[ceph.git] / ceph / src / dpdk / lib / librte_ip_frag / rte_ipv4_fragmentation.c

/*-
 *   BSD LICENSE
 *
 *   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
 *   are met:
 *
 *     * 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
 *       distribution.
 *     * 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
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stddef.h>
#include <errno.h>

#include <rte_memcpy.h>
#include <rte_mempool.h>
#include <rte_debug.h>

#include "ip_frag_common.h"

/* Fragment Offset */
#define	IPV4_HDR_DF_SHIFT			14
#define	IPV4_HDR_MF_SHIFT			13
#define	IPV4_HDR_FO_SHIFT			3

#define	IPV4_HDR_DF_MASK			(1 << IPV4_HDR_DF_SHIFT)
#define	IPV4_HDR_MF_MASK			(1 << IPV4_HDR_MF_SHIFT)

#define	IPV4_HDR_FO_MASK			((1 << IPV4_HDR_FO_SHIFT) - 1)

static inline void __fill_ipv4hdr_frag(struct ipv4_hdr *dst,
		const struct ipv4_hdr *src, uint16_t len, uint16_t fofs,
		uint16_t dofs, uint32_t mf)
{
	rte_memcpy(dst, src, sizeof(*dst));
	fofs = (uint16_t)(fofs + (dofs >> IPV4_HDR_FO_SHIFT));
	fofs = (uint16_t)(fofs | mf << IPV4_HDR_MF_SHIFT);
	dst->fragment_offset = rte_cpu_to_be_16(fofs);
	dst->total_length = rte_cpu_to_be_16(len);
	dst->hdr_checksum = 0;
}

static inline void __free_fragments(struct rte_mbuf *mb[], uint32_t num)
{
	uint32_t i;
	for (i = 0; i != num; i++)
		rte_pktmbuf_free(mb[i]);
}

/**
 * IPv4 fragmentation.
 *
 * This function implements the fragmentation of IPv4 packets.
 *
 * @param pkt_in
 *   The input packet.
 * @param pkts_out
 *   Array storing the output fragments.
 * @param mtu_size
 *   Size in bytes of the Maximum Transfer Unit (MTU) for the outgoing IPv4
 *   datagrams. This value includes the size of the IPv4 header.
 * @param pool_direct
 *   MBUF pool used for allocating direct buffers for the output fragments.
 * @param pool_indirect
 *   MBUF pool used for allocating indirect buffers for the output fragments.
 * @return
 *   Upon successful completion - number of output fragments placed
 *   in the pkts_out array.
 *   Otherwise - (-1) * <errno>.
 */
int32_t
rte_ipv4_fragment_packet(struct rte_mbuf *pkt_in,
	struct rte_mbuf **pkts_out,
	uint16_t nb_pkts_out,
	uint16_t mtu_size,
	struct rte_mempool *pool_direct,
	struct rte_mempool *pool_indirect)
{
	struct rte_mbuf *in_seg = NULL;
	struct ipv4_hdr *in_hdr;
	uint32_t out_pkt_pos, in_seg_data_pos;
	uint32_t more_in_segs;
	uint16_t fragment_offset, flag_offset, frag_size;

	frag_size = (uint16_t)(mtu_size - sizeof(struct ipv4_hdr));

	/* Fragment size should be a multiply of 8. */
	RTE_ASSERT((frag_size & IPV4_HDR_FO_MASK) == 0);

	in_hdr = rte_pktmbuf_mtod(pkt_in, struct ipv4_hdr *);
	flag_offset = rte_cpu_to_be_16(in_hdr->fragment_offset);

	/* If Don't Fragment flag is set */
	if (unlikely ((flag_offset & IPV4_HDR_DF_MASK) != 0))
		return -ENOTSUP;

	/* Check that pkts_out is big enough to hold all fragments */
	if (unlikely(frag_size * nb_pkts_out <
	    (uint16_t)(pkt_in->pkt_len - sizeof (struct ipv4_hdr))))
		return -EINVAL;

	in_seg = pkt_in;
	in_seg_data_pos = sizeof(struct ipv4_hdr);
	out_pkt_pos = 0;
	fragment_offset = 0;

	more_in_segs = 1;
	while (likely(more_in_segs)) {
		struct rte_mbuf *out_pkt = NULL, *out_seg_prev = NULL;
		uint32_t more_out_segs;
		struct ipv4_hdr *out_hdr;

		/* Allocate direct buffer */
		out_pkt = rte_pktmbuf_alloc(pool_direct);
		if (unlikely(out_pkt == NULL)) {
			__free_fragments(pkts_out, out_pkt_pos);
			return -ENOMEM;
		}

		/* Reserve space for the IP header that will be built later */
		out_pkt->data_len = sizeof(struct ipv4_hdr);
		out_pkt->pkt_len = sizeof(struct ipv4_hdr);

		out_seg_prev = out_pkt;
		more_out_segs = 1;
		while (likely(more_out_segs && more_in_segs)) {
			struct rte_mbuf *out_seg = NULL;
			uint32_t len;

			/* Allocate indirect buffer */
			out_seg = rte_pktmbuf_alloc(pool_indirect);
			if (unlikely(out_seg == NULL)) {
				rte_pktmbuf_free(out_pkt);
				__free_fragments(pkts_out, out_pkt_pos);
				return -ENOMEM;
			}
			out_seg_prev->next = out_seg;
			out_seg_prev = out_seg;

			/* Prepare indirect buffer */
			rte_pktmbuf_attach(out_seg, in_seg);
			len = mtu_size - out_pkt->pkt_len;
			if (len > (in_seg->data_len - in_seg_data_pos)) {
				len = in_seg->data_len - in_seg_data_pos;
			}
			out_seg->data_off = in_seg->data_off + in_seg_data_pos;
			out_seg->data_len = (uint16_t)len;
			out_pkt->pkt_len = (uint16_t)(len +
			    out_pkt->pkt_len);
			out_pkt->nb_segs += 1;
			in_seg_data_pos += len;

			/* Current output packet (i.e. fragment) done ? */
			if (unlikely(out_pkt->pkt_len >= mtu_size))
				more_out_segs = 0;

			/* Current input segment done ? */
			if (unlikely(in_seg_data_pos == in_seg->data_len)) {
				in_seg = in_seg->next;
				in_seg_data_pos = 0;

				if (unlikely(in_seg == NULL))
					more_in_segs = 0;
			}
		}

		/* Build the IP header */

		out_hdr = rte_pktmbuf_mtod(out_pkt, struct ipv4_hdr *);

		__fill_ipv4hdr_frag(out_hdr, in_hdr,
		    (uint16_t)out_pkt->pkt_len,
		    flag_offset, fragment_offset, more_in_segs);

		fragment_offset = (uint16_t)(fragment_offset +
		    out_pkt->pkt_len - sizeof(struct ipv4_hdr));

		out_pkt->ol_flags |= PKT_TX_IP_CKSUM;
		out_pkt->l3_len = sizeof(struct ipv4_hdr);

		/* Write the fragment to the output list */
		pkts_out[out_pkt_pos] = out_pkt;
		out_pkt_pos ++;
	}

