*/
#include "kvm.h"
+#include "x86.h"
#include "x86_emulate.h"
+#include "irq.h"
#include "vmx.h"
#include "segment_descriptor.h"
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/highmem.h>
-#include <linux/profile.h>
#include <linux/sched.h>
+#include <linux/moduleparam.h>
#include <asm/io.h>
#include <asm/desc.h>
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+static int bypass_guest_pf = 1;
+module_param(bypass_guest_pf, bool, 0);
+
struct vmcs {
u32 revision_id;
u32 abort;
struct vcpu_vmx {
struct kvm_vcpu vcpu;
int launched;
+ u8 fail;
+ u32 idt_vectoring_info;
struct kvm_msr_entry *guest_msrs;
struct kvm_msr_entry *host_msrs;
int nmsrs;
struct {
int loaded;
u16 fs_sel, gs_sel, ldt_sel;
- int fs_gs_ldt_reload_needed;
- }host_state;
-
+ int gs_ldt_reload_needed;
+ int fs_reload_needed;
+ int guest_efer_loaded;
+ } host_state;
+ struct {
+ struct {
+ bool pending;
+ u8 vector;
+ unsigned rip;
+ } irq;
+ } rmode;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
static struct page *vmx_io_bitmap_a;
static struct page *vmx_io_bitmap_b;
-#define EFER_SAVE_RESTORE_BITS ((u64)EFER_SCE)
-
static struct vmcs_config {
int size;
int order;
u32 revision_id;
u32 pin_based_exec_ctrl;
u32 cpu_based_exec_ctrl;
+ u32 cpu_based_2nd_exec_ctrl;
u32 vmexit_ctrl;
u32 vmentry_ctrl;
} vmcs_config;
rdmsrl(e[i].index, e[i].data);
}
-static inline u64 msr_efer_save_restore_bits(struct kvm_msr_entry msr)
-{
- return (u64)msr.data & EFER_SAVE_RESTORE_BITS;
-}
-
-static inline int msr_efer_need_save_restore(struct vcpu_vmx *vmx)
-{
- int efer_offset = vmx->msr_offset_efer;
- return msr_efer_save_restore_bits(vmx->host_msrs[efer_offset]) !=
- msr_efer_save_restore_bits(vmx->guest_msrs[efer_offset]);
-}
-
static inline int is_page_fault(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
(INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
}
+static inline int is_invalid_opcode(u32 intr_info)
+{
+ return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
+ INTR_INFO_VALID_MASK)) ==
+ (INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+}
+
static inline int is_external_interrupt(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
+static inline int cpu_has_vmx_tpr_shadow(void)
+{
+ return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW);
+}
+
+static inline int vm_need_tpr_shadow(struct kvm *kvm)
+{
+ return ((cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm)));
+}
+
+static inline int cpu_has_secondary_exec_ctrls(void)
+{
+ return (vmcs_config.cpu_based_exec_ctrl &
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
+}
+
+static inline int vm_need_secondary_exec_ctrls(struct kvm *kvm)
+{
+ return ((cpu_has_secondary_exec_ctrls()) && (irqchip_in_kernel(kvm)));
+}
+
+static inline int cpu_has_vmx_virtualize_apic_accesses(void)
+{
+ return (vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+}
+
+static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
+{
+ return ((cpu_has_vmx_virtualize_apic_accesses()) &&
+ (irqchip_in_kernel(kvm)));
+}
+
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
int i;
static void vcpu_clear(struct vcpu_vmx *vmx)
{
- if (vmx->vcpu.cpu != raw_smp_processor_id() && vmx->vcpu.cpu != -1)
- smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear,
- vmx, 0, 1);
- else
- __vcpu_clear(vmx);
+ if (vmx->vcpu.cpu == -1)
+ return;
+ smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 0, 1);
vmx->launched = 0;
}
u8 error;
asm volatile (ASM_VMX_VMWRITE_RAX_RDX "; setna %0"
- : "=q"(error) : "a"(value), "d"(field) : "cc" );
+ : "=q"(error) : "a"(value), "d"(field) : "cc");
if (unlikely(error))
vmwrite_error(field, value);
}
{
u32 eb;
- eb = 1u << PF_VECTOR;
+ eb = (1u << PF_VECTOR) | (1u << UD_VECTOR);
if (!vcpu->fpu_active)
eb |= 1u << NM_VECTOR;
if (vcpu->guest_debug.enabled)
static void load_transition_efer(struct vcpu_vmx *vmx)
{
- u64 trans_efer;
int efer_offset = vmx->msr_offset_efer;
+ u64 host_efer = vmx->host_msrs[efer_offset].data;
+ u64 guest_efer = vmx->guest_msrs[efer_offset].data;
+ u64 ignore_bits;
- trans_efer = vmx->host_msrs[efer_offset].data;
- trans_efer &= ~EFER_SAVE_RESTORE_BITS;
- trans_efer |= msr_efer_save_restore_bits(vmx->guest_msrs[efer_offset]);
- wrmsrl(MSR_EFER, trans_efer);
+ if (efer_offset < 0)
+ return;
+ /*
+ * NX is emulated; LMA and LME handled by hardware; SCE meaninless
+ * outside long mode
+ */
+ ignore_bits = EFER_NX | EFER_SCE;
+#ifdef CONFIG_X86_64
+ ignore_bits |= EFER_LMA | EFER_LME;
+ /* SCE is meaningful only in long mode on Intel */
+ if (guest_efer & EFER_LMA)
+ ignore_bits &= ~(u64)EFER_SCE;
+#endif
+ if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits))
+ return;
+
+ vmx->host_state.guest_efer_loaded = 1;
+ guest_efer &= ~ignore_bits;
+ guest_efer |= host_efer & ignore_bits;
+ wrmsrl(MSR_EFER, guest_efer);
vmx->vcpu.stat.efer_reload++;
}
-static void vmx_save_host_state(struct vcpu_vmx *vmx)
+static void reload_host_efer(struct vcpu_vmx *vmx)
+{
+ if (vmx->host_state.guest_efer_loaded) {
+ vmx->host_state.guest_efer_loaded = 0;
+ load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1);
+ }
+}
+
+static void vmx_save_host_state(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (vmx->host_state.loaded)
return;
* allow segment selectors with cpl > 0 or ti == 1.
*/
vmx->host_state.ldt_sel = read_ldt();
- vmx->host_state.fs_gs_ldt_reload_needed = vmx->host_state.ldt_sel;
+ vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
vmx->host_state.fs_sel = read_fs();
- if (!(vmx->host_state.fs_sel & 7))
+ if (!(vmx->host_state.fs_sel & 7)) {
vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
- else {
+ vmx->host_state.fs_reload_needed = 0;
+ } else {
vmcs_write16(HOST_FS_SELECTOR, 0);
- vmx->host_state.fs_gs_ldt_reload_needed = 1;
+ vmx->host_state.fs_reload_needed = 1;
}
vmx->host_state.gs_sel = read_gs();
if (!(vmx->host_state.gs_sel & 7))
vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel);
else {
vmcs_write16(HOST_GS_SELECTOR, 0);
- vmx->host_state.fs_gs_ldt_reload_needed = 1;
+ vmx->host_state.gs_ldt_reload_needed = 1;
}
#ifdef CONFIG_X86_64
#endif
#ifdef CONFIG_X86_64
- if (is_long_mode(&vmx->vcpu)) {
+ if (is_long_mode(&vmx->vcpu))
save_msrs(vmx->host_msrs +
vmx->msr_offset_kernel_gs_base, 1);
- }
+
#endif
load_msrs(vmx->guest_msrs, vmx->save_nmsrs);
- if (msr_efer_need_save_restore(vmx))
- load_transition_efer(vmx);
+ load_transition_efer(vmx);
}
static void vmx_load_host_state(struct vcpu_vmx *vmx)
if (!vmx->host_state.loaded)
return;
+ ++vmx->vcpu.stat.host_state_reload;
vmx->host_state.loaded = 0;
- if (vmx->host_state.fs_gs_ldt_reload_needed) {
- load_ldt(vmx->host_state.ldt_sel);
+ if (vmx->host_state.fs_reload_needed)
load_fs(vmx->host_state.fs_sel);
+ if (vmx->host_state.gs_ldt_reload_needed) {
+ load_ldt(vmx->host_state.ldt_sel);
/*
* If we have to reload gs, we must take care to
* preserve our gs base.
wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE));
#endif
local_irq_restore(flags);
-
- reload_tss();
}
+ reload_tss();
save_msrs(vmx->guest_msrs, vmx->save_nmsrs);
load_msrs(vmx->host_msrs, vmx->save_nmsrs);
- if (msr_efer_need_save_restore(vmx))
- load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1);
+ reload_host_efer(vmx);
}
/*
u64 phys_addr = __pa(vmx->vmcs);
u64 tsc_this, delta;
- if (vcpu->cpu != cpu)
+ if (vcpu->cpu != cpu) {
vcpu_clear(vmx);
+ kvm_migrate_apic_timer(vcpu);
+ }
if (per_cpu(current_vmcs, cpu) != vmx->vmcs) {
u8 error;
static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
vmx_load_host_state(to_vmx(vcpu));
- kvm_put_guest_fpu(vcpu);
}
static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
+ if (vcpu->rmode.active)
+ rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
vmcs_writel(GUEST_RFLAGS, rflags);
}
INTR_INFO_VALID_MASK);
}
+static void vmx_inject_ud(struct kvm_vcpu *vcpu)
+{
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ UD_VECTOR |
+ INTR_TYPE_EXCEPTION |
+ INTR_INFO_VALID_MASK);
+}
+
/*
* Swap MSR entry in host/guest MSR entry array.
*/
#ifdef CONFIG_X86_64
case MSR_EFER:
ret = kvm_set_msr_common(vcpu, msr_index, data);
- if (vmx->host_state.loaded)
+ if (vmx->host_state.loaded) {
+ reload_host_efer(vmx);
load_transition_efer(vmx);
+ }
break;
case MSR_FS_BASE:
vmcs_writel(GUEST_FS_BASE, data);
return 0;
}
+static int vmx_get_irq(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 idtv_info_field;
+
+ idtv_info_field = vmx->idt_vectoring_info;
+ if (idtv_info_field & INTR_INFO_VALID_MASK) {
+ if (is_external_interrupt(idtv_info_field))
+ return idtv_info_field & VECTORING_INFO_VECTOR_MASK;
+ else
+ printk(KERN_DEBUG "pending exception: not handled yet\n");
+ }
+ return -1;
+}
+
static __init int cpu_has_kvm_support(void)
{
unsigned long ecx = cpuid_ecx(1);
}
static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
- u32 msr, u32* result)
+ u32 msr, u32 *result)
{
u32 vmx_msr_low, vmx_msr_high;
u32 ctl = ctl_min | ctl_opt;
u32 min, opt;
u32 _pin_based_exec_control = 0;
u32 _cpu_based_exec_control = 0;
+ u32 _cpu_based_2nd_exec_control = 0;
u32 _vmexit_control = 0;
u32 _vmentry_control = 0;
CPU_BASED_USE_IO_BITMAPS |
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING;
- opt = 0;
+ opt = CPU_BASED_TPR_SHADOW |
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
&_cpu_based_exec_control) < 0)
return -EIO;
+#ifdef CONFIG_X86_64
+ if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
+ _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING &
+ ~CPU_BASED_CR8_STORE_EXITING;
+#endif
+ if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
+ min = 0;
+ opt = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_WBINVD_EXITING;
+ if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS2,
+ &_cpu_based_2nd_exec_control) < 0)
+ return -EIO;
+ }
+#ifndef CONFIG_X86_64
+ if (!(_cpu_based_2nd_exec_control &
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+ _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW;
+#endif
min = 0;
#ifdef CONFIG_X86_64
vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
+ vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control;
vmcs_conf->vmexit_ctrl = _vmexit_control;
vmcs_conf->vmentry_ctrl = _vmentry_control;
vmcs_write32(GUEST_TR_AR_BYTES, vcpu->rmode.tr.ar);
flags = vmcs_readl(GUEST_RFLAGS);
- flags &= ~(IOPL_MASK | X86_EFLAGS_VM);
+ flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
flags |= (vcpu->rmode.save_iopl << IOPL_SHIFT);
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_write32(GUEST_CS_AR_BYTES, 0x9b);
}
-static int rmode_tss_base(struct kvm* kvm)
+static gva_t rmode_tss_base(struct kvm *kvm)
{
- gfn_t base_gfn = kvm->memslots[0].base_gfn + kvm->memslots[0].npages - 3;
- return base_gfn << PAGE_SHIFT;
+ if (!kvm->tss_addr) {
+ gfn_t base_gfn = kvm->memslots[0].base_gfn +
+ kvm->memslots[0].npages - 3;
+ return base_gfn << PAGE_SHIFT;
+ }
+ return kvm->tss_addr;
}
static void fix_rmode_seg(int seg, struct kvm_save_segment *save)
vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
flags = vmcs_readl(GUEST_RFLAGS);
- vcpu->rmode.save_iopl = (flags & IOPL_MASK) >> IOPL_SHIFT;
+ vcpu->rmode.save_iopl = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
- flags |= IOPL_MASK | X86_EFLAGS_VM;
+ flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
fix_rmode_seg(VCPU_SREG_GS, &vcpu->rmode.gs);
fix_rmode_seg(VCPU_SREG_FS, &vcpu->rmode.fs);
+ kvm_mmu_reset_context(vcpu);
init_rmode_tss(vcpu->kvm);
}
vmcs_writel(GUEST_GDTR_BASE, dt->base);
}
-static int init_rmode_tss(struct kvm* kvm)
+static int init_rmode_tss(struct kvm *kvm)
{
