From: Christian Marangi Date: Mon, 18 Sep 2023 14:36:34 +0000 (+0200) Subject: ipq806x: add patch fixing regression from stmmac TX timer X-Git-Url: http://git.openwrt.org/?p=openwrt%2Fopenwrt.git;a=commitdiff_plain;h=cafa8804a4c5fdea18c7435c09c549841855c98c ipq806x: add patch fixing regression from stmmac TX timer Add patch fixing regression from stmmac TX timer. Refer to the single patch for extensive details on the problem. This should restore original performance before 4.19 kernel. Fixes: #11676 Signed-off-by: Christian Marangi --- diff --git a/target/linux/ipq806x/patches-6.1/700-01-net-introduce-napi_is_scheduled-helper.patch b/target/linux/ipq806x/patches-6.1/700-01-net-introduce-napi_is_scheduled-helper.patch index 813ec97abc..9694bf1144 100644 --- a/target/linux/ipq806x/patches-6.1/700-01-net-introduce-napi_is_scheduled-helper.patch +++ b/target/linux/ipq806x/patches-6.1/700-01-net-introduce-napi_is_scheduled-helper.patch @@ -1,7 +1,7 @@ From b5532bdc6d09e6e789417f0c7a0b665b57b0e7be Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 18 Sep 2023 14:21:56 +0200 -Subject: [PATCH 1/3] net: introduce napi_is_scheduled helper +Subject: [PATCH 1/4] net: introduce napi_is_scheduled helper We currently have napi_if_scheduled_mark_missed that can be used to check if napi is scheduled but that does more thing than simply checking diff --git a/target/linux/ipq806x/patches-6.1/700-02-net-stmmac-improve-TX-timer-arm-logic.patch b/target/linux/ipq806x/patches-6.1/700-02-net-stmmac-improve-TX-timer-arm-logic.patch deleted file mode 100644 index 0f2f366fa9..0000000000 --- a/target/linux/ipq806x/patches-6.1/700-02-net-stmmac-improve-TX-timer-arm-logic.patch +++ /dev/null @@ -1,76 +0,0 @@ -From 26e872db0f14c09ab57486b538ecc3a24c579df2 Mon Sep 17 00:00:00 2001 -From: Christian Marangi -Date: Mon, 18 Sep 2023 14:39:01 +0200 -Subject: [PATCH 2/3] net: stmmac: improve TX timer arm logic - -There is currently a problem with the TX timer getting armed multiple -unnecessary times causing big performance regression on some device that -suffer from heavy handling of hrtimer rearm. - -The use of the TX timer is an old implementation that predates the napi -implementation and the interrupt enable/disable handling. - -Due to stmmac being a very old code, the TX timer was never evaluated -again with this new implementation and was kept there causing -performance regression. The performance regression started to appear -with kernel version 4.19 with 8fce33317023 ("net: stmmac: Rework coalesce -timer and fix multi-queue races") where the timer was reduced to 1ms -causing it to be armed 40 times more than before. - -Decreasing the timer made the problem more present and caused the -regression in the other of 600-700mbps on some device (regression where -this was notice is ipq806x). - -The problem is in the fact that handling the hrtimer on some target is -expensive and recent kernel made the timer armed much more times. -A solution that was proposed was reverting the hrtimer change and use -mod_timer but such solution would still hide the real problem in the -current implementation. - -To fix the regression, apply some additional logic and skip arming the -timer when not needed. - -Arm the timer ONLY if a napi is not already scheduled. Running the timer -is redundant since the same function (stmmac_tx_clean) will run in the -napi TX poll. Also try to cancel any timer if a napi is scheduled to -prevent redundant run of TX call. - -With the following new logic the original performance are restored while -keeping using the hrtimer. - -Signed-off-by: Christian Marangi ---- - .../net/ethernet/stmicro/stmmac/stmmac_main.c | 18 +++++++++++++++--- - 1 file changed, 15 insertions(+), 3 deletions(-) - ---- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c -+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c -@@ -2974,13 +2974,25 @@ static void stmmac_tx_timer_arm(struct s - { - struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; - u32 tx_coal_timer = priv->tx_coal_timer[queue]; -+ struct stmmac_channel *ch; -+ struct napi_struct *napi; - - if (!tx_coal_timer) - return; - -- hrtimer_start(&tx_q->txtimer, -- STMMAC_COAL_TIMER(tx_coal_timer), -- HRTIMER_MODE_REL); -+ ch = &priv->channel[tx_q->queue_index]; -+ napi = tx_q->xsk_pool ? &ch->rxtx_napi : &ch->tx_napi; -+ -+ /* Arm timer only if napi is not already scheduled. -+ * Try to cancel any timer if napi is scheduled, timer will be armed -+ * again in the next scheduled napi. -+ */ -+ if (unlikely(!napi_is_scheduled(napi))) -+ hrtimer_start(&tx_q->txtimer, -+ STMMAC_COAL_TIMER(tx_coal_timer), -+ HRTIMER_MODE_REL); -+ else -+ hrtimer_try_to_cancel(&tx_q->txtimer); - } - - /** diff --git a/target/linux/ipq806x/patches-6.1/700-02-net-stmmac-move-TX-timer-arm-after-DMA-enable.patch b/target/linux/ipq806x/patches-6.1/700-02-net-stmmac-move-TX-timer-arm-after-DMA-enable.patch new file mode 100644 index 0000000000..2b52398425 --- /dev/null +++ b/target/linux/ipq806x/patches-6.1/700-02-net-stmmac-move-TX-timer-arm-after-DMA-enable.patch @@ -0,0 +1,89 @@ +From fb04db35447d1e8ff557c8e57139164cecab7de5 Mon Sep 17 00:00:00 2001 +From: Christian Marangi +Date: Wed, 27 Sep 2023 15:38:31 +0200 +Subject: [PATCH 2/4] net: stmmac: move TX timer arm after DMA enable + +Move TX timer arm call after DMA interrupt is enabled again. + +The TX timer arm function changed logic and now is skipped if a napi is +already scheduled. By moving the TX timer arm call after DMA is enabled, +we permit to correctly skip if a DMA interrupt has been fired and a napi +has been scheduled again. + +Signed-off-by: Christian Marangi +--- + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 19 +++++++++++++++---- + 1 file changed, 15 insertions(+), 4 deletions(-) + +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +@@ -2529,7 +2529,8 @@ static void stmmac_bump_dma_threshold(st + * @queue: TX queue index + * Description: it reclaims the transmit resources after transmission completes. + */ +-static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) ++static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue, ++ bool *pending_packets) + { + struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; + unsigned int bytes_compl = 0, pkts_compl = 0; +@@ -2692,7 +2693,7 @@ static int stmmac_tx_clean(struct stmmac + + /* We still have pending packets, let's call for a new scheduling */ + if (tx_q->dirty_tx != tx_q->cur_tx) +- stmmac_tx_timer_arm(priv, queue); ++ *pending_packets = true; + + __netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue)); + +@@ -5474,12 +5475,13 @@ static int stmmac_napi_poll_tx(struct na + struct stmmac_channel *ch = + container_of(napi, struct stmmac_channel, tx_napi); + struct stmmac_priv *priv = ch->priv_data; ++ bool pending_packets = false; + u32 chan = ch->index; + int work_done; + + priv->xstats.napi_poll++; + +- work_done = stmmac_tx_clean(priv, budget, chan); ++ work_done = stmmac_tx_clean(priv, budget, chan, &pending_packets); + work_done = min(work_done, budget); + + if (work_done < budget && napi_complete_done(napi, work_done)) { +@@ -5490,6 +5492,10 @@ static int stmmac_napi_poll_tx(struct na + spin_unlock_irqrestore(&ch->lock, flags); + } + ++ /* TX still have packet to handle, check if we need to arm tx timer */ ++ if (pending_packets) ++ stmmac_tx_timer_arm(priv, chan); ++ + return work_done; + } + +@@ -5499,11 +5505,12 @@ static int stmmac_napi_poll_rxtx(struct + container_of(napi, struct stmmac_channel, rxtx_napi); + struct stmmac_priv *priv = ch->priv_data; + int