summaryrefslogtreecommitdiffstats
path: root/drivers
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-12-11 12:20:31 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-11 12:20:31 -0800
commit6b9e2cea428cf7af93a84bcb865e478d8bf1c165 (patch)
tree11be387e37129fce0c4c111803df1a2e56637b60 /drivers
parent14ba9a2e4bacc6f5a0dbe0de5390daedd544508f (diff)
parentf01a2a811ae04124fc9382925038fcbbd2f0b7c8 (diff)
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull virtio updates from Michael Tsirkin: "virtio: virtio 1.0 support, misc patches This adds a lot of infrastructure for virtio 1.0 support. Notable missing pieces: virtio pci, virtio balloon (needs spec extension), vhost scsi. Plus, there are some minor fixes in a couple of places. Note: some net drivers are affected by these patches. David said he's fine with merging these patches through my tree. Rusty's on vacation, he acked using my tree for these, too" * tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (70 commits) virtio_ccw: finalize_features error handling virtio_ccw: future-proof finalize_features virtio_pci: rename virtio_pci -> virtio_pci_common virtio_pci: update file descriptions and copyright virtio_pci: split out legacy device support virtio_pci: setup config vector indirectly virtio_pci: setup vqs indirectly virtio_pci: delete vqs indirectly virtio_pci: use priv for vq notification virtio_pci: free up vq->priv virtio_pci: fix coding style for structs virtio_pci: add isr field virtio: drop legacy_only driver flag virtio_balloon: drop legacy_only driver flag virtio_ccw: rev 1 devices set VIRTIO_F_VERSION_1 virtio: allow finalize_features to fail virtio_ccw: legacy: don't negotiate rev 1/features virtio: add API to detect legacy devices virtio_console: fix sparse warnings vhost: remove unnecessary forward declarations in vhost.h ...
Diffstat (limited to 'drivers')
-rw-r--r--drivers/block/virtio_blk.c74
-rw-r--r--drivers/char/virtio_console.c39
-rw-r--r--drivers/lguest/lguest_device.c17
-rw-r--r--drivers/misc/mic/card/mic_virtio.c14
-rw-r--r--drivers/net/macvtap.c68
-rw-r--r--drivers/net/tun.c168
-rw-r--r--drivers/net/virtio_net.c161
-rw-r--r--drivers/remoteproc/remoteproc_virtio.c11
-rw-r--r--drivers/s390/kvm/kvm_virtio.c11
-rw-r--r--drivers/s390/kvm/virtio_ccw.c203
-rw-r--r--drivers/scsi/virtio_scsi.c50
-rw-r--r--drivers/vhost/net.c31
-rw-r--r--drivers/vhost/scsi.c22
-rw-r--r--drivers/vhost/vhost.c93
-rw-r--r--drivers/vhost/vhost.h41
-rw-r--r--drivers/virtio/Makefile1
-rw-r--r--drivers/virtio/virtio.c102
-rw-r--r--drivers/virtio/virtio_mmio.c17
-rw-r--r--drivers/virtio/virtio_pci.c802
-rw-r--r--drivers/virtio/virtio_pci_common.c464
-rw-r--r--drivers/virtio/virtio_pci_common.h136
-rw-r--r--drivers/virtio/virtio_pci_legacy.c326
-rw-r--r--drivers/virtio/virtio_ring.c109
23 files changed, 1696 insertions, 1264 deletions
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c6a27d54ad6..1fb9e09fbbc 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -80,7 +80,7 @@ static int __virtblk_add_req(struct virtqueue *vq,
{
struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
unsigned int num_out = 0, num_in = 0;
- int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT;
+ __virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
sgs[num_out++] = &hdr;
@@ -91,19 +91,19 @@ static int __virtblk_add_req(struct virtqueue *vq,
* block, and before the normal inhdr we put the sense data and the
* inhdr with additional status information.
*/
- if (type == VIRTIO_BLK_T_SCSI_CMD) {
+ if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
sgs[num_out++] = &cmd;
}
if (have_data) {
- if (vbr->out_hdr.type & VIRTIO_BLK_T_OUT)
+ if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
sgs[num_out++] = data_sg;
else
sgs[num_out + num_in++] = data_sg;
}
- if (type == VIRTIO_BLK_T_SCSI_CMD) {
+ if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
sgs[num_out + num_in++] = &sense;
sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
@@ -119,12 +119,13 @@ static int __virtblk_add_req(struct virtqueue *vq,
static inline void virtblk_request_done(struct request *req)
{
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+ struct virtio_blk *vblk = req->q->queuedata;
int error = virtblk_result(vbr);
if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
- req->resid_len = vbr->in_hdr.residual;
- req->sense_len = vbr->in_hdr.sense_len;
- req->errors = vbr->in_hdr.errors;
+ req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+ req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+ req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
req->errors = (error != 0);
}
@@ -173,25 +174,25 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
vbr->req = req;
if (req->cmd_flags & REQ_FLUSH) {
- vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
+ vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
vbr->out_hdr.sector = 0;
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
} else {
switch (req->cmd_type) {
case REQ_TYPE_FS:
vbr->out_hdr.type = 0;
- vbr->out_hdr.sector = blk_rq_pos(vbr->req);
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
case REQ_TYPE_BLOCK_PC:
- vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
+ vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
vbr->out_hdr.sector = 0;
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
case REQ_TYPE_SPECIAL:
- vbr->out_hdr.type = VIRTIO_BLK_T_GET_ID;
+ vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
vbr->out_hdr.sector = 0;
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
default:
/* We don't put anything else in the queue. */
@@ -204,9 +205,9 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
if (num) {
if (rq_data_dir(vbr->req) == WRITE)
- vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+ vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
else
- vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+ vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
}
spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
@@ -331,7 +332,8 @@ static ssize_t virtblk_serial_show(struct device *dev,
return err;
}
-DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
+
+static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
static void virtblk_config_changed_work(struct work_struct *work)
{
@@ -476,7 +478,8 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev)
struct virtio_blk_config, wce,
&writeback);
if (err)
- writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);
+ writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE) ||
+ virtio_has_feature(vdev, VIRTIO_F_VERSION_1);
return writeback;
}
@@ -821,25 +824,34 @@ static const struct virtio_device_id id_table[] = {
{ 0 },
};
-static unsigned int features[] = {
+static unsigned int features_legacy[] = {
VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
VIRTIO_BLK_F_MQ,
+}
+;
+static unsigned int features[] = {
+ VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
+ VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+ VIRTIO_BLK_F_TOPOLOGY,
+ VIRTIO_BLK_F_MQ,
};
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,
- .probe = virtblk_probe,
- .remove = virtblk_remove,
- .config_changed = virtblk_config_changed,
+ .feature_table = features,
+ .feature_table_size = ARRAY_SIZE(features),
+ .feature_table_legacy = features_legacy,
+ .feature_table_size_legacy = ARRAY_SIZE(features_legacy),
+ .driver.name = KBUILD_MODNAME,
+ .driver.owner = THIS_MODULE,
+ .id_table = id_table,
+ .probe = virtblk_probe,
+ .remove = virtblk_remove,
+ .config_changed = virtblk_config_changed,
#ifdef CONFIG_PM_SLEEP
- .freeze = virtblk_freeze,
- .restore = virtblk_restore,
+ .freeze = virtblk_freeze,
+ .restore = virtblk_restore,
#endif
};
@@ -871,8 +883,8 @@ out_destroy_workqueue:
static void __exit fini(void)
{
- unregister_blkdev(major, "virtblk");
unregister_virtio_driver(&virtio_blk);
+ unregister_blkdev(major, "virtblk");
destroy_workqueue(virtblk_wq);
}
module_init(init);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index cf7a561fad7..de03df9dd7c 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -355,7 +355,7 @@ static inline bool use_multiport(struct ports_device *portdev)
*/
if (!portdev->vdev)
return 0;
- return portdev->vdev->features[0] & (1 << VIRTIO_CONSOLE_F_MULTIPORT);
+ return __virtio_test_bit(portdev->vdev, VIRTIO_CONSOLE_F_MULTIPORT);
}
static DEFINE_SPINLOCK(dma_bufs_lock);
@@ -566,9 +566,9 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
if (!use_multiport(portdev))
return 0;
- cpkt.id = port_id;
- cpkt.event = event;
- cpkt.value = value;
+ cpkt.id = cpu_to_virtio32(portdev->vdev, port_id);
+ cpkt.event = cpu_to_virtio16(portdev->vdev, event);
+ cpkt.value = cpu_to_virtio16(portdev->vdev, value);
vq = portdev->c_ovq;
@@ -669,8 +669,8 @@ done:
* Give out the data that's requested from the buffer that we have
* queued up.
*/
-static ssize_t fill_readbuf(struct port *port, char *out_buf, size_t out_count,
- bool to_user)
+static ssize_t fill_readbuf(struct port *port, char __user *out_buf,
+ size_t out_count, bool to_user)
{
struct port_buffer *buf;
unsigned long flags;
@@ -688,7 +688,8 @@ static ssize_t fill_readbuf(struct port *port, char *out_buf, size_t out_count,
if (ret)
return -EFAULT;
} else {
- memcpy(out_buf, buf->buf + buf->offset, out_count);
+ memcpy((__force char *)out_buf, buf->buf + buf->offset,
+ out_count);
}
buf->offset += out_count;
@@ -1162,7 +1163,7 @@ static int get_chars(u32 vtermno, char *buf, int count)
/* If we don't have an input queue yet, we can't get input. */
BUG_ON(!port->in_vq);
- return fill_readbuf(port, buf, count, false);
+ return fill_readbuf(port, (__force char __user *)buf, count, false);
}
static void resize_console(struct port *port)
@@ -1602,7 +1603,8 @@ static void unplug_port(struct port *port)
}
/* Any private messages that the Host and Guest want to share */
-static void handle_control_message(struct ports_device *portdev,
+static void handle_control_message(struct virtio_device *vdev,
+ struct ports_device *portdev,
struct port_buffer *buf)
{
struct virtio_console_control *cpkt;
@@ -1612,15 +1614,16 @@ static void handle_control_message(struct ports_device *portdev,
cpkt = (struct virtio_console_control *)(buf->buf + buf->offset);
- port = find_port_by_id(portdev, cpkt->id);
- if (!port && cpkt->event != VIRTIO_CONSOLE_PORT_ADD) {
+ port = find_port_by_id(portdev, virtio32_to_cpu(vdev, cpkt->id));
+ if (!port &&
+ cpkt->event != cpu_to_virtio16(vdev, VIRTIO_CONSOLE_PORT_ADD)) {
/* No valid header at start of buffer. Drop it. */
dev_dbg(&portdev->vdev->dev,
"Invalid index %u in control packet\n", cpkt->id);
return;
}
- switch (cpkt->event) {
+ switch (virtio16_to_cpu(vdev, cpkt->event)) {
case VIRTIO_CONSOLE_PORT_ADD:
if (port) {
dev_dbg(&portdev->vdev->dev,
@@ -1628,13 +1631,15 @@ static void handle_control_message(struct ports_device *portdev,
send_control_msg(port, VIRTIO_CONSOLE_PORT_READY, 1);
break;
}
- if (cpkt->id >= portdev->config.max_nr_ports) {
+ if (virtio32_to_cpu(vdev, cpkt->id) >=
+ portdev->config.max_nr_ports) {
dev_warn(&portdev->vdev->dev,
- "Request for adding port with out-of-bound id %u, max. supported id: %u\n",
+ "Request for adding port with "
+ "out-of-bound id %u, max. supported id: %u\n",
cpkt->id, portdev->config.max_nr_ports - 1);
break;
}
- add_port(portdev, cpkt->id);
+ add_port(portdev, virtio32_to_cpu(vdev, cpkt->id));
break;
case VIRTIO_CONSOLE_PORT_REMOVE:
unplug_port(port);
@@ -1670,7 +1675,7 @@ static void handle_control_message(struct ports_device *portdev,
break;
}
case VIRTIO_CONSOLE_PORT_OPEN:
- port->host_connected = cpkt->value;
+ port->host_connected = virtio16_to_cpu(vdev, cpkt->value);
wake_up_interruptible(&port->waitqueue);
/*
* If the host port got closed and the host had any
@@ -1752,7 +1757,7 @@ static void control_work_handler(struct work_struct *work)
buf->len = len;
buf->offset = 0;
- handle_control_message(portdev, buf);
+ handle_control_message(vq->vdev, portdev, buf);
spin_lock(&portdev->c_ivq_lock);
if (add_inbuf(portdev->c_ivq, buf) < 0) {
diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index d0a1d8a45c8..89088d6538f 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -94,7 +94,7 @@ static unsigned desc_size(const struct lguest_device_desc *desc)
}
/* This gets the device's feature bits. */
-static u32 lg_get_features(struct virtio_device *vdev)
+static u64 lg_get_features(struct virtio_device *vdev)
{
unsigned int i;
u32 features = 0;
@@ -126,7 +126,7 @@ static void status_notify(struct virtio_device *vdev)
* sorted out, this routine is called so we can tell the Host which features we
* understand and accept.
*/
-static void lg_finalize_features(struct virtio_device *vdev)
+static int lg_finalize_features(struct virtio_device *vdev)
{
unsigned int i, bits;
struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
@@ -136,20 +136,25 @@ static void lg_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
+ /* Make sure we don't have any features > 32 bits! */
+ BUG_ON((u32)vdev->features != vdev->features);
+
/*
- * The vdev->feature array is a Linux bitmask: this isn't the same as a
- * the simple array of bits used by lguest devices for features. So we
- * do this slow, manual conversion which is completely general.
+ * Since lguest is currently x86-only, we're little-endian. That
+ * means we could just memcpy. But it's not time critical, and in
+ * case someone copies this code, we do it the slow, obvious way.
*/
memset(out_features, 0, desc->feature_len);
bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
for (i = 0; i < bits; i++) {
- if (test_bit(i, vdev->features))
+ if (__virtio_test_bit(vdev, i))
out_features[i / 8] |= (1 << (i % 8));
}
/* Tell Host we've finished with this device's feature negotiation */
status_notify(vdev);
+
+ return 0;
}
/* Once they've found a field, getting a copy of it is easy. */
diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c
index e64794730e2..e486a0c2626 100644
--- a/drivers/misc/mic/card/mic_virtio.c
+++ b/drivers/misc/mic/card/mic_virtio.c
@@ -68,7 +68,7 @@ static inline struct device *mic_dev(struct mic_vdev *mvdev)
}
/* This gets the device's feature bits. */
-static u32 mic_get_features(struct virtio_device *vdev)
+static u64 mic_get_features(struct virtio_device *vdev)
{
unsigned int i, bits;
u32 features = 0;
@@ -76,8 +76,7 @@ static u32 mic_get_features(struct virtio_device *vdev)
u8 __iomem *in_features = mic_vq_features(desc);
int feature_len = ioread8(&desc->feature_len);
- bits = min_t(unsigned, feature_len,
- sizeof(vdev->features)) * 8;
+ bits = min_t(unsigned, feature_len, sizeof(features)) * 8;
for (i = 0; i < bits; i++)
if (ioread8(&in_features[i / 8]) & (BIT(i % 8)))
features |= BIT(i);
@@ -85,7 +84,7 @@ static u32 mic_get_features(struct virtio_device *vdev)
return features;
}
-static void mic_finalize_features(struct virtio_device *vdev)
+static int mic_finalize_features(struct virtio_device *vdev)
{
unsigned int i, bits;
struct mic_device_desc __iomem *desc = to_micvdev(vdev)->desc;
@@ -97,14 +96,19 @@ static void mic_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
+ /* Make sure we don't have any features > 32 bits! */
+ BUG_ON((u32)vdev->features != vdev->features);
+
memset_io(out_features, 0, feature_len);
bits = min_t(unsigned, feature_len,
sizeof(vdev->features)) * 8;
for (i = 0; i < bits; i++) {
- if (test_bit(i, vdev->features))
+ if (__virtio_test_bit(vdev, i))
iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)),
&out_features[i / 8]);
}
+
+ return 0;
}
/*
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 880cc090dc4..af90ab5e576 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -45,6 +45,18 @@ struct macvtap_queue {
struct list_head next;
};
+#define MACVTAP_FEATURES (IFF_VNET_HDR | IFF_VNET_LE | IFF_MULTI_QUEUE)
+
+static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val)
+{
+ return __virtio16_to_cpu(q->flags & IFF_VNET_LE, val);
+}
+
+static inline __virtio16 cpu_to_macvtap16(struct macvtap_queue *q, u16 val)
+{
+ return __cpu_to_virtio16(q->flags & IFF_VNET_LE, val);
+}
+
static struct proto macvtap_proto = {
.name = "macvtap",
.owner = THIS_MODULE,
@@ -557,7 +569,8 @@ static inline struct sk_buff *macvtap_alloc_skb(struct sock *sk, size_t prepad,
* macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should
* be shared with the tun/tap driver.
*/
-static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
+static int macvtap_skb_from_vnet_hdr(struct macvtap_queue *q,
+ struct sk_buff *skb,
struct virtio_net_hdr *vnet_hdr)
{
unsigned short gso_type = 0;
@@ -588,13 +601,13 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
}
if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
- if (!skb_partial_csum_set(skb, vnet_hdr->csum_start,
- vnet_hdr->csum_offset))
+ if (!skb_partial_csum_set(skb, macvtap16_to_cpu(q, vnet_hdr->csum_start),
+ macvtap16_to_cpu(q, vnet_hdr->csum_offset)))
return -EINVAL;
}
if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
- skb_shinfo(skb)->gso_size = vnet_hdr->gso_size;
+ skb_shinfo(skb)->gso_size = macvtap16_to_cpu(q, vnet_hdr->gso_size);
skb_shinfo(skb)->gso_type = gso_type;
/* Header must be checked, and gso_segs computed. */
@@ -604,8 +617,9 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
return 0;
}
-static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
- struct virtio_net_hdr *vnet_hdr)
+static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
+ const struct sk_buff *skb,
+ struct virtio_net_hdr *vnet_hdr)
{
memset(vnet_hdr, 0, sizeof(*vnet_hdr));
@@ -613,8 +627,8 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
struct skb_shared_info *sinfo = skb_shinfo(skb);
/* This is a hint as to how much should be linear. */
- vnet_hdr->hdr_len = skb_headlen(skb);
- vnet_hdr->gso_size = sinfo->gso_size;
+ vnet_hdr->hdr_len = cpu_to_macvtap16(q, skb_headlen(skb));
+ vnet_hdr->gso_size = cpu_to_macvtap16(q, sinfo->gso_size);
if (sinfo->gso_type & SKB_GSO_TCPV4)
vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (sinfo->gso_type & SKB_GSO_TCPV6)
@@ -628,10 +642,13 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
if (skb->ip_summed == CHECKSUM_PARTIAL) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
- vnet_hdr->csum_start = skb_checksum_start_offset(skb);
if (vlan_tx_tag_present(skb))
- vnet_hdr->csum_start += VLAN_HLEN;
- vnet_hdr->csum_offset = skb->csum_offset;
+ vnet_hdr->csum_start = cpu_to_macvtap16(q,
+ skb_checksum_start_offset(skb) + VLAN_HLEN);
+ else
+ vnet_hdr->csum_start = cpu_to_macvtap16(q,
+ skb_checksum_start_offset(skb));
+ vnet_hdr->csum_offset = cpu_to_macvtap16(q, skb->csum_offset);
} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
} /* else everything is zero */
@@ -666,12 +683,14 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
if (err < 0)
goto err;
if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
- vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
- vnet_hdr.hdr_len)
- vnet_hdr.hdr_len = vnet_hdr.csum_start +
- vnet_hdr.csum_offset + 2;
+ macvtap16_to_cpu(q, vnet_hdr.csum_start) +
+ macvtap16_to_cpu(q, vnet_hdr.csum_offset) + 2 >
+ macvtap16_to_cpu(q, vnet_hdr.hdr_len))
+ vnet_hdr.hdr_len = cpu_to_macvtap16(q,
+ macvtap16_to_cpu(q, vnet_hdr.csum_start) +
+ macvtap16_to_cpu(q, vnet_hdr.csum_offset) + 2);
err = -EINVAL;
- if (vnet_hdr.hdr_len > len)
+ if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > len)
goto err;
}
@@ -684,7 +703,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
goto err;
if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
- copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
+ copylen = vnet_hdr.hdr_len ?
+ macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
if (copylen > good_linear)
copylen = good_linear;
linear = copylen;
@@ -695,10 +715,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
if (!zerocopy) {
copylen = len;
- if (vnet_hdr.hdr_len > good_linear)
+ if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
linear = good_linear;
else
- linear = vnet_hdr.hdr_len;
+ linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
}
skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
@@ -725,7 +745,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
skb->protocol = eth_hdr(skb)->h_proto;
if (vnet_hdr_len) {
- err = macvtap_skb_from_vnet_hdr(skb, &vnet_hdr);
+ err = macvtap_skb_from_vnet_hdr(q, skb, &vnet_hdr);
if (err)
goto err_kfree;
}
@@ -791,7 +811,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
if ((len -= vnet_hdr_len) < 0)
return -EINVAL;
- macvtap_skb_to_vnet_hdr(skb, &vnet_hdr);
+ macvtap_skb_to_vnet_hdr(q, skb, &vnet_hdr);
if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
return -EFAULT;
@@ -1003,8 +1023,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
return -EFAULT;
ret = 0;
- if ((u & ~(IFF_VNET_HDR | IFF_MULTI_QUEUE)) !=
- (IFF_NO_PI | IFF_TAP))
+ if ((u & ~MACVTAP_FEATURES) != (IFF_NO_PI | IFF_TAP))
ret = -EINVAL;
else
q->flags = u;
@@ -1036,8 +1055,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
return ret;
case TUNGETFEATURES:
- if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR |
- IFF_MULTI_QUEUE, up))
+ if (put_user(IFF_TAP | IFF_NO_PI | MACVTAP_FEATURES, up))
return -EFAULT;
return 0;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 4d332dc93b7..798ce70e3d6 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -103,6 +103,15 @@ do { \
} while (0)
#endif
+/* TUN device flags */
+
+/* IFF_ATTACH_QUEUE is never stored in device flags,
+ * overload it to mean fasync when stored there.
+ */
+#define TUN_FASYNC IFF_ATTACH_QUEUE
+
+#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
+ IFF_VNET_LE | IFF_MULTI_QUEUE)
#define GOODCOPY_LEN 128
#define FLT_EXACT_COUNT 8
@@ -196,6 +205,16 @@ struct tun_struct {
u32 flow_count;
};
+static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
+{
+ return __virtio16_to_cpu(tun->flags & IFF_VNET_LE, val);
+}
+
+static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
+{
+ return __cpu_to_virtio16(tun->flags & IFF_VNET_LE, val);
+}
+
static inline u32 tun_hashfn(u32 rxhash)
{
return rxhash & 0x3ff;
@@ -472,7 +491,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
if (tun && tun->numqueues == 0 && tun->numdisabled == 0) {
netif_carrier_off(tun->dev);
- if (!(tun->flags & TUN_PERSIST) &&
+ if (!(tun->flags & IFF_PERSIST) &&
tun->dev->reg_state == NETREG_REGISTERED)
unregister_netdevice(tun->dev);
}
@@ -523,7 +542,7 @@ static void tun_detach_all(struct net_device *dev)
}
BUG_ON(tun->numdisabled != 0);
- if (tun->flags & TUN_PERSIST)
+ if (tun->flags & IFF_PERSIST)
module_put(THIS_MODULE);
}
@@ -541,7 +560,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
goto out;
err = -EBUSY;
- if (!(tun->flags & TUN_TAP_MQ) && tun->numqueues == 1)
+ if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1)
goto out;
err = -E2BIG;
@@ -920,7 +939,7 @@ static void tun_net_init(struct net_device *dev)
struct tun_struct *tun = netdev_priv(dev);
switch (tun->flags & TUN_TYPE_MASK) {
- case TUN_TUN_DEV:
+ case IFF_TUN:
dev->netdev_ops = &tun_netdev_ops;
/* Point-to-Point TUN Device */
@@ -934,7 +953,7 @@ static void tun_net_init(struct net_device *dev)
dev->tx_queue_len = TUN_READQ_SIZE; /* We prefer our own queue length */
break;
- case TUN_TAP_DEV:
+ case IFF_TAP:
dev->netdev_ops = &tap_netdev_ops;
/* Ethernet TAP Device */
ether_setup(dev);
@@ -1025,7 +1044,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
int err;
u32 rxhash;
- if (!(tun->flags & TUN_NO_PI)) {
+ if (!(tun->flags & IFF_NO_PI)) {
if (len < sizeof(pi))
return -EINVAL;
len -= sizeof(pi);
@@ -1035,7 +1054,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
offset += sizeof(pi);
}
- if (tun->flags & TUN_VNET_HDR) {
+ if (tun->flags & IFF_VNET_HDR) {
if (len < tun->vnet_hdr_sz)
return -EINVAL;
len -= tun->vnet_hdr_sz;
@@ -1044,18 +1063,18 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
return -EFAULT;
if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
- gso.csum_start + gso.csum_offset + 2 > gso.hdr_len)
- gso.hdr_len = gso.csum_start + gso.csum_offset + 2;
+ tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2 > tun16_to_cpu(tun, gso.hdr_len))
+ gso.hdr_len = cpu_to_tun16(tun, tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2);
- if (gso.hdr_len > len)
+ if (tun16_to_cpu(tun, gso.hdr_len) > len)
return -EINVAL;
offset += tun->vnet_hdr_sz;
}
- if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
+ if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
align += NET_IP_ALIGN;
if (unlikely(len < ETH_HLEN ||
- (gso.hdr_len && gso.hdr_len < ETH_HLEN)))
+ (gso.hdr_len && tun16_to_cpu(tun, gso.hdr_len) < ETH_HLEN)))
return -EINVAL;
}
@@ -1066,7 +1085,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
* enough room for skb expand head in case it is used.
* The rest of the buffer is mapped from userspace.
*/
- copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
+ copylen = gso.hdr_len ? tun16_to_cpu(tun, gso.hdr_len) : GOODCOPY_LEN;
if (copylen > good_linear)
copylen = good_linear;
linear = copylen;
@@ -1076,10 +1095,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (!zerocopy) {
copylen = len;
- if (gso.hdr_len > good_linear)
+ if (tun16_to_cpu(tun, gso.hdr_len) > good_linear)
linear = good_linear;
else
- linear = gso.hdr_len;
+ linear = tun16_to_cpu(tun, gso.hdr_len);
}
skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
@@ -1106,8 +1125,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
}
if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
- if (!skb_partial_csum_set(skb, gso.csum_start,
- gso.csum_offset)) {
+ if (!skb_partial_csum_set(skb, tun16_to_cpu(tun, gso.csum_start),
+ tun16_to_cpu(tun, gso.csum_offset))) {
tun->dev->stats.rx_frame_errors++;
kfree_skb(skb);
return -EINVAL;
@@ -1115,8 +1134,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
}
switch (tun->flags & TUN_TYPE_MASK) {
- case TUN_TUN_DEV:
- if (tun->flags & TUN_NO_PI) {
+ case IFF_TUN:
+ if (tun->flags & IFF_NO_PI) {
switch (skb->data[0] & 0xf0) {
case 0x40:
pi.proto = htons(ETH_P_IP);
@@ -1135,7 +1154,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
skb->protocol = pi.proto;
skb->dev = tun->dev;
break;
- case TUN_TAP_DEV:
+ case IFF_TAP:
skb->protocol = eth_type_trans(skb, tun->dev);
break;
}
@@ -1175,7 +1194,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
- skb_shinfo(skb)->gso_size = gso.gso_size;
+ skb_shinfo(skb)->gso_size = tun16_to_cpu(tun, gso.gso_size);
if (skb_shinfo(skb)->gso_size == 0) {
tun->dev->stats.rx_frame_errors++;
kfree_skb(skb);
@@ -1241,10 +1260,10 @@ static ssize_t tun_put_user(struct tun_struct *tun,
if (vlan_tx_tag_present(skb))
vlan_hlen = VLAN_HLEN;
- if (tun->flags & TUN_VNET_HDR)
+ if (tun->flags & IFF_VNET_HDR)
vnet_hdr_sz = tun->vnet_hdr_sz;
- if (!(tun->flags & TUN_NO_PI)) {
+ if (!(tun->flags & IFF_NO_PI)) {
if ((len -= sizeof(pi)) < 0)
return -EINVAL;
@@ -1267,8 +1286,8 @@ static ssize_t tun_put_user(struct tun_struct *tun,
struct skb_shared_info *sinfo = skb_shinfo(skb);
/* This is a hint as to how much should be linear. */
- gso.hdr_len = skb_headlen(skb);
- gso.gso_size = sinfo->gso_size;
+ gso.hdr_len = cpu_to_tun16(tun, skb_headlen(skb));
+ gso.gso_size = cpu_to_tun16(tun, sinfo->gso_size);
if (sinfo->gso_type & SKB_GSO_TCPV4)
gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (sinfo->gso_type & SKB_GSO_TCPV6)
@@ -1276,12 +1295,12 @@ static ssize_t tun_put_user(struct tun_struct *tun,
else {
pr_err("unexpected GSO type: "
"0x%x, gso_size %d, hdr_len %d\n",
- sinfo->gso_type, gso.gso_size,
- gso.hdr_len);
+ sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
+ tun16_to_cpu(tun, gso.hdr_len));
print_hex_dump(KERN_ERR, "tun: ",
DUMP_PREFIX_NONE,
16, 1, skb->head,
- min((int)gso.hdr_len, 64), true);
+ min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
WARN_ON_ONCE(1);
return -EINVAL;
}
@@ -1292,9 +1311,9 @@ static ssize_t tun_put_user(struct tun_struct *tun,
if (skb->ip_summed == CHECKSUM_PARTIAL) {
gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
- gso.csum_start = skb_checksum_start_offset(skb) +
- vlan_hlen;
- gso.csum_offset = skb->csum_offset;
+ gso.csum_start = cpu_to_tun16(tun, skb_checksum_start_offset(skb) +
+ vlan_hlen);
+ gso.csum_offset = cpu_to_tun16(tun, skb->csum_offset);
} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
gso.flags = VIRTIO_NET_HDR_F_DATA_VALID;
} /* else everything is zero */
@@ -1521,32 +1540,7 @@ static struct proto tun_proto = {
static int tun_flags(struct tun_struct *tun)
{
- int flags = 0;
-
- if (tun->flags & TUN_TUN_DEV)
- flags |= IFF_TUN;
- else
- flags |= IFF_TAP;
-
- if (tun->flags & TUN_NO_PI)
- flags |= IFF_NO_PI;
-
- /* This flag has no real effect. We track the value for backwards
- * compatibility.
- */
- if (tun->flags & TUN_ONE_QUEUE)
- flags |= IFF_ONE_QUEUE;
-
- if (tun->flags & TUN_VNET_HDR)
- flags |= IFF_VNET_HDR;
-
- if (tun->flags & TUN_TAP_MQ)
- flags |= IFF_MULTI_QUEUE;
-
- if (tun->flags & TUN_PERSIST)
- flags |= IFF_PERSIST;
-
- return flags;
+ return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP);
}
static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr,
@@ -1602,7 +1596,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
return -EINVAL;
if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) !=
- !!(tun->flags & TUN_TAP_MQ))
+ !!(tun->flags & IFF_MULTI_QUEUE))
return -EINVAL;
if (tun_not_capable(tun))
@@ -1615,7 +1609,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
if (err < 0)
return err;
- if (tun->flags & TUN_TAP_MQ &&
+ if (tun->flags & IFF_MULTI_QUEUE &&
(tun->numqueues + tun->numdisabled > 1)) {
/* One or more queue has already been attached, no need
* to initialize the device again.
@@ -1638,11 +1632,11 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
/* Set dev type */
if (ifr->ifr_flags & IFF_TUN) {
/* TUN device */
- flags |= TUN_TUN_DEV;
+ flags |= IFF_TUN;
name = "tun%d";
} else if (ifr->ifr_flags & IFF_TAP) {
/* TAP device */
- flags |= TUN_TAP_DEV;
+ flags |= IFF_TAP;
name = "tap%d";
} else
return -EINVAL;
@@ -1706,28 +1700,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
tun_debug(KERN_INFO, tun, "tun_set_iff\n");
- if (ifr->ifr_flags & IFF_NO_PI)
- tun->flags |= TUN_NO_PI;
- else
- tun->flags &= ~TUN_NO_PI;
-
- /* This flag has no real effect. We track the value for backwards
- * compatibility.
- */
- if (ifr->ifr_flags & IFF_ONE_QUEUE)
- tun->flags |= TUN_ONE_QUEUE;
- else
- tun->flags &= ~TUN_ONE_QUEUE;
-
- if (ifr->ifr_flags & IFF_VNET_HDR)
- tun->flags |= TUN_VNET_HDR;
- else
- tun->flags &= ~TUN_VNET_HDR;
-
- if (ifr->ifr_flags & IFF_MULTI_QUEUE)
- tun->flags |= TUN_TAP_MQ;
- else
- tun->flags &= ~TUN_TAP_MQ;
+ tun->flags = (tun->flags & ~TUN_FEATURES) |
+ (ifr->ifr_flags & TUN_FEATURES);
/* Make sure persistent devices do not get stuck in
* xoff state.
@@ -1855,7 +1829,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
ret = tun_attach(tun, file, false);
} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
tun = rtnl_dereference(tfile->tun);
- if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached)
+ if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
ret = -EINVAL;
else
__tun_detach(tfile, false);
@@ -1890,9 +1864,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
if (cmd == TUNGETFEATURES) {
/* Currently this just means: "what IFF flags are valid?".
* This is needed because we never checked for invalid flags on
- * TUNSETIFF. */
- return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
- IFF_VNET_HDR | IFF_MULTI_QUEUE,
+ * TUNSETIFF.
+ */
+ return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES,
(unsigned int __user*)argp);
} else if (cmd == TUNSETQUEUE)
return tun_set_queue(file, &ifr);
@@ -1959,12 +1933,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
/* Disable/Enable persist mode. Keep an extra reference to the
* module to prevent the module being unprobed.
*/
- if (arg && !(tun->flags & TUN_PERSIST)) {
- tun->flags |= TUN_PERSIST;
+ if (arg && !(tun->flags & IFF_PERSIST)) {
+ tun->flags |= IFF_PERSIST;
__module_get(THIS_MODULE);
}
- if (!arg && (tun->flags & TUN_PERSIST)) {
- tun->flags &= ~TUN_PERSIST;
+ if (!arg && (tun->flags & IFF_PERSIST)) {
+ tun->flags &= ~IFF_PERSIST;
module_put(THIS_MODULE);
}
@@ -2022,7 +1996,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
case TUNSETTXFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
break;
ret = update_filter(&tun->txflt, (void __user *)arg);
break;
@@ -2081,7 +2055,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
case TUNATTACHFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
break;
ret = -EFAULT;
if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog)))
@@ -2093,7 +2067,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
case TUNDETACHFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
break;
ret = 0;
tun_detach_filter(tun, tun->numqueues);
@@ -2101,7 +2075,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
case TUNGETFILTER:
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP)
break;
ret = -EFAULT;
if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog)))
@@ -2294,10 +2268,10 @@ static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
strlcpy(info->version, DRV_VERSION, sizeof(info->version));
switch (tun->flags & TUN_TYPE_MASK) {
- case TUN_TUN_DEV:
+ case IFF_TUN:
strlcpy(info->bus_info, "tun", sizeof(info->bus_info));
break;
- case TUN_TAP_DEV:
+ case IFF_TAP:
strlcpy(info->bus_info, "tap", sizeof(info->bus_info));
break;
}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b0bc8ead47d..b8bd7191572 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -123,6 +123,9 @@ struct virtnet_info {
/* Host can handle any s/g split between our header and packet data */
bool any_header_sg;
+ /* Packet virtio header size */
+ u8 hdr_len;
+
/* Active statistics */
struct virtnet_stats __percpu *stats;
@@ -139,21 +142,14 @@ struct virtnet_info {
struct notifier_block nb;
};
-struct skb_vnet_hdr {
- union {
- struct virtio_net_hdr hdr;
- struct virtio_net_hdr_mrg_rxbuf mhdr;
- };
-};
-
struct padded_vnet_hdr {
- struct virtio_net_hdr hdr;
+ struct virtio_net_hdr_mrg_rxbuf hdr;
/*
- * virtio_net_hdr should be in a separated sg buffer because of a
- * QEMU bug, and data sg buffer shares same page with this header sg.
- * This padding makes next sg 16 byte aligned after virtio_net_hdr.
+ * hdr is in a separate sg buffer, and data sg buffer shares same page
+ * with this header sg. This padding makes next sg 16 byte aligned
+ * after the header.
*/
- char padding[6];
+ char padding[4];
};
/* Converting between virtqueue no. and kernel tx/rx queue no.
