search for: get_buf

...n we triger a tx interrupt, > the vq->event_triggered will be set to true. It will no longer be set to > false. Unless we explicitly call virtqueue_enable_cb_delayed or > virtqueue_enable_cb_prepare. This patch (commited as 35395770f803 ("virtio_ring: don't update event idx on get_buf") in next-20230327 apparently breaks 9p, as reported by Luis in https://lkml.kernel.org/r/ZCI+7Wg5OclSlE8c at bombadil.infradead.org I've just hit had a look at recent patches[1] and reverted this to test and I can mount again, so I'm pretty sure this is the culprit, but I didn't...

...er is relatively small. > > Because event_triggered is true. Therefore, VRING_AVAIL_F_NO_INTERRUPT or > VRING_PACKED_EVENT_FLAG_DISABLE will not be set. So we update > vring_used_event(&vq->split.vring) or vq->packed.vring.driver->off_wrap > every time we call virtqueue_get_buf_ctx. This will bring more interruptions. > > To summarize: > 1) event_triggered was set to true in vring_interrupt() > 2) after this nothing will happen for virtqueue_disable_cb() so > VRING_AVAIL_F_NO_INTERRUPT is not set in avail_flags_shadow > 3) virtqueue_get_buf_ctx_split...

virtqueue ops were introduced in the hope that we'll have multiple implementations besides virtio_ring, but none have surfaced so far, and given that existing virtio ring is deployed in production we are likely stuck with it now, so this layer just adds complexity and overhead. Further, the need to pass vq twice to each call (as in dev->vq->vq_ops->kick(dev->vq) ) adds potential

virtqueue ops were introduced in the hope that we'll have multiple implementations besides virtio_ring, but none have surfaced so far, and given that existing virtio ring is deployed in production we are likely stuck with it now, so this layer just adds complexity and overhead. Further, the need to pass vq twice to each call (as in dev->vq->vq_ops->kick(dev->vq) ) adds potential

The get_buf() API sets the second arg to the number of bytes *written* by the other side; in this case it should be zero as these are output buffers. lguest gets this right (obviously kvm's console doesn't), resulting in continual buildup of console writes. Signed-off-by: Rusty Russell <rusty at r...

The get_buf() API sets the second arg to the number of bytes *written* by the other side; in this case it should be zero as these are output buffers. lguest gets this right (obviously kvm's console doesn't), resulting in continual buildup of console writes. Signed-off-by: Rusty Russell <rusty at r...

Rusty, I have seen an oops triggered by the following bug statement in virtio-rng: if (vq->vq_ops->add_buf(vq, &sg, 0, 1, &random_data) != 0) BUG(); The problem is that we never called get_buf for complete buffers. The fix is simple: We have to free the buffer on interrupt to avoid a virtqueue "overflow". Christian Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> --- drivers/char/hw_random/virtio-rng.c | 3 +++ 1 file changed, 3 insertions(+) Index...

Rusty, I have seen an oops triggered by the following bug statement in virtio-rng: if (vq->vq_ops->add_buf(vq, &sg, 0, 1, &random_data) != 0) BUG(); The problem is that we never called get_buf for complete buffers. The fix is simple: We have to free the buffer on interrupt to avoid a virtqueue "overflow". Christian Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> --- drivers/char/hw_random/virtio-rng.c | 3 +++ 1 file changed, 3 insertions(+) Index...

...; > Because event_triggered is true.Therefore, VRING_AVAIL_F_NO_INTERRUPT or > > > VRING_PACKED_EVENT_FLAG_DISABLE will not be set.So we update > > > vring_used_event(&vq->split.vring) or vq->packed.vring.driver->off_wrap > > > every time we call virtqueue_get_buf_ctx.This will bring more interruptions. > > > > Can you please post how to test with the performance numbers? > > > > iperf3 tcp stream: > vm1 -----------------> vm2 > vm2 just receive tcp data stream from vm1, and send the ack to vm1, > there are so > many tx...

...ful for measuring overhead */ +void alloc_ring(void) +{ +} + +/* guest side */ +int add_inbuf(unsigned len, void *buf, void *datap) +{ + return 0; +} + +/* + * skb_array API provides no way for producer to find out whether a given + * buffer was consumed. Our tests merely require that a successful get_buf + * implies that add_inbuf succeed in the past, and that add_inbuf will succeed, + * fake it accordingly. + */ +void *get_buf(unsigned *lenp, void **bufp) +{ + return "Buffer"; +} + +void poll_used(void) +{ +} + +void disable_call() +{ + assert(0); +} + +bool enable_call() +{ + assert(0);...

...ful for measuring overhead */ +void alloc_ring(void) +{ +} + +/* guest side */ +int add_inbuf(unsigned len, void *buf, void *datap) +{ + return 0; +} + +/* + * skb_array API provides no way for producer to find out whether a given + * buffer was consumed. Our tests merely require that a successful get_buf + * implies that add_inbuf succeed in the past, and that add_inbuf will succeed, + * fake it accordingly. + */ +void *get_buf(unsigned *lenp, void **bufp) +{ + return "Buffer"; +} + +void poll_used(void) +{ +} + +void disable_call() +{ + assert(0); +} + +bool enable_call() +{ + assert(0);...

