[lkml]   [2002]   [Aug]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: MM patches against 2.5.31
Christian Ehrhardt wrote:
> ...
> So what we want CPUB do instead is
> spin_lock(lru_lock);
> page = list_entry(lru)
> page_cache_get(page);
> res = (page_count (page) == 1)
> if (res) {
> atomic_dec (&page->count);
> continue; /* with next page */
> }
> ...
> page_cache_release (page);
> I.e. we want to detect _atomically_ that we just raised the page count
> from zero to one. My patch actually has a solution that implements the
> needed atomic operation above by means of the atomic functions that we
> currently have on all archs (it's called get_page_testzero and
> should probably called get_page_testone).
> The more I think about this the more I think this is the way to go.

Yes, I think that would provide a minimal fix to the problem.
(I'd prefer a solution in which presence on the LRU contributes
to page->count, because that means I can dump a load of expensive
page_cache_get-inside-lru-lock instances, but whatever)

You had:

-#define put_page_testzero(p) atomic_dec_and_test(&(p)->count)
-#define page_count(p) atomic_read(&(p)->count)
-#define set_page_count(p,v) atomic_set(&(p)->count, v)
+#define put_page_testzero(p) atomic_add_negative(-1, &(p)->count)
+#define page_count(p) (1+atomic_read(&(p)->count))
+#define set_page_count(p,v) atomic_set(&(p)->count, v-1)
+#define get_page_testzero(p) atomic_inc_and_test(&(p)->count)

So the page count is actually offset by -1, and that is hidden by
the macros. Fair enough.

atomic_add_negative() is not implemented on quite a number of
architectures (sparc64, mips, ppc, sh, cris, 68k, alpha..), so
some legwork is needed there. Looks to be pretty simple though;
alpha, ppc and others already have atomic_add_return().
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at
Please read the FAQ at

 \ /
  Last update: 2005-03-22 13:28    [W:0.209 / U:1.396 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site