X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=06eceba374a9b4a8c33a01dbaa53078b551fae94;hb=d27a6261875d203424e93d7316a0e92852f367b5;hp=4476d75379fd2578ce96d885034b772125a8958e;hpb=4fb7e803eb1af3f37455dc92b2ae24616dd28fb9;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 4476d75379..06eceba374 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -1,35 +1,6 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. - * Copyright 2014 6WIND S.A. - * 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. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2014 Intel Corporation. + * Copyright 2014 6WIND S.A. */ #ifndef _RTE_MBUF_H_ @@ -44,6 +15,13 @@ * buffers. The message buffers are stored in a mempool, using the * RTE mempool library. * + * The preferred way to create a mbuf pool is to use + * rte_pktmbuf_pool_create(). However, in some situations, an + * application may want to have more control (ex: populate the pool with + * specific memory), in this case it is possible to use functions from + * rte_mempool. See how rte_pktmbuf_pool_create() is implemented for + * details. + * * This library provides an API to allocate/free packet mbufs, which are * used to carry network packets. * @@ -54,7 +32,9 @@ */ #include +#include #include +#include #include #include #include @@ -82,12 +62,13 @@ extern "C" { */ /** - * RX packet is a 802.1q VLAN packet. This flag was set by PMDs when - * the packet is recognized as a VLAN, but the behavior between PMDs - * was not the same. This flag is kept for some time to avoid breaking - * applications and should be replaced by PKT_RX_VLAN_STRIPPED. + * The RX packet is a 802.1q VLAN packet, and the tci has been + * saved in in mbuf->vlan_tci. + * If the flag PKT_RX_VLAN_STRIPPED is also present, the VLAN + * header has been stripped from mbuf data, else it is still + * present. */ -#define PKT_RX_VLAN_PKT (1ULL << 0) +#define PKT_RX_VLAN (1ULL << 0) #define PKT_RX_RSS_HASH (1ULL << 1) /**< RX packet with RSS hash result. */ #define PKT_RX_FDIR (1ULL << 2) /**< RX packet with FDIR match indicate. */ @@ -116,6 +97,7 @@ extern "C" { * A vlan has been stripped by the hardware and its tci is saved in * mbuf->vlan_tci. This can only happen if vlan stripping is enabled * in the RX configuration of the PMD. + * When PKT_RX_VLAN_STRIPPED is set, PKT_RX_VLAN must also be set. */ #define PKT_RX_VLAN_STRIPPED (1ULL << 6) @@ -158,18 +140,12 @@ extern "C" { * The 2 vlans have been stripped by the hardware and their tci are * saved in mbuf->vlan_tci (inner) and mbuf->vlan_tci_outer (outer). * This can only happen if vlan stripping is enabled in the RX - * configuration of the PMD. If this flag is set, PKT_RX_VLAN_STRIPPED - * must also be set. + * configuration of the PMD. If this flag is set, + * When PKT_RX_QINQ_STRIPPED is set, the flags (PKT_RX_VLAN | + * PKT_RX_VLAN_STRIPPED | PKT_RX_QINQ) must also be set. */ #define PKT_RX_QINQ_STRIPPED (1ULL << 15) -/** - * Deprecated. - * RX packet with double VLAN stripped. - * This flag is replaced by PKT_RX_QINQ_STRIPPED. - */ -#define PKT_RX_QINQ_PKT PKT_RX_QINQ_STRIPPED - /** * When packets are coalesced by a hardware or virtual driver, this flag * can be set in the RX mbuf, meaning that the m->tso_segsz field is @@ -177,10 +153,52 @@ extern "C" { */ #define PKT_RX_LRO (1ULL << 16) +/** + * Indicate that the timestamp field in the mbuf is valid. + */ +#define PKT_RX_TIMESTAMP (1ULL << 17) + +/** + * Indicate that security offload processing was applied on the RX packet. + */ +#define PKT_RX_SEC_OFFLOAD (1ULL << 18) + +/** + * Indicate that security offload processing failed on the RX packet. + */ +#define PKT_RX_SEC_OFFLOAD_FAILED (1ULL << 19) + +/** + * The RX packet is a double VLAN, and the outer tci has been + * saved in in mbuf->vlan_tci_outer. + * If the flag PKT_RX_QINQ_STRIPPED is also present, both VLANs + * headers have been stripped from mbuf data, else they are