diff options
Diffstat (limited to 'lib/librte_mbuf')
| -rw-r--r-- | lib/librte_mbuf/Makefile | 3 | ||||
| -rw-r--r-- | lib/librte_mbuf/meson.build | 1 | ||||
| -rw-r--r-- | lib/librte_mbuf/rte_mbuf.c | 26 | ||||
| -rw-r--r-- | lib/librte_mbuf/rte_mbuf.h | 540 | ||||
| -rw-r--r-- | lib/librte_mbuf/rte_mbuf_pool_ops.c | 14 | ||||
| -rw-r--r-- | lib/librte_mbuf/rte_mbuf_pool_ops.h | 13 | ||||
| -rw-r--r-- | lib/librte_mbuf/rte_mbuf_ptype.c | 3 | ||||
| -rw-r--r-- | lib/librte_mbuf/rte_mbuf_ptype.h | 53 | ||||
| -rw-r--r-- | lib/librte_mbuf/rte_mbuf_version.map | 4 |
9 files changed, 472 insertions, 185 deletions
diff --git a/lib/librte_mbuf/Makefile b/lib/librte_mbuf/Makefile index 367568ae..e2b98a25 100644 --- a/lib/librte_mbuf/Makefile +++ b/lib/librte_mbuf/Makefile @@ -6,13 +6,12 @@ include $(RTE_SDK)/mk/rte.vars.mk # library name LIB = librte_mbuf.a -CFLAGS += -DALLOW_EXPERIMENTAL_API CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -O3 LDLIBS += -lrte_eal -lrte_mempool EXPORT_MAP := rte_mbuf_version.map -LIBABIVER := 3 +LIBABIVER := 4 # all source are stored in SRCS-y SRCS-$(CONFIG_RTE_LIBRTE_MBUF) := rte_mbuf.c rte_mbuf_ptype.c rte_mbuf_pool_ops.c diff --git a/lib/librte_mbuf/meson.build b/lib/librte_mbuf/meson.build index 869c17c1..45ffb0db 100644 --- a/lib/librte_mbuf/meson.build +++ b/lib/librte_mbuf/meson.build @@ -2,7 +2,6 @@ # Copyright(c) 2017 Intel Corporation version = 3 -allow_experimental_apis = true sources = files('rte_mbuf.c', 'rte_mbuf_ptype.c', 'rte_mbuf_pool_ops.c') headers = files('rte_mbuf.h', 'rte_mbuf_ptype.h', 'rte_mbuf_pool_ops.h') deps += ['mempool'] diff --git a/lib/librte_mbuf/rte_mbuf.c b/lib/librte_mbuf/rte_mbuf.c index 091d388d..e714c5a5 100644 --- a/lib/librte_mbuf/rte_mbuf.c +++ b/lib/librte_mbuf/rte_mbuf.c @@ -33,21 +33,6 @@ #include <rte_memcpy.h> /* - * ctrlmbuf constructor, given as a callback function to - * rte_mempool_obj_iter() or rte_mempool_create() - */ -void -rte_ctrlmbuf_init(struct rte_mempool *mp, - __attribute__((unused)) void *opaque_arg, - void *_m, - __attribute__((unused)) unsigned i) -{ - struct rte_mbuf *m = _m; - rte_pktmbuf_init(mp, opaque_arg, _m, i); - m->ol_flags |= CTRL_MBUF_FLAG; -} - -/* * pktmbuf pool constructor, given as a callback function to * rte_mempool_create(), or called directly if using * rte_mempool_create_empty()/rte_mempool_populate() @@ -122,7 +107,7 @@ rte_pktmbuf_init(struct rte_mempool *mp, } /* Helper to create a mbuf pool with given mempool ops name*/ -struct rte_mempool * __rte_experimental +struct rte_mempool * 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) @@ -405,6 +390,9 @@ const char *rte_get_tx_ol_flag_name(uint64_t mask) case PKT_TX_TUNNEL_IPIP: return "PKT_TX_TUNNEL_IPIP"; case PKT_TX_TUNNEL_GENEVE: return "PKT_TX_TUNNEL_GENEVE"; case PKT_TX_TUNNEL_MPLSINUDP: return "PKT_TX_TUNNEL_MPLSINUDP"; + case PKT_TX_TUNNEL_VXLAN_GPE: return "PKT_TX_TUNNEL_VXLAN_GPE"; + case PKT_TX_TUNNEL_IP: return "PKT_TX_TUNNEL_IP"; + case PKT_TX_TUNNEL_UDP: return "PKT_TX_TUNNEL_UDP"; case PKT_TX_MACSEC: return "PKT_TX_MACSEC"; case PKT_TX_SEC_OFFLOAD: return "PKT_TX_SEC_OFFLOAD"; default: return NULL; @@ -439,6 +427,12 @@ rte_get_tx_ol_flag_list(uint64_t mask, char *buf, size_t buflen) "PKT_TX_TUNNEL_NONE" }, { PKT_TX_TUNNEL_MPLSINUDP, PKT_TX_TUNNEL_MASK, "PKT_TX_TUNNEL_NONE" }, + { PKT_TX_TUNNEL_VXLAN_GPE, PKT_TX_TUNNEL_MASK, + "PKT_TX_TUNNEL_NONE" }, + { PKT_TX_TUNNEL_IP, PKT_TX_TUNNEL_MASK, + "PKT_TX_TUNNEL_NONE" }, + { PKT_TX_TUNNEL_UDP, PKT_TX_TUNNEL_MASK, + "PKT_TX_TUNNEL_NONE" }, { PKT_TX_MACSEC, PKT_TX_MACSEC, NULL }, { PKT_TX_SEC_OFFLOAD, PKT_TX_SEC_OFFLOAD, NULL }, }; diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 62740254..9ce5d76d 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -201,15 +201,44 @@ extern "C" { /** * 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. + * The tunnel type must be specified for TSO or