diff options
Diffstat (limited to 'drivers/vhost')
| -rw-r--r-- | drivers/vhost/net.c | 12 | ||||
| -rw-r--r-- | drivers/vhost/scsi.c | 12 | ||||
| -rw-r--r-- | drivers/vhost/test.c | 27 | ||||
| -rw-r--r-- | drivers/vhost/vhost.c | 530 | ||||
| -rw-r--r-- | drivers/vhost/vhost.h | 42 | ||||
| -rw-r--r-- | drivers/vhost/vringh.c | 8 | ||||
| -rw-r--r-- | drivers/vhost/vsock.c | 186 |
7 files changed, 142 insertions, 675 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 1a2dd53caade..e158159671fa 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1751,14 +1751,6 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl, } } -#ifdef CONFIG_COMPAT -static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl, - unsigned long arg) -{ - return vhost_net_ioctl(f, ioctl, (unsigned long)compat_ptr(arg)); -} -#endif - static ssize_t vhost_net_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; @@ -1794,9 +1786,7 @@ static const struct file_operations vhost_net_fops = { .write_iter = vhost_net_chr_write_iter, .poll = vhost_net_chr_poll, .unlocked_ioctl = vhost_net_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = vhost_net_compat_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, .open = vhost_net_open, .llseek = noop_llseek, }; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index a9caf1bc3c3e..0b949a14bce3 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1727,21 +1727,11 @@ vhost_scsi_ioctl(struct file *f, } } -#ifdef CONFIG_COMPAT -static long vhost_scsi_compat_ioctl(struct file *f, unsigned int ioctl, - unsigned long arg) -{ - return vhost_scsi_ioctl(f, ioctl, (unsigned long)compat_ptr(arg)); -} -#endif - static const struct file_operations vhost_scsi_fops = { .owner = THIS_MODULE, .release = vhost_scsi_release, .unlocked_ioctl = vhost_scsi_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = vhost_scsi_compat_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, .open = vhost_scsi_open, .llseek = noop_llseek, }; diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 9e90e969af55..e37c92d4d7ad 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -22,6 +22,12 @@ * Using this limit prevents one virtqueue from starving others. */ #define VHOST_TEST_WEIGHT 0x80000 +/* Max number of packets transferred before requeueing the job. + * Using this limit prevents one virtqueue from starving others with + * pkts. + */ +#define VHOST_TEST_PKT_WEIGHT 256 + enum { VHOST_TEST_VQ = 0, VHOST_TEST_VQ_MAX = 1, @@ -80,10 +86,8 @@ static void handle_vq(struct vhost_test *n) } vhost_add_used_and_signal(&n->dev, vq, head, 0); total_len += len; - if (unlikely(total_len >= VHOST_TEST_WEIGHT)) { - vhost_poll_queue(&vq->poll); + if (unlikely(vhost_exceeds_weight(vq, 0, total_len))) break; - } } mutex_unlock(&vq->mutex); @@ -115,7 +119,8 @@ static int vhost_test_open(struct inode *inode, struct file *f) dev = &n->dev; vqs[VHOST_TEST_VQ] = &n->vqs[VHOST_TEST_VQ]; n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick; - vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX); + vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV, + VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT); f->private_data = n; @@ -156,6 +161,7 @@ static int vhost_test_release(struct inode *inode, struct file *f) vhost_test_stop(n, &private); vhost_test_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_cleanup(&n->dev); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ @@ -232,6 +238,7 @@ static long vhost_test_reset_owner(struct vhost_test *n) } vhost_test_stop(n, &priv); vhost_test_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); done: mutex_unlock(&n->dev.mutex); @@ -297,21 +304,11 @@ static long vhost_test_ioctl(struct file *f, unsigned int ioctl, } } -#ifdef CONFIG_COMPAT -static long vhost_test_compat_ioctl(struct file *f, unsigned int ioctl, - unsigned long arg) -{ - return vhost_test_ioctl(f, ioctl, (unsigned long)compat_ptr(arg)); -} -#endif - static const