linux-stable/drivers/net/phy/mdio_bus.c

653 lines
16 KiB
C
Raw Normal View History

/* MDIO Bus interface
*
* Author: Andy Fleming
*
* Copyright (c) 2004 Freescale Semiconductor, Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/of_device.h>
#include <linux/of_mdio.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
#include <linux/phy.h>
#include <linux/io.h>
#include <linux/uaccess.h>
#include <asm/irq.h>
#define CREATE_TRACE_POINTS
#include <trace/events/mdio.h>
int mdiobus_register_device(struct mdio_device *mdiodev)
{
if (mdiodev->bus->mdio_map[mdiodev->addr])
return -EBUSY;
mdiodev->bus->mdio_map[mdiodev->addr] = mdiodev;
return 0;
}
EXPORT_SYMBOL(mdiobus_register_device);
int mdiobus_unregister_device(struct mdio_device *mdiodev)
{
if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev)
return -EINVAL;
mdiodev->bus->mdio_map[mdiodev->addr] = NULL;
return 0;
}
EXPORT_SYMBOL(mdiobus_unregister_device);
struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr)
{
struct mdio_device *mdiodev = bus->mdio_map[addr];
if (!mdiodev)
return NULL;
if (!(mdiodev->flags & MDIO_DEVICE_FLAG_PHY))
return NULL;
return container_of(mdiodev, struct phy_device, mdio);
}
EXPORT_SYMBOL(mdiobus_get_phy);
bool mdiobus_is_registered_device(struct mii_bus *bus, int addr)
{
return bus->mdio_map[addr];
}
EXPORT_SYMBOL(mdiobus_is_registered_device);
/**
* mdiobus_alloc_size - allocate a mii_bus structure
* @size: extra amount of memory to allocate for private storage.
* If non-zero, then bus->priv is points to that memory.
*
* Description: called by a bus driver to allocate an mii_bus
* structure to fill in.
*/
struct mii_bus *mdiobus_alloc_size(size_t size)
{
struct mii_bus *bus;
size_t aligned_size = ALIGN(sizeof(*bus), NETDEV_ALIGN);
size_t alloc_size;
int i;
/* If we alloc extra space, it should be aligned */
if (size)
alloc_size = aligned_size + size;
else
alloc_size = sizeof(*bus);
bus = kzalloc(alloc_size, GFP_KERNEL);
if (!bus)
return NULL;
bus->state = MDIOBUS_ALLOCATED;
if (size)
bus->priv = (void *)bus + aligned_size;
/* Initialise the interrupts to polling */
for (i = 0; i < PHY_MAX_ADDR; i++)
bus->irq[i] = PHY_POLL;
return bus;
}
EXPORT_SYMBOL(mdiobus_alloc_size);
static void _devm_mdiobus_free(struct device *dev, void *res)
{
mdiobus_free(*(struct mii_bus **)res);
}
static int devm_mdiobus_match(struct device *dev, void *res, void *data)
{
struct mii_bus **r = res;
if (WARN_ON(!r || !*r))
return 0;
return *r == data;
}
/**
* devm_mdiobus_alloc_size - Resource-managed mdiobus_alloc_size()
* @dev: Device to allocate mii_bus for
* @sizeof_priv: Space to allocate for private structure.
*
* Managed mdiobus_alloc_size. mii_bus allocated with this function is
* automatically freed on driver detach.
*
* If an mii_bus allocated with this function needs to be freed separately,
* devm_mdiobus_free() must be used.
*
* RETURNS:
* Pointer to allocated mii_bus on success, NULL on failure.
*/
struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv)
{
struct mii_bus **ptr, *bus;
ptr = devres_alloc(_devm_mdiobus_free, sizeof(*ptr), GFP_KERNEL);
if (!ptr)
return NULL;
/* use raw alloc_dr for kmalloc caller tracing */
bus = mdiobus_alloc_size(sizeof_priv);
if (bus) {
*ptr = bus;
devres_add(dev, ptr);
} else {
devres_free(ptr);
}
return bus;
}
EXPORT_SYMBOL_GPL(devm_mdiobus_alloc_size);
/**
* devm_mdiobus_free - Resource-managed mdiobus_free()
* @dev: Device this mii_bus belongs to
* @bus: the mii_bus associated with the device
*
* Free mii_bus allocated with devm_mdiobus_alloc_size().
