WSL2-Linux-Kernel/arch/x86/lib/usercopy_32.c

879 строки
25 KiB
C
Исходник Обычный вид История

/*
* 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>
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))
/*
* Copy a null terminated string from userspace.
*/
#define __do_strncpy_from_user(dst, src, count, res) \
do { \
int __d0, __d1, __d2; \
might_sleep(); \
__asm__ __volatile__( \
" testl %1,%1\n" \
" jz 2f\n" \
"0: lodsb\n" \
" stosb\n" \
" testb %%al,%%al\n" \
" jz 1f\n" \
" decl %1\n" \
" jnz 0b\n" \
"1: subl %1,%0\n" \
"2:\n" \
".section .fixup,\"ax\"\n" \
"3: movl %5,%0\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(0b,3b) \
: "=d"(res), "=c"(count), "=&a" (__d0), "=&S" (__d1), \
"=&D" (__d2) \
: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
: "memory"); \
} while (0)
/**
* __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking.
* @dst: Destination address, in kernel space. This buffer must be at
* least @count bytes long.
* @src: Source address, in user space.
* @count: Maximum number of bytes to copy, including the trailing NUL.
*
* Copies a NUL-terminated string from userspace to kernel space.
* Caller must check the specified block with access_ok() before calling
* this function.
*
* On success, returns the length of the string (not including the trailing
* NUL).
*
* If access to userspace fails, returns -EFAULT (some data may have been
* copied).
*
* If @count is smaller than the length of the string, copies @count bytes
* and returns @count.
*/
long
__strncpy_from_user(char *dst, const char __user *src, long count)
{
long res;
__do_strncpy_from_user(dst, src, count, res);
return res;
}
EXPORT_SYMBOL(__strncpy_from_user);
/**
* strncpy_from_user: - Copy a NUL terminated string from userspace.
* @dst: Destination address, in kernel space. This buffer must be at
* least @count bytes long.
* @src: Source address, in user space.
* @count: Maximum number of bytes to copy, including the trailing NUL.
*
* Copies a NUL-terminated string from userspace to kernel space.
*
* On success, returns the length of the string (not including the trailing
* NUL).
*
* If access to userspace fails, returns -EFAULT (some data may have been
* copied).
*
* If @count is smaller than the length of the string, copies @count bytes
* and returns @count.
*/
long
strncpy_from_user(char *dst, const char __user *src, long count)
{
long res = -EFAULT;
if (access_ok(VERIFY_READ, src, 1))
__do_strncpy_from_user(dst, src, count, res);
return res;
}
EXPORT_SYMBOL(strncpy_from_user);
/*
* Zero Userspace
*/
#define __do_clear_user(addr,size) \
do { \
int __d0; \
might_sleep(); \
__asm__ __volatile__( \
"0: rep; stosl\n" \
" movl %2,%0\n" \
"1: rep; stosb\n" \
"2:\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_sleep();
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);
/**
* strnlen_user: - Get the size of a string in user space.
* @s: The string to measure.
* @n: The maximum valid length
*
* Get the size of a NUL-terminated string in user space.
*
* Returns the size of the string INCLUDING the terminating NUL.
* On exception, returns 0.
* If the string is too long, returns a value greater than @n.
*/
long strnlen_user(const char __user *s, long n)
{
unsigned long mask = -__addr_ok(s);
unsigned long res, tmp;
might_sleep();
__asm__ __volatile__(
" testl %0, %0\n"
" jz 3f\n"
" andl %0,%%ecx\n"
"0: repne; scasb\n"
" setne %%al\n"
" subl %%ecx,%0\n"
" addl %0,%%eax\n"
"1:\n"
".section .fixup,\"ax\"\n"
"2: xorl %%eax,%%eax\n"
" jmp 1b\n"
"3: movb $1,%%al\n"
" jmp 1b\n"
".previous\n"
".section __ex_table,\"a\"\n"
" .align 4\n"
" .long 0b,2b\n"
".previous"
:"=r" (n), "=D" (s), "=a" (res), "=c" (tmp)
:"0" (n), "1" (s), "2" (0), "3" (mask)
:"cc");
return res & mask;
}
EXPORT_SYMBOL(strnlen_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"
".section __ex_table,\"a\"\n"
" .align 4\n"
" .long 1b,100b\n"
" .long 2b,100b\n"
" .long 3b,100b\n"
" .long 4b,100b\n"
" .long 5b,100b\n"
" .long 6b,100b\n"
" .long 7b,100b\n"
" .long 8b,100b\n"
" .long 9b,100b\n"
" .long 10b,100b\n"
" .long 11b,100b\n"
" .long 12b,100b\n"
" .long 13b,100b\n"
" .long 14b,100b\n"
" .long 15b,100b\n"
" .long 16b,100b\n"
" .long 17b,100b\n"
" .long 18b,100b\n"
" .long 19b,100b\n"
" .long 20b,100b\n"
" .long 21b,100b\n"
" .long 22b,100b\n"
" .long 23b,100b\n"
" .long 24b,100b\n"
" .long 25b,100b\n"
" .long 26b,100b\n"
" .long 27b,100b\n"
" .long 28b,100b\n"
" .long 29b,100b\n"
" .long 30b,100b\n"
" .long 31b,100b\n"
" .long 32b,100b\n"
" .long 33b,100b\n"
" .long 34b,100b\n"
" .long 35b,100b\n"
" .long 36b,100b\n"
" .long 37b,100b\n"
" .long 99b,101b\n"
".previous"
: "=&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"
".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;
}
[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 13:04:16 +04:00
/*
* 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 13:04:16 +04:00
__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"
".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;
}
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"
".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
[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 13:04:16 +04:00
/*
* 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 13:04:16 +04:00
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" \
".section __ex_table,\"a\"\n" \
" .align 4\n" \
" .long 4b,5b\n" \
" .long 0b,3b\n" \
" .long 1b,2b\n" \
".previous" \
: "=&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" \
".section __ex_table,\"a\"\n" \
" .align 4\n" \
" .long 4b,5b\n" \
" .long 0b,3b\n" \
" .long 1b,6b\n" \
".previous" \
: "=&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 13:04:16 +04:00
unsigned long __copy_to_user_ll(void __user *to, const void *from,
unsigned long n)
{
#ifndef CONFIG_X86_WP_WORKS_OK
if (unlikely(boot_cpu_data.wp_works_ok == 0) &&
((unsigned long)to) < TASK_SIZE) {
/*
* When we are in an atomic section (see
* mm/filemap.c:file_read_actor), return the full
* length to take the slow path.
*/
if (in_atomic())
return n;
/*
* CPU does not honor the WP bit when writing
* from supervisory mode, and due to preemption or SMP,
* the page tables can change at any time.
* Do it manually. Manfred <manfred@colorfullife.com>
*/
while (n) {
unsigned long offset = ((unsigned long)to)%PAGE_SIZE;
unsigned long len = PAGE_SIZE - offset;
int retval;
struct page *pg;
void *maddr;
if (len > n)
len = n;
survive:
down_read(&current->mm->mmap_sem);
retval = get_user_pages(current, current->mm,
(unsigned long)to, 1, 1, 0, &pg, NULL);
pid namespaces: define is_global_init() and is_container_init() is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 10:39:52 +04:00
if (retval == -ENOMEM && is_global_init(current)) {
up_read(&current->mm->mmap_sem);
congestion_wait(WRITE, HZ/50);
goto survive;
}
if (retval != 1) {
up_read(&current->mm->mmap_sem);
break;
}
maddr = kmap_atomic(pg, KM_USER0);
memcpy(maddr + offset, from, len);
kunmap_atomic(maddr, KM_USER0);
set_page_dirty_lock(pg);
put_page(pg);
up_read(&current->mm->mmap_sem);
from += len;
to += len;
n -= len;
}
return n;
}
#endif
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel(to, from, n);
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 13:04:16 +04:00
unsigned long __copy_from_user_ll(void *to, const void __user *from,
unsigned long n)
{
if (movsl_is_ok(to, from, n))
__copy_user_zeroing(to, from, n);
else
n = __copy_user_zeroing_intel(to, from, n);
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll);
unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
unsigned long n)
{
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel((void __user *)to,
(const void *)from, n);
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 13:04:16 +04:00
unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
unsigned long n)
{
#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 13:04:16 +04:00
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 13:04:16 +04:00
#endif
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 13:04:16 +04:00
unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
unsigned long n)
{
#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
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 long 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.
*/
unsigned long
copy_from_user(void *to, const void __user *from, unsigned long 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);