still + * present. + */ +#define PKT_RX_QINQ (1ULL << 20) + /* add new RX flags here */ /* add new TX flags here */ +/** + * UDP Fragmentation Offload flag. This flag is used for enabling UDP + * fragmentation in SW or in HW. When use UFO, mbuf->tso_segsz is used + * to store the MSS of UDP fragments. + */ +#define PKT_TX_UDP_SEG (1ULL << 42) + +/** + * Request security offload processing on the TX packet. + */ +#define PKT_TX_SEC_OFFLOAD (1ULL << 43) + +/** + * Offload the MACsec. This flag must be set by the application to enable + * this offload feature for a packet to be transmitted. + */ +#define PKT_TX_MACSEC (1ULL << 44) + /** * Bits 45:48 used for the tunnel type. * When doing Tx offload like TSO or checksum, the HW needs to configure the @@ -190,13 +208,17 @@ extern "C" { #define PKT_TX_TUNNEL_GRE (0x2ULL << 45) #define PKT_TX_TUNNEL_IPIP (0x3ULL << 45) #define PKT_TX_TUNNEL_GENEVE (0x4ULL << 45) +/**< TX packet with MPLS-in-UDP RFC 7510 header. */ +#define PKT_TX_TUNNEL_MPLSINUDP (0x5ULL << 45) /* add new TX TUNNEL type here */ #define PKT_TX_TUNNEL_MASK (0xFULL << 45) /** * Second VLAN insertion (QinQ) flag. */ -#define PKT_TX_QINQ_PKT (1ULL << 49) /**< TX packet with double VLAN inserted. */ +#define PKT_TX_QINQ (1ULL << 49) /**< TX packet with double VLAN inserted. */ +/* this old name is deprecated */ +#define PKT_TX_QINQ_PKT PKT_TX_QINQ /** * TCP segmentation offload. To enable this offload feature for a @@ -257,7 +279,12 @@ extern "C" { */ #define PKT_TX_IPV6 (1ULL << 56) -#define PKT_TX_VLAN_PKT (1ULL << 57) /**< TX packet is a 802.1q VLAN packet. */ +/** + * TX packet is a 802.1q VLAN packet. + */ +#define PKT_TX_VLAN (1ULL << 57) +/* this old name is deprecated */ +#define PKT_TX_VLAN_PKT PKT_TX_VLAN /** * Offload the IP checksum of an external header in the hardware. The @@ -292,17 +319,17 @@ extern "C" { PKT_TX_L4_MASK | \ PKT_TX_OUTER_IP_CKSUM | \ PKT_TX_TCP_SEG | \ + PKT_TX_IEEE1588_TMST | \ PKT_TX_QINQ_PKT | \ PKT_TX_VLAN_PKT | \ - PKT_TX_TUNNEL_MASK) + PKT_TX_TUNNEL_MASK | \ + PKT_TX_MACSEC | \ + PKT_TX_SEC_OFFLOAD) #define __RESERVED (1ULL << 61) /**< reserved for future mbuf use */ #define IND_ATTACHED_MBUF (1ULL << 62) /**< Indirect attached mbuf */ -/* Use final bit of flags to indicate a control mbuf */ -#define CTRL_MBUF_FLAG (1ULL << 63) /**< Mbuf contains control data */ - /** Alignment constraint of mbuf private area. */ #define RTE_MBUF_PRIV_ALIGN 8 @@ -383,16 +410,25 @@ struct rte_mbuf { MARKER cacheline0; void *buf_addr; /**< Virtual address of segment buffer. */ - phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */ - - uint16_t buf_len; /**< Length of segment buffer. */ + /** + * Physical address of segment buffer. + * Force alignment to 8-bytes, so as to ensure we have the exact + * same mbuf cacheline0 layout for 32-bit and 64-bit. This makes + * working on vector drivers easier. + */ + RTE_STD_C11 + union { + rte_iova_t buf_iova; + rte_iova_t buf_physaddr; /**< deprecated */ + } __rte_aligned(sizeof(rte_iova_t)); - /* next 6 bytes are initialised on RX descriptor rearm */ - MARKER8 rearm_data; + /* next 8 bytes are initialised on RX descriptor rearm */ + MARKER64 rearm_data; uint16_t data_off; /** - * 16-bit Reference counter. + * Reference counter. Its size should at least equal to the size + * of port field (16 bits), to support zero-copy broadcast. * It should only be accessed using the following functions: * rte_mbuf_refcnt_update(), rte_mbuf_refcnt_read(), and * rte_mbuf_refcnt_set(). The functionality of these functions (atomic, @@ -404,8 +440,10 @@ struct rte_mbuf { rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ uint16_t refcnt; /**< Non-atomically accessed refcnt */ }; - uint8_t nb_segs; /**< Number of segments. */ - uint8_t port; /**< Input port. */ + uint16_t nb_segs; /**< Number of segments. */ + + /** Input port (16 bits to support more than 256 virtual ports). */ + uint16_t