checksum on the inner part + * of tunnel packets. + * These flags can be used with PKT_TX_TCP_SEG for TSO, or PKT_TX_xxx_CKSUM. + * The mbuf fields for inner and outer header lengths are required: + * outer_l2_len, outer_l3_len, l2_len, l3_len, l4_len and tso_segsz for TSO. */ #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) -/**< TX packet with MPLS-in-UDP RFC 7510 header. */ +/** TX packet with MPLS-in-UDP RFC 7510 header. */ #define PKT_TX_TUNNEL_MPLSINUDP (0x5ULL << 45) +#define PKT_TX_TUNNEL_VXLAN_GPE (0x6ULL << 45) +/** + * Generic IP encapsulated tunnel type, used for TSO and checksum offload. + * It can be used for tunnels which are not standards or listed above. + * It is preferred to use specific tunnel flags like PKT_TX_TUNNEL_GRE + * or PKT_TX_TUNNEL_IPIP if possible. + * The ethdev must be configured with DEV_TX_OFFLOAD_IP_TNL_TSO. + * Outer and inner checksums are done according to the existing flags like + * PKT_TX_xxx_CKSUM. + * Specific tunnel headers that contain payload length, sequence id + * or checksum are not expected to be updated. + */ +#define PKT_TX_TUNNEL_IP (0xDULL << 45) +/** + * Generic UDP encapsulated tunnel type, used for TSO and checksum offload. + * UDP tunnel type implies outer IP layer. + * It can be used for tunnels which are not standards or listed above. + * It is preferred to use specific tunnel flags like PKT_TX_TUNNEL_VXLAN + * if possible. + * The ethdev must be configured with DEV_TX_OFFLOAD_UDP_TNL_TSO. + * Outer and inner checksums are done according to the existing flags like + * PKT_TX_xxx_CKSUM. + * Specific tunnel headers that contain payload length, sequence id + * or checksum are not expected to be updated. + */ +#define PKT_TX_TUNNEL_UDP (0xEULL << 45) /* add new TX TUNNEL type here */ #define PKT_TX_TUNNEL_MASK (0xFULL << 45) @@ -226,12 +255,8 @@ extern "C" { * - set the PKT_TX_TCP_SEG flag in mbuf->ol_flags (this flag implies * PKT_TX_TCP_CKSUM) * - set the flag PKT_TX_IPV4 or PKT_TX_IPV6 - * - if it's IPv4, set the PKT_TX_IP_CKSUM flag and write the IP checksum - * to 0 in the packet + * - if it's IPv4, set the PKT_TX_IP_CKSUM flag * - fill the mbuf offload information: l2_len, l3_len, l4_len, tso_segsz - * - calculate the pseudo header checksum without taking ip_len in account, - * 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 << 50) @@ -244,9 +269,6 @@ extern "C" { * - fill l2_len and l3_len in mbuf * - set the flags PKT_TX_TCP_CKSUM, PKT_TX_SCTP_CKSUM or PKT_TX_UDP_CKSUM * - set the flag PKT_TX_IPV4 or PKT_TX_IPV6 - * - calculate the pseudo header checksum and set it in the L4 header (only - * for TCP or UDP). See rte_ipv4_phdr_cksum() and rte_ipv6_phdr_cksum(). - * For SCTP, set the crc field to 0. */ #define PKT_TX_L4_NO_CKSUM (0ULL << 52) /**< Disable L4 cksum of TX pkt. */ #define PKT_TX_TCP_CKSUM (1ULL << 52) /**< TCP cksum of TX pkt. computed by NIC. */ @@ -258,7 +280,6 @@ extern "C" { * 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) @@ -288,10 +309,8 @@ extern "C" { /** * 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 + * flag PKT_TX_OUTER_IPV4 should also be set by the application, although + * a PMD will only check PKT_TX_OUTER_IP_CKSUM. * - fill the mbuf offload information: outer_l2_len, outer_l3_len */ #define PKT_TX_OUTER_IP_CKSUM (1ULL << 58) @@ -326,13 +345,13 @@ extern "C" { PKT_TX_MACSEC | \ PKT_TX_SEC_OFFLOAD) -#define __RESERVED (1ULL << 61) /**< reserved for future mbuf use */ +/** + * Mbuf having an external buffer attached. shinfo in mbuf must be filled. + */ +#define EXT_ATTACHED_MBUF (1ULL << 61) #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 @@ -569,8 +588,27 @@ struct rte_mbuf { /** Sequence number. See also rte_reorder_insert(). */ uint32_t seqn; + /** Shared data for external buffer attached to mbuf. See + * rte_pktmbuf_attach_extbuf(). + */ + struct rte_mbuf_ext_shared_info *shinfo; + } __rte_cache_aligned; +/** + * Function