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...
 
 Cheers,
 Rusty.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.12 (GNU/Linux)
 
 iQIcBAABAgAGBQJRga7lAAoJENkgDmzRrbjx/yIQAKpqIBtxOJeYH3SY+Uoe7Cfp
 toNYcpJEldvb0UcWN8M2cSZpHoxl1SUoq9djwcM29tcKa7EZAjHaGtb/Q1qMTDgv
 +B3WAfiGU2pmXFxLAkbrlLNGnysy24JspqJQ5hcYV84EiBxQdZp+nCYgOphd+GMK
 ww16vo9ya8jFjzt3GeRp/Heb3vEzV4Cp6BC3i0m8A3WNpEpbRb66pqXNk5o8ggJO
 SxQOKSXmUM+0m+jKSul5xn3e2Ls2LOrZZ8/DIHA+gW66N4Zab7n2/j1Q9VRxb4lh
 FqnR7KwgBX8OCh9IsBDqQYS7MohvMYge6eUdLtFrq84jvMleMEhrC8q9v2tucFUb
 5t18CLwvyK7Gdg6UCKiZ7YSPcuURAILO16al9bh5IseeBDsuX+43VsvQoBmFn9k6
 cLOVTZ6BlOmahK5PyRYFSvLa9Rxzr/05Mr7oYq9UgshD9io78dnqczFYIORF53rW
 zD7C4HuTZfYJFfNd0wAJ0RfVXnf8QvDlMdo7zPC26DSXNWqj8OexCY0qqSWUB+2F
 vcfJP6NkV4fZB8aawWIFUVwc64yqtt2uPVLa7ATZWqk16PgKrchGewmw3tiEwOgu
 1l7xgffTRRUIJsqaCZoXdgw3yezcKRjuUBcOxL09lDAAhc+NxWNvzZBsKp66DwDk
 yZQKn0OdXnuf0CeEOfFf
 =1tYL
 -----END PGP SIGNATURE-----

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
  ...

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

@@ -1,12 +1,14 @@
 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

@@ -0,0 +1,14 @@
+#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

@@ -0,0 +1,10 @@
+#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/err.h

@@ -0,0 +1,26 @@
+#ifndef ERR_H
+#define ERR_H
+#define MAX_ERRNO	4095
+
+#define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO)
+
+static inline void * __must_check ERR_PTR(long error)
+{
+	return (void *) error;
+}
+
+static inline long __must_check PTR_ERR(const void *ptr)
+{
+	return (long) ptr;
+}
+
+static inline long __must_check IS_ERR(const void *ptr)
+{
+	return IS_ERR_VALUE((unsigned long)ptr);
+}
+
+static inline long __must_check IS_ERR_OR_NULL(const void *ptr)
+{
+	return !ptr || IS_ERR_VALUE((unsigned long)ptr);
+}
+#endif /* ERR_H */

tools/virtio/linux/export.h

@@ -0,0 +1,5 @@
+#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

@@ -0,0 +1 @@
+#include "../../../include/linux/irqreturn.h"

tools/virtio/linux/kernel.h

@@ -0,0 +1,112 @@
+#ifndef KERNEL_H
+#define KERNEL_H
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include <stdarg.h>
+
+#include <linux/types.h>
+#include <linux/printk.h>
+#include <linux/bug.h>
+#include <errno.h>
+#include <unistd.h>
+#include <asm/barrier.h>
+
+#define CONFIG_SMP
+
+#define PAGE_SIZE getpagesize()
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+typedef unsigned long long dma_addr_t;
+typedef size_t __kernel_size_t;
+
+struct page {
+	unsigned long long dummy;
+};
+
+/* Physical == Virtual */
+#define virt_to_phys(p) ((unsigned long)p)
+#define phys_to_virt(a) ((void *)(unsigned long)(a))
+/* Page address: Virtual / 4K */
+#define page_to_phys(p) ((dma_addr_t)(unsigned long)(p))
+#define virt_to_page(p) ((struct page *)((unsigned long)p & PAGE_MASK))
+
+#define offset_in_page(p) (((unsigned long)p) % PAGE_SIZE)
+
+#define __printf(a,b) __attribute__((format(printf,a,b)))
+
+typedef enum {
+	GFP_KERNEL,
+	GFP_ATOMIC,
+	__GFP_HIGHMEM,
+	__GFP_HIGH
+} gfp_t;
+
+#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
+
+extern void *__kmalloc_fake, *__kfree_ignore_start, *__kfree_ignore_end;
+static inline void *kmalloc(size_t s, gfp_t gfp)
+{
+	if (__kmalloc_fake)
+		return __kmalloc_fake;
+	return malloc(s);
+}
+
+static inline void kfree(void *p)
+{
+	if (p >= __kfree_ignore_start && p < __kfree_ignore_end)
+		return;
+	free(p);
+}
+
+static inline void *krealloc(void *p, size_t s, gfp_t gfp)
+{
+	return realloc(p, s);
+}
+
+
+static inline unsigned long __get_free_page(gfp_t gfp)
+{
+	void *p;
+
+	posix_memalign(&p, PAGE_SIZE, PAGE_SIZE);
+	return (unsigned long)p;
+}
+
+static inline void free_page(unsigned long addr)
+{
+	free((void *)addr);
+}
+
+#define container_of(ptr, type, member) ({			\
+	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
+	(type *)( (char *)__mptr - offsetof(type,member) );})
+
+#define uninitialized_var(x) x = x
+
+# ifndef likely
+#  define likely(x)	(__builtin_expect(!!(x), 1))
+# endif
+# ifndef unlikely
+#  define unlikely(x)	(__builtin_expect(!!(x), 0))
+# endif
+
+#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#ifdef DEBUG
+#define pr_debug(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#else
+#define pr_debug(format, ...) do {} while (0)
+#endif
+#define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+
+#define min(x, y) ({				\
+	typeof(x) _min1 = (x);			\
+	typeof(y) _min2 = (y);			\
+	(void) (&_min1 == &_min2);		\
+	_min1 < _min2 ? _min1 : _min2; })
+
+#endif /* KERNEL_H */

tools/virtio/linux/module.h

@@ -0,0 +1 @@
+#include <linux/export.h>

tools/virtio/linux/printk.h

@@ -0,0 +1,4 @@
+#include "../../../include/linux/kern_levels.h"
+
+#define printk printf
+#define vprintk vprintf

tools/virtio/linux/ratelimit.h

@@ -0,0 +1,4 @@
+#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)	int name = 0
+
+#define __ratelimit(x) (*(x))
+

tools/virtio/linux/scatterlist.h

@@ -0,0 +1,189 @@
+#ifndef SCATTERLIST_H
+#define SCATTERLIST_H
+#include <linux/kernel.h>
+
+struct scatterlist {
+	unsigned long	page_link;
+	unsigned int	offset;
+	unsigned int	length;
+	dma_addr_t	dma_address;
+};
+
+/* Scatterlist helpers, stolen from linux/scatterlist.h */
+#define sg_is_chain(sg)		((sg)->page_link & 0x01)
+#define sg_is_last(sg)		((sg)->page_link & 0x02)
+#define sg_chain_ptr(sg)	\
+	((struct scatterlist *) ((sg)->page_link & ~0x03))
+
+/**
+ * sg_assign_page - Assign a given page to an SG entry
+ * @sg:		    SG entry
+ * @page:	    The page
+ *
+ * Description:
+ *   Assign page to sg entry. Also see sg_set_page(), the most commonly used
+ *   variant.
+ *
+ **/
+static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
+{
+	unsigned long page_link = sg->page_link & 0x3;
+
+	/*
+	 * In order for the low bit stealing approach to work, pages
+	 * must be aligned at a 32-bit boundary as a minimum.
+	 */
+	BUG_ON((unsigned long) page & 0x03);
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sg->sg_magic != SG_MAGIC);
+	BUG_ON(sg_is_chain(sg));
+#endif
+	sg->page_link = page_link | (unsigned long) page;
+}
+
+/**
+ * sg_set_page - Set sg entry to point at given page
+ * @sg:		 SG entry
+ * @page:	 The page
+ * @len:	 Length of data
+ * @offset:	 Offset into page
+ *
+ * Description:
+ *   Use this function to set an sg entry pointing at a page, never assign
+ *   the page directly. We encode sg table information in the lower bits
+ *   of the page pointer. See sg_page() for looking up the page belonging
+ *   to an sg entry.
+ *
+ **/
+static inline void sg_set_page(struct scatterlist *sg, struct page *page,
+			       unsigned int len, unsigned int offset)
+{
+	sg_assign_page(sg, page);
+	sg->offset = offset;
+	sg->length = len;
+}
+
+static inline struct page *sg_page(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sg->sg_magic != SG_MAGIC);
+	BUG_ON(sg_is_chain(sg));
+#endif
+	return (struct page *)((sg)->page_link & ~0x3);
+}
+
+/*
+ * Loop over each sg element, following the pointer to a new list if necessary
+ */
+#define for_each_sg(sglist, sg, nr, __i)	\
+	for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg))
+
+/**
+ * sg_chain - Chain two sglists together
+ * @prv:	First scatterlist
+ * @prv_nents:	Number of entries in prv
+ * @sgl:	Second scatterlist
+ *
+ * Description:
+ *   Links @prv@ and @sgl@ together, to form a longer scatterlist.
+ *
+ **/
+static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
+			    struct scatterlist *sgl)
+{
+	/*
+	 * offset and length are unused for chain entry.  Clear them.
+	 */
+	prv[prv_nents - 1].offset = 0;
+	prv[prv_nents - 1].length = 0;
+
+	/*
+	 * Set lowest bit to indicate a link pointer, and make sure to clear
+	 * the termination bit if it happens to be set.
+	 */
+	prv[prv_nents - 1].page_link = ((unsigned long) sgl | 0x01) & ~0x02;
+}
+
+/**
+ * sg_mark_end - Mark the end of the scatterlist
+ * @sg:		 SG entryScatterlist
+ *
+ * Description:
+ *   Marks the passed in sg entry as the termination point for the sg
+ *   table. A call to sg_next() on this entry will return NULL.
+ *
+ **/
+static inline void sg_mark_end(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+	/*
+	 * Set termination bit, clear potential chain bit
+	 */
+	sg->page_link |= 0x02;
+	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;
+}
+
+static inline struct scatterlist *sg_next(struct scatterlist *sg)
+{
+#ifdef CONFIG_DEBUG_SG
+	BUG_ON(sg->sg_magic != SG_MAGIC);
+#endif
+	if (sg_is_last(sg))
+		return NULL;
+
+	sg++;
+	if (unlikely(sg_is_chain(sg)))
+		sg = sg_chain_ptr(sg);
+
+	return sg;
+}
+
+static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
+{
+	memset(sgl, 0, sizeof(*sgl) * nents);
+#ifdef CONFIG_DEBUG_SG
+	{
+		unsigned int i;
+		for (i = 0; i < nents; i++)
+			sgl[i].sg_magic = SG_MAGIC;
+	}
+#endif
+	sg_mark_end(&sgl[nents - 1]);
+}
+
+static inline dma_addr_t sg_phys(struct scatterlist *sg)
+{
+	return page_to_phys(sg_page(sg)) + sg->offset;
+}
+
+static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
+			      unsigned int buflen)
+{
+	sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
+}
+
+static inline void sg_init_one(struct scatterlist *sg,
+			       const void *buf, unsigned int buflen)
+{
+	sg_init_table(sg, 1);
+	sg_set_buf(sg, buf, buflen);
+}
+#endif /* SCATTERLIST_H */

tools/virtio/linux/types.h

@@ -0,0 +1,28 @@
+#ifndef TYPES_H
+#define TYPES_H
+#include <stdint.h>
+
+#define __force
+#define __user
+#define __must_check
+#define __cold
+
+typedef uint64_t u64;
+typedef int64_t s64;
+typedef uint32_t u32;
+typedef int32_t s32;
+typedef uint16_t u16;
+typedef int16_t s16;
+typedef uint8_t u8;
+typedef int8_t s8;
+
+typedef uint64_t __u64;
+typedef int64_t __s64;
+typedef uint32_t __u32;
+typedef int32_t __s32;
+typedef uint16_t __u16;
+typedef int16_t __s16;
+typedef uint8_t __u8;
+typedef int8_t __s8;
+
+#endif /* TYPES_H */

