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

Pull virtio updates from Michael Tsirkin:

 - A huge patchset supporting vq resize using the new vq reset
   capability

 - Features, fixes, and cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (88 commits)
  vdpa/mlx5: Fix possible uninitialized return value
  vdpa_sim_blk: add support for discard and write-zeroes
  vdpa_sim_blk: add support for VIRTIO_BLK_T_FLUSH
  vdpa_sim_blk: make vdpasim_blk_check_range usable by other requests
  vdpa_sim_blk: check if sector is 0 for commands other than read or write
  vdpa_sim: Implement suspend vdpa op
  vhost-vdpa: uAPI to suspend the device
  vhost-vdpa: introduce SUSPEND backend feature bit
  vdpa: Add suspend operation
  virtio-blk: Avoid use-after-free on suspend/resume
  virtio_vdpa: support the arg sizes of find_vqs()
  vhost-vdpa: Call ida_simple_remove() when failed
  vDPA: fix 'cast to restricted le16' warnings in vdpa.c
  vDPA: !FEATURES_OK should not block querying device config space
  vDPA/ifcvf: support userspace to query features and MQ of a management device
  vDPA/ifcvf: get_config_size should return a value no greater than dev implementation
  vhost scsi: Allow user to control num virtqueues
  vhost-scsi: Fix max number of virtqueues
  vdpa/mlx5: Support different address spaces for control and data
  vdpa/mlx5: Implement susupend virtqueue callback
  ...

3 files changed, 153 insertions, 48 deletions

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 9b65509424dc..7ebf106d50c1 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -159,9 +159,13 @@ enum {
 };
 
 #define VHOST_SCSI_MAX_TARGET	256
-#define VHOST_SCSI_MAX_VQ	128
+#define VHOST_SCSI_MAX_IO_VQ	1024
 #define VHOST_SCSI_MAX_EVENT	128
 
+static unsigned vhost_scsi_max_io_vqs = 128;
+module_param_named(max_io_vqs, vhost_scsi_max_io_vqs, uint, 0644);
+MODULE_PARM_DESC(max_io_vqs, "Set the max number of IO virtqueues a vhost scsi device can support. The default is 128. The max is 1024.");
+
 struct vhost_scsi_virtqueue {
 	struct vhost_virtqueue vq;
 	/*
@@ -186,7 +190,9 @@ struct vhost_scsi {
 	char vs_vhost_wwpn[TRANSPORT_IQN_LEN];
 
 	struct vhost_dev dev;
-	struct vhost_scsi_virtqueue vqs[VHOST_SCSI_MAX_VQ];
+	struct vhost_scsi_virtqueue *vqs;
+	unsigned long *compl_bitmap;
+	struct vhost_scsi_inflight **old_inflight;
 
 	struct vhost_work vs_completion_work; /* cmd completion work item */
 	struct llist_head vs_completion_list; /* cmd completion queue */
@@ -245,7 +251,7 @@ static void vhost_scsi_init_inflight(struct vhost_scsi *vs,
 	struct vhost_virtqueue *vq;
 	int idx, i;
 
-	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
+	for (i = 0; i < vs->dev.nvqs;  i++) {
 		vq = &vs->vqs[i].vq;
 
 		mutex_lock(&vq->mutex);
@@ -533,7 +539,6 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 {
 	struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
 					vs_completion_work);
-	DECLARE_BITMAP(signal, VHOST_SCSI_MAX_VQ);
 	struct virtio_scsi_cmd_resp v_rsp;
 	struct vhost_scsi_cmd *cmd, *t;
 	struct llist_node *llnode;
@@ -541,7 +546,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 	struct iov_iter iov_iter;
 	int ret, vq;
 
-	bitmap_zero(signal, VHOST_SCSI_MAX_VQ);
+	bitmap_zero(vs->compl_bitmap, vs->dev.nvqs);
 	llnode = llist_del_all(&vs->vs_completion_list);
 	llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
 		se_cmd = &cmd->tvc_se_cmd;
@@ -566,7 +571,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 			vhost_add_used(cmd->tvc_vq, cmd->tvc_vq_desc, 0);
 			q = container_of(cmd->tvc_vq, struct vhost_scsi_virtqueue, vq);
 			vq = q - vs->vqs;
-			__set_bit(vq, signal);
+			__set_bit(vq, vs->compl_bitmap);
 		} else
 			pr_err("Faulted on virtio_scsi_cmd_resp\n");
 
@@ -574,8 +579,8 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 	}
 
 	vq = -1;
-	while ((vq = find_next_bit(signal, VHOST_SCSI_MAX_VQ, vq + 1))
-		< VHOST_SCSI_MAX_VQ)
+	while ((vq = find_next_bit(vs->compl_bitmap, vs->dev.nvqs, vq + 1))
+		< vs->dev.nvqs)
 		vhost_signal(&vs->dev, &vs->vqs[vq].vq);
 }
 
@@ -1419,26 +1424,25 @@ static void vhost_scsi_handle_kick(struct vhost_work *work)
 /* Callers must hold dev mutex */
 static void vhost_scsi_flush(struct vhost_scsi *vs)
 {
-	struct vhost_scsi_inflight *old_inflight[VHOST_SCSI_MAX_VQ];
 	int i;
 
 	/* Init new inflight and remember the old inflight */
-	vhost_scsi_init_inflight(vs, old_inflight);
+	vhost_scsi_init_inflight(vs, vs->old_inflight);
 
 	/*
 	 * The inflight->kref was initialized to 1. We decrement it here to
 	 * indicate the start of the flush operation so that it will reach 0
 	 * when all the reqs are finished.
 	 */
-	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
-		kref_put(&old_inflight[i]->kref, vhost_scsi_done_inflight);
+	for (i = 0; i < vs->dev.nvqs; i++)
+		kref_put(&vs->old_inflight[i]->kref, vhost_scsi_done_inflight);
 
 	/* Flush both the vhost poll and vhost work */
 	vhost_dev_flush(&vs->dev);
 
 	/* Wait for all reqs issued before the flush to be finished */
-	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
-		wait_for_completion(&old_inflight[i]->comp);
+	for (i = 0; i < vs->dev.nvqs; i++)
+		wait_for_completion(&vs->old_inflight[i]->comp);
 }
 
 static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq)
@@ -1601,7 +1605,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 		memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
 		       sizeof(vs->vs_vhost_wwpn));
 
-		for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
+		for (i = VHOST_SCSI_VQ_IO; i < vs->dev.nvqs; i++) {
 			vq = &vs->vqs[i].vq;
 			if (!vhost_vq_is_setup(vq))
 				continue;
@@ -1611,7 +1615,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 				goto destroy_vq_cmds;
 		}
 
-		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
+		for (i = 0; i < vs->dev.nvqs; i++) {
 			vq = &vs->vqs[i].vq;
 			mutex_lock(&vq->mutex);
 			vhost_vq_set_backend(vq, vs_tpg);
@@ -1713,7 +1717,7 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
 		target_undepend_item(&se_tpg->tpg_group.cg_item);
 	}
 	if (match) {
-		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
+		for (i = 0; i < vs->dev.nvqs; i++) {
 			vq = &vs->vqs[i].vq;
 			mutex_lock(&vq->mutex);
 			vhost_vq_set_backend(vq, NULL);
@@ -1722,7 +1726,7 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
 		/* Make sure cmds are not running before tearing them down. */
 		vhost_scsi_flush(vs);
 
-		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
+		for (i = 0; i < vs->dev.nvqs; i++) {
 			vq = &vs->vqs[i].vq;
 			vhost_scsi_destroy_vq_cmds(vq);
 		}
@@ -1762,7 +1766,7 @@ static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features)
 		return -EFAULT;
 	}
 
-	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
+	for (i = 0; i < vs->dev.nvqs; i++) {
 		vq = &vs->vqs[i].vq;
 		mutex_lock(&vq->mutex);
 		vq->acked_features = features;
@@ -1776,16 +1780,40 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 {
 	struct vhost_scsi *vs;
 	struct vhost_virtqueue **vqs;
-	int r = -ENOMEM, i;
+	int r = -ENOMEM, i, nvqs = vhost_scsi_max_io_vqs;
 
 	vs = kvzalloc(sizeof(*vs), GFP_KERNEL);
 	if (!vs)
 		goto err_vs;
 
-	vqs = kmalloc_array(VHOST_SCSI_MAX_VQ, sizeof(*vqs), GFP_KERNEL);
-	if (!vqs)
+	if (nvqs > VHOST_SCSI_MAX_IO_VQ) {
+		pr_err("Invalid max_io_vqs of %d. Using %d.\n", nvqs,
+		       VHOST_SCSI_MAX_IO_VQ);
+		nvqs = VHOST_SCSI_MAX_IO_VQ;
+	} else if (nvqs == 0) {
+		pr_err("Invalid max_io_vqs of %d. Using 1.\n", nvqs);
+		nvqs = 1;
+	}
+	nvqs += VHOST_SCSI_VQ_IO;
+
+	vs->compl_bitmap = bitmap_alloc(nvqs, GFP_KERNEL);
+	if (!vs->compl_bitmap)
+		goto err_compl_bitmap;
+
+	vs->old_inflight = kmalloc_array(nvqs, sizeof(*vs->old_inflight),
+					 GFP_KERNEL | __GFP_ZERO);
+	if (!vs->old_inflight)
+		goto err_inflight;
+
+	vs->vqs = kmalloc_array(nvqs, sizeof(*vs->vqs),
+				GFP_KERNEL | __GFP_ZERO);
+	if (!vs->vqs)
 		goto err_vqs;
 