*/
void devm_mdiobus_free(struct device *dev, struct mii_bus *bus)
{
int rc;
rc = devres_release(dev, _devm_mdiobus_free,
devm_mdiobus_match, bus);
WARN_ON(rc);
}
EXPORT_SYMBOL_GPL(devm_mdiobus_free);
/**
* mdiobus_release - mii_bus device release callback
* @d: the target struct device that contains the mii_bus
*
* Description: called when the last reference to an mii_bus is
* dropped, to free the underlying memory.
*/
static void mdiobus_release(struct device *d)
{
struct mii_bus *bus = to_mii_bus(d);
BUG_ON(bus->state != MDIOBUS_RELEASED &&
/* for compatibility with error handling in drivers */
bus->state != MDIOBUS_ALLOCATED);
kfree(bus);
}
static struct class mdio_bus_class = {
.name = "mdio_bus",
.dev_release = mdiobus_release,
};
#if IS_ENABLED(CONFIG_OF_MDIO)
/* Helper function for of_mdio_find_bus */
static int of_mdio_bus_match(struct device *dev, const void *mdio_bus_np)
{
return dev->of_node == mdio_bus_np;
}
/**
* of_mdio_find_bus - Given an mii_bus node, find the mii_bus.
* @mdio_bus_np: Pointer to the mii_bus.
*
* Returns a reference to the mii_bus, or NULL if none found. The
* embedded struct device will have its reference count incremented,
* and this must be put once the bus is finished with.
*
* Because the association of a device_node and mii_bus is made via
* of_mdiobus_register(), the mii_bus cannot be found before it is
* registered with of_mdiobus_register().
*
*/
struct mii_bus *of_mdio_find_bus(struct device_node *mdio_bus_np)
{
struct device *d;
if (!mdio_bus_np)
return NULL;
d = class_find_device(&mdio_bus_class, NULL, mdio_bus_np,
of_mdio_bus_match);
return d ? to_mii_bus(d) : NULL;
}
EXPORT_SYMBOL(of_mdio_find_bus);
/* Walk the list of subnodes of a mdio bus and look for a node that
* matches the mdio device's address with its 'reg' property. If
* found, set the of_node pointer for the mdio device. This allows
* auto-probed phy devices to be supplied with information passed in
* via DT.
*/
static void of_mdiobus_link_mdiodev(struct mii_bus *bus,
struct mdio_device *mdiodev)
{
struct device *dev = &mdiodev->dev;
struct device_node *child;
if (dev->of_node || !bus->dev.of_node)
return;
for_each_available_child_of_node(bus->dev.of_node, child) {
int addr;
int ret;
ret = of_property_read_u32(child, "reg", &addr);
if (ret < 0) {
dev_err(dev, "%s has invalid MDIO address\n",
child->full_name);
continue;
}
/* A MDIO device must have a reg property in the range [0-31] */
if (addr >= PHY_MAX_ADDR) {
dev_err(dev, "%s MDIO address %i is too large\n",
child->full_name, addr);
continue;
}
if (addr == mdiodev->addr) {
dev->of_node = child;
return;
}
}
}
#else /* !IS_ENABLED(CONFIG_OF_MDIO) */
static inline void of_mdiobus_link_mdiodev(struct mii_bus *mdio,
struct mdio_device *mdiodev)
{
}
#endif
/**
* __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus
* @bus: target mii_bus
* @owner: module containing bus accessor functions
*
* Description: Called by a bus driver to bring up all the PHYs
* on a given bus, and attach them to the bus. Drivers should use
* mdiobus_register() rather than __mdiobus_register() unless they
* need to pass a specific owner module. MDIO devices which are not
* PHYs will not be brought up by this function. They are expected to
* to be explicitly listed in DT and instantiated by of_mdiobus_register().
*
* Returns 0 on success or < 0 on error.
*/
int __mdiobus_register(struct mii_bus *bus, struct module *owner)
{
struct mdio_device *mdiodev;
int i, err;
if (NULL == bus || NULL == bus->name ||
NULL == bus->read || NULL == bus->write)
return -EINVAL;
BUG_ON(bus->state != MDIOBUS_ALLOCATED &&
bus->state != MDIOBUS_UNREGISTERED);
bus->owner = owner;
bus->dev.parent = bus->parent;
bus->dev.class = &mdio_bus_class;
bus->dev.groups = NULL;
dev_set_name(&bus->dev, "%s", bus->id);
err = device_register(&bus->dev);
if (err) {
pr_err("mii_bus %s failed to register\n", bus->id);
put_device(&bus->dev);
return -EINVAL;
}
mutex_init(&bus->mdio_lock);
if (bus->reset)
bus->reset(bus);
for (i = 0; i < PHY_MAX_ADDR; i++) {
if ((bus->phy_mask & (1 << i)) == 0) {
struct phy_device *phydev;
phydev = mdiobus_scan(bus, i);
mdio_bus: Fix MDIO bus scanning in __mdiobus_register() Since commit b74766a0a0fe ("phylib: don't return NULL from get_phy_device()") in linux-next, phy_get_device() will return ERR_PTR(-ENODEV) instead of NULL if the PHY device ID is all ones. This causes problem with stmmac driver and likely some other drivers which call mdiobus_register(). I triggered this bug on SoCFPGA MCVEVK board with linux-next 20160427 and 20160428. In case of the stmmac, if there is no PHY node specified in the DT for the stmmac block, the stmmac driver ( drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c function stmmac_mdio_register() ) will call mdiobus_register() , which will register the MDIO bus and probe for the PHY. The mdiobus_register() resp. __mdiobus_register() iterates over all of the addresses on the MDIO bus and calls mdiobus_scan() for each of them, which invokes get_phy_device(). Before the aforementioned patch, the mdiobus_scan() would return NULL if no PHY was found on a given address and mdiobus_register() would continue and try the next PHY address. Now, mdiobus_scan() returns ERR_PTR(-ENODEV), which is caught by the 'if (IS_ERR(phydev))' condition and the loop exits immediately if the PHY address does not contain PHY. Repair this by explicitly checking for the ERR_PTR(-ENODEV) and if this error comes around, continue with the next PHY address. Signed-off-by: Marek Vasut <marex@denx.de> Cc: Arnd Bergmann <arnd@arndb.de> Cc: David S. Miller <davem@davemloft.net> Cc: Dinh Nguyen <dinguyen@opensource.altera.com> Cc: Florian Fainelli <f.fainelli@gmail.com> Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Acked-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-02 00:47:31 +00:00
if (IS_ERR(phydev) && (PTR_ERR(phydev) != -ENODEV)) {
err = PTR_ERR(phydev);
goto error;
}
}
}
bus->state = MDIOBUS_REGISTERED;
pr_info("%s: probed\n", bus->name);
return 0;
error:
while (--i >= 0) {
mdiodev = bus->mdio_map[i];
if (!mdiodev)
continue;
mdiodev->device_remove(mdiodev);
mdiodev->device_free(mdiodev);
}
device_del(&bus->dev);
return err;
}
EXPORT_SYMBOL(__mdiobus_register);
void mdiobus_unregister(struct mii_bus *bus)
{
struct mdio_device *mdiodev;
int i;
BUG_ON(bus->state != MDIOBUS_REGISTERED);
bus->state = MDIOBUS_UNREGISTERED;
for (i = 0; i < PHY_MAX_ADDR; i++) {
