From: Saeed Mahameed <saeed@kernel•org>
To: "David S. Miller" <davem@davemloft•net>,
Jakub Kicinski <kuba@kernel•org>, Paolo Abeni <pabeni@redhat•com>,
Eric Dumazet <edumazet@google•com>
Cc: Saeed Mahameed <saeedm@nvidia•com>,
netdev@vger•kernel.org, Tariq Toukan <tariqt@nvidia•com>,
Yevgeny Kliteynik <kliteyn@nvidia•com>,
Alex Vesker <valex@nvidia•com>
Subject: [net-next 05/14] net/mlx5: DR, Allocate ste_arr on stack instead of dynamically
Date: Mon, 24 Oct 2022 14:57:25 +0100 [thread overview]
Message-ID: <20221024135734.69673-6-saeed@kernel.org> (raw)
In-Reply-To: <20221024135734.69673-1-saeed@kernel.org>
From: Yevgeny Kliteynik <kliteyn@nvidia•com>
While creting rule, ste_arr is a short array that is allocated in
the beginning of the function and freed at the end.
To avoid memory allocation "hiccups" that sometimes take up to 10ms,
allocate it on stack.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia•com>
Reviewed-by: Alex Vesker <valex@nvidia•com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia•com>
---
.../net/ethernet/mellanox/mlx5/core/steering/dr_rule.c | 9 +--------
1 file changed, 1 insertion(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index ddfaf7891188..cd90f0a02434 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -1089,6 +1089,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
size_t num_actions,
struct mlx5dr_action *actions[])
{
+ u8 hw_ste_arr[DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE] = {};
struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info;
struct mlx5dr_matcher *matcher = rule->matcher;
struct mlx5dr_domain *dmn = matcher->tbl->dmn;
@@ -1098,7 +1099,6 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
struct mlx5dr_ste_htbl *cur_htbl;
struct mlx5dr_ste *ste = NULL;
LIST_HEAD(send_ste_list);
- u8 *hw_ste_arr = NULL;
u32 new_hw_ste_arr_sz;
int ret, i;
@@ -1109,10 +1109,6 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
rule->flow_source))
return 0;
- hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL);
- if (!hw_ste_arr)
- return -ENOMEM;
-
mlx5dr_domain_nic_lock(nic_dmn);
ret = mlx5dr_matcher_add_to_tbl_nic(dmn, nic_matcher);
@@ -1187,8 +1183,6 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
mlx5dr_domain_nic_unlock(nic_dmn);
- kfree(hw_ste_arr);
-
return 0;
free_rule:
@@ -1204,7 +1198,6 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
free_hw_ste:
mlx5dr_domain_nic_unlock(nic_dmn);
- kfree(hw_ste_arr);
return ret;
}
--
2.37.3
next prev parent reply other threads:[~2022-10-24 16:28 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-24 13:57 [pull request][net-next 00/14] mlx5 updates 2022-10-24 Saeed Mahameed
2022-10-24 13:57 ` [net-next 01/14] net/mlx5: DR, In destroy flow, free resources even if FW command failed Saeed Mahameed
2022-10-24 13:57 ` [net-next 02/14] net/mlx5: DR, Fix the SMFS sync_steering for fast teardown Saeed Mahameed
2022-10-24 13:57 ` [net-next 03/14] net/mlx5: DR, Check device state when polling CQ Saeed Mahameed
2022-10-24 13:57 ` [net-next 04/14] net/mlx5: DR, Remove unneeded argument from dr_icm_chunk_destroy Saeed Mahameed
2022-10-24 13:57 ` Saeed Mahameed [this message]
2022-10-25 4:24 ` [net-next 05/14] net/mlx5: DR, Allocate ste_arr on stack instead of dynamically Jakub Kicinski
2022-10-25 10:22 ` Yevgeny Kliteynik
2022-10-24 13:57 ` [net-next 06/14] net/mlx5: DR, Initialize chunk's ste_arrays at chunk creation Saeed Mahameed
2022-10-24 13:57 ` [net-next 07/14] net/mlx5: DR, Handle domain memory resources init/uninit separately Saeed Mahameed
2022-10-24 13:57 ` [net-next 08/14] net/mlx5: DR, In rehash write the line in the entry immediately Saeed Mahameed
2022-10-24 13:57 ` [net-next 09/14] net/mlx5: DR, Manage STE send info objects in pool Saeed Mahameed
2022-10-24 13:57 ` [net-next 10/14] net/mlx5: DR, Allocate icm_chunks from their own slab allocator Saeed Mahameed
2022-10-24 13:57 ` [net-next 11/14] net/mlx5: DR, Allocate htbl from its " Saeed Mahameed
2022-10-24 13:57 ` [net-next 12/14] net/mlx5: DR, Lower sync threshold for ICM hot memory Saeed Mahameed
2022-10-24 13:57 ` [net-next 13/14] net/mlx5: DR, Keep track of hot ICM chunks in an array instead of list Saeed Mahameed
2022-10-24 13:57 ` [net-next 14/14] net/mlx5: DR, Remove the buddy used_list Saeed Mahameed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221024135734.69673-6-saeed@kernel.org \
--to=saeed@kernel$(echo .)org \
--cc=davem@davemloft$(echo .)net \
--cc=edumazet@google$(echo .)com \
--cc=kliteyn@nvidia$(echo .)com \
--cc=kuba@kernel$(echo .)org \
--cc=netdev@vger$(echo .)kernel.org \
--cc=pabeni@redhat$(echo .)com \
--cc=saeedm@nvidia$(echo .)com \
--cc=tariqt@nvidia$(echo .)com \
--cc=valex@nvidia$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox