- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
the kernel may now execute it. We handle this by also setting spte.nx.
If we get a user fetch or read fault, we'll change spte.u=1 and
- spte.nx=gpte.nx back.
+ spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when
+ shadow paging is in use.
- if CR4.SMAP is disabled: since the page has been changed to a kernel
page, it can not be reused when CR4.SMAP is enabled. We set
CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
write-protected pages
- the guest page must be wholly contained by a single memory slot
- To check the last two conditions, the mmu maintains a ->write_count set of
+ To check the last two conditions, the mmu maintains a ->disallow_lpage set of
arrays for each memory slot and large page size. Every write protected page
- causes its write_count to be incremented, thus preventing instantiation of
+ causes its disallow_lpage to be incremented, thus preventing instantiation of
a large spte. The frames at the end of an unaligned memory slot have
- artificially inflated ->write_counts so they can never be instantiated.
+ artificially inflated ->disallow_lpages so they can never be instantiated.
Zapping all pages (page generation count)
=========================================
#include <linux/sched.h>
#include <linux/kvm.h>
#include <trace/events/kvm.h>
+ #include <kvm/arm_pmu.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
kvm_mmu_free_memory_caches(vcpu);
kvm_timer_vcpu_terminate(vcpu);
kvm_vgic_vcpu_destroy(vcpu);
+ kvm_pmu_vcpu_destroy(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
vcpu->cpu = -1;
kvm_arm_set_running_vcpu(NULL);
+ kvm_timer_vcpu_put(vcpu);
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) {
- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
vcpu->arch.pause = false;
- wake_up_interruptible(wq);
+ swake_up(wq);
}
}
static void vcpu_sleep(struct kvm_vcpu *vcpu)
{
- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
- wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+ swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
(!vcpu->arch.pause)));
}
* non-preemptible context.
*/
preempt_disable();
+ kvm_pmu_flush_hwstate(vcpu);
kvm_timer_flush_hwstate(vcpu);
kvm_vgic_flush_hwstate(vcpu);
if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
vcpu->arch.power_off || vcpu->arch.pause) {
local_irq_enable();
+ kvm_pmu_sync_hwstate(vcpu);
kvm_timer_sync_hwstate(vcpu);
kvm_vgic_sync_hwstate(vcpu);
preempt_enable();
trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
/*
- * We must sync the timer state before the vgic state so that
- * the vgic can properly sample the updated state of the
+ * We must sync the PMU and timer state before the vgic state so
+ * that the vgic can properly sample the updated state of the
* interrupt line.
*/
+ kvm_pmu_sync_hwstate(vcpu);
kvm_timer_sync_hwstate(vcpu);
kvm_vgic_sync_hwstate(vcpu);
return 0;
}
+ static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+ {
+ int ret = -ENXIO;
+
+ switch (attr->group) {
+ default:
+ ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr);
+ break;
+ }
+
+ return ret;
+ }
+
+ static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+ {
+ int ret = -ENXIO;
+
+ switch (attr->group) {
+ default:
+ ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr);
+ break;
+ }
+
+ return ret;
+ }
+
+ static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+ {
+ int ret = -ENXIO;
+
+ switch (attr->group) {
+ default:
+ ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr);
+ break;
+ }
+
+ return ret;
+ }
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
+ struct kvm_device_attr attr;
switch (ioctl) {
case KVM_ARM_VCPU_INIT: {
return -E2BIG;
return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
}
+ case KVM_SET_DEVICE_ATTR: {
+ if (copy_from_user(&attr, argp, sizeof(attr)))
+ return -EFAULT;
+ return kvm_arm_vcpu_set_attr(vcpu, &attr);
+ }
+ case KVM_GET_DEVICE_ATTR: {
+ if (copy_from_user(&attr, argp, sizeof(attr)))
+ return -EFAULT;
+ return kvm_arm_vcpu_get_attr(vcpu, &attr);
+ }
+ case KVM_HAS_DEVICE_ATTR: {
+ if (copy_from_user(&attr, argp, sizeof(attr)))
+ return -EFAULT;
+ return kvm_arm_vcpu_has_attr(vcpu, &attr);
+ }
default:
return -EINVAL;
}
}
}
+ static void cpu_init_stage2(void *dummy)
+ {
+ __cpu_init_stage2();
+ }
+
static void cpu_init_hyp_mode(void *dummy)
{
phys_addr_t boot_pgd_ptr;
vector_ptr = (unsigned long)__kvm_hyp_vector;
__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+ __cpu_init_stage2();
kvm_arm_init_debug();
}
}
#endif
+ static void teardown_common_resources(void)
+ {
+ free_percpu(kvm_host_cpu_state);
+ }
+
+ static int init_common_resources(void)
+ {
+ kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
+ if (!kvm_host_cpu_state) {
+ kvm_err("Cannot allocate host CPU state\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+ }
+
+ static int init_subsystems(void)
+ {
+ int err;
+
+ /*
+ * Init HYP view of VGIC
+ */
+ err = kvm_vgic_hyp_init();
+ switch (err) {
+ case 0:
+ vgic_present = true;
+ break;
+ case -ENODEV:
+ case -ENXIO:
+ vgic_present = false;
+ break;
+ default:
+ return err;
+ }
+
+ /*
+ * Init HYP architected timer support
+ */
+ err = kvm_timer_hyp_init();
+ if (err)
+ return err;
+
+ kvm_perf_init();
+ kvm_coproc_table_init();
+
+ return 0;
+ }
+
+ static void teardown_hyp_mode(void)
+ {
+ int cpu;
+
+ if (is_kernel_in_hyp_mode())
+ return;
+
+ free_hyp_pgds();
+ for_each_possible_cpu(cpu)
+ free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+ }
+
+ static int init_vhe_mode(void)
+ {
+ /*
+ * Execute the init code on each CPU.
+ */
+ on_each_cpu(cpu_init_stage2, NULL, 1);
+
+ /* set size of VMID supported by CPU */
+ kvm_vmid_bits = kvm_get_vmid_bits();
+ kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
+ kvm_info("VHE mode initialized successfully\n");
+ return 0;
+ }
+
/**
* Inits Hyp-mode on all online CPUs
*/
stack_page = __get_free_page(GFP_KERNEL);
if (!stack_page) {
err = -ENOMEM;
- goto out_free_stack_pages;
+ goto out_err;
}
per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
/*
* Map the Hyp-code called directly from the host
*/
- err = create_hyp_mappings(__kvm_hyp_code_start, __kvm_hyp_code_end);
+ err = create_hyp_mappings(__hyp_text_start, __hyp_text_end);
if (err) {
kvm_err("Cannot map world-switch code\n");
- goto out_free_mappings;
+ goto out_err;
}
err = create_hyp_mappings(__start_rodata, __end_rodata);
if (err) {
kvm_err("Cannot map rodata section\n");
- goto out_free_mappings;
+ goto out_err;
}
/*
if (err) {
kvm_err("Cannot map hyp stack\n");
- goto out_free_mappings;
+ goto out_err;
}
}
- /*
- * Map the host CPU structures
- */
- kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
- if (!kvm_host_cpu_state) {
- err = -ENOMEM;
- kvm_err("Cannot allocate host CPU state\n");
- goto out_free_mappings;
- }
-
for_each_possible_cpu(cpu) {
kvm_cpu_context_t *cpu_ctxt;
if (err) {
kvm_err("Cannot map host CPU state: %d\n", err);
- goto out_free_context;
+ goto out_err;
}
}
*/
on_each_cpu(cpu_init_hyp_mode, NULL, 1);
- /*
- * Init HYP view of VGIC
- */
- err = kvm_vgic_hyp_init();
- switch (err) {
- case 0:
- vgic_present = true;
- break;
- case -ENODEV:
- case -ENXIO:
- vgic_present = false;
- break;
- default:
- goto out_free_context;
- }
-
- /*
- * Init HYP architected timer support
- */
- err = kvm_timer_hyp_init();
- if (err)
- goto out_free_context;
-
#ifndef CONFIG_HOTPLUG_CPU
free_boot_hyp_pgd();
#endif
- kvm_perf_init();
+ cpu_notifier_register_begin();
+
+ err = __register_cpu_notifier(&hyp_init_cpu_nb);
+
+ cpu_notifier_register_done();
+
+ if (err) {
+ kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+ goto out_err;
+ }
+
+ hyp_cpu_pm_init();
/* set size of VMID supported by CPU */
kvm_vmid_bits = kvm_get_vmid_bits();
kvm_info("Hyp mode initialized successfully\n");
return 0;
- out_free_context:
- free_percpu(kvm_host_cpu_state);
- out_free_mappings:
- free_hyp_pgds();
- out_free_stack_pages:
- for_each_possible_cpu(cpu)
- free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+
out_err:
+ teardown_hyp_mode();
kvm_err("error initializing Hyp mode: %d\n", err);
return err;
}
}
}
- cpu_notifier_register_begin();
-
- err = init_hyp_mode();
+ err = init_common_resources();
if (err)
- goto out_err;
+ return err;
- err = __register_cpu_notifier(&hyp_init_cpu_nb);
- if (err) {
- kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+ if (is_kernel_in_hyp_mode())
+ err = init_vhe_mode();
+ else
+ err = init_hyp_mode();
+ if (err)
goto out_err;
- }
-
- cpu_notifier_register_done();
- hyp_cpu_pm_init();
+ err = init_subsystems();
+ if (err)
+ goto out_hyp;
- kvm_coproc_table_init();
return 0;
+
+ out_hyp:
+ teardown_hyp_mode();
out_err:
- cpu_notifier_register_done();
+ teardown_common_resources();
return err;
}
#include <asm/cputype.h>
#include <asm/uaccess.h>
#include <asm/kvm.h>
- #include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
u32 __user *uaddr = (u32 __user *)(long)reg->addr;
- struct kvm_regs *regs = &vcpu->arch.regs;
+ struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs;
u64 off;
if (KVM_REG_SIZE(reg->id) != 4)
static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
u32 __user *uaddr = (u32 __user *)(long)reg->addr;
- struct kvm_regs *regs = &vcpu->arch.regs;
+ struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs;
u64 off, val;
if (KVM_REG_SIZE(reg->id) != 4)
u64 val;
val = kvm_arm_timer_get_reg(vcpu, reg->id);
- return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
}
static unsigned long num_core_regs(void)
u64 val;
val = kvm_arm_timer_get_reg(vcpu, reg->id);
- return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
}
/**
}
return 0;
}
+
+ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+ {
+ int ret;
+
+ switch (attr->group) {
+ case KVM_ARM_VCPU_PMU_V3_CTRL:
+ ret = kvm_arm_pmu_v3_set_attr(vcpu, attr);
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+
+ return ret;
+ }
+
+ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+ {
+ int ret;
+
+ switch (attr->group) {
+ case KVM_ARM_VCPU_PMU_V3_CTRL:
+ ret = kvm_arm_pmu_v3_get_attr(vcpu, attr);
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+
+ return ret;
+ }
+
+ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+ struct kvm_device_attr *attr)
+ {
+ int ret;
+
+ switch (attr->group) {
+ case KVM_ARM_VCPU_PMU_V3_CTRL:
+ ret = kvm_arm_pmu_v3_has_attr(vcpu, attr);
+ break;
+ default:
+ ret = -ENXIO;
+ break;
+ }
+
+ return ret;
+ }
struct list_head list;
struct kvm *kvm;
u64 liobn;
- u32 window_size;
+ struct rcu_head rcu;
+ u32 page_shift;
+ u64 offset; /* in pages */
+ u64 size; /* window size in pages */
struct page *pages[0];
};
struct list_head runnable_threads;
struct list_head preempt_list;
spinlock_t lock;
- wait_queue_head_t wq;
+ struct swait_queue_head wq;
spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */
u64 stolen_tb;
u64 preempt_tb;
u8 prodded;
u32 last_inst;
- wait_queue_head_t *wqp;
+ struct swait_queue_head *wqp;
struct kvmppc_vcore *vcore;
int ret;
int trap;
#ifdef CONFIG_PPC_SMP_MUXED_IPI
struct cpu_messages {
- int messages; /* current messages */
+ long messages; /* current messages */
unsigned long data; /* data for cause ipi */
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);
info->data = data;
}
- void smp_muxed_ipi_message_pass(int cpu, int msg)
+ void smp_muxed_ipi_set_message(int cpu, int msg)
{
struct cpu_messages *info = &per_cpu(ipi_message, cpu);
char *message = (char *)&info->messages;
*/
smp_mb();
message[msg] = 1;
+ }
+
+ void smp_muxed_ipi_message_pass(int cpu, int msg)
+ {
+ struct cpu_messages *info = &per_cpu(ipi_message, cpu);
+
+ smp_muxed_ipi_set_message(cpu, msg);
/*
* cause_ipi functions are required to include a full barrier
* before doing whatever causes the IPI.
