Re: [PATCH 21/25] KVM: x86: Introduce KVM_TDX_GET_CPUID

Xiaoyao Li <xiaoyao.li@xxxxxxxxx> · Mon, 30 Sep 2024 14:26:55 +0800

On 8/13/2024 6:48 AM, Rick Edgecombe wrote:
From: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>

Implement an IOCTL to allow userspace to read the CPUID bit values for a
configured TD.

The TDX module doesn't provide the ability to set all CPUID bits. Instead
some are configured indirectly, or have fixed values. But it does allow
for the final resulting CPUID bits to be read. This information will be
useful for userspace to understand the configuration of the TD, and set
KVM's copy via KVM_SET_CPUID2.

To prevent userspace from starting to use features that might not have KVM
support yet, filter the reported values by KVM's support CPUID bits.

This patch lacks the documentation of KVM_TDX_GET_CPUID to describe what 
it returns and how the returned data is used or expected to be used by 
userspace.

Set aside the filtering of KVM's support CPUID bits, KVM_TDX_GET_CPUID 
only returns the CPUID leaves that can be readable by TDX module (in 
tdx_mask_cpuid()). So what about the leaves that aren't readable? e.g., 
CPUID leaf 6,9,0xc,etc, and leaf 0x40000000 and 0x40000001.

Should userspace to intercept it as the leaves that aren't covered by 
KVM_TDX_GET_CPUID are totally controlled by userspace itself and it's 
userspace's responsibility to set a sane and valid value?

Signed-off-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
---
uAPI breakout v1:
  - New patch
---
  arch/x86/include/uapi/asm/kvm.h |   1 +
  arch/x86/kvm/vmx/tdx.c          | 131 ++++++++++++++++++++++++++++++++
  arch/x86/kvm/vmx/tdx.h          |   5 ++
  arch/x86/kvm/vmx/tdx_arch.h     |   5 ++
  arch/x86/kvm/vmx/tdx_errno.h    |   1 +
  5 files changed, 143 insertions(+)

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index b4f12997052d..39636be5c891 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -931,6 +931,7 @@ enum kvm_tdx_cmd_id {
  	KVM_TDX_CAPABILITIES = 0,
  	KVM_TDX_INIT_VM,
  	KVM_TDX_INIT_VCPU,
+	KVM_TDX_GET_CPUID,
  
  	KVM_TDX_CMD_NR_MAX,
  };
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b2ed031ac0d6..fe2bbc2ced41 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -813,6 +813,76 @@ static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params,
  	return ret;
  }
  
+static u64 tdx_td_metadata_field_read(struct kvm_tdx *tdx, u64 field_id,
+				      u64 *data)
+{
+	u64 err;
+
+	err = tdh_mng_rd(tdx, field_id, data);
+
+	return err;
+}
+
+#define TDX_MD_UNREADABLE_LEAF_MASK	GENMASK(30, 7)
+#define TDX_MD_UNREADABLE_SUBLEAF_MASK	GENMASK(31, 7)
+
+static int tdx_mask_cpuid(struct kvm_tdx *tdx, struct kvm_cpuid_entry2 *entry)
+{
+	u64 field_id = TD_MD_FIELD_ID_CPUID_VALUES;
+	u64 ebx_eax, edx_ecx;
+	u64 err = 0;
+
+	if (entry->function & TDX_MD_UNREADABLE_LEAF_MASK ||
+	    entry->index & TDX_MD_UNREADABLE_SUBLEAF_MASK)
+		return -EINVAL;
+
+	/*
+	 * bit 23:17, REVSERVED: reserved, must be 0;
+	 * bit 16,    LEAF_31: leaf number bit 31;
+	 * bit 15:9,  LEAF_6_0: leaf number bits 6:0, leaf bits 30:7 are
+	 *                      implicitly 0;
+	 * bit 8,     SUBLEAF_NA: sub-leaf not applicable flag;
+	 * bit 7:1,   SUBLEAF_6_0: sub-leaf number bits 6:0. If SUBLEAF_NA is 1,
+	 *                         the SUBLEAF_6_0 is all-1.
+	 *                         sub-leaf bits 31:7 are implicitly 0;
+	 * bit 0,     ELEMENT_I: Element index within field;
+	 */
+	field_id |= ((entry->function & 0x80000000) ? 1 : 0) << 16;
+	field_id |= (entry->function & 0x7f) << 9;
+	if (entry->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX)
+		field_id |= (entry->index & 0x7f) << 1;
+	else
+		field_id |= 0x1fe;
+
+	err = tdx_td_metadata_field_read(tdx, field_id, &ebx_eax);
+	if (err) //TODO check for specific errors
+		goto err_out;
+
+	entry->eax &= (u32) ebx_eax;
+	entry->ebx &= (u32) (ebx_eax >> 32);
+
+	field_id++;
+	err = tdx_td_metadata_field_read(tdx, field_id, &edx_ecx);
+	/*
+	 * It's weird that reading edx_ecx fails while reading ebx_eax
+	 * succeeded.
+	 */
+	if (WARN_ON_ONCE(err))
+		goto err_out;
+
+	entry->ecx &= (u32) edx_ecx;
+	entry->edx &= (u32) (edx_ecx >> 32);
+	return 0;
+
+err_out:
+	entry->eax = 0;
+	entry->ebx = 0;
+	entry->ecx = 0;
+	entry->edx = 0;
+
+	return -EIO;
+}
+
  static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
  {
  	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
@@ -1038,6 +1108,64 @@ static int __maybe_unused tdx_get_kvm_supported_cpuid(struct kvm_cpuid2 **cpuid)
  	return r;
  }
  
