X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_ring%2Frte_ring.h;h=97f025a1fb61968f5805483cf71c2d44e92053b0;hb=c3b047be7328c70e0542d40db15f847181208a22;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..97f025a1fb 100644 --- a/lib/librte_ring/rte_ring.h +++ b/lib/librte_ring/rte_ring.h @@ -147,7 +147,7 @@ struct rte_ring { * compatibility requirements, it could be changed to RTE_RING_NAMESIZE * next time the ABI changes */ - char name[RTE_MEMZONE_NAMESIZE]; /**< Name of the ring. */ + char name[RTE_MEMZONE_NAMESIZE] __rte_cache_aligned; /**< Name of the ring. */ int flags; /**< Flags supplied at creation. */ const struct rte_memzone *memzone; /**< Memzone, if any, containing the rte_ring */ @@ -159,16 +159,18 @@ struct rte_ring { /** 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 */ +/* @internal defines for passing to the enqueue dequeue worker functions */ +#define __IS_SP 1 +#define __IS_MP 0 +#define __IS_SC 1 +#define __IS_MC 0 + /** * Calculate the memory size needed for a ring * @@ -284,134 +286,147 @@ 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) +static inline __attribute__((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 Enqueue several objects on the ring (multi-producers safe). - * - * This function uses a "compare and set" instruction to move the - * producer index atomically. + * @internal This function updates the producer head for enqueue * * @param r - * A pointer to the ring structure. - * @param obj_table - * A pointer to a table of void * pointers (objects). + * A pointer to the ring structure + * @param is_sp + * Indicates whether multi-producer path is needed or not * @param n - * The number of objects to add in the ring from the obj_table. + * 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 a possible from 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 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) +static inline __attribute__((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) { - uint32_t prod_head, prod_next; - uint32_t cons_tail, free_entries; - const unsigned int max = n; + const uint32_t mask = r->mask; + 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; + *old_head = r->prod.head; + 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 - * prod_head > cons_tail). So 'free_entries' is always between 0 + * *old_head > cons_tail). So 'free_entries' is always between 0 * and size(ring)-1. */ - free_entries = (mask + cons_tail - prod_head); + *free_entries = (mask + cons_tail - *old_head); /* check that we have enough room in ring */ - if (unlikely(n > free_entries)) + if (unlikely(n > *free_entries)) n = (behavior == RTE_RING_QUEUE_FIXED) ? - 0 : free_entries; + 0 : *free_entries; if (n == 0) - goto end; - - prod_next = prod_head + n; - success = rte_atomic32_cmpset(&r->prod.head, prod_head, - prod_next); + 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)); - - /* 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; } /** - * @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 +434,32 @@ 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 inline __attribute__((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, + 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; - - prod_next = prod_head + n; - r->prod.head = prod_next; - - /* write entries in ring */ - ENQUEUE_PTRS(); + ENQUEUE_PTRS(r, &r[1], prod_head, obj_table, n, void *); rte_smp_wmb(); - r->prod.tail = prod_next; + update_tail(&r->prod, prod_head, prod_next, is_sp); end: if (free_space != NULL) *free_space = free_entries - n; @@ -465,132 +467,105 @@ 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. + * @internal This function updates the consumer head for dequeue * * @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 the ring structure + * @param is_sc + * Indicates whether multi-consumer path is needed or not * @param n - * The number of objects to dequeue from the ring to the obj_table. + * 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 a possible from 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 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) +static inline __attribute__((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) { - uint32_t cons_head, prod_tail; - uint32_t cons_next, entries; - const unsigned max = n; + unsigned int 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; + *old_head = r->cons.head; + 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 - cons_head); + *entries = (prod_tail - *old_head); /* Set the actual entries for dequeue */ - if (n > entries) - n = (behavior == RTE_RING_QUEUE_FIXED) ? 0 : entries; + 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); + 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)); - - /* 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 inline __attribute__((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) + 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; - - if (unlikely(entries == 0)) - goto end; + uint32_t cons_head, cons_next; + uint32_t entries; - cons_next = cons_head + n; - r->cons.head = cons_next; + n = __rte_ring_move_cons_head(r, is_sc, n, behavior, + &cons_head, &cons_next, &entries); + if (n == 0) + goto end; - /* copy in table */ - DEQUEUE_PTRS(); + DEQUEUE_PTRS(r, &r[1], cons_head, obj_table, n, void *); rte_smp_rmb(); - r->cons.tail = cons_next; + update_tail(&r->cons, cons_head, cons_next, is_sc); + end: if (available != NULL) *available = entries - n; @@ -619,8 +594,8 @@ static inline unsigned int __attribute__((always_inline)) 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, + __IS_MP, free_space); } /** @@ -642,8 +617,8 @@ static inline unsigned int __attribute__((always_inline)) 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, + __IS_SP, free_space); } /** @@ -669,10 +644,8 @@ static inline unsigned int __attribute__((always_inline)) 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 - return rte_ring_mp_enqueue_bulk(r, obj_table, n, free_space); + return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_FIXED, + r->prod.single, free_space); } /** @@ -755,8 +728,8 @@ static inline unsigned int __attribute__((always_inline)) 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, + __IS_MC, available); } /** @@ -779,8 +752,8 @@ static inline unsigned int __attribute__((always_inline)) 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, + __IS_SC, available); } /** @@ -806,10 +779,8 @@ static inline unsigned int __attribute__((always_inline)) 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 - return rte_ring_mc_dequeue_bulk(r, obj_table, n, available); + return __rte_ring_do_dequeue(r, obj_table, n, RTE_RING_QUEUE_FIXED, + r->cons.single, available); } /** @@ -870,7 +841,7 @@ rte_ring_sc_dequeue(struct rte_ring *r, void **obj_p) static inline int __attribute__((always_inline)) 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; } /** @@ -995,8 +966,8 @@ static inline unsigned __attribute__((always_inline)) 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, __IS_MP, free_space); } /** @@ -1018,8 +989,8 @@ static inline unsigned __attribute__((always_inline)) 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, __IS_SP, free_space); } /** @@ -1045,10 +1016,8 @@ static inline unsigned __attribute__((always_inline)) 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 - return rte_ring_mp_enqueue_burst(r, obj_table, n, free_space); + return __rte_ring_do_enqueue(r, obj_table, n, RTE_RING_QUEUE_VARIABLE, + r->prod.single, free_space); } /** @@ -1075,8 +1044,8 @@ static inline unsigned __attribute__((always_inline)) 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, __IS_MC, available); } /** @@ -1100,8 +1069,8 @@ static inline unsigned __attribute__((always_inline)) 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, __IS_SC, available); } /** @@ -1127,10 +1096,9 @@ static inline unsigned __attribute__((always_inline)) 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 - return rte_ring_mc_dequeue_burst(r, obj_table, n, available); + return __rte_ring_do_dequeue(r, obj_table, n, + RTE_RING_QUEUE_VARIABLE, + r->cons.single, available); } #ifdef __cplusplus