[v7,28/52] i386/tdx: Wire TDX_REPORT_FATAL_ERROR with GuestPanic facility

Commit Message

Xiaoyao Li Jan. 24, 2025, 1:20 p.m. UTC

Integrate TDX's TDX_REPORT_FATAL_ERROR into QEMU GuestPanic facility

Originated-from: Isaku Yamahata <[e-mail]>
Signed-off-by: Xiaoyao Li <[e-mail]>
---
Changes in v6:
- change error_code of GuestPanicInformationTdx from uint64_t to
  uint32_t, to only contains the bit 31:0 returned in r12.

Changes in v5:
- mention additional error information in gpa when it presents;
- refine the documentation; (Markus)

Changes in v4:
- refine the documentation; (Markus)

Changes in v3:
- Add docmentation of new type and struct; (Daniel)
- refine the error message handling; (Daniel)
---
 qapi/run-state.json   | 31 ++++++++++++++++++--
 system/runstate.c     | 67 +++++++++++++++++++++++++++++++++++++++++++
 target/i386/kvm/tdx.c | 24 +++++++++++++++-
 3 files changed, 119 insertions(+), 3 deletions(-)

Patch

diff --git a/qapi/run-state.json b/qapi/run-state.json
index ce95cfa46b73..e63611780a2c 100644
--- a/qapi/run-state.json
+++ b/qapi/run-state.json
@@ -501,10 +501,12 @@ 
 #
 # @s390: s390 guest panic information type (Since: 2.12)
 #
+# @tdx: tdx guest panic information type (Since: 9.0)
+#
 # Since: 2.9
 ##
 { 'enum': 'GuestPanicInformationType',
-  'data': [ 'hyper-v', 's390' ] }
+  'data': [ 'hyper-v', 's390', 'tdx' ] }
 
 ##
 # @GuestPanicInformation:
@@ -519,7 +521,8 @@ 
  'base': {'type': 'GuestPanicInformationType'},
  'discriminator': 'type',
  'data': {'hyper-v': 'GuestPanicInformationHyperV',
-          's390': 'GuestPanicInformationS390'}}
+          's390': 'GuestPanicInformationS390',
+          'tdx' : 'GuestPanicInformationTdx'}}
 
 ##
 # @GuestPanicInformationHyperV:
@@ -598,6 +601,30 @@ 
           'psw-addr': 'uint64',
           'reason': 'S390CrashReason'}}
 
+##
+# @GuestPanicInformationTdx:
+#
+# TDX Guest panic information specific to TDX, as specified in the
+# "Guest-Hypervisor Communication Interface (GHCI) Specification",
+# section TDG.VP.VMCALL<ReportFatalError>.
+#
+# @error-code: TD-specific error code
+#
+# @message: Human-readable error message provided by the guest. Not
+#     to be trusted.
+#
+# @gpa: guest-physical address of a page that contains more verbose
+#     error information, as zero-terminated string.  Present when the
+#     "GPA valid" bit (bit 63) is set in @error-code.
+#
+#
+# Since: 10.0
+##
+{'struct': 'GuestPanicInformationTdx',
+ 'data': {'error-code': 'uint32',
+          'message': 'str',
+          '*gpa': 'uint64'}}
+
 ##
 # @MEMORY_FAILURE:
 #
diff --git a/system/runstate.c b/system/runstate.c
index 272801d30769..c4244c8915c6 100644
--- a/system/runstate.c
+++ b/system/runstate.c
@@ -565,6 +565,60 @@  static void qemu_system_wakeup(void)
     }
 }
 
