pmem: add wb_cache_pmem() to the PMEM API

__arch_wb_cache_pmem() was already an internal implementation detail of
the x86 PMEM API, but this functionality needs to be exported as part of
the general PMEM API to handle the fsync/msync case for DAX mmaps.

One thing worth noting is that we really do want this to be part of the
PMEM API as opposed to a stand-alone function like clflush_cache_range()
because of ordering restrictions. By having wb_cache_pmem() as part of
the PMEM API we can leave it unordered, call it multiple times to write
back large amounts of memory, and then order the multiple calls with a
single wmb_pmem().

Signed-off-by: Ross Zwisler <[e-mail]>
Cc: "H. Peter Anvin" <[e-mail]>
Cc: "J. Bruce Fields" <[e-mail]>
Cc: "Theodore Ts'o" <[e-mail]>
Cc: Alexander Viro <[e-mail]>
Cc: Andreas Dilger <[e-mail]>
Cc: Dave Chinner <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jan Kara <[e-mail]>
Cc: Jeff Layton <[e-mail]>
Cc: Matthew Wilcox <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: Dan Williams <[e-mail]>
Cc: Matthew Wilcox <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

arch/x86/include/asm/pmem.h

···
 }
 
 /**
- * __arch_wb_cache_pmem - write back a cache range with CLWB
+ * arch_wb_cache_pmem - write back a cache range with CLWB
  * @vaddr:	virtual start address
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
  * instruction.  This function requires explicit ordering with an
- * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ * arch_wmb_pmem() call.
  */
-static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
+static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
 {
 	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
 	unsigned long clflush_mask = x86_clflush_size - 1;
+	void *vaddr = (void __force *)addr;
 	void *vend = vaddr + size;
 	void *p;
 
···
 	len = copy_from_iter_nocache(vaddr, bytes, i);
 
 	if (__iter_needs_pmem_wb(i))
-		__arch_wb_cache_pmem(vaddr, bytes);
+		arch_wb_cache_pmem(addr, bytes);
 
 	return len;
 }
···
 	void *vaddr = (void __force *)addr;
 
 	memset(vaddr, 0, size);
-	__arch_wb_cache_pmem(vaddr, size);
+	arch_wb_cache_pmem(addr, size);
 }
 
 static inline bool __arch_has_wmb_pmem(void)

include/linux/pmem.h

···
 {
 	BUG();
 }
+
+static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
+{
+	BUG();
+}
 #endif
 
 /*
  * Architectures that define ARCH_HAS_PMEM_API must provide
  * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(),
- * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem().
+ * arch_copy_from_iter_pmem(), arch_clear_pmem(), arch_wb_cache_pmem()
+ * and arch_has_wmb_pmem().
  */
 static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size)
 {
···
 		arch_clear_pmem(addr, size);
 	else
 		default_clear_pmem(addr, size);
+}
+
+/**
+ * wb_cache_pmem - write back processor cache for PMEM memory range
+ * @addr:	virtual start address
+ * @size:	number of bytes to write back
+ *
+ * Write back the processor cache range starting at 'addr' for 'size' bytes.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline void wb_cache_pmem(void __pmem *addr, size_t size)
+{
+	if (arch_has_pmem_api())
+		arch_wb_cache_pmem(addr, size);
 }
 #endif /* __PMEM_H__ */