tools/virtio/linux/uaccess.h

@@ -0,0 +1,50 @@
+#ifndef UACCESS_H
+#define UACCESS_H
+extern void *__user_addr_min, *__user_addr_max;
+
+#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+static inline void __chk_user_ptr(const volatile void *p, size_t size)
+{
+	assert(p >= __user_addr_min && p + size <= __user_addr_max);
+}
+
+#define put_user(x, ptr)					\
+({								\
+	typeof(ptr) __pu_ptr = (ptr);				\
+	__chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr));		\
+	ACCESS_ONCE(*(__pu_ptr)) = x;				\
+	0;							\
+})
+
+#define get_user(x, ptr)					\
+({								\
+	typeof(ptr) __pu_ptr = (ptr);				\
+	__chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr));		\
+	x = ACCESS_ONCE(*(__pu_ptr));				\
+	0;							\
+})
+
+static void volatile_memcpy(volatile char *to, const volatile char *from, 
+			    unsigned long n)
+{
+	while (n--)
+		*(to++) = *(from++);
+}
+
+static inline int copy_from_user(void *to, const void __user volatile *from,
+				 unsigned long n)
+{
+	__chk_user_ptr(from, n);
+	volatile_memcpy(to, from, n);
+	return 0;
+}
+
+static inline int copy_to_user(void __user volatile *to, const void *from,
+			       unsigned long n)
+{
+	__chk_user_ptr(to, n);
+	volatile_memcpy(to, from, n);
+	return 0;
+}
+#endif /* UACCESS_H */

tools/virtio/linux/uio.h

@@ -0,0 +1,3 @@
+#include <linux/kernel.h>
+
+#include "../../../include/linux/uio.h"

tools/virtio/linux/virtio.h

@@ -1,127 +1,7 @@
 #ifndef LINUX_VIRTIO_H
 #define LINUX_VIRTIO_H
-
-#include <stdbool.h>
-#include <stdlib.h>
-#include <stddef.h>
-#include <stdio.h>
-#include <string.h>
-#include <assert.h>
-
-#include <linux/types.h>
-#include <errno.h>
-
-typedef unsigned long long dma_addr_t;
-
-struct scatterlist {
-	unsigned long	page_link;
-	unsigned int	offset;
-	unsigned int	length;
-	dma_addr_t	dma_address;
-};
-
-struct page {
-	unsigned long long dummy;
-};
-
-#define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
-
-/* Physical == Virtual */
-#define virt_to_phys(p) ((unsigned long)p)
-#define phys_to_virt(a) ((void *)(unsigned long)(a))
-/* Page address: Virtual / 4K */
-#define virt_to_page(p) ((struct page*)((virt_to_phys(p) / 4096) * \
-					sizeof(struct page)))
-#define offset_in_page(p) (((unsigned long)p) % 4096)
-#define sg_phys(sg) ((sg->page_link & ~0x3) / sizeof(struct page) * 4096 + \
-		     sg->offset)
-static inline void sg_mark_end(struct scatterlist *sg)
-{
-	/*
-	 * Set termination bit, clear potential chain bit
-	 */
-	sg->page_link |= 0x02;
-	sg->page_link &= ~0x01;
-}
-static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents)
-{
-	memset(sgl, 0, sizeof(*sgl) * nents);
-	sg_mark_end(&sgl[nents - 1]);
-}
-static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
-{
-	unsigned long page_link = sg->page_link & 0x3;
-
-	/*
-	 * In order for the low bit stealing approach to work, pages
-	 * must be aligned at a 32-bit boundary as a minimum.
-	 */
-	BUG_ON((unsigned long) page & 0x03);
-	sg->page_link = page_link | (unsigned long) page;
-}
-
-static inline void sg_set_page(struct scatterlist *sg, struct page *page,
-			       unsigned int len, unsigned int offset)
-{
-	sg_assign_page(sg, page);
-	sg->offset = offset;
-	sg->length = len;
-}
-
-static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
-			      unsigned int buflen)
-{
-	sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
-}
-
-static inline void sg_init_one(struct scatterlist *sg, const void *buf, unsigned int buflen)
-{
-	sg_init_table(sg, 1);
-	sg_set_buf(sg, buf, buflen);
-}
-
-typedef __u16 u16;
-
-typedef enum {
-	GFP_KERNEL,
-	GFP_ATOMIC,
-} gfp_t;
-typedef enum {
-	IRQ_NONE,
-	IRQ_HANDLED
-} irqreturn_t;
-
-static inline void *kmalloc(size_t s, gfp_t gfp)
-{
-	return malloc(s);
-}
-
-static inline void kfree(void *p)
-{
-	free(p);
-}
-
-#define container_of(ptr, type, member) ({			\
-	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
-	(type *)( (char *)__mptr - offsetof(type,member) );})
-
-#define uninitialized_var(x) x = x
-
-# ifndef likely
-#  define likely(x)	(__builtin_expect(!!(x), 1))
-# endif
-# ifndef unlikely
-#  define unlikely(x)	(__builtin_expect(!!(x), 0))
-# endif
-
-#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#ifdef DEBUG
-#define pr_debug(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#else
-#define pr_debug(format, ...) do {} while (0)
-#endif
-#define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#include <linux/scatterlist.h>
+#include <linux/kernel.h>
 
 /* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
 #define list_add_tail(a, b) do {} while (0)
@@ -131,6 +11,7 @@ static inline void kfree(void *p)
 #define BITS_PER_BYTE		8
 #define BITS_PER_LONG (sizeof(long) * BITS_PER_BYTE)
 #define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+
 /* TODO: Not atomic as it should be:
  * we don't use this for anything important. */
 static inline void clear_bit(int nr, volatile unsigned long *addr)
@@ -145,10 +26,6 @@ static inline int test_bit(int nr, const volatile unsigned long *addr)
 {
         return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
-
-/* The only feature we care to support */
-#define virtio_has_feature(dev, feature) \
-	test_bit((feature), (dev)->features)
 /* end of stubs */
 
 struct virtio_device {
@@ -163,39 +40,32 @@ struct virtqueue {
 	void (*callback)(struct virtqueue *vq);
 	const char *name;
 	struct virtio_device *vdev;
+        unsigned int index;
+        unsigned int num_free;
 	void *priv;
 };
 
-#define EXPORT_SYMBOL_GPL(__EXPORT_SYMBOL_GPL_name) \
-	void __EXPORT_SYMBOL_GPL##__EXPORT_SYMBOL_GPL_name() { \
-}
 #define MODULE_LICENSE(__MODULE_LICENSE_value) \
 	const char *__MODULE_LICENSE_name = __MODULE_LICENSE_value
 
