diff mbox series

[v1,3/3] ring: rename and refactor ring library

Message ID 20201221111359.22013-4-feifei.wang2@arm.com (mailing list archive)
State Superseded, archived
Delegated to: David Marchand
Headers show
Series refactoring ring library | expand

Checks

Context Check Description
ci/iol-testing success Testing PASS
ci/iol-abi-testing success Testing PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-intel-Functional success Functional Testing PASS
ci/Intel-compilation success Compilation OK
ci/iol-broadcom-Functional success Functional Testing PASS
ci/iol-broadcom-Performance success Performance Testing PASS
ci/checkpatch success coding style OK

Commit Message

Feifei Wang Dec. 21, 2020, 11:13 a.m. UTC
For legacy modes, rename ring_generic/c11 to ring_generic/c11_pvt.
Furthermore, add new file ring_elem_pvt.h which includes ring_do_eq/deq
and ring element copy/delete APIs.

For other modes, rename xx_c11_mem to xx_elem_pvt. Move all private APIs
into these new header files.

Suggested-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
 lib/librte_ring/meson.build                   |  15 +-
 .../{rte_ring_c11_mem.h => ring_c11_pvt.h}    |   9 +-
 lib/librte_ring/ring_elem_pvt.h               | 385 ++++++++++++++++++
 ...{rte_ring_generic.h => ring_generic_pvt.h} |   6 +-
 ...ring_hts_c11_mem.h => ring_hts_elem_pvt.h} |  88 +++-
 ...ng_peek_c11_mem.h => ring_peek_elem_pvt.h} |  75 +++-
 ...ring_rts_c11_mem.h => ring_rts_elem_pvt.h} |  88 +++-
 lib/librte_ring/rte_ring_elem.h               | 374 +----------------
 lib/librte_ring/rte_ring_hts.h                |  84 +---
 lib/librte_ring/rte_ring_peek.h               |  71 +---
 lib/librte_ring/rte_ring_peek_zc.h            |   2 +-
 lib/librte_ring/rte_ring_rts.h                |  84 +---
 12 files changed, 646 insertions(+), 635 deletions(-)
 rename lib/librte_ring/{rte_ring_c11_mem.h => ring_c11_pvt.h} (96%)
 create mode 100644 lib/librte_ring/ring_elem_pvt.h
 rename lib/librte_ring/{rte_ring_generic.h => ring_generic_pvt.h} (98%)
 rename lib/librte_ring/{rte_ring_hts_c11_mem.h => ring_hts_elem_pvt.h} (60%)
 rename lib/librte_ring/{rte_ring_peek_c11_mem.h => ring_peek_elem_pvt.h} (62%)
 rename lib/librte_ring/{rte_ring_rts_c11_mem.h => ring_rts_elem_pvt.h} (62%)

Comments

Konstantin Ananyev Jan. 22, 2021, 1:08 p.m. UTC | #1
> For legacy modes, rename ring_generic/c11 to ring_generic/c11_pvt.
> Furthermore, add new file ring_elem_pvt.h which includes ring_do_eq/deq
> and ring element copy/delete APIs.
> 
> For other modes, rename xx_c11_mem to xx_elem_pvt. Move all private APIs
> into these new header files.
> 
> Suggested-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> ---
>  lib/librte_ring/meson.build                   |  15 +-
>  .../{rte_ring_c11_mem.h => ring_c11_pvt.h}    |   9 +-
>  lib/librte_ring/ring_elem_pvt.h               | 385 ++++++++++++++++++
>  ...{rte_ring_generic.h => ring_generic_pvt.h} |   6 +-
>  ...ring_hts_c11_mem.h => ring_hts_elem_pvt.h} |  88 +++-
>  ...ng_peek_c11_mem.h => ring_peek_elem_pvt.h} |  75 +++-
>  ...ring_rts_c11_mem.h => ring_rts_elem_pvt.h} |  88 +++-
>  lib/librte_ring/rte_ring_elem.h               | 374 +----------------
>  lib/librte_ring/rte_ring_hts.h                |  84 +---
>  lib/librte_ring/rte_ring_peek.h               |  71 +---
>  lib/librte_ring/rte_ring_peek_zc.h            |   2 +-
>  lib/librte_ring/rte_ring_rts.h                |  84 +---
>  12 files changed, 646 insertions(+), 635 deletions(-)
>  rename lib/librte_ring/{rte_ring_c11_mem.h => ring_c11_pvt.h} (96%)
>  create mode 100644 lib/librte_ring/ring_elem_pvt.h
>  rename lib/librte_ring/{rte_ring_generic.h => ring_generic_pvt.h} (98%)
>  rename lib/librte_ring/{rte_ring_hts_c11_mem.h => ring_hts_elem_pvt.h} (60%)
>  rename lib/librte_ring/{rte_ring_peek_c11_mem.h => ring_peek_elem_pvt.h} (62%)
>  rename lib/librte_ring/{rte_ring_rts_c11_mem.h => ring_rts_elem_pvt.h} (62%)
> 

Sorry, but I don't understand the purpose of that patch. 
As I remember by DPDK naming convention all installable headers
should have 'rte_' prefix. Same for public defines (RTE_).
Why to abandon it here?

> diff --git a/lib/librte_ring/meson.build b/lib/librte_ring/meson.build
> index 36fdcb6a5..98eac5810 100644
> --- a/lib/librte_ring/meson.build
> +++ b/lib/librte_ring/meson.build
> @@ -2,15 +2,16 @@
>  # Copyright(c) 2017 Intel Corporation
> 
>  sources = files('rte_ring.c')
> -headers = files('rte_ring.h',
> +headers = files('ring_c11_pvt.h',
> +		'ring_elem_pvt.h',
> +		'ring_generic_pvt.h',
> +		'ring_hts_elem_pvt.h',
> +		'ring_peek_elem_pvt.h',
> +		'ring_rts_elem_pvt.h',
> +		'rte_ring.h',
>  		'rte_ring_core.h',
>  		'rte_ring_elem.h',
> -		'rte_ring_c11_mem.h',
> -		'rte_ring_generic.h',
>  		'rte_ring_hts.h',
> -		'rte_ring_hts_c11_mem.h',
>  		'rte_ring_peek.h',
> -		'rte_ring_peek_c11_mem.h',
>  		'rte_ring_peek_zc.h',
> -		'rte_ring_rts.h',
> -		'rte_ring_rts_c11_mem.h')
> +		'rte_ring_rts.h')
> diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/ring_c11_pvt.h
> similarity index 96%
> rename from lib/librte_ring/rte_ring_c11_mem.h
> rename to lib/librte_ring/ring_c11_pvt.h
> index 7f5eba262..9f2f5318f 100644
> --- a/lib/librte_ring/rte_ring_c11_mem.h
> +++ b/lib/librte_ring/ring_c11_pvt.h
> @@ -7,8 +7,8 @@
>   * Used as BSD-3 Licensed with permission from Kip Macy.
>   */
> 
> -#ifndef _RTE_RING_C11_MEM_H_
> -#define _RTE_RING_C11_MEM_H_
> +#ifndef _RING_C11_PVT_H_
> +#define _RING_C11_PVT_H_
> 
>  static __rte_always_inline void
>  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
> @@ -69,9 +69,6 @@ __rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
>  		/* Ensure the head is read before tail */
>  		__atomic_thread_fence(__ATOMIC_ACQUIRE);
> 
> -		/* load-acquire synchronize with store-release of ht->tail
> -		 * in update_tail.
> -		 */
>  		cons_tail = __atomic_load_n(&r->cons.tail,
>  					__ATOMIC_ACQUIRE);
> 
> @@ -178,4 +175,4 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
>  	return n;
>  }
> 
> -#endif /* _RTE_RING_C11_MEM_H_ */
> +#endif /* _RING_C11_PVT_H_ */
> diff --git a/lib/librte_ring/ring_elem_pvt.h b/lib/librte_ring/ring_elem_pvt.h
> new file mode 100644
> index 000000000..8003e5edc
> --- /dev/null
> +++ b/lib/librte_ring/ring_elem_pvt.h
> @@ -0,0 +1,385 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + *
> + * Copyright (c) 2017,2018 HXT-semitech Corporation.
> + * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
> + * All rights reserved.
> + * Derived from FreeBSD's bufring.h
> + * Used as BSD-3 Licensed with permission from Kip Macy.
> + */
> +
> +#ifndef _RING_ELEM_PVT_H_
> +#define _RING_ELEM_PVT_H_
> +
> +static __rte_always_inline void
> +__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> +		uint32_t idx, const void *obj_table, uint32_t n)
> +{
> +	unsigned int i;
> +	uint32_t *ring = (uint32_t *)&r[1];
> +	const uint32_t *obj = (const uint32_t *)obj_table;
> +	if (likely(idx + n < size)) {
> +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> +			ring[idx] = obj[i];
> +			ring[idx + 1] = obj[i + 1];
> +			ring[idx + 2] = obj[i + 2];
> +			ring[idx + 3] = obj[i + 3];
> +			ring[idx + 4] = obj[i + 4];
> +			ring[idx + 5] = obj[i + 5];
> +			ring[idx + 6] = obj[i + 6];
> +			ring[idx + 7] = obj[i + 7];
> +		}
> +		switch (n & 0x7) {
> +		case 7:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 6:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 5:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 4:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 3:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 2:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 1:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		}
> +	} else {
> +		for (i = 0; idx < size; i++, idx++)
> +			ring[idx] = obj[i];
> +		/* Start at the beginning */
> +		for (idx = 0; i < n; i++, idx++)
> +			ring[idx] = obj[i];
> +	}
> +}
> +
> +static __rte_always_inline void
> +__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> +		const void *obj_table, uint32_t n)
> +{
> +	unsigned int i;
> +	const uint32_t size = r->size;
> +	uint32_t idx = prod_head & r->mask;
> +	uint64_t *ring = (uint64_t *)&r[1];
> +	const unaligned_uint64_t *obj = (const unaligned_uint64_t *)obj_table;
> +	if (likely(idx + n < size)) {
> +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> +			ring[idx] = obj[i];
> +			ring[idx + 1] = obj[i + 1];
> +			ring[idx + 2] = obj[i + 2];
> +			ring[idx + 3] = obj[i + 3];
> +		}
> +		switch (n & 0x3) {
> +		case 3:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 2:
> +			ring[idx++] = obj[i++]; /* fallthrough */
> +		case 1:
> +			ring[idx++] = obj[i++];
> +		}
> +	} else {
> +		for (i = 0; idx < size; i++, idx++)
> +			ring[idx] = obj[i];
> +		/* Start at the beginning */
> +		for (idx = 0; i < n; i++, idx++)
> +			ring[idx] = obj[i];
> +	}
> +}
> +
> +static __rte_always_inline void
> +__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> +		const void *obj_table, uint32_t n)
> +{
> +	unsigned int i;
> +	const uint32_t size = r->size;
> +	uint32_t idx = prod_head & r->mask;
> +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> +	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> +	if (likely(idx + n < size)) {
> +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> +			memcpy((void *)(ring + idx),
> +				(const void *)(obj + i), 32);
> +		switch (n & 0x1) {
> +		case 1:
> +			memcpy((void *)(ring + idx),
> +				(const void *)(obj + i), 16);
> +		}
> +	} else {
> +		for (i = 0; idx < size; i++, idx++)
> +			memcpy((void *)(ring + idx),
> +				(const void *)(obj + i), 16);
> +		/* Start at the beginning */
> +		for (idx = 0; i < n; i++, idx++)
> +			memcpy((void *)(ring + idx),
> +				(const void *)(obj + i), 16);
> +	}
> +}
> +
> +/* the actual enqueue of elements on the ring.
> + * Placed here since identical code needed in both
> + * single and multi producer enqueue functions.
> + */
> +static __rte_always_inline void
> +__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> +		const void *obj_table, uint32_t esize, uint32_t num)
> +{
> +	/* 8B and 16B copies implemented individually to retain
> +	 * the current performance.
> +	 */
> +	if (esize == 8)
> +		__rte_ring_enqueue_elems_64(r, prod_head, obj_table, num);
> +	else if (esize == 16)
> +		__rte_ring_enqueue_elems_128(r, prod_head, obj_table, num);
> +	else {
> +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> +
> +		/* Normalize to uint32_t */
> +		scale = esize / sizeof(uint32_t);
> +		nr_num = num * scale;
> +		idx = prod_head & r->mask;
> +		nr_idx = idx * scale;
> +		nr_size = r->size * scale;
> +		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> +				obj_table, nr_num);
> +	}
> +}
> +
> +static __rte_always_inline void
> +__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> +		uint32_t idx, void *obj_table, uint32_t n)
> +{
> +	unsigned int i;
> +	uint32_t *ring = (uint32_t *)&r[1];
> +	uint32_t *obj = (uint32_t *)obj_table;
> +	if (likely(idx + n < size)) {
> +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> +			obj[i] = ring[idx];
> +			obj[i + 1] = ring[idx + 1];
> +			obj[i + 2] = ring[idx + 2];
> +			obj[i + 3] = ring[idx + 3];
> +			obj[i + 4] = ring[idx + 4];
> +			obj[i + 5] = ring[idx + 5];
> +			obj[i + 6] = ring[idx + 6];
> +			obj[i + 7] = ring[idx + 7];
> +		}
> +		switch (n & 0x7) {
> +		case 7:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 6:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 5:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 4:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 3:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 2:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 1:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		}
> +	} else {
> +		for (i = 0; idx < size; i++, idx++)
> +			obj[i] = ring[idx];
> +		/* Start at the beginning */
> +		for (idx = 0; i < n; i++, idx++)
> +			obj[i] = ring[idx];
> +	}
> +}
> +
> +static __rte_always_inline void
> +__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> +		void *obj_table, uint32_t n)
> +{
> +	unsigned int i;
> +	const uint32_t size = r->size;
> +	uint32_t idx = prod_head & r->mask;
> +	uint64_t *ring = (uint64_t *)&r[1];
> +	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> +	if (likely(idx + n < size)) {
> +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> +			obj[i] = ring[idx];
> +			obj[i + 1] = ring[idx + 1];
> +			obj[i + 2] = ring[idx + 2];
> +			obj[i + 3] = ring[idx + 3];
> +		}
> +		switch (n & 0x3) {
> +		case 3:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 2:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		case 1:
> +			obj[i++] = ring[idx++]; /* fallthrough */
> +		}
> +	} else {
> +		for (i = 0; idx < size; i++, idx++)
> +			obj[i] = ring[idx];
> +		/* Start at the beginning */
> +		for (idx = 0; i < n; i++, idx++)
> +			obj[i] = ring[idx];
> +	}
> +}
> +
> +static __rte_always_inline void
> +__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> +		void *obj_table, uint32_t n)
> +{
> +	unsigned int i;
> +	const uint32_t size = r->size;
> +	uint32_t idx = prod_head & r->mask;
> +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> +	rte_int128_t *obj = (rte_int128_t *)obj_table;
> +	if (likely(idx + n < size)) {
> +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> +			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> +		switch (n & 0x1) {
> +		case 1:
> +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> +		}
> +	} else {
> +		for (i = 0; idx < size; i++, idx++)
> +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> +		/* Start at the beginning */
> +		for (idx = 0; i < n; i++, idx++)
> +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> +	}
> +}
> +
> +/* the actual dequeue of elements from the ring.
> + * Placed here since identical code needed in both
> + * single and multi producer enqueue functions.
> + */
> +static __rte_always_inline void
> +__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> +		void *obj_table, uint32_t esize, uint32_t num)
> +{
> +	/* 8B and 16B copies implemented individually to retain
> +	 * the current performance.
> +	 */
> +	if (esize == 8)
> +		__rte_ring_dequeue_elems_64(r, cons_head, obj_table, num);
> +	else if (esize == 16)
> +		__rte_ring_dequeue_elems_128(r, cons_head, obj_table, num);
> +	else {
> +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> +
> +		/* Normalize to uint32_t */
> +		scale = esize / sizeof(uint32_t);
> +		nr_num = num * scale;
> +		idx = cons_head & r->mask;
> +		nr_idx = idx * scale;
> +		nr_size = r->size * scale;
> +		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> +				obj_table, nr_num);
> +	}
> +}
> +
> +/* Between load and load. there might be cpu reorder in weak model
> + * (powerpc/arm).
> + * There are 2 choices for the users
> + * 1.use rmb() memory barrier
> + * 2.use one-direction load_acquire/store_release barrier
> + * It depends on performance test results.
> + */
> +#ifdef RTE_USE_C11_MEM_MODEL
> +#include "ring_c11_pvt.h"
> +#else
> +#include "ring_generic_pvt.h"
> +#endif
> +
> +/**
> + * @internal Enqueue several objects on the ring
> + *
> + * @param r
> + *   A pointer to the ring structure.
> + * @param obj_table
> + *   A pointer to a table of objects.
> + * @param esize
> + *   The size of ring element, in bytes. It must be a multiple of 4.
> + *   This must be the same value used while creating the ring. Otherwise
> + *   the results are undefined.
> + * @param n
> + *   The number of objects to add in the ring from the obj_table.
> + * @param behavior
> + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
> + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
> + * @param is_sp
> + *   Indicates whether to use single producer or multi-producer head update
> + * @param free_space
> + *   returns the amount of space after the enqueue operation has finished
> + * @return
> + *   Actual number of objects enqueued.
> + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> +		unsigned int esize, unsigned int n,
> +		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> +		unsigned int *free_space)
> +{
> +	uint32_t prod_head, prod_next;
> +	uint32_t free_entries;
> +
> +	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> +			&prod_head, &prod_next, &free_entries);
> +	if (n == 0)
> +		goto end;
> +
> +	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> +
> +	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> +end:
> +	if (free_space != NULL)
> +		*free_space = free_entries - n;
> +	return n;
> +}
> +
> +/**
> + * @internal Dequeue several objects from the ring
> + *
> + * @param r
> + *   A pointer to the ring structure.
> + * @param obj_table
> + *   A pointer to a table of objects.
> + * @param esize
> + *   The size of ring element, in bytes. It must be a multiple of 4.
> + *   This must be the same value used while creating the ring. Otherwise
> + *   the results are undefined.
> + * @param n
> + *   The number of objects to pull from the ring.
> + * @param behavior
> + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
> + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
> + * @param is_sc
> + *   Indicates whether to use single consumer or multi-consumer head update
> + * @param available
> + *   returns the number of remaining ring entries after the dequeue has finished
> + * @return
> + *   - Actual number of objects dequeued.
> + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> +		unsigned int esize, unsigned int n,
> +		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> +		unsigned int *available)
> +{
> +	uint32_t cons_head, cons_next;
> +	uint32_t entries;
> +
> +	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> +			&cons_head, &cons_next, &entries);
> +	if (n == 0)
> +		goto end;
> +
> +	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> +
> +	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> +
> +end:
> +	if (available != NULL)
> +		*available = entries - n;
> +	return n;
> +}
> +
> +#endif /* _RING_ELEM_PVT_H_ */
> diff --git a/lib/librte_ring/rte_ring_generic.h b/lib/librte_ring/ring_generic_pvt.h
> similarity index 98%
> rename from lib/librte_ring/rte_ring_generic.h
> rename to lib/librte_ring/ring_generic_pvt.h
> index 37c62b8d6..fc46a27b2 100644
> --- a/lib/librte_ring/rte_ring_generic.h
> +++ b/lib/librte_ring/ring_generic_pvt.h
> @@ -7,8 +7,8 @@
>   * Used as BSD-3 Licensed with permission from Kip Macy.
>   */
> 
> -#ifndef _RTE_RING_GENERIC_H_
> -#define _RTE_RING_GENERIC_H_
> +#ifndef _RING_GENERIC_PVT_H_
> +#define _RING_GENERIC_PVT_H_
> 
>  static __rte_always_inline void
>  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
> @@ -170,4 +170,4 @@ __rte_ring_move_cons_head(struct rte_ring *r, unsigned int is_sc,
>  	return n;
>  }
> 
> -#endif /* _RTE_RING_GENERIC_H_ */
> +#endif /* _RING_GENERIC_PVT_H_ */
> diff --git a/lib/librte_ring/rte_ring_hts_c11_mem.h b/lib/librte_ring/ring_hts_elem_pvt.h
> similarity index 60%
> rename from lib/librte_ring/rte_ring_hts_c11_mem.h
> rename to lib/librte_ring/ring_hts_elem_pvt.h
> index 16e54b6ff..9268750b0 100644
> --- a/lib/librte_ring/rte_ring_hts_c11_mem.h
> +++ b/lib/librte_ring/ring_hts_elem_pvt.h
> @@ -7,8 +7,8 @@
>   * Used as BSD-3 Licensed with permission from Kip Macy.
>   */
> 
> -#ifndef _RTE_RING_HTS_C11_MEM_H_
> -#define _RTE_RING_HTS_C11_MEM_H_
> +#ifndef _RING_HTS_ELEM_PVT_H_
> +#define _RING_HTS_ELEM_PVT_H_
> 
>  /**
>   * @file rte_ring_hts_c11_mem.h
> @@ -161,4 +161,86 @@ __rte_ring_hts_move_cons_head(struct rte_ring *r, unsigned int num,
>  	return n;
>  }
> 
> -#endif /* _RTE_RING_HTS_C11_MEM_H_ */
> +/**
> + * @internal Enqueue several objects on the HTS ring.
> + *
> + * @param r
> + *   A pointer to the ring structure.
> + * @param obj_table
> + *   A pointer to a table of objects.
> + * @param esize
> + *   The size of ring element, in bytes. It must be a multiple of 4.
> + *   This must be the same value used while creating the ring. Otherwise
> + *   the results are undefined.
> + * @param n
> + *   The number of objects to add in the ring from the obj_table.
> + * @param behavior
> + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
> + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
> + * @param free_space
> + *   returns the amount of space after the enqueue operation has finished
> + * @return
> + *   Actual number of objects enqueued.
> + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void *obj_table,
> +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> +	uint32_t *free_space)
> +{
> +	uint32_t free, head;
> +
> +	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> +
> +	if (n != 0) {
> +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> +		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> +	}
> +
> +	if (free_space != NULL)
> +		*free_space = free - n;
> +	return n;
> +}
> +
> +/**
> + * @internal Dequeue several objects from the HTS ring.
> + *
> + * @param r
> + *   A pointer to the ring structure.
> + * @param obj_table
> + *   A pointer to a table of objects.
> + * @param esize
> + *   The size of ring element, in bytes. It must be a multiple of 4.
> + *   This must be the same value used while creating the ring. Otherwise
> + *   the results are undefined.
> + * @param n
> + *   The number of objects to pull from the ring.
> + * @param behavior
> + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
> + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
> + * @param available
> + *   returns the number of remaining ring entries after the dequeue has finished
> + * @return
> + *   - Actual number of objects dequeued.
> + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> +	uint32_t *available)
> +{
> +	uint32_t entries, head;
> +
> +	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head, &entries);
> +
> +	if (n != 0) {
> +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> +		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> +	}
> +
> +	if (available != NULL)
> +		*available = entries - n;
> +	return n;
> +}
> +
> +#endif /* _RING_HTS_ELEM_PVT_H_ */
> diff --git a/lib/librte_ring/rte_ring_peek_c11_mem.h b/lib/librte_ring/ring_peek_elem_pvt.h
> similarity index 62%
> rename from lib/librte_ring/rte_ring_peek_c11_mem.h
> rename to lib/librte_ring/ring_peek_elem_pvt.h
> index 283c7e70b..1c57bcdd6 100644
> --- a/lib/librte_ring/rte_ring_peek_c11_mem.h
> +++ b/lib/librte_ring/ring_peek_elem_pvt.h
> @@ -7,8 +7,8 @@
>   * Used as BSD-3 Licensed with permission from Kip Macy.
>   */
> 
> -#ifndef _RTE_RING_PEEK_C11_MEM_H_
> -#define _RTE_RING_PEEK_C11_MEM_H_
> +#ifndef _RING_PEEK_ELEM_PVT_H_
> +#define _RING_PEEK_ELEM_PVT_H_
> 
>  /**
>   * @file rte_ring_peek_c11_mem.h
> @@ -107,4 +107,73 @@ __rte_ring_hts_set_head_tail(struct rte_ring_hts_headtail *ht, uint32_t tail,
>  	__atomic_store_n(&ht->ht.raw, p.raw, __ATOMIC_RELEASE);
>  }
> 
> -#endif /* _RTE_RING_PEEK_C11_MEM_H_ */
> +/**
> + * @internal This function moves prod head value.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> +		enum rte_ring_queue_behavior behavior, uint32_t *free_space)
> +{
> +	uint32_t free, head, next;
> +
> +	switch (r->prod.sync_type) {
> +	case RTE_RING_SYNC_ST:
> +		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> +			behavior, &head, &next, &free);
> +		break;
> +	case RTE_RING_SYNC_MT_HTS:
> +		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> +			&head, &free);
> +		break;
> +	case RTE_RING_SYNC_MT:
> +	case RTE_RING_SYNC_MT_RTS:
> +	default:
> +		/* unsupported mode, shouldn't be here */
> +		RTE_ASSERT(0);
> +		n = 0;
> +		free = 0;
> +	}
> +
> +	if (free_space != NULL)
> +		*free_space = free - n;
> +	return n;
> +}
> +
> +/**
> + * @internal This function moves cons head value and copies up to *n*
> + * objects from the ring to the user provided obj_table.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> +	uint32_t *available)
> +{
> +	uint32_t avail, head, next;
> +
> +	switch (r->cons.sync_type) {
> +	case RTE_RING_SYNC_ST:
> +		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> +			behavior, &head, &next, &avail);
> +		break;
> +	case RTE_RING_SYNC_MT_HTS:
> +		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> +			&head, &avail);
> +		break;
> +	case RTE_RING_SYNC_MT:
> +	case RTE_RING_SYNC_MT_RTS:
> +	default:
> +		/* unsupported mode, shouldn't be here */
> +		RTE_ASSERT(0);
> +		n = 0;
> +		avail = 0;
> +	}
> +
> +	if (n != 0)
> +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> +
> +	if (available != NULL)
> +		*available = avail - n;
> +	return n;
> +}
> +
> +#endif /* _RING_PEEK_ELEM_PVT_H_ */
> diff --git a/lib/librte_ring/rte_ring_rts_c11_mem.h b/lib/librte_ring/ring_rts_elem_pvt.h
> similarity index 62%
> rename from lib/librte_ring/rte_ring_rts_c11_mem.h
> rename to lib/librte_ring/ring_rts_elem_pvt.h
> index 327f22796..cbcec73eb 100644
> --- a/lib/librte_ring/rte_ring_rts_c11_mem.h
> +++ b/lib/librte_ring/ring_rts_elem_pvt.h
> @@ -7,8 +7,8 @@
>   * Used as BSD-3 Licensed with permission from Kip Macy.
>   */
> 
> -#ifndef _RTE_RING_RTS_C11_MEM_H_
> -#define _RTE_RING_RTS_C11_MEM_H_
> +#ifndef _RING_RTS_ELEM_PVT_H_
> +#define _RING_RTS_ELEM_PVT_H_
> 
>  /**
>   * @file rte_ring_rts_c11_mem.h
> @@ -176,4 +176,86 @@ __rte_ring_rts_move_cons_head(struct rte_ring *r, uint32_t num,
>  	return n;
>  }
> 
> -#endif /* _RTE_RING_RTS_C11_MEM_H_ */
> +/**
> + * @internal Enqueue several objects on the RTS ring.
> + *
> + * @param r
> + *   A pointer to the ring structure.
> + * @param obj_table
> + *   A pointer to a table of objects.
> + * @param esize
> + *   The size of ring element, in bytes. It must be a multiple of 4.
> + *   This must be the same value used while creating the ring. Otherwise
> + *   the results are undefined.
> + * @param n
> + *   The number of objects to add in the ring from the obj_table.
> + * @param behavior
> + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
> + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
> + * @param free_space
> + *   returns the amount of space after the enqueue operation has finished
> + * @return
> + *   Actual number of objects enqueued.
> + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void *obj_table,
> +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> +	uint32_t *free_space)
> +{
> +	uint32_t free, head;
> +
> +	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> +
> +	if (n != 0) {
> +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> +		__rte_ring_rts_update_tail(&r->rts_prod);
> +	}
> +
> +	if (free_space != NULL)
> +		*free_space = free - n;
> +	return n;
> +}
> +
> +/**
> + * @internal Dequeue several objects from the RTS ring.
> + *
> + * @param r
> + *   A pointer to the ring structure.
> + * @param obj_table
> + *   A pointer to a table of objects.
> + * @param esize
> + *   The size of ring element, in bytes. It must be a multiple of 4.
> + *   This must be the same value used while creating the ring. Otherwise
> + *   the results are undefined.
> + * @param n
> + *   The number of objects to pull from the ring.
> + * @param behavior
> + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
> + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
> + * @param available
> + *   returns the number of remaining ring entries after the dequeue has finished
> + * @return
> + *   - Actual number of objects dequeued.
> + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> + */
> +static __rte_always_inline unsigned int
> +__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> +	uint32_t *available)
> +{
> +	uint32_t entries, head;
> +
> +	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head, &entries);
> +
> +	if (n != 0) {
> +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> +		__rte_ring_rts_update_tail(&r->rts_cons);
> +	}
> +
> +	if (available != NULL)
> +		*available = entries - n;
> +	return n;
> +}
> +
> +#endif /* _RING_RTS_ELEM_PVT_H_ */
> diff --git a/lib/librte_ring/rte_ring_elem.h b/lib/librte_ring/rte_ring_elem.h
> index 57344d47d..119b5c0b6 100644
> --- a/lib/librte_ring/rte_ring_elem.h
> +++ b/lib/librte_ring/rte_ring_elem.h
> @@ -21,6 +21,7 @@ extern "C" {
>  #endif
> 
>  #include <rte_ring_core.h>
> +#include <ring_elem_pvt.h>
> 
>  /**
>   * Calculate the memory size needed for a ring with given element size
> @@ -105,379 +106,6 @@ ssize_t rte_ring_get_memsize_elem(unsigned int esize, unsigned int count);
>  struct rte_ring *rte_ring_create_elem(const char *name, unsigned int esize,
>  			unsigned int count, int socket_id, unsigned int flags);
> 
> -static __rte_always_inline void
> -__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> -		uint32_t idx, const void *obj_table, uint32_t n)
> -{
> -	unsigned int i;
> -	uint32_t *ring = (uint32_t *)&r[1];
> -	const uint32_t *obj = (const uint32_t *)obj_table;
> -	if (likely(idx + n < size)) {
> -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> -			ring[idx] = obj[i];
> -			ring[idx + 1] = obj[i + 1];
> -			ring[idx + 2] = obj[i + 2];
> -			ring[idx + 3] = obj[i + 3];
> -			ring[idx + 4] = obj[i + 4];
> -			ring[idx + 5] = obj[i + 5];
> -			ring[idx + 6] = obj[i + 6];
> -			ring[idx + 7] = obj[i + 7];
> -		}
> -		switch (n & 0x7) {
> -		case 7:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 6:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 5:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 4:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 3:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 2:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 1:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		}
> -	} else {
> -		for (i = 0; idx < size; i++, idx++)
> -			ring[idx] = obj[i];
> -		/* Start at the beginning */
> -		for (idx = 0; i < n; i++, idx++)
> -			ring[idx] = obj[i];
> -	}
> -}
> -
> -static __rte_always_inline void
> -__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> -		const void *obj_table, uint32_t n)
> -{
> -	unsigned int i;
> -	const uint32_t size = r->size;
> -	uint32_t idx = prod_head & r->mask;
> -	uint64_t *ring = (uint64_t *)&r[1];
> -	const unaligned_uint64_t *obj = (const unaligned_uint64_t *)obj_table;
> -	if (likely(idx + n < size)) {
> -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> -			ring[idx] = obj[i];
> -			ring[idx + 1] = obj[i + 1];
> -			ring[idx + 2] = obj[i + 2];
> -			ring[idx + 3] = obj[i + 3];
> -		}
> -		switch (n & 0x3) {
> -		case 3:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 2:
> -			ring[idx++] = obj[i++]; /* fallthrough */
> -		case 1:
> -			ring[idx++] = obj[i++];
> -		}
> -	} else {
> -		for (i = 0; idx < size; i++, idx++)
> -			ring[idx] = obj[i];
> -		/* Start at the beginning */
> -		for (idx = 0; i < n; i++, idx++)
> -			ring[idx] = obj[i];
> -	}
> -}
> -
> -static __rte_always_inline void
> -__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> -		const void *obj_table, uint32_t n)
> -{
> -	unsigned int i;
> -	const uint32_t size = r->size;
> -	uint32_t idx = prod_head & r->mask;
> -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> -	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> -	if (likely(idx + n < size)) {
> -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> -			memcpy((void *)(ring + idx),
> -				(const void *)(obj + i), 32);
> -		switch (n & 0x1) {
> -		case 1:
> -			memcpy((void *)(ring + idx),
> -				(const void *)(obj + i), 16);
> -		}
> -	} else {
> -		for (i = 0; idx < size; i++, idx++)
> -			memcpy((void *)(ring + idx),
> -				(const void *)(obj + i), 16);
> -		/* Start at the beginning */
> -		for (idx = 0; i < n; i++, idx++)
> -			memcpy((void *)(ring + idx),
> -				(const void *)(obj + i), 16);
> -	}
> -}
> -
> -/* the actual enqueue of elements on the ring.
> - * Placed here since identical code needed in both
> - * single and multi producer enqueue functions.
> - */
> -static __rte_always_inline void
> -__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> -		const void *obj_table, uint32_t esize, uint32_t num)
> -{
> -	/* 8B and 16B copies implemented individually to retain
> -	 * the current performance.
> -	 */
> -	if (esize == 8)
> -		__rte_ring_enqueue_elems_64(r, prod_head, obj_table, num);
> -	else if (esize == 16)
> -		__rte_ring_enqueue_elems_128(r, prod_head, obj_table, num);
> -	else {
> -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> -
> -		/* Normalize to uint32_t */
> -		scale = esize / sizeof(uint32_t);
> -		nr_num = num * scale;
> -		idx = prod_head & r->mask;
> -		nr_idx = idx * scale;
> -		nr_size = r->size * scale;
> -		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> -				obj_table, nr_num);
> -	}
> -}
> -
> -static __rte_always_inline void
> -__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> -		uint32_t idx, void *obj_table, uint32_t n)
> -{
> -	unsigned int i;
> -	uint32_t *ring = (uint32_t *)&r[1];
> -	uint32_t *obj = (uint32_t *)obj_table;
> -	if (likely(idx + n < size)) {
> -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> -			obj[i] = ring[idx];
> -			obj[i + 1] = ring[idx + 1];
> -			obj[i + 2] = ring[idx + 2];
> -			obj[i + 3] = ring[idx + 3];
> -			obj[i + 4] = ring[idx + 4];
> -			obj[i + 5] = ring[idx + 5];
> -			obj[i + 6] = ring[idx + 6];
> -			obj[i + 7] = ring[idx + 7];
> -		}
> -		switch (n & 0x7) {
> -		case 7:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 6:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 5:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 4:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 3:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 2:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 1:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		}
> -	} else {
> -		for (i = 0; idx < size; i++, idx++)
> -			obj[i] = ring[idx];
> -		/* Start at the beginning */
> -		for (idx = 0; i < n; i++, idx++)
> -			obj[i] = ring[idx];
> -	}
> -}
> -
> -static __rte_always_inline void
> -__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> -		void *obj_table, uint32_t n)
> -{
> -	unsigned int i;
> -	const uint32_t size = r->size;
> -	uint32_t idx = prod_head & r->mask;
> -	uint64_t *ring = (uint64_t *)&r[1];
> -	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> -	if (likely(idx + n < size)) {
> -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> -			obj[i] = ring[idx];
> -			obj[i + 1] = ring[idx + 1];
> -			obj[i + 2] = ring[idx + 2];
> -			obj[i + 3] = ring[idx + 3];
> -		}
> -		switch (n & 0x3) {
> -		case 3:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 2:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		case 1:
> -			obj[i++] = ring[idx++]; /* fallthrough */
> -		}
> -	} else {
> -		for (i = 0; idx < size; i++, idx++)
> -			obj[i] = ring[idx];
> -		/* Start at the beginning */
> -		for (idx = 0; i < n; i++, idx++)
> -			obj[i] = ring[idx];
> -	}
> -}
> -
> -static __rte_always_inline void
> -__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> -		void *obj_table, uint32_t n)
> -{
> -	unsigned int i;
> -	const uint32_t size = r->size;
> -	uint32_t idx = prod_head & r->mask;
> -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> -	rte_int128_t *obj = (rte_int128_t *)obj_table;
> -	if (likely(idx + n < size)) {
> -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> -		switch (n & 0x1) {
> -		case 1:
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> -		}
> -	} else {
> -		for (i = 0; idx < size; i++, idx++)
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> -		/* Start at the beginning */
> -		for (idx = 0; i < n; i++, idx++)
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> -	}
> -}
> -
> -/* the actual dequeue of elements from the ring.
> - * Placed here since identical code needed in both
> - * single and multi producer enqueue functions.
> - */
> -static __rte_always_inline void
> -__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> -		void *obj_table, uint32_t esize, uint32_t num)
> -{
> -	/* 8B and 16B copies implemented individually to retain
> -	 * the current performance.
> -	 */
> -	if (esize == 8)
> -		__rte_ring_dequeue_elems_64(r, cons_head, obj_table, num);
> -	else if (esize == 16)
> -		__rte_ring_dequeue_elems_128(r, cons_head, obj_table, num);
> -	else {
> -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> -
> -		/* Normalize to uint32_t */
> -		scale = esize / sizeof(uint32_t);
> -		nr_num = num * scale;
> -		idx = cons_head & r->mask;
> -		nr_idx = idx * scale;
> -		nr_size = r->size * scale;
> -		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> -				obj_table, nr_num);
> -	}
> -}
> -
> -/* Between load and load. there might be cpu reorder in weak model
> - * (powerpc/arm).
> - * There are 2 choices for the users
> - * 1.use rmb() memory barrier
> - * 2.use one-direction load_acquire/store_release barrier
> - * It depends on performance test results.
> - * By default, move common functions to rte_ring_generic.h
> - */
> -#ifdef RTE_USE_C11_MEM_MODEL
> -#include "rte_ring_c11_mem.h"
> -#else
> -#include "rte_ring_generic.h"
> -#endif
> -
> -/**
> - * @internal Enqueue several objects on the ring
> - *
> - * @param r
> - *   A pointer to the ring structure.
> - * @param obj_table
> - *   A pointer to a table of objects.
> - * @param esize
> - *   The size of ring element, in bytes. It must be a multiple of 4.
> - *   This must be the same value used while creating the ring. Otherwise
> - *   the results are undefined.
> - * @param n
> - *   The number of objects to add in the ring from the obj_table.
> - * @param behavior
> - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
> - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
> - * @param is_sp
> - *   Indicates whether to use single producer or multi-producer head update
> - * @param free_space
> - *   returns the amount of space after the enqueue operation has finished
> - * @return
> - *   Actual number of objects enqueued.
> - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> -		unsigned int esize, unsigned int n,
> -		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> -		unsigned int *free_space)
> -{
> -	uint32_t prod_head, prod_next;
> -	uint32_t free_entries;
> -
> -	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> -			&prod_head, &prod_next, &free_entries);
> -	if (n == 0)
> -		goto end;
> -
> -	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> -
> -	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> -end:
> -	if (free_space != NULL)
> -		*free_space = free_entries - n;
> -	return n;
> -}
> -
> -/**
> - * @internal Dequeue several objects from the ring
> - *
> - * @param r
> - *   A pointer to the ring structure.
> - * @param obj_table
> - *   A pointer to a table of objects.
> - * @param esize
> - *   The size of ring element, in bytes. It must be a multiple of 4.
> - *   This must be the same value used while creating the ring. Otherwise
> - *   the results are undefined.
> - * @param n
> - *   The number of objects to pull from the ring.
> - * @param behavior
> - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
> - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
> - * @param is_sc
> - *   Indicates whether to use single consumer or multi-consumer head update
> - * @param available
> - *   returns the number of remaining ring entries after the dequeue has finished
> - * @return
> - *   - Actual number of objects dequeued.
> - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> -		unsigned int esize, unsigned int n,
> -		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> -		unsigned int *available)
> -{
> -	uint32_t cons_head, cons_next;
> -	uint32_t entries;
> -
> -	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> -			&cons_head, &cons_next, &entries);
> -	if (n == 0)
> -		goto end;
> -
> -	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> -
> -	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> -
> -end:
> -	if (available != NULL)
> -		*available = entries - n;
> -	return n;
> -}
> -
>  /**
>   * Enqueue several objects on the ring (multi-producers safe).
>   *
> diff --git a/lib/librte_ring/rte_ring_hts.h b/lib/librte_ring/rte_ring_hts.h
> index 359b15771..bdbdafc9f 100644
> --- a/lib/librte_ring/rte_ring_hts.h
> +++ b/lib/librte_ring/rte_ring_hts.h
> @@ -29,89 +29,7 @@
>  extern "C" {
>  #endif
> 
> -#include <rte_ring_hts_c11_mem.h>
> -
> -/**
> - * @internal Enqueue several objects on the HTS ring.
> - *
> - * @param r
> - *   A pointer to the ring structure.
> - * @param obj_table
> - *   A pointer to a table of objects.
> - * @param esize
> - *   The size of ring element, in bytes. It must be a multiple of 4.
> - *   This must be the same value used while creating the ring. Otherwise
> - *   the results are undefined.
> - * @param n
> - *   The number of objects to add in the ring from the obj_table.
> - * @param behavior
> - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
> - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
> - * @param free_space
> - *   returns the amount of space after the enqueue operation has finished
> - * @return
> - *   Actual number of objects enqueued.
> - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void *obj_table,
> -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> -	uint32_t *free_space)
> -{
> -	uint32_t free, head;
> -
> -	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> -
> -	if (n != 0) {
> -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> -		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> -	}
> -
> -	if (free_space != NULL)
> -		*free_space = free - n;
> -	return n;
> -}
> -
> -/**
> - * @internal Dequeue several objects from the HTS ring.
> - *
> - * @param r
> - *   A pointer to the ring structure.
> - * @param obj_table
> - *   A pointer to a table of objects.
> - * @param esize
> - *   The size of ring element, in bytes. It must be a multiple of 4.
> - *   This must be the same value used while creating the ring. Otherwise
> - *   the results are undefined.
> - * @param n
> - *   The number of objects to pull from the ring.
> - * @param behavior
> - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
> - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
> - * @param available
> - *   returns the number of remaining ring entries after the dequeue has finished
> - * @return
> - *   - Actual number of objects dequeued.
> - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> -	uint32_t *available)
> -{
> -	uint32_t entries, head;
> -
> -	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head, &entries);
> -
> -	if (n != 0) {
> -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> -		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> -	}
> -
> -	if (available != NULL)
> -		*available = entries - n;
> -	return n;
> -}
> +#include <ring_hts_elem_pvt.h>
> 
>  /**
>   * Enqueue several objects on the HTS ring (multi-producers safe).
> diff --git a/lib/librte_ring/rte_ring_peek.h b/lib/librte_ring/rte_ring_peek.h
> index 45f707dc7..0dd402be4 100644
> --- a/lib/librte_ring/rte_ring_peek.h
> +++ b/lib/librte_ring/rte_ring_peek.h
> @@ -48,39 +48,7 @@
>  extern "C" {
>  #endif
> 
> -#include <rte_ring_peek_c11_mem.h>
> -
> -/**
> - * @internal This function moves prod head value.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> -		enum rte_ring_queue_behavior behavior, uint32_t *free_space)
> -{
> -	uint32_t free, head, next;
> -
> -	switch (r->prod.sync_type) {
> -	case RTE_RING_SYNC_ST:
> -		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> -			behavior, &head, &next, &free);
> -		break;
> -	case RTE_RING_SYNC_MT_HTS:
> -		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> -			&head, &free);
> -		break;
> -	case RTE_RING_SYNC_MT:
> -	case RTE_RING_SYNC_MT_RTS:
> -	default:
> -		/* unsupported mode, shouldn't be here */
> -		RTE_ASSERT(0);
> -		n = 0;
> -		free = 0;
> -	}
> -
> -	if (free_space != NULL)
> -		*free_space = free - n;
> -	return n;
> -}
> +#include <ring_peek_elem_pvt.h>
> 
>  /**
>   * Start to enqueue several objects on the ring.
> @@ -248,43 +216,6 @@ rte_ring_enqueue_finish(struct rte_ring *r, void * const *obj_table,
>  	rte_ring_enqueue_elem_finish(r, obj_table, sizeof(uintptr_t), n);
>  }
> 
> -/**
> - * @internal This function moves cons head value and copies up to *n*
> - * objects from the ring to the user provided obj_table.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> -	uint32_t *available)
> -{
> -	uint32_t avail, head, next;
> -
> -	switch (r->cons.sync_type) {
> -	case RTE_RING_SYNC_ST:
> -		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> -			behavior, &head, &next, &avail);
> -		break;
> -	case RTE_RING_SYNC_MT_HTS:
> -		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> -			&head, &avail);
> -		break;
> -	case RTE_RING_SYNC_MT:
> -	case RTE_RING_SYNC_MT_RTS:
> -	default:
> -		/* unsupported mode, shouldn't be here */
> -		RTE_ASSERT(0);
> -		n = 0;
> -		avail = 0;
> -	}
> -
> -	if (n != 0)
> -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> -
> -	if (available != NULL)
> -		*available = avail - n;
> -	return n;
> -}
> -
>  /**
>   * Start to dequeue several objects from the ring.
>   * Note that user has to call appropriate dequeue_finish()
> diff --git a/lib/librte_ring/rte_ring_peek_zc.h b/lib/librte_ring/rte_ring_peek_zc.h
> index cb3bbd067..bc8252a18 100644
> --- a/lib/librte_ring/rte_ring_peek_zc.h
> +++ b/lib/librte_ring/rte_ring_peek_zc.h
> @@ -72,7 +72,7 @@
>  extern "C" {
>  #endif
> 
> -#include <rte_ring_peek_c11_mem.h>
> +#include <ring_peek_elem_pvt.h>
> 
>  /**
>   * Ring zero-copy information structure.
> diff --git a/lib/librte_ring/rte_ring_rts.h b/lib/librte_ring/rte_ring_rts.h
> index afc12abe2..83d9903e2 100644
> --- a/lib/librte_ring/rte_ring_rts.h
> +++ b/lib/librte_ring/rte_ring_rts.h
> @@ -56,89 +56,7 @@
>  extern "C" {
>  #endif
> 
> -#include <rte_ring_rts_c11_mem.h>
> -
> -/**
> - * @internal Enqueue several objects on the RTS ring.
> - *
> - * @param r
> - *   A pointer to the ring structure.
> - * @param obj_table
> - *   A pointer to a table of objects.
> - * @param esize
> - *   The size of ring element, in bytes. It must be a multiple of 4.
> - *   This must be the same value used while creating the ring. Otherwise
> - *   the results are undefined.
> - * @param n
> - *   The number of objects to add in the ring from the obj_table.
> - * @param behavior
> - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
> - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
> - * @param free_space
> - *   returns the amount of space after the enqueue operation has finished
> - * @return
> - *   Actual number of objects enqueued.
> - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void *obj_table,
> -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> -	uint32_t *free_space)
> -{
> -	uint32_t free, head;
> -
> -	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> -
> -	if (n != 0) {
> -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> -		__rte_ring_rts_update_tail(&r->rts_prod);
> -	}
> -
> -	if (free_space != NULL)
> -		*free_space = free - n;
> -	return n;
> -}
> -
> -/**
> - * @internal Dequeue several objects from the RTS ring.
> - *
> - * @param r
> - *   A pointer to the ring structure.
> - * @param obj_table
> - *   A pointer to a table of objects.
> - * @param esize
> - *   The size of ring element, in bytes. It must be a multiple of 4.
> - *   This must be the same value used while creating the ring. Otherwise
> - *   the results are undefined.
> - * @param n
> - *   The number of objects to pull from the ring.
> - * @param behavior
> - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
> - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
> - * @param available
> - *   returns the number of remaining ring entries after the dequeue has finished
> - * @return
> - *   - Actual number of objects dequeued.
> - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> - */
> -static __rte_always_inline unsigned int
> -__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> -	uint32_t *available)
> -{
> -	uint32_t entries, head;
> -
> -	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head, &entries);
> -
> -	if (n != 0) {
> -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> -		__rte_ring_rts_update_tail(&r->rts_cons);
> -	}
> -
> -	if (available != NULL)
> -		*available = entries - n;
> -	return n;
> -}
> +#include <ring_rts_elem_pvt.h>
> 
>  /**
>   * Enqueue several objects on the RTS ring (multi-producers safe).
> --
> 2.17.1
Feifei Wang Jan. 24, 2021, 12:12 p.m. UTC | #2
Hi, Konstantin

> -----邮件原件-----
> 发件人: Ananyev, Konstantin <konstantin.ananyev@intel.com>
> 发送时间: 2021年1月22日 21:09
> 收件人: Feifei Wang <Feifei.Wang2@arm.com>; Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>
> 抄送: dev@dpdk.org; nd <nd@arm.com>
> 主题: RE: [PATCH v1 3/3] ring: rename and refactor ring library
> 
> 
> > For legacy modes, rename ring_generic/c11 to ring_generic/c11_pvt.
> > Furthermore, add new file ring_elem_pvt.h which includes
> > ring_do_eq/deq and ring element copy/delete APIs.
> >
> > For other modes, rename xx_c11_mem to xx_elem_pvt. Move all private
> > APIs into these new header files.
> >
> > Suggested-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > ---
> >  lib/librte_ring/meson.build                   |  15 +-
> >  .../{rte_ring_c11_mem.h => ring_c11_pvt.h}    |   9 +-
> >  lib/librte_ring/ring_elem_pvt.h               | 385 ++++++++++++++++++
> >  ...{rte_ring_generic.h => ring_generic_pvt.h} |   6 +-
> >  ...ring_hts_c11_mem.h => ring_hts_elem_pvt.h} |  88 +++-
> > ...ng_peek_c11_mem.h => ring_peek_elem_pvt.h} |  75 +++-
> > ...ring_rts_c11_mem.h => ring_rts_elem_pvt.h} |  88 +++-
> >  lib/librte_ring/rte_ring_elem.h               | 374 +----------------
> >  lib/librte_ring/rte_ring_hts.h                |  84 +---
> >  lib/librte_ring/rte_ring_peek.h               |  71 +---
> >  lib/librte_ring/rte_ring_peek_zc.h            |   2 +-
> >  lib/librte_ring/rte_ring_rts.h                |  84 +---
> >  12 files changed, 646 insertions(+), 635 deletions(-)  rename
> > lib/librte_ring/{rte_ring_c11_mem.h => ring_c11_pvt.h} (96%)  create
> > mode 100644 lib/librte_ring/ring_elem_pvt.h  rename
> > lib/librte_ring/{rte_ring_generic.h => ring_generic_pvt.h} (98%)
> > rename lib/librte_ring/{rte_ring_hts_c11_mem.h => ring_hts_elem_pvt.h}
> > (60%)  rename lib/librte_ring/{rte_ring_peek_c11_mem.h =>
> > ring_peek_elem_pvt.h} (62%)  rename
> > lib/librte_ring/{rte_ring_rts_c11_mem.h => ring_rts_elem_pvt.h} (62%)
> >
> 
> Sorry, but I don't understand the purpose of that patch.
> As I remember by DPDK naming convention all installable headers should
> have 'rte_' prefix. Same for public defines (RTE_).
> Why to abandon it here?

This change refers to you and Honnappa's discussion about ring:
https://mails.dpdk.org/archives/dev/2020-May/166803.html

And it is to separate the external APIs that can be called by users, 
from internal APIs that cannot be called by users. 
The internal functions are included in the files with xx_pvt.h.

Best Regards
Feifei
> 
> > diff --git a/lib/librte_ring/meson.build b/lib/librte_ring/meson.build
> > index 36fdcb6a5..98eac5810 100644
> > --- a/lib/librte_ring/meson.build
> > +++ b/lib/librte_ring/meson.build
> > @@ -2,15 +2,16 @@
> >  # Copyright(c) 2017 Intel Corporation
> >
> >  sources = files('rte_ring.c')
> > -headers = files('rte_ring.h',
> > +headers = files('ring_c11_pvt.h',
> > +		'ring_elem_pvt.h',
> > +		'ring_generic_pvt.h',
> > +		'ring_hts_elem_pvt.h',
> > +		'ring_peek_elem_pvt.h',
> > +		'ring_rts_elem_pvt.h',
> > +		'rte_ring.h',
> >  		'rte_ring_core.h',
> >  		'rte_ring_elem.h',
> > -		'rte_ring_c11_mem.h',
> > -		'rte_ring_generic.h',
> >  		'rte_ring_hts.h',
> > -		'rte_ring_hts_c11_mem.h',
> >  		'rte_ring_peek.h',
> > -		'rte_ring_peek_c11_mem.h',
> >  		'rte_ring_peek_zc.h',
> > -		'rte_ring_rts.h',
> > -		'rte_ring_rts_c11_mem.h')
> > +		'rte_ring_rts.h')
> > diff --git a/lib/librte_ring/rte_ring_c11_mem.h
> > b/lib/librte_ring/ring_c11_pvt.h similarity index 96% rename from
> > lib/librte_ring/rte_ring_c11_mem.h
> > rename to lib/librte_ring/ring_c11_pvt.h index 7f5eba262..9f2f5318f
> > 100644
> > --- a/lib/librte_ring/rte_ring_c11_mem.h
> > +++ b/lib/librte_ring/ring_c11_pvt.h
> > @@ -7,8 +7,8 @@
> >   * Used as BSD-3 Licensed with permission from Kip Macy.
> >   */
> >
> > -#ifndef _RTE_RING_C11_MEM_H_
> > -#define _RTE_RING_C11_MEM_H_
> > +#ifndef _RING_C11_PVT_H_
> > +#define _RING_C11_PVT_H_
> >
> >  static __rte_always_inline void
> >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > old_val, @@ -69,9 +69,6 @@ __rte_ring_move_prod_head(struct rte_ring
> *r, unsigned int is_sp,
> >  		/* Ensure the head is read before tail */
> >  		__atomic_thread_fence(__ATOMIC_ACQUIRE);
> >
> > -		/* load-acquire synchronize with store-release of ht->tail
> > -		 * in update_tail.
> > -		 */
> >  		cons_tail = __atomic_load_n(&r->cons.tail,
> >  					__ATOMIC_ACQUIRE);
> >
> > @@ -178,4 +175,4 @@ __rte_ring_move_cons_head(struct rte_ring *r, int
> is_sc,
> >  	return n;
> >  }
> >
> > -#endif /* _RTE_RING_C11_MEM_H_ */
> > +#endif /* _RING_C11_PVT_H_ */
> > diff --git a/lib/librte_ring/ring_elem_pvt.h
> > b/lib/librte_ring/ring_elem_pvt.h new file mode 100644 index
> > 000000000..8003e5edc
> > --- /dev/null
> > +++ b/lib/librte_ring/ring_elem_pvt.h
> > @@ -0,0 +1,385 @@
> > +/* SPDX-License-Identifier: BSD-3-Clause
> > + *
> > + * Copyright (c) 2017,2018 HXT-semitech Corporation.
> > + * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
> > + * All rights reserved.
> > + * Derived from FreeBSD's bufring.h
> > + * Used as BSD-3 Licensed with permission from Kip Macy.
> > + */
> > +
> > +#ifndef _RING_ELEM_PVT_H_
> > +#define _RING_ELEM_PVT_H_
> > +
> > +static __rte_always_inline void
> > +__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> > +		uint32_t idx, const void *obj_table, uint32_t n) {
> > +	unsigned int i;
> > +	uint32_t *ring = (uint32_t *)&r[1];
> > +	const uint32_t *obj = (const uint32_t *)obj_table;
> > +	if (likely(idx + n < size)) {
> > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > +			ring[idx] = obj[i];
> > +			ring[idx + 1] = obj[i + 1];
> > +			ring[idx + 2] = obj[i + 2];
> > +			ring[idx + 3] = obj[i + 3];
> > +			ring[idx + 4] = obj[i + 4];
> > +			ring[idx + 5] = obj[i + 5];
> > +			ring[idx + 6] = obj[i + 6];
> > +			ring[idx + 7] = obj[i + 7];
> > +		}
> > +		switch (n & 0x7) {
> > +		case 7:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 6:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 5:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 4:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 3:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 2:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 1:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		}
> > +	} else {
> > +		for (i = 0; idx < size; i++, idx++)
> > +			ring[idx] = obj[i];
> > +		/* Start at the beginning */
> > +		for (idx = 0; i < n; i++, idx++)
> > +			ring[idx] = obj[i];
> > +	}
> > +}
> > +
> > +static __rte_always_inline void
> > +__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > +		const void *obj_table, uint32_t n)
> > +{
> > +	unsigned int i;
> > +	const uint32_t size = r->size;
> > +	uint32_t idx = prod_head & r->mask;
> > +	uint64_t *ring = (uint64_t *)&r[1];
> > +	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> *)obj_table;
> > +	if (likely(idx + n < size)) {
> > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > +			ring[idx] = obj[i];
> > +			ring[idx + 1] = obj[i + 1];
> > +			ring[idx + 2] = obj[i + 2];
> > +			ring[idx + 3] = obj[i + 3];
> > +		}
> > +		switch (n & 0x3) {
> > +		case 3:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 2:
> > +			ring[idx++] = obj[i++]; /* fallthrough */
> > +		case 1:
> > +			ring[idx++] = obj[i++];
> > +		}
> > +	} else {
> > +		for (i = 0; idx < size; i++, idx++)
> > +			ring[idx] = obj[i];
> > +		/* Start at the beginning */
> > +		for (idx = 0; i < n; i++, idx++)
> > +			ring[idx] = obj[i];
> > +	}
> > +}
> > +
> > +static __rte_always_inline void
> > +__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > +		const void *obj_table, uint32_t n)
> > +{
> > +	unsigned int i;
> > +	const uint32_t size = r->size;
> > +	uint32_t idx = prod_head & r->mask;
> > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > +	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > +	if (likely(idx + n < size)) {
> > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > +			memcpy((void *)(ring + idx),
> > +				(const void *)(obj + i), 32);
> > +		switch (n & 0x1) {
> > +		case 1:
> > +			memcpy((void *)(ring + idx),
> > +				(const void *)(obj + i), 16);
> > +		}
> > +	} else {
> > +		for (i = 0; idx < size; i++, idx++)
> > +			memcpy((void *)(ring + idx),
> > +				(const void *)(obj + i), 16);
> > +		/* Start at the beginning */
> > +		for (idx = 0; i < n; i++, idx++)
> > +			memcpy((void *)(ring + idx),
> > +				(const void *)(obj + i), 16);
> > +	}
> > +}
> > +
> > +/* the actual enqueue of elements on the ring.
> > + * Placed here since identical code needed in both
> > + * single and multi producer enqueue functions.
> > + */
> > +static __rte_always_inline void
> > +__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > +		const void *obj_table, uint32_t esize, uint32_t num) {
> > +	/* 8B and 16B copies implemented individually to retain
> > +	 * the current performance.
> > +	 */
> > +	if (esize == 8)
> > +		__rte_ring_enqueue_elems_64(r, prod_head, obj_table,
> num);
> > +	else if (esize == 16)
> > +		__rte_ring_enqueue_elems_128(r, prod_head, obj_table,
> num);
> > +	else {
> > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > +
> > +		/* Normalize to uint32_t */
> > +		scale = esize / sizeof(uint32_t);
> > +		nr_num = num * scale;
> > +		idx = prod_head & r->mask;
> > +		nr_idx = idx * scale;
> > +		nr_size = r->size * scale;
> > +		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > +				obj_table, nr_num);
> > +	}
> > +}
> > +
> > +static __rte_always_inline void
> > +__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> > +		uint32_t idx, void *obj_table, uint32_t n) {
> > +	unsigned int i;
> > +	uint32_t *ring = (uint32_t *)&r[1];
> > +	uint32_t *obj = (uint32_t *)obj_table;
> > +	if (likely(idx + n < size)) {
> > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > +			obj[i] = ring[idx];
> > +			obj[i + 1] = ring[idx + 1];
> > +			obj[i + 2] = ring[idx + 2];
> > +			obj[i + 3] = ring[idx + 3];
> > +			obj[i + 4] = ring[idx + 4];
> > +			obj[i + 5] = ring[idx + 5];
> > +			obj[i + 6] = ring[idx + 6];
> > +			obj[i + 7] = ring[idx + 7];
> > +		}
> > +		switch (n & 0x7) {
> > +		case 7:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 6:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 5:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 4:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 3:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 2:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 1:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		}
> > +	} else {
> > +		for (i = 0; idx < size; i++, idx++)
> > +			obj[i] = ring[idx];
> > +		/* Start at the beginning */
> > +		for (idx = 0; i < n; i++, idx++)
> > +			obj[i] = ring[idx];
> > +	}
> > +}
> > +
> > +static __rte_always_inline void
> > +__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > +		void *obj_table, uint32_t n)
> > +{
> > +	unsigned int i;
> > +	const uint32_t size = r->size;
> > +	uint32_t idx = prod_head & r->mask;
> > +	uint64_t *ring = (uint64_t *)&r[1];
> > +	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > +	if (likely(idx + n < size)) {
> > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > +			obj[i] = ring[idx];
> > +			obj[i + 1] = ring[idx + 1];
> > +			obj[i + 2] = ring[idx + 2];
> > +			obj[i + 3] = ring[idx + 3];
> > +		}
> > +		switch (n & 0x3) {
> > +		case 3:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 2:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		case 1:
> > +			obj[i++] = ring[idx++]; /* fallthrough */
> > +		}
> > +	} else {
> > +		for (i = 0; idx < size; i++, idx++)
> > +			obj[i] = ring[idx];
> > +		/* Start at the beginning */
> > +		for (idx = 0; i < n; i++, idx++)
> > +			obj[i] = ring[idx];
> > +	}
> > +}
> > +
> > +static __rte_always_inline void
> > +__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > +		void *obj_table, uint32_t n)
> > +{
> > +	unsigned int i;
> > +	const uint32_t size = r->size;
> > +	uint32_t idx = prod_head & r->mask;
> > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > +	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > +	if (likely(idx + n < size)) {
> > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > +			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> > +		switch (n & 0x1) {
> > +		case 1:
> > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > +		}
> > +	} else {
> > +		for (i = 0; idx < size; i++, idx++)
> > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > +		/* Start at the beginning */
> > +		for (idx = 0; i < n; i++, idx++)
> > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > +	}
> > +}
> > +
> > +/* the actual dequeue of elements from the ring.
> > + * Placed here since identical code needed in both
> > + * single and multi producer enqueue functions.
> > + */
> > +static __rte_always_inline void
> > +__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > +		void *obj_table, uint32_t esize, uint32_t num) {
> > +	/* 8B and 16B copies implemented individually to retain
> > +	 * the current performance.
> > +	 */
> > +	if (esize == 8)
> > +		__rte_ring_dequeue_elems_64(r, cons_head, obj_table,
> num);
> > +	else if (esize == 16)
> > +		__rte_ring_dequeue_elems_128(r, cons_head, obj_table,
> num);
> > +	else {
> > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > +
> > +		/* Normalize to uint32_t */
> > +		scale = esize / sizeof(uint32_t);
> > +		nr_num = num * scale;
> > +		idx = cons_head & r->mask;
> > +		nr_idx = idx * scale;
> > +		nr_size = r->size * scale;
> > +		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > +				obj_table, nr_num);
> > +	}
> > +}
> > +
> > +/* Between load and load. there might be cpu reorder in weak model
> > + * (powerpc/arm).
> > + * There are 2 choices for the users
> > + * 1.use rmb() memory barrier
> > + * 2.use one-direction load_acquire/store_release barrier
> > + * It depends on performance test results.
> > + */
> > +#ifdef RTE_USE_C11_MEM_MODEL
> > +#include "ring_c11_pvt.h"
> > +#else
> > +#include "ring_generic_pvt.h"
> > +#endif
> > +
> > +/**
> > + * @internal Enqueue several objects on the ring
> > + *
> > + * @param r
> > + *   A pointer to the ring structure.
> > + * @param obj_table
> > + *   A pointer to a table of objects.
> > + * @param esize
> > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > + *   This must be the same value used while creating the ring. Otherwise
> > + *   the results are undefined.
> > + * @param n
> > + *   The number of objects to add in the ring from the obj_table.
> > + * @param behavior
> > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> ring
> > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> from ring
> > + * @param is_sp
> > + *   Indicates whether to use single producer or multi-producer head
> update
> > + * @param free_space
> > + *   returns the amount of space after the enqueue operation has finished
> > + * @return
> > + *   Actual number of objects enqueued.
> > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> > +		unsigned int esize, unsigned int n,
> > +		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> > +		unsigned int *free_space)
> > +{
> > +	uint32_t prod_head, prod_next;
> > +	uint32_t free_entries;
> > +
> > +	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > +			&prod_head, &prod_next, &free_entries);
> > +	if (n == 0)
> > +		goto end;
> > +
> > +	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> > +
> > +	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> > +end:
> > +	if (free_space != NULL)
> > +		*free_space = free_entries - n;
> > +	return n;
> > +}
> > +
> > +/**
> > + * @internal Dequeue several objects from the ring
> > + *
> > + * @param r
> > + *   A pointer to the ring structure.
> > + * @param obj_table
> > + *   A pointer to a table of objects.
> > + * @param esize
> > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > + *   This must be the same value used while creating the ring. Otherwise
> > + *   the results are undefined.
> > + * @param n
> > + *   The number of objects to pull from the ring.
> > + * @param behavior
> > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> ring
> > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> from ring
> > + * @param is_sc
> > + *   Indicates whether to use single consumer or multi-consumer head
> update
> > + * @param available
> > + *   returns the number of remaining ring entries after the dequeue has
> finished
> > + * @return
> > + *   - Actual number of objects dequeued.
> > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > +		unsigned int esize, unsigned int n,
> > +		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> > +		unsigned int *available)
> > +{
> > +	uint32_t cons_head, cons_next;
> > +	uint32_t entries;
> > +
> > +	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > +			&cons_head, &cons_next, &entries);
> > +	if (n == 0)
> > +		goto end;
> > +
> > +	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> > +
> > +	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> > +
> > +end:
> > +	if (available != NULL)
> > +		*available = entries - n;
> > +	return n;
> > +}
> > +
> > +#endif /* _RING_ELEM_PVT_H_ */
> > diff --git a/lib/librte_ring/rte_ring_generic.h
> > b/lib/librte_ring/ring_generic_pvt.h
> > similarity index 98%
> > rename from lib/librte_ring/rte_ring_generic.h
> > rename to lib/librte_ring/ring_generic_pvt.h
> > index 37c62b8d6..fc46a27b2 100644
> > --- a/lib/librte_ring/rte_ring_generic.h
> > +++ b/lib/librte_ring/ring_generic_pvt.h
> > @@ -7,8 +7,8 @@
> >   * Used as BSD-3 Licensed with permission from Kip Macy.
> >   */
> >
> > -#ifndef _RTE_RING_GENERIC_H_
> > -#define _RTE_RING_GENERIC_H_
> > +#ifndef _RING_GENERIC_PVT_H_
> > +#define _RING_GENERIC_PVT_H_
> >
> >  static __rte_always_inline void
> >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > old_val, @@ -170,4 +170,4 @@ __rte_ring_move_cons_head(struct
> rte_ring *r, unsigned int is_sc,
> >  	return n;
> >  }
> >
> > -#endif /* _RTE_RING_GENERIC_H_ */
> > +#endif /* _RING_GENERIC_PVT_H_ */
> > diff --git a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > b/lib/librte_ring/ring_hts_elem_pvt.h
> > similarity index 60%
> > rename from lib/librte_ring/rte_ring_hts_c11_mem.h
> > rename to lib/librte_ring/ring_hts_elem_pvt.h
> > index 16e54b6ff..9268750b0 100644
> > --- a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > +++ b/lib/librte_ring/ring_hts_elem_pvt.h
> > @@ -7,8 +7,8 @@
> >   * Used as BSD-3 Licensed with permission from Kip Macy.
> >   */
> >
> > -#ifndef _RTE_RING_HTS_C11_MEM_H_
> > -#define _RTE_RING_HTS_C11_MEM_H_
> > +#ifndef _RING_HTS_ELEM_PVT_H_
> > +#define _RING_HTS_ELEM_PVT_H_
> >
> >  /**
> >   * @file rte_ring_hts_c11_mem.h
> > @@ -161,4 +161,86 @@ __rte_ring_hts_move_cons_head(struct rte_ring
> *r, unsigned int num,
> >  	return n;
> >  }
> >
> > -#endif /* _RTE_RING_HTS_C11_MEM_H_ */
> > +/**
> > + * @internal Enqueue several objects on the HTS ring.
> > + *
> > + * @param r
> > + *   A pointer to the ring structure.
> > + * @param obj_table
> > + *   A pointer to a table of objects.
> > + * @param esize
> > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > + *   This must be the same value used while creating the ring. Otherwise
> > + *   the results are undefined.
> > + * @param n
> > + *   The number of objects to add in the ring from the obj_table.
> > + * @param behavior
> > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> ring
> > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> from ring
> > + * @param free_space
> > + *   returns the amount of space after the enqueue operation has finished
> > + * @return
> > + *   Actual number of objects enqueued.
> > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> *obj_table,
> > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > +	uint32_t *free_space)
> > +{
> > +	uint32_t free, head;
> > +
> > +	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> > +
> > +	if (n != 0) {
> > +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > +		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> > +	}
> > +
> > +	if (free_space != NULL)
> > +		*free_space = free - n;
> > +	return n;
> > +}
> > +
> > +/**
> > + * @internal Dequeue several objects from the HTS ring.
> > + *
> > + * @param r
> > + *   A pointer to the ring structure.
> > + * @param obj_table
> > + *   A pointer to a table of objects.
> > + * @param esize
> > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > + *   This must be the same value used while creating the ring. Otherwise
> > + *   the results are undefined.
> > + * @param n
> > + *   The number of objects to pull from the ring.
> > + * @param behavior
> > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> ring
> > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> from ring
> > + * @param available
> > + *   returns the number of remaining ring entries after the dequeue has
> finished
> > + * @return
> > + *   - Actual number of objects dequeued.
> > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > +	uint32_t *available)
> > +{
> > +	uint32_t entries, head;
> > +
> > +	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> &entries);
> > +
> > +	if (n != 0) {
> > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > +		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> > +	}
> > +
> > +	if (available != NULL)
> > +		*available = entries - n;
> > +	return n;
> > +}
> > +
> > +#endif /* _RING_HTS_ELEM_PVT_H_ */
> > diff --git a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > b/lib/librte_ring/ring_peek_elem_pvt.h
> > similarity index 62%
> > rename from lib/librte_ring/rte_ring_peek_c11_mem.h
> > rename to lib/librte_ring/ring_peek_elem_pvt.h
> > index 283c7e70b..1c57bcdd6 100644
> > --- a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > +++ b/lib/librte_ring/ring_peek_elem_pvt.h
> > @@ -7,8 +7,8 @@
> >   * Used as BSD-3 Licensed with permission from Kip Macy.
> >   */
> >
> > -#ifndef _RTE_RING_PEEK_C11_MEM_H_
> > -#define _RTE_RING_PEEK_C11_MEM_H_
> > +#ifndef _RING_PEEK_ELEM_PVT_H_
> > +#define _RING_PEEK_ELEM_PVT_H_
> >
> >  /**
> >   * @file rte_ring_peek_c11_mem.h
> > @@ -107,4 +107,73 @@ __rte_ring_hts_set_head_tail(struct
> rte_ring_hts_headtail *ht, uint32_t tail,
> >  	__atomic_store_n(&ht->ht.raw, p.raw, __ATOMIC_RELEASE);  }
> >
> > -#endif /* _RTE_RING_PEEK_C11_MEM_H_ */
> > +/**
> > + * @internal This function moves prod head value.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > +		enum rte_ring_queue_behavior behavior, uint32_t
> *free_space) {
> > +	uint32_t free, head, next;
> > +
> > +	switch (r->prod.sync_type) {
> > +	case RTE_RING_SYNC_ST:
> > +		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> > +			behavior, &head, &next, &free);
> > +		break;
> > +	case RTE_RING_SYNC_MT_HTS:
> > +		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > +			&head, &free);
> > +		break;
> > +	case RTE_RING_SYNC_MT:
> > +	case RTE_RING_SYNC_MT_RTS:
> > +	default:
> > +		/* unsupported mode, shouldn't be here */
> > +		RTE_ASSERT(0);
> > +		n = 0;
> > +		free = 0;
> > +	}
> > +
> > +	if (free_space != NULL)
> > +		*free_space = free - n;
> > +	return n;
> > +}
> > +
> > +/**
> > + * @internal This function moves cons head value and copies up to *n*
> > + * objects from the ring to the user provided obj_table.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > +	uint32_t *available)
> > +{
> > +	uint32_t avail, head, next;
> > +
> > +	switch (r->cons.sync_type) {
> > +	case RTE_RING_SYNC_ST:
> > +		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> > +			behavior, &head, &next, &avail);
> > +		break;
> > +	case RTE_RING_SYNC_MT_HTS:
> > +		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > +			&head, &avail);
> > +		break;
> > +	case RTE_RING_SYNC_MT:
> > +	case RTE_RING_SYNC_MT_RTS:
> > +	default:
> > +		/* unsupported mode, shouldn't be here */
> > +		RTE_ASSERT(0);
> > +		n = 0;
> > +		avail = 0;
> > +	}
> > +
> > +	if (n != 0)
> > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > +
> > +	if (available != NULL)
> > +		*available = avail - n;
> > +	return n;
> > +}
> > +
> > +#endif /* _RING_PEEK_ELEM_PVT_H_ */
> > diff --git a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > b/lib/librte_ring/ring_rts_elem_pvt.h
> > similarity index 62%
> > rename from lib/librte_ring/rte_ring_rts_c11_mem.h
> > rename to lib/librte_ring/ring_rts_elem_pvt.h
> > index 327f22796..cbcec73eb 100644
> > --- a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > +++ b/lib/librte_ring/ring_rts_elem_pvt.h
> > @@ -7,8 +7,8 @@
> >   * Used as BSD-3 Licensed with permission from Kip Macy.
> >   */
> >
> > -#ifndef _RTE_RING_RTS_C11_MEM_H_
> > -#define _RTE_RING_RTS_C11_MEM_H_
> > +#ifndef _RING_RTS_ELEM_PVT_H_
> > +#define _RING_RTS_ELEM_PVT_H_
> >
> >  /**
> >   * @file rte_ring_rts_c11_mem.h
> > @@ -176,4 +176,86 @@ __rte_ring_rts_move_cons_head(struct rte_ring
> *r, uint32_t num,
> >  	return n;
> >  }
> >
> > -#endif /* _RTE_RING_RTS_C11_MEM_H_ */
> > +/**
> > + * @internal Enqueue several objects on the RTS ring.
> > + *
> > + * @param r
> > + *   A pointer to the ring structure.
> > + * @param obj_table
> > + *   A pointer to a table of objects.
> > + * @param esize
> > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > + *   This must be the same value used while creating the ring. Otherwise
> > + *   the results are undefined.
> > + * @param n
> > + *   The number of objects to add in the ring from the obj_table.
> > + * @param behavior
> > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> ring
> > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> from ring
> > + * @param free_space
> > + *   returns the amount of space after the enqueue operation has finished
> > + * @return
> > + *   Actual number of objects enqueued.
> > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> *obj_table,
> > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > +	uint32_t *free_space)
> > +{
> > +	uint32_t free, head;
> > +
> > +	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> > +
> > +	if (n != 0) {
> > +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > +		__rte_ring_rts_update_tail(&r->rts_prod);
> > +	}
> > +
> > +	if (free_space != NULL)
> > +		*free_space = free - n;
> > +	return n;
> > +}
> > +
> > +/**
> > + * @internal Dequeue several objects from the RTS ring.
> > + *
> > + * @param r
> > + *   A pointer to the ring structure.
> > + * @param obj_table
> > + *   A pointer to a table of objects.
> > + * @param esize
> > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > + *   This must be the same value used while creating the ring. Otherwise
> > + *   the results are undefined.
> > + * @param n
> > + *   The number of objects to pull from the ring.
> > + * @param behavior
> > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> ring
> > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> from ring
> > + * @param available
> > + *   returns the number of remaining ring entries after the dequeue has
> finished
> > + * @return
> > + *   - Actual number of objects dequeued.
> > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > + */
> > +static __rte_always_inline unsigned int
> > +__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > +	uint32_t *available)
> > +{
> > +	uint32_t entries, head;
> > +
> > +	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> &entries);
> > +
> > +	if (n != 0) {
> > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > +		__rte_ring_rts_update_tail(&r->rts_cons);
> > +	}
> > +
> > +	if (available != NULL)
> > +		*available = entries - n;
> > +	return n;
> > +}
> > +
> > +#endif /* _RING_RTS_ELEM_PVT_H_ */
> > diff --git a/lib/librte_ring/rte_ring_elem.h
> > b/lib/librte_ring/rte_ring_elem.h index 57344d47d..119b5c0b6 100644
> > --- a/lib/librte_ring/rte_ring_elem.h
> > +++ b/lib/librte_ring/rte_ring_elem.h
> > @@ -21,6 +21,7 @@ extern "C" {
> >  #endif
> >
> >  #include <rte_ring_core.h>
> > +#include <ring_elem_pvt.h>
> >
> >  /**
> >   * Calculate the memory size needed for a ring with given element
> > size @@ -105,379 +106,6 @@ ssize_t
> rte_ring_get_memsize_elem(unsigned
> > int esize, unsigned int count);  struct rte_ring *rte_ring_create_elem(const
> char *name, unsigned int esize,
> >  			unsigned int count, int socket_id, unsigned int flags);
> >
> > -static __rte_always_inline void
> > -__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> > -		uint32_t idx, const void *obj_table, uint32_t n)
> > -{
> > -	unsigned int i;
> > -	uint32_t *ring = (uint32_t *)&r[1];
> > -	const uint32_t *obj = (const uint32_t *)obj_table;
> > -	if (likely(idx + n < size)) {
> > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > -			ring[idx] = obj[i];
> > -			ring[idx + 1] = obj[i + 1];
> > -			ring[idx + 2] = obj[i + 2];
> > -			ring[idx + 3] = obj[i + 3];
> > -			ring[idx + 4] = obj[i + 4];
> > -			ring[idx + 5] = obj[i + 5];
> > -			ring[idx + 6] = obj[i + 6];
> > -			ring[idx + 7] = obj[i + 7];
> > -		}
> > -		switch (n & 0x7) {
> > -		case 7:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 6:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 5:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 4:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 3:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 2:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 1:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		}
> > -	} else {
> > -		for (i = 0; idx < size; i++, idx++)
> > -			ring[idx] = obj[i];
> > -		/* Start at the beginning */
> > -		for (idx = 0; i < n; i++, idx++)
> > -			ring[idx] = obj[i];
> > -	}
> > -}
> > -
> > -static __rte_always_inline void
> > -__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > -		const void *obj_table, uint32_t n)
> > -{
> > -	unsigned int i;
> > -	const uint32_t size = r->size;
> > -	uint32_t idx = prod_head & r->mask;
> > -	uint64_t *ring = (uint64_t *)&r[1];
> > -	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> *)obj_table;
> > -	if (likely(idx + n < size)) {
> > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > -			ring[idx] = obj[i];
> > -			ring[idx + 1] = obj[i + 1];
> > -			ring[idx + 2] = obj[i + 2];
> > -			ring[idx + 3] = obj[i + 3];
> > -		}
> > -		switch (n & 0x3) {
> > -		case 3:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 2:
> > -			ring[idx++] = obj[i++]; /* fallthrough */
> > -		case 1:
> > -			ring[idx++] = obj[i++];
> > -		}
> > -	} else {
> > -		for (i = 0; idx < size; i++, idx++)
> > -			ring[idx] = obj[i];
> > -		/* Start at the beginning */
> > -		for (idx = 0; i < n; i++, idx++)
> > -			ring[idx] = obj[i];
> > -	}
> > -}
> > -
> > -static __rte_always_inline void
> > -__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > -		const void *obj_table, uint32_t n)
> > -{
> > -	unsigned int i;
> > -	const uint32_t size = r->size;
> > -	uint32_t idx = prod_head & r->mask;
> > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > -	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > -	if (likely(idx + n < size)) {
> > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > -			memcpy((void *)(ring + idx),
> > -				(const void *)(obj + i), 32);
> > -		switch (n & 0x1) {
> > -		case 1:
> > -			memcpy((void *)(ring + idx),
> > -				(const void *)(obj + i), 16);
> > -		}
> > -	} else {
> > -		for (i = 0; idx < size; i++, idx++)
> > -			memcpy((void *)(ring + idx),
> > -				(const void *)(obj + i), 16);
> > -		/* Start at the beginning */
> > -		for (idx = 0; i < n; i++, idx++)
> > -			memcpy((void *)(ring + idx),
> > -				(const void *)(obj + i), 16);
> > -	}
> > -}
> > -
> > -/* the actual enqueue of elements on the ring.
> > - * Placed here since identical code needed in both
> > - * single and multi producer enqueue functions.
> > - */
> > -static __rte_always_inline void
> > -__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > -		const void *obj_table, uint32_t esize, uint32_t num)
> > -{
> > -	/* 8B and 16B copies implemented individually to retain
> > -	 * the current performance.
> > -	 */
> > -	if (esize == 8)
> > -		__rte_ring_enqueue_elems_64(r, prod_head, obj_table,
> num);
> > -	else if (esize == 16)
> > -		__rte_ring_enqueue_elems_128(r, prod_head, obj_table,
> num);
> > -	else {
> > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > -
> > -		/* Normalize to uint32_t */
> > -		scale = esize / sizeof(uint32_t);
> > -		nr_num = num * scale;
> > -		idx = prod_head & r->mask;
> > -		nr_idx = idx * scale;
> > -		nr_size = r->size * scale;
> > -		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > -				obj_table, nr_num);
> > -	}
> > -}
> > -
> > -static __rte_always_inline void
> > -__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> > -		uint32_t idx, void *obj_table, uint32_t n)
> > -{
> > -	unsigned int i;
> > -	uint32_t *ring = (uint32_t *)&r[1];
> > -	uint32_t *obj = (uint32_t *)obj_table;
> > -	if (likely(idx + n < size)) {
> > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > -			obj[i] = ring[idx];
> > -			obj[i + 1] = ring[idx + 1];
> > -			obj[i + 2] = ring[idx + 2];
> > -			obj[i + 3] = ring[idx + 3];
> > -			obj[i + 4] = ring[idx + 4];
> > -			obj[i + 5] = ring[idx + 5];
> > -			obj[i + 6] = ring[idx + 6];
> > -			obj[i + 7] = ring[idx + 7];
> > -		}
> > -		switch (n & 0x7) {
> > -		case 7:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 6:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 5:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 4:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 3:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 2:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 1:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		}
> > -	} else {
> > -		for (i = 0; idx < size; i++, idx++)
> > -			obj[i] = ring[idx];
> > -		/* Start at the beginning */
> > -		for (idx = 0; i < n; i++, idx++)
> > -			obj[i] = ring[idx];
> > -	}
> > -}
> > -
> > -static __rte_always_inline void
> > -__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > -		void *obj_table, uint32_t n)
> > -{
> > -	unsigned int i;
> > -	const uint32_t size = r->size;
> > -	uint32_t idx = prod_head & r->mask;
> > -	uint64_t *ring = (uint64_t *)&r[1];
> > -	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > -	if (likely(idx + n < size)) {
> > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > -			obj[i] = ring[idx];
> > -			obj[i + 1] = ring[idx + 1];
> > -			obj[i + 2] = ring[idx + 2];
> > -			obj[i + 3] = ring[idx + 3];
> > -		}
> > -		switch (n & 0x3) {
> > -		case 3:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 2:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		case 1:
> > -			obj[i++] = ring[idx++]; /* fallthrough */
> > -		}
> > -	} else {
> > -		for (i = 0; idx < size; i++, idx++)
> > -			obj[i] = ring[idx];
> > -		/* Start at the beginning */
> > -		for (idx = 0; i < n; i++, idx++)
> > -			obj[i] = ring[idx];
> > -	}
> > -}
> > -
> > -static __rte_always_inline void
> > -__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > -		void *obj_table, uint32_t n)
> > -{
> > -	unsigned int i;
> > -	const uint32_t size = r->size;
> > -	uint32_t idx = prod_head & r->mask;
> > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > -	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > -	if (likely(idx + n < size)) {
> > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > -			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> > -		switch (n & 0x1) {
> > -		case 1:
> > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > -		}
> > -	} else {
> > -		for (i = 0; idx < size; i++, idx++)
> > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > -		/* Start at the beginning */
> > -		for (idx = 0; i < n; i++, idx++)
> > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > -	}
> > -}
> > -
> > -/* the actual dequeue of elements from the ring.
> > - * Placed here since identical code needed in both
> > - * single and multi producer enqueue functions.
> > - */
> > -static __rte_always_inline void
> > -__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > -		void *obj_table, uint32_t esize, uint32_t num)
> > -{
> > -	/* 8B and 16B copies implemented individually to retain
> > -	 * the current performance.
> > -	 */
> > -	if (esize == 8)
> > -		__rte_ring_dequeue_elems_64(r, cons_head, obj_table,
> num);
> > -	else if (esize == 16)
> > -		__rte_ring_dequeue_elems_128(r, cons_head, obj_table,
> num);
> > -	else {
> > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > -
> > -		/* Normalize to uint32_t */
> > -		scale = esize / sizeof(uint32_t);
> > -		nr_num = num * scale;
> > -		idx = cons_head & r->mask;
> > -		nr_idx = idx * scale;
> > -		nr_size = r->size * scale;
> > -		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > -				obj_table, nr_num);
> > -	}
> > -}
> > -
> > -/* Between load and load. there might be cpu reorder in weak model
> > - * (powerpc/arm).
> > - * There are 2 choices for the users
> > - * 1.use rmb() memory barrier
> > - * 2.use one-direction load_acquire/store_release barrier
> > - * It depends on performance test results.
> > - * By default, move common functions to rte_ring_generic.h
> > - */
> > -#ifdef RTE_USE_C11_MEM_MODEL
> > -#include "rte_ring_c11_mem.h"
> > -#else
> > -#include "rte_ring_generic.h"
> > -#endif
> > -
> > -/**
> > - * @internal Enqueue several objects on the ring
> > - *
> > - * @param r
> > - *   A pointer to the ring structure.
> > - * @param obj_table
> > - *   A pointer to a table of objects.
> > - * @param esize
> > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > - *   This must be the same value used while creating the ring. Otherwise
> > - *   the results are undefined.
> > - * @param n
> > - *   The number of objects to add in the ring from the obj_table.
> > - * @param behavior
> > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> ring
> > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> from ring
> > - * @param is_sp
> > - *   Indicates whether to use single producer or multi-producer head
> update
> > - * @param free_space
> > - *   returns the amount of space after the enqueue operation has finished
> > - * @return
> > - *   Actual number of objects enqueued.
> > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> > -		unsigned int esize, unsigned int n,
> > -		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> > -		unsigned int *free_space)
> > -{
> > -	uint32_t prod_head, prod_next;
> > -	uint32_t free_entries;
> > -
> > -	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > -			&prod_head, &prod_next, &free_entries);
> > -	if (n == 0)
> > -		goto end;
> > -
> > -	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> > -
> > -	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> > -end:
> > -	if (free_space != NULL)
> > -		*free_space = free_entries - n;
> > -	return n;
> > -}
> > -
> > -/**
> > - * @internal Dequeue several objects from the ring
> > - *
> > - * @param r
> > - *   A pointer to the ring structure.
> > - * @param obj_table
> > - *   A pointer to a table of objects.
> > - * @param esize
> > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > - *   This must be the same value used while creating the ring. Otherwise
> > - *   the results are undefined.
> > - * @param n
> > - *   The number of objects to pull from the ring.
> > - * @param behavior
> > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> ring
> > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> from ring
> > - * @param is_sc
> > - *   Indicates whether to use single consumer or multi-consumer head
> update
> > - * @param available
> > - *   returns the number of remaining ring entries after the dequeue has
> finished
> > - * @return
> > - *   - Actual number of objects dequeued.
> > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > -		unsigned int esize, unsigned int n,
> > -		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> > -		unsigned int *available)
> > -{
> > -	uint32_t cons_head, cons_next;
> > -	uint32_t entries;
> > -
> > -	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > -			&cons_head, &cons_next, &entries);
> > -	if (n == 0)
> > -		goto end;
> > -
> > -	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> > -
> > -	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> > -
> > -end:
> > -	if (available != NULL)
> > -		*available = entries - n;
> > -	return n;
> > -}
> > -
> >  /**
> >   * Enqueue several objects on the ring (multi-producers safe).
> >   *
> > diff --git a/lib/librte_ring/rte_ring_hts.h
> > b/lib/librte_ring/rte_ring_hts.h index 359b15771..bdbdafc9f 100644
> > --- a/lib/librte_ring/rte_ring_hts.h
> > +++ b/lib/librte_ring/rte_ring_hts.h
> > @@ -29,89 +29,7 @@
> >  extern "C" {
> >  #endif
> >
> > -#include <rte_ring_hts_c11_mem.h>
> > -
> > -/**
> > - * @internal Enqueue several objects on the HTS ring.
> > - *
> > - * @param r
> > - *   A pointer to the ring structure.
> > - * @param obj_table
> > - *   A pointer to a table of objects.
> > - * @param esize
> > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > - *   This must be the same value used while creating the ring. Otherwise
> > - *   the results are undefined.
> > - * @param n
> > - *   The number of objects to add in the ring from the obj_table.
> > - * @param behavior
> > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> ring
> > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> from ring
> > - * @param free_space
> > - *   returns the amount of space after the enqueue operation has finished
> > - * @return
> > - *   Actual number of objects enqueued.
> > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> *obj_table,
> > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > -	uint32_t *free_space)
> > -{
> > -	uint32_t free, head;
> > -
> > -	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> > -
> > -	if (n != 0) {
> > -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > -		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> > -	}
> > -
> > -	if (free_space != NULL)
> > -		*free_space = free - n;
> > -	return n;
> > -}
> > -
> > -/**
> > - * @internal Dequeue several objects from the HTS ring.
> > - *
> > - * @param r
> > - *   A pointer to the ring structure.
> > - * @param obj_table
> > - *   A pointer to a table of objects.
> > - * @param esize
> > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > - *   This must be the same value used while creating the ring. Otherwise
> > - *   the results are undefined.
> > - * @param n
> > - *   The number of objects to pull from the ring.
> > - * @param behavior
> > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> ring
> > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> from ring
> > - * @param available
> > - *   returns the number of remaining ring entries after the dequeue has
> finished
> > - * @return
> > - *   - Actual number of objects dequeued.
> > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > -	uint32_t *available)
> > -{
> > -	uint32_t entries, head;
> > -
> > -	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> &entries);
> > -
> > -	if (n != 0) {
> > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > -		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> > -	}
> > -
> > -	if (available != NULL)
> > -		*available = entries - n;
> > -	return n;
> > -}
> > +#include <ring_hts_elem_pvt.h>
> >
> >  /**
> >   * Enqueue several objects on the HTS ring (multi-producers safe).
> > diff --git a/lib/librte_ring/rte_ring_peek.h
> > b/lib/librte_ring/rte_ring_peek.h index 45f707dc7..0dd402be4 100644
> > --- a/lib/librte_ring/rte_ring_peek.h
> > +++ b/lib/librte_ring/rte_ring_peek.h
> > @@ -48,39 +48,7 @@
> >  extern "C" {
> >  #endif
> >
> > -#include <rte_ring_peek_c11_mem.h>
> > -
> > -/**
> > - * @internal This function moves prod head value.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > -		enum rte_ring_queue_behavior behavior, uint32_t
> *free_space)
> > -{
> > -	uint32_t free, head, next;
> > -
> > -	switch (r->prod.sync_type) {
> > -	case RTE_RING_SYNC_ST:
> > -		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> > -			behavior, &head, &next, &free);
> > -		break;
> > -	case RTE_RING_SYNC_MT_HTS:
> > -		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > -			&head, &free);
> > -		break;
> > -	case RTE_RING_SYNC_MT:
> > -	case RTE_RING_SYNC_MT_RTS:
> > -	default:
> > -		/* unsupported mode, shouldn't be here */
> > -		RTE_ASSERT(0);
> > -		n = 0;
> > -		free = 0;
> > -	}
> > -
> > -	if (free_space != NULL)
> > -		*free_space = free - n;
> > -	return n;
> > -}
> > +#include <ring_peek_elem_pvt.h>
> >
> >  /**
> >   * Start to enqueue several objects on the ring.
> > @@ -248,43 +216,6 @@ rte_ring_enqueue_finish(struct rte_ring *r, void *
> const *obj_table,
> >  	rte_ring_enqueue_elem_finish(r, obj_table, sizeof(uintptr_t), n);  }
> >
> > -/**
> > - * @internal This function moves cons head value and copies up to *n*
> > - * objects from the ring to the user provided obj_table.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > -	uint32_t *available)
> > -{
> > -	uint32_t avail, head, next;
> > -
> > -	switch (r->cons.sync_type) {
> > -	case RTE_RING_SYNC_ST:
> > -		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> > -			behavior, &head, &next, &avail);
> > -		break;
> > -	case RTE_RING_SYNC_MT_HTS:
> > -		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > -			&head, &avail);
> > -		break;
> > -	case RTE_RING_SYNC_MT:
> > -	case RTE_RING_SYNC_MT_RTS:
> > -	default:
> > -		/* unsupported mode, shouldn't be here */
> > -		RTE_ASSERT(0);
> > -		n = 0;
> > -		avail = 0;
> > -	}
> > -
> > -	if (n != 0)
> > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > -
> > -	if (available != NULL)
> > -		*available = avail - n;
> > -	return n;
> > -}
> > -
> >  /**
> >   * Start to dequeue several objects from the ring.
> >   * Note that user has to call appropriate dequeue_finish() diff --git
> > a/lib/librte_ring/rte_ring_peek_zc.h
> > b/lib/librte_ring/rte_ring_peek_zc.h
> > index cb3bbd067..bc8252a18 100644
> > --- a/lib/librte_ring/rte_ring_peek_zc.h
> > +++ b/lib/librte_ring/rte_ring_peek_zc.h
> > @@ -72,7 +72,7 @@
> >  extern "C" {
> >  #endif
> >
> > -#include <rte_ring_peek_c11_mem.h>
> > +#include <ring_peek_elem_pvt.h>
> >
> >  /**
> >   * Ring zero-copy information structure.
> > diff --git a/lib/librte_ring/rte_ring_rts.h
> > b/lib/librte_ring/rte_ring_rts.h index afc12abe2..83d9903e2 100644
> > --- a/lib/librte_ring/rte_ring_rts.h
> > +++ b/lib/librte_ring/rte_ring_rts.h
> > @@ -56,89 +56,7 @@
> >  extern "C" {
> >  #endif
> >
> > -#include <rte_ring_rts_c11_mem.h>
> > -
> > -/**
> > - * @internal Enqueue several objects on the RTS ring.
> > - *
> > - * @param r
> > - *   A pointer to the ring structure.
> > - * @param obj_table
> > - *   A pointer to a table of objects.
> > - * @param esize
> > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > - *   This must be the same value used while creating the ring. Otherwise
> > - *   the results are undefined.
> > - * @param n
> > - *   The number of objects to add in the ring from the obj_table.
> > - * @param behavior
> > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> ring
> > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> from ring
> > - * @param free_space
> > - *   returns the amount of space after the enqueue operation has finished
> > - * @return
> > - *   Actual number of objects enqueued.
> > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> *obj_table,
> > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > -	uint32_t *free_space)
> > -{
> > -	uint32_t free, head;
> > -
> > -	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> > -
> > -	if (n != 0) {
> > -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > -		__rte_ring_rts_update_tail(&r->rts_prod);
> > -	}
> > -
> > -	if (free_space != NULL)
> > -		*free_space = free - n;
> > -	return n;
> > -}
> > -
> > -/**
> > - * @internal Dequeue several objects from the RTS ring.
> > - *
> > - * @param r
> > - *   A pointer to the ring structure.
> > - * @param obj_table
> > - *   A pointer to a table of objects.
> > - * @param esize
> > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > - *   This must be the same value used while creating the ring. Otherwise
> > - *   the results are undefined.
> > - * @param n
> > - *   The number of objects to pull from the ring.
> > - * @param behavior
> > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> ring
> > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> from ring
> > - * @param available
> > - *   returns the number of remaining ring entries after the dequeue has
> finished
> > - * @return
> > - *   - Actual number of objects dequeued.
> > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > - */
> > -static __rte_always_inline unsigned int
> > -__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > -	uint32_t *available)
> > -{
> > -	uint32_t entries, head;
> > -
> > -	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> &entries);
> > -
> > -	if (n != 0) {
> > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > -		__rte_ring_rts_update_tail(&r->rts_cons);
> > -	}
> > -
> > -	if (available != NULL)
> > -		*available = entries - n;
> > -	return n;
> > -}
> > +#include <ring_rts_elem_pvt.h>
> >
> >  /**
> >   * Enqueue several objects on the RTS ring (multi-producers safe).
> > --
> > 2.17.1
Konstantin Ananyev Jan. 25, 2021, 10:17 a.m. UTC | #3
Hi Feifei,

> > > For legacy modes, rename ring_generic/c11 to ring_generic/c11_pvt.
> > > Furthermore, add new file ring_elem_pvt.h which includes
> > > ring_do_eq/deq and ring element copy/delete APIs.
> > >
> > > For other modes, rename xx_c11_mem to xx_elem_pvt. Move all private
> > > APIs into these new header files.
> > >
> > > Suggested-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > > Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > ---
> > >  lib/librte_ring/meson.build                   |  15 +-
> > >  .../{rte_ring_c11_mem.h => ring_c11_pvt.h}    |   9 +-
> > >  lib/librte_ring/ring_elem_pvt.h               | 385 ++++++++++++++++++
> > >  ...{rte_ring_generic.h => ring_generic_pvt.h} |   6 +-
> > >  ...ring_hts_c11_mem.h => ring_hts_elem_pvt.h} |  88 +++-
> > > ...ng_peek_c11_mem.h => ring_peek_elem_pvt.h} |  75 +++-
> > > ...ring_rts_c11_mem.h => ring_rts_elem_pvt.h} |  88 +++-
> > >  lib/librte_ring/rte_ring_elem.h               | 374 +----------------
> > >  lib/librte_ring/rte_ring_hts.h                |  84 +---
> > >  lib/librte_ring/rte_ring_peek.h               |  71 +---
> > >  lib/librte_ring/rte_ring_peek_zc.h            |   2 +-
> > >  lib/librte_ring/rte_ring_rts.h                |  84 +---
> > >  12 files changed, 646 insertions(+), 635 deletions(-)  rename
> > > lib/librte_ring/{rte_ring_c11_mem.h => ring_c11_pvt.h} (96%)  create
> > > mode 100644 lib/librte_ring/ring_elem_pvt.h  rename
> > > lib/librte_ring/{rte_ring_generic.h => ring_generic_pvt.h} (98%)
> > > rename lib/librte_ring/{rte_ring_hts_c11_mem.h => ring_hts_elem_pvt.h}
> > > (60%)  rename lib/librte_ring/{rte_ring_peek_c11_mem.h =>
> > > ring_peek_elem_pvt.h} (62%)  rename
> > > lib/librte_ring/{rte_ring_rts_c11_mem.h => ring_rts_elem_pvt.h} (62%)
> > >
> >
> > Sorry, but I don't understand the purpose of that patch.
> > As I remember by DPDK naming convention all installable headers should
> > have 'rte_' prefix. Same for public defines (RTE_).
> > Why to abandon it here?
> 
> This change refers to you and Honnappa's discussion about ring:
> https://mails.dpdk.org/archives/dev/2020-May/166803.html
> 
> And it is to separate the external APIs that can be called by users,
> from internal APIs that cannot be called by users.
> The internal functions are included in the files with xx_pvt.h.

Even these xx_pvt.h files contain internal API and not supposed to be included directly,
they have to be installed into public dir (<dpdk-install-dir/include).
So I think we need to keep DPDK public prefixes for them (and inside them):
rte_xx_pvt.h (_RTE_). 

Konstantin

> 
> Best Regards
> Feifei
> >
> > > diff --git a/lib/librte_ring/meson.build b/lib/librte_ring/meson.build
> > > index 36fdcb6a5..98eac5810 100644
> > > --- a/lib/librte_ring/meson.build
> > > +++ b/lib/librte_ring/meson.build
> > > @@ -2,15 +2,16 @@
> > >  # Copyright(c) 2017 Intel Corporation
> > >
> > >  sources = files('rte_ring.c')
> > > -headers = files('rte_ring.h',
> > > +headers = files('ring_c11_pvt.h',
> > > +		'ring_elem_pvt.h',
> > > +		'ring_generic_pvt.h',
> > > +		'ring_hts_elem_pvt.h',
> > > +		'ring_peek_elem_pvt.h',
> > > +		'ring_rts_elem_pvt.h',
> > > +		'rte_ring.h',
> > >  		'rte_ring_core.h',
> > >  		'rte_ring_elem.h',
> > > -		'rte_ring_c11_mem.h',
> > > -		'rte_ring_generic.h',
> > >  		'rte_ring_hts.h',
> > > -		'rte_ring_hts_c11_mem.h',
> > >  		'rte_ring_peek.h',
> > > -		'rte_ring_peek_c11_mem.h',
> > >  		'rte_ring_peek_zc.h',
> > > -		'rte_ring_rts.h',
> > > -		'rte_ring_rts_c11_mem.h')
> > > +		'rte_ring_rts.h')
> > > diff --git a/lib/librte_ring/rte_ring_c11_mem.h
> > > b/lib/librte_ring/ring_c11_pvt.h similarity index 96% rename from
> > > lib/librte_ring/rte_ring_c11_mem.h
> > > rename to lib/librte_ring/ring_c11_pvt.h index 7f5eba262..9f2f5318f
> > > 100644
> > > --- a/lib/librte_ring/rte_ring_c11_mem.h
> > > +++ b/lib/librte_ring/ring_c11_pvt.h
> > > @@ -7,8 +7,8 @@
> > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > >   */
> > >
> > > -#ifndef _RTE_RING_C11_MEM_H_
> > > -#define _RTE_RING_C11_MEM_H_
> > > +#ifndef _RING_C11_PVT_H_
> > > +#define _RING_C11_PVT_H_
> > >
> > >  static __rte_always_inline void
> > >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > > old_val, @@ -69,9 +69,6 @@ __rte_ring_move_prod_head(struct rte_ring
> > *r, unsigned int is_sp,
> > >  		/* Ensure the head is read before tail */
> > >  		__atomic_thread_fence(__ATOMIC_ACQUIRE);
> > >
> > > -		/* load-acquire synchronize with store-release of ht->tail
> > > -		 * in update_tail.
> > > -		 */
> > >  		cons_tail = __atomic_load_n(&r->cons.tail,
> > >  					__ATOMIC_ACQUIRE);
> > >
> > > @@ -178,4 +175,4 @@ __rte_ring_move_cons_head(struct rte_ring *r, int
> > is_sc,
> > >  	return n;
> > >  }
> > >
> > > -#endif /* _RTE_RING_C11_MEM_H_ */
> > > +#endif /* _RING_C11_PVT_H_ */
> > > diff --git a/lib/librte_ring/ring_elem_pvt.h
> > > b/lib/librte_ring/ring_elem_pvt.h new file mode 100644 index
> > > 000000000..8003e5edc
> > > --- /dev/null
> > > +++ b/lib/librte_ring/ring_elem_pvt.h
> > > @@ -0,0 +1,385 @@
> > > +/* SPDX-License-Identifier: BSD-3-Clause
> > > + *
> > > + * Copyright (c) 2017,2018 HXT-semitech Corporation.
> > > + * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
> > > + * All rights reserved.
> > > + * Derived from FreeBSD's bufring.h
> > > + * Used as BSD-3 Licensed with permission from Kip Macy.
> > > + */
> > > +
> > > +#ifndef _RING_ELEM_PVT_H_
> > > +#define _RING_ELEM_PVT_H_
> > > +
> > > +static __rte_always_inline void
> > > +__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> > > +		uint32_t idx, const void *obj_table, uint32_t n) {
> > > +	unsigned int i;
> > > +	uint32_t *ring = (uint32_t *)&r[1];
> > > +	const uint32_t *obj = (const uint32_t *)obj_table;
> > > +	if (likely(idx + n < size)) {
> > > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > +			ring[idx] = obj[i];
> > > +			ring[idx + 1] = obj[i + 1];
> > > +			ring[idx + 2] = obj[i + 2];
> > > +			ring[idx + 3] = obj[i + 3];
> > > +			ring[idx + 4] = obj[i + 4];
> > > +			ring[idx + 5] = obj[i + 5];
> > > +			ring[idx + 6] = obj[i + 6];
> > > +			ring[idx + 7] = obj[i + 7];
> > > +		}
> > > +		switch (n & 0x7) {
> > > +		case 7:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 6:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 5:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 4:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 3:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 2:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 1:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		}
> > > +	} else {
> > > +		for (i = 0; idx < size; i++, idx++)
> > > +			ring[idx] = obj[i];
> > > +		/* Start at the beginning */
> > > +		for (idx = 0; i < n; i++, idx++)
> > > +			ring[idx] = obj[i];
> > > +	}
> > > +}
> > > +
> > > +static __rte_always_inline void
> > > +__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > +		const void *obj_table, uint32_t n)
> > > +{
> > > +	unsigned int i;
> > > +	const uint32_t size = r->size;
> > > +	uint32_t idx = prod_head & r->mask;
> > > +	uint64_t *ring = (uint64_t *)&r[1];
> > > +	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> > *)obj_table;
> > > +	if (likely(idx + n < size)) {
> > > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > +			ring[idx] = obj[i];
> > > +			ring[idx + 1] = obj[i + 1];
> > > +			ring[idx + 2] = obj[i + 2];
> > > +			ring[idx + 3] = obj[i + 3];
> > > +		}
> > > +		switch (n & 0x3) {
> > > +		case 3:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 2:
> > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > +		case 1:
> > > +			ring[idx++] = obj[i++];
> > > +		}
> > > +	} else {
> > > +		for (i = 0; idx < size; i++, idx++)
> > > +			ring[idx] = obj[i];
> > > +		/* Start at the beginning */
> > > +		for (idx = 0; i < n; i++, idx++)
> > > +			ring[idx] = obj[i];
> > > +	}
> > > +}
> > > +
> > > +static __rte_always_inline void
> > > +__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > +		const void *obj_table, uint32_t n)
> > > +{
> > > +	unsigned int i;
> > > +	const uint32_t size = r->size;
> > > +	uint32_t idx = prod_head & r->mask;
> > > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > +	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > > +	if (likely(idx + n < size)) {
> > > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > +			memcpy((void *)(ring + idx),
> > > +				(const void *)(obj + i), 32);
> > > +		switch (n & 0x1) {
> > > +		case 1:
> > > +			memcpy((void *)(ring + idx),
> > > +				(const void *)(obj + i), 16);
> > > +		}
> > > +	} else {
> > > +		for (i = 0; idx < size; i++, idx++)
> > > +			memcpy((void *)(ring + idx),
> > > +				(const void *)(obj + i), 16);
> > > +		/* Start at the beginning */
> > > +		for (idx = 0; i < n; i++, idx++)
> > > +			memcpy((void *)(ring + idx),
> > > +				(const void *)(obj + i), 16);
> > > +	}
> > > +}
> > > +
> > > +/* the actual enqueue of elements on the ring.
> > > + * Placed here since identical code needed in both
> > > + * single and multi producer enqueue functions.
> > > + */
> > > +static __rte_always_inline void
> > > +__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > > +		const void *obj_table, uint32_t esize, uint32_t num) {
> > > +	/* 8B and 16B copies implemented individually to retain
> > > +	 * the current performance.
> > > +	 */
> > > +	if (esize == 8)
> > > +		__rte_ring_enqueue_elems_64(r, prod_head, obj_table,
> > num);
> > > +	else if (esize == 16)
> > > +		__rte_ring_enqueue_elems_128(r, prod_head, obj_table,
> > num);
> > > +	else {
> > > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > +
> > > +		/* Normalize to uint32_t */
> > > +		scale = esize / sizeof(uint32_t);
> > > +		nr_num = num * scale;
> > > +		idx = prod_head & r->mask;
> > > +		nr_idx = idx * scale;
> > > +		nr_size = r->size * scale;
> > > +		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > > +				obj_table, nr_num);
> > > +	}
> > > +}
> > > +
> > > +static __rte_always_inline void
> > > +__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> > > +		uint32_t idx, void *obj_table, uint32_t n) {
> > > +	unsigned int i;
> > > +	uint32_t *ring = (uint32_t *)&r[1];
> > > +	uint32_t *obj = (uint32_t *)obj_table;
> > > +	if (likely(idx + n < size)) {
> > > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > +			obj[i] = ring[idx];
> > > +			obj[i + 1] = ring[idx + 1];
> > > +			obj[i + 2] = ring[idx + 2];
> > > +			obj[i + 3] = ring[idx + 3];
> > > +			obj[i + 4] = ring[idx + 4];
> > > +			obj[i + 5] = ring[idx + 5];
> > > +			obj[i + 6] = ring[idx + 6];
> > > +			obj[i + 7] = ring[idx + 7];
> > > +		}
> > > +		switch (n & 0x7) {
> > > +		case 7:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 6:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 5:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 4:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 3:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 2:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 1:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		}
> > > +	} else {
> > > +		for (i = 0; idx < size; i++, idx++)
> > > +			obj[i] = ring[idx];
> > > +		/* Start at the beginning */
> > > +		for (idx = 0; i < n; i++, idx++)
> > > +			obj[i] = ring[idx];
> > > +	}
> > > +}
> > > +
> > > +static __rte_always_inline void
> > > +__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > +		void *obj_table, uint32_t n)
> > > +{
> > > +	unsigned int i;
> > > +	const uint32_t size = r->size;
> > > +	uint32_t idx = prod_head & r->mask;
> > > +	uint64_t *ring = (uint64_t *)&r[1];
> > > +	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > > +	if (likely(idx + n < size)) {
> > > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > +			obj[i] = ring[idx];
> > > +			obj[i + 1] = ring[idx + 1];
> > > +			obj[i + 2] = ring[idx + 2];
> > > +			obj[i + 3] = ring[idx + 3];
> > > +		}
> > > +		switch (n & 0x3) {
> > > +		case 3:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 2:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		case 1:
> > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > +		}
> > > +	} else {
> > > +		for (i = 0; idx < size; i++, idx++)
> > > +			obj[i] = ring[idx];
> > > +		/* Start at the beginning */
> > > +		for (idx = 0; i < n; i++, idx++)
> > > +			obj[i] = ring[idx];
> > > +	}
> > > +}
> > > +
> > > +static __rte_always_inline void
> > > +__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > +		void *obj_table, uint32_t n)
> > > +{
> > > +	unsigned int i;
> > > +	const uint32_t size = r->size;
> > > +	uint32_t idx = prod_head & r->mask;
> > > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > +	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > > +	if (likely(idx + n < size)) {
> > > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> > > +		switch (n & 0x1) {
> > > +		case 1:
> > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > +		}
> > > +	} else {
> > > +		for (i = 0; idx < size; i++, idx++)
> > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > +		/* Start at the beginning */
> > > +		for (idx = 0; i < n; i++, idx++)
> > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > +	}
> > > +}
> > > +
> > > +/* the actual dequeue of elements from the ring.
> > > + * Placed here since identical code needed in both
> > > + * single and multi producer enqueue functions.
> > > + */
> > > +static __rte_always_inline void
> > > +__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > > +		void *obj_table, uint32_t esize, uint32_t num) {
> > > +	/* 8B and 16B copies implemented individually to retain
> > > +	 * the current performance.
> > > +	 */
> > > +	if (esize == 8)
> > > +		__rte_ring_dequeue_elems_64(r, cons_head, obj_table,
> > num);
> > > +	else if (esize == 16)
> > > +		__rte_ring_dequeue_elems_128(r, cons_head, obj_table,
> > num);
> > > +	else {
> > > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > +
> > > +		/* Normalize to uint32_t */
> > > +		scale = esize / sizeof(uint32_t);
> > > +		nr_num = num * scale;
> > > +		idx = cons_head & r->mask;
> > > +		nr_idx = idx * scale;
> > > +		nr_size = r->size * scale;
> > > +		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > > +				obj_table, nr_num);
> > > +	}
> > > +}
> > > +
> > > +/* Between load and load. there might be cpu reorder in weak model
> > > + * (powerpc/arm).
> > > + * There are 2 choices for the users
> > > + * 1.use rmb() memory barrier
> > > + * 2.use one-direction load_acquire/store_release barrier
> > > + * It depends on performance test results.
> > > + */
> > > +#ifdef RTE_USE_C11_MEM_MODEL
> > > +#include "ring_c11_pvt.h"
> > > +#else
> > > +#include "ring_generic_pvt.h"
> > > +#endif
> > > +
> > > +/**
> > > + * @internal Enqueue several objects on the ring
> > > + *
> > > + * @param r
> > > + *   A pointer to the ring structure.
> > > + * @param obj_table
> > > + *   A pointer to a table of objects.
> > > + * @param esize
> > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > + *   This must be the same value used while creating the ring. Otherwise
> > > + *   the results are undefined.
> > > + * @param n
> > > + *   The number of objects to add in the ring from the obj_table.
> > > + * @param behavior
> > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > ring
> > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > from ring
> > > + * @param is_sp
> > > + *   Indicates whether to use single producer or multi-producer head
> > update
> > > + * @param free_space
> > > + *   returns the amount of space after the enqueue operation has finished
> > > + * @return
> > > + *   Actual number of objects enqueued.
> > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> > > +		unsigned int esize, unsigned int n,
> > > +		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> > > +		unsigned int *free_space)
> > > +{
> > > +	uint32_t prod_head, prod_next;
> > > +	uint32_t free_entries;
> > > +
> > > +	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > > +			&prod_head, &prod_next, &free_entries);
> > > +	if (n == 0)
> > > +		goto end;
> > > +
> > > +	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> > > +
> > > +	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> > > +end:
> > > +	if (free_space != NULL)
> > > +		*free_space = free_entries - n;
> > > +	return n;
> > > +}
> > > +
> > > +/**
> > > + * @internal Dequeue several objects from the ring
> > > + *
> > > + * @param r
> > > + *   A pointer to the ring structure.
> > > + * @param obj_table
> > > + *   A pointer to a table of objects.
> > > + * @param esize
> > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > + *   This must be the same value used while creating the ring. Otherwise
> > > + *   the results are undefined.
> > > + * @param n
> > > + *   The number of objects to pull from the ring.
> > > + * @param behavior
> > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > ring
> > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > from ring
> > > + * @param is_sc
> > > + *   Indicates whether to use single consumer or multi-consumer head
> > update
> > > + * @param available
> > > + *   returns the number of remaining ring entries after the dequeue has
> > finished
> > > + * @return
> > > + *   - Actual number of objects dequeued.
> > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > +		unsigned int esize, unsigned int n,
> > > +		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> > > +		unsigned int *available)
> > > +{
> > > +	uint32_t cons_head, cons_next;
> > > +	uint32_t entries;
> > > +
> > > +	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > > +			&cons_head, &cons_next, &entries);
> > > +	if (n == 0)
> > > +		goto end;
> > > +
> > > +	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> > > +
> > > +	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> > > +
> > > +end:
> > > +	if (available != NULL)
> > > +		*available = entries - n;
> > > +	return n;
> > > +}
> > > +
> > > +#endif /* _RING_ELEM_PVT_H_ */
> > > diff --git a/lib/librte_ring/rte_ring_generic.h
> > > b/lib/librte_ring/ring_generic_pvt.h
> > > similarity index 98%
> > > rename from lib/librte_ring/rte_ring_generic.h
> > > rename to lib/librte_ring/ring_generic_pvt.h
> > > index 37c62b8d6..fc46a27b2 100644
> > > --- a/lib/librte_ring/rte_ring_generic.h
> > > +++ b/lib/librte_ring/ring_generic_pvt.h
> > > @@ -7,8 +7,8 @@
> > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > >   */
> > >
> > > -#ifndef _RTE_RING_GENERIC_H_
> > > -#define _RTE_RING_GENERIC_H_
> > > +#ifndef _RING_GENERIC_PVT_H_
> > > +#define _RING_GENERIC_PVT_H_
> > >
> > >  static __rte_always_inline void
> > >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > > old_val, @@ -170,4 +170,4 @@ __rte_ring_move_cons_head(struct
> > rte_ring *r, unsigned int is_sc,
> > >  	return n;
> > >  }
> > >
> > > -#endif /* _RTE_RING_GENERIC_H_ */
> > > +#endif /* _RING_GENERIC_PVT_H_ */
> > > diff --git a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > > b/lib/librte_ring/ring_hts_elem_pvt.h
> > > similarity index 60%
> > > rename from lib/librte_ring/rte_ring_hts_c11_mem.h
> > > rename to lib/librte_ring/ring_hts_elem_pvt.h
> > > index 16e54b6ff..9268750b0 100644
> > > --- a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > > +++ b/lib/librte_ring/ring_hts_elem_pvt.h
> > > @@ -7,8 +7,8 @@
> > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > >   */
> > >
> > > -#ifndef _RTE_RING_HTS_C11_MEM_H_
> > > -#define _RTE_RING_HTS_C11_MEM_H_
> > > +#ifndef _RING_HTS_ELEM_PVT_H_
> > > +#define _RING_HTS_ELEM_PVT_H_
> > >
> > >  /**
> > >   * @file rte_ring_hts_c11_mem.h
> > > @@ -161,4 +161,86 @@ __rte_ring_hts_move_cons_head(struct rte_ring
> > *r, unsigned int num,
> > >  	return n;
> > >  }
> > >
> > > -#endif /* _RTE_RING_HTS_C11_MEM_H_ */
> > > +/**
> > > + * @internal Enqueue several objects on the HTS ring.
> > > + *
> > > + * @param r
> > > + *   A pointer to the ring structure.
> > > + * @param obj_table
> > > + *   A pointer to a table of objects.
> > > + * @param esize
> > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > + *   This must be the same value used while creating the ring. Otherwise
> > > + *   the results are undefined.
> > > + * @param n
> > > + *   The number of objects to add in the ring from the obj_table.
> > > + * @param behavior
> > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > ring
> > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > from ring
> > > + * @param free_space
> > > + *   returns the amount of space after the enqueue operation has finished
> > > + * @return
> > > + *   Actual number of objects enqueued.
> > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> > *obj_table,
> > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > +	uint32_t *free_space)
> > > +{
> > > +	uint32_t free, head;
> > > +
> > > +	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> > > +
> > > +	if (n != 0) {
> > > +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > +		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> > > +	}
> > > +
> > > +	if (free_space != NULL)
> > > +		*free_space = free - n;
> > > +	return n;
> > > +}
> > > +
> > > +/**
> > > + * @internal Dequeue several objects from the HTS ring.
> > > + *
> > > + * @param r
> > > + *   A pointer to the ring structure.
> > > + * @param obj_table
> > > + *   A pointer to a table of objects.
> > > + * @param esize
> > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > + *   This must be the same value used while creating the ring. Otherwise
> > > + *   the results are undefined.
> > > + * @param n
> > > + *   The number of objects to pull from the ring.
> > > + * @param behavior
> > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > ring
> > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > from ring
> > > + * @param available
> > > + *   returns the number of remaining ring entries after the dequeue has
> > finished
> > > + * @return
> > > + *   - Actual number of objects dequeued.
> > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > +	uint32_t *available)
> > > +{
> > > +	uint32_t entries, head;
> > > +
> > > +	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> > &entries);
> > > +
> > > +	if (n != 0) {
> > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > +		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> > > +	}
> > > +
> > > +	if (available != NULL)
> > > +		*available = entries - n;
> > > +	return n;
> > > +}
> > > +
> > > +#endif /* _RING_HTS_ELEM_PVT_H_ */
> > > diff --git a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > > b/lib/librte_ring/ring_peek_elem_pvt.h
> > > similarity index 62%
> > > rename from lib/librte_ring/rte_ring_peek_c11_mem.h
> > > rename to lib/librte_ring/ring_peek_elem_pvt.h
> > > index 283c7e70b..1c57bcdd6 100644
> > > --- a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > > +++ b/lib/librte_ring/ring_peek_elem_pvt.h
> > > @@ -7,8 +7,8 @@
> > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > >   */
> > >
> > > -#ifndef _RTE_RING_PEEK_C11_MEM_H_
> > > -#define _RTE_RING_PEEK_C11_MEM_H_
> > > +#ifndef _RING_PEEK_ELEM_PVT_H_
> > > +#define _RING_PEEK_ELEM_PVT_H_
> > >
> > >  /**
> > >   * @file rte_ring_peek_c11_mem.h
> > > @@ -107,4 +107,73 @@ __rte_ring_hts_set_head_tail(struct
> > rte_ring_hts_headtail *ht, uint32_t tail,
> > >  	__atomic_store_n(&ht->ht.raw, p.raw, __ATOMIC_RELEASE);  }
> > >
> > > -#endif /* _RTE_RING_PEEK_C11_MEM_H_ */
> > > +/**
> > > + * @internal This function moves prod head value.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > > +		enum rte_ring_queue_behavior behavior, uint32_t
> > *free_space) {
> > > +	uint32_t free, head, next;
> > > +
> > > +	switch (r->prod.sync_type) {
> > > +	case RTE_RING_SYNC_ST:
> > > +		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> > > +			behavior, &head, &next, &free);
> > > +		break;
> > > +	case RTE_RING_SYNC_MT_HTS:
> > > +		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > > +			&head, &free);
> > > +		break;
> > > +	case RTE_RING_SYNC_MT:
> > > +	case RTE_RING_SYNC_MT_RTS:
> > > +	default:
> > > +		/* unsupported mode, shouldn't be here */
> > > +		RTE_ASSERT(0);
> > > +		n = 0;
> > > +		free = 0;
> > > +	}
> > > +
> > > +	if (free_space != NULL)
> > > +		*free_space = free - n;
> > > +	return n;
> > > +}
> > > +
> > > +/**
> > > + * @internal This function moves cons head value and copies up to *n*
> > > + * objects from the ring to the user provided obj_table.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > +	uint32_t *available)
> > > +{
> > > +	uint32_t avail, head, next;
> > > +
> > > +	switch (r->cons.sync_type) {
> > > +	case RTE_RING_SYNC_ST:
> > > +		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> > > +			behavior, &head, &next, &avail);
> > > +		break;
> > > +	case RTE_RING_SYNC_MT_HTS:
> > > +		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > > +			&head, &avail);
> > > +		break;
> > > +	case RTE_RING_SYNC_MT:
> > > +	case RTE_RING_SYNC_MT_RTS:
> > > +	default:
> > > +		/* unsupported mode, shouldn't be here */
> > > +		RTE_ASSERT(0);
> > > +		n = 0;
> > > +		avail = 0;
> > > +	}
> > > +
> > > +	if (n != 0)
> > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > +
> > > +	if (available != NULL)
> > > +		*available = avail - n;
> > > +	return n;
> > > +}
> > > +
> > > +#endif /* _RING_PEEK_ELEM_PVT_H_ */
> > > diff --git a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > > b/lib/librte_ring/ring_rts_elem_pvt.h
> > > similarity index 62%
> > > rename from lib/librte_ring/rte_ring_rts_c11_mem.h
> > > rename to lib/librte_ring/ring_rts_elem_pvt.h
> > > index 327f22796..cbcec73eb 100644
> > > --- a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > > +++ b/lib/librte_ring/ring_rts_elem_pvt.h
> > > @@ -7,8 +7,8 @@
> > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > >   */
> > >
> > > -#ifndef _RTE_RING_RTS_C11_MEM_H_
> > > -#define _RTE_RING_RTS_C11_MEM_H_
> > > +#ifndef _RING_RTS_ELEM_PVT_H_
> > > +#define _RING_RTS_ELEM_PVT_H_
> > >
> > >  /**
> > >   * @file rte_ring_rts_c11_mem.h
> > > @@ -176,4 +176,86 @@ __rte_ring_rts_move_cons_head(struct rte_ring
> > *r, uint32_t num,
> > >  	return n;
> > >  }
> > >
> > > -#endif /* _RTE_RING_RTS_C11_MEM_H_ */
> > > +/**
> > > + * @internal Enqueue several objects on the RTS ring.
> > > + *
> > > + * @param r
> > > + *   A pointer to the ring structure.
> > > + * @param obj_table
> > > + *   A pointer to a table of objects.
> > > + * @param esize
> > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > + *   This must be the same value used while creating the ring. Otherwise
> > > + *   the results are undefined.
> > > + * @param n
> > > + *   The number of objects to add in the ring from the obj_table.
> > > + * @param behavior
> > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > ring
> > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > from ring
> > > + * @param free_space
> > > + *   returns the amount of space after the enqueue operation has finished
> > > + * @return
> > > + *   Actual number of objects enqueued.
> > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> > *obj_table,
> > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > +	uint32_t *free_space)
> > > +{
> > > +	uint32_t free, head;
> > > +
> > > +	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> > > +
> > > +	if (n != 0) {
> > > +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > +		__rte_ring_rts_update_tail(&r->rts_prod);
> > > +	}
> > > +
> > > +	if (free_space != NULL)
> > > +		*free_space = free - n;
> > > +	return n;
> > > +}
> > > +
> > > +/**
> > > + * @internal Dequeue several objects from the RTS ring.
> > > + *
> > > + * @param r
> > > + *   A pointer to the ring structure.
> > > + * @param obj_table
> > > + *   A pointer to a table of objects.
> > > + * @param esize
> > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > + *   This must be the same value used while creating the ring. Otherwise
> > > + *   the results are undefined.
> > > + * @param n
> > > + *   The number of objects to pull from the ring.
> > > + * @param behavior
> > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > ring
> > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > from ring
> > > + * @param available
> > > + *   returns the number of remaining ring entries after the dequeue has
> > finished
> > > + * @return
> > > + *   - Actual number of objects dequeued.
> > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > + */
> > > +static __rte_always_inline unsigned int
> > > +__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > +	uint32_t *available)
> > > +{
> > > +	uint32_t entries, head;
> > > +
> > > +	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> > &entries);
> > > +
> > > +	if (n != 0) {
> > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > +		__rte_ring_rts_update_tail(&r->rts_cons);
> > > +	}
> > > +
> > > +	if (available != NULL)
> > > +		*available = entries - n;
> > > +	return n;
> > > +}
> > > +
> > > +#endif /* _RING_RTS_ELEM_PVT_H_ */
> > > diff --git a/lib/librte_ring/rte_ring_elem.h
> > > b/lib/librte_ring/rte_ring_elem.h index 57344d47d..119b5c0b6 100644
> > > --- a/lib/librte_ring/rte_ring_elem.h
> > > +++ b/lib/librte_ring/rte_ring_elem.h
> > > @@ -21,6 +21,7 @@ extern "C" {
> > >  #endif
> > >
> > >  #include <rte_ring_core.h>
> > > +#include <ring_elem_pvt.h>
> > >
> > >  /**
> > >   * Calculate the memory size needed for a ring with given element
> > > size @@ -105,379 +106,6 @@ ssize_t
> > rte_ring_get_memsize_elem(unsigned
> > > int esize, unsigned int count);  struct rte_ring *rte_ring_create_elem(const
> > char *name, unsigned int esize,
> > >  			unsigned int count, int socket_id, unsigned int flags);
> > >
> > > -static __rte_always_inline void
> > > -__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> > > -		uint32_t idx, const void *obj_table, uint32_t n)
> > > -{
> > > -	unsigned int i;
> > > -	uint32_t *ring = (uint32_t *)&r[1];
> > > -	const uint32_t *obj = (const uint32_t *)obj_table;
> > > -	if (likely(idx + n < size)) {
> > > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > -			ring[idx] = obj[i];
> > > -			ring[idx + 1] = obj[i + 1];
> > > -			ring[idx + 2] = obj[i + 2];
> > > -			ring[idx + 3] = obj[i + 3];
> > > -			ring[idx + 4] = obj[i + 4];
> > > -			ring[idx + 5] = obj[i + 5];
> > > -			ring[idx + 6] = obj[i + 6];
> > > -			ring[idx + 7] = obj[i + 7];
> > > -		}
> > > -		switch (n & 0x7) {
> > > -		case 7:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 6:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 5:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 4:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 3:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 2:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 1:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		}
> > > -	} else {
> > > -		for (i = 0; idx < size; i++, idx++)
> > > -			ring[idx] = obj[i];
> > > -		/* Start at the beginning */
> > > -		for (idx = 0; i < n; i++, idx++)
> > > -			ring[idx] = obj[i];
> > > -	}
> > > -}
> > > -
> > > -static __rte_always_inline void
> > > -__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > -		const void *obj_table, uint32_t n)
> > > -{
> > > -	unsigned int i;
> > > -	const uint32_t size = r->size;
> > > -	uint32_t idx = prod_head & r->mask;
> > > -	uint64_t *ring = (uint64_t *)&r[1];
> > > -	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> > *)obj_table;
> > > -	if (likely(idx + n < size)) {
> > > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > -			ring[idx] = obj[i];
> > > -			ring[idx + 1] = obj[i + 1];
> > > -			ring[idx + 2] = obj[i + 2];
> > > -			ring[idx + 3] = obj[i + 3];
> > > -		}
> > > -		switch (n & 0x3) {
> > > -		case 3:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 2:
> > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > -		case 1:
> > > -			ring[idx++] = obj[i++];
> > > -		}
> > > -	} else {
> > > -		for (i = 0; idx < size; i++, idx++)
> > > -			ring[idx] = obj[i];
> > > -		/* Start at the beginning */
> > > -		for (idx = 0; i < n; i++, idx++)
> > > -			ring[idx] = obj[i];
> > > -	}
> > > -}
> > > -
> > > -static __rte_always_inline void
> > > -__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > -		const void *obj_table, uint32_t n)
> > > -{
> > > -	unsigned int i;
> > > -	const uint32_t size = r->size;
> > > -	uint32_t idx = prod_head & r->mask;
> > > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > -	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > > -	if (likely(idx + n < size)) {
> > > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > -			memcpy((void *)(ring + idx),
> > > -				(const void *)(obj + i), 32);
> > > -		switch (n & 0x1) {
> > > -		case 1:
> > > -			memcpy((void *)(ring + idx),
> > > -				(const void *)(obj + i), 16);
> > > -		}
> > > -	} else {
> > > -		for (i = 0; idx < size; i++, idx++)
> > > -			memcpy((void *)(ring + idx),
> > > -				(const void *)(obj + i), 16);
> > > -		/* Start at the beginning */
> > > -		for (idx = 0; i < n; i++, idx++)
> > > -			memcpy((void *)(ring + idx),
> > > -				(const void *)(obj + i), 16);
> > > -	}
> > > -}
> > > -
> > > -/* the actual enqueue of elements on the ring.
> > > - * Placed here since identical code needed in both
> > > - * single and multi producer enqueue functions.
> > > - */
> > > -static __rte_always_inline void
> > > -__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > > -		const void *obj_table, uint32_t esize, uint32_t num)
> > > -{
> > > -	/* 8B and 16B copies implemented individually to retain
> > > -	 * the current performance.
> > > -	 */
> > > -	if (esize == 8)
> > > -		__rte_ring_enqueue_elems_64(r, prod_head, obj_table,
> > num);
> > > -	else if (esize == 16)
> > > -		__rte_ring_enqueue_elems_128(r, prod_head, obj_table,
> > num);
> > > -	else {
> > > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > -
> > > -		/* Normalize to uint32_t */
> > > -		scale = esize / sizeof(uint32_t);
> > > -		nr_num = num * scale;
> > > -		idx = prod_head & r->mask;
> > > -		nr_idx = idx * scale;
> > > -		nr_size = r->size * scale;
> > > -		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > > -				obj_table, nr_num);
> > > -	}
> > > -}
> > > -
> > > -static __rte_always_inline void
> > > -__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> > > -		uint32_t idx, void *obj_table, uint32_t n)
> > > -{
> > > -	unsigned int i;
> > > -	uint32_t *ring = (uint32_t *)&r[1];
> > > -	uint32_t *obj = (uint32_t *)obj_table;
> > > -	if (likely(idx + n < size)) {
> > > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > -			obj[i] = ring[idx];
> > > -			obj[i + 1] = ring[idx + 1];
> > > -			obj[i + 2] = ring[idx + 2];
> > > -			obj[i + 3] = ring[idx + 3];
> > > -			obj[i + 4] = ring[idx + 4];
> > > -			obj[i + 5] = ring[idx + 5];
> > > -			obj[i + 6] = ring[idx + 6];
> > > -			obj[i + 7] = ring[idx + 7];
> > > -		}
> > > -		switch (n & 0x7) {
> > > -		case 7:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 6:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 5:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 4:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 3:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 2:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 1:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		}
> > > -	} else {
> > > -		for (i = 0; idx < size; i++, idx++)
> > > -			obj[i] = ring[idx];
> > > -		/* Start at the beginning */
> > > -		for (idx = 0; i < n; i++, idx++)
> > > -			obj[i] = ring[idx];
> > > -	}
> > > -}
> > > -
> > > -static __rte_always_inline void
> > > -__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > -		void *obj_table, uint32_t n)
> > > -{
> > > -	unsigned int i;
> > > -	const uint32_t size = r->size;
> > > -	uint32_t idx = prod_head & r->mask;
> > > -	uint64_t *ring = (uint64_t *)&r[1];
> > > -	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > > -	if (likely(idx + n < size)) {
> > > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > -			obj[i] = ring[idx];
> > > -			obj[i + 1] = ring[idx + 1];
> > > -			obj[i + 2] = ring[idx + 2];
> > > -			obj[i + 3] = ring[idx + 3];
> > > -		}
> > > -		switch (n & 0x3) {
> > > -		case 3:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 2:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		case 1:
> > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > -		}
> > > -	} else {
> > > -		for (i = 0; idx < size; i++, idx++)
> > > -			obj[i] = ring[idx];
> > > -		/* Start at the beginning */
> > > -		for (idx = 0; i < n; i++, idx++)
> > > -			obj[i] = ring[idx];
> > > -	}
> > > -}
> > > -
> > > -static __rte_always_inline void
> > > -__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > -		void *obj_table, uint32_t n)
> > > -{
> > > -	unsigned int i;
> > > -	const uint32_t size = r->size;
> > > -	uint32_t idx = prod_head & r->mask;
> > > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > -	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > > -	if (likely(idx + n < size)) {
> > > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> > > -		switch (n & 0x1) {
> > > -		case 1:
> > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > -		}
> > > -	} else {
> > > -		for (i = 0; idx < size; i++, idx++)
> > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > -		/* Start at the beginning */
> > > -		for (idx = 0; i < n; i++, idx++)
> > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > -	}
> > > -}
> > > -
> > > -/* the actual dequeue of elements from the ring.
> > > - * Placed here since identical code needed in both
> > > - * single and multi producer enqueue functions.
> > > - */
> > > -static __rte_always_inline void
> > > -__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > > -		void *obj_table, uint32_t esize, uint32_t num)
> > > -{
> > > -	/* 8B and 16B copies implemented individually to retain
> > > -	 * the current performance.
> > > -	 */
> > > -	if (esize == 8)
> > > -		__rte_ring_dequeue_elems_64(r, cons_head, obj_table,
> > num);
> > > -	else if (esize == 16)
> > > -		__rte_ring_dequeue_elems_128(r, cons_head, obj_table,
> > num);
> > > -	else {
> > > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > -
> > > -		/* Normalize to uint32_t */
> > > -		scale = esize / sizeof(uint32_t);
> > > -		nr_num = num * scale;
> > > -		idx = cons_head & r->mask;
> > > -		nr_idx = idx * scale;
> > > -		nr_size = r->size * scale;
> > > -		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > > -				obj_table, nr_num);
> > > -	}
> > > -}
> > > -
> > > -/* Between load and load. there might be cpu reorder in weak model
> > > - * (powerpc/arm).
> > > - * There are 2 choices for the users
> > > - * 1.use rmb() memory barrier
> > > - * 2.use one-direction load_acquire/store_release barrier
> > > - * It depends on performance test results.
> > > - * By default, move common functions to rte_ring_generic.h
> > > - */
> > > -#ifdef RTE_USE_C11_MEM_MODEL
> > > -#include "rte_ring_c11_mem.h"
> > > -#else
> > > -#include "rte_ring_generic.h"
> > > -#endif
> > > -
> > > -/**
> > > - * @internal Enqueue several objects on the ring
> > > - *
> > > - * @param r
> > > - *   A pointer to the ring structure.
> > > - * @param obj_table
> > > - *   A pointer to a table of objects.
> > > - * @param esize
> > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > - *   This must be the same value used while creating the ring. Otherwise
> > > - *   the results are undefined.
> > > - * @param n
> > > - *   The number of objects to add in the ring from the obj_table.
> > > - * @param behavior
> > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > ring
> > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > from ring
> > > - * @param is_sp
> > > - *   Indicates whether to use single producer or multi-producer head
> > update
> > > - * @param free_space
> > > - *   returns the amount of space after the enqueue operation has finished
> > > - * @return
> > > - *   Actual number of objects enqueued.
> > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> > > -		unsigned int esize, unsigned int n,
> > > -		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> > > -		unsigned int *free_space)
> > > -{
> > > -	uint32_t prod_head, prod_next;
> > > -	uint32_t free_entries;
> > > -
> > > -	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > > -			&prod_head, &prod_next, &free_entries);
> > > -	if (n == 0)
> > > -		goto end;
> > > -
> > > -	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> > > -
> > > -	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> > > -end:
> > > -	if (free_space != NULL)
> > > -		*free_space = free_entries - n;
> > > -	return n;
> > > -}
> > > -
> > > -/**
> > > - * @internal Dequeue several objects from the ring
> > > - *
> > > - * @param r
> > > - *   A pointer to the ring structure.
> > > - * @param obj_table
> > > - *   A pointer to a table of objects.
> > > - * @param esize
> > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > - *   This must be the same value used while creating the ring. Otherwise
> > > - *   the results are undefined.
> > > - * @param n
> > > - *   The number of objects to pull from the ring.
> > > - * @param behavior
> > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > ring
> > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > from ring
> > > - * @param is_sc
> > > - *   Indicates whether to use single consumer or multi-consumer head
> > update
> > > - * @param available
> > > - *   returns the number of remaining ring entries after the dequeue has
> > finished
> > > - * @return
> > > - *   - Actual number of objects dequeued.
> > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > -		unsigned int esize, unsigned int n,
> > > -		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> > > -		unsigned int *available)
> > > -{
> > > -	uint32_t cons_head, cons_next;
> > > -	uint32_t entries;
> > > -
> > > -	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > > -			&cons_head, &cons_next, &entries);
> > > -	if (n == 0)
> > > -		goto end;
> > > -
> > > -	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> > > -
> > > -	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> > > -
> > > -end:
> > > -	if (available != NULL)
> > > -		*available = entries - n;
> > > -	return n;
> > > -}
> > > -
> > >  /**
> > >   * Enqueue several objects on the ring (multi-producers safe).
> > >   *
> > > diff --git a/lib/librte_ring/rte_ring_hts.h
> > > b/lib/librte_ring/rte_ring_hts.h index 359b15771..bdbdafc9f 100644
> > > --- a/lib/librte_ring/rte_ring_hts.h
> > > +++ b/lib/librte_ring/rte_ring_hts.h
> > > @@ -29,89 +29,7 @@
> > >  extern "C" {
> > >  #endif
> > >
> > > -#include <rte_ring_hts_c11_mem.h>
> > > -
> > > -/**
> > > - * @internal Enqueue several objects on the HTS ring.
> > > - *
> > > - * @param r
> > > - *   A pointer to the ring structure.
> > > - * @param obj_table
> > > - *   A pointer to a table of objects.
> > > - * @param esize
> > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > - *   This must be the same value used while creating the ring. Otherwise
> > > - *   the results are undefined.
> > > - * @param n
> > > - *   The number of objects to add in the ring from the obj_table.
> > > - * @param behavior
> > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > ring
> > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > from ring
> > > - * @param free_space
> > > - *   returns the amount of space after the enqueue operation has finished
> > > - * @return
> > > - *   Actual number of objects enqueued.
> > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> > *obj_table,
> > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > -	uint32_t *free_space)
> > > -{
> > > -	uint32_t free, head;
> > > -
> > > -	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> > > -
> > > -	if (n != 0) {
> > > -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > -		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> > > -	}
> > > -
> > > -	if (free_space != NULL)
> > > -		*free_space = free - n;
> > > -	return n;
> > > -}
> > > -
> > > -/**
> > > - * @internal Dequeue several objects from the HTS ring.
> > > - *
> > > - * @param r
> > > - *   A pointer to the ring structure.
> > > - * @param obj_table
> > > - *   A pointer to a table of objects.
> > > - * @param esize
> > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > - *   This must be the same value used while creating the ring. Otherwise
> > > - *   the results are undefined.
> > > - * @param n
> > > - *   The number of objects to pull from the ring.
> > > - * @param behavior
> > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > ring
> > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > from ring
> > > - * @param available
> > > - *   returns the number of remaining ring entries after the dequeue has
> > finished
> > > - * @return
> > > - *   - Actual number of objects dequeued.
> > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > -	uint32_t *available)
> > > -{
> > > -	uint32_t entries, head;
> > > -
> > > -	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> > &entries);
> > > -
> > > -	if (n != 0) {
> > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > -		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> > > -	}
> > > -
> > > -	if (available != NULL)
> > > -		*available = entries - n;
> > > -	return n;
> > > -}
> > > +#include <ring_hts_elem_pvt.h>
> > >
> > >  /**
> > >   * Enqueue several objects on the HTS ring (multi-producers safe).
> > > diff --git a/lib/librte_ring/rte_ring_peek.h
> > > b/lib/librte_ring/rte_ring_peek.h index 45f707dc7..0dd402be4 100644
> > > --- a/lib/librte_ring/rte_ring_peek.h
> > > +++ b/lib/librte_ring/rte_ring_peek.h
> > > @@ -48,39 +48,7 @@
> > >  extern "C" {
> > >  #endif
> > >
> > > -#include <rte_ring_peek_c11_mem.h>
> > > -
> > > -/**
> > > - * @internal This function moves prod head value.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > > -		enum rte_ring_queue_behavior behavior, uint32_t
> > *free_space)
> > > -{
> > > -	uint32_t free, head, next;
> > > -
> > > -	switch (r->prod.sync_type) {
> > > -	case RTE_RING_SYNC_ST:
> > > -		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> > > -			behavior, &head, &next, &free);
> > > -		break;
> > > -	case RTE_RING_SYNC_MT_HTS:
> > > -		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > > -			&head, &free);
> > > -		break;
> > > -	case RTE_RING_SYNC_MT:
> > > -	case RTE_RING_SYNC_MT_RTS:
> > > -	default:
> > > -		/* unsupported mode, shouldn't be here */
> > > -		RTE_ASSERT(0);
> > > -		n = 0;
> > > -		free = 0;
> > > -	}
> > > -
> > > -	if (free_space != NULL)
> > > -		*free_space = free - n;
> > > -	return n;
> > > -}
> > > +#include <ring_peek_elem_pvt.h>
> > >
> > >  /**
> > >   * Start to enqueue several objects on the ring.
> > > @@ -248,43 +216,6 @@ rte_ring_enqueue_finish(struct rte_ring *r, void *
> > const *obj_table,
> > >  	rte_ring_enqueue_elem_finish(r, obj_table, sizeof(uintptr_t), n);  }
> > >
> > > -/**
> > > - * @internal This function moves cons head value and copies up to *n*
> > > - * objects from the ring to the user provided obj_table.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > -	uint32_t *available)
> > > -{
> > > -	uint32_t avail, head, next;
> > > -
> > > -	switch (r->cons.sync_type) {
> > > -	case RTE_RING_SYNC_ST:
> > > -		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> > > -			behavior, &head, &next, &avail);
> > > -		break;
> > > -	case RTE_RING_SYNC_MT_HTS:
> > > -		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > > -			&head, &avail);
> > > -		break;
> > > -	case RTE_RING_SYNC_MT:
> > > -	case RTE_RING_SYNC_MT_RTS:
> > > -	default:
> > > -		/* unsupported mode, shouldn't be here */
> > > -		RTE_ASSERT(0);
> > > -		n = 0;
> > > -		avail = 0;
> > > -	}
> > > -
> > > -	if (n != 0)
> > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > -
> > > -	if (available != NULL)
> > > -		*available = avail - n;
> > > -	return n;
> > > -}
> > > -
> > >  /**
> > >   * Start to dequeue several objects from the ring.
> > >   * Note that user has to call appropriate dequeue_finish() diff --git
> > > a/lib/librte_ring/rte_ring_peek_zc.h
> > > b/lib/librte_ring/rte_ring_peek_zc.h
> > > index cb3bbd067..bc8252a18 100644
> > > --- a/lib/librte_ring/rte_ring_peek_zc.h
> > > +++ b/lib/librte_ring/rte_ring_peek_zc.h
> > > @@ -72,7 +72,7 @@
> > >  extern "C" {
> > >  #endif
> > >
> > > -#include <rte_ring_peek_c11_mem.h>
> > > +#include <ring_peek_elem_pvt.h>
> > >
> > >  /**
> > >   * Ring zero-copy information structure.
> > > diff --git a/lib/librte_ring/rte_ring_rts.h
> > > b/lib/librte_ring/rte_ring_rts.h index afc12abe2..83d9903e2 100644
> > > --- a/lib/librte_ring/rte_ring_rts.h
> > > +++ b/lib/librte_ring/rte_ring_rts.h
> > > @@ -56,89 +56,7 @@
> > >  extern "C" {
> > >  #endif
> > >
> > > -#include <rte_ring_rts_c11_mem.h>
> > > -
> > > -/**
> > > - * @internal Enqueue several objects on the RTS ring.
> > > - *
> > > - * @param r
> > > - *   A pointer to the ring structure.
> > > - * @param obj_table
> > > - *   A pointer to a table of objects.
> > > - * @param esize
> > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > - *   This must be the same value used while creating the ring. Otherwise
> > > - *   the results are undefined.
> > > - * @param n
> > > - *   The number of objects to add in the ring from the obj_table.
> > > - * @param behavior
> > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > ring
> > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > from ring
> > > - * @param free_space
> > > - *   returns the amount of space after the enqueue operation has finished
> > > - * @return
> > > - *   Actual number of objects enqueued.
> > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> > *obj_table,
> > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > -	uint32_t *free_space)
> > > -{
> > > -	uint32_t free, head;
> > > -
> > > -	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> > > -
> > > -	if (n != 0) {
> > > -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > -		__rte_ring_rts_update_tail(&r->rts_prod);
> > > -	}
> > > -
> > > -	if (free_space != NULL)
> > > -		*free_space = free - n;
> > > -	return n;
> > > -}
> > > -
> > > -/**
> > > - * @internal Dequeue several objects from the RTS ring.
> > > - *
> > > - * @param r
> > > - *   A pointer to the ring structure.
> > > - * @param obj_table
> > > - *   A pointer to a table of objects.
> > > - * @param esize
> > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > - *   This must be the same value used while creating the ring. Otherwise
> > > - *   the results are undefined.
> > > - * @param n
> > > - *   The number of objects to pull from the ring.
> > > - * @param behavior
> > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > ring
> > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > from ring
> > > - * @param available
> > > - *   returns the number of remaining ring entries after the dequeue has
> > finished
> > > - * @return
> > > - *   - Actual number of objects dequeued.
> > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > - */
> > > -static __rte_always_inline unsigned int
> > > -__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > -	uint32_t *available)
> > > -{
> > > -	uint32_t entries, head;
> > > -
> > > -	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> > &entries);
> > > -
> > > -	if (n != 0) {
> > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > -		__rte_ring_rts_update_tail(&r->rts_cons);
> > > -	}
> > > -
> > > -	if (available != NULL)
> > > -		*available = entries - n;
> > > -	return n;
> > > -}
> > > +#include <ring_rts_elem_pvt.h>
> > >
> > >  /**
> > >   * Enqueue several objects on the RTS ring (multi-producers safe).
> > > --
> > > 2.17.1
Konstantin Ananyev Jan. 25, 2021, 10:29 a.m. UTC | #4
> 
> Hi Feifei,
> 
> > > > For legacy modes, rename ring_generic/c11 to ring_generic/c11_pvt.
> > > > Furthermore, add new file ring_elem_pvt.h which includes
> > > > ring_do_eq/deq and ring element copy/delete APIs.
> > > >
> > > > For other modes, rename xx_c11_mem to xx_elem_pvt. Move all private
> > > > APIs into these new header files.
> > > >
> > > > Suggested-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > > > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > > > Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > > ---
> > > >  lib/librte_ring/meson.build                   |  15 +-
> > > >  .../{rte_ring_c11_mem.h => ring_c11_pvt.h}    |   9 +-
> > > >  lib/librte_ring/ring_elem_pvt.h               | 385 ++++++++++++++++++
> > > >  ...{rte_ring_generic.h => ring_generic_pvt.h} |   6 +-
> > > >  ...ring_hts_c11_mem.h => ring_hts_elem_pvt.h} |  88 +++-
> > > > ...ng_peek_c11_mem.h => ring_peek_elem_pvt.h} |  75 +++-
> > > > ...ring_rts_c11_mem.h => ring_rts_elem_pvt.h} |  88 +++-
> > > >  lib/librte_ring/rte_ring_elem.h               | 374 +----------------
> > > >  lib/librte_ring/rte_ring_hts.h                |  84 +---
> > > >  lib/librte_ring/rte_ring_peek.h               |  71 +---
> > > >  lib/librte_ring/rte_ring_peek_zc.h            |   2 +-
> > > >  lib/librte_ring/rte_ring_rts.h                |  84 +---
> > > >  12 files changed, 646 insertions(+), 635 deletions(-)  rename
> > > > lib/librte_ring/{rte_ring_c11_mem.h => ring_c11_pvt.h} (96%)  create
> > > > mode 100644 lib/librte_ring/ring_elem_pvt.h  rename
> > > > lib/librte_ring/{rte_ring_generic.h => ring_generic_pvt.h} (98%)
> > > > rename lib/librte_ring/{rte_ring_hts_c11_mem.h => ring_hts_elem_pvt.h}
> > > > (60%)  rename lib/librte_ring/{rte_ring_peek_c11_mem.h =>
> > > > ring_peek_elem_pvt.h} (62%)  rename
> > > > lib/librte_ring/{rte_ring_rts_c11_mem.h => ring_rts_elem_pvt.h} (62%)
> > > >
> > >
> > > Sorry, but I don't understand the purpose of that patch.
> > > As I remember by DPDK naming convention all installable headers should
> > > have 'rte_' prefix. Same for public defines (RTE_).
> > > Why to abandon it here?
> >
> > This change refers to you and Honnappa's discussion about ring:
> > https://mails.dpdk.org/archives/dev/2020-May/166803.html
> >
> > And it is to separate the external APIs that can be called by users,
> > from internal APIs that cannot be called by users.
> > The internal functions are included in the files with xx_pvt.h.
> 
> Even these xx_pvt.h files contain internal API and not supposed to be included directly,
> they have to be installed into public dir (<dpdk-install-dir/include).
> So I think we need to keep DPDK public prefixes for them (and inside them):
> rte_xx_pvt.h (_RTE_).

As another thought - it is probably good to introduce new generic naming convention
for such sort of files (internal ones that still have to be exposed).
Might be '_rte_' prefix or so...
Though I suppose it would require broader discussion first.

> 
> Konstantin
> 
> >
> > Best Regards
> > Feifei
> > >
> > > > diff --git a/lib/librte_ring/meson.build b/lib/librte_ring/meson.build
> > > > index 36fdcb6a5..98eac5810 100644
> > > > --- a/lib/librte_ring/meson.build
> > > > +++ b/lib/librte_ring/meson.build
> > > > @@ -2,15 +2,16 @@
> > > >  # Copyright(c) 2017 Intel Corporation
> > > >
> > > >  sources = files('rte_ring.c')
> > > > -headers = files('rte_ring.h',
> > > > +headers = files('ring_c11_pvt.h',
> > > > +		'ring_elem_pvt.h',
> > > > +		'ring_generic_pvt.h',
> > > > +		'ring_hts_elem_pvt.h',
> > > > +		'ring_peek_elem_pvt.h',
> > > > +		'ring_rts_elem_pvt.h',
> > > > +		'rte_ring.h',
> > > >  		'rte_ring_core.h',
> > > >  		'rte_ring_elem.h',
> > > > -		'rte_ring_c11_mem.h',
> > > > -		'rte_ring_generic.h',
> > > >  		'rte_ring_hts.h',
> > > > -		'rte_ring_hts_c11_mem.h',
> > > >  		'rte_ring_peek.h',
> > > > -		'rte_ring_peek_c11_mem.h',
> > > >  		'rte_ring_peek_zc.h',
> > > > -		'rte_ring_rts.h',
> > > > -		'rte_ring_rts_c11_mem.h')
> > > > +		'rte_ring_rts.h')
> > > > diff --git a/lib/librte_ring/rte_ring_c11_mem.h
> > > > b/lib/librte_ring/ring_c11_pvt.h similarity index 96% rename from
> > > > lib/librte_ring/rte_ring_c11_mem.h
> > > > rename to lib/librte_ring/ring_c11_pvt.h index 7f5eba262..9f2f5318f
> > > > 100644
> > > > --- a/lib/librte_ring/rte_ring_c11_mem.h
> > > > +++ b/lib/librte_ring/ring_c11_pvt.h
> > > > @@ -7,8 +7,8 @@
> > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > >   */
> > > >
> > > > -#ifndef _RTE_RING_C11_MEM_H_
> > > > -#define _RTE_RING_C11_MEM_H_
> > > > +#ifndef _RING_C11_PVT_H_
> > > > +#define _RING_C11_PVT_H_
> > > >
> > > >  static __rte_always_inline void
> > > >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > > > old_val, @@ -69,9 +69,6 @@ __rte_ring_move_prod_head(struct rte_ring
> > > *r, unsigned int is_sp,
> > > >  		/* Ensure the head is read before tail */
> > > >  		__atomic_thread_fence(__ATOMIC_ACQUIRE);
> > > >
> > > > -		/* load-acquire synchronize with store-release of ht->tail
> > > > -		 * in update_tail.
> > > > -		 */
> > > >  		cons_tail = __atomic_load_n(&r->cons.tail,
> > > >  					__ATOMIC_ACQUIRE);
> > > >
> > > > @@ -178,4 +175,4 @@ __rte_ring_move_cons_head(struct rte_ring *r, int
> > > is_sc,
> > > >  	return n;
> > > >  }
> > > >
> > > > -#endif /* _RTE_RING_C11_MEM_H_ */
> > > > +#endif /* _RING_C11_PVT_H_ */
> > > > diff --git a/lib/librte_ring/ring_elem_pvt.h
> > > > b/lib/librte_ring/ring_elem_pvt.h new file mode 100644 index
> > > > 000000000..8003e5edc
> > > > --- /dev/null
> > > > +++ b/lib/librte_ring/ring_elem_pvt.h
> > > > @@ -0,0 +1,385 @@
> > > > +/* SPDX-License-Identifier: BSD-3-Clause
> > > > + *
> > > > + * Copyright (c) 2017,2018 HXT-semitech Corporation.
> > > > + * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
> > > > + * All rights reserved.
> > > > + * Derived from FreeBSD's bufring.h
> > > > + * Used as BSD-3 Licensed with permission from Kip Macy.
> > > > + */
> > > > +
> > > > +#ifndef _RING_ELEM_PVT_H_
> > > > +#define _RING_ELEM_PVT_H_
> > > > +
> > > > +static __rte_always_inline void
> > > > +__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> > > > +		uint32_t idx, const void *obj_table, uint32_t n) {
> > > > +	unsigned int i;
> > > > +	uint32_t *ring = (uint32_t *)&r[1];
> > > > +	const uint32_t *obj = (const uint32_t *)obj_table;
> > > > +	if (likely(idx + n < size)) {
> > > > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > +			ring[idx] = obj[i];
> > > > +			ring[idx + 1] = obj[i + 1];
> > > > +			ring[idx + 2] = obj[i + 2];
> > > > +			ring[idx + 3] = obj[i + 3];
> > > > +			ring[idx + 4] = obj[i + 4];
> > > > +			ring[idx + 5] = obj[i + 5];
> > > > +			ring[idx + 6] = obj[i + 6];
> > > > +			ring[idx + 7] = obj[i + 7];
> > > > +		}
> > > > +		switch (n & 0x7) {
> > > > +		case 7:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 6:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 5:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 4:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 3:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 2:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 1:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		}
> > > > +	} else {
> > > > +		for (i = 0; idx < size; i++, idx++)
> > > > +			ring[idx] = obj[i];
> > > > +		/* Start at the beginning */
> > > > +		for (idx = 0; i < n; i++, idx++)
> > > > +			ring[idx] = obj[i];
> > > > +	}
> > > > +}
> > > > +
> > > > +static __rte_always_inline void
> > > > +__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > > +		const void *obj_table, uint32_t n)
> > > > +{
> > > > +	unsigned int i;
> > > > +	const uint32_t size = r->size;
> > > > +	uint32_t idx = prod_head & r->mask;
> > > > +	uint64_t *ring = (uint64_t *)&r[1];
> > > > +	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> > > *)obj_table;
> > > > +	if (likely(idx + n < size)) {
> > > > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > +			ring[idx] = obj[i];
> > > > +			ring[idx + 1] = obj[i + 1];
> > > > +			ring[idx + 2] = obj[i + 2];
> > > > +			ring[idx + 3] = obj[i + 3];
> > > > +		}
> > > > +		switch (n & 0x3) {
> > > > +		case 3:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 2:
> > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > +		case 1:
> > > > +			ring[idx++] = obj[i++];
> > > > +		}
> > > > +	} else {
> > > > +		for (i = 0; idx < size; i++, idx++)
> > > > +			ring[idx] = obj[i];
> > > > +		/* Start at the beginning */
> > > > +		for (idx = 0; i < n; i++, idx++)
> > > > +			ring[idx] = obj[i];
> > > > +	}
> > > > +}
> > > > +
> > > > +static __rte_always_inline void
> > > > +__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > > +		const void *obj_table, uint32_t n)
> > > > +{
> > > > +	unsigned int i;
> > > > +	const uint32_t size = r->size;
> > > > +	uint32_t idx = prod_head & r->mask;
> > > > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > +	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > > > +	if (likely(idx + n < size)) {
> > > > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > +			memcpy((void *)(ring + idx),
> > > > +				(const void *)(obj + i), 32);
> > > > +		switch (n & 0x1) {
> > > > +		case 1:
> > > > +			memcpy((void *)(ring + idx),
> > > > +				(const void *)(obj + i), 16);
> > > > +		}
> > > > +	} else {
> > > > +		for (i = 0; idx < size; i++, idx++)
> > > > +			memcpy((void *)(ring + idx),
> > > > +				(const void *)(obj + i), 16);
> > > > +		/* Start at the beginning */
> > > > +		for (idx = 0; i < n; i++, idx++)
> > > > +			memcpy((void *)(ring + idx),
> > > > +				(const void *)(obj + i), 16);
> > > > +	}
> > > > +}
> > > > +
> > > > +/* the actual enqueue of elements on the ring.
> > > > + * Placed here since identical code needed in both
> > > > + * single and multi producer enqueue functions.
> > > > + */
> > > > +static __rte_always_inline void
> > > > +__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > > > +		const void *obj_table, uint32_t esize, uint32_t num) {
> > > > +	/* 8B and 16B copies implemented individually to retain
> > > > +	 * the current performance.
> > > > +	 */
> > > > +	if (esize == 8)
> > > > +		__rte_ring_enqueue_elems_64(r, prod_head, obj_table,
> > > num);
> > > > +	else if (esize == 16)
> > > > +		__rte_ring_enqueue_elems_128(r, prod_head, obj_table,
> > > num);
> > > > +	else {
> > > > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > +
> > > > +		/* Normalize to uint32_t */
> > > > +		scale = esize / sizeof(uint32_t);
> > > > +		nr_num = num * scale;
> > > > +		idx = prod_head & r->mask;
> > > > +		nr_idx = idx * scale;
> > > > +		nr_size = r->size * scale;
> > > > +		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > > > +				obj_table, nr_num);
> > > > +	}
> > > > +}
> > > > +
> > > > +static __rte_always_inline void
> > > > +__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> > > > +		uint32_t idx, void *obj_table, uint32_t n) {
> > > > +	unsigned int i;
> > > > +	uint32_t *ring = (uint32_t *)&r[1];
> > > > +	uint32_t *obj = (uint32_t *)obj_table;
> > > > +	if (likely(idx + n < size)) {
> > > > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > +			obj[i] = ring[idx];
> > > > +			obj[i + 1] = ring[idx + 1];
> > > > +			obj[i + 2] = ring[idx + 2];
> > > > +			obj[i + 3] = ring[idx + 3];
> > > > +			obj[i + 4] = ring[idx + 4];
> > > > +			obj[i + 5] = ring[idx + 5];
> > > > +			obj[i + 6] = ring[idx + 6];
> > > > +			obj[i + 7] = ring[idx + 7];
> > > > +		}
> > > > +		switch (n & 0x7) {
> > > > +		case 7:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 6:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 5:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 4:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 3:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 2:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 1:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		}
> > > > +	} else {
> > > > +		for (i = 0; idx < size; i++, idx++)
> > > > +			obj[i] = ring[idx];
> > > > +		/* Start at the beginning */
> > > > +		for (idx = 0; i < n; i++, idx++)
> > > > +			obj[i] = ring[idx];
> > > > +	}
> > > > +}
> > > > +
> > > > +static __rte_always_inline void
> > > > +__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > > +		void *obj_table, uint32_t n)
> > > > +{
> > > > +	unsigned int i;
> > > > +	const uint32_t size = r->size;
> > > > +	uint32_t idx = prod_head & r->mask;
> > > > +	uint64_t *ring = (uint64_t *)&r[1];
> > > > +	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > > > +	if (likely(idx + n < size)) {
> > > > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > +			obj[i] = ring[idx];
> > > > +			obj[i + 1] = ring[idx + 1];
> > > > +			obj[i + 2] = ring[idx + 2];
> > > > +			obj[i + 3] = ring[idx + 3];
> > > > +		}
> > > > +		switch (n & 0x3) {
> > > > +		case 3:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 2:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		case 1:
> > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > +		}
> > > > +	} else {
> > > > +		for (i = 0; idx < size; i++, idx++)
> > > > +			obj[i] = ring[idx];
> > > > +		/* Start at the beginning */
> > > > +		for (idx = 0; i < n; i++, idx++)
> > > > +			obj[i] = ring[idx];
> > > > +	}
> > > > +}
> > > > +
> > > > +static __rte_always_inline void
> > > > +__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > > +		void *obj_table, uint32_t n)
> > > > +{
> > > > +	unsigned int i;
> > > > +	const uint32_t size = r->size;
> > > > +	uint32_t idx = prod_head & r->mask;
> > > > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > +	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > > > +	if (likely(idx + n < size)) {
> > > > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> > > > +		switch (n & 0x1) {
> > > > +		case 1:
> > > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > > +		}
> > > > +	} else {
> > > > +		for (i = 0; idx < size; i++, idx++)
> > > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > > +		/* Start at the beginning */
> > > > +		for (idx = 0; i < n; i++, idx++)
> > > > +			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > > +	}
> > > > +}
> > > > +
> > > > +/* the actual dequeue of elements from the ring.
> > > > + * Placed here since identical code needed in both
> > > > + * single and multi producer enqueue functions.
> > > > + */
> > > > +static __rte_always_inline void
> > > > +__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > > > +		void *obj_table, uint32_t esize, uint32_t num) {
> > > > +	/* 8B and 16B copies implemented individually to retain
> > > > +	 * the current performance.
> > > > +	 */
> > > > +	if (esize == 8)
> > > > +		__rte_ring_dequeue_elems_64(r, cons_head, obj_table,
> > > num);
> > > > +	else if (esize == 16)
> > > > +		__rte_ring_dequeue_elems_128(r, cons_head, obj_table,
> > > num);
> > > > +	else {
> > > > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > +
> > > > +		/* Normalize to uint32_t */
> > > > +		scale = esize / sizeof(uint32_t);
> > > > +		nr_num = num * scale;
> > > > +		idx = cons_head & r->mask;
> > > > +		nr_idx = idx * scale;
> > > > +		nr_size = r->size * scale;
> > > > +		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > > > +				obj_table, nr_num);
> > > > +	}
> > > > +}
> > > > +
> > > > +/* Between load and load. there might be cpu reorder in weak model
> > > > + * (powerpc/arm).
> > > > + * There are 2 choices for the users
> > > > + * 1.use rmb() memory barrier
> > > > + * 2.use one-direction load_acquire/store_release barrier
> > > > + * It depends on performance test results.
> > > > + */
> > > > +#ifdef RTE_USE_C11_MEM_MODEL
> > > > +#include "ring_c11_pvt.h"
> > > > +#else
> > > > +#include "ring_generic_pvt.h"
> > > > +#endif
> > > > +
> > > > +/**
> > > > + * @internal Enqueue several objects on the ring
> > > > + *
> > > > + * @param r
> > > > + *   A pointer to the ring structure.
> > > > + * @param obj_table
> > > > + *   A pointer to a table of objects.
> > > > + * @param esize
> > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > + *   This must be the same value used while creating the ring. Otherwise
> > > > + *   the results are undefined.
> > > > + * @param n
> > > > + *   The number of objects to add in the ring from the obj_table.
> > > > + * @param behavior
> > > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > > ring
> > > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > > from ring
> > > > + * @param is_sp
> > > > + *   Indicates whether to use single producer or multi-producer head
> > > update
> > > > + * @param free_space
> > > > + *   returns the amount of space after the enqueue operation has finished
> > > > + * @return
> > > > + *   Actual number of objects enqueued.
> > > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> > > > +		unsigned int esize, unsigned int n,
> > > > +		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> > > > +		unsigned int *free_space)
> > > > +{
> > > > +	uint32_t prod_head, prod_next;
> > > > +	uint32_t free_entries;
> > > > +
> > > > +	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > > > +			&prod_head, &prod_next, &free_entries);
> > > > +	if (n == 0)
> > > > +		goto end;
> > > > +
> > > > +	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> > > > +
> > > > +	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> > > > +end:
> > > > +	if (free_space != NULL)
> > > > +		*free_space = free_entries - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +/**
> > > > + * @internal Dequeue several objects from the ring
> > > > + *
> > > > + * @param r
> > > > + *   A pointer to the ring structure.
> > > > + * @param obj_table
> > > > + *   A pointer to a table of objects.
> > > > + * @param esize
> > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > + *   This must be the same value used while creating the ring. Otherwise
> > > > + *   the results are undefined.
> > > > + * @param n
> > > > + *   The number of objects to pull from the ring.
> > > > + * @param behavior
> > > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > > ring
> > > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > > from ring
> > > > + * @param is_sc
> > > > + *   Indicates whether to use single consumer or multi-consumer head
> > > update
> > > > + * @param available
> > > > + *   returns the number of remaining ring entries after the dequeue has
> > > finished
> > > > + * @return
> > > > + *   - Actual number of objects dequeued.
> > > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > +		unsigned int esize, unsigned int n,
> > > > +		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> > > > +		unsigned int *available)
> > > > +{
> > > > +	uint32_t cons_head, cons_next;
> > > > +	uint32_t entries;
> > > > +
> > > > +	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > > > +			&cons_head, &cons_next, &entries);
> > > > +	if (n == 0)
> > > > +		goto end;
> > > > +
> > > > +	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> > > > +
> > > > +	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> > > > +
> > > > +end:
> > > > +	if (available != NULL)
> > > > +		*available = entries - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +#endif /* _RING_ELEM_PVT_H_ */
> > > > diff --git a/lib/librte_ring/rte_ring_generic.h
> > > > b/lib/librte_ring/ring_generic_pvt.h
> > > > similarity index 98%
> > > > rename from lib/librte_ring/rte_ring_generic.h
> > > > rename to lib/librte_ring/ring_generic_pvt.h
> > > > index 37c62b8d6..fc46a27b2 100644
> > > > --- a/lib/librte_ring/rte_ring_generic.h
> > > > +++ b/lib/librte_ring/ring_generic_pvt.h
> > > > @@ -7,8 +7,8 @@
> > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > >   */
> > > >
> > > > -#ifndef _RTE_RING_GENERIC_H_
> > > > -#define _RTE_RING_GENERIC_H_
> > > > +#ifndef _RING_GENERIC_PVT_H_
> > > > +#define _RING_GENERIC_PVT_H_
> > > >
> > > >  static __rte_always_inline void
> > > >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > > > old_val, @@ -170,4 +170,4 @@ __rte_ring_move_cons_head(struct
> > > rte_ring *r, unsigned int is_sc,
> > > >  	return n;
> > > >  }
> > > >
> > > > -#endif /* _RTE_RING_GENERIC_H_ */
> > > > +#endif /* _RING_GENERIC_PVT_H_ */
> > > > diff --git a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > > > b/lib/librte_ring/ring_hts_elem_pvt.h
> > > > similarity index 60%
> > > > rename from lib/librte_ring/rte_ring_hts_c11_mem.h
> > > > rename to lib/librte_ring/ring_hts_elem_pvt.h
> > > > index 16e54b6ff..9268750b0 100644
> > > > --- a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > > > +++ b/lib/librte_ring/ring_hts_elem_pvt.h
> > > > @@ -7,8 +7,8 @@
> > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > >   */
> > > >
> > > > -#ifndef _RTE_RING_HTS_C11_MEM_H_
> > > > -#define _RTE_RING_HTS_C11_MEM_H_
> > > > +#ifndef _RING_HTS_ELEM_PVT_H_
> > > > +#define _RING_HTS_ELEM_PVT_H_
> > > >
> > > >  /**
> > > >   * @file rte_ring_hts_c11_mem.h
> > > > @@ -161,4 +161,86 @@ __rte_ring_hts_move_cons_head(struct rte_ring
> > > *r, unsigned int num,
> > > >  	return n;
> > > >  }
> > > >
> > > > -#endif /* _RTE_RING_HTS_C11_MEM_H_ */
> > > > +/**
> > > > + * @internal Enqueue several objects on the HTS ring.
> > > > + *
> > > > + * @param r
> > > > + *   A pointer to the ring structure.
> > > > + * @param obj_table
> > > > + *   A pointer to a table of objects.
> > > > + * @param esize
> > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > + *   This must be the same value used while creating the ring. Otherwise
> > > > + *   the results are undefined.
> > > > + * @param n
> > > > + *   The number of objects to add in the ring from the obj_table.
> > > > + * @param behavior
> > > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > > ring
> > > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > > from ring
> > > > + * @param free_space
> > > > + *   returns the amount of space after the enqueue operation has finished
> > > > + * @return
> > > > + *   Actual number of objects enqueued.
> > > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> > > *obj_table,
> > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > +	uint32_t *free_space)
> > > > +{
> > > > +	uint32_t free, head;
> > > > +
> > > > +	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> > > > +
> > > > +	if (n != 0) {
> > > > +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > > +		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> > > > +	}
> > > > +
> > > > +	if (free_space != NULL)
> > > > +		*free_space = free - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +/**
> > > > + * @internal Dequeue several objects from the HTS ring.
> > > > + *
> > > > + * @param r
> > > > + *   A pointer to the ring structure.
> > > > + * @param obj_table
> > > > + *   A pointer to a table of objects.
> > > > + * @param esize
> > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > + *   This must be the same value used while creating the ring. Otherwise
> > > > + *   the results are undefined.
> > > > + * @param n
> > > > + *   The number of objects to pull from the ring.
> > > > + * @param behavior
> > > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > > ring
> > > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > > from ring
> > > > + * @param available
> > > > + *   returns the number of remaining ring entries after the dequeue has
> > > finished
> > > > + * @return
> > > > + *   - Actual number of objects dequeued.
> > > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > +	uint32_t *available)
> > > > +{
> > > > +	uint32_t entries, head;
> > > > +
> > > > +	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> > > &entries);
> > > > +
> > > > +	if (n != 0) {
> > > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > > +		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> > > > +	}
> > > > +
> > > > +	if (available != NULL)
> > > > +		*available = entries - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +#endif /* _RING_HTS_ELEM_PVT_H_ */
> > > > diff --git a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > > > b/lib/librte_ring/ring_peek_elem_pvt.h
> > > > similarity index 62%
> > > > rename from lib/librte_ring/rte_ring_peek_c11_mem.h
> > > > rename to lib/librte_ring/ring_peek_elem_pvt.h
> > > > index 283c7e70b..1c57bcdd6 100644
> > > > --- a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > > > +++ b/lib/librte_ring/ring_peek_elem_pvt.h
> > > > @@ -7,8 +7,8 @@
> > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > >   */
> > > >
> > > > -#ifndef _RTE_RING_PEEK_C11_MEM_H_
> > > > -#define _RTE_RING_PEEK_C11_MEM_H_
> > > > +#ifndef _RING_PEEK_ELEM_PVT_H_
> > > > +#define _RING_PEEK_ELEM_PVT_H_
> > > >
> > > >  /**
> > > >   * @file rte_ring_peek_c11_mem.h
> > > > @@ -107,4 +107,73 @@ __rte_ring_hts_set_head_tail(struct
> > > rte_ring_hts_headtail *ht, uint32_t tail,
> > > >  	__atomic_store_n(&ht->ht.raw, p.raw, __ATOMIC_RELEASE);  }
> > > >
> > > > -#endif /* _RTE_RING_PEEK_C11_MEM_H_ */
> > > > +/**
> > > > + * @internal This function moves prod head value.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > > > +		enum rte_ring_queue_behavior behavior, uint32_t
> > > *free_space) {
> > > > +	uint32_t free, head, next;
> > > > +
> > > > +	switch (r->prod.sync_type) {
> > > > +	case RTE_RING_SYNC_ST:
> > > > +		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> > > > +			behavior, &head, &next, &free);
> > > > +		break;
> > > > +	case RTE_RING_SYNC_MT_HTS:
> > > > +		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > > > +			&head, &free);
> > > > +		break;
> > > > +	case RTE_RING_SYNC_MT:
> > > > +	case RTE_RING_SYNC_MT_RTS:
> > > > +	default:
> > > > +		/* unsupported mode, shouldn't be here */
> > > > +		RTE_ASSERT(0);
> > > > +		n = 0;
> > > > +		free = 0;
> > > > +	}
> > > > +
> > > > +	if (free_space != NULL)
> > > > +		*free_space = free - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +/**
> > > > + * @internal This function moves cons head value and copies up to *n*
> > > > + * objects from the ring to the user provided obj_table.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > +	uint32_t *available)
> > > > +{
> > > > +	uint32_t avail, head, next;
> > > > +
> > > > +	switch (r->cons.sync_type) {
> > > > +	case RTE_RING_SYNC_ST:
> > > > +		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> > > > +			behavior, &head, &next, &avail);
> > > > +		break;
> > > > +	case RTE_RING_SYNC_MT_HTS:
> > > > +		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > > > +			&head, &avail);
> > > > +		break;
> > > > +	case RTE_RING_SYNC_MT:
> > > > +	case RTE_RING_SYNC_MT_RTS:
> > > > +	default:
> > > > +		/* unsupported mode, shouldn't be here */
> > > > +		RTE_ASSERT(0);
> > > > +		n = 0;
> > > > +		avail = 0;
> > > > +	}
> > > > +
> > > > +	if (n != 0)
> > > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > > +
> > > > +	if (available != NULL)
> > > > +		*available = avail - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +#endif /* _RING_PEEK_ELEM_PVT_H_ */
> > > > diff --git a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > > > b/lib/librte_ring/ring_rts_elem_pvt.h
> > > > similarity index 62%
> > > > rename from lib/librte_ring/rte_ring_rts_c11_mem.h
> > > > rename to lib/librte_ring/ring_rts_elem_pvt.h
> > > > index 327f22796..cbcec73eb 100644
> > > > --- a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > > > +++ b/lib/librte_ring/ring_rts_elem_pvt.h
> > > > @@ -7,8 +7,8 @@
> > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > >   */
> > > >
> > > > -#ifndef _RTE_RING_RTS_C11_MEM_H_
> > > > -#define _RTE_RING_RTS_C11_MEM_H_
> > > > +#ifndef _RING_RTS_ELEM_PVT_H_
> > > > +#define _RING_RTS_ELEM_PVT_H_
> > > >
> > > >  /**
> > > >   * @file rte_ring_rts_c11_mem.h
> > > > @@ -176,4 +176,86 @@ __rte_ring_rts_move_cons_head(struct rte_ring
> > > *r, uint32_t num,
> > > >  	return n;
> > > >  }
> > > >
> > > > -#endif /* _RTE_RING_RTS_C11_MEM_H_ */
> > > > +/**
> > > > + * @internal Enqueue several objects on the RTS ring.
> > > > + *
> > > > + * @param r
> > > > + *   A pointer to the ring structure.
> > > > + * @param obj_table
> > > > + *   A pointer to a table of objects.
> > > > + * @param esize
> > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > + *   This must be the same value used while creating the ring. Otherwise
> > > > + *   the results are undefined.
> > > > + * @param n
> > > > + *   The number of objects to add in the ring from the obj_table.
> > > > + * @param behavior
> > > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > > ring
> > > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > > from ring
> > > > + * @param free_space
> > > > + *   returns the amount of space after the enqueue operation has finished
> > > > + * @return
> > > > + *   Actual number of objects enqueued.
> > > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> > > *obj_table,
> > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > +	uint32_t *free_space)
> > > > +{
> > > > +	uint32_t free, head;
> > > > +
> > > > +	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> > > > +
> > > > +	if (n != 0) {
> > > > +		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > > +		__rte_ring_rts_update_tail(&r->rts_prod);
> > > > +	}
> > > > +
> > > > +	if (free_space != NULL)
> > > > +		*free_space = free - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +/**
> > > > + * @internal Dequeue several objects from the RTS ring.
> > > > + *
> > > > + * @param r
> > > > + *   A pointer to the ring structure.
> > > > + * @param obj_table
> > > > + *   A pointer to a table of objects.
> > > > + * @param esize
> > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > + *   This must be the same value used while creating the ring. Otherwise
> > > > + *   the results are undefined.
> > > > + * @param n
> > > > + *   The number of objects to pull from the ring.
> > > > + * @param behavior
> > > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > > ring
> > > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > > from ring
> > > > + * @param available
> > > > + *   returns the number of remaining ring entries after the dequeue has
> > > finished
> > > > + * @return
> > > > + *   - Actual number of objects dequeued.
> > > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > + */
> > > > +static __rte_always_inline unsigned int
> > > > +__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > +	uint32_t *available)
> > > > +{
> > > > +	uint32_t entries, head;
> > > > +
> > > > +	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> > > &entries);
> > > > +
> > > > +	if (n != 0) {
> > > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > > +		__rte_ring_rts_update_tail(&r->rts_cons);
> > > > +	}
> > > > +
> > > > +	if (available != NULL)
> > > > +		*available = entries - n;
> > > > +	return n;
> > > > +}
> > > > +
> > > > +#endif /* _RING_RTS_ELEM_PVT_H_ */
> > > > diff --git a/lib/librte_ring/rte_ring_elem.h
> > > > b/lib/librte_ring/rte_ring_elem.h index 57344d47d..119b5c0b6 100644
> > > > --- a/lib/librte_ring/rte_ring_elem.h
> > > > +++ b/lib/librte_ring/rte_ring_elem.h
> > > > @@ -21,6 +21,7 @@ extern "C" {
> > > >  #endif
> > > >
> > > >  #include <rte_ring_core.h>
> > > > +#include <ring_elem_pvt.h>
> > > >
> > > >  /**
> > > >   * Calculate the memory size needed for a ring with given element
> > > > size @@ -105,379 +106,6 @@ ssize_t
> > > rte_ring_get_memsize_elem(unsigned
> > > > int esize, unsigned int count);  struct rte_ring *rte_ring_create_elem(const
> > > char *name, unsigned int esize,
> > > >  			unsigned int count, int socket_id, unsigned int flags);
> > > >
> > > > -static __rte_always_inline void
> > > > -__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
> > > > -		uint32_t idx, const void *obj_table, uint32_t n)
> > > > -{
> > > > -	unsigned int i;
> > > > -	uint32_t *ring = (uint32_t *)&r[1];
> > > > -	const uint32_t *obj = (const uint32_t *)obj_table;
> > > > -	if (likely(idx + n < size)) {
> > > > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > -			ring[idx] = obj[i];
> > > > -			ring[idx + 1] = obj[i + 1];
> > > > -			ring[idx + 2] = obj[i + 2];
> > > > -			ring[idx + 3] = obj[i + 3];
> > > > -			ring[idx + 4] = obj[i + 4];
> > > > -			ring[idx + 5] = obj[i + 5];
> > > > -			ring[idx + 6] = obj[i + 6];
> > > > -			ring[idx + 7] = obj[i + 7];
> > > > -		}
> > > > -		switch (n & 0x7) {
> > > > -		case 7:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 6:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 5:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 4:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 3:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 2:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 1:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		}
> > > > -	} else {
> > > > -		for (i = 0; idx < size; i++, idx++)
> > > > -			ring[idx] = obj[i];
> > > > -		/* Start at the beginning */
> > > > -		for (idx = 0; i < n; i++, idx++)
> > > > -			ring[idx] = obj[i];
> > > > -	}
> > > > -}
> > > > -
> > > > -static __rte_always_inline void
> > > > -__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > > -		const void *obj_table, uint32_t n)
> > > > -{
> > > > -	unsigned int i;
> > > > -	const uint32_t size = r->size;
> > > > -	uint32_t idx = prod_head & r->mask;
> > > > -	uint64_t *ring = (uint64_t *)&r[1];
> > > > -	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> > > *)obj_table;
> > > > -	if (likely(idx + n < size)) {
> > > > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > -			ring[idx] = obj[i];
> > > > -			ring[idx + 1] = obj[i + 1];
> > > > -			ring[idx + 2] = obj[i + 2];
> > > > -			ring[idx + 3] = obj[i + 3];
> > > > -		}
> > > > -		switch (n & 0x3) {
> > > > -		case 3:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 2:
> > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > -		case 1:
> > > > -			ring[idx++] = obj[i++];
> > > > -		}
> > > > -	} else {
> > > > -		for (i = 0; idx < size; i++, idx++)
> > > > -			ring[idx] = obj[i];
> > > > -		/* Start at the beginning */
> > > > -		for (idx = 0; i < n; i++, idx++)
> > > > -			ring[idx] = obj[i];
> > > > -	}
> > > > -}
> > > > -
> > > > -static __rte_always_inline void
> > > > -__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > > -		const void *obj_table, uint32_t n)
> > > > -{
> > > > -	unsigned int i;
> > > > -	const uint32_t size = r->size;
> > > > -	uint32_t idx = prod_head & r->mask;
> > > > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > -	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > > > -	if (likely(idx + n < size)) {
> > > > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > -			memcpy((void *)(ring + idx),
> > > > -				(const void *)(obj + i), 32);
> > > > -		switch (n & 0x1) {
> > > > -		case 1:
> > > > -			memcpy((void *)(ring + idx),
> > > > -				(const void *)(obj + i), 16);
> > > > -		}
> > > > -	} else {
> > > > -		for (i = 0; idx < size; i++, idx++)
> > > > -			memcpy((void *)(ring + idx),
> > > > -				(const void *)(obj + i), 16);
> > > > -		/* Start at the beginning */
> > > > -		for (idx = 0; i < n; i++, idx++)
> > > > -			memcpy((void *)(ring + idx),
> > > > -				(const void *)(obj + i), 16);
> > > > -	}
> > > > -}
> > > > -
> > > > -/* the actual enqueue of elements on the ring.
> > > > - * Placed here since identical code needed in both
> > > > - * single and multi producer enqueue functions.
> > > > - */
> > > > -static __rte_always_inline void
> > > > -__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > > > -		const void *obj_table, uint32_t esize, uint32_t num)
> > > > -{
> > > > -	/* 8B and 16B copies implemented individually to retain
> > > > -	 * the current performance.
> > > > -	 */
> > > > -	if (esize == 8)
> > > > -		__rte_ring_enqueue_elems_64(r, prod_head, obj_table,
> > > num);
> > > > -	else if (esize == 16)
> > > > -		__rte_ring_enqueue_elems_128(r, prod_head, obj_table,
> > > num);
> > > > -	else {
> > > > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > -
> > > > -		/* Normalize to uint32_t */
> > > > -		scale = esize / sizeof(uint32_t);
> > > > -		nr_num = num * scale;
> > > > -		idx = prod_head & r->mask;
> > > > -		nr_idx = idx * scale;
> > > > -		nr_size = r->size * scale;
> > > > -		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > > > -				obj_table, nr_num);
> > > > -	}
> > > > -}
> > > > -
> > > > -static __rte_always_inline void
> > > > -__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
> > > > -		uint32_t idx, void *obj_table, uint32_t n)
> > > > -{
> > > > -	unsigned int i;
> > > > -	uint32_t *ring = (uint32_t *)&r[1];
> > > > -	uint32_t *obj = (uint32_t *)obj_table;
> > > > -	if (likely(idx + n < size)) {
> > > > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > -			obj[i] = ring[idx];
> > > > -			obj[i + 1] = ring[idx + 1];
> > > > -			obj[i + 2] = ring[idx + 2];
> > > > -			obj[i + 3] = ring[idx + 3];
> > > > -			obj[i + 4] = ring[idx + 4];
> > > > -			obj[i + 5] = ring[idx + 5];
> > > > -			obj[i + 6] = ring[idx + 6];
> > > > -			obj[i + 7] = ring[idx + 7];
> > > > -		}
> > > > -		switch (n & 0x7) {
> > > > -		case 7:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 6:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 5:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 4:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 3:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 2:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 1:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		}
> > > > -	} else {
> > > > -		for (i = 0; idx < size; i++, idx++)
> > > > -			obj[i] = ring[idx];
> > > > -		/* Start at the beginning */
> > > > -		for (idx = 0; i < n; i++, idx++)
> > > > -			obj[i] = ring[idx];
> > > > -	}
> > > > -}
> > > > -
> > > > -static __rte_always_inline void
> > > > -__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
> > > > -		void *obj_table, uint32_t n)
> > > > -{
> > > > -	unsigned int i;
> > > > -	const uint32_t size = r->size;
> > > > -	uint32_t idx = prod_head & r->mask;
> > > > -	uint64_t *ring = (uint64_t *)&r[1];
> > > > -	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > > > -	if (likely(idx + n < size)) {
> > > > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > -			obj[i] = ring[idx];
> > > > -			obj[i + 1] = ring[idx + 1];
> > > > -			obj[i + 2] = ring[idx + 2];
> > > > -			obj[i + 3] = ring[idx + 3];
> > > > -		}
> > > > -		switch (n & 0x3) {
> > > > -		case 3:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 2:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		case 1:
> > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > -		}
> > > > -	} else {
> > > > -		for (i = 0; idx < size; i++, idx++)
> > > > -			obj[i] = ring[idx];
> > > > -		/* Start at the beginning */
> > > > -		for (idx = 0; i < n; i++, idx++)
> > > > -			obj[i] = ring[idx];
> > > > -	}
> > > > -}
> > > > -
> > > > -static __rte_always_inline void
> > > > -__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
> > > > -		void *obj_table, uint32_t n)
> > > > -{
> > > > -	unsigned int i;
> > > > -	const uint32_t size = r->size;
> > > > -	uint32_t idx = prod_head & r->mask;
> > > > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > -	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > > > -	if (likely(idx + n < size)) {
> > > > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> > > > -		switch (n & 0x1) {
> > > > -		case 1:
> > > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > > -		}
> > > > -	} else {
> > > > -		for (i = 0; idx < size; i++, idx++)
> > > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > > -		/* Start at the beginning */
> > > > -		for (idx = 0; i < n; i++, idx++)
> > > > -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> > > > -	}
> > > > -}
> > > > -
> > > > -/* the actual dequeue of elements from the ring.
> > > > - * Placed here since identical code needed in both
> > > > - * single and multi producer enqueue functions.
> > > > - */
> > > > -static __rte_always_inline void
> > > > -__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > > > -		void *obj_table, uint32_t esize, uint32_t num)
> > > > -{
> > > > -	/* 8B and 16B copies implemented individually to retain
> > > > -	 * the current performance.
> > > > -	 */
> > > > -	if (esize == 8)
> > > > -		__rte_ring_dequeue_elems_64(r, cons_head, obj_table,
> > > num);
> > > > -	else if (esize == 16)
> > > > -		__rte_ring_dequeue_elems_128(r, cons_head, obj_table,
> > > num);
> > > > -	else {
> > > > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > -
> > > > -		/* Normalize to uint32_t */
> > > > -		scale = esize / sizeof(uint32_t);
> > > > -		nr_num = num * scale;
> > > > -		idx = cons_head & r->mask;
> > > > -		nr_idx = idx * scale;
> > > > -		nr_size = r->size * scale;
> > > > -		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > > > -				obj_table, nr_num);
> > > > -	}
> > > > -}
> > > > -
> > > > -/* Between load and load. there might be cpu reorder in weak model
> > > > - * (powerpc/arm).
> > > > - * There are 2 choices for the users
> > > > - * 1.use rmb() memory barrier
> > > > - * 2.use one-direction load_acquire/store_release barrier
> > > > - * It depends on performance test results.
> > > > - * By default, move common functions to rte_ring_generic.h
> > > > - */
> > > > -#ifdef RTE_USE_C11_MEM_MODEL
> > > > -#include "rte_ring_c11_mem.h"
> > > > -#else
> > > > -#include "rte_ring_generic.h"
> > > > -#endif
> > > > -
> > > > -/**
> > > > - * @internal Enqueue several objects on the ring
> > > > - *
> > > > - * @param r
> > > > - *   A pointer to the ring structure.
> > > > - * @param obj_table
> > > > - *   A pointer to a table of objects.
> > > > - * @param esize
> > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > - *   This must be the same value used while creating the ring. Otherwise
> > > > - *   the results are undefined.
> > > > - * @param n
> > > > - *   The number of objects to add in the ring from the obj_table.
> > > > - * @param behavior
> > > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > > ring
> > > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > > from ring
> > > > - * @param is_sp
> > > > - *   Indicates whether to use single producer or multi-producer head
> > > update
> > > > - * @param free_space
> > > > - *   returns the amount of space after the enqueue operation has finished
> > > > - * @return
> > > > - *   Actual number of objects enqueued.
> > > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
> > > > -		unsigned int esize, unsigned int n,
> > > > -		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
> > > > -		unsigned int *free_space)
> > > > -{
> > > > -	uint32_t prod_head, prod_next;
> > > > -	uint32_t free_entries;
> > > > -
> > > > -	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > > > -			&prod_head, &prod_next, &free_entries);
> > > > -	if (n == 0)
> > > > -		goto end;
> > > > -
> > > > -	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
> > > > -
> > > > -	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
> > > > -end:
> > > > -	if (free_space != NULL)
> > > > -		*free_space = free_entries - n;
> > > > -	return n;
> > > > -}
> > > > -
> > > > -/**
> > > > - * @internal Dequeue several objects from the ring
> > > > - *
> > > > - * @param r
> > > > - *   A pointer to the ring structure.
> > > > - * @param obj_table
> > > > - *   A pointer to a table of objects.
> > > > - * @param esize
> > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > - *   This must be the same value used while creating the ring. Otherwise
> > > > - *   the results are undefined.
> > > > - * @param n
> > > > - *   The number of objects to pull from the ring.
> > > > - * @param behavior
> > > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > > ring
> > > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > > from ring
> > > > - * @param is_sc
> > > > - *   Indicates whether to use single consumer or multi-consumer head
> > > update
> > > > - * @param available
> > > > - *   returns the number of remaining ring entries after the dequeue has
> > > finished
> > > > - * @return
> > > > - *   - Actual number of objects dequeued.
> > > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > -		unsigned int esize, unsigned int n,
> > > > -		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
> > > > -		unsigned int *available)
> > > > -{
> > > > -	uint32_t cons_head, cons_next;
> > > > -	uint32_t entries;
> > > > -
> > > > -	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > > > -			&cons_head, &cons_next, &entries);
> > > > -	if (n == 0)
> > > > -		goto end;
> > > > -
> > > > -	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
> > > > -
> > > > -	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
> > > > -
> > > > -end:
> > > > -	if (available != NULL)
> > > > -		*available = entries - n;
> > > > -	return n;
> > > > -}
> > > > -
> > > >  /**
> > > >   * Enqueue several objects on the ring (multi-producers safe).
> > > >   *
> > > > diff --git a/lib/librte_ring/rte_ring_hts.h
> > > > b/lib/librte_ring/rte_ring_hts.h index 359b15771..bdbdafc9f 100644
> > > > --- a/lib/librte_ring/rte_ring_hts.h
> > > > +++ b/lib/librte_ring/rte_ring_hts.h
> > > > @@ -29,89 +29,7 @@
> > > >  extern "C" {
> > > >  #endif
> > > >
> > > > -#include <rte_ring_hts_c11_mem.h>
> > > > -
> > > > -/**
> > > > - * @internal Enqueue several objects on the HTS ring.
> > > > - *
> > > > - * @param r
> > > > - *   A pointer to the ring structure.
> > > > - * @param obj_table
> > > > - *   A pointer to a table of objects.
> > > > - * @param esize
> > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > - *   This must be the same value used while creating the ring. Otherwise
> > > > - *   the results are undefined.
> > > > - * @param n
> > > > - *   The number of objects to add in the ring from the obj_table.
> > > > - * @param behavior
> > > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > > ring
> > > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > > from ring
> > > > - * @param free_space
> > > > - *   returns the amount of space after the enqueue operation has finished
> > > > - * @return
> > > > - *   Actual number of objects enqueued.
> > > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> > > *obj_table,
> > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > -	uint32_t *free_space)
> > > > -{
> > > > -	uint32_t free, head;
> > > > -
> > > > -	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
> > > > -
> > > > -	if (n != 0) {
> > > > -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > > -		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
> > > > -	}
> > > > -
> > > > -	if (free_space != NULL)
> > > > -		*free_space = free - n;
> > > > -	return n;
> > > > -}
> > > > -
> > > > -/**
> > > > - * @internal Dequeue several objects from the HTS ring.
> > > > - *
> > > > - * @param r
> > > > - *   A pointer to the ring structure.
> > > > - * @param obj_table
> > > > - *   A pointer to a table of objects.
> > > > - * @param esize
> > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > - *   This must be the same value used while creating the ring. Otherwise
> > > > - *   the results are undefined.
> > > > - * @param n
> > > > - *   The number of objects to pull from the ring.
> > > > - * @param behavior
> > > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > > ring
> > > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > > from ring
> > > > - * @param available
> > > > - *   returns the number of remaining ring entries after the dequeue has
> > > finished
> > > > - * @return
> > > > - *   - Actual number of objects dequeued.
> > > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > -	uint32_t *available)
> > > > -{
> > > > -	uint32_t entries, head;
> > > > -
> > > > -	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> > > &entries);
> > > > -
> > > > -	if (n != 0) {
> > > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > > -		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
> > > > -	}
> > > > -
> > > > -	if (available != NULL)
> > > > -		*available = entries - n;
> > > > -	return n;
> > > > -}
> > > > +#include <ring_hts_elem_pvt.h>
> > > >
> > > >  /**
> > > >   * Enqueue several objects on the HTS ring (multi-producers safe).
> > > > diff --git a/lib/librte_ring/rte_ring_peek.h
> > > > b/lib/librte_ring/rte_ring_peek.h index 45f707dc7..0dd402be4 100644
> > > > --- a/lib/librte_ring/rte_ring_peek.h
> > > > +++ b/lib/librte_ring/rte_ring_peek.h
> > > > @@ -48,39 +48,7 @@
> > > >  extern "C" {
> > > >  #endif
> > > >
> > > > -#include <rte_ring_peek_c11_mem.h>
> > > > -
> > > > -/**
> > > > - * @internal This function moves prod head value.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > > > -		enum rte_ring_queue_behavior behavior, uint32_t
> > > *free_space)
> > > > -{
> > > > -	uint32_t free, head, next;
> > > > -
> > > > -	switch (r->prod.sync_type) {
> > > > -	case RTE_RING_SYNC_ST:
> > > > -		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
> > > > -			behavior, &head, &next, &free);
> > > > -		break;
> > > > -	case RTE_RING_SYNC_MT_HTS:
> > > > -		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > > > -			&head, &free);
> > > > -		break;
> > > > -	case RTE_RING_SYNC_MT:
> > > > -	case RTE_RING_SYNC_MT_RTS:
> > > > -	default:
> > > > -		/* unsupported mode, shouldn't be here */
> > > > -		RTE_ASSERT(0);
> > > > -		n = 0;
> > > > -		free = 0;
> > > > -	}
> > > > -
> > > > -	if (free_space != NULL)
> > > > -		*free_space = free - n;
> > > > -	return n;
> > > > -}
> > > > +#include <ring_peek_elem_pvt.h>
> > > >
> > > >  /**
> > > >   * Start to enqueue several objects on the ring.
> > > > @@ -248,43 +216,6 @@ rte_ring_enqueue_finish(struct rte_ring *r, void *
> > > const *obj_table,
> > > >  	rte_ring_enqueue_elem_finish(r, obj_table, sizeof(uintptr_t), n);  }
> > > >
> > > > -/**
> > > > - * @internal This function moves cons head value and copies up to *n*
> > > > - * objects from the ring to the user provided obj_table.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > -	uint32_t *available)
> > > > -{
> > > > -	uint32_t avail, head, next;
> > > > -
> > > > -	switch (r->cons.sync_type) {
> > > > -	case RTE_RING_SYNC_ST:
> > > > -		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
> > > > -			behavior, &head, &next, &avail);
> > > > -		break;
> > > > -	case RTE_RING_SYNC_MT_HTS:
> > > > -		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > > > -			&head, &avail);
> > > > -		break;
> > > > -	case RTE_RING_SYNC_MT:
> > > > -	case RTE_RING_SYNC_MT_RTS:
> > > > -	default:
> > > > -		/* unsupported mode, shouldn't be here */
> > > > -		RTE_ASSERT(0);
> > > > -		n = 0;
> > > > -		avail = 0;
> > > > -	}
> > > > -
> > > > -	if (n != 0)
> > > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > > -
> > > > -	if (available != NULL)
> > > > -		*available = avail - n;
> > > > -	return n;
> > > > -}
> > > > -
> > > >  /**
> > > >   * Start to dequeue several objects from the ring.
> > > >   * Note that user has to call appropriate dequeue_finish() diff --git
> > > > a/lib/librte_ring/rte_ring_peek_zc.h
> > > > b/lib/librte_ring/rte_ring_peek_zc.h
> > > > index cb3bbd067..bc8252a18 100644
> > > > --- a/lib/librte_ring/rte_ring_peek_zc.h
> > > > +++ b/lib/librte_ring/rte_ring_peek_zc.h
> > > > @@ -72,7 +72,7 @@
> > > >  extern "C" {
> > > >  #endif
> > > >
> > > > -#include <rte_ring_peek_c11_mem.h>
> > > > +#include <ring_peek_elem_pvt.h>
> > > >
> > > >  /**
> > > >   * Ring zero-copy information structure.
> > > > diff --git a/lib/librte_ring/rte_ring_rts.h
> > > > b/lib/librte_ring/rte_ring_rts.h index afc12abe2..83d9903e2 100644
> > > > --- a/lib/librte_ring/rte_ring_rts.h
> > > > +++ b/lib/librte_ring/rte_ring_rts.h
> > > > @@ -56,89 +56,7 @@
> > > >  extern "C" {
> > > >  #endif
> > > >
> > > > -#include <rte_ring_rts_c11_mem.h>
> > > > -
> > > > -/**
> > > > - * @internal Enqueue several objects on the RTS ring.
> > > > - *
> > > > - * @param r
> > > > - *   A pointer to the ring structure.
> > > > - * @param obj_table
> > > > - *   A pointer to a table of objects.
> > > > - * @param esize
> > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > - *   This must be the same value used while creating the ring. Otherwise
> > > > - *   the results are undefined.
> > > > - * @param n
> > > > - *   The number of objects to add in the ring from the obj_table.
> > > > - * @param behavior
> > > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a
> > > ring
> > > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible
> > > from ring
> > > > - * @param free_space
> > > > - *   returns the amount of space after the enqueue operation has finished
> > > > - * @return
> > > > - *   Actual number of objects enqueued.
> > > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> > > *obj_table,
> > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > -	uint32_t *free_space)
> > > > -{
> > > > -	uint32_t free, head;
> > > > -
> > > > -	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
> > > > -
> > > > -	if (n != 0) {
> > > > -		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
> > > > -		__rte_ring_rts_update_tail(&r->rts_prod);
> > > > -	}
> > > > -
> > > > -	if (free_space != NULL)
> > > > -		*free_space = free - n;
> > > > -	return n;
> > > > -}
> > > > -
> > > > -/**
> > > > - * @internal Dequeue several objects from the RTS ring.
> > > > - *
> > > > - * @param r
> > > > - *   A pointer to the ring structure.
> > > > - * @param obj_table
> > > > - *   A pointer to a table of objects.
> > > > - * @param esize
> > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > - *   This must be the same value used while creating the ring. Otherwise
> > > > - *   the results are undefined.
> > > > - * @param n
> > > > - *   The number of objects to pull from the ring.
> > > > - * @param behavior
> > > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a
> > > ring
> > > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible
> > > from ring
> > > > - * @param available
> > > > - *   returns the number of remaining ring entries after the dequeue has
> > > finished
> > > > - * @return
> > > > - *   - Actual number of objects dequeued.
> > > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > - */
> > > > -static __rte_always_inline unsigned int
> > > > -__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
> > > > -	uint32_t *available)
> > > > -{
> > > > -	uint32_t entries, head;
> > > > -
> > > > -	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> > > &entries);
> > > > -
> > > > -	if (n != 0) {
> > > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
> > > > -		__rte_ring_rts_update_tail(&r->rts_cons);
> > > > -	}
> > > > -
> > > > -	if (available != NULL)
> > > > -		*available = entries - n;
> > > > -	return n;
> > > > -}
> > > > +#include <ring_rts_elem_pvt.h>
> > > >
> > > >  /**
> > > >   * Enqueue several objects on the RTS ring (multi-producers safe).
> > > > --
> > > > 2.17.1
Feifei Wang Jan. 26, 2021, 3:41 a.m. UTC | #5
Hi, Konstantin

> -----邮件原件-----
> 发件人: Ananyev, Konstantin <konstantin.ananyev@intel.com>
> 发送时间: 2021年1月25日 18:29
> 收件人: Ananyev, Konstantin <konstantin.ananyev@intel.com>; Feifei Wang
> <Feifei.Wang2@arm.com>; Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>
> 抄送: dev@dpdk.org; nd <nd@arm.com>; nd <nd@arm.com>
> 主题: RE: [PATCH v1 3/3] ring: rename and refactor ring library
> 
> 
> 
> >
> > Hi Feifei,
> >
> > > > > For legacy modes, rename ring_generic/c11 to ring_generic/c11_pvt.
> > > > > Furthermore, add new file ring_elem_pvt.h which includes
> > > > > ring_do_eq/deq and ring element copy/delete APIs.
> > > > >
> > > > > For other modes, rename xx_c11_mem to xx_elem_pvt. Move all
> private
> > > > > APIs into these new header files.
> > > > >
> > > > > Suggested-by: Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>
> > > > > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > > > > Reviewed-by: Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>
> > > > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > > > ---
> > > > >  lib/librte_ring/meson.build                   |  15 +-
> > > > >  .../{rte_ring_c11_mem.h => ring_c11_pvt.h}    |   9 +-
> > > > >  lib/librte_ring/ring_elem_pvt.h               | 385 ++++++++++++++++++
> > > > >  ...{rte_ring_generic.h => ring_generic_pvt.h} |   6 +-
> > > > >  ...ring_hts_c11_mem.h => ring_hts_elem_pvt.h} |  88 +++-
> > > > > ...ng_peek_c11_mem.h => ring_peek_elem_pvt.h} |  75 +++-
> > > > > ...ring_rts_c11_mem.h => ring_rts_elem_pvt.h} |  88 +++-
> > > > >  lib/librte_ring/rte_ring_elem.h               | 374 +----------------
> > > > >  lib/librte_ring/rte_ring_hts.h                |  84 +---
> > > > >  lib/librte_ring/rte_ring_peek.h               |  71 +---
> > > > >  lib/librte_ring/rte_ring_peek_zc.h            |   2 +-
> > > > >  lib/librte_ring/rte_ring_rts.h                |  84 +---
> > > > >  12 files changed, 646 insertions(+), 635 deletions(-)  rename
> > > > > lib/librte_ring/{rte_ring_c11_mem.h => ring_c11_pvt.h} (96%)  create
> > > > > mode 100644 lib/librte_ring/ring_elem_pvt.h  rename
> > > > > lib/librte_ring/{rte_ring_generic.h => ring_generic_pvt.h} (98%)
> > > > > rename lib/librte_ring/{rte_ring_hts_c11_mem.h =>
> ring_hts_elem_pvt.h}
> > > > > (60%)  rename lib/librte_ring/{rte_ring_peek_c11_mem.h =>
> > > > > ring_peek_elem_pvt.h} (62%)  rename
> > > > > lib/librte_ring/{rte_ring_rts_c11_mem.h => ring_rts_elem_pvt.h}
> (62%)
> > > > >
> > > >
> > > > Sorry, but I don't understand the purpose of that patch.
> > > > As I remember by DPDK naming convention all installable headers
> should
> > > > have 'rte_' prefix. Same for public defines (RTE_).
> > > > Why to abandon it here?
> > >
> > > This change refers to you and Honnappa's discussion about ring:
> > > https://mails.dpdk.org/archives/dev/2020-May/166803.html
> > >
> > > And it is to separate the external APIs that can be called by users,
> > > from internal APIs that cannot be called by users.
> > > The internal functions are included in the files with xx_pvt.h.
> >
> > Even these xx_pvt.h files contain internal API and not supposed to be
> included directly,
> > they have to be installed into public dir (<dpdk-install-dir/include).
> > So I think we need to keep DPDK public prefixes for them (and inside
> them):
> > rte_xx_pvt.h (_RTE_).
> 
> As another thought - it is probably good to introduce new generic naming
> convention
> for such sort of files (internal ones that still have to be exposed).
> Might be '_rte_' prefix or so...
> Though I suppose it would require broader discussion first.
> 

Thanks very much for your comments. According to this, I think maybe we can only
separate the external APIs from internal APIs in this patch and keep DPDK public prefixes
for this files. Thus, though these private files can be exposed, the "xx__pvt" suffix can remind
users not to use them.

On the other side, for new generic naming convention, we can leave it for later discussion.

