linux/arch/x86/lib/usercopy_32.c

690 lines
20 KiB
C
Raw Normal View History

/*
* User address space access functions.
* The non inlined parts of asm-i386/uaccess.h are here.
*
* Copyright 1997 Andi Kleen <ak@muc.de>
* Copyright 1997 Linus Torvalds
*/
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/interrupt.h>
#include <asm/uaccess.h>
#include <asm/mmx.h>
#include <asm/asm.h>
#ifdef CONFIG_X86_INTEL_USERCOPY
/*
* Alignment at which movsl is preferred for bulk memory copies.
*/
struct movsl_mask movsl_mask __read_mostly;
#endif
static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned long n)
{
#ifdef CONFIG_X86_INTEL_USERCOPY
if (n >= 64 && ((a1 ^ a2) & movsl_mask.mask))
return 0;
#endif
return 1;
}
#define movsl_is_ok(a1, a2, n) \
__movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n))
/*
* Zero Userspace
*/
#define __do_clear_user(addr,size) \
do { \
int __d0; \
might_fault(); \
__asm__ __volatile__( \
ASM_STAC "\n" \
"0: rep; stosl\n" \
" movl %2,%0\n" \
"1: rep; stosb\n" \
"2: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"3: lea 0(%2,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(0b,3b) \
_ASM_EXTABLE(1b,2b) \
: "=&c"(size), "=&D" (__d0) \
: "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
} while (0)
/**
* clear_user: - Zero a block of memory in user space.
* @to: Destination address, in user space.
* @n: Number of bytes to zero.
*
* Zero a block of memory in user space.
*
* Returns number of bytes that could not be cleared.
* On success, this will be zero.
*/
unsigned long
clear_user(void __user *to, unsigned long n)
{
might_fault();
if (access_ok(VERIFY_WRITE, to, n))
__do_clear_user(to, n);
return n;
}
EXPORT_SYMBOL(clear_user);
/**
* __clear_user: - Zero a block of memory in user space, with less checking.
* @to: Destination address, in user space.
* @n: Number of bytes to zero.
*
* Zero a block of memory in user space. Caller must check
* the specified block with access_ok() before calling this function.
*
* Returns number of bytes that could not be cleared.
* On success, this will be zero.
*/
unsigned long
__clear_user(void __user *to, unsigned long n)
{
__do_clear_user(to, n);
return n;
}
EXPORT_SYMBOL(__clear_user);
#ifdef CONFIG_X86_INTEL_USERCOPY
static unsigned long
__copy_user_intel(void __user *to, const void *from, unsigned long size)
{
int d0, d1;
__asm__ __volatile__(
" .align 2,0x90\n"
"1: movl 32(%4), %%eax\n"
" cmpl $67, %0\n"
" jbe 3f\n"
"2: movl 64(%4), %%eax\n"
" .align 2,0x90\n"
"3: movl 0(%4), %%eax\n"
"4: movl 4(%4), %%edx\n"
"5: movl %%eax, 0(%3)\n"
"6: movl %%edx, 4(%3)\n"
"7: movl 8(%4), %%eax\n"
"8: movl 12(%4),%%edx\n"
"9: movl %%eax, 8(%3)\n"
"10: movl %%edx, 12(%3)\n"
"11: movl 16(%4), %%eax\n"
"12: movl 20(%4), %%edx\n"
"13: movl %%eax, 16(%3)\n"
"14: movl %%edx, 20(%3)\n"
"15: movl 24(%4), %%eax\n"
"16: movl 28(%4), %%edx\n"
"17: movl %%eax, 24(%3)\n"
"18: movl %%edx, 28(%3)\n"
"19: movl 32(%4), %%eax\n"
"20: movl 36(%4), %%edx\n"
"21: movl %%eax, 32(%3)\n"
"22: movl %%edx, 36(%3)\n"
"23: movl 40(%4), %%eax\n"
"24: movl 44(%4), %%edx\n"
"25: movl %%eax, 40(%3)\n"
"26: movl %%edx, 44(%3)\n"
"27: movl 48(%4), %%eax\n"
"28: movl 52(%4), %%edx\n"
"29: movl %%eax, 48(%3)\n"
"30: movl %%edx, 52(%3)\n"
"31: movl 56(%4), %%eax\n"
"32: movl 60(%4), %%edx\n"
"33: movl %%eax, 56(%3)\n"
"34: movl %%edx, 60(%3)\n"
" addl $-64, %0\n"
" addl $64, %4\n"
" addl $64, %3\n"
" cmpl $63, %0\n"
" ja 1b\n"
"35: movl %0, %%eax\n"
" shrl $2, %0\n"
" andl $3, %%eax\n"
" cld\n"
"99: rep; movsl\n"
"36: movl %%eax, %0\n"
"37: rep; movsb\n"
"100:\n"
".section .fixup,\"ax\"\n"
"101: lea 0(%%eax,%0,4),%0\n"
" jmp 100b\n"
".previous\n"
_ASM_EXTABLE(1b,100b)
_ASM_EXTABLE(2b,100b)
_ASM_EXTABLE(3b,100b)
_ASM_EXTABLE(4b,100b)
