All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yan Zhao <yan.y.zhao@intel.com>
To: seanjc@google.com, pbonzini@redhat.com, dave.hansen@linux.intel.com
Cc: tglx@kernel.org, mingo@redhat.com, bp@alien8.de, kas@kernel.org,
	x86@kernel.org, linux-kernel@vger.kernel.org,
	kvm@vger.kernel.org, linux-coco@lists.linux.dev,
	kai.huang@intel.com, rick.p.edgecombe@intel.com,
	yan.y.zhao@intel.com, yilun.xu@linux.intel.com,
	vannapurve@google.com, ackerleytng@google.com, sagis@google.com,
	binbin.wu@linux.intel.com, xiaoyao.li@intel.com,
	isaku.yamahata@intel.com
Subject: [PATCH 1/2] x86/virt/tdx: Use PFN directly for mapping guest private memory
Date: Thu, 19 Mar 2026 08:57:03 +0800	[thread overview]
Message-ID: <20260319005703.8983-1-yan.y.zhao@intel.com> (raw)
In-Reply-To: <20260319005605.8965-1-yan.y.zhao@intel.com>

From: Sean Christopherson <seanjc@google.com>

Remove the completely unnecessary assumption that memory mapped into a TDX
guest is backed by refcounted struct page memory. From KVM's point of view,
TDH_MEM_PAGE_ADD and TDH_MEM_PAGE_AUG are glorified writes to PTEs, so they
have no business placing requirements on how KVM and guest_memfd manage
memory.

Rip out the misguided struct page assumptions/constraints and instead have
the two SEAMCALL wrapper APIs take PFN directly. This ensures that for
future huge page support in S-EPT, the kernel doesn't pick up even worse
assumptions like "a hugepage must be contained in a single folio".

Use "kvm_pfn_t pfn" for type safety. Using this KVM type is appropriate
since APIs tdh_mem_page_add() and tdh_mem_page_aug() are exported to KVM
only.

[ Yan: Replace "u64 pfn" with "kvm_pfn_t pfn" ]

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
---
 arch/x86/include/asm/tdx.h  |  5 +++--
 arch/x86/kvm/vmx/tdx.c      |  7 +++----
 arch/x86/virt/vmx/tdx/tdx.c | 20 +++++++++++++-------
 3 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index a149740b24e8..f3f0b1872176 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/bits.h>
 #include <linux/mmzone.h>
+#include <linux/kvm_types.h>
 
 #include <asm/errno.h>
 #include <asm/ptrace.h>
@@ -195,10 +196,10 @@ static inline int pg_level_to_tdx_sept_level(enum pg_level level)
 
 u64 tdh_vp_enter(struct tdx_vp *vp, struct tdx_module_args *args);
 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_page_add(struct tdx_td *td, u64 gpa, kvm_pfn_t pfn, 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, kvm_pfn_t pfn, 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 1e47c194af53..1f1abc5b5655 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1624,8 +1624,8 @@ static int tdx_mem_page_add(struct kvm *kvm, gfn_t gfn, enum pg_level level,
 	    KVM_BUG_ON(!kvm_tdx->page_add_src, kvm))
 		return -EIO;
 
-	err = tdh_mem_page_add(&kvm_tdx->td, gpa, pfn_to_page(pfn),
-			       kvm_tdx->page_add_src, &entry, &level_state);
+	err = tdh_mem_page_add(&kvm_tdx->td, gpa, pfn, kvm_tdx->page_add_src,
+			       &entry, &level_state);
 	if (unlikely(tdx_operand_busy(err)))
 		return -EBUSY;
 
@@ -1640,12 +1640,11 @@ 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 page *page = pfn_to_page(pfn);
 	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, pfn, &entry, &level_state);
 	if (unlikely(tdx_operand_busy(err)))
 		return -EBUSY;
 
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index cb9b3210ab71..a9dd75190c67 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -30,7 +30,6 @@
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/idr.h>
-#include <linux/kvm_types.h>
 #include <asm/page.h>
 #include <asm/special_insns.h>
 #include <asm/msr-index.h>
@@ -1568,6 +1567,11 @@ static void tdx_clflush_page(struct page *page)
 	clflush_cache_range(page_to_virt(page), PAGE_SIZE);
 }
 
+static void tdx_clflush_pfn(kvm_pfn_t pfn)
+{
+	clflush_cache_range(__va(PFN_PHYS(pfn)), PAGE_SIZE);
+}
+
 noinstr u64 tdh_vp_enter(struct tdx_vp *td, struct tdx_module_args *args)
 {
 	args->rcx = td->tdvpr_pa;
@@ -1588,17 +1592,18 @@ u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page)
 }
 EXPORT_SYMBOL_FOR_KVM(tdh_mng_addcx);
 