@@ -179,9 +175,9 @@ static int rxq2vq(int rxq)
return rxq * 2;
}
-static inline struct skb_vnet_hdr *skb_vnet_hdr(struct sk_buff *skb)
+static inline struct virtio_net_hdr_mrg_rxbuf *skb_vnet_hdr(struct sk_buff *skb)
{
- return (struct skb_vnet_hdr *)skb->cb;
+ return (struct virtio_net_hdr_mrg_rxbuf *)skb->cb;
}
/*
@@ -241,13 +237,13 @@ static unsigned long mergeable_buf_to_ctx(void *buf, unsigned int truesize)
}
/* Called from bottom half context */
-static struct sk_buff *page_to_skb(struct receive_queue *rq,
+static struct sk_buff *page_to_skb(struct virtnet_info *vi,
+ struct receive_queue *rq,
struct page *page, unsigned int offset,
unsigned int len, unsigned int truesize)
{
- struct virtnet_info *vi = rq->vq->vdev->priv;
struct sk_buff *skb;
- struct skb_vnet_hdr *hdr;
+ struct virtio_net_hdr_mrg_rxbuf *hdr;
unsigned int copy, hdr_len, hdr_padded_len;
char *p;
@@ -260,13 +256,11 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,
hdr = skb_vnet_hdr(skb);
- if (vi->mergeable_rx_bufs) {
- hdr_len = sizeof hdr->mhdr;
- hdr_padded_len = sizeof hdr->mhdr;
- } else {
- hdr_len = sizeof hdr->hdr;
+ hdr_len = vi->hdr_len;
+ if (vi->mergeable_rx_bufs)
+ hdr_padded_len = sizeof *hdr;
+ else
hdr_padded_len = sizeof(struct padded_vnet_hdr);
- }
memcpy(hdr, p, hdr_len);
@@ -317,23 +311,24 @@ static struct sk_buff *page_to_skb(struct receive_queue *rq,
return skb;
}
-static struct sk_buff *receive_small(void *buf, unsigned int len)
+static struct sk_buff *receive_small(struct virtnet_info *vi, void *buf, unsigned int len)
{
struct sk_buff * skb = buf;
- len -= sizeof(struct virtio_net_hdr);
+ len -= vi->hdr_len;
skb_trim(skb, len);
return skb;
}
static struct sk_buff *receive_big(struct net_device *dev,
+ struct virtnet_info *vi,
struct receive_queue *rq,
void *buf,
unsigned int len)
{
struct page *page = buf;
- struct sk_buff *skb = page_to_skb(rq, page, 0, len, PAGE_SIZE);
+ struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
if (unlikely(!skb))
goto err;
@@ -347,18 +342,20 @@ err:
}
static struct sk_buff *receive_mergeable(struct net_device *dev,
+ struct virtnet_info *vi,
struct receive_queue *rq,
unsigned long ctx,
unsigned int len)
{
void *buf = mergeable_ctx_to_buf_address(ctx);
- struct skb_vnet_hdr *hdr = buf;
- int num_buf = hdr->mhdr.num_buffers;
+ struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
+ u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
struct page *page = virt_to_head_page(buf);
int offset = buf - page_address(page);
unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
- struct sk_buff *head_skb = page_to_skb(rq, page, offset, len, truesize);
+ struct sk_buff *head_skb = page_to_skb(vi, rq, page, offset, len,
+ truesize);
struct sk_buff *curr_skb = head_skb;
if (unlikely(!curr_skb))
@@ -369,7 +366,9 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
if (unlikely(!ctx)) {
pr_debug("%s: rx error: %d buffers out of %d missing\n",
- dev->name, num_buf, hdr->mhdr.num_buffers);
+ dev->name, num_buf,
+ virtio16_to_cpu(vi->vdev,
+ hdr->num_buffers));
dev->stats.rx_length_errors++;
goto err_buf;
}
@@ -430,15 +429,15 @@ err_buf:
return NULL;
}
-static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
+static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
+ void *buf, unsigned int len)
{
- struct virtnet_info *vi = rq->vq->vdev->priv;
struct net_device *dev = vi->dev;
struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
struct sk_buff *skb;
- struct skb_vnet_hdr *hdr;
+ struct virtio_net_hdr_mrg_rxbuf *hdr;
- if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
+ if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
pr_debug("%s: short packet %i\n", dev->name, len);
dev->stats.rx_length_errors++;
if (vi->mergeable_rx_bufs) {
@@ -454,11 +453,11 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
}
if (vi->mergeable_rx_bufs)
- skb = receive_mergeable(dev, rq, (unsigned long)buf, len);
+ skb = receive_mergeable(dev, vi, rq, (unsigned long)buf, len);
else if (vi->big_packets)
- skb = receive_big(dev, rq, buf, len);
+ skb = receive_big(dev, vi, rq, buf, len);
else
- skb = receive_small(buf, len);
+ skb = receive_small(vi, buf, len);
if (unlikely(!skb))
return;
@@ -473,8 +472,8 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
pr_debug("Needs csum!\n");
if (!skb_partial_csum_set(skb,
- hdr->hdr.csum_start,
- hdr->hdr.csum_offset))
+ virtio16_to_cpu(vi->vdev, hdr->hdr.csum_start),
+ virtio16_to_cpu(vi->vdev, hdr->hdr.csum_offset)))
goto frame_err;
} else if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -514,7 +513,8 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
- skb_shinfo(skb)->gso_size = hdr->hdr.gso_size;
+ skb_shinfo(skb)->gso_size = virtio16_to_cpu(vi->vdev,
+ hdr->hdr.gso_size);
if (skb_shinfo(skb)->gso_size == 0) {
net_warn_ratelimited("%s: zero gso size.\n", dev->name);
goto frame_err;
@@ -535,11 +535,11 @@ frame_err:
dev_kfree_skb(skb);
}
-static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
+static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
+ gfp_t gfp)
{
- struct virtnet_info *vi = rq->vq->vdev->priv;
struct sk_buff *skb;
- struct skb_vnet_hdr *hdr;
+ struct virtio_net_hdr_mrg_rxbuf *hdr;
int err;
skb = __netdev_alloc_skb_ip_align(vi->dev, GOOD_PACKET_LEN, gfp);
@@ -550,7 +550,7 @@ static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
hdr = skb_vnet_hdr(skb);
sg_init_table(rq->sg, MAX_SKB_FRAGS + 2);
- sg_set_buf(rq->sg, &hdr->hdr, sizeof hdr->hdr);
+ sg_set_buf(rq->sg, hdr, vi->hdr_len);
skb_to_sgvec(skb, rq->sg + 1, 0, skb->len);
err = virtqueue_add_inbuf(rq->vq, rq->sg, 2, skb, gfp);
@@ -560,7 +560,8 @@ static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
return err;
}
-static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
+static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
+ gfp_t gfp)
{
struct page *first, *list = NULL;
char *p;
@@ -591,8 +592,8 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp)
p = page_address(first);
/* rq->sg[0], rq->sg[1] share the same page */
- /* a separated rq->sg[0] for virtio_net_hdr only due to QEMU bug */
- sg_set_buf(&rq->sg[0], p, sizeof(struct virtio_net_hdr));
+ /* a separated rq->sg[0] for header - required in case !any_header_sg */
+ sg_set_buf(&rq->sg[0], p, vi->hdr_len);
/* rq->sg[1] for data packet, from offset */
offset = sizeof(struct padded_vnet_hdr);
@@ -660,9 +661,9 @@ static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
* before we're receiving packets, or from refill_work which is
* careful to disable receiving (using napi_disable).
*/
-static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
+static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
+ gfp_t gfp)
{
- struct virtnet_info *vi = rq->vq->vdev->priv;
int err;
bool oom;
@@ -671,9 +672,9 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
if (vi->mergeable_rx_bufs)
err = add_recvbuf_mergeable(rq, gfp);
else if (vi->big_packets)
- err = add_recvbuf_big(rq, gfp);
+ err = add_recvbuf_big(vi, rq, gfp);
else
- err = add_recvbuf_small(rq, gfp);
+ err = add_recvbuf_small(vi, rq, gfp);
oom = err == -ENOMEM;
if (err)
@@ -722,7 +723,7 @@ static void refill_work(struct work_struct *work)
struct receive_queue *rq = &vi->rq[i];
napi_disable(&rq->napi);
- still_empty = !try_fill_recv(rq, GFP_KERNEL);
+ still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
virtnet_napi_enable(rq);
/* In theory, this can happen: if we don't get any buffers in
@@ -741,12 +742,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget)
while (received < budget &&
(buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
- receive_buf(rq, buf, len);
+ receive_buf(vi, rq, buf, len);
received++;
}
if (rq->vq->num_free > virtqueue_get_vring_size(rq->vq) / 2) {
- if (!try_fill_recv(rq, GFP_ATOMIC))
+ if (!try_fill_recv(vi, rq, GFP_ATOMIC))
schedule_delayed_work(&vi->refill, 0);
}
@@ -822,7 +823,7 @@ static int virtnet_open(struct net_device *dev)
for (i = 0; i < vi->max_queue_pairs; i++) {
if (i < vi->curr_queue_pairs)
/* Make sure we have some buffers: if oom use wq. */
- if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
schedule_delayed_work(&vi->refill, 0);
virtnet_napi_enable(&vi->rq[i]);
}
@@ -851,18 +852,14 @@ static void free_old_xmit_skbs(struct send_queue *sq)
static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
{
- struct skb_vnet_hdr *hdr;
+ struct virtio_net_hdr_mrg_rxbuf *hdr;
const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
struct virtnet_info *vi = sq->vq->vdev->priv;
unsigned num_sg;
- unsigned hdr_len;
+ unsigned hdr_len = vi->hdr_len;
bool can_push;
pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
- if (vi->mergeable_rx_bufs)
- hdr_len = sizeof hdr->mhdr;
- else
- hdr_len = sizeof hdr->hdr;
can_push = vi->any_header_sg &&
!((unsigned long)skb->data & (__alignof__(*hdr) - 1)) &&
@@ -870,22 +867,25 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
/* Even if we can, don't push here yet as this would skew
* csum_start offset below. */
if (can_push)
- hdr = (struct skb_vnet_hdr *)(skb->data - hdr_len);
+ hdr = (struct virtio_net_hdr_mrg_rxbuf *)(skb->data - hdr_len);
else
hdr = skb_vnet_hdr(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
- hdr->hdr.csum_start = skb_checksum_start_offset(skb);
- hdr->hdr.csum_offset = skb->csum_offset;
+ hdr->hdr.csum_start = cpu_to_virtio16(vi->vdev,
+ skb_checksum_start_offset(skb));
+ hdr->hdr.csum_offset = cpu_to_virtio16(vi->vdev,
+ skb->csum_offset);
} else {
hdr->hdr.flags = 0;
hdr->hdr.csum_offset = hdr->hdr.csum_start = 0;
}
if (skb_is_gso(skb)) {
- hdr->hdr.hdr_len = skb_headlen(skb);
- hdr->hdr.gso_size = skb_shinfo(skb)->gso_size;
+ hdr->hdr.hdr_len = cpu_to_virtio16(vi->vdev, skb_headlen(skb));
+ hdr->hdr.gso_size = cpu_to_virtio16(vi->vdev,
+ skb_shinfo(skb)->gso_size);
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
@@ -900,7 +900,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
}
if (vi->mergeable_rx_bufs)
- hdr->mhdr.num_buffers = 0;
+ hdr->num_buffers = 0;
sg_init_table(sq->sg, MAX_SKB_FRAGS + 2);
if (can_push) {
@@ -1030,7 +1030,8 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p)
"Failed to set mac address by vq command.\n");
return -EINVAL;
}
- } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) {
+ } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) &&
+ !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
unsigned int i;
/* Naturally, this has an atomicity problem. */
@@ -1112,7 +1113,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
return 0;
- s.virtqueue_pairs = queue_pairs;
+ s.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
sg_init_one(&sg, &s, sizeof(s));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
@@ -1189,7 +1190,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
sg_init_table(sg, 2);
/* Store the unicast list and count in the front of the buffer */
- mac_data->entries = uc_count;
+ mac_data->entries = cpu_to_virtio32(vi->vdev, uc_count);
i = 0;
netdev_for_each_uc_addr(ha, dev)
memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
@@ -1200,7 +1201,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
/* multicast list and count fill the end */
mac_data = (void *)&mac_data->macs[uc_count][0];
- mac_data->entries = mc_count;
+ mac_data->entries = cpu_to_virtio32(vi->vdev, mc_count);
i = 0;
netdev_for_each_mc_addr(ha, dev)
memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
@@ -1805,18 +1806,20 @@ static int virtnet_probe(struct virtio_device *vdev)
if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
vi->mergeable_rx_bufs = true;
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) ||
+ virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
+ vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ else
+ vi->hdr_len = sizeof(struct virtio_net_hdr);
+
if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT))
vi->any_header_sg = true;
if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
vi->has_cvq = true;
- if (vi->any_header_sg) {
- if (vi->mergeable_rx_bufs)
- dev->needed_headroom = sizeof(struct virtio_net_hdr_mrg_rxbuf);
- else
- dev->needed_headroom = sizeof(struct virtio_net_hdr);
- }
+ if (vi->any_header_sg)
+ dev->needed_headroom = vi->hdr_len;
/* Use single tx/rx queue pair as default */
vi->curr_queue_pairs = 1;
@@ -1844,7 +1847,7 @@ static int virtnet_probe(struct virtio_device *vdev)
/* Last of all, set up some receive buffers. */
for (i = 0; i < vi->curr_queue_pairs; i++) {
- try_fill_recv(&vi->rq[i], GFP_KERNEL);
+ try_fill_recv(vi, &vi->rq[i], GFP_KERNEL);
/* If we didn't even get one input buffer, we're useless. */
if (vi->rq[i].vq->num_free ==
@@ -1964,7 +1967,7 @@ static int virtnet_restore(struct virtio_device *vdev)
if (netif_running(vi->dev)) {
for (i = 0; i < vi->curr_queue_pairs; i++)
- if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
schedule_delayed_work(&vi->refill, 0);
for (i = 0; i < vi->max_queue_pairs; i++)
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index a34b50690b4..e1a10232a94 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -207,7 +207,7 @@ static void rproc_virtio_reset(struct virtio_device *vdev)
}
/* provide the vdev features as retrieved from the firmware */
-static u32 rproc_virtio_get_features(struct virtio_device *vdev)
+static u64 rproc_virtio_get_features(struct virtio_device *vdev)
{
struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
struct fw_rsc_vdev *rsc;
@@ -217,7 +217,7 @@ static u32 rproc_virtio_get_features(struct virtio_device *vdev)
return rsc->dfeatures;
}
-static void rproc_virtio_finalize_features(struct virtio_device *vdev)
+static int rproc_virtio_finalize_features(struct virtio_device *vdev)
{
struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
struct fw_rsc_vdev *rsc;
@@ -227,11 +227,16 @@ static void rproc_virtio_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features */
vring_transport_features(vdev);
+ /* Make sure we don't have any features > 32 bits! */
+ BUG_ON((u32)vdev->features != vdev->features);
+
/*
* Remember the finalized features of our vdev, and provide it
* to the remote processor once it is powered on.