mdiodev = bus->mdio_map[i];
if (!mdiodev)
continue;
mdiodev->device_remove(mdiodev);
mdiodev->device_free(mdiodev);
}
phylib: fix device deletion order in mdiobus_unregister() commit 8b63ec1837fa ("phylib: Make PHYs children of their MDIO bus, not the bus' parent.") uncovered a problem in mdiobus_unregister() which leads to this warning when I reboot an APM Mustang (arm64) platform: WARNING: CPU: 7 PID: 4239 at fs/sysfs/group.c:224 sysfs_remove_group+0xa0/0xa4() sysfs group fffffe0000e07a10 not found for kobject 'xgene-mii-eth0:03' ... CPU: 7 PID: 4239 Comm: reboot Tainted: G E 4.2.0-0.18.el7.test15.aarch64 #1 Hardware name: AppliedMicro Mustang/Mustang, BIOS 1.1.0 Aug 26 2015 Call Trace: [<fffffe000009739c>] dump_backtrace+0x0/0x170 [<fffffe000009752c>] show_stack+0x20/0x2c [<fffffe00007436f0>] dump_stack+0x78/0x9c [<fffffe00000c2cb4>] warn_slowpath_common+0xa0/0xd8 [<fffffe00000c2d60>] warn_slowpath_fmt+0x74/0x88 [<fffffe0000293d3c>] sysfs_remove_group+0x9c/0xa4 [<fffffe00004a8bac>] dpm_sysfs_remove+0x5c/0x70 [<fffffe000049b388>] device_del+0x44/0x208 [<fffffe000049b578>] device_unregister+0x2c/0x7c [<fffffe000050dc68>] mdiobus_unregister+0x48/0x94 [<fffffe000052afd0>] xgene_enet_mdio_remove+0x28/0x44 [<fffffe000052d3f0>] xgene_enet_remove+0xd0/0xd8 [<fffffe000052d424>] xgene_enet_shutdown+0x2c/0x3c [<fffffe00004a204c>] platform_drv_shutdown+0x24/0x40 [<fffffe000049d4f4>] device_shutdown+0xf0/0x1b4 [<fffffe00000e31ec>] kernel_restart_prepare+0x40/0x4c [<fffffe00000e32f8>] kernel_restart+0x1c/0x80 [<fffffe00000e3670>] SyS_reboot+0x17c/0x250 The problem is that mdiobus_unregister() deletes the bus device before unregistering the phy devices on the bus. This wasn't a problem before because the phys were not children of the bus: /sys/devices/platform/APMC0D05:00/net/eth0/xgene-mii-eth0:03 /sys/devices/platform/APMC0D05:00/net/eth0/xgene-mii-eth0 But now that they are: /sys/devices/platform/APMC0D05:00/net/eth0/xgene-mii-eth0/xgene-mii-eth0:03 when mdiobus_unregister deletes the bus device, the phy subdirs are removed from sysfs also. So when the phys are unregistered afterward, we get the warning. This patch changes the order so that phys are unregistered before the bus device is deleted. Fixes: 8b63ec1837fa ("phylib: Make PHYs children of their MDIO bus, not the bus' parent.") Signed-off-by: Mark Salter <msalter@redhat.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Tested-by: Mark Langsdorf <mlangsdo@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-01 13:36:05 +00:00
device_del(&bus->dev);
}
EXPORT_SYMBOL(mdiobus_unregister);
/**
* mdiobus_free - free a struct mii_bus
* @bus: mii_bus to free
*
* This function releases the reference to the underlying device
* object in the mii_bus. If this is the last reference, the mii_bus
* will be freed.
*/
void mdiobus_free(struct mii_bus *bus)
{
/* For compatibility with error handling in drivers. */
if (bus->state == MDIOBUS_ALLOCATED) {
kfree(bus);
return;
}
BUG_ON(bus->state != MDIOBUS_UNREGISTERED);
bus->state = MDIOBUS_RELEASED;
put_device(&bus->dev);
}
EXPORT_SYMBOL(mdiobus_free);
/**
* mdiobus_scan - scan a bus for MDIO devices.
* @bus: mii_bus to scan
* @addr: address on bus to scan
*
* This function scans the MDIO bus, looking for devices which can be
* identified using a vendor/product ID in registers 2 and 3. Not all
* MDIO devices have such registers, but PHY devices typically
* do. Hence this function assumes anything found is a PHY, or can be
* treated as a PHY. Other MDIO devices, such as switches, will
* probably not be found during the scan.
*/
struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr)
{
struct phy_device *phydev;
int err;
phydev = get_phy_device(bus, addr, false);
if (IS_ERR(phydev))
return phydev;
/*
* For DT, see if the auto-probed phy has a correspoding child
* in the bus node, and set the of_node pointer in this case.
*/
of_mdiobus_link_mdiodev(bus, &phydev->mdio);
err = phy_device_register(phydev);
if (err) {
phy_device_free(phydev);
return ERR_PTR(-ENODEV);
}
return phydev;
}
EXPORT_SYMBOL(mdiobus_scan);
/**
* mdiobus_read_nested - Nested version of the mdiobus_read function
* @bus: the mii_bus struct
* @addr: the phy address
* @regnum: register number to read
*
* In case of nested MDIO bus access avoid lockdep false positives by
* using mutex_lock_nested().
*
* NOTE: MUST NOT be called from interrupt context,
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum)
{
int retval;
BUG_ON(in_interrupt());
mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
retval = bus->read(bus, addr, regnum);
mutex_unlock(&bus->mdio_lock);
trace_mdio_access(bus, 1, addr, regnum, retval, retval);
return retval;
}
EXPORT_SYMBOL(mdiobus_read_nested);
/**
* mdiobus_read - Convenience function for reading a given MII mgmt register
* @bus: the mii_bus struct
* @addr: the phy address
* @regnum: register number to read
*
* NOTE: MUST NOT be called from interrupt context,
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
{
int retval;
BUG_ON(in_interrupt());
mutex_lock(&bus->mdio_lock);
retval = bus->read(bus, addr, regnum);
mutex_unlock(&bus->mdio_lock);
trace_mdio_access(bus, 1, addr, regnum, retval, retval);
return retval;
}
EXPORT_SYMBOL(mdiobus_read);
/**
* mdiobus_write_nested - Nested version of the mdiobus_write function
* @bus: the mii_bus struct
* @addr: the phy address
* @regnum: register number to write
* @val: value to write to @regnum
*
* In case of nested MDIO bus access avoid lockdep false positives by
* using mutex_lock_nested().
*
* NOTE: MUST NOT be called from interrupt context,
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val)
{
int err;
BUG_ON(in_interrupt());
mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
err = bus->write(bus, addr, regnum, val);
mutex_unlock(&bus->mdio_lock);
trace_mdio_access(bus, 0, addr, regnum, val, err);
return err;
}
EXPORT_SYMBOL(mdiobus_write_nested);
/**
* mdiobus_write - Convenience function for writing a given MII mgmt register
* @bus: the mii_bus struct
* @addr: the phy address
* @regnum: register number to write
* @val: value to write to @regnum
*
* NOTE: MUST NOT be called from interrupt context,
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
{
int err;
BUG_ON(in_interrupt());
mutex_lock(&bus->mdio_lock);
err = bus->write(bus, addr, regnum, val);
mutex_unlock(&bus->mdio_lock);
trace_mdio_access(bus, 0, addr, regnum, val, err);
return err;
}
EXPORT_SYMBOL(mdiobus_write);
/**
* mdio_bus_match - determine if given MDIO driver supports the given
* MDIO device
* @dev: target MDIO device
* @drv: given MDIO driver
*
* Description: Given a MDIO device, and a MDIO driver, return 1 if
* the driver supports the device. Otherwise, return 0. This may
* require calling the devices own match function, since different classes
* of MDIO devices have different match criteria.
