diff options
Diffstat (limited to 'arch/x86/lib')
27 files changed, 295 insertions, 705 deletions
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index c6506c6a7092..f76747862bd2 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -63,7 +63,6 @@ ifeq ($(CONFIG_X86_32),y) ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += cmpxchg8b_emu.o atomic64_386_32.o endif - lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o else obj-y += iomap_copy_64.o lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 16bc9130e7a5..e768815e58ae 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -9,81 +9,83 @@ #include <asm/alternative.h> /* if you want SMP support, implement these with real spinlocks */ -.macro LOCK reg +.macro IRQ_SAVE reg pushfl cli .endm -.macro UNLOCK reg +.macro IRQ_RESTORE reg popfl .endm -#define BEGIN(op) \ +#define BEGIN_IRQ_SAVE(op) \ .macro endp; \ SYM_FUNC_END(atomic64_##op##_386); \ .purgem endp; \ .endm; \ SYM_FUNC_START(atomic64_##op##_386); \ - LOCK v; + IRQ_SAVE v; #define ENDP endp -#define RET \ - UNLOCK v; \ - ret - -#define RET_ENDP \ - RET; \ - ENDP +#define RET_IRQ_RESTORE \ + IRQ_RESTORE v; \ + RET #define v %ecx -BEGIN(read) +BEGIN_IRQ_SAVE(read) movl (v), %eax movl 4(v), %edx -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %esi -BEGIN(set) +BEGIN_IRQ_SAVE(set) movl %ebx, (v) movl %ecx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %esi -BEGIN(xchg) +BEGIN_IRQ_SAVE(xchg) movl (v), %eax movl 4(v), %edx movl %ebx, (v) movl %ecx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %ecx -BEGIN(add) +BEGIN_IRQ_SAVE(add) addl %eax, (v) adcl %edx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %ecx -BEGIN(add_return) +BEGIN_IRQ_SAVE(add_return) addl (v), %eax adcl 4(v), %edx movl %eax, (v) movl %edx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %ecx -BEGIN(sub) +BEGIN_IRQ_SAVE(sub) subl %eax, (v) sbbl %edx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %ecx -BEGIN(sub_return) +BEGIN_IRQ_SAVE(sub_return) negl %edx negl %eax sbbl $0, %edx @@ -91,47 +93,52 @@ BEGIN(sub_return) adcl 4(v), %edx movl %eax, (v) movl %edx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %esi -BEGIN(inc) +BEGIN_IRQ_SAVE(inc) addl $1, (v) adcl $0, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %esi -BEGIN(inc_return) +BEGIN_IRQ_SAVE(inc_return) movl (v), %eax movl 4(v), %edx addl $1, %eax adcl $0, %edx movl %eax, (v) movl %edx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %esi -BEGIN(dec) +BEGIN_IRQ_SAVE(dec) subl $1, (v) sbbl $0, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %esi -BEGIN(dec_return) +BEGIN_IRQ_SAVE(dec_return) movl (v), %eax movl 4(v), %edx subl $1, %eax sbbl $0, %edx movl %eax, (v) movl %edx, 4(v) -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v #define v %esi -BEGIN(add_unless) +BEGIN_IRQ_SAVE(add_unless) addl %eax, %ecx adcl %edx, %edi addl (v), %eax @@ -143,7 +150,7 @@ BEGIN(add_unless) movl %edx, 4(v) movl $1, %eax 2: - RET + RET_IRQ_RESTORE 3: cmpl %edx, %edi jne 1b @@ -153,7 +160,7 @@ ENDP #undef v #define v %esi -BEGIN(inc_not_zero) +BEGIN_IRQ_SAVE(inc_not_zero) movl (v), %eax movl 4(v), %edx testl %eax, %eax @@ -165,7 +172,7 @@ BEGIN(inc_not_zero) movl %edx, 4(v) movl $1, %eax 2: - RET + RET_IRQ_RESTORE 3: testl %edx, %edx jne 1b @@ -174,7 +181,7 @@ ENDP #undef v #define v %esi -BEGIN(dec_if_positive) +BEGIN_IRQ_SAVE(dec_if_positive) movl (v), %eax movl 4(v), %edx subl $1, %eax @@ -183,5 +190,6 @@ BEGIN(dec_if_positive) movl %eax, (v) movl %edx, 4(v) 1: -RET_ENDP + RET_IRQ_RESTORE +ENDP #undef v diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index ce6935690766..90afb488b396 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -18,7 +18,7 @@ SYM_FUNC_START(atomic64_read_cx8) read64 %ecx - ret + RET SYM_FUNC_END(atomic64_read_cx8) SYM_FUNC_START(atomic64_set_cx8) @@ -28,7 +28,7 @@ SYM_FUNC_START(atomic64_set_cx8) cmpxchg8b (%esi) jne 1b - ret + RET SYM_FUNC_END(atomic64_set_cx8) SYM_FUNC_START(atomic64_xchg_cx8) @@ -37,7 +37,7 @@ SYM_FUNC_START(atomic64_xchg_cx8) cmpxchg8b (%esi) jne 1b - ret + RET SYM_FUNC_END(atomic64_xchg_cx8) .macro addsub_return func ins insc @@ -68,7 +68,7 @@ SYM_FUNC_START(atomic64_\func\()_return_cx8) popl %esi popl %ebx popl %ebp - ret + RET SYM_FUNC_END(atomic64_\func\()_return_cx8) .endm @@ -93,7 +93,7 @@ SYM_FUNC_START(atomic64_\func\()_return_cx8) movl %ebx, %eax movl %ecx, %edx popl %ebx - ret + RET SYM_FUNC_END(atomic64_\func\()_return_cx8) .endm @@ -118,7 +118,7 @@ SYM_FUNC_START(atomic64_dec_if_positive_cx8) movl %ebx, %eax movl %ecx, %edx popl %ebx - ret + RET SYM_FUNC_END(atomic64_dec_if_positive_cx8) SYM_FUNC_START(atomic64_add_unless_cx8) @@ -149,7 +149,7 @@ SYM_FUNC_START(atomic64_add_unless_cx8) addl $8, %esp popl %ebx popl %ebp - ret + RET 4: cmpl %edx, 4(%esp) jne 2b @@ -176,5 +176,5 @@ SYM_FUNC_START(atomic64_inc_not_zero_cx8) movl $1, %eax 3: popl %ebx - ret + RET SYM_FUNC_END(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4304320e51f4..23318c338db0 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -127,7 +127,7 @@ SYM_FUNC_START(csum_partial) 8: popl %ebx popl %esi - ret + RET SYM_FUNC_END(csum_partial) #else @@ -245,7 +245,7 @@ SYM_FUNC_START(csum_partial) 90: popl %ebx popl %esi - ret + RET SYM_FUNC_END(csum_partial) #endif @@ -260,9 +260,9 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst, * Copy from ds while checksumming, otherwise like csum_partial */ -#define EXC(y...) \ - 9999: y; \ - _ASM_EXTABLE_UA(9999b, 6001f) +#define EXC(y...) \ + 9999: y; \ + _ASM_EXTABLE_TYPE(9999b, 7f, EX_TYPE_UACCESS | EX_FLAG_CLEAR_AX) #ifndef CONFIG_X86_USE_PPRO_CHECKSUM @@ -358,20 +358,11 @@ EXC( movb %cl, (%edi) ) adcl $0, %eax 7: -# Exception handler: -.section .fixup, "ax" - -6001: - xorl %eax, %eax - jmp 7b - -.previous - popl %ebx popl %esi popl %edi popl %ecx # equivalent to addl $4,%esp - ret + RET SYM_FUNC_END(csum_partial_copy_generic) #else @@ -439,15 +430,11 @@ EXC( movb %dl, (%edi) ) 6: addl %edx, %eax adcl $0, %eax 7: -.section .fixup, "ax" -6001: xorl %eax, %eax - jmp 7b -.previous popl %esi popl %edi popl %ebx - ret + RET SYM_FUNC_END(csum_partial_copy_generic) #undef ROUND diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index c4c7dd115953..fe59b8ac4fcc 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -17,7 +17,7 @@ SYM_FUNC_START(clear_page_rep) movl $4096/8,%ecx xorl %eax,%eax rep stosq - ret + RET SYM_FUNC_END(clear_page_rep) EXPORT_SYMBOL_GPL(clear_page_rep) @@ -39,7 +39,7 @@ SYM_FUNC_START(clear_page_orig) leaq 64(%rdi),%rdi jnz .Lloop nop - ret + RET SYM_FUNC_END(clear_page_orig) EXPORT_SYMBOL_GPL(clear_page_orig) @@ -47,6 +47,6 @@ SYM_FUNC_START(clear_page_erms) movl $4096,%ecx xorl %eax,%eax rep stosb - ret + RET SYM_FUNC_END(clear_page_erms) EXPORT_SYMBOL_GPL(clear_page_erms) diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index 3542502faa3b..33c70c0160ea 