[RFC PATCH v2 09/15] KVM: TDX: Pass desired page level in err code for page fault handler

From: isaku . yamahata
Date: Thu Dec 08 2022 - 18:36:34 EST


From: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>

For TDX, EPT violation can happen when TDG.MEM.PAGE.ACCEPT.
And TDG.MEM.PAGE.ACCEPT contains the desired accept page level of TD guest.

1. KVM can map it with 4KB page while TD guest wants to accept 2MB page.

TD geust will get TDX_PAGE_SIZE_MISMATCH and it should try to accept
4KB size.

2. KVM can map it with 2MB page while TD guest wants to accept 4KB page.

KVM needs to honor it because
a) there is no way to tell guest KVM maps it as 2MB size. And
b) guest accepts it in 4KB size since guest knows some other 4KB page
in the same 2MB range will be used as shared page.

For case 2, it need to pass desired page level to MMU's
page_fault_handler. Use bit 29:31 of kvm PF error code for this purpose.

Signed-off-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/kvm/vmx/common.h | 2 +-
arch/x86/kvm/vmx/tdx.c | 7 ++++++-
arch/x86/kvm/vmx/tdx.h | 19 -------------------
arch/x86/kvm/vmx/tdx_arch.h | 19 +++++++++++++++++++
arch/x86/kvm/vmx/vmx.c | 2 +-
6 files changed, 29 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f9d64775193b..bb790466ebae 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -279,6 +279,8 @@ enum x86_intercept_stage;
PFERR_WRITE_MASK | \
PFERR_PRESENT_MASK)

+#define PFERR_LEVEL(err_code) (((err_code) & PFERR_LEVEL_MASK) >> PFERR_LEVEL_START_BIT)
+
/* apic attention bits */
#define KVM_APIC_CHECK_VAPIC 0
/*
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index 995cf22f47cf..69464ae0f7e8 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -99,7 +99,7 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa,
error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ?
PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;

- if (err_page_level > 0)
+ if (err_page_level > PG_LEVEL_NONE)
error_code |= (err_page_level << PFERR_LEVEL_START_BIT) & PFERR_LEVEL_MASK;

return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index fad7413f7eab..39760ee95f04 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -2312,6 +2312,7 @@ static int tdx_init_mem_region(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
struct kvm_tdx_init_mem_region region;
struct kvm_vcpu *vcpu;
struct page *page;
+ u64 error_code;
kvm_pfn_t pfn;
int idx, ret = 0;

@@ -2364,7 +2365,11 @@ static int tdx_init_mem_region(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
kvm_tdx->source_pa = pfn_to_hpa(page_to_pfn(page)) |
(cmd->flags & KVM_TDX_MEASURE_MEMORY_REGION);

- pfn = kvm_mmu_map_tdp_page(vcpu, region.gpa, TDX_SEPT_PFERR,
+ /* TODO: large page support. */
+ error_code = TDX_SEPT_PFERR;
+ error_code |= (PG_LEVEL_4K << PFERR_LEVEL_START_BIT) &
+ PFERR_LEVEL_MASK;
+ pfn = kvm_mmu_map_tdp_page(vcpu, region.gpa, error_code,
PG_LEVEL_4K);
if (is_error_noslot_pfn(pfn) || kvm->vm_bugged)
ret = -EFAULT;
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index e09757acc6f9..6eca8bf4d9e1 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -62,25 +62,6 @@ union tdx_exit_reason {
u64 full;
};

-union tdx_ext_exit_qualification {
- struct {
- u64 type : 4;
- u64 reserved0 : 28;
- u64 req_sept_level : 3;
- u64 err_sept_level : 3;
- u64 err_sept_state : 8;
- u64 err_sept_is_leaf : 1;
- u64 reserved1 : 17;
- };
- u64 full;
-};
-
-enum tdx_ext_exit_qualification_type {
- EXT_EXIT_QUAL_NONE,
- EXT_EXIT_QUAL_ACCEPT,
- NUM_EXT_EXIT_QUAL,
-};
-
struct vcpu_tdx {
struct kvm_vcpu vcpu;

diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h
index 18604734fb14..471a9f61fc81 100644
--- a/arch/x86/kvm/vmx/tdx_arch.h
+++ b/arch/x86/kvm/vmx/tdx_arch.h
@@ -163,4 +163,23 @@ struct td_params {
#define TDX_MIN_TSC_FREQUENCY_KHZ (100 * 1000)
#define TDX_MAX_TSC_FREQUENCY_KHZ (10 * 1000 * 1000)

+union tdx_ext_exit_qualification {
+ struct {
+ u64 type : 4;
+ u64 reserved0 : 28;
+ u64 req_sept_level : 3;
+ u64 err_sept_level : 3;
+ u64 err_sept_state : 8;
+ u64 err_sept_is_leaf : 1;
+ u64 reserved1 : 17;
+ };
+ u64 full;
+};
+
+enum tdx_ext_exit_qualification_type {
+ EXT_EXIT_QUAL_NONE = 0,
+ EXT_EXIT_QUAL_ACCEPT,
+ NUM_EXT_EXIT_QUAL,
+};
+
#endif /* __KVM_X86_TDX_ARCH_H */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 30a715c22647..420c4cf9adeb 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5784,7 +5784,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
if (unlikely(allow_smaller_maxphyaddr && kvm_vcpu_is_illegal_gpa(vcpu, gpa)))
return kvm_emulate_instruction(vcpu, 0);

- return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification, 0);
+ return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification, PG_LEVEL_NONE);
}

static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
--
2.25.1