} \
} while (0)
-static __rte_always_inline void
-update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val,
- uint32_t single)
-{
- /*
- * If there are other enqueues/dequeues in progress that preceded us,
- * we need to wait for them to complete
- */
- if (!single)
- while (unlikely(ht->tail != old_val))
- rte_pause();
-
- ht->tail = new_val;
-}
-
-/**
- * @internal This function updates the producer head for enqueue
- *
- * @param r
- * A pointer to the ring structure
- * @param is_sp
- * Indicates whether multi-producer path is needed or not
- * @param n
- * The number of elements we will want to enqueue, i.e. how far should the
- * head be moved
- * @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 old_head
- * Returns head value as it was before the move, i.e. where enqueue starts
- * @param new_head
- * Returns the current/new head value i.e. where enqueue finishes
- * @param free_entries
- * Returns the amount of free space in the ring BEFORE head was moved
- * @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_move_prod_head(struct rte_ring *r, int is_sp,
- unsigned int n, enum rte_ring_queue_behavior behavior,
- uint32_t *old_head, uint32_t *new_head,
- uint32_t *free_entries)
-{
- const uint32_t capacity = r->capacity;
- unsigned int max = n;
- int success;
-
- do {
- /* Reset n to the initial burst count */
- n = max;
-
- *old_head = r->prod.head;
-
- /* add rmb barrier to avoid load/load reorder in weak
- * memory model. It is noop on x86
- */
- rte_smp_rmb();
-
- const uint32_t 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
- * *old_head > cons_tail). So 'free_entries' is always between 0
- * and capacity (which is < size).
- */
- *free_entries = (capacity + cons_tail - *old_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)
- return 0;
-
- *new_head = *old_head + n;
- if (is_sp)
- r->prod.head = *new_head, success = 1;
- else
- success = rte_atomic32_cmpset(&r->prod.head,
- *old_head, *new_head);
- } while (unlikely(success == 0));
- return n;
-}
+/* 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-direcion load_acquire/store_release barrier,defined by
+ * CONFIG_RTE_RING_USE_C11_MEM_MODEL=y
+ * It depends on performance test results.
+ * By default, move common functions to rte_ring_generic.h
+ */
+#ifdef RTE_RING_USE_C11_MEM_MODEL
+#include "rte_ring_c11_mem.h"
+#else
+#include "rte_ring_generic.h"
+#endif
/**
* @internal Enqueue several objects on the ring
goto end;
ENQUEUE_PTRS(r, &r[1], prod_head, obj_table, n, void *);
- rte_smp_wmb();
- update_tail(&r->prod, prod_head, prod_next, is_sp);
+ update_tail(&r->prod, prod_head, prod_next, is_sp, 1);
end:
if (free_space != NULL)
*free_space = free_entries - n;
return n;
}
-/**
- * @internal This function updates the consumer head for dequeue
- *
- * @param r
- * A pointer to the ring structure
- * @param is_sc
- * Indicates whether multi-consumer path is needed or not
- * @param n
- * The number of elements we will want to enqueue, i.e. how far should the
- * head be moved
- * @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 old_head
- * Returns head value as it was before the move, i.e. where dequeue starts
- * @param new_head
- * Returns the current/new head value i.e. where dequeue finishes
- * @param entries
- * Returns the number of entries in the ring BEFORE head was moved
- * @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_move_cons_head(struct rte_ring *r, int is_sc,
- unsigned int n, enum rte_ring_queue_behavior behavior,
- uint32_t *old_head, uint32_t *new_head,
- uint32_t *entries)
-{
- unsigned int max = n;
- int success;
-
- /* move cons.head atomically */
- do {
- /* Restore n as it may change every loop */
- n = max;
-
- *old_head = r->cons.head;
-
- /* add rmb barrier to avoid load/load reorder in weak
- * memory model. It is noop on x86
- */
- rte_smp_rmb();
-
- const uint32_t 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 - *old_head);
-
- /* Set the actual entries for dequeue */
- if (n > *entries)
- n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : *entries;
-
- if (unlikely(n == 0))
- return 0;
-
- *new_head = *old_head + n;
- if (is_sc)
- r->cons.head = *new_head, success = 1;
- else
- success = rte_atomic32_cmpset(&r->cons.head, *old_head,
- *new_head);
- } while (unlikely(success == 0));
- return n;
-}
-
/**
* @internal Dequeue several objects from the ring
*
goto end;
DEQUEUE_PTRS(r, &r[1], cons_head, obj_table, n, void *);
- rte_smp_rmb();
- update_tail(&r->cons, cons_head, cons_next, is_sc);
+ update_tail(&r->cons, cons_head, cons_next, is_sc, 0);
end:
if (available != NULL)
git.droids-corp.org / dpdk.git / blobdiff