diff options
Diffstat (limited to 'arch/x86/kernel')
35 files changed, 159 insertions, 175 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 76ec0f8f138..4eb5ce84110 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -6,7 +6,15 @@ extra-y := head_$(BITS).o init_task.o vmlinux.lds extra-$(CONFIG_X86_64) += head64.o CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) -CFLAGS_vsyscall_64.o := $(PROFILING) -g0 + +# +# vsyscalls (which work on the user stack) should have +# no stack-protector checks: +# +nostackp := $(call cc-option, -fno-stack-protector) +CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp) +CFLAGS_hpet.o := $(nostackp) +CFLAGS_tsc_64.o := $(nostackp) obj-y := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o obj-y += traps_$(BITS).o irq_$(BITS).o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 680b7300a48..2cdc9de9371 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -72,7 +72,8 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return #define PREFIX "ACPI: " int acpi_noirq; /* skip ACPI IRQ initialization */ -int acpi_pci_disabled __initdata; /* skip ACPI PCI scan and IRQ initialization */ +int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ +EXPORT_SYMBOL(acpi_pci_disabled); int acpi_ht __initdata = 1; /* enable HT */ int acpi_lapic; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index afd84463b71..8ea040124f7 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -20,10 +20,8 @@ #include <xen/interface/xen.h> -#ifdef CONFIG_LGUEST_GUEST #include <linux/lguest.h> #include "../../../drivers/lguest/lg.h" -#endif #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) @@ -130,10 +128,12 @@ void foo(void) OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); #endif -#ifdef CONFIG_LGUEST_GUEST +#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir); + + BLANK(); OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9b95edcfc6a..027e5c003b1 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -25,14 +25,6 @@ static int __init no_halt(char *s) __setup("no-hlt", no_halt); -static int __init mca_pentium(char *s) -{ - mca_pentium_flag = 1; - return 1; -} - -__setup("mca-pentium", mca_pentium); - static int __init no_387(char *s) { boot_cpu_data.hard_math = 0; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f86a3c4a266..a38aafaefc2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -504,7 +504,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Clear all flags overriden by options */ for (i = 0; i < NCAPINTS; i++) - c->x86_capability[i] ^= cleared_cpu_caps[i]; + c->x86_capability[i] &= ~cleared_cpu_caps[i]; /* Init Machine Check Exception if available. */ mcheck_init(c); diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index b6e136f23d3..be83336fddb 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -43,6 +43,7 @@ #include <asm/uaccess.h> #include <asm/processor.h> #include <asm/msr.h> +#include <asm/kvm_para.h> #include "mtrr.h" u32 num_var_ranges = 0; @@ -649,6 +650,7 @@ static __init int amd_special_default_mtrr(void) /** * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs + * @end_pfn: ending page frame number * * Some buggy BIOSes don't setup the MTRRs properly for systems with certain * memory configurations. This routine checks that the highest MTRR matches @@ -688,8 +690,11 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* kvm/qemu doesn't have mtrr set right, don't trim them all */ if (!highest_pfn) { - printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n"); - WARN_ON(1); + if (!kvm_para_available()) { + printk(KERN_WARNING + "WARNING: strange, CPU MTRRs all blank?