X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost.h;h=d49c3b8a98cacb4ef3436a6374fed4e6cb3edfec;hb=6d13ea8e8e49ab957deae2bba5ecf4a4bfe747d1;hp=68ca19769b5b40bee83a12e85220e57b3bdc4bf2;hpb=40ef286f236af0e7729089c16a9afba9b3f502c6;p=dpdk.git diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h index 68ca19769b..d49c3b8a98 100644 --- a/lib/librte_vhost/vhost.h +++ b/lib/librte_vhost/vhost.h @@ -1,64 +1,50 @@ -/*- - * 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) 2010-2018 Intel Corporation */ #ifndef _VHOST_NET_CDEV_H_ #define _VHOST_NET_CDEV_H_ #include #include +#include #include #include #include #include +#include +#include +#include #include +#include +#include +#include -#include "rte_virtio_net.h" +#include "rte_vhost.h" +#include "rte_vdpa.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 +/* Used to indicate that the device has its own data path and configured */ +#define VIRTIO_DEV_VDPA_CONFIGURED 8 /* Backend value set by guest. */ #define VIRTIO_DEV_STOPPED -1 #define BUF_VECTOR_MAX 256 +#define VHOST_LOG_CACHE_NR 32 + /** * Structure contains buffer address, length and descriptor index * from vring to do scatter RX. */ struct buf_vector { + uint64_t buf_iova; uint64_t buf_addr; uint32_t buf_len; uint32_t desc_idx; @@ -71,33 +57,73 @@ struct buf_vector { struct zcopy_mbuf { struct rte_mbuf *mbuf; uint32_t desc_idx; + uint16_t desc_count; uint16_t in_use; TAILQ_ENTRY(zcopy_mbuf) next; }; 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 that contains the info for batched dirty logging. + */ +struct log_cache_entry { + uint32_t offset; + unsigned long val; +}; + +struct vring_used_elem_packed { + uint16_t id; + uint32_t len; + uint32_t count; +}; + /** * Structure contains variables relevant to RX/TX virtqueues. */ struct vhost_virtqueue { - struct vring_desc *desc; - struct vring_avail *avail; - struct vring_used *used; + union { + struct vring_desc *desc; + struct vring_packed_desc *desc_packed; + }; + union { + struct vring_avail *avail; + struct vring_packed_desc_event *driver_event; + }; + union { + struct vring_used *used; + struct vring_packed_desc_event *device_event; + }; uint32_t size; uint16_t last_avail_idx; uint16_t last_used_idx; + /* Last used index we notify to front end. */ + uint16_t signalled_used; + bool signalled_used_valid; #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; @@ -108,8 +134,27 @@ struct vhost_virtqueue { struct zcopy_mbuf *zmbufs; struct zcopy_mbuf_list zmbuf_list; - struct vring_used_elem *shadow_used_ring; + union { + struct vring_used_elem *shadow_used_split; + struct vring_used_elem_packed *shadow_used_packed; + }; uint16_t shadow_used_idx; + struct vhost_vring_addr ring_addrs; + + struct batch_copy_elem *batch_copy_elems; + uint16_t batch_copy_nb_elems; + bool used_wrap_counter; + bool avail_wrap_counter; + + struct log_cache_entry log_cache[VHOST_LOG_CACHE_NR]; + uint16_t log_cache_nb_elem; + + 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 +173,41 @@ 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 */ @@ -135,10 +215,45 @@ struct vhost_virtqueue { #define VIRTIO_F_VERSION_1 32 #endif -#define VHOST_USER_F_PROTOCOL_FEATURES 30 +/* Declare packed ring related bits for older kernels */ +#ifndef VIRTIO_F_RING_PACKED + +#define VIRTIO_F_RING_PACKED 34 + +struct vring_packed_desc { + uint64_t addr; + uint32_t len; + uint16_t id; + uint16_t flags; +}; + +struct vring_packed_desc_event { + uint16_t off_wrap; + uint16_t flags; +}; +#endif + +/* + * Declare below packed ring defines unconditionally + * as Kernel header might use different names. + */ +#define VRING_DESC_F_AVAIL (1ULL << 7) +#define VRING_DESC_F_USED (1ULL << 15) + +#define VRING_EVENT_F_ENABLE 0x0 +#define VRING_EVENT_F_DISABLE 0x1 +#define VRING_EVENT_F_DESC 0x2 + +/* + * Available and used descs are in same order + */ +#ifndef VIRTIO_F_IN_ORDER +#define VIRTIO_F_IN_ORDER 35 +#endif /* 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 +261,23 @@ 