x86/xen: Support kexec/kdump in HVM guests by doing a soft reset

[ Upstream commit 0b34a166f291d255755be46e43ed5497cdd194f2 ]

Currently there is a number of issues preventing PVHVM Xen guests from
doing successful kexec/kdump:

  - Bound event channels.
  - Registered vcpu_info.
  - PIRQ/emuirq mappings.
  - shared_info frame after XENMAPSPACE_shared_info operation.
  - Active grant mappings.

Basically, newly booted kernel stumbles upon already set up Xen
interfaces and there is no way to reestablish them. In Xen-4.7 a new
feature called 'soft reset' is coming. A guest performing kexec/kdump
operation is supposed to call SCHEDOP_shutdown hypercall with
SHUTDOWN_soft_reset reason before jumping to new kernel. Hypervisor
(with some help from toolstack) will do full domain cleanup (but
keeping its memory and vCPU contexts intact) returning the guest to
the state it had when it was first booted and thus allowing it to
start over.

Doing SHUTDOWN_soft_reset on Xen hypervisors which don't support it is
probably OK as by default all unknown shutdown reasons cause domain
destroy with a message in toolstack log: 'Unknown shutdown reason code
5. Destroying domain.'  which gives a clue to what the problem is and
eliminates false expectations.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

2 files changed, 31 insertions, 0 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d8d81d1aa1d5..7e365d231a93 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,6 +33,10 @@
 #include <linux/memblock.h>
 #include <linux/edd.h>
 
+#ifdef CONFIG_KEXEC_CORE
+#include <linux/kexec.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
@@ -1859,6 +1863,21 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 	.notifier_call	= xen_hvm_cpu_notify,
 };
 
+#ifdef CONFIG_KEXEC_CORE
+static void xen_hvm_shutdown(void)
+{
+	native_machine_shutdown();
+	if (kexec_in_progress)
+		xen_reboot(SHUTDOWN_soft_reset);
+}
+
+static void xen_hvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_machine_crash_shutdown(regs);
+	xen_reboot(SHUTDOWN_soft_reset);
+}
+#endif
+
 static void __init xen_hvm_guest_init(void)
 {
 	init_hvm_pv_info();
@@ -1875,6 +1894,10 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.shutdown = xen_hvm_shutdown;
+	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
+#endif
 }
 
 static bool xen_nopv = false;
diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h
index 9ce083960a25..f18490985fc8 100644
--- a/include/xen/interface/sched.h
+++ b/include/xen/interface/sched.h
@@ -107,5 +107,13 @@ struct sched_watchdog {
 #define SHUTDOWN_suspend    2  /* Clean up, save suspend info, kill.         */
 #define SHUTDOWN_crash      3  /* Tell controller we've crashed.             */
 #define SHUTDOWN_watchdog   4  /* Restart because watchdog time expired.     */
+/*
+ * Domain asked to perform 'soft reset' for it. The expected behavior is to
+ * reset internal Xen state for the domain returning it to the point where it
+ * was created but leaving the domain's memory contents and vCPU contexts
+ * intact. This will allow the domain to start over and set up all Xen specific
+ * interfaces again.
+ */
+#define SHUTDOWN_soft_reset 5
 
 #endif /* __XEN_PUBLIC_SCHED_H__ */