#include <asm/traps.h>
#include <linux/hardirq.h>
+ #include <linux/pkeys.h>
#define CREATE_TRACE_POINTS
#include <asm/trace/fpu.h>
return this_cpu_read(in_kernel_fpu);
}
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
static bool interrupted_kernel_fpu_idle(void)
{
- if (kernel_fpu_disabled())
- return false;
-
- if (use_eager_fpu())
- return true;
-
- return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+ return !kernel_fpu_disabled();
}
/*
*/
copy_fpregs_to_fpstate(fpu);
} else {
- this_cpu_write(fpu_fpregs_owner_ctx, NULL);
- __fpregs_activate_hw();
+ __cpu_invalidate_fpregs_state();
}
}
EXPORT_SYMBOL(__kernel_fpu_begin);
if (fpu->fpregs_active)
copy_kernel_to_fpregs(&fpu->state);
- else
- __fpregs_deactivate_hw();
kernel_fpu_enable();
}
trace_x86_fpu_before_save(fpu);
if (fpu->fpregs_active) {
if (!copy_fpregs_to_fpstate(fpu)) {
- if (use_eager_fpu())
- copy_kernel_to_fpregs(&fpu->state);
- else
- fpregs_deactivate(fpu);
+ copy_kernel_to_fpregs(&fpu->state);
}
}
trace_x86_fpu_after_save(fpu);
int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
{
- dst_fpu->counter = 0;
dst_fpu->fpregs_active = 0;
dst_fpu->last_cpu = -1;
* Don't let 'init optimized' areas of the XSAVE area
* leak into the child task:
*/
- if (use_eager_fpu())
- memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
+ memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
/*
* Save current FPU registers directly into the child
memcpy(&src_fpu->state, &dst_fpu->state,
fpu_kernel_xstate_size);
- if (use_eager_fpu())
- copy_kernel_to_fpregs(&src_fpu->state);
- else
- fpregs_deactivate(src_fpu);
+ copy_kernel_to_fpregs(&src_fpu->state);
}
preempt_enable();
if (fpu->fpstate_active) {
/* Invalidate any lazy state: */
- fpu->last_cpu = -1;
+ __fpu_invalidate_fpregs_state(fpu);
} else {
fpstate_init(&fpu->state);
trace_x86_fpu_init_state(fpu);
* ensures we will not be lazy and skip a XRSTOR in the
* future.
*/
- fpu->last_cpu = -1;
+ __fpu_invalidate_fpregs_state(fpu);
}
/*
trace_x86_fpu_before_restore(fpu);
fpregs_activate(fpu);
copy_kernel_to_fpregs(&fpu->state);
- fpu->counter++;
trace_x86_fpu_after_restore(fpu);
kernel_fpu_enable();
}
void fpu__drop(struct fpu *fpu)
{
preempt_disable();
- fpu->counter = 0;
if (fpu->fpregs_active) {
/* Ignore delayed exceptions from user space */
copy_kernel_to_fxregs(&init_fpstate.fxsave);
else
copy_kernel_to_fregs(&init_fpstate.fsave);
+
+ if (boot_cpu_has(X86_FEATURE_OSPKE))
+ copy_init_pkru_to_fpregs();
}
/*
{
WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */
- if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
+ if (!static_cpu_has(X86_FEATURE_FPU)) {
/* FPU state will be reallocated lazily at the first use. */
fpu__drop(fpu);
} else {
static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
{
- u64 curr_offset = kvm_x86_ops->read_tsc_offset(vcpu);
+ u64 curr_offset = vcpu->arch.tsc_offset;
vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
}
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
+ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+ {
+ kvm_x86_ops->write_tsc_offset(vcpu, offset);
+ vcpu->arch.tsc_offset = offset;
+ }
+
void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
struct kvm *kvm = vcpu->kvm;
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_compute_tsc_offset(vcpu, data);
- ns = get_kernel_ns();
+ ns = ktime_get_boot_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
if (vcpu->arch.virtual_tsc_khz) {
if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated)
update_ia32_tsc_adjust_msr(vcpu, offset);
- kvm_x86_ops->write_tsc_offset(vcpu, offset);
+ kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
#endif
}
+ static u64 __get_kvmclock_ns(struct kvm *kvm)
+ {
+ struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
+ struct kvm_arch *ka = &kvm->arch;
+ s64 ns;
+
+ if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
+ u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+ ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
+ } else {
+ ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+ }
+
+ return ns;
+ }
+
+ u64 get_kvmclock_ns(struct kvm *kvm)
+ {
+ unsigned long flags;
+ s64 ns;
+
+ local_irq_save(flags);
+ ns = __get_kvmclock_ns(kvm);
+ local_irq_restore(flags);
+
+ return ns;
+ }
+
+ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
+ {
+ struct kvm_vcpu_arch *vcpu = &v->arch;
+ struct pvclock_vcpu_time_info guest_hv_clock;
+
+ if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+ &guest_hv_clock, sizeof(guest_hv_clock))))
+ return;
+
+ /* This VCPU is paused, but it's legal for a guest to read another
+ * VCPU's kvmclock, so we really have to follow the specification where
+ * it says that version is odd if data is being modified, and even after
+ * it is consistent.
+ *
+ * Version field updates must be kept separate. This is because
+ * kvm_write_guest_cached might use a "rep movs" instruction, and
+ * writes within a string instruction are weakly ordered. So there
+ * are three writes overall.
