search for: vhost_virtqueu

...+- > 2 files changed, 58 insertions(+), 11 deletions(-) > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index b4a6e44d56a8..be822f0c9428 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -2292,13 +2292,12 @@ static int fetch_descs(struct vhost_virtqueue *vq) > * number of output then some number of input descriptors, it's actually two > * iovecs, but we pack them into one and note how many of each there were. > * > - * This function returns the descriptor number found, or vq->num (which is > - * never a valid descri...

...+- > 2 files changed, 58 insertions(+), 11 deletions(-) > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index b4a6e44d56a8..be822f0c9428 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -2292,13 +2292,12 @@ static int fetch_descs(struct vhost_virtqueue *vq) > * number of output then some number of input descriptors, it's actually two > * iovecs, but we pack them into one and note how many of each there were. > * > - * This function returns the descriptor number found, or vq->num (which is > - * never a valid descri...

...struct vhost_umem { - struct rb_root umem_tree; - struct list_head umem_list; - int numem; -}; - -enum vhost_uaddr_type { - VHOST_ADDR_DESC = 0, - VHOST_ADDR_AVAIL = 1, - VHOST_ADDR_USED = 2, - VHOST_NUM_ADDRS = 3, -}; - -/* The virtqueue structure describes a queue attached to a device. */ -struct vhost_virtqueue { - struct vhost_dev *dev; - - /* The actual ring of buffers. */ - struct mutex mutex; - unsigned int num; - struct vring_desc __user *desc; - struct vring_avail __user *avail; - struct vring_used __user *used; - const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS]; - struct file *kick; - str...

...struct vhost_umem { - struct rb_root umem_tree; - struct list_head umem_list; - int numem; -}; - -enum vhost_uaddr_type { - VHOST_ADDR_DESC = 0, - VHOST_ADDR_AVAIL = 1, - VHOST_ADDR_USED = 2, - VHOST_NUM_ADDRS = 3, -}; - -/* The virtqueue structure describes a queue attached to a device. */ -struct vhost_virtqueue { - struct vhost_dev *dev; - - /* The actual ring of buffers. */ - struct mutex mutex; - unsigned int num; - struct vring_desc __user *desc; - struct vring_avail __user *avail; - struct vring_used __user *used; - const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS]; - struct file *kick; - str...

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be

Hi all: This series implements packed virtqueues which were described at [1]. In this version we try to address the performance regression saw by V2. The root cause is packed virtqueue need more times of userspace memory accesssing which turns out to be very expensive. Thanks to the help of 7f466032dc9e ("vhost: access vq metadata through kernel virtual address"), such overhead cold be

...ers/vhost/vhost.h | 17 +++++++++++++- 2 files changed, 58 insertions(+), 11 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index b4a6e44d56a8..be822f0c9428 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2292,13 +2292,12 @@ static int fetch_descs(struct vhost_virtqueue *vq) * number of output then some number of input descriptors, it's actually two * iovecs, but we pack them into one and note how many of each there were. * - * This function returns the descriptor number found, or vq->num (which is - * never a valid descriptor number) if none was fou...

...; 1 file changed, 77 insertions(+), 17 deletions(-) > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index 400aa78..29709e7 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -869,6 +869,34 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, > ret; \ > }) > > +static inline int vhost_put_avail_event(struct vhost_virtqueue *vq) > +{ > + return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx), > + vhost_avail_event(vq)); > +} > + > +static inline int vhost_put_used(struct vhost_virtque...

...; 1 file changed, 77 insertions(+), 17 deletions(-) > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index 400aa78..29709e7 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -869,6 +869,34 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, > ret; \ > }) > > +static inline int vhost_put_avail_event(struct vhost_virtqueue *vq) > +{ > + return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx), > + vhost_avail_event(vq)); > +} > + > +static inline int vhost_put_used(struct vhost_virtque...

...CAN_ACCEL_UACCESS err_mmu_notifier: vhost_dev_free_iovecs(dev); #endif @@ -828,7 +828,7 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } -#if VHOST_ARCH_CAN_ACCEL_UACCESS +#ifdef VHOST_ARCH_CAN_ACCEL_UACCESS static void vhost_setup_uaddr(struct vhost_virtqueue *vq, int index, unsigned long uaddr, size_t size, bool write) @@ -959,12 +959,12 @@ void vhost_dev_cleanup(struct vhost_dev *dev) dev->worker = NULL; } if (dev->mm) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS +#ifdef VHOST_ARCH_CAN_ACCEL_UACCESS mmu_notifier_unregister(...

...CAN_ACCEL_UACCESS err_mmu_notifier: vhost_dev_free_iovecs(dev); #endif @@ -828,7 +828,7 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } -#if VHOST_ARCH_CAN_ACCEL_UACCESS +#ifdef VHOST_ARCH_CAN_ACCEL_UACCESS static void vhost_setup_uaddr(struct vhost_virtqueue *vq, int index, unsigned long uaddr, size_t size, bool write) @@ -959,12 +959,12 @@ void vhost_dev_cleanup(struct vhost_dev *dev) dev->worker = NULL; } if (dev->mm) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS +#ifdef VHOST_ARCH_CAN_ACCEL_UACCESS mmu_notifier_unregister(...

...drivers/vhost/vhost.h | 12 ------------ 2 files changed, 8 insertions(+), 40 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 72ee55c810c4..e6931b760b61 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2299,12 +2299,12 @@ static int fetch_buf(struct vhost_virtqueue *vq) return 1; } -/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */ +/* Revert the effect of fetch_buf. Useful for error handling. */ +static void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n) { vq->last_avail_idx -= n; } -EXPORT_SYMBOL_GPL(vhost_dis...

...nsertions(+), 11 deletions(-) > > > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > > index b4a6e44d56a8..be822f0c9428 100644 > > --- a/drivers/vhost/vhost.c > > +++ b/drivers/vhost/vhost.c > > @@ -2292,13 +2292,12 @@ static int fetch_descs(struct vhost_virtqueue *vq) > > * number of output then some number of input descriptors, it's actually two > > * iovecs, but we pack them into one and note how many of each there were. > > * > > - * This function returns the descriptor number found, or vq->num (which is > >...

...644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -43,11 +43,16 @@ enum { > #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num]) > > #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY > -static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq) > +static void vhost_disable_user_be(struct vhost_virtqueue *vq) > { > vq->user_be = !virtio_legacy_is_little_endian(); > } > Hmm this doesn't look like an improvement to me. What does it mean to disable big endian? Make it little endian? Existing reset seems to m...

...644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -43,11 +43,16 @@ enum { > #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num]) > > #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY > -static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq) > +static void vhost_disable_user_be(struct vhost_virtqueue *vq) > { > vq->user_be = !virtio_legacy_is_little_endian(); > } > Hmm this doesn't look like an improvement to me. What does it mean to disable big endian? Make it little endian? Existing reset seems to m...

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through vmap() and resigter MMU notifier for invalidation. Test shows about 24% improvement on TX PPS. TCP_STREAM doesn't see obvious improvement.

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through vmap() and resigter MMU notifier for invalidation. Test shows about 24% improvement on TX PPS. TCP_STREAM doesn't see obvious improvement.

Hi all: This RFC implement packed ring layout. The code were tested with Tiwei's RFC V5 at https://lkml.org/lkml/2018/5/22/138. Some fixups and tweaks were needed on top of Tiwei's code to make it run for event index. Pktgen reports about 20% improvement on TX PPS when doing pktgen from guest to host. No ovbious improvement on RX PPS. We can do lots of optimizations on top but for simple

...t_head umem_list; > - int numem; > -}; > - > -enum vhost_uaddr_type { > - VHOST_ADDR_DESC = 0, > - VHOST_ADDR_AVAIL = 1, > - VHOST_ADDR_USED = 2, > - VHOST_NUM_ADDRS = 3, > -}; > - > -/* The virtqueue structure describes a queue attached to a device. */ > -struct vhost_virtqueue { > - struct vhost_dev *dev; > - > - /* The actual ring of buffers. */ > - struct mutex mutex; > - unsigned int num; > - struct vring_desc __user *desc; > - struct vring_avail __user *avail; > - struct vring_used __user *used; > - const struct vhost_umem_node *meta_iotlb...

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Changes from V1: - instead of pinning pages, use MMU notifier to invalidate vmaps and remap duing