*/
static int mdio_bus_match(struct device *dev, struct device_driver *drv)
{
struct mdio_device *mdio = to_mdio_device(dev);
if (of_driver_match_device(dev, drv))
return 1;
if (mdio->bus_match)
return mdio->bus_match(dev, drv);
return 0;
}
#ifdef CONFIG_PM
static int mdio_bus_suspend(struct device *dev)
{
struct mdio_device *mdio = to_mdio_device(dev);
if (mdio->pm_ops && mdio->pm_ops->suspend)
return mdio->pm_ops->suspend(dev);
phylib: Fix deadlock on resume Sometimes kernel hangs on resume with the following trace: ucc_geth e0102000.ucc: resume INFO: task bash:1764 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. bash D 0fecf43c 0 1764 1763 0x00000000 Call Trace: [cf9a7c10] [c0012868] ret_from_except+0x0/0x14 (unreliable) --- Exception: cf9a7ce0 at __switch_to+0x4c/0x6c LR = 0xcf9a7cc0 [cf9a7cd0] [c0008c14] __switch_to+0x4c/0x6c (unreliable) [cf9a7ce0] [c028bcfc] schedule+0x158/0x260 [cf9a7d10] [c028c720] __mutex_lock_slowpath+0x80/0xd8 [cf9a7d40] [c01cf388] phy_stop+0x20/0x70 [cf9a7d50] [c01d514c] ugeth_resume+0x6c/0x13c [...] Here is why. On suspend: - PM core starts suspending devices, ucc_geth_suspend gets called; - ucc_geth calls phy_stop() on suspend. Note that phy_stop() is mostly asynchronous so it doesn't block ucc_geth's suspend routine, it just sets PHY_HALTED state and disables PHY's interrupts; - Suddenly the state machine gets scheduled, it grabs the phydev->lock mutex and tries to process the PHY_HALTED state, so it calls phydev->adjust_link(phydev->attached_dev). In ucc_geth case adjust_link() calls msleep(), which reschedules the code flow back to PM core, which now finishes suspend and so we end up sleeping with phydev->lock mutex held. On resume: - PM core starts resuming devices (notice that nobody rescheduled the state machine yet, so the mutex is still held), the core calls ucc_geth's resume routine; - ucc_geth_resume restarts the PHY with phy_stop()/phy_start() sequence, and the phy_*() calls are trying to grab the phydev->lock mutex. Here comes the deadlock. This patch fixes the issue by stopping the state machine on suspend and starting it again on resume. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-30 08:23:28 +00:00
return 0;
}
static int mdio_bus_resume(struct device *dev)
{
struct mdio_device *mdio = to_mdio_device(dev);
phylib: Fix deadlock on resume Sometimes kernel hangs on resume with the following trace: ucc_geth e0102000.ucc: resume INFO: task bash:1764 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. bash D 0fecf43c 0 1764 1763 0x00000000 Call Trace: [cf9a7c10] [c0012868] ret_from_except+0x0/0x14 (unreliable) --- Exception: cf9a7ce0 at __switch_to+0x4c/0x6c LR = 0xcf9a7cc0 [cf9a7cd0] [c0008c14] __switch_to+0x4c/0x6c (unreliable) [cf9a7ce0] [c028bcfc] schedule+0x158/0x260 [cf9a7d10] [c028c720] __mutex_lock_slowpath+0x80/0xd8 [cf9a7d40] [c01cf388] phy_stop+0x20/0x70 [cf9a7d50] [c01d514c] ugeth_resume+0x6c/0x13c [...] Here is why. On suspend: - PM core starts suspending devices, ucc_geth_suspend gets called; - ucc_geth calls phy_stop() on suspend. Note that phy_stop() is mostly asynchronous so it doesn't block ucc_geth's suspend routine, it just sets PHY_HALTED state and disables PHY's interrupts; - Suddenly the state machine gets scheduled, it grabs the phydev->lock mutex and tries to process the PHY_HALTED state, so it calls phydev->adjust_link(phydev->attached_dev). In ucc_geth case adjust_link() calls