diff mbox series

[v3,57/70] i386/tdx: Wire TDX_REPORT_FATAL_ERROR with GuestPanic facility

Message ID 20231115071519.2864957-58-xiaoyao.li@intel.com (mailing list archive)
State New, archived
Headers show
Series QEMU Guest memfd + QEMU TDX support | expand

Commit Message

Xiaoyao Li Nov. 15, 2023, 7:15 a.m. UTC
Integrate TDX's TDX_REPORT_FATAL_ERROR into QEMU GuestPanic facility

Originated-from: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
---
Changes from v2:
- Add docmentation of new type and struct (Daniel)
- refine the error message handling (Daniel)
---
 qapi/run-state.json   | 27 ++++++++++++++++++++--
 system/runstate.c     | 54 +++++++++++++++++++++++++++++++++++++++++++
 target/i386/kvm/tdx.c | 24 +++++++++++++++++--
 3 files changed, 101 insertions(+), 4 deletions(-)

Comments

Markus Armbruster Dec. 1, 2023, 11:11 a.m. UTC | #1
Xiaoyao Li <xiaoyao.li@intel.com> writes:

> Integrate TDX's TDX_REPORT_FATAL_ERROR into QEMU GuestPanic facility
>
> Originated-from: Isaku Yamahata <isaku.yamahata@intel.com>
> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
> ---
> Changes from v2:
> - Add docmentation of new type and struct (Daniel)
> - refine the error message handling (Daniel)
> ---
>  qapi/run-state.json   | 27 ++++++++++++++++++++--
>  system/runstate.c     | 54 +++++++++++++++++++++++++++++++++++++++++++
>  target/i386/kvm/tdx.c | 24 +++++++++++++++++--
>  3 files changed, 101 insertions(+), 4 deletions(-)
>
> diff --git a/qapi/run-state.json b/qapi/run-state.json
> index f216ba54ec4c..e18f62eaef77 100644
> --- a/qapi/run-state.json
> +++ b/qapi/run-state.json
> @@ -496,10 +496,12 @@
>  #
>  # @s390: s390 guest panic information type (Since: 2.12)
>  #
> +# @tdx: tdx guest panic information type (Since: 8.2)
> +#
>  # Since: 2.9
>  ##
>  { 'enum': 'GuestPanicInformationType',
> -  'data': [ 'hyper-v', 's390' ] }
> +  'data': [ 'hyper-v', 's390', 'tdx' ] }
>  
>  ##
>  # @GuestPanicInformation:
> @@ -514,7 +516,8 @@
>   'base': {'type': 'GuestPanicInformationType'},
>   'discriminator': 'type',
>   'data': {'hyper-v': 'GuestPanicInformationHyperV',
> -          's390': 'GuestPanicInformationS390'}}
> +          's390': 'GuestPanicInformationS390',
> +          'tdx' : 'GuestPanicInformationTdx'}}
>  
>  ##
>  # @GuestPanicInformationHyperV:
> @@ -577,6 +580,26 @@
>            'psw-addr': 'uint64',
>            'reason': 'S390CrashReason'}}
>  
> +##
> +# @GuestPanicInformationTdx:
> +#
> +# TDX GHCI TDG.VP.VMCALL<ReportFatalError> specific guest panic information

Long line.  Suggest

   # Guest panic information specific to TDX GHCI
   # TDG.VP.VMCALL<ReportFatalError>.

> +#
> +# @error-code: TD-specific error code
> +#
> +# @gpa: 4KB-aligned guest physical address of the page that containing
> +#     additional error data

"address of a page" implies the address is page-aligned.  4KB-aligned
feels redundant.  What about

   # @qpa: guest-physical address of a page that contains additional
   #     error data.

But in what format is the "additional error data"?

> +#
> +# @message: TD guest provided message string.  (It's not so trustable
> +#     and cannot be assumed to be well formed because it comes from guest)

guest-provided

For "well-formed" to make sense, we'd need an idea of the form / syntax.

