Merge tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux

Pull virtio & lguest updates from Rusty Russell:
 "Lots of virtio work which wasn't quite ready for last merge window.

  Plus I dived into lguest again, reworking the pagetable code so we can
  move the switcher page: our fixmaps sometimes take more than 2MB now..."

Ugh.  Annoying conflicts with the tcm_vhost -> vhost_scsi rename.
Hopefully correctly resolved.

* tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (57 commits)
  caif_virtio: Remove bouncing email addresses
  lguest: improve code readability in lg_cpu_start.
  virtio-net: fill only rx queues which are being used
  lguest: map Switcher below fixmap.
  lguest: cache last cpu we ran on.
  lguest: map Switcher text whenever we allocate a new pagetable.
  lguest: don't share Switcher PTE pages between guests.
  lguest: expost switcher_pages array (as lg_switcher_pages).
  lguest: extract shadow PTE walking / allocating.
  lguest: make check_gpte et. al return bool.
  lguest: assume Switcher text is a single page.
  lguest: rename switcher_page to switcher_pages.
  lguest: remove RESERVE_MEM constant.
  lguest: check vaddr not pgd for Switcher protection.
  lguest: prepare to make SWITCHER_ADDR a variable.
  virtio: console: replace EMFILE with EBUSY for already-open port
  virtio-scsi: reset virtqueue affinity when doing cpu hotplug
  virtio-scsi: introduce multiqueue support
  virtio-scsi: push vq lock/unlock into virtscsi_vq_done
  virtio-scsi: pass struct virtio_scsi to virtqueue completion function
  ...

Documentation/virtual/00-INDEX

@@ -6,6 +6,3 @@ kvm/
 	- Kernel Virtual Machine.  See also http://linux-kvm.org
 uml/
 	- User Mode Linux, builds/runs Linux kernel as a userspace program.
-virtio.txt
-	- Text version of draft virtio spec.
-          See http://ozlabs.org/~rusty/virtio-spec

MAINTAINERS

@@ -8743,6 +8743,7 @@ F:	drivers/virtio/
 F:	drivers/net/virtio_net.c
 F:	drivers/block/virtio_blk.c
 F:	include/linux/virtio_*.h
+F:	include/uapi/linux/virtio_*.h
 
 VIRTIO HOST (VHOST)
 M:	"Michael S. Tsirkin" <mst@redhat.com>

arch/x86/include/asm/lguest.h

@@ -11,18 +11,11 @@
 
 #define GUEST_PL 1
 
-/* Every guest maps the core switcher code. */
-#define SHARED_SWITCHER_PAGES \
-	DIV_ROUND_UP(end_switcher_text - start_switcher_text, PAGE_SIZE)
-/* Pages for switcher itself, then two pages per cpu */
-#define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * nr_cpu_ids)
-
-/* We map at -4M (-2M for PAE) for ease of mapping (one PTE page). */
-#ifdef CONFIG_X86_PAE
-#define SWITCHER_ADDR 0xFFE00000
-#else
-#define SWITCHER_ADDR 0xFFC00000
-#endif
+/* Page for Switcher text itself, then two pages per cpu */
+#define TOTAL_SWITCHER_PAGES (1 + 2 * nr_cpu_ids)
+
+/* Where we map the Switcher, in both Host and Guest. */
+extern unsigned long switcher_addr;
 
 /* Found in switcher.S */
 extern unsigned long default_idt_entries[];

block/blk-integrity.c

@@ -110,7 +110,7 @@ int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio,
 			if (!sg)
 				sg = sglist;
 			else {
-				sg->page_link &= ~0x02;
+				sg_unmark_end(sg);
 				sg = sg_next(sg);
 			}
 

block/blk-merge.c

@@ -143,7 +143,7 @@ __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
 			 * termination bit to avoid doing a full
 			 * sg_init_table() in drivers for each command.
 			 */
-			(*sg)->page_link &= ~0x02;
+			sg_unmark_end(*sg);
 			*sg = sg_next(*sg);
 		}
 

drivers/Makefile

@@ -124,7 +124,7 @@ obj-$(CONFIG_PPC_PS3)		+= ps3/
 obj-$(CONFIG_OF)		+= of/
 obj-$(CONFIG_SSB)		+= ssb/
 obj-$(CONFIG_BCMA)		+= bcma/
-obj-$(CONFIG_VHOST_NET)		+= vhost/
+obj-$(CONFIG_VHOST_RING)	+= vhost/
 obj-$(CONFIG_VLYNQ)		+= vlynq/
 obj-$(CONFIG_STAGING)		+= staging/
 obj-y				+= platform/

drivers/block/virtio_blk.c

@@ -100,96 +100,103 @@ static inline struct virtblk_req *virtblk_alloc_req(struct virtio_blk *vblk,
 	return vbr;
 }
 
-static void virtblk_add_buf_wait(struct virtio_blk *vblk,
-				 struct virtblk_req *vbr,
-				 unsigned long out,
-				 unsigned long in)
+static int __virtblk_add_req(struct virtqueue *vq,
+			     struct virtblk_req *vbr,
+			     struct scatterlist *data_sg,
+			     bool have_data)
 {
-	DEFINE_WAIT(wait);
+	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
+	unsigned int num_out = 0, num_in = 0;
+	int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT;
 
-	for (;;) {
-		prepare_to_wait_exclusive(&vblk->queue_wait, &wait,
-					  TASK_UNINTERRUPTIBLE);
+	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
+	sgs[num_out++] = &hdr;
 
-		spin_lock_irq(vblk->disk->queue->queue_lock);
-		if (virtqueue_add_buf(vblk->vq, vbr->sg, out, in, vbr,
-				      GFP_ATOMIC) < 0) {
-			spin_unlock_irq(vblk->disk->queue->queue_lock);
-			io_schedule();
-		} else {
-			virtqueue_kick(vblk->vq);
-			spin_unlock_irq(vblk->disk->queue->queue_lock);
-			break;
-		}
+	/*
+	 * If this is a packet command we need a couple of additional headers.
+	 * Behind the normal outhdr we put a segment with the scsi command
+	 * block, and before the normal inhdr we put the sense data and the
+	 * inhdr with additional status information.
+	 */
+	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
+		sgs[num_out++] = &cmd;
+	}
 
+	if (have_data) {
+		if (vbr->out_hdr.type & VIRTIO_BLK_T_OUT)
+			sgs[num_out++] = data_sg;
+		else
+			sgs[num_out + num_in++] = data_sg;
 	}
 
-	finish_wait(&vblk->queue_wait, &wait);
+	if (type == VIRTIO_BLK_T_SCSI_CMD) {
+		sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
+		sgs[num_out + num_in++] = &sense;
+		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
+		sgs[num_out + num_in++] = &inhdr;
+	}
+
+	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
+	sgs[num_out + num_in++] = &status;
+
+	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
-static inline void virtblk_add_req(struct virtblk_req *vbr,
-				   unsigned int out, unsigned int in)
+static void virtblk_add_req(struct virtblk_req *vbr, bool have_data)
 {
 	struct virtio_blk *vblk = vbr->vblk;
+	DEFINE_WAIT(wait);
+	int ret;
 
 	spin_lock_irq(vblk->disk->queue->queue_lock);
-	if (unlikely(virtqueue_add_buf(vblk->vq, vbr->sg, out, in, vbr,
-					GFP_ATOMIC) < 0)) {
+	while (unlikely((ret = __virtblk_add_req(vblk->vq, vbr, vbr->sg,
+						 have_data)) < 0)) {
+		prepare_to_wait_exclusive(&vblk->queue_wait, &wait,
+					  TASK_UNINTERRUPTIBLE);
+
 		spin_unlock_irq(vblk->disk->queue->queue_lock);
-		virtblk_add_buf_wait(vblk, vbr, out, in);
-		return;
+		io_schedule();
+		spin_lock_irq(vblk->disk->queue->queue_lock);
+
+		finish_wait(&vblk->queue_wait, &wait);
 	}
+
 	virtqueue_kick(vblk->vq);
 	spin_unlock_irq(vblk->disk->queue->queue_lock);
 }
 
-static int virtblk_bio_send_flush(struct virtblk_req *vbr)
+static void virtblk_bio_send_flush(struct virtblk_req *vbr)
 {
-	unsigned int out = 0, in = 0;
-
 	vbr->flags |= VBLK_IS_FLUSH;
 	vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
 	vbr->out_hdr.sector = 0;
 	vbr->out_hdr.ioprio = 0;
-	sg_set_buf(&vbr->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
-	sg_set_buf(&vbr->sg[out + in++], &vbr->status, sizeof(vbr->status));
-
-	virtblk_add_req(vbr, out, in);
 
-	return 0;
+	virtblk_add_req(vbr, false);
 }
 
-static int virtblk_bio_send_data(struct virtblk_req *vbr)
+static void virtblk_bio_send_data(struct virtblk_req *vbr)
 {
 	struct virtio_blk *vblk = vbr->vblk;
-	unsigned int num, out = 0, in = 0;
 	struct bio *bio = vbr->bio;
+	bool have_data;
 
 	vbr->flags &= ~VBLK_IS_FLUSH;
 	vbr->out_hdr.type = 0;
 	vbr->out_hdr.sector = bio->bi_sector;
 	vbr->out_hdr.ioprio = bio_prio(bio);
 
-	sg_set_buf(&vbr->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
-
-	num = blk_bio_map_sg(vblk->disk->queue, bio, vbr->sg + out);
-
-	sg_set_buf(&vbr->sg[num + out + in++], &vbr->status,
-		   sizeof(vbr->status));
-
-	if (num) {
-		if (bio->bi_rw & REQ_WRITE) {
+	if (blk_bio_map_sg(vblk->disk->queue, bio, vbr->sg)) {
+		have_data = true;
+		if (bio->bi_rw & REQ_WRITE)
 			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
-			out += num;
-		} else {
+		else
 			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
-			in += num;
-		}
-	}
+	} else
+		have_data = false;
 
-	virtblk_add_req(vbr, out, in);
-
-	return 0;
+	virtblk_add_req(vbr, have_data);
 }
 
 static void virtblk_bio_send_data_work(struct work_struct *work)
@@ -298,7 +305,7 @@ static void virtblk_done(struct virtqueue *vq)
 static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		   struct request *req)
 {
-	unsigned long num, out = 0, in = 0;
+	unsigned int num;
 	struct virtblk_req *vbr;
 
 	vbr = virtblk_alloc_req(vblk, GFP_ATOMIC);
@@ -335,40 +342,15 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		}
 	}
 
-	sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
-
-	/*
-	 * If this is a packet command we need a couple of additional headers.
-	 * Behind the normal outhdr we put a segment with the scsi command
-	 * block, and before the normal inhdr we put the sense data and the
-	 * inhdr with additional status information before the normal inhdr.
-	 */
-	if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC)
-		sg_set_buf(&vblk->sg[out++], vbr->req->cmd, vbr->req->cmd_len);
-
-	num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
-
-	if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
-		sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
-			   sizeof(vbr->in_hdr));
-	}
-
-	sg_set_buf(&vblk->sg[num + out + in++], &vbr->status,
-		   sizeof(vbr->status));
-
+	num = blk_rq_map_sg(q, vbr->req, vblk->sg);
 	if (num) {
-		if (rq_data_dir(vbr->req) == WRITE) {
+		if (rq_data_dir(vbr->req) == WRITE)
 			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
-			out += num;
-		} else {
+		else
 			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
-			in += num;
-		}
 	}
 
-	if (virtqueue_add_buf(vblk->vq, vblk->sg, out, in, vbr,
-			      GFP_ATOMIC) < 0) {
+	if (__virtblk_add_req(vblk->vq, vbr, vblk->sg, num) < 0) {
 		mempool_free(vbr, vblk->pool);
 		return false;
 	}
@@ -539,6 +521,7 @@ static void virtblk_config_changed_work(struct work_struct *work)
 	struct virtio_device *vdev = vblk->vdev;
 	struct request_queue *q = vblk->disk->queue;
 	char cap_str_2[10], cap_str_10[10];
+	char *envp[] = { "RESIZE=1", NULL };
 	u64 capacity, size;
 
 	mutex_lock(&vblk->config_lock);
@@ -568,6 +551,7 @@ static void virtblk_config_changed_work(struct work_struct *work)
 
 	set_capacity(vblk->disk, capacity);
 	revalidate_disk(vblk->disk);
+	kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp);
 done:
 	mutex_unlock(&vblk->config_lock);
 }

drivers/char/hw_random/virtio-rng.c

@@ -47,7 +47,7 @@ static void register_buffer(u8 *buf, size_t size)
 	sg_init_one(&sg, buf, size);
 
