[dpdk-dev] [PATCH v2 7/9] ring: introduce peek style API

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

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 <konstantin.ananyev@intel.com>
---
 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 <rte_ring_peek.h>
+#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 0b3931ffa..7eac761f9 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 <rte_ring_hts.h>.
  */
 
+/**
+ * @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 <rte_ring_elem.h> 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