[PATCH v7 04/13] KVM: TDX: Update tdx_sept_{set,drop}_private_spte() to support large page

From: isaku . yamahata
Date: Mon Jan 22 2024 - 20:03:04 EST


From: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>

Allow large page level AUG and REMOVE for TDX pages.

Signed-off-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx>
Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
---
arch/x86/kvm/vmx/tdx.c | 68 ++++++++++++++++++++++--------------------
1 file changed, 35 insertions(+), 33 deletions(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 68f3a4c40be4..e2a0d521f806 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1504,11 +1504,12 @@ void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa & PAGE_MASK);
}

-static void tdx_unpin(struct kvm *kvm, kvm_pfn_t pfn)
+static void tdx_unpin(struct kvm *kvm, kvm_pfn_t pfn, enum pg_level level)
{
- struct page *page = pfn_to_page(pfn);
+ int i;

- put_page(page);
+ for (i = 0; i < KVM_PAGES_PER_HPAGE(level); i++)
+ put_page(pfn_to_page(pfn + i));
}

static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,
@@ -1525,7 +1526,7 @@ static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,

err = tdh_mem_page_aug(kvm_tdx->tdr_pa, gpa, tdx_level, hpa, &out);
if (unlikely(err == TDX_ERROR_SEPT_BUSY)) {
- tdx_unpin(kvm, pfn);
+ tdx_unpin(kvm, pfn, level);
return -EAGAIN;
}
if (unlikely(err == (TDX_EPT_ENTRY_STATE_INCORRECT | TDX_OPERAND_ID_RCX))) {
@@ -1534,7 +1535,7 @@ static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,
if (level_state.level == tdx_level &&
level_state.state == TDX_SEPT_PENDING &&
entry.leaf && entry.pfn == pfn && entry.sve) {
- tdx_unpin(kvm, pfn);
+ tdx_unpin(kvm, pfn, level);
WARN_ON_ONCE(!(to_kvm_tdx(kvm)->attributes &
TDX_TD_ATTR_SEPT_VE_DISABLE));
return -EAGAIN;
@@ -1542,7 +1543,7 @@ static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,
}
if (KVM_BUG_ON(err, kvm)) {
pr_tdx_error(TDH_MEM_PAGE_AUG, err, &out);
- tdx_unpin(kvm, pfn);
+ tdx_unpin(kvm, pfn, level);
return -EIO;
}

@@ -1578,7 +1579,7 @@ static int tdx_mem_page_add(struct kvm *kvm, gfn_t gfn,
* always uses vcpu 0's page table and protected by vcpu->mutex).
*/
if (KVM_BUG_ON(kvm_tdx->source_pa == INVALID_PAGE, kvm)) {
- tdx_unpin(kvm, pfn);
+ tdx_unpin(kvm, pfn, level);
return -EINVAL;
}

@@ -1596,7 +1597,7 @@ static int tdx_mem_page_add(struct kvm *kvm, gfn_t gfn,
} while (unlikely(err == TDX_ERROR_SEPT_BUSY));
if (KVM_BUG_ON(err, kvm)) {
pr_tdx_error(TDH_MEM_PAGE_ADD, err, &out);
- tdx_unpin(kvm, pfn);
+ tdx_unpin(kvm, pfn, level);
return -EIO;
} else if (measure) {
for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) {
@@ -1616,10 +1617,7 @@ static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
enum pg_level level, kvm_pfn_t pfn)
{
struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
-
- /* TODO: handle large pages. */
- if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
- return -EINVAL;
+ int i;

/*
* Because restricted mem doesn't support page migration with
@@ -1629,7 +1627,8 @@ static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
* TODO: Once restricted mem introduces callback on page migration,
* implement it and remove get_page/put_page().
*/
- get_page(pfn_to_page(pfn));
+ for (i = 0; i < KVM_PAGES_PER_HPAGE(level); i++)
+ get_page(pfn_to_page(pfn + i));

if (likely(is_td_finalized(kvm_tdx)))
return tdx_mem_page_aug(kvm, gfn, level, pfn);
@@ -1646,11 +1645,9 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
gpa_t gpa = gfn_to_gpa(gfn);
hpa_t hpa = pfn_to_hpa(pfn);
hpa_t hpa_with_hkid;
+ int r = 0;
u64 err;
-
- /* TODO: handle large pages. */
- if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
- return -EINVAL;
+ int i;

if (unlikely(!is_hkid_assigned(kvm_tdx))) {
/*
@@ -1660,7 +1657,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
err = tdx_reclaim_page(hpa, level);
if (KVM_BUG_ON(err, kvm))
return -EIO;
- tdx_unpin(kvm, pfn);
+ tdx_unpin(kvm, pfn, level);
return 0;
}

@@ -1677,22 +1674,27 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
return -EIO;
}

- hpa_with_hkid = set_hkid_to_hpa(hpa, (u16)kvm_tdx->hkid);
- do {
- /*
- * TDX_OPERAND_BUSY can happen on locking PAMT entry. Because
- * this page was removed above, other thread shouldn't be
- * repeatedly operating on this page. Just retry loop.
- */
- err = tdh_phymem_page_wbinvd(hpa_with_hkid);
- } while (unlikely(err == (TDX_OPERAND_BUSY | TDX_OPERAND_ID_RCX)));
- if (KVM_BUG_ON(err, kvm)) {
- pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err, NULL);
- return -EIO;
+ for (i = 0; i < KVM_PAGES_PER_HPAGE(level); i++) {
+ hpa_with_hkid = set_hkid_to_hpa(hpa, (u16)kvm_tdx->hkid);
+ do {
+ /*
+ * TDX_OPERAND_BUSY can happen on locking PAMT entry.
+ * Because this page was removed above, other thread
+ * shouldn't be repeatedly operating on this page.
+ * Simple retry should work.
+ */
+ err = tdh_phymem_page_wbinvd(hpa_with_hkid);
+ } while (unlikely(err == (TDX_OPERAND_BUSY | TDX_OPERAND_ID_RCX)));
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err, NULL);
+ r = -EIO;
+ } else {
+ tdx_clear_page(hpa, PAGE_SIZE);
+ tdx_unpin(kvm, pfn + i, PG_LEVEL_4K);
+ }
+ hpa += PAGE_SIZE;
}
- tdx_clear_page(hpa, PAGE_SIZE);
- tdx_unpin(kvm, pfn);
- return 0;
+ return r;
}

static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
--
2.25.1