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

Pull virtio updates from Michael Tsirkin:

 - vduse driver ("vDPA Device in Userspace") supporting emulated virtio
   block devices

 - virtio-vsock support for end of record with SEQPACKET

 - vdpa: mac and mq support for ifcvf and mlx5

 - vdpa: management netlink for ifcvf

 - virtio-i2c, gpio dt bindings

 - misc fixes and cleanups

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (39 commits)
  Documentation: Add documentation for VDUSE
  vduse: Introduce VDUSE - vDPA Device in Userspace
  vduse: Implement an MMU-based software IOTLB
  vdpa: Support transferring virtual addressing during DMA mapping
  vdpa: factor out vhost_vdpa_pa_map() and vhost_vdpa_pa_unmap()
  vdpa: Add an opaque pointer for vdpa_config_ops.dma_map()
  vhost-iotlb: Add an opaque pointer for vhost IOTLB
  vhost-vdpa: Handle the failure of vdpa_reset()
  vdpa: Add reset callback in vdpa_config_ops
  vdpa: Fix some coding style issues
  file: Export receive_fd() to modules
  eventfd: Export eventfd_wake_count to modules
  iova: Export alloc_iova_fast() and free_iova_fast()
  virtio-blk: remove unneeded "likely" statements
  virtio-balloon: Use virtio_find_vqs() helper
  vdpa: Make use of PFN_PHYS/PFN_UP/PFN_DOWN helper macro
  vsock_test: update message bounds test for MSG_EOR
  af_vsock: rename variables in receive loop
  virtio/vsock: support MSG_EOR bit processing
  vhost/vsock: support MSG_EOR bit processing
  ...

4 files changed, 177 insertions, 73 deletions

diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c
index 0582079e4bcc..670d56c879e5 100644
--- a/drivers/vhost/iotlb.c
+++ b/drivers/vhost/iotlb.c
@@ -36,19 +36,21 @@ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
 EXPORT_SYMBOL_GPL(vhost_iotlb_map_free);
 
 /**
- * vhost_iotlb_add_range - add a new range to vhost IOTLB
+ * vhost_iotlb_add_range_ctx - add a new range to vhost IOTLB
  * @iotlb: the IOTLB
  * @start: start of the IOVA range
  * @last: last of IOVA range
  * @addr: the address that is mapped to @start
  * @perm: access permission of this range
+ * @opaque: the opaque pointer for the new mapping
  *
  * Returns an error last is smaller than start or memory allocation
  * fails
  */
-int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
-			  u64 start, u64 last,
-			  u64 addr, unsigned int perm)
+int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb,
+			      u64 start, u64 last,
+			      u64 addr, unsigned int perm,
+			      void *opaque)
 {
 	struct vhost_iotlb_map *map;
 
@@ -71,6 +73,7 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
 	map->last = last;
 	map->addr = addr;
 	map->perm = perm;
+	map->opaque = opaque;
 
 	iotlb->nmaps++;
 	vhost_iotlb_itree_insert(map, &iotlb->root);
@@ -80,6 +83,15 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vhost_iotlb_add_range_ctx);
+
+int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
+			  u64 start, u64 last,
+			  u64 addr, unsigned int perm)
+{
+	return vhost_iotlb_add_range_ctx(iotlb, start, last,
+					 addr, perm, NULL);
+}
 EXPORT_SYMBOL_GPL(vhost_iotlb_add_range);
 
 /**
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 46f897e41217..532e204f2b1b 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1,24 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*******************************************************************************
  * Vhost kernel TCM fabric driver for virtio SCSI initiators
  *
  * (C) Copyright 2010-2013 Datera, Inc.
  * (C) Copyright 2010-2012 IBM Corp.
  *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
- *
  * Authors: Nicholas A. Bellinger <nab@daterainc.com>
  *          Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that 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/module.h>
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 9479f7f79217..f41d081777f5 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -116,12 +116,13 @@ static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid)
 	irq_bypass_unregister_producer(&vq->call_ctx.producer);
 }
 
-static void vhost_vdpa_reset(struct vhost_vdpa *v)
+static int vhost_vdpa_reset(struct vhost_vdpa *v)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 
-	vdpa_reset(vdpa);
 	v->in_batch = 0;
+
+	return vdpa_reset(vdpa);
 }
 
 static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp)
@@ -157,7 +158,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
 	u8 status, status_old;
-	int nvqs = v->nvqs;
+	int ret, nvqs = v->nvqs;
 	u16 i;
 
 	if (copy_from_user(&status, statusp, sizeof(status)))
@@ -172,7 +173,12 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
 	if (status != 0 && (ops->get_status(vdpa) & ~status) != 0)
 		return -EINVAL;
 
-	ops->set_status(vdpa, status);
+	if (status == 0) {
+		ret = ops->reset(vdpa);
+		if (ret)
+			return ret;
+	} else
+		ops->set_status(vdpa, status);
 
 	if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK))
 		for (i = 0; i < nvqs; i++)
@@ -498,7 +504,7 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 	return r;
 }
 
-static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vhost_iotlb *iotlb = dev->iotlb;
@@ -507,19 +513,44 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 	unsigned long pfn, pinned;
 
 	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
-		pinned = map->size >> PAGE_SHIFT;
-		for (pfn = map->addr >> PAGE_SHIFT;
+		pinned = PFN_DOWN(map->size);
+		for (pfn = PFN_DOWN(map->addr);
 		     pinned > 0; pfn++, pinned--) {
 			page = pfn_to_page(pfn);
 			if (map->perm & VHOST_ACCESS_WO)
 				set_page_dirty_lock(page);
 			unpin_user_page(page);
 		}
-		atomic64_sub(map->size >> PAGE_SHIFT, &dev->mm->pinned_vm);
+		atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm);
 		vhost_iotlb_map_free(iotlb, map);
 	}
 }
 
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vhost_iotlb *iotlb = dev->iotlb;
+	struct vhost_iotlb_map *map;
+	struct vdpa_map_file *map_file;
+
+	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
+		map_file = (struct vdpa_map_file *)map->opaque;
+		fput(map_file->file);
+		kfree(map_file);
+		vhost_iotlb_map_free(iotlb, map);
+	}
+}
+
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+
+	if (vdpa->use_va)
+		return vhost_vdpa_va_unmap(v, start, last);
+
+	return vhost_vdpa_pa_unmap(v, start, last);
+}
+
 static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v)
 {
 	struct vhost_dev *dev = &v->vdev;
@@ -551,21 +582,21 @@ static int perm_to_iommu_flags(u32 perm)
 	return flags | IOMMU_CACHE;
 }
 
-static int vhost_vdpa_map(struct vhost_vdpa *v,
-			  u64 iova, u64 size, u64 pa, u32 perm)
+static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova,
+			  u64 size, u64 pa, u32 perm, void *opaque)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
 	int r = 0;
 
-	r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1,
-				  pa, perm);
+	r = vhost_iotlb_add_range_ctx(dev->iotlb, iova, iova + size - 1,
+				      pa, perm, opaque);
 	if (r)
 		return r;
 
 	if (ops->dma_map) {
-		r = ops->dma_map(vdpa, iova, size, pa, perm);
+		r = ops->dma_map(vdpa, iova, size, pa, perm, opaque);
 	} else if (ops->set_map) {
 		if (!v->in_batch)
 			r = ops->set_map(vdpa, dev->iotlb);
@@ -573,13 +604,15 @@ static int vhost_vdpa_map(struct vhost_vdpa *v,
 		r = iommu_map(v->domain, iova, pa, size,
 			      perm_to_iommu_flags(perm));
 	}
-
-	if (r)
+	if (r) {
 		vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
-	else
-		atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm);
+		return r;
+	}
 
-	return r;
+	if (!vdpa->use_va)
+		atomic64_add(PFN_DOWN(size), &dev->mm->pinned_vm);
+
+	return 0;
 }
 
 static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
@@ -600,38 +633,78 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
 	}
 }
 
