search for: __vhost_get_user_slow

...q_meta_fetch(struct vhost_virtqueue *vq, if (!map) return NULL; - return (void *)(uintptr_t)(map->addr + addr - map->start); + return (void __user *)(uintptr_t)(map->addr + addr - map->start); } /* Can we switch to this memory table? */ @@ -869,7 +869,7 @@ static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, * not happen in this case. */ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, - void *addr, unsigned int size, + void __user *addr, unsigned int size, int type) { void __user *uaddr = vhost_vq_meta_fetch(vq, -- M...

...ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); @@ -782,17 +823,12 @@ static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to, return ret; } -static void __user *__vhost_get_user(struct vhost_virtqueue *vq, - void *addr, unsigned size) +static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, + void *addr, unsigned int size, + int type) { int ret; - /* This function should be called after iotlb - * prefetch, which means we're sure that vq - * could be access through iotlb. So -EAGAIN should - * not happen in this case. - */ - /* TODO:...

...ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); @@ -782,17 +823,12 @@ static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to, return ret; } -static void __user *__vhost_get_user(struct vhost_virtqueue *vq, - void *addr, unsigned size) +static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, + void *addr, unsigned int size, + int type) { int ret; - /* This function should be called after iotlb - * prefetch, which means we're sure that vq - * could be access through iotlb. So -EAGAIN should - * not happen in this case. - */ - /* TODO:...

...ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); @@ -782,17 +823,12 @@ static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to, return ret; } -static void __user *__vhost_get_user(struct vhost_virtqueue *vq, - void *addr, unsigned size) +static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, + void *addr, unsigned int size, + int type) { int ret; - /* This function should be called after iotlb - * prefetch, which means we're sure that vq - * could be access through iotlb. So -EAGAIN should - * not happen in this case. - */ - /* TODO:...

...ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); @@ -782,17 +823,12 @@ static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to, return ret; } -static void __user *__vhost_get_user(struct vhost_virtqueue *vq, - void *addr, unsigned size) +static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, + void *addr, unsigned int size, + int type) { int ret; - /* This function should be called after iotlb - * prefetch, which means we're sure that vq - * could be access through iotlb. So -EAGAIN should - * not happen in this case. - */ - /* TODO:...

...x\n", from, - (unsigned long long) size); + vq_err(vq, "IOTLB translation failure: uaddr %p size 0x%llx\n", + from, (unsigned long long)size); goto out; } iov_iter_init(&f, READ, vq->iotlb_iov, ret, size); @@ -827,16 +826,14 @@ static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); if (ret < 0) { - vq_err(vq, "IOTLB translation failure: uaddr " - "%p size 0x%llx\n", addr, - (unsigned long long) size); + vq_err(vq, "IOTLB translation failure: uaddr...

...x\n", from, - (unsigned long long) size); + vq_err(vq, "IOTLB translation failure: uaddr %p size 0x%llx\n", + from, (unsigned long long)size); goto out; } iov_iter_init(&f, READ, vq->iotlb_iov, ret, size); @@ -827,16 +826,14 @@ static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); if (ret < 0) { - vq_err(vq, "IOTLB translation failure: uaddr " - "%p size 0x%llx\n", addr, - (unsigned long long) size); + vq_err(vq, "IOTLB translation failure: uaddr...

Hi all: This RFC implement packed ring layout. The code were tested with pmd implement by Jens at http://dpdk.org/ml/archives/dev/2018-January/089417.html. Minor change was needed for pmd codes to kick virtqueue since it assumes a busy polling backend. Test were done between localhost and guest. Testpmd (rxonly) in guest reports 2.4Mpps. Testpmd (txonly) repots about 2.1Mpps. Notes: The event

Hi all: This RFC implement packed ring layout. The code were tested with pmd implement by Jens at http://dpdk.org/ml/archives/dev/2018-January/089417.html. Minor change was needed for pmd codes to kick virtqueue since it assumes a busy polling backend. Test were done between localhost and guest. Testpmd (rxonly) in guest reports 2.4Mpps. Testpmd (txonly) repots about 2.1Mpps. Notes: The event

Hi all: This RFC implement packed ring layout. The code were tested with Tiwei's RFC V3 ahttps://lkml.org/lkml/2018/4/25/34. 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 PPS (event index is off). More testing is ongoing. Notes for tester: - Start from this version, vhost need qemu co-operation to work

Hi all: This RFC implement packed ring layout. The code were tested with Tiwei's RFC V3 ahttps://lkml.org/lkml/2018/4/25/34. 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 PPS (event index is off). More testing is ongoing. Notes for tester: - Start from this version, vhost need qemu co-operation to work

Hi all: This RFC implement packed ring layout. The code were tested with Tiwei's RFC V2 a thttps://lkml.org/lkml/2018/4/1/48. Some fixups and tweaks were needed on top of Tiwei's code to make it run. TCP stream and pktgen does not show obvious difference compared with split ring. Changes from V2: - do not use & in checking desc_event_flags - off should be most significant bit -

Hi all: This RFC implement packed ring layout. The code were tested with Tiwei's RFC V2 a thttps://lkml.org/lkml/2018/4/1/48. Some fixups and tweaks were needed on top of Tiwei's code to make it run. TCP stream and pktgen does not show obvious difference compared with split ring. Changes from V2: - do not use & in checking desc_event_flags - off should be most significant bit -

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

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's guest driver series at https://patchwork.ozlabs.org/cover/942297/ Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's guest driver series at https://patchwork.ozlabs.org/cover/942297/ Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's RFC V6 at https://lkml.org/lkml/2018/6/5/120. Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test virtio-net pmd as well when

Hi all: This series implements packed virtqueues. The code were tested with Tiwei's RFC V6 at https://lkml.org/lkml/2018/6/5/120. Pktgen test for both RX and TX does not show obvious difference with split virtqueues. The main bottleneck is the guest Linux driver, since it can not stress vhost for a 100% CPU utilization. A full TCP benchmark is ongoing. Will test virtio-net pmd as well when

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