linux_dsm_epyc7002/arch/x86/include/asm/special_insns.h
Andy Lutomirski 1e02ce4ccc x86: Store a per-cpu shadow copy of CR4
Context switches and TLB flushes can change individual bits of CR4.
CR4 reads take several cycles, so store a shadow copy of CR4 in a
per-cpu variable.

To avoid wasting a cache line, I added the CR4 shadow to
cpu_tlbstate, which is already touched in switch_mm.  The heaviest
users of the cr4 shadow will be switch_mm and __switch_to_xtra, and
__switch_to_xtra is called shortly after switch_mm during context
switch, so the cacheline is likely to be hot.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Vince Weaver <vince@deater.net>
Cc: "hillf.zj" <hillf.zj@alibaba-inc.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/3a54dd3353fffbf84804398e00dfdc5b7c1afd7d.1414190806.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-04 12:10:42 +01:00

208 lines
4.1 KiB
C

#ifndef _ASM_X86_SPECIAL_INSNS_H
#define _ASM_X86_SPECIAL_INSNS_H
#ifdef __KERNEL__
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
*/
extern 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"
_ASM_EXTABLE(1b, 2b)
: "=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));
}
#ifdef CONFIG_X86_64
static inline unsigned long native_read_cr8(void)
{
unsigned long cr8;
asm volatile("movq %%cr8,%0" : "=r" (cr8));
return cr8;
}
static inline void native_write_cr8(unsigned long val)
{
asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
}
#endif
static inline void native_wbinvd(void)
{
asm volatile("wbinvd": : :"memory");
}
extern asmlinkage void native_load_gs_index(unsigned);
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
static inline unsigned long read_cr0(void)
{
return native_read_cr0();
}
static inline void write_cr0(unsigned long x)
{
native_write_cr0(x);
}
static inline unsigned long read_cr2(void)
{
return native_read_cr2();
}
static inline void write_cr2(unsigned long x)
{
native_write_cr2(x);
}
static inline unsigned long read_cr3(void)
{
return native_read_cr3();
}
static inline void write_cr3(unsigned long x)
{
native_write_cr3(x);
}
static inline unsigned long __read_cr4(void)
{
return native_read_cr4();
}
static inline unsigned long __read_cr4_safe(void)
{
return native_read_cr4_safe();
}
static inline void __write_cr4(unsigned long x)
{
native_write_cr4(x);
}
static inline void wbinvd(void)
{
native_wbinvd();
}
#ifdef CONFIG_X86_64
static inline unsigned long read_cr8(void)
{
return native_read_cr8();
}
static inline void write_cr8(unsigned long x)
{
native_write_cr8(x);
}
static inline void load_gs_index(unsigned selector)
{
native_load_gs_index(selector);
}
#endif
/* Clear the 'TS' bit */
static inline void clts(void)
{
native_clts();
}
#endif/* CONFIG_PARAVIRT */
#define stts() write_cr0(read_cr0() | X86_CR0_TS)
static inline void clflush(volatile void *__p)
{
asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
}
static inline void clflushopt(volatile void *__p)
{
alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
".byte 0x66; clflush %P0",
X86_FEATURE_CLFLUSHOPT,
"+m" (*(volatile char __force *)__p));
}
#define nop() asm volatile ("nop")
#endif /* __KERNEL__ */
#endif /* _ASM_X86_SPECIAL_INSNS_H */