X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_kni%2Frte_kni.c;h=a80cefd2a06e33e58f02dc6f36ae8f93c2400e8e;hb=57a304ef29821bcbca2926ae0cfffe9db64da431;hp=0854b215e0a5b886cb98757b61dd351d6111db24;hpb=3fc5ca2f63529ec5ad7b1b75f517d61dc7613bd9;p=dpdk.git

diff --git a/lib/librte_kni/rte_kni.c b/lib/librte_kni/rte_kni.c
old mode 100755
new mode 100644
index 0854b215e0..a80cefd2a0
--- a/lib/librte_kni/rte_kni.c
+++ b/lib/librte_kni/rte_kni.c
@@ -1,35 +1,34 @@
 /*-
  *   BSD LICENSE
- * 
- *   Copyright(c) 2010-2012 Intel Corporation. All rights reserved.
+ *
+ *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
  *   All rights reserved.
- * 
- *   Redistribution and use in source and binary forms, with or without 
- *   modification, are permitted provided that the following conditions 
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
  *   are met:
- * 
- *     * Redistributions of source code must retain the above copyright 
+ *
+ *     * Redistributions of source code must retain the above copyright
  *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright 
- *       notice, this list of conditions and the following disclaimer in 
- *       the documentation and/or other materials provided with the 
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
  *       distribution.
- *     * Neither the name of Intel Corporation nor the names of its 
- *       contributors may be used to endorse or promote products derived 
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
  *       from this software without specific prior written permission.
- * 
- *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 
- *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 
- *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 
- *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 
- *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 
- *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 
- *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 
- *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 
- *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 
- *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- * 
  */
 
 #ifndef RTE_EXEC_ENV_LINUXAPP
@@ -40,9 +39,8 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <sys/ioctl.h>
-#include <netinet/in.h>
-#include <linux/if.h>
 
+#include <rte_spinlock.h>
 #include <rte_string_fns.h>
 #include <rte_ethdev.h>
 #include <rte_malloc.h>
@@ -61,12 +59,15 @@
 
 #define KNI_REQUEST_MBUF_NUM_MAX      32
 
+#define KNI_MEM_CHECK(cond) do { if (cond) goto kni_fail; } while (0)
+
 /**
  * KNI context
  */
 struct rte_kni {
-	char name[IFNAMSIZ];                /**< KNI interface name */
-	uint8_t port_id;                    /**< Port id KNI associate with */
+	char name[RTE_KNI_NAMESIZE];        /**< KNI interface name */
+	uint16_t group_id;                  /**< Group ID of KNI devices */
+	uint32_t slot_id;                   /**< KNI pool slot ID */
 	struct rte_mempool *pktmbuf_pool;   /**< pkt mbuf mempool */
 	unsigned mbuf_size;                 /**< mbuf size */
 
@@ -78,166 +79,431 @@ struct rte_kni {
 	/* For request & response */
 	struct rte_kni_fifo *req_q;         /**< Request queue */
 	struct rte_kni_fifo *resp_q;        /**< Response queue */
-	void * sync_addr;					/**< Req/Resp Mem address */
+	void * sync_addr;                   /**< Req/Resp Mem address */
 
 	struct rte_kni_ops ops;             /**< operations for request */
+	uint8_t in_use : 1;                 /**< kni in use */
+};
+
+enum kni_ops_status {
+	KNI_REQ_NO_REGISTER = 0,
+	KNI_REQ_REGISTERED,
+};
+
+/**
+ * KNI memzone pool slot
+ */
+struct rte_kni_memzone_slot {
+	uint32_t id;
+	uint8_t in_use : 1;                    /**< slot in use */
+
+	/* Memzones */
+	const struct rte_memzone *m_ctx;       /**< KNI ctx */
+	const struct rte_memzone *m_tx_q;      /**< TX queue */
+	const struct rte_memzone *m_rx_q;      /**< RX queue */
+	const struct rte_memzone *m_alloc_q;   /**< Allocated mbufs queue */
+	const struct rte_memzone *m_free_q;    /**< To be freed mbufs queue */
+	const struct rte_memzone *m_req_q;     /**< Request queue */
+	const struct rte_memzone *m_resp_q;    /**< Response queue */
+	const struct rte_memzone *m_sync_addr;
+
+	/* Free linked list */
+	struct rte_kni_memzone_slot *next;     /**< Next slot link.list */
 };
 