 	/* There should always be room for one buffer. */
-	if (virtqueue_add_buf(vq, &sg, 0, 1, buf, GFP_KERNEL) < 0)
+	if (virtqueue_add_inbuf(vq, &sg, 1, buf, GFP_KERNEL) < 0)
 		BUG();
 
 	virtqueue_kick(vq);

drivers/char/virtio_console.c

@@ -78,8 +78,8 @@ struct ports_driver_data {
 };
 static struct ports_driver_data pdrvdata;
 
-DEFINE_SPINLOCK(pdrvdata_lock);
-DECLARE_COMPLETION(early_console_added);
+static DEFINE_SPINLOCK(pdrvdata_lock);
+static DECLARE_COMPLETION(early_console_added);
 
 /* This struct holds information that's relevant only for console ports */
 struct console {
@@ -503,7 +503,7 @@ static int add_inbuf(struct virtqueue *vq, struct port_buffer *buf)
 
 	sg_init_one(sg, buf->buf, buf->size);
 
-	ret = virtqueue_add_buf(vq, sg, 0, 1, buf, GFP_ATOMIC);
+	ret = virtqueue_add_inbuf(vq, sg, 1, buf, GFP_ATOMIC);
 	virtqueue_kick(vq);
 	if (!ret)
 		ret = vq->num_free;
@@ -572,7 +572,7 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
 	sg_init_one(sg, &cpkt, sizeof(cpkt));
 
 	spin_lock(&portdev->c_ovq_lock);
-	if (virtqueue_add_buf(vq, sg, 1, 0, &cpkt, GFP_ATOMIC) == 0) {
+	if (virtqueue_add_outbuf(vq, sg, 1, &cpkt, GFP_ATOMIC) == 0) {
 		virtqueue_kick(vq);
 		while (!virtqueue_get_buf(vq, &len))
 			cpu_relax();
@@ -622,7 +622,7 @@ static ssize_t __send_to_port(struct port *port, struct scatterlist *sg,
 
 	reclaim_consumed_buffers(port);
 
-	err = virtqueue_add_buf(out_vq, sg, nents, 0, data, GFP_ATOMIC);
+	err = virtqueue_add_outbuf(out_vq, sg, nents, data, GFP_ATOMIC);
 
 	/* Tell Host to go! */
 	virtqueue_kick(out_vq);
@@ -1040,7 +1040,7 @@ static int port_fops_open(struct inode *inode, struct file *filp)
 	spin_lock_irq(&port->inbuf_lock);
 	if (port->guest_connected) {
 		spin_unlock_irq(&port->inbuf_lock);
-		ret = -EMFILE;
+		ret = -EBUSY;
 		goto out;
 	}
 
@@ -1202,7 +1202,7 @@ int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int))
 	return hvc_instantiate(0, 0, &hv_ops);
 }
 
-int init_port_console(struct port *port)
+static int init_port_console(struct port *port)
 {
 	int ret;
 

drivers/lguest/Kconfig

@@ -5,10 +5,9 @@ config LGUEST
 	---help---
 	  This is a very simple module which allows you to run
 	  multiple instances of the same Linux kernel, using the
-	  "lguest" command found in the Documentation/virtual/lguest
-	  directory.
+	  "lguest" command found in the tools/lguest directory.
 
 	  Note that "lguest" is pronounced to rhyme with "fell quest",
-	  not "rustyvisor". See Documentation/virtual/lguest/lguest.txt.
+	  not "rustyvisor". See tools/lguest/lguest.txt.
 
 	  If unsure, say N.  If curious, say M.  If masochistic, say Y.

drivers/lguest/core.c

@@ -20,9 +20,9 @@
 #include <asm/asm-offsets.h>
 #include "lg.h"
 
-
+unsigned long switcher_addr;
+struct page **lg_switcher_pages;
 static struct vm_struct *switcher_vma;
-static struct page **switcher_page;
 
 /* This One Big lock protects all inter-guest data structures. */
 DEFINE_MUTEX(lguest_lock);
@@ -52,13 +52,21 @@ static __init int map_switcher(void)
 	 * easy.
 	 */
 
+	/* We assume Switcher text fits into a single page. */
+	if (end_switcher_text - start_switcher_text > PAGE_SIZE) {
+		printk(KERN_ERR "lguest: switcher text too large (%zu)\n",
+		       end_switcher_text - start_switcher_text);
+		return -EINVAL;
+	}
+
 	/*
 	 * We allocate an array of struct page pointers.  map_vm_area() wants
 	 * this, rather than just an array of pages.
 	 */
-	switcher_page = kmalloc(sizeof(switcher_page[0])*TOTAL_SWITCHER_PAGES,
-				GFP_KERNEL);
-	if (!switcher_page) {
+	lg_switcher_pages = kmalloc(sizeof(lg_switcher_pages[0])
+				    * TOTAL_SWITCHER_PAGES,
+				    GFP_KERNEL);
+	if (!lg_switcher_pages) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -68,32 +76,29 @@ static __init int map_switcher(void)
 	 * so we make sure they're zeroed.
 	 */
 	for (i = 0; i < TOTAL_SWITCHER_PAGES; i++) {
-		switcher_page[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
-		if (!switcher_page[i]) {
+		lg_switcher_pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
+		if (!lg_switcher_pages[i]) {
 			err = -ENOMEM;
 			goto free_some_pages;
 		}
 	}
 
 	/*
-	 * First we check that the Switcher won't overlap the fixmap area at
-	 * the top of memory.  It's currently nowhere near, but it could have
-	 * very strange effects if it ever happened.
+	 * We place the Switcher underneath the fixmap area, which is the
+	 * highest virtual address we can get.  This is important, since we
+	 * tell the Guest it can't access this memory, so we want its ceiling
+	 * as high as possible.
 	 */
-	if (SWITCHER_ADDR + (TOTAL_SWITCHER_PAGES+1)*PAGE_SIZE > FIXADDR_START){
-		err = -ENOMEM;
-		printk("lguest: mapping switcher would thwack fixmap\n");
-		goto free_pages;
-	}
+	switcher_addr = FIXADDR_START - (TOTAL_SWITCHER_PAGES+1)*PAGE_SIZE;
 
