net/mlx5: add option to allocate memory from system

Currently, for MLX5 PMD, once millions of flows created, the memory
consumption of the flows are also very huge. For the system with limited
memory, it means the system need to reserve most of the memory as huge
page memory to serve the flows in advance. And other normal applications
will have no chance to use this reserved memory any more. While most of
the time, the system will not have lots of flows, the  reserved huge
page memory becomes a bit waste of memory at most of the time.

By the new sys_mem_en devarg, once set it to be true, it allows the PMD
allocate the memory from system by default with the new add mlx5 memory
management functions. Only once the MLX5_MEM_RTE flag is set, the memory
will be allocate from rte, otherwise, it allocates memory from system.

So in this case, the system with limited memory no need to reserve most
of the memory for hugepage. Only some needed memory for datapath objects
will be enough to allocated with explicitly flag. Other memory will be
allocated from system. For system with enough memory, no need to care
about the devarg, the memory will always be from rte hugepage.

One restriction is that for DPDK application with multiple PCI devices,
if the sys_mem_en devargs are different between the devices, the
sys_mem_en only gets the value from the first device devargs, and print
out a message to warn that.

Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>

diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index c185129..00427b0 100644 (file)
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -916,6 +916,13 @@ Driver options
 
   By default, the PMD will set this value to 0.
 
+- ``sys_mem_en`` parameter [int]
+
+  A non-zero value enables the PMD memory management allocating memory
+  from system by default, without explicit rte memory flag.
+
+  By default, the PMD will set this value to 0.
+
 .. _mlx5_firmware_config:
 
 Firmware configuration

diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c
index f228bab..df0fae9 100644 (file)
--- a/drivers/net/mlx5/linux/mlx5_os.c
+++ b/drivers/net/mlx5/linux/mlx5_os.c
@@ -43,6 +43,7 @@
 #include <mlx5_common.h>
 #include <mlx5_common_mp.h>
 #include <mlx5_common_mr.h>
+#include <mlx5_malloc.h>
 
 #include "mlx5_defs.h"
 #include "mlx5.h"
@@ -495,6 +496,7 @@ err_secondary:
                        strerror(rte_errno));
                goto error;
        }
+       mlx5_malloc_mem_select(config.sys_mem_en);
        sh = mlx5_alloc_shared_dev_ctx(spawn, &config);
        if (!sh)
                return NULL;

diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 723c1dd..b2a8460 100644 (file)
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -180,6 +180,9 @@
 /* Flow memory reclaim mode. */
 #define MLX5_RECLAIM_MEM "reclaim_mem_mode"
 
+/* The default memory allocator used in PMD. */
+#define MLX5_SYS_MEM_EN "sys_mem_en"
+
 static const char *MZ_MLX5_PMD_SHARED_DATA = "mlx5_pmd_shared_data";
 
 /* Shared memory between primary and secondary processes. */
@@ -1533,6 +1536,8 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
                        return -rte_errno;
                }
                config->reclaim_mode = tmp;
+       } else if (strcmp(MLX5_SYS_MEM_EN, key) == 0) {
+               config->sys_mem_en = !!tmp;
        } else {
                DRV_LOG(WARNING, "%s: unknown parameter", key);
                rte_errno = EINVAL;
@@ -1591,6 +1596,7 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs)
                MLX5_CLASS_ARG_NAME,
                MLX5_HP_BUF_SIZE,
                MLX5_RECLAIM_MEM,
+               MLX5_SYS_MEM_EN,
                NULL,
        };
        struct rte_kvargs *kvlist;

diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 2e61d0c..4d90a19 100644 (file)
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -217,6 +217,7 @@ struct mlx5_dev_config {
        unsigned int dest_tir:1; /* Whether advanced DR API is available. */
        unsigned int reclaim_mode:2; /* Memory reclaim mode. */
        unsigned int rt_timestamp:1; /* realtime timestamp format. */
+       unsigned int sys_mem_en:1; /* The default memory allocator. */
        struct {
                unsigned int enabled:1; /* Whether MPRQ is enabled. */
                unsigned int stride_num_n; /* Number of strides. */