+/**
+ * KNI memzone pool
+ */
+struct rte_kni_memzone_pool {
+	uint8_t initialized : 1;            /**< Global KNI pool init flag */
+
+	uint32_t max_ifaces;                /**< Max. num of KNI ifaces */
+	struct rte_kni_memzone_slot *slots;        /**< Pool slots */
+	rte_spinlock_t mutex;               /**< alloc/relase mutex */
+
+	/* Free memzone slots linked-list */
+	struct rte_kni_memzone_slot *free;         /**< First empty slot */
+	struct rte_kni_memzone_slot *free_tail;    /**< Last empty slot */
+};
+
+
 static void kni_free_mbufs(struct rte_kni *kni);
 static void kni_allocate_mbufs(struct rte_kni *kni);
 
-static int kni_fd = -1;
+static volatile int kni_fd = -1;
+static struct rte_kni_memzone_pool kni_memzone_pool = {
+	.initialized = 0,
+};
 
+static const struct rte_memzone *
+kni_memzone_reserve(const char *name, size_t len, int socket_id,
+						unsigned flags)
+{
+	const struct rte_memzone *mz = rte_memzone_lookup(name);
 
-struct rte_kni *
-rte_kni_create(uint8_t port_id,
-		unsigned mbuf_size,
-		struct rte_mempool *pktmbuf_pool,
-		struct rte_kni_ops *ops)
+	if (mz == NULL)
+		mz = rte_memzone_reserve(name, len, socket_id, flags);
+
+	return mz;
+}
+
+/* Pool mgmt */
+static struct rte_kni_memzone_slot*
+kni_memzone_pool_alloc(void)
 {
-	struct rte_kni_device_info dev_info;
-	struct rte_eth_dev_info eth_dev_info;
-	struct rte_kni *ctx;
-	char itf_name[IFNAMSIZ];
+	struct rte_kni_memzone_slot *slot;
+
+	rte_spinlock_lock(&kni_memzone_pool.mutex);
+
+	if (!kni_memzone_pool.free) {
+		rte_spinlock_unlock(&kni_memzone_pool.mutex);
+		return NULL;
+	}
+
+	slot = kni_memzone_pool.free;
+	kni_memzone_pool.free = slot->next;
+	slot->in_use = 1;
+
+	if (!kni_memzone_pool.free)
+		kni_memzone_pool.free_tail = NULL;
+
+	rte_spinlock_unlock(&kni_memzone_pool.mutex);
+
+	return slot;
+}
+
+static void
+kni_memzone_pool_release(struct rte_kni_memzone_slot *slot)
+{
+	rte_spinlock_lock(&kni_memzone_pool.mutex);
+
+	if (kni_memzone_pool.free)
+		kni_memzone_pool.free_tail->next = slot;
+	else
+		kni_memzone_pool.free = slot;
+
+	kni_memzone_pool.free_tail = slot;
+	slot->next = NULL;
+	slot->in_use = 0;
+
+	rte_spinlock_unlock(&kni_memzone_pool.mutex);
+}
+
+
+/* Shall be called before any allocation happens */
+void
+rte_kni_init(unsigned int max_kni_ifaces)
+{
+	uint32_t i;
+	struct rte_kni_memzone_slot *it;
+	const struct rte_memzone *mz;
 #define OBJNAMSIZ 32
 	char obj_name[OBJNAMSIZ];
-	const struct rte_memzone *mz;
+	char mz_name[RTE_MEMZONE_NAMESIZE];
 
