vhost: provide helpers for virtio ring relay

[dpdk.git] / lib / librte_vhost / vhost.h

diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index 25ffd76..3b3265c 100644 (file)
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -18,6 +18,7 @@
 #include <rte_log.h>
 #include <rte_ether.h>
 #include <rte_rwlock.h>
+#include <rte_malloc.h>
 
 #include "rte_vhost.h"
 #include "rte_vdpa.h"
@@ -219,13 +220,6 @@ struct vhost_msg {
 
 #define VIRTIO_F_RING_PACKED 34
 
-#define VRING_DESC_F_NEXT      1
-#define VRING_DESC_F_WRITE     2
-#define VRING_DESC_F_INDIRECT  4
-
-#define VRING_DESC_F_AVAIL     (1ULL << 7)
-#define VRING_DESC_F_USED      (1ULL << 15)
-
 struct vring_packed_desc {
        uint64_t addr;
        uint32_t len;
@@ -233,16 +227,23 @@ struct vring_packed_desc {
        uint16_t flags;
 };
 
-#define VRING_EVENT_F_ENABLE 0x0
-#define VRING_EVENT_F_DISABLE 0x1
-#define VRING_EVENT_F_DESC 0x2
-
 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
  */
@@ -275,7 +276,8 @@ struct vring_packed_desc_event {
                                (1ULL << VIRTIO_RING_F_EVENT_IDX) | \
                                (1ULL << VIRTIO_NET_F_MTU)  | \
                                (1ULL << VIRTIO_F_IN_ORDER) | \
-                               (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+                               (1ULL << VIRTIO_F_IOMMU_PLATFORM) | \
+                               (1ULL << VIRTIO_F_RING_PACKED))
 
 
 struct guest_page {
@@ -284,6 +286,16 @@ struct guest_page {
        uint64_t size;
 };
 
+/* The possible results of a message handling function */
+enum vh_result {
+       /* Message handling failed */
+       VH_RESULT_ERR   = -1,
+       /* Message handling successful */
+       VH_RESULT_OK    =  0,
+       /* Message handling successful and reply prepared */
+       VH_RESULT_REPLY =  1,
+};
+
 /**
  * function prototype for the vhost backend to handler specific vhost user
  * messages prior to the master message handling
@@ -292,17 +304,15 @@ struct guest_page {
  *  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
+ *  VH_RESULT_OK on success, VH_RESULT_REPLY on success with reply,
+ *  VH_RESULT_ERR on failure
  */
-typedef int (*vhost_msg_pre_handle)(int vid, void *msg,
-               uint32_t *require_reply, uint32_t *skip_master);
+typedef enum vh_result (*vhost_msg_pre_handle)(int vid, void *msg,
+               uint32_t *skip_master);
 
 /**
  * function prototype for the vhost backend to handler specific vhost user
@@ -312,14 +322,11 @@ typedef int (*vhost_msg_pre_handle)(int vid, void *msg,
  *  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
+ *  VH_RESULT_OK on success, VH_RESULT_REPLY on success with reply,
+ *  VH_RESULT_ERR on failure
  */
-typedef int (*vhost_msg_post_handle)(int vid, void *msg,
-               uint32_t *require_reply);
+typedef enum vh_result (*vhost_msg_post_handle)(int vid, void *msg);
 
 /**
  * pre and post vhost user message handlers
@@ -363,6 +370,9 @@ struct virtio_net {
        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.
@@ -384,8 +394,10 @@ vq_is_packed(struct virtio_net *dev)
 static inline bool
 desc_is_avail(struct vring_packed_desc *desc, bool wrap_counter)
 {
-       return wrap_counter == !!(desc->flags & VRING_DESC_F_AVAIL) &&
-               wrap_counter != !!(desc->flags & VRING_DESC_F_USED);
+       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
@@ -618,7 +630,6 @@ 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_set_ifname(int, const char *if_name, unsigned int if_len);
 void vhost_enable_dequeue_zero_copy(int vid);
@@ -744,4 +755,43 @@ 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);
+}
+
 #endif /* _VHOST_NET_CDEV_H_ */