--- zzzz-none-000/linux-3.10.107/arch/x86/lib/copy_user_64.S 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/x86/lib/copy_user_64.S 2021-02-04 17:41:59.000000000 +0000 @@ -7,10 +7,6 @@ */ #include -#include - -#define FIX_ALIGNMENT 1 - #include #include #include @@ -19,92 +15,40 @@ #include #include -/* - * By placing feature2 after feature1 in altinstructions section, we logically - * implement: - * If CPU has feature2, jmp to alt2 is used - * else if CPU has feature1, jmp to alt1 is used - * else jmp to orig is used. - */ - .macro ALTERNATIVE_JUMP feature1,feature2,orig,alt1,alt2 -0: - .byte 0xe9 /* 32bit jump */ - .long \orig-1f /* by default jump to orig */ -1: - .section .altinstr_replacement,"ax" -2: .byte 0xe9 /* near jump with 32bit immediate */ - .long \alt1-1b /* offset */ /* or alternatively to alt1 */ -3: .byte 0xe9 /* near jump with 32bit immediate */ - .long \alt2-1b /* offset */ /* or alternatively to alt2 */ - .previous - - .section .altinstructions,"a" - altinstruction_entry 0b,2b,\feature1,5,5 - altinstruction_entry 0b,3b,\feature2,5,5 - .previous - .endm - - .macro ALIGN_DESTINATION -#ifdef FIX_ALIGNMENT - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) -#endif - .endm - /* Standard copy_to_user with segment limit checking */ ENTRY(_copy_to_user) - CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rdi,%rcx addq %rdx,%rcx jc bad_to_user cmpq TI_addr_limit(%rax),%rcx ja bad_to_user - ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS, \ - copy_user_generic_unrolled,copy_user_generic_string, \ - copy_user_enhanced_fast_string - CFI_ENDPROC + ALTERNATIVE_2 "jmp copy_user_generic_unrolled", \ + "jmp copy_user_generic_string", \ + X86_FEATURE_REP_GOOD, \ + "jmp copy_user_enhanced_fast_string", \ + X86_FEATURE_ERMS ENDPROC(_copy_to_user) /* Standard copy_from_user with segment limit checking */ ENTRY(_copy_from_user) - CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rsi,%rcx addq %rdx,%rcx jc bad_from_user cmpq TI_addr_limit(%rax),%rcx ja bad_from_user - ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS, \ - copy_user_generic_unrolled,copy_user_generic_string, \ - copy_user_enhanced_fast_string - CFI_ENDPROC + ALTERNATIVE_2 "jmp copy_user_generic_unrolled", \ + "jmp copy_user_generic_string", \ + X86_FEATURE_REP_GOOD, \ + "jmp copy_user_enhanced_fast_string", \ + X86_FEATURE_ERMS ENDPROC(_copy_from_user) .section .fixup,"ax" /* must zero dest */ ENTRY(bad_from_user) bad_from_user: - CFI_STARTPROC movl %edx,%ecx xorl %eax,%eax rep @@ -112,7 +56,6 @@ bad_to_user: movl %edx,%eax ret - CFI_ENDPROC ENDPROC(bad_from_user) .previous @@ -130,7 +73,6 @@ * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_generic_unrolled) - CFI_STARTPROC ASM_STAC cmpl $8,%edx jb 20f /* less then 8 bytes, go to byte copy loop */ @@ -186,7 +128,7 @@ 30: shll $6,%ecx addl %ecx,%edx jmp 60f -40: lea (%rdx,%rcx,8),%rdx +40: leal (%rdx,%rcx,8),%edx jmp 60f 50: movl %ecx,%edx 60: jmp copy_user_handle_tail /* ecx is zerorest also */ @@ -212,7 +154,6 @@ _ASM_EXTABLE(19b,40b) _ASM_EXTABLE(21b,50b) _ASM_EXTABLE(22b,50b) - CFI_ENDPROC ENDPROC(copy_user_generic_unrolled) /* Some CPUs run faster using the string copy instructions. @@ -234,10 +175,7 @@ * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_generic_string) - CFI_STARTPROC ASM_STAC - andl %edx,%edx - jz 4f cmpl $8,%edx jb 2f /* less than 8 bytes, go to byte copy loop */ ALIGN_DESTINATION @@ -249,19 +187,18 @@ 2: movl %edx,%ecx 3: rep movsb -4: xorl %eax,%eax + xorl %eax,%eax ASM_CLAC ret .section .fixup,"ax" -11: lea (%rdx,%rcx,8),%rcx +11: leal (%rdx,%rcx,8),%ecx 12: movl %ecx,%edx /* ecx is zerorest also */ jmp copy_user_handle_tail .previous _ASM_EXTABLE(1b,11b) _ASM_EXTABLE(3b,12b) - CFI_ENDPROC ENDPROC(copy_user_generic_string) /* @@ -277,14 +214,11 @@ * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_enhanced_fast_string) - CFI_STARTPROC ASM_STAC - andl %edx,%edx - jz 2f movl %edx,%ecx 1: rep movsb -2: xorl %eax,%eax + xorl %eax,%eax ASM_CLAC ret @@ -294,5 +228,154 @@ .previous _ASM_EXTABLE(1b,12b) - CFI_ENDPROC ENDPROC(copy_user_enhanced_fast_string) + +/* + * copy_user_nocache - Uncached memory copy with exception handling + * 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 .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 .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 +4: movq 3*8(%rsi),%r11 +5: movnti %r8,(%rdi) +6: movnti %r9,1*8(%rdi) +7: movnti %r10,2*8(%rdi) +8: movnti %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movnti %r8,4*8(%rdi) +14: movnti %r9,5*8(%rdi) +15: movnti %r10,6*8(%rdi) +16: movnti %r11,7*8(%rdi) + leaq 64(%rsi),%rsi + leaq 64(%rdi),%rdi + decl %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 .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 .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 + 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 .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax + ASM_CLAC + sfence + ret + + .section .fixup,"ax" +.L_fixup_4x8b_copy: + shll $6,%ecx + addl %ecx,%edx + 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,.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)