Commit a57ed936 authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/asm changes from Ingo Molnar:
 "The biggest change (by line count) is the unification of the XOR code
  and then the introduction of an additional SSE based XOR assembly
  method.

  The other bigger change is the head_32.S rework/cleanup by Borislav
  Petkov.

  Last but not least there's the usual laundry list of small but
  dangerous (and hopefully perfectly tested) changes to subtle low level
  x86 code, plus cleanups."

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, head_32: Give the 6 label a real name
  x86, head_32: Remove second CPUID detection from default_entry
  x86: Detect CPUID support early at boot
  x86, head_32: Remove i386 pieces
  x86: Require MOVBE feature in cpuid when we use it
  x86: Enable ARCH_USE_BUILTIN_BSWAP
  x86/xor: Add alternative SSE implementation only prefetching once per 64-byte line
  x86/xor: Unify SSE-base xor-block routines
  x86: Fix a typo
  x86/mm: Fix the argument passed to sync_global_pgds()
  x86/mm: Convert update_mmu_cache() and update_mmu_cache_pmd() to functions
  ix86: Tighten asmlinkage_protect() constraints
parents 5800700f 5e2a044d
......@@ -116,6 +116,7 @@ config X86
select MODULES_USE_ELF_RELA if X86_64
select CLONE_BACKWARDS if X86_32
select GENERIC_SIGALTSTACK
select ARCH_USE_BUILTIN_BSWAP
config INSTRUCTION_DECODER
def_bool y
......
......@@ -27,20 +27,20 @@
#define __asmlinkage_protect0(ret) \
__asmlinkage_protect_n(ret)
#define __asmlinkage_protect1(ret, arg1) \
__asmlinkage_protect_n(ret, "g" (arg1))
__asmlinkage_protect_n(ret, "m" (arg1))
#define __asmlinkage_protect2(ret, arg1, arg2) \
__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2))
__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2))
#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \
__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3))
__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3))
#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \
__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
"g" (arg4))
__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
"m" (arg4))
#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \
__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
"g" (arg4), "g" (arg5))
__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
"m" (arg4), "m" (arg5))
#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \
__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
"g" (arg4), "g" (arg5), "g" (arg6))
__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
"m" (arg4), "m" (arg5), "m" (arg6))
#endif /* CONFIG_X86_32 */
......
......@@ -786,6 +786,18 @@ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
memcpy(dst, src, count * sizeof(pgd_t));
}
/*
* The x86 doesn't have any external MMU info: the kernel page
* tables contain all the necessary information.
*/
static inline void update_mmu_cache(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
}
static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd)
{
}
#include <asm-generic/pgtable.h>
#endif /* __ASSEMBLY__ */
......
......@@ -66,13 +66,6 @@ do { \
__flush_tlb_one((vaddr)); \
} while (0)
/*
* The i386 doesn't have any external MMU info: the kernel page
* tables contain all the necessary information.
*/
#define update_mmu_cache(vma, address, ptep) do { } while (0)
#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
#endif /* !__ASSEMBLY__ */
/*
......
......@@ -142,9 +142,6 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
#define pte_unmap(pte) ((void)(pte))/* NOP */
#define update_mmu_cache(vma, address, ptep) do { } while (0)
#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
/* Encode and de-code a swap entry */
#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
......
......@@ -47,6 +47,12 @@
# define NEED_NOPL 0
#endif
#ifdef CONFIG_MATOM
# define NEED_MOVBE (1<<(X86_FEATURE_MOVBE & 31))
#else
# define NEED_MOVBE 0
#endif
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT
/* Paravirtualized systems may not have PSE or PGE available */
......@@ -80,7 +86,7 @@
#define REQUIRED_MASK2 0
#define REQUIRED_MASK3 (NEED_NOPL)
#define REQUIRED_MASK4 0
#define REQUIRED_MASK4 (NEED_MOVBE)
#define REQUIRED_MASK5 0
#define REQUIRED_MASK6 0
#define REQUIRED_MASK7 0
......
#ifdef CONFIG_KMEMCHECK
/* kmemcheck doesn't handle MMX/SSE/SSE2 instructions */
# include <asm-generic/xor.h>
#elif !defined(_ASM_X86_XOR_H)
#define _ASM_X86_XOR_H
/*
* Optimized RAID-5 checksumming functions for SSE.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* You should have received a copy of the GNU General Public License
* (for example /usr/src/linux/COPYING); if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
* Cache avoiding checksumming functions utilizing KNI instructions
* Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
*/
/*
* Based on
* High-speed RAID5 checksumming functions utilizing SSE instructions.