-static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
-					   struct vhost_iotlb_msg *msg)
+static int vhost_vdpa_va_map(struct vhost_vdpa *v,
+			     u64 iova, u64 size, u64 uaddr, u32 perm)
+{
+	struct vhost_dev *dev = &v->vdev;
+	u64 offset, map_size, map_iova = iova;
+	struct vdpa_map_file *map_file;
+	struct vm_area_struct *vma;
+	int ret;
+
+	mmap_read_lock(dev->mm);
+
+	while (size) {
+		vma = find_vma(dev->mm, uaddr);
+		if (!vma) {
+			ret = -EINVAL;
+			break;
+		}
+		map_size = min(size, vma->vm_end - uaddr);
+		if (!(vma->vm_file && (vma->vm_flags & VM_SHARED) &&
+			!(vma->vm_flags & (VM_IO | VM_PFNMAP))))
+			goto next;
+
+		map_file = kzalloc(sizeof(*map_file), GFP_KERNEL);
+		if (!map_file) {
+			ret = -ENOMEM;
+			break;
+		}
+		offset = (vma->vm_pgoff << PAGE_SHIFT) + uaddr - vma->vm_start;
+		map_file->offset = offset;
+		map_file->file = get_file(vma->vm_file);
+		ret = vhost_vdpa_map(v, map_iova, map_size, uaddr,
+				     perm, map_file);
+		if (ret) {
+			fput(map_file->file);
+			kfree(map_file);
+			break;
+		}
+next:
+		size -= map_size;
+		uaddr += map_size;
+		map_iova += map_size;
+	}
+	if (ret)
+		vhost_vdpa_unmap(v, iova, map_iova - iova);
+
+	mmap_read_unlock(dev->mm);
+
+	return ret;
+}
+
+static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
+			     u64 iova, u64 size, u64 uaddr, u32 perm)
 {
 	struct vhost_dev *dev = &v->vdev;
-	struct vhost_iotlb *iotlb = dev->iotlb;
 	struct page **page_list;
 	unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
 	unsigned int gup_flags = FOLL_LONGTERM;
 	unsigned long npages, cur_base, map_pfn, last_pfn = 0;
 	unsigned long lock_limit, sz2pin, nchunks, i;
-	u64 iova = msg->iova;
+	u64 start = iova;
 	long pinned;
 	int ret = 0;
 
-	if (msg->iova < v->range.first || !msg->size ||
-	    msg->iova > U64_MAX - msg->size + 1 ||
-	    msg->iova + msg->size - 1 > v->range.last)
-		return -EINVAL;
-
-	if (vhost_iotlb_itree_first(iotlb, msg->iova,
-				    msg->iova + msg->size - 1))
-		return -EEXIST;
-
 	/* Limit the use of memory for bookkeeping */
 	page_list = (struct page **) __get_free_page(GFP_KERNEL);
 	if (!page_list)
 		return -ENOMEM;
 
-	if (msg->perm & VHOST_ACCESS_WO)
+	if (perm & VHOST_ACCESS_WO)
 		gup_flags |= FOLL_WRITE;
 
-	npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT;
+	npages = PFN_UP(size + (iova & ~PAGE_MASK));
 	if (!npages) {
 		ret = -EINVAL;
 		goto free;
@@ -639,13 +712,13 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 
 	mmap_read_lock(dev->mm);
 
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	lock_limit = PFN_DOWN(rlimit(RLIMIT_MEMLOCK));
 	if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) {
 		ret = -ENOMEM;
 		goto unlock;
 	}
 
-	cur_base = msg->uaddr & PAGE_MASK;
+	cur_base = uaddr & PAGE_MASK;
 	iova &= PAGE_MASK;
 	nchunks = 0;
 
@@ -673,10 +746,10 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 
 			if (last_pfn && (this_pfn != last_pfn + 1)) {
 				/* Pin a contiguous chunk of memory */
-				csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
+				csize = PFN_PHYS(last_pfn - map_pfn + 1);
 				ret = vhost_vdpa_map(v, iova, csize,
-						     map_pfn << PAGE_SHIFT,
-						     msg->perm);
+						     PFN_PHYS(map_pfn),
+						     perm, NULL);
 				if (ret) {
 					/*
 					 * Unpin the pages that are left unmapped
@@ -699,13 +772,13 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 			last_pfn = this_pfn;
 		}
 
-		cur_base += pinned << PAGE_SHIFT;
+		cur_base += PFN_PHYS(pinned);
 		npages -= pinned;
 	}
 
