Netdev List
 help / color / mirror / Atom feed
From: Joe Perches <joe@perches.com>
To: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Cc: Shradha Shah <sshah@solarflare.com>,
	David Miller <davem@davemloft.net>,
	netdev@vger.kernel.org, linux-net-drivers@solarflare.com
Subject: Re: [PATCH net v4 1/2] sfc: use 64-bit writes for PIO.
Date: Tue, 03 Jun 2014 10:55:23 -0700	[thread overview]
Message-ID: <1401818123.18833.17.camel@joe-AO725> (raw)
In-Reply-To: <538DFBAF.2030703@cogentembedded.com>

On Tue, 2014-06-03 at 20:45 +0400, Sergei Shtylyov wrote:
> Hello.
> 
> On 06/03/2014 02:04 PM, Shradha Shah wrote:
> 
> > From: Jon Cooper <jcooper@solarflare.com>
> 
> > Patch to open-code the memory copy routines.
> > 32bit writes over the PCI bus causes data corruption.
> 
> > Fixes:ee45fd92c739
> > ("sfc: Use TX PIO for sufficiently small packets")
> 
> > Signed-off-by: Shradha Shah <sshah@solarflare.com>
> > ---
> >   drivers/net/ethernet/sfc/tx.c | 24 +++++++++++++++++++-----
> >   1 file changed, 19 insertions(+), 5 deletions(-)
> 
> > diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
> > index fa94753..d2c9ca0 100644
> > --- a/drivers/net/ethernet/sfc/tx.c
> > +++ b/drivers/net/ethernet/sfc/tx.c
> > @@ -189,6 +189,20 @@ struct efx_short_copy_buffer {
> >   	u8 buf[L1_CACHE_BYTES];
> >   };
> >
> > +/* Copy in explicit 64-bit writes. */
> > +static void efx_memcpy_64(void __iomem *dest, void *src, size_t len)
> > +{
> > +	u64 *src64 = src, __iomem *dest64 = dest;
> > +	size_t i, l64 = len / 8;
> > +
> > +	WARN_ON_ONCE(len % 8 != 0);
> > +	WARN_ON_ONCE(((u8 __iomem *)dest - (u8 __iomem *)0) % 8 != 0);
> > +	BUILD_BUG_ON(sizeof(uint64_t) != 8);
> > +
> > +	for (i = 0; i < l64; ++i)
> > +		writeq(src64[i], dest64+i);
> 
>     Could you please surround + by spaces for consistency?
> 
> > +}
> > +

The BUILD_BUG_ON seems unnecessary.
The separate WARN_ON_ONCEs could be combined.
The subtraction of 0 just seems odd.

Would this be clearer as:

static void efx_memcpy_64(void __iomem *dest, void *src, size_t len)
{
	u64 *src64 = src,
	u64 __iomem *dest64 = dest;
	size_t l64 = len / 8;
	size_t i;

	WARN_ON_ONCE(len % 8 || dest64 % 8);

	for (i = 0; i < l64; i++)
		writeq(src64[i], &dest64[i]);
 }

  reply	other threads:[~2014-06-03 17:55 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-03 10:02 [PATCH net v4 0/2] sfc: Restrict PIO for 64bit arch in order to avoid data corruption Shradha Shah
2014-06-03 10:04 ` [PATCH net v4 1/2] sfc: use 64-bit writes for PIO Shradha Shah
2014-06-03 16:45   ` Sergei Shtylyov
2014-06-03 17:55     ` Joe Perches [this message]
2014-06-03 22:58   ` David Miller
2014-06-05 17:08     ` Robert Stonehouse
2014-06-03 10:05 ` [PATCH net v4 2/2] sfc: Restrict PIO to 64-bit architectures Shradha Shah

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=1401818123.18833.17.camel@joe-AO725 \
    --to=joe@perches.com \
    --cc=davem@davemloft.net \
    --cc=linux-net-drivers@solarflare.com \
    --cc=netdev@vger.kernel.org \
    --cc=sergei.shtylyov@cogentembedded.com \
    --cc=sshah@solarflare.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox