linux/arch/x86/include/asm/alternative.h
Mathias Krause 6b32c126d3 x86/alternatives: Fix alt_max_short macro to really be a max()
The alt_max_short() macro in asm/alternative.h does not work as
intended, leading to nasty bugs. E.g. alt_max_short("1", "3")
evaluates to 3, but alt_max_short("3", "1") evaluates to 1 -- not
exactly the maximum of 1 and 3.

In fact, I had to learn it the hard way by crashing my kernel in not
so funny ways by attempting to make use of the ALTENATIVE_2 macro
with alternatives where the first one was larger than the second
one.

According to [1] and commit dbe4058a6a ("x86/alternatives: Fix
ALTERNATIVE_2 padding generation properly") the right handed side
should read "-(-(a < b))" not "-(-(a - b))". Fix that, to make the
macro work as intended.

While at it, fix up the comments regarding the additional "-", too.
It's not about gas' usage of s32 but brain dead logic of having a
"true" value of -1 for the < operator ... *sigh*

Btw., the one in asm/alternative-asm.h is correct. And, apparently,
all current users of ALTERNATIVE_2() pass same sized alternatives,
avoiding to hit the bug.

[1] http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax

Reviewed-and-tested-by: Borislav Petkov <bp@suse.de>
Fixes: dbe4058a6a ("x86/alternatives: Fix ALTERNATIVE_2 padding generation properly")
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1507228213-13095-1-git-send-email-minipli@googlemail.com
2017-10-09 13:35:17 +02:00

243 lines
8.3 KiB
C

#ifndef _ASM_X86_ALTERNATIVE_H
#define _ASM_X86_ALTERNATIVE_H
#ifndef __ASSEMBLY__
#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 \
".pushsection .smp_locks,\"a\"\n" \
".balign 4\n" \
".long 671f - .\n" /* offset */ \
".popsection\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 */
u8 padlen; /* length of build-time padding */
} __packed;
/*
* Debug flag that can be tested to see whether alternative
* instructions were patched in already:
*/
extern int alternatives_patched;
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_enable_smp(void);
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_enable_smp(void) {}
static inline int alternatives_text_reserved(void *start, void *end)
{
return 0;
}
#endif /* CONFIG_SMP */
#define b_replacement(num) "664"#num
#define e_replacement(num) "665"#num
#define alt_end_marker "663"
#define alt_slen "662b-661b"
#define alt_pad_len alt_end_marker"b-662b"
#define alt_total_slen alt_end_marker"b-661b"
#define alt_rlen(num) e_replacement(num)"f-"b_replacement(num)"f"
#define __OLDINSTR(oldinstr, num) \
"661:\n\t" oldinstr "\n662:\n" \
".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * " \
"((" alt_rlen(num) ")-(" alt_slen ")),0x90\n"
#define OLDINSTR(oldinstr, num) \
__OLDINSTR(oldinstr, num) \
alt_end_marker ":\n"
/*
* gas compatible max based on the idea from:
* http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
*
* The additional "-" is needed because gas uses a "true" value of -1.
*/
#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))"
/*
* Pad the second replacement alternative with additional NOPs if it is
* additionally longer than the first replacement alternative.
*/
#define OLDINSTR_2(oldinstr, num1, num2) \
"661:\n\t" oldinstr "\n662:\n" \
".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * " \
"(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n" \
alt_end_marker ":\n"
#define ALTINSTR_ENTRY(feature, num) \
" .long 661b - .\n" /* label */ \
" .long " b_replacement(num)"f - .\n" /* new instruction */ \
" .word " __stringify(feature) "\n" /* feature bit */ \
" .byte " alt_total_slen "\n" /* source len */ \
" .byte " alt_rlen(num) "\n" /* replacement len */ \
" .byte " alt_pad_len "\n" /* pad len */
#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \
b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t"
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
OLDINSTR(oldinstr, 1) \
".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feature, 1) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
".popsection"
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
OLDINSTR_2(oldinstr, 1, 2) \
".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feature1, 1) \
ALTINSTR_ENTRY(feature2, 2) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
".popsection"
/*
* 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")
#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "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)
/*
* This is similar to alternative_input. But it has two features and
* respective instructions.
*
* If CPU has feature2, newinstr2 is used.
* Otherwise, if CPU has feature1, newinstr1 is used.
* Otherwise, oldinstr is used.
*/
#define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2, \
feature2, input...) \
asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, \
newinstr2, feature2) \
: : "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, ASM_CALL_CONSTRAINT \
: [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
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_ALTERNATIVE_H */