Merge branch '2.6.37-rc4-pvhvm-fixes' of git://xenbits.xen.org/people/sstabellini/linux-pvhvm

* '2.6.37-rc4-pvhvm-fixes' of git://xenbits.xen.org/people/sstabellini/linux-pvhvm:
  xen: unplug the emulated devices at resume time
  xen: fix save/restore for PV on HVM guests with pirq remapping
  xen: resume the pv console for hvm guests too
  xen: fix MSI setup and teardown for PV on HVM guests
  xen: use PHYSDEVOP_get_free_pirq to implement find_unbound_pirq

8 files changed, 114 insertions, 41 deletions

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index d7b5109f7a9c..25cd4a07d09f 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -70,6 +70,9 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
 struct xen_pci_frontend_ops *xen_pci_frontend;
 EXPORT_SYMBOL_GPL(xen_pci_frontend);
 
+#define XEN_PIRQ_MSI_DATA  (MSI_DATA_TRIGGER_EDGE | \
+		MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0))
+
 static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 		struct msi_msg *msg)
 {
@@ -83,12 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 		MSI_ADDR_REDIRECTION_CPU |
 		MSI_ADDR_DEST_ID(pirq);
 
-	msg->data =
-		MSI_DATA_TRIGGER_EDGE |
-		MSI_DATA_LEVEL_ASSERT |
-		/* delivery mode reserved */
-		(3 << 8) |
-		MSI_DATA_VECTOR(0);
+	msg->data = XEN_PIRQ_MSI_DATA;
 }
 
 static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
@@ -98,8 +96,23 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	struct msi_msg msg;
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
+		__read_msi_msg(msidesc, &msg);
+		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
+			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
+		if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) {
+			xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
+					"msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ);
+			if (irq < 0)
+				goto error;
+			ret = set_irq_msi(irq, msidesc);
+			if (ret < 0)
+				goto error_while;
+			printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d"
+					" pirq=%d\n", irq, pirq);
+			return 0;
+		}
 		xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ?
-				"msi-x" : "msi", &irq, &pirq);
+				"msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ));
 		if (irq < 0 || pirq < 0)
 			goto error;
 		printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq);
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 0f456386cce5..25c52f94a27c 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -68,7 +68,7 @@ static int __init check_platform_magic(void)
 	return 0;
 }
 
-void __init xen_unplug_emulated_devices(void)
+void xen_unplug_emulated_devices(void)
 {
 	int r;
 
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 1d789d56877c..9bbd63a129b5 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -31,6 +31,7 @@ void xen_hvm_post_suspend(int suspend_cancelled)
 	int cpu;
 	xen_hvm_init_shared_info();
 	xen_callback_vector();
+	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
 		for_each_online_cpu(cpu) {
 			xen_setup_runstate_info(cpu);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 64044747348e..9d41bf985757 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -43,7 +43,7 @@ void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
 void xen_hvm_init_shared_info(void);
-void __init xen_unplug_emulated_devices(void);
+void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);
 
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 0009e489272c..31af0ac31a98 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -105,7 +105,6 @@ struct irq_info
 
 static struct irq_info *irq_info;
 static int *pirq_to_irq;
-static int nr_pirqs;
 
 static int *evtchn_to_irq;
 struct cpu_evtchn_s {
@@ -385,12 +384,17 @@ static int get_nr_hw_irqs(void)
 	return ret;
 }
 
-/* callers of this function should make sure that PHYSDEVOP_get_nr_pirqs
- * succeeded otherwise nr_pirqs won't hold the right value */
-static int find_unbound_pirq(void)
+static int find_unbound_pirq(int type)
 {
-	int i;
-	for (i = nr_pirqs-1; i >= 0; i--) {
+	int rc, i;
+	struct physdev_get_free_pirq op_get_free_pirq;
+	op_get_free_pirq.type = type;
+
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
+	if (!rc)
+		return op_get_free_pirq.pirq;
+
+	for (i = 0; i < nr_irqs; i++) {
 		if (pirq_to_irq[i] < 0)
 			return i;
 	}
@@ -611,10 +615,10 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name)
 
 	spin_lock(&irq_mapping_update_lock);
 
-	if ((pirq > nr_pirqs) || (gsi > nr_irqs)) {
+	if ((pirq > nr_irqs) || (gsi > nr_irqs)) {
 		printk(KERN_WARNING "xen_map_pirq_gsi: %s %s is incorrect!\n",
-			pirq > nr_pirqs ? "nr_pirqs" :"",
-			gsi > nr_irqs ? "nr_irqs" : "");
+			pirq > nr_irqs ? "pirq" :"",
+			gsi > nr_irqs ? "gsi" : "");
 		goto out;
 	}
 
@@ -664,17 +668,21 @@ out:
 #include <linux/msi.h>
 #include "../pci/msi.h"
 
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq)
+void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc)
 {
 	spin_lock(&irq_mapping_update_lock);
 
-	*irq = find_unbound_irq();
-	if (*irq == -1)
-		goto out;
+	if (alloc & XEN_ALLOC_IRQ) {
+		*irq = find_unbound_irq();
+		if (*irq == -1)
+			goto out;
+	}
 
-	*pirq = find_unbound_pirq();
-	if (*pirq == -1)
-		goto out;
+	if (alloc & XEN_ALLOC_PIRQ) {
+		*pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
+		if (*pirq == -1)
+			goto out;
+	}
 
 	set_irq_chip_and_handler_name(*irq, &xen_pirq_chip,
 				      handle_level_irq, name);
@@ -762,6 +770,7 @@ int xen_destroy_irq(int irq)
 			printk(KERN_WARNING "unmap irq failed %d\n", rc);
 			goto out;
 		}
+		pirq_to_irq[info->u.pirq.pirq] = -1;
 	}
 	irq_info[irq] = mk_unbound_info();
 
