Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

x86: optimize clflush

Browse source 
clflush is sufficient to be issued on one CPU. The invalidation is
broadcast throughout the coherence domain.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Thomas Gleixner 2008-01-30 13:34:08 +01:00 committed by Ingo Molnar
parent cd8ddf1a28
commit 3b233e52f7
1 changed files with 8 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
arch/x86/mm/pageattr.c
View file

@ -64,35 +64,29 @@ static void cpa_flush_all(void)
on_each_cpu(__cpa_flush_all, NULL, 1, 1);
}
struct clflush_data {
unsigned long addr;
int numpages;
};
static void __cpa_flush_range(void *arg)
{
struct clflush_data *cld = arg;
/*
* We could optimize that further and do individual per page
* tlb invalidates for a low number of pages. Caveat: we must
* flush the high aliases on 64bit as well.
*/
__flush_tlb_all();
clflush_cache_range((void *) cld->addr, cld->numpages * PAGE_SIZE);
}
static void cpa_flush_range(unsigned long addr, int numpages)
{
struct clflush_data cld;
BUG_ON(irqs_disabled());
cld.addr = addr;
cld.numpages = numpages;
on_each_cpu(__cpa_flush_range, NULL, 1, 1);
on_each_cpu(__cpa_flush_range, &cld, 1, 1);
/*
* We only need to flush on one CPU,
* clflush is a MESI-coherent instruction that
* will cause all other CPUs to flush the same
* cachelines:
*/
clflush_cache_range((void *) addr, numpages * PAGE_SIZE);
}
/*