@@ -7264,13 +7264,13 @@ 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;
}
}
@@ -7289,7 +7289,7 @@ 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);
@@ -7323,6 +7323,8 @@ 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);
@@ -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 it. Because enable/disable of the PPU 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 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_phy_destroy(), grab the ppu_mutex to make sure the work function either has already exited, or (should it run) cannot do anything, mutex_trylock() in the worker function fails to grab the mutex and returns. - In addition to destroying the timer, also destroy the work item, in case the timer has already fired. - Do all of this synchronously, to make sure timer & work item are destroyed and none of the callbacks are running. - Because of the nesting of the timer & work item, cancel_work_sync() alone is not sufficient and the order of the cancellation steps matters. 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 | 8 +++++--- drivers/net/dsa/mv88e6xxx/phy.c | 3 +++ 2 files changed, 8 insertions(+), 3 deletions(-)