This is mainly to test the drivers/vhost/vringh.c code, but it also
uses the drivers/virtio/virtio_ring.c code for the guest side.

Usage for testing the basic implementation:

        ./vringh_test
        # Test with indirect descriptors
        ./vringh_test --indirect
        # Test with indirect descriptors and event indexex
        ./vringh_test --indirect --eventidx

You can run a parallel stress test by adding --parallel to any of the
above options.

eg ./vringh_test --parallel:
        Using CPUS 0 and 3
        Guest: notified 10107974, pinged 107970
        Host: notified 108158, pinged 3172148
        Time: R=17.659 U=6.640 S=6.640

./vringh_test --eventidx --parallel:
        Using CPUS 0 and 3
        Guest: notified 156357, pinged 156251
        Host: notified 156251, pinged 78179
        Time: R=4.518 U=3.536 S=3.536

Signed-off-by: Rusty Russell <ru...@rustcorp.com.au>
---
 tools/virtio/Makefile      |    6 +-
 tools/virtio/vringh_test.c |  659 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 662 insertions(+), 3 deletions(-)
 create mode 100644 tools/virtio/vringh_test.c

diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile
index d1d442e..e961545 100644
--- a/tools/virtio/Makefile
+++ b/tools/virtio/Makefile
@@ -1,12 +1,12 @@
 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
+CFLAGS += -g -O2 -Wall -I. -I ../../usr/include/ -Wno-pointer-sign 
-fno-strict-overflow -fno-strict-aliasing -Wno-unused-result -MMD
 vpath %.c ../../drivers/virtio
 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
diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c
new file mode 100644
index 0000000..1536b8e
--- /dev/null
+++ b/tools/virtio/vringh_test.c
@@ -0,0 +1,659 @@
+/* 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 <../../drivers/vhost/vringh.c>
+#include <../../drivers/virtio/virtio_ring.c>
+#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++;
+}
+
+#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;
+               }
+       }
+}
+
+static int parallel_test(unsigned long features,
+                        bool (*getrange)(struct vringh *vrh,
+                                         u64 addr, struct vringh_range *r))
+{
+       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;
+
+       /* 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;
+
+               /* 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;
+                       char buf[5];
+                       u16 head;
+                       int rlen, err;
+
+                       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) {
+                               char buf[128];
+
+                               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. */
+                       rlen = vringh_iov_pull_user(&riov, buf, sizeof(buf));
+                       if (rlen < 0)
+                               errx(1, "vringh_iov_pull_user: %i", rlen);
+                       err = vringh_iov_push_user(&wiov, buf, rlen);
+                       if (err != rlen)
+                               errx(1, "vringh_iov_push_user: %i", err);
+                       xfers++;
+                       assert(wiov.i == wiov.used);
+
+                       err = vringh_complete_user(&vrh, head, rlen);
+                       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];
+
+               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, 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[6];
+                       unsigned int num_sg, len;
+                       int *din, *dout, err;
+
+                       /* Consume bufs. */
+                       while ((din = virtqueue_get_buf(vq, &len)) != NULL) {
+                               dout = din + 1;
+                               assert(*dout == *din);
+                               assert(len == 4);
+                               finished++;
+                       }
+
+                       /* Produce a buffer. */
+                       din = data + (xfers % (RINGSIZE + 1)) * 2;
+                       dout = din + 1;
+
+                       *din = xfers;
+                       switch ((xfers / sizeof(*din)) % 3) {
+                       case 0:
+                               /* Nasty three-element sg list. */
+                               sg_init_table(sg, num_sg = 3);
+                               sg_set_buf(&sg[0], (void *)din, 1);
+                               sg_set_buf(&sg[1], (void *)din + 1, 2);
+                               sg_set_buf(&sg[2], (void *)din + 3, 1);
+                               sg_init_table(sg + num_sg, num_sg);
+                               sg_set_buf(&sg[num_sg+0], (void *)dout, 1);
+                               sg_set_buf(&sg[num_sg+1], (void *)dout + 1, 2);
+                               sg_set_buf(&sg[num_sg+2], (void *)dout + 3, 1);
+                               break;
+                       case 1:
+                               sg_init_table(sg, num_sg = 2);
+                               sg_set_buf(&sg[0], (void *)din, 1);