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -37,11 +37,11 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu) popfq mov $1, %al - ret + RET .Lnot_same: popfq xor %al,%al - ret + RET SYM_FUNC_END(this_cpu_cmpxchg16b_emu) diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index ca01ed6029f4..6a912d58fecc 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -32,7 +32,7 @@ SYM_FUNC_START(cmpxchg8b_emu) movl %ecx, 4(%esi) popfl - ret + RET .Lnot_same: movl (%esi), %eax @@ -40,7 +40,7 @@ SYM_FUNC_START(cmpxchg8b_emu) movl 4(%esi), %edx popfl - ret + RET SYM_FUNC_END(cmpxchg8b_emu) EXPORT_SYMBOL(cmpxchg8b_emu) diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S index 7334055157ba..c859a8a09860 100644 --- a/arch/x86/lib/copy_mc_64.S +++ b/arch/x86/lib/copy_mc_64.S @@ -77,10 +77,8 @@ SYM_FUNC_START(copy_mc_fragile) .L_done_memcpy_trap: xorl %eax, %eax .L_done: - ret -SYM_FUNC_END(copy_mc_fragile) + RET - .section .fixup, "ax" /* * Return number of bytes not copied for any failure. Note that * there is no "tail" handling since the source buffer is 8-byte @@ -105,14 +103,14 @@ SYM_FUNC_END(copy_mc_fragile) movl %ecx, %edx jmp copy_mc_fragile_handle_tail - .previous - _ASM_EXTABLE_TYPE(.L_read_leading_bytes, .E_leading_bytes, EX_TYPE_DEFAULT_MCE_SAFE) _ASM_EXTABLE_TYPE(.L_read_words, .E_read_words, EX_TYPE_DEFAULT_MCE_SAFE) _ASM_EXTABLE_TYPE(.L_read_trailing_bytes, .E_trailing_bytes, EX_TYPE_DEFAULT_MCE_SAFE) _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) _ASM_EXTABLE(.L_write_words, .E_write_words) _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) + +SYM_FUNC_END(copy_mc_fragile) #endif /* CONFIG_X86_MCE */ /* @@ -132,10 +130,8 @@ SYM_FUNC_START(copy_mc_enhanced_fast_string) rep movsb /* Copy successful. Return zero */ xorl %eax, %eax - ret -SYM_FUNC_END(copy_mc_enhanced_fast_string) + RET - .section .fixup, "ax" .E_copy: /* * On fault %rcx is updated such that the copy instruction could @@ -145,9 +141,9 @@ SYM_FUNC_END(copy_mc_enhanced_fast_string) * user-copy routines. */ movq %rcx, %rax - ret - - .previous + RET _ASM_EXTABLE_TYPE(.L_copy, .E_copy, EX_TYPE_DEFAULT_MCE_SAFE) + +SYM_FUNC_END(copy_mc_enhanced_fast_string) #endif /* !CONFIG_UML */ diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index db4b4f9197c7..30ea644bf446 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -17,7 +17,7 @@ SYM_FUNC_START(copy_page) ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq - ret + RET SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) @@ -85,5 +85,5 @@ SYM_FUNC_START_LOCAL(copy_page_regs) movq (%rsp), %rbx movq 1*8(%rsp), %r12 addq $2*8, %rsp - ret + RET SYM_FUNC_END(copy_page_regs) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index a2cbeae4b180..8ca5ecf16dc4 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -32,14 +32,10 @@ decl %ecx jnz 100b 102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp .Lcopy_user_handle_tail - .previous - _ASM_EXTABLE_CPY(100b, 103b) - _ASM_EXTABLE_CPY(101b, 103b) - .endm + _ASM_EXTABLE_CPY(100b, .Lcopy_user_handle_align) + _ASM_EXTABLE_CPY(101b, .Lcopy_user_handle_align) +.endm /* * copy_user_generic_unrolled - memory copy with exception handling. @@ -105,9 +101,8 @@ SYM_FUNC_START(copy_user_generic_unrolled) jnz 21b 23: xor %eax,%eax ASM_CLAC - ret + RET - .section .fixup,"ax" 30: shll $6,%ecx addl %ecx,%edx jmp 60f @@ -115,7 +110,6 @@ SYM_FUNC_START(copy_user_generic_unrolled) jmp 60f 