x86, cpu: Clean up and unify the NOP selection infrastructure

Clean up and unify the NOP selection infrastructure:

- Make the atomic 5-byte NOP a part of the selection system.
- Pick NOPs once during early boot and then be done with it.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Link: http://lkml.kernel.org/r/1303166160-10315-3-git-send-email-hpa@linux.intel.com
This commit is contained in:
H. Peter Anvin 2011-04-18 15:19:51 -07:00
parent b1e7734f02
commit dc326fca2b
6 changed files with 191 additions and 162 deletions

View file

@ -191,12 +191,4 @@ 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);
#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
#define IDEAL_NOP_SIZE_5 5
extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
extern void arch_init_ideal_nop5(void);
#else
static inline void arch_init_ideal_nop5(void) {}
#endif
#endif /* _ASM_X86_ALTERNATIVE_H */

View file

@ -1,7 +1,13 @@
#ifndef _ASM_X86_NOPS_H
#define _ASM_X86_NOPS_H
/* Define nops for use with alternative() */
/*
* Define nops for use with alternative() and for tracing.
*
* *_NOP5_ATOMIC must be a single instruction.
*/
#define NOP_DS_PREFIX 0x3e
/* generic versions from gas
1: nop
@ -13,14 +19,15 @@
6: leal 0x00000000(%esi),%esi
7: leal 0x00000000(,%esi,1),%esi
*/
#define GENERIC_NOP1 ".byte 0x90\n"
#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
#define GENERIC_NOP1 0x90
#define GENERIC_NOP2 0x89,0xf6
#define GENERIC_NOP3 0x8d,0x76,0x00
#define GENERIC_NOP4 0x8d,0x74,0x26,0x00
#define GENERIC_NOP5 GENERIC_NOP1,GENERIC_NOP4
#define GENERIC_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00
#define GENERIC_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
#define GENERIC_NOP8 GENERIC_NOP1,GENERIC_NOP7
#define GENERIC_NOP5_ATOMIC NOP_DS_PREFIX,GENERIC_NOP4
/* Opteron 64bit nops
1: nop
@ -29,13 +36,14 @@
4: osp osp osp nop
*/
#define K8_NOP1 GENERIC_NOP1
#define K8_NOP2 ".byte 0x66,0x90\n"
#define K8_NOP3 ".byte 0x66,0x66,0x90\n"
#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n"
#define K8_NOP5 K8_NOP3 K8_NOP2
#define K8_NOP6 K8_NOP3 K8_NOP3
#define K8_NOP7 K8_NOP4 K8_NOP3
#define K8_NOP8 K8_NOP4 K8_NOP4
#define K8_NOP2 0x66,K8_NOP1
#define K8_NOP3 0x66,K8_NOP2
#define K8_NOP4 0x66,K8_NOP3
#define K8_NOP5 K8_NOP3,K8_NOP2
#define K8_NOP6 K8_NOP3,K8_NOP3
#define K8_NOP7 K8_NOP4,K8_NOP3
#define K8_NOP8 K8_NOP4,K8_NOP4
#define K8_NOP5_ATOMIC 0x66,K8_NOP4
/* K7 nops
uses eax dependencies (arbitrary choice)
@ -47,13 +55,14 @@
7: leal 0x00000000(,%eax,1),%eax
*/
#define K7_NOP1 GENERIC_NOP1
#define K7_NOP2 ".byte 0x8b,0xc0\n"
#define K7_NOP3 ".byte 0x8d,0x04,0x20\n"
#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n"
#define K7_NOP5 K7_NOP4 ASM_NOP1
#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n"
#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n"
#define K7_NOP8 K7_NOP7 ASM_NOP1
#define K7_NOP2 0x8b,0xc0
#define K7_NOP3 0x8d,0x04,0x20
#define K7_NOP4 0x8d,0x44,0x20,0x00
#define K7_NOP5 K7_NOP4,K7_NOP1
#define K7_NOP6 0x8d,0x80,0,0,0,0
#define K7_NOP7 0x8D,0x04,0x05,0,0,0,0
#define K7_NOP8 K7_NOP7,K7_NOP1
#define K7_NOP5_ATOMIC NOP_DS_PREFIX,K7_NOP4
/* P6 nops
uses eax dependencies (Intel-recommended choice)
@ -69,52 +78,65 @@
There is kernel code that depends on this.
*/
#define P6_NOP1 GENERIC_NOP1
#define P6_NOP2 ".byte 0x66,0x90\n"
#define P6_NOP3 ".byte 0x0f,0x1f,0x00\n"
#define P6_NOP4 ".byte 0x0f,0x1f,0x40,0\n"
#define P6_NOP5 ".byte 0x0f,0x1f,0x44,0x00,0\n"
#define P6_NOP6 ".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
#define P6_NOP7 ".byte 0x0f,0x1f,0x80,0,0,0,0\n"
#define P6_NOP8 ".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
#define P6_NOP2 0x66,0x90
#define P6_NOP3 0x0f,0x1f,0x00
#define P6_NOP4 0x0f,0x1f,0x40,0
#define P6_NOP5 0x0f,0x1f,0x44,0x00,0
#define P6_NOP6 0x66,0x0f,0x1f,0x44,0x00,0
#define P6_NOP7 0x0f,0x1f,0x80,0,0,0,0
#define P6_NOP8 0x0f,0x1f,0x84,0x00,0,0,0,0
#define P6_NOP5_ATOMIC P6_NOP5
#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
#if defined(CONFIG_MK7)
#define ASM_NOP1 K7_NOP1
#define ASM_NOP2 K7_NOP2
#define ASM_NOP3 K7_NOP3
#define ASM_NOP4 K7_NOP4
#define ASM_NOP5 K7_NOP5
#define ASM_NOP6 K7_NOP6
#define ASM_NOP7 K7_NOP7
#define ASM_NOP8 K7_NOP8
#define ASM_NOP1 _ASM_MK_NOP(K7_NOP1)
#define ASM_NOP2 _ASM_MK_NOP(K7_NOP2)
#define ASM_NOP3 _ASM_MK_NOP(K7_NOP3)
#define ASM_NOP4 _ASM_MK_NOP(K7_NOP4)
#define ASM_NOP5 _ASM_MK_NOP(K7_NOP5)
#define ASM_NOP6 _ASM_MK_NOP(K7_NOP6)
#define ASM_NOP7 _ASM_MK_NOP(K7_NOP7)
#define ASM_NOP8 _ASM_MK_NOP(K7_NOP8)
#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K7_NOP5_ATOMIC)
#elif defined(CONFIG_X86_P6_NOP)
#define ASM_NOP1 P6_NOP1
#define ASM_NOP2 P6_NOP2
#define ASM_NOP3 P6_NOP3
#define ASM_NOP4 P6_NOP4
#define ASM_NOP5 P6_NOP5
#define ASM_NOP6 P6_NOP6
#define ASM_NOP7 P6_NOP7
#define ASM_NOP8 P6_NOP8
#define ASM_NOP1 _ASM_MK_NOP(P6_NOP1)
#define ASM_NOP2 _ASM_MK_NOP(P6_NOP2)
#define ASM_NOP3 _ASM_MK_NOP(P6_NOP3)
#define ASM_NOP4 _ASM_MK_NOP(P6_NOP4)
#define ASM_NOP5 _ASM_MK_NOP(P6_NOP5)
#define ASM_NOP6 _ASM_MK_NOP(P6_NOP6)
#define ASM_NOP7 _ASM_MK_NOP(P6_NOP7)
#define ASM_NOP8 _ASM_MK_NOP(P6_NOP8)
#define ASM_NOP5_ATOMIC _ASM_MK_NOP(P6_NOP5_ATOMIC)
#elif defined(CONFIG_X86_64)
#define ASM_NOP1 K8_NOP1
#define ASM_NOP2 K8_NOP2
#define ASM_NOP3 K8_NOP3
#define ASM_NOP4 K8_NOP4
#define ASM_NOP5 K8_NOP5
#define ASM_NOP6 K8_NOP6
#define ASM_NOP7 K8_NOP7
#define ASM_NOP8 K8_NOP8
#define ASM_NOP1 _ASM_MK_NOP(K8_NOP1)
#define ASM_NOP2 _ASM_MK_NOP(K8_NOP2)
#define ASM_NOP3 _ASM_MK_NOP(K8_NOP3)
#define ASM_NOP4 _ASM_MK_NOP(K8_NOP4)
#define ASM_NOP5 _ASM_MK_NOP(K8_NOP5)
#define ASM_NOP6 _ASM_MK_NOP(K8_NOP6)
#define ASM_NOP7 _ASM_MK_NOP(K8_NOP7)
#define ASM_NOP8 _ASM_MK_NOP(K8_NOP8)
#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K8_NOP5_ATOMIC)
#else
#define ASM_NOP1 GENERIC_NOP1
#define ASM_NOP2 GENERIC_NOP2
#define ASM_NOP3 GENERIC_NOP3
#define ASM_NOP4 GENERIC_NOP4
#define ASM_NOP5 GENERIC_NOP5
#define ASM_NOP6 GENERIC_NOP6
#define ASM_NOP7 GENERIC_NOP7
#define ASM_NOP8 GENERIC_NOP8
#define ASM_NOP1 _ASM_MK_NOP(GENERIC_NOP1)
#define ASM_NOP2 _ASM_MK_NOP(GENERIC_NOP2)
#define ASM_NOP3 _ASM_MK_NOP(GENERIC_NOP3)
#define ASM_NOP4 _ASM_MK_NOP(GENERIC_NOP4)
#define ASM_NOP5 _ASM_MK_NOP(GENERIC_NOP5)
#define ASM_NOP6 _ASM_MK_NOP(GENERIC_NOP6)
#define ASM_NOP7 _ASM_MK_NOP(GENERIC_NOP7)
#define ASM_NOP8 _ASM_MK_NOP(GENERIC_NOP8)
#define ASM_NOP5_ATOMIC _ASM_MK_NOP(GENERIC_NOP5_ATOMIC)
#endif
#define ASM_NOP_MAX 8
#define NOP_ATOMIC5 (ASM_NOP_MAX+1) /* Entry for the 5-byte atomic NOP */
#ifndef __ASSEMBLY__
extern const unsigned char * const *ideal_nops;
extern void arch_init_ideal_nops(void);
#endif
#endif /* _ASM_X86_NOPS_H */

View file

@ -67,17 +67,30 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
#define DPRINTK(fmt, args...) if (debug_alternative) \
printk(KERN_DEBUG fmt, args)
/*
* Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
* that correspond to that nop. Getting from one nop to the next, we
* add to the array the offset that is equal to the sum of all sizes of
* nops preceding the one we are after.
*
* Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
* nice symmetry of sizes of the previous nops.
*/
#if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
/* Use inline assembly to define this because the nops are defined
as inline assembly strings in the include files and we cannot
get them easily into strings. */
asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nintelnops: "
GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
GENERIC_NOP7 GENERIC_NOP8
"\t.previous");
extern const unsigned char intelnops[];
static const unsigned char *const __initconst_or_module
intel_nops[ASM_NOP_MAX+1] = {
static const unsigned char intelnops[] =
{
GENERIC_NOP1,
GENERIC_NOP2,
GENERIC_NOP3,
GENERIC_NOP4,
GENERIC_NOP5,
GENERIC_NOP6,
GENERIC_NOP7,
GENERIC_NOP8,
GENERIC_NOP5_ATOMIC
};
static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
{
NULL,
intelnops,
intelnops + 1,
@ -87,17 +100,25 @@ intel_nops[ASM_NOP_MAX+1] = {
intelnops + 1 + 2 + 3 + 4 + 5,
intelnops + 1 + 2 + 3 + 4 + 5 + 6,
intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
#ifdef K8_NOP1
asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk8nops: "
K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
K8_NOP7 K8_NOP8
"\t.previous");
extern const unsigned char k8nops[];
static const unsigned char *const __initconst_or_module
k8_nops[ASM_NOP_MAX+1] = {
static const unsigned char k8nops[] =
{
K8_NOP1,
K8_NOP2,
K8_NOP3,
K8_NOP4,
K8_NOP5,
K8_NOP6,
K8_NOP7,
K8_NOP8,
K8_NOP5_ATOMIC
};
static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
{
NULL,
k8nops,
k8nops + 1,
@ -107,17 +128,25 @@ k8_nops[ASM_NOP_MAX+1] = {
k8nops + 1 + 2 + 3 + 4 + 5,
k8nops + 1 + 2 + 3 + 4 + 5 + 6,
k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
#if defined(K7_NOP1) && !defined(CONFIG_X86_64)
asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk7nops: "
K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
K7_NOP7 K7_NOP8
"\t.previous");
extern const unsigned char k7nops[];
static const unsigned char *const __initconst_or_module
k7_nops[ASM_NOP_MAX+1] = {
static const unsigned char k7nops[] =
{
K7_NOP1,
K7_NOP2,
K7_NOP3,
K7_NOP4,
K7_NOP5,
K7_NOP6,
K7_NOP7,
K7_NOP8,
K7_NOP5_ATOMIC
};
static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
{
NULL,
k7nops,
k7nops + 1,
@ -127,17 +156,25 @@ k7_nops[ASM_NOP_MAX+1] = {
k7nops + 1 + 2 + 3 + 4 + 5,
k7nops + 1 + 2 + 3 + 4 + 5 + 6,
k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
#ifdef P6_NOP1
asm("\t" __stringify(__INITRODATA_OR_MODULE) "\np6nops: "
P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
P6_NOP7 P6_NOP8
"\t.previous");
extern const unsigned char p6nops[];
static const unsigned char *const __initconst_or_module
p6_nops[ASM_NOP_MAX+1] = {
static const unsigned char __initconst_or_module p6nops[] =
{
P6_NOP1,
P6_NOP2,
P6_NOP3,
P6_NOP4,
P6_NOP5,
P6_NOP6,
P6_NOP7,
P6_NOP8,
P6_NOP5_ATOMIC
};
static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
{
NULL,
p6nops,
p6nops + 1,
@ -147,47 +184,53 @@ p6_nops[ASM_NOP_MAX+1] = {
p6nops + 1 + 2 + 3 + 4 + 5,
p6nops + 1 + 2 + 3 + 4 + 5 + 6,
p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif
/* Initialize these to a safe default */
#ifdef CONFIG_X86_64
const unsigned char * const *ideal_nops = p6_nops;
#else
const unsigned char * const *ideal_nops = intel_nops;
#endif
extern char __vsyscall_0;
static const unsigned char *const *__init_or_module find_nop_table(void)
void __init arch_init_ideal_nops(void)
{
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
boot_cpu_has(X86_FEATURE_NOPL))
return p6_nops;
else
return k8_nops;
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_INTEL:
if (boot_cpu_has(X86_FEATURE_NOPL)) {
ideal_nops = p6_nops;
} else {
#ifdef CONFIG_X86_64
ideal_nops = k8_nops;
#else
ideal_nops = intel_nops;
#endif
}
default:
#ifdef CONFIG_X86_64
ideal_nops = k8_nops;
#else
if (boot_cpu_has(X86_FEATURE_K8))
ideal_nops = k8_nops;
else if (boot_cpu_has(X86_FEATURE_K7))
ideal_nops = k7_nops;
else
ideal_nops = intel_nops;
#endif
}
}
#else /* CONFIG_X86_64 */
static const unsigned char *const *__init_or_module find_nop_table(void)
{
if (boot_cpu_has(X86_FEATURE_K8))
return k8_nops;
else if (boot_cpu_has(X86_FEATURE_K7))
return k7_nops;
else if (boot_cpu_has(X86_FEATURE_NOPL))
return p6_nops;
else
return intel_nops;
}
#endif /* CONFIG_X86_64 */
/* Use this to add nops to a buffer, then text_poke the whole buffer. */
static void __init_or_module add_nops(void *insns, unsigned int len)
{
const unsigned char *const *noptable = find_nop_table();
while (len > 0) {
unsigned int noplen = len;
if (noplen > ASM_NOP_MAX)
noplen = ASM_NOP_MAX;
memcpy(insns, noptable[noplen], noplen);
memcpy(insns, ideal_nops[noplen], noplen);
insns += noplen;
len -= noplen;
}
@ -195,6 +238,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
extern char __vsyscall_0;
void *text_poke_early(void *addr, const void *opcode, size_t len);
/* Replace instructions with better alternatives for this CPU type.
@ -678,29 +722,3 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
wrote_text = 0;
__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
}
#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
#ifdef CONFIG_X86_64
unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };
#else
unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
#endif
void __init arch_init_ideal_nop5(void)
{
/*
* There is no good nop for all x86 archs. This selection
* algorithm should be unified with the one in find_nop_table(),
* but this should be good enough for now.
*
* For cases other than the ones below, use the safe (as in
* always functional) defaults above.
*/
#ifdef CONFIG_X86_64
/* Don't use these on 32 bits due to broken virtualizers */
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
memcpy(ideal_nop5, p6_nops[5], 5);
#endif
}
#endif