Best Regards
Feifei
> >
> > Konstantin
> >
> > >
> > > Best Regards
> > > Feifei
> > > >
> > > > > diff --git a/lib/librte_ring/meson.build b/lib/librte_ring/meson.build
> > > > > index 36fdcb6a5..98eac5810 100644
> > > > > --- a/lib/librte_ring/meson.build
> > > > > +++ b/lib/librte_ring/meson.build
> > > > > @@ -2,15 +2,16 @@
> > > > >  # Copyright(c) 2017 Intel Corporation
> > > > >
> > > > >  sources = files('rte_ring.c')
> > > > > -headers = files('rte_ring.h',
> > > > > +headers = files('ring_c11_pvt.h',
> > > > > +		'ring_elem_pvt.h',
> > > > > +		'ring_generic_pvt.h',
> > > > > +		'ring_hts_elem_pvt.h',
> > > > > +		'ring_peek_elem_pvt.h',
> > > > > +		'ring_rts_elem_pvt.h',
> > > > > +		'rte_ring.h',
> > > > >  		'rte_ring_core.h',
> > > > >  		'rte_ring_elem.h',
> > > > > -		'rte_ring_c11_mem.h',
> > > > > -		'rte_ring_generic.h',
> > > > >  		'rte_ring_hts.h',
> > > > > -		'rte_ring_hts_c11_mem.h',
> > > > >  		'rte_ring_peek.h',
> > > > > -		'rte_ring_peek_c11_mem.h',
> > > > >  		'rte_ring_peek_zc.h',
> > > > > -		'rte_ring_rts.h',
> > > > > -		'rte_ring_rts_c11_mem.h')
> > > > > +		'rte_ring_rts.h')
> > > > > diff --git a/lib/librte_ring/rte_ring_c11_mem.h
> > > > > b/lib/librte_ring/ring_c11_pvt.h similarity index 96% rename from
> > > > > lib/librte_ring/rte_ring_c11_mem.h
> > > > > rename to lib/librte_ring/ring_c11_pvt.h index 7f5eba262..9f2f5318f
> > > > > 100644
> > > > > --- a/lib/librte_ring/rte_ring_c11_mem.h
> > > > > +++ b/lib/librte_ring/ring_c11_pvt.h
> > > > > @@ -7,8 +7,8 @@
> > > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > > >   */
> > > > >
> > > > > -#ifndef _RTE_RING_C11_MEM_H_
> > > > > -#define _RTE_RING_C11_MEM_H_
> > > > > +#ifndef _RING_C11_PVT_H_
> > > > > +#define _RING_C11_PVT_H_
> > > > >
> > > > >  static __rte_always_inline void
> > > > >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > > > > old_val, @@ -69,9 +69,6 @@ __rte_ring_move_prod_head(struct
> rte_ring
> > > > *r, unsigned int is_sp,
> > > > >  		/* Ensure the head is read before tail */
> > > > >  		__atomic_thread_fence(__ATOMIC_ACQUIRE);
> > > > >
> > > > > -		/* load-acquire synchronize with store-release of ht-
> >tail
> > > > > -		 * in update_tail.
> > > > > -		 */
> > > > >  		cons_tail = __atomic_load_n(&r->cons.tail,
> > > > >  					__ATOMIC_ACQUIRE);
> > > > >
> > > > > @@ -178,4 +175,4 @@ __rte_ring_move_cons_head(struct rte_ring
> *r, int
> > > > is_sc,
> > > > >  	return n;
> > > > >  }
> > > > >
> > > > > -#endif /* _RTE_RING_C11_MEM_H_ */
> > > > > +#endif /* _RING_C11_PVT_H_ */
> > > > > diff --git a/lib/librte_ring/ring_elem_pvt.h
> > > > > b/lib/librte_ring/ring_elem_pvt.h new file mode 100644 index
> > > > > 000000000..8003e5edc
> > > > > --- /dev/null
> > > > > +++ b/lib/librte_ring/ring_elem_pvt.h
> > > > > @@ -0,0 +1,385 @@
> > > > > +/* SPDX-License-Identifier: BSD-3-Clause
> > > > > + *
> > > > > + * Copyright (c) 2017,2018 HXT-semitech Corporation.
> > > > > + * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
> > > > > + * All rights reserved.
> > > > > + * Derived from FreeBSD's bufring.h
> > > > > + * Used as BSD-3 Licensed with permission from Kip Macy.
> > > > > + */
> > > > > +
> > > > > +#ifndef _RING_ELEM_PVT_H_
> > > > > +#define _RING_ELEM_PVT_H_
> > > > > +
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t
> size,
> > > > > +		uint32_t idx, const void *obj_table, uint32_t n) {
> > > > > +	unsigned int i;
> > > > > +	uint32_t *ring = (uint32_t *)&r[1];
> > > > > +	const uint32_t *obj = (const uint32_t *)obj_table;
> > > > > +	if (likely(idx + n < size)) {
> > > > > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > > +			ring[idx] = obj[i];
> > > > > +			ring[idx + 1] = obj[i + 1];
> > > > > +			ring[idx + 2] = obj[i + 2];
> > > > > +			ring[idx + 3] = obj[i + 3];
> > > > > +			ring[idx + 4] = obj[i + 4];
> > > > > +			ring[idx + 5] = obj[i + 5];
> > > > > +			ring[idx + 6] = obj[i + 6];
> > > > > +			ring[idx + 7] = obj[i + 7];
> > > > > +		}
> > > > > +		switch (n & 0x7) {
> > > > > +		case 7:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 6:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 5:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 4:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 3:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 2:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 1:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		}
> > > > > +	} else {
> > > > > +		for (i = 0; idx < size; i++, idx++)
> > > > > +			ring[idx] = obj[i];
> > > > > +		/* Start at the beginning */
> > > > > +		for (idx = 0; i < n; i++, idx++)
> > > > > +			ring[idx] = obj[i];
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t
> prod_head,
> > > > > +		const void *obj_table, uint32_t n)
> > > > > +{
> > > > > +	unsigned int i;
> > > > > +	const uint32_t size = r->size;
> > > > > +	uint32_t idx = prod_head & r->mask;
> > > > > +	uint64_t *ring = (uint64_t *)&r[1];
> > > > > +	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> > > > *)obj_table;
> > > > > +	if (likely(idx + n < size)) {
> > > > > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > > +			ring[idx] = obj[i];
> > > > > +			ring[idx + 1] = obj[i + 1];
> > > > > +			ring[idx + 2] = obj[i + 2];
> > > > > +			ring[idx + 3] = obj[i + 3];
> > > > > +		}
> > > > > +		switch (n & 0x3) {
> > > > > +		case 3:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 2:
> > > > > +			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > +		case 1:
> > > > > +			ring[idx++] = obj[i++];
> > > > > +		}
> > > > > +	} else {
> > > > > +		for (i = 0; idx < size; i++, idx++)
> > > > > +			ring[idx] = obj[i];
> > > > > +		/* Start at the beginning */
> > > > > +		for (idx = 0; i < n; i++, idx++)
> > > > > +			ring[idx] = obj[i];
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t
> prod_head,
> > > > > +		const void *obj_table, uint32_t n)
> > > > > +{
> > > > > +	unsigned int i;
> > > > > +	const uint32_t size = r->size;
> > > > > +	uint32_t idx = prod_head & r->mask;
> > > > > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > > +	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > > > > +	if (likely(idx + n < size)) {
> > > > > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > > +			memcpy((void *)(ring + idx),
> > > > > +				(const void *)(obj + i), 32);
> > > > > +		switch (n & 0x1) {
> > > > > +		case 1:
> > > > > +			memcpy((void *)(ring + idx),
> > > > > +				(const void *)(obj + i), 16);
> > > > > +		}
> > > > > +	} else {
> > > > > +		for (i = 0; idx < size; i++, idx++)
> > > > > +			memcpy((void *)(ring + idx),
> > > > > +				(const void *)(obj + i), 16);
> > > > > +		/* Start at the beginning */
> > > > > +		for (idx = 0; i < n; i++, idx++)
> > > > > +			memcpy((void *)(ring + idx),
> > > > > +				(const void *)(obj + i), 16);
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +/* the actual enqueue of elements on the ring.
> > > > > + * Placed here since identical code needed in both
> > > > > + * single and multi producer enqueue functions.
> > > > > + */
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > > > > +		const void *obj_table, uint32_t esize, uint32_t num) {
> > > > > +	/* 8B and 16B copies implemented individually to retain
> > > > > +	 * the current performance.
> > > > > +	 */
> > > > > +	if (esize == 8)
> > > > > +		__rte_ring_enqueue_elems_64(r, prod_head,
> obj_table,
> > > > num);
> > > > > +	else if (esize == 16)
> > > > > +		__rte_ring_enqueue_elems_128(r, prod_head,
> obj_table,
> > > > num);
> > > > > +	else {
> > > > > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > > +
> > > > > +		/* Normalize to uint32_t */
> > > > > +		scale = esize / sizeof(uint32_t);
> > > > > +		nr_num = num * scale;
> > > > > +		idx = prod_head & r->mask;
> > > > > +		nr_idx = idx * scale;
> > > > > +		nr_size = r->size * scale;
> > > > > +		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > > > > +				obj_table, nr_num);
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t
> size,
> > > > > +		uint32_t idx, void *obj_table, uint32_t n) {
> > > > > +	unsigned int i;
> > > > > +	uint32_t *ring = (uint32_t *)&r[1];
> > > > > +	uint32_t *obj = (uint32_t *)obj_table;
> > > > > +	if (likely(idx + n < size)) {
> > > > > +		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > > +			obj[i] = ring[idx];
> > > > > +			obj[i + 1] = ring[idx + 1];
> > > > > +			obj[i + 2] = ring[idx + 2];
> > > > > +			obj[i + 3] = ring[idx + 3];
> > > > > +			obj[i + 4] = ring[idx + 4];
> > > > > +			obj[i + 5] = ring[idx + 5];
> > > > > +			obj[i + 6] = ring[idx + 6];
> > > > > +			obj[i + 7] = ring[idx + 7];
> > > > > +		}
> > > > > +		switch (n & 0x7) {
> > > > > +		case 7:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 6:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 5:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 4:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 3:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 2:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 1:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		}
> > > > > +	} else {
> > > > > +		for (i = 0; idx < size; i++, idx++)
> > > > > +			obj[i] = ring[idx];
> > > > > +		/* Start at the beginning */
> > > > > +		for (idx = 0; i < n; i++, idx++)
> > > > > +			obj[i] = ring[idx];
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t
> prod_head,
> > > > > +		void *obj_table, uint32_t n)
> > > > > +{
> > > > > +	unsigned int i;
> > > > > +	const uint32_t size = r->size;
> > > > > +	uint32_t idx = prod_head & r->mask;
> > > > > +	uint64_t *ring = (uint64_t *)&r[1];
> > > > > +	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > > > > +	if (likely(idx + n < size)) {
> > > > > +		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > > +			obj[i] = ring[idx];
> > > > > +			obj[i + 1] = ring[idx + 1];
> > > > > +			obj[i + 2] = ring[idx + 2];
> > > > > +			obj[i + 3] = ring[idx + 3];
> > > > > +		}
> > > > > +		switch (n & 0x3) {
> > > > > +		case 3:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 2:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		case 1:
> > > > > +			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > +		}
> > > > > +	} else {
> > > > > +		for (i = 0; idx < size; i++, idx++)
> > > > > +			obj[i] = ring[idx];
> > > > > +		/* Start at the beginning */
> > > > > +		for (idx = 0; i < n; i++, idx++)
> > > > > +			obj[i] = ring[idx];
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t
> prod_head,
> > > > > +		void *obj_table, uint32_t n)
> > > > > +{
> > > > > +	unsigned int i;
> > > > > +	const uint32_t size = r->size;
> > > > > +	uint32_t idx = prod_head & r->mask;
> > > > > +	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > > +	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > > > > +	if (likely(idx + n < size)) {
> > > > > +		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > > +			memcpy((void *)(obj + i), (void *)(ring + idx),
> 32);
> > > > > +		switch (n & 0x1) {
> > > > > +		case 1:
> > > > > +			memcpy((void *)(obj + i), (void *)(ring + idx),
> 16);
> > > > > +		}
> > > > > +	} else {
> > > > > +		for (i = 0; idx < size; i++, idx++)
> > > > > +			memcpy((void *)(obj + i), (void *)(ring + idx),
> 16);
> > > > > +		/* Start at the beginning */
> > > > > +		for (idx = 0; i < n; i++, idx++)
> > > > > +			memcpy((void *)(obj + i), (void *)(ring + idx),
> 16);
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +/* the actual dequeue of elements from the ring.
> > > > > + * Placed here since identical code needed in both
> > > > > + * single and multi producer enqueue functions.
> > > > > + */
> > > > > +static __rte_always_inline void
> > > > > +__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > > > > +		void *obj_table, uint32_t esize, uint32_t num) {
> > > > > +	/* 8B and 16B copies implemented individually to retain
> > > > > +	 * the current performance.
> > > > > +	 */
> > > > > +	if (esize == 8)
> > > > > +		__rte_ring_dequeue_elems_64(r, cons_head,
> obj_table,
> > > > num);
> > > > > +	else if (esize == 16)
> > > > > +		__rte_ring_dequeue_elems_128(r, cons_head,
> obj_table,
> > > > num);
> > > > > +	else {
> > > > > +		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > > +
> > > > > +		/* Normalize to uint32_t */
> > > > > +		scale = esize / sizeof(uint32_t);
> > > > > +		nr_num = num * scale;
> > > > > +		idx = cons_head & r->mask;
> > > > > +		nr_idx = idx * scale;
> > > > > +		nr_size = r->size * scale;
> > > > > +		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > > > > +				obj_table, nr_num);
> > > > > +	}
> > > > > +}
> > > > > +
> > > > > +/* Between load and load. there might be cpu reorder in weak
> model
> > > > > + * (powerpc/arm).
> > > > > + * There are 2 choices for the users
> > > > > + * 1.use rmb() memory barrier
> > > > > + * 2.use one-direction load_acquire/store_release barrier
> > > > > + * It depends on performance test results.
> > > > > + */
> > > > > +#ifdef RTE_USE_C11_MEM_MODEL
> > > > > +#include "ring_c11_pvt.h"
> > > > > +#else
> > > > > +#include "ring_generic_pvt.h"
> > > > > +#endif
> > > > > +
> > > > > +/**
> > > > > + * @internal Enqueue several objects on the ring
> > > > > + *
> > > > > + * @param r
> > > > > + *   A pointer to the ring structure.
> > > > > + * @param obj_table
> > > > > + *   A pointer to a table of objects.
> > > > > + * @param esize
> > > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > + *   This must be the same value used while creating the ring.
> Otherwise
> > > > > + *   the results are undefined.
> > > > > + * @param n
> > > > > + *   The number of objects to add in the ring from the obj_table.
> > > > > + * @param behavior
> > > > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items
> from a
> > > > ring
> > > > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as
> possible
> > > > from ring
> > > > > + * @param is_sp
> > > > > + *   Indicates whether to use single producer or multi-producer head
> > > > update
> > > > > + * @param free_space
> > > > > + *   returns the amount of space after the enqueue operation has
> finished
> > > > > + * @return
> > > > > + *   Actual number of objects enqueued.
> > > > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_enqueue_elem(struct rte_ring *r, const void
> *obj_table,
> > > > > +		unsigned int esize, unsigned int n,
> > > > > +		enum rte_ring_queue_behavior behavior, unsigned
> int is_sp,
> > > > > +		unsigned int *free_space)
> > > > > +{
> > > > > +	uint32_t prod_head, prod_next;
> > > > > +	uint32_t free_entries;
> > > > > +
> > > > > +	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > > > > +			&prod_head, &prod_next, &free_entries);
> > > > > +	if (n == 0)
> > > > > +		goto end;
> > > > > +
> > > > > +	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize,
> n);
> > > > > +
> > > > > +	__rte_ring_update_tail(&r->prod, prod_head, prod_next,
> is_sp, 1);
> > > > > +end:
> > > > > +	if (free_space != NULL)
> > > > > +		*free_space = free_entries - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +/**
> > > > > + * @internal Dequeue several objects from the ring
> > > > > + *
> > > > > + * @param r
> > > > > + *   A pointer to the ring structure.
> > > > > + * @param obj_table
> > > > > + *   A pointer to a table of objects.
> > > > > + * @param esize
> > > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > + *   This must be the same value used while creating the ring.
> Otherwise
> > > > > + *   the results are undefined.
> > > > > + * @param n
> > > > > + *   The number of objects to pull from the ring.
> > > > > + * @param behavior
> > > > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items
> from a
> > > > ring
> > > > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as
> possible
> > > > from ring
> > > > > + * @param is_sc
> > > > > + *   Indicates whether to use single consumer or multi-consumer
> head
> > > > update
> > > > > + * @param available
> > > > > + *   returns the number of remaining ring entries after the dequeue
> has
> > > > finished
> > > > > + * @return
> > > > > + *   - Actual number of objects dequeued.
> > > > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > > +		unsigned int esize, unsigned int n,
> > > > > +		enum rte_ring_queue_behavior behavior, unsigned
> int is_sc,
> > > > > +		unsigned int *available)
> > > > > +{
> > > > > +	uint32_t cons_head, cons_next;
> > > > > +	uint32_t entries;
> > > > > +
> > > > > +	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > > > > +			&cons_head, &cons_next, &entries);
> > > > > +	if (n == 0)
> > > > > +		goto end;
> > > > > +
> > > > > +	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize,
> n);
> > > > > +
> > > > > +	__rte_ring_update_tail(&r->cons, cons_head, cons_next,
> is_sc, 0);
> > > > > +
> > > > > +end:
> > > > > +	if (available != NULL)
> > > > > +		*available = entries - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +#endif /* _RING_ELEM_PVT_H_ */
> > > > > diff --git a/lib/librte_ring/rte_ring_generic.h
> > > > > b/lib/librte_ring/ring_generic_pvt.h
> > > > > similarity index 98%
> > > > > rename from lib/librte_ring/rte_ring_generic.h
> > > > > rename to lib/librte_ring/ring_generic_pvt.h
> > > > > index 37c62b8d6..fc46a27b2 100644
> > > > > --- a/lib/librte_ring/rte_ring_generic.h
> > > > > +++ b/lib/librte_ring/ring_generic_pvt.h
> > > > > @@ -7,8 +7,8 @@
> > > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > > >   */
> > > > >
> > > > > -#ifndef _RTE_RING_GENERIC_H_
> > > > > -#define _RTE_RING_GENERIC_H_
> > > > > +#ifndef _RING_GENERIC_PVT_H_
> > > > > +#define _RING_GENERIC_PVT_H_
> > > > >
> > > > >  static __rte_always_inline void
> > > > >  __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t
> > > > > old_val, @@ -170,4 +170,4 @@ __rte_ring_move_cons_head(struct
> > > > rte_ring *r, unsigned int is_sc,
> > > > >  	return n;
> > > > >  }
> > > > >
> > > > > -#endif /* _RTE_RING_GENERIC_H_ */
> > > > > +#endif /* _RING_GENERIC_PVT_H_ */
> > > > > diff --git a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > > > > b/lib/librte_ring/ring_hts_elem_pvt.h
> > > > > similarity index 60%
> > > > > rename from lib/librte_ring/rte_ring_hts_c11_mem.h
> > > > > rename to lib/librte_ring/ring_hts_elem_pvt.h
> > > > > index 16e54b6ff..9268750b0 100644
> > > > > --- a/lib/librte_ring/rte_ring_hts_c11_mem.h
> > > > > +++ b/lib/librte_ring/ring_hts_elem_pvt.h
> > > > > @@ -7,8 +7,8 @@
> > > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > > >   */
> > > > >
> > > > > -#ifndef _RTE_RING_HTS_C11_MEM_H_
> > > > > -#define _RTE_RING_HTS_C11_MEM_H_
> > > > > +#ifndef _RING_HTS_ELEM_PVT_H_
> > > > > +#define _RING_HTS_ELEM_PVT_H_
> > > > >
> > > > >  /**
> > > > >   * @file rte_ring_hts_c11_mem.h
> > > > > @@ -161,4 +161,86 @@ __rte_ring_hts_move_cons_head(struct
> rte_ring
> > > > *r, unsigned int num,
> > > > >  	return n;
> > > > >  }
> > > > >
> > > > > -#endif /* _RTE_RING_HTS_C11_MEM_H_ */
> > > > > +/**
> > > > > + * @internal Enqueue several objects on the HTS ring.
> > > > > + *
> > > > > + * @param r
> > > > > + *   A pointer to the ring structure.
> > > > > + * @param obj_table
> > > > > + *   A pointer to a table of objects.
> > > > > + * @param esize
> > > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > + *   This must be the same value used while creating the ring.
> Otherwise
> > > > > + *   the results are undefined.
> > > > > + * @param n
> > > > > + *   The number of objects to add in the ring from the obj_table.
> > > > > + * @param behavior
> > > > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items
> from a
> > > > ring
> > > > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as
> possible
> > > > from ring
> > > > > + * @param free_space
> > > > > + *   returns the amount of space after the enqueue operation has
> finished
> > > > > + * @return
> > > > > + *   Actual number of objects enqueued.
> > > > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> > > > *obj_table,
> > > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > +	uint32_t *free_space)
> > > > > +{
> > > > > +	uint32_t free, head;
> > > > > +
> > > > > +	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head,
> &free);
> > > > > +
> > > > > +	if (n != 0) {
> > > > > +		__rte_ring_enqueue_elems(r, head, obj_table, esize,
> n);
> > > > > +		__rte_ring_hts_update_tail(&r->hts_prod, head, n,
> 1);
> > > > > +	}
> > > > > +
> > > > > +	if (free_space != NULL)
> > > > > +		*free_space = free - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +/**
> > > > > + * @internal Dequeue several objects from the HTS ring.
> > > > > + *
> > > > > + * @param r
> > > > > + *   A pointer to the ring structure.
> > > > > + * @param obj_table
> > > > > + *   A pointer to a table of objects.
> > > > > + * @param esize
> > > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > + *   This must be the same value used while creating the ring.
> Otherwise
> > > > > + *   the results are undefined.
> > > > > + * @param n
> > > > > + *   The number of objects to pull from the ring.
> > > > > + * @param behavior
> > > > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items
> from a
> > > > ring
> > > > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as
> possible
> > > > from ring
> > > > > + * @param available
> > > > > + *   returns the number of remaining ring entries after the dequeue
> has
> > > > finished
> > > > > + * @return
> > > > > + *   - Actual number of objects dequeued.
> > > > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void
> *obj_table,
> > > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > +	uint32_t *available)
> > > > > +{
> > > > > +	uint32_t entries, head;
> > > > > +
> > > > > +	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> > > > &entries);
> > > > > +
> > > > > +	if (n != 0) {
> > > > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize,
> n);
> > > > > +		__rte_ring_hts_update_tail(&r->hts_cons, head, n,
> 0);
> > > > > +	}
> > > > > +
> > > > > +	if (available != NULL)
> > > > > +		*available = entries - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +#endif /* _RING_HTS_ELEM_PVT_H_ */
> > > > > diff --git a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > > > > b/lib/librte_ring/ring_peek_elem_pvt.h
> > > > > similarity index 62%
> > > > > rename from lib/librte_ring/rte_ring_peek_c11_mem.h
> > > > > rename to lib/librte_ring/ring_peek_elem_pvt.h
> > > > > index 283c7e70b..1c57bcdd6 100644
> > > > > --- a/lib/librte_ring/rte_ring_peek_c11_mem.h
> > > > > +++ b/lib/librte_ring/ring_peek_elem_pvt.h
> > > > > @@ -7,8 +7,8 @@
> > > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > > >   */
> > > > >
> > > > > -#ifndef _RTE_RING_PEEK_C11_MEM_H_
> > > > > -#define _RTE_RING_PEEK_C11_MEM_H_
> > > > > +#ifndef _RING_PEEK_ELEM_PVT_H_
> > > > > +#define _RING_PEEK_ELEM_PVT_H_
> > > > >
> > > > >  /**
> > > > >   * @file rte_ring_peek_c11_mem.h
> > > > > @@ -107,4 +107,73 @@ __rte_ring_hts_set_head_tail(struct
> > > > rte_ring_hts_headtail *ht, uint32_t tail,
> > > > >  	__atomic_store_n(&ht->ht.raw, p.raw,
> __ATOMIC_RELEASE);  }
> > > > >
> > > > > -#endif /* _RTE_RING_PEEK_C11_MEM_H_ */
> > > > > +/**
> > > > > + * @internal This function moves prod head value.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > > > > +		enum rte_ring_queue_behavior behavior, uint32_t
> > > > *free_space) {
> > > > > +	uint32_t free, head, next;
> > > > > +
> > > > > +	switch (r->prod.sync_type) {
> > > > > +	case RTE_RING_SYNC_ST:
> > > > > +		n = __rte_ring_move_prod_head(r,
> RTE_RING_SYNC_ST, n,
> > > > > +			behavior, &head, &next, &free);
> > > > > +		break;
> > > > > +	case RTE_RING_SYNC_MT_HTS:
> > > > > +		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > > > > +			&head, &free);
> > > > > +		break;
> > > > > +	case RTE_RING_SYNC_MT:
> > > > > +	case RTE_RING_SYNC_MT_RTS:
> > > > > +	default:
> > > > > +		/* unsupported mode, shouldn't be here */
> > > > > +		RTE_ASSERT(0);
> > > > > +		n = 0;
> > > > > +		free = 0;
> > > > > +	}
> > > > > +
> > > > > +	if (free_space != NULL)
> > > > > +		*free_space = free - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +/**
> > > > > + * @internal This function moves cons head value and copies up to
> *n*
> > > > > + * objects from the ring to the user provided obj_table.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > +	uint32_t *available)
> > > > > +{
> > > > > +	uint32_t avail, head, next;
> > > > > +
> > > > > +	switch (r->cons.sync_type) {
> > > > > +	case RTE_RING_SYNC_ST:
> > > > > +		n = __rte_ring_move_cons_head(r,
> RTE_RING_SYNC_ST, n,
> > > > > +			behavior, &head, &next, &avail);
> > > > > +		break;
> > > > > +	case RTE_RING_SYNC_MT_HTS:
> > > > > +		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > > > > +			&head, &avail);
> > > > > +		break;
> > > > > +	case RTE_RING_SYNC_MT:
> > > > > +	case RTE_RING_SYNC_MT_RTS:
> > > > > +	default:
> > > > > +		/* unsupported mode, shouldn't be here */
> > > > > +		RTE_ASSERT(0);
> > > > > +		n = 0;
> > > > > +		avail = 0;
> > > > > +	}
> > > > > +
> > > > > +	if (n != 0)
> > > > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize,
> n);
> > > > > +
> > > > > +	if (available != NULL)
> > > > > +		*available = avail - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +#endif /* _RING_PEEK_ELEM_PVT_H_ */
> > > > > diff --git a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > > > > b/lib/librte_ring/ring_rts_elem_pvt.h
> > > > > similarity index 62%
> > > > > rename from lib/librte_ring/rte_ring_rts_c11_mem.h
> > > > > rename to lib/librte_ring/ring_rts_elem_pvt.h
> > > > > index 327f22796..cbcec73eb 100644
> > > > > --- a/lib/librte_ring/rte_ring_rts_c11_mem.h
> > > > > +++ b/lib/librte_ring/ring_rts_elem_pvt.h
> > > > > @@ -7,8 +7,8 @@
> > > > >   * Used as BSD-3 Licensed with permission from Kip Macy.
> > > > >   */
> > > > >
> > > > > -#ifndef _RTE_RING_RTS_C11_MEM_H_
> > > > > -#define _RTE_RING_RTS_C11_MEM_H_
> > > > > +#ifndef _RING_RTS_ELEM_PVT_H_
> > > > > +#define _RING_RTS_ELEM_PVT_H_
> > > > >
> > > > >  /**
> > > > >   * @file rte_ring_rts_c11_mem.h
> > > > > @@ -176,4 +176,86 @@ __rte_ring_rts_move_cons_head(struct
> rte_ring
> > > > *r, uint32_t num,
> > > > >  	return n;
> > > > >  }
> > > > >
> > > > > -#endif /* _RTE_RING_RTS_C11_MEM_H_ */
> > > > > +/**
> > > > > + * @internal Enqueue several objects on the RTS ring.
> > > > > + *
> > > > > + * @param r
> > > > > + *   A pointer to the ring structure.
> > > > > + * @param obj_table
> > > > > + *   A pointer to a table of objects.
> > > > > + * @param esize
> > > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > + *   This must be the same value used while creating the ring.
> Otherwise
> > > > > + *   the results are undefined.
> > > > > + * @param n
> > > > > + *   The number of objects to add in the ring from the obj_table.
> > > > > + * @param behavior
> > > > > + *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items
> from a
> > > > ring
> > > > > + *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as
> possible
> > > > from ring
> > > > > + * @param free_space
> > > > > + *   returns the amount of space after the enqueue operation has
> finished
> > > > > + * @return
> > > > > + *   Actual number of objects enqueued.
> > > > > + *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> > > > *obj_table,
> > > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > +	uint32_t *free_space)
> > > > > +{
> > > > > +	uint32_t free, head;
> > > > > +
> > > > > +	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head,
> &free);
> > > > > +
> > > > > +	if (n != 0) {
> > > > > +		__rte_ring_enqueue_elems(r, head, obj_table, esize,
> n);
> > > > > +		__rte_ring_rts_update_tail(&r->rts_prod);
> > > > > +	}
> > > > > +
> > > > > +	if (free_space != NULL)
> > > > > +		*free_space = free - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +/**
> > > > > + * @internal Dequeue several objects from the RTS ring.
> > > > > + *
> > > > > + * @param r
> > > > > + *   A pointer to the ring structure.
> > > > > + * @param obj_table
> > > > > + *   A pointer to a table of objects.
> > > > > + * @param esize
> > > > > + *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > + *   This must be the same value used while creating the ring.
> Otherwise
> > > > > + *   the results are undefined.
> > > > > + * @param n
> > > > > + *   The number of objects to pull from the ring.
> > > > > + * @param behavior
> > > > > + *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items
> from a
> > > > ring
> > > > > + *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as
> possible
> > > > from ring
> > > > > + * @param available
> > > > > + *   returns the number of remaining ring entries after the dequeue
> has
> > > > finished
> > > > > + * @return
> > > > > + *   - Actual number of objects dequeued.
> > > > > + *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > + */
> > > > > +static __rte_always_inline unsigned int
> > > > > +__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void
> *obj_table,
> > > > > +	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > +	uint32_t *available)
> > > > > +{
> > > > > +	uint32_t entries, head;
> > > > > +
> > > > > +	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> > > > &entries);
> > > > > +
> > > > > +	if (n != 0) {
> > > > > +		__rte_ring_dequeue_elems(r, head, obj_table, esize,
> n);
> > > > > +		__rte_ring_rts_update_tail(&r->rts_cons);
> > > > > +	}
> > > > > +
> > > > > +	if (available != NULL)
> > > > > +		*available = entries - n;
> > > > > +	return n;
> > > > > +}
> > > > > +
> > > > > +#endif /* _RING_RTS_ELEM_PVT_H_ */
> > > > > diff --git a/lib/librte_ring/rte_ring_elem.h
> > > > > b/lib/librte_ring/rte_ring_elem.h index 57344d47d..119b5c0b6 100644
> > > > > --- a/lib/librte_ring/rte_ring_elem.h
> > > > > +++ b/lib/librte_ring/rte_ring_elem.h
> > > > > @@ -21,6 +21,7 @@ extern "C" {
> > > > >  #endif
> > > > >
> > > > >  #include <rte_ring_core.h>
> > > > > +#include <ring_elem_pvt.h>
> > > > >
> > > > >  /**
> > > > >   * Calculate the memory size needed for a ring with given element
> > > > > size @@ -105,379 +106,6 @@ ssize_t
> > > > rte_ring_get_memsize_elem(unsigned
> > > > > int esize, unsigned int count);  struct rte_ring
> *rte_ring_create_elem(const
> > > > char *name, unsigned int esize,
> > > > >  			unsigned int count, int socket_id, unsigned
> int flags);
> > > > >
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t
> size,
> > > > > -		uint32_t idx, const void *obj_table, uint32_t n)
> > > > > -{
> > > > > -	unsigned int i;
> > > > > -	uint32_t *ring = (uint32_t *)&r[1];
> > > > > -	const uint32_t *obj = (const uint32_t *)obj_table;
> > > > > -	if (likely(idx + n < size)) {
> > > > > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > > -			ring[idx] = obj[i];
> > > > > -			ring[idx + 1] = obj[i + 1];
> > > > > -			ring[idx + 2] = obj[i + 2];
> > > > > -			ring[idx + 3] = obj[i + 3];
> > > > > -			ring[idx + 4] = obj[i + 4];
> > > > > -			ring[idx + 5] = obj[i + 5];
> > > > > -			ring[idx + 6] = obj[i + 6];
> > > > > -			ring[idx + 7] = obj[i + 7];
> > > > > -		}
> > > > > -		switch (n & 0x7) {
> > > > > -		case 7:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 6:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 5:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 4:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 3:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 2:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 1:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		}
> > > > > -	} else {
> > > > > -		for (i = 0; idx < size; i++, idx++)
> > > > > -			ring[idx] = obj[i];
> > > > > -		/* Start at the beginning */
> > > > > -		for (idx = 0; i < n; i++, idx++)
> > > > > -			ring[idx] = obj[i];
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t
> prod_head,
> > > > > -		const void *obj_table, uint32_t n)
> > > > > -{
> > > > > -	unsigned int i;
> > > > > -	const uint32_t size = r->size;
> > > > > -	uint32_t idx = prod_head & r->mask;
> > > > > -	uint64_t *ring = (uint64_t *)&r[1];
> > > > > -	const unaligned_uint64_t *obj = (const unaligned_uint64_t
> > > > *)obj_table;
> > > > > -	if (likely(idx + n < size)) {
> > > > > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > > -			ring[idx] = obj[i];
> > > > > -			ring[idx + 1] = obj[i + 1];
> > > > > -			ring[idx + 2] = obj[i + 2];
> > > > > -			ring[idx + 3] = obj[i + 3];
> > > > > -		}
> > > > > -		switch (n & 0x3) {
> > > > > -		case 3:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 2:
> > > > > -			ring[idx++] = obj[i++]; /* fallthrough */
> > > > > -		case 1:
> > > > > -			ring[idx++] = obj[i++];
> > > > > -		}
> > > > > -	} else {
> > > > > -		for (i = 0; idx < size; i++, idx++)
> > > > > -			ring[idx] = obj[i];
> > > > > -		/* Start at the beginning */
> > > > > -		for (idx = 0; i < n; i++, idx++)
> > > > > -			ring[idx] = obj[i];
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t
> prod_head,
> > > > > -		const void *obj_table, uint32_t n)
> > > > > -{
> > > > > -	unsigned int i;
> > > > > -	const uint32_t size = r->size;
> > > > > -	uint32_t idx = prod_head & r->mask;
> > > > > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > > -	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
> > > > > -	if (likely(idx + n < size)) {
> > > > > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > > -			memcpy((void *)(ring + idx),
> > > > > -				(const void *)(obj + i), 32);
> > > > > -		switch (n & 0x1) {
> > > > > -		case 1:
> > > > > -			memcpy((void *)(ring + idx),
> > > > > -				(const void *)(obj + i), 16);
> > > > > -		}
> > > > > -	} else {
> > > > > -		for (i = 0; idx < size; i++, idx++)
> > > > > -			memcpy((void *)(ring + idx),
> > > > > -				(const void *)(obj + i), 16);
> > > > > -		/* Start at the beginning */
> > > > > -		for (idx = 0; i < n; i++, idx++)
> > > > > -			memcpy((void *)(ring + idx),
> > > > > -				(const void *)(obj + i), 16);
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -/* the actual enqueue of elements on the ring.
> > > > > - * Placed here since identical code needed in both
> > > > > - * single and multi producer enqueue functions.
> > > > > - */
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
> > > > > -		const void *obj_table, uint32_t esize, uint32_t num)
> > > > > -{
> > > > > -	/* 8B and 16B copies implemented individually to retain
> > > > > -	 * the current performance.
> > > > > -	 */
> > > > > -	if (esize == 8)
> > > > > -		__rte_ring_enqueue_elems_64(r, prod_head,
> obj_table,
> > > > num);
> > > > > -	else if (esize == 16)
> > > > > -		__rte_ring_enqueue_elems_128(r, prod_head,
> obj_table,
> > > > num);
> > > > > -	else {
> > > > > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > > -
> > > > > -		/* Normalize to uint32_t */
> > > > > -		scale = esize / sizeof(uint32_t);
> > > > > -		nr_num = num * scale;
> > > > > -		idx = prod_head & r->mask;
> > > > > -		nr_idx = idx * scale;
> > > > > -		nr_size = r->size * scale;
> > > > > -		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
> > > > > -				obj_table, nr_num);
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t
> size,
> > > > > -		uint32_t idx, void *obj_table, uint32_t n)
> > > > > -{
> > > > > -	unsigned int i;
> > > > > -	uint32_t *ring = (uint32_t *)&r[1];
> > > > > -	uint32_t *obj = (uint32_t *)obj_table;
> > > > > -	if (likely(idx + n < size)) {
> > > > > -		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
> > > > > -			obj[i] = ring[idx];
> > > > > -			obj[i + 1] = ring[idx + 1];
> > > > > -			obj[i + 2] = ring[idx + 2];
> > > > > -			obj[i + 3] = ring[idx + 3];
> > > > > -			obj[i + 4] = ring[idx + 4];
> > > > > -			obj[i + 5] = ring[idx + 5];
> > > > > -			obj[i + 6] = ring[idx + 6];
> > > > > -			obj[i + 7] = ring[idx + 7];
> > > > > -		}
> > > > > -		switch (n & 0x7) {
> > > > > -		case 7:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 6:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 5:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 4:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 3:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 2:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 1:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		}
> > > > > -	} else {
> > > > > -		for (i = 0; idx < size; i++, idx++)
> > > > > -			obj[i] = ring[idx];
> > > > > -		/* Start at the beginning */
> > > > > -		for (idx = 0; i < n; i++, idx++)
> > > > > -			obj[i] = ring[idx];
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t
> prod_head,
> > > > > -		void *obj_table, uint32_t n)
> > > > > -{
> > > > > -	unsigned int i;
> > > > > -	const uint32_t size = r->size;
> > > > > -	uint32_t idx = prod_head & r->mask;
> > > > > -	uint64_t *ring = (uint64_t *)&r[1];
> > > > > -	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
> > > > > -	if (likely(idx + n < size)) {
> > > > > -		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
> > > > > -			obj[i] = ring[idx];
> > > > > -			obj[i + 1] = ring[idx + 1];
> > > > > -			obj[i + 2] = ring[idx + 2];
> > > > > -			obj[i + 3] = ring[idx + 3];
> > > > > -		}
> > > > > -		switch (n & 0x3) {
> > > > > -		case 3:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 2:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		case 1:
> > > > > -			obj[i++] = ring[idx++]; /* fallthrough */
> > > > > -		}
> > > > > -	} else {
> > > > > -		for (i = 0; idx < size; i++, idx++)
> > > > > -			obj[i] = ring[idx];
> > > > > -		/* Start at the beginning */
> > > > > -		for (idx = 0; i < n; i++, idx++)
> > > > > -			obj[i] = ring[idx];
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t
> prod_head,
> > > > > -		void *obj_table, uint32_t n)
> > > > > -{
> > > > > -	unsigned int i;
> > > > > -	const uint32_t size = r->size;
> > > > > -	uint32_t idx = prod_head & r->mask;
> > > > > -	rte_int128_t *ring = (rte_int128_t *)&r[1];
> > > > > -	rte_int128_t *obj = (rte_int128_t *)obj_table;
> > > > > -	if (likely(idx + n < size)) {
> > > > > -		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> > > > > -			memcpy((void *)(obj + i), (void *)(ring + idx),
> 32);
> > > > > -		switch (n & 0x1) {
> > > > > -		case 1:
> > > > > -			memcpy((void *)(obj + i), (void *)(ring + idx),
> 16);
> > > > > -		}
> > > > > -	} else {
> > > > > -		for (i = 0; idx < size; i++, idx++)
> > > > > -			memcpy((void *)(obj + i), (void *)(ring + idx),
> 16);
> > > > > -		/* Start at the beginning */
> > > > > -		for (idx = 0; i < n; i++, idx++)
> > > > > -			memcpy((void *)(obj + i), (void *)(ring + idx),
> 16);
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -/* the actual dequeue of elements from the ring.
> > > > > - * Placed here since identical code needed in both
> > > > > - * single and multi producer enqueue functions.
> > > > > - */
> > > > > -static __rte_always_inline void
> > > > > -__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
> > > > > -		void *obj_table, uint32_t esize, uint32_t num)
> > > > > -{
> > > > > -	/* 8B and 16B copies implemented individually to retain
> > > > > -	 * the current performance.
> > > > > -	 */
> > > > > -	if (esize == 8)
> > > > > -		__rte_ring_dequeue_elems_64(r, cons_head,
> obj_table,
> > > > num);
> > > > > -	else if (esize == 16)
> > > > > -		__rte_ring_dequeue_elems_128(r, cons_head,
> obj_table,
> > > > num);
> > > > > -	else {
> > > > > -		uint32_t idx, scale, nr_idx, nr_num, nr_size;
> > > > > -
> > > > > -		/* Normalize to uint32_t */
> > > > > -		scale = esize / sizeof(uint32_t);
> > > > > -		nr_num = num * scale;
> > > > > -		idx = cons_head & r->mask;
> > > > > -		nr_idx = idx * scale;
> > > > > -		nr_size = r->size * scale;
> > > > > -		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
> > > > > -				obj_table, nr_num);
> > > > > -	}
> > > > > -}
> > > > > -
> > > > > -/* Between load and load. there might be cpu reorder in weak
> model
> > > > > - * (powerpc/arm).
> > > > > - * There are 2 choices for the users
> > > > > - * 1.use rmb() memory barrier
> > > > > - * 2.use one-direction load_acquire/store_release barrier
> > > > > - * It depends on performance test results.
> > > > > - * By default, move common functions to rte_ring_generic.h
> > > > > - */
> > > > > -#ifdef RTE_USE_C11_MEM_MODEL
> > > > > -#include "rte_ring_c11_mem.h"
> > > > > -#else
> > > > > -#include "rte_ring_generic.h"
> > > > > -#endif
> > > > > -
> > > > > -/**
> > > > > - * @internal Enqueue several objects on the ring
> > > > > - *
> > > > > - * @param r
> > > > > - *   A pointer to the ring structure.
> > > > > - * @param obj_table
> > > > > - *   A pointer to a table of objects.
> > > > > - * @param esize
> > > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > - *   This must be the same value used while creating the ring.
> Otherwise
> > > > > - *   the results are undefined.
> > > > > - * @param n
> > > > > - *   The number of objects to add in the ring from the obj_table.
> > > > > - * @param behavior
> > > > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items
> from a
> > > > ring
> > > > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as
> possible
> > > > from ring
> > > > > - * @param is_sp
> > > > > - *   Indicates whether to use single producer or multi-producer head
> > > > update
> > > > > - * @param free_space
> > > > > - *   returns the amount of space after the enqueue operation has
> finished
> > > > > - * @return
> > > > > - *   Actual number of objects enqueued.
> > > > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_enqueue_elem(struct rte_ring *r, const void
> *obj_table,
> > > > > -		unsigned int esize, unsigned int n,
> > > > > -		enum rte_ring_queue_behavior behavior, unsigned
> int is_sp,
> > > > > -		unsigned int *free_space)
> > > > > -{
> > > > > -	uint32_t prod_head, prod_next;
> > > > > -	uint32_t free_entries;
> > > > > -
> > > > > -	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
> > > > > -			&prod_head, &prod_next, &free_entries);
> > > > > -	if (n == 0)
> > > > > -		goto end;
> > > > > -
> > > > > -	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize,
> n);
> > > > > -
> > > > > -	__rte_ring_update_tail(&r->prod, prod_head, prod_next,
> is_sp, 1);
> > > > > -end:
> > > > > -	if (free_space != NULL)
> > > > > -		*free_space = free_entries - n;
> > > > > -	return n;
> > > > > -}
> > > > > -
> > > > > -/**
> > > > > - * @internal Dequeue several objects from the ring
> > > > > - *
> > > > > - * @param r
> > > > > - *   A pointer to the ring structure.
> > > > > - * @param obj_table
> > > > > - *   A pointer to a table of objects.
> > > > > - * @param esize
> > > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > - *   This must be the same value used while creating the ring.
> Otherwise
> > > > > - *   the results are undefined.
> > > > > - * @param n
> > > > > - *   The number of objects to pull from the ring.
> > > > > - * @param behavior
> > > > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items
> from a
> > > > ring
> > > > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as
> possible
> > > > from ring
> > > > > - * @param is_sc
> > > > > - *   Indicates whether to use single consumer or multi-consumer
> head
> > > > update
> > > > > - * @param available
> > > > > - *   returns the number of remaining ring entries after the dequeue
> has
> > > > finished
> > > > > - * @return
> > > > > - *   - Actual number of objects dequeued.
> > > > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
> > > > > -		unsigned int esize, unsigned int n,
> > > > > -		enum rte_ring_queue_behavior behavior, unsigned
> int is_sc,
> > > > > -		unsigned int *available)
> > > > > -{
> > > > > -	uint32_t cons_head, cons_next;
> > > > > -	uint32_t entries;
> > > > > -
> > > > > -	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
> > > > > -			&cons_head, &cons_next, &entries);
> > > > > -	if (n == 0)
> > > > > -		goto end;
> > > > > -
> > > > > -	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize,
> n);
> > > > > -
> > > > > -	__rte_ring_update_tail(&r->cons, cons_head, cons_next,
> is_sc, 0);
> > > > > -
> > > > > -end:
> > > > > -	if (available != NULL)
> > > > > -		*available = entries - n;
> > > > > -	return n;
> > > > > -}
> > > > > -
> > > > >  /**
> > > > >   * Enqueue several objects on the ring (multi-producers safe).
> > > > >   *
> > > > > diff --git a/lib/librte_ring/rte_ring_hts.h
> > > > > b/lib/librte_ring/rte_ring_hts.h index 359b15771..bdbdafc9f 100644
> > > > > --- a/lib/librte_ring/rte_ring_hts.h
> > > > > +++ b/lib/librte_ring/rte_ring_hts.h
> > > > > @@ -29,89 +29,7 @@
> > > > >  extern "C" {
> > > > >  #endif
> > > > >
> > > > > -#include <rte_ring_hts_c11_mem.h>
> > > > > -
> > > > > -/**
> > > > > - * @internal Enqueue several objects on the HTS ring.
> > > > > - *
> > > > > - * @param r
> > > > > - *   A pointer to the ring structure.
> > > > > - * @param obj_table
> > > > > - *   A pointer to a table of objects.
> > > > > - * @param esize
> > > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > - *   This must be the same value used while creating the ring.
> Otherwise
> > > > > - *   the results are undefined.
> > > > > - * @param n
> > > > > - *   The number of objects to add in the ring from the obj_table.
> > > > > - * @param behavior
> > > > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items
> from a
> > > > ring
> > > > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as
> possible
> > > > from ring
> > > > > - * @param free_space
> > > > > - *   returns the amount of space after the enqueue operation has
> finished
> > > > > - * @return
> > > > > - *   Actual number of objects enqueued.
> > > > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void
> > > > *obj_table,
> > > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > -	uint32_t *free_space)
> > > > > -{
> > > > > -	uint32_t free, head;
> > > > > -
> > > > > -	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head,
> &free);
> > > > > -
> > > > > -	if (n != 0) {
> > > > > -		__rte_ring_enqueue_elems(r, head, obj_table, esize,
> n);
> > > > > -		__rte_ring_hts_update_tail(&r->hts_prod, head, n,
> 1);
> > > > > -	}
> > > > > -
> > > > > -	if (free_space != NULL)
> > > > > -		*free_space = free - n;
> > > > > -	return n;
> > > > > -}
> > > > > -
> > > > > -/**
> > > > > - * @internal Dequeue several objects from the HTS ring.
> > > > > - *
> > > > > - * @param r
> > > > > - *   A pointer to the ring structure.
> > > > > - * @param obj_table
> > > > > - *   A pointer to a table of objects.
> > > > > - * @param esize
> > > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > - *   This must be the same value used while creating the ring.
> Otherwise
> > > > > - *   the results are undefined.
> > > > > - * @param n
> > > > > - *   The number of objects to pull from the ring.
> > > > > - * @param behavior
> > > > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items
> from a
> > > > ring
> > > > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as
> possible
> > > > from ring
> > > > > - * @param available
> > > > > - *   returns the number of remaining ring entries after the dequeue
> has
> > > > finished
> > > > > - * @return
> > > > > - *   - Actual number of objects dequeued.
> > > > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void
> *obj_table,
> > > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > -	uint32_t *available)
> > > > > -{
> > > > > -	uint32_t entries, head;
> > > > > -
> > > > > -	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head,
> > > > &entries);
> > > > > -
> > > > > -	if (n != 0) {
> > > > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize,
> n);
> > > > > -		__rte_ring_hts_update_tail(&r->hts_cons, head, n,
> 0);
> > > > > -	}
> > > > > -
> > > > > -	if (available != NULL)
> > > > > -		*available = entries - n;
> > > > > -	return n;
> > > > > -}
> > > > > +#include <ring_hts_elem_pvt.h>
> > > > >
> > > > >  /**
> > > > >   * Enqueue several objects on the HTS ring (multi-producers safe).
> > > > > diff --git a/lib/librte_ring/rte_ring_peek.h
> > > > > b/lib/librte_ring/rte_ring_peek.h index 45f707dc7..0dd402be4 100644
> > > > > --- a/lib/librte_ring/rte_ring_peek.h
> > > > > +++ b/lib/librte_ring/rte_ring_peek.h
> > > > > @@ -48,39 +48,7 @@
> > > > >  extern "C" {
> > > > >  #endif
> > > > >
> > > > > -#include <rte_ring_peek_c11_mem.h>
> > > > > -
> > > > > -/**
> > > > > - * @internal This function moves prod head value.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
> > > > > -		enum rte_ring_queue_behavior behavior, uint32_t
> > > > *free_space)
> > > > > -{
> > > > > -	uint32_t free, head, next;
> > > > > -
> > > > > -	switch (r->prod.sync_type) {
> > > > > -	case RTE_RING_SYNC_ST:
> > > > > -		n = __rte_ring_move_prod_head(r,
> RTE_RING_SYNC_ST, n,
> > > > > -			behavior, &head, &next, &free);
> > > > > -		break;
> > > > > -	case RTE_RING_SYNC_MT_HTS:
> > > > > -		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
> > > > > -			&head, &free);
> > > > > -		break;
> > > > > -	case RTE_RING_SYNC_MT:
> > > > > -	case RTE_RING_SYNC_MT_RTS:
> > > > > -	default:
> > > > > -		/* unsupported mode, shouldn't be here */
> > > > > -		RTE_ASSERT(0);
> > > > > -		n = 0;
> > > > > -		free = 0;
> > > > > -	}
> > > > > -
> > > > > -	if (free_space != NULL)
> > > > > -		*free_space = free - n;
> > > > > -	return n;
> > > > > -}
> > > > > +#include <ring_peek_elem_pvt.h>
> > > > >
> > > > >  /**
> > > > >   * Start to enqueue several objects on the ring.
> > > > > @@ -248,43 +216,6 @@ rte_ring_enqueue_finish(struct rte_ring *r,
> void *
> > > > const *obj_table,
> > > > >  	rte_ring_enqueue_elem_finish(r, obj_table,
> sizeof(uintptr_t), n);  }
> > > > >
> > > > > -/**
> > > > > - * @internal This function moves cons head value and copies up to
> *n*
> > > > > - * objects from the ring to the user provided obj_table.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
> > > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > -	uint32_t *available)
> > > > > -{
> > > > > -	uint32_t avail, head, next;
> > > > > -
> > > > > -	switch (r->cons.sync_type) {
> > > > > -	case RTE_RING_SYNC_ST:
> > > > > -		n = __rte_ring_move_cons_head(r,
> RTE_RING_SYNC_ST, n,
> > > > > -			behavior, &head, &next, &avail);
> > > > > -		break;
> > > > > -	case RTE_RING_SYNC_MT_HTS:
> > > > > -		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
> > > > > -			&head, &avail);
> > > > > -		break;
> > > > > -	case RTE_RING_SYNC_MT:
> > > > > -	case RTE_RING_SYNC_MT_RTS:
> > > > > -	default:
> > > > > -		/* unsupported mode, shouldn't be here */
> > > > > -		RTE_ASSERT(0);
> > > > > -		n = 0;
> > > > > -		avail = 0;
> > > > > -	}
> > > > > -
> > > > > -	if (n != 0)
> > > > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize,
> n);
> > > > > -
> > > > > -	if (available != NULL)
> > > > > -		*available = avail - n;
> > > > > -	return n;
> > > > > -}
> > > > > -
> > > > >  /**
> > > > >   * Start to dequeue several objects from the ring.
> > > > >   * Note that user has to call appropriate dequeue_finish() diff --git
> > > > > a/lib/librte_ring/rte_ring_peek_zc.h
> > > > > b/lib/librte_ring/rte_ring_peek_zc.h
> > > > > index cb3bbd067..bc8252a18 100644
> > > > > --- a/lib/librte_ring/rte_ring_peek_zc.h
> > > > > +++ b/lib/librte_ring/rte_ring_peek_zc.h
> > > > > @@ -72,7 +72,7 @@
> > > > >  extern "C" {
> > > > >  #endif
> > > > >
> > > > > -#include <rte_ring_peek_c11_mem.h>
> > > > > +#include <ring_peek_elem_pvt.h>
> > > > >
> > > > >  /**
> > > > >   * Ring zero-copy information structure.
> > > > > diff --git a/lib/librte_ring/rte_ring_rts.h
> > > > > b/lib/librte_ring/rte_ring_rts.h index afc12abe2..83d9903e2 100644
> > > > > --- a/lib/librte_ring/rte_ring_rts.h
> > > > > +++ b/lib/librte_ring/rte_ring_rts.h
> > > > > @@ -56,89 +56,7 @@
> > > > >  extern "C" {
> > > > >  #endif
> > > > >
> > > > > -#include <rte_ring_rts_c11_mem.h>
> > > > > -
> > > > > -/**
> > > > > - * @internal Enqueue several objects on the RTS ring.
> > > > > - *
> > > > > - * @param r
> > > > > - *   A pointer to the ring structure.
> > > > > - * @param obj_table
> > > > > - *   A pointer to a table of objects.
> > > > > - * @param esize
> > > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > - *   This must be the same value used while creating the ring.
> Otherwise
> > > > > - *   the results are undefined.
> > > > > - * @param n
> > > > > - *   The number of objects to add in the ring from the obj_table.
> > > > > - * @param behavior
> > > > > - *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items
> from a
> > > > ring
> > > > > - *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as
> possible
> > > > from ring
> > > > > - * @param free_space
> > > > > - *   returns the amount of space after the enqueue operation has
> finished
> > > > > - * @return
> > > > > - *   Actual number of objects enqueued.
> > > > > - *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void
> > > > *obj_table,
> > > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > -	uint32_t *free_space)
> > > > > -{
> > > > > -	uint32_t free, head;
> > > > > -
> > > > > -	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head,
> &free);
> > > > > -
> > > > > -	if (n != 0) {
> > > > > -		__rte_ring_enqueue_elems(r, head, obj_table, esize,
> n);
> > > > > -		__rte_ring_rts_update_tail(&r->rts_prod);
> > > > > -	}
> > > > > -
> > > > > -	if (free_space != NULL)
> > > > > -		*free_space = free - n;
> > > > > -	return n;
> > > > > -}
> > > > > -
> > > > > -/**
> > > > > - * @internal Dequeue several objects from the RTS ring.
> > > > > - *
> > > > > - * @param r
> > > > > - *   A pointer to the ring structure.
> > > > > - * @param obj_table
> > > > > - *   A pointer to a table of objects.
> > > > > - * @param esize
> > > > > - *   The size of ring element, in bytes. It must be a multiple of 4.
> > > > > - *   This must be the same value used while creating the ring.
> Otherwise
> > > > > - *   the results are undefined.
> > > > > - * @param n
> > > > > - *   The number of objects to pull from the ring.
> > > > > - * @param behavior
> > > > > - *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items
> from a
> > > > ring
> > > > > - *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as
> possible
> > > > from ring
> > > > > - * @param available
> > > > > - *   returns the number of remaining ring entries after the dequeue
> has
> > > > finished
> > > > > - * @return
> > > > > - *   - Actual number of objects dequeued.
> > > > > - *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
> > > > > - */
> > > > > -static __rte_always_inline unsigned int
> > > > > -__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void
> *obj_table,
> > > > > -	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior
> behavior,
> > > > > -	uint32_t *available)
> > > > > -{
> > > > > -	uint32_t entries, head;
> > > > > -
> > > > > -	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head,
> > > > &entries);
> > > > > -
> > > > > -	if (n != 0) {
> > > > > -		__rte_ring_dequeue_elems(r, head, obj_table, esize,
> n);
> > > > > -		__rte_ring_rts_update_tail(&r->rts_cons);
> > > > > -	}
> > > > > -
> > > > > -	if (available != NULL)
> > > > > -		*available = entries - n;
> > > > > -	return n;
> > > > > -}
> > > > > +#include <ring_rts_elem_pvt.h>
> > > > >
> > > > >  /**
> > > > >   * Enqueue several objects on the RTS ring (multi-producers safe).
> > > > > --
> > > > > 2.17.1
diff mbox series

Patch

diff --git a/lib/librte_ring/meson.build b/lib/librte_ring/meson.build
index 36fdcb6a5..98eac5810 100644
--- a/lib/librte_ring/meson.build
+++ b/lib/librte_ring/meson.build
@@ -2,15 +2,16 @@ 
 # Copyright(c) 2017 Intel Corporation
 
 sources = files('rte_ring.c')
-headers = files('rte_ring.h',
+headers = files('ring_c11_pvt.h',
+		'ring_elem_pvt.h',
+		'ring_generic_pvt.h',
+		'ring_hts_elem_pvt.h',
+		'ring_peek_elem_pvt.h',
+		'ring_rts_elem_pvt.h',
+		'rte_ring.h',
 		'rte_ring_core.h',
 		'rte_ring_elem.h',
-		'rte_ring_c11_mem.h',
-		'rte_ring_generic.h',
 		'rte_ring_hts.h',
-		'rte_ring_hts_c11_mem.h',
 		'rte_ring_peek.h',
-		'rte_ring_peek_c11_mem.h',
 		'rte_ring_peek_zc.h',
-		'rte_ring_rts.h',
-		'rte_ring_rts_c11_mem.h')
+		'rte_ring_rts.h')
diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/ring_c11_pvt.h
similarity index 96%
rename from lib/librte_ring/rte_ring_c11_mem.h
rename to lib/librte_ring/ring_c11_pvt.h
index 7f5eba262..9f2f5318f 100644
--- a/lib/librte_ring/rte_ring_c11_mem.h
+++ b/lib/librte_ring/ring_c11_pvt.h
@@ -7,8 +7,8 @@ 
  * Used as BSD-3 Licensed with permission from Kip Macy.
  */
 
-#ifndef _RTE_RING_C11_MEM_H_
-#define _RTE_RING_C11_MEM_H_
+#ifndef _RING_C11_PVT_H_
+#define _RING_C11_PVT_H_
 
 static __rte_always_inline void
 __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
@@ -69,9 +69,6 @@  __rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
 		/* Ensure the head is read before tail */
 		__atomic_thread_fence(__ATOMIC_ACQUIRE);
 
-		/* load-acquire synchronize with store-release of ht->tail
-		 * in update_tail.
-		 */
 		cons_tail = __atomic_load_n(&r->cons.tail,
 					__ATOMIC_ACQUIRE);
 
@@ -178,4 +175,4 @@  __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
 	return n;
 }
 