- struct page *p1, *p2, *p3;
gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT;
- char *page;
-
- p1 = gfn_to_page(kvm, fn++);
- p2 = gfn_to_page(kvm, fn++);
- p3 = gfn_to_page(kvm, fn);
+ u16 data = 0;
+ int r;
- if (!p1 || !p2 || !p3) {
- kvm_printf(kvm,"%s: gfn_to_page failed\n", __FUNCTION__);
+ r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
+ if (r < 0)
+ return 0;
+ data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
+ r = kvm_write_guest_page(kvm, fn++, &data, 0x66, sizeof(u16));
+ if (r < 0)
+ return 0;
+ r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE);
+ if (r < 0)
+ return 0;
+ r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
+ if (r < 0)
+ return 0;
+ data = ~0;
+ r = kvm_write_guest_page(kvm, fn, &data, RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
+ sizeof(u8));
+ if (r < 0)
return 0;
- }
-
- page = kmap_atomic(p1, KM_USER0);
- clear_page(page);
- *(u16*)(page + 0x66) = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
- kunmap_atomic(page, KM_USER0);
-
- page = kmap_atomic(p2, KM_USER0);
- clear_page(page);
- kunmap_atomic(page, KM_USER0);
-
- page = kmap_atomic(p3, KM_USER0);
- clear_page(page);
- *(page + RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1) = ~0;
- kunmap_atomic(page, KM_USER0);
-
return 1;
}
vmcs_write32(sf->ar_bytes, 0x93);
}
+static int alloc_apic_access_page(struct kvm *kvm)
+{
+ struct kvm_userspace_memory_region kvm_userspace_mem;
+ int r = 0;
+
+ mutex_lock(&kvm->lock);
+ if (kvm->apic_access_page)
+ goto out;
+ kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
+ kvm_userspace_mem.flags = 0;
+ kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL;
+ kvm_userspace_mem.memory_size = PAGE_SIZE;
+ r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0);
+ if (r)
+ goto out;
+ kvm->apic_access_page = gfn_to_page(kvm, 0xfee00);
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
/*
* Sets up the vmcs for emulated real mode.
*/
unsigned long a;
struct descriptor_table dt;
int i;
- int ret = 0;
unsigned long kvm_vmx_return;
-
- if (!init_rmode_tss(vmx->vcpu.kvm)) {
- ret = -ENOMEM;
- goto out;
- }
-
- vmx->vcpu.regs[VCPU_REGS_RDX] = get_rdx_init_val();
- vmx->vcpu.cr8 = 0;
- vmx->vcpu.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
- if (vmx->vcpu.vcpu_id == 0)
- vmx->vcpu.apic_base |= MSR_IA32_APICBASE_BSP;
-
- fx_init(&vmx->vcpu);
-
- /*
- * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
- * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh.
- */
- vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
- vmcs_writel(GUEST_CS_BASE, 0x000f0000);
- vmcs_write32(GUEST_CS_LIMIT, 0xffff);
- vmcs_write32(GUEST_CS_AR_BYTES, 0x9b);
-
- seg_setup(VCPU_SREG_DS);
- seg_setup(VCPU_SREG_ES);
- seg_setup(VCPU_SREG_FS);
- seg_setup(VCPU_SREG_GS);
- seg_setup(VCPU_SREG_SS);
-
- vmcs_write16(GUEST_TR_SELECTOR, 0);
- vmcs_writel(GUEST_TR_BASE, 0);
- vmcs_write32(GUEST_TR_LIMIT, 0xffff);
- vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
-
- vmcs_write16(GUEST_LDTR_SELECTOR, 0);
- vmcs_writel(GUEST_LDTR_BASE, 0);
- vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
- vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);
-
- vmcs_write32(GUEST_SYSENTER_CS, 0);
- vmcs_writel(GUEST_SYSENTER_ESP, 0);
- vmcs_writel(GUEST_SYSENTER_EIP, 0);
-
- vmcs_writel(GUEST_RFLAGS, 0x02);
- vmcs_writel(GUEST_RIP, 0xfff0);
- vmcs_writel(GUEST_RSP, 0);
-
- //todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0
- vmcs_writel(GUEST_DR7, 0x400);
-
- vmcs_writel(GUEST_GDTR_BASE, 0);
- vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
-
- vmcs_writel(GUEST_IDTR_BASE, 0);
- vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);
-
- vmcs_write32(GUEST_ACTIVITY_STATE, 0);
- vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
- vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+ u32 exec_control;
/* I/O */
vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a));
vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b));
- guest_write_tsc(0);
-
vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
- /* Special registers */
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
-
/* Control */
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL,
vmcs_config.pin_based_exec_ctrl);
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
- vmcs_config.cpu_based_exec_ctrl);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
+ exec_control = vmcs_config.cpu_based_exec_ctrl;
+ if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) {
+ exec_control &= ~CPU_BASED_TPR_SHADOW;
+#ifdef CONFIG_X86_64
+ exec_control |= CPU_BASED_CR8_STORE_EXITING |
+ CPU_BASED_CR8_LOAD_EXITING;
+#endif
+ }
+ if (!vm_need_secondary_exec_ctrls(vmx->vcpu.kvm))
+ exec_control &= ~CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
+
+ if (vm_need_secondary_exec_ctrls(vmx->vcpu.kvm))
+ vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+ vmcs_config.cpu_based_2nd_exec_ctrl);
+
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf);
vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */
vmcs_writel(HOST_CR0, read_cr0()); /* 22.2.3 */
get_idt(&dt);
vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */
- asm ("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
+ asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
++vmx->nmsrs;
}
- setup_msrs(vmx);
-
vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
/* 22.2.1, 20.8.1 */
vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl);
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
+ vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);
+
+ if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
+ if (alloc_apic_access_page(vmx->vcpu.kvm) != 0)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 msr;
+ int ret;
+
+ if (!init_rmode_tss(vmx->vcpu.kvm)) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ vmx->vcpu.rmode.active = 0;
+
+ vmx->vcpu.regs[VCPU_REGS_RDX] = get_rdx_init_val();
+ set_cr8(&vmx->vcpu, 0);
+ msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+ if (vmx->vcpu.vcpu_id == 0)
+ msr |= MSR_IA32_APICBASE_BSP;
+ kvm_set_apic_base(&vmx->vcpu, msr);
+
+ fx_init(&vmx->vcpu);
+
+ /*
+ * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
+ * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh.