typedef of callback to free externally attached buffer. + */ +typedef void (*rte_mbuf_extbuf_free_callback_t)(void *addr, void *opaque); + +/** + * Shared data at the end of an external buffer. + */ +struct rte_mbuf_ext_shared_info { + rte_mbuf_extbuf_free_callback_t free_cb; /**< Free callback function */ + void *fcb_opaque; /**< Free callback argument */ + rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ +}; + /**< Maximum number of nb_segs allowed. */ #define RTE_MBUF_MAX_NB_SEGS UINT16_MAX @@ -691,14 +729,53 @@ rte_mbuf_to_baddr(struct rte_mbuf *md) } /** - * Returns TRUE if given mbuf is indirect, or FALSE otherwise. + * Return the starting address of the private data area embedded in + * the given mbuf. + * + * Note that no check is made to ensure that a private data area + * actually exists in the supplied mbuf. + * + * @param m + * The pointer to the mbuf. + * @return + * The starting address of the private data area of the given mbuf. + */ +static inline void * __rte_experimental +rte_mbuf_to_priv(struct rte_mbuf *m) +{ + return RTE_PTR_ADD(m, sizeof(struct rte_mbuf)); +} + +/** + * Returns TRUE if given mbuf is cloned by mbuf indirection, or FALSE + * otherwise. + * + * If a mbuf has its data in another mbuf and references it by mbuf + * indirection, this mbuf can be defined as a cloned mbuf. + */ +#define RTE_MBUF_CLONED(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF) + +/** + * Deprecated. + * Use RTE_MBUF_CLONED(). + */ +#define RTE_MBUF_INDIRECT(mb) RTE_MBUF_CLONED(mb) + +/** + * Returns TRUE if given mbuf has an external buffer, or FALSE otherwise. + * + * External buffer is a user-provided anonymous buffer. */ -#define RTE_MBUF_INDIRECT(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF) +#define RTE_MBUF_HAS_EXTBUF(mb) ((mb)->ol_flags & EXT_ATTACHED_MBUF) /** * Returns TRUE if given mbuf is direct, or FALSE otherwise. + * + * If a mbuf embeds its own data after the rte_mbuf structure, this mbuf + * can be defined as a direct mbuf. */ -#define RTE_MBUF_DIRECT(mb) (!RTE_MBUF_INDIRECT(mb)) +#define RTE_MBUF_DIRECT(mb) \ + (!((mb)->ol_flags & (IND_ATTACHED_MBUF | EXT_ATTACHED_MBUF))) /** * Private data in case of pktmbuf pool. @@ -748,7 +825,7 @@ rte_mbuf_refcnt_read(const struct rte_mbuf *m) static inline void rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) { - rte_atomic16_set(&m->refcnt_atomic, new_value); + rte_atomic16_set(&m->refcnt_atomic, (int16_t)new_value); } /* internal */ @@ -778,8 +855,9 @@ rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) * reference counter can occur. */ if (likely(rte_mbuf_refcnt_read(m) == 1)) { - rte_mbuf_refcnt_set(m, 1 + value); - return 1 + value; + ++value; + rte_mbuf_refcnt_set(m, (uint16_t)value); + return (uint16_t)value; } return __rte_mbuf_refcnt_update(m, value); @@ -824,6 +902,59 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) #endif /* RTE_MBUF_REFCNT_ATOMIC */ +/** + * Reads the refcnt of an external buffer. + * + * @param shinfo + * Shared data of the external buffer. + * @return + * Reference count number. + */ +static inline uint16_t +rte_mbuf_ext_refcnt_read(const struct rte_mbuf_ext_shared_info *shinfo) +{ + return (uint16_t)(rte_atomic16_read(&shinfo->refcnt_atomic)); +} + +/** + * Set refcnt of an external buffer. + * + * @param shinfo + * Shared data of the external buffer. + * @param new_value + * Value set + */ +static inline void +rte_mbuf_ext_refcnt_set(struct rte_mbuf_ext_shared_info *shinfo, + uint16_t new_value) +{ + rte_atomic16_set(&shinfo->refcnt_atomic, (int16_t)new_value); +} + +/** + * Add given value to refcnt of an external buffer and return its new + * value. + * + * @param shinfo + * Shared data of the external buffer. + * @param value + * Value to add/subtract + * @return + * Updated value + */ +static inline uint16_t +rte_mbuf_ext_refcnt_update(struct rte_mbuf_ext_shared_info *shinfo, + int16_t value) +{ + if (likely(rte_mbuf_ext_refcnt_read(shinfo) == 1)) { + ++value; + rte_mbuf_ext_refcnt_set(shinfo, (uint16_t)value); + return (uint16_t)value; + } + + return (uint16_t)rte_atomic16_add_return(&shinfo->refcnt_atomic, value); +} + /** Mbuf prefetch */ #define RTE_MBUF_PREFETCH_TO_FREE(m) do { \ if ((m) != NULL) \ @@ -915,89 +1046,6 @@ __rte_mbuf_raw_free(struct rte_mbuf *m) rte_mbuf_raw_free(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_obj_iter() or 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 is the opaque argument passed to - * rte_mempool_obj_iter() or 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) -{ - return !!(m->ol_flags & CTRL_MBUF_FLAG); -} - -/* Operations on pkt mbuf */ - /** * The packet mbuf constructor. * @@ -1116,7 +1164,7 @@ rte_pktmbuf_pool_create(const char *name, unsigned n, * - 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 +struct rte_mempool * 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); @@ -1172,7 +1220,8 @@ rte_pktmbuf_priv_size(struct rte_mempool *mp) */ static inline void rte_pktmbuf_reset_headroom(struct rte_mbuf *m) { - m->data_off = RTE_MIN(RTE_PKTMBUF_HEADROOM, (uint16_t)m->buf_len); + m->data_off = (uint16_t)RTE_MIN((uint16_t)RTE_PKTMBUF_HEADROOM, + (uint16_t)m->buf_len); } /** @@ -1281,11 +1330,161 @@ static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool, } /** + * Initialize shared data at the end of an external buffer before attaching + * to a mbuf by ``rte_pktmbuf_attach_extbuf()``. This is not a mandatory + * initialization but a helper function to simply spare a few bytes at the + * end of the buffer for shared data. If shared data is allocated + * separately, this should not be called but application has to properly + * initialize the shared data according to its need. + * + * Free callback and its argument is saved and the refcnt is set to 1. + * + * @warning + * The value of buf_len will be reduced to RTE_PTR_DIFF(shinfo, buf_addr) + * after this initialization. This shall be used for + * ``rte_pktmbuf_attach_extbuf()`` + * + * @param buf_addr + * The pointer to the external buffer. + * @param [in,out] buf_len + * The pointer to length of the external buffer. Input value must be + * larger than the size of ``struct rte_mbuf_ext_shared_info`` and + * padding for alignment. If not enough, this function will return NULL. + * Adjusted buffer length will be returned through this pointer. + * @param free_cb + * Free callback function to call when the external buffer needs to be + * freed. + * @param fcb_opaque + * Argument for the free callback function. + * + * @return + * A pointer to the initialized shared data on success, return NULL + * otherwise. + */ +static inline struct rte_mbuf_ext_shared_info * +rte_pktmbuf_ext_shinfo_init_helper(void *buf_addr, uint16_t *buf_len, + rte_mbuf_extbuf_free_callback_t free_cb, void *fcb_opaque) +{ + struct rte_mbuf_ext_shared_info *shinfo; + void *buf_end = RTE_PTR_ADD(buf_addr, *buf_len); + void *addr; + + addr = RTE_PTR_ALIGN_FLOOR(RTE_PTR_SUB(buf_end, sizeof(*shinfo)), + sizeof(uintptr_t)); + if (addr <= buf_addr) + return NULL; + + shinfo = (struct rte_mbuf_ext_shared_info *)addr; + shinfo->free_cb = free_cb; + shinfo->fcb_opaque = fcb_opaque; + rte_mbuf_ext_refcnt_set(shinfo, 1); + + *buf_len = (uint16_t)RTE_PTR_DIFF(shinfo, buf_addr); + return shinfo; +} + +/** + * Attach an external buffer to a mbuf. + * + * User-managed anonymous buffer can be attached to an mbuf. When attaching + * it, corresponding free callback function and its argument should be + * provided via shinfo. This callback function will be called once all the + * mbufs are detached from the buffer (refcnt becomes zero). + * + * The headroom for the attaching mbuf will be set to zero and this can be + * properly adjusted after attachment. For example, ``rte_pktmbuf_adj()`` + * or ``rte_pktmbuf_reset_headroom()`` might