linux/arch/x86/include/asm/alternative.h
Linus Torvalds a7f934d4f1 asm alternatives: remove incorrect alignment notes
On x86-64, they were just wasteful: with the explicitly added (now
unnecessary) padding, the size of the alternatives structure was 16
bytes, and an alignment of 8 bytes didn't hurt much.

However, it was still silly, since the natural size and alignment for
the structure is actually just 12 bytes, 4-byte aligned since commit
59e97e4d6f ("x86: Make alternative instruction pointers relative").
So removing the padding, and removing the extra alignment is just a good
idea.

On x86-32, the alignment of 4 bytes was correct, but was incorrectly
hardcoded as 8 bytes in <asm/alternative-asm.h>.  That header file had
used to be an x86-64 only header file, but various unification efforts
have made it be used for x86-32 too (ie the unification of rwlock and
rwsem).

That in turn caused x86-32 boot failures, because the extra alignment
would result in random zero-filled words in the altinstructions section,
causing oopses early at boot when doing alternative instruction
replacement.

So just remove all the alignment noise entirely.  It's wrong, and it's
unnecessary.  The section itself is already properly aligned by the
linker scripts, and all additions to the section had better be of the
proper 12-byte format, keeping it aligned.  So if the align directive
were to ever make a difference, that would be an indication of a serious
bug to begin with.

Reported-by: Werner Landgraf <w.landgraf@ru.r>
Acked-by: Andrew Lutomirski <luto@mit.edu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-09-15 13:28:33 -07:00

190 lines
6.6 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 */
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
\
"661:\n\t" oldinstr "\n662:\n" \
".section .altinstructions,\"a\"\n" \
" .long 661b - .\n" /* label */ \
" .long 663f - .\n" /* new instruction */ \
" .word " __stringify(feature) "\n" /* feature bit */ \
" .byte 662b-661b\n" /* sourcelen */ \
" .byte 664f-663f\n" /* replacementlen */ \
".previous\n" \
".section .discard,\"aw\",@progbits\n" \
" .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \
".previous\n" \
".section .altinstr_replacement, \"ax\"\n" \
"663:\n\t" newinstr "\n664:\n" /* replacement */ \
".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)
/*
* use this macro(s) if you need more than one output parameter
* in alternative_io
*/
#define ASM_OUTPUT2(a...) a
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 */