+	vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL);
+	if (!vqs)
+		goto err_local_vqs;
+
 	vhost_work_init(&vs->vs_completion_work, vhost_scsi_complete_cmd_work);
 	vhost_work_init(&vs->vs_event_work, vhost_scsi_evt_work);
 
@@ -1796,11 +1824,11 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	vqs[VHOST_SCSI_VQ_EVT] = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
 	vs->vqs[VHOST_SCSI_VQ_CTL].vq.handle_kick = vhost_scsi_ctl_handle_kick;
 	vs->vqs[VHOST_SCSI_VQ_EVT].vq.handle_kick = vhost_scsi_evt_handle_kick;
-	for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
+	for (i = VHOST_SCSI_VQ_IO; i < nvqs; i++) {
 		vqs[i] = &vs->vqs[i].vq;
 		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
 	}
-	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV,
+	vhost_dev_init(&vs->dev, vqs, nvqs, UIO_MAXIOV,
 		       VHOST_SCSI_WEIGHT, 0, true, NULL);
 
 	vhost_scsi_init_inflight(vs, NULL);
@@ -1808,7 +1836,13 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	f->private_data = vs;
 	return 0;
 
+err_local_vqs:
+	kfree(vs->vqs);
 err_vqs:
+	kfree(vs->old_inflight);
+err_inflight:
+	bitmap_free(vs->compl_bitmap);
+err_compl_bitmap:
 	kvfree(vs);
 err_vs:
 	return r;
@@ -1826,6 +1860,9 @@ static int vhost_scsi_release(struct inode *inode, struct file *f)
 	vhost_dev_stop(&vs->dev);
 	vhost_dev_cleanup(&vs->dev);
 	kfree(vs->dev.vqs);
+	kfree(vs->vqs);
+	kfree(vs->old_inflight);
+	bitmap_free(vs->compl_bitmap);
 	kvfree(vs);
 	return 0;
 }
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 23dcbfdfa13b..166044642fd5 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -347,6 +347,14 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v,
 	return 0;
 }
 
+static bool vhost_vdpa_can_suspend(const struct vhost_vdpa *v)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return ops->suspend;
+}
+
 static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
 {
 	struct vdpa_device *vdpa = v->vdpa;
@@ -470,6 +478,22 @@ static long vhost_vdpa_get_vqs_count(struct vhost_vdpa *v, u32 __user *argp)
 	return 0;
 }
 
+/* After a successful return of ioctl the device must not process more
+ * virtqueue descriptors. The device can answer to read or writes of config
+ * fields as if it were not suspended. In particular, writing to "queue_enable"
+ * with a value of 1 will not make the device start processing buffers.
+ */
+static long vhost_vdpa_suspend(struct vhost_vdpa *v)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (!ops->suspend)
+		return -EOPNOTSUPP;
+
+	return ops->suspend(vdpa);
+}
+
 static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 				   void __user *argp)
 {
@@ -577,7 +601,11 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 	if (cmd == VHOST_SET_BACKEND_FEATURES) {
 		if (copy_from_user(&features, featurep, sizeof(features)))
 			return -EFAULT;
-		if (features & ~VHOST_VDPA_BACKEND_FEATURES)
+		if (features & ~(VHOST_VDPA_BACKEND_FEATURES |
+				 BIT_ULL(VHOST_BACKEND_F_SUSPEND)))
+			return -EOPNOTSUPP;
+		if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) &&
+		     !vhost_vdpa_can_suspend(v))
 			return -EOPNOTSUPP;
 		vhost_set_backend_features(&v->vdev, features);
 		return 0;
@@ -628,6 +656,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 		break;
 	case VHOST_GET_BACKEND_FEATURES:
 		features = VHOST_VDPA_BACKEND_FEATURES;
+		if (vhost_vdpa_can_suspend(v))
+			features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND);
 		if (copy_to_user(featurep, &features, sizeof(features)))
 			r = -EFAULT;
 		break;
@@ -640,6 +670,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 	case VHOST_VDPA_GET_VQS_COUNT:
 		r = vhost_vdpa_get_vqs_count(v, argp);
 		break;
+	case VHOST_VDPA_SUSPEND:
+		r = vhost_vdpa_suspend(v);
+		break;
 	default:
 		r = vhost_dev_ioctl(&v->vdev, cmd, argp);
 		if (r == -ENOIOCTLCMD)
@@ -1076,7 +1109,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
 	if (!bus)
 		return -EFAULT;
 
