[PATCH v3 04/14] x86/virt/tdx: Add SEAMCALL wrappers for TDX page cache management

[Paolo Bonzini]

From: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>

Intel TDX protects guest VMs from malicious host and certain physical
attacks. The TDX module uses pages provided by the host for both control
structures and for TD guest pages. These pages are encrypted using the
MK-TME encryption engine, with its special requirements around cache
invalidation. For its own security, the TDX module ensures pages are
flushed properly and track which usage they are currently assigned. For
creating and tearing down TD VMs and vCPUs KVM will need to use the
TDH.PHYMEM.PAGE.RECLAIM, TDH.PHYMEM.CACHE.WB, and TDH.PHYMEM.PAGE.WBINVD
SEAMCALLs.

Add tdh_phymem_page_reclaim() to enable KVM to call
TDH.PHYMEM.PAGE.RECLAIM to reclaim the page for use by the host kernel.
This effectively resets its state in the TDX module's page tracking
(PAMT), if the page is available to be reclaimed. This will be used by KVM
to reclaim the various types of pages owned by the TDX module. It will
have a small wrapper in KVM that retries in the case of a relevant error
code. Don't implement this wrapper in arch/x86 because KVM's solution
around retrying SEAMCALLs will be better located in a single place.

Add tdh_phymem_cache_wb() to enable KVM to call TDH.PHYMEM.CACHE.WB to do
a cache write back in a way that the TDX module can verify, before it
allows a KeyID to be freed. The KVM code will use this to have a small
wrapper that handles retries. Since the TDH.PHYMEM.CACHE.WB operation is
interruptible, have tdh_phymem_cache_wb() take a resume argument to pass
this info to the TDX module for restarts. It is worth noting that this
SEAMCALL uses a SEAM specific MSR to do the write back in sections. In
this way it does export some new functionality that affects CPU state.

Add tdh_phymem_page_wbinvd_tdr() to enable KVM to call
TDH.PHYMEM.PAGE.WBINVD to do a cache write back and invalidate of a TDR,
using the global KeyID. The underlying TDH.PHYMEM.PAGE.WBINVD SEAMCALL
requires the related KeyID to be encoded into the SEAMCALL args. Since the
global KeyID is not exposed to KVM, a dedicated wrapper is needed for TDR
focused TDH.PHYMEM.PAGE.WBINVD operations.

Co-developed-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
Signed-off-by: Kai Huang <kai.huang@xxxxxxxxx>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
Reviewed-by: Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx>
Reviewed-by: Yuan Yao <yuan.yao@xxxxxxxxx>
Message-ID: <20241203010317.827803-5-rick.p.edgecombe@xxxxxxxxx>
Acked-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
 arch/x86/include/asm/tdx.h  | 16 ++++++++++++++
 arch/x86/virt/vmx/tdx/tdx.c | 42 +++++++++++++++++++++++++++++++++++++
 arch/x86/virt/vmx/tdx/tdx.h |  3 +++
 3 files changed, 61 insertions(+)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 2b993ea24297..4176f734118b 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -137,6 +137,19 @@ 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 |= hkid << boot_cpu_data.x86_phys_bits;
+	
+	return ret;
+
+}
+
 u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page);
 u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page);
 u64 tdh_mng_key_config(struct tdx_td *td);
@@ -146,6 +159,9 @@ u64 tdh_mng_key_freeid(struct tdx_td *td);
 u64 tdh_mng_init(struct tdx_td *td, u64 td_params, u64 *extended_err);
 u64 tdh_vp_init(struct tdx_vp *vp, u64 initial_rcx);
 u64 tdh_vp_init_apicid(struct tdx_vp *vp, u64 initial_rcx, u32 x2apicid);
+u64 tdh_phymem_page_reclaim(struct page *page, u64 *tdx_pt, u64 *tdx_owner, u64 *tdx_size);
+u64 tdh_phymem_cache_wb(bool resume);
+u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td);
 #else
 static inline void tdx_init(void) { }
 static inline int tdx_cpu_enable(void) { return -ENODEV; }
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index a3804e8bdf55..39c4d023e452 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1586,3 +1586,45 @@ u64 tdh_vp_init_apicid(struct tdx_vp *vp, u64 initial_rcx, u32 x2apicid)
 	return seamcall(TDH_VP_INIT | (1ULL << TDX_VERSION_SHIFT), &args);
 }
 EXPORT_SYMBOL_GPL(tdh_vp_init_apicid);
+
+/*
+ * TDX ABI defines output operands as PT, OWNER and SIZE. These are TDX defined fomats.
+ * So despite the names, they must be interpted specially as described by the spec. Return
+ * them only for error reporting purposes.
+ */
+u64 tdh_phymem_page_reclaim(struct page *page, u64 *tdx_pt, u64 *tdx_owner, u64 *tdx_size)
+{
+	struct tdx_module_args args = {
+		.rcx = page_to_phys(page),
+	};
+	u64 ret;
+
+	ret = seamcall_ret(TDH_PHYMEM_PAGE_RECLAIM, &args);
+
+	*tdx_pt = args.rcx;
+	*tdx_owner = args.rdx;
+	*tdx_size = args.r8;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_page_reclaim);
+
+u64 tdh_phymem_cache_wb(bool resume)
+{
+	struct tdx_module_args args = {
+		.rcx = resume ? 1 : 0,
+	};
+
+	return seamcall(TDH_PHYMEM_CACHE_WB, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_cache_wb);
+
+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);
+
+	return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_page_wbinvd_tdr);
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index f0464f7d9780..7a15c9afcdfa 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -24,11 +24,14 @@
 #define TDH_MNG_INIT			21
 #define TDH_VP_INIT			22
 #define TDH_PHYMEM_PAGE_RDMD		24
+#define TDH_PHYMEM_PAGE_RECLAIM		28
 #define TDH_SYS_KEY_CONFIG		31
 #define TDH_SYS_INIT			33
 #define TDH_SYS_RD			34
 #define TDH_SYS_LP_INIT			35
 #define TDH_SYS_TDMR_INIT		36
+#define TDH_PHYMEM_CACHE_WB		40
+#define TDH_PHYMEM_PAGE_WBINVD		41
 #define TDH_SYS_CONFIG			45
 
 /*
-- 
2.43.5