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 new file mode 100644 index 00000000000..813ec97abce --- /dev/null +++ b/target/linux/ipq806x/patches-6.1/700-01-net-introduce-napi_is_scheduled-helper.patch @@ -0,0 +1,77 @@ +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 + +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 +it and return a bool. Some driver already implement custom function to +check if napi is scheduled. + +Drop these custom function and introduce napi_is_scheduled that simply +check if napi is scheduled atomically. + +Update any driver and code that implement a similar check and instead +use this new helper. + +Signed-off-by: Christian Marangi +--- + drivers/net/ethernet/chelsio/cxgb3/sge.c | 8 -------- + drivers/net/wireless/realtek/rtw89/core.c | 2 +- + include/linux/netdevice.h | 5 +++++ + net/core/dev.c | 2 +- + 4 files changed, 7 insertions(+), 10 deletions(-) + +--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c ++++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c +@@ -2507,14 +2507,6 @@ static int napi_rx_handler(struct napi_s + return work_done; + } + +-/* +- * Returns true if the device is already scheduled for polling. +- */ +-static inline int napi_is_scheduled(struct napi_struct *napi) +-{ +- return test_bit(NAPI_STATE_SCHED, &napi->state); +-} +- + /** + * process_pure_responses - process pure responses from a response queue + * @adap: the adapter +--- a/drivers/net/wireless/realtek/rtw89/core.c ++++ b/drivers/net/wireless/realtek/rtw89/core.c +@@ -1479,7 +1479,7 @@ static void rtw89_core_rx_to_mac80211(st + struct napi_struct *napi = &rtwdev->napi; + + /* In low power mode, napi isn't scheduled. Receive it to netif. */ +- if (unlikely(!test_bit(NAPI_STATE_SCHED, &napi->state))) ++ if (unlikely(!napi_is_scheduled(napi))) + napi = NULL; + + rtw89_core_hw_to_sband_rate(rx_status); +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -468,6 +468,11 @@ static inline bool napi_prefer_busy_poll + return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); + } + ++static inline bool napi_is_scheduled(struct napi_struct *n) ++{ ++ return test_bit(NAPI_STATE_SCHED, &n->state); ++} ++ + bool napi_schedule_prep(struct napi_struct *n); + + /** +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -6562,7 +6562,7 @@ static int __napi_poll(struct napi_struc + * accidentally calling ->poll() when NAPI is not scheduled. + */ + work = 0; +- if (test_bit(NAPI_STATE_SCHED, &n->state)) { ++ if (napi_is_scheduled(n)) { + work = n->poll(n, weight); + trace_napi_poll(n, work, weight); + } 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 new file mode 100644 index 00000000000..0f2f366fa94 --- /dev/null +++ b/target/linux/ipq806x/patches-6.1/700-02-net-stmmac-improve-TX-timer-arm-logic.patch @@ -0,0 +1,76 @@ +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-6.1/700-03-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 new file mode 100644 index 00000000000..f86c16ec81b --- /dev/null +++ b/target/linux/ipq806x/patches-6.1/700-03-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch @@ -0,0 +1,37 @@ +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