X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvhost.h;h=0f294f39596ff9f7f29e67ed0f5500da3ed02035;hb=8e3cfa66e71557dcfde9f5cc16d9c79791abfee0;hp=c2dfc3ca6d832bc63c8045323ddbb0950761fe30;hpb=a277c715987647ecd4ec80d18c5cc95c28d9dfd3;p=dpdk.git diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h index c2dfc3ca6d..0f294f3959 100644 --- a/lib/librte_vhost/vhost.h +++ b/lib/librte_vhost/vhost.h @@ -36,15 +36,22 @@ #include #include #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 /* Backend value set by guest. */ #define VIRTIO_DEV_STOPPED -1 @@ -61,6 +68,19 @@ struct buf_vector { uint32_t desc_idx; }; +/* + * A structure to hold some fields needed in zero copy code path, + * mainly for associating an mbuf with the right desc_idx. + */ +struct zcopy_mbuf { + struct rte_mbuf *mbuf; + uint32_t desc_idx; + uint16_t in_use; + + TAILQ_ENTRY(zcopy_mbuf) next; +}; +TAILQ_HEAD(zcopy_mbuf_list, zcopy_mbuf); + /** * Structure contains variables relevant to RX/TX virtqueues. */ @@ -70,8 +90,8 @@ struct vhost_virtqueue { struct vring_used *used; uint32_t size; - /* Last index used on the available ring */ - volatile uint16_t last_used_idx; + uint16_t last_avail_idx; + uint16_t last_used_idx; #define VIRTIO_INVALID_EVENTFD (-1) #define VIRTIO_UNINITIALIZED_EVENTFD (-2) @@ -85,26 +105,31 @@ struct vhost_virtqueue { /* Physical address of used ring, for logging */ uint64_t log_guest_addr; + + uint16_t nr_zmbuf; + uint16_t zmbuf_size; + uint16_t last_zmbuf_idx; + struct zcopy_mbuf *zmbufs; + struct zcopy_mbuf_list zmbuf_list; + + struct vring_used_elem *shadow_used_ring; + uint16_t shadow_used_idx; } __rte_cache_aligned; -/* Old kernels have no such macro defined */ +/* Old kernels have no such macros defined */ #ifndef VIRTIO_NET_F_GUEST_ANNOUNCE #define VIRTIO_NET_F_GUEST_ANNOUNCE 21 #endif +#ifndef VIRTIO_NET_F_MQ + #define VIRTIO_NET_F_MQ 22 +#endif -/* - * Make an extra wrapper for VIRTIO_NET_F_MQ and - * VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX as they are - * introduced since kernel v3.8. This makes our - * code buildable for older kernel. - */ -#ifdef VIRTIO_NET_F_MQ - #define VHOST_MAX_QUEUE_PAIRS VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX - #define VHOST_SUPPORTS_MQ (1ULL << VIRTIO_NET_F_MQ) -#else - #define VHOST_MAX_QUEUE_PAIRS 1 - #define VHOST_SUPPORTS_MQ 0 +#define VHOST_MAX_VRING 0x100 +#define VHOST_MAX_QUEUE_PAIRS 0x80 + +#ifndef VIRTIO_NET_F_MTU + #define VIRTIO_NET_F_MTU 3 #endif /* @@ -114,13 +139,40 @@ struct vhost_virtqueue { #define VIRTIO_F_VERSION_1 32 #endif +#define VHOST_USER_F_PROTOCOL_FEATURES 30 + +/* Features supported by this builtin vhost-user net driver. */ +#define VIRTIO_NET_SUPPORTED_FEATURES ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | \ + (1ULL << VIRTIO_NET_F_CTRL_VQ) | \ + (1ULL << VIRTIO_NET_F_CTRL_RX) | \ + (1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE) | \ + (1ULL << VIRTIO_NET_F_MQ) | \ + (1ULL << VIRTIO_F_VERSION_1) | \ + (1ULL << VHOST_F_LOG_ALL) | \ + (1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \ + (1ULL << VIRTIO_NET_F_HOST_TSO4) | \ + (1ULL << VIRTIO_NET_F_HOST_TSO6) | \ + (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_RING_F_INDIRECT_DESC) | \ + (1ULL << VIRTIO_NET_F_MTU)) + + +struct guest_page { + uint64_t