Re: [dpdk-dev] [PATCH v2] mbuf: support dynamic fields and flags

["Ananyev, Konstantin" <konstantin.ananyev@intel.com>]

> 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@6wind.com>
> Acked-by: Thomas Monjalon <thomas@monjalon.net>
> ---
> 
> v2
> 
> * Rebase on top of master: solve conflict with Stephen's patchset
>   (packet copy)
> * Add new apis to register a dynamic field/flag at a specific place
> * Add a dump function (sugg by David)
> * Enhance field registration function to select the best offset, keeping
>   large aligned zones as much as possible (sugg by Konstantin)
> * Use a size_t and unsigned int instead of int when relevant
>   (sugg by Konstantin)
> * Use "uint64_t dynfield1[2]" in mbuf instead of 2 uint64_t fields
>   (sugg by Konstantin)
> * Remove unused argument in private function (sugg by Konstantin)
> * Fix and simplify locking (sugg by Konstantin)
> * Fix minor typo
> 
> rfc -> v1
> 
> * Rebase on top of master
> * Change registration API to use a structure instead of
>   variables, getting rid of #defines (Stephen's comment)
> * Update flag registration to use a similar API as fields.
> * Change max name length from 32 to 64 (sugg. by Thomas)
> * Enhance API documentation (Haiyue's and Andrew's comments)
> * Add a debug log at registration
> * Add some words in release note
> * Did some performance tests (sugg. by Andrew):
>   On my platform, reading a dynamic field takes ~3 cycles more
>   than a static field, and ~2 cycles more for writing.
> 
>  app/test/test_mbuf.c                   | 145 ++++++-
>  doc/guides/rel_notes/release_19_11.rst |   7 +
>  lib/librte_mbuf/Makefile               |   2 +
>  lib/librte_mbuf/meson.build            |   6 +-
>  lib/librte_mbuf/rte_mbuf.h             |  23 +-
>  lib/librte_mbuf/rte_mbuf_dyn.c         | 548 +++++++++++++++++++++++++
>  lib/librte_mbuf/rte_mbuf_dyn.h         | 226 ++++++++++
>  lib/librte_mbuf/rte_mbuf_version.map   |   7 +
>  8 files changed, 959 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 b9c2b2500..01cafad59 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"
> 
> @@ -657,7 +658,6 @@ 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
> @@ -1276,6 +1276,143 @@ test_tx_offload(void)
>  	return (v1 == v2) ? 0 : -EINVAL;
>  }
> 
> +static int
> +test_mbuf_dyn(struct rte_mempool *pktmbuf_pool)
> +{
> +	const struct rte_mbuf_dynfield dynfield = {
> +		.name = "test-dynfield",
> +		.size = sizeof(uint8_t),
> +		.align = __alignof__(uint8_t),
> +		.flags = 0,
> +	};
> +	const struct rte_mbuf_dynfield dynfield2 = {
> +		.name = "test-dynfield2",
> +		.size = sizeof(uint16_t),
> +		.align = __alignof__(uint16_t),
> +		.flags = 0,
> +	};
> +	const struct rte_mbuf_dynfield dynfield3 = {
> +		.name = "test-dynfield3",
> +		.size = sizeof(uint8_t),
> +		.align = __alignof__(uint8_t),
> +		.flags = 0,
> +	};
> +	const struct rte_mbuf_dynfield dynfield_fail_big = {
> +		.name = "test-dynfield-fail-big",
> +		.size = 256,
> +		.align = 1,
> +		.flags = 0,
> +	};
> +	const struct rte_mbuf_dynfield dynfield_fail_align = {
> +		.name = "test-dynfield-fail-align",
> +		.size = 1,
> +		.align = 3,
> +		.flags = 0,
> +	};
> +	const struct rte_mbuf_dynflag dynflag = {
> +		.name = "test-dynflag",
> +		.flags = 0,
> +	};
> +	const struct rte_mbuf_dynflag dynflag2 = {
> +		.name = "test-dynflag2",
> +		.flags = 0,
> +	};
> +	const struct rte_mbuf_dynflag dynflag3 = {
> +		.name = "test-dynflag3",
