#include <rte_log.h>
#include <rte_ether.h>
#include <rte_rwlock.h>
+#include <rte_malloc.h>
#include "rte_vhost.h"
#include "rte_vdpa.h"
+#include "rte_vdpa_dev.h"
+
+#include "rte_vhost_async.h"
/* Used to indicate that the device is running on a data core */
#define VIRTIO_DEV_RUNNING 1
#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
+/* Used to indicate that the feature negotiation failed */
+#define VIRTIO_DEV_FEATURES_FAILED 16
/* Backend value set by guest. */
#define VIRTIO_DEV_STOPPED -1
#define BUF_VECTOR_MAX 256
+#define VHOST_LOG_CACHE_NR 32
+
+#define MAX_PKT_BURST 32
+
+#define ASYNC_MAX_POLL_SEG 255
+
+#define VHOST_MAX_ASYNC_IT (MAX_PKT_BURST * 2)
+#define VHOST_MAX_ASYNC_VEC (BUF_VECTOR_MAX * 2)
+
+#define PACKED_DESC_ENQUEUE_USED_FLAG(w) \
+ ((w) ? (VRING_DESC_F_AVAIL | VRING_DESC_F_USED | VRING_DESC_F_WRITE) : \
+ VRING_DESC_F_WRITE)
+#define PACKED_DESC_DEQUEUE_USED_FLAG(w) \
+ ((w) ? (VRING_DESC_F_AVAIL | VRING_DESC_F_USED) : 0x0)
+#define PACKED_DESC_SINGLE_DEQUEUE_FLAG (VRING_DESC_F_NEXT | \
+ VRING_DESC_F_INDIRECT)
+
+#define PACKED_BATCH_SIZE (RTE_CACHE_LINE_SIZE / \
+ sizeof(struct vring_packed_desc))
+#define PACKED_BATCH_MASK (PACKED_BATCH_SIZE - 1)
+
+#ifdef VHOST_GCC_UNROLL_PRAGMA
+#define vhost_for_each_try_unroll(iter, val, size) _Pragma("GCC unroll 4") \
+ for (iter = val; iter < size; iter++)
+#endif
+
+#ifdef VHOST_CLANG_UNROLL_PRAGMA
+#define vhost_for_each_try_unroll(iter, val, size) _Pragma("unroll 4") \
+ for (iter = val; iter < size; iter++)
+#endif
+
+#ifdef VHOST_ICC_UNROLL_PRAGMA
+#define vhost_for_each_try_unroll(iter, val, size) _Pragma("unroll (4)") \
+ for (iter = val; iter < size; iter++)
+#endif
+
+#ifndef vhost_for_each_try_unroll
+#define vhost_for_each_try_unroll(iter, val, num) \
+ for (iter = val; iter < num; iter++)
+#endif
+
/**
* 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;
struct zcopy_mbuf {
struct rte_mbuf *mbuf;
uint32_t desc_idx;
+ uint16_t desc_count;
uint16_t in_use;
TAILQ_ENTRY(zcopy_mbuf) next;
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;
+ uint16_t flags;
+ 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)
int backend;
int enabled;
int access_ok;
+ int ready;
+ int notif_enable;
+#define VIRTIO_UNINITIALIZED_NOTIF (-1)
+
rte_spinlock_t access_lock;
/* Used to notify the guest (trigger interrupt) */
/* Physical address of used ring, for logging */
uint64_t log_guest_addr;
+ /* inflight share memory info */
+ union {
+ struct rte_vhost_inflight_info_split *inflight_split;
+ struct rte_vhost_inflight_info_packed *inflight_packed;
+ };
+ struct rte_vhost_resubmit_info *resubmit_inflight;
+ uint64_t global_counter;
+
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;
+ union {
+ struct vring_used_elem *shadow_used_split;
+ struct vring_used_elem_packed *shadow_used_packed;
+ };
uint16_t shadow_used_idx;
+ /* Record packed ring enqueue latest desc cache aligned index */
+ uint16_t shadow_aligned_idx;
+ /* Record packed ring first dequeue desc index */
+ uint16_t shadow_last_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;
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 */
-#ifndef VIRTIO_NET_F_GUEST_ANNOUNCE
- #define VIRTIO_NET_F_GUEST_ANNOUNCE 21
-#endif
+ /* operation callbacks for async dma */
+ struct rte_vhost_async_channel_ops async_ops;
+
+ struct rte_vhost_iov_iter it_pool[VHOST_MAX_ASYNC_IT];
+ struct iovec vec_pool[VHOST_MAX_ASYNC_VEC];
+
+ /* async data transfer status */
