[RFC PATCH v2 20/23] KVM: TDX: Handle Dynamic PAMT in tdh_mem_page_demote()

[Yan Zhao <yan.y.zhao@xxxxxxxxx>]

From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>

If Dynamic PAMT is enabled, TDH.MEM.PAGE.DEMOTE will take the PAMT page
pair in registers R12 and R13.

Pass the pamt_pages list down to tdh_mem_page_demote() and populate
registers R12 and R13 from it.

Instead of using seamcall_ret(), use seamcall_saved_ret() as it can
handle registers above R11.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Yan Zhao <yan.y.zhao@xxxxxxxxx>
---
RFC v2:
- Pulled from
  git://git.kernel.org/pub/scm/linux/kernel/git/kas/linux.git tdx/dpamt-huge.
- Rebased on top of TDX huge page RFC v2 (Yan).
---
 arch/x86/include/asm/tdx.h  |  1 +
 arch/x86/kvm/vmx/tdx.c      |  4 ++--
 arch/x86/virt/vmx/tdx/tdx.c | 13 +++++++++++--
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index c058a82d4a97..2e529f0c578a 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -180,6 +180,7 @@ u64 tdh_mng_create(struct tdx_td *td, u16 hkid);
 u64 tdh_vp_create(struct tdx_td *td, struct tdx_vp *vp);
 u64 tdh_mng_rd(struct tdx_td *td, u64 field, u64 *data);
 u64 tdh_mem_page_demote(struct tdx_td *td, u64 gpa, int level, struct page *page,
+			struct list_head *pamt_pages,
 			u64 *ext_err1, u64 *ext_err2);
 u64 tdh_mr_extend(struct tdx_td *td, u64 gpa, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_mr_finalize(struct tdx_td *td);
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 24aa9aaad6d8..9d24a1a86a23 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1924,12 +1924,12 @@ static int tdx_spte_demote_private_spte(struct kvm *kvm, gfn_t gfn,
 	u64 err, entry, level_state;
 
 	err = tdh_mem_page_demote(&kvm_tdx->td, gpa, tdx_level, page,
-				  &entry, &level_state);
+				  NULL, &entry, &level_state);
 
 	if (unlikely(tdx_operand_busy(err))) {
 		tdx_no_vcpus_enter_start(kvm);
 		err = tdh_mem_page_demote(&kvm_tdx->td, gpa, tdx_level, page,
-					  &entry, &level_state);
+					  NULL, &entry, &level_state);
 		tdx_no_vcpus_enter_stop(kvm);
 	}
 
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index b7a0ee0f4a50..50f9d49f1c91 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1825,6 +1825,7 @@ u64 tdh_mng_rd(struct tdx_td *td, u64 field, u64 *data)
 EXPORT_SYMBOL_GPL(tdh_mng_rd);
 
 u64 tdh_mem_page_demote(struct tdx_td *td, u64 gpa, int level, struct page *page,
+			struct list_head *pamt_pages,
 			u64 *ext_err1, u64 *ext_err2)
 {
 	struct tdx_module_args args = {
@@ -1832,10 +1833,18 @@ u64 tdh_mem_page_demote(struct tdx_td *td, u64 gpa, int level, struct page *page
 		.rdx = tdx_tdr_pa(td),
 		.r8 = page_to_phys(page),
 	};
-	u64 ret;
+	struct page *pamt_page;
+	u64 *p, ret;
 
+	if (level == TDX_PS_2M) {
+		p = &args.r12;
+		list_for_each_entry(pamt_page, pamt_pages, lru) {
+			*p = page_to_phys(pamt_page);
+			p++;
+		}
+	}
 	tdx_clflush_page(page);
-	ret = seamcall_ret(TDH_MEM_PAGE_DEMOTE, &args);
+	ret = seamcall_saved_ret(TDH_MEM_PAGE_DEMOTE, &args);
 
 	*ext_err1 = args.rcx;
 	*ext_err2 = args.rdx;
-- 
2.43.2