msleep(), which reschedules the code flow back to PM core, which now finishes suspend and so we end up sleeping with phydev->lock mutex held. On resume: - PM core starts resuming devices (notice that nobody rescheduled the state machine yet, so the mutex is still held), the core calls ucc_geth's resume routine; - ucc_geth_resume restarts the PHY with phy_stop()/phy_start() sequence, and the phy_*() calls are trying to grab the phydev->lock mutex. Here comes the deadlock. This patch fixes the issue by stopping the state machine on suspend and starting it again on resume. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-30 08:23:28 +00:00
if (mdio->pm_ops && mdio->pm_ops->resume)
return mdio->pm_ops->resume(dev);
phylib: Fix deadlock on resume Sometimes kernel hangs on resume with the following trace: ucc_geth e0102000.ucc: resume INFO: task bash:1764 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. bash D 0fecf43c 0 1764 1763 0x00000000 Call Trace: [cf9a7c10] [c0012868] ret_from_except+0x0/0x14 (unreliable) --- Exception: cf9a7ce0 at __switch_to+0x4c/0x6c LR = 0xcf9a7cc0 [cf9a7cd0] [c0008c14] __switch_to+0x4c/0x6c (unreliable) [cf9a7ce0] [c028bcfc] schedule+0x158/0x260 [cf9a7d10] [c028c720] __mutex_lock_slowpath+0x80/0xd8 [cf9a7d40] [c01cf388] phy_stop+0x20/0x70 [cf9a7d50] [c01d514c] ugeth_resume+0x6c/0x13c [...] Here is why. On suspend: - PM core starts suspending devices, ucc_geth_suspend gets called; - ucc_geth calls phy_stop() on suspend. Note that phy_stop() is mostly asynchronous so it doesn't block ucc_geth's suspend routine, it just sets PHY_HALTED state and disables PHY's interrupts; - Suddenly the state machine gets scheduled, it grabs the phydev->lock mutex and tries to process the PHY_HALTED state, so it calls phydev->adjust_link(phydev->attached_dev). In ucc_geth case adjust_link() calls msleep(), which reschedules the code flow back to PM core, which now finishes suspend and so we end up sleeping with phydev->lock mutex held. On resume: - PM core starts resuming devices (notice that nobody rescheduled the state machine yet, so the mutex is still held), the core calls ucc_geth's resume routine; - ucc_geth_resume restarts the PHY with phy_stop()/phy_start() sequence, and the phy_*() calls are trying to grab the phydev->lock mutex. Here comes the deadlock. This patch fixes the issue by stopping the state machine on suspend and starting it again on resume. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-12-30 08:23:28 +00:00
return 0;
}
static int mdio_bus_restore(struct device *dev)
{
struct mdio_device *mdio = to_mdio_device(dev);
if (mdio->pm_ops && mdio->pm_ops->restore)
return mdio->pm_ops->restore(dev);
return 0;
}
static const struct dev_pm_ops mdio_bus_pm_ops = {
.suspend = mdio_bus_suspend,
.resume = mdio_bus_resume,
.freeze = mdio_bus_suspend,
.thaw = mdio_bus_resume,
.restore = mdio_bus_restore,
};
#define MDIO_BUS_PM_OPS (&mdio_bus_pm_ops)
#else
#define MDIO_BUS_PM_OPS NULL
#endif /* CONFIG_PM */
struct bus_type mdio_bus_type = {
.name = "mdio_bus",
.match = mdio_bus_match,
.pm = MDIO_BUS_PM_OPS,
};
EXPORT_SYMBOL(mdio_bus_type);
int __init mdio_bus_init(void)
{
int ret;
ret = class_register(&mdio_bus_class);
if (!ret) {
ret = bus_register(&mdio_bus_type);
if (ret)
class_unregister(&mdio_bus_class);
}
return ret;
}
void mdio_bus_exit(void)
{
class_unregister(&mdio_bus_class);
bus_unregister(&mdio_bus_type);
}