From c11f6540424750af68ab5cdb68e7e8c9892fed07 Mon Sep 17 00:00:00 2001 From: Xiaoyun Li Date: Tue, 18 Sep 2018 10:22:40 +0800 Subject: [PATCH] net/i40e: add option to use latest vector path For IA, the AVX2 vector path is only recommended to be used on later platforms (identified by AVX512 support, like SKL etc.) This is because performance benchmark shows downgrade when running AVX2 vector path on early platform (BDW/HSW) in some cases. But we still observe perf gain with some real work loading. So this patch introduced the new devarg use-latest-supported-vec to force the driver always selecting the latest supported vec path. Then apps are able to take AVX2 path on early platforms. And this logic can be re-used if we will have AVX512 vec path in future. This patch only affects IA platforms. The selected vec path would be like the following: Without devarg/devarg = 0: Machine vPMD AVX512F AVX2 AVX2 SSE4.2 SSE4.2 SSE4.2 Reviewed-by: Ferruh Yigit Acked-by: Qi Zhang --- doc/guides/nics/i40e.rst | 9 ++ doc/guides/rel_notes/release_18_11.rst | 5 + drivers/net/i40e/i40e_ethdev.c | 65 ++++++++++- drivers/net/i40e/i40e_ethdev.h | 3 + drivers/net/i40e/i40e_rxtx.c | 143 +++++++++++++------------ 5 files changed, 157 insertions(+), 68 deletions(-) diff --git a/doc/guides/nics/i40e.rst b/doc/guides/nics/i40e.rst index 5d8500cef6..0acda43721 100644 --- a/doc/guides/nics/i40e.rst +++ b/doc/guides/nics/i40e.rst @@ -163,6 +163,15 @@ Runtime Config Options Currently hot-plugging of representor ports is not supported so all required representors must be specified on the creation of the PF. +- ``Use latest supported vector`` (default ``disable``) + + Latest supported vector path may not always get the best perf so vector path was + recommended to use only on later platform. But users may want the latest vector path + since it can get better perf in some real work loading cases. So ``devargs`` param + ``use-latest-supported-vec`` is introduced, for example:: + + -w 84:00.0,use-latest-supported-vec=1 + Driver compilation and testing ------------------------------ diff --git a/doc/guides/rel_notes/release_18_11.rst b/doc/guides/rel_notes/release_18_11.rst index bc9b74ec44..13763e3db7 100644 --- a/doc/guides/rel_notes/release_18_11.rst +++ b/doc/guides/rel_notes/release_18_11.rst @@ -61,6 +61,11 @@ New Features * Match items: destination MAC address. * Action items: push/pop/rewrite vlan header. +* **Added a devarg to use the latest supported vector path in i40e.** + A new devarg ``use-latest-supported-vec`` was introduced to allow users to + choose the latest vector path that the platform supported. For example, users + can use AVX2 vector path on BDW/HSW to get better performance. + * **Added support for SR-IOV in netvsc PMD.** The ``netvsc`` poll mode driver now supports the Accelerated Networking diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c index 24d73f2ff4..51ad847e8f 100644 --- a/drivers/net/i40e/i40e_ethdev.c +++ b/drivers/net/i40e/i40e_ethdev.c @@ -44,6 +44,7 @@ #define ETH_I40E_FLOATING_VEB_LIST_ARG "floating_veb_list" #define ETH_I40E_SUPPORT_MULTI_DRIVER "support-multi-driver" #define ETH_I40E_QUEUE_NUM_PER_VF_ARG "queue-num-per-vf" +#define ETH_I40E_USE_LATEST_VEC "use-latest-supported-vec" #define I40E_CLEAR_PXE_WAIT_MS 200 @@ -409,6 +410,7 @@ static const char *const valid_keys[] = { ETH_I40E_FLOATING_VEB_LIST_ARG, ETH_I40E_SUPPORT_MULTI_DRIVER, ETH_I40E_QUEUE_NUM_PER_VF_ARG, + ETH_I40E_USE_LATEST_VEC, NULL}; static const struct rte_pci_id pci_id_i40e_map[] = { @@ -1202,6 +1204,64 @@ i40e_aq_debug_write_global_register(struct i40e_hw *hw, return i40e_aq_debug_write_register(hw, reg_addr, reg_val, cmd_details); } +static int +i40e_parse_latest_vec_handler(__rte_unused const char *key, + const char *value, + void *opaque) +{ + struct i40e_adapter *ad; + int use_latest_vec; + + ad = (struct i40e_adapter *)opaque; + + use_latest_vec = atoi(value); + + if (use_latest_vec != 0 && use_latest_vec != 1) + PMD_DRV_LOG(WARNING, "Value should be 0 or 1, set it as 1!"); + + ad->use_latest_vec = (uint8_t)use_latest_vec; + + return 0; +} + +static int +i40e_use_latest_vec(struct rte_eth_dev *dev) +{ + struct i40e_adapter *ad = + I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private); + struct rte_kvargs *kvlist; + int kvargs_count; + + ad->use_latest_vec = false; + + if (!dev->device->devargs) + return 0; + + kvlist = rte_kvargs_parse(dev->device->devargs->args, valid_keys); + if (!kvlist) + return -EINVAL; + + kvargs_count = rte_kvargs_count(kvlist, ETH_I40E_USE_LATEST_VEC); + if (!kvargs_count) { + rte_kvargs_free(kvlist); + return 0; + } + + if (kvargs_count > 1) + PMD_DRV_LOG(WARNING, "More than one argument \"%s\" and only " + "the first invalid or last valid one is used !", + ETH_I40E_USE_LATEST_VEC); + + if (rte_kvargs_process(kvlist, ETH_I40E_USE_LATEST_VEC, + i40e_parse_latest_vec_handler, ad) < 0) { + rte_kvargs_free(kvlist); + return -EINVAL; + } + + rte_kvargs_free(kvlist); + return 0; +} + #define I40E_ALARM_INTERVAL 50000 /* us */ static int @@ -1266,6 +1326,8 @@ eth_i40e_dev_init(struct rte_eth_dev *dev, void *init_params __rte_unused) /* Check if need to support multi-driver */ i40e_support_multi_driver(dev); + /* Check if users want the latest supported vec path */ + i40e_use_latest_vec(dev); /* Make sure all is clean before doing PF reset */ i40e_clear_hw(hw); @@ -12599,4 +12661,5 @@ RTE_PMD_REGISTER_PARAM_STRING(net_i40e, ETH_I40E_FLOATING_VEB_ARG "=1" ETH_I40E_FLOATING_VEB_LIST_ARG "=" ETH_I40E_QUEUE_NUM_PER_VF_ARG "=1|2|4|8|16" - ETH_I40E_SUPPORT_MULTI_DRIVER "=1"); + ETH_I40E_SUPPORT_MULTI_DRIVER "=1" + ETH_I40E_USE_LATEST_VEC "=0|1"); diff --git a/drivers/net/i40e/i40e_ethdev.h b/drivers/net/i40e/i40e_ethdev.h index 3fffe5a555..7d197f6aa8 100644 --- a/drivers/net/i40e/i40e_ethdev.h +++ b/drivers/net/i40e/i40e_ethdev.h @@ -1078,6 +1078,9 @@ struct i40e_adapter { uint64_t pctypes_tbl[I40E_FLOW_TYPE_MAX] __rte_cache_min_aligned; uint64_t flow_types_mask; uint64_t pctypes_mask; + + /* For devargs */ + uint8_t use_latest_vec; }; /** diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c index 5e78d489e2..7c986d5357 100644 --- a/drivers/net/i40e/i40e_rxtx.c +++ b/drivers/net/i40e/i40e_rxtx.c @@ -2909,6 +2909,35 @@ i40e_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id, qinfo->conf.offloads = txq->offloads; } +static eth_rx_burst_t +i40e_get_latest_rx_vec(bool scatter) +{ +#ifdef RTE_ARCH_X86 + if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2)) + return scatter ? i40e_recv_scattered_pkts_vec_avx2 : + i40e_recv_pkts_vec_avx2; +#endif + return scatter ? i40e_recv_scattered_pkts_vec : + i40e_recv_pkts_vec; +} + +static eth_rx_burst_t +i40e_get_recommend_rx_vec(bool scatter) +{ +#ifdef RTE_ARCH_X86 + /* + * since AVX frequency can be different to base frequency, limit + * use of AVX2 version to later plaforms, not all those that could + * theoretically run it. + */ + if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F)) + return scatter ? i40e_recv_scattered_pkts_vec_avx2 : + i40e_recv_pkts_vec_avx2; +#endif + return scatter ? i40e_recv_scattered_pkts_vec : + i40e_recv_pkts_vec; +} + void __attribute__((cold)) i40e_set_rx_function(struct rte_eth_dev *dev) { @@ -2940,57 +2969,17 @@ i40e_set_rx_function(struct rte_eth_dev *dev) } } - if (dev->data->scattered_rx) { - /* Set the non-LRO scattered callback: there are Vector and - * single allocation versions. - */ - if (ad->rx_vec_allowed) { - PMD_INIT_LOG(DEBUG, "Using Vector Scattered Rx " - "callback (port=%d).", - dev->data->port_id); - - dev->rx_pkt_burst = i40e_recv_scattered_pkts_vec; -#ifdef RTE_ARCH_X86 - /* - * since AVX frequency can be different to base - * frequency, limit use of AVX2 version to later - * plaforms, not all those that could theoretically - * run it. - */ - if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F)) - dev->rx_pkt_burst = - i40e_recv_scattered_pkts_vec_avx2; -#endif - } else { - PMD_INIT_LOG(DEBUG, "Using a Scattered with bulk " - "allocation callback (port=%d).", - dev->data->port_id); - dev->rx_pkt_burst = i40e_recv_scattered_pkts; - } - /* If parameters allow we are going to choose between the following - * callbacks: - * - Vector - * - Bulk Allocation - * - Single buffer allocation (the simplest one) - */ - } else if (ad->rx_vec_allowed) { - PMD_INIT_LOG(DEBUG, "Vector rx enabled, please make sure RX " - "burst size no less than %d (port=%d).", - RTE_I40E_DESCS_PER_LOOP, - dev->data->port_id); - - dev->rx_pkt_burst = i40e_recv_pkts_vec; -#ifdef RTE_ARCH_X86 - /* - * since AVX frequency can be different to base - * frequency, limit use of AVX2 version to later - * plaforms, not all those that could theoretically - * run it. - */ - if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F)) - dev->rx_pkt_burst = i40e_recv_pkts_vec_avx2; -#endif - } else if (ad->rx_bulk_alloc_allowed) { + if (ad->rx_vec_allowed) { + /* Vec Rx path */ + PMD_INIT_LOG(DEBUG, "Vector Rx path will be used on port=%d.", + dev->data->port_id); + if (ad->use_latest_vec) + dev->rx_pkt_burst = + i40e_get_latest_rx_vec(dev->data->scattered_rx); + else + dev->rx_pkt_burst = + i40e_get_recommend_rx_vec(dev->data->scattered_rx); + } else if (!dev->data->scattered_rx && ad->rx_bulk_alloc_allowed) { PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are " "satisfied. Rx Burst Bulk Alloc function " "will be used on port=%d.", @@ -2998,12 +2987,12 @@ i40e_set_rx_function(struct rte_eth_dev *dev) dev->rx_pkt_burst = i40e_recv_pkts_bulk_alloc; } else { - PMD_INIT_LOG(DEBUG, "Rx Burst Bulk Alloc Preconditions are not " - "satisfied, or Scattered Rx is requested " - "(port=%d).", + /* Simple Rx Path. */ + PMD_INIT_LOG(DEBUG, "Simple Rx path will be used on port=%d.", dev->data->port_id); - - dev->rx_pkt_burst = i40e_recv_pkts; + dev->rx_pkt_burst = dev->data->scattered_rx ? + i40e_recv_scattered_pkts : + i40e_recv_pkts; } /* Propagate information about RX function choice through all queues. */ @@ -3049,6 +3038,31 @@ i40e_set_tx_function_flag(struct rte_eth_dev *dev, struct i40e_tx_queue *txq) txq->queue_id); } +static eth_tx_burst_t +i40e_get_latest_tx_vec(void) +{ +#ifdef RTE_ARCH_X86 + if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2)) + return i40e_xmit_pkts_vec_avx2; +#endif + return i40e_xmit_pkts_vec; +} + +static eth_tx_burst_t +i40e_get_recommend_tx_vec(void) +{ +#ifdef RTE_ARCH_X86 + /* + * since AVX frequency can be different to base frequency, limit + * use of AVX2 version to later plaforms, not all those that could + * theoretically run it. + */ + if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F)) + return i40e_xmit_pkts_vec_avx2; +#endif + return i40e_xmit_pkts_vec; +} + void __attribute__((cold)) i40e_set_tx_function(struct rte_eth_dev *dev) { @@ -3073,17 +3087,12 @@ i40e_set_tx_function(struct rte_eth_dev *dev) if (ad->tx_simple_allowed) { if (ad->tx_vec_allowed) { PMD_INIT_LOG(DEBUG, "Vector tx finally be used."); - dev->tx_pkt_burst = i40e_xmit_pkts_vec; -#ifdef RTE_ARCH_X86 - /* - * since AVX frequency can be different to base - * frequency, limit use of AVX2 version to later - * plaforms, not all those that could theoretically - * run it. - */ - if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F)) - dev->tx_pkt_burst = i40e_xmit_pkts_vec_avx2; -#endif + if (ad->use_latest_vec) + dev->tx_pkt_burst = + i40e_get_latest_tx_vec(); + else + dev->tx_pkt_burst = + i40e_get_recommend_tx_vec(); } else { PMD_INIT_LOG(DEBUG, "Simple tx finally be used."); dev->tx_pkt_burst = i40e_xmit_pkts_simple; -- 2.20.1