| Message ID | d4680b02ff88b2687cbb807afd8eb47784dd3a33.1588711355.git.ashish.kalra@amd.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Add AMD SEV guest live migration support | expand |
On Tue, May 5, 2020 at 2:17 PM Ashish Kalra <Ashish.Kalra@amd.com> wrote: > > From: Brijesh Singh <Brijesh.Singh@amd.com> > > The ioctl can be used to retrieve page encryption bitmap for a given > gfn range. > > Return the correct bitmap as per the number of pages being requested > by the user. Ensure that we only copy bmap->num_pages bytes in the > userspace buffer, if bmap->num_pages is not byte aligned we read > the trailing bits from the userspace and copy those bits as is. > > Cc: Thomas Gleixner <tglx@linutronix.de> > Cc: Ingo Molnar <mingo@redhat.com> > Cc: "H. Peter Anvin" <hpa@zytor.com> > Cc: Paolo Bonzini <pbonzini@redhat.com> > Cc: "Radim Krčmář" <rkrcmar@redhat.com> > Cc: Joerg Roedel <joro@8bytes.org> > Cc: Borislav Petkov <bp@suse.de> > Cc: Tom Lendacky <thomas.lendacky@amd.com> > Cc: x86@kernel.org > Cc: kvm@vger.kernel.org > Cc: linux-kernel@vger.kernel.org > Reviewed-by: Venu Busireddy <venu.busireddy@oracle.com> > Signed-off-by: Brijesh Singh <brijesh.singh@amd.com> > Signed-off-by: Ashish Kalra <ashish.kalra@amd.com> > --- > Documentation/virt/kvm/api.rst | 27 +++++++++++++ > arch/x86/include/asm/kvm_host.h | 2 + > arch/x86/kvm/svm/sev.c | 70 +++++++++++++++++++++++++++++++++ > arch/x86/kvm/svm/svm.c | 1 + > arch/x86/kvm/svm/svm.h | 1 + > arch/x86/kvm/x86.c | 12 ++++++ > include/uapi/linux/kvm.h | 12 ++++++ > 7 files changed, 125 insertions(+) > > diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst > index efbbe570aa9b..ecad84086892 100644 > --- a/Documentation/virt/kvm/api.rst > +++ b/Documentation/virt/kvm/api.rst > @@ -4636,6 +4636,33 @@ This ioctl resets VCPU registers and control structures according to > the clear cpu reset definition in the POP. However, the cpu is not put > into ESA mode. This reset is a superset of the initial reset. > > +4.125 KVM_GET_PAGE_ENC_BITMAP (vm ioctl) > +--------------------------------------- > + > +:Capability: basic > +:Architectures: x86 > +:Type: vm ioctl > +:Parameters: struct kvm_page_enc_bitmap (in/out) > +:Returns: 0 on success, -1 on error > + > +/* for KVM_GET_PAGE_ENC_BITMAP */ > +struct kvm_page_enc_bitmap { > + __u64 start_gfn; > + __u64 num_pages; > + union { > + void __user *enc_bitmap; /* one bit per page */ > + __u64 padding2; > + }; > +}; > + > +The encrypted VMs have the concept of private and shared pages. The private > +pages are encrypted with the guest-specific key, while the shared pages may > +be encrypted with the hypervisor key. The KVM_GET_PAGE_ENC_BITMAP can > +be used to get the bitmap indicating whether the guest page is private > +or shared. The bitmap can be used during the guest migration. If the page > +is private then the userspace need to use SEV migration commands to transmit > +the page. > + > > 4.125 KVM_S390_PV_COMMAND > ------------------------- > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h > index 4a8ee22f4f5b..9e428befb6a4 100644 > --- a/arch/x86/include/asm/kvm_host.h > +++ b/arch/x86/include/asm/kvm_host.h > @@ -1256,6 +1256,8 @@ struct kvm_x86_ops { > int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); > int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa, > unsigned long sz, unsigned long mode); > + int (*get_page_enc_bitmap)(struct kvm *kvm, > + struct kvm_page_enc_bitmap *bmap); > }; > > struct kvm_x86_init_ops { > diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c > index f088467708f0..387045902470 100644 > --- a/arch/x86/kvm/svm/sev.c > +++ b/arch/x86/kvm/svm/sev.c > @@ -1434,6 +1434,76 @@ int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa, > return 0; > } > > +int svm_get_page_enc_bitmap(struct kvm *kvm, > + struct kvm_page_enc_bitmap *bmap) > +{ > + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; > + unsigned long gfn_start, gfn_end; > + unsigned long sz, i, sz_bytes; > + unsigned long *bitmap; > + int ret, n; > + > + if (!sev_guest(kvm)) > + return -ENOTTY; > + > + gfn_start = bmap->start_gfn; > + gfn_end = gfn_start + bmap->num_pages; > + > + sz = ALIGN(bmap->num_pages, BITS_PER_LONG) / BITS_PER_BYTE; > + bitmap = kmalloc(sz, GFP_KERNEL); > + if (!bitmap) > + return -ENOMEM; > + > + /* by default all pages are marked encrypted */ > + memset(bitmap, 0xff, sz); > + > + mutex_lock(&kvm->lock); > + if (sev->page_enc_bmap) { > + i = gfn_start; > + for_each_clear_bit_from(i, sev->page_enc_bmap, > + min(sev->page_enc_bmap_size, gfn_end)) gfn_end is not a size? I believe you want either gfn_end - gfn_start or bmap->num_pages. > + clear_bit(i - gfn_start, bitmap); > + } > + mutex_unlock(&kvm->lock); > + > + ret = -EFAULT; > + > + n = bmap->num_pages % BITS_PER_BYTE; > + sz_bytes = ALIGN(bmap->num_pages, BITS_PER_BYTE) / BITS_PER_BYTE; > + > + /* > + * Return the correct bitmap as per the number of pages being > + * requested by the user. Ensure that we only copy bmap->num_pages > + * bytes in the userspace buffer, if bmap->num_pages is not byte > + * aligned we read the trailing bits from the userspace and copy Nit: "userspace" instead of "the userspace". > + * those bits as is. > + */ > + > + if (n) { > + unsigned char *bitmap_kernel = (unsigned char *)bitmap; > + unsigned char bitmap_user; > + unsigned long offset, mask; > + > + offset = bmap->num_pages / BITS_PER_BYTE; > + if (copy_from_user(&bitmap_user, bmap->enc_bitmap + offset, > + sizeof(unsigned char))) > + goto out; > + > + mask = GENMASK(n - 1, 0); > + bitmap_user &= ~mask; > + bitmap_kernel[offset] &= mask; > + bitmap_kernel[offset] |= bitmap_user; > + } > + > + if (copy_to_user(bmap->enc_bitmap, bitmap, sz_bytes)) > + goto out; > + > + ret = 0; > +out: > + kfree(bitmap); > + return ret; > +} > + > int svm_mem_enc_op(struct kvm *kvm, void __user *argp) > { > struct kvm_sev_cmd sev_cmd; > diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c > index 1013ef0f4ce2..588709a9f68e 100644 > --- a/arch/x86/kvm/svm/svm.c > +++ b/arch/x86/kvm/svm/svm.c > @@ -4016,6 +4016,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { > .check_nested_events = svm_check_nested_events, > > .page_enc_status_hc = svm_page_enc_status_hc, > + .get_page_enc_bitmap = svm_get_page_enc_bitmap, > }; > > static struct kvm_x86_init_ops svm_init_ops __initdata = { > diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h > index 6a562f5928a2..f087fa7b380c 100644 > --- a/arch/x86/kvm/svm/svm.h > +++ b/arch/x86/kvm/svm/svm.h > @@ -404,6 +404,7 @@ int svm_check_nested_events(struct kvm_vcpu *vcpu); > int nested_svm_exit_special(struct vcpu_svm *svm); > int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa, > unsigned long npages, unsigned long enc); > +int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap); > > /* avic.c */ > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index 5f5ddb5765e2..937797cfaf9a 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -5208,6 +5208,18 @@ long kvm_arch_vm_ioctl(struct file *filp, > case KVM_SET_PMU_EVENT_FILTER: > r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); > break; > + case KVM_GET_PAGE_ENC_BITMAP: { > + struct kvm_page_enc_bitmap bitmap; > + > + r = -EFAULT; > + if (copy_from_user(&bitmap, argp, sizeof(bitmap))) > + goto out; > + > + r = -ENOTTY; > + if (kvm_x86_ops.get_page_enc_bitmap) > + r = kvm_x86_ops.get_page_enc_bitmap(kvm, &bitmap); > + break; > + } > default: > r = -ENOTTY; > } > diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h > index 0fe1d206d750..af62f2afaa5d 100644 > --- a/include/uapi/linux/kvm.h > +++ b/include/uapi/linux/kvm.h > @@ -505,6 +505,16 @@ struct kvm_dirty_log { > }; > }; > > +/* for KVM_GET_PAGE_ENC_BITMAP */ > +struct kvm_page_enc_bitmap { > + __u64 start_gfn; > + __u64 num_pages; > + union { > + void __user *enc_bitmap; /* one bit per page */ > + __u64 padding2; > + }; > +}; > + > /* for KVM_CLEAR_DIRTY_LOG */ > struct kvm_clear_dirty_log { > __u32 slot; > @@ -1518,6 +1528,8 @@ struct kvm_pv_cmd { > /* Available with KVM_CAP_S390_PROTECTED */ > #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) > > +#define KVM_GET_PAGE_ENC_BITMAP _IOW(KVMIO, 0xc6, struct kvm_page_enc_bitmap) > + > /* Secure Encrypted Virtualization command */ > enum sev_cmd_id { > /* Guest initialization commands */ > -- > 2.17.1 >
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index efbbe570aa9b..ecad84086892 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4636,6 +4636,33 @@ This ioctl resets VCPU registers and control structures according to the clear cpu reset definition in the POP. However, the cpu is not put into ESA mode. This reset is a superset of the initial reset. +4.125 KVM_GET_PAGE_ENC_BITMAP (vm ioctl) +--------------------------------------- + +:Capability: basic +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_page_enc_bitmap (in/out) +:Returns: 0 on success, -1 on error + +/* for KVM_GET_PAGE_ENC_BITMAP */ +struct kvm_page_enc_bitmap { + __u64 start_gfn; + __u64 num_pages; + union { + void __user *enc_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +The encrypted VMs have the concept of private and shared pages. The private +pages are encrypted with the guest-specific key, while the shared pages may +be encrypted with the hypervisor key. The KVM_GET_PAGE_ENC_BITMAP can +be used to get the bitmap indicating whether the guest page is private +or shared. The bitmap can be used during the guest migration. If the page +is private then the userspace need to use SEV migration commands to transmit +the page. + 4.125 KVM_S390_PV_COMMAND ------------------------- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4a8ee22f4f5b..9e428befb6a4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1256,6 +1256,8 @@ struct kvm_x86_ops { int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa, unsigned long sz, unsigned long mode); + int (*get_page_enc_bitmap)(struct kvm *kvm, + struct kvm_page_enc_bitmap *bmap); }; struct kvm_x86_init_ops { diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index f088467708f0..387045902470 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1434,6 +1434,76 @@ int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa, return 0; } +int svm_get_page_enc_bitmap(struct kvm *kvm, + struct kvm_page_enc_bitmap *bmap) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + unsigned long gfn_start, gfn_end; + unsigned long sz, i, sz_bytes; + unsigned long *bitmap; + int ret, n; + + if (!sev_guest(kvm)) + return -ENOTTY; + + gfn_start = bmap->start_gfn; + gfn_end = gfn_start + bmap->num_pages; + + sz = ALIGN(bmap->num_pages, BITS_PER_LONG) / BITS_PER_BYTE; + bitmap = kmalloc(sz, GFP_KERNEL); + if (!bitmap) + return -ENOMEM; + + /* by default all pages are marked encrypted */ + memset(bitmap, 0xff, sz); + + mutex_lock(&kvm->lock); + if (sev->page_enc_bmap) { + i = gfn_start; + for_each_clear_bit_from(i, sev->page_enc_bmap, + min(sev->page_enc_bmap_size, gfn_end)) + clear_bit(i - gfn_start, bitmap); + } + mutex_unlock(&kvm->lock); + + ret = -EFAULT; + + n = bmap->num_pages % BITS_PER_BYTE; + sz_bytes = ALIGN(bmap->num_pages, BITS_PER_BYTE) / BITS_PER_BYTE; + + /* + * Return the correct bitmap as per the number of pages being + * requested by the user. Ensure that we only copy bmap->num_pages + * bytes in the userspace buffer, if bmap->num_pages is not byte + * aligned we read the trailing bits from the userspace and copy + * those bits as is. + */ + + if (n) { + unsigned char *bitmap_kernel = (unsigned char *)bitmap; + unsigned char bitmap_user; + unsigned long offset, mask; + + offset = bmap->num_pages / BITS_PER_BYTE; + if (copy_from_user(&bitmap_user, bmap->enc_bitmap + offset, + sizeof(unsigned char))) + goto out; + + mask = GENMASK(n - 1, 0); + bitmap_user &= ~mask; + bitmap_kernel[offset] &= mask; + bitmap_kernel[offset] |= bitmap_user; + } + + if (copy_to_user(bmap->enc_bitmap, bitmap, sz_bytes)) + goto out; + + ret = 0; +out: + kfree(bitmap); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1013ef0f4ce2..588709a9f68e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4016,6 +4016,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_nested_events = svm_check_nested_events, .page_enc_status_hc = svm_page_enc_status_hc, + .get_page_enc_bitmap = svm_get_page_enc_bitmap, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 6a562f5928a2..f087fa7b380c 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -404,6 +404,7 @@ int svm_check_nested_events(struct kvm_vcpu *vcpu); int nested_svm_exit_special(struct vcpu_svm *svm); int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa, unsigned long npages, unsigned long enc); +int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap); /* avic.c */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5f5ddb5765e2..937797cfaf9a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5208,6 +5208,18 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; + case KVM_GET_PAGE_ENC_BITMAP: { + struct kvm_page_enc_bitmap bitmap; + + r = -EFAULT; + if (copy_from_user(&bitmap, argp, sizeof(bitmap))) + goto out; + + r = -ENOTTY; + if (kvm_x86_ops.get_page_enc_bitmap) + r = kvm_x86_ops.get_page_enc_bitmap(kvm, &bitmap); + break; + } default: r = -ENOTTY; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0fe1d206d750..af62f2afaa5d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -505,6 +505,16 @@ struct kvm_dirty_log { }; }; +/* for KVM_GET_PAGE_ENC_BITMAP */ +struct kvm_page_enc_bitmap { + __u64 start_gfn; + __u64 num_pages; + union { + void __user *enc_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + /* for KVM_CLEAR_DIRTY_LOG */ struct kvm_clear_dirty_log { __u32 slot; @@ -1518,6 +1528,8 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) +#define KVM_GET_PAGE_ENC_BITMAP _IOW(KVMIO, 0xc6, struct kvm_page_enc_bitmap) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */