[PATCH 6.18.y] net: dsa: mt7530: fix .get_stats64 sleeping in atomic context

[PATCH 6.18.y] net: dsa: mt7530: fix .get_stats64 sleeping in atomic context

[Aleksei Sviridkin]

From: Daniel Golle <daniel@makrotopia.org>

commit 07d99587396024932e02474c3a5bede71d108454 upstream.

The .get_stats64 callback runs in atomic context, but on
MDIO-connected switches every register read acquires the MDIO bus
mutex, which can sleep:
[   12.645973] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:609
[   12.654442] in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 759, name: grep
[   12.663377] preempt_count: 0, expected: 0
[   12.667410] RCU nest depth: 1, expected: 0
[   12.671511] INFO: lockdep is turned off.
[   12.675441] CPU: 0 UID: 0 PID: 759 Comm: grep Tainted: G S      W           7.0.0+ #0 PREEMPT
[   12.675453] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN
[   12.675456] Hardware name: Bananapi BPI-R64 (DT)
[   12.675459] Call trace:
[   12.675462]  show_stack+0x14/0x1c (C)
[   12.675477]  dump_stack_lvl+0x68/0x8c
[   12.675487]  dump_stack+0x14/0x1c
[   12.675495]  __might_resched+0x14c/0x220
[   12.675504]  __might_sleep+0x44/0x80
[   12.675511]  __mutex_lock+0x50/0xb10
[   12.675523]  mutex_lock_nested+0x20/0x30
[   12.675532]  mt7530_get_stats64+0x40/0x2ac
[   12.675542]  dsa_user_get_stats64+0x2c/0x40
[   12.675553]  dev_get_stats+0x44/0x1e0
[   12.675564]  dev_seq_printf_stats+0x24/0xe0
[   12.675575]  dev_seq_show+0x14/0x3c
[   12.675583]  seq_read_iter+0x37c/0x480
[   12.675595]  seq_read+0xd0/0xec
[   12.675605]  proc_reg_read+0x94/0xe4
[   12.675615]  vfs_read+0x98/0x29c
[   12.675625]  ksys_read+0x54/0xdc
[   12.675633]  __arm64_sys_read+0x18/0x20
[   12.675642]  invoke_syscall.constprop.0+0x54/0xec
[   12.675653]  do_el0_svc+0x3c/0xb4
[   12.675662]  el0_svc+0x38/0x200
[   12.675670]  el0t_64_sync_handler+0x98/0xdc
[   12.675679]  el0t_64_sync+0x158/0x15c

For MDIO-connected switches, poll MIB counters asynchronously using a
delayed workqueue every second and let .get_stats64 return the cached
values under a spinlock. A mod_delayed_work() call on each read
triggers an immediate refresh so counters stay responsive when queried
more frequently.

MMIO-connected switches (MT7988, EN7581, AN7583) are not affected
because their regmap does not sleep, so they continue to read MIB
counters directly in .get_stats64.

Fixes: 88c810f35ed5 ("net: dsa: mt7530: implement .get_stats64")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Acked-by: Chester A. Unal <chester.a.unal@arinc9.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/6940b913da2c29156f0feff74b678d3c526ee84c.1777719253.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[ Aleksei: context adjusted, 6.18 still exports mt7530_switch_ops ]
Signed-off-by: Aleksei Sviridkin <f@lex.la>
---
Context adjusted: 6.18 still exports mt7530_switch_ops. The +/- lines
are the same as upstream. Tested on an MT7981 board with an MT7531 on
MDIO: without it a /proc/net/dev read loop under
CONFIG_DEBUG_ATOMIC_SLEEP=y locked up a CPU within a minute, with it
the loop ran 41 minutes clean.

 drivers/net/dsa/mt7530.c | 75 ++++++++++++++++++++++++++++++++++++++--
 drivers/net/dsa/mt7530.h |  8 +++++
 2 files changed, 80 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 4001779a9159..bd0a37ead0de 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -25,6 +25,9 @@
 
 #include "mt7530.h"
 
+#define MT7530_STATS_POLL_INTERVAL	(1 * HZ)
+#define MT7530_STATS_RATE_LIMIT		(HZ / 10)
+
 static struct mt753x_pcs *pcs_to_mt753x_pcs(struct phylink_pcs *pcs)
 {
 	return container_of(pcs, struct mt753x_pcs, pcs);
@@ -888,10 +891,9 @@ static void mt7530_get_rmon_stats(struct dsa_switch *ds, int port,
 	*ranges = mt7530_rmon_ranges;
 }
 
-static void mt7530_get_stats64(struct dsa_switch *ds, int port,
-			       struct rtnl_link_stats64 *storage)
+static void mt7530_read_port_stats64(struct mt7530_priv *priv, int port,
+				     struct rtnl_link_stats64 *storage)
 {
-	struct mt7530_priv *priv = ds->priv;
 	uint64_t data;
 
 	/* MIB counter doesn't provide a FramesTransmittedOK but instead
@@ -933,6 +935,54 @@ static void mt7530_get_stats64(struct dsa_switch *ds, int port,
 			       &storage->rx_crc_errors);
 }
 
