fish/immortalwrt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge Official Source

Browse Source 
Signed-off-by: Tianling Shen <cnsztl@immortalwrt.org>
This commit is contained in:
Tianling Shen 2023-10-01 10:19:08 +08:00
commit 29eb193847
No known key found for this signature in database
GPG Key ID: 6850B6345C862176
5 changed files with 279 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
target/linux/ipq806x/config-6.1
View File

@ -493,8 +493,6 @@ CONFIG_SPMI_MSM_PMIC_ARB=y
CONFIG_SRCU=y
CONFIG_STMMAC_ETH=y
CONFIG_STMMAC_PLATFORM=y
CONFIG_SWCONFIG=y
CONFIG_SWCONFIG_LEDS=y
CONFIG_SWPHY=y
CONFIG_SWP_EMULATE=y
CONFIG_SYS_SUPPORTS_APM_EMULATION=y

77
target/linux/ipq806x/patches-6.1/700-01-net-introduce-napi_is_scheduled-helper.patch Normal file
View File

@ -0,0 +1,77 @@
From b5532bdc6d09e6e789417f0c7a0b665b57b0e7be Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Mon, 18 Sep 2023 14:21:56 +0200
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
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 <ansuelsmth@gmail.com>
---
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);
}

89
target/linux/ipq806x/patches-6.1/700-02-net-stmmac-move-TX-timer-arm-after-DMA-enable.patch Normal file
View File

@ -0,0 +1,89 @@
From fb04db35447d1e8ff557c8e57139164cecab7de5 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
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 <ansuelsmth@gmail.com>
---
.../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);
}

76
target/linux/ipq806x/patches-6.1/700-03-net-stmmac-improve-TX-timer-arm-logic.patch Normal file
View File

@ -0,0 +1,76 @@
From cd40cd8b1ca4a6f531c6c3fd78b306e5014f9c04 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
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 <ansuelsmth@gmail.com>
---
.../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);
}
/**

37
target/linux/ipq806x/patches-6.1/700-04-net-stmmac-increase-TX-coalesce-timer-to-5ms.patch Normal file
View File

@ -0,0 +1,37 @@
From 95281ab33fbaa1e974bceb20cfb0f5c92934f2b3 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
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 <ansuelsmth@gmail.com>
---
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