summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/hyperv.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/hyperv.c')
-rw-r--r--arch/x86/kvm/hyperv.c1756
1 files changed, 1395 insertions, 361 deletions
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index c90a5352d158..de92292eb1f5 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* KVM Microsoft Hyper-V emulation
*
@@ -15,28 +16,51 @@
* Amit Shah <amit.shah@qumranet.com>
* Ben-Ami Yassour <benami@il.ibm.com>
* Andrey Smetanin <asmetanin@virtuozzo.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include "x86.h"
#include "lapic.h"
#include "ioapic.h"
+#include "cpuid.h"
#include "hyperv.h"
+#include "mmu.h"
+#include "xen.h"
+#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <linux/sched/cputime.h>
+#include <linux/spinlock.h>
#include <linux/eventfd.h>
#include <asm/apicdef.h>
+#include <asm/mshyperv.h>
#include <trace/events/kvm.h>
#include "trace.h"
+#include "irq.h"
+#include "fpu.h"
-#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64)
+#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK)
+
+/*
+ * As per Hyper-V TLFS, extended hypercalls start from 0x8001
+ * (HvExtCallQueryCapabilities). Response of this hypercalls is a 64 bit value
+ * where each bit tells which extended hypercall is available besides
+ * HvExtCallQueryCapabilities.
+ *
+ * 0x8001 - First extended hypercall, HvExtCallQueryCapabilities, no bit
+ * assigned.
+ *
+ * 0x8002 - Bit 0
+ * 0x8003 - Bit 1
+ * ..
+ * 0x8041 - Bit 63
+ *
+ * Therefore, HV_EXT_CALL_MAX = 0x8001 + 64
+ */
+#define HV_EXT_CALL_MAX (HV_EXT_CALL_QUERY_CAPABILITIES + 64)
static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
bool vcpu_kick);
@@ -83,6 +107,10 @@ static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic,
static void synic_update_vector(struct kvm_vcpu_hv_synic *synic,
int vector)
{
+ struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+ bool auto_eoi_old, auto_eoi_new;
+
if (vector < HV_SYNIC_FIRST_VALID_VECTOR)
return;
@@ -91,10 +119,37 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic,
else
__clear_bit(vector, synic->vec_bitmap);
+ auto_eoi_old = !bitmap_empty(synic->auto_eoi_bitmap, 256);
+
if (synic_has_vector_auto_eoi(synic, vector))
__set_bit(vector, synic->auto_eoi_bitmap);
else
__clear_bit(vector, synic->auto_eoi_bitmap);
+
+ auto_eoi_new = !bitmap_empty(synic->auto_eoi_bitmap, 256);
+
+ if (auto_eoi_old == auto_eoi_new)
+ return;
+
+ if (!enable_apicv)
+ return;
+
+ down_write(&vcpu->kvm->arch.apicv_update_lock);
+
+ if (auto_eoi_new)
+ hv->synic_auto_eoi_used++;
+ else
+ hv->synic_auto_eoi_used--;
+
+ /*
+ * Inhibit APICv if any vCPU is using SynIC's AutoEOI, which relies on
+ * the hypervisor to manually inject IRQs.
+ */
+ __kvm_set_or_clear_apicv_inhibit(vcpu->kvm,
+ APICV_INHIBIT_REASON_HYPERV,
+ !!hv->synic_auto_eoi_used);
+
+ up_write(&vcpu->kvm->arch.apicv_update_lock);
}
static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
@@ -128,23 +183,23 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
synic_update_vector(synic, vector);
/* Load SynIC vectors into EOI exit bitmap */
- kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic));
+ kvm_make_request(KVM_REQ_SCAN_IOAPIC, hv_synic_to_vcpu(synic));
return 0;
}
static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx)
{
struct kvm_vcpu *vcpu = NULL;
- int i;
+ unsigned long i;
if (vpidx >= KVM_MAX_VCPUS)
return NULL;
vcpu = kvm_get_vcpu(kvm, vpidx);
- if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
+ if (vcpu && kvm_hv_get_vpindex(vcpu) == vpidx)
return vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
- if (vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
+ if (kvm_hv_get_vpindex(vcpu) == vpidx)
return vcpu;
return NULL;
}
@@ -155,17 +210,17 @@ static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx)
struct kvm_vcpu_hv_synic *synic;
vcpu = get_vcpu_by_vpidx(kvm, vpidx);
- if (!vcpu)
+ if (!vcpu || !to_hv_vcpu(vcpu))
return NULL;
- synic = vcpu_to_synic(vcpu);
+ synic = to_hv_synic(vcpu);
return (synic->active) ? synic : NULL;
}
static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint)
{
struct kvm *kvm = vcpu->kvm;
- struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
- struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+ struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
struct kvm_vcpu_hv_stimer *stimer;
int gsi, idx;
@@ -189,8 +244,8 @@ static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint)
static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr)
{
- struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
- struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
+ struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC;
hv_vcpu->exit.u.synic.msr = msr;
@@ -204,10 +259,10 @@ static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr)
static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
u32 msr, u64 data, bool host)
{
- struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+ struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
int ret;
- if (!synic->active && !host)
+ if (!synic->active && (!host || data))
return 1;
trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host);
@@ -253,6 +308,9 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
case HV_X64_MSR_EOM: {
int i;
+ if (!synic->active)
+ break;
+
for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
kvm_hv_notify_acked_sint(vcpu, i);
break;
@@ -267,6 +325,115 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
return ret;
}
+static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ return hv_vcpu->cpuid_cache.syndbg_cap_eax &
+ HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING;
+}
+
+static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu)
+{
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+ if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL)
+ hv->hv_syndbg.control.status =
+ vcpu->run->hyperv.u.syndbg.status;
+ return 1;
+}
+
+static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG;
+ hv_vcpu->exit.u.syndbg.msr = msr;
+ hv_vcpu->exit.u.syndbg.control = syndbg->control.control;
+ hv_vcpu->exit.u.syndbg.send_page = syndbg->control.send_page;
+ hv_vcpu->exit.u.syndbg.recv_page = syndbg->control.recv_page;
+ hv_vcpu->exit.u.syndbg.pending_page = syndbg->control.pending_page;
+ vcpu->arch.complete_userspace_io =
+ kvm_hv_syndbg_complete_userspace;
+
+ kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
+}
+
+static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
+{
+ struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu);
+
+ if (!kvm_hv_is_syndbg_enabled(vcpu) && !host)
+ return 1;
+
+ trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id,
+ to_hv_vcpu(vcpu)->vp_index, msr, data);
+ switch (msr) {
+ case HV_X64_MSR_SYNDBG_CONTROL:
+ syndbg->control.control = data;
+ if (!host)
+ syndbg_exit(vcpu, msr);
+ break;
+ case HV_X64_MSR_SYNDBG_STATUS:
+ syndbg->control.status = data;
+ break;
+ case HV_X64_MSR_SYNDBG_SEND_BUFFER:
+ syndbg->control.send_page = data;
+ break;
+ case HV_X64_MSR_SYNDBG_RECV_BUFFER:
+ syndbg->control.recv_page = data;
+ break;
+ case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ syndbg->control.pending_page = data;
+ if (!host)
+ syndbg_exit(vcpu, msr);
+ break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ syndbg->options = data;
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
+{
+ struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu);
+
+ if (!kvm_hv_is_syndbg_enabled(vcpu) && !host)
+ return 1;
+
+ switch (msr) {
+ case HV_X64_MSR_SYNDBG_CONTROL:
+ *pdata = syndbg->control.control;
+ break;
+ case HV_X64_MSR_SYNDBG_STATUS:
+ *pdata = syndbg->control.status;
+ break;
+ case HV_X64_MSR_SYNDBG_SEND_BUFFER:
+ *pdata = syndbg->control.send_page;
+ break;
+ case HV_X64_MSR_SYNDBG_RECV_BUFFER:
+ *pdata = syndbg->control.recv_page;
+ break;
+ case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ *pdata = syndbg->control.pending_page;
+ break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ *pdata = syndbg->options;
+ break;
+ default:
+ break;
+ }
+
+ trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id, kvm_hv_get_vpindex(vcpu), msr, *pdata);
+
+ return 0;
+}
+
static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata,
bool host)
{
@@ -304,10 +471,13 @@ static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata,
static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
{
- struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+ struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
struct kvm_lapic_irq irq;
int ret, vector;
+ if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm))
+ return -EINVAL;
+
if (sint >= ARRAY_SIZE(synic->sint))
return -EINVAL;
@@ -327,20 +497,24 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
return ret;
}
-int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint)
+int kvm_hv_synic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status)
{
struct kvm_vcpu_hv_synic *synic;
- synic = synic_get(kvm, vpidx);
+ if (!level)
+ return -1;
+
+ synic = synic_get(kvm, e->hv_sint.vcpu);
if (!synic)
return -EINVAL;
- return synic_set_irq(synic, sint);
+ return synic_set_irq(synic, e->hv_sint.sint);
}
void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector)
{
- struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+ struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
int i;
trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector);
@@ -397,15 +571,15 @@ static void synic_init(struct kvm_vcpu_hv_synic *synic)
static u64 get_time_ref_counter(struct kvm *kvm)
{
- struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
struct kvm_vcpu *vcpu;
u64 tsc;
/*
- * The guest has not set up the TSC page or the clock isn't
- * stable, fall back to get_kvmclock_ns.
+ * Fall back to get_kvmclock_ns() when TSC page hasn't been set up,
+ * is broken, disabled or being updated.
