X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_ring%2Frte_ring.h;h=86faede8100611bda3e411ab8f8b991a021724ab;hb=251dab27d517a8dd52b9fa7eb208b3fd18972476;hp=2b6896bf114e1bbb123b2bda5eb7c8df3d87279a;hpb=ecaed092b677d09b4b8645a3ddc38aac0ea929f7;p=dpdk.git diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h index 2b6896bf11..86faede810 100644 --- a/lib/librte_ring/rte_ring.h +++ b/lib/librte_ring/rte_ring.h @@ -1,67 +1,11 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2017 Intel Corporation. All rights reserved. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -/* - * Derived from FreeBSD's bufring.h - * - ************************************************************************** +/* SPDX-License-Identifier: BSD-3-Clause * + * Copyright (c) 2010-2020 Intel Corporation * Copyright (c) 2007-2009 Kip Macy kmacy@freebsd.org * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright notice, - * this list of conditions and the following disclaimer. - * - * 2. The name of Kip Macy nor the names of other - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - * - ***************************************************************************/ + * Derived from FreeBSD's bufring.h + * Used as BSD-3 Licensed with permission from Kip Macy. + */ #ifndef _RTE_RING_H_ #define _RTE_RING_H_ @@ -81,9 +25,13 @@ * - Multi- or single-producer enqueue. * - Bulk dequeue. * - Bulk enqueue. + * - Ability to select different sync modes for producer/consumer. + * - Dequeue start/finish (depending on consumer sync modes). + * - Enqueue start/finish (depending on producer sync mode). * - * Note: the ring implementation is not preemptable. A lcore must not - * be interrupted by another task that uses the same ring. + * Note: the ring implementation is not preemptible. Refer to Programmer's + * guide/Environment Abstraction Layer/Multiple pthread/Known Issues/rte_ring + * for more information. * */ @@ -91,83 +39,7 @@ extern "C" { #endif -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define RTE_TAILQ_RING_NAME "RTE_RING" - -enum rte_ring_queue_behavior { - RTE_RING_QUEUE_FIXED = 0, /* Enq/Deq a fixed number of items from a ring */ - RTE_RING_QUEUE_VARIABLE /* Enq/Deq as many items as possible from ring */ -}; - -#define RTE_RING_MZ_PREFIX "RG_" -/**< The maximum length of a ring name. */ -#define RTE_RING_NAMESIZE (RTE_MEMZONE_NAMESIZE - \ - sizeof(RTE_RING_MZ_PREFIX) + 1) - -struct rte_memzone; /* forward declaration, so as not to require memzone.h */ - -#if RTE_CACHE_LINE_SIZE < 128 -#define PROD_ALIGN (RTE_CACHE_LINE_SIZE * 2) -#define CONS_ALIGN (RTE_CACHE_LINE_SIZE * 2) -#else -#define PROD_ALIGN RTE_CACHE_LINE_SIZE -#define CONS_ALIGN RTE_CACHE_LINE_SIZE -#endif - -/* structure to hold a pair of head/tail values and other metadata */ -struct rte_ring_headtail { - volatile uint32_t head; /**< Prod/consumer head. */ - volatile uint32_t tail; /**< Prod/consumer tail. */ - uint32_t single; /**< True if single prod/cons */ -}; - -/** - * An RTE ring structure. - * - * The producer and the consumer have a head and a tail index. The particularity - * of these index is that they are not between 0 and size(ring). These indexes - * are between 0 and 2^32, and we mask their value when we access the ring[] - * field. Thanks to this assumption, we can do subtractions between 2 index - * values in a modulo-32bit base: that's why the overflow of the indexes is not - * a problem. - */ -struct rte_ring { - /* - * Note: this field kept the RTE_MEMZONE_NAMESIZE size due to ABI - * compatibility requirements, it could be changed to RTE_RING_NAMESIZE - * next time the ABI changes - */ - char name[RTE_MEMZONE_NAMESIZE]; /**< Name of the ring. */ - int flags; /**< Flags supplied at creation. */ - const struct rte_memzone *memzone; - /**< Memzone, if any, containing the rte_ring */ - uint32_t size; /**< Size of ring. */ - uint32_t mask; /**< Mask (size-1) of ring. */ - - /** Ring producer status. */ - struct rte_ring_headtail prod __rte_aligned(PROD_ALIGN); - - /** Ring consumer status. */ - struct rte_ring_headtail cons __rte_aligned(CONS_ALIGN); - - void *ring[] __rte_cache_aligned; /**< Memory space of ring starts here. - * not volatile so need to be careful - * about compiler re-ordering */ -}; - -#define RING_F_SP_ENQ 0x0001 /**< The default enqueue is "single-producer". */ -#define RING_F_SC_DEQ 0x0002 /**< The default dequeue is "single-consumer". */ -#define RTE_RING_SZ_MASK (unsigned)(0x0fffffff) /**< Ring size mask */ +#include /** * Calculate the memory size needed for a ring @@ -210,12 +82,30 @@ ssize_t rte_ring_get_memsize(unsigned count); * The number of elements in the ring (must be a power of 2). * @param flags * An OR of the following: - * - RING_F_SP_ENQ: If this flag is set, the default behavior when - * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` - * is "single-producer". Otherwise, it is "multi-producers". - * - RING_F_SC_DEQ: If this flag is set, the default behavior when - * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` - * is "single-consumer". Otherwise, it is "multi-consumers". + * - One of mutually exclusive flags that define producer behavior: + * - RING_F_SP_ENQ: If this flag is set, the default behavior when + * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` + * is "single-producer". + * - RING_F_MP_RTS_ENQ: If this flag is set, the default behavior when + * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` + * is "multi-producer RTS mode". + * - RING_F_MP_HTS_ENQ: If this flag is set, the default behavior when + * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` + * is "multi-producer HTS mode". + * If none of these flags is set, then default "multi-producer" + * behavior is selected. + * - One of mutually exclusive flags that define consumer behavior: + * - RING_F_SC_DEQ: If this flag is set, the default behavior when + * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` + * is "single-consumer". Otherwise, it is "multi-consumers". + * - RING_F_MC_RTS_DEQ: If this flag is set, the default behavior when + * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` + * is "multi-consumer RTS mode". + * - RING_F_MC_HTS_DEQ: If this flag is set, the default behavior when + * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` + * is "multi-consumer HTS mode". + * If none of these flags is set, then default "multi-consumer" + * behavior is selected. * @return * 0 on success, or a negative value on error. */ @@ -245,12 +135,30 @@ int rte_ring_init(struct rte_ring *r, const char *name, unsigned count, * constraint for the reserved zone. * @param flags * An OR of the following: - * - RING_F_SP_ENQ: If this flag is set, the default behavior when - * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` - * is "single-producer". Otherwise, it is "multi-producers". - * - RING_F_SC_DEQ: If this flag is set, the default behavior when - * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` - * is "single-consumer". Otherwise, it is "multi-consumers". + * - One of mutually exclusive flags that define producer behavior: + * - RING_F_SP_ENQ: If this flag is set, the default behavior when + * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` + * is "single-producer". + * - RING_F_MP_RTS_ENQ: If this flag is set, the default behavior when + * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` + * is "multi-producer RTS mode". + * - RING_F_MP_HTS_ENQ: If this flag is set, the default behavior when + * using ``rte_ring_enqueue()`` or ``rte_ring_enqueue_bulk()`` + * is "multi-producer HTS mode". + * If none of these flags is set, then default "multi-producer" + * behavior is selected. + * - One of mutually exclusive flags that define consumer behavior: + * - RING_F_SC_DEQ: If this flag is set, the default behavior when + * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` + * is "single-consumer". Otherwise, it is "multi-consumers". + * - RING_F_MC_RTS_DEQ: If this flag is set, the default behavior when + * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` + * is "multi-consumer RTS mode". + * - RING_F_MC_HTS_DEQ: If this flag is set, the default behavior when + * using ``rte_ring_dequeue()`` or ``rte_ring_dequeue_bulk()`` + * is "multi-consumer HTS mode". + * If none of these flags is set, then default "multi-consumer" + * behavior is selected. * @return * On success, the pointer to the new allocated ring. NULL on error with * rte_errno set appropriately. Possible errno values include: @@ -263,6 +171,7 @@ int rte_ring_init(struct rte_ring *r, const char *name, unsigned count, */ struct rte_ring *rte_ring_create(const char *name, unsigned count, int socket_id, unsigned flags); + /** * De-allocate all memory used by the ring. * @@ -284,134 +193,84 @@ void rte_ring_dump(FILE *f, const struct rte_ring *r); /* the actual enqueue of pointers on the ring. * Placed here since identical code needed in both * single and multi producer enqueue functions */ -#define ENQUEUE_PTRS() do { \ - const uint32_t size = r->size; \ - uint32_t idx = prod_head & mask; \ +#define ENQUEUE_PTRS(r, ring_start, prod_head, obj_table, n, obj_type) do { \ + unsigned int i; \ + const uint32_t size = (r)->size; \ + uint32_t idx = prod_head & (r)->mask; \ + obj_type *ring = (obj_type *)ring_start; \ if (likely(idx + n < size)) { \ for (i = 0; i < (n & ((~(unsigned)0x3))); i+=4, idx+=4) { \ - r->ring[idx] = obj_table[i]; \ - r->ring[idx+1] = obj_table[i+1]; \ - r->ring[idx+2] = obj_table[i+2]; \ - r->ring[idx+3] = obj_table[i+3]; \ + ring[idx] = obj_table[i]; \ + ring[idx+1] = obj_table[i+1]; \ + ring[idx+2] = obj_table[i+2]; \ + ring[idx+3] = obj_table[i+3]; \ } \ switch (n & 0x3) { \ - case 3: r->ring[idx++] = obj_table[i++]; \ - case 2: r->ring[idx++] = obj_table[i++]; \ - case 1: r->ring[idx++] = obj_table[i++]; \ + case 3: \ + ring[idx++] = obj_table[i++]; /* fallthrough */ \ + case 2: \ + ring[idx++] = obj_table[i++]; /* fallthrough */ \ + case 1: \ + ring[idx++] = obj_table[i++]; \ } \ } else { \ for (i = 0; idx < size; i++, idx++)\ - r->ring[idx] = obj_table[i]; \ + ring[idx] = obj_table[i]; \ for (idx = 0; i < n; i++, idx++) \ - r->ring[idx] = obj_table[i]; \ + ring[idx] = obj_table[i]; \ } \ -} while(0) +} while (0) /* the actual copy of pointers on the ring to obj_table. * Placed here since identical code needed in both * single and multi consumer dequeue functions */ -#define DEQUEUE_PTRS() do { \ - uint32_t idx = cons_head & mask; \ - const uint32_t size = r->size; \ +#define DEQUEUE_PTRS(r, ring_start, cons_head, obj_table, n, obj_type) do { \ + unsigned int i; \ + uint32_t idx = cons_head & (r)->mask; \ + const uint32_t size = (r)->size; \ + obj_type *ring = (obj_type *)ring_start; \ if (likely(idx + n < size)) { \ for (i = 0; i < (n & (~(unsigned)0x3)); i+=4, idx+=4) {\ - obj_table[i] = r->ring[idx]; \ - obj_table[i+1] = r->ring[idx+1]; \ - obj_table[i+2] = r->ring[idx+2]; \ - obj_table[i+3] = r->ring[idx+3]; \ + obj_table[i] = ring[idx]; \ + obj_table[i+1] = ring[idx+1]; \ + obj_table[i+2] = ring[idx+2]; \ + obj_table[i+3] = ring[idx+3]; \ } \ switch (n & 0x3) { \ - case 3: obj_table[i++] = r->ring[idx++]; \ - case 2: obj_table[i++] = r->ring[idx++]; \ - case 1: obj_table[i++] = r->ring[idx++]; \ + case 3: \ + obj_table[i++] = ring[idx++]; /* fallthrough */ \ + case 2: \ + obj_table[i++] = ring[idx++]; /* fallthrough */ \ + case 1: \ + obj_table[i++] = ring[idx++]; \ } \ } else { \ for (i = 0; idx < size; i++, idx++) \ - obj_table[i] = r->ring[idx]; \ + obj_table[i] = ring[idx]; \ for (idx = 0; i < n; i++, idx++) \ - obj_table[i] = r->ring[idx]; \ + obj_table[i] = ring[idx]; \ } \ } while (0) -/** - * @internal Enqueue several objects on the ring (multi-producers safe). - * - * This function uses a "compare and set" instruction to move the - * producer index atomically. - * - * @param r - * A pointer to the ring structure. - * @param obj_table - * A pointer to a table of void * pointers (objects). - * @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 a possible from ring - * @return - * Actual number of objects enqueued. - * If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only. +/* 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,defined by + * CONFIG_RTE_USE_C11_MEM_MODEL=y + * It depends on performance test results. + * By default, move common functions to rte_ring_generic.h */ -static inline unsigned int __attribute__((always_inline)) -__rte_ring_mp_do_enqueue(struct rte_ring *r, void * const *obj_table, - unsigned int n, enum rte_ring_queue_behavior behavior, - unsigned int *free_space) -{ - uint32_t prod_head, prod_next; - uint32_t cons_tail, free_entries; - const unsigned int max = n; - int success; - unsigned int i; - uint32_t mask = r->mask; - - /* move prod.head atomically */ - do { - /* Reset n to the initial burst count */ - n = max; - - prod_head = r->prod.head; - cons_tail = r->cons.tail; - /* The subtraction is done between two unsigned 32bits value - * (the result is always modulo 32 bits even if we have - * prod_head > cons_tail). So 'free_entries' is always between 0 - * and size(ring)-1. */ - free_entries = (mask + cons_tail - prod_head); - - /* check that we have enough room in ring */ - if (unlikely(n > free_entries)) - n = (behavior == RTE_RING_QUEUE_FIXED) ? - 0 : free_entries; - - if (n == 0) - goto end; - - prod_next = prod_head + n; - success = rte_atomic32_cmpset(&r->prod.head, prod_head, - prod_next); - } while (unlikely(success == 0)); - - /* write entries in ring */ - ENQUEUE_PTRS(); - rte_smp_wmb(); - - /* - * If there are other enqueues in progress that preceded us, - * we need to wait for them to complete - */ - while (unlikely(r->prod.tail != prod_head)) - rte_pause(); - - r->prod.tail = prod_next; -end: - if (free_space != NULL) - *free_space = free_entries - n; - return n; -} +#ifdef RTE_USE_C11_MEM_MODEL +#include "rte_ring_c11_mem.h" +#else +#include "rte_ring_generic.h" +#endif /** - * @internal Enqueue several objects on a ring (NOT multi-producers safe). + * @internal Enqueue several objects on the ring * - * @param r + * @param r * A pointer to the ring structure. * @param obj_table * A pointer to a table of void * pointers (objects). @@ -419,45 +278,31 @@ end: * 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 a possible from 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 inline unsigned int __attribute__((always_inline)) -__rte_ring_sp_do_enqueue(struct rte_ring *r, void * const *obj_table, - unsigned int n, enum rte_ring_queue_behavior behavior, - unsigned int *free_space) +static __rte_always_inline unsigned int +__rte_ring_do_enqueue(struct rte_ring *r, void * const *obj_table, + unsigned int n, enum rte_ring_queue_behavior behavior, + unsigned int is_sp, unsigned int *free_space) { - uint32_t prod_head, cons_tail; - uint32_t prod_next, free_entries; - unsigned int i; - uint32_t mask = r->mask; - - prod_head = r->prod.head; - cons_tail = r->cons.tail; - /* The subtraction is done between two unsigned 32bits value - * (the result is always modulo 32 bits even if we have - * prod_head > cons_tail). So 'free_entries' is always between 0 - * and size(ring)-1. */ - free_entries = mask + cons_tail - prod_head; - - /* check that we have enough room in ring */ - if (unlikely(n > free_entries)) - n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : free_entries; + 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; + ENQUEUE_PTRS(r, &r[1], prod_head, obj_table, n, void *); - prod_next = prod_head + n; - r->prod.head = prod_next; - - /* write entries in ring */ - ENQUEUE_PTRS(); - rte_smp_wmb(); - - r->prod.tail = prod_next; + update_tail(&r->prod, prod_head, prod_next, is_sp, 1); end: if (free_space != NULL) *free_space = free_entries - n; @@ -465,132 +310,42 @@ end: } /** - * @internal Dequeue several objects from a ring (multi-consumers safe). When - * the request objects are more than the available objects, only dequeue the - * actual number of objects - * - * This function uses a "compare and set" instruction to move the - * consumer index atomically. - * - * @param r - * A pointer to the ring structure. - * @param obj_table - * A pointer to a table of void * pointers (objects) that will be filled. - * @param n - * The number of objects to dequeue from the ring to the obj_table. - * @param behavior - * RTE_RING_QUEUE_FIXED: Dequeue a fixed number of items from a ring - * RTE_RING_QUEUE_VARIABLE: Dequeue as many items a possible from ring - * @return - * - Actual number of objects dequeued. - * If behavior == RTE_RING_QUEUE_FIXED, this will be 0 or n only. - */ - -static inline unsigned int __attribute__((always_inline)) -__rte_ring_mc_do_dequeue(struct rte_ring *r, void **obj_table, - unsigned int n, enum rte_ring_queue_behavior behavior, - unsigned int *available) -{ - uint32_t cons_head, prod_tail; - uint32_t cons_next, entries; - const unsigned max = n; - int success; - unsigned int i; - uint32_t mask = r->mask; - - /* move cons.head atomically */ - do { - /* Restore n as it may change every loop */ - n = max; - - cons_head = r->cons.head; - prod_tail = r->prod.tail; - /* The subtraction is done between two unsigned 32bits value - * (the result is always modulo 32 bits even if we have - * cons_head > prod_tail). So 'entries' is always between 0 - * and size(ring)-1. */ - entries = (prod_tail - cons_head); - - /* Set the actual entries for dequeue */ - if (n > entries) - n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : entries; - - if (unlikely(n == 0)) - goto end; - - cons_next = cons_head + n; - success = rte_atomic32_cmpset(&r->cons.head, cons_head, - cons_next); - } while (unlikely(success == 0)); - - /* copy in table */ - DEQUEUE_PTRS(); - rte_smp_rmb(); - - /* - * If there are other dequeues in progress that preceded us, - * we need to wait for them to complete - */ - while (unlikely(r->cons.tail != cons_head)) - rte_pause(); - - r->cons.tail = cons_next; -end: - if (available != NULL) - *available = entries - n; - return n; -} - -/** - * @internal Dequeue several objects from a ring (NOT multi-consumers safe). - * When the request objects are more than the available objects, only dequeue - * the actual number of objects + * @internal Dequeue several objects from the ring * * @param r * A pointer to the ring structure. * @param obj_table - * A pointer to a table of void * pointers (objects) that will be filled. + * A pointer to a table of void * pointers (objects). * @param n - * The number of objects to dequeue from the ring to the obj_table. + * 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 a possible from 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 inline unsigned int __attribute__((always_inline)) -__rte_ring_sc_do_dequeue(struct rte_ring *r, void **obj_table, +static __rte_always_inline unsigned int +__rte_ring_do_dequeue(struct rte_ring *r, void **obj_table, unsigned int n, enum rte_ring_queue_behavior behavior, - unsigned int *available) + unsigned int is_sc, unsigned int *available) { - uint32_t cons_head, prod_tail; - uint32_t cons_next, entries; - unsigned int i; - uint32_t mask = r->mask; - - cons_head = r->cons.head; - prod_tail = r->prod.tail; - /* The subtraction is done between two unsigned 32bits value - * (the result is always modulo 32 bits even if we have - * cons_head > prod_tail). So 'entries' is always between 0 - * and size(ring)-1. */ - entries = prod_tail - cons_head; - - if (n > entries) - n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : entries; + uint32_t cons_head, cons_next; + uint32_t entries; - if (unlikely(entries == 0)) + n = __rte_ring_move_cons_head(r, (int)is_sc, n, behavior, + &cons_head, &cons_next, &entries); + if (n == 0) goto end; - cons_next = cons_head + n; - r->cons.head = cons_next; + DEQUEUE_PTRS(r, &r[1], cons_head, obj_table, n, void *); - /* copy in table */ - DEQUEUE_PTRS(); - rte_smp_rmb(); + update_tail(&r->cons, cons_head, cons_next, is_sc, 0); - r->cons.tail = cons_next; end: if (available != NULL) *available = entries - n; @@ -615,12 +370,12 @@ end: * @return * The number of objects enqueued, either 0 or n */ -static inline unsigned int __attribute__((always_inline)) +static __rte_always_inline unsigned int rte_ring_mp_enqueue_bulk(struct rte_ring *r, void * const *obj_table, unsigned int n, unsigned int *free_space) { - return __rte_ring_mp_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED, - free_space); + return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED, + RTE_RING_SYNC_MT, free_space); } /** @@ -638,14 +393,18 @@ rte_ring_mp_enqueue_bulk(struct rte_ring *r, void * const *obj_table, * @return * The number of objects enqueued, either 0 or n */ -static inline unsigned int __attribute__((always_inline)) +static __rte_always_inline unsigned int rte_ring_sp_enqueue_bulk(struct rte_ring *r, void * const *obj_table, unsigned int n, unsigned int *free_space) { - return __rte_ring_sp_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED, - free_space); + return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED, + RTE_RING_SYNC_ST, free_space); } +#ifdef ALLOW_EXPERIMENTAL_API +#include +#endif + /** * Enqueue several objects on a ring. * @@ -665,14 +424,28 @@ rte_ring_sp_enqueue_bulk(struct rte_ring *r, void * const *obj_table, * @return * The number of objects enqueued, either 0 or n */ -static inline unsigned int __attribute__((always_inline)) +static __rte_always_inline unsigned int rte_ring_enqueue_bulk(struct rte_ring *r, void * const *obj_table, unsigned int n, unsigned int *free_space) { - if (r->prod.single) - return rte_ring_sp_enqueue_bulk(r, obj_table, n, free_space); - else + switch (r->prod.sync_type) { + case RTE_RING_SYNC_MT: return rte_ring_mp_enqueue_bulk(r, obj_table, n, free_space); + case RTE_RING_SYNC_ST: + return rte_ring_sp_enqueue_bulk(r, obj_table, n, free_space); +#ifdef ALLOW_EXPERIMENTAL_API + case RTE_RING_SYNC_MT_RTS: + return rte_ring_mp_rts_enqueue_bulk(r, obj_table, n, + free_space); + case RTE_RING_SYNC_MT_HTS: + return rte_ring_mp_hts_enqueue_bulk(r, obj_table, n, + free_space); +#endif + } + + /* valid ring should never reach this point */ + RTE_ASSERT(0); + return 0; } /** @@ -689,7 +462,7 @@ rte_ring_enqueue_bulk(struct rte_ring *r, void * const *obj_table, * - 0: Success; objects enqueued. * - -ENOBUFS: Not enough room in the ring to enqueue; no object is enqueued. */ -static inline int __attribute__((always_inline)) +static __rte_always_inline int rte_ring_mp_enqueue(struct rte_ring *r, void *obj) { return rte_ring_mp_enqueue_bulk(r, &obj, 1, NULL) ? 0 : -ENOBUFS; @@ -706,7 +479,7 @@ rte_ring_mp_enqueue(struct rte_ring *r, void *obj) * - 0: Success; objects enqueued. * - -ENOBUFS: Not enough room in the ring to enqueue; no object is enqueued. */ -static inline int __attribute__((always_inline)) +static __rte_always_inline int rte_ring_sp_enqueue(struct rte_ring *r, void *obj) { return rte_ring_sp_enqueue_bulk(r, &obj, 1, NULL) ? 0 : -ENOBUFS; @@ -727,7 +500,7 @@ rte_ring_sp_enqueue(struct rte_ring *r, void *obj) * - 0: Success; objects enqueued. * - -ENOBUFS: Not enough room in the ring to enqueue; no object is enqueued. */ -static inline int __attribute__((always_inline)) +static __rte_always_inline int rte_ring_enqueue(struct rte_ring *r, void *obj) { return rte_ring_enqueue_bulk(r, &obj, 1, NULL) ? 0 : -ENOBUFS; @@ -751,12 +524,12 @@ rte_ring_enqueue(struct rte_ring *r, void *obj) * @return * The number of objects dequeued, either 0 or n */ -static inline unsigned int __attribute__((always_inline)) +static __rte_always_inline unsigned int rte_ring_mc_dequeue_bulk(struct rte_ring *r, void **obj_table, unsigned int n, unsigned int *available) { - return __rte_ring_mc_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED, - available); + return __rte_ring_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED, + RTE_RING_SYNC_MT, available); } /** @@ -775,12 +548,12 @@ rte_ring_mc_dequeue_bulk(struct rte_ring *r, void **obj_table, * @return * The number of objects dequeued, either 0 or n */ -static inline unsigned int __attribute__((always_inline)) +static __rte_always_inline unsigned int rte_ring_sc_dequeue_bulk(struct rte_ring *r, void **obj_table, unsigned int n, unsigned int *available) { - return __rte_ring_sc_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED, - available); + return __rte_ring_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED, + RTE_RING_SYNC_ST, available); } /** @@ -802,14 +575,26 @@ rte_ring_sc_dequeue_bulk(struct rte_ring *r, void **obj_table, * @return * The number of objects dequeued, either 0 or n */ -static inline unsigned int __attribute__((always_inline)) +static __rte_always_inline unsigned int rte_ring_dequeue_bulk(struct rte_ring *r, void **obj_table, unsigned int n, unsigned int *available) { - if (r->cons.single) - return rte_ring_sc_dequeue_bulk(r, obj_table, n, available); - else + switch (r->cons.sync_type) { + case RTE_RING_SYNC_MT: return rte_ring_mc_dequeue_bulk(r, obj_table, n, available); + case RTE_RING_SYNC_ST: + return rte_ring_sc_dequeue_bulk(r, obj_table, n, available); +#ifdef ALLOW_EXPERIMENTAL_API + case RTE_RING_SYNC_MT_RTS: + return rte_ring_mc_rts_dequeue_bulk(r, obj_table, n, available); + case RTE_RING_SYNC_MT_HTS: + return rte_ring_mc_hts_dequeue_bulk(r, obj_table, n, available); +#endif + } + + /* valid ring should never reach this point */ + RTE_ASSERT(0); + return 0; } /** @@ -827,10 +612,10 @@ rte_ring_dequeue_bulk(struct rte_ring *r, void **obj_table, unsigned int n, * - -ENOENT: Not enough entries in the ring to dequeue; no object is * dequeued. */ -static inline int __attribute__((always_inline)) +static __rte_always_inline int rte_ring_mc_dequeue(struct rte_ring *r, void **obj_p) { - return rte_ring_mc_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOBUFS; + return rte_ring_mc_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOENT; } /** @@ -845,10 +630,10 @@ rte_ring_mc_dequeue(struct rte_ring *r, void **obj_p) * - -ENOENT: Not enough entries in the ring to dequeue, no object is * dequeued. */ -static inline int __attribute__((always_inline)) +static __rte_always_inline int rte_ring_sc_dequeue(struct rte_ring *r, void **obj_p) { - return rte_ring_sc_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOBUFS; + return rte_ring_sc_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOENT; } /** @@ -867,10 +652,58 @@ rte_ring_sc_dequeue(struct rte_ring *r, void **obj_p) * - -ENOENT: Not enough entries in the ring to dequeue, no object is * dequeued. */ -static inline int __attribute__((always_inline)) +static __rte_always_inline int rte_ring_dequeue(struct rte_ring *r, void **obj_p) { - return rte_ring_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOBUFS; + return rte_ring_dequeue_bulk(r, obj_p, 1, NULL) ? 