\n"); + WARN_ON(1); + } return 0; } diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 200fb3f9ebf..e8b422c1c51 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -76,13 +76,6 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) /* All Transmeta CPUs have a constant TSC */ set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability); - /* If we can run i686 user-space code, call us an i686 */ -#define USER686 ((1 << X86_FEATURE_TSC)|\ - (1 << X86_FEATURE_CX8)|\ - (1 << X86_FEATURE_CMOV)) - if (c->x86 == 5 && (c->x86_capability[0] & USER686) == USER686) - c->x86 = 6; - #ifdef CONFIG_SYSCTL /* randomize_va_space slows us down enormously; it probably triggers retranslation of x86->native bytecode */ diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index 0c0eeb163d9..759e02bec07 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -54,7 +54,7 @@ EXPORT_SYMBOL(efi); struct efi_memory_map memmap; -struct efi efi_phys __initdata; +static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; static int __init setup_noefi(char *arg) diff --git a/arch/x86/kernel/efi_32.c b/arch/x86/kernel/efi_32.c index cb91f985b4a..5d23d85624d 100644 --- a/arch/x86/kernel/efi_32.c +++ b/arch/x86/kernel/efi_32.c @@ -28,6 +28,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> +#include <asm/efi.h> /* * To make EFI call EFI runtime service in physical addressing mode we need diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 824e21b80aa..4b87c32b639 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -409,7 +409,7 @@ restore_nocheck_notrace: RESTORE_REGS addl $4, %esp # skip orig_eax/error_code CFI_ADJUST_CFA_OFFSET -4 -ENTRY(irq_return) +irq_return: INTERRUPT_RETURN .section .fixup,"ax" iret_exc: diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 6be39a387c5..c20c9e7e08d 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -453,6 +453,7 @@ ENTRY(stub_execve) CFI_REGISTER rip, r11 SAVE_REST FIXUP_TOP_OF_STACK %r11 + movq %rsp, %rcx call sys_execve RESTORE_TOP_OF_STACK %r11 movq %rax,RAX(%rsp) @@ -583,7 +584,7 @@ retint_restore_args: /* return to kernel space */ restore_args: RESTORE_ARGS 0,8,0 -ENTRY(irq_return) +irq_return: INTERRUPT_RETURN .section __ex_table, "a" @@ -1036,15 +1037,16 @@ ENDPROC(child_rip) * rdi: name, rsi: argv, rdx: envp * * We want to fallback into: - * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs) + * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs *regs) * * do_sys_execve asm fallback arguments: - * rdi: name, rsi: argv, rdx: envp, fake frame on the stack + * rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack */ ENTRY(kernel_execve) CFI_STARTPROC FAKE_STACK_FRAME $0 SAVE_ALL + movq %rsp,%rcx call sys_execve movq %rax, RAX(%rsp) RESTORE_REST diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 24dbf56928d..ad2440832de 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -88,6 +88,9 @@ void __init x86_64_start_kernel(char * real_mode_data) /* Make NULL pointers segfault */ zap_identity_mappings(); + /* Cleanup the over mapped high alias */ + cleanup_highmap(); + for (i = 0; i < IDT_ENTRIES; i++) { #ifdef CONFIG_EARLY_PRINTK set_intr_gate(i, &early_idt_handlers[i]); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 74ef4a41f22..fd8ca53943a 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -606,13 +606,13 @@ ENTRY(_stext) .section ".bss.page_aligned","wa" .align PAGE_SIZE_asm #ifdef CONFIG_X86_PAE -ENTRY(swapper_pg_pmd) +swapper_pg_pmd: .fill 1024*KPMDS,4,0 #else ENTRY(swapper_pg_dir) .fill 1024,4,0 #endif -ENTRY(swapper_pg_fixmap) +swapper_pg_fixmap: .fill 1024,4,0 ENTRY(empty_zero_page) .fill 4096,1,0 diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 09b38d539b0..a007454133a 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -107,8 +107,13 @@ startup_64: movq %rdx, 0(%rbx, %rax, 8) ident_complete: - /* Fixup the kernel text+data virtual addresses + /* + * Fixup the kernel text+data virtual addresses. Note that + * we might write invalid pmds, when the kernel is relocated + * cleanup_highmap() fixes this up along with the mappings + * beyond _end. */ + leaq level2_kernel_pgt(%rip), %rdi leaq 4096(%rdi), %r8 /* See if it is a valid page table entry */ @@ -250,7 +255,7 @@ ENTRY(secondary_startup_64) lretq /* SMP bootup changes these two */ - __CPUINITDATA + __REFDATA .align 8 ENTRY(initial_code) .quad x86_64_start_kernel @@ -374,18 +379,24 @@ NEXT_PAGE(level2_ident_pgt) /* Since I easily can, map the first 1G. * Don't set NX because code runs from these pages. */ - PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD) + PMDS(0, __PAGE_KERNEL_LARGE_EXEC, PTRS_PER_PMD) NEXT_PAGE(level2_kernel_pgt) - /* 40MB kernel mapping. The