diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-07-24 19:01:20 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-07-24 19:01:20 (GMT) |
commit | 5fecc9d8f59e765c2a48379dd7c6f5cf88c7d75a (patch) | |
tree | d1fc25d9650d3ac24591bba6f5e2e7a1afc54796 /arch/x86/kvm/vmx.c | |
parent | 3c4cfadef6a1665d9cd02a543782d03d3e6740c6 (diff) | |
parent | 1a577b72475d161b6677c05abe57301362023bb2 (diff) | |
download | linux-fsl-qoriq-5fecc9d8f59e765c2a48379dd7c6f5cf88c7d75a.tar.xz |
Merge tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Avi Kivity:
"Highlights include
- full big real mode emulation on pre-Westmere Intel hosts (can be
disabled with emulate_invalid_guest_state=0)
- relatively small ppc and s390 updates
- PCID/INVPCID support in guests
- EOI avoidance; 3.6 guests should perform better on 3.6 hosts on
interrupt intensive workloads)
- Lockless write faults during live migration
- EPT accessed/dirty bits support for new Intel processors"
Fix up conflicts in:
- Documentation/virtual/kvm/api.txt:
Stupid subchapter numbering, added next to each other.
- arch/powerpc/kvm/booke_interrupts.S:
PPC asm changes clashing with the KVM fixes
- arch/s390/include/asm/sigp.h, arch/s390/kvm/sigp.c:
Duplicated commits through the kvm tree and the s390 tree, with
subsequent edits in the KVM tree.
* tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
KVM: fix race with level interrupts
x86, hyper: fix build with !CONFIG_KVM_GUEST
Revert "apic: fix kvm build on UP without IOAPIC"
KVM guest: switch to apic_set_eoi_write, apic_write
apic: add apic_set_eoi_write for PV use
KVM: VMX: Implement PCID/INVPCID for guests with EPT
KVM: Add x86_hyper_kvm to complete detect_hypervisor_platform check
KVM: PPC: Critical interrupt emulation support
KVM: PPC: e500mc: Fix tlbilx emulation for 64-bit guests
KVM: PPC64: booke: Set interrupt computation mode for 64-bit host
KVM: PPC: bookehv: Add ESR flag to Data Storage Interrupt
KVM: PPC: bookehv64: Add support for std/ld emulation.
booke: Added crit/mc exception handler for e500v2
booke/bookehv: Add host crit-watchdog exception support
KVM: MMU: document mmu-lock and fast page fault
KVM: MMU: fix kvm_mmu_pagetable_walk tracepoint
KVM: MMU: trace fast page fault
KVM: MMU: fast path of handling guest page fault
KVM: MMU: introduce SPTE_MMU_WRITEABLE bit
KVM: MMU: fold tlb flush judgement into mmu_spte_update
...
Diffstat (limited to 'arch/x86/kvm/vmx.c')
-rw-r--r-- | arch/x86/kvm/vmx.c | 189 |
1 files changed, 152 insertions, 37 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 32eb588..c39b607 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -71,7 +71,10 @@ static bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, S_IRUGO); -static bool __read_mostly emulate_invalid_guest_state = 0; +static bool __read_mostly enable_ept_ad_bits = 1; +module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); + +static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly vmm_exclusive = 1; @@ -615,6 +618,10 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); +static void vmx_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); +static void vmx_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -789,6 +796,11 @@ static inline bool cpu_has_vmx_ept_4levels(void) return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT; } +static inline bool cpu_has_vmx_ept_ad_bits(void) +{ + return vmx_capability.ept & VMX_EPT_AD_BIT; +} + static inline bool cpu_has_vmx_invept_individual_addr(void) { return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT; @@ -849,6 +861,12 @@ static inline bool cpu_has_vmx_rdtscp(void) SECONDARY_EXEC_RDTSCP; } +static inline bool cpu_has_vmx_invpcid(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_ENABLE_INVPCID; +} + static inline bool cpu_has_virtual_nmis(void) { return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; @@ -1739,6 +1757,11 @@ static bool vmx_rdtscp_supported(void) return cpu_has_vmx_rdtscp(); } +static bool vmx_invpcid_supported(void) +{ + return cpu_has_vmx_invpcid() && enable_ept; +} + /* * Swap MSR entry in host/guest MSR entry array. */ @@ -2458,7 +2481,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_ENABLE_EPT | SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_RDTSCP; + SECONDARY_EXEC_RDTSCP | + SECONDARY_EXEC_ENABLE_INVPCID; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2645,8 +2669,12 @@ static __init int hardware_setup(void) !cpu_has_vmx_ept_4levels()) { enable_ept = 0; enable_unrestricted_guest = 0; + enable_ept_ad_bits = 0; } + if (!cpu_has_vmx_ept_ad_bits()) + enable_ept_ad_bits = 0; + if (!cpu_has_vmx_unrestricted_guest()) enable_unrestricted_guest = 0; @@ -2770,6 +2798,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_segment var; if (enable_unrestricted_guest) return; @@ -2813,20 +2842,23 @@ static void enter_rmode(struct kvm_vcpu *vcpu) if (emulate_invalid_guest_state) goto continue_rmode; - vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4); - vmcs_write32(GUEST_SS_LIMIT, 0xffff); - vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); + vmx_get_segment(vcpu, &var, VCPU_SREG_SS); + vmx_set_segment(vcpu, &var, VCPU_SREG_SS); + + vmx_get_segment(vcpu, &var, VCPU_SREG_CS); + vmx_set_segment(vcpu, &var, VCPU_SREG_CS); + + vmx_get_segment(vcpu, &var, VCPU_SREG_ES); + vmx_set_segment(vcpu, &var, VCPU_SREG_ES); + + vmx_get_segment(vcpu, &var, VCPU_SREG_DS); + vmx_set_segment(vcpu, &var, VCPU_SREG_DS); - vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); - vmcs_write32(GUEST_CS_LIMIT, 0xffff); - if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) - vmcs_writel(GUEST_CS_BASE, 0xf0000); - vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); + vmx_get_segment(vcpu, &var, VCPU_SREG_GS); + vmx_set_segment(vcpu, &var, VCPU_SREG_GS); - fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es); - fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds); - fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs); - fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs); + vmx_get_segment(vcpu, &var, VCPU_SREG_FS); + vmx_set_segment(vcpu, &var, VCPU_SREG_FS); continue_rmode: kvm_mmu_reset_context(vcpu); @@ -3027,6 +3059,8 @@ static u64 construct_eptp(unsigned long root_hpa) /* TODO write the value reading from MSR */ eptp = VMX_EPT_DEFAULT_MT | VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT; + if (enable_ept_ad_bits) + eptp |= VMX_EPT_AD_ENABLE_BIT; eptp |= (root_hpa & PAGE_MASK); return eptp; @@ -3153,11 +3187,22 @@ static int __vmx_get_cpl(struct kvm_vcpu *vcpu) static int vmx_get_cpl(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * If we enter real mode with cs.sel & 3 != 0, the normal CPL calculations + * fail; use the cache instead. + */ + if (unlikely(vmx->emulation_required && emulate_invalid_guest_state)) { + return vmx->cpl; + } + if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - to_vmx(vcpu)->cpl = __vmx_get_cpl(vcpu); + vmx->cpl = __vmx_get_cpl(vcpu); } - return to_vmx(vcpu)->cpl; + + return vmx->cpl; } @@ -3165,7 +3210,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable) + if (var->unusable || !var->present) ar = 1 << 16; else { ar = var->type & 15; @@ -3177,8 +3222,6 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) ar |= (var->db & 1) << 14; ar |= (var->g & 1) << 15; } - if (ar == 0) /* a 0 value means unusable */ - ar = AR_UNUSABLE_MASK; return ar; } @@ -3229,6 +3272,44 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, vmcs_write32(sf->ar_bytes, ar); __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + + /* + * Fix segments for real mode guest in hosts that don't have + * "unrestricted_mode" or it was disabled. + * This is done to allow migration of the guests from hosts with + * unrestricted guest like Westmere to older host that don't have + * unrestricted guest like Nehelem. + */ + if (!enable_unrestricted_guest && vmx->rmode.vm86_active) { + switch (seg) { + case VCPU_SREG_CS: + vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); + vmcs_write32(GUEST_CS_LIMIT, 0xffff); + if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) + vmcs_writel(GUEST_CS_BASE, 0xf0000); + vmcs_write16(GUEST_CS_SELECTOR, + vmcs_readl(GUEST_CS_BASE) >> 4); + break; + case VCPU_SREG_ES: + fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es); + break; + case VCPU_SREG_DS: + fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds); + break; + case VCPU_SREG_GS: + fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs); + break; + case VCPU_SREG_FS: + fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs); + break; + case VCPU_SREG_SS: + vmcs_write16(GUEST_SS_SELECTOR, + vmcs_readl(GUEST_SS_BASE) >> 4); + vmcs_write32(GUEST_SS_LIMIT, 0xffff); + vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); + break; + } + } } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -3731,6 +3812,8 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; enable_unrestricted_guest = 0; + /* Enable INVPCID for non-ept guests may cause performance regression. */ + exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; @@ -4489,7 +4572,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; } vcpu->run->exit_reason = 0; - pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", + vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } @@ -4769,6 +4852,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; gpa_t gpa; + u32 error_code; int gla_validity; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -4793,7 +4877,13 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(gpa, exit_qualification); - return kvm_mmu_page_fault(vcpu, gpa, exit_qualification & 0x3, NULL, 0); + + /* It is a write fault? */ + error_code = exit_qualification & (1U << 1); + /* ept page table is present? */ + error_code |= (exit_qualification >> 3) & 0x1; + + return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } static u64 ept_rsvd_mask(u64 spte, int level) @@ -4908,15 +4998,18 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) int ret = 1; u32 cpu_exec_ctrl; bool intr_window_requested; + unsigned count = 130; cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING; - while (!guest_state_valid(vcpu)) { - if (intr_window_requested - && (kvm_get_rflags(&vmx->vcpu) & X86_EFLAGS_IF)) + while (!guest_state_valid(vcpu) && count-- != 0) { + if (intr_window_requested && vmx_interrupt_allowed(vcpu)) return handle_interrupt_window(&vmx->vcpu); + if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) + return 1; + err = emulate_instruction(vcpu, 0); if (err == EMULATE_DO_MMIO) { @@ -4924,8 +5017,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) goto out; } - if (err != EMULATE_DONE) + if (err != EMULATE_DONE) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; + } if (signal_pending(current)) goto out; @@ -4933,7 +5030,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) schedule(); } - vmx->emulation_required = 0; + vmx->emulation_required = !guest_state_valid(vcpu); out: return ret; } @@ -6467,6 +6564,23 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) } } } + + exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + /* Exposing INVPCID only when PCID is exposed */ + best = kvm_find_cpuid_entry(vcpu, 0x7, 0); + if (vmx_invpcid_supported() && + best && (best->ecx & bit(X86_FEATURE_INVPCID)) && + guest_cpuid_has_pcid(vcpu)) { + exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + exec_control); + } else { + exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + exec_control); + if (best) + best->ecx &= ~bit(X86_FEATURE_INVPCID); + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -7201,6 +7315,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .cpuid_update = vmx_cpuid_update, .rdtscp_supported = vmx_rdtscp_supported, + .invpcid_supported = vmx_invpcid_supported, .set_supported_cpuid = vmx_set_supported_cpuid, @@ -7230,23 +7345,21 @@ static int __init vmx_init(void) if (!vmx_io_bitmap_a) return -ENOMEM; + r = -ENOMEM; + vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_io_bitmap_b) { - r = -ENOMEM; + if (!vmx_io_bitmap_b) goto out; - } vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy) { - r = -ENOMEM; + if (!vmx_msr_bitmap_legacy) goto out1; - } + vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode) { - r = -ENOMEM; + if (!vmx_msr_bitmap_longmode) goto out2; - } + /* * Allow direct access to the PC debug port (it is often used for I/O @@ -7275,8 +7388,10 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); if (enable_ept) { - kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull, - VMX_EPT_EXECUTABLE_MASK); + kvm_mmu_set_mask_ptes(0ull, + (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, + (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK); ept_set_mmio_spte_mask(); kvm_enable_tdp(); } else |