From 10ebd8556b7990499c896a550e3d416b444211e6 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 02:23:07 +0000
Subject: [PATCH] add led
---
kernel/arch/x86/kernel/kvm.c | 632 +++++++++++++++++++++++++++++++++++++--------------------
1 files changed, 409 insertions(+), 223 deletions(-)
diff --git a/kernel/arch/x86/kernel/kvm.c b/kernel/arch/x86/kernel/kvm.c
index cee45d4..fe9babe 100644
--- a/kernel/arch/x86/kernel/kvm.c
+++ b/kernel/arch/x86/kernel/kvm.c
@@ -1,27 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* KVM paravirt_ops implementation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
* Copyright IBM Corporation, 2007
* Authors: Anthony Liguori <aliguori@us.ibm.com>
*/
+#define pr_fmt(fmt) "kvm-guest: " fmt
+
#include <linux/context_tracking.h>
#include <linux/init.h>
+#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/kvm_para.h>
#include <linux/cpu.h>
@@ -34,9 +24,9 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kprobes.h>
-#include <linux/debugfs.h>
#include <linux/nmi.h>
#include <linux/swait.h>
+#include <linux/syscore_ops.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
@@ -46,6 +36,12 @@
#include <asm/apicdef.h>
#include <asm/hypervisor.h>
#include <asm/tlb.h>
+#include <asm/cpuidle_haltpoll.h>
+#include <asm/ptrace.h>
+#include <asm/reboot.h>
+#include <asm/svm.h>
+
+DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
static int kvmapf = 1;
@@ -67,9 +63,10 @@
early_param("no-steal-acc", parse_no_stealacc);
static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
-static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64);
+DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
static int has_steal_clock = 0;
+static int has_guest_poll = 0;
/*
* No need for any "IO delay" on KVM
*/
@@ -85,7 +82,6 @@
struct swait_queue_head wq;
u32 token;
int cpu;
- bool halted;
};
static struct kvm_task_sleep_head {
@@ -108,77 +104,64 @@
return NULL;
}
-/*
- * @interrupt_kernel: Is this called from a routine which interrupts the kernel
- * (other than user space)?
- */
-void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
+static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
{
u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
- struct kvm_task_sleep_node n, *e;
- DECLARE_SWAITQUEUE(wait);
-
- rcu_irq_enter();
+ struct kvm_task_sleep_node *e;
raw_spin_lock(&b->lock);
e = _find_apf_task(b, token);
if (e) {
/* dummy entry exist -> wake up was delivered ahead of PF */
hlist_del(&e->link);
- kfree(e);
raw_spin_unlock(&b->lock);
-
- rcu_irq_exit();
- return;
+ kfree(e);
+ return false;
}
- n.token = token;
- n.cpu = smp_processor_id();
- n.halted = is_idle_task(current) ||
- (IS_ENABLED(CONFIG_PREEMPT_COUNT)
- ? preempt_count() > 1 || rcu_preempt_depth()
- : interrupt_kernel);
- init_swait_queue_head(&n.wq);
- hlist_add_head(&n.link, &b->list);
+ n->token = token;
+ n->cpu = smp_processor_id();
+ init_swait_queue_head(&n->wq);
+ hlist_add_head(&n->link, &b->list);
raw_spin_unlock(&b->lock);
+ return true;
+}
+
+/*
+ * kvm_async_pf_task_wait_schedule - Wait for pagefault to be handled
+ * @token: Token to identify the sleep node entry
+ *
+ * Invoked from the async pagefault handling code or from the VM exit page
+ * fault handler. In both cases RCU is watching.
+ */
+void kvm_async_pf_task_wait_schedule(u32 token)
+{
+ struct kvm_task_sleep_node n;
+ DECLARE_SWAITQUEUE(wait);
+
+ lockdep_assert_irqs_disabled();
+
+ if (!kvm_async_pf_queue_task(token, &n))
+ return;
for (;;) {
- if (!n.halted)
- prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
if (hlist_unhashed(&n.link))
break;
- rcu_irq_exit();
-
- if (!n.halted) {
- local_irq_enable();
- schedule();
- local_irq_disable();
- } else {
- /*
- * We cannot reschedule. So halt.
- */
- native_safe_halt();
- local_irq_disable();
- }
-
- rcu_irq_enter();
+ local_irq_enable();
+ schedule();
+ local_irq_disable();
}
- if (!n.halted)
- finish_swait(&n.wq, &wait);
-
- rcu_irq_exit();
- return;
+ finish_swait(&n.wq, &wait);
}
-EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
+EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait_schedule);
static void apf_task_wake_one(struct kvm_task_sleep_node *n)
{
hlist_del_init(&n->link);
- if (n->halted)
- smp_send_reschedule(n->cpu);
- else if (swq_has_sleeper(&n->wq))
+ if (swq_has_sleeper(&n->wq))
swake_up_one(&n->wq);
}
@@ -187,12 +170,13 @@
int i;
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
- struct hlist_node *p, *next;
struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
+ struct kvm_task_sleep_node *n;
+ struct hlist_node *p, *next;
+
raw_spin_lock(&b->lock);
hlist_for_each_safe(p, next, &b->list) {
- struct kvm_task_sleep_node *n =
- hlist_entry(p, typeof(*n), link);
+ n = hlist_entry(p, typeof(*n), link);
if (n->cpu == smp_processor_id())
apf_task_wake_one(n);
}
@@ -204,7 +188,7 @@
{
u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
- struct kvm_task_sleep_node *n;
+ struct kvm_task_sleep_node *n, *dummy = NULL;
if (token == ~0) {
apf_task_wake_all();
@@ -216,74 +200,115 @@
n = _find_apf_task(b, token);
if (!n) {
/*
- * async PF was not yet handled.
- * Add dummy entry for the token.
+ * Async #PF not yet handled, add a dummy entry for the token.
+ * Allocating the token must be down outside of the raw lock
+ * as the allocator is preemptible on PREEMPT_RT kernels.
*/
- n = kzalloc(sizeof(*n), GFP_ATOMIC);
- if (!n) {
- /*
- * Allocation failed! Busy wait while other cpu
- * handles async PF.
- */
+ if (!dummy) {
raw_spin_unlock(&b->lock);
- cpu_relax();
+ dummy = kzalloc(sizeof(*dummy), GFP_ATOMIC);
+
+ /*
+ * Continue looping on allocation failure, eventually
+ * the async #PF will be handled and allocating a new
+ * node will be unnecessary.
+ */
+ if (!dummy)
+ cpu_relax();
+
+ /*
+ * Recheck for async #PF completion before enqueueing
+ * the dummy token to avoid duplicate list entries.
+ */
goto again;
}
- n->token = token;
- n->cpu = smp_processor_id();
- init_swait_queue_head(&n->wq);
- hlist_add_head(&n->link, &b->list);
- } else
+ dummy->token = token;
+ dummy->cpu = smp_processor_id();
+ init_swait_queue_head(&dummy->wq);
+ hlist_add_head(&dummy->link, &b->list);
+ dummy = NULL;
+ } else {
apf_task_wake_one(n);
+ }
raw_spin_unlock(&b->lock);
- return;
+
+ /* A dummy token might be allocated and ultimately not used. */
+ if (dummy)
+ kfree(dummy);
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
-u32 kvm_read_and_reset_pf_reason(void)
+noinstr u32 kvm_read_and_reset_apf_flags(void)
{
- u32 reason = 0;
+ u32 flags = 0;
if (__this_cpu_read(apf_reason.enabled)) {
- reason = __this_cpu_read(apf_reason.reason);
- __this_cpu_write(apf_reason.reason, 0);
+ flags = __this_cpu_read(apf_reason.flags);
+ __this_cpu_write(apf_reason.flags, 0);
}
- return reason;
+ return flags;
}
-EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
-NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason);
+EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);
-dotraplinkage void
-do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
+noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
{
- enum ctx_state prev_state;
+ u32 flags = kvm_read_and_reset_apf_flags();
+ irqentry_state_t state;
- switch (kvm_read_and_reset_pf_reason()) {
- default:
- do_page_fault(regs, error_code);
- break;
- case KVM_PV_REASON_PAGE_NOT_PRESENT:
- /* page is swapped out by the host. */
- prev_state = exception_enter();
- kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs));
- exception_exit(prev_state);
- break;
- case KVM_PV_REASON_PAGE_READY:
- rcu_irq_enter();
- kvm_async_pf_task_wake((u32)read_cr2());
- rcu_irq_exit();
- break;
+ if (!flags)
+ return false;
+
+ state = irqentry_enter(regs);
+ instrumentation_begin();
+
+ /*
+ * If the host managed to inject an async #PF into an interrupt
+ * disabled region, then die hard as this is not going to end well
+ * and the host side is seriously broken.
