diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-05 16:26:26 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-05 16:26:26 -0800 |
commit | 933425fb0010bd02bd459b41e63082756818ffce (patch) | |
tree | 1cbc6c2035b9dcff8cb265c9ac562cbee7c6bb82 /virt/kvm/arm/arch_timer.c | |
parent | a3e7531535a0c6e5acbaa5436f37933bb471aa95 (diff) | |
parent | a3eaa8649e4c6a6afdafaa04b9114fb230617bb1 (diff) | |
download | op-kernel-dev-933425fb0010bd02bd459b41e63082756818ffce.zip op-kernel-dev-933425fb0010bd02bd459b41e63082756818ffce.tar.gz |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
"First batch of KVM changes for 4.4.
s390:
A bunch of fixes and optimizations for interrupt and time handling.
PPC:
Mostly bug fixes.
ARM:
No big features, but many small fixes and prerequisites including:
- a number of fixes for the arch-timer
- introducing proper level-triggered semantics for the arch-timers
- a series of patches to synchronously halt a guest (prerequisite
for IRQ forwarding)
- some tracepoint improvements
- a tweak for the EL2 panic handlers
- some more VGIC cleanups getting rid of redundant state
x86:
Quite a few changes:
- support for VT-d posted interrupts (i.e. PCI devices can inject
interrupts directly into vCPUs). This introduces a new
component (in virt/lib/) that connects VFIO and KVM together.
The same infrastructure will be used for ARM interrupt
forwarding as well.
- more Hyper-V features, though the main one Hyper-V synthetic
interrupt controller will have to wait for 4.5. These will let
KVM expose Hyper-V devices.
- nested virtualization now supports VPID (same as PCID but for
vCPUs) which makes it quite a bit faster
- for future hardware that supports NVDIMM, there is support for
clflushopt, clwb, pcommit
- support for "split irqchip", i.e. LAPIC in kernel +
IOAPIC/PIC/PIT in userspace, which reduces the attack surface of
the hypervisor
- obligatory smattering of SMM fixes
- on the guest side, stable scheduler clock support was rewritten
to not require help from the hypervisor"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (123 commits)
KVM: VMX: Fix commit which broke PML
KVM: x86: obey KVM_X86_QUIRK_CD_NW_CLEARED in kvm_set_cr0()
KVM: x86: allow RSM from 64-bit mode
KVM: VMX: fix SMEP and SMAP without EPT
KVM: x86: move kvm_set_irq_inatomic to legacy device assignment
KVM: device assignment: remove pointless #ifdefs
KVM: x86: merge kvm_arch_set_irq with kvm_set_msi_inatomic
KVM: x86: zero apic_arb_prio on reset
drivers/hv: share Hyper-V SynIC constants with userspace
KVM: x86: handle SMBASE as physical address in RSM
KVM: x86: add read_phys to x86_emulate_ops
KVM: x86: removing unused variable
KVM: don't pointlessly leave KVM_COMPAT=y in non-KVM configs
KVM: arm/arm64: Merge vgic_set_lr() and vgic_sync_lr_elrsr()
KVM: arm/arm64: Clean up vgic_retire_lr() and surroundings
KVM: arm/arm64: Optimize away redundant LR tracking
KVM: s390: use simple switch statement as multiplexer
KVM: s390: drop useless newline in debugging data
KVM: s390: SCA must not cross page boundaries
KVM: arm: Do not indent the arguments of DECLARE_BITMAP
...
Diffstat (limited to 'virt/kvm/arm/arch_timer.c')
-rw-r--r-- | virt/kvm/arm/arch_timer.c | 173 |
1 files changed, 117 insertions, 56 deletions
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index b9d3a32..21a0ab2 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -28,6 +28,8 @@ #include <kvm/arm_vgic.h> #include <kvm/arm_arch_timer.h> +#include "trace.h" + static struct timecounter *timecounter; static struct workqueue_struct *wqueue; static unsigned int host_vtimer_irq; @@ -59,18 +61,6 @@ static void timer_disarm(struct arch_timer_cpu *timer) } } -static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu) -{ - int ret; - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - - kvm_vgic_set_phys_irq_active(timer->map, true); - ret = kvm_vgic_inject_mapped_irq(vcpu->kvm, vcpu->vcpu_id, - timer->map, - timer->irq->level); - WARN_ON(ret); -} - static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; @@ -111,14 +101,20 @@ static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt) return HRTIMER_NORESTART; } +static bool kvm_timer_irq_can_fire(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + return !(timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) && + (timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE); +} + bool kvm_timer_should_fire(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; cycle_t cval, now; - if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) || - !