 	/*
-	 * Now we reserve the "virtual memory area" we want: 0xFFC00000
-	 * (SWITCHER_ADDR).  We might not get it in theory, but in practice
-	 * it's worked so far.  The end address needs +1 because __get_vm_area
-	 * allocates an extra guard page, so we need space for that.
+	 * Now we reserve the "virtual memory area" we want.  We might
+	 * not get it in theory, but in practice it's worked so far.
+	 * The end address needs +1 because __get_vm_area allocates an
+	 * extra guard page, so we need space for that.
 	 */
 	switcher_vma = __get_vm_area(TOTAL_SWITCHER_PAGES * PAGE_SIZE,
-				     VM_ALLOC, SWITCHER_ADDR, SWITCHER_ADDR
+				     VM_ALLOC, switcher_addr, switcher_addr
 				     + (TOTAL_SWITCHER_PAGES+1) * PAGE_SIZE);
 	if (!switcher_vma) {
 		err = -ENOMEM;
@@ -103,12 +108,12 @@ static __init int map_switcher(void)
 
 	/*
 	 * This code actually sets up the pages we've allocated to appear at
-	 * SWITCHER_ADDR.  map_vm_area() takes the vma we allocated above, the
+	 * switcher_addr.  map_vm_area() takes the vma we allocated above, the
 	 * kind of pages we're mapping (kernel pages), and a pointer to our
 	 * array of struct pages.  It increments that pointer, but we don't
 	 * care.
 	 */
-	pagep = switcher_page;
+	pagep = lg_switcher_pages;
 	err = map_vm_area(switcher_vma, PAGE_KERNEL_EXEC, &pagep);
 	if (err) {
 		printk("lguest: map_vm_area failed: %i\n", err);
@@ -133,8 +138,8 @@ static __init int map_switcher(void)
 	i = TOTAL_SWITCHER_PAGES;
 free_some_pages:
 	for (--i; i >= 0; i--)
-		__free_pages(switcher_page[i], 0);
-	kfree(switcher_page);
+		__free_pages(lg_switcher_pages[i], 0);
+	kfree(lg_switcher_pages);
 out:
 	return err;
 }
@@ -149,8 +154,8 @@ static void unmap_switcher(void)
 	vunmap(switcher_vma->addr);
 	/* Now we just need to free the pages we copied the switcher into */
 	for (i = 0; i < TOTAL_SWITCHER_PAGES; i++)
-		__free_pages(switcher_page[i], 0);
-	kfree(switcher_page);
+		__free_pages(lg_switcher_pages[i], 0);
+	kfree(lg_switcher_pages);
 }
 
 /*H:032
@@ -323,15 +328,10 @@ static int __init init(void)
 	if (err)
 		goto out;
 
-	/* Now we set up the pagetable implementation for the Guests. */
-	err = init_pagetables(switcher_page, SHARED_SWITCHER_PAGES);
-	if (err)
-		goto unmap;
-
 	/* We might need to reserve an interrupt vector. */
 	err = init_interrupts();
 	if (err)
-		goto free_pgtables;
+		goto unmap;
 
 	/* /dev/lguest needs to be registered. */
 	err = lguest_device_init();
@@ -346,8 +346,6 @@ static int __init init(void)
 
 free_interrupts:
 	free_interrupts();
-free_pgtables:
-	free_pagetables();
 unmap:
 	unmap_switcher();
 out:
@@ -359,7 +357,6 @@ static void __exit fini(void)
 {
 	lguest_device_remove();
 	free_interrupts();
-	free_pagetables();
 	unmap_switcher();
 
 	lguest_arch_host_fini();

drivers/lguest/lg.h

@@ -14,11 +14,10 @@
 
 #include <asm/lguest.h>
 
-void free_pagetables(void);
-int init_pagetables(struct page **switcher_page, unsigned int pages);
-
 struct pgdir {
 	unsigned long gpgdir;
+	bool switcher_mapped;
+	int last_host_cpu;
 	pgd_t *pgdir;
 };
 
@@ -124,6 +123,7 @@ bool lguest_address_ok(const struct lguest *lg,
 		       unsigned long addr, unsigned long len);
 void __lgread(struct lg_cpu *, void *, unsigned long, unsigned);
 void __lgwrite(struct lg_cpu *, unsigned long, const void *, unsigned);
+extern struct page **lg_switcher_pages;
 
 /*H:035
  * Using memory-copy operations like that is usually inconvient, so we

drivers/lguest/lguest_user.c

@@ -250,13 +250,13 @@ static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o)
  */
 static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip)
 {
-	/* We have a limited number the number of CPUs in the lguest struct. */
+	/* We have a limited number of CPUs in the lguest struct. */
 	if (id >= ARRAY_SIZE(cpu->lg->cpus))
 		return -EINVAL;
 
 	/* Set up this CPU's id, and pointer back to the lguest struct. */
 	cpu->id = id;
-	cpu->lg = container_of((cpu - id), struct lguest, cpus[0]);
+	cpu->lg = container_of(cpu, struct lguest, cpus[id]);
 	cpu->lg->nr_cpus++;
 
 	/* Each CPU has a timer it can set. */
@@ -270,7 +270,7 @@ static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip)
 	if (!cpu->regs_page)
 		return -ENOMEM;
 
-	/* We actually put the registers at the bottom of the page. */
+	/* We actually put the registers at the end of the page. */
 	cpu->regs = (void *)cpu->regs_page + PAGE_SIZE - sizeof(*cpu->regs);
 
 	/*

drivers/lguest/x86/core.c

@@ -59,14 +59,13 @@ static struct {
 /* Offset from where switcher.S was compiled to where we've copied it */
 static unsigned long switcher_offset(void)
 {
-	return SWITCHER_ADDR - (unsigned long)start_switcher_text;
+	return switcher_addr - (unsigned long)start_switcher_text;
 }
 
-/* This cpu's struct lguest_pages. */
+/* This cpu's struct lguest_pages (after the Switcher text page) */
 static struct lguest_pages *lguest_pages(unsigned int cpu)
 {
-	return &(((struct lguest_pages *)
-		  (SWITCHER_ADDR + SHARED_SWITCHER_PAGES*PAGE_SIZE))[cpu]);
+	return &(((struct lguest_pages *)(switcher_addr + PAGE_SIZE))[cpu]);
 }
 
 static DEFINE_PER_CPU(struct lg_cpu *, lg_last_cpu);

drivers/net/caif/Kconfig

@@ -40,3 +40,17 @@ config CAIF_HSI
        The caif low level driver for CAIF over HSI.
        Be aware that if you enable this then you also need to
        enable a low-level HSI driver.
+
+config CAIF_VIRTIO
+	tristate "CAIF virtio transport driver"
+	depends on CAIF
+	select VHOST_RING
+	select VIRTIO
+	select GENERIC_ALLOCATOR
+	default n
+	---help---
+	The caif driver for CAIF over Virtio.
+
+if CAIF_VIRTIO
+source "drivers/vhost/Kconfig"
+endif

drivers/net/caif/Makefile

@@ -9,3 +9,6 @@ obj-$(CONFIG_CAIF_SPI_SLAVE) += cfspi_slave.o
 
 # HSI interface
 obj-$(CONFIG_CAIF_HSI) += caif_hsi.o
+
+# Virtio interface
+obj-$(CONFIG_CAIF_VIRTIO) += caif_virtio.o

drivers/net/virtio_net.c

@@ -39,7 +39,6 @@ module_param(gso, bool, 0444);
 #define MAX_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
 #define GOOD_COPY_LEN	128
 
