DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws;
  s=s1024; d=pacbell.net;
  h=Received:X-YMail-OSG:From:To:Subject:Date:User-Agent:Cc:References:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Content-Disposition:Message-Id;
  b=YXEHQbKWGJrQSs1hmi978uMBCfG6MP7ArwOqfFCyMJ9eaJw+xS8S6MJ08G2dtEYG98n4kFZASWXwir8HvdVm7QX/g3CGv8XTnuv0AAPsYIAcFQkmzrbskHs2XdOtwbEzyBL93tqIjae5CYXngs7Flz2Ka5Zns+g0oi8yqSXBHkc=  ;
From: David Brownell <david-b@pacbell.net>
To: Linux Kernel list <linux-kernel@vger.kernel.org>
Subject: Re: [patch/rfc 1/4] GPIO implementation framework
Date: Mon, 5 Nov 2007 13:05:13 -0800
User-Agent: KMail/1.9.6
Cc: Felipe Balbi <felipebalbi@users.sourceforge.net>,
       Bill Gatliff <bgat@billgatliff.com>,
       Haavard Skinnemoen <hskinnemoen@atmel.com>,
       Andrew Victor <andrew@sanpeople.com>, Tony Lindgren <tony@atomide.com>,
       Jean Delvare <khali@linux-fr.org>, "eric miao" <eric.y.miao@gmail.com>,
       Kevin Hilman <khilman@mvista.com>, Paul Mundt <lethal@linux-sh.org>,
       Ben Dooks <ben@trinity.fluff.org>
References: <200710291809.29936.david-b@pacbell.net> <200710291851.23821.david-b@pacbell.net>
In-Reply-To: <200710291851.23821.david-b@pacbell.net>
MIME-Version: 1.0
Content-Type: text/plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: 8bit
Content-Disposition: inline
Message-Id: <200711051305.13980.david-b@pacbell.net>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 4099
Lines: 91

On Monday 29 October 2007, David Brownell wrote:
> 
> Provides new implementation infrastructure that platforms may choose to use
> when implementing the GPIO programming interface. ?Platforms can update their
> GPIO support to use this. ?The downside is slower access to non-inlined GPIOs;
> rarely a problem except when bitbanging some protocol.

I was asked just what that overhead *is* ... and it surprised me.
A summary of the results is appended to this note.

Fortuntely it turns out those problems all go away if the gpiolib
code uses a *raw* spinlock to guard its table lookups.  With a raw
spinlock, any performance impact of gpiolib seems to be well under
a microsecond in this bitbang context (and not objectionable).
Preempt became free; enabling debug options had only a minor cost.

That's as it should be, since the only substantive changes were to
grab and release a lock, do one table lookup a bit differently, and
add one indirection function call ... changes which should not have
any visible performance impact on per-bit codepaths, and one might
expect to cost on the order of one dozen instructions.


So the next version of this code will include a few minor bugfixes,
and will also use a raw spinlock to protect that table.  A raw lock
seems appropriate there in any case, since non-sleeping GPIOs should
be accessible from hardirq contexts even on RT kernels.

If anyone has any strong arguments against using a raw spinlock
to protect that table, it'd be nice to know them sooner rather
than later.

- Dave


SUMMARY:

Using the i2c-gpio driver on a preempt kernel with all the usual
kernel debug options enabled, the per-bit times (*) went up in a
bad way:  from about 6.4 usec/bit (original GPIO code on this board)
up to about 11.2 usec/bit (just switching to gpiolib), which is
well into "objectionable overhead" territory for bit access.

Just enabling preempt shot the time up to 7.4 usec/bit ... which is
also objectionable (it's all-the-time overhead that is clearly
needless), but much less so.

Converting the table lock to be a raw spinlock essentially removed
all non-debug overheads.  It took enabling all those debug options
plus internal gpiolib debugging overhead to get those times up to
the 7.4 usec/bit that previously applied even with just preempt.

(*) Those times being eyeballed medians; I didn't make time to find
    a way to export a few thousand measurements from the tool and
    do the math.  The typical range was +/- one usec.

    The numbers include udelay() calls, so the relevant point is
    the time *delta* attributable only to increased gpiolib costs,
    not the base time (with udelays).  The delta probably reflects
    on the order of four GPIO calls:  set two different bits, clear
    one of them, and read it to make sure it cleared.


> The upside is: 
> 
> ? * Providing two features which were "want to have (but OK to defer)" when
> ? ? GPIO interfaces were first discussed in November 2006:
> 
> ? ? -???A "struct gpio_chip" to plug in GPIOs that aren't directly supported
> ????????by SOC platforms, but come from FPGAs or other multifunction devices
> ????????(like UCB-1x00 GPIOs).
> 
> ? ? -???Full support for message-based GPIO expanders, needing a gpio_chip
> ????????hookup; previous support for this part of the programming interface
> ????????was just stubs. ?(One example: the widely used pcf8574 I2C chips,
> ????????with 8 GPIOs each.)
> 
> ? * Including a non-stub implementation of the gpio_{request,free}() calls,
> ? ? which makes those calls much more useful. ?The diagnostic labels are
> ? ? also recorded given DEBUG_FS, so /sys/kernel/debug/gpio can show a
> ? ? snapshot of all GPIOs known to this infrastructure.
> 
> The driver programming interfaces introduced in 2.6.21 do not change at all;
> this new infrastructure is entirely below the covers.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/