Netdev List
 help / color / mirror / Atom feed
From: Stephen Hemminger <stephen@networkplumber.org>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, Haiyang Zhang <haiyangz@microsoft.com>
Subject: [PATCH net-stable 09/24] hv_netvsc: Use the num_online_cpus() for channel limit
Date: Mon, 14 May 2018 15:32:08 -0700	[thread overview]
Message-ID: <20180514223223.25433-10-sthemmin@microsoft.com> (raw)
In-Reply-To: <20180514223223.25433-1-sthemmin@microsoft.com>

From: Haiyang Zhang <haiyangz@microsoft.com>

commit 25a39f7f975c3c26a0052fbf9b59201c06744332 upstream

Since we no longer localize channel/CPU affiliation within one NUMA
node, num_online_cpus() is used as the number of channel cap, instead of
the number of processors in a NUMA node.

This patch allows a bigger range for tuning the number of channels.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/rndis_filter.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 0c99d9926085..05109ed5377c 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1221,7 +1221,6 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	u32 mtu, size;
-	const struct cpumask *node_cpu_mask;
 	u32 num_possible_rss_qs;
 	int i, ret;
 
@@ -1290,14 +1289,8 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 	if (ret || rsscap.num_recv_que < 2)
 		goto out;
 
-	/*
-	 * We will limit the VRSS channels to the number CPUs in the NUMA node
-	 * the primary channel is currently bound to.
-	 *
-	 * This also guarantees that num_possible_rss_qs <= num_online_cpus
-	 */
-	node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
-	num_possible_rss_qs = min_t(u32, cpumask_weight(node_cpu_mask),
+	/* This guarantees that num_possible_rss_qs <= num_online_cpus */
+	num_possible_rss_qs = min_t(u32, num_online_cpus(),
 				    rsscap.num_recv_que);
 
 	net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, num_possible_rss_qs);
-- 
2.17.0

  parent reply	other threads:[~2018-05-14 22:32 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-14 22:31 [PATCH net-stable 00/24] hv_netvsc patches for 4.14 stable Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 01/24] hv_netvsc: Fix the real number of queues of non-vRSS cases Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 02/24] hv_netvsc: Rename ind_table to rx_table Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 03/24] hv_netvsc: Rename tx_send_table to tx_table Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 04/24] hv_netvsc: Add initialization of tx_table in netvsc_device_add() Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 05/24] hv_netvsc: Set tx_table to equal weight after subchannels open Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 06/24] hv_netvsc: netvsc_teardown_gpadl() split Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 07/24] hv_netvsc: preserve hw_features on mtu/channels/ringparam changes Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 08/24] hv_netvsc: empty current transmit aggregation if flow blocked Stephen Hemminger
2018-05-14 22:32 ` Stephen Hemminger [this message]
2018-05-14 22:32 ` [PATCH net-stable 10/24] hv_netvsc: avoid retry on send during shutdown Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 11/24] hv_netvsc: only wake transmit queue if link is up Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 12/24] hv_netvsc: fix error unwind handling if vmbus_open fails Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 13/24] hv_netvsc: cancel subchannel setup before halting device Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 14/24] hv_netvsc: fix race in napi poll when rescheduling Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 15/24] hv_netvsc: defer queue selection to VF Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 16/24] hv_netvsc: disable NAPI before channel close Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 17/24] hv_netvsc: use RCU to fix concurrent rx and queue changes Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 18/24] hv_netvsc: change GPAD teardown order on older versions Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 19/24] hv_netvsc: common detach logic Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 20/24] hv_netvsc: Use Windows version instead of NVSP version on GPAD teardown Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 21/24] hv_netvsc: Split netvsc_revoke_buf() and netvsc_teardown_gpadl() Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 22/24] hv_netvsc: Ensure correct teardown message sequence order Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 23/24] hv_netvsc: Fix net device attach on older Windows hosts Stephen Hemminger
2018-05-14 22:32 ` [PATCH net-stable 24/24] hv_netvsc: set master device Stephen Hemminger

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=20180514223223.25433-10-sthemmin@microsoft.com \
    --to=stephen@networkplumber.org \
    --cc=davem@davemloft.net \
    --cc=haiyangz@microsoft.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
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