[PATCH net-next RFC 2/3] vhost: support urgent descriptors

From: Jason Wang
Date: Sat Oct 11 2014 - 03:17:53 EST

This patches let vhost-net support urgent descriptors. For zerocopy case,
two new types of length was introduced to make it work.

Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
---
drivers/vhost/net.c | 43 +++++++++++++++++++++++++++++++------------
drivers/vhost/scsi.c | 23 +++++++++++++++--------
drivers/vhost/test.c | 5 +++--
drivers/vhost/vhost.c | 44 +++++++++++++++++++++++++++++---------------
drivers/vhost/vhost.h | 19 +++++++++++++------
5 files changed, 91 insertions(+), 43 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 8dae2f7..37b0bb5 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -48,9 +48,13 @@ 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 5
+/* Lower device DMA doen, urgent bit set */
+#define VHOST_DMA_DONE_LEN_URGENT 4
/* Lower device DMA done */
-#define VHOST_DMA_DONE_LEN 2
+#define VHOST_DMA_DONE_LEN 3
+/* Lower device DMA in progress, urgent bit set */
+#define VHOST_DMA_URGENT 2
/* Lower device DMA in progress */
#define VHOST_DMA_IN_PROGRESS 1
/* Buffer unused */
@@ -284,11 +288,13 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
container_of(vq, struct vhost_net_virtqueue, vq);
int i, add;
int j = 0;
+ bool urgent = false;

for (i = nvq->done_idx; i != nvq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
if (vq->heads[i].len == VHOST_DMA_FAILED_LEN)
vhost_net_tx_err(net);
if (VHOST_DMA_IS_DONE(vq->heads[i].len)) {
+ urgent = urgent || vq->heads[i].len == VHOST_DMA_DONE_LEN_URGENT;
vq->heads[i].len = VHOST_DMA_CLEAR_LEN;
++j;
} else
@@ -296,7 +302,7 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
}
while (j) {
add = min(UIO_MAXIOV - nvq->done_idx, j);
- vhost_add_used_and_signal_n(vq->dev, vq,
+ vhost_add_used_and_signal_n(vq->dev, vq, urgent,
&vq->heads[nvq->done_idx], add);
nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV;
j -= add;
@@ -311,9 +317,14 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)

rcu_read_lock_bh();

- /* set len to mark this desc buffers done DMA */
- vq->heads[ubuf->desc].len = success ?
- VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
+ if (success) {
+ if (vq->heads[ubuf->desc].len == VHOST_DMA_IN_PROGRESS)
+ vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN;
+ else
+ vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN_URGENT;
+ } else {
+ vq->heads[ubuf->desc].len = VHOST_DMA_FAILED_LEN;
+ }
cnt = vhost_net_ubuf_put(ubufs);

/*
@@ -363,6 +374,7 @@ static void handle_tx(struct vhost_net *net)
zcopy = nvq->ubufs;

for (;;) {
+ bool urgent;
/* Release DMAs done buffers first */
if (zcopy)
vhost_zerocopy_signal_used(net, vq);
@@ -374,7 +386,7 @@ static void handle_tx(struct vhost_net *net)
% UIO_MAXIOV == nvq->done_idx))
break;

- head = vhost_get_vq_desc(vq, vq->iov,
+ head = vhost_get_vq_desc(vq, &urgent, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
@@ -417,7 +429,8 @@ static void handle_tx(struct vhost_net *net)
ubuf = nvq->ubuf_info + nvq->upend_idx;

vq->heads[nvq->upend_idx].id = head;
- vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
+ vq->heads[nvq->upend_idx].len = urgent ?
+ VHOST_DMA_URGENT : VHOST_DMA_IN_PROGRESS;
ubuf->callback = vhost_zerocopy_callback;
ubuf->ctx = nvq->ubufs;
ubuf->desc = nvq->upend_idx;
@@ -445,7 +458,7 @@ static void handle_tx(struct vhost_net *net)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
if (!zcopy_used)
- vhost_add_used_and_signal(&net->dev, vq, head, 0);
+ vhost_add_used_and_signal(&net->dev, vq, urgent, head, 0);
else
vhost_zerocopy_signal_used(net, vq);
total_len += len;
@@ -488,6 +501,7 @@ static int peek_head_len(struct sock *sk)
* returns number of buffer heads allocated, negative on error
*/
static int get_rx_bufs(struct vhost_virtqueue *vq,
+ bool *urgentp,
struct vring_used_elem *heads,
int datalen,
unsigned *iovcount,
@@ -502,11 +516,13 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
int r, nlogs = 0;

while (datalen > 0 && headcount < quota) {
+ bool urgent = false;
+
if (unlikely(seg >= UIO_MAXIOV)) {
r = -ENOBUFS;
goto err;
}
- r = vhost_get_vq_desc(vq, vq->iov + seg,
+ r = vhost_get_vq_desc(vq, &urgent, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
if (unlikely(r < 0))
@@ -527,6 +543,7 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
nlogs += *log_num;
log += *log_num;
}
+ *urgentp = *urgentp || urgent;
heads[headcount].id = d;
heads[headcount].len = iov_length(vq->iov + seg, in);
datalen -= heads[headcount].len;
@@ -590,9 +607,11 @@ static void handle_rx(struct vhost_net *net)
mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);

while ((sock_len = peek_head_len(sock->sk))) {
+ bool urgent = false;
+
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
- headcount = get_rx_bufs(vq, vq->heads, vhost_len,
+ headcount = get_rx_bufs(vq, &urgent, vq->heads, vhost_len,
&in, vq_log, &log,
likely(mergeable) ? UIO_MAXIOV : 1);
/* On error, stop handling until the next kick. */
@@ -654,7 +673,7 @@ static void handle_rx(struct vhost_net *net)
vhost_discard_vq_desc(vq, headcount);
break;
}
- vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+ vhost_add_used_and_signal_n(&net->dev, vq, urgent, vq->heads,
headcount);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 69906ca..0a7e5bc 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -72,6 +72,8 @@ struct tcm_vhost_cmd {
int tvc_vq_desc;
/* virtio-scsi initiator task attribute */
int tvc_task_attr;
+ /* Descriptor urgent? */
+ bool tvc_vq_desc_urgent;
/* virtio-scsi initiator data direction */
enum dma_data_direction tvc_data_direction;
/* Expected data transfer length from virtio-scsi header */
@@ -606,6 +608,7 @@ tcm_vhost_do_evt_work(struct vhost_scsi *vs, struct tcm_vhost_evt *evt)
struct virtio_scsi_event __user *eventp;
unsigned out, in;
int head, ret;
+ bool urgent;

if (!vq->private_data) {
vs->vs_events_missed = true;
@@ -614,7 +617,7 @@ tcm_vhost_do_evt_work(struct vhost_scsi *vs, struct tcm_vhost_evt *evt)

again:
vhost_disable_notify(&vs->dev, vq);
- head = vhost_get_vq_desc(vq, vq->iov,
+ head = vhost_get_vq_desc(vq, &urgent, vq->iov,
ARRAY_SIZE(vq->iov), &out, &in,
NULL, NULL);
if (head < 0) {
@@ -643,7 +646,7 @@ again:
eventp = vq->iov[out].iov_base;
ret = __copy_to_user(eventp, event, sizeof(*event));
if (!ret)
- vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+ vhost_add_used_and_signal(&vs->dev, vq, urgent, head, 0);
else
vq_err(vq, "Faulted on tcm_vhost_send_event\n");
}
@@ -704,7 +707,8 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
ret = copy_to_user(cmd->tvc_resp, &v_rsp, sizeof(v_rsp));
if (likely(ret == 0)) {
struct vhost_scsi_virtqueue *q;
- vhost_add_used(cmd->tvc_vq, cmd->tvc_vq_desc, 0);
+ vhost_add_used(cmd->tvc_vq, cmd->tvc_vq_desc_urgent,
+ cmd->tvc_vq_desc, 0);
q = container_of(cmd->tvc_vq, struct vhost_scsi_virtqueue, vq);
vq = q - vs->vqs;
__set_bit(vq, signal);
@@ -947,6 +951,7 @@ static void tcm_vhost_submission_work(struct work_struct *work)
static void
vhost_scsi_send_bad_target(struct vhost_scsi *vs,
struct vhost_virtqueue *vq,
+ bool urgent,
int head, unsigned out)
{
struct virtio_scsi_cmd_resp __user *resp;
@@ -958,7 +963,7 @@ vhost_scsi_send_bad_target(struct vhost_scsi *vs,
resp = vq->iov[out].iov_base;
ret = __copy_to_user(resp, &rsp, sizeof(rsp));
if (!ret)
- vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+ vhost_add_used_and_signal(&vs->dev, vq, urgent, head, 0);
else
pr_err("Faulted on virtio_scsi_cmd_resp\n");
}
@@ -980,6 +985,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
u8 *target, *lunp, task_attr;
bool hdr_pi;
void *req, *cdb;
+ bool urgent;

mutex_lock(&vq->mutex);
/*
@@ -993,7 +999,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
vhost_disable_notify(&vs->dev, vq);

for (;;) {
- head = vhost_get_vq_desc(vq, vq->iov,
+ head = vhost_get_vq_desc(vq, &urgent, vq->iov,
ARRAY_SIZE(vq->iov), &out, &in,
NULL, NULL);
pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
@@ -1067,7 +1073,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)

/* virtio-scsi spec requires byte 0 of the lun to be 1 */
if (unlikely(*lunp != 1)) {
- vhost_scsi_send_bad_target(vs, vq, head, out);
+ vhost_scsi_send_bad_target(vs, vq, urgent, head, out);
continue;
}

@@ -1075,7 +1081,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)

/* Target does not exist, fail the request */
if (unlikely(!tpg)) {
- vhost_scsi_send_bad_target(vs, vq, head, out);
+ vhost_scsi_send_bad_target(vs, vq, urgent, head, out);
continue;
}

@@ -1187,6 +1193,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
* tcm_vhost_queue_data_in() and tcm_vhost_queue_status()
*/
cmd->tvc_vq_desc = head;
+ cmd->tvc_vq_desc_urgent = urgent;
/*
* Dispatch tv_cmd descriptor for cmwq execution in process
* context provided by tcm_vhost_workqueue. This also ensures
@@ -1203,7 +1210,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
err_free:
vhost_scsi_free_cmd(cmd);
err_cmd:
- vhost_scsi_send_bad_target(vs, vq, head, out);
+ vhost_scsi_send_bad_target(vs, vq, urgent, head, out);
out:
mutex_unlock(&vq->mutex);
}
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index d9c501e..757f3a2 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -42,6 +42,7 @@ static void handle_vq(struct vhost_test *n)
int head;
size_t len, total_len = 0;
void *private;
+ bool urgent;

mutex_lock(&vq->mutex);
private = vq->private_data;
@@ -53,7 +54,7 @@ static void handle_vq(struct vhost_test *n)
vhost_disable_notify(&n->dev, vq);

for (;;) {
- head = vhost_get_vq_desc(vq, vq->iov,
+ head = vhost_get_vq_desc(vq, &urgent, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
@@ -79,7 +80,7 @@ static void handle_vq(struct vhost_test *n)
vq_err(vq, "Unexpected 0 len for TX\n");
break;
}
- vhost_add_used_and_signal(&n->dev, vq, head, 0);
+ vhost_add_used_and_signal(&n->dev, vq, urgent, head, 0);
total_len += len;
if (unlikely(total_len >= VHOST_TEST_WEIGHT)) {
vhost_poll_queue(&vq->poll);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c90f437..8a35e14 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -186,6 +186,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
vq->last_used_idx = 0;
vq->signalled_used = 0;
vq->signalled_used_valid = false;
+ vq->urgent = false;
vq->used_flags = 0;
vq->log_used = false;
vq->log_addr = -1ull;
@@ -1201,7 +1202,7 @@ static int get_indirect(struct vhost_virtqueue *vq,
* This function returns the descriptor number found, or vq->num (which is
* never a valid descriptor number) if none was found. A negative code is
* returned on error. */
-int vhost_get_vq_desc(struct vhost_virtqueue *vq,
+int vhost_get_vq_desc(struct vhost_virtqueue *vq, bool *urgent,
struct iovec iov[], unsigned int iov_size,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num)
@@ -1211,6 +1212,8 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
u16 last_avail_idx;
int ret;

+ *urgent = false;
+
/* 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))) {
@@ -1274,6 +1277,8 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
i, vq->desc + i);
return -EFAULT;
}
+ if (desc.flags & VRING_DESC_F_URGENT)
+ *urgent = true;
if (desc.flags & VRING_DESC_F_INDIRECT) {
ret = get_indirect(vq, iov, iov_size,
out_num, in_num,
@@ -1333,11 +1338,11 @@ EXPORT_SYMBOL_GPL(vhost_discard_vq_desc);

/* After we've used one of their buffers, we tell them about it. We'll then
* want to notify the guest, using eventfd. */
-int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
+int vhost_add_used(struct vhost_virtqueue *vq, bool urgent, unsigned int head, int len)
{
struct vring_used_elem heads = { head, len };

