diff options
| -rw-r--r-- | arch/x86/include/asm/bug.h | 9 | ||||
| -rw-r--r-- | arch/x86/include/asm/idtentry.h | 15 | ||||
| -rw-r--r-- | arch/x86/include/asm/msr.h | 4 | ||||
| -rw-r--r-- | arch/x86/include/asm/page_64.h | 33 | ||||
| -rw-r--r-- | arch/x86/include/asm/page_64_types.h | 23 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/common.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/monitor.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/nmi.c | 10 | ||||
| -rw-r--r-- | arch/x86/kernel/smpboot.c | 3 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/svm.c | 39 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 55 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 9 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.h | 45 | ||||
| -rw-r--r-- | include/linux/context_tracking.h | 92 | ||||
| -rw-r--r-- | include/linux/kvm_host.h | 45 | ||||
| -rw-r--r-- | include/linux/vtime.h | 108 |
16 files changed, 263 insertions, 233 deletions
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 297fa12e7e27..84b87538a15d 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -7,18 +7,9 @@ /* * Despite that some emulators terminate on UD2, we use it for WARN(). - * - * Since various instruction decoders/specs disagree on the encoding of - * UD0/UD1. */ - -#define ASM_UD0 ".byte 0x0f, 0xff" /* + ModRM (for Intel) */ -#define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */ #define ASM_UD2 ".byte 0x0f, 0x0b" - -#define INSN_UD0 0xff0f #define INSN_UD2 0x0b0f - #define LEN_UD2 2 #ifdef CONFIG_GENERIC_BUG diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index e35e342673c7..73d45b0dfff2 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -588,6 +588,21 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC, xenpv_exc_machine_check); #endif /* NMI */ + +#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) +/* + * Special NOIST entry point for VMX which invokes this on the kernel + * stack. asm_exc_nmi() requires an IST to work correctly vs. the NMI + * 'executing' marker. + * + * On 32bit this just uses the regular NMI entry point because 32-bit does + * not have ISTs. + */ +DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_noist); +#else +#define asm_exc_nmi_noist asm_exc_nmi +#endif + DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); #ifdef CONFIG_XEN_PV DECLARE_IDTENTRY_RAW(X86_TRAP_NMI, xenpv_exc_nmi); diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index e16cccdd0420..a3f87f1015d3 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -324,10 +324,6 @@ static inline int wrmsrl_safe(u32 msr, u64 val) return wrmsr_safe(msr, (u32)val, (u32)(val >> 32)); } -#define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high)) - -#define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0) - struct msr *msrs_alloc(void); void msrs_free(struct msr *msrs); int msr_set_bit(u32 msr, u8 bit); diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 939b1cff4a7b..ca840fec7776 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -56,6 +56,39 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); +#ifdef CONFIG_X86_5LEVEL +/* + * User space process size. This is the first address outside the user range. + * There are a few constraints that determine this: + * + * On Intel CPUs, if a SYSCALL instruction is at the highest canonical + * address, then that syscall will enter the kernel with a + * non-canonical return address, and SYSRET will explode dangerously. + * We avoid this particular problem by preventing anything + * from being mapped at the maximum canonical address. + * + * On AMD CPUs in the Ryzen family, there's a nasty bug in which the + * CPUs malfunction if they execute code from the highest canonical page. + * They'll speculate right off the end of the canonical space, and + * bad things happen. This is worked around in the same way as the + * Intel problem. + * + * With page table isolation enabled, we map the LDT in ... [stay tuned] + */ +static inline unsigned long task_size_max(void) +{ + unsigned long ret; + + alternative_io("movq %[small],%0","movq %[large],%0", + X86_FEATURE_LA57, + "=r" (ret), + [small] "i" ((1ul << 47)-PAGE_SIZE), + [large] "i" ((1ul << 56)-PAGE_SIZE)); + + return ret; +} +#endif /* CONFIG_X86_5LEVEL */ + #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 64297eabad63..a8d4ad856568 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -55,30 +55,13 @@ #ifdef CONFIG_X86_5LEVEL #define __VIRTUAL_MASK_SHIFT (pgtable_l5_enabled() ? 