--- zzzz-none-000/linux-3.10.107/arch/x86/include/asm/special_insns.h	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/x86/include/asm/special_insns.h	2021-02-04 17:41:59.000000000 +0000
@@ -4,6 +4,8 @@
 
 #ifdef __KERNEL__
 
+#include <asm/nops.h>
+
 static inline void native_clts(void)
 {
 	asm volatile("clts");
@@ -16,7 +18,7 @@
  * 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;
+extern unsigned long __force_order;
 
 static inline unsigned long native_read_cr0(void)
 {
@@ -101,7 +103,7 @@
 	asm volatile("wbinvd": : :"memory");
 }
 
-extern void native_load_gs_index(unsigned);
+extern asmlinkage void native_load_gs_index(unsigned);
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
@@ -137,17 +139,17 @@
 	native_write_cr3(x);
 }
 
-static inline unsigned long read_cr4(void)
+static inline unsigned long __read_cr4(void)
 {
 	return native_read_cr4();
 }
 
-static inline unsigned long read_cr4_safe(void)
+static inline unsigned long __read_cr4_safe(void)
 {
 	return native_read_cr4_safe();
 }
 
-static inline void write_cr4(unsigned long x)
+static inline void __write_cr4(unsigned long x)
 {
 	native_write_cr4(x);
 }
@@ -191,6 +193,74 @@
 	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));
+}
+
+/**
+ * pcommit_sfence() - persistent commit and fence
+ *
+ * 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.
+ *
+ * Example:
+ * void flush_and_commit_buffer(void *vaddr, unsigned int size)
+ * {
+ *         unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ *         void *vend = vaddr + size;
+ *         void *p;
+ *
+ *         for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ *              p < vend; p += boot_cpu_data.x86_clflush_size)
+ *                 clwb(p);
+ *
+ *         // 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' 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().
+ */
+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")