x86: remove CR reads from exit-to-guest path

CR3 is - during normal operation - only ever loaded from v->arch.cr3,
so there's no need to read the actual control register. For CR4 we can
generally use the cached value on all synchronous entry end exit paths.
Drop the write_cr3 macro, as the two use sites are probably easier to
follow without its use.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
master commit: 31bf55cb5f
master date: 2018-03-06 16:49:36 +0100

xen/arch/x86/x86_64/asm-offsets.c

@@ -88,6 +88,7 @@ void __dummy__(void)
     OFFSET(VCPU_kernel_ss, struct vcpu, arch.pv_vcpu.kernel_ss);
     OFFSET(VCPU_iopl, struct vcpu, arch.pv_vcpu.iopl);
     OFFSET(VCPU_guest_context_flags, struct vcpu, arch.vgc_flags);
+    OFFSET(VCPU_cr3, struct vcpu, arch.cr3);
     OFFSET(VCPU_arch_spec_ctrl, struct vcpu, arch.spec_ctrl);
     OFFSET(VCPU_nmi_pending, struct vcpu, nmi_pending);
     OFFSET(VCPU_mce_pending, struct vcpu, mce_pending);

xen/arch/x86/x86_64/entry.S

@@ -43,7 +43,7 @@ restore_all_guest:
         mov   VCPU_arch_spec_ctrl(%rbx), %r15d
 
         /* Copy guest mappings and switch to per-CPU root page table. */
-        mov   %cr3, %r9
+        mov   VCPU_cr3(%rbx), %r9
         GET_STACK_END(dx)
         mov   STACK_CPUINFO_FIELD(pv_cr3)(%rdx), %rdi
         movabs $PADDR_MASK & PAGE_MASK, %rsi
@@ -65,8 +65,13 @@ restore_all_guest:
         sub   $(ROOT_PAGETABLE_FIRST_XEN_SLOT - \
                 ROOT_PAGETABLE_LAST_XEN_SLOT - 1) * 8, %rdi
         rep movsq
+        mov   STACK_CPUINFO_FIELD(cr4)(%rdx), %rdi
         mov   %r9, STACK_CPUINFO_FIELD(xen_cr3)(%rdx)
-        write_cr3 rax, rdi, rsi
+        mov   %rdi, %rsi
+        and   $~X86_CR4_PGE, %rdi
+        mov   %rdi, %cr4
+        mov   %rax, %cr3
+        mov   %rsi, %cr4
 .Lrag_keep_cr3:
 
         /* Restore stashed SPEC_CTRL value. */
@@ -122,7 +127,12 @@ restore_all_xen:
          * so "g" will have to do.
          */
 UNLIKELY_START(g, exit_cr3)
-        write_cr3 rax, rdi, rsi
+        mov   %cr4, %rdi
+        mov   %rdi, %rsi
+        and   $~X86_CR4_PGE, %rdi
+        mov   %rdi, %cr4
+        mov   %rax, %cr3
+        mov   %rsi, %cr4
 UNLIKELY_END(exit_cr3)
 
         /* WARNING! `ret`, `call *`, `jmp *` not safe beyond this point. */

xen/include/asm-x86/asm_defns.h

@@ -207,15 +207,6 @@ void ret_from_intr(void);
 #define ASM_STAC ASM_AC(STAC)
 #define ASM_CLAC ASM_AC(CLAC)
 
-.macro write_cr3 val:req, tmp1:req, tmp2:req
-        mov   %cr4, %\tmp1
-        mov   %\tmp1, %\tmp2
-        and   $~X86_CR4_PGE, %\tmp1
-        mov   %\tmp1, %cr4
-        mov   %\val, %cr3
-        mov   %\tmp2, %cr4
-.endm
-
 #define CR4_PV32_RESTORE                                           \
         667: ASM_NOP5;                                             \
         .pushsection .altinstr_replacement, "ax";                  \