+static int tdx_vcpu_get_cpuid(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd)
+{
+	struct kvm_cpuid2 __user *output, *td_cpuid;
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+	struct kvm_cpuid2 *supported_cpuid;
+	int r = 0, i, j = 0;
+
+	output = u64_to_user_ptr(cmd->data);
+	td_cpuid = kzalloc(sizeof(*td_cpuid) +
+			sizeof(output->entries[0]) * KVM_MAX_CPUID_ENTRIES,
+			GFP_KERNEL);
+	if (!td_cpuid)
+		return -ENOMEM;
+
+	r = tdx_get_kvm_supported_cpuid(&supported_cpuid);
+	if (r)
+		goto out;
+
+	for (i = 0; i < supported_cpuid->nent; i++) {
+		struct kvm_cpuid_entry2 *supported = &supported_cpuid->entries[i];
+		struct kvm_cpuid_entry2 *output_e = &td_cpuid->entries[j];
+
+		*output_e = *supported;
+
+		/* Only allow values of bits that KVM's supports to be exposed */
+		if (tdx_mask_cpuid(kvm_tdx, output_e))
+			continue;
+
+		/*
+		 * Work around missing support on old TDX modules, fetch
+		 * guest maxpa from gfn_direct_bits.
+		 */
+		if (output_e->function == 0x80000008) {
+			gpa_t gpa_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
+			unsigned int g_maxpa = __ffs(gpa_bits) + 1;
+
+			output_e->eax &= ~0x00ff0000;
+			output_e->eax |= g_maxpa << 16;
+		}
+
+		j++;
+	}
+	td_cpuid->nent = j;
+
+	if (copy_to_user(output, td_cpuid, sizeof(*output))) {
+		r = -EFAULT;
+		goto out;
+	}
+	if (copy_to_user(output->entries, td_cpuid->entries,
+			 td_cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
+		r = -EFAULT;
+
+out:
+	kfree(td_cpuid);
+	kfree(supported_cpuid);
+	return r;
+}
+
  static int tdx_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd)
  {
  	struct msr_data apic_base_msr;
@@ -1089,6 +1217,9 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
  	case KVM_TDX_INIT_VCPU:
  		ret = tdx_vcpu_init(vcpu, &cmd);
  		break;
+	case KVM_TDX_GET_CPUID:
+		ret = tdx_vcpu_get_cpuid(vcpu, &cmd);
+		break;
  	default:
  		ret = -EINVAL;
  		break;
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index 8349b542836e..7eeb54fbcae1 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -25,6 +25,11 @@ struct kvm_tdx {
  	bool finalized;
  
  	u64 tsc_offset;
+
+	/* For KVM_MAP_MEMORY and KVM_TDX_INIT_MEM_REGION. */
+	atomic64_t nr_premapped;
+
+	struct kvm_cpuid2 *cpuid;
  };
  
  struct vcpu_tdx {
diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h
index d2d7f9cab740..815e74408a34 100644
--- a/arch/x86/kvm/vmx/tdx_arch.h
+++ b/arch/x86/kvm/vmx/tdx_arch.h
@@ -157,4 +157,9 @@ struct td_params {
  
  #define MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM	BIT_ULL(20)
  
+/*
+ * TD scope metadata field ID.
+ */
+#define TD_MD_FIELD_ID_CPUID_VALUES		0x9410000300000000ULL
+
  #endif /* __KVM_X86_TDX_ARCH_H */
diff --git a/arch/x86/kvm/vmx/tdx_errno.h b/arch/x86/kvm/vmx/tdx_errno.h
index dc3fa2a58c2c..f9dbb3a065cc 100644
--- a/arch/x86/kvm/vmx/tdx_errno.h
+++ b/arch/x86/kvm/vmx/tdx_errno.h
@@ -23,6 +23,7 @@
  #define TDX_FLUSHVP_NOT_DONE			0x8000082400000000ULL
  #define TDX_EPT_WALK_FAILED			0xC0000B0000000000ULL
  #define TDX_EPT_ENTRY_STATE_INCORRECT		0xC0000B0D00000000ULL
+#define TDX_METADATA_FIELD_NOT_READABLE		0xC0000C0200000000ULL
  
  /*
   * TDX module operand ID, appears in 31:0 part of error code as