+ */
+ if (vmx->vcpu.vcpu_id == 0) {
+ vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
+ vmcs_writel(GUEST_CS_BASE, 0x000f0000);
+ } else {
+ vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.sipi_vector << 8);
+ vmcs_writel(GUEST_CS_BASE, vmx->vcpu.sipi_vector << 12);
+ }
+ vmcs_write32(GUEST_CS_LIMIT, 0xffff);
+ vmcs_write32(GUEST_CS_AR_BYTES, 0x9b);
+
+ seg_setup(VCPU_SREG_DS);
+ seg_setup(VCPU_SREG_ES);
+ seg_setup(VCPU_SREG_FS);
+ seg_setup(VCPU_SREG_GS);
+ seg_setup(VCPU_SREG_SS);
+
+ vmcs_write16(GUEST_TR_SELECTOR, 0);
+ vmcs_writel(GUEST_TR_BASE, 0);
+ vmcs_write32(GUEST_TR_LIMIT, 0xffff);
+ vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
+
+ vmcs_write16(GUEST_LDTR_SELECTOR, 0);
+ vmcs_writel(GUEST_LDTR_BASE, 0);
+ vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
+ vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);
+
+ vmcs_write32(GUEST_SYSENTER_CS, 0);
+ vmcs_writel(GUEST_SYSENTER_ESP, 0);
+ vmcs_writel(GUEST_SYSENTER_EIP, 0);
+
+ vmcs_writel(GUEST_RFLAGS, 0x02);
+ if (vmx->vcpu.vcpu_id == 0)
+ vmcs_writel(GUEST_RIP, 0xfff0);
+ else
+ vmcs_writel(GUEST_RIP, 0);
+ vmcs_writel(GUEST_RSP, 0);
+
+ /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */
+ vmcs_writel(GUEST_DR7, 0x400);
+
+ vmcs_writel(GUEST_GDTR_BASE, 0);
+ vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
+
+ vmcs_writel(GUEST_IDTR_BASE, 0);
+ vmcs_write32(GUEST_IDTR_LIMIT, 0xffff);
+
+ vmcs_write32(GUEST_ACTIVITY_STATE, 0);
+ vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
+ vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+
+ guest_write_tsc(0);
+
+ /* Special registers */
+ vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+
+ setup_msrs(vmx);
+
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */
-#ifdef CONFIG_X86_64
- vmcs_writel(VIRTUAL_APIC_PAGE_ADDR, 0);
- vmcs_writel(TPR_THRESHOLD, 0);
-#endif
+ if (cpu_has_vmx_tpr_shadow()) {
+ vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
+ if (vm_need_tpr_shadow(vmx->vcpu.kvm))
+ vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
+ page_to_phys(vmx->vcpu.apic->regs_page));
+ vmcs_write32(TPR_THRESHOLD, 0);
+ }
- vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
- vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);
+ if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
+ vmcs_write64(APIC_ACCESS_ADDR,
+ page_to_phys(vmx->vcpu.kvm->apic_access_page));
vmx->vcpu.cr0 = 0x60000010;
- vmx_set_cr0(&vmx->vcpu, vmx->vcpu.cr0); // enter rmode
+ vmx_set_cr0(&vmx->vcpu, vmx->vcpu.cr0); /* enter rmode */
vmx_set_cr4(&vmx->vcpu, 0);
#ifdef CONFIG_X86_64
vmx_set_efer(&vmx->vcpu, 0);
return ret;
}
-static void inject_rmode_irq(struct kvm_vcpu *vcpu, int irq)
+static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
{
- u16 ent[2];
- u16 cs;
- u16 ip;
- unsigned long flags;
- unsigned long ss_base = vmcs_readl(GUEST_SS_BASE);
- u16 sp = vmcs_readl(GUEST_RSP);
- u32 ss_limit = vmcs_read32(GUEST_SS_LIMIT);
-
- if (sp > ss_limit || sp < 6 ) {
- vcpu_printf(vcpu, "%s: #SS, rsp 0x%lx ss 0x%lx limit 0x%x\n",
- __FUNCTION__,
- vmcs_readl(GUEST_RSP),
- vmcs_readl(GUEST_SS_BASE),
- vmcs_read32(GUEST_SS_LIMIT));
- return;
- }
-
- if (emulator_read_std(irq * sizeof(ent), &ent, sizeof(ent), vcpu) !=
- X86EMUL_CONTINUE) {
- vcpu_printf(vcpu, "%s: read guest err\n", __FUNCTION__);
- return;
- }
-
- flags = vmcs_readl(GUEST_RFLAGS);
- cs = vmcs_readl(GUEST_CS_BASE) >> 4;
- ip = vmcs_readl(GUEST_RIP);
-
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (emulator_write_emulated(ss_base + sp - 2, &flags, 2, vcpu) != X86EMUL_CONTINUE ||
- emulator_write_emulated(ss_base + sp - 4, &cs, 2, vcpu) != X86EMUL_CONTINUE ||
- emulator_write_emulated(ss_base + sp - 6, &ip, 2, vcpu) != X86EMUL_CONTINUE) {
- vcpu_printf(vcpu, "%s: write guest err\n", __FUNCTION__);
+ if (vcpu->rmode.active) {
+ vmx->rmode.irq.pending = true;
+ vmx->rmode.irq.vector = irq;
+ vmx->rmode.irq.rip = vmcs_readl(GUEST_RIP);
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ irq | INTR_TYPE_SOFT_INTR | INTR_INFO_VALID_MASK);
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
+ vmcs_writel(GUEST_RIP, vmx->rmode.irq.rip - 1);
return;
}
-
- vmcs_writel(GUEST_RFLAGS, flags &
- ~( X86_EFLAGS_IF | X86_EFLAGS_AC | X86_EFLAGS_TF));
- vmcs_write16(GUEST_CS_SELECTOR, ent[1]) ;
- vmcs_writel(GUEST_CS_BASE, ent[1] << 4);
- vmcs_writel(GUEST_RIP, ent[0]);
- vmcs_writel(GUEST_RSP, (vmcs_readl(GUEST_RSP) & ~0xffff) | (sp - 6));
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
static void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
clear_bit(bit_index, &vcpu->irq_pending[word_index]);
if (!vcpu->irq_pending[word_index])
clear_bit(word_index, &vcpu->irq_summary);
-
- if (vcpu->rmode.active) {
- inject_rmode_irq(vcpu, irq);
- return;
- }
- vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
- irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
+ vmx_inject_irq(vcpu, irq);
}
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
}
+static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
+{
+ int ret;
+ struct kvm_userspace_memory_region tss_mem = {
+ .slot = 8,
+ .guest_phys_addr = addr,
+ .memory_size = PAGE_SIZE * 3,
+ .flags = 0,
+ };
+
+ ret = kvm_set_memory_region(kvm, &tss_mem, 0);
+ if (ret)
+ return ret;
+ kvm->tss_addr = addr;
+ return 0;
+}
+
static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
{
struct kvm_guest_debug *dbg = &vcpu->guest_debug;
* Cause the #SS fault with 0 error code in VM86 mode.
*/
if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0)
- if (emulate_instruction(vcpu, NULL, 0, 0) == EMULATE_DONE)
+ if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE)
return 1;
return 0;
}
static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info, error_code;
unsigned long cr2, rip;
u32 vect_info;
enum emulation_result er;
- int r;
- vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
+ vect_info = vmx->idt_vectoring_info;
intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
if ((vect_info & VECTORING_INFO_VALID_MASK) &&
- !is_page_fault(intr_info)) {
+ !is_page_fault(intr_info))
printk(KERN_ERR "%s: unexpected, vectoring info 0x%x "
"intr info 0x%x\n", __FUNCTION__, vect_info, intr_info);
- }
- if (is_external_interrupt(vect_info)) {
+ if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) {
int irq = vect_info & VECTORING_INFO_VECTOR_MASK;
set_bit(irq, vcpu->irq_pending);
set_bit(irq / BITS_PER_LONG, &vcpu->irq_summary);
}
- if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) { /* nmi */
- asm ("int $2");
- return 1;
- }
+ if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */
+ return 1; /* already handled by vmx_vcpu_run() */
if (is_no_device(intr_info)) {
vmx_fpu_activate(vcpu);
return 1;
}
+ if (is_invalid_opcode(intr_info)) {
+ er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
+ if (er != EMULATE_DONE)
+ vmx_inject_ud(vcpu);
+
+ return 1;
+ }
+
error_code = 0;
rip = vmcs_readl(GUEST_RIP);
if (intr_info & INTR_INFO_DELIEVER_CODE_MASK)
error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
if (is_page_fault(intr_info)) {
cr2 = vmcs_readl(EXIT_QUALIFICATION);
-
- mutex_lock(&vcpu->kvm->lock);
- r = kvm_mmu_page_fault(vcpu, cr2, error_code);
- if (r < 0) {
- mutex_unlock(&vcpu->kvm->lock);
- return r;
- }
- if (!r) {
- mutex_unlock(&vcpu->kvm->lock);
- return 1;
- }
-
- er = emulate_instruction(vcpu, kvm_run, cr2, error_code);
- mutex_unlock(&vcpu->kvm->lock);
-
- switch (er) {
- case EMULATE_DONE:
- return 1;
- case EMULATE_DO_MMIO:
- ++vcpu->stat.mmio_exits;
- return 0;
- case EMULATE_FAIL:
- vcpu_printf(vcpu, "%s: emulate fail\n", __FUNCTION__);
- break;
- default:
- BUG();
- }
+ return kvm_mmu_page_fault(vcpu, cr2, error_code);
}
if (vcpu->rmode.active &&
return 1;
}
- if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == (INTR_TYPE_EXCEPTION | 1)) {
+ if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) ==
+ (INTR_TYPE_EXCEPTION | 1)) {
kvm_run->exit_reason = KVM_EXIT_DEBUG;
return 0;
}
static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
- u64 exit_qualification;
+ unsigned long exit_qualification;
int size, down, in, string, rep;
unsigned port;
++vcpu->stat.io_exits;
- exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
+ exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
string = (exit_qualification & 16) != 0;
if (string) {
- if (emulate_instruction(vcpu, kvm_run, 0, 0) == EMULATE_DO_MMIO)
+ if (emulate_instruction(vcpu,
+ kvm_run, 0, 0, 0) == EMULATE_DO_MMIO)
return 0;
return 1;
}
hypercall[0] = 0x0f;
hypercall[1] = 0x01;
hypercall[2] = 0xc1;
- hypercall[3] = 0xc3;
}
static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
- u64 exit_qualification;
+ unsigned long exit_qualification;
int cr;
int reg;
- exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
+ exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
cr = exit_qualification & 15;
reg = (exit_qualification >> 8) & 15;
switch ((exit_qualification >> 4) & 3) {
return 1;
case 8:
vcpu_load_rsp_rip(vcpu);
- vcpu->regs[reg] = vcpu->cr8;
+ vcpu->regs[reg] = get_cr8(vcpu);
vcpu_put_rsp_rip(vcpu);
skip_emulated_instruction(vcpu);
return 1;
static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
- u64 exit_qualification;
+ unsigned long exit_qualification;
unsigned long val;
int dr, reg;
* FIXME: this code assumes the host is debugging the guest.
* need to deal with guest debugging itself too.
*/
- exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
+ exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
dr = exit_qualification & 7;
reg = (exit_qualification >> 8) & 15;
vcpu_load_rsp_rip(vcpu);
return 1;
}
-static void post_kvm_run_save(struct kvm_vcpu *vcpu,
- struct kvm_run *kvm_run)
+static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu,
+ struct kvm_run *kvm_run)
{
- kvm_run->if_flag = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) != 0;
- kvm_run->cr8 = vcpu->cr8;
- kvm_run->apic_base = vcpu->apic_base;
- kvm_run->ready_for_interrupt_injection = (vcpu->interrupt_window_open &&
- vcpu->irq_summary == 0);
+ return 1;
}
static int handle_interrupt_window(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
+ u32 cpu_based_vm_exec_control;
+
+ /* clear pending irq */
+ cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
/*
* If the user space waits to inject interrupts, exit as soon as
* possible
static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
skip_emulated_instruction(vcpu);
- return kvm_hypercall(vcpu, kvm_run);
+ kvm_emulate_hypercall(vcpu);
+ return 1;
+}
+
+static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ skip_emulated_instruction(vcpu);
+ /* TODO: Add support for VT-d/pass-through device */
+ return 1;
+}
+
+static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ u64 exit_qualification;
+ enum emulation_result er;
+ unsigned long offset;
+
+ exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
+ offset = exit_qualification & 0xffful;
+
+ er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
+
+ if (er != EMULATE_DONE) {
+ printk(KERN_ERR
+ "Fail to handle apic access vmexit! Offset is 0x%lx\n",
+ offset);
+ return -ENOTSUPP;
+ }
+ return 1;
}
/*
[EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window,
[EXIT_REASON_HLT] = handle_halt,
[EXIT_REASON_VMCALL] = handle_vmcall,
+ [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,
+ [EXIT_REASON_APIC_ACCESS] = handle_apic_access,
+ [EXIT_REASON_WBINVD] = handle_wbinvd,
};
static const int kvm_vmx_max_exit_handlers =
*/
static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
- u32 vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
u32 exit_reason = vmcs_read32(VM_EXIT_REASON);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 vectoring_info = vmx->idt_vectoring_info;
+
+ if (unlikely(vmx->fail)) {
+ kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ kvm_run->fail_entry.hardware_entry_failure_reason
+ = vmcs_read32(VM_INSTRUCTION_ERROR);
+ return 0;
+ }
- if ( (vectoring_info & VECTORING_INFO_VALID_MASK) &&
- exit_reason != EXIT_REASON_EXCEPTION_NMI )
+ if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ exit_reason != EXIT_REASON_EXCEPTION_NMI)
printk(KERN_WARNING "%s: unexpected, valid vectoring info and "
"exit reason is 0x%x\n", __FUNCTION__, exit_reason);
if (exit_reason < kvm_vmx_max_exit_handlers
return 0;
}
-/*
- * Check if userspace requested an interrupt window, and that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
-static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
- struct kvm_run *kvm_run)
+static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
{
- return (!vcpu->irq_summary &&
- kvm_run->request_interrupt_window &&
- vcpu->interrupt_window_open &&
- (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF));
}
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+static void update_tpr_threshold(struct kvm_vcpu *vcpu)
{
+ int max_irr, tpr;
+
+ if (!vm_need_tpr_shadow(vcpu->kvm))
+ return;
+
+ if (!kvm_lapic_enabled(vcpu) ||
+ ((max_irr = kvm_lapic_find_highest_irr(vcpu)) == -1)) {
+ vmcs_write32(TPR_THRESHOLD, 0);
+ return;
+ }
+
+ tpr = (kvm_lapic_get_cr8(vcpu) & 0x0f) << 4;
+ vmcs_write32(TPR_THRESHOLD, (max_irr > tpr) ? tpr >> 4 : max_irr >> 4);
}
-static int vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void enable_irq_window(struct kvm_vcpu *vcpu)
+{
+ u32 cpu_based_vm_exec_control;
+
+ cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+}
+
+static void vmx_intr_assist(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u8 fail;
- int r;
+ u32 idtv_info_field, intr_info_field;
+ int has_ext_irq, interrupt_window_open;
+ int vector;
+
+ update_tpr_threshold(vcpu);
+
+ has_ext_irq = kvm_cpu_has_interrupt(vcpu);
+ intr_info_field = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD);
+ idtv_info_field = vmx->idt_vectoring_info;
+ if (intr_info_field & INTR_INFO_VALID_MASK) {
+ if (idtv_info_field & INTR_INFO_VALID_MASK) {
+ /* TODO: fault when IDT_Vectoring */
+ printk(KERN_ERR "Fault when IDT_Vectoring\n");
+ }
+ if (has_ext_irq)
+ enable_irq_window(vcpu);
+ return;
+ }
+ if (unlikely(idtv_info_field & INTR_INFO_VALID_MASK)) {
+ if ((idtv_info_field & VECTORING_INFO_TYPE_MASK)
+ == INTR_TYPE_EXT_INTR
+ && vcpu->rmode.active) {
+ u8 vect = idtv_info_field & VECTORING_INFO_VECTOR_MASK;
+
+ vmx_inject_irq(vcpu, vect);
+ if (unlikely(has_ext_irq))
+ enable_irq_window(vcpu);
+ return;
+ }
-preempted:
- if (vcpu->guest_debug.enabled)
- kvm_guest_debug_pre(vcpu);
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field);
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
-again:
- r = kvm_mmu_reload(vcpu);
- if (unlikely(r))
- goto out;
+ if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK))
+ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
+ vmcs_read32(IDT_VECTORING_ERROR_CODE));
+ if (unlikely(has_ext_irq))
+ enable_irq_window(vcpu);
+ return;
+ }
+ if (!has_ext_irq)
+ return;
+ interrupt_window_open =
+ ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+ (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0);
+ if (interrupt_window_open) {
+ vector = kvm_cpu_get_interrupt(vcpu);
+ vmx_inject_irq(vcpu, vector);
+ kvm_timer_intr_post(vcpu, vector);
+ } else
+ enable_irq_window(vcpu);
+}
- preempt_disable();
+/*
+ * Failure to inject an interrupt should give us the information
+ * in IDT_VECTORING_INFO_FIELD. However, if the failure occurs
+ * when fetching the interrupt redirection bitmap in the real-mode
+ * tss, this doesn't happen. So we do it ourselves.
+ */
+static void fixup_rmode_irq(struct vcpu_vmx *vmx)
+{
+ vmx->rmode.irq.pending = 0;
+ if (vmcs_readl(GUEST_RIP) + 1 != vmx->rmode.irq.rip)
+ return;
+ vmcs_writel(GUEST_RIP, vmx->rmode.irq.rip);
+ if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) {
+ vmx->idt_vectoring_info &= ~VECTORING_INFO_TYPE_MASK;
+ vmx->idt_vectoring_info |= INTR_TYPE_EXT_INTR;
+ return;
+ }
+ vmx->idt_vectoring_info =
+ VECTORING_INFO_VALID_MASK
+ | INTR_TYPE_EXT_INTR
+ | vmx->rmode.irq.vector;
+}
- vmx_save_host_state(vmx);
- kvm_load_guest_fpu(vcpu);
+static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 intr_info;
/*
* Loading guest fpu may have cleared host cr0.ts
*/
vmcs_writel(HOST_CR0, read_cr0());
- local_irq_disable();
-
- if (signal_pending(current)) {
- local_irq_enable();
- preempt_enable();
- r = -EINTR;
- kvm_run->exit_reason = KVM_EXIT_INTR;
- ++vcpu->stat.signal_exits;
- goto out;
- }
-
- if (!vcpu->mmio_read_completed)
- do_interrupt_requests(vcpu, kvm_run);
-
- vcpu->guest_mode = 1;
- if (vcpu->requests)
- if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
- vmx_flush_tlb(vcpu);
-
- asm (
+ asm(
/* Store host registers */
#ifdef CONFIG_X86_64
- "push %%rax; push %%rbx; push %%rdx;"
- "push %%rsi; push %%rdi; push %%rbp;"
- "push %%r8; push %%r9; push %%r10; push %%r11;"
- "push %%r12; push %%r13; push %%r14; push %%r15;"
+ "push %%rdx; push %%rbp;"
"push %%rcx \n\t"
- ASM_VMX_VMWRITE_RSP_RDX "\n\t"
#else
- "pusha; push %%ecx \n\t"
- ASM_VMX_VMWRITE_RSP_RDX "\n\t"
+ "push %%edx; push %%ebp;"
+ "push %%ecx \n\t"
#endif
+ ASM_VMX_VMWRITE_RSP_RDX "\n\t"
/* Check if vmlaunch of vmresume is needed */
- "cmp $0, %1 \n\t"
+ "cmpl $0, %c[launched](%0) \n\t"
/* Load guest registers. Don't clobber flags. */
#ifdef CONFIG_X86_64
- "mov %c[cr2](%3), %%rax \n\t"
+ "mov %c[cr2](%0), %%rax \n\t"
"mov %%rax, %%cr2 \n\t"
- "mov %c[rax](%3), %%rax \n\t"
- "mov %c[rbx](%3), %%rbx \n\t"
- "mov %c[rdx](%3), %%rdx \n\t"
- "mov %c[rsi](%3), %%rsi \n\t"
- "mov %c[rdi](%3), %%rdi \n\t"
- "mov %c[rbp](%3), %%rbp \n\t"
- "mov %c[r8](%3), %%r8 \n\t"
- "mov %c[r9](%3), %%r9 \n\t"
- "mov %c[r10](%3), %%r10 \n\t"
- "mov %c[r11](%3), %%r11 \n\t"
- "mov %c[r12](%3), %%r12 \n\t"
- "mov %c[r13](%3), %%r13 \n\t"
- "mov %c[r14](%3), %%r14 \n\t"
- "mov %c[r15](%3), %%r15 \n\t"
- "mov %c[rcx](%3), %%rcx \n\t" /* kills %3 (rcx) */
+ "mov %c[rax](%0), %%rax \n\t"
+ "mov %c[rbx](%0), %%rbx \n\t"
+ "mov %c[rdx](%0), %%rdx \n\t"
+ "mov %c[rsi](%0), %%rsi \n\t"
+ "mov %c[rdi](%0), %%rdi \n\t"
+ "mov %c[rbp](%0), %%rbp \n\t"
+ "mov %c[r8](%0), %%r8 \n\t"
+ "mov %c[r9](%0), %%r9 \n\t"
+ "mov %c[r10](%0), %%r10 \n\t"
+ "mov %c[r11](%0), %%r11 \n\t"
+ "mov %c[r12](%0), %%r12 \n\t"
+ "mov %c[r13](%0), %%r13 \n\t"
+ "mov %c[r14](%0), %%r14 \n\t"
+ "mov %c[r15](%0), %%r15 \n\t"
+ "mov %c[rcx](%0), %%rcx \n\t" /* kills %0 (rcx) */
#else
- "mov %c[cr2](%3), %%eax \n\t"
+ "mov %c[cr2](%0), %%eax \n\t"
"mov %%eax, %%cr2 \n\t"
- "mov %c[rax](%3), %%eax \n\t"
- "mov %c[rbx](%3), %%ebx \n\t"
- "mov %c[rdx](%3), %%edx \n\t"
- "mov %c[rsi](%3), %%esi \n\t"
- "mov %c[rdi](%3), %%edi \n\t"
- "mov %c[rbp](%3), %%ebp \n\t"
- "mov %c[rcx](%3), %%ecx \n\t" /* kills %3 (ecx) */
+ "mov %c[rax](%0), %%eax \n\t"
+ "mov %c[rbx](%0), %%ebx \n\t"
+ "mov %c[rdx](%0), %%edx \n\t"
+ "mov %c[rsi](%0), %%esi \n\t"
+ "mov %c[rdi](%0), %%edi \n\t"
+ "mov %c[rbp](%0), %%ebp \n\t"
+ "mov %c[rcx](%0), %%ecx \n\t" /* kills %0 (ecx) */
#endif
/* Enter guest mode */
"jne .Llaunched \n\t"
".Lkvm_vmx_return: "
/* Save guest registers, load host registers, keep flags */
#ifdef CONFIG_X86_64
- "xchg %3, (%%rsp) \n\t"
- "mov %%rax, %c[rax](%3) \n\t"
- "mov %%rbx, %c[rbx](%3) \n\t"
- "pushq (%%rsp); popq %c[rcx](%3) \n\t"
- "mov %%rdx, %c[rdx](%3) \n\t"
- "mov %%rsi, %c[rsi](%3) \n\t"
- "mov %%rdi, %c[rdi](%3) \n\t"
- "mov %%rbp, %c[rbp](%3) \n\t"
- "mov %%r8, %c[r8](%3) \n\t"
- "mov %%r9, %c[r9](%3) \n\t"
- "mov %%r10, %c[r10](%3) \n\t"
- "mov %%r11, %c[r11](%3) \n\t"
- "mov %%r12, %c[r12](%3) \n\t"
- "mov %%r13, %c[r13](%3) \n\t"
- "mov %%r14, %c[r14](%3) \n\t"
- "mov %%r15, %c[r15](%3) \n\t"
+ "xchg %0, (%%rsp) \n\t"
+ "mov %%rax, %c[rax](%0) \n\t"
+ "mov %%rbx, %c[rbx](%0) \n\t"
+ "pushq (%%rsp); popq %c[rcx](%0) \n\t"
+ "mov %%rdx, %c[rdx](%0) \n\t"
+ "mov %%rsi, %c[rsi](%0) \n\t"
+ "mov %%rdi, %c[rdi](%0) \n\t"
+ "mov %%rbp, %c[rbp](%0) \n\t"
+ "mov %%r8, %c[r8](%0) \n\t"
+ "mov %%r9, %c[r9](%0) \n\t"
+ "mov %%r10, %c[r10](%0) \n\t"
+ "mov %%r11, %c[r11](%0) \n\t"
+ "mov %%r12, %c[r12](%0) \n\t"
+ "mov %%r13, %c[r13](%0) \n\t"
+ "mov %%r14, %c[r14](%0) \n\t"
+ "mov %%r15, %c[r15](%0) \n\t"
"mov %%cr2, %%rax \n\t"
- "mov %%rax, %c[cr2](%3) \n\t"
- "mov (%%rsp), %3 \n\t"
+ "mov %%rax, %c[cr2](%0) \n\t"
- "pop %%rcx; pop %%r15; pop %%r14; pop %%r13; pop %%r12;"
- "pop %%r11; pop %%r10; pop %%r9; pop %%r8;"
- "pop %%rbp; pop %%rdi; pop %%rsi;"
- "pop %%rdx; pop %%rbx; pop %%rax \n\t"
+ "pop %%rbp; pop %%rbp; pop %%rdx \n\t"
#else
- "xchg %3, (%%esp) \n\t"
- "mov %%eax, %c[rax](%3) \n\t"
- "mov %%ebx, %c[rbx](%3) \n\t"
- "pushl (%%esp); popl %c[rcx](%3) \n\t"
- "mov %%edx, %c[rdx](%3) \n\t"
- "mov %%esi, %c[rsi](%3) \n\t"
- "mov %%edi, %c[rdi](%3) \n\t"
- "mov %%ebp, %c[rbp](%3) \n\t"
+ "xchg %0, (%%esp) \n\t"
+ "mov %%eax, %c[rax](%0) \n\t"
+ "mov %%ebx, %c[rbx](%0) \n\t"
+ "pushl (%%esp); popl %c[rcx](%0) \n\t"
+ "mov %%edx, %c[rdx](%0) \n\t"
+ "mov %%esi, %c[rsi](%0) \n\t"
+ "mov %%edi, %c[rdi](%0) \n\t"
+ "mov %%ebp, %c[rbp](%0) \n\t"
"mov %%cr2, %%eax \n\t"
- "mov %%eax, %c[cr2](%3) \n\t"
- "mov (%%esp), %3 \n\t"
+ "mov %%eax, %c[cr2](%0) \n\t"
- "pop %%ecx; popa \n\t"
+ "pop %%ebp; pop %%ebp; pop %%edx \n\t"
#endif
- "setbe %0 \n\t"
- : "=q" (fail)
- : "r"(vmx->launched), "d"((unsigned long)HOST_RSP),
- "c"(vcpu),
- [rax]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RAX])),
- [rbx]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RBX])),
- [rcx]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RCX])),
- [rdx]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RDX])),
- [rsi]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RSI])),
- [rdi]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RDI])),
- [rbp]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RBP])),
+ "setbe %c[fail](%0) \n\t"
+ : : "c"(vmx), "d"((unsigned long)HOST_RSP),
+ [launched]"i"(offsetof(struct vcpu_vmx, launched)),
+ [fail]"i"(offsetof(struct vcpu_vmx, fail)),
+ [rax]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_RAX])),
+ [rbx]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_RBX])),
+ [rcx]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_RCX])),
+ [rdx]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_RDX])),
+ [rsi]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_RSI])),
+ [rdi]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_RDI])),
+ [rbp]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_RBP])),
#ifdef CONFIG_X86_64
- [r8 ]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R8 ])),
- [r9 ]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R9 ])),
- [r10]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R10])),
- [r11]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R11])),
- [r12]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R12])),
- [r13]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R13])),
- [r14]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R14])),
- [r15]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R15])),
+ [r8]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R8])),
+ [r9]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R9])),
+ [r10]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R10])),
+ [r11]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R11])),
+ [r12]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R12])),
+ [r13]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R13])),
+ [r14]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R14])),
+ [r15]"i"(offsetof(struct vcpu_vmx, vcpu.regs[VCPU_REGS_R15])),
#endif
- [cr2]"i"(offsetof(struct kvm_vcpu, cr2))
- : "cc", "memory" );
-
- vcpu->guest_mode = 0;
- local_irq_enable();
+ [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.cr2))
+ : "cc", "memory"
+#ifdef CONFIG_X86_64
+ , "rbx", "rdi", "rsi"
+ , "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
+#else
+ , "ebx", "edi", "rsi"
+#endif
+ );
- ++vcpu->stat.exits;
+ vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
+ if (vmx->rmode.irq.pending)
+ fixup_rmode_irq(vmx);
- vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0;
+ vcpu->interrupt_window_open =
+ (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0;
- asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
+ asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
vmx->launched = 1;
- preempt_enable();
-
- if (unlikely(fail)) {
- kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
- kvm_run->fail_entry.hardware_entry_failure_reason
- = vmcs_read32(VM_INSTRUCTION_ERROR);
- r = 0;
- goto out;
- }
- /*
- * Profile KVM exit RIPs:
- */
- if (unlikely(prof_on == KVM_PROFILING))
- profile_hit(KVM_PROFILING, (void *)vmcs_readl(GUEST_RIP));
-
- r = kvm_handle_exit(kvm_run, vcpu);
- if (r > 0) {
- if (dm_request_for_irq_injection(vcpu, kvm_run)) {
- r = -EINTR;
- kvm_run->exit_reason = KVM_EXIT_INTR;
- ++vcpu->stat.request_irq_exits;
- goto out;
- }
- if (!need_resched()) {
- ++vcpu->stat.light_exits;
- goto again;
- }
- }
-
-out:
- if (r > 0) {
- kvm_resched(vcpu);
- goto preempted;
- }
+ intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- post_kvm_run_save(vcpu, kvm_run);
- return r;
+ /* We need to handle NMIs before interrupts are enabled */
+ if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */
+ asm("int $2");
}
static void vmx_inject_page_fault(struct kvm_vcpu *vcpu,
unsigned long addr,
u32 err_code)
{
- u32 vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 vect_info = vmx->idt_vectoring_info;
++vcpu->stat.pf_guest;
}
}
-static struct kvm_arch_ops vmx_arch_ops = {
+static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.hardware_setup = hardware_setup,
.vcpu_create = vmx_create_vcpu,
.vcpu_free = vmx_free_vcpu,
+ .vcpu_reset = vmx_vcpu_reset,
+ .prepare_guest_switch = vmx_save_host_state,
.vcpu_load = vmx_vcpu_load,
.vcpu_put = vmx_vcpu_put,
.vcpu_decache = vmx_vcpu_decache,
.set_guest_debug = set_guest_debug,
+ .guest_debug_pre = kvm_guest_debug_pre,
.get_msr = vmx_get_msr,
.set_msr = vmx_set_msr,
.get_segment_base = vmx_get_segment_base,
.inject_gp = vmx_inject_gp,
.run = vmx_vcpu_run,
+ .handle_exit = kvm_handle_exit,
.skip_emulated_instruction = skip_emulated_instruction,
.patch_hypercall = vmx_patch_hypercall,
+ .get_irq = vmx_get_irq,
+ .set_irq = vmx_inject_irq,
+ .inject_pending_irq = vmx_intr_assist,
+ .inject_pending_vectors = do_interrupt_requests,
+
+ .set_tss_addr = vmx_set_tss_addr,
};
static int __init vmx_init(void)
memset(iova, 0xff, PAGE_SIZE);
kunmap(vmx_io_bitmap_b);
- r = kvm_init_arch(&vmx_arch_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
if (r)
goto out1;
+ if (bypass_guest_pf)
+ kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
+
return 0;
out1:
__free_page(vmx_io_bitmap_b);
__free_page(vmx_io_bitmap_a);
- kvm_exit_arch();
+ kvm_exit();
}
module_init(vmx_init)
git.openpandora.org / pandora-kernel.git / blobdiff