diff options
Diffstat (limited to 'arch/x86')
84 files changed, 1177 insertions, 593 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 725e1573ea85..e903c71f7e69 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -22,6 +22,7 @@ config X86_64 config X86 def_bool y select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK select ARCH_SUPPORTS_NUMA_BALANCING @@ -90,7 +91,6 @@ config X86 select GENERIC_IRQ_SHOW select GENERIC_CLOCKEVENTS_MIN_ADJUST select IRQ_FORCED_THREADING - select USE_GENERIC_SMP_HELPERS if SMP select HAVE_BPF_JIT if X86_64 select HAVE_ARCH_TRANSPARENT_HUGEPAGE select CLKEVT_I8253 @@ -255,10 +255,6 @@ config ARCH_HWEIGHT_CFLAGS default "-fcall-saved-ecx -fcall-saved-edx" if X86_32 default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64 -config ARCH_CPU_PROBE_RELEASE - def_bool y - depends on HOTPLUG_CPU - config ARCH_SUPPORTS_UPROBES def_bool y @@ -639,10 +635,10 @@ config PARAVIRT_SPINLOCKS spinlock implementation with something virtualization-friendly (for example, block the virtual CPU rather than spinning). - Unfortunately the downside is an up to 5% performance hit on - native kernels, with various workloads. + It has a minimal impact on native kernels and gives a nice performance + benefit on paravirtualized KVM / Xen kernels. - If you are unsure how to answer this question, answer N. + If you are unsure how to answer this question, answer Y. source "arch/x86/xen/Kconfig" @@ -1889,6 +1885,10 @@ config USE_PERCPU_NUMA_NODE_ID def_bool y depends on NUMA +config ARCH_ENABLE_SPLIT_PMD_PTLOCK + def_bool y + depends on X86_64 || X86_PAE + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index bae3aba95b15..d21ff89207cd 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -25,6 +25,7 @@ #include <linux/personality.h> #include <linux/init.h> #include <linux/jiffies.h> +#include <linux/perf_event.h> #include <asm/uaccess.h> #include <asm/pgalloc.h> @@ -33,14 +34,18 @@ #include <asm/ia32.h> #undef WARN_OLD -#undef CORE_DUMP /* definitely broken */ static int load_aout_binary(struct linux_binprm *); static int load_aout_library(struct file *); -#ifdef CORE_DUMP -static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, - unsigned long limit); +#ifdef CONFIG_COREDUMP +static int aout_core_dump(struct coredump_params *); + +static unsigned long get_dr(int n) +{ + struct perf_event *bp = current->thread.ptrace_bps[n]; + return bp ? bp->hw.info.address : 0; +} /* * fill in the user structure for a core dump.. @@ -48,6 +53,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, static void dump_thread32(struct pt_regs *regs, struct user32 *dump) { u32 fs, gs; + memset(dump, 0, sizeof(*dump)); /* changed the size calculations - should hopefully work better. lbt */ dump->magic = CMAGIC; @@ -57,15 +63,12 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump) dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT; dump->u_dsize -= dump->u_tsize; - dump->u_ssize = 0; - dump->u_debugreg[0] = current->thread.debugreg0; - dump->u_debugreg[1] = current->thread.debugreg1; - dump->u_debugreg[2] = current->thread.debugreg2; - dump->u_debugreg[3] = current->thread.debugreg3; - dump->u_debugreg[4] = 0; - dump->u_debugreg[5] = 0; + dump->u_debugreg[0] = get_dr(0); + dump->u_debugreg[1] = get_dr(1); + dump->u_debugreg[2] = get_dr(2); + dump->u_debugreg[3] = get_dr(3); dump->u_debugreg[6] = current->thread.debugreg6; - dump->u_debugreg[7] = current->thread.debugreg7; + dump->u_debugreg[7] = current->thread.ptrace_dr7; if (dump->start_stack < 0xc0000000) { unsigned long tmp; @@ -74,24 +77,24 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump) dump->u_ssize = tmp >> PAGE_SHIFT; } - dump->regs.bx = regs->bx; - dump->regs.cx = regs->cx; - dump->regs.dx = regs->dx; - dump->regs.si = regs->si; - dump->regs.di = regs->di; - dump->regs.bp = regs->bp; - dump->regs.ax = regs->ax; + dump->regs.ebx = regs->bx; + dump->regs.ecx = regs->cx; + dump->regs.edx = regs->dx; + dump->regs.esi = regs->si; + dump->regs.edi = regs->di; + dump->regs.ebp = regs->bp; + dump->regs.eax = regs->ax; dump->regs.ds = current->thread.ds; dump->regs.es = current->thread.es; savesegment(fs, fs); dump->regs.fs = fs; savesegment(gs, gs); dump->regs.gs = gs; - dump->regs.orig_ax = regs->orig_ax; - dump->regs.ip = regs->ip; + dump->regs.orig_eax = regs->orig_ax; + dump->regs.eip = regs->ip; dump->regs.cs = regs->cs; - dump->regs.flags = regs->flags; - dump->regs.sp = regs->sp; + dump->regs.eflags = regs->flags; + dump->regs.esp = regs->sp; dump->regs.ss = regs->ss; #if 1 /* FIXME */ @@ -107,7 +110,7 @@ static struct linux_binfmt aout_format = { .module = THIS_MODULE, .load_binary = load_aout_binary, .load_shlib = load_aout_library, -#ifdef CORE_DUMP +#ifdef CONFIG_COREDUMP .core_dump = aout_core_dump, #endif .min_coredump = PAGE_SIZE @@ -122,7 +125,7 @@ static void set_brk(unsigned long start, unsigned long end) vm_brk(start, end - start); } -#ifdef CORE_DUMP +#ifdef CONFIG_COREDUMP /* * These are the only things you should do on a core-file: use only these * macros to write out all the necessary info. @@ -130,15 +133,7 @@ static void set_brk(unsigned long start, unsigned long end) #include <linux/coredump.h> -#define DUMP_WRITE(addr, nr) \ - if (!dump_write(file, (void *)(addr), (nr))) \ - goto end_coredump; - -#define DUMP_SEEK(offset) \ - if (!dump_seek(file, offset)) \ - goto end_coredump; - -#define START_DATA() (u.u_tsize << PAGE_SHIFT) +#define START_DATA(u) (u.u_tsize << PAGE_SHIFT) #define START_STACK(u) (u.start_stack) /* @@ -151,8 +146,7 @@ static void set_brk(unsigned long start, unsigned long end) * dumping of the process results in another error.. */ -static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, - unsigned long limit) +static int aout_core_dump(struct coredump_params *cprm) { mm_segment_t fs; int has_dumped = 0; @@ -164,19 +158,19 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, has_dumped = 1; strncpy(dump.u_comm, current->comm, sizeof(current->comm)); dump.u_ar0 = offsetof(struct user32, regs); - dump.signal = signr; - dump_thread32(regs, &dump); + dump.signal = cprm->siginfo->si_signo; + dump_thread32(cprm->regs, &dump); /* * If the size of the dump file exceeds the rlimit, then see * what would happen if we wrote the stack, but not the data * area. */ - if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit) + if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) dump.u_dsize = 0; /* Make sure we have enough room to write the stack and data areas. */ - if ((dump.u_ssize + 1) * PAGE_SIZE > limit) + if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) dump.u_ssize = 0; /* make sure we actually have a data and stack area to dump */ @@ -190,22 +184,26 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, set_fs(KERNEL_DS); /* struct user */ - DUMP_WRITE(&dump, sizeof(dump)); + if (!dump_emit(cprm, &dump, sizeof(dump))) + goto end_coredump; /* Now dump all of the user data. Include malloced stuff as well */ - DUMP_SEEK(PAGE_SIZE - sizeof(dump)); + if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump))) + goto end_coredump; /* now we start writing out the user space info */ set_fs(USER_DS); /* Dump the data area */ if (dump.u_dsize != 0) { dump_start = START_DATA(dump); dump_size = dump.u_dsize << PAGE_SHIFT; - DUMP_WRITE(dump_start, dump_size); + if (!dump_emit(cprm, (void *)dump_start, dump_size)) + goto end_coredump; } /* Now prepare to dump the stack area */ if (dump.u_ssize != 0) { dump_start = START_STACK(dump); dump_size = dump.u_ssize << PAGE_SHIFT; - DUMP_WRITE(dump_start, dump_size); + if (!dump_emit(cprm, (void *)dump_start, dump_size)) + goto end_coredump; } end_coredump: set_fs(fs); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 665a730307f2..220675795e08 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -34,7 +34,7 @@ #include <asm/sys_ia32.h> #include <asm/smap.h> -int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) { int err = 0; bool ia32 = test_thread_flag(TIF_IA32); diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index b1977bad5435..c8c1e700c26e 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -26,6 +26,7 @@ #include <acpi/pdc_intel.h> #include <asm/numa.h> +#include <asm/fixmap.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mpspec.h> diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index b90e5dfeee46..50d033a8947d 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -327,10 +327,25 @@ static inline void write_trace_idt_entry(int entry, const gate_desc *gate) { write_idt_entry(trace_idt_table, entry, gate); } + +static inline void _trace_set_gate(int gate, unsigned type, void *addr, + unsigned dpl, unsigned ist, unsigned seg) +{ + gate_desc s; + + pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg); + /* + * does not need to be atomic because it is only done once at + * setup time + */ + write_trace_idt_entry(gate, &s); +} #else static inline void write_trace_idt_entry(int entry, const gate_desc *gate) { } + +#define _trace_set_gate(gate, type, addr, dpl, ist, seg) #endif static inline void _set_gate(int gate, unsigned type, void *addr, @@ -353,11 +368,14 @@ static inline void _set_gate(int gate, unsigned type, void *addr, * Pentium F0 0F bugfix can have resulted in the mapped * IDT being write-protected. */ -static inline void set_intr_gate(unsigned int n, void *addr) -{ - BUG_ON((unsigned)n > 0xFF); - _set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS); -} +#define set_intr_gate(n, addr) \ + do { \ + BUG_ON((unsigned)n > 0xFF); \ + _set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0, \ + __KERNEL_CS); \ + _trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\ + 0, 0, __KERNEL_CS); \ + } while (0) extern int first_system_vector; /* used_vectors is BITMAP for irq is not managed by percpu vector_irq */ @@ -374,37 +392,10 @@ static inline void alloc_system_vector(int vector) } } -#ifdef CONFIG_TRACING -static inline void trace_set_intr_gate(unsigned int gate, void *addr) -{ - gate_desc s; - - pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS); - write_idt_entry(trace_idt_table, gate, &s); -} - -static inline void __trace_alloc_intr_gate(unsigned int n, void *addr) -{ - trace_set_intr_gate(n, addr); -} -#else -static inline void trace_set_intr_gate(unsigned int gate, void *addr) -{ -} - -#define __trace_alloc_intr_gate(n, addr) -#endif - -static inline void __alloc_intr_gate(unsigned int n, void *addr) -{ - set_intr_gate(n, addr); -} - #define alloc_intr_gate(n, addr) \ do { \ alloc_system_vector(n); \ - __alloc_intr_gate(n, addr); \ - __trace_alloc_intr_gate(n, trace_##addr); \ + set_intr_gate(n, addr); \ } while (0) /* diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 4d0bda7b11e3..c49a613c6452 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -365,7 +365,7 @@ static inline void drop_fpu(struct task_struct *tsk) * Forget coprocessor state.. */ preempt_disable(); - tsk->fpu_counter = 0; + tsk->thread.fpu_counter = 0; __drop_fpu(tsk); clear_used_math(); preempt_enable(); @@ -424,7 +424,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta * or if the past 5 consecutive context-switches used math. */ fpu.preload = tsk_used_math(new) && (use_eager_fpu() || - new->fpu_counter > 5); + new->thread.fpu_counter > 5); if (__thread_has_fpu(old)) { if (!__save_init_fpu(old)) cpu = ~0; @@ -433,16 +433,16 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta /* Don't change CR0.TS if we just switch! */ if (fpu.preload) { - new->fpu_counter++; + new->thread.fpu_counter++; __thread_set_has_fpu(new); prefetch(new->thread.fpu.state); } else if (!use_eager_fpu()) stts(); } else { - old->fpu_counter = 0; + old->thread.fpu_counter = 0; old->thread.fpu.last_cpu = ~0; if (fpu.preload) { - new->fpu_counter++; + new->thread.fpu_counter++; if (!use_eager_fpu() && fpu_lazy_restore(new, cpu)) fpu.preload = 0; else diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 92b3bae08b74..cba45d99ac1a 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -187,6 +187,9 @@ extern __visible void smp_invalidate_interrupt(struct pt_regs *); #endif extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); +#ifdef CONFIG_TRACING +#define trace_interrupt interrupt +#endif typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 15f960c06ff7..24ec1216596e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -274,13 +274,17 @@ struct x86_emulate_ctxt { bool guest_mode; /* guest running a nested guest */ bool perm_ok; /* do not check permissions if true */ - bool only_vendor_specific_insn; + bool ud; /* inject an #UD if host doesn't support insn */ bool have_exception; struct x86_exception exception; - /* decode cache */ - u8 twobyte; + /* + * decode cache + */ + + /* current opcode length in bytes */ + u8 opcode_len; u8 b; u8 intercept; u8 lock_prefix; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c76ff74a98f2..ae5d7830855c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -79,6 +79,13 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) +static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) +{ + /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */ + return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); +} + #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 @@ -253,7 +260,6 @@ struct kvm_pio_request { * mode. */ struct kvm_mmu { - void (*new_cr3)(struct kvm_vcpu *vcpu); void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); @@ -261,7 +267,6 @@ struct kvm_mmu { bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - void (*free)(struct kvm_vcpu *vcpu); gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access, struct x86_exception *exception); gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access); @@ -389,6 +394,8 @@ struct kvm_vcpu_arch { struct fpu guest_fpu; u64 xcr0; + u64 guest_supported_xcr0; + u32 guest_xstate_size; struct kvm_pio_request pio; void *pio_data; @@ -557,7 +564,9 @@ struct kvm_arch { struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; - int iommu_flags; + bool iommu_noncoherent; +#define __KVM_HAVE_ARCH_NONCOHERENT_DMA + atomic_t