linux/include/asm-x86/system.h
Andi Kleen fde1b3fa94 x86: introduce rdtsc_barrier()
rdtsc_barrier() is a new barrier primitive that stops RDTSC speculation
to avoid races with timer interrupts on other CPUs.

It expands either to LFENCE (for Intel CPUs) or MFENCE (for
AMD CPUs) which stops RDTSC on all currently known microarchitectures
that implement SSE. On CPUs without SSE there is generally no RDTSC
speculation.

[ mingo@elte.hu: renamed it to rdtsc_barrier() and made it x86-only ]

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 13:32:38 +01:00

412 lines
11 KiB
C

#ifndef _ASM_X86_SYSTEM_H_
#define _ASM_X86_SYSTEM_H_
#include <asm/asm.h>
#include <asm/segment.h>
#include <asm/cpufeature.h>
#include <asm/cmpxchg.h>
#include <asm/nops.h>
#include <linux/kernel.h>
#include <linux/irqflags.h>
/* entries in ARCH_DLINFO: */
#ifdef CONFIG_IA32_EMULATION
# define AT_VECTOR_SIZE_ARCH 2
#else
# define AT_VECTOR_SIZE_ARCH 1
#endif
#ifdef CONFIG_X86_32
struct task_struct; /* one of the stranger aspects of C forward declarations */
extern struct task_struct *FASTCALL(__switch_to(struct task_struct *prev,
struct task_struct *next));
/*
* Saving eflags is important. It switches not only IOPL between tasks,
* it also protects other tasks from NT leaking through sysenter etc.
*/
#define switch_to(prev, next, last) do { \
unsigned long esi, edi; \
asm volatile("pushfl\n\t" /* Save flags */ \
"pushl %%ebp\n\t" \
"movl %%esp,%0\n\t" /* save ESP */ \
"movl %5,%%esp\n\t" /* restore ESP */ \
"movl $1f,%1\n\t" /* save EIP */ \
"pushl %6\n\t" /* restore EIP */ \
"jmp __switch_to\n" \
"1:\t" \
"popl %%ebp\n\t" \
"popfl" \
:"=m" (prev->thread.sp), "=m" (prev->thread.ip), \
"=a" (last), "=S" (esi), "=D" (edi) \
:"m" (next->thread.sp), "m" (next->thread.ip), \
"2" (prev), "d" (next)); \
} while (0)
/*
* disable hlt during certain critical i/o operations
*/
#define HAVE_DISABLE_HLT
#else
#define __SAVE(reg, offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
#define __RESTORE(reg, offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
/* frame pointer must be last for get_wchan */
#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
#define __EXTRA_CLOBBER \
, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
"r12", "r13", "r14", "r15"
/* Save restore flags to clear handle leaking NT */
#define switch_to(prev, next, last) \
asm volatile(SAVE_CONTEXT \
"movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
"movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \
"call __switch_to\n\t" \
".globl thread_return\n" \
"thread_return:\n\t" \
"movq %%gs:%P[pda_pcurrent],%%rsi\n\t" \
"movq %P[thread_info](%%rsi),%%r8\n\t" \
LOCK_PREFIX "btr %[tif_fork],%P[ti_flags](%%r8)\n\t" \
"movq %%rax,%%rdi\n\t" \
"jc ret_from_fork\n\t" \
RESTORE_CONTEXT \
: "=a" (last) \
: [next] "S" (next), [prev] "D" (prev), \
[threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
[ti_flags] "i" (offsetof(struct thread_info, flags)), \
[tif_fork] "i" (TIF_FORK), \
[thread_info] "i" (offsetof(struct task_struct, stack)), \
[pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent)) \
: "memory", "cc" __EXTRA_CLOBBER)
#endif
#ifdef __KERNEL__
#define _set_base(addr, base) do { unsigned long __pr; \
__asm__ __volatile__ ("movw %%dx,%1\n\t" \
"rorl $16,%%edx\n\t" \
"movb %%dl,%2\n\t" \
"movb %%dh,%3" \
:"=&d" (__pr) \
:"m" (*((addr)+2)), \
"m" (*((addr)+4)), \
"m" (*((addr)+7)), \
"0" (base) \
); } while (0)
#define _set_limit(addr, limit) do { unsigned long __lr; \
__asm__ __volatile__ ("movw %%dx,%1\n\t" \
"rorl $16,%%edx\n\t" \
"movb %2,%%dh\n\t" \
"andb $0xf0,%%dh\n\t" \
"orb %%dh,%%dl\n\t" \
"movb %%dl,%2" \
:"=&d" (__lr) \
:"m" (*(addr)), \
"m" (*((addr)+6)), \
"0" (limit) \
