Fixed MTP to work with TWRP

tools/virtio/Makefile

@@ -0,0 +1,14 @@
+all: test mod
+test: virtio_test vringh_test
+virtio_test: virtio_ring.o virtio_test.o
+vringh_test: vringh_test.o vringh.o virtio_ring.o
+
+CFLAGS += -g -O2 -Wall -I. -I../include/ -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 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/device.h

@@ -0,0 +1,2 @@
+#ifndef LINUX_DEVICE_H
+#endif

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/irqreturn.h

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

tools/virtio/linux/kernel.h

@@ -0,0 +1,105 @@
+#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)))
+
+#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/kmemleak.h

@@ -0,0 +1,3 @@
+static inline void kmemleak_ignore(const void *ptr)
+{
+}

tools/virtio/linux/module.h

@@ -0,0 +1,6 @@
+#include <linux/export.h>
+
+#define MODULE_LICENSE(__MODULE_LICENSE_value) \
+	static __attribute__((unused)) const char *__MODULE_LICENSE_name = \
+		__MODULE_LICENSE_value
+

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/slab.h

@@ -0,0 +1,2 @@
+#ifndef LINUX_SLAB_H
+#endif

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

@@ -0,0 +1,87 @@
+#ifndef LINUX_VIRTIO_H
+#define LINUX_VIRTIO_H
+#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)
+#define list_del(a) do {} while (0)
+
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#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)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+        return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+/* end of stubs */
+
+struct virtio_device {
+	void *dev;
+	unsigned long features[1];
+};
+
+struct virtqueue {
+	/* TODO: commented as list macros are empty stubs for now.
+	 * Broken but enough for virtio_ring.c
+	 * struct list_head list; */
+	void (*callback)(struct virtqueue *vq);
+	const char *name;
+	struct virtio_device *vdev;
+        unsigned int index;
+        unsigned int num_free;
+	void *priv;
+};
+
+/* Interfaces exported by virtio_ring. */
+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);
+
+bool virtqueue_kick(struct virtqueue *vq);
+
+void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
+
+void virtqueue_disable_cb(struct virtqueue *vq);
+
+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 index,
+				      unsigned int num,
+				      unsigned int vring_align,
+				      struct virtio_device *vdev,
+				      bool weak_barriers,
+				      void *pages,
+				      bool (*notify)(struct virtqueue *vq),
+				      void (*callback)(struct virtqueue *vq),
+				      const char *name);
+void vring_del_virtqueue(struct virtqueue *vq);
+
+#endif

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/vhost_test/Makefile

@@ -0,0 +1,2 @@
+obj-m += vhost_test.o
+EXTRA_CFLAGS += -Idrivers/vhost

tools/virtio/vhost_test/vhost_test.c

@@ -0,0 +1 @@
+#include "test.c"

tools/virtio/virtio-trace/Makefile

@@ -0,0 +1,13 @@
+CC = gcc
+CFLAGS = -O2 -Wall -pthread
+
+all: trace-agent
+
+.c.o:
+	$(CC) $(CFLAGS) -c $^ -o $@
+
+trace-agent: trace-agent.o trace-agent-ctl.o trace-agent-rw.o
+	$(CC) $(CFLAGS) -o $@ $^
+
+clean:
+	rm -f *.o trace-agent

