X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=002e86bc8a65870afd6c794ea462dee01fb70b20;hb=ad606c9f6a9f77dfb88a0625d821bccbf578b63b;hp=4a9318927122450391c65f2ab6721f5e819eb5ce;hpb=139debc42dc0a320dad40f5295b74d2e3ab8a7f9;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 4a93189271..002e86bc8a 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -65,10 +65,6 @@ extern "C" { #endif -/* deprecated options */ -#pragma GCC poison RTE_MBUF_SCATTER_GATHER -#pragma GCC poison RTE_MBUF_REFCNT - /* * Packet Offload Features Flags. It also carry packet type information. * Critical resources. Both rx/tx shared these bits. Be cautious on any change @@ -83,25 +79,67 @@ extern "C" { * Keep these flags synchronized with rte_get_rx_ol_flag_name() and * rte_get_tx_ol_flag_name(). */ -#define PKT_RX_VLAN_PKT (1ULL << 0) /**< RX packet is a 802.1q VLAN packet. */ + +/** + * 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. + */ +#define PKT_RX_VLAN_PKT (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. */ #define PKT_RX_L4_CKSUM_BAD (1ULL << 3) /**< L4 cksum of RX pkt. is not OK. */ #define PKT_RX_IP_CKSUM_BAD (1ULL << 4) /**< IP cksum of RX pkt. is not OK. */ -#define PKT_RX_EIP_CKSUM_BAD (0ULL << 0) /**< External IP header checksum error. */ -#define PKT_RX_OVERSIZE (0ULL << 0) /**< Num of desc of an RX pkt oversize. */ -#define PKT_RX_HBUF_OVERFLOW (0ULL << 0) /**< Header buffer overflow. */ -#define PKT_RX_RECIP_ERR (0ULL << 0) /**< Hardware processing error. */ -#define PKT_RX_MAC_ERR (0ULL << 0) /**< MAC error. */ +#define PKT_RX_EIP_CKSUM_BAD (1ULL << 5) /**< External IP header checksum error. */ + +/** + * 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. + */ +#define PKT_RX_VLAN_STRIPPED (1ULL << 6) + +/* hole, some bits can be reused here */ + #define PKT_RX_IEEE1588_PTP (1ULL << 9) /**< RX IEEE1588 L2 Ethernet PT Packet. */ #define PKT_RX_IEEE1588_TMST (1ULL << 10) /**< RX IEEE1588 L2/L4 timestamped packet.*/ #define PKT_RX_FDIR_ID (1ULL << 13) /**< FD id reported if FDIR match. */ #define PKT_RX_FDIR_FLX (1ULL << 14) /**< Flexible bytes reported if FDIR match. */ -#define PKT_RX_QINQ_PKT (1ULL << 15) /**< RX packet with double VLAN stripped. */ + +/** + * 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. + */ +#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 + /* add new RX flags here */ /* add new TX flags here */ +/** + * Bits 45:48 used for the tunnel type. + * When doing Tx offload like TSO or checksum, the HW needs to configure the + * tunnel type into the HW descriptors. + */ +#define PKT_TX_TUNNEL_VXLAN (0x1ULL << 45) +#define PKT_TX_TUNNEL_GRE (0x2ULL << 45) +#define PKT_TX_TUNNEL_IPIP (0x3ULL << 45) +#define PKT_TX_TUNNEL_GENEVE (0x4ULL << 45) +/* add new TX TUNNEL type here */ +#define PKT_TX_TUNNEL_MASK (0xFULL << 45) + /** * Second VLAN insertion (QinQ) flag. */ @@ -277,6 +315,13 @@ extern "C" { * <'ether type'=0x88CC> */ #define RTE_PTYPE_L2_ETHER_LLDP 0x00000004 +/** + * NSH (Network Service Header) packet type. + * + * Packet format: + * <'ether type'=0x894F> + */ +#define RTE_PTYPE_L2_ETHER_NSH 0x00000005 /** * Mask of layer 2 packet types. * It is used for outer packet for tunneling cases. @@ -723,8 +768,11 @@ const char *rte_get_tx_ol_flag_name(uint64_t mask); /* define a set of marker types that can be used to refer to set points in the * mbuf */ +__extension__ typedef void *MARKER[0]; /**< generic marker for a point in a structure */ +__extension__ typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */ +__extension__ typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes * with a single assignment */ @@ -751,6 +799,7 @@ struct rte_mbuf { * or non-atomic) is controlled by the CONFIG_RTE_MBUF_REFCNT_ATOMIC * config option. */ + RTE_STD_C11 union { rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ uint16_t refcnt; /**< Non-atomically accessed refcnt */ @@ -765,8 +814,12 @@ struct rte_mbuf { /* * The packet type, which is the combination of outer/inner L2, L3, L4 - * and tunnel types. + * and tunnel types. The packet_type is about data really present in the + * mbuf. Example: if vlan stripping is enabled, a received vlan packet + * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN because the + * vlan is stripped from the data. */ + RTE_STD_C11 union { uint32_t packet_type; /**< L2/L3/L4 and tunnel information. */ struct { @@ -782,11 +835,13 @@ struct rte_mbuf { uint32_t pkt_len; /**< Total pkt len: sum of all segments. */ uint16_t data_len; /**< Amount of data in segment buffer. */ - uint16_t vlan_tci; /**< VLAN Tag Control Identifier (CPU order) */ + /** VLAN TCI (CPU order), valid if PKT_RX_VLAN_STRIPPED is set. */ + uint16_t vlan_tci; union { uint32_t rss; /**< RSS hash result if RSS enabled */ struct { + RTE_STD_C11 union { struct { uint16_t hash; @@ -799,17 +854,22 @@ struct rte_mbuf { /**< First 4 flexible bytes or FD ID, dependent on PKT_RX_FDIR_* flag in ol_flags. */ } fdir; /**< Filter identifier if FDIR enabled */ - uint32_t sched; /**< Hierarchical scheduler */ + struct { + uint32_t lo; + uint32_t hi; + } sched; /**< Hierarchical scheduler */ uint32_t usr; /**< User defined tags. See rte_distributor_process() */ } hash; /**< hash information */ uint32_t seqn; /**< Sequence number. See also rte_reorder_insert() */ - uint16_t vlan_tci_outer; /**< Outer VLAN Tag Control Identifier (CPU order) */ + /** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ_STRIPPED is set. */ + uint16_t vlan_tci_outer; /* second cache line - fields only used in slow path or on TX */ - MARKER cacheline1 __rte_cache_aligned; + MARKER cacheline1 __rte_cache_min_aligned; + RTE_STD_C11 union { void *userdata; /**< Can be used for external metadata */ uint64_t udata64; /**< Allow 8-byte userdata on 32-bit */ @@ -819,10 +879,15 @@ struct rte_mbuf { struct rte_mbuf *next; /**< Next segment of scattered packet. */ /* fields to support TX offloads */ + RTE_STD_C11 union { uint64_t tx_offload; /**< combined for easy fetch */ + __extension__ struct { - uint64_t l2_len:7; /**< L2 (MAC) Header Length. */ + uint64_t l2_len:7; + /**< L2 (MAC) Header Length for non-tunneling pkt. + * Outer_L4_len + ... + Inner_L2_len for tunneling pkt. + */ uint64_t l3_len:9; /**< L3 (IP) Header Length. */ uint64_t l4_len:8; /**< L4 (TCP/UDP) Header Length. */ uint64_t tso_segsz:16; /**< TCP TSO segment size */ @@ -843,8 +908,78 @@ struct rte_mbuf { uint16_t timesync; } __rte_cache_aligned; +/** + * Prefetch the first part of the mbuf + * + * The first 64 bytes of the mbuf corresponds to fields that are used early + * in the receive path. If the cache line of the architecture is higher than + * 64B, the second part will also be prefetched. + * + * @param m + * The pointer to the mbuf. + */ +static inline void +rte_mbuf_prefetch_part1(struct rte_mbuf *m) +{ + rte_prefetch0(&m->cacheline0); +} + +/** + * Prefetch the second part of the mbuf + * + * The next 64 bytes of the mbuf corresponds to fields that are used in the + * transmit path. If the cache line of the architecture is higher than 64B, + * this function does nothing as it is expected that the full mbuf is + * already in cache. + * + * @param m + * The pointer to the mbuf. + */ +static inline void +rte_mbuf_prefetch_part2(struct rte_mbuf *m) +{ +#if RTE_CACHE_LINE_SIZE == 64 + rte_prefetch0(&m->cacheline1); +#else + RTE_SET_USED(m); +#endif +} + + static inline uint16_t rte_pktmbuf_priv_size(struct rte_mempool *mp); +/** + * Return the DMA 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 + */ +static inline phys_addr_t +rte_mbuf_data_dma_addr(const struct rte_mbuf *mb) +{ + return mb->buf_physaddr + mb->data_off; +} + +/** + * Return the default DMA 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 + * the default headroom in