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_IN_ORDER) | \ + (1ULL << VIRTIO_F_IOMMU_PLATFORM) | \ + (1ULL << VIRTIO_F_RING_PACKED)) struct guest_page { @@ -176,7 +300,7 @@ 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) @@ -184,24 +308,204 @@ struct virtio_net { uint64_t log_size; uint64_t log_base; uint64_t log_addr; - struct ether_addr mac; + struct rte_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_spinlock_t slave_req_lock; + + int postcopy_ufd; + int postcopy_listening; + + /* + * Device id to identify a specific backend device. + * It's set to -1 for the default software implementation. + */ + int vdpa_dev_id; + + /* context data for the external message handlers */ + void *extern_data; + /* pre and post vhost user message handlers for the device */ + struct rte_vhost_user_extern_ops extern_ops; } __rte_cache_aligned; +static __rte_always_inline bool +vq_is_packed(struct virtio_net *dev) +{ + return dev->features & (1ull << VIRTIO_F_RING_PACKED); +} + +static inline bool +desc_is_avail(struct vring_packed_desc *desc, bool wrap_counter) +{ + uint16_t flags = *((volatile uint16_t *) &desc->flags); + + return wrap_counter == !!(flags & VRING_DESC_F_AVAIL) && + wrap_counter != !!(flags & VRING_DESC_F_USED); +} + +#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) +{ +#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION < 70100) + /* + * __sync_ built-ins are deprecated, but __atomic_ ones + * are sub-optimized in older GCC versions. + */ + __sync_fetch_and_or_1(addr, (1U << nr)); +#else + __atomic_fetch_or(addr, (1U << nr), __ATOMIC_RELAXED); +#endif +} + +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_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq) +{ + unsigned long *log_base; + int i; + + if (likely(((dev->features & (1ULL << VHOST_F_LOG_ALL)) == 0) || + !dev->log_base)) + return; + + rte_smp_wmb(); + + log_base = (unsigned long *)(uintptr_t)dev->log_base; + + for (i = 0; i < vq->log_cache_nb_elem; i++) { + struct log_cache_entry *elem = vq->log_cache + i; + +#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION < 70100) + /* + * '__sync' builtins are deprecated, but '__atomic' ones + * are sub-optimized in older GCC versions. + */ + __sync_fetch_and_or(log_base + elem->offset, elem->val); +#else + __atomic_fetch_or(log_base + elem->offset, elem->val, + __ATOMIC_RELAXED); +#endif + } + + rte_smp_wmb(); + + vq->log_cache_nb_elem = 0; +} + +static __rte_always_inline void +vhost_log_cache_page(struct virtio_net *dev, struct vhost_virtqueue *vq, + uint64_t page) +{ + uint32_t bit_nr = page % (sizeof(unsigned long) << 3); + uint32_t offset = page / (sizeof(unsigned long) << 3); + int i; + + for (i = 0; i < vq->log_cache_nb_elem; i++) { + struct log_cache_entry *elem = vq->log_cache + i; + + if (elem->offset == offset) { + elem->val |= (1UL << bit_nr); + return; + } + } + + if (unlikely(i >= VHOST_LOG_CACHE_NR)) { + /* + * No more room for a new log cache entry, + * so write the dirty log map directly. + */ + rte_smp_wmb(); + vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page); + + return; + } + + vq->log_cache[i].offset = offset; + vq->log_cache[i].val = (1UL << bit_nr); + vq->log_cache_nb_elem++; +} + +static __rte_always_inline void +vhost_log_cache_write(struct virtio_net *dev, struct vhost_virtqueue *vq, + 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; + + page = addr / VHOST_LOG_PAGE; + while (page * VHOST_LOG_PAGE < addr + len) { + vhost_log_cache_page(dev, vq, page); + page += 1; + } +} + +static __rte_always_inline void +vhost_log_cache_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq, + uint64_t offset, uint64_t len) +{ + vhost_log_cache_write(dev, vq, vq->log_guest_addr + offset, len); +} + +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 +521,10 @@ 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 +532,8 @@ 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 +552,37 @@ 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); +void vhost_destroy_device_notify(struct virtio_net *dev); + +void cleanup_vq(struct vhost_virtqueue *vq, int destroy); +void free_vq(struct virtio_net *dev, struct vhost_virtqueue *vq); -int alloc_vring_queue_pair(struct virtio_net *dev, uint32_t qp_idx); +int alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx); + +void vhost_attach_vdpa_device(int vid, int did); 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 +591,192 @@ 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 *len, 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 *len, uint8_t perm) +{ + if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) + return rte_vhost_va_from_guest_pa(dev->mem, iova, len); + + return __vhost_iova_to_vva(dev, vq, iova, len, perm); +} + +#define vhost_avail_event(vr) \ + (*(volatile uint16_t*)&(vr)->used->ring[(vr)->size]) +#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_split(struct virtio_net *dev, struct vhost_virtqueue *vq) +{ + /* Flush used->idx update before we read avail->flags. */ + rte_smp_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; + bool signalled_used_valid = vq->signalled_used_valid; + + vq->signalled_used = new; + vq->signalled_used_valid = true; + + 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)) || + unlikely(!signalled_used_valid)) + 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); + } +} + +static __rte_always_inline void +vhost_vring_call_packed(struct virtio_net *dev, struct vhost_virtqueue *vq) +{ + uint16_t old, new, off, off_wrap; + bool signalled_used_valid, kick = false; + + /* Flush used desc update. */ + rte_smp_mb(); + + if (!(dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))) { + if (vq->driver_event->flags != + VRING_EVENT_F_DISABLE) + kick = true; + goto kick; + } + + old = vq->signalled_used; + new = vq->last_used_idx; + vq->signalled_used = new; + signalled_used_valid = vq->signalled_used_valid; + vq->signalled_used_valid = true; + + if (vq->driver_event->flags != VRING_EVENT_F_DESC) { + if (vq->driver_event->flags != VRING_EVENT_F_DISABLE) + kick = true; + goto kick; + } + + if (unlikely(!signalled_used_valid)) { + kick = true; + goto kick; + } + + rte_smp_rmb(); + + off_wrap = vq->driver_event->off_wrap; + off = off_wrap & ~(1 << 15); + + if (new <= old) + old -= vq->size; + + if (vq->used_wrap_counter != off_wrap >> 15) + off -= vq->size; + + if (vhost_need_event(off, new, old)) + kick = true; +kick: + if (kick) + eventfd_write(vq->callfd, (eventfd_t)1); +} + +static __rte_always_inline void * +alloc_copy_ind_table(struct virtio_net *dev, struct vhost_virtqueue *vq, + uint64_t desc_addr, uint64_t desc_len) +{ + void *idesc; + uint64_t src, dst; + uint64_t len, remain = desc_len; + + idesc = rte_malloc(__func__, desc_len, 0); + if (unlikely(!idesc)) + return 0; + + dst = (uint64_t)(uintptr_t)idesc; + + while (remain) { + len = remain; + src = vhost_iova_to_vva(dev, vq, desc_addr, &len, + VHOST_ACCESS_RO); + if (unlikely(!src || !len)) { + rte_free(idesc); + return 0; + } + + rte_memcpy((void *)(uintptr_t)dst, (void *)(uintptr_t)src, len); + + remain -= len; + dst += len; + desc_addr += len; + } + + return idesc; +} + +static __rte_always_inline void +free_ind_table(void *idesc) +{ + rte_free(idesc); +} + +static __rte_always_inline void +restore_mbuf(struct rte_mbuf *m) +{ + uint32_t mbuf_size, priv_size; + + while (m) { + priv_size = rte_pktmbuf_priv_size(m->pool); + mbuf_size = sizeof(struct rte_mbuf) + priv_size; + /* start of buffer is after mbuf structure and priv data */ + + m->buf_addr = (char *)m + mbuf_size; + m->buf_iova = rte_mempool_virt2iova(m) + mbuf_size; + m = m->next; + } +} + +static __rte_always_inline bool +mbuf_is_consumed(struct rte_mbuf *m) +{ + while (m) { + if (rte_mbuf_refcnt_read(m) > 1) + return false; + m = m->next; + } + + return true; +} + +static __rte_always_inline void +put_zmbuf(struct zcopy_mbuf *zmbuf) +{ + zmbuf->in_use = 0; +} + #endif /* _VHOST_NET_CDEV_H_ */