port; uint64_t ol_flags; /**< Offload features. */ @@ -427,15 +465,28 @@ struct rte_mbuf { uint32_t l3_type:4; /**< (Outer) L3 type. */ uint32_t l4_type:4; /**< (Outer) L4 type. */ uint32_t tun_type:4; /**< Tunnel type. */ - uint32_t inner_l2_type:4; /**< Inner L2 type. */ - uint32_t inner_l3_type:4; /**< Inner L3 type. */ + RTE_STD_C11 + union { + uint8_t inner_esp_next_proto; + /**< ESP next protocol type, valid if + * RTE_PTYPE_TUNNEL_ESP tunnel type is set + * on both Tx and Rx. + */ + __extension__ + struct { + uint8_t inner_l2_type:4; + /**< Inner L2 type. */ + uint8_t inner_l3_type:4; + /**< Inner L3 type. */ + }; + }; uint32_t inner_l4_type:4; /**< Inner L4 type. */ }; }; uint32_t pkt_len; /**< Total pkt len: sum of all segments. */ uint16_t data_len; /**< Amount of data in segment buffer. */ - /** VLAN TCI (CPU order), valid if PKT_RX_VLAN_STRIPPED is set. */ + /** VLAN TCI (CPU order), valid if PKT_RX_VLAN is set. */ uint16_t vlan_tci; union { @@ -461,11 +512,16 @@ struct rte_mbuf { uint32_t usr; /**< User defined tags. See rte_distributor_process() */ } hash; /**< hash information */ - uint32_t seqn; /**< Sequence number. See also rte_reorder_insert() */ - - /** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ_STRIPPED is set. */ + /** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ is set. */ uint16_t vlan_tci_outer; + uint16_t buf_len; /**< Length of segment buffer. */ + + /** Valid if PKT_RX_TIMESTAMP is set. The unit and time reference + * are not normalized but are always the same for a given port. + */ + uint64_t timestamp; + /* second cache line - fields only used in slow path or on TX */ MARKER cacheline1 __rte_cache_min_aligned; @@ -506,8 +562,15 @@ struct rte_mbuf { /** Timesync flags for use with IEEE1588. */ uint16_t timesync; + + /** Sequence number. See also rte_reorder_insert(). */ + uint32_t seqn; + } __rte_cache_aligned; +/**< Maximum number of nb_segs allowed. */ +#define RTE_MBUF_MAX_NB_SEGS UINT16_MAX + /** * Prefetch the first part of the mbuf * @@ -549,21 +612,28 @@ rte_mbuf_prefetch_part2(struct rte_mbuf *m) static inline uint16_t rte_pktmbuf_priv_size(struct rte_mempool *mp); /** - * Return the DMA address of the beginning of the mbuf data + * Return the IO address of the beginning of the mbuf data * * @param mb * The pointer to the mbuf. * @return - * The physical address of the beginning of the mbuf data + * The IO address of the beginning of the mbuf data */ +static inline rte_iova_t +rte_mbuf_data_iova(const struct rte_mbuf *mb) +{ + return mb->buf_iova + mb->data_off; +} + +__rte_deprecated static inline phys_addr_t rte_mbuf_data_dma_addr(const struct rte_mbuf *mb) { - return mb->buf_physaddr + mb->data_off; + return rte_mbuf_data_iova(mb); } /** - * Return the default DMA address of the beginning of the mbuf data + * Return the default IO address of the beginning of the mbuf data * * This function is used by drivers in their receive function, as it * returns the location where data should be written by the NIC, taking @@ -572,12 +642,19 @@ rte_mbuf_data_dma_addr(const struct rte_mbuf *mb) * @param mb * The pointer to the mbuf. * @return - * The physical address of the beginning of the mbuf data + * The IO address of the beginning of the mbuf data */ +static inline rte_iova_t +rte_mbuf_data_iova_default(const struct rte_mbuf *mb) +{ + return mb->buf_iova + RTE_PKTMBUF_HEADROOM; +} + +__rte_deprecated static inline phys_addr_t rte_mbuf_data_dma_addr_default(const struct rte_mbuf *mb) { - return mb->buf_physaddr + RTE_PKTMBUF_HEADROOM; + return rte_mbuf_data_iova_default(mb); } /** @@ -671,6 +748,13 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) rte_atomic16_set(&m->refcnt_atomic, new_value); } +/* internal */ +static inline uint16_t +__rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) +{ + return (uint16_t)(rte_atomic16_add_return(&m->refcnt_atomic, value)); +} + /** * Adds given value to