be used. + * + * More mbufs can be attached to the same external buffer by + * ``rte_pktmbuf_attach()`` once the external buffer has been attached by + * this API. + * + * Detachment can be done by either ``rte_pktmbuf_detach_extbuf()`` or + * ``rte_pktmbuf_detach()``. + * + * Memory for shared data must be provided and user must initialize all of + * the content properly, escpecially free callback and refcnt. The pointer + * of shared data will be stored in m->shinfo. + * ``rte_pktmbuf_ext_shinfo_init_helper`` can help to simply spare a few + * bytes at the end of buffer for the shared data, store free callback and + * its argument and set the refcnt to 1. The following is an example: + * + * struct rte_mbuf_ext_shared_info *shinfo = + * rte_pktmbuf_ext_shinfo_init_helper(buf_addr, &buf_len, + * free_cb, fcb_arg); + * rte_pktmbuf_attach_extbuf(m, buf_addr, buf_iova, buf_len, shinfo); + * rte_pktmbuf_reset_headroom(m); + * rte_pktmbuf_adj(m, data_len); + * + * Attaching an external buffer is quite similar to mbuf indirection in + * replacing buffer addresses and length of a mbuf, but a few differences: + * - When an indirect mbuf is attached, refcnt of the direct mbuf would be + * 2 as long as the direct mbuf itself isn't freed after the attachment. + * In such cases, the buffer area of a direct mbuf must be read-only. But + * external buffer has its own refcnt and it starts from 1. Unless + * multiple mbufs are attached to a mbuf having an external buffer, the + * external buffer is writable. + * - There's no need to allocate buffer from a mempool. Any buffer can be + * attached with appropriate free callback and its IO address. + * - Smaller metadata is required to maintain shared data such as refcnt. + * + * @warning + * @b EXPERIMENTAL: This API may change without prior notice. + * Once external buffer is enabled by allowing experimental API, + * ``RTE_MBUF_DIRECT()`` and ``RTE_MBUF_INDIRECT()`` are no longer + * exclusive. A mbuf can be considered direct if it is neither indirect nor + * having external buffer. + * + * @param m + * The pointer to the mbuf. + * @param buf_addr + * The pointer to the external buffer. + * @param buf_iova + * IO address of the external buffer. + * @param buf_len + * The size of the external buffer. + * @param shinfo + * User-provided memory for shared data of the external buffer. + */ +static inline void __rte_experimental +rte_pktmbuf_attach_extbuf(struct rte_mbuf *m, void *buf_addr, + rte_iova_t buf_iova, uint16_t buf_len, + struct rte_mbuf_ext_shared_info *shinfo) +{ + /* mbuf should not be read-only */ + RTE_ASSERT(RTE_MBUF_DIRECT(m) && rte_mbuf_refcnt_read(m) == 1); + RTE_ASSERT(shinfo->free_cb != NULL); + + m->buf_addr = buf_addr; + m->buf_iova = buf_iova; + m->buf_len = buf_len; + + m->data_len = 0; + m->data_off = 0; + + m->ol_flags |= EXT_ATTACHED_MBUF; + m->shinfo = shinfo; +} + +/** + * Detach the external buffer attached to a mbuf, same as + * ``rte_pktmbuf_detach()`` + * + * @param m + * The mbuf having external buffer. + */ +#define rte_pktmbuf_detach_extbuf(m) rte_pktmbuf_detach(m) + +/** * 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. + * If the mbuf we are attaching to isn't a direct buffer and is attached to + * an external buffer, the mbuf being attached will be attached to the + * external buffer instead of mbuf indirection. + * + * Otherwise, the mbuf will be indirectly attached. 