}
#ifdef __BIG_ENDIAN__
- #define IPI_MESSAGE(A) (1 << (24 - 8 * (A)))
+ #define IPI_MESSAGE(A) (1uL << ((BITS_PER_LONG - 8) - 8 * (A)))
#else
- #define IPI_MESSAGE(A) (1 << (8 * (A)))
+ #define IPI_MESSAGE(A) (1uL << (8 * (A)))
#endif
irqreturn_t smp_ipi_demux(void)
{
struct cpu_messages *info = this_cpu_ptr(&ipi_message);
- unsigned int all;
+ unsigned long all;
mb(); /* order any irq clear */
do {
all = xchg(&info->messages, 0);
+ #if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+ /*
+ * Must check for PPC_MSG_RM_HOST_ACTION messages
+ * before PPC_MSG_CALL_FUNCTION messages because when
+ * a VM is destroyed, we call kick_all_cpus_sync()
+ * to ensure that any pending PPC_MSG_RM_HOST_ACTION
+ * messages have completed before we free any VCPUs.
+ */
+ if (all & IPI_MESSAGE(PPC_MSG_RM_HOST_ACTION))
+ kvmppc_xics_ipi_action();
+ #endif
if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION))
generic_smp_call_function_interrupt();
if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
local_irq_enable();
- cpu_startup_entry(CPUHP_ONLINE);
+ cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
BUG();
}
module_param(target_smt_mode, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
+ #ifdef CONFIG_KVM_XICS
+ static struct kernel_param_ops module_param_ops = {
+ .set = param_set_int,
+ .get = param_get_int,
+ };
+
+ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
+ S_IRUGO | S_IWUSR);
+ MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
+ #endif
+
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
int cpu;
- wait_queue_head_t *wqp;
+ struct swait_queue_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swait_active(wqp)) {
+ swake_up(wqp);
++vcpu->stat.halt_wakeup;
}
tvcpu->arch.prodded = 1;
smp_mb();
if (vcpu->arch.ceded) {
- if (waitqueue_active(&vcpu->wq)) {
- wake_up_interruptible(&vcpu->wq);
+ if (swait_active(&vcpu->wq)) {
+ swake_up(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
if (kvmppc_xics_enabled(vcpu)) {
ret = kvmppc_xics_hcall(vcpu, req);
break;
- } /* fallthrough */
+ }
+ return RESUME_HOST;
+ case H_PUT_TCE:
+ ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_PUT_TCE_INDIRECT:
+ ret = kvmppc_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_STUFF_TCE:
+ ret = kvmppc_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
default:
return RESUME_HOST;
}
INIT_LIST_HEAD(&vcore->runnable_threads);
spin_lock_init(&vcore->lock);
spin_lock_init(&vcore->stoltb_lock);
- init_waitqueue_head(&vcore->wq);
+ init_swait_queue_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
vcore->first_vcpuid = core * threads_per_subcore;
spin_unlock(&vc->lock);
}
+ /*
+ * Clear core from the list of active host cores as we are about to
+ * enter the guest. Only do this if it is the primary thread of the
+ * core (not if a subcore) that is entering the guest.
+ */
+ static inline void kvmppc_clear_host_core(int cpu)
+ {
+ int core;
+
+ if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
+ return;
+ /*
+ * Memory barrier can be omitted here as we will do a smp_wmb()
+ * later in kvmppc_start_thread and we need ensure that state is
+ * visible to other CPUs only after we enter guest.
+ */
+ core = cpu >> threads_shift;
+ kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
+ }
+
+ /*
+ * Advertise this core as an active host core since we exited the guest
+ * Only need to do this if it is the primary thread of the core that is
+ * exiting.
+ */
+ static inline void kvmppc_set_host_core(int cpu)
+ {
+ int core;
+
+ if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
+ return;
+
+ /*
+ * Memory barrier can be omitted here because we do a spin_unlock
+ * immediately after this which provides the memory barrier.
+ */
+ core = cpu >> threads_shift;
+ kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
+ }
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
}
}
+ kvmppc_clear_host_core(pcpu);
+
/* Start all the threads */
active = 0;
for (sub = 0; sub < core_info.n_subcores; ++sub) {
kvmppc_ipi_thread(pcpu + i);
}
+ kvmppc_set_host_core(pcpu);
+
spin_unlock(&vc->lock);
/* make sure updates to secondary vcpu structs are visible now */
{
struct kvm_vcpu *vcpu;
int do_sleep = 1;
+ DECLARE_SWAITQUEUE(wait);
- DEFINE_WAIT(wait);
-
- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
/*
* Check one last time for pending exceptions and ceded state after
}
if (!do_sleep) {
- finish_wait(&vc->wq, &wait);
+ finish_swait(&vc->wq, &wait);
return;
}
trace_kvmppc_vcore_blocked(vc, 0);
spin_unlock(&vc->lock);
schedule();
- finish_wait(&vc->wq, &wait);
+ finish_swait(&vc->wq, &wait);
spin_lock(&vc->lock);
vc->vcore_state = VCORE_INACTIVE;
trace_kvmppc_vcore_blocked(vc, 1);
kvmppc_start_thread(vcpu, vc);
trace_kvm_guest_enter(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
- wake_up(&vc->wq);
+ swake_up(&vc->wq);
}
}
goto out_srcu;
}
+ #ifdef CONFIG_KVM_XICS
+ static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long action,
+ void *hcpu)
+ {
+ unsigned long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ kvmppc_set_host_core(cpu);
+ break;
+
+ #ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
+ kvmppc_clear_host_core(cpu);
+ break;
+ #endif
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+ }
+
+ static struct notifier_block kvmppc_cpu_notifier = {
+ .notifier_call = kvmppc_cpu_notify,
+ };
+
+ /*
+ * Allocate a per-core structure for managing state about which cores are
+ * running in the host versus the guest and for exchanging data between
+ * real mode KVM and CPU running in the host.
+ * This is only done for the first VM.
+ * The allocated structure stays even if all VMs have stopped.
+ * It is only freed when the kvm-hv module is unloaded.
+ * It's OK for this routine to fail, we just don't support host
+ * core operations like redirecting H_IPI wakeups.
+ */
+ void kvmppc_alloc_host_rm_ops(void)
+ {
+ struct kvmppc_host_rm_ops *ops;
+ unsigned long l_ops;
+ int cpu, core;
+ int size;
+
+ /* Not the first time here ? */
+ if (kvmppc_host_rm_ops_hv != NULL)
+ return;
+
+ ops = kzalloc(sizeof(struct kvmppc_host_rm_ops), GFP_KERNEL);
+ if (!ops)
+ return;
+
+ size = cpu_nr_cores() * sizeof(struct kvmppc_host_rm_core);
+ ops->rm_core = kzalloc(size, GFP_KERNEL);
+
+ if (!ops->rm_core) {
+ kfree(ops);
+ return;
+ }
+
+ get_online_cpus();
+
+ for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
+ if (!cpu_online(cpu))
+ continue;
+
+ core = cpu >> threads_shift;
+ ops->rm_core[core].rm_state.in_host = 1;
+ }
+
+ ops->vcpu_kick = kvmppc_fast_vcpu_kick_hv;
+
+ /*
+ * Make the contents of the kvmppc_host_rm_ops structure visible
+ * to other CPUs before we assign it to the global variable.
+ * Do an atomic assignment (no locks used here), but if someone
+ * beats us to it, just free our copy and return.
+ */
+ smp_wmb();
+ l_ops = (unsigned long) ops;
+
+ if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
+ put_online_cpus();
+ kfree(ops->rm_core);
+ kfree(ops);
+ return;
+ }
+
+ register_cpu_notifier(&kvmppc_cpu_notifier);
+
+ put_online_cpus();
+ }
+
+ void kvmppc_free_host_rm_ops(void)
+ {
+ if (kvmppc_host_rm_ops_hv) {
+ unregister_cpu_notifier(&kvmppc_cpu_notifier);
+ kfree(kvmppc_host_rm_ops_hv->rm_core);
+ kfree(kvmppc_host_rm_ops_hv);
+ kvmppc_host_rm_ops_hv = NULL;
+ }
+ }
+ #endif
+
static int kvmppc_core_init_vm_hv(struct kvm *kvm)
{
unsigned long lpcr, lpid;
return -ENOMEM;
kvm->arch.lpid = lpid;
+ kvmppc_alloc_host_rm_ops();
+
/*
* Since we don't flush the TLB when tearing down a VM,
* and this lpid might have previously been used,
static void kvmppc_book3s_exit_hv(void)
{
+ kvmppc_free_host_rm_ops();
kvmppc_hv_ops = NULL;
}
std r6, VCPU_ACOP(r9)
stw r7, VCPU_GUEST_PID(r9)
std r8, VCPU_WORT(r9)
+ /*
+ * Restore various registers to 0, where non-zero values
+ * set by the guest could disrupt the host.
+ */
+ li r0, 0
+ mtspr SPRN_IAMR, r0
+ mtspr SPRN_CIABR, r0
+ mtspr SPRN_DAWRX, r0
+ mtspr SPRN_TCSCR, r0
+ mtspr SPRN_WORT, r0
+ /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
+ li r0, 1
+ sldi r0, r0, 31
+ mtspr SPRN_MMCRS, r0
8:
/* Save and reset AMR and UAMOR before turning on the MMU */
.long 0 /* 0x12c */
.long 0 /* 0x130 */
.long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
- .long 0 /* 0x138 */
- .long 0 /* 0x13c */
+ .long DOTSYM(kvmppc_h_stuff_tce) - hcall_real_table
+ .long DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table
.long 0 /* 0x140 */
.long 0 /* 0x144 */
.long 0 /* 0x148 */
#include <linux/kvm_types.h>
#include <linux/kvm_host.h>
#include <linux/kvm.h>
+ #include <linux/seqlock.h>
#include <asm/debug.h>
#include <asm/cpu.h>
#include <asm/fpu/api.h>
__u8 data[256];
} __packed;
- struct kvm_s390_vregs {
- __vector128 vrs[32];
- __u8 reserved200[512]; /* for future vector expansion */
- } __packed;
-
struct sie_page {
struct kvm_s390_sie_block sie_block;
__u8 reserved200[1024]; /* 0x0200 */
struct kvm_s390_itdb itdb; /* 0x0600 */
- __u8 reserved700[1280]; /* 0x0700 */
- struct kvm_s390_vregs vregs; /* 0x0c00 */
+ __u8 reserved700[2304]; /* 0x0700 */
} __packed;
struct kvm_vcpu_stat {
struct kvm_s390_local_interrupt {
spinlock_t lock;
struct kvm_s390_float_interrupt *float_int;
- wait_queue_head_t *wq;
+ struct swait_queue_head *wq;
atomic_t *cpuflags;
DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
struct kvm_s390_irq_payload irq;
unsigned long pfault_token;
unsigned long pfault_select;
unsigned long pfault_compare;
+ bool cputm_enabled;
+ /*
+ * The seqcount protects updates to cputm_start and sie_block.cputm,
+ * this way we can have non-blocking reads with consistent values.
+ * Only the owning VCPU thread (vcpu->cpu) is allowed to change these
+ * values and to start/stop/enable/disable cpu timer accounting.
+ */
+ seqcount_t cputm_seqcount;
+ __u64 cputm_start;
};
struct kvm_vm_stat {
#define S390_ARCH_FAC_MASK_SIZE_U64 \
(S390_ARCH_FAC_MASK_SIZE_BYTE / sizeof(u64))
- struct kvm_s390_fac {
- /* facility list requested by guest */
- __u64 list[S390_ARCH_FAC_LIST_SIZE_U64];
- /* facility mask supported by kvm & hosting machine */
- __u64 mask[S390_ARCH_FAC_LIST_SIZE_U64];
- };
-
struct kvm_s390_cpu_model {
- struct kvm_s390_fac *fac;
+ /* facility mask supported by kvm & hosting machine */
+ __u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64];
+ /* facility list requested by guest (in dma page) */
+ __u64 *fac_list;
struct cpuid cpu_id;
unsigned short ibc;
};
__u8 reserved80[128]; /* 0x0080 */
};
+ /*
+ * sie_page2 has to be allocated as DMA because fac_list and crycb need
+ * 31bit addresses in the sie control block.