*/
- rsc->gfeatures = vdev->features[0];
+ rsc->gfeatures = vdev->features;
+
+ return 0;
}
static void rproc_virtio_get(struct virtio_device *vdev, unsigned offset,
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index 643129070c5..dd65c8b4c7f 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -80,7 +80,7 @@ static unsigned desc_size(const struct kvm_device_desc *desc)
}
/* This gets the device's feature bits. */
-static u32 kvm_get_features(struct virtio_device *vdev)
+static u64 kvm_get_features(struct virtio_device *vdev)
{
unsigned int i;
u32 features = 0;
@@ -93,7 +93,7 @@ static u32 kvm_get_features(struct virtio_device *vdev)
return features;
}
-static void kvm_finalize_features(struct virtio_device *vdev)
+static int kvm_finalize_features(struct virtio_device *vdev)
{
unsigned int i, bits;
struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
@@ -103,12 +103,17 @@ static void kvm_finalize_features(struct virtio_device *vdev)
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
+ /* Make sure we don't have any features > 32 bits! */
+ BUG_ON((u32)vdev->features != vdev->features);
+
memset(out_features, 0, desc->feature_len);
bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
for (i = 0; i < bits; i++) {
- if (test_bit(i, vdev->features))
+ if (__virtio_test_bit(vdev, i))
out_features[i / 8] |= (1 << (i % 8));
}
+
+ return 0;
}
/*
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index bda52f18e96..71d7802aa8b 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -55,6 +55,7 @@ struct virtio_ccw_device {
struct ccw_device *cdev;
__u32 curr_io;
int err;
+ unsigned int revision; /* Transport revision */
wait_queue_head_t wait_q;
spinlock_t lock;
struct list_head virtqueues;
@@ -67,13 +68,22 @@ struct virtio_ccw_device {
void *airq_info;
};
-struct vq_info_block {
+struct vq_info_block_legacy {
__u64 queue;
__u32 align;
__u16 index;
__u16 num;
} __packed;
+struct vq_info_block {
+ __u64 desc;
+ __u32 res0;
+ __u16 index;
+ __u16 num;
+ __u64 avail;
+ __u64 used;
+} __packed;
+
struct virtio_feature_desc {
__u32 features;
__u8 index;
@@ -86,11 +96,23 @@ struct virtio_thinint_area {
u8 isc;
} __packed;
+struct virtio_rev_info {
+ __u16 revision;
+ __u16 length;
+ __u8 data[];
+};
+
+/* the highest virtio-ccw revision we support */
+#define VIRTIO_CCW_REV_MAX 1
+
struct virtio_ccw_vq_info {
struct virtqueue *vq;
int num;
void *queue;
- struct vq_info_block *info_block;
+ union {
+ struct vq_info_block s;
+ struct vq_info_block_legacy l;
+ } *info_block;
int bit_nr;
struct list_head node;
long cookie;
@@ -122,6 +144,7 @@ static struct airq_info *airq_areas[MAX_AIRQ_AREAS];
#define CCW_CMD_WRITE_STATUS 0x31
#define CCW_CMD_READ_VQ_CONF 0x32
#define CCW_CMD_SET_IND_ADAPTER 0x73
+#define CCW_CMD_SET_VIRTIO_REV 0x83
#define VIRTIO_CCW_DOING_SET_VQ 0x00010000
#define VIRTIO_CCW_DOING_RESET 0x00040000
@@ -134,6 +157,7 @@ static struct airq_info *airq_areas[MAX_AIRQ_AREAS];
#define VIRTIO_CCW_DOING_READ_VQ_CONF 0x02000000
#define VIRTIO_CCW_DOING_SET_CONF_IND 0x04000000
#define VIRTIO_CCW_DOING_SET_IND_ADAPTER 0x08000000
+#define VIRTIO_CCW_DOING_SET_VIRTIO_REV 0x10000000
#define VIRTIO_CCW_INTPARM_MASK 0xffff0000
static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev)
@@ -399,13 +423,22 @@ static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw)
spin_unlock_irqrestore(&vcdev->lock, flags);
/* Release from host. */
- info->info_block->queue = 0;
- info->info_block->align = 0;
- info->info_block->index = index;
- info->info_block->num = 0;
+ if (vcdev->revision == 0) {
+ info->info_block->l.queue = 0;
+ info->info_block->l.align = 0;
+ info->info_block->l.index = index;
+ info->info_block->l.num = 0;
+ ccw->count = sizeof(info->info_block->l);
+ } else {
+ info->info_block->s.desc = 0;
+ info->info_block->s.index = index;
+ info->info_block->s.num = 0;
+ info->info_block->s.avail = 0;
+ info->info_block->s.used = 0;
+ ccw->count = sizeof(info->info_block->s);
+ }
ccw->cmd_code = CCW_CMD_SET_VQ;
ccw->flags = 0;
- ccw->count = sizeof(*info->info_block);
ccw->cda = (__u32)(unsigned long)(info->info_block);
ret = ccw_io_helper(vcdev, ccw,
VIRTIO_CCW_DOING_SET_VQ | index);
@@ -488,13 +521,22 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev,
}
/* Register it with the host. */
- info->info_block->queue = (__u64)info->queue;
- info->info_block->align = KVM_VIRTIO_CCW_RING_ALIGN;
- info->info_block->index = i;
- info->info_block->num = info->num;
+ if (vcdev->revision == 0) {
+ info->info_block->l.queue = (__u64)info->queue;
+ info->info_block->l.align = KVM_VIRTIO_CCW_RING_ALIGN;
+ info->info_block->l.index = i;
+ info->info_block->l.num = info->num;
+ ccw->count = sizeof(info->info_block->l);
+ } else {
+ info->info_block->s.desc = (__u64)info->queue;
+ info->info_block->s.index = i;
+ info->info_block->s.num = info->num;
+ info->info_block->s.avail = (__u64)virtqueue_get_avail(vq);
+ info->info_block->s.used = (__u64)virtqueue_get_used(vq);
+ ccw->count = sizeof(info->info_block->s);
+ }
ccw->cmd_code = CCW_CMD_SET_VQ;
ccw->flags = 0;
- ccw->count = sizeof(*info->info_block);
ccw->cda = (__u32)(unsigned long)(info->info_block);
err = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_VQ | i);
if (err) {
@@ -660,11 +702,12 @@ static void virtio_ccw_reset(struct virtio_device *vdev)
kfree(ccw);
}
-static u32 virtio_ccw_get_features(struct virtio_device *vdev)
+static u64 virtio_ccw_get_features(struct virtio_device *vdev)
{
struct virtio_ccw_device *vcdev = to_vc_device(vdev);
struct virtio_feature_desc *features;
- int ret, rc;
+ int ret;
+ u64 rc;
struct ccw1 *ccw;
ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
@@ -677,7 +720,6 @@ static u32 virtio_ccw_get_features(struct virtio_device *vdev)
goto out_free;
}
/* Read the feature bits from the host. */
- /* TODO: Features > 32 bits */
features->index = 0;
ccw->cmd_code = CCW_CMD_READ_FEAT;
ccw->flags = 0;
@@ -691,46 +733,79 @@ static u32 virtio_ccw_get_features(struct virtio_device *vdev)
rc = le32_to_cpu(features->features);
+ if (vcdev->revision == 0)
+ goto out_free;
+
+ /* Read second half of the feature bits from the host. */
+ features->index = 1;
+ ccw->cmd_code = CCW_CMD_READ_FEAT;
+ ccw->flags = 0;
+ ccw->count = sizeof(*features);
+ ccw->cda = (__u32)(unsigned long)features;
+ ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_FEAT);
+ if (ret == 0)
+ rc |= (u64)le32_to_cpu(features->features) << 32;
+
out_free:
kfree(features);
kfree(ccw);
return rc;
}
-static void virtio_ccw_finalize_features(struct virtio_device *vdev)
+static int virtio_ccw_finalize_features(struct virtio_device *vdev)
{
struct virtio_ccw_device *vcdev = to_vc_device(vdev);
struct virtio_feature_desc *features;
- int i;
struct ccw1 *ccw;
+ int ret;
+
+ if (vcdev->revision >= 1 &&
+ !__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
+ dev_err(&vdev->dev, "virtio: device uses revision 1 "
+ "but does not have VIRTIO_F_VERSION_1\n");
+ return -EINVAL;
+ }
ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
if (!ccw)
- return;
+ return -ENOMEM;
features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL);
- if (!features)
+ if (!features) {
+ ret = -ENOMEM;
goto out_free;
-
+ }
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
- for (i = 0; i < sizeof(*vdev->features) / sizeof(features->features);
- i++) {
- int highbits = i % 2 ? 32 : 0;
- features->index = i;
- features->features = cpu_to_le32(vdev->features[i / 2]
- >> highbits);
- /* Write the feature bits to the host. */
- ccw->cmd_code = CCW_CMD_WRITE_FEAT;
- ccw->flags = 0;
- ccw->count = sizeof(*features);
- ccw->cda = (__u32)(unsigned long)features;
- ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT);
- }
+ features->index = 0;
+ features->features = cpu_to_le32((u32)vdev->features);
+ /* Write the first half of the feature bits to the host. */
+ ccw->cmd_code = CCW_CMD_WRITE_FEAT;
+ ccw->flags = 0;
+ ccw->count = sizeof(*features);
+ ccw->cda = (__u32)(unsigned long)features;
+ ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT);
+ if (ret)
+ goto out_free;
+
+ if (vcdev->revision == 0)
+ goto out_free;
+
+ features->index = 1;
+ features->features = cpu_to_le32(vdev->features >> 32);
+ /* Write the second half of the feature bits to the host. */
+ ccw->cmd_code = CCW_CMD_WRITE_FEAT;
+ ccw->flags = 0;
+ ccw->count = sizeof(*features);
+ ccw->cda = (__u32)(unsigned long)features;
+ ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT);
+
out_free:
kfree(features);
kfree(ccw);
+
+ return ret;
}
static void virtio_ccw_get_config(struct virtio_device *vdev,
@@ -806,7 +881,9 @@ static u8 virtio_ccw_get_status(struct virtio_device *vdev)
static void virtio_ccw_set_status(struct virtio_device *vdev, u8 status)
{
struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+ u8 old_status = *vcdev->status;
struct ccw1 *ccw;
+ int ret;
ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
if (!ccw)
@@ -818,7 +895,10 @@ static void virtio_ccw_set_status(struct virtio_device *vdev, u8 status)
ccw->flags = 0;
ccw->count = sizeof(status);
ccw->cda = (__u32)(unsigned long)vcdev->status;
- ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_STATUS);
+ ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_STATUS);
+ /* Write failed? We assume status is unchanged. */
+ if (ret)
+ *vcdev->status = old_status;
kfree(ccw);
}
@@ -919,6 +999,7 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev,
case VIRTIO_CCW_DOING_RESET:
case VIRTIO_CCW_DOING_READ_VQ_CONF:
case VIRTIO_CCW_DOING_SET_IND_ADAPTER:
+ case VIRTIO_CCW_DOING_SET_VIRTIO_REV:
vcdev->curr_io &= ~activity;
wake_up(&vcdev->wait_q);
break;
@@ -1034,6 +1115,51 @@ static int virtio_ccw_offline(struct ccw_device *cdev)
return 0;
}
+static int virtio_ccw_set_transport_rev(struct virtio_ccw_device *vcdev)
+{
+ struct virtio_rev_info *rev;
+ struct ccw1 *ccw;
+ int ret;
+
+ ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+ if (!ccw)
+ return -ENOMEM;
+ rev = kzalloc(sizeof(*rev), GFP_DMA | GFP_KERNEL);
+ if (!rev) {
+ kfree(ccw);
+ return -ENOMEM;
+ }
+
+ /* Set transport revision */
+ ccw->cmd_code = CCW_CMD_SET_VIRTIO_REV;
+ ccw->flags = 0;
+ ccw->count = sizeof(*rev);
+ ccw->cda = (__u32)(unsigned long)rev;
+
+ vcdev->revision = VIRTIO_CCW_REV_MAX;
+ do {
+ rev->revision = vcdev->revision;
+ /* none of our supported revisions carry payload */
+ rev->length = 0;
+ ret = ccw_io_helper(vcdev, ccw,
+ VIRTIO_CCW_DOING_SET_VIRTIO_REV);
+ if (ret == -EOPNOTSUPP) {
+ if (vcdev->revision == 0)
+ /*
+ * The host device does not support setting
+ * the revision: let's operate it in legacy
+ * mode.
+ */
+ ret = 0;
+ else
+ vcdev->revision--;
+ }
+ } while (ret == -EOPNOTSUPP);
+
+ kfree(ccw);
+ kfree(rev);
+ return ret;
+}
static int virtio_ccw_online(struct ccw_device *cdev)
{
@@ -1074,6 +1200,15 @@ static int virtio_ccw_online(struct ccw_device *cdev)
spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
vcdev->vdev.id.vendor = cdev->id.cu_type;
vcdev->vdev.id.device = cdev->id.cu_model;
+
+ if (virtio_device_is_legacy_only(vcdev->vdev.id)) {
+ vcdev->revision = 0;
+ } else {
+ ret = virtio_ccw_set_transport_rev(vcdev);
+ if (ret)
+ goto out_free;
+ }
+
ret = register_virtio_device(&vcdev->vdev);
if (ret) {
dev_warn(&cdev->dev, "Failed to register virtio device: %d\n",
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 22e70126425..c52bb5dfaed 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -158,7 +158,7 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
sc, resp->response, resp->status, resp->sense_len);
sc->result = resp->status;
- virtscsi_compute_resid(sc, resp->resid);
+ virtscsi_compute_resid(sc, virtio32_to_cpu(vscsi->vdev, resp->resid));
switch (resp->response) {
case VIRTIO_SCSI_S_OK:
set_host_byte(sc, DID_OK);
@@ -196,10 +196,13 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
break;
}
- WARN_ON(resp->sense_len > VIRTIO_SCSI_SENSE_SIZE);
+ WARN_ON(virtio32_to_cpu(vscsi->vdev, resp->sense_len) >
+ VIRTIO_SCSI_SENSE_SIZE);
if (sc->sense_buffer) {
memcpy(sc->sense_buffer, resp->sense,
- min_t(u32, resp->sense_len, VIRTIO_SCSI_SENSE_SIZE));
+ min_t(u32,
+ virtio32_to_cpu(vscsi->vdev, resp->sense_len),
+ VIRTIO_SCSI_SENSE_SIZE));
if (resp->sense_len)
set_driver_byte(sc, DRIVER_SENSE);
}
@@ -323,7 +326,7 @@ static void virtscsi_handle_transport_reset(struct virtio_scsi *vscsi,
unsigned int target = event->lun[1];
unsigned int lun = (event->lun[2] << 8) | event->lun[3];
- switch (event->reason) {
+ switch (virtio32_to_cpu(vscsi->vdev, event->reason)) {
case VIRTIO_SCSI_EVT_RESET_RESCAN:
scsi_add_device(shost, 0, target, lun);
break;
@@ -349,8 +352,8 @@ static void virtscsi_handle_param_change(struct virtio_scsi *vscsi,
struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
unsigned int target = event->lun[1];
unsigned int lun = (event->lun[2] << 8) | event->lun[3];
- u8 asc = event->reason & 255;
- u8 ascq = event->reason >> 8;
+ u8 asc = virtio32_to_cpu(vscsi->vdev, event->reason) & 255;
+ u8 ascq = virtio32_to_cpu(vscsi->vdev, event->reason) >> 8;
sdev = scsi_device_lookup(shost, 0, target, lun);
if (!sdev) {
@@ -374,12 +377,14 @@ static void virtscsi_handle_event(struct work_struct *work)
struct virtio_scsi *vscsi = event_node->vscsi;
struct virtio_scsi_event *event = &event_node->event;
- if (event->event & VIRTIO_SCSI_T_EVENTS_MISSED) {
- event->event &= ~VIRTIO_SCSI_T_EVENTS_MISSED;
+ if (event->event &
+ cpu_to_virtio32(vscsi->vdev, VIRTIO_SCSI_T_EVENTS_MISSED)) {
+ event->event &= ~cpu_to_virtio32(vscsi->vdev,
+ VIRTIO_SCSI_T_EVENTS_MISSED);
scsi_scan_host(virtio_scsi_host(vscsi->vdev));
}
- switch (event->event) {
+ switch (virtio32_to_cpu(vscsi->vdev, event->event)) {
case VIRTIO_SCSI_T_NO_EVENT:
break;
case VIRTIO_SCSI_T_TRANSPORT_RESET:
@@ -482,26 +487,28 @@ static int virtscsi_kick_cmd(struct virtio_scsi_vq *vq,
return err;
}
-static void virtio_scsi_init_hdr(struct virtio_scsi_cmd_req *cmd,
+static void virtio_scsi_init_hdr(struct virtio_device *vdev,
+ struct virtio_scsi_cmd_req *cmd,
struct scsi_cmnd *sc)
{
cmd->lun[0] = 1;
cmd->lun[1] = sc->device->id;
cmd->lun[2] = (sc->device->lun >> 8) | 0x40;
cmd->lun[3] = sc->device->lun & 0xff;
- cmd->tag = (unsigned long)sc;
+ cmd->tag = cpu_to_virtio64(vdev, (unsigned long)sc);
cmd->task_attr = VIRTIO_SCSI_S_SIMPLE;
cmd->prio = 0;
cmd->crn = 0;
}
-static void virtio_scsi_init_hdr_pi(struct virtio_scsi_cmd_req_pi *cmd_pi,
+static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
+ struct virtio_scsi_cmd_req_pi *cmd_pi,
struct scsi_cmnd *sc)
{
struct request *rq = sc->request;
struct blk_integrity *bi;
- virtio_scsi_init_hdr((struct virtio_scsi_cmd_req *)cmd_pi, sc);
+ virtio_scsi_init_hdr(vdev, (struct virtio_scsi_cmd_req *)cmd_pi, sc);
if (!rq || !scsi_prot_sg_count(sc))
return;
@@ -509,9 +516,13 @@ static void virtio_scsi_init_hdr_pi(struct virtio_scsi_cmd_req_pi *cmd_pi,
bi = blk_get_integrity(rq->rq_disk);
if (sc->sc_data_direction == DMA_TO_DEVICE)
- cmd_pi->pi_bytesout = blk_rq_sectors(rq) * bi->tuple_size;
+ cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
+ blk_rq_sectors(rq) *
+ bi->tuple_size);
else if (sc->sc_data_direction == DMA_FROM_DEVICE)
- cmd_pi->pi_bytesin = blk_rq_sectors(rq) * bi->tuple_size;
+ cmd_pi->pi_bytesin = cpu_to_virtio32(vdev,
+ blk_rq_sectors(rq) *
+ bi->tuple_size);
}
static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
@@ -536,11 +547,11 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
BUG_ON(sc->cmd_len > VIRTIO_SCSI_CDB_SIZE);
if (virtio_has_feature(vscsi->vdev, VIRTIO_SCSI_F_T10_PI)) {
- virtio_scsi_init_hdr_pi(&cmd->req.cmd_pi, sc);
+ virtio_scsi_init_hdr_pi(vscsi->vdev, &cmd->req.cmd_pi, sc);
memcpy(cmd->req.cmd_pi.cdb, sc->cmnd, sc->cmd_len);
req_size = sizeof(cmd->req.cmd_pi);
} else {
- virtio_scsi_init_hdr(&cmd->req.cmd, sc);
+ virtio_scsi_init_hdr(vscsi->vdev, &cmd->req.cmd, sc);
memcpy(cmd->req.cmd.cdb, sc->cmnd, sc->cmd_len);
req_size = sizeof(cmd->req.cmd);
}
@@ -669,7 +680,8 @@ static int virtscsi_device_reset(struct scsi_cmnd *sc)
cmd->sc = sc;
cmd->req.tmf = (struct virtio_scsi_ctrl_tmf_req){
.type = VIRTIO_SCSI_T_TMF,
- .subtype = VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET,
+ .subtype = cpu_to_virtio32(vscsi->vdev,
+ VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET),
.lun[0] = 1,
.lun[1] = sc->device->id,
.lun[2] = (sc->device->lun >> 8) | 0x40,
@@ -710,7 +722,7 @@ static int virtscsi_abort(struct scsi_cmnd *sc)
.lun[1] = sc->device->id,
.lun[2] = (sc->device->lun >> 8) | 0x40,
.lun[3] = sc->device->lun & 0xff,
- .tag = (unsigned long)sc,
+ .tag = cpu_to_virtio64(vscsi->vdev, (unsigned long)sc),
};
return virtscsi_tmf(vscsi, cmd);
}
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 8dae2f724a3..a935c254749 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -48,20 +48,21 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
* status internally; used for zerocopy tx only.
*/
/* Lower device DMA failed */
-#define VHOST_DMA_FAILED_LEN 3
+#define VHOST_DMA_FAILED_LEN ((__force __virtio32)3)
/* Lower device DMA done */
-#define VHOST_DMA_DONE_LEN 2
+#define VHOST_DMA_DONE_LEN ((__force __virtio32)2)
/* Lower device DMA in progress */
-#define VHOST_DMA_IN_PROGRESS 1
+#define VHOST_DMA_IN_PROGRESS ((__force __virtio32)1)
/* Buffer unused */
-#define VHOST_DMA_CLEAR_LEN 0
+#define VHOST_DMA_CLEAR_LEN ((__force __virtio32)0)
-#define VHOST_DMA_IS_DONE(len) ((len) >= VHOST_DMA_DONE_LEN)
+#define VHOST_DMA_IS_DONE(len) ((__force u32)(len) >= (__force u32)VHOST_DMA_DONE_LEN)
enum {
VHOST_NET_FEATURES = VHOST_FEATURES |
(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
- (1ULL << VIRTIO_NET_F_MRG_RXBUF),
+ (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+ (1ULL << VIRTIO_F_VERSION_1),
};
enum {
@@ -416,7 +417,7 @@ static void handle_tx(struct vhost_net *net)
struct ubuf_info *ubuf;
ubuf = nvq->ubuf_info + nvq->upend_idx;
- vq->heads[nvq->upend_idx].id = head;
+ vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
ubuf->callback = vhost_zerocopy_callback;
ubuf->ctx = nvq->ubufs;
@@ -500,6 +501,10 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
int headcount = 0;
unsigned d;
int r, nlogs = 0;
+ /* len is always initialized before use since we are always called with
+ * datalen > 0.
