lkml.org 
[lkml]   [2006]   [Jul]   [8]   [last100]   RSS Feed
Views: [more markup]  [less markup]  [headers]  [forward] 
 
Messages in this thread
/
DateFri, 7 Jul 2006 22:25:10 -0700 (PDT)
FromLinus Torvalds <>
SubjectRe: [patch] spinlocks: remove 'volatile'

On Fri, 7 Jul 2006, Albert Cahalan wrote:
> 
> Key thing being "language environment", meaning gcc.

No.

The key thing is "language environment", meaning THE HARDWARE.

> By the language spec, volatile is a low-performance way to
> get the job done.

No.

"volatile" simply CANNOT get the job done. It fundamentally does _nothing_ 
for all the issues that are fundamental today: CPU memory ordering in SMP, 
special IO synchronization requirements for memory-mapped IO registers etc 
etc.

It's not that "volatile" is the "portable way". It's that "volatile" is 
fundamentally not sufficient for the job.

		Linus
-
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/

\
 
 \ /
  Last update: 2006-07-08 05:29    [from the cache]
©2003-2008