This not only eases using the cached value in assembly code, but also
improves the generated code resulting from such reads in C.

Signed-off-by: Jan Beulich <jbeulich@suse.com>

--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -64,7 +64,6 @@
 #include <asm/psr.h>
 
 DEFINE_PER_CPU(struct vcpu *, curr_vcpu);
-DEFINE_PER_CPU(unsigned long, cr4);
 
 static void default_idle(void);
 void (*pm_idle) (void) __read_mostly = default_idle;
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -645,7 +645,7 @@ void __init noreturn __start_xen(unsigne
     parse_video_info();
 
     rdmsrl(MSR_EFER, this_cpu(efer));
-    asm volatile ( "mov %%cr4,%0" : "=r" (this_cpu(cr4)) );
+    asm volatile ( "mov %%cr4,%0" : "=r" (get_cpu_info()->cr4) );
 
     /* We initialise the serial devices very early so we can get debugging. */
     ns16550.io_base = 0x3f8;
--- a/xen/include/asm-x86/current.h
+++ b/xen/include/asm-x86/current.h
@@ -41,8 +41,8 @@ struct cpu_info {
     unsigned int processor_id;
     struct vcpu *current_vcpu;
     unsigned long per_cpu_offset;
+    unsigned long cr4;
     /* get_stack_bottom() must be 16-byte aligned */
-    unsigned long __pad_for_stack_bottom;
 };
 
 static inline struct cpu_info *get_cpu_info(void)
--- a/xen/include/asm-x86/processor.h
+++ b/xen/include/asm-x86/processor.h
@@ -328,8 +328,6 @@ static inline unsigned long read_cr2(voi
     return cr2;
 }
 
-DECLARE_PER_CPU(unsigned long, cr4);
-
 static inline void raw_write_cr4(unsigned long val)
 {
     asm volatile ( "mov %0,%%cr4" : : "r" (val) );
@@ -337,12 +335,12 @@ static inline void raw_write_cr4(unsigne
 
 static inline unsigned long read_cr4(void)
 {
-    return this_cpu(cr4);
+    return get_cpu_info()->cr4;
 }
 
 static inline void write_cr4(unsigned long val)
 {
-    this_cpu(cr4) = val;
+    get_cpu_info()->cr4 = val;
     raw_write_cr4(val);
 }