linux-stable/arch/x86/include/asm/special_insns.h
Ross Zwisler d9dc64f30a x86/asm: Add support for the CLWB instruction
Add support for the new CLWB (cache line write back)
instruction.  This instruction was announced in the document
"Intel Architecture Instruction Set Extensions Programming
Reference" with reference number 319433-022.

  https://software.intel.com/sites/default/files/managed/0d/53/319433-022.pdf

The CLWB instruction is used to write back the contents of
dirtied cache lines to memory without evicting the cache lines
from the processor's cache hierarchy.  This should be used in
favor of clflushopt or clflush in cases where you require the
cache line to be written to memory but plan to access the data
again in the near future.

One of the main use cases for this is with persistent memory
where CLWB can be used with PCOMMIT to ensure that data has been
accepted to memory and is durable on the DIMM.

This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH
and PCOMMIT with appropriate fencing:

void flush_and_commit_buffer(void *vaddr, unsigned int size)
{
	void *vend = vaddr + size - 1;

	for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
		clwb(vaddr);

	/* Flush any possible final partial cacheline */
	clwb(vend);

	/*
	 * Use SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes.
	 * (MFENCE via mb() also works)
	 */
	wmb();

	/* PCOMMIT and the required SFENCE for ordering */
	pcommit_sfence();
}

After this function completes the data pointed to by vaddr is
has been accepted to memory and will be durable if the vaddr
points to persistent memory.

Regarding the details of how the alternatives assembly is set
up, we need one additional byte at the beginning of the CLFLUSH
so that we can flip it into a CLFLUSHOPT by changing that byte
into a 0x66 prefix.  Two options are to either insert a 1 byte
ASM_NOP1, or to add a 1 byte NOP_DS_PREFIX.  Both have no
functional effect with the plain CLFLUSH, but I've been told
that executing a CLFLUSH + prefix should be faster than
executing a CLFLUSH + NOP.

We had to hard code the assembly for CLWB because, lacking the
ability to assemble the CLWB instruction itself, the next
closest thing is to have an xsaveopt instruction with a 0x66
prefix.  Unfortunately XSAVEOPT itself is also relatively new,
and isn't included by all the GCC versions that the kernel needs
to support.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Acked-by: Borislav Petkov <bp@suse.de>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1422377631-8986-3-git-send-email-ross.zwisler@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-03 06:56:38 +02:00

231 lines
4.6 KiB
C

#ifndef _ASM_X86_SPECIAL_INSNS_H
#define _ASM_X86_SPECIAL_INSNS_H
#ifdef __KERNEL__
#include <asm/nops.h>
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));
}
static inline void clwb(volatile void *__p)
{
volatile struct { char x[64]; } *p = __p;
asm volatile(ALTERNATIVE_2(
".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])",
".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */
X86_FEATURE_CLFLUSHOPT,
".byte 0x66, 0x0f, 0xae, 0x30", /* clwb (%%rax) */
X86_FEATURE_CLWB)
: [p] "+m" (*p)
: [pax] "a" (p));
}
static inline void pcommit_sfence(void)
{
alternative(ASM_NOP7,
".byte 0x66, 0x0f, 0xae, 0xf8\n\t" /* pcommit */
"sfence",
X86_FEATURE_PCOMMIT);
}
#define nop() asm volatile ("nop")
#endif /* __KERNEL__ */
#endif /* _ASM_X86_SPECIAL_INSNS_H */