[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/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c
index 4cf981d..6979297 100644
--- a/arch/i386/lib/usercopy.c
+++ b/arch/i386/lib/usercopy.c
@@ -425,15 +425,121 @@
 		       : "eax", "edx", "memory");
 	return size;
 }
+
+/*
+ * Non Temporal Hint version of __copy_user_zeroing_intel.  It is cache aware.
+ * hyoshiok@miraclelinux.com
+ */
+
+static unsigned long __copy_user_zeroing_intel_nocache(void *to,
+				const void __user *from, unsigned long size)
+{
+        int d0, d1;
+
+	__asm__ __volatile__(
+	       "        .align 2,0x90\n"
+	       "0:      movl 32(%4), %%eax\n"
+	       "        cmpl $67, %0\n"
+	       "        jbe 2f\n"
+	       "1:      movl 64(%4), %%eax\n"
+	       "        .align 2,0x90\n"
+	       "2:      movl 0(%4), %%eax\n"
+	       "21:     movl 4(%4), %%edx\n"
+	       "        movnti %%eax, 0(%3)\n"
+	       "        movnti %%edx, 4(%3)\n"
+	       "3:      movl 8(%4), %%eax\n"
+	       "31:     movl 12(%4),%%edx\n"
+	       "        movnti %%eax, 8(%3)\n"
+	       "        movnti %%edx, 12(%3)\n"
+	       "4:      movl 16(%4), %%eax\n"
+	       "41:     movl 20(%4), %%edx\n"
+	       "        movnti %%eax, 16(%3)\n"
+	       "        movnti %%edx, 20(%3)\n"
+	       "10:     movl 24(%4), %%eax\n"
+	       "51:     movl 28(%4), %%edx\n"
+	       "        movnti %%eax, 24(%3)\n"
+	       "        movnti %%edx, 28(%3)\n"
+	       "11:     movl 32(%4), %%eax\n"
+	       "61:     movl 36(%4), %%edx\n"
+	       "        movnti %%eax, 32(%3)\n"
+	       "        movnti %%edx, 36(%3)\n"
+	       "12:     movl 40(%4), %%eax\n"
+	       "71:     movl 44(%4), %%edx\n"
+	       "        movnti %%eax, 40(%3)\n"
+	       "        movnti %%edx, 44(%3)\n"
+	       "13:     movl 48(%4), %%eax\n"
+	       "81:     movl 52(%4), %%edx\n"
+	       "        movnti %%eax, 48(%3)\n"
+	       "        movnti %%edx, 52(%3)\n"
+	       "14:     movl 56(%4), %%eax\n"
+	       "91:     movl 60(%4), %%edx\n"
+	       "        movnti %%eax, 56(%3)\n"
+	       "        movnti %%edx, 60(%3)\n"
+	       "        addl $-64, %0\n"
+	       "        addl $64, %4\n"
+	       "        addl $64, %3\n"
+	       "        cmpl $63, %0\n"
+	       "        ja  0b\n"
+	       "        sfence \n"
+	       "5:      movl  %0, %%eax\n"
+	       "        shrl  $2, %0\n"
+	       "        andl $3, %%eax\n"
+	       "        cld\n"
+	       "6:      rep; movsl\n"
+	       "        movl %%eax,%0\n"
+	       "7:      rep; movsb\n"
+	       "8:\n"
+	       ".section .fixup,\"ax\"\n"
+	       "9:      lea 0(%%eax,%0,4),%0\n"
+	       "16:     pushl %0\n"
+	       "        pushl %%eax\n"
+	       "        xorl %%eax,%%eax\n"
+	       "        rep; stosb\n"
+	       "        popl %%eax\n"
+	       "        popl %0\n"
+	       "        jmp 8b\n"
+	       ".previous\n"
+	       ".section __ex_table,\"a\"\n"
+	       "	.align 4\n"
+	       "	.long 0b,16b\n"
+	       "	.long 1b,16b\n"
+	       "	.long 2b,16b\n"
+	       "	.long 21b,16b\n"
+	       "	.long 3b,16b\n"
+	       "	.long 31b,16b\n"
+	       "	.long 4b,16b\n"
+	       "	.long 41b,16b\n"
+	       "	.long 10b,16b\n"
+	       "	.long 51b,16b\n"
+	       "	.long 11b,16b\n"
+	       "	.long 61b,16b\n"
+	       "	.long 12b,16b\n"
+	       "	.long 71b,16b\n"
+	       "	.long 13b,16b\n"
+	       "	.long 81b,16b\n"
+	       "	.long 14b,16b\n"
+	       "	.long 91b,16b\n"
+	       "	.long 6b,9b\n"
+	       "        .long 7b,16b\n"
+	       ".previous"
+	       : "=&c"(size), "=&D" (d0), "=&S" (d1)
+	       :  "1"(to), "2"(from), "0"(size)
+	       : "eax", "edx", "memory");
+	return size;
+}
+
 #else
+
 /*
  * Leave these declared but undefined.  They should not be any references to
  * them
  */
-unsigned long
-__copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size);
-unsigned long
-__copy_user_intel(void __user *to, const void *from, unsigned long size);
+unsigned long __copy_user_zeroing_intel(void *to, const void __user *from,
+					unsigned long size);
+unsigned long __copy_user_intel(void __user *to, const void *from,
+					unsigned long size);
+unsigned long __copy_user_zeroing_intel_nocache(void *to,
+				const void __user *from, unsigned long size);
 #endif /* CONFIG_X86_INTEL_USERCOPY */
 
