Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull vhost updates from Michael Tsirkin:
 "virtio, vhost: optimizations, fixes

  Looks like a quiet cycle for vhost/virtio, just a couple of minor
  tweaks. Most notable is automatic interrupt affinity for blk and scsi.
  Hopefully other devices are not far behind"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio-console: avoid DMA from stack
  vhost: introduce O(1) vq metadata cache
  virtio_scsi: use virtio IRQ affinity
  virtio_blk: use virtio IRQ affinity
  blk-mq: provide a default queue mapping for virtio device
  virtio: provide a method to get the IRQ affinity mask for a virtqueue
  virtio: allow drivers to request IRQ affinity when creating VQs
  virtio_pci: simplify MSI-X setup
  virtio_pci: don't duplicate the msix_enable flag in struct pci_dev
  virtio_pci: use shared interrupts for virtqueues
  virtio_pci: remove struct virtio_pci_vq_info
  vhost: try avoiding avail index access when getting descriptor
  virtio_mmio: expose header to userspace

block/Kconfig

@@ -189,4 +189,9 @@ config BLK_MQ_PCI
 	depends on BLOCK && PCI
 	default y
 
+config BLK_MQ_VIRTIO
+	bool
+	depends on BLOCK && VIRTIO
+	default y
+
 source block/Kconfig.iosched

block/Makefile

@@ -25,6 +25,7 @@ obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
+obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o

block/blk-mq-virtio.c

+/*
+ * Copyright (c) 2016 Christoph Hellwig.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/device.h>
+#include <linux/blk-mq.h>
+#include <linux/blk-mq-virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/module.h>
+#include "blk-mq.h"
+
+/**
+ * blk_mq_virtio_map_queues - provide a default queue mapping for virtio device
+ * @set:	tagset to provide the mapping for
+ * @vdev:	virtio device associated with @set.
+ * @first_vec:	first interrupt vectors to use for queues (usually 0)
+ *
+ * This function assumes the virtio device @vdev has at least as many available
+ * interrupt vetors as @set has queues.  It will then queuery the vector
+ * corresponding to each queue for it's affinity mask and built queue mapping
+ * that maps a queue to the CPUs that have irq affinity for the corresponding
+ * vector.
+ */
+int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
+		struct virtio_device *vdev, int first_vec)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	if (!vdev->config->get_vq_affinity)
+		goto fallback;
+
+	for (queue = 0; queue < set->nr_hw_queues; queue++) {
+		mask = vdev->config->get_vq_affinity(vdev, first_vec + queue);
+		if (!mask)
+			goto fallback;
+
+		for_each_cpu(cpu, mask)
+			set->mq_map[cpu] = queue;
+	}
+
+	return 0;
+fallback:
+	return blk_mq_map_queues(set);
+}
+EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues);

drivers/block/virtio_blk.c

@@ -5,6 +5,7 @@
 #include <linux/hdreg.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/interrupt.h>
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
@@ -12,6 +13,7 @@
 #include <scsi/scsi_cmnd.h>
 #include <linux/idr.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-mq-virtio.h>
 #include <linux/numa.h>
 
 #define PART_BITS 4
@@ -426,6 +428,7 @@ static int init_vq(struct virtio_blk *vblk)
 	struct virtqueue **vqs;
 	unsigned short num_vqs;
 	struct virtio_device *vdev = vblk->vdev;
+	struct irq_affinity desc = { 0, };
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ,
 				   struct virtio_blk_config, num_queues,
@@ -452,7 +455,8 @@ static int init_vq(struct virtio_blk *vblk)
 	}
 
 	/* Discover virtqueues and write information to configuration.  */
-	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
+	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
+			&desc);
 	if (err)
 		goto out;
 
@@ -586,10 +590,18 @@ static int virtblk_init_request(void *data, struct request *rq,
 	return 0;
 }
 
+static int virtblk_map_queues(struct blk_mq_tag_set *set)
+{
+	struct virtio_blk *vblk = set->driver_data;
+
+	return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
+}
+
 static struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.complete	= virtblk_request_done,
 	.init_request	= virtblk_init_request,
+	.map_queues	= virtblk_map_queues,
 };
 
 static unsigned int virtblk_queue_depth;

drivers/char/virtio_console.c

@@ -1136,6 +1136,8 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 {
 	struct port *port;
 	struct scatterlist sg[1];
+	void *data;
+	int ret;
 
 	if (unlikely(early_put_chars))
 		return early_put_chars(vtermno, buf, count);
@@ -1144,8 +1146,14 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 	if (!port)
 		return -EPIPE;
 
-	sg_init_one(sg, buf, count);
-	return __send_to_port(port, sg, 1, count, (void *)buf, false);
+	data = kmemdup(buf, count, GFP_ATOMIC);
+	if (!data)
+		return -ENOMEM;
+
+	sg_init_one(sg, data, count);
+	ret = __send_to_port(port, sg, 1, count, data, false);
+	kfree(data);
+	return ret;
 }
 
 /*
@@ -1939,7 +1947,7 @@ static int init_vqs(struct ports_device *portdev)
 	/* Find the queues. */
 	err = portdev->vdev->config->find_vqs(portdev->vdev, nr_queues, vqs,
 					      io_callbacks,
-					      (const char **)io_names);
+					      (const char **)io_names, NULL);
 	if (err)
 		goto free;
 

drivers/crypto/virtio/virtio_crypto_core.c

@@ -120,7 +120,7 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi)
 	}
 
 	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names);
+					 names, NULL);
 	if (ret)
 		goto err_find;
 

drivers/gpu/drm/virtio/virtgpu_kms.c

@@ -176,7 +176,7 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags)
 #endif
 
 	ret = vgdev->vdev->config->find_vqs(vgdev->vdev, 2, vqs,
-					    callbacks, names);
+					    callbacks, names, NULL);
 	if (ret) {
 		DRM_ERROR("failed to find virt queues\n");
 		goto err_vqs;

drivers/misc/mic/vop/vop_main.c

@@ -374,7 +374,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev,
 static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
 			struct virtqueue *vqs[],
 			vq_callback_t *callbacks[],
-			const char * const names[])
+			const char * const names[], struct irq_affinity *desc)
 {
 	struct _vop_vdev *vdev = to_vopvdev(dev);
 	struct vop_device *vpdev = vdev->vpdev;

drivers/net/caif/caif_virtio.c

@@ -679,7 +679,8 @@ static int cfv_probe(struct virtio_device *vdev)
 		goto err;
 
 	/* Get the TX virtio ring. This is a "guest side vring". */
-	err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names);
+	err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names,
+			NULL);
 	if (err)
 		goto err;
 

drivers/net/virtio_net.c

@@ -2080,7 +2080,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	}
 
 	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names);
+					 names, NULL);
 	if (ret)
 		goto err_find;
 

drivers/remoteproc/remoteproc_virtio.c

@@ -137,7 +137,8 @@ static void rproc_virtio_del_vqs(struct virtio_device *vdev)
 static int rproc_virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				 struct virtqueue *vqs[],
 				 vq_callback_t *callbacks[],
-				 const char * const names[])
+				 const char * const names[],
+				 struct irq_affinity *desc)
 {
 	int i, ret;
 

drivers/rpmsg/virtio_rpmsg_bus.c

@@ -869,7 +869,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
 	init_waitqueue_head(&vrp->sendq);
 
 	/* We expect two virtqueues, rx and tx (and in this order) */
-	err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names);
+	err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names, NULL);
 	if (err)
 		goto free_vrp;
 

drivers/s390/virtio/kvm_virtio.c

@@ -255,7 +255,8 @@ static void kvm_del_vqs(struct virtio_device *vdev)
 static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			struct virtqueue *vqs[],
 			vq_callback_t *callbacks[],
-			const char * const names[])
+			const char * const names[],
+			struct irq_affinity *desc)
 {
 	struct kvm_device *kdev = to_kvmdev(vdev);
 	int i;

drivers/s390/virtio/virtio_ccw.c

@@ -628,7 +628,8 @@ static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev,
 static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			       struct virtqueue *vqs[],
 			       vq_callback_t *callbacks[],
-			       const char * const names[])
+			       const char * const names[],
+			       struct irq_affinity *desc)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
 	unsigned long *indicatorp = NULL;

drivers/scsi/virtio_scsi.c

@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/mempool.h>
+#include <linux/interrupt.h>
 #include <linux/virtio.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
@@ -29,6 +30,7 @@
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_tcq.h>
 #include <linux/seqlock.h>
+#include <linux/blk-mq-virtio.h>
 
 #define VIRTIO_SCSI_MEMPOOL_SZ 64
 #define VIRTIO_SCSI_EVENT_LEN 8
@@ -108,7 +110,6 @@ struct virtio_scsi {
 	bool affinity_hint_set;
 
 	struct hlist_node node;
-	struct hlist_node node_dead;
 
