linux/arch/x86/lib/csum-copy_64.S

257 lines
4.2 KiB
ArmAsm
Raw Normal View History

/*
* 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)
*
* 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, .Lfault)
.endm
.macro dest
20:
_ASM_EXTABLE_UA(20b, .Lfault)
.endm
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
2019-10-11 19:51:04 +08:00
SYM_FUNC_START(csum_partial_copy_generic)
subq $5*8, %rsp
movq %rbx, 0*8(%rsp)
movq %r12, 1*8(%rsp)
movq %r14, 2*8(%rsp)
movq %r13, 3*8(%rsp)
movq %r15, 4*8(%rsp)
movl $-1, %eax
xorl %r9d, %r9d
movl %edx, %ecx
cmpl $8, %ecx
jb .Lshort
testb $7, %sil
jne .Lunaligned
.Laligned:
movl %ecx, %r12d
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 */
x86/asm: Don't use RBP as a temporary register in csum_partial_copy_generic() Andrey Konovalov reported the following warning while fuzzing the kernel with syzkaller: WARNING: kernel stack regs at ffff8800686869f8 in a.out:4933 has bad 'bp' value c3fc855a10167ec0 The unwinder dump revealed that RBP had a bad value when an interrupt occurred in csum_partial_copy_generic(). That function saves RBP on the stack and then overwrites it, using it as a scratch register. That's problematic because it breaks stack traces if an interrupt occurs in the middle of the function. Replace the usage of RBP with another callee-saved register (R15) so stack traces are no longer affected. Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: David S . Miller <davem@davemloft.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: linux-sctp@vger.kernel.org Cc: netdev <netdev@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Link: http://lkml.kernel.org/r/4b03a961efda5ec9bfe46b7b9c9ad72d1efad343.1493909486.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-04 22:51:40 +08:00
/* 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
x86/asm: Don't use RBP as a temporary register in csum_partial_copy_generic() Andrey Konovalov reported the following warning while fuzzing the kernel with syzkaller: WARNING: kernel stack regs at ffff8800686869f8 in a.out:4933 has bad 'bp' value c3fc855a10167ec0 The unwinder dump revealed that RBP had a bad value when an interrupt occurred in csum_partial_copy_generic(). That function saves RBP on the stack and then overwrites it, using it as a scratch register. That's problematic because it breaks stack traces if an interrupt occurs in the middle of the function. Replace the usage of RBP with another callee-saved register (R15) so stack traces are no longer affected. Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: David S . Miller <davem@davemloft.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: linux-sctp@vger.kernel.org Cc: netdev <netdev@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Link: http://lkml.kernel.org/r/4b03a961efda5ec9bfe46b7b9c9ad72d1efad343.1493909486.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-04 22:51:40 +08:00
movq 40(%rdi), %r15
source
movq 48(%rdi), %r14
source
movq 56(%rdi), %r13
30:
/*
* No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
* potentially unmapped kernel address.
*/
_ASM_EXTABLE(30b, 2f)
prefetcht0 5*64(%rdi)
2:
adcq %rbx, %rax
adcq %r8, %rax
adcq %r11, %rax
adcq %rdx, %rax
adcq %r10, %rax
x86/asm: Don't use RBP as a temporary register in csum_partial_copy_generic() Andrey Konovalov reported the following warning while fuzzing the kernel with syzkaller: WARNING: kernel stack regs at ffff8800686869f8 in a.out:4933 has bad 'bp' value c3fc855a10167ec0 The unwinder dump revealed that RBP had a bad value when an interrupt occurred in csum_partial_copy_generic(). That function saves RBP on the stack and then overwrites it, using it as a scratch register. That's problematic because it breaks stack traces if an interrupt occurs in the middle of the function. Replace the usage of RBP with another callee-saved register (R15) so stack traces are no longer affected. Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: David S . Miller <davem@davemloft.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: linux-sctp@vger.kernel.org Cc: netdev <netdev@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Link: http://lkml.kernel.org/r/4b03a961efda5ec9bfe46b7b9c9ad72d1efad343.1493909486.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-04 22:51:40 +08:00
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
x86/asm: Don't use RBP as a temporary register in csum_partial_copy_generic() Andrey Konovalov reported the following warning while fuzzing the kernel with syzkaller: WARNING: kernel stack regs at ffff8800686869f8 in a.out:4933 has bad 'bp' value c3fc855a10167ec0 The unwinder dump revealed that RBP had a bad value when an interrupt occurred in csum_partial_copy_generic(). That function saves RBP on the stack and then overwrites it, using it as a scratch register. That's problematic because it breaks stack traces if an interrupt occurs in the middle of the function. Replace the usage of RBP with another callee-saved register (R15) so stack traces are no longer affected. Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: David S . Miller <davem@davemloft.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: linux-sctp@vger.kernel.org Cc: netdev <netdev@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Link: http://lkml.kernel.org/r/4b03a961efda5ec9bfe46b7b9c9ad72d1efad343.1493909486.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-04 22:51:40 +08:00