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE) || - kvm_vgic_get_phys_irq_active(timer->map)) + if (!kvm_timer_irq_can_fire(vcpu)) return false; cval = timer->cntv_cval; @@ -127,12 +123,94 @@ bool kvm_timer_should_fire(struct kvm_vcpu *vcpu) return cval <= now; } +static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level) +{ + int ret; + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + BUG_ON(!vgic_initialized(vcpu->kvm)); + + timer->irq.level = new_level; + trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq, + timer->irq.level); + ret = kvm_vgic_inject_mapped_irq(vcpu->kvm, vcpu->vcpu_id, + timer->map, + timer->irq.level); + WARN_ON(ret); +} + +/* + * Check if there was a change in the timer state (should we raise or lower + * the line level to the GIC). + */ +static void kvm_timer_update_state(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + /* + * If userspace modified the timer registers via SET_ONE_REG before + * the vgic was initialized, we mustn't set the timer->irq.level value + * because the guest would never see the interrupt. Instead wait + * until we call this function from kvm_timer_flush_hwstate. + */ + if (!vgic_initialized(vcpu->kvm)) + return; + + if (kvm_timer_should_fire(vcpu) != timer->irq.level) + kvm_timer_update_irq(vcpu, !timer->irq.level); +} + +/* + * Schedule the background timer before calling kvm_vcpu_block, so that this + * thread is removed from its waitqueue and made runnable when there's a timer + * interrupt to handle. + */ +void kvm_timer_schedule(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + u64 ns; + cycle_t cval, now; + + BUG_ON(timer_is_armed(timer)); + + /* + * No need to schedule a background timer if the guest timer has + * already expired, because kvm_vcpu_block will return before putting + * the thread to sleep. + */ + if (kvm_timer_should_fire(vcpu)) + return; + + /* + * If the timer is not capable of raising interrupts (disabled or + * masked), then there's no more work for us to do. + */ + if (!kvm_timer_irq_can_fire(vcpu)) + return; + + /* The timer has not yet expired, schedule a background timer */ + cval = timer->cntv_cval; + now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; + + ns = cyclecounter_cyc2ns(timecounter->cc, + cval - now, + timecounter->mask, + &timecounter->frac); + timer_arm(timer, ns); +} + +void kvm_timer_unschedule(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + timer_disarm(timer); +} + /** * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu * @vcpu: The vcpu pointer * - * Disarm any pending soft timers, since the world-switch code will write the - * virtual timer state back to the physical CPU. + * Check if the virtual timer has expired while we were running in the host, + * and inject an interrupt if that was the case. */ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) { @@ -140,28 +218,20 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) bool phys_active; int ret; - /* - * We're about to run this vcpu again, so there is no need to - * keep the background timer running, as we're about to - * populate the CPU timer again. - */ - timer_disarm(timer); + kvm_timer_update_state(vcpu); /* - * If the timer expired while we were not scheduled, now is the time - * to inject it. + * If we enter the guest with the virtual input level to the VGIC + * asserted, then we have already told the VGIC what we need to, and + * we don't need to exit from the guest until the guest deactivates + * the already injected interrupt, so therefore we should set the + * hardware active state to prevent unnecessary exits from the guest. + * + * Conversely, if the virtual input level is deasserted, then always + * clear the hardware active state to ensure that hardware interrupts + * from the timer triggers a guest exit. */ - if (kvm_timer_should_fire(vcpu)) - kvm_timer_inject_irq(vcpu); - - /* - * We keep track of whether the edge-triggered interrupt has been - * signalled to the vgic/guest, and if so, we mask the interrupt and - * the physical distributor to prevent the timer from raising a - * physical interrupt whenever we run a guest, preventing forward - * VCPU progress. - */ - if (kvm_vgic_get_phys_irq_active(timer->map)) + if (timer->irq.level) phys_active = true; else phys_active = false; @@ -176,32 +246,20 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) * kvm_timer_sync_hwstate - sync timer state from cpu * @vcpu: The vcpu pointer * - * Check if the virtual timer was armed and either schedule a corresponding - * soft timer or inject directly if already expired. + * Check if the virtual timer has expired while we were running in the guest, + * and inject an interrupt if that was the case. */ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - cycle_t cval, now; - u64 ns; BUG_ON(timer_is_armed(timer)); - if (kvm_timer_should_fire(vcpu)) { - /* - * Timer has already expired while we were not - * looking. Inject the interrupt and carry on. - */ - kvm_timer_inject_irq(vcpu); - return; - } - - cval = timer->cntv_cval; - now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff; - - ns = cyclecounter_cyc2ns(timecounter->cc, cval - now, timecounter->mask, - &timecounter->frac); - timer_arm(timer, ns); + /* + * The guest could have modified the timer registers or the timer + * could have expired, update the timer state. + */ + kvm_timer_update_state(vcpu); } int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, @@ -216,7 +274,7 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, * kvm_vcpu_set_target(). To handle this, we determine * vcpu timer irq number when the vcpu is reset. */ - timer->irq = irq; + timer->irq.irq = irq->irq; /* * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8 @@ -225,6 +283,7 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, * the ARMv7 architecture. */ timer->cntv_ctl = 0; + kvm_timer_update_state(vcpu); /* * Tell the VGIC that the virtual interrupt is tied to a @@ -269,6 +328,8 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) default: return -1; } + + kvm_timer_update_state(vcpu); return 0; } |