diff options
30 files changed, 996 insertions, 1612 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bb0c0d0f6db..3b1b1da78da 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -283,7 +283,7 @@ config X86_VOYAGER config X86_VISWS bool "SGI 320/540 (Visual Workstation)" - depends on X86_32 && !PCI + depends on X86_32 && PCI help The SGI Visual Workstation series is an IA32-based workstation based on SGI systems chips with some legacy PC hardware attached. @@ -355,7 +355,7 @@ config X86_RDC321X config X86_VSMP bool "Support for ScaleMP vSMP" select PARAVIRT - depends on X86_64 && !PCI + depends on X86_64 && PCI help Support for ScaleMP vSMP systems. Say 'Y' here if this kernel is supposed to run on these EM64T-based machines. Only choose this option @@ -575,7 +575,7 @@ config SWIOTLB 3 GB of memory. If unsure, say Y. config IOMMU_HELPER - def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB) + def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU) config MAXSMP bool "Configure Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 3d22bb8175b..abff1b84ed5 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -344,7 +344,7 @@ config X86_F00F_BUG config X86_WP_WORKS_OK def_bool y - depends on X86_32 && !M386 + depends on !M386 config X86_INVLPG def_bool y diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 24e4d4928d6..20371d0635e 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -116,7 +116,7 @@ ENTRY(ia32_sysenter_target) pushfq CFI_ADJUST_CFA_OFFSET 8 /*CFI_REL_OFFSET rflags,0*/ - movl 8*3-THREAD_SIZE+threadinfo_sysenter_return(%rsp), %r10d + movl 8*3-THREAD_SIZE+TI_sysenter_return(%rsp), %r10d CFI_REGISTER rip,r10 pushq $__USER32_CS CFI_ADJUST_CFA_OFFSET 8 @@ -136,8 +136,9 @@ ENTRY(ia32_sysenter_target) .quad 1b,ia32_badarg .previous GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + orl $TS_COMPAT,TI_status(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%r10) CFI_REMEMBER_STATE jnz sysenter_tracesys sysenter_do_call: @@ -149,9 +150,9 @@ sysenter_do_call: GET_THREAD_INFO(%r10) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) + testl $_TIF_ALLWORK_MASK,TI_flags(%r10) jnz int_ret_from_sys_call - andl $~TS_COMPAT,threadinfo_status(%r10) + andl $~TS_COMPAT,TI_status(%r10) /* clear IF, that popfq doesn't enable interrupts early */ andl $~0x200,EFLAGS-R11(%rsp) movl RIP-R11(%rsp),%edx /* User %eip */ @@ -240,8 +241,9 @@ ENTRY(ia32_cstar_target) .quad 1b,ia32_badarg .previous GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + orl $TS_COMPAT,TI_status(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%r10) CFI_REMEMBER_STATE jnz cstar_tracesys cstar_do_call: @@ -253,9 +255,9 @@ cstar_do_call: GET_THREAD_INFO(%r10) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) + testl $_TIF_ALLWORK_MASK,TI_flags(%r10) jnz int_ret_from_sys_call - andl $~TS_COMPAT,threadinfo_status(%r10) + andl $~TS_COMPAT,TI_status(%r10) RESTORE_ARGS 1,-ARG_SKIP,1,1,1 movl RIP-ARGOFFSET(%rsp),%ecx CFI_REGISTER rip,rcx @@ -333,8 +335,9 @@ ENTRY(ia32_syscall) this could be a problem. */ SAVE_ARGS 0,0,1 GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + orl $TS_COMPAT,TI_status(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%r10) jnz ia32_tracesys ia32_do_syscall: cmpl $(IA32_NR_syscalls-1),%eax diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index bf7b4f7f60e..a31a579a47c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -109,21 +109,6 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; */ enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC; -#ifdef CONFIG_X86_64 - -/* rely on all ACPI tables being in the direct mapping */ -char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size) -{ - if (!phys_addr || !size) - return NULL; - - if (phys_addr+size <= (max_pfn_mapped << PAGE_SHIFT) + PAGE_SIZE) - return __va(phys_addr); - - return NULL; -} - -#else /* * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END, @@ -142,11 +127,15 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) unsigned long base, offset, mapped_size; int idx; - if (phys + size < 8 * 1024 * 1024) + if (!phys || !size) + return NULL; + + if (phys+size <= (max_pfn_mapped << PAGE_SHIFT)) return __va(phys); offset = phys & (PAGE_SIZE - 1); mapped_size = PAGE_SIZE - offset; + clear_fixmap(FIX_ACPI_END); set_fixmap(FIX_ACPI_END, phys); base = fix_to_virt(FIX_ACPI_END); @@ -158,13 +147,13 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) if (--idx < FIX_ACPI_BEGIN) return NULL; /* cannot handle this */ phys += PAGE_SIZE; + clear_fixmap(idx); set_fixmap(idx, phys); mapped_size += PAGE_SIZE; } return ((unsigned char *)base + offset); } -#endif #ifdef CONFIG_PCI_MMCONFIG /* The physical address of the MMCONFIG aperture. Set from ACPI tables. */ diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 3295e7c08fe..bacf5deeec2 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -34,7 +34,7 @@ int main(void) ENTRY(pid); BLANK(); #undef ENTRY -#define ENTRY(entry) DEFINE(threadinfo_ ## entry, offsetof(struct thread_info, entry)) +#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry)) ENTRY(flags); ENTRY(addr_limit); ENTRY(preempt_count); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 2e08619a9c5..9836a079cfd 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1066,6 +1066,9 @@ unsigned long __init e820_end(void) struct e820entry *ei = &e820.map[i]; unsigned long end_pfn; + if (ei->type != E820_RAM) + continue; + end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT; if (end_pfn > last_pfn) last_pfn = end_pfn; @@ -1193,6 +1196,9 @@ static int __init parse_memmap_opt(char *p) char *oldp; u64 start_at, mem_size; + if (!p) + return -EINVAL; + if (!strcmp(p, "exactmap")) { #ifdef CONFIG_CRASH_DUMP /* diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 07d69f26233..466b9284ed2 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -168,13 +168,13 @@ ENTRY(ret_from_fork) CFI_ADJUST_CFA_OFFSET -4 call schedule_tail GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx) jnz rff_trace rff_action: RESTORE_REST testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread? je int_ret_from_sys_call - testl $_TIF_IA32,threadinfo_flags(%rcx) + testl $_TIF_IA32,TI_flags(%rcx) jnz int_ret_from_sys_call RESTORE_TOP_OF_STACK %rdi,ARGOFFSET jmp ret_from_sys_call @@ -243,7 +243,8 @@ ENTRY(system_call_after_swapgs) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \ + TI_flags(%rcx) jnz tracesys cmpq $__NR_syscall_max,%rax ja badsys @@ -262,7 +263,7 @@ sysret_check: GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx jnz sysret_careful CFI_REMEMBER_STATE @@ -347,10 +348,10 @@ int_ret_from_sys_call: int_with_check: LOCKDEP_SYS_EXIT_IRQ GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx jnz int_careful - andl $~TS_COMPAT,threadinfo_status(%rcx) + andl $~TS_COMPAT,TI_status(%rcx) jmp retint_swapgs /* Either reschedule or signal or syscall exit tracking needed. */ @@ -558,7 +559,7 @@ retint_with_reschedule: movl $_TIF_WORK_MASK,%edi retint_check: LOCKDEP_SYS_EXIT_IRQ - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx CFI_REMEMBER_STATE jnz retint_careful @@ -654,9 +655,9 @@ retint_signal: /* Returning to kernel space. Check if we need preemption */ /* rcx: threadinfo. interrupts off. */ ENTRY(retint_kernel) - cmpl $0,threadinfo_preempt_count(%rcx) + cmpl $0,TI_preempt_count(%rcx) jnz retint_restore_args - bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx) + bt $TIF_NEED_RESCHED,TI_flags(%rcx) jnc retint_restore_args bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args @@ -819,7 +820,7 @@ paranoid_restore\trace: jmp irq_return paranoid_userspace\trace: GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%ebx + movl TI_flags(%rcx),%ebx andl $_TIF_WORK_MASK,%ebx jz paranoid_swapgs\trace movq %rsp,%rdi /* &pt_regs */ @@ -917,7 +918,7 @@ error_exit: testl %eax,%eax jne retint_kernel LOCKDEP_SYS_EXIT_IRQ - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx movl $_TIF_WORK_MASK,%edi andl %edi,%edx jnz retint_careful diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c index 0494cdb270c..848411753c7 100644 --- a/arch/x86/kernel/io_apic_64.c +++ b/arch/x86/kernel/io_apic_64.c @@ -1724,11 +1724,6 @@ static inline void __init check_timer(void) apic2 = apic1; } - replace_pin_at_irq(0, 0, 0, apic1, pin1); - apic1 = 0; - pin1 = 0; - setup_timer_IRQ0_pin(apic1, pin1, cfg->vector); - if (pin1 != -1) { /* * Ok, does IRQ0 through the IOAPIC work? diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 3c36f92160c..4a775d00195 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -513,6 +513,7 @@ void __init tsc_init(void) */ for_each_possible_cpu(cpu) set_cyc2ns_scale(cpu_khz, cpu); + use_tsc_delay(); if (tsc_disabled > 0) return; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 76f60f52a88..83226e0a7ce 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -4,8 +4,8 @@ obj-$(CONFIG_SMP) := msr-on-cpu.o -lib-y := delay_$(BITS).o -lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o +lib-y := delay.o +lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o ifeq ($(CONFIG_X86_32),y) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index ee1c3f63515..e5afb4ad3f1 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -1,8 +1,10 @@ -/* Copyright 2002 Andi Kleen, SuSE Labs. +/* + * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com> + * Copyright 2002 Andi Kleen, SuSE Labs. * Subject to the GNU Public License v2. - * - * Functions to copy from and to user space. - */ + * + * Functions to copy from and to user space. + */ #include <linux/linkage.h> #include <asm/dwarf2.h> @@ -20,60 +22,88 @@ .long \orig-1f /* by default jump to orig */ 1: .section .altinstr_replacement,"ax" -2: .byte 0xe9 /* near jump with 32bit immediate */ +2: .byte 0xe9 /* near jump with 32bit immediate */ .long \alt-1b /* offset */ /* or alternatively to alt */ .previous .section .altinstructions,"a" .align 8 .quad 0b .quad 2b - .byte \feature /* when feature is set */ + .byte \feature /* when feature is set */ .byte 5 .byte 5 .previous .endm -/* Standard copy_to_user with segment limit checking */ + .macro ALIGN_DESTINATION +#ifdef FIX_ALIGNMENT + /* check for bad alignment of destination */ + movl %edi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %r8d,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous + + .section __ex_table,"a" + .align 8 + .quad 100b,103b + .quad 101b,103b + .previous +#endif + .endm + +/* Standard copy_to_user with segment limit checking */ ENTRY(copy_to_user) CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rdi,%rcx addq %rdx,%rcx - jc bad_to_user - cmpq threadinfo_addr_limit(%rax),%rcx + jc bad_to_user + cmpq TI_addr_limit(%rax),%rcx jae bad_to_user - xorl %eax,%eax /* clear zero flag */ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC -ENTRY(copy_user_generic) +/* Standard copy_from_user with segment limit checking */ +ENTRY(copy_from_user) CFI_STARTPROC - movl $1,%ecx /* set zero flag */ + GET_THREAD_INFO(%rax) + movq %rsi,%rcx + addq %rdx,%rcx + jc bad_from_user + cmpq TI_addr_limit(%rax),%rcx + jae bad_from_user ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC +ENDPROC(copy_from_user) -ENTRY(__copy_from_user_inatomic) +ENTRY(copy_user_generic) CFI_STARTPROC - xorl %ecx,%ecx /* clear zero flag */ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC +ENDPROC(copy_user_generic) -/* Standard copy_from_user with segment limit checking */ -ENTRY(copy_from_user) +ENTRY(__copy_from_user_inatomic) CFI_STARTPROC - GET_THREAD_INFO(%rax) - movq %rsi,%rcx - addq %rdx,%rcx - jc bad_from_user - cmpq threadinfo_addr_limit(%rax),%rcx - jae bad_from_user - movl $1,%ecx /* set zero flag */ ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string CFI_ENDPROC -ENDPROC(copy_from_user) - +ENDPROC(__copy_from_user_inatomic) + .section .fixup,"ax" /* must zero dest */ +ENTRY(bad_from_user) bad_from_user: CFI_STARTPROC movl %edx,%ecx @@ -81,271 +111,158 @@ bad_from_user: rep stosb bad_to_user: - movl %edx,%eax + movl %edx,%eax ret CFI_ENDPROC -END(bad_from_user) +ENDPROC(bad_from_user) .previous - - + /* * copy_user_generic_unrolled - memory copy with exception handling. - * This version is for CPUs like P4 that don't have efficient micro code for rep movsq - * - * Input: + * This version is for CPUs like P4 that don't have efficient micro + * code for rep movsq + * + * Input: * rdi destination * rsi source * rdx count - * ecx zero flag -- if true zero destination on error * - * Output: - * eax uncopied bytes or 0 if successful. + * Output: + * eax uncopied bytes or 0 if successfull. */ ENTRY(copy_user_generic_unrolled) CFI_STARTPROC - pushq %rbx - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rbx, 0 - pushq %rcx - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rcx, 0 - xorl %eax,%eax /*zero for the exception handler */ - -#ifdef FIX_ALIGNMENT - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jnz .Lbad_alignment -.Lafter_bad_alignment: -#endif - - movq %rdx,%rcx - - movl $64,%ebx - shrq $6,%rdx - decq %rdx - js .Lhandle_tail - - .p2align 4 -.Lloop: -.Ls1: movq (%rsi),%r11 -.Ls2: movq 1*8(%rsi),%r8 -.Ls3: movq 2*8(%rsi),%r9 -.Ls4: movq 3*8(%rsi),%r10 -.Ld1: movq %r11,(%rdi) -.Ld2: movq %r8,1*8(%rdi) -.Ld3: movq %r9,2*8(%rdi) -.Ld4: movq %r10,3*8(%rdi) - -.Ls5: movq 4*8(%rsi),%r11 -.Ls6: movq 5*8(%rsi),%r8 -.Ls7: movq 6*8(%rsi),%r9 -.Ls8: movq 7*8(%rsi),%r10 -.Ld5: movq %r11,4*8(%rdi) -.Ld6: movq %r8,5*8(%rdi) -.Ld7: movq %r9,6*8(%rdi) -.Ld8: movq %r10,7*8(%rdi) - - decq %rdx - + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 +5: movq %r8,(%rdi) +6: movq %r9,1*8(%rdi) +7: movq %r10,2*8(%rdi) +8: movq %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movq %r8,4*8(%rdi) +14: movq %r9,5*8(%rdi) +15: movq %r10,6*8(%rdi) +16: movq %r11,7*8(%rdi) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi - - jns .Lloop - - .p2align 4 -.Lhandle_tail: - movl %ecx,%edx - andl $63,%ecx - shrl $3,%ecx - jz .Lhandle_7 - movl $8,%ebx - .p2align 4 -.Lloop_8: -.Ls9: movq (%rsi),%r8 -.Ld9: movq %r8,(%rdi) decl %ecx - leaq 8(%rdi),%rdi + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 +19: movq %r8,(%rdi) leaq 8(%rsi),%rsi - jnz .Lloop_8 - -.Lhandle_7: + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f movl %edx,%ecx - andl $7,%ecx - jz .Lende - .p2align 4 -.Lloop_1: -.Ls10: movb (%rsi),%bl -.Ld10: movb %bl,(%rdi) - incq %rdi +21: movb (%rsi),%al +22: movb %al,(%rdi) incq %rsi + incq %rdi decl %ecx - jnz .Lloop_1 - - CFI_REMEMBER_STATE -.Lende: - popq %rcx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE rcx - popq %rbx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE rbx + jnz 21b +23: xor %eax,%eax ret - CFI_RESTORE_STATE -#ifdef FIX_ALIGNMENT - /* align destination */ - .p2align 4 -.Lbad_alignment: - movl $8,%r9d - subl %ecx,%r9d - movl %r9d,%ecx - cmpq %r9,%rdx - jz .Lhandle_7 - js .Lhandle_7 -.Lalign_1: -.Ls11: movb (%rsi),%bl -.Ld11: movb %bl,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .Lalign_1 - subq %r9,%rdx - jmp .Lafter_bad_alignment -#endif + .section .fixup,"ax" +30: shll $6,%ecx + addl %ecx,%edx + jmp 60f +40: leal (%edx,%ecx,8),%edx + jmp 60f +50: movl %ecx,%edx +60: jmp copy_user_handle_tail /* ecx is zerorest also */ + .previous - /* table sorted by exception address */ .section __ex_table,"a" .align 8 - .quad .Ls1,.Ls1e /* Ls1-Ls4 have copied zero bytes */ - .quad .Ls2,.Ls1e - .quad .Ls3,.Ls1e - .quad .Ls4,.Ls1e - .quad .Ld1,.Ls1e /* Ld1-Ld4 have copied 0-24 bytes */ - .quad .Ld2,.Ls2e - .quad .Ld3,.Ls3e - .quad .Ld4,.Ls4e - .quad .Ls5,.Ls5e /* Ls5-Ls8 have copied 32 bytes */ - .quad .Ls6,.Ls5e - .quad .Ls7,.Ls5e - .quad .Ls8,.Ls5e - .quad .Ld5,.Ls5e /* Ld5-Ld8 have copied 32-56 bytes */ - .quad .Ld6,.Ls6e - .quad .Ld7,.Ls7e - .quad .Ld8,.Ls8e - .quad .Ls9,.Le_quad - .quad .Ld9,.Le_quad - .quad .Ls10,.Le_byte - .quad .Ld10,.Le_byte -#ifdef FIX_ALIGNMENT - .quad .Ls11,.Lzero_rest - .quad .Ld11,.Lzero_rest -#endif - .quad .Le5,.Le_zero + .quad 1b,30b + .quad 2b,30b + .quad 3b,30b + .quad 4b,30b + .quad 5b,30b + .quad 6b,30b + .quad 7b,30b + .quad 8b,30b + .quad 9b,30b + .quad 10b,30b + .quad 11b,30b + .quad 12b,30b + .quad 13b,30b + .quad 14b,30b + .quad 15b,30b + .quad 16b,30b + .quad 18b,40b + .quad 19b,40b + .quad 21b,50b + .quad 22b,50b .previous - - /* eax: zero, ebx: 64 */ -.Ls1e: addl $8,%eax /* eax is bytes left uncopied within the loop (Ls1e: 64 .. Ls8e: 8) */ -.Ls2e: addl $8,%eax -.Ls3e: addl $8,%eax -.Ls4e: addl $8,%eax -.Ls5e: addl $8,%eax -.Ls6e: addl $8,%eax -.Ls7e: addl $8,%eax -.Ls8e: addl $8,%eax - addq %rbx,%rdi /* +64 */ - subq %rax,%rdi /* correct destination with computed offset */ - - shlq $6,%rdx /* loop counter * 64 (stride length) */ - addq %rax,%rdx /* add offset to loopcnt */ - andl $63,%ecx /* remaining bytes */ - addq %rcx,%rdx /* add them */ - jmp .Lzero_rest - - /* exception on quad word loop in tail handling */ - /* ecx: loopcnt/8, %edx: length, rdi: correct */ -.Le_quad: - shll $3,%ecx - andl $7,%edx - addl %ecx,%edx - /* edx: bytes to zero, rdi: dest, eax:zero */ -.Lzero_rest: - cmpl $0,(%rsp) - jz .Le_zero - movq %rdx,%rcx -.Le_byte: - xorl %eax,%eax -.Le5: rep - stosb - /* when there is another exception while zeroing the rest just return */ -.Le_zero: - movq %rdx,%rax - jmp .Lende CFI_ENDPROC -ENDPROC(copy_user_generic) +ENDPROC(copy_user_generic_unrolled) - - /* Some CPUs run faster using the string copy instructions. - This is also a lot simpler. Use them when possible. - Patch in jmps to this code instead of copying it fully - to avoid unwanted aliasing in the exception tables. */ - - /* rdi destination - * rsi source - * rdx count - * ecx zero flag - * - * Output: - * eax uncopied bytes or 0 if successfull. - * - * Only 4GB of copy is supported. This shouldn't be a problem - * because the kernel normally only writes from/to page sized chunks - * even if user space passed a longer buffer. - * And more would be dangerous because both Intel and AMD have - * errata with rep movsq > 4GB. If someone feels the need to fix - * this please consider this. - */ +/* Some CPUs run faster using the string copy instructions. + * This is also a lot simpler. Use them when possible. + * + * Only 4GB of copy is supported. This shouldn't be a problem + * because the kernel normally only writes from/to page sized chunks + * even if user space passed a longer buffer. + * And more would be dangerous because both Intel and AMD have + * errata with rep movsq > 4GB. If someone feels the need to fix + * this please consider this. + * + * Input: + * rdi destination + * rsi source + * rdx count + * + * Output: + * eax uncopied bytes or 0 if successful. + */ ENTRY(copy_user_generic_string) CFI_STARTPROC - movl %ecx,%r8d /* save zero flag */ + andl %edx,%edx + jz 4f + cmpl $8,%edx + jb 2f /* less than 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION movl %edx,%ecx shrl $3,%ecx - andl $7,%edx - jz 10f -1: rep - movsq - movl %edx,%ecx -2: rep - movsb -9: movl %ecx,%eax - ret - - /* multiple of 8 byte */ -10: rep + andl $7,%edx +1: rep movsq - xor %eax,%eax +2: movl %edx,%ecx +3: rep + movsb +4: xorl %eax,%eax ret - /* exception handling */ -3: lea (%rdx,%rcx,8),%rax /* exception on quad loop */ - jmp 6f -5: movl %ecx,%eax /* exception on byte loop */ - /* eax: left over bytes */ -6: testl %r8d,%r8d /* zero flag set? */ - jz 7f - movl %eax,%ecx /* initialize x86 loop counter */ - push %rax - xorl %eax,%eax -8: rep - stosb /* zero the rest */ -11: pop %rax -7: ret - CFI_ENDPROC -END(copy_user_generic_c) + .section .fixup,"ax" +11: leal (%edx,%ecx,8),%ecx +12: movl %ecx,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous .section __ex_table,"a" - .quad 1b,3b - .quad 2b,5b - .quad 8b,11b - .quad 10b,3b + .align 8 + .quad 1b,11b + .quad 3b,12b .previous + CFI_ENDPROC +ENDPROC(copy_user_generic_string) diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S index 9d3d1ab8376..93353d6a526 100644 --- a/arch/x86/lib/copy_user_nocache_64.S +++ b/arch/x86/lib/copy_user_nocache_64.S @@ -1,4 +1,6 @@ -/* Copyright 2002 Andi Kleen, SuSE Labs. +/* + * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com> + * Copyright 2002 Andi Kleen, SuSE Labs. * Subject to the GNU Public License v2. * * Functions to copy from and to user space. @@ -12,204 +14,125 @@ #include <asm/current.