*** vhost support inflight share memory protocol feature ***

index 0226b3eff..417ad8b16 100644
@@ -11,6 +11,7 @@
  */
 
 #include <stdint.h>
+#include <stdbool.h>
 #include <sys/eventfd.h>
 
 #include <rte_memory.h>

@@ -71,6 +72,10 @@ extern "C" {
 #define VHOST_USER_PROTOCOL_F_HOST_NOTIFIER 11
 #endif
 
+#ifndef VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD
+#define VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD 12
+#endif
+
 /** Indicate whether protocol features negotiation is supported. */
 #ifndef VHOST_USER_F_PROTOCOL_FEATURES
 #define VHOST_USER_F_PROTOCOL_FEATURES	30

@@ -98,10 +103,85 @@ struct rte_vhost_memory {
 	struct rte_vhost_mem_region regions[];
 };
 
+struct inflight_desc_packed {
+	uint8_t inflight;
+	uint8_t padding;
+	uint16_t next;
+	uint16_t last;
+	uint16_t num;
+	uint64_t counter;
+	uint16_t id;
+	uint16_t flags;
+	uint32_t len;
+	uint64_t addr;
+};
+
+struct inflight_info_packed {
+	uint64_t features;
+	uint16_t version;
+	uint16_t desc_num;
+	uint16_t free_head;
+	uint16_t old_free_head;
+	uint16_t used_idx;
+	uint16_t old_used_idx;
+	uint8_t used_wrap_counter;
+	uint8_t old_used_wrap_counter;
+	uint8_t padding[7];
+	struct inflight_desc_packed desc[0];
+};
+
+struct rte_vhost_resubmit_desc {
+	uint16_t index;
+	uint64_t counter;
+};
+
+struct rte_vhost_resubmit_info {
+	struct rte_vhost_resubmit_desc	*resubmit_list;
+	uint16_t resubmit_num;
+};
+
+struct rte_vhost_ring_inflight{
+	union {
+		struct inflight_info_split *inflight_split;
+		struct inflight_info_packed *inflight_packed;
+	};
+
+	struct rte_vhost_resubmit_info *resubmit_inflight;
+};
+
+struct vring_packed_desc {
+	uint64_t addr;
+	uint32_t len;
+	uint16_t id;
+	uint16_t flags;
+};
+
+struct vring_split_desc {
+	uint64_t addr;
+	uint32_t len;
+	uint16_t flags;
+	uint16_t next;
+};
+
+struct vring_packed_desc_event {
+	uint16_t off_wrap;
+	uint16_t flags;
+};
+
 struct rte_vhost_vring {
-	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;
+	};
+
 	uint64_t		log_guest_addr;
 
 	/** Deprecated, use rte_vhost_vring_call() instead. */

@@ -603,6 +683,33 @@ uint16_t rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
  */
 int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem);
 
+/**
+ * Get vq is packed
+ *
+ * @param vid
+ *  vhost device ID
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_vq_is_packed(int vid);
+
+/**
+ * Get guest inflight vring info, including inflight ring and resubmit list.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param vring
+ *  the structure to hold the requested inflight vring info
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_get_vhost_ring_inflight(int vid, uint16_t vring_idx,
+	struct rte_vhost_ring_inflight *vring);
+
 /**
  * Get guest vring info, including the vring address, vring size, etc.
  *

@@ -616,7 +723,7 @@ int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem);
  *  0 on success, -1 on failure
  */
 int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
-			      struct rte_vhost_vring *vring);
+	struct rte_vhost_vring *vring);
 
 /**
  * Notify the guest that used descriptors have been added to the vring.  This

@@ -631,6 +738,112 @@ int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
  */
 int rte_vhost_vring_call(int vid, uint16_t vring_idx);
 
+/**
+ * set split inflight descriptor.
+ *
+ * This function save descriptors that has been comsumed in available
+ * ring
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_set_inflight_desc_split(int vid, uint16_t vring_idx,
+	uint16_t idx);
+
+/**
+ * set packed inflight descriptor and get corresponding inflight entry
+ *
+ * This function save descriptors that has been comsumed
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_set_inflight_desc_packed(int vid, uint16_t vring_idx,
+	uint16_t head, uint16_t last, uint16_t *inflight_entry);
+
+/**
+ * save the head of list that the last batch of used descriptors.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  descriptor entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_set_last_inflight_io_split(int vid, uint16_t vring_idx,
+	uint16_t idx);
+
+/**
+ * update the inflight free_head, used_idx and used_wrap_counter.
+ *
+ * This function will update status first before updating descriptors
+ * to used
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_set_last_inflight_io_packed(int vid, uint16_t vring_idx,
+	uint16_t head);
+
+/**
+ * clear the split inflight status.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param last_used_idx
+ *  last used idx of used ring
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_clr_inflight_desc_split(int vid, uint16_t vring_idx,
+	uint16_t last_used_idx, uint16_t idx);
+
+/**
+ * clear the packed inflight status.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param head
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_clr_inflight_desc_packed(int vid, uint16_t vring_idx,
+	uint16_t head);
+
 /**
  * Get vhost RX queue avail count.
  *