-#define VIRTNET_SEND_COMMAND_SG_MAX    2
 #define VIRTNET_DRIVER_VERSION "1.0.0"
 
 struct virtnet_stats {
@@ -444,7 +443,7 @@ static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
 
 	skb_to_sgvec(skb, rq->sg + 1, 0, skb->len);
 
-	err = virtqueue_add_buf(rq->vq, rq->sg, 0, 2, skb, gfp);
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, 2, skb, gfp);
 	if (err < 0)
 		dev_kfree_skb(skb);
 
@@ -489,8 +488,8 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
 
 	/* chain first in list head */
 	first->private = (unsigned long)list;
-	err = virtqueue_add_buf(rq->vq, rq->sg, 0, MAX_SKB_FRAGS + 2,
-				first, gfp);
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, MAX_SKB_FRAGS + 2,
+				  first, gfp);
 	if (err < 0)
 		give_pages(rq, first);
 
@@ -508,7 +507,7 @@ static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
 
 	sg_init_one(rq->sg, page_address(page), PAGE_SIZE);
 
-	err = virtqueue_add_buf(rq->vq, rq->sg, 0, 1, page, gfp);
+	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, page, gfp);
 	if (err < 0)
 		give_pages(rq, page);
 
@@ -582,7 +581,7 @@ static void refill_work(struct work_struct *work)
 	bool still_empty;
 	int i;
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		struct receive_queue *rq = &vi->rq[i];
 
 		napi_disable(&rq->napi);
@@ -637,7 +636,7 @@ static int virtnet_open(struct net_device *dev)
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		/* Make sure we have some buffers: if oom use wq. */
 		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
 			schedule_delayed_work(&vi->refill, 0);
@@ -711,8 +710,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 		sg_set_buf(sq->sg, &hdr->hdr, sizeof hdr->hdr);
 
 	num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1;
-	return virtqueue_add_buf(sq->vq, sq->sg, num_sg,
-				 0, skb, GFP_ATOMIC);
+	return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC);
 }
 
 static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -767,32 +765,35 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
  * never fail unless improperly formated.
  */
 static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
-				 struct scatterlist *data, int out, int in)
+				 struct scatterlist *out,
+				 struct scatterlist *in)
 {
-	struct scatterlist *s, sg[VIRTNET_SEND_COMMAND_SG_MAX + 2];
+	struct scatterlist *sgs[4], hdr, stat;
 	struct virtio_net_ctrl_hdr ctrl;
 	virtio_net_ctrl_ack status = ~0;
-	unsigned int tmp;
-	int i;
+	unsigned out_num = 0, in_num = 0, tmp;
 
 	/* Caller should know better */
-	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ||
-		(out + in > VIRTNET_SEND_COMMAND_SG_MAX));
-
-	out++; /* Add header */
-	in++; /* Add return status */
+	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
 
 	ctrl.class = class;
 	ctrl.cmd = cmd;
+	/* Add header */
+	sg_init_one(&hdr, &ctrl, sizeof(ctrl));
+	sgs[out_num++] = &hdr;
 
-	sg_init_table(sg, out + in);
+	if (out)
+		sgs[out_num++] = out;
+	if (in)
+		sgs[out_num + in_num++] = in;
 
-	sg_set_buf(&sg[0], &ctrl, sizeof(ctrl));
-	for_each_sg(data, s, out + in - 2, i)
-		sg_set_buf(&sg[i + 1], sg_virt(s), s->length);
-	sg_set_buf(&sg[out + in - 1], &status, sizeof(status));
+	/* Add return status. */
+	sg_init_one(&stat, &status, sizeof(status));
+	sgs[out_num + in_num++] = &stat;
 
-	BUG_ON(virtqueue_add_buf(vi->cvq, sg, out, in, vi, GFP_ATOMIC) < 0);
+	BUG_ON(out_num + in_num > ARRAY_SIZE(sgs));
+	BUG_ON(virtqueue_add_sgs(vi->cvq, sgs, out_num, in_num, vi, GFP_ATOMIC)
+	       < 0);
 
 	virtqueue_kick(vi->cvq);
 
@@ -821,7 +822,7 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p)
 		sg_init_one(&sg, addr->sa_data, dev->addr_len);
 		if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
 					  VIRTIO_NET_CTRL_MAC_ADDR_SET,
-					  &sg, 1, 0)) {
+					  &sg, NULL)) {
 			dev_warn(&vdev->dev,
 				 "Failed to set mac address by vq command.\n");
 			return -EINVAL;
@@ -889,8 +890,7 @@ static void virtnet_ack_link_announce(struct virtnet_info *vi)
 {
 	rtnl_lock();
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE,
-				  VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL,
-				  0, 0))
+				  VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL, NULL))
 		dev_warn(&vi->dev->dev, "Failed to ack link announce.\n");
 	rtnl_unlock();
 }
@@ -900,6 +900,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	struct scatterlist sg;
 	struct virtio_net_ctrl_mq s;
 	struct net_device *dev = vi->dev;
+	int i;
 
 	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
 		return 0;
@@ -908,12 +909,16 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	sg_init_one(&sg, &s, sizeof(s));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
-				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg, 1, 0)){
+				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg, NULL)) {
 		dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
 			 queue_pairs);
 		return -EINVAL;
-	} else
+	} else {
+		for (i = vi->curr_queue_pairs; i < queue_pairs; i++)
+			if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+				schedule_delayed_work(&vi->refill, 0);
 		vi->curr_queue_pairs = queue_pairs;
+	}
 
 	return 0;
 }
@@ -955,7 +960,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_PROMISC,
-				  sg, 1, 0))
+				  sg, NULL))
 		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
 			 promisc ? "en" : "dis");
 