...q = to_vvq(_vq); + + return vq->num_free ? true : false; +} + static int vring_add_buf(struct virtqueue *_vq, struct scatterlist sg[], unsigned int out, @@ -350,6 +357,7 @@ EXPORT_SYMBOL_GPL(vring_interrupt); static struct virtqueue_ops vring_vq_ops = { .add_buf = vring_add_buf, .get_buf = vring_get_buf, + .can_add_buf = vring_can_add_buf, .kick = vring_kick, .disable_cb = vring_disable_cb, .enable_cb = vring_enable_cb, diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4fca4f5..cc0e3aa 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -35,6...

...q = to_vvq(_vq); + + return vq->num_free ? true : false; +} + static int vring_add_buf(struct virtqueue *_vq, struct scatterlist sg[], unsigned int out, @@ -350,6 +357,7 @@ EXPORT_SYMBOL_GPL(vring_interrupt); static struct virtqueue_ops vring_vq_ops = { .add_buf = vring_add_buf, .get_buf = vring_get_buf, + .can_add_buf = vring_can_add_buf, .kick = vring_kick, .disable_cb = vring_disable_cb, .enable_cb = vring_enable_cb, diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4fca4f5..cc0e3aa 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -35,6...

...} > } > Because event_triggered is true.Therefore, VRING_AVAIL_F_NO_INTERRUPT or > VRING_PACKED_EVENT_FLAG_DISABLE will not be set.So we update > vring_used_event(&vq->split.vring) or vq->packed.vring.driver->off_wrap > every time we call virtqueue_get_buf_ctx.This will bring more interruptions. Can you please post how to test with the performance numbers? > > if event_triggered is set to true, do not update vring_used_event(&vq->split.vring) > or vq->packed.vring.driver->off_wrap > > Signed-off-by: huangjie.albert <h...

...gt;len = 0; + len = 0; goto fail; } @@ -444,13 +421,11 @@ static ssize_t send_buf(struct port *port, const char *in_buf, size_t in_count, * sent. Also ensure we return to userspace the number of * bytes that were successfully consumed by the host. */ - while (!out_vq->vq_ops->get_buf(out_vq, &tmplen)) + while (!out_vq->vq_ops->get_buf(out_vq, &len)) cpu_relax(); - - buf->len = tmplen; fail: /* We're expected to return the amount of data we wrote */ - return buf->len; + return len; } /* @@ -461,26 +436,25 @@ static ssize_t fill_readbuf(struct po...

...gt;len = 0; + len = 0; goto fail; } @@ -444,13 +421,11 @@ static ssize_t send_buf(struct port *port, const char *in_buf, size_t in_count, * sent. Also ensure we return to userspace the number of * bytes that were successfully consumed by the host. */ - while (!out_vq->vq_ops->get_buf(out_vq, &tmplen)) + while (!out_vq->vq_ops->get_buf(out_vq, &len)) cpu_relax(); - - buf->len = tmplen; fail: /* We're expected to return the amount of data we wrote */ - return buf->len; + return len; } /* @@ -461,26 +436,25 @@ static ssize_t fill_readbuf(struct po...

Hello, This is the patch that I have for adding support for multiple ports to virtio_console. It's pretty stable in my testing so far and the memory corruption that I had earlier has been resolved in linux-next so I'm proposing this for inclusion. This currently uses device major number 60 from the experimental range; Alan could you please reserve a new major number for virtio_console?

Hello, This is the patch that I have for adding support for multiple ports to virtio_console. It's pretty stable in my testing so far and the memory corruption that I had earlier has been resolved in linux-next so I'm proposing this for inclusion. This currently uses device major number 60 from the experimental range; Alan could you please reserve a new major number for virtio_console?

...any - * non-NULL pointer, since there's only ever one buffer. */ - if (out_vq->vq_ops->add_buf(out_vq, sg, 1, 0, (void *)1) >= 0) { - /* Tell Host to go! */ - out_vq->vq_ops->kick(out_vq); - /* Chill out until it's done with the buffer. */ - while (!out_vq->vq_ops->get_buf(out_vq, &len)) - cpu_relax(); + struct virtio_console_port *port; + + list_for_each_entry(port, &virtconsole.port_head, next) { + if (port->dev->devt == devt) + return port; } + return NULL; +} + +static struct virtio_console_port *get_port_from_id(u32 id) +{ + struct virtio_co...

...any - * non-NULL pointer, since there's only ever one buffer. */ - if (out_vq->vq_ops->add_buf(out_vq, sg, 1, 0, (void *)1) >= 0) { - /* Tell Host to go! */ - out_vq->vq_ops->kick(out_vq); - /* Chill out until it's done with the buffer. */ - while (!out_vq->vq_ops->get_buf(out_vq, &len)) - cpu_relax(); + struct virtio_console_port *port; + + list_for_each_entry(port, &virtconsole.port_head, next) { + if (port->dev->devt == devt) + return port; } + return NULL; +} + +static struct virtio_console_port *get_port_from_id(u32 id) +{ + struct virtio_co...