-	if (port_id >= RTE_MAX_ETHPORTS || pktmbuf_pool == NULL || !ops)
-		return NULL;
+	/* Immediately return if KNI is already initialized */
+	if (kni_memzone_pool.initialized) {
+		RTE_LOG(WARNING, KNI, "Double call to rte_kni_init()");
+		return;
+	}
 
-	/* Check FD and open once */
+	if (max_kni_ifaces == 0) {
+		RTE_LOG(ERR, KNI, "Invalid number of max_kni_ifaces %d\n",
+							max_kni_ifaces);
+		RTE_LOG(ERR, KNI, "Unable to initialize KNI\n");
+		return;
+	}
+
+	/* Check FD and open */
 	if (kni_fd < 0) {
 		kni_fd = open("/dev/" KNI_DEVICE, O_RDWR);
 		if (kni_fd < 0) {
-			RTE_LOG(ERR, KNI, "Can not open /dev/%s\n",
-							KNI_DEVICE);
-			return NULL;
+			RTE_LOG(ERR, KNI,
+				"Can not open /dev/%s\n", KNI_DEVICE);
+			return;
 		}
 	}
 
-	rte_eth_dev_info_get(port_id, &eth_dev_info);
-	RTE_LOG(INFO, KNI, "pci: %02x:%02x:%02x \t %02x:%02x\n",
-					eth_dev_info.pci_dev->addr.bus,
-					eth_dev_info.pci_dev->addr.devid,
-					eth_dev_info.pci_dev->addr.function,
-					eth_dev_info.pci_dev->id.vendor_id,
-					eth_dev_info.pci_dev->id.device_id);
-	dev_info.bus = eth_dev_info.pci_dev->addr.bus;
-	dev_info.devid = eth_dev_info.pci_dev->addr.devid;
-	dev_info.function = eth_dev_info.pci_dev->addr.function;
-	dev_info.vendor_id = eth_dev_info.pci_dev->id.vendor_id;
-	dev_info.device_id = eth_dev_info.pci_dev->id.device_id;
-
-	ctx = rte_zmalloc("kni devs", sizeof(struct rte_kni), 0);
-	if (ctx == NULL)
-		rte_panic("Cannot allocate memory for kni dev\n");
-	memcpy(&ctx->ops, ops, sizeof(struct rte_kni_ops));
-
-	rte_snprintf(itf_name, IFNAMSIZ, "vEth%u", port_id);
-	rte_snprintf(ctx->name, IFNAMSIZ, itf_name);
-	rte_snprintf(dev_info.name, IFNAMSIZ, itf_name);
+	/* Allocate slot objects */
+	kni_memzone_pool.slots = (struct rte_kni_memzone_slot *)
+					rte_malloc(NULL,
+					sizeof(struct rte_kni_memzone_slot) *
+					max_kni_ifaces,
+					0);
+	KNI_MEM_CHECK(kni_memzone_pool.slots == NULL);
+
+	/* Initialize general pool variables */
+	kni_memzone_pool.initialized = 1;
+	kni_memzone_pool.max_ifaces = max_kni_ifaces;
+	kni_memzone_pool.free = &kni_memzone_pool.slots[0];
+	rte_spinlock_init(&kni_memzone_pool.mutex);
+
+	/* Pre-allocate all memzones of all the slots; panic on error */
+	for (i = 0; i < max_kni_ifaces; i++) {
+
+		/* Recover current slot */
+		it = &kni_memzone_pool.slots[i];
+		it->id = i;
+
+		/* Allocate KNI context */
+		snprintf(mz_name, RTE_MEMZONE_NAMESIZE, "KNI_INFO_%d", i);
+		mz = kni_memzone_reserve(mz_name, sizeof(struct rte_kni),
+					SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_ctx = mz;
+
+		/* TX RING */
+		snprintf(obj_name, OBJNAMSIZ, "kni_tx_%d", i);
+		mz = kni_memzone_reserve(obj_name, KNI_FIFO_SIZE,
+							SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_tx_q = mz;
+
+		/* RX RING */
+		snprintf(obj_name, OBJNAMSIZ, "kni_rx_%d", i);
+		mz = kni_memzone_reserve(obj_name, KNI_FIFO_SIZE,
+							SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_rx_q = mz;
+
+		/* ALLOC RING */
+		snprintf(obj_name, OBJNAMSIZ, "kni_alloc_%d", i);
+		mz = kni_memzone_reserve(obj_name, KNI_FIFO_SIZE,
+							SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_alloc_q = mz;
+
+		/* FREE RING */
+		snprintf(obj_name, OBJNAMSIZ, "kni_free_%d", i);
+		mz = kni_memzone_reserve(obj_name, KNI_FIFO_SIZE,
+							SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_free_q = mz;
+
+		/* Request RING */
+		snprintf(obj_name, OBJNAMSIZ, "kni_req_%d", i);
+		mz = kni_memzone_reserve(obj_name, KNI_FIFO_SIZE,
+							SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_req_q = mz;
+
+		/* Response RING */
+		snprintf(obj_name, OBJNAMSIZ, "kni_resp_%d", i);
+		mz = kni_memzone_reserve(obj_name, KNI_FIFO_SIZE,
+							SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_resp_q = mz;
+
+		/* Req/Resp sync mem area */
+		snprintf(obj_name, OBJNAMSIZ, "kni_sync_%d", i);
+		mz = kni_memzone_reserve(obj_name, KNI_FIFO_SIZE,
+							SOCKET_ID_ANY, 0);
+		KNI_MEM_CHECK(mz == NULL);
+		it->m_sync_addr = mz;
+
+		if ((i+1) == max_kni_ifaces) {
+			it->next = NULL;
+			kni_memzone_pool.free_tail = it;
+		} else
+			it->next = &kni_memzone_pool.slots[i+1];
+	}
 
+	return;
+
+kni_fail:
+	RTE_LOG(ERR, KNI, "Unable to allocate memory for max_kni_ifaces:%d."
+		"Increase the amount of hugepages memory\n", max_kni_ifaces);
+}
+
+
+struct rte_kni *
+rte_kni_alloc(struct rte_mempool *pktmbuf_pool,
+	      const struct rte_kni_conf *conf,
+	      struct rte_kni_ops *ops)
+{
+	int ret;
+	struct rte_kni_device_info dev_info;
+	struct rte_kni *ctx;
+	char intf_name[RTE_KNI_NAMESIZE];
+	const struct rte_memzone *mz;
+	struct rte_kni_memzone_slot *slot = NULL;
+
+	if (!pktmbuf_pool || !conf || !conf->name[0])
+		return NULL;
+
+	/* Check if KNI subsystem has been initialized */
+	if (kni_memzone_pool.initialized != 1) {
+		RTE_LOG(ERR, KNI, "KNI subsystem has not been initialized. Invoke rte_kni_init() first\n");
+		return NULL;
+	}
+
+	/* Get an available slot from the pool */
+	slot = kni_memzone_pool_alloc();
+	if (!slot) {
+		RTE_LOG(ERR, KNI, "Cannot allocate more KNI interfaces; increase the number of max_kni_ifaces(current %d) or release unusued ones.\n",
+			kni_memzone_pool.max_ifaces);
+		return NULL;
+	}
+
+	/* Recover ctx */
+	ctx = slot->m_ctx->addr;
+	snprintf(intf_name, RTE_KNI_NAMESIZE, "%s", conf->name);
+
+	if (ctx->in_use) {
+		RTE_LOG(ERR, KNI, "KNI %s is in use\n", ctx->name);
+		return NULL;
+	}
+	memset(ctx, 0, sizeof(struct rte_kni));
+	if (ops)
+		memcpy(&ctx->ops, ops, sizeof(struct rte_kni_ops));
+
+	memset(&dev_info, 0, sizeof(dev_info));
+	dev_info.bus = conf->addr.bus;
+	dev_info.devid = conf->addr.devid;
+	dev_info.function = conf->addr.function;
+	dev_info.vendor_id = conf->id.vendor_id;
+	dev_info.device_id = conf->id.device_id;
+	dev_info.core_id = conf->core_id;
+	dev_info.force_bind = conf->force_bind;
+	dev_info.group_id = conf->group_id;
+	dev_info.mbuf_size = conf->mbuf_size;
+
+	snprintf(ctx->name, RTE_KNI_NAMESIZE, "%s", intf_name);
+	snprintf(dev_info.name, RTE_KNI_NAMESIZE, "%s", intf_name);
+
+	RTE_LOG(INFO, KNI, "pci: %02x:%02x:%02x \t %02x:%02x\n",
+		dev_info.bus, dev_info.devid, dev_info.function,
+			dev_info.vendor_id, dev_info.device_id);
 	/* TX RING */
-	rte_snprintf(obj_name, OBJNAMSIZ, "kni_tx_%d", port_id);
-	mz = rte_memzone_reserve(obj_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
-	if (mz == NULL || mz->addr == NULL)
-		rte_panic("Cannot create kni_tx_%d queue\n", port_id);
+	mz = slot->m_tx_q;
 	ctx->tx_q = mz->addr;
 	kni_fifo_init(ctx->tx_q, KNI_FIFO_COUNT_MAX);
 	dev_info.tx_phys = mz->phys_addr;
 