50: movl %ecx,%edx 60: jmp .Lcopy_user_handle_tail /* ecx is zerorest also */ - .previous _ASM_EXTABLE_CPY(1b, 30b) _ASM_EXTABLE_CPY(2b, 30b) @@ -166,20 +160,16 @@ SYM_FUNC_START(copy_user_generic_string) movl %edx,%ecx shrl $3,%ecx andl $7,%edx -1: rep - movsq +1: rep movsq 2: movl %edx,%ecx -3: rep - movsb +3: rep movsb xorl %eax,%eax ASM_CLAC - ret + RET - .section .fixup,"ax" 11: leal (%rdx,%rcx,8),%ecx 12: movl %ecx,%edx /* ecx is zerorest also */ jmp .Lcopy_user_handle_tail - .previous _ASM_EXTABLE_CPY(1b, 11b) _ASM_EXTABLE_CPY(3b, 12b) @@ -203,16 +193,13 @@ SYM_FUNC_START(copy_user_enhanced_fast_string) /* CPUs without FSRM should avoid rep movsb for short copies */ ALTERNATIVE "cmpl $64, %edx; jb .L_copy_short_string", "", X86_FEATURE_FSRM movl %edx,%ecx -1: rep - movsb +1: rep movsb xorl %eax,%eax ASM_CLAC - ret + RET - .section .fixup,"ax" 12: movl %ecx,%edx /* ecx is zerorest also */ jmp .Lcopy_user_handle_tail - .previous _ASM_EXTABLE_CPY(1b, 12b) SYM_FUNC_END(copy_user_enhanced_fast_string) @@ -241,7 +228,7 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) 1: rep movsb 2: mov %ecx,%eax ASM_CLAC - ret + RET 3: movl %edx,%eax @@ -249,6 +236,11 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) RET _ASM_EXTABLE_CPY(1b, 2b) + +.Lcopy_user_handle_align: + addl %ecx,%edx /* ecx is zerorest also */ + jmp .Lcopy_user_handle_tail + SYM_CODE_END(.Lcopy_user_handle_tail) /* @@ -357,9 +349,8 @@ SYM_FUNC_START(__copy_user_nocache) xorl %eax,%eax ASM_CLAC sfence - ret + RET - .section .fixup,"ax" .L_fixup_4x8b_copy: shll $6,%ecx addl %ecx,%edx @@ -375,7 +366,6 @@ SYM_FUNC_START(__copy_user_nocache) .L_fixup_handle_tail: sfence jmp .Lcopy_user_handle_tail - .previous _ASM_EXTABLE_CPY(1b, .L_fixup_4x8b_copy) _ASM_EXTABLE_CPY(2b, .L_fixup_4x8b_copy) diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index 1fbd8ee9642d..d9e16a2cf285 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -201,7 +201,7 @@ SYM_FUNC_START(csum_partial_copy_generic) movq 3*8(%rsp), %r13 movq 4*8(%rsp), %r15 addq $5*8, %rsp - ret + RET .Lshort: movl %ecx, %r10d jmp .L1 diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index e7925d668b68..1f8a8f895173 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -9,6 +9,7 @@ #include <linux/compiler.h> #include <linux/export.h> #include <asm/checksum.h> +#include <asm/word-at-a-time.h> static inline unsigned short from32to16(unsigned a) { @@ -21,120 +22,119 @@ static inline unsigned short from32to16(unsigned a) } /* - * Do a 64-bit checksum on an arbitrary memory area. + * Do a checksum on an arbitrary memory area. * Returns a 32bit checksum. * * This isn't as time critical as it used to be because many NICs * do hardware checksumming these days. - * - * Things tried and found to not make it faster: - * Manual Prefetching - * Unrolling to an 128 bytes inner loop. - * Using interleaving with more registers to break the carry chains. + * + * Still, with CHECKSUM_COMPLETE this is called to compute + * checksums on IPv6 headers (40 bytes) and other small parts. + * it's best to have buff aligned on a 64-bit boundary */ -static unsigned do_csum(const unsigned char *buff, unsigned len) +__wsum csum_partial(const void *buff, int len, __wsum sum) { - unsigned odd, count; - unsigned long result = 0; + u64 temp64 = (__force u64)sum; + unsigned odd, result; - if (unlikely(len == 0)) - return result; odd = 1 & (unsigned long) buff; if (unlikely(odd)) { - result = *buff << 8; + if (unlikely(len == 0)) + return sum; + temp64 = ror32((__force u32)sum, 8); + temp64 += (*(unsigned char *)buff << 8); len--; buff++; } - count = len >> 1; /* nr of 16-bit words.. */ - if (count) { - if (2 & (unsigned long) buff) { - result += *(unsigned short *)buff; - count--; - len -= 2; - buff += 2; - } - count >>= 1; /* nr of 32-bit words.. */ - if (count) { - unsigned long zero; - unsigned count64; - if (4 & (unsigned long) buff) { - result += *(unsigned int *) buff; - count--; - len -= 4; - buff += 4; - } - count >>= 1; /* nr of 64-bit words.. */ - /* main loop using 64byte blocks */ - zero = 0; - count64 = count >> 3; - while (count64) { - asm("addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcq 4*8(%[src]),%[res]\n\t" - "adcq 5*8(%[src]),%[res]\n\t" - "adcq 6*8(%[src]),%[res]\n\t" - "adcq 7*8(%[src]),%[res]\n\t" - "adcq %[zero],%[res]" - : [res] "=r" (result) - : [src] "r" (buff), [zero] "r" (zero), - "[res]" (result)); - buff += 64; - count64--; - } + while (unlikely(len >= 64)) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq 1*8(%[src]),%[res]\n\t" + "adcq 2*8(%[src]),%[res]\n\t" + "adcq 3*8(%[src]),%[res]\n\t" + "adcq 4*8(%[src]),%[res]\n\t" + "adcq 5*8(%[src]),%[res]\n\t" + "adcq 6*8(%[src]),%[res]\n\t" + "adcq 7*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 64; + len -= 64; + } + + if (len & 32) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq 1*8(%[src]),%[res]\n\t" + "adcq 2*8(%[src]),%[res]\n\t" + "adcq 3*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 32; + } + if (len & 16) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq 1*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 16; + } + if (len & 8) { + asm("addq 0*8(%[src]),%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [src] "r" (buff) + : "memory"); + buff += 8; + } + if (len & 7) { +#ifdef CONFIG_DCACHE_WORD_ACCESS + unsigned int shift = (8 - (len & 7)) * 8; + unsigned long trail; - /* last up to 7 8byte blocks */ - count %= 8; - while (count) { - asm("addq %1,%0\n\t" - "adcq %2,%0\n" - : "=r" (result) - : "m" (*(unsigned long *)buff), - "r" (zero), "0" (result)); - --count; - buff += 8; - } - result = add32_with_carry(result>>32, - result&0xffffffff); + trail = (load_unaligned_zeropad(buff) << shift) >> shift; - if (len & 4) { - result += *(unsigned int *) buff; - buff += 4; - } + asm("addq %[trail],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [trail] "r" (trail)); +#else + if (len & 4) { + asm("addq %[val],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [val] "r" ((u64)*(u32 *)buff) + : "memory"); + buff += 4; } if (len & 2) { - result += *(unsigned short *) buff; + asm("addq %[val],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [val] "r" ((u64)*(u16 *)buff) + : "memory"); buff += 2; } + if (len & 1) { + asm("addq %[val],%[res]\n\t" + "adcq $0,%[res]" + : [res] "+r" (temp64) + : [val] "r" ((u64)*(u8 *)buff) + : "memory"); + } +#endif } - if (len & 1) - result += *buff; - result = add32_with_carry(result>>32, result & 0xffffffff); - if (unlikely(odd)) { + result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); + if (unlikely(odd)) { result = from32to16(result); result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); } - return result; -} - -/* - * computes the checksum of a memory block at buff, length len, - * and adds in "sum" (32-bit) - * - * returns a 32-bit number suitable for feeding