 	/* Pin the rest chunk */
-	ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
-			     map_pfn << PAGE_SHIFT, msg->perm);
+	ret = vhost_vdpa_map(v, iova, PFN_PHYS(last_pfn - map_pfn + 1),
+			     PFN_PHYS(map_pfn), perm, NULL);
 out:
 	if (ret) {
 		if (nchunks) {
@@ -724,13 +797,38 @@ out:
 			for (pfn = map_pfn; pfn <= last_pfn; pfn++)
 				unpin_user_page(pfn_to_page(pfn));
 		}
-		vhost_vdpa_unmap(v, msg->iova, msg->size);
+		vhost_vdpa_unmap(v, start, size);
 	}
 unlock:
 	mmap_read_unlock(dev->mm);
 free:
 	free_page((unsigned long)page_list);
 	return ret;
+
+}
+
+static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
+					   struct vhost_iotlb_msg *msg)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vdpa_device *vdpa = v->vdpa;
+	struct vhost_iotlb *iotlb = dev->iotlb;
+
+	if (msg->iova < v->range.first || !msg->size ||
+	    msg->iova > U64_MAX - msg->size + 1 ||
+	    msg->iova + msg->size - 1 > v->range.last)
+		return -EINVAL;
+
+	if (vhost_iotlb_itree_first(iotlb, msg->iova,
+				    msg->iova + msg->size - 1))
+		return -EEXIST;
+
+	if (vdpa->use_va)
+		return vhost_vdpa_va_map(v, msg->iova, msg->size,
+					 msg->uaddr, msg->perm);
+
+	return vhost_vdpa_pa_map(v, msg->iova, msg->size, msg->uaddr,
+				 msg->perm);
 }
 
 static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
@@ -860,7 +958,9 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)
 		return -EBUSY;
 
 	nvqs = v->nvqs;
-	vhost_vdpa_reset(v);
+	r = vhost_vdpa_reset(v);
+	if (r)
+		goto err;
 
 	vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {
@@ -945,7 +1045,7 @@ static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf)
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	if (remap_pfn_range(vma, vmf->address & PAGE_MASK,
-			    notify.addr >> PAGE_SHIFT, PAGE_SIZE,
+			    PFN_DOWN(notify.addr), PAGE_SIZE,
 			    vma->vm_page_prot))
 		return VM_FAULT_SIGBUS;
 
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index f249622ef11b..938aefbc75ec 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -114,7 +114,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		size_t nbytes;
 		size_t iov_len, payload_len;
 		int head;
-		bool restore_flag = false;
+		u32 flags_to_restore = 0;
 
 		spin_lock_bh(&vsock->send_pkt_list_lock);
 		if (list_empty(&vsock->send_pkt_list)) {
@@ -178,16 +178,21 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			 * small rx buffers, headers of packets in rx queue are
 			 * created dynamically and are initialized with header
 			 * of current packet(except length). But in case of
-			 * SOCK_SEQPACKET, we also must clear record delimeter
-			 * bit(VIRTIO_VSOCK_SEQ_EOR). Otherwise, instead of one
-			 * packet with delimeter(which marks end of record),
-			 * there will be sequence of packets with delimeter
-			 * bit set. After initialized header will be copied to
-			 * rx buffer, this bit will be restored.
+			 * SOCK_SEQPACKET, we also must clear message delimeter
+			 * bit (VIRTIO_VSOCK_SEQ_EOM) and MSG_EOR bit
+			 * (VIRTIO_VSOCK_SEQ_EOR) if set. Otherwise,
+			 * there will be sequence of packets with these
+			 * bits set. After initialized header will be copied to
+			 * rx buffer, these required bits will be restored.
 			 */
-			if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
-				pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
-				restore_flag = true;
+			if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM) {
+				pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM);
+				flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM;
+
+				if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
+					pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+					flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR;
+				}
 			}
 		}
 
@@ -224,8 +229,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		 * to send it with the next available buffer.
 		 */
 		if (pkt->off < pkt->len) {
-			if (restore_flag)
-				pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+			pkt->hdr.flags |= cpu_to_le32(flags_to_restore);
 
 			/* We are queueing the same virtio_vsock_pkt to handle
 			 * the remaining bytes, and we want to deliver it