From 8c3ba334f8588e1d5099f8602cf01897720e0eca Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 18 Jul 2011 17:17:15 +0300 Subject: KVM: x86: Raise the hard VCPU count limit The patch raises the hard limit of VCPU count to 254. This will allow developers to easily work on scalability and will allow users to test high VCPU setups easily without patching the kernel. To prevent possible issues with current setups, KVM_CAP_NR_VCPUS now returns the recommended VCPU limit (which is still 64) - this should be a safe value for everybody, while a new KVM_CAP_MAX_VCPUS returns the hard limit which is now 254. Cc: Avi Kivity Cc: Ingo Molnar Cc: Marcelo Tosatti Cc: Pekka Enberg Suggested-by: Pekka Enberg Signed-off-by: Sasha Levin Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd51c83aa5de..c00ec28e7147 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -26,7 +26,8 @@ #include #include -#define KVM_MAX_VCPUS 64 +#define KVM_MAX_VCPUS 254 +#define KVM_SOFT_MAX_VCPUS 64 #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 -- cgit v1.2.3 From 0d460ffc0956d2dbe12ca9f5f6aa0f8701ea9d73 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Fri, 22 Jul 2011 12:46:53 +0100 Subject: KVM: Use __print_symbolic() for vmexit tracepoints The vmexit tracepoints format the exit_reason to make it human-readable. Since the exit_reason depends on the instruction set (vmx or svm), formatting is handled with ftrace_print_symbols_seq() by referring to the appropriate exit reason table. However, the ftrace_print_symbols_seq() function is not meant to be used directly in tracepoints since it does not export the formatting table which userspace tools like trace-cmd and perf use to format traces. In practice perf dies when formatting vmexit-related events and trace-cmd falls back to printing the numeric value (with extra formatting code in the kvm plugin to paper over this limitation). Other userspace consumers of vmexit-related tracepoints would be in similar trouble. To avoid significant changes to the kvm_exit tracepoint, this patch moves the vmx and svm exit reason tables into arch/x86/kvm/trace.h and selects the right table with __print_symbolic() depending on the instruction set. Note that __print_symbolic() is designed for exporting the formatting table to userspace and allows trace-cmd and perf to work. Signed-off-by: Stefan Hajnoczi Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 2 - arch/x86/kvm/svm.c | 55 --------------------- arch/x86/kvm/trace.h | 106 +++++++++++++++++++++++++++++++++++++--- arch/x86/kvm/vmx.c | 44 ----------------- 4 files changed, 100 insertions(+), 107 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c00ec28e7147..307e3cfa28ad 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -635,8 +635,6 @@ struct kvm_x86_ops { int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage); - - const struct trace_print_flags *exit_reasons_str; }; struct kvm_arch_async_pf { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6adb7ba13a4a..2b24a88f2c67 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3899,60 +3899,6 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) } } -static const struct trace_print_flags svm_exit_reasons_str[] = { - { SVM_EXIT_READ_CR0, "read_cr0" }, - { SVM_EXIT_READ_CR3, "read_cr3" }, - { SVM_EXIT_READ_CR4, "read_cr4" }, - { SVM_EXIT_READ_CR8, "read_cr8" }, - { SVM_EXIT_WRITE_CR0, "write_cr0" }, - { SVM_EXIT_WRITE_CR3, "write_cr3" }, - { SVM_EXIT_WRITE_CR4, "write_cr4" }, - { SVM_EXIT_WRITE_CR8, "write_cr8" }, - { SVM_EXIT_READ_DR0, "read_dr0" }, - { SVM_EXIT_READ_DR1, "read_dr1" }, - { SVM_EXIT_READ_DR2, "read_dr2" }, - { SVM_EXIT_READ_DR3, "read_dr3" }, - { SVM_EXIT_WRITE_DR0, "write_dr0" }, - { SVM_EXIT_WRITE_DR1, "write_dr1" }, - { SVM_EXIT_WRITE_DR2, "write_dr2" }, - { SVM_EXIT_WRITE_DR3, "write_dr3" }, - { SVM_EXIT_WRITE_DR5, "write_dr5" }, - { SVM_EXIT_WRITE_DR7, "write_dr7" }, - { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, - { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, - { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, - { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, - { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, - { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, - { SVM_EXIT_INTR, "interrupt" }, - { SVM_EXIT_NMI, "nmi" }, - { SVM_EXIT_SMI, "smi" }, - { SVM_EXIT_INIT, "init" }, - { SVM_EXIT_VINTR, "vintr" }, - { SVM_EXIT_CPUID, "cpuid" }, - { SVM_EXIT_INVD, "invd" }, - { SVM_EXIT_HLT, "hlt" }, - { SVM_EXIT_INVLPG, "invlpg" }, - { SVM_EXIT_INVLPGA, "invlpga" }, - { SVM_EXIT_IOIO, "io" }, - { SVM_EXIT_MSR, "msr" }, - { SVM_EXIT_TASK_SWITCH, "task_switch" }, - { SVM_EXIT_SHUTDOWN, "shutdown" }, - { SVM_EXIT_VMRUN, "vmrun" }, - { SVM_EXIT_VMMCALL, "hypercall" }, - { SVM_EXIT_VMLOAD, "vmload" }, - { SVM_EXIT_VMSAVE, "vmsave" }, - { SVM_EXIT_STGI, "stgi" }, - { SVM_EXIT_CLGI, "clgi" }, - { SVM_EXIT_SKINIT, "skinit" }, - { SVM_EXIT_WBINVD, "wbinvd" }, - { SVM_EXIT_MONITOR, "monitor" }, - { SVM_EXIT_MWAIT, "mwait" }, - { SVM_EXIT_XSETBV, "xsetbv" }, - { SVM_EXIT_NPF, "npf" }, - { -1, NULL } -}; - static int svm_get_lpage_level(void) { return PT_PDPE_LEVEL; @@ -4225,7 +4171,6 @@ static struct kvm_x86_ops svm_x86_ops = { .get_mt_mask = svm_get_mt_mask, .get_exit_info = svm_get_exit_info, - .exit_reasons_str = svm_exit_reasons_str, .get_lpage_level = svm_get_lpage_level, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 4e1716bf88a4..911d2641f14c 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -2,6 +2,8 @@ #define _TRACE_KVM_H #include +#include +#include #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm @@ -181,6 +183,95 @@ TRACE_EVENT(kvm_apic, #define KVM_ISA_VMX 1 #define KVM_ISA_SVM 2 +#define VMX_EXIT_REASONS \ + { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ + { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ + { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ + { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ + { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ + { EXIT_REASON_CPUID, "CPUID" }, \ + { EXIT_REASON_HLT, "HLT" }, \ + { EXIT_REASON_INVLPG, "INVLPG" }, \ + { EXIT_REASON_RDPMC, "RDPMC" }, \ + { EXIT_REASON_RDTSC, "RDTSC" }, \ + { EXIT_REASON_VMCALL, "VMCALL" }, \ + { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ + { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ + { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ + { EXIT_REASON_VMPTRST, "VMPTRST" }, \ + { EXIT_REASON_VMREAD, "VMREAD" }, \ + { EXIT_REASON_VMRESUME, "VMRESUME" }, \ + { EXIT_REASON_VMWRITE, "VMWRITE" }, \ + { EXIT_REASON_VMOFF, "VMOFF" }, \ + { EXIT_REASON_VMON, "VMON" }, \ + { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ + { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ + { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ + { EXIT_REASON_MSR_READ, "MSR_READ" }, \ + { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ + { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ + { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ + { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ + { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ + { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ + { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ + { EXIT_REASON_WBINVD, "WBINVD" } + +#define SVM_EXIT_REASONS \ + { SVM_EXIT_READ_CR0, "read_cr0" }, \ + { SVM_EXIT_READ_CR3, "read_cr3" }, \ + { SVM_EXIT_READ_CR4, "read_cr4" }, \ + { SVM_EXIT_READ_CR8, "read_cr8" }, \ + { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ + { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ + { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ + { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ + { SVM_EXIT_READ_DR0, "read_dr0" }, \ + { SVM_EXIT_READ_DR1, "read_dr1" }, \ + { SVM_EXIT_READ_DR2, "read_dr2" }, \ + { SVM_EXIT_READ_DR3, "read_dr3" }, \ + { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ + { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ + { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ + { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ + { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ + { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ + { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ + { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ + { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ + { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ + { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ + { SVM_EXIT_INTR, "interrupt" }, \ + { SVM_EXIT_NMI, "nmi" }, \ + { SVM_EXIT_SMI, "smi" }, \ + { SVM_EXIT_INIT, "init" }, \ + { SVM_EXIT_VINTR, "vintr" }, \ + { SVM_EXIT_CPUID, "cpuid" }, \ + { SVM_EXIT_INVD, "invd" }, \ + { SVM_EXIT_HLT, "hlt" }, \ + { SVM_EXIT_INVLPG, "invlpg" }, \ + { SVM_EXIT_INVLPGA, "invlpga" }, \ + { SVM_EXIT_IOIO, "io" }, \ + { SVM_EXIT_MSR, "msr" }, \ + { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ + { SVM_EXIT_SHUTDOWN, "shutdown" }, \ + { SVM_EXIT_VMRUN, "vmrun" }, \ + { SVM_EXIT_VMMCALL, "hypercall" }, \ + { SVM_EXIT_VMLOAD, "vmload" }, \ + { SVM_EXIT_VMSAVE, "vmsave" }, \ + { SVM_EXIT_STGI, "stgi" }, \ + { SVM_EXIT_CLGI, "clgi" }, \ + { SVM_EXIT_SKINIT, "skinit" }, \ + { SVM_EXIT_WBINVD, "wbinvd" }, \ + { SVM_EXIT_MONITOR, "monitor" }, \ + { SVM_EXIT_MWAIT, "mwait" }, \ + { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_NPF, "npf" } + /* * Tracepoint for kvm guest exit: */ @@ -205,8 +296,9 @@ TRACE_EVENT(kvm_exit, ), TP_printk("reason %s rip 0x%lx info %llx %llx", - ftrace_print_symbols_seq(p, __entry->exit_reason, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS), __entry->guest_rip, __entry->info1, __entry->info2) ); @@ -512,8 +604,9 @@ TRACE_EVENT(kvm_nested_vmexit, TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", __entry->rip, - ftrace_print_symbols_seq(p, __entry->exit_code, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); @@ -548,8 +641,9 @@ TRACE_EVENT(kvm_nested_vmexit_inject, TP_printk("reason: %s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", - ftrace_print_symbols_seq(p, __entry->exit_code, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e65a158dee64..e26629fbf1d7 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6241,49 +6241,6 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return ret; } -#define _ER(x) { EXIT_REASON_##x, #x } - -static const struct trace_print_flags vmx_exit_reasons_str[] = { - _ER(EXCEPTION_NMI), - _ER(EXTERNAL_INTERRUPT), - _ER(TRIPLE_FAULT), - _ER(PENDING_INTERRUPT), - _ER(NMI_WINDOW), - _ER(TASK_SWITCH), - _ER(CPUID), - _ER(HLT), - _ER(INVLPG), - _ER(RDPMC), - _ER(RDTSC), - _ER(VMCALL), - _ER(VMCLEAR), - _ER(VMLAUNCH), - _ER(VMPTRLD), - _ER(VMPTRST), - _ER(VMREAD), - _ER(VMRESUME), - _ER(VMWRITE), - _ER(VMOFF), - _ER(VMON), - _ER(CR_ACCESS), - _ER(DR_ACCESS), - _ER(IO_INSTRUCTION), - _ER(MSR_READ), - _ER(MSR_WRITE), - _ER(MWAIT_INSTRUCTION), - _ER(MONITOR_INSTRUCTION), - _ER(PAUSE_INSTRUCTION), - _ER(MCE_DURING_VMENTRY), - _ER(TPR_BELOW_THRESHOLD), - _ER(APIC_ACCESS), - _ER(EPT_VIOLATION), - _ER(EPT_MISCONFIG), - _ER(WBINVD), - { -1, NULL } -}; - -#undef _ER - static int vmx_get_lpage_level(void) { if (enable_ept && !cpu_has_vmx_ept_1g_page()) @@ -7039,7 +6996,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .get_mt_mask = vmx_get_mt_mask, .get_exit_info = vmx_get_exit_info, - .exit_reasons_str = vmx_exit_reasons_str, .get_lpage_level = vmx_get_lpage_level, -- cgit v1.2.3 From e4e517b4be019787ada4cbbce2f04570c21b0cbd Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 28 Jul 2011 11:36:17 +0300 Subject: KVM: MMU: Do not unconditionally read PDPTE from guest memory Architecturally, PDPTEs are cached in the PDPTRs when CR3 is reloaded. On SVM, it is not possible to implement this, but on VMX this is possible and was indeed implemented until nested SVM changed this to unconditionally read PDPTEs dynamically. This has noticable impact when running PAE guests. Fix by changing the MMU to read PDPTRs from the cache, falling back to reading from memory for the nested MMU. Signed-off-by: Avi Kivity Tested-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/kvm_cache_regs.h | 7 ------- arch/x86/kvm/mmu.c | 5 ++++- arch/x86/kvm/paging_tmpl.h | 2 +- arch/x86/kvm/svm.c | 15 +++++++++++++++ 5 files changed, 21 insertions(+), 9 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 307e3cfa28ad..b31a3417a405 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -265,6 +265,7 @@ 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); int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 3377d53fcd36..544076c4f44b 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -45,13 +45,6 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) return vcpu->arch.walk_mmu->pdptrs[index]; } -static inline u64 kvm_pdptr_read_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, int index) -{ - load_pdptrs(vcpu, mmu, mmu->get_cr3(vcpu)); - - return mmu->pdptrs[index]; -} - static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8e8da7960dbe..f1b36cf3e3d0 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2770,7 +2770,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { - pdptr = kvm_pdptr_read_mmu(vcpu, &vcpu->arch.mmu, i); + pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i); if (!is_present_gpte(pdptr)) { vcpu->arch.mmu.pae_root[i] = 0; continue; @@ -3318,6 +3318,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->direct_map = true; context->set_cr3 = kvm_x86_ops->set_tdp_cr3; context->get_cr3 = get_cr3; + context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; context->nx = is_nx(vcpu); @@ -3376,6 +3377,7 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu) 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; @@ -3386,6 +3388,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; g_context->get_cr3 = get_cr3; + g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; /* diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 507e2b844cfa..f6dd9feb201b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -163,7 +163,7 @@ retry_walk: #if PTTYPE == 64 if (walker->level == PT32E_ROOT_LEVEL) { - pte = kvm_pdptr_read_mmu(vcpu, mmu, (addr >> 30) & 3); + pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); if (!is_present_gpte(pte)) goto error; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 2b24a88f2c67..f043168a5ab1 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1844,6 +1844,20 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) return svm->nested.nested_cr3; } +static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr3 = svm->nested.nested_cr3; + u64 pdpte; + int ret; + + ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); + if (ret) + return 0; + return pdpte; +} + static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) { @@ -1875,6 +1889,7 @@ static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3; vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3; + vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr; 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; -- cgit v1.2.3 From d5c1785d2f3aabe284d91bc7fc8f0abc58525dc9 Mon Sep 17 00:00:00 2001 From: Nadav Har'El Date: Tue, 2 Aug 2011 15:54:20 +0300 Subject: KVM: L1 TSC handling KVM assumed in several places that reading the TSC MSR returns the value for L1. This is incorrect, because when L2 is running, the correct TSC read exit emulation is to return L2's value. We therefore add a new x86_ops function, read_l1_tsc, to use in places that specifically need to read the L1 TSC, NOT the TSC of the current level of guest. Note that one change, of one line in kvm_arch_vcpu_load, is made redundant by a different patch sent by Zachary Amsden (and not yet applied): kvm_arch_vcpu_load() should not read the guest TSC, and if it didn't, of course we didn't have to change the call of kvm_get_msr() to read_l1_tsc(). [avi: moved callback to kvm_x86_ops tsc block] Signed-off-by: Nadav Har'El Acked-by: Zachary Amsdem Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm.c | 8 ++++++++ arch/x86/kvm/vmx.c | 16 ++++++++++++++++ arch/x86/kvm/x86.c | 8 ++++---- 4 files changed, 29 insertions(+), 4 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b31a3417a405..6ab4241c27cb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -630,6 +630,7 @@ struct kvm_x86_ops { void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); + u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f043168a5ab1..590d1d2d620b 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2910,6 +2910,13 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } +u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); + return vmcb->control.tsc_offset + + svm_scale_tsc(vcpu, native_read_tsc()); +} + static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4201,6 +4208,7 @@ static struct kvm_x86_ops svm_x86_ops = { .