56 : 47) +/* See task_size_max() in <asm/page_64.h> */ #else #define __VIRTUAL_MASK_SHIFT 47 +#define task_size_max() ((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE) #endif -/* - * User space process size. This is the first address outside the user range. - * There are a few constraints that determine this: - * - * On Intel CPUs, if a SYSCALL instruction is at the highest canonical - * address, then that syscall will enter the kernel with a - * non-canonical return address, and SYSRET will explode dangerously. - * We avoid this particular problem by preventing anything - * from being mapped at the maximum canonical address. - * - * On AMD CPUs in the Ryzen family, there's a nasty bug in which the - * CPUs malfunction if they execute code from the highest canonical page. - * They'll speculate right off the end of the canonical space, and - * bad things happen. This is worked around in the same way as the - * Intel problem. - * - * With page table isolation enabled, we map the LDT in ... [stay tuned] - */ -#define TASK_SIZE_MAX ((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE) - +#define TASK_SIZE_MAX task_size_max() #define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE) /* This decides where the kernel will search for a free chunk of vm diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6bdb69a9a7dc..a1b756c49a93 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1851,8 +1851,8 @@ static inline void setup_getcpu(int cpu) unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); struct desc_struct d = { }; - if (boot_cpu_has(X86_FEATURE_RDTSCP)) - write_rdtscp_aux(cpudata); + if (boot_cpu_has(X86_FEATURE_RDTSCP) || boot_cpu_has(X86_FEATURE_RDPID)) + wrmsr(MSR_TSC_AUX, cpudata, 0); /* Store CPU and node number in limit. */ d.limit0 = cpudata; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index dbeaa8409313..f07c10b87a87 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -84,7 +84,7 @@ unsigned int resctrl_cqm_threshold; static const struct mbm_correction_factor_table { u32 rmidthreshold; u64 cf; -} mbm_cf_table[] __initdata = { +} mbm_cf_table[] __initconst = { {7, CF(1.000000)}, {15, CF(1.000000)}, {15, CF(0.969650)}, diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index bf250a339655..2ef961cf4cfc 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -524,6 +524,16 @@ nmi_restart: mds_user_clear_cpu_buffers(); } +#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) +DEFINE_IDTENTRY_RAW(exc_nmi_noist) +{ + exc_nmi(regs); +} +#endif +#if IS_MODULE(CONFIG_KVM_INTEL) +EXPORT_SYMBOL_GPL(asm_exc_nmi_noist); +#endif + void stop_nmi(void) { ignore_nmis++; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7ffb0cf3f997..0ad5214f598a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1865,9 +1865,6 @@ static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) return true; } -#include <asm/cpu_device_id.h> -#include <asm/intel-family.h> - #define X86_MATCH(model) \ X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9790c73f2a32..b649f92287a2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3710,25 +3710,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); unsigned long vmcb_pa = svm->current_vmcb->pa; - /* - * VMENTER enables interrupts (host state), but the kernel state is - * interrupts disabled when this is invoked. Also tell RCU about - * it. This is the same logic as for exit_to_user_mode(). - * - * This ensures that e.g. latency analysis on the host observes - * guest mode as interrupt enabled. - * - * guest_enter_irqoff() informs context tracking about the - * transition to guest mode and if enabled adjusts RCU state - * accordingly. - */ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - instrumentation_end(); - - guest_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); + kvm_guest_enter_irqoff(); if (sev_es_guest(vcpu->kvm)) { __svm_sev_es_vcpu_run(vmcb_pa); @@ -3748,24 +3730,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) vmload(__sme_page_pa(sd->save_area)); } - /* - * VMEXIT disables interrupts (host state), but tracing and lockdep - * have them in state 'on' as recorded before entering guest mode. - * Same as enter_from_user_mode(). - * - * guest_exit_irqoff() restores host context and reinstates RCU if - * enabled and required. - * - * This needs to be done before the below as native_read_msr() - * contains a tracepoint and x86_spec_ctrl_restore_host() calls - * into world and some more. - */ - lockdep_hardirqs_off(CALLER_ADDR0); - guest_exit_irqoff(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - instrumentation_end(); + kvm_guest_exit_irqoff(); } static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index cbe0cdade38a..d000cddbd734 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -36,6 +36,7 @@ #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/fpu/internal.h> +#include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> #include <asm/kexec.h> @@ -6415,18 +6416,17 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) void vmx_do_interrupt_nmi_irqoff(unsigned long entry); -static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) +static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, + unsigned long entry) { - unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - gate_desc *desc = (gate_desc *)host_idt_base + vector; - kvm_before_interrupt(vcpu); - vmx_do_interrupt_nmi_irqoff(gate_offset(desc)); + vmx_do_interrupt_nmi_irqoff(entry); kvm_after_interrupt(vcpu); } static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) { + const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist; u32 intr_info = vmx_get_intr_info(&vmx->vcpu); /* if exit due to PF check for async PF */ @@ -6437,18 +6437,20 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ else if (is_nmi(intr_info)) - handle_interrupt_nmi_irqoff(&vmx->vcpu, intr_info); + handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) { u32 intr_info = vmx_get_intr_info(vcpu); + unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; + gate_desc *desc = (gate_desc *)host_idt_base + vector; if (WARN_ONCE(!is_external_intr(intr_info), "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; - handle_interrupt_nmi_irqoff(vcpu, intr_info); + handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) @@ -6662,25 +6664,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - /* - * VMENTER enables interrupts (host state), but the kernel state is - * interrupts disabled when this is invoked. Also tell RCU about - * it. This is the same logic as for exit_to_user_mode(). - * - * This ensures that e.g. latency analysis on the host observes - * guest mode as interrupt enabled. - * - * guest_enter_irqoff() informs context tracking about the - * transition to guest mode and if enabled adjusts RCU state - * accordingly. - */ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - instrumentation_end(); - - guest_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); + kvm_guest_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) @@ -6696,24 +6680,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vcpu->arch.cr2 = native_read_cr2(); - /* - * VMEXIT disables interrupts (host state), but tracing and lockdep - * have them in state 'on' as recorded before entering guest mode. - * Same as enter_from_user_mode(). - * - * guest_exit_irqoff() restores host context and reinstates RCU if - * enabled and required. - * - * This needs to be done before the below as native_read_msr() - * contains a tracepoint and x86_spec_ctrl_restore_host() calls - * into world and some more. - */ - lockdep_hardirqs_off(CALLER_ADDR0); - guest_exit_irqoff(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - instrumentation_end(); + kvm_guest_exit_irqoff(); } static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cebdaa1e3cf5..6eda2834fc05 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9315,6 +9315,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) local_irq_disable(); kvm_after_interrupt(vcpu); + /* + * Wait until after servicing IRQs to account guest time so that any + * ticks that occurred while running the guest are properly accounted + * to the guest. Waiting until IRQs are enabled degrades the accuracy + * of accounting via context tracking, but the loss of accuracy is + * acceptable for all known use cases. + */ + vtime_account_guest_exit(); + if (lapic_in_kernel(vcpu)) { s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta; if (delta != S64_MIN) { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 8ddd38146525..521f74e5bbf2 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -8,6 +8,51 @@ #include "kvm_cache_regs.h" #include "kvm_emulate.h" +static __always_inline void kvm_guest_enter_irqoff(void) +{ + /* + * VMENTER enables interrupts (host state), but the kernel state is + * interrupts disabled when this is invoked. Also tell RCU about + * it. This is the same logic as for exit_to_user_mode(). + * + * This ensures that e.g. latency analysis on the host observes + * guest mode as interrupt enabled. + * + * guest_enter_irqoff() informs context tracking about the + * transition to guest mode and if enabled adjusts RCU state + * accordingly. + */ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + instrumentation_end(); + + guest_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +static __always_inline void kvm_guest_exit_irqoff(void) +{ + /* + * VMEXIT disables interrupts (host state), but tracing and lockdep + * have them in state 'on' as recorded before entering guest mode. + * Same as enter_from_user_mode(). + * + * context_tracking_guest_exit() restores host context and reinstates + * RCU if enabled and required. + * + * This needs to be done immediately after VM-Exit, before any code + * that might contain tracepoints or call out to the greater world, + * e.g. before x86_spec_ctrl_restore_host(). + */ + lockdep_hardirqs_off(CALLER_ADDR0); + context_tracking_guest_exit(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \ ({ \ bool