+ */
+ u32 uninitialized_var(len);
while (datalen > 0 && headcount < quota) {
if (unlikely(seg >= UIO_MAXIOV)) {
@@ -527,13 +532,14 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
nlogs += *log_num;
log += *log_num;
}
- heads[headcount].id = d;
- heads[headcount].len = iov_length(vq->iov + seg, in);
- datalen -= heads[headcount].len;
+ heads[headcount].id = cpu_to_vhost32(vq, d);
+ len = iov_length(vq->iov + seg, in);
+ heads[headcount].len = cpu_to_vhost32(vq, len);
+ datalen -= len;
++headcount;
seg += in;
}
- heads[headcount - 1].len += datalen;
+ heads[headcount - 1].len = cpu_to_vhost32(vq, len - datalen);
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
@@ -1025,7 +1031,8 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
size_t vhost_hlen, sock_hlen, hdr_len;
int i;
- hdr_len = (features & (1 << VIRTIO_NET_F_MRG_RXBUF)) ?
+ hdr_len = (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+ (1ULL << VIRTIO_F_VERSION_1))) ?
sizeof(struct virtio_net_hdr_mrg_rxbuf) :
sizeof(struct virtio_net_hdr);
if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index a17f1185066..01c01cb3933 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -168,6 +168,7 @@ enum {
VHOST_SCSI_VQ_IO = 2,
};
+/* Note: can't set VIRTIO_F_VERSION_1 yet, since that implies ANY_LAYOUT. */
enum {
VHOST_SCSI_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_SCSI_F_HOTPLUG) |
(1ULL << VIRTIO_SCSI_F_T10_PI)
@@ -577,8 +578,8 @@ tcm_vhost_allocate_evt(struct vhost_scsi *vs,
return NULL;
}
- evt->event.event = event;
- evt->event.reason = reason;
+ evt->event.event = cpu_to_vhost32(vq, event);
+ evt->event.reason = cpu_to_vhost32(vq, reason);
vs->vs_events_nr++;
return evt;
@@ -636,7 +637,7 @@ again:
}
if (vs->vs_events_missed) {
- event->event |= VIRTIO_SCSI_T_EVENTS_MISSED;
+ event->event |= cpu_to_vhost32(vq, VIRTIO_SCSI_T_EVENTS_MISSED);
vs->vs_events_missed = false;
}
@@ -695,12 +696,13 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
cmd, se_cmd->residual_count, se_cmd->scsi_status);
memset(&v_rsp, 0, sizeof(v_rsp));
- v_rsp.resid = se_cmd->residual_count;
+ v_rsp.resid = cpu_to_vhost32(cmd->tvc_vq, se_cmd->residual_count);
/* TODO is status_qualifier field needed? */
v_rsp.status = se_cmd->scsi_status;
- v_rsp.sense_len = se_cmd->scsi_sense_length;
+ v_rsp.sense_len = cpu_to_vhost32(cmd->tvc_vq,
+ se_cmd->scsi_sense_length);
memcpy(v_rsp.sense, cmd->tvc_sense_buf,
- v_rsp.sense_len);
+ se_cmd->scsi_sense_length);
ret = copy_to_user(cmd->tvc_resp, &v_rsp, sizeof(v_rsp));
if (likely(ret == 0)) {
struct vhost_scsi_virtqueue *q;
@@ -1095,14 +1097,14 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
", but wrong data_direction\n");
goto err_cmd;
}
- prot_bytes = v_req_pi.pi_bytesout;
+ prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesout);
} else if (v_req_pi.pi_bytesin) {
if (data_direction != DMA_FROM_DEVICE) {
vq_err(vq, "Received non zero di_pi_niov"
", but wrong data_direction\n");
goto err_cmd;
}
- prot_bytes = v_req_pi.pi_bytesin;
+ prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin);
}
if (prot_bytes) {
int tmp = 0;
@@ -1117,12 +1119,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
data_first += prot_niov;
data_niov = data_num - prot_niov;
}
- tag = v_req_pi.tag;
+ tag = vhost64_to_cpu(vq, v_req_pi.tag);
task_attr = v_req_pi.task_attr;
cdb = &v_req_pi.cdb[0];
lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF;
} else {
- tag = v_req.tag;
+ tag = vhost64_to_cpu(vq, v_req.tag);
task_attr = v_req.task_attr;
cdb = &v_req.cdb[0];
lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c90f4374442..ed71b5347a7 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -33,8 +33,8 @@ enum {
VHOST_MEMORY_F_LOG = 0x1,
};
-#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
-#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
+#define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
+#define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
poll_table *pt)
@@ -1001,7 +1001,7 @@ EXPORT_SYMBOL_GPL(vhost_log_write);
static int vhost_update_used_flags(struct vhost_virtqueue *vq)
{
void __user *used;
- if (__put_user(vq->used_flags, &vq->used->flags) < 0)
+ if (__put_user(cpu_to_vhost16(vq, vq->used_flags), &vq->used->flags) < 0)
return -EFAULT;
if (unlikely(vq->log_used)) {
/* Make sure the flag is seen before log. */
@@ -1019,7 +1019,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
{
- if (__put_user(vq->avail_idx, vhost_avail_event(vq)))
+ if (__put_user(cpu_to_vhost16(vq, vq->avail_idx), vhost_avail_event(vq)))
return -EFAULT;
if (unlikely(vq->log_used)) {
void __user *used;
@@ -1038,6 +1038,7 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
int vhost_init_used(struct vhost_virtqueue *vq)
{
+ __virtio16 last_used_idx;
int r;
if (!vq->private_data)
return 0;
@@ -1046,7 +1047,13 @@ int vhost_init_used(struct vhost_virtqueue *vq)
if (r)
return r;
vq->signalled_used_valid = false;
- return get_user(vq->last_used_idx, &vq->used->idx);
+ if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx))
+ return -EFAULT;
+ r = __get_user(last_used_idx, &vq->used->idx);
+ if (r)
+ return r;
+ vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx);
+ return 0;
}
EXPORT_SYMBOL_GPL(vhost_init_used);
@@ -1087,16 +1094,16 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
/* Each buffer in the virtqueues is actually a chain of descriptors. This
* function returns the next descriptor in the chain,
* or -1U if we're at the end. */
-static unsigned next_desc(struct vring_desc *desc)
+static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc)
{
unsigned int next;
/* If this descriptor says it doesn't chain, we're done. */
- if (!(desc->flags & VRING_DESC_F_NEXT))
+ if (!(desc->flags & cpu_to_vhost16(vq, VRING_DESC_F_NEXT)))
return -1U;
/* Check they're not leading us off end of descriptors. */
- next = desc->next;
+ next = vhost16_to_cpu(vq, desc->next);
/* Make sure compiler knows to grab that: we don't want it changing! */
/* We will use the result as an index in an array, so most
* architectures only need a compiler barrier here. */
@@ -1113,18 +1120,19 @@ static int get_indirect(struct vhost_virtqueue *vq,
{
struct vring_desc desc;
unsigned int i = 0, count, found = 0;
+ u32 len = vhost32_to_cpu(vq, indirect->len);
int ret;
/* Sanity check */
- if (unlikely(indirect->len % sizeof desc)) {
+ if (unlikely(len % sizeof desc)) {
vq_err(vq, "Invalid length in indirect descriptor: "
"len 0x%llx not multiple of 0x%zx\n",
- (unsigned long long)indirect->len,
+ (unsigned long long)len,
sizeof desc);
return -EINVAL;
}
- ret = translate_desc(vq, indirect->addr, indirect->len, vq->indirect,
+ ret = translate_desc(vq, vhost64_to_cpu(vq, indirect->addr), len, vq->indirect,
UIO_MAXIOV);
if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d in indirect.\n", ret);
@@ -1135,7 +1143,7 @@ static int get_indirect(struct vhost_virtqueue *vq,
* architectures only need a compiler barrier here. */
read_barrier_depends();
- count = indirect->len / sizeof desc;
+ count = len / sizeof desc;
/* Buffers are chained via a 16 bit next field, so
* we can have at most 2^16 of these. */
if (unlikely(count > USHRT_MAX + 1)) {
@@ -1155,16 +1163,17 @@ static int get_indirect(struct vhost_virtqueue *vq,
if (unlikely(memcpy_fromiovec((unsigned char *)&desc,
vq->indirect, sizeof desc))) {
vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
- i, (size_t)indirect->addr + i * sizeof desc);
+ i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
return -EINVAL;
}
- if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) {
+ if (unlikely(desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT))) {
vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
- i, (size_t)indirect->addr + i * sizeof desc);
+ i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
return -EINVAL;
}
- ret = translate_desc(vq, desc.addr, desc.len, iov + iov_count,
+ ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
+ vhost32_to_cpu(vq, desc.len), iov + iov_count,
iov_size - iov_count);
if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d indirect idx %d\n",
@@ -1172,11 +1181,11 @@ static int get_indirect(struct vhost_virtqueue *vq,
return ret;
}
/* If this is an input descriptor, increment that count. */
- if (desc.flags & VRING_DESC_F_WRITE) {
+ if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE)) {
*in_num += ret;
if (unlikely(log)) {
- log[*log_num].addr = desc.addr;
- log[*log_num].len = desc.len;
+ log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
+ log[*log_num].len = vhost32_to_cpu(vq, desc.len);
++*log_num;
}
} else {
@@ -1189,7 +1198,7 @@ static int get_indirect(struct vhost_virtqueue *vq,
}
*out_num += ret;
}
- } while ((i = next_desc(&desc)) != -1);
+ } while ((i = next_desc(vq, &desc)) != -1);
return 0;
}
@@ -1209,15 +1218,18 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
struct vring_desc desc;
unsigned int i, head, found = 0;
u16 last_avail_idx;
+ __virtio16 avail_idx;
+ __virtio16 ring_head;
int ret;
/* Check it isn't doing very strange things with descriptor numbers. */
last_avail_idx = vq->last_avail_idx;
- if (unlikely(__get_user(vq->avail_idx, &vq->avail->idx))) {
+ if (unlikely(__get_user(avail_idx, &vq->avail->idx))) {
vq_err(vq, "Failed to access avail idx at %p\n",
&vq->avail->idx);
return -EFAULT;
}
+ vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
vq_err(vq, "Guest moved used index from %u to %u",
@@ -1234,7 +1246,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
- if (unlikely(__get_user(head,
+ if (unlikely(__get_user(ring_head,
&vq->avail->ring[last_avail_idx % vq->num]))) {
vq_err(vq, "Failed to read head: idx %d address %p\n",
last_avail_idx,
@@ -1242,6 +1254,8 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
return -EFAULT;
}
+ head = vhost16_to_cpu(vq, ring_head);
+
/* If their number is silly, that's an error. */
if (unlikely(head >= vq->num)) {
vq_err(vq, "Guest says index %u > %u is available",
@@ -1274,7 +1288,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
i, vq->desc + i);
return -EFAULT;
}
- if (desc.flags & VRING_DESC_F_INDIRECT) {
+ if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT)) {
ret = get_indirect(vq, iov, iov_size,
out_num, in_num,
log, log_num, &desc);
@@ -1286,20 +1300,21 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
continue;
}
- ret = translate_desc(vq, desc.addr, desc.len, iov + iov_count,
+ ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
+ vhost32_to_cpu(vq, desc.len), iov + iov_count,
iov_size - iov_count);
if (unlikely(ret < 0)) {
vq_err(vq, "Translation failure %d descriptor idx %d\n",
ret, i);
return ret;
}
- if (desc.flags & VRING_DESC_F_WRITE) {
+ if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE)) {
/* If this is an input descriptor,
* increment that count. */
*in_num += ret;
if (unlikely(log)) {
- log[*log_num].addr = desc.addr;
- log[*log_num].len = desc.len;
+ log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
+ log[*log_num].len = vhost32_to_cpu(vq, desc.len);
++*log_num;
}
} else {
@@ -1312,7 +1327,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
}
*out_num += ret;
}
- } while ((i = next_desc(&desc)) != -1);
+ } while ((i = next_desc(vq, &desc)) != -1);
/* On success, increment avail index. */
vq->last_avail_idx++;
@@ -1335,7 +1350,10 @@ EXPORT_SYMBOL_GPL(vhost_discard_vq_desc);
* want to notify the guest, using eventfd. */
int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
{
- struct vring_used_elem heads = { head, len };
+ struct vring_used_elem heads = {
+ cpu_to_vhost32(vq, head),
+ cpu_to_vhost32(vq, len)
+ };
return vhost_add_used_n(vq, &heads, 1);
}
@@ -1404,7 +1422,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
/* Make sure buffer is written before we update index. */
smp_wmb();
- if (put_user(vq->last_used_idx, &vq->used->idx)) {
+ if (__put_user(cpu_to_vhost16(vq, vq->last_used_idx), &vq->used->idx)) {
vq_err(vq, "Failed to increment used idx");
return -EFAULT;
}
@@ -1422,7 +1440,8 @@ EXPORT_SYMBOL_GPL(vhost_add_used_n);
static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
- __u16 old, new, event;
+ __u16 old, new;
+ __virtio16 event;
bool v;
/* Flush out used index updates. This is paired
* with the barrier that the Guest executes when enabling
@@ -1434,12 +1453,12 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
return true;
if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
- __u16 flags;
+ __virtio16 flags;
if (__get_user(flags, &vq->avail->flags)) {
vq_err(vq, "Failed to get flags");
return true;
}
- return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
+ return !(flags & cpu_to_vhost16(vq, VRING_AVAIL_F_NO_INTERRUPT));
}
old = vq->signalled_used;
v = vq->signalled_used_valid;
@@ -1449,11 +1468,11 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
if (unlikely(!v))
return true;
- if (get_user(event, vhost_used_event(vq))) {
+ if (__get_user(event, vhost_used_event(vq))) {
vq_err(vq, "Failed to get used event idx");
return true;
}
- return vring_need_event(event, new, old);
+ return vring_need_event(vhost16_to_cpu(vq, event), new, old);
}
/* This actually signals the guest, using eventfd. */
@@ -1488,7 +1507,7 @@ EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);
/* OK, now we need to know about added descriptors. */
bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
- u16 avail_idx;
+ __virtio16 avail_idx;
int r;
if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
@@ -1519,7 +1538,7 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
return false;
}
- return avail_idx != vq->avail_idx;
+ return vhost16_to_cpu(vq, avail_idx) != vq->avail_idx;
}
EXPORT_SYMBOL_GPL(vhost_enable_notify);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 3eda654b8f5..8c1c792900b 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -12,8 +12,6 @@
#include <linux/virtio_ring.h>
#include <linux/atomic.h>
-struct vhost_device;
-
struct vhost_work;
typedef void (*vhost_work_fn_t)(struct vhost_work *work);
@@ -54,8 +52,6 @@ struct vhost_log {
u64 len;
};
-struct vhost_virtqueue;
-
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
@@ -106,7 +102,7 @@ struct vhost_virtqueue {
/* Protected by virtqueue mutex. */
struct vhost_memory *memory;
void *private_data;
- unsigned acked_features;
+ u64 acked_features;
/* Log write descriptors */
void __user *log_base;
struct vhost_log *log;
@@ -172,8 +168,39 @@ enum {
(1ULL << VHOST_F_LOG_ALL),
};
-static inline int vhost_has_feature(struct vhost_virtqueue *vq, int bit)
+static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
+{
+ return vq->acked_features & (1ULL << bit);
+}
+
+/* Memory accessors */
+static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val)
+{
+ return __virtio16_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio16 cpu_to_vhost16(struct vhost_virtqueue *vq, u16 val)
+{
+ return __cpu_to_virtio16(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u32 vhost32_to_cpu(struct vhost_virtqueue *vq, __virtio32 val)
+{
+ return __virtio32_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio32 cpu_to_vhost32(struct vhost_virtqueue *vq, u32 val)
+{
+ return __cpu_to_virtio32(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u64 vhost64_to_cpu(struct vhost_virtqueue *vq, __virtio64 val)
+{
+ return __virtio64_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio64 cpu_to_vhost64(struct vhost_virtqueue *vq, u64 val)
{
- return vq->acked_features & (1 << bit);
+ return __cpu_to_virtio64(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
}
#endif
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 9076635697b..bf5104b5689 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,4 +1,5 @@
obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
+virtio_pci-y := virtio_pci_legacy.o virtio_pci_common.o
obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index df598dd8c5c..f2266586878 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -3,6 +3,7 @@
#include <linux/virtio_config.h>
#include <linux/module.h>
#include <linux/idr.h>
+#include <uapi/linux/virtio_ids.h>
/* Unique numbering for virtio devices. */
static DEFINE_IDA(virtio_index_ida);
@@ -49,9 +50,9 @@ static ssize_t features_show(struct device *_d,
/* We actually represent this as a bitstring, as it could be
* arbitrary length in future. */
- for (i = 0; i < ARRAY_SIZE(dev->features)*BITS_PER_LONG; i++)
+ for (i = 0; i < sizeof(dev->features)*8; i++)
len += sprintf(buf+len, "%c",
- test_bit(i, dev->features) ? '1' : '0');
+ __virtio_test_bit(dev, i) ? '1' : '0');
len += sprintf(buf+len, "\n");
return len;
}
@@ -113,6 +114,13 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
for (i = 0; i < drv->feature_table_size; i++)
if (drv->feature_table[i] == fbit)
return;
+
+ if (drv->feature_table_legacy) {
+ for (i = 0; i < drv->feature_table_size_legacy; i++)
+ if (drv->feature_table_legacy[i] == fbit)
+ return;
+ }
+
BUG();
}
EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
@@ -159,7 +167,10 @@ static int virtio_dev_probe(struct device *_d)
int err, i;
struct virtio_device *dev = dev_to_virtio(_d);
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
- u32 device_features;
+ u64 device_features;
+ u64 driver_features;
+ u64 driver_features_legacy;
+ unsigned status;
/* We have a driver! */
add_status(dev, VIRTIO_CONFIG_S_DRIVER);
@@ -167,34 +178,66 @@ static int virtio_dev_probe(struct device *_d)
/* Figure out what features the device supports. */
device_features = dev->config->get_features(dev);
- /* Features supported by both device and driver into dev->features. */
- memset(dev->features, 0, sizeof(dev->features));
+ /* Figure out what features the driver supports. */
+ driver_features = 0;
for (i = 0; i < drv->feature_table_size; i++) {
unsigned int f = drv->feature_table[i];
- BUG_ON(f >= 32);
- if (device_features & (1 << f))
- set_bit(f, dev->features);
+ BUG_ON(f >= 64);
+ driver_features |= (1ULL << f);
+ }
+
+ /* Some drivers have a separate feature table for virtio v1.0 */
+ if (drv->feature_table_legacy) {
+ driver_features_legacy = 0;
+ for (i = 0; i < drv->feature_table_size_legacy; i++) {
+ unsigned int f = drv->feature_table_legacy[i];
+ BUG_ON(f >= 64);
+ driver_features_legacy |= (1ULL << f);
+ }
+ } else {
+ driver_features_legacy = driver_features;
}
+ if (device_features & (1ULL << VIRTIO_F_VERSION_1))
+ dev->features = driver_features & device_features;
+ else
+ dev->features = driver_features_legacy & device_features;
+
/* Transport features always preserved to pass to finalize_features. */
for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
- if (device_features & (1 << i))
- set_bit(i, dev->features);
+ if (device_features & (1ULL << i))
+ __virtio_set_bit(dev, i);
- dev->config->finalize_features(dev);
+ err = dev->config->finalize_features(dev);
+ if (err)
+ goto err;
+
+ if (virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+ add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK);
+ status = dev->config->get_status(dev);
+ if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+ dev_err(_d, "virtio: device refuses features: %x\n",
+ status);
+ err = -ENODEV;
+ goto err;
+ }
+ }
err = drv->probe(dev);
if (err)
- add_status(dev, VIRTIO_CONFIG_S_FAILED);
- else {
- add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
- if (drv->scan)
- drv->scan(dev);
+ goto err;
- virtio_config_enable(dev);
- }
+ add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+ if (drv->scan)
+ drv->scan(dev);
+
+ virtio_config_enable(dev);
+ return 0;
+err:
+ add_status(dev, VIRTIO_CONFIG_S_FAILED);
return err;
+
}
static int virtio_dev_remove(struct device *_d)
@@ -223,6 +266,12 @@ static struct bus_type virtio_bus = {
.remove = virtio_dev_remove,
};
+bool virtio_device_is_legacy_only(struct virtio_device_id id)
+{
+ return id.device == VIRTIO_ID_BALLOON;
+}
+EXPORT_SYMBOL_GPL(virtio_device_is_legacy_only);
+
int register_virtio_driver(struct virtio_driver *driver)
{
/* Catch this early. */
@@ -303,6 +352,7 @@ EXPORT_SYMBOL_GPL(virtio_device_freeze);
int virtio_device_restore(struct virtio_device *dev)
{
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+ int ret;
/* We always start by resetting the device, in case a previous
* driver messed it up. */
@@ -322,14 +372,14 @@ int virtio_device_restore(struct virtio_device *dev)
/* We have a driver! */
add_status(dev, VIRTIO_CONFIG_S_DRIVER);
- dev->config->finalize_features(dev);
+ ret = dev->config->finalize_features(dev);
+ if (ret)
+ goto err;
if (drv->restore) {
- int ret = drv->restore(dev);
- if (ret) {
- add_status(dev, VIRTIO_CONFIG_S_FAILED);
- return ret;
- }
+ ret = drv->restore(dev);
+ if (ret)
+ goto err;
}
/* Finally, tell the device we're all set */
@@ -338,6 +388,10 @@ int virtio_device_restore(struct virtio_device *dev)
virtio_config_enable(dev);
return 0;
+
+err:
+ add_status(dev, VIRTIO_CONFIG_S_FAILED);
+ return ret;
}
EXPORT_SYMBOL_GPL(virtio_device_restore);
#endif
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index ef9a1650bb8..5219210d31c 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -142,7 +142,7 @@ struct virtio_mmio_vq_info {
/* Configuration interface */
-static u32 vm_get_features(struct virtio_device *vdev)
+static u64 vm_get_features(struct virtio_device *vdev)
{
struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
@@ -152,19 +152,20 @@ static u32 vm_get_features(struct virtio_device *vdev)
return readl(vm_dev->base + VIRTIO_MMIO_HOST_FEATURES);
}
-static void vm_finalize_features(struct virtio_device *vdev)
+static int vm_finalize_features(struct virtio_device *vdev)
{
struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
- int i;
/* Give virtio_ring a chance to accept features. */
vring_transport_features(vdev);
- for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
- writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
- writel(vdev->features[i],
- vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
- }
+ /* Make sure we don't have any features > 32 bits! */
+ BUG_ON((u32)vdev->features != vdev->features);
+
+ writel(0, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
+ writel(vdev->features, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
+
+ return 0;
}
static void vm_get(struct virtio_device *vdev, unsigned offset,
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
deleted file mode 100644
index d34ebfa604f..00000000000
--- a/drivers/virtio/virtio_pci.c
+++ /dev/null
@@ -1,802 +0,0 @@
-/*
- * Virtio PCI driver
- *
- * This module allows virtio devices to be used over a virtual PCI device.
- * This can be used with QEMU based VMMs like KVM or Xen.
- *
- * Copyright IBM Corp. 2007
- *
- * Authors:
- * Anthony Liguori <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#include <linux/module.h>
-#include <linux/list.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_ring.h>
-#include <linux/virtio_pci.h>
-#include <linux/highmem.h>
-#include <linux/spinlock.h>
-
-MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
-MODULE_DESCRIPTION("virtio-pci");
-MODULE_LICENSE("GPL");
-MODULE_VERSION("1");
-
-/* Our device structure */
-struct virtio_pci_device
-{
- struct virtio_device vdev;
- struct pci_dev *pci_dev;
-
- /* the IO mapping for the PCI config space */
- void __iomem *ioaddr;
-
- /* a list of queues so we can dispatch IRQs */
- spinlock_t lock;
- struct list_head virtqueues;
-
- /* MSI-X support */
- int msix_enabled;
- int intx_enabled;
- struct msix_entry *msix_entries;
- cpumask_var_t *msix_affinity_masks;
- /* Name strings for interrupts. This size should be enough,
- * and I'm too lazy to allocate each name separately. */
- char (*msix_names)[256];
- /* Number of available vectors */
- unsigned msix_vectors;
- /* Vectors allocated, excluding per-vq vectors if any */
- unsigned msix_used_vectors;
-
- /* Whether we have vector per vq */
- bool per_vq_vectors;
-};
-
-/* Constants for MSI-X */
-/* Use first vector for configuration changes, second and the rest for
- * virtqueues Thus, we need at least 2 vectors for MSI. */
-enum {
- VP_MSIX_CONFIG_VECTOR = 0,
- VP_MSIX_VQ_VECTOR = 1,
-};
-
-struct virtio_pci_vq_info
-{
- /* the actual virtqueue */
- struct virtqueue *vq;
-
- /* the number of entries in the queue */
- int num;
-
- /* the virtual address of the ring queue */
- void *queue;
-
- /* the list node for the virtqueues list */
- struct list_head node;
-
- /* MSI-X vector (or none) */
- unsigned msix_vector;
-};
-
-/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
-static const struct pci_device_id virtio_pci_id_table[] = {
- { PCI_DEVICE(0x1af4, PCI_ANY_ID) },
- { 0 }
-};
-
-MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
-
-/* Convert a generic virtio device to our structure */
-static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
-{
- return container_of(vdev, struct virtio_pci_device, vdev);
-}
-
-/* virtio config->get_features() implementation */
-static u32 vp_get_features(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
- /* When someone needs more than 32 feature bits, we'll need to
- * steal a bit to indicate that the rest are somewhere else. */
- return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
-}
-
-/* virtio config->finalize_features() implementation */
-static void vp_finalize_features(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
- /* Give virtio_ring a chance to accept features. */
- vring_transport_features(vdev);
-
- /* We only support 32 feature bits. */
- BUILD_BUG_ON(ARRAY_SIZE(vdev->features) != 1);
- iowrite32(vdev->features[0], vp_dev->ioaddr+VIRTIO_PCI_GUEST_FEATURES);
-}
-
-/* virtio config->get() implementation */
-static void vp_get(struct virtio_device *vdev, unsigned offset,
- void *buf, unsigned len)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- void __iomem *ioaddr = vp_dev->ioaddr +
- VIRTIO_PCI_CONFIG(vp_dev) + offset;
- u8 *ptr = buf;
- int i;
-
- for (i = 0; i < len; i++)
- ptr[i] = ioread8(ioaddr + i);
-}
-
-/* the config->set() implementation. it's symmetric to the config->get()
- * implementation */
-static void vp_set(struct virtio_device *vdev, unsigned offset,
- const void *buf, unsigned len)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- void __iomem *ioaddr = vp_dev->ioaddr +
- VIRTIO_PCI_CONFIG(vp_dev) + offset;
- const u8 *ptr = buf;
- int i;
-
- for (i = 0; i < len; i++)
- iowrite8(ptr[i], ioaddr + i);
-}
-
-/* config->{get,set}_status() implementations */
-static u8 vp_get_status(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
-}
-
-static void vp_set_status(struct virtio_device *vdev, u8 status)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- /* We should never be setting status to 0. */
- BUG_ON(status == 0);
- iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
-}
-
-/* wait for pending irq handlers */
-static void vp_synchronize_vectors(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- int i;
-
- if (vp_dev->intx_enabled)
- synchronize_irq(vp_dev->pci_dev->irq);
-
- for (i = 0; i < vp_dev->msix_vectors; ++i)
- synchronize_irq(vp_dev->msix_entries[i].vector);
-}
-
-static void vp_reset(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- /* 0 status means a reset. */
- iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
- /* Flush out the status write, and flush in device writes,
- * including MSi-X interrupts, if any. */
- ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
- /* Flush pending VQ/configuration callbacks. */
- vp_synchronize_vectors(vdev);
-}
-
-/* the notify function used when creating a virt queue */
-static bool vp_notify(struct virtqueue *vq)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
-
- /* we write the queue's selector into the notification register to
- * signal the other end */
- iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
- return true;
-}
-
-/* Handle a configuration change: Tell driver if it wants to know. */
-static irqreturn_t vp_config_changed(int irq, void *opaque)
-{
- struct virtio_pci_device *vp_dev = opaque;
-
- virtio_config_changed(&vp_dev->vdev);
- return IRQ_HANDLED;
-}
-
-/* Notify all virtqueues on an interrupt. */
-static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
-{
- struct virtio_pci_device *vp_dev = opaque;
- struct virtio_pci_vq_info *info;
- irqreturn_t ret = IRQ_NONE;
- unsigned long flags;
-
- spin_lock_irqsave(&vp_dev->lock, flags);
- list_for_each_entry(info, &vp_dev->virtqueues, node) {
- if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
- ret = IRQ_HANDLED;
- }
- spin_unlock_irqrestore(&vp_dev->lock, flags);
-
- return ret;
-}
-
-/* A small wrapper to also acknowledge the interrupt when it's handled.
- * I really need an EIO hook for the vring so I can ack the interrupt once we
- * know that we'll be handling the IRQ but before we invoke the callback since
- * the callback may notify the host which results in the host attempting to
- * raise an interrupt that we would then mask once we acknowledged the
- * interrupt. */
-static irqreturn_t vp_interrupt(int irq, void *opaque)
-{
- struct virtio_pci_device *vp_dev = opaque;
- u8 isr;
-
- /* reading the ISR has the effect of also clearing it so it's very
- * important to save off the value. */
- isr = ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
-
- /* It's definitely not us if the ISR was not high */
- if (!isr)
- return IRQ_NONE;
-
- /* Configuration change? Tell driver if it wants to know. */
- if (isr & VIRTIO_PCI_ISR_CONFIG)
- vp_config_changed(irq, opaque);
-
- return vp_vring_interrupt(irq, opaque);
-}
-
-static void vp_free_vectors(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- int i;
-
- if (vp_dev->intx_enabled) {
- free_irq(vp_dev->pci_dev->irq, vp_dev);
- vp_dev->intx_enabled = 0;
- }
-
- for (i = 0; i < vp_dev->msix_used_vectors; ++i)
- free_irq(vp_dev->msix_entries[i].vector, vp_dev);
-
- for (i = 0; i < vp_dev->msix_vectors; i++)
- if (vp_dev->msix_affinity_masks[i])
- free_cpumask_var(vp_dev->msix_affinity_masks[i]);
-
- if (vp_dev->msix_enabled) {
- /* Disable the vector used for configuration */
- iowrite16(VIRTIO_MSI_NO_VECTOR,
- vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
- /* Flush the write out to device */
- ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
-
- pci_disable_msix(vp_dev->pci_dev);
- vp_dev->msix_enabled = 0;
- }
-
- vp_dev->msix_vectors = 0;
- vp_dev->msix_used_vectors = 0;
- kfree(vp_dev->msix_names);
- vp_dev->msix_names = NULL;
- kfree(vp_dev->msix_entries);
- vp_dev->msix_entries = NULL;
- kfree(vp_dev->msix_affinity_masks);
- vp_dev->msix_affinity_masks = NULL;
-}
-
-static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
- bool per_vq_vectors)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- const char *name = dev_name(&vp_dev->vdev.dev);
- unsigned i, v;
- int err = -ENOMEM;
-
- vp_dev->msix_vectors = nvectors;
-
- vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
- GFP_KERNEL);
- if (!vp_dev->msix_entries)
- goto error;
- vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
- GFP_KERNEL);
- if (!vp_dev->msix_names)
- goto error;
- vp_dev->msix_affinity_masks
- = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
- GFP_KERNEL);
- if (!vp_dev->msix_affinity_masks)
- goto error;
- for (i = 0; i < nvectors; ++i)
- if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
- GFP_KERNEL))
- goto error;
-
- for (i = 0; i < nvectors; ++i)
- vp_dev->msix_entries[i].entry = i;
-
- err = pci_enable_msix_exact(vp_dev->pci_dev,
- vp_dev->msix_entries, nvectors);
- if (err)
- goto error;
- vp_dev->msix_enabled = 1;
-
- /* Set the vector used for configuration */
- v = vp_dev->msix_used_vectors;
- snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
- "%s-config", name);
- err = request_irq(vp_dev->msix_entries[v].vector,
- vp_config_changed, 0, vp_dev->msix_names[v],
- vp_dev);
- if (err)
- goto error;
- ++vp_dev->msix_used_vectors;
-
- iowrite16(v, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
- /* Verify we had enough resources to assign the vector */
- v = ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
- if (v == VIRTIO_MSI_NO_VECTOR) {
- err = -EBUSY;
- goto error;
- }
-
- if (!per_vq_vectors) {
- /* Shared vector for all VQs */
- v = vp_dev->msix_used_vectors;
- snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
- "%s-virtqueues", name);
- err = request_irq(vp_dev->msix_entries[v].vector,
- vp_vring_interrupt, 0, vp_dev->msix_names[v],
- vp_dev);
- if (err)
- goto error;
- ++vp_dev->msix_used_vectors;
- }
- return 0;
-error:
- vp_free_vectors(vdev);
- return err;
-}
-
-static int vp_request_intx(struct virtio_device *vdev)
-{
- int err;
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
- err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
- IRQF_SHARED, dev_name(&vdev->dev), vp_dev);
- if (!err)
- vp_dev->intx_enabled = 1;
- return err;
-}
-
-static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
- void (*callback)(struct virtqueue *vq),
- const char *name,
- u16 msix_vec)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- struct virtio_pci_vq_info *info;
- struct virtqueue *vq;
- unsigned long flags, size;
- u16 num;
- int err;
-
- /* Select the queue we're interested in */
- iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
-
- /* Check if queue is either not available or already active. */
- num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
- if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
- return ERR_PTR(-ENOENT);
-
- /* allocate and fill out our structure the represents an active
- * queue */
- info = kmalloc(sizeof(struct virtio_pci_vq_info), GFP_KERNEL);
- if (!info)
- return ERR_PTR(-ENOMEM);
-
- info->num = num;
- info->msix_vector = msix_vec;
-
- size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
- info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
- if (info->queue == NULL) {
- err = -ENOMEM;
- goto out_info;
- }
-
- /* activate the queue */
- iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
- vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
-
- /* create the vring */
- vq = vring_new_virtqueue(index, info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
- true, info->queue, vp_notify, callback, name);
- if (!vq) {
- err = -ENOMEM;
- goto out_activate_queue;
- }
-
- vq->priv = info;
- info->vq = vq;
-
- if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
- iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
- msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
- if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
- err = -EBUSY;
- goto out_assign;
- }
- }
-
- if (callback) {
- spin_lock_irqsave(&vp_dev->lock, flags);
- list_add(&info->node, &vp_dev->virtqueues);
- spin_unlock_irqrestore(&vp_dev->lock, flags);
- } else {
- INIT_LIST_HEAD(&info->node);
- }
-
- return vq;
-
-out_assign:
- vring_del_virtqueue(vq);
-out_activate_queue:
- iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
- free_pages_exact(info->queue, size);
-out_info:
- kfree(info);
- return ERR_PTR(err);
-}
-
-static void vp_del_vq(struct virtqueue *vq)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
- struct virtio_pci_vq_info *info = vq->priv;
- unsigned long flags, size;
-
- spin_lock_irqsave(&vp_dev->lock, flags);
- list_del(&info->node);
- spin_unlock_irqrestore(&vp_dev->lock, flags);
-
- iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
-
- if (vp_dev->msix_enabled) {
- iowrite16(VIRTIO_MSI_NO_VECTOR,
- vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
- /* Flush the write out to device */
- ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
- }
-
- vring_del_virtqueue(vq);
-
- /* Select and deactivate the queue */
- iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
-
- size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
- free_pages_exact(info->queue, size);
- kfree(info);
-}
-
-/* the config->del_vqs() implementation */
-static void vp_del_vqs(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- struct virtqueue *vq, *n;
- struct virtio_pci_vq_info *info;
-
- list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
- info = vq->priv;
- if (vp_dev->per_vq_vectors &&
- info->msix_vector != VIRTIO_MSI_NO_VECTOR)
- free_irq(vp_dev->msix_entries[info->msix_vector].vector,
- vq);
- vp_del_vq(vq);
- }
- vp_dev->per_vq_vectors = false;
-
- vp_free_vectors(vdev);
-}
-
-static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
- struct virtqueue *vqs[],
- vq_callback_t *callbacks[],
- const char *names[],
- bool use_msix,
- bool per_vq_vectors)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- u16 msix_vec;
- int i, err, nvectors, allocated_vectors;
-
- if (!use_msix) {
- /* Old style: one normal interrupt for change and all vqs. */
- err = vp_request_intx(vdev);
- if (err)
- goto error_request;
- } else {
- if (per_vq_vectors) {
- /* Best option: one for change interrupt, one per vq. */
- nvectors = 1;
- for (i = 0; i < nvqs; ++i)
- if (callbacks[i])
- ++nvectors;
- } else {
- /* Second best: one for change, shared for all vqs. */
- nvectors = 2;
- }
-
- err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
- if (err)
- goto error_request;
- }
-
- vp_dev->per_vq_vectors = per_vq_vectors;
- allocated_vectors = vp_dev->msix_used_vectors;
- for (i = 0; i < nvqs; ++i) {
- if (!names[i]) {
- vqs[i] = NULL;
- continue;
- } else if (!callbacks[i] || !vp_dev->msix_enabled)
- msix_vec = VIRTIO_MSI_NO_VECTOR;
- else if (vp_dev->per_vq_vectors)
- msix_vec = allocated_vectors++;
- else
- msix_vec = VP_MSIX_VQ_VECTOR;
- vqs[i] = setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
- if (IS_ERR(vqs[i])) {
- err = PTR_ERR(vqs[i]);
- goto error_find;
- }
-
- if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
- continue;
-
- /* allocate per-vq irq if available and necessary */
- snprintf(vp_dev->msix_names[msix_vec],
- sizeof *vp_dev->msix_names,
- "%s-%s",
- dev_name(&vp_dev->vdev.dev), names[i]);
- err = request_irq(vp_dev->msix_entries[msix_vec].vector,
- vring_interrupt, 0,
- vp_dev->msix_names[msix_vec],
- vqs[i]);
- if (err) {
- vp_del_vq(vqs[i]);
- goto error_find;
- }
- }
- return 0;
-
-error_find:
- vp_del_vqs(vdev);
-
-error_request:
- return err;
-}
-
-/* the config->find_vqs() implementation */
-static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
- struct virtqueue *vqs[],
- vq_callback_t *callbacks[],
- const char *names[])
-{
- int err;
-
- /* Try MSI-X with one vector per queue. */
- err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true);
- if (!err)
- return 0;
- /* Fallback: MSI-X with one vector for config, one shared for queues. */
- err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
- true, false);
- if (!err)
- return 0;
- /* Finally fall back to regular interrupts. */
- return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
- false, false);
-}
-
-static const char *vp_bus_name(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
- return pci_name(vp_dev->pci_dev);
-}
-
-/* Setup the affinity for a virtqueue:
- * - force the affinity for per vq vector
- * - OR over all affinities for shared MSI
- * - ignore the affinity request if we're using INTX
- */
-static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
-{
- struct virtio_device *vdev = vq->vdev;
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- struct virtio_pci_vq_info *info = vq->priv;
- struct cpumask *mask;
- unsigned int irq;
-
- if (!vq->callback)
- return -EINVAL;
-
- if (vp_dev->msix_enabled) {
- mask = vp_dev->msix_affinity_masks[info->msix_vector];
- irq = vp_dev->msix_entries[info->msix_vector].vector;
- if (cpu == -1)
- irq_set_affinity_hint(irq, NULL);
- else {
- cpumask_set_cpu(cpu, mask);
- irq_set_affinity_hint(irq, mask);
- }
- }
- return 0;
-}
-
-static const struct virtio_config_ops virtio_pci_config_ops = {
- .get = vp_get,
- .set = vp_set,
- .get_status = vp_get_status,
- .set_status = vp_set_status,
- .reset = vp_reset,
- .find_vqs = vp_find_vqs,
- .del_vqs = vp_del_vqs,
- .get_features = vp_get_features,
- .finalize_features = vp_finalize_features,
- .bus_name = vp_bus_name,
- .set_vq_affinity = vp_set_vq_affinity,
-};
-
-static void virtio_pci_release_dev(struct device *_d)
-{
- /*
- * No need for a release method as we allocate/free
- * all devices together with the pci devices.
- * Provide an empty one to avoid getting a warning from core.
- */
-}
-
-/* the PCI probing function */
-static int virtio_pci_probe(struct pci_dev *pci_dev,
- const struct pci_device_id *id)
-{
- struct virtio_pci_device *vp_dev;
- int err;
-
- /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
- if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
- return -ENODEV;
-
- if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
- printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
- VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
- return -ENODEV;
- }
-
- /* allocate our structure and fill it out */
- vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
- if (vp_dev == NULL)
- return -ENOMEM;
-
- vp_dev->vdev.dev.parent = &pci_dev->dev;
- vp_dev->vdev.dev.release = virtio_pci_release_dev;
- vp_dev->vdev.config = &virtio_pci_config_ops;
- vp_dev->pci_dev = pci_dev;
- INIT_LIST_HEAD(&vp_dev->virtqueues);
- spin_lock_init(&vp_dev->lock);
-
- /* Disable MSI/MSIX to bring device to a known good state. */
- pci_msi_off(pci_dev);
-
- /* enable the device */
- err = pci_enable_device(pci_dev);
- if (err)
- goto out;
-
- err = pci_request_regions(pci_dev, "virtio-pci");
- if (err)
- goto out_enable_device;
-
- vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
- if (vp_dev->ioaddr == NULL) {
- err = -ENOMEM;
- goto out_req_regions;
- }
-
- pci_set_drvdata(pci_dev, vp_dev);
- pci_set_master(pci_dev);
-
- /* we use the subsystem vendor/device id as the virtio vendor/device
- * id. this allows us to use the same PCI vendor/device id for all
- * virtio devices and to identify the particular virtio driver by
- * the subsystem ids */
- vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
- vp_dev->vdev.id.device = pci_dev->subsystem_device;
-
- /* finally register the virtio device */
- err = register_virtio_device(&vp_dev->vdev);
- if (err)
- goto out_set_drvdata;
-
- return 0;
-
-out_set_drvdata:
- pci_iounmap(pci_dev, vp_dev->ioaddr);
-out_req_regions:
- pci_release_regions(pci_dev);
-out_enable_device:
- pci_disable_device(pci_dev);
-out:
- kfree(vp_dev);
- return err;
-}
-
-static void virtio_pci_remove(struct pci_dev *pci_dev)
-{
- struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-
- unregister_virtio_device(&vp_dev->vdev);
-
- vp_del_vqs(&vp_dev->vdev);
- pci_iounmap(pci_dev, vp_dev->ioaddr);
- pci_release_regions(pci_dev);
- pci_disable_device(pci_dev);
- kfree(vp_dev);
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int virtio_pci_freeze(struct device *dev)
-{
- struct pci_dev *pci_dev = to_pci_dev(dev);
- struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
- int ret;
-
- ret = virtio_device_freeze(&vp_dev->vdev);
-
- if (!ret)
- pci_disable_device(pci_dev);
- return ret;
-}
-
-static int virtio_pci_restore(struct device *dev)
-{
- struct pci_dev *pci_dev = to_pci_dev(dev);
- struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
- int ret;
-
- ret = pci_enable_device(pci_dev);
- if (ret)
- return ret;
-
- pci_set_master(pci_dev);
- return virtio_device_restore(&vp_dev->vdev);
-}
-
-static const struct dev_pm_ops virtio_pci_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
-};
-#endif
-
-static struct pci_driver virtio_pci_driver = {
- .name = "virtio-pci",
- .id_table = virtio_pci_id_table,
- .probe = virtio_pci_probe,
- .remove = virtio_pci_remove,
-#ifdef CONFIG_PM_SLEEP
- .driver.pm = &virtio_pci_pm_ops,
-#endif
-};
-
-module_pci_driver(virtio_pci_driver);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
new file mode 100644
index 00000000000..953057d8418
--- /dev/null
+++ b/drivers/virtio/virtio_pci_common.c
@@ -0,0 +1,464 @@
+/*
+ * Virtio PCI driver - common functionality for all device versions
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ * Rusty Russell <rusty@rustcorp.com.au>
+ * Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "virtio_pci_common.h"
+
+/* wait for pending irq handlers */
+void vp_synchronize_vectors(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ int i;
+
+ if (vp_dev->intx_enabled)
+ synchronize_irq(vp_dev->pci_dev->irq);
+
+ for (i = 0; i < vp_dev->msix_vectors; ++i)
+ synchronize_irq(vp_dev->msix_entries[i].vector);
+}
+
+/* the notify function used when creating a virt queue */
+bool vp_notify(struct virtqueue *vq)
+{
+ /* we write the queue's selector into the notification register to
+ * signal the other end */
+ iowrite16(vq->index, (void __iomem *)vq->priv);
+ return true;
+}
+
+/* Handle a configuration change: Tell driver if it wants to know. */
+static irqreturn_t vp_config_changed(int irq, void *opaque)
+{
+ struct virtio_pci_device *vp_dev = opaque;
+
+ virtio_config_changed(&vp_dev->vdev);
+ return IRQ_HANDLED;
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
+{
+ struct virtio_pci_device *vp_dev = opaque;
+ struct virtio_pci_vq_info *info;
+ irqreturn_t ret = IRQ_NONE;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_for_each_entry(info, &vp_dev->virtqueues, node) {
+ if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+ ret = IRQ_HANDLED;
+ }
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+ return ret;
+}
+
+/* A small wrapper to also acknowledge the interrupt when it's handled.
+ * I really need an EIO hook for the vring so I can ack the interrupt once we
+ * know that we'll be handling the IRQ but before we invoke the callback since
+ * the callback may notify the host which results in the host attempting to
+ * raise an interrupt that we would then mask once we acknowledged the
+ * interrupt. */
+static irqreturn_t vp_interrupt(int irq, void *opaque)
+{
+ struct virtio_pci_device *vp_dev = opaque;
+ u8 isr;
+
+ /* reading the ISR has the effect of also clearing it so it's very
+ * important to save off the value. */
+ isr = ioread8(vp_dev->isr);
+
+ /* It's definitely not us if the ISR was not high */
+ if (!isr)
+ return IRQ_NONE;
+
+ /* Configuration change? Tell driver if it wants to know. */
+ if (isr & VIRTIO_PCI_ISR_CONFIG)
+ vp_config_changed(irq, opaque);
+
+ return vp_vring_interrupt(irq, opaque);
+}
+
+static void vp_free_vectors(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ int i;
+
+ if (vp_dev->intx_enabled) {
+ free_irq(vp_dev->pci_dev->irq, vp_dev);
+ vp_dev->intx_enabled = 0;
+ }
+
+ for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+ free_irq(vp_dev->msix_entries[i].vector, vp_dev);
+
+ for (i = 0; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->msix_affinity_masks[i])
+ free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+
+ if (vp_dev->msix_enabled) {
+ /* Disable the vector used for configuration */
+ vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
+
+ pci_disable_msix(vp_dev->pci_dev);
+ vp_dev->msix_enabled = 0;
+ }
+
+ vp_dev->msix_vectors = 0;
+ vp_dev->msix_used_vectors = 0;
+ kfree(vp_dev->msix_names);
+ vp_dev->msix_names = NULL;
+ kfree(vp_dev->msix_entries);
+ vp_dev->msix_entries = NULL;
+ kfree(vp_dev->msix_affinity_masks);
+ vp_dev->msix_affinity_masks = NULL;
+}
+
+static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
+ bool per_vq_vectors)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ const char *name = dev_name(&vp_dev->vdev.dev);
+ unsigned i, v;
+ int err = -ENOMEM;
+
+ vp_dev->msix_vectors = nvectors;
+
+ vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
+ GFP_KERNEL);
+ if (!vp_dev->msix_entries)
+ goto error;
+ vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
+ GFP_KERNEL);
+ if (!vp_dev->msix_names)
+ goto error;
+ vp_dev->msix_affinity_masks
+ = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+ GFP_KERNEL);
+ if (!vp_dev->msix_affinity_masks)
+ goto error;
+ for (i = 0; i < nvectors; ++i)
+ if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+ GFP_KERNEL))
+ goto error;
+
+ for (i = 0; i < nvectors; ++i)
+ vp_dev->msix_entries[i].entry = i;
+
+ err = pci_enable_msix_exact(vp_dev->pci_dev,
+ vp_dev->msix_entries, nvectors);
+ if (err)
+ goto error;
+ vp_dev->msix_enabled = 1;
+
+ /* Set the vector used for configuration */
+ v = vp_dev->msix_used_vectors;
+ snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+ "%s-config", name);
+ err = request_irq(vp_dev->msix_entries[v].vector,
+ vp_config_changed, 0, vp_dev->msix_names[v],
+ vp_dev);
+ if (err)
+ goto error;
+ ++vp_dev->msix_used_vectors;
+
+ v = vp_dev->config_vector(vp_dev, v);
+ /* Verify we had enough resources to assign the vector */
+ if (v == VIRTIO_MSI_NO_VECTOR) {
+ err = -EBUSY;
+ goto error;
+ }
+
+ if (!per_vq_vectors) {
+ /* Shared vector for all VQs */
+ v = vp_dev->msix_used_vectors;
+ snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+ "%s-virtqueues", name);
+ err = request_irq(vp_dev->msix_entries[v].vector,
+ vp_vring_interrupt, 0, vp_dev->msix_names[v],
+ vp_dev);
+ if (err)
+ goto error;
+ ++vp_dev->msix_used_vectors;
+ }
+ return 0;
+error:
+ vp_free_vectors(vdev);
+ return err;
+}
+
+static int vp_request_intx(struct virtio_device *vdev)
+{
+ int err;
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
+ IRQF_SHARED, dev_name(&vdev->dev), vp_dev);
+ if (!err)
+ vp_dev->intx_enabled = 1;
+ return err;
+}
+
+static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name,
+ u16 msix_vec)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
+ struct virtqueue *vq;
+ unsigned long flags;
+
+ /* fill out our structure that represents an active queue */
+ if (!info)
+ return ERR_PTR(-ENOMEM);
+
+ vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, msix_vec);
+ if (IS_ERR(vq))
+ goto out_info;
+
+ info->vq = vq;
+ if (callback) {
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_add(&info->node, &vp_dev->virtqueues);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+ } else {
+ INIT_LIST_HEAD(&info->node);
+ }
+
+ vp_dev->vqs[index] = info;
+ return vq;
+
+out_info:
+ kfree(info);
+ return vq;
+}
+
+static void vp_del_vq(struct virtqueue *vq)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+ struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+ unsigned long flags;
+
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+ vp_dev->del_vq(info);
+ kfree(info);
+}
+
+/* the config->del_vqs() implementation */
+void vp_del_vqs(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtqueue *vq, *n;
+ struct virtio_pci_vq_info *info;
+
+ list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+ info = vp_dev->vqs[vq->index];
+ if (vp_dev->per_vq_vectors &&
+ info->msix_vector != VIRTIO_MSI_NO_VECTOR)
+ free_irq(vp_dev->msix_entries[info->msix_vector].vector,
+ vq);
+ vp_del_vq(vq);
+ }
+ vp_dev->per_vq_vectors = false;
+
+ vp_free_vectors(vdev);
+ kfree(vp_dev->vqs);
+}
+
+static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char *names[],
+ bool use_msix,
+ bool per_vq_vectors)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ u16 msix_vec;
+ int i, err, nvectors, allocated_vectors;
+
+ vp_dev->vqs = kmalloc(nvqs * sizeof *vp_dev->vqs, GFP_KERNEL);
+ if (!vp_dev->vqs)
+ return -ENOMEM;
+
+ if (!use_msix) {
+ /* Old style: one normal interrupt for change and all vqs. */
+ err = vp_request_intx(vdev);
+ if (err)
+ goto error_find;
+ } else {
+ if (per_vq_vectors) {
+ /* Best option: one for change interrupt, one per vq. */
+ nvectors = 1;
+ for (i = 0; i < nvqs; ++i)
+ if (callbacks[i])
+ ++nvectors;
+ } else {
+ /* Second best: one for change, shared for all vqs. */
+ nvectors = 2;
+ }
+
+ err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
+ if (err)
+ goto error_find;
+ }
+
+ vp_dev->per_vq_vectors = per_vq_vectors;
+ allocated_vectors = vp_dev->msix_used_vectors;
+ for (i = 0; i < nvqs; ++i) {
+ if (!names[i]) {
+ vqs[i] = NULL;
+ continue;
+ } else if (!callbacks[i] || !vp_dev->msix_enabled)
+ msix_vec = VIRTIO_MSI_NO_VECTOR;
+ else if (vp_dev->per_vq_vectors)
+ msix_vec = allocated_vectors++;
+ else
+ msix_vec = VP_MSIX_VQ_VECTOR;
+ vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
+ if (IS_ERR(vqs[i])) {
+ err = PTR_ERR(vqs[i]);
+ goto error_find;
+ }
+
+ if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
+ continue;
+
+ /* allocate per-vq irq if available and necessary */
+ snprintf(vp_dev->msix_names[msix_vec],
+ sizeof *vp_dev->msix_names,
+ "%s-%s",
+ dev_name(&vp_dev->vdev.dev), names[i]);
+ err = request_irq(vp_dev->msix_entries[msix_vec].vector,
+ vring_interrupt, 0,
+ vp_dev->msix_names[msix_vec],
+ vqs[i]);
+ if (err) {
+ vp_del_vq(vqs[i]);
+ goto error_find;
+ }
+ }
+ return 0;
+
+error_find:
+ vp_del_vqs(vdev);
+ return err;
+}
+
+/* the config->find_vqs() implementation */
+int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char *names[])
+{
+ int err;
+
+ /* Try MSI-X with one vector per queue. */
+ err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true);
+ if (!err)
+ return 0;
+ /* Fallback: MSI-X with one vector for config, one shared for queues. */
+ err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
+ true, false);
+ if (!err)
+ return 0;
+ /* Finally fall back to regular interrupts. */
+ return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
+ false, false);
+}
+
+const char *vp_bus_name(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ return pci_name(vp_dev->pci_dev);
+}
+
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+{
+ struct virtio_device *vdev = vq->vdev;
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+ struct cpumask *mask;
+ unsigned int irq;
+
+ if (!vq->callback)
+ return -EINVAL;
+
+ if (vp_dev->msix_enabled) {
+ mask = vp_dev->msix_affinity_masks[info->msix_vector];
+ irq = vp_dev->msix_entries[info->msix_vector].vector;
+ if (cpu == -1)
+ irq_set_affinity_hint(irq, NULL);
+ else {
+ cpumask_set_cpu(cpu, mask);
+ irq_set_affinity_hint(irq, mask);
+ }
+ }
+ return 0;
+}
+
+void virtio_pci_release_dev(struct device *_d)
+{
+ /*
+ * No need for a release method as we allocate/free
+ * all devices together with the pci devices.
+ * Provide an empty one to avoid getting a warning from core.