+ */
+ if (unlikely(!(regs->flags & X86_EFLAGS_IF)))
+ panic("Host injected async #PF in interrupt disabled region\n");
+
+ if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) {
+ if (unlikely(!(user_mode(regs))))
+ panic("Host injected async #PF in kernel mode\n");
+ /* Page is swapped out by the host. */
+ kvm_async_pf_task_wait_schedule(token);
+ } else {
+ WARN_ONCE(1, "Unexpected async PF flags: %x\n", flags);
}
+
+ instrumentation_end();
+ irqentry_exit(regs, state);
+ return true;
}
-NOKPROBE_SYMBOL(do_async_page_fault);
+
+DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ u32 token;
+
+ ack_APIC_irq();
+
+ inc_irq_stat(irq_hv_callback_count);
+
+ if (__this_cpu_read(apf_reason.enabled)) {
+ token = __this_cpu_read(apf_reason.token);
+ kvm_async_pf_task_wake(token);
+ __this_cpu_write(apf_reason.token, 0);
+ wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
+ }
+
+ set_irq_regs(old_regs);
+}
static void __init paravirt_ops_setup(void)
{
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
- pv_cpu_ops.io_delay = kvm_io_delay;
+ pv_ops.cpu.io_delay = kvm_io_delay;
#ifdef CONFIG_X86_IO_APIC
no_timer_check = 1;
@@ -299,8 +324,8 @@
return;
wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
- pr_info("kvm-stealtime: cpu %d, msr %llx\n",
- cpu, (unsigned long long) slow_virt_to_phys(st));
+ pr_info("stealtime: cpu %d, msr %llx\n", cpu,
+ (unsigned long long) slow_virt_to_phys(st));
}
static DEFINE_PER_CPU_DECRYPTED(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED;
@@ -321,28 +346,27 @@
static void kvm_guest_cpu_init(void)
{
- if (!kvm_para_available())
- return;
-
- if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
+ if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) {
u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
-#ifdef CONFIG_PREEMPT
- pa |= KVM_ASYNC_PF_SEND_ALWAYS;
-#endif
- pa |= KVM_ASYNC_PF_ENABLED;
+ WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled));
+
+ pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
+ pa |= KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT;
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
+ wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
+
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
__this_cpu_write(apf_reason.enabled, 1);
- printk(KERN_INFO"KVM setup async PF for cpu %d\n",
- smp_processor_id());
+ pr_info("KVM setup async PF for cpu %d\n", smp_processor_id());
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) {
unsigned long pa;
+
/* Size alignment is implied but just to make it explicit. */
BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
__this_cpu_write(kvm_apic_eoi, 0);
@@ -363,8 +387,15 @@
wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
__this_cpu_write(apf_reason.enabled, 0);
- printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
- smp_processor_id());
+ pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id());
+}
+
+static void kvm_disable_steal_time(void)
+{
+ if (!has_steal_clock)
+ return;
+
+ wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
}
static void kvm_pv_guest_cpu_reboot(void *unused)
@@ -409,14 +440,6 @@
return steal;
}
-void kvm_disable_steal_time(void)
-{
- if (!has_steal_clock)
- return;
-
- wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
-}
-
static inline void __set_percpu_decrypted(void *ptr, unsigned long size)
{
early_set_memory_decrypted((unsigned long) ptr, size);
@@ -444,7 +467,50 @@
}
}
+static bool pv_tlb_flush_supported(void)
+{
+ return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask);
+
+static void kvm_guest_cpu_offline(bool shutdown)
+{
+ kvm_disable_steal_time();
+ if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
+ wrmsrl(MSR_KVM_PV_EOI_EN, 0);
+ kvm_pv_disable_apf();
+ if (!shutdown)
+ apf_task_wake_all();
+ kvmclock_disable();
+}
+
+static int kvm_cpu_online(unsigned int cpu)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ kvm_guest_cpu_init();
+ local_irq_restore(flags);
+ return 0;
+}
+
#ifdef CONFIG_SMP
+
+static bool pv_ipi_supported(void)
+{
+ return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI);
+}
+
+static bool pv_sched_yield_supported(void)
+{
+ return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+}
+
#define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG)
static void __send_ipi_mask(const struct cpumask *mask, int vector)
@@ -480,12 +546,13 @@
} else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) {
ipi_bitmap <<= min - apic_id;
min = apic_id;
- } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
+ } else if (apic_id > min && apic_id < min + KVM_IPI_CLUSTER_SIZE) {
max = apic_id < max ? max : apic_id;
} else {
ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
- WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
+ WARN_ONCE(ret < 0, "kvm-guest: failed to send PV IPI: %ld",
+ ret);
min = max = apic_id;
ipi_bitmap = 0;
}
@@ -495,7 +562,8 @@
if (ipi_bitmap) {
ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
- WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
+ WARN_ONCE(ret < 0, "kvm-guest: failed to send PV IPI: %ld",
+ ret);
}
local_irq_restore(flags);
@@ -509,23 +577,13 @@
static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
{
unsigned int this_cpu = smp_processor_id();
- struct cpumask new_mask;
+ struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
const struct cpumask *local_mask;
- cpumask_copy(&new_mask, mask);
- cpumask_clear_cpu(this_cpu, &new_mask);
- local_mask = &new_mask;
+ cpumask_copy(new_mask, mask);
+ cpumask_clear_cpu(this_cpu, new_mask);
+ local_mask = new_mask;
__send_ipi_mask(local_mask, vector);
-}
-
-static void kvm_send_ipi_allbutself(int vector)
-{
- kvm_send_ipi_mask_allbutself(cpu_online_mask, vector);
-}
-
-static void kvm_send_ipi_all(int vector)
-{
- __send_ipi_mask(cpu_online_mask, vector);
}
/*
@@ -535,16 +593,22 @@
{
apic->send_IPI_mask = kvm_send_ipi_mask;
apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
- apic->send_IPI_allbutself = kvm_send_ipi_allbutself;
- apic->send_IPI_all = kvm_send_ipi_all;
- pr_info("KVM setup pv IPIs\n");
+ pr_info("setup PV IPIs\n");
}
-static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
+static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
{
- native_smp_prepare_cpus(max_cpus);
- if (kvm_para_has_hint(KVM_HINTS_REALTIME))
- static_branch_disable(&virt_spin_lock_key);
+ int cpu;
+
+ native_send_call_func_ipi(mask);
+
+ /* Make sure other vCPUs get a chance to run if they need to. */
+ for_each_cpu(cpu, mask) {
+ if (vcpu_is_preempted(cpu)) {
+ kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu));
+ break;
+ }
+ }
}
static void __init kvm_smp_prepare_boot_cpu(void)
@@ -560,38 +624,60 @@
kvm_spinlock_init();
}
-static void kvm_guest_cpu_offline(void)
-{
- kvm_disable_steal_time();
- if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
- wrmsrl(MSR_KVM_PV_EOI_EN, 0);
- kvm_pv_disable_apf();
- apf_task_wake_all();
-}
-
-static int kvm_cpu_online(unsigned int cpu)
-{
- local_irq_disable();
- kvm_guest_cpu_init();
- local_irq_enable();
- return 0;
-}
-
static int kvm_cpu_down_prepare(unsigned int cpu)
{
- local_irq_disable();
- kvm_guest_cpu_offline();
- local_irq_enable();
+ unsigned long flags;
+
+ local_irq_save(flags);
+ kvm_guest_cpu_offline(false);
+ local_irq_restore(flags);
return 0;
}
+
#endif
-static void __init kvm_apf_trap_init(void)
+static int kvm_suspend(void)
{
- update_intr_gate(X86_TRAP_PF, async_page_fault);
+ u64 val = 0;
+
+ kvm_guest_cpu_offline(false);
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+ if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+ rdmsrl(MSR_KVM_POLL_CONTROL, val);
+ has_guest_poll = !(val & 1);
+#endif
+ return 0;
}
-static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
+static void kvm_resume(void)
+{
+ kvm_cpu_online(raw_smp_processor_id());
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+ if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
+ wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+#endif
+}
+
+static struct syscore_ops kvm_syscore_ops = {
+ .suspend = kvm_suspend,
+ .resume = kvm_resume,
+};
+
+/*
+ * After a PV feature is registered, the host will keep writing to the
+ * registered memory location. If the guest happens to shutdown, this memory
+ * won't be valid. In cases like kexec, in which you install a new kernel, this
+ * means a random memory location will be kept being written.
+ */
+#ifdef CONFIG_KEXEC_CORE
+static void kvm_crash_shutdown(struct pt_regs *regs)
+{
+ kvm_guest_cpu_offline(true);
+ native_machine_crash_shutdown(regs);
+}
+#endif
static void kvm_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
@@ -599,7 +685,7 @@
u8 state;
int cpu;
struct kvm_steal_time *src;
- struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+ struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask);
cpumask_copy(flushmask, cpumask);
/*
@@ -623,41 +709,49 @@
{
int i;
- if (!kvm_para_available())
- return;
-
paravirt_ops_setup();
register_reboot_notifier(&kvm_pv_reboot_nb);
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
raw_spin_lock_init(&async_pf_sleepers[i].lock);
- if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
- x86_init.irqs.trap_init = kvm_apf_trap_init;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
- pv_time_ops.steal_clock = kvm_steal_clock;
+ pv_ops.time.steal_clock = kvm_steal_clock;
}
- if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
- kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
- pv_mmu_ops.tlb_remove_table = tlb_remove_table;
+ if (pv_tlb_flush_supported()) {
+ pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
+ pv_ops.mmu.tlb_remove_table = tlb_remove_table;
+ pr_info("KVM setup pv remote TLB flush\n");
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apic_set_eoi_write(kvm_guest_apic_eoi_write);
+ if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) {
+ static_branch_enable(&kvm_async_pf_enabled);
+ alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_kvm_asyncpf_interrupt);
+ }
+
#ifdef CONFIG_SMP
- smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+ if (pv_sched_yield_supported()) {
+ smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
+ pr_info("setup PV sched yield\n");
+ }
if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
kvm_cpu_online, kvm_cpu_down_prepare) < 0)
- pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
+ pr_err("failed to install cpu hotplug callbacks\n");
#else
sev_map_percpu_data();
kvm_guest_cpu_init();
#endif
+
+#ifdef CONFIG_KEXEC_CORE
+ machine_ops.crash_shutdown = kvm_crash_shutdown;
+#endif
+
+ register_syscore_ops(&kvm_syscore_ops);
/*
* Hard lockup detection is enabled by default. Disable it, as guests
@@ -703,6 +797,7 @@
{
return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES);
}
+EXPORT_SYMBOL_GPL(kvm_arch_para_hints);
static uint32_t __init kvm_detect(void)
{
@@ -712,7 +807,7 @@
static void __init kvm_apic_init(void)
{
#if defined(CONFIG_SMP)
- if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI))
+ if (pv_ipi_supported())
kvm_setup_pv_ipi();
#endif
}
@@ -723,13 +818,34 @@
x86_platform.apic_post_init = kvm_apic_init;
}
+#if defined(CONFIG_AMD_MEM_ENCRYPT)
+static void kvm_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs)
+{
+ /* RAX and CPL are already in the GHCB */
+ ghcb_set_rbx(ghcb, regs->bx);
+ ghcb_set_rcx(ghcb, regs->cx);
+ ghcb_set_rdx(ghcb, regs->dx);
+ ghcb_set_rsi(ghcb, regs->si);
+}
+
+static bool kvm_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs)
+{
+ /* No checking of the return state needed */
+ return true;
+}
+#endif
+
const __initconst struct hypervisor_x86 x86_hyper_kvm = {
- .name = "KVM",
- .detect = kvm_detect,
- .type = X86_HYPER_KVM,
- .init.guest_late_init = kvm_guest_init,
- .init.x2apic_available = kvm_para_available,
- .init.init_platform = kvm_init_platform,
+ .name = "KVM",
+ .detect = kvm_detect,
+ .type = X86_HYPER_KVM,
+ .init.guest_late_init = kvm_guest_init,
+ .init.x2apic_available = kvm_para_available,
+ .init.init_platform = kvm_init_platform,
+#if defined(CONFIG_AMD_MEM_ENCRYPT)
+ .runtime.sev_es_hcall_prepare = kvm_sev_es_hcall_prepare,
+ .runtime.sev_es_hcall_finish = kvm_sev_es_hcall_finish,
+#endif
};
static __init int activate_jump_labels(void)