 	/* RX RING */
-	rte_snprintf(obj_name, OBJNAMSIZ, "kni_rx_%d", port_id);
-	mz = rte_memzone_reserve(obj_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
-	if (mz == NULL || mz->addr == NULL)
-		rte_panic("Cannot create kni_rx_%d queue\n", port_id);
+	mz = slot->m_rx_q;
 	ctx->rx_q = mz->addr;
 	kni_fifo_init(ctx->rx_q, KNI_FIFO_COUNT_MAX);
 	dev_info.rx_phys = mz->phys_addr;
 
 	/* ALLOC RING */
-	rte_snprintf(obj_name, OBJNAMSIZ, "kni_alloc_%d", port_id);
-	mz = rte_memzone_reserve(obj_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
-	if (mz == NULL || mz->addr == NULL)
-		rte_panic("Cannot create kni_alloc_%d queue\n", port_id);
+	mz = slot->m_alloc_q;
 	ctx->alloc_q = mz->addr;
 	kni_fifo_init(ctx->alloc_q, KNI_FIFO_COUNT_MAX);
 	dev_info.alloc_phys = mz->phys_addr;
 
 	/* FREE RING */
-	rte_snprintf(obj_name, OBJNAMSIZ, "kni_free_%d", port_id);
-	mz = rte_memzone_reserve(obj_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
-	if (mz == NULL || mz->addr == NULL)
-		rte_panic("Cannot create kni_free_%d queue\n", port_id);
+	mz = slot->m_free_q;
 	ctx->free_q = mz->addr;
 	kni_fifo_init(ctx->free_q, KNI_FIFO_COUNT_MAX);
 	dev_info.free_phys = mz->phys_addr;
 
 	/* Request RING */
-	rte_snprintf(obj_name, OBJNAMSIZ, "kni_req_%d", port_id);
-	mz = rte_memzone_reserve(obj_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
-	if (mz == NULL || mz->addr == NULL)
-		rte_panic("Cannot create kni_req_%d ring\n", port_id);
+	mz = slot->m_req_q;
 	ctx->req_q = mz->addr;
 	kni_fifo_init(ctx->req_q, KNI_FIFO_COUNT_MAX);
 	dev_info.req_phys = mz->phys_addr;
 
 	/* Response RING */
-	rte_snprintf(obj_name, OBJNAMSIZ, "kni_resp_%d", port_id);
-	mz = rte_memzone_reserve(obj_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
-	if (mz == NULL || mz->addr == NULL)
-		rte_panic("Cannot create kni_resp_%d ring\n", port_id);
+	mz = slot->m_resp_q;
 	ctx->resp_q = mz->addr;
 	kni_fifo_init(ctx->resp_q, KNI_FIFO_COUNT_MAX);
 	dev_info.resp_phys = mz->phys_addr;
 
 	/* Req/Resp sync mem area */
-	rte_snprintf(obj_name, OBJNAMSIZ, "kni_sync_%d", port_id);
-	mz = rte_memzone_reserve(obj_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
-	if (mz == NULL || mz->addr == NULL)
-		rte_panic("Cannot create kni_sync_%d mem\n", port_id);
+	mz = slot->m_sync_addr;
 	ctx->sync_addr = mz->addr;
 	dev_info.sync_va = mz->addr;
 	dev_info.sync_phys = mz->phys_addr;
 
-	/* MBUF mempool */
-	mz = rte_memzone_lookup("MP_mbuf_pool");
-	if (mz == NULL) {
-		RTE_LOG(ERR, KNI, "Can not find MP_mbuf_pool\n");
-		goto fail;
-	}
-	dev_info.mbuf_va = mz->addr;
-	dev_info.mbuf_phys = mz->phys_addr;
 	ctx->pktmbuf_pool = pktmbuf_pool;
-	ctx->port_id = port_id;
-	ctx->mbuf_size = mbuf_size;
+	ctx->group_id = conf->group_id;
+	ctx->slot_id = slot->id;
+	ctx->mbuf_size = conf->mbuf_size;
 
-	/* Configure the buffer size which will be checked in kernel module */
-	dev_info.mbuf_size = ctx->mbuf_size;
+	ret = ioctl(kni_fd, RTE_KNI_IOCTL_CREATE, &dev_info);
+	KNI_MEM_CHECK(ret < 0);
 
-	if (ioctl(kni_fd, RTE_KNI_IOCTL_CREATE, &dev_info) < 0) {
-		RTE_LOG(ERR, KNI, "Fail to create kni device\n");
-		goto fail;
-	}
+	ctx->in_use = 1;
+
+	/* Allocate mbufs and then put them into alloc_q */
+	kni_allocate_mbufs(ctx);
 
 	return ctx;
 
-fail:
-	if (ctx != NULL)
-		rte_free(ctx);
+kni_fail:
+	if (slot)
+		kni_memzone_pool_release(&kni_memzone_pool.slots[slot->id]);
 
 	return NULL;
 }
 
-/**
- * It is called in the same lcore of receiving packets, and polls the request
- * mbufs sent from kernel space. Then analyzes it and calls the specific
- * actions for the specific requests. Finally constructs the response mbuf and
- * puts it back to the resp_q.
- */
-static int
-kni_request_handler(struct rte_kni *kni)
+static void
+kni_free_fifo(struct rte_kni_fifo *fifo)
+{
+	int ret;
+	struct rte_mbuf *pkt;
+
+	do {
+		ret = kni_fifo_get(fifo, (void **)&pkt, 1);
+		if (ret)
+			rte_pktmbuf_free(pkt);
+	} while (ret);
+}
+
+static void
+kni_free_fifo_phy(struct rte_kni_fifo *fifo)
+{
+	void *mbuf_phys;
+	int ret;
+
+	do {
+		ret = kni_fifo_get(fifo, &mbuf_phys, 1);
+		/*
+		 * TODO: free mbufs
+		 */
+	} while (ret);
+}
+
+int
+rte_kni_release(struct rte_kni *kni)
+{
+	struct rte_kni_device_info dev_info;
+	uint32_t slot_id;
+
+	if (!kni || !kni->in_use)
+		return -1;
+
+	snprintf(dev_info.name, sizeof(dev_info.name), "%s", kni->name);
+	if (ioctl(kni_fd, RTE_KNI_IOCTL_RELEASE, &dev_info) < 0) {
+		RTE_LOG(ERR, KNI, "Fail to release kni device\n");
+		return -1;
+	}
+
+	/* mbufs in all fifo should be released, except request/response */
+	kni_free_fifo(kni->tx_q);
+	kni_free_fifo_phy(kni->rx_q);
+	kni_free_fifo_phy(kni->alloc_q);
+	kni_free_fifo(kni->free_q);
+
+	slot_id = kni->slot_id;
+
+	/* Memset the KNI struct */
+	memset(kni, 0, sizeof(struct rte_kni));
+
+	/* Release memzone */
+	if (slot_id > kni_memzone_pool.max_ifaces) {
+		RTE_LOG(ERR, KNI, "KNI pool: corrupted slot ID: %d, max: %d\n",
+			slot_id, kni_memzone_pool.max_ifaces);
+		return -1;
+	}
+	kni_memzone_pool_release(&kni_memzone_pool.slots[slot_id]);
+
+	return 0;
+}
+
+int
+rte_kni_handle_request(struct rte_kni *kni)
 {
 	unsigned ret;
 	struct rte_kni_request *req;
@@ -251,20 +517,21 @@ kni_request_handler(struct rte_kni *kni)
 		return 0; /* It is OK of can not getting the request mbuf */
 
