[dpdk-dev] [RFC] mbuf: support dynamic fields and flags

Wang, Haiyue haiyue.wang at intel.com
Wed Jul 10 19:14:33 CEST 2019


Hi,

Sounds cool, just have some questions inline.

> -----Original Message-----
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz
> Sent: Wednesday, July 10, 2019 17:29
> To: dev at dpdk.org
> Subject: [dpdk-dev] [RFC] mbuf: support dynamic fields and flags
> 
> Many features require to store data inside the mbuf. As the room in mbuf
> structure is limited, it is not possible to have a field for each
> feature. Also, changing fields in the mbuf structure can break the API
> or ABI.
> 
> This commit addresses these issues, by enabling the dynamic registration
> of fields or flags:
> 
> - a dynamic field is a named area in the rte_mbuf structure, with a
>   given size (>= 1 byte) and alignment constraint.
> - a dynamic flag is a named bit in the rte_mbuf structure.
> 
> The typical use case is a PMD that registers space for an offload
> feature, when the application requests to enable this feature.  As
> the space in mbuf is limited, the space should only be reserved if it
> is going to be used (i.e when the application explicitly asks for it).
> 
> The registration can be done at any moment, but it is not possible
> to unregister fields or flags for now.
> 
> Signed-off-by: Olivier Matz <olivier.matz at 6wind.com>
> ---
>  app/test/test_mbuf.c                 |  83 +++++++-
>  lib/librte_mbuf/Makefile             |   2 +
>  lib/librte_mbuf/meson.build          |   6 +-
>  lib/librte_mbuf/rte_mbuf.h           |  25 ++-
>  lib/librte_mbuf/rte_mbuf_dyn.c       | 373 +++++++++++++++++++++++++++++++++++
>  lib/librte_mbuf/rte_mbuf_dyn.h       | 119 +++++++++++
>  lib/librte_mbuf/rte_mbuf_version.map |   4 +
>  7 files changed, 607 insertions(+), 5 deletions(-)
>  create mode 100644 lib/librte_mbuf/rte_mbuf_dyn.c
>  create mode 100644 lib/librte_mbuf/rte_mbuf_dyn.h
> 
> diff --git a/app/test/test_mbuf.c b/app/test/test_mbuf.c
> index 2a97afe20..8008cc766 100644
> --- a/app/test/test_mbuf.c
> +++ b/app/test/test_mbuf.c
> @@ -28,6 +28,7 @@
>  #include <rte_random.h>
>  #include <rte_cycles.h>
>  #include <rte_malloc.h>
> +#include <rte_mbuf_dyn.h>
> 
>  #include "test.h"
> 
> @@ -502,7 +503,6 @@ test_attach_from_different_pool(struct rte_mempool *pktmbuf_pool,
>  		rte_pktmbuf_free(clone2);
>  	return -1;
>  }
> -#undef GOTO_FAIL
> 
>  /*
>   * test allocation and free of mbufs
> @@ -1122,6 +1122,81 @@ test_tx_offload(void)
>  }
> 
>  static int
> +test_mbuf_dyn(struct rte_mempool *pktmbuf_pool)
> +{
> +	struct rte_mbuf *m = NULL;
> +	int offset, offset2;
> +	int flag, flag2;
> +
> +	offset = rte_mbuf_dynfield_register("test-dynfield", sizeof(uint8_t),
> +					__alignof__(uint8_t), 0);
> +	if (offset == -1)
> +		GOTO_FAIL("failed to register dynamic field, offset=%d: %s",
> +			offset, strerror(errno));
> +
> +	offset2 = rte_mbuf_dynfield_register("test-dynfield", sizeof(uint8_t),
