x86: Make it so that __pa_symbol can only process kernel symbols on x86_64

I submitted an earlier patch that make __phys_addr an inline. This obviously
results in an increase in the code size. One step I can take to reduce that
is to make it so that the __pa_symbol call does a direct translation for
kernel addresses instead of covering all of virtual memory.

On my system this reduced the size for __pa_symbol from 5 instructions
totalling 30 bytes to 3 instructions totalling 16 bytes.

Signed-off-by: Alexander Duyck <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: H. Peter Anvin <[e-mail]>

arch/x86/include/asm/page.h

···
  * case properly. Once all supported versions of gcc understand it, we can
  * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated)
  */
-#define __pa_symbol(x)	__pa(__phys_reloc_hide((unsigned long)(x)))
+#define __pa_symbol(x) \
+	__phys_addr_symbol(__phys_reloc_hide((unsigned long)(x)))
 
 #define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
 

arch/x86/include/asm/page_32.h

···
 #else
 #define __phys_addr(x)		__phys_addr_nodebug(x)
 #endif
+#define __phys_addr_symbol(x)	__phys_addr(x)
 #define __phys_reloc_hide(x)	RELOC_HIDE((x), 0)
 
 #ifdef CONFIG_FLATMEM

arch/x86/include/asm/page_64.h

···
 
 #ifdef CONFIG_DEBUG_VIRTUAL
 extern unsigned long __phys_addr(unsigned long);
+extern unsigned long __phys_addr_symbol(unsigned long);
 #else
 #define __phys_addr(x)		__phys_addr_nodebug(x)
+#define __phys_addr_symbol(x) \
+	((unsigned long)(x) - __START_KERNEL_map + phys_base)
 #endif
 
 #define __phys_reloc_hide(x)	(x)

arch/x86/mm/physaddr.c

···
 	return x;
 }
 EXPORT_SYMBOL(__phys_addr);
+
+unsigned long __phys_addr_symbol(unsigned long x)
+{
+	unsigned long y = x - __START_KERNEL_map;
+
+	/* only check upper bounds since lower bounds will trigger carry */
+	VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE);
+
+	return y + phys_base;
+}
+EXPORT_SYMBOL(__phys_addr_symbol);
 #endif
 
 bool __virt_addr_valid(unsigned long x)