	return out_pkt_pos;
}
Commit	Line	Data
7c673cae FG	1	/*-
	2	* BSD LICENSE
	3	*
	4	* Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
	5	* All rights reserved.
	6	*
	7	* Redistribution and use in source and binary forms, with or without
	8	* modification, are permitted provided that the following conditions
	9	* are met:
	10	*
	11	* * Redistributions of source code must retain the above copyright
	12	* notice, this list of conditions and the following disclaimer.
	13	* * Redistributions in binary form must reproduce the above copyright
	14	* notice, this list of conditions and the following disclaimer in
	15	* the documentation and/or other materials provided with the
	16	* distribution.
	17	* * Neither the name of Intel Corporation nor the names of its
	18	* contributors may be used to endorse or promote products derived
	19	* from this software without specific prior written permission.
	20	*
	21	* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
	22	* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
	23	* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
	24	* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
	25	* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
	26	* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
	27	* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
	28	* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
	29	* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
	30	* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
	31	* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
	32	*/
	33
	34	#include <stddef.h>
	35	#include <errno.h>
	36
	37	#include <rte_memcpy.h>
	38	#include <rte_mempool.h>
	39	#include <rte_debug.h>
	40
	41	#include "ip_frag_common.h"
	42
	43	/* Fragment Offset */
	44	#define IPV4_HDR_DF_SHIFT 14
	45	#define IPV4_HDR_MF_SHIFT 13
	46	#define IPV4_HDR_FO_SHIFT 3
	47
	48	#define IPV4_HDR_DF_MASK (1 << IPV4_HDR_DF_SHIFT)
	49	#define IPV4_HDR_MF_MASK (1 << IPV4_HDR_MF_SHIFT)
	50
	51	#define IPV4_HDR_FO_MASK ((1 << IPV4_HDR_FO_SHIFT) - 1)
	52
	53	static inline void __fill_ipv4hdr_frag(struct ipv4_hdr *dst,
	54	const struct ipv4_hdr *src, uint16_t len, uint16_t fofs,
	55	uint16_t dofs, uint32_t mf)
	56	{
	57	rte_memcpy(dst, src, sizeof(*dst));
	58	fofs = (uint16_t)(fofs + (dofs >> IPV4_HDR_FO_SHIFT));
	59	fofs = (uint16_t)(fofs \| mf << IPV4_HDR_MF_SHIFT);
	60	dst->fragment_offset = rte_cpu_to_be_16(fofs);
	61	dst->total_length = rte_cpu_to_be_16(len);
	62	dst->hdr_checksum = 0;
	63	}
	64
65	static inline void __free_fragments(struct rte_mbuf *mb[], uint32_t num)
66	{
67	uint32_t i;
68	for (i = 0; i != num; i++)
69	rte_pktmbuf_free(mb[i]);
70	}
71
72	/**
73	* IPv4 fragmentation.
74	*
75	* This function implements the fragmentation of IPv4 packets.
76	*
77	* @param pkt_in
78	* The input packet.
79	* @param pkts_out
80	* Array storing the output fragments.
81	* @param mtu_size
82	* Size in bytes of the Maximum Transfer Unit (MTU) for the outgoing IPv4
83	* datagrams. This value includes the size of the IPv4 header.
84	* @param pool_direct
85	* MBUF pool used for allocating direct buffers for the output fragments.
86	* @param pool_indirect
87	* MBUF pool used for allocating indirect buffers for the output fragments.
88	* @return
89	* Upon successful completion - number of output fragments placed
90	* in the pkts_out array.
91	* Otherwise - (-1) * <errno>.
92	*/
93	int32_t
94	rte_ipv4_fragment_packet(struct rte_mbuf *pkt_in,
