Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-f…

…or-linus

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
  lguest: make Launcher see device status updates
  lguest: remove bogus NULL cpu check
  lguest: avoid using NR_CPUS as a bounds check.
  virtio: add virtio disk geometry feature
  virtio: explicit advertisement of driver features
  virtio: change config to guest endian.
  virtio: finer-grained features for virtio_net
  virtio: wean net driver off NETDEV_TX_BUSY
  virtio-blk: fix remove oops
  virtio: fix scatterlist sizing in net driver.
  virtio: de-structify virtio_block status byte
  virtio: export more headers to userspace
  virtio: fix sparse return void-valued expression warnings
  virtio: fix tx_ stats in virtio_net
  virtio: ignore corrupted virtqueues rather than spinning.

Documentation/lguest/lguest.c

@@ -131,6 +131,9 @@ struct device
 	/* Any queues attached to this device */
 	struct virtqueue *vq;
 
+	/* Handle status being finalized (ie. feature bits stable). */
+	void (*ready)(struct device *me);
+
 	/* Device-specific data. */
 	void *priv;
 };
@@ -925,24 +928,40 @@ static void enable_fd(int fd, struct virtqueue *vq)
 	write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
 }
 
-/* When the Guest asks us to reset a device, it's is fairly easy. */
-static void reset_device(struct device *dev)
+/* When the Guest tells us they updated the status field, we handle it. */
+static void update_device_status(struct device *dev)
 {
 	struct virtqueue *vq;
 
-	verbose("Resetting device %s\n", dev->name);
-	/* Clear the status. */
-	dev->desc->status = 0;
+	/* This is a reset. */
+	if (dev->desc->status == 0) {
+		verbose("Resetting device %s\n", dev->name);
 
-	/* Clear any features they've acked. */
-	memset(get_feature_bits(dev) + dev->desc->feature_len, 0,
-	       dev->desc->feature_len);
+		/* Clear any features they've acked. */
+		memset(get_feature_bits(dev) + dev->desc->feature_len, 0,
+		       dev->desc->feature_len);
 
-	/* Zero out the virtqueues. */
-	for (vq = dev->vq; vq; vq = vq->next) {
-		memset(vq->vring.desc, 0,
-		       vring_size(vq->config.num, getpagesize()));
-		vq->last_avail_idx = 0;
+		/* Zero out the virtqueues. */
+		for (vq = dev->vq; vq; vq = vq->next) {
+			memset(vq->vring.desc, 0,
+			       vring_size(vq->config.num, getpagesize()));
+			vq->last_avail_idx = 0;
+		}
+	} else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
+		warnx("Device %s configuration FAILED", dev->name);
+	} else if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
+		unsigned int i;
+
+		verbose("Device %s OK: offered", dev->name);
+		for (i = 0; i < dev->desc->feature_len; i++)
+			verbose(" %08x", get_feature_bits(dev)[i]);
+		verbose(", accepted");
+		for (i = 0; i < dev->desc->feature_len; i++)
+			verbose(" %08x", get_feature_bits(dev)
+				[dev->desc->feature_len+i]);
+
+		if (dev->ready)
+			dev->ready(dev);
 	}
 }
 
@@ -954,9 +973,9 @@ static void handle_output(int fd, unsigned long addr)
 
 	/* Check each device and virtqueue. */
 	for (i = devices.dev; i; i = i->next) {
-		/* Notifications to device descriptors reset the device. */
+		/* Notifications to device descriptors update device status. */
 		if (from_guest_phys(addr) == i->desc) {
-			reset_device(i);
+			update_device_status(i);
 			return;
 		}
 
@@ -1170,6 +1189,7 @@ static struct device *new_device(const char *name, u16 type, int fd,
 	dev->handle_input = handle_input;
 	dev->name = name;
 	dev->vq = NULL;
+	dev->ready = 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
@@ -1398,7 +1418,7 @@ static bool service_io(struct device *dev)
 	struct vblk_info *vblk = dev->priv;
 	unsigned int head, out_num, in_num, wlen;
 	int ret;
-	struct virtio_blk_inhdr *in;
+	u8 *in;
 	struct virtio_blk_outhdr *out;
 	struct iovec iov[dev->vq->vring.num];
 	off64_t off;
@@ -1416,7 +1436,7 @@ static bool service_io(struct device *dev)
 		     head, out_num, in_num);
 
 	out = convert(&iov[0], struct virtio_blk_outhdr);
-	in = convert(&iov[out_num+in_num-1], struct virtio_blk_inhdr);
+	in = convert(&iov[out_num+in_num-1], u8);
 	off = out->sector * 512;
 
 	/* The block device implements "barriers", where the Guest indicates
@@ -1430,7 +1450,7 @@ static bool service_io(struct device *dev)
 	 * It'd be nice if we supported eject, for example, but we don't. */
 	if (out->type & VIRTIO_BLK_T_SCSI_CMD) {
 		fprintf(stderr, "Scsi commands unsupported\n");
-		in->status = VIRTIO_BLK_S_UNSUPP;
+		*in = VIRTIO_BLK_S_UNSUPP;
 		wlen = sizeof(*in);
 	} else if (out->type & VIRTIO_BLK_T_OUT) {
 		/* Write */
@@ -1453,7 +1473,7 @@ static bool service_io(struct device *dev)
 			errx(1, "Write past end %llu+%u", off, ret);
 		}
 		wlen = sizeof(*in);
-		in->status = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
 	} else {
 		/* Read */
 
@@ -1466,10 +1486,10 @@ static bool service_io(struct device *dev)
 		verbose("READ from sector %llu: %i\n", out->sector, ret);
 		if (ret >= 0) {
 			wlen = sizeof(*in) + ret;
-			in->status = VIRTIO_BLK_S_OK;
+			*in = VIRTIO_BLK_S_OK;
 		} else {
 			wlen = sizeof(*in);
-			in->status = VIRTIO_BLK_S_IOERR;
+			*in = VIRTIO_BLK_S_IOERR;
 		}
 	}
 

drivers/block/virtio_blk.c

@@ -35,7 +35,7 @@ struct virtblk_req
 	struct list_head list;
 	struct request *req;
 	struct virtio_blk_outhdr out_hdr;
-	struct virtio_blk_inhdr in_hdr;
+	u8 status;
 };
 
 static void blk_done(struct virtqueue *vq)
@@ -48,7 +48,7 @@ static void blk_done(struct virtqueue *vq)
 	spin_lock_irqsave(&vblk->lock, flags);
 	while ((vbr = vblk->vq->vq_ops->get_buf(vblk->vq, &len)) != NULL) {
 		int uptodate;
-		switch (vbr->in_hdr.status) {
+		switch (vbr->status) {
 		case VIRTIO_BLK_S_OK:
 			uptodate = 1;
 			break;
@@ -101,7 +101,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	sg_init_table(vblk->sg, VIRTIO_MAX_SG);
 	sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
 	num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
-	sg_set_buf(&vblk->sg[num+1], &vbr->in_hdr, sizeof(vbr->in_hdr));
+	sg_set_buf(&vblk->sg[num+1], &vbr->status, sizeof(vbr->status));
 
 	if (rq_data_dir(vbr->req) == WRITE) {
 		vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
@@ -157,10 +157,25 @@ static int virtblk_ioctl(struct inode *inode, struct file *filp,
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
-	/* some standard values, similar to sd */
-	geo->heads = 1 << 6;
-	geo->sectors = 1 << 5;
-	geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+	struct virtio_blk *vblk = bd->bd_disk->private_data;
+	struct virtio_blk_geometry vgeo;
+	int err;
+
+	/* see if the host passed in geometry config */
+	err = virtio_config_val(vblk->vdev, VIRTIO_BLK_F_GEOMETRY,
+				offsetof(struct virtio_blk_config, geometry),
+				&vgeo);
+
+	if (!err) {
+		geo->heads = vgeo.heads;
+		geo->sectors = vgeo.sectors;
+		geo->cylinders = vgeo.cylinders;
+	} else {
+		/* some standard values, similar to sd */
+		geo->heads = 1 << 6;
+		geo->sectors = 1 << 5;
+		geo->cylinders = get_capacity(bd->bd_disk) >> 11;
+	}
 	return 0;
 }
 
@@ -242,12 +257,12 @@ static int virtblk_probe(struct virtio_device *vdev)
 	index++;
 
 	/* If barriers are supported, tell block layer that queue is ordered */
-	if (vdev->config->feature(vdev, VIRTIO_BLK_F_BARRIER))
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER))
 		blk_queue_ordered(vblk->disk->queue, QUEUE_ORDERED_TAG, NULL);
 
 	/* Host must always specify the capacity. */
-	__virtio_config_val(vdev, offsetof(struct virtio_blk_config, capacity),
-			    &cap);
+	vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+			  &cap, sizeof(cap));
 
 	/* If capacity is too big, truncate with warning. */
 	if ((sector_t)cap != cap) {
@@ -289,7 +304,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 static void virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
-	int major = vblk->disk->major;
 
 	/* Nothing should be pending. */
 	BUG_ON(!list_empty(&vblk->reqs));
@@ -299,7 +313,6 @@ static void virtblk_remove(struct virtio_device *vdev)
 
 	blk_cleanup_queue(vblk->disk->queue);
 	put_disk(vblk->disk);
-	unregister_blkdev(major, "virtblk");
 	mempool_destroy(vblk->pool);
 	vdev->config->del_vq(vblk->vq);
 	kfree(vblk);
@@ -310,7 +323,14 @@ static struct virtio_device_id id_table[] = {
 	{ 0 },
 };
 
+static unsigned int features[] = {
+	VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX,
+	VIRTIO_BLK_F_GEOMETRY,
+};
+
 static struct virtio_driver virtio_blk = {
+	.feature_table = features,
+	.feature_table_size = ARRAY_SIZE(features),
 	.driver.name =	KBUILD_MODNAME,
 	.driver.owner =	THIS_MODULE,
 	.id_table =	id_table,

drivers/lguest/lguest_device.c

@@ -85,27 +85,34 @@ static unsigned desc_size(const struct lguest_device_desc *desc)
 		+ desc->config_len;
 }
 
-/* This tests (and acknowleges) a feature bit. */
-static bool lg_feature(struct virtio_device *vdev, unsigned fbit)
+/* This gets the device's feature bits. */
+static u32 lg_get_features(struct virtio_device *vdev)
 {
+	unsigned int i;
+	u32 features = 0;
 	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
-	u8 *features;
-
-	/* Obviously if they ask for a feature off the end of our feature
-	 * bitmap, it's not set. */
-	if (fbit / 8 > desc->feature_len)
-		return false;
-
-	/* The feature bitmap comes after the virtqueues. */
-	features = lg_features(desc);
-	if (!(features[fbit / 8] & (1 << (fbit % 8))))
-		return false;
-
-	/* We set the matching bit in the other half of the bitmap to tell the
-	 * Host we want to use this feature.  We don't use this yet, but we
-	 * could in future. */
-	features[desc->feature_len + fbit / 8] |= (1 << (fbit % 8));
-	return true;
+	u8 *in_features = lg_features(desc);
+
+	/* We do this the slow but generic way. */
+	for (i = 0; i < min(desc->feature_len * 8, 32); i++)
+		if (in_features[i / 8] & (1 << (i % 8)))
+			features |= (1 << i);
+
+	return features;
+}
+
+static void lg_set_features(struct virtio_device *vdev, u32 features)
+{
+	unsigned int i;
+	struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
+	/* Second half of bitmap is features we accept. */
+	u8 *out_features = lg_features(desc) + desc->feature_len;
+
+	memset(out_features, 0, desc->feature_len);
+	for (i = 0; i < min(desc->feature_len * 8, 32); i++) {
+		if (features & (1 << i))
+			out_features[i / 8] |= (1 << (i % 8));
+	}
 }
 
 /* Once they've found a field, getting a copy of it is easy. */
@@ -137,20 +144,26 @@ static u8 lg_get_status(struct virtio_device *vdev)
 	return to_lgdev(vdev)->desc->status;
 }
 
+/* To notify on status updates, we (ab)use the NOTIFY hypercall, with the
+ * descriptor address of the device.  A zero status means "reset". */
+static void set_status(struct virtio_device *vdev, u8 status)
+{
+	unsigned long offset = (void *)to_lgdev(vdev)->desc - lguest_devices;
+
+	/* We set the status. */
+	to_lgdev(vdev)->desc->status = status;
+	hcall(LHCALL_NOTIFY, (max_pfn<<PAGE_SHIFT) + offset, 0, 0);
+}
+
 static void lg_set_status(struct virtio_device *vdev, u8 status)
 {
 	BUG_ON(!status);
-	to_lgdev(vdev)->desc->status = status;
+	set_status(vdev, status);
 }
 
-/* To reset the device, we (ab)use the NOTIFY hypercall, with the descriptor
- * address of the device.  The Host will zero the status and all the
- * features. */
 static void lg_reset(struct virtio_device *vdev)
 {
-	unsigned long offset = (void *)to_lgdev(vdev)->desc - lguest_devices;
-
-	hcall(LHCALL_NOTIFY, (max_pfn<<PAGE_SHIFT) + offset, 0, 0);
+	set_status(vdev, 0);
 }
 
 /*
@@ -286,7 +299,8 @@ static void lg_del_vq(struct virtqueue *vq)
 
 /* The ops structure which hooks everything together. */
 static struct virtio_config_ops lguest_config_ops = {
-	.feature = lg_feature,
+	.get_features = lg_get_features,
+	.set_features = lg_set_features,
 	.get = lg_get,
 	.set = lg_set,
 	.get_status = lg_get_status,

drivers/lguest/lguest_user.c

@@ -102,7 +102,7 @@ static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o)
 static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip)
 {
 	/* We have a limited number the number of CPUs in the lguest struct. */
-	if (id >= NR_CPUS)
+	if (id >= ARRAY_SIZE(cpu->lg->cpus))
 		return -EINVAL;
 
 	/* Set up this CPU's id, and pointer back to the lguest struct. */
@@ -251,8 +251,6 @@ static ssize_t write(struct file *file, const char __user *in,
 		if (!lg || (cpu_id >= lg->nr_cpus))
 			return -EINVAL;
 		cpu = &lg->cpus[cpu_id];
-		if (!cpu)
-			return -EINVAL;
 
 		/* Once the Guest is dead, you can only read() why it died. */
 		if (lg->dead)