_ASM_EXTABLE(5b,100b)
_ASM_EXTABLE(6b,100b)
_ASM_EXTABLE(7b,100b)
_ASM_EXTABLE(8b,100b)
_ASM_EXTABLE(9b,100b)
_ASM_EXTABLE(10b,100b)
_ASM_EXTABLE(11b,100b)
_ASM_EXTABLE(12b,100b)
_ASM_EXTABLE(13b,100b)
_ASM_EXTABLE(14b,100b)
_ASM_EXTABLE(15b,100b)
_ASM_EXTABLE(16b,100b)
_ASM_EXTABLE(17b,100b)
_ASM_EXTABLE(18b,100b)
_ASM_EXTABLE(19b,100b)
_ASM_EXTABLE(20b,100b)
_ASM_EXTABLE(21b,100b)
_ASM_EXTABLE(22b,100b)
_ASM_EXTABLE(23b,100b)
_ASM_EXTABLE(24b,100b)
_ASM_EXTABLE(25b,100b)
_ASM_EXTABLE(26b,100b)
_ASM_EXTABLE(27b,100b)
_ASM_EXTABLE(28b,100b)
_ASM_EXTABLE(29b,100b)
_ASM_EXTABLE(30b,100b)
_ASM_EXTABLE(31b,100b)
_ASM_EXTABLE(32b,100b)
_ASM_EXTABLE(33b,100b)
_ASM_EXTABLE(34b,100b)
_ASM_EXTABLE(35b,100b)
_ASM_EXTABLE(36b,100b)
_ASM_EXTABLE(37b,100b)
_ASM_EXTABLE(99b,101b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
return size;
}
static unsigned long
__copy_user_zeroing_intel(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"
" movl %%eax, 0(%3)\n"
" movl %%edx, 4(%3)\n"
"3: movl 8(%4), %%eax\n"
"31: movl 12(%4),%%edx\n"
" movl %%eax, 8(%3)\n"
" movl %%edx, 12(%3)\n"
"4: movl 16(%4), %%eax\n"
"41: movl 20(%4), %%edx\n"
" movl %%eax, 16(%3)\n"
" movl %%edx, 20(%3)\n"
"10: movl 24(%4), %%eax\n"
"51: movl 28(%4), %%edx\n"
" movl %%eax, 24(%3)\n"
" movl %%edx, 28(%3)\n"
"11: movl 32(%4), %%eax\n"
"61: movl 36(%4), %%edx\n"
" movl %%eax, 32(%3)\n"
" movl %%edx, 36(%3)\n"
"12: movl 40(%4), %%eax\n"
"71: movl 44(%4), %%edx\n"
" movl %%eax, 40(%3)\n"
" movl %%edx, 44(%3)\n"
"13: movl 48(%4), %%eax\n"
"81: movl 52(%4), %%edx\n"
" movl %%eax, 48(%3)\n"
" movl %%edx, 52(%3)\n"
"14: movl 56(%4), %%eax\n"
"91: movl 60(%4), %%edx\n"
" movl %%eax, 56(%3)\n"
" movl %%edx, 60(%3)\n"
" addl $-64, %0\n"
" addl $64, %4\n"
" addl $64, %3\n"
" cmpl $63, %0\n"
" ja 0b\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"
_ASM_EXTABLE(0b,16b)
_ASM_EXTABLE(1b,16b)
_ASM_EXTABLE(2b,16b)
_ASM_EXTABLE(21b,16b)
_ASM_EXTABLE(3b,16b)
_ASM_EXTABLE(31b,16b)
_ASM_EXTABLE(4b,16b)
_ASM_EXTABLE(41b,16b)
_ASM_EXTABLE(10b,16b)
_ASM_EXTABLE(51b,16b)
_ASM_EXTABLE(11b,16b)
_ASM_EXTABLE(61b,16b)
_ASM_EXTABLE(12b,16b)
_ASM_EXTABLE(71b,16b)
_ASM_EXTABLE(13b,16b)
_ASM_EXTABLE(81b,16b)
_ASM_EXTABLE(14b,16b)
_ASM_EXTABLE(91b,16b)
_ASM_EXTABLE(6b,9b)
_ASM_EXTABLE(7b,16b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
return size;
}
[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>
2006-06-23 09:04:16 +00:00
/*
* 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;
[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>
2006-06-23 09:04:16 +00:00
__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"
_ASM_EXTABLE(0b,16b)
_ASM_EXTABLE(1b,16b)
_ASM_EXTABLE(2b,16b)
_ASM_EXTABLE(21b,16b)
_ASM_EXTABLE(3b,16b)
_ASM_EXTABLE(31b,16b)
_ASM_EXTABLE(4b,16b)
_ASM_EXTABLE(41b,16b)
_ASM_EXTABLE(10b,16b)
_ASM_EXTABLE(51b,16b)
_ASM_EXTABLE(11b,16b)
_ASM_EXTABLE(61b,16b)
_ASM_EXTABLE(12b,16b)
_ASM_EXTABLE(71b,16b)
_ASM_EXTABLE(13b,16b)
_ASM_EXTABLE(81b,16b)
_ASM_EXTABLE(14b,16b)
_ASM_EXTABLE(91b,16b)
_ASM_EXTABLE(6b,9b)
_ASM_EXTABLE(7b,16b)
[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>
2006-06-23 09:04:16 +00:00
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
return size;
}
static unsigned long __copy_user_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: jmp 8b\n"
".previous\n"
_ASM_EXTABLE(0b,16b)
_ASM_EXTABLE(1b,16b)
_ASM_EXTABLE(2b,16b)
_ASM_EXTABLE(21b,16b)
_ASM_EXTABLE(3b,16b)
_ASM_EXTABLE(31b,16b)
_ASM_EXTABLE(4b,16b)
_ASM_EXTABLE(41b,16b)
_ASM_EXTABLE(10b,16b)
_ASM_EXTABLE(51b,16b)
_ASM_EXTABLE(11b,16b)
_ASM_EXTABLE(61b,16b)
_ASM_EXTABLE(12b,16b)
_ASM_EXTABLE(71b,16b)
_ASM_EXTABLE(13b,16b)
_ASM_EXTABLE(81b,16b)
_ASM_EXTABLE(14b,16b)
_ASM_EXTABLE(91b,16b)
_ASM_EXTABLE(6b,9b)