tools/virtio/virtio-trace/README

@@ -0,0 +1,118 @@
+Trace Agent for virtio-trace
+============================
+
+Trace agent is a user tool for sending trace data of a guest to a Host in low
+overhead. Trace agent has the following functions:
+ - splice a page of ring-buffer to read_pipe without memory copying
+ - splice the page from write_pipe to virtio-console without memory copying
+ - write trace data to stdout by using -o option
+ - controlled by start/stop orders from a Host
+
+The trace agent operates as follows:
+ 1) Initialize all structures.
+ 2) Create a read/write thread per CPU. Each thread is bound to a CPU.
+    The read/write threads hold it.
+ 3) A controller thread does poll() for a start order of a host.
+ 4) After the controller of the trace agent receives a start order from a host,
+    the controller wake read/write threads.
+ 5) The read/write threads start to read trace data from ring-buffers and
+    write the data to virtio-serial.
+ 6) If the controller receives a stop order from a host, the read/write threads
+    stop to read trace data.
+
+
+Files
+=====
+
+README: this file
+Makefile: Makefile of trace agent for virtio-trace
+trace-agent.c: includes main function, sets up for operating trace agent
+trace-agent.h: includes all structures and some macros
+trace-agent-ctl.c: includes controller function for read/write threads
+trace-agent-rw.c: includes read/write threads function
+
+
+Setup
+=====
+
+To use this trace agent for virtio-trace, we need to prepare some virtio-serial
+I/Fs.
+
+1) Make FIFO in a host
+ virtio-trace uses virtio-serial pipe as trace data paths as to the number
+of CPUs and a control path, so FIFO (named pipe) should be created as follows:
+	# mkdir /tmp/virtio-trace/
+	# mkfifo /tmp/virtio-trace/trace-path-cpu{0,1,2,...,X}.{in,out}
+	# mkfifo /tmp/virtio-trace/agent-ctl-path.{in,out}
+
+For example, if a guest use three CPUs, the names are
+	trace-path-cpu{0,1,2}.{in.out}
+and
+	agent-ctl-path.{in,out}.
+
+2) Set up of virtio-serial pipe in a host
+ Add qemu option to use virtio-serial pipe.
+
+ ##virtio-serial device##
+     -device virtio-serial-pci,id=virtio-serial0\
+ ##control path##
+     -chardev pipe,id=charchannel0,path=/tmp/virtio-trace/agent-ctl-path\
+     -device virtserialport,bus=virtio-serial0.0,nr=1,chardev=charchannel0,\
+      id=channel0,name=agent-ctl-path\
+ ##data path##
+     -chardev pipe,id=charchannel1,path=/tmp/virtio-trace/trace-path-cpu0\
+     -device virtserialport,bus=virtio-serial0.0,nr=2,chardev=charchannel0,\
+      id=channel1,name=trace-path-cpu0\
+      ...
+
+If you manage guests with libvirt, add the following tags to domain XML files.
+Then, libvirt passes the same command option to qemu.
+
+	<channel type='pipe'>
+	   <source path='/tmp/virtio-trace/agent-ctl-path'/>
+	   <target type='virtio' name='agent-ctl-path'/>
+	   <address type='virtio-serial' controller='0' bus='0' port='0'/>
+	</channel>
+	<channel type='pipe'>
+	   <source path='/tmp/virtio-trace/trace-path-cpu0'/>
+	   <target type='virtio' name='trace-path-cpu0'/>
+	   <address type='virtio-serial' controller='0' bus='0' port='1'/>
+	</channel>
+	...
+Here, chardev names are restricted to trace-path-cpuX and agent-ctl-path. For
+example, if a guest use three CPUs, chardev names should be trace-path-cpu0,
+trace-path-cpu1, trace-path-cpu2, and agent-ctl-path.
+
+3) Boot the guest
+ You can find some chardev in /dev/virtio-ports/ in the guest.
+
+
+Run
+===
+
+0) Build trace agent in a guest
+	$ make
+
+1) Enable ftrace in the guest
+ <Example>
+	# echo 1 > /sys/kernel/debug/tracing/events/sched/enable
+
+2) Run trace agent in the guest
+ This agent must be operated as root.
+	# ./trace-agent
+read/write threads in the agent wait for start order from host. If you add -o
+option, trace data are output via stdout in the guest.
+
+3) Open FIFO in a host
+	# cat /tmp/virtio-trace/trace-path-cpu0.out
+If a host does not open these, trace data get stuck in buffers of virtio. Then,
+the guest will stop by specification of chardev in QEMU. This blocking mode may
+be solved in the future.
+
+4) Start to read trace data by ordering from a host
+ A host injects read start order to the guest via virtio-serial.
+	# echo 1 > /tmp/virtio-trace/agent-ctl-path.in
+
+5) Stop to read trace data by ordering from a host
+ A host injects read stop order to the guest via virtio-serial.
+	# echo 0 > /tmp/virtio-trace/agent-ctl-path.in

tools/virtio/virtio-trace/trace-agent-ctl.c

@@ -0,0 +1,137 @@
+/*
+ * Controller of read/write threads for virtio-trace
+ *
+ * Copyright (C) 2012 Hitachi, Ltd.
+ * Created by Yoshihiro Yunomae <yoshihiro.yunomae.ez@hitachi.com>
+ *            Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+ *
+ * Licensed under GPL version 2 only.
+ *
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include "trace-agent.h"
+
+#define HOST_MSG_SIZE		256
+#define EVENT_WAIT_MSEC		100
+
+static volatile sig_atomic_t global_signal_val;
+bool global_sig_receive;	/* default false */
+bool global_run_operation;	/* default false*/
+
+/* Handle SIGTERM/SIGINT/SIGQUIT to exit */
+static void signal_handler(int sig)
+{
+	global_signal_val = sig;
+}
+
+int rw_ctl_init(const char *ctl_path)
+{
+	int ctl_fd;
+
+	ctl_fd = open(ctl_path, O_RDONLY);
+	if (ctl_fd == -1) {
+		pr_err("Cannot open ctl_fd\n");
+		goto error;
+	}
+
+	return ctl_fd;
+
+error:
+	exit(EXIT_FAILURE);
+}
+
+static int wait_order(int ctl_fd)
+{
+	struct pollfd poll_fd;
+	int ret = 0;
+
+	while (!global_sig_receive) {
+		poll_fd.fd = ctl_fd;
+		poll_fd.events = POLLIN;
+
+		ret = poll(&poll_fd, 1, EVENT_WAIT_MSEC);
+
+		if (global_signal_val) {
+			global_sig_receive = true;
+			pr_info("Receive interrupt %d\n", global_signal_val);
+
+			/* Wakes rw-threads when they are sleeping */
+			if (!global_run_operation)
+				pthread_cond_broadcast(&cond_wakeup);
+
+			ret = -1;
+			break;
+		}
+
+		if (ret < 0) {
+			pr_err("Polling error\n");
+			goto error;
+		}
+
+		if (ret)
+			break;
+	};
+
+	return ret;
+
+error:
+	exit(EXIT_FAILURE);
+}
+
+/*
+ * contol read/write threads by handling global_run_operation
+ */
+void *rw_ctl_loop(int ctl_fd)
+{
+	ssize_t rlen;
+	char buf[HOST_MSG_SIZE];
+	int ret;
+
+	/* Setup signal handlers */
+	signal(SIGTERM, signal_handler);
+	signal(SIGINT, signal_handler);
+	signal(SIGQUIT, signal_handler);
+
+	while (!global_sig_receive) {
+
+		ret = wait_order(ctl_fd);
+		if (ret < 0)
+			break;
+
+		rlen = read(ctl_fd, buf, sizeof(buf));
+		if (rlen < 0) {
+			pr_err("read data error in ctl thread\n");
+			goto error;
+		}
+
+		if (rlen == 2 && buf[0] == '1') {
+			/*
+			 * If host writes '1' to a control path,
+			 * this controller wakes all read/write threads.
+			 */
+			global_run_operation = true;
+			pthread_cond_broadcast(&cond_wakeup);
+			pr_debug("Wake up all read/write threads\n");
+		} else if (rlen == 2 && buf[0] == '0') {
+			/*
+			 * If host writes '0' to a control path, read/write
+			 * threads will wait for notification from Host.
+			 */
+			global_run_operation = false;
+			pr_debug("Stop all read/write threads\n");
+		} else
+			pr_info("Invalid host notification: %s\n", buf);
+	}
+
+	return NULL;
+
+error:
+	exit(EXIT_FAILURE);
+}

tools/virtio/virtio-trace/trace-agent-rw.c

@@ -0,0 +1,192 @@
+/*
+ * Read/write thread of a guest agent for virtio-trace
+ *
+ * Copyright (C) 2012 Hitachi, Ltd.
+ * Created by Yoshihiro Yunomae <yoshihiro.yunomae.ez@hitachi.com>
+ *            Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+ *
+ * Licensed under GPL version 2 only.
+ *
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include "trace-agent.h"
+
+#define READ_WAIT_USEC	100000
+
+void *rw_thread_info_new(void)
+{
+	struct rw_thread_info *rw_ti;
+
+	rw_ti = zalloc(sizeof(struct rw_thread_info));
+	if (rw_ti == NULL) {
+		pr_err("rw_thread_info zalloc error\n");
+		exit(EXIT_FAILURE);
+	}
+
+	rw_ti->cpu_num = -1;
+	rw_ti->in_fd = -1;
+	rw_ti->out_fd = -1;
+	rw_ti->read_pipe = -1;
+	rw_ti->write_pipe = -1;
+	rw_ti->pipe_size = PIPE_INIT;
+
+	return rw_ti;
+}
+
+void *rw_thread_init(int cpu, const char *in_path, const char *out_path,
+				bool stdout_flag, unsigned long pipe_size,
+				struct rw_thread_info *rw_ti)
+{
+	int data_pipe[2];
+
+	rw_ti->cpu_num = cpu;
+
+	/* set read(input) fd */
+	rw_ti->in_fd = open(in_path, O_RDONLY);
+	if (rw_ti->in_fd == -1) {
+		pr_err("Could not open in_fd (CPU:%d)\n", cpu);
+		goto error;
+	}
+
+	/* set write(output) fd */
+	if (!stdout_flag) {
+		/* virtio-serial output mode */
+		rw_ti->out_fd = open(out_path, O_WRONLY);
+		if (rw_ti->out_fd == -1) {
+			pr_err("Could not open out_fd (CPU:%d)\n", cpu);
+			goto error;
+		}
+	} else
+		/* stdout mode */
+		rw_ti->out_fd = STDOUT_FILENO;
+
+	if (pipe2(data_pipe, O_NONBLOCK) < 0) {
+		pr_err("Could not create pipe in rw-thread(%d)\n", cpu);
+		goto error;
+	}
+
+	/*
+	 * Size of pipe is 64kB in default based on fs/pipe.c.
+	 * To read/write trace data speedy, pipe size is changed.
+	 */
+	if (fcntl(*data_pipe, F_SETPIPE_SZ, pipe_size) < 0) {
+		pr_err("Could not change pipe size in rw-thread(%d)\n", cpu);
+		goto error;
+	}
+
+	rw_ti->read_pipe = data_pipe[1];
+	rw_ti->write_pipe = data_pipe[0];
+	rw_ti->pipe_size = pipe_size;
+
+	return NULL;
+
+error:
+	exit(EXIT_FAILURE);
+}
+
+/* Bind a thread to a cpu */
+static void bind_cpu(int cpu_num)
+{
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu_num, &mask);
+
+	/* bind my thread to cpu_num by assigning zero to the first argument */
+	if (sched_setaffinity(0, sizeof(mask), &mask) == -1)
+		pr_err("Could not set CPU#%d affinity\n", (int)cpu_num);
+}
+
+static void *rw_thread_main(void *thread_info)
+{
+	ssize_t rlen, wlen;
+	ssize_t ret;
+	struct rw_thread_info *ts = (struct rw_thread_info *)thread_info;
+
+	bind_cpu(ts->cpu_num);
+
+	while (1) {
+		/* Wait for a read order of trace data by Host OS */
+		if (!global_run_operation) {
+			pthread_mutex_lock(&mutex_notify);
+			pthread_cond_wait(&cond_wakeup, &mutex_notify);
+			pthread_mutex_unlock(&mutex_notify);
+		}
+
+		if (global_sig_receive)
+			break;
+
+		/*
+		 * Each thread read trace_pipe_raw of each cpu bounding the
+		 * thread, so contention of multi-threads does not occur.
+		 */
+		rlen = splice(ts->in_fd, NULL, ts->read_pipe, NULL,
+				ts->pipe_size, SPLICE_F_MOVE | SPLICE_F_MORE);
+
+		if (rlen < 0) {
+			pr_err("Splice_read in rw-thread(%d)\n", ts->cpu_num);
+			goto error;
+		} else if (rlen == 0) {
+			/*
+			 * If trace data do not exist or are unreadable not
+			 * for exceeding the page size, splice_read returns
+			 * NULL. Then, this waits for being filled the data in a
+			 * ring-buffer.
+			 */
+			usleep(READ_WAIT_USEC);
+			pr_debug("Read retry(cpu:%d)\n", ts->cpu_num);
+			continue;
+		}
+
+		wlen = 0;
+
+		do {
+			ret = splice(ts->write_pipe, NULL, ts->out_fd, NULL,
+					rlen - wlen,
+					SPLICE_F_MOVE | SPLICE_F_MORE);
+
+			if (ret < 0) {
+				pr_err("Splice_write in rw-thread(%d)\n",
+								ts->cpu_num);
+				goto error;
+			} else if (ret == 0)
+				/*
+				 * When host reader is not in time for reading
+				 * trace data, guest will be stopped. This is
+				 * because char dev in QEMU is not supported
+				 * non-blocking mode. Then, writer might be
+				 * sleep in that case.
+				 * This sleep will be removed by supporting
+				 * non-blocking mode.
+				 */
+				sleep(1);
+			wlen += ret;
+		} while (wlen < rlen);
+	}
+
+	return NULL;
+
+error:
+	exit(EXIT_FAILURE);
+}
+
+
+pthread_t rw_thread_run(struct rw_thread_info *rw_ti)
+{
+	int ret;
+	pthread_t rw_thread_per_cpu;
+
+	ret = pthread_create(&rw_thread_per_cpu, NULL, rw_thread_main, rw_ti);
+	if (ret != 0) {
+		pr_err("Could not create a rw thread(%d)\n", rw_ti->cpu_num);
+		exit(EXIT_FAILURE);
+	}
+
+	return rw_thread_per_cpu;
+}

tools/virtio/virtio-trace/trace-agent.c

@@ -0,0 +1,270 @@
+/*
+ * Guest agent for virtio-trace
+ *
+ * Copyright (C) 2012 Hitachi, Ltd.
+ * Created by Yoshihiro Yunomae <yoshihiro.yunomae.ez@hitachi.com>
+ *            Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+ *
+ * Licensed under GPL version 2 only.
+ *
+ */
+
+#define _GNU_SOURCE
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include "trace-agent.h"
+
+#define PAGE_SIZE		(sysconf(_SC_PAGE_SIZE))
+#define PIPE_DEF_BUFS		16
+#define PIPE_MIN_SIZE		(PAGE_SIZE*PIPE_DEF_BUFS)
+#define PIPE_MAX_SIZE		(1024*1024)
+#define READ_PATH_FMT	\
+		"/sys/kernel/debug/tracing/per_cpu/cpu%d/trace_pipe_raw"
+#define WRITE_PATH_FMT		"/dev/virtio-ports/trace-path-cpu%d"
+#define CTL_PATH		"/dev/virtio-ports/agent-ctl-path"
+
+pthread_mutex_t mutex_notify = PTHREAD_MUTEX_INITIALIZER;
+pthread_cond_t cond_wakeup = PTHREAD_COND_INITIALIZER;
+
+static int get_total_cpus(void)
+{
+	int nr_cpus = (int)sysconf(_SC_NPROCESSORS_CONF);
+
+	if (nr_cpus <= 0) {
+		pr_err("Could not read cpus\n");
+		goto error;
+	} else if (nr_cpus > MAX_CPUS) {
+		pr_err("Exceed max cpus(%d)\n", (int)MAX_CPUS);
+		goto error;
+	}
+
+	return nr_cpus;
+
+error:
+	exit(EXIT_FAILURE);
+}
+
+static void *agent_info_new(void)
+{
+	struct agent_info *s;
+	int i;
+
+	s = zalloc(sizeof(struct agent_info));
+	if (s == NULL) {
+		pr_err("agent_info zalloc error\n");
+		exit(EXIT_FAILURE);
+	}
+
+	s->pipe_size = PIPE_INIT;
+	s->use_stdout = false;
+	s->cpus = get_total_cpus();
+	s->ctl_fd = -1;
+
+	/* read/write threads init */
+	for (i = 0; i < s->cpus; i++)
+		s->rw_ti[i] = rw_thread_info_new();
+
+	return s;
+}
+
+static unsigned long parse_size(const char *arg)
+{
+	unsigned long value, round;
+	char *ptr;
+
+	value = strtoul(arg, &ptr, 10);
+	switch (*ptr) {
+	case 'K': case 'k':
+		value <<= 10;
+		break;
+	case 'M': case 'm':
+		value <<= 20;
+		break;
+	default:
+		break;
+	}
+
+	if (value > PIPE_MAX_SIZE) {
+		pr_err("Pipe size must be less than 1MB\n");
+		goto error;
+	} else if (value < PIPE_MIN_SIZE) {
+		pr_err("Pipe size must be over 64KB\n");
+		goto error;
+	}
+
+	/* Align buffer size with page unit */
+	round = value & (PAGE_SIZE - 1);
+	value = value - round;
+
+	return value;
+error:
+	return 0;
+}
+
+static void usage(char const *prg)
+{
+	pr_err("usage: %s [-h] [-o] [-s <size of pipe>]\n", prg);
+}
+
+static const char *make_path(int cpu_num, bool this_is_write_path)
+{
+	int ret;
+	char *buf;
+
+	buf = zalloc(PATH_MAX);
+	if (buf == NULL) {
+		pr_err("Could not allocate buffer\n");
+		goto error;
+	}
+
+	if (this_is_write_path)
+		/* write(output) path */
+		ret = snprintf(buf, PATH_MAX, WRITE_PATH_FMT, cpu_num);
+	else
+		/* read(input) path */
+		ret = snprintf(buf, PATH_MAX, READ_PATH_FMT, cpu_num);
+
+	if (ret <= 0) {
+		pr_err("Failed to generate %s path(CPU#%d):%d\n",
+			this_is_write_path ? "read" : "write", cpu_num, ret);
+		goto error;
+	}
+
+	return buf;
+
+error:
+	free(buf);
+	return NULL;
+}
+
+static const char *make_input_path(int cpu_num)
+{
+	return make_path(cpu_num, false);
+}
+
+static const char *make_output_path(int cpu_num)
+{
+	return make_path(cpu_num, true);
+}
+
+static void *agent_info_init(struct agent_info *s)
+{
+	int cpu;
+	const char *in_path = NULL;
+	const char *out_path = NULL;
+
+	/* init read/write threads */
+	for (cpu = 0; cpu < s->cpus; cpu++) {
+		/* set read(input) path per read/write thread */
+		in_path = make_input_path(cpu);
+		if (in_path == NULL)
+			goto error;
+
+		/* set write(output) path per read/write thread*/
+		if (!s->use_stdout) {
+			out_path = make_output_path(cpu);
+			if (out_path == NULL)
+				goto error;
+		} else
+			/* stdout mode */
+			pr_debug("stdout mode\n");
+
+		rw_thread_init(cpu, in_path, out_path, s->use_stdout,
+						s->pipe_size, s->rw_ti[cpu]);
+	}
+
+	/* init controller of read/write threads */
+	s->ctl_fd = rw_ctl_init((const char *)CTL_PATH);
+
+	return NULL;
+
+error:
+	exit(EXIT_FAILURE);
+}
+
+static void *parse_args(int argc, char *argv[], struct agent_info *s)
+{
+	int cmd;
+	unsigned long size;
+
+	while ((cmd = getopt(argc, argv, "hos:")) != -1) {
+		switch (cmd) {
+		/* stdout mode */
+		case 'o':
+			s->use_stdout = true;
+			break;
+		/* size of pipe */
+		case 's':
+			size = parse_size(optarg);
+			if (size == 0)
+				goto error;
+			s->pipe_size = size;
+			break;
+		case 'h':
+		default:
+			usage(argv[0]);
+			goto error;
+		}
+	}
+
+	agent_info_init(s);
+
+	return NULL;
+
+error:
+	exit(EXIT_FAILURE);
+}
+
+static void agent_main_loop(struct agent_info *s)
+{
+	int cpu;
+	pthread_t rw_thread_per_cpu[MAX_CPUS];
+
+	/* Start all read/write threads */
+	for (cpu = 0; cpu < s->cpus; cpu++)
+		rw_thread_per_cpu[cpu] = rw_thread_run(s->rw_ti[cpu]);
+
+	rw_ctl_loop(s->ctl_fd);
+
+	/* Finish all read/write threads */
+	for (cpu = 0; cpu < s->cpus; cpu++) {
+		int ret;
+
+		ret = pthread_join(rw_thread_per_cpu[cpu], NULL);
+		if (ret != 0) {
+			pr_err("pthread_join() error:%d (cpu %d)\n", ret, cpu);
+			exit(EXIT_FAILURE);
+		}
+	}
+}
+
+static void agent_info_free(struct agent_info *s)
+{
+	int i;
+
+	close(s->ctl_fd);
+	for (i = 0; i < s->cpus; i++) {
+		close(s->rw_ti[i]->in_fd);
+		close(s->rw_ti[i]->out_fd);
+		close(s->rw_ti[i]->read_pipe);
+		close(s->rw_ti[i]->write_pipe);
+		free(s->rw_ti[i]);
+	}
+	free(s);
+}
+
+int main(int argc, char *argv[])
+{
+	struct agent_info *s = NULL;
+
+	s = agent_info_new();
+	parse_args(argc, argv, s);
+
+	agent_main_loop(s);
+
+	agent_info_free(s);
+
+	return 0;
+}

