Lets make wifi fast again!
 help / color / mirror / Atom feed
From: Rajkumar Manoharan <rmanohar@codeaurora.org>
To: "Toke Høiland-Jørgensen" <toke@toke.dk>
Cc: linux-wireless@vger.kernel.org,
	make-wifi-fast@lists.bufferbloat.net,
	Felix Fietkau <nbd@nbd.name>, Kan Yan <kyan@google.com>,
	linux-wireless-owner@vger.kernel.org
Subject: Re: [Make-wifi-fast] [PATCH RFC v4 3/4] mac80211: Add airtime accounting and scheduling to TXQs
Date: Thu, 27 Sep 2018 22:29:03 -0700	[thread overview]
Message-ID: <863bc54fbf04441d38dd53f523300a7e@codeaurora.org> (raw)
In-Reply-To: <8f7145bf5abe50194bced025a5e739b9@codeaurora.org>

On 2018-09-26 17:09, Rajkumar Manoharan wrote:
> On 2018-09-26 02:22, Toke Høiland-Jørgensen wrote:
>> Rajkumar Manoharan <rmanohar@codeaurora.org> writes:

> :( Yeah... I got confused with attached soft lockup in ARM platform.
> 
Toke,

Cause for the soft lockup exposed in multi client scenario is due to
mixed order of fq_lock and active_txqs_lock. In wake_tx_queue or 
push_pending
case, driver acquires active_txq_lock first by schedule_start and 
followed by
fq_lock in tx_dequeue. The same order should be maintained in sta 
cleanup.
Below change fixed the issue.

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 4814710a64f3..2029d600663b 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -114,9 +114,7 @@ static void __cleanup_single_sta(struct sta_info 
*sta)
                 for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
                         struct txq_info *txqi = 
to_txq_info(sta->sta.txq[i]);

-                       spin_lock_bh(&fq->lock);
                         ieee80211_txq_purge(local, txqi);
-                       spin_unlock_bh(&fq->lock);
                 }
         }

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 884d9ce5ce4b..5d70f64a205c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1467,8 +1467,10 @@ void ieee80211_txq_purge(struct ieee80211_local 
*local,
         struct fq *fq = &local->fq;
         struct fq_tin *tin = &txqi->tin;

+       spin_lock_bh(&fq->lock);
         fq_tin_reset(fq, tin, fq_skb_free_func);
         ieee80211_purge_tx_queue(&local->hw, &txqi->frags);
+       spin_unlock_bh(&fq->lock);
         spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]);
         list_del_init(&txqi->schedule_order);
         spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]);

-Rajkumar

  reply	other threads:[~2018-09-28  5:29 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-16 17:42 [Make-wifi-fast] [PATCH RFC v4 0/4] Move TXQ scheduling into mac80211 Toke Høiland-Jørgensen
2018-09-16 17:42 ` [Make-wifi-fast] [PATCH RFC v4 2/4] cfg80211: Add airtime statistics and settings Toke Høiland-Jørgensen
2018-09-16 17:42 ` [Make-wifi-fast] [PATCH RFC v4 1/4] mac80211: Add TXQ scheduling API Toke Høiland-Jørgensen
2018-09-18  0:57   ` Rajkumar Manoharan
2018-09-18 10:29     ` Toke Høiland-Jørgensen
2018-09-18 18:51       ` Rajkumar Manoharan
2018-09-18 20:41         ` Toke Høiland-Jørgensen
2018-09-18 21:30           ` Rajkumar Manoharan
2018-09-19  9:09             ` Toke Høiland-Jørgensen
2018-09-19 14:43               ` Kalle Valo
2018-09-19 14:50                 ` Toke Høiland-Jørgensen
2018-09-19 16:54                   ` Rajkumar Manoharan
2018-09-16 17:42 ` [Make-wifi-fast] [PATCH RFC v4 4/4] ath9k: Switch to mac80211 TXQ scheduling and airtime APIs Toke Høiland-Jørgensen
2018-09-16 17:42 ` [Make-wifi-fast] [PATCH RFC v4 3/4] mac80211: Add airtime accounting and scheduling to TXQs Toke Høiland-Jørgensen
2018-09-26  7:09   ` Rajkumar Manoharan
2018-09-26  9:22     ` Toke Høiland-Jørgensen
2018-09-27  0:09       ` Rajkumar Manoharan
2018-09-28  5:29         ` Rajkumar Manoharan [this message]
2018-09-28  7:51           ` Toke Høiland-Jørgensen
2018-09-28  9:27             ` Rajkumar Manoharan
2018-09-28  9:44               ` Rajkumar Manoharan
2018-09-28  9:58               ` Toke Høiland-Jørgensen
2018-09-28 10:19                 ` Rajkumar Manoharan
2018-09-28 10:35                   ` Jonathan Morton
2018-09-28 10:47                     ` Rajkumar Manoharan
2018-09-28 11:02                       ` Toke Høiland-Jørgensen
2018-09-28 19:51                         ` Rajkumar Manoharan
2018-10-02  6:58                         ` Rajkumar Manoharan
2018-10-02  7:41                           ` Rajkumar Manoharan
2018-10-02  8:22                           ` Toke Høiland-Jørgensen
2018-10-02 16:33                             ` Rajkumar Manoharan
2018-10-02 19:00                               ` Toke Høiland-Jørgensen
2018-10-02 23:07                                 ` Rajkumar Manoharan
2018-10-03  5:53                                   ` Rajkumar Manoharan
2018-10-03  6:27                                     ` Rajkumar Manoharan
2018-10-03  8:41                                     ` Toke Høiland-Jørgensen
2018-09-20 21:29 ` [Make-wifi-fast] [PATCH RFC v4 0/4] Move TXQ scheduling into mac80211 Rajkumar Manoharan
2018-09-21 12:41   ` Toke Høiland-Jørgensen

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

  List information: https://lists.bufferbloat.net/postorius/lists/make-wifi-fast.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=863bc54fbf04441d38dd53f523300a7e@codeaurora.org \
    --to=rmanohar@codeaurora.org \
    --cc=kyan@google.com \
    --cc=linux-wireless-owner@vger.kernel.org \
    --cc=linux-wireless@vger.kernel.org \
    --cc=make-wifi-fast@lists.bufferbloat.net \
    --cc=nbd@nbd.name \
    --cc=toke@toke.dk \
    /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