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

Olivier Matz olivier.matz at 6wind.com
Wed Sep 18 18:54:48 CEST 2019


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>
Acked-by: Thomas Monjalon <thomas at monjalon.net>
---

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                   | 114 ++++++-
 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             |  25 +-
 lib/librte_mbuf/rte_mbuf_dyn.c         | 408 +++++++++++++++++++++++++
 lib/librte_mbuf/rte_mbuf_dyn.h         | 163 ++++++++++
 lib/librte_mbuf/rte_mbuf_version.map   |   4 +
 8 files changed, 724 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..96acfc4b2 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
@@ -1121,6 +1121,112 @@ 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 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,
+	};
+	struct rte_mbuf *m = NULL;
+	int offset, offset2;
+	int flag, flag2;
+
+	printf("Test mbuf dynamic fields and flags\n");
+
+	offset = rte_mbuf_dynfield_register(&dynfield);
+	if (offset == -1)
+		GOTO_FAIL("failed to register dynamic field, offset=%d: %s",
+			offset, strerror(errno));
+
+	offset2 = rte_mbuf_dynfield_register(&dynfield);
+	if (offset2 != offset)
+		GOTO_FAIL("failed to lookup dynamic field, offset=%d, offset2=%d: %s",
+			offset, offset2, strerror(errno));
+
+	offset2 = rte_mbuf_dynfield_register(&dynfield2);
+	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("dynfield: offset = %d, offset2 = %d\n", offset, offset2);
+
+	offset = rte_mbuf_dynfield_register(&dynfield_fail_big);
+	if (offset != -1)
+		GOTO_FAIL("dynamic field creation should fail (too big)");
+
+	offset = rte_mbuf_dynfield_register(&dynfield_fail_align);
+	if (offset != -1)
+		GOTO_FAIL("dynamic field creation should fail (bad alignment)");
+
+	flag = rte_mbuf_dynflag_register(&dynflag);
+	if (flag == -1)
+		GOTO_FAIL("failed to register dynamic field, flag=%d: %s",
+			flag, strerror(errno));
+
+	flag2 = rte_mbuf_dynflag_register(&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(&dynflag2);
+	if (flag2 == -1 || flag2 == flag)
+		GOTO_FAIL("failed to register dynflag field 2, flag=%d, flag2=%d: %s",
+			flag, flag2, strerror(errno));
+
+	printf("dynflag: 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)
 {
@@ -1140,6 +1246,12 @@ 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 27cfbd9e3..0fcb76f76 100644
--- a/doc/guides/rel_notes/release_19_11.rst
+++ b/doc/guides/rel_notes/release_19_11.rst
@@ -56,6 +56,13 @@ New Features
      Also, make sure to start the actual text at the margin.
      =========================================================
 
+* **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.
+
 
 Removed Items
 -------------
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;
 
