diff options
Diffstat (limited to 'drivers/vhost/vhost.h')
| -rw-r--r-- | drivers/vhost/vhost.h | 171 |
1 files changed, 130 insertions, 41 deletions
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index c8e96a095d3b..4fe99765c5c7 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -13,40 +13,65 @@ #include <linux/virtio_ring.h> #include <linux/atomic.h> #include <linux/vhost_iotlb.h> +#include <linux/irqbypass.h> +#include <linux/unroll.h> struct vhost_work; +struct vhost_task; typedef void (*vhost_work_fn_t)(struct vhost_work *work); #define VHOST_WORK_QUEUED 1 struct vhost_work { - struct llist_node node; - vhost_work_fn_t fn; - unsigned long flags; + struct llist_node node; + vhost_work_fn_t fn; + unsigned long flags; +}; + +struct vhost_worker; +struct vhost_dev; + +struct vhost_worker_ops { + int (*create)(struct vhost_worker *worker, struct vhost_dev *dev, + const char *name); + void (*stop)(struct vhost_worker *worker); + void (*wakeup)(struct vhost_worker *worker); +}; + +struct vhost_worker { + struct task_struct *kthread_task; + struct vhost_task *vtsk; + struct vhost_dev *dev; + /* Used to serialize device wide flushing with worker swapping. */ + struct mutex mutex; + struct llist_head work_list; + u64 kcov_handle; + u32 id; + int attachment_cnt; + bool killed; + const struct vhost_worker_ops *ops; }; /* Poll a file (eventfd or socket) */ /* Note: there's nothing vhost specific about this structure. */ struct vhost_poll { - poll_table table; - wait_queue_head_t *wqh; - wait_queue_entry_t wait; - struct vhost_work work; - __poll_t mask; - struct vhost_dev *dev; + poll_table table; + wait_queue_head_t *wqh; + wait_queue_entry_t wait; + struct vhost_work work; + __poll_t mask; + struct vhost_dev *dev; + struct vhost_virtqueue *vq; }; -void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn); -void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work); -bool vhost_has_work(struct vhost_dev *dev); - void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, - __poll_t mask, struct vhost_dev *dev); + __poll_t mask, struct vhost_dev *dev, + struct vhost_virtqueue *vq); int vhost_poll_start(struct vhost_poll *poll, struct file *file); void vhost_poll_stop(struct vhost_poll *poll); -void vhost_poll_flush(struct vhost_poll *poll); void vhost_poll_queue(struct vhost_poll *poll); -void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work); -long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp); + +void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn); +void vhost_dev_flush(struct vhost_dev *dev); struct vhost_log { u64 addr; @@ -60,9 +85,15 @@ enum vhost_uaddr_type { VHOST_NUM_ADDRS = 3, }; +struct vhost_vring_call { + struct eventfd_ctx *ctx; + struct irq_bypass_producer producer; +}; + /* The virtqueue structure describes a queue attached to a device. */ struct vhost_virtqueue { struct vhost_dev *dev; + struct vhost_worker __rcu *worker; /* The actual ring of buffers. */ struct mutex mutex; @@ -72,7 +103,7 @@ struct vhost_virtqueue { vring_used_t __user *used; const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS]; struct file *kick; - struct eventfd_ctx *call_ctx; + struct vhost_vring_call call_ctx; struct eventfd_ctx *error_ctx; struct eventfd_ctx *log_ctx; @@ -81,13 +112,19 @@ struct vhost_virtqueue { /* The routine to call when the Guest pings us, or timeout. */ vhost_work_fn_t handle_kick; - /* Last available index we saw. */ + /* Last available index we saw. + * Values are limited to 0x7fff, and the high bit is used as + * a wrap counter when using VIRTIO_F_RING_PACKED. */ u16 last_avail_idx; + /* Next avail ring head when VIRTIO_F_IN_ORDER is negoitated */ + u16 next_avail_head; /* Caches available index value from user. */ u16 avail_idx; - /* Last index we used. */ + /* Last index we used. + * Values are limited to 0x7fff, and the high bit is used as + * a wrap counter when using VIRTIO_F_RING_PACKED. */ u16 last_used_idx; /* Used flags */ @@ -107,15 +144,17 @@ struct vhost_virtqueue { struct iovec iotlb_iov[64]; struct iovec *indirect; struct vring_used_elem *heads; + u16 *nheads; /* Protected by virtqueue mutex. */ struct vhost_iotlb *umem; struct vhost_iotlb *iotlb; void *private_data; - u64 acked_features; + VIRTIO_DECLARE_FEATURES(acked_features); u64 acked_backend_features; /* Log write descriptors */ void __user *log_base; struct vhost_log *log; + struct iovec log_iov[64]; /* Ring endianness. Defaults to legacy native endianness. * Set to true when starting a modern virtio device. */ @@ -142,8 +181,6 @@ struct vhost_dev { struct vhost_virtqueue **vqs; int nvqs; struct eventfd_ctx *log_ctx; - struct llist_head work_list; - struct task_struct *worker; struct vhost_iotlb *umem; struct vhost_iotlb *iotlb; spinlock_t iotlb_lock; @@ -153,9 +190,19 @@ struct vhost_dev { int iov_limit; int weight; int byte_weight; - u64 kcov_handle; + struct xarray worker_xa; bool use_worker; - int (*msg_handler)(struct vhost_dev *dev, + /* + * If fork_owner is true we use vhost_tasks to create + * the worker so all settings/limits like cgroups, NPROC, + * scheduler, etc are inherited from the owner. If false, + * we use