95	struct rte_mbuf **pkts_out,
96	uint16_t nb_pkts_out,
97	uint16_t mtu_size,
98	struct rte_mempool *pool_direct,
99	struct rte_mempool *pool_indirect)
100	{
101	struct rte_mbuf *in_seg = NULL;
102	struct ipv4_hdr *in_hdr;
103	uint32_t out_pkt_pos, in_seg_data_pos;
104	uint32_t more_in_segs;
105	uint16_t fragment_offset, flag_offset, frag_size;
106
107	frag_size = (uint16_t)(mtu_size - sizeof(struct ipv4_hdr));
108
109	/* Fragment size should be a multiply of 8. */
110	RTE_ASSERT((frag_size & IPV4_HDR_FO_MASK) == 0);
111
112	in_hdr = rte_pktmbuf_mtod(pkt_in, struct ipv4_hdr *);
113	flag_offset = rte_cpu_to_be_16(in_hdr->fragment_offset);
114
115	/* If Don't Fragment flag is set */
116	if (unlikely ((flag_offset & IPV4_HDR_DF_MASK) != 0))
117	return -ENOTSUP;
118
119	/* Check that pkts_out is big enough to hold all fragments */
120	if (unlikely(frag_size * nb_pkts_out <
121	(uint16_t)(pkt_in->pkt_len - sizeof (struct ipv4_hdr))))
122	return -EINVAL;
123
124	in_seg = pkt_in;
125	in_seg_data_pos = sizeof(struct ipv4_hdr);
126	out_pkt_pos = 0;
127	fragment_offset = 0;
128
129	more_in_segs = 1;
130	while (likely(more_in_segs)) {
131	struct rte_mbuf out_pkt = NULL, out_seg_prev = NULL;
132	uint32_t more_out_segs;
133	struct ipv4_hdr *out_hdr;
134
135	/* Allocate direct buffer */
136	out_pkt = rte_pktmbuf_alloc(pool_direct);
137	if (unlikely(out_pkt == NULL)) {
138	__free_fragments(pkts_out, out_pkt_pos);
139	return -ENOMEM;
140	}
141
142	/* Reserve space for the IP header that will be built later */
143	out_pkt->data_len = sizeof(struct ipv4_hdr);
144	out_pkt->pkt_len = sizeof(struct ipv4_hdr);
145
146	out_seg_prev = out_pkt;
147	more_out_segs = 1;
148	while (likely(more_out_segs && more_in_segs)) {
149	struct rte_mbuf *out_seg = NULL;
150	uint32_t len;
151
152	/* Allocate indirect buffer */
153	out_seg = rte_pktmbuf_alloc(pool_indirect);
154	if (unlikely(out_seg == NULL)) {
155	rte_pktmbuf_free(out_pkt);
156	__free_fragments(pkts_out, out_pkt_pos);
157	return -ENOMEM;
158	}
159	out_seg_prev->next = out_seg;
160	out_seg_prev = out_seg;
161
162	/* Prepare indirect buffer */
163	rte_pktmbuf_attach(out_seg, in_seg);
164	len = mtu_size - out_pkt->pkt_len;
165	if (len > (in_seg->data_len - in_seg_data_pos)) {
166	len = in_seg->data_len - in_seg_data_pos;
167	}
168	out_seg->data_off = in_seg->data_off + in_seg_data_pos;
169	out_seg->data_len = (uint16_t)len;
170	out_pkt->pkt_len = (uint16_t)(len +
171	out_pkt->pkt_len);
172	out_pkt->nb_segs += 1;
173	in_seg_data_pos += len;
174
175	/* Current output packet (i.e. fragment) done ? */
176	if (unlikely(out_pkt->pkt_len >= mtu_size))
177	more_out_segs = 0;
178
179	/* Current input segment done ? */
180	if (unlikely(in_seg_data_pos == in_seg->data_len)) {
181	in_seg = in_seg->next;
182	in_seg_data_pos = 0;
183
184	if (unlikely(in_seg == NULL))
185	more_in_segs = 0;
186	}
187	}
188
189	/* Build the IP header */
190
191	out_hdr = rte_pktmbuf_mtod(out_pkt, struct ipv4_hdr *);
192
193	__fill_ipv4hdr_frag(out_hdr, in_hdr,
194	(uint16_t)out_pkt->pkt_len,
195	flag_offset, fragment_offset, more_in_segs);
196
197	fragment_offset = (uint16_t)(fragment_offset +
198	out_pkt->pkt_len - sizeof(struct ipv4_hdr));
199
200	out_pkt->ol_flags \|= PKT_TX_IP_CKSUM;
201	out_pkt->l3_len = sizeof(struct ipv4_hdr);
202
203	/* Write the fragment to the output list */
204	pkts_out[out_pkt_pos] = out_pkt;
205	out_pkt_pos ++;
206	}
207
208	return out_pkt_pos;
209	}