diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/kernel/alternative.c | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/emulate.c | 4 | ||||
| -rw-r--r-- | arch/x86/kvm/i8259.c | 17 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx.c | 90 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 4 | ||||
| -rw-r--r-- | arch/x86/syscalls/syscall_64.tbl | 2 | ||||
| -rw-r--r-- | arch/x86/xen/enlighten.c | 1 | ||||
| -rw-r--r-- | arch/x86/xen/p2m.c | 5 |
8 files changed, 101 insertions, 24 deletions
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1f84794f075..73ef56c5a8b 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -219,7 +219,7 @@ void __init arch_init_ideal_nops(void) ideal_nops = intel_nops; #endif } - + break; default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f95d242ee9f..4837375baee 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4426,12 +4426,12 @@ twobyte_insn: break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; - ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val + ctxt->dst.val = (ctxt->src.bytes == 1) ? (u8) ctxt->src.val : (u16) ctxt->src.val; break; case 0xbe ... 0xbf: /* movsx */ ctxt->dst.bytes = ctxt->op_bytes; - ctxt->dst.val = (ctxt->d & ByteOp) ? (s8) ctxt->src.val : + ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val : (s16) ctxt->src.val; break; case 0xc0 ... 0xc1: /* xadd */ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 81cf4fa4a2b..0147d165708 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -305,6 +305,11 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) addr &= 1; if (addr == 0) { if (val & 0x10) { + u8 edge_irr = s->irr & ~s->elcr; + int i; + bool found; + struct kvm_vcpu *vcpu; + s->init4 = val & 1; s->last_irr = 0; s->irr &= s->elcr; @@ -322,6 +327,18 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x08) pr_pic_unimpl( "level sensitive irq not supported"); + + kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm) + if (kvm_apic_accept_pic_intr(vcpu)) { + found = true; + break; + } + + + if (found) + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) + if (edge_irr & (1 << irq)) + pic_clear_isr(s, irq); } else if (val & 0x08) { if (val & 0x04) s->poll = 1; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 32eb5886629..86c8704e92a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -615,6 +615,10 @@ 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); @@ -1470,13 +1474,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) loadsegment(ds, vmx->host_state.ds_sel); loadsegment(es, vmx->host_state.es_sel); } -#else - /* - * The sysexit path does not restore ds/es, so we must set them to - * a reasonable value ourselves. - */ - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); #endif reload_tss(); #ifdef CONFIG_X86_64 @@ -2770,6 +2767,7 @@ 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 +2811,23 @@ 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); - 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_DS); + vmx_set_segment(vcpu, &var, VCPU_SREG_DS); - 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_GS); + vmx_set_segment(vcpu, &var, VCPU_SREG_GS); + + vmx_get_segment(vcpu, &var, VCPU_SREG_FS); + vmx_set_segment(vcpu, &var, VCPU_SREG_FS); continue_rmode: kvm_mmu_reset_context(vcpu); @@ -3229,6 +3230,44 @@ 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) @@ -6273,6 +6312,19 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); +#ifndef CONFIG_X86_64 + /* + * The sysexit path does not restore ds/es, so we must set them to + * a reasonable value ourselves. + * + * We can't defer this to vmx_load_host_state() since that function + * may be executed in interrupt context, which saves and restore segments + * around it, nullifying its effect. + */ + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#endif + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) | (1 << VCPU_EXREG_RFLAGS) | (1 << VCPU_EXREG_CPL) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index be6d54929fa..14c290de798 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -907,6 +907,10 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) */ getboottime(&boot); + if (kvm->arch.kvmclock_offset) { + struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset); + boot = timespec_sub(boot, ts); + } wc.sec = boot.tv_sec; wc.nsec = boot.tv_nsec; wc.version = version; diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 51171aeff0d..29aed7ac2c0 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -318,7 +318,7 @@ 309 common getcpu sys_getcpu 310 64 process_vm_readv sys_process_vm_readv 311 64 process_vm_writev sys_process_vm_writev -312 64 kcmp sys_kcmp +312 common kcmp sys_kcmp # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c7cadd61022..ff962d4b821 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -949,7 +949,6 @@ static void xen_write_cr4(unsigned long cr4) { cr4 &= ~X86_CR4_PGE; cr4 &= ~X86_CR4_PSE; - cr4 &= ~X86_CR4_OSXSAVE; native_write_cr4(cr4); } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 64effdc6da9..b2e91d40a4c 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -194,6 +194,11 @@ RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID * boundary violation will require three middle nodes. */ RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); +/* When we populate back during bootup, the amount of pages can vary. The + * max we have is seen is 395979, but that does not mean it can't be more. + * But some machines can have 3GB I/O holes even. So lets reserve enough + * for 4GB of I/O and E820 holes. */ +RESERVE_BRK(p2m_populated, PMD_SIZE * 4); static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); |