Merge branch 'x86/urgent' into x86/asm, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 101 insertions, 41 deletions

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fba343062055..2b0ef26da0bd 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
+ * This will force destination out of cache for more performance.
+ *
+ * Note: Cached memory copy is used when destination or size is not
+ * naturally aligned. That is:
+ *  - Require 8-byte alignment when size is 8 bytes or larger.
+ *  - Require 4-byte alignment when size is 4 bytes.
  */
 ENTRY(__copy_user_nocache)
         ASM_STAC
+
+        /* If size is less than 8 bytes, go to 4-byte copy */
         cmpl $8,%edx
-        jb 20f          /* less then 8 bytes, go to byte copy loop */
+        jb .L_4b_nocache_copy_entry
+
+        /* If destination is not 8-byte aligned, "cache" copy to align it */
         ALIGN_DESTINATION
+
+        /* Set 4x8-byte copy count and remainder */
         movl %edx,%ecx
         andl $63,%edx
         shrl $6,%ecx
-        jz 17f
+        jz .L_8b_nocache_copy_entry     /* jump if count is 0 */
+
+        /* Perform 4x8-byte nocache loop-copy */
+.L_4x8b_nocache_copy_loop:
 1:      movq (%rsi),%r8
 2:      movq 1*8(%rsi),%r9
 3:      movq 2*8(%rsi),%r10
@@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache)
         leaq 64(%rsi),%rsi
         leaq 64(%rdi),%rdi
         decl %ecx
-        jnz 1b
-17:     movl %edx,%ecx
+        jnz .L_4x8b_nocache_copy_loop
+
+        /* Set 8-byte copy count and remainder */
+.L_8b_nocache_copy_entry:
+        movl %edx,%ecx
         andl $7,%edx
         shrl $3,%ecx
-        jz 20f
-18:     movq (%rsi),%r8
-19:     movnti %r8,(%rdi)
+        jz .L_4b_nocache_copy_entry     /* jump if count is 0 */
+
+        /* Perform 8-byte nocache loop-copy */
+.L_8b_nocache_copy_loop:
+20:     movq (%rsi),%r8
+21:     movnti %r8,(%rdi)
         leaq 8(%rsi),%rsi
         leaq 8(%rdi),%rdi
         decl %ecx
-        jnz 18b
-20:     andl %edx,%edx
-        jz 23f
+        jnz .L_8b_nocache_copy_loop
+
+        /* If no byte left, we're done */
+.L_4b_nocache_copy_entry:
+        andl %edx,%edx
+        jz .L_finish_copy
+
+        /* If destination is not 4-byte aligned, go to byte copy: */
+        movl %edi,%ecx
+        andl $3,%ecx
+        jnz .L_1b_cache_copy_entry
+
+        /* Set 4-byte copy count (1 or 0) and remainder */
         movl %edx,%ecx
-21:     movb (%rsi),%al
-22:     movb %al,(%rdi)
+        andl $3,%edx
+        shrl $2,%ecx
+        jz .L_1b_cache_copy_entry       /* jump if count is 0 */
+
+        /* Perform 4-byte nocache copy: */
+30:     movl (%rsi),%r8d
+31:     movnti %r8d,(%rdi)
+        leaq 4(%rsi),%rsi
+        leaq 4(%rdi),%rdi
+
+        /* If no bytes left, we're done: */
+        andl %edx,%edx
+        jz .L_finish_copy
+
+        /* Perform byte "cache" loop-copy for the remainder */
+.L_1b_cache_copy_entry:
+        movl %edx,%ecx
+.L_1b_cache_copy_loop:
+40:     movb (%rsi),%al
+41:     movb %al,(%rdi)
         incq %rsi
         incq %rdi
         decl %ecx
-        jnz 21b
-23:     xorl %eax,%eax
+        jnz .L_1b_cache_copy_loop
+
+        /* Finished copying; fence the prior stores */
+.L_finish_copy:
+        xorl %eax,%eax
         ASM_CLAC
         sfence
         ret
 
         .section .fixup,"ax"
-30:     shll $6,%ecx
+.L_fixup_4x8b_copy:
+        shll $6,%ecx
         addl %ecx,%edx
-        jmp 60f
-40:     lea (%rdx,%rcx,8),%rdx
-        jmp 60f
-50:     movl %ecx,%edx
-60:     sfence
+        jmp .L_fixup_handle_tail
+.L_fixup_8b_copy:
+        lea (%rdx,%rcx,8),%rdx
+        jmp .L_fixup_handle_tail
+.L_fixup_4b_copy:
+        lea (%rdx,%rcx,4),%rdx
+        jmp .L_fixup_handle_tail
+.L_fixup_1b_copy:
+        movl %ecx,%edx
+.L_fixup_handle_tail:
+        sfence
         jmp copy_user_handle_tail
         .previous
 
-        _ASM_EXTABLE(1b,30b)
-        _ASM_EXTABLE(2b,30b)
-        _ASM_EXTABLE(3b,30b)
-        _ASM_EXTABLE(4b,30b)
-        _ASM_EXTABLE(5b,30b)
-        _ASM_EXTABLE(6b,30b)
-        _ASM_EXTABLE(7b,30b)
-        _ASM_EXTABLE(8b,30b)
-        _ASM_EXTABLE(9b,30b)
-        _ASM_EXTABLE(10b,30b)
-        _ASM_EXTABLE(11b,30b)
-        _ASM_EXTABLE(12b,30b)
-        _ASM_EXTABLE(13b,30b)
-        _ASM_EXTABLE(14b,30b)
-        _ASM_EXTABLE(15b,30b)
-        _ASM_EXTABLE(16b,30b)
-        _ASM_EXTABLE(18b,40b)
-        _ASM_EXTABLE(19b,40b)
-        _ASM_EXTABLE(21b,50b)
-        _ASM_EXTABLE(22b,50b)
+        _ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
+        _ASM_EXTABLE(20b,.L_fixup_8b_copy)
+        _ASM_EXTABLE(21b,.L_fixup_8b_copy)
+        _ASM_EXTABLE(30b,.L_fixup_4b_copy)
+        _ASM_EXTABLE(31b,.L_fixup_4b_copy)
+        _ASM_EXTABLE(40b,.L_fixup_1b_copy)
+        _ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)