 	if (req != kni->sync_addr) {
-		rte_panic("Wrong req pointer %p\n", req);
+		RTE_LOG(ERR, KNI, "Wrong req pointer %p\n", req);
+		return -1;
 	}
 
 	/* Analyze the request and call the relevant actions for it */
 	switch (req->req_id) {
 	case RTE_KNI_REQ_CHANGE_MTU: /* Change MTU */
 		if (kni->ops.change_mtu)
-			req->result = kni->ops.change_mtu(kni->port_id,
+			req->result = kni->ops.change_mtu(kni->ops.port_id,
 							req->new_mtu);
 		break;
 	case RTE_KNI_REQ_CFG_NETWORK_IF: /* Set network interface up/down */
 		if (kni->ops.config_network_if)
-			req->result = kni->ops.config_network_if(kni->port_id,
-								req->if_up);
+			req->result = kni->ops.config_network_if(\
+					kni->ops.port_id, req->if_up);
 		break;
 	default:
 		RTE_LOG(ERR, KNI, "Unknown request id %u\n", req->req_id);
@@ -282,17 +549,29 @@ kni_request_handler(struct rte_kni *kni)
 	return 0;
 }
 
+static void *
+va2pa(struct rte_mbuf *m)
+{
+	return (void *)((unsigned long)m -
+			((unsigned long)m->buf_addr -
+			 (unsigned long)m->buf_physaddr));
+}
+
 unsigned
 rte_kni_tx_burst(struct rte_kni *kni, struct rte_mbuf **mbufs, unsigned num)
 {
-	unsigned ret = kni_fifo_put(kni->rx_q, (void **)mbufs, num);
+	void *phy_mbufs[num];
+	unsigned int ret;
+	unsigned int i;
+
+	for (i = 0; i < num; i++)
+		phy_mbufs[i] = va2pa(mbufs[i]);
+
+	ret = kni_fifo_put(kni->rx_q, phy_mbufs, num);
 
 	/* Get mbufs from free_q and then free them */
 	kni_free_mbufs(kni);
 
-	/* Handle the requests from kernel space */
-	kni_request_handler(kni);
-
 	return ret;
 }
 
@@ -301,8 +580,9 @@ rte_kni_rx_burst(struct rte_kni *kni, struct rte_mbuf **mbufs, unsigned num)
 {
 	unsigned ret = kni_fifo_get(kni->tx_q, (void **)mbufs, num);
 
-	/* Allocate mbufs and then put them into alloc_q */
-	kni_allocate_mbufs(kni);
+	/* If buffers removed, allocate mbufs and then put them into alloc_q */
+	if (ret)
+		kni_allocate_mbufs(kni);
 
 	return ret;
 }
@@ -325,6 +605,22 @@ kni_allocate_mbufs(struct rte_kni *kni)
 {
 	int i, ret;
 	struct rte_mbuf *pkts[MAX_MBUF_BURST_NUM];
+	void *phys[MAX_MBUF_BURST_NUM];
+
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pool) !=
+			 offsetof(struct rte_kni_mbuf, pool));
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_addr) !=
+			 offsetof(struct rte_kni_mbuf, buf_addr));
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, next) !=
+			 offsetof(struct rte_kni_mbuf, next));
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_off) !=
+			 offsetof(struct rte_kni_mbuf, data_off));
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+			 offsetof(struct rte_kni_mbuf, data_len));
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+			 offsetof(struct rte_kni_mbuf, pkt_len));
+	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
+			 offsetof(struct rte_kni_mbuf, ol_flags));
 