> +					__alignof__(uint8_t), 0);
> +	if (offset2 != offset)
> +		GOTO_FAIL("failed to lookup dynamic field, offset=%d, offset2=%d: %s",
> +			offset, offset2, strerror(errno));
> +
> +	offset2 = rte_mbuf_dynfield_register("test-dynfield2", sizeof(uint16_t),
> +					__alignof__(uint16_t), 0);
> +	if (offset2 == -1 || offset2 == offset || (offset & 1))
> +		GOTO_FAIL("failed to register dynfield field 2, offset=%d, offset2=%d: %s",
> +			offset, offset2, strerror(errno));
> +
> +	printf("offset = %d, offset2 = %d\n", offset, offset2);
> +
> +	offset = rte_mbuf_dynfield_register("test-dynfield-fail", 256, 1, 0);
> +	if (offset != -1)
> +		GOTO_FAIL("dynamic field creation should fail (too big)");
> +
> +	offset = rte_mbuf_dynfield_register("test-dynfield-fail", 1, 3, 0);
> +	if (offset != -1)
> +		GOTO_FAIL("dynamic field creation should fail (bad alignment)");
> +
> +	flag = rte_mbuf_dynflag_register("test-dynflag");
> +	if (flag == -1)
> +		GOTO_FAIL("failed to register dynamic field, flag=%d: %s",
> +			flag, strerror(errno));
> +
> +	flag2 = rte_mbuf_dynflag_register("test-dynflag");
> +	if (flag2 != flag)
> +		GOTO_FAIL("failed to lookup dynamic field, flag=%d, flag2=%d: %s",
> +			flag, flag2, strerror(errno));
> +
> +	flag2 = rte_mbuf_dynflag_register("test-dynflag2");
> +	if (flag2 == -1 || flag2 == flag)
> +		GOTO_FAIL("failed to register dynflag field 2, flag=%d, flag2=%d: %s",
> +			flag, flag2, strerror(errno));
> +
> +	printf("flag = %d, flag2 = %d\n", flag, flag2);
> +
> +	/* set, get dynamic field */
> +	m = rte_pktmbuf_alloc(pktmbuf_pool);
> +	if (m == NULL)
> +		GOTO_FAIL("Cannot allocate mbuf");
> +
> +	*RTE_MBUF_DYNFIELD(m, offset, uint8_t *) = 1;
> +	if (*RTE_MBUF_DYNFIELD(m, offset, uint8_t *) != 1)
> +		GOTO_FAIL("failed to read dynamic field");
> +	*RTE_MBUF_DYNFIELD(m, offset2, uint16_t *) = 1000;
> +	if (*RTE_MBUF_DYNFIELD(m, offset2, uint16_t *) != 1000)
> +		GOTO_FAIL("failed to read dynamic field");
> +
> +	/* set a dynamic flag */
> +	m->ol_flags |= (1ULL << flag);
> +
> +	rte_pktmbuf_free(m);
> +	return 0;
> +fail:
> +	rte_pktmbuf_free(m);
> +	return -1;
> +}
> +#undef GOTO_FAIL
> +
> +static int
>  test_mbuf(void)
>  {
>  	int ret = -1;
> @@ -1140,6 +1215,12 @@ test_mbuf(void)
>  		goto err;
>  	}
> 
> +	/* test registration of dynamic fields and flags */
> +	if (test_mbuf_dyn(pktmbuf_pool) < 0) {
> +		printf("mbuf dynflag test failed\n");
> +		goto err;
> +	}
> +
>  	/* create a specific pktmbuf pool with a priv_size != 0 and no data
>  	 * room size */
>  	pktmbuf_pool2 = rte_pktmbuf_pool_create("test_pktmbuf_pool2",
> diff --git a/lib/librte_mbuf/Makefile b/lib/librte_mbuf/Makefile
> index c8f6d2689..5a9bcee73 100644
> --- a/lib/librte_mbuf/Makefile
> +++ b/lib/librte_mbuf/Makefile
> @@ -17,8 +17,10 @@ LIBABIVER := 5
> 
>  # all source are stored in SRCS-y
>  SRCS-$(CONFIG_RTE_LIBRTE_MBUF) := rte_mbuf.c rte_mbuf_ptype.c rte_mbuf_pool_ops.c