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). @@ -1299,19 +1498,20 @@ static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool, */ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) { - struct rte_mbuf *md; - RTE_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); + if (RTE_MBUF_HAS_EXTBUF(m)) { + rte_mbuf_ext_refcnt_update(m->shinfo, 1); + mi->ol_flags = m->ol_flags; + mi->shinfo = m->shinfo; + } else { + /* if m is not direct, get the mbuf that embeds the data */ + rte_mbuf_refcnt_update(rte_mbuf_from_indirect(m), 1); + mi->priv_size = m->priv_size; + mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF; + } - rte_mbuf_refcnt_update(md, 1); - mi->priv_size = m->priv_size; mi->buf_iova = m->buf_iova; mi->buf_addr = m->buf_addr; mi->buf_len = m->buf_len; @@ -1327,7 +1527,6 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) mi->next = NULL; mi->pkt_len = mi->data_len; mi->nb_segs = 1; - mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF; mi->packet_type = m->packet_type; mi->timestamp = m->timestamp; @@ -1336,12 +1535,52 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) } /** - * Detach an indirect packet mbuf. + * @internal used by rte_pktmbuf_detach(). + * + * Decrement the reference counter of the external buffer. When the + * reference counter becomes 0, the buffer is freed by pre-registered + * callback. + */ +static inline void +__rte_pktmbuf_free_extbuf(struct rte_mbuf *m) +{ + RTE_ASSERT(RTE_MBUF_HAS_EXTBUF(m)); + RTE_ASSERT(m->shinfo != NULL); + + if (rte_mbuf_ext_refcnt_update(m->shinfo, -1) == 0) + m->shinfo->free_cb(m->buf_addr, m->shinfo->fcb_opaque); +} + +/** + * @internal used by rte_pktmbuf_detach(). + * + * Decrement the direct mbuf's reference counter. When the reference + * counter becomes 0, the direct mbuf is freed. + */ +static inline void +__rte_pktmbuf_free_direct(struct rte_mbuf *m) +{ + struct rte_mbuf *md; + + RTE_ASSERT(RTE_MBUF_INDIRECT(m)); + + md = rte_mbuf_from_indirect(m); + + 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); + } +} + +/** + * Detach a packet mbuf from external buffer or direct buffer. * + * - decrement refcnt and free the external/direct buffer if refcnt + * becomes zero. * - restore original mbuf address and length values. * - reset pktmbuf data and data_len to their default values. - * - 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. * @@ -1350,12 +1589,17 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) */ 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; + uint32_t mbuf_size, buf_len; + uint16_t priv_size; + + if (RTE_MBUF_HAS_EXTBUF(m)) + __rte_pktmbuf_free_extbuf(m); + else + __rte_pktmbuf_free_direct(m); priv_size = rte_pktmbuf_priv_size(mp); - mbuf_size = sizeof(struct rte_mbuf) + priv_size; + mbuf_size = (uint32_t)(sizeof(struct rte_mbuf) + priv_size); buf_len = rte_pktmbuf_data_room_size(mp); m->priv_size = priv_size; @@ -1365,13 +1609,6 @@ static inline void rte_pktmbuf_detach(struct rte_mbuf *m) rte_pktmbuf_reset_headroom(m); m->data_len = 0; m->ol_flags = 0; - - 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); - } } /** @@ -1395,7 +1632,7 @@ rte_pktmbuf_prefree_seg(struct rte_mbuf *m) if (likely(rte_mbuf_refcnt_read(m) == 1)) { - if (RTE_MBUF_INDIRECT(m)) + if (!RTE_MBUF_DIRECT(m)) rte_pktmbuf_detach(m); if (m->next != NULL) { @@ -1407,7 +1644,7 @@ rte_pktmbuf_prefree_seg(struct rte_mbuf *m) } else if (__rte_mbuf_refcnt_update(m, -1) == 0) { - if (RTE_MBUF_INDIRECT(m)) + if (!RTE_MBUF_DIRECT(m)) rte_pktmbuf_detach(m); if (m->next != NULL) { @@ -1690,7 +1927,10 @@ static inline char *rte_pktmbuf_prepend(struct rte_mbuf *m, if (unlikely(len > rte_pktmbuf_headroom(m))) return NULL; - m->data_off -= len; + /* NB: elaborating the subtraction like this instead of using + * -= allows us to ensure the result type is uint16_t + * avoiding compiler warnings on gcc 8.1 at least */ + m->data_off = (uint16_t)(m->data_off - len); m->data_len = (uint16_t)(m->data_len + len); m->pkt_len = (m->pkt_len + len); @@ -1750,8 +1990,11 @@ static inline char *rte_pktmbuf_adj(struct rte_mbuf *m, uint16_t len) if (unlikely(len > m->data_len)) return NULL; + /* NB: elaborating the addition like this instead of using + * += allows us to ensure the result type is uint16_t + * avoiding compiler warnings on gcc 8.1 at least */ m->data_len = (uint16_t)(m->data_len - len); - m->data_off += len; + m->data_off = (uint16_t)(m->data_off + len); m->pkt_len = (m->pkt_len - len); return (char *)m->buf_addr + m->data_off; } @@ -1863,8 +2106,11 @@ static inline int rte_pktmbuf_chain(struct rte_mbuf *head, struct rte_mbuf *tail cur_tail = rte_pktmbuf_lastseg(head); cur_tail->next = tail; - /* accumulate number of segments and total length. */ - head->nb_segs += tail->nb_segs; + /* accumulate number of segments and total length. + * NB: elaborating the addition like this instead of using + * -= allows us to ensure the result type is uint16_t + * avoiding compiler warnings on gcc 8.1 at least */ + head->nb_segs = (uint16_t)(head->nb_segs + tail->nb_segs); head->pkt_len += tail->pkt_len; /* pkt_len is only set in the head */ @@ -1894,7 +2140,11 @@ rte_validate_tx_offload(const struct rte_mbuf *m) return 0; if (ol_flags & PKT_TX_OUTER_IP_CKSUM) - inner_l3_offset += m->outer_l2_len + m->outer_l3_len; + /* NB: elaborating the addition like this instead of using + * += gives the result uint64_t type instead of int, + * avoiding compiler warnings on gcc 8.1 at least */ + inner_l3_offset = inner_l3_offset + m->outer_l2_len + + m->outer_l3_len; /* Headers are fragmented */ if (rte_pktmbuf_data_len(m) < inner_l3_offset + m->l3_len + m->l4_len) @@ -1939,7 +2189,7 @@ rte_validate_tx_offload(const struct rte_mbuf *m) static inline int rte_pktmbuf_linearize(struct rte_mbuf *mbuf) { - int seg_len, copy_len; + size_t seg_len, copy_len; struct rte_mbuf *m; struct rte_mbuf *m_next; char *buffer; diff --git a/lib/librte_mbuf/rte_mbuf_pool_ops.c b/lib/librte_mbuf/rte_mbuf_pool_ops.c index 48cc3420..5722976f 100644 --- a/lib/librte_mbuf/rte_mbuf_pool_ops.c +++ b/lib/librte_mbuf/rte_mbuf_pool_ops.c @@ -9,7 +9,7 @@ #include <rte_errno.h> #include <rte_mbuf_pool_ops.h> -int __rte_experimental +int rte_mbuf_set_platform_mempool_ops(const char *ops_name) { const struct rte_memzone *mz; @@ -23,7 +23,7 @@ rte_mbuf_set_platform_mempool_ops(const char *ops_name) RTE_MEMPOOL_OPS_NAMESIZE, SOCKET_ID_ANY, 0); if (mz == NULL) return -rte_errno; - strncpy(mz->addr, ops_name, strlen(ops_name)); + strcpy(mz->addr, ops_name); return 0; } else if (strcmp(mz->addr, ops_name) == 0) { return 0; @@ -35,7 +35,7 @@ rte_mbuf_set_platform_mempool_ops(const char *ops_name) return -EEXIST; } -const char * __rte_experimental +const char * rte_mbuf_platform_mempool_ops(void) { const struct rte_memzone *mz; @@ -46,7 +46,7 @@ rte_mbuf_platform_mempool_ops(void) return mz->addr; } -int __rte_experimental +int rte_mbuf_set_user_mempool_ops(const char *ops_name) { const struct rte_memzone *mz; @@ -62,12 +62,12 @@ rte_mbuf_set_user_mempool_ops(const char *ops_name) return -rte_errno; } - strncpy(mz->addr, ops_name, strlen(ops_name)); + strcpy(mz->addr, ops_name); return 0; } -const char * __rte_experimental +const char * rte_mbuf_user_mempool_ops(void) { const struct rte_memzone *mz; @@ -79,7 +79,7 @@ rte_mbuf_user_mempool_ops(void) } /* Return mbuf pool ops name */ -const char * __rte_experimental +const char * rte_mbuf_best_mempool_ops(void) { /* User defined mempool ops takes the priority */ diff --git a/lib/librte_mbuf/rte_mbuf_pool_ops.h b/lib/librte_mbuf/rte_mbuf_pool_ops.h index ebf5bf0f..7ed95a49 100644 --- a/lib/librte_mbuf/rte_mbuf_pool_ops.h +++ b/lib/librte_mbuf/rte_mbuf_pool_ops.h @@ -12,9 +12,6 @@ * These APIs are for configuring the mbuf pool ops names to be largely used by * rte_pktmbuf_pool_create(). However, this can also be used to set and inquire * the best mempool ops available. - * - * @warning - * @b EXPERIMENTAL: this API may change without prior notice */ #include <rte_compat.h> @@ -34,7 +31,7 @@ extern "C" { * - On success, zero. * - On failure, a negative value. */ -int __rte_experimental +int rte_mbuf_set_platform_mempool_ops(const char *ops_name); /** @@ -46,7 +43,7 @@ rte_mbuf_set_platform_mempool_ops(const char *ops_name); * - On success, platform pool ops