0 : -ENOENT; +} + +/** + * Flush a ring. + * + * This function flush all the elements in a ring + * + * @b EXPERIMENTAL: this API may change without prior notice + * + * @warning + * Make sure the ring is not in use while calling this function. + * + * @param r + * A pointer to the ring structure. + */ +__rte_experimental +void +rte_ring_reset(struct rte_ring *r); + +/** + * Return the number of entries in a ring. + * + * @param r + * A pointer to the ring structure. + * @return + * The number of entries in the ring. + */ +static inline unsigned +rte_ring_count(const struct rte_ring *r) +{ + uint32_t prod_tail = r->prod.tail; + uint32_t cons_tail = r->cons.tail; + uint32_t count = (prod_tail - cons_tail) & r->mask; + return (count > r->capacity) ? r->capacity : count; +} + +/** + * Return the number of free entries in a ring. + * + * @param r + * A pointer to the ring structure. + * @return + * The number of free entries in the ring. + */ +static inline unsigned +rte_ring_free_count(const struct rte_ring *r) +{ + return r->capacity - rte_ring_count(r); } /** @@ -885,9 +718,7 @@ rte_ring_dequeue(struct rte_ring *r, void **obj_p) static inline int rte_ring_full(const struct rte_ring *r) { - uint32_t prod_tail = r->prod.tail; - uint32_t cons_tail = r->cons.tail; - return ((cons_tail - prod_tail - 1) & r->mask) == 0; + return rte_ring_free_count(r) == 0; } /** @@ -902,55 +733,93 @@ rte_ring_full(const struct rte_ring *r) static inline int rte_ring_empty(const struct rte_ring *r) { - uint32_t prod_tail = r->prod.tail; - uint32_t cons_tail = r->cons.tail; - return !!(cons_tail == prod_tail); + return rte_ring_count(r) == 0; } /** - * Return the number of entries in a ring. + * Return the size of the ring. * * @param r * A pointer to the ring structure. * @return - * The number of entries in the ring. + * The size of the data store used by the ring. + * NOTE: this is not the same as the usable space in the ring. To query that + * use ``rte_ring_get_capacity()``. */ -static inline unsigned -rte_ring_count(const struct rte_ring *r) +static inline unsigned int +rte_ring_get_size(const struct rte_ring *r) { - uint32_t prod_tail = r->prod.tail; - uint32_t cons_tail = r->cons.tail; - return (prod_tail - cons_tail) & r->mask; + return r->size; } /** - * Return the number of free entries in a ring. + * Return the number of elements which can be stored in the ring. * * @param r * A pointer to the ring structure. * @return - * The number of free entries in the ring. + * The usable size of the ring. */ -static inline unsigned -rte_ring_free_count(const struct rte_ring *r) +static inline unsigned int +rte_ring_get_capacity(const struct rte_ring *r) { - uint32_t prod_tail = r->prod.tail; - uint32_t cons_tail = r->cons.tail; - return (cons_tail - prod_tail - 1) & r->mask; + return r->capacity; } /** - * Return the size of the ring. + * Return sync type used by producer in the ring. * * @param r * A pointer to the ring structure. * @return - * The number of elements which can be stored in the ring. + * Producer sync type value. */ -static inline unsigned int -rte_ring_get_size(const struct rte_ring *r) +static inline enum rte_ring_sync_type +rte_ring_get_prod_sync_type(const struct rte_ring *r) { - return r->size; + return r->prod.sync_type; +} + +/** + * Check is the ring for single producer. + * + * @param r + * A pointer to the ring structure. + * @return + * true if ring is SP, zero otherwise. + */ +static inline int +rte_ring_is_prod_single(const struct rte_ring *r) +{ + return (rte_ring_get_prod_sync_type(r) == RTE_RING_SYNC_ST); +} + +/** + * Return sync type used by consumer in the ring. + * + * @param r + * A pointer to the ring structure. + * @return + * Consumer sync type value. + */ +static inline enum rte_ring_sync_type +rte_ring_get_cons_sync_type(const struct rte_ring *r) +{ + return r->cons.sync_type; +} + +/** + * Check is the ring for single consumer. + * + * @param r + * A pointer to the ring