virtio: simplify config mechanism.

Previously we used a type/len pair within the config space, but this
seems overkill.  We now simply define a structure which represents the
layout in the config space: the config space can now only be extended
at the end.

The main driver-visible changes:
1) We indicate what fields are present with an explicit feature bit.
2) Virtqueues are explicitly numbered, and not in the config space.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

1 files changed, 105 insertions, 71 deletions

diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 6c8a2386cd50..4df1804169dc 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -34,6 +34,8 @@
 #include <zlib.h>
 #include <assert.h>
 #include <sched.h>
+#include <limits.h>
+#include <stddef.h>
 #include "linux/lguest_launcher.h"
 #include "linux/virtio_config.h"
 #include "linux/virtio_net.h"
@@ -99,13 +101,11 @@ struct device_list
         /* The descriptor page for the devices. */
         u8 *descpage;
 
-        /* The tail of the last descriptor. */
-        unsigned int desc_used;
-
         /* A single linked list of devices. */
         struct device *dev;
-        /* ... And an end pointer so we can easily append new devices */
-        struct device **lastdev;
+        /* And a pointer to the last device for easy append and also for
+         * configuration appending. */
+        struct device *lastdev;
 };
 
 /* The list of Guest devices, based on command line arguments. */
@@ -191,7 +191,7 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
 #define cpu_to_le64(v64) (v64)
 #define le16_to_cpu(v16) (v16)
 #define le32_to_cpu(v32) (v32)
-#define le64_to_cpu(v32) (v64)
+#define le64_to_cpu(v64) (v64)
 
 /*L:100 The Launcher code itself takes us out into userspace, that scary place
  * where pointers run wild and free!  Unfortunately, like most userspace
@@ -986,54 +986,44 @@ static void handle_input(int fd)
  *
  * All devices need a descriptor so the Guest knows it exists, and a "struct
  * device" so the Launcher can keep track of it.  We have common helper
- * routines to allocate them.
- *
- * This routine allocates a new "struct lguest_device_desc" from descriptor
- * table just above the Guest's normal memory.  It returns a pointer to that
- * descriptor. */
-static struct lguest_device_desc *new_dev_desc(u16 type)
-{
-        struct lguest_device_desc *d;
+ * routines to allocate and manage them. */
 
-        /* We only have one page for all the descriptors. */
-        if (devices.desc_used + sizeof(*d) > getpagesize())
-                errx(1, "Too many devices");
-
-        /* We don't need to set config_len or status: page is 0 already. */
-        d = (void *)devices.descpage + devices.desc_used;
-        d->type = type;
-        devices.desc_used += sizeof(*d);
-
-        return d;
+/* The layout of the device page is a "struct lguest_device_desc" followed by a
+ * number of virtqueue descriptors, then two sets of feature bits, then an
+ * array of configuration bytes.  This routine returns the configuration
+ * pointer. */
+static u8 *device_config(const struct device *dev)
+{
+        return (void *)(dev->desc + 1)
+                + dev->desc->num_vq * sizeof(struct lguest_vqconfig)
+                + dev->desc->feature_len * 2;
 }
 
-/* Each device descriptor is followed by some configuration information.
- * Each configuration field looks like: u8 type, u8 len, [... len bytes...].
- *
- * This routine adds a new field to an existing device's descriptor.  It only
- * works for the last device, but that's OK because that's how we use it. */
-static void add_desc_field(struct device *dev, u8 type, u8 len, const void *c)
+/* This routine allocates a new "struct lguest_device_desc" from descriptor
+ * table page just above the Guest's normal memory.  It returns a pointer to
+ * that descriptor. */
+static struct lguest_device_desc *new_dev_desc(u16 type)
 {
-        /* This is the last descriptor, right? */
-        assert(devices.descpage + devices.desc_used
-               == (u8 *)(dev->desc + 1) + dev->desc->config_len);
+        struct lguest_device_desc d = { .type = type };
+        void *p;
 
-        /* We only have one page of device descriptions. */
-        if (devices.desc_used + 2 + len > getpagesize())
-                errx(1, "Too many devices");
+        /* Figure out where the next device config is, based on the last one. */
+        if (devices.lastdev)
+                p = device_config(devices.lastdev)
+                        + devices.lastdev->desc->config_len;
+        else
+                p = devices.descpage;
 
-        /* Copy in the new config header: type then length. */
-        devices.descpage[devices.desc_used++] = type;
-        devices.descpage[devices.desc_used++] = len;
-        memcpy(devices.descpage + devices.desc_used, c, len);
-        devices.desc_used += len;
+        /* We only have one page for all the descriptors. */
+        if (p + sizeof(d) > (void *)devices.descpage + getpagesize())
+                errx(1, "Too many devices");
 
-        /* Update the device descriptor length: two byte head then data. */
-        dev->desc->config_len += 2 + len;
+        /* p might not be aligned, so we memcpy in. */
+        return memcpy(p, &d, sizeof(d));
 }
 
-/* This routine adds a virtqueue to a device.  We specify how many descriptors
- * the virtqueue is to have. */
+/* Each device descriptor is followed by the description of its virtqueues.  We
+ * specify how many descriptors the virtqueue is to have. */
 static void add_virtqueue(struct device *dev, unsigned int num_descs,
                           void (*handle_output)(int fd, struct virtqueue *me))
 {
@@ -1059,9 +1049,15 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
         /* Initialize the vring. */
         vring_init(&vq->vring, num_descs, p, getpagesize());
 
-        /* Add the configuration information to this device's descriptor. */
-        add_desc_field(dev, VIRTIO_CONFIG_F_VIRTQUEUE,
-                       sizeof(vq->config), &vq->config);
+        /* Append virtqueue to this device's descriptor.  We use
+         * device_config() to get the end of the device's current virtqueues;
+         * we check that we haven't added any config or feature information
+         * yet, otherwise we'd be overwriting them. */
+        assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0);
+        memcpy(device_config(dev), &vq->config, sizeof(vq->config));
+        dev->desc->num_vq++;
+
+        verbose("Virtqueue page %#lx\n", to_guest_phys(p));
 
         /* Add to tail of list, so dev->vq is first vq, dev->vq->next is
          * second.  */
@@ -1077,6 +1073,37 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
                 vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;
 }
 
+/* The virtqueue descriptors are followed by feature bytes. */
+static void add_feature(struct device *dev, unsigned bit)
+{
+        u8 *features;
+
+        /* We can't extend the feature bits once we've added config bytes */
+        if (dev->desc->feature_len <= bit / CHAR_BIT) {
+                assert(dev->desc->config_len == 0);
+                dev->desc->feature_len = (bit / CHAR_BIT) + 1;
+        }
+
+        features = (u8 *)(dev->desc + 1)
+                + dev->desc->num_vq * sizeof(struct lguest_vqconfig);
+
+        features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT));
+}
+
+/* This routine sets the configuration fields for an existing device's
+ * descriptor.  It only works for the last device, but that's OK because that's
+ * how we use it. */
+static void set_config(struct device *dev, unsigned len, const void *conf)
+{
+        /* Check we haven't overflowed our single page. */
+        if (device_config(dev) + len > devices.descpage + getpagesize())
+                errx(1, "Too many devices");
+
+        /* Copy in the config information, and store the length. */
+        memcpy(device_config(dev), conf, len);
+        dev->desc->config_len = len;
+}
+
 /* This routine does all the creation and setup of a new device, including
  * calling new_dev_desc() to allocate the descriptor and device memory. */
 static struct device *new_device(const char *name, u16 type, int fd,
@@ -1084,14 +1111,6 @@ static struct device *new_device(const char *name, u16 type, int fd,
 {
         struct device *dev = malloc(sizeof(*dev));
 
-        /* Append to device list.  Prepending to a single-linked list is
-         * easier, but the user expects the devices to be arranged on the bus
-         * in command-line order.  The first network device on the command line
-         * is eth0, the first block device /dev/vda, etc. */
-        *devices.lastdev = dev;
-        dev->next = NULL;
-        devices.lastdev = &dev->next;
-
         /* Now we populate the fields one at a time. */
         dev->fd = fd;
         /* If we have an input handler for this file descriptor, then we add it
@@ -1102,6 +1121,17 @@ static struct device *new_device(const char *name, u16 type, int fd,
         dev->handle_input = handle_input;
         dev->name = name;
         dev->vq = NULL;
+
+        /* Append to device list.  Prepending to a single-linked list is
+         * easier, but the user expects the devices to be arranged on the bus
+         * in command-line order.  The first network device on the command line
+         * is eth0, the first block device /dev/vda, etc. */
+        if (devices.lastdev)
+                devices.lastdev->next = dev;
+        else
+                devices.dev = dev;
+        devices.lastdev = dev;
+
         return dev;
 }
 
