[PATCH 4.4 45/88] KVM: VMX: make MSR bitmaps per-VCPU

From: Greg Kroah-Hartman
Date: Fri Dec 14 2018 - 07:15:11 EST


4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Bonzini <pbonzini@xxxxxxxxxx>

commit 904e14fb7cb96401a7dc803ca2863fd5ba32ffe6 upstream.

Place the MSR bitmap in struct loaded_vmcs, and update it in place
every time the x2apic or APICv state can change. This is rare and
the loop can handle 64 MSRs per iteration, in a similar fashion as
nested_vmx_prepare_msr_bitmap.

This prepares for choosing, on a per-VM basis, whether to intercept
the SPEC_CTRL and PRED_CMD MSRs.

Suggested-by: Jim Mattson <jmattson@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
[bwh: Backported to 4.4:
- APICv support looked different
- We still need to intercept the APIC_ID MSR
- Adjust context]
Signed-off-by: Ben Hutchings <ben.hutchings@xxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 254 +++++++++++++++++++++++------------------------------
1 file changed, 112 insertions(+), 142 deletions(-)

--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -109,6 +109,14 @@ static u64 __read_mostly host_xss;
static bool __read_mostly enable_pml = 1;
module_param_named(pml, enable_pml, bool, S_IRUGO);

+#define MSR_TYPE_R 1
+#define MSR_TYPE_W 2
+#define MSR_TYPE_RW 3
+
+#define MSR_BITMAP_MODE_X2APIC 1
+#define MSR_BITMAP_MODE_X2APIC_APICV 2
+#define MSR_BITMAP_MODE_LM 4
+
#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL

#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
@@ -188,6 +196,7 @@ struct loaded_vmcs {
struct vmcs *vmcs;
int cpu;
int launched;
+ unsigned long *msr_bitmap;
struct list_head loaded_vmcss_on_cpu_link;
};

@@ -423,8 +432,6 @@ struct nested_vmx {
u16 posted_intr_nv;
u64 msr_ia32_feature_control;

- unsigned long *msr_bitmap;
-
struct hrtimer preemption_timer;
bool preemption_timer_expired;

@@ -525,6 +532,7 @@ struct vcpu_vmx {
unsigned long host_rsp;
u8 fail;
bool nmi_known_unmasked;
+ u8 msr_bitmap_mode;
u32 exit_intr_info;
u32 idt_vectoring_info;
ulong rflags;
@@ -883,6 +891,7 @@ static void vmx_sync_pir_to_irr_dummy(st
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
static int alloc_identity_pagetable(struct kvm *kvm);
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);

static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -902,10 +911,6 @@ static DEFINE_PER_CPU(spinlock_t, blocke

static unsigned long *vmx_io_bitmap_a;
static unsigned long *vmx_io_bitmap_b;
-static unsigned long *vmx_msr_bitmap_legacy;
-static unsigned long *vmx_msr_bitmap_longmode;
-static unsigned long *vmx_msr_bitmap_legacy_x2apic;
-static unsigned long *vmx_msr_bitmap_longmode_x2apic;
static unsigned long *vmx_vmread_bitmap;
static unsigned long *vmx_vmwrite_bitmap;

@@ -2346,27 +2351,6 @@ static void move_msr_up(struct vcpu_vmx
vmx->guest_msrs[from] = tmp;
}

-static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
-{
- unsigned long *msr_bitmap;
-
- if (is_guest_mode(vcpu))
- msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
- else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
- if (is_long_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
- else
- msr_bitmap = vmx_msr_bitmap_legacy_x2apic;
- } else {
- if (is_long_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_longmode;
- else
- msr_bitmap = vmx_msr_bitmap_legacy;
- }
-
- vmcs_write64(MSR_BITMAP, __pa(msr_bitmap));
-}
-
/*
* Set up the vmcs to automatically save and restore system
* msrs. Don't touch the 64-bit msrs if the guest is in legacy
@@ -2407,7 +2391,7 @@ static void setup_msrs(struct vcpu_vmx *
vmx->save_nmsrs = save_nmsrs;

if (cpu_has_vmx_msr_bitmap())
- vmx_set_msr_bitmap(&vmx->vcpu);
+ vmx_update_msr_bitmap(&vmx->vcpu);
}

/*
@@ -3360,6 +3344,8 @@ static void free_loaded_vmcs(struct load
loaded_vmcs_clear(loaded_vmcs);
free_vmcs(loaded_vmcs->vmcs);
loaded_vmcs->vmcs = NULL;
+ if (loaded_vmcs->msr_bitmap)
+ free_page((unsigned long)loaded_vmcs->msr_bitmap);
}

static struct vmcs *alloc_vmcs(void)
@@ -3374,7 +3360,18 @@ static int alloc_loaded_vmcs(struct load
return -ENOMEM;

loaded_vmcs_init(loaded_vmcs);
+
+ if (cpu_has_vmx_msr_bitmap()) {
+ loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!loaded_vmcs->msr_bitmap)
+ goto out_vmcs;
+ memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
+ }
return 0;
+
+out_vmcs:
+ free_loaded_vmcs(loaded_vmcs);
+ return -ENOMEM;
}

static void free_kvm_area(void)
@@ -4373,10 +4370,8 @@ static void free_vpid(int vpid)
spin_unlock(&vmx_vpid_lock);
}