+static void mt7530_stats_refresh(struct mt7530_priv *priv)
+{
+	struct rtnl_link_stats64 stats = {};
+	struct dsa_port *dp;
+	int port;
+
+	dsa_switch_for_each_user_port(dp, priv->ds) {
+		port = dp->index;
+
+		mt7530_read_port_stats64(priv, port, &stats);
+
+		spin_lock_bh(&priv->stats_lock);
+		priv->ports[port].stats = stats;
+		priv->stats_last = jiffies;
+		spin_unlock_bh(&priv->stats_lock);
+	}
+}
+
+static void mt7530_stats_poll(struct work_struct *work)
+{
+	struct mt7530_priv *priv = container_of(work, struct mt7530_priv,
+						stats_work.work);
+
+	mt7530_stats_refresh(priv);
+	schedule_delayed_work(&priv->stats_work,
+			      MT7530_STATS_POLL_INTERVAL);
+}
+
+static void mt7530_get_stats64(struct dsa_switch *ds, int port,
+			       struct rtnl_link_stats64 *storage)
+{
+	struct mt7530_priv *priv = ds->priv;
+	bool refresh;
+
+	if (priv->bus) {
+		spin_lock_bh(&priv->stats_lock);
+		*storage = priv->ports[port].stats;
+		refresh = time_after(jiffies, priv->stats_last +
+					      MT7530_STATS_RATE_LIMIT);
+		spin_unlock_bh(&priv->stats_lock);
+		if (refresh)
+			mod_delayed_work(system_percpu_wq,
+					 &priv->stats_work, 0);
+	} else {
+		mt7530_read_port_stats64(priv, port, storage);
+	}
+}
+
 static void mt7530_get_eth_ctrl_stats(struct dsa_switch *ds, int port,
 				      struct ethtool_eth_ctrl_stats *ctrl_stats)
 {
@@ -3169,9 +3219,24 @@ mt753x_setup(struct dsa_switch *ds)
 	if (ret && priv->irq_domain)
 		mt7530_free_mdio_irq(priv);
 
+	if (!ret && priv->bus) {
+		mt7530_stats_refresh(priv);
+		schedule_delayed_work(&priv->stats_work,
+				      MT7530_STATS_POLL_INTERVAL);
+	}
+
 	return ret;
 }
 
+static void
+mt753x_teardown(struct dsa_switch *ds)
+{
+	struct mt7530_priv *priv = ds->priv;
+
+	if (priv->bus)
+		cancel_delayed_work_sync(&priv->stats_work);
+}
+
 static int mt753x_set_mac_eee(struct dsa_switch *ds, int port,
 			      struct ethtool_keee *e)
 {
@@ -3290,6 +3355,7 @@ static int mt7988_setup(struct dsa_switch *ds)
 const struct dsa_switch_ops mt7530_switch_ops = {
 	.get_tag_protocol	= mtk_get_tag_protocol,
 	.setup			= mt753x_setup,
+	.teardown		= mt753x_teardown,
 	.preferred_default_local_cpu_port = mt753x_preferred_default_local_cpu_port,
 	.get_strings		= mt7530_get_strings,
 	.get_ethtool_stats	= mt7530_get_ethtool_stats,
@@ -3437,6 +3503,9 @@ mt7530_probe_common(struct mt7530_priv *priv)
 	priv->ds->ops = &mt7530_switch_ops;
 	priv->ds->phylink_mac_ops = &mt753x_phylink_mac_ops;
 	mutex_init(&priv->reg_mutex);
+	spin_lock_init(&priv->stats_lock);
+	INIT_DELAYED_WORK(&priv->stats_work, mt7530_stats_poll);
+
 	dev_set_drvdata(dev, priv);
 
 	return 0;
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 69be713bab80..ca665f87f1f6 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -797,6 +797,7 @@ struct mt7530_fdb {
  * @pvid:	The VLAN specified is to be considered a PVID at ingress.  Any
  *		untagged frames will be assigned to the related VLAN.
  * @sgmii_pcs:	Pointer to PCS instance for SerDes ports
+ * @stats:	Cached port statistics for MDIO-connected switches
  */
 struct mt7530_port {
 	bool enable;
@@ -804,6 +805,7 @@ struct mt7530_port {
 	u32 pm;
 	u16 pvid;
 	struct phylink_pcs *sgmii_pcs;
+	struct rtnl_link_stats64 stats;
 };
 
 /* Port 5 mode definitions of the MT7530 switch */
@@ -876,6 +878,9 @@ struct mt753x_info {
  * @create_sgmii:	Pointer to function creating SGMII PCS instance(s)
  * @active_cpu_ports:	Holding the active CPU ports
  * @mdiodev:		The pointer to the MDIO device structure
+ * @stats_lock:		Protects cached per-port stats from concurrent access
+ * @stats_work:		Delayed work for polling MIB counters on MDIO switches
+ * @stats_last:		Jiffies timestamp of last MIB counter poll
  */
 struct mt7530_priv {
 	struct device		*dev;
@@ -901,6 +906,9 @@ struct mt7530_priv {
 	int (*create_sgmii)(struct mt7530_priv *priv);
 	u8 active_cpu_ports;
 	struct mdio_device *mdiodev;
+	spinlock_t stats_lock; /* protects cached stats counters */
+	struct delayed_work stats_work;
+	unsigned long stats_last;
 };
 
 struct mt7530_hw_vlan_entry {
-- 
2.53.0

Re: [PATCH 6.18.y] net: dsa: mt7530: fix .get_stats64 sleeping in atomic context

[Sasha Levin]

> The .get_stats64 callback runs in atomic context, but on
> MDIO-connected switches every register read acquires the MDIO bus
> mutex, which can sleep:

Queued for 6.18, thanks.

-- 
Thanks,
Sasha