| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1385585007.25738.138.camel@ul30vt.home>
Date: Wed, 27 Nov 2013 13:43:27 -0700
From: Alex Williamson <alex.williamson@...hat.com>
To: Alexey Kardashevskiy <aik@...abs.ru>
Cc: linuxppc-dev@...ts.ozlabs.org, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org, kvm-ppc@...r.kernel.org
Subject: Re: [PATCH v4] KVM: PPC: vfio kvm device: support spapr tce
On Mon, 2013-11-25 at 19:49 +1100, Alexey Kardashevskiy wrote:
> In addition to the external VFIO user API, a VFIO KVM device
> has been introduced recently.
>
> sPAPR TCE IOMMU is para-virtualized and the guest does map/unmap
> via hypercalls which take a logical bus id (LIOBN) as a target IOMMU
> identifier. LIOBNs are made up and linked to IOMMU groups by the user
> space. In order to accelerate IOMMU operations in the KVM, we need
> to tell KVM the information about LIOBN-to-group mapping.
>
> For that, a new KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE_LIOBN parameter
> is added. It accepts a pair of a VFIO group fd and LIOBN.
>
> This also adds a new kvm_vfio_find_group_by_liobn() function which
> receives kvm struct, LIOBN and a callback. As it increases the IOMMU
> group use counter, the KVMr is required to pass a callback which
> called when the VFIO group is about to be removed VFIO-KVM tracking so
> the KVM is able to call iommu_group_put() to release the IOMMU group.
>
> The KVM uses kvm_vfio_find_group_by_liobn() once per KVM run and caches
> the result in kvm_arch. iommu_group_put() for all groups will be called
> when KVM finishes (in the SPAPR TCE in KVM enablement patch).
>
> Signed-off-by: Alexey Kardashevskiy <aik@...abs.ru>
> ---
> Changes:
> v4:
> * fixed few bugs
> * changed kvm_vfio_find_group_by_liobn() to return informative errors
>
> v3:
> * total rework
> * added a release callback into kvm_vfio_find_group_by_liobn so now
> the user of the API can get a notification if the group is about to
> disappear
> ---
> Documentation/virtual/kvm/devices/vfio.txt | 19 ++++-
> arch/powerpc/kvm/Kconfig | 1 +
> arch/powerpc/kvm/Makefile | 3 +
> include/linux/kvm_host.h | 18 +++++
> include/uapi/linux/kvm.h | 7 ++
> virt/kvm/vfio.c | 116 ++++++++++++++++++++++++++++-
> 6 files changed, 161 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
> index ef51740..7ecb3b2 100644
> --- a/Documentation/virtual/kvm/devices/vfio.txt
> +++ b/Documentation/virtual/kvm/devices/vfio.txt
> @@ -16,7 +16,22 @@ Groups:
>
> KVM_DEV_VFIO_GROUP attributes:
> KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
> + kvm_device_attr.addr points to an int32_t file descriptor
> + for the VFIO group.
> +
> KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
> + kvm_device_attr.addr points to an int32_t file descriptor
> + for the VFIO group.
> +
> + KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE_LIOBN: sets a liobn for a VFIO group
> + kvm_device_attr.addr points to a struct:
> + struct kvm_vfio_spapr_tce_liobn {
> + __u32 argsz;
> + __u32 fd;
__s32 per the definition below
> + __u32 liobn;
> + };
> + where
> + @argsz is a struct size;
> + @fd is a file descriptor for a VFIO group;
> + @liobn is a logical bus id to be associated with the group.
>
> -For each, kvm_device_attr.addr points to an int32_t file descriptor
> -for the VFIO group.
> diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
> index 9a50d82..f463958 100644
> --- a/arch/powerpc/kvm/Kconfig
> +++ b/arch/powerpc/kvm/Kconfig
> @@ -60,6 +60,7 @@ config KVM_BOOK3S_64
> select KVM_BOOK3S_64_HANDLER
> select KVM
> select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
> + select KVM_VFIO
> ---help---
> Support running unmodified book3s_64 and book3s_32 guest kernels
> in virtual machines on book3s_64 host processors.
> diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
> index 6646c95..2438d2e 100644
> --- a/arch/powerpc/kvm/Makefile
> +++ b/arch/powerpc/kvm/Makefile
> @@ -87,6 +87,9 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
> kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
> book3s_xics.o
>
> +kvm-book3s_64-objs-$(CONFIG_KVM_VFIO) += \
> + $(KVM)/vfio.o \
> +
> kvm-book3s_64-module-objs := \
> $(KVM)/kvm_main.o \
> $(KVM)/eventfd.o \
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 88ff96a..1d2ad5e 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -1112,5 +1112,23 @@ static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
> }
>
> #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
> +
> +typedef void (*kvm_vfio_release_group_callback)(struct kvm *kvm,
> + unsigned long liobn);
Seems like a bit of namespace pollution that this is named generically
but is specific to spapr/liobn. Is this ever needed w/o
CONFIG_SPAPR_TCE_IOMMU?
> +#if defined(CONFIG_KVM_VFIO) && defined(CONFIG_SPAPR_TCE_IOMMU)
> +
> +extern struct iommu_group *kvm_vfio_find_group_by_liobn(struct kvm *kvm,
> + unsigned long liobn, kvm_vfio_release_group_callback cb);
> +
> +#else
> +
> +static inline struct iommu_group *kvm_vfio_find_group_by_liobn(struct kvm *kvm,
> + unsigned long liobn, ikvm_vfio_release_group_callback cb)
> +{
> + return NULL;
The real function returns ERR_PTR(-errno) now, this should too.
> +}
> +#endif /* CONFIG_KVM_VFIO && CONFIG_SPAPR_TCE_IOMMU */
Why isn't this
#ifdef CONFIG_SPAPR_TCE_IOMMU
#ifdef CONFIG_KVM_VFIO
extern...
#else
static inline...
#endif
#endif
?
> +
> #endif
>
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 7c1a349..51d5464 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -847,6 +847,13 @@ struct kvm_device_attr {
> #define KVM_DEV_VFIO_GROUP 1
> #define KVM_DEV_VFIO_GROUP_ADD 1
> #define KVM_DEV_VFIO_GROUP_DEL 2
> +#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE_LIOBN 3
> +
> +struct kvm_vfio_spapr_tce_liobn {
> + __u32 argsz;
> + __s32 fd;
> + __u32 liobn;
> +};
>
> /*
> * ioctls for VM fds
> diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
> index ca4260e..ddc945d 100644
> --- a/virt/kvm/vfio.c
> +++ b/virt/kvm/vfio.c
> @@ -22,6 +22,12 @@
> struct kvm_vfio_group {
> struct list_head node;
> struct vfio_group *vfio_group;
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> + struct {
> + unsigned long liobn;
> + kvm_vfio_release_group_callback cb;
> + } spapr_tce;
> +#endif
> };
>
> struct kvm_vfio {
> @@ -59,6 +65,51 @@ static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
> symbol_put(vfio_group_put_external_user);
> }
>
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +struct iommu_group *kvm_vfio_find_group_by_liobn(struct kvm *kvm,
> + unsigned long liobn, kvm_vfio_release_group_callback cb)
> +{
> + struct kvm_vfio_group *kvg;
> + int group_id;
> + struct iommu_group *grp;
> + struct kvm_vfio *kv = NULL;
> + struct kvm_device *tmp;
> +
> + if (!cb)
> + return ERR_PTR(-EINVAL);
> +
> + /* Find a VFIO KVM device */
> + list_for_each_entry(tmp, &kvm->devices, vm_node) {
> + if (tmp->ops != &kvm_vfio_ops)
> + continue;
> +
> + kv = tmp->private;
> + break;
> + }
> +
> + if (!kv)
> + return ERR_PTR(-EIO);
> +
I'm getting tired of noting that this ignores kv->lock...
> + /* Find a group */
> + list_for_each_entry(kvg, &kv->group_list, node) {
> + if (kvg->spapr_tce.liobn != liobn)
> + continue;
> +
> + if (kvg->spapr_tce.cb)
> + return ERR_PTR(-EBUSY);
> +
> + kvg->spapr_tce.cb = cb;
> + group_id = vfio_external_user_iommu_id(kvg->vfio_group);
> + grp = iommu_group_get_by_id(group_id);
> +
> + return grp;
> + }
> +
> + return ERR_PTR(-ENODEV);
> +}
> +EXPORT_SYMBOL_GPL(kvm_vfio_find_group_by_liobn);
> +#endif
> +
> /*
> * Groups can use the same or different IOMMU domains. If the same then
> * adding a new group may change the coherency of groups we've previously
> @@ -140,7 +191,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
>
> list_add_tail(&kvg->node, &kv->group_list);
> kvg->vfio_group = vfio_group;
> -
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> + kvg->spapr_tce.liobn = -1;
> +#endif
> mutex_unlock(&kv->lock);
>
> kvm_vfio_update_coherency(dev);
> @@ -170,6 +223,11 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
> continue;
>
> list_del(&kvg->node);
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> + if (kvg->spapr_tce.cb)
> + kvg->spapr_tce.cb(dev->kvm,
> + kvg->spapr_tce.liobn);
> +#endif
> kvm_vfio_group_put_external_user(kvg->vfio_group);
> kfree(kvg);
> ret = 0;
> @@ -183,6 +241,59 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
> kvm_vfio_update_coherency(dev);
>
> return ret;
> +
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> + case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE_LIOBN: {
> + struct kvm_vfio_spapr_tce_liobn param;
> + unsigned long minsz;
> + struct kvm_vfio *kv = dev->private;
> + struct vfio_group *vfio_group;
> + struct kvm_vfio_group *kvg;
> + struct fd f;
> +
> + minsz = offsetofend(struct kvm_vfio_spapr_tce_liobn, liobn);
> +
> + if (copy_from_user(¶m, (void __user *)arg, minsz))
> + return -EFAULT;
> +
> + if (param.argsz < minsz)
> + return -EINVAL;
> +
> + f = fdget(param.fd);
> + if (!f.file)
> + return -EBADF;
> +
> + vfio_group = kvm_vfio_group_get_external_user(f.file);
> + fdput(f);
> +
> + if (IS_ERR(vfio_group))
> + return PTR_ERR(vfio_group);
> +
> + ret = -ENOENT;
> +
> + mutex_lock(&kv->lock);
> +
> + list_for_each_entry(kvg, &kv->group_list, node) {
> + if (kvg->vfio_group != vfio_group)
> + continue;
> +
> + if (kvg->spapr_tce.liobn != -1) {
> + ret = -EBUSY;
> + break;
> + }
> +
> + kvg->spapr_tce.liobn = param.liobn;
> + ret = 0;
> + break;
> + }
> +
> + mutex_unlock(&kv->lock);
> +
> + kvm_vfio_group_put_external_user(vfio_group);
> +
> + return ret;
> + }
> +#endif /* CONFIG_SPAPR_TCE_IOMMU */
> }
>
> return -ENXIO;
> @@ -207,6 +318,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
> switch (attr->attr) {
> case KVM_DEV_VFIO_GROUP_ADD:
> case KVM_DEV_VFIO_GROUP_DEL:
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> + case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE_LIOBN:
> +#endif
> return 0;
> }
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists