#include <stdint.h>
#include <rte_mempool.h>
+#include <rte_memory.h>
#include <rte_atomic.h>
#include <rte_prefetch.h>
#include <rte_branch_prediction.h>
extern "C" {
#endif
-/* deprecated feature, renamed in RTE_MBUF_REFCNT */
+/* 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.
* and set it in the TCP header. Refer to rte_ipv4_phdr_cksum() and
* rte_ipv6_phdr_cksum() that can be used as helpers.
*/
-#define PKT_TX_TCP_SEG (1ULL << 49)
+#define PKT_TX_TCP_SEG (1ULL << 50)
-#define PKT_TX_VXLAN_CKSUM (1ULL << 50) /**< TX checksum of VXLAN computed by NIC */
#define PKT_TX_IEEE1588_TMST (1ULL << 51) /**< TX IEEE1588 packet to timestamp. */
/**
#define PKT_TX_UDP_CKSUM (3ULL << 52) /**< UDP cksum of TX pkt. computed by NIC. */
#define PKT_TX_L4_MASK (3ULL << 52) /**< Mask for L4 cksum offload request. */
-#define PKT_TX_IP_CKSUM (1ULL << 54) /**< IP cksum of TX pkt. computed by NIC. */
-#define PKT_TX_IPV4_CSUM PKT_TX_IP_CKSUM /**< Alias of PKT_TX_IP_CKSUM. */
+/**
+ * Offload the IP checksum in the hardware. The flag PKT_TX_IPV4 should
+ * also be set by the application, although a PMD will only check
+ * PKT_TX_IP_CKSUM.
+ * - set the IP checksum field in the packet to 0
+ * - fill the mbuf offload information: l2_len, l3_len
+ */
+#define PKT_TX_IP_CKSUM (1ULL << 54)
-/** Packet is IPv4 without requiring IP checksum offload. */
+/**
+ * Packet is IPv4. This flag must be set when using any offload feature
+ * (TSO, L3 or L4 checksum) to tell the NIC that the packet is an IPv4
+ * packet. If the packet is a tunneled packet, this flag is related to
+ * the inner headers.
+ */
#define PKT_TX_IPV4 (1ULL << 55)
-/** Tell the NIC it's an IPv6 packet.*/
+/**
+ * Packet is IPv6. This flag must be set when using an offload feature
+ * (TSO or L4 checksum) to tell the NIC that the packet is an IPv6
+ * packet. If the packet is a tunneled packet, this flag is related to
+ * the inner headers.
+ */
#define PKT_TX_IPV6 (1ULL << 56)
#define PKT_TX_VLAN_PKT (1ULL << 57) /**< TX packet is a 802.1q VLAN packet. */
+/**
+ * Offload the IP checksum of an external header in the hardware. The
+ * flag PKT_TX_OUTER_IPV4 should also be set by the application, alto ugh
+ * a PMD will only check PKT_TX_IP_CKSUM. The IP checksum field in the
+ * packet must be set to 0.
+ * - set the outer IP checksum field in the packet to 0
+ * - fill the mbuf offload information: outer_l2_len, outer_l3_len
+ */
+#define PKT_TX_OUTER_IP_CKSUM (1ULL << 58)
+
+/**
+ * Packet outer header is IPv4. This flag must be set when using any
+ * outer offload feature (L3 or L4 checksum) to tell the NIC that the
+ * outer header of the tunneled packet is an IPv4 packet.
+ */
+#define PKT_TX_OUTER_IPV4 (1ULL << 59)
+
+/**
+ * Packet outer header is IPv6. This flag must be set when using any
+ * outer offload feature (L4 checksum) to tell the NIC that the outer
+ * header of the tunneled packet is an IPv6 packet.
+ */
+#define PKT_TX_OUTER_IPV6 (1ULL << 60)
+
+#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 */
*/
const char *rte_get_tx_ol_flag_name(uint64_t mask);
+/**
+ * Some NICs need at least 2KB buffer to RX standard Ethernet frame without
+ * splitting it into multiple segments.
+ * So, for mbufs that planned to be involved into RX/TX, the recommended
+ * minimal buffer length is 2KB + RTE_PKTMBUF_HEADROOM.
+ */
+#define RTE_MBUF_DEFAULT_DATAROOM 2048
+#define RTE_MBUF_DEFAULT_BUF_SIZE \
+ (RTE_MBUF_DEFAULT_DATAROOM + RTE_PKTMBUF_HEADROOM)
+
/* define a set of marker types that can be used to refer to set points in the
* mbuf */
typedef void *MARKER[0]; /**< generic marker for a point in a structure */
+typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */
typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes
* with a single assignment */
+
/**
* The generic rte_mbuf, containing a packet mbuf.
*/
void *buf_addr; /**< Virtual address of segment buffer. */
phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */
- /* next 8 bytes are initialised on RX descriptor rearm */
- MARKER64 rearm_data;
uint16_t buf_len; /**< Length of segment buffer. */
+
+ /* next 6 bytes are initialised on RX descriptor rearm */
+ MARKER8 rearm_data;
uint16_t data_off;
/**
* config option.
*/
union {
-#ifdef RTE_MBUF_REFCNT
rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */
uint16_t refcnt; /**< Non-atomically accessed refcnt */
-#endif
- uint16_t refcnt_reserved; /**< Do not use this field */
};
uint8_t nb_segs; /**< Number of segments. */
uint8_t port; /**< Input port. */
PKT_RX_FDIR_* flag in ol_flags. */
} fdir; /**< Filter identifier if FDIR enabled */
uint32_t sched; /**< Hierarchical scheduler */
- uint32_t usr; /**< User defined tags. See @rte_distributor_process */
+ uint32_t usr; /**< User defined tags. See rte_distributor_process() */
} hash; /**< hash information */
+ uint32_t seqn; /**< Sequence number. See also rte_reorder_insert() */
+
/* second cache line - fields only used in slow path or on TX */
MARKER cacheline1 __rte_cache_aligned;
uint64_t tso_segsz:16; /**< TCP TSO segment size */
/* fields for TX offloading of tunnels */
- uint64_t inner_l3_len:9; /**< inner L3 (IP) Hdr Length. */
- uint64_t inner_l2_len:7; /**< inner L2 (MAC) Hdr Length. */
+ uint64_t outer_l3_len:9; /**< Outer L3 (IP) Hdr Length. */
+ uint64_t outer_l2_len:7; /**< Outer L2 (MAC) Hdr Length. */
/* uint64_t unused:8; */
};
};
+
+ /** Size of the application private data. In case of an indirect
+ * mbuf, it stores the direct mbuf private data size. */
+ uint16_t priv_size;
} __rte_cache_aligned;
+static inline uint16_t rte_pktmbuf_priv_size(struct rte_mempool *mp);
+
/**
- * Given the buf_addr returns the pointer to corresponding mbuf.
+ * Return the mbuf owning the data buffer address of an indirect mbuf.
+ *
+ * @param mi
+ * The pointer to the indirect mbuf.
+ * @return
+ * The address of the direct mbuf corresponding to buffer_addr.
*/
-#define RTE_MBUF_FROM_BADDR(ba) (((struct rte_mbuf *)(ba)) - 1)
+static inline struct rte_mbuf *
+rte_mbuf_from_indirect(struct rte_mbuf *mi)
+{
+ struct rte_mbuf *md;
+
+ /* mi->buf_addr and mi->priv_size correspond to buffer and
+ * private size of the direct mbuf */
+ md = (struct rte_mbuf *)((char *)mi->buf_addr - sizeof(*mi) -
+ mi->priv_size);
+ return md;
+}
/**
- * Given the pointer to mbuf returns an address where it's buf_addr
- * should point to.
+ * Return the buffer address embedded in the given mbuf.
+ *
+ * @param md
+ * The pointer to the mbuf.
+ * @return
+ * The address of the data buffer owned by the mbuf.
*/
-#define RTE_MBUF_TO_BADDR(mb) (((struct rte_mbuf *)(mb)) + 1)
+static inline char *
+rte_mbuf_to_baddr(struct rte_mbuf *md)
+{
+ char *buffer_addr;
+ buffer_addr = (char *)md + sizeof(*md) + rte_pktmbuf_priv_size(md->pool);
+ return buffer_addr;
+}
/**
* Returns TRUE if given mbuf is indirect, or FALSE otherwise.
*/
-#define RTE_MBUF_INDIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb))
+#define RTE_MBUF_INDIRECT(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF)
/**
* Returns TRUE if given mbuf is direct, or FALSE otherwise.