* Copyright (C) 1998 Ingo Molnar.
*/
/*
* x86-64 changes / gcc fixes from Andi Kleen.
* Copyright 2002 Andi Kleen, SuSE Labs.
*
* This hasn't been optimized for the hammer yet, but there are likely
* no advantages to be gotten from x86-64 here anyways.
*/
#include <asm/i387.h>
#ifdef CONFIG_X86_32
/* reduce register pressure */
# define XOR_CONSTANT_CONSTRAINT "i"
#else
# define XOR_CONSTANT_CONSTRAINT "re"
#endif
#define OFFS(x) "16*("#x")"
#define PF_OFFS(x) "256+16*("#x")"
#define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1]) ;\n"
#define LD(x, y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y" ;\n"
#define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%[p1]) ;\n"
#define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n"
#define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n"
#define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n"
#define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n"
#define XO1(x, y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n"
#define XO2(x, y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n"
#define XO3(x, y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n"
#define XO4(x, y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n"
#define NOP(x)
#define BLK64(pf, op, i) \
pf(i) \
op(i, 0) \
op(i + 1, 1) \
op(i + 2, 2) \
op(i + 3, 3)
static void
xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
LD(i, 0) \
LD(i + 1, 1) \
PF1(i) \
PF1(i + 2) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF0(i + 4) \
PF0(i + 6) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines),
[p1] "+r" (p1), [p2] "+r" (p2)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_2_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
BLK64(PF0, LD, i) \
BLK64(PF1, XO1, i) \
BLK64(NOP, ST, i) \
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines),
[p1] "+r" (p1), [p2] "+r" (p2)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" add %[inc], %[p3] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines),
[p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_3_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
BLK64(PF0, LD, i) \
BLK64(PF1, XO1, i) \
BLK64(PF2, XO2, i) \
BLK64(NOP, ST, i) \
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" add %[inc], %[p3] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines),
[p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
PF3(i) \
PF3(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
XO3(i, 0) \
XO3(i + 1, 1) \
XO3(i + 2, 2) \
XO3(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" add %[inc], %[p3] ;\n"
" add %[inc], %[p4] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines), [p1] "+r" (p1),
[p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_4_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
BLK64(PF0, LD, i) \
BLK64(PF1, XO1, i) \
BLK64(PF2, XO2, i) \
BLK64(PF3, XO3, i) \
BLK64(NOP, ST, i) \
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" add %[inc], %[p3] ;\n"
" add %[inc], %[p4] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines), [p1] "+r" (p1),
[p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
PF3(i) \
PF3(i + 2) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
PF4(i) \
PF4(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO3(i, 0) \
XO3(i + 1, 1) \
XO3(i + 2, 2) \
XO3(i + 3, 3) \
XO4(i, 0) \
XO4(i + 1, 1) \
XO4(i + 2, 2) \
XO4(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" add %[inc], %[p3] ;\n"
" add %[inc], %[p4] ;\n"
" add %[inc], %[p5] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2),
[p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_5_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
BLK64(PF0, LD, i) \
BLK64(PF1, XO1, i) \
BLK64(PF2, XO2, i) \
BLK64(PF3, XO3, i) \
BLK64(PF4, XO4, i) \
BLK64(NOP, ST, i) \
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" add %[inc], %[p1] ;\n"
" add %[inc], %[p2] ;\n"
" add %[inc], %[p3] ;\n"
" add %[inc], %[p4] ;\n"
" add %[inc], %[p5] ;\n"
" dec %[cnt] ;\n"
" jnz 1b ;\n"
: [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2),
[p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5)
: [inc] XOR_CONSTANT_CONSTRAINT (256UL)
: "memory");
kernel_fpu_end();
}
static struct xor_block_template xor_block_sse_pf64 = {
.name = "prefetch64-sse",
.do_2 = xor_sse_2_pf64,
.do_3 = xor_sse_3_pf64,
.do_4 = xor_sse_4_pf64,
.do_5 = xor_sse_5_pf64,
};
#undef LD
#undef XO1
#undef XO2
#undef XO3
#undef XO4
#undef ST
#undef NOP
#undef BLK64
#undef BLOCK
#undef XOR_CONSTANT_CONSTRAINT
#ifdef CONFIG_X86_32
# include <asm/xor_32.h>
#else
# include <asm/xor_64.h>
#endif
#endif
#define XOR_SELECT_TEMPLATE(FASTEST) \
AVX_SELECT(FASTEST)
#endif /* _ASM_X86_XOR_H */
......@@ -2,7 +2,7 @@
#define _ASM_X86_XOR_32_H
/*
* Optimized RAID-5 checksumming functions for MMX and SSE.
* Optimized RAID-5 checksumming functions for MMX.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
......@@ -529,290 +529,6 @@ static struct xor_block_template xor_block_p5_mmx = {
.do_5 = xor_p5_mmx_5,
};
/*
* Cache avoiding checksumming functions utilizing KNI instructions
* Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
*/
#define OFFS(x) "16*("#x")"
#define PF_OFFS(x) "256+16*("#x")"
#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n"
#define LD(x, y) " movaps "OFFS(x)"(%1), %%xmm"#y" ;\n"
#define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%1) ;\n"
#define PF1(x) " prefetchnta "PF_OFFS(x)"(%2) ;\n"
#define PF2(x) " prefetchnta "PF_OFFS(x)"(%3) ;\n"
#define PF3(x) " prefetchnta "PF_OFFS(x)"(%4) ;\n"
#define PF4(x) " prefetchnta "PF_OFFS(x)"(%5) ;\n"
#define PF5(x) " prefetchnta "PF_OFFS(x)"(%6) ;\n"
#define XO1(x, y) " xorps "OFFS(x)"(%2), %%xmm"#y" ;\n"
#define XO2(x, y) " xorps "OFFS(x)"(%3), %%xmm"#y" ;\n"
#define XO3(x, y) " xorps "OFFS(x)"(%4), %%xmm"#y" ;\n"
#define XO4(x, y) " xorps "OFFS(x)"(%5), %%xmm"#y" ;\n"
#define XO5(x, y) " xorps "OFFS(x)"(%6), %%xmm"#y" ;\n"
static void
xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
LD(i, 0) \
LD(i + 1, 1) \
PF1(i) \
PF1(i + 2) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF0(i + 4) \
PF0(i + 6) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $256, %1 ;\n"
" addl $256, %2 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2)
:
: "memory");
kernel_fpu_end();
}
static void
xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i,0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO1(i,0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
XO2(i,0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
ST(i,0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $256, %1 ;\n"
" addl $256, %2 ;\n"
" addl $256, %3 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r"(p2), "+r"(p3)
:
: "memory" );
kernel_fpu_end();
}
static void
xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i,0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
XO1(i,0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
PF3(i) \
PF3(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO2(i,0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
XO3(i,0) \
XO3(i + 1, 1) \
XO3(i + 2, 2) \
XO3(i + 3, 3) \
ST(i,0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $256, %1 ;\n"
" addl $256, %2 ;\n"
" addl $256, %3 ;\n"
" addl $256, %4 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
:
: "memory" );
kernel_fpu_end();
}
static void
xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned long lines = bytes >> 8;
kernel_fpu_begin();
/* Make sure GCC forgets anything it knows about p4 or p5,
such that it won't pass to the asm volatile below a
register that is shared with any other variable. That's
because we modify p4 and p5 there, but we can't mark them
as read/write, otherwise we'd overflow the 10-asm-operands
limit of GCC < 3.1. */
asm("" : "+r" (p4), "+r" (p5));
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i,0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
XO1(i,0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
PF3(i) \
PF3(i + 2) \
XO2(i,0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
PF4(i) \
PF4(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO3(i,0) \
XO3(i + 1, 1) \
XO3(i + 2, 2) \
XO3(i + 3, 3) \
XO4(i,0) \
XO4(i + 1, 1) \
XO4(i + 2, 2) \
XO4(i + 3, 3) \
ST(i,0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addl $256, %1 ;\n"
" addl $256, %2 ;\n"
" addl $256, %3 ;\n"
" addl $256, %4 ;\n"
" addl $256, %5 ;\n"
" decl %0 ;\n"
" jnz 1b ;\n"
: "+r" (lines),
"+r" (p1), "+r" (p2), "+r" (p3)
: "r" (p4), "r" (p5)
: "memory");
/* p4 and p5 were modified, and now the variables are dead.