account. + * + * @param mb + * The pointer to the mbuf. + * @return + * The physical address of the beginning of the mbuf data + */ +static inline phys_addr_t +rte_mbuf_data_dma_addr_default(const struct rte_mbuf *mb) +{ + return mb->buf_physaddr + RTE_PKTMBUF_HEADROOM; +} + /** * Return the mbuf owning the data buffer address of an indirect mbuf. * @@ -901,29 +1036,11 @@ struct rte_pktmbuf_pool_private { /** check mbuf type in debug mode */ #define __rte_mbuf_sanity_check(m, is_h) rte_mbuf_sanity_check(m, is_h) -/** check mbuf type in debug mode if mbuf pointer is not null */ -#define __rte_mbuf_sanity_check_raw(m, is_h) do { \ - if ((m) != NULL) \ - rte_mbuf_sanity_check(m, is_h); \ -} while (0) - -/** MBUF asserts in debug mode */ -#define RTE_MBUF_ASSERT(exp) \ -if (!(exp)) { \ - rte_panic("line%d\tassert \"" #exp "\" failed\n", __LINE__); \ -} - #else /* RTE_LIBRTE_MBUF_DEBUG */ /** check mbuf type in debug mode */ #define __rte_mbuf_sanity_check(m, is_h) do { } while (0) -/** check mbuf type in debug mode if mbuf pointer is not null */ -#define __rte_mbuf_sanity_check_raw(m, is_h) do { } while (0) - -/** MBUF asserts in debug mode */ -#define RTE_MBUF_ASSERT(exp) do { } while (0) - #endif /* RTE_LIBRTE_MBUF_DEBUG */ #ifdef RTE_MBUF_REFCNT_ATOMIC @@ -1036,9 +1153,12 @@ void rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header); /** - * @internal Allocate a new mbuf from mempool *mp*. - * The use of that function is reserved for RTE internal needs. - * Please use rte_pktmbuf_alloc(). + * Allocate an unitialized 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 + * initializing all the required fields. See rte_pktmbuf_reset(). + * For standard needs, prefer rte_pktmbuf_alloc(). * * @param mp * The mempool from which mbuf is allocated. @@ -1046,15 +1166,18 @@ rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header); * - The pointer to the new mbuf on success. * - NULL if allocation failed. */ -static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp) +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) return NULL; m = (struct rte_mbuf *)mb; - RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0); + RTE_ASSERT(rte_mbuf_refcnt_read(m) == 0); rte_mbuf_refcnt_set(m, 1); + __rte_mbuf_sanity_check(m, 0); + return m; } @@ -1069,7 +1192,7 @@ static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp) static inline void __attribute__((always_inline)) __rte_mbuf_raw_free(struct rte_mbuf *m) { - RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0); + RTE_ASSERT(rte_mbuf_refcnt_read(m) == 0); rte_mempool_put(m->pool, m); } @@ -1278,6 +1401,19 @@ rte_pktmbuf_priv_size(struct rte_mempool *mp) return mbp_priv->mbuf_priv_size; } +/** + * Reset the data_off field of a packet mbuf to its default value. + * + * The given mbuf must have only one segment, which should be empty. + * + * @param m + * The packet mbuf's data_off field has to be reset. + */ +static inline void rte_pktmbuf_reset_headroom(struct rte_mbuf *m) +{ + m->data_off = RTE_MIN(RTE_PKTMBUF_HEADROOM, (uint16_t)m->buf_len); +} + /** * Reset the fields of a packet mbuf to their default values. * @@ -1298,8 +1434,7 @@ static inline void rte_pktmbuf_reset(struct rte_mbuf *m) m->ol_flags = 0; m->packet_type = 0; - m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ? - RTE_PKTMBUF_HEADROOM : m->buf_len; + rte_pktmbuf_reset_headroom(m); m->data_len = 0; __rte_mbuf_sanity_check(m, 1); @@ -1321,16 +1456,73 @@ static inline void rte_pktmbuf_reset(struct rte_mbuf *m) static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp) { struct rte_mbuf *m; - if ((m = __rte_mbuf_raw_alloc(mp)) != NULL) + if ((m = rte_mbuf_raw_alloc(mp)) != NULL) rte_pktmbuf_reset(m); return m; } +/** + * Allocate a bulk of mbufs, initialize refcnt and reset the fields to default + * values. + * + * @param pool + * The mempool from which mbufs are allocated. + * @param