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset = svm_adjust_tsc_offset, .compute_tsc_offset = svm_compute_tsc_offset, + .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 03df703c8f20..97b64543d4ed 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1747,6 +1747,21 @@ static u64 guest_read_tsc(void) return host_tsc + tsc_offset; } +/* + * Like guest_read_tsc, but always returns L1's notion of the timestamp + * counter, even if a nested guest (L2) is currently running. + */ +u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu) +{ + u64 host_tsc, tsc_offset; + + rdtscll(host_tsc); + tsc_offset = is_guest_mode(vcpu) ? + to_vmx(vcpu)->nested.vmcs01_tsc_offset : + vmcs_read64(TSC_OFFSET); + return host_tsc + tsc_offset; +} + /* * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ * ioctl. In this case the call-back should update internal vmx state to make @@ -7010,6 +7025,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .write_tsc_offset = vmx_write_tsc_offset, .adjust_tsc_offset = vmx_adjust_tsc_offset, .compute_tsc_offset = vmx_compute_tsc_offset, + .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ea8f9f03e923..6b37f18a1663 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1098,7 +1098,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp); + tsc_timestamp = kvm_x86_ops->read_l1_tsc(v); kernel_ns = get_kernel_ns(); this_tsc_khz = vcpu_tsc_khz(v); if (unlikely(this_tsc_khz == 0)) { @@ -2218,7 +2218,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) s64 tsc_delta; u64 tsc; - kvm_get_msr(vcpu, MSR_IA32_TSC, &tsc); + tsc = kvm_x86_ops->read_l1_tsc(vcpu); tsc_delta = !vcpu->arch.last_guest_tsc ? 0 : tsc - vcpu->arch.last_guest_tsc; @@ -2242,7 +2242,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); } static int is_efer_nx(void) @@ -5729,7 +5729,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); -- cgit v1.2.3 From 58fbbf26eb01cf6d92cf18da8d14b3a4af9c4b47 Mon Sep 17 00:00:00 2001 From: Kevin Tian Date: Tue, 30 Aug 2011 13:56:17 +0300 Subject: KVM: APIC: avoid instruction emulation for EOI writes Instruction emulation for EOI writes can be skipped, since sane guest simply uses MOV instead of string operations. This is a nice improvement when guest doesn't support x2apic or hyper-V EOI support. a single VM bandwidth is observed with ~8% bandwidth improvement (7.4Gbps->8Gbps), by saving ~5% cycles from EOI emulation. Signed-off-by: Kevin Tian : Signed-off-by: Eddie Dong Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/include/asm/vmx.h | 12 ++++++++++++ arch/x86/kvm/lapic.c | 9 +++++++++ arch/x86/kvm/lapic.h | 1 + arch/x86/kvm/vmx.c | 21 +++++++++++++++++++++ 4 files changed, 43 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2caf290e9895..31f180c21ce9 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -350,6 +350,18 @@ enum vmcs_field { #define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */ +/* + * Exit Qualifications for APIC-Access + */ +#define APIC_ACCESS_OFFSET 0xfff /* 11:0, offset within the APIC page */ +#define APIC_ACCESS_TYPE 0xf000 /* 15:12, access type */ +#define TYPE_LINEAR_APIC_INST_READ (0 << 12) +#define TYPE_LINEAR_APIC_INST_WRITE (1 << 12) +#define TYPE_LINEAR_APIC_INST_FETCH (2 << 12) +#define TYPE_LINEAR_APIC_EVENT (3 << 12) +#define TYPE_PHYSICAL_APIC_EVENT (10 << 12) +#define TYPE_PHYSICAL_APIC_INST (15 << 12) + /* segment AR */ #define SEGMENT_AR_L_MASK (1 << 13) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 57dcbd4308fa..52645f283870 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -864,6 +864,15 @@ static int apic_mmio_write(struct kvm_io_device *this, return 0; } +void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (apic) + apic_reg_write(vcpu->arch.apic, APIC_EOI, 0); +} +EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); + void kvm_free_lapic(struct kvm_vcpu *vcpu) { if (!vcpu->arch.apic) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 52c9e6b9e725..82872432d475 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -26,6 +26,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); +void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5e8d411b0a81..47419d6031ea 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -71,6 +71,9 @@ module_param(vmm_exclusive, bool, S_IRUGO); static int __read_mostly yield_on_hlt = 1; module_param(yield_on_hlt, bool, S_IRUGO); +static int __read_mostly fasteoi = 1; +module_param(fasteoi, bool, S_IRUGO); + /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not @@ -4540,6 +4543,24 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) static int handle_apic_access(struct kvm_vcpu *vcpu) { + if (likely(fasteoi)) { + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + int access_type, offset; + + access_type = exit_qualification & APIC_ACCESS_TYPE; + offset = exit_qualification & APIC_ACCESS_OFFSET; + /* + * Sane guest uses MOV to write EOI, with written value + * not cared. So make a short-circuit here by avoiding + * heavy instruction emulation. + */ + if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) && + (offset == APIC_EOI)) { + kvm_lapic_set_eoi(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + } return emulate_instruction(vcpu, 0) == EMULATE_DONE; } -- cgit v1.2.3 From f09ed83e211d253809e575e05bd4de1e335c0cb2 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Tue, 13 Sep 2011 10:45:40 +0300 Subject: KVM: x86 emulator: move memop, memopp into emulation context Simplifies further generalization of decode. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_emulate.h | 2 ++ arch/x86/kvm/emulate.c | 34 +++++++++++++++++----------------- 2 files changed, 19 insertions(+), 17 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 6040d115ef51..56bac3e3423e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -275,6 +275,8 @@ struct x86_emulate_ctxt { unsigned long _eip; /* Fields above regs are cleared together. */ unsigned long regs[NR_VCPU_REGS]; + struct operand memop; + struct operand *memopp; struct fetch_cache fetch; struct read_cache io_read; struct read_cache mem_read; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ed819bdf475d..58172fb9a09a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3323,8 +3323,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) int def_op_bytes, def_ad_bytes, goffset, simd_prefix; bool op_prefix = false; struct opcode opcode; - struct operand memop = { .type = OP_NONE }, *memopp = NULL; + ctxt->memop.type = OP_NONE; + ctxt->memopp = NULL; ctxt->_eip = ctxt->eip; ctxt->fetch.start = ctxt->_eip; ctxt->fetch.end = ctxt->fetch.start + insn_len; @@ -3482,21 +3483,21 @@ done_prefixes: /* ModRM and SIB bytes. */ if (ctxt->d & ModRM) { - rc = decode_modrm(ctxt, &memop); + rc = decode_modrm(ctxt, &ctxt->memop); if (!ctxt->has_seg_override) set_seg_override(ctxt, ctxt->modrm_seg); } else if (ctxt->d & MemAbs) - rc = decode_abs(ctxt, &memop); + rc = decode_abs(ctxt, &ctxt->memop); if (rc != X86EMUL_CONTINUE) goto done; if (!ctxt->has_seg_override) set_seg_override(ctxt, VCPU_SREG_DS); - memop.addr.mem.seg = seg_override(ctxt); + ctxt->memop.addr.mem.seg = seg_override(ctxt); - if (memop.type == OP_MEM && ctxt->ad_bytes != 8) - memop.addr.mem.ea = (u32)memop.addr.mem.ea; + if (ctxt->memop.type == OP_MEM && ctxt->ad_bytes != 8) + ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea; /* * Decode and fetch the source operand: register, memory @@ -3509,17 +3510,16 @@ done_prefixes: decode_register_operand(ctxt, &ctxt->src, 0); break; case SrcMem16: - memop.bytes = 2; + ctxt->memop.bytes = 2; goto srcmem_common; case SrcMem32: - memop.bytes = 4; + ctxt->memop.bytes = 4; goto srcmem_common; case SrcMem: - memop.bytes = (ctxt->d & ByteOp) ? 1 : - ctxt->op_bytes; + ctxt->memop.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; srcmem_common: - ctxt->src = memop; - memopp = &ctxt->src; + ctxt->src = ctxt->memop; + ctxt->memopp = &ctxt->src; break; case SrcImmU16: rc = decode_imm(ctxt, &ctxt->src, 2, false); @@ -3561,7 +3561,7 @@ done_prefixes: insn_fetch_arr(ctxt->src.valptr, ctxt->src.bytes, ctxt); break; case SrcMemFAddr: - memop.bytes = ctxt->op_bytes + 2; + ctxt->memop.bytes = ctxt->op_bytes + 2; goto srcmem_common; break; case SrcDX: @@ -3615,8 +3615,8 @@ done_prefixes: break; case DstMem: case DstMem64: - ctxt->dst = memop; - memopp = &ctxt->dst; + ctxt->dst = ctxt->memop; + ctxt->memopp = &ctxt->dst; if ((ctxt->d & DstMask) == DstMem64) ctxt->dst.bytes = 8; else @@ -3654,8 +3654,8 @@ done_prefixes: } done: - if (memopp && memopp->type == OP_MEM && ctxt->rip_relative) - memopp->addr.mem.ea += ctxt->_eip; + if (ctxt->memopp && ctxt->memopp->type == OP_MEM && ctxt->rip_relative) + ctxt->memopp->addr.mem.ea += ctxt->_eip; return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } -- cgit v1.2.3 From b1ea50b2b63a95aa5a7944b48ba4d0e9b32211d3 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Tue, 13 Sep 2011 10:45:42 +0300 Subject: KVM: x86 emulator: expand decode flags to 64 bits Unifiying the operands means not taking advantage of the fact that some operand types can only go into certain operands (for example, DI can only be used by the destination), so we need more bits to hold the operand type. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_emulate.h | 2 +- arch/x86/kvm/emulate.c | 38 +++++++++++++++++++------------------- 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 56bac3e3423e..a026507893e9 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -262,7 +262,7 @@ struct x86_emulate_ctxt { struct operand dst; bool has_seg_override; u8 seg_override; - unsigned int d; + u64 d; int (*execute)(struct x86_emulate_ctxt *ctxt); int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* modrm */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 6a6aed9a29df..8c65ff274785 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -31,18 +31,18 @@ /* * Operand types */ -#define OpNone 0 -#define OpImplicit 1 /* No generic decode */ -#define OpReg 2 /* Register */ -#define OpMem 3 /* Memory */ -#define OpAcc 4 /* Accumulator: AL/AX/EAX/RAX */ -#define OpDI 5 /* ES:DI/EDI/RDI */ -#define OpMem64 6 /* Memory, 64-bit */ -#define OpImmUByte 7 /* Zero-extended 8-bit immediate */ -#define OpDX 8 /* DX register */ +#define OpNone 0ull +#define OpImplicit 1ull /* No generic decode */ +#define OpReg 2ull /* Register */ +#define OpMem 3ull /* Memory */ +#define OpAcc 4ull /* Accumulator: AL/AX/EAX/RAX */ +#define OpDI 5ull /* ES:DI/EDI/RDI */ +#define OpMem64 6ull /* Memory, 64-bit */ +#define OpImmUByte 7ull /* Zero-extended 8-bit immediate */ +#define OpDX 8ull /* DX register */ #define OpBits 4 /* Width of operand field */ -#define OpMask ((1 << OpBits) - 1) +#define OpMask ((1ull << OpBits) - 1) /* * Opcode effective-address decode tables. @@ -108,12 +108,12 @@ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) /* Source 2 operand type */ -#define Src2None (0<<29) -#define Src2CL (1<<29) -#define Src2ImmByte (2<<29) -#define Src2One (3<<29) -#define Src2Imm (4<<29) -#define Src2Mask (7<<29) +#define Src2None (0u<<29) +#define Src2CL (1u<<29) +#define Src2ImmByte (2u<<29) +#define Src2One (3u<<29) +#define Src2Imm (4u<<29) +#define Src2Mask (7u<<29) #define X2(x...) x, x #define X3(x...) X2(x), x @@ -125,8 +125,8 @@ #define X16(x...) X8(x), X8(x) struct