an mbuf's refcnt and returns its new value. * @param m @@ -695,19 +779,26 @@ rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) return 1 + value; } - return (uint16_t)(rte_atomic16_add_return(&m->refcnt_atomic, value)); + return __rte_mbuf_refcnt_update(m, value); } #else /* ! RTE_MBUF_REFCNT_ATOMIC */ +/* internal */ +static inline uint16_t +__rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) +{ + m->refcnt = (uint16_t)(m->refcnt + value); + return m->refcnt; +} + /** * Adds given value to an mbuf's refcnt and returns its new value. */ static inline uint16_t rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) { - m->refcnt = (uint16_t)(m->refcnt + value); - return m->refcnt; + return __rte_mbuf_refcnt_update(m, value); } /** @@ -752,14 +843,26 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) void rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header); +#define MBUF_RAW_ALLOC_CHECK(m) do { \ + RTE_ASSERT(rte_mbuf_refcnt_read(m) == 1); \ + RTE_ASSERT((m)->next == NULL); \ + RTE_ASSERT((m)->nb_segs == 1); \ + __rte_mbuf_sanity_check(m, 0); \ +} while (0) + /** - * Allocate an unitialized mbuf from mempool *mp*. + * Allocate an uninitialized mbuf from mempool *mp*. * * This function can be used by PMDs (especially in RX functions) to - * allocate an unitialized mbuf. The driver is responsible of + * allocate an uninitialized mbuf. The driver is responsible of * initializing all the required fields. See rte_pktmbuf_reset(). * For standard needs, prefer rte_pktmbuf_alloc(). * + * The caller can expect that the following fields of the mbuf structure + * are initialized: buf_addr, buf_iova, buf_len, refcnt=1, nb_segs=1, + * next=NULL, pool, priv_size. The other fields must be initialized + * by the caller. + * * @param mp * The mempool from which mbuf is allocated. * @return @@ -769,130 +872,60 @@ rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header); static inline struct rte_mbuf *rte_mbuf_raw_alloc(struct rte_mempool *mp) { struct rte_mbuf *m; - void *mb = NULL; - if (rte_mempool_get(mp, &mb) < 0) + if (rte_mempool_get(mp, (void **)&m) < 0) return NULL; - m = (struct rte_mbuf *)mb; - RTE_ASSERT(rte_mbuf_refcnt_read(m) == 0); - rte_mbuf_refcnt_set(m, 1); - __rte_mbuf_sanity_check(m, 0); - + MBUF_RAW_ALLOC_CHECK(m); return m; } /** - * @internal Put mbuf back into its original mempool. - * The use of that function is reserved for RTE internal needs. - * Please use rte_pktmbuf_free(). + * Put mbuf back into its original mempool. + * + * The caller must ensure that the mbuf is direct and properly + * reinitialized (refcnt=1, next=NULL, nb_segs=1), as done by + * rte_pktmbuf_prefree_seg(). + * + * This function should be used with care, when optimization is + * required. For standard needs, prefer rte_pktmbuf_free() or + * rte_pktmbuf_free_seg(). * * @param m * The mbuf to be freed. */ -static inline void __attribute__((always_inline)) -__rte_mbuf_raw_free(struct rte_mbuf *m) +static __rte_always_inline void +rte_mbuf_raw_free(struct rte_mbuf *m) { - RTE_ASSERT(rte_mbuf_refcnt_read(m) == 0); + RTE_ASSERT(RTE_MBUF_DIRECT(m)); + RTE_ASSERT(rte_mbuf_refcnt_read(m) == 1); + RTE_ASSERT(m->next == NULL); + RTE_ASSERT(m->nb_segs == 1); + __rte_mbuf_sanity_check(m, 0); rte_mempool_put(m->pool, m); } -/* Operations on ctrl mbuf */ - -/** - * The control mbuf constructor. - * - * This function initializes some fields in an mbuf structure that are - * not modified by the user once created (mbuf type, origin pool, buffer - * start address, and so on). This function is given as a callback function - * to rte_mempool_create() at pool creation time. - * - * @param mp - * The mempool from which the mbuf is allocated. - * @param opaque_arg - * A pointer that can be used by the user to retrieve useful information - * for mbuf initialization. This pointer comes from the ``init_arg`` - * parameter of rte_mempool_create(). - * @param m - * The mbuf to initialize. - * @param i - * The index of the mbuf in the pool table. - */ -void rte_ctrlmbuf_init(struct rte_mempool *mp, void *opaque_arg, - void *m, unsigned i); - -/** - * Allocate a new mbuf (type is ctrl) from mempool *mp*. - * - * This new mbuf is initialized with data pointing to the beginning of - * buffer, and with a length of zero. - * - * @param mp - * The mempool from which the mbuf is allocated. - * @return - * - The pointer to the new mbuf on success. - * - NULL if allocation failed. - */ -#define rte_ctrlmbuf_alloc(mp) rte_pktmbuf_alloc(mp) - -/** - * Free a control mbuf back into its original mempool. - * - * @param m - * The control mbuf to be freed. - */ -#define rte_ctrlmbuf_free(m) rte_pktmbuf_free(m) - -/** - * A macro that returns the pointer to the carried data. - * - * The value that can be read or assigned. - * - * @param m - * The control mbuf. - */ -#define rte_ctrlmbuf_data(m) ((char *)((m)->buf_addr) + (m)->data_off) - -/** - * A macro that returns the length of the carried data. - * - * The value that can be read or assigned. - * - * @param m - * The control mbuf. - */ -#define rte_ctrlmbuf_len(m) rte_pktmbuf_data_len(m) - -/** - * Tests if an mbuf is a control mbuf - * - * @param m - * The mbuf to be tested - * @return - * - True (1) if the mbuf is a control mbuf - * - False(0) otherwise - */ -static inline int -rte_is_ctrlmbuf(struct rte_mbuf *m) +/* compat with older versions */ +__rte_deprecated +static inline void +__rte_mbuf_raw_free(struct rte_mbuf *m) { - return !!(m->ol_flags & CTRL_MBUF_FLAG); + rte_mbuf_raw_free(m); } -/* Operations on pkt mbuf */ - /** * The packet mbuf constructor. * * This function initializes some fields in the mbuf structure that are * not modified by the user once created (origin pool, buffer start * address, and so on). This function is given as a callback function to - * rte_mempool_create() at pool creation time. + * rte_mempool_obj_iter() or rte_mempool_create() at pool creation time. * * @param mp * The mempool from which mbufs originate. * @param opaque_arg * A pointer that can be used by the user to retrieve useful information - * for mbuf initialization. This pointer comes from the ``init_arg`` - * parameter of rte_mempool_create(). + * for mbuf initialization. This pointer is the opaque argument passed to + * rte_mempool_obj_iter() or rte_mempool_create(). * @param m * The mbuf to initialize. * @param i @@ -907,7 +940,8 @@ void rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg, * * This function initializes the mempool private data in the case of a * pktmbuf pool. This private data is needed by the driver. The - * function is given as a callback function to rte_mempool_create() at + * function must be called on the mempool before it is used, or it + * can be given as a callback function to rte_mempool_create() at * pool creation. It can be extended by the user, for example, to * provide another packet size. * @@ -915,8 +949,8 @@ void rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg, * The mempool from which mbufs originate. * @param opaque_arg * A pointer that can be used by the user to retrieve useful information - * for mbuf initialization. This pointer comes from the ``init_arg`` - * parameter of rte_mempool_create(). + * for mbuf initialization. This pointer is the opaque argument passed to + * rte_mempool_create(). */ void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg); @@ -924,8 +958,7 @@ void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg); * Create a mbuf pool. * * This function creates and initializes a packet mbuf pool. It is - * a wrapper to rte_mempool_create() with the proper packet constructor - * and mempool constructor. + * a wrapper to rte_mempool functions. * * @param name * The name of the mbuf pool. @@ -960,6 +993,48 @@ rte_pktmbuf_pool_create(const char *name, unsigned n, unsigned cache_size, uint16_t priv_size, uint16_t