+                               sg_set_buf(&sg[1], (void *)din + 1, 3);
+                               sg_init_table(sg + num_sg, num_sg);
+                               sg_set_buf(&sg[num_sg+0], (void *)dout, 1);
+                               sg_set_buf(&sg[num_sg+1], (void *)dout + 1, 3);
+                               break;
+                       case 2:
+                               sg_init_table(sg, num_sg = 1);
+                               sg_set_buf(&sg[0], (void *)din, 4);
+                               sg_init_table(sg + num_sg, num_sg);
+                               sg_set_buf(&sg[num_sg+0], (void *)dout, 4);
+                               break;
+                       }
+
+                       /* May allocate an indirect, so force it to allocate
+                        * user addr */
+                       __kmalloc_fake = indirects + (xfers % RINGSIZE) * 6;
+                       err = virtqueue_add_buf(vq, sg, num_sg, num_sg, din,
+                                               GFP_KERNEL);
+                       if (err == -ENOSPC) {
+                               char buf[128];
+
+                               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_buf: %i", err);
+
+                       xfers++;
+                       virtqueue_kick(vq);
+               }
+
+               /* Any extra? */
+               while (finished != xfers) {
+                       char buf[128];
+                       int *din, *dout;
+                       unsigned int len;
+
+                       /* Consume bufs. */
+                       din = virtqueue_get_buf(vq, &len);
+                       if (din) {
+                               dout = din + 1;
+                               assert(*dout == *din);
+                               assert(len == 4);
+                               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);
+               return 0;
+       }
+}
+
+int main(int argc, char *argv[])
+{
+       struct virtio_device vdev;
+       struct virtqueue *vq;
+       struct vringh vrh;
+       struct scatterlist guest_sg[RINGSIZE];
+       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);
+
+       getrange = getrange_iov;
+       vdev.features[0] = 0;
+
+       if (argv[1] && strcmp(argv[1], "--indirect") == 0) {
+               vdev.features[0] |= (1 << VIRTIO_RING_F_INDIRECT_DESC);
+               argv++;
+       }
+
+       if (argv[1] && strcmp(argv[1], "--eventidx") == 0) {
+               vdev.features[0] |= (1 << VIRTIO_RING_F_EVENT_IDX);
+               argv++;
+       }
+
+       if (argv[1] && strcmp(argv[1], "--slow") == 0) {
+               getrange = getrange_slow;
+               argv++;
+       }
+
+       if (argv[1] && strcmp(argv[1], "--parallel") == 0)
+               return parallel_test(vdev.features[0], getrange);
+
+       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);
+
+       /* May allocate an indirect, so force it to allocate user addr */
+       __kmalloc_fake = __user_addr_min + vring_size(RINGSIZE, ALIGN);
+       err = virtqueue_add_buf(vq, guest_sg, 1, 1, &err, GFP_KERNEL);
+       if (err)
+               errx(1, "virtqueue_add_buf: %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_buf(vq, guest_sg, RINGSIZE, 0, &err, GFP_KERNEL);
+       if (err)
+               errx(1, "virtqueue_add_buf (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_buf(vq, guest_sg, 1, 0, &err, GFP_KERNEL);
+               if (err)
+                       errx(1, "virtqueue_add_buf (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)) {
+               struct vring_virtqueue *vvq = to_vvq(vq);
+               char *data = __user_addr_max - USER_MEM/4;
+               struct vring_desc *d = __user_addr_max - USER_MEM/2;
+               unsigned int n = vvq->free_head;
+
+               /* Force creation of direct, which we modify. */
+               vvq->indirect = false;
+               
+               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_buf(vq, guest_sg, 4, 0, &err, GFP_KERNEL);
+               if (err)
+                       errx(1, "virtqueue_add_buf (indirect): %i", err);
+
+               /* They're used in order, but double-check... */
+               assert(vvq->vring.desc[n].addr == (unsigned long)d);
+               assert(vvq->vring.desc[n-1].addr == (unsigned long)(d+2));
+               assert(vvq->vring.desc[n-2].addr == (unsigned long)data + 6);
+               assert(vvq->vring.desc[n-3].addr == (unsigned long)(d+3));
+               vvq->vring.desc[n].flags |= VRING_DESC_F_INDIRECT;
+               vvq->vring.desc[n-1].flags |= VRING_DESC_F_INDIRECT;
+               vvq->vring.desc[n-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 != n)
+                       errx(1, "vringh_getdesc_user: head %i not %i", head, n);
+
+               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;
+}
-- 
1.7.10.4

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Reply via email to