+ */
+ struct sie_page2 {
+ __u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */
+ struct kvm_s390_crypto_cb crycb; /* 0x0800 */
+ u8 reserved900[0x1000 - 0x900]; /* 0x0900 */
+ } __packed;
+
struct kvm_arch{
void *sca;
int use_esca;
int ipte_lock_count;
struct mutex ipte_mutex;
spinlock_t start_stop_lock;
+ struct sie_page2 *sie_page2;
struct kvm_s390_cpu_model model;
struct kvm_s390_crypto crypto;
u64 epoch;
static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
{
- return (vcpu->arch.sie_block->cputm >> 63) &&
- cpu_timer_interrupts_enabled(vcpu);
+ if (!cpu_timer_interrupts_enabled(vcpu))
+ return 0;
+ return kvm_s390_get_cpu_timer(vcpu) >> 63;
}
static inline int is_ioirq(unsigned long irq_type)
set_intercept_indicators_stop(vcpu);
}
- static u16 get_ilc(struct kvm_vcpu *vcpu)
- {
- switch (vcpu->arch.sie_block->icptcode) {
- case ICPT_INST:
- case ICPT_INSTPROGI:
- case ICPT_OPEREXC:
- case ICPT_PARTEXEC:
- case ICPT_IOINST:
- /* last instruction only stored for these icptcodes */
- return insn_length(vcpu->arch.sie_block->ipa >> 8);
- case ICPT_PROGI:
- return vcpu->arch.sie_block->pgmilc;
- default:
- return 0;
- }
- }
-
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_pgm_info pgm_info;
int rc = 0, nullifying = false;
- u16 ilc = get_ilc(vcpu);
+ u16 ilen;
spin_lock(&li->lock);
pgm_info = li->irq.pgm;
memset(&li->irq.pgm, 0, sizeof(pgm_info));
spin_unlock(&li->lock);
- VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
- pgm_info.code, ilc);
+ ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
+ VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
+ pgm_info.code, ilen);
vcpu->stat.deliver_program_int++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info.code, 0);
(u8 *) __LC_PER_ACCESS_ID);
}
- if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
- kvm_s390_rewind_psw(vcpu, ilc);
+ if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND))
+ kvm_s390_rewind_psw(vcpu, ilen);
- rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
+ /* bit 1+2 of the target are the ilc, so we can directly use ilen */
+ rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
(u64 *) __LC_LAST_BREAK);
rc |= put_guest_lc(vcpu, pgm_info.code,
return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
}
+ static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
+ {
+ u64 now, cputm, sltime = 0;
+
+ if (ckc_interrupts_enabled(vcpu)) {
+ now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+ sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+ /* already expired or overflow? */
+ if (!sltime || vcpu->arch.sie_block->ckc <= now)
+ return 0;
+ if (cpu_timer_interrupts_enabled(vcpu)) {
+ cputm = kvm_s390_get_cpu_timer(vcpu);
+ /* already expired? */
+ if (cputm >> 63)
+ return 0;
+ return min(sltime, tod_to_ns(cputm));
+ }
+ } else if (cpu_timer_interrupts_enabled(vcpu)) {
+ sltime = kvm_s390_get_cpu_timer(vcpu);
+ /* already expired? */
+ if (sltime >> 63)
+ return 0;
+ }
+ return sltime;
+ }
+
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
- u64 now, sltime;
+ u64 sltime;
vcpu->stat.exit_wait_state++;
return -EOPNOTSUPP; /* disabled wait */
}
- if (!ckc_interrupts_enabled(vcpu)) {
+ if (!ckc_interrupts_enabled(vcpu) &&
+ !cpu_timer_interrupts_enabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
__set_cpu_idle(vcpu);
goto no_timer;
}
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-
- /* underflow */
- if (vcpu->arch.sie_block->ckc < now)
+ sltime = __calculate_sltime(vcpu);
+ if (!sltime)
return 0;
__set_cpu_idle(vcpu);
hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
- VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
+ VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
no_timer:
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
kvm_vcpu_block(vcpu);
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
- if (waitqueue_active(&vcpu->wq)) {
+ if (swait_active(&vcpu->wq)) {
/*
* The vcpu gave up the cpu voluntarily, mark it as a good
* yield-candidate.
*/
vcpu->preempted = true;
- wake_up_interruptible(&vcpu->wq);
+ swake_up(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
struct kvm_vcpu *vcpu;
- u64 now, sltime;
+ u64 sltime;
vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+ sltime = __calculate_sltime(vcpu);
/*
* If the monotonic clock runs faster than the tod clock we might be
* woken up too early and have to go back to sleep to avoid deadlocks.
*/
- if (vcpu->arch.sie_block->ckc > now &&
- hrtimer_forward_now(timer, ns_to_ktime(sltime)))
+ if (sltime && hrtimer_forward_now(timer, ns_to_ktime(sltime)))
return HRTIMER_RESTART;
kvm_s390_vcpu_wakeup(vcpu);
return HRTIMER_NORESTART;
trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
irq->u.pgm.code, 0);
+ if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) {
+ /* auto detection if no valid ILC was given */
+ irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK;
+ irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu);
+ irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID;
+ }
+
if (irq->u.pgm.code == PGM_PER) {
li->irq.pgm.code |= PGM_PER;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify PER related information */
li->irq.pgm.per_address = irq->u.pgm.per_address;
li->irq.pgm.per_code = irq->u.pgm.per_code;
} else if (!(irq->u.pgm.code & PGM_PER)) {
li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) |
irq->u.pgm.code;
+ li->irq.pgm.flags = irq->u.pgm.flags;
/* only modify non-PER information */
li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code;
li->irq.pgm.mon_code = irq->u.pgm.mon_code;
kvm->arch.epoch -= *delta;
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.sie_block->epoch -= *delta;
+ if (vcpu->arch.cputm_enabled)
+ vcpu->arch.cputm_start += *delta;
}
}
return NOTIFY_OK;
unsigned long address;
struct gmap *gmap = kvm->arch.gmap;
- down_read(&gmap->mm->mmap_sem);
/* Loop over all guest pages */
last_gfn = memslot->base_gfn + memslot->npages;
for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
if (gmap_test_and_clear_dirty(address, gmap))
mark_page_dirty(kvm, cur_gfn);
+ if (fatal_signal_pending(current))
+ return;
+ cond_resched();
}
- up_read(&gmap->mm->mmap_sem);
}
/* Section: vm related */
if (atomic_read(&kvm->online_vcpus)) {
r = -EBUSY;
} else if (MACHINE_HAS_VX) {
- set_kvm_facility(kvm->arch.model.fac->mask, 129);
- set_kvm_facility(kvm->arch.model.fac->list, 129);
+ set_kvm_facility(kvm->arch.model.fac_mask, 129);
+ set_kvm_facility(kvm->arch.model.fac_list, 129);
r = 0;
} else
r = -EINVAL;
if (atomic_read(&kvm->online_vcpus)) {
r = -EBUSY;
} else if (test_facility(64)) {
- set_kvm_facility(kvm->arch.model.fac->mask, 64);
- set_kvm_facility(kvm->arch.model.fac->list, 64);
+ set_kvm_facility(kvm->arch.model.fac_mask, 64);
+ set_kvm_facility(kvm->arch.model.fac_list, 64);
r = 0;
}
mutex_unlock(&kvm->lock);
memcpy(&kvm->arch.model.cpu_id, &proc->cpuid,
sizeof(struct cpuid));
kvm->arch.model.ibc = proc->ibc;
- memcpy(kvm->arch.model.fac->list, proc->fac_list,
+ memcpy(kvm->arch.model.fac_list, proc->fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
} else
ret = -EFAULT;
}
memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid));
proc->ibc = kvm->arch.model.ibc;
- memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE);
+ memcpy(&proc->fac_list, kvm->arch.model.fac_list,
+ S390_ARCH_FAC_LIST_SIZE_BYTE);
if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
ret = -EFAULT;
kfree(proc);
}
get_cpu_id((struct cpuid *) &mach->cpuid);
mach->ibc = sclp.ibc;
- memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
+ memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
cpu_id->version = 0xff;
}
- static int kvm_s390_crypto_init(struct kvm *kvm)
+ static void kvm_s390_crypto_init(struct kvm *kvm)
{
if (!test_kvm_facility(kvm, 76))
- return 0;
-
- kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb),
- GFP_KERNEL | GFP_DMA);
- if (!kvm->arch.crypto.crycb)
- return -ENOMEM;
+ return;
+ kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
kvm_s390_set_crycb_format(kvm);
/* Enable AES/DEA protected key functions by default */
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
-
- return 0;
}
static void sca_dispose(struct kvm *kvm)
if (!kvm->arch.dbf)
goto out_err;
- /*
- * The architectural maximum amount of facilities is 16 kbit. To store
- * this amount, 2 kbyte of memory is required. Thus we need a full
- * page to hold the guest facility list (arch.model.fac->list) and the
- * facility mask (arch.model.fac->mask). Its address size has to be
- * 31 bits and word aligned.
- */
- kvm->arch.model.fac =
- (struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
- if (!kvm->arch.model.fac)
+ kvm->arch.sie_page2 =
+ (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+ if (!kvm->arch.sie_page2)
goto out_err;
/* Populate the facility mask initially. */
- memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
+ memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
if (i < kvm_s390_fac_list_mask_size())
- kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i];
+ kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
else
- kvm->arch.model.fac->mask[i] = 0UL;
+ kvm->arch.model.fac_mask[i] = 0UL;
}
/* Populate the facility list initially. */
- memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask,
+ kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
+ memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
kvm->arch.model.ibc = sclp.ibc & 0x0fff;
- if (kvm_s390_crypto_init(kvm) < 0)
- goto out_err;
+ kvm_s390_crypto_init(kvm);
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
return 0;
out_err:
- kfree(kvm->arch.crypto.crycb);
- free_page((unsigned long)kvm->arch.model.fac);
+ free_page((unsigned long)kvm->arch.sie_page2);
debug_unregister(kvm->arch.dbf);
sca_dispose(kvm);
KVM_EVENT(3, "creation of vm failed: %d", rc);
void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_free_vcpus(kvm);
- free_page((unsigned long)kvm->arch.model.fac);
sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
- kfree(kvm->arch.crypto.crycb);
+ free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
gmap_free(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
KVM_SYNC_PFAULT;
if (test_kvm_facility(vcpu->kvm, 64))
vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
- if (test_kvm_facility(vcpu->kvm, 129))
+ /* fprs can be synchronized via vrs, even if the guest has no vx. With
+ * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+ */
+ if (MACHINE_HAS_VX)
vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+ else
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
if (kvm_is_ucontrol(vcpu->kvm))
return __kvm_ucontrol_vcpu_init(vcpu);
return 0;
}
+ /* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+ static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+ {
+ WARN_ON_ONCE(vcpu->arch.cputm_start != 0);
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ vcpu->arch.cputm_start = get_tod_clock_fast();
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+ }
+
+ /* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+ static void __stop_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+ {
+ WARN_ON_ONCE(vcpu->arch.cputm_start == 0);
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ vcpu->arch.sie_block->cputm -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+ vcpu->arch.cputm_start = 0;
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+ }
+
+ /* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+ static void __enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+ {
+ WARN_ON_ONCE(vcpu->arch.cputm_enabled);
+ vcpu->arch.cputm_enabled = true;
+ __start_cpu_timer_accounting(vcpu);
+ }
+
+ /* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+ static void __disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+ {
+ WARN_ON_ONCE(!vcpu->arch.cputm_enabled);
+ __stop_cpu_timer_accounting(vcpu);
+ vcpu->arch.cputm_enabled = false;
+ }
+
+ static void enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+ {
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ __enable_cpu_timer_accounting(vcpu);
+ preempt_enable();
+ }
+
+ static void disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+ {
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ __disable_cpu_timer_accounting(vcpu);
+ preempt_enable();
+ }
+
+ /* set the cpu timer - may only be called from the VCPU thread itself */
+ void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm)
+ {
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+ if (vcpu->arch.cputm_enabled)
+ vcpu->arch.cputm_start = get_tod_clock_fast();
+ vcpu->arch.sie_block->cputm = cputm;
+ raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+ preempt_enable();
+ }
+
+ /* update and get the cpu timer - can also be called from other VCPU threads */
+ __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
+ {
+ unsigned int seq;
+ __u64 value;
+
+ if (unlikely(!vcpu->arch.cputm_enabled))
+ return vcpu->arch.sie_block->cputm;
+
+ preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+ do {
+ seq = raw_read_seqcount(&vcpu->arch.cputm_seqcount);
+ /*
+ * If the writer would ever execute a read in the critical
+ * section, e.g. in irq context, we have a deadlock.
+ */
+ WARN_ON_ONCE((seq & 1) && smp_processor_id() == vcpu->cpu);
+ value = vcpu->arch.sie_block->cputm;
+ /* if cputm_start is 0, accounting is being started/stopped */
+ if (likely(vcpu->arch.cputm_start))
+ value -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+ } while (read_seqcount_retry(&vcpu->arch.cputm_seqcount, seq & ~1));
+ preempt_enable();
+ return value;
+ }
+
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
/* Save host register state */
vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
- /* Depending on MACHINE_HAS_VX, data stored to vrs either
- * has vector register or floating point register format.