 	/* Check if pktmbuf pool has been configured */
 	if (kni->pktmbuf_pool == NULL) {
@@ -339,13 +635,14 @@ kni_allocate_mbufs(struct rte_kni *kni)
 			RTE_LOG(ERR, KNI, "Out of memory\n");
 			break;
 		}
+		phys[i] = va2pa(pkts[i]);
 	}
 
 	/* No pkt mbuf alocated */
 	if (i <= 0)
 		return;
 
-	ret = kni_fifo_put(kni->alloc_q, (void **)pkts, i);
+	ret = kni_fifo_put(kni->alloc_q, phys, i);
 
 	/* Check if any mbufs not put into alloc_q, and then free them */
 	if (ret >= 0 && ret < i && ret < MAX_MBUF_BURST_NUM) {
@@ -356,12 +653,88 @@ kni_allocate_mbufs(struct rte_kni *kni)
 	}
 }
 
-uint8_t
-rte_kni_get_port_id(struct rte_kni *kni)
+struct rte_kni *
+rte_kni_get(const char *name)
 {
-	if (kni == NULL)
-		return ~0x0;
+	uint32_t i;
+	struct rte_kni_memzone_slot *it;
+	struct rte_kni *kni;
+
+	/* Note: could be improved perf-wise if necessary */
+	for (i = 0; i < kni_memzone_pool.max_ifaces; i++) {
+		it = &kni_memzone_pool.slots[i];
+		if (it->in_use == 0)
+			continue;
+		kni = it->m_ctx->addr;
+		if (strncmp(kni->name, name, RTE_KNI_NAMESIZE) == 0)
+			return kni;
+	}
+
+	return NULL;
+}
 
-	return kni->port_id;
+const char *
+rte_kni_get_name(const struct rte_kni *kni)
+{
+	return kni->name;
 }
 
+static enum kni_ops_status
+kni_check_request_register(struct rte_kni_ops *ops)
+{
+	/* check if KNI request ops has been registered*/
+	if( NULL == ops )
+		return KNI_REQ_NO_REGISTER;
+
+	if((NULL == ops->change_mtu) && (NULL == ops->config_network_if))
+		return KNI_REQ_NO_REGISTER;
+
+	return KNI_REQ_REGISTERED;
+}
+
+int
+rte_kni_register_handlers(struct rte_kni *kni,struct rte_kni_ops *ops)
+{
+	enum kni_ops_status req_status;
+
+	if (NULL == ops) {
+		RTE_LOG(ERR, KNI, "Invalid KNI request operation.\n");
+		return -1;
+	}
+
+	if (NULL == kni) {
+		RTE_LOG(ERR, KNI, "Invalid kni info.\n");
+		return -1;
+	}
+
+	req_status = kni_check_request_register(&kni->ops);
+	if ( KNI_REQ_REGISTERED == req_status) {
+		RTE_LOG(ERR, KNI, "The KNI request operation has already registered.\n");
+		return -1;
+	}
+
+	memcpy(&kni->ops, ops, sizeof(struct rte_kni_ops));
+	return 0;
+}
+
+int
+rte_kni_unregister_handlers(struct rte_kni *kni)
+{
+	if (NULL == kni) {
+		RTE_LOG(ERR, KNI, "Invalid kni info.\n");
+		return -1;
+	}
+
+	kni->ops.change_mtu = NULL;
+	kni->ops.config_network_if = NULL;
+	return 0;
+}
+void
+rte_kni_close(void)
+{
+	if (kni_fd < 0)
+		return;
+
+	close(kni_fd);
+	kni_fd = -1;
+}