movq %r15, 40(%rsi)
dest
movq %r14, 48(%rsi)
dest
movq %r13, 56(%rsi)
leaq 64(%rdi), %rdi
leaq 64(%rsi), %rsi
jnz .Lloop
adcq %r9, %rax
/* do last up to 56 bytes */
.Lhandle_tail:
/* ecx: count, rcx.63: the end result needs to be rol8 */
movq %rcx, %r10
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
.L1: /* .Lshort rejoins the common path here */
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:
x86/asm: Optimize unnecessarily wide TEST instructions By the nature of the TEST operation, it is often possible to test a narrower part of the operand: "testl $3, mem" -> "testb $3, mem", "testq $3, %rcx" -> "testb $3, %cl" This results in shorter instructions, because the TEST instruction has no sign-entending byte-immediate forms unlike other ALU ops. Note that this change does not create any LCP (Length-Changing Prefix) stalls, which happen when adding a 0x66 prefix, which happens when 16-bit immediates are used, which changes such TEST instructions: [test_opcode] [modrm] [imm32] to: [0x66] [test_opcode] [modrm] [imm16] where [imm16] has a *different length* now: 2 bytes instead of 4. This confuses the decoder and slows down execution. REX prefixes were carefully designed to almost never hit this case: adding REX prefix does not change instruction length except MOVABS and MOV [addr],RAX instruction. This patch does not add instructions which would use a 0x66 prefix, code changes in assembly are: -48 f7 07 01 00 00 00 testq $0x1,(%rdi) +f6 07 01 testb $0x1,(%rdi) -48 f7 c1 01 00 00 00 test $0x1,%rcx +f6 c1 01 test $0x1,%cl -48 f7 c1 02 00 00 00 test $0x2,%rcx +f6 c1 02 test $0x2,%cl -41 f7 c2 01 00 00 00 test $0x1,%r10d +41 f6 c2 01 test $0x1,%r10b -48 f7 c1 04 00 00 00 test $0x4,%rcx +f6 c1 04 test $0x4,%cl -48 f7 c1 08 00 00 00 test $0x8,%rcx +f6 c1 08 test $0x8,%cl Linus further notes: "There are no stalls from using 8-bit instruction forms. Now, changing from 64-bit or 32-bit 'test' instructions to 8-bit ones *could* cause problems if it ends up having forwarding issues, so that instead of just forwarding the result, you end up having to wait for it to be stable in the L1 cache (or possibly the register file). The forwarding from the store buffer is simplest and most reliable if the read is done at the exact same address and the exact same size as the write that gets forwarded. But that's true only if: (a) the write was very recent and is still in the write queue. I'm not sure that's the case here anyway. (b) on at least most Intel microarchitectures, you have to test a different byte than the lowest one (so forwarding a 64-bit write to a 8-bit read ends up working fine, as long as the 8-bit read is of the low 8 bits of the written data). A very similar issue *might* show up for registers too, not just memory writes, if you use 'testb' with a high-byte register (where instead of forwarding the value from the original producer it needs to go through the register file and then shifted). But it's mainly a problem for store buffers. But afaik, the way Denys changed the test instructions, neither of the above issues should be true. The real problem for store buffer forwarding tends to be "write 8 bits, read 32 bits". That can be really surprisingly expensive, because the read ends up having to wait until the write has hit the cacheline, and we might talk tens of cycles of latency here. But "write 32 bits, read the low 8 bits" *should* be fast on pretty much all x86 chips, afaik." Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Acked-by: Andy Lutomirski <luto@amacapital.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Will Drewry <wad@chromium.org> Link: http://lkml.kernel.org/r/1425675332-31576-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-07 04:55:32 +08:00
testb $1, %r10b
jz .Lende
xorl %ebx, %ebx
source
movb (%rdi), %bl
dest
movb %bl, (%rsi)
addl %ebx, %eax
adcl %r9d, %eax /* carry */
.Lende:
testq %r10, %r10
js .Lwas_odd
.Lout:
movq 0*8(%rsp), %rbx
movq 1*8(%rsp), %r12
movq 2*8(%rsp), %r14
movq 3*8(%rsp), %r13
movq 4*8(%rsp), %r15
addq $5*8, %rsp
RET
.Lshort:
movl %ecx, %r10d
jmp .L1
.Lunaligned:
xorl %ebx, %ebx
testb $1, %sil
jne .Lodd
1: testb $2, %sil
je 2f
source
movw (%rdi), %bx
dest
movw %bx, (%rsi)
leaq 2(%rdi), %rdi
subq $2, %rcx
leaq 2(%rsi), %rsi
addq %rbx, %rax
2: testb $4, %sil
je .Laligned
source
movl (%rdi), %ebx
dest
movl %ebx, (%rsi)
leaq 4(%rdi), %rdi
subq $4, %rcx
leaq 4(%rsi), %rsi
addq %rbx, %rax
jmp .Laligned
.Lodd:
source
movb (%rdi), %bl
dest
movb %bl, (%rsi)
leaq 1(%rdi), %rdi
leaq 1(%rsi), %rsi
/* decrement, set MSB */
leaq -1(%rcx, %rcx), %rcx
rorq $1, %rcx
shll $8, %ebx
addq %rbx, %rax
jmp 1b
.Lwas_odd:
roll $8, %eax
jmp .Lout
/* Exception: just return 0 */
.Lfault:
xorl %eax, %eax
jmp .Lout
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
2019-10-11 19:51:04 +08:00
SYM_FUNC_END(csum_partial_copy_generic)