[PATCH RESEND v9 1/2] x86/tdx: Retry TDVMCALL_MAP_GPA() when needed

[Dexuan Cui]

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@xxxxxxxxxxxxxxx>
Reviewed-by: Michael Kelley <mikelley@xxxxxxxxxxxxx>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@xxxxxxxxxxxxxxx>
Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
---
 arch/x86/coco/tdx/tdx.c           | 64 +++++++++++++++++++++++++------
 arch/x86/include/asm/shared/tdx.h |  2 +
 2 files changed, 54 insertions(+), 12 deletions(-)

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@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Changes in v8:
  Rebased to tip.git's master branch.

Changes in v9:
  Added a comment before 'max_retries_per_page'.
  Moved 'args', 'map_fail_paddr' and 'ret' into the loop.
  Added Kuppuswamy Sathyanarayanan's Reviewed-by.

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 1d6b863c42b0..746075d20cd2 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -703,14 +703,15 @@ static bool tdx_cache_flush_required(void)
 }
 
 /*
- * 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);
+	/* Retrying the hypercall a second time should succeed; use 3 just in case */
+	const int max_retries_per_page = 3;
+	int retry_count = 0;
 
 	if (!enc) {
 		/* Set the shared (decrypted) bits: */
@@ -718,12 +719,51 @@ 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) {
+		struct tdx_hypercall_args args = {
+			.r10 = TDX_HYPERCALL_STANDARD,
+			.r11 = TDVMCALL_MAP_GPA,
+			.r12 = start,
+			.r13 = end - start };
+
+		u64 map_fail_paddr;
+		u64 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;
 
 	/* shared->private conversion requires memory to be accepted before use */
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index 90ea813c4b99..9db89a99ae5b 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -24,6 +24,8 @@
 #define TDVMCALL_MAP_GPA		0x10001
 #define TDVMCALL_REPORT_FATAL_ERROR	0x10003
 
+#define TDVMCALL_STATUS_RETRY		1
+
 #ifndef __ASSEMBLY__
 
 /*
-- 
2.25.1