linux/arch/x86/lib/usercopy_32.c

360 lines
10 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:07:57 +00:00
// SPDX-License-Identifier: GPL-2.0
/*
* 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/export.h>
#include <linux/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_UA(0b, 3b) \
_ASM_EXTABLE_UA(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.
*
* Return: 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();
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 02:57:57 +00:00
if (access_ok(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.
*
* Return: 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_UA(1b, 100b)
_ASM_EXTABLE_UA(2b, 100b)
_ASM_EXTABLE_UA(3b, 100b)
_ASM_EXTABLE_UA(4b, 100b)
_ASM_EXTABLE_UA(5b, 100b)
_ASM_EXTABLE_UA(6b, 100b)
_ASM_EXTABLE_UA(7b, 100b)
_ASM_EXTABLE_UA(8b, 100b)
_ASM_EXTABLE_UA(9b, 100b)
_ASM_EXTABLE_UA(10b, 100b)
_ASM_EXTABLE_UA(11b, 100b)
_ASM_EXTABLE_UA(12b, 100b)
_ASM_EXTABLE_UA(13b, 100b)
_ASM_EXTABLE_UA(14b, 100b)
_ASM_EXTABLE_UA(15b, 100b)
_ASM_EXTABLE_UA(16b, 100b)
_ASM_EXTABLE_UA(17b, 100b)
_ASM_EXTABLE_UA(18b, 100b)
_ASM_EXTABLE_UA(19b, 100b)
_ASM_EXTABLE_UA(20b, 100b)
_ASM_EXTABLE_UA(21b, 100b)
_ASM_EXTABLE_UA(22b, 100b)
_ASM_EXTABLE_UA(23b, 100b)
_ASM_EXTABLE_UA(24b, 100b)
_ASM_EXTABLE_UA(25b, 100b)
_ASM_EXTABLE_UA(26b, 100b)
_ASM_EXTABLE_UA(27b, 100b)
_ASM_EXTABLE_UA(28b, 100b)
_ASM_EXTABLE_UA(29b, 100b)
_ASM_EXTABLE_UA(30b, 100b)
_ASM_EXTABLE_UA(31b, 100b)
_ASM_EXTABLE_UA(32b, 100b)
_ASM_EXTABLE_UA(33b, 100b)
_ASM_EXTABLE_UA(34b, 100b)
_ASM_EXTABLE_UA(35b, 100b)
_ASM_EXTABLE_UA(36b, 100b)
_ASM_EXTABLE_UA(37b, 100b)
_ASM_EXTABLE_UA(99b, 101b)
: "=&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_UA(0b, 16b)
_ASM_EXTABLE_UA(1b, 16b)
_ASM_EXTABLE_UA(2b, 16b)
_ASM_EXTABLE_UA(21b, 16b)
_ASM_EXTABLE_UA(3b, 16b)
_ASM_EXTABLE_UA(31b, 16b)
_ASM_EXTABLE_UA(4b, 16b)
_ASM_EXTABLE_UA(41b, 16b)
_ASM_EXTABLE_UA(10b, 16b)
_ASM_EXTABLE_UA(51b, 16b)
_ASM_EXTABLE_UA(11b, 16b)
_ASM_EXTABLE_UA(61b, 16b)
_ASM_EXTABLE_UA(12b, 16b)
_ASM_EXTABLE_UA(71b, 16b)
_ASM_EXTABLE_UA(13b, 16b)
_ASM_EXTABLE_UA(81b, 16b)
_ASM_EXTABLE_UA(14b, 16b)
_ASM_EXTABLE_UA(91b, 16b)
_ASM_EXTABLE_UA(6b, 9b)
_ASM_EXTABLE_UA(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_intel(void __user *to, const void *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_UA(4b, 5b) \
_ASM_EXTABLE_UA(0b, 3b) \
_ASM_EXTABLE_UA(1b, 2b) \
: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
: "3"(size), "0"(size), "1"(to), "2"(from) \
: "memory"); \
} while (0)
unsigned long __copy_user_ll(void *to, const void *from, unsigned long n)
{
__uaccess_begin_nospec();
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel(to, from, n);
__uaccess_end();
return n;
}
EXPORT_SYMBOL(__copy_user_ll);
unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
unsigned long n)
{
__uaccess_begin_nospec();
#ifdef CONFIG_X86_INTEL_USERCOPY
if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
n = __copy_user_intel_nocache(to, from, n);
else
__copy_user(to, from, n);
#else
__copy_user(to, from, n);
#endif
__uaccess_end();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);