*/
- if (!hv->tsc_ref.tsc_sequence)
+ if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET)
return div_u64(get_kvmclock_ns(kvm), 100);
vcpu = kvm_get_vcpu(kvm, 0);
@@ -417,10 +591,10 @@ static u64 get_time_ref_counter(struct kvm *kvm)
static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
bool vcpu_kick)
{
- struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+ struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
set_bit(stimer->index,
- vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
+ to_hv_vcpu(vcpu)->stimer_pending_bitmap);
kvm_make_request(KVM_REQ_HV_STIMER, vcpu);
if (vcpu_kick)
kvm_vcpu_kick(vcpu);
@@ -428,14 +602,14 @@ static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer)
{
- struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+ struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
- trace_kvm_hv_stimer_cleanup(stimer_to_vcpu(stimer)->vcpu_id,
+ trace_kvm_hv_stimer_cleanup(hv_stimer_to_vcpu(stimer)->vcpu_id,
stimer->index);
hrtimer_cancel(&stimer->timer);
clear_bit(stimer->index,
- vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
+ to_hv_vcpu(vcpu)->stimer_pending_bitmap);
stimer->msg_pending = false;
stimer->exp_time = 0;
}
@@ -445,7 +619,7 @@ static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer)
struct kvm_vcpu_hv_stimer *stimer;
stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer);
- trace_kvm_hv_stimer_callback(stimer_to_vcpu(stimer)->vcpu_id,
+ trace_kvm_hv_stimer_callback(hv_stimer_to_vcpu(stimer)->vcpu_id,
stimer->index);
stimer_mark_pending(stimer, true);
@@ -462,7 +636,7 @@ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer)
u64 time_now;
ktime_t ktime_now;
- time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm);
+ time_now = get_time_ref_counter(hv_stimer_to_vcpu(stimer)->kvm);
ktime_now = ktime_get();
if (stimer->config.periodic) {
@@ -479,7 +653,7 @@ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer)
stimer->exp_time = time_now + stimer->count;
trace_kvm_hv_stimer_start_periodic(
- stimer_to_vcpu(stimer)->vcpu_id,
+ hv_stimer_to_vcpu(stimer)->vcpu_id,
stimer->index,
time_now, stimer->exp_time);
@@ -501,7 +675,7 @@ static int stimer_start(struct kvm_vcpu_hv_stimer *stimer)
return 0;
}
- trace_kvm_hv_stimer_start_one_shot(stimer_to_vcpu(stimer)->vcpu_id,
+ trace_kvm_hv_stimer_start_one_shot(hv_stimer_to_vcpu(stimer)->vcpu_id,
stimer->index,
time_now, stimer->count);
@@ -516,8 +690,19 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
{
union hv_stimer_config new_config = {.as_uint64 = config},
old_config = {.as_uint64 = stimer->config.as_uint64};
+ struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
- trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id,
+ if (!synic->active && (!host || config))
+ return 1;
+
+ if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode &&
+ !(hv_vcpu->cpuid_cache.features_edx &
+ HV_STIMER_DIRECT_MODE_AVAILABLE)))
+ return 1;
+
+ trace_kvm_hv_stimer_set_config(hv_stimer_to_vcpu(stimer)->vcpu_id,
stimer->index, config, host);
stimer_cleanup(stimer);
@@ -526,23 +711,36 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
new_config.enable = 0;
stimer->config.as_uint64 = new_config.as_uint64;
- stimer_mark_pending(stimer, false);
+ if (stimer->config.enable)
+ stimer_mark_pending(stimer, false);
+
return 0;
}
static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
bool host)
{
- trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id,
+ struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
+ struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
+
+ if (!synic->active && (!host || count))
+ return 1;
+
+ trace_kvm_hv_stimer_set_count(hv_stimer_to_vcpu(stimer)->vcpu_id,
stimer->index, count, host);
stimer_cleanup(stimer);
stimer->count = count;
- if (stimer->count == 0)
- stimer->config.enable = 0;
- else if (stimer->config.auto_enable)
- stimer->config.enable = 1;
- stimer_mark_pending(stimer, false);
+ if (!host) {
+ if (stimer->count == 0)
+ stimer->config.enable = 0;
+ else if (stimer->config.auto_enable)
+ stimer->config.enable = 1;
+ }
+
+ if (stimer->config.enable)
+ stimer_mark_pending(stimer, false);
+
return 0;
}
@@ -561,7 +759,7 @@ static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount)
static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint,
struct hv_message *src_msg, bool no_retry)
{
- struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
+ struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
int msg_off = offsetof(struct hv_message_page, sint_message[sint]);
gfn_t msg_page_gfn;
struct hv_message_header hv_hdr;
@@ -617,7 +815,7 @@ static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint,
static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer)
{
- struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+ struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
struct hv_message *msg = &stimer->msg;
struct hv_timer_message_payload *payload =
(struct hv_timer_message_payload *)&msg->u.payload;
@@ -630,20 +828,22 @@ static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer)
payload->expiration_time = stimer->exp_time;
payload->delivery_time = get_time_ref_counter(vcpu->kvm);
- return synic_deliver_msg(vcpu_to_synic(vcpu),
+ return synic_deliver_msg(to_hv_synic(vcpu),
stimer->config.sintx, msg,
no_retry);
}
static int stimer_notify_direct(struct kvm_vcpu_hv_stimer *stimer)
{
- struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+ struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
struct kvm_lapic_irq irq = {
.delivery_mode = APIC_DM_FIXED,
.vector = stimer->config.apic_vector
};
- return !kvm_apic_set_irq(vcpu, &irq, NULL);
+ if (lapic_in_kernel(vcpu))
+ return !kvm_apic_set_irq(vcpu, &irq, NULL);
+ return 0;
}
static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer)
@@ -655,7 +855,7 @@ static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer)
r = stimer_send_msg(stimer);
else
r = stimer_notify_direct(stimer);
- trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id,
+ trace_kvm_hv_stimer_expiration(hv_stimer_to_vcpu(stimer)->vcpu_id,
stimer->index, direct, r);
if (!r) {
stimer->msg_pending = false;
@@ -666,11 +866,14 @@ static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer)
void kvm_hv_process_stimers(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
struct kvm_vcpu_hv_stimer *stimer;
u64 time_now, exp_time;
int i;
+ if (!hv_vcpu)
+ return;
+
for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) {
stimer = &hv_vcpu->stimer[i];
@@ -696,30 +899,43 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu)
void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
int i;
+ if (!hv_vcpu)
+ return;
+
for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
stimer_cleanup(&hv_vcpu->stimer[i]);
+
+ kfree(hv_vcpu);
+ vcpu->arch.hyperv = NULL;
}
bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu)
{
- if (!(vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE))
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ if (!hv_vcpu)
+ return false;
+
+ if (!(hv_vcpu->hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE))
return false;
return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED;
}
-EXPORT_SYMBOL_GPL(kvm_hv_assist_page_enabled);
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_hv_assist_page_enabled);
-bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
- struct hv_vp_assist_page *assist_page)
+int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu)
{
- if (!kvm_hv_assist_page_enabled(vcpu))
- return false;
- return !kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data,
- assist_page, sizeof(*assist_page));
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ if (!hv_vcpu || !kvm_hv_assist_page_enabled(vcpu))
+ return -EFAULT;
+
+ return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data,
+ &hv_vcpu->vp_assist_page, sizeof(struct hv_vp_assist_page));
}
-EXPORT_SYMBOL_GPL(kvm_hv_get_assist_page);
+EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_hv_get_assist_page);
static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer)
{
@@ -740,41 +956,55 @@ static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index)
{
memset(stimer, 0, sizeof(*stimer));
stimer->index = timer_index;
- hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
- stimer->timer.function = stimer_timer_callback;
+ hrtimer_setup(&stimer->timer, stimer_timer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
stimer_prepare_msg(stimer);
}
-void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
+int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
int i;
+ if (hv_vcpu)
+ return 0;
+
+ hv_vcpu = kzalloc(sizeof(struct kvm_vcpu_hv), GFP_KERNEL_ACCOUNT);
+ if (!hv_vcpu)
+ return -ENOMEM;
+
+ vcpu->arch.hyperv = hv_vcpu;
+ hv_vcpu->vcpu = vcpu;
+
synic_init(&hv_vcpu->synic);
bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
stimer_init(&hv_vcpu->stimer[i], i);
-}
-void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu)
-{
- struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+ hv_vcpu->vp_index = vcpu->vcpu_idx;
- hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu);
+ for (i = 0; i < HV_NR_TLB_FLUSH_FIFOS; i++) {
+ INIT_KFIFO(hv_vcpu->tlb_flush_fifo[i].entries);
+ spin_lock_init(&hv_vcpu->tlb_flush_fifo[i].write_lock);
+ }
+
+ return 0;
}
int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages)
{
- struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+ struct kvm_vcpu_hv_synic *synic;
+ int r;
+
+ r = kvm_hv_vcpu_init(vcpu);
+ if (r)
+ return r;
+
+ synic = to_hv_synic(vcpu);
- /*
- * Hyper-V SynIC auto EOI SINT's are
- * not compatible with APICV, so deactivate APICV
- */
- kvm_vcpu_deactivate_apicv(vcpu);
synic->active = true;
synic->dont_zero_synic_pages = dont_zero_synic_pages;
+ synic->control = HV_SYNIC_CONTROL_ENABLE;
return 0;
}
@@ -793,6 +1023,9 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
case HV_X64_MSR_TSC_EMULATION_CONTROL:
case HV_X64_MSR_TSC_EMULATION_STATUS:
+ case HV_X64_MSR_TSC_INVARIANT_CONTROL:
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
r = true;
break;
}
@@ -800,58 +1033,44 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
return r;
}
-static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
- u32 index, u64 *pdata)
+static int kvm_hv_msr_get_crash_data(struct kvm *kvm, u32 index, u64 *pdata)
{
- struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+ size_t size = ARRAY_SIZE(hv->hv_crash_param);
- if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+ if (WARN_ON_ONCE(index >= size))
return -EINVAL;
- *pdata = hv->hv_crash_param[index];
+ *pdata = hv->hv_crash_param[array_index_nospec(index, size)];
return 0;
}
-static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata)
+static int kvm_hv_msr_get_crash_ctl(struct kvm *kvm, u64 *pdata)
{
- struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
*pdata = hv->hv_crash_ctl;
return 0;
}
-static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host)
+static int kvm_hv_msr_set_crash_ctl(struct kvm *kvm, u64 data)
{
- struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
-
- if (host)
- hv->hv_crash_ctl = data & HV_CRASH_CTL_CRASH_NOTIFY;
-
- if (!host && (data & HV_CRASH_CTL_CRASH_NOTIFY)) {
-
- vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
- hv->hv_crash_param[0],
- hv->hv_crash_param[1],
- hv->hv_crash_param[2],
- hv->hv_crash_param[3],
- hv->hv_crash_param[4]);
+ struct kvm_hv *hv = to_kvm_hv(kvm);
- /* Send notification about crash to user space */
- kvm_make_request(KVM_REQ_HV_CRASH, vcpu);
- }
+ hv->hv_crash_ctl = data & HV_CRASH_CTL_CRASH_NOTIFY;
return 0;
}
-static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
- u32 index, u64 data)
+static int kvm_hv_msr_set_crash_data(struct kvm *kvm, u32 index, u64 data)
{
- struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+ size_t size = ARRAY_SIZE(hv->hv_crash_param);
- if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+ if (WARN_ON_ONCE(index >= size))
return -EINVAL;
- hv->hv_crash_param[index] = data;
+ hv->hv_crash_param[array_index_nospec(index, size)] = data;
return 0;
}
@@ -891,7 +1110,7 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
* These two equivalencies are implemented in this function.
*/
static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock,
- HV_REFERENCE_TSC_PAGE *tsc_ref)
+ struct ms_hyperv_tsc_page *tsc_ref)
{
u64 max_mul;
@@ -924,22 +1143,40 @@ static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock,
return true;
}
+/*
+ * Don't touch TSC page values if the guest has opted for TSC emulation after
+ * migration. KVM doesn't fully support reenlightenment notifications and TSC
+ * access emulation and Hyper-V is known to expect the values in TSC page to
+ * stay constant before TSC access emulation is disabled from guest side
+ * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC
+ * frequency and guest visible TSC value across migration (and prevent it when
+ * TSC scaling is unsupported).
+ */
+static inline bool tsc_page_update_unsafe(struct kvm_hv *hv)
+{
+ return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) &&
+ hv->hv_tsc_emulation_control;
+}
+
void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock)
{
- struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
u32 tsc_seq;
u64 gfn;
BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence));
- BUILD_BUG_ON(offsetof(HV_REFERENCE_TSC_PAGE, tsc_sequence) != 0);
+ BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0);
- if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+ guard(mutex)(&hv->hv_lock);
+
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+ hv->hv_tsc_page_status == HV_TSC_PAGE_SET ||
+ hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
return;
- mutex_lock(&kvm->arch.hyperv.hv_lock);
if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
- goto out_unlock;
+ return;
gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
/*
@@ -948,7 +1185,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
*/
if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn),
&tsc_seq, sizeof(tsc_seq))))
- goto out_unlock;
+ goto out_err;
+
+ if (tsc_seq && tsc_page_update_unsafe(hv)) {
+ if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
+ goto out_err;
+
+ hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
+ return;
+ }
/*
* While we're computing and writing the parameters, force the
@@ -957,15 +1202,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
hv->tsc_ref.tsc_sequence = 0;
if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
- goto out_unlock;
+ goto out_err;
if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref))
- goto out_unlock;
+ goto out_err;
/* Ensure sequence is zero before writing the rest of the struct. */
smp_wmb();
if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
- goto out_unlock;
+ goto out_err;
/*
* Now switch to the TSC page mechanism by writing the sequence.
@@ -978,17 +1223,164 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
smp_wmb();
hv->tsc_ref.tsc_sequence = tsc_seq;
- kvm_write_guest(kvm, gfn_to_gpa(gfn),
- &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
-out_unlock:
- mutex_unlock(&kvm->arch.hyperv.hv_lock);
+ if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+ &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+ goto out_err;
+
+ hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
+ return;
+
+out_err:
+ hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+}
+
+void kvm_hv_request_tsc_page_update(struct kvm *kvm)
+{
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+
+ mutex_lock(&hv->hv_lock);
+
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET &&
+ !tsc_page_update_unsafe(hv))
+ hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED;
+
+ mutex_unlock(&hv->hv_lock);
+}
+
+static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
+{
+ if (!hv_vcpu->enforce_cpuid)
+ return true;
+
+ switch (msr) {
+ case HV_X64_MSR_GUEST_OS_ID:
+ case HV_X64_MSR_HYPERCALL:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_HYPERCALL_AVAILABLE;
+ case HV_X64_MSR_VP_RUNTIME:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_VP_RUNTIME_AVAILABLE;
+ case HV_X64_MSR_TIME_REF_COUNT:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_TIME_REF_COUNT_AVAILABLE;
+ case HV_X64_MSR_VP_INDEX:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_VP_INDEX_AVAILABLE;
+ case HV_X64_MSR_RESET:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_RESET_AVAILABLE;
+ case HV_X64_MSR_REFERENCE_TSC:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_REFERENCE_TSC_AVAILABLE;
+ case HV_X64_MSR_SCONTROL:
+ case HV_X64_MSR_SVERSION:
+ case HV_X64_MSR_SIEFP:
+ case HV_X64_MSR_SIMP:
+ case HV_X64_MSR_EOM:
+ case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_SYNIC_AVAILABLE;
+ case HV_X64_MSR_STIMER0_CONFIG:
+ case HV_X64_MSR_STIMER1_CONFIG:
+ case HV_X64_MSR_STIMER2_CONFIG:
+ case HV_X64_MSR_STIMER3_CONFIG:
+ case HV_X64_MSR_STIMER0_COUNT:
+ case HV_X64_MSR_STIMER1_COUNT:
+ case HV_X64_MSR_STIMER2_COUNT:
+ case HV_X64_MSR_STIMER3_COUNT:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_SYNTIMER_AVAILABLE;
+ case HV_X64_MSR_EOI:
+ case HV_X64_MSR_ICR:
+ case HV_X64_MSR_TPR:
+ case HV_X64_MSR_VP_ASSIST_PAGE:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_MSR_APIC_ACCESS_AVAILABLE;
+ case HV_X64_MSR_TSC_FREQUENCY:
+ case HV_X64_MSR_APIC_FREQUENCY:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_ACCESS_FREQUENCY_MSRS;
+ case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
+ case HV_X64_MSR_TSC_EMULATION_CONTROL:
+ case HV_X64_MSR_TSC_EMULATION_STATUS:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_ACCESS_REENLIGHTENMENT;
+ case HV_X64_MSR_TSC_INVARIANT_CONTROL:
+ return hv_vcpu->cpuid_cache.features_eax &
+ HV_ACCESS_TSC_INVARIANT;
+ case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
+ case HV_X64_MSR_CRASH_CTL:
+ return hv_vcpu->cpuid_cache.features_edx &
+ HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ return hv_vcpu->cpuid_cache.features_edx &
+ HV_FEATURE_DEBUG_MSRS_AVAILABLE;
+ default:
+ break;
+ }
+
+ return false;
+}
+
+#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839
+#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */
+
+/*
+ * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC
+ * configuration.
+ * Such configuration can result from, for example, AMD Erratum 1386 workaround.
+ *
+ * Print a notice so users aren't left wondering what's suddenly gone wrong.
+ */
+static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+
+ /* Check again under the hv_lock. */
+ if (hv->xsaves_xsavec_checked)
+ return;
+
+ if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) !=
+ KVM_HV_WIN2016_GUEST_ID)
+ return;
+
+ hv->xsaves_xsavec_checked = true;
+
+ /* UP configurations aren't affected */
+ if (atomic_read(&kvm->online_vcpus) < 2)
+ return;
+
+ if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) ||
+ !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVEC))
+ return;
+
+ pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. "
+ "If it fails to boot try disabling XSAVEC in the VM config.\n");
+}
+
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+ if (!vcpu->arch.hyperv_enabled ||
+ hv->xsaves_xsavec_checked)
+ return;
+
+ mutex_lock(&hv->hv_lock);
+ __kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+ mutex_unlock(&hv->hv_lock);
}
static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
bool host)
{
struct kvm *kvm = vcpu->kvm;
- struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+
+ if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr)))
+ return 1;
switch (msr) {
case HV_X64_MSR_GUEST_OS_ID:
@@ -998,9 +1390,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
break;
case HV_X64_MSR_HYPERCALL: {
- u64 gfn;
- unsigned long addr;
- u8 instructions[4];
+ u8 instructions[9];
+ int i = 0;
+ u64 addr;
/* if guest os id is not set hypercall should remain disabled */
if (!hv->hv_guest_os_id)
@@ -1009,29 +1401,67 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
hv->hv_hypercall = data;
break;
}
- gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
- addr = gfn_to_hva(kvm, gfn);
- if (kvm_is_error_hva(addr))
- return 1;
- kvm_x86_ops->patch_hypercall(vcpu, instructions);
- ((unsigned char *)instructions)[3] = 0xc3; /* ret */
- if (__copy_to_user((void __user *)addr, instructions, 4))
+
+ /*
+ * If Xen and Hyper-V hypercalls are both enabled, disambiguate
+ * the same way Xen itself does, by setting the bit 31 of EAX
+ * which is RsvdZ in the 32-bit Hyper-V hypercall ABI and just
+ * going to be clobbered on 64-bit.