struct file_operations vhost_test_fops = { .owner = THIS_MODULE, .release = vhost_test_release, .unlocked_ioctl = vhost_test_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = vhost_test_compat_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, .open = vhost_test_open, .llseek = noop_llseek, }; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 0536f8526359..f44340b41494 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -30,6 +30,7 @@ #include <linux/sched/signal.h> #include <linux/interval_tree_generic.h> #include <linux/nospec.h> +#include <linux/kcov.h> #include "vhost.h" @@ -203,7 +204,6 @@ EXPORT_SYMBOL_GPL(vhost_poll_init); int vhost_poll_start(struct vhost_poll *poll, struct file *file) { __poll_t mask; - int ret = 0; if (poll->wqh) return 0; @@ -213,10 +213,10 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file) vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask)); if (mask & EPOLLERR) { vhost_poll_stop(poll); - ret = -EINVAL; + return -EINVAL; } - return ret; + return 0; } EXPORT_SYMBOL_GPL(vhost_poll_start); @@ -298,160 +298,6 @@ static void vhost_vq_meta_reset(struct vhost_dev *d) __vhost_vq_meta_reset(d->vqs[i]); } -#if VHOST_ARCH_CAN_ACCEL_UACCESS -static void vhost_map_unprefetch(struct vhost_map *map) -{ - kfree(map->pages); - map->pages = NULL; - map->npages = 0; - map->addr = NULL; -} - -static void vhost_uninit_vq_maps(struct vhost_virtqueue *vq) -{ - struct vhost_map *map[VHOST_NUM_ADDRS]; - int i; - - spin_lock(&vq->mmu_lock); - for (i = 0; i < VHOST_NUM_ADDRS; i++) { - map[i] = rcu_dereference_protected(vq->maps[i], - lockdep_is_held(&vq->mmu_lock)); - if (map[i]) - rcu_assign_pointer(vq->maps[i], NULL); - } - spin_unlock(&vq->mmu_lock); - - synchronize_rcu(); - - for (i = 0; i < VHOST_NUM_ADDRS; i++) - if (map[i]) - vhost_map_unprefetch(map[i]); - -} - -static void vhost_reset_vq_maps(struct vhost_virtqueue *vq) -{ - int i; - - vhost_uninit_vq_maps(vq); - for (i = 0; i < VHOST_NUM_ADDRS; i++) - vq->uaddrs[i].size = 0; -} - -static bool vhost_map_range_overlap(struct vhost_uaddr *uaddr, - unsigned long start, - unsigned long end) -{ - if (unlikely(!uaddr->size)) - return false; - - return !(end < uaddr->uaddr || start > uaddr->uaddr - 1 + uaddr->size); -} - -static void vhost_invalidate_vq_start(struct vhost_virtqueue *vq, - int index, - unsigned long start, - unsigned long end) -{ - struct vhost_uaddr *uaddr = &vq->uaddrs[index]; - struct vhost_map *map; - int i; - - if (!vhost_map_range_overlap(uaddr, start, end)) - return; - - spin_lock(&vq->mmu_lock); - ++vq->invalidate_count; - - map = rcu_dereference_protected(vq->maps[index], - lockdep_is_held(&vq->mmu_lock)); - if (map) { - if (uaddr->write) { - for (i = 0; i < map->npages; i++) - set_page_dirty(map->pages[i]); - } - rcu_assign_pointer(vq->maps[index], NULL); - } - spin_unlock(&vq->mmu_lock); - - if (map) { - synchronize_rcu(); - vhost_map_unprefetch(map); - } -} - -static void vhost_invalidate_vq_end(struct vhost_virtqueue *vq, - int index, - unsigned long start, - unsigned long end) -{ - if (!vhost_map_range_overlap(&vq->uaddrs[index], start, end)) - return; - - spin_lock(&vq->mmu_lock); - --vq->invalidate_count; - spin_unlock(&vq->mmu_lock); -} - -static int vhost_invalidate_range_start(struct mmu_notifier *mn, - const struct mmu_notifier_range *range) -{ - struct vhost_dev *dev = container_of(mn, struct vhost_dev, - mmu_notifier); - int i, j; - - if (!mmu_notifier_range_blockable(range)) - return -EAGAIN; - - for (i = 0; i < dev->nvqs; i++) { - struct vhost_virtqueue *vq = dev->vqs[i]; - - for (j = 0; j < VHOST_NUM_ADDRS; j++) - vhost_invalidate_vq_start(vq, j, - range->start, - range->end); - } - - return 0; -} - -static void vhost_invalidate_range_end(struct mmu_notifier *mn, - const struct mmu_notifier_range *range) -{ - struct vhost_dev *dev = container_of(mn, struct vhost_dev, - mmu_notifier); - int i, j; - - for (i = 0; i < dev->nvqs; i++) { - struct vhost_virtqueue *vq = dev->vqs[i]; - - for (j = 0; j < VHOST_NUM_ADDRS; j++) - vhost_invalidate_vq_end(vq, j, - range->start, - range->end); - } -} - -static const struct mmu_notifier_ops vhost_mmu_notifier_ops = { - .invalidate_range_start = vhost_invalidate_range_start, - .invalidate_range_end = vhost_invalidate_range_end, -}; - -static void vhost_init_maps(struct vhost_dev *dev) -{ - struct vhost_virtqueue *vq; - int i, j; - - dev->mmu_notifier.ops = &vhost_mmu_notifier_ops; - - for (i = 0; i < dev->nvqs; ++i) { - vq = dev->vqs[i]; - for (j = 0; j < VHOST_NUM_ADDRS; j++) - RCU_INIT_POINTER(vq->maps[j], NULL); - } -} -#endif - static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { @@ -480,11 +326,7 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->busyloop_timeout = 0; vq->umem = NULL; vq->iotlb = NULL; - vq->invalidate_count = 0; __vhost_vq_meta_reset(vq); -#if VHOST_ARCH_CAN_ACCEL_UACCESS - vhost_reset_vq_maps(vq); -#endif } static int vhost_worker(void *data) @@ -516,7 +358,9 @@ static int vhost_worker(void *data) llist_for_each_entry_safe(work, work_next, node, node) { clear_bit(VHOST_WORK_QUEUED, &work->flags); __set_current_state(TASK_RUNNING); + kcov_remote_start_common(dev->kcov_handle); work->fn(work); + kcov_remote_stop(); if (need_resched()) schedule(); } @@ -634,9 +478,7 @@ void vhost_dev_init(struct vhost_dev *dev, INIT_LIST_HEAD(&dev->read_list); INIT_LIST_HEAD(&dev->pending_list); spin_lock_init(&dev->iotlb_lock); -#if VHOST_ARCH_CAN_ACCEL_UACCESS - vhost_init_maps(dev); -#endif + for (i = 0; i < dev->nvqs; ++i) { vq = dev->vqs[i]; @@ -645,7 +487,6 @@ void vhost_dev_init(struct vhost_dev *dev, vq->heads = NULL; vq->dev = dev; mutex_init(&vq->mutex); - spin_lock_init(&vq->mmu_lock); vhost_vq_reset(dev, vq); if (vq->handle_kick) vhost_poll_init(&vq->poll, vq->handle_kick, @@ -708,6 +549,7 @@ long vhost_dev_set_owner(struct vhost_dev *dev) /* No owner, become one */ dev->mm = get_task_mm(current); + dev->kcov_handle = kcov_common_handle(); worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid); if (IS_ERR(worker)) { err = PTR_ERR(worker); @@ -725,18 +567,7 @@ long vhost_dev_set_owner(struct vhost_dev *dev) if (err) goto err_cgroup; -#if VHOST_ARCH_CAN_ACCEL_UACCESS - err = mmu_notifier_register(&dev->mmu_notifier, dev->mm); - if (err) - goto err_mmu_notifier; -#endif - return 0; - -#if VHOST_ARCH_CAN_ACCEL_UACCESS -err_mmu_notifier: - vhost_dev_free_iovecs(dev); -#endif err_cgroup: kthread_stop(worker); dev->worker = NULL; @@ -744,6 +575,7 @@ err_worker: if (dev->mm) mmput(dev->mm); dev->mm = NULL; + dev->kcov_handle = 0; err_mm: return err; } @@ -827,107 +659,6 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } -#if VHOST_ARCH_CAN_ACCEL_UACCESS -static void vhost_setup_uaddr(struct vhost_virtqueue *vq, - int index, unsigned long uaddr, - size_t size, bool write) -{ - struct vhost_uaddr *addr = &vq->uaddrs[index]; - - addr->uaddr = uaddr; - addr->size = size; - addr->write = write; -} - -static void vhost_setup_vq_uaddr(struct vhost_virtqueue *vq) -{ - vhost_setup_uaddr(vq, VHOST_ADDR_DESC, - (unsigned long)vq->desc, - vhost_get_desc_size(vq, vq->num), - false); - vhost_setup_uaddr(vq, VHOST_ADDR_AVAIL, - (unsigned long)vq->avail, - vhost_get_avail_size(vq, vq->num), - false); - vhost_setup_uaddr(vq, VHOST_ADDR_USED, - (unsigned long)vq->used, - vhost_get_used_size(vq, vq->num), - true); -} - -static int vhost_map_prefetch(struct vhost_virtqueue *vq, - int index) -{ - struct vhost_map *map; - struct vhost_uaddr *uaddr = &vq->uaddrs[index]; - struct page **pages; - int npages = DIV_ROUND_UP(uaddr->size, PAGE_SIZE); - int npinned; - void *vaddr, *v; - int err; - int i; - - spin_lock(&vq->mmu_lock); - - err = -EFAULT; - if (vq->invalidate_count) - goto err; - - err = -ENOMEM; - map = kmalloc(sizeof(*map), GFP_ATOMIC); - if (!map) - goto err; - - pages = kmalloc_array(npages, sizeof(struct page *), GFP_ATOMIC); - if (!pages) - goto