On Fri, Apr 13, 2018 at 10:20:57AM +0200, Eric Auger wrote:
> Now all the internals are ready to handle multiple redistributor
> regions, let's allow the userspace to register them.
>
> Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
>
> ---
>
> v2 -> v3:
> - early exit if vgic_v3_rdist_region_from_index() fails
> ---
> virt/kvm/arm/vgic/vgic-kvm-device.c | 42 +++++++++++++++++++++++++++++++++++--
> virt/kvm/arm/vgic/vgic-mmio-v3.c | 4 ++--
> virt/kvm/arm/vgic/vgic.h | 9 +++++++-
> 3 files changed, 50 insertions(+), 5 deletions(-)
>
> diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
> index e7b5a86..00e03d3 100644
> --- a/virt/kvm/arm/vgic/vgic-kvm-device.c
> +++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
> @@ -65,7 +65,8 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
> {
> int r = 0;
> struct vgic_dist *vgic = &kvm->arch.vgic;
> - phys_addr_t *addr_ptr, alignment;
> + phys_addr_t *addr_ptr = NULL;
> + phys_addr_t alignment;
> uint64_t undef_value = VGIC_ADDR_UNDEF;
nit: mussed this one before, type should be u64
>
> mutex_lock(&kvm->lock);
> @@ -92,7 +93,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
> if (r)
> break;
> if (write) {
> - r = vgic_v3_set_redist_base(kvm, *addr);
> + r = vgic_v3_set_redist_base(kvm, 0, *addr, 0);
> goto out;
> }
> rdreg = list_first_entry(&vgic->rd_regions,
> @@ -103,6 +104,42 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
> addr_ptr = &rdreg->base;
> break;
> }
> + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION:
> + {
> + struct vgic_redist_region *rdreg;
> + uint8_t index;
> +
we tend to use u8, u32, etc. in the kernel.
> + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
> + if (r)
> + break;
> +
> + index = *addr & KVM_VGIC_V3_RDIST_INDEX_MASK;
> +
> + if (write) {
> + gpa_t base = *addr & KVM_VGIC_V3_RDIST_BASE_MASK;
> + uint32_t count = (*addr & KVM_VGIC_V3_RDIST_COUNT_MASK)
> + >> KVM_VGIC_V3_RDIST_COUNT_SHIFT;
> + uint8_t flags = (*addr & KVM_VGIC_V3_RDIST_FLAGS_MASK)
> + >> KVM_VGIC_V3_RDIST_FLAGS_SHIFT;
> +
> + if (!count || flags)
> + r = -EINVAL;
> + else
> + r = vgic_v3_set_redist_base(kvm, index,
> + base, count);
> + goto out;
> + }
> +
> + rdreg = vgic_v3_rdist_region_from_index(kvm, index);
> + if (!rdreg) {
> + r = -ENODEV;
> + goto out;
> + }
> +
> + *addr_ptr = rdreg->base & index &
> + (uint64_t)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT;
This looks fairly broken, isn't this a clear null pointer dereference?
(If we're making this ioctl read-only using the parameter as both in/out
for set/get, that should also be documented in the API text, then you
should consider writing a small test along with your userspace
implementation to actually test that functionality - otherwise we should
just make this write-only and omit the index part. It could be said
that retrieving what the kernel actually has is a reasonable debug
feature.)
I think you want (notice the | instead of & as well):
*addr = index;
*addr |= rdreg->base;
*addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT;
goto out;
It is then debatable if the addr_ptr construct gets too convoluted when
not used in every case, and if the logic should be embedded into each
case, and the addr_ptr variable dropped. Meh, I don't mind leaving it
for now.
> + break;
> + }
> default:
> r = -ENODEV;
> }
> @@ -674,6 +711,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
> switch (attr->attr) {
> case KVM_VGIC_V3_ADDR_TYPE_DIST:
> case KVM_VGIC_V3_ADDR_TYPE_REDIST:
> + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION:
> return 0;
> }
> break;
> diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
> index df23e66..f603fdf 100644
> --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
> +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
> @@ -770,11 +770,11 @@ static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index,
> return ret;
> }
>
> -int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr)
> +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count)
> {
> int ret;
>
> - ret = vgic_v3_insert_redist_region(kvm, 0, addr, 0);
> + ret = vgic_v3_insert_redist_region(kvm, index, addr, count);
> if (ret)
> return ret;
>
> diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
> index 95b8345..0a95b43 100644
> --- a/virt/kvm/arm/vgic/vgic.h
> +++ b/virt/kvm/arm/vgic/vgic.h
> @@ -96,6 +96,13 @@
> /* we only support 64 kB translation table page size */
> #define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16)
>
> +#define KVM_VGIC_V3_RDIST_INDEX_MASK GENMASK_ULL(11, 0)
> +#define KVM_VGIC_V3_RDIST_FLAGS_MASK GENMASK_ULL(15, 12)
> +#define KVM_VGIC_V3_RDIST_FLAGS_SHIFT 12
> +#define KVM_VGIC_V3_RDIST_BASE_MASK GENMASK_ULL(51, 16)
> +#define KVM_VGIC_V3_RDIST_COUNT_MASK GENMASK_ULL(63, 52)
> +#define KVM_VGIC_V3_RDIST_COUNT_SHIFT 52
> +
> /* Requires the irq_lock to be held by the caller. */
> static inline bool irq_is_pending(struct vgic_irq *irq)
> {
> @@ -201,7 +208,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info);
> int vgic_v3_map_resources(struct kvm *kvm);
> int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
> int vgic_v3_save_pending_tables(struct kvm *kvm);
> -int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr);
> +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count);
> int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
> bool vgic_v3_check_base(struct kvm *kvm);
>
> --
> 2.5.5
>
Thanks,
-Christoffer