+ */
+ if (kvm_xen_hypercall_enabled(kvm)) {
+ /* orl $0x80000000, %eax */
+ instructions[i++] = 0x0d;
+ instructions[i++] = 0x00;
+ instructions[i++] = 0x00;
+ instructions[i++] = 0x00;
+ instructions[i++] = 0x80;
+ }
+
+ /* vmcall/vmmcall */
+ kvm_x86_call(patch_hypercall)(vcpu, instructions + i);
+ i += 3;
+
+ /* ret */
+ ((unsigned char *)instructions)[i++] = 0xc3;
+
+ addr = data & HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK;
+ if (kvm_vcpu_write_guest(vcpu, addr, instructions, i))
return 1;
hv->hv_hypercall = data;
- mark_page_dirty(kvm, gfn);
break;
}
case HV_X64_MSR_REFERENCE_TSC:
hv->hv_tsc_page = data;
- if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)
+ if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) {
+ if (!host)
+ hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED;
+ else
+ hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED;
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
+ } else {
+ hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET;
+ }
break;
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
- return kvm_hv_msr_set_crash_data(vcpu,
+ return kvm_hv_msr_set_crash_data(kvm,
msr - HV_X64_MSR_CRASH_P0,
data);
case HV_X64_MSR_CRASH_CTL:
- return kvm_hv_msr_set_crash_ctl(vcpu, data, host);
+ if (host)
+ return kvm_hv_msr_set_crash_ctl(kvm, data);
+
+ if (data & HV_CRASH_CTL_CRASH_NOTIFY) {
+ vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
+ hv->hv_crash_param[0],
+ hv->hv_crash_param[1],
+ hv->hv_crash_param[2],
+ hv->hv_crash_param[3],
+ hv->hv_crash_param[4]);
+
+ /* Send notification about crash to user space */
+ kvm_make_request(KVM_REQ_HV_CRASH, vcpu);
+ }
+ break;
case HV_X64_MSR_RESET:
if (data == 1) {
vcpu_debug(vcpu, "hyper-v reset requested\n");
@@ -1045,6 +1475,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
hv->hv_tsc_emulation_control = data;
break;
case HV_X64_MSR_TSC_EMULATION_STATUS:
+ if (data && !host)
+ return 1;
+
hv->hv_tsc_emulation_status = data;
break;
case HV_X64_MSR_TIME_REF_COUNT:
@@ -1052,9 +1485,22 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
if (!host)
return 1;
break;
+ case HV_X64_MSR_TSC_INVARIANT_CONTROL:
+ /* Only bit 0 is supported */
+ if (data & ~HV_EXPOSE_INVARIANT_TSC)
+ return 1;
+
+ /* The feature can't be disabled from the guest */
+ if (!host && hv->hv_invtsc_control && !data)
+ return 1;
+
+ hv->hv_invtsc_control = data;
+ break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ return syndbg_set_msr(vcpu, msr, data, host);
default:
- vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
- msr, data);
+ kvm_pr_unimpl_wrmsr(vcpu, msr, data);
return 1;
}
return 0;
@@ -1072,12 +1518,14 @@ static u64 current_task_runtime_100ns(void)
static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
{
- struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr)))
+ return 1;
switch (msr) {
case HV_X64_MSR_VP_INDEX: {
- struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
- int vcpu_idx = kvm_vcpu_get_idx(vcpu);
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
u32 new_vp_index = (u32)data;
if (!host || new_vp_index >= KVM_MAX_VCPUS)
@@ -1092,9 +1540,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
* VP index is changing, adjust num_mismatched_vp_indexes if
* it now matches or no longer matches vcpu_idx.
*/
- if (hv_vcpu->vp_index == vcpu_idx)
+ if (hv_vcpu->vp_index == vcpu->vcpu_idx)
atomic_inc(&hv->num_mismatched_vp_indexes);
- else if (new_vp_index == vcpu_idx)
+ else if (new_vp_index == vcpu->vcpu_idx)
atomic_dec(&hv->num_mismatched_vp_indexes);
hv_vcpu->vp_index = new_vp_index;
@@ -1106,7 +1554,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) {
hv_vcpu->hv_vapic = data;
- if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0))
+ if (kvm_lapic_set_pv_eoi(vcpu, 0, 0))
return 1;
break;
}
@@ -1116,15 +1564,15 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
return 1;
/*
- * Clear apic_assist portion of f(struct hv_vp_assist_page
+ * Clear apic_assist portion of struct hv_vp_assist_page
* only, there can be valuable data in the rest which needs
* to be preserved e.g. on migration.
*/
- if (__clear_user((void __user *)addr, sizeof(u32)))
+ if (put_user(0, (u32 __user *)addr))
return 1;
hv_vcpu->hv_vapic = data;
kvm_vcpu_mark_page_dirty(vcpu, gfn);
- if (kvm_lapic_enable_pv_eoi(vcpu,
+ if (kvm_lapic_set_pv_eoi(vcpu,
gfn_to_gpa(gfn) | KVM_MSR_ENABLED,
sizeof(struct hv_vp_assist_page)))
return 1;
@@ -1147,14 +1595,14 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
case HV_X64_MSR_SIMP:
case HV_X64_MSR_EOM:
case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
- return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host);
+ return synic_set_msr(to_hv_synic(vcpu), msr, data, host);
case HV_X64_MSR_STIMER0_CONFIG:
case HV_X64_MSR_STIMER1_CONFIG:
case HV_X64_MSR_STIMER2_CONFIG:
case HV_X64_MSR_STIMER3_CONFIG: {
int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;
- return stimer_set_config(vcpu_to_stimer(vcpu, timer_index),
+ return stimer_set_config(to_hv_stimer(vcpu, timer_index),
data, host);
}
case HV_X64_MSR_STIMER0_COUNT:
@@ -1163,7 +1611,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
case HV_X64_MSR_STIMER3_COUNT: {
int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2;
- return stimer_set_count(vcpu_to_stimer(vcpu, timer_index),
+ return stimer_set_count(to_hv_stimer(vcpu, timer_index),
data, host);
}
case HV_X64_MSR_TSC_FREQUENCY:
@@ -1173,19 +1621,22 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
return 1;
break;
default:
- vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
- msr, data);
+ kvm_pr_unimpl_wrmsr(vcpu, msr, data);
return 1;
}
return 0;
}
-static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
+ bool host)
{
u64 data = 0;
struct kvm *kvm = vcpu->kvm;
- struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+
+ if (unlikely(!host && !hv_check_msr_access(to_hv_vcpu(vcpu), msr)))
+ return 1;
switch (msr) {
case HV_X64_MSR_GUEST_OS_ID:
@@ -1201,11 +1652,11 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
data = hv->hv_tsc_page;
break;
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
- return kvm_hv_msr_get_crash_data(vcpu,
+ return kvm_hv_msr_get_crash_data(kvm,
msr - HV_X64_MSR_CRASH_P0,
pdata);
case HV_X64_MSR_CRASH_CTL:
- return kvm_hv_msr_get_crash_ctl(vcpu, pdata);
+ return kvm_hv_msr_get_crash_ctl(kvm, pdata);
case HV_X64_MSR_RESET:
data = 0;
break;
@@ -1218,8 +1669,14 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case HV_X64_MSR_TSC_EMULATION_STATUS:
data = hv->hv_tsc_emulation_status;
break;
+ case HV_X64_MSR_TSC_INVARIANT_CONTROL:
+ data = hv->hv_invtsc_control;
+ break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ return syndbg_get_msr(vcpu, msr, pdata, host);
default:
- vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+ kvm_pr_unimpl_rdmsr(vcpu, msr);
return 1;
}
@@ -1231,7 +1688,10 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
bool host)
{
u64 data = 0;
- struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ if (unlikely(!host && !hv_check_msr_access(hv_vcpu, msr)))
+ return 1;
switch (msr) {
case HV_X64_MSR_VP_INDEX:
@@ -1255,14 +1715,14 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
case HV_X64_MSR_SIMP:
case HV_X64_MSR_EOM:
case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
- return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata, host);
+ return synic_get_msr(to_hv_synic(vcpu), msr, pdata, host);
case HV_X64_MSR_STIMER0_CONFIG:
case HV_X64_MSR_STIMER1_CONFIG:
case HV_X64_MSR_STIMER2_CONFIG:
case HV_X64_MSR_STIMER3_CONFIG: {
int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;
- return stimer_get_config(vcpu_to_stimer(vcpu, timer_index),
+ return stimer_get_config(to_hv_stimer(vcpu, timer_index),
pdata);
}
case HV_X64_MSR_STIMER0_COUNT:
@@ -1271,17 +1731,18 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
case HV_X64_MSR_STIMER3_COUNT: {
int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2;
- return stimer_get_count(vcpu_to_stimer(vcpu, timer_index),
+ return stimer_get_count(to_hv_stimer(vcpu, timer_index),
pdata);
}
case HV_X64_MSR_TSC_FREQUENCY:
data = (u64)vcpu->arch.virtual_tsc_khz * 1000;
break;
case HV_X64_MSR_APIC_FREQUENCY:
- data = APIC_BUS_FREQUENCY;
+ data = div64_u64(1000000000ULL,
+ vcpu->kvm->arch.apic_bus_cycle_ns);
break;
default:
- vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+ kvm_pr_unimpl_rdmsr(vcpu, msr);
return 1;
}
*pdata = data;
@@ -1290,12 +1751,20 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
{
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+ if (!host && !vcpu->arch.hyperv_enabled)
+ return 1;
+
+ if (kvm_hv_vcpu_init(vcpu))
+ return 1;
+
if (kvm_hv_msr_partition_wide(msr)) {
int r;
- mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock);
+ mutex_lock(&hv->hv_lock);
r = kvm_hv_set_msr_pw(vcpu, msr, data, host);
- mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock);
+ mutex_unlock(&hv->hv_lock);
return r;
} else
return kvm_hv_set_msr(vcpu, msr, data, host);
@@ -1303,132 +1772,446 @@ int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
{
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+ if (!host && !vcpu->arch.hyperv_enabled)
+ return 1;
+
+ if (kvm_hv_vcpu_init(vcpu))
+ return 1;
+
if (kvm_hv_msr_partition_wide(msr)) {
int r;
- mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock);
- r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
- mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock);
+ mutex_lock(&hv->hv_lock);
+ r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host);
+ mutex_unlock(&hv->hv_lock);
return r;
} else
return kvm_hv_get_msr(vcpu, msr, pdata, host);
}
-static __always_inline unsigned long *sparse_set_to_vcpu_mask(
- struct kvm *kvm, u64 *sparse_banks, u64 valid_bank_mask,
- u64 *vp_bitmap, unsigned long *vcpu_bitmap)
+static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks,
+ u64 valid_bank_mask, unsigned long *vcpu_mask)
{
- struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+ bool has_mismatch = atomic_read(&hv->num_mismatched_vp_indexes);
+ u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
struct kvm_vcpu *vcpu;
- int i, bank, sbank = 0;
+ int bank, sbank = 0;
+ unsigned long i;
+ u64 *bitmap;
+
+ BUILD_BUG_ON(sizeof(vp_bitmap) >
+ sizeof(*vcpu_mask) * BITS_TO_LONGS(KVM_MAX_VCPUS));
- memset(vp_bitmap, 0,
- KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap));
+ /*
+ * If vp_index == vcpu_idx for all vCPUs, fill vcpu_mask directly, else
+ * fill a temporary buffer and manually test each vCPU's VP index.
