xen: add support for MSI message groups

Add support for MSI message groups for Xen Dom0 using the
MAP_PIRQ_TYPE_MULTI_MSI pirq map type.

In order to keep track of which pirq is the first one in the group all
pirqs in the MSI group except for the first one have the newly
introduced PIRQ_MSI_GROUP flag set. This prevents calling
PHYSDEVOP_unmap_pirq on them, since the unmap must be done with the
first pirq in the group.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>

arch/x86/pci/xen.c

@@ -178,6 +178,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	i = 0;
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
+					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
 					       "pcifront-msi-x" :
 					       "pcifront-msi",
@@ -245,6 +246,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 				"xen: msi already bound to pirq=%d\n", pirq);
 		}
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
+					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
 					       "msi-x" : "msi",
 					       DOMID_SELF);
@@ -269,9 +271,6 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	int ret = 0;
 	struct msi_desc *msidesc;
 
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
 		struct physdev_map_pirq map_irq;
 		domid_t domid;
@@ -291,7 +290,10 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 			      (pci_domain_nr(dev->bus) << 16);
 		map_irq.devfn = dev->devfn;
 
-		if (type == PCI_CAP_ID_MSIX) {
+		if (type == PCI_CAP_ID_MSI && nvec > 1) {
+			map_irq.type = MAP_PIRQ_TYPE_MULTI_MSI;
+			map_irq.entry_nr = nvec;
+		} else if (type == PCI_CAP_ID_MSIX) {
 			int pos;
 			u32 table_offset, bir;
 
@@ -308,6 +310,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		if (pci_seg_supported)
 			ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq,
 						    &map_irq);
+		if (type == PCI_CAP_ID_MSI && nvec > 1 && ret) {
+			/*
+			 * If MAP_PIRQ_TYPE_MULTI_MSI is not available
+			 * there's nothing else we can do in this case.
+			 * Just set ret > 0 so driver can retry with
+			 * single MSI.
+			 */
+			ret = 1;
+			goto out;
+		}
 		if (ret == -EINVAL && !pci_domain_nr(dev->bus)) {
 			map_irq.type = MAP_PIRQ_TYPE_MSI;
 			map_irq.index = -1;
@@ -324,10 +336,9 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 			goto out;
 		}
 
-		ret = xen_bind_pirq_msi_to_irq(dev, msidesc,
-					       map_irq.pirq,
-					       (type == PCI_CAP_ID_MSIX) ?
-					       "msi-x" : "msi",
+		ret = xen_bind_pirq_msi_to_irq(dev, msidesc, map_irq.pirq,
+		                               (type == PCI_CAP_ID_MSI) ? nvec : 1,
+		                               (type == PCI_CAP_ID_MSIX) ? "msi-x" : "msi",
 		                               domid);
 		if (ret < 0)
 			goto out;

drivers/xen/events/events_base.c

@@ -391,10 +391,10 @@ static void xen_irq_init(unsigned irq)
 	list_add_tail(&info->list, &xen_irq_list_head);
 }
 
-static int __must_check xen_allocate_irq_dynamic(void)
+static int __must_check xen_allocate_irqs_dynamic(int nvec)
 {
 	int first = 0;
-	int irq;
+	int i, irq;
 
 #ifdef CONFIG_X86_IO_APIC
 	/*
@@ -408,14 +408,22 @@ static int __must_check xen_allocate_irq_dynamic(void)
 		first = get_nr_irqs_gsi();
 #endif
 
-	irq = irq_alloc_desc_from(first, -1);
+	irq = irq_alloc_descs_from(first, nvec, -1);
 
-	if (irq >= 0)
-		xen_irq_init(irq);
+	if (irq >= 0) {
+		for (i = 0; i < nvec; i++)
+			xen_irq_init(irq + i);
+	}
 
 	return irq;
 }
 
+static inline int __must_check xen_allocate_irq_dynamic(void)
+{
+
+	return xen_allocate_irqs_dynamic(1);
+}
+
 static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 {
 	int irq;
@@ -738,22 +746,25 @@ int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
 }
 
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-			     int pirq, const char *name, domid_t domid)
+			     int pirq, int nvec, const char *name, domid_t domid)
 {
-	int irq, ret;
+	int i, irq, ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = xen_allocate_irq_dynamic();
+	irq = xen_allocate_irqs_dynamic(nvec);
 	if (irq < 0)
 		goto out;
 
-	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
-			name);
+	for (i = 0; i < nvec; i++) {
+		irq_set_chip_and_handler_name(irq + i, &xen_pirq_chip, handle_edge_irq, name);
 
-	ret = xen_irq_info_pirq_setup(irq, 0, pirq, 0, domid, 0);
+		ret = xen_irq_info_pirq_setup(irq + i, 0, pirq + i, 0, domid,
+					      i == 0 ? 0 : PIRQ_MSI_GROUP);
 		if (ret < 0)
 			goto error_irq;
+	}
+
 	ret = irq_set_msi_desc(irq, msidesc);
 	if (ret < 0)
 		goto error_irq;
@@ -761,7 +772,8 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 	mutex_unlock(&irq_mapping_update_lock);
 	return irq;
 error_irq:
-	__unbind_from_irq(irq);
+	for (; i >= 0; i--)
+		__unbind_from_irq(irq + i);
 	mutex_unlock(&irq_mapping_update_lock);
 	return ret;
 }
@@ -780,7 +792,12 @@ int xen_destroy_irq(int irq)
 	if (!desc)
 		goto out;
 
-	if (xen_initial_domain()) {
+	/*
+	 * If trying to remove a vector in a MSI group different
+	 * than the first one skip the PIRQ unmap unless this vector
+	 * is the first one in the group.
+	 */
+	if (xen_initial_domain() && !(info->u.pirq.flags & PIRQ_MSI_GROUP)) {
 		unmap_irq.pirq = info->u.pirq.pirq;
 		unmap_irq.domid = info->u.pirq.domid;
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);

drivers/xen/events/events_internal.h

@@ -53,6 +53,7 @@ struct irq_info {
 
 #define PIRQ_NEEDS_EOI	(1 << 0)
 #define PIRQ_SHAREABLE	(1 << 1)
+#define PIRQ_MSI_GROUP	(1 << 2)
 
 struct evtchn_ops {
 	unsigned (*max_channels)(void);

include/xen/events.h

@@ -2,6 +2,9 @@
 #define _XEN_EVENTS_H
 
 #include <linux/interrupt.h>
+#ifdef CONFIG_PCI_MSI
+#include <linux/msi.h>
+#endif
 
 #include <xen/interface/event_channel.h>
 #include <asm/xen/hypercall.h>
@@ -101,7 +104,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
 /* Bind an PSI pirq to an irq. */
 int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-			     int pirq, const char *name, domid_t domid);
+			     int pirq, int nvec, const char *name, domid_t domid);
 #endif
 
 /* De-allocates the above mentioned physical interrupt. */

include/xen/interface/physdev.h

@@ -131,6 +131,7 @@ struct physdev_irq {
 #define MAP_PIRQ_TYPE_GSI		0x1
 #define MAP_PIRQ_TYPE_UNKNOWN		0x2
 #define MAP_PIRQ_TYPE_MSI_SEG		0x3
+#define MAP_PIRQ_TYPE_MULTI_MSI		0x4
 
 #define PHYSDEVOP_map_pirq		13
 struct physdev_map_pirq {
@@ -141,11 +142,16 @@ struct physdev_map_pirq {
     int index;
     /* IN or OUT */
     int pirq;
-    /* IN - high 16 bits hold segment for MAP_PIRQ_TYPE_MSI_SEG */
+    /* IN - high 16 bits hold segment for ..._MSI_SEG and ..._MULTI_MSI */
     int bus;
     /* IN */
     int devfn;
-    /* IN */
+    /* IN
+     * - For MSI-X contains entry number.
+     * - For MSI with ..._MULTI_MSI contains number of vectors.
+     * OUT (..._MULTI_MSI only)
+     * - Number of vectors allocated.
+     */
     int entry_nr;
     /* IN */
     uint64_t table_base;