+ uintptr_t **async_pkts_pending;
+ #define ASYNC_PENDING_INFO_N_MSK 0xFFFF
+ #define ASYNC_PENDING_INFO_N_SFT 16
+ uint64_t *async_pending_info;
+ uint16_t async_pkts_idx;
+ uint16_t async_pkts_inflight_n;
+ uint16_t async_last_seg_n;
+
+ /* vq async features */
+ bool async_inorder;
+ bool async_registered;
+ uint16_t async_threshold;
+} __rte_cache_aligned;
-#ifndef VIRTIO_NET_F_MQ
- #define VIRTIO_NET_F_MQ 22
-#endif
+/* Virtio device status as per Virtio specification */
+#define VIRTIO_DEVICE_STATUS_ACK 0x01
+#define VIRTIO_DEVICE_STATUS_DRIVER 0x02
+#define VIRTIO_DEVICE_STATUS_DRIVER_OK 0x04
+#define VIRTIO_DEVICE_STATUS_FEATURES_OK 0x08
+#define VIRTIO_DEVICE_STATUS_DEV_NEED_RESET 0x40
+#define VIRTIO_DEVICE_STATUS_FAILED 0x80
#define VHOST_MAX_VRING 0x100
#define VHOST_MAX_QUEUE_PAIRS 0x80
-#ifndef VIRTIO_NET_F_MTU
- #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_VERSION_1 32
#endif
+/* 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_GUEST_ECN) | \
(1ULL << VIRTIO_RING_F_INDIRECT_DESC) | \
(1ULL << VIRTIO_RING_F_EVENT_IDX) | \
- (1ULL << VIRTIO_NET_F_MTU) | \
- (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ (1ULL << VIRTIO_NET_F_MTU) | \
+ (1ULL << VIRTIO_F_IN_ORDER) | \
+ (1ULL << VIRTIO_F_IOMMU_PLATFORM) | \
+ (1ULL << VIRTIO_F_RING_PACKED))
struct guest_page {
uint64_t size;
};
-/**
- * function prototype for the vhost backend to handler specific vhost user
- * messages prior to the master message handling
- *
- * @param vid
- * vhost device id
- * @param msg
- * Message pointer.
- * @param require_reply
- * If the handler requires sending a reply, this varaible shall be written 1,
- * otherwise 0.
- * @param skip_master
- * If the handler requires skipping the master message handling, this variable
- * shall be written 1, otherwise 0.
- * @return
- * 0 on success, -1 on failure
- */
-typedef int (*vhost_msg_pre_handle)(int vid, void *msg,
- uint32_t *require_reply, uint32_t *skip_master);
-
-/**
- * function prototype for the vhost backend to handler specific vhost user
- * messages after the master message handling is done
- *
- * @param vid
- * vhost device id
- * @param msg
- * Message pointer.
- * @param require_reply
- * If the handler requires sending a reply, this varaible shall be written 1,
- * otherwise 0.
- * @return
- * 0 on success, -1 on failure
- */
-typedef int (*vhost_msg_post_handle)(int vid, void *msg,
- uint32_t *require_reply);
-
-/**
- * pre and post vhost user message handlers
- */
-struct vhost_user_extern_ops {
- vhost_msg_pre_handle pre_msg_handle;
- vhost_msg_post_handle post_msg_handle;
+struct inflight_mem_info {
+ int fd;
+ void *addr;
+ uint64_t size;
};
/**
uint32_t flags;
uint16_t vhost_hlen;
/* to tell if we need broadcast rarp packet */
- rte_atomic16_t broadcast_rarp;
+ int16_t broadcast_rarp;
uint32_t nr_vring;
int dequeue_zero_copy;
+ int async_copy;
+ int extbuf;
+ int linearbuf;
struct vhost_virtqueue *virtqueue[VHOST_MAX_QUEUE_PAIRS * 2];
+ struct inflight_mem_info *inflight_info;
#define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)
char ifname[IF_NAME_SZ];
uint64_t log_size;
uint64_t log_base;
uint64_t log_addr;
- struct ether_addr mac;
+ struct rte_ether_addr mac;
uint16_t mtu;
+ uint8_t status;
struct vhost_device_ops const *notify_ops;
struct guest_page *guest_pages;
int slave_req_fd;
+ rte_spinlock_t slave_req_lock;
- /*
- * Device id to identify a specific backend device.
