[RFC PATCH v2 01/23] x86/tdx: Enhance tdh_mem_page_aug() to support huge pages

[Yan Zhao <yan.y.zhao@intel.com>]

Enhance the SEAMCALL wrapper tdh_mem_page_aug() to support huge pages.

The SEAMCALL TDH_MEM_PAGE_AUG currently supports adding physical memory to
the S-EPT up to 2MB in size.

While keeping the "level" parameter in the tdh_mem_page_aug() wrapper to
allow callers to specify the physical memory size, introduce the parameters
"folio" and "start_idx" to specify the physical memory starting from the
page at "start_idx" within the "folio". The specified physical memory must
be fully contained within a single folio.

Invoke tdx_clflush_page() for each 4KB segment of the physical memory being
added. tdx_clflush_page() performs CLFLUSH operations on certain
TDX-capable platforms, or conservatively on all TDX-capable platforms, to
prevent dirty cache lines from writing back later and corrupting TD memory.

Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
---
RFC v2:
- Refine patch log. (Rick)
- Removed the level checking. (Kirill, Chao Gao)
- Use "folio", and "start_idx" rather than "page".
- Return TDX_OPERAND_INVALID if the specified physical memory is not
  contained within a single folio.
- Use PTE_SHIFT to replace the 9 in "1 << (level * 9)" (Kirill)
- Use C99-style definition of variables inside a loop. (Nikolay Borisov)

RFC v1:
- Rebased to new tdh_mem_page_aug() with "struct page *" as param.
- Check folio, folio_page_idx.
---
 arch/x86/include/asm/tdx.h  |  3 ++-
 arch/x86/kvm/vmx/tdx.c      |  4 +++-
 arch/x86/virt/vmx/tdx/tdx.c | 14 +++++++++++---
 3 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 48d579092590..f968b736871a 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -171,7 +171,8 @@ u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page);
 u64 tdh_mem_page_add(struct tdx_td *td, u64 gpa, struct page *page, struct page *source, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page);
-u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct folio *folio,
+		     unsigned long start_idx, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_mem_range_block(struct tdx_td *td, u64 gpa, int level, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_mng_key_config(struct tdx_td *td);
 u64 tdh_mng_create(struct tdx_td *td, u16 hkid);
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index ed67f842b6ec..0a2b183899d8 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1593,11 +1593,13 @@ static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,
 {
 	int tdx_level = pg_level_to_tdx_sept_level(level);
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	struct folio *folio = page_folio(page);
 	gpa_t gpa = gfn_to_gpa(gfn);
 	u64 entry, level_state;
 	u64 err;
 
-	err = tdh_mem_page_aug(&kvm_tdx->td, gpa, tdx_level, page, &entry, &level_state);
+	err = tdh_mem_page_aug(&kvm_tdx->td, gpa, tdx_level, folio,
+			       folio_page_idx(folio, page), &entry, &level_state);
 	if (unlikely(tdx_operand_busy(err))) {
 		tdx_unpin(kvm, page);
 		return -EBUSY;
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index e411cf878547..580f14f64822 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1730,16 +1730,24 @@ u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page)
 }
 EXPORT_SYMBOL_GPL(tdh_vp_addcx);
 
-u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2)
+u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct folio *folio,
+		     unsigned long start_idx, u64 *ext_err1, u64 *ext_err2)
 {
+	struct page *start = folio_page(folio, start_idx);
+	unsigned long npages = 1 << (level * PTE_SHIFT);
 	struct tdx_module_args args = {
 		.rcx = gpa | level,
 		.rdx = tdx_tdr_pa(td),
-		.r8 = page_to_phys(page),
+		.r8 = page_to_phys(start),
 	};
 	u64 ret;
 
-	tdx_clflush_page(page);
+	if (start_idx + npages > folio_nr_pages(folio))
+		return TDX_OPERAND_INVALID;
+
+	for (int i = 0; i < npages; i++)
+		tdx_clflush_page(nth_page(start, i));
+
 	ret = seamcall_ret(TDH_MEM_PAGE_AUG, &args);
 
 	*ext_err1 = args.rcx;
-- 
2.43.2