> +SRCS-$(CONFIG_RTE_LIBRTE_MBUF) += rte_mbuf_dyn.c
> 
>  # install includes
>  SYMLINK-$(CONFIG_RTE_LIBRTE_MBUF)-include := rte_mbuf.h rte_mbuf_ptype.h rte_mbuf_pool_ops.h
> +SYMLINK-$(CONFIG_RTE_LIBRTE_MBUF)-include += rte_mbuf_dyn.h
> 
>  include $(RTE_SDK)/mk/rte.lib.mk
> diff --git a/lib/librte_mbuf/meson.build b/lib/librte_mbuf/meson.build
> index 6cc11ebb4..9137e8f26 100644
> --- a/lib/librte_mbuf/meson.build
> +++ b/lib/librte_mbuf/meson.build
> @@ -2,8 +2,10 @@
>  # Copyright(c) 2017 Intel Corporation
> 
>  version = 5
> -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')
> +sources = files('rte_mbuf.c', 'rte_mbuf_ptype.c', 'rte_mbuf_pool_ops.c',
> +	'rte_mbuf_dyn.c')
> +headers = files('rte_mbuf.h', 'rte_mbuf_ptype.h', 'rte_mbuf_pool_ops.h',
> +	'rte_mbuf_dyn.h')
>  deps += ['mempool']
> 
>  allow_experimental_apis = true
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index 98225ec80..ef588cd54 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -198,9 +198,12 @@ extern "C" {
>  #define PKT_RX_OUTER_L4_CKSUM_GOOD	(1ULL << 22)
>  #define PKT_RX_OUTER_L4_CKSUM_INVALID	((1ULL << 21) | (1ULL << 22))
> 
> -/* add new RX flags here */
> +/* add new RX flags here, don't forget to update PKT_FIRST_FREE */
> 
> -/* add new TX flags here */
> +#define PKT_FIRST_FREE (1ULL << 23)
> +#define PKT_LAST_FREE (1ULL << 39)
> +
> +/* add new TX flags here, don't forget to update PKT_LAST_FREE  */
> 
>  /**
>   * Indicate that the metadata field in the mbuf is in use.
> @@ -738,6 +741,8 @@ struct rte_mbuf {
>  	 */
>  	struct rte_mbuf_ext_shared_info *shinfo;
> 
> +	uint64_t dynfield1; /**< Reserved for dynamic fields. */
> +	uint64_t dynfield2; /**< Reserved for dynamic fields. */
>  } __rte_cache_aligned;
> 
>  /**
> @@ -1685,6 +1690,21 @@ rte_pktmbuf_attach_extbuf(struct rte_mbuf *m, void *buf_addr,
>  #define rte_pktmbuf_detach_extbuf(m) rte_pktmbuf_detach(m)
> 
>  /**
> + * Copy dynamic fields from m_src to m_dst.
> + *
> + * @param m_dst
> + *   The destination mbuf.
> + * @param m_src
> + *   The source mbuf.
> + */
> +static inline void
> +rte_mbuf_dynfield_copy(struct rte_mbuf *m_dst, const struct rte_mbuf *m_src)
> +{
> +	m_dst->dynfield1 = m_src->dynfield1;
> +	m_dst->dynfield2 = m_src->dynfield2;
> +}
> +
> +/**
>   * Attach packet mbuf to another packet mbuf.
>   *
>   * If the mbuf we are attaching to isn't a direct buffer and is attached to
> @@ -1732,6 +1752,7 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m)
>  	mi->vlan_tci_outer = m->vlan_tci_outer;
>  	mi->tx_offload = m->tx_offload;
>  	mi->hash = m->hash;
> +	rte_mbuf_dynfield_copy(mi, m);
> 
>  	mi->next = NULL;
>  	mi->pkt_len = mi->data_len;
> diff --git a/lib/librte_mbuf/rte_mbuf_dyn.c b/lib/librte_mbuf/rte_mbuf_dyn.c
> new file mode 100644
> index 000000000..6a96a43da
> --- /dev/null
> +++ b/lib/librte_mbuf/rte_mbuf_dyn.c
> @@ -0,0 +1,373 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright 2019 6WIND S.A.
> + */
> +
> +#include <sys/queue.h>
> +
> +#include <rte_common.h>
> +#include <rte_eal.h>
> +#include <rte_eal_memconfig.h>
> +#include <rte_tailq.h>
> +#include <rte_errno.h>
> +#include <rte_malloc.h>
> +#include <rte_string_fns.h>
> +#include <rte_mbuf.h>
> +#include <rte_mbuf_dyn.h>
> +
> +#define RTE_MBUF_DYN_MZNAME "rte_mbuf_dyn"
> +
> +struct mbuf_dynfield {
> +	TAILQ_ENTRY(mbuf_dynfield) next;
> +	char name[RTE_MBUF_DYN_NAMESIZE];
> +	size_t size;
> +	size_t align;
> +	unsigned int flags;
> +	int offset;
> +};
> +TAILQ_HEAD(mbuf_dynfield_list, rte_tailq_entry);
> +
> +static struct rte_tailq_elem mbuf_dynfield_tailq = {
> +	.name = "RTE_MBUF_DYNFIELD",
> +};
> +EAL_REGISTER_TAILQ(mbuf_dynfield_tailq);
> +
> +struct mbuf_dynflag {
> +	TAILQ_ENTRY(mbuf_dynflag) next;
> +	char name[RTE_MBUF_DYN_NAMESIZE];
> +	int bitnum;
> +};
> +TAILQ_HEAD(mbuf_dynflag_list, rte_tailq_entry);
> +
> +static struct rte_tailq_elem mbuf_dynflag_tailq = {
> +	.name = "RTE_MBUF_DYNFLAG",
> +};
> +EAL_REGISTER_TAILQ(mbuf_dynflag_tailq);
> +
> +struct mbuf_dyn_shm {
> +	/** For each mbuf byte, free_space[i] == 1 if space is free. */
> +	uint8_t free_space[sizeof(struct rte_mbuf)];
> +	/** Bitfield of available flags. */
> +	uint64_t free_flags;
> +};
> +static struct mbuf_dyn_shm *shm;
> +
> +/* allocate and initialize the shared memory */
> +static int
> +init_shared_mem(void)
> +{
> +	const struct rte_memzone *mz;
> +	uint64_t mask;
> +
> +	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
> +		mz = rte_memzone_reserve_aligned(RTE_MBUF_DYN_MZNAME,
> +						sizeof(struct mbuf_dyn_shm),
> +						SOCKET_ID_ANY, 0,
> +						RTE_CACHE_LINE_SIZE);
> +	} else {
> +		mz = rte_memzone_lookup(RTE_MBUF_DYN_MZNAME);
> +	}
> +	if (mz == NULL)
> +		return -1;
> +
> +	shm = mz->addr;
> +
> +#define mark_free(field)						\
> +	memset(&shm->free_space[offsetof(struct rte_mbuf, field)],	\
> +		0xff, sizeof(((struct rte_mbuf *)0)->field))
> +
> +	if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
> +		/* init free_space, keep it sync'd with
> +		 * rte_mbuf_dynfield_copy().
> +		 */
> +		memset(shm, 0, sizeof(*shm));
> +		mark_free(dynfield1);
> +		mark_free(dynfield2);
> +
> +		/* init free_flags */
> +		for (mask = PKT_FIRST_FREE; mask <= PKT_LAST_FREE; mask <<= 1)
> +			shm->free_flags |= mask;
> +	}
> +#undef mark_free
> +
> +	return 0;
> +}
> +
> +/* check if this offset can be used */
> +static int
> +check_offset(size_t offset, size_t size, size_t align, unsigned int flags)
> +{
> +	size_t i;
> +
> +	(void)flags;
> +
> +	if ((offset & (align - 1)) != 0)
> +		return -1;
> +	if (offset + size > sizeof(struct rte_mbuf))
> +		return -1;
> +
> +	for (i = 0; i < size; i++) {
> +		if (!shm->free_space[i + offset])
> +			return -1;
> +	}
> +
> +	return 0;
> +}
> +
> +/* assume tailq is locked */
> +static struct mbuf_dynfield *
> +__mbuf_dynfield_lookup(const char *name)
> +{
> +	struct mbuf_dynfield_list *mbuf_dynfield_list;
> +	struct mbuf_dynfield *mbuf_dynfield;
> +	struct rte_tailq_entry *te;
> +
> +	mbuf_dynfield_list = RTE_TAILQ_CAST(
> +		mbuf_dynfield_tailq.head, mbuf_dynfield_list);
> +
> +	TAILQ_FOREACH(te, mbuf_dynfield_list, next) {
> +		mbuf_dynfield = (struct mbuf_dynfield *)te->data;
> +		if (strncmp(name, mbuf_dynfield->name,
> +				RTE_MBUF_DYN_NAMESIZE) == 0)
> +			break;
> +	}
> +
> +	if (te == NULL) {
> +		rte_errno = ENOENT;
> +		return NULL;
> +	}
> +
> +	return mbuf_dynfield;
> +}
> +
> +int
> +rte_mbuf_dynfield_lookup(const char *name, size_t *size, size_t *align)
> +{
> +	struct mbuf_dynfield *mbuf_dynfield;
> +
> +	if (shm == NULL) {
> +		rte_errno = ENOENT;
> +		return -1;
> +	}
> +
> +	rte_mcfg_tailq_read_lock();
> +	mbuf_dynfield = __mbuf_dynfield_lookup(name);
> +	rte_mcfg_tailq_read_unlock();
> +
> +	if (mbuf_dynfield == NULL) {
> +		rte_errno = ENOENT;
> +		return -1;
> +	}
> +
> +	if (size != NULL)
> +		*size = mbuf_dynfield->size;
> +	if (align != NULL)
> +		*align = mbuf_dynfield->align;
> +
> +	return mbuf_dynfield->offset;
> +}
> +
> +int
> +rte_mbuf_dynfield_register(const char *name, size_t size, size_t align,
> +			unsigned int flags)
> +{
> +	struct mbuf_dynfield_list *mbuf_dynfield_list;
> +	struct mbuf_dynfield *mbuf_dynfield = NULL;
> +	struct rte_tailq_entry *te = NULL;
> +	int offset, ret;
> +	size_t i;
> +
> +	if (shm == NULL && init_shared_mem() < 0)
> +		goto fail;
> +	if (size >= sizeof(struct rte_mbuf)) {
> +		rte_errno = EINVAL;
> +		goto fail;
> +	}
> +	if (!rte_is_power_of_2(align)) {
> +		rte_errno = EINVAL;
> +		goto fail;
> +	}
> +
> +	rte_mcfg_tailq_write_lock();
> +
> +	mbuf_dynfield = __mbuf_dynfield_lookup(name);
> +	if (mbuf_dynfield != NULL) {
> +		if (mbuf_dynfield->size != size ||
> +				mbuf_dynfield->align != align ||
> +				mbuf_dynfield->flags != flags) {
> +			rte_errno = EEXIST;
> +			goto fail_unlock;
> +		}
> +		offset = mbuf_dynfield->offset;
> +		goto out_unlock;
> +	}
> +
> +	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
> +		rte_errno = EPERM;
> +		goto fail_unlock;
> +	}
> +
> +	for (offset = 0;
> +	     offset < (int)sizeof(struct rte_mbuf);
> +	     offset++) {
> +		if (check_offset(offset, size, align, flags) == 0)