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> -#include <asm/cpufeature.h> - -/* - * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. - * - * Input: - * rdi destination - * rsi source - * rdx count - * rcx zero flag when 1 zero on exception - * - * Output: - * eax uncopied bytes or 0 if successful. - */ -ENTRY(__copy_user_nocache) - CFI_STARTPROC - pushq %rbx - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rbx, 0 - pushq %rcx /* save zero flag */ - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rcx, 0 - - xorl %eax,%eax /* zero for the exception handler */ + .macro ALIGN_DESTINATION #ifdef FIX_ALIGNMENT /* check for bad alignment of destination */ movl %edi,%ecx andl $7,%ecx - jnz .Lbad_alignment -.Lafter_bad_alignment: -#endif - - movq %rdx,%rcx - - movl $64,%ebx - shrq $6,%rdx - decq %rdx - js .Lhandle_tail - - .p2align 4 -.Lloop: -.Ls1: movq (%rsi),%r11 -.Ls2: movq 1*8(%rsi),%r8 -.Ls3: movq 2*8(%rsi),%r9 -.Ls4: movq 3*8(%rsi),%r10 -.Ld1: movnti %r11,(%rdi) -.Ld2: movnti %r8,1*8(%rdi) -.Ld3: movnti %r9,2*8(%rdi) -.Ld4: movnti %r10,3*8(%rdi) - -.Ls5: movq 4*8(%rsi),%r11 -.Ls6: movq 5*8(%rsi),%r8 -.Ls7: movq 6*8(%rsi),%r9 -.Ls8: movq 7*8(%rsi),%r10 -.Ld5: movnti %r11,4*8(%rdi) -.Ld6: movnti %r8,5*8(%rdi) -.Ld7: movnti %r9,6*8(%rdi) -.Ld8: movnti %r10,7*8(%rdi) + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %r8d,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous - dec %rdx + .section __ex_table,"a" + .align 8 + .quad 100b,103b + .quad 101b,103b + .previous +#endif + .endm +/* + * copy_user_nocache - Uncached memory copy with exception handling + * This will force destination/source out of cache for more performance. + */ +ENTRY(__copy_user_nocache) + CFI_STARTPROC + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 +5: movnti %r8,(%rdi) +6: movnti %r9,1*8(%rdi) +7: movnti %r10,2*8(%rdi) +8: movnti %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movnti %r8,4*8(%rdi) +14: movnti %r9,5*8(%rdi) +15: movnti %r10,6*8(%rdi) +16: movnti %r11,7*8(%rdi) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi - - jns .Lloop - - .p2align 4 -.Lhandle_tail: - movl %ecx,%edx - andl $63,%ecx - shrl $3,%ecx - jz .Lhandle_7 - movl $8,%ebx - .p2align 4 -.Lloop_8: -.Ls9: movq (%rsi),%r8 -.Ld9: movnti %r8,(%rdi) decl %ecx - leaq 8(%rdi),%rdi + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 +19: movnti %r8,(%rdi) leaq 8(%rsi),%rsi - jnz .Lloop_8 - -.Lhandle_7: + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f movl %edx,%ecx - andl $7,%ecx - jz .Lende - .p2align 4 -.Lloop_1: -.Ls10: movb (%rsi),%bl -.Ld10: movb %bl,(%rdi) - incq %rdi +21: movb (%rsi),%al +22: movb %al,(%rdi) incq %rsi + incq %rdi decl %ecx - jnz .Lloop_1 - - CFI_REMEMBER_STATE -.Lende: - popq %rcx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE %rcx - popq %rbx - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE rbx + jnz 21b +23: xorl %eax,%eax sfence ret - CFI_RESTORE_STATE -#ifdef FIX_ALIGNMENT - /* align destination */ - .p2align 4 -.Lbad_alignment: - movl $8,%r9d - subl %ecx,%r9d - movl %r9d,%ecx - cmpq %r9,%rdx - jz .Lhandle_7 - js .Lhandle_7 -.Lalign_1: -.Ls11: movb (%rsi),%bl -.Ld11: movb %bl,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz .Lalign_1 - subq %r9,%rdx - jmp .Lafter_bad_alignment -#endif + .section .fixup,"ax" +30: shll $6,%ecx + addl %ecx,%edx + jmp 60f +40: leal (%edx,%ecx,8),%edx + jmp 60f +50: movl %ecx,%edx +60: sfence + movl %r8d,%ecx + jmp copy_user_handle_tail + .previous - /* table sorted by exception address */ .section __ex_table,"a" - .align 8 - .quad .Ls1,.Ls1e /* .Ls[1-4] - 0 bytes copied */ - .quad .Ls2,.Ls1e - .quad .Ls3,.Ls1e - .quad .Ls4,.Ls1e - .quad .Ld1,.Ls1e /* .Ld[1-4] - 0..24 bytes coped */ - .quad .Ld2,.Ls2e - .quad .Ld3,.Ls3e - .quad .Ld4,.Ls4e - .quad .Ls5,.Ls5e /* .Ls[5-8] - 32 bytes copied */ - .quad .Ls6,.Ls5e - .quad .Ls7,.Ls5e - .quad .Ls8,.Ls5e - .quad .Ld5,.Ls5e /* .Ld[5-8] - 32..56 bytes copied */ - .quad .Ld6,.Ls6e - .quad .Ld7,.Ls7e - .quad .Ld8,.Ls8e - .quad .Ls9,.Le_quad - .quad .Ld9,.Le_quad - .quad .Ls10,.Le_byte - .quad .Ld10,.Le_byte -#ifdef FIX_ALIGNMENT - .quad .Ls11,.Lzero_rest - .quad .Ld11,.Lzero_rest -#endif - .quad .Le5,.Le_zero + .quad 1b,30b + .quad 2b,30b + .quad 3b,30b + .quad 4b,30b + .quad 5b,30b + .quad 6b,30b + .quad 7b,30b + .quad 8b,30b + .quad 9b,30b + .quad 10b,30b + .quad 11b,30b + .quad 12b,30b + .quad 13b,30b + .quad 14b,30b + .quad 15b,30b + .quad 16b,30b + .quad 18b,40b + .quad 19b,40b + .quad 21b,50b + .quad 22b,50b .previous - - /* eax: zero, ebx: 64 */ -.Ls1e: addl $8,%eax /* eax: bytes left uncopied: Ls1e: 64 .. Ls8e: 8 */ -.Ls2e: addl $8,%eax -.Ls3e: addl $8,%eax -.Ls4e: addl $8,%eax -.Ls5e: addl $8,%eax -.Ls6e: addl $8,%eax -.Ls7e: addl $8,%eax -.Ls8e: addl $8,%eax - addq %rbx,%rdi /* +64 */ - subq %rax,%rdi /* correct destination with computed offset */ - - shlq $6,%rdx /* loop counter * 64 (stride length) */ - addq %rax,%rdx /* add offset to loopcnt */ - andl $63,%ecx /* remaining bytes */ - addq %rcx,%rdx /* add them */ - jmp .Lzero_rest - - /* exception on quad word loop in tail handling */ - /* ecx: loopcnt/8, %edx: length, rdi: correct */ -.Le_quad: - shll $3,%ecx - andl $7,%edx - addl %ecx,%edx - /* edx: bytes to zero, rdi: dest, eax:zero */ -.Lzero_rest: - cmpl $0,(%rsp) /* zero flag set? */ - jz .Le_zero - movq %rdx,%rcx -.Le_byte: - xorl %eax,%eax -.Le5: rep - stosb - /* when there is another exception while zeroing the rest just return */ -.Le_zero: - movq %rdx,%rax - jmp .Lende CFI_ENDPROC ENDPROC(__copy_user_nocache) - - diff --git a/arch/x86/lib/delay_32.c b/arch/x86/lib/delay.c index ef691316f8b..f4568605d7d 100644 --- a/arch/x86/lib/delay_32.c +++ b/arch/x86/lib/delay.c @@ -29,7 +29,7 @@ /* simple loop based delay: */ static void delay_loop(unsigned long loops) { - __asm__ __volatile__( + asm volatile( " test %0,%0 \n" " jz 3f \n" " jmp 1f \n" @@ -38,9 +38,9 @@ static void delay_loop(unsigned long loops) "1: jmp 2f \n" ".align 16 \n" - "2: decl %0 \n" + "2: dec %0 \n" " jnz 2b \n" - "3: decl %0 \n" + "3: dec %0 \n" : /* we don't need output */ :"a" (loops) @@ -98,7 +98,7 @@ void use_tsc_delay(void) int __devinit read_current_timer(unsigned long *timer_val) { if (delay_fn == delay_tsc) { - rdtscl(*timer_val); + rdtscll(*timer_val); return 0; } return -1; @@ -108,31 +108,30 @@ void __delay(unsigned long loops) { delay_fn(loops); } +EXPORT_SYMBOL(__delay); inline void __const_udelay(unsigned long xloops) { int d0; xloops *= 4; - __asm__("mull %0" + asm("mull %%edx" :"=d" (xloops), "=&a" (d0) :"1" (xloops), "0" (cpu_data(raw_smp_processor_id()).loops_per_jiffy * (HZ/4))); __delay(++xloops); } +EXPORT_SYMBOL(__const_udelay); void __udelay(unsigned long usecs) { __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ } +EXPORT_SYMBOL(__udelay); void __ndelay(unsigned long nsecs) { __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ } - -EXPORT_SYMBOL(__delay); -EXPORT_SYMBOL(__const_udelay); -EXPORT_SYMBOL(__udelay); EXPORT_SYMBOL(__ndelay); diff --git a/arch/x86/lib/delay_64.c b/arch/x86/lib/delay_64.c deleted file mode 100644 index 4c441be9264..00000000000 --- a/arch/x86/lib/delay_64.c +++ /dev/null @@ -1,85 +0,0 @@ -/* - * Precise Delay Loops for x86-64 - * - * Copyright (C) 1993 Linus Torvalds - * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz> - * - * The __delay function must _NOT_ be inlined as its execution time - * depends wildly on alignment on many x86 processors. - */ - -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/timex.h> -#include <linux/preempt.h> -#include <linux/delay.h> -#include <linux/init.h> - -#include <asm/delay.h> -#include <asm/msr.h> - -#ifdef CONFIG_SMP -#include <asm/smp.h> -#endif - -int __devinit read_current_timer(unsigned long *timer_value) -{ - rdtscll(*timer_value); - return 0; -} - -void __delay(unsigned long loops) -{ - unsigned bclock, now; - int cpu; - - preempt_disable(); - cpu = smp_processor_id(); - rdtscl(bclock); - for (;;) { - rdtscl(now); - if ((now - bclock) >= loops) - break; - - /* Allow RT tasks to run */ - preempt_enable(); - rep_nop(); - preempt_disable(); - - /* - * It is possible that we moved to another CPU, and - * since TSC's are per-cpu we need to calculate - * that. The delay must guarantee that we wait "at - * least" the amount of time. Being moved to another - * CPU could make the wait longer but we just need to - * make sure we waited long enough. Rebalance the - * counter for this CPU. - */ - if (unlikely(cpu != smp_processor_id())) { - loops -= (now - bclock); - cpu = smp_processor_id(); - rdtscl(bclock); - } - } - preempt_enable(); -} -EXPORT_SYMBOL(__delay); - -inline void __const_udelay(unsigned long xloops) -{ - __delay(((xloops * HZ * - cpu_data(raw_smp_processor_id()).loops_per_jiffy) >> 32) + 1); -} -EXPORT_SYMBOL(__const_udelay); - -void __udelay(unsigned long usecs) -{ - __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ -} -EXPORT_SYMBOL(__udelay); - -void __ndelay(unsigned long nsecs) -{ - __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ -} -EXPORT_SYMBOL(__ndelay); diff --git a/arch/x86/lib/getuser_64.S b/arch/x86/lib/getuser.S index 5448876261f..ad374003742 100644 --- a/arch/x86/lib/getuser_64.S +++ b/arch/x86/lib/getuser.S @@ -3,6 +3,7 @@ * * (C) Copyright 1998 Linus Torvalds * (C) Copyright 2005 Andi Kleen + * (C) Copyright 2008 Glauber Costa * * These functions have a non-standard call interface * to make them more efficient, especially as they @@ -13,14 +14,13 @@ /* * __get_user_X * - * Inputs: %rcx contains the address. + * Inputs: %[r|e]ax contains the address. * The register is modified, but all changes are undone * before returning because the C code doesn't know about it. * - * Outputs: %rax is error code (0 or -EFAULT) - * %rdx contains zero-extended value - * - * %r8 is destroyed. + * Outputs: %[r|e]ax is error code (0 or -EFAULT) + * %[r|e]dx contains zero-extended value + * * * These functions should not modify any other registers, * as they get called from within inline assembly. @@ -32,78 +32,73 @@ #include <asm/errno.