@@ -782,6 +791,11 @@ int xen_gsi_from_irq(unsigned irq)
 	return gsi_from_irq(irq);
 }
 
+int xen_irq_from_pirq(unsigned pirq)
+{
+	return pirq_to_irq[pirq];
+}
+
 int bind_evtchn_to_irq(unsigned int evtchn)
 {
 	int irq;
@@ -1279,6 +1293,42 @@ static int retrigger_dynirq(unsigned int irq)
 	return ret;
 }
 
+static void restore_cpu_pirqs(void)
+{
+	int pirq, rc, irq, gsi;
+	struct physdev_map_pirq map_irq;
+
+	for (pirq = 0; pirq < nr_irqs; pirq++) {
+		irq = pirq_to_irq[pirq];
+		if (irq == -1)
+			continue;
+
+		/* save/restore of PT devices doesn't work, so at this point the
+		 * only devices present are GSI based emulated devices */
+		gsi = gsi_from_irq(irq);
+		if (!gsi)
+			continue;
+
+		map_irq.domid = DOMID_SELF;
+		map_irq.type = MAP_PIRQ_TYPE_GSI;
+		map_irq.index = gsi;
+		map_irq.pirq = pirq;
+
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
+		if (rc) {
+			printk(KERN_WARNING "xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
+					gsi, irq, pirq, rc);
+			irq_info[irq] = mk_unbound_info();
+			pirq_to_irq[pirq] = -1;
+			continue;
+		}
+
+		printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
+
+		startup_pirq(irq);
+	}
+}
+
 static void restore_cpu_virqs(unsigned int cpu)
 {
 	struct evtchn_bind_virq bind_virq;
@@ -1422,6 +1472,8 @@ void xen_irq_resume(void)
 
 		unmask_evtchn(evtchn);
 	}
+
+	restore_cpu_pirqs();
 }
 
 static struct irq_chip xen_dynamic_chip __read_mostly = {
@@ -1506,26 +1558,17 @@ void xen_callback_vector(void) {}
 
 void __init xen_init_IRQ(void)
 {
-	int i, rc;
-	struct physdev_nr_pirqs op_nr_pirqs;
+	int i;
 
 	cpu_evtchn_mask_p = kcalloc(nr_cpu_ids, sizeof(struct cpu_evtchn_s),
 				    GFP_KERNEL);
 	irq_info = kcalloc(nr_irqs, sizeof(*irq_info), GFP_KERNEL);
 
-	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_nr_pirqs, &op_nr_pirqs);
-	if (rc < 0) {
-		nr_pirqs = nr_irqs;
-		if (rc != -ENOSYS)
-			printk(KERN_WARNING "PHYSDEVOP_get_nr_pirqs returned rc=%d\n", rc);
-	} else {
-		if (xen_pv_domain() && !xen_initial_domain())
-			nr_pirqs = max((int)op_nr_pirqs.nr_pirqs, nr_irqs);
-		else
-			nr_pirqs = op_nr_pirqs.nr_pirqs;
-	}
-	pirq_to_irq = kcalloc(nr_pirqs, sizeof(*pirq_to_irq), GFP_KERNEL);
-	for (i = 0; i < nr_pirqs; i++)
+	/* We are using nr_irqs as the maximum number of pirq available but
+	 * that number is actually chosen by Xen and we don't know exactly
+	 * what it is. Be careful choosing high pirq numbers. */
+	pirq_to_irq = kcalloc(nr_irqs, sizeof(*pirq_to_irq), GFP_KERNEL);
+	for (i = 0; i < nr_irqs; i++)
 		pirq_to_irq[i] = -1;
 
 	evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index ef9c7db52077..db8c4c4ac880 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -49,6 +49,7 @@ static int xen_hvm_suspend(void *data)
 
 	if (!*cancelled) {
 		xen_irq_resume();
+		xen_console_resume();
 		xen_timer_resume();
 	}
 
diff --git a/include/xen/events.h b/include/xen/events.h
index 646dd17d3aa4..00f53ddcc062 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -76,7 +76,9 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 
 #ifdef CONFIG_PCI_MSI
 /* Allocate an irq and a pirq to be used with MSIs. */
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq);
+#define XEN_ALLOC_PIRQ (1 << 0)
+#define XEN_ALLOC_IRQ  (1 << 1)
+void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_mask);
 int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
 #endif
 
@@ -89,4 +91,7 @@ int xen_vector_from_irq(unsigned pirq);
 /* Return gsi allocated to pirq */
 int xen_gsi_from_irq(unsigned pirq);
 
+/* Return irq from pirq */
+int xen_irq_from_pirq(unsigned pirq);
+
 #endif	/* _XEN_EVENTS_H */
diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h
index 2b2c66c3df00..534cac89a77d 100644
--- a/include/xen/interface/physdev.h
+++ b/include/xen/interface/physdev.h
@@ -188,6 +188,16 @@ struct physdev_nr_pirqs {
     uint32_t nr_pirqs;
 };
 
+/* type is MAP_PIRQ_TYPE_GSI or MAP_PIRQ_TYPE_MSI
+ * the hypercall returns a free pirq */
+#define PHYSDEVOP_get_free_pirq    23
+struct physdev_get_free_pirq {
+    /* IN */ 
+    int type;
+    /* OUT */
+    uint32_t pirq;
+};
+
 /*
  * Notify that some PIRQ-bound event channels have been unmasked.
  * ** This command is obsolete since interface version 0x00030202 and is **