View file

@ -260,9 +260,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
return mod_code_status;
}
static unsigned char *ftrace_nop_replace(void)
static const unsigned char *ftrace_nop_replace(void)
{
return ideal_nop5;
return ideal_nops[NOP_ATOMIC5];
}
static int

View file

@ -34,7 +34,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
code.offset = entry->target -
(entry->code + JUMP_LABEL_NOP_SIZE);
} else
memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE);
memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
get_online_cpus();
mutex_lock(&text_mutex);
text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
@ -44,7 +44,8 @@ void arch_jump_label_transform(struct jump_entry *entry,
void arch_jump_label_text_poke_early(jump_label_t addr)
{
text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE);
text_poke_early((void *)addr, ideal_nops[NOP_ATOMIC5],
JUMP_LABEL_NOP_SIZE);
}
#endif

View file

@ -691,8 +691,6 @@ early_param("reservelow", parse_reservelow);
void __init setup_arch(char **cmdline_p)
{
unsigned long flags;
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
visws_early_detect();
@ -1036,9 +1034,7 @@ void __init setup_arch(char **cmdline_p)
mcheck_init();
local_irq_save(flags);
arch_init_ideal_nop5();
local_irq_restore(flags);
arch_init_ideal_nops();
}
#ifdef CONFIG_X86_32