noncoherent_dma_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; @@ -780,11 +789,11 @@ void kvm_mmu_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); -int kvm_mmu_setup(struct kvm_vcpu *vcpu); +void kvm_mmu_setup(struct kvm_vcpu *vcpu); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask); -int kvm_mmu_reset_context(struct kvm_vcpu *vcpu); +void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot); void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -922,13 +931,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu); void kvm_enable_tdp(void); void kvm_disable_tdp(void); -int complete_pio(struct kvm_vcpu *vcpu); -bool kvm_check_iopl(struct kvm_vcpu *vcpu); - static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) { return gpa; diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 626cf70082d7..3142a94c7b4b 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -94,7 +94,7 @@ static inline void early_reserve_e820_mpc_new(void) { } #define default_get_smp_config x86_init_uint_noop #endif -void generic_processor_info(int apicid, int version); +int generic_processor_info(int apicid, int version); #ifdef CONFIG_ACPI extern void mp_register_ioapic(int id, u32 address, u32 gsi_base); extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index cb7502852acb..e139b13f2a33 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -218,10 +218,14 @@ void msrs_free(struct msr *msrs); #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q); void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); #else /* CONFIG_SMP */ @@ -235,6 +239,16 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) wrmsr(msr_no, l, h); return 0; } +static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + rdmsrl(msr_no, *q); + return 0; +} +static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + wrmsrl(msr_no, q); + return 0; +} static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr *msrs) { @@ -254,6 +268,14 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { return wrmsr_safe(msr_no, l, h); } +static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + return rdmsrl_safe(msr_no, q); +} +static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + return wrmsrl_safe(msr_no, q); +} static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return rdmsr_safe_regs(regs); diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index b3e18f800302..94220d14d5cc 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -378,9 +378,6 @@ do { \ #define __this_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) #define __this_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) #define __this_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val) -#define __this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val) -#define __this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val) #define __this_cpu_xchg_1(pcp, val) percpu_xchg_op(pcp, val) #define __this_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val) #define __this_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val) @@ -400,9 +397,6 @@ do { \ #define this_cpu_or_1(pcp, val) percpu_to_op("or", (pcp), val) #define this_cpu_or_2(pcp, val) percpu_to_op("or", (pcp), val) #define this_cpu_or_4(pcp, val) percpu_to_op("or", (pcp), val) -#define this_cpu_xor_1(pcp, val) percpu_to_op("xor", (pcp), val) -#define this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val) -#define this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val) #define this_cpu_xchg_1(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(pcp, nval) @@ -447,7 +441,6 @@ do { \ #define __this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define __this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) #define __this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) -#define __this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) #define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) #define __this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) #define __this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) @@ -457,7 +450,6 @@ do { \ #define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) #define this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val) -#define this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) #define this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val) #define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) #define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index b4389a468fb6..c4412e972bbd 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -80,12 +80,21 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, #if PAGETABLE_LEVELS > 2 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + struct page *page; + page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); + if (!page) + return NULL; + if (!pgtable_pmd_page_ctor(page)) { + __free_pages(page, 0); + return NULL; + } + return (pmd_t *)page_address(page); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); + pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 987c75ecc334..7b034a4057f9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -488,6 +488,15 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; + /* + * fpu_counter contains the number of consecutive context switches + * that the FPU is used. If this is over a threshold, the lazy fpu + * saving becomes unlazy to save the trap. This is an unsigned char + * so that after 256 times the counter wraps and the behavior turns + * lazy again; this to deal with bursty apps that only use FPU for + * a short time + */ + unsigned char fpu_counter; }; /* diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index bade6ac3b14f..fbeb06ed0eaa 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -39,10 +39,5 @@ static inline void x86_dtb_init(void) { } extern char cmd_line[COMMAND_LINE_SIZE]; -#define pci_address_to_pio pci_address_to_pio -unsigned long pci_address_to_pio(phys_addr_t addr); - -#define HAVE_ARCH_DEVTREE_FIXUPS - #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index be8269b00e2a..d6b078e9fa28 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -14,6 +14,8 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall, struct timespec *ts); void pvclock_resume(void); +void pvclock_touch_watchdogs(void); + /* * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, * yielding a 64-bit result. diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index c48a95035a77..6f1c3a8a33ab 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -214,6 +214,9 @@ #ifdef __KERNEL__ #ifndef __ASSEMBLY__ extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5]; +#ifdef CONFIG_TRACING +#define trace_early_idt_handlers early_idt_handlers +#endif /* * Load a segment. Fall back on loading the zero diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index c46a46be1ec6..3ba3de457d05 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -153,8 +153,6 @@ struct thread_info { #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) -#define PREEMPT_ACTIVE 0x10000000 - #ifdef CONFIG_X86_32 #define STACK_WARN (THREAD_SIZE/8) diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h new file mode 100644 index 000000000000..2fbc66c7885b --- /dev/null +++ b/arch/x86/include/asm/trace/exceptions.h @@ -0,0 +1,52 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM exceptions + +#if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGE_FAULT_H + +#include <linux/tracepoint.h> + +extern void trace_irq_vector_regfunc(void); +extern void trace_irq_vector_unregfunc(void); + +DECLARE_EVENT_CLASS(x86_exceptions, + + TP_PROTO(unsigned long address, struct pt_regs *regs, + unsigned long error_code), + + TP_ARGS(address, regs, error_code), + + TP_STRUCT__entry( + __field( unsigned long, address ) + __field( unsigned long, ip ) + __field( unsigned long, error_code ) + ), + + TP_fast_assign( + __entry->address = address; + __entry->ip = regs->ip; + __entry->error_code = error_code; + ), + + TP_printk("address=%pf ip=%pf error_code=0x%lx", + (void *)__entry->address, (void *)__entry->ip, + __entry->error_code) ); + +#define DEFINE_PAGE_FAULT_EVENT(name) \ +DEFINE_EVENT_FN(x86_exceptions, name, \ + TP_PROTO(unsigned long address, struct pt_regs *regs, \ + unsigned long error_code), \ + TP_ARGS(address, regs, error_code), \ + trace_irq_vector_regfunc, \ + trace_irq_vector_unregfunc); + +DEFINE_PAGE_FAULT_EVENT(page_fault_user); +DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE exceptions +#endif /* _TRACE_PAGE_FAULT_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 7036cb60cd87..58d66fe06b61 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -37,6 +37,23 @@ asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ asmlinkage void simd_coprocessor_error(void); +#ifdef CONFIG_TRACING +asmlinkage void trace_page_fault(void); +#define trace_divide_error divide_error +#define trace_bounds bounds +#define trace_invalid_op invalid_op +#define trace_device_not_available device_not_available +#define trace_coprocessor_segment_overrun coprocessor_segment_overrun +#define trace_invalid_TSS invalid_TSS +#define trace_segment_not_present segment_not_present +#define trace_general_protection general_protection +#define trace_spurious_interrupt_bug spurious_interrupt_bug +#define trace_coprocessor_error coprocessor_error +#define trace_alignment_check alignment_check +#define trace_simd_coprocessor_error simd_coprocessor_error +#define trace_async_page_fault async_page_fault +#endif + dotraplinkage void do_divide_error(struct pt_regs *, long); dotraplinkage void do_debug(struct pt_regs *, long); dotraplinkage void do_nmi(struct pt_regs *, long); @@ -55,6 +72,9 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); +#ifdef CONFIG_TRACING +dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long); +#endif dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); dotraplinkage void do_coprocessor_error(struct pt_regs *, long); dotraplinkage void do_alignment_check(struct pt_regs *, long); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 828a1565ba57..0f1be11e43d2 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -172,6 +172,7 @@ struct x86_platform_ops { struct pci_dev; struct msi_msg; +struct msi_desc; struct x86_msi_ops { int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); @@ -182,6 +183,8 @@ struct x86_msi_ops { void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev, int irq); int (*setup_hpet_msi)(unsigned int irq, unsigned int id); + u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag); + u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag); }; struct IO_APIC_route_entry; diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h new file mode 100644 index 000000000000..7f02fe4e2c7b --- /dev/null +++ b/arch/x86/include/asm/xen/page-coherent.h @@ -0,0 +1,38 @@ +#ifndef _ASM_X86_XEN_PAGE_COHERENT_H +#define _ASM_X86_XEN_PAGE_COHERENT_H + +#include <asm/page.h> +#include <linux/dma-attrs.h> +#include <linux/dma-mapping.h> + +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) +{ + void *vstart = (void*)__get_free_pages(flags, get_order(size)); + *dma_handle = virt_to_phys(vstart); + return vstart; +} + +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + free_pages((unsigned long) cpu_addr, get_order(size)); +} + +static inline void xen_dma_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { } + +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { } + +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) { } + +static inline void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) { } + +#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5d9a3033b3d7..d3a87780c70b 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 { __u32 padding[3]; }; -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1 -#define KVM_CPUID_FLAG_STATEFUL_FUNC 2 -#define KVM_CPUID_FLAG_STATE_READ_NEXT 4 +#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) +#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) +#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* for KVM_SET_CPUID2 */ struct kvm_cpuid2 { diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index bb0465090ae5..b93e09a0fa21 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -536,6 +536,7 @@ /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) +#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F /* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 40c76604199f..6c0b43bd024b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -189,24 +189,31 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -static void acpi_register_lapic(int id, u8 enabled) +/** + * acpi_register_lapic - register a local apic and generates a logic cpu number + * @id: local apic id to register + * @enabled: this cpu is enabled or not + * + * Returns the logic cpu number which maps to the local apic + */ +static int acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; if (id >= MAX_LOCAL_APIC) { printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); - return; + return -EINVAL; } if (!enabled) { ++disabled_cpus; - return; + return -EINVAL; } if (boot_cpu_physical_apicid != -1U) ver = apic_version[boot_cpu_physical_apicid]; - generic_processor_info(id, ver); + return generic_processor_info(id, ver); } static int __init @@ -614,84 +621,27 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) #endif } -static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *obj; - struct acpi_madt_local_apic *lapic; - cpumask_var_t tmp_map, new_map; - u8 physid; int cpu; - int retval = -ENOMEM; - - if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) - return -EINVAL; - - if (!buffer.length || !buffer.pointer) - return -EINVAL; - - obj = buffer.pointer; - if (obj->type != ACPI_TYPE_BUFFER || - obj->buffer.length < sizeof(*lapic)) { - kfree(buffer.pointer); - return -EINVAL; - } - lapic = (struct acpi_madt_local_apic *)obj->buffer.pointer; - - if (lapic->header.type != ACPI_MADT_TYPE_LOCAL_APIC || - !