> +		.flags = 0,
> +	};
> +	struct rte_mbuf *m = NULL;
> +	int offset, offset2, offset3;
> +	int flag, flag2, flag3;
> +	int ret;
> +
> +	printf("Test mbuf dynamic fields and flags\n");
> +	rte_mbuf_dyn_dump(stdout);
> +
> +	offset = rte_mbuf_dynfield_register(&dynfield);
> +	if (offset == -1)
> +		GOTO_FAIL("failed to register dynamic field, offset=%d: %s",
> +			offset, strerror(errno));
> +
> +	ret = rte_mbuf_dynfield_register(&dynfield);
> +	if (ret != offset)
> +		GOTO_FAIL("failed to lookup dynamic field, ret=%d: %s",
> +			ret, strerror(errno));
> +
> +	offset2 = rte_mbuf_dynfield_register(&dynfield2);
> +	if (offset2 == -1 || offset2 == offset || (offset2 & 1))
> +		GOTO_FAIL("failed to register dynamic field 2, offset2=%d: %s",
> +			offset2, strerror(errno));
> +
> +	offset3 = rte_mbuf_dynfield_register_offset(&dynfield3,
> +				offsetof(struct rte_mbuf, dynfield1[1]));
> +	if (offset3 != offsetof(struct rte_mbuf, dynfield1[1]))
> +		GOTO_FAIL("failed to register dynamic field 3, offset=%d: %s",
> +			offset3, strerror(errno));
> +
> +	printf("dynfield: offset=%d, offset2=%d, offset3=%d\n",
> +		offset, offset2, offset3);
> +
> +	ret = rte_mbuf_dynfield_register(&dynfield_fail_big);
> +	if (ret != -1)
> +		GOTO_FAIL("dynamic field creation should fail (too big)");
> +
> +	ret = rte_mbuf_dynfield_register(&dynfield_fail_align);
> +	if (ret != -1)
> +		GOTO_FAIL("dynamic field creation should fail (bad alignment)");
> +
> +	ret = rte_mbuf_dynfield_register_offset(&dynfield_fail_align,
> +				offsetof(struct rte_mbuf, ol_flags));
> +	if (ret != -1)
> +		GOTO_FAIL("dynamic field creation should fail (not avail)");
> +
> +	flag = rte_mbuf_dynflag_register(&dynflag);
> +	if (flag == -1)
> +		GOTO_FAIL("failed to register dynamic flag, flag=%d: %s",
> +			flag, strerror(errno));
> +
> +	ret = rte_mbuf_dynflag_register(&dynflag);
> +	if (ret != flag)
> +		GOTO_FAIL("failed to lookup dynamic flag, ret=%d: %s",
> +			ret, strerror(errno));
> +
> +	flag2 = rte_mbuf_dynflag_register(&dynflag2);
> +	if (flag2 == -1 || flag2 == flag)
> +		GOTO_FAIL("failed to register dynamic flag 2, flag2=%d: %s",
> +			flag2, strerror(errno));
> +
> +	flag3 = rte_mbuf_dynflag_register_bitnum(&dynflag3,
> +						rte_bsf64(PKT_LAST_FREE));
> +	if (flag3 != rte_bsf64(PKT_LAST_FREE))
> +		GOTO_FAIL("failed to register dynamic flag 3, flag2=%d: %s",
> +			flag3, strerror(errno));
> +
> +	printf("dynflag: flag=%d, flag2=%d, flag3=%d\n", flag, flag2, flag3);
> +
> +	/* 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_mbuf_dyn_dump(stdout);
> +	rte_pktmbuf_free(m);
> +	return 0;
> +fail:
> +	rte_pktmbuf_free(m);
> +	return -1;
> +}
> +#undef GOTO_FAIL
> +
>  static int
>  test_mbuf(void)
>  {
> @@ -1295,6 +1432,12 @@ 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/doc/guides/rel_notes/release_19_11.rst b/doc/guides/rel_notes/release_19_11.rst
> index 85953b962..9e9c94554 100644
> --- a/doc/guides/rel_notes/release_19_11.rst
> +++ b/doc/guides/rel_notes/release_19_11.rst
> @@ -21,6 +21,13 @@ DPDK Release 19.11
> 
>        xdg-open build/doc/html/guides/rel_notes/release_19_11.html
> 
> +* **Add support of support dynamic fields and flags in mbuf.**
> +
> +  This new feature adds the ability to dynamically register some room
> +  for a field or a flag in the mbuf structure. This is typically used
> +  for specific offload features, where adding a static field or flag
> +  in the mbuf is not justified.