+ */
+ if (likely(!has_mismatch))
+ bitmap = (u64 *)vcpu_mask;
+ else
+ bitmap = vp_bitmap;
+
+ /*
+ * Each set of 64 VPs is packed into sparse_banks, with valid_bank_mask
+ * having a '1' for each bank that exists in sparse_banks. Sets must
+ * be in ascending order, i.e. bank0..bankN.
+ */
+ memset(bitmap, 0, sizeof(vp_bitmap));
for_each_set_bit(bank, (unsigned long *)&valid_bank_mask,
KVM_HV_MAX_SPARSE_VCPU_SET_BITS)
- vp_bitmap[bank] = sparse_banks[sbank++];
+ bitmap[bank] = sparse_banks[sbank++];
- if (likely(!atomic_read(&hv->num_mismatched_vp_indexes))) {
- /* for all vcpus vp_index == vcpu_idx */
- return (unsigned long *)vp_bitmap;
- }
+ if (likely(!has_mismatch))
+ return;
- bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
+ bitmap_zero(vcpu_mask, KVM_MAX_VCPUS);
kvm_for_each_vcpu(i, vcpu, kvm) {
- if (test_bit(vcpu_to_hv_vcpu(vcpu)->vp_index,
- (unsigned long *)vp_bitmap))
- __set_bit(i, vcpu_bitmap);
+ if (test_bit(kvm_hv_get_vpindex(vcpu), (unsigned long *)vp_bitmap))
+ __set_bit(i, vcpu_mask);
+ }
+}
+
+static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_banks[])
+{
+ int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK;
+ unsigned long sbank;
+
+ if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask))
+ return false;
+
+ /*
+ * The index into the sparse bank is the number of preceding bits in
+ * the valid mask. Optimize for VMs with <64 vCPUs by skipping the
+ * fancy math if there can't possibly be preceding bits.
+ */
+ if (valid_bit_nr)
+ sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr - 1, 0));
+ else
+ sbank = 0;
+
+ return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK,
+ (unsigned long *)&sparse_banks[sbank]);
+}
+
+struct kvm_hv_hcall {
+ /* Hypercall input data */
+ u64 param;
+ u64 ingpa;
+ u64 outgpa;
+ u16 code;
+ u16 var_cnt;
+ u16 rep_cnt;
+ u16 rep_idx;
+ bool fast;
+ bool rep;
+ sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
+
+ /*
+ * Current read offset when KVM reads hypercall input data gradually,
+ * either offset in bytes from 'ingpa' for regular hypercalls or the
+ * number of already consumed 'XMM halves' for 'fast' hypercalls.
+ */
+ union {
+ gpa_t data_offset;
+ int consumed_xmm_halves;
+ };
+};
+
+
+static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc,
+ u16 orig_cnt, u16 cnt_cap, u64 *data)
+{
+ /*
+ * Preserve the original count when ignoring entries via a "cap", KVM
+ * still needs to validate the guest input (though the non-XMM path
+ * punts on the checks).
+ */
+ u16 cnt = min(orig_cnt, cnt_cap);
+ int i, j;
+
+ if (hc->fast) {
+ /*
+ * Each XMM holds two sparse banks, but do not count halves that
+ * have already been consumed for hypercall parameters.
+ */
+ if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves)
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ for (i = 0; i < cnt; i++) {
+ j = i + hc->consumed_xmm_halves;
+ if (j % 2)
+ data[i] = sse128_hi(hc->xmm[j / 2]);
+ else
+ data[i] = sse128_lo(hc->xmm[j / 2]);
+ }
+ return 0;
+ }
+
+ return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data,
+ cnt * sizeof(*data));
+}
+
+static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc,
+ u64 *sparse_banks)
+{
+ if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS)
+ return -EINVAL;
+
+ /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */
+ return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS,
+ sparse_banks);
+}
+
+static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[])
+{
+ return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries);
+}
+
+static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo,
+ u64 *entries, int count)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u64 flush_all_entry = KVM_HV_TLB_FLUSHALL_ENTRY;
+
+ if (!hv_vcpu)
+ return;
+
+ spin_lock(&tlb_flush_fifo->write_lock);
+
+ /*
+ * All entries should fit on the fifo leaving one free for 'flush all'
+ * entry in case another request comes in. In case there's not enough
+ * space, just put 'flush all' entry there.
+ */
+ if (count && entries && count < kfifo_avail(&tlb_flush_fifo->entries)) {
+ WARN_ON(kfifo_in(&tlb_flush_fifo->entries, entries, count) != count);
+ goto out_unlock;
+ }
+
+ /*
+ * Note: full fifo always contains 'flush all' entry, no need to check the
+ * return value.
+ */
+ kfifo_in(&tlb_flush_fifo->entries, &flush_all_entry, 1);
+
+out_unlock:
+ spin_unlock(&tlb_flush_fifo->write_lock);
+}
+
+int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u64 entries[KVM_HV_TLB_FLUSH_FIFO_SIZE];
+ int i, j, count;
+ gva_t gva;
+
+ if (!tdp_enabled || !hv_vcpu)
+ return -EINVAL;
+
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu));
+
+ count = kfifo_out(&tlb_flush_fifo->entries, entries, KVM_HV_TLB_FLUSH_FIFO_SIZE);
+
+ for (i = 0; i < count; i++) {
+ if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
+ goto out_flush_all;
+
+ if (is_noncanonical_invlpg_address(entries[i], vcpu))
+ continue;
+
+ /*
+ * Lower 12 bits of 'address' encode the number of additional
+ * pages to flush.
+ */
+ gva = entries[i] & PAGE_MASK;
+ for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++)
+ kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE);
+
+ ++vcpu->stat.tlb_flush;
}
- return vcpu_bitmap;
+ return 0;
+
+out_flush_all:
+ kfifo_reset_out(&tlb_flush_fifo->entries);
+
+ /* Fall back to full flush. */
+ return -ENOSPC;
}
-static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
- u16 rep_cnt, bool ex)
+static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
- struct kvm *kvm = current_vcpu->kvm;
- struct kvm_vcpu_hv *hv_vcpu = &current_vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
+ u64 *sparse_banks = hv_vcpu->sparse_banks;
+ struct kvm *kvm = vcpu->kvm;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
- u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
- DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
- unsigned long *vcpu_mask;
+ struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
+ /*
+ * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'
+ * entries on the TLB flush fifo. The last entry, however, needs to be
+ * always left free for 'flush all' entry which gets placed when
+ * there is not enough space to put all the requested entries.
+ */
+ u64 __tlb_flush_entries[KVM_HV_TLB_FLUSH_FIFO_SIZE - 1];
+ u64 *tlb_flush_entries;
u64 valid_bank_mask;
- u64 sparse_banks[64];
- int sparse_banks_len;
+ struct kvm_vcpu *v;
+ unsigned long i;
bool all_cpus;
- if (!ex) {
- if (unlikely(kvm_read_guest(kvm, ingpa, &flush, sizeof(flush))))
+ /*
+ * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS
+ * sparse banks. Fail the build if KVM's max allowed number of
+ * vCPUs (>4096) exceeds this limit.
+ */
+ BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > HV_MAX_SPARSE_VCPU_BANKS);
+
+ /*
+ * 'Slow' hypercall's first parameter is the address in guest's memory
+ * where hypercall parameters are placed. This is either a GPA or a
+ * nested GPA when KVM is handling the call from L2 ('direct' TLB
+ * flush). Translate the address here so the memory can be uniformly
+ * read with kvm_read_guest().
+ */
+ if (!hc->fast && is_guest_mode(vcpu)) {
+ hc->ingpa = translate_nested_gpa(vcpu, hc->ingpa, 0, NULL);
+ if (unlikely(hc->ingpa == INVALID_GPA))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ }
+
+ if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST ||
+ hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) {
+ if (hc->fast) {
+ flush.address_space = hc->ingpa;
+ flush.flags = hc->outgpa;
+ flush.processor_mask = sse128_lo(hc->xmm[0]);
+ hc->consumed_xmm_halves = 1;
+ } else {
+ if (unlikely(kvm_read_guest(kvm, hc->ingpa,
+ &flush, sizeof(flush))))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ hc->data_offset = sizeof(flush);
+ }
trace_kvm_hv_flush_tlb(flush.processor_mask,
- flush.address_space, flush.flags);
+ flush.address_space, flush.flags,
+ is_guest_mode(vcpu));
valid_bank_mask = BIT_ULL(0);
sparse_banks[0] = flush.processor_mask;
- all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+
+ /*
+ * Work around possible WS2012 bug: it sends hypercalls
+ * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear,
+ * while also expecting us to flush something and crashing if
+ * we don't. Let's treat processor_mask == 0 same as
+ * HV_FLUSH_ALL_PROCESSORS.
