linux/arch/x86/lib/csum-copy_64.S
Jiri Slaby 6dcc5627f6 x86/asm: Change all ENTRY+ENDPROC to SYM_FUNC_*
These are all functions which are invoked from elsewhere, so annotate
them as global using the new SYM_FUNC_START and their ENDPROC's by
SYM_FUNC_END.

Make sure ENTRY/ENDPROC is not defined on X86_64, given these were the
last users.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> [hibernate]
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen bits]
Acked-by: Herbert Xu <herbert@gondor.apana.org.au> [crypto]
Cc: Allison Randal <allison@lohutok.net>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Andy Shevchenko <andy@infradead.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Armijn Hemel <armijn@tjaldur.nl>
Cc: Cao jin <caoj.fnst@cn.fujitsu.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Enrico Weigelt <info@metux.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jim Mattson <jmattson@google.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: kvm ML <kvm@vger.kernel.org>
Cc: Len Brown <len.brown@intel.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-crypto@vger.kernel.org
Cc: linux-efi <linux-efi@vger.kernel.org>
Cc: linux-efi@vger.kernel.org
Cc: linux-pm@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: platform-driver-x86@vger.kernel.org
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: Wei Huang <wei@redhat.com>
Cc: x86-ml <x86@kernel.org>
Cc: xen-devel@lists.xenproject.org
Cc: Xiaoyao Li <xiaoyao.li@linux.intel.com>
Link: https://lkml.kernel.org/r/20191011115108.12392-25-jslaby@suse.cz
2019-10-18 11:58:33 +02:00

229 lines
3.8 KiB
ArmAsm

/*
* Copyright 2002, 2003 Andi Kleen, SuSE Labs.
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file COPYING in the main directory of this archive
* for more details. No warranty for anything given at all.
*/
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/asm.h>
/*
* Checksum copy with exception handling.
* On exceptions src_err_ptr or dst_err_ptr is set to -EFAULT and the
* destination is zeroed.
*
* Input
* rdi source
* rsi destination
* edx len (32bit)
* ecx sum (32bit)
* r8 src_err_ptr (int)
* r9 dst_err_ptr (int)
*
* Output
* eax 64bit sum. undefined in case of exception.
*
* Wrappers need to take care of valid exception sum and zeroing.
* They also should align source or destination to 8 bytes.
*/
.macro source
10:
_ASM_EXTABLE_UA(10b, .Lbad_source)
.endm
.macro dest
20:
_ASM_EXTABLE_UA(20b, .Lbad_dest)
.endm
/*
* No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
* potentially unmapped kernel address.
*/
.macro ignore L=.Lignore
30:
_ASM_EXTABLE(30b, \L)
.endm
SYM_FUNC_START(csum_partial_copy_generic)
cmpl $3*64, %edx
jle .Lignore
.Lignore:
subq $7*8, %rsp
movq %rbx, 2*8(%rsp)
movq %r12, 3*8(%rsp)
movq %r14, 4*8(%rsp)
movq %r13, 5*8(%rsp)
movq %r15, 6*8(%rsp)
movq %r8, (%rsp)
movq %r9, 1*8(%rsp)
movl %ecx, %eax
movl %edx, %ecx
xorl %r9d, %r9d
movq %rcx, %r12
shrq $6, %r12
jz .Lhandle_tail /* < 64 */
clc
/* 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, r15: temp6, r14 temp7, r13 temp8 */
.p2align 4
.Lloop:
source
movq (%rdi), %rbx
source
movq 8(%rdi), %r8
source
movq 16(%rdi), %r11
source
movq 24(%rdi), %rdx
source
movq 32(%rdi), %r10
source
movq 40(%rdi), %r15
source
movq 48(%rdi), %r14
source
movq 56(%rdi), %r13
ignore 2f
prefetcht0 5*64(%rdi)
2:
adcq %rbx, %rax
adcq %r8, %rax
adcq %r11, %rax
adcq %rdx, %rax
adcq %r10, %rax
adcq %r15, %rax
adcq %r14, %rax
adcq %r13, %rax
decl %r12d
dest
movq %rbx, (%rsi)
dest
movq %r8, 8(%rsi)
dest
movq %r11, 16(%rsi)
dest
movq %rdx, 24(%rsi)
dest
movq %r10, 32(%rsi)
dest
movq %r15, 40(%rsi)
dest
movq %r14, 48(%rsi)
dest
movq %r13, 56(%rsi)
3:
leaq 64(%rdi), %rdi
leaq 64(%rsi), %rsi
jnz .Lloop
adcq %r9, %rax
/* do last up to 56 bytes */
.Lhandle_tail:
/* ecx: count */
movl %ecx, %r10d
andl $63, %ecx
shrl $3, %ecx
jz .Lfold
clc
.p2align 4
.Lloop_8:
source
movq (%rdi), %rbx
adcq %rbx, %rax
decl %ecx
dest
movq %rbx, (%rsi)
leaq 8(%rsi), %rsi /* preserve carry */
leaq 8(%rdi), %rdi
jnz .Lloop_8
adcq %r9, %rax /* add in carry */
.Lfold:
/* reduce checksum to 32bits */
movl %eax, %ebx
shrq $32, %rax
addl %ebx, %eax
adcl %r9d, %eax
/* do last up to 6 bytes */
.Lhandle_7:
movl %r10d, %ecx
andl $7, %ecx
shrl $1, %ecx
jz .Lhandle_1
movl $2, %edx
xorl %ebx, %ebx
clc
.p2align 4
.Lloop_1:
source
movw (%rdi), %bx
adcl %ebx, %eax
decl %ecx
dest
movw %bx, (%rsi)
leaq 2(%rdi), %rdi
leaq 2(%rsi), %rsi
jnz .Lloop_1
adcl %r9d, %eax /* add in carry */
/* handle last odd byte */
.Lhandle_1:
testb $1, %r10b
jz .Lende
xorl %ebx, %ebx
source
movb (%rdi), %bl
dest
movb %bl, (%rsi)
addl %ebx, %eax
adcl %r9d, %eax /* carry */
.Lende:
movq 2*8(%rsp), %rbx
movq 3*8(%rsp), %r12
movq 4*8(%rsp), %r14
movq 5*8(%rsp), %r13
movq 6*8(%rsp), %r15
addq $7*8, %rsp
ret
/* Exception handlers. Very simple, zeroing is done in the wrappers */
.Lbad_source:
movq (%rsp), %rax
testq %rax, %rax
jz .Lende
movl $-EFAULT, (%rax)
jmp .Lende
.Lbad_dest:
movq 8(%rsp), %rax
testq %rax, %rax
jz .Lende
movl $-EFAULT, (%rax)
jmp .Lende
SYM_FUNC_END(csum_partial_copy_generic)