> +
> 
>  New Features
>  ------------
> 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 fb0849ac1..5740b1e93 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 +741,7 @@ struct rte_mbuf {
>  	 */
>  	struct rte_mbuf_ext_shared_info *shinfo;
> 
> +	uint64_t dynfield1[2]; /**< Reserved for dynamic fields. */
>  } __rte_cache_aligned;
> 
>  /**
> @@ -1684,6 +1688,20 @@ 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 *mdst, const struct rte_mbuf *msrc)
> +{
> +	memcpy(&mdst->dynfield1, msrc->dynfield1, sizeof(mdst->dynfield1));
> +}
> +
>  /* internal */
>  static inline void
>  __rte_pktmbuf_copy_hdr(struct rte_mbuf *mdst, const struct rte_mbuf *msrc)
> @@ -1695,6 +1713,7 @@ __rte_pktmbuf_copy_hdr(struct rte_mbuf *mdst, const struct rte_mbuf *msrc)
>  	mdst->hash = msrc->hash;
>  	mdst->packet_type = msrc->packet_type;
>  	mdst->timestamp = msrc->timestamp;
> +	rte_mbuf_dynfield_copy(mdst, msrc);
>  }
> 
>  /**
> diff --git a/lib/librte_mbuf/rte_mbuf_dyn.c b/lib/librte_mbuf/rte_mbuf_dyn.c
> new file mode 100644
> index 000000000..9ef235483
> --- /dev/null
> +++ b/lib/librte_mbuf/rte_mbuf_dyn.c
> @@ -0,0 +1,548 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright 2019 6WIND S.A.
> + */
> +
> +#include <sys/queue.h>
> +#include <stdint.h>
> +#include <limits.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_elt {
> +	TAILQ_ENTRY(mbuf_dynfield_elt) next;
> +	struct rte_mbuf_dynfield params;
> +	size_t 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_elt {
> +	TAILQ_ENTRY(mbuf_dynflag_elt) next;
> +	struct rte_mbuf_dynflag params;
> +	unsigned 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] != 0 if space is free.
> +	 * The value is the size of the biggest aligned element that
> +	 * can fit in the zone.
> +	 */
> +	uint8_t free_space[sizeof(struct rte_mbuf)];
> +	/** Bitfield of available flags. */
> +	uint64_t free_flags;
> +};
> +static struct mbuf_dyn_shm *shm;
> +
> +/* Set the value of free_space[] according to the size and alignment of
> + * the free areas. This helps to select the best place when reserving a
> + * dynamic field. Assume tailq is locked.
> + */
> +static void
> +process_score(void)
> +{
> +	size_t off, align, size, i;
> +
> +	/* first, erase previous info */
> +	for (i = 0; i < sizeof(struct rte_mbuf); i++) {
> +		if (shm->free_space[i])
> +			shm->free_space[i] = 1;
> +	}
> +
> +	for (off = 0; off < sizeof(struct rte_mbuf); off++) {
> +		/* get the size of the free zone */
> +		for (size = 0; shm->free_space[off + size]; size++)
> +			;
> +		if (size == 0)
> +			continue;
> +
> +		/* get the alignment of biggest object that can fit in
> +		 * the zone at this offset.
> +		 */
> +		for (align = 1;
> +		     (off % (align << 1)) == 0 && (align << 1) <= size;
> +		     align <<= 1)
> +			;
> +
> +		/* save it in free_space[] */
> +		for (i = off; i < off + size; i++)
> +			shm->free_space[i] = RTE_MAX(align, shm->free_space[i]);
> +	}
> +}
> +
> +/* Allocate and initialize the shared memory. Assume tailq is locked */
> +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)],	\
> +		1, sizeof(((struct rte_mbuf *)0)->field))

Still think it would look nicer without multi-line macro defines/undef in the middle of the function.

> +
> +	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);
> +
> +		/* init free_flags */
> +		for (mask = PKT_FIRST_FREE; mask <= PKT_LAST_FREE; mask <<= 1)
> +			shm->free_flags |= mask;
> +
> +		process_score();
> +	}
> +#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)
> +{
> +	size_t i;
> +
> +	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_elt *
> +__mbuf_dynfield_lookup(const char *name)
> +{
> +	struct mbuf_dynfield_list *mbuf_dynfield_list;
> +	struct mbuf_dynfield_elt *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_elt *)te->data;
> +		if (strcmp(name, mbuf_dynfield->params.name) == 0)
> +			break;
> +	}
> +
> +	if (te == NULL) {
> +		rte_errno = ENOENT;
> +		return NULL;
> +	}
> +
> +	return mbuf_dynfield;
> +}
> +
> +int
> +rte_mbuf_dynfield_lookup(const char *name, struct rte_mbuf_dynfield *params)
> +{
> +	struct mbuf_dynfield_elt *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 (params != NULL)
> +		memcpy(params, &mbuf_dynfield->params, sizeof(*params));
> +
> +	return mbuf_dynfield->offset;
> +}
> +
> +static int mbuf_dynfield_cmp(const struct rte_mbuf_dynfield *params1,
> +		const struct rte_mbuf_dynfield *params2)
> +{
> +	if (strcmp(params1->name, params2->name))
> +		return -1;
> +	if (params1->size != params2->size)
> +		return -1;
> +	if (params1->align != params2->align)
> +		return -1;
> +	if (params1->flags != params2->flags)
> +		return -1;
> +	return 0;
> +}
> +
> +/* assume tailq is locked */
> +static int
> +__rte_mbuf_dynfield_register_offset(const struct rte_mbuf_dynfield *params,
> +				size_t req)
> +{
> +	struct mbuf_dynfield_list *mbuf_dynfield_list;
> +	struct mbuf_dynfield_elt *mbuf_dynfield = NULL;
> +	struct rte_tailq_entry *te = NULL;
> +	unsigned int best_zone = UINT_MAX;
> +	size_t i, offset;
> +	int ret;
> +
> +	if (shm == NULL && init_shared_mem() < 0)
> +		return -1;
> +
> +	mbuf_dynfield = __mbuf_dynfield_lookup(params->name);
> +	if (mbuf_dynfield != NULL) {
> +		if (req != SIZE_MAX && req != mbuf_dynfield->offset) {
> +			rte_errno = EEXIST;
> +			return -1;
> +		}
> +		if (mbuf_dynfield_cmp(params, &mbuf_dynfield->params) < 0) {
> +			rte_errno = EEXIST;
> +			return -1;
> +		}
> +		return mbuf_dynfield->offset;
> +	}
> +
> +	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
> +		rte_errno = EPERM;
> +		return -1;
> +	}
> +
> +	if (req == SIZE_MAX) {
> +		for (offset = 0;
> +		     offset < sizeof(struct rte_mbuf);
> +		     offset++) {
> +			if (check_offset(offset, params->size,
> +						params->align) == 0 &&
> +					shm->free_space[offset] < best_zone) {

Probably worth to explain  a bit more here about best_zone logic -
trying to find offset with minimal score (minimal continuous length), etc.


> +				best_zone = shm->free_space[offset];
> +				req = offset;
> +			}
> +		}
> +		if (req == SIZE_MAX) {
> +			rte_errno = ENOENT;
> +			return -1;
> +		}
> +	} else {
> +		if (check_offset(req, params->size, params->align) < 0) {
> +			rte_errno = EBUSY;
> +			return -1;
> +		}
> +	}
> +
> +	offset = req;
> +	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)
> +		return -1;
> +
> +	mbuf_dynfield = rte_zmalloc("mbuf_dynfield", sizeof(*mbuf_dynfield), 0);
> +	if (mbuf_dynfield == NULL) {
> +		rte_free(te);
> +		return -1;
> +	}
> +
> +	ret = strlcpy(mbuf_dynfield->params.name, params->name,
> +		sizeof(mbuf_dynfield->params.name));
> +	if (ret < 0 || ret >= (int)sizeof(mbuf_dynfield->params.name)) {
> +		rte_errno = ENAMETOOLONG;
> +		rte_free(mbuf_dynfield);
> +		rte_free(te);
> +		return -1;
> +	}
> +	memcpy(&mbuf_dynfield->params, params, sizeof(mbuf_dynfield->params));
> +	mbuf_dynfield->offset = offset;
> +	te->data = mbuf_dynfield;
> +
> +	TAILQ_INSERT_TAIL(mbuf_dynfield_list, te, next);
> +
> +	for (i = offset; i < offset + params->size; i++)
> +		shm->free_space[i] = 0;
> +	process_score();
> +
> +	RTE_LOG(DEBUG, MBUF, "Registered dynamic field %s (sz=%zu, al=%zu, fl=0x%x) -> %zd\n",
> +		params->name, params->size, params->align, params->flags,
> +		offset);
> +
> +	return offset;
> +}
> +
> +int