(lapic->lapic_flags & ACPI_MADT_ENABLED)) { - kfree(buffer.pointer); - return -EINVAL; - } - - physid = lapic->id; - - kfree(buffer.pointer); - buffer.length = ACPI_ALLOCATE_BUFFER; - buffer.pointer = NULL; - lapic = NULL; - - if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL)) - goto out; - - if (!alloc_cpumask_var(&new_map, GFP_KERNEL)) - goto free_tmp_map; - - cpumask_copy(tmp_map, cpu_present_mask); - acpi_register_lapic(physid, ACPI_MADT_ENABLED); - - /* - * If acpi_register_lapic successfully generates a new logical cpu - * number, then the following will get us exactly what was mapped - */ - cpumask_andnot(new_map, cpu_present_mask, tmp_map); - if (cpumask_empty(new_map)) { - printk ("Unable to map lapic to logical cpu number\n"); - retval = -EINVAL; - goto free_new_map; + cpu = acpi_register_lapic(physid, ACPI_MADT_ENABLED); + if (cpu < 0) { + pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); + return cpu; } acpi_processor_set_pdc(handle); - - cpu = cpumask_first(new_map); acpi_map_cpu2node(handle, cpu, physid); *pcpu = cpu; - retval = 0; - -free_new_map: - free_cpumask_var(new_map); -free_tmp_map: - free_cpumask_var(tmp_map); -out: - return retval; + return 0; } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu) +int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - return _acpi_map_lsapic(handle, pcpu); + return _acpi_map_lsapic(handle, physid, pcpu); } EXPORT_SYMBOL(acpi_map_lsapic); @@ -745,7 +695,7 @@ static int __init acpi_parse_sbf(struct acpi_table_header *table) #ifdef CONFIG_HPET_TIMER #include <asm/hpet.h> -static struct __initdata resource *hpet_res; +static struct resource *hpet_res __initdata; static int __init acpi_parse_hpet(struct acpi_table_header *table) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 33120100ff5e..3a2ae4c88948 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -26,6 +26,17 @@ static char temp_stack[4096]; #endif /** + * x86_acpi_enter_sleep_state - enter sleep state + * @state: Sleep state to enter. + * + * Wrapper around acpi_enter_sleep_state() to be called by assmebly. + */ +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state) +{ + return acpi_enter_sleep_state(state); +} + +/** * x86_acpi_suspend_lowlevel - save kernel state * * Create an identity mapped page table and copy the wakeup routine to diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index c9c2c982d5e4..65c7b606b606 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -17,3 +17,5 @@ extern void wakeup_long64(void); extern void do_suspend_lowlevel(void); extern int x86_acpi_suspend_lowlevel(void); + +acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index d1daa66ab162..665c6b7d2ea9 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers pushl $3 - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state addl $4, %esp # In case of S3 failure, we'll emerge here. Jump diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 8ea5164cbd04..ae693b51ed8e 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel) addq $8, %rsp movl $3, %edi xorl %eax, %eax - call acpi_enter_sleep_state + call x86_acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 15e8563e5c24..df94598ad05a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -402,17 +402,6 @@ void alternatives_enable_smp(void) { struct smp_alt_module *mod; -#ifdef CONFIG_LOCKDEP - /* - * Older binutils section handling bug prevented - * alternatives-replacement from working reliably. - * - * If this still occurs then you should see a hang - * or crash shortly after this line: - */ - pr_info("lockdep: fixing up alternatives\n"); -#endif - /* Why bother if there are no other CPUs? */ BUG_ON(num_possible_cpus() == 1); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index befe4982198a..d278736bf774 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2108,7 +2108,7 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -void generic_processor_info(int apicid, int version) +int generic_processor_info(int apicid, int version) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2128,7 +2128,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -ENODEV; } if (num_processors >= nr_cpu_ids) { @@ -2139,7 +2139,7 @@ void generic_processor_info(int apicid, int version) " Processor %d/0x%x ignored.\n", max, thiscpu, apicid); disabled_cpus++; - return; + return -EINVAL; } num_processors++; @@ -2184,6 +2184,8 @@ void generic_processor_info(int apicid, int version) #endif set_cpu_possible(cpu, true); set_cpu_present(cpu, true); + + return cpu; } int hard_smp_processor_id(void) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3daece79a142..bca023bdd6b2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -339,7 +339,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) #endif /* - * On a AMD dual core setup the lower bits of the APIC id distingush the cores. + * On a AMD dual core setup the lower bits of the APIC id distinguish the cores. * Assumes number of cores is a power of two. */ static void amd_detect_cmp(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 1414c90feaba..0641113e2965 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -1,5 +1,5 @@ /* - * Routines to indentify caches on Intel CPU. + * Routines to identify caches on Intel CPU. * * Changes: * Venkatesh Pallipadi : Adding cache identification through cpuid(4) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index f2cc63e9cf08..b6f794aa1693 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -1,5 +1,5 @@ /* - * Routines to indentify additional cpu features that are scattered in + * Routines to identify additional cpu features that are scattered in * cpuid space. */ #include <linux/cpu.h> diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 376dc7873447..d35078ea1446 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -20,22 +20,13 @@ #include <asm/hpet.h> #include <asm/apic.h> #include <asm/pci_x86.h> +#include <asm/setup.h> __initdata u64 initial_dtb; char __initdata cmd_line[COMMAND_LINE_SIZE]; int __initdata of_ioapic; -unsigned long pci_address_to_pio(phys_addr_t address) -{ - /* - * The ioport address can be directly used by inX / outX - */ - BUG_ON(address >= (1 << 16)); - return (unsigned long)address; -} -EXPORT_SYMBOL_GPL(pci_address_to_pio); - void __init early_init_dt_scan_chosen_arch(unsigned long node) { BUG(); @@ -51,15 +42,6 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } -#ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(u64 start, u64 end) -{ - initrd_start = (unsigned long)__va(start); - initrd_end = (unsigned long)__va(end); - initrd_below_start_ok = 1; -} -#endif - void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); @@ -105,7 +87,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) static int x86_of_pci_irq_enable(struct pci_dev *dev) { - struct of_irq oirq; u32 virq; int ret; u8 pin; @@ -116,12 +97,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) if (!pin) return 0; - ret = of_irq_map_pci(dev, &oirq); - if (ret) - return ret; - - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); + virq = of_irq_parse_and_map_pci(dev, 0, 0); if (virq == 0) return -EINVAL; dev->irq = virq; @@ -230,7 +206,7 @@ static void __init dtb_apic_setup(void) static void __init x86_flattree_get_config(void) { u32 size, map_len; - void *new_dtb; + struct boot_param_header *dt; if (!initial_dtb) return; @@ -238,24 +214,17 @@ static void __init x86_flattree_get_config(void) map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)sizeof(struct boot_param_header)); - initial_boot_params = early_memremap(initial_dtb, map_len); - size = be32_to_cpu(initial_boot_params->totalsize); + dt = early_memremap(initial_dtb, map_len); + size = be32_to_cpu(dt->totalsize); if (map_len < size) { - early_iounmap(initial_boot_params, map_len); - initial_boot_params = early_memremap(initial_dtb, size); + early_iounmap(dt, map_len); + dt = early_memremap(initial_dtb, size); map_len = size; } - new_dtb = alloc_bootmem(size); - memcpy(new_dtb, initial_boot_params, size); - early_iounmap(initial_boot_params, map_len); - - initial_boot_params = new_dtb; - - /* root level address cells */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); - - unflatten_device_tree(); + initial_boot_params = dt; + unflatten_and_copy_device_tree(); + early_iounmap(dt, map_len); } #else static inline void x86_flattree_get_config(void) { } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index b3cd3ebae077..96f958d8cd45 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -313,6 +313,16 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } +static inline size_t gen8_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= BDW_GMCH_GMS_SHIFT; + gmch_ctrl &= BDW_GMCH_GMS_MASK; + return gmch_ctrl << 25; /* 32 MB units */ +} + typedef size_t (*stolen_size_fn)(int num, int slot, int func); static struct pci_device_id intel_stolen_ids[] __initdata = { @@ -336,6 +346,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = { INTEL_IVB_D_IDS(gen6_stolen_size), INTEL_HSW_D_IDS(gen6_stolen_size), INTEL_HSW_M_IDS(gen6_stolen_size), + INTEL_BDW_M_IDS(gen8_stolen_size), + INTEL_BDW_D_IDS(gen8_stolen_size) }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index fd1bc1b15e6d..51e2988c5728 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1244,6 +1244,16 @@ return_to_handler: */ .pushsection .kprobes.text, "ax" +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + RING0_EC_FRAME + ASM_CLAC + pushl_cfi $trace_do_page_fault + jmp error_code + CFI_ENDPROC +END(trace_page_fault) +#endif + ENTRY(page_fault) RING0_EC_FRAME ASM_CLAC diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 603be7c70675..e21b0785a85b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1278,6 +1278,17 @@ ENTRY(\sym) END(\sym) .endm +#ifdef CONFIG_TRACING +.macro trace_errorentry sym do_sym +errorentry trace(\sym) trace(\do_sym) +errorentry \sym \do_sym +.endm +#else +.macro trace_errorentry sym do_sym +errorentry \sym \do_sym +.endm +#endif + /* error code is on the stack already */ .macro paranoiderrorentry sym do_sym ENTRY(\sym) @@ -1480,7 +1491,7 @@ zeroentry xen_int3 do_int3 errorentry xen_stack_segment do_stack_segment #endif errorentry general_protection do_general_protection -errorentry page_fault do_page_fault +trace_errorentry page_fault do_page_fault #ifdef CONFIG_KVM_GUEST errorentry async_page_fault do_async_page_fault #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 42a392a9fd02..d4bdd253fea7 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -248,6 +248,15 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } +static int is_ftrace_caller(unsigned long ip) +{ + if (ip == (unsigned long)(&ftrace_call) || + ip == (unsigned long)(&ftrace_regs_call)) + return 1; + + return 0; +} + /* * A breakpoint was added to the code address we are about to * modify, and this is the handle that will just skip over it. @@ -257,10 +266,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func) */ int ftrace_int3_handler(struct pt_regs *regs) { + unsigned long ip; + if (WARN_ON_ONCE(!regs)) return 0; - if (!ftrace_location(regs->ip - 1)) + ip = regs->ip - 1; + if (!ftrace_location(ip) && !is_ftrace_caller(ip)) return 0; regs->ip += MCOUNT_INSN_SIZE - 1; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 1be8e43b669e..85126ccbdf6b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -162,7 +162,7 @@ asmlinkage void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, &early_idt_handlers[i]); + set_intr_gate(i, early_idt_handlers[i]); load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 5d576ab34403..e8368c6dd2a2 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -100,7 +100,7 @@ void unlazy_fpu(struct task_struct *tsk) __save_init_fpu(tsk); __thread_fpu_end(tsk); } else - tsk->fpu_counter = 0; + tsk->thread.fpu_counter = 0; preempt_enable(); } EXPORT_SYMBOL(unlazy_fpu); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index ee11b7dfbfbb..26d5a55a2736 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -42,15 +42,27 @@ static void __jump_label_transform(struct jump_entry *entry, int init) { union jump_code_union code; + const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; if (type == JUMP_LABEL_ENABLE) { - /* - * We are enabling this jump label. If it is not a nop - * then something must have gone wrong. - */ - if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) != 0)) - bug_at((void *)entry->code, __LINE__); + if (init) { + /* + * Jump label is enabled for the first time. + * So we expect a default_nop... + */ + if (unlikely(memcmp((void *)entry->code, default_nop, 5) + != 0)) + bug_at((void *)entry->code, __LINE__); + } else { + /* + * ...otherwise expect an ideal_nop. Otherwise + * something went horribly wrong. + */ + if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) + != 0)) + bug_at((void *)entry->code, __LINE__); + } code.jump = 0xe9; code.offset = entry->target - @@ -63,7 +75,6 @@ static void __jump_label_transform(struct jump_entry *entry, * are converting the default nop to the ideal nop. */ if (init) { - const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0)) bug_at((void *)entry->code, __LINE__); } else { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b2046e4d0b59..6dd802c6d780 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -464,7 +464,7 @@ static struct notifier_block kvm_cpu_notifier = { static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, &async_page_fault); + set_intr_gate(14, async_page_fault); } void __init kvm_guest_init(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1570e0741344..e6041094ff26 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -139,6 +139,7 @@ bool kvm_check_and_clear_guest_paused(void) src = &hv_clock[cpu].pvti; if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { src->flags &= ~PVCLOCK_GUEST_STOPPED; + pvclock_touch_watchdogs(); ret = true; } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 216a4d754b0c..18be189368bb 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -49,7 +49,7 @@ void *module_alloc(unsigned long size) return NULL; return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c2ec1aa6d454..6f1236c29c4b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -153,7 