+ *
+ * As a small optimization, only write the version field in the first
+ * and third write. The vcpu->pv_time cache is still valid, because the
+ * version field is the first in the struct.
+ */
+ BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+
+ vcpu->hv_clock.version = guest_hv_clock.version + 1;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
+
+ smp_wmb();
+
+ /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
+ vcpu->hv_clock.flags |= (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
+
+ if (vcpu->pvclock_set_guest_stopped_request) {
+ vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
+ vcpu->pvclock_set_guest_stopped_request = false;
+ }
+
+ trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
+
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock));
+
+ smp_wmb();
+
+ vcpu->hv_clock.version++;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
+ }
+
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
unsigned long flags, tgt_tsc_khz;
struct kvm_arch *ka = &v->kvm->arch;
s64 kernel_ns;
u64 tsc_timestamp, host_tsc;
- struct pvclock_vcpu_time_info guest_hv_clock;
u8 pvclock_flags;
bool use_master_clock;
}
if (!use_master_clock) {
host_tsc = rdtsc();
- kernel_ns = get_kernel_ns();
+ kernel_ns = ktime_get_boot_ns();
}
tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
local_irq_restore(flags);
- if (!vcpu->pv_time_enabled)
- return 0;
+ /* With all the info we got, fill in the values */
if (kvm_has_tsc_control)
tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
vcpu->hw_tsc_khz = tgt_tsc_khz;
}
- /* With all the info we got, fill in the values */
vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
vcpu->last_guest_tsc = tsc_timestamp;
- if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
- &guest_hv_clock, sizeof(guest_hv_clock))))
- return 0;
-
- /* This VCPU is paused, but it's legal for a guest to read another
- * VCPU's kvmclock, so we really have to follow the specification where
- * it says that version is odd if data is being modified, and even after
- * it is consistent.
- *
- * Version field updates must be kept separate. This is because
- * kvm_write_guest_cached might use a "rep movs" instruction, and
- * writes within a string instruction are weakly ordered. So there
- * are three writes overall.
- *
- * As a small optimization, only write the version field in the first
- * and third write. The vcpu->pv_time cache is still valid, because the
- * version field is the first in the struct.
- */
- BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
-
- vcpu->hv_clock.version = guest_hv_clock.version + 1;
- kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock.version));
-
- smp_wmb();
-
- /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
- pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
-
- if (vcpu->pvclock_set_guest_stopped_request) {
- pvclock_flags |= PVCLOCK_GUEST_STOPPED;
- vcpu->pvclock_set_guest_stopped_request = false;
- }
-
/* If the host uses TSC clocksource, then it is stable */
+ pvclock_flags = 0;
if (use_master_clock)
pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
vcpu->hv_clock.flags = pvclock_flags;
- trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
-
- kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock));
-
- smp_wmb();
-
- vcpu->hv_clock.version++;
- kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock.version));
+ if (vcpu->pv_time_enabled)
+ kvm_setup_pvclock_page(v);
+ if (v == kvm_get_vcpu(v->kvm, 0))
+ kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
return 0;
}
if (check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
- kvm_x86_ops->write_tsc_offset(vcpu, offset);
+ kvm_vcpu_write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
if (kvm_lapic_hv_timer_in_use(vcpu) &&
case KVM_SET_CLOCK: {
struct kvm_clock_data user_ns;
u64 now_ns;
- s64 delta;
r = -EFAULT;
if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
r = 0;
local_irq_disable();
- now_ns = get_kernel_ns();
- delta = user_ns.clock - now_ns;
+ now_ns = __get_kvmclock_ns(kvm);
+ kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
local_irq_enable();
- kvm->arch.kvmclock_offset = delta;
kvm_gen_update_masterclock(kvm);
break;
}
struct kvm_clock_data user_ns;
u64 now_ns;
- local_irq_disable();
- now_ns = get_kernel_ns();
- user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
- local_irq_enable();
+ now_ns = get_kvmclock_ns(kvm);
+ user_ns.clock = now_ns;
user_ns.flags = 0;
memset(&user_ns.pad, 0, sizeof(user_ns.pad));
kvm_put_guest_xcr0(vcpu);
- /* Interrupt is enabled by handle_external_intr() */
kvm_x86_ops->handle_external_intr(vcpu);
++vcpu->stat.exits;
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
- if (!vcpu->guest_fpu_loaded) {
- vcpu->fpu_counter = 0;
+ if (!vcpu->guest_fpu_loaded)
return;
- }
vcpu->guest_fpu_loaded = 0;
copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
__kernel_fpu_end();
++vcpu->stat.fpu_reload;
- /*
- * If using eager FPU mode, or if the guest is a frequent user
- * of the FPU, just leave the FPU active for next time.
- * 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 (!use_eager_fpu()) {
- if (++vcpu->fpu_counter < 5)
- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
- }
trace_kvm_fpu(0);
}
* before any KVM threads can be running. Unfortunately, we can't
* bring the TSCs fully up to date with real time, as we aren't yet far
* enough into CPU bringup that we know how much real time has actually
- * elapsed; our helper function, get_kernel_ns() will be using boot
+ * elapsed; our helper function, ktime_get_boot_ns() will be using boot
* variables that haven't been updated yet.
*
* So we simply find the maximum observed TSC above, then record the
mutex_init(&kvm->arch.apic_map_lock);
spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+ kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
pvclock_update_vm_gtod_copy(kvm);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
projects / linux.git / commitdiff