-	if (!iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
+	if (!device_iommu_capable(dma_dev, IOMMU_CAP_CACHE_COHERENCY))
 		return -ENOTSUPP;
 
 	v->domain = iommu_domain_alloc(bus);
@@ -1363,6 +1396,7 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 
 err:
 	put_device(&v->dev);
+	ida_simple_remove(&vhost_vdpa_ida, v->minor);
 	return r;
 }
 
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index eab55accf381..11f59dd06a74 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -1095,7 +1095,8 @@ EXPORT_SYMBOL(vringh_need_notify_kern);
 #if IS_REACHABLE(CONFIG_VHOST_IOTLB)
 
 static int iotlb_translate(const struct vringh *vrh,
-			   u64 addr, u64 len, struct bio_vec iov[],
+			   u64 addr, u64 len, u64 *translated,
+			   struct bio_vec iov[],
 			   int iov_size, u32 perm)
 {
 	struct vhost_iotlb_map *map;
@@ -1136,43 +1137,76 @@ static int iotlb_translate(const struct vringh *vrh,
 
 	spin_unlock(vrh->iotlb_lock);
 
+	if (translated)
+		*translated = min(len, s);
+
 	return ret;
 }
 
 static inline int copy_from_iotlb(const struct vringh *vrh, void *dst,
 				  void *src, size_t len)
 {
-	struct iov_iter iter;
-	struct bio_vec iov[16];
-	int ret;
+	u64 total_translated = 0;
 
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)src,
-			      len, iov, 16, VHOST_MAP_RO);
-	if (ret < 0)
-		return ret;
+	while (total_translated < len) {
+		struct bio_vec iov[16];
+		struct iov_iter iter;
+		u64 translated;
+		int ret;
 
-	iov_iter_bvec(&iter, READ, iov, ret, len);
+		ret = iotlb_translate(vrh, (u64)(uintptr_t)src,
+				      len - total_translated, &translated,
+				      iov, ARRAY_SIZE(iov), VHOST_MAP_RO);
+		if (ret == -ENOBUFS)
+			ret = ARRAY_SIZE(iov);
+		else if (ret < 0)
+			return ret;
 
-	ret = copy_from_iter(dst, len, &iter);
+		iov_iter_bvec(&iter, READ, iov, ret, translated);
 
-	return ret;
+		ret = copy_from_iter(dst, translated, &iter);
+		if (ret < 0)
+			return ret;
+
+		src += translated;
+		dst += translated;
+		total_translated += translated;
+	}
+
+	return total_translated;
 }
 
 static inline int copy_to_iotlb(const struct vringh *vrh, void *dst,
 				void *src, size_t len)
 {
-	struct iov_iter iter;
-	struct bio_vec iov[16];
-	int ret;
+	u64 total_translated = 0;
 
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)dst,
-			      len, iov, 16, VHOST_MAP_WO);
-	if (ret < 0)
-		return ret;
+	while (total_translated < len) {
+		struct bio_vec iov[16];
+		struct iov_iter iter;
+		u64 translated;
+		int ret;
+
+		ret = iotlb_translate(vrh, (u64)(uintptr_t)dst,
+				      len - total_translated, &translated,
+				      iov, ARRAY_SIZE(iov), VHOST_MAP_WO);
+		if (ret == -ENOBUFS)
+			ret = ARRAY_SIZE(iov);
+		else if (ret < 0)
+			return ret;
 
-	iov_iter_bvec(&iter, WRITE, iov, ret, len);
+		iov_iter_bvec(&iter, WRITE, iov, ret, translated);
+
+		ret = copy_to_iter(src, translated, &iter);
+		if (ret < 0)
+			return ret;
+
+		src += translated;
+		dst += translated;
+		total_translated += translated;
+	}
 
-	return copy_to_iter(src, len, &iter);
+	return total_translated;
 }
 
 static inline int getu16_iotlb(const struct vringh *vrh,
@@ -1183,7 +1217,7 @@ static inline int getu16_iotlb(const struct vringh *vrh,
 	int ret;
 
 	/* Atomic read is needed for getu16 */
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p),
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL,
 			      &iov, 1, VHOST_MAP_RO);
 	if (ret < 0)
 		return ret;
@@ -1204,7 +1238,7 @@ static inline int putu16_iotlb(const struct vringh *vrh,
 	int ret;
 
 	/* Atomic write is needed for putu16 */
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p),
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL,
 			      &iov, 1, VHOST_MAP_WO);
 	if (ret < 0)
 		return ret;