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; @@ -166,7 +166,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 176ad94e1d57..9c0280f93d05 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -163,7 +163,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.usersp = me->thread.usersp; set_tsk_thread_flag(p, TIF_FORK); - p->fpu_counter = 0; + p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index a16bae3f83b3..2f355d229a58 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -43,6 +43,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src) return pv_tsc_khz; } +void pvclock_touch_watchdogs(void) +{ + touch_softlockup_watchdog_sync(); + clocksource_touch_watchdog(); + rcu_cpu_stall_reset(); + reset_hung_task_detector(); +} + static atomic64_t last_value = ATOMIC64_INIT(0); void pvclock_resume(void) @@ -74,6 +82,11 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) version = __pvclock_read_cycles(src, &ret, &flags); } while ((src->version & 1) || version != src->version); + if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { + src->flags &= ~PVCLOCK_GUEST_STOPPED; + pvclock_touch_watchdogs(); + } + if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) && (flags & PVCLOCK_TSC_STABLE_BIT)) return ret; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 918d489fa53d..cb233bc9dee3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1121,8 +1121,6 @@ void __init setup_arch(char **cmdline_p) acpi_initrd_override((void *)initrd_start, initrd_end - initrd_start); #endif - reserve_crashkernel(); - vsmp_init(); io_delay_init(); @@ -1135,6 +1133,13 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); initmem_init(); + + /* + * Reserve memory for crash kernel after SRAT is parsed so that it + * won't consume hotpluggable memory. + */ + reserve_crashkernel(); + memblock_find_dma_reserve(); #ifdef CONFIG_KVM_GUEST diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2a165580fa16..85dc05a3aa02 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -81,27 +81,6 @@ /* State of each CPU */ DEFINE_PER_CPU(int, cpu_state) = { 0 }; -#ifdef CONFIG_HOTPLUG_CPU -/* - * We need this for trampoline_base protection from concurrent accesses when - * off- and onlining cores wildly. - */ -static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex); - -void cpu_hotplug_driver_lock(void) -{ - mutex_lock(&x86_cpu_hotplug_driver_mutex); -} - -void cpu_hotplug_driver_unlock(void) -{ - mutex_unlock(&x86_cpu_hotplug_driver_mutex); -} - -ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; } -ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; } -#endif - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 6e60b5fe2244..649b010da00b 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -65,29 +65,32 @@ int __ref _debug_hotplug_cpu(int cpu, int action) if (!cpu_is_hotpluggable(cpu)) return -EINVAL; - cpu_hotplug_driver_lock(); + lock_device_hotplug(); switch (action) { case 0: ret = cpu_down(cpu); if (!ret) { pr_info("CPU %u is now offline\n", cpu); + dev->offline = true; kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } else pr_debug("Can't offline CPU%d.\n", cpu); break; case 1: ret = cpu_up(cpu); - if (!ret) + if (!ret) { + dev->offline = false; kobject_uevent(&dev->kobj, KOBJ_ONLINE); - else + } else { pr_debug("Can't online CPU%d.\n", cpu); + } break; default: ret = -EINVAL; } - cpu_hotplug_driver_unlock(); + unlock_device_hotplug(); return ret; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 729aa779ff75..b857ed890b4c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -653,7 +653,7 @@ void math_state_restore(void) return; } - tsk->fpu_counter++; + tsk->thread.fpu_counter++; } EXPORT_SYMBOL_GPL(math_state_restore); @@ -713,7 +713,7 @@ void __init early_trap_init(void) /* int3 can be called from all */ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); #ifdef CONFIG_X86_32 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif load_idt(&idt_descr); } @@ -721,7 +721,7 @@ void __init early_trap_init(void) void __init early_trap_pf_init(void) { #ifdef CONFIG_X86_64 - set_intr_gate(X86_TRAP_PF, &page_fault); + set_intr_gate(X86_TRAP_PF, page_fault); #endif } @@ -737,30 +737,30 @@ void __init trap_init(void) early_iounmap(p, 4); #endif - set_intr_gate(X86_TRAP_DE, ÷_error); + set_intr_gate(X86_TRAP_DE, divide_error); set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); /* int4 can be called from all */ set_system_intr_gate(X86_TRAP_OF, &overflow); - set_intr_gate(X86_TRAP_BR, &bounds); - set_intr_gate(X86_TRAP_UD, &invalid_op); - set_intr_gate(X86_TRAP_NM, &device_not_available); + set_intr_gate(X86_TRAP_BR, bounds); + set_intr_gate(X86_TRAP_UD, invalid_op); + set_intr_gate(X86_TRAP_NM, device_not_available); #ifdef CONFIG_X86_32 set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); #else set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); #endif - set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun); - set_intr_gate(X86_TRAP_TS, &invalid_TSS); - set_intr_gate(X86_TRAP_NP, &segment_not_present); + set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); + set_intr_gate(X86_TRAP_TS, invalid_TSS); + set_intr_gate(X86_TRAP_NP, segment_not_present); set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); - set_intr_gate(X86_TRAP_GP, &general_protection); - set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug); - set_intr_gate(X86_TRAP_MF, &coprocessor_error); - set_intr_gate(X86_TRAP_AC, &alignment_check); + set_intr_gate(X86_TRAP_GP, general_protection); + set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); + set_intr_gate(X86_TRAP_MF, coprocessor_error); + set_intr_gate(X86_TRAP_AC, alignment_check); #ifdef CONFIG_X86_MCE set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); #endif - set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error); + set_intr_gate(X86_TRAP_XF, simd_coprocessor_error); /* Reserve all the builtin and the syscall vector: */ for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 8ce0072cd700..021783b1f46a 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -116,6 +116,8 @@ struct x86_msi_ops x86_msi = { .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, .setup_hpet_msi = default_setup_hpet_msi, + .msi_mask_irq = default_msi_mask_irq, + .msix_mask_irq = default_msix_mask_irq, }; /* MSI arch specific hooks */ @@ -138,6 +140,14 @@ void arch_restore_msi_irqs(struct pci_dev *dev, int irq) { x86_msi.restore_msi_irqs(dev, irq); } +u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + return x86_msi.msi_mask_irq(desc, mask, flag); +} +u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + return x86_msi.msix_mask_irq(desc, flag); +} #endif struct x86_io_apic_ops x86_io_apic_ops = { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a47a3e54b964..b89c5db2b832 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -38,6 +38,7 @@ config KVM select PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT + select KVM_VFIO ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index bf4fb04d0112..25d22b2d6509 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -9,7 +9,7 @@ KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \ $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o + $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b110fe6c03d4..c6976257eff5 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -23,6 +23,26 @@ #include "mmu.h" #include "trace.h" +static u32 xstate_required_size(u64 xstate_bv) +{ + int feature_bit = 0; + u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + + xstate_bv &= ~XSTATE_FPSSE; + while (xstate_bv) { + if (xstate_bv & 0x1) { + u32 eax, ebx, ecx, edx; + cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); + ret = max(ret, eax + ebx); + } + + xstate_bv >>= 1; + feature_bit++; + } + + return ret; +} + void kvm_update_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -46,6 +66,18 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu) apic->lapic_timer.timer_mode_mask = 1 << 17; } + best = kvm_find_cpuid_entry(vcpu, 0xD, 0); + if (!best) { + vcpu->arch.guest_supported_xcr0 = 0; + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + } else { + vcpu->arch.guest_supported_xcr0 = + (best->eax | ((u64)best->edx << 32)) & + host_xcr0 & KVM_SUPPORTED_XCR0; + vcpu->arch.guest_xstate_size = + xstate_required_size(vcpu->arch.guest_supported_xcr0); + } + kvm_pmu_cpuid_update(vcpu); } @@ -182,13 +214,35 @@ static bool supported_xcr0_bit(unsigned bit) { u64 mask = ((u64)1 << bit); - return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0; + return mask & KVM_SUPPORTED_XCR0 & host_xcr0; } #define F(x) bit(X86_FEATURE_##x) -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, u32 index, int *nent, int maxnent) +{ + switch (func) { + case 0: + entry->eax = 1; /* only one leaf currently */ + ++*nent; + break; + case 1: + entry->ecx = F(MOVBE); + ++*nent; + break; + default: + break; + } + + entry->function = func; + entry->index = index; + + return 0; +} + +static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index, int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -383,6 +437,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 0xd: { int idx, i; + entry->eax &= host_xcr0 & KVM_SUPPORTED_XCR0; + entry->edx &= (host_xcr0 & KVM_SUPPORTED_XCR0) >> 32; entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; for (idx = 1, i = 1; idx < 64; ++idx) { if (*nent >= maxnent) @@ -481,6 +537,15 @@ out: return r; } +static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, + u32 idx, int *nent, int maxnent, unsigned int type) +{ + if (type == KVM_GET_EMULATED_CPUID) + return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + + return __do_cpuid_ent(entry, func, idx, nent, maxnent); +} + #undef F struct kvm_cpuid_param { @@ -495,8 +560,36 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param) return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; } -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, + __u32 num_entries, unsigned int ioctl_type) +{ + int i; + __u32 pad[3]; + + if (ioctl_type != KVM_GET_EMULATED_CPUID) + return false; + + /* + * We want to make sure that ->padding is being passed clean from + * userspace in case we want to use it for something in the future. + * + * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we + * have to give ourselves satisfied only with the emulated side. /me + * sheds a tear. + */ + for (i = 0; i < num_entries; i++) { + if (copy_from_user(pad, entries[i].padding, sizeof(pad))) + return true; + + if (pad[0] || pad[1] || pad[2]) + return true; + } + return false; +} + +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type) { struct kvm_cpuid_entry2 *cpuid_entries; int limit, nent = 0, r = -E2BIG, i; @@ -513,8 +606,12 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, goto out; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; + + if (sanity_check_entries(entries, cpuid->nent, type)) + return -EINVAL; + r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); + cpuid_entries = vzalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); if (!cpuid_entries) goto out; @@ -526,7 +623,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, continue; r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; @@ -537,7 +634,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; @@ -661,6 +758,7 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) *edx = best->edx; } else *eax = *ebx = *ecx = *edx = 0; + trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx); } EXPORT_SYMBOL_GPL(kvm_cpuid); @@ -676,6 +774,5 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) kvm_register_write(vcpu, VCPU_REGS_RCX, ecx); kvm_register_write(vcpu, VCPU_REGS_RDX, edx); kvm_x86_ops->skip_emulated_instruction(vcpu); - trace_kvm_cpuid(function, eax, ebx, ecx, edx); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index b7fd07984888..f1e4895174b2 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -6,8 +6,9 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type); int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, struct kvm_cpuid_entry __user *entries); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddc3f3d2afdb..07ffca0a89e9 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -130,7 +130,7 @@ #define Mov (1<<20) /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ -#define VendorSpecific (1<<22) /* Vendor specific instruction */ +#define EmulateOnUD (1<<22) /* Emulate if unsupported by the host */ #define NoAccess (1<<23) /* Don't access memory (lea/invlpg/verr etc) */ #define Op3264 (1<<24) /* Operand is 64b in long mode, 32b otherwise */ #define Undefined (1<<25) /* No Such Instruction */ @@ -785,9 +785,10 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, * @highbyte_regs specifies whether to decode AH,CH,DH,BH. */ static void *decode_register(struct x86_emulate_ctxt *ctxt, u8 modrm_reg, - int highbyte_regs) + int byteop) { void *p; + int highbyte_regs = (ctxt->rex_prefix == 0) && byteop; if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8) p = (unsigned char *)reg_rmw(ctxt, modrm_reg & 3) + 1; @@ -1024,7 +1025,6 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { unsigned reg = ctxt->modrm_reg; - int highbyte_regs = ctxt->rex_prefix == 0; if (!(ctxt->d & ModRM)) reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3); @@ -1045,13 +1045,9 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, } op->type = OP_REG; - if (ctxt->d & ByteOp) { - op->addr.reg = decode_register(ctxt, reg, highbyte_regs); - op->bytes = 1; - } else { - op->addr.reg = decode_register(ctxt, reg, 0); - op->bytes = ctxt->op_bytes; - } + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.reg = decode_register(ctxt, reg, ctxt->d & ByteOp); + fetch_register_operand(op); op->orig_val = op->val; } @@ -1082,12 +1078,10 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_seg = VCPU_SREG_DS; if (ctxt->modrm_mod == 3) { - int highbyte_regs = ctxt->rex_prefix == 0; - op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, - highbyte_regs && (ctxt->d & ByteOp)); + ctxt->d & ByteOp); if (ctxt->d & Sse) { op->type = OP_XMM; op->bytes = 16; @@ -2961,6 +2955,46 @@ static int em_mov(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +#define FFL(x) bit(X86_FEATURE_##x) + +static int em_movbe(struct x86_emulate_ctxt *ctxt) +{ + u32 ebx, ecx, edx, eax = 1; + u16 tmp; + + /* + * Check MOVBE is set in the guest-visible CPUID leaf. + */ + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + if (!