[RFC PATCH V3 4/5] vhost: introduce helpers to get the size of metadata area
Signed-off-by: Jason Wang --- drivers/vhost/vhost.c | 46 ++- 1 file changed, 28 insertions(+), 18 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 27b5c03feaac..54b43feef8d9 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -489,6 +489,27 @@ bool vhost_dev_has_owner(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_has_owner); +static size_t vhost_get_avail_size(struct vhost_virtqueue *vq, int num) +{ + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; + + return sizeof(*vq->avail) + + sizeof(*vq->avail->ring) * num + event; +} + +static size_t vhost_get_used_size(struct vhost_virtqueue *vq, int num) +{ + size_t event = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; + + return sizeof(*vq->used) + + sizeof(*vq->used->ring) * num + event; +} + +static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, int num) +{ + return sizeof(*vq->desc) * num; +} + /* Caller should have device mutex */ long vhost_dev_set_owner(struct vhost_dev *dev) { @@ -1248,13 +1269,9 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, struct vring_used __user *used) { - size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; - - return access_ok(VERIFY_READ, desc, num * sizeof *desc) && - access_ok(VERIFY_READ, avail, -sizeof *avail + num * sizeof *avail->ring + s) && - access_ok(VERIFY_WRITE, used, - sizeof *used + num * sizeof *used->ring + s); + return access_ok(VERIFY_READ, desc, vhost_get_desc_size(vq, num)) && + access_ok(VERIFY_READ, avail, vhost_get_avail_size(vq, num)) && + access_ok(VERIFY_WRITE, used, vhost_get_used_size(vq, num)); } static void vhost_vq_meta_update(struct vhost_virtqueue *vq, @@ -1306,22 +1323,18 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq, int vq_meta_prefetch(struct vhost_virtqueue *vq) { - size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; unsigned int num = vq->num; if (!vq->iotlb) return 1; return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc, - num * sizeof(*vq->desc), VHOST_ADDR_DESC) && + vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) && iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail, - sizeof *vq->avail + - num * sizeof(*vq->avail->ring) + s, + vhost_get_avail_size(vq, num), VHOST_ADDR_AVAIL) && iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used, - sizeof *vq->used + - num * sizeof(*vq->used->ring) + s, - VHOST_ADDR_USED); + vhost_get_used_size(vq, num), VHOST_ADDR_USED); } EXPORT_SYMBOL_GPL(vq_meta_prefetch); @@ -1338,13 +1351,10 @@ EXPORT_SYMBOL_GPL(vhost_log_access_ok); static bool vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base) { - size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; - return vq_memory_access_ok(log_base, vq->umem, vhost_has_feature(vq, VHOST_F_LOG_ALL)) && (!vq->log_used || log_access_ok(log_base, vq->log_addr, - sizeof *vq->used + - vq->num * sizeof *vq->used->ring + s)); + vhost_get_used_size(vq, vq->num))); } /* Can we start vq? */ -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[RFC PATCH V3 3/5] vhost: rename vq_iotlb_prefetch() to vq_meta_prefetch()
Rename the function to be more accurate since it actually tries to prefetch vq metadata address in IOTLB. And this will be used by following patch to prefetch metadata virtual addresses. Signed-off-by: Jason Wang --- drivers/vhost/net.c | 4 ++-- drivers/vhost/vhost.c | 4 ++-- drivers/vhost/vhost.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 36f3d0f49e60..0b4b3deab5aa 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -971,7 +971,7 @@ static void handle_tx(struct vhost_net *net) if (!sock) goto out; - if (!vq_iotlb_prefetch(vq)) + if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(>dev, vq); @@ -1140,7 +1140,7 @@ static void handle_rx(struct vhost_net *net) if (!sock) goto out; - if (!vq_iotlb_prefetch(vq)) + if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(>dev, vq); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 337ce6f5a098..27b5c03feaac 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1304,7 +1304,7 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq, return true; } -int vq_iotlb_prefetch(struct vhost_virtqueue *vq) +int vq_meta_prefetch(struct vhost_virtqueue *vq) { size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; unsigned int num = vq->num; @@ -1323,7 +1323,7 @@ int vq_iotlb_prefetch(struct vhost_virtqueue *vq) num * sizeof(*vq->used->ring) + s, VHOST_ADDR_USED); } -EXPORT_SYMBOL_GPL(vq_iotlb_prefetch); +EXPORT_SYMBOL_GPL(vq_meta_prefetch); /* Can we log writes? */ /* Caller should have device mutex but not vq mutex */ diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 466ef7542291..0d1ff977a43e 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -206,7 +206,7 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *); int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log, unsigned int log_num, u64 len); -int vq_iotlb_prefetch(struct vhost_virtqueue *vq); +int vq_meta_prefetch(struct vhost_virtqueue *vq); struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type); void vhost_enqueue_msg(struct vhost_dev *dev, -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[RFC PATCH V3 5/5] vhost: access vq metadata through kernel virtual address
It was noticed that the copy_user() friends that was used to access virtqueue metdata tends to be very expensive for dataplane implementation like vhost since it involves lots of software checks, speculation barrier, hardware feature toggling (e.g SMAP). The extra cost will be more obvious when transferring small packets since the time spent on metadata accessing become significant.. This patch tries to eliminate those overhead by accessing them through kernel virtual address by vmap(). To make the pages can be migrated, instead of pinning them through GUP, we use mmu notifiers to invalidate vmaps and re-establish vmaps during each round of metadata prefetching in necessary. For devices that doesn't use metadata prefetching, the memory acessors fallback to normal copy_user() implementation gracefully. The invalidation was synchronized with datapath through vq mutex, and in order to avoid hold vq mutex during range checking, MMU notifier was teared down when trying to modify vq metadata. Note that this was only done when device IOTLB is not enabled. We could use similar method to optimize it in the future. Tests shows about ~24% improvement on TX PPS when using virtio-user + vhost_net + xdp1 on TAP: Before: ~5.0Mpps After: ~6.1Mpps Signed-off-by: Jason Wang --- drivers/vhost/vhost.c | 263 +- drivers/vhost/vhost.h | 13 +++ 2 files changed, 274 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 54b43feef8d9..e1ecb8acf8a3 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -440,6 +440,9 @@ void vhost_dev_init(struct vhost_dev *dev, vq->indirect = NULL; vq->heads = NULL; vq->dev = dev; + memset(>avail_ring, 0, sizeof(vq->avail_ring)); + memset(>used_ring, 0, sizeof(vq->used_ring)); + memset(>desc_ring, 0, sizeof(vq->desc_ring)); mutex_init(>mutex); vhost_vq_reset(dev, vq); if (vq->handle_kick) @@ -510,6 +513,73 @@ static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, int num) return sizeof(*vq->desc) * num; } +static void vhost_uninit_vmap(struct vhost_vmap *map) +{ + if (map->addr) + vunmap(map->unmap_addr); + + map->addr = NULL; + map->unmap_addr = NULL; +} + +static int vhost_invalidate_vmap(struct vhost_virtqueue *vq, +struct vhost_vmap *map, +unsigned long ustart, +size_t size, +unsigned long start, +unsigned long end, +bool blockable) +{ + if (end < ustart || start > ustart - 1 + size) + return 0; + + if (!blockable) + return -EAGAIN; + + mutex_lock(>mutex); + vhost_uninit_vmap(map); + mutex_unlock(>mutex); + + return 0; +} + +static int vhost_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, +struct mm_struct *mm, +unsigned long start, +unsigned long end, +bool blockable) +{ + struct vhost_dev *dev = container_of(mn, struct vhost_dev, +mmu_notifier); + int i; + + for (i = 0; i < dev->nvqs; i++) { + struct vhost_virtqueue *vq = dev->vqs[i]; + + if (vhost_invalidate_vmap(vq, >avail_ring, + (unsigned long)vq->avail, + vhost_get_avail_size(vq, vq->num), + start, end, blockable)) + return -EAGAIN; + if (vhost_invalidate_vmap(vq, >desc_ring, + (unsigned long)vq->desc, + vhost_get_desc_size(vq, vq->num), + start, end, blockable)) + return -EAGAIN; + if (vhost_invalidate_vmap(vq, >used_ring, + (unsigned long)vq->used, + vhost_get_used_size(vq, vq->num), + start, end, blockable)) + return -EAGAIN; + } + + return 0; +} + +static const struct mmu_notifier_ops vhost_mmu_notifier_ops = { + .invalidate_range_start = vhost_mmu_notifier_invalidate_range_start, +}; + /* Caller should have device mutex */ long vhost_dev_set_owner(struct vhost_dev *dev) { @@ -541,7 +611,14 @@ long vhost_dev_set_owner(struct vhost_dev *dev) if (err) goto err_cgroup; + dev->mmu_notifier.ops =
[RFC PATCH V3 2/5] vhost: fine grain userspace memory accessors
This is used to hide the metadata address from virtqueue helpers. This will allow to implement a vmap based fast accessing to metadata. Signed-off-by: Jason Wang --- drivers/vhost/vhost.c | 94 +++ 1 file changed, 77 insertions(+), 17 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index f179b5ee14c4..337ce6f5a098 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -868,6 +868,34 @@ 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_virtqueue *vq, +struct vring_used_elem *head, int idx, +int count) +{ + return vhost_copy_to_user(vq, vq->used->ring + idx, head, + count * sizeof(*head)); +} + +static inline int vhost_put_used_flags(struct vhost_virtqueue *vq) + +{ + return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags), + >used->flags); +} + +static inline int vhost_put_used_idx(struct vhost_virtqueue *vq) + +{ + return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx), + >used->idx); +} + #define vhost_get_user(vq, x, ptr, type) \ ({ \ int ret; \ @@ -906,6 +934,43 @@ static void vhost_dev_unlock_vqs(struct vhost_dev *d) mutex_unlock(>vqs[i]->mutex); } +static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq, + __virtio16 *idx) +{ + return vhost_get_avail(vq, *idx, >avail->idx); +} + +static inline int vhost_get_avail_head(struct vhost_virtqueue *vq, + __virtio16 *head, int idx) +{ + return vhost_get_avail(vq, *head, + >avail->ring[idx & (vq->num - 1)]); +} + +static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq, + __virtio16 *flags) +{ + return vhost_get_avail(vq, *flags, >avail->flags); +} + +static inline int vhost_get_used_event(struct vhost_virtqueue *vq, + __virtio16 *event) +{ + return vhost_get_avail(vq, *event, vhost_used_event(vq)); +} + +static inline int vhost_get_used_idx(struct vhost_virtqueue *vq, +__virtio16 *idx) +{ + return vhost_get_used(vq, *idx, >used->idx); +} + +static inline int vhost_get_desc(struct vhost_virtqueue *vq, +struct vring_desc *desc, int idx) +{ + return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc)); +} + static int vhost_new_umem_range(struct vhost_umem *umem, u64 start, u64 size, u64 end, u64 userspace_addr, int perm) @@ -1761,8 +1826,7 @@ EXPORT_SYMBOL_GPL(vhost_log_write); static int vhost_update_used_flags(struct vhost_virtqueue *vq) { void __user *used; - if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags), - >used->flags) < 0) + if (vhost_put_used_flags(vq)) return -EFAULT; if (unlikely(vq->log_used)) { /* Make sure the flag is seen before log. */ @@ -1780,8 +1844,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq) static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event) { - if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx), - vhost_avail_event(vq))) + if (vhost_put_avail_event(vq)) return -EFAULT; if (unlikely(vq->log_used)) { void __user *used; @@ -1818,7 +1881,7 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq) r = -EFAULT; goto err; } - r = vhost_get_used(vq, last_used_idx, >used->idx); + r = vhost_get_used_idx(vq, _used_idx); if (r) { vq_err(vq, "Can't access used idx at %p\n", >used->idx); @@ -2017,7 +2080,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, last_avail_idx = vq->last_avail_idx; if (vq->avail_idx == vq->last_avail_idx) { - if (unlikely(vhost_get_avail(vq, avail_idx, >avail->idx))) { + if (unlikely(vhost_get_avail_idx(vq, _idx))) { vq_err(vq, "Failed to access avail idx at %p\n", >avail->idx); return -EFAULT; @@ -2044,8 +2107,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ - if
[RFC PATCH V3 1/5] vhost: generalize adding used elem
Use one generic vhost_copy_to_user() instead of two dedicated accessor. This will simplify the conversion to fine grain accessors. About 2% improvement of PPS were seen during vitio-user txonly test. Signed-off-by: Jason Wang --- drivers/vhost/vhost.c | 11 +-- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 55e5aa662ad5..f179b5ee14c4 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2174,16 +2174,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, start = vq->last_used_idx & (vq->num - 1); used = vq->used->ring + start; - if (count == 1) { - if (vhost_put_user(vq, heads[0].id, >id)) { - vq_err(vq, "Failed to write used id"); - return -EFAULT; - } - if (vhost_put_user(vq, heads[0].len, >len)) { - vq_err(vq, "Failed to write used len"); - return -EFAULT; - } - } else if (vhost_copy_to_user(vq, used, heads, count * sizeof *used)) { + if (vhost_copy_to_user(vq, used, heads, count * sizeof *used)) { vq_err(vq, "Failed to write used"); return -EFAULT; } -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[RFC PATCH V3 0/5] 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 V2: - fix buggy range overlapping check - tear down MMU notifier during vhost ioctl to make sure invalidation request can read metadata userspace address and vq size without holding vq mutex. Changes from V1: - instead of pinning pages, use MMU notifier to invalidate vmaps and remap duing metadata prefetch - fix build warning on MIPS Jason Wang (5): vhost: generalize adding used elem vhost: fine grain userspace memory accessors vhost: rename vq_iotlb_prefetch() to vq_meta_prefetch() vhost: introduce helpers to get the size of metadata area vhost: access vq metadata through kernel virtual address drivers/vhost/net.c | 4 +- drivers/vhost/vhost.c | 416 +- drivers/vhost/vhost.h | 15 +- 3 files changed, 384 insertions(+), 51 deletions(-) -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [RFC PATCH V2 3/3] vhost: access vq metadata through kernel virtual address
On 2018/12/29 上午3:34, David Miller wrote: From: Jason Wang Date: Fri, 28 Dec 2018 15:55:37 +0800 +static int vhost_invalidate_vmap(struct vhost_virtqueue *vq, +struct vhost_vmap *map, +unsigned long uaddr, +unsigned long start, +unsigned long end, +bool blockable) +{ + if (start < uaddr && end >= uaddr) { + if (!blockable) + return -EAGAIN; + mutex_lock(>mutex); + if (map->addr) + vunmap(map->unmap_addr); + map->addr = NULL; + map->unmap_addr = NULL; + mutex_unlock(>mutex); + } + + return 0; +} What are the rules for these invalidate operations? Can there be partial overlaps? If so, wouldn't you need some way of keeping track of the partially overlapping unmaps so that once all of the invalidates covering the range occur you properly cleanup and do the vunmap()? Yes, there can be partial overlap, so the check is buggy. We will remap the whole range in vq_meta_prefetch() before datapath path try to use them, so there's no need to track partial mapping here. I spot another bug that the caller will access vq->avail without synchronized with vhost ioctl. Since we don't want to hold vq mutex for each invalidation, I will tear down MMU notifier during vhost ioctl to make sure invalidation request can access them without hold vq mutex. Thanks ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization