@@ -7350,13 +7350,13 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
err = mv88e6xxx_switch_reset(chip);
mv88e6xxx_reg_unlock(chip);
if (err)
- goto out;
+ goto out_phy;
if (np) {
chip->irq = of_irq_get(np, 0);
if (chip->irq == -EPROBE_DEFER) {
err = chip->irq;
- goto out;
+ goto out_phy;
}
}
@@ -7375,7 +7375,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
mv88e6xxx_reg_unlock(chip);
if (err)
- goto out;
+ goto out_phy;
if (chip->info->g2_irqs > 0) {
err = mv88e6xxx_g2_irq_setup(chip);
@@ -7409,6 +7409,8 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
mv88e6xxx_g1_irq_free(chip);
else
mv88e6xxx_irq_poll_free(chip);
+out_phy:
+ mv88e6xxx_phy_destroy(chip);
out:
if (pdata)
dev_put(pdata->netdev);
@@ -7431,7 +7433,6 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
mv88e6xxx_ptp_free(chip);
}
- mv88e6xxx_phy_destroy(chip);
mv88e6xxx_unregister_switch(chip);
mv88e6xxx_g1_vtu_prob_irq_free(chip);
@@ -7444,6 +7445,8 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
mv88e6xxx_g1_irq_free(chip);
else
mv88e6xxx_irq_poll_free(chip);
+
+ mv88e6xxx_phy_destroy(chip);
}
static void mv88e6xxx_shutdown(struct mdio_device *mdiodev)
@@ -229,7 +229,10 @@ static void mv88e6xxx_phy_ppu_state_init(struct mv88e6xxx_chip *chip)
static void mv88e6xxx_phy_ppu_state_destroy(struct mv88e6xxx_chip *chip)
{
+ mutex_lock(&chip->ppu_mutex);
del_timer_sync(&chip->ppu_timer);
+ cancel_work_sync(&chip->ppu_work);
+ mutex_unlock(&chip->ppu_mutex);
}
int mv88e6185_phy_ppu_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus,
The mv88e6xxx has an internal PPU that polls PHY state. If we want to access the internal PHYs, we need to disable the PPU first. Because that is a slow operation, a 10ms timer is used to re-enable it, canceled with every access, so bulk operations effectively only disable it once and re-enable it some 10ms after the last access. If a PHY is accessed and then the mv88e6xxx module is removed before the 10ms are up, the PPU re-enable ends up accessing a dangling pointer. This especially affects probing during bootup. The MDIO bus and PHY registration may succeed, but registration with the DSA framework may fail later on (e.g. because the CPU port depends on another, very slow device that isn't done probing yet, returning -EPROBE_DEFER). In this case, probe() fails, but the MDIO subsystem may already have accessed the MIDO bus or PHYs, arming the timer. This is fixed as follows: - If probe fails after mv88e6xxx_phy_init(), make sure we also call mv88e6xxx_phy_destroy() before returning - In mv88e6xxx_remove(), make sure we do the teardown in the correct order, calling mv88e6xxx_phy_destroy() after unregistering the switch device. - In mv88e6xxx_phy_destroy(), destroy both the timer and the work item that the timer might schedule, synchronously waiting in case one of the callbacks already fired and destroying the timer first, before waiting for the work item. - Access to the PPU is guarded by a mutex, the worker acquires it with a mutex_trylock(), not proceeding with the expensive shutdown if that fails. We grab the mutex in mv88e6xxx_phy_destroy() to make sure the slow PPU shutdown is already done or won't even enter, when we wait for the work item. Fixes: 2e5f032095ff ("dsa: add support for the Marvell 88E6131 switch chip") Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at> --- FWIW, this is a forward port of a patch I'm using on v6.6. Thanks, David --- drivers/net/dsa/mv88e6xxx/chip.c | 11 +++++++---- drivers/net/dsa/mv88e6xxx/phy.c | 3 +++ 2 files changed, 10 insertions(+), 4 deletions(-)