@@ -676,6 +889,68 @@ int __rte_experimental
 rte_vhost_get_vring_base(int vid, uint16_t queue_id,
 		uint16_t *last_avail_idx, uint16_t *last_used_idx);
 
+/**
+ * Get avail_wrap_counter/used_wrap_counter of the vhost virtqueue
+ *
+ * @param vid
+ *  vhost device ID
+ * @param queue_id
+ *  vhost queue index
+ * @param avail_wrap_counter
+ *  vhost avail_wrap_counter to get
+ * @param used_wrap_counter
+ *  vhost used_wrap_counter to get
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_get_vring_base_counter(int vid, uint16_t queue_id,
+		bool *avail_wrap_counter, bool *used_wrap_counter);
+
+/**
+ * Get last_avail/last_used of the vhost virtqueue
+ *
+ * This function is designed for the reconnection and it's specific for
+ * the packed ring as we can get the two parameters from the inflight
+ * queueregion
+ *
+ * @param vid
+ *  vhost device ID
+ * @param queue_id
+ *  vhost queue index
+ * @param last_avail_idx
+ *  vhost last_avail_idx to get
+ * @param last_used_idx
+ *  vhost last_used_idx to get
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_get_vring_base_from_inflight(int vid, uint16_t queue_id,
+		uint16_t *last_avail_idx, uint16_t *last_used_idx);
+
+/**
+ * Get avail_wrap_counter/used_wrap_counter of the vhost virtqueue
+ *
+ * This function is designed for the reconnection and it's specific for
+ * the packed ring as we can get the two parameters from the inflight
+ * queueregion
+ *
+ * @param vid
+ *  vhost device ID
+ * @param queue_id
+ *  vhost queue index
+ * @param avail_wrap_counter
+ *  vhost avail_wrap_counter to get
+ * @param used_wrap_counter
+ *  vhost used_wrap_counter to get
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_get_vring_base_counter_from_inflight(int vid,
+		uint16_t queue_id, bool *avail_wrap_counter, bool *used_wrap_counter);
+
 /**
  * Set last_avail/used_idx of the vhost virtqueue
  *

@@ -694,6 +969,24 @@ int __rte_experimental
 rte_vhost_set_vring_base(int vid, uint16_t queue_id,
 		uint16_t last_avail_idx, uint16_t last_used_idx);
 
+/**
+ * Set avail_wrap_counter/used_wrap_counter of the vhost virtqueue
+ *
+ * @param vid
+ *  vhost device ID
+ * @param queue_id
+ *  vhost queue index
+ * @param avail_wrap_counter
+ *  avail_wrap_counter to set
+ * @param used_wrap_counter
+ *  used_wrap_counter to set
+ * @return
+ *  0 on success, -1 on failure
+ */
+int __rte_experimental
+rte_vhost_set_vring_base_counter(int vid, uint16_t queue_id,
+		bool avail_wrap_counter, bool used_wrap_counter);
+
 /**
  * Register external message handling callbacks
  *

442 lines not on this page · raw message

96 lines not on this page · raw message

478 lines not on this page · raw message

index 2a650fe4b..99a773910 100644
@@ -54,7 +54,9 @@ typedef enum VhostUserRequest {
 	VHOST_USER_POSTCOPY_ADVISE = 28,
 	VHOST_USER_POSTCOPY_LISTEN = 29,
 	VHOST_USER_POSTCOPY_END = 30,
-	VHOST_USER_MAX = 31
+	VHOST_USER_GET_INFLIGHT_FD = 31,
+	VHOST_USER_SET_INFLIGHT_FD = 32,
+	VHOST_USER_MAX = 33
 } VhostUserRequest;
 
 typedef enum VhostUserSlaveRequest {

@@ -112,6 +114,13 @@ typedef struct VhostUserVringArea {
 	uint64_t offset;
 } VhostUserVringArea;
 
+typedef struct VhostUserInflight {
+	uint64_t mmap_size;
+	uint64_t mmap_offset;
+	uint16_t num_queues;
+	uint16_t queue_size;
+} VhostUserInflight;
+
 typedef struct VhostUserMsg {
 	union {
 		uint32_t master; /* a VhostUserRequest value */

@@ -131,6 +140,7 @@ typedef struct VhostUserMsg {
 		struct vhost_vring_addr addr;
 		VhostUserMemory memory;
 		VhostUserLog    log;
+		VhostUserInflight inflight;
 		struct vhost_iotlb_msg iotlb;
 		VhostUserCryptoSessionParam crypto_session;
 		VhostUserVringArea area;

@@ -148,6 +158,7 @@ typedef struct VhostUserMsg {
 /* vhost_user.c */
 int vhost_user_msg_handler(int vid, int fd);
 int vhost_user_iotlb_miss(struct virtio_net *dev, uint64_t iova, uint8_t perm);
+void *inflight_mem_alloc(const char *name, size_t size, int *fd);
 
 /* socket.c */
 int read_fd_message(int sockfd, char *buf, int buflen, int *fds, int max_fds,

122 lines not on this page · raw message

95 lines not on this page · raw message

1,054 lines not on this page · raw message

114 lines not on this page · raw message

193 lines not on this page · raw message