KVM/ARM updates for v4.9-rc4
- Kick the vcpu when a pending interrupt becomes pending again - Prevent access to invalid interrupt registers - Invalid TLBs when two vcpus from the same VM share a CPU -----BEGIN PGP SIGNATURE----- iQIyBAABCAAcBQJYHNMTFRxtYXJjLnp5bmdpZXJAYXJtLmNvbQAKCRAj0NC60T16 Q1WDD/9d5KfQ3dWiLtBXbeD3w2K0gXknwLAMsCCAdhgkCdLenxSBjlB7lmVYi1lZ pTnshnR4HC0P3yW3bA78J7LZnUzJg72pq/S5K/om9KylVUdXz9WzQ3u+XyB3KTFW b+viTUK3mqose67UcBSKGfFEWpIOmJ/nZVvWAIaUTg49btxnetKjyhv2Ux744Hm/ Jba3trcA4m8RPJ8Vu6mIfd6gkTXzSkQaN2wGVaEFhCFHOPDCQHjcdspe20Ig9fmY kTXEBe4r0sC+8fXoymEM6TDQFWB8WthIIqfeIJ3FgfoETKrwmyJ23YfLAh49m1cB nFpyy/lr9PNsOjJKXFi84pzx6l8U/CDslnBm5klYTT2kFc3stKbyDtIILvUOwKl8 n9UZSO8NGhOpKscGXLzO/CmIO+wgL15LTsxYsOh3HK7KjzocspQpxyD7pPWN8CUI M2IGLvYMzCaBAOzs6WO4P9xlJRNtUMK8lvAthnBiCeE2Nnu3Oajf8krR4DZmBcQh Q/GOACa1kuBMfqmWNrCVq3UNiFLxxAseShgxq9/E/dNe20daXOnxSaRGdRzTvAQF dRBEtHXdY0qDgLz3tVzBdTTmx3M2k4B4/t+VxnsFFVlvbr0OyOozvFH42tGeTw5t IBoXP9x87+Rpl6P6wW+ICketXQMRmdl40JXNjR96sXN94Y/Z4A== =vj/s -----END PGP SIGNATURE----- Merge tag 'kvm-arm-for-v4.9-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD KVM/ARM updates for v4.9-rc4 - Kick the vcpu when a pending interrupt becomes pending again - Prevent access to invalid interrupt registers - Invalid TLBs when two vcpus from the same VM share a CPU
This commit is contained in:
commit
05d36a7dff
|
@ -66,6 +66,7 @@ extern char __kvm_hyp_vector[];
|
|||
extern void __kvm_flush_vm_context(void);
|
||||
extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
|
||||
extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
|
||||
extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
|
||||
|
||||
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
|
||||
|
||||
|
|
|
@ -57,6 +57,9 @@ struct kvm_arch {
|
|||
/* VTTBR value associated with below pgd and vmid */
|
||||
u64 vttbr;
|
||||
|
||||
/* The last vcpu id that ran on each physical CPU */
|
||||
int __percpu *last_vcpu_ran;
|
||||
|
||||
/* Timer */
|
||||
struct arch_timer_kvm timer;
|
||||
|
||||
|
|
|
@ -71,6 +71,7 @@
|
|||
#define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0)
|
||||
#define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0)
|
||||
#define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0)
|
||||
#define TLBIALL __ACCESS_CP15(c8, 0, c7, 0)
|
||||
#define TLBIALLNSNHIS __ACCESS_CP15(c8, 4, c3, 4)
|
||||
#define PRRR __ACCESS_CP15(c10, 0, c2, 0)
|
||||
#define NMRR __ACCESS_CP15(c10, 0, c2, 1)
|
||||
|
|
|
@ -114,11 +114,18 @@ void kvm_arch_check_processor_compat(void *rtn)
|
|||
*/
|
||||
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
|
||||
{
|
||||
int ret = 0;
|
||||
int ret, cpu;
|
||||
|
||||
if (type)
|
||||
return -EINVAL;
|
||||
|
||||
kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
|
||||
if (!kvm->arch.last_vcpu_ran)
|
||||
return -ENOMEM;
|
||||
|
||||
for_each_possible_cpu(cpu)
|
||||
*per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
|
||||
|
||||
ret = kvm_alloc_stage2_pgd(kvm);
|
||||
if (ret)
|
||||
goto out_fail_alloc;
|
||||
|
@ -141,6 +148,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
|
|||
out_free_stage2_pgd:
|
||||
kvm_free_stage2_pgd(kvm);
|
||||
out_fail_alloc:
|
||||
free_percpu(kvm->arch.last_vcpu_ran);
|
||||
kvm->arch.last_vcpu_ran = NULL;
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
@ -168,6 +177,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
|
|||
{
|
||||
int i;
|
||||
|
||||
free_percpu(kvm->arch.last_vcpu_ran);
|
||||
kvm->arch.last_vcpu_ran = NULL;
|
||||
|
||||
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
|
||||
if (kvm->vcpus[i]) {
|
||||
kvm_arch_vcpu_free(kvm->vcpus[i]);
|
||||
|
@ -312,6 +324,19 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
|
|||
|
||||
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
|
||||
{
|
||||
int *last_ran;
|
||||
|
||||
last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
|
||||
|
||||
/*
|
||||
* We might get preempted before the vCPU actually runs, but
|
||||
* over-invalidation doesn't affect correctness.
