Re: [PATCH] kvm: fix race with level interrupts

[Michael S. Tsirkin]

On Wed, Jul 18, 2012 at 04:26:41PM -0600, Alex Williamson wrote:
> On Thu, 2012-07-19 at 00:52 +0300, Michael S. Tsirkin wrote:
> > When more than 1 source id is in use for the same GSI, we have the
> > following race related to handling irq_states:
> > 
> > CPU 0 clears bit in irq_states. CPU 0 reads irq_state as 0.
> > CPU 1 sets bit in irq_states.  CPU 1 calls kvm_ioapic_set_irq(1). CPU 0
> > calls kvm_ioapic_set_irq(0).
> > 
> > Now ioapic thinks the level is 0 but irq_state is not 0.
> > 
> > Note that above is valid behaviour if CPU0 and CPU1 are using different
> > source ids.
> > 
> > Fix by performing all irq_states bitmap handling under pic/ioapic lock.
> > This also removes the need for atomics with irq_states handling.
> > 
> > Reported-by: Gleb Natapov <gleb@xxxxxxxxxx>
> > Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
> > ---
> > 
> > This survives stress testing for me (though I only tried virtio, not
> > device assignment).
> > Avi, Marcelo, though we have not observed this in the field,
> > it's a bugfix so probably 3.5 material?
> > I assume yes so the patch is against 3.5-rc7.
> > Also stable? It's a very old bug.
> > 
> > 
> >  arch/x86/include/asm/kvm_host.h | 15 ++++++++++++++-
> >  arch/x86/kvm/i8259.c            | 14 ++++++++++++--
> >  virt/kvm/ioapic.c               | 13 ++++++++++++-
> >  virt/kvm/ioapic.h               |  4 +++-
> >  virt/kvm/irq_comm.c             | 31 ++++---------------------------
> >  5 files changed, 45 insertions(+), 32 deletions(-)
> > 
> > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> > index db7c1f2..fe6e9f1 100644
> > --- a/arch/x86/include/asm/kvm_host.h
> > +++ b/arch/x86/include/asm/kvm_host.h
> > @@ -802,7 +802,20 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
> >  void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
> >  bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
> >  
> > -int kvm_pic_set_irq(void *opaque, int irq, int level);
> > +static inline int kvm_irq_line_state(unsigned long *irq_state,
> > +				     int irq_source_id, int level)
> 
> This should probably be __kvm_irq_line_state given the calling
> restrictions.

It's such a trivial helper, do we need to split hairs about this?

Look it's not a good time for minor coding style nits.
3.5 is imminent, it's about 1am here and I really don't have time to retest
today, so we'll release another kernel with a bug.

Could you focus on reviewing the functionality and correctness, and
leave ideas for better variable naming aside until 3.6?

> > +{
> > +	/* Logical OR for level trig interrupt */
> > +	if (level)
> > +		__set_bit(irq_source_id, irq_state);
> > +	else
> > +		__clear_bit(irq_source_id, irq_state);
> > +
> > +	return !!(*irq_state);
> > +}
> > +
> > +int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
> > +void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
> >  
> >  void kvm_inject_nmi(struct kvm_vcpu *vcpu);
> >  
> > diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
> > index 81cf4fa..95b504b 100644
> > --- a/arch/x86/kvm/i8259.c
> > +++ b/arch/x86/kvm/i8259.c
> > @@ -188,13 +188,14 @@ void kvm_pic_update_irq(struct kvm_pic *s)
> >  	pic_unlock(s);
> >  }
> >  
> > -int kvm_pic_set_irq(void *opaque, int irq, int level)
> > +int kvm_pic_set_irq(struct kvm_pic *s, int irq, int src_id, int l)
> >  {
> > -	struct kvm_pic *s = opaque;
> >  	int ret = -1;
> > +	int level;
> >  
> >  	pic_lock(s);
> >  	if (irq >= 0 && irq < PIC_NUM_PINS) {
> > +		level = kvm_irq_line_state(&s->irq_states[irq], src_id, l);
> >  		ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
> >  		pic_update_irq(s);
> >  		trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
> > @@ -205,6 +206,15 @@ int kvm_pic_set_irq(void *opaque, int irq, int level)
> >  	return ret;
> >  }
> >  
> > +void kvm_pic_clear_all(struct kvm_pic *s, int src_id)
> > +{
> > +	int i;
> > +	pic_lock(s);
> > +	for (i = 0; i < PIC_NUM_PINS; i++)
> > +		__clear_bit(src_id, &s->irq_states[i]);
> > +	pic_unlock(s);
> > +}
> > +
> >  /*
> >   * acknowledge interrupt 'irq'
> >   */
> > diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
> > index 26fd54d..268b332 100644
> > --- a/virt/kvm/ioapic.c
> > +++ b/virt/kvm/ioapic.c
> > @@ -191,17 +191,19 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
> >  	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
> >  }
> >  
> > -int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
> > +int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int src_id, int l)
> >  {
> >  	u32 old_irr;
> >  	u32 mask = 1 << irq;
> >  	union kvm_ioapic_redirect_entry entry;
> >  	int ret = 1;
> > +	int level;
> >  
> >  	spin_lock(&ioapic->lock);
> >  	old_irr = ioapic->irr;
> >  	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
> >  		entry = ioapic->redirtbl[irq];
> > +		level = kvm_irq_line_state(&ioapic->irq_states[irq], src_id, l);
> >  		level ^= entry.fields.polarity;
> >  		if (!level)
> >  			ioapic->irr &= ~mask;
> > @@ -221,6 +223,15 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
> >  	return ret;
> >  }
> >  
> > +void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int src_id)
> > +{
> > +	int i;
> > +	spin_lock(&ioapic->lock);
> > +	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
> > +		__clear_bit(src_id, &ioapic->irq_states[i]);
> > +	spin_unlock(&ioapic->lock);
> > +}
> > +
> >  static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
> >  				     int trigger_mode)
> >  {
> > diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
> > index 32872a0..a30abfe 100644
> > --- a/virt/kvm/ioapic.h
> > +++ b/virt/kvm/ioapic.h
> > @@ -74,7 +74,9 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
> >  bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
> >  int kvm_ioapic_init(struct kvm *kvm);
> >  void kvm_ioapic_destroy(struct kvm *kvm);
> > -int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
> > +int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
> > +		       int level);
> > +void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
> >  void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
> >  int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
> >  		struct kvm_lapic_irq *irq);
> > diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
> > index 5afb431..83402d7 100644
> > --- a/virt/kvm/irq_comm.c
> > +++ b/virt/kvm/irq_comm.c
> > @@ -33,26 +33,12 @@
> >  
> >  #include "ioapic.h"
> >  
> > -static inline int kvm_irq_line_state(unsigned long *irq_state,
> > -				     int irq_source_id, int level)
> > -{
> > -	/* Logical OR for level trig interrupt */
> > -	if (level)
> > -		set_bit(irq_source_id, irq_state);
> > -	else
> > -		clear_bit(irq_source_id, irq_state);
> > -
> > -	return !!(*irq_state);
> > -}
> > -
> >  static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
> >  			   struct kvm *kvm, int irq_source_id, int level)
> >  {
> >  #ifdef CONFIG_X86
> >  	struct kvm_pic *pic = pic_irqchip(kvm);
> > -	level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin],
> > -				   irq_source_id, level);
> > -	return kvm_pic_set_irq(pic, e->irqchip.pin, level);
> > +	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
> >  #else
> >  	return -1;
> >  #endif
> > @@ -62,10 +48,7 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
> >  			      struct kvm *kvm, int irq_source_id, int level)
> >  {
> >  	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
> > -	level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin],
> > -				   irq_source_id, level);
> > -
> > -	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level);
> > +	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level);
> >  }
> >  
> >  inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
> > @@ -249,8 +232,6 @@ unlock:
> >  
> >  void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
> >  {
> > -	int i;
> > -
> >  	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
> >  
> >  	mutex_lock(&kvm->irq_lock);
> > @@ -263,14 +244,10 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
> >  	if (!irqchip_in_kernel(kvm))
> >  		goto unlock;
> >  
> > -	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) {
> > -		clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]);
> > -		if (i >= 16)
> > -			continue;
> > +	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
> >  #ifdef CONFIG_X86
> > -		clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]);
> > +	kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
> >  #endif
> > -	}
> >  unlock:
> >  	mutex_unlock(&kvm->irq_lock);
> >  }
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/