X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost.h;h=58aec2e0d81b2adb82573340729018b803b7546f;hb=1633d3c4c1290eb52f82d5144d4e19fa3d220fae;hp=68ca19769b5b40bee83a12e85220e57b3bdc4bf2;hpb=40ef286f236af0e7729089c16a9afba9b3f502c6;p=dpdk.git diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h index 68ca19769b..58aec2e0d8 100644 --- a/lib/librte_vhost/vhost.h +++ b/lib/librte_vhost/vhost.h @@ -1,34 +1,5 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2014 Intel Corporation */ #ifndef _VHOST_NET_CDEV_H_ @@ -39,15 +10,22 @@ #include #include #include +#include +#include +#include #include +#include +#include -#include "rte_virtio_net.h" +#include "rte_vhost.h" /* Used to indicate that the device is running on a data core */ #define VIRTIO_DEV_RUNNING 1 /* Used to indicate that the device is ready to operate */ #define VIRTIO_DEV_READY 2 +/* Used to indicate that the built-in vhost net device backend is enabled */ +#define VIRTIO_DEV_BUILTIN_VIRTIO_NET 4 /* Backend value set by guest. */ #define VIRTIO_DEV_STOPPED -1 @@ -77,6 +55,16 @@ struct zcopy_mbuf { }; TAILQ_HEAD(zcopy_mbuf_list, zcopy_mbuf); +/* + * Structure contains the info for each batched memory copy. + */ +struct batch_copy_elem { + void *dst; + void *src; + uint32_t len; + uint64_t log_addr; +}; + /** * Structure contains variables relevant to RX/TX virtqueues. */ @@ -88,16 +76,21 @@ struct vhost_virtqueue { uint16_t last_avail_idx; uint16_t last_used_idx; + /* Last used index we notify to front end. */ + uint16_t signalled_used; #define VIRTIO_INVALID_EVENTFD (-1) #define VIRTIO_UNINITIALIZED_EVENTFD (-2) /* Backend value to determine if device should started/stopped */ int backend; + int enabled; + int access_ok; + rte_spinlock_t access_lock; + /* Used to notify the guest (trigger interrupt) */ int callfd; /* Currently unused as polling mode is enabled */ int kickfd; - int enabled; /* Physical address of used ring, for logging */ uint64_t log_guest_addr; @@ -110,6 +103,17 @@ struct vhost_virtqueue { struct vring_used_elem *shadow_used_ring; uint16_t shadow_used_idx; + struct vhost_vring_addr ring_addrs; + + struct batch_copy_elem *batch_copy_elems; + uint16_t batch_copy_nb_elems; + + rte_rwlock_t iotlb_lock; + rte_rwlock_t iotlb_pending_lock; + struct rte_mempool *iotlb_pool; + TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list; + int iotlb_cache_nr; + TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list; } __rte_cache_aligned; /* Old kernels have no such macros defined */ @@ -128,6 +132,41 @@ struct vhost_virtqueue { #define VIRTIO_NET_F_MTU 3 #endif +#ifndef VIRTIO_F_ANY_LAYOUT + #define VIRTIO_F_ANY_LAYOUT 27 +#endif + +/* Declare IOMMU related bits for older kernels */ +#ifndef VIRTIO_F_IOMMU_PLATFORM + +#define VIRTIO_F_IOMMU_PLATFORM 33 + +struct vhost_iotlb_msg { + __u64 iova; + __u64 size; + __u64 uaddr; +#define VHOST_ACCESS_RO 0x1 +#define VHOST_ACCESS_WO 0x2 +#define VHOST_ACCESS_RW 0x3 + __u8 perm; +#define VHOST_IOTLB_MISS 1 +#define VHOST_IOTLB_UPDATE 2 +#define VHOST_IOTLB_INVALIDATE 3 +#define VHOST_IOTLB_ACCESS_FAIL 4 + __u8 type; +}; + +#define VHOST_IOTLB_MSG 0x1 + +struct vhost_msg { + int type; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; +#endif + /* * Define virtio 1.0 for older kernels */ @@ -139,6 +178,7 @@ struct vhost_virtqueue { /* Features supported by this builtin vhost-user net driver. */ #define VIRTIO_NET_SUPPORTED_FEATURES ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | \ + (1ULL << VIRTIO_F_ANY_LAYOUT) | \ (1ULL << VIRTIO_NET_F_CTRL_VQ) | \ (1ULL << VIRTIO_NET_F_CTRL_RX) | \ (1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE) | \ @@ -146,14 +186,21 @@ struct vhost_virtqueue { (1ULL << VIRTIO_F_VERSION_1) | \ (1ULL << VHOST_F_LOG_ALL) | \ (1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \ + (1ULL << VIRTIO_NET_F_GSO) | \ (1ULL << VIRTIO_NET_F_HOST_TSO4) | \ (1ULL << VIRTIO_NET_F_HOST_TSO6) | \ + (1ULL << VIRTIO_NET_F_HOST_UFO) | \ + (1ULL << VIRTIO_NET_F_HOST_ECN) | \ (1ULL << VIRTIO_NET_F_CSUM) | \ (1ULL << VIRTIO_NET_F_GUEST_CSUM) | \ (1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \ + (1ULL << VIRTIO_NET_F_GUEST_UFO) | \ + (1ULL << VIRTIO_NET_F_GUEST_ECN) | \ (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | \ - (1ULL << VIRTIO_NET_F_MTU)) + (1ULL << VIRTIO_RING_F_EVENT_IDX) | \ + (1ULL << VIRTIO_NET_F_MTU) | \ + (1ULL << VIRTIO_F_IOMMU_PLATFORM)) struct guest_page { @@ -176,7 +223,7 @@ struct virtio_net { uint16_t vhost_hlen; /* to tell if we need broadcast rarp packet */ rte_atomic16_t broadcast_rarp; - uint32_t virt_qp_nb; + uint32_t nr_vring; int dequeue_zero_copy; struct vhost_virtqueue *virtqueue[VHOST_MAX_QUEUE_PAIRS * 2]; #define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ) @@ -187,21 +234,70 @@ struct virtio_net { struct ether_addr mac; uint16_t mtu; - struct virtio_net_device_ops const *notify_ops; + struct vhost_device_ops const *notify_ops; uint32_t nr_guest_pages; uint32_t max_guest_pages; struct guest_page *guest_pages; + + int slave_req_fd; } __rte_cache_aligned; + +#define VHOST_LOG_PAGE 4096 + +/* + * Atomically set a bit in memory. + */ +static __rte_always_inline void +vhost_set_bit(unsigned int nr, volatile uint8_t *addr) +{ + __sync_fetch_and_or_8(addr, (1U << nr)); +} + +static __rte_always_inline void +vhost_log_page(uint8_t *log_base, uint64_t page) +{ + vhost_set_bit(page % 8, &log_base[page / 8]); +} + +static __rte_always_inline void +vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len) +{ + uint64_t page; + + if (likely(((dev->features & (1ULL << VHOST_F_LOG_ALL)) == 0) || + !dev->log_base || !len)) + return; + + if (unlikely(dev->log_size <= ((addr + len - 1) / VHOST_LOG_PAGE / 8))) + return; + + /* To make sure guest memory updates are committed before logging */ + rte_smp_wmb(); + + page = addr / VHOST_LOG_PAGE; + while (page * VHOST_LOG_PAGE < addr + len) { + vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page); + page += 1; + } +} + +static __rte_always_inline void +vhost_log_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq, + uint64_t offset, uint64_t len) +{ + vhost_log_write(dev, vq->log_guest_addr + offset, len); +} + /* Macros for printing using RTE_LOG */ #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1 #define RTE_LOGTYPE_VHOST_DATA RTE_LOGTYPE_USER1 #ifdef RTE_LIBRTE_VHOST_DEBUG #define VHOST_MAX_PRINT_BUFF 6072 -#define LOG_LEVEL RTE_LOG_DEBUG -#define LOG_DEBUG(log_type, fmt, args...) RTE_LOG(DEBUG, log_type, fmt, ##args) +#define VHOST_LOG_DEBUG(log_type, fmt, args...) \ + RTE_LOG(DEBUG, log_type, fmt, ##args) #define PRINT_PACKET(device, addr, size, header) do { \ char *pkt_addr = (char *)(addr); \ unsigned int index; \ @@ -217,11 +313,10 @@ struct virtio_net { } \ snprintf(packet + strnlen(packet, VHOST_MAX_PRINT_BUFF), VHOST_MAX_PRINT_BUFF - strnlen(packet, VHOST_MAX_PRINT_BUFF), "\n"); \ \ - LOG_DEBUG(VHOST_DATA, "%s", packet); \ + VHOST_LOG_DEBUG(VHOST_DATA, "%s", packet); \ } while (0) #else -#define LOG_LEVEL RTE_LOG_INFO -#define LOG_DEBUG(log_type, fmt, args...) do {} while (0) +#define VHOST_LOG_DEBUG(log_type, fmt, args...) do {} while (0) #define PRINT_PACKET(device, addr, size, header) do {} while (0) #endif @@ -229,27 +324,8 @@ extern uint64_t VHOST_FEATURES; #define MAX_VHOST_DEVICE 1024 extern struct virtio_net *vhost_devices[MAX_VHOST_DEVICE]; -/* Convert guest physical Address to host virtual address */ -static inline uint64_t __attribute__((always_inline)) -gpa_to_vva(struct virtio_net *dev, uint64_t gpa) -{ - struct