@@ -963,7 +968,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_ALLMULTI,
-				  sg, 1, 0))
+				  sg, NULL))
 		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
 			 allmulti ? "en" : "dis");
 
@@ -1000,7 +1005,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC,
 				  VIRTIO_NET_CTRL_MAC_TABLE_SET,
-				  sg, 2, 0))
+				  sg, NULL))
 		dev_warn(&dev->dev, "Failed to set MAC fitler table.\n");
 
 	kfree(buf);
@@ -1015,7 +1020,7 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 	sg_init_one(&sg, &vid, sizeof(vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
-				  VIRTIO_NET_CTRL_VLAN_ADD, &sg, 1, 0))
+				  VIRTIO_NET_CTRL_VLAN_ADD, &sg, NULL))
 		dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid);
 	return 0;
 }
@@ -1029,7 +1034,7 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 	sg_init_one(&sg, &vid, sizeof(vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
-				  VIRTIO_NET_CTRL_VLAN_DEL, &sg, 1, 0))
+				  VIRTIO_NET_CTRL_VLAN_DEL, &sg, NULL))
 		dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid);
 	return 0;
 }
@@ -1570,7 +1575,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	}
 
 	/* Last of all, set up some receive buffers. */
-	for (i = 0; i < vi->max_queue_pairs; i++) {
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		try_fill_recv(&vi->rq[i], GFP_KERNEL);
 
 		/* If we didn't even get one input buffer, we're useless. */
@@ -1694,7 +1699,7 @@ static int virtnet_restore(struct virtio_device *vdev)
 
 	netif_device_attach(vi->dev);
 
-	for (i = 0; i < vi->max_queue_pairs; i++)
+	for (i = 0; i < vi->curr_queue_pairs; i++)
 		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
 			schedule_delayed_work(&vi->refill, 0);
 

drivers/rpmsg/virtio_rpmsg_bus.c

@@ -757,14 +757,14 @@ int rpmsg_send_offchannel_raw(struct rpmsg_channel *rpdev, u32 src, u32 dst,
 	mutex_lock(&vrp->tx_lock);
 
 	/* add message to the remote processor's virtqueue */
-	err = virtqueue_add_buf(vrp->svq, &sg, 1, 0, msg, GFP_KERNEL);
+	err = virtqueue_add_outbuf(vrp->svq, &sg, 1, msg, GFP_KERNEL);
 	if (err) {
 		/*
 		 * need to reclaim the buffer here, otherwise it's lost
 		 * (memory won't leak, but rpmsg won't use it again for TX).
 		 * this will wait for a buffer management overhaul.
 		 */
-		dev_err(dev, "virtqueue_add_buf failed: %d\n", err);
+		dev_err(dev, "virtqueue_add_outbuf failed: %d\n", err);
 		goto out;
 	}
 
@@ -839,7 +839,7 @@ static void rpmsg_recv_done(struct virtqueue *rvq)
 	sg_init_one(&sg, msg, RPMSG_BUF_SIZE);
 
 	/* add the buffer back to the remote processor's virtqueue */
-	err = virtqueue_add_buf(vrp->rvq, &sg, 0, 1, msg, GFP_KERNEL);
+	err = virtqueue_add_inbuf(vrp->rvq, &sg, 1, msg, GFP_KERNEL);
 	if (err < 0) {
 		dev_err(dev, "failed to add a virtqueue buffer: %d\n", err);
 		return;
@@ -972,7 +972,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
 
 		sg_init_one(&sg, cpu_addr, RPMSG_BUF_SIZE);
 
-		err = virtqueue_add_buf(vrp->rvq, &sg, 0, 1, cpu_addr,
+		err = virtqueue_add_inbuf(vrp->rvq, &sg, 1, cpu_addr,
 								GFP_KERNEL);
 		WARN_ON(err); /* sanity check; this can't really happen */
 	}

drivers/vhost/Kconfig

 config VHOST_NET
 	tristate "Host kernel accelerator for virtio net"
 	depends on NET && EVENTFD && (TUN || !TUN) && (MACVTAP || !MACVTAP)
+	select VHOST_RING
 	---help---
 	  This kernel module can be loaded in host kernel to accelerate
 	  guest networking with virtio_net. Not to be confused with virtio_net
@@ -12,7 +13,14 @@ config VHOST_NET
 config VHOST_SCSI
 	tristate "VHOST_SCSI TCM fabric driver"
 	depends on TARGET_CORE && EVENTFD && m
+	select VHOST_RING
 	default n
 	---help---
 	Say M here to enable the vhost_scsi TCM fabric module
 	for use with virtio-scsi guests
+
+config VHOST_RING
+	tristate
+	---help---
+	  This option is selected by any driver which needs to access
+	  the host side of a virtio ring.

drivers/vhost/Makefile

@@ -3,3 +3,5 @@ vhost_net-y := vhost.o net.o
 
 obj-$(CONFIG_VHOST_SCSI) += vhost_scsi.o
 vhost_scsi-y := scsi.o
+
+obj-$(CONFIG_VHOST_RING) += vringh.o

drivers/vhost/test.c

@@ -282,7 +282,9 @@ static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
 		return vhost_test_reset_owner(n);
 	default:
 		mutex_lock(&n->dev.mutex);
-		r = vhost_dev_ioctl(&n->dev, ioctl, arg);
+		r = vhost_dev_ioctl(&n->dev, ioctl, argp);
+                if (r == -ENOIOCTLCMD)
+                        r = vhost_vring_ioctl(&n->dev, ioctl, argp);
 		vhost_test_flush(n);
 		mutex_unlock(&n->dev.mutex);
 		return r;

drivers/virtio/virtio_balloon.c

@@ -108,7 +108,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 	sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);
 
 	/* We should always be able to add one buffer to an empty queue. */
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
+	if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL) < 0)
 		BUG();
 	virtqueue_kick(vq);
 
@@ -256,7 +256,7 @@ static void stats_handle_request(struct virtio_balloon *vb)
 	if (!virtqueue_get_buf(vq, &len))
 		return;
 	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
+	if (virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL) < 0)
 		BUG();
 	virtqueue_kick(vq);
 }
@@ -341,7 +341,7 @@ static int init_vqs(struct virtio_balloon *vb)
 		 * use it to signal us later.
 		 */
 		sg_init_one(&sg, vb->stats, sizeof vb->stats);
-		if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb, GFP_KERNEL)
+		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
 		    < 0)
 			BUG();
 		virtqueue_kick(vb->stats_vq);

include/linux/scatterlist.h

@@ -171,6 +171,22 @@ static inline void sg_mark_end(struct scatterlist *sg)
 	sg->page_link &= ~0x01;
 }
 
+/**
+ * sg_unmark_end - Undo setting the end of the scatterlist
+ * @sg:		 SG entryScatterlist
+ *
+ * Description:
+ *   Removes the termination marker from the given entry of the scatterlist.
+ *
+ **/
+static inline void sg_unmark_end(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+	sg->page_link &= ~0x02;
+}
+
 /**
  * sg_phys - Return physical address of an sg entry
  * @sg:	     SG entry

include/linux/virtio.h

@@ -8,6 +8,7 @@
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
 #include <linux/gfp.h>
+#include <linux/vringh.h>
 
 /**
  * virtqueue - a queue to register buffers for sending or receiving.
@@ -40,6 +41,23 @@ int virtqueue_add_buf(struct virtqueue *vq,
 		      void *data,
 		      gfp_t gfp);
 
+int virtqueue_add_outbuf(struct virtqueue *vq,
+			 struct scatterlist sg[], unsigned int num,
+			 void *data,
+			 gfp_t gfp);
+
+int virtqueue_add_inbuf(struct virtqueue *vq,
+			struct scatterlist sg[], unsigned int num,
+			void *data,
+			gfp_t gfp);
+
+int virtqueue_add_sgs(struct virtqueue *vq,
+		      struct scatterlist *sgs[],
+		      unsigned int out_sgs,
+		      unsigned int in_sgs,
+		      void *data,
+		      gfp_t gfp);
+
 void virtqueue_kick(struct virtqueue *vq);
 
 bool virtqueue_kick_prepare(struct virtqueue *vq);
@@ -64,6 +82,7 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
  * @dev: underlying device.
  * @id: the device type identification (used to match it with a driver).
  * @config: the configuration ops for this device.
+ * @vringh_config: configuration ops for host vrings.
  * @vqs: the list of virtqueues for this device.
  * @features: the features supported by both driver and device.
  * @priv: private pointer for the driver's use.
@@ -73,6 +92,7 @@ struct virtio_device {
 	struct device dev;
 	struct virtio_device_id id;
 	const struct virtio_config_ops *config;
+	const struct vringh_config_ops *vringh_config;
 	struct list_head vqs;
 	/* Note that this is a Linux set_bit-style bitmap. */
 	unsigned long features[1];

include/linux/virtio_caif.h

+/*
+ * Copyright (C) ST-Ericsson AB 2012
+ * Author: Sjur Brændeland <sjur.brandeland@stericsson.com>
+ *
+ * This header is BSD licensed so
+ * anyone can use the definitions to implement compatible remote processors
+ */
+
+#ifndef VIRTIO_CAIF_H
+#define VIRTIO_CAIF_H
+
+#include <linux/types.h>
+struct virtio_caif_transf_config {
+	u16 headroom;
+	u16 tailroom;
+	u32 mtu;
+	u8 reserved[4];
+};
+
+struct virtio_caif_config {
+	struct virtio_caif_transf_config uplink, downlink;
+	u8 reserved[8];
+};
+#endif

include/linux/virtio_ring.h

@@ -4,6 +4,63 @@
 #include <linux/irqreturn.h>
 #include <uapi/linux/virtio_ring.h>
 
+/*
+ * Barriers in virtio are tricky.  Non-SMP virtio guests can't assume
+ * they're not on an SMP host system, so they need to assume real
+ * barriers.  Non-SMP virtio hosts could skip the barriers, but does
+ * anyone care?
+ *
+ * For virtio_pci on SMP, we don't need to order with respect to MMIO
+ * accesses through relaxed memory I/O windows, so smp_mb() et al are
+ * sufficient.
+ *
+ * For using virtio to talk to real devices (eg. other heterogeneous
+ * CPUs) we do need real barriers.  In theory, we could be using both
+ * kinds of virtio, so it's a runtime decision, and the branch is
+ * actually quite cheap.
+ */
+
+#ifdef CONFIG_SMP
+static inline void virtio_mb(bool weak_barriers)
+{
+	if (weak_barriers)
+		smp_mb();
+	else
+		mb();
+}
+
+static inline void virtio_rmb(bool weak_barriers)
+{
+	if (weak_barriers)
+		smp_rmb();
+	else
+		rmb();
+}
+
+static inline void virtio_wmb(bool weak_barriers)
+{
+	if (weak_barriers)
+		smp_wmb();
+	else
+		wmb();
+}
+#else
+static inline void virtio_mb(bool weak_barriers)
+{
+	mb();
+}
+
+static inline void virtio_rmb(bool weak_barriers)
+{
+	rmb();
+}
+
+static inline void virtio_wmb(bool weak_barriers)
+{
+	wmb();
+}
+#endif
+
 struct virtio_device;
 struct virtqueue;
 

include/uapi/linux/virtio_balloon.h

@@ -52,8 +52,8 @@ struct virtio_balloon_config
 #define VIRTIO_BALLOON_S_NR       6
 
 struct virtio_balloon_stat {
-	u16 tag;
-	u64 val;
+	__u16 tag;
+	__u64 val;
 } __attribute__((packed));
 
 #endif /* _LINUX_VIRTIO_BALLOON_H */

include/uapi/linux/virtio_ids.h

@@ -38,5 +38,6 @@
 #define VIRTIO_ID_SCSI		8 /* virtio scsi */
 #define VIRTIO_ID_9P		9 /* 9p virtio console */
 #define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */
+#define VIRTIO_ID_CAIF	       12 /* Virtio caif */
 
 #endif /* _LINUX_VIRTIO_IDS_H */

net/9p/trans_virtio.c

@@ -194,11 +194,14 @@ static int pack_sg_list(struct scatterlist *sg, int start,
 		if (s > count)
 			s = count;
 		BUG_ON(index > limit);
+		/* Make sure we don't terminate early. */
+		sg_unmark_end(&sg[index]);
 		sg_set_buf(&sg[index++], data, s);
 		count -= s;
 		data += s;
 	}
-
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
 	return index-start;
 }
 