+static char *tdx_parse_panic_message(char *message)
+{
+    bool printable = false;
+    char *buf = NULL;
+    int len = 0, i;
+
+    /*
+     * Although message is defined as a json string, we shouldn't
+     * unconditionally treat it as is because the guest generated it and
+     * it's not necessarily trustable.
+     */
+    if (message) {
+        /* The caller guarantees the NULL-terminated string. */
+        len = strlen(message);
+
+        printable = len > 0;
+        for (i = 0; i < len; i++) {
+            if (!(0x20 <= message[i] && message[i] <= 0x7e)) {
+                printable = false;
+                break;
+            }
+        }
+    }
+
+    if (len == 0) {
+        buf = g_malloc(1);
+        buf[0] = '\0';
+    } else {
+        if (!printable) {
+            /* 3 = length of "%02x " */
+            buf = g_malloc(len * 3);
+            for (i = 0; i < len; i++) {
+                if (message[i] == '\0') {
+                    break;
+                } else {
+                    sprintf(buf + 3 * i, "%02x ", message[i]);
+                }
+            }
+            if (i > 0) {
+                /* replace the last ' '(space) to NULL */
+                buf[i * 3 - 1] = '\0';
+            } else {
+                buf[0] = '\0';
+            }
+
+        } else {
+            buf = g_malloc(len);
+            memcpy(buf, message, len);
+        }
+    }
+
+    return buf;
+}
+
 void qemu_system_guest_panicked(GuestPanicInformation *info)
 {
     qemu_log_mask(LOG_GUEST_ERROR, "Guest crashed");
@@ -606,7 +660,20 @@  void qemu_system_guest_panicked(GuestPanicInformation *info)
                           S390CrashReason_str(info->u.s390.reason),
                           info->u.s390.psw_mask,
                           info->u.s390.psw_addr);
+        } else if (info->type == GUEST_PANIC_INFORMATION_TYPE_TDX) {
+            char *message = tdx_parse_panic_message(info->u.tdx.message);
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "\nTDX guest reports fatal error:"
+                          " error code: 0x%" PRIx32 " error message:\"%s\"\n",
+                          info->u.tdx.error_code, message);
+            g_free(message);
+            if (info->u.tdx.gpa != -1ull) {
+                qemu_log_mask(LOG_GUEST_ERROR, "Additional error information "
+                              "can be found at gpa page: 0x%" PRIx64 "\n",
+                              info->u.tdx.gpa);
+            }
         }
+
         qapi_free_GuestPanicInformation(info);
     }
 }
diff --git a/target/i386/kvm/tdx.c b/target/i386/kvm/tdx.c
index f857fddd839b..591de30eedf4 100644
--- a/target/i386/kvm/tdx.c
+++ b/target/i386/kvm/tdx.c
@@ -16,6 +16,7 @@ 
 #include "qapi/error.h"
 #include "qom/object_interfaces.h"
 #include "crypto/hash.h"
+#include "system/runstate.h"
 #include "system/system.h"
 #include "exec/ramblock.h"
 
@@ -601,10 +602,25 @@  int tdx_parse_tdvf(void *flash_ptr, int size)
     return tdvf_parse_metadata(&tdx_guest->tdvf, flash_ptr, size);
 }
 
+static void tdx_panicked_on_fatal_error(X86CPU *cpu, uint64_t error_code,
+                                        char *message, uint64_t gpa)
+{
+    GuestPanicInformation *panic_info;
+
+    panic_info = g_new0(GuestPanicInformation, 1);
+    panic_info->type = GUEST_PANIC_INFORMATION_TYPE_TDX;
+    panic_info->u.tdx.error_code = (uint32_t) error_code;
+    panic_info->u.tdx.message = message;
+    panic_info->u.tdx.gpa = gpa;
+
+    qemu_system_guest_panicked(panic_info);
+}
+
 int tdx_handle_report_fatal_error(X86CPU *cpu, struct kvm_run *run)
 {
     uint64_t error_code = run->system_event.data[0];
     char *message = NULL;
+    uint64_t gpa = -1ull;
 
     if (error_code & 0xffff) {
         error_report("TDX: REPORT_FATAL_ERROR: invalid error code: 0x%lx",
@@ -621,7 +637,13 @@  int tdx_handle_report_fatal_error(X86CPU *cpu, struct kvm_run *run)
         message[TDX_FATAL_MESSAGE_MAX] = '\0';
     }
 
-    error_report("TD guest reports fatal error. %s", message ? : "");
+#define TDX_REPORT_FATAL_ERROR_GPA_VALID    BIT_ULL(63)
+    if (error_code & TDX_REPORT_FATAL_ERROR_GPA_VALID) {
+        gpa = run->system_event.data[1];
+    }
+
+    tdx_panicked_on_fatal_error(cpu, error_code, message, gpa);
+
     return -1;
 }