data_room_size, int socket_id); +/** + * Create a mbuf pool with a given mempool ops name + * + * This function creates and initializes a packet mbuf pool. It is + * a wrapper to rte_mempool functions. + * + * @param name + * The name of the mbuf pool. + * @param n + * The number of elements in the mbuf pool. The optimum size (in terms + * of memory usage) for a mempool is when n is a power of two minus one: + * n = (2^q - 1). + * @param cache_size + * Size of the per-core object cache. See rte_mempool_create() for + * details. + * @param priv_size + * Size of application private are between the rte_mbuf structure + * and the data buffer. This value must be aligned to RTE_MBUF_PRIV_ALIGN. + * @param data_room_size + * Size of data buffer in each mbuf, including RTE_PKTMBUF_HEADROOM. + * @param socket_id + * The socket identifier where the memory should be allocated. The + * value can be *SOCKET_ID_ANY* if there is no NUMA constraint for the + * reserved zone. + * @param ops_name + * The mempool ops name to be used for this mempool instead of + * default mempool. The value can be *NULL* to use default mempool. + * @return + * The pointer to the new allocated mempool, on success. NULL on error + * with rte_errno set appropriately. Possible rte_errno values include: + * - E_RTE_NO_CONFIG - function could not get pointer to rte_config structure + * - E_RTE_SECONDARY - function was called from a secondary process instance + * - EINVAL - cache size provided is too large, or priv_size is not aligned. + * - ENOSPC - the maximum number of memzones has already been allocated + * - EEXIST - a memzone with the same name already exists + * - ENOMEM - no appropriate memory area found in which to create memzone + */ +struct rte_mempool * __rte_experimental +rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n, + unsigned int cache_size, uint16_t priv_size, uint16_t data_room_size, + int socket_id, const char *ops_name); + /** * Get the data room size of mbufs stored in a pktmbuf_pool * @@ -1022,6 +1097,8 @@ static inline void rte_pktmbuf_reset_headroom(struct rte_mbuf *m) * @param m * The packet mbuf to be resetted. */ +#define MBUF_INVALID_PORT UINT16_MAX + static inline void rte_pktmbuf_reset(struct rte_mbuf *m) { m->next = NULL; @@ -1030,7 +1107,7 @@ static inline void rte_pktmbuf_reset(struct rte_mbuf *m) m->vlan_tci = 0; m->vlan_tci_outer = 0; m->nb_segs = 1; - m->port = 0xff; + m->port = MBUF_INVALID_PORT; m->ol_flags = 0; m->packet_type = 0; @@ -1073,6 +1150,7 @@ static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp) * Array size * @return * - 0: Success + * - -ENOENT: Not enough entries in the mempool; no mbufs are retrieved. */ static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool, struct rte_mbuf **mbufs, unsigned count) @@ -1092,25 +1170,25 @@ static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool, switch (count % 4) { case 0: while (idx != count) { - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ case 3: - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ case 2: - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ case 1: - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ } } return 0; @@ -1148,11 +1226,10 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) rte_mbuf_refcnt_update(md, 1); mi->priv_size = m->priv_size; - mi->buf_physaddr = m->buf_physaddr; + mi->buf_iova = m->buf_iova; mi->buf_addr = m->buf_addr; mi->buf_len = m->buf_len; - mi->next = m->next; mi->data_off = m->data_off; mi->data_len = m->data_len; mi->port = m->port; @@ -1166,6 +1243,7 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) mi->nb_segs = 1; mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF; mi->packet_type = m->packet_type; + mi->timestamp = m->timestamp; __rte_mbuf_sanity_check(mi, 1); __rte_mbuf_sanity_check(m, 0); @@ -1196,30 +1274,75 @@ static inline void rte_pktmbuf_detach(struct rte_mbuf *m) m->priv_size = priv_size; m->buf_addr = (char *)m + mbuf_size; - m->buf_physaddr = rte_mempool_virt2phy(mp, m) + mbuf_size; + m->buf_iova = rte_mempool_virt2iova(m) + mbuf_size; m->buf_len = (uint16_t)buf_len; rte_pktmbuf_reset_headroom(m); m->data_len = 0; m->ol_flags = 0; - if (rte_mbuf_refcnt_update(md, -1) == 0) - __rte_mbuf_raw_free(md); + if (rte_mbuf_refcnt_update(md, -1) == 0) { + md->next = NULL; + md->nb_segs = 1; + rte_mbuf_refcnt_set(md, 1); + rte_mbuf_raw_free(md); + } } -static inline struct rte_mbuf* __attribute__((always_inline)) -__rte_pktmbuf_prefree_seg(struct rte_mbuf *m) +/** + * Decrease reference counter and unlink a mbuf segment + * + * This function does the same than a free, except that it does not + * return the segment to its pool. + * It decreases the reference counter, and if it reaches 0, it is + * detached from its parent for an indirect mbuf. + * + * @param m + * The mbuf to be unlinked + * @return + * - (m) if it is the last reference. It can be recycled or freed. + * - (NULL) if the mbuf still has remaining references on it. + */ +static __rte_always_inline struct rte_mbuf * +rte_pktmbuf_prefree_seg(struct rte_mbuf *m) { __rte_mbuf_sanity_check(m, 0); - if (likely(rte_mbuf_refcnt_update(m, -1) == 0)) { - /* if this is an indirect mbuf, it is detached. */ + if (likely(rte_mbuf_refcnt_read(m) == 1)) { + + if (RTE_MBUF_INDIRECT(m)) + rte_pktmbuf_detach(m); + + if (m->next != NULL) { + m->next = NULL; + m->nb_segs = 1; + } + + return m; + + } else if (__rte_mbuf_refcnt_update(m, -1) == 0) { + if (RTE_MBUF_INDIRECT(m)) rte_pktmbuf_detach(m); + + if (m->next != NULL) { + m->next = NULL; + m->nb_segs = 1; + } + rte_mbuf_refcnt_set(m, 1); + return m; } return NULL; } +/* deprecated, replaced by rte_pktmbuf_prefree_seg() */ +__rte_deprecated +static inline struct rte_mbuf * +__rte_pktmbuf_prefree_seg(struct rte_mbuf *m) +{ + return rte_pktmbuf_prefree_seg(m); +} + /** * Free a segment of a packet mbuf into its original mempool. * @@ -1229,13 +1352,12 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m) * @param m * The packet mbuf segment to be freed. */ -static inline void __attribute__((always_inline)) +static __rte_always_inline void rte_pktmbuf_free_seg(struct rte_mbuf *m) { - if (likely(NULL != (m = __rte_pktmbuf_prefree_seg(m)))) { - m->next = NULL; - __rte_mbuf_raw_free(m); - } + m = rte_pktmbuf_prefree_seg(m); + if (likely(m != NULL)) + rte_mbuf_raw_free(m); } /** @@ -1245,13 +1367,14 @@ rte_pktmbuf_free_seg(struct rte_mbuf *m) * segment is added back into its original mempool. * * @param m - * The packet mbuf to be freed. + * The packet mbuf to be freed. If NULL, the function does nothing. */ static inline void rte_pktmbuf_free(struct rte_mbuf *m) { struct rte_mbuf *m_next; - __rte_mbuf_sanity_check(m, 1); + if (m != NULL) + __rte_mbuf_sanity_check(m, 1); while (m != NULL) { m_next = m->next; @@ -1282,7 +1405,7 @@ static inline struct rte_mbuf *rte_pktmbuf_clone(struct rte_mbuf *md, { struct rte_mbuf *mc, *mi, **prev; uint32_t pktlen; - uint8_t nseg; + uint16_t nseg; if (unlikely ((mc = rte_pktmbuf_alloc(mp)) == NULL)) return NULL; @@ -1344,7 +1467,7 @@ static inline void rte_pktmbuf_refcnt_update(struct rte_mbuf *m, int16_t v) */ static inline uint16_t rte_pktmbuf_headroom(const struct rte_mbuf *m) { - __rte_mbuf_sanity_check(m, 1); + __rte_mbuf_sanity_check(m, 0); return m->data_off; } @@ -1358,7 +1481,7 @@ static inline uint16_t rte_pktmbuf_headroom(const struct rte_mbuf *m) */ static inline uint16_t rte_pktmbuf_tailroom(const struct rte_mbuf *m) { - __rte_mbuf_sanity_check(m, 1); + __rte_mbuf_sanity_check(m, 0); return (uint16_t)(m->buf_len - rte_pktmbuf_headroom(m) - m->data_len); } @@ -1373,12 +1496,10 @@ static inline uint16_t rte_pktmbuf_tailroom(const struct rte_mbuf *m) */ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) { - struct rte_mbuf *m2 = (struct rte_mbuf *)m; - __rte_mbuf_sanity_check(m, 1); - while (m2->next != NULL) - m2 = m2->next; - return m2; + while (m->next != NULL) + m = m->next; + return m; } /** @@ -1413,7 +1534,7 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) #define rte_pktmbuf_mtod(m, t) rte_pktmbuf_mtod_offset(m, t, 0) /** - * A macro that returns the physical address that points to an offset of the + * A macro that returns the IO address that points to an offset of the * start of the data in the mbuf * * @param m @@ -1421,17 +1542,24 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) * @param o * The offset into the data to calculate address from. */ +#define rte_pktmbuf_iova_offset(m, o) \ + (rte_iova_t)((m)->buf_iova + (m)->data_off + (o)) + +/* deprecated */ #define rte_pktmbuf_mtophys_offset(m, o) \ - (phys_addr_t)((m)->buf_physaddr + (m)->data_off + (o)) + rte_pktmbuf_iova_offset(m, o) /** - * A macro that returns the physical address that points to the start of the + * A macro that returns the IO address that points to the start of the * data in the mbuf * * @param m * The packet mbuf. */ -#define rte_pktmbuf_mtophys(m) rte_pktmbuf_mtophys_offset(m, 0) +#define rte_pktmbuf_iova(m) rte_pktmbuf_iova_offset(m, 0) + +/* deprecated */ +#define rte_pktmbuf_mtophys(m) rte_pktmbuf_iova(m) /** * A macro that returns the length of the packet. @@ -1606,7 +1734,7 @@ const void *__rte_pktmbuf_read(const struct rte_mbuf *m, uint32_t off, * @param len * The amount of bytes to read. * @param buf - * The buffer where data is copied if it is not contigous in mbuf + * The buffer where data is copied if it is not contiguous in mbuf * data. Its length should be at least equal to the len parameter. * @return * The pointer to the data, either in the mbuf if it is contiguous, @@ -1635,14 +1763,14 @@ static inline const void *rte_pktmbuf_read(const struct rte_mbuf *m, * * @return * - 0, on success. - * - -EOVERFLOW, if the chain is full (256 entries) + * - -EOVERFLOW, if the chain segment limit exceeded */ static inline int rte_pktmbuf_chain(struct rte_mbuf *head, struct rte_mbuf *tail) { struct rte_mbuf *cur_tail; /* Check for number-of-segments-overflow */ - if (head->nb_segs + tail->nb_segs >= 1 << (sizeof(head->nb_segs) * 8)) + if (head->nb_segs + tail->nb_segs > RTE_MBUF_MAX_NB_SEGS) return -EOVERFLOW; /* Chain 'tail' onto the old tail */ @@ -1650,7 +1778,7 @@ static inline int rte_pktmbuf_chain(struct rte_mbuf *head, struct rte_mbuf *tail cur_tail->next = tail; /* accumulate number of segments and total length. */ - head->nb_segs = (uint8_t)(head->nb_segs + tail->nb_segs); + head->nb_segs += tail->nb_segs; head->pkt_len += tail->pkt_len; /* pkt_len is only set in the head */ @@ -1710,6 +1838,57 @@ rte_validate_tx_offload(const struct rte_mbuf *m) return 0; } +/** + * Linearize data in mbuf. + * + * This function moves the mbuf data in the first segment if there is enough + * tailroom. The subsequent segments are unchained and freed. + * + * @param mbuf + * mbuf to linearize + * @return + * - 0, on success + * - -1, on error + */ +static inline int +rte_pktmbuf_linearize(struct rte_mbuf *mbuf) +{ + int seg_len, copy_len; + struct rte_mbuf *m; + struct rte_mbuf *m_next; + char *buffer; + + if (rte_pktmbuf_is_contiguous(mbuf)) + return 0; + + /* Extend first segment to the total packet length */ + copy_len = rte_pktmbuf_pkt_len(mbuf) - rte_pktmbuf_data_len(mbuf); + + if (unlikely(copy_len > rte_pktmbuf_tailroom(mbuf))) + return -1; + + buffer = rte_pktmbuf_mtod_offset(mbuf, char *, mbuf->data_len); + mbuf->data_len = (uint16_t)(mbuf->pkt_len); + + /* Append data from next segments to the first one */ + m = mbuf->next; + while (m != NULL) { + m_next = m->next; + + seg_len = rte_pktmbuf_data_len(m); + rte_memcpy(buffer, rte_pktmbuf_mtod(m, char *), seg_len); + buffer += seg_len; + + rte_pktmbuf_free_seg(m); + m = m_next; + } + + mbuf->next = NULL; + mbuf->nb_segs = 1; + + return 0; +} + /** * Dump an mbuf structure to a file. *