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 2/2] x86/virt/tdx: Use PFN directly for unmapping guest private memory
Date: Thu, 19 Mar 2026 08:58:08 +0800 [thread overview]
Message-ID: <20260319005808.9013-1-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 assumptions that memory unmapped from a
TDX guest is backed by refcounted struct page memory.
APIs tdh_phymem_page_wbinvd_hkid(), tdx_quirk_reset_page() are used when
unmapping guest private memory from S-EPT. Since mapping of guest private
memory places no requirements on how KVM and guest_memfd manage memory,
neither does guest private memory unmapping.
Rip out the misguided struct page assumptions/constraints by having the two
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_phymem_page_wbinvd_hkid() and tdx_quirk_reset_page() are
exported to KVM only.
Update mk_keyed_paddr(), which is invoked by tdh_phymem_page_wbinvd_hkid(),
to take PFN as parameter accordingly. Opportunistically, move
mk_keyed_paddr() from tdx.h to tdx.c since there are no external users.
Have tdx_reclaim_page() remain using struct page as parameter since it's
currently not used for removing guest private memory yet.
[Yan: Use kvm_pfn_t, drop reclaim API param update, move mk_keyed_paddr()]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
---
arch/x86/include/asm/tdx.h | 15 ++-------------
arch/x86/kvm/vmx/tdx.c | 10 +++++-----
arch/x86/virt/vmx/tdx/tdx.c | 16 +++++++++++-----
3 files changed, 18 insertions(+), 23 deletions(-)
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index f3f0b1872176..6ceb4cd9ff21 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -153,7 +153,7 @@ int tdx_guest_keyid_alloc(void);
u32 tdx_get_nr_guest_keyids(void);
void tdx_guest_keyid_free(unsigned int keyid);
-void tdx_quirk_reset_page(struct page *page);
+void tdx_quirk_reset_page(kvm_pfn_t pfn);
struct tdx_td {
/* TD root structure: */
@@ -177,17 +177,6 @@ struct tdx_vp {
struct page **tdcx_pages;
};
-static inline u64 mk_keyed_paddr(u16 hkid, struct page *page)
-{
- u64 ret;
-
- ret = page_to_phys(page);
- /* KeyID bits are just above the physical address bits: */
- ret |= (u64)hkid << boot_cpu_data.x86_phys_bits;
-
- return ret;
-}
-
static inline int pg_level_to_tdx_sept_level(enum pg_level level)
{
WARN_ON_ONCE(level == PG_LEVEL_NONE);
@@ -219,7 +208,7 @@ u64 tdh_mem_track(struct tdx_td *tdr);
u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, u64 level, u64 *ext_err1, u64 *ext_err2);
u64 tdh_phymem_cache_wb(bool resume);
u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td);
-u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page);
+u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, kvm_pfn_t pfn);
#else
static inline void tdx_init(void) { }
static inline u32 tdx_get_nr_guest_keyids(void) { return 0; }
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 1f1abc5b5655..75ad3debcd84 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -343,7 +343,7 @@ static int tdx_reclaim_page(struct page *page)
r = __tdx_reclaim_page(page);
if (!r)
- tdx_quirk_reset_page(page);
+ tdx_quirk_reset_page(page_to_pfn(page));
return r;
}
@@ -597,7 +597,7 @@ static void tdx_reclaim_td_control_pages(struct kvm *kvm)
if (TDX_BUG_ON(err, TDH_PHYMEM_PAGE_WBINVD, kvm))
return;
- tdx_quirk_reset_page(kvm_tdx->td.tdr_page);
+ tdx_quirk_reset_page(page_to_pfn(kvm_tdx->td.tdr_page));
__free_page(kvm_tdx->td.tdr_page);
kvm_tdx->td.tdr_page = NULL;
@@ -1776,9 +1776,9 @@ static int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
static void tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
enum pg_level level, u64 mirror_spte)
{
- struct page *page = pfn_to_page(spte_to_pfn(mirror_spte));
int tdx_level = pg_level_to_tdx_sept_level(level);
struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ kvm_pfn_t pfn = spte_to_pfn(mirror_spte);
gpa_t gpa = gfn_to_gpa(gfn);
u64 err, entry, level_state;
@@ -1817,11 +1817,11 @@ static void tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
if (TDX_BUG_ON_2(err, TDH_MEM_PAGE_REMOVE, entry, level_state, kvm))
return;
- err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page);
+ err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, pfn);
if (TDX_BUG_ON(err, TDH_PHYMEM_PAGE_WBINVD, kvm))
return;
- tdx_quirk_reset_page(page);
+ tdx_quirk_reset_page(pfn);
}
void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index a9dd75190c67..2f9d07ad1a9a 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -730,9 +730,9 @@ static void tdx_quirk_reset_paddr(unsigned long base, unsigned long size)
mb();
}
-void tdx_quirk_reset_page(struct page *page)
+void tdx_quirk_reset_page(kvm_pfn_t pfn)
{
- tdx_quirk_reset_paddr(page_to_phys(page), PAGE_SIZE);
+ tdx_quirk_reset_paddr(PFN_PHYS(pfn), PAGE_SIZE);
}
EXPORT_SYMBOL_FOR_KVM(tdx_quirk_reset_page);
@@ -1907,21 +1907,27 @@ u64 tdh_phymem_cache_wb(bool resume)
}
EXPORT_SYMBOL_FOR_KVM(tdh_phymem_cache_wb);
+static inline u64 mk_keyed_paddr(u16 hkid, kvm_pfn_t pfn)
+{
+ /* KeyID bits are just above the physical address bits. */
+ return PFN_PHYS(pfn) | ((u64)hkid << boot_cpu_data.x86_phys_bits);
+}
+
u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td)
{
struct tdx_module_args args = {};
- args.rcx = mk_keyed_paddr(tdx_global_keyid, td->tdr_page);
+ args.rcx = mk_keyed_paddr(tdx_global_keyid, page_to_pfn(td->tdr_page));
return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
}
EXPORT_SYMBOL_FOR_KVM(tdh_phymem_page_wbinvd_tdr);
-u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page)
+u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, kvm_pfn_t pfn)
{
struct tdx_module_args args = {};
- args.rcx = mk_keyed_paddr(hkid, page);
+ args.rcx = mk_keyed_paddr(hkid, pfn);
return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
}
--
2.43.2
next prev parent reply other threads:[~2026-03-19 1:37 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 ` [PATCH 1/2] x86/virt/tdx: Use PFN directly for mapping " Yan Zhao
2026-03-19 10:39 ` 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 ` Yan Zhao [this message]
2026-03-19 3:20 ` [PATCH 2/2] x86/virt/tdx: Use PFN directly for unmapping " 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=20260319005808.9013-1-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.