*/
-#define RTE_MBUF_DIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) == (mb))
-
+#define RTE_MBUF_DIRECT(mb) (!RTE_MBUF_INDIRECT(mb))
/**
* Private data in case of pktmbuf pool.
* appended after the mempool structure (in private data).
*/
struct rte_pktmbuf_pool_private {
- uint16_t mbuf_data_room_size; /**< Size of data space in each mbuf.*/
+ uint16_t mbuf_data_room_size; /**< Size of data space in each mbuf. */
+ uint16_t mbuf_priv_size; /**< Size of private area in each mbuf. */
};
#ifdef RTE_LIBRTE_MBUF_DEBUG
#endif /* RTE_LIBRTE_MBUF_DEBUG */
-#ifdef RTE_MBUF_REFCNT
#ifdef RTE_MBUF_REFCNT_ATOMIC
/**
rte_prefetch0(m); \
} while (0)
-#else /* ! RTE_MBUF_REFCNT */
-
-/** Mbuf prefetch */
-#define RTE_MBUF_PREFETCH_TO_FREE(m) do { } while(0)
-
-#define rte_mbuf_refcnt_set(m,v) do { } while(0)
-
-#endif /* RTE_MBUF_REFCNT */
-
/**
* Sanity checks on an mbuf.
if (rte_mempool_get(mp, &mb) < 0)
return NULL;
m = (struct rte_mbuf *)mb;
-#ifdef RTE_MBUF_REFCNT
RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0);
rte_mbuf_refcnt_set(m, 1);
-#endif /* RTE_MBUF_REFCNT */
return (m);
}
static inline void __attribute__((always_inline))
__rte_mbuf_raw_free(struct rte_mbuf *m)
{
-#ifdef RTE_MBUF_REFCNT
RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0);
-#endif /* RTE_MBUF_REFCNT */
rte_mempool_put(m->pool, m);
}
*/
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.
+ *
+ * @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.
+ * @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.
+ * @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
+ * - 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_pktmbuf_pool_create(const char *name, unsigned n,
+ unsigned cache_size, uint16_t priv_size, uint16_t data_room_size,
+ int socket_id);
+
+/**
+ * Get the data room size of mbufs stored in a pktmbuf_pool
+ *
+ * The data room size is the amount of data that can be stored in a
+ * mbuf including the headroom (RTE_PKTMBUF_HEADROOM).
+ *
+ * @param mp
+ * The packet mbuf pool.
+ * @return
+ * The data room size of mbufs stored in this mempool.
+ */
+static inline uint16_t
+rte_pktmbuf_data_room_size(struct rte_mempool *mp)
+{
+ struct rte_pktmbuf_pool_private *mbp_priv;
+
+ mbp_priv = (struct rte_pktmbuf_pool_private *)rte_mempool_get_priv(mp);
+ return mbp_priv->mbuf_data_room_size;
+}
+
+/**
+ * Get the application private size of mbufs stored in a pktmbuf_pool
+ *
+ * The private size of mbuf is a zone located between the rte_mbuf
+ * structure and the data buffer where an application can store data
+ * associated to a packet.
+ *
+ * @param mp
+ * The packet mbuf pool.
+ * @return
+ * The private size of mbufs stored in this mempool.
+ */
+static inline uint16_t
+rte_pktmbuf_priv_size(struct rte_mempool *mp)
+{
+ struct rte_pktmbuf_pool_private *mbp_priv;
+
+ mbp_priv = (struct rte_pktmbuf_pool_private *)rte_mempool_get_priv(mp);
+ return mbp_priv->mbuf_priv_size;
+}
+
/**
* Reset the fields of a packet mbuf to their default values.
*
return (m);
}
-#ifdef RTE_MBUF_REFCNT
-
/**
* Attach packet mbuf to another packet mbuf.
+ *
* After attachment we refer the mbuf we attached as 'indirect',
* while mbuf we attached to as 'direct'.
* Right now, not supported:
- * - attachment to indirect mbuf (e.g. - md has to be direct).
* - attachment for already indirect mbuf (e.g. - mi has to be direct).
* - mbuf we trying to attach (mi) is used by someone else
* e.g. it's reference counter is greater then 1.
*
* @param mi
* The indirect packet mbuf.
- * @param md
- * The direct packet mbuf.
+ * @param m
+ * The packet mbuf we're attaching to.
