mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 19:41:34 +07:00
6dcc5627f6
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
143 lines
2.8 KiB
ArmAsm
143 lines
2.8 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* Copyright 2002 Andi Kleen, SuSE Labs */
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/cpufeatures.h>
|
|
#include <asm/alternative-asm.h>
|
|
#include <asm/export.h>
|
|
|
|
.weak memset
|
|
|
|
/*
|
|
* ISO C memset - set a memory block to a byte value. This function uses fast
|
|
* string to get better performance than the original function. The code is
|
|
* simpler and shorter than the original function as well.
|
|
*
|
|
* rdi destination
|
|
* rsi value (char)
|
|
* rdx count (bytes)
|
|
*
|
|
* rax original destination
|
|
*/
|
|
SYM_FUNC_START_ALIAS(memset)
|
|
SYM_FUNC_START(__memset)
|
|
/*
|
|
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
|
|
* to use it when possible. If not available, use fast string instructions.
|
|
*
|
|
* Otherwise, use original memset function.
|
|
*/
|
|
ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
|
|
"jmp memset_erms", X86_FEATURE_ERMS
|
|
|
|
movq %rdi,%r9
|
|
movq %rdx,%rcx
|
|
andl $7,%edx
|
|
shrq $3,%rcx
|
|
/* expand byte value */
|
|
movzbl %sil,%esi
|
|
movabs $0x0101010101010101,%rax
|
|
imulq %rsi,%rax
|
|
rep stosq
|
|
movl %edx,%ecx
|
|
rep stosb
|
|
movq %r9,%rax
|
|
ret
|
|
SYM_FUNC_END(__memset)
|
|
SYM_FUNC_END_ALIAS(memset)
|
|
EXPORT_SYMBOL(memset)
|
|
EXPORT_SYMBOL(__memset)
|
|
|
|
/*
|
|
* ISO C memset - set a memory block to a byte value. This function uses
|
|
* enhanced rep stosb to override the fast string function.
|
|
* The code is simpler and shorter than the fast string function as well.
|
|
*
|
|
* rdi destination
|
|
* rsi value (char)
|
|
* rdx count (bytes)
|
|
*
|
|
* rax original destination
|
|
*/
|
|
SYM_FUNC_START_LOCAL(memset_erms)
|
|
movq %rdi,%r9
|
|
movb %sil,%al
|
|
movq %rdx,%rcx
|
|
rep stosb
|
|
movq %r9,%rax
|
|
ret
|
|
SYM_FUNC_END(memset_erms)
|
|
|
|
SYM_FUNC_START_LOCAL(memset_orig)
|
|
movq %rdi,%r10
|
|
|
|
/* expand byte value */
|
|
movzbl %sil,%ecx
|
|
movabs $0x0101010101010101,%rax
|
|
imulq %rcx,%rax
|
|
|
|
/* align dst */
|
|
movl %edi,%r9d
|
|
andl $7,%r9d
|
|
jnz .Lbad_alignment
|
|
.Lafter_bad_alignment:
|
|
|
|
movq %rdx,%rcx
|
|
shrq $6,%rcx
|
|
jz .Lhandle_tail
|
|
|
|
.p2align 4
|
|
.Lloop_64:
|
|
decq %rcx
|
|
movq %rax,(%rdi)
|
|
movq %rax,8(%rdi)
|
|
movq %rax,16(%rdi)
|
|
movq %rax,24(%rdi)
|
|
movq %rax,32(%rdi)
|
|
movq %rax,40(%rdi)
|
|
movq %rax,48(%rdi)
|
|
movq %rax,56(%rdi)
|
|
leaq 64(%rdi),%rdi
|
|
jnz .Lloop_64
|
|
|
|
/* Handle tail in loops. The loops should be faster than hard
|
|
to predict jump tables. */
|
|
.p2align 4
|
|
.Lhandle_tail:
|
|
movl %edx,%ecx
|
|
andl $63&(~7),%ecx
|
|
jz .Lhandle_7
|
|
shrl $3,%ecx
|
|
.p2align 4
|
|
.Lloop_8:
|
|
decl %ecx
|
|
movq %rax,(%rdi)
|
|
leaq 8(%rdi),%rdi
|
|
jnz .Lloop_8
|
|
|
|
.Lhandle_7:
|
|
andl $7,%edx
|
|
jz .Lende
|
|
.p2align 4
|
|
.Lloop_1:
|
|
decl %edx
|
|
movb %al,(%rdi)
|
|
leaq 1(%rdi),%rdi
|
|
jnz .Lloop_1
|
|
|
|
.Lende:
|
|
movq %r10,%rax
|
|
ret
|
|
|
|
.Lbad_alignment:
|
|
cmpq $7,%rdx
|
|
jbe .Lhandle_7
|
|
movq %rax,(%rdi) /* unaligned store */
|
|
movq $8,%r8
|
|
subq %r9,%r8
|
|
addq %r8,%rdi
|
|
subq %r8,%rdx
|
|
jmp .Lafter_bad_alignment
|
|
.Lfinal:
|
|
SYM_FUNC_END(memset_orig)
|