From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 5C80EA0562; Fri, 3 Apr 2020 19:44:14 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id A77201C228; Fri, 3 Apr 2020 19:43:16 +0200 (CEST) Received: from mga12.intel.com (mga12.intel.com [192.55.52.136]) by dpdk.org (Postfix) with ESMTP id 77B701C228 for ; Fri, 3 Apr 2020 19:43:14 +0200 (CEST) IronPort-SDR: WrmPms0vpgbn1bdFeUKfHqeYoohVJpi0T4fQtatKgm+nEIcFVfd0FiGMht+R0xcG+gdqu+247e WlXZVJdXLWnQ== X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by fmsmga106.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 03 Apr 2020 10:43:14 -0700 IronPort-SDR: W1M/Z0NcRUDJHC4UWeWyR6tlIg1dy8GdzdYzzLDBtKvix9Ur1zGtG5NugYl6dzTu2p0KI9CXjM UXdId+GWHiEw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.72,340,1580803200"; d="scan'208";a="296048768" Received: from sivswdev08.ir.intel.com ([10.237.217.47]) by FMSMGA003.fm.intel.com with ESMTP; 03 Apr 2020 10:43:12 -0700 From: Konstantin Ananyev To: dev@dpdk.org Cc: honnappa.nagarahalli@arm.com, david.marchand@redhat.com, jielong.zjl@antfin.com, Konstantin Ananyev Date: Fri, 3 Apr 2020 18:42:33 +0100 Message-Id: <20200403174235.23308-8-konstantin.ananyev@intel.com> X-Mailer: git-send-email 2.18.0 In-Reply-To: <20200403174235.23308-1-konstantin.ananyev@intel.com> References: <20200402220959.29885-1-konstantin.ananyev@intel.com> <20200403174235.23308-1-konstantin.ananyev@intel.com> Subject: [dpdk-dev] [PATCH v3 7/9] ring: introduce peek style API X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" For rings with producer/consumer in RTE_RING_SYNC_ST, RTE_RING_SYNC_MT_HTS mode, provide an ability to split enqueue/dequeue operation into two phases: - enqueue/dequeue start - enqueue/dequeue finish That allows user to inspect objects in the ring without removing them from it (aka MT safe peek). Signed-off-by: Konstantin Ananyev --- lib/librte_ring/Makefile | 1 + lib/librte_ring/meson.build | 1 + lib/librte_ring/rte_ring_c11_mem.h | 44 +++ lib/librte_ring/rte_ring_elem.h | 4 + lib/librte_ring/rte_ring_generic.h | 48 ++++ lib/librte_ring/rte_ring_hts_generic.h | 47 ++- lib/librte_ring/rte_ring_peek.h | 379 +++++++++++++++++++++++++ 7 files changed, 519 insertions(+), 5 deletions(-) create mode 100644 lib/librte_ring/rte_ring_peek.h diff --git a/lib/librte_ring/Makefile b/lib/librte_ring/Makefile index 6fe500f0d..5f8662737 100644 --- a/lib/librte_ring/Makefile +++ b/lib/librte_ring/Makefile @@ -22,6 +22,7 @@ SYMLINK-$(CONFIG_RTE_LIBRTE_RING)-include := rte_ring.h \ rte_ring_hts.h \ rte_ring_hts_elem.h \ rte_ring_hts_generic.h \ + rte_ring_peek.h \ rte_ring_rts.h \ rte_ring_rts_elem.h \ rte_ring_rts_generic.h diff --git a/lib/librte_ring/meson.build b/lib/librte_ring/meson.build index 8e86e037a..f5f84dc6e 100644 --- a/lib/librte_ring/meson.build +++ b/lib/librte_ring/meson.build @@ -9,6 +9,7 @@ headers = files('rte_ring.h', 'rte_ring_hts.h', 'rte_ring_hts_elem.h', 'rte_ring_hts_generic.h', + 'rte_ring_peek.h', 'rte_ring_rts.h', 'rte_ring_rts_elem.h', 'rte_ring_rts_generic.h') diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/rte_ring_c11_mem.h index 0fb73a337..bb3096721 100644 --- a/lib/librte_ring/rte_ring_c11_mem.h +++ b/lib/librte_ring/rte_ring_c11_mem.h @@ -10,6 +10,50 @@ #ifndef _RTE_RING_C11_MEM_H_ #define _RTE_RING_C11_MEM_H_ +/** + * @internal get current tail value. + * This function should be used only for single thread producer/consumer. + * Check that user didn't request to move tail above the head. + * In that situation: + * - return zero, that will cause abort any pending changes and + * return