err_pages; - - err = EFAULT; - npinned = __get_user_pages_fast(uaddr->uaddr, npages, - uaddr->write, pages); - if (npinned > 0) - release_pages(pages, npinned); - if (npinned != npages) - goto err_gup; - - for (i = 0; i < npinned; i++) - if (PageHighMem(pages[i])) - goto err_gup; - - vaddr = v = page_address(pages[0]); - - /* For simplicity, fallback to userspace address if VA is not - * contigious. - */ - for (i = 1; i < npinned; i++) { - v += PAGE_SIZE; - if (v != page_address(pages[i])) - goto err_gup; - } - - map->addr = vaddr + (uaddr->uaddr & (PAGE_SIZE - 1)); - map->npages = npages; - map->pages = pages; - - rcu_assign_pointer(vq->maps[index], map); - /* No need for a synchronize_rcu(). This function should be - * called by dev->worker so we are serialized with all - * readers. - */ - spin_unlock(&vq->mmu_lock); - - return 0; - -err_gup: - kfree(pages); -err_pages: - kfree(map); -err: - spin_unlock(&vq->mmu_lock); - return err; -} -#endif - void vhost_dev_cleanup(struct vhost_dev *dev) { int i; @@ -956,17 +687,10 @@ void vhost_dev_cleanup(struct vhost_dev *dev) if (dev->worker) { kthread_stop(dev->worker); dev->worker = NULL; + dev->kcov_handle = 0; } - if (dev->mm) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - mmu_notifier_unregister(&dev->mmu_notifier, dev->mm); -#endif + if (dev->mm) mmput(dev->mm); - } -#if VHOST_ARCH_CAN_ACCEL_UACCESS - for (i = 0; i < dev->nvqs; i++) - vhost_uninit_vq_maps(dev->vqs[i]); -#endif dev->mm = NULL; } EXPORT_SYMBOL_GPL(vhost_dev_cleanup); @@ -1195,26 +919,6 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, static inline int vhost_put_avail_event(struct vhost_virtqueue *vq) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_used *used; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_USED]); - if (likely(map)) { - used = map->addr; - *((__virtio16 *)&used->ring[vq->num]) = - cpu_to_vhost16(vq, vq->avail_idx); - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx), vhost_avail_event(vq)); } @@ -1223,27 +927,6 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq, struct vring_used_elem *head, int idx, int count) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_used *used; - size_t size; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_USED]); - if (likely(map)) { - used = map->addr; - size = count * sizeof(*head); - memcpy(used->ring + idx, head, size); - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_copy_to_user(vq, vq->used->ring + idx, head, count * sizeof(*head)); } @@ -1251,25 +934,6 @@ static inline int vhost_put_used(struct vhost_virtqueue *vq, static inline int vhost_put_used_flags(struct vhost_virtqueue *vq) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_used *used; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_USED]); - if (likely(map)) { - used = map->addr; - used->flags = cpu_to_vhost16(vq, vq->used_flags); - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags), &vq->used->flags); } @@ -1277,25 +941,6 @@ static inline int vhost_put_used_flags(struct vhost_virtqueue *vq) static inline int vhost_put_used_idx(struct vhost_virtqueue *vq) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_used *used; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_USED]); - if (likely(map)) { - used = map->addr; - used->idx = cpu_to_vhost16(vq, vq->last_used_idx); - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx), &vq->used->idx); } @@ -1341,50 +986,12 @@ static void vhost_dev_unlock_vqs(struct vhost_dev *d) static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq, __virtio16 *idx) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_avail *avail; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]); - if (likely(map)) { - avail = map->addr; - *idx = avail->idx; - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_get_avail(vq, *idx, &vq->avail->idx); } static inline int vhost_get_avail_head(struct vhost_virtqueue *vq, __virtio16 *head, int idx) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_avail *avail; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]); - if (likely(map)) { - avail = map->addr; - *head = avail->ring[idx & (vq->num - 1)]; - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_get_avail(vq, *head, &vq->avail->ring[idx & (vq->num - 1)]); } @@ -1392,98 +999,24 @@ static inline int vhost_get_avail_head(struct vhost_virtqueue *vq, static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq, __virtio16 *flags) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_avail *avail; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]); - if (likely(map)) { - avail = map->addr; - *flags = avail->flags; - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_get_avail(vq, *flags, &vq->avail->flags); } static inline int vhost_get_used_event(struct vhost_virtqueue *vq, __virtio16 *event) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_avail *avail; - - if (!vq->iotlb) { - rcu_read_lock(); - map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]); - if (likely(map)) { - avail = map->addr; - *event = (__virtio16)avail->ring[vq->num]; - rcu_read_unlock(); - return 0; - } - rcu_read_unlock(); - } -#endif - return vhost_get_avail(vq, *event, vhost_used_event(vq)); } static inline int vhost_get_used_idx(struct vhost_virtqueue *vq, __virtio16 *idx) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_used *used; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_USED]); - if (likely(map)) { - used = map->addr; - *idx = used->idx; - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_get_used(vq, *idx, &vq->used->idx); } static inline int vhost_get_desc(struct vhost_virtqueue *vq, struct vring_desc *desc, int idx) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - struct vhost_map *map; - struct vring_desc *d; - - if (!vq->iotlb) { - rcu_read_lock(); - - map = rcu_dereference(vq->maps[VHOST_ADDR_DESC]); - if (likely(map)) { - d = map->addr; - *desc = *(d + idx); - rcu_read_unlock(); - return 0; - } - - rcu_read_unlock(); - } -#endif - return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc)); } @@ -1824,32 +1357,12 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq, return true; } -#if VHOST_ARCH_CAN_ACCEL_UACCESS -static void vhost_vq_map_prefetch(struct vhost_virtqueue *vq) -{ - struct vhost_map __rcu *map; - int i; - - for (i = 0; i < VHOST_NUM_ADDRS; i++) { - rcu_read_lock(); - map = rcu_dereference(vq->maps[i]); - rcu_read_unlock(); - if (unlikely(!map)) - vhost_map_prefetch(vq, i); - } -} -#endif - int vq_meta_prefetch(struct vhost_virtqueue *vq) { unsigned int num = vq->num; - if (!vq->iotlb) { -#if VHOST_ARCH_CAN_ACCEL_UACCESS - vhost_vq_map_prefetch(vq); -#endif + if (!vq->iotlb) return 1; - } return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc, vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) && @@ -2060,16 +1573,6 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d, mutex_lock(&vq->mutex); -#if VHOST_ARCH_CAN_ACCEL_UACCESS - /* Unregister MMU notifer to allow invalidation callback - * can access vq->uaddrs[] without holding a lock. - */ - if (d->mm) - mmu_notifier_unregister(&d->mmu_notifier, d->mm); - - vhost_uninit_vq_maps(vq); -#endif - switch (ioctl) { case VHOST_SET_VRING_NUM: r = vhost_vring_set_num(d, vq, argp); @@ -2081,13 +1584,6 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d, BUG(); } -#if VHOST_ARCH_CAN_ACCEL_UACCESS - vhost_setup_vq_uaddr(vq); - - if (d->mm) - mmu_notifier_register(&d->mmu_notifier, d->mm); -#endif - mutex_unlock(&vq->mutex); return r; @@ -2688,7 +2184,7 @@ static int get_indirect(struct vhost_virtqueue *vq, /* If this is an input descriptor, increment that count. */ if (access == VHOST_ACCESS_WO) { *in_num += ret; - if (unlikely(log)) { + if (unlikely(log && ret)) { log[*log_num].addr = vhost64_to_cpu(vq, desc.addr); log[*log_num].len = vhost32_to_cpu(vq, desc.len); ++*log_num; @@ -2829,7 +2325,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, /* If