tools/virtio/virtio-trace/trace-agent.h

@@ -0,0 +1,75 @@
+#ifndef __TRACE_AGENT_H__
+#define __TRACE_AGENT_H__
+#include <pthread.h>
+#include <stdbool.h>
+
+#define MAX_CPUS	256
+#define PIPE_INIT       (1024*1024)
+
+/*
+ * agent_info - structure managing total information of guest agent
+ * @pipe_size:	size of pipe (default 1MB)
+ * @use_stdout:	set to true when o option is added (default false)
+ * @cpus:	total number of CPUs
+ * @ctl_fd:	fd of control path, /dev/virtio-ports/agent-ctl-path
+ * @rw_ti:	structure managing information of read/write threads
+ */
+struct agent_info {
+	unsigned long pipe_size;
+	bool use_stdout;
+	int cpus;
+	int ctl_fd;
+	struct rw_thread_info *rw_ti[MAX_CPUS];
+};
+
+/*
+ * rw_thread_info - structure managing a read/write thread a cpu
+ * @cpu_num:	cpu number operating this read/write thread
+ * @in_fd:	fd of reading trace data path in cpu_num
+ * @out_fd:	fd of writing trace data path in cpu_num
+ * @read_pipe:	fd of read pipe
+ * @write_pipe:	fd of write pipe
+ * @pipe_size:	size of pipe (default 1MB)
+ */
+struct rw_thread_info {
+	int cpu_num;
+	int in_fd;
+	int out_fd;
+	int read_pipe;
+	int write_pipe;
+	unsigned long pipe_size;
+};
+
+/* use for stopping rw threads */
+extern bool global_sig_receive;
+
+/* use for notification */
+extern bool global_run_operation;
+extern pthread_mutex_t mutex_notify;
+extern pthread_cond_t cond_wakeup;
+
+/* for controller of read/write threads */
+extern int rw_ctl_init(const char *ctl_path);
+extern void *rw_ctl_loop(int ctl_fd);
+
+/* for trace read/write thread */
+extern void *rw_thread_info_new(void);
+extern void *rw_thread_init(int cpu, const char *in_path, const char *out_path,
+			bool stdout_flag, unsigned long pipe_size,
+			struct rw_thread_info *rw_ti);
+extern pthread_t rw_thread_run(struct rw_thread_info *rw_ti);
+
+static inline void *zalloc(size_t size)
+{
+	return calloc(1, size);
+}
+
+#define pr_err(format, ...) fprintf(stderr, format, ## __VA_ARGS__)
+#define pr_info(format, ...) fprintf(stdout, format, ## __VA_ARGS__)
+#ifdef DEBUG
+#define pr_debug(format, ...) fprintf(stderr, format, ## __VA_ARGS__)
+#else
+#define pr_debug(format, ...) do {} while (0)
+#endif
+
+#endif /*__TRACE_AGENT_H__*/

tools/virtio/virtio_test.c

@@ -0,0 +1,290 @@
+#define _GNU_SOURCE
+#include <getopt.h>
+#include <string.h>
+#include <poll.h>
+#include <sys/eventfd.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#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;
+	int num;
+	int idx;
+	void *ring;
+	/* copy used for control */
+	struct vring vring;
+	struct virtqueue *vq;
+};
+
+struct vdev_info {
+	struct virtio_device vdev;
+	int control;
+	struct pollfd fds[1];
+	struct vq_info vqs[1];
+	int nvqs;
+	void *buf;
+	size_t buf_size;
+	struct vhost_memory *mem;
+};
+
+bool vq_notify(struct virtqueue *vq)
+{
+	struct vq_info *info = vq->priv;
+	unsigned long long v = 1;
+	int r;
+	r = write(info->kick, &v, sizeof v);
+	assert(r == sizeof v);
+	return true;
+}
+
+void vq_callback(struct virtqueue *vq)
+{
+}
+
+
+void vhost_vq_setup(struct vdev_info *dev, struct vq_info *info)
+{
+	struct vhost_vring_state state = { .index = info->idx };
+	struct vhost_vring_file file = { .index = info->idx };
+	unsigned long long features = dev->vdev.features[0];
+	struct vhost_vring_addr addr = {
+		.index = info->idx,
+		.desc_user_addr = (uint64_t)(unsigned long)info->vring.desc,
+		.avail_user_addr = (uint64_t)(unsigned long)info->vring.avail,
+		.used_user_addr = (uint64_t)(unsigned long)info->vring.used,
+	};
+	int r;
+	r = ioctl(dev->control, VHOST_SET_FEATURES, &features);
+	assert(r >= 0);
+	state.num = info->vring.num;
+	r = ioctl(dev->control, VHOST_SET_VRING_NUM, &state);
+	assert(r >= 0);
+	state.num = 0;
+	r = ioctl(dev->control, VHOST_SET_VRING_BASE, &state);
+	assert(r >= 0);
+	r = ioctl(dev->control, VHOST_SET_VRING_ADDR, &addr);
+	assert(r >= 0);
+	file.fd = info->kick;
+	r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file);
+	assert(r >= 0);
+	file.fd = info->call;
+	r = ioctl(dev->control, VHOST_SET_VRING_CALL, &file);
+	assert(r >= 0);
+}
+
+static void vq_info_add(struct vdev_info *dev, int num)
+{
+	struct vq_info *info = &dev->vqs[dev->nvqs];
+	int r;
+	info->idx = dev->nvqs;
+	info->kick = eventfd(0, EFD_NONBLOCK);
+	info->call = eventfd(0, EFD_NONBLOCK);
+	r = posix_memalign(&info->ring, 4096, vring_size(num, 4096));
+	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->idx,
+				       info->vring.num, 4096, &dev->vdev,
+				       true, info->ring,
+				       vq_notify, vq_callback, "test");
+	assert(info->vq);
+	info->vq->priv = info;
+	vhost_vq_setup(dev, info);
+	dev->fds[info->idx].fd = info->call;
+	dev->fds[info->idx].events = POLLIN;
+	dev->nvqs++;
+}
+
+static void vdev_info_init(struct vdev_info* dev, unsigned long long features)
+{
+	int r;
+	memset(dev, 0, sizeof *dev);
+	dev->vdev.features[0] = features;
+	dev->vdev.features[1] = features >> 32;
+	dev->buf_size = 1024;
+	dev->buf = malloc(dev->buf_size);
+	assert(dev->buf);
+        dev->control = open("/dev/vhost-test", O_RDWR);
+	assert(dev->control >= 0);
+	r = ioctl(dev->control, VHOST_SET_OWNER, NULL);
+	assert(r >= 0);
+	dev->mem = malloc(offsetof(struct vhost_memory, regions) +
+			  sizeof dev->mem->regions[0]);
+	assert(dev->mem);
+	memset(dev->mem, 0, offsetof(struct vhost_memory, regions) +
+                          sizeof dev->mem->regions[0]);
+	dev->mem->nregions = 1;
+	dev->mem->regions[0].guest_phys_addr = (long)dev->buf;
+	dev->mem->regions[0].userspace_addr = (long)dev->buf;
+	dev->mem->regions[0].memory_size = dev->buf_size;
+	r = ioctl(dev->control, VHOST_SET_MEM_TABLE, dev->mem);
+	assert(r >= 0);
+}
+
+/* TODO: this is pretty bad: we get a cache line bounce
+ * for the wait queue on poll and another one on read,
+ * plus the read which is there just to clear the
+ * current state. */
+static void wait_for_interrupt(struct vdev_info *dev)
+{
+	int i;
+	unsigned long long val;
+	poll(dev->fds, dev->nvqs, -1);
+	for (i = 0; i < dev->nvqs; ++i)
+		if (dev->fds[i].revents & POLLIN) {
+			read(dev->fds[i].fd, &val, sizeof val);
+		}
+}
+
+static void run_test(struct vdev_info *dev, struct vq_info *vq,
+		     bool delayed, int bufs)
+{
+	struct scatterlist sl;
+	long started = 0, completed = 0;
+	long completed_before;
+	int r, test = 1;
+	unsigned len;
+	long long spurious = 0;
+	r = ioctl(dev->control, VHOST_TEST_RUN, &test);
+	assert(r >= 0);
+	for (;;) {
+		virtqueue_disable_cb(vq->vq);
+		completed_before = completed;
+		do {
+			if (started < bufs) {
+				sg_init_one(&sl, dev->buf, dev->buf_size);
+				r = virtqueue_add_outbuf(vq->vq, &sl, 1,
+							 dev->buf + started,
+							 GFP_ATOMIC);
+				if (likely(r == 0)) {
+					++started;
+					if (unlikely(!virtqueue_kick(vq->vq)))
+						r = -1;
+				}
+			} else
+				r = -1;
+
+			/* Flush out completed bufs if any */
+			if (virtqueue_get_buf(vq->vq, &len)) {
+				++completed;
+				r = 0;
+			}
+
+		} while (r == 0);
+		if (completed == completed_before)
+			++spurious;
+		assert(completed <= bufs);
+		assert(started <= bufs);
+		if (completed == bufs)
+			break;
+		if (delayed) {
+			if (virtqueue_enable_cb_delayed(vq->vq))
+				wait_for_interrupt(dev);
+		} else {
+			if (virtqueue_enable_cb(vq->vq))
+				wait_for_interrupt(dev);
+		}
+	}
+	test = 0;
+	r = ioctl(dev->control, VHOST_TEST_RUN, &test);
+	assert(r >= 0);
+	fprintf(stderr, "spurious wakeus: 0x%llx\n", spurious);
+}
+
+const char optstring[] = "h";
+const struct option longopts[] = {
+	{
+		.name = "help",
+		.val = 'h',
+	},
+	{
+		.name = "event-idx",
+		.val = 'E',
+	},
+	{
+		.name = "no-event-idx",
+		.val = 'e',
+	},
+	{
+		.name = "indirect",
+		.val = 'I',
+	},
+	{
+		.name = "no-indirect",
+		.val = 'i',
+	},
+	{
+		.name = "delayed-interrupt",
+		.val = 'D',
+	},
+	{
+		.name = "no-delayed-interrupt",
+		.val = 'd',
+	},
+	{
+	}
+};
+
+static void help(void)
+{
+	fprintf(stderr, "Usage: virtio_test [--help]"
+		" [--no-indirect]"
+		" [--no-event-idx]"
+		" [--delayed-interrupt]"
+		"\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct vdev_info dev;
+	unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+		(1ULL << VIRTIO_RING_F_EVENT_IDX);
+	int o;
+	bool delayed = false;
+
+	for (;;) {
+		o = getopt_long(argc, argv, optstring, longopts, NULL);
+		switch (o) {
+		case -1:
+			goto done;
+		case '?':
+			help();
+			exit(2);
+		case 'e':
+			features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX);
+			break;
+		case 'h':
+			help();
+			goto done;
+		case 'i':
+			features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC);
+			break;
+		case 'D':
+			delayed = true;
+			break;
+		default:
+			assert(0);
+			break;
+		}
+	}
+
+done:
+	vdev_info_init(&dev, features);
+	vq_info_add(&dev, 256);
+	run_test(&dev, &dev.vqs[0], delayed, 0x100000);
+	return 0;
+}

tools/virtio/vringh_test.c

@@ -0,0 +1,746 @@
+/* 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 bool 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 bool parallel_notify_host(struct virtqueue *vq)
+{
+	int rc;
+	struct guest_virtio_device *gvdev;
+
+	gvdev = container_of(vq->vdev, struct guest_virtio_device, vdev);
+	rc = write(gvdev->to_host_fd, "", 1);
+	if (rc < 0)
+		return false;
+	gvdev->notifies++;
+	return true;
+}
+
+static bool no_notify_host(struct virtqueue *vq)
+{
+	return true;
+}
+
+#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;
+}