head to its previous position. + * - throw an assert in debug mode. + */ +static __rte_always_inline uint32_t +__rte_ring_st_get_tail(struct rte_ring_headtail *ht, uint32_t *tail, + uint32_t num) +{ + uint32_t h, n, t; + + h = ht->head; + t = ht->tail; + n = h - t; + + RTE_ASSERT(n >= num); + num = (n >= num) ? num : 0; + + *tail = h; + return num; +} + +/** + * @internal set new values for head and tail. + * This function should be used only for single thread producer/consumer. + * Should be used only in conjunction with __rte_ring_st_get_tail. + */ +static __rte_always_inline void +__rte_ring_st_set_head_tail(struct rte_ring_headtail *ht, uint32_t tail, + uint32_t num, uint32_t enqueue) +{ + uint32_t pos; + + RTE_SET_USED(enqueue); + + pos = tail + num; + ht->head = pos; + __atomic_store_n(&ht->tail, pos, __ATOMIC_RELEASE); +} + static __rte_always_inline void update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val, uint32_t single, uint32_t enqueue) diff --git a/lib/librte_ring/rte_ring_elem.h b/lib/librte_ring/rte_ring_elem.h index 010a564c1..5bf7c1c1b 100644 --- a/lib/librte_ring/rte_ring_elem.h +++ b/lib/librte_ring/rte_ring_elem.h @@ -1083,6 +1083,10 @@ rte_ring_dequeue_burst_elem(struct rte_ring *r, void *obj_table, return 0; } +#ifdef ALLOW_EXPERIMENTAL_API +#include +#endif + #ifdef __cplusplus } #endif diff --git a/lib/librte_ring/rte_ring_generic.h b/lib/librte_ring/rte_ring_generic.h index 953cdbbd5..9f5fdf13b 100644 --- a/lib/librte_ring/rte_ring_generic.h +++ b/lib/librte_ring/rte_ring_generic.h @@ -10,6 +10,54 @@ #ifndef _RTE_RING_GENERIC_H_ #define _RTE_RING_GENERIC_H_ +/** + * @internal get current tail value. + * This function should be used only for single thread producer/consumer. + * Check that user didn't request to move tail above the head. + * In that situation: + * - return zero, that will cause abort any pending changes and + * return head to its previous position. + * - throw an assert in debug mode. + */ +static __rte_always_inline uint32_t +__rte_ring_st_get_tail(struct rte_ring_headtail *ht, uint32_t *tail, + uint32_t num) +{ + uint32_t h, n, t; + + h = ht->head; + t = ht->tail; + n = h - t; + + RTE_ASSERT(n >= num); + num = (n >= num) ? num : 0; + + *tail = h; + return num; +} + +/** + * @internal set new values for head and tail. + * This function should be used only for single thread producer/consumer. + * Should be used only in conjunction with __rte_ring_st_get_tail. + */ +static __rte_always_inline void +__rte_ring_st_set_head_tail(struct rte_ring_headtail *ht, uint32_t tail, + uint32_t num, uint32_t enqueue) +{ + uint32_t pos; + + pos = tail + num; + + if (enqueue) + rte_smp_wmb(); + else + rte_smp_rmb(); + + ht->head = pos; + ht->tail = pos; +} + static __rte_always_inline void update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val, uint32_t single, uint32_t enqueue) diff --git a/lib/librte_ring/rte_ring_hts_generic.h b/lib/librte_ring/rte_ring_hts_generic.h index da08f1d94..8e699c006 100644 --- a/lib/librte_ring/rte_ring_hts_generic.h +++ b/lib/librte_ring/rte_ring_hts_generic.h @@ -18,9 +18,38 @@ * For more information please refer to . */ +/** + * @internal get current tail value. + * Check that user didn't request to move tail above the head. + * In that situation: + * - return zero, that will cause abort any pending changes and + * return head to its previous position. + * - throw an assert in debug mode. + */ +static __rte_always_inline uint32_t +__rte_ring_hts_get_tail(struct rte_ring_hts_headtail *ht, uint32_t *tail, + uint32_t num) +{ + uint32_t n; + union rte_ring_ht_pos p; + + p.raw = rte_atomic64_read((rte_atomic64_t *)(uintptr_t)&ht->ht.raw); + n = p.pos.head - p.pos.tail; + + RTE_ASSERT(n >= num); + num = (n >= num) ? num : 0; + + *tail = p.pos.tail; + return num; +} + +/** + * @internal set new values for head and tail as one atomic 64 bit operation. + * Should be used only in conjunction with __rte_ring_hts_get_tail. + */ static __rte_always_inline void -__rte_ring_hts_update_tail(struct rte_ring_hts_headtail *ht, uint32_t num, - uint32_t enqueue) +__rte_ring_hts_set_head_tail(struct rte_ring_hts_headtail *ht, uint32_t tail, + uint32_t num, uint32_t enqueue) { union rte_ring_ht_pos p; @@ -29,14 +58,22 @@ __rte_ring_hts_update_tail(struct rte_ring_hts_headtail *ht, uint32_t num, else rte_smp_rmb(); - p.raw = rte_atomic64_read((rte_atomic64_t *)(uintptr_t)&ht->ht.raw); - - p.pos.head = p.pos.tail + num; + p.pos.head = tail + num; p.pos.tail = p.pos.head; rte_atomic64_set((rte_atomic64_t *)(uintptr_t)&ht->ht.raw, p.raw); } +static __rte_always_inline void +__rte_ring_hts_update_tail(struct rte_ring_hts_headtail *ht, uint32_t num, + uint32_t enqueue) +{ + uint32_t tail; + + num = __rte_ring_hts_get_tail(ht, &tail, num); + __rte_ring_hts_set_head_tail(ht, tail, num, enqueue); +} + /** * @internal waits till tail will become equal to head. * Means no writer/reader is active for that ring. diff --git a/lib/librte_ring/rte_ring_peek.h b/lib/librte_ring/rte_ring_peek.h new file mode 100644 index 000000000..baefd2f7b --- /dev/null +++ b/lib/librte_ring/rte_ring_peek.h @@ -0,0 +1,379 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * + * Copyright (c) 2010-2017 Intel 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 _RTE_RING_PEEK_H_ +#define _RTE_RING_PEEK_H_ + +/** + * @file + * @b EXPERIMENTAL: this API may change without prior notice + * It is not recommended to include this file directly. + * Please include instead. + * + * Ring Peek AP + * Introduction of rte_ring with serialized producer/consumer (HTS sync mode) + * makes possible to split public enqueue/dequeue API into two phases: + * - enqueue/dequeue start + * - enqueue/dequeue finish + * That allows user to inspect objects in the ring without removing them + * from it (aka MT safe peek). + * Note that right now this new API is avaialble only for two sync modes: + * 1) Single Producer/Single Consumer (RTE_RING_SYNC_ST) + * 2) Serialized Producer/Serialized Consumer (RTE_RING_SYNC_MT_HTS). + * It is a user responsibility to create/init ring with appropriate sync + * modes selected. + * As an example: + * // read 1 elem from the ring: + * n = rte_ring_hts_dequeue_bulk_start(ring, &obj, 1, NULL); + * if (n != 0) { + * //examine object + * if (object_examine(obj) == KEEP) + * //decided to keep it in the ring. + * rte_ring_hts_dequeue_finish(ring, 0); + * else + * //decided to remove it from the ring. + * rte_ring_hts_dequeue_finish(ring, n); + * } + * Note that between _start_ and _finish_ the ring is sort of locked - + * none other thread can proceed with enqueue(/dequeue) operation till + * _finish_ will complete. + */ + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * @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; + default: + /* unsupported mode, shouldn't be here */ + RTE_ASSERT(0); + n = 0; + } + + if (free_space != NULL) + *free_space = free - n; + return n; +} + +/** + * Start to enqueue several objects on the ring. + * Note that no actual objects are put in the queue by this function, + * it just reserves for user such ability. + * User has to call appropriate