diff options
Diffstat (limited to 'arch/x86/kernel/paravirt.c')
| -rw-r--r-- | arch/x86/kernel/paravirt.c | 210 |
1 files changed, 109 insertions, 101 deletions
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 300da17e61c..548d25f00c9 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -23,12 +23,13 @@ #include <linux/efi.h> #include <linux/bcd.h> #include <linux/highmem.h> +#include <linux/kprobes.h> #include <asm/bug.h> #include <asm/paravirt.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/setup.h> -#include <asm/arch_hooks.h> #include <asm/pgtable.h> #include <asm/time.h> #include <asm/pgalloc.h> @@ -38,27 +39,29 @@ #include <asm/apic.h> #include <asm/tlbflush.h> #include <asm/timer.h> +#include <asm/special_insns.h> /* nop stub */ void _paravirt_nop(void) { } -static void __init default_banner(void) +/* identity function, which can be inlined */ +u32 _paravirt_ident_32(u32 x) { - printk(KERN_INFO "Booting paravirtualized kernel on %s\n", - pv_info.name); + return x; } -char *memory_setup(void) +u64 _paravirt_ident_64(u64 x) { - return pv_init_ops.memory_setup(); + return x; } -/* Simple instruction patching code. */ -#define DEF_NATIVE(ops, name, code) \ - extern const char start_##ops##_##name[], end_##ops##_##name[]; \ - asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") +void __init default_banner(void) +{ + printk(KERN_INFO "Booting paravirtualized kernel on %s\n", + pv_info.name); +} /* Undefined instruction for dealing with missing ops pointers. */ static const unsigned char ud2a[] = { 0x0f, 0x0b }; @@ -124,7 +127,9 @@ static void *get_call_destination(u8 type) .pv_irq_ops = pv_irq_ops, .pv_apic_ops = pv_apic_ops, .pv_mmu_ops = pv_mmu_ops, +#ifdef CONFIG_PARAVIRT_SPINLOCKS .pv_lock_ops = pv_lock_ops, +#endif }; return *((void **)&tmpl + type); } @@ -138,9 +143,16 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, if (opfunc == NULL) /* If there's no function, patch it with a ud2a (BUG) */ ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); - else if (opfunc == paravirt_nop) + else if (opfunc == _paravirt_nop) /* If the operation is a nop, then nop the callsite */ ret = paravirt_patch_nop(); + + /* identity functions just return their single argument */ + else if (opfunc == _paravirt_ident_32) + ret = paravirt_patch_ident_32(insnbuf, len); + else if (opfunc == _paravirt_ident_64) + ret = paravirt_patch_ident_64(insnbuf, len); + else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || @@ -169,11 +181,6 @@ unsigned paravirt_patch_insns(void *insnbuf, unsigned len, return insn_len; } -void init_IRQ(void) -{ - pv_irq_ops.init_IRQ(); -} - static void native_flush_tlb(void) { __native_flush_tlb(); @@ -193,19 +200,20 @@ static void native_flush_tlb_single(unsigned long addr) __native_flush_tlb_single(addr); } +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; + +static u64 native_steal_clock(int cpu) +{ + return 0; +} + /* These are in entry.S */ extern void native_iret(void); extern void native_irq_enable_sysexit(void); extern void native_usergs_sysret32(void); extern void native_usergs_sysret64(void); -static int __init print_banner(void) -{ - pv_init_ops.banner(); - return 0; -} -core_initcall(print_banner); - static struct resource reserve_ioports = { .start = 0, .end = IO_SPACE_LIMIT, @@ -229,18 +237,16 @@ static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LA static inline void enter_lazy(enum paravirt_lazy_mode mode) { - BUG_ON(__get_cpu_var(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE); - BUG_ON(preemptible()); + BUG_ON(this_cpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE); - __get_cpu_var(paravirt_lazy_mode) = mode; + this_cpu_write(paravirt_lazy_mode, mode); } -void