+ */
+ all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) ||
+ flush.processor_mask == 0;
} else {
- if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
- sizeof(flush_ex))))
- return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ if (hc->fast) {
+ flush_ex.address_space = hc->ingpa;
+ flush_ex.flags = hc->outgpa;
+ memcpy(&flush_ex.hv_vp_set,
+ &hc->xmm[0], sizeof(hc->xmm[0]));
+ hc->consumed_xmm_halves = 2;
+ } else {
+ if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex,
+ sizeof(flush_ex))))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ hc->data_offset = sizeof(flush_ex);
+ }
trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask,
flush_ex.hv_vp_set.format,
flush_ex.address_space,
- flush_ex.flags);
+ flush_ex.flags, is_guest_mode(vcpu));
valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask;
all_cpus = flush_ex.hv_vp_set.format !=
HV_GENERIC_SET_SPARSE_4K;
- sparse_banks_len =
- bitmap_weight((unsigned long *)&valid_bank_mask, 64) *
- sizeof(sparse_banks[0]);
+ if (hc->var_cnt != hweight64(valid_bank_mask))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
- if (!sparse_banks_len && !all_cpus)
- goto ret_success;
+ if (!all_cpus) {
+ if (!hc->var_cnt)
+ goto ret_success;
- if (!all_cpus &&
- kvm_read_guest(kvm,
- ingpa + offsetof(struct hv_tlb_flush_ex,
- hv_vp_set.bank_contents),
- sparse_banks,
- sparse_banks_len))
- return HV_STATUS_INVALID_HYPERCALL_INPUT;
- }
+ if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ }
- cpumask_clear(&hv_vcpu->tlb_flush);
+ /*
+ * Hyper-V TLFS doesn't explicitly forbid non-empty sparse vCPU
+ * banks (and, thus, non-zero 'var_cnt') for the 'all vCPUs'
+ * case (HV_GENERIC_SET_ALL). Always adjust data_offset and
+ * consumed_xmm_halves to make sure TLB flush entries are read
+ * from the correct offset.
+ */
+ if (hc->fast)
+ hc->consumed_xmm_halves += hc->var_cnt;
+ else
+ hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
+ }
- vcpu_mask = all_cpus ? NULL :
- sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
- vp_bitmap, vcpu_bitmap);
+ if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE ||
+ hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX ||
+ hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) {
+ tlb_flush_entries = NULL;
+ } else {
+ if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ tlb_flush_entries = __tlb_flush_entries;
+ }
/*
* vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
* analyze it here, flush TLB regardless of the specified address space.
*/
- kvm_make_vcpus_request_mask(kvm,
- KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
- vcpu_mask, &hv_vcpu->tlb_flush);
+ if (all_cpus && !is_guest_mode(vcpu)) {
+ kvm_for_each_vcpu(i, v, kvm) {
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false);
+ hv_tlb_flush_enqueue(v, tlb_flush_fifo,
+ tlb_flush_entries, hc->rep_cnt);
+ }
+
+ kvm_make_all_cpus_request(kvm, KVM_REQ_HV_TLB_FLUSH);
+ } else if (!is_guest_mode(vcpu)) {
+ sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask);
+
+ for_each_set_bit(i, vcpu_mask, KVM_MAX_VCPUS) {
+ v = kvm_get_vcpu(kvm, i);
+ if (!v)
+ continue;
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false);
+ hv_tlb_flush_enqueue(v, tlb_flush_fifo,
+ tlb_flush_entries, hc->rep_cnt);
+ }
+
+ kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask);
+ } else {
+ struct kvm_vcpu_hv *hv_v;
+
+ bitmap_zero(vcpu_mask, KVM_MAX_VCPUS);
+
+ kvm_for_each_vcpu(i, v, kvm) {
+ hv_v = to_hv_vcpu(v);
+
+ /*
+ * The following check races with nested vCPUs entering/exiting
+ * and/or migrating between L1's vCPUs, however the only case when
+ * KVM *must* flush the TLB is when the target L2 vCPU keeps
+ * running on the same L1 vCPU from the moment of the request until
+ * kvm_hv_flush_tlb() returns. TLB is fully flushed in all other
+ * cases, e.g. when the target L2 vCPU migrates to a different L1
+ * vCPU or when the corresponding L1 vCPU temporary switches to a
+ * different L2 vCPU while the request is being processed.
+ */
+ if (!hv_v || hv_v->nested.vm_id != hv_vcpu->nested.vm_id)
+ continue;
+
+ if (!all_cpus &&
+ !hv_is_vp_in_sparse_set(hv_v->nested.vp_id, valid_bank_mask,
+ sparse_banks))
+ continue;
+
+ __set_bit(i, vcpu_mask);
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, true);
+ hv_tlb_flush_enqueue(v, tlb_flush_fifo,
+ tlb_flush_entries, hc->rep_cnt);
+ }
+
+ kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask);
+ }
ret_success:
- /* We always do full TLB flush, set rep_done = rep_cnt. */
+ /* We always do full TLB flush, set 'Reps completed' = 'Rep Count' */
return (u64)HV_STATUS_SUCCESS |
- ((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
+ ((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
}
-static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
- unsigned long *vcpu_bitmap)
+static void kvm_hv_send_ipi_to_many(struct kvm *kvm, u32 vector,
+ u64 *sparse_banks, u64 valid_bank_mask)
{
struct kvm_lapic_irq irq = {
.delivery_mode = APIC_DM_FIXED,
.vector = vector
};
struct kvm_vcpu *vcpu;
- int i;
+ unsigned long i;
kvm_for_each_vcpu(i, vcpu, kvm) {
- if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
+ if (sparse_banks &&
+ !hv_is_vp_in_sparse_set(kvm_hv_get_vpindex(vcpu),
+ valid_bank_mask, sparse_banks))
continue;
/* We fail only when APIC is disabled */
@@ -1436,43 +2219,48 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
}
}
-static u64 kvm_hv_send_ipi(struct kvm_vcpu *current_vcpu, u64 ingpa, u64 outgpa,
- bool ex, bool fast)
+static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
- struct kvm *kvm = current_vcpu->kvm;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u64 *sparse_banks = hv_vcpu->sparse_banks;
+ struct kvm *kvm = vcpu->kvm;
struct hv_send_ipi_ex send_ipi_ex;
struct hv_send_ipi send_ipi;
- u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
- DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
- unsigned long *vcpu_mask;
- unsigned long valid_bank_mask;
- u64 sparse_banks[64];
- int sparse_banks_len;
+ u64 valid_bank_mask;
u32 vector;
bool all_cpus;
- if (!ex) {
- if (!fast) {
- if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi,
+ if (!lapic_in_kernel(vcpu))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ if (hc->code == HVCALL_SEND_IPI) {
+ if (!hc->fast) {
+ if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi,
sizeof(send_ipi))))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
sparse_banks[0] = send_ipi.cpu_mask;
vector = send_ipi.vector;
} else {
/* 'reserved' part of hv_send_ipi should be 0 */
- if (unlikely(ingpa >> 32 != 0))
+ if (unlikely(hc->ingpa >> 32 != 0))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- sparse_banks[0] = outgpa;
- vector = (u32)ingpa;
+ sparse_banks[0] = hc->outgpa;
+ vector = (u32)hc->ingpa;
}
all_cpus = false;
valid_bank_mask = BIT_ULL(0);
trace_kvm_hv_send_ipi(vector, sparse_banks[0]);
} else {
- if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi_ex,
- sizeof(send_ipi_ex))))
- return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ if (!hc->fast) {
+ if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex,
+ sizeof(send_ipi_ex))))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ } else {
+ send_ipi_ex.vector = (u32)hc->ingpa;
+ send_ipi_ex.vp_set.format = hc->outgpa;
+ send_ipi_ex.vp_set.valid_bank_mask = sse128_lo(hc->xmm[0]);
+ }
trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector,
send_ipi_ex.vp_set.format,
@@ -1480,59 +2268,140 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *current_vcpu, u64 ingpa, u64 outgpa,
vector = send_ipi_ex.vector;
valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask;
- sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
- sizeof(sparse_banks[0]);
-
all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
- if (!sparse_banks_len)
+ if (hc->var_cnt != hweight64(valid_bank_mask))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ if (all_cpus)
+ goto check_and_send_ipi;
+
+ if (!hc->var_cnt)
goto ret_success;
- if (!all_cpus &&
- kvm_read_guest(kvm,
- ingpa + offsetof(struct hv_send_ipi_ex,
- vp_set.bank_contents),
- sparse_banks,
- sparse_banks_len))
+ if (!hc->fast)
+ hc->data_offset = offsetof(struct hv_send_ipi_ex,
+ vp_set.bank_contents);
+ else
+ hc->consumed_xmm_halves = 1;
+
+ if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
}
+check_and_send_ipi:
if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- vcpu_mask = all_cpus ? NULL :
- sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
- vp_bitmap, vcpu_bitmap);
-
- kvm_send_ipi_to_many(kvm, vector, vcpu_mask);
+ if (all_cpus)
+ kvm_hv_send_ipi_to_many(kvm, vector, NULL, 0);
+ else
+ kvm_hv_send_ipi_to_many(kvm, vector, sparse_banks, valid_bank_mask);
ret_success:
return HV_STATUS_SUCCESS;
}
-bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled)
{
- return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ struct kvm_cpuid_entry2 *entry;
+
+ vcpu->arch.hyperv_enabled = hyperv_enabled;
+
+ if (!hv_vcpu) {
+ /*
+ * KVM should have already allocated kvm_vcpu_hv if Hyper-V is
+ * enabled in CPUID.
