lkml.org 
[lkml]   [2022]   [Apr]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRE: staging: r8188eu: how to handle nested mutex under spinlock
Date
From: Pavel Skripkin
> Sent: 04 April 2022 17:39
>
> Hi David,
>
> On 4/4/22 11:50, David Laight wrote:
> >>
> >> > while (pwrpriv->bInSuspend &&
> >>
> >> I've looked into what gcc11 produced from this function and looks like
> >> my compiler is smart enough to not cache that value, but I am afraid not
> >> all compilers are that smart.
> >
> > The compiler can't cache the value because of the function call.
> >
>
> Hm, I am a newbie in compilers, so can you, please, explain (or give a
> link to any resource where I can read about it) how function call here
> prevent caching.
>
> IIUC compiler generates code that works well in scope of single-threaded
> application, so why can't compiler cache that value instead of accessing
> memory on each iteration... Isn't register access a way faster than even
> cache hit?

Because calls to external functions are allowed to change
any data via 'other' references.
For instance the structure pointer the function has could
also be in global data somewhere.

David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
\
 
 \ /
  Last update: 2022-09-17 16:19    [W:0.090 / U:0.420 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site