X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=app%2Ftest-bbdev%2Ftest_bbdev_perf.c;h=fad3b1e49d0a872091604d52fb63c0cf1a9376a1;hb=3dea1b2693ab8b46f5add0642b08714884634bae;hp=469597b8b333f0e67a2999e175f7e8f3254c7220;hpb=49ca9e5a256b7db55af71923ce827c1fa480b473;p=dpdk.git diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c index 469597b8b3..fad3b1e49d 100644 --- a/app/test-bbdev/test_bbdev_perf.c +++ b/app/test-bbdev/test_bbdev_perf.c @@ -50,7 +50,6 @@ #define DL_5G_BANDWIDTH 3 #define UL_5G_LOAD_BALANCE 128 #define DL_5G_LOAD_BALANCE 128 -#define FLR_5G_TIMEOUT 610 #endif #ifdef RTE_BASEBAND_ACC100 @@ -133,7 +132,7 @@ struct test_op_params { uint16_t num_to_process; uint16_t num_lcores; int vector_mask; - rte_atomic16_t sync; + uint16_t sync; struct test_buffers q_bufs[RTE_MAX_NUMA_NODES][MAX_QUEUES]; }; @@ -148,9 +147,9 @@ struct thread_params { uint8_t iter_count; double iter_average; double bler; - rte_atomic16_t nb_dequeued; - rte_atomic16_t processing_status; - rte_atomic16_t burst_sz; + uint16_t nb_dequeued; + int16_t processing_status; + uint16_t burst_sz; struct test_op_params *op_params; struct rte_bbdev_dec_op *dec_ops[MAX_BURST]; struct rte_bbdev_enc_op *enc_ops[MAX_BURST]; @@ -227,6 +226,45 @@ clear_soft_out_cap(uint32_t *op_flags) *op_flags &= ~RTE_BBDEV_TURBO_NEG_LLR_1_BIT_SOFT_OUT; } +/* This API is to convert all the test vector op data entries + * to big endian format. It is used when the device supports + * the input in the big endian format. + */ +static inline void +convert_op_data_to_be(void) +{ + struct op_data_entries *op; + enum op_data_type type; + uint8_t nb_segs, *rem_data, temp; + uint32_t *data, len; + int complete, rem, i, j; + + for (type = DATA_INPUT; type < DATA_NUM_TYPES; ++type) { + nb_segs = test_vector.entries[type].nb_segments; + op = &test_vector.entries[type]; + + /* Invert byte endianness for all the segments */ + for (i = 0; i < nb_segs; ++i) { + len = op->segments[i].length; + data = op->segments[i].addr; + + /* Swap complete u32 bytes */ + complete = len / 4; + for (j = 0; j < complete; j++) + data[j] = rte_bswap32(data[j]); + + /* Swap any remaining bytes */ + rem = len % 4; + rem_data = (uint8_t *)&data[j]; + for (j = 0; j < rem/2; j++) { + temp = rem_data[j]; + rem_data[j] = rem_data[rem - j - 1]; + rem_data[rem - j - 1] = temp; + } + } + } +} + static int check_dev_cap(const struct rte_bbdev_info *dev_info) { @@ -234,6 +272,7 @@ check_dev_cap(const struct rte_bbdev_info *dev_info) unsigned int nb_inputs, nb_soft_outputs, nb_hard_outputs, nb_harq_inputs, nb_harq_outputs; const struct rte_bbdev_op_cap *op_cap = dev_info->drv.capabilities; + uint8_t dev_data_endianness = dev_info->drv.data_endianness; nb_inputs = test_vector.entries[DATA_INPUT].nb_segments; nb_soft_outputs = test_vector.entries[DATA_SOFT_OUTPUT].nb_segments; @@ -245,6 +284,9 @@ check_dev_cap(const struct rte_bbdev_info *dev_info) if (op_cap->type != test_vector.op_type) continue; + if (dev_data_endianness == RTE_BIG_ENDIAN) + convert_op_data_to_be(); + if (op_cap->type == RTE_BBDEV_OP_TURBO_DEC) { const struct rte_bbdev_op_cap_turbo_dec *cap = &op_cap->cap.turbo_dec; @@ -656,9 +698,6 @@ add_bbdev_dev(uint8_t dev_id, struct rte_bbdev_info *info, conf.ul_load_balance = UL_5G_LOAD_BALANCE; conf.dl_load_balance = DL_5G_LOAD_BALANCE; - /**< FLR timeout value */ - conf.flr_time_out = FLR_5G_TIMEOUT; - /* setup FPGA PF with configuration information */ ret = rte_fpga_5gnr_fec_configure(info->dev_name, &conf); TEST_ASSERT_SUCCESS(ret, @@ -2594,46 +2633,46 @@ dequeue_event_callback(uint16_t dev_id, } if (unlikely(event != RTE_BBDEV_EVENT_DEQUEUE)) { - rte_atomic16_set(&tp->processing_status, TEST_FAILED); + __atomic_store_n(&tp->processing_status, TEST_FAILED, __ATOMIC_RELAXED); printf( "Dequeue interrupt handler called for incorrect event!