> +			break;
> +	}
> +
> +	if (offset == sizeof(struct rte_mbuf)) {
> +		rte_errno = ENOENT;
> +		goto fail_unlock;
> +	}
> +
> +	mbuf_dynfield_list = RTE_TAILQ_CAST(
> +		mbuf_dynfield_tailq.head, mbuf_dynfield_list);
> +
> +	te = rte_zmalloc("MBUF_DYNFIELD_TAILQ_ENTRY", sizeof(*te), 0);
> +	if (te == NULL)
> +		goto fail_unlock;
> +
> +	mbuf_dynfield = rte_zmalloc("mbuf_dynfield", sizeof(*mbuf_dynfield), 0);
> +	if (mbuf_dynfield == NULL)
> +		goto fail_unlock;
> +
> +	ret = strlcpy(mbuf_dynfield->name, name, sizeof(mbuf_dynfield->name));
> +	if (ret < 0 || ret >= (int)sizeof(mbuf_dynfield->name)) {
> +		rte_errno = ENAMETOOLONG;
> +		goto fail_unlock;
> +	}
> +	mbuf_dynfield->size = size;
> +	mbuf_dynfield->align = align;
> +	mbuf_dynfield->flags = flags;
> +	mbuf_dynfield->offset = offset;
> +	te->data = mbuf_dynfield;
> +
> +	TAILQ_INSERT_TAIL(mbuf_dynfield_list, te, next);
> +
> +	for (i = offset; i < offset + size; i++)
> +		shm->free_space[i] = 0;
> +
> +out_unlock:
> +	rte_mcfg_tailq_write_unlock();
> +
> +	return offset;
> +
> +fail_unlock:
> +	rte_mcfg_tailq_write_unlock();
> +fail:
> +	rte_free(mbuf_dynfield);
> +	rte_free(te);
> +	return -1;
> +}
> +
> +/* assume tailq is locked */
> +static struct mbuf_dynflag *
> +__mbuf_dynflag_lookup(const char *name)
> +{
> +	struct mbuf_dynflag_list *mbuf_dynflag_list;
> +	struct mbuf_dynflag *mbuf_dynflag;
> +	struct rte_tailq_entry *te;
> +
> +	mbuf_dynflag_list = RTE_TAILQ_CAST(
> +		mbuf_dynflag_tailq.head, mbuf_dynflag_list);
> +
> +	TAILQ_FOREACH(te, mbuf_dynflag_list, next) {
> +		mbuf_dynflag = (struct mbuf_dynflag *)te->data;
> +		if (strncmp(name, mbuf_dynflag->name,
> +				RTE_MBUF_DYN_NAMESIZE) == 0)
> +			break;
> +	}
> +
> +	if (te == NULL) {
> +		rte_errno = ENOENT;
> +		return NULL;
> +	}
> +
> +	return mbuf_dynflag;
> +}
> +
> +int
> +rte_mbuf_dynflag_lookup(const char *name)
> +{
> +	struct mbuf_dynflag *mbuf_dynflag;
> +
> +	if (shm == NULL) {
> +		rte_errno = ENOENT;
> +		return -1;
> +	}
> +
> +	rte_mcfg_tailq_read_lock();
> +	mbuf_dynflag = __mbuf_dynflag_lookup(name);
> +	rte_mcfg_tailq_read_unlock();
> +
> +	if (mbuf_dynflag == NULL) {
> +		rte_errno = ENOENT;
> +		return -1;
> +	}
> +
> +	return mbuf_dynflag->bitnum;
> +}
> +
> +int
> +rte_mbuf_dynflag_register(const char *name)
> +{
> +	struct mbuf_dynflag_list *mbuf_dynflag_list;
> +	struct mbuf_dynflag *mbuf_dynflag = NULL;
> +	struct rte_tailq_entry *te = NULL;
> +	int bitnum, ret;
> +
> +	if (shm == NULL && init_shared_mem() < 0)
> +		goto fail;
> +
> +	rte_mcfg_tailq_write_lock();
> +
> +	mbuf_dynflag = __mbuf_dynflag_lookup(name);
> +	if (mbuf_dynflag != NULL) {
> +		bitnum = mbuf_dynflag->bitnum;
> +		goto out_unlock;
> +	}
> +
> +	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
> +		rte_errno = EPERM;
> +		goto fail_unlock;
> +	}
> +
> +	if (shm->free_flags == 0) {
> +		rte_errno = ENOENT;
> +		goto fail_unlock;
> +	}
> +	bitnum = rte_bsf64(shm->free_flags);
> +
> +	mbuf_dynflag_list = RTE_TAILQ_CAST(
> +		mbuf_dynflag_tailq.head, mbuf_dynflag_list);