-#define CONFIG_SMP
-
-#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
-
 /* Interfaces exported by virtio_ring. */
-int virtqueue_add_buf(struct virtqueue *vq,
-		      struct scatterlist sg[],
-		      unsigned int out_num,
-		      unsigned int in_num,
+int virtqueue_add_sgs(struct virtqueue *vq,
+		      struct scatterlist *sgs[],
+		      unsigned int out_sgs,
+		      unsigned int in_sgs,
 		      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);
+
 void virtqueue_kick(struct virtqueue *vq);
 
 void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
@@ -206,7 +76,8 @@ bool virtqueue_enable_cb(struct virtqueue *vq);
 bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
 
 void *virtqueue_detach_unused_buf(struct virtqueue *vq);
-struct virtqueue *vring_new_virtqueue(unsigned int num,
+struct virtqueue *vring_new_virtqueue(unsigned int index,
+				      unsigned int num,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,

tools/virtio/linux/virtio_config.h

@@ -0,0 +1,6 @@
+#define VIRTIO_TRANSPORT_F_START	28
+#define VIRTIO_TRANSPORT_F_END		32
+
+#define virtio_has_feature(dev, feature) \
+	test_bit((feature), (dev)->features)
+

tools/virtio/linux/virtio_ring.h

@@ -0,0 +1 @@
+#include "../../../include/linux/virtio_ring.h"

tools/virtio/linux/vringh.h

@@ -0,0 +1 @@
+#include "../../../include/linux/vringh.h"

tools/virtio/uapi/linux/uio.h

@@ -0,0 +1 @@
+#include <sys/uio.h>

tools/virtio/uapi/linux/virtio_config.h

@@ -0,0 +1 @@
+#include "../../../../include/uapi/linux/virtio_config.h"

tools/virtio/uapi/linux/virtio_ring.h

@@ -0,0 +1,4 @@
+#ifndef VIRTIO_RING_H
+#define VIRTIO_RING_H
+#include "../../../../include/uapi/linux/virtio_ring.h"
+#endif /* VIRTIO_RING_H */

tools/virtio/virtio_test.c

@@ -10,11 +10,15 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <fcntl.h>
+#include <stdbool.h>
 #include <linux/vhost.h>
 #include <linux/virtio.h>
 #include <linux/virtio_ring.h>
 #include "../../drivers/vhost/test.h"
 
+/* Unused */
+void *__kmalloc_fake, *__kfree_ignore_start, *__kfree_ignore_end;
+
 struct vq_info {
 	int kick;
 	int call;
@@ -92,7 +96,8 @@ static void vq_info_add(struct vdev_info *dev, int num)
 	assert(r >= 0);
 	memset(info->ring, 0, vring_size(num, 4096));
 	vring_init(&info->vring, num, info->ring, 4096);
-	info->vq = vring_new_virtqueue(info->vring.num, 4096, &dev->vdev,
+	info->vq = vring_new_virtqueue(info->idx,
+				       info->vring.num, 4096, &dev->vdev,
 				       true, info->ring,
 				       vq_notify, vq_callback, "test");
 	assert(info->vq);
@@ -161,9 +166,9 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
 		do {
 			if (started < bufs) {
 				sg_init_one(&sl, dev->buf, dev->buf_size);
-				r = virtqueue_add_buf(vq->vq, &sl, 1, 0,
-						      dev->buf + started,
-						      GFP_ATOMIC);
+				r = virtqueue_add_outbuf(vq->vq, &sl, 1,
+							 dev->buf + started,
+							 GFP_ATOMIC);
 				if (likely(r == 0)) {
 					++started;
 					virtqueue_kick(vq->vq);

