xen: add support for automatic debug key actions in case of crash

When the host crashes it would sometimes be nice to have additional
debug data available which could be produced via debug keys, but
halting the server for manual intervention might be impossible due to
the need to reboot/kexec rather sooner than later.

Add support for automatic debug key actions in case of crashes which
can be activated via boot- or runtime-parameter.

Depending on the type of crash the desired data might be different, so
support different settings for the possible types of crashes.

The parameter is "crash-debug" with the following syntax:

  crash-debug-<type>=<string>

with <type> being one of:

  panic, hwdom, watchdog, kexeccmd, debugkey

and <string> a sequence of debug key characters with '+' having the
special semantics of a 10 millisecond pause.

So "crash-debug-watchdog=0+0qr" would result in special output in case
of watchdog triggered crash (dom0 state, 10 ms pause, dom0 state,
domain info, run queues).

Don't call key handlers in early boot, as some (e.g. for 'd') require
some initializations to be finished, like scheduler or idle domain.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
index 7ec1e804b737df3579423e7529929b9a89fefa28..a713a0535c219665c231e61e9bae71b14c42d27b 100644 (file)
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -574,6 +574,47 @@ reduction of features at Xen's disposal to manage guests.
 ### cpuinfo (x86)
 > `= <boolean>`
 
+### crash-debug-debugkey
+### crash-debug-hwdom
+### crash-debug-kexeccmd
+### crash-debug-panic
+### crash-debug-watchdog
+> `= <string>`
+
+> Can be modified at runtime
+
+Specify debug-key actions in cases of crashes. Each of the parameters applies
+to a different crash reason. The `<string>` is a sequence of debug key
+characters, with `+` having the special meaning of a 10 millisecond pause.
+
+`crash-debug-debugkey` will be used for crashes induced by the `C` debug
+key (i.e. manually induced crash).
+
+`crash-debug-hwdom` denotes a crash of dom0.
+
+`crash-debug-kexeccmd` is an explicit request of dom0 to continue with the
+kdump kernel via kexec. Only available on hypervisors built with CONFIG_KEXEC.
+
+`crash-debug-panic` is a crash of the hypervisor.
+
+`crash-debug-watchdog` is a crash due to the watchdog timer expiring.
+
+It should be noted that dumping diagnosis data to the console can fail in
+multiple ways (missing data, hanging system, ...) depending on the reason
+of the crash, which might have left the hypervisor in a bad state. In case
+a debug-key action leads to another crash recursion will be avoided, so no
+additional debug-key actions will be performed in this case. A crash in the
+early boot phase will not result in any debug-key action, as the system
+might not yet be in a state where the handlers can work.
+
+So e.g. `crash-debug-watchdog=0+0r` would dump dom0 state twice with 10
+milliseconds between the two state dumps, followed by the run queues of the
+hypervisor, if the system crashes due to a watchdog timeout.
+
+Depending on the reason of the system crash it might happen that triggering
+some debug key action will result in a hang instead of dumping data and then
+doing a reboot or crash dump.
+
 ### crashinfo_maxaddr
 > `= <size>`
 

diff --git a/xen/common/kexec.c b/xen/common/kexec.c
index 52cdc4ebc333676a543e421e5d7a9a851410b89e..ebeee6405a1e3e2ef1608891aa27f63f281c401b 100644 (file)
--- a/xen/common/kexec.c
+++ b/xen/common/kexec.c
@@ -373,10 +373,12 @@ static int kexec_common_shutdown(void)
     return 0;
 }
 
-void kexec_crash(void)
+void kexec_crash(enum crash_reason reason)
 {
     int pos;
 
