From a51805efae5dda0da66f79268ffcf0715f9dbea4 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 8 Jul 2013 14:23:49 -0700 Subject: lockdep: Introduce lock_acquire_exclusive()/shared() helper macros In lockdep.h, the spinlock/mutex/rwsem/rwlock/lock_map acquire macros have different definitions based on the value of CONFIG_PROVE_LOCKING. We have separate ifdefs for each of these definitions, which seems redundant. Introduce lock_acquire_{exclusive,shared,shared_recursive} helpers which will have different definitions based on CONFIG_PROVE_LOCKING. Then all other helper macros can be defined based on the above ones, which reduces the amount of ifdefined code. Signed-off-by: Michel Lespinasse Signed-off-by: Andrew Morton Signed-off-by: Peter Zijlstra Cc: Oleg Nesterov Cc: Lai Jiangshan Cc: "Srivatsa S. Bhat" Cc: Rusty Russell Cc: Andi Kleen Cc: "Paul E. McKenney" Cc: Steven Rostedt Link: http://lkml.kernel.org/r/20130708212350.6DD1931C15E@corp2gmr1-1.hot.corp.google.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 92 +++++++++++++------------------------------------ 1 file changed, 23 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index f1e877b79ed8..cfc2f119779a 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -365,7 +365,7 @@ extern void lockdep_trace_alloc(gfp_t mask); #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) -#else /* !LOCKDEP */ +#else /* !CONFIG_LOCKDEP */ static inline void lockdep_off(void) { @@ -479,82 +479,36 @@ static inline void print_irqtrace_events(struct task_struct *curr) * on the per lock-class debug mode: */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# else -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# endif -# define spin_release(l, n, i) lock_release(l, n, i) +#ifdef CONFIG_PROVE_LOCKING + #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) + #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 2, n, i) + #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 2, n, i) #else -# define spin_acquire(l, s, t, i) do { } while (0) -# define spin_release(l, n, i) do { } while (0) + #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) + #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) + #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) #endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 2, NULL, i) -# else -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 1, NULL, i) -# endif -# define rwlock_release(l, n, i) lock_release(l, n, i) -#else -# define rwlock_acquire(l, s, t, i) do { } while (0) -# define rwlock_acquire_read(l, s, t, i) do { } while (0) -# define rwlock_release(l, n, i) do { } while (0) -#endif +#define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define spin_release(l, n, i) lock_release(l, n, i) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define mutex_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# else -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define mutex_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) -# endif -# define mutex_release(l, n, i) lock_release(l, n, i) -#else -# define mutex_acquire(l, s, t, i) do { } while (0) -# define mutex_acquire_nest(l, s, t, n, i) do { } while (0) -# define mutex_release(l, n, i) do { } while (0) -#endif +#define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define rwlock_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) +#define rwlock_release(l, n, i) lock_release(l, n, i) -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) -# define rwsem_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 2, NULL, i) -# else -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) -# define rwsem_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 1, NULL, i) -# endif +#define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define mutex_release(l, n, i) lock_release(l, n, i) + +#define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) +#define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) +#define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) # define rwsem_release(l, n, i) lock_release(l, n, i) -#else -# define rwsem_acquire(l, s, t, i) do { } while (0) -# define rwsem_acquire_nest(l, s, t, n, i) do { } while (0) -# define rwsem_acquire_read(l, s, t, i) do { } while (0) -# define rwsem_release(l, n, i) do { } while (0) -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# ifdef CONFIG_PROVE_LOCKING -# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_) -# define lock_map_acquire_read(l) lock_acquire(l, 0, 0, 2, 2, NULL, _THIS_IP_) -# else -# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_) -# define lock_map_acquire_read(l) lock_acquire(l, 0, 0, 2, 1, NULL, _THIS_IP_) -# endif +#define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) # define lock_map_release(l) lock_release(l, 1, _THIS_IP_) -#else -# define lock_map_acquire(l) do { } while (0) -# define lock_map_acquire_read(l) do { } while (0) -# define lock_map_release(l) do { } while (0) -#endif #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ -- cgit v1.2.3-71-gd317 From 728ce22b696f9f1404a74d7b2279a65933553a1b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 12 Jun 2013 15:08:51 +0200 Subject: cpuidle: Make cpuidle's sysfs directory dynamically allocated The cpuidle sysfs code is designed to have a single instance of per CPU cpuidle directory. It is not possible to remove the sysfs entry and create it again. This is not a problem with the current code but future changes will add CPU hotplug support to enable/disable the device, so it will need to remove the sysfs entry like other subsystems do. That won't be possible without this change, because the kobj is a static object which can't be reused for kobj_init_and_add(). Add cpuidle_device_kobj to be allocated dynamically when adding/removing a sysfs entry which is consistent with the other cpuidle's sysfs entries. An added benefit is that the sysfs code is now more self-contained and the includes needed for sysfs can be moved from cpuidle.h directly into sysfs.c so as to reduce the total number of headers dragged along with cpuidle.h. [rjw: Changelog] Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/sysfs.c | 63 +++++++++++++++++++++++++++++++++++++------------ include/linux/cpuidle.h | 7 +++--- 2 files changed, 51 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 7d4448a9fbbd..8739cc05228c 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -11,8 +11,10 @@ #include #include #include +#include #include #include +#include #include "cpuidle.h" @@ -167,14 +169,27 @@ struct cpuidle_attr { #define define_one_rw(_name, show, store) \ static struct cpuidle_attr attr_##_name = __ATTR(_name, 0644, show, store) -#define kobj_to_cpuidledev(k) container_of(k, struct cpuidle_device, kobj) #define attr_to_cpuidleattr(a) container_of(a, struct cpuidle_attr, attr) +struct cpuidle_device_kobj { + struct cpuidle_device *dev; + struct completion kobj_unregister; + struct kobject kobj; +}; + +static inline struct cpuidle_device *to_cpuidle_device(struct kobject *kobj) +{ + struct cpuidle_device_kobj *kdev = + container_of(kobj, struct cpuidle_device_kobj, kobj); + + return kdev->dev; +} + static ssize_t cpuidle_show(struct kobject *kobj, struct attribute *attr, char *buf) { int ret = -EIO; - struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_device *dev = to_cpuidle_device(kobj); struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr); if (cattr->show) { @@ -189,7 +204,7 @@ static ssize_t cpuidle_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { int ret = -EIO; - struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_device *dev = to_cpuidle_device(kobj); struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr); if (cattr->store) { @@ -207,9 +222,10 @@ static const struct sysfs_ops cpuidle_sysfs_ops = { static void cpuidle_sysfs_release(struct kobject *kobj) { - struct cpuidle_device *dev = kobj_to_cpuidledev(kobj); + struct cpuidle_device_kobj *kdev = + container_of(kobj, struct cpuidle_device_kobj, kobj); - complete(&dev->kobj_unregister); + complete(&kdev->kobj_unregister); } static struct kobj_type ktype_cpuidle = { @@ -377,6 +393,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) { int i, ret = -ENOMEM; struct cpuidle_state_kobj *kobj; + struct cpuidle_device_kobj *kdev = device->kobj_dev; struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); /* state statistics */ @@ -389,7 +406,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) init_completion(&kobj->kobj_unregister); ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle, - &device->kobj, "state%d", i); + &kdev->kobj, "state%d", i); if (ret) { kfree(kobj); goto error_state; @@ -506,6 +523,7 @@ static struct kobj_type ktype_driver_cpuidle = { static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev) { struct cpuidle_driver_kobj *kdrv; + struct cpuidle_device_kobj *kdev = dev->kobj_dev; struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int ret; @@ -517,7 +535,7 @@ static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev) init_completion(&kdrv->kobj_unregister); ret = kobject_init_and_add(&kdrv->kobj, &ktype_driver_cpuidle, - &dev->kobj, "driver"); + &kdev->kobj, "driver"); if (ret) { kfree(kdrv); return ret; @@ -586,16 +604,28 @@ void cpuidle_remove_device_sysfs(struct cpuidle_device *device) */ int cpuidle_add_sysfs(struct cpuidle_device *dev) { + struct cpuidle_device_kobj *kdev; struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu); int error; - init_completion(&dev->kobj_unregister); + kdev = kzalloc(sizeof(*kdev), GFP_KERNEL); + if (!kdev) + return -ENOMEM; + kdev->dev = dev; + dev->kobj_dev = kdev; + + init_completion(&kdev->kobj_unregister); + + error = kobject_init_and_add(&kdev->kobj, &ktype_cpuidle, &cpu_dev->kobj, + "cpuidle"); + if (error) { + kfree(kdev); + return error; + } - error = kobject_init_and_add(&dev->kobj, &ktype_cpuidle, &cpu_dev->kobj, - "cpuidle"); - if (!error) - kobject_uevent(&dev->kobj, KOBJ_ADD); - return error; + kobject_uevent(&kdev->kobj, KOBJ_ADD); + + return 0; } /** @@ -604,6 +634,9 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev) */ void cpuidle_remove_sysfs(struct cpuidle_device *dev) { - kobject_put(&dev->kobj); - wait_for_completion(&dev->kobj_unregister); + struct cpuidle_device_kobj *kdev = dev->kobj_dev; + + kobject_put(&kdev->kobj); + wait_for_completion(&kdev->kobj_unregister); + kfree(kdev); } diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 0bc4b74668e9..b922db53b7ab 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -13,8 +13,6 @@ #include #include -#include -#include #include #define CPUIDLE_STATE_MAX 10 @@ -61,6 +59,8 @@ struct cpuidle_state { #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) +struct cpuidle_device_kobj; + struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; @@ -71,9 +71,8 @@ struct cpuidle_device { struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; + struct cpuidle_device_kobj *kobj_dev; struct list_head device_list; - struct kobject kobj; - struct completion kobj_unregister; #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED int safe_state_index; -- cgit v1.2.3-71-gd317 From 1a7064380e6639e1cc5ed609ceb1ed46f3f188e3 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 12 Jun 2013 15:08:52 +0200 Subject: cpuidle: Add missing forward declarations of structures Add missing forward declarations of struct cpuidle_state_kobj and struct cpuidle_driver_kobj in cpuidle.h. [rjw: Changelog] Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b922db53b7ab..781addc66f03 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -60,6 +60,8 @@ struct cpuidle_state { #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) struct cpuidle_device_kobj; +struct cpuidle_state_kobj; +struct cpuidle_driver_kobj; struct cpuidle_device { unsigned int registered:1; -- cgit v1.2.3-71-gd317 From dc9ceed6a12aff627c81e01ada191e8a23fcbe3e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 4 Jul 2013 17:27:14 +0100 Subject: regulator: core: Make set_voltage_tol() try for mid-range first The expected semantic for something expressed as a tolerance is that it should deliver the specified value with some deviation allowed but this is not what set_voltage_tol() currently does. Instead it just passes the maximum possible range to set_voltage() which will typically result in a voltage aimed at lower than the target voltage. Instead first try to set a voltage between the target voltage and the upper limit, then fall back on the full range. This will be much more robust against physical variation in systems and makes the API behave more like users would expect. Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 3a76389c6aaa..3610df8dd229 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -369,8 +369,11 @@ static inline int regulator_count_voltages(struct regulator *regulator) static inline int regulator_set_voltage_tol(struct regulator *regulator, int new_uV, int tol_uV) { - return regulator_set_voltage(regulator, - new_uV - tol_uV, new_uV + tol_uV); + if (regulator_set_voltage(regulator, new_uV, new_uV + tol_uV) == 0) + return 0; + else + return regulator_set_voltage(regulator, + new_uV - tol_uV, new_uV + tol_uV); } static inline int regulator_is_supported_voltage_tol(struct regulator *regulator, -- cgit v1.2.3-71-gd317 From 94d33c02c7186b69849c292e1216a08ad1c0d99d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 2 Jul 2013 22:52:41 +0100 Subject: regulator: core: Add helpers for multiple linear ranges Many regulators have several linear ranges of selector with different step sizes, for example offering better resolution at lower voltages. Provide regulator_{map,list}_voltage_linear_range() allowing these regulators to use generic code. To do so a table of regulator_linear_range structs needs to be pointed to from the descriptor. This was inspired by similar code included in a driver submission from Chao Xie and Yi Zhang at Marvell. Signed-off-by: Mark Brown --- drivers/regulator/core.c | 87 ++++++++++++++++++++++++++++++++++++++++ include/linux/regulator/driver.h | 25 ++++++++++++ 2 files changed, 112 insertions(+) (limited to 'include/linux') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 288c75abc190..e8604be4c66d 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -2078,6 +2078,43 @@ int regulator_list_voltage_linear(struct regulator_dev *rdev, } EXPORT_SYMBOL_GPL(regulator_list_voltage_linear); +/** + * regulator_list_voltage_linear_range - List voltages for linear ranges + * + * @rdev: Regulator device + * @selector: Selector to convert into a voltage + * + * Regulators with a series of simple linear mappings between voltages + * and selectors can set linear_ranges in the regulator descriptor and + * then use this function as their list_voltage() operation, + */ +int regulator_list_voltage_linear_range(struct regulator_dev *rdev, + unsigned int selector) +{ + const struct regulator_linear_range *range; + int i; + + if (!rdev->desc->n_linear_ranges) { + BUG_ON(!rdev->desc->n_linear_ranges); + return -EINVAL; + } + + for (i = 0; i < rdev->desc->n_linear_ranges; i++) { + range = &rdev->desc->linear_ranges[i]; + + if (!(selector >= range->min_sel && + selector <= range->max_sel)) + continue; + + selector -= range->min_sel; + + return range->min_uV + (range->uV_step * selector); + } + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(regulator_list_voltage_linear_range); + /** * regulator_list_voltage_table - List voltages with table based mapping * @@ -2368,6 +2405,56 @@ int regulator_map_voltage_linear(struct regulator_dev *rdev, } EXPORT_SYMBOL_GPL(regulator_map_voltage_linear); +/** + * regulator_map_voltage_linear - map_voltage() for multiple linear ranges + * + * @rdev: Regulator to operate on + * @min_uV: Lower bound for voltage + * @max_uV: Upper bound for voltage + * + * Drivers providing linear_ranges in their descriptor can use this as + * their map_voltage() callback. + */ +int regulator_map_voltage_linear_range(struct regulator_dev *rdev, + int min_uV, int max_uV) +{ + const struct regulator_linear_range *range; + int ret = -EINVAL; + int voltage, i; + + if (!rdev->desc->n_linear_ranges) { + BUG_ON(!rdev->desc->n_linear_ranges); + return -EINVAL; + } + + for (i = 0; i < rdev->desc->n_linear_ranges; i++) { + range = &rdev->desc->linear_ranges[i]; + + if (!(min_uV <= range->max_uV && max_uV >= range->min_uV)) + continue; + + if (min_uV <= range->min_uV) + min_uV = range->min_uV; + + ret = DIV_ROUND_UP(min_uV - range->min_uV, range->uV_step); + if (ret < 0) + return ret; + + break; + } + + if (i == rdev->desc->n_linear_ranges) + return -EINVAL; + + /* Map back into a voltage to verify we're still in bounds */ + voltage = rdev->desc->ops->list_voltage(rdev, ret); + if (voltage < min_uV || voltage > max_uV) + return -EINVAL; + + return ret; +} +EXPORT_SYMBOL_GPL(regulator_map_voltage_linear_range); + static int _regulator_do_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV) { diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 6700cc94bdd1..67e13aa5a478 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -39,6 +39,24 @@ enum regulator_status { REGULATOR_STATUS_UNDEFINED, }; +/** + * Specify a range of voltages for regulator_map_linar_range() and + * regulator_list_linear_range(). + * + * @min_uV: Lowest voltage in range + * @max_uV: Highest voltage in range + * @min_sel: Lowest selector for range + * @max_sel: Highest selector for range + * @uV_step: Step size + */ +struct regulator_linear_range { + unsigned int min_uV; + unsigned int max_uV; + unsigned int min_sel; + unsigned int max_sel; + unsigned int uV_step; +}; + /** * struct regulator_ops - regulator operations. * @@ -223,6 +241,9 @@ struct regulator_desc { unsigned int linear_min_sel; unsigned int ramp_delay; + const struct regulator_linear_range *linear_ranges; + int n_linear_ranges; + const unsigned int *volt_table; unsigned int vsel_reg; @@ -326,10 +347,14 @@ int regulator_mode_to_status(unsigned int); int regulator_list_voltage_linear(struct regulator_dev *rdev, unsigned int selector); +int regulator_list_voltage_linear_range(struct regulator_dev *rdev, + unsigned int selector); int regulator_list_voltage_table(struct regulator_dev *rdev, unsigned int selector); int regulator_map_voltage_linear(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_map_voltage_linear_range(struct regulator_dev *rdev, + int min_uV, int max_uV); int regulator_map_voltage_iterate(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_ascend(struct regulator_dev *rdev, -- cgit v1.2.3-71-gd317 From 1653ccf4c52df6a4abe8ec2f33f2cb2896d129ea Mon Sep 17 00:00:00 2001 From: Yadwinder Singh Brar Date: Sat, 29 Jun 2013 18:21:15 +0530 Subject: regulator: core: Add support for disabling ramp delay Some hardwares support disabling ramp delay, so adding ramp_disable flag to constraints. It will be used to figure out whether ramp_delay in constraints is explicitly set to zero or its unintialized (zero by default). And we don't need to call set_voltage_time_sel() for regulators for whom ramp delay is disabled in constraints. Signed-off-by: Yadwinder Singh Brar Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/regulator/regulator.txt | 2 ++ drivers/regulator/core.c | 6 ++++-- drivers/regulator/of_regulator.c | 12 +++++++++--- include/linux/regulator/machine.h | 1 + 4 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt index 48a3b8e5d6bd..2bd8f0978765 100644 --- a/Documentation/devicetree/bindings/regulator/regulator.txt +++ b/Documentation/devicetree/bindings/regulator/regulator.txt @@ -12,6 +12,8 @@ Optional properties: - regulator-allow-bypass: allow the regulator to go into bypass mode - -supply: phandle to the parent supply/regulator node - regulator-ramp-delay: ramp delay for regulator(in uV/uS) + For hardwares which support disabling ramp rate, it should be explicitly + intialised to zero (regulator-ramp-delay = <0>) for disabling ramp delay. Deprecated properties: - regulator-compatible: If a regulator chip contains multiple diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 288c75abc190..6e6371c2346c 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -984,7 +984,8 @@ static int set_machine_constraints(struct regulator_dev *rdev, } } - if (rdev->constraints->ramp_delay && ops->set_ramp_delay) { + if ((rdev->constraints->ramp_delay || rdev->constraints->ramp_disable) + && ops->set_ramp_delay) { ret = ops->set_ramp_delay(rdev, rdev->constraints->ramp_delay); if (ret < 0) { rdev_err(rdev, "failed to set ramp_delay\n"); @@ -2438,7 +2439,8 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, } /* Call set_voltage_time_sel if successfully obtained old_selector */ - if (ret == 0 && _regulator_is_enabled(rdev) && old_selector >= 0 && + if (ret == 0 && !rdev->constraints->ramp_disable && + _regulator_is_enabled(rdev) && old_selector >= 0 && old_selector != selector && rdev->desc->ops->set_voltage_time_sel) { delay = rdev->desc->ops->set_voltage_time_sel(rdev, diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index f3c8f8f9dc39..7827384680d6 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -21,6 +21,7 @@ static void of_get_regulation_constraints(struct device_node *np, { const __be32 *min_uV, *max_uV, *uV_offset; const __be32 *min_uA, *max_uA, *ramp_delay; + struct property *prop; struct regulation_constraints *constraints = &(*init_data)->constraints; constraints->name = of_get_property(np, "regulator-name", NULL); @@ -64,9 +65,14 @@ static void of_get_regulation_constraints(struct device_node *np, if (of_property_read_bool(np, "regulator-allow-bypass")) constraints->valid_ops_mask |= REGULATOR_CHANGE_BYPASS; - ramp_delay = of_get_property(np, "regulator-ramp-delay", NULL); - if (ramp_delay) - constraints->ramp_delay = be32_to_cpu(*ramp_delay); + prop = of_find_property(np, "regulator-ramp-delay", NULL); + if (prop && prop->value) { + ramp_delay = prop->value; + if (*ramp_delay) + constraints->ramp_delay = be32_to_cpu(*ramp_delay); + else + constraints->ramp_disable = true; + } } /** diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 36adbc82de6a..999b20ce06cf 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -134,6 +134,7 @@ struct regulation_constraints { unsigned always_on:1; /* regulator never off when system is on */ unsigned boot_on:1; /* bootloader/firmware enabled regulator */ unsigned apply_uV:1; /* apply uV constraint if min == max */ + unsigned ramp_disable:1; /* disable ramp delay */ }; /** -- cgit v1.2.3-71-gd317 From 874b31585650afa6745de5133849365e7e6af418 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 5 Jul 2013 11:44:49 +0100 Subject: spi/bitbang: Unexport spi_bitbang_transfer() Currently no drivers use the ability to override spi_bitbang_transfer() and if any started this would make it harder to convert the bitbang code to use transfer_one_message() so remove the export in order to prevent anyone starting. Signed-off-by: Mark Brown --- drivers/spi/spi-bitbang.c | 3 +-- include/linux/spi/spi_bitbang.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index a63d7da3bfe2..495ce0a51d2f 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -376,7 +376,7 @@ static void bitbang_work(struct work_struct *work) /** * spi_bitbang_transfer - default submit to transfer queue */ -int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m) +static int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m) { struct spi_bitbang *bitbang; unsigned long flags; @@ -398,7 +398,6 @@ int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m) return status; } -EXPORT_SYMBOL_GPL(spi_bitbang_transfer); /*----------------------------------------------------------------------*/ diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index f987a2bee16a..b5aa215493f6 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -41,7 +41,6 @@ struct spi_bitbang { */ extern int spi_bitbang_setup(struct spi_device *spi); extern void spi_bitbang_cleanup(struct spi_device *spi); -extern int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m); extern int spi_bitbang_setup_transfer(struct spi_device *spi, struct spi_transfer *t); -- cgit v1.2.3-71-gd317 From a2fd4f9fa3b9f051550b36c4dfa74bc32bda24ee Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 10 Jul 2013 14:57:26 +0100 Subject: spi: Support transfer speed checking in the core Allow drivers to avoid implementing their own checks for simple rates by specifying the limits in the master structure. Signed-off-by: Mark Brown --- drivers/spi/spi.c | 7 +++++++ include/linux/spi/spi.h | 6 ++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 978dda2c5239..a52f16685d6a 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1387,6 +1387,13 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message) BIT(xfer->bits_per_word - 1))) return -EINVAL; } + + if (xfer->speed_hz && master->min_speed_hz && + xfer->speed_hz < master->min_speed_hz) + return -EINVAL; + if (xfer->speed_hz && master->max_speed_hz && + xfer->speed_hz > master->max_speed_hz) + return -EINVAL; } message->spi = spi; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..cdf668156154 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -233,6 +233,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * suported. If set, the SPI core will reject any transfer with an * unsupported bits_per_word. If not set, this value is simply ignored, * and it's up to the individual driver to perform any validation. + * @min_speed_hz: Lowest supported transfer speed + * @max_speed_hz: Highest supported transfer speed * @flags: other constraints relevant to this driver * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for SPI bus locking @@ -312,6 +314,10 @@ struct spi_master { #define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0UL : (BIT(bits) - 1)) #define SPI_BPW_RANGE_MASK(min, max) (SPI_BIT_MASK(max) - SPI_BIT_MASK(min - 1)) + /* limits on transfer speed */ + u32 min_speed_hz; + u32 max_speed_hz; + /* other constraints relevant to this driver */ u16 flags; #define SPI_MASTER_HALF_DUPLEX BIT(0) /* can't do full duplex */ -- cgit v1.2.3-71-gd317 From 939c02777a27ea7915764ecca5263dbb60c664f3 Mon Sep 17 00:00:00 2001 From: Yadwinder Singh Brar Date: Sat, 29 Jun 2013 18:21:16 +0530 Subject: regulator: s2mps11: Implement set_ramp_rate callback for bucks Implementing set_ramp_rate() and using standard constraints for getting ramp_delay and ramp_disable, instead of getting it as s2mps11 specific data through platform data, makes driver more compliant with framework and reduces the complexity for adding DT support. Signed-off-by: Yadwinder Singh Brar Signed-off-by: Mark Brown --- drivers/regulator/s2mps11.c | 117 ++++++++++++++++++++++++++++++++++++ include/linux/mfd/samsung/s2mps11.h | 11 ++++ 2 files changed, 128 insertions(+) (limited to 'include/linux') diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index a671eb63a4e5..4b84e7660637 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -104,6 +105,121 @@ static int s2mps11_regulator_set_voltage_time_sel(struct regulator_dev *rdev, return DIV_ROUND_UP(abs(new_volt - old_volt), ramp_delay); } +static int s2mps11_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) +{ + struct s2mps11_info *s2mps11 = rdev_get_drvdata(rdev); + unsigned int ramp_val, ramp_shift, ramp_reg = S2MPS11_REG_RAMP_BUCK; + unsigned int ramp_enable = 1, enable_shift = 0; + int ret; + + switch (rdev->desc->id) { + case S2MPS11_BUCK1: + if (ramp_delay > s2mps11->ramp_delay16) + s2mps11->ramp_delay16 = ramp_delay; + else + ramp_delay = s2mps11->ramp_delay16; + + ramp_shift = S2MPS11_BUCK16_RAMP_SHIFT; + break; + case S2MPS11_BUCK2: + enable_shift = S2MPS11_BUCK2_RAMP_EN_SHIFT; + if (!ramp_delay) { + ramp_enable = 0; + break; + } + + s2mps11->ramp_delay2 = ramp_delay; + ramp_shift = S2MPS11_BUCK2_RAMP_SHIFT; + ramp_reg = S2MPS11_REG_RAMP; + break; + case S2MPS11_BUCK3: + enable_shift = S2MPS11_BUCK3_RAMP_EN_SHIFT; + if (!ramp_delay) { + ramp_enable = 0; + break; + } + + if (ramp_delay > s2mps11->ramp_delay34) + s2mps11->ramp_delay34 = ramp_delay; + else + ramp_delay = s2mps11->ramp_delay34; + + ramp_shift = S2MPS11_BUCK34_RAMP_SHIFT; + ramp_reg = S2MPS11_REG_RAMP; + break; + case S2MPS11_BUCK4: + enable_shift = S2MPS11_BUCK4_RAMP_EN_SHIFT; + if (!ramp_delay) { + ramp_enable = 0; + break; + } + + if (ramp_delay > s2mps11->ramp_delay34) + s2mps11->ramp_delay34 = ramp_delay; + else + ramp_delay = s2mps11->ramp_delay34; + + ramp_shift = S2MPS11_BUCK34_RAMP_SHIFT; + ramp_reg = S2MPS11_REG_RAMP; + break; + case S2MPS11_BUCK5: + s2mps11->ramp_delay5 = ramp_delay; + ramp_shift = S2MPS11_BUCK5_RAMP_SHIFT; + break; + case S2MPS11_BUCK6: + enable_shift = S2MPS11_BUCK6_RAMP_EN_SHIFT; + if (!ramp_delay) { + ramp_enable = 0; + break; + } + + if (ramp_delay > s2mps11->ramp_delay16) + s2mps11->ramp_delay16 = ramp_delay; + else + ramp_delay = s2mps11->ramp_delay16; + + ramp_shift = S2MPS11_BUCK16_RAMP_SHIFT; + break; + case S2MPS11_BUCK7: + case S2MPS11_BUCK8: + case S2MPS11_BUCK10: + if (ramp_delay > s2mps11->ramp_delay7810) + s2mps11->ramp_delay7810 = ramp_delay; + else + ramp_delay = s2mps11->ramp_delay7810; + + ramp_shift = S2MPS11_BUCK7810_RAMP_SHIFT; + break; + case S2MPS11_BUCK9: + s2mps11->ramp_delay9 = ramp_delay; + ramp_shift = S2MPS11_BUCK9_RAMP_SHIFT; + break; + default: + return 0; + } + + if (!ramp_enable) + goto ramp_disable; + + if (enable_shift) { + ret = regmap_update_bits(rdev->regmap, S2MPS11_REG_RAMP, + 1 << enable_shift, 1 << enable_shift); + if (ret) { + dev_err(&rdev->dev, "failed to enable ramp rate\n"); + return ret; + } + } + + ramp_val = get_ramp_delay(ramp_delay); + + return regmap_update_bits(rdev->regmap, ramp_reg, + ramp_val << ramp_shift, 1 << ramp_shift); + +ramp_disable: + return regmap_update_bits(rdev->regmap, S2MPS11_REG_RAMP, 0, + 1 << enable_shift); +} + static struct regulator_ops s2mps11_ldo_ops = { .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, @@ -124,6 +240,7 @@ static struct regulator_ops s2mps11_buck_ops = { .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, .set_voltage_time_sel = s2mps11_regulator_set_voltage_time_sel, + .set_ramp_delay = s2mps11_set_ramp_delay, }; #define regulator_desc_ldo1(num) { \ diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index 4e94dc65f987..d0d52ea60074 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -191,6 +191,17 @@ enum s2mps11_regulators { #define S2MPS11_BUCK_N_VOLTAGES (S2MPS11_BUCK_VSEL_MASK + 1) #define S2MPS11_RAMP_DELAY 25000 /* uV/us */ + +#define S2MPS11_BUCK2_RAMP_SHIFT 6 +#define S2MPS11_BUCK34_RAMP_SHIFT 4 +#define S2MPS11_BUCK5_RAMP_SHIFT 6 +#define S2MPS11_BUCK16_RAMP_SHIFT 4 +#define S2MPS11_BUCK7810_RAMP_SHIFT 2 +#define S2MPS11_BUCK9_RAMP_SHIFT 0 +#define S2MPS11_BUCK2_RAMP_EN_SHIFT 3 +#define S2MPS11_BUCK3_RAMP_EN_SHIFT 2 +#define S2MPS11_BUCK4_RAMP_EN_SHIFT 1 +#define S2MPS11_BUCK6_RAMP_EN_SHIFT 0 #define S2MPS11_PMIC_EN_SHIFT 6 #define S2MPS11_REGULATOR_MAX (S2MPS11_REG_MAX - 3) -- cgit v1.2.3-71-gd317 From dc34e7e1a701134c2639dc7af78dc91055616477 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Mon, 1 Jul 2013 00:01:32 +0400 Subject: libata: move 'struct ata_taskfile' and friends from ata.h to libata.h Move 'struct ata_taskfile', ata_prot_flags() and their friends from to . They were misplaced from the beginning, as should cover ATA/ATAPI and related standards only -- to which the aforementioned structure and function have only remote relation. I would have moved 'enum ata_tf_protocols' closely related to 'struct ata_taskfile' but it unfortunately gets used by 'drivers/ide/ide-ioctls.c'... Signed-off-by: Sergei Shtylyov Signed-off-by: Tejun Heo --- include/linux/ata.h | 102 ------------------------------------------------- include/linux/libata.h | 102 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 102 insertions(+), 102 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index ee0bd9524055..f63fb1afc5cc 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -446,22 +446,6 @@ enum { SERR_TRANS_ST_ERROR = (1 << 24), /* Transport state trans. error */ SERR_UNRECOG_FIS = (1 << 25), /* Unrecognized FIS */ SERR_DEV_XCHG = (1 << 26), /* device exchanged */ - - /* struct ata_taskfile flags */ - ATA_TFLAG_LBA48 = (1 << 0), /* enable 48-bit LBA and "HOB" */ - ATA_TFLAG_ISADDR = (1 << 1), /* enable r/w to nsect/lba regs */ - ATA_TFLAG_DEVICE = (1 << 2), /* enable r/w to device reg */ - ATA_TFLAG_WRITE = (1 << 3), /* data dir: host->dev==1 (write) */ - ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ - ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ - ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ - - /* protocol flags */ - ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ - ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ - ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, - ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ - ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ }; enum ata_tf_protocols { @@ -488,83 +472,6 @@ struct ata_bmdma_prd { __le32 flags_len; }; -struct ata_taskfile { - unsigned long flags; /* ATA_TFLAG_xxx */ - u8 protocol; /* ATA_PROT_xxx */ - - u8 ctl; /* control reg */ - - u8 hob_feature; /* additional data */ - u8 hob_nsect; /* to support LBA48 */ - u8 hob_lbal; - u8 hob_lbam; - u8 hob_lbah; - - u8 feature; - u8 nsect; - u8 lbal; - u8 lbam; - u8 lbah; - - u8 device; - - u8 command; /* IO operation */ -}; - -/* - * protocol tests - */ -static inline unsigned int ata_prot_flags(u8 prot) -{ - switch (prot) { - case ATA_PROT_NODATA: - return 0; - case ATA_PROT_PIO: - return ATA_PROT_FLAG_PIO; - case ATA_PROT_DMA: - return ATA_PROT_FLAG_DMA; - case ATA_PROT_NCQ: - return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; - case ATAPI_PROT_NODATA: - return ATA_PROT_FLAG_ATAPI; - case ATAPI_PROT_PIO: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; - case ATAPI_PROT_DMA: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; - } - return 0; -} - -static inline int ata_is_atapi(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; -} - -static inline int ata_is_nodata(u8 prot) -{ - return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); -} - -static inline int ata_is_pio(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; -} - -static inline int ata_is_dma(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; -} - -static inline int ata_is_ncq(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; -} - -static inline int ata_is_data(u8 prot) -{ - return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; -} - /* * id tests */ @@ -1060,15 +967,6 @@ static inline unsigned ata_set_lba_range_entries(void *_buffer, return used_bytes; } -static inline int is_multi_taskfile(struct ata_taskfile *tf) -{ - return (tf->command == ATA_CMD_READ_MULTI) || - (tf->command == ATA_CMD_WRITE_MULTI) || - (tf->command == ATA_CMD_READ_MULTI_EXT) || - (tf->command == ATA_CMD_WRITE_MULTI_EXT) || - (tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT); -} - static inline bool ata_ok(u8 status) { return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR)) diff --git a/include/linux/libata.h