- */
- current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+ if (MACHINE_HAS_VX)
+ current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+ else
+ current->thread.fpu.regs = vcpu->run->s.regs.fprs;
current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
if (test_fp_ctl(current->thread.fpu.fpc))
/* User space provided an invalid FPC, let's clear it */
restore_access_regs(vcpu->run->s.regs.acrs);
gmap_enable(vcpu->arch.gmap);
atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+ __start_cpu_timer_accounting(vcpu);
+ vcpu->cpu = cpu;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ vcpu->cpu = -1;
+ if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+ __stop_cpu_timer_accounting(vcpu);
atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
gmap_disable(vcpu->arch.gmap);
vcpu->arch.sie_block->gpsw.mask = 0UL;
vcpu->arch.sie_block->gpsw.addr = 0UL;
kvm_s390_set_prefix(vcpu, 0);
- vcpu->arch.sie_block->cputm = 0UL;
+ kvm_s390_set_cpu_timer(vcpu, 0);
vcpu->arch.sie_block->ckc = 0UL;
vcpu->arch.sie_block->todpr = 0;
memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
vcpu->arch.cpu_id = model->cpu_id;
vcpu->arch.sie_block->ibc = model->ibc;
- vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
+ if (test_kvm_facility(vcpu->kvm, 7))
+ vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
}
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
vcpu->arch.local_int.wq = &vcpu->wq;
vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+ seqcount_init(&vcpu->arch.cputm_seqcount);
rc = kvm_vcpu_init(vcpu, kvm, id);
if (rc)
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CPU_TIMER:
- r = put_user(vcpu->arch.sie_block->cputm,
+ r = put_user(kvm_s390_get_cpu_timer(vcpu),
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CLOCK_COMP:
struct kvm_one_reg *reg)
{
int r = -EINVAL;
+ __u64 val;
switch (reg->id) {
case KVM_REG_S390_TODPR:
(u64 __user *)reg->addr);
break;
case KVM_REG_S390_CPU_TIMER:
- r = get_user(vcpu->arch.sie_block->cputm,
- (u64 __user *)reg->addr);
+ r = get_user(val, (u64 __user *)reg->addr);
+ if (!r)
+ kvm_s390_set_cpu_timer(vcpu, val);
break;
case KVM_REG_S390_CLOCK_COMP:
r = get_user(vcpu->arch.sie_block->ckc,
static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
{
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
- u8 opcode;
+ struct kvm_s390_pgm_info pgm_info = {
+ .code = PGM_ADDRESSING,
+ };
+ u8 opcode, ilen;
int rc;
VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
* to look up the current opcode to get the length of the instruction
* to be able to forward the PSW.
*/
- rc = read_guest(vcpu, psw->addr, 0, &opcode, 1);
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- psw->addr = __rewind_psw(*psw, -insn_length(opcode));
-
- return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ rc = read_guest_instr(vcpu, &opcode, 1);
+ ilen = insn_length(opcode);
+ if (rc < 0) {
+ return rc;
+ } else if (rc) {
+ /* Instruction-Fetching Exceptions - we can't detect the ilen.
+ * Forward by arbitrary ilc, injection will take care of
+ * nullification if necessary.
+ */
+ pgm_info = vcpu->arch.pgm;
+ ilen = 4;
+ }
+ pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID;
+ kvm_s390_forward_psw(vcpu, ilen);
+ return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
*/
local_irq_disable();
__kvm_guest_enter();
+ __disable_cpu_timer_accounting(vcpu);
local_irq_enable();
exit_reason = sie64a(vcpu->arch.sie_block,
vcpu->run->s.regs.gprs);
local_irq_disable();
+ __enable_cpu_timer_accounting(vcpu);
__kvm_guest_exit();
local_irq_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
- vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm;
+ kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
- kvm_run->s.regs.cputm = vcpu->arch.sie_block->cputm;
+ kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
}
sync_regs(vcpu, kvm_run);
+ enable_cpu_timer_accounting(vcpu);
might_fault();
rc = __vcpu_run(vcpu);
rc = 0;
}
+ disable_cpu_timer_accounting(vcpu);
store_regs(vcpu, kvm_run);
if (vcpu->sigset_active)
unsigned char archmode = 1;
freg_t fprs[NUM_FPRS];
unsigned int px;
- u64 clkcomp;
+ u64 clkcomp, cputm;
int rc;
px = kvm_s390_get_prefix(vcpu);
/* manually convert vector registers if necessary */
if (MACHINE_HAS_VX) {
- convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
fprs, 128);
} else {
rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
- vcpu->run->s.regs.vrs, 128);
+ vcpu->run->s.regs.fprs, 128);
}
rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
vcpu->run->s.regs.gprs, 128);
&vcpu->run->s.regs.fpc, 4);
rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
&vcpu->arch.sie_block->todpr, 4);
+ cputm = kvm_s390_get_cpu_timer(vcpu);
rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
- &vcpu->arch.sie_block->cputm, 8);
+ &cputm, 8);
clkcomp = vcpu->arch.sie_block->ckc >> 8;
rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
&clkcomp, 8);
switch (mop->op) {
case KVM_S390_MEMOP_LOGICAL_READ:
if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+ mop->size, GACC_FETCH);
break;
}
r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
break;
case KVM_S390_MEMOP_LOGICAL_WRITE:
if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+ mop->size, GACC_STORE);
break;
}
if (copy_from_user(tmpbuf, uaddr, mop->size)) {
struct kvm_cpuid_entry2 *feat;
u32 v = APIC_VERSION;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return;
feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
{
- int highest_irr;
-
/* This may race with setting of irr in __apic_accept_irq() and
* value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq
* will cause vmexit immediately and the value will be recalculated
* on the next vmentry.
*/
- if (!kvm_vcpu_has_lapic(vcpu))
- return 0;
- highest_irr = apic_find_highest_irr(vcpu->arch.apic);
-
- return highest_irr;
+ return apic_find_highest_irr(vcpu->arch.apic);
}
static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
int vector, int level, int trig_mode,
- unsigned long *dest_map);
+ struct dest_map *dest_map);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
- unsigned long *dest_map)
+ struct dest_map *dest_map)
{
struct kvm_lapic *apic = vcpu->arch.apic;
}
}
+ int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
+ const unsigned long *bitmap, u32 bitmap_size)
+ {
+ u32 mod;
+ int i, idx = -1;
+
+ mod = vector % dest_vcpus;
+
+ for (i = 0; i <= mod; i++) {
+ idx = find_next_bit(bitmap, bitmap_size, idx + 1);
+ BUG_ON(idx == bitmap_size);
+ }
+
+ return idx;
+ }
+
+ static void kvm_apic_disabled_lapic_found(struct kvm *kvm)
+ {
+ if (!kvm->arch.disabled_lapic_found) {
+ kvm->arch.disabled_lapic_found = true;
+ printk(KERN_INFO
+ "Disabled LAPIC found during irq injection\n");
+ }
+ }
+
bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
- struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map)
+ struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map)
{
struct kvm_apic_map *map;
unsigned long bitmap = 1;
dst = map->logical_map[cid];
- if (kvm_lowest_prio_delivery(irq)) {
+ if (!kvm_lowest_prio_delivery(irq))
+ goto set_irq;
+
+ if (!kvm_vector_hashing_enabled()) {
int l = -1;
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
continue;
if (l < 0)
l = i;
- else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+ else if (kvm_apic_compare_prio(dst[i]->vcpu,
+ dst[l]->vcpu) < 0)
l = i;
}
-
bitmap = (l >= 0) ? 1 << l : 0;
+ } else {
+ int idx;
+ unsigned int dest_vcpus;
+
+ dest_vcpus = hweight16(bitmap);
+ if (dest_vcpus == 0)
+ goto out;
+
+ idx = kvm_vector_to_index(irq->vector,
+ dest_vcpus, &bitmap, 16);
+
+ if (!dst[idx]) {
+ kvm_apic_disabled_lapic_found(kvm);
+ goto out;
+ }
+
+ bitmap = (idx >= 0) ? 1 << idx : 0;
}
}
+ set_irq:
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
continue;
return ret;
}
+ /*
+ * This routine tries to handler interrupts in posted mode, here is how
+ * it deals with different cases:
+ * - For single-destination interrupts, handle it in posted mode
+ * - Else if vector hashing is enabled and it is a lowest-priority
+ * interrupt, handle it in posted mode and use the following mechanism
+ * to find the destinaiton vCPU.
+ * 1. For lowest-priority interrupts, store all the possible
+ * destination vCPUs in an array.
+ * 2. Use "guest vector % max number of destination vCPUs" to find
+ * the right destination vCPU in the array for the lowest-priority
+ * interrupt.
+ * - Otherwise, use remapped mode to inject the interrupt.
+ */
bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu)
{
if (cid >= ARRAY_SIZE(map->logical_map))
goto out;
- for_each_set_bit(i, &bitmap, 16) {
- dst = map->logical_map[cid][i];
- if (++r == 2)
+ if (kvm_vector_hashing_enabled() &&
+ kvm_lowest_prio_delivery(irq)) {
+ int idx;
+ unsigned int dest_vcpus;
+
+ dest_vcpus = hweight16(bitmap);
+ if (dest_vcpus == 0)
goto out;
- }
- if (dst && kvm_apic_present(dst->vcpu))
+ idx = kvm_vector_to_index(irq->vector, dest_vcpus,
+ &bitmap, 16);
+
+ dst = map->logical_map[cid][idx];
+ if (!dst) {
+ kvm_apic_disabled_lapic_found(kvm);
+ goto out;
+ }
+
*dest_vcpu = dst->vcpu;
- else
- goto out;
+ } else {
+ for_each_set_bit(i, &bitmap, 16) {
+ dst = map->logical_map[cid][i];
+ if (++r == 2)
+ goto out;
+ }
+
+ if (dst && kvm_apic_present(dst->vcpu))
+ *dest_vcpu = dst->vcpu;
+ else
+ goto out;
+ }
}
ret = true;
*/
static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
int vector, int level, int trig_mode,
- unsigned long *dest_map)
+ struct dest_map *dest_map)
{
int result = 0;
struct kvm_vcpu *vcpu = apic->vcpu;
result = 1;
- if (dest_map)
- __set_bit(vcpu->vcpu_id, dest_map);
+ if (dest_map) {
+ __set_bit(vcpu->vcpu_id, dest_map->map);
+ dest_map->vectors[vcpu->vcpu_id] = vector;
+ }
if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
if (trig_mode)
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
- wait_queue_head_t *q = &vcpu->wq;
+ struct swait_queue_head *q = &vcpu->wq;
struct kvm_timer *ktimer = &apic->lapic_timer;
if (atomic_read(&apic->lapic_timer.pending))
atomic_inc(&apic->lapic_timer.pending);
kvm_set_pending_timer(vcpu);
- if (waitqueue_active(q))
- wake_up_interruptible(q);
+ if (swait_active(q))
+ swake_up(q);
if (apic_lvtt_tscdeadline(apic))
ktimer->expired_tscdeadline = ktimer->tscdeadline;
struct kvm_lapic *apic = vcpu->arch.apic;
u64 guest_tsc, tsc_deadline;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return;
if (apic->lapic_timer.expired_tscdeadline == 0)
void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
{
- if (kvm_vcpu_has_lapic(vcpu))
- apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
+ apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
}
EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+ if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
apic_lvtt_period(apic))
return 0;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+ if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
apic_lvtt_period(apic))
return;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu))
- return;
-
apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
| (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4));
}
{
u64 tpr;
- if (!kvm_vcpu_has_lapic(vcpu))
- return 0;
-
tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
return (tpr & 0xf0) >> 4;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (kvm_vcpu_has_lapic(vcpu) && apic_enabled(apic) &&
- apic_lvt_enabled(apic, APIC_LVTT))
+ if (apic_enabled(apic) && apic_lvt_enabled(apic, APIC_LVTT))
return atomic_read(&apic->lapic_timer.pending);
return 0;
struct kvm_lapic *apic = vcpu->arch.apic;
int highest_irr;
- if (!kvm_vcpu_has_lapic(vcpu) || !apic_enabled(apic))
+ if (!apic_enabled(apic))
return -1;
apic_update_ppr(apic);
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu))
- return;
-
if (atomic_read(&apic->lapic_timer.pending) > 0) {
kvm_apic_local_deliver(apic, APIC_LVTT);
if (apic_lvtt_tscdeadline(apic))
{
struct hrtimer *timer;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return;
timer = &vcpu->arch.apic->lapic_timer.timer;
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return 1;
/* if this is ICR write vector before command */
struct kvm_lapic *apic = vcpu->arch.apic;
u32 low, high = 0;
- if (!kvm_vcpu_has_lapic(vcpu))
+ if (!lapic_in_kernel(vcpu))
return 1;
if (apic_reg_read(apic, reg, 4, &low))
u8 sipi_vector;
unsigned long pe;
- if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
+ if (!lapic_in_kernel(vcpu) || !apic->pending_events)
return;
/*
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/vmx.h>
+ #include <asm/kvm_page_track.h>
/*
* When setting this variable to true it enables Two-Dimensional-Paging
return &slot->arch.lpage_info[level - 2][idx];
}
+ static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot,
+ gfn_t gfn, int count)
+ {
+ struct kvm_lpage_info *linfo;
+ int i;
+
+ for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
+ linfo = lpage_info_slot(gfn, slot, i);
