Hi Amit. Thanks for the patch and incorporating V3 review comments. Further review comments inline below:
Amit Machhiwal <[email protected]> writes: > Introduce a new capability and ioctl to expose CPU compatibility modes > supported by the host processor for nested guests. > > On IBM POWER systems, newer processor generations (N) can operate in > compatibility modes corresponding to earlier generations, like (N-1) and > (N-2). This is particularly relevant for nested virtualization, where > nested KVM guests may need to run with a specific processor compatibility > level. > > Introduce KVM_CAP_PPC_COMPAT_CAPS capability and the corresponding > KVM_PPC_GET_COMPAT_CAPS vm ioctl. The ioctl returns a bitmap describing > the compatibility modes supported by the host in respective bit numbers, > allowing userspace (e.g., QEMU) to select an appropriate compatibility > level when configuring nested KVM guests. > > The ioctl handling is added in kvm_arch_vm_ioctl() and retrieves host > CPU compatibility capabilities via a PowerPC-specific backend > implementation when available. The implementation validates the structure > size from userspace to ensure forward compatibility and returns > appropriate error codes (EINVAL for invalid size, EFAULT for copy > failures, ENOTTY if backend is not implemented). The struct > kvm_ppc_compat_caps includes a size field to support future ABI > extensions. > > Suggested-by: Vaibhav Jain <[email protected]> > Signed-off-by: Amit Machhiwal <[email protected]> > --- > arch/powerpc/include/asm/kvm_ppc.h | 1 + > arch/powerpc/include/uapi/asm/kvm.h | 7 ++++++ > arch/powerpc/kvm/powerpc.c | 35 +++++++++++++++++++++++++++++ > include/uapi/linux/kvm.h | 4 ++++ > 4 files changed, 47 insertions(+) > > diff --git a/arch/powerpc/include/asm/kvm_ppc.h > b/arch/powerpc/include/asm/kvm_ppc.h > index 0953f2daa466..169ea6a7fbad 100644 > --- a/arch/powerpc/include/asm/kvm_ppc.h > +++ b/arch/powerpc/include/asm/kvm_ppc.h > @@ -319,6 +319,7 @@ struct kvmppc_ops { > bool (*hash_v3_possible)(void); > int (*create_vm_debugfs)(struct kvm *kvm); > int (*create_vcpu_debugfs)(struct kvm_vcpu *vcpu, struct dentry > *debugfs_dentry); > + int (*get_compat_caps)(struct kvm_ppc_compat_caps *host_caps); > }; > > extern struct kvmppc_ops *kvmppc_hv_ops; > diff --git a/arch/powerpc/include/uapi/asm/kvm.h > b/arch/powerpc/include/uapi/asm/kvm.h > index 077c5437f521..8a38be6c3b03 100644 > --- a/arch/powerpc/include/uapi/asm/kvm.h > +++ b/arch/powerpc/include/uapi/asm/kvm.h > @@ -437,6 +437,13 @@ struct kvm_ppc_cpu_char { > __u64 behaviour_mask; /* valid bits in behaviour */ > }; > > +/* For KVM_PPC_GET_COMPAT_CAPS */ > +struct kvm_ppc_compat_caps { > + __u64 flags; /* Reserved for future use */ > + __u64 size; /* Size of this structure */ Suggesting moving the 'size' as the first member of the struct. That way copying the struct from userspace becomes bit easier. > + __u64 compat_capabilities; /* Capabilities supported by the host */ > +}; > + > /* > * Values for character and character_mask. > * These are identical to the values used by H_GET_CPU_CHARACTERISTICS. > diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c > index 98de68379b18..9153b0034b45 100644 > --- a/arch/powerpc/kvm/powerpc.c > +++ b/arch/powerpc/kvm/powerpc.c > @@ -701,6 +701,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long > ext) > } > } > break; > +#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) > + case KVM_CAP_PPC_COMPAT_CAPS: > + r = 0; > + if (kvmhv_on_pseries()) > + r = 1; > + break; > +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ > default: > r = 0; > break; > @@ -2467,6 +2474,34 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int > ioctl, unsigned long arg) > r = kvm->arch.kvm_ops->svm_off(kvm); > break; > } > + case KVM_PPC_GET_COMPAT_CAPS: { > + struct kvm_ppc_compat_caps host_caps; > + u64 user_size; > + > + r = -EFAULT; > + /* First, get the size field from userspace to validate */ > + if (copy_from_user(&user_size, &((struct kvm_ppc_compat_caps > + __user *)argp)->size, sizeof(user_size))) { move the struct size member to the first field. That way from_from_user() call is simplified and you wont have to do some wired pointer arithmetic. > + goto out; > + } > + > + /* Validate size - must be at least the current structure size > */ > + r = -EINVAL; > + if (user_size < sizeof(host_caps)) > + goto out; Check should be strengthed to if (user_size != sizeof(host_caps)) So that in case used space sends a struct larger than what kernel knows abt it will be rejected. This will prevent surprises in future in case VMM sends a larger struct expecting kernel to know abt it but an older kernel only knows abt older smaller sized struct. Also look at the review comment below. > + > + r = -ENOTTY; > + memset(&host_caps, 0, sizeof(host_caps)); > + if (!kvm->arch.kvm_ops->get_compat_caps) > + goto out; > + > + r = kvm->arch.kvm_ops->get_compat_caps(&host_caps); > + /* Set the actual size of the structure we're returning */ > + host_caps.size = sizeof(host_caps); > + if (!r && copy_to_user(argp, &host_caps, sizeof(host_caps))) > + r = -EFAULT; You are allowing a future userspace VMM to potentially send a larger 'struct kvm_ppc_compat_caps' that what kernel knows about. This makes error handling in userspace bit involved since there might be some fields in the 'struct kvm_ppc_compat_caps' given from userspace may remain un-initialized when userspace sees it. So please mention this subtle behaviour should be mentioned in patch description and also update it the doc in the later patch. > + break; > + } > default: { > struct kvm *kvm = filp->private_data; > r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg); > diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h > index 6c8afa2047bf..1788a0068662 100644 > --- a/include/uapi/linux/kvm.h > +++ b/include/uapi/linux/kvm.h > @@ -996,6 +996,7 @@ struct kvm_enable_cap { > #define KVM_CAP_S390_USER_OPEREXEC 246 > #define KVM_CAP_S390_KEYOP 247 > #define KVM_CAP_S390_VSIE_ESAMODE 248 > +#define KVM_CAP_PPC_COMPAT_CAPS 249 > > struct kvm_irq_routing_irqchip { > __u32 irqchip; > @@ -1349,6 +1350,9 @@ struct kvm_s390_keyop { > #define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xe2, struct kvm_device_attr) > #define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xe3, struct kvm_device_attr) > > +/* Available with KVM_CAP_PPC_COMPAT_CAPS */ > +#define KVM_PPC_GET_COMPAT_CAPS _IOR(KVMIO, 0xe4, struct > kvm_ppc_compat_caps) > + > /* > * ioctls for vcpu fds > */ > -- > 2.50.1 (Apple Git-155) > > -- Cheers ~ Vaibhav
