* Use XORL instead of XORQ to avoid a REX prefix and save some bytes in

the .fixup section, by Uros Bizjak.
 
 * Replace __force_order dummy variable with a memory clobber to fix LLVM
 requiring a definition for former and to prevent memory accesses from
 still being cached/reordered, by Arvind Sankar.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAl+EODIACgkQEsHwGGHe
 VUqPBRAAguaiNy8gPGNRSvqRWTzbxh/IAqB+5rjSH48biRnZm4o7Nsw9tL8kSXN/
 yWcGJxEtvheaITFh+rN31jINPCuLdQ2/LaJ+fX13zhgaMmX5RrLZ3FPoGa+eu+y5
 yAN8GaBM3VZ14Yzou8q5JF5001yRxXM8UsRzg8XVO7TORB6OOxnnrUbxYvUcLer5
 O219NnRtClU1ojZc5u2P1vR5McwIMf66qIkH1gn477utxeFOL380p/ukPOTNPYUH
 HsCVLJl0RPVQMI0UNiiRw6V76fHi38kIYJfR7Rg6Jy+k/U0z+eDXPg2/aHZj63NP
 K7pZ7XgbaBWbHSr8C9+CsCCAmTBYOascVpcu7X+qXJPS93IKpg7e+9rAKKqlY5Wq
 oe6IN975TjzZ+Ay0ZBRlxzFOn2ZdSPJIJhCC3MyDlBgx7KNIVgmvKQ1BiKQ/4ZQX
 foEr6HWIIKzQQwyI++pC0AvZ63hwM8X3xIF+6YsyXvNrGs+ypEhsAQpa4Q3XXvDi
 88afyFAhdgClbvAjbjefkPekzzLv+CYJa2hUCqsuR8Kh55DiAs204oszVHs4HzBk
 nqLffuaKXo7Vg6XOMiK/y8pGWsu5Sdp1YMBVoedvENvrVf5awt1SapV31dKC+6g9
 iF6ljSMJWYmLOmNSC3wmdivEgMLxWfgejKH6ltWnR6MZUE5KeGE=
 =8moV
 -----END PGP SIGNATURE-----

Merge tag 'x86_asm_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Borislav Petkov:
 "Two asm wrapper fixes:

   - Use XORL instead of XORQ to avoid a REX prefix and save some bytes
     in the .fixup section, by Uros Bizjak.

   - Replace __force_order dummy variable with a memory clobber to fix
     LLVM requiring a definition for former and to prevent memory
     accesses from still being cached/reordered, by Arvind Sankar"

* tag 'x86_asm_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/asm: Replace __force_order with a memory clobber
  x86/uaccess: Use XORL %0,%0 in __get_user_asm()

arch/x86/boot/compressed/pgtable_64.c

@@ -5,15 +5,6 @@
 #include "pgtable.h"
 #include "../string.h"
 
-/*
- * __force_order is used by special_insns.h asm code to force instruction
- * serialization.
- *
- * It is not referenced from the code, but GCC < 5 with -fPIE would fail
- * due to an undefined symbol. Define it to make these ancient GCCs work.
- */
-unsigned long __force_order;
-
 #define BIOS_START_MIN		0x20000U	/* 128K, less than this is insane */
 #define BIOS_START_MAX		0x9f000U	/* 640K, absolute maximum */
 

arch/x86/include/asm/special_insns.h

@@ -11,45 +11,47 @@
 #include <linux/jump_label.h>
 
 /*
- * Volatile isn't enough to prevent the compiler from reordering the
+ * The compiler should not reorder volatile asm statements with respect to each
- * read/write functions for the control registers and messing everything up.
+ * other: they should execute in program order. However GCC 4.9.x and 5.x have
- * A memory clobber would solve the problem, but would prevent reordering of
+ * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder
- * all loads stores around it, which can hurt performance. Solution is to
+ * volatile asm. The write functions are not affected since they have memory
- * use a variable and mimic reads and writes to it to enforce serialization
+ * clobbers preventing reordering. To prevent reads from being reordered with
+ * respect to writes, use a dummy memory operand.
  */
-extern unsigned long __force_order;
+
+#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL)
 
 void native_write_cr0(unsigned long val);
 
 static inline unsigned long native_read_cr0(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static __always_inline unsigned long native_read_cr2(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static __always_inline void native_write_cr2(unsigned long val)
 {
-	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
 }
 
 static inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
 static inline void native_write_cr3(unsigned long val)
 {
-	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+	asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
 }
 
 static inline unsigned long native_read_cr4(void)
@@ -64,10 +66,10 @@ static inline unsigned long native_read_cr4(void)
 	asm volatile("1: mov %%cr4, %0\n"
 		     "2:\n"
 		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val), "=m" (__force_order) : "0" (0));
+		     : "=r" (val) : "0" (0), __FORCE_ORDER);
 #else
 	/* CR4 always exists on x86_64. */
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 #endif
 	return val;
 }

arch/x86/include/asm/uaccess.h

@@ -418,7 +418,7 @@ do {									\
 		     "2:\n"						\
 		     ".section .fixup,\"ax\"\n"				\
 		     "3:	mov %[efault],%[errout]\n"		\
-		     "	xor"itype" %[output],%[output]\n"		\
+		     "	xorl %k[output],%k[output]\n"			\
 		     "	jmp 2b\n"					\
 		     ".previous\n"					\
 		     _ASM_EXTABLE_UA(1b, 3b)				\

arch/x86/kernel/cpu/common.c

@@ -360,7 +360,7 @@ void native_write_cr0(unsigned long val)
 	unsigned long bits_missing = 0;
 
 set_register:
-	asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order));
+	asm volatile("mov %0,%%cr0": "+r" (val) : : "memory");
 
 	if (static_branch_likely(&cr_pinning)) {
 		if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) {
@@ -379,7 +379,7 @@ void native_write_cr4(unsigned long val)
 	unsigned long bits_changed = 0;
 
 set_register:
-	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
+	asm volatile("mov %0,%%cr4": "+r" (val) : : "memory");
 
 	if (static_branch_likely(&cr_pinning)) {
 		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {