aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kvm/vmx.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2008-04-27 10:13:52 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-04-27 10:13:52 -0700
commit42cadc86008aae0fd9ff31642dc01ed50723cf32 (patch)
treeb05d4c8f0561bad5a0183a89fb23ce4c8ee1653c /arch/x86/kvm/vmx.c
parentfba5c1af5c4fd6645fe62ea84ccde0981282cf66 (diff)
parent66c0b394f08fd89236515c1c84485ea712a157be (diff)
Merge branch 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm
* 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (147 commits) KVM: kill file->f_count abuse in kvm KVM: MMU: kvm_pv_mmu_op should not take mmap_sem KVM: SVM: remove selective CR0 comment KVM: SVM: remove now obsolete FIXME comment KVM: SVM: disable CR8 intercept when tpr is not masking interrupts KVM: SVM: sync V_TPR with LAPIC.TPR if CR8 write intercept is disabled KVM: export kvm_lapic_set_tpr() to modules KVM: SVM: sync TPR value to V_TPR field in the VMCB KVM: ppc: PowerPC 440 KVM implementation KVM: Add MAINTAINERS entry for PowerPC KVM KVM: ppc: Add DCR access information to struct kvm_run ppc: Export tlb_44x_hwater for KVM KVM: Rename debugfs_dir to kvm_debugfs_dir KVM: x86 emulator: fix lea to really get the effective address KVM: x86 emulator: fix smsw and lmsw with a memory operand KVM: x86 emulator: initialize src.val and dst.val for register operands KVM: SVM: force a new asid when initializing the vmcb KVM: fix kvm_vcpu_kick vs __vcpu_run race KVM: add ioctls to save/store mpstate KVM: Rename VCPU_MP_STATE_* to KVM_MP_STATE_* ...
Diffstat (limited to 'arch/x86/kvm/vmx.c')
-rw-r--r--arch/x86/kvm/vmx.c278
1 files changed, 234 insertions, 44 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8e1462880d1..8e5d6645b90 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -17,7 +17,6 @@
#include "irq.h"
#include "vmx.h"
-#include "segment_descriptor.h"
#include "mmu.h"
#include <linux/kvm_host.h>
@@ -37,6 +36,12 @@ MODULE_LICENSE("GPL");
static int bypass_guest_pf = 1;
module_param(bypass_guest_pf, bool, 0);
+static int enable_vpid = 1;
+module_param(enable_vpid, bool, 0);
+
+static int flexpriority_enabled = 1;
+module_param(flexpriority_enabled, bool, 0);
+
struct vmcs {
u32 revision_id;
u32 abort;
@@ -71,6 +76,7 @@ struct vcpu_vmx {
unsigned rip;
} irq;
} rmode;
+ int vpid;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
@@ -85,6 +91,10 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
static struct page *vmx_io_bitmap_a;
static struct page *vmx_io_bitmap_b;
+static struct page *vmx_msr_bitmap;
+
+static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
+static DEFINE_SPINLOCK(vmx_vpid_lock);
static struct vmcs_config {
int size;
@@ -176,6 +186,11 @@ static inline int is_external_interrupt(u32 intr_info)
== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
+static inline int cpu_has_vmx_msr_bitmap(void)
+{
+ return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS);
+}
+
static inline int cpu_has_vmx_tpr_shadow(void)
{
return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW);
@@ -194,8 +209,9 @@ static inline int cpu_has_secondary_exec_ctrls(void)
static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
{
- return (vmcs_config.cpu_based_2nd_exec_ctrl &
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+ return flexpriority_enabled
+ && (vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
}
static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
@@ -204,6 +220,12 @@ static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
(irqchip_in_kernel(kvm)));
}
+static inline int cpu_has_vmx_vpid(void)
+{
+ return (vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_ENABLE_VPID);
+}
+
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
int i;
@@ -214,6 +236,20 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
return -1;
}
+static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+{
+ struct {
+ u64 vpid : 16;
+ u64 rsvd : 48;
+ u64 gva;
+ } operand = { vpid, 0, gva };
+
+ asm volatile (ASM_VMX_INVVPID
+ /* CF==1 or ZF==1 --> rc = -1 */
+ "; ja 1f ; ud2 ; 1:"
+ : : "a"(&operand), "c"(ext) : "cc", "memory");
+}
+
static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
{
int i;
@@ -257,6 +293,14 @@ static void vcpu_clear(struct vcpu_vmx *vmx)
vmx->launched = 0;
}
+static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx)
+{
+ if (vmx->vpid == 0)
+ return;
+
+ __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0);
+}
+
static unsigned long vmcs_readl(unsigned long field)
{
unsigned long value;
@@ -353,7 +397,7 @@ static void reload_tss(void)
* VT restores TR but not its size. Useless.
*/
struct descriptor_table gdt;
- struct segment_descriptor *descs;
+ struct desc_struct *descs;
get_gdt(&gdt);
descs = (void *)gdt.base;
@@ -485,11 +529,12 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 phys_addr = __pa(vmx->vmcs);
- u64 tsc_this, delta;
+ u64 tsc_this, delta, new_offset;
if (vcpu->cpu != cpu) {
vcpu_clear(vmx);
kvm_migrate_apic_timer(vcpu);
+ vpid_sync_vcpu_all(vmx);
}
if (per_cpu(current_vmcs, cpu) != vmx->vmcs) {
@@ -524,8 +569,11 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
* Make sure the time stamp counter is monotonous.
*/
rdtscll(tsc_this);
- delta = vcpu->arch.host_tsc - tsc_this;
- vmcs_write64(TSC_OFFSET, vmcs_read64(TSC_OFFSET) + delta);
+ if (tsc_this < vcpu->arch.host_tsc) {
+ delta = vcpu->arch.host_tsc - tsc_this;
+ new_offset = vmcs_read64(TSC_OFFSET) + delta;
+ vmcs_write64(TSC_OFFSET, new_offset);
+ }
}
}
@@ -596,7 +644,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
{
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
nr | INTR_TYPE_EXCEPTION
- | (has_error_code ? INTR_INFO_DELIEVER_CODE_MASK : 0)
+ | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
| INTR_INFO_VALID_MASK);
if (has_error_code)
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
@@ -959,6 +1007,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING;
opt = CPU_BASED_TPR_SHADOW |
+ CPU_BASED_USE_MSR_BITMAPS |
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
&_cpu_based_exec_control) < 0)
@@ -971,7 +1020,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
min = 0;
opt = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
- SECONDARY_EXEC_WBINVD_EXITING;
+ SECONDARY_EXEC_WBINVD_EXITING |
+ SECONDARY_EXEC_ENABLE_VPID;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
return -EIO;
@@ -1080,6 +1130,10 @@ static __init int hardware_setup(void)
{
if (setup_vmcs_config(&vmcs_config) < 0)
return -EIO;
+
+ if (boot_cpu_has(X86_FEATURE_NX))
+ kvm_enable_efer_bits(EFER_NX);
+
return alloc_kvm_area();
}
@@ -1214,7 +1268,7 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
printk(KERN_DEBUG "%s: tss fixup for long mode. \n",
- __FUNCTION__);
+ __func__);
vmcs_write32(GUEST_TR_AR_BYTES,
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
@@ -1239,6 +1293,11 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
#endif
+static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ vpid_sync_vcpu_all(to_vmx(vcpu));
+}
+
static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK;
@@ -1275,6 +1334,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
+ vmx_flush_tlb(vcpu);
vmcs_writel(GUEST_CR3, cr3);
if (vcpu->arch.cr0 & X86_CR0_PE)
vmx_fpu_deactivate(vcpu);
@@ -1288,14 +1348,14 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
vcpu->arch.cr4 = cr4;
}
-#ifdef CONFIG_X86_64
-
static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
vcpu->arch.shadow_efer = efer;
+ if (!msr)
+ return;
if (efer & EFER_LMA) {
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS) |
@@ -1312,8 +1372,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
setup_msrs(vmx);
}
-#endif
-
static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
@@ -1344,6 +1402,20 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
var->unusable = (ar >> 16) & 1;
}
+static int vmx_get_cpl(struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment kvm_seg;
+
+ if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */
+ return 0;
+
+ if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */
+ return 3;
+
+ vmx_get_segment(vcpu, &kvm_seg, VCPU_SREG_CS);
+ return kvm_seg.selector & 3;
+}
+
static u32 vmx_segment_access_rights(struct kvm_segment *var)
{
u32 ar;
@@ -1433,7 +1505,6 @@ static int init_rmode_tss(struct kvm *kvm)
int ret = 0;
int r;
- down_read(&kvm->slots_lock);
r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
if (r < 0)
goto out;
@@ -1456,7 +1527,6 @@ static int init_rmode_tss(struct kvm *kvm)
ret = 1;
out:
- up_read(&kvm->slots_lock);
return ret;
}
@@ -1494,6 +1564,46 @@ out:
return r;
}
+static void allocate_vpid(struct vcpu_vmx *vmx)
+{
+ int vpid;
+
+ vmx->vpid = 0;
+ if (!enable_vpid || !cpu_has_vmx_vpid())
+ return;
+ spin_lock(&vmx_vpid_lock);
+ vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
+ if (vpid < VMX_NR_VPIDS) {
+ vmx->vpid = vpid;
+ __set_bit(vpid, vmx_vpid_bitmap);
+ }
+ spin_unlock(&vmx_vpid_lock);
+}
+
+void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
+{
+ void *va;
+
+ if (!cpu_has_vmx_msr_bitmap())
+ return;
+
+ /*
+ * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+ * have the write-low and read-high bitmap offsets the wrong way round.
+ * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+ */
+ va = kmap(msr_bitmap);
+ if (msr <= 0x1fff) {
+ __clear_bit(msr, va + 0x000); /* read-low */
+ __clear_bit(msr, va + 0x800); /* write-low */
+ } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+ msr &= 0x1fff;
+ __clear_bit(msr, va + 0x400); /* read-high */
+ __clear_bit(msr, va + 0xc00); /* write-high */
+ }
+ kunmap(msr_bitmap);
+}
+
/*
* Sets up the vmcs for emulated real mode.
*/
@@ -1511,6 +1621,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a));
vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b));
+ if (cpu_has_vmx_msr_bitmap())
+ vmcs_write64(MSR_BITMAP, page_to_phys(vmx_msr_bitmap));
+
vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
/* Control */
@@ -1532,6 +1645,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
exec_control &=
~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ if (vmx->vpid == 0)
+ exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
@@ -1613,6 +1728,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
u64 msr;
int ret;
+ down_read(&vcpu->kvm->slots_lock);
if (!init_rmode_tss(vmx->vcpu.kvm)) {
ret = -ENOMEM;
goto out;
@@ -1621,7 +1737,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->vcpu.arch.rmode.active = 0;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
- set_cr8(&vmx->vcpu, 0);
+ kvm_set_cr8(&vmx->vcpu, 0);
msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
if (vmx->vcpu.vcpu_id == 0)
msr |= MSR_IA32_APICBASE_BSP;
@@ -1704,18 +1820,22 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write64(APIC_ACCESS_ADDR,
page_to_phys(vmx->vcpu.kvm->arch.apic_access_page));
+ if (vmx->vpid != 0)
+ vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+
vmx->vcpu.arch.cr0 = 0x60000010;
vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */
vmx_set_cr4(&vmx->vcpu, 0);
-#ifdef CONFIG_X86_64
vmx_set_efer(&vmx->vcpu, 0);
-#endif
vmx_fpu_activate(&vmx->vcpu);
update_exception_bitmap(&vmx->vcpu);
- return 0;
+ vpid_sync_vcpu_all(vmx);
+
+ ret = 0;
out:
+ up_read(&vcpu->kvm->slots_lock);
return ret;
}
@@ -1723,6 +1843,8 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler);
+
if (vcpu->arch.rmode.active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = irq;
@@ -1844,7 +1966,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if ((vect_info & VECTORING_INFO_VALID_MASK) &&
!is_page_fault(intr_info))
printk(KERN_ERR "%s: unexpected, vectoring info 0x%x "
- "intr info 0x%x\n", __FUNCTION__, vect_info, intr_info);
+ "intr info 0x%x\n", __func__, vect_info, intr_info);
if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) {
int irq = vect_info & VECTORING_INFO_VECTOR_MASK;
@@ -1869,10 +1991,12 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
error_code = 0;
rip = vmcs_readl(GUEST_RIP);
- if (intr_info & INTR_INFO_DELIEVER_CODE_MASK)
+ if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
if (is_page_fault(intr_info)) {
cr2 = vmcs_readl(EXIT_QUALIFICATION);
+ KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2,
+ (u32)((u64)cr2 >> 32), handler);
return kvm_mmu_page_fault(vcpu, cr2, error_code);
}
@@ -1901,6 +2025,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
++vcpu->stat.irq_exits;
+ KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler);
return 1;
}
@@ -1958,25 +2083,27 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
reg = (exit_qualification >> 8) & 15;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
+ KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)vcpu->arch.regs[reg],
+ (u32)((u64)vcpu->arch.regs[reg] >> 32), handler);
switch (cr) {
case 0:
vcpu_load_rsp_rip(vcpu);
- set_cr0(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr0(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
case 3:
vcpu_load_rsp_rip(vcpu);
- set_cr3(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr3(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
case 4:
vcpu_load_rsp_rip(vcpu);
- set_cr4(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr4(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
case 8:
vcpu_load_rsp_rip(vcpu);
- set_cr8(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr8(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
if (irqchip_in_kernel(vcpu->kvm))
return 1;
@@ -1990,6 +2117,7 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->arch.cr0 &= ~X86_CR0_TS;
vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
vmx_fpu_activate(vcpu);
+ KVMTRACE_0D(CLTS, vcpu, handler);
skip_emulated_instruction(vcpu);
return 1;
case 1: /*mov from cr*/
@@ -1998,18 +2126,24 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu_load_rsp_rip(vcpu);
vcpu->arch.regs[reg] = vcpu->arch.cr3;
vcpu_put_rsp_rip(vcpu);
+ KVMTRACE_3D(CR_READ, vcpu, (u32)cr,
+ (u32)vcpu->arch.regs[reg],
+ (u32)((u64)vcpu->arch.regs[reg] >> 32),
+ handler);
skip_emulated_instruction(vcpu);
return 1;
case 8:
vcpu_load_rsp_rip(vcpu);
- vcpu->arch.regs[reg] = get_cr8(vcpu);
+ vcpu->arch.regs[reg] = kvm_get_cr8(vcpu);
vcpu_put_rsp_rip(vcpu);
+ KVMTRACE_2D(CR_READ, vcpu, (u32)cr,
+ (u32)vcpu->arch.regs[reg], handler);
skip_emulated_instruction(vcpu);
return 1;
}
break;
case 3: /* lmsw */
- lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
+ kvm_lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
skip_emulated_instruction(vcpu);
return 1;
@@ -2049,6 +2183,7 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
val = 0;
}
vcpu->arch.regs[reg] = val;
+ KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
} else {
/* mov to dr */
}
@@ -2073,6 +2208,9 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
+ KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32),
+ handler);
+
/* FIXME: handling of bits 32:63 of rax, rdx */
vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u;
vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u;
@@ -2086,6 +2224,9 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
+ KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32),
+ handler);
+
if (vmx_set_msr(vcpu, ecx, data) != 0) {
kvm_inject_gp(vcpu, 0);
return 1;
@@ -2110,6 +2251,9 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu,
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);
+
+ KVMTRACE_0D(PEND_INTR, vcpu, handler);
+
/*
* If the user space waits to inject interrupts, exit as soon as
* possible
@@ -2152,6 +2296,8 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
offset = exit_qualification & 0xffful;
+ KVMTRACE_1D(APIC_ACCESS, vcpu, (u32)offset, handler);
+
er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
if (er != EMULATE_DONE) {
@@ -2163,6 +2309,20 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
+static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ unsigned long exit_qualification;
+ u16 tss_selector;
+ int reason;
+
+ exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+ reason = (u32)exit_qualification >> 30;
+ tss_selector = exit_qualification;
+
+ return kvm_task_switch(vcpu, tss_selector, reason);
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -2185,6 +2345,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
[EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,
[EXIT_REASON_APIC_ACCESS] = handle_apic_access,
[EXIT_REASON_WBINVD] = handle_wbinvd,
+ [EXIT_REASON_TASK_SWITCH] = handle_task_switch,
};
static const int kvm_vmx_max_exit_handlers =
@@ -2200,6 +2361,9 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 vectoring_info = vmx->idt_vectoring_info;
+ KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)vmcs_readl(GUEST_RIP),
+ (u32)((u64)vmcs_readl(GUEST_RIP) >> 32), entryexit);
+
if (unlikely(vmx->fail)) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
kvm_run->fail_entry.hardware_entry_failure_reason
@@ -2210,7 +2374,7 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
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);
+ "exit reason is 0x%x\n", __func__, exit_reason);
if (exit_reason < kvm_vmx_max_exit_handlers
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run);
@@ -2221,10 +2385,6 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
return 0;
}
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
-{
-}
-
static void update_tpr_threshold(struct kvm_vcpu *vcpu)
{
int max_irr, tpr;
@@ -2285,11 +2445,13 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
return;
}
+ KVMTRACE_1D(REDELIVER_EVT, vcpu, idtv_info_field, handler);
+
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field);
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
- if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK))
+ if (unlikely(idtv_info_field & INTR_INFO_DELIVER_CODE_MASK))
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
vmcs_read32(IDT_VECTORING_ERROR_CODE));
if (unlikely(has_ext_irq))
@@ -2470,8 +2632,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
/* We need to handle NMIs before interrupts are enabled */
- if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */
+ if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) { /* nmi */
+ KVMTRACE_0D(NMI, vcpu, handler);
asm("int $2");
+ }
}
static void vmx_free_vmcs(struct kvm_vcpu *vcpu)
@@ -2489,6 +2653,10 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ spin_lock(&vmx_vpid_lock);
+ if (vmx->vpid != 0)
+ __clear_bit(vmx->vpid, vmx_vpid_bitmap);
+ spin_unlock(&vmx_vpid_lock);
vmx_free_vmcs(vcpu);
kfree(vmx->host_msrs);
kfree(vmx->guest_msrs);
@@ -2505,6 +2673,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
if (!vmx)
return ERR_PTR(-ENOMEM);
+ allocate_vpid(vmx);
+
err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
if (err)
goto free_vcpu;
@@ -2591,14 +2761,13 @@ static struct kvm_x86_ops vmx_x86_ops = {
.get_segment_base = vmx_get_segment_base,
.get_segment = vmx_get_segment,
.set_segment = vmx_set_segment,
+ .get_cpl = vmx_get_cpl,
.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
.set_cr0 = vmx_set_cr0,
.set_cr3 = vmx_set_cr3,
.set_cr4 = vmx_set_cr4,
-#ifdef CONFIG_X86_64
.set_efer = vmx_set_efer,
-#endif
.get_idt = vmx_get_idt,
.set_idt = vmx_set_idt,
.get_gdt = vmx_get_gdt,
@@ -2626,7 +2795,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
static int __init vmx_init(void)
{
- void *iova;
+ void *va;
int r;
vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
@@ -2639,28 +2808,48 @@ static int __init vmx_init(void)
goto out;
}
+ vmx_msr_bitmap = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
+ if (!vmx_msr_bitmap) {
+ r = -ENOMEM;
+ goto out1;
+ }
+
/*
* Allow direct access to the PC debug port (it is often used for I/O
* delays, but the vmexits simply slow things down).
*/
- iova = kmap(vmx_io_bitmap_a);
- memset(iova, 0xff, PAGE_SIZE);
- clear_bit(0x80, iova);
+ va = kmap(vmx_io_bitmap_a);
+ memset(va, 0xff, PAGE_SIZE);
+ clear_bit(0x80, va);
kunmap(vmx_io_bitmap_a);
- iova = kmap(vmx_io_bitmap_b);
- memset(iova, 0xff, PAGE_SIZE);
+ va = kmap(vmx_io_bitmap_b);
+ memset(va, 0xff, PAGE_SIZE);
kunmap(vmx_io_bitmap_b);
+ va = kmap(vmx_msr_bitmap);
+ memset(va, 0xff, PAGE_SIZE);
+ kunmap(vmx_msr_bitmap);
+
+ set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+
r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
if (r)
- goto out1;
+ goto out2;
+
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_FS_BASE);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_GS_BASE);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_CS);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP);
if (bypass_guest_pf)
kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
return 0;
+out2:
+ __free_page(vmx_msr_bitmap);
out1:
__free_page(vmx_io_bitmap_b);
out:
@@ -2670,6 +2859,7 @@ out:
static void __exit vmx_exit(void)
{
+ __free_page(vmx_msr_bitmap);
__free_page(vmx_io_bitmap_b);
__free_page(vmx_io_bitmap_a);