structure. + * @return + * true if ring is SC, zero otherwise. + */ +static inline int +rte_ring_is_cons_single(const struct rte_ring *r) +{ + return (rte_ring_get_cons_sync_type(r) == RTE_RING_SYNC_ST); } /** @@ -991,12 +860,12 @@ struct rte_ring *rte_ring_lookup(const char *name); * @return * - n: Actual number of objects enqueued. */ -static inline unsigned __attribute__((always_inline)) +static __rte_always_inline unsigned rte_ring_mp_enqueue_burst(struct rte_ring *r, void * const *obj_table, unsigned int n, unsigned int *free_space) { - return __rte_ring_mp_do_enqueue(r, obj_table, n, - RTE_RING_QUEUE_VARIABLE, free_space); + return __rte_ring_do_enqueue(r, obj_table, n, + RTE_RING_QUEUE_VARIABLE, RTE_RING_SYNC_MT, free_space); } /** @@ -1014,12 +883,12 @@ rte_ring_mp_enqueue_burst(struct rte_ring *r, void * const *obj_table, * @return * - n: Actual number of objects enqueued. */ -static inline unsigned __attribute__((always_inline)) +static __rte_always_inline unsigned rte_ring_sp_enqueue_burst(struct rte_ring *r, void * const *obj_table, unsigned int n, unsigned int *free_space) { - return __rte_ring_sp_do_enqueue(r, obj_table, n, - RTE_RING_QUEUE_VARIABLE, free_space); + return __rte_ring_do_enqueue(r, obj_table, n, + RTE_RING_QUEUE_VARIABLE, RTE_RING_SYNC_ST, free_space); } /** @@ -1041,14 +910,28 @@ rte_ring_sp_enqueue_burst(struct rte_ring *r, void * const *obj_table, * @return * - n: Actual number of objects enqueued. */ -static inline unsigned __attribute__((always_inline)) +static __rte_always_inline unsigned rte_ring_enqueue_burst(struct rte_ring *r, void * const *obj_table, unsigned int n, unsigned int *free_space) { - if (r->prod.single) - return rte_ring_sp_enqueue_burst(r, obj_table, n, free_space); - else + switch (r->prod.sync_type) { + case RTE_RING_SYNC_MT: return rte_ring_mp_enqueue_burst(r, obj_table, n, free_space); + case RTE_RING_SYNC_ST: + return rte_ring_sp_enqueue_burst(r, obj_table, n, free_space); +#ifdef ALLOW_EXPERIMENTAL_API + case RTE_RING_SYNC_MT_RTS: + return rte_ring_mp_rts_enqueue_burst(r, obj_table, n, + free_space); + case RTE_RING_SYNC_MT_HTS: + return rte_ring_mp_hts_enqueue_burst(r, obj_table, n, + free_space); +#endif + } + + /* valid ring should never reach this point */ + RTE_ASSERT(0); + return 0; } /** @@ -1071,12 +954,12 @@ rte_ring_enqueue_burst(struct rte_ring *r, void * const *obj_table, * @return * - n: Actual number of objects dequeued, 0 if ring is empty */ -static inline unsigned __attribute__((always_inline)) +static __rte_always_inline unsigned rte_ring_mc_dequeue_burst(struct rte_ring *r, void **obj_table, unsigned int n, unsigned int *available) { - return __rte_ring_mc_do_dequeue(r, obj_table, n, - RTE_RING_QUEUE_VARIABLE, available); + return __rte_ring_do_dequeue(r, obj_table, n, + RTE_RING_QUEUE_VARIABLE, RTE_RING_SYNC_MT, available); } /** @@ -1096,12 +979,12 @@ rte_ring_mc_dequeue_burst(struct rte_ring *r, void **obj_table, * @return * - n: Actual number of objects dequeued, 0 if ring is empty */ -static inline unsigned __attribute__((always_inline)) +static __rte_always_inline unsigned rte_ring_sc_dequeue_burst(struct rte_ring *r, void **obj_table, unsigned int n, unsigned int *available) { - return __rte_ring_sc_do_dequeue(r, obj_table, n, - RTE_RING_QUEUE_VARIABLE, available); + return __rte_ring_do_dequeue(r, obj_table, n, + RTE_RING_QUEUE_VARIABLE, RTE_RING_SYNC_ST, available); } /** @@ -1123,14 +1006,28 @@ rte_ring_sc_dequeue_burst(struct rte_ring *r, void **obj_table, * @return * - Number of objects dequeued */ -static inline unsigned __attribute__((always_inline)) +static __rte_always_inline unsigned rte_ring_dequeue_burst(struct rte_ring *r, void **obj_table, unsigned int n, unsigned int *available) { - if (r->cons.single) - return rte_ring_sc_dequeue_burst(r, obj_table, n, available); - else + switch (r->cons.sync_type) { + case RTE_RING_SYNC_MT: return rte_ring_mc_dequeue_burst(r, obj_table, n, available); + case RTE_RING_SYNC_ST: + return rte_ring_sc_dequeue_burst(r, obj_table, n, available); +#ifdef ALLOW_EXPERIMENTAL_API + case RTE_RING_SYNC_MT_RTS: + return rte_ring_mc_rts_dequeue_burst(r, obj_table, n, + available); + case RTE_RING_SYNC_MT_HTS: + return rte_ring_mc_hts_dequeue_burst(r, obj_table, n, + available); +#endif + } + + /* valid ring should never reach this point */ + RTE_ASSERT(0); + return 0; } #ifdef __cplusplus