All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michal Kazior <michal.kazior@tieto.com>
To: ath10k@lists.infradead.org
Cc: linux-wireless@vger.kernel.org, Michal Kazior <michal.kazior@tieto.com>
Subject: [PATCH] ath10k: improve tx scheduling
Date: Mon,  9 May 2016 14:25:08 +0200	[thread overview]
Message-ID: <1462796708-13880-1-git-send-email-michal.kazior@tieto.com> (raw)

Recent changes revolving around implementing
wake_tx_queue support introduced a significant
performance regressions on some (slower, uni-proc)
systems.

Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c | 3 ---
 drivers/net/wireless/ath/ath10k/mac.c    | 7 ++++---
 drivers/net/wireless/ath/ath10k/txrx.c   | 3 +++
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index cc979a4faeb0..7411b69fde42 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -2291,7 +2291,6 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 			ath10k_htt_tx_mgmt_dec_pending(htt);
 			spin_unlock_bh(&htt->tx_lock);
 		}
-		ath10k_mac_tx_push_pending(ar);
 		break;
 	}
 	case HTT_T2H_MSG_TYPE_TX_COMPL_IND:
@@ -2442,8 +2441,6 @@ static void ath10k_htt_txrx_compl_task(unsigned long ptr)
 		dev_kfree_skb_any(skb);
 	}
 
-	ath10k_mac_tx_push_pending(ar);
-
 	num_mpdus = atomic_read(&htt->num_mpdus_ready);
 
 	while (num_mpdus) {
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 6dd1d26b357f..1dd415d3c0ee 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -3781,6 +3781,9 @@ void ath10k_mac_tx_push_pending(struct ath10k *ar)
 	int ret;
 	int max;
 
+	if (ar->htt.num_pending_tx >= (ar->htt.max_num_pending_tx / 2))
+		return;
+
 	spin_lock_bh(&ar->txqs_lock);
 	rcu_read_lock();
 
@@ -4051,9 +4054,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 		list_add_tail(&artxq->list, &ar->txqs);
 	spin_unlock_bh(&ar->txqs_lock);
 
-	if (ath10k_mac_tx_can_push(hw, txq))
-		tasklet_schedule(&ar->htt.txrx_compl_task);
-
+	ath10k_mac_tx_push_pending(ar);
 	ath10k_htt_tx_txq_update(hw, txq);
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index 576e7c42ed65..1966c787998b 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -117,6 +117,9 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 
 	ieee80211_tx_status(htt->ar->hw, msdu);
 	/* we do not own the msdu anymore */
+
+	ath10k_mac_tx_push_pending(ar);
+
 	return 0;
 }
 
-- 
2.1.4


WARNING: multiple messages have this Message-ID (diff)
From: Michal Kazior <michal.kazior@tieto.com>
To: ath10k@lists.infradead.org
Cc: linux-wireless@vger.kernel.org, Michal Kazior <michal.kazior@tieto.com>
Subject: [PATCH] ath10k: improve tx scheduling
Date: Mon,  9 May 2016 14:25:08 +0200	[thread overview]
Message-ID: <1462796708-13880-1-git-send-email-michal.kazior@tieto.com> (raw)

Recent changes revolving around implementing
wake_tx_queue support introduced a significant
performance regressions on some (slower, uni-proc)
systems.

Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c | 3 ---
 drivers/net/wireless/ath/ath10k/mac.c    | 7 ++++---
 drivers/net/wireless/ath/ath10k/txrx.c   | 3 +++
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index cc979a4faeb0..7411b69fde42 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -2291,7 +2291,6 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 			ath10k_htt_tx_mgmt_dec_pending(htt);
 			spin_unlock_bh(&htt->tx_lock);
 		}
-		ath10k_mac_tx_push_pending(ar);
 		break;
 	}
 	case HTT_T2H_MSG_TYPE_TX_COMPL_IND:
@@ -2442,8 +2441,6 @@ static void ath10k_htt_txrx_compl_task(unsigned long ptr)
 		dev_kfree_skb_any(skb);
 	}
 
-	ath10k_mac_tx_push_pending(ar);
-
 	num_mpdus = atomic_read(&htt->num_mpdus_ready);
 
 	while (num_mpdus) {
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 6dd1d26b357f..1dd415d3c0ee 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -3781,6 +3781,9 @@ void ath10k_mac_tx_push_pending(struct ath10k *ar)
 	int ret;
 	int max;
 
+	if (ar->htt.num_pending_tx >= (ar->htt.max_num_pending_tx / 2))
+		return;
+
 	spin_lock_bh(&ar->txqs_lock);
 	rcu_read_lock();
 
@@ -4051,9 +4054,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 		list_add_tail(&artxq->list, &ar->txqs);
 	spin_unlock_bh(&ar->txqs_lock);
 
-	if (ath10k_mac_tx_can_push(hw, txq))
-		tasklet_schedule(&ar->htt.txrx_compl_task);
-
+	ath10k_mac_tx_push_pending(ar);
 	ath10k_htt_tx_txq_update(hw, txq);
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index 576e7c42ed65..1966c787998b 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -117,6 +117,9 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 
 	ieee80211_tx_status(htt->ar->hw, msdu);
 	/* we do not own the msdu anymore */
+
+	ath10k_mac_tx_push_pending(ar);
+
 	return 0;
 }
 
-- 
2.1.4


_______________________________________________
ath10k mailing list
ath10k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath10k

             reply	other threads:[~2016-05-09 12:23 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-05-09 12:25 Michal Kazior [this message]
2016-05-09 12:25 ` [PATCH] ath10k: improve tx scheduling Michal Kazior
2016-05-24 17:52 ` Kalle Valo
2016-05-24 17:52   ` Kalle Valo

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=1462796708-13880-1-git-send-email-michal.kazior@tieto.com \
    --to=michal.kazior@tieto.com \
    --cc=ath10k@lists.infradead.org \
    --cc=linux-wireless@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.