opcode { - u32 flags; - u8 intercept; + u64 flags : 56; + u64 intercept : 8; union { int (*execute)(struct x86_emulate_ctxt *ctxt); struct opcode *group; @@ -3530,7 +3530,7 @@ done_prefixes: return EMULATION_FAILED; } - ctxt->d &= ~GroupMask; + ctxt->d &= ~(u64)GroupMask; ctxt->d |= opcode.flags; } -- cgit v1.2.3 From 7460fb4a340033107530df19e7e125bd0969bfb2 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Tue, 20 Sep 2011 13:43:14 +0300 Subject: KVM: Fix simultaneous NMIs If simultaneous NMIs happen, we're supposed to queue the second and next (collapsing them), but currently we sometimes collapse the second into the first. Fix by using a counter for pending NMIs instead of a bool; since the counter limit depends on whether the processor is currently in an NMI handler, which can only be checked in vcpu context (via the NMI mask), we add a new KVM_REQ_NMI to request recalculation of the counter. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_host.h | 5 +++-- arch/x86/kvm/x86.c | 48 ++++++++++++++++++++++++++--------------- include/linux/kvm_host.h | 1 + 3 files changed, 35 insertions(+), 19 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6ab4241c27cb..ab62711ccb78 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -413,8 +413,9 @@ struct kvm_vcpu_arch { u32 tsc_catchup_mult; s8 tsc_catchup_shift; - bool nmi_pending; - bool nmi_injected; + atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ + unsigned nmi_pending; /* NMI queued after currently running handler */ + bool nmi_injected; /* Trying to inject an NMI this entry */ struct mtrr_state_type mtrr_state; u32 pat; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6b37f18a1663..d51e40733fcb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -83,6 +83,7 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static void update_cr8_intercept(struct kvm_vcpu *vcpu); static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -359,8 +360,8 @@ void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) void kvm_inject_nmi(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, vcpu); - vcpu->arch.nmi_pending = 1; + atomic_inc(&vcpu->arch.nmi_queued); + kvm_make_request(KVM_REQ_NMI, vcpu); } EXPORT_SYMBOL_GPL(kvm_inject_nmi); @@ -2827,6 +2828,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { + process_nmi(vcpu); events->exception.injected = vcpu->arch.exception.pending && !kvm_exception_is_soft(vcpu->arch.exception.nr); @@ -2844,7 +2846,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.pending = vcpu->arch.nmi_pending != 0; events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); events->nmi.pad = 0; @@ -2864,6 +2866,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SHADOW)) return -EINVAL; + process_nmi(vcpu); vcpu->arch.exception.pending = events->exception.injected; vcpu->arch.exception.nr = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; @@ -4763,7 +4766,7 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) kvm_set_rflags(vcpu, ctxt->eflags); if (irq == NMI_VECTOR) - vcpu->arch.nmi_pending = false; + vcpu->arch.nmi_pending = 0; else vcpu->arch.interrupt.pending = false; @@ -5572,7 +5575,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) /* try to inject new event if pending */ if (vcpu->arch.nmi_pending) { if (kvm_x86_ops->nmi_allowed(vcpu)) { - vcpu->arch.nmi_pending = false; + --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; kvm_x86_ops->set_nmi(vcpu); } @@ -5604,10 +5607,26 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) } } +static void process_nmi(struct kvm_vcpu *vcpu) +{ + unsigned limit = 2; + + /* + * x86 is limited to one NMI running, and one NMI pending after it. + * If an NMI is already in progress, limit further NMIs to just one. + * Otherwise, allow two (and we'll inject the first one immediately). + */ + if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + limit = 1; + + vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool nmi_pending; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; @@ -5647,6 +5666,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_NMI, vcpu)) + process_nmi(vcpu); } @@ -5654,19 +5675,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (unlikely(r)) goto out; - /* - * An NMI can be injected between local nmi_pending read and - * vcpu->arch.nmi_pending read inside inject_pending_event(). - * But in that case, KVM_REQ_EVENT will be set, which makes - * the race described above benign. - */ - nmi_pending = ACCESS_ONCE(vcpu->arch.nmi_pending); - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ - if (nmi_pending) + if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); else if (kvm_cpu_has_interrupt(vcpu) || req_int_win) kvm_x86_ops->enable_irq_window(vcpu); @@ -6374,7 +6387,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) { - vcpu->arch.nmi_pending = false; + atomic_set(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; vcpu->arch.switch_db_regs = 0; @@ -6649,7 +6663,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted) || !list_empty_careful(&vcpu->async_pf.done) || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED - || vcpu->arch.nmi_pending || + || atomic_read(&vcpu->arch.nmi_queued) || (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2a414f66af28..d52623199978 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -49,6 +49,7 @@ #define KVM_REQ_EVENT 11 #define KVM_REQ_APF_HALT 12 #define KVM_REQ_STEAL_UPDATE 13 +#define KVM_REQ_NMI 14 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 -- cgit v1.2.3 From b90dfb0419a79a90395e04fee3fbda3c12ba8237 Mon Sep 17 00:00:00 2001 From: "Liu, Jinsong" Date: Thu, 22 Sep 2011 