@@ -744,23 +860,31 @@
}
arch_initcall(activate_jump_labels);
-static __init int kvm_setup_pv_tlb_flush(void)
+static __init int kvm_alloc_cpumask(void)
{
int cpu;
+ bool alloc = false;
- if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
- kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ if (!kvm_para_available() || nopv)
+ return 0;
+
+ if (pv_tlb_flush_supported())
+ alloc = true;
+
+#if defined(CONFIG_SMP)
+ if (pv_ipi_supported())
+ alloc = true;
+#endif
+
+ if (alloc)
for_each_possible_cpu(cpu) {
- zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+ zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
GFP_KERNEL, cpu_to_node(cpu));
}
- pr_info("KVM setup pv remote TLB flush\n");
- }
return 0;
}
-arch_initcall(kvm_setup_pv_tlb_flush);
+arch_initcall(kvm_alloc_cpumask);
#ifdef CONFIG_PARAVIRT_SPINLOCKS
@@ -829,7 +953,7 @@
"movq __per_cpu_offset(,%rdi,8), %rax;"
"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
"setne %al;"
-"ret;"
+ASM_RET
".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
".popsection");
@@ -840,29 +964,91 @@
*/
void __init kvm_spinlock_init(void)
{
- if (!kvm_para_available())
+ /*
+ * In case host doesn't support KVM_FEATURE_PV_UNHALT there is still an
+ * advantage of keeping virt_spin_lock_key enabled: virt_spin_lock() is
+ * preferred over native qspinlock when vCPU is preempted.
+ */
+ if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) {
+ pr_info("PV spinlocks disabled, no host support\n");
return;
- /* Does host kernel support KVM_FEATURE_PV_UNHALT? */
- if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
- return;
+ }
- if (kvm_para_has_hint(KVM_HINTS_REALTIME))
- return;
+ /*
+ * Disable PV spinlocks and use native qspinlock when dedicated pCPUs
+ * are available.
+ */
+ if (kvm_para_has_hint(KVM_HINTS_REALTIME)) {
+ pr_info("PV spinlocks disabled with KVM_HINTS_REALTIME hints\n");
+ goto out;
+ }
- /* Don't use the pvqspinlock code if there is only 1 vCPU. */
- if (num_possible_cpus() == 1)
- return;
+ if (num_possible_cpus() == 1) {
+ pr_info("PV spinlocks disabled, single CPU\n");
+ goto out;
+ }
+
+ if (nopvspin) {
+ pr_info("PV spinlocks disabled, forced by \"nopvspin\" parameter\n");
+ goto out;
+ }
+
+ pr_info("PV spinlocks enabled\n");
__pv_init_lock_hash();
- pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_lock_ops.wait = kvm_wait;
- pv_lock_ops.kick = kvm_kick_cpu;
+ pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops.lock.queued_spin_unlock =
+ PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_ops.lock.wait = kvm_wait;
+ pv_ops.lock.kick = kvm_kick_cpu;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_lock_ops.vcpu_is_preempted =
+ pv_ops.lock.vcpu_is_preempted =
PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
}
+ /*
+ * When PV spinlock is enabled which is preferred over
+ * virt_spin_lock(), virt_spin_lock_key's value is meaningless.
+ * Just disable it anyway.
+ */
+out:
+ static_branch_disable(&virt_spin_lock_key);
}
#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+
+static void kvm_disable_host_haltpoll(void *i)
+{
+ wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+}
+
+static void kvm_enable_host_haltpoll(void *i)
+{
+ wrmsrl(MSR_KVM_POLL_CONTROL, 1);
+}
+
+void arch_haltpoll_enable(unsigned int cpu)
+{
+ if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) {
+ pr_err_once("host does not support poll control\n");
+ pr_err_once("host upgrade recommended\n");
+ return;
+ }
+
+ /* Enable guest halt poll disables host halt poll */
+ smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_enable);
+
+void arch_haltpoll_disable(unsigned int cpu)
+{
+ if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+ return;
+
+ /* Disable guest halt poll enables host halt poll */
+ smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
+#endif
--
Gitblit v1.6.2