+ */
+ WARN_ON_ONCE(vcpu->arch.hyperv_enabled);
+ return;
+ }
+
+ memset(&hv_vcpu->cpuid_cache, 0, sizeof(hv_vcpu->cpuid_cache));
+
+ if (!vcpu->arch.hyperv_enabled)
+ return;
+
+ entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES);
+ if (entry) {
+ hv_vcpu->cpuid_cache.features_eax = entry->eax;
+ hv_vcpu->cpuid_cache.features_ebx = entry->ebx;
+ hv_vcpu->cpuid_cache.features_edx = entry->edx;
+ }
+
+ entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO);
+ if (entry) {
+ hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax;
+ hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx;
+ }
+
+ entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES);
+ if (entry)
+ hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax;
+
+ entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_NESTED_FEATURES);
+ if (entry) {
+ hv_vcpu->cpuid_cache.nested_eax = entry->eax;
+ hv_vcpu->cpuid_cache.nested_ebx = entry->ebx;
+ }
+}
+
+int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce)
+{
+ struct kvm_vcpu_hv *hv_vcpu;
+ int ret = 0;
+
+ if (!to_hv_vcpu(vcpu)) {
+ if (enforce) {
+ ret = kvm_hv_vcpu_init(vcpu);
+ if (ret)
+ return ret;
+ } else {
+ return 0;
+ }
+ }
+
+ hv_vcpu = to_hv_vcpu(vcpu);
+ hv_vcpu->enforce_cpuid = enforce;
+
+ return ret;
}
static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
{
bool longmode;
- longmode = is_64_bit_mode(vcpu);
+ longmode = is_64_bit_hypercall(vcpu);
if (longmode)
- kvm_register_write(vcpu, VCPU_REGS_RAX, result);
+ kvm_rax_write(vcpu, result);
else {
- kvm_register_write(vcpu, VCPU_REGS_RDX, result >> 32);
- kvm_register_write(vcpu, VCPU_REGS_RAX, result & 0xffffffff);
+ kvm_rdx_write(vcpu, result >> 32);
+ kvm_rax_write(vcpu, result & 0xffffffff);
}
}
static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
{
+ u32 tlb_lock_count = 0;
+ int ret;
+
+ if (hv_result_success(result) && is_guest_mode(vcpu) &&
+ kvm_hv_is_tlb_flush_hcall(vcpu) &&
+ kvm_read_guest(vcpu->kvm, to_hv_vcpu(vcpu)->nested.pa_page_gpa,
+ &tlb_lock_count, sizeof(tlb_lock_count)))
+ result = HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ trace_kvm_hv_hypercall_done(result);
kvm_hv_hypercall_set_result(vcpu, result);
++vcpu->stat.hypercalls;
- return kvm_skip_emulated_instruction(vcpu);
+
+ ret = kvm_skip_emulated_instruction(vcpu);
+
+ if (tlb_lock_count)
+ kvm_x86_ops.nested_ops->hv_inject_synthetic_vmexit_post_tlb_flush(vcpu);
+
+ return ret;
}
static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
@@ -1540,19 +2409,21 @@ static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result);
}
-static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
+static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
struct eventfd_ctx *eventfd;
- if (unlikely(!fast)) {
+ if (unlikely(!hc->fast)) {
int ret;
- gpa_t gpa = param;
+ gpa_t gpa = hc->ingpa;
- if ((gpa & (__alignof__(param) - 1)) ||
- offset_in_page(gpa) + sizeof(param) > PAGE_SIZE)
+ if ((gpa & (__alignof__(hc->ingpa) - 1)) ||
+ offset_in_page(gpa) + sizeof(hc->ingpa) > PAGE_SIZE)
return HV_STATUS_INVALID_ALIGNMENT;
- ret = kvm_vcpu_read_guest(vcpu, gpa, &param, sizeof(param));
+ ret = kvm_vcpu_read_guest(vcpu, gpa,
+ &hc->ingpa, sizeof(hc->ingpa));
if (ret < 0)
return HV_STATUS_INVALID_ALIGNMENT;
}
@@ -1562,164 +2433,289 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
* have no use for it, and in all known usecases it is zero, so just
* report lookup failure if it isn't.
*/
- if (param & 0xffff00000000ULL)
+ if (hc->ingpa & 0xffff00000000ULL)
return HV_STATUS_INVALID_PORT_ID;
/* remaining bits are reserved-zero */
- if (param & ~KVM_HYPERV_CONN_ID_MASK)
+ if (hc->ingpa & ~KVM_HYPERV_CONN_ID_MASK)
return HV_STATUS_INVALID_HYPERCALL_INPUT;
/* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */
rcu_read_lock();
- eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+ eventfd = idr_find(&hv->conn_to_evt, hc->ingpa);
rcu_read_unlock();
if (!eventfd)
return HV_STATUS_INVALID_PORT_ID;
- eventfd_signal(eventfd, 1);
+ eventfd_signal(eventfd);
return HV_STATUS_SUCCESS;
}
+static bool is_xmm_fast_hypercall(struct kvm_hv_hcall *hc)
+{
+ switch (hc->code) {
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST:
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
+ case HVCALL_SEND_IPI_EX:
+ return true;
+ }
+
+ return false;
+}
+
+static void kvm_hv_hypercall_read_xmm(struct kvm_hv_hcall *hc)
+{
+ int reg;
+
+ kvm_fpu_get();
+ for (reg = 0; reg < HV_HYPERCALL_MAX_XMM_REGISTERS; reg++)
+ _kvm_read_sse_reg(reg, &hc->xmm[reg]);
+ kvm_fpu_put();
+}
+
+static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code)
+{
+ if (!hv_vcpu->enforce_cpuid)
+ return true;
+
+ switch (code) {
+ case HVCALL_NOTIFY_LONG_SPIN_WAIT:
+ return hv_vcpu->cpuid_cache.enlightenments_ebx &&
+ hv_vcpu->cpuid_cache.enlightenments_ebx != U32_MAX;
+ case HVCALL_POST_MESSAGE:
+ return hv_vcpu->cpuid_cache.features_ebx & HV_POST_MESSAGES;
+ case HVCALL_SIGNAL_EVENT:
+ return hv_vcpu->cpuid_cache.features_ebx & HV_SIGNAL_EVENTS;
+ case HVCALL_POST_DEBUG_DATA:
+ case HVCALL_RETRIEVE_DEBUG_DATA:
+ case HVCALL_RESET_DEBUG_SESSION:
+ /*
+ * Return 'true' when SynDBG is disabled so the resulting code
+ * will be HV_STATUS_INVALID_HYPERCALL_CODE.
+ */
+ return !kvm_hv_is_syndbg_enabled(hv_vcpu->vcpu) ||
+ hv_vcpu->cpuid_cache.features_ebx & HV_DEBUGGING;
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
+ if (!(hv_vcpu->cpuid_cache.enlightenments_eax &
+ HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+ return false;
+ fallthrough;
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST:
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
+ return hv_vcpu->cpuid_cache.enlightenments_eax &
+ HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
+ case HVCALL_SEND_IPI_EX:
+ if (!(hv_vcpu->cpuid_cache.enlightenments_eax &
+ HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+ return false;
+ fallthrough;
+ case HVCALL_SEND_IPI:
+ return hv_vcpu->cpuid_cache.enlightenments_eax &
+ HV_X64_CLUSTER_IPI_RECOMMENDED;
+ case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX:
+ return hv_vcpu->cpuid_cache.features_ebx &
+ HV_ENABLE_EXTENDED_HYPERCALLS;
+ default:
+ break;
+ }
+
+ return true;
+}
+
int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
{
- u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS;
- uint16_t code, rep_idx, rep_cnt;
- bool fast, longmode, rep;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ struct kvm_hv_hcall hc;
+ u64 ret = HV_STATUS_SUCCESS;
/*
* hypercall generates UD from non zero cpl and real mode
* per HYPER-V spec
*/
- if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
+ if (kvm_x86_call(get_cpl)(vcpu) != 0 || !is_protmode(vcpu)) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
- longmode = is_64_bit_mode(vcpu);
+#ifdef CONFIG_X86_64
+ if (is_64_bit_hypercall(vcpu)) {
+ hc.param = kvm_rcx_read(vcpu);
+ hc.ingpa = kvm_rdx_read(vcpu);
+ hc.outgpa = kvm_r8_read(vcpu);
+ } else
+#endif
+ {
+ hc.param = ((u64)kvm_rdx_read(vcpu) << 32) |
+ (kvm_rax_read(vcpu) & 0xffffffff);
+ hc.ingpa = ((u64)kvm_rbx_read(vcpu) << 32) |
+ (kvm_rcx_read(vcpu) & 0xffffffff);
+ hc.outgpa = ((u64)kvm_rdi_read(vcpu) << 32) |
+ (kvm_rsi_read(vcpu) & 0xffffffff);
+ }
+
+ hc.code = hc.param & 0xffff;
+ hc.var_cnt = (hc.param & HV_HYPERCALL_VARHEAD_MASK) >> HV_HYPERCALL_VARHEAD_OFFSET;
+ hc.fast = !!(hc.param & HV_HYPERCALL_FAST_BIT);
+ hc.rep_cnt = (hc.param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff;
+ hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
+ hc.rep = !!(hc.rep_cnt || hc.rep_idx);
- if (!longmode) {
- param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
- (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
- ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
- (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
- outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
- (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+ trace_kvm_hv_hypercall(hc.code, hc.fast, hc.var_cnt, hc.rep_cnt,
+ hc.rep_idx, hc.ingpa, hc.outgpa);
+
+ if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) {
+ ret = HV_STATUS_ACCESS_DENIED;
+ goto hypercall_complete;
}
-#ifdef CONFIG_X86_64
- else {
- param = kvm_register_read(vcpu, VCPU_REGS_RCX);
- ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
- outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+
+ if (unlikely(hc.param & HV_HYPERCALL_RSVD_MASK)) {
+ ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+ goto hypercall_complete;
}
-#endif
- code = param & 0xffff;
- fast = !!(param & HV_HYPERCALL_FAST_BIT);
- rep_cnt = (param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff;
- rep_idx = (param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
- rep = !!(rep_cnt || rep_idx);
+ if (hc.fast && is_xmm_fast_hypercall(&hc)) {
+ if (unlikely(hv_vcpu->enforce_cpuid &&
+ !(hv_vcpu->cpuid_cache.features_edx &
+ HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
- trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+ kvm_hv_hypercall_read_xmm(&hc);
+ }
- switch (code) {
+ switch (hc.code) {
case HVCALL_NOTIFY_LONG_SPIN_WAIT:
- if (unlikely(rep)) {
+ if (unlikely(hc.rep || hc.var_cnt)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
kvm_vcpu_on_spin(vcpu, true);
break;
case HVCALL_SIGNAL_EVENT:
- if (unlikely(rep)) {
+ if (unlikely(hc.rep || hc.var_cnt)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
+ ret = kvm_hvcall_signal_event(vcpu, &hc);
if (ret != HV_STATUS_INVALID_PORT_ID)
break;
- /* maybe userspace knows this conn_id: fall through */
+ fallthrough; /* maybe userspace knows this conn_id */