 	/* Protected by event_vq lock */
 	bool stop_events;
@@ -118,7 +119,6 @@ struct virtio_scsi {
 	struct virtio_scsi_vq req_vqs[];
 };
 
-static enum cpuhp_state virtioscsi_online;
 static struct kmem_cache *virtscsi_cmd_cache;
 static mempool_t *virtscsi_cmd_pool;
 
@@ -766,6 +766,13 @@ static void virtscsi_target_destroy(struct scsi_target *starget)
 	kfree(tgt);
 }
 
+static int virtscsi_map_queues(struct Scsi_Host *shost)
+{
+	struct virtio_scsi *vscsi = shost_priv(shost);
+
+	return blk_mq_virtio_map_queues(&shost->tag_set, vscsi->vdev, 2);
+}
+
 static struct scsi_host_template virtscsi_host_template_single = {
 	.module = THIS_MODULE,
 	.name = "Virtio SCSI HBA",
@@ -801,6 +808,7 @@ static struct scsi_host_template virtscsi_host_template_multi = {
 	.use_clustering = ENABLE_CLUSTERING,
 	.target_alloc = virtscsi_target_alloc,
 	.target_destroy = virtscsi_target_destroy,
+	.map_queues = virtscsi_map_queues,
 	.track_queue_depth = 1,
 };
 
@@ -817,80 +825,6 @@ static struct scsi_host_template virtscsi_host_template_multi = {
 		virtio_cwrite(vdev, struct virtio_scsi_config, fld, &__val); \
 	} while(0)
 
-static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
-{
-	int i;
-	int cpu;
-
-	/* In multiqueue mode, when the number of cpu is equal
-	 * to the number of request queues, we let the qeueues
-	 * to be private to one cpu by setting the affinity hint
-	 * to eliminate the contention.
-	 */
-	if ((vscsi->num_queues == 1 ||
-	     vscsi->num_queues != num_online_cpus()) && affinity) {
-		if (vscsi->affinity_hint_set)
-			affinity = false;
-		else
-			return;
-	}
-
-	if (affinity) {
-		i = 0;
-		for_each_online_cpu(cpu) {
-			virtqueue_set_affinity(vscsi->req_vqs[i].vq, cpu);
-			i++;
-		}
-
-		vscsi->affinity_hint_set = true;
-	} else {
-		for (i = 0; i < vscsi->num_queues; i++) {
-			if (!vscsi->req_vqs[i].vq)
-				continue;
-
-			virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1);
-		}
-
-		vscsi->affinity_hint_set = false;
-	}
-}
-
-static void virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
-{
-	get_online_cpus();
-	__virtscsi_set_affinity(vscsi, affinity);
-	put_online_cpus();
-}
-
-static int virtscsi_cpu_online(unsigned int cpu, struct hlist_node *node)
-{
-	struct virtio_scsi *vscsi = hlist_entry_safe(node, struct virtio_scsi,
-						     node);
-	__virtscsi_set_affinity(vscsi, true);
-	return 0;
-}
-
-static int virtscsi_cpu_notif_add(struct virtio_scsi *vi)
-{
-	int ret;
-
-	ret = cpuhp_state_add_instance(virtioscsi_online, &vi->node);
-	if (ret)
-		return ret;
-
-	ret = cpuhp_state_add_instance(CPUHP_VIRT_SCSI_DEAD, &vi->node_dead);
-	if (ret)
-		cpuhp_state_remove_instance(virtioscsi_online, &vi->node);
-	return ret;
-}
-
-static void virtscsi_cpu_notif_remove(struct virtio_scsi *vi)
-{
-	cpuhp_state_remove_instance_nocalls(virtioscsi_online, &vi->node);
-	cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_SCSI_DEAD,
-					    &vi->node_dead);
-}
-
 static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
 			     struct virtqueue *vq)
 {
@@ -900,14 +834,8 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
 
 static void virtscsi_remove_vqs(struct virtio_device *vdev)
 {
-	struct Scsi_Host *sh = virtio_scsi_host(vdev);
-	struct virtio_scsi *vscsi = shost_priv(sh);
-
-	virtscsi_set_affinity(vscsi, false);
-
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
-
 	vdev->config->del_vqs(vdev);
 }
 
@@ -920,6 +848,7 @@ static int virtscsi_init(struct virtio_device *vdev,
 	vq_callback_t **callbacks;
 	const char **names;
 	struct virtqueue **vqs;
+	struct irq_affinity desc = { .pre_vectors = 2 };
 
 	num_vqs = vscsi->num_queues + VIRTIO_SCSI_VQ_BASE;
 	vqs = kmalloc(num_vqs * sizeof(struct virtqueue *), GFP_KERNEL);
@@ -941,7 +870,8 @@ static int virtscsi_init(struct virtio_device *vdev,
 	}
 
 	/* Discover virtqueues and write information to configuration.  */
-	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
+	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
+			&desc);
 	if (err)
 		goto out;
 
@@ -1007,10 +937,6 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	if (err)
 		goto virtscsi_init_failed;
 
-	err = virtscsi_cpu_notif_add(vscsi);
-	if (err)
-		goto scsi_add_host_failed;
-
 	cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1;
 	shost->cmd_per_lun = min_t(u32, cmd_per_lun, shost->can_queue);
 	shost->max_sectors = virtscsi_config_get(vdev, max_sectors) ?: 0xFFFF;
@@ -1065,9 +991,6 @@ static void virtscsi_remove(struct virtio_device *vdev)
 		virtscsi_cancel_event_work(vscsi);
 
 	scsi_remove_host(shost);
-
-	virtscsi_cpu_notif_remove(vscsi);
-
 	virtscsi_remove_vqs(vdev);
 	scsi_host_put(shost);
 }
@@ -1075,10 +998,6 @@ static void virtscsi_remove(struct virtio_device *vdev)
 #ifdef CONFIG_PM_SLEEP
 static int virtscsi_freeze(struct virtio_device *vdev)
 {
-	struct Scsi_Host *sh = virtio_scsi_host(vdev);
-	struct virtio_scsi *vscsi = shost_priv(sh);
-
-	virtscsi_cpu_notif_remove(vscsi);
 	virtscsi_remove_vqs(vdev);
 	return 0;
 }
@@ -1093,11 +1012,6 @@ static int virtscsi_restore(struct virtio_device *vdev)
 	if (err)
 		return err;
 
-	err = virtscsi_cpu_notif_add(vscsi);
-	if (err) {
-		vdev->config->del_vqs(vdev);
-		return err;
-	}
 	virtio_device_ready(vdev);
 
 	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
@@ -1152,16 +1066,6 @@ static int __init init(void)
 		pr_err("mempool_create() for virtscsi_cmd_pool failed\n");
 		goto error;
 	}
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
-				      "scsi/virtio:online",
-				      virtscsi_cpu_online, NULL);
-	if (ret < 0)
-		goto error;
-	virtioscsi_online = ret;
-	ret = cpuhp_setup_state_multi(CPUHP_VIRT_SCSI_DEAD, "scsi/virtio:dead",
-				      NULL, virtscsi_cpu_online);
-	if (ret)
-		goto error;
 	ret = register_virtio_driver(&virtio_scsi_driver);
 	if (ret < 0)
 		goto error;
@@ -1177,17 +1081,12 @@ static int __init init(void)
 		kmem_cache_destroy(virtscsi_cmd_cache);
 		virtscsi_cmd_cache = NULL;
 	}
-	if (virtioscsi_online)
-		cpuhp_remove_multi_state(virtioscsi_online);
-	cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD);
 	return ret;
 }
 
 static void __exit fini(void)
 {
 	unregister_virtio_driver(&virtio_scsi_driver);
-	cpuhp_remove_multi_state(virtioscsi_online);
-	cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD);
 	mempool_destroy(virtscsi_cmd_pool);
 	kmem_cache_destroy(virtscsi_cmd_cache);
 }

drivers/vhost/vhost.h

@@ -76,6 +76,13 @@ struct vhost_umem {
 	int numem;
 };
 
+enum vhost_uaddr_type {
+	VHOST_ADDR_DESC = 0,
+	VHOST_ADDR_AVAIL = 1,
+	VHOST_ADDR_USED = 2,
+	VHOST_NUM_ADDRS = 3,
+};
+
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
 	struct vhost_dev *dev;
@@ -86,6 +93,7 @@ struct vhost_virtqueue {
 	struct vring_desc __user *desc;
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
+	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
 	struct file *kick;
 	struct file *call;
 	struct file *error;

drivers/virtio/virtio_balloon.c

@@ -413,7 +413,8 @@ static int init_vqs(struct virtio_balloon *vb)
 	 * optionally stat.
 	 */
 	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names);
+	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names,
+			NULL);
 	if (err)
 		return err;
 

drivers/virtio/virtio_input.c

@@ -173,7 +173,8 @@ static int virtinput_init_vqs(struct virtio_input *vi)
 	static const char * const names[] = { "events", "status" };
 	int err;
 
-	err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names);
+	err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names,
+			NULL);
 	if (err)
 		return err;
 	vi->evt = vqs[0];

drivers/virtio/virtio_mmio.c

@@ -70,7 +70,7 @@
 #include <linux/spinlock.h>
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
-#include <linux/virtio_mmio.h>
+#include <uapi/linux/virtio_mmio.h>
 #include <linux/virtio_ring.h>
 
 
@@ -446,7 +446,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
-		       const char * const names[])
+		       const char * const names[],
+		       struct irq_affinity *desc)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);

drivers/virtio/virtio_pci_common.h

@@ -31,17 +31,6 @@
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
 
-struct virtio_pci_vq_info {
-	/* the actual virtqueue */
-	struct virtqueue *vq;
-
-	/* the list node for the virtqueues list */
-	struct list_head node;
-
-	/* MSI-X vector (or none) */
-	unsigned msix_vector;
-};
-
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -75,47 +64,25 @@ struct virtio_pci_device {
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
 
-	/* a list of queues so we can dispatch IRQs */
-	spinlock_t lock;
-	struct list_head virtqueues;
-
-	/* array of all queues for house-keeping */
-	struct virtio_pci_vq_info **vqs;
-
-	/* MSI-X support */
-	int msix_enabled;
-	int intx_enabled;
 	cpumask_var_t *msix_affinity_masks;
 	/* Name strings for interrupts. This size should be enough,
 	 * and I'm too lazy to allocate each name separately. */
 	char (*msix_names)[256];
-	/* Number of available vectors */
-	unsigned msix_vectors;
-	/* Vectors allocated, excluding per-vq vectors if any */
-	unsigned msix_used_vectors;
-
-	/* Whether we have vector per vq */
-	bool per_vq_vectors;
+	/* Total Number of MSI-X vectors (including per-VQ ones). */
+	int msix_vectors;
+	/* Map of per-VQ MSI-X vectors, may be NULL */
+	unsigned *msix_vector_map;
 
 	struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
-				      struct virtio_pci_vq_info *info,
 				      unsigned idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
 				      u16 msix_vec);
-	void (*del_vq)(struct virtio_pci_vq_info *info);
+	void (*del_vq)(struct virtqueue *vq);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
 };
 
-/* Constants for MSI-X */
-/* Use first vector for configuration changes, second and the rest for
- * virtqueues Thus, we need at least 2 vectors for MSI. */
-enum {
-	VP_MSIX_CONFIG_VECTOR = 0,
-	VP_MSIX_VQ_VECTOR = 1,
-};
-
 /* Convert a generic virtio device to our structure */
 static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
 {
@@ -130,9 +97,8 @@ bool vp_notify(struct virtqueue *vq);
 void vp_del_vqs(struct virtio_device *vdev);
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-		       struct virtqueue *vqs[],
-		       vq_callback_t *callbacks[],
-		       const char * const names[]);
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc);
 const char *vp_bus_name(struct virtio_device *vdev);
 
 /* Setup the affinity for a virtqueue:
@@ -142,6 +108,8 @@ const char *vp_bus_name(struct virtio_device *vdev);
  */
 int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
 
+const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index);
+
 #if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
 int virtio_pci_legacy_probe(struct virtio_pci_device *);
 void virtio_pci_legacy_remove(struct virtio_pci_device *);

drivers/virtio/virtio_pci_legacy.c

@@ -112,7 +112,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
-				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -130,8 +129,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
 		return ERR_PTR(-ENOENT);
 
-	info->msix_vector = msix_vec;
-
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
@@ -162,14 +159,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	return ERR_PTR(err);
 }
 
-static void del_vq(struct virtio_pci_vq_info *info)
+static void del_vq(struct virtqueue *vq)
 {
-	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,
 			  vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
 		/* Flush the write out to device */
@@ -194,6 +190,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 /* the PCI probing function */

drivers/virtio/virtio_pci_modern.c

@@ -293,7 +293,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 }
 
 static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
-				  struct virtio_pci_vq_info *info,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
@@ -323,8 +322,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	/* get offset of notification word for this vq */
 	off = vp_ioread16(&cfg->queue_notify_off);
 
