[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160519175224.GH4128@hmsreliant.think-freely.org>
Date: Thu, 19 May 2016 13:52:24 -0400
From: Neil Horman <nhorman@...driver.com>
To: Eric Dumazet <eric.dumazet@...il.com>
Cc: netdev@...r.kernel.org, "David S. Miller" <davem@...emloft.net>,
Alexander Duyck <alexander.duyck@...il.com>
Subject: Re: [PATCHv2] net: suppress warnings on dev_alloc_skb
On Thu, May 19, 2016 at 10:39:50AM -0700, Eric Dumazet wrote:
> On Thu, 2016-05-19 at 13:34 -0400, Neil Horman wrote:
> > On Thu, May 19, 2016 at 08:48:56AM -0700, Eric Dumazet wrote:
> > > On Thu, 2016-05-19 at 11:30 -0400, Neil Horman wrote:
> > > > Noticed an allocation failure in a network driver the other day on a 32 bit
> > > > system:
> > >
> > > Presumably driver could fall back to HIGH memory allocation for the page
> > > frag.
> > >
> > Is that safe on a 32 bit system?
> > Neil
>
> This should be.
>
> Unless a bug somewhere was added, since most dev are using 64bit kernels
> these days.
>
> All frag consumers use the appropriate kmap_atomic()/kunmap_atomic()
> pairs before copying data from a page frag. Meaning the page can be in
> HIGH memory.
>
Ok, understood, I'll look into a fallback option soon
Neil
>
>
>
>
>
>
Powered by blists - more mailing lists