On Tue, Nov 05, 2024 at 01:23:13AM -0500, Xiaoyao Li wrote:
> KVM provides TDX capabilities via sub command KVM_TDX_CAPABILITIES of
> IOCTL(KVM_MEMORY_ENCRYPT_OP). Get the capabilities when initializing
> TDX context. It will be used to validate user's setting later.
>
> Since there is no interface reporting how many cpuid configs contains in
> KVM_TDX_CAPABILITIES, QEMU chooses to try starting with a known number
> and abort when it exceeds KVM_MAX_CPUID_ENTRIES.
>
> Besides, introduce the interfaces to invoke TDX "ioctls" at VCPU scope
> in preparation.
>
> Signed-off-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>
> ---
> Changes in v6:
> - Pass CPUState * to tdx_vcpu_ioctl();
> - update commit message to remove platform scope thing;
> - dump hw_error when it's non-zero to help debug;
>
> Changes in v4:
> - use {} to initialize struct kvm_tdx_cmd, to avoid memset();
> - remove tdx_platform_ioctl() because no user;
>
> Changes in v3:
> - rename __tdx_ioctl() to tdx_ioctl_internal()
> - Pass errp in get_tdx_capabilities();
>
> changes in v2:
> - Make the error message more clear;
>
> changes in v1:
> - start from nr_cpuid_configs = 6 for the loop;
> - stop the loop when nr_cpuid_configs exceeds KVM_MAX_CPUID_ENTRIES;
> ---
> target/i386/kvm/kvm.c | 2 -
> target/i386/kvm/kvm_i386.h | 2 +
> target/i386/kvm/tdx.c | 93 +++++++++++++++++++++++++++++++++++++-
> 3 files changed, 94 insertions(+), 3 deletions(-)
>
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index 2bbac603da70..b843de7f2379 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -1782,8 +1782,6 @@ static int hyperv_init_vcpu(X86CPU *cpu)
>
> static Error *invtsc_mig_blocker;
>
> -#define KVM_MAX_CPUID_ENTRIES 100
> -
> static void kvm_init_xsave(CPUX86State *env)
> {
> if (has_xsave2) {
> diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h
> index 9de9c0d30388..7ac4c3a91171 100644
> --- a/target/i386/kvm/kvm_i386.h
> +++ b/target/i386/kvm/kvm_i386.h
> @@ -13,6 +13,8 @@
>
> #include "sysemu/kvm.h"
>
> +#define KVM_MAX_CPUID_ENTRIES 100
> +
> #ifdef CONFIG_KVM
>
> #define kvm_pit_in_kernel() \
> diff --git a/target/i386/kvm/tdx.c b/target/i386/kvm/tdx.c
> index 85f006c1d6b4..907044910fec 100644
> --- a/target/i386/kvm/tdx.c
> +++ b/target/i386/kvm/tdx.c
> @@ -12,17 +12,108 @@
> */
>
> #include "qemu/osdep.h"
> +#include "qemu/error-report.h"
> +#include "qapi/error.h"
> #include "qom/object_interfaces.h"
>
> #include "hw/i386/x86.h"
> #include "kvm_i386.h"
> #include "tdx.h"
>
> +static struct kvm_tdx_capabilities *tdx_caps;
> +
> +enum tdx_ioctl_level {
> + TDX_VM_IOCTL,
> + TDX_VCPU_IOCTL,
> +};
> +
> +static int tdx_ioctl_internal(enum tdx_ioctl_level level, void *state,
> + int cmd_id, __u32 flags, void *data)
> +{
> + struct kvm_tdx_cmd tdx_cmd = {};
> + int r;
> +
> + tdx_cmd.id = cmd_id;
> + tdx_cmd.flags = flags;
> + tdx_cmd.data = (__u64)(unsigned long)data;
> +
> + switch (level) {
> + case TDX_VM_IOCTL:
> + r = kvm_vm_ioctl(kvm_state, KVM_MEMORY_ENCRYPT_OP, &tdx_cmd);
> + break;
> + case TDX_VCPU_IOCTL:
> + r = kvm_vcpu_ioctl(state, KVM_MEMORY_ENCRYPT_OP, &tdx_cmd);
> + break;
> + default:
> + error_report("Invalid tdx_ioctl_level %d", level);
> + exit(1);
> + }
> +
> + if (r && tdx_cmd.hw_error) {
> + error_report("TDX ioctl %d return with %d, hw_errors: 0x%llx",
> + cmd_id, r, tdx_cmd.hw_error);
> + }
> + return r;
> +}
I feel like the error handling of this method is rather inconsistent.
In one place we error_report() and then exit(), in another place
we error_report() but return, and in another place we report nothing
at all. When we return, the caller propagates an Error **errp object,
but this propagated message lacks the potentially useful 'hw_errors'
info.
IMHO this method ought to have an 'Error **errp' parameter and always
fill it & propagate. Let the caller decide whether to exit or not.
If you continue returning 'r', then the caller can still handle
E2BIG, discarding the 'Error' object in that case.
> +
> +static inline int tdx_vm_ioctl(int cmd_id, __u32 flags, void *data)
> +{
> + return tdx_ioctl_internal(TDX_VM_IOCTL, NULL, cmd_id, flags, data);
> +}
> +
> +static inline int tdx_vcpu_ioctl(CPUState *cpu, int cmd_id, __u32 flags,
> + void *data)
> +{
> + return tdx_ioctl_internal(TDX_VCPU_IOCTL, cpu, cmd_id, flags, data);
> +}
> +
> +static int get_tdx_capabilities(Error **errp)
> +{
> + struct kvm_tdx_capabilities *caps;
> + /* 1st generation of TDX reports 6 cpuid configs */
> + int nr_cpuid_configs = 6;
> + size_t size;
> + int r;
> +
> + do {
> + size = sizeof(struct kvm_tdx_capabilities) +
> + nr_cpuid_configs * sizeof(struct kvm_cpuid_entry2);
> + caps = g_malloc0(size);
> + caps->cpuid.nent = nr_cpuid_configs;
> +
> + r = tdx_vm_ioctl(KVM_TDX_CAPABILITIES, 0, caps);
> + if (r == -E2BIG) {
> + g_free(caps);
> + nr_cpuid_configs *= 2;
> + if (nr_cpuid_configs > KVM_MAX_CPUID_ENTRIES) {
> + error_setg(errp, "%s: KVM TDX seems broken that number of CPUID"
> + " entries in kvm_tdx_capabilities exceeds limit %d",
> + __func__, KVM_MAX_CPUID_ENTRIES);
> + return r;
> + }
> + } else if (r < 0) {
> + g_free(caps);
> + error_setg_errno(errp, -r, "%s: KVM_TDX_CAPABILITIES failed", __func__);
> + return r;
> + }
> + } while (r == -E2BIG);
> +
> + tdx_caps = caps;
> +
> + return 0;
> +}
> +
> static int tdx_kvm_init(ConfidentialGuestSupport *cgs, Error **errp)
> {
> + int r = 0;
> +
> kvm_mark_guest_state_protected();
>
> - return 0;
> + if (!tdx_caps) {
> + r = get_tdx_capabilities(errp);
> + }
> +
> + return r;
> }
>
> static int tdx_kvm_type(X86ConfidentialGuest *cg)
> --
> 2.34.1
>
With regards,
Daniel
--
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org -o- https://fstop138.berrange.com :|
|: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