rte_vhost_mem_region *reg; - uint32_t i; - - for (i = 0; i < dev->mem->nregions; i++) { - reg = &dev->mem->regions[i]; - if (gpa >= reg->guest_phys_addr && - gpa < reg->guest_phys_addr + reg->size) { - return gpa - reg->guest_phys_addr + - reg->host_user_addr; - } - } - - return 0; -} - /* Convert guest physical address to host physical address */ -static inline phys_addr_t __attribute__((always_inline)) +static __rte_always_inline rte_iova_t gpa_to_hpa(struct virtio_net *dev, uint64_t gpa, uint64_t size) { uint32_t i; @@ -268,19 +344,34 @@ gpa_to_hpa(struct virtio_net *dev, uint64_t gpa, uint64_t size) return 0; } -struct virtio_net *get_device(int vid); +static __rte_always_inline struct virtio_net * +get_device(int vid) +{ + struct virtio_net *dev = vhost_devices[vid]; + + if (unlikely(!dev)) { + RTE_LOG(ERR, VHOST_CONFIG, + "(%d) device not found.\n", vid); + } + + return dev; +} int vhost_new_device(void); void cleanup_device(struct virtio_net *dev, int destroy); void reset_device(struct virtio_net *dev); void vhost_destroy_device(int); -int alloc_vring_queue_pair(struct virtio_net *dev, uint32_t qp_idx); +void cleanup_vq(struct vhost_virtqueue *vq, int destroy); +void free_vq(struct vhost_virtqueue *vq); + +int alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx); void vhost_set_ifname(int, const char *if_name, unsigned int if_len); void vhost_enable_dequeue_zero_copy(int vid); +void vhost_set_builtin_virtio_net(int vid, bool enable); -struct virtio_net_device_ops const *vhost_driver_callback_get(const char *path); +struct vhost_device_ops const *vhost_driver_callback_get(const char *path); /* * Backend-specific cleanup. @@ -289,4 +380,62 @@ struct virtio_net_device_ops const *vhost_driver_callback_get(const char *path); */ void vhost_backend_cleanup(struct virtio_net *dev); +uint64_t __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq, + uint64_t iova, uint64_t size, uint8_t perm); +int vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq); +void vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq); + +static __rte_always_inline uint64_t +vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq, + uint64_t iova, uint64_t size, uint8_t perm) +{ + if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) + return rte_vhost_gpa_to_vva(dev->mem, iova); + + return __vhost_iova_to_vva(dev, vq, iova, size, perm); +} + +#define vhost_used_event(vr) \ + (*(volatile uint16_t*)&(vr)->avail->ring[(vr)->size]) + +/* + * The following is used with VIRTIO_RING_F_EVENT_IDX. + * Assuming a given event_idx value from the other size, if we have + * just incremented index from old to new_idx, should we trigger an + * event? + */ +static __rte_always_inline int +vhost_need_event(uint16_t event_idx, uint16_t new_idx, uint16_t old) +{ + return (uint16_t)(new_idx - event_idx - 1) < (uint16_t)(new_idx - old); +} + +static __rte_always_inline void +vhost_vring_call(struct virtio_net *dev, struct vhost_virtqueue *vq) +{ + /* Flush used->idx update before we read avail->flags. */ + rte_mb(); + + /* Don't kick guest if we don't reach index specified by guest. */ + if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX)) { + uint16_t old = vq->signalled_used; + uint16_t new = vq->last_used_idx; + + VHOST_LOG_DEBUG(VHOST_DATA, "%s: used_event_idx=%d, old=%d, new=%d\n", + __func__, + vhost_used_event(vq), + old, new); + if (vhost_need_event(vhost_used_event(vq), new, old) + && (vq->callfd >= 0)) { + vq->signalled_used = vq->last_used_idx; + eventfd_write(vq->callfd, (eventfd_t) 1); + } + } else { + /* Kick the guest if necessary. */ + if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT) + && (vq->callfd >= 0)) + eventfd_write(vq->callfd, (eventfd_t)1); + } +} + #endif /* _VHOST_NET_CDEV_H_ */