> +
> +	te = rte_zmalloc("MBUF_DYNFLAG_TAILQ_ENTRY", sizeof(*te), 0);
> +	if (te == NULL)
> +		goto fail_unlock;
> +
> +	mbuf_dynflag = rte_zmalloc("mbuf_dynflag", sizeof(*mbuf_dynflag), 0);
> +	if (mbuf_dynflag == NULL)
> +		goto fail_unlock;
> +
> +	ret = strlcpy(mbuf_dynflag->name, name, sizeof(mbuf_dynflag->name));
> +	if (ret < 0 || ret >= (int)sizeof(mbuf_dynflag->name)) {
> +		rte_errno = ENAMETOOLONG;
> +		goto fail_unlock;
> +	}
> +	mbuf_dynflag->bitnum = bitnum;
> +	te->data = mbuf_dynflag;
> +
> +	TAILQ_INSERT_TAIL(mbuf_dynflag_list, te, next);
> +
> +	shm->free_flags &= ~(1ULL << bitnum);
> +
> +out_unlock:
> +	rte_mcfg_tailq_write_unlock();
> +
> +	return bitnum;
> +
> +fail_unlock:
> +	rte_mcfg_tailq_write_unlock();
> +fail:
> +	rte_free(mbuf_dynflag);
> +	rte_free(te);
> +	return -1;
> +}
> diff --git a/lib/librte_mbuf/rte_mbuf_dyn.h b/lib/librte_mbuf/rte_mbuf_dyn.h
> new file mode 100644
> index 000000000..a86986a0f
> --- /dev/null
> +++ b/lib/librte_mbuf/rte_mbuf_dyn.h
> @@ -0,0 +1,119 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright 2019 6WIND S.A.
> + */
> +
> +#ifndef _RTE_MBUF_DYN_H_
> +#define _RTE_MBUF_DYN_H_
> +
> +/**
> + * @file
> + * RTE Mbuf dynamic fields and flags
> + *
> + * Many features require to store data inside the mbuf. As the room in
> + * mbuf structure is limited, it is not possible to have a field for
> + * each feature. Also, changing fields in the mbuf structure can break
> + * the API or ABI.
> + *
> + * This module addresses this issue, by enabling the dynamic
> + * registration of fields or flags:
> + *
> + * - a dynamic field is a named area in the rte_mbuf structure, with a
> + *   given size (>= 1 byte) and alignment constraint.
> + * - a dynamic flag is a named bit in the rte_mbuf structure.
> + *
> + * The typical use case is a PMD that registers space for an offload
> + * feature, when the application requests to enable this feature.  As
> + * the space in mbuf is limited, the space should only be reserved if it
> + * is going to be used (i.e when the application explicitly asks for it).
> + *
> + * The registration can be done at any moment, but it is not possible
> + * to unregister fields or flags for now.
> + *
> + * Example of use:
> + *
> + * - RTE_MBUF_DYN_<feature>_(ID|SIZE|ALIGN) are defined in this file

Does it means that all PMDs define their own 'RTE_MBUF_DYN_<feature>_(ID|SIZE|ALIGN)'
here ? In other words, each PMD can expose its private DYN_<feature> here for public
using ?

How about adding another eth_dev_ops API definitions to show the PMD's supporting feature
names, sizes, align in run time for testpmd ? And also another eth_dev_ops API for showing
the data saved in rte_mbuf by 'dump_pkt_burst' ? Adding a new command for testpmd to set
the dynamic feature may be good for PMD test.

> + * - If the application asks for the feature, the PMD use

How does the application ask for the feature ? By ' rte_mbuf_dynfield_register()' ?

> + *   rte_mbuf_dynfield_register() to get the dynamic offset and stores
> + *   in a global variable.