@@ -236,12 +239,17 @@ pack_sg_list_p(struct scatterlist *sg, int start, int limit,
 		s = rest_of_page(data);
 		if (s > count)
 			s = count;
+		/* Make sure we don't terminate early. */
+		sg_unmark_end(&sg[index]);
 		sg_set_page(&sg[index++], pdata[i++], s, data_off);
 		data_off = 0;
 		data += s;
 		count -= s;
 		nr_pages--;
 	}
+
+	if (index-start)
+		sg_mark_end(&sg[index - 1]);
 	return index - start;
 }
 
@@ -256,9 +264,10 @@ static int
 p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 {
 	int err;
-	int in, out;
+	int in, out, out_sgs, in_sgs;
 	unsigned long flags;
 	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[2];
 
 	p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n");
 
@@ -266,14 +275,19 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 req_retry:
 	spin_lock_irqsave(&chan->lock, flags);
 
+	out_sgs = in_sgs = 0;
 	/* Handle out VirtIO ring buffers */
 	out = pack_sg_list(chan->sg, 0,
 			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+	if (out)
+		sgs[out_sgs++] = chan->sg;
 
 	in = pack_sg_list(chan->sg, out,
 			  VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
 
-	err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc,
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
 				GFP_ATOMIC);
 	if (err < 0) {
 		if (err == -ENOSPC) {
@@ -289,7 +303,7 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 		} else {
 			spin_unlock_irqrestore(&chan->lock, flags);
 			p9_debug(P9_DEBUG_TRANS,
-				 "virtio rpc add_buf returned failure\n");
+				 "virtio rpc add_sgs returned failure\n");
 			return -EIO;
 		}
 	}
@@ -351,11 +365,12 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 		     char *uidata, char *uodata, int inlen,
 		     int outlen, int in_hdr_len, int kern_buf)
 {
-	int in, out, err;
+	int in, out, err, out_sgs, in_sgs;
 	unsigned long flags;
 	int in_nr_pages = 0, out_nr_pages = 0;
 	struct page **in_pages = NULL, **out_pages = NULL;
 	struct virtio_chan *chan = client->trans;
+	struct scatterlist *sgs[4];
 
 	p9_debug(P9_DEBUG_TRANS, "virtio request\n");
 
@@ -396,13 +411,22 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	req->status = REQ_STATUS_SENT;
 req_retry_pinned:
 	spin_lock_irqsave(&chan->lock, flags);
+
+	out_sgs = in_sgs = 0;
+
 	/* out data */
 	out = pack_sg_list(chan->sg, 0,
 			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
 
-	if (out_pages)
+	if (out)
+		sgs[out_sgs++] = chan->sg;
+
+	if (out_pages) {
+		sgs[out_sgs++] = chan->sg + out;
 		out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
 				      out_pages, out_nr_pages, uodata, outlen);
+	}
+		
 	/*
 	 * Take care of in data
 	 * For example TREAD have 11.
@@ -412,11 +436,17 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	 */
 	in = pack_sg_list(chan->sg, out,
 			  VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
-	if (in_pages)
+	if (in)
+		sgs[out_sgs + in_sgs++] = chan->sg + out;
+
+	if (in_pages) {
+		sgs[out_sgs + in_sgs++] = chan->sg + out + in;
 		in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM,
 				     in_pages, in_nr_pages, uidata, inlen);
+	}
 
-	err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc,
+	BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
+	err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
 				GFP_ATOMIC);
 	if (err < 0) {
 		if (err == -ENOSPC) {
@@ -432,7 +462,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 		} else {
 			spin_unlock_irqrestore(&chan->lock, flags);
 			p9_debug(P9_DEBUG_TRANS,
-				 "virtio rpc add_buf returned failure\n");
+				 "virtio rpc add_sgs returned failure\n");
 			err = -EIO;
 			goto err_out;
 		}

tools/lguest/lguest.txt

@@ -70,7 +70,7 @@ Running Lguest:
 
 - Run an lguest as root:
 
-      Documentation/virtual/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \
+      tools/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \
         --block=rootfile root=/dev/vda
 
    Explanation:

tools/virtio/Makefile

 all: test mod
-test: virtio_test
+test: virtio_test vringh_test
 virtio_test: virtio_ring.o virtio_test.o
-CFLAGS += -g -O2 -Wall -I. -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow  -MMD
-vpath %.c ../../drivers/virtio
+vringh_test: vringh_test.o vringh.o virtio_ring.o
+
+CFLAGS += -g -O2 -Wall -I. -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE
+vpath %.c ../../drivers/virtio ../../drivers/vhost
 mod:
 	${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test
 .PHONY: all test mod clean
 clean:
-	${RM} *.o vhost_test/*.o vhost_test/.*.cmd \
+	${RM} *.o vringh_test virtio_test vhost_test/*.o vhost_test/.*.cmd \
               vhost_test/Module.symvers vhost_test/modules.order *.d
 -include *.d

tools/virtio/asm/barrier.h

+#if defined(__i386__) || defined(__x86_64__)
+#define barrier() asm volatile("" ::: "memory")
+#define mb() __sync_synchronize()
+
+#define smp_mb()	mb()
+# define smp_rmb()	barrier()
+# define smp_wmb()	barrier()
+/* Weak barriers should be used. If not - it's a bug */
+# define rmb()	abort()
+# define wmb()	abort()
+#else
+#error Please fill in barrier macros
+#endif
+

tools/virtio/linux/bug.h

+#ifndef BUG_H
+#define BUG_H
+
+#define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
+
+#define BUILD_BUG_ON(x)
+
+#define BUG() abort()
+
+#endif /* BUG_H */

tools/virtio/linux/export.h

+#define EXPORT_SYMBOL(sym)
+#define EXPORT_SYMBOL_GPL(sym)
+#define EXPORT_SYMBOL_GPL_FUTURE(sym)
+#define EXPORT_UNUSED_SYMBOL(sym)
+#define EXPORT_UNUSED_SYMBOL_GPL(sym)

tools/virtio/linux/irqreturn.h

+#include "../../../include/linux/irqreturn.h"

tools/virtio/linux/module.h

+#include <linux/export.h>

tools/virtio/linux/printk.h

+#include "../../../include/linux/kern_levels.h"
+
+#define printk printf
+#define vprintk vprintf

tools/virtio/linux/ratelimit.h

+#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)	int name = 0
+
+#define __ratelimit(x) (*(x))
+

tools/virtio/linux/virtio_ring.h

+#include "../../../include/linux/virtio_ring.h"

tools/virtio/linux/vringh.h

+#include "../../../include/linux/vringh.h"