@@ -1226,7 +1256,7 @@ static void setup_tun_net(const char *arg)
         int netfd, ipfd;
         u32 ip;
         const char *br_name = NULL;
-        u8 hwaddr[6];
+        struct virtio_net_config conf;
 
         /* We open the /dev/net/tun device and tell it we want a tap device.  A
          * tap device is like a tun device, only somehow different.  To tell
@@ -1265,12 +1295,13 @@ static void setup_tun_net(const char *arg)
                 ip = str2ip(arg);
 
         /* Set up the tun device, and get the mac address for the interface. */
-        configure_device(ipfd, ifr.ifr_name, ip, hwaddr);
+        configure_device(ipfd, ifr.ifr_name, ip, conf.mac);
 
         /* Tell Guest what MAC address to use. */
-        add_desc_field(dev, VIRTIO_CONFIG_NET_MAC_F, sizeof(hwaddr), hwaddr);
+        add_feature(dev, VIRTIO_NET_F_MAC);
+        set_config(dev, sizeof(conf), &conf);
 
-        /* We don't seed the socket any more; setup is done. */
+        /* We don't need the socket any more; setup is done. */
         close(ipfd);
 
         verbose("device %u: tun net %u.%u.%u.%u\n",
@@ -1458,8 +1489,7 @@ static void setup_block_file(const char *filename)
         struct device *dev;
         struct vblk_info *vblk;
         void *stack;
-        u64 cap;
-        unsigned int val;
+        struct virtio_blk_config conf;
 
         /* This is the pipe the I/O thread will use to tell us I/O is done. */
         pipe(p);
@@ -1477,14 +1507,18 @@ static void setup_block_file(const char *filename)
         vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
         vblk->len = lseek64(vblk->fd, 0, SEEK_END);
 
+        /* We support barriers. */
+        add_feature(dev, VIRTIO_BLK_F_BARRIER);
+
         /* Tell Guest how many sectors this device has. */
-        cap = cpu_to_le64(vblk->len / 512);
-        add_desc_field(dev, VIRTIO_CONFIG_BLK_F_CAPACITY, sizeof(cap), &cap);
+        conf.capacity = cpu_to_le64(vblk->len / 512);
 
         /* Tell Guest not to put in too many descriptors at once: two are used
          * for the in and out elements. */
-        val = cpu_to_le32(VIRTQUEUE_NUM - 2);
-        add_desc_field(dev, VIRTIO_CONFIG_BLK_F_SEG_MAX, sizeof(val), &val);
+        add_feature(dev, VIRTIO_BLK_F_SEG_MAX);
+        conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2);
+
+        set_config(dev, sizeof(conf), &conf);
 
         /* The I/O thread writes to this end of the pipe when done. */
         vblk->done_fd = p[1];
@@ -1505,7 +1539,7 @@ static void setup_block_file(const char *filename)
         close(vblk->workpipe[0]);
 
         verbose("device %u: virtblock %llu sectors\n",
-                devices.device_num, cap);
+                devices.device_num, le64_to_cpu(conf.capacity));
 }
 /* That's the end of device setup. :*/
 
@@ -1610,12 +1644,12 @@ int main(int argc, char *argv[])
         /* First we initialize the device list.  Since console and network
          * device receive input from a file descriptor, we keep an fdset
          * (infds) and the maximum fd number (max_infd) with the head of the
-         * list.  We also keep a pointer to the last device, for easy appending
-         * to the list.  Finally, we keep the next interrupt number to hand out
-         * (1: remember that 0 is used by the timer). */
+         * list.  We also keep a pointer to the last device.  Finally, we keep
+         * the next interrupt number to hand out (1: remember that 0 is used by
+         * the timer). */
         FD_ZERO(&devices.infds);
         devices.max_infd = -1;
-        devices.lastdev = &devices.dev;
+        devices.lastdev = NULL;
         devices.next_irq = 1;
 
         cpu_id = 0;