vhost: handle dirty pages logging request

VHOST_USER_SET_LOG_BASE request is used to tell the backend (dpdk
vhost-user) where we should log dirty pages, and how big the log
buffer is.

This request introduces a new payload:

    typedef struct VhostUserLog {
            uint64_t mmap_size;
            uint64_t mmap_offset;
    } VhostUserLog;

Also, a fd is delivered from QEMU by ancillary data.

With those info given, an area of memory is mmaped, assigned
to dev->log_base, for logging dirty pages.

Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: Victor Kaplansky <victork@redhat.com>
Tested-by: Pavel Fedin <p.fedin@samsung.com>

Author: Yuanhan Liu

lib/librte_vhost/rte_virtio_net.h

@@ -129,7 +129,9 @@ struct virtio_net {
 	char			ifname[IF_NAME_SZ];	/**< Name of the tap device or socket path. */
 	uint32_t		virt_qp_nb;	/**< number of queue pair we have allocated */
 	void			*priv;		/**< private context */
-	uint64_t		reserved[64];	/**< Reserve some spaces for future extension. */
+	uint64_t		log_size;	/**< Size of log area */
+	uint64_t		log_base;	/**< Where dirty pages are logged */
+	uint64_t		reserved[62];	/**< Reserve some spaces for future extension. */
 	struct vhost_virtqueue	*virtqueue[VHOST_MAX_QUEUE_PAIRS * 2];	/**< Contains all virtqueue information. */
 } __rte_cache_aligned;
 

lib/librte_vhost/vhost_user/vhost-net-user.c

@@ -388,9 +388,12 @@ vserver_message_handler(int connfd, void *dat, int *remove)
 		break;
 
 	case VHOST_USER_SET_LOG_BASE:
-		RTE_LOG(INFO, VHOST_CONFIG, "not implemented.\n");
-		break;
+		user_set_log_base(ctx, &msg);
 
+		/* it needs a reply */
+		msg.size = sizeof(msg.payload.u64);
+		send_vhost_message(connfd, &msg);
+		break;
 	case VHOST_USER_SET_LOG_FD:
 		close(msg.fds[0]);
 		RTE_LOG(INFO, VHOST_CONFIG, "not implemented.\n");

lib/librte_vhost/vhost_user/vhost-net-user.h

@@ -83,6 +83,11 @@ typedef struct VhostUserMemory {
 	VhostUserMemoryRegion regions[VHOST_MEMORY_MAX_NREGIONS];
 } VhostUserMemory;
 
+typedef struct VhostUserLog {
+	uint64_t mmap_size;
+	uint64_t mmap_offset;
+} VhostUserLog;
+
 typedef struct VhostUserMsg {
 	VhostUserRequest request;
 
@@ -97,6 +102,7 @@ typedef struct VhostUserMsg {
 		struct vhost_vring_state state;
 		struct vhost_vring_addr addr;
 		VhostUserMemory memory;
+		VhostUserLog    log;
 	} payload;
 	int fds[VHOST_MEMORY_MAX_NREGIONS];
 } __attribute((packed)) VhostUserMsg;

lib/librte_vhost/vhost_user/virtio-net-user.c

@@ -365,3 +365,51 @@ user_set_protocol_features(struct vhost_device_ctx ctx,
 
 	dev->protocol_features = protocol_features;
 }
+
+int
+user_set_log_base(struct vhost_device_ctx ctx,
+		 struct VhostUserMsg *msg)
+{
+	struct virtio_net *dev;
+	int fd = msg->fds[0];
+	uint64_t size, off;
+	void *addr;
+
+	dev = get_device(ctx);
+	if (!dev)
+		return -1;
+
+	if (fd < 0) {
+		RTE_LOG(ERR, VHOST_CONFIG, "invalid log fd: %d\n", fd);
+		return -1;
+	}
+
+	if (msg->size != sizeof(VhostUserLog)) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"invalid log base msg size: %"PRId32" != %d\n",
+			msg->size, (int)sizeof(VhostUserLog));
+		return -1;
+	}
+
+	size = msg->payload.log.mmap_size;
+	off  = msg->payload.log.mmap_offset;
+	RTE_LOG(INFO, VHOST_CONFIG,
+		"log mmap size: %"PRId64", offset: %"PRId64"\n",
+		size, off);
+
+	/*
+	 * mmap from 0 to workaround a hugepage mmap bug: mmap will
+	 * fail when offset is not page size aligned.
+	 */
+	addr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED) {
+		RTE_LOG(ERR, VHOST_CONFIG, "mmap log base failed!\n");
+		return -1;
+	}
+
+	/* TODO: unmap on stop */
+	dev->log_base = (uint64_t)(uintptr_t)addr + off;
+	dev->log_size = size;
+
+	return 0;
+}

lib/librte_vhost/vhost_user/virtio-net-user.h

@@ -49,6 +49,7 @@ void user_set_vring_kick(struct vhost_device_ctx, struct VhostUserMsg *);
 
 void user_set_protocol_features(struct vhost_device_ctx ctx,
 				uint64_t protocol_features);
+int user_set_log_base(struct vhost_device_ctx ctx, struct VhostUserMsg *);
 
 int user_get_vring_base(struct vhost_device_ctx, struct vhost_vring_state *);