 /**
@@ -1684,6 +1689,21 @@ 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.
  *
@@ -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..13b8742d0
--- /dev/null
+++ b/lib/librte_mbuf/rte_mbuf_dyn.c
@@ -0,0 +1,408 @@
+/* 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_elt {
+	TAILQ_ENTRY(mbuf_dynfield_elt) next;
+	struct rte_mbuf_dynfield params;
+	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_elt {
+	TAILQ_ENTRY(mbuf_dynflag_elt) next;
+	struct rte_mbuf_dynflag params;
+	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_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;
+}
+
+int
+rte_mbuf_dynfield_register(const struct rte_mbuf_dynfield *params)
+{
+	struct mbuf_dynfield_list *mbuf_dynfield_list;
+	struct mbuf_dynfield_elt *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 (params->size >= sizeof(struct rte_mbuf)) {
+		rte_errno = EINVAL;
+		goto fail;
+	}
+	if (!rte_is_power_of_2(params->align)) {
+		rte_errno = EINVAL;
+		goto fail;
+	}
+	if (params->flags != 0) {
+		rte_errno = EINVAL;
+		goto fail;
+	}
+
+	rte_mcfg_tailq_write_lock();
+
+	mbuf_dynfield = __mbuf_dynfield_lookup(params->name);
+	if (mbuf_dynfield != NULL) {
+		if (mbuf_dynfield_cmp(params, &mbuf_dynfield->params) < 0) {
+			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, params->size, params->align,
+					params->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->params.name, params->name,
+		sizeof(mbuf_dynfield->params.name));
+	if (ret < 0 || ret >= (int)sizeof(mbuf_dynfield->params.name)) {
+		rte_errno = ENAMETOOLONG;
+		goto fail_unlock;
+	}
+	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;
+
+	RTE_LOG(DEBUG, MBUF, "Registered dynamic field %s (sz=%zu, al=%zu, fl=0x%x) -> %d\n",
+		params->name, params->size, params->align, params->flags,
+		offset);
+
+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_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;
+}
+
+int
+rte_mbuf_dynflag_register(const struct rte_mbuf_dynflag *params)
+{
+	struct mbuf_dynflag_list *mbuf_dynflag_list;
+	struct mbuf_dynflag_elt *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(params->name);
+	if (mbuf_dynflag != NULL) {
+		if (mbuf_dynflag_cmp(params, &mbuf_dynflag->params) < 0) {
+			rte_errno = EEXIST;
+			goto fail_unlock;
+		}
+		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->params.name, params->name,
+		sizeof(mbuf_dynflag->params.name));
+	if (ret < 0 || ret >= (int)sizeof(mbuf_dynflag->params.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);
+
+	RTE_LOG(DEBUG, MBUF, "Registered dynamic flag %s (fl=0x%x) -> %u\n",
+		params->name, params->flags, 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..6e2c81654
--- /dev/null
+++ b/lib/librte_mbuf/rte_mbuf_dyn.h
@@ -0,0 +1,163 @@
+/* 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, stored
+ *   in mbuf->ol_flags.
+ *
+ * The typical use case is when a specific offload feature requires to
+ * register a dedicated offload field in the mbuf structure, and adding
+ * a static field or flag is not justified.
+ *
+ * Example of use:
+ *
+ * - A rte_mbuf_dynfield structure is defined, containing the parameters
+ *   of the dynamic field to be registered:
+ *   const struct rte_mbuf_dynfield rte_dynfield_my_feature = { ... };
+ * - The application initializes the PMD, and asks for this feature
+ *   at port initialization by passing DEV_RX_OFFLOAD_MY_FEATURE in
+ *   rxconf. This will make the PMD to register the field by calling
+ *   rte_mbuf_dynfield_register(&rte_dynfield_my_feature). The PMD
+ *   stores the returned offset.
+ * - The application that uses the offload feature also registers
+ *   the field to retrieve the same offset.
+ * - When the PMD receives a packet, it can set the field:
+ *   *RTE_MBUF_DYNFIELD(m, offset, <type *>) = value;
+ * - In the main loop, the application can retrieve the value with
+ *   the same macro.
+ *
+ * To avoid wasting space, the dynamic fields or flags must only be
+ * reserved on demand, when an application asks for the related feature.
+ *
+ * The registration can be done at any moment, but it is not possible
+ * to unregister fields or flags for now.
+ *
+ * A dynamic field can be reserved and used by an application only.
+ * It can for instance be a packet mark.
+ */
+
+#include <sys/types.h>
+/**
+ * Maximum length of the dynamic field or flag string.
+ */
+#define RTE_MBUF_DYN_NAMESIZE 64
+
+/**
+ * Structure describing the parameters of a mbuf dynamic field.
+ */
+struct rte_mbuf_dynfield {
+	char name[RTE_MBUF_DYN_NAMESIZE]; /**< Name of the field. */
+	size_t size;        /**< The number of bytes to reserve. */
+	size_t align;       /**< The alignment constraint (power of 2). */
+	unsigned int flags; /**< Reserved for future use, must be 0. */
+};
+
+/**
+ * Structure describing the parameters of a mbuf dynamic flag.
+ */
+struct rte_mbuf_dynflag {
+	char name[RTE_MBUF_DYN_NAMESIZE]; /**< Name of the dynamic flag. */
+	unsigned int flags; /**< Reserved for future use, must be 0. */
+};
+
+/**
+ * Register space for a dynamic field in the mbuf structure.
+ *
+ * If the field is already registered (same name and parameters), its
+ * offset is returned.
+ *
+ * @param params
+ *   A structure containing the requested parameters (name, size,
+ *   alignment constraint and flags).
+ * @return
+ *   The offset in the mbuf structure, or -1 on error.
+ *   Possible values for rte_errno:
+ *   - EINVAL: invalid parameters (size, align, or flags).
+ *   - EEXIST: this name is already register with different parameters.
+ *   - EPERM: called from a secondary process.
+ *   - ENOENT: not enough room in mbuf.
+ *   - ENOMEM: allocation failure.
+ *   - ENAMETOOLONG: name does not ends with \0.
+ */
+__rte_experimental
+int rte_mbuf_dynfield_register(const struct rte_mbuf_dynfield *params);
+
+/**
+ * Lookup for a registered dynamic mbuf field.
+ *
+ * @param name
+ *   A string identifying the dynamic field.
+ * @param params
+ *   If not NULL, and if the lookup is successful, the structure is
+ *   filled with the parameters of the dynamic field.
+ * @return
+ *   The offset of this field in the mbuf structure, or -1 on error.
+ *   Possible values for rte_errno:
+ *   - ENOENT: no dynamic field matches this name.
+ */
+__rte_experimental
+int rte_mbuf_dynfield_lookup(const char *name,
+			struct rte_mbuf_dynfield *params);
+
+/**
+ * Register a dynamic flag in the mbuf structure.
+ *
+ * If the flag is already registered (same name and parameters), its
+ * offset is returned.
+ *
+ * @param params
+ *   A structure containing the requested parameters of the dynamic
+ *   flag (name and options).
+ * @return
+ *   The number of the reserved bit, or -1 on error.
+ *   Possible values for rte_errno:
+ *   - EINVAL: invalid parameters (size, align, or flags).
+ *   - EEXIST: this name is already register with different parameters.
+ *   - EPERM: called from a secondary process.
+ *   - ENOENT: no more flag available.
+ *   - ENOMEM: allocation failure.
+ *   - ENAMETOOLONG: name is longer than RTE_MBUF_DYN_NAMESIZE - 1.
+ */
+__rte_experimental
+int rte_mbuf_dynflag_register(const struct rte_mbuf_dynflag *params);
+
+/**
+ * Lookup for a registered dynamic mbuf flag.
+ *
+ * @param name
+ *   A string identifying the dynamic flag.
+ * @param params
+ *   If not NULL, and if the lookup is successful, the structure is
+ *   filled with the parameters of the dynamic flag.
+ * @return
+ *   The offset of this flag in the mbuf structure, or -1 on error.
+ *   Possible values for rte_errno:
+ *   - ENOENT: no dynamic flag matches this name.
+ */
+__rte_experimental
+int rte_mbuf_dynflag_lookup(const char *name,
+			struct rte_mbuf_dynflag *params);
+
+/**
+ * Helper macro to access to a dynamic field.
+ */
+#define RTE_MBUF_DYNFIELD(m, offset, type) ((type)((uintptr_t)(m) + (offset)))
+
+#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;
-- 
2.20.1



More information about the dev mailing list