paravirt_leave_lazy(enum paravirt_lazy_mode mode) +static void leave_lazy(enum paravirt_lazy_mode mode) { - BUG_ON(__get_cpu_var(paravirt_lazy_mode) != mode); - BUG_ON(preemptible()); + BUG_ON(this_cpu_read(paravirt_lazy_mode) != mode); - __get_cpu_var(paravirt_lazy_mode) = PARAVIRT_LAZY_NONE; + this_cpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE); } void paravirt_enter_lazy_mmu(void) @@ -250,33 +256,48 @@ void paravirt_enter_lazy_mmu(void) void paravirt_leave_lazy_mmu(void) { - paravirt_leave_lazy(PARAVIRT_LAZY_MMU); + leave_lazy(PARAVIRT_LAZY_MMU); } -void paravirt_enter_lazy_cpu(void) +void paravirt_flush_lazy_mmu(void) { - enter_lazy(PARAVIRT_LAZY_CPU); + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); } -void paravirt_leave_lazy_cpu(void) +void paravirt_start_context_switch(struct task_struct *prev) { - paravirt_leave_lazy(PARAVIRT_LAZY_CPU); + BUG_ON(preemptible()); + + if (this_cpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES); + } + enter_lazy(PARAVIRT_LAZY_CPU); } -enum paravirt_lazy_mode paravirt_get_lazy_mode(void) +void paravirt_end_context_switch(struct task_struct *next) { - return __get_cpu_var(paravirt_lazy_mode); + BUG_ON(preemptible()); + + leave_lazy(PARAVIRT_LAZY_CPU); + + if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES)) + arch_enter_lazy_mmu_mode(); } -void __init paravirt_use_bytelocks(void) +enum paravirt_lazy_mode paravirt_get_lazy_mode(void) { -#ifdef CONFIG_SMP - pv_lock_ops.spin_is_locked = __byte_spin_is_locked; - pv_lock_ops.spin_is_contended = __byte_spin_is_contended; - pv_lock_ops.spin_lock = __byte_spin_lock; - pv_lock_ops.spin_trylock = __byte_spin_trylock; - pv_lock_ops.spin_unlock = __byte_spin_unlock; -#endif + if (in_interrupt()) + return PARAVIRT_LAZY_NONE; + + return this_cpu_read(paravirt_lazy_mode); } struct pv_info pv_info = { @@ -284,29 +305,26 @@ struct pv_info pv_info = { .paravirt_enabled = 0, .kernel_rpl = 0, .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ + +#ifdef CONFIG_X86_64 + .extra_user_64bit_cs = __USER_CS, +#endif }; struct pv_init_ops pv_init_ops = { .patch = native_patch, - .banner = default_banner, - .arch_setup = paravirt_nop, - .memory_setup = machine_specific_memory_setup, }; struct pv_time_ops pv_time_ops = { - .time_init = hpet_time_init, - .get_wallclock = native_get_wallclock, - .set_wallclock = native_set_wallclock, .sched_clock = native_sched_clock, - .get_tsc_khz = native_calibrate_tsc, + .steal_clock = native_steal_clock, }; -struct pv_irq_ops pv_irq_ops = { - .init_IRQ = native_init_IRQ, - .save_fl = native_save_fl, - .restore_fl = native_restore_fl, - .irq_disable = native_irq_disable, - .irq_enable = native_irq_enable, +__visible struct pv_irq_ops pv_irq_ops = { + .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), + .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), + .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), + .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .safe_halt = native_safe_halt, .halt = native_halt, #ifdef CONFIG_X86_64 @@ -314,7 +332,7 @@ struct pv_irq_ops pv_irq_ops = { #endif }; -struct pv_cpu_ops pv_cpu_ops = { +__visible struct pv_cpu_ops pv_cpu_ops = { .cpuid = native_cpuid, .get_debugreg = native_get_debugreg, .set_debugreg = native_set_debugreg, @@ -338,7 +356,6 @@ struct pv_cpu_ops pv_cpu_ops = { .