kernel code cannot be bigger than that. - When you change this change KERNEL_TEXT_SIZE in page.h too. */ - /* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */ - PMDS(0x0000000000000000, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, KERNEL_TEXT_SIZE/PMD_SIZE) - /* Module mapping starts here */ - .fill (PTRS_PER_PMD - (KERNEL_TEXT_SIZE/PMD_SIZE)),8,0 + /* + * 128 MB kernel mapping. We spend a full page on this pagetable + * anyway. + * + * The kernel code+data+bss must not be bigger than that. + * + * (NOTE: at +128MB starts the module area, see MODULES_VADDR. + * If you want to increase this then increase MODULES_VADDR + * too.) + */ + PMDS(0, __PAGE_KERNEL_LARGE_EXEC|_PAGE_GLOBAL, + KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_spare_pgt) - .fill 512,8,0 + .fill 512, 8, 0 #undef PMDS #undef NEXT_PAGE diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 429d084e014..235fd6c7750 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -368,8 +368,8 @@ static int hpet_clocksource_register(void) return 0; } -/* - * Try to setup the HPET timer +/** + * hpet_enable - Try to setup the HPET timer. Returns 1 on success. */ int __init hpet_enable(void) { diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 26719bd2c77..763dfc40723 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -39,7 +39,7 @@ #define HAVE_HWFP 1 #endif -unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; void mxcsr_feature_mask_init(void) { diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259_32.c index 2d25b77102f..fe631967d62 100644 --- a/arch/x86/kernel/i8259_32.c +++ b/arch/x86/kernel/i8259_32.c @@ -26,8 +26,6 @@ * present in the majority of PC/AT boxes. * plus some generic x86 specific things if generic specifics makes * any sense at all. - * this file should become arch/i386/kernel/irq.c when the old irq.c - * moves to arch independent land */ static int i8259A_auto_eoi; @@ -362,23 +360,12 @@ void __init init_ISA_irqs (void) #endif init_8259A(0); - for (i = 0; i < NR_IRQS; i++) { - irq_desc[i].status = IRQ_DISABLED; - irq_desc[i].action = NULL; - irq_desc[i].depth = 1; - - if (i < 16) { - /* - * 16 old-style INTA-cycle interrupts: - */ - set_irq_chip_and_handler_name(i, &i8259A_chip, - handle_level_irq, "XT"); - } else { - /* - * 'high' PCI IRQs filled in on demand - */ - irq_desc[i].chip = &no_irq_chip; - } + /* + * 16 old-style INTA-cycle interrupts: + */ + for (i = 0; i < 16; i++) { + set_irq_chip_and_handler_name(i, &i8259A_chip, + handle_level_irq, "XT"); } } diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c index 5b3ce793436..3d01e47777d 100644 --- a/arch/x86/kernel/init_task.c +++ b/arch/x86/kernel/init_task.c @@ -15,6 +15,7 @@ static struct files_struct init_files = INIT_FILES; static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); struct mm_struct init_mm = INIT_MM(init_mm); +EXPORT_UNUSED_SYMBOL(init_mm); /* will be removed in 2.6.26 */ /* * Initial thread structure. diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c index bd49321034d..c706a306155 100644 --- a/arch/x86/kernel/io_delay.c +++ b/arch/x86/kernel/io_delay.c @@ -13,7 +13,6 @@ #include <asm/io.h> int io_delay_type __read_mostly = CONFIG_DEFAULT_IO_DELAY_TYPE; -EXPORT_SYMBOL_GPL(io_delay_type); static int __initdata io_delay_override; diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index a99e764fd66..34a591283f5 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -581,7 +581,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. */ -void __kprobes kretprobe_trampoline_holder(void) +static void __used __kprobes kretprobe_trampoline_holder(void) { asm volatile ( ".global kretprobe_trampoline\n" @@ -673,7 +673,7 @@ void __kprobes kretprobe_trampoline_holder(void) /* * Called from kretprobe_trampoline */ -void * __kprobes trampoline_handler(struct pt_regs *regs) +static __used __kprobes void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c index edd413650b3..6a0aa703868 100644 --- a/arch/x86/kernel/nmi_32.c +++ b/arch/x86/kernel/nmi_32.c @@ -46,9 +46,6 @@ static unsigned int nmi_hz = HZ; static DEFINE_PER_CPU(short, wd_enabled); -/* local prototypes */ -static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu); - static int endflag __initdata = 0; #ifdef CONFIG_SMP @@ -391,15 +388,6 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) return rc; } -int do_nmi_callback(struct pt_regs * regs, int cpu) -{ -#ifdef CONFIG_SYSCTL - if (unknown_nmi_panic) - return unknown_nmi_panic_callback(regs, cpu); -#endif - return 0; -} - #ifdef CONFIG_SYSCTL static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) @@ -453,6 +441,15 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, #endif +int do_nmi_callback(struct pt_regs *regs, int cpu) +{ +#ifdef CONFIG_SYSCTL + if (unknown_nmi_panic) + return unknown_nmi_panic_callback(regs, cpu); +#endif + return 0; +} + void __trigger_all_cpu_backtrace(void) { int i; diff --git a/arch/x86/kernel/nmi_64.c b/arch/x86/kernel/nmi_64.c index fb99484d21c..9a4fde74bee 100644 --- a/arch/x86/kernel/nmi_64.c +++ b/arch/x86/kernel/nmi_64.c @@ -46,9 +46,6 @@ static unsigned int nmi_hz = HZ; static DEFINE_PER_CPU(short, wd_enabled); -/* local prototypes */ -static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu); - /* Run after command line and cpu_init init, but before all other checks */ void nmi_watchdog_default(void) { @@ -394,15 +391,6 @@ asmlinkage __kprobes void do_nmi(struct pt_regs * regs, long error_code) nmi_exit(); } -int do_nmi_callback(struct pt_regs * regs, int cpu) -{ -#ifdef CONFIG_SYSCTL - if (unknown_nmi_panic) - return unknown_nmi_panic_callback(regs, cpu); -#endif - return 0; -} - void stop_nmi(void) { acpi_nmi_disable(); @@ -464,6 +452,15 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, #endif +int do_nmi_callback(struct pt_regs *regs, int cpu) +{ +#ifdef CONFIG_SYSCTL + if (unknown_nmi_panic) + return unknown_nmi_panic_callback(regs, cpu); +#endif + return 0; +} + void __trigger_all_cpu_backtrace(void) { int i; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a7d50a547dc..be3c7a299f0 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -603,11 +603,13 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, } #endif +#ifdef X86_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS); if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES); +#endif if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b0cc8f0136d..3baf9b9f4c8 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -604,11 +604,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +#ifdef X86_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS); if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES); +#endif } /* @@ -730,16 +732,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ asmlinkage long sys_execve(char __user *name, char __user * __user *argv, - char __user * __user *envp, struct pt_regs regs) + char __user * __user *envp, struct pt_regs *regs) { long error; char * filename; filename = getname(name); error = PTR_ERR(filename); - if (IS_ERR(filename)) + if (IS_ERR(filename)) return error; - error = do_execve(filename, argv, envp, ®s); + error = do_execve(filename, argv, envp, regs); putname(filename); return error; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 702c33efea8..f41fdc98efb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -544,6 +544,8 @@ static int ptrace_set_debugreg(struct task_struct *child, return 0; } +#ifdef X86_BTS + static int ptrace_bts_get_size(struct task_struct *child) { if (!child->thread.ds_area_msr) @@ -826,6 +828,7 @@ void ptrace_bts_take_timestamp(struct task_struct *tsk, ptrace_bts_write_record(tsk, &rec); } +#endif /* X86_BTS */ /* * Called by kernel/ptrace.c when detaching.. @@ -839,7 +842,9 @@ void ptrace_disable(struct task_struct *child) clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); #endif if (child->thread.ds_area_msr) { +#ifdef X86_BTS ptrace_bts_realloc(child, 0, 0); +#endif child->thread.debugctlmsr &= ~ds_debugctl_mask(); if (!child->thread.debugctlmsr) clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR); @@ -961,6 +966,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; #endif + /* + * These bits need more cooking - not enabled yet: + */ +#ifdef X86_BTS case PTRACE_BTS_CONFIG: ret = ptrace_bts_config (child, data, (struct ptrace_bts_config __user *)addr); @@ -988,6 +997,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = ptrace_bts_drain (child, data, (struct bts_struct __user *) addr); break; +#endif default: ret = ptrace_request(child, request, addr, data); @@ -1160,7 +1170,7 @@ static int genregs32_set(struct task_struct *target, if (kbuf) { const compat_ulong_t *k = kbuf; while (count > 0 && !ret) { - ret = putreg(target, pos, *k++); + ret = putreg32(target, pos, *k++); count -= sizeof(*k); pos += sizeof(*k); } @@ -1171,7 +1181,7 @@ static int genregs32_set(struct task_struct *target, ret = __get_user(word, u++); if (ret) break; - ret = putreg(target, pos, word); + ret = putreg32(target, pos, word); count -= sizeof(*u); pos += sizeof(*u); } @@ -1226,12 +1236,14 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data) case PTRACE_SETOPTIONS: case PTRACE_SET_THREAD_AREA: case PTRACE_GET_THREAD_AREA: +#ifdef X86_BTS case PTRACE_BTS_CONFIG: case PTRACE_BTS_STATUS: case PTRACE_BTS_SIZE: case PTRACE_BTS_GET: case PTRACE_BTS_CLEAR: case PTRACE_BTS_DRAIN: +#endif return sys_ptrace(request, pid, addr, data); default: diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c index 691ab4cb167..a1d7071a51c 100644 --- a/arch/x86/kernel/setup_32.c +++ b/arch/x86/kernel/setup_32.c @@ -164,7 +164,6 @@ unsigned long mmu_cr4_features = X86_CR4_PAE; unsigned int machine_id; unsigned int machine_submodel_id; unsigned int BIOS_revision; -unsigned int mca_pentium_flag; /* Boot loader ID as an integer, for the benefit of proc_dointvec */ int bootloader_type; diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index c0d8208af12..7637dc91c79 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -518,7 +518,7 @@ static void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c) } #ifdef CONFIG_NUMA -static int nearby_node(int apicid) +static int __cpuinit nearby_node(int apicid) { int i, node; @@ -791,7 +791,7 @@ static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c) return 1; } -static void srat_detect_node(void) +static void __cpuinit srat_detect_node(void) { #ifdef CONFIG_NUMA unsigned node; @@ -1021,7 +1021,7 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* Clear all flags overriden by options */ for (i = 0; i < NCAPINTS; i++) - c->x86_capability[i] ^= cleared_cpu_caps[i]; + c->x86_capability[i] &= ~cleared_cpu_caps[i]; #ifdef CONFIG_X86_MCE mcheck_init(c); @@ -1046,7 +1046,7 @@ __setup("noclflush", setup_noclflush); void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) { if (c->x86_model_id[0]) - printk(KERN_INFO "%s", c->x86_model_id); + printk(KERN_CONT "%s", c->x86_model_id); if (c->x86_mask || c->cpuid_level >= 0) printk(KERN_CONT " stepping %02x\n", c->x86_mask); diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c index d53bd6fcb42..0880f2c388a 100644 --- a/arch/x86/kernel/smpboot_64.c +++ b/arch/x86/kernel/smpboot_64.c @@ -554,10 +554,10 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid) int timeout; unsigned long start_rip; struct create_idle c_idle = { - .work = __WORK_INITIALIZER(c_idle.work, do_fork_idle), .cpu = cpu, .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; + INIT_WORK(&c_idle.work, do_fork_idle); /* allocate memory for gdts of secondary cpus. Hotplug is considered */ if (!cpu_gdt_descr[cpu].address && diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 02f0f61f5b1..c28c342c162 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -25,6 +25,8 @@ static int save_stack_stack(void *data, char *name) static void save_stack_address(void *data, unsigned long addr, int reliable) { struct stack_trace *trace = data; + if (!reliable) + return; if (trace->skip > 0) { trace->skip--; return; @@ -37,6 +39,8 @@ static void save_stack_address_nosched(void *data, unsigned long addr, int reliable) { struct stack_trace *trace = (struct stack_trace *)data; + if (!reliable) + return; if (in_sched_functions(addr)) return; if (trace->skip > 0) { diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6dfd4e76661..022bcaa3b42 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -91,7 +91,9 @@ int do_set_thread_area(struct task_struct *p, int idx, asmlinkage int sys_set_thread_area(struct user_desc __user *u_info) { - return do_set_thread_area(current, -1, u_info, 1); + int ret = do_set_thread_area(current, -1, u_info, 1); + prevent_tail_call(ret); + return ret; } @@ -139,7 +141,9 @@ int do_get_thread_area(struct task_struct *p, int idx, asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) { - return do_get_thread_area(current, -1, u_info); + int ret = do_get_thread_area(current, -1, u_info); + prevent_tail_call(ret); + return ret; } int regset_tls_active(struct task_struct *target, diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index a40051b71d9..0fcc95a354f 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -34,7 +34,7 @@ static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); #ifdef CONFIG_HOTPLUG_CPU -int arch_register_cpu(int num) +int __ref arch_register_cpu(int num) { /* * CPU0 cannot be offlined due to several diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index 43517e324be..f14cfd9d1f9 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -28,7 +28,8 @@ EXPORT_SYMBOL_GPL(tsc_khz); static int __init tsc_setup(char *str) { printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC.\n"); + "cannot disable TSC completely.\n"); + mark_tsc_unstable("user disabled TSC"); return 1; } #else diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index f1148ac8abe..2ffa9656fe7 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -38,7 +38,7 @@ SECTIONS /* read-only */ .text : AT(ADDR(.text) - LOAD_OFFSET) { - . = ALIGN(4096); /* not really needed, already page aligned */ + . = ALIGN(PAGE_SIZE); /* not really needed, already page aligned */ *(.text.page_aligned) TEXT_TEXT SCHED_TEXT @@ -70,21 +70,21 @@ SECTIONS RODATA /* writeable */ - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); .data : AT(ADDR(.data) - LOAD_OFFSET) { /* Data */ DATA_DATA CONSTRUCTORS } :data - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { __nosave_begin = .; *(.data.nosave) - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __nosave_end = .; } - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) { *(.data.page_aligned) *(.data.idt) @@ -108,7 +108,7 @@ SECTIONS } /* might get freed after init */ - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) { __smp_locks = .; *(.smp_locks) @@ -120,10 +120,10 @@ SECTIONS * after boot. Always make sure that ALIGN() directive is present after * the section which contains __smp_alt_end. */ - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); /* will be freed after init */ - . = ALIGN(4096); /* Init code and data */ + . = ALIGN(PAGE_SIZE); /* Init code and data */ .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { __init_begin = .; _sinittext = .; @@ -174,23 +174,23 @@ SECTIONS EXIT_DATA } #if defined(CONFIG_BLK_DEV_INITRD) - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { __initramfs_start = .; *(.init.ramfs) __initramfs_end = .; } #endif - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { __per_cpu_start = .; *(.data.percpu) *(.data.percpu.shared_aligned) __per_cpu_end = .; } - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); /* freed after init ends here */ - + .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __init_end = .; __bss_start = .; /* BSS */ @@ -200,7 +200,7 @@ SECTIONS __bss_stop = .; _end = . ; /* This is where the kernel creates the early boot page tables */ - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); pg0 = . ; } diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index 0992b9946c6..fab13229973 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -37,7 +37,7 @@ SECTIONS KPROBES_TEXT *(.fixup) *(.gnu.warning) - _etext = .; /* End of text section */ + _etext = .; /* End of text section */ } :text = 0x9090 . = ALIGN(16); /* Exception table */ @@ -60,7 +60,7 @@ SECTIONS __tracedata_end = .; } - . = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */ + . = ALIGN(PAGE_SIZE); /* Align data segment to page size boundary */ /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA @@ -119,7 +119,7 @@ SECTIONS .