into itself - * or csum_tcpudp_magic - * - * this function must be called with even lengths, except - * for the last fragment, which may be odd - * - * it's best to have buff aligned on a 64-bit boundary - */ -__wsum csum_partial(const void *buff, int len, __wsum sum) -{ - return (__force __wsum)add32_with_carry(do_csum(buff, len), - (__force u32)sum); + return (__force __wsum)result; } EXPORT_SYMBOL(csum_partial); @@ -147,4 +147,3 @@ __sum16 ip_compute_csum(const void *buff, int len) return csum_fold(csum_partial(buff,len,0)); } EXPORT_SYMBOL(ip_compute_csum); - diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index be5b5fb1598b..520897061ee0 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/linkage.h> #include <linux/error-injection.h> #include <linux/kprobes.h> @@ -10,7 +11,7 @@ asm( ".type just_return_func, @function\n" ".globl just_return_func\n" "just_return_func:\n" - " ret\n" + ASM_RET ".size just_return_func, .-just_return_func\n" ); diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index fa1bc2104b32..b70d98d79a9d 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -57,7 +57,7 @@ SYM_FUNC_START(__get_user_1) 1: movzbl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_1) EXPORT_SYMBOL(__get_user_1) @@ -71,7 +71,7 @@ SYM_FUNC_START(__get_user_2) 2: movzwl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_2) EXPORT_SYMBOL(__get_user_2) @@ -85,7 +85,7 @@ SYM_FUNC_START(__get_user_4) 3: movl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_4) EXPORT_SYMBOL(__get_user_4) @@ -100,7 +100,7 @@ SYM_FUNC_START(__get_user_8) 4: movq (%_ASM_AX),%rdx xor %eax,%eax ASM_CLAC - ret + RET #else LOAD_TASK_SIZE_MINUS_N(7) cmp %_ASM_DX,%_ASM_AX @@ -112,7 +112,7 @@ SYM_FUNC_START(__get_user_8) 5: movl 4(%_ASM_AX),%ecx xor %eax,%eax ASM_CLAC - ret + RET #endif SYM_FUNC_END(__get_user_8) EXPORT_SYMBOL(__get_user_8) @@ -124,7 +124,7 @@ SYM_FUNC_START(__get_user_nocheck_1) 6: movzbl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_1) EXPORT_SYMBOL(__get_user_nocheck_1) @@ -134,7 +134,7 @@ SYM_FUNC_START(__get_user_nocheck_2) 7: movzwl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_2) EXPORT_SYMBOL(__get_user_nocheck_2) @@ -144,7 +144,7 @@ SYM_FUNC_START(__get_user_nocheck_4) 8: movl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_4) EXPORT_SYMBOL(__get_user_nocheck_4) @@ -159,7 +159,7 @@ SYM_FUNC_START(__get_user_nocheck_8) #endif xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_8) EXPORT_SYMBOL(__get_user_nocheck_8) @@ -169,7 +169,7 @@ SYM_CODE_START_LOCAL(.Lbad_get_user_clac) bad_get_user: xor %edx,%edx mov $(-EFAULT),%_ASM_AX - ret + RET SYM_CODE_END(.Lbad_get_user_clac) #ifdef CONFIG_X86_32 @@ -179,7 +179,7 @@ bad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX - ret + RET SYM_CODE_END(.Lbad_get_user_8_clac) #endif diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index dbf8cc97b7f5..12c16c6aa44a 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -32,7 +32,7 @@ SYM_FUNC_START(__sw_hweight32) imull $0x01010101, %eax, %eax # w_tmp *= 0x01010101 shrl $24, %eax # w = w_tmp >> 24 __ASM_SIZE(pop,) %__ASM_REG(dx) - ret + RET SYM_FUNC_END(__sw_hweight32) EXPORT_SYMBOL(__sw_hweight32) @@ -65,7 +65,7 @@ SYM_FUNC_START(__sw_hweight64) popq %rdx popq %rdi - ret + RET #else /* CONFIG_X86_32 */ /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */ pushl %ecx @@ -77,7 +77,7 @@ SYM_FUNC_START(__sw_hweight64) addl %ecx, %eax # result |