+    keyhandler_crash_action(reason);
+
     pos = (test_bit(KEXEC_FLAG_CRASH_POS, &kexec_flags) != 0);
     if ( !test_bit(KEXEC_IMAGE_CRASH_BASE + pos, &kexec_flags) )
         return;
@@ -409,7 +411,7 @@ static long kexec_reboot(void *_image)
 static void do_crashdump_trigger(unsigned char key)
 {
     printk("'%c' pressed -> triggering crashdump\n", key);
-    kexec_crash();
+    kexec_crash(CRASHREASON_DEBUGKEY);
     printk(" * no crash kernel loaded!\n");
 }
 
@@ -840,7 +842,7 @@ static int kexec_exec(XEN_GUEST_HANDLE_PARAM(void) uarg)
         ret = continue_hypercall_on_cpu(0, kexec_reboot, image);
         break;
     case KEXEC_TYPE_CRASH:
-        kexec_crash(); /* Does not return */
+        kexec_crash(CRASHREASON_KEXECCMD); /* Does not return */
         break;
     }
 

diff --git a/xen/common/keyhandler.c b/xen/common/keyhandler.c
index 38020a1360eb972e3763108177ee62d275fbb289..8b9f37837162cba0ce50746f882d460419273810 100644 (file)
--- a/xen/common/keyhandler.c
+++ b/xen/common/keyhandler.c
@@ -3,7 +3,9 @@
  */
 
 #include <asm/regs.h>
+#include <xen/delay.h>
 #include <xen/keyhandler.h>
+#include <xen/param.h>
 #include <xen/shutdown.h>
 #include <xen/event.h>
 #include <xen/console.h>
@@ -518,6 +520,59 @@ void __init initialize_keytable(void)
     }
 }
 
+#define CRASHACTION_SIZE  32
+static char crash_debug_panic[CRASHACTION_SIZE];
+string_runtime_param("crash-debug-panic", crash_debug_panic);
+static char crash_debug_hwdom[CRASHACTION_SIZE];
+string_runtime_param("crash-debug-hwdom", crash_debug_hwdom);
+static char crash_debug_watchdog[CRASHACTION_SIZE];
+string_runtime_param("crash-debug-watchdog", crash_debug_watchdog);
+#ifdef CONFIG_KEXEC
+static char crash_debug_kexeccmd[CRASHACTION_SIZE];
+string_runtime_param("crash-debug-kexeccmd", crash_debug_kexeccmd);
+#else
+#define crash_debug_kexeccmd NULL
+#endif
+static char crash_debug_debugkey[CRASHACTION_SIZE];
+string_runtime_param("crash-debug-debugkey", crash_debug_debugkey);
+
+void keyhandler_crash_action(enum crash_reason reason)
+{
+    static const char *const crash_action[] = {
+        [CRASHREASON_PANIC] = crash_debug_panic,
+        [CRASHREASON_HWDOM] = crash_debug_hwdom,
+        [CRASHREASON_WATCHDOG] = crash_debug_watchdog,
+        [CRASHREASON_KEXECCMD] = crash_debug_kexeccmd,
+        [CRASHREASON_DEBUGKEY] = crash_debug_debugkey,
+    };
+    static bool ignore;
+    const char *action;
+
+    /* Some handlers are not functional too early. */
+    if ( system_state < SYS_STATE_smp_boot )
+        return;
+
+    if ( (unsigned int)reason >= ARRAY_SIZE(crash_action) )
+        return;
+    action = crash_action[reason];
+    if ( !action )
+        return;
+
+    /* Avoid recursion. */
+    if ( ignore )
+        return;
+    ignore = true;
+
+    while ( *action )
+    {
+        if ( *action == '+' )
+            mdelay(10);
+        else
+            handle_keypress(*action, NULL);
+        action++;
+    }
+}
+
 /*
  * Local variables:
  * mode: C

diff --git a/xen/common/shutdown.c b/xen/common/shutdown.c
index 912593915b3701b7ff8b95fd2178e2c2dd0028d0..abde48aa4ca0c107f96623733aac2da2611b2df7 100644 (file)
--- a/xen/common/shutdown.c
+++ b/xen/common/shutdown.c
@@ -43,7 +43,7 @@ void hwdom_shutdown(u8 reason)
     case SHUTDOWN_crash:
         debugger_trap_immediate();
         printk("Hardware Dom%u crashed: ", hardware_domain->domain_id);
-        kexec_crash();
+        kexec_crash(CRASHREASON_HWDOM);
         maybe_reboot();
         break; /* not reached */
 
@@ -56,7 +56,7 @@ void hwdom_shutdown(u8 reason)
     case SHUTDOWN_watchdog:
         printk("Hardware Dom%u shutdown: watchdog rebooting machine\n",
                hardware_domain->domain_id);
-        kexec_crash();
+        kexec_crash(CRASHREASON_WATCHDOG);
         machine_restart(0);
         break; /* not reached */
 

diff --git a/xen/drivers/char/console.c b/xen/drivers/char/console.c
index e3c483fd13cbac5afd28e889cf0b96934afc16c4..23583751709c6ff7c842846b91cb1a320e5852d7 100644 (file)
--- a/xen/drivers/char/console.c
+++ b/xen/drivers/char/console.c
@@ -1271,7 +1271,7 @@ void panic(const char *fmt, ...)
 
     debugger_trap_immediate();
 
-    kexec_crash();
+    kexec_crash(CRASHREASON_PANIC);
 
     if ( opt_noreboot )
         machine_halt();

diff --git a/xen/include/xen/kexec.h b/xen/include/xen/kexec.h
index e85ba16405889565c2ff24ec79190489061f29d2..9f7a912e97aab0ffcddacdb0992a23b55e006cd1 100644 (file)
--- a/xen/include/xen/kexec.h
+++ b/xen/include/xen/kexec.h
@@ -1,6 +1,8 @@
 #ifndef __XEN_KEXEC_H__
 #define __XEN_KEXEC_H__
 
+#include <xen/keyhandler.h>
+
 #ifdef CONFIG_KEXEC
 
 #include <public/kexec.h>
@@ -48,7 +50,7 @@ void machine_kexec_unload(struct kexec_image *image);
 void machine_kexec_reserved(xen_kexec_reserve_t *reservation);
 void machine_reboot_kexec(struct kexec_image *image);
 void machine_kexec(struct kexec_image *image);
-void kexec_crash(void);
+void kexec_crash(enum crash_reason reason);
 void kexec_crash_save_cpu(void);
 struct crash_xen_info *kexec_crash_save_info(void);
 void machine_crash_shutdown(void);
@@ -82,7 +84,11 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 #define kexecing 0
 
 static inline void kexec_early_calculations(void) {}
-static inline void kexec_crash(void) {}
+static inline void kexec_crash(enum crash_reason reason)
+{
+    keyhandler_crash_action(reason);
+}
+
 static inline void kexec_crash_save_cpu(void) {}
 static inline void set_kexec_crash_area_size(u64 system_ram) {}
 

diff --git a/xen/include/xen/keyhandler.h b/xen/include/xen/keyhandler.h
index 5131e86cbca7797c8d50e8554e2ee65d1c829fdf..9c5830a037b34c0fa5198c9282d0389ef464a214 100644 (file)
--- a/xen/include/xen/keyhandler.h
+++ b/xen/include/xen/keyhandler.h
@@ -48,4 +48,14 @@ void register_irq_keyhandler(unsigned char key,
 /* Inject a keypress into the key-handling subsystem. */
 extern void handle_keypress(unsigned char key, struct cpu_user_regs *regs);
 
+enum crash_reason {
+    CRASHREASON_PANIC,
+    CRASHREASON_HWDOM,
+    CRASHREASON_WATCHDOG,
+    CRASHREASON_KEXECCMD,
+    CRASHREASON_DEBUGKEY,
+};
+
+void keyhandler_crash_action(enum crash_reason reason);
+
 #endif /* __XEN_KEYHANDLER_H__ */