search for: rcu_read_unlock_bh

...insertions(+), 5 deletions(-) > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index 9eda69e..c91af93 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + l...

...insertions(+), 5 deletions(-) > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index 9eda69e..c91af93 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + l...

...insertions(+), 5 deletions(-) > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index 9eda69e..c91af93 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + li...

...insertions(+), 5 deletions(-) > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index 9eda69e..c91af93 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + li...

...this desc buffers done DMA */ vq->heads[ubuf->desc].len = success ? VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN; @@ -322,6 +324,8 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) */ if (cnt <= 1 || !(cnt % 16)) vhost_poll_queue(&vq->poll); + + rcu_read_unlock_bh(); } /* Expects to be always run from workqueue - which acts as @@ -804,6 +808,8 @@ static int vhost_net_release(struct inode *inode, struct file *f) fput(tx_sock->file); if (rx_sock) fput(rx_sock->file); + /* Make sure no callbacks are outstanding */ + synchronize_rcu_bh(); /*...

...this desc buffers done DMA */ vq->heads[ubuf->desc].len = success ? VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN; @@ -322,6 +324,8 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) */ if (cnt <= 1 || !(cnt % 16)) vhost_poll_queue(&vq->poll); + + rcu_read_unlock_bh(); } /* Expects to be always run from workqueue - which acts as @@ -804,6 +808,8 @@ static int vhost_net_release(struct inode *inode, struct file *f) fput(tx_sock->file); if (rx_sock) fput(rx_sock->file); + /* Make sure no callbacks are outstanding */ + synchronize_rcu_bh(); /*...

...g the units and the special value 0. > MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" > " 1 -Enable; 0 - Disable"); > > @@ -287,12 +289,23 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static bool tx_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + unsigned long now = local_clock() >> 10; local_clock might go backwards if we jump between CPUs. One way to fix would be to record the CPU id and break out of loop...

...g the units and the special value 0. > MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" > " 1 -Enable; 0 - Disable"); > > @@ -287,12 +289,23 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static bool tx_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + unsigned long now = local_clock() >> 10; local_clock might go backwards if we jump between CPUs. One way to fix would be to record the CPU id and break out of loop...

...insertions(+), 5 deletions(-) > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index 9eda69e..ce6da77 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -287,6 +287,41 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + l...

...insertions(+), 5 deletions(-) > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > index 9eda69e..ce6da77 100644 > --- a/drivers/vhost/net.c > +++ b/drivers/vhost/net.c > @@ -287,6 +287,41 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > rcu_read_unlock_bh(); > } > > +static inline unsigned long busy_clock(void) > +{ > + return local_clock() >> 10; > +} > + > +static bool vhost_can_busy_poll(struct vhost_dev *dev, > + unsigned long endtime) > +{ > + return likely(!need_resched()) && > + l...

...diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > >>index 9eda69e..ce6da77 100644 > >>--- a/drivers/vhost/net.c > >>+++ b/drivers/vhost/net.c > >>@@ -287,6 +287,41 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > >> rcu_read_unlock_bh(); > >> } > >> > >>+static inline unsigned long busy_clock(void) > >>+{ > >>+ return local_clock() >> 10; > >>+} > >>+ > >>+static bool vhost_can_busy_poll(struct vhost_dev *dev, > >>+ unsigned long endtime)...

...diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > >>index 9eda69e..ce6da77 100644 > >>--- a/drivers/vhost/net.c > >>+++ b/drivers/vhost/net.c > >>@@ -287,6 +287,41 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) > >> rcu_read_unlock_bh(); > >> } > >> > >>+static inline unsigned long busy_clock(void) > >>+{ > >>+ return local_clock() >> 10; > >>+} > >>+ > >>+static bool vhost_can_busy_poll(struct vhost_dev *dev, > >>+ unsigned long endtime)...

This path introduces a helper which can give a hint for whether or not there's a work queued in the work list. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 6 ++++++ drivers/vhost/vhost.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index eec2f11..d42d11e 100644 --- a/drivers/vhost/vhost.c +++

This path introduces a helper which can give a hint for whether or not there's a work queued in the work list. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 6 ++++++ drivers/vhost/vhost.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index eec2f11..d42d11e 100644 --- a/drivers/vhost/vhost.c +++

...opytx, int, 0444); +module_param(busyloop_timeout, int, 0444); MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" " 1 -Enable; 0 - Disable"); @@ -287,12 +289,23 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) rcu_read_unlock_bh(); } +static bool tx_can_busy_poll(struct vhost_dev *dev, + unsigned long endtime) +{ + unsigned long now = local_clock() >> 10; + + return busyloop_timeout && !need_resched() && + !time_after(now, endtime) && !vhost_has_work(dev) && + s...

...--git a/drivers/vhost/net.c b/drivers/vhost/net.c >> > index 9eda69e..c91af93 100644 >> > --- a/drivers/vhost/net.c >> > +++ b/drivers/vhost/net.c >> > @@ -287,6 +287,44 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) >> > rcu_read_unlock_bh(); >> > } >> > >> > +static inline unsigned long busy_clock(void) >> > +{ >> > + return local_clock() >> 10; >> > +} >> > + >> > +static bool vhost_can_busy_poll(struct vhost_dev *dev, >> > + unsigned long...

...this desc buffers done DMA */ vq->heads[ubuf->desc].len = success ? VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN; @@ -322,6 +324,8 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) */ if (cnt <= 1 || !(cnt % 16)) vhost_poll_queue(&vq->poll); + + rcu_read_unlock_bh(); } /* Expects to be always run from workqueue - which acts as @@ -804,6 +808,8 @@ static int vhost_net_release(struct inode *inode, struct file *f) fput(tx_sock->file); if (rx_sock) fput(rx_sock->file); + /* Make sure no callbacks are outstanding */ + synchronize_rcu_bh(); /*...

...++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index afa06d2..2923eee 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -288,6 +288,16 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) rcu_read_unlock_bh(); } +static void fix_virtio_net_hdr(struct vhost_virtqueue *vq) +{ + struct virtio_net_hdr *hdr = vq->iov[0].iov_base; + + hdr->hdr_len = vhost16_to_cpu(vq, hdr->hdr_len); + hdr->gso_size = vhost16_to_cpu(vq, hdr->gso_size); + hdr->csum_start = vhost16_to_cpu(vq, hdr->csum...

...++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index afa06d2..2923eee 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -288,6 +288,16 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) rcu_read_unlock_bh(); } +static void fix_virtio_net_hdr(struct vhost_virtqueue *vq) +{ + struct virtio_net_hdr *hdr = vq->iov[0].iov_base; + + hdr->hdr_len = vhost16_to_cpu(vq, hdr->hdr_len); + hdr->gso_size = vhost16_to_cpu(vq, hdr->gso_size); + hdr->csum_start = vhost16_to_cpu(vq, hdr->csum...

This series tries to add basic busy polling for vhost net. The idea is simple: at the end of tx/rx processing, busy polling for new tx added descriptor and rx receive socket for a while. The maximum number of time (in us) could be spent on busy polling was specified ioctl. Test A were done through: - 50 us as busy loop timeout - Netperf 2.6 - Two machines with back to back connected mlx4 - Guest