linux-kernel - [PATCH v7 1/2] x86/tdx: Retry TDVMCALL_MAP

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230616044701.15888-2-decui@microsoft.com>
Date:   Thu, 15 Jun 2023 21:47:00 -0700
From:   Dexuan Cui <decui@...rosoft.com>
To:     ak@...ux.intel.com, arnd@...db.de, bp@...en8.de,
        brijesh.singh@....com, dan.j.williams@...el.com,
        dave.hansen@...el.com, dave.hansen@...ux.intel.com,
        haiyangz@...rosoft.com, hpa@...or.com, jane.chu@...cle.com,
        kirill.shutemov@...ux.intel.com, kys@...rosoft.com,
        linux-arch@...r.kernel.org, linux-hyperv@...r.kernel.org,
        luto@...nel.org, mingo@...hat.com, peterz@...radead.org,
        rostedt@...dmis.org, sathyanarayanan.kuppuswamy@...ux.intel.com,
        seanjc@...gle.com, tglx@...utronix.de, tony.luck@...el.com,
        wei.liu@...nel.org, x86@...nel.org, mikelley@...rosoft.com
Cc:     linux-kernel@...r.kernel.org, Tianyu.Lan@...rosoft.com,
        rick.p.edgecombe@...el.com, Dexuan Cui <decui@...rosoft.com>
Subject: [PATCH v7 1/2] x86/tdx: Retry TDVMCALL_MAP_GPA() when needed

GHCI spec for TDX 1.0 says that the MapGPA call may fail with the R10
error code = TDG.VP.VMCALL_RETRY (1), and the guest must retry this
operation for the pages in the region starting at the GPA specified
in R11.

When a fully enlightened TDX guest runs on Hyper-V, Hyper-V can return
the retry error when set_memory_decrypted() is called to decrypt up to
1GB of swiotlb bounce buffers.

Acked-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Reviewed-by: Michael Kelley <mikelley@...rosoft.com>
Signed-off-by: Dexuan Cui <decui@...rosoft.com>
---

Changes in v2:
  Used __tdx_hypercall() directly in tdx_map_gpa().
  Added a max_retry_cnt of 1000.
  Renamed a few variables, e.g., r11 -> map_fail_paddr.

Changes in v3:
  Changed max_retry_cnt from 1000 to 3.

Changes in v4:
  __tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT) -> __tdx_hypercall_ret()
  Added Kirill's Acked-by.

Changes in v5:
  Added Michael's Reviewed-by.

Changes in v6: None.

Changes in v7:
  Addressed Dave's comments:
  see https://lwn.net/ml/linux-kernel/SA1PR21MB1335736123C2BCBBFD7460C3BF46A@SA1PR21MB1335.namprd21.prod.outlook.com


 arch/x86/coco/tdx/tdx.c | 65 +++++++++++++++++++++++++++++++++--------
 1 file changed, 53 insertions(+), 12 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index cde174f4e239..5b62a1f5bd79 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -28,6 +28,8 @@
 #define TDVMCALL_MAP_GPA		0x10001
 #define TDVMCALL_REPORT_FATAL_ERROR	0x10003
 
+#define TDVMCALL_STATUS_RETRY		1
+
 /* MMIO direction */
 #define EPT_READ	0
 #define EPT_WRITE	1
@@ -777,14 +779,16 @@ static bool try_accept_one(phys_addr_t *start, unsigned long len,
 }
 
 /*
- * Inform the VMM of the guest's intent for this physical page: shared with
- * the VMM or private to the guest.  The VMM is expected to change its mapping
- * of the page in response.
+ * Notify the VMM about page mapping conversion. More info about ABI
+ * can be found in TDX Guest-Host-Communication Interface (GHCI),
+ * section "TDG.VP.VMCALL<MapGPA>".
  */
-static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
+static bool tdx_map_gpa(phys_addr_t start, phys_addr_t end, bool enc)
 {
-	phys_addr_t start = __pa(vaddr);
-	phys_addr_t end   = __pa(vaddr + numpages * PAGE_SIZE);
+	const int max_retries_per_page = 3;
+	struct tdx_hypercall_args args;
+	u64 map_fail_paddr, ret;
+	int retry_count = 0;
 
 	if (!enc) {
 		/* Set the shared (decrypted) bits: */
@@ -792,12 +796,49 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
 		end   |= cc_mkdec(0);
 	}
 
-	/*
-	 * Notify the VMM about page mapping conversion. More info about ABI
-	 * can be found in TDX Guest-Host-Communication Interface (GHCI),
-	 * section "TDG.VP.VMCALL<MapGPA>"
-	 */
-	if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0))
+	while (retry_count < max_retries_per_page) {
+		memset(&args, 0, sizeof(args));
+		args.r10 = TDX_HYPERCALL_STANDARD;
+		args.r11 = TDVMCALL_MAP_GPA;
+		args.r12 = start;
+		args.r13 = end - start;
+
+		ret = __tdx_hypercall_ret(&args);
+		if (ret != TDVMCALL_STATUS_RETRY)
+			return !ret;
+		/*
+		 * The guest must retry the operation for the pages in the
+		 * region starting at the GPA specified in R11. R11 comes
+		 * from the untrusted VMM. Sanity check it.
+		 */
+		map_fail_paddr = args.r11;
+		if (map_fail_paddr < start || map_fail_paddr >= end)
+			return false;
+
+		/* "Consume" a retry without forward progress */
+		if (map_fail_paddr == start) {
+			retry_count++;
+			continue;
+		}
+
+		start = map_fail_paddr;
+		retry_count = 0;
+	}
+
+	return false;
+}
+
+/*
+ * Inform the VMM of the guest's intent for this physical page: shared with
+ * the VMM or private to the guest. The VMM is expected to change its mapping
+ * of the page in response.
+ */
+static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
+{
+	phys_addr_t start = __pa(vaddr);
+	phys_addr_t end   = __pa(vaddr + numpages * PAGE_SIZE);
+
+	if (!tdx_map_gpa(start, end, enc))
 		return false;
 
 	/* private->shared conversion  requires only MapGPA call */
-- 
2.25.1