Add support for suspend/resume/migration operations when running as a

Xen PVHVM guest.

Submitted by:	Roger Pau Monné
Sponsored by:	Citrix Systems R&D
Reviewed by:	gibbs
Approved by:	re (blanket Xen)
MFC after:	2 weeks

sys/amd64/amd64/mp_machdep.c:
sys/i386/i386/mp_machdep.c:
	- Make sure that are no MMU related IPIs pending on migration.
	- Reset pending IPI_BITMAP on resume.
	- Init vcpu_info on resume.

sys/amd64/include/intr_machdep.h:
sys/i386/include/intr_machdep.h:
sys/x86/acpica/acpi_wakeup.c:
sys/x86/x86/intr_machdep.c:
sys/x86/isa/atpic.c:
sys/x86/x86/io_apic.c:
sys/x86/x86/local_apic.c:
	- Add a "suspend_cancelled" parameter to pic_resume().  For the
	  Xen PIC, restoration of interrupt services differs between
	  the aborted suspend and normal resume cases, so we must provide
	  this information.

sys/dev/acpica/acpi_timer.c:
sys/dev/xen/timer/timer.c:
sys/timetc.h:
	- Don't swap out "suspend safe" timers across a suspend/resume
	  cycle.  This includes the Xen PV and ACPI timers.

sys/dev/xen/control/control.c:
	- Perform proper suspend/resume process for PVHVM:
		- Suspend all APs before going into suspension, this allows us
		  to reset the vcpu_info on resume for each AP.
		- Reset shared info page and callback on resume.

sys/dev/xen/timer/timer.c:
	- Implement suspend/resume support for the PV timer. Since FreeBSD
	  doesn't perform a per-cpu resume of the timer, we need to call
	  smp_rendezvous in order to correctly resume the timer on each CPU.

sys/dev/xen/xenpci/xenpci.c:
	- Don't reset the PCI interrupt on each suspend/resume.

sys/kern/subr_smp.c:
	- When suspending a PVHVM domain make sure there are no MMU IPIs
	  in-flight, or we will get a lockup on resume due to the fact that
	  pending event channels are not carried over on migration.
	- Implement a generic version of restart_cpus that can be used by
	  suspended and stopped cpus.

sys/x86/xen/hvm.c:
	- Implement resume support for the hypercall page and shared info.
	- Clear vcpu_info so it can be reset by APs when resuming from
	  suspension.

sys/dev/xen/xenpci/xenpci.c:
sys/x86/xen/hvm.c:
sys/x86/xen/xen_intr.c:
	- Support UP kernel configurations.

sys/x86/xen/xen_intr.c:
	- Properly rebind per-cpus VIRQs and IPIs on resume.

1 files changed, 65 insertions, 12 deletions

diff --git a/sys/dev/xen/control/control.c b/sys/dev/xen/control/control.c
index 649f281..a74042b 100644
--- a/sys/dev/xen/control/control.c
+++ b/sys/dev/xen/control/control.c
@@ -119,11 +119,9 @@ __FBSDID("$FreeBSD$");
 #include <sys/taskqueue.h>
 #include <sys/types.h>
 #include <sys/vnode.h>
-
-#ifndef XENHVM
 #include <sys/sched.h>
 #include <sys/smp.h>
-#endif
+#include <sys/eventhandler.h>
 
 #include <geom/geom.h>
 
@@ -140,6 +138,10 @@ __FBSDID("$FreeBSD$");
 #include <xen/gnttab.h>
 #include <xen/xen_intr.h>
 
+#ifdef XENHVM
+#include <xen/hvm.h>
+#endif
+
 #include <xen/interface/event_channel.h>
 #include <xen/interface/grant_table.h>
 
@@ -199,7 +201,7 @@ extern void xencons_resume(void);
 static void
 xctrl_suspend()
 {
-	int i, j, k, fpp;
+	int i, j, k, fpp, suspend_cancelled;
 	unsigned long max_pfn, start_info_mfn;
 
 	EVENTHANDLER_INVOKE(power_suspend);
@@ -264,7 +266,7 @@ xctrl_suspend()
 	 */
 	start_info_mfn = VTOMFN(xen_start_info);
 	pmap_suspend();
-	HYPERVISOR_suspend(start_info_mfn);
+	suspend_cancelled = HYPERVISOR_suspend(start_info_mfn);
 	pmap_resume();
 
 	pmap_kenter_ma((vm_offset_t) shared_info, xen_start_info->shared_info);
@@ -287,7 +289,7 @@ xctrl_suspend()
 	HYPERVISOR_shared_info->arch.max_pfn = max_pfn;
 
 	gnttab_resume();
-	intr_resume();
+	intr_resume(suspend_cancelled != 0);
 	local_irq_enable();
 	xencons_resume();
 
@@ -331,16 +333,31 @@ xen_pv_shutdown_final(void *arg, int howto)
 }
 
 #else
-extern void xenpci_resume(void);
 
 /* HVM mode suspension. */
 static void
 xctrl_suspend()
 {
+#ifdef SMP
+	cpuset_t cpu_suspend_map;
+#endif
 	int suspend_cancelled;
 
 	EVENTHANDLER_INVOKE(power_suspend);
 
+	if (smp_started) {
+		thread_lock(curthread);
+		sched_bind(curthread, 0);
+		thread_unlock(curthread);
+	}
+	KASSERT((PCPU_GET(cpuid) == 0), ("Not running on CPU#0"));
+
+	/*
+	 * Clear our XenStore node so the toolstack knows we are
+	 * responding to the suspend request.
+	 */
+	xs_write(XST_NIL, "control", "shutdown", "");
+
 	/*
 	 * Be sure to hold Giant across DEVICE_SUSPEND/RESUME since non-MPSAFE
 	 * drivers need this.
@@ -353,31 +370,67 @@ xctrl_suspend()
 	}
 	mtx_unlock(&Giant);
 
+#ifdef SMP
+	if (smp_started) {
+		/*
+		 * Suspend other CPUs. This prevents IPIs while we
+		 * are resuming, and will allow us to reset per-cpu
+		 * vcpu_info on resume.
+		 */
+		cpu_suspend_map = all_cpus;
+		CPU_CLR(PCPU_GET(cpuid), &cpu_suspend_map);
+		if (!CPU_EMPTY(&cpu_suspend_map))
+			suspend_cpus(cpu_suspend_map);
+	}
+#endif
+
 	/*
 	 * Prevent any races with evtchn_interrupt() handler.
 	 */
 	disable_intr();
 	intr_suspend();
+	xen_hvm_suspend();
 
 	suspend_cancelled = HYPERVISOR_suspend(0);
 
-	intr_resume();
+	xen_hvm_resume(suspend_cancelled != 0);
+	intr_resume(suspend_cancelled != 0);
+	enable_intr();
 
 	/*
-	 * Re-enable interrupts and put the scheduler back to normal.
+	 * Reset grant table info.
 	 */
-	enable_intr();
+	gnttab_resume();
+
+#ifdef SMP
+	if (smp_started && !CPU_EMPTY(&cpu_suspend_map)) {
+		/*
+		 * Now that event channels have been initialized,
+		 * resume CPUs.
+		 */
+		resume_cpus(cpu_suspend_map);
+	}
+#endif
 
 	/*
 	 * FreeBSD really needs to add DEVICE_SUSPEND_CANCEL or
 	 * similar.
 	 */
 	mtx_lock(&Giant);
-	if (!suspend_cancelled)
-		DEVICE_RESUME(root_bus);
+	DEVICE_RESUME(root_bus);
 	mtx_unlock(&Giant);
 
+	if (smp_started) {
+		thread_lock(curthread);
+		sched_unbind(curthread);
+		thread_unlock(curthread);
+	}
+
 	EVENTHANDLER_INVOKE(power_resume);
+
+	if (bootverbose)
+		printf("System resumed after suspension\n");
+
 }
 #endif