this is an input descriptor, * increment that count. */ *in_num += ret; - if (unlikely(log)) { + if (unlikely(log && ret)) { log[*log_num].addr = vhost64_to_cpu(vq, desc.addr); log[*log_num].len = vhost32_to_cpu(vq, desc.len); ++*log_num; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 42a8c2a13ab1..a123fd70847e 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -12,9 +12,6 @@ #include <linux/virtio_config.h> #include <linux/virtio_ring.h> #include <linux/atomic.h> -#include <linux/pagemap.h> -#include <linux/mmu_notifier.h> -#include <asm/cacheflush.h> struct vhost_work; typedef void (*vhost_work_fn_t)(struct vhost_work *work); @@ -83,24 +80,6 @@ enum vhost_uaddr_type { VHOST_NUM_ADDRS = 3, }; -struct vhost_map { - int npages; - void *addr; - struct page **pages; -}; - -struct vhost_uaddr { - unsigned long uaddr; - size_t size; - bool write; -}; - -#if defined(CONFIG_MMU_NOTIFIER) && ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0 -#define VHOST_ARCH_CAN_ACCEL_UACCESS 0 -#else -#define VHOST_ARCH_CAN_ACCEL_UACCESS 0 -#endif - /* The virtqueue structure describes a queue attached to a device. */ struct vhost_virtqueue { struct vhost_dev *dev; @@ -111,22 +90,7 @@ struct vhost_virtqueue { struct vring_desc __user *desc; struct vring_avail __user *avail; struct vring_used __user *used; - -#if VHOST_ARCH_CAN_ACCEL_UACCESS - /* Read by memory accessors, modified by meta data - * prefetching, MMU notifier and vring ioctl(). - * Synchonrized through mmu_lock (writers) and RCU (writers - * and readers). - */ - struct vhost_map __rcu *maps[VHOST_NUM_ADDRS]; - /* Read by MMU notifier, modified by vring ioctl(), - * synchronized through MMU notifier - * registering/unregistering. - */ - struct vhost_uaddr uaddrs[VHOST_NUM_ADDRS]; -#endif const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS]; - struct file *kick; struct eventfd_ctx *call_ctx; struct eventfd_ctx *error_ctx; @@ -181,8 +145,6 @@ struct vhost_virtqueue { bool user_be; #endif u32 busyloop_timeout; - spinlock_t mmu_lock; - int invalidate_count; }; struct vhost_msg_node { @@ -196,9 +158,6 @@ struct vhost_msg_node { struct vhost_dev { struct mm_struct *mm; -#ifdef CONFIG_MMU_NOTIFIER - struct mmu_notifier mmu_notifier; -#endif struct mutex mutex; struct vhost_virtqueue **vqs; int nvqs; @@ -214,6 +173,7 @@ struct vhost_dev { int iov_limit; int weight; int byte_weight; + u64 kcov_handle; }; bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len); diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 08ad0d1f0476..a0a2d74967ef 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -852,6 +852,12 @@ static inline int xfer_kern(void *src, void *dst, size_t len) return 0; } +static inline int kern_xfer(void *dst, void *src, size_t len) +{ + memcpy(dst, src, len); + return 0; +} + /** * vringh_init_kern - initialize a vringh for a kernelspace vring. * @vrh: the vringh to initialize. @@ -958,7 +964,7 @@ EXPORT_SYMBOL(vringh_iov_pull_kern); ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov, const void *src, size_t len) { - return vringh_iov_xfer(wiov, (void *)src, len, xfer_kern); + return vringh_iov_xfer(wiov, (void *)src, len, kern_xfer); } EXPORT_SYMBOL(vringh_iov_push_kern); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 6a50e1d0529c..c2d7d57e98cf 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -102,7 +102,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, struct iov_iter iov_iter; unsigned out, in; size_t nbytes; - size_t len; + size_t iov_len, payload_len; int head; spin_lock_bh(&vsock->send_pkt_list_lock); @@ -147,8 +147,24 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - len = iov_length(&vq->iov[out], in); - iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len); + iov_len = iov_length(&vq->iov[out], in); + if (iov_len < sizeof(pkt->hdr)) { + virtio_transport_free_pkt(pkt); + vq_err(vq, "Buffer len [%zu] too small\n", iov_len); + break; + } + + iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len); + payload_len = pkt->len - pkt->off; + + /* If the packet is greater than the space available in the + * buffer, we split it using multiple buffers. + */ + if (payload_len > iov_len - sizeof(pkt->hdr)) + payload_len = iov_len - sizeof(pkt->hdr); + + /* Set the correct length in the header */ + pkt->hdr.len = cpu_to_le32(payload_len); nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter); if (nbytes != sizeof(pkt->hdr)) { @@ -157,33 +173,47 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter); - if (nbytes != pkt->len) { + nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len, + &iov_iter); + if (nbytes != payload_len) { virtio_transport_free_pkt(pkt); vq_err(vq, "Faulted on copying pkt buf\n"); break; } - vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len); + vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); added = true; - if (pkt->reply) { - int val; - - val = atomic_dec_return(&vsock->queued_replies); - - /* Do we have resources to resume tx processing? */ - if (val + 1 == tx_vq->num) - restart_tx = true; - } - /* Deliver to monitoring devices all correctly transmitted * packets. */ virtio_transport_deliver_tap_pkt(pkt); - total_len += pkt->len; - virtio_transport_free_pkt(pkt); + pkt->off += payload_len; + total_len += payload_len; + + /* If we didn't send all the payload we can requeue the packet + * to send it with the next available buffer. + */ + if (pkt->off < pkt->len) { + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + } else { + if (pkt->reply) { + int val; + + val = atomic_dec_return(&vsock->queued_replies); + + /* Do we have resources to resume tx + * processing? + */ + if (val + 1 == tx_vq->num) + restart_tx = true; + } + + virtio_transport_free_pkt(pkt); + } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) vhost_signal(&vsock->dev, vq); @@ -329,6 +359,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } + pkt->buf_len = pkt->len; + nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter); if (nbytes != pkt->len) { vq_err(vq, "Expected %u byte payload, got %zu bytes\n", @@ -352,6 +384,49 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) return val < vq->num; } +static struct virtio_transport vhost_transport = { + .transport = { + .module = THIS_MODULE, + + .get_local_cid = vhost_transport_get_local_cid, + + .init = virtio_transport_do_socket_init, + .destruct = virtio_transport_destruct, + .release = virtio_transport_release, + .connect = virtio_transport_connect, + .shutdown = virtio_transport_shutdown, + .cancel_pkt = vhost_transport_cancel_pkt, + + .dgram_enqueue = virtio_transport_dgram_enqueue, + .dgram_dequeue = virtio_transport_dgram_dequeue, + .dgram_bind = virtio_transport_dgram_bind, + .dgram_allow = virtio_transport_dgram_allow, + + .stream_enqueue = virtio_transport_stream_enqueue, + .stream_dequeue = virtio_transport_stream_dequeue, + .stream_has_data = virtio_transport_stream_has_data, + .stream_has_space = virtio_transport_stream_has_space, + .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, + .stream_is_active = virtio_transport_stream_is_active, + .stream_allow = virtio_transport_stream_allow, + + .notify_poll_in = virtio_transport_notify_poll_in, + .notify_poll_out = virtio_transport_notify_poll_out, + .notify_recv_init = virtio_transport_notify_recv_init, + .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, + .notify_send_init = virtio_transport_notify_send_init, + .notify_send_pre_block = virtio_transport_notify_send_pre_block, + .