+ */
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int virtio_pci_freeze(struct device *dev)
+{
+ struct pci_dev *pci_dev = to_pci_dev(dev);
+ struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+ int ret;
+
+ ret = virtio_device_freeze(&vp_dev->vdev);
+
+ if (!ret)
+ pci_disable_device(pci_dev);
+ return ret;
+}
+
+static int virtio_pci_restore(struct device *dev)
+{
+ struct pci_dev *pci_dev = to_pci_dev(dev);
+ struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+ int ret;
+
+ ret = pci_enable_device(pci_dev);
+ if (ret)
+ return ret;
+
+ pci_set_master(pci_dev);
+ return virtio_device_restore(&vp_dev->vdev);
+}
+
+const struct dev_pm_ops virtio_pci_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
+};
+#endif
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
new file mode 100644
index 00000000000..d840dad4149
--- /dev/null
+++ b/drivers/virtio/virtio_pci_common.h
@@ -0,0 +1,136 @@
+#ifndef _DRIVERS_VIRTIO_VIRTIO_PCI_COMMON_H
+#define _DRIVERS_VIRTIO_VIRTIO_PCI_COMMON_H
+/*
+ * Virtio PCI driver - APIs for common functionality for all device versions
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ * Rusty Russell <rusty@rustcorp.com.au>
+ * Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#define VIRTIO_PCI_NO_LEGACY
+#include <linux/virtio_pci.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+
+struct virtio_pci_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the number of entries in the queue */
+ int num;
+
+ /* the virtual address of the ring queue */
+ void *queue;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+
+ /* MSI-X vector (or none) */
+ unsigned msix_vector;
+};
+
+/* Our device structure */
+struct virtio_pci_device {
+ struct virtio_device vdev;
+ struct pci_dev *pci_dev;
+
+ /* the IO mapping for the PCI config space */
+ void __iomem *ioaddr;
+
+ /* the IO mapping for ISR operation */
+ void __iomem *isr;
+
+ /* a list of queues so we can dispatch IRQs */
+ spinlock_t lock;
+ struct list_head virtqueues;
+
+ /* array of all queues for house-keeping */
+ struct virtio_pci_vq_info **vqs;
+
+ /* MSI-X support */
+ int msix_enabled;
+ int intx_enabled;
+ struct msix_entry *msix_entries;
+ cpumask_var_t *msix_affinity_masks;
+ /* Name strings for interrupts. This size should be enough,
+ * and I'm too lazy to allocate each name separately. */
+ char (*msix_names)[256];
+ /* Number of available vectors */
+ unsigned msix_vectors;
+ /* Vectors allocated, excluding per-vq vectors if any */
+ unsigned msix_used_vectors;
+
+ /* Whether we have vector per vq */
+ bool per_vq_vectors;
+
+ struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
+ unsigned idx,
+ void (*callback)(struct virtqueue *vq),
+ const char *name,
+ u16 msix_vec);
+ void (*del_vq)(struct virtio_pci_vq_info *info);
+
+ u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
+};
+
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+ VP_MSIX_CONFIG_VECTOR = 0,
+ VP_MSIX_VQ_VECTOR = 1,
+};
+
+/* Convert a generic virtio device to our structure */
+static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
+{
+ return container_of(vdev, struct virtio_pci_device, vdev);
+}
+
+/* wait for pending irq handlers */
+void vp_synchronize_vectors(struct virtio_device *vdev);
+/* the notify function used when creating a virt queue */
+bool vp_notify(struct virtqueue *vq);
+/* the config->del_vqs() implementation */
+void vp_del_vqs(struct virtio_device *vdev);
+/* the config->find_vqs() implementation */
+int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char *names[]);
+const char *vp_bus_name(struct virtio_device *vdev);
+
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
+void virtio_pci_release_dev(struct device *);
+
+#ifdef CONFIG_PM_SLEEP
+extern const struct dev_pm_ops virtio_pci_pm_ops;
+#endif
+
+#endif
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
new file mode 100644
index 00000000000..2588252e5c1
--- /dev/null
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -0,0 +1,326 @@
+/*
+ * Virtio PCI driver - legacy device support
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ * Rusty Russell <rusty@rustcorp.com.au>
+ * Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "virtio_pci_common.h"
+
+/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
+static const struct pci_device_id virtio_pci_id_table[] = {
+ { PCI_DEVICE(0x1af4, PCI_ANY_ID) },
+ { 0 }
+};
+
+MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
+
+/* virtio config->get_features() implementation */
+static u64 vp_get_features(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ /* When someone needs more than 32 feature bits, we'll need to
+ * steal a bit to indicate that the rest are somewhere else. */
+ return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+}
+
+/* virtio config->finalize_features() implementation */
+static int vp_finalize_features(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ /* Give virtio_ring a chance to accept features. */
+ vring_transport_features(vdev);
+
+ /* Make sure we don't have any features > 32 bits! */
+ BUG_ON((u32)vdev->features != vdev->features);
+
+ /* We only support 32 feature bits. */
+ iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+
+ return 0;
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ void __iomem *ioaddr = vp_dev->ioaddr +
+ VIRTIO_PCI_CONFIG(vp_dev) + offset;
+ u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ ptr[i] = ioread8(ioaddr + i);
+}
+
+/* the config->set() implementation. it's symmetric to the config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ void __iomem *ioaddr = vp_dev->ioaddr +
+ VIRTIO_PCI_CONFIG(vp_dev) + offset;
+ const u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ iowrite8(ptr[i], ioaddr + i);
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ /* We should never be setting status to 0. */
+ BUG_ON(status == 0);
+ iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ /* 0 status means a reset. */
+ iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+ /* Flush out the status write, and flush in device writes,
+ * including MSi-X interrupts, if any. */
+ ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+ /* Flush pending VQ/configuration callbacks. */
+ vp_synchronize_vectors(vdev);
+}
+
+static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+{
+ /* Setup the vector used for configuration events */
+ iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+ /* Verify we had enough resources to assign the vector */
+ /* Will also flush the write out to device */
+ return ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+}
+
+static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
+ unsigned index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name,
+ u16 msix_vec)
+{
+ struct virtqueue *vq;
+ unsigned long size;
+ u16 num;
+ int err;
+
+ /* Select the queue we're interested in */
+ iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+ /* Check if queue is either not available or already active. */
+ num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
+ if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
+ return ERR_PTR(-ENOENT);
+
+ info->num = num;
+ info->msix_vector = msix_vec;
+
+ size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
+ info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
+ if (info->queue == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ /* activate the queue */
+ iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
+ vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+ /* create the vring */
+ vq = vring_new_virtqueue(index, info->num,
+ VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
+ true, info->queue, vp_notify, callback, name);
+ if (!vq) {
+ err = -ENOMEM;
+ goto out_activate_queue;
+ }
+
+ vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
+
+ if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+ iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+ msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+ if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+ err = -EBUSY;
+ goto out_assign;
+ }
+ }
+
+ return vq;
+
+out_assign:
+ vring_del_virtqueue(vq);
+out_activate_queue:
+ iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+ free_pages_exact(info->queue, size);
+ return ERR_PTR(err);
+}
+
+static void del_vq(struct virtio_pci_vq_info *info)
+{
+ struct virtqueue *vq = info->vq;
+ struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+ unsigned long size;
+
+ iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+ if (vp_dev->msix_enabled) {
+ iowrite16(VIRTIO_MSI_NO_VECTOR,
+ vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+ /* Flush the write out to device */
+ ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+ }
+
+ vring_del_virtqueue(vq);
+
+ /* Select and deactivate the queue */
+ iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+ size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
+ free_pages_exact(info->queue, size);
+}
+
+static const struct virtio_config_ops virtio_pci_config_ops = {
+ .get = vp_get,
+ .set = vp_set,
+ .get_status = vp_get_status,
+ .set_status = vp_set_status,
+ .reset = vp_reset,
+ .find_vqs = vp_find_vqs,
+ .del_vqs = vp_del_vqs,
+ .get_features = vp_get_features,
+ .finalize_features = vp_finalize_features,
+ .bus_name = vp_bus_name,
+ .set_vq_affinity = vp_set_vq_affinity,
+};
+
+/* the PCI probing function */
+static int virtio_pci_probe(struct pci_dev *pci_dev,
+ const struct pci_device_id *id)
+{
+ struct virtio_pci_device *vp_dev;
+ int err;
+
+ /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
+ if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
+ return -ENODEV;
+
+ if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
+ printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
+ VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
+ return -ENODEV;
+ }
+
+ /* allocate our structure and fill it out */
+ vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+ if (vp_dev == NULL)
+ return -ENOMEM;
+
+ vp_dev->vdev.dev.parent = &pci_dev->dev;
+ vp_dev->vdev.dev.release = virtio_pci_release_dev;
+ vp_dev->vdev.config = &virtio_pci_config_ops;
+ vp_dev->pci_dev = pci_dev;
+ INIT_LIST_HEAD(&vp_dev->virtqueues);
+ spin_lock_init(&vp_dev->lock);
+
+ /* Disable MSI/MSIX to bring device to a known good state. */
+ pci_msi_off(pci_dev);
+
+ /* enable the device */
+ err = pci_enable_device(pci_dev);
+ if (err)
+ goto out;
+
+ err = pci_request_regions(pci_dev, "virtio-pci");
+ if (err)
+ goto out_enable_device;
+
+ vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
+ if (vp_dev->ioaddr == NULL) {
+ err = -ENOMEM;
+ goto out_req_regions;
+ }
+
+ vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
+
+ pci_set_drvdata(pci_dev, vp_dev);
+ pci_set_master(pci_dev);
+
+ /* we use the subsystem vendor/device id as the virtio vendor/device
+ * id. this allows us to use the same PCI vendor/device id for all
+ * virtio devices and to identify the particular virtio driver by
+ * the subsystem ids */
+ vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+ vp_dev->vdev.id.device = pci_dev->subsystem_device;
+
+ vp_dev->config_vector = vp_config_vector;
+ vp_dev->setup_vq = setup_vq;
+ vp_dev->del_vq = del_vq;
+
+ /* finally register the virtio device */
+ err = register_virtio_device(&vp_dev->vdev);
+ if (err)
+ goto out_set_drvdata;
+
+ return 0;
+
+out_set_drvdata:
+ pci_iounmap(pci_dev, vp_dev->ioaddr);
+out_req_regions:
+ pci_release_regions(pci_dev);
+out_enable_device:
+ pci_disable_device(pci_dev);
+out:
+ kfree(vp_dev);
+ return err;
+}
+
+static void virtio_pci_remove(struct pci_dev *pci_dev)
+{
+ struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+ unregister_virtio_device(&vp_dev->vdev);
+
+ vp_del_vqs(&vp_dev->vdev);
+ pci_iounmap(pci_dev, vp_dev->ioaddr);
+ pci_release_regions(pci_dev);
+ pci_disable_device(pci_dev);
+ kfree(vp_dev);
+}
+
+static struct pci_driver virtio_pci_driver = {
+ .name = "virtio-pci",
+ .id_table = virtio_pci_id_table,
+ .probe = virtio_pci_probe,
+ .remove = virtio_pci_remove,
+#ifdef CONFIG_PM_SLEEP
+ .driver.pm = &virtio_pci_pm_ops,
+#endif
+};
+
+module_pci_driver(virtio_pci_driver);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 3b1f89b6e74..00ec6b3f96b 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -99,7 +99,8 @@ struct vring_virtqueue
#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
-static struct vring_desc *alloc_indirect(unsigned int total_sg, gfp_t gfp)
+static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
+ unsigned int total_sg, gfp_t gfp)
{
struct vring_desc *desc;
unsigned int i;
@@ -116,7 +117,7 @@ static struct vring_desc *alloc_indirect(unsigned int total_sg, gfp_t gfp)
return NULL;
for (i = 0; i < total_sg; i++)
- desc[i].next = i+1;
+ desc[i].next = cpu_to_virtio16(_vq->vdev, i + 1);
return desc;
}
@@ -165,17 +166,17 @@ static inline int virtqueue_add(struct virtqueue *_vq,
/* If the host supports indirect descriptor tables, and we have multiple
* buffers, then go indirect. FIXME: tune this threshold */
if (vq->indirect && total_sg > 1 && vq->vq.num_free)
- desc = alloc_indirect(total_sg, gfp);
+ desc = alloc_indirect(_vq, total_sg, gfp);
else
desc = NULL;
if (desc) {
/* Use a single buffer which doesn't continue */
- vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
- vq->vring.desc[head].addr = virt_to_phys(desc);
+ vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT);
+ vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, virt_to_phys(desc));
/* avoid kmemleak false positive (hidden by virt_to_phys) */
kmemleak_ignore(desc);
- vq->vring.desc[head].len = total_sg * sizeof(struct vring_desc);
+ vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc));
/* Set up rest to use this indirect table. */
i = 0;
@@ -205,28 +206,28 @@ static inline int virtqueue_add(struct virtqueue *_vq,
for (n = 0; n < out_sgs; n++) {
for (sg = sgs[n]; sg; sg = sg_next(sg)) {
- desc[i].flags = VRING_DESC_F_NEXT;
- desc[i].addr = sg_phys(sg);
- desc[i].len = sg->length;
+ desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT);
+ desc[i].addr = cpu_to_virtio64(_vq->vdev, sg_phys(sg));
+ desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
prev = i;
- i = desc[i].next;
+ i = virtio16_to_cpu(_vq->vdev, desc[i].next);
}
}
for (; n < (out_sgs + in_sgs); n++) {
for (sg = sgs[n]; sg; sg = sg_next(sg)) {
- desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
- desc[i].addr = sg_phys(sg);
- desc[i].len = sg->length;
+ desc[i].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE);
+ desc[i].addr = cpu_to_virtio64(_vq->vdev, sg_phys(sg));
+ desc[i].len = cpu_to_virtio32(_vq->vdev, sg->length);
prev = i;
- i = desc[i].next;
+ i = virtio16_to_cpu(_vq->vdev, desc[i].next);
}
}
/* Last one doesn't continue. */
- desc[prev].flags &= ~VRING_DESC_F_NEXT;
+ desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
/* Update free pointer */
if (indirect)
- vq->free_head = vq->vring.desc[head].next;
+ vq->free_head = virtio16_to_cpu(_vq->vdev, vq->vring.desc[head].next);
else
vq->free_head = i;
@@ -235,13 +236,13 @@ static inline int virtqueue_add(struct virtqueue *_vq,
/* Put entry in available array (but don't update avail->idx until they
* do sync). */
- avail = (vq->vring.avail->idx & (vq->vring.num-1));
- vq->vring.avail->ring[avail] = head;
+ avail = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) & (vq->vring.num - 1);
+ vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
/* Descriptors and available array need to be set before we expose the
* new available array entries. */
virtio_wmb(vq->weak_barriers);
- vq->vring.avail->idx++;
+ vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) + 1);
vq->num_added++;
/* This is very unlikely, but theoretically possible. Kick
@@ -354,8 +355,8 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq)
* event. */
virtio_mb(vq->weak_barriers);
- old = vq->vring.avail->idx - vq->num_added;
- new = vq->vring.avail->idx;
+ old = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->num_added;
+ new = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx);
vq->num_added = 0;
#ifdef DEBUG
@@ -367,10 +368,10 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq)
#endif
if (vq->event) {
- needs_kick = vring_need_event(vring_avail_event(&vq->vring),
+ needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
new, old);
} else {
- needs_kick = !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY);
+ needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
}
END_USE(vq);
return needs_kick;
@@ -432,15 +433,15 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
i = head;
/* Free the indirect table */
- if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT)
- kfree(phys_to_virt(vq->vring.desc[i].addr));
+ if (vq->vring.desc[i].flags & cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT))
+ kfree(phys_to_virt(virtio64_to_cpu(vq->vq.vdev, vq->vring.desc[i].addr)));
- while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
- i = vq->vring.desc[i].next;
+ while (vq->vring.desc[i].flags & cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT)) {
+ i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
vq->vq.num_free++;
}
- vq->vring.desc[i].next = vq->free_head;
+ vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
vq->free_head = head;
/* Plus final descriptor */
vq->vq.num_free++;
@@ -448,7 +449,7 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
static inline bool more_used(const struct vring_virtqueue *vq)
{
- return vq->last_used_idx != vq->vring.used->idx;
+ return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
}
/**
@@ -491,8 +492,8 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
virtio_rmb(vq->weak_barriers);
last_used = (vq->last_used_idx & (vq->vring.num - 1));
- i = vq->vring.used->ring[last_used].id;
- *len = vq->vring.used->ring[last_used].len;
+ i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
+ *len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
if (unlikely(i >= vq->vring.num)) {
BAD_RING(vq, "id %u out of range\n", i);
@@ -510,8 +511,8 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
/* If we expect an interrupt for the next entry, tell host
* by writing event index and flush out the write before
* the read in the next get_buf call. */
- if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
- vring_used_event(&vq->vring) = vq->last_used_idx;
+ if (!(vq->vring.avail->flags & cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT))) {
+ vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx);
virtio_mb(vq->weak_barriers);
}
@@ -537,7 +538,7 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+ vq->vring.avail->flags |= cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT);
}
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
@@ -565,8 +566,8 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
* either clear the flags bit or point the event index at the next
* entry. Always do both to keep code simple. */
- vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vring_used_event(&vq->vring) = last_used_idx = vq->last_used_idx;
+ vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
+ vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
END_USE(vq);
return last_used_idx;
}
@@ -586,7 +587,7 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
struct vring_virtqueue *vq = to_vvq(_vq);
virtio_mb(vq->weak_barriers);
- return (u16)last_used_idx != vq->vring.used->idx;
+ return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
}
EXPORT_SYMBOL_GPL(virtqueue_poll);
@@ -633,12 +634,12 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
* either clear the flags bit or point the event index at the next
* entry. Always do both to keep code simple. */
- vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
/* TODO: tune this threshold */
- bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
- vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
+ bufs = (u16)(virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->last_used_idx) * 3 / 4;
+ vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs);
virtio_mb(vq->weak_barriers);
- if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
+ if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
END_USE(vq);
return false;
}
@@ -670,7 +671,7 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
/* detach_buf clears data, so grab it now. */
buf = vq->data[i];
detach_buf(vq, i);
- vq->vring.avail->idx--;
+ vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - 1);
END_USE(vq);
return buf;
}
@@ -747,12 +748,12 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
/* No callback? Tell other side not to bother us. */
if (!callback)
- vq->vring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
+ vq->vring.avail->flags |= cpu_to_virtio16(vdev, VRING_AVAIL_F_NO_INTERRUPT);
/* Put everything in free lists. */
vq->free_head = 0;
for (i = 0; i < num-1; i++) {
- vq->vring.desc[i].next = i+1;
+ vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
vq->data[i] = NULL;
}
vq->data[i] = NULL;
@@ -779,9 +780,11 @@ void vring_transport_features(struct virtio_device *vdev)
break;
case VIRTIO_RING_F_EVENT_IDX:
break;
+ case VIRTIO_F_VERSION_1:
+ break;
default:
/* We don't understand this bit. */
- clear_bit(i, vdev->features);
+ __virtio_clear_bit(vdev, i);
}
}
}
@@ -826,4 +829,20 @@ void virtio_break_device(struct virtio_device *dev)
}
EXPORT_SYMBOL_GPL(virtio_break_device);
+void *virtqueue_get_avail(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ return vq->vring.avail;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_avail);
+
+void *virtqueue_get_used(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ return vq->vring.used;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_used);
+
MODULE_LICENSE("GPL");
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-22 22:20:16 +0000