failed = (consistency_check); \ diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index bceb06498521..4d7fced3a39f 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -71,6 +71,19 @@ static inline void exception_exit(enum ctx_state prev_ctx) } } +static __always_inline bool context_tracking_guest_enter(void) +{ + if (context_tracking_enabled()) + __context_tracking_enter(CONTEXT_GUEST); + + return context_tracking_enabled_this_cpu(); +} + +static __always_inline void context_tracking_guest_exit(void) +{ + if (context_tracking_enabled()) + __context_tracking_exit(CONTEXT_GUEST); +} /** * ct_state() - return the current context tracking state if known @@ -92,6 +105,9 @@ static inline void user_exit_irqoff(void) { } static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } +static inline bool context_tracking_guest_enter(void) { return false; } +static inline void context_tracking_guest_exit(void) { } + #endif /* !CONFIG_CONTEXT_TRACKING */ #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) @@ -102,80 +118,4 @@ extern void context_tracking_init(void); static inline void context_tracking_init(void) { } #endif /* CONFIG_CONTEXT_TRACKING_FORCE */ - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -/* must be called with irqs disabled */ -static __always_inline void guest_enter_irqoff(void) -{ - instrumentation_begin(); - if (vtime_accounting_enabled_this_cpu()) - vtime_guest_enter(current); - else - current->flags |= PF_VCPU; - instrumentation_end(); - - if (context_tracking_enabled()) - __context_tracking_enter(CONTEXT_GUEST); - - /* KVM does not hold any references to rcu protected data when it - * switches CPU into a guest mode. In fact switching to a guest mode - * is very similar to exiting to userspace from rcu point of view. In - * addition CPU may stay in a guest mode for quite a long time (up to - * one time slice). Lets treat guest mode as quiescent state, just like - * we do with user-mode execution. - */ - if (!context_tracking_enabled_this_cpu()) { - instrumentation_begin(); - rcu_virt_note_context_switch(smp_processor_id()); - instrumentation_end(); - } -} - -static __always_inline void guest_exit_irqoff(void) -{ - if (context_tracking_enabled()) - __context_tracking_exit(CONTEXT_GUEST); - - instrumentation_begin(); - if (vtime_accounting_enabled_this_cpu()) - vtime_guest_exit(current); - else - current->flags &= ~PF_VCPU; - instrumentation_end(); -} - -#else -static __always_inline void guest_enter_irqoff(void) -{ - /* - * This is running in ioctl context so its safe - * to assume that it's the stime pending cputime - * to flush. - */ - instrumentation_begin(); - vtime_account_kernel(current); - current->flags |= PF_VCPU; - rcu_virt_note_context_switch(smp_processor_id()); - instrumentation_end(); -} - -static __always_inline void guest_exit_irqoff(void) -{ - instrumentation_begin(); - /* Flush the guest cputime we spent on the guest */ - vtime_account_kernel(current); - current->flags &= ~PF_VCPU; - instrumentation_end(); -} -#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ - -static inline void guest_exit(void) -{ - unsigned long flags; - - local_irq_save(flags); - guest_exit_irqoff(); - local_irq_restore(flags); -} - #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8895b95b6a22..2f34487e21f2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -338,6 +338,51 @@ struct kvm_vcpu { struct kvm_dirty_ring dirty_ring; }; +/* must be called with irqs disabled */ +static __always_inline void guest_enter_irqoff(void) +{ + /* + * This is running in ioctl context so its safe to assume that it's the + * stime pending cputime to flush. + */ + instrumentation_begin(); + vtime_account_guest_enter(); + instrumentation_end(); + + /* + * KVM does not hold any references to rcu protected data when it + * switches CPU into a guest mode. In fact switching to a guest mode + * is very similar to exiting to userspace from rcu point of view. In + * addition CPU may stay in a guest mode for quite a long time (up to + * one time slice). Lets treat guest mode as quiescent state, just like + * we do with user-mode execution. + */ + if (!context_tracking_guest_enter()) { + instrumentation_begin(); + rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); + } +} + +static __always_inline void guest_exit_irqoff(void) +{ + context_tracking_guest_exit(); + + instrumentation_begin(); + /* Flush the guest cputime we spent on the guest */ + vtime_account_guest_exit(); + instrumentation_end(); +} + +static inline void guest_exit(void) +{ + unsigned long flags; + + local_irq_save(flags); + guest_exit_irqoff(); + local_irq_restore(flags); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 041d6524d144..3684487d01e1 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -3,12 +3,46 @@ #define _LINUX_KERNEL_VTIME_H #include <linux/context_tracking_state.h> +#include <linux/sched.h> + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <asm/vtime.h> #endif +/* + * Common vtime APIs + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +extern void vtime_account_kernel(struct task_struct *tsk); +extern void vtime_account_idle(struct task_struct *tsk); +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ -struct task_struct; +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void arch_vtime_task_switch(struct task_struct *tsk); +extern void vtime_user_enter(struct task_struct *tsk); +extern void vtime_user_exit(struct task_struct *tsk); +extern void vtime_guest_enter(struct task_struct *tsk); +extern void vtime_guest_exit(struct task_struct *tsk); +extern void vtime_init_idle(struct task_struct *tsk, int cpu); +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ +static inline void vtime_user_enter(struct task_struct *tsk) { } +static inline void vtime_user_exit(struct task_struct *tsk) { } +static inline void vtime_guest_enter(struct task_struct *tsk) { } +static inline void vtime_guest_exit(struct task_struct *tsk) { } +static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } +#endif + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset); +extern void vtime_account_softirq(struct task_struct *tsk); +extern void vtime_account_hardirq(struct task_struct *tsk); +extern void vtime_flush(struct task_struct *tsk); +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { } +static inline void vtime_account_softirq(struct task_struct *tsk) { } +static inline void vtime_account_hardirq(struct task_struct *tsk) { } +static inline void vtime_flush(struct task_struct *tsk) { } +#endif /* * vtime_accounting_enabled_this_cpu() definitions/declarations @@ -18,6 +52,18 @@ struct task_struct; static inline bool vtime_accounting_enabled_this_cpu(void) { return true; } extern void vtime_task_switch(struct task_struct *prev); +static __always_inline void vtime_account_guest_enter(void) +{ + vtime_account_kernel(current); + current->flags |= PF_VCPU; +} + +static __always_inline void vtime_account_guest_exit(void) +{ + vtime_account_kernel(current); + current->flags &= ~PF_VCPU; +} + #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) /* @@ -49,49 +95,37 @@ static inline void vtime_task_switch(struct task_struct *prev) vtime_task_switch_generic(prev); } +static __always_inline void vtime_account_guest_enter(void) +{ + if (vtime_accounting_enabled_this_cpu()) + vtime_guest_enter(current); + else + current->flags |= PF_VCPU; +} + +static __always_inline void vtime_account_guest_exit(void) +{ + if (vtime_accounting_enabled_this_cpu()) + vtime_guest_exit(current); + else + current->flags &= ~PF_VCPU; +} + #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ -static inline bool vtime_accounting_enabled_cpu(int cpu) {return false; } static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } -#endif - -/* - * Common vtime APIs - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void vtime_account_kernel(struct task_struct *tsk); -extern void vtime_account_idle(struct task_struct *tsk); -#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ -static inline void vtime_account_kernel(struct task_struct *tsk) { } -#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ +static __always_inline void vtime_account_guest_enter(void) +{ + current->flags |= PF_VCPU; +} -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void arch_vtime_task_switch(struct task_struct *tsk); -extern void vtime_user_enter(struct task_struct *tsk); -extern void vtime_user_exit(struct task_struct *tsk); -extern void vtime_guest_enter(struct task_struct *tsk); -extern void vtime_guest_exit(struct task_struct *tsk); -extern void vtime_init_idle(struct task_struct *tsk, int cpu); -#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -static inline void vtime_user_enter(struct task_struct *tsk) { } -static inline void vtime_user_exit(struct task_struct *tsk) { } -static inline void vtime_guest_enter(struct task_struct *tsk) { } -static inline void vtime_guest_exit(struct task_struct *tsk) { } -static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } -#endif +static __always_inline void vtime_account_guest_exit(void) +{ + current->flags &= ~PF_VCPU; +} -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset); -extern void vtime_account_softirq(struct task_struct *tsk); -extern void vtime_account_hardirq(struct task_struct *tsk); -extern void vtime_flush(struct task_struct *tsk); -#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ -static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { } -static inline void vtime_account_softirq(struct task_struct *tsk) { } -static inline void vtime_account_hardirq(struct task_struct *tsk) { } -static inline void vtime_flush(struct task_struct *tsk) { } #endif |