mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: tglx@linutronix.de
Cc: eranian@gmail.com, sfr@canb.auug.org.au, andi@firstfloor.org,
	linux-kernel@vger.kernel.org, akpm@linux-foundation.org,
	mingo@elte.hu, x86@kernel.org
Subject: Re: [patch 05/24] perfmon: X86 generic code (x86)
Date: Thu, 27 Nov 2008 03:37:42 -0800 (PST)	[thread overview]
Message-ID: <20081127.033742.175440395.davem@davemloft.net> (raw)
In-Reply-To: <alpine.LFD.2.00.0811271132290.3325@localhost.localdomain>

From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 27 Nov 2008 11:56:24 +0100 (CET)

> Stephane,
> 
> On Thu, 27 Nov 2008, stephane eranian wrote:
> > > Why do you want to do u64 -> u32 BE32 magic on every interrupt,
> > > context switch etc., if you can do it once in the userspace interface ?
> > >
> > I think we agree as to why the user visible structures have to have fixed size.
> > 
> > Some structures have bitfields in them (no in the current patchset yet).
> > Here is an example:
> > 
> > #define PFM_PMD_BV   (256/sizeof(__u64))
> > 
> > struct pfarg_pmd_attr {
> >         __u16 reg_num;          /* which register */
> >         __u16 reg_set;          /* which event set */
> >         __u32 reg_flags;        /* REGFL flags */
> >         __u64 reg_value;        /* 64-bit value */
> >         __u64 reg_long_reset;   /* write: value to reload after notification */
> >         __u64 reg_short_reset;  /* write: reset after counter overflow */
> >         __u64 reg_random_mask;  /* write: bitmask used to limit random value */
> >         __u64 reg_smpl_pmds[PFM_PMD_BV];  /* write: record in sample */
> >         __u64 reg_reset_pmds[PFM_PMD_BV]; /* write: reset on overflow */
> >         __u64 reg_ovfl_swcnt;   /* write: # of overflows before switch */
> >         __u64 reg_smpl_eventid; /* write: opaque event identifier */
> >         __u64 reg_last_value;   /* read : return: PMD last reset value */
> >         __u64 reg_reserved[8];  /* for future use */
> > };
> 
>   __attribute__ ((packed)); ???

Shouldn't be needed and this woule kill performance on RISC (every
struct member is accessed with byte sized loads and shifts/masking).

We did this for the pfkey.h structures by accident, and I truly regret
it.

  reply	other threads:[~2008-11-27 11:37 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-11-26  8:42 eranian
2008-11-26 11:33 ` Andi Kleen
2008-11-26 12:05   ` Stephen Rothwell
2008-11-26 12:22     ` Andi Kleen
2008-11-26 12:48       ` Stephen Rothwell
2008-11-26 13:32     ` Thomas Gleixner
2008-11-26 13:56       ` stephane eranian
2008-11-26 16:38         ` Thomas Gleixner
2008-11-27  9:51           ` stephane eranian
2008-11-27 10:56             ` Thomas Gleixner
2008-11-27 11:37               ` David Miller [this message]
2008-11-27 14:40                 ` Thomas Gleixner
2008-11-26 13:35 ` Thomas Gleixner
2008-11-26 14:00   ` Andi Kleen
2008-11-26 21:18     ` Thomas Gleixner
2008-11-26 21:37       ` stephane eranian
2008-11-26 23:16         ` Thomas Gleixner
2008-11-27  9:38           ` stephane eranian
2008-11-26 22:54     ` Thomas Gleixner
2008-11-27 10:06       ` Andi Kleen
2008-11-27 10:09         ` stephane eranian
2008-11-27 10:29           ` Thomas Gleixner
2008-11-27 11:31           ` Andi Kleen
2008-11-27 11:35             ` stephane eranian
2008-11-27 11:42               ` David Miller
2008-11-27 11:49                 ` Thomas Gleixner
2008-11-27 12:38                   ` Andi Kleen
2008-11-27 12:31                     ` stephane eranian
2008-11-27 12:46                       ` Andi Kleen
2008-11-27 13:32                       ` Thomas Gleixner
2008-11-27 13:37                         ` stephane eranian
2008-11-27 13:51                           ` Andi Kleen
2008-11-27 13:50                         ` Andi Kleen
2008-11-27 11:52               ` Peter Zijlstra
2008-11-27 12:04                 ` stephane eranian
2008-11-27 12:16                   ` Peter Zijlstra
2008-11-27 12:32               ` Andi Kleen
2008-11-27 12:28                 ` stephane eranian
2008-11-27 12:45                   ` Andi Kleen
2008-11-27 13:30                     ` stephane eranian
2008-11-27 13:49                       ` Andi Kleen
2008-11-27 13:47                         ` stephane eranian
  -- strict thread matches above, loose matches on Subject: below --
2008-11-25 21:36 eranian

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=20081127.033742.175440395.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=eranian@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=sfr@canb.auug.org.au \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    /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

all inboxes | Powered by JetHome®