-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_page_add(struct tdx_td *td, u64 gpa, kvm_pfn_t pfn, struct page *source,
+		     u64 *ext_err1, u64 *ext_err2)
 {
 	struct tdx_module_args args = {
 		.rcx = gpa,
 		.rdx = tdx_tdr_pa(td),
-		.r8 = page_to_phys(page),
+		.r8 = PFN_PHYS(pfn),
 		.r9 = page_to_phys(source),
 	};
 	u64 ret;
 
-	tdx_clflush_page(page);
+	tdx_clflush_pfn(pfn);
 	ret = seamcall_ret(TDH_MEM_PAGE_ADD, &args);
 
 	*ext_err1 = args.rcx;
@@ -1639,16 +1644,17 @@ u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page)
 }
 EXPORT_SYMBOL_FOR_KVM(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, kvm_pfn_t pfn,
+		     u64 *ext_err1, u64 *ext_err2)
 {
 	struct tdx_module_args args = {
 		.rcx = gpa | level,
 		.rdx = tdx_tdr_pa(td),
-		.r8 = page_to_phys(page),
+		.r8 = PFN_PHYS(pfn),
 	};
 	u64 ret;
 
-	tdx_clflush_page(page);
+	tdx_clflush_pfn(pfn);
 	ret = seamcall_ret(TDH_MEM_PAGE_AUG, &args);
 
 	*ext_err1 = args.rcx;
-- 
2.43.2


  reply	other threads:[~2026-03-19  1:36 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-19  0:56 [PATCH 0/2] struct page to PFN conversion for TDX guest private memory Yan Zhao
2026-03-19  0:57 ` Yan Zhao [this message]
2026-03-19 10:39   ` [PATCH 1/2] x86/virt/tdx: Use PFN directly for mapping " Kiryl Shutsemau
2026-03-19 11:59     ` Yan Zhao
2026-03-19 12:14       ` Yan Zhao
2026-03-19 12:57       ` Kiryl Shutsemau
2026-03-19 17:27         ` Edgecombe, Rick P
2026-03-20 12:59           ` Kiryl Shutsemau
2026-03-20 17:31             ` Edgecombe, Rick P
2026-03-20 17:38               ` Dave Hansen
2026-03-20 17:48                 ` Edgecombe, Rick P
2026-03-19 18:05   ` Dave Hansen
2026-03-25  9:10     ` Yan Zhao
2026-03-25 16:57       ` Edgecombe, Rick P
2026-03-27  7:03         ` Yan Zhao
2026-03-31 19:13           ` Sean Christopherson
2026-04-02 20:47     ` Sean Christopherson
2026-04-02 21:09       ` Dave Hansen
2026-04-02 22:11         ` Sean Christopherson
2026-04-02 23:23   ` Ackerley Tng
2026-04-02 23:35     ` Sean Christopherson
2026-04-02 23:36     ` Edgecombe, Rick P
2026-04-02 23:46       ` Sean Christopherson
2026-04-02 23:53         ` Edgecombe, Rick P
2026-03-19  0:58 ` [PATCH 2/2] x86/virt/tdx: Use PFN directly for unmapping " Yan Zhao
2026-03-19  3:20   ` Xiaoyao Li
2026-03-19  6:45     ` Yan Zhao
2026-03-19  8:56       ` Xiaoyao Li
2026-03-19  8:56         ` Yan Zhao
2026-04-04  6:39           ` Paolo Bonzini
2026-04-07  0:44             ` Yan Zhao
2026-04-09  6:54               ` Yan Zhao
2026-03-19 18:44         ` Edgecombe, Rick P
2026-03-19 10:48   ` Kiryl Shutsemau
2026-04-09  7:42     ` Yan Zhao

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260319005703.8983-1-yan.y.zhao@intel.com \
    --to=yan.y.zhao@intel.com \
    --cc=ackerleytng@google.com \
    --cc=binbin.wu@linux.intel.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=isaku.yamahata@intel.com \
    --cc=kai.huang@intel.com \
    --cc=kas@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-coco@lists.linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=rick.p.edgecombe@intel.com \
    --cc=sagis@google.com \
    --cc=seanjc@google.com \
    --cc=tglx@kernel.org \
    --cc=vannapurve@google.com \
    --cc=x86@kernel.org \
    --cc=xiaoyao.li@intel.com \
    --cc=yilun.xu@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.