If it's a human-readable error message, we could go with

   # @message: Human-readable error message provided by the guest.  Not
   #     to be trusted.

> +#
> +# Since: 8.2
> +##
> +{'struct': 'GuestPanicInformationTdx',
> + 'data': {'error-code': 'uint64',
> +          'gpa': 'uint64',
> +          'message': 'str'}}
> +
>  ##
>  # @MEMORY_FAILURE:
>  #

[...]
Xiaoyao Li Dec. 7, 2023, 8:11 a.m. UTC | #2
On 12/1/2023 7:11 PM, Markus Armbruster wrote:
> Xiaoyao Li <xiaoyao.li@intel.com> writes:
> 
>> Integrate TDX's TDX_REPORT_FATAL_ERROR into QEMU GuestPanic facility
>>
>> Originated-from: Isaku Yamahata <isaku.yamahata@intel.com>
>> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
>> ---
>> Changes from v2:
>> - Add docmentation of new type and struct (Daniel)
>> - refine the error message handling (Daniel)
>> ---
>>   qapi/run-state.json   | 27 ++++++++++++++++++++--
>>   system/runstate.c     | 54 +++++++++++++++++++++++++++++++++++++++++++
>>   target/i386/kvm/tdx.c | 24 +++++++++++++++++--
>>   3 files changed, 101 insertions(+), 4 deletions(-)
>>
>> diff --git a/qapi/run-state.json b/qapi/run-state.json
>> index f216ba54ec4c..e18f62eaef77 100644
>> --- a/qapi/run-state.json
>> +++ b/qapi/run-state.json
>> @@ -496,10 +496,12 @@
>>   #
>>   # @s390: s390 guest panic information type (Since: 2.12)
>>   #
>> +# @tdx: tdx guest panic information type (Since: 8.2)
>> +#
>>   # Since: 2.9
>>   ##
>>   { 'enum': 'GuestPanicInformationType',
>> -  'data': [ 'hyper-v', 's390' ] }
>> +  'data': [ 'hyper-v', 's390', 'tdx' ] }
>>   
>>   ##
>>   # @GuestPanicInformation:
>> @@ -514,7 +516,8 @@
>>    'base': {'type': 'GuestPanicInformationType'},
>>    'discriminator': 'type',
>>    'data': {'hyper-v': 'GuestPanicInformationHyperV',
>> -          's390': 'GuestPanicInformationS390'}}
>> +          's390': 'GuestPanicInformationS390',
>> +          'tdx' : 'GuestPanicInformationTdx'}}
>>   
>>   ##
>>   # @GuestPanicInformationHyperV:
>> @@ -577,6 +580,26 @@
>>             'psw-addr': 'uint64',
>>             'reason': 'S390CrashReason'}}
>>   
>> +##
>> +# @GuestPanicInformationTdx:
>> +#
>> +# TDX GHCI TDG.VP.VMCALL<ReportFatalError> specific guest panic information
> 
> Long line.  Suggest
> 
>     # Guest panic information specific to TDX GHCI
>     # TDG.VP.VMCALL<ReportFatalError>.

As I asked in patch #52, what's the limitation of one line?

>> +#
>> +# @error-code: TD-specific error code
>> +#
>> +# @gpa: 4KB-aligned guest physical address of the page that containing
>> +#     additional error data
> 
> "address of a page" implies the address is page-aligned.  4KB-aligned
> feels redundant.  What about
> 
>     # @qpa: guest-physical address of a page that contains additional
>     #     error data.
> 
> But in what format is the "additional error data"?

it's expected to hold a zero-terminated string.

>> +#
>> +# @message: TD guest provided message string.  (It's not so trustable
>> +#     and cannot be assumed to be well formed because it comes from guest)
> 
> guest-provided
> 
> For "well-formed" to make sense, we'd need an idea of the form / syntax.
> 
> If it's a human-readable error message, we could go with
> 
>     # @message: Human-readable error message provided by the guest.  Not
>     #     to be trusted.
>

looks good. I will your version.

>> +#
>> +# Since: 8.2
>> +##
>> +{'struct': 'GuestPanicInformationTdx',
>> + 'data': {'error-code': 'uint64',
>> +          'gpa': 'uint64',
>> +          'message': 'str'}}
>> +
>>   ##
>>   # @MEMORY_FAILURE:
>>   #
> 
> [...]
>
diff mbox series

Patch

diff --git a/qapi/run-state.json b/qapi/run-state.json
index f216ba54ec4c..e18f62eaef77 100644
--- a/qapi/run-state.json
+++ b/qapi/run-state.json
@@ -496,10 +496,12 @@ 
 #
 # @s390: s390 guest panic information type (Since: 2.12)
 #
+# @tdx: tdx guest panic information type (Since: 8.2)
+#
 # Since: 2.9
 ##
 { 'enum': 'GuestPanicInformationType',
-  'data': [ 'hyper-v', 's390' ] }
+  'data': [ 'hyper-v', 's390', 'tdx' ] }
 
 ##
 # @GuestPanicInformation:
@@ -514,7 +516,8 @@ 
  'base': {'type': 'GuestPanicInformationType'},
  'discriminator': 'type',
  'data': {'hyper-v': 'GuestPanicInformationHyperV',
-          's390': 'GuestPanicInformationS390'}}
+          's390': 'GuestPanicInformationS390',
+          'tdx' : 'GuestPanicInformationTdx'}}
 
