net/mlx5: add reclaim memory mode

Currently, when flow destroyed, some memory resources may still be kept
as cached to help next time create flow more efficiently.

Some system may need the resources to be more flexible with flow create
and destroy.  After peak time, with millions of flows destroyed, the
system would prefer the resources to be reclaimed completely, no cache
is needed. Then the resources can be allocated and used by other
components. The system is not so sensitive about the flow insertion
rate, but more care about the resources.

Both DPDK mlx5 PMD driver and the low level component rdma-core have
provided the flow resources to be configured cached or not, but there is
no APIs or parameters exposed to user to configure the flow resources
cache mode. In this case, introduce a new PMD devarg to let user
configure the flow resources cache mode will be helpful.

This commit is to add a new "reclaim_mem_mode" to help user configure if
the destroyed flows' cache resources should be kept or not.

Their will be three mode can be chosen:
1. 0(none). It means the flow resources will be cached as usual. The
resources will be cached, helpful with flow insertion rate.
2. 1(light). It will only enable the DPDK PMD level resources reclaim.
3. 2(aggressive). Both DPDK PMD level and rdma-core low level will be
configured as reclaimed mode.

With these three mode, user can configure the resources cache mode with
different levels.

Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>

diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index bb03df6..0ff3c53 100644 (file)
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -849,6 +849,26 @@ Driver options
   By default, the PMD will set this value to 16, which means that 9KB jumbo
   frames will be supported.
 
+- ``reclaim_mem_mode`` parameter [int]
+
+  Cache some resources in flow destroy will help flow recreation more efficient.
+  While some systems may require the all the resources can be reclaimed after
+  flow destroyed.
+  The parameter ``reclaim_mem_mode`` provides the option for user to configure
+  if the resource cache is needed or not.
+
+  There are three options to choose:
+
+  - 0. It means the flow resources will be cached as usual. The resources will
+    be cached, helpful with flow insertion rate.
+
+  - 1. It will only enable the DPDK PMD level resources reclaim.
+
+  - 2. Both DPDK PMD level and rdma-core low level will be configured as
+    reclaimed mode.
+
+  By default, the PMD will set this value to 0.
+
 .. _mlx5_firmware_config:
 
 Firmware configuration

diff --git a/doc/guides/rel_notes/release_20_08.rst b/doc/guides/rel_notes/release_20_08.rst
index 39064af..dee4ccb 100644 (file)
--- a/doc/guides/rel_notes/release_20_08.rst
+++ b/doc/guides/rel_notes/release_20_08.rst
@@ -56,6 +56,12 @@ New Features
      Also, make sure to start the actual text at the margin.
      =========================================================
 
+* **Updated Mellanox mlx5 driver.**
+
+  Updated Mellanox mlx5 driver with new features and improvements, including:
+
+  * Added new PMD devarg ``reclaim_mem_mode``.
+
 
 Removed Items
 -------------

diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 469ff73..95a0f33 100644 (file)
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -161,6 +161,9 @@
  */
 #define MLX5_HP_BUF_SIZE "hp_buf_log_sz"
 
+/* Flow memory reclaim mode. */
+#define MLX5_RECLAIM_MEM "reclaim_mem_mode"
+
 #ifndef HAVE_IBV_MLX5_MOD_MPW
 #define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2)
 #define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3)
@@ -577,8 +580,11 @@ mlx5_flow_ipool_create(struct mlx5_ibv_shared *sh,
                mlx5_ipool_cfg[MLX5_IPOOL_MLX5_FLOW].size =
                                        MLX5_FLOW_HANDLE_VERBS_SIZE;
 #endif
-       for (i = 0; i < MLX5_IPOOL_MAX; ++i)
+       for (i = 0; i < MLX5_IPOOL_MAX; ++i) {
+               if (config->reclaim_mode)
+                       mlx5_ipool_cfg[i].release_mem_en = 1;
                sh->ipool[i] = mlx5_ipool_create(&mlx5_ipool_cfg[i]);
+       }
 }
 
 /**
@@ -1192,6 +1198,12 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv)
                sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop();
        }
 #endif
+       if (priv->config.reclaim_mode == MLX5_RCM_AGGR) {
+               mlx5_glue->dr_reclaim_domain_memory(sh->rx_domain, 1);
+               mlx5_glue->dr_reclaim_domain_memory(sh->tx_domain, 1);
+               if (sh->fdb_domain)
+                       mlx5_glue->dr_reclaim_domain_memory(sh->fdb_domain, 1);
+       }
        sh->pop_vlan_action = mlx5_glue->dr_create_flow_action_pop_vlan();
 #endif /* HAVE_MLX5DV_DR */
        sh->dv_refcnt++;
@@ -1862,6 +1874,15 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
                DRV_LOG(DEBUG, "class argument is %s.", val);
        } else if (strcmp(MLX5_HP_BUF_SIZE, key) == 0) {
                config->log_hp_size = tmp;
+       } else if (strcmp(MLX5_RECLAIM_MEM, key) == 0) {
+               if (tmp != MLX5_RCM_NONE &&
+                   tmp != MLX5_RCM_LIGHT &&
+                   tmp != MLX5_RCM_AGGR) {
+                       DRV_LOG(ERR, "Unrecognize %s: \"%s\"", key, val);
+                       rte_errno = EINVAL;
+                       return -rte_errno;
+               }
+               config->reclaim_mode = tmp;
        } else {
                DRV_LOG(WARNING, "%s: unknown parameter", key);
                rte_errno = EINVAL;
@@ -1916,6 +1937,7 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs)
                MLX5_LRO_TIMEOUT_USEC,
                MLX5_CLASS_ARG_NAME,
                MLX5_HP_BUF_SIZE,
+               MLX5_RECLAIM_MEM,
                NULL,
        };
        struct rte_kvargs *kvlist;

diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 2908c8b..8e60897 100644 (file)
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -60,6 +60,18 @@ enum mlx5_ipool_index {
        MLX5_IPOOL_MAX,
 };
 
+/*
+ * There are three reclaim memory mode supported.
+ * 0(none) means no memory reclaim.
+ * 1(light) means only PMD level reclaim.
+ * 2(aggressive) means both PMD and rdma-core level reclaim.
+ */
+enum mlx5_reclaim_mem_mode {
+       MLX5_RCM_NONE, /* Don't reclaim memory. */
+       MLX5_RCM_LIGHT, /* Reclaim PMD level. */
+       MLX5_RCM_AGGR, /* Reclaim PMD and rdma-core level. */
+};
+
 /** Key string for IPC. */
 #define MLX5_MP_NAME "net_mlx5_mp"
 
@@ -160,6 +172,7 @@ struct mlx5_dev_config {
        unsigned int swp:1; /* Tx generic tunnel checksum and TSO offload. */
        unsigned int devx:1; /* Whether devx interface is available or not. */
        unsigned int dest_tir:1; /* Whether advanced DR API is available. */
+       unsigned int reclaim_mode:2; /* Memory reclaim mode. */
        struct {
                unsigned int enabled:1; /* Whether MPRQ is enabled. */
                unsigned int stride_num_n; /* Number of strides. */