 /* Generic arbitrary sized copy.  */
@@ -515,8 +621,8 @@
 		: "memory");						\
 } while (0)
 
-
-unsigned long __copy_to_user_ll(void __user *to, const void *from, unsigned long n)
+unsigned long __copy_to_user_ll(void __user *to, const void *from,
+				unsigned long n)
 {
 	BUG_ON((long) n < 0);
 #ifndef CONFIG_X86_WP_WORKS_OK
@@ -576,8 +682,8 @@
 }
 EXPORT_SYMBOL(__copy_to_user_ll);
 
-unsigned long
-__copy_from_user_ll(void *to, const void __user *from, unsigned long n)
+unsigned long __copy_from_user_ll(void *to, const void __user *from,
+					unsigned long n)
 {
 	BUG_ON((long)n < 0);
 	if (movsl_is_ok(to, from, n))
@@ -588,6 +694,21 @@
 }
 EXPORT_SYMBOL(__copy_from_user_ll);
 
+unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
+					unsigned long n)
+{
+	BUG_ON((long)n < 0);
+#ifdef CONFIG_X86_INTEL_USERCOPY
+	if ( n > 64 && cpu_has_xmm2)
+                n = __copy_user_zeroing_intel_nocache(to, from, n);
+	else
+		__copy_user_zeroing(to, from, n);
+#else
+        __copy_user_zeroing(to, from, n);
+#endif
+	return n;
+}
+
 /**
  * copy_to_user: - Copy a block of data into user space.
  * @to:   Destination address, in user space.
diff --git a/include/asm-i386/uaccess.h b/include/asm-i386/uaccess.h
index 1ec6552..82af28a 100644
--- a/include/asm-i386/uaccess.h
+++ b/include/asm-i386/uaccess.h
@@ -390,6 +390,8 @@
 				const void *from, unsigned long n);
 unsigned long __must_check __copy_from_user_ll(void *to,
 				const void __user *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll_nocache(void *to,
+				const void __user *from, unsigned long n);
 
 /*
  * Here we special-case 1, 2 and 4-byte copy_*_user invocations.  On a fault
@@ -478,12 +480,43 @@
 	return __copy_from_user_ll(to, from, n);
 }
 
+#define ARCH_HAS_NOCACHE_UACCESS
+
+static __always_inline unsigned long __copy_from_user_inatomic_nocache(void *to,
+				const void __user *from, unsigned long n)
+{
+	if (__builtin_constant_p(n)) {
+		unsigned long ret;
+
+		switch (n) {
+		case 1:
+			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			return ret;
+		case 2:
+			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			return ret;
+		case 4:
+			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			return ret;
+		}
+	}
+	return __copy_from_user_ll_nocache(to, from, n);
+}
+
 static __always_inline unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
        might_sleep();
        return __copy_from_user_inatomic(to, from, n);
 }
+
+static __always_inline unsigned long
+__copy_from_user_nocache(void *to, const void __user *from, unsigned long n)
+{
+       might_sleep();
+       return __copy_from_user_inatomic_nocache(to, from, n);
+}
+
 unsigned long __must_check copy_to_user(void __user *to,
 				const void *from, unsigned long n);
 unsigned long __must_check copy_from_user(void *to,
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
new file mode 100644
index 0000000..391e7ed
--- /dev/null
+++ b/include/linux/uaccess.h
@@ -0,0 +1,22 @@
+#ifndef __LINUX_UACCESS_H__
+#define __LINUX_UACCESS_H__
+
+#include <asm/uaccess.h>
+
+#ifndef ARCH_HAS_NOCACHE_UACCESS
+
+static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
+				const void __user *from, unsigned long n)
+{
+	return __copy_from_user_inatomic(to, from, n);
+}
+
+static inline unsigned long __copy_from_user_nocache(void *to,
+				const void __user *from, unsigned long n)
+{
+	return __copy_from_user(to, from, n);
+}
+
+#endif		/* ARCH_HAS_NOCACHE_UACCESS */
+
+#endif		/* __LINUX_UACCESS_H__ */
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;