Clobber them just to be sure nobody does something stupid
like assuming they have some legal value. */
asm("" : "=r" (p4), "=r" (p5));
kernel_fpu_end();
}
static struct xor_block_template xor_block_pIII_sse = {
.name = "pIII_sse",
.do_2 = xor_sse_2,
......@@ -827,26 +543,25 @@ static struct xor_block_template xor_block_pIII_sse = {
/* Also try the generic routines. */
#include <asm-generic/xor.h>
/* We force the use of the SSE xor block because it can write around L2.
We may also be able to load into the L1 only depending on how the cpu
deals with a load to a line that is being prefetched. */
#undef XOR_TRY_TEMPLATES
#define XOR_TRY_TEMPLATES \
do { \
xor_speed(&xor_block_8regs); \
xor_speed(&xor_block_8regs_p); \
xor_speed(&xor_block_32regs); \
xor_speed(&xor_block_32regs_p); \
AVX_XOR_SPEED; \
if (cpu_has_xmm) \
if (cpu_has_xmm) { \
xor_speed(&xor_block_pIII_sse); \
if (cpu_has_mmx) { \
xor_speed(&xor_block_sse_pf64); \
} else if (cpu_has_mmx) { \
xor_speed(&xor_block_pII_mmx); \
xor_speed(&xor_block_p5_mmx); \
} else { \
xor_speed(&xor_block_8regs); \
xor_speed(&xor_block_8regs_p); \
xor_speed(&xor_block_32regs); \
xor_speed(&xor_block_32regs_p); \
} \
} while (0)
/* We force the use of the SSE xor block because it can write around L2.
We may also be able to load into the L1 only depending on how the cpu
deals with a load to a line that is being prefetched. */
#define XOR_SELECT_TEMPLATE(FASTEST) \
AVX_SELECT(cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
#endif /* _ASM_X86_XOR_32_H */
#ifndef _ASM_X86_XOR_64_H
#define _ASM_X86_XOR_64_H
/*
* Optimized RAID-5 checksumming functions for MMX and SSE.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* You should have received a copy of the GNU General Public License
* (for example /usr/src/linux/COPYING); if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
* Cache avoiding checksumming functions utilizing KNI instructions
* Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
*/
/*
* Based on
* High-speed RAID5 checksumming functions utilizing SSE instructions.
* Copyright (C) 1998 Ingo Molnar.
*/
/*
* x86-64 changes / gcc fixes from Andi Kleen.
* Copyright 2002 Andi Kleen, SuSE Labs.
*
* This hasn't been optimized for the hammer yet, but there are likely
* no advantages to be gotten from x86-64 here anyways.
*/
#include <asm/i387.h>
#define OFFS(x) "16*("#x")"
#define PF_OFFS(x) "256+16*("#x")"
#define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1]) ;\n"
#define LD(x, y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y" ;\n"
#define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%[p1]) ;\n"
#define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n"
#define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n"
#define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n"
#define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n"
#define PF5(x) " prefetchnta "PF_OFFS(x)"(%[p6]) ;\n"
#define XO1(x, y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n"
#define XO2(x, y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n"
#define XO3(x, y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n"
#define XO4(x, y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n"
#define XO5(x, y) " xorps "OFFS(x)"(%[p6]), %%xmm"#y" ;\n"
static void
xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned int lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
LD(i, 0) \
LD(i + 1, 1) \
PF1(i) \
PF1(i + 2) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF0(i + 4) \
PF0(i + 6) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addq %[inc], %[p1] ;\n"
" addq %[inc], %[p2] ;\n"
" decl %[cnt] ; jnz 1b"
: [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines)