- * It's set to -1 for the default software implementation.
- */
- int vdpa_dev_id;
+ int postcopy_ufd;
+ int postcopy_listening;
- /* private data for virtio device */
+ struct rte_vdpa_device *vdpa_dev;
+
+ /* context data for the external message handlers */
void *extern_data;
/* pre and post vhost user message handlers for the device */
- struct vhost_user_extern_ops extern_ops;
+ struct rte_vhost_user_extern_ops extern_ops;
} __rte_cache_aligned;
-#define VHOST_LOG_PAGE 4096
+static __rte_always_inline bool
+vq_is_packed(struct virtio_net *dev)
+{
+ return dev->features & (1ull << VIRTIO_F_RING_PACKED);
+}
-/*
- * Mark all pages belonging to the same dirty log bitmap byte
- * as dirty. The goal is to avoid concurrency between different
- * threads doing atomic read-modify-writes on the same byte.
- */
-static __rte_always_inline void
-vhost_log_page(uint8_t *log_base, uint64_t page)
+static inline bool
+desc_is_avail(struct vring_packed_desc *desc, bool wrap_counter)
{
- log_base[page / 8] = 0xff;
+ uint16_t flags = __atomic_load_n(&desc->flags, __ATOMIC_ACQUIRE);
+
+ return wrap_counter == !!(flags & VRING_DESC_F_AVAIL) &&
+ wrap_counter != !!(flags & VRING_DESC_F_USED);
+}
+
+static inline void
+vq_inc_last_used_packed(struct vhost_virtqueue *vq, uint16_t num)
+{
+ vq->last_used_idx += num;
+ if (vq->last_used_idx >= vq->size) {
+ vq->used_wrap_counter ^= 1;
+ vq->last_used_idx -= vq->size;
+ }
}
+static inline void
+vq_inc_last_avail_packed(struct vhost_virtqueue *vq, uint16_t num)
+{
+ vq->last_avail_idx += num;
+ if (vq->last_avail_idx >= vq->size) {
+ vq->avail_wrap_counter ^= 1;
+ vq->last_avail_idx -= vq->size;
+ }
+}
+
+void __vhost_log_cache_write(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint64_t addr, uint64_t len);
+void __vhost_log_cache_write_iova(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint64_t iova, uint64_t len);
+void __vhost_log_cache_sync(struct virtio_net *dev,
+ struct vhost_virtqueue *vq);
+void __vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len);
+void __vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint64_t iova, uint64_t len);
+
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->features & (1ULL << VHOST_F_LOG_ALL)))
+ __vhost_log_write(dev, addr, len);
+}
- if (unlikely(dev->log_size <= ((addr + len - 1) / VHOST_LOG_PAGE / 8)))
- return;
+static __rte_always_inline void
+vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+ if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL)))
+ __vhost_log_cache_sync(dev, vq);
+}
- /* To make sure guest memory updates are committed before logging */
- rte_smp_wmb();
+static __rte_always_inline void
+vhost_log_cache_write(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint64_t addr, uint64_t len)
+{
+ if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL)))
+ __vhost_log_cache_write(dev, vq, addr, len);
+}
- 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_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint64_t offset, uint64_t len)
+{
+ if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL))) {
+ if (unlikely(vq->log_guest_addr == 0))
+ return;
+ __vhost_log_cache_write(dev, vq, vq->log_guest_addr + offset,
+ len);
}
}
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);
+ if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL))) {
+ if (unlikely(vq->log_guest_addr == 0))
+ return;
+ __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
+static __rte_always_inline void
+vhost_log_cache_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint64_t iova, uint64_t len)
+{
+ if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
+ return;
