From 719d359dc7b6be3e43d6661f192ceb980b10ee26 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Thu, 19 Feb 2015 10:37:28 -0700 Subject: [PATCH] x86/asm: Add support for the pcommit instruction Add support for the new pcommit (persistent commit) 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 pcommit instruction ensures that data that has been flushed from the processor's cache hierarchy with clwb, clflushopt or clflush is accepted to memory and is durable on the DIMM. The primary use case for this is persistent memory. 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); /* * 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. Pcommit must always be ordered by an mfence or sfence, so to help simplify things we include both the pcommit and the required sfence in the alternatives generated by pcommit_sfence(). The other option is to keep them separated, but on platforms that don't support pcommit this would then turn into: 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); /* * sfence to order clwb/clflushopt/clflush cache flushes * mfence via mb() also works */ wmb(); nop(); /* from pcommit(), via alternatives */ /* * sfence to order pcommit * mfence via mb() also works */ wmb(); } This is still correct, but now you've got two fences separated by only a nop. With the commit and the fence together in pcommit_sfence() you avoid the final unneeded fence. Signed-off-by: Ross Zwisler Acked-by: Borislav Petkov Acked-by: H. Peter Anvin Cc: Linus Torvalds Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1424367448-24254-1-git-send-email-ross.zwisler@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpufeature.h | 1 + arch/x86/include/asm/special_insns.h | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 90a5485..d6428ea 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -231,6 +231,7 @@ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index e820c08..0962501 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -4,6 +4,8 @@ #ifdef __KERNEL__ +#include + static inline void native_clts(void) { asm volatile("clts"); @@ -199,6 +201,14 @@ static inline void clflushopt(volatile void *__p) "+m" (*(volatile char __force *)__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") -- 2.7.4