[PATCH] x86: cache pollution aware __copy_from_user_ll()

Use the x86 cache-bypassing copy instructions for copy_from_user().

Some performance data are

Total of GLOBAL_POWER_EVENTS (CPU cycle samples)

2.6.12.4.orig    1921587
2.6.12.4.nt      1599424
1599424/1921587=83.23% (16.77% reduction)

BSQ_CACHE_REFERENCE (L3 cache miss)
2.6.12.4.orig      57427
2.6.12.4.nt        20858
20858/57427=36.32% (63.7% reduction)

L3 cache miss reduction of __copy_from_user_ll
samples  %
37408    65.1412  vmlinux                  __copy_from_user_ll
23        0.1103  vmlinux                  __copy_user_zeroing_intel_nocache
23/37408=0.061% (99.94% reduction)

Top 5 of 2.6.12.4.nt
Counted GLOBAL_POWER_EVENTS events (time during which processor is not stopped) with a unit mask of 0x01 (mandatory) count 100000
samples  %        app name                 symbol name
128392    8.0274  vmlinux                  __copy_user_zeroing_intel_nocache
64206     4.0143  vmlinux                  journal_add_journal_head
59746     3.7355  vmlinux                  do_get_write_access
47674     2.9807  vmlinux                  journal_put_journal_head
46021     2.8774  vmlinux                  journal_dirty_metadata
pattern9-0-cpu4-0-09011728/summary.out

Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x3f (multiple flags) count 3000
samples  %        app name                 symbol name
69755     4.2861  vmlinux                  __copy_user_zeroing_intel_nocache
55685     3.4215  vmlinux                  journal_add_journal_head
52371     3.2179  vmlinux                  __find_get_block
45504     2.7960  vmlinux                  journal_put_journal_head
36005     2.2123  vmlinux                  journal_stop
pattern9-0-cpu4-0-09011744/summary.out

Counted BSQ_CACHE_REFERENCE events (cache references seen by the bus unit) with a unit mask of 0x200 (read 3rd level cache miss) count 3000
samples  %        app name                 symbol name
1147      5.4994  vmlinux                  journal_add_journal_head
881       4.2240  vmlinux                  journal_dirty_data
872       4.1809  vmlinux                  blk_rq_map_sg
734       3.5192  vmlinux                  journal_commit_transaction
617       2.9582  vmlinux                  radix_tree_delete
pattern9-0-cpu4-0-09011731/summary.out

iozone results are

original 2.6.12.4 CPU time = 207.768 sec
cache aware       CPU time = 184.783 sec
(three times run)
184.783/207.768=88.94% (11.06% reduction)

original:
pattern9-0-cpu4-0-08191720/iozone.out:  CPU Utilization: Wall time   45.997    CPU time   64.527    CPU utilization 140.28 %
pattern9-0-cpu4-0-08191741/iozone.out:  CPU Utilization: Wall time   46.878    CPU time   71.933    CPU utilization 153.45 %
pattern9-0-cpu4-0-08191743/iozone.out:  CPU Utilization: Wall time   45.152    CPU time   71.308    CPU utilization 157.93 %

cache awre:
pattern9-0-cpu4-0-09011728/iozone.out:  CPU Utilization: Wall time   44.842    CPU time   62.465    CPU utilization 139.30 %
pattern9-0-cpu4-0-09011731/iozone.out:  CPU Utilization: Wall time   44.718    CPU time   59.273    CPU utilization 132.55 %
pattern9-0-cpu4-0-09011744/iozone.out:  CPU Utilization: Wall time   44.367    CPU time   63.045    CPU utilization 142.10 %

Signed-off-by: Hiro Yoshioka <hyoshiok@miraclelinux.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/mm/filemap.c b/mm/filemap.c
index 368678c..807a463f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/compiler.h>
 #include <linux/fs.h>
+#include <linux/uaccess.h>
 #include <linux/aio.h>
 #include <linux/capability.h>
 #include <linux/kernel_stat.h>
@@ -38,7 +39,6 @@
  */
 #include <linux/buffer_head.h> /* for generic_osync_inode */
 
-#include <asm/uaccess.h>
 #include <asm/mman.h>
 
 static ssize_t
@@ -1902,7 +1902,7 @@
 		int copy = min(bytes, iov->iov_len - base);
 
 		base = 0;
-		left = __copy_from_user_inatomic(vaddr, buf, copy);
+		left = __copy_from_user_inatomic_nocache(vaddr, buf, copy);
 		copied += copy;
 		bytes -= copy;
 		vaddr += copy;
diff --git a/mm/filemap.h b/mm/filemap.h
index 13793ba..5683cde 100644
--- a/mm/filemap.h
+++ b/mm/filemap.h
@@ -13,7 +13,7 @@
 #include <linux/highmem.h>
 #include <linux/uio.h>
 #include <linux/config.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 size_t
 __filemap_copy_from_user_iovec(char *vaddr,
@@ -34,13 +34,13 @@
 	int left;
 
 	kaddr = kmap_atomic(page, KM_USER0);
-	left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
+	left = __copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
 	kunmap_atomic(kaddr, KM_USER0);
 
 	if (left != 0) {
 		/* Do it the slow way */
 		kaddr = kmap(page);
-		left = __copy_from_user(kaddr + offset, buf, bytes);
+		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
 		kunmap(page);
 	}
 	return bytes - left;