From: Alexander Duyck <alexander.duyck@gmail.com>
To: David Laight <David.Laight@ACULAB.COM>,
'Alexander Duyck' <alexander.h.duyck@redhat.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>
Cc: Florian Fainelli <f.fainelli@gmail.com>,
"eric.dumazet@gmail.com" <eric.dumazet@gmail.com>,
Ariel Elior <ariel.elior@qlogic.com>,
"brouer@redhat.com" <brouer@redhat.com>,
Gary Zambrano <zambrano@broadcom.com>,
"davem@davemloft.net" <davem@davemloft.net>,
"ast@plumgrid.com" <ast@plumgrid.com>
Subject: Re: [net-next PATCH 6/6] ethernet/broadcom: Use napi_alloc_skb instead of netdev_alloc_skb_ip_align
Date: Wed, 10 Dec 2014 07:16:14 -0800 [thread overview]
Message-ID: <548863BE.302@gmail.com> (raw)
In-Reply-To: <063D6719AE5E284EB5DD2968C1650D6D1CA09DA9@AcuExch.aculab.com>
On 12/10/2014 01:52 AM, David Laight wrote:
> From: David Laight
>> From: Alexander Duyck
>>> This patch replaces the calls to netdev_alloc_skb_ip_align in the
>>> copybreak paths.
>> Why?
>>
>> You still want the IP header to be aligned and you also want the
>> memcpy() to be copying aligned data.
>>
>> I suspect this fails on both counts?
> Or am I confused by the naming?
>
> David
>
The bit you are missing is that napi_alloc_skb is always IP aligned.
The general idea with napi_alloc_skb is that it is a cheaper way
allocate frames that are about to be passed up the stack as a NAPI or
GRO receive so the IP aligned part is a given.
- Alex
next prev parent reply other threads:[~2014-12-10 15:16 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-12-10 3:40 [net-next PATCH 0/6] net: Alloc NAPI page frags from their own pool Alexander Duyck
2014-12-10 3:40 ` [net-next PATCH 1/6] net: Split netdev_alloc_frag into __alloc_page_frag and add __napi_alloc_frag Alexander Duyck
2014-12-10 4:16 ` Alexei Starovoitov
2014-12-10 15:21 ` Alexander Duyck
2014-12-10 16:02 ` Eric Dumazet
2014-12-10 17:06 ` Alexander Duyck
2014-12-10 17:13 ` Eric Dumazet
2014-12-10 17:16 ` Alexander Duyck
2014-12-10 3:40 ` [net-next PATCH 2/6] net: Pull out core bits of __netdev_alloc_skb and add __napi_alloc_skb Alexander Duyck
2014-12-10 3:40 ` [net-next PATCH 3/6] ethernet/intel: Use napi_alloc_skb Alexander Duyck
2014-12-11 21:43 ` Jeff Kirsher
2014-12-10 3:41 ` [net-next PATCH 4/6] cxgb: Use napi_alloc_skb instead of netdev_alloc_skb_ip_align Alexander Duyck
2014-12-10 3:41 ` [net-next PATCH 5/6] ethernet/realtek: use " Alexander Duyck
2014-12-10 3:41 ` [net-next PATCH 6/6] ethernet/broadcom: Use " Alexander Duyck
2014-12-10 9:50 ` David Laight
2014-12-10 9:52 ` David Laight
2014-12-10 15:16 ` Alexander Duyck [this message]
2014-12-10 14:15 ` [RFC PATCH 0/3] Faster than SLAB caching of SKBs with qmempool (backed by alf_queue) Jesper Dangaard Brouer
2014-12-10 14:15 ` Jesper Dangaard Brouer
2014-12-10 14:15 ` [RFC PATCH 1/3] lib: adding an Array-based Lock-Free (ALF) queue Jesper Dangaard Brouer
2014-12-10 14:15 ` Jesper Dangaard Brouer
2014-12-11 19:15 ` David Miller
2014-12-11 19:15 ` David Miller
2014-12-11 19:15 ` David Miller
2014-12-10 14:15 ` [RFC PATCH 2/3] mm: qmempool - quick queue based memory pool Jesper Dangaard Brouer
2014-12-10 14:15 ` Jesper Dangaard Brouer
2014-12-10 14:15 ` [RFC PATCH 3/3] net: use qmempool in-front of sk_buff kmem_cache Jesper Dangaard Brouer
2014-12-10 14:15 ` Jesper Dangaard Brouer
2014-12-10 14:22 ` [RFC PATCH 0/3] Faster than SLAB caching of SKBs with qmempool (backed by alf_queue) David Laight
2014-12-10 14:22 ` David Laight
2014-12-10 14:40 ` Jesper Dangaard Brouer
2014-12-10 14:40 ` Jesper Dangaard Brouer
2014-12-10 15:17 ` Christoph Lameter
2014-12-10 15:17 ` Christoph Lameter
2014-12-10 15:33 ` Jesper Dangaard Brouer
2014-12-10 15:33 ` Jesper Dangaard Brouer
[not found] ` <20141210163321.0e4e4fd2-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2014-12-10 16:17 ` Christoph Lameter
2014-12-10 16:17 ` Christoph Lameter
2014-12-10 16:17 ` Christoph Lameter
2014-12-10 19:51 ` Christoph Lameter
2014-12-10 19:51 ` Christoph Lameter
2014-12-11 10:18 ` Jesper Dangaard Brouer
2014-12-11 10:18 ` Jesper Dangaard Brouer
2014-12-10 18:32 ` [net-next PATCH 0/6] net: Alloc NAPI page frags from their own pool David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=548863BE.302@gmail.com \
--to=alexander.duyck@gmail.com \
--cc=David.Laight@ACULAB.COM \
--cc=alexander.h.duyck@redhat.com \
--cc=ariel.elior@qlogic.com \
--cc=ast@plumgrid.com \
--cc=brouer@redhat.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=f.fainelli@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=zambrano@broadcom.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.