name. * - On failure, NULL. */ -const char * __rte_experimental +const char * rte_mbuf_platform_mempool_ops(void); /** @@ -60,7 +57,7 @@ rte_mbuf_platform_mempool_ops(void); * - On success, zero. * - On failure, a negative value. */ -int __rte_experimental +int rte_mbuf_set_user_mempool_ops(const char *ops_name); /** @@ -72,7 +69,7 @@ rte_mbuf_set_user_mempool_ops(const char *ops_name); * - On success, user pool ops name.. * - On failure, NULL. */ -const char * __rte_experimental +const char * rte_mbuf_user_mempool_ops(void); /** @@ -87,7 +84,7 @@ rte_mbuf_user_mempool_ops(void); * @return * returns preferred mbuf pool ops name */ -const char * __rte_experimental +const char * rte_mbuf_best_mempool_ops(void); diff --git a/lib/librte_mbuf/rte_mbuf_ptype.c b/lib/librte_mbuf/rte_mbuf_ptype.c index 1feefacc..d7835e28 100644 --- a/lib/librte_mbuf/rte_mbuf_ptype.c +++ b/lib/librte_mbuf/rte_mbuf_ptype.c @@ -65,6 +65,9 @@ const char *rte_get_ptype_tunnel_name(uint32_t ptype) case RTE_PTYPE_TUNNEL_GTPU: return "TUNNEL_GTPU"; case RTE_PTYPE_TUNNEL_ESP: return "TUNNEL_ESP"; case RTE_PTYPE_TUNNEL_L2TP: return "TUNNEL_L2TP"; + case RTE_PTYPE_TUNNEL_VXLAN_GPE: return "TUNNEL_VXLAN_GPE"; + case RTE_PTYPE_TUNNEL_MPLS_IN_UDP: return "TUNNEL_MPLS_IN_UDP"; + case RTE_PTYPE_TUNNEL_MPLS_IN_GRE: return "TUNNEL_MPLS_IN_GRE"; default: return "TUNNEL_UNKNOWN"; } } diff --git a/lib/librte_mbuf/rte_mbuf_ptype.h b/lib/librte_mbuf/rte_mbuf_ptype.h index b9a33811..01acc66e 100644 --- a/lib/librte_mbuf/rte_mbuf_ptype.h +++ b/lib/librte_mbuf/rte_mbuf_ptype.h @@ -423,6 +423,53 @@ extern "C" { */ #define RTE_PTYPE_TUNNEL_L2TP 0x0000a000 /** + * VXLAN-GPE (VXLAN Generic Protocol Extension) tunneling packet type. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=17 + * | 'destination port'=4790> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=17 + * | 'destination port'=4790> + */ +#define RTE_PTYPE_TUNNEL_VXLAN_GPE 0x0000b000 +/** + * MPLS-in-GRE tunneling packet type (RFC 4023). + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=47 + * | 'protocol'=0x8847> + * or, + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=47 + * | 'protocol'=0x8848> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'protocol'=47 + * | 'protocol'=0x8847> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=47 + * | 'protocol'=0x8848> + */ +#define RTE_PTYPE_TUNNEL_MPLS_IN_GRE 0x0000c000 +/** + * MPLS-in-UDP tunneling packet type (RFC 7510). + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=17 + * | 'destination port'=6635> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=17 + * | 'destination port'=6635> + */ +#define RTE_PTYPE_TUNNEL_MPLS_IN_UDP 0x0000d000 +/** * Mask of tunneling packet types. */ #define RTE_PTYPE_TUNNEL_MASK 0x0000f000 @@ -606,9 +653,9 @@ extern "C" { #define RTE_ETH_IS_IPV4_HDR(ptype) ((ptype) & RTE_PTYPE_L3_IPV4) /** - * Check if the (outer) L3 header is IPv4. To avoid comparing IPv4 types one by - * one, bit 6 is selected to be used for IPv4 only. Then checking bit 6 can - * determine if it is an IPV4 packet. + * Check if the (outer) L3 header is IPv6. To avoid comparing IPv6 types one by + * one, bit 6 is selected to be used for IPv6 only. Then checking bit 6 can + * determine if it is an IPV6 packet. */ #define RTE_ETH_IS_IPV6_HDR(ptype) ((ptype) & RTE_PTYPE_L3_IPV6) diff --git a/lib/librte_mbuf/rte_mbuf_version.map b/lib/librte_mbuf/rte_mbuf_version.map index d418dcb8..cae68db8 100644 --- a/lib/librte_mbuf/rte_mbuf_version.map +++ b/lib/librte_mbuf/rte_mbuf_version.map @@ -1,7 +1,6 @@ DPDK_2.0 { global: - rte_ctrlmbuf_init; rte_get_rx_ol_flag_name; rte_get_tx_ol_flag_name; rte_mbuf_sanity_check; @@ -36,7 +35,7 @@ DPDK_16.11 { } DPDK_2.1; -EXPERIMENTAL { +DPDK_18.08 { global: rte_mbuf_best_mempool_ops; @@ -45,5 +44,4 @@ EXPERIMENTAL { rte_mbuf_set_user_mempool_ops; rte_mbuf_user_mempool_ops; rte_pktmbuf_pool_create_by_ops; - } DPDK_16.11; |