[PATCH RFC 3/4] xen/pvhvm: Unmap all PIRQs on startup and shutdown

[Vitaly Kuznetsov]

When kexec is being run PIRQs from Qemu-emulated devices are still
mapped to old event channels and new kernel has no information about
that. Trying to map them twice results in the following in Xen's dmesg:

 (XEN) irq.c:2278: dom7: pirq 24 or emuirq 8 already mapped
 (XEN) irq.c:2278: dom7: pirq 24 or emuirq 12 already mapped
 (XEN) irq.c:2278: dom7: pirq 24 or emuirq 1 already mapped
 ...

 and the following in new kernel's dmesg:

 [   92.286796] xen:events: Failed to obtain physical IRQ 4

The result is that the new kernel doesn't recieve IRQs for Qemu-emulated
devices. Address the issue by unmapping all mapped PIRQs on kernel shutdown
when kexec was requested and on every kernel startup. We need to do this
twice to deal with the following issues:
- startup-time unmapping is required to make kdump work;
- shutdown-time unmapping is required to support kexec-ing non-fixed kernels;
- shutdown-time unmapping is required to make Qemu-emulated NICs work after
  kexec (event channel is being closed on shutdown but no PHYSDEVOP_unmap_pirq
  is being performed).

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 arch/x86/xen/smp.c               |  1 +
 drivers/xen/events/events_base.c | 76 ++++++++++++++++++++++++++++++++++++++++
 include/xen/events.h             |  3 ++
 3 files changed, 80 insertions(+)

diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 35dcf39..e2b4deb 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -768,6 +768,7 @@ void xen_kexec_shutdown(void)
 #ifdef CONFIG_KEXEC
 	if (!kexec_in_progress)
 		return;
+	xen_unmap_all_pirqs();
 #endif
 }
 
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index c919d3d..7701c7f 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1643,6 +1643,80 @@ void xen_callback_vector(void) {}
 static bool fifo_events = true;
 module_param(fifo_events, bool, 0);
 
+void xen_unmap_all_pirqs(void)
+{
+	int pirq, rc, gsi, irq, evtchn;
+	struct physdev_unmap_pirq unmap_irq;
+	struct irq_info *info;
+	struct evtchn_close close;
+
+	mutex_lock(&irq_mapping_update_lock);
+
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		if (info->type != IRQT_PIRQ)
+			continue;
+
+		pirq = info->u.pirq.pirq;
+		gsi = info->u.pirq.gsi;
+		evtchn = info->evtchn;
+		irq = info->irq;
+
+		pr_debug("unmapping pirq gsi=%d pirq=%d irq=%d evtchn=%d\n",
+			gsi, pirq, irq, evtchn);
+
+		if (evtchn > 0) {
+			close.port = evtchn;
+			if (HYPERVISOR_event_channel_op(EVTCHNOP_close,
+							&close) != 0)
+				pr_warn("close evtchn %d failed\n", evtchn);
+		}
+
+		unmap_irq.pirq = pirq;
+		unmap_irq.domid = DOMID_SELF;
+
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
+		if (rc)
+			pr_warn("unmap pirq failed gsi=%d pirq=%d irq=%d rc=%d\n",
+				gsi, pirq, irq, rc);
+	}
+
+	mutex_unlock(&irq_mapping_update_lock);
+}
+EXPORT_SYMBOL_GPL(xen_unmap_all_pirqs);
+
+static void xen_startup_unmap_pirqs(void)
+{
+	struct evtchn_status status;
+	int port, rc = -ENOENT;
+	struct physdev_unmap_pirq unmap_irq;
+	struct evtchn_close close;
+
+	memset(&status, 0, sizeof(status));
+	for (port = 0; port < xen_evtchn_max_channels(); port++) {
+		status.dom = DOMID_SELF;
+		status.port = port;
+		rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status);
+		if (rc < 0)
+			continue;
+		if (status.status == EVTCHNSTAT_pirq) {
+			close.port = port;
+			if (HYPERVISOR_event_channel_op(EVTCHNOP_close,
+							&close) != 0)
+				pr_warn("xen: failed to close evtchn %d\n",
+					port);
+			unmap_irq.pirq = status.u.pirq;
+			unmap_irq.domid = DOMID_SELF;
+			pr_warn("xen: unmapping previously mapped pirq %d\n",
+				unmap_irq.pirq);
+			if (HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq,
+						  &unmap_irq) != 0)
+				pr_warn("xen: failed to unmap pirq %d\n",
+					unmap_irq.pirq);
+		}
+	}
+}
+
+
 void __init xen_init_IRQ(void)
 {
 	int ret = -EINVAL;
@@ -1671,6 +1745,8 @@ void __init xen_init_IRQ(void)
 		xen_callback_vector();
 
 	if (xen_hvm_domain()) {
+		xen_startup_unmap_pirqs();
+
 		native_init_IRQ();
 		/* pci_xen_hvm_init must be called after native_init_IRQ so that
 		 * __acpi_register_gsi can point at the right function */
diff --git a/include/xen/events.h b/include/xen/events.h
index 8bee7a7..3f9f428 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -122,6 +122,9 @@ int xen_irq_from_gsi(unsigned gsi);
 /* Determine whether to ignore this IRQ if it is passed to a guest. */
 int xen_test_irq_shared(int irq);
 
+/* Unmap all PIRQs and close event channels */
+void xen_unmap_all_pirqs(void);
+
 /* initialize Xen IRQ subsystem */
 void xen_init_IRQ(void);
 #endif	/* _XEN_EVENTS_H */
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/