mirror of
https://github.com/torvalds/linux.git
synced 2024-12-22 10:56:40 +00:00
954e482bde
According to Intel 64 and IA-32 SDM and Optimization Reference Manual, beginning with Ivybridge, REG string operation using MOVSB and STOSB can provide both flexible and high-performance REG string operations in cases like memory copy. Enhancement availability is indicated by CPUID.7.0.EBX[9] (Enhanced REP MOVSB/ STOSB). If CPU erms feature is detected, patch copy_user_generic with enhanced fast string version of copy_user_generic. A few new macros are defined to reduce duplicate code in ALTERNATIVE and ALTERNATIVE_2. Signed-off-by: Fenghua Yu <fenghua.yu@intel.com> Link: http://lkml.kernel.org/r/1337908785-14015-1-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
240 lines
8.3 KiB
C
240 lines
8.3 KiB
C
#ifndef _ASM_X86_ALTERNATIVE_H
|
|
#define _ASM_X86_ALTERNATIVE_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/stringify.h>
|
|
#include <asm/asm.h>
|
|
|
|
/*
|
|
* Alternative inline assembly for SMP.
|
|
*
|
|
* The LOCK_PREFIX macro defined here replaces the LOCK and
|
|
* LOCK_PREFIX macros used everywhere in the source tree.
|
|
*
|
|
* SMP alternatives use the same data structures as the other
|
|
* alternatives and the X86_FEATURE_UP flag to indicate the case of a
|
|
* UP system running a SMP kernel. The existing apply_alternatives()
|
|
* works fine for patching a SMP kernel for UP.
|
|
*
|
|
* The SMP alternative tables can be kept after boot and contain both
|
|
* UP and SMP versions of the instructions to allow switching back to
|
|
* SMP at runtime, when hotplugging in a new CPU, which is especially
|
|
* useful in virtualized environments.
|
|
*
|
|
* The very common lock prefix is handled as special case in a
|
|
* separate table which is a pure address list without replacement ptr
|
|
* and size information. That keeps the table sizes small.
|
|
*/
|
|
|
|
#ifdef CONFIG_SMP
|
|
#define LOCK_PREFIX_HERE \
|
|
".section .smp_locks,\"a\"\n" \
|
|
".balign 4\n" \
|
|
".long 671f - .\n" /* offset */ \
|
|
".previous\n" \
|
|
"671:"
|
|
|
|
#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
|
|
|
|
#else /* ! CONFIG_SMP */
|
|
#define LOCK_PREFIX_HERE ""
|
|
#define LOCK_PREFIX ""
|
|
#endif
|
|
|
|
struct alt_instr {
|
|
s32 instr_offset; /* original instruction */
|
|
s32 repl_offset; /* offset to replacement instruction */
|
|
u16 cpuid; /* cpuid bit set for replacement */
|
|
u8 instrlen; /* length of original instruction */
|
|
u8 replacementlen; /* length of new instruction, <= instrlen */
|
|
};
|
|
|
|
extern void alternative_instructions(void);
|
|
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
|
|
|
|
struct module;
|
|
|
|
#ifdef CONFIG_SMP
|
|
extern void alternatives_smp_module_add(struct module *mod, char *name,
|
|
void *locks, void *locks_end,
|
|
void *text, void *text_end);
|
|
extern void alternatives_smp_module_del(struct module *mod);
|
|
extern void alternatives_smp_switch(int smp);
|
|
extern int alternatives_text_reserved(void *start, void *end);
|
|
extern bool skip_smp_alternatives;
|
|
#else
|
|
static inline void alternatives_smp_module_add(struct module *mod, char *name,
|
|
void *locks, void *locks_end,
|
|
void *text, void *text_end) {}
|
|
static inline void alternatives_smp_module_del(struct module *mod) {}
|
|
static inline void alternatives_smp_switch(int smp) {}
|
|
static inline int alternatives_text_reserved(void *start, void *end)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#define OLDINSTR(oldinstr) "661:\n\t" oldinstr "\n662:\n"
|
|
|
|
#define b_replacement(number) "663"#number
|
|
#define e_replacement(number) "664"#number
|
|
|
|
#define alt_slen "662b-661b"
|
|
#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f"
|
|
|
|
#define ALTINSTR_ENTRY(feature, number) \
|
|
" .long 661b - .\n" /* label */ \
|
|
" .long " b_replacement(number)"f - .\n" /* new instruction */ \
|
|
" .word " __stringify(feature) "\n" /* feature bit */ \
|
|
" .byte " alt_slen "\n" /* source len */ \
|
|
" .byte " alt_rlen(number) "\n" /* replacement len */
|
|
|
|
#define DISCARD_ENTRY(number) /* rlen <= slen */ \
|
|
" .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n"
|
|
|
|
#define ALTINSTR_REPLACEMENT(newinstr, feature, number) /* replacement */ \
|
|
b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t"
|
|
|
|
/* alternative assembly primitive: */
|
|
#define ALTERNATIVE(oldinstr, newinstr, feature) \
|
|
OLDINSTR(oldinstr) \
|
|
".section .altinstructions,\"a\"\n" \
|
|
ALTINSTR_ENTRY(feature, 1) \
|
|
".previous\n" \
|
|
".section .discard,\"aw\",@progbits\n" \
|
|
DISCARD_ENTRY(1) \
|
|
".previous\n" \
|
|
".section .altinstr_replacement, \"ax\"\n" \
|
|
ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
|
|
".previous"
|
|
|
|
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
|
|
OLDINSTR(oldinstr) \
|
|
".section .altinstructions,\"a\"\n" \
|
|
ALTINSTR_ENTRY(feature1, 1) \
|
|
ALTINSTR_ENTRY(feature2, 2) \
|
|
".previous\n" \
|
|
".section .discard,\"aw\",@progbits\n" \
|
|
DISCARD_ENTRY(1) \
|
|
DISCARD_ENTRY(2) \
|
|
".previous\n" \
|
|
".section .altinstr_replacement, \"ax\"\n" \
|
|
ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
|
|
ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
|
|
".previous"
|
|
|
|
/*
|
|
* This must be included *after* the definition of ALTERNATIVE due to
|
|
* <asm/arch_hweight.h>
|
|
*/
|
|
#include <asm/cpufeature.h>
|
|
|
|
/*
|
|
* Alternative instructions for different CPU types or capabilities.
|
|
*
|
|
* This allows to use optimized instructions even on generic binary
|
|
* kernels.
|
|
*
|
|
* length of oldinstr must be longer or equal the length of newinstr
|
|
* It can be padded with nops as needed.
|
|
*
|
|
* For non barrier like inlines please define new variants
|
|
* without volatile and memory clobber.
|
|
*/
|
|
#define alternative(oldinstr, newinstr, feature) \
|
|
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
|
|
|
|
/*
|
|
* Alternative inline assembly with input.
|
|
*
|
|
* Pecularities:
|
|
* No memory clobber here.
|
|
* Argument numbers start with 1.
|
|
* Best is to use constraints that are fixed size (like (%1) ... "r")
|
|
* If you use variable sized constraints like "m" or "g" in the
|
|
* replacement make sure to pad to the worst case length.
|
|
* Leaving an unused argument 0 to keep API compatibility.
|
|
*/
|
|
#define alternative_input(oldinstr, newinstr, feature, input...) \
|
|
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
|
|
: : "i" (0), ## input)
|
|
|
|
/* Like alternative_input, but with a single output argument */
|
|
#define alternative_io(oldinstr, newinstr, feature, output, input...) \
|
|
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
|
|
: output : "i" (0), ## input)
|
|
|
|
/* Like alternative_io, but for replacing a direct call with another one. */
|
|
#define alternative_call(oldfunc, newfunc, feature, output, input...) \
|
|
asm volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \
|
|
: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
|
|
|
|
/*
|
|
* Like alternative_call, but there are two features and respective functions.
|
|
* If CPU has feature2, function2 is used.
|
|
* Otherwise, if CPU has feature1, function1 is used.
|
|
* Otherwise, old function is used.
|
|
*/
|
|
#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
|
|
output, input...) \
|
|
asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
|
|
"call %P[new2]", feature2) \
|
|
: output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
|
|
[new2] "i" (newfunc2), ## input)
|
|
|
|
/*
|
|
* use this macro(s) if you need more than one output parameter
|
|
* in alternative_io
|
|
*/
|
|
#define ASM_OUTPUT2(a...) a
|
|
|
|
/*
|
|
* use this macro if you need clobbers but no inputs in
|
|
* alternative_{input,io,call}()
|
|
*/
|
|
#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
|
|
|
|
struct paravirt_patch_site;
|
|
#ifdef CONFIG_PARAVIRT
|
|
void apply_paravirt(struct paravirt_patch_site *start,
|
|
struct paravirt_patch_site *end);
|
|
#else
|
|
static inline void apply_paravirt(struct paravirt_patch_site *start,
|
|
struct paravirt_patch_site *end)
|
|
{}
|
|
#define __parainstructions NULL
|
|
#define __parainstructions_end NULL
|
|
#endif
|
|
|
|
extern void *text_poke_early(void *addr, const void *opcode, size_t len);
|
|
|
|
/*
|
|
* Clear and restore the kernel write-protection flag on the local CPU.
|
|
* Allows the kernel to edit read-only pages.
|
|
* Side-effect: any interrupt handler running between save and restore will have
|
|
* the ability to write to read-only pages.
|
|
*
|
|
* Warning:
|
|
* Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
|
|
* no thread can be preempted in the instructions being modified (no iret to an
|
|
* invalid instruction possible) or if the instructions are changed from a
|
|
* consistent state to another consistent state atomically.
|
|
* More care must be taken when modifying code in the SMP case because of
|
|
* Intel's errata. text_poke_smp() takes care that errata, but still
|
|
* doesn't support NMI/MCE handler code modifying.
|
|
* On the local CPU you need to be protected again NMI or MCE handlers seeing an
|
|
* inconsistent instruction while you patch.
|
|
*/
|
|
struct text_poke_param {
|
|
void *addr;
|
|
const void *opcode;
|
|
size_t len;
|
|
};
|
|
|
|
extern void *text_poke(void *addr, const void *opcode, size_t len);
|
|
extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
|
|
extern void text_poke_smp_batch(struct text_poke_param *params, int n);
|
|
|
|
#endif /* _ASM_X86_ALTERNATIVE_H */
|