case HVCALL_POST_MESSAGE:
/* don't bother userspace if it has no way to handle it */
- if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
+ if (unlikely(hc.rep || hc.var_cnt || !to_hv_synic(vcpu)->active)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- vcpu->run->exit_reason = KVM_EXIT_HYPERV;
- vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL;
- vcpu->run->hyperv.u.hcall.input = param;
- vcpu->run->hyperv.u.hcall.params[0] = ingpa;
- vcpu->run->hyperv.u.hcall.params[1] = outgpa;
- vcpu->arch.complete_userspace_io =
- kvm_hv_hypercall_complete_userspace;
- return 0;
+ goto hypercall_userspace_exit;
case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST:
- if (unlikely(fast || !rep_cnt || rep_idx)) {
+ if (unlikely(hc.var_cnt)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false);
- break;
- case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
- if (unlikely(fast || rep)) {
+ fallthrough;
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
+ if (unlikely(!hc.rep_cnt || hc.rep_idx)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false);
+ ret = kvm_hv_flush_tlb(vcpu, &hc);
break;
- case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
- if (unlikely(fast || !rep_cnt || rep_idx)) {
+ case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
+ if (unlikely(hc.var_cnt)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true);
- break;
+ fallthrough;
case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
- if (unlikely(fast || rep)) {
+ if (unlikely(hc.rep)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true);
+ ret = kvm_hv_flush_tlb(vcpu, &hc);
break;
case HVCALL_SEND_IPI:
- if (unlikely(rep)) {
+ if (unlikely(hc.var_cnt)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, false, fast);
- break;
+ fallthrough;
case HVCALL_SEND_IPI_EX:
- if (unlikely(fast || rep)) {
+ if (unlikely(hc.rep)) {
ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
break;
}
- ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false);
+ ret = kvm_hv_send_ipi(vcpu, &hc);
break;
+ case HVCALL_POST_DEBUG_DATA:
+ case HVCALL_RETRIEVE_DEBUG_DATA:
+ if (unlikely(hc.fast)) {
+ ret = HV_STATUS_INVALID_PARAMETER;
+ break;
+ }
+ fallthrough;
+ case HVCALL_RESET_DEBUG_SESSION: {
+ struct kvm_hv_syndbg *syndbg = to_hv_syndbg(vcpu);
+
+ if (!kvm_hv_is_syndbg_enabled(vcpu)) {
+ ret = HV_STATUS_INVALID_HYPERCALL_CODE;
+ break;
+ }
+
+ if (!(syndbg->options & HV_X64_SYNDBG_OPTION_USE_HCALLS)) {
+ ret = HV_STATUS_OPERATION_DENIED;
+ break;
+ }
+ goto hypercall_userspace_exit;
+ }
+ case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX:
+ if (unlikely(hc.fast)) {
+ ret = HV_STATUS_INVALID_PARAMETER;
+ break;
+ }
+ goto hypercall_userspace_exit;
default:
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
break;
}
+hypercall_complete:
return kvm_hv_hypercall_complete(vcpu, ret);
+
+hypercall_userspace_exit:
+ vcpu->run->exit_reason = KVM_EXIT_HYPERV;
+ vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL;
+ vcpu->run->hyperv.u.hcall.input = hc.param;
+ vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa;
+ vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa;
+ vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace;
+ return 0;
}
void kvm_hv_init_vm(struct kvm *kvm)
{
- mutex_init(&kvm->arch.hyperv.hv_lock);
- idr_init(&kvm->arch.hyperv.conn_to_evt);
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+
+ mutex_init(&hv->hv_lock);
+ idr_init(&hv->conn_to_evt);
}
void kvm_hv_destroy_vm(struct kvm *kvm)
{
+ struct kvm_hv *hv = to_kvm_hv(kvm);
struct eventfd_ctx *eventfd;
int i;
- idr_for_each_entry(&kvm->arch.hyperv.conn_to_evt, eventfd, i)
+ idr_for_each_entry(&hv->conn_to_evt, eventfd, i)
eventfd_ctx_put(eventfd);
- idr_destroy(&kvm->arch.hyperv.conn_to_evt);
+ idr_destroy(&hv->conn_to_evt);
}
static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd)
{
- struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
struct eventfd_ctx *eventfd;
int ret;
@@ -1729,7 +2725,7 @@ static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd)
mutex_lock(&hv->hv_lock);
ret = idr_alloc(&hv->conn_to_evt, eventfd, conn_id, conn_id + 1,
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
mutex_unlock(&hv->hv_lock);
if (ret >= 0)
@@ -1743,7 +2739,7 @@ static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd)
static int kvm_hv_eventfd_deassign(struct kvm *kvm, u32 conn_id)
{
- struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
struct eventfd_ctx *eventfd;
mutex_lock(&hv->hv_lock);
@@ -1769,10 +2765,10 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args)
return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd);
}
-int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries)
+int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries)
{
- uint16_t evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+ uint16_t evmcs_ver = 0;
struct kvm_cpuid_entry2 cpuid_entries[] = {
{ .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS },
{ .function = HYPERV_CPUID_INTERFACE },
@@ -1780,13 +2776,15 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
{ .function = HYPERV_CPUID_FEATURES },
{ .function = HYPERV_CPUID_ENLIGHTMENT_INFO },
{ .function = HYPERV_CPUID_IMPLEMENT_LIMITS },
+ { .function = HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS },
+ { .function = HYPERV_CPUID_SYNDBG_INTERFACE },
+ { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES },
{ .function = HYPERV_CPUID_NESTED_FEATURES },
};
int i, nent = ARRAY_SIZE(cpuid_entries);
- /* Skip NESTED_FEATURES if eVMCS is not supported */
- if (!evmcs_ver)
- --nent;
+ if (kvm_x86_ops.nested_ops->get_evmcs_version)
+ evmcs_ver = kvm_x86_ops.nested_ops->get_evmcs_version(vcpu);
if (cpuid->nent < nent)
return -E2BIG;
@@ -1802,15 +2800,14 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS:
memcpy(signature, "Linux KVM Hv", 12);
- ent->eax = HYPERV_CPUID_NESTED_FEATURES;
+ ent->eax = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES;
ent->ebx = signature[0];
ent->ecx = signature[1];
ent->edx = signature[2];
break;
case HYPERV_CPUID_INTERFACE:
- memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12);
- ent->eax = signature[0];
+ ent->eax = HYPERV_CPUID_SIGNATURE_EAX;
break;
case HYPERV_CPUID_VERSION:
@@ -1823,37 +2820,54 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
break;
case HYPERV_CPUID_FEATURES:
- ent->eax |= HV_X64_MSR_VP_RUNTIME_AVAILABLE;
+ ent->eax |= HV_MSR_VP_RUNTIME_AVAILABLE;
ent->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE;
- ent->eax |= HV_X64_MSR_SYNIC_AVAILABLE;
+ ent->eax |= HV_MSR_SYNIC_AVAILABLE;
ent->eax |= HV_MSR_SYNTIMER_AVAILABLE;
- ent->eax |= HV_X64_MSR_APIC_ACCESS_AVAILABLE;
- ent->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE;
- ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE;
- ent->eax |= HV_X64_MSR_RESET_AVAILABLE;
+ ent->eax |= HV_MSR_APIC_ACCESS_AVAILABLE;
+ ent->eax |= HV_MSR_HYPERCALL_AVAILABLE;
+ ent->eax |= HV_MSR_VP_INDEX_AVAILABLE;
+ ent->eax |= HV_MSR_RESET_AVAILABLE;
ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE;
- ent->eax |= HV_X64_MSR_GUEST_IDLE_AVAILABLE;
- ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS;
- ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT;
+ ent->eax |= HV_ACCESS_FREQUENCY_MSRS;
+ ent->eax |= HV_ACCESS_REENLIGHTENMENT;
+ ent->eax |= HV_ACCESS_TSC_INVARIANT;
- ent->ebx |= HV_X64_POST_MESSAGES;
- ent->ebx |= HV_X64_SIGNAL_EVENTS;
+ ent->ebx |= HV_POST_MESSAGES;
+ ent->ebx |= HV_SIGNAL_EVENTS;
+ ent->ebx |= HV_ENABLE_EXTENDED_HYPERCALLS;
+ ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE;
ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE;
ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
- ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE;
+
+ ent->ebx |= HV_DEBUGGING;
+ ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE;
+ ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE;
+ ent->edx |= HV_FEATURE_EXT_GVA_RANGES_FLUSH;
+
+ /*
+ * Direct Synthetic timers only make sense with in-kernel
+ * LAPIC
+ */
+ if (!vcpu || lapic_in_kernel(vcpu))
+ ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE;
break;
case HYPERV_CPUID_ENLIGHTMENT_INFO:
ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
- ent->eax |= HV_X64_SYSTEM_RESET_RECOMMENDED;
ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
- ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
+ if (!vcpu || lapic_in_kernel(vcpu))
+ ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
- ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
+ if (evmcs_ver)
+ ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
+ if (!cpu_smt_possible())
+ ent->eax |= HV_X64_NO_NONARCH_CORESHARING;
+ ent->eax |= HV_DEPRECATING_AEOI_RECOMMENDED;
/*
* Default number of spinlock retry attempts, matches
* HyperV 2016.
@@ -1875,7 +2889,27 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_NESTED_FEATURES:
ent->eax = evmcs_ver;
+ ent->eax |= HV_X64_NESTED_DIRECT_FLUSH;
+ ent->eax |= HV_X64_NESTED_MSR_BITMAP;
+ ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL;
+ break;
+
+ case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS:
+ memcpy(signature, "Linux KVM Hv", 12);
+
+ ent->eax = 0;
+ ent->ebx = signature[0];
+ ent->ecx = signature[1];
+ ent->edx = signature[2];
+ break;
+
+ case HYPERV_CPUID_SYNDBG_INTERFACE:
+ memcpy(signature, "VS#1\0\0\0\0\0\0\0\0", 12);
+ ent->eax = signature[0];
+ break;
+ case HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES:
+ ent->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING;
break;
default:
generated by cgit (git 2.34.1) at 2025-12-22 09:54:03 +0000