\n"); return; } - burst_sz = rte_atomic16_read(&tp->burst_sz); + burst_sz = __atomic_load_n(&tp->burst_sz, __ATOMIC_RELAXED); num_ops = tp->op_params->num_to_process; if (test_vector.op_type == RTE_BBDEV_OP_TURBO_DEC) deq = rte_bbdev_dequeue_dec_ops(dev_id, queue_id, &tp->dec_ops[ - rte_atomic16_read(&tp->nb_dequeued)], + __atomic_load_n(&tp->nb_dequeued, __ATOMIC_RELAXED)], burst_sz); else if (test_vector.op_type == RTE_BBDEV_OP_LDPC_DEC) deq = rte_bbdev_dequeue_ldpc_dec_ops(dev_id, queue_id, &tp->dec_ops[ - rte_atomic16_read(&tp->nb_dequeued)], + __atomic_load_n(&tp->nb_dequeued, __ATOMIC_RELAXED)], burst_sz); else if (test_vector.op_type == RTE_BBDEV_OP_LDPC_ENC) deq = rte_bbdev_dequeue_ldpc_enc_ops(dev_id, queue_id, &tp->enc_ops[ - rte_atomic16_read(&tp->nb_dequeued)], + __atomic_load_n(&tp->nb_dequeued, __ATOMIC_RELAXED)], burst_sz); else /*RTE_BBDEV_OP_TURBO_ENC*/ deq = rte_bbdev_dequeue_enc_ops(dev_id, queue_id, &tp->enc_ops[ - rte_atomic16_read(&tp->nb_dequeued)], + __atomic_load_n(&tp->nb_dequeued, __ATOMIC_RELAXED)], burst_sz); if (deq < burst_sz) { printf( "After receiving the interrupt all operations should be dequeued. Expected: %u, got: %u\n", burst_sz, deq); - rte_atomic16_set(&tp->processing_status, TEST_FAILED); + __atomic_store_n(&tp->processing_status, TEST_FAILED, __ATOMIC_RELAXED); return; } - if (rte_atomic16_read(&tp->nb_dequeued) + deq < num_ops) { - rte_atomic16_add(&tp->nb_dequeued, deq); + if (__atomic_load_n(&tp->nb_dequeued, __ATOMIC_RELAXED) + deq < num_ops) { + __atomic_fetch_add(&tp->nb_dequeued, deq, __ATOMIC_RELAXED); return; } @@ -2670,7 +2709,7 @@ dequeue_event_callback(uint16_t dev_id, if (ret) { printf("Buffers validation failed\n"); - rte_atomic16_set(&tp->processing_status, TEST_FAILED); + __atomic_store_n(&tp->processing_status, TEST_FAILED, __ATOMIC_RELAXED); } switch (test_vector.op_type) { @@ -2691,7 +2730,7 @@ dequeue_event_callback(uint16_t dev_id, break; default: printf("Unknown op type: %d\n", test_vector.op_type); - rte_atomic16_set(&tp->processing_status, TEST_FAILED); + __atomic_store_n(&tp->processing_status, TEST_FAILED, __ATOMIC_RELAXED); return; } @@ -2700,7 +2739,7 @@ dequeue_event_callback(uint16_t dev_id, tp->mbps += (((double)(num_ops * tb_len_bits)) / 1000000.0) / ((double)total_time / (double)rte_get_tsc_hz()); - rte_atomic16_add(&tp->nb_dequeued, deq); + __atomic_fetch_add(&tp->nb_dequeued, deq, __ATOMIC_RELAXED); } static int @@ -2738,11 +2777,10 @@ throughput_intr_lcore_ldpc_dec(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - rte_atomic16_clear(&tp->processing_status); - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->processing_status, 0, __ATOMIC_RELAXED); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_dec_op_alloc_bulk(tp->op_params->mp, ops, num_to_process); @@ -2790,17 +2828,15 @@ throughput_intr_lcore_ldpc_dec(void *arg) * the number of operations is not a multiple of * burst size. */ - rte_atomic16_set(&tp->burst_sz, num_to_enq); + __atomic_store_n(&tp->burst_sz, num_to_enq, __ATOMIC_RELAXED); /* Wait