 ##
 # @GuestPanicInformationHyperV:
@@ -577,6 +580,26 @@ 
           'psw-addr': 'uint64',
           'reason': 'S390CrashReason'}}
 
+##
+# @GuestPanicInformationTdx:
+#
+# TDX GHCI TDG.VP.VMCALL<ReportFatalError> specific guest panic information
+#
+# @error-code: TD-specific error code
+#
+# @gpa: 4KB-aligned guest physical address of the page that containing
+#     additional error data
+#
+# @message: TD guest provided message string.  (It's not so trustable
+#     and cannot be assumed to be well formed because it comes from guest)
+#
+# Since: 8.2
+##
+{'struct': 'GuestPanicInformationTdx',
+ 'data': {'error-code': 'uint64',
+          'gpa': 'uint64',
+          'message': 'str'}}
+
 ##
 # @MEMORY_FAILURE:
 #
diff --git a/system/runstate.c b/system/runstate.c
index ea9d6c2a32a4..9275e2f265f3 100644
--- a/system/runstate.c
+++ b/system/runstate.c
@@ -518,6 +518,52 @@  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 NUL-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 (!printable && len) {
+        /* 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 NUL */
+            buf[i * 3 - 1] = '\0';
+        else
+            buf[0] = '\0';
+
+        return buf;
+    }
+
+    return message;
+}
+
 void qemu_system_guest_panicked(GuestPanicInformation *info)
 {
     qemu_log_mask(LOG_GUEST_ERROR, "Guest crashed");
@@ -559,7 +605,15 @@  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) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          " TDX guest reports fatal error:\"%s\""
+                          " error code: 0x%016" PRIx64 " gpa page: 0x%016" PRIx64 "\n",
+                          tdx_parse_panic_message(info->u.tdx.message),
+                          info->u.tdx.error_code,
+                          info->u.tdx.gpa);
         }
+
         qapi_free_GuestPanicInformation(info);
     }
 }
diff --git a/target/i386/kvm/tdx.c b/target/i386/kvm/tdx.c
index a42b5cea36c5..23504ba3b05e 100644
--- a/target/i386/kvm/tdx.c
+++ b/target/i386/kvm/tdx.c
@@ -20,6 +20,7 @@ 
 #include "qom/object_interfaces.h"
 #include "standard-headers/asm-x86/kvm_para.h"
 #include "sysemu/kvm.h"
+#include "sysemu/runstate.h"
 #include "sysemu/sysemu.h"
 #include "exec/address-spaces.h"
 #include "exec/ramblock.h"
@@ -1479,11 +1480,26 @@  static void tdx_handle_get_quote(X86CPU *cpu, struct kvm_tdx_vmcall *vmcall)
     vmcall->status_code = TDG_VP_VMCALL_SUCCESS;
 }
 
+static void tdx_panicked_on_fatal_error(X86CPU *cpu, uint64_t error_code,
+                                        uint64_t gpa, char *message)
+{
+    GuestPanicInformation *panic_info;
+
+    panic_info = g_new0(GuestPanicInformation, 1);
+    panic_info->type = GUEST_PANIC_INFORMATION_TYPE_TDX;
+    panic_info->u.tdx.error_code = error_code;
+    panic_info->u.tdx.gpa = gpa;
+    panic_info->u.tdx.message = message;
+
+    qemu_system_guest_panicked(panic_info);
+}
+
 static void tdx_handle_report_fatal_error(X86CPU *cpu,
                                           struct kvm_tdx_vmcall *vmcall)
 {
     uint64_t error_code = vmcall->in_r12;
     char *message = NULL;
+    uint64_t gpa = -1ull;
 
     if (error_code & 0xffff) {
         error_report("invalid error code of TDG.VP.VMCALL<REPORT_FATAL_ERROR>\n");
@@ -1511,8 +1527,12 @@  static void tdx_handle_report_fatal_error(X86CPU *cpu,
         assert((char *)tmp == message + GUEST_PANIC_INFO_TDX_MESSAGE_MAX);
     }
 
-    error_report("TD guest reports fatal error. %s\n", message ? : "");
-    exit(1);
+#define TDX_REPORT_FATAL_ERROR_GPA_VALID    BIT_ULL(63)
+    if (error_code & TDX_REPORT_FATAL_ERROR_GPA_VALID) {
+        gpa = vmcall->in_r13;
+    }
+
+    tdx_panicked_on_fatal_error(cpu, error_code, gpa, message);
 }
 
 static void tdx_handle_setup_event_notify_interrupt(X86CPU *cpu,