b/include/linux/libata.h index 4ea55bb45deb..283d66bc603c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -138,6 +138,22 @@ enum { ATA_SHT_THIS_ID = -1, ATA_SHT_USE_CLUSTERING = 1, + /* struct ata_taskfile flags */ + ATA_TFLAG_LBA48 = (1 << 0), /* enable 48-bit LBA and "HOB" */ + ATA_TFLAG_ISADDR = (1 << 1), /* enable r/w to nsect/lba regs */ + ATA_TFLAG_DEVICE = (1 << 2), /* enable r/w to device reg */ + ATA_TFLAG_WRITE = (1 << 3), /* data dir: host->dev==1 (write) */ + ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ + ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ + ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ + + /* protocol flags */ + ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ + ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ + ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, + ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ + ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ + /* struct ata_device stuff */ ATA_DFLAG_LBA = (1 << 0), /* device supports LBA */ ATA_DFLAG_LBA48 = (1 << 1), /* device supports LBA48 */ @@ -518,6 +534,29 @@ enum sw_activity { BLINK_OFF, }; +struct ata_taskfile { + unsigned long flags; /* ATA_TFLAG_xxx */ + u8 protocol; /* ATA_PROT_xxx */ + + u8 ctl; /* control reg */ + + u8 hob_feature; /* additional data */ + u8 hob_nsect; /* to support LBA48 */ + u8 hob_lbal; + u8 hob_lbam; + u8 hob_lbah; + + u8 feature; + u8 nsect; + u8 lbal; + u8 lbam; + u8 lbah; + + u8 device; + + u8 command; /* IO operation */ +}; + #ifdef CONFIG_ATA_SFF struct ata_ioports { void __iomem *cmd_addr; @@ -959,6 +998,69 @@ extern const unsigned long sata_deb_timing_long[]; extern struct ata_port_operations ata_dummy_port_ops; extern const struct ata_port_info ata_dummy_port_info; +/* + * protocol tests + */ +static inline unsigned int ata_prot_flags(u8 prot) +{ + switch (prot) { + case ATA_PROT_NODATA: + return 0; + case ATA_PROT_PIO: + return ATA_PROT_FLAG_PIO; + case ATA_PROT_DMA: + return ATA_PROT_FLAG_DMA; + case ATA_PROT_NCQ: + return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; + case ATAPI_PROT_NODATA: + return ATA_PROT_FLAG_ATAPI; + case ATAPI_PROT_PIO: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; + case ATAPI_PROT_DMA: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; + } + return 0; +} + +static inline int ata_is_atapi(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; +} + +static inline int ata_is_nodata(u8 prot) +{ + return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); +} + +static inline int ata_is_pio(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; +} + +static inline int ata_is_dma(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; +} + +static inline int ata_is_ncq(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; +} + +static inline int ata_is_data(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; +} + +static inline int is_multi_taskfile(struct ata_taskfile *tf) +{ + return (tf->command == ATA_CMD_READ_MULTI) || + (tf->command == ATA_CMD_WRITE_MULTI) || + (tf->command == ATA_CMD_READ_MULTI_EXT) || + (tf->command == ATA_CMD_WRITE_MULTI_EXT) || + (tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT); +} + static inline const unsigned long * sata_ehc_deb_timing(struct ata_eh_context *ehc) { -- cgit v1.2.3-71-gd317 From 2025172e32808a327b00f968c72baa79adc594c2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 5 Jul 2013 20:07:27 +0100 Subject: spi/bitbang: Use core message pump Convert drivers using bitbang to use the core mesasge pump infrastructure, saving some code and meaning that these drivers get to take advantage of work done on improving the core implementation. Signed-off-by: Mark Brown --- drivers/spi/spi-bitbang.c | 100 ++++++++++++---------------------------- include/linux/spi/spi_bitbang.h | 4 -- 2 files changed, 30 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index 8b8487c9694e..c100875cfd42 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -255,6 +255,21 @@ static int spi_bitbang_bufs(struct spi_device *spi, struct spi_transfer *t) * Drivers can provide word-at-a-time i/o primitives, or provide * transfer-at-a-time ones to leverage dma or fifo hardware. */ + +static int spi_bitbang_prepare_hardware(struct spi_master *spi) +{ + struct spi_bitbang *bitbang; + unsigned long flags; + + bitbang = spi_master_get_devdata(spi); + + spin_lock_irqsave(&bitbang->lock, flags); + bitbang->busy = 1; + spin_unlock_irqrestore(&bitbang->lock, flags); + + return 0; +} + static int spi_bitbang_transfer_one(struct spi_device *spi, struct spi_message *m) { @@ -346,7 +361,6 @@ static int spi_bitbang_transfer_one(struct spi_device *spi, } m->status = status; - m->complete(m->context); /* normally deactivate chipselect ... unless no error and * cs_change has hinted that the next message will probably @@ -358,54 +372,23 @@ static int spi_bitbang_transfer_one(struct spi_device *spi, ndelay(nsecs); } - return status; -} - -static void bitbang_work(struct work_struct *work) -{ - struct spi_bitbang *bitbang = - container_of(work, struct spi_bitbang, work); - unsigned long flags; - struct spi_message *m, *_m; - - spin_lock_irqsave(&bitbang->lock, flags); - bitbang->busy = 1; - list_for_each_entry_safe(m, _m, &bitbang->queue, queue) { - list_del(&m->queue); - spin_unlock_irqrestore(&bitbang->lock, flags); - - spi_bitbang_transfer_one(m->spi, m); + spi_finalize_current_message(spi->master); - spin_lock_irqsave(&bitbang->lock, flags); - } - bitbang->busy = 0; - spin_unlock_irqrestore(&bitbang->lock, flags); + return status; } -/** - * spi_bitbang_transfer - default submit to transfer queue - */ -static int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m) +static int spi_bitbang_unprepare_hardware(struct spi_master *spi) { - struct spi_bitbang *bitbang; + struct spi_bitbang *bitbang; unsigned long flags; - int status = 0; - - m->actual_length = 0; - m->status = -EINPROGRESS; - bitbang = spi_master_get_devdata(spi->master); + bitbang = spi_master_get_devdata(spi); spin_lock_irqsave(&bitbang->lock, flags); - if (!spi->max_speed_hz) - status = -ENETDOWN; - else { - list_add_tail(&m->queue, &bitbang->queue); - queue_work(bitbang->workqueue, &bitbang->work); - } + bitbang->busy = 0; spin_unlock_irqrestore(&bitbang->lock, flags); - return status; + return 0; } /*----------------------------------------------------------------------*/ @@ -436,20 +419,22 @@ static int spi_bitbang_transfer(struct spi_device *spi, struct spi_message *m) int spi_bitbang_start(struct spi_bitbang *bitbang) { struct spi_master *master = bitbang->master; - int status; if (!master || !bitbang->chipselect) return -EINVAL; - INIT_WORK(&bitbang->work, bitbang_work); spin_lock_init(&bitbang->lock); - INIT_LIST_HEAD(&bitbang->queue); if (!master->mode_bits) master->mode_bits = SPI_CPOL | SPI_CPHA | bitbang->flags; - if (!master->transfer) - master->transfer = spi_bitbang_transfer; + if (master->transfer || master->transfer_one_message) + return -EINVAL; + + master->prepare_transfer_hardware = spi_bitbang_prepare_hardware; + master->unprepare_transfer_hardware = spi_bitbang_unprepare_hardware; + master->transfer_one_message = spi_bitbang_transfer_one; + if (!bitbang->txrx_bufs) { bitbang->use_dma = 0; bitbang->txrx_bufs = spi_bitbang_bufs; @@ -462,32 +447,11 @@ int spi_bitbang_start(struct spi_bitbang *bitbang) } } else if (!master->setup) return -EINVAL; - if (master->transfer == spi_bitbang_transfer && - !bitbang->setup_transfer) - return -EINVAL; - - /* this task is the only thing to touch the SPI bits */ - bitbang->busy = 0; - bitbang->workqueue = create_singlethread_workqueue( - dev_name(master->dev.parent)); - if (bitbang->workqueue == NULL) { - status = -EBUSY; - goto err1; - } /* driver may get busy before register() returns, especially * if someone registered boardinfo for devices */ - status = spi_register_master(master); - if (status < 0) - goto err2; - - return status; - -err2: - destroy_workqueue(bitbang->workqueue); -err1: - return status; + return spi_register_master(master); } EXPORT_SYMBOL_GPL(spi_bitbang_start); @@ -498,10 +462,6 @@ int spi_bitbang_stop(struct spi_bitbang *bitbang) { spi_unregister_master(bitbang->master); - WARN_ON(!list_empty(&bitbang->queue)); - - destroy_workqueue(bitbang->workqueue); - return 0; } EXPORT_SYMBOL_GPL(spi_bitbang_stop); diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index b5aa215493f6..daebaba886aa 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -4,11 +4,7 @@ #include struct spi_bitbang { - struct workqueue_struct *workqueue; - struct work_struct work; - spinlock_t lock; - struct list_head queue; u8 busy; u8 use_dma; u8 flags; /* extra spi->mode support */ -- cgit v1.2.3-71-gd317 From e69f61862ab833e9b8d3c15b6ce07fd69f3bfecc Mon Sep 17 00:00:00 2001 From: Yacine Belkadi Date: Fri, 12 Jul 2013 20:45:47 +0200 Subject: sched: Fix some kernel-doc warnings When building the htmldocs (in verbose mode), scripts/kernel-doc reports the follwing type of warnings: Warning(kernel/sched/core.c:936): No description found for return value of 'task_curr' ... Fix those by: - adding the missing descriptions - using "Return" sections for the descriptions Signed-off-by: Yacine Belkadi Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1373654747-2389-1-git-send-email-yacine.belkadi.1@gmail.com [ While at it, fix the cpupri_set() explanation. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ++++ kernel/sched/core.c | 82 ++++++++++++++++++++++++++++++++++++++------------- kernel/sched/cpupri.c | 4 +-- kernel/sched/fair.c | 9 ++++-- 4 files changed, 76 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50d04b92ceda..82300247974c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1532,6 +1532,8 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) * Test if a process is not yet dead (at most zombie state) * If pid_alive fails, then pointers within the task structure * can be stale and must not be dereferenced. + * + * Return: 1 if the process is alive. 0 otherwise. */ static inline int pid_alive(struct task_struct *p) { @@ -1543,6 +1545,8 @@ static inline int pid_alive(struct task_struct *p) * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. + * + * Return: 1 if the task structure is init. 0 otherwise. */ static inline int is_global_init(struct task_struct *tsk) { @@ -1893,6 +1897,8 @@ extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. + * + * Return: 1 if @p is an idle task. 0 otherwise. */ static inline bool is_idle_task(const struct task_struct *p) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0d8eb4525e76..4c3967f91e20 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -933,6 +933,8 @@ static int effective_prio(struct task_struct *p) /** * task_curr - is this task currently executing on a CPU? * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. */ inline int task_curr(const struct task_struct *p) { @@ -1482,7 +1484,7 @@ static void ttwu_queue(struct task_struct *p, int cpu) * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * Returns %true if @p was woken up, %false if it was already running + * Return: %true if @p was woken up, %false if it was already running. * or @state didn't match @p's state. */ static int @@ -1577,8 +1579,9 @@ out: * @p: The process to be woken up. * * Attempt to wake up the nominated process and move it to the set of runnable - * processes. Returns 1 if the process was woken up, 0 if it was already - * running. + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. * * It may be assumed that this function implies a write memory barrier before * changing the task state if and only if any tasks are woken up. @@ -2191,6 +2194,8 @@ void scheduler_tick(void) * This makes sure that uptime, CFS vruntime, load * balancing, etc... continue to move forward, even * with a very low granularity. + * + * Return: Maximum deferment in nanoseconds. */ u64 scheduler_tick_max_deferment(void) { @@ -2796,8 +2801,8 @@ EXPORT_SYMBOL(wait_for_completion); * specified timeout to expire. The timeout is in jiffies. It is not * interruptible. * - * The return value is 0 if timed out, and positive (at least 1, or number of - * jiffies left till timeout) if completed. + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. */ unsigned long __sched wait_for_completion_timeout(struct completion *x, unsigned long timeout) @@ -2829,8 +2834,8 @@ EXPORT_SYMBOL(wait_for_completion_io); * specified timeout to expire. The timeout is in jiffies. It is not * interruptible. The caller is accounted as waiting for IO. * - * The return value is 0 if timed out, and positive (at least 1, or number of - * jiffies left till timeout) if completed. + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. */ unsigned long __sched wait_for_completion_io_timeout(struct completion *x, unsigned long timeout) @@ -2846,7 +2851,7 @@ EXPORT_SYMBOL(wait_for_completion_io_timeout); * This waits for completion of a specific task to be signaled. It is * interruptible. * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. + * Return: -ERESTARTSYS if interrupted, 0 if completed. */ int __sched wait_for_completion_interruptible(struct completion *x) { @@ -2865,8 +2870,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible); * This waits for either a completion of a specific task to be signaled or for a * specified timeout to expire. It is interruptible. The timeout is in jiffies. * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. */ long __sched wait_for_completion_interruptible_timeout(struct completion *x, @@ -2883,7 +2888,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); * This waits to be signaled for completion of a specific task. It can be * interrupted by a kill signal. * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. + * Return: -ERESTARTSYS if interrupted, 0 if completed. */ int __sched wait_for_completion_killable(struct completion *x) { @@ -2903,8 +2908,8 @@ EXPORT_SYMBOL(wait_for_completion_killable); * signaled or for a specified timeout to expire. It can be * interrupted by a kill signal. The timeout is in jiffies. * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. + * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1, + * or number of jiffies left till timeout) if completed. */ long __sched wait_for_completion_killable_timeout(struct completion *x, @@ -2918,7 +2923,7 @@ EXPORT_SYMBOL(wait_for_completion_killable_timeout); * try_wait_for_completion - try to decrement a completion without blocking * @x: completion structure * - * Returns: 0 if a decrement cannot be done without blocking + * Return: 0 if a decrement cannot be done without blocking * 1 if a decrement succeeded. * * If a completion is being used as a counting completion, @@ -2945,7 +2950,7 @@ EXPORT_SYMBOL(try_wait_for_completion); * completion_done - Test to see if a completion has any waiters * @x: completion structure * - * Returns: 0 if there are waiters (wait_for_completion() in progress) + * Return: 0 if there are waiters (wait_for_completion() in progress) * 1 if there are no waiters. * */ @@ -3182,7 +3187,7 @@ SYSCALL_DEFINE1(nice, int, increment) * task_prio - return the priority value of a given task. * @p: the task in question. * - * This is the priority value as seen by users in /proc. + * Return: The priority value as seen by users in /proc. * RT tasks are offset by -200. Normal tasks are centered * around 0, value goes from -16 to +15. */ @@ -3194,6 +3199,8 @@ int task_prio(const struct task_struct *p) /** * task_nice - return the nice value of a given task. * @p: the task in question. + * + * Return: The nice value [ -20 ... 0 ... 19 ]. */ int task_nice(const struct task_struct *p) { @@ -3204,6 +3211,8 @@ EXPORT_SYMBOL(task_nice); /** * idle_cpu - is a given cpu idle currently? * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. */ int idle_cpu(int cpu) { @@ -3226,6 +3235,8 @@ int idle_cpu(int cpu) /** * idle_task - return the idle task for a given cpu. * @cpu: the processor in question. + * + * Return: The idle task for the cpu @cpu. */ struct task_struct *idle_task(int cpu) { @@ -3235,6 +3246,8 @@ struct task_struct *idle_task(int cpu) /** * find_process_by_pid - find a process with a matching PID value. * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. */ static struct task_struct *find_process_by_pid(pid_t pid) { @@ -3432,6 +3445,8 @@ recheck: * @policy: new policy. * @param: structure containing the new RT priority. * + * Return: 0 on success. An error code otherwise. + * * NOTE that the task may be already dead. */ int sched_setscheduler(struct task_struct *p, int policy, @@ -3451,6 +3466,8 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); * current context has permission. For example, this is needed in * stop_machine(): we create temporary high priority worker threads, * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. */ int sched_setscheduler_nocheck(struct task_struct *p, int policy, const struct sched_param *param) @@ -3485,6 +3502,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) * @pid: the pid in question. * @policy: new policy. * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) @@ -3500,6 +3519,8 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, * sys_sched_setparam - set/change the RT priority of a thread * @pid: the pid in question. * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) { @@ -3509,6 +3530,9 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) /** * sys_sched_getscheduler - get the policy (scheduling class) of a thread * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. */ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) { @@ -3535,6 +3559,9 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) * sys_sched_getparam - get the RT priority of a thread * @pid: the pid in question. * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. */ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) { @@ -3659,6 +3686,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr * @user_mask_ptr: user-space pointer to the new cpu mask + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, unsigned long __user *, user_mask_ptr) @@ -3710,6 +3739,8 @@ out_unlock: * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr * @user_mask_ptr: user-space pointer to hold the current cpu mask + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, unsigned long __user *, user_mask_ptr) @@ -3744,6 +3775,8 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, * * This function yields the current CPU to other tasks. If there are no * other threads running on this CPU then this function will return. + * + * Return: 0. */ SYSCALL_DEFINE0(sched_yield) { @@ -3869,7 +3902,7 @@ EXPORT_SYMBOL(yield); * It's the caller's job to ensure that the target task struct * can't go away on us before we can do any checks. * - * Returns: + * Return: * true (>0) if we indeed boosted the target task. * false (0) if we failed to boost the target. * -ESRCH if there's no task to yield to. @@ -3972,8 +4005,9 @@ long __sched io_schedule_timeout(long timeout) * sys_sched_get_priority_max - return maximum RT priority. * @policy: scheduling class. * - * this syscall returns the maximum rt_priority that can be used - * by a given scheduling class. + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. */ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) { @@ -3997,8 +4031,9 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) * sys_sched_get_priority_min - return minimum RT priority. * @policy: scheduling class. * - * this syscall returns the minimum rt_priority that can be used - * by a given scheduling class. + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. */ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) { @@ -4024,6 +4059,9 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) * * this syscall writes the default timeslice value of a given process * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. */ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, struct timespec __user *, interval) @@ -6632,6 +6670,8 @@ void normalize_rt_tasks(void) * @cpu: the processor in question. * * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + * + * Return: The current task for @cpu. */ struct task_struct *curr_task(int cpu) { diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 1095e878a46f..8b836b376d91 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -62,7 +62,7 @@ static int convert_prio(int prio) * any discrepancies created by racing against the uncertainty of the current * priority configuration. * - * Returns: (int)bool - CPUs were found + * Return: (int)bool - CPUs were found */ int cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask) @@ -203,7 +203,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * cpupri_init - initialize the cpupri structure * @cp: The cpupri context * - * Returns: -ENOMEM if memory fails. + * Return: -ENOMEM on memory allocation failure. */ int cpupri_init(struct cpupri *cp) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f77f9c527449..98d135584b4b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4280,6 +4280,8 @@ struct sg_lb_stats { * get_sd_load_idx - Obtain the load index for a given sched domain. * @sd: The sched_domain whose load_idx is to be obtained. * @idle: The Idle status of the CPU for whose sd load_icx is obtained. + * + * Return: The load index. */ static inline int get_sd_load_idx(struct sched_domain *sd, enum cpu_idle_type idle) @@ -4574,6 +4576,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, * * Determine if @sg is a busier group than the previously selected * busiest group. + * + * Return: %true if @sg is a busier group than the previously selected + * busiest group. %false otherwise. */ static bool update_sd_pick_busiest(struct lb_env *env, struct sd_lb_stats *sds, @@ -4691,7 +4696,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, * assuming lower CPU number will be equivalent to lower a SMT thread * number. * - * Returns 1 when packing is required and a task should be moved to + * Return: 1 when packing is required and a task should be moved to * this CPU. The amount of the imbalance is returned in *imbalance. * * @env: The load balancing environment. @@ -4869,7 +4874,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * @balance: Pointer to a variable indicating if this_cpu * is the appropriate cpu to perform load balancing at this_level. * - * Returns: - the busiest group if imbalance exists. + * Return: - The busiest group if imbalance exists. * - If no imbalance and user has opted for power-savings balance, * return the least loaded group whose CPUs can be * put to idle by rebalancing its tasks onto our group. -- cgit v1.2.3-71-gd317 From 078726ce6d56a767533064e0f2f2100d7cb6fc22 Mon Sep 17 00:00:00 2001 From: Sourav Poddar Date: Thu, 18 Jul 2013 15:31:25 +0530 Subject: driver: spi: Modify core to compute the message length Make spi core calculate the message length while populating the other transfer parameters. Usecase, driver can use it to populate framelength filed in their controller. Signed-off-by: Sourav Poddar Signed-off-by: Mark Brown --- drivers/spi/spi.c | 1 + include/linux/spi/spi.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 978dda2c5239..7e3446cab72f 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1375,6 +1375,7 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message) * it is not set for this transfer. */ list_for_each_entry(xfer, &message->transfers, transfer_list) { + message->frame_length += xfer->len; if (!xfer->bits_per_word) xfer->bits_per_word = spi->bits_per_word; if (!xfer->speed_hz) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..aadd0a885a0f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -578,6 +578,7 @@ struct spi_message { /* completion is reported through a callback */ void (*complete)(void *context); void *context; + unsigned frame_length; unsigned actual_length; int status; -- cgit v1.2.3-71-gd317 From a1a8e1dc111d6f05e7164e851e58219d428359e1 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 16 Jul 2013 15:28:00 +0100 Subject: iio:trigger: Fix use_count race condition When using more than one trigger consumer it can happen that multiple threads perform a read-modify-update cycle on 'use_count' concurrently. This can cause updates to be lost and use_count can get stuck at non-zero value, in which case the IIO core assumes that at least one thread is still running and will wait for it to finish before running any trigger handlers again. This effectively renders the trigger disabled and a reboot is necessary before it can be used again. To fix this make use_count an atomic variable. Also set it to the number of consumers before starting the first consumer, otherwise it might happen that use_count drops to 0 even though not all consumers have been run yet. Signed-off-by: Lars-Peter Clausen Tested-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-trigger.c | 34 ++++++++++++++++++++++------------ include/linux/iio/trigger.h | 3 ++- 2 files changed, 24 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index ea8a4146620d..0dd9bb873130 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -127,12 +127,17 @@ static struct iio_trigger *iio_trigger_find_by_name(const char *name, void iio_trigger_poll(struct iio_trigger *trig, s64 time) { int i; - if (!trig->use_count) - for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++) - if (trig->subirqs[i].enabled) { - trig->use_count++; + + if (!atomic_read(&trig->use_count)) { + atomic_set(&trig->use_count, CONFIG_IIO_CONSUMERS_PER_TRIGGER); + + for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++) { + if (trig->subirqs[i].enabled) generic_handle_irq(trig->subirq_base + i); - } + else + iio_trigger_notify_done(trig); + } + } } EXPORT_SYMBOL(iio_trigger_poll); @@ -146,19 +151,24 @@ EXPORT_SYMBOL(iio_trigger_generic_data_rdy_poll); void iio_trigger_poll_chained(struct iio_trigger *trig, s64 time) { int i; - if (!trig->use_count) - for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++) - if (trig->subirqs[i].enabled) { - trig->use_count++; + + if (!atomic_read(&trig->use_count)) { + atomic_set(&trig->use_count, CONFIG_IIO_CONSUMERS_PER_TRIGGER); + + for (i = 0; i < CONFIG_IIO_CONSUMERS_PER_TRIGGER; i++) { + if (trig->subirqs[i].enabled) handle_nested_irq(trig->subirq_base + i); - } + else + iio_trigger_notify_done(trig); + } + } } EXPORT_SYMBOL(iio_trigger_poll_chained); void iio_trigger_notify_done(struct iio_trigger *trig) { - trig->use_count--; - if (trig->use_count == 0 && trig->ops && trig->ops->try_reenable) + if (atomic_dec_and_test(&trig->use_count) && trig->ops && + trig->ops->try_reenable) if (trig->ops->try_reenable(trig)) /* Missed an interrupt so launch new poll now */ iio_trigger_poll(trig, 0); diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 3869c525b052..369cf2cd5144 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -8,6 +8,7 @@ */ #include #include +#include #ifndef _IIO_TRIGGER_H_ #define _IIO_TRIGGER_H_ @@ -61,7 +62,7 @@ struct iio_trigger { struct list_head list; struct list_head alloc_list; - int use_count; + atomic_t use_count; struct irq_chip subirq_chip; int subirq_base; -- cgit v1.2.3-71-gd317 From b1451e546899bc8f450773b2af02e0cd000cf1fa Mon Sep 17 00:00:00 2001 From: "Patil, Rachna" Date: Sat, 20 Jul 2013 17:27:00 +0100 Subject: iio: ti_am335x_adc: Fix wrong samples received on 1st read Previously we tried to read data form ADC even before ADC sequencer finished sampling. This led to wrong samples. We now wait on ADC status register idle bit to be set. Signed-off-by: Patil, Rachna Signed-off-by: Zubair Lutfullah Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti_am335x_adc.c | 30 ++++++++++++++++++++++-------- include/linux/mfd/ti_am335x_tscadc.h | 16 ++++++++++++++++ 2 files changed, 38 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 0ad208a69c29..3ceac3e91dde 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -60,7 +60,6 @@ static void tiadc_step_config(struct tiadc_device *adc_dev) { unsigned int stepconfig; int i, steps; - u32 step_en; /* * There are 16 configurable steps and 8 analog input @@ -86,8 +85,7 @@ static void tiadc_step_config(struct tiadc_device *adc_dev) adc_dev->channel_step[i] = steps; steps++; } - step_en = get_adc_step_mask(adc_dev); - am335x_tsc_se_set(adc_dev->mfd_tscadc, step_en); + } static const char * const chan_name_ain[] = { @@ -142,10 +140,22 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct tiadc_device *adc_dev = iio_priv(indio_dev); - int i; - unsigned int fifo1count, read; + int i, map_val; + unsigned int fifo1count, read, stepid; u32 step = UINT_MAX; bool found = false; + u32 step_en; + unsigned long timeout = jiffies + usecs_to_jiffies + (IDLE_TIMEOUT * adc_dev->channels); + step_en = get_adc_step_mask(adc_dev); + am335x_tsc_se_set(adc_dev->mfd_tscadc, step_en); + + /* Wait for ADC sequencer to complete sampling */ + while (tiadc_readl(adc_dev, REG_ADCFSM) & SEQ_STATUS) { + if (time_after(jiffies, timeout)) + return -EAGAIN; + } + map_val = chan->channel + TOTAL_CHANNELS; /* * When the sub-system is first enabled, @@ -170,12 +180,16 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT); for (i = 0; i < fifo1count; i++) { read = tiadc_readl(adc_dev, REG_FIFO1); - if (read >> 16 == step) { - *val = read & 0xfff; + stepid = read & FIFOREAD_CHNLID_MASK; + stepid = stepid >> 0x10; + + if (stepid == map_val) { + read = read & FIFOREAD_DATA_MASK; found = true; + *val = read; } } - am335x_tsc_se_update(adc_dev->mfd_tscadc); + if (found == false) return -EBUSY; return IIO_VAL_INT; diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 8d73fe29796a..db1791bb997a 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -113,11 +113,27 @@ #define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) #define CNTRLREG_TSCENB BIT(7) +/* FIFO READ Register */ +#define FIFOREAD_DATA_MASK (0xfff << 0) +#define FIFOREAD_CHNLID_MASK (0xf << 16) + +/* Sequencer Status */ +#define SEQ_STATUS BIT(5) + #define ADC_CLK 3000000 #define MAX_CLK_DIV 7 #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 +/* +* ADC runs at 3MHz, and it takes +* 15 cycles to latch one data output. +* Hence the idle time for ADC to +* process one sample data would be +* around 5 micro seconds. +*/ +#define IDLE_TIMEOUT 5 /* microsec */ + #define TSCADC_CELLS 2 struct ti_tscadc_dev { -- cgit v1.2.3-71-gd317 From be1c9de98d8904c75a5ab8b2a0d97bea0f7c07cc Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 13 Jul 2013 23:27:23 +0200 Subject: ACPI / PCI: Make bus registration and unregistration symmetric Since acpi_pci_slot_enumerate() and acpiphp_enumerate_slots() can get the ACPI device handle they need from bus->bridge, it is not necessary to pass that handle to them as an argument. Drop the second argument of acpi_pci_slot_enumerate() and acpiphp_enumerate_slots(), rework them to obtain the ACPI handle from bus->bridge and make acpi_pci_add_bus() and acpi_pci_remove_bus() entirely symmetrical. Tested-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki Acked-by: Yinghai Lu --- drivers/acpi/pci_slot.c | 14 +++++++++----- drivers/pci/hotplug/acpiphp_glue.c | 6 ++++-- drivers/pci/pci-acpi.c | 16 ++++------------ include/linux/pci-acpi.h | 10 ++++------ 4 files changed, 21 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c index 033d1179bdb5..d678a180ca2a 100644 --- a/drivers/acpi/pci_slot.c +++ b/drivers/acpi/pci_slot.c @@ -159,12 +159,16 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv) return AE_OK; } -void acpi_pci_slot_enumerate(struct pci_bus *bus, acpi_handle handle) +void acpi_pci_slot_enumerate(struct pci_bus *bus) { - mutex_lock(&slot_list_lock); - acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, - register_slot, NULL, bus, NULL); - mutex_unlock(&slot_list_lock); + acpi_handle handle = ACPI_HANDLE(bus->bridge); + + if (handle) { + mutex_lock(&slot_list_lock); + acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, + register_slot, NULL, bus, NULL); + mutex_unlock(&slot_list_lock); + } } void acpi_pci_slot_remove(struct pci_bus *bus) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 8bfad0dc29ab..a203ba529fef 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -1147,14 +1147,16 @@ static void handle_hotplug_event_func(acpi_handle handle, u32 type, * Create hotplug slots for the PCI bus. * It should always return 0 to avoid skipping following notifiers. */ -void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle) +void acpiphp_enumerate_slots(struct pci_bus *bus) { + acpi_handle handle; struct acpiphp_bridge *bridge; if (acpiphp_disabled) return; - if (detect_ejectable_slots(handle) <= 0) + handle = ACPI_HANDLE(bus->bridge); + if (!handle || detect_ejectable_slots(handle) <= 0) return; bridge = kzalloc(sizeof(struct acpiphp_bridge), GFP_KERNEL); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index dbdc5f7e2b29..c78cc432edab 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -290,24 +290,16 @@ static struct pci_platform_pm_ops acpi_pci_platform_pm = { void acpi_pci_add_bus(struct pci_bus *bus) { - acpi_handle handle = NULL; - - if (bus->bridge) - handle = ACPI_HANDLE(bus->bridge); - if (acpi_pci_disabled || handle == NULL) + if (acpi_pci_disabled || !bus->bridge) return; - acpi_pci_slot_enumerate(bus, handle); - acpiphp_enumerate_slots(bus, handle); + acpi_pci_slot_enumerate(bus); + acpiphp_enumerate_slots(bus); } void acpi_pci_remove_bus(struct pci_bus *bus) { - /* - * bus->bridge->acpi_node.handle has already been reset to NULL - * when acpi_pci_remove_bus() is called, so don't check ACPI handle. - */ - if (acpi_pci_disabled) + if (acpi_pci_disabled || !bus->bridge) return; acpiphp_remove_slots(bus); diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 170447977278..d006f0ca60f4 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -47,24 +47,22 @@ void acpi_pci_remove_bus(struct pci_bus *bus); #ifdef CONFIG_ACPI_PCI_SLOT void acpi_pci_slot_init(void); -void acpi_pci_slot_enumerate(struct pci_bus *bus, acpi_handle handle); +void acpi_pci_slot_enumerate(struct pci_bus *bus); void acpi_pci_slot_remove(struct pci_bus *bus); #else static inline void acpi_pci_slot_init(void) { } -static inline void acpi_pci_slot_enumerate(struct pci_bus *bus, - acpi_handle handle) { } +static inline void acpi_pci_slot_enumerate(struct pci_bus *bus) { } static inline void acpi_pci_slot_remove(struct pci_bus *bus) { } #endif #ifdef CONFIG_HOTPLUG_PCI_ACPI void acpiphp_init(void); -void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle); +void acpiphp_enumerate_slots(struct pci_bus *bus); void acpiphp_remove_slots(struct pci_bus *bus); void acpiphp_check_host_bridge(acpi_handle handle); #else static inline void acpiphp_init(void) { } -static inline void acpiphp_enumerate_slots(struct pci_bus *bus, - acpi_handle handle) { } +static inline void acpiphp_enumerate_slots(struct pci_bus *bus) { } static inline void acpiphp_remove_slots(struct pci_bus *bus) { } static inline void acpiphp_check_host_bridge(acpi_handle handle) { } #endif -- cgit v1.2.3-71-gd317 From 62470419e993f8d9d93db0effd3af4296ecb79a5 Mon Sep 17 00:00:00 2001 From: Michael Wang Date: Thu, 4 Jul 2013 12:55:51 +0800 Subject: sched: Implement smarter wake-affine logic The wake-affine scheduler feature is currently always trying to pull the wakee close to the waker. In theory this should be beneficial if the waker's CPU caches hot data for the wakee, and it's also beneficial in the extreme ping-pong high context switch rate case. Testing shows it can benefit hackbench up to 15%. However, the feature is somewhat blind, from which some workloads such as pgbench suffer. It's also time-consuming algorithmically. Testing shows it can damage pgbench up to 50% - far more than the benefit it brings in the best case. So wake-affine should be smarter and it should realize when to stop its thankless effort at trying to find a suitable CPU to wake on. This patch introduces 'wakee_flips', which will be increased each time the task flips (switches) its wakee target. So a high 'wakee_flips' value means the task has more than one wakee, and the bigger the number, the higher the wakeup frequency. Now when making the decision on whether to pull or not, pay attention to the wakee with a high 'wakee_flips', pulling such a task may benefit the wakee. Also imply that the waker will face cruel competition later, it could be very cruel or very fast depends on the story behind 'wakee_flips', waker therefore suffers. Furthermore, if waker also has a high 'wakee_flips', that implies that multiple tasks rely on it, then waker's higher latency will damage all of them, so pulling wakee seems to be a bad deal. Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes higher and higher, the cost of pulling seems to be worse and worse. The patch therefore helps the wake-affine feature to stop its pulling work when: wakee->wakee_flips > factor && waker->wakee_flips > (factor * wakee->wakee_flips) The 'factor' here is the number of CPUs in the current CPU's NUMA node, so a bigger node will lead to more pulling since the trial becomes more severe. After applying the patch, pgbench shows up to 40% improvements and no regressions. Tested with 12 cpu x86 server and tip 3.10.0-rc7. The percentages in the final column highlight the areas with the biggest wins, all other areas improved as well: pgbench base smart | db_size | clients | tps | | tps | +---------+---------+-------+ +-------+ | 22 MB | 1 | 10598 | | 10796 | | 22 MB | 2 | 21257 | | 21336 | | 22 MB | 4 | 41386 | | 41622 | | 22 MB | 8 | 51253 | | 57932 | | 22 MB | 12 | 48570 | | 54000 | | 22 MB | 16 | 46748 | | 55982 | +19.75% | 22 MB | 24 | 44346 | | 55847 | +25.93% | 22 MB | 32 | 43460 | | 54614 | +25.66% | 7484 MB | 1 | 8951 | | 9193 | | 7484 MB | 2 | 19233 | | 19240 | | 7484 MB | 4 | 37239 | | 37302 | | 7484 MB | 8 | 46087 | | 50018 | | 7484 MB | 12 | 42054 | | 48763 | | 7484 MB | 16 | 40765 | | 51633 | +26.66% | 7484 MB | 24 | 37651 | | 52377 | +39.11% | 7484 MB | 32 | 37056 | | 51108 | +37.92% | 15 GB | 1 | 8845 | | 9104 | | 15 GB | 2 | 19094 | | 19162 | | 15 GB | 4 | 36979 | | 36983 | | 15 GB | 8 | 46087 | | 49977 | | 15 GB | 12 | 41901 | | 48591 | | 15 GB | 16 | 40147 | | 50651 | +26.16% | 15 GB | 24 | 37250 | | 52365 | +40.58% | 15 GB | 32 | 36470 | | 50015 | +37.14% Signed-off-by: Michael Wang Cc: Mike Galbraith Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com [ Improved the changelog. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ kernel/sched/fair.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 50d04b92ceda..4f163a8ffabf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1034,6 +1034,9 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; int on_cpu; + struct task_struct *last_wakee; + unsigned long wakee_flips; + unsigned long wakee_flip_decay_ts; #endif int on_rq; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 765d87acdf05..860063a8c849 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3017,6 +3017,23 @@ static unsigned long cpu_avg_load_per_task(int cpu) return 0; } +static void record_wakee(struct task_struct *p) +{ + /* + * Rough decay (wiping) for cost saving, don't worry + * about the boundary, really active task won't care + * about the loss. + */ + if (jiffies > current->wakee_flip_decay_ts + HZ) { + current->wakee_flips = 0; + current->wakee_flip_decay_ts = jiffies; + } + + if (current->last_wakee != p) { + current->last_wakee = p; + current->wakee_flips++; + } +} static void task_waking_fair(struct task_struct *p) { @@ -3037,6 +3054,7 @@ static void task_waking_fair(struct task_struct *p) #endif se->vruntime -= min_vruntime; + record_wakee(p); } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -3155,6 +3173,28 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu, #endif +static int wake_wide(struct task_struct *p) +{ + int factor = nr_cpus_node(cpu_to_node(smp_processor_id())); + + /* + * Yeah, it's the switching-frequency, could means many wakee or + * rapidly switch, use factor here will just help to automatically + * adjust the loose-degree, so bigger node will lead to more pull. + */ + if (p->wakee_flips > factor) { + /* + * wakee is somewhat hot, it needs certain amount of cpu + * resource, so if waker is far more hot, prefer to leave + * it alone. + */ + if (current->wakee_flips > (factor * p->wakee_flips)) + return 1; + } + + return 0; +} + static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) { s64 this_load, load; @@ -3164,6 +3204,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) unsigned long weight; int balanced; + /* + * If we wake multiple tasks be careful to not bounce + * ourselves around too much. + */ + if (wake_wide(p)) + return 0; + idx = sd->wake_idx; this_cpu = smp_processor_id(); prev_cpu = task_cpu(p); -- cgit v1.2.3-71-gd317 From 2753e6f8207355ab72574d48287cec187272a151 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 22 Jul 2013 17:15:52 +0200 Subject: regmap: irq: Allow to acknowledge masked interrupts during initialization In case the hardware interrupt mask register does not prevent the chip level irq from being asserted by the corresponding interrupt status bit, already set interrupt bits should to be cleared once after masking them during initialization. Add a flag to let drivers enable this behavior. Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 25 +++++++++++++++++++++++++ include/linux/regmap.h | 2 ++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 1643e889bafc..d10456ffd811 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -418,6 +418,31 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, reg, ret); goto err_alloc; } + + if (!chip->init_ack_masked) + continue; + + /* Ack masked but set interrupts */ + reg = chip->status_base + + (i * map->reg_stride * d->irq_reg_stride); + ret = regmap_read(map, reg, &d->status_buf[i]); + if (ret != 0) { + dev_err(map->dev, "Failed to read IRQ status: %d\n", + ret); + goto err_alloc; + } + + if (d->status_buf[i] && chip->ack_base) { + reg = chip->ack_base + + (i * map->reg_stride * d->irq_reg_stride); + ret = regmap_write(map, reg, + d->status_buf[i] & d->mask_buf[i]); + if (ret != 0) { + dev_err(map->dev, "Failed to ack 0x%x: %d\n", + reg, ret); + goto err_alloc; + } + } } /* Wake is disabled by default */ diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 75981d0b57dc..34ebe7778033 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -470,6 +470,7 @@ struct regmap_irq { * @ack_base: Base ack address. If zero then the chip is clear on read. * @wake_base: Base address for wake enables. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. + * @init_ack_masked: Ack all masked interrupts once during initalization. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. @@ -485,6 +486,7 @@ struct regmap_irq_chip { unsigned int ack_base; unsigned int wake_base; unsigned int irq_reg_stride; + bool init_ack_masked; unsigned int mask_invert; unsigned int wake_invert; bool runtime_pm; -- cgit v1.2.3-71-gd317 From 36697529b5bbe36911e39a6309e7a7c9250d280a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 07:04:48 -0400 Subject: tty: Replace ldisc locking with ldisc_sem Line discipline locking was performed with a combination of a mutex, a status bit, a count, and a waitqueue -- basically, a rw semaphore. Replace the existing combination with an ld_semaphore. Fixes: 1) the 'reference acquire after ldisc locked' bug 2) the over-complicated halt mechanism 3) lock order wrt. tty_lock() 4) dropping locks while changing ldisc 5) previously unidentified deadlock while locking ldisc from both linked ttys concurrently 6) previously unidentified recursive deadlocks Adds much-needed lockdep diagnostics. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 2 +- drivers/tty/tty_io.c | 7 +- drivers/tty/tty_ldisc.c | 329 +++++++--------------------------------------- include/linux/tty.h | 4 +- include/linux/tty_ldisc.h | 3 +- 5 files changed, 52 insertions(+), 293 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 9121c1f7aeef..a42a028a9d4e 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -429,7 +429,7 @@ static void flush_to_ldisc(struct work_struct *work) return; disc = tty_ldisc_ref(tty); - if (disc == NULL) /* !TTY_LDISC */ + if (disc == NULL) return; spin_lock_irqsave(&buf->lock, flags); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index fa80af3656a3..0fa5db4c7a7a 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1388,8 +1388,7 @@ static int tty_reopen(struct tty_struct *tty) struct tty_driver *driver = tty->driver; if (test_bit(TTY_CLOSING, &tty->flags) || - test_bit(TTY_HUPPING, &tty->flags) || - test_bit(TTY_LDISC_CHANGING, &tty->flags)) + test_bit(TTY_HUPPING, &tty->flags)) return -EIO; if (driver->type == TTY_DRIVER_TYPE_PTY && @@ -1405,7 +1404,7 @@ static int tty_reopen(struct tty_struct *tty) } tty->count++; - WARN_ON(!test_bit(TTY_LDISC, &tty->flags)); + WARN_ON(!tty->ldisc); return 0; } @@ -3017,7 +3016,7 @@ void initialize_tty_struct(struct tty_struct *tty, tty->pgrp = NULL; mutex_init(&tty->legacy_mutex); mutex_init(&tty->termios_mutex); - mutex_init(&tty->ldisc_mutex); + init_ldsem(&tty->ldisc_sem); init_waitqueue_head(&tty->write_wait); init_waitqueue_head(&tty->read_wait); INIT_WORK(&tty->hangup_work, do_tty_hangup); diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 418c9f64a9fd..b7b8048f1253 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -45,7 +45,6 @@ enum { */ static DEFINE_RAW_SPINLOCK(tty_ldiscs_lock); -static DECLARE_WAIT_QUEUE_HEAD(tty_ldisc_wait); /* Line disc dispatch table */ static struct tty_ldisc_ops *tty_ldiscs[NR_LDISCS]; @@ -153,7 +152,7 @@ static void put_ldops(struct tty_ldisc_ops *ldops) * takes tty_ldiscs_lock to guard against ldisc races */ -static struct tty_ldisc *tty_ldisc_get(int disc) +static struct tty_ldisc *tty_ldisc_get(struct tty_struct *tty, int disc) { struct tty_ldisc *ld; struct tty_ldisc_ops *ldops; @@ -180,8 +179,7 @@ static struct tty_ldisc *tty_ldisc_get(int disc) } ld->ops = ldops; - atomic_set(&ld->users, 1); - init_waitqueue_head(&ld->wq_idle); + ld->tty = tty; return ld; } @@ -193,20 +191,11 @@ static struct tty_ldisc *tty_ldisc_get(int disc) */ static inline void tty_ldisc_put(struct tty_ldisc *ld) { - unsigned long flags; - if (WARN_ON_ONCE(!ld)) return; - raw_spin_lock_irqsave(&tty_ldiscs_lock, flags); - - /* unreleased reader reference(s) will cause this WARN */ - WARN_ON(!atomic_dec_and_test(&ld->users)); - - ld->ops->refcount--; - module_put(ld->ops->owner); + put_ldops(ld->ops); kfree(ld); - raw_spin_unlock_irqrestore(&tty_ldiscs_lock, flags); } static void *tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos) @@ -257,34 +246,6 @@ const struct file_operations tty_ldiscs_proc_fops = { .release = seq_release, }; -/** - * tty_ldisc_try - internal helper - * @tty: the tty - * - * Make a single attempt to grab and bump the refcount on - * the tty ldisc. Return 0 on failure or 1 on success. This is - * used to implement both the waiting and non waiting versions - * of tty_ldisc_ref - * - * Locking: takes tty_ldiscs_lock - */ - -static struct tty_ldisc *tty_ldisc_try(struct tty_struct *tty) -{ - unsigned long flags; - struct tty_ldisc *ld; - - /* FIXME: this allows reference acquire after TTY_LDISC is cleared */ - raw_spin_lock_irqsave(&tty_ldiscs_lock, flags); - ld = NULL; - if (test_bit(TTY_LDISC, &tty->flags) && tty->ldisc) { - ld = tty->ldisc; - atomic_inc(&ld->users); - } - raw_spin_unlock_irqrestore(&tty_ldiscs_lock, flags); - return ld; -} - /** * tty_ldisc_ref_wait - wait for the tty ldisc * @tty: tty device @@ -298,16 +259,15 @@ static struct tty_ldisc *tty_ldisc_try(struct tty_struct *tty) * against a discipline change, such as an existing ldisc reference * (which we check for) * - * Locking: call functions take tty_ldiscs_lock + * Note: only callable from a file_operations routine (which + * guarantees tty->ldisc != NULL when the lock is acquired). */ struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *tty) { - struct tty_ldisc *ld; - - /* wait_event is a macro */ - wait_event(tty_ldisc_wait, (ld = tty_ldisc_try(tty)) != NULL); - return ld; + ldsem_down_read(&tty->ldisc_sem, MAX_SCHEDULE_TIMEOUT); + WARN_ON(!tty->ldisc); + return tty->ldisc; } EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait); @@ -318,13 +278,18 @@ EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait); * Dereference the line discipline for the terminal and take a * reference to it. If the line discipline is in flux then * return NULL. Can be called from IRQ and timer functions. - * - * Locking: called functions take tty_ldiscs_lock */ struct tty_ldisc *tty_ldisc_ref(struct tty_struct *tty) { - return tty_ldisc_try(tty); + struct tty_ldisc *ld = NULL; + + if (ldsem_down_read_trylock(&tty->ldisc_sem)) { + ld = tty->ldisc; + if (!ld) + ldsem_up_read(&tty->ldisc_sem); + } + return ld; } EXPORT_SYMBOL_GPL(tty_ldisc_ref); @@ -334,27 +299,11 @@ EXPORT_SYMBOL_GPL(tty_ldisc_ref); * * Undoes the effect of tty_ldisc_ref or tty_ldisc_ref_wait. May * be called in IRQ context. - * - * Locking: takes tty_ldiscs_lock */ void tty_ldisc_deref(struct tty_ldisc *ld) { - unsigned long flags; - - if (WARN_ON_ONCE(!ld)) - return; - - raw_spin_lock_irqsave(&tty_ldiscs_lock, flags); - /* - * WARNs if one-too-many reader references were released - * - the last reference must be released with tty_ldisc_put - */ - WARN_ON(atomic_dec_and_test(&ld->users)); - raw_spin_unlock_irqrestore(&tty_ldiscs_lock, flags); - - if (waitqueue_active(&ld->wq_idle)) - wake_up(&ld->wq_idle); + ldsem_up_read(&ld->tty->ldisc_sem); } EXPORT_SYMBOL_GPL(tty_ldisc_deref); @@ -437,27 +386,6 @@ static void __lockfunc tty_ldisc_enable_pair(struct tty_struct *tty, tty_ldisc_unlock_pair(tty, tty2); } - -/** - * tty_ldisc_enable - allow ldisc use - * @tty: terminal to activate ldisc on - * - * Set the TTY_LDISC flag when the line discipline can be called - * again. Do necessary wakeups for existing sleepers. Clear the LDISC - * changing flag to indicate any ldisc change is now over. - * - * Note: nobody should set the TTY_LDISC bit except via this function. - * Clearing directly is allowed. - */ - -static void tty_ldisc_enable(struct tty_struct *tty) -{ - clear_bit(TTY_LDISC_HALTED, &tty->flags); - set_bit(TTY_LDISC, &tty->flags); - clear_bit(TTY_LDISC_CHANGING, &tty->flags); - wake_up(&tty_ldisc_wait); -} - /** * tty_ldisc_flush - flush line discipline queue * @tty: tty @@ -555,14 +483,14 @@ static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old) int r; /* There is an outstanding reference here so this is safe */ - old = tty_ldisc_get(old->ops->num); + old = tty_ldisc_get(tty, old->ops->num); WARN_ON(IS_ERR(old)); tty->ldisc = old; tty_set_termios_ldisc(tty, old->ops->num); if (tty_ldisc_open(tty, old) < 0) { tty_ldisc_put(old); /* This driver is always present */ - new_ldisc = tty_ldisc_get(N_TTY); + new_ldisc = tty_ldisc_get(tty, N_TTY); if (IS_ERR(new_ldisc)) panic("n_tty: get"); tty->ldisc = new_ldisc; @@ -575,101 +503,6 @@ static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old) } } -/** - * tty_ldisc_wait_idle - wait for the ldisc to become idle - * @tty: tty to wait for - * @timeout: for how long to wait at most - * - * Wait for the line discipline to become idle. The discipline must - * have been halted for this to guarantee it remains idle. - */ -static int tty_ldisc_wait_idle(struct tty_struct *tty, long timeout) -{ - long ret; - ret = wait_event_timeout(tty->ldisc->wq_idle, - atomic_read(&tty->ldisc->users) == 1, timeout); - return ret > 0 ? 0 : -EBUSY; -} - -/** - * tty_ldisc_halt - shut down the line discipline - * @tty: tty device - * @o_tty: paired pty device (can be NULL) - * @timeout: # of jiffies to wait for ldisc refs to be released - * - * Shut down the line discipline and work queue for this tty device and - * its paired pty (if exists). Clearing the TTY_LDISC flag ensures - * no further references can be obtained, while waiting for existing - * references to be released ensures no more data is fed to the ldisc. - * - * You need to do a 'flush_scheduled_work()' (outside the ldisc_mutex) - * in order to make sure any currently executing ldisc work is also - * flushed. - */ - -static int tty_ldisc_halt(struct tty_struct *tty, struct tty_struct *o_tty, - long timeout) -{ - int retval; - - clear_bit(TTY_LDISC, &tty->flags); - if (o_tty) - clear_bit(TTY_LDISC, &o_tty->flags); - - retval = tty_ldisc_wait_idle(tty, timeout); - if (!retval && o_tty) - retval = tty_ldisc_wait_idle(o_tty, timeout); - if (retval) - return retval; - - set_bit(TTY_LDISC_HALTED, &tty->flags); - if (o_tty) - set_bit(TTY_LDISC_HALTED, &o_tty->flags); - - return 0; -} - -/** - * tty_ldisc_hangup_halt - halt the line discipline for hangup - * @tty: tty being hung up - * - * Shut down the line discipline and work queue for the tty device - * being hungup. Clear the TTY_LDISC flag to ensure no further - * references can be obtained and wait for remaining references to be - * released to ensure no more data is fed to this ldisc. - * Caller must hold legacy and ->ldisc_mutex. - * - * NB: tty_set_ldisc() is prevented from changing the ldisc concurrently - * with this function by checking the TTY_HUPPING flag. - */ -static bool tty_ldisc_hangup_halt(struct tty_struct *tty) -{ - char cur_n[TASK_COMM_LEN], tty_n[64]; - long timeout = 3 * HZ; - - clear_bit(TTY_LDISC, &tty->flags); - - if (tty->ldisc) { /* Not yet closed */ - tty_unlock(tty); - - while (tty_ldisc_wait_idle(tty, timeout) == -EBUSY) { - timeout = MAX_SCHEDULE_TIMEOUT; - printk_ratelimited(KERN_WARNING - "%s: waiting (%s) for %s took too long, but we keep waiting...