5 files changed, 18 insertions, 14 deletions
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index c5959576c315..020f75cc8cf6 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -37,7 +37,7 @@ ENTRY(copy_user_generic_unrolled)
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_copy_short_string
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -58,7 +58,8 @@ ENTRY(copy_user_generic_unrolled)
 	leaq 64(%rdi),%rdi
 	decl %ecx
 	jnz 1b
-17:	movl %edx,%ecx
+.L_copy_short_string:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
 	jz 20f
@@ -174,6 +175,8 @@ EXPORT_SYMBOL(copy_user_generic_string)
  */
 ENTRY(copy_user_enhanced_fast_string)
 	ASM_STAC
+	cmpl $64,%edx
+	jb .L_copy_short_string	/* less then 64 bytes, avoid the costly 'rep' */
 	movl %edx,%ecx
 1:	rep
 	movsb
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 7e48807b2fa1..45a53dfe1859 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -55,7 +55,7 @@ ENTRY(csum_partial_copy_generic)
 	movq  %r12, 3*8(%rsp)
 	movq  %r14, 4*8(%rsp)
 	movq  %r13, 5*8(%rsp)
-	movq  %rbp, 6*8(%rsp)
+	movq  %r15, 6*8(%rsp)
 
 	movq  %r8, (%rsp)
 	movq  %r9, 1*8(%rsp)
@@ -74,7 +74,7 @@ ENTRY(csum_partial_copy_generic)
 	/* main loop. clear in 64 byte blocks */
 	/* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */
 	/* r11:	temp3, rdx: temp4, r12 loopcnt */
-	/* r10:	temp5, rbp: temp6, r14 temp7, r13 temp8 */
+	/* r10:	temp5, r15: temp6, r14 temp7, r13 temp8 */
 	.p2align 4
 .Lloop:
 	source
@@ -89,7 +89,7 @@ ENTRY(csum_partial_copy_generic)
 	source
 	movq  32(%rdi), %r10
 	source
-	movq  40(%rdi), %rbp
+	movq  40(%rdi), %r15
 	source
 	movq  48(%rdi), %r14
 	source
@@ -103,7 +103,7 @@ ENTRY(csum_partial_copy_generic)
 	adcq  %r11, %rax
 	adcq  %rdx, %rax
 	adcq  %r10, %rax
-	adcq  %rbp, %rax
+	adcq  %r15, %rax
 	adcq  %r14, %rax
 	adcq  %r13, %rax
 
@@ -121,7 +121,7 @@ ENTRY(csum_partial_copy_generic)
 	dest
 	movq %r10, 32(%rsi)
 	dest
-	movq %rbp, 40(%rsi)
+	movq %r15, 40(%rsi)
 	dest
 	movq %r14, 48(%rsi)
 	dest
@@ -203,7 +203,7 @@ ENTRY(csum_partial_copy_generic)
 	movq 3*8(%rsp), %r12
 	movq 4*8(%rsp), %r14
 	movq 5*8(%rsp), %r13
-	movq 6*8(%rsp), %rbp
+	movq 6*8(%rsp), %r15
 	addq $7*8, %rsp
 	ret
 
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 5761a4f19455..ab2d1d73e9e7 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -5,6 +5,7 @@
  * kernel starts. This file is included in the compressed kernel and
  * normally linked in the regular.
  */
+#include <asm/asm.h>
 #include <asm/kaslr.h>
 #include <asm/msr.h>
 #include <asm/archrandom.h>
@@ -79,7 +80,7 @@ unsigned long kaslr_get_random_long(const char *purpose)
 	}
 
 	/* Circular multiply for better bit diffusion */
-	asm("mul %3"
+	asm(_ASM_MUL "%3"
 	    : "=a" (random), "=d" (raw)
 	    : "a" (random), "rm" (mix_const));
 	random += raw;
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index c81556409bbb..10ffa7e8519f 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -13,14 +13,14 @@
 .macro op_safe_regs op
 ENTRY(\op\()_safe_regs)
 	pushq %rbx
-	pushq %rbp
+	pushq %r12
 	movq	%rdi, %r10	/* Save pointer */
 	xorl	%r11d, %r11d	/* Return value */
 	movl    (%rdi), %eax
 	movl    4(%rdi), %ecx
 	movl    8(%rdi), %edx
 	movl    12(%rdi), %ebx
-	movl    20(%rdi), %ebp
+	movl    20(%rdi), %r12d
 	movl    24(%rdi), %esi
 	movl    28(%rdi), %edi
 1:	\op
@@ -29,10 +29,10 @@ ENTRY(\op\()_safe_regs)
 	movl    %ecx, 4(%r10)
 	movl    %edx, 8(%r10)
 	movl    %ebx, 12(%r10)
-	movl    %ebp, 20(%r10)
+	movl    %r12d, 20(%r10)
 	movl    %esi, 24(%r10)
 	movl    %edi, 28(%r10)
-	popq %rbp
+	popq %r12
 	popq %rbx
 	ret
 3:
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 767be7c76034..12e377184ee4 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1009,7 +1009,7 @@ GrpTable: Grp15
 1: fxstor | RDGSBASE Ry (F3),(11B)
 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
-4: XSAVE
+4: XSAVE | ptwrite Ey (F3),(11B)
 5: XRSTOR | lfence (11B)
 6: XSAVEOPT | clwb (66) | mfence (11B)
 7: clflush | clflushopt (66) | sfence (11B)