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ __vhost_log_cache_write_iova(dev, vq, iova, len);
+ else
+ __vhost_log_cache_write(dev, vq, iova, len);
+}
+
+static __rte_always_inline void
+vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint64_t iova, uint64_t len)
+{
+ if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
+ return;
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ __vhost_log_write_iova(dev, vq, iova, len);
+ else
+ __vhost_log_write(dev, iova, len);
+}
+
+extern int vhost_config_log_level;
+extern int vhost_data_log_level;
+
+#define VHOST_LOG_CONFIG(level, fmt, args...) \
+ rte_log(RTE_LOG_ ## level, vhost_config_log_level, \
+ "VHOST_CONFIG: " fmt, ##args)
+
+#define VHOST_LOG_DATA(level, fmt, args...) \
+ (void)((RTE_LOG_ ## level <= RTE_LOG_DP_LEVEL) ? \
+ rte_log(RTE_LOG_ ## level, vhost_data_log_level, \
+ "VHOST_DATA : " fmt, ##args) : \
+ 0)
#ifdef RTE_LIBRTE_VHOST_DEBUG
#define VHOST_MAX_PRINT_BUFF 6072
-#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; \
} \
snprintf(packet + strnlen(packet, VHOST_MAX_PRINT_BUFF), VHOST_MAX_PRINT_BUFF - strnlen(packet, VHOST_MAX_PRINT_BUFF), "\n"); \
\
- VHOST_LOG_DEBUG(VHOST_DATA, "%s", packet); \
+ VHOST_LOG_DATA(DEBUG, "%s", packet); \
} while (0)
#else
-#define VHOST_LOG_DEBUG(log_type, fmt, args...) do {} while (0)
#define PRINT_PACKET(device, addr, size, header) do {} while (0)
#endif
-extern uint64_t VHOST_FEATURES;
#define MAX_VHOST_DEVICE 1024
extern struct virtio_net *vhost_devices[MAX_VHOST_DEVICE];
+#define VHOST_BINARY_SEARCH_THRESH 256
+
+static __rte_always_inline int guest_page_addrcmp(const void *p1,
+ const void *p2)
+{
+ const struct guest_page *page1 = (const struct guest_page *)p1;
+ const struct guest_page *page2 = (const struct guest_page *)p2;
+
+ if (page1->guest_phys_addr > page2->guest_phys_addr)
+ return 1;
+ if (page1->guest_phys_addr < page2->guest_phys_addr)
+ return -1;
+
+ return 0;
+}
+
/* Convert guest physical address to host physical address */
static __rte_always_inline rte_iova_t
gpa_to_hpa(struct virtio_net *dev, uint64_t gpa, uint64_t size)
{
uint32_t i;
struct guest_page *page;
+ struct guest_page key;
+
+ if (dev->nr_guest_pages >= VHOST_BINARY_SEARCH_THRESH) {
+ key.guest_phys_addr = gpa;
+ page = bsearch(&key, dev->guest_pages, dev->nr_guest_pages,
+ sizeof(struct guest_page), guest_page_addrcmp);
+ if (page) {
+ if (gpa + size < page->guest_phys_addr + page->size)
+ return gpa - page->guest_phys_addr +
+ page->host_phys_addr;
+ }
+ } else {
+ 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;
+ }
+ }
- for (i = 0; i < dev->nr_guest_pages; i++) {
- page = &dev->guest_pages[i];
+ return 0;
+}
- if (gpa >= page->guest_phys_addr &&
- gpa + size < page->guest_phys_addr + page->size) {
- return gpa - page->guest_phys_addr +
- page->host_phys_addr;
+static __rte_always_inline rte_iova_t
+gpa_to_first_hpa(struct virtio_net *dev, uint64_t gpa,
+ uint64_t gpa_size, uint64_t *hpa_size)
+{
+ uint32_t i;
+ struct guest_page *page;
+ struct guest_page key;
+
+ *hpa_size = gpa_size;
+ if (dev->nr_guest_pages >= VHOST_BINARY_SEARCH_THRESH) {
+ key.guest_phys_addr = gpa & ~(dev->guest_pages[0].size - 1);
+ page = bsearch(&key, dev->guest_pages, dev->nr_guest_pages,
+ sizeof(struct guest_page), guest_page_addrcmp);
+ if (page) {
+ if (gpa + gpa_size <=
+ page->guest_phys_addr + page->size) {
+ return gpa - page->guest_phys_addr +
+ page->host_phys_addr;
+ } else if (gpa < page->guest_phys_addr +
+ page->size) {
+ *hpa_size = page->guest_phys_addr +
+ page->size - gpa;
+ return gpa - page->guest_phys_addr +
+ page->host_phys_addr;
+ }
+ }
+ } else {
+ for (i = 0; i < dev->nr_guest_pages; i++) {
+ page = &dev->guest_pages[i];
+
+ if (gpa >= page->guest_phys_addr) {