kthreads and only attach to the same cgroups + * as the owner for compat with older kernels. + * here we use true as default value. + * The default value is set by fork_from_owner_default + */ + bool fork_owner; + int (*msg_handler)(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg); }; @@ -163,7 +210,7 @@ bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len); void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs, int iov_limit, int weight, int byte_weight, bool use_worker, - int (*msg_handler)(struct vhost_dev *dev, + int (*msg_handler)(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg)); long vhost_dev_set_owner(struct vhost_dev *dev); bool vhost_dev_has_owner(struct vhost_dev *dev); @@ -174,23 +221,38 @@ void vhost_dev_cleanup(struct vhost_dev *); void vhost_dev_stop(struct vhost_dev *); long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp); long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp); +long vhost_worker_ioctl(struct vhost_dev *dev, unsigned int ioctl, + void __user *argp); bool vhost_vq_access_ok(struct vhost_virtqueue *vq); bool vhost_log_access_ok(struct vhost_dev *); +void vhost_clear_msg(struct vhost_dev *dev); int vhost_get_vq_desc(struct vhost_virtqueue *, - struct iovec iov[], unsigned int iov_count, + struct iovec iov[], unsigned int iov_size, unsigned int *out_num, unsigned int *in_num, struct vhost_log *log, unsigned int *log_num); -void vhost_discard_vq_desc(struct vhost_virtqueue *, int n); +int vhost_get_vq_desc_n(struct vhost_virtqueue *vq, + struct iovec iov[], unsigned int iov_size, + unsigned int *out_num, unsigned int *in_num, + struct vhost_log *log, unsigned int *log_num, + unsigned int *ndesc); + +void vhost_discard_vq_desc(struct vhost_virtqueue *, int nbuf, + unsigned int ndesc); + +bool vhost_vq_work_queue(struct vhost_virtqueue *vq, struct vhost_work *work); +bool vhost_vq_has_work(struct vhost_virtqueue *vq); +bool vhost_vq_is_setup(struct vhost_virtqueue *vq); int vhost_vq_init_access(struct vhost_virtqueue *); int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len); int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads, - unsigned count); + u16 *nheads, unsigned count); void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *, unsigned int id, int len); void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *, - struct vring_used_elem *heads, unsigned count); + struct vring_used_elem *heads, u16 *nheads, + unsigned count); void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *); void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *); bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *); @@ -207,13 +269,15 @@ void vhost_enqueue_msg(struct vhost_dev *dev, struct vhost_msg_node *node); struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev, struct list_head *head); +void vhost_set_backend_features(struct vhost_dev *dev, u64 features); + __poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev, poll_table *wait); ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to, int noblock); ssize_t vhost_chr_write_iter(struct vhost_dev *dev, struct iov_iter *from); -int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled); +int vhost_init_device_iotlb(struct vhost_dev *d); void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, struct vhost_iotlb_map *map); @@ -221,17 +285,42 @@ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, #define vq_err(vq, fmt, ...) do { \ pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \ if ((vq)->error_ctx) \ - eventfd_signal((vq)->error_ctx, 1);\ + eventfd_signal((vq)->error_ctx);\ } while (0) -enum { - VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | - (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | - (1ULL << VIRTIO_RING_F_EVENT_IDX) | - (1ULL << VHOST_F_LOG_ALL) | - (1ULL << VIRTIO_F_ANY_LAYOUT) | - (1ULL << VIRTIO_F_VERSION_1) -}; +#define VHOST_FEATURES \ + VIRTIO_F_NOTIFY_ON_EMPTY, \ + VIRTIO_RING_F_INDIRECT_DESC, \ + VIRTIO_RING_F_EVENT_IDX, \ + VHOST_F_LOG_ALL, \ + VIRTIO_F_ANY_LAYOUT, \ + VIRTIO_F_VERSION_1 + +static inline u64 vhost_features_u64(const int *features, int size, int idx) +{ + u64 res = 0; + + unrolled_count(VIRTIO_FEATURES_BITS) + for (int i = 0; i < size; ++i) { + int bit = features[i]; + + if (virtio_features_chk_bit(bit) && VIRTIO_U64(bit) == idx) + res |= VIRTIO_BIT(bit); + } + return res; +} + +#define VHOST_FEATURES_U64(features, idx) \ + vhost_features_u64(features, ARRAY_SIZE(features), idx) + +#define DEFINE_VHOST_FEATURES_ARRAY_ENTRY(idx, features) \ + [idx] = VHOST_FEATURES_U64(features, idx), + +#define DEFINE_VHOST_FEATURES_ARRAY(array, features) \ + u64 array[VIRTIO_FEATURES_U64S] = { \ + UNROLL(VIRTIO_FEATURES_U64S, \ + DEFINE_VHOST_FEATURES_ARRAY_ENTRY, features) \ + } /** * vhost_vq_set_backend - Set backend. @@ -262,7 +351,7 @@ static inline void *vhost_vq_get_backend(struct vhost_virtqueue *vq) static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) { - return vq->acked_features & (1ULL << bit); + return virtio_features_test_bit(vq->acked_features_array, bit); } static inline bool vhost_backend_has_feature(struct vhost_virtqueue *vq, int bit) |