[RFC PATCH v2 11/15] KVM: x86/tdp_mmu, TDX: Split a large page when 4KB page within it converted to shared

From: isaku . yamahata
Date: Thu Dec 08 2022 - 18:36:41 EST

From: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>

When mapping the shared page for TDX, it needs to zap private alias.

In the case that private page is mapped as large page (2MB), it can be
removed directly only when the whole 2MB is converted to shared.
Otherwise, it has to split 2MB page into 512 4KB page, and only remove
the pages that converted to shared.

When a present large leaf spte switches to present non-leaf spte, TDX needs
to split the corresponding SEPT page to reflect it.

Signed-off-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>
Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
---
arch/x86/include/asm/kvm-x86-ops.h | 1 +
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/kvm/mmu/tdp_mmu.c | 24 +++++++++++++++---------
arch/x86/kvm/vmx/tdx.c | 25 +++++++++++++++++++++++--
arch/x86/kvm/vmx/tdx_arch.h | 1 +
arch/x86/kvm/vmx/tdx_ops.h | 7 +++++++
6 files changed, 49 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 0cf928d12067..1e86542141f7 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -97,6 +97,7 @@ KVM_X86_OP_OPTIONAL_RET0(get_mt_mask)
KVM_X86_OP(load_mmu_pgd)
KVM_X86_OP_OPTIONAL(link_private_spt)
KVM_X86_OP_OPTIONAL(free_private_spt)
+KVM_X86_OP_OPTIONAL(split_private_spt)
KVM_X86_OP_OPTIONAL(set_private_spte)
KVM_X86_OP_OPTIONAL(remove_private_spte)
KVM_X86_OP_OPTIONAL(zap_private_spte)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index bb790466ebae..282b083f9b6a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1687,6 +1687,8 @@ struct kvm_x86_ops {
void *private_spt);
int (*free_private_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level,
void *private_spt);
+ int (*split_private_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level,
+ void *private_spt);
int (*set_private_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level,
kvm_pfn_t pfn);
int (*remove_private_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index e9af8c95a3ae..6fd982e3701e 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -566,18 +566,24 @@ static int __must_check handle_changed_private_spte(struct kvm *kvm, gfn_t gfn,

lockdep_assert_held(&kvm->mmu_lock);
if (is_present) {
- /* TDP MMU doesn't change present -> present */
- KVM_BUG_ON(was_present, kvm);
+ void *private_spt;

- /*
- * Use different call to either set up middle level
- * private page table, or leaf.
- */
- if (is_leaf)
+ if (level > PG_LEVEL_4K && was_leaf && !is_leaf) {
+ /*
+ * splitting large page into 4KB.
+ * tdp_mmu_split_huage_page() => tdp_mmu_link_sp()
+ */
+ private_spt = get_private_spt(gfn, new_spte, level);
+ KVM_BUG_ON(!private_spt, kvm);
+ ret = static_call(kvm_x86_zap_private_spte)(kvm, gfn, level);
+ kvm_flush_remote_tlbs(kvm);
+ if (!ret)
+ ret = static_call(kvm_x86_split_private_spt)(kvm, gfn,
+ level, private_spt);
+ } else if (is_leaf)
ret = static_call(kvm_x86_set_private_spte)(kvm, gfn, level, new_pfn);
else {
- void *private_spt = get_private_spt(gfn, new_spte, level);
-
+ private_spt = get_private_spt(gfn, new_spte, level);
KVM_BUG_ON(!private_spt, kvm);
ret = static_call(kvm_x86_link_private_spt)(kvm, gfn, level, private_spt);
}
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 39760ee95f04..ce7026136334 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1465,6 +1465,28 @@ static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
return 0;
}

+static int tdx_sept_split_private_spt(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, void *private_spt)
+{
+ int tdx_level = pg_level_to_tdx_sept_level(level);
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ gpa_t gpa = gfn_to_gpa(gfn);
+ hpa_t hpa = __pa(private_spt);
+ struct tdx_module_output out;
+ u64 err;
+
+ /* See comment in tdx_sept_set_private_spte() */
+ err = tdh_mem_page_demote(kvm_tdx->tdr.pa, gpa, tdx_level, hpa, &out);
+ if (err == TDX_ERROR_SEPT_BUSY)
+ return -EAGAIN;
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error(TDH_MEM_PAGE_DEMOTE, err, &out);
+ return -EIO;
+ }
+
+ return 0;
+}
+
static int tdx_sept_zap_private_spte(struct kvm *kvm, gfn_t gfn,
enum pg_level level)
{
@@ -1474,8 +1496,6 @@ static int tdx_sept_zap_private_spte(struct kvm *kvm, gfn_t gfn,
struct tdx_module_output out;
u64 err;

- /* For now large page isn't supported yet. */
- WARN_ON_ONCE(level != PG_LEVEL_4K);
err = tdh_mem_range_block(kvm_tdx->tdr.pa, gpa, tdx_level, &out);
if (err == TDX_ERROR_SEPT_BUSY)
return -EAGAIN;
@@ -2660,6 +2680,7 @@ int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops)

x86_ops->link_private_spt = tdx_sept_link_private_spt;
x86_ops->free_private_spt = tdx_sept_free_private_spt;
+ x86_ops->split_private_spt = tdx_sept_split_private_spt;
x86_ops->set_private_spte = tdx_sept_set_private_spte;
x86_ops->remove_private_spte = tdx_sept_remove_private_spte;
x86_ops->zap_private_spte = tdx_sept_zap_private_spte;
diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h
index 471a9f61fc81..508d9a1139ce 100644
--- a/arch/x86/kvm/vmx/tdx_arch.h
+++ b/arch/x86/kvm/vmx/tdx_arch.h
@@ -21,6 +21,7 @@
#define TDH_MNG_CREATE 9
#define TDH_VP_CREATE 10
#define TDH_MNG_RD 11
+#define TDH_MEM_PAGE_DEMOTE 15
#define TDH_MR_EXTEND 16
#define TDH_MR_FINALIZE 17
#define TDH_VP_FLUSH 18
diff --git a/arch/x86/kvm/vmx/tdx_ops.h b/arch/x86/kvm/vmx/tdx_ops.h
index 4b03acce5003..60cbc7f94b18 100644
--- a/arch/x86/kvm/vmx/tdx_ops.h
+++ b/arch/x86/kvm/vmx/tdx_ops.h
@@ -133,6 +133,13 @@ static inline u64 tdh_mng_rd(hpa_t tdr, u64 field, struct tdx_module_output *out
return __seamcall(TDH_MNG_RD, tdr, field, 0, 0, out);
}

+static inline u64 tdh_mem_page_demote(hpa_t tdr, gpa_t gpa, int level, hpa_t page,
+ struct tdx_module_output *out)
+{
+ tdx_clflush_page(page, PG_LEVEL_4K);
+ return seamcall_sept(TDH_MEM_PAGE_DEMOTE, gpa | level, tdr, page, 0, out);
+}
+
static inline u64 tdh_mr_extend(hpa_t tdr, gpa_t gpa,
struct tdx_module_output *out)
{
--
2.25.1