_ASM_EXTABLE(7b,16b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
return size;
}
#else
[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>
2006-06-23 09:04:16 +00:00
/*
* Leave these declared but undefined. They should not be any references to
* them
*/
[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>
2006-06-23 09:04:16 +00:00
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. */
#define __copy_user(to, from, size) \
do { \
int __d0, __d1, __d2; \
__asm__ __volatile__( \
" cmp $7,%0\n" \
" jbe 1f\n" \
" movl %1,%0\n" \
" negl %0\n" \
" andl $7,%0\n" \
" subl %0,%3\n" \
"4: rep; movsb\n" \
" movl %3,%0\n" \
" shrl $2,%0\n" \
" andl $3,%3\n" \
" .align 2,0x90\n" \
"0: rep; movsl\n" \
" movl %3,%0\n" \
"1: rep; movsb\n" \
"2:\n" \
".section .fixup,\"ax\"\n" \
"5: addl %3,%0\n" \
" jmp 2b\n" \
"3: lea 0(%3,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(4b,5b) \
_ASM_EXTABLE(0b,3b) \
_ASM_EXTABLE(1b,2b) \
: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
: "3"(size), "0"(size), "1"(to), "2"(from) \
: "memory"); \
} while (0)
#define __copy_user_zeroing(to, from, size) \
do { \
int __d0, __d1, __d2; \
__asm__ __volatile__( \
" cmp $7,%0\n" \
" jbe 1f\n" \
" movl %1,%0\n" \
" negl %0\n" \
" andl $7,%0\n" \
" subl %0,%3\n" \
"4: rep; movsb\n" \
" movl %3,%0\n" \
" shrl $2,%0\n" \
" andl $3,%3\n" \
" .align 2,0x90\n" \
"0: rep; movsl\n" \
" movl %3,%0\n" \
"1: rep; movsb\n" \
"2:\n" \
".section .fixup,\"ax\"\n" \
"5: addl %3,%0\n" \
" jmp 6f\n" \
"3: lea 0(%3,%0,4),%0\n" \
"6: pushl %0\n" \
" pushl %%eax\n" \
" xorl %%eax,%%eax\n" \
" rep; stosb\n" \
" popl %%eax\n" \
" popl %0\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(4b,5b) \
_ASM_EXTABLE(0b,3b) \
_ASM_EXTABLE(1b,6b) \
: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
: "3"(size), "0"(size), "1"(to), "2"(from) \
: "memory"); \
} while (0)
[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>
2006-06-23 09:04:16 +00:00
unsigned long __copy_to_user_ll(void __user *to, const void *from,
unsigned long n)
{
stac();
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel(to, from, n);
clac();
return n;
}
EXPORT_SYMBOL(__copy_to_user_ll);
[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>
2006-06-23 09:04:16 +00:00
unsigned long __copy_from_user_ll(void *to, const void __user *from,
unsigned long n)
{
stac();
if (movsl_is_ok(to, from, n))
__copy_user_zeroing(to, from, n);
else
n = __copy_user_zeroing_intel(to, from, n);
clac();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll);
unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
unsigned long n)
{
stac();
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel((void __user *)to,
(const void *)from, n);
clac();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll_nozero);
[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>
2006-06-23 09:04:16 +00:00
unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
unsigned long n)
{
stac();
[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>
2006-06-23 09:04:16 +00:00
#ifdef CONFIG_X86_INTEL_USERCOPY
if (n > 64 && cpu_has_xmm2)
n = __copy_user_zeroing_intel_nocache(to, from, n);
[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>
2006-06-23 09:04:16 +00:00
else
__copy_user_zeroing(to, from, n);
#else
__copy_user_zeroing(to, from, n);
[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>
2006-06-23 09:04:16 +00:00
#endif
clac();
[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>
2006-06-23 09:04:16 +00:00
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll_nocache);
[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>
2006-06-23 09:04:16 +00:00
unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
unsigned long n)
{
stac();
