Message ID | 20160707171550.14675-5-rkrcmar@redhat.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On 2016/7/8 1:15, Radim Krčmář wrote: > x2APIC supports up to 2^32-1 LAPICs, but most guest in coming years will > have slighly less VCPUs. Dynamic size saves memory at the cost of > turning one constant into a variable. > > apic_map mutex had to be moved before allocation to avoid races with cpu > hotplug. > > Signed-off-by: Radim Krčmář <rkrcmar@redhat.com> > --- > v2: > * replaced size with max_apic_id to minimize chances of overflow [Andrew] > * fixed allocation size [Paolo] > > arch/x86/include/asm/kvm_host.h | 3 ++- > arch/x86/kvm/lapic.c | 18 +++++++++++++----- > arch/x86/kvm/lapic.h | 2 +- > 3 files changed, 16 insertions(+), 7 deletions(-) > > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h > index 3194b19b9c7b..643e3dffcd85 100644 > --- a/arch/x86/include/asm/kvm_host.h > +++ b/arch/x86/include/asm/kvm_host.h > @@ -682,11 +682,12 @@ struct kvm_arch_memory_slot { > struct kvm_apic_map { > struct rcu_head rcu; > u8 mode; > - struct kvm_lapic *phys_map[256]; > + u32 max_apic_id; > union { > struct kvm_lapic *xapic_flat_map[8]; > struct kvm_lapic *xapic_cluster_map[16][4]; > }; > + struct kvm_lapic *phys_map[]; > }; > > /* Hyper-V emulation context */ > diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c > index 9880d03f533d..224fc1c5fcc6 100644 > --- a/arch/x86/kvm/lapic.c > +++ b/arch/x86/kvm/lapic.c > @@ -120,7 +120,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, > switch (map->mode) { > case KVM_APIC_MODE_X2APIC: { > u32 offset = (dest_id >> 16) * 16; > - u32 max_apic_id = ARRAY_SIZE(map->phys_map) - 1; > + u32 max_apic_id = map->max_apic_id; > > if (offset <= max_apic_id) { > u8 cluster_size = min(max_apic_id - offset + 1, 16U); > @@ -152,14 +152,22 @@ static void recalculate_apic_map(struct kvm *kvm) > struct kvm_apic_map *new, *old = NULL; > struct kvm_vcpu *vcpu; > int i; > - > - new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL); > + u32 max_id = 255; > > mutex_lock(&kvm->arch.apic_map_lock); > > + kvm_for_each_vcpu(i, vcpu, kvm) > + if (kvm_apic_present(vcpu)) > + max_id = max(max_id, kvm_apic_id(vcpu->arch.apic)); > + > + new = kzalloc(sizeof(struct kvm_apic_map) + > + sizeof(struct kvm_lapic *) * (max_id + 1), GFP_KERNEL); > + I think this may cause the host runs out of memory if a malicious guest did follow thing: 1. vcpu a is doing apic map recalculation. 2. vcpu b write the apic id with 0xff 3. then vcpu b enable the x2apic: in kvm_lapic_set_base(), we will set apic_base to new value before reset the apic id. 4. vcpu a may see the x2apic enabled in vcpu b plus an old apic id(0xff), and max_id will become (0xff >> 24). > if (!new) > goto out; > > + new->max_apic_id = max_id; > + > kvm_for_each_vcpu(i, vcpu, kvm) { > struct kvm_lapic *apic = vcpu->arch.apic; > struct kvm_lapic **cluster; > @@ -172,7 +180,7 @@ static void recalculate_apic_map(struct kvm *kvm) > aid = kvm_apic_id(apic); > ldr = kvm_lapic_get_reg(apic, APIC_LDR); > > - if (aid < ARRAY_SIZE(new->phys_map)) > + if (aid <= new->max_apic_id) > new->phys_map[aid] = apic; > > if (apic_x2apic_mode(apic)) { > @@ -710,7 +718,7 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, > return false; > > if (irq->dest_mode == APIC_DEST_PHYSICAL) { > - if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) { > + if (irq->dest_id > map->max_apic_id) { > *bitmap = 0; > } else { > *dst = &map->phys_map[irq->dest_id]; > diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h > index 336ba51bb16e..8d811139d2b3 100644 > --- a/arch/x86/kvm/lapic.h > +++ b/arch/x86/kvm/lapic.h > @@ -200,7 +200,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) > return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); > } > > -static inline int kvm_apic_id(struct kvm_lapic *apic) > +static inline u32 kvm_apic_id(struct kvm_lapic *apic) > { > return (kvm_lapic_get_reg(apic, APIC_ID) >> 24) & 0xff; > } >