16:53:58 +0800 Subject: x86: TSC deadline definitions This pre-defination is preparing for KVM tsc deadline timer emulation, but theirself are not kvm specific. Signed-off-by: Liu, Jinsong Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/apicdef.h | 2 ++ arch/x86/include/asm/cpufeature.h | 1 + arch/x86/include/asm/msr-index.h | 2 ++ 3 files changed, 5 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 34595d5e1038..3925d8007864 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -100,7 +100,9 @@ #define APIC_TIMER_BASE_CLKIN 0x0 #define APIC_TIMER_BASE_TMBASE 0x1 #define APIC_TIMER_BASE_DIV 0x2 +#define APIC_LVT_TIMER_ONESHOT (0 << 17) #define APIC_LVT_TIMER_PERIODIC (1 << 17) +#define APIC_LVT_TIMER_TSCDEADLINE (2 << 17) #define APIC_LVT_MASKED (1 << 16) #define APIC_LVT_LEVEL_TRIGGER (1 << 15) #define APIC_LVT_REMOTE_IRR (1 << 14) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 88b23a43f340..94dfb0a3e544 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -120,6 +120,7 @@ #define X86_FEATURE_X2APIC (4*32+21) /* x2APIC */ #define X86_FEATURE_MOVBE (4*32+22) /* MOVBE instruction */ #define X86_FEATURE_POPCNT (4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER (4*32+24) /* Tsc deadline timer */ #define X86_FEATURE_AES (4*32+25) /* AES instructions */ #define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d52609aeeab8..a6962d9161a0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -229,6 +229,8 @@ #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define MSR_IA32_TSCDEADLINE 0x000006e0 + #define MSR_IA32_UCODE_WRITE 0x00000079 #define MSR_IA32_UCODE_REV 0x0000008b -- cgit v1.2.3 From a3e06bbe8445f57eb949e6474c5a9b30f24d2057 Mon Sep 17 00:00:00 2001 From: "Liu, Jinsong" Date: Thu, 22 Sep 2011 16:55:52 +0800 Subject: KVM: emulate lapic tsc deadline timer for guest This patch emulate lapic tsc deadline timer for guest: Enumerate tsc deadline timer capability by CPUID; Enable tsc deadline timer mode by lapic MMIO; Start tsc deadline timer by WRMSR; [jan: use do_div()] [avi: fix for !irqchip_in_kernel()] [marcelo: another fix for !irqchip_in_kernel()] Signed-off-by: Liu, Jinsong Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 2 + arch/x86/kvm/kvm_timer.h | 2 + arch/x86/kvm/lapic.c | 142 ++++++++++++++++++++++++++++++++-------- arch/x86/kvm/lapic.h | 3 + arch/x86/kvm/x86.c | 21 +++++- 5 files changed, 140 insertions(+), 30 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ab62711ccb78..b4973f4dab98 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -674,6 +674,8 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); extern bool tdp_enabled; +u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); + /* control of guest tsc rate supported? */ extern bool kvm_has_tsc_control; /* minimum supported tsc_khz for guests */ diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h index 64bc6ea78d90..497dbaa366d4 100644 --- a/arch/x86/kvm/kvm_timer.h +++ b/arch/x86/kvm/kvm_timer.h @@ -2,6 +2,8 @@ struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ + u32 timer_mode_mask; + u64 tscdeadline; atomic_t pending; /* accumulated triggered timers */ bool reinject; struct kvm_timer_ops *t_ops; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2fb20caae5d8..54abb40199d6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -138,9 +138,23 @@ static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; } +static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) +{ + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT); +} + static inline int apic_lvtt_period(struct kvm_lapic *apic) { - return apic_get_reg(apic, APIC_LVTT) & APIC_LVT_TIMER_PERIODIC; + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC); +} + +static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic) +{ + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == + APIC_LVT_TIMER_TSCDEADLINE); } static inline int apic_lvt_nmi_mode(u32 lvt_val) @@ -169,7 +183,7 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) } static unsigned int apic_lvt_mask[APIC_LVT_NUM] = { - LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */ + LVT_MASK , /* part LVTT mask, timer mode mask added at runtime */ LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */ LVT_MASK | APIC_MODE_MASK, /* LVTPC */ LINT_MASK, LINT_MASK, /* LVT0-1 */ @@ -572,6 +586,9 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) break; case APIC_TMCCT: /* Timer CCR */ + if (apic_lvtt_tscdeadline(apic)) + return 0; + val = apic_get_tmcct(apic); break; @@ -666,37 +683,40 @@ static void update_divide_count(struct kvm_lapic *apic) static void start_apic_timer(struct kvm_lapic *apic) { - ktime_t now = apic->lapic_timer.timer.base->get_time(); - - apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) * - APIC_BUS_CYCLE_NS * apic->divide_count; + ktime_t now; atomic_set(&apic->lapic_timer.pending, 0); - if (!apic->lapic_timer.period) - return; - /* - * Do not allow the guest to program periodic timers with small - * interval, since the hrtimers are not throttled by the host - * scheduler. - */ - if (apic_lvtt_period(apic)) { - s64 min_period = min_timer_period_us * 1000LL; - - if (apic->lapic_timer.period < min_period) { - pr_info_ratelimited( - "kvm: vcpu %i: requested %lld ns " - "lapic timer period limited to %lld ns\n", - apic->vcpu->vcpu_id, apic->lapic_timer.period, - min_period); - apic->lapic_timer.period = min_period; + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { + /* lapic timer in oneshot or peroidic mode */ + now = apic->lapic_timer.timer.base->get_time(); + apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) + * APIC_BUS_CYCLE_NS * apic->divide_count; + + if (!apic->lapic_timer.period) + return; + /* + * Do not allow the guest to program periodic timers with small + * interval, since the hrtimers are not throttled by the host + * scheduler. + */ + if (apic_lvtt_period(apic)) { + s64 min_period = min_timer_period_us * 1000LL; + + if (apic->lapic_timer.period < min_period) { + pr_info_ratelimited( + "kvm: vcpu %i: requested %lld ns " + "lapic timer period limited to %lld ns\n", + apic->vcpu->vcpu_id, + apic->lapic_timer.period, min_period); + apic->lapic_timer.period = min_period; + } } - } - hrtimer_start(&apic->lapic_timer.timer, - ktime_add_ns(now, apic->lapic_timer.period), - HRTIMER_MODE_ABS); + hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, apic->lapic_timer.period), + HRTIMER_MODE_ABS); - apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" + apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " "timer initial count 0x%x, period %lldns, " "expire @ 0x%016" PRIx64 ".\n", __func__, @@ -705,6 +725,30 @@ static void start_apic_timer(struct kvm_lapic *apic) apic->lapic_timer.period, ktime_to_ns(ktime_add_ns(now, apic->lapic_timer.period))); + } else if (apic_lvtt_tscdeadline(apic)) { + /* lapic timer in tsc deadline mode */ + u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + u64 ns = 0; + struct kvm_vcpu *vcpu = apic->vcpu; + unsigned long this_tsc_khz = vcpu_tsc_khz(vcpu); + unsigned long flags; + + if (unlikely(!tscdeadline || !this_tsc_khz)) + return; + + local_irq_save(flags); + + now = apic->lapic_timer.timer.base->get_time(); + guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); + if (likely(tscdeadline > guest_tsc)) { + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + } + hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, ns), HRTIMER_MODE_ABS); + + local_irq_restore(flags); + } } static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) @@ -792,7 +836,6 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVT0: apic_manage_nmi_watchdog(apic, val); - case APIC_LVTT: case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: @@ -806,7 +849,22 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; + case APIC_LVTT: + if ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) != + (val & apic->lapic_timer.timer_mode_mask)) + hrtimer_cancel(&apic->lapic_timer.timer); + + if (!apic_sw_enabled(apic)) + val |= APIC_LVT_MASKED; + val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); + apic_set_reg(apic, APIC_LVTT, val); + break; + case APIC_TMICT: + if (apic_lvtt_tscdeadline(apic)) + break; + hrtimer_cancel(&apic->lapic_timer.timer); apic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); @@ -902,6 +960,32 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) *---------------------------------------------------------------------- */ +u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + if (!apic) + return 0; + + if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) + return 0; + + return apic->lapic_timer.tscdeadline; +} + +void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + if (!apic) + return; + + if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) + return; + + hrtimer_cancel(&apic->lapic_timer.timer); + apic->lapic_timer.tscdeadline = data; + start_apic_timer(apic); +} + void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) { struct kvm_lapic *apic = vcpu->arch.apic; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 82872432d475..138e8cc6fea6 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -42,6 +42,9 @@ int kvm_lapic_enabled(struct kvm_vcpu *vcpu); bool kvm_apic_present(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); +u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); +void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); + void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d51e40733fcb..cf269096eadf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -600,6 +600,8 @@ static bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) static void update_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; + struct kvm_lapic *apic = vcpu->arch.apic; + u32 timer_mode_mask; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (!best) @@ -611,6 +613,16 @@ static void update_cpuid(struct kvm_vcpu *vcpu) if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) best->ecx |= bit(X86_FEATURE_OSXSAVE); } + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + best->function == 0x1) { + best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER); + timer_mode_mask = 3 << 17; + } else + timer_mode_mask = 1 << 17; + + if (apic) + apic->lapic_timer.timer_mode_mask = timer_mode_mask; } int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -826,6 +838,7 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; static u32 emulated_msrs[] = { + MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -1001,7 +1014,7 @@ static inline int kvm_tsc_changes_freq(void) return ret; } -static u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) +u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) { if (vcpu->arch.virtual_tsc_khz) return vcpu->arch.virtual_tsc_khz; @@ -1565,6 +1578,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_write(vcpu, msr, data); + case MSR_IA32_TSCDEADLINE: + kvm_set_lapic_tscdeadline_msr(vcpu, data); + break; case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; @@ -1894,6 +1910,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_read(vcpu, msr, pdata); break; + case MSR_IA32_TSCDEADLINE: + data = kvm_get_lapic_tscdeadline_msr(vcpu); + break; case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; -- cgit v1.2.3