- return vhost_add_used_n(vq, &heads, 1);
+ return vhost_add_used_n(vq, urgent, &heads, 1);
}
EXPORT_SYMBOL_GPL(vhost_add_used);

@@ -1386,7 +1391,8 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,

/* After we've used one of their buffers, we tell them about it. We'll then
* want to notify the guest, using eventfd. */
-int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
+int vhost_add_used_n(struct vhost_virtqueue *vq, bool urgent,
+ struct vring_used_elem *heads,
unsigned count)
{
int start, n, r;
@@ -1416,13 +1422,14 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
+ vq->urgent = vq->urgent || urgent;
return r;
}
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, event, flags;
bool v;
/* Flush out used index updates. This is paired
* with the barrier that the Guest executes when enabling
@@ -1433,14 +1440,17 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
unlikely(vq->avail_idx == vq->last_avail_idx))
return true;

- if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
- __u16 flags;
- if (__get_user(flags, &vq->avail->flags)) {
- vq_err(vq, "Failed to get flags");
- return true;
- }
- return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
+ if (__get_user(flags, &vq->avail->flags)) {
+ vq_err(vq, "Failed to get flags");
+ return true;
}
+
+ if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX))
+ return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
+
+ if (vq->urgent && !(flags & VRING_AVAIL_F_NO_URGENT_INTERRUPT))
+ return true;
+
old = vq->signalled_used;
v = vq->signalled_used_valid;
new = vq->signalled_used = vq->last_used_idx;
@@ -1460,17 +1470,20 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
/* Signal the Guest tell them we used something up. */
- if (vq->call_ctx && vhost_notify(dev, vq))
+ if (vq->call_ctx && vhost_notify(dev, vq)) {
eventfd_signal(vq->call_ctx, 1);
+ vq->urgent = false;
+ }
}
EXPORT_SYMBOL_GPL(vhost_signal);

/* And here's the combo meal deal. Supersize me! */
void vhost_add_used_and_signal(struct vhost_dev *dev,
struct vhost_virtqueue *vq,
+ bool urgent,
unsigned int head, int len)
{
- vhost_add_used(vq, head, len);
+ vhost_add_used(vq, urgent, head, len);
vhost_signal(dev, vq);
}
EXPORT_SYMBOL_GPL(vhost_add_used_and_signal);
@@ -1478,9 +1491,10 @@ EXPORT_SYMBOL_GPL(vhost_add_used_and_signal);
/* multi-buffer version of vhost_add_used_and_signal */
void vhost_add_used_and_signal_n(struct vhost_dev *dev,
struct vhost_virtqueue *vq,
+ bool urgent,
struct vring_used_elem *heads, unsigned count)
{
- vhost_add_used_n(vq, heads, count);
+ vhost_add_used_n(vq, urgent, heads, count);
vhost_signal(dev, vq);
}
EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 3eda654..61ca542 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -96,6 +96,9 @@ struct vhost_virtqueue {
/* Last used index value we have signalled on */
bool signalled_used_valid;

+ /* Urgent descriptor was used */
+ bool urgent;
+
/* Log writes to used structure. */
bool log_used;
u64 log_addr;
@@ -138,20 +141,24 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp);
int vhost_vq_access_ok(struct vhost_virtqueue *vq);
int vhost_log_access_ok(struct vhost_dev *);

-int vhost_get_vq_desc(struct vhost_virtqueue *,
+int vhost_get_vq_desc(struct vhost_virtqueue *, bool *urgent,
struct iovec iov[], unsigned int iov_count,
unsigned int *out_num, unsigned int *in_num,
struct vhost_log *log, unsigned int *log_num);
void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);

int vhost_init_used(struct vhost_virtqueue *);
-int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
-int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
- unsigned count);
-void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
+int vhost_add_used(struct vhost_virtqueue *, bool urgent,
+ unsigned int head, int len);
+int vhost_add_used_n(struct vhost_virtqueue *, bool urgent,
+ struct vring_used_elem *heads, unsigned count);
+void vhost_add_used_and_signal(struct vhost_dev *,
+ struct vhost_virtqueue *,
+ bool urgent,
unsigned int id, int len);
void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
- struct vring_used_elem *heads, unsigned count);
+ bool urgent,
+ struct vring_used_elem *heads, unsigned count);
void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
--
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/