-#endif /* _RTE_RING_C11_MEM_H_ */
+#endif /* _RING_C11_PVT_H_ */
diff --git a/lib/librte_ring/ring_elem_pvt.h b/lib/librte_ring/ring_elem_pvt.h
new file mode 100644
index 000000000..8003e5edc
--- /dev/null
+++ b/lib/librte_ring/ring_elem_pvt.h
@@ -0,0 +1,385 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ *
+ * Copyright (c) 2017,2018 HXT-semitech Corporation.
+ * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org
+ * All rights reserved.
+ * Derived from FreeBSD's bufring.h
+ * Used as BSD-3 Licensed with permission from Kip Macy.
+ */
+
+#ifndef _RING_ELEM_PVT_H_
+#define _RING_ELEM_PVT_H_
+
+static __rte_always_inline void
+__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
+		uint32_t idx, const void *obj_table, uint32_t n)
+{
+	unsigned int i;
+	uint32_t *ring = (uint32_t *)&r[1];
+	const uint32_t *obj = (const uint32_t *)obj_table;
+	if (likely(idx + n < size)) {
+		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
+			ring[idx] = obj[i];
+			ring[idx + 1] = obj[i + 1];
+			ring[idx + 2] = obj[i + 2];
+			ring[idx + 3] = obj[i + 3];
+			ring[idx + 4] = obj[i + 4];
+			ring[idx + 5] = obj[i + 5];
+			ring[idx + 6] = obj[i + 6];
+			ring[idx + 7] = obj[i + 7];
+		}
+		switch (n & 0x7) {
+		case 7:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 6:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 5:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 4:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 3:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 2:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 1:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		}
+	} else {
+		for (i = 0; idx < size; i++, idx++)
+			ring[idx] = obj[i];
+		/* Start at the beginning */
+		for (idx = 0; i < n; i++, idx++)
+			ring[idx] = obj[i];
+	}
+}
+
+static __rte_always_inline void
+__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
+		const void *obj_table, uint32_t n)
+{
+	unsigned int i;
+	const uint32_t size = r->size;
+	uint32_t idx = prod_head & r->mask;
+	uint64_t *ring = (uint64_t *)&r[1];
+	const unaligned_uint64_t *obj = (const unaligned_uint64_t *)obj_table;
+	if (likely(idx + n < size)) {
+		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
+			ring[idx] = obj[i];
+			ring[idx + 1] = obj[i + 1];
+			ring[idx + 2] = obj[i + 2];
+			ring[idx + 3] = obj[i + 3];
+		}
+		switch (n & 0x3) {
+		case 3:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 2:
+			ring[idx++] = obj[i++]; /* fallthrough */
+		case 1:
+			ring[idx++] = obj[i++];
+		}
+	} else {
+		for (i = 0; idx < size; i++, idx++)
+			ring[idx] = obj[i];
+		/* Start at the beginning */
+		for (idx = 0; i < n; i++, idx++)
+			ring[idx] = obj[i];
+	}
+}
+
+static __rte_always_inline void
+__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
+		const void *obj_table, uint32_t n)
+{
+	unsigned int i;
+	const uint32_t size = r->size;
+	uint32_t idx = prod_head & r->mask;
+	rte_int128_t *ring = (rte_int128_t *)&r[1];
+	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
+	if (likely(idx + n < size)) {
+		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
+			memcpy((void *)(ring + idx),
+				(const void *)(obj + i), 32);
+		switch (n & 0x1) {
+		case 1:
+			memcpy((void *)(ring + idx),
+				(const void *)(obj + i), 16);
+		}
+	} else {
+		for (i = 0; idx < size; i++, idx++)
+			memcpy((void *)(ring + idx),
+				(const void *)(obj + i), 16);
+		/* Start at the beginning */
+		for (idx = 0; i < n; i++, idx++)
+			memcpy((void *)(ring + idx),
+				(const void *)(obj + i), 16);
+	}
+}
+
+/* the actual enqueue of elements on the ring.
+ * Placed here since identical code needed in both
+ * single and multi producer enqueue functions.
+ */
+static __rte_always_inline void
+__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
+		const void *obj_table, uint32_t esize, uint32_t num)
+{
+	/* 8B and 16B copies implemented individually to retain
+	 * the current performance.
+	 */
+	if (esize == 8)
+		__rte_ring_enqueue_elems_64(r, prod_head, obj_table, num);
+	else if (esize == 16)
+		__rte_ring_enqueue_elems_128(r, prod_head, obj_table, num);
+	else {
+		uint32_t idx, scale, nr_idx, nr_num, nr_size;
+
+		/* Normalize to uint32_t */
+		scale = esize / sizeof(uint32_t);
+		nr_num = num * scale;
+		idx = prod_head & r->mask;
+		nr_idx = idx * scale;
+		nr_size = r->size * scale;
+		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
+				obj_table, nr_num);
+	}
+}
+
+static __rte_always_inline void
+__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
+		uint32_t idx, void *obj_table, uint32_t n)
+{
+	unsigned int i;
+	uint32_t *ring = (uint32_t *)&r[1];
+	uint32_t *obj = (uint32_t *)obj_table;
+	if (likely(idx + n < size)) {
+		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
+			obj[i] = ring[idx];
+			obj[i + 1] = ring[idx + 1];
+			obj[i + 2] = ring[idx + 2];
+			obj[i + 3] = ring[idx + 3];
+			obj[i + 4] = ring[idx + 4];
+			obj[i + 5] = ring[idx + 5];
+			obj[i + 6] = ring[idx + 6];
+			obj[i + 7] = ring[idx + 7];
+		}
+		switch (n & 0x7) {
+		case 7:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 6:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 5:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 4:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 3:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 2:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 1:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		}
+	} else {
+		for (i = 0; idx < size; i++, idx++)
+			obj[i] = ring[idx];
+		/* Start at the beginning */
+		for (idx = 0; i < n; i++, idx++)
+			obj[i] = ring[idx];
+	}
+}
+
+static __rte_always_inline void
+__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
+		void *obj_table, uint32_t n)
+{
+	unsigned int i;
+	const uint32_t size = r->size;
+	uint32_t idx = prod_head & r->mask;
+	uint64_t *ring = (uint64_t *)&r[1];
+	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
+	if (likely(idx + n < size)) {
+		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
+			obj[i] = ring[idx];
+			obj[i + 1] = ring[idx + 1];
+			obj[i + 2] = ring[idx + 2];
+			obj[i + 3] = ring[idx + 3];
+		}
+		switch (n & 0x3) {
+		case 3:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 2:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		case 1:
+			obj[i++] = ring[idx++]; /* fallthrough */
+		}
+	} else {
+		for (i = 0; idx < size; i++, idx++)
+			obj[i] = ring[idx];
+		/* Start at the beginning */
+		for (idx = 0; i < n; i++, idx++)
+			obj[i] = ring[idx];
+	}
+}
+
+static __rte_always_inline void
+__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
+		void *obj_table, uint32_t n)
+{
+	unsigned int i;
+	const uint32_t size = r->size;
+	uint32_t idx = prod_head & r->mask;
+	rte_int128_t *ring = (rte_int128_t *)&r[1];
+	rte_int128_t *obj = (rte_int128_t *)obj_table;
+	if (likely(idx + n < size)) {
+		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
+			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
+		switch (n & 0x1) {
+		case 1:
+			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
+		}
+	} else {
+		for (i = 0; idx < size; i++, idx++)
+			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
+		/* Start at the beginning */
+		for (idx = 0; i < n; i++, idx++)
+			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
+	}
+}
+
+/* the actual dequeue of elements from the ring.
+ * Placed here since identical code needed in both
+ * single and multi producer enqueue functions.
+ */
+static __rte_always_inline void
+__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
+		void *obj_table, uint32_t esize, uint32_t num)
+{
+	/* 8B and 16B copies implemented individually to retain
+	 * the current performance.
+	 */
+	if (esize == 8)
+		__rte_ring_dequeue_elems_64(r, cons_head, obj_table, num);
+	else if (esize == 16)
+		__rte_ring_dequeue_elems_128(r, cons_head, obj_table, num);
+	else {
+		uint32_t idx, scale, nr_idx, nr_num, nr_size;
+
+		/* Normalize to uint32_t */
+		scale = esize / sizeof(uint32_t);
+		nr_num = num * scale;
+		idx = cons_head & r->mask;
+		nr_idx = idx * scale;
+		nr_size = r->size * scale;
+		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
+				obj_table, nr_num);
+	}
+}
+
+/* Between load and load. there might be cpu reorder in weak model
+ * (powerpc/arm).
+ * There are 2 choices for the users
+ * 1.use rmb() memory barrier
+ * 2.use one-direction load_acquire/store_release barrier
+ * It depends on performance test results.
+ */
+#ifdef RTE_USE_C11_MEM_MODEL
+#include "ring_c11_pvt.h"
+#else
+#include "ring_generic_pvt.h"
+#endif
+
+/**
+ * @internal Enqueue several objects on the ring
+ *
+ * @param r
+ *   A pointer to the ring structure.
+ * @param obj_table
+ *   A pointer to a table of objects.
+ * @param esize
+ *   The size of ring element, in bytes. It must be a multiple of 4.
+ *   This must be the same value used while creating the ring. Otherwise
+ *   the results are undefined.
+ * @param n
+ *   The number of objects to add in the ring from the obj_table.
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
+ * @param is_sp
+ *   Indicates whether to use single producer or multi-producer head update
+ * @param free_space
+ *   returns the amount of space after the enqueue operation has finished
+ * @return
+ *   Actual number of objects enqueued.
+ *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
+		unsigned int esize, unsigned int n,
+		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
+		unsigned int *free_space)
+{
+	uint32_t prod_head, prod_next;
+	uint32_t free_entries;
+
+	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
+			&prod_head, &prod_next, &free_entries);
+	if (n == 0)
+		goto end;
+
+	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
+
+	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
+end:
+	if (free_space != NULL)
+		*free_space = free_entries - n;
+	return n;
+}
+
+/**
+ * @internal Dequeue several objects from the ring
+ *
+ * @param r
+ *   A pointer to the ring structure.
+ * @param obj_table
+ *   A pointer to a table of objects.
+ * @param esize
+ *   The size of ring element, in bytes. It must be a multiple of 4.
+ *   This must be the same value used while creating the ring. Otherwise
+ *   the results are undefined.
+ * @param n
+ *   The number of objects to pull from the ring.
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
+ * @param is_sc
+ *   Indicates whether to use single consumer or multi-consumer head update
+ * @param available
+ *   returns the number of remaining ring entries after the dequeue has finished
+ * @return
+ *   - Actual number of objects dequeued.
+ *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
+		unsigned int esize, unsigned int n,
+		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
+		unsigned int *available)
+{
+	uint32_t cons_head, cons_next;
+	uint32_t entries;
+
+	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
+			&cons_head, &cons_next, &entries);
+	if (n == 0)
+		goto end;
+
+	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
+
+	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
+
+end:
+	if (available != NULL)
+		*available = entries - n;
+	return n;
+}
+
+#endif /* _RING_ELEM_PVT_H_ */
diff --git a/lib/librte_ring/rte_ring_generic.h b/lib/librte_ring/ring_generic_pvt.h
similarity index 98%
rename from lib/librte_ring/rte_ring_generic.h
rename to lib/librte_ring/ring_generic_pvt.h
index 37c62b8d6..fc46a27b2 100644
--- a/lib/librte_ring/rte_ring_generic.h
+++ b/lib/librte_ring/ring_generic_pvt.h
@@ -7,8 +7,8 @@ 
  * Used as BSD-3 Licensed with permission from Kip Macy.
  */
 
-#ifndef _RTE_RING_GENERIC_H_
-#define _RTE_RING_GENERIC_H_
+#ifndef _RING_GENERIC_PVT_H_
+#define _RING_GENERIC_PVT_H_
 
 static __rte_always_inline void
 __rte_ring_update_tail(struct rte_ring_headtail *ht, uint32_t old_val,
@@ -170,4 +170,4 @@  __rte_ring_move_cons_head(struct rte_ring *r, unsigned int is_sc,
 	return n;
 }
 
-#endif /* _RTE_RING_GENERIC_H_ */
+#endif /* _RING_GENERIC_PVT_H_ */
diff --git a/lib/librte_ring/rte_ring_hts_c11_mem.h b/lib/librte_ring/ring_hts_elem_pvt.h
similarity index 60%
rename from lib/librte_ring/rte_ring_hts_c11_mem.h
rename to lib/librte_ring/ring_hts_elem_pvt.h
index 16e54b6ff..9268750b0 100644
--- a/lib/librte_ring/rte_ring_hts_c11_mem.h
+++ b/lib/librte_ring/ring_hts_elem_pvt.h
@@ -7,8 +7,8 @@ 
  * Used as BSD-3 Licensed with permission from Kip Macy.
  */
 
-#ifndef _RTE_RING_HTS_C11_MEM_H_
-#define _RTE_RING_HTS_C11_MEM_H_
+#ifndef _RING_HTS_ELEM_PVT_H_
+#define _RING_HTS_ELEM_PVT_H_
 
 /**
  * @file rte_ring_hts_c11_mem.h
@@ -161,4 +161,86 @@  __rte_ring_hts_move_cons_head(struct rte_ring *r, unsigned int num,
 	return n;
 }
 
-#endif /* _RTE_RING_HTS_C11_MEM_H_ */
+/**
+ * @internal Enqueue several objects on the HTS ring.
+ *
+ * @param r
+ *   A pointer to the ring structure.
+ * @param obj_table
+ *   A pointer to a table of objects.
+ * @param esize
+ *   The size of ring element, in bytes. It must be a multiple of 4.
+ *   This must be the same value used while creating the ring. Otherwise
+ *   the results are undefined.
+ * @param n
+ *   The number of objects to add in the ring from the obj_table.
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
+ * @param free_space
+ *   returns the amount of space after the enqueue operation has finished
+ * @return
+ *   Actual number of objects enqueued.
+ *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void *obj_table,
+	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
+	uint32_t *free_space)
+{
+	uint32_t free, head;
+
+	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
+
+	if (n != 0) {
+		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
+		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
+	}
+
+	if (free_space != NULL)
+		*free_space = free - n;
+	return n;
+}
+
+/**
+ * @internal Dequeue several objects from the HTS ring.
+ *
+ * @param r
+ *   A pointer to the ring structure.
+ * @param obj_table
+ *   A pointer to a table of objects.
+ * @param esize
+ *   The size of ring element, in bytes. It must be a multiple of 4.
+ *   This must be the same value used while creating the ring. Otherwise
+ *   the results are undefined.
+ * @param n
+ *   The number of objects to pull from the ring.
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
+ * @param available
+ *   returns the number of remaining ring entries after the dequeue has finished
+ * @return
+ *   - Actual number of objects dequeued.
+ *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
+	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
+	uint32_t *available)
+{
+	uint32_t entries, head;
+
+	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head, &entries);
+
+	if (n != 0) {
+		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
+		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
+	}
+
+	if (available != NULL)
+		*available = entries - n;
+	return n;
+}
+
+#endif /* _RING_HTS_ELEM_PVT_H_ */
diff --git a/lib/librte_ring/rte_ring_peek_c11_mem.h b/lib/librte_ring/ring_peek_elem_pvt.h
similarity index 62%
rename from lib/librte_ring/rte_ring_peek_c11_mem.h
rename to lib/librte_ring/ring_peek_elem_pvt.h
index 283c7e70b..1c57bcdd6 100644
--- a/lib/librte_ring/rte_ring_peek_c11_mem.h
+++ b/lib/librte_ring/ring_peek_elem_pvt.h
@@ -7,8 +7,8 @@ 
  * Used as BSD-3 Licensed with permission from Kip Macy.
  */
 
-#ifndef _RTE_RING_PEEK_C11_MEM_H_
-#define _RTE_RING_PEEK_C11_MEM_H_
+#ifndef _RING_PEEK_ELEM_PVT_H_
+#define _RING_PEEK_ELEM_PVT_H_
 
 /**
  * @file rte_ring_peek_c11_mem.h
@@ -107,4 +107,73 @@  __rte_ring_hts_set_head_tail(struct rte_ring_hts_headtail *ht, uint32_t tail,
 	__atomic_store_n(&ht->ht.raw, p.raw, __ATOMIC_RELEASE);
 }
 
-#endif /* _RTE_RING_PEEK_C11_MEM_H_ */
+/**
+ * @internal This function moves prod head value.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
+		enum rte_ring_queue_behavior behavior, uint32_t *free_space)
+{
+	uint32_t free, head, next;
+
+	switch (r->prod.sync_type) {
+	case RTE_RING_SYNC_ST:
+		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
+			behavior, &head, &next, &free);
+		break;
+	case RTE_RING_SYNC_MT_HTS:
+		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
+			&head, &free);
+		break;
+	case RTE_RING_SYNC_MT:
+	case RTE_RING_SYNC_MT_RTS:
+	default:
+		/* unsupported mode, shouldn't be here */
+		RTE_ASSERT(0);
+		n = 0;
+		free = 0;
+	}
+
+	if (free_space != NULL)
+		*free_space = free - n;
+	return n;
+}
+
+/**
+ * @internal This function moves cons head value and copies up to *n*
+ * objects from the ring to the user provided obj_table.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
+	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
+	uint32_t *available)
+{
+	uint32_t avail, head, next;
+
+	switch (r->cons.sync_type) {
+	case RTE_RING_SYNC_ST:
+		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
+			behavior, &head, &next, &avail);
+		break;
+	case RTE_RING_SYNC_MT_HTS:
+		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
+			&head, &avail);
+		break;
+	case RTE_RING_SYNC_MT:
+	case RTE_RING_SYNC_MT_RTS:
+	default:
+		/* unsupported mode, shouldn't be here */
+		RTE_ASSERT(0);
+		n = 0;
+		avail = 0;
+	}
+
+	if (n != 0)
+		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
+
+	if (available != NULL)
+		*available = avail - n;
+	return n;
+}
+
+#endif /* _RING_PEEK_ELEM_PVT_H_ */
diff --git a/lib/librte_ring/rte_ring_rts_c11_mem.h b/lib/librte_ring/ring_rts_elem_pvt.h
similarity index 62%
rename from lib/librte_ring/rte_ring_rts_c11_mem.h
rename to lib/librte_ring/ring_rts_elem_pvt.h
index 327f22796..cbcec73eb 100644
--- a/lib/librte_ring/rte_ring_rts_c11_mem.h
+++ b/lib/librte_ring/ring_rts_elem_pvt.h
@@ -7,8 +7,8 @@ 
  * Used as BSD-3 Licensed with permission from Kip Macy.
  */
 
-#ifndef _RTE_RING_RTS_C11_MEM_H_
-#define _RTE_RING_RTS_C11_MEM_H_
+#ifndef _RING_RTS_ELEM_PVT_H_
+#define _RING_RTS_ELEM_PVT_H_
 
 /**
  * @file rte_ring_rts_c11_mem.h
@@ -176,4 +176,86 @@  __rte_ring_rts_move_cons_head(struct rte_ring *r, uint32_t num,
 	return n;
 }
 
-#endif /* _RTE_RING_RTS_C11_MEM_H_ */
+/**
+ * @internal Enqueue several objects on the RTS ring.
+ *
+ * @param r
+ *   A pointer to the ring structure.
+ * @param obj_table
+ *   A pointer to a table of objects.
+ * @param esize
+ *   The size of ring element, in bytes. It must be a multiple of 4.
+ *   This must be the same value used while creating the ring. Otherwise
+ *   the results are undefined.
+ * @param n
+ *   The number of objects to add in the ring from the obj_table.
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
+ * @param free_space
+ *   returns the amount of space after the enqueue operation has finished
+ * @return
+ *   Actual number of objects enqueued.
+ *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void *obj_table,
+	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
+	uint32_t *free_space)
+{
+	uint32_t free, head;
+
+	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
+
+	if (n != 0) {
+		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
+		__rte_ring_rts_update_tail(&r->rts_prod);
+	}
+
+	if (free_space != NULL)
+		*free_space = free - n;
+	return n;
+}
+
+/**
+ * @internal Dequeue several objects from the RTS ring.
+ *
+ * @param r
+ *   A pointer to the ring structure.
+ * @param obj_table
+ *   A pointer to a table of objects.
+ * @param esize
+ *   The size of ring element, in bytes. It must be a multiple of 4.
+ *   This must be the same value used while creating the ring. Otherwise
+ *   the results are undefined.
+ * @param n
+ *   The number of objects to pull from the ring.
+ * @param behavior
+ *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
+ *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
+ * @param available
+ *   returns the number of remaining ring entries after the dequeue has finished
+ * @return
+ *   - Actual number of objects dequeued.
+ *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
+ */
+static __rte_always_inline unsigned int
+__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
+	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
+	uint32_t *available)
+{
+	uint32_t entries, head;
+
+	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head, &entries);
+
+	if (n != 0) {
+		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
+		__rte_ring_rts_update_tail(&r->rts_cons);
+	}
+
+	if (available != NULL)
+		*available = entries - n;
+	return n;
+}
+
+#endif /* _RING_RTS_ELEM_PVT_H_ */
diff --git a/lib/librte_ring/rte_ring_elem.h b/lib/librte_ring/rte_ring_elem.h
index 57344d47d..119b5c0b6 100644
--- a/lib/librte_ring/rte_ring_elem.h
+++ b/lib/librte_ring/rte_ring_elem.h
@@ -21,6 +21,7 @@  extern "C" {
 #endif
 
 #include <rte_ring_core.h>
+#include <ring_elem_pvt.h>
 
 /**
  * Calculate the memory size needed for a ring with given element size
@@ -105,379 +106,6 @@  ssize_t rte_ring_get_memsize_elem(unsigned int esize, unsigned int count);
 struct rte_ring *rte_ring_create_elem(const char *name, unsigned int esize,
 			unsigned int count, int socket_id, unsigned int flags);
 
-static __rte_always_inline void
-__rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
-		uint32_t idx, const void *obj_table, uint32_t n)
-{
-	unsigned int i;
-	uint32_t *ring = (uint32_t *)&r[1];
-	const uint32_t *obj = (const uint32_t *)obj_table;
-	if (likely(idx + n < size)) {
-		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
-			ring[idx] = obj[i];
-			ring[idx + 1] = obj[i + 1];
-			ring[idx + 2] = obj[i + 2];
-			ring[idx + 3] = obj[i + 3];
-			ring[idx + 4] = obj[i + 4];
-			ring[idx + 5] = obj[i + 5];
-			ring[idx + 6] = obj[i + 6];
-			ring[idx + 7] = obj[i + 7];
-		}
-		switch (n & 0x7) {
-		case 7:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 6:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 5:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 4:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 3:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 2:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 1:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		}
-	} else {
-		for (i = 0; idx < size; i++, idx++)
-			ring[idx] = obj[i];
-		/* Start at the beginning */
-		for (idx = 0; i < n; i++, idx++)
-			ring[idx] = obj[i];
-	}
-}
-
-static __rte_always_inline void
-__rte_ring_enqueue_elems_64(struct rte_ring *r, uint32_t prod_head,
-		const void *obj_table, uint32_t n)
-{
-	unsigned int i;
-	const uint32_t size = r->size;
-	uint32_t idx = prod_head & r->mask;
-	uint64_t *ring = (uint64_t *)&r[1];
-	const unaligned_uint64_t *obj = (const unaligned_uint64_t *)obj_table;
-	if (likely(idx + n < size)) {
-		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
-			ring[idx] = obj[i];
-			ring[idx + 1] = obj[i + 1];
-			ring[idx + 2] = obj[i + 2];
-			ring[idx + 3] = obj[i + 3];
-		}
-		switch (n & 0x3) {
-		case 3:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 2:
-			ring[idx++] = obj[i++]; /* fallthrough */
-		case 1:
-			ring[idx++] = obj[i++];
-		}
-	} else {
-		for (i = 0; idx < size; i++, idx++)
-			ring[idx] = obj[i];
-		/* Start at the beginning */
-		for (idx = 0; i < n; i++, idx++)
-			ring[idx] = obj[i];
-	}
-}
-
-static __rte_always_inline void
-__rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t prod_head,
-		const void *obj_table, uint32_t n)
-{
-	unsigned int i;
-	const uint32_t size = r->size;
-	uint32_t idx = prod_head & r->mask;
-	rte_int128_t *ring = (rte_int128_t *)&r[1];
-	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
-	if (likely(idx + n < size)) {
-		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
-			memcpy((void *)(ring + idx),
-				(const void *)(obj + i), 32);
-		switch (n & 0x1) {
-		case 1:
-			memcpy((void *)(ring + idx),
-				(const void *)(obj + i), 16);
-		}
-	} else {
-		for (i = 0; idx < size; i++, idx++)
-			memcpy((void *)(ring + idx),
-				(const void *)(obj + i), 16);
-		/* Start at the beginning */
-		for (idx = 0; i < n; i++, idx++)
-			memcpy((void *)(ring + idx),
-				(const void *)(obj + i), 16);
-	}
-}
-
-/* the actual enqueue of elements on the ring.
- * Placed here since identical code needed in both
- * single and multi producer enqueue functions.
- */
-static __rte_always_inline void
-__rte_ring_enqueue_elems(struct rte_ring *r, uint32_t prod_head,
-		const void *obj_table, uint32_t esize, uint32_t num)
-{
-	/* 8B and 16B copies implemented individually to retain
-	 * the current performance.
-	 */
-	if (esize == 8)
-		__rte_ring_enqueue_elems_64(r, prod_head, obj_table, num);
-	else if (esize == 16)
-		__rte_ring_enqueue_elems_128(r, prod_head, obj_table, num);
-	else {
-		uint32_t idx, scale, nr_idx, nr_num, nr_size;
-
-		/* Normalize to uint32_t */
-		scale = esize / sizeof(uint32_t);
-		nr_num = num * scale;
-		idx = prod_head & r->mask;
-		nr_idx = idx * scale;
-		nr_size = r->size * scale;
-		__rte_ring_enqueue_elems_32(r, nr_size, nr_idx,
-				obj_table, nr_num);
-	}
-}
-
-static __rte_always_inline void
-__rte_ring_dequeue_elems_32(struct rte_ring *r, const uint32_t size,
-		uint32_t idx, void *obj_table, uint32_t n)
-{
-	unsigned int i;
-	uint32_t *ring = (uint32_t *)&r[1];
-	uint32_t *obj = (uint32_t *)obj_table;
-	if (likely(idx + n < size)) {
-		for (i = 0; i < (n & ~0x7); i += 8, idx += 8) {
-			obj[i] = ring[idx];
-			obj[i + 1] = ring[idx + 1];
-			obj[i + 2] = ring[idx + 2];
-			obj[i + 3] = ring[idx + 3];
-			obj[i + 4] = ring[idx + 4];
-			obj[i + 5] = ring[idx + 5];
-			obj[i + 6] = ring[idx + 6];
-			obj[i + 7] = ring[idx + 7];
-		}
-		switch (n & 0x7) {
-		case 7:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 6:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 5:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 4:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 3:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 2:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 1:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		}
-	} else {
-		for (i = 0; idx < size; i++, idx++)
-			obj[i] = ring[idx];
-		/* Start at the beginning */
-		for (idx = 0; i < n; i++, idx++)
-			obj[i] = ring[idx];
-	}
-}
-
-static __rte_always_inline void
-__rte_ring_dequeue_elems_64(struct rte_ring *r, uint32_t prod_head,
-		void *obj_table, uint32_t n)
-{
-	unsigned int i;
-	const uint32_t size = r->size;
-	uint32_t idx = prod_head & r->mask;
-	uint64_t *ring = (uint64_t *)&r[1];
-	unaligned_uint64_t *obj = (unaligned_uint64_t *)obj_table;
-	if (likely(idx + n < size)) {
-		for (i = 0; i < (n & ~0x3); i += 4, idx += 4) {
-			obj[i] = ring[idx];
-			obj[i + 1] = ring[idx + 1];
-			obj[i + 2] = ring[idx + 2];
-			obj[i + 3] = ring[idx + 3];
-		}
-		switch (n & 0x3) {
-		case 3:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 2:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		case 1:
-			obj[i++] = ring[idx++]; /* fallthrough */
-		}
-	} else {
-		for (i = 0; idx < size; i++, idx++)
-			obj[i] = ring[idx];
-		/* Start at the beginning */
-		for (idx = 0; i < n; i++, idx++)
-			obj[i] = ring[idx];
-	}
-}
-
-static __rte_always_inline void
-__rte_ring_dequeue_elems_128(struct rte_ring *r, uint32_t prod_head,
-		void *obj_table, uint32_t n)
-{
-	unsigned int i;
-	const uint32_t size = r->size;
-	uint32_t idx = prod_head & r->mask;
-	rte_int128_t *ring = (rte_int128_t *)&r[1];
-	rte_int128_t *obj = (rte_int128_t *)obj_table;
-	if (likely(idx + n < size)) {
-		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
-			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
-		switch (n & 0x1) {
-		case 1:
-			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
-		}
-	} else {
-		for (i = 0; idx < size; i++, idx++)
-			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
-		/* Start at the beginning */
-		for (idx = 0; i < n; i++, idx++)
-			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
-	}
-}
-
-/* the actual dequeue of elements from the ring.
- * Placed here since identical code needed in both
- * single and multi producer enqueue functions.
- */
-static __rte_always_inline void
-__rte_ring_dequeue_elems(struct rte_ring *r, uint32_t cons_head,
-		void *obj_table, uint32_t esize, uint32_t num)
-{
-	/* 8B and 16B copies implemented individually to retain
-	 * the current performance.
-	 */
-	if (esize == 8)
-		__rte_ring_dequeue_elems_64(r, cons_head, obj_table, num);
-	else if (esize == 16)
-		__rte_ring_dequeue_elems_128(r, cons_head, obj_table, num);
-	else {
-		uint32_t idx, scale, nr_idx, nr_num, nr_size;
-
-		/* Normalize to uint32_t */
-		scale = esize / sizeof(uint32_t);
-		nr_num = num * scale;
-		idx = cons_head & r->mask;
-		nr_idx = idx * scale;
-		nr_size = r->size * scale;
-		__rte_ring_dequeue_elems_32(r, nr_size, nr_idx,
-				obj_table, nr_num);
-	}
-}
-
-/* Between load and load. there might be cpu reorder in weak model
- * (powerpc/arm).
- * There are 2 choices for the users
- * 1.use rmb() memory barrier
- * 2.use one-direction load_acquire/store_release barrier
- * It depends on performance test results.
- * By default, move common functions to rte_ring_generic.h
- */
-#ifdef RTE_USE_C11_MEM_MODEL
-#include "rte_ring_c11_mem.h"
-#else
-#include "rte_ring_generic.h"
-#endif
-
-/**
- * @internal Enqueue several objects on the ring
- *
- * @param r
- *   A pointer to the ring structure.
- * @param obj_table
- *   A pointer to a table of objects.
- * @param esize
- *   The size of ring element, in bytes. It must be a multiple of 4.
- *   This must be the same value used while creating the ring. Otherwise
- *   the results are undefined.
- * @param n
- *   The number of objects to add in the ring from the obj_table.
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
- * @param is_sp
- *   Indicates whether to use single producer or multi-producer head update
- * @param free_space
- *   returns the amount of space after the enqueue operation has finished
- * @return
- *   Actual number of objects enqueued.
- *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_enqueue_elem(struct rte_ring *r, const void *obj_table,
-		unsigned int esize, unsigned int n,
-		enum rte_ring_queue_behavior behavior, unsigned int is_sp,
-		unsigned int *free_space)
-{
-	uint32_t prod_head, prod_next;
-	uint32_t free_entries;
-
-	n = __rte_ring_move_prod_head(r, is_sp, n, behavior,
-			&prod_head, &prod_next, &free_entries);
-	if (n == 0)
-		goto end;
-
-	__rte_ring_enqueue_elems(r, prod_head, obj_table, esize, n);
-
-	__rte_ring_update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
-end:
-	if (free_space != NULL)
-		*free_space = free_entries - n;
-	return n;
-}
-
-/**
- * @internal Dequeue several objects from the ring
- *
- * @param r
- *   A pointer to the ring structure.
- * @param obj_table
- *   A pointer to a table of objects.
- * @param esize
- *   The size of ring element, in bytes. It must be a multiple of 4.
- *   This must be the same value used while creating the ring. Otherwise
- *   the results are undefined.
- * @param n
- *   The number of objects to pull from the ring.
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
- * @param is_sc
- *   Indicates whether to use single consumer or multi-consumer head update
- * @param available
- *   returns the number of remaining ring entries after the dequeue has finished
- * @return
- *   - Actual number of objects dequeued.
- *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
-		unsigned int esize, unsigned int n,
-		enum rte_ring_queue_behavior behavior, unsigned int is_sc,
-		unsigned int *available)
-{
-	uint32_t cons_head, cons_next;
-	uint32_t entries;
-
-	n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior,
-			&cons_head, &cons_next, &entries);
-	if (n == 0)
-		goto end;
-
-	__rte_ring_dequeue_elems(r, cons_head, obj_table, esize, n);
-
-	__rte_ring_update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
-
-end:
-	if (available != NULL)
-		*available = entries - n;
-	return n;
-}
-
 /**
  * Enqueue several objects on the ring (multi-producers safe).
  *
diff --git a/lib/librte_ring/rte_ring_hts.h b/lib/librte_ring/rte_ring_hts.h
index 359b15771..bdbdafc9f 100644
--- a/lib/librte_ring/rte_ring_hts.h
+++ b/lib/librte_ring/rte_ring_hts.h
@@ -29,89 +29,7 @@ 
 extern "C" {
 #endif
 
-#include <rte_ring_hts_c11_mem.h>
-
-/**
- * @internal Enqueue several objects on the HTS ring.
- *
- * @param r
- *   A pointer to the ring structure.
- * @param obj_table
- *   A pointer to a table of objects.
- * @param esize
- *   The size of ring element, in bytes. It must be a multiple of 4.
- *   This must be the same value used while creating the ring. Otherwise
- *   the results are undefined.
- * @param n
- *   The number of objects to add in the ring from the obj_table.
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
- * @param free_space
- *   returns the amount of space after the enqueue operation has finished
- * @return
- *   Actual number of objects enqueued.
- *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_hts_enqueue_elem(struct rte_ring *r, const void *obj_table,
-	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
-	uint32_t *free_space)
-{
-	uint32_t free, head;
-
-	n =  __rte_ring_hts_move_prod_head(r, n, behavior, &head, &free);
-
-	if (n != 0) {
-		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
-		__rte_ring_hts_update_tail(&r->hts_prod, head, n, 1);
-	}
-
-	if (free_space != NULL)
-		*free_space = free - n;
-	return n;
-}
-
-/**
- * @internal Dequeue several objects from the HTS ring.
- *
- * @param r
- *   A pointer to the ring structure.
- * @param obj_table
- *   A pointer to a table of objects.
- * @param esize
- *   The size of ring element, in bytes. It must be a multiple of 4.
- *   This must be the same value used while creating the ring. Otherwise
- *   the results are undefined.
- * @param n
- *   The number of objects to pull from the ring.
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
- * @param available
- *   returns the number of remaining ring entries after the dequeue has finished
- * @return
- *   - Actual number of objects dequeued.
- *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_hts_dequeue_elem(struct rte_ring *r, void *obj_table,
-	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
-	uint32_t *available)
-{
-	uint32_t entries, head;
-
-	n = __rte_ring_hts_move_cons_head(r, n, behavior, &head, &entries);
-
-	if (n != 0) {
-		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
-		__rte_ring_hts_update_tail(&r->hts_cons, head, n, 0);
-	}
-
-	if (available != NULL)
-		*available = entries - n;
-	return n;
-}
+#include <ring_hts_elem_pvt.h>
 
 /**
  * Enqueue several objects on the HTS ring (multi-producers safe).
diff --git a/lib/librte_ring/rte_ring_peek.h b/lib/librte_ring/rte_ring_peek.h
index 45f707dc7..0dd402be4 100644
--- a/lib/librte_ring/rte_ring_peek.h
+++ b/lib/librte_ring/rte_ring_peek.h
@@ -48,39 +48,7 @@ 
 extern "C" {
 #endif
 
-#include <rte_ring_peek_c11_mem.h>
-
-/**
- * @internal This function moves prod head value.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_enqueue_start(struct rte_ring *r, uint32_t n,
-		enum rte_ring_queue_behavior behavior, uint32_t *free_space)
-{
-	uint32_t free, head, next;
-
-	switch (r->prod.sync_type) {
-	case RTE_RING_SYNC_ST:
-		n = __rte_ring_move_prod_head(r, RTE_RING_SYNC_ST, n,
-			behavior, &head, &next, &free);
-		break;
-	case RTE_RING_SYNC_MT_HTS:
-		n =  __rte_ring_hts_move_prod_head(r, n, behavior,
-			&head, &free);
-		break;
-	case RTE_RING_SYNC_MT:
-	case RTE_RING_SYNC_MT_RTS:
-	default:
-		/* unsupported mode, shouldn't be here */
-		RTE_ASSERT(0);
-		n = 0;
-		free = 0;
-	}
-
-	if (free_space != NULL)
-		*free_space = free - n;
-	return n;
-}
+#include <ring_peek_elem_pvt.h>
 
 /**
  * Start to enqueue several objects on the ring.
@@ -248,43 +216,6 @@  rte_ring_enqueue_finish(struct rte_ring *r, void * const *obj_table,
 	rte_ring_enqueue_elem_finish(r, obj_table, sizeof(uintptr_t), n);
 }
 
-/**
- * @internal This function moves cons head value and copies up to *n*
- * objects from the ring to the user provided obj_table.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_dequeue_start(struct rte_ring *r, void *obj_table,
-	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
-	uint32_t *available)
-{
-	uint32_t avail, head, next;
-
-	switch (r->cons.sync_type) {
-	case RTE_RING_SYNC_ST:
-		n = __rte_ring_move_cons_head(r, RTE_RING_SYNC_ST, n,
-			behavior, &head, &next, &avail);
-		break;
-	case RTE_RING_SYNC_MT_HTS:
-		n =  __rte_ring_hts_move_cons_head(r, n, behavior,
-			&head, &avail);
-		break;
-	case RTE_RING_SYNC_MT:
-	case RTE_RING_SYNC_MT_RTS:
-	default:
-		/* unsupported mode, shouldn't be here */
-		RTE_ASSERT(0);
-		n = 0;
-		avail = 0;
-	}
-
-	if (n != 0)
-		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
-
-	if (available != NULL)
-		*available = avail - n;
-	return n;
-}
-
 /**
  * Start to dequeue several objects from the ring.
  * Note that user has to call appropriate dequeue_finish()
diff --git a/lib/librte_ring/rte_ring_peek_zc.h b/lib/librte_ring/rte_ring_peek_zc.h
index cb3bbd067..bc8252a18 100644
--- a/lib/librte_ring/rte_ring_peek_zc.h
+++ b/lib/librte_ring/rte_ring_peek_zc.h
@@ -72,7 +72,7 @@ 
 extern "C" {
 #endif
 
-#include <rte_ring_peek_c11_mem.h>
+#include <ring_peek_elem_pvt.h>
 
 /**
  * Ring zero-copy information structure.
diff --git a/lib/librte_ring/rte_ring_rts.h b/lib/librte_ring/rte_ring_rts.h
index afc12abe2..83d9903e2 100644
--- a/lib/librte_ring/rte_ring_rts.h
+++ b/lib/librte_ring/rte_ring_rts.h
@@ -56,89 +56,7 @@ 
 extern "C" {
 #endif
 
-#include <rte_ring_rts_c11_mem.h>
-
-/**
- * @internal Enqueue several objects on the RTS ring.
- *
- * @param r
- *   A pointer to the ring structure.
- * @param obj_table
- *   A pointer to a table of objects.
- * @param esize
- *   The size of ring element, in bytes. It must be a multiple of 4.
- *   This must be the same value used while creating the ring. Otherwise
- *   the results are undefined.
- * @param n
- *   The number of objects to add in the ring from the obj_table.
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Enqueue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Enqueue as many items as possible from ring
- * @param free_space
- *   returns the amount of space after the enqueue operation has finished
- * @return
- *   Actual number of objects enqueued.
- *   If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_rts_enqueue_elem(struct rte_ring *r, const void *obj_table,
-	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
-	uint32_t *free_space)
-{
-	uint32_t free, head;
-
-	n =  __rte_ring_rts_move_prod_head(r, n, behavior, &head, &free);
-
-	if (n != 0) {
-		__rte_ring_enqueue_elems(r, head, obj_table, esize, n);
-		__rte_ring_rts_update_tail(&r->rts_prod);
-	}
-
-	if (free_space != NULL)
-		*free_space = free - n;
-	return n;
-}
-
-/**
- * @internal Dequeue several objects from the RTS ring.
- *
- * @param r
- *   A pointer to the ring structure.
- * @param obj_table
- *   A pointer to a table of objects.
- * @param esize
- *   The size of ring element, in bytes. It must be a multiple of 4.
- *   This must be the same value used while creating the ring. Otherwise
- *   the results are undefined.
- * @param n
- *   The number of objects to pull from the ring.
- * @param behavior
- *   RTE_RING_QUEUE_FIXED:    Dequeue a fixed number of items from a ring
- *   RTE_RING_QUEUE_VARIABLE: Dequeue as many items as possible from ring
- * @param available
- *   returns the number of remaining ring entries after the dequeue has finished
- * @return
- *   - Actual number of objects dequeued.
- *     If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only.
- */
-static __rte_always_inline unsigned int
-__rte_ring_do_rts_dequeue_elem(struct rte_ring *r, void *obj_table,
-	uint32_t esize, uint32_t n, enum rte_ring_queue_behavior behavior,
-	uint32_t *available)
-{
-	uint32_t entries, head;
-
-	n = __rte_ring_rts_move_cons_head(r, n, behavior, &head, &entries);
-
-	if (n != 0) {
-		__rte_ring_dequeue_elems(r, head, obj_table, esize, n);
-		__rte_ring_rts_update_tail(&r->rts_cons);
-	}
-
-	if (available != NULL)
-		*available = entries - n;
-	return n;
-}
+#include <ring_rts_elem_pvt.h>
 
 /**
  * Enqueue several objects on the RTS ring (multi-producers safe).