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> +#include <asm/asm.h> .text ENTRY(__get_user_1) CFI_STARTPROC - GET_THREAD_INFO(%r8) - cmpq threadinfo_addr_limit(%r8),%rcx + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user -1: movzb (%rcx),%edx - xorl %eax,%eax +1: movzb (%_ASM_AX),%edx + xor %eax,%eax ret CFI_ENDPROC ENDPROC(__get_user_1) ENTRY(__get_user_2) CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $1,%rcx - jc 20f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 20f - decq %rcx -2: movzwl (%rcx),%edx - xorl %eax,%eax + add $1,%_ASM_AX + jc bad_get_user + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX + jae bad_get_user +2: movzwl -1(%_ASM_AX),%edx + xor %eax,%eax ret -20: decq %rcx - jmp bad_get_user CFI_ENDPROC ENDPROC(__get_user_2) ENTRY(__get_user_4) CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $3,%rcx - jc 30f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 30f - subq $3,%rcx -3: movl (%rcx),%edx - xorl %eax,%eax + add $3,%_ASM_AX + jc bad_get_user + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX + jae bad_get_user +3: mov -3(%_ASM_AX),%edx + xor %eax,%eax ret -30: subq $3,%rcx - jmp bad_get_user CFI_ENDPROC ENDPROC(__get_user_4) +#ifdef CONFIG_X86_64 ENTRY(__get_user_8) CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $7,%rcx - jc 40f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 40f - subq $7,%rcx -4: movq (%rcx),%rdx - xorl %eax,%eax + add $7,%_ASM_AX + jc bad_get_user + GET_THREAD_INFO(%_ASM_DX) + cmp TI_addr_limit(%_ASM_DX),%_ASM_AX + jae bad_get_user +4: movq -7(%_ASM_AX),%_ASM_DX + xor %eax,%eax ret -40: subq $7,%rcx - jmp bad_get_user CFI_ENDPROC ENDPROC(__get_user_8) +#endif bad_get_user: CFI_STARTPROC - xorl %edx,%edx - movq $(-EFAULT),%rax + xor %edx,%edx + mov $(-EFAULT),%_ASM_AX ret CFI_ENDPROC END(bad_get_user) .section __ex_table,"a" - .quad 1b,bad_get_user - .quad 2b,bad_get_user - .quad 3b,bad_get_user - .quad 4b,bad_get_user -.previous + _ASM_PTR 1b,bad_get_user + _ASM_PTR 2b,bad_get_user + _ASM_PTR 3b,bad_get_user +#ifdef CONFIG_X86_64 + _ASM_PTR 4b,bad_get_user +#endif diff --git a/arch/x86/lib/getuser_32.S b/arch/x86/lib/getuser_32.S deleted file mode 100644 index 6d84b53f12a..00000000000 --- a/arch/x86/lib/getuser_32.S +++ /dev/null @@ -1,78 +0,0 @@ -/* - * __get_user functions. - * - * (C) Copyright 1998 Linus Torvalds - * - * These functions have a non-standard call interface - * to make them more efficient, especially as they - * return an error value in addition to the "real" - * return value. - */ -#include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/thread_info.h> - - -/* - * __get_user_X - * - * Inputs: %eax contains the address - * - * Outputs: %eax is error code (0 or -EFAULT) - * %edx contains zero-extended value - * - * These functions should not modify any other registers, - * as they get called from within inline assembly. - */ - -.text -ENTRY(__get_user_1) - CFI_STARTPROC - GET_THREAD_INFO(%edx) - cmpl TI_addr_limit(%edx),%eax - jae bad_get_user -1: movzbl (%eax),%edx - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__get_user_1) - -ENTRY(__get_user_2) - CFI_STARTPROC - addl $1,%eax - jc bad_get_user - GET_THREAD_INFO(%edx) - cmpl TI_addr_limit(%edx),%eax - jae bad_get_user -2: movzwl -1(%eax),%edx - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__get_user_2) - -ENTRY(__get_user_4) - CFI_STARTPROC - addl $3,%eax - jc bad_get_user - GET_THREAD_INFO(%edx) - cmpl TI_addr_limit(%edx),%eax - jae bad_get_user -3: movl -3(%eax),%edx - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__get_user_4) - -bad_get_user: - CFI_STARTPROC - xorl %edx,%edx - movl $-14,%eax - ret - CFI_ENDPROC -END(bad_get_user) - -.section __ex_table,"a" - .long 1b,bad_get_user - .long 2b,bad_get_user - .long 3b,bad_get_user -.previous diff --git a/arch/x86/lib/putuser_32.S b/arch/x86/lib/putuser.S index f58fba109d1..36b0d15ae6e 100644 --- a/arch/x86/lib/putuser_32.S +++ b/arch/x86/lib/putuser.S @@ -2,6 +2,8 @@ * __put_user functions. * * (C) Copyright 2005 Linus Torvalds + * (C) Copyright 2005 Andi Kleen + * (C) Copyright 2008 Glauber Costa * * These functions have a non-standard call interface * to make them more efficient, especially as they @@ -11,6 +13,8 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/thread_info.h> +#include <asm/errno.h> +#include <asm/asm.h> /* @@ -26,73 +30,68 @@ */ #define ENTER CFI_STARTPROC ; \ - pushl %ebx ; \ - CFI_ADJUST_CFA_OFFSET 4 ; \ - CFI_REL_OFFSET ebx, 0 ; \ - GET_THREAD_INFO(%ebx) -#define EXIT popl %ebx ; \ - CFI_ADJUST_CFA_OFFSET -4 ; \ - CFI_RESTORE ebx ; \ - ret ; \ + GET_THREAD_INFO(%_ASM_BX) +#define EXIT ret ; \ CFI_ENDPROC .text ENTRY(__put_user_1) ENTER - cmpl TI_addr_limit(%ebx),%ecx + cmp TI_addr_limit(%_ASM_BX),%_ASM_CX jae bad_put_user -1: movb %al,(%ecx) - xorl %eax,%eax +1: movb %al,(%_ASM_CX) + xor %eax,%eax EXIT ENDPROC(__put_user_1) ENTRY(__put_user_2) ENTER - movl TI_addr_limit(%ebx),%ebx - subl $1,%ebx - cmpl %ebx,%ecx + mov TI_addr_limit(%_ASM_BX),%_ASM_BX + sub $1,%_ASM_BX + cmp %_ASM_BX,%_ASM_CX jae bad_put_user -2: movw %ax,(%ecx) - xorl %eax,%eax +2: movw %ax,(%_ASM_CX) + xor %eax,%eax EXIT ENDPROC(__put_user_2) ENTRY(__put_user_4) ENTER - movl TI_addr_limit(%ebx),%ebx - subl $3,%ebx - cmpl %ebx,%ecx + mov TI_addr_limit(%_ASM_BX),%_ASM_BX + sub $3,%_ASM_BX + cmp %_ASM_BX,%_ASM_CX jae bad_put_user -3: movl %eax,(%ecx) - xorl %eax,%eax +3: movl %eax,(%_ASM_CX) + xor %eax,%eax EXIT ENDPROC(__put_user_4) ENTRY(__put_user_8) ENTER - movl TI_addr_limit(%ebx),%ebx - subl $7,%ebx - cmpl %ebx,%ecx + mov TI_addr_limit(%_ASM_BX),%_ASM_BX + sub $7,%_ASM_BX + cmp %_ASM_BX,%_ASM_CX jae bad_put_user -4: movl %eax,(%ecx) -5: movl %edx,4(%ecx) - xorl %eax,%eax +4: mov %_ASM_AX,(%_ASM_CX) +#ifdef CONFIG_X86_32 +5: movl %edx,4(%_ASM_CX) +#endif + xor %eax,%eax EXIT ENDPROC(__put_user_8) bad_put_user: - CFI_STARTPROC simple - CFI_DEF_CFA esp, 2*4 - CFI_OFFSET eip, -1*4 - CFI_OFFSET ebx, -2*4 - movl $-14,%eax + CFI_STARTPROC + movl $-EFAULT,%eax EXIT END(bad_put_user) .section __ex_table,"a" - .long 1b,bad_put_user - .long 2b,bad_put_user - .long 3b,bad_put_user - .long 4b,bad_put_user - .long 5b,bad_put_user + _ASM_PTR 1b,bad_put_user + _ASM_PTR 2b,bad_put_user + _ASM_PTR 3b,bad_put_user + _ASM_PTR 4b,bad_put_user +#ifdef CONFIG_X86_32 + _ASM_PTR 5b,bad_put_user +#endif .previous diff --git a/arch/x86/lib/putuser_64.S b/arch/x86/lib/putuser_64.S deleted file mode 100644 index 4989f5a8fa9..00000000000 --- a/arch/x86/lib/putuser_64.S +++ /dev/null @@ -1,106 +0,0 @@ -/* - * __put_user functions. - * - * (C) Copyright 1998 Linus Torvalds - * (C) Copyright 2005 Andi Kleen - * - * These functions have a non-standard call interface - * to make them more efficient, especially as they - * return an error value in addition to the "real" - * return value. - */ - -/* - * __put_user_X - * - * Inputs: %rcx contains the address - * %rdx contains new value - * - * Outputs: %rax is error code (0 or -EFAULT) - * - * %r8 is destroyed. - * - * These functions should not modify any other registers, - * as they get called from within inline assembly. - */ - -#include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/page.h> -#include <asm/errno.h> -#include <asm/asm-offsets.h> -#include <asm/thread_info.h> - - .text -ENTRY(__put_user_1) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - cmpq threadinfo_addr_limit(%r8),%rcx - jae bad_put_user -1: movb %dl,(%rcx) - xorl %eax,%eax - ret - CFI_ENDPROC -ENDPROC(__put_user_1) - -ENTRY(__put_user_2) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $1,%rcx - jc 20f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 20f - decq %rcx -2: movw %dx,(%rcx) - xorl %eax,%eax - ret -20: decq %rcx - jmp bad_put_user - CFI_ENDPROC -ENDPROC(__put_user_2) - -ENTRY(__put_user_4) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $3,%rcx - jc 30f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 30f - subq $3,%rcx -3: movl %edx,(%rcx) - xorl %eax,%eax - ret -30: subq $3,%rcx - jmp bad_put_user - CFI_ENDPROC -ENDPROC(__put_user_4) - -ENTRY(__put_user_8) - CFI_STARTPROC - GET_THREAD_INFO(%r8) - addq $7,%rcx - jc 40f - cmpq threadinfo_addr_limit(%r8),%rcx - jae 40f - subq $7,%rcx -4: movq %rdx,(%rcx) - xorl %eax,%eax - ret -40: subq $7,%rcx - jmp bad_put_user - CFI_ENDPROC -ENDPROC(__put_user_8) - -bad_put_user: - CFI_STARTPROC - movq $(-EFAULT),%rax - ret - CFI_ENDPROC -END(bad_put_user) - -.section __ex_table,"a" - .quad 1b,bad_put_user - .quad 2b,bad_put_user - .quad 3b,bad_put_user - .quad 4b,bad_put_user -.previous diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0c89d1bb028..f4df6e7c718 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -158,3 +158,26 @@ unsigned long copy_in_user(void __user *to, const void __user *from, unsigned le } EXPORT_SYMBOL(copy_in_user); +/* + * Try to copy last bytes and clear the rest if needed. + * Since protection fault in copy_from/to_user is not a normal situation, + * it is not necessary to optimize tail handling. + */ +unsigned long +copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) +{ + char c; + unsigned zero_len; + + for (; len; --len) { + if (__get_user_nocheck(c, from++, sizeof(char))) + break; + if (__put_user_nocheck(c, to++, sizeof(char))) + break; + } + + for (c = 0, zero_len = len; zerorest && zero_len; --zero_len) + if (__put_user_nocheck(c, to++, sizeof(char))) + break; + return len; +} diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 51f69b39b75..48548ef7ddf 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -302,11 +302,13 @@ static __meminit void unmap_low_page(void *adr) early_iounmap(adr, PAGE_SIZE); } -static void __meminit +static unsigned long __meminit phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end) { unsigned pages = 0; + unsigned long last_map_addr = end; int i; + pte_t *pte = pte_page + pte_index(addr); for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) { @@ -326,17 +328,20 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end) printk(" pte=%p addr=%lx pte=%016lx\n", pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte); set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL)); + last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE; pages++; } update_page_count(PG_LEVEL_4K, pages); + + return last_map_addr; } -static void __meminit +static unsigned long __meminit phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end) { pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd); - phys_pte_init(pte, address, end); + return phys_pte_init(pte, address, end); } static unsigned long __meminit @@ -344,6 +349,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, unsigned long page_size_mask) { unsigned long pages = 0; + unsigned long last_map_addr = end; int i = pmd_index(address); @@ -362,7 +368,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, if (pmd_val(*pmd)) { if (!pmd_large(*pmd)) - phys_pte_update(pmd, address, end); + last_map_addr = phys_pte_update(pmd, address, + end); continue; } @@ -370,17 +377,18 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, pages++; set_pte((pte_t *)pmd, pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + last_map_addr = (address & PMD_MASK) + PMD_SIZE; continue; } pte = alloc_low_page(&pte_phys); - phys_pte_init(pte, address, end); + last_map_addr = phys_pte_init(pte, address, end); unmap_low_page(pte); pmd_populate_kernel(&init_mm, pmd, __va(pte_phys)); } update_page_count(PG_LEVEL_2M, pages); - return address; + return last_map_addr; } static unsigned long __meminit @@ -659,6 +667,32 @@ static unsigned long __init kernel_physical_mapping_init(unsigned long start, return last_map_addr; } + +struct map_range { + unsigned long start; + unsigned long end; + unsigned page_size_mask; +}; + +#define NR_RANGE_MR 5 + +static int save_mr(struct map_range *mr, int nr_range, + unsigned long start_pfn, unsigned long end_pfn, + unsigned long page_size_mask) +{ + + if (start_pfn < end_pfn) { + if (nr_range >= NR_RANGE_MR) + panic("run out of range for init_memory_mapping\n"); + mr[nr_range].start = start_pfn<<PAGE_SHIFT; + mr[nr_range].end = end_pfn<<PAGE_SHIFT; + mr[nr_range].page_size_mask = page_size_mask; + nr_range++; + } + + return nr_range; +} + /* * Setup the direct mapping of the physical memory at PAGE_OFFSET. * This runs before bootmem is initialized and gets pages directly from @@ -667,10 +701,13 @@ static unsigned long __init kernel_physical_mapping_init(unsigned long start, unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long end) { - unsigned long last_map_addr = end; + unsigned long last_map_addr = 0; unsigned long page_size_mask = 0; unsigned long start_pfn, end_pfn; + struct map_range mr[NR_RANGE_MR]; + int nr_range, i; + printk(KERN_INFO "init_memory_mapping\n"); /* @@ -680,24 +717,22 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, * memory mapped. Unfortunately this is done currently before the * nodes are discovered. */ - if (!after_bootmem) { + if (!after_bootmem) init_gbpages(); - find_early_table_space(end); - } if (direct_gbpages) page_size_mask |= 1 << PG_LEVEL_1G; if (cpu_has_pse) page_size_mask |= 1 << PG_LEVEL_2M; - /* head if not big page aligment ?*/ + memset(mr, 0, sizeof(mr)); + nr_range = 0; + + /* head if not big page alignment ?*/ start_pfn = start >> PAGE_SHIFT; end_pfn = ((start + (PMD_SIZE - 1)) >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) - last_map_addr = kernel_physical_mapping_init( - start_pfn<<PAGE_SHIFT, - end_pfn<<PAGE_SHIFT, 0); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); /* big page (2M) range*/ start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) @@ -706,37 +741,40 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, << (PUD_SHIFT - PAGE_SHIFT); if (end_pfn > ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT))) end_pfn = ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT)); - if (start_pfn < end_pfn) - last_map_addr = kernel_physical_mapping_init( - start_pfn<<PAGE_SHIFT, - end_pfn<<PAGE_SHIFT, - page_size_mask & (1<<PG_LEVEL_2M)); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); /* big page (1G) range */ start_pfn = end_pfn; end_pfn = (end>>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) - last_map_addr = kernel_physical_mapping_init( - start_pfn<<PAGE_SHIFT, - end_pfn<<PAGE_SHIFT, - page_size_mask & ((1<<PG_LEVEL_2M) - | (1<<PG_LEVEL_1G))); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & + ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); /* tail is not big page (1G) alignment */ start_pfn = end_pfn; end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - if (start_pfn < end_pfn) - last_map_addr = kernel_physical_mapping_init( - start_pfn<<PAGE_SHIFT, - end_pfn<<PAGE_SHIFT, - page_size_mask & (1<<PG_LEVEL_2M)); + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<<PG_LEVEL_2M)); + /* tail is not big page (2M) alignment */ start_pfn = end_pfn; end_pfn = end>>PAGE_SHIFT; - if (start_pfn < end_pfn) + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + + for (i = 0; i < nr_range; i++) + printk(KERN_DEBUG " %010lx - %010lx page %s\n", + mr[i].start, mr[i].end, + (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":( + (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k")); + + if (!after_bootmem) + find_early_table_space(end); + + for (i = 0; i < nr_range; i++) last_map_addr = kernel_physical_mapping_init( - start_pfn<<PAGE_SHIFT, - end_pfn<<PAGE_SHIFT, 0); + mr[i].start, mr[i].end, + mr[i].page_size_mask); if (!after_bootmem) mmu_cr4_features = read_cr4(); diff --git a/include/asm-x86/asm.h b/include/asm-x86/asm.h index 70939820c55..97220321f39 100644 --- a/include/asm-x86/asm.h +++ b/include/asm-x86/asm.h @@ -3,8 +3,10 @@ #ifdef __ASSEMBLY__ # define __ASM_FORM(x) x +# define __ASM_EX_SEC .section __ex_table #else # define __ASM_FORM(x) " " #x " " +# define __ASM_EX_SEC " .section __ex_table,\"a\"\n" #endif #ifdef CONFIG_X86_32 @@ -14,6 +16,7 @@ #endif #define __ASM_SIZE(inst) __ASM_SEL(inst##l, inst##q) +#define __ASM_REG(reg) __ASM_SEL(e##reg, r##reg) #define _ASM_PTR __ASM_SEL(.long, .quad) #define _ASM_ALIGN __ASM_SEL(.balign 4, .balign 8) @@ -24,10 +27,14 @@ #define _ASM_ADD __ASM_SIZE(add) #define _ASM_SUB __ASM_SIZE(sub) #define _ASM_XADD __ASM_SIZE(xadd) +#define _ASM_AX __ASM_REG(ax) +#define _ASM_BX __ASM_REG(bx) +#define _ASM_CX __ASM_REG(cx) +#define _ASM_DX __ASM_REG(dx) /* Exception table entry */ # define _ASM_EXTABLE(from,to) \ - " .section __ex_table,\"a\"\n" \ + __ASM_EX_SEC \ _ASM_ALIGN "\n" \ _ASM_PTR #from "," #to "\n" \ " .previous\n" diff --git a/include/asm-x86/delay.h b/include/asm-x86/delay.h index bb80880c834..409a649204a 100644 --- a/include/asm-x86/delay.h +++ b/include/asm-x86/delay.h @@ -26,10 +26,6 @@ extern void __delay(unsigned long loops); ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \ __ndelay(n)) -#ifdef CONFIG_X86_32 void use_tsc_delay(void); -#else -#define use_tsc_delay() {} -#endif #endif /* _ASM_X86_DELAY_H */ diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h index 1a0b61eb02f..6a4789d57e6 100644 --- a/include/asm-x86/fixmap_64.h +++ b/include/asm-x86/fixmap_64.h @@ -12,6 +12,7 @@ #define _ASM_FIXMAP_64_H #include <linux/kernel.h> +#include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> #include <asm/vsyscall.h> @@ -49,6 +50,10 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif +#ifdef CONFIG_ACPI + FIX_ACPI_BEGIN, + FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1, +#endif #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT FIX_OHCI1394_BASE, #endif diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h index 417f76ea677..33b9aeeb35a 100644 --- a/include/asm-x86/gart.h +++ b/include/asm-x86/gart.h @@ -1,40 +1,14 @@ -#ifndef _ASM_X8664_IOMMU_H -#define _ASM_X8664_IOMMU_H 1 +#ifndef _ASM_X8664_GART_H +#define _ASM_X8664_GART_H 1 #include <asm/e820.h> +#include <asm/iommu.h> -extern void pci_iommu_shutdown(void); -extern void no_iommu_init(void); -extern int force_iommu, no_iommu; -extern int iommu_detected; -extern int agp_amd64_init(void); -#ifdef CONFIG_GART_IOMMU -extern void gart_iommu_init(void); -extern void gart_iommu_shutdown(void); -extern void __init gart_parse_options(char *); -extern void early_gart_iommu_check(void); -extern void gart_iommu_hole_init(void); extern void set_up_gart_resume(u32, u32); + extern int fallback_aper_order; extern int fallback_aper_force; -extern int gart_iommu_aperture; -extern int gart_iommu_aperture_allowed; -extern int gart_iommu_aperture_disabled; extern int fix_aperture; -#else -#define gart_iommu_aperture 0 -#define gart_iommu_aperture_allowed 0 -#define gart_iommu_aperture_disabled 1 - -static inline void early_gart_iommu_check(void) -{ -} - -static inline void gart_iommu_shutdown(void) -{ -} - -#endif /* PTE bits. */ #define GPTE_VALID 1 diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h index 8d4c8bdb906..33a73f5ed22 100644 --- a/include/asm-x86/genapic_32.h +++ b/include/asm-x86/genapic_32.h @@ -119,6 +119,10 @@ enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; #define is_uv_system() 0 #define uv_wakeup_secondary(a, b) 1 +#ifdef CONFIG_X86_IO_APIC extern void force_mask_ioapic_irq_2(void); +#else +static inline void force_mask_ioapic_irq_2(void) { } +#endif #endif diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h index 082ad020e41..647e4e5c258 100644 --- a/include/asm-x86/genapic_64.h +++ b/include/asm-x86/genapic_64.h @@ -46,6 +46,10 @@ extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip); extern void setup_apic_routing(void); +#ifdef CONFIG_X86_IO_APIC extern void force_mask_ioapic_irq_2(void); +#else +static inline void force_mask_ioapic_irq_2(void) { } +#endif #endif diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h index 07862fdd23c..068c9a40aa5 100644 --- a/include/asm-x86/iommu.h +++ b/include/asm-x86/iommu.h @@ -1,29 +1,34 @@ -#ifndef _ASM_X8664_GART_H -#define _ASM_X8664_GART_H 1 +#ifndef _ASM_X8664_IOMMU_H +#define _ASM_X8664_IOMMU_H 1 extern void pci_iommu_shutdown(void); extern void no_iommu_init(void); extern int force_iommu, no_iommu; extern int iommu_detected; -#ifdef CONFIG_IOMMU + +#ifdef CONFIG_GART_IOMMU +extern int gart_iommu_aperture; +extern int gart_iommu_aperture_allowed; +extern int gart_iommu_aperture_disabled; + +extern void early_gart_iommu_check(void); extern void gart_iommu_init(void); extern void gart_iommu_shutdown(void); extern void __init gart_parse_options(char *); -extern void iommu_hole_init(void); -extern int fallback_aper_order; -extern int fallback_aper_force; -extern int iommu_aperture; -extern int iommu_aperture_allowed; -extern int iommu_aperture_disabled; -extern int fix_aperture; +extern void gart_iommu_hole_init(void); + #else -#define iommu_aperture 0 -#define iommu_aperture_allowed 0 +#define gart_iommu_aperture 0 +#define gart_iommu_aperture_allowed 0 +#define gart_iommu_aperture_disabled 1 -static inline void gart_iommu_shutdown(void) +static inline void early_gart_iommu_check(void) { } +static inline void gart_iommu_shutdown(void) +{ +} #endif #endif diff --git a/include/asm-x86/uaccess.h