tools/virtio/vringh_test.c

@@ -0,0 +1,741 @@
+/* Simple test of virtio code, entirely in userpsace. */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <err.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/virtio.h>
+#include <linux/vringh.h>
+#include <linux/virtio_ring.h>
+#include <linux/uaccess.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <fcntl.h>
+
+#define USER_MEM (1024*1024)
+void *__user_addr_min, *__user_addr_max;
+void *__kmalloc_fake, *__kfree_ignore_start, *__kfree_ignore_end;
+static u64 user_addr_offset;
+
+#define RINGSIZE 256
+#define ALIGN 4096
+
+static void never_notify_host(struct virtqueue *vq)
+{
+	abort();
+}
+
+static void never_callback_guest(struct virtqueue *vq)
+{
+	abort();
+}
+
+static bool getrange_iov(struct vringh *vrh, u64 addr, struct vringh_range *r)
+{
+	if (addr < (u64)(unsigned long)__user_addr_min - user_addr_offset)
+		return false;
+	if (addr >= (u64)(unsigned long)__user_addr_max - user_addr_offset)
+		return false;
+
+	r->start = (u64)(unsigned long)__user_addr_min - user_addr_offset;
+	r->end_incl = (u64)(unsigned long)__user_addr_max - 1 - user_addr_offset;
+	r->offset = user_addr_offset;
+	return true;
+}
+
+/* We return single byte ranges. */
+static bool getrange_slow(struct vringh *vrh, u64 addr, struct vringh_range *r)
+{
+	if (addr < (u64)(unsigned long)__user_addr_min - user_addr_offset)
+		return false;
+	if (addr >= (u64)(unsigned long)__user_addr_max - user_addr_offset)
+		return false;
+
+	r->start = addr;
+	r->end_incl = r->start;
+	r->offset = user_addr_offset;
+	return true;
+}
+
+struct guest_virtio_device {
+	struct virtio_device vdev;
+	int to_host_fd;
+	unsigned long notifies;
+};
+
+static void parallel_notify_host(struct virtqueue *vq)
+{
+	struct guest_virtio_device *gvdev;
+
+	gvdev = container_of(vq->vdev, struct guest_virtio_device, vdev);
+	write(gvdev->to_host_fd, "", 1);
+	gvdev->notifies++;
+}
+
+static void no_notify_host(struct virtqueue *vq)
+{
+}
+
+#define NUM_XFERS (10000000)
+
+/* We aim for two "distant" cpus. */
+static void find_cpus(unsigned int *first, unsigned int *last)
+{
+	unsigned int i;
+
+	*first = -1U;
+	*last = 0;
+	for (i = 0; i < 4096; i++) {
+		cpu_set_t set;
+		CPU_ZERO(&set);
+		CPU_SET(i, &set);
+		if (sched_setaffinity(getpid(), sizeof(set), &set) == 0) {
+			if (i < *first)
+				*first = i;
+			if (i > *last)
+				*last = i;
+		}
+	}
+}
+
+/* Opencoded version for fast mode */
+static inline int vringh_get_head(struct vringh *vrh, u16 *head)
+{
+	u16 avail_idx, i;
+	int err;
+
+	err = get_user(avail_idx, &vrh->vring.avail->idx);
+	if (err)
+		return err;
+
+	if (vrh->last_avail_idx == avail_idx)
+		return 0;
+
+	/* Only get avail ring entries after they have been exposed by guest. */
+	virtio_rmb(vrh->weak_barriers);
+
+	i = vrh->last_avail_idx & (vrh->vring.num - 1);
+
+	err = get_user(*head, &vrh->vring.avail->ring[i]);
+	if (err)
+		return err;
+
+	vrh->last_avail_idx++;
+	return 1;
+}
+
+static int parallel_test(unsigned long features,
+			 bool (*getrange)(struct vringh *vrh,
+					  u64 addr, struct vringh_range *r),
+			 bool fast_vringh)
+{
+	void *host_map, *guest_map;
+	int fd, mapsize, to_guest[2], to_host[2];
+	unsigned long xfers = 0, notifies = 0, receives = 0;
+	unsigned int first_cpu, last_cpu;
+	cpu_set_t cpu_set;
+	char buf[128];
+
+	/* Create real file to mmap. */
+	fd = open("/tmp/vringh_test-file", O_RDWR|O_CREAT|O_TRUNC, 0600);
+	if (fd < 0)
+		err(1, "Opening /tmp/vringh_test-file");
+
+	/* Extra room at the end for some data, and indirects */
+	mapsize = vring_size(RINGSIZE, ALIGN)
+		+ RINGSIZE * 2 * sizeof(int)
+		+ RINGSIZE * 6 * sizeof(struct vring_desc);
+	mapsize = (mapsize + getpagesize() - 1) & ~(getpagesize() - 1);
+	ftruncate(fd, mapsize);
+
+	/* Parent and child use separate addresses, to check our mapping logic! */
+	host_map = mmap(NULL, mapsize, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
+	guest_map = mmap(NULL, mapsize, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
+
+	pipe(to_guest);
+	pipe(to_host);
+
+	CPU_ZERO(&cpu_set);
+	find_cpus(&first_cpu, &last_cpu);
+	printf("Using CPUS %u and %u\n", first_cpu, last_cpu);
+	fflush(stdout);
+
+	if (fork() != 0) {
+		struct vringh vrh;
+		int status, err, rlen = 0;
+		char rbuf[5];
+
+		/* We are the host: never access guest addresses! */
+		munmap(guest_map, mapsize);
+
+		__user_addr_min = host_map;
+		__user_addr_max = __user_addr_min + mapsize;
+		user_addr_offset = host_map - guest_map;
+		assert(user_addr_offset);
+
+		close(to_guest[0]);
+		close(to_host[1]);
+
+		vring_init(&vrh.vring, RINGSIZE, host_map, ALIGN);
+		vringh_init_user(&vrh, features, RINGSIZE, true,
+				 vrh.vring.desc, vrh.vring.avail, vrh.vring.used);
+		CPU_SET(first_cpu, &cpu_set);
+		if (sched_setaffinity(getpid(), sizeof(cpu_set), &cpu_set))
+			errx(1, "Could not set affinity to cpu %u", first_cpu);
+
+		while (xfers < NUM_XFERS) {
+			struct iovec host_riov[2], host_wiov[2];
+			struct vringh_iov riov, wiov;
+			u16 head, written;
+
+			if (fast_vringh) {
+				for (;;) {
+					err = vringh_get_head(&vrh, &head);
+					if (err != 0)
+						break;
+					err = vringh_need_notify_user(&vrh);
+					if (err < 0)
+						errx(1, "vringh_need_notify_user: %i",
+						     err);
+					if (err) {
+						write(to_guest[1], "", 1);
+						notifies++;
+					}
+				}
+				if (err != 1)
+					errx(1, "vringh_get_head");
+				written = 0;
+				goto complete;
+			} else {
+				vringh_iov_init(&riov,
+						host_riov,
+						ARRAY_SIZE(host_riov));
+				vringh_iov_init(&wiov,
+						host_wiov,
+						ARRAY_SIZE(host_wiov));
+
+				err = vringh_getdesc_user(&vrh, &riov, &wiov,
+							  getrange, &head);
+			}
+			if (err == 0) {
+				err = vringh_need_notify_user(&vrh);
+				if (err < 0)
+					errx(1, "vringh_need_notify_user: %i",
+					     err);
+				if (err) {
+					write(to_guest[1], "", 1);
+					notifies++;
+				}
+
+				if (!vringh_notify_enable_user(&vrh))
+					continue;
+
+				/* Swallow all notifies at once. */
+				if (read(to_host[0], buf, sizeof(buf)) < 1)
+					break;
+
+				vringh_notify_disable_user(&vrh);
+				receives++;
+				continue;
+			}
+			if (err != 1)
+				errx(1, "vringh_getdesc_user: %i", err);
+
+			/* We simply copy bytes. */
+			if (riov.used) {
+				rlen = vringh_iov_pull_user(&riov, rbuf,
+							    sizeof(rbuf));
+				if (rlen != 4)
+					errx(1, "vringh_iov_pull_user: %i",
+					     rlen);
+				assert(riov.i == riov.used);
+				written = 0;
+			} else {
+				err = vringh_iov_push_user(&wiov, rbuf, rlen);
+				if (err != rlen)
+					errx(1, "vringh_iov_push_user: %i",
+					     err);
+				assert(wiov.i == wiov.used);
+				written = err;
+			}
+		complete:
+			xfers++;
+
+			err = vringh_complete_user(&vrh, head, written);
+			if (err != 0)
+				errx(1, "vringh_complete_user: %i", err);
+		}
+
+		err = vringh_need_notify_user(&vrh);
+		if (err < 0)
+			errx(1, "vringh_need_notify_user: %i", err);
+		if (err) {
+			write(to_guest[1], "", 1);
+			notifies++;
+		}
+		wait(&status);
+		if (!WIFEXITED(status))
+			errx(1, "Child died with signal %i?", WTERMSIG(status));
+		if (WEXITSTATUS(status) != 0)
+			errx(1, "Child exited %i?", WEXITSTATUS(status));
+		printf("Host: notified %lu, pinged %lu\n", notifies, receives);
+		return 0;
+	} else {
+		struct guest_virtio_device gvdev;
+		struct virtqueue *vq;
+		unsigned int *data;
+		struct vring_desc *indirects;
+		unsigned int finished = 0;
+
+		/* We pass sg[]s pointing into here, but we need RINGSIZE+1 */
+		data = guest_map + vring_size(RINGSIZE, ALIGN);
+		indirects = (void *)data + (RINGSIZE + 1) * 2 * sizeof(int);
+
+		/* We are the guest. */
+		munmap(host_map, mapsize);
+
+		close(to_guest[1]);
+		close(to_host[0]);
+
+		gvdev.vdev.features[0] = features;
+		gvdev.to_host_fd = to_host[1];
+		gvdev.notifies = 0;
+
+		CPU_SET(first_cpu, &cpu_set);
+		if (sched_setaffinity(getpid(), sizeof(cpu_set), &cpu_set))
+			err(1, "Could not set affinity to cpu %u", first_cpu);
+
+		vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &gvdev.vdev, true,
+					 guest_map, fast_vringh ? no_notify_host
+					 : parallel_notify_host,
+					 never_callback_guest, "guest vq");
+
+		/* Don't kfree indirects. */
+		__kfree_ignore_start = indirects;
+		__kfree_ignore_end = indirects + RINGSIZE * 6;
+
+		while (xfers < NUM_XFERS) {
+			struct scatterlist sg[4];
+			unsigned int num_sg, len;
+			int *dbuf, err;
+			bool output = !(xfers % 2);
+
+			/* Consume bufs. */
+			while ((dbuf = virtqueue_get_buf(vq, &len)) != NULL) {
+				if (len == 4)
+					assert(*dbuf == finished - 1);
+				else if (!fast_vringh)
+					assert(*dbuf == finished);
+				finished++;
+			}
+
+			/* Produce a buffer. */
+			dbuf = data + (xfers % (RINGSIZE + 1));
+
+			if (output)
+				*dbuf = xfers;
+			else
+				*dbuf = -1;
+
+			switch ((xfers / sizeof(*dbuf)) % 4) {
+			case 0:
+				/* Nasty three-element sg list. */
+				sg_init_table(sg, num_sg = 3);
+				sg_set_buf(&sg[0], (void *)dbuf, 1);
+				sg_set_buf(&sg[1], (void *)dbuf + 1, 2);
+				sg_set_buf(&sg[2], (void *)dbuf + 3, 1);
+				break;
+			case 1:
+				sg_init_table(sg, num_sg = 2);
+				sg_set_buf(&sg[0], (void *)dbuf, 1);
+				sg_set_buf(&sg[1], (void *)dbuf + 1, 3);
+				break;
+			case 2:
+				sg_init_table(sg, num_sg = 1);
+				sg_set_buf(&sg[0], (void *)dbuf, 4);
+				break;
+			case 3:
+				sg_init_table(sg, num_sg = 4);
+				sg_set_buf(&sg[0], (void *)dbuf, 1);
+				sg_set_buf(&sg[1], (void *)dbuf + 1, 1);
+				sg_set_buf(&sg[2], (void *)dbuf + 2, 1);
+				sg_set_buf(&sg[3], (void *)dbuf + 3, 1);
+				break;
+			}
+
+			/* May allocate an indirect, so force it to allocate
+			 * user addr */
+			__kmalloc_fake = indirects + (xfers % RINGSIZE) * 4;
+			if (output)
+				err = virtqueue_add_outbuf(vq, sg, num_sg, dbuf,
+							   GFP_KERNEL);
+			else
+				err = virtqueue_add_inbuf(vq, sg, num_sg,
+							  dbuf, GFP_KERNEL);
+
+			if (err == -ENOSPC) {
+				if (!virtqueue_enable_cb_delayed(vq))
+					continue;
+				/* Swallow all notifies at once. */
+				if (read(to_guest[0], buf, sizeof(buf)) < 1)
+					break;
+				
+				receives++;
+				virtqueue_disable_cb(vq);
+				continue;
+			}
+
+			if (err)
+				errx(1, "virtqueue_add_in/outbuf: %i", err);
+
+			xfers++;
+			virtqueue_kick(vq);
+		}
+
+		/* Any extra? */
+		while (finished != xfers) {
+			int *dbuf;
+			unsigned int len;
+
+			/* Consume bufs. */
+			dbuf = virtqueue_get_buf(vq, &len);
+			if (dbuf) {
+				if (len == 4)
+					assert(*dbuf == finished - 1);
+				else
+					assert(len == 0);
+				finished++;
+				continue;
+			}
+
+			if (!virtqueue_enable_cb_delayed(vq))
+				continue;
+			if (read(to_guest[0], buf, sizeof(buf)) < 1)
+				break;
+				
+			receives++;
+			virtqueue_disable_cb(vq);
+		}
+
+		printf("Guest: notified %lu, pinged %lu\n",
+		       gvdev.notifies, receives);
+		vring_del_virtqueue(vq);
+		return 0;
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	struct virtio_device vdev;
+	struct virtqueue *vq;
+	struct vringh vrh;
+	struct scatterlist guest_sg[RINGSIZE], *sgs[2];
+	struct iovec host_riov[2], host_wiov[2];
+	struct vringh_iov riov, wiov;
+	struct vring_used_elem used[RINGSIZE];
+	char buf[28];
+	u16 head;
+	int err;
+	unsigned i;
+	void *ret;
+	bool (*getrange)(struct vringh *vrh, u64 addr, struct vringh_range *r);
+	bool fast_vringh = false, parallel = false;
+
+	getrange = getrange_iov;
+	vdev.features[0] = 0;
+
+	while (argv[1]) {
+		if (strcmp(argv[1], "--indirect") == 0)
+			vdev.features[0] |= (1 << VIRTIO_RING_F_INDIRECT_DESC);
+		else if (strcmp(argv[1], "--eventidx") == 0)
+			vdev.features[0] |= (1 << VIRTIO_RING_F_EVENT_IDX);
+		else if (strcmp(argv[1], "--slow-range") == 0)
+			getrange = getrange_slow;
+		else if (strcmp(argv[1], "--fast-vringh") == 0)
+			fast_vringh = true;
+		else if (strcmp(argv[1], "--parallel") == 0)
+			parallel = true;
+		else
+			errx(1, "Unknown arg %s", argv[1]);
+		argv++;
+	}
+
+	if (parallel)
+		return parallel_test(vdev.features[0], getrange, fast_vringh);
+
+	if (posix_memalign(&__user_addr_min, PAGE_SIZE, USER_MEM) != 0)
+		abort();
+	__user_addr_max = __user_addr_min + USER_MEM;
+	memset(__user_addr_min, 0, vring_size(RINGSIZE, ALIGN));
+
+	/* Set up guest side. */
+	vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
+				 __user_addr_min,
+				 never_notify_host, never_callback_guest,
+				 "guest vq");
+
+	/* Set up host side. */
+	vring_init(&vrh.vring, RINGSIZE, __user_addr_min, ALIGN);
+	vringh_init_user(&vrh, vdev.features[0], RINGSIZE, true,
+			 vrh.vring.desc, vrh.vring.avail, vrh.vring.used);
+
+	/* No descriptor to get yet... */
+	err = vringh_getdesc_user(&vrh, &riov, &wiov, getrange, &head);
+	if (err != 0)
+		errx(1, "vringh_getdesc_user: %i", err);
+
+	/* Guest puts in a descriptor. */
+	memcpy(__user_addr_max - 1, "a", 1);
+	sg_init_table(guest_sg, 1);
+	sg_set_buf(&guest_sg[0], __user_addr_max - 1, 1);
+	sg_init_table(guest_sg+1, 1);
+	sg_set_buf(&guest_sg[1], __user_addr_max - 3, 2);
+	sgs[0] = &guest_sg[0];
+	sgs[1] = &guest_sg[1];
+
+	/* May allocate an indirect, so force it to allocate user addr */
+	__kmalloc_fake = __user_addr_min + vring_size(RINGSIZE, ALIGN);
+	err = virtqueue_add_sgs(vq, sgs, 1, 1, &err, GFP_KERNEL);
+	if (err)
+		errx(1, "virtqueue_add_sgs: %i", err);
+	__kmalloc_fake = NULL;
+
+	/* Host retreives it. */
+	vringh_iov_init(&riov, host_riov, ARRAY_SIZE(host_riov));
+	vringh_iov_init(&wiov, host_wiov, ARRAY_SIZE(host_wiov));
+
+	err = vringh_getdesc_user(&vrh, &riov, &wiov, getrange, &head);
+	if (err != 1)
+		errx(1, "vringh_getdesc_user: %i", err);
+
+	assert(riov.used == 1);
+	assert(riov.iov[0].iov_base == __user_addr_max - 1);
+	assert(riov.iov[0].iov_len == 1);
+	if (getrange != getrange_slow) {
+		assert(wiov.used == 1);
+		assert(wiov.iov[0].iov_base == __user_addr_max - 3);
+		assert(wiov.iov[0].iov_len == 2);
+	} else {
+		assert(wiov.used == 2);
+		assert(wiov.iov[0].iov_base == __user_addr_max - 3);
+		assert(wiov.iov[0].iov_len == 1);
+		assert(wiov.iov[1].iov_base == __user_addr_max - 2);
+		assert(wiov.iov[1].iov_len == 1);
+	}
+
+	err = vringh_iov_pull_user(&riov, buf, 5);
+	if (err != 1)
+		errx(1, "vringh_iov_pull_user: %i", err);
+	assert(buf[0] == 'a');
+	assert(riov.i == 1);
+	assert(vringh_iov_pull_user(&riov, buf, 5) == 0);
+
+	memcpy(buf, "bcdef", 5);
+	err = vringh_iov_push_user(&wiov, buf, 5);
+	if (err != 2)
+		errx(1, "vringh_iov_push_user: %i", err);
+	assert(memcmp(__user_addr_max - 3, "bc", 2) == 0);
+	assert(wiov.i == wiov.used);
+	assert(vringh_iov_push_user(&wiov, buf, 5) == 0);
+
+	/* Host is done. */
+	err = vringh_complete_user(&vrh, head, err);
+	if (err != 0)
+		errx(1, "vringh_complete_user: %i", err);
+
+	/* Guest should see used token now. */
+	__kfree_ignore_start = __user_addr_min + vring_size(RINGSIZE, ALIGN);
+	__kfree_ignore_end = __kfree_ignore_start + 1;
+	ret = virtqueue_get_buf(vq, &i);
+	if (ret != &err)
+		errx(1, "virtqueue_get_buf: %p", ret);
+	assert(i == 2);
+
+	/* Guest puts in a huge descriptor. */
+	sg_init_table(guest_sg, RINGSIZE);
+	for (i = 0; i < RINGSIZE; i++) {
+		sg_set_buf(&guest_sg[i],
+			   __user_addr_max - USER_MEM/4, USER_MEM/4);
+	}
+
+	/* Fill contents with recognisable garbage. */
+	for (i = 0; i < USER_MEM/4; i++)
+		((char *)__user_addr_max - USER_MEM/4)[i] = i;
+
+	/* This will allocate an indirect, so force it to allocate user addr */
+	__kmalloc_fake = __user_addr_min + vring_size(RINGSIZE, ALIGN);
+	err = virtqueue_add_outbuf(vq, guest_sg, RINGSIZE, &err, GFP_KERNEL);
+	if (err)
+		errx(1, "virtqueue_add_outbuf (large): %i", err);
+	__kmalloc_fake = NULL;
+
+	/* Host picks it up (allocates new iov). */