until processing of previous batch is * completed */ - while (rte_atomic16_read(&tp->nb_dequeued) != - (int16_t) enqueued) - rte_pause(); + rte_wait_until_equal_16(&tp->nb_dequeued, enqueued, __ATOMIC_RELAXED); } if (j != TEST_REPETITIONS - 1) - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); } return TEST_SUCCESS; @@ -2835,11 +2871,10 @@ throughput_intr_lcore_dec(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - rte_atomic16_clear(&tp->processing_status); - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->processing_status, 0, __ATOMIC_RELAXED); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_dec_op_alloc_bulk(tp->op_params->mp, ops, num_to_process); @@ -2880,17 +2915,15 @@ throughput_intr_lcore_dec(void *arg) * the number of operations is not a multiple of * burst size. */ - rte_atomic16_set(&tp->burst_sz, num_to_enq); + __atomic_store_n(&tp->burst_sz, num_to_enq, __ATOMIC_RELAXED); /* Wait until processing of previous batch is * completed */ - while (rte_atomic16_read(&tp->nb_dequeued) != - (int16_t) enqueued) - rte_pause(); + rte_wait_until_equal_16(&tp->nb_dequeued, enqueued, __ATOMIC_RELAXED); } if (j != TEST_REPETITIONS - 1) - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); } return TEST_SUCCESS; @@ -2925,11 +2958,10 @@ throughput_intr_lcore_enc(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - rte_atomic16_clear(&tp->processing_status); - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->processing_status, 0, __ATOMIC_RELAXED); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_enc_op_alloc_bulk(tp->op_params->mp, ops, num_to_process); @@ -2969,17 +3001,15 @@ throughput_intr_lcore_enc(void *arg) * the number of operations is not a multiple of * burst size. */ - rte_atomic16_set(&tp->burst_sz, num_to_enq); + __atomic_store_n(&tp->burst_sz, num_to_enq, __ATOMIC_RELAXED); /* Wait until processing of previous batch is * completed */ - while (rte_atomic16_read(&tp->nb_dequeued) != - (int16_t) enqueued) - rte_pause(); + rte_wait_until_equal_16(&tp->nb_dequeued, enqueued, __ATOMIC_RELAXED); } if (j != TEST_REPETITIONS - 1) - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); } return TEST_SUCCESS; @@ -3015,11 +3045,10 @@ throughput_intr_lcore_ldpc_enc(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - rte_atomic16_clear(&tp->processing_status); - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->processing_status, 0, __ATOMIC_RELAXED); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_enc_op_alloc_bulk(tp->op_params->mp, ops, num_to_process); @@ -3061,17 +3090,15 @@ throughput_intr_lcore_ldpc_enc(void *arg) * the number of operations is not a multiple of * burst size. */ - rte_atomic16_set(&tp->burst_sz, num_to_enq); + __atomic_store_n(&tp->burst_sz, num_to_enq, __ATOMIC_RELAXED); /* Wait until processing of previous batch is * completed */ - while (rte_atomic16_read(&tp->nb_dequeued) != - (int16_t) enqueued) - rte_pause(); + rte_wait_until_equal_16(&tp->nb_dequeued, enqueued, __ATOMIC_RELAXED); } if (j != TEST_REPETITIONS - 1) - rte_atomic16_clear(&tp->nb_dequeued); + __atomic_store_n(&tp->nb_dequeued, 0, __ATOMIC_RELAXED); } return TEST_SUCCESS; @@ -3105,8 +3132,7 @@ throughput_pmd_lcore_dec(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_dec_op_alloc_bulk(tp->op_params->mp, ops_enq, num_ops); TEST_ASSERT_SUCCESS(ret, "Allocation failed for %d ops", num_ops); @@ -3209,8 +3235,7 @@ bler_pmd_lcore_ldpc_dec(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_dec_op_alloc_bulk(tp->op_params->mp, ops_enq, num_ops); TEST_ASSERT_SUCCESS(ret, "Allocation failed for %d ops", num_ops); @@ -3339,8 +3364,7 @@ throughput_pmd_lcore_ldpc_dec(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_dec_op_alloc_bulk(tp->op_params->mp, ops_enq, num_ops); TEST_ASSERT_SUCCESS(ret, "Allocation failed for %d ops", num_ops); @@ -3456,8 +3480,7 @@ throughput_pmd_lcore_enc(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_enc_op_alloc_bulk(tp->op_params->mp, ops_enq, num_ops); @@ -3547,8 +3570,7 @@ throughput_pmd_lcore_ldpc_enc(void *arg) bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; - while (rte_atomic16_read(&tp->op_params->sync) == SYNC_WAIT) - rte_pause(); + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = rte_bbdev_enc_op_alloc_bulk(tp->op_params->mp, ops_enq, num_ops); @@ -3731,7 +3753,7 @@ bler_test(struct active_device *ad, else return TEST_SKIPPED; - rte_atomic16_set(&op_params->sync, SYNC_WAIT); + __atomic_store_n(&op_params->sync, SYNC_WAIT, __ATOMIC_RELAXED); /* Main core is set at first entry */ t_params[0].dev_id = ad->dev_id; @@ -3754,7 +3776,7 @@ bler_test(struct active_device *ad, &t_params[used_cores++], lcore_id); } - rte_atomic16_set(&op_params->sync, SYNC_START); + __atomic_store_n(&op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = bler_function(&t_params[0]); /* Main core is always used */ @@ -3849,7 +3871,7 @@ throughput_test(struct active_device *ad, throughput_function = throughput_pmd_lcore_enc; } - rte_atomic16_set(&op_params->sync, SYNC_WAIT); + __atomic_store_n(&op_params->sync, SYNC_WAIT, __ATOMIC_RELAXED); /* Main core is set at first entry */ t_params[0].dev_id = ad->dev_id; @@ -3872,7 +3894,7 @@ throughput_test(struct active_device *ad, &t_params[used_cores++], lcore_id); } - rte_atomic16_set(&op_params->sync, SYNC_START); + __atomic_store_n(&op_params->sync, SYNC_START, __ATOMIC_RELAXED); ret = throughput_function(&t_params[0]); /* Main core is always used */ @@ -3902,29 +3924,29 @@ throughput_test(struct active_device *ad, * Wait for main lcore operations. */ tp = &t_params[0]; - while ((rte_atomic16_read(&tp->nb_dequeued) < - op_params->num_to_process) && - (rte_atomic16_read(&tp->processing_status) != - TEST_FAILED)) + while ((__atomic_load_n(&tp->nb_dequeued, __ATOMIC_RELAXED) < + op_params->num_to_process) && + (__atomic_load_n(&tp->processing_status, __ATOMIC_RELAXED) != + TEST_FAILED)) rte_pause(); tp->ops_per_sec /= TEST_REPETITIONS; tp->mbps /= TEST_REPETITIONS; - ret |= (int)rte_atomic16_read(&tp->processing_status); + ret |= (int)__atomic_load_n(&tp->processing_status, __ATOMIC_RELAXED); /* Wait for worker lcores operations */ for (used_cores = 1; used_cores < num_lcores; used_cores++) { tp = &t_params[used_cores]; - while ((rte_atomic16_read(&tp->nb_dequeued) < - op_params->num_to_process) && - (rte_atomic16_read(&tp->processing_status) != - TEST_FAILED)) + while ((__atomic_load_n(&tp->nb_dequeued, __ATOMIC_RELAXED) < + op_params->num_to_process) && + (__atomic_load_n(&tp->processing_status, __ATOMIC_RELAXED) != + TEST_FAILED)) rte_pause(); tp->ops_per_sec /= TEST_REPETITIONS; tp->mbps /= TEST_REPETITIONS; - ret |= (int)rte_atomic16_read(&tp->processing_status); + ret |= (int)__atomic_load_n(&tp->processing_status, __ATOMIC_RELAXED); } /* Print throughput if test passed */