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, .load_idt = native_load_idt, - .store_gdt = native_store_gdt, .store_idt = native_store_idt, .store_tr = native_store_tr, .load_tls = native_load_tls, @@ -348,6 +365,10 @@ struct pv_cpu_ops pv_cpu_ops = { .write_ldt_entry = native_write_ldt_entry, .write_gdt_entry = native_write_gdt_entry, .write_idt_entry = native_write_idt_entry, + + .alloc_ldt = paravirt_nop, + .free_ldt = paravirt_nop, + .load_sp0 = native_load_sp0, #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) @@ -365,31 +386,31 @@ struct pv_cpu_ops pv_cpu_ops = { .set_iopl_mask = native_set_iopl_mask, .io_delay = native_io_delay, - .lazy_mode = { - .enter = paravirt_nop, - .leave = paravirt_nop, - }, + .start_context_switch = paravirt_nop, + .end_context_switch = paravirt_nop, }; +/* At this point, native_get/set_debugreg has real function entries */ +NOKPROBE_SYMBOL(native_get_debugreg); +NOKPROBE_SYMBOL(native_set_debugreg); +NOKPROBE_SYMBOL(native_load_idt); + struct pv_apic_ops pv_apic_ops = { #ifdef CONFIG_X86_LOCAL_APIC - .apic_write = native_apic_write, - .apic_read = native_apic_read, - .setup_boot_clock = setup_boot_APIC_clock, - .setup_secondary_clock = setup_secondary_APIC_clock, .startup_ipi_hook = paravirt_nop, #endif }; -struct pv_mmu_ops pv_mmu_ops = { -#ifndef CONFIG_X86_64 - .pagetable_setup_start = native_pagetable_setup_start, - .pagetable_setup_done = native_pagetable_setup_done, +#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) +/* 32-bit pagetable entries */ +#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) #else - .pagetable_setup_start = paravirt_nop, - .pagetable_setup_done = paravirt_nop, +/* 64-bit pagetable entries */ +#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) #endif +struct pv_mmu_ops pv_mmu_ops = { + .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, .read_cr3 = native_read_cr3, @@ -405,7 +426,6 @@ struct pv_mmu_ops pv_mmu_ops = { .alloc_pte = paravirt_nop, .alloc_pmd = paravirt_nop, - .alloc_pmd_clone = paravirt_nop, .alloc_pud = paravirt_nop, .release_pte = paravirt_nop, .release_pmd = paravirt_nop, @@ -414,40 +434,39 @@ struct pv_mmu_ops pv_mmu_ops = { .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, .set_pmd = native_set_pmd, + .set_pmd_at = native_set_pmd_at, .pte_update = paravirt_nop, .pte_update_defer = paravirt_nop, + .pmd_update = paravirt_nop, + .pmd_update_defer = paravirt_nop, .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, -#ifdef CONFIG_HIGHPTE - .kmap_atomic_pte = kmap_atomic, -#endif - #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE .set_pte_atomic = native_set_pte_atomic, - .set_pte_present = native_set_pte_present, .pte_clear = native_pte_clear, .pmd_clear = native_pmd_clear, #endif .set_pud = native_set_pud, - .pmd_val = native_pmd_val, - .make_pmd = native_make_pmd, + + .pmd_val = PTE_IDENT, + .make_pmd = PTE_IDENT, #if PAGETABLE_LEVELS == 4 - .pud_val = native_pud_val, - .make_pud = native_make_pud, + .pud_val = PTE_IDENT, + .make_pud = PTE_IDENT, + .set_pgd = native_set_pgd, #endif #endif /* PAGETABLE_LEVELS >= 3 */ - .pte_val = native_pte_val, - .pte_flags = native_pte_flags, - .pgd_val = native_pgd_val, + .pte_val = PTE_IDENT, + .pgd_val = PTE_IDENT, - .make_pte = native_make_pte, - .make_pgd = native_make_pgd, + .make_pte = PTE_IDENT, + .make_pgd = PTE_IDENT, .dup_mmap = paravirt_nop, .exit_mmap = paravirt_nop, @@ -456,23 +475,12 @@ struct pv_mmu_ops pv_mmu_ops = { .lazy_mode = { .enter = paravirt_nop, .leave = paravirt_nop, + .flush = paravirt_nop, }, .set_fixmap = native_set_fixmap, }; -struct pv_lock_ops pv_lock_ops = { -#ifdef CONFIG_SMP - .spin_is_locked = __ticket_spin_is_locked, - .spin_is_contended = __ticket_spin_is_contended, - - .spin_lock = __ticket_spin_lock, - .spin_trylock = __ticket_spin_trylock, - .spin_unlock = __ticket_spin_unlock, -#endif -}; -EXPORT_SYMBOL(pv_lock_ops); - EXPORT_SYMBOL_GPL(pv_time_ops); EXPORT_SYMBOL (pv_cpu_ops); EXPORT_SYMBOL (pv_mmu_ops); |