that lock... no.
> Right now I do not see.
OK, this is actually not hard to fix - for infiniband, we can just look at
neighbour->dev->type or compare neighbour->dev and
neighbour->parms->dev - if they are different, d
> Quoting Alexey Kuznetsov <[EMAIL PROTECTED]>:
> Subject: Re: [ofa-general] Re: dst_ifdown breaks infiniband?
>
> > Does this look sane (untested)?
>
> It does not, unfortunately.
>
> Instead of regular crash in infiniband you will get numerous
> random NULL pointer dereferences both due to dst
Hello!
> I think the thing to do is to just leave the loopback references
> in place, try to unregister the per-namespace loopback device,
> and that will safely wait for all the references to go away.
Yes, it is exactly how it works in openvz. All the sockets are killed,
queues are cleared, nobo
Hello!
> Does this look sane (untested)?
It does not, unfortunately.
Instead of regular crash in infiniband you will get numerous
random NULL pointer dereferences both due to dst->neighbour
and due to dst->dev.
Alexey
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the bo
This patch fixes two NULL dereferences spotted by the Coverity checker.
For a better understanding, the "diff -uwp" output (that ignores the
indentation changes) is:
--- linux-2.6.21-rc3-mm2/net/x25/x25_forward.c.old 2007-03-19
02:28:34.0 +0100
+++ linux-2.6.21-rc3-mm2/net/x25/x25_
Hello!
> Well I don't think the loopback device is currently but as soon
> as we get network namespace support we will have multiple loopback
> devices and they will get unregistered when we remove the network
> namespace.
There is no logical difference. At the moment when namespace is gone
there
90 matches
Mail list logo