-	info->msix_vector = msix_vec;
-
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
@@ -387,13 +384,12 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 }
 
 static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-			      struct virtqueue *vqs[],
-			      vq_callback_t *callbacks[],
-			      const char * const names[])
+		struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		const char * const names[], struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtqueue *vq;
-	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names);
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, desc);
 
 	if (rc)
 		return rc;
@@ -409,14 +405,13 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	return 0;
 }
 
-static void del_vq(struct virtio_pci_vq_info *info)
+static void del_vq(struct virtqueue *vq)
 {
-	struct virtqueue *vq = info->vq;
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	vp_iowrite16(vq->index, &vp_dev->common->queue_select);
 
-	if (vp_dev->msix_enabled) {
+	if (vp_dev->pci_dev->msix_enabled) {
 		vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
 			     &vp_dev->common->queue_msix_vector);
 		/* Flush the write out to device */
@@ -442,6 +437,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -457,6 +453,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
 };
 
 /**

include/linux/blk-mq-virtio.h

+#ifndef _LINUX_BLK_MQ_VIRTIO_H
+#define _LINUX_BLK_MQ_VIRTIO_H
+
+struct blk_mq_tag_set;
+struct virtio_device;
+
+int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set,
+		struct virtio_device *vdev, int first_vec);
+
+#endif /* _LINUX_BLK_MQ_VIRTIO_H */

include/linux/cpuhotplug.h

@@ -26,7 +26,6 @@ enum cpuhp_state {
 	CPUHP_ARM_OMAP_WAKE_DEAD,
 	CPUHP_IRQ_POLL_DEAD,
 	CPUHP_BLOCK_SOFTIRQ_DEAD,
-	CPUHP_VIRT_SCSI_DEAD,
 	CPUHP_ACPI_CPUDRV_DEAD,
 	CPUHP_S390_PFAULT_DEAD,
 	CPUHP_BLK_MQ_DEAD,

include/linux/virtio_config.h

@@ -7,6 +7,8 @@
 #include <linux/virtio_byteorder.h>
 #include <uapi/linux/virtio_config.h>
 
+struct irq_affinity;
+
 /**
  * virtio_config_ops - operations for configuring a virtio device
  * @get: read the value of a configuration field
@@ -56,6 +58,7 @@
  *      This returns a pointer to the bus name a la pci_name from which
  *      the caller can then copy.
  * @set_vq_affinity: set the affinity for a virtqueue.
+ * @get_vq_affinity: get the affinity for a virtqueue (optional).
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
@@ -68,14 +71,15 @@ struct virtio_config_ops {
 	void (*set_status)(struct virtio_device *vdev, u8 status);
 	void (*reset)(struct virtio_device *vdev);
 	int (*find_vqs)(struct virtio_device *, unsigned nvqs,
-			struct virtqueue *vqs[],
-			vq_callback_t *callbacks[],
-			const char * const names[]);
+			struct virtqueue *vqs[], vq_callback_t *callbacks[],
+			const char * const names[], struct irq_affinity *desc);
 	void (*del_vqs)(struct virtio_device *);
 	u64 (*get_features)(struct virtio_device *vdev);
 	int (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
 	int (*set_vq_affinity)(struct virtqueue *vq, int cpu);
+	const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev,
+			int index);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
@@ -169,7 +173,7 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 	vq_callback_t *callbacks[] = { c };
 	const char *names[] = { n };
 	struct virtqueue *vq;
-	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names);
+	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 	return vq;

include/uapi/linux/Kbuild

@@ -466,6 +466,7 @@ header-y += virtio_console.h
 header-y += virtio_gpu.h
 header-y += virtio_ids.h
 header-y += virtio_input.h
+header-y += virtio_mmio.h
 header-y += virtio_net.h
 header-y += virtio_pci.h
 header-y += virtio_ring.h

include/uapi/linux/virtio_pci.h

@@ -79,7 +79,7 @@
  * configuration space */
 #define VIRTIO_PCI_CONFIG_OFF(msix_enabled)	((msix_enabled) ? 24 : 20)
 /* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */
-#define VIRTIO_PCI_CONFIG(dev)	VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled)
+#define VIRTIO_PCI_CONFIG(dev)	VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled)
 
 /* Virtio ABI version, this must match exactly */
 #define VIRTIO_PCI_ABI_VERSION		0

net/vmw_vsock/virtio_transport.c

@@ -532,7 +532,8 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 	vsock->vdev = vdev;
 
 	ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX,
-					    vsock->vqs, callbacks, names);
+					    vsock->vqs, callbacks, names,
+					    NULL);
 	if (ret < 0)
 		goto out;