(ecx & FFL(MOVBE))) + return emulate_ud(ctxt); + + switch (ctxt->op_bytes) { + case 2: + /* + * From MOVBE definition: "...When the operand size is 16 bits, + * the upper word of the destination register remains unchanged + * ..." + * + * Both casting ->valptr and ->val to u16 breaks strict aliasing + * rules so we have to do the operation almost per hand. + */ + tmp = (u16)ctxt->src.val; + ctxt->dst.val &= ~0xffffUL; + ctxt->dst.val |= (unsigned long)swab16(tmp); + break; + case 4: + ctxt->dst.val = swab32((u32)ctxt->src.val); + break; + case 8: + ctxt->dst.val = swab64(ctxt->src.val); + break; + default: + return X86EMUL_PROPAGATE_FAULT; + } + return X86EMUL_CONTINUE; +} + static int em_cr_write(struct x86_emulate_ctxt *ctxt) { if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) @@ -3256,6 +3290,18 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_sahf(struct x86_emulate_ctxt *ctxt) +{ + u32 flags; + + flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF; + flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8; + + ctxt->eflags &= ~0xffUL; + ctxt->eflags |= flags | X86_EFLAGS_FIXED; + return X86EMUL_CONTINUE; +} + static int em_lahf(struct x86_emulate_ctxt *ctxt) { *reg_rmw(ctxt, VCPU_REGS_RAX) &= ~0xff00UL; @@ -3502,7 +3548,7 @@ static const struct opcode group7_rm1[] = { static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), - II(SrcNone | Prot | VendorSpecific, em_vmmcall, vmmcall), + II(SrcNone | Prot | EmulateOnUD, em_vmmcall, vmmcall), DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), DIP(SrcNone | Prot | Priv, stgi, check_svme), @@ -3587,7 +3633,7 @@ static const struct group_dual group7 = { { II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg), }, { - I(SrcNone | Priv | VendorSpecific, em_vmcall), + I(SrcNone | Priv | EmulateOnUD, em_vmcall), EXT(0, group7_rm1), N, EXT(0, group7_rm3), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, @@ -3750,7 +3796,8 @@ static const struct opcode opcode_table[256] = { D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), I(SrcImmFAddr | No64, em_call_far), N, II(ImplicitOps | Stack, em_pushf, pushf), - II(ImplicitOps | Stack, em_popf, popf), N, I(ImplicitOps, em_lahf), + II(ImplicitOps | Stack, em_popf, popf), + I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf), /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), @@ -3810,7 +3857,7 @@ static const struct opcode opcode_table[256] = { static const struct opcode twobyte_table[256] = { /* 0x00 - 0x0F */ G(0, group6), GD(0, &group7), N, N, - N, I(ImplicitOps | VendorSpecific, em_syscall), + N, I(ImplicitOps | EmulateOnUD, em_syscall), II(ImplicitOps | Priv, em_clts, clts), N, DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM), N, N, @@ -3830,8 +3877,8 @@ static const struct opcode twobyte_table[256] = { IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), II(ImplicitOps | Priv, em_rdmsr, rdmsr), IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc), - I(ImplicitOps | VendorSpecific, em_sysenter), - I(ImplicitOps | Priv | VendorSpecific, em_sysexit), + I(ImplicitOps | EmulateOnUD, em_sysenter), + I(ImplicitOps | Priv | EmulateOnUD, em_sysexit), N, N, N, N, N, N, N, N, N, N, /* 0x40 - 0x4F */ @@ -3892,6 +3939,30 @@ static const struct opcode twobyte_table[256] = { N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N }; +static const struct gprefix three_byte_0f_38_f0 = { + I(DstReg | SrcMem | Mov, em_movbe), N, N, N +}; + +static const struct gprefix three_byte_0f_38_f1 = { + I(DstMem | SrcReg | Mov, em_movbe), N, N, N +}; + +/* + * Insns below are selected by the prefix which indexed by the third opcode + * byte. + */ +static const struct opcode opcode_map_0f_38[256] = { + /* 0x00 - 0x7f */ + X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), + /* 0x80 - 0xef */ + X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), + /* 0xf0 - 0xf1 */ + GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f0), + GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f1), + /* 0xf2 - 0xff */ + N, N, X4(N), X8(N) +}; + #undef D #undef N #undef G @@ -4040,7 +4111,8 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, case OpMem8: ctxt->memop.bytes = 1; if (ctxt->memop.type == OP_REG) { - ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1); + ctxt->memop.addr.reg = decode_register(ctxt, + ctxt->modrm_rm, true); fetch_register_operand(&ctxt->memop); } goto mem_common; @@ -4126,6 +4198,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->_eip = ctxt->eip; ctxt->fetch.start = ctxt->_eip; ctxt->fetch.end = ctxt->fetch.start + insn_len; + ctxt->opcode_len = 1; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); @@ -4208,9 +4281,16 @@ done_prefixes: opcode = opcode_table[ctxt->b]; /* Two-byte opcode? */ if (ctxt->b == 0x0f) { - ctxt->twobyte = 1; + ctxt->opcode_len = 2; ctxt->b = insn_fetch(u8, ctxt); opcode = twobyte_table[ctxt->b]; + + /* 0F_38 opcode map */ + if (ctxt->b == 0x38) { + ctxt->opcode_len = 3; + ctxt->b = insn_fetch(u8, ctxt); + opcode = opcode_map_0f_38[ctxt->b]; + } } ctxt->d = opcode.flags; @@ -4267,7 +4347,7 @@ done_prefixes: if (ctxt->d == 0 || (ctxt->d & NotImpl)) return EMULATION_FAILED; - if (!(ctxt->d & VendorSpecific) && ctxt->only_vendor_specific_insn) + if (!(ctxt->d & EmulateOnUD) && ctxt->ud) return EMULATION_FAILED; if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack)) @@ -4540,8 +4620,10 @@ special_insn: goto writeback; } - if (ctxt->twobyte) + if (ctxt->opcode_len == 2) goto twobyte_insn; + else if (ctxt->opcode_len == 3) + goto threebyte_insn; switch (ctxt->b) { case 0x63: /* movsxd */ @@ -4726,6 +4808,8 @@ twobyte_insn: goto cannot_emulate; } +threebyte_insn: + if (rc != X86EMUL_CONTINUE) goto done; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index dce0df8150df..40772ef0f2b1 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2570,11 +2570,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, kvm_release_pfn_clean(pfn); } -static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) -{ - mmu_free_roots(vcpu); -} - static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { @@ -3424,18 +3419,11 @@ out_unlock: return 0; } -static void nonpaging_free(struct kvm_vcpu *vcpu) -{ - mmu_free_roots(vcpu); -} - -static int nonpaging_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void nonpaging_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - context->new_cr3 = nonpaging_new_cr3; context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; - context->free = nonpaging_free; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -3444,7 +3432,6 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu, context->root_hpa = INVALID_PAGE; context->direct_map = true; context->nx = false; - return 0; } void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) @@ -3454,9 +3441,8 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb); -static void paging_new_cr3(struct kvm_vcpu *vcpu) +void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu) { - pgprintk("%s: cr3 %lx\n", __func__, kvm_read_cr3(vcpu)); mmu_free_roots(vcpu); } @@ -3471,11 +3457,6 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, vcpu->arch.mmu.inject_page_fault(vcpu, fault); } -static void paging_free(struct kvm_vcpu *vcpu) -{ - nonpaging_free(vcpu); -} - static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, unsigned access, int *nr_present) { @@ -3665,9 +3646,9 @@ static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->last_pte_bitmap = map; } -static int paging64_init_context_common(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, - int level) +static void paging64_init_context_common(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, + int level) { context->nx = is_nx(vcpu); context->root_level = level; @@ -3677,27 +3658,24 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, update_last_pte_bitmap(vcpu, context); ASSERT(is_pae(vcpu)); - context->new_cr3 = paging_new_cr3; context->page_fault = paging64_page_fault; context->gva_to_gpa = paging64_gva_to_gpa; context->sync_page = paging64_sync_page; context->invlpg = paging64_invlpg; context->update_pte = paging64_update_pte; - context->free = paging_free; context->shadow_root_level = level; context->root_hpa = INVALID_PAGE; context->direct_map = false; - return 0; } -static int paging64_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging64_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - return paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL); + paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL); } -static int paging32_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging32_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { context->nx = false; context->root_level = PT32_ROOT_LEVEL; @@ -3706,33 +3684,28 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); - context->new_cr3 = paging_new_cr3; context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; - context->free = paging_free; context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; context->update_pte = paging32_update_pte; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; context->direct_map = false; - return 0; } -static int paging32E_init_context(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void paging32E_init_context(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - return paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); + paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL); } -static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *context = vcpu->arch.walk_mmu; context->base_role.word = 0; - context->new_cr3 = nonpaging_new_cr3; context->page_fault = tdp_page_fault; - context->free = nonpaging_free; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -3767,37 +3740,32 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); - - return 0; } -int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) +void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { - int r; bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (!is_paging(vcpu)) - r = nonpaging_init_context(vcpu, context); + nonpaging_init_context(vcpu, context); else if (is_long_mode(vcpu)) - r = paging64_init_context(vcpu, context); + paging64_init_context(vcpu, context); else if (is_pae(vcpu)) - r = paging32E_init_context(vcpu, context); + paging32E_init_context(vcpu, context); else - r = paging32_init_context(vcpu, context); + paging32_init_context(vcpu, context); vcpu->arch.mmu.base_role.nxe = is_nx(vcpu); vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu); vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu); vcpu->arch.mmu.base_role.smep_andnot_wp = smep && !is_write_protection(vcpu); - - return r; } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); -int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, +void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { ASSERT(vcpu); @@ -3806,37 +3774,30 @@ int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, context->shadow_root_level = kvm_x86_ops->get_tdp_level(); context->nx = true; - context->new_cr3 = paging_new_cr3; context->page_fault = ept_page_fault; context->gva_to_gpa = ept_gva_to_gpa; context->sync_page = ept_sync_page; context->invlpg = ept_invlpg; context->update_pte = ept_update_pte; - context->free = paging_free; context->root_level = context->shadow_root_level; context->root_hpa = INVALID_PAGE; context->direct_map = false; update_permission_bitmask(vcpu, context, true); reset_rsvds_bits_mask_ept(vcpu, context, execonly); - - return 0; } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); -static int init_kvm_softmmu(struct kvm_vcpu *vcpu) +static void init_kvm_softmmu(struct kvm_vcpu *vcpu) { - int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu); - + kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu); vcpu->arch.walk_mmu->set_cr3 = kvm_x86_ops->set_cr3; vcpu->arch.walk_mmu->get_cr3 = get_cr3; vcpu->arch.walk_mmu->get_pdptr = kvm_pdptr_read; vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; - - return r; } -static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; @@ -3873,11 +3834,9 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) update_permission_bitmask(vcpu, g_context, false); update_last_pte_bitmap(vcpu, g_context); - - return 0; } -static int init_kvm_mmu(struct kvm_vcpu *vcpu) +static void init_kvm_mmu(struct kvm_vcpu *vcpu) { if (mmu_is_nested(vcpu)) return init_kvm_nested_mmu(vcpu); @@ -3887,18 +3846,12 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu) return init_kvm_softmmu(vcpu); } -static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) +void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - if (VALID_PAGE(vcpu->arch.mmu.root_hpa)) - /* mmu.free() should set root_hpa = INVALID_PAGE */ - vcpu->arch.mmu.free(vcpu); -} -int kvm_mmu_reset_context(struct kvm_vcpu *vcpu) -{ - destroy_kvm_mmu(vcpu); - return init_kvm_mmu(vcpu); + kvm_mmu_unload(vcpu); + init_kvm_mmu(vcpu); } EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); @@ -3923,6 +3876,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { mmu_free_roots(vcpu); + WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); } EXPORT_SYMBOL_GPL(kvm_mmu_unload); @@ -4281,12 +4235,12 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) return alloc_mmu_pages(vcpu); } -int kvm_mmu_setup(struct kvm_vcpu *vcpu) +void kvm_mmu_setup(struct kvm_vcpu *vcpu) { ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); - return init_kvm_mmu(vcpu); + init_kvm_mmu(vcpu); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) @@ -4428,7 +4382,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) int nr_to_scan = sc->nr_to_scan; unsigned long freed = 0; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -4478,9 +4432,8 @@ unlock: break; } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); return freed; - } static unsigned long @@ -4574,7 +4527,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - destroy_kvm_mmu(vcpu); + kvm_mmu_unload(vcpu); free_mmu_pages(vcpu); mmu_free_memory_caches(vcpu); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 77e044a0f5f7..292615274358 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -70,8 +70,8 @@ enum { }; int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); -int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); -int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, +void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); +void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c0bc80391e40..c7168a5cff1b 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1959,11 +1959,9 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, nested_svm_vmexit(svm); } -static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) +static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) { - int r; - - r = kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu); + kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu); vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3; vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3; @@ -1971,8 +1969,6 @@ static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; - - return r; } static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2b2fce1b2009..b2fe1c252f35 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1498,7 +1498,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, break; if (i == NR_AUTOLOAD_MSRS) { - printk_once(KERN_WARNING"Not enough mst switch entries. " + printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; } else if (i == m->nr) { @@ -1898,16 +1898,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) /* * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. - * This function assumes it is called with the exit reason in vmcs02 being - * a #PF exception (this is the only case in which KVM injects a #PF when L2 - * is running). */ -static int nested_pf_handled(struct kvm_vcpu *vcpu) +static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ - if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR))) + if (!(vmcs12->exception_bitmap & (1u << nr))) return 0; nested_vmx_vmexit(vcpu); @@ -1921,8 +1917,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info = nr | INTR_INFO_VALID_MASK; - if (nr == PF_VECTOR && is_guest_mode(vcpu) && - !vmx->nested.nested_run_pending && nested_pf_handled(vcpu)) + if (!reinject && is_guest_mode(vcpu) && + nested_vmx_check_exception(vcpu, nr)) return; if (has_error_code) { @@ -2204,9 +2200,15 @@ static __init void nested_vmx_setup_ctls_msrs(void) #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif - VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT; + VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + if (!(nested_vmx_pinbased_ctls_high & PIN_BASED_VMX_PREEMPTION_TIMER) || + !(nested_vmx_exit_ctls_high & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) { + nested_vmx_exit_ctls_high &= ~VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + nested_vmx_pinbased_ctls_high &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + } nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | - VM_EXIT_LOAD_IA32_EFER); + VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER); /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, @@ -2226,7 +2228,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high); nested_vmx_procbased_ctls_low = 0; nested_vmx_procbased_ctls_high &= - CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_VIRTUAL_INTR_PENDING | + CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | @@ -2252,13 +2255,15 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_WBINVD_EXITING; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | - VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT; + VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | + VMX_EPT_INVEPT_BIT; nested_vmx_ept_caps &= vmx_capability.ept; /* * Since invept is completely emulated we support both global @@ -3380,8 +3385,10 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (enable_ept) { eptp = construct_eptp(cr3); vmcs_write64(EPT_POINTER, eptp); - guest_cr3 = is_paging(vcpu) ? kvm_read_cr3(vcpu) : - vcpu->kvm->arch.ept_identity_map_addr; + if (is_paging(vcpu) || is_guest_mode(vcpu)) + guest_cr3 = kvm_read_cr3(vcpu); + else + guest_cr3 = vcpu->kvm->arch.ept_identity_map_addr; ept_load_pdptrs(vcpu); } @@ -4879,6 +4886,17 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xc1; } +static bool nested_cr0_valid(struct vmcs12 *vmcs12, unsigned long val) +{ + unsigned long always_on = VMXON_CR0_ALWAYSON; + + if (nested_vmx_secondary_ctls_high & + SECONDARY_EXEC_UNRESTRICTED_GUEST && + nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST)) + always_on &= ~(X86_CR0_PE | X86_CR0_PG); + return (val & always_on) == always_on; +} + /* called to set cr0 as appropriate for a mov-to-cr0 exit. */ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) { @@ -4897,9 +4915,7 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) val = (val & ~vmcs12->cr0_guest_host_mask) | (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); - /* TODO: will have to take unrestricted guest mode into - * account */ - if ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) + if (!nested_cr0_valid(vmcs12, val)) return 1; if (kvm_set_cr0(vcpu, val)) @@ -6627,6 +6643,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return 0; else if (is_page_fault(intr_info)) return enable_ept; + else if (is_no_device(intr_info) && + !(nested_read_cr0(vmcs12) & X86_CR0_TS)) + return 0; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: @@ -6722,6 +6741,27 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = vmcs_read32(VM_EXIT_INTR_INFO); } +static void nested_adjust_preemption_timer(struct kvm_vcpu *vcpu) +{ + u64 delta_tsc_l1; + u32 preempt_val_l1, preempt_val_l2, preempt_scale; + + if (!(get_vmcs12(vcpu)->pin_based_vm_exec_control & + PIN_BASED_VMX_PREEMPTION_TIMER)) + return; + preempt_scale = native_read_msr(MSR_IA32_VMX_MISC) & + MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE; + preempt_val_l2 = vmcs_read32(VMX_PREEMPTION_TIMER_VALUE); + delta_tsc_l1 = vmx_read_l1_tsc(vcpu, native_read_tsc()) + - vcpu->arch.last_guest_tsc; + preempt_val_l1 = delta_tsc_l1 >> preempt_scale; + if (preempt_val_l2 <= preempt_val_l1) + preempt_val_l2 = 0; + else + preempt_val_l2 -= preempt_val_l1; + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, preempt_val_l2); +} + /* * The guest has exited. See if we can fix it or if we need userspace * assistance. @@ -6736,20 +6776,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); - /* - * the KVM_REQ_EVENT optimization bit is only on for one entry, and if - * we did not inject a still-pending event to L1 now because of - * nested_run_pending, we need to re-enable this bit. - */ - if (vmx->nested.nested_run_pending) - kvm_make_request(KVM_REQ_EVENT, vcpu); - - if (!is_guest_mode(vcpu) && (exit_reason == EXIT_REASON_VMLAUNCH || - exit_reason == EXIT_REASON_VMRESUME)) - vmx->nested.nested_run_pending = 1; - else - vmx->nested.nested_run_pending = 0; - if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) { nested_vmx_vmexit(vcpu); return 1; @@ -7061,9 +7087,9 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, case INTR_TYPE_HARD_EXCEPTION: if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { u32 err = vmcs_read32(error_code_field); - kvm_queue_exception_e(vcpu, vector, err); + kvm_requeue_exception_e(vcpu, vector, err); } else - kvm_queue_exception(vcpu, vector); + kvm_requeue_exception(vcpu, vector); break; case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); @@ -7146,6 +7172,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); + if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) + nested_adjust_preemption_timer(vcpu); vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -7284,6 +7312,16 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); + /* + * the KVM_REQ_EVENT optimization bit is only on for one entry, and if + * we did not inject a still-pending event to L1 now because of + * nested_run_pending, we need to re-enable this bit. + */ + if (vmx->nested.nested_run_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); + + vmx->nested.nested_run_pending = 0; + vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); @@ -7410,8 +7448,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) */ if (is_mmio) ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - else if (vcpu->kvm->arch.iommu_domain && - !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)) + else if (kvm_arch_has_noncoherent_dma(vcpu->kvm)) ret = kvm_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; else @@ -7501,9 +7538,9 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) return get_vmcs12(vcpu)->ept_pointer; } -static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) +static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { - int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu, + kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu, nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT); vcpu->arch.mmu.set_cr3 = vmx_set_cr3; @@ -7511,8 +7548,6 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault; vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; - - return r; } static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) @@ -7520,6 +7555,20 @@ static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu = &vcpu->arch.mmu; } +static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, + struct x86_exception *fault) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + WARN_ON(!is_guest_mode(vcpu)); + + /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ + if (vmcs12->exception_bitmap & (1u << PF_VECTOR)) + nested_vmx_vmexit(vcpu); + else + kvm_inject_page_fault(vcpu, fault); +} + /* * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it @@ -7533,6 +7582,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; + u32 exit_control; vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); @@ -7706,7 +7756,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits are further modified by vmx_set_efer() below. */ - vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); + exit_control = vmcs_config.vmexit_ctrl; + if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) + exit_control |= VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + vmcs_write32(VM_EXIT_CONTROLS, exit_control); /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are * emulated by vmx_set_efer(), below. @@ -7773,6 +7826,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) kvm_set_cr3(vcpu, vmcs12->guest_cr3); kvm_mmu_reset_context(vcpu); + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; + /* * L1 may access the L2's PDPTR, so save them to construct vmcs12 */ @@ -7876,7 +7932,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } - if (((vmcs12->guest_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) || + if (!nested_cr0_valid(vmcs12, vmcs12->guest_cr0) || ((vmcs12->guest_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) { nested_vmx_entry_failure(vcpu, vmcs12, EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); @@ -7938,6 +7994,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) enter_guest_mode(vcpu); + vmx->nested.nested_run_pending = 1; + vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET); cpu = get_cpu(); @@ -8005,7 +8063,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, u32 idt_vectoring; unsigned int nr; - if (vcpu->arch.exception.pending) { + if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) { nr = vcpu->arch.exception.nr; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; @@ -8023,7 +8081,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, } vmcs12->idt_vectoring_info_field = idt_vectoring; - } else if (vcpu->arch.nmi_pending) { + } else if (vcpu->arch.nmi_injected) { vmcs12->idt_vectoring_info_field = INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR; } else if (vcpu->arch.interrupt.pending) { @@ -8105,6 +8163,11 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + if ((vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) && + (vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) + vmcs12->vmx_preemption_timer_value = + vmcs_read32(VMX_PREEMPTION_TIMER_VALUE); + /* * In some cases (usually, nested EPT), L2 is allowed to change its * own CR3 without exiting. If it has changed it, we must keep it. @@ -8130,6 +8193,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT); + if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) + vmcs12->guest_ia32_efer = vcpu->arch.efer; vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); @@ -8201,7 +8266,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * fpu_active (which may have changed). * Note that vmx_set_cr0 refers to efer set above. */ - kvm_set_cr0(vcpu, vmcs12->host_cr0); + vmx_set_cr0(vcpu, vmcs12->host_cr0); /* * If we did fpu_activate()/fpu_deactivate() during L2's run, we need * to apply the same changes to L1's vmcs. We just set cr0 correctly, @@ -8224,6 +8289,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, kvm_set_cr3(vcpu, vmcs12->host_cr3); kvm_mmu_reset_context(vcpu); + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; + if (enable_vpid) { /* * Trivially support vpid by letting L2s share their parent diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e5ca72a5cdb6..21ef1ba184ae 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -577,6 +577,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0; + u64 valid_bits; /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ if (index != XCR_XFEATURE_ENABLED_MASK) @@ -586,8 +587,16 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) return 1; if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) return 1; - if (xcr0 & ~host_xcr0) + + /* + * Do not allow the guest to set bits that we do not support + * saving. However, xcr0 bit 0 is always set, even if the + * emulated CPU does not support XSAVE (see fx_init). + */ + valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP; + if (xcr0 & ~valid_bits) return 1; + kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; return 0; @@ -684,7 +693,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vcpu->arch.cr3 = cr3; __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); - vcpu->arch.mmu.new_cr3(vcpu); + kvm_mmu_new_cr3(vcpu); return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr3); @@ -2564,6 +2573,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: @@ -2673,15 +2683,17 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_SUPPORTED_CPUID: { + case KVM_GET_SUPPORTED_CPUID: + case KVM_GET_EMULATED_CPUID: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; - r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, - cpuid_arg->entries); + + r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, + ioctl); if (r) goto out; @@ -2715,8 +2727,7 @@ static void wbinvd_ipi(void *garbage) static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) { - return vcpu->kvm->arch.iommu_domain && - !