); } while (0)
#define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base))
#define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1))
extern void load_gs_index(unsigned);
/*
* Load a segment. Fall back on loading the zero
* segment if something goes wrong..
*/
#define loadsegment(seg, value) \
asm volatile("\n" \
"1:\t" \
"movl %k0,%%" #seg "\n" \
"2:\n" \
".section .fixup,\"ax\"\n" \
"3:\t" \
"movl %k1, %%" #seg "\n\t" \
"jmp 2b\n" \
".previous\n" \
".section __ex_table,\"a\"\n\t" \
_ASM_ALIGN "\n\t" \
_ASM_PTR " 1b,3b\n" \
".previous" \
: :"r" (value), "r" (0))
/*
* Save a segment register away
*/
#define savesegment(seg, value) \
asm volatile("mov %%" #seg ",%0":"=rm" (value))
static inline unsigned long get_limit(unsigned long segment)
{
unsigned long __limit;
__asm__("lsll %1,%0"
:"=r" (__limit):"r" (segment));
return __limit+1;
}
static inline void native_clts(void)
{
asm volatile ("clts");
}
/*
* Volatile isn't enough to prevent the compiler from reordering the
* read/write functions for the control registers and messing everything up.
* A memory clobber would solve the problem, but would prevent reordering of
* all loads stores around it, which can hurt performance. Solution is to
* use a variable and mimic reads and writes to it to enforce serialization
*/
static unsigned long __force_order;
static inline unsigned long native_read_cr0(void)
{
unsigned long val;
asm volatile("mov %%cr0,%0\n\t" :"=r" (val), "=m" (__force_order));
return val;
}
static inline void native_write_cr0(unsigned long val)
{
asm volatile("mov %0,%%cr0": :"r" (val), "m" (__force_order));
}
static inline unsigned long native_read_cr2(void)
{
unsigned long val;
asm volatile("mov %%cr2,%0\n\t" :"=r" (val), "=m" (__force_order));
return val;
}
static inline void native_write_cr2(unsigned long val)
{
asm volatile("mov %0,%%cr2": :"r" (val), "m" (__force_order));
}
static inline unsigned long native_read_cr3(void)
{
unsigned long val;
asm volatile("mov %%cr3,%0\n\t" :"=r" (val), "=m" (__force_order));
return val;
}
static inline void native_write_cr3(unsigned long val)
{
asm volatile("mov %0,%%cr3": :"r" (val), "m" (__force_order));
}
static inline unsigned long native_read_cr4(void)
{
unsigned long val;
asm volatile("mov %%cr4,%0\n\t" :"=r" (val), "=m" (__force_order));
return val;
}
static inline unsigned long native_read_cr4_safe(void)
{
unsigned long val;
/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
* exists, so it will never fail. */
#ifdef CONFIG_X86_32
asm volatile("1: mov %%cr4, %0 \n"
"2: \n"
".section __ex_table,\"a\" \n"
".long 1b,2b \n"
".previous \n"
: "=r" (val), "=m" (__force_order) : "0" (0));
#else
val = native_read_cr4();
#endif
return val;
}
static inline void native_write_cr4(unsigned long val)
{
asm volatile("mov %0,%%cr4": :"r" (val), "m" (__force_order));
}
static inline void native_wbinvd(void)
{
asm volatile("wbinvd": : :"memory");
}
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define read_cr0() (native_read_cr0())
#define write_cr0(x) (native_write_cr0(x))
#define read_cr2() (native_read_cr2())
#define write_cr2(x) (native_write_cr2(x))
#define read_cr3() (native_read_cr3())
#define write_cr3(x) (native_write_cr3(x))
#define read_cr4() (native_read_cr4())
#define read_cr4_safe() (native_read_cr4_safe())
#define write_cr4(x) (native_write_cr4(x))
#define wbinvd() (native_wbinvd())
#ifdef CONFIG_X86_64
static inline unsigned long read_cr8(void)
{
unsigned long cr8;
asm volatile("movq %%cr8,%0" : "=r" (cr8));
return cr8;
}
static inline void write_cr8(unsigned long val)
{
asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
}
#endif
/* Clear the 'TS' bit */
#define clts() (native_clts())
#endif/* CONFIG_PARAVIRT */