: [inc] "r" (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned int lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addq %[inc], %[p1] ;\n"
" addq %[inc], %[p2] ;\n"
" addq %[inc], %[p3] ;\n"
" decl %[cnt] ; jnz 1b"
: [cnt] "+r" (lines),
[p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
: [inc] "r" (256UL)
: "memory");
kernel_fpu_end();
}
static void
xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned int lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
PF3(i) \
PF3(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
XO3(i, 0) \
XO3(i + 1, 1) \
XO3(i + 2, 2) \
XO3(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addq %[inc], %[p1] ;\n"
" addq %[inc], %[p2] ;\n"
" addq %[inc], %[p3] ;\n"
" addq %[inc], %[p4] ;\n"
" decl %[cnt] ; jnz 1b"
: [cnt] "+c" (lines),
[p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
: [inc] "r" (256UL)
: "memory" );
kernel_fpu_end();
}
static void
xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned int lines = bytes >> 8;
kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
PF1(i) \
PF1(i + 2) \
LD(i, 0) \
LD(i + 1, 1) \
LD(i + 2, 2) \
LD(i + 3, 3) \
PF2(i) \
PF2(i + 2) \
XO1(i, 0) \
XO1(i + 1, 1) \
XO1(i + 2, 2) \
XO1(i + 3, 3) \
PF3(i) \
PF3(i + 2) \
XO2(i, 0) \
XO2(i + 1, 1) \
XO2(i + 2, 2) \
XO2(i + 3, 3) \
PF4(i) \
PF4(i + 2) \
PF0(i + 4) \
PF0(i + 6) \
XO3(i, 0) \
XO3(i + 1, 1) \
XO3(i + 2, 2) \
XO3(i + 3, 3) \
XO4(i, 0) \
XO4(i + 1, 1) \
XO4(i + 2, 2) \
XO4(i + 3, 3) \
ST(i, 0) \
ST(i + 1, 1) \
ST(i + 2, 2) \
ST(i + 3, 3) \
PF0(0)
PF0(2)
" .align 32 ;\n"
" 1: ;\n"
BLOCK(0)
BLOCK(4)
BLOCK(8)
BLOCK(12)
" addq %[inc], %[p1] ;\n"
" addq %[inc], %[p2] ;\n"
" addq %[inc], %[p3] ;\n"
" addq %[inc], %[p4] ;\n"
" addq %[inc], %[p5] ;\n"
" decl %[cnt] ; jnz 1b"
: [cnt] "+c" (lines),
[p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4),
[p5] "+r" (p5)
: [inc] "r" (256UL)
: "memory");
kernel_fpu_end();
}
static struct xor_block_template xor_block_sse = {
.name = "generic_sse",
.do_2 = xor_sse_2,
......@@ -308,17 +13,15 @@ static struct xor_block_template xor_block_sse = {
/* Also try the AVX routines */
#include <asm/xor_avx.h>
/* We force the use of the SSE xor block because it can write around L2.
We may also be able to load into the L1 only depending on how the cpu
deals with a load to a line that is being prefetched. */
#undef XOR_TRY_TEMPLATES
#define XOR_TRY_TEMPLATES \
do { \
AVX_XOR_SPEED; \
xor_speed(&xor_block_sse_pf64); \
xor_speed(&xor_block_sse); \
} while (0)
/* We force the use of the SSE xor block because it can write around L2.
We may also be able to load into the L1 only depending on how the cpu
deals with a load to a line that is being prefetched. */
#define XOR_SELECT_TEMPLATE(FASTEST) \
AVX_SELECT(&xor_block_sse)
#endif /* _ASM_X86_XOR_64_H */
......@@ -307,36 +307,45 @@ default_entry:
movl %eax,%cr0
/*
* New page tables may be in 4Mbyte page mode and may
* be using the global pages.
* We want to start out with EFLAGS unambiguously cleared. Some BIOSes leave
* bits like NT set. This would confuse the debugger if this code is traced. So
* initialize them properly now before switching to protected mode. That means
* DF in particular (even though we have cleared it earlier after copying the
* command line) because GCC expects it.
*/
pushl $0
popfl
/*
* New page tables may be in 4Mbyte page mode and may be using the global pages.
*
* NOTE! If we are on a 486 we may have no cr4 at all!
* Specifically, cr4 exists if and only if CPUID exists
* and has flags other than the FPU flag set.
* NOTE! If we are on a 486 we may have no cr4 at all! Specifically, cr4 exists
* if and only if CPUID exists and has flags other than the FPU flag set.