#ifdef CONFIG_X86_INTEL_USERCOPY
if (n > 64 && cpu_has_xmm2)
n = __copy_user_intel_nocache(to, from, n);
else
__copy_user(to, from, n);
#else
__copy_user(to, from, n);
#endif
clac();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
/**
* copy_to_user: - Copy a block of data into user space.
* @to: Destination address, in user space.
* @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
* Context: User context only. This function may sleep.
*
* Copy data from kernel space to user space.
*
* Returns number of bytes that could not be copied.
* On success, this will be zero.
*/
unsigned long _copy_to_user(void __user *to, const void *from, unsigned n)
{
if (access_ok(VERIFY_WRITE, to, n))
n = __copy_to_user(to, from, n);
return n;
}
EXPORT_SYMBOL(_copy_to_user);
/**
* copy_from_user: - Copy a block of data from user space.
* @to: Destination address, in kernel space.
* @from: Source address, in user space.
* @n: Number of bytes to copy.
*
* Context: User context only. This function may sleep.
*
* Copy data from user space to kernel space.
*
* Returns number of bytes that could not be copied.
* On success, this will be zero.
*
* If some data could not be copied, this function will pad the copied
* data to the requested size using zero bytes.
*/
x86: Unify copy_from_user() size checking Commits 4a3127693001c61a21d1ce680db6340623f52e93 ("x86: Turn the copy_from_user check into an (optional) compile time warning") and 63312b6a6faae3f2e5577f2b001e3b504f10a2aa ("x86: Add a Kconfig option to turn the copy_from_user warnings into errors") touched only the 32-bit variant of copy_from_user(), whereas the original commit 9f0cf4adb6aa0bfccf675c938124e68f7f06349d ("x86: Use __builtin_object_size() to validate the buffer size for copy_from_user()") also added the same code to the 64-bit one. Further the earlier conversion from an inline WARN() to the call to copy_from_user_overflow() went a little too far: When the number of bytes to be copied is not a constant (e.g. [looking at 3.11] in drivers/net/tun.c:__tun_chr_ioctl() or drivers/pci/pcie/aer/aer_inject.c:aer_inject_write()), the compiler will always have to keep the funtion call, and hence there will always be a warning. By using __builtin_constant_p() we can avoid this. And then this slightly extends the effect of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS in that apart from converting warnings to errors in the constant size case, it retains the (possibly wrong) warnings in the non-constant size case, such that if someone is prepared to get a few false positives, (s)he'll be able to recover the current behavior (except that these diagnostics now will never be converted to errors). Since the 32-bit variant (intentionally) didn't call might_fault(), the unification results in this being called twice now. Adding a suitable #ifdef would be the alternative if that's a problem. I'd like to point out though that with __compiletime_object_size() being restricted to gcc before 4.6, the whole construct is going to become more and more pointless going forward. I would question however that commit 2fb0815c9ee6b9ac50e15dd8360ec76d9fa46a2 ("gcc4: disable __compiletime_object_size for GCC 4.6+") was really necessary, and instead this should have been dealt with as is done here from the beginning. Signed-off-by: Jan Beulich <jbeulich@suse.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/5265056D02000078000FC4F3@nat28.tlf.novell.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-10-21 08:43:57 +00:00
unsigned long _copy_from_user(void *to, const void __user *from, unsigned n)
{
if (access_ok(VERIFY_READ, from, n))
n = __copy_from_user(to, from, n);
else
memset(to, 0, n);
return n;
}
EXPORT_SYMBOL(_copy_from_user);