+ linfo->disallow_lpage += count;
+ WARN_ON(linfo->disallow_lpage < 0);
+ }
+ }
+
+ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+ {
+ update_gfn_disallow_lpage_count(slot, gfn, 1);
+ }
+
+ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+ {
+ update_gfn_disallow_lpage_count(slot, gfn, -1);
+ }
+
static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
- struct kvm_lpage_info *linfo;
gfn_t gfn;
- int i;
+ kvm->arch.indirect_shadow_pages++;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
- for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
- linfo = lpage_info_slot(gfn, slot, i);
- linfo->write_count += 1;
- }
- kvm->arch.indirect_shadow_pages++;
+
+ /* the non-leaf shadow pages are keeping readonly. */
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_add_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_disallow_lpage(slot, gfn);
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *slot;
- struct kvm_lpage_info *linfo;
gfn_t gfn;
- int i;
+ kvm->arch.indirect_shadow_pages--;
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
- for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
- linfo = lpage_info_slot(gfn, slot, i);
- linfo->write_count -= 1;
- WARN_ON(linfo->write_count < 0);
- }
- kvm->arch.indirect_shadow_pages--;
+ if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+ return kvm_slot_page_track_remove_page(kvm, slot, gfn,
+ KVM_PAGE_TRACK_WRITE);
+
+ kvm_mmu_gfn_allow_lpage(slot, gfn);
}
- static int __has_wrprotected_page(gfn_t gfn, int level,
- struct kvm_memory_slot *slot)
+ static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
+ struct kvm_memory_slot *slot)
{
struct kvm_lpage_info *linfo;
if (slot) {
linfo = lpage_info_slot(gfn, slot, level);
- return linfo->write_count;
+ return !!linfo->disallow_lpage;
}
- return 1;
+ return true;
}
- static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+ static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
+ int level)
{
struct kvm_memory_slot *slot;
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
- return __has_wrprotected_page(gfn, level, slot);
+ return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
}
static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
- if (__has_wrprotected_page(large_gfn, level, slot))
+ if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot))
break;
return level - 1;
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
- static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+ struct kvm_memory_slot *slot, u64 gfn)
{
- struct kvm_memory_slot *slot;
struct kvm_rmap_head *rmap_head;
int i;
bool write_protected = false;
- slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-
for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
rmap_head = __gfn_to_rmap(gfn, i, slot);
- write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true);
+ write_protected |= __rmap_write_protect(kvm, rmap_head, true);
}
return write_protected;
}
+ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+ {
+ struct kvm_memory_slot *slot;
+
+ slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn);
+ }
+
static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
{
u64 *sptep;
static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp)
{
- return 1;
+ return 0;
}
static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
return nr_unsync_leaf;
}
+ #define INVALID_INDEX (-1)
+
static int mmu_unsync_walk(struct kvm_mmu_page *sp,
struct kvm_mmu_pages *pvec)
{
+ pvec->nr = 0;
if (!sp->unsync_children)
return 0;
- mmu_pages_add(pvec, sp, 0);
+ mmu_pages_add(pvec, sp, INVALID_INDEX);
return __mmu_unsync_walk(sp, pvec);
}
if ((_sp)->role.direct || (_sp)->role.invalid) {} else
/* @sp->gfn should be write-protected at the call site */
- static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
- struct list_head *invalid_list, bool clear_unsync)
+ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+ struct list_head *invalid_list)
{
if (sp->role.cr4_pae != !!is_pae(vcpu)) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
- return 1;
+ return false;
}
- if (clear_unsync)
- kvm_unlink_unsync_page(vcpu->kvm, sp);
-
- if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
+ if (vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
- return 1;
+ return false;
}
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- return 0;
+ return true;
}
- static int kvm_sync_page_transient(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp)
+ static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu,
+ struct list_head *invalid_list,
+ bool remote_flush, bool local_flush)
{
- LIST_HEAD(invalid_list);
- int ret;
-
- ret = __kvm_sync_page(vcpu, sp, &invalid_list, false);
- if (ret)
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+ if (!list_empty(invalid_list)) {
+ kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list);
+ return;
+ }
- return ret;
+ if (remote_flush)
+ kvm_flush_remote_tlbs(vcpu->kvm);
+ else if (local_flush)
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
#ifdef CONFIG_KVM_MMU_AUDIT
static void mmu_audit_disable(void) { }
#endif
- static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+ static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
- return __kvm_sync_page(vcpu, sp, invalid_list, true);
+ kvm_unlink_unsync_page(vcpu->kvm, sp);
+ return __kvm_sync_page(vcpu, sp, invalid_list);
}
/* @gfn should be write-protected at the call site */
- static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
+ static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn,
+ struct list_head *invalid_list)
{
struct kvm_mmu_page *s;
- LIST_HEAD(invalid_list);
- bool flush = false;
+ bool ret = false;
for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
if (!s->unsync)
continue;
WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
- kvm_unlink_unsync_page(vcpu->kvm, s);
- if ((s->role.cr4_pae != !!is_pae(vcpu)) ||
- (vcpu->arch.mmu.sync_page(vcpu, s))) {
- kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list);
- continue;
- }
- flush = true;
+ ret |= kvm_sync_page(vcpu, s, invalid_list);
}
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
- if (flush)
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ return ret;
}
struct mmu_page_path {
- struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1];
- unsigned int idx[PT64_ROOT_LEVEL-1];
+ struct kvm_mmu_page *parent[PT64_ROOT_LEVEL];
+ unsigned int idx[PT64_ROOT_LEVEL];
};
#define for_each_sp(pvec, sp, parents, i) \
- for (i = mmu_pages_next(&pvec, &parents, -1), \
- sp = pvec.page[i].sp; \
+ for (i = mmu_pages_first(&pvec, &parents); \
i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \
i = mmu_pages_next(&pvec, &parents, i))
for (n = i+1; n < pvec->nr; n++) {
struct kvm_mmu_page *sp = pvec->page[n].sp;
+ unsigned idx = pvec->page[n].idx;
+ int level = sp->role.level;
- if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
- parents->idx[0] = pvec->page[n].idx;
- return n;
- }
+ parents->idx[level-1] = idx;
+ if (level == PT_PAGE_TABLE_LEVEL)
+ break;
- parents->parent[sp->role.level-2] = sp;
- parents->idx[sp->role.level-1] = pvec->page[n].idx;
+ parents->parent[level-2] = sp;
}
return n;
}
+ static int mmu_pages_first(struct kvm_mmu_pages *pvec,
+ struct mmu_page_path *parents)
+ {
+ struct kvm_mmu_page *sp;
+ int level;
+
+ if (pvec->nr == 0)
+ return 0;
+
+ WARN_ON(pvec->page[0].idx != INVALID_INDEX);
+
+ sp = pvec->page[0].sp;
+ level = sp->role.level;
+ WARN_ON(level == PT_PAGE_TABLE_LEVEL);
+
+ parents->parent[level-2] = sp;
+
+ /* Also set up a sentinel. Further entries in pvec are all
+ * children of sp, so this element is never overwritten.
+ */
+ parents->parent[level-1] = NULL;
+ return mmu_pages_next(pvec, parents, 0);
+ }
+
static void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
struct kvm_mmu_page *sp;
do {
unsigned int idx = parents->idx[level];
-
sp = parents->parent[level];
if (!sp)
return;
+ WARN_ON(idx == INVALID_INDEX);
clear_unsync_child_bit(sp, idx);
level++;
- } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children);
- }
-
- static void kvm_mmu_pages_init(struct kvm_mmu_page *parent,
- struct mmu_page_path *parents,
- struct kvm_mmu_pages *pvec)
- {
- parents->parent[parent->role.level-1] = NULL;
- pvec->nr = 0;
+ } while (!sp->unsync_children);
}
static void mmu_sync_children(struct kvm_vcpu *vcpu,
struct mmu_page_path parents;
struct kvm_mmu_pages pages;
LIST_HEAD(invalid_list);
+ bool flush = false;
- kvm_mmu_pages_init(parent, &parents, &pages);
while (mmu_unsync_walk(parent, &pages)) {
bool protected = false;
for_each_sp(pages, sp, parents, i)
protected |= rmap_write_protect(vcpu, sp->gfn);
- if (protected)
+ if (protected) {
kvm_flush_remote_tlbs(vcpu->kvm);
+ flush = false;
+ }
for_each_sp(pages, sp, parents, i) {
- kvm_sync_page(vcpu, sp, &invalid_list);
+ flush |= kvm_sync_page(vcpu, sp, &invalid_list);
mmu_pages_clear_parents(&parents);
}
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
- cond_resched_lock(&vcpu->kvm->mmu_lock);
- kvm_mmu_pages_init(parent, &parents, &pages);
+ if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) {
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+ cond_resched_lock(&vcpu->kvm->mmu_lock);
+ flush = false;
+ }
}
+
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
}
static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
{
- sp->write_flooding_count = 0;
+ atomic_set(&sp->write_flooding_count, 0);
}
static void clear_sp_write_flooding_count(u64 *spte)
unsigned quadrant;
struct kvm_mmu_page *sp;
bool need_sync = false;
+ bool flush = false;
+ LIST_HEAD(invalid_list);
role = vcpu->arch.mmu.base_role;
role.level = level;
if (sp->role.word != role.word)
continue;
- if (sp->unsync && kvm_sync_page_transient(vcpu, sp))
- break;
+ if (sp->unsync) {
+ /* The page is good, but __kvm_sync_page might still end
+ * up zapping it. If so, break in order to rebuild it.
+ */
+ if (!__kvm_sync_page(vcpu, sp, &invalid_list))
+ break;
+
+ WARN_ON(!list_empty(&invalid_list));
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ }
if (sp->unsync_children)
kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
hlist_add_head(&sp->hash_link,
&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
if (!direct) {
- if (rmap_write_protect(vcpu, gfn))
+ /*
+ * we should do write protection before syncing pages
+ * otherwise the content of the synced shadow page may
+ * be inconsistent with guest page table.
+ */
+ account_shadowed(vcpu->kvm, sp);
+ if (level == PT_PAGE_TABLE_LEVEL &&
+ rmap_write_protect(vcpu, gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
- if (level > PT_PAGE_TABLE_LEVEL && need_sync)
- kvm_sync_pages(vcpu, gfn);
- account_shadowed(vcpu->kvm, sp);
+ if (level > PT_PAGE_TABLE_LEVEL && need_sync)
+ flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
}
sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
clear_page(sp->spt);
trace_kvm_mmu_get_page(sp, true);
+
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
return sp;
}
if (parent->role.level == PT_PAGE_TABLE_LEVEL)
return 0;
- kvm_mmu_pages_init(parent, &parents, &pages);
while (mmu_unsync_walk(parent, &pages)) {
struct kvm_mmu_page *sp;
mmu_pages_clear_parents(&parents);
zapped++;
}
- kvm_mmu_pages_init(parent, &parents, &pages);
}
return zapped;
if (list_empty(&kvm->arch.active_mmu_pages))
return false;
- sp = list_entry(kvm->arch.active_mmu_pages.prev,
- struct kvm_mmu_page, link);
+ sp = list_last_entry(&kvm->arch.active_mmu_pages,
+ struct kvm_mmu_page, link);
kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
return true;
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
- static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
trace_kvm_mmu_unsync_page(sp);
++vcpu->kvm->stat.mmu_unsync;
kvm_mmu_mark_parents_unsync(sp);
}
- static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
+ static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
+ bool can_unsync)
{
- struct kvm_mmu_page *s;
-
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
- if (s->unsync)
- continue;
- WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
- __kvm_unsync_page(vcpu, s);
- }
- }
+ struct kvm_mmu_page *sp;
- static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
- bool can_unsync)
- {
- struct kvm_mmu_page *s;
- bool need_unsync = false;
+ if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+ return true;
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
+ for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (!can_unsync)
- return 1;
+ return true;
- if (s->role.level != PT_PAGE_TABLE_LEVEL)
- return 1;
+ if (sp->unsync)
+ continue;
- if (!s->unsync)
- need_unsync = true;
+ WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
+ kvm_unsync_page(vcpu, sp);
}
- if (need_unsync)
- kvm_unsync_pages(vcpu, gfn);
- return 0;
+
+ return false;
}
static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
* be fixed if guest refault.