-#define MSR_TYPE_R 1
-#define MSR_TYPE_W 2
-static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
- u32 msr, int type)
+static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+ u32 msr, int type)
{
int f = sizeof(unsigned long);

@@ -4410,8 +4405,8 @@ static void __vmx_disable_intercept_for_
}
}

-static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
- u32 msr, int type)
+static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+ u32 msr, int type)
{
int f = sizeof(unsigned long);

@@ -4491,37 +4486,76 @@ static void nested_vmx_disable_intercept
}
}

-static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only)
+static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
+ u32 msr, int type, bool value)
{
- if (!longmode_only)
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy,
- msr, MSR_TYPE_R | MSR_TYPE_W);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode,
- msr, MSR_TYPE_R | MSR_TYPE_W);
+ if (value)
+ vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
+ else
+ vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
}

-static void vmx_enable_intercept_msr_read_x2apic(u32 msr)
+static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
{
- __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
- msr, MSR_TYPE_R);
- __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
- msr, MSR_TYPE_R);
+ u8 mode = 0;
+
+ if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+ mode |= MSR_BITMAP_MODE_X2APIC;
+ if (enable_apicv)
+ mode |= MSR_BITMAP_MODE_X2APIC_APICV;
+ }
+
+ if (is_long_mode(vcpu))
+ mode |= MSR_BITMAP_MODE_LM;
+
+ return mode;
}

-static void vmx_disable_intercept_msr_read_x2apic(u32 msr)
+#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+
+static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
+ u8 mode)
{
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
- msr, MSR_TYPE_R);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
- msr, MSR_TYPE_R);
+ int msr;
+
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+ msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
+ msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+ }
+
+ if (mode & MSR_BITMAP_MODE_X2APIC) {
+ /*
+ * TPR reads and writes can be virtualized even if virtual interrupt
+ * delivery is not in use.
+ */
+ vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+ if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
+ vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_ID), MSR_TYPE_R);
+ vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
+ vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
+ vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+ }
+ }
}

-static void vmx_disable_intercept_msr_write_x2apic(u32 msr)
+static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
{
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic,
- msr, MSR_TYPE_W);
- __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic,
- msr, MSR_TYPE_W);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+ u8 mode = vmx_msr_bitmap_mode(vcpu);
+ u8 changed = mode ^ vmx->msr_bitmap_mode;
+
+ if (!changed)
+ return;
+
+ vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
+ !(mode & MSR_BITMAP_MODE_LM));
+
+ if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
+ vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
+
+ vmx->msr_bitmap_mode = mode;
}

static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu)
@@ -4842,7 +4876,7 @@ static int vmx_vcpu_setup(struct vcpu_vm
vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
}
if (cpu_has_vmx_msr_bitmap())
- vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy));
+ vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));

vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */

@@ -6183,7 +6217,7 @@ static void wakeup_handler(void)

static __init int hardware_setup(void)
{
- int r = -ENOMEM, i, msr;
+ int r = -ENOMEM, i;

rdmsrl_safe(MSR_EFER, &host_efer);

@@ -6198,31 +6232,13 @@ static __init int hardware_setup(void)
if (!vmx_io_bitmap_b)
goto out;

- vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_legacy)
- goto out1;
-
- vmx_msr_bitmap_legacy_x2apic =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_legacy_x2apic)
- goto out2;
-
- vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_longmode)
- goto out3;
-
- vmx_msr_bitmap_longmode_x2apic =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_longmode_x2apic)
- goto out4;
-
vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_vmread_bitmap)
- goto out6;
+ goto out1;

vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_vmwrite_bitmap)
- goto out7;
+ goto out2;

memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
@@ -6231,12 +6247,9 @@ static __init int hardware_setup(void)

memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);

- memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
- memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
-
if (setup_vmcs_config(&vmcs_config) < 0) {
r = -EIO;
- goto out8;
+ goto out3;
}

if (boot_cpu_has(X86_FEATURE_NX))
@@ -6302,38 +6315,8 @@ static __init int hardware_setup(void)
kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy;
}

- vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
- vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
- vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-
- memcpy(vmx_msr_bitmap_legacy_x2apic,
- vmx_msr_bitmap_legacy, PAGE_SIZE);
- memcpy(vmx_msr_bitmap_longmode_x2apic,
- vmx_msr_bitmap_longmode, PAGE_SIZE);
-
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */

- if (enable_apicv) {
- for (msr = 0x800; msr <= 0x8ff; msr++)
- vmx_disable_intercept_msr_read_x2apic(msr);
-
- /* According SDM, in x2apic mode, the whole id reg is used.
- * But in KVM, it only use the highest eight bits. Need to
- * intercept it */
- vmx_enable_intercept_msr_read_x2apic(0x802);
- /* TMCCT */
- vmx_enable_intercept_msr_read_x2apic(0x839);
- /* TPR */
- vmx_disable_intercept_msr_write_x2apic(0x808);
- /* EOI */
- vmx_disable_intercept_msr_write_x2apic(0x80b);
- /* SELF-IPI */
- vmx_disable_intercept_msr_write_x2apic(0x83f);
- }
-
if (enable_ept) {
kvm_mmu_set_mask_ptes(0ull,
(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
@@ -6364,18 +6347,10 @@ static __init int hardware_setup(void)

return alloc_kvm_area();

-out8:
- free_page((unsigned long)vmx_vmwrite_bitmap);
-out7:
- free_page((unsigned long)vmx_vmread_bitmap);
-out6:
- free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-out4:
- free_page((unsigned long)vmx_msr_bitmap_longmode);
out3:
- free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+ free_page((unsigned long)vmx_vmwrite_bitmap);
out2:
- free_page((unsigned long)vmx_msr_bitmap_legacy);
+ free_page((unsigned long)vmx_vmread_bitmap);
out1:
free_page((unsigned long)vmx_io_bitmap_b);
out:
@@ -6386,10 +6361,6 @@ out:

static __exit void hardware_unsetup(void)
{
- free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
- free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
- free_page((unsigned long)vmx_msr_bitmap_legacy);
- free_page((unsigned long)vmx_msr_bitmap_longmode);
free_page((unsigned long)vmx_io_bitmap_b);
free_page((unsigned long)vmx_io_bitmap_a);
free_page((unsigned long)vmx_vmwrite_bitmap);
@@ -6753,13 +6724,6 @@ static int handle_vmon(struct kvm_vcpu *
if (r < 0)
goto out_vmcs02;

- if (cpu_has_vmx_msr_bitmap()) {
- vmx->nested.msr_bitmap =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx->nested.msr_bitmap)
- goto out_msr_bitmap;
- }
-
if (enable_shadow_vmcs) {
shadow_vmcs = alloc_vmcs();
if (!shadow_vmcs)
@@ -6784,9 +6748,6 @@ static int handle_vmon(struct kvm_vcpu *
return 1;

out_shadow_vmcs:
- free_page((unsigned long)vmx->nested.msr_bitmap);
-
-out_msr_bitmap:
free_loaded_vmcs(&vmx->nested.vmcs02);

out_vmcs02:
@@ -6860,10 +6821,6 @@ static void free_nested(struct vcpu_vmx
vmx->nested.vmxon = false;
free_vpid(vmx->nested.vpid02);
nested_release_vmcs12(vmx);
- if (vmx->nested.msr_bitmap) {
- free_page((unsigned long)vmx->nested.msr_bitmap);
- vmx->nested.msr_bitmap = NULL;
- }
if (enable_shadow_vmcs)
free_vmcs(vmx->nested.current_shadow_vmcs);
/* Unpin physical memory we referred to in the vmcs02 */
@@ -8200,7 +8157,7 @@ static void vmx_set_virtual_x2apic_mode(
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);

- vmx_set_msr_bitmap(vcpu);
+ vmx_update_msr_bitmap(vcpu);
}

static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
@@ -8780,6 +8737,7 @@ static struct kvm_vcpu *vmx_create_vcpu(
{
int err;
struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+ unsigned long *msr_bitmap;
int cpu;

if (!vmx)
@@ -8820,6 +8778,15 @@ static struct kvm_vcpu *vmx_create_vcpu(
if (err < 0)
goto free_msrs;

+ msr_bitmap = vmx->vmcs01.msr_bitmap;
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+ vmx->msr_bitmap_mode = 0;
+
vmx->loaded_vmcs = &vmx->vmcs01;
cpu = get_cpu();
vmx_vcpu_load(&vmx->vcpu, cpu);
@@ -9204,7 +9171,7 @@ static inline bool nested_vmx_merge_msr_
int msr;
struct page *page;
unsigned long *msr_bitmap_l1;
- unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap;
+ unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;

/* This shortcut is ok because we support only x2APIC MSRs so far. */
if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
@@ -9715,6 +9682,9 @@ static void prepare_vmcs02(struct kvm_vc
else
vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);

+ if (cpu_has_vmx_msr_bitmap())
+ vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+
if (enable_vpid) {
/*
* There is no direct mapping between vpid02 and vpid12, the
@@ -10415,7 +10385,7 @@ static void load_vmcs12_host_state(struc
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);

if (cpu_has_vmx_msr_bitmap())
- vmx_set_msr_bitmap(vcpu);
+ vmx_update_msr_bitmap(vcpu);

if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
vmcs12->vm_exit_msr_load_count))