In case, the PMD calls 'rte_mbuf_dynfield_register()' for 'dyn_feature' firstly, this
means that PMD requests the dynamic feature itself if I understand correctly. Should
PMD calls 'rte_mbuf_dynfield_lookup' for 'dyn_feature' to query the name exists, the
size and align are right as expected ? If exists, but size and align are not right, may
be for PMD change its definition, then PMD can give a warning or error message. If name
exists, both size and align are expected, then PMD think that the application request
the right dynamic features.

> + * - The application also calls rte_mbuf_dynfield_register() to get the
> + *   dynamic offset and stores it in a global variable.
> + * - When the field must be used by the PMD or the application, they
> + *   use the RTE_MBUF_DYNFIELD() helper.
> + */
> +
> +struct rte_mbuf;
> +
> +/**
> + * Register space for a dynamic field in the mbuf structure.
> + *
> + * @param name
> + *   A string identifying the dynamic field. External applications or
> + *   libraries must not define identifers prefixed with "rte_", which
> + *   are reserved for standard features.
> + * @param size
> + *   The number of bytes to reserve.
> + * @param align
> + *   The alignment constraint, which must be a power of 2.
> + * @param flags
> + *   Reserved for future use.
> + * @return
> + *   The offset in the mbuf structure, or -1 on error (rte_errno is set).
> + */
> +__rte_experimental
> +int rte_mbuf_dynfield_register(const char *name, size_t size, size_t align,
> +			unsigned int flags);
> +
> +/**
> + * Lookup for a registered dynamic mbuf field.
> + *
> + * @param name
> + *   A string identifying the dynamic field.
> + * @param size
> + *   If not NULL, the number of reserved bytes for this field is stored
> + *   at this address.
> + * @param align
> + *   If not NULL, the alignement constraint for this field is stored
> + *   at this address.
> + * @return
> + *   The offset of this field in the mbuf structure, or -1 on error
> + *   (rte_errno is set).
> + */
> +__rte_experimental
> +int rte_mbuf_dynfield_lookup(const char *name, size_t *size, size_t *align);
> +
> +/**
> + * Register a dynamic flag in the mbuf structure.
> + *
> + * @param name
> + *   A string identifying the dynamic flag. External applications or
> + *   libraries must not define identifers prefixed with "rte_", which
> + *   are reserved for standard features.
> + * @return
> + *   The number of the reserved bit, or -1 on error (rte_errno is set).
> + */
> +__rte_experimental
> +int rte_mbuf_dynflag_register(const char *name);
> +
> +/**
> + * Lookup for a registered dynamic mbuf flag.
> + *
> + * @param name
> + *   A string identifying the dynamic flag.
> + * @return
> + *   The offset of this flag in the mbuf structure, or -1 on error
> + *   (rte_errno is set).
> + */
> +__rte_experimental
> +int rte_mbuf_dynflag_lookup(const char *name);
> +
> +/**
> + * Helper macro to access to a dynamic field.
> + */
> +#define RTE_MBUF_DYNFIELD(m, offset, type) ((type)((char *)(m) + (offset)))
> +
> +/**
> + * Maximum length of the dynamic field or flag string.
> + */
> +#define RTE_MBUF_DYN_NAMESIZE 32
> +
> +#endif
> diff --git a/lib/librte_mbuf/rte_mbuf_version.map b/lib/librte_mbuf/rte_mbuf_version.map
> index 2662a37bf..a98310570 100644
> --- a/lib/librte_mbuf/rte_mbuf_version.map
> +++ b/lib/librte_mbuf/rte_mbuf_version.map
> @@ -50,4 +50,8 @@ EXPERIMENTAL {
>  	global:
> 
>  	rte_mbuf_check;
> +	rte_mbuf_dynfield_lookup;
> +	rte_mbuf_dynfield_register;
> +	rte_mbuf_dynflag_lookup;
> +	rte_mbuf_dynflag_register;
>  } DPDK_18.08;
> --
> 2.11.0



More information about the dev mailing list