|
||||
*/
|
||||
if (*last_ran != vcpu->vcpu_id) {
|
||||
kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
|
||||
*last_ran = vcpu->vcpu_id;
|
||||
}
|
||||
|
||||
vcpu->cpu = cpu;
|
||||
vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
|
||||
|
||||
|
|
|
@ -55,6 +55,21 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
|
|||
__kvm_tlb_flush_vmid(kvm);
|
||||
}
|
||||
|
||||
void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
|
||||
|
||||
/* Switch to requested VMID */
|
||||
write_sysreg(kvm->arch.vttbr, VTTBR);
|
||||
isb();
|
||||
|
||||
write_sysreg(0, TLBIALL);
|
||||
dsb(nsh);
|
||||
isb();
|
||||
|
||||
write_sysreg(0, VTTBR);
|
||||
}
|
||||
|
||||
void __hyp_text __kvm_flush_vm_context(void)
|
||||
{
|
||||
write_sysreg(0, TLBIALLNSNHIS);
|
||||
|
|
|
@ -54,6 +54,7 @@ extern char __kvm_hyp_vector[];
|
|||
extern void __kvm_flush_vm_context(void);
|
||||
extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
|
||||
extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
|
||||
extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
|
||||
|
||||
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
|
||||
|
||||
|
|
|
@ -62,6 +62,9 @@ struct kvm_arch {
|
|||
/* VTTBR value associated with above pgd and vmid */
|
||||
u64 vttbr;
|
||||
|
||||
/* The last vcpu id that ran on each physical CPU */
|
||||
int __percpu *last_vcpu_ran;
|
||||
|
||||
/* The maximum number of vCPUs depends on the used GIC model */
|
||||
int max_vcpus;
|
||||
|
||||
|
|
|
@ -128,7 +128,7 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
|
|||
return v;
|
||||
}
|
||||
|
||||
#define kern_hyp_va(v) (typeof(v))(__kern_hyp_va((unsigned long)(v)))
|
||||
#define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v))))
|
||||
|
||||
/*
|
||||
* We currently only support a 40bit IPA.