*/
if (level > PT_PAGE_TABLE_LEVEL &&
- has_wrprotected_page(vcpu, gfn, level))
+ mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
goto done;
spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
level == PT_PAGE_TABLE_LEVEL &&
PageTransCompound(pfn_to_page(pfn)) &&
- !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
+ !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
unsigned long mask;
/*
* mmu_notifier_retry was successful and we hold the
static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
kvm_pfn_t pfn, unsigned access, int *ret_val)
{
- bool ret = true;
-
/* The pfn is invalid, report the error! */
if (unlikely(is_error_pfn(pfn))) {
*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
- goto exit;
+ return true;
}
if (unlikely(is_noslot_pfn(pfn)))
vcpu_cache_mmio_info(vcpu, gva, gfn, access);
- ret = false;
- exit:
- return ret;
+ return false;
}
static bool page_fault_can_be_fast(u32 error_code)
return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
}
- static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
if (direct)
return vcpu_match_mmio_gpa(vcpu, addr);
u64 spte;
bool reserved;
- if (quickly_check_mmio_pf(vcpu, addr, direct))
+ if (mmio_info_in_cache(vcpu, addr, direct))
return RET_MMIO_PF_EMULATE;
reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
}
EXPORT_SYMBOL_GPL(handle_mmio_page_fault);
+ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
+ u32 error_code, gfn_t gfn)
+ {
+ if (unlikely(error_code & PFERR_RSVD_MASK))
+ return false;
+
+ if (!(error_code & PFERR_PRESENT_MASK) ||
+ !(error_code & PFERR_WRITE_MASK))
+ return false;
+
+ /*
+ * guest is writing the page which is write tracked which can
+ * not be fixed by page fault handler.
+ */
+ if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+ return true;
+
+ return false;
+ }
+
+ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
+ {
+ struct kvm_shadow_walk_iterator iterator;
+ u64 spte;
+
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return;
+
+ walk_shadow_page_lockless_begin(vcpu);
+ for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
+ clear_sp_write_flooding_count(iterator.sptep);
+ if (!is_shadow_present_pte(spte))
+ break;
+ }
+ walk_shadow_page_lockless_end(vcpu);
+ }
+
static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
u32 error_code, bool prefault)
{
- gfn_t gfn;
+ gfn_t gfn = gva >> PAGE_SHIFT;
int r;
pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
- if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, gva, true);
-
- if (likely(r != RET_MMIO_PF_INVALID))
- return r;
- }
+ if (page_fault_handle_page_track(vcpu, error_code, gfn))
+ return 1;
r = mmu_topup_memory_caches(vcpu);
if (r)
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
- gfn = gva >> PAGE_SHIFT;
return nonpaging_map(vcpu, gva & PAGE_MASK,
error_code, gfn, prefault);
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
- if (unlikely(error_code & PFERR_RSVD_MASK)) {
- r = handle_mmio_page_fault(vcpu, gpa, true);
-
- if (likely(r != RET_MMIO_PF_INVALID))
- return r;
- }
+ if (page_fault_handle_page_track(vcpu, error_code, gfn))
+ return 1;
r = mmu_topup_memory_caches(vcpu);
if (r)
return false;
}
- static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
+ static inline bool is_last_gpte(struct kvm_mmu *mmu,
+ unsigned level, unsigned gpte)
{
- unsigned index;
+ /*
+ * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set
+ * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
+ * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
+ */
+ gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
- index = level - 1;
- index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2);
- return mmu->last_pte_bitmap & (1 << index);
+ /*
+ * The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
+ * If it is clear, there are no large pages at this level, so clear
+ * PT_PAGE_SIZE_MASK in gpte if that is the case.
+ */
+ gpte &= level - mmu->last_nonleaf_level;
+
+ return gpte & PT_PAGE_SIZE_MASK;
}
#define PTTYPE_EPT 18 /* arbitrary */
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
+ bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+
/*
* Passing "true" to the last argument is okay; it adds a check
* on bit 8 of the SPTEs which KVM doesn't use anyway.
*/
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
- context->shadow_root_level, context->nx,
+ context->shadow_root_level, uses_nx,
guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
true);
}
}
}
- static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+ static void update_last_nonleaf_level(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
{
- u8 map;
- unsigned level, root_level = mmu->root_level;
- const unsigned ps_set_index = 1 << 2; /* bit 2 of index: ps */
-
- if (root_level == PT32E_ROOT_LEVEL)
- --root_level;
- /* PT_PAGE_TABLE_LEVEL always terminates */
- map = 1 | (1 << ps_set_index);
- for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
- if (level <= PT_PDPE_LEVEL
- && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
- map |= 1 << (ps_set_index | (level - 1));
- }
- mmu->last_pte_bitmap = map;
+ unsigned root_level = mmu->root_level;
+
+ mmu->last_nonleaf_level = root_level;
+ if (root_level == PT32_ROOT_LEVEL && is_pse(vcpu))
+ mmu->last_nonleaf_level++;
}
static void paging64_init_context_common(struct kvm_vcpu *vcpu,
reset_rsvds_bits_mask(vcpu, context);
update_permission_bitmask(vcpu, context, false);
- update_last_pte_bitmap(vcpu, context);
+ update_last_nonleaf_level(vcpu, context);
MMU_WARN_ON(!is_pae(vcpu));
context->page_fault = paging64_page_fault;
reset_rsvds_bits_mask(vcpu, context);
update_permission_bitmask(vcpu, context, false);
- update_last_pte_bitmap(vcpu, context);
+ update_last_nonleaf_level(vcpu, context);
context->page_fault = paging32_page_fault;
context->gva_to_gpa = paging32_gva_to_gpa;
}
update_permission_bitmask(vcpu, context, false);
- update_last_pte_bitmap(vcpu, context);
+ update_last_nonleaf_level(vcpu, context);
reset_tdp_shadow_zero_bits_mask(vcpu, context);
}
}
update_permission_bitmask(vcpu, g_context, false);
- update_last_pte_bitmap(vcpu, g_context);
+ update_last_nonleaf_level(vcpu, g_context);
}
static void init_kvm_mmu(struct kvm_vcpu *vcpu)
return (old & ~new & PT64_PERM_MASK) != 0;
}
- static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
- bool remote_flush, bool local_flush)
- {
- if (zap_page)
- return;
-
- if (remote_flush)
- kvm_flush_remote_tlbs(vcpu->kvm);
- else if (local_flush)
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- }
-
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
const u8 *new, int *bytes)
{
if (sp->role.level == PT_PAGE_TABLE_LEVEL)
return false;
- return ++sp->write_flooding_count >= 3;
+ atomic_inc(&sp->write_flooding_count);
+ return atomic_read(&sp->write_flooding_count) >= 3;
}
/*
return spte;
}
- void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes)
+ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+ const u8 *new, int bytes)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_mmu_page *sp;
LIST_HEAD(invalid_list);
u64 entry, gentry, *spte;
int npte;
- bool remote_flush, local_flush, zap_page;
+ bool remote_flush, local_flush;
union kvm_mmu_page_role mask = { };
mask.cr0_wp = 1;
if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
return;
- zap_page = remote_flush = local_flush = false;
+ remote_flush = local_flush = false;
pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (detect_write_misaligned(sp, gpa, bytes) ||
detect_write_flooding(sp)) {
- zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
- &invalid_list);
+ kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
++vcpu->kvm->stat.mmu_flooded;
continue;
}
++spte;
}
}
- mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush);
- kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+ kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush);
kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE);
spin_unlock(&vcpu->kvm->mmu_lock);
}
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
}
- static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
- {
- if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
- return vcpu_match_mmio_gpa(vcpu, addr);
-
- return vcpu_match_mmio_gva(vcpu, addr);
- }
-
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
void *insn, int insn_len)
{
int r, emulation_type = EMULTYPE_RETRY;
enum emulation_result er;
+ bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu);
+
+ if (unlikely(error_code & PFERR_RSVD_MASK)) {
+ r = handle_mmio_page_fault(vcpu, cr2, direct);
+ if (r == RET_MMIO_PF_EMULATE) {
+ emulation_type = 0;
+ goto emulate;
+ }
+ if (r == RET_MMIO_PF_RETRY)
+ return 1;
+ if (r < 0)
+ return r;
+ }
r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
if (r < 0)
- goto out;
-
- if (!r) {
- r = 1;
- goto out;
- }
+ return r;
+ if (!r)
+ return 1;
- if (is_mmio_page_fault(vcpu, cr2))
+ if (mmio_info_in_cache(vcpu, cr2, direct))
emulation_type = 0;
-
+ emulate:
er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
switch (er) {
default:
BUG();
}
- out:
- return r;
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
init_kvm_mmu(vcpu);
}
+ void kvm_mmu_init_vm(struct kvm *kvm)
+ {
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ node->track_write = kvm_mmu_pte_write;
+ kvm_page_track_register_notifier(kvm, node);
+ }
+
+ void kvm_mmu_uninit_vm(struct kvm *kvm)
+ {
+ struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+ kvm_page_track_unregister_notifier(kvm, node);
+ }
+
/* The return value indicates if tlb flush on all vcpus is needed. */
typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+
+ u64 current_tsc_ratio;
};
enum segment_cache_field {
static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
- static bool vmx_mpx_supported(void);
static bool vmx_xsaves_supported(void);
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
static void vmx_set_segment(struct kvm_vcpu *vcpu,
MSR_EFER, MSR_TSC_AUX, MSR_STAR,
};
- static inline bool is_page_fault(u32 intr_info)
+ static inline bool is_exception_n(u32 intr_info, u8 vector)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+ (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+ }
+
+ static inline bool is_debug(u32 intr_info)
+ {
+ return is_exception_n(intr_info, DB_VECTOR);
+ }
+
+ static inline bool is_breakpoint(u32 intr_info)
+ {
+ return is_exception_n(intr_info, BP_VECTOR);
+ }
+
+ static inline bool is_page_fault(u32 intr_info)
+ {
+ return is_exception_n(intr_info, PF_VECTOR);
}
static inline bool is_no_device(u32 intr_info)
{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
- INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+ return is_exception_n(intr_info, NM_VECTOR);
}
static inline bool is_invalid_opcode(u32 intr_info)
{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
- INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+ return is_exception_n(intr_info, UD_VECTOR);
}
static inline bool is_external_interrupt(u32 intr_info)
return;
}
break;
+ case MSR_IA32_PEBS_ENABLE:
+ /* PEBS needs a quiescent period after being disabled (to write
+ * a record). Disabling PEBS through VMX MSR swapping doesn't
+ * provide that period, so a CPU could write host's record into
+ * guest's memory.
+ */
+ wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
for (i = 0; i < m->nr; ++i)
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
{
- u64 guest_efer;
- u64 ignore_bits;
+ u64 guest_efer = vmx->vcpu.arch.efer;
+ u64 ignore_bits = 0;
- guest_efer = vmx->vcpu.arch.efer;
+ if (!enable_ept) {
+ /*
+ * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing
+ * host CPUID is more efficient than testing guest CPUID
+ * or CR4. Host SMEP is anyway a requirement for guest SMEP.
+ */
+ if (boot_cpu_has(X86_FEATURE_SMEP))
+ guest_efer |= EFER_NX;
+ else if (!(guest_efer & EFER_NX))
+ ignore_bits |= EFER_NX;
+ }
/*
- * NX is emulated; LMA and LME handled by hardware; SCE meaningless
- * outside long mode
+ * LMA and LME handled by hardware; SCE meaningless outside long mode.
*/
- ignore_bits = EFER_NX | EFER_SCE;
+ ignore_bits |= EFER_SCE;
#ifdef CONFIG_X86_64
ignore_bits |= EFER_LMA | EFER_LME;
/* SCE is meaningful only in long mode on Intel */
if (guest_efer & EFER_LMA)
ignore_bits &= ~(u64)EFER_SCE;
#endif
- guest_efer &= ~ignore_bits;
- guest_efer |= host_efer & ignore_bits;
- vmx->guest_msrs[efer_offset].data = guest_efer;
- vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
clear_atomic_switch_msr(vmx, MSR_EFER);
*/
if (cpu_has_load_ia32_efer ||
(enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
- guest_efer = vmx->vcpu.arch.efer;
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
guest_efer, host_efer);
return false;
- }
+ } else {
+ guest_efer &= ~ignore_bits;
+ guest_efer |= host_efer & ignore_bits;
+
+ vmx->guest_msrs[efer_offset].data = guest_efer;
+ vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
- return true;
+ return true;
+ }
}
static unsigned long segment_base(u16 selector)
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
- /* Setup TSC multiplier */
- if (cpu_has_vmx_tsc_scaling())
- vmcs_write64(TSC_MULTIPLIER,
- vcpu->arch.tsc_scaling_ratio);
-
vmx->loaded_vmcs->cpu = cpu;
}
+ /* Setup TSC multiplier */
+ if (kvm_has_tsc_control &&
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+ vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+ }
+
vmx_vcpu_pi_load(vcpu, cpu);
}
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
/* We support free control of debug control saving. */
VM_ENTRY_LOAD_IA32_PAT;
vmx->nested.nested_vmx_entry_ctls_high |=
(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
/* We support free control of debug control loading. */
msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
case MSR_IA32_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported())
return 1;
msr_info->data = vmcs_read64(GUEST_BNDCFGS);
break;
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
case MSR_IA32_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported())
return 1;
vmcs_write64(GUEST_BNDCFGS, data);
break;
for (i = j = 0; i < max_shadow_read_write_fields; i++) {
switch (shadow_read_write_fields[i]) {
case GUEST_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported())
continue;
break;
default:
}
if (vcpu->guest_debug == 0) {
- u32 cpu_based_vm_exec_control;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_MOV_DR_EXITING);
/*
* No more DR vmexits; force a reload of the debug registers
static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
{
- u32 cpu_based_vm_exec_control;
-
get_debugreg(vcpu->arch.db[0], 0);
get_debugreg(vcpu->arch.db[1], 1);
get_debugreg(vcpu->arch.db[2], 2);
vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+ vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING);
}
static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
static int handle_vmcall(struct kvm_vcpu *vcpu)
{
- kvm_emulate_hypercall(vcpu);
- return 1;
+ return kvm_emulate_hypercall(vcpu);
}
static int handle_invd(struct kvm_vcpu *vcpu)
if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
/* Recycle the least recently used VMCS. */
- item = list_entry(vmx->nested.vmcs02_pool.prev,
- struct vmcs02_list, list);
+ item = list_last_entry(&vmx->nested.vmcs02_pool,
+ struct vmcs02_list, list);
item->vmptr = vmx->nested.current_vmptr;
list_move(&item->list, &vmx->nested.vmcs02_pool);
return &item->vmcs02;
else if (is_no_device(intr_info) &&
!(vmcs12->guest_cr0 & X86_CR0_TS))
return false;
+ else if (is_debug(intr_info) &&
+ vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+ return false;
+ else if (is_breakpoint(intr_info) &&
+ vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+ return false;
return vmcs12->exception_bitmap &
(1u << (intr_info & INTR_INFO_VECTOR_MASK));
case EXIT_REASON_EXTERNAL_INTERRUPT:
vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
if (nested_cpu_has_xsaves(vmcs12))
vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
*/
kvm_set_msi_irq(e, &irq);
- if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu))
+ if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+ /*
+ * Make sure the IRTE is in remapped mode if
+ * we don't handle it in posted mode.
+ */
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (ret < 0) {
+ printk(KERN_INFO
+ "failed to back to remapped mode, irq: %u\n",
+ host_irq);
+ goto out;
+ }
+
continue;
+ }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
- trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi,
+ trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
if (set)
unsigned int __read_mostly lapic_timer_advance_ns = 0;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+ static bool __read_mostly vector_hashing = true;
+ module_param(vector_hashing, bool, S_IRUGO);
+
static bool __read_mostly backwards_tsc_observed = false;
#define KVM_NR_SHARED_MSRS 16
static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
- uint32_t quotient, remainder;
-
- /* Don't try to replace with do_div(), this one calculates
- * "(dividend << 32) / divisor" */
- __asm__ ( "divl %4"
- : "=a" (quotient), "=d" (remainder)
- : "0" (0), "1" (dividend), "r" (divisor) );
- return quotient;
+ do_shl32_div32(dividend, divisor);
+ return dividend;
}
- static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
+ static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz,
s8 *pshift, u32 *pmultiplier)
{
uint64_t scaled64;
uint64_t tps64;
uint32_t tps32;
- tps64 = base_khz * 1000LL;
- scaled64 = scaled_khz * 1000LL;
+ tps64 = base_hz;
+ scaled64 = scaled_hz;
while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
tps64 >>= 1;
shift--;
*pshift = shift;
*pmultiplier = div_frac(scaled64, tps32);
- pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
- __func__, base_khz, scaled_khz, shift, *pmultiplier);
+ pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n",
+ __func__, base_hz, scaled_hz, shift, *pmultiplier);
}
#ifdef CONFIG_X86_64
return 0;
}
- static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
+ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
{
u32 thresh_lo, thresh_hi;
int use_scaling = 0;
/* tsc_khz can be zero if TSC calibration fails */
- if (this_tsc_khz == 0) {
+ if (user_tsc_khz == 0) {
/* set tsc_scaling_ratio to a safe value */
vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
return -1;
}
/* Compute a scale to convert nanoseconds in TSC cycles */
- kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
+ kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC,
&vcpu->arch.virtual_tsc_shift,
&vcpu->arch.virtual_tsc_mult);
- vcpu->arch.virtual_tsc_khz = this_tsc_khz;
+ vcpu->arch.virtual_tsc_khz = user_tsc_khz;
/*
* Compute the variation in TSC rate which is acceptable
*/
thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
- if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) {
- pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
+ if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) {
+ pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi);
use_scaling = 1;
}
- return set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
+ return set_tsc_khz(vcpu, user_tsc_khz, use_scaling);
}
static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
- unsigned long flags, this_tsc_khz, tgt_tsc_khz;
+ unsigned long flags, tgt_tsc_khz;
struct kvm_vcpu_arch *vcpu = &v->arch;
struct kvm_arch *ka = &v->kvm->arch;
s64 kernel_ns;
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
- if (unlikely(this_tsc_khz == 0)) {
+ tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
+ if (unlikely(tgt_tsc_khz == 0)) {
local_irq_restore(flags);
kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
return 1;
if (!vcpu->pv_time_enabled)
return 0;
- if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
- tgt_tsc_khz = kvm_has_tsc_control ?
- vcpu->virtual_tsc_khz : this_tsc_khz;
- kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz,
+ if (kvm_has_tsc_control)
+ tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
+
+ if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
+ kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
&vcpu->hv_clock.tsc_shift,
&vcpu->hv_clock.tsc_to_system_mul);
- vcpu->hw_tsc_khz = this_tsc_khz;
+ vcpu->hw_tsc_khz = tgt_tsc_khz;
}
/* With all the info we got, fill in the values */
}
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
- vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR &&
- kvm_vcpu_has_lapic(vcpu))
+ lapic_in_kernel(vcpu))
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
else
vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
- if (kvm_vcpu_has_lapic(vcpu)) {
+ if (lapic_in_kernel(vcpu)) {
if (events->smi.latched_init)
set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
else
switch (ioctl) {
case KVM_GET_LAPIC: {
r = -EINVAL;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
}
case KVM_SET_LAPIC: {
r = -EINVAL;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = memdup_user(argp, sizeof(*u.lapic));
if (IS_ERR(u.lapic))
static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;
+
+ BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));
+
+ mutex_lock(&kps->lock);
+ memcpy(ps, &kps->channels, sizeof(*ps));
+ mutex_unlock(&kps->lock);
return 0;
}
static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
{
int i;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
for (i = 0; i < 3; i++)
- kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
+ mutex_unlock(&pit->pit_state.lock);
return 0;
}
int start = 0;
int i;
u32 prev_legacy, cur_legacy;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
if (!prev_legacy && cur_legacy)
start = 1;
- memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
- sizeof(kvm->arch.vpit->pit_state.channels));
- kvm->arch.vpit->pit_state.flags = ps->flags;
+ memcpy(&pit->pit_state.channels, &ps->channels,
+ sizeof(pit->pit_state.channels));
+ pit->pit_state.flags = ps->flags;
for (i = 0; i < 3; i++)
- kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count,
+ kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
start && i == 0);
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ mutex_unlock(&pit->pit_state.lock);
return 0;
}
static int kvm_vm_ioctl_reinject(struct kvm *kvm,
struct kvm_reinject_control *control)
{
- if (!kvm->arch.vpit)
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ if (!pit)
return -ENXIO;
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- kvm->arch.vpit->pit_state.reinject = control->pit_reinject;
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+
+ /* pit->pit_state.lock was overloaded to prevent userspace from getting
+ * an inconsistent state after running multiple KVM_REINJECT_CONTROL
+ * ioctls in parallel. Use a separate lock if that ioctl isn't rare.
+ */
+ mutex_lock(&pit->pit_state.lock);
+ kvm_pit_set_reinject(pit, control->pit_reinject);
+ mutex_unlock(&pit->pit_state.lock);
+
return 0;
}
do {
n = min(len, 8);
- if (!(vcpu->arch.apic &&
+ if (!(lapic_in_kernel(vcpu) &&
!kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v))
&& kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v))
break;
do {
n = min(len, 8);
- if (!(vcpu->arch.apic &&
+ if (!(lapic_in_kernel(vcpu) &&
!kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev,
addr, n, v))
&& kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
if (ret < 0)
return 0;
- kvm_mmu_pte_write(vcpu, gpa, val, bytes);
+ kvm_page_track_write(vcpu, gpa, val, bytes);
return 1;
}
return X86EMUL_CMPXCHG_FAILED;
kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
- kvm_mmu_pte_write(vcpu, gpa, new, bytes);
+ kvm_page_track_write(vcpu, gpa, new, bytes);
return X86EMUL_CONTINUE;
if (!kvm_x86_ops->update_cr8_intercept)
return;
- if (!vcpu->arch.apic)
+ if (!lapic_in_kernel(vcpu))
return;
if (vcpu->arch.apicv_active)
* KVM_DEBUGREG_WONT_EXIT again.
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
- int i;
-
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
kvm_x86_ops->sync_dirty_debug_regs(vcpu);
- for (i = 0; i < KVM_NR_DB_REGS; i++)
- vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ kvm_update_dr0123(vcpu);
+ kvm_update_dr6(vcpu);
+ kvm_update_dr7(vcpu);
+ vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
/*
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- if (!kvm_vcpu_has_lapic(vcpu) &&
+ if (!lapic_in_kernel(vcpu) &&
mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
return -EINVAL;
* Every 255 times fpu_counter rolls over to 0; a guest that uses
* the FPU in bursts will revert to loading it on demand.
*/
- if (!vcpu->arch.eager_fpu) {
+ if (!use_eager_fpu()) {
if (++vcpu->fpu_counter < 5)
kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
}
}
struct static_key kvm_no_apic_vcpu __read_mostly;
+ EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
+ kvm_page_track_init(kvm);
+ kvm_mmu_init_vm(kvm);
+
return 0;
}
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+ kvm_mmu_uninit_vm(kvm);
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
free->arch.lpage_info[i - 1] = NULL;
}
}
+
+ kvm_page_track_free_memslot(free, dont);
}
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
int i;
for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ struct kvm_lpage_info *linfo;
unsigned long ugfn;
int lpages;
int level = i + 1;
if (i == 0)
continue;
- slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages *
- sizeof(*slot->arch.lpage_info[i - 1]));
- if (!slot->arch.lpage_info[i - 1])
+ linfo = kvm_kvzalloc(lpages * sizeof(*linfo));
+ if (!linfo)
goto out_free;
+ slot->arch.lpage_info[i - 1] = linfo;
+
if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i - 1][0].write_count = 1;
+ linfo[0].disallow_lpage = 1;
if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1;
+ linfo[lpages - 1].disallow_lpage = 1;
ugfn = slot->userspace_addr >> PAGE_SHIFT;
/*
* If the gfn and userspace address are not aligned wrt each
unsigned long j;
for (j = 0; j < lpages; ++j)
- slot->arch.lpage_info[i - 1][j].write_count = 1;
+ linfo[j].disallow_lpage = 1;
}
}
+ if (kvm_page_track_create_memslot(slot, npages))
+ goto out_free;
+
return 0;
out_free:
return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
}
+ bool kvm_vector_hashing_enabled(void)
+ {
+ return vector_hashing;
+ }
+ EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
+
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
#define CNTTIDR 0x08
#define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4))
+#define CNTACR(n) (0x40 + ((n) * 4))
+#define CNTACR_RPCT BIT(0)
+#define CNTACR_RVCT BIT(1)
+#define CNTACR_RFRQ BIT(2)
+#define CNTACR_RVOFF BIT(3)
+#define CNTACR_RWVT BIT(4)
+#define CNTACR_RWPT BIT(5)
+
#define CNTVCT_LO 0x08
#define CNTVCT_HI 0x0c
#define CNTFRQ 0x10
static struct clock_event_device __percpu *arch_timer_evt;
- static bool arch_timer_use_virtual = true;
+ static enum ppi_nr arch_timer_uses_ppi = VIRT_PPI;
static bool arch_timer_c3stop;
static bool arch_timer_mem_use_virtual;
clk->name = "arch_sys_timer";
clk->rating = 450;
clk->cpumask = cpumask_of(smp_processor_id());
- if (arch_timer_use_virtual) {
- clk->irq = arch_timer_ppi[VIRT_PPI];
+ clk->irq = arch_timer_ppi[arch_timer_uses_ppi];
+ switch (arch_timer_uses_ppi) {
+ case VIRT_PPI:
clk->set_state_shutdown = arch_timer_shutdown_virt;
+ clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
clk->set_next_event = arch_timer_set_next_event_virt;
- } else {
- clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+ break;
+ case PHYS_SECURE_PPI:
+ case PHYS_NONSECURE_PPI:
+ case HYP_PPI:
clk->set_state_shutdown = arch_timer_shutdown_phys;
+ clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
clk->set_next_event = arch_timer_set_next_event_phys;
+ break;
+ default:
+ BUG();
}
} else {
clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
clk->cpumask = cpu_all_mask;
if (arch_timer_mem_use_virtual) {
clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
+ clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem;
clk->set_next_event =
arch_timer_set_next_event_virt_mem;
} else {
clk->set_state_shutdown = arch_timer_shutdown_phys_mem;
+ clk->set_state_oneshot_stopped = arch_timer_shutdown_phys_mem;
clk->set_next_event =
arch_timer_set_next_event_phys_mem;
}
arch_timer_set_cntkctl(cntkctl);
}
+ static bool arch_timer_has_nonsecure_ppi(void)
+ {
+ return (arch_timer_uses_ppi == PHYS_SECURE_PPI &&
+ arch_timer_ppi[PHYS_NONSECURE_PPI]);
+ }
+
static int arch_timer_setup(struct clock_event_device *clk)
{
__arch_timer_setup(ARCH_CP15_TIMER, clk);
- if (arch_timer_use_virtual)
- enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
- else {
- enable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI], 0);
- if (arch_timer_ppi[PHYS_NONSECURE_PPI])
- enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
- }
+ enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0);
+
+ if (arch_timer_has_nonsecure_ppi())
+ enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
arch_counter_set_user_access();
if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM))
(unsigned long)arch_timer_rate / 1000000,
(unsigned long)(arch_timer_rate / 10000) % 100,
type & ARCH_CP15_TIMER ?
- arch_timer_use_virtual ? "virt" : "phys" :
+ (arch_timer_uses_ppi == VIRT_PPI) ? "virt" : "phys" :
"",
type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ? "/" : "",
type & ARCH_MEM_TIMER ?
/* Register the CP15 based counter if we have one */
if (type & ARCH_CP15_TIMER) {
- if (IS_ENABLED(CONFIG_ARM64) || arch_timer_use_virtual)
+ if (IS_ENABLED(CONFIG_ARM64) || arch_timer_uses_ppi == VIRT_PPI)
arch_timer_read_counter = arch_counter_get_cntvct;
else
arch_timer_read_counter = arch_counter_get_cntpct;
pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
clk->irq, smp_processor_id());
- if (arch_timer_use_virtual)
- disable_percpu_irq(arch_timer_ppi[VIRT_PPI]);
- else {
- disable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI]);
- if (arch_timer_ppi[PHYS_NONSECURE_PPI])
- disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
- }
+ disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]);
+ if (arch_timer_has_nonsecure_ppi())
+ disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
clk->set_state_shutdown(clk);
}
goto out;
}
- if (arch_timer_use_virtual) {
- ppi = arch_timer_ppi[VIRT_PPI];
+ ppi = arch_timer_ppi[arch_timer_uses_ppi];
+ switch (arch_timer_uses_ppi) {
+ case VIRT_PPI:
err = request_percpu_irq(ppi, arch_timer_handler_virt,
"arch_timer", arch_timer_evt);
- } else {
- ppi = arch_timer_ppi[PHYS_SECURE_PPI];
+ break;
+ case PHYS_SECURE_PPI:
+ case PHYS_NONSECURE_PPI:
err = request_percpu_irq(ppi, arch_timer_handler_phys,
"arch_timer", arch_timer_evt);
if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
arch_timer_evt);
}
+ break;
+ case HYP_PPI:
+ err = request_percpu_irq(ppi, arch_timer_handler_phys,
+ "arch_timer", arch_timer_evt);
+ break;
+ default:
+ BUG();
}
if (err) {
out_unreg_notify:
unregister_cpu_notifier(&arch_timer_cpu_nb);
out_free_irq:
- if (arch_timer_use_virtual)
- free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
- else {
- free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+ free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt);
+ if (arch_timer_has_nonsecure_ppi())
+ free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
arch_timer_evt);
- if (arch_timer_ppi[PHYS_NONSECURE_PPI])
- free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
- arch_timer_evt);
- }
out_free:
free_percpu(arch_timer_evt);
*
* If no interrupt provided for virtual timer, we'll have to
* stick to the physical timer. It'd better be accessible...
+ *
+ * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
+ * accesses to CNTP_*_EL1 registers are silently redirected to
+ * their CNTHP_*_EL2 counterparts, and use a different PPI
+ * number.
*/
if (is_hyp_mode_available() || !arch_timer_ppi[VIRT_PPI]) {
- arch_timer_use_virtual = false;
+ bool has_ppi;
+
+ if (is_kernel_in_hyp_mode()) {
+ arch_timer_uses_ppi = HYP_PPI;
+ has_ppi = !!arch_timer_ppi[HYP_PPI];
+ } else {
+ arch_timer_uses_ppi = PHYS_SECURE_PPI;
+ has_ppi = (!!arch_timer_ppi[PHYS_SECURE_PPI] ||
+ !!arch_timer_ppi[PHYS_NONSECURE_PPI]);
+ }
- if (!arch_timer_ppi[PHYS_SECURE_PPI] ||
- !arch_timer_ppi[PHYS_NONSECURE_PPI]) {
+ if (!has_ppi) {
pr_warn("arch_timer: No interrupt available, giving up\n");
return;
}
*/
if (IS_ENABLED(CONFIG_ARM) &&
of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
- arch_timer_use_virtual = false;
+ arch_timer_uses_ppi = PHYS_SECURE_PPI;
arch_timer_init();
}
}
cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
- iounmap(cntctlbase);
/*
* Try to find a virtual capable frame. Otherwise fall back to a
*/
for_each_available_child_of_node(np, frame) {
int n;
+ u32 cntacr;
if (of_property_read_u32(frame, "frame-number", &n)) {
pr_err("arch_timer: Missing frame-number\n");
- of_node_put(best_frame);
of_node_put(frame);
- return;
+ goto out;
}
- if (cnttidr & CNTTIDR_VIRT(n)) {
+ /* Try enabling everything, and see what sticks */
+ cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT |
+ CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT;
+ writel_relaxed(cntacr, cntctlbase + CNTACR(n));
+ cntacr = readl_relaxed(cntctlbase + CNTACR(n));
+
+ if ((cnttidr & CNTTIDR_VIRT(n)) &&
+ !(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) {
of_node_put(best_frame);
best_frame = frame;
arch_timer_mem_use_virtual = true;
break;
}
+
+ if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT))
+ continue;
+
of_node_put(best_frame);
best_frame = of_node_get(frame);
}
base = arch_counter_base = of_iomap(best_frame, 0);
if (!base) {
pr_err("arch_timer: Can't map frame's registers\n");
- of_node_put(best_frame);
- return;
+ goto out;
}
if (arch_timer_mem_use_virtual)
irq = irq_of_parse_and_map(best_frame, 1);
else
irq = irq_of_parse_and_map(best_frame, 0);
- of_node_put(best_frame);
+
if (!irq) {
pr_err("arch_timer: Frame missing %s irq",
arch_timer_mem_use_virtual ? "virt" : "phys");
- return;
+ goto out;
}
arch_timer_detect_rate(base, np);
arch_timer_mem_register(base, irq);
arch_timer_common_init();
+out:
+ iounmap(cntctlbase);
+ of_node_put(best_frame);
}
CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
arch_timer_mem_init);
* This memory barrier pairs with prepare_to_wait's set_current_state()
*/
smp_mb();
- if (waitqueue_active(&vcpu->wq))
- wake_up_interruptible(&vcpu->wq);
+ if (swait_active(&vcpu->wq))
+ swake_up(&vcpu->wq);
mmput(mm);
kvm_put_kvm(vcpu->kvm);
/* cancel outstanding work queue item */
while (!list_empty(&vcpu->async_pf.queue)) {
struct kvm_async_pf *work =
- list_entry(vcpu->async_pf.queue.next,
- typeof(*work), queue);
+ list_first_entry(&vcpu->async_pf.queue,
+ typeof(*work), queue);
list_del(&work->queue);
#ifdef CONFIG_KVM_ASYNC_PF_SYNC
spin_lock(&vcpu->async_pf.lock);
while (!list_empty(&vcpu->async_pf.done)) {
struct kvm_async_pf *work =
- list_entry(vcpu->async_pf.done.next,
- typeof(*work), link);
+ list_first_entry(&vcpu->async_pf.done,
+ typeof(*work), link);
list_del(&work->link);
kmem_cache_free(async_pf_cache, work);
}
/* Default doubles per-vcpu halt_poll_ns. */
static unsigned int halt_poll_ns_grow = 2;
- module_param(halt_poll_ns_grow, int, S_IRUGO);
+ module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
/* Default resets per-vcpu halt_poll_ns . */
static unsigned int halt_poll_ns_shrink;
- module_param(halt_poll_ns_shrink, int, S_IRUGO);
+ module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
/*
* Ordering of locks:
vcpu->kvm = kvm;
vcpu->vcpu_id = id;
vcpu->pid = NULL;
- vcpu->halt_poll_ns = 0;
- init_waitqueue_head(&vcpu->wq);
+ init_swait_queue_head(&vcpu->wq);
kvm_async_pf_vcpu_init(vcpu);
vcpu->pre_pcpu = -1;
static void kvm_destroy_devices(struct kvm *kvm)
{
- struct list_head *node, *tmp;
+ struct kvm_device *dev, *tmp;
- list_for_each_safe(node, tmp, &kvm->devices) {
- struct kvm_device *dev =
- list_entry(node, struct kvm_device, vm_node);
-
- list_del(node);
+ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
+ list_del(&dev->vm_node);
dev->ops->destroy(dev);
}
}
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
- if (addr == KVM_HVA_ERR_RO_BAD)
+ if (addr == KVM_HVA_ERR_RO_BAD) {
+ if (writable)
+ *writable = false;
return KVM_PFN_ERR_RO_FAULT;
+ }
- if (kvm_is_error_hva(addr))
+ if (kvm_is_error_hva(addr)) {
+ if (writable)
+ *writable = false;
return KVM_PFN_NOSLOT;
+ }
/* Do not map writable pfn in the readonly memslot. */
if (writable && memslot_is_readonly(slot)) {
static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
{
- int old, val;
+ unsigned int old, val, grow;
old = val = vcpu->halt_poll_ns;
+ grow = READ_ONCE(halt_poll_ns_grow);
/* 10us base */
- if (val == 0 && halt_poll_ns_grow)
+ if (val == 0 && grow)
val = 10000;
else
- val *= halt_poll_ns_grow;
+ val *= grow;
+ if (val > halt_poll_ns)
+ val = halt_poll_ns;
+
vcpu->halt_poll_ns = val;
trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
}
static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
{
- int old, val;
+ unsigned int old, val, shrink;
old = val = vcpu->halt_poll_ns;
- if (halt_poll_ns_shrink == 0)
+ shrink = READ_ONCE(halt_poll_ns_shrink);
+ if (shrink == 0)
val = 0;
else
- val /= halt_poll_ns_shrink;
+ val /= shrink;
vcpu->halt_poll_ns = val;
trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
ktime_t start, cur;
- DEFINE_WAIT(wait);
+ DECLARE_SWAITQUEUE(wait);
bool waited = false;
u64 block_ns;
kvm_arch_vcpu_blocking(vcpu);
for (;;) {
- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
if (kvm_vcpu_check_block(vcpu) < 0)
break;
schedule();
}
- finish_wait(&vcpu->wq, &wait);
+ finish_swait(&vcpu->wq, &wait);
cur = ktime_get();
kvm_arch_vcpu_unblocking(vcpu);
{
int me;
int cpu = vcpu->cpu;
- wait_queue_head_t *wqp;
+ struct swait_queue_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
- if (waitqueue_active(wqp)) {
- wake_up_interruptible(wqp);
+ if (swait_active(wqp)) {
+ swake_up(wqp);
++vcpu->stat.halt_wakeup;
}
continue;
if (vcpu == me)
continue;
- if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+ if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;