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + .notify_buffer_size = virtio_transport_notify_buffer_size, + + }, + + .send_pkt = vhost_transport_send_pkt, +}; + static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -405,8 +480,10 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) virtio_transport_deliver_tap_pkt(pkt); /* Only accept correctly addressed packets */ - if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid) - virtio_transport_recv_pkt(pkt); + if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid && + le64_to_cpu(pkt->hdr.dst_cid) == + vhost_transport_get_local_cid()) + virtio_transport_recv_pkt(&vhost_transport, pkt); else virtio_transport_free_pkt(pkt); @@ -643,6 +720,12 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) if (guest_cid > U32_MAX) return -EINVAL; + /* Refuse if CID is assigned to the guest->host transport (i.e. nested + * VM), to make the loopback work. + */ + if (vsock_find_cid(guest_cid)) + return -EADDRINUSE; + /* Refuse if CID is already in use */ mutex_lock(&vhost_vsock_mutex); other = vhost_vsock_get(guest_cid); @@ -729,23 +812,13 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl, } } -#ifdef CONFIG_COMPAT -static long vhost_vsock_dev_compat_ioctl(struct file *f, unsigned int ioctl, - unsigned long arg) -{ - return vhost_vsock_dev_ioctl(f, ioctl, (unsigned long)compat_ptr(arg)); -} -#endif - static const struct file_operations vhost_vsock_fops = { .owner = THIS_MODULE, .open = vhost_vsock_dev_open, .release = vhost_vsock_dev_release, .llseek = noop_llseek, .unlocked_ioctl = vhost_vsock_dev_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = vhost_vsock_dev_compat_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, }; static struct miscdevice vhost_vsock_misc = { @@ -754,57 +827,12 @@ static struct miscdevice vhost_vsock_misc = { .fops = &vhost_vsock_fops, }; -static struct virtio_transport vhost_transport = { - .transport = { - .get_local_cid = vhost_transport_get_local_cid, - - .init = virtio_transport_do_socket_init, - .destruct = virtio_transport_destruct, - .release = virtio_transport_release, - .connect = virtio_transport_connect, - .shutdown = virtio_transport_shutdown, - .cancel_pkt = vhost_transport_cancel_pkt, - - .dgram_enqueue = virtio_transport_dgram_enqueue, - .dgram_dequeue = virtio_transport_dgram_dequeue, - .dgram_bind = virtio_transport_dgram_bind, - .dgram_allow = virtio_transport_dgram_allow, - - .stream_enqueue = virtio_transport_stream_enqueue, - .stream_dequeue = virtio_transport_stream_dequeue, - .stream_has_data = virtio_transport_stream_has_data, - .stream_has_space = virtio_transport_stream_has_space, - .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, - .stream_is_active = virtio_transport_stream_is_active, - .stream_allow = virtio_transport_stream_allow, - - .notify_poll_in = virtio_transport_notify_poll_in, - .notify_poll_out = virtio_transport_notify_poll_out, - .notify_recv_init = virtio_transport_notify_recv_init, - .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, - .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, - .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, - .notify_send_init = virtio_transport_notify_send_init, - .notify_send_pre_block = virtio_transport_notify_send_pre_block, - .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, - .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, - - .set_buffer_size = virtio_transport_set_buffer_size, - .set_min_buffer_size = virtio_transport_set_min_buffer_size, - .set_max_buffer_size = virtio_transport_set_max_buffer_size, - .get_buffer_size = virtio_transport_get_buffer_size, - .get_min_buffer_size = virtio_transport_get_min_buffer_size, - .get_max_buffer_size = virtio_transport_get_max_buffer_size, - }, - - .send_pkt = vhost_transport_send_pkt, -}; - static int __init vhost_vsock_init(void) { int ret; - ret = vsock_core_init(&vhost_transport.transport); + ret = vsock_core_register(&vhost_transport.transport, + VSOCK_TRANSPORT_F_H2G); if (ret < 0) return ret; return misc_register(&vhost_vsock_misc); @@ -813,7 +841,7 @@ static int __init vhost_vsock_init(void) static void __exit vhost_vsock_exit(void) { misc_deregister(&vhost_vsock_misc); - vsock_core_exit(); + vsock_core_unregister(&vhost_transport.transport); }; module_init(vhost_vsock_init); |