enqueue_finish() to copy objects into the + * queue and complete given enqueue operation. + * + * @param r + * A pointer to the ring structure. + * @param n + * The number of objects to add in the ring from the obj_table. + * @param free_space + * if non-NULL, returns the amount of space in the ring after the + * enqueue operation has finished. + * @return + * The number of objects that can be enqueued, either 0 or n + */ +__rte_experimental +static __rte_always_inline unsigned int +rte_ring_enqueue_bulk_start(struct rte_ring *r, unsigned int n, + unsigned int *free_space) +{ + return __rte_ring_do_enqueue_start(r, n, RTE_RING_QUEUE_FIXED, + free_space); +} + +/** + * Start to enqueue several objects on the ring. + * Note that no actual objects are put in the queue by this function, + * it just reserves for user such ability. + * User has to call appropriate enqueue_finish() to copy objects into the + * queue and complete given enqueue operation. + * + * @param r + * A pointer to the ring structure. + * @param n + * The number of objects to add in the ring from the obj_table. + * @param free_space + * if non-NULL, returns the amount of space in the ring after the + * enqueue operation has finished. + * @return + * Actual number of objects that can be enqueued. + */ +__rte_experimental +static __rte_always_inline unsigned int +rte_ring_enqueue_burst_start(struct rte_ring *r, unsigned int n, + unsigned int *free_space) +{ + return __rte_ring_do_enqueue_start(r, n, RTE_RING_QUEUE_VARIABLE, + free_space); +} + +/** + * Complete to enqueue several objects on the ring. + * Note that number of objects to enqueue should not exceed previous + * enqueue_start return value. + * + * @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 to the ring from the obj_table. + */ +__rte_experimental +static __rte_always_inline void +rte_ring_enqueue_elem_finish(struct rte_ring *r, void * const *obj_table, + unsigned int esize, unsigned int n) +{ + uint32_t tail; + + switch (r->prod.sync_type) { + case RTE_RING_SYNC_ST: + n = __rte_ring_st_get_tail(&r->prod, &tail, n); + if (n != 0) + __rte_ring_enqueue_elems(r, tail, obj_table, esize, n); + __rte_ring_st_set_head_tail(&r->prod, tail, n, 1); + break; + case RTE_RING_SYNC_MT_HTS: + n = __rte_ring_hts_get_tail(&r->hts_prod, &tail, n); + if (n != 0) + __rte_ring_enqueue_elems(r, tail, obj_table, esize, n); + __rte_ring_hts_set_head_tail(&r->hts_prod, tail, n, 1); + break; + default: + /* unsupported mode, shouldn't be here */ + RTE_ASSERT(0); + } +} + +/** + * Complete to enqueue several objects on the ring. + * Note that number of objects to enqueue should not exceed previous + * enqueue_start return value. + * + * @param r + * A pointer to the ring structure. + * @param obj_table + * A pointer to a table of objects. + * @param n + * The number of objects to add to the ring from the obj_table. + */ +__rte_experimental +static __rte_always_inline void +rte_ring_enqueue_finish(struct rte_ring *r, void * const *obj_table, + unsigned int n) +{ + 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; + default: + /* unsupported mode, shouldn't be here */ + RTE_ASSERT(0); + n = 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() + * to complete given dequeue operation and actually remove objects 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. + * @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 dequeue from the ring to the obj_table. + * @param available + * If non-NULL, returns the number of remaining ring entries after the + * dequeue has finished. + * @return + * The number