#define stts() write_cr0(8 | read_cr0())
#endif /* __KERNEL__ */
static inline void clflush(void *__p)
{
asm volatile("clflush %0" : "+m" (*(char __force *)__p));
}
#define nop() __asm__ __volatile__ ("nop")
void disable_hlt(void);
void enable_hlt(void);
extern int es7000_plat;
void cpu_idle_wait(void);
extern unsigned long arch_align_stack(unsigned long sp);
extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
void default_idle(void);
/*
* Force strict CPU ordering.
* And yes, this is required on UP too when we're talking
* to devices.
*/
#ifdef CONFIG_X86_32
/*
* For now, "wmb()" doesn't actually do anything, as all
* Intel CPU's follow what Intel calls a *Processor Order*,
* in which all writes are seen in the program order even
* outside the CPU.
*
* I expect future Intel CPU's to have a weaker ordering,
* but I'd also expect them to finally get their act together
* and add some real memory barriers if so.
*
* Some non intel clones support out of order store. wmb() ceases to be a
* nop for these.
*/
#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
#else
#define mb() asm volatile("mfence":::"memory")
#define rmb() asm volatile("lfence":::"memory")
#define wmb() asm volatile("sfence" ::: "memory")
#endif
/**
* read_barrier_depends - Flush all pending reads that subsequents reads
* depend on.
*
* No data-dependent reads from memory-like regions are ever reordered
* over this barrier. All reads preceding this primitive are guaranteed
* to access memory (but not necessarily other CPUs' caches) before any
* reads following this primitive that depend on the data return by
* any of the preceding reads. This primitive is much lighter weight than
* rmb() on most CPUs, and is never heavier weight than is
* rmb().
*
* These ordering constraints are respected by both the local CPU
* and the compiler.
*
* Ordering is not guaranteed by anything other than these primitives,
* not even by data dependencies. See the documentation for
* memory_barrier() for examples and URLs to more information.
*
* For example, the following code would force ordering (the initial
* value of "a" is zero, "b" is one, and "p" is "&a"):
*
* <programlisting>
* CPU 0 CPU 1
*
* b = 2;
* memory_barrier();
* p = &b; q = p;
* read_barrier_depends();
* d = *q;
* </programlisting>
*
* because the read of "*q" depends on the read of "p" and these
* two reads are separated by a read_barrier_depends(). However,
* the following code, with the same initial values for "a" and "b":
*
* <programlisting>
* CPU 0 CPU 1
*
* a = 2;
* memory_barrier();
* b = 3; y = b;
* read_barrier_depends();
* x = a;
* </programlisting>
*
* does not enforce ordering, since there is no data dependency between
* the read of "a" and the read of "b". Therefore, on some CPUs, such
* as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
* in cases like this where there are no data dependencies.
**/
#define read_barrier_depends() do { } while (0)
#ifdef CONFIG_SMP
#define smp_mb() mb()
#ifdef CONFIG_X86_PPRO_FENCE
# define smp_rmb() rmb()
#else
# define smp_rmb() barrier()
#endif
#ifdef CONFIG_X86_OOSTORE
# define smp_wmb() wmb()
#else
# define smp_wmb() barrier()
#endif
#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
#else
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
#define smp_read_barrier_depends() do { } while (0)
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif
/*
* Stop RDTSC speculation. This is needed when you need to use RDTSC
* (or get_cycles or vread that possibly accesses the TSC) in a defined
* code region.
*
* (Could use an alternative three way for this if there was one.)
*/
static inline void rdtsc_barrier(void)
{
alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
}
#endif