> +rte_mbuf_dynfield_register_offset(const struct rte_mbuf_dynfield *params,
> +				size_t req)
> +{
> +	int ret;
> +
> +	if (params->size >= sizeof(struct rte_mbuf)) {
> +		rte_errno = EINVAL;
> +		return -1;
> +	}
> +	if (!rte_is_power_of_2(params->align)) {
> +		rte_errno = EINVAL;
> +		return -1;
> +	}
> +	if (params->flags != 0) {
> +		rte_errno = EINVAL;
> +		return -1;
> +	}
> +
> +	rte_mcfg_tailq_write_lock();
> +	ret = __rte_mbuf_dynfield_register_offset(params, req);
> +	rte_mcfg_tailq_write_unlock();
> +
> +	return ret;
> +}
> +
> +int
> +rte_mbuf_dynfield_register(const struct rte_mbuf_dynfield *params)
> +{
> +	return rte_mbuf_dynfield_register_offset(params, SIZE_MAX);
> +}
> +
> +/* assume tailq is locked */
> +static struct mbuf_dynflag_elt *
> +__mbuf_dynflag_lookup(const char *name)
> +{
> +	struct mbuf_dynflag_list *mbuf_dynflag_list;
> +	struct mbuf_dynflag_elt *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_elt *)te->data;
> +		if (strncmp(name, mbuf_dynflag->params.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 rte_mbuf_dynflag *params)
> +{
> +	struct mbuf_dynflag_elt *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;
> +	}
> +
> +	if (params != NULL)
> +		memcpy(params, &mbuf_dynflag->params, sizeof(*params));
> +
> +	return mbuf_dynflag->bitnum;
> +}
> +
> +static int mbuf_dynflag_cmp(const struct rte_mbuf_dynflag *params1,
> +		const struct rte_mbuf_dynflag *params2)
> +{
> +	if (strcmp(params1->name, params2->name))
> +		return -1;
> +	if (params1->flags != params2->flags)
> +		return -1;
> +	return 0;
> +}
> +
> +/* assume tailq is locked */
> +static int
> +__rte_mbuf_dynflag_register_bitnum(const struct rte_mbuf_dynflag *params,
> +				unsigned int req)
> +{
> +	struct mbuf_dynflag_list *mbuf_dynflag_list;
> +	struct mbuf_dynflag_elt *mbuf_dynflag = NULL;
> +	struct rte_tailq_entry *te = NULL;
> +	unsigned int bitnum;
> +	int ret;
> +
> +	if (shm == NULL && init_shared_mem() < 0)
> +		return -1;
> +
> +	mbuf_dynflag = __mbuf_dynflag_lookup(params->name);
> +	if (mbuf_dynflag != NULL) {
> +		if (req != UINT_MAX && req != mbuf_dynflag->bitnum) {
> +			rte_errno = EEXIST;
> +			return -1;
> +		}
> +		if (mbuf_dynflag_cmp(params, &mbuf_dynflag->params) < 0) {
> +			rte_errno = EEXIST;
> +			return -1;
> +		}
> +		return mbuf_dynflag->bitnum;
> +	}
> +
> +	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
> +		rte_errno = EPERM;
> +		return -1;
> +	}
> +
> +	if (req == UINT_MAX) {
> +		if (shm->free_flags == 0) {
> +			rte_errno = ENOENT;
> +			return -1;
> +		}
> +		bitnum = rte_bsf64(shm->free_flags);
> +	} else {
> +		if ((shm->free_flags & (1ULL << req)) == 0) {
> +			rte_errno = EBUSY;
> +			return -1;
> +		}
> +		bitnum = req;
> +	}
> +
> +	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)
> +		return -1;
> +
> +	mbuf_dynflag = rte_zmalloc("mbuf_dynflag", sizeof(*mbuf_dynflag), 0);
> +	if (mbuf_dynflag == NULL) {
> +		rte_free(te);
> +		return -1;
> +	}
> +
> +	ret = strlcpy(mbuf_dynflag->params.name, params->name,
> +		sizeof(mbuf_dynflag->params.name));
> +	if (ret < 0 || ret >= (int)sizeof(mbuf_dynflag->params.name)) {
> +		rte_free(mbuf_dynflag);
> +		rte_free(te);
> +		rte_errno = ENAMETOOLONG;
> +		return -1;
> +	}
> +	mbuf_dynflag->bitnum = bitnum;
> +	te->data = mbuf_dynflag;
> +
> +	TAILQ_INSERT_TAIL(mbuf_dynflag_list, te, next);
> +
> +	shm->free_flags &= ~(1ULL << bitnum);
> +
> +	RTE_LOG(DEBUG, MBUF, "Registered dynamic flag %s (fl=0x%x) -> %u\n",
> +		params->name, params->flags, bitnum);
> +
> +	return bitnum;
> +}
> +
> +int
> +rte_mbuf_dynflag_register_bitnum(const struct rte_mbuf_dynflag *params,
> +				unsigned int req)
> +{
> +	int ret;
> +
> +	if (req != UINT_MAX && req >= 64) {

Might be better to replace 64 with something like sizeof(mbuf->ol_flags) * CHAR_BIT or so.
Apart from that:
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

> +		rte_errno = EINVAL;
> +		return -1;
> +	}
> +
> +	rte_mcfg_tailq_write_lock();
> +	ret = __rte_mbuf_dynflag_register_bitnum(params, req);
> +	rte_mcfg_tailq_write_unlock();
> +
> +	return ret;
> +}
> +