of objects dequeued, either 0 or n. + */ +__rte_experimental +static __rte_always_inline unsigned int +rte_ring_dequeue_bulk_elem_start(struct rte_ring *r, void **obj_table, + unsigned int esize, unsigned int n, unsigned int *available) +{ + return __rte_ring_do_dequeue_start(r, obj_table, esize, n, + RTE_RING_QUEUE_FIXED, available); +} + +/** + * Start to dequeue several objects from the ring. + * Note that user has to call appropriate dequeue_finish() + * to complete given dequeue operation and actually remove objects 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. + * @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 dequeue from the ring to the obj_table. + * @param available + * If non-NULL, returns the number of remaining ring entries after the + * dequeue has finished. + * @return + * Actual number of objects dequeued. + */ +__rte_experimental +static __rte_always_inline unsigned int +rte_ring_dequeue_bulk_start(struct rte_ring *r, void **obj_table, + unsigned int n, unsigned int *available) +{ + return rte_ring_dequeue_bulk_elem_start(r, obj_table, sizeof(uintptr_t), + n, available); +} + +/** + * Start to dequeue several objects from the ring. + * Note that user has to call appropriate dequeue_finish() + * to complete given dequeue operation and actually remove objects 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. + * @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 dequeue from the ring to the obj_table. + * @param available + * If non-NULL, returns the number of remaining ring entries after the + * dequeue has finished. + * @return + * The actual number of objects dequeued. + */ +__rte_experimental +static __rte_always_inline unsigned int +rte_ring_dequeue_burst_elem_start(struct rte_ring *r, void **obj_table, + unsigned int esize, unsigned int n, unsigned int *available) +{ + return __rte_ring_do_dequeue_start(r, obj_table, esize, n, + RTE_RING_QUEUE_VARIABLE, available); +} + +/** + * Start to dequeue several objects from the ring. + * Note that user has to call appropriate dequeue_finish() + * to complete given dequeue operation and actually remove objects 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. + * @param n + * The number of objects to dequeue from the ring to the obj_table. + * @param available + * If non-NULL, returns the number of remaining ring entries after the + * dequeue has finished. + * @return + * The actual number of objects dequeued. + */ +__rte_experimental +static __rte_always_inline unsigned int +rte_ring_dequeue_burst_start(struct rte_ring *r, void **obj_table, + unsigned int n, unsigned int *available) +{ + return rte_ring_dequeue_burst_elem_start(r, obj_table, + sizeof(uintptr_t), n, available); +} + +/** + * Complete to dequeue several objects from the ring. + * Note that number of objects to dequeue should not exceed previous + * dequeue_start return value. + * + * @param r + * A pointer to the ring structure. + * @param n + * The number of objects to add to the ring from the obj_table. + */ +__rte_experimental +static __rte_always_inline void +rte_ring_dequeue_finish(struct rte_ring *r, unsigned int n) +{ + uint32_t tail; + + switch (r->cons.sync_type) { + case RTE_RING_SYNC_ST: + n = __rte_ring_st_get_tail(&r->cons, &tail, n); + __rte_ring_st_set_head_tail(&r->cons, tail, n, 0); + break; + case RTE_RING_SYNC_MT_HTS: + __rte_ring_hts_update_tail(&r->hts_cons, n, 0); + break; + default: + /* unsupported mode, shouldn't be here */ + RTE_ASSERT(0); + } +} + +#ifdef __cplusplus +} +#endif + +#endif /* _RTE_RING_PEEK_H_ */ -- 2.17.1