*/
movl $-1,pa(X86_CPUID) # preset CPUID level
movl $X86_EFLAGS_ID,%ecx
pushl %ecx
popfl
popfl # set EFLAGS=ID
pushfl
popl %eax
pushl $0
popfl
pushfl
popl %edx
xorl %edx,%eax
testl %ecx,%eax
jz 6f # No ID flag = no CPUID = no CR4
popl %eax # get EFLAGS
testl $X86_EFLAGS_ID,%eax # did EFLAGS.ID remained set?
jz enable_paging # hw disallowed setting of ID bit
# which means no CPUID and no CR4
xorl %eax,%eax
cpuid
movl %eax,pa(X86_CPUID) # save largest std CPUID function
movl $1,%eax
cpuid
andl $~1,%edx # Ignore CPUID.FPU
jz 6f # No flags or only CPUID.FPU = no CR4
jz enable_paging # No flags or only CPUID.FPU = no CR4
movl pa(mmu_cr4_features),%eax
movl %eax,%cr4
testb $X86_CR4_PAE, %al # check if PAE is enabled
jz 6f
jz enable_paging
/* Check if extended functions are implemented */
movl $0x80000000, %eax
......@@ -344,7 +353,7 @@ default_entry:
/* Value must be in the range 0x80000001 to 0x8000ffff */
subl $0x80000001, %eax
cmpl $(0x8000ffff-0x80000001), %eax
ja 6f
ja enable_paging
/* Clear bogus XD_DISABLE bits */
call verify_cpu
......@@ -353,7 +362,7 @@ default_entry:
cpuid
/* Execute Disable bit supported? */
btl $(X86_FEATURE_NX & 31), %edx
jnc 6f
jnc enable_paging
/* Setup EFER (Extended Feature Enable Register) */
movl $MSR_EFER, %ecx
......@@ -363,7 +372,7 @@ default_entry:
/* Make changes effective */
wrmsr
6:
enable_paging:
/*
* Enable paging
......@@ -377,14 +386,6 @@ default_entry:
/* Shift the stack pointer to a virtual address */
addl $__PAGE_OFFSET, %esp
/*
* Initialize eflags. Some BIOS's leave bits like NT set. This would
* confuse the debugger if this code is traced.
* XXX - best to initialize before switching to protected mode.
*/
pushl $0
popfl
/*
* start system 32-bit setup. We need to re-do some of the things done
* in 16-bit mode for the "real" operations.
......@@ -395,30 +396,10 @@ default_entry:
call *%eax
1:
/* check if it is 486 or 386. */
/*
* XXX - this does a lot of unnecessary setup. Alignment checks don't
* apply at our cpl of 0 and the stack ought to be aligned already, and
* we don't need to preserve eflags.
* Check if it is 486
*/
movl $-1,X86_CPUID # -1 for no CPUID initially
movb $3,X86 # at least 386
pushfl # push EFLAGS
popl %eax # get EFLAGS
movl %eax,%ecx # save original EFLAGS
xorl $0x240000,%eax # flip AC and ID bits in EFLAGS
pushl %eax # copy to EFLAGS
popfl # set EFLAGS
pushfl # get new EFLAGS
popl %eax # put it in eax
xorl %ecx,%eax # change in flags
pushl %ecx # restore original EFLAGS
popfl
testl $0x40000,%eax # check if AC bit changed
je is386
movb $4,X86 # at least 486
testl $0x200000,%eax # check if ID bit changed
cmpl $-1,X86_CPUID
je is486
/* get vendor info */
......@@ -444,11 +425,10 @@ default_entry:
movb %cl,X86_MASK
movl %edx,X86_CAPABILITY
is486: movl $0x50022,%ecx # set AM, WP, NE and MP
jmp 2f
is386: movl $2,%ecx # set MP
2: movl %cr0,%eax
is486:
movb $4,X86
movl $0x50022,%ecx # set AM, WP, NE and MP
movl %cr0,%eax
andl $0x80000011,%eax # Save PG,PE,ET
orl %ecx,%eax
movl %eax,%cr0
......@@ -473,7 +453,6 @@ is386: movl $2,%ecx # set MP
xorl %eax,%eax # Clear LDT
lldt %ax
cld # gcc2 wants the direction flag cleared at all times
pushl $0 # fake return address for unwinder
jmp *(initial_code)
......
......@@ -157,7 +157,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
if (flags & MAP_FIXED)
return addr;
/* for MAP_32BIT mappings we force the legact mmap base */
/* for MAP_32BIT mappings we force the legacy mmap base */
if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
goto bottomup;
......
......@@ -605,7 +605,7 @@ kernel_physical_mapping_init(unsigned long start,
}
if (pgd_changed)
sync_global_pgds(addr, end);
sync_global_pgds(addr, end - 1);
__flush_tlb_all();
......@@ -984,7 +984,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
}
}
sync_global_pgds((unsigned long)start_page, end);
sync_global_pgds((unsigned long)start_page, end - 1);
return 0;
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment