[RFC,3/6] vringh: support VA with iotlb

Message ID	20221214163025.103075-4-sgarzare@redhat.com (mailing list archive)
State	RFC
Headers	show Return-Path: <netdev-owner@kernel.org> From: Stefano Garzarella <sgarzare@redhat.com> To: virtualization@lists.linux-foundation.org Cc: Jason Wang <jasowang@redhat.com>, Andrey Zhadchenko <andrey.zhadchenko@virtuozzo.com>, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, "Michael S. Tsirkin" <mst@redhat.com>, eperezma@redhat.com, stefanha@redhat.com, netdev@vger.kernel.org, Stefano Garzarella <sgarzare@redhat.com> Subject: [RFC PATCH 3/6] vringh: support VA with iotlb Date: Wed, 14 Dec 2022 17:30:22 +0100 Message-Id: <20221214163025.103075-4-sgarzare@redhat.com> In-Reply-To: <20221214163025.103075-1-sgarzare@redhat.com> References: <20221214163025.103075-1-sgarzare@redhat.com> MIME-Version: 1.0 Content-type: text/plain Content-Transfer-Encoding: 8bit Precedence: bulk
Series	vdpa_sim: add support for user VA \| expand [RFC,0/6] vdpa_sim: add support for user VA [RFC,1/6] vdpa: add bind_mm callback [RFC,2/6] vhost-vdpa: use bind_mm device callback [RFC,3/6] vringh: support VA with iotlb [RFC,4/6] vdpa_sim: make devices agnostic for work management [RFC,5/6] vdpa_sim: use kthread worker [RFC,6/6] vdpa_sim: add support for user VA

Context	Check	Description
netdev/tree_selection	success	Not a local patch

diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 212892cf9822..c70962f16b1f 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -32,6 +32,9 @@ struct vringh { /* Can we get away with weak barriers? */ bool weak_barriers; + /* Use user's VA */ + bool use_va; + /* Last available index we saw (ie. where we're up to). */ u16 last_avail_idx; @@ -279,7 +282,7 @@ void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb, spinlock_t *iotlb_lock); int vringh_init_iotlb(struct vringh *vrh, u64 features, - unsigned int num, bool weak_barriers, + unsigned int num, bool weak_barriers, bool use_va, struct vring_desc *desc, struct vring_avail *avail, struct vring_used *used); diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 9800f9bec225..e0bab3458b40 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -233,7 +233,8 @@ static int init_ctrl_vq(struct mlx5_vdpa_dev *mvdev) if (!mvdev->cvq.iotlb) return -ENOMEM; - vringh_set_iotlb(&mvdev->cvq.vring, mvdev->cvq.iotlb, &mvdev->cvq.iommu_lock); + vringh_set_iotlb(&mvdev->cvq.vring, mvdev->cvq.iotlb, + &mvdev->cvq.iommu_lock); return 0; } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 90913365def4..81ba0867e2c8 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2504,7 +2504,7 @@ static int setup_cvq_vring(struct mlx5_vdpa_dev *mvdev) if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)) err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features, - MLX5_CVQ_MAX_ENT, false, + MLX5_CVQ_MAX_ENT, false, false, (struct vring_desc *)(uintptr_t)cvq->desc_addr, (struct vring_avail *)(uintptr_t)cvq->driver_addr, (struct vring_used *)(uintptr_t)cvq->device_addr); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index b20689f8fe89..2e0ee7280aa8 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -67,7 +67,7 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) { struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; - vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false, + vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false, false, (struct vring_desc *)(uintptr_t)vq->desc_addr, (struct vring_avail *) (uintptr_t)vq->driver_addr, @@ -87,7 +87,7 @@ static void vdpasim_vq_reset(struct vdpasim *vdpasim, vq->cb = NULL; vq->private = NULL; vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features, - VDPASIM_QUEUE_MAX, false, NULL, NULL, NULL); + VDPASIM_QUEUE_MAX, false, false, NULL, NULL, NULL); vq->vring.notify = NULL; } diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 11f59dd06a74..c1f77dc93482 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1094,15 +1094,99 @@ EXPORT_SYMBOL(vringh_need_notify_kern); #if IS_REACHABLE(CONFIG_VHOST_IOTLB) -static int iotlb_translate(const struct vringh *vrh, - u64 addr, u64 len, u64 *translated, - struct bio_vec iov[], - int iov_size, u32 perm) +static int iotlb_translate_va(const struct vringh *vrh, + u64 addr, u64 len, u64 *translated, + struct iovec iov[], + int iov_size, u32 perm) { struct vhost_iotlb_map *map; struct vhost_iotlb *iotlb = vrh->iotlb; + u64 s = 0, last = addr + len - 1; + int ret = 0; + + spin_lock(vrh->iotlb_lock); + + while (len > s) { + u64 size; + + if (unlikely(ret >= iov_size)) { + ret = -ENOBUFS; + break; + } + + map = vhost_iotlb_itree_first(iotlb, addr, last); + if (!map || map->start > addr) { + ret = -EINVAL; + break; + } else if (!(map->perm & perm)) { + ret = -EPERM; + break; + } + + size = map->size - addr + map->start; + iov[ret].iov_len = min(len - s, size); + iov[ret].iov_base = (void __user *)(unsigned long) + (map->addr + addr - map->start); + s += size; + addr += size; + ++ret; + } + + spin_unlock(vrh->iotlb_lock); + + if (translated) + *translated = min(len, s); + + return ret; +} + +static inline int copy_from_va(const struct vringh *vrh, void *dst, void *src, + u64 len, u64 *translated) +{ + struct iovec iov[16]; + struct iov_iter iter; + int ret; + + ret = iotlb_translate_va(vrh, (u64)(uintptr_t)src, len, translated, iov, + ARRAY_SIZE(iov), VHOST_MAP_RO); + if (ret == -ENOBUFS) + ret = ARRAY_SIZE(iov); + else if (ret < 0) + return ret; + + iov_iter_init(&iter, READ, iov, ret, *translated); + + return copy_from_iter(dst, *translated, &iter); +} + +static inline int copy_to_va(const struct vringh *vrh, void *dst, void *src, + u64 len, u64 *translated) +{ + struct iovec iov[16]; + struct iov_iter iter; + int ret; + + ret = iotlb_translate_va(vrh, (u64)(uintptr_t)dst, len, translated, iov, + ARRAY_SIZE(iov), VHOST_MAP_WO); + if (ret == -ENOBUFS) + ret = ARRAY_SIZE(iov); + else if (ret < 0) + return ret; + + iov_iter_init(&iter, WRITE, iov, ret, *translated); + + return copy_to_iter(src, *translated, &iter); +} + +static int iotlb_translate_pa(const struct vringh *vrh, + u64 addr, u64 len, u64 *translated, + struct bio_vec iov[], + int iov_size, u32 perm) +{ + struct vhost_iotlb_map *map; + struct vhost_iotlb *iotlb = vrh->iotlb; + u64 s = 0, last = addr + len - 1; int ret = 0; - u64 s = 0; spin_lock(vrh->iotlb_lock); @@ -1114,8 +1198,7 @@ static int iotlb_translate(const struct vringh *vrh, break; } - map = vhost_iotlb_itree_first(iotlb, addr, - addr + len - 1); + map = vhost_iotlb_itree_first(iotlb, addr, last); if (!map || map->start > addr) { ret = -EINVAL; break; @@ -1143,28 +1226,61 @@ static int iotlb_translate(const struct vringh *vrh, return ret; } +static inline int copy_from_pa(const struct vringh *vrh, void *dst, void *src, + u64 len, u64 *translated) +{ + struct