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 | |
parent | a3e7531535a0c6e5acbaa5436f37933bb471aa95 (diff) | |
parent | a3eaa8649e4c6a6afdafaa04b9114fb230617bb1 (diff) |
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')
-rw-r--r-- | virt/Makefile | 1 | ||||
-rw-r--r-- | virt/kvm/Kconfig | 5 | ||||
-rw-r--r-- | virt/kvm/arm/arch_timer.c | 173 | ||||
-rw-r--r-- | virt/kvm/arm/trace.h | 63 | ||||
-rw-r--r-- | virt/kvm/arm/vgic-v2.c | 6 | ||||
-rw-r--r-- | virt/kvm/arm/vgic-v3.c | 6 | ||||
-rw-r--r-- | virt/kvm/arm/vgic.c | 308 | ||||
-rw-r--r-- | virt/kvm/async_pf.c | 4 | ||||
-rw-r--r-- | virt/kvm/eventfd.c | 190 | ||||
-rw-r--r-- | virt/kvm/irqchip.c | 18 | ||||
-rw-r--r-- | virt/kvm/kvm_main.c | 11 | ||||
-rw-r--r-- | virt/lib/Kconfig | 2 | ||||
-rw-r--r-- | virt/lib/Makefile | 1 | ||||
-rw-r--r-- | virt/lib/irqbypass.c | 257 |
14 files changed, 681 insertions, 364 deletions
diff --git a/virt/Makefile b/virt/Makefile new file mode 100644 index 000000000000..be783472ac81 --- /dev/null +++ b/virt/Makefile @@ -0,0 +1 @@ +obj-y += lib/ diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index e2c876d5a03b..7a79b6853583 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -46,4 +46,7 @@ config KVM_GENERIC_DIRTYLOG_READ_PROTECT config KVM_COMPAT def_bool y - depends on COMPAT && !S390 + depends on KVM && COMPAT && !S390 + +config HAVE_KVM_IRQ_BYPASS + bool diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index b9d3a32cbc04..21a0ab2d8919 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; } diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h new file mode 100644 index 000000000000..37d8b98867d5 --- /dev/null +++ b/virt/kvm/arm/trace.h @@ -0,0 +1,63 @@ +#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_H + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm + +/* + * Tracepoints for vgic + */ +TRACE_EVENT(vgic_update_irq_pending, + TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level), + TP_ARGS(vcpu_id, irq, level), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_id ) + __field( __u32, irq ) + __field( bool, level ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->irq = irq; + __entry->level = level; + ), + + TP_printk("VCPU: %ld, IRQ %d, level: %d", + __entry->vcpu_id, __entry->irq, __entry->level) +); + +/* + * Tracepoints for arch_timer + */ +TRACE_EVENT(kvm_timer_update_irq, + TP_PROTO(unsigned long vcpu_id, __u32 irq, int level), + TP_ARGS(vcpu_id, irq, level), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_id ) + __field( __u32, irq ) + __field( int, level ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->irq = irq; + __entry->level = level; + ), + + TP_printk("VCPU: %ld, IRQ %d, level %d", + __entry->vcpu_id, __entry->irq, __entry->level) +); + +#endif /* _TRACE_KVM_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c index 8d7b04db8471..ff02f08df74d 100644 --- a/virt/kvm/arm/vgic-v2.c +++ b/virt/kvm/arm/vgic-v2.c @@ -79,11 +79,7 @@ static void vgic_v2_set_lr(struct kvm_vcpu *vcpu, int lr, lr_val |= (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT); vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val; -} -static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, - struct vgic_lr lr_desc) -{ if (!(lr_desc.state & LR_STATE_MASK)) vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr); else @@ -158,6 +154,7 @@ static void vgic_v2_enable(struct kvm_vcpu *vcpu) * anyway. */ vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0; + vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr = ~0; /* Get the show on the road... */ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN; @@ -166,7 +163,6 @@ static void vgic_v2_enable(struct kvm_vcpu *vcpu) static const struct vgic_ops vgic_v2_ops = { .get_lr = vgic_v2_get_lr, .set_lr = vgic_v2_set_lr, - .sync_lr_elrsr = vgic_v2_sync_lr_elrsr, .get_elrsr = vgic_v2_get_elrsr, .get_eisr = vgic_v2_get_eisr, .clear_eisr = vgic_v2_clear_eisr, diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c index 7dd5d62f10a1..487d6357b7e7 100644 --- a/virt/kvm/arm/vgic-v3.c +++ b/virt/kvm/arm/vgic-v3.c @@ -112,11 +112,7 @@ static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr, } vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)] = lr_val; -} -static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, - struct vgic_lr lr_desc) -{ if (!