guest_phys_addr; + uint64_t host_phys_addr; + uint64_t size; +}; + /** * Device structure contains all configuration information relating * to the device. */ struct virtio_net { /* Frontend (QEMU) memory and memory region information */ - struct virtio_memory *mem; + struct rte_vhost_memory *mem; uint64_t features; uint64_t protocol_features; int vid; @@ -128,7 +180,8 @@ 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) char ifname[IF_NAME_SZ]; @@ -136,34 +189,52 @@ struct virtio_net { uint64_t log_base; uint64_t log_addr; struct ether_addr mac; + uint16_t mtu; + + struct vhost_device_ops const *notify_ops; + uint32_t nr_guest_pages; + uint32_t max_guest_pages; + struct guest_page *guest_pages; } __rte_cache_aligned; -/** - * Information relating to memory regions including offsets to - * addresses in QEMUs memory file. - */ -struct virtio_memory_regions { - uint64_t guest_phys_address; - uint64_t guest_phys_address_end; - uint64_t memory_size; - uint64_t userspace_address; - uint64_t address_offset; -}; +#define VHOST_LOG_PAGE 4096 -/** - * Memory structure includes region and mapping information. - */ -struct virtio_memory { - /* Base QEMU userspace address of the memory file. */ - uint64_t base_address; - uint64_t mapped_address; - uint64_t mapped_size; - uint32_t nregions; - struct virtio_memory_regions regions[0]; -}; +static __rte_always_inline void +vhost_log_page(uint8_t *log_base, uint64_t page) +{ + log_base[page / 8] |= 1 << (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 @@ -200,29 +271,26 @@ extern uint64_t VHOST_FEATURES; #define MAX_VHOST_DEVICE 1024 extern struct virtio_net *vhost_devices[MAX_VHOST_DEVICE]; -/** - * Function to convert guest physical addresses to vhost virtual addresses. - * This is used to convert guest virtio buffer addresses. - */ -static inline uint64_t __attribute__((always_inline)) -gpa_to_vva(struct virtio_net *dev, uint64_t guest_pa) +/* Convert guest physical address to host physical address */ +static __rte_always_inline phys_addr_t +gpa_to_hpa(struct virtio_net *dev, uint64_t gpa, uint64_t size) { - struct virtio_memory_regions *region; - uint32_t regionidx; - uint64_t vhost_va = 0; - - for (regionidx = 0; regionidx < dev->mem->nregions; regionidx++) { - region = &dev->mem->regions[regionidx]; - if ((guest_pa >= region->guest_phys_address) && - (guest_pa <= region->guest_phys_address_end)) { - vhost_va = region->address_offset + guest_pa; - break; + uint32_t i; + struct guest_page *page; + + for (i = 0; i < dev->nr_guest_pages; i++) { + page = &dev->guest_pages[i]; + + if (gpa >= page->guest_phys_addr && + gpa + size < page->guest_phys_addr + page->size) { + return gpa - page->guest_phys_addr + + page->host_phys_addr; } } - return vhost_va; + + return 0; } -struct virtio_net_device_ops const *notify_ops; struct virtio_net *get_device(int vid); int vhost_new_device(void); @@ -230,12 +298,17 @@ 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); +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); + +struct vhost_device_ops const *vhost_driver_callback_get(const char *path); /* - * Backend-specific cleanup. Defined by vhost-cuse and vhost-user. + * Backend-specific cleanup. + * + * TODO: fix it; we have one backend now */ void vhost_backend_cleanup(struct virtio_net *dev);