bio_vec iov[16]; + struct iov_iter iter; + int ret; + + ret = iotlb_translate_pa(vrh, (u64)(uintptr_t)src, len, translated, iov, + ARRAY_SIZE(iov), VHOST_MAP_RO); + if (ret == -ENOBUFS) + ret = ARRAY_SIZE(iov); + else if (ret < 0) + return ret; + + iov_iter_bvec(&iter, READ, iov, ret, *translated); + + return copy_from_iter(dst, *translated, &iter); +} + +static inline int copy_to_pa(const struct vringh *vrh, void *dst, void *src, + u64 len, u64 *translated) +{ + struct bio_vec iov[16]; + struct iov_iter iter; + int ret; + + ret = iotlb_translate_pa(vrh, (u64)(uintptr_t)dst, len, translated, iov, + ARRAY_SIZE(iov), VHOST_MAP_WO); + if (ret == -ENOBUFS) + ret = ARRAY_SIZE(iov); + else if (ret < 0) + return ret; + + iov_iter_bvec(&iter, WRITE, iov, ret, *translated); + + return copy_to_iter(src, *translated, &iter); +} + static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, void *src, size_t len) { u64 total_translated = 0; while (total_translated < len) { - struct bio_vec iov[16]; - struct iov_iter iter; u64 translated; int ret; - ret = iotlb_translate(vrh, (u64)(uintptr_t)src, - len - total_translated, &translated, - iov, ARRAY_SIZE(iov), VHOST_MAP_RO); - if (ret == -ENOBUFS) - ret = ARRAY_SIZE(iov); - else if (ret < 0) - return ret; - - iov_iter_bvec(&iter, READ, iov, ret, translated); + if (vrh->use_va) { + ret = copy_from_va(vrh, dst, src, + len - total_translated, &translated); + } else { + ret = copy_from_pa(vrh, dst, src, + len - total_translated, &translated); + } - ret = copy_from_iter(dst, translated, &iter); if (ret < 0) return ret; @@ -1182,22 +1298,17 @@ static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, u64 total_translated = 0; while (total_translated < len) { - struct bio_vec iov[16]; - struct iov_iter iter; u64 translated; int ret; - ret = iotlb_translate(vrh, (u64)(uintptr_t)dst, - len - total_translated, &translated, - iov, ARRAY_SIZE(iov), VHOST_MAP_WO); - if (ret == -ENOBUFS) - ret = ARRAY_SIZE(iov); - else if (ret < 0) - return ret; - - iov_iter_bvec(&iter, WRITE, iov, ret, translated); + if (vrh->use_va) { + ret = copy_to_va(vrh, dst, src, + len - total_translated, &translated); + } else { + ret = copy_to_pa(vrh, dst, src, + len - total_translated, &translated); + } - ret = copy_to_iter(src, translated, &iter); if (ret < 0) return ret; @@ -1212,20 +1323,36 @@ static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, static inline int getu16_iotlb(const struct vringh *vrh, u16 *val, const __virtio16 *p) { - struct bio_vec iov; - void *kaddr, *from; int ret; /* Atomic read is needed for getu16 */ - ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL, - &iov, 1, VHOST_MAP_RO); - if (ret < 0) - return ret; + if (vrh->use_va) { + struct iovec iov; + + ret = iotlb_translate_va(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &iov, 1, VHOST_MAP_RO); + if (ret < 0) + return ret; - kaddr = kmap_atomic(iov.bv_page); - from = kaddr + iov.bv_offset; - *val = vringh16_to_cpu(vrh, READ_ONCE(*(__virtio16 *)from)); - kunmap_atomic(kaddr); + ret = __get_user(*val, (__virtio16 *)iov.iov_base); + if (ret) + return ret; + + *val = vringh16_to_cpu(vrh, *val); + } else { + struct bio_vec iov; + void *kaddr, *from; + + ret = iotlb_translate_pa(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &iov, 1, VHOST_MAP_RO); + if (ret < 0) + return ret; + + kaddr = kmap_atomic(iov.bv_page); + from = kaddr + iov.bv_offset; + *val = vringh16_to_cpu(vrh, READ_ONCE(*(__virtio16 *)from)); + kunmap_atomic(kaddr); + } return 0; } @@ -1233,20 +1360,36 @@ static inline int getu16_iotlb(const struct vringh *vrh, static inline int putu16_iotlb(const struct vringh *vrh, __virtio16 *p, u16 val) { - struct bio_vec iov; - void *kaddr, *to; int ret; /* Atomic write is needed for putu16 */ - ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL, - &iov, 1, VHOST_MAP_WO); - if (ret < 0) - return ret; + if (vrh->use_va) { + struct iovec iov; - kaddr = kmap_atomic(iov.bv_page); - to = kaddr + iov.bv_offset; - WRITE_ONCE(*(__virtio16 *)to, cpu_to_vringh16(vrh, val)); - kunmap_atomic(kaddr); + ret = iotlb_translate_va(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &iov, 1, VHOST_MAP_RO); + if (ret < 0) + return ret; + + val = cpu_to_vringh16(vrh, val); + + ret = __put_user(val, (__virtio16 *)iov.iov_base); + if (ret) + return ret; + } else { + struct bio_vec iov; + void *kaddr, *to; + + ret = iotlb_translate_pa(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL, + &iov, 1, VHOST_MAP_WO); + if (ret < 0) + return ret; + + kaddr = kmap_atomic(iov.bv_page); + to = kaddr + iov.bv_offset; + WRITE_ONCE(*(__virtio16 *)to, cpu_to_vringh16(vrh, val)); + kunmap_atomic(kaddr); + } return 0; } @@ -1308,6 +1451,7 @@ static inline int putused_iotlb(const struct vringh *vrh, * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. + * @use_va: true if IOTLB contains user VA * @desc: the userpace descriptor pointer. * @avail: the userpace avail pointer. * @used: the userpace used pointer. @@ -1315,11 +1459,13 @@ static inline int putused_iotlb(const struct vringh *vrh, * Returns an error if num is invalid. */ int vringh_init_iotlb(struct vringh *vrh, u64 features, - unsigned int num, bool weak_barriers, + unsigned int num, bool weak_barriers, bool use_va, struct vring_desc *desc, struct vring_avail *avail, struct vring_used *used) { + vrh->use_va = use_va; + return vringh_init_kern(vrh, features, num, weak_barriers, desc, avail, used); }

[RFC,3/6] vringh: support VA with iotlb

Checks

Commit Message

Patch