mbufs + * Array of pointers to mbufs + * @param count + * Array size + * @return + * - 0: Success + */ +static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool, + struct rte_mbuf **mbufs, unsigned count) +{ + unsigned idx = 0; + int rc; + + rc = rte_mempool_get_bulk(pool, (void **)mbufs, count); + if (unlikely(rc)) + return rc; + + /* To understand duff's device on loop unwinding optimization, see + * https://en.wikipedia.org/wiki/Duff's_device. + * Here while() loop is used rather than do() while{} to avoid extra + * check if count is zero. + */ + switch (count % 4) { + case 0: + while (idx != count) { + RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); + rte_mbuf_refcnt_set(mbufs[idx], 1); + rte_pktmbuf_reset(mbufs[idx]); + idx++; + case 3: + RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); + rte_mbuf_refcnt_set(mbufs[idx], 1); + rte_pktmbuf_reset(mbufs[idx]); + idx++; + case 2: + RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); + rte_mbuf_refcnt_set(mbufs[idx], 1); + rte_pktmbuf_reset(mbufs[idx]); + idx++; + case 1: + RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); + rte_mbuf_refcnt_set(mbufs[idx], 1); + rte_pktmbuf_reset(mbufs[idx]); + idx++; + } + } + return 0; +} + /** * Attach packet mbuf to another packet mbuf. * * After attachment we refer the mbuf we attached as 'indirect', * while mbuf we attached to as 'direct'. + * The direct mbuf's reference counter is incremented. + * * Right now, not supported: * - attachment for already indirect mbuf (e.g. - mi has to be direct). * - mbuf we trying to attach (mi) is used by someone else @@ -1345,7 +1537,7 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) { struct rte_mbuf *md; - RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(mi) && + RTE_ASSERT(RTE_MBUF_DIRECT(mi) && rte_mbuf_refcnt_read(mi) == 1); /* if m is not direct, get the mbuf that embeds the data */ @@ -1384,13 +1576,17 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) * * - restore original mbuf address and length values. * - reset pktmbuf data and data_len to their default values. - * All other fields of the given packet mbuf will be left intact. + * - decrement the direct mbuf's reference counter. When the + * reference counter becomes 0, the direct mbuf is freed. + * + * All other fields of the given packet mbuf will be left intact. * * @param m * The indirect attached packet mbuf. */ static inline void rte_pktmbuf_detach(struct rte_mbuf *m) { + struct rte_mbuf *md = rte_mbuf_from_indirect(m); struct rte_mempool *mp = m->pool; uint32_t mbuf_size, buf_len, priv_size; @@ -1402,9 +1598,12 @@ static inline void rte_pktmbuf_detach(struct rte_mbuf *m) m->buf_addr = (char *)m + mbuf_size; m->buf_physaddr = rte_mempool_virt2phy(mp, m) + mbuf_size; m->buf_len = (uint16_t)buf_len; - m->data_off = RTE_MIN(RTE_PKTMBUF_HEADROOM, (uint16_t)m->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); } static inline struct rte_mbuf* __attribute__((always_inline)) @@ -1413,17 +1612,9 @@ __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, then - * - detach mbuf - * - free attached mbuf segment - */ - if (RTE_MBUF_INDIRECT(m)) { - struct rte_mbuf *md = rte_mbuf_from_indirect(m); + /* if this is an indirect mbuf, it is detached. */ + if (RTE_MBUF_INDIRECT(m)) rte_pktmbuf_detach(m); - if (rte_mbuf_refcnt_update(md, -1) == 0) - __rte_mbuf_raw_free(md); - } return m; } return NULL; @@ -1621,6 +1812,27 @@ 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 + * start of the data in the mbuf + * + * @param m + * The packet mbuf. + * @param o + * The offset into the data to calculate address from. + */ +#define rte_pktmbuf_mtophys_offset(m, o) \ + (phys_addr_t)((m)->buf_physaddr + (m)->data_off + (o)) + +/** + * A macro that returns the physical 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) + /** * A macro that returns the length of the packet. *