This patch makes vhost_scsi_flush() wait for all the pending requests
issued before the flush operation to be finished.
Changes in v4:
- Introduce vhost_scsi_inflight
- Drop array to track flush
- Use RCU to protect vs_inflight explicitly
Changes in v3:
- Rebase
- Drop 'tcm_vhost: Wait for pending requests in
vhost_scsi_clear_endpoint()' in this series, we already did that in
'tcm_vhost: Use vq->private_data to indicate if the endpoint is setup'
Changes in v2:
- Increase/Decrease inflight requests in
vhost_scsi_{allocate,free}_cmd and tcm_vhost_{allocate,free}_evt
Signed-off-by: Asias He <asias@xxxxxxxxxx>
---
drivers/vhost/tcm_vhost.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++
drivers/vhost/tcm_vhost.h | 5 ++++
2 files changed, 78 insertions(+)
diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c
index e09f0fe..5dde525 100644
--- a/drivers/vhost/tcm_vhost.c
+++ b/drivers/vhost/tcm_vhost.c
@@ -74,6 +74,11 @@ enum {
#define VHOST_SCSI_MAX_VQ 128
#define VHOST_SCSI_MAX_EVENT 128
+struct vhost_scsi_inflight {
+ wait_queue_head_t wait;
+ atomic_t count;
+};
+
struct vhost_scsi {
/* Protected by vhost_scsi->dev.mutex */
struct tcm_vhost_tpg **vs_tpg;
@@ -91,6 +96,8 @@ struct vhost_scsi {
struct mutex vs_events_lock; /* protect vs_events_dropped,events_nr */
bool vs_events_dropped; /* any missed events */
int vs_events_nr; /* num of pending events */
+
+ struct vhost_scsi_inflight __rcu *vs_inflight; /* track inflight req */
};
/* Local pointer to allocated TCM configfs fabric module */
@@ -108,6 +115,51 @@ static int iov_num_pages(struct iovec *iov)
((unsigned long)iov->iov_base & PAGE_MASK)) >> PAGE_SHIFT;
}
+static struct vhost_scsi_inflight *
+tcm_vhost_alloc_inflight(struct vhost_scsi *vs)
+{
+ struct vhost_scsi_inflight *inflight;
+
+ inflight = kzalloc(sizeof(*inflight), GFP_KERNEL);
+ if (inflight) {
+ atomic_set(&inflight->count, 0);
+ init_waitqueue_head(&inflight->wait);
+ }
+ rcu_assign_pointer(vs->vs_inflight, inflight);
+ synchronize_rcu();
+
+ return inflight;
+}
+
+static struct vhost_scsi_inflight *
+tcm_vhost_inc_inflight(struct vhost_scsi *vs)
+{
+ struct vhost_scsi_inflight *inflight;
+
+ rcu_read_lock();
+ inflight = rcu_dereference(vs->vs_inflight);
+ if (inflight)
+ atomic_inc(&inflight->count);
+ rcu_read_unlock();
+
+ return inflight;
+}
+
+static void tcm_vhost_dec_inflight(struct vhost_scsi_inflight *inflight)
+{
+ /*
+ * Wakeup the waiter when all the requests issued before the flush
+ * operation are finished.
+ */
+ if (inflight && !atomic_dec_return(&inflight->count))
+ wake_up(&inflight->wait);
+}
+
+static bool tcm_vhost_done_inflight(struct vhost_scsi_inflight *inflight)
+{
+ return atomic_read(&inflight->count) == 0;
+}
+
static bool tcm_vhost_check_feature(struct vhost_scsi *vs, int feature)
{
bool ret = false;
@@ -402,6 +454,7 @@ static int tcm_vhost_queue_tm_rsp(struct se_cmd *se_cmd)
static void tcm_vhost_free_evt(struct vhost_scsi *vs, struct tcm_vhost_evt *evt)
{
mutex_lock(&vs->vs_events_lock);
+ tcm_vhost_dec_inflight(evt->inflight);
vs->vs_events_nr--;
kfree(evt);
mutex_unlock(&vs->vs_events_lock);
@@ -423,6 +476,7 @@ static struct tcm_vhost_evt *tcm_vhost_allocate_evt(struct vhost_scsi *vs,
if (evt) {
evt->event.event = event;
evt->event.reason = reason;
+ evt->inflight = tcm_vhost_inc_inflight(vs);
vs->vs_events_nr++;
}
mutex_unlock(&vs->vs_events_lock);
@@ -445,6 +499,8 @@ static void vhost_scsi_free_cmd(struct tcm_vhost_cmd *tv_cmd)
kfree(tv_cmd->tvc_sgl);
}
+ tcm_vhost_dec_inflight(tv_cmd->inflight);
+
kfree(tv_cmd);
}
@@ -595,6 +651,7 @@ static struct tcm_vhost_cmd *vhost_scsi_allocate_cmd(
tv_cmd->tvc_data_direction = data_direction;
tv_cmd->tvc_nexus = tv_nexus;
tv_cmd->tvc_vhost = vs;
+ tv_cmd->inflight = tcm_vhost_inc_inflight(vs);
return tv_cmd;
}
@@ -983,10 +1040,22 @@ static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index)
static void vhost_scsi_flush(struct vhost_scsi *vs)
{
int i;
+ struct vhost_scsi_inflight *inflight;
+
+ inflight = ACCESS_ONCE(vs->vs_inflight);
+ if (!tcm_vhost_alloc_inflight(vs))
+ return;
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
vhost_scsi_flush_vq(vs, i);
vhost_work_flush(&vs->dev, &vs->vs_completion_work);
+ vhost_work_flush(&vs->dev, &vs->vs_event_work);
+
+ /* Wait until all requests issued before the flush to be finished */
+ if (inflight) {
+ wait_event(inflight->wait, tcm_vhost_done_inflight(inflight));
+ kfree(inflight);
+ }
}
/*
@@ -1195,6 +1264,9 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
s->vs_events_dropped = false;
mutex_init(&s->vs_events_lock);
+ if (!tcm_vhost_alloc_inflight(s))
+ return -ENOMEM;
+
s->vqs[VHOST_SCSI_VQ_CTL].handle_kick = vhost_scsi_ctl_handle_kick;
s->vqs[VHOST_SCSI_VQ_EVT].handle_kick = vhost_scsi_evt_handle_kick;
for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++)
@@ -1220,6 +1292,7 @@ static int vhost_scsi_release(struct inode *inode, struct file *f)
vhost_scsi_clear_endpoint(s, &t);
vhost_dev_stop(&s->dev);
vhost_dev_cleanup(&s->dev, false);
+ kfree(s->vs_inflight);
kfree(s);
return 0;
}
diff --git a/drivers/vhost/tcm_vhost.h b/drivers/vhost/tcm_vhost.h
index 94e9ee53..7567767 100644
--- a/drivers/vhost/tcm_vhost.h
+++ b/drivers/vhost/tcm_vhost.h
@@ -2,6 +2,7 @@
#define TCM_VHOST_NAMELEN 256
#define TCM_VHOST_MAX_CDB_SIZE 32
+struct vhost_scsi_inflight;
struct tcm_vhost_cmd {
/* Descriptor from vhost_get_vq_desc() for virt_queue segment */
int tvc_vq_desc;
@@ -37,6 +38,8 @@ struct tcm_vhost_cmd {
unsigned char tvc_sense_buf[TRANSPORT_SENSE_BUFFER];
/* Completed commands list, serviced from vhost worker thread */
struct llist_node tvc_completion_list;
+ /* Used to track inflight req */
+ struct vhost_scsi_inflight *inflight;
};
struct tcm_vhost_nexus {
@@ -91,6 +94,8 @@ struct tcm_vhost_evt {
struct virtio_scsi_event event;
/* virtio_scsi event list, serviced from vhost worker thread */
struct llist_node list;
+ /* Used to track inflight req */
+ struct vhost_scsi_inflight *inflight;
};
/*
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
