netdev - Re: [PATCH 2/2] ixgbe: add LRO support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:	Tue, 10 Jun 2008 12:47:07 -0700
From:	Malli <mchilakala@...il.com>
To:	"Ben Hutchings" <bhutchings@...arflare.com>
Cc:	"Jeff Kirsher" <jeffrey.t.kirsher@...el.com>, jeff@...zik.org,
	netdev@...r.kernel.org, e1000-devel@...ts.sourceforge.net
Subject: Re: [PATCH 2/2] ixgbe: add LRO support

Forwarding my reply. It got rejected from netdev list, as it was sent in HTML

Thanks for your feedback Ben. I'll update the patch with ethtool get
and set flags. But in packet split mode we still wouldn't want to
limit this with MAX_SKB_FRAGS because we don't actually add the frags
to the previous packet.  They just chain them together using the
frag_list and next pointers in the skb. Let me know if it still
doesn't address your concern in max aggregation.
Thanks & Regards
-Malli

> On Mon, Jun 9, 2008 at 4:26 PM, Ben Hutchings <bhutchings@...arflare.com> wrote:
>>
>> Jeff Kirsher wrote:
>> > Support for in-kernel LRO
>> >
>> > Signed-off-by: Mallikarjuna R Chilakala <mallikarjuna.chilakala@...el.com>
>> > Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
>> > ---
>> >
>> >  drivers/net/ixgbe/ixgbe.h         |    9 +++
>> >  drivers/net/ixgbe/ixgbe_ethtool.c |    9 +++
>> >  drivers/net/ixgbe/ixgbe_main.c    |  111 ++++++++++++++++++++++++++++++-------
>> >  3 files changed, 108 insertions(+), 21 deletions(-)
>> >
>> > diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
>> > index d981134..956914a 100644
>> > --- a/drivers/net/ixgbe/ixgbe.h
>> > +++ b/drivers/net/ixgbe/ixgbe.h
>> > @@ -32,6 +32,7 @@
>> >  #include <linux/types.h>
>> >  #include <linux/pci.h>
>> >  #include <linux/netdevice.h>
>> > +#include <linux/inet_lro.h>
>> >
>> >  #include "ixgbe_type.h"
>> >  #include "ixgbe_common.h"
>> > @@ -100,6 +101,9 @@
>> >  #define IXGBE_TX_FLAGS_VLAN_MASK     0xffff0000
>> >  #define IXGBE_TX_FLAGS_VLAN_SHIFT    16
>> >
>> > +#define IXGBE_MAX_LRO_DESCRIPTORS       8
>> > +#define IXGBE_MAX_LRO_AGGREGATE         32
>>
>> I think this is supposed to be <= MAX_SKB_FRAGS, though that's only
>> critical if you aggregating pages.
>>
>> [...]
>> > @@ -3517,6 +3585,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
>> >                          NETIF_F_HW_VLAN_RX |
>> >                          NETIF_F_HW_VLAN_FILTER;
>> >
>> > +     netdev->features |= NETIF_F_LRO;
>>
>> There needs to be a way of turning LRO off.  It should be sufficient
>> to add:
>>
>>        .get_flags =    ethtool_op_get_flags,
>>        .set_flags =    ethtool_op_set_flags,
>>
>> to your ethtool_ops.  A module parameter to set the default might be
>> worthwhile too.
>>
>> Ben.
>>
>> --
>> Ben Hutchings, Senior Software Engineer, Solarflare Communications
>> Not speaking for my employer; that's the marketing department's job.
>> --
>> To unsubscribe from this list: send the line "unsubscribe netdev" in
>> the body of a message to majordomo@...r.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html