b/include/asm-x86/uaccess.h index 9fefd2947e7..f6fa4d841bb 100644 --- a/include/asm-x86/uaccess.h +++ b/include/asm-x86/uaccess.h @@ -1,5 +1,453 @@ +#ifndef _ASM_UACCES_H_ +#define _ASM_UACCES_H_ +/* + * User space memory access functions + */ +#include <linux/errno.h> +#include <linux/compiler.h> +#include <linux/thread_info.h> +#include <linux/prefetch.h> +#include <linux/string.h> +#include <asm/asm.h> +#include <asm/page.h> + +#define VERIFY_READ 0 +#define VERIFY_WRITE 1 + +/* + * The fs value determines whether argument validity checking should be + * performed or not. If get_fs() == USER_DS, checking is performed, with + * get_fs() == KERNEL_DS, checking is bypassed. + * + * For historical reasons, these macros are grossly misnamed. + */ + +#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) + +#define KERNEL_DS MAKE_MM_SEG(-1UL) +#define USER_DS MAKE_MM_SEG(PAGE_OFFSET) + +#define get_ds() (KERNEL_DS) +#define get_fs() (current_thread_info()->addr_limit) +#define set_fs(x) (current_thread_info()->addr_limit = (x)) + +#define segment_eq(a, b) ((a).seg == (b).seg) + +#define __addr_ok(addr) \ + ((unsigned long __force)(addr) < \ + (current_thread_info()->addr_limit.seg)) + +/* + * Test whether a block of memory is a valid user space address. + * Returns 0 if the range is valid, nonzero otherwise. + * + * This is equivalent to the following test: + * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64) + * + * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry... + */ + +#define __range_not_ok(addr, size) \ +({ \ + unsigned long flag, roksum; \ + __chk_user_ptr(addr); \ + asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \ + : "=&r" (flag), "=r" (roksum) \ + : "1" (addr), "g" ((long)(size)), \ + "rm" (current_thread_info()->addr_limit.seg)); \ + flag; \ +}) + +/** + * access_ok: - Checks if a user space pointer is valid + * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that + * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe + * to write to a block, it is always safe to read from it. + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * + * Context: User context only. This function may sleep. + * + * Checks if a pointer to a block of memory in user space is valid. + * + * Returns true (nonzero) if the memory block may be valid, false (zero) + * if it is definitely invalid. + * + * Note that, depending on architecture, this function probably just + * checks that the pointer is in the user space range - after calling + * this function, memory access functions may still return -EFAULT. + */ +#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0)) + +/* + * The exception table consists of pairs of addresses: the first is the + * address of an instruction that is allowed to fault, and the second is + * the address at which the program should continue. No registers are + * modified, so it is entirely up to the continuation code to figure out + * what to do. + * + * All the routines below use bits of fixup code that are out of line + * with the main instruction path. This means when everything is well, + * we don't even have to jump over them. Further, they do not intrude + * on our cache or tlb entries. + */ + +struct exception_table_entry { + unsigned long insn, fixup; +}; + +extern int fixup_exception(struct pt_regs *regs); + +/* + * These are the main single-value transfer routines. They automatically + * use the right size if we just have the right pointer type. + * + * This gets kind of ugly. We want to return _two_ values in "get_user()" + * and yet we don't want to do any pointers, because that is too much + * of a performance impact. Thus we have a few rather ugly macros here, + * and hide all the ugliness from the user. + * + * The "__xxx" versions of the user access functions are versions that + * do not verify the address space, that must have been done previously + * with a separate "access_ok()" call (this is used when we do multiple + * accesses to the same area of user memory). + */ + +extern int __get_user_1(void); +extern int __get_user_2(void); +extern int __get_user_4(void); +extern int __get_user_8(void); +extern int __get_user_bad(void); + +#define __get_user_x(size, ret, x, ptr) \ + asm volatile("call __get_user_" #size \ + : "=a" (ret),"=d" (x) \ + : "0" (ptr)) \ + +/* Careful: we have to cast the result to the type of the pointer + * for sign reasons */ + +/** + * get_user: - Get a simple variable from user space. + * @x: Variable to store result. + * @ptr: Source address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and the result of + * dereferencing @ptr must be assignable to @x without a cast. + * + * Returns zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ +#ifdef CONFIG_X86_32 +#define __get_user_8(__ret_gu, __val_gu, ptr) \ + __get_user_x(X, __ret_gu, __val_gu, ptr) +#else +#define __get_user_8(__ret_gu, __val_gu, ptr) \ + __get_user_x(8, __ret_gu, __val_gu, ptr) +#endif + +#define get_user(x, ptr) \ +({ \ + int __ret_gu; \ + unsigned long __val_gu; \ + __chk_user_ptr(ptr); \ + switch (sizeof(*(ptr))) { \ + case 1: \ + __get_user_x(1, __ret_gu, __val_gu, ptr); \ + break; \ + case 2: \ + __get_user_x(2, __ret_gu, __val_gu, ptr); \ + break; \ + case 4: \ + __get_user_x(4, __ret_gu, __val_gu, ptr); \ + break; \ + case 8: \ + __get_user_8(__ret_gu, __val_gu, ptr); \ + break; \ + default: \ + __get_user_x(X, __ret_gu, __val_gu, ptr); \ + break; \ + } \ + (x) = (__typeof__(*(ptr)))__val_gu; \ + __ret_gu; \ +}) + +#define __put_user_x(size, x, ptr, __ret_pu) \ + asm volatile("call __put_user_" #size : "=a" (__ret_pu) \ + :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") + + + +#ifdef CONFIG_X86_32 +#define __put_user_u64(x, addr, err) \ + asm volatile("1: movl %%eax,0(%2)\n" \ + "2: movl %%edx,4(%2)\n" \ + "3:\n" \ + ".section .fixup,\"ax\"\n" \ + "4: movl %3,%0\n" \ + " jmp 3b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 4b) \ + _ASM_EXTABLE(2b, 4b) \ + : "=r" (err) \ + : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err)) + +#define __put_user_x8(x, ptr, __ret_pu) \ + asm volatile("call __put_user_8" : "=a" (__ret_pu) \ + : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") +#else +#define __put_user_u64(x, ptr, retval) \ + __put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT) +#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu) +#endif + +extern void __put_user_bad(void); + +/* + * Strange magic calling convention: pointer in %ecx, + * value in %eax(:%edx), return value in %eax. clobbers %rbx + */ +extern void __put_user_1(void); +extern void __put_user_2(void); +extern void __put_user_4(void); +extern void __put_user_8(void); + +#ifdef CONFIG_X86_WP_WORKS_OK + +/** + * put_user: - Write a simple value into user space. + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and @x must be assignable + * to the result of dereferencing @ptr. + * + * Returns zero on success, or -EFAULT on error. + */ +#define put_user(x, ptr) \ +({ \ + int __ret_pu; \ + __typeof__(*(ptr)) __pu_val; \ + __chk_user_ptr(ptr); \ + __pu_val = x; \ + switch (sizeof(*(ptr))) { \ + case 1: \ + __put_user_x(1, __pu_val, ptr, __ret_pu); \ + break; \ + case 2: \ + __put_user_x(2, __pu_val, ptr, __ret_pu); \ + break; \ + case 4: \ + __put_user_x(4, __pu_val, ptr, __ret_pu); \ + break; \ + case 8: \ + __put_user_x8(__pu_val, ptr, __ret_pu); \ + break; \ + default: \ + __put_user_x(X, __pu_val, ptr, __ret_pu); \ + break; \ + } \ + __ret_pu; \ +}) + +#define __put_user_size(x, ptr, size, retval, errret) \ +do { \ + retval = 0; \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: \ + __put_user_asm(x, ptr, retval, "b", "b", "iq", errret); \ + break; \ + case 2: \ + __put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \ + break; \ + case 4: \ + __put_user_asm(x, ptr, retval, "l", "k", "ir", errret);\ + break; \ + case 8: \ + __put_user_u64((__typeof__(*ptr))(x), ptr, retval); \ + break; \ + default: \ + __put_user_bad(); \ + } \ +} while (0) + +#else + +#define __put_user_size(x, ptr, size, retval, errret) \ +do { \ + __typeof__(*(ptr))__pus_tmp = x; \ + retval = 0; \ + \ + if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0)) \ + retval = errret; \ +} while (0) + +#define put_user(x, ptr) \ +({ \ + int __ret_pu; \ + __typeof__(*(ptr))__pus_tmp = x; \ + __ret_pu = 0; \ + if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, \ + sizeof(*(ptr))) != 0)) \ + __ret_pu = -EFAULT; \ + __ret_pu; \ +}) +#endif + +#ifdef CONFIG_X86_32 +#define __get_user_asm_u64(x, ptr, retval, errret) (x) = __get_user_bad() +#else +#define __get_user_asm_u64(x, ptr, retval, errret) \ + __get_user_asm(x, ptr, retval, "q", "", "=r", errret) +#endif + +#define __get_user_size(x, ptr, size, retval, errret) \ +do { \ + retval = 0; \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: \ + __get_user_asm(x, ptr, retval, "b", "b", "=q", errret); \ + break; \ + case 2: \ + __get_user_asm(x, ptr, retval, "w", "w", "=r", errret); \ + break; \ + case 4: \ + __get_user_asm(x, ptr, retval, "l", "k", "=r", errret); \ + break; \ + case 8: \ + __get_user_asm_u64(x, ptr, retval, errret); \ + break; \ + default: \ + (x) = __get_user_bad(); \ + } \ +} while (0) + +#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret) \ + asm volatile("1: mov"itype" %2,%"rtype"1\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: mov %3,%0\n" \ + " xor"itype" %"rtype"1,%"rtype"1\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "=r" (err), ltype(x) \ + : "m" (__m(addr)), "i" (errret), "0" (err)) + +#define __put_user_nocheck(x, ptr, size) \ +({ \ + long __pu_err; \ + __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \ + __pu_err; \ +}) + +#define __get_user_nocheck(x, ptr, size) \ +({ \ + long __gu_err; \ + unsigned long __gu_val; \ + __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ + __gu_err; \ +}) + +/* FIXME: this hack is definitely wrong -AK */ +struct __large_struct { unsigned long buf[100]; }; +#define __m(x) (*(struct __large_struct __user *)(x)) + +/* + * Tell gcc we read from memory instead of writing: this is because + * we do not write to any memory gcc knows about, so there are no + * aliasing issues. + */ +#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret) \ + asm volatile("1: mov"itype" %"rtype"1,%2\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: mov %3,%0\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "=r"(err) \ + : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err)) +/** + * __get_user: - Get a simple variable from user space, with less checking. + * @x: Variable to store result. + * @ptr: Source address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and the result of + * dereferencing @ptr must be assignable to @x without a cast. + * + * Caller must check the pointer with access_ok() before calling this + * function. + * + * Returns zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ + +#define __get_user(x, ptr) \ + __get_user_nocheck((x), (ptr), sizeof(*(ptr))) +/** + * __put_user: - Write a simple value into user space, with less checking. + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and @x must be assignable + * to the result of dereferencing @ptr. + * + * Caller must check the pointer with access_ok() before calling this + * function. + * + * Returns zero on success, or -EFAULT on error. + */ + +#define __put_user(x, ptr) \ + __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) + +#define __get_user_unaligned __get_user +#define __put_user_unaligned __put_user + +/* + * movsl can be slow when source and dest are not both 8-byte aligned + */ +#ifdef CONFIG_X86_INTEL_USERCOPY +extern struct movsl_mask { + int mask; +} ____cacheline_aligned_in_smp movsl_mask; +#endif + +#define ARCH_HAS_NOCACHE_UACCESS 1 + #ifdef CONFIG_X86_32 # include "uaccess_32.h" #else +# define ARCH_HAS_SEARCH_EXTABLE # include "uaccess_64.h" #endif + +#endif diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h index 8e7595c1f34..6fdef39a0bc 100644 --- a/include/asm-x86/uaccess_32.h +++ b/include/asm-x86/uaccess_32.h @@ -11,426 +11,6 @@ #include <asm/asm.h> #include <asm/page.h> -#define VERIFY_READ 0 -#define VERIFY_WRITE 1 - -/* - * The fs value determines whether argument validity checking should be - * performed or not. If get_fs() == USER_DS, checking is performed, with - * get_fs() == KERNEL_DS, checking is bypassed. - * - * For historical reasons, these macros are grossly misnamed. - */ - -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - - -#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFFUL) -#define USER_DS MAKE_MM_SEG(PAGE_OFFSET) - -#define get_ds() (KERNEL_DS) -#define get_fs() (current_thread_info()->addr_limit) -#define set_fs(x) (current_thread_info()->addr_limit = (x)) - -#define segment_eq(a, b) ((a).seg == (b).seg) - -/* - * movsl can be slow when source and dest are not both 8-byte aligned - */ -#ifdef CONFIG_X86_INTEL_USERCOPY -extern struct movsl_mask { - int mask; -} ____cacheline_aligned_in_smp movsl_mask; -#endif - -#define __addr_ok(addr) \ - ((unsigned long __force)(addr) < \ - (current_thread_info()->addr_limit.seg)) - -/* - * Test whether a block of memory is a valid user space address. - * Returns 0 if the range is valid, nonzero otherwise. - * - * This is equivalent to the following test: - * (u33)addr + (u33)size >= (u33)current->addr_limit.seg - * - * This needs 33-bit arithmetic. We have a carry... - */ -#define __range_ok(addr, size) \ -({ \ - unsigned long flag, roksum; \ - __chk_user_ptr(addr); \ - asm("addl %3,%1 ; sbbl %0,%0; cmpl %1,%4; sbbl $0,%0" \ - :"=&r" (flag), "=r" (roksum) \ - :"1" (addr), "g" ((int)(size)), \ - "rm" (current_thread_info()->addr_limit.seg)); \ - flag; \ -}) - -/** - * access_ok: - Checks if a user space pointer is valid - * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that - * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe - * to write to a block, it is always safe to read from it. - * @addr: User space pointer to start of block to check - * @size: Size of block to check - * - * Context: User context only. This function may sleep. - * - * Checks if a pointer to a block of memory in user space is valid. - * - * Returns true (nonzero) if the memory block may be valid, false (zero) - * if it is definitely invalid. - * - * Note that, depending on architecture, this function probably just - * checks that the pointer is in the user space range - after calling - * this function, memory access functions may still return -EFAULT. - */ -#define access_ok(type, addr, size) (likely(__range_ok(addr, size) == 0)) - -/* - * The exception table consists of pairs of addresses: the first is the - * address of an instruction that is allowed to fault, and the second is - * the address at which the program should continue. No registers are - * modified, so it is entirely up to the continuation code to figure out - * what to do. - * - * All the routines below use bits of fixup code that are out of line - * with the main instruction path. This means when everything is well, - * we don't even have to jump over them. Further, they do not intrude - * on our cache or tlb entries. - */ - -struct exception_table_entry { - unsigned long insn, fixup; -}; - -extern int fixup_exception(struct pt_regs *regs); - -/* - * These are the main single-value transfer routines. They automatically - * use the right size if we just have the right pointer type. - * - * This gets kind of ugly. We want to return _two_ values in "get_user()" - * and yet we don't want to do any pointers, because that is too much - * of a performance impact. Thus we have a few rather ugly macros here, - * and hide all the ugliness from the user. - * - * The "__xxx" versions of the user access functions are versions that - * do not verify the address space, that must have been done previously - * with a separate "access_ok()" call (this is used when we do multiple - * accesses to the same area of user memory). - */ - -extern void __get_user_1(void); -extern void __get_user_2(void); -extern void __get_user_4(void); - -#define __get_user_x(size, ret, x, ptr) \ - asm volatile("call __get_user_" #size \ - :"=a" (ret),"=d" (x) \ - :"0" (ptr)) - - -/* Careful: we have to cast the result to the type of the pointer - * for sign reasons */ - -/** - * get_user: - Get a simple variable from user space. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Returns zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ -#define get_user(x, ptr) \ -({ \ - int __ret_gu; \ - unsigned long __val_gu; \ - __chk_user_ptr(ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - __get_user_x(1, __ret_gu, __val_gu, ptr); \ - break; \ - case 2: \ - __get_user_x(2, __ret_gu, __val_gu, ptr); \ - break; \ - case 4: \ - __get_user_x(4, __ret_gu, __val_gu, ptr); \ - break; \ - default: \ - __get_user_x(X, __ret_gu, __val_gu, ptr); \ - break; \ - } \ - (x) = (__typeof__(*(ptr)))__val_gu; \ - __ret_gu; \ -}) - -extern void __put_user_bad(void); - -/* - * Strange magic calling convention: pointer in %ecx, - * value in %eax(:%edx), return value in %eax, no clobbers. - */ -extern void __put_user_1(void); -extern void __put_user_2(void); -extern void __put_user_4(void); -extern void __put_user_8(void); - -#define __put_user_1(x, ptr) \ - asm volatile("call __put_user_1" : "=a" (__ret_pu) \ - : "0" ((typeof(*(ptr)))(x)), "c" (ptr)) - -#define __put_user_2(x, ptr) \ - asm volatile("call __put_user_2" : "=a" (__ret_pu) \ - : "0" ((typeof(*(ptr)))(x)), "c" (ptr)) - -#define __put_user_4(x, ptr) \ - asm volatile("call __put_user_4" : "=a" (__ret_pu) \ - : "0" ((typeof(*(ptr)))(x)), "c" (ptr)) - -#define __put_user_8(x, ptr) \ - asm volatile("call __put_user_8" : "=a" (__ret_pu) \ - : "A" ((typeof(*(ptr)))(x)), "c" (ptr)) - -#define __put_user_X(x, ptr) \ - asm volatile("call __put_user_X" : "=a" (__ret_pu) \ - : "c" (ptr)) - -/** - * put_user: - Write a simple value into user space. - * @x: Value to copy to user space. - * @ptr: Destination address, in user space. - * - * Context: User context only. This function may sleep. - * - * This macro copies a single simple value from kernel space to user - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. - * - * Returns zero on success, or -EFAULT on error. - */ -#ifdef CONFIG_X86_WP_WORKS_OK - -#define put_user(x, ptr) \ -({ \ - int __ret_pu; \ - __typeof__(*(ptr)) __pu_val; \ - __chk_user_ptr(ptr); \ - __pu_val = x; \ - switch (sizeof(*(ptr))) { \ - case 1: \ - __put_user_1(__pu_val, ptr); \ - break; \ - case 2: \ - __put_user_2(__pu_val, ptr); \ - break; \ - case 4: \ - __put_user_4(__pu_val, ptr); \ - break; \ - case 8: \ - __put_user_8(__pu_val, ptr); \ - break; \ - default: \ - __put_user_X(__pu_val, ptr); \ - break; \ - } \ - __ret_pu; \ -}) - -#else -#define put_user(x, ptr) \ -({ \ - int __ret_pu; \ - __typeof__(*(ptr))__pus_tmp = x; \ - __ret_pu = 0; \ - if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, \ - sizeof(*(ptr))) != 0)) \ - __ret_pu = -EFAULT; \ - __ret_pu; \ -}) - - -#endif - -/** - * __get_user: - Get a simple variable from user space, with less checking. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Returns zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ -#define __get_user(x, ptr) \ - __get_user_nocheck((x), (ptr), sizeof(*(ptr))) - - -/** - * __put_user: - Write a simple value into user space, with less checking. - * @x: Value to copy to user space. - * @ptr: Destination address, in user space. - * - * Context: User context only. This function may sleep. - * - * This macro copies a single simple value from kernel space to user - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Returns zero on success, or -EFAULT on error. - */ -#define __put_user(x, ptr) \ - __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) - -#define __put_user_nocheck(x, ptr, size) \ -({ \ - long __pu_err; \ - __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \ - __pu_err; \ -}) - - -#define __put_user_u64(x, addr, err) \ - asm volatile("1: movl %%eax,0(%2)\n" \ - "2: movl %%edx,4(%2)\n" \ - "3:\n" \ - ".section .fixup,\"ax\"\n" \ - "4: movl %3,%0\n" \ - " jmp 3b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 4b) \ - _ASM_EXTABLE(2b, 4b) \ - : "=r" (err) \ - : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err)) - -#ifdef CONFIG_X86_WP_WORKS_OK - -#define __put_user_size(x, ptr, size, retval, errret) \ -do { \ - retval = 0; \ - __chk_user_ptr(ptr); \ - switch (size) { \ - case 1: \ - __put_user_asm(x, ptr, retval, "b", "b", "iq", errret); \ - break; \ - case 2: \ - __put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \ - break; \ - case 4: \ - __put_user_asm(x, ptr, retval, "l", "", "ir", errret); \ - break; \ - case 8: \ - __put_user_u64((__typeof__(*ptr))(x), ptr, retval); \ - break; \ - default: \ - __put_user_bad(); \ - } \ -} while (0) - -#else - -#define __put_user_size(x, ptr, size, retval, errret) \ -do { \ - __typeof__(*(ptr))__pus_tmp = x; \ - retval = 0; \ - \ - if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0)) \ - retval = errret; \ -} while (0) - -#endif -struct __large_struct { unsigned long buf[100]; }; -#define __m(x) (*(struct __large_struct __user *)(x)) - -/* - * Tell gcc we read from memory instead of writing: this is because - * we do not write to any memory gcc knows about, so there are no - * aliasing issues. - */ -#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile("1: mov"itype" %"rtype"1,%2\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl %3,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : "=r"(err) \ - : ltype (x), "m" (__m(addr)), "i" (errret), "0" (err)) - - -#define __get_user_nocheck(x, ptr, size) \ -({ \ - long __gu_err; \ - unsigned long __gu_val; \ - __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ - (x) = (__typeof__(*(ptr)))__gu_val; \ - __gu_err; \ -}) - -extern long __get_user_bad(void); - -#define __get_user_size(x, ptr, size, retval, errret) \ -do { \ - retval = 0; \ - __chk_user_ptr(ptr); \ - switch (size) { \ - case 1: \ - __get_user_asm(x, ptr, retval, "b", "b", "=q", errret); \ - break; \ - case 2: \ - __get_user_asm(x, ptr, retval, "w", "w", "=r", errret); \ - break; \ - case 4: \ - __get_user_asm(x, ptr, retval, "l", "", "=r", errret); \ - break; \ - default: \ - (x) = __get_user_bad(); \ - } \ -} while (0) - -#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile("1: mov"itype" %2,%"rtype"1\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl %3,%0\n" \ - " xor"itype" %"rtype"1,%"rtype"1\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : "=r" (err), ltype (x) \ - : "m" (__m(addr)), "i" (errret), "0" (err)) - - unsigned long __must_check __copy_to_user_ll (void __user *to, const void *from, unsigned long n); unsigned long __must_check __copy_from_user_ll @@ -576,8 +156,6 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) return __copy_from_user_ll(to, from, n); } -#define ARCH_HAS_NOCACHE_UACCESS - static __always_inline unsigned long __copy_from_user_nocache(void *to, const void __user *from, unsigned long n) { diff --git a/include/asm-x86/uaccess_64.h b/include/asm-x86/uaccess_64.h index b8a2f433990..515d4dce96b 100644 --- a/include/asm-x86/uaccess_64.h +++ b/include/asm-x86/uaccess_64.h @@ -9,265 +9,6 @@ #include <linux/prefetch.h> #include <asm/page.h> -#define VERIFY_READ 0 -#define VERIFY_WRITE 1 - -/* - * The fs value determines whether argument validity checking should be - * performed or not. If get_fs() == USER_DS, checking is performed, with - * get_fs() == KERNEL_DS, checking is bypassed. - * - * For historical reasons, these macros are grossly misnamed. - */ - -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - -#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFFFFFFFFFFUL) -#define USER_DS MAKE_MM_SEG(PAGE_OFFSET) - -#define get_ds() (KERNEL_DS) -#define get_fs() (current_thread_info()->addr_limit) -#define set_fs(x) (current_thread_info()->addr_limit = (x)) - -#define segment_eq(a, b) ((a).seg == (b).seg) - -#define __addr_ok(addr) (!((unsigned long)(addr) & \ - (current_thread_info()->addr_limit.seg))) - -/* - * Uhhuh, this needs 65-bit arithmetic. We have a carry.. - */ -#define __range_not_ok(addr, size) \ -({ \ - unsigned long flag, roksum; \ - __chk_user_ptr(addr); \ - asm("# range_ok\n\r" \ - "addq %3,%1 ; sbbq %0,%0 ; cmpq %1,%4 ; sbbq $0,%0" \ - : "=&r" (flag), "=r" (roksum) \ - : "1" (addr), "g" ((long)(size)), \ - "g" (current_thread_info()->addr_limit.seg)); \ - flag; \ -}) - -#define access_ok(type, addr, size) (__range_not_ok(addr, size) == 0) - -/* - * The exception table consists of pairs of addresses: the first is the - * address of an instruction that is allowed to fault, and the second is - * the address at which the program should continue. No registers are - * modified, so it is entirely up to the continuation code to figure out - * what to do. - * - * All the routines below use bits of fixup code that are out of line - * with the main instruction path. This means when everything is well, - * we don't even have to jump over them. Further, they do not intrude - * on our cache or tlb entries. - */ - -struct exception_table_entry { - unsigned long insn, fixup; -}; - -extern int fixup_exception(struct pt_regs *regs); - -#define ARCH_HAS_SEARCH_EXTABLE - -/* - * These are the main single-value transfer routines. They automatically - * use the right size if we just have the right pointer type. - * - * This gets kind of ugly. We want to return _two_ values in "get_user()" - * and yet we don't want to do any pointers, because that is too much - * of a performance impact. Thus we have a few rather ugly macros here, - * and hide all the ugliness from the user. - * - * The "__xxx" versions of the user access functions are versions that - * do not verify the address space, that must have been done previously - * with a separate "access_ok()" call (this is used when we do multiple - * accesses to the same area of user memory). - */ - -#define __get_user_x(size, ret, x, ptr) \ - asm volatile("call __get_user_" #size \ - : "=a" (ret),"=d" (x) \ - : "c" (ptr) \ - : "r8") - -/* Careful: we have to cast the result to the type of the pointer - * for sign reasons */ - -#define get_user(x, ptr) \ -({ \ - unsigned long __val_gu; \ - int __ret_gu; \ - __chk_user_ptr(ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - __get_user_x(1, __ret_gu, __val_gu, ptr); \ - break; \ - case 2: \ - __get_user_x(2, __ret_gu, __val_gu, ptr); \ - break; \ - case 4: \ - __get_user_x(4, __ret_gu, __val_gu, ptr); \ - break; \ - case 8: \ - __get_user_x(8, __ret_gu, __val_gu, ptr); \ - break; \ - default: \ - __get_user_bad(); \ - break; \ - } \ - (x) = (__force typeof(*(ptr)))__val_gu; \ - __ret_gu; \ -}) - -extern void __put_user_1(void); -extern void __put_user_2(void); -extern void __put_user_4(void); -extern void __put_user_8(void); -extern void __put_user_bad(void); - -#define __put_user_x(size, ret, x, ptr) \ - asm volatile("call __put_user_" #size \ - :"=a" (ret) \ - :"c" (ptr),"d" (x) \ - :"r8") - -#define put_user(x, ptr) \ - __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) - -#define __get_user(x, ptr) \ - __get_user_nocheck((x), (ptr), sizeof(*(ptr))) -#define __put_user(x, ptr) \ - __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) - -#define __get_user_unaligned __get_user -#define __put_user_unaligned __put_user - -#define __put_user_nocheck(x, ptr, size) \ -({ \ - int __pu_err; \ - __put_user_size((x), (ptr), (size), __pu_err); \ - __pu_err; \ -}) - - -#define __put_user_check(x, ptr, size) \ -({ \ - int __pu_err; \ - typeof(*(ptr)) __user *__pu_addr = (ptr); \ - switch (size) { \ - case 1: \ - __put_user_x(1, __pu_err, x, __pu_addr); \ - break; \ - case 2: \ - __put_user_x(2, __pu_err, x, __pu_addr); \ - break; \ - case 4: \ - __put_user_x(4, __pu_err, x, __pu_addr); \ - break; \ - case 8: \ - __put_user_x(8, __pu_err, x, __pu_addr); \ - break; \ - default: \ - __put_user_bad(); \ - } \ - __pu_err; \ -}) - -#define __put_user_size(x, ptr, size, retval) \ -do { \ - retval = 0; \ - __chk_user_ptr(ptr); \ - switch (size) { \ - case 1: \ - __put_user_asm(x, ptr, retval, "b", "b", "iq", -EFAULT);\ - break; \ - case 2: \ - __put_user_asm(x, ptr, retval, "w", "w", "ir", -EFAULT);\ - break; \ - case 4: \ - __put_user_asm(x, ptr, retval, "l", "k", "ir", -EFAULT);\ - break; \ - case 8: \ - __put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT); \ - break; \ - default: \ - __put_user_bad(); \ - } \ -} while (0) - -/* FIXME: this hack is definitely wrong -AK */ -struct __large_struct { unsigned long buf[100]; }; -#define __m(x) (*(struct __large_struct __user *)(x)) - -/* - * Tell gcc we read from memory instead of writing: this is because - * we do not write to any memory gcc knows about, so there are no - * aliasing issues. - */ -#define __put_user_asm(x, addr, err, itype, rtype, ltype, errno) \ - asm volatile("1: mov"itype" %"rtype"1,%2\n" \ - "2:\n" \ - ".section .fixup, \"ax\"\n" \ - "3: mov %3,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : "=r"(err) \ - : ltype (x), "m" (__m(addr)), "i" (errno), "0" (err)) - - -#define __get_user_nocheck(x, ptr, size) \ -({ \ - int __gu_err; \ - unsigned long __gu_val; \ - __get_user_size(__gu_val, (ptr), (size), __gu_err); \ - (x) = (__force typeof(*(ptr)))__gu_val; \ - __gu_err; \ -}) - -extern int __get_user_1(void); -extern int __get_user_2(void); -extern int __get_user_4(void); -extern int __get_user_8(void); -extern int __get_user_bad(void); - -#define __get_user_size(x, ptr, size, retval) \ -do { \ - retval = 0; \ - __chk_user_ptr(ptr); \ - switch (size) { \ - case 1: \ - __get_user_asm(x, ptr, retval, "b", "b", "=q", -EFAULT);\ - break; \ - case 2: \ - __get_user_asm(x, ptr, retval, "w", "w", "=r", -EFAULT);\ - break; \ - case 4: \ - __get_user_asm(x, ptr, retval, "l", "k", "=r", -EFAULT);\ - break; \ - case 8: \ - __get_user_asm(x, ptr, retval, "q", "", "=r", -EFAULT); \ - break; \ - default: \ - (x) = __get_user_bad(); \ - } \ -} while (0) - -#define __get_user_asm(x, addr, err, itype, rtype, ltype, errno) \ - asm volatile("1: mov"itype" %2,%"rtype"1\n" \ - "2:\n" \ - ".section .fixup, \"ax\"\n" \ - "3: mov %3,%0\n" \ - " xor"itype" %"rtype"1,%"rtype"1\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : "=r" (err), ltype (x) \ - : "m" (__m(addr)), "i"(errno), "0"(err)) - /* * Copy To/From Userspace */ @@ -437,7 +178,6 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size) return copy_user_generic((__force void *)dst, src, size); } -#define ARCH_HAS_NOCACHE_UACCESS 1 extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); @@ -455,4 +195,7 @@ static inline int __copy_from_user_inatomic_nocache(void *dst, return __copy_user_nocache(dst, src, size, 0); } +unsigned long +copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest); + #endif /* __X86_64_UACCESS_H */ |