*/
-
-static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
+static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m)
{
- RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(md) &&
- RTE_MBUF_DIRECT(mi) &&
+ struct rte_mbuf *md;
+
+ RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(mi) &&
rte_mbuf_refcnt_read(mi) == 1);
+ /* if m is not direct, get the mbuf that embeds the data */
+ if (RTE_MBUF_DIRECT(m))
+ md = m;
+ else
+ md = rte_mbuf_from_indirect(m);
+
rte_mbuf_refcnt_update(md, 1);
- mi->buf_physaddr = md->buf_physaddr;
- mi->buf_addr = md->buf_addr;
- mi->buf_len = md->buf_len;
-
- mi->next = md->next;
- mi->data_off = md->data_off;
- mi->data_len = md->data_len;
- mi->port = md->port;
- mi->vlan_tci = md->vlan_tci;
- mi->tx_offload = md->tx_offload;
- mi->hash = md->hash;
+ mi->priv_size = m->priv_size;
+ mi->buf_physaddr = m->buf_physaddr;
+ 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;
+ mi->vlan_tci = m->vlan_tci;
+ mi->tx_offload = m->tx_offload;
+ mi->hash = m->hash;
mi->next = NULL;
mi->pkt_len = mi->data_len;
mi->nb_segs = 1;
- mi->ol_flags = md->ol_flags;
- mi->packet_type = md->packet_type;
+ mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF;
+ mi->packet_type = m->packet_type;
__rte_mbuf_sanity_check(mi, 1);
- __rte_mbuf_sanity_check(md, 0);
+ __rte_mbuf_sanity_check(m, 0);
}
/**
- * Detach an indirect packet mbuf -
+ * Detach an indirect packet mbuf.
+ *
* - 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.
* @param m
* The indirect attached packet mbuf.
*/
-
static inline void rte_pktmbuf_detach(struct rte_mbuf *m)
{
- const struct rte_mempool *mp = m->pool;
- void *buf = RTE_MBUF_TO_BADDR(m);
- uint32_t buf_len = mp->elt_size - sizeof(*m);
- m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof (*m);
-
- m->buf_addr = buf;
- m->buf_len = (uint16_t)buf_len;
+ struct rte_mempool *mp = m->pool;
+ uint32_t mbuf_size, buf_len, priv_size;
- m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ?
- RTE_PKTMBUF_HEADROOM : m->buf_len;
+ priv_size = rte_pktmbuf_priv_size(mp);
+ mbuf_size = sizeof(struct rte_mbuf) + priv_size;
+ buf_len = rte_pktmbuf_data_room_size(mp);
+ m->priv_size = priv_size;
+ 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);
m->data_len = 0;
+ m->ol_flags = 0;
}
-#endif /* RTE_MBUF_REFCNT */
-
-
static inline struct rte_mbuf* __attribute__((always_inline))
__rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
{
__rte_mbuf_sanity_check(m, 0);
-#ifdef RTE_MBUF_REFCNT
+ /*
+ * Check to see if this is the last reference to the mbuf.
+ * Note: the double check here is deliberate. If the ref_cnt is "atomic"
+ * the call to "refcnt_update" is a very expensive operation, so we
+ * don't want to call it in the case where we know we are the holder
+ * of the last reference to this mbuf i.e. ref_cnt == 1.
+ * If however, ref_cnt != 1, it's still possible that we may still be
+ * the final decrementer of the count, so we need to check that
+ * result also, to make sure the mbuf is freed properly.
+ */
if (likely (rte_mbuf_refcnt_read(m) == 1) ||
likely (rte_mbuf_refcnt_update(m, -1) == 0)) {
- struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr);
rte_mbuf_refcnt_set(m, 0);
* - detach mbuf
* - free attached mbuf segment
*/
- if (unlikely (md != m)) {
+ if (RTE_MBUF_INDIRECT(m)) {
+ struct rte_mbuf *md = rte_mbuf_from_indirect(m);
rte_pktmbuf_detach(m);
if (rte_mbuf_refcnt_update(md, -1) == 0)
__rte_mbuf_raw_free(md);
}
-#endif
return(m);
-#ifdef RTE_MBUF_REFCNT
}
return (NULL);
-#endif
}
/**
}
}
-#ifdef RTE_MBUF_REFCNT
-
/**
* Creates a "clone" of the given packet mbuf.
*
} while ((m = m->next) != NULL);
}
-#endif /* RTE_MBUF_REFCNT */
-
/**
* Get the headroom in a packet mbuf.
*