|
||||
|
|
|
@ -64,6 +64,21 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
|
|||
write_sysreg(0, vttbr_el2);
|
||||
}
|
||||
|
||||
void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
|
||||
|
||||
/* Switch to requested VMID */
|
||||
write_sysreg(kvm->arch.vttbr, vttbr_el2);
|
||||
isb();
|
||||
|
||||
asm volatile("tlbi vmalle1" : : );
|
||||
dsb(nsh);
|
||||
isb();
|
||||
|
||||
write_sysreg(0, vttbr_el2);
|
||||
}
|
||||
|
||||
void __hyp_text __kvm_flush_vm_context(void)
|
||||
{
|
||||
dsb(ishst);
|
||||
|
|
|
@ -453,17 +453,33 @@ struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev)
|
|||
return container_of(dev, struct vgic_io_device, dev);
|
||||
}
|
||||
|
||||
static bool check_region(const struct vgic_register_region *region,
|
||||
static bool check_region(const struct kvm *kvm,
|
||||
const struct vgic_register_region *region,
|
||||
gpa_t addr, int len)
|
||||
{
|
||||
if ((region->access_flags & VGIC_ACCESS_8bit) && len == 1)
|
||||
return true;
|
||||
if ((region->access_flags & VGIC_ACCESS_32bit) &&
|
||||
len == sizeof(u32) && !(addr & 3))
|
||||
return true;
|
||||
if ((region->access_flags & VGIC_ACCESS_64bit) &&
|
||||
len == sizeof(u64) && !(addr & 7))
|
||||
return true;
|
||||
int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
|
||||
|
||||
switch (len) {
|
||||
case sizeof(u8):
|
||||
flags = VGIC_ACCESS_8bit;
|
||||
break;
|
||||
case sizeof(u32):
|
||||
flags = VGIC_ACCESS_32bit;
|
||||
break;
|
||||
case sizeof(u64):
|
||||
flags = VGIC_ACCESS_64bit;
|
||||
break;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
|
||||
if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) {
|
||||
if (!region->bits_per_irq)
|
||||
return true;
|
||||
|
||||
/* Do we access a non-allocated IRQ? */
|
||||
return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
@ -477,7 +493,7 @@ static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
|
|||
|
||||
region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
|
||||
addr - iodev->base_addr);
|
||||
if (!region || !check_region(region, addr, len)) {
|
||||
if (!region || !check_region(vcpu->kvm, region, addr, len)) {
|
||||
memset(val, 0, len);
|
||||
return 0;
|
||||
}
|
||||
|
@ -510,10 +526,7 @@ static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
|
|||
|
||||
region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
|
||||
addr - iodev->base_addr);
|
||||
if (!region)
|
||||
return 0;
|
||||
|
||||
if (!check_region(region, addr, len))
|
||||
if (!region || !check_region(vcpu->kvm, region, addr, len))
|
||||
return 0;
|
||||
|
||||
switch (iodev->iodev_type) {
|
||||
|
|
|
@ -50,15 +50,15 @@ extern struct kvm_io_device_ops kvm_io_gic_ops;
|
|||
#define VGIC_ADDR_IRQ_MASK(bits) (((bits) * 1024 / 8) - 1)
|
||||
|
||||
/*
|
||||
* (addr & mask) gives us the byte offset for the INT ID, so we want to
|
||||
* divide this with 'bytes per irq' to get the INT ID, which is given
|
||||
* by '(bits) / 8'. But we do this with fixed-point-arithmetic and
|
||||
* take advantage of the fact that division by a fraction equals
|
||||
* multiplication with the inverted fraction, and scale up both the
|
||||
* numerator and denominator with 8 to support at most 64 bits per IRQ:
|
||||
* (addr & mask) gives us the _byte_ offset for the INT ID.
|
||||
* We multiply this by 8 the get the _bit_ offset, then divide this by
|
||||
* the number of bits to learn the actual INT ID.
|
||||
* But instead of a division (which requires a "long long div" implementation),
|
||||
* we shift by the binary logarithm of <bits>.
|
||||
* This assumes that <bits> is a power of two.
|
||||
*/
|
||||
#define VGIC_ADDR_TO_INTID(addr, bits) (((addr) & VGIC_ADDR_IRQ_MASK(bits)) * \
|
||||
64 / (bits) / 8)
|
||||
8 >> ilog2(bits))
|
||||
|
||||
/*
|
||||
* Some VGIC registers store per-IRQ information, with a different number
|
||||
|
|
|
@ -273,6 +273,18 @@ retry:
|
|||
* no more work for us to do.
|
||||
*/
|
||||
spin_unlock(&irq->irq_lock);
|
||||
|
||||
/*
|
||||
* We have to kick the VCPU here, because we could be
|
||||
* queueing an edge-triggered interrupt for which we
|
||||
* get no EOI maintenance interrupt. In that case,
|
||||
* while the IRQ is already on the VCPU's AP list, the
|
||||
* VCPU could have EOI'ed the original interrupt and
|
||||
* won't see this one until it exits for some other
|
||||
* reason.
|
||||
*/
|
||||
if (vcpu)
|
||||
kvm_vcpu_kick(vcpu);
|
||||
return false;
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in New Issue