+	vringh_iov_init(&riov, host_riov, ARRAY_SIZE(host_riov));
+	vringh_iov_init(&wiov, host_wiov, ARRAY_SIZE(host_wiov));
+
+	err = vringh_getdesc_user(&vrh, &riov, &wiov, getrange, &head);
+	if (err != 1)
+		errx(1, "vringh_getdesc_user: %i", err);
+
+	assert(riov.max_num & VRINGH_IOV_ALLOCATED);
+	assert(riov.iov != host_riov);
+	if (getrange != getrange_slow)
+		assert(riov.used == RINGSIZE);
+	else
+		assert(riov.used == RINGSIZE * USER_MEM/4);
+
+	assert(!(wiov.max_num & VRINGH_IOV_ALLOCATED));
+	assert(wiov.used == 0);
+
+	/* Pull data back out (in odd chunks), should be as expected. */
+	for (i = 0; i < RINGSIZE * USER_MEM/4; i += 3) {
+		err = vringh_iov_pull_user(&riov, buf, 3);
+		if (err != 3 && i + err != RINGSIZE * USER_MEM/4)
+			errx(1, "vringh_iov_pull_user large: %i", err);
+		assert(buf[0] == (char)i);
+		assert(err < 2 || buf[1] == (char)(i + 1));
+		assert(err < 3 || buf[2] == (char)(i + 2));
+	}
+	assert(riov.i == riov.used);
+	vringh_iov_cleanup(&riov);
+	vringh_iov_cleanup(&wiov);
+
+	/* Complete using multi interface, just because we can. */
+	used[0].id = head;
+	used[0].len = 0;
+	err = vringh_complete_multi_user(&vrh, used, 1);
+	if (err)
+		errx(1, "vringh_complete_multi_user(1): %i", err);
+
+	/* Free up those descriptors. */
+	ret = virtqueue_get_buf(vq, &i);
+	if (ret != &err)
+		errx(1, "virtqueue_get_buf: %p", ret);
+
+	/* Add lots of descriptors. */
+	sg_init_table(guest_sg, 1);
+	sg_set_buf(&guest_sg[0], __user_addr_max - 1, 1);
+	for (i = 0; i < RINGSIZE; i++) {
+		err = virtqueue_add_outbuf(vq, guest_sg, 1, &err, GFP_KERNEL);
+		if (err)
+			errx(1, "virtqueue_add_outbuf (multiple): %i", err);
+	}
+
+	/* Now get many, and consume them all at once. */
+	vringh_iov_init(&riov, host_riov, ARRAY_SIZE(host_riov));
+	vringh_iov_init(&wiov, host_wiov, ARRAY_SIZE(host_wiov));
+
+	for (i = 0; i < RINGSIZE; i++) {
+		err = vringh_getdesc_user(&vrh, &riov, &wiov, getrange, &head);
+		if (err != 1)
+			errx(1, "vringh_getdesc_user: %i", err);
+		used[i].id = head;
+		used[i].len = 0;
+	}
+	/* Make sure it wraps around ring, to test! */
+	assert(vrh.vring.used->idx % RINGSIZE != 0);
+	err = vringh_complete_multi_user(&vrh, used, RINGSIZE);
+	if (err)
+		errx(1, "vringh_complete_multi_user: %i", err);
+
+	/* Free those buffers. */
+	for (i = 0; i < RINGSIZE; i++) {
+		unsigned len;
+		assert(virtqueue_get_buf(vq, &len) != NULL);
+	}
+
+	/* Test weird (but legal!) indirect. */
+	if (vdev.features[0] & (1 << VIRTIO_RING_F_INDIRECT_DESC)) {
+		char *data = __user_addr_max - USER_MEM/4;
+		struct vring_desc *d = __user_addr_max - USER_MEM/2;
+		struct vring vring;
+
+		/* Force creation of direct, which we modify. */
+		vdev.features[0] &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC);
+		vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
+					 __user_addr_min,
+					 never_notify_host,
+					 never_callback_guest,
+					 "guest vq");
+
+		sg_init_table(guest_sg, 4);
+		sg_set_buf(&guest_sg[0], d, sizeof(*d)*2);
+		sg_set_buf(&guest_sg[1], d + 2, sizeof(*d)*1);
+		sg_set_buf(&guest_sg[2], data + 6, 4);
+		sg_set_buf(&guest_sg[3], d + 3, sizeof(*d)*3);
+
+		err = virtqueue_add_outbuf(vq, guest_sg, 4, &err, GFP_KERNEL);
+		if (err)
+			errx(1, "virtqueue_add_outbuf (indirect): %i", err);
+
+		vring_init(&vring, RINGSIZE, __user_addr_min, ALIGN);
+
+		/* They're used in order, but double-check... */
+		assert(vring.desc[0].addr == (unsigned long)d);
+		assert(vring.desc[1].addr == (unsigned long)(d+2));
+		assert(vring.desc[2].addr == (unsigned long)data + 6);
+		assert(vring.desc[3].addr == (unsigned long)(d+3));
+		vring.desc[0].flags |= VRING_DESC_F_INDIRECT;
+		vring.desc[1].flags |= VRING_DESC_F_INDIRECT;
+		vring.desc[3].flags |= VRING_DESC_F_INDIRECT;
+
+		/* First indirect */
+		d[0].addr = (unsigned long)data;
+		d[0].len = 1;
+		d[0].flags = VRING_DESC_F_NEXT;
+		d[0].next = 1;
+		d[1].addr = (unsigned long)data + 1;
+		d[1].len = 2;
+		d[1].flags = 0;
+
+		/* Second indirect */
+		d[2].addr = (unsigned long)data + 3;
+		d[2].len = 3;
+		d[2].flags = 0;
+
+		/* Third indirect */
+		d[3].addr = (unsigned long)data + 10;
+		d[3].len = 5;
+		d[3].flags = VRING_DESC_F_NEXT;
+		d[3].next = 1;
+		d[4].addr = (unsigned long)data + 15;
+		d[4].len = 6;
+		d[4].flags = VRING_DESC_F_NEXT;
+		d[4].next = 2;
+		d[5].addr = (unsigned long)data + 21;
+		d[5].len = 7;
+		d[5].flags = 0;
+
+		/* Host picks it up (allocates new iov). */
+		vringh_iov_init(&riov, host_riov, ARRAY_SIZE(host_riov));
+		vringh_iov_init(&wiov, host_wiov, ARRAY_SIZE(host_wiov));
+
+		err = vringh_getdesc_user(&vrh, &riov, &wiov, getrange, &head);
+		if (err != 1)
+			errx(1, "vringh_getdesc_user: %i", err);
+
+		if (head != 0)
+			errx(1, "vringh_getdesc_user: head %i not 0", head);
+
+		assert(riov.max_num & VRINGH_IOV_ALLOCATED);
+		if (getrange != getrange_slow)
+			assert(riov.used == 7);
+		else
+			assert(riov.used == 28);
+		err = vringh_iov_pull_user(&riov, buf, 29);
+		assert(err == 28);
+
+		/* Data should be linear. */
+		for (i = 0; i < err; i++)
+			assert(buf[i] == i);
+		vringh_iov_cleanup(&riov);
+	}
+
+	/* Don't leak memory... */
+	vring_del_virtqueue(vq);
+	free(__user_addr_min);
+
+	return 0;
+}