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) { *(.vsyscall_3) } - . = VSYSCALL_VIRT_ADDR + 4096; + . = VSYSCALL_VIRT_ADDR + PAGE_SIZE; #undef VSYSCALL_ADDR #undef VSYSCALL_PHYS_ADDR @@ -129,28 +129,28 @@ SECTIONS #undef VVIRT_OFFSET #undef VVIRT - . = ALIGN(8192); /* init_task */ + . = ALIGN(THREAD_SIZE); /* init_task */ .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) { *(.data.init_task) }:data.init - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) { *(.data.page_aligned) } /* might get freed after init */ - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __smp_alt_begin = .; __smp_locks = .; .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) { *(.smp_locks) } __smp_locks_end = .; - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __smp_alt_end = .; - . = ALIGN(4096); /* Init code and data */ + . = ALIGN(PAGE_SIZE); /* Init code and data */ __init_begin = .; .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; @@ -191,7 +191,7 @@ SECTIONS .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { *(.altinstructions) } - __alt_instructions_end = .; + __alt_instructions_end = .; .altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) { *(.altinstr_replacement) } @@ -207,25 +207,25 @@ SECTIONS /* vdso blob that is mapped into user space */ vdso_start = . ; .vdso : AT(ADDR(.vdso) - LOAD_OFFSET) { *(.vdso) } - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); vdso_end = .; #ifdef CONFIG_BLK_DEV_INITRD - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __initramfs_start = .; .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { *(.init.ramfs) } __initramfs_end = .; #endif - PERCPU(4096) + PERCPU(PAGE_SIZE) - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __init_end = .; - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __nosave_begin = .; .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { *(.data.nosave) } - . = ALIGN(4096); + . = ALIGN(PAGE_SIZE); __nosave_end = .; __bss_start = .; /* BSS */ diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 3f824277458..edff4c98548 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -44,11 +44,6 @@ #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) #define __syscall_clobber "r11","cx","memory" -#define __pa_vsymbol(x) \ - ({unsigned long v; \ - extern char __vsyscall_0; \ - asm("" : "=r" (v) : "0" (x)); \ - ((v - VSYSCALL_START) + __pa_symbol(&__vsyscall_0)); }) /* * vsyscall_gtod_data contains data that is : @@ -102,7 +97,7 @@ static __always_inline void do_get_tz(struct timezone * tz) static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) { int ret; - asm volatile("vsysc2: syscall" + asm volatile("syscall" : "=a" (ret) : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber ); @@ -112,7 +107,7 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) static __always_inline long time_syscall(long *t) { long secs; - asm volatile("vsysc1: syscall" + asm volatile("syscall" : "=a" (secs) : "0" (__NR_time),"D" (t) : __syscall_clobber); return secs; @@ -228,42 +223,11 @@ long __vsyscall(3) venosys_1(void) #ifdef CONFIG_SYSCTL -#define SYSCALL 0x050f -#define NOP2 0x9090 - -/* - * NOP out syscall in vsyscall page when not needed. - */ -static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int +vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, + void __user *buffer, size_t *lenp, loff_t *ppos) { - extern u16 vsysc1, vsysc2; - u16 __iomem *map1; - u16 __iomem *map2; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - if (!write) - return ret; - /* gcc has some trouble with __va(__pa()), so just do it this - way. */ - map1 = ioremap(__pa_vsymbol(&vsysc1), 2); - if (!map1) - return -ENOMEM; - map2 = ioremap(__pa_vsymbol(&vsysc2), 2); - if (!map2) { - ret = -ENOMEM; - goto out; - } - if (!vsyscall_gtod_data.sysctl_enabled) { - writew(SYSCALL, map1); - writew(SYSCALL, map2); - } else { - writew(NOP2, map1); - writew(NOP2, map2); - } - iounmap(map2); -out: - iounmap(map1); - return ret; + return proc_dointvec(ctl, write, filp, buffer, lenp, ppos); } static ctl_table kernel_table2[] = { @@ -279,7 +243,6 @@ static ctl_table kernel_root_table2[] = { .child = kernel_table2 }, {} }; - #endif /* Assume __initcall executes before all user space. Hopefully kmod |