(lr_desc.state & LR_STATE_MASK)) vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr); else @@ -193,6 +189,7 @@ static void vgic_v3_enable(struct kvm_vcpu *vcpu) * anyway. */ vgic_v3->vgic_vmcr = 0; + vgic_v3->vgic_elrsr = ~0; /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible @@ -211,7 +208,6 @@ static void vgic_v3_enable(struct kvm_vcpu *vcpu) static const struct vgic_ops vgic_v3_ops = { .get_lr = vgic_v3_get_lr, .set_lr = vgic_v3_set_lr, - .sync_lr_elrsr = vgic_v3_sync_lr_elrsr, .get_elrsr = vgic_v3_get_elrsr, .get_eisr = vgic_v3_get_eisr, .clear_eisr = vgic_v3_clear_eisr, diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 30489181922d..533538385d5d 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -34,6 +34,9 @@ #include <asm/kvm.h> #include <kvm/iodev.h> +#define CREATE_TRACE_POINTS +#include "trace.h" + /* * How the whole thing works (courtesy of Christoffer Dall): * @@ -102,11 +105,13 @@ #include "vgic.h" static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); -static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); +static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu); static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); +static u64 vgic_get_elrsr(struct kvm_vcpu *vcpu); static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, int virt_irq); +static int compute_pending_for_cpu(struct kvm_vcpu *vcpu); static const struct vgic_ops *vgic_ops; static const struct vgic_params *vgic; @@ -357,6 +362,11 @@ static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq) struct vgic_dist *dist = &vcpu->kvm->arch.vgic; vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0); + if (!vgic_dist_irq_get_level(vcpu, irq)) { + vgic_dist_irq_clear_pending(vcpu, irq); + if (!compute_pending_for_cpu(vcpu)) + clear_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu); + } } static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq) @@ -531,34 +541,6 @@ bool vgic_handle_set_pending_reg(struct kvm *kvm, return false; } -/* - * If a mapped interrupt's state has been modified by the guest such that it - * is no longer active or pending, without it have gone through the sync path, - * then the map->active field must be cleared so the interrupt can be taken - * again. - */ -static void vgic_handle_clear_mapped_irq(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct list_head *root; - struct irq_phys_map_entry *entry; - struct irq_phys_map *map; - - rcu_read_lock(); - - /* Check for PPIs */ - root = &vgic_cpu->irq_phys_map_list; - list_for_each_entry_rcu(entry, root, entry) { - map = &entry->map; - - if (!vgic_dist_irq_is_pending(vcpu, map->virt_irq) && - !vgic_irq_is_active(vcpu, map->virt_irq)) - map->active = false; - } - - rcu_read_unlock(); -} - bool vgic_handle_clear_pending_reg(struct kvm *kvm, struct kvm_exit_mmio *mmio, phys_addr_t offset, int vcpu_id) @@ -589,7 +571,6 @@ bool vgic_handle_clear_pending_reg(struct kvm *kvm, vcpu_id, offset); vgic_reg_access(mmio, reg, offset, mode); - vgic_handle_clear_mapped_irq(kvm_get_vcpu(kvm, vcpu_id)); vgic_update_state(kvm); return true; } @@ -627,7 +608,6 @@ bool vgic_handle_clear_active_reg(struct kvm *kvm, ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT); if (mmio->is_write) { - vgic_handle_clear_mapped_irq(kvm_get_vcpu(kvm, vcpu_id)); vgic_update_state(kvm); return true; } @@ -684,10 +664,9 @@ bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio, vgic_reg_access(mmio, &val, offset, ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); if (mmio->is_write) { - if (offset < 8) { - *reg = ~0U; /* Force PPIs/SGIs to 1 */ + /* Ignore writes to read-only SGI and PPI bits */ + if (offset < 8) return false; - } val = vgic_cfg_compress(val); if (offset & 4) { @@ -713,9 +692,11 @@ bool vgic_handle_cfg_reg(u32 *reg, struct kvm_exit_mmio *mmio, void vgic_unqueue_irqs(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + u64 elrsr = vgic_get_elrsr(vcpu); + unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr); int i; - for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) { + for_each_clear_bit(i, elrsr_ptr, vgic_cpu->nr_lr) { struct vgic_lr lr = vgic_get_lr(vcpu, i); /* @@ -736,30 +717,14 @@ void vgic_unqueue_irqs(struct kvm_vcpu *vcpu) * interrupt then move the active state to the * distributor tracking bit. */ - if (lr.state & LR_STATE_ACTIVE) { + if (lr.state & LR_STATE_ACTIVE) vgic_irq_set_active(vcpu, lr.irq); - lr.state &= ~LR_STATE_ACTIVE; - } /* * Reestablish the pending state on the distributor and the - * CPU interface. It may have already been pending, but that - * is fine, then we are only setting a few bits that were - * already set. + * CPU interface and mark the LR as free for other use. */ - if (lr.state & LR_STATE_PENDING) { - vgic_dist_irq_set_pending(vcpu, lr.irq); - lr.state &= ~LR_STATE_PENDING; - } - - vgic_set_lr(vcpu, i, lr); - - /* - * Mark the LR as free for other use. - */ - BUG_ON(lr.state & LR_STATE_MASK); - vgic_retire_lr(i, lr.irq, vcpu); - vgic_irq_clear_queued(vcpu, lr.irq); + vgic_retire_lr(i, vcpu); /* Finally update the VGIC state. */ vgic_update_state(vcpu->kvm); @@ -1067,12 +1032,6 @@ static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, vgic_ops->set_lr(vcpu, lr, vlr); } -static void vgic_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr, - struct vgic_lr vlr) -{ - vgic_ops->sync_lr_elrsr(vcpu, lr, vlr); -} - static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu) { return vgic_ops->get_elrsr(vcpu); @@ -1118,25 +1077,23 @@ static inline void vgic_enable(struct kvm_vcpu *vcpu) vgic_ops->enable(vcpu); } -static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu) +static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu) { - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr); + vgic_irq_clear_queued(vcpu, vlr.irq); + /* * We must transfer the pending state back to the distributor before * retiring the LR, otherwise we may loose edge-triggered interrupts. */ if (vlr.state & LR_STATE_PENDING) { - vgic_dist_irq_set_pending(vcpu, irq); + vgic_dist_irq_set_pending(vcpu, vlr.irq); vlr.hwirq = 0; } vlr.state = 0; vgic_set_lr(vcpu, lr_nr, vlr); - clear_bit(lr_nr, vgic_cpu->lr_used); - vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY; - vgic_sync_lr_elrsr(vcpu, lr_nr, vlr); } /* @@ -1150,17 +1107,15 @@ static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu) */ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu) { - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + u64 elrsr = vgic_get_elrsr(vcpu); + unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr); int lr; - for_each_set_bit(lr, vgic_cpu->lr_used, vgic->nr_lr) { + for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) { struct vgic_lr vlr = vgic_get_lr(vcpu, lr); - if (!vgic_irq_is_enabled(vcpu, vlr.irq)) { - vgic_retire_lr(lr, vlr.irq, vcpu); - if (vgic_irq_is_queued(vcpu, vlr.irq)) - vgic_irq_clear_queued(vcpu, vlr.irq); - } + if (!vgic_irq_is_enabled(vcpu, vlr.irq)) + vgic_retire_lr(lr, vcpu); } } @@ -1200,7 +1155,6 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, } vgic_set_lr(vcpu, lr_nr, vlr); - vgic_sync_lr_elrsr(vcpu, lr_nr, vlr); } /* @@ -1210,8 +1164,9 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, */ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) { - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + u64 elrsr = vgic_get_elrsr(vcpu); + unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr); struct vgic_lr vlr; int lr; @@ -1222,28 +1177,22 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) kvm_debug("Queue IRQ%d\n", irq); - lr = vgic_cpu->vgic_irq_lr_map[irq]; - /* Do we have an active interrupt for the same CPUID? */ - if (lr != LR_EMPTY) { + for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) { vlr = vgic_get_lr(vcpu, lr); - if (vlr.source == sgi_source_id) { + if (vlr.irq == irq && vlr.source == sgi_source_id) { kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq); - BUG_ON(!test_bit(lr, vgic_cpu->lr_used)); vgic_queue_irq_to_lr(vcpu, irq, lr, vlr); return true; } } /* Try to use another LR for this interrupt */ - lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used, - vgic->nr_lr); + lr = find_first_bit(elrsr_ptr, vgic->nr_lr); if (lr >= vgic->nr_lr) return false; kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id); - vgic_cpu->vgic_irq_lr_map[irq] = lr; - set_bit(lr, vgic_cpu->lr_used); vlr.irq = irq; vlr.source = sgi_source_id; @@ -1338,12 +1287,60 @@ epilog: } } +static int process_queued_irq(struct kvm_vcpu *vcpu, + int lr, struct vgic_lr vlr) +{ + int pending = 0; + + /* + * If the IRQ was EOIed (called from vgic_process_maintenance) or it + * went from active to non-active (called from vgic_sync_hwirq) it was + * also ACKed and we we therefore assume we can clear the soft pending + * state (should it had been set) for this interrupt. + * + * Note: if the IRQ soft pending state was set after the IRQ was + * acked, it actually shouldn't be cleared, but we have no way of + * knowing that unless we start trapping ACKs when the soft-pending + * state is set. + */ + vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq); + + /* + * Tell the gic to start sampling this interrupt again. + */ + vgic_irq_clear_queued(vcpu, vlr.irq); + + /* Any additional pending interrupt? */ + if (vgic_irq_is_edge(vcpu, vlr.irq)) { + BUG_ON(!(vlr.state & LR_HW)); + pending = vgic_dist_irq_is_pending(vcpu, vlr.irq); + } else { + if (vgic_dist_irq_get_level(vcpu, vlr.irq)) { + vgic_cpu_irq_set(vcpu, vlr.irq); + pending = 1; + } else { + vgic_dist_irq_clear_pending(vcpu, vlr.irq); + vgic_cpu_irq_clear(vcpu, vlr.irq); + } + } + + /* + * Despite being EOIed, the LR may not have + * been marked as empty. + */ + vlr.state = 0; + vlr.hwirq = 0; + vgic_set_lr(vcpu, lr, vlr); + + return pending; +} + static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) { u32 status = vgic_get_interrupt_status(vcpu); struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - bool level_pending = false; struct kvm *kvm = vcpu->kvm; + int level_pending = 0; kvm_debug("STATUS = %08x\n", status); @@ -1358,54 +1355,22 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) { struct vgic_lr vlr = vgic_get_lr(vcpu, lr); - WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq)); - spin_lock(&dist->lock); - vgic_irq_clear_queued(vcpu, vlr.irq); + WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq)); WARN_ON(vlr.state & LR_STATE_MASK); - vlr.state = 0; - vgic_set_lr(vcpu, lr, vlr); - /* - * If the IRQ was EOIed it was also ACKed and we we - * therefore assume we can clear the soft pending - * state (should it had been set) for this interrupt. - * - * Note: if the IRQ soft pending state was set after - * the IRQ was acked, it actually shouldn't be - * cleared, but we have no way of knowing that unless - * we start trapping ACKs when the soft-pending state - * is set. - */ - vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq); /* * kvm_notify_acked_irq calls kvm_set_irq() - * to reset the IRQ level. Need to release the - * lock for kvm_set_irq to grab it. + * to reset the IRQ level, which grabs the dist->lock + * so we call this before taking the dist->lock. */ - spin_unlock(&dist->lock); - kvm_notify_acked_irq(kvm, 0, vlr.irq - VGIC_NR_PRIVATE_IRQS); - spin_lock(&dist->lock); - - /* Any additional pending interrupt? */ - if (vgic_dist_irq_get_level(vcpu, vlr.irq)) { - vgic_cpu_irq_set(vcpu, vlr.irq); - level_pending = true; - } else { - vgic_dist_irq_clear_pending(vcpu, vlr.irq); - vgic_cpu_irq_clear(vcpu, vlr.irq); - } + spin_lock(&dist->lock); + level_pending |= process_queued_irq(vcpu, lr, vlr); spin_unlock(&dist->lock); - - /* - * Despite being EOIed, the LR may not have - * been marked as empty. - */ - vgic_sync_lr_elrsr(vcpu, lr, vlr); } } @@ -1426,35 +1391,40 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) /* * Save the physical active state, and reset it to inactive. * - * Return 1 if HW interrupt went from active to inactive, and 0 otherwise. + * Return true if there's a pending forwarded interrupt to queue. */ -static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr) +static bool vgic_sync_hwirq(struct kvm_vcpu *vcpu, int lr, struct vgic_lr vlr) { + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct irq_phys_map *map; + bool phys_active; + bool level_pending; int ret; if (!(vlr.state & LR_HW)) - return 0; + return false; map = vgic_irq_map_search(vcpu, vlr.irq); BUG_ON(!map); ret = irq_get_irqchip_state(map->irq, IRQCHIP_STATE_ACTIVE, - &map->active); + &phys_active); WARN_ON(ret); - if (map->active) + if (phys_active) return 0; - return 1; + spin_lock(&dist->lock); + level_pending = process_queued_irq(vcpu, lr, vlr); + spin_unlock(&dist->lock); + return level_pending; } /* Sync back the VGIC state after a guest run */ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; u64 elrsr; unsigned long *elrsr_ptr; @@ -1462,40 +1432,18 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) bool level_pending; level_pending = vgic_process_maintenance(vcpu); - elrsr = vgic_get_elrsr(vcpu); - elrsr_ptr = u64_to_bitmask(&elrsr); /* Deal with HW interrupts, and clear mappings for empty LRs */ for (lr = 0; lr < vgic->nr_lr; lr++) { - struct vgic_lr vlr; - - if (!test_bit(lr, vgic_cpu->lr_used)) - continue; - - vlr = vgic_get_lr(vcpu, lr); - if (vgic_sync_hwirq(vcpu, vlr)) { - /* - * So this is a HW interrupt that the guest - * EOI-ed. Clean the LR state and allow the - * interrupt to be sampled again. - */ - vlr.state = 0; - vlr.hwirq = 0; - vgic_set_lr(vcpu, lr, vlr); - vgic_irq_clear_queued(vcpu, vlr.irq); - set_bit(lr, elrsr_ptr); - } - - if (!test_bit(lr, elrsr_ptr)) - continue; - - clear_bit(lr, vgic_cpu->lr_used); + struct vgic_lr vlr = vgic_get_lr(vcpu, lr); + level_pending |= vgic_sync_hwirq(vcpu, lr, vlr); BUG_ON(vlr.irq >= dist->nr_irqs); - vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY; } /* Check if we still have something up our sleeve... */ + elrsr = vgic_get_elrsr(vcpu); + elrsr_ptr = u64_to_bitmask(&elrsr); pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr); if (level_pending || pending < vgic->nr_lr) set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu); @@ -1585,6 +1533,8 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid, int enabled; bool ret = true, can_inject = true; + trace_vgic_update_irq_pending(cpuid, irq_num, level); + if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020)) return -EINVAL; @@ -1864,30 +1814,6 @@ static void vgic_free_phys_irq_map_rcu(struct rcu_head *rcu) } /** - * kvm_vgic_get_phys_irq_active - Return the active state of a mapped IRQ - * - * Return the logical active state of a mapped interrupt. This doesn't - * necessarily reflects the current HW state. - */ -bool kvm_vgic_get_phys_irq_active(struct irq_phys_map *map) -{ - BUG_ON(!map); - return map->active; -} - -/** - * kvm_vgic_set_phys_irq_active - Set the active state of a mapped IRQ - * - * Set the logical active state of a mapped interrupt. This doesn't - * immediately affects the HW state. - */ -void kvm_vgic_set_phys_irq_active(struct irq_phys_map *map, bool active) -{ - BUG_ON(!map); - map->active = active; -} - -/** * kvm_vgic_unmap_phys_irq - Remove a virtual to physical IRQ mapping * @vcpu: The VCPU pointer * @map: The pointer to a mapping obtained through kvm_v |