On Mon, Aug 12, 2024 at 03:48:09PM -0700, Rick Edgecombe wrote:
> From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
>
...
> +static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
> +{
> + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
> + struct kvm_tdx_init_vm *init_vm;
> + struct td_params *td_params = NULL;
> + int ret;
> +
> + BUILD_BUG_ON(sizeof(*init_vm) != 256 + sizeof_field(struct kvm_tdx_init_vm, cpuid));
> + BUILD_BUG_ON(sizeof(struct td_params) != 1024);
> +
> + if (is_hkid_assigned(kvm_tdx))
> + return -EINVAL;
> +
> + if (cmd->flags)
> + return -EINVAL;
> +
> + init_vm = kmalloc(sizeof(*init_vm) +
> + sizeof(init_vm->cpuid.entries[0]) * KVM_MAX_CPUID_ENTRIES,
> + GFP_KERNEL);
> + if (!init_vm)
> + return -ENOMEM;
> +
> + if (copy_from_user(init_vm, u64_to_user_ptr(cmd->data), sizeof(*init_vm))) {
> + ret = -EFAULT;
> + goto out;
> + }
> +
> + if (init_vm->cpuid.nent > KVM_MAX_CPUID_ENTRIES) {
> + ret = -E2BIG;
> + goto out;
> + }
> +
> + if (copy_from_user(init_vm->cpuid.entries,
> + u64_to_user_ptr(cmd->data) + sizeof(*init_vm),
> + flex_array_size(init_vm, cpuid.entries, init_vm->cpuid.nent))) {
> + ret = -EFAULT;
> + goto out;
> + }
> +
> + if (memchr_inv(init_vm->reserved, 0, sizeof(init_vm->reserved))) {
> + ret = -EINVAL;
> + goto out;
> + }
> +
> + if (init_vm->cpuid.padding) {
> + ret = -EINVAL;
> + goto out;
> + }
> +
> + td_params = kzalloc(sizeof(struct td_params), GFP_KERNEL);
> + if (!td_params) {
> + ret = -ENOMEM;
> + goto out;
> + }
> +
> + ret = setup_tdparams(kvm, td_params, init_vm);
> + if (ret)
> + goto out;
> +
> + ret = __tdx_td_init(kvm, td_params, &cmd->hw_error);
> + if (ret)
> + goto out;
> +
> + kvm_tdx->tsc_offset = td_tdcs_exec_read64(kvm_tdx, TD_TDCS_EXEC_TSC_OFFSET);
> + kvm_tdx->attributes = td_params->attributes;
> + kvm_tdx->xfam = td_params->xfam;
> +
> + if (td_params->exec_controls & TDX_EXEC_CONTROL_MAX_GPAW)
> + kvm->arch.gfn_direct_bits = gpa_to_gfn(BIT_ULL(51));
> + else
> + kvm->arch.gfn_direct_bits = gpa_to_gfn(BIT_ULL(47));
> +
Could we introduce a initialized field in struct kvm_tdx and set it true
here? e.g
+ kvm_tdx->initialized = true;
Then reject vCPU creation in tdx_vcpu_create() before KVM_TDX_INIT_VM is
executed successfully? e.g.
@@ -584,6 +589,9 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu)
struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
struct vcpu_tdx *tdx = to_tdx(vcpu);
+ if (!kvm_tdx->initialized)
+ return -EIO;
+
/* TDX only supports x2APIC, which requires an in-kernel local APIC. */
if (!vcpu->arch.apic)
return -EINVAL;
Allowing vCPU creation only after TD is initialized can prevent unexpected
userspace access to uninitialized TD primitives.
See details in the next comment.
> +out:
> + /* kfree() accepts NULL. */
> + kfree(init_vm);
> + kfree(td_params);
> +
> + return ret;
> +}
> +
> int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
> {
> struct kvm_tdx_cmd tdx_cmd;
> @@ -613,6 +827,9 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
> case KVM_TDX_CAPABILITIES:
> r = tdx_get_capabilities(&tdx_cmd);
> break;
> + case KVM_TDX_INIT_VM:
> + r = tdx_td_init(kvm, &tdx_cmd);
> + break;
> default:
> r = -EINVAL;
> goto out;
QEMU should invoke VM ioctl KVM_TDX_INIT_VM in tdx_pre_create_vcpu() before
creating vCPUs via VM ioctl KVM_CREATE_VCPU, but KVM should not count on
userspace always doing the right thing.
e.g. running below selftest would produce warning in KVM due to
td_vmcs_write64() error in tdx_load_mmu_pgd().