On 11/07/2016 08:07, Yang Zhang wrote: >> >> mutex_lock(&kvm->arch.apic_map_lock); >> >> + kvm_for_each_vcpu(i, vcpu, kvm) >> + if (kvm_apic_present(vcpu)) >> + max_id = max(max_id, kvm_apic_id(vcpu->arch.apic)); >> + >> + new = kzalloc(sizeof(struct kvm_apic_map) + >> + sizeof(struct kvm_lapic *) * (max_id + 1), >> GFP_KERNEL); >> + > > I think this may cause the host runs out of memory if a malicious guest > did follow thing: > 1. vcpu a is doing apic map recalculation. > 2. vcpu b write the apic id with 0xff > 3. then vcpu b enable the x2apic: in kvm_lapic_set_base(), we will set > apic_base to new value before reset the apic id. > 4. vcpu a may see the x2apic enabled in vcpu b plus an old apic > id(0xff), and max_id will become (0xff >> 24). The bug is not really here but in patch 6---but you're right nevertheless! I guess the easiest solution is to replace kvm_apic_id with a field in struct kvm_lapic, which is already shifted right by 24 in xAPIC mode. It can be added easily in patch 6 itself, it's like 3 new lines of code because all reads and writes go through kvm_apic_id and kvm_apic_set_id; the kvm_apic_id wrapper can be kept for simplicity. Thanks again! Paolo -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3194b19b9c7b..643e3dffcd85 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -682,11 +682,12 @@ struct kvm_arch_memory_slot { struct kvm_apic_map { struct rcu_head rcu; u8 mode; - struct kvm_lapic *phys_map[256]; + u32 max_apic_id; union { struct kvm_lapic *xapic_flat_map[8]; struct kvm_lapic *xapic_cluster_map[16][4]; }; + struct kvm_lapic *phys_map[]; }; /* Hyper-V emulation context */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9880d03f533d..224fc1c5fcc6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -120,7 +120,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, switch (map->mode) { case KVM_APIC_MODE_X2APIC: { u32 offset = (dest_id >> 16) * 16; - u32 max_apic_id = ARRAY_SIZE(map->phys_map) - 1; + u32 max_apic_id = map->max_apic_id; if (offset <= max_apic_id) { u8 cluster_size = min(max_apic_id - offset + 1, 16U); @@ -152,14 +152,22 @@ static void recalculate_apic_map(struct kvm *kvm) struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; int i; - - new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL); + u32 max_id = 255; mutex_lock(&kvm->arch.apic_map_lock); + kvm_for_each_vcpu(i, vcpu, kvm) + if (kvm_apic_present(vcpu)) + max_id = max(max_id, kvm_apic_id(vcpu->arch.apic)); + + new = kzalloc(sizeof(struct kvm_apic_map) + + sizeof(struct kvm_lapic *) * (max_id + 1), GFP_KERNEL); + if (!new) goto out; + new->max_apic_id = max_id; + kvm_for_each_vcpu(i, vcpu, kvm) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_lapic **cluster; @@ -172,7 +180,7 @@ static void recalculate_apic_map(struct kvm *kvm) aid = kvm_apic_id(apic); ldr = kvm_lapic_get_reg(apic, APIC_LDR); - if (aid < ARRAY_SIZE(new->phys_map)) + if (aid <= new->max_apic_id) new->phys_map[aid] = apic; if (apic_x2apic_mode(apic)) { @@ -710,7 +718,7 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, return false; if (irq->dest_mode == APIC_DEST_PHYSICAL) { - if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) { + if (irq->dest_id > map->max_apic_id) { *bitmap = 0; } else { *dst = &map->phys_map[irq->dest_id]; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 336ba51bb16e..8d811139d2b3 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -200,7 +200,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } -static inline int kvm_apic_id(struct kvm_lapic *apic) +static inline u32 kvm_apic_id(struct kvm_lapic *apic) { return (kvm_lapic_get_reg(apic, APIC_ID) >> 24) & 0xff; }
x2APIC supports up to 2^32-1 LAPICs, but most guest in coming years will have slighly less VCPUs. Dynamic size saves memory at the cost of turning one constant into a variable. apic_map mutex had to be moved before allocation to avoid races with cpu hotplug. Signed-off-by: Radim Krčmář <rkrcmar@redhat.com> --- v2: * replaced size with max_apic_id to minimize chances of overflow [Andrew] * fixed allocation size [Paolo] arch/x86/include/asm/kvm_host.h | 3 ++- arch/x86/kvm/lapic.c | 18 +++++++++++++----- arch/x86/kvm/lapic.h | 2 +- 3 files changed, 16 insertions(+), 7 deletions(-)