+ if (gpa + gpa_size <=
+ page->guest_phys_addr + page->size) {
+ return gpa - page->guest_phys_addr +
+ page->host_phys_addr;
+ } else if (gpa < page->guest_phys_addr +
+ page->size) {
+ *hpa_size = page->guest_phys_addr +
+ page->size - gpa;
+ return gpa - page->guest_phys_addr +
+ page->host_phys_addr;
+ }
+ }
}
}
+ *hpa_size = 0;
+ return 0;
+}
+
+static __rte_always_inline uint64_t
+hva_to_gpa(struct virtio_net *dev, uint64_t vva, uint64_t len)
+{
+ struct rte_vhost_mem_region *r;
+ uint32_t i;
+
+ if (unlikely(!dev || !dev->mem))
+ return 0;
+
+ for (i = 0; i < dev->mem->nregions; i++) {
+ r = &dev->mem->regions[i];
+
+ if (vva >= r->host_user_addr &&
+ vva + len < r->host_user_addr + r->size) {
+ return r->guest_phys_addr + vva - r->host_user_addr;
+ }
+ }
return 0;
}
struct virtio_net *dev = vhost_devices[vid];
if (unlikely(!dev)) {
- RTE_LOG(ERR, VHOST_CONFIG,
+ VHOST_LOG_CONFIG(ERR,
"(%d) device not found.\n", vid);
}
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 vhost_virtqueue *vq);
+void cleanup_vq_inflight(struct virtio_net *dev, struct vhost_virtqueue *vq);
+void free_vq(struct virtio_net *dev, struct vhost_virtqueue *vq);
int alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx);
-void vhost_attach_vdpa_device(int vid, int did);
-void vhost_detach_vdpa_device(int vid);
+void vhost_attach_vdpa_device(int vid, struct rte_vdpa_device *dev);
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);
+void vhost_enable_extbuf(int vid);
+void vhost_enable_linearbuf(int vid);
+int vhost_enable_guest_notification(struct virtio_net *dev,
+ struct vhost_virtqueue *vq, int enable);
struct vhost_device_ops const *vhost_driver_callback_get(const char *path);
uint64_t __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
uint64_t iova, uint64_t *len, uint8_t perm);
+void *vhost_alloc_copy_ind_table(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint64_t desc_addr, uint64_t desc_len);
int vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq);
+uint64_t translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint64_t log_addr);
void vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq);
static __rte_always_inline uint64_t
uint64_t iova, uint64_t *len, uint8_t perm)
{
if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
- return rte_vhost_gpa_to_vva(dev->mem, iova);
+ 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])
}
static __rte_always_inline void
-vhost_vring_call(struct virtio_net *dev, struct vhost_virtqueue *vq)
+vhost_vring_call_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
/* Flush used->idx update before we read avail->flags. */
- rte_mb();
+ 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;
+ uint16_t new = vq->async_pkts_inflight_n ?
+ vq->used->idx: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",
+ VHOST_LOG_DATA(DEBUG, "%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;
+
+ if ((vhost_need_event(vhost_used_event(vq), new, old) &&
+ (vq->callfd >= 0)) ||
+ unlikely(!signalled_used_valid)) {
eventfd_write(vq->callfd, (eventfd_t) 1);
+ if (dev->notify_ops->guest_notified)
+ dev->notify_ops->guest_notified(dev->vid);
}
} else {
/* Kick the guest if necessary. */
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
- && (vq->callfd >= 0))
+ && (vq->callfd >= 0)) {
eventfd_write(vq->callfd, (eventfd_t)1);
+ if (dev->notify_ops->guest_notified)
+ dev->notify_ops->guest_notified(dev->vid);
+ }
}
}
+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);
+ if (dev->notify_ops->guest_notified)
+ dev->notify_ops->guest_notified(dev->vid);
+ }
+}
+
+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_ */
git.droids-corp.org / dpdk.git / blobdiff