summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorChris Wilson <chris@chris-wilson.co.uk>2016-01-08 09:55:33 (GMT)
committerThomas Gleixner <tglx@linutronix.de>2016-01-08 18:27:39 (GMT)
commit1f1a89ac05f6e88aa341e86e57435fdbb1177c0c (patch)
treef2ccbc5afe94040c6ba411038e91c63d1ea90101 /arch/x86
parent2039e6acaf94d83ec6b6d9f3d0bce7ea1f099918 (diff)
downloadlinux-1f1a89ac05f6e88aa341e86e57435fdbb1177c0c.tar.xz
x86/mm: Micro-optimise clflush_cache_range()
Whilst inspecting the asm for clflush_cache_range() and some perf profiles that required extensive flushing of single cachelines (from part of the intel-gpu-tools GPU benchmarks), we noticed that gcc was reloading boot_cpu_data.x86_clflush_size on every iteration of the loop. We can manually hoist that read which perf regarded as taking ~25% of the function time for a single cacheline flush. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Borislav Petkov <bp@suse.de> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Sai Praneeth <sai.praneeth.prakhya@intel.com> Link: http://lkml.kernel.org/r/1452246933-10890-1-git-send-email-chris@chris-wilson.co.uk Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/mm/pageattr.c10
1 files changed, 6 insertions, 4 deletions
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a3137a4..6000ad7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -129,14 +129,16 @@ within(unsigned long addr, unsigned long start, unsigned long end)
*/
void clflush_cache_range(void *vaddr, unsigned int size)
{
- unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ const unsigned long clflush_size = boot_cpu_data.x86_clflush_size;
+ void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1));
void *vend = vaddr + size;
- void *p;
+
+ if (p >= vend)
+ return;
mb();
- for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
- p < vend; p += boot_cpu_data.x86_clflush_size)
+ for (; p < vend; p += clflush_size)
clflushopt(p);
mb();