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY); + return kvm_arch_has_noncoherent_dma(vcpu->kvm); } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -2984,11 +2995,13 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - if (cpu_has_xsave) + if (cpu_has_xsave) { memcpy(guest_xsave->region, &vcpu->arch.guest_fpu.state->xsave, - xstate_size); - else { + vcpu->arch.guest_xstate_size); + *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &= + vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE; + } else { memcpy(guest_xsave->region, &vcpu->arch.guest_fpu.state->fxsave, sizeof(struct i387_fxsave_struct)); @@ -3003,10 +3016,19 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; - if (cpu_has_xsave) + if (cpu_has_xsave) { + /* + * Here we allow setting states that are not present in + * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility + * with old userspace. + */ + if (xstate_bv & ~KVM_SUPPORTED_XCR0) + return -EINVAL; + if (xstate_bv & ~host_xcr0) + return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state->xsave, - guest_xsave->region, xstate_size); - else { + guest_xsave->region, vcpu->arch.guest_xstate_size); + } else { if (xstate_bv & ~XSTATE_FPSSE) return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state->fxsave, @@ -3042,9 +3064,9 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, for (i = 0; i < guest_xcrs->nr_xcrs; i++) /* Only support XCR0 currently */ - if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) { + if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) { r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK, - guest_xcrs->xcrs[0].value); + guest_xcrs->xcrs[i].value); break; } if (r) @@ -4775,8 +4797,8 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu) static void init_decode_cache(struct x86_emulate_ctxt *ctxt) { - memset(&ctxt->twobyte, 0, - (void *)&ctxt->_regs - (void *)&ctxt->twobyte); + memset(&ctxt->opcode_len, 0, + (void *)&ctxt->_regs - (void *)&ctxt->opcode_len); ctxt->fetch.start = 0; ctxt->fetch.end = 0; @@ -5094,8 +5116,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, ctxt->have_exception = false; ctxt->perm_ok = false; - ctxt->only_vendor_specific_insn - = emulation_type & EMULTYPE_TRAP_UD; + ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; r = x86_decode_insn(ctxt, insn, insn_len); @@ -5263,7 +5284,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) @@ -5273,7 +5294,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va send_ipi = 1; } } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -5426,12 +5447,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests); atomic_set(&kvm_guest_has_master_clock, 0); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -5945,10 +5966,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = IN_GUEST_MODE; + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + /* We should set ->mode before check ->requests, * see the comment in make_all_cpus_request. */ - smp_mb(); + smp_mb__after_srcu_read_unlock(); local_irq_disable(); @@ -5958,12 +5981,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = 1; goto cancel_injection; } - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); @@ -6688,7 +6710,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) if (r) return r; kvm_vcpu_reset(vcpu); - r = kvm_mmu_setup(vcpu); + kvm_mmu_setup(vcpu); vcpu_put(vcpu); return r; @@ -6940,6 +6962,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.ia32_tsc_adjust_msr = 0x0; vcpu->arch.pv_time_enabled = false; + + vcpu->arch.guest_supported_xcr0 = 0; + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); @@ -6981,6 +7007,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); + atomic_set(&kvm->arch.noncoherent_dma_count, 0); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); @@ -7065,7 +7092,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { int i; @@ -7086,7 +7113,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, } } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { int i; @@ -7283,7 +7311,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) int r; if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) || - is_error_page(work->page)) + work->wakeup_all) return; r = kvm_mmu_reload(vcpu); @@ -7393,7 +7421,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct x86_exception fault; trace_kvm_async_pf_ready(work->arch.token, work->gva); - if (is_error_page(work->page)) + if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); @@ -7420,6 +7448,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) kvm_x86_ops->interrupt_allowed(vcpu); } +void kvm_arch_register_noncoherent_dma(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); + +void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); + +bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.noncoherent_dma_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index e224f7a671b6..587fb9ede436 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -122,6 +122,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +#define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) extern u64 host_xcr0; extern struct static_key kvm_no_apic_vcpu; diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index a6b1b86d2253..518532e6a3fa 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -47,6 +47,21 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) } EXPORT_SYMBOL(rdmsr_on_cpu); +int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); + *q = rv.reg.q; + + return err; +} +EXPORT_SYMBOL(rdmsrl_on_cpu); + int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { int err; @@ -63,6 +78,22 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_on_cpu); +int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.q = q; + + err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); + + return err; +} +EXPORT_SYMBOL(wrmsrl_on_cpu); + static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs, void (*msr_func) (void *info)) @@ -159,6 +190,37 @@ int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) } EXPORT_SYMBOL(wrmsr_safe_on_cpu); +int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + rv.reg.q = q; + + err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(wrmsrl_safe_on_cpu); + +int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + int err; + struct msr_info rv; + + memset(&rv, 0, sizeof(rv)); + + rv.msr_no = msr_no; + err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); + *q = rv.reg.q; + + return err ? err : rv.err; +} +EXPORT_SYMBOL(rdmsrl_safe_on_cpu); + /* * These variants are significantly slower, but allows control over * the entire 32-bit GPR set. diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 23d8e5fecf76..6a19ad9f370d 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -6,6 +6,8 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) CFLAGS_setup_nx.o := $(nostackp) +CFLAGS_fault.o := -I$(src)/../include/asm/trace + obj-$(CONFIG_X86_PAT) += pat_rbtree.o obj-$(CONFIG_SMP) += tlb.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e7e1cac74e8d..9ff85bb8dd69 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,9 @@ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_START */ +#define CREATE_TRACE_POINTS +#include <asm/trace/exceptions.h> + /* * Page fault error code bits: * @@ -1232,3 +1235,23 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code); exception_exit(prev_state); } + +static void trace_page_fault_entries(struct pt_regs *regs, + unsigned long error_code) +{ + if (user_mode(regs)) + trace_page_fault_user(read_cr2(), regs, error_code); + else + trace_page_fault_kernel(read_cr2(), regs, error_code); +} + +dotraplinkage void __kprobes +trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + enum ctx_state prev_state; + + prev_state = exception_enter(); + trace_page_fault_entries(regs, error_code); + __do_page_fault(regs, error_code); + exception_exit(prev_state); +} diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index ce32017c5e38..f97130618113 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -53,12 +53,12 @@ __ref void *alloc_low_pages(unsigned int num) if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { unsigned long ret; if (min_pfn_mapped >= max_pfn_mapped) - panic("alloc_low_page: ran out of memory"); + panic("alloc_low_pages: ran out of memory"); ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT, max_pfn_mapped << PAGE_SHIFT, PAGE_SIZE * num , PAGE_SIZE); if (!ret) - panic("alloc_low_page: can not alloc memory"); + panic("alloc_low_pages: can not alloc memory"); memblock_reserve(ret, PAGE_SIZE * num); pfn = ret >> PAGE_SHIFT; } else { @@ -418,27 +418,27 @@ static unsigned long __init get_new_step_size(unsigned long step_size) return step_size << 5; } -void __init init_mem_mapping(void) +/** + * memory_map_top_down - Map [map_start, map_end) top down + * @map_start: start address of the target memory range + * @map_end: end address of the target memory range + * + * This function will setup direct mapping for memory range + * [map_start, map_end) in top-down. That said, the page tables + * will be allocated at the end of the memory, and we map the + * memory in top-down. + */ +static void __init memory_map_top_down(unsigned long map_start, + unsigned long map_end) { - unsigned long end, real_end, start, last_start; + unsigned long real_end, start, last_start; unsigned long step_size; unsigned long addr; unsigned long mapped_ram_size = 0; unsigned long new_mapped_ram_size; - probe_page_size_mask(); - -#ifdef CONFIG_X86_64 - end = max_pfn << PAGE_SHIFT; -#else - end = max_low_pfn << PAGE_SHIFT; -#endif - - /* the ISA range is always mapped regardless of memory holes */ - init_memory_mapping(0, ISA_END_ADDRESS); - /* xen has big range in reserved near end of ram, skip it at first.*/ - addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, PMD_SIZE); + addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ @@ -453,13 +453,13 @@ void __init init_mem_mapping(void) * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ - while (last_start > ISA_END_ADDRESS) { + while (last_start > map_start) { if (last_start > step_size) { start = round_down(last_start - 1, step_size); - if (start < ISA_END_ADDRESS) - start = ISA_END_ADDRESS; + if (start < map_start) + start = map_start; } else - start = ISA_END_ADDRESS; + start = map_start; new_mapped_ram_size = init_range_memory_mapping(start, last_start); last_start = start; @@ -470,8 +470,89 @@ void __init init_mem_mapping(void) mapped_ram_size += new_mapped_ram_size; } - if (real_end < end) - init_range_memory_mapping(real_end, end); + if (real_end < map_end) + init_range_memory_mapping(real_end, map_end); +} + +/** + * memory_map_bottom_up - Map [map_start, map_end) bottom up + * @map_start: start address of the target memory range + * @map_end: end address of the target memory range + * + * This function will setup direct mapping for memory range + * [map_start, map_end) in bottom-up. Since we have limited the + * bottom-up allocation above the kernel, the page tables will + * be allocated just above the kernel and we map the memory + * in [map_start, map_end) in bottom-up. + */ +static void __init memory_map_bottom_up(unsigned long map_start, + unsigned long map_end) +{ + unsigned long next, new_mapped_ram_size, start; + unsigned long mapped_ram_size = 0; + /* step_size need to be small so pgt_buf from BRK could cover it */ + unsigned long step_size = PMD_SIZE; + + start = map_start; + min_pfn_mapped = start >> PAGE_SHIFT; + + /* + * We start from the bottom (@map_start) and go to the top (@map_end). + * The memblock_find_in_range() gets us a block of RAM from the + * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages + * for page table. + */ + while (start < map_end) { + if (map_end - start > step_size) { + next = round_up(start + 1, step_size); + if (next > map_end) + next = map_end; + } else + next = map_end; + + new_mapped_ram_size = init_range_memory_mapping(start, next); + start = next; + + if (new_mapped_ram_size > mapped_ram_size) + step_size = get_new_step_size(step_size); + mapped_ram_size += new_mapped_ram_size; + } +} + +void __init init_mem_mapping(void) +{ + unsigned long end; + + probe_page_size_mask(); + +#ifdef CONFIG_X86_64 + end = max_pfn << PAGE_SHIFT; +#else + end = max_low_pfn << PAGE_SHIFT; +#endif + + /* the ISA range is always mapped regardless of memory holes */ + init_memory_mapping(0, ISA_END_ADDRESS); + + /* + * If the allocation is in bottom-up direction, we setup direct mapping + * in bottom-up, otherwise we setup direct mapping in top-down. + */ + if (memblock_bottom_up()) { + unsigned long kernel_end = __pa_symbol(_end); + + /* + * we need two separate calls here. This is because we want to + * allocate page tables above the kernel. So we first map + * [kernel_end, end) to make memory above the kernel be mapped + * as soon as possible. And then use page tables allocated above + * the kernel to map [ISA_END_ADDRESS, kernel_end). + */ + memory_map_bottom_up(kernel_end, end); + memory_map_bottom_up(ISA_END_ADDRESS, kernel_end); + } else { + memory_map_top_down(ISA_END_ADDRESS, end); + } #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 8bf93bae1f13..24aec58d6afd 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -567,6 +567,17 @@ static int __init numa_init(int (*init_func)(void)) ret = init_func(); if (ret < 0) return ret; + + /* + * We reset memblock back to the top-down direction + * here because if we configured ACPI_NUMA, we have + * parsed SRAT in init_func(). It is ok to have the + * reset here even if we did't configure ACPI_NUMA + * or acpi numa init fails and fallbacks to dummy + * numa init. + */ + memblock_set_bottom_up(false); + ret = numa_cleanup_meminfo(&numa_meminfo); if (ret < 0) return ret; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index dfa537a03be1..a7cccb6d7fec 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -25,8 +25,12 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) struct page *pte; pte = alloc_pages(__userpte_alloc_gfp, 0); - if (pte) - pgtable_page_ctor(pte); + if (!pte) + return NULL; + if (!pgtable_page_ctor(pte)) { + __free_page(pte); + return NULL; + } return pte; } @@ -189,8 +193,10 @@ static void free_pmds(pmd_t *pmds[]) int i; for(i = 0; i < PREALLOCATED_PMDS; i++) - if (pmds[i]) + if (pmds[i]) { + pgtable_pmd_page_dtor(virt_to_page(pmds[i])); free_page((unsigned long)pmds[i]); + } } static int preallocate_pmds(pmd_t *pmds[]) @@ -200,8 +206,13 @@ static int preallocate_pmds(pmd_t *pmds[]) for(i = 0; i < PREALLOCATED_PMDS; i++) { pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP); - if (pmd == NULL) + if (!pmd) failed = true; + if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) { + free_page((unsigned long)pmds[i]); + pmd = NULL; + failed = true; + } pmds[i] = pmd; } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 516593e1ce33..26328e800869 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -788,5 +788,7 @@ void bpf_jit_free(struct sk_filter *fp) if (fp->bpf_func != sk_run_filter) { INIT_WORK(&fp->work, bpf_jit_free_deferred); schedule_work(&fp->work); + } else { + kfree(fp); } } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b30e937689d6..7fb24e53d4c8 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -354,12 +354,12 @@ static void coalesce_windows(struct pci_root_info *info, unsigned long type) * the kernel resource tree doesn't allow overlaps. */ if (resource_overlaps(res1, res2)) { - res1->start = min(res1->start, res2->start); - res1->end = max(res1->end, res2->end); + res2->start = min(res1->start, res2->start); + res2->end = max(res1->end, res2->end); dev_info(&info->bridge->dev, "host bridge window expanded to %pR; %pR ignored\n", - res1, res2); - res2->flags = 0; + res2, res1); + res1->flags = 0; } } } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f5809fa2753e..b046e070e088 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -231,7 +231,7 @@ static int quirk_pcie_aspm_write(struct pci_bus *bus, unsigned int devfn, int wh offset = quirk_aspm_offset[GET_INDEX(bus->self->device, devfn)]; if ((offset) && (where == offset)) - value = value & 0xfffffffc; + value = value & ~PCI_EXP_LNKCTL_ASPMC; return raw_pci_write(pci_domain_nr(bus), bus->number, devfn, where, size, value); @@ -252,7 +252,7 @@ static struct pci_ops quirk_pcie_aspm_ops = { */ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) { - int cap_base, i; + int i; struct pci_bus *pbus; struct pci_dev *dev; @@ -278,7 +278,7 @@ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) for (i = GET_INDEX(pdev->device, 0); i <= GET_INDEX(pdev->device, 7); ++i) quirk_aspm_offset[i] = 0; - pbus->ops = pbus->parent->ops; + pci_bus_set_ops(pbus, pbus->parent->ops); } else { /* * If devices are attached to the root port at power-up or @@ -286,13 +286,15 @@ static void pcie_rootport_aspm_quirk(struct pci_dev *pdev) * each root port to save the register offsets and replace the * bus ops. */ - list_for_each_entry(dev, &pbus->devices, bus_list) { + list_for_each_entry(dev, &pbus->devices, bus_list) /* There are 0 to 8 devices attached to this bus */ - cap_base = pci_find_capability(dev, PCI_CAP_ID_EXP); - quirk_aspm_offset[GET_INDEX(pdev->device, dev->devfn)] = cap_base + 0x10; - } - pbus->ops = &quirk_pcie_aspm_ops; + quirk_aspm_offset[GET_INDEX(pdev->device, dev->devfn)] = + dev->pcie_cap + PCI_EXP_LNKCTL; + + pci_bus_set_ops(pbus, &quirk_pcie_aspm_ops); + dev_info(&pbus->dev, "writes to ASPM control bits will be ignored\n"); } + } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA, pcie_rootport_aspm_quirk); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PA1, pcie_rootport_aspm_quirk); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 48e8461057ba..5eee4959785d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -382,7 +382,14 @@ static void xen_teardown_msi_irq(unsigned int irq) { xen_destroy_irq(irq); } - +static u32 xen_nop_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +{ + return 0; +} +static u32 xen_nop_msix_mask_irq(struct msi_desc *desc, u32 flag) +{ + return 0; +} #endif int __init pci_xen_init(void) @@ -406,6 +413,8 @@ int __init pci_xen_init(void) x86_msi.setup_msi_irqs = xen_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs; + x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; + x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; #endif return 0; } @@ -485,6 +494,8 @@ int __init pci_xen_initial_domain(void) x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; + x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; + x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; #endif xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index fef7d0ba7e3a..649a12befba9 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -40,16 +40,9 @@ static bool lid_wake_on_close; */ static int set_lid_wake_behavior(bool wake_on_close) { - struct acpi_object_list arg_list; - union acpi_object arg; acpi_status status; - arg_list.count = 1; - arg_list.pointer = &arg; - arg.type = ACPI_TYPE_INTEGER; - arg.integer.value = wake_on_close; - - status = acpi_evaluate_object(NULL, "\\_SB.PCI0.LID.LIDW", &arg_list, NULL); + status = acpi_execute_simple_method(NULL, "\\_SB.PCI0.LID.LIDW", wake_on_close); if (ACPI_FAILURE(status)) { pr_warning(PFX "failed to set lid behavior\n"); return 1; diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 6bb49b687c97..7bb89a27a5e4 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -11,8 +11,7 @@ Elf32_Half elf_core_extra_phdrs(void) return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; } -int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, - unsigned long limit) +int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = @@ -32,17 +31,14 @@ int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, phdr.p_offset += ofs; } phdr.p_paddr = 0; /* match other core phdrs */ - *size += sizeof(phdr); - if (*size > limit - || !dump_write(file, &phdr, sizeof(phdr))) + if (!dump_emit(cprm, &phdr, sizeof(phdr))) return 0; } } return 1; } -int elf_core_write_extra_data(struct file *file, size_t *size, - unsigned long limit) +int elf_core_write_extra_data(struct coredump_params *cprm) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = @@ -55,10 +51,7 @@ int elf_core_write_extra_data(struct file *file, size_t *size, if (phdrp[i].p_type == PT_LOAD) { void *addr = (void *) phdrp[i].p_vaddr; size_t filesz = phdrp[i].p_filesz; - - *size += filesz; - if (*size > limit - || !dump_write(file, addr, filesz)) + if (!dump_emit(cprm, addr, filesz)) return 0; } } diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 72074d528400..2ada505067cc 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->wall_time_snsec; @@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts) ts->tv_nsec = 0; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->monotonic_time_sec; ns = gtod->monotonic_time_snsec; @@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); ts->tv_sec = gtod->wall_time_coarse.tv_sec; ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqcount_begin(>od->seq); + seq = read_seqcount_begin_no_lockdep(>od->seq); ts->tv_sec = gtod->monotonic_time_coarse.tv_sec; ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec; } while (unlikely(read_seqcount_retry(>od->seq, seq))); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index fdc3ba28ca38..ce563be09cc1 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -468,8 +468,8 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val); * 3 PCD PWT UC UC UC * 4 PAT WB WC WB * 5 PAT PWT WC WP WT - * 6 PAT PCD UC- UC UC- - * 7 PAT PCD PWT UC UC UC + * 6 PAT PCD UC- rsv UC- + * 7 PAT PCD PWT UC rsv UC */ void xen_set_pat(u64 pat) @@ -796,8 +796,8 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) { spinlock_t *ptl = NULL; -#if USE_SPLIT_PTLOCKS - ptl = __pte_lockptr(page); +#if USE_SPLIT_PTE_PTLOCKS + ptl = ptlock_ptr(page); spin_lock_nest_lock(ptl, &mm->page_table_lock); #endif @@ -1637,7 +1637,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTLOCKS) + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); xen_mc_issue(PARAVIRT_LAZY_MMU); @@ -1671,7 +1671,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level) if (!PageHighMem(page)) { xen_mc_batch(); - if (level == PT_PTE && USE_SPLIT_PTLOCKS) + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); __set_pfn_prot(pfn, PAGE_KERNEL); @@ -2328,12 +2328,14 @@ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in, return success; } -int xen_create_contiguous_region(unsigned long vstart, unsigned int order, - unsigned int address_bits) +int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, + unsigned int address_bits, + dma_addr_t *dma_handle) { unsigned long *in_frames = discontig_frames, out_frame; unsigned long flags; int success; + unsigned long vstart = (unsigned long)phys_to_virt(pstart); /* * Currently an auto-translated guest will not perform I/O, nor will @@ -2368,15 +2370,17 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order, spin_unlock_irqrestore(&xen_reservation_lock, flags); + *dma_handle = virt_to_machine(vstart).maddr; return success ? 0 : -ENOMEM; } EXPORT_SYMBOL_GPL(xen_create_contiguous_region); -void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) +void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { unsigned long *out_frames = discontig_frames, in_frame; unsigned long flags; int success; + unsigned long vstart; if (xen_feature(XENFEAT_auto_translated_physmap)) return; @@ -2384,6 +2388,7 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) if (unlikely(order > MAX_CONTIG_ORDER)) return; + vstart = (unsigned long)phys_to_virt(pstart); memset((void *) vstart, 0, PAGE_SIZE << order); spin_lock_irqsave(&xen_reservation_lock, flags); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index a61c7d5811be..2ae8699e8767 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -799,10 +799,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) { unsigned topidx, mididx, idx; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + /* don't track P2M changes in autotranslate guests */ + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) return true; - } + if (unlikely(pfn >= MAX_P2M_PFN)) { BUG_ON(mfn != INVALID_P2M_ENTRY); return true; diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 969570491c39..0e98e5d241d0 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -75,8 +75,10 @@ void __init pci_xen_swiotlb_init(void) xen_swiotlb_init(1, true /* early */); dma_ops = &xen_swiotlb_dma_ops; +#ifdef CONFIG_PCI /* Make sure ACS will be enabled */ pci_request_acs(); +#endif } } @@ -92,8 +94,10 @@ int pci_xen_swiotlb_init_late(void) return rc; dma_ops = &xen_swiotlb_dma_ops; +#ifdef CONFIG_PCI /* Make sure ACS will be enabled */ pci_request_acs(); +#endif return 0; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 09f3059cb00b..68c054f59de6 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -556,7 +556,7 @@ void xen_enable_syscall(void) } #endif /* CONFIG_X86_64 */ } -void __cpuinit xen_enable_nmi(void) +void xen_enable_nmi(void) { #ifdef CONFIG_X86_64 if (register_callback(CALLBACKTYPE_nmi, nmi)) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 31d04758b76f..c36b325abd83 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -149,7 +149,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, xen_reschedule_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, resched_name, NULL); if (rc < 0) @@ -161,7 +161,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, xen_call_function_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, callfunc_name, NULL); if (rc < 0) @@ -171,7 +171,7 @@ static int xen_smp_intr_init(unsigned int cpu) debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, - IRQF_DISABLED | IRQF_PERCPU | IRQF_NOBALANCING, + IRQF_PERCPU | IRQF_NOBALANCING, debug_name, NULL); if (rc < 0) goto fail; @@ -182,7 +182,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, xen_call_function_single_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, callfunc_name, NULL); if (rc < 0) @@ -201,7 +201,7 @@ static int xen_smp_intr_init(unsigned int cpu) rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR, cpu, xen_irq_work_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, callfunc_name, NULL); if (rc < 0) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index be6b86078957..0e36cde12f7e 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -234,7 +234,7 @@ void xen_init_lock_cpu(int cpu) irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR, cpu, dummy_handler, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING, + IRQF_PERCPU|IRQF_NOBALANCING, name, NULL); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index ee365895b06b..12a1ca707b94 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -443,8 +443,7 @@ void xen_setup_timer(int cpu) name = "<timer kasprintf failed>"; irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, - IRQF_DISABLED|IRQF_PERCPU| - IRQF_NOBALANCING|IRQF_TIMER| + IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER| IRQF_FORCE_RESUME, name, NULL); |