rx_done, tx_done, rxtx_done; ++ bool tx_pending_packets = false; + u32 chan = ch->index; + + priv->xstats.napi_poll++; + +- tx_done = stmmac_tx_clean(priv, budget, chan); ++ tx_done = stmmac_tx_clean(priv, budget, chan, &tx_pending_packets); + tx_done = min(tx_done, budget); + + rx_done = stmmac_rx_zc(priv, budget, chan); +@@ -5528,6 +5535,10 @@ static int stmmac_napi_poll_rxtx(struct + spin_unlock_irqrestore(&ch->lock, flags); + } + ++ /* TX still have packet to handle, check if we need to arm tx timer */ ++ if (tx_pending_packets) ++ stmmac_tx_timer_arm(priv, chan); ++ + return min(rxtx_done, budget - 1); + } + diff --git a/target/linux/ipq806x/patches-6.1/700-03-net-stmmac-improve-TX-timer-arm-logic.patch b/target/linux/ipq806x/patches-6.1/700-03-net-stmmac-improve-TX-timer-arm-logic.patch new file mode 100644 index 0000000000..6160b95e60 --- /dev/null +++ b/target/linux/ipq806x/patches-6.1/700-03-net-stmmac-improve-TX-timer-arm-logic.patch @@ -0,0 +1,76 @@ +From cd40cd8b1ca4a6f531c6c3fd78b306e5014f9c04 Mon Sep 17 00:00:00 2001 +From: Christian Marangi +Date: Mon, 18 Sep 2023 14:39:01 +0200 +Subject: [PATCH 3/4] net: stmmac: improve TX timer arm logic + +There is currently a problem with the TX timer getting armed multiple +unnecessary times causing big performance regression on some device that +suffer from heavy handling of hrtimer rearm. + +The use of the TX timer is an old implementation that predates the napi +implementation and the interrupt enable/disable handling. + +Due to stmmac being a very old code, the TX timer was never evaluated +again with this new implementation and was kept there causing +performance regression. The performance regression started to appear +with kernel version 4.19 with 8fce33317023 ("net: stmmac: Rework coalesce +timer and fix multi-queue races") where the timer was reduced to 1ms +causing it to be armed 40 times more than before. + +Decreasing the timer made the problem more present and caused the +regression in the other of 600-700mbps on some device (regression where +this was notice is ipq806x). + +The problem is in the fact that handling the hrtimer on some target is +expensive and recent kernel made the timer armed much more times. +A solution that was proposed was reverting the hrtimer change and use +mod_timer but such solution would still hide the real problem in the +current implementation. + +To fix the regression, apply some additional logic and skip arming the +timer when not needed. + +Arm the timer ONLY if a napi is not already scheduled. Running the timer +is redundant since the same function (stmmac_tx_clean) will run in the +napi TX poll. Also try to cancel any timer if a napi is scheduled to +prevent redundant run of TX call. + +With the following new logic the original performance are restored while +keeping using the hrtimer. + +Signed-off-by: Christian Marangi +--- + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 18 +++++++++++++++--- + 1 file changed, 15 insertions(+), 3 deletions(-) + +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +@@ -2975,13 +2975,25 @@ static void stmmac_tx_timer_arm(struct s + { + struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; + u32 tx_coal_timer = priv->tx_coal_timer[queue]; ++ struct stmmac_channel *ch; ++ struct napi_struct *napi; + + if (!tx_coal_timer) + return; + +- hrtimer_start(&tx_q->txtimer, +- STMMAC_COAL_TIMER(tx_coal_timer), +- HRTIMER_MODE_REL); ++ ch = &priv->channel[tx_q->queue_index]; ++ napi = tx_q->xsk_pool ? &ch->rxtx_napi : &ch->tx_napi; ++ ++ /* Arm timer only if napi is not already scheduled. ++ * Try to cancel any timer if napi is scheduled, timer will be armed ++ * again in the next scheduled napi. ++ */ ++ if (unlikely(!napi_is_scheduled(napi))) ++ hrtimer_start(&tx_q->txtimer, ++ STMMAC_COAL_TIMER(tx_coal_timer), ++ HRTIMER_MODE_REL); ++ else ++ hrtimer_try_to_cancel(&tx_q->txtimer); + } + + /** diff --git a/target/linux/ipq806x/patches-6.1/700-03-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch b/target/linux/ipq806x/patches-6.1/700-03-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch deleted file mode 100644 index f86c16ec81..0000000000 --- a/target/linux/ipq806x/patches-6.1/700-03-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch +++ /dev/null @@ -1,37 +0,0 @@ -From 13e24b0c4318b8b4d0a0fde7e5e7ccb982821c63 Mon Sep 17 00:00:00 2001 -From: Christian Marangi -Date: Mon, 18 Sep 2023 15:11:13 +0200 -Subject: [PATCH 3/3] net: stmmac: increase TX coalesce timer to 5ms - -Commit 8fce33317023 ("net: stmmac: Rework coalesce timer and fix -multi-queue races") decreased the TX coalesce timer from 40ms to 1ms. - -This caused some performance regression on some target (regression was -reported at least on ipq806x) in the order of 600mbps dropping from -gigabit handling to only 200mbps. - -The problem was identified in the TX timer getting armed too much time. -While this was fixed and improved in another commit, performance can be -improved even further by increasing the timer delay a bit moving from -1ms to 5ms. - -The value is a good balance between battery saving by prevending too -much interrupt to be generated and permitting good performance for -internet oriented devices. - -Signed-off-by: Christian Marangi ---- - drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - ---- a/drivers/net/ethernet/stmicro/stmmac/common.h -+++ b/drivers/net/ethernet/stmicro/stmmac/common.h -@@ -286,7 +286,7 @@ struct stmmac_safety_stats { - #define MIN_DMA_RIWT 0x10 - #define DEF_DMA_RIWT 0xa0 - /* Tx coalesce parameters */ --#define STMMAC_COAL_TX_TIMER 1000 -+#define STMMAC_COAL_TX_TIMER 5000 - #define STMMAC_MAX_COAL_TX_TICK 100000 - #define STMMAC_TX_MAX_FRAMES 256 - #define STMMAC_TX_FRAMES 25 diff --git a/target/linux/ipq806x/patches-6.1/700-04-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch b/target/linux/ipq806x/patches-6.1/700-04-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch new file mode 100644 index 0000000000..3f97702097 --- /dev/null +++ b/target/linux/ipq806x/patches-6.1/700-04-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch @@ -0,0 +1,37 @@ +From 95281ab33fbaa1e974bceb20cfb0f5c92934f2b3 Mon Sep 17 00:00:00 2001 +From: Christian Marangi +Date: Mon, 18 Sep 2023 15:11:13 +0200 +Subject: [PATCH 4/4] net: stmmac: increase TX coalesce timer to 5ms + +Commit 8fce33317023 ("net: stmmac: Rework coalesce timer and fix +multi-queue races") decreased the TX coalesce timer from 40ms to 1ms. + +This caused some performance regression on some target (regression was +reported at least on ipq806x) in the order of 600mbps dropping from +gigabit handling to only 200mbps. + +The problem was identified in the TX timer getting armed too much time. +While this was fixed and improved in another commit, performance can be +improved even further by increasing the timer delay a bit moving from +1ms to 5ms. + +The value is a good balance between battery saving by prevending too +much interrupt to be generated and permitting good performance for +internet oriented devices. + +Signed-off-by: Christian Marangi +--- + drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/ethernet/stmicro/stmmac/common.h ++++ b/drivers/net/ethernet/stmicro/stmmac/common.h +@@ -286,7 +286,7 @@ struct stmmac_safety_stats { + #define MIN_DMA_RIWT 0x10 + #define DEF_DMA_RIWT 0xa0 + /* Tx coalesce parameters */ +-#define STMMAC_COAL_TX_TIMER 1000 ++#define STMMAC_COAL_TX_TIMER 5000 + #define STMMAC_MAX_COAL_TX_TICK 100000 + #define STMMAC_TX_MAX_FRAMES 256 + #define STMMAC_TX_FRAMES 25