void verify_td_negative_test(void)
{
struct kvm_vm *vm;
struct kvm_vcpu *vcpu;
vm = td_create();
vm_enable_cap(vm, KVM_CAP_SPLIT_IRQCHIP, 24);
vcpu = __vm_vcpu_add(vm, 0);
vcpu_run(vcpu);
kvm_vm_free(vm);
}
[ 5600.721996] WARNING: CPU: 116 PID: 7914 at arch/x86/kvm/vmx/tdx.h:237 tdx_load_mmu_pgd+0x55/0xa0 [kvm_intel]
[ 5600.735999] Modules linked in: kvm_intel kvm idxd i2c_i801 nls_iso8859_1 i2c_smbus i2c_ismt nls_cp437 squashfs hid_generic crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel crypto_simd cryptd [last unloaded: kvm]
[ 5600.762904] CPU: 116 PID: 7914 Comm: tdx_vm_tests Not tainted 6.10.0-rc7-upstream+ #278 5e882f76313c2b130a0f7525b7eda06f47d8ea02
[ 5600.779772] Hardware name: Intel Corporation ArcherCity/ArcherCity, BIOS EGSDCRB1.SYS.0101.D29.2303301937 03/30/2023
[ 5600.795940] RIP: 0010:tdx_load_mmu_pgd+0x55/0xa0 [kvm_intel]
[ 5600.805013] Code: 00 e8 8f b4 ff ff 48 85 c0 74 52 49 89 c5 48 8b 03 44 0f b6 b0 89 a3 00 00 41 80 fe 01 0f 87 ae 74 00 00 41 83 e6 01 75 1d 90 <0f> 0b 90 48 8b 3b b8 01 01 00 00 be 01 03 00 00 66 89 87 89 a3 00
[ 5600.833286] RSP: 0018:ff3550cf49297c78 EFLAGS: 00010246
[ 5600.842233] RAX: ff3550cf4dfd9000 RBX: ff2c5edc10600000 RCX: 0000000000000000
[ 5600.853400] RDX: 0000000000000000 RSI: ff3550cf49297be8 RDI: 000000000000002b
[ 5600.864609] RBP: ff3550cf49297c98 R08: 0000000000000000 R09: ffffffffffffffff
[ 5600.875915] R10: 0000000000000000 R11: 0000000000000000 R12: 000000048d10c000
[ 5600.887255] R13: c000030000000001 R14: 0000000000000000 R15: 0000000000000000
[ 5600.898584] FS: 00007f9597799740(0000) GS:ff2c5ee7ad700000(0000) knlGS:0000000000000000
[ 5600.911113] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5600.921064] CR2: 00007f959759b8c0 CR3: 000000010b83e005 CR4: 0000000000773ef0
[ 5600.932675] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 5600.944319] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
[ 5600.955987] PKRU: 55555554
[ 5600.962665] Call Trace:
[ 5600.969084] <TASK>
[ 5600.975079] ? show_regs+0x64/0x70
[ 5600.982536] ? __warn+0x8a/0x100
[ 5600.989840] ? tdx_load_mmu_pgd+0x55/0xa0 [kvm_intel b63d7b2e0213930160302a21a156d5f897483840]
[ 5601.006321] ? report_bug+0x1b6/0x220
[ 5601.014351] ? handle_bug+0x43/0x80
[ 5601.022248] ? exc_invalid_op+0x18/0x70
[ 5601.030554] ? asm_exc_invalid_op+0x1b/0x20
[ 5601.039297] ? tdx_load_mmu_pgd+0x55/0xa0 [kvm_intel b63d7b2e0213930160302a21a156d5f897483840]
[ 5601.056276] ? tdx_load_mmu_pgd+0x31/0xa0 [kvm_intel b63d7b2e0213930160302a21a156d5f897483840]
[ 5601.073270] vt_load_mmu_pgd+0x57/0x70 [kvm_intel b63d7b2e0213930160302a21a156d5f897483840]
[ 5601.089991] kvm_mmu_load+0xa4/0xc0 [kvm 2979fa2240d2f299e1c4576243100dec1104b4cd]
[ 5601.102708] vcpu_enter_guest+0xbe2/0x1140 [kvm 2979fa2240d2f299e1c4576243100dec1104b4cd]
[ 5601.116042] ? __this_cpu_preempt_check+0x13/0x20
[ 5601.125373] ? debug_smp_processor_id+0x17/0x20
[ 5601.134400] vcpu_run+0x4d/0x280 [kvm 2979fa2240d2f299e1c4576243100dec1104b4cd]
[ 5601.146657] ? vcpu_run+0x4d/0x280 [kvm 2979fa2240d2f299e1c4576243100dec1104b4cd]
[ 5601.159108] kvm_arch_vcpu_ioctl_run+0x224/0x680 [kvm 2979fa2240d2f299e1c4576243100dec1104b4cd]
[ 5601.175943] kvm_vcpu_ioctl+0x238/0x750 [kvm 2979fa2240d2f299e1c4576243100dec1104b4cd]
[ 5601.188912] ? __ct_user_exit+0xd1/0x120
[ 5601.197305] ? __lock_release.isra.0+0x61/0x160
[ 5601.206432] ? __ct_user_exit+0xd1/0x120
[ 5601.214791] __x64_sys_ioctl+0x98/0xd0
[ 5601.222980] x64_sys_call+0x1222/0x2040
[ 5601.231268] do_syscall_64+0xc3/0x220
[ 5601.239321] entry_SYSCALL_64_after_hwframe+0x77/0x7f
[ 5601.248913] RIP: 0033:0x7f9597524ded
[ 5601.256781] Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1a 48 8b 45 c8 64 48 2b 04 25 28 00 00 00
[ 5601.288181] RSP: 002b:00007ffd117315c0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[ 5601.300843] RAX: ffffffffffffffda RBX: 00000000108a32a0 RCX: 00007f9597524ded
[ 5601.313108] RDX: 0000000000000000 RSI: 000000000000ae80 RDI: 0000000000000005
[ 5601.325411] RBP: 00007ffd11731610 R08: 0000000000422078 R09: 0000000000428e48
[ 5601.337721] R10: 0000000000000001 R11: 0000000000000246 R12: 00000000108a54a0
[ 5601.349965] R13: 0000000000000000 R14: 0000000000434e00 R15: 00007f95977eb000
[ 5601.362131] </TASK>
> diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
> index 268959d0f74f..8912cb6d5bc2 100644
> --- a/arch/x86/kvm/vmx/tdx.h
> +++ b/arch/x86/kvm/vmx/tdx.h
> @@ -16,7 +16,11 @@ struct kvm_tdx {
> unsigned long tdr_pa;
> unsigned long *tdcs_pa;
>
> + u64 attributes;
> + u64 xfam;
> int hkid;
> +
> + u64 tsc_offset;
> };
>
>
