linux-kernel - [PATCH net] net: renesas: rswitch: handle stop vs interrupt race

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20241209113204.175015-1-nikita.yoush@cogentembedded.com>
Date: Mon,  9 Dec 2024 16:32:04 +0500
From: Nikita Yushchenko <nikita.yoush@...entembedded.com>
To: Yoshihiro Shimoda <yoshihiro.shimoda.uh@...esas.com>,
	Andrew Lunn <andrew@...n.ch>,
	"David S. Miller" <davem@...emloft.net>,
	Eric Dumazet <edumazet@...gle.com>,
	Jakub Kicinski <kuba@...nel.org>,
	Paolo Abeni <pabeni@...hat.com>,
	Geert Uytterhoeven <geert+renesas@...der.be>
Cc: netdev@...r.kernel.org,
	linux-renesas-soc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Michael Dege <michael.dege@...esas.com>,
	Christian Mardmoeller <christian.mardmoeller@...esas.com>,
	Dennis Ostermann <dennis.ostermann@...esas.com>,
	Nikita Yushchenko <nikita.yoush@...entembedded.com>
Subject: [PATCH net] net: renesas: rswitch: handle stop vs interrupt race

Currently the stop routine of rswitch driver does not immediately
prevent hardware from continuing to update descriptors and requesting
interrupts.

It can happen that when rswitch_stop() executes the masking of
interrupts from the queues of the port being closed, napi poll for
that port is already scheduled or running on a different CPU. When
execution of this napi poll completes, it will unmask the interrupts.
And unmasked interrupt can fire after rswitch_stop() returns from
napi_disable() call. Then, the handler won't mask it, because
napi_schedule_prep() will return false, and interrupt storm will
happen.

This can't be fixed by making rswitch_stop() call napi_disable() before
masking interrupts. In this case, the interrupt storm will happen if
interrupt fires between napi_disable() and masking.

Fix this by checking for priv->opened_ports bit when unmasking
interrupts after napi poll. For that to be consistent, move
priv->opened_ports changes into spinlock-protected areas, and reorder
other operations in rswitch_open() and rswitch_stop() accordingly.

Signed-off-by: Nikita Yushchenko <nikita.yoush@...entembedded.com>
---
 drivers/net/ethernet/renesas/rswitch.c | 33 ++++++++++++++------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 6ca5f72193eb..a33f74e1c447 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -918,8 +918,10 @@ static int rswitch_poll(struct napi_struct *napi, int budget)
 
 	if (napi_complete_done(napi, budget - quota)) {
 		spin_lock_irqsave(&priv->lock, flags);
-		rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true);
-		rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true);
+		if (test_bit(rdev->port, priv->opened_ports)) {
+			rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true);
+			rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true);
+		}
 		spin_unlock_irqrestore(&priv->lock, flags);
 	}
 
@@ -1582,20 +1584,20 @@ static int rswitch_open(struct net_device *ndev)
 	struct rswitch_device *rdev = netdev_priv(ndev);
 	unsigned long flags;
 
-	phy_start(ndev->phydev);
+	if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
+		iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE);
 
 	napi_enable(&rdev->napi);
-	netif_start_queue(ndev);
 
 	spin_lock_irqsave(&rdev->priv->lock, flags);
+	bitmap_set(rdev->priv->opened_ports, rdev->port, 1);
 	rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, true);
 	rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, true);
 	spin_unlock_irqrestore(&rdev->priv->lock, flags);
 
-	if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
-		iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE);
+	phy_start(ndev->phydev);
 
-	bitmap_set(rdev->priv->opened_ports, rdev->port, 1);
+	netif_start_queue(ndev);
 
 	return 0;
 };
@@ -1607,7 +1609,16 @@ static int rswitch_stop(struct net_device *ndev)
 	unsigned long flags;
 
 	netif_tx_stop_all_queues(ndev);
+
+	phy_stop(ndev->phydev);
+
+	spin_lock_irqsave(&rdev->priv->lock, flags);
+	rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false);
+	rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false);
 	bitmap_clear(rdev->priv->opened_ports, rdev->port, 1);
+	spin_unlock_irqrestore(&rdev->priv->lock, flags);
+
+	napi_disable(&rdev->napi);
 
 	if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
 		iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID);
@@ -1620,14 +1631,6 @@ static int rswitch_stop(struct net_device *ndev)
 		kfree(ts_info);
 	}
 
-	spin_lock_irqsave(&rdev->priv->lock, flags);
-	rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false);
-	rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false);
-	spin_unlock_irqrestore(&rdev->priv->lock, flags);
-
-	phy_stop(ndev->phydev);
-	napi_disable(&rdev->napi);
-
 	return 0;
 };
 
-- 
2.39.5