\n", - __func__, get_task_comm(cur_n, current), - tty_name(tty, tty_n)); - } - - set_bit(TTY_LDISC_HALTED, &tty->flags); - - /* must reacquire both locks and preserve lock order */ - mutex_unlock(&tty->ldisc_mutex); - tty_lock(tty); - mutex_lock(&tty->ldisc_mutex); - } - return !!tty->ldisc; -} - /** * tty_set_ldisc - set line discipline * @tty: the terminal to set @@ -679,103 +512,47 @@ static bool tty_ldisc_hangup_halt(struct tty_struct *tty) * context. The ldisc change logic has to protect itself against any * overlapping ldisc change (including on the other end of pty pairs), * the close of one side of a tty/pty pair, and eventually hangup. - * - * Locking: takes tty_ldiscs_lock, termios_mutex */ int tty_set_ldisc(struct tty_struct *tty, int ldisc) { int retval; struct tty_ldisc *o_ldisc, *new_ldisc; - struct tty_struct *o_tty; + struct tty_struct *o_tty = tty->link; - new_ldisc = tty_ldisc_get(ldisc); + new_ldisc = tty_ldisc_get(tty, ldisc); if (IS_ERR(new_ldisc)) return PTR_ERR(new_ldisc); - tty_lock(tty); - /* - * We need to look at the tty locking here for pty/tty pairs - * when both sides try to change in parallel. - */ - - o_tty = tty->link; /* o_tty is the pty side or NULL */ - + retval = tty_ldisc_lock_pair_timeout(tty, o_tty, 5 * HZ); + if (retval) { + tty_ldisc_put(new_ldisc); + return retval; + } /* * Check the no-op case */ if (tty->ldisc->ops->num == ldisc) { - tty_unlock(tty); + tty_ldisc_enable_pair(tty, o_tty); tty_ldisc_put(new_ldisc); return 0; } - mutex_lock(&tty->ldisc_mutex); - - /* - * We could be midstream of another ldisc change which has - * dropped the lock during processing. If so we need to wait. - */ - - while (test_bit(TTY_LDISC_CHANGING, &tty->flags)) { - mutex_unlock(&tty->ldisc_mutex); - tty_unlock(tty); - wait_event(tty_ldisc_wait, - test_bit(TTY_LDISC_CHANGING, &tty->flags) == 0); - tty_lock(tty); - mutex_lock(&tty->ldisc_mutex); - } - - set_bit(TTY_LDISC_CHANGING, &tty->flags); - - /* - * No more input please, we are switching. The new ldisc - * will update this value in the ldisc open function - */ - + /* FIXME: why 'shutoff' input if the ldisc is locked? */ tty->receive_room = 0; o_ldisc = tty->ldisc; - - tty_unlock(tty); - /* - * Make sure we don't change while someone holds a - * reference to the line discipline. The TTY_LDISC bit - * prevents anyone taking a reference once it is clear. - * We need the lock to avoid racing reference takers. - * - * We must clear the TTY_LDISC bit here to avoid a livelock - * with a userspace app continually trying to use the tty in - * parallel to the change and re-referencing the tty. - */ - - retval = tty_ldisc_halt(tty, o_tty, 5 * HZ); - - /* - * Wait for hangup to complete, if pending. - * We must drop the mutex here in case a hangup is also in process. - */ - - mutex_unlock(&tty->ldisc_mutex); - - flush_work(&tty->hangup_work); - tty_lock(tty); - mutex_lock(&tty->ldisc_mutex); - /* handle wait idle failure locked */ - if (retval) { - tty_ldisc_put(new_ldisc); - goto enable; - } + /* FIXME: for testing only */ + WARN_ON(test_bit(TTY_HUPPED, &tty->flags)); if (test_bit(TTY_HUPPING, &tty->flags)) { /* We were raced by the hangup method. It will have stomped the ldisc data and closed the ldisc down */ - clear_bit(TTY_LDISC_CHANGING, &tty->flags); - mutex_unlock(&tty->ldisc_mutex); + tty_ldisc_enable_pair(tty, o_tty); tty_ldisc_put(new_ldisc); tty_unlock(tty); return -EIO; @@ -804,14 +581,10 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc) tty_ldisc_put(o_ldisc); -enable: /* * Allow ldisc referencing to occur again */ - - tty_ldisc_enable(tty); - if (o_tty) - tty_ldisc_enable(o_tty); + tty_ldisc_enable_pair(tty, o_tty); /* Restart the work queue in case no characters kick it off. Safe if already running */ @@ -819,7 +592,6 @@ enable: if (o_tty) schedule_work(&o_tty->port->buf.work); - mutex_unlock(&tty->ldisc_mutex); tty_unlock(tty); return retval; } @@ -852,7 +624,7 @@ static void tty_reset_termios(struct tty_struct *tty) static int tty_ldisc_reinit(struct tty_struct *tty, int ldisc) { - struct tty_ldisc *ld = tty_ldisc_get(ldisc); + struct tty_ldisc *ld = tty_ldisc_get(tty, ldisc); if (IS_ERR(ld)) return -1; @@ -891,14 +663,8 @@ void tty_ldisc_hangup(struct tty_struct *tty) tty_ldisc_debug(tty, "closing ldisc: %p\n", tty->ldisc); - /* - * FIXME! What are the locking issues here? This may me overdoing - * things... This question is especially important now that we've - * removed the irqlock. - */ ld = tty_ldisc_ref(tty); if (ld != NULL) { - /* We may have no line discipline at this point */ if (ld->ops->flush_buffer) ld->ops->flush_buffer(tty); tty_driver_flush_buffer(tty); @@ -909,21 +675,22 @@ void tty_ldisc_hangup(struct tty_struct *tty) ld->ops->hangup(tty); tty_ldisc_deref(ld); } - /* - * FIXME: Once we trust the LDISC code better we can wait here for - * ldisc completion and fix the driver call race - */ + wake_up_interruptible_poll(&tty->write_wait, POLLOUT); wake_up_interruptible_poll(&tty->read_wait, POLLIN); + + tty_unlock(tty); + /* * Shutdown the current line discipline, and reset it to * N_TTY if need be. * * Avoid racing set_ldisc or tty_ldisc_release */ - mutex_lock(&tty->ldisc_mutex); + tty_ldisc_lock_pair(tty, tty->link); + tty_lock(tty); - if (tty_ldisc_hangup_halt(tty)) { + if (tty->ldisc) { /* At this point we have a halted ldisc; we want to close it and reopen a new ldisc. We could defer the reopen to the next @@ -942,9 +709,8 @@ void tty_ldisc_hangup(struct tty_struct *tty) BUG_ON(tty_ldisc_reinit(tty, N_TTY)); WARN_ON(tty_ldisc_open(tty, tty->ldisc)); } - tty_ldisc_enable(tty); } - mutex_unlock(&tty->ldisc_mutex); + tty_ldisc_enable_pair(tty, tty->link); if (reset) tty_reset_termios(tty); @@ -976,15 +742,12 @@ int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty) tty_ldisc_close(tty, ld); return retval; } - tty_ldisc_enable(o_tty); } - tty_ldisc_enable(tty); return 0; } static void tty_ldisc_kill(struct tty_struct *tty) { - mutex_lock(&tty->ldisc_mutex); /* * Now kill off the ldisc */ @@ -995,7 +758,6 @@ static void tty_ldisc_kill(struct tty_struct *tty) /* Ensure the next open requests the N_TTY ldisc */ tty_set_termios_ldisc(tty, N_TTY); - mutex_unlock(&tty->ldisc_mutex); } /** @@ -1017,15 +779,16 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty) tty_ldisc_debug(tty, "closing ldisc: %p\n", tty->ldisc); - tty_ldisc_halt(tty, o_tty, MAX_SCHEDULE_TIMEOUT); - + tty_ldisc_lock_pair(tty, o_tty); tty_lock_pair(tty, o_tty); - /* This will need doing differently if we need to lock */ + tty_ldisc_kill(tty); if (o_tty) tty_ldisc_kill(o_tty); tty_unlock_pair(tty, o_tty); + tty_ldisc_unlock_pair(tty, o_tty); + /* And the memory resources remaining (buffers, termios) will be disposed of when the kref hits zero */ @@ -1042,7 +805,7 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty) void tty_ldisc_init(struct tty_struct *tty) { - struct tty_ldisc *ld = tty_ldisc_get(N_TTY); + struct tty_ldisc *ld = tty_ldisc_get(tty, N_TTY); if (IS_ERR(ld)) panic("n_tty: init_tty"); tty->ldisc = ld; diff --git a/include/linux/tty.h b/include/linux/tty.h index 01ac30efd6a6..7269daf7632b 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -238,7 +238,7 @@ struct tty_struct { int index; /* Protects ldisc changes: Lock tty not pty */ - struct mutex ldisc_mutex; + struct ld_semaphore ldisc_sem; struct tty_ldisc *ldisc; struct mutex atomic_write_lock; @@ -305,8 +305,6 @@ struct tty_file_private { #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ #define TTY_PUSH 6 /* n_tty private */ #define TTY_CLOSING 7 /* ->close() in progress */ -#define TTY_LDISC 9 /* Line discipline attached */ -#define TTY_LDISC_CHANGING 10 /* Line discipline changing */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ #define TTY_PTY_LOCK 16 /* pty private */ #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index a1b048999821..23bdd9debb84 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -203,8 +203,7 @@ struct tty_ldisc_ops { struct tty_ldisc { struct tty_ldisc_ops *ops; - atomic_t users; - wait_queue_head_t wq_idle; + struct tty_struct *tty; }; #define TTY_LDISC_MAGIC 0x5403 -- cgit v1.2.3-71-gd317 From 24a89d1cb69b6c488cf16d98dd02e7820f62b40c Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:15 -0400 Subject: tty: Make ldisc input flow control concurrency-friendly Although line discipline receiving is single-producer/single-consumer, using tty->receive_room to manage flow control creates unnecessary critical regions requiring additional lock use. Instead, introduce the optional .receive_buf2() ldisc method which returns the # of bytes actually received. Serialization is guaranteed by the caller. In turn, the line discipline should schedule the buffer work item whenever space becomes available; ie., when there is room to receive data and receive_room() previously returned 0 (the buffer work item stops processing if receive_buf2() returns 0). Note the 'no room' state need not be atomic despite concurrent use by two threads because only the buffer work thread can set the state and only the read() thread can clear the state. Add n_tty_receive_buf2() as the receive_buf2() method for N_TTY. Provide a public helper function, tty_ldisc_receive_buf(), to use when directly accessing the receive_buf() methods. Line disciplines not using input flow control can continue to set tty->receive_room to a fixed value and only provide the receive_buf() method. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 72 +++++++++++++++++++++++++++++----------------- drivers/tty/tty_buffer.c | 13 ++++++--- drivers/tty/vt/selection.c | 4 +-- include/linux/tty.h | 13 +++++++++ include/linux/tty_ldisc.h | 13 +++++++++ 5 files changed, 82 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 4bf0fc0843d7..eddeb7889e62 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -79,6 +79,9 @@ struct n_tty_data { unsigned long overrun_time; int num_overrun; + /* non-atomic */ + bool no_room; + unsigned char lnext:1, erasing:1, raw:1, real_raw:1, icanon:1; unsigned char echo_overrun:1; @@ -114,25 +117,10 @@ static inline int tty_put_user(struct tty_struct *tty, unsigned char x, return put_user(x, ptr); } -/** - * n_tty_set_room - receive space - * @tty: terminal - * - * Updates tty->receive_room to reflect the currently available space - * in the input buffer, and re-schedules the flip buffer work if space - * just became available. - * - * Locks: Concurrent update is protected with read_lock - */ - -static int set_room(struct tty_struct *tty) +static int receive_room(struct tty_struct *tty) { struct n_tty_data *ldata = tty->disc_data; int left; - int old_left; - unsigned long flags; - - raw_spin_lock_irqsave(&ldata->read_lock, flags); if (I_PARMRK(tty)) { /* Multiply read_cnt by 3, since each byte might take up to @@ -150,18 +138,27 @@ static int set_room(struct tty_struct *tty) */ if (left <= 0) left = ldata->icanon && !ldata->canon_data; - old_left = tty->receive_room; - tty->receive_room = left; - raw_spin_unlock_irqrestore(&ldata->read_lock, flags); - - return left && !old_left; + return left; } +/** + * n_tty_set_room - receive space + * @tty: terminal + * + * Re-schedules the flip buffer work if space just became available. + * + * Locks: Concurrent update is protected with read_lock + */ + static void n_tty_set_room(struct tty_struct *tty) { + struct n_tty_data *ldata = tty->disc_data; + /* Did this open up the receive buffer? We may need to flip */ - if (set_room(tty)) { + if (unlikely(ldata->no_room) && receive_room(tty)) { + ldata->no_room = 0; + WARN_RATELIMIT(tty->port->itty == NULL, "scheduling with invalid itty\n"); /* see if ldisc has been killed - if so, this means that @@ -1408,8 +1405,8 @@ static void n_tty_write_wakeup(struct tty_struct *tty) * calls one at a time and in order (or using flush_to_ldisc) */ -static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp, - char *fp, int count) +static void __receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) { struct n_tty_data *ldata = tty->disc_data; const unsigned char *p; @@ -1464,8 +1461,6 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp, tty->ops->flush_chars(tty); } - set_room(tty); - if ((!ldata->icanon && (ldata->read_cnt >= ldata->minimum_to_wake)) || L_EXTPROC(tty)) { kill_fasync(&tty->fasync, SIGIO, POLL_IN); @@ -1480,7 +1475,7 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp, */ while (1) { tty_set_flow_change(tty, TTY_THROTTLE_SAFE); - if (tty->receive_room >= TTY_THRESHOLD_THROTTLE) + if (receive_room(tty) >= TTY_THRESHOLD_THROTTLE) break; if (!tty_throttle_safe(tty)) break; @@ -1488,6 +1483,28 @@ static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp, __tty_set_flow_change(tty, 0); } +static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) +{ + __receive_buf(tty, cp, fp, count); +} + +static int n_tty_receive_buf2(struct tty_struct *tty, const unsigned char *cp, + char *fp, int count) +{ + struct n_tty_data *ldata = tty->disc_data; + int room; + + tty->receive_room = room = receive_room(tty); + if (!room) + ldata->no_room = 1; + count = min(count, room); + if (count) + __receive_buf(tty, cp, fp, count); + + return count; +} + int is_ignored(int sig) { return (sigismember(¤t->blocked, sig) || @@ -2203,6 +2220,7 @@ struct tty_ldisc_ops tty_ldisc_N_TTY = { .receive_buf = n_tty_receive_buf, .write_wakeup = n_tty_write_wakeup, .fasync = n_tty_fasync, + .receive_buf2 = n_tty_receive_buf2, }; /** diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 6c7a1d043c76..ff1b2e37c3ca 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -407,11 +407,16 @@ static int receive_buf(struct tty_struct *tty, struct tty_buffer *head, int count) { struct tty_ldisc *disc = tty->ldisc; + char *p = head->char_buf_ptr + head->read; + unsigned char *f = head->flag_buf_ptr + head->read; - count = min_t(int, count, tty->receive_room); - if (count) - disc->ops->receive_buf(tty, head->char_buf_ptr + head->read, - head->flag_buf_ptr + head->read, count); + if (disc->ops->receive_buf2) + count = disc->ops->receive_buf2(tty, p, f, count); + else { + count = min_t(int, count, tty->receive_room); + if (count) + disc->ops->receive_buf(tty, p, f, count); + } head->read += count; return count; } diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 60b7b6926059..2ca8d6b6514c 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -356,8 +356,8 @@ int paste_selection(struct tty_struct *tty) continue; } count = sel_buffer_lth - pasted; - count = min(count, tty->receive_room); - ld->ops->receive_buf(tty, sel_buffer + pasted, NULL, count); + count = tty_ldisc_receive_buf(ld, sel_buffer + pasted, NULL, + count); pasted += count; } remove_wait_queue(&vc->paste_wait, &wait); diff --git a/include/linux/tty.h b/include/linux/tty.h index 7269daf7632b..8323ee4f95b9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -557,6 +557,19 @@ extern void tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); extern void tty_ldisc_begin(void); +static inline int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p, + char *f, int count) +{ + if (ld->ops->receive_buf2) + count = ld->ops->receive_buf2(ld->tty, p, f, count); + else { + count = min_t(int, count, ld->tty->receive_room); + if (count) + ld->ops->receive_buf(ld->tty, p, f, count); + } + return count; +} + /* n_tty.c */ extern struct tty_ldisc_ops tty_ldisc_N_TTY; diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 23bdd9debb84..f15c898ff462 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -109,6 +109,17 @@ * * Tells the discipline that the DCD pin has changed its status. * Used exclusively by the N_PPS (Pulse-Per-Second) line discipline. + * + * int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + * char *fp, int count); + * + * This function is called by the low-level tty driver to send + * characters received by the hardware to the line discpline for + * processing. is a pointer to the buffer of input + * character received by the device. is a pointer to a + * pointer of flag bytes which indicate whether a character was + * received with a parity error, etc. + * If assigned, prefer this function for automatic flow control. */ #include @@ -195,6 +206,8 @@ struct tty_ldisc_ops { void (*write_wakeup)(struct tty_struct *); void (*dcd_change)(struct tty_struct *, unsigned int); void (*fasync)(struct tty_struct *tty, int on); + int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + char *fp, int count); struct module *owner; -- cgit v1.2.3-71-gd317 From 6a1c0680cf3ba94356ecd58833e1540c93472a57 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:23 -0400 Subject: tty: Convert termios_mutex to termios_rwsem termios is commonly accessed unsafely (especially by N_TTY) because the existing mutex forces exclusive access. Convert existing usage. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/net/irda/irtty-sir.c | 8 ++-- drivers/tty/n_tty.c | 2 +- drivers/tty/pty.c | 4 +- drivers/tty/tty_io.c | 14 +++---- drivers/tty/tty_ioctl.c | 90 ++++++++++++++++++++++---------------------- drivers/tty/tty_ldisc.c | 10 ++--- drivers/tty/vt/vt.c | 4 +- include/linux/tty.h | 7 ++-- 8 files changed, 70 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c index a41267197839..177441afeb96 100644 --- a/drivers/net/irda/irtty-sir.c +++ b/drivers/net/irda/irtty-sir.c @@ -123,14 +123,14 @@ static int irtty_change_speed(struct sir_dev *dev, unsigned speed) tty = priv->tty; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); old_termios = tty->termios; cflag = tty->termios.c_cflag; tty_encode_baud_rate(tty, speed, speed); if (tty->ops->set_termios) tty->ops->set_termios(tty, &old_termios); priv->io.speed = speed; - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return 0; } @@ -280,7 +280,7 @@ static inline void irtty_stop_receiver(struct tty_struct *tty, int stop) struct ktermios old_termios; int cflag; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); old_termios = tty->termios; cflag = tty->termios.c_cflag; @@ -292,7 +292,7 @@ static inline void irtty_stop_receiver(struct tty_struct *tty, int stop) tty->termios.c_cflag = cflag; if (tty->ops->set_termios) tty->ops->set_termios(tty, &old_termios); - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); } /*****************************************************************/ diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index d159059560e8..ab923bb2b262 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1539,7 +1539,7 @@ int is_ignored(int sig) * guaranteed that this function will not be re-entered or in progress * when the ldisc is closed. * - * Locking: Caller holds tty->termios_mutex + * Locking: Caller holds tty->termios_rwsem */ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index abfd99089781..1b39dd639ee9 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -287,7 +287,7 @@ static int pty_resize(struct tty_struct *tty, struct winsize *ws) struct tty_struct *pty = tty->link; /* For a PTY we need to lock the tty side */ - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) goto done; @@ -314,7 +314,7 @@ static int pty_resize(struct tty_struct *tty, struct winsize *ws) tty->winsize = *ws; pty->winsize = *ws; /* Never used so will go away soon */ done: - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return 0; } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 0fa5db4c7a7a..639e24ade9bf 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -604,7 +604,7 @@ static int tty_signal_session_leader(struct tty_struct *tty, int exit_session) * redirect lock for undoing redirection * file list lock for manipulating list of ttys * tty_ldiscs_lock from called functions - * termios_mutex resetting termios data + * termios_rwsem resetting termios data * tasklist_lock to walk task list for hangup event * ->siglock to protect ->signal/->sighand */ @@ -2230,7 +2230,7 @@ static int tiocsti(struct tty_struct *tty, char __user *p) * * Copies the kernel idea of the window size into the user buffer. * - * Locking: tty->termios_mutex is taken to ensure the winsize data + * Locking: tty->termios_rwsem is taken to ensure the winsize data * is consistent. */ @@ -2238,9 +2238,9 @@ static int tiocgwinsz(struct tty_struct *tty, struct winsize __user *arg) { int err; - mutex_lock(&tty->termios_mutex); + down_read(&tty->termios_rwsem); err = copy_to_user(arg, &tty->winsize, sizeof(*arg)); - mutex_unlock(&tty->termios_mutex); + up_read(&tty->termios_rwsem); return err ? -EFAULT: 0; } @@ -2261,7 +2261,7 @@ int tty_do_resize(struct tty_struct *tty, struct winsize *ws) unsigned long flags; /* Lock the tty */ - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) goto done; /* Get the PID values and reference them so we can @@ -2276,7 +2276,7 @@ int tty_do_resize(struct tty_struct *tty, struct winsize *ws) tty->winsize = *ws; done: - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return 0; } EXPORT_SYMBOL(tty_do_resize); @@ -3015,7 +3015,7 @@ void initialize_tty_struct(struct tty_struct *tty, tty->session = NULL; tty->pgrp = NULL; mutex_init(&tty->legacy_mutex); - mutex_init(&tty->termios_mutex); + init_rwsem(&tty->termios_rwsem); init_ldsem(&tty->ldisc_sem); init_waitqueue_head(&tty->write_wait); init_waitqueue_head(&tty->read_wait); diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 3500d4114147..9ce20df8a2c8 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -94,20 +94,20 @@ EXPORT_SYMBOL(tty_driver_flush_buffer); * @tty: terminal * * Indicate that a tty should stop transmitting data down the stack. - * Takes the termios mutex to protect against parallel throttle/unthrottle + * Takes the termios rwsem to protect against parallel throttle/unthrottle * and also to ensure the driver can consistently reference its own * termios data at this point when implementing software flow control. */ void tty_throttle(struct tty_struct *tty) { - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); /* check TTY_THROTTLED first so it indicates our state */ if (!test_and_set_bit(TTY_THROTTLED, &tty->flags) && tty->ops->throttle) tty->ops->throttle(tty); tty->flow_change = 0; - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); } EXPORT_SYMBOL(tty_throttle); @@ -116,7 +116,7 @@ EXPORT_SYMBOL(tty_throttle); * @tty: terminal * * Indicate that a tty may continue transmitting data down the stack. - * Takes the termios mutex to protect against parallel throttle/unthrottle + * Takes the termios rwsem to protect against parallel throttle/unthrottle * and also to ensure the driver can consistently reference its own * termios data at this point when implementing software flow control. * @@ -126,12 +126,12 @@ EXPORT_SYMBOL(tty_throttle); void tty_unthrottle(struct tty_struct *tty) { - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); if (test_and_clear_bit(TTY_THROTTLED, &tty->flags) && tty->ops->unthrottle) tty->ops->unthrottle(tty); tty->flow_change = 0; - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); } EXPORT_SYMBOL(tty_unthrottle); @@ -151,7 +151,7 @@ int tty_throttle_safe(struct tty_struct *tty) { int ret = 0; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); if (!test_bit(TTY_THROTTLED, &tty->flags)) { if (tty->flow_change != TTY_THROTTLE_SAFE) ret = 1; @@ -161,7 +161,7 @@ int tty_throttle_safe(struct tty_struct *tty) tty->ops->throttle(tty); } } - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return ret; } @@ -182,7 +182,7 @@ int tty_unthrottle_safe(struct tty_struct *tty) { int ret = 0; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); if (test_bit(TTY_THROTTLED, &tty->flags)) { if (tty->flow_change != TTY_UNTHROTTLE_SAFE) ret = 1; @@ -192,7 +192,7 @@ int tty_unthrottle_safe(struct tty_struct *tty) tty->ops->unthrottle(tty); } } - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return ret; } @@ -468,7 +468,7 @@ EXPORT_SYMBOL_GPL(tty_termios_encode_baud_rate); * @obad: output baud rate * * Update the current termios data for the tty with the new speed - * settings. The caller must hold the termios_mutex for the tty in + * settings. The caller must hold the termios_rwsem for the tty in * question. */ @@ -528,7 +528,7 @@ EXPORT_SYMBOL(tty_termios_hw_change); * is a bit of layering violation here with n_tty in terms of the * internal knowledge of this function. * - * Locking: termios_mutex + * Locking: termios_rwsem */ int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) @@ -544,7 +544,7 @@ int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) /* FIXME: we need to decide on some locking/ordering semantics for the set_termios notification eventually */ - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); old_termios = tty->termios; tty->termios = *new_termios; unset_locked_termios(&tty->termios, &old_termios, &tty->termios_locked); @@ -586,7 +586,7 @@ int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) (ld->ops->set_termios)(tty, &old_termios); tty_ldisc_deref(ld); } - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return 0; } EXPORT_SYMBOL_GPL(tty_set_termios); @@ -601,7 +601,7 @@ EXPORT_SYMBOL_GPL(tty_set_termios); * functions before using tty_set_termios to do the actual changes. * * Locking: - * Called functions take ldisc and termios_mutex locks + * Called functions take ldisc and termios_rwsem locks */ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) @@ -613,9 +613,9 @@ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) if (retval) return retval; - mutex_lock(&tty->termios_mutex); + down_read(&tty->termios_rwsem); tmp_termios = tty->termios; - mutex_unlock(&tty->termios_mutex); + up_read(&tty->termios_rwsem); if (opt & TERMIOS_TERMIO) { if (user_termio_to_kernel_termios(&tmp_termios, @@ -667,16 +667,16 @@ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) static void copy_termios(struct tty_struct *tty, struct ktermios *kterm) { - mutex_lock(&tty->termios_mutex); + down_read(&tty->termios_rwsem); *kterm = tty->termios; - mutex_unlock(&tty->termios_mutex); + up_read(&tty->termios_rwsem); } static void copy_termios_locked(struct tty_struct *tty, struct ktermios *kterm) { - mutex_lock(&tty->termios_mutex); + down_read(&tty->termios_rwsem); *kterm = tty->termios_locked; - mutex_unlock(&tty->termios_mutex); + up_read(&tty->termios_rwsem); } static int get_termio(struct tty_struct *tty, struct termio __user *termio) @@ -723,10 +723,10 @@ static int set_termiox(struct tty_struct *tty, void __user *arg, int opt) return -ERESTARTSYS; } - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); if (tty->ops->set_termiox) tty->ops->set_termiox(tty, &tnew); - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return 0; } @@ -761,13 +761,13 @@ static int get_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) { struct sgttyb tmp; - mutex_lock(&tty->termios_mutex); + down_read(&tty->termios_rwsem); tmp.sg_ispeed = tty->termios.c_ispeed; tmp.sg_ospeed = tty->termios.c_ospeed; tmp.sg_erase = tty->termios.c_cc[VERASE]; tmp.sg_kill = tty->termios.c_cc[VKILL]; tmp.sg_flags = get_sgflags(tty); - mutex_unlock(&tty->termios_mutex); + up_read(&tty->termios_rwsem); return copy_to_user(sgttyb, &tmp, sizeof(tmp)) ? -EFAULT : 0; } @@ -806,7 +806,7 @@ static void set_sgflags(struct ktermios *termios, int flags) * Updates a terminal from the legacy BSD style terminal information * structure. * - * Locking: termios_mutex + * Locking: termios_rwsem */ static int set_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) @@ -822,7 +822,7 @@ static int set_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) if (copy_from_user(&tmp, sgttyb, sizeof(tmp))) return -EFAULT; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); termios = tty->termios; termios.c_cc[VERASE] = tmp.sg_erase; termios.c_cc[VKILL] = tmp.sg_kill; @@ -832,7 +832,7 @@ static int set_sgttyb(struct tty_struct *tty, struct sgttyb __user *sgttyb) tty_termios_encode_baud_rate(&termios, termios.c_ispeed, termios.c_ospeed); #endif - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); tty_set_termios(tty, &termios); return 0; } @@ -843,14 +843,14 @@ static int get_tchars(struct tty_struct *tty, struct tchars __user *tchars) { struct tchars tmp; - mutex_lock(&tty->termios_mutex); + down_read(&tty->termios_rwsem); tmp.t_intrc = tty->termios.c_cc[VINTR]; tmp.t_quitc = tty->termios.c_cc[VQUIT]; tmp.t_startc = tty->termios.c_cc[VSTART]; tmp.t_stopc = tty->termios.c_cc[VSTOP]; tmp.t_eofc = tty->termios.c_cc[VEOF]; tmp.t_brkc = tty->termios.c_cc[VEOL2]; /* what is brkc anyway? */ - mutex_unlock(&tty->termios_mutex); + up_read(&tty->termios_rwsem); return copy_to_user(tchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } @@ -860,14 +860,14 @@ static int set_tchars(struct tty_struct *tty, struct tchars __user *tchars) if (copy_from_user(&tmp, tchars, sizeof(tmp))) return -EFAULT; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); tty->termios.c_cc[VINTR] = tmp.t_intrc; tty->termios.c_cc[VQUIT] = tmp.t_quitc; tty->termios.c_cc[VSTART] = tmp.t_startc; tty->termios.c_cc[VSTOP] = tmp.t_stopc; tty->termios.c_cc[VEOF] = tmp.t_eofc; tty->termios.c_cc[VEOL2] = tmp.t_brkc; /* what is brkc anyway? */ - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return 0; } #endif @@ -877,7 +877,7 @@ static int get_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) { struct ltchars tmp; - mutex_lock(&tty->termios_mutex); + down_read(&tty->termios_rwsem); tmp.t_suspc = tty->termios.c_cc[VSUSP]; /* what is dsuspc anyway? */ tmp.t_dsuspc = tty->termios.c_cc[VSUSP]; @@ -886,7 +886,7 @@ static int get_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) tmp.t_flushc = tty->termios.c_cc[VEOL2]; tmp.t_werasc = tty->termios.c_cc[VWERASE]; tmp.t_lnextc = tty->termios.c_cc[VLNEXT]; - mutex_unlock(&tty->termios_mutex); + up_read(&tty->termios_rwsem); return copy_to_user(ltchars, &tmp, sizeof(tmp)) ? -EFAULT : 0; } @@ -897,7 +897,7 @@ static int set_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) if (copy_from_user(&tmp, ltchars, sizeof(tmp))) return -EFAULT; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); tty->termios.c_cc[VSUSP] = tmp.t_suspc; /* what is dsuspc anyway? */ tty->termios.c_cc[VEOL2] = tmp.t_dsuspc; @@ -906,7 +906,7 @@ static int set_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars) tty->termios.c_cc[VEOL2] = tmp.t_flushc; tty->termios.c_cc[VWERASE] = tmp.t_werasc; tty->termios.c_cc[VLNEXT] = tmp.t_lnextc; - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return 0; } #endif @@ -946,7 +946,7 @@ static int send_prio_char(struct tty_struct *tty, char ch) * @arg: enable/disable CLOCAL * * Perform a change to the CLOCAL state and call into the driver - * layer to make it visible. All done with the termios mutex + * layer to make it visible. All done with the termios rwsem */ static int tty_change_softcar(struct tty_struct *tty, int arg) @@ -955,7 +955,7 @@ static int tty_change_softcar(struct tty_struct *tty, int arg) int bit = arg ? CLOCAL : 0; struct ktermios old; - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); old = tty->termios; tty->termios.c_cflag &= ~CLOCAL; tty->termios.c_cflag |= bit; @@ -963,7 +963,7 @@ static int tty_change_softcar(struct tty_struct *tty, int arg) tty->ops->set_termios(tty, &old); if ((tty->termios.c_cflag & CLOCAL) != bit) ret = -EINVAL; - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); return ret; } @@ -1066,9 +1066,9 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file, if (user_termios_to_kernel_termios(&kterm, (struct termios __user *) arg)) return -EFAULT; - mutex_lock(&real_tty->termios_mutex); + down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; - mutex_unlock(&real_tty->termios_mutex); + up_write(&real_tty->termios_rwsem); return 0; #else case TIOCGLCKTRMIOS: @@ -1083,9 +1083,9 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file, if (user_termios_to_kernel_termios_1(&kterm, (struct termios __user *) arg)) return -EFAULT; - mutex_lock(&real_tty->termios_mutex); + down_write(&real_tty->termios_rwsem); real_tty->termios_locked = kterm; - mutex_unlock(&real_tty->termios_mutex); + up_write(&real_tty->termios_rwsem); return ret; #endif #ifdef TCGETX @@ -1093,9 +1093,9 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file, struct termiox ktermx; if (real_tty->termiox == NULL) return -EINVAL; - mutex_lock(&real_tty->termios_mutex); + down_read(&real_tty->termios_rwsem); memcpy(&ktermx, real_tty->termiox, sizeof(struct termiox)); - mutex_unlock(&real_tty->termios_mutex); + up_read(&real_tty->termios_rwsem); if (copy_to_user(p, &ktermx, sizeof(struct termiox))) ret = -EFAULT; return ret; diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index e52d61573553..6458e11e8e9d 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -415,14 +415,14 @@ EXPORT_SYMBOL_GPL(tty_ldisc_flush); * they are not on hot paths so a little discipline won't do * any harm. * - * Locking: takes termios_mutex + * Locking: takes termios_rwsem */ static void tty_set_termios_ldisc(struct tty_struct *tty, int num) { - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); tty->termios.c_line = num; - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); } /** @@ -602,11 +602,11 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc) static void tty_reset_termios(struct tty_struct *tty) { - mutex_lock(&tty->termios_mutex); + down_write(&tty->termios_rwsem); tty->termios = tty->driver->init_termios; tty->termios.c_ispeed = tty_termios_input_baud_rate(&tty->termios); tty->termios.c_ospeed = tty_termios_baud_rate(&tty->termios); - mutex_unlock(&tty->termios_mutex); + up_write(&tty->termios_rwsem); } diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index c677829baa8b..02af6ccefe6a 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -828,7 +828,7 @@ static inline int resize_screen(struct vc_data *vc, int width, int height, * If the caller passes a tty structure then update the termios winsize * information and perform any necessary signal handling. * - * Caller must hold the console semaphore. Takes the termios mutex and + * Caller must hold the console semaphore. Takes the termios rwsem and * ctrl_lock of the tty IFF a tty is passed. */ @@ -972,7 +972,7 @@ int vc_resize(struct vc_data *vc, unsigned int cols, unsigned int rows) * the actual work. * * Takes the console sem and the called methods then take the tty - * termios_mutex and the tty ctrl_lock in that order. + * termios_rwsem and the tty ctrl_lock in that order. */ static int vt_resize(struct tty_struct *tty, struct winsize *ws) { diff --git a/include/linux/tty.h b/include/linux/tty.h index 8323ee4f95b9..d3042076d163 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -10,6 +10,7 @@ #include #include #include +#include @@ -243,9 +244,9 @@ struct tty_struct { struct mutex atomic_write_lock; struct mutex legacy_mutex; - struct mutex termios_mutex; + struct rw_semaphore termios_rwsem; spinlock_t ctrl_lock; - /* Termios values are protected by the termios mutex */ + /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; struct termiox *termiox; /* May be NULL for unsupported */ char name[64]; @@ -253,7 +254,7 @@ struct tty_struct { struct pid *session; unsigned long flags; int count; - struct winsize winsize; /* termios mutex */ + struct winsize winsize; /* termios rwsem */ unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ -- cgit v1.2.3-71-gd317 From d8c1f929aa8164cd8eaa830068d2fa3159c0764a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:14:31 -0400 Subject: tty: Only guarantee termios read safety for throttle/unthrottle No tty driver modifies termios during throttle() or unthrottle(). Therefore, only read safety is required. However, tty_throttle_safe and tty_unthrottle_safe must still be mutually exclusive; introduce throttle_mutex for that purpose. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 4 ---- drivers/tty/tty_io.c | 1 + drivers/tty/tty_ioctl.c | 8 ++++---- include/linux/tty.h | 1 + 4 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index d0c8805d8131..b78ee464bd09 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1518,9 +1518,7 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp, tty_set_flow_change(tty, TTY_THROTTLE_SAFE); if (receive_room(tty) >= TTY_THRESHOLD_THROTTLE) break; - up_read(&tty->termios_rwsem); throttled = tty_throttle_safe(tty); - down_read(&tty->termios_rwsem); if (!throttled) break; } @@ -2086,9 +2084,7 @@ do_it_again: if (!tty->count) break; n_tty_set_room(tty); - up_read(&tty->termios_rwsem); unthrottled = tty_unthrottle_safe(tty); - down_read(&tty->termios_rwsem); if (!unthrottled) break; } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 639e24ade9bf..1b32da6f6cdd 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3015,6 +3015,7 @@ void initialize_tty_struct(struct tty_struct *tty, tty->session = NULL; tty->pgrp = NULL; mutex_init(&tty->legacy_mutex); + mutex_init(&tty->throttle_mutex); init_rwsem(&tty->termios_rwsem); init_ldsem(&tty->ldisc_sem); init_waitqueue_head(&tty->write_wait); diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 9ce20df8a2c8..03ba081c5772 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -151,7 +151,7 @@ int tty_throttle_safe(struct tty_struct *tty) { int ret = 0; - down_write(&tty->termios_rwsem); + mutex_lock(&tty->throttle_mutex); if (!test_bit(TTY_THROTTLED, &tty->flags)) { if (tty->flow_change != TTY_THROTTLE_SAFE) ret = 1; @@ -161,7 +161,7 @@ int tty_throttle_safe(struct tty_struct *tty) tty->ops->throttle(tty); } } - up_write(&tty->termios_rwsem); + mutex_unlock(&tty->throttle_mutex); return ret; } @@ -182,7 +182,7 @@ int tty_unthrottle_safe(struct tty_struct *tty) { int ret = 0; - down_write(&tty->termios_rwsem); + mutex_lock(&tty->throttle_mutex); if (test_bit(TTY_THROTTLED, &tty->flags)) { if (tty->flow_change != TTY_UNTHROTTLE_SAFE) ret = 1; @@ -192,7 +192,7 @@ int tty_unthrottle_safe(struct tty_struct *tty) tty->ops->unthrottle(tty); } } - up_write(&tty->termios_rwsem); + mutex_unlock(&tty->throttle_mutex); return ret; } diff --git a/include/linux/tty.h b/include/linux/tty.h index d3042076d163..57a70d1d0412 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -244,6 +244,7 @@ struct tty_struct { struct mutex atomic_write_lock; struct mutex legacy_mutex; + struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; spinlock_t ctrl_lock; /* Termios values are protected by the termios rwsem */ -- cgit v1.2.3-71-gd317 From 1fc359fc3ea72314cc3ebdfa94c60e020c152cd2 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:01 -0400 Subject: tty: Compute flip buffer ptrs The char_buf_ptr and flag_buf_ptr values are trivially derived from the .data field offset; compute values as needed. Fixes a long-standing type-mismatch with the char and flag ptrs. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 22 ++++++++++------------ include/linux/tty.h | 12 ++++++++++-- include/linux/tty_flip.h | 4 ++-- 3 files changed, 22 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index ff1b2e37c3ca..170674cb68fc 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -71,8 +71,6 @@ static struct tty_buffer *tty_buffer_alloc(struct tty_port *port, size_t size) p->next = NULL; p->commit = 0; p->read = 0; - p->char_buf_ptr = (char *)(p->data); - p->flag_buf_ptr = (unsigned char *)p->char_buf_ptr + size; port->buf.memory_used += size; return p; } @@ -265,8 +263,8 @@ int tty_insert_flip_string_fixed_flag(struct tty_port *port, if (unlikely(space == 0)) { break; } - memcpy(tb->char_buf_ptr + tb->used, chars, space); - memset(tb->flag_buf_ptr + tb->used, flag, space); + memcpy(char_buf_ptr(tb, tb->used), chars, space); + memset(flag_buf_ptr(tb, tb->used), flag, space); tb->used += space; copied += space; chars += space; @@ -303,8 +301,8 @@ int tty_insert_flip_string_flags(struct tty_port *port, if (unlikely(space == 0)) { break; } - memcpy(tb->char_buf_ptr + tb->used, chars, space); - memcpy(tb->flag_buf_ptr + tb->used, flags, space); + memcpy(char_buf_ptr(tb, tb->used), chars, space); + memcpy(flag_buf_ptr(tb, tb->used), flags, space); tb->used += space; copied += space; chars += space; @@ -364,8 +362,8 @@ int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, int space = tty_buffer_request_room(port, size); if (likely(space)) { struct tty_buffer *tb = port->buf.tail; - *chars = tb->char_buf_ptr + tb->used; - memset(tb->flag_buf_ptr + tb->used, TTY_NORMAL, space); + *chars = char_buf_ptr(tb, tb->used); + memset(flag_buf_ptr(tb, tb->used), TTY_NORMAL, space); tb->used += space; } return space; @@ -394,8 +392,8 @@ int tty_prepare_flip_string_flags(struct tty_port *port, int space = tty_buffer_request_room(port, size); if (likely(space)) { struct tty_buffer *tb = port->buf.tail; - *chars = tb->char_buf_ptr + tb->used; - *flags = tb->flag_buf_ptr + tb->used; + *chars = char_buf_ptr(tb, tb->used); + *flags = flag_buf_ptr(tb, tb->used); tb->used += space; } return space; @@ -407,8 +405,8 @@ static int receive_buf(struct tty_struct *tty, struct tty_buffer *head, int count) { struct tty_ldisc *disc = tty->ldisc; - char *p = head->char_buf_ptr + head->read; - unsigned char *f = head->flag_buf_ptr + head->read; + unsigned char *p = char_buf_ptr(head, head->read); + char *f = flag_buf_ptr(head, head->read); if (disc->ops->receive_buf2) count = disc->ops->receive_buf2(tty, p, f, count); diff --git a/include/linux/tty.h b/include/linux/tty.h index 57a70d1d0412..87bbaa31ebf5 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -31,8 +31,6 @@ struct tty_buffer { struct tty_buffer *next; - char *char_buf_ptr; - unsigned char *flag_buf_ptr; int used; int size; int commit; @@ -41,6 +39,16 @@ struct tty_buffer { unsigned long data[0]; }; +static inline unsigned char *char_buf_ptr(struct tty_buffer *b, int ofs) +{ + return ((unsigned char *)b->data) + ofs; +} + +static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) +{ + return (char *)char_buf_ptr(b, ofs) + b->size; +} + /* * We default to dicing tty buffer allocations to this many characters * in order to avoid multiple page allocations. We know the size of diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index e0f252633b47..ad0303994c32 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -18,8 +18,8 @@ static inline int tty_insert_flip_char(struct tty_port *port, { struct tty_buffer *tb = port->buf.tail; if (tb && tb->used < tb->size) { - tb->flag_buf_ptr[tb->used] = flag; - tb->char_buf_ptr[tb->used++] = ch; + *flag_buf_ptr(tb, tb->used) = flag; + *char_buf_ptr(tb, tb->used++) = ch; return 1; } return tty_insert_flip_string_flags(port, &ch, &flag, 1); -- cgit v1.2.3-71-gd317 From 809850b7a5fcc0a96d023e1171a7944c60fd5a71 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:06 -0400 Subject: tty: Use lockless flip buffer free list In preparation for lockless flip buffers, make the flip buffer free list lockless. NB: using llist is not the optimal solution, as the driver and buffer work may contend over the llist head unnecessarily. However, test measurements indicate this contention is low. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 29 ++++++++++++----------------- include/linux/llist.h | 23 +++++++++++++++++++++++ include/linux/tty.h | 8 ++++++-- 3 files changed, 41 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 0259a766b875..069640e5b9c0 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -44,16 +44,17 @@ static void tty_buffer_reset(struct tty_buffer *p, size_t size) void tty_buffer_free_all(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; - struct tty_buffer *p; + struct tty_buffer *p, *next; + struct llist_node *llist; while ((p = buf->head) != NULL) { buf->head = p->next; kfree(p); } - while ((p = buf->free) != NULL) { - buf->free = p->next; + llist = llist_del_all(&buf->free); + llist_for_each_entry_safe(p, next, llist, free) kfree(p); - } + buf->tail = NULL; buf->memory_used = 0; } @@ -68,22 +69,20 @@ void tty_buffer_free_all(struct tty_port *port) * allocation behaviour. * Return NULL if out of memory or the allocation would exceed the * per device queue - * - * Locking: Caller must hold tty->buf.lock */ static struct tty_buffer *tty_buffer_alloc(struct tty_port *port, size_t size) { - struct tty_buffer **tbh = &port->buf.free; + struct llist_node *free; struct tty_buffer *p; /* Round the buffer size out */ size = __ALIGN_MASK(size, TTYB_ALIGN_MASK); if (size <= MIN_TTYB_SIZE) { - if (*tbh) { - p = *tbh; - *tbh = p->next; + free = llist_del_first(&port->buf.free); + if (free) { + p = llist_entry(free, struct tty_buffer, free); goto found; } } @@ -109,8 +108,6 @@ found: * * Free a tty buffer, or add it to the free list according to our * internal strategy - * - * Locking: Caller must hold tty->buf.lock */ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b) @@ -123,10 +120,8 @@ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b) if (b->size > MIN_TTYB_SIZE) kfree(b); - else { - b->next = buf->free; - buf->free = b; - } + else + llist_add(&b->free, &buf->free); } /** @@ -542,7 +537,7 @@ void tty_buffer_init(struct tty_port *port) spin_lock_init(&buf->lock); buf->head = NULL; buf->tail = NULL; - buf->free = NULL; + init_llist_head(&buf->free); buf->memory_used = 0; INIT_WORK(&buf->work, flush_to_ldisc); } diff --git a/include/linux/llist.h b/include/linux/llist.h index cdaa7f023899..8828a78dec9a 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -124,6 +124,29 @@ static inline void init_llist_head(struct llist_head *list) &(pos)->member != NULL; \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) +/** + * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type + * safe against removal of list entry + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as temporary storage + * @node: the first entry of deleted list entries. + * @member: the name of the llist_node with the struct. + * + * In general, some entries of the lock-less list can be traversed + * safely only after being removed from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_entry_safe(pos, n, node, member) \ + for (pos = llist_entry((node), typeof(*pos), member); \ + &pos->member != NULL && \ + (n = llist_entry(pos->member.next, typeof(*n), member), true); \ + pos = n) + /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test diff --git a/include/linux/tty.h b/include/linux/tty.h index 87bbaa31ebf5..5043b12f23ea 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -11,6 +11,7 @@ #include #include #include +#include @@ -30,7 +31,10 @@ #define __DISABLED_CHAR '\0' struct tty_buffer { - struct tty_buffer *next; + union { + struct tty_buffer *next; + struct llist_node free; + }; int used; int size; int commit; @@ -65,7 +69,7 @@ struct tty_bufhead { spinlock_t lock; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ - struct tty_buffer *free; /* Free queue head */ + struct llist_head free; /* Free queue head */ int memory_used; /* Buffer space used excluding free queue */ }; -- cgit v1.2.3-71-gd317 From 7391ee16950e772076d321792d9fbf030f921345 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:07 -0400 Subject: tty: Simplify flip buffer list with 0-sized sentinel Use a 0-sized sentinel to avoid assigning the head ptr from the driver side thread. This also eliminates testing head/tail for NULL. When the sentinel is first 'consumed' by the buffer work (or by tty_buffer_flush()), it is detached from the list but not freed nor added to the free list. Both buffer work and tty_buffer_flush() continue to preserve at least 1 flip buffer to which head & tail is pointed. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 49 ++++++++++++++++++------------------------------ include/linux/tty.h | 1 + 2 files changed, 19 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 069640e5b9c0..231b7a8710f1 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -49,13 +49,16 @@ void tty_buffer_free_all(struct tty_port *port) while ((p = buf->head) != NULL) { buf->head = p->next; - kfree(p); + if (p->size > 0) + kfree(p); } llist = llist_del_all(&buf->free); llist_for_each_entry_safe(p, next, llist, free) kfree(p); - buf->tail = NULL; + tty_buffer_reset(&buf->sentinel, 0); + buf->head = &buf->sentinel; + buf->tail = &buf->sentinel; buf->memory_used = 0; } @@ -120,7 +123,7 @@ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b) if (b->size > MIN_TTYB_SIZE) kfree(b); - else + else if (b->size > 0) llist_add(&b->free, &buf->free); } @@ -140,8 +143,6 @@ static void __tty_buffer_flush(struct tty_port *port) struct tty_bufhead *buf = &port->buf; struct tty_buffer *next; - if (unlikely(buf->head == NULL)) - return; while ((next = buf->head->next) != NULL) { tty_buffer_free(port, buf->head); buf->head = next; @@ -200,23 +201,14 @@ int tty_buffer_request_room(struct tty_port *port, size_t size) int left; unsigned long flags; spin_lock_irqsave(&buf->lock, flags); - /* OPTIMISATION: We could keep a per tty "zero" sized buffer to - remove this conditional if its worth it. This would be invisible - to the callers */ b = buf->tail; - if (b != NULL) - left = b->size - b->used; - else - left = 0; + left = b->size - b->used; if (left < size) { /* This is the slow path - looking for new buffers to use */ if ((n = tty_buffer_alloc(port, size)) != NULL) { - if (b != NULL) { - b->next = n; - b->commit = b->used; - } else - buf->head = n; + b->next = n; + b->commit = b->used; buf->tail = n; } else size = left; @@ -247,10 +239,8 @@ int tty_insert_flip_string_fixed_flag(struct tty_port *port, int goal = min_t(size_t, size - copied, TTY_BUFFER_PAGE); int space = tty_buffer_request_room(port, goal); struct tty_buffer *tb = port->buf.tail; - /* If there is no space then tb may be NULL */ - if (unlikely(space == 0)) { + if (unlikely(space == 0)) break; - } memcpy(char_buf_ptr(tb, tb->used), chars, space); memset(flag_buf_ptr(tb, tb->used), flag, space); tb->used += space; @@ -285,10 +275,8 @@ int tty_insert_flip_string_flags(struct tty_port *port, int goal = min_t(size_t, size - copied, TTY_BUFFER_PAGE); int space = tty_buffer_request_room(port, goal); struct tty_buffer *tb = port->buf.tail; - /* If there is no space then tb may be NULL */ - if (unlikely(space == 0)) { + if (unlikely(space == 0)) break; - } memcpy(char_buf_ptr(tb, tb->used), chars, space); memcpy(flag_buf_ptr(tb, tb->used), flags, space); tb->used += space; @@ -322,8 +310,7 @@ void tty_schedule_flip(struct tty_port *port) WARN_ON(port->low_latency); spin_lock_irqsave(&buf->lock, flags); - if (buf->tail != NULL) - buf->tail->commit = buf->tail->used; + buf->tail->commit = buf->tail->used; spin_unlock_irqrestore(&buf->lock, flags); schedule_work(&buf->work); } @@ -438,8 +425,8 @@ static void flush_to_ldisc(struct work_struct *work) spin_lock_irqsave(&buf->lock, flags); if (!test_and_set_bit(TTYP_FLUSHING, &port->iflags)) { - struct tty_buffer *head; - while ((head = buf->head) != NULL) { + while (1) { + struct tty_buffer *head = buf->head; int count; count = head->commit - head->read; @@ -509,8 +496,7 @@ void tty_flip_buffer_push(struct tty_port *port) unsigned long flags; spin_lock_irqsave(&buf->lock, flags); - if (buf->tail != NULL) - buf->tail->commit = buf->tail->used; + buf->tail->commit = buf->tail->used; spin_unlock_irqrestore(&buf->lock, flags); if (port->low_latency) @@ -535,8 +521,9 @@ void tty_buffer_init(struct tty_port *port) struct tty_bufhead *buf = &port->buf; spin_lock_init(&buf->lock); - buf->head = NULL; - buf->tail = NULL; + tty_buffer_reset(&buf->sentinel, 0); + buf->head = &buf->sentinel; + buf->tail = &buf->sentinel; init_llist_head(&buf->free); buf->memory_used = 0; INIT_WORK(&buf->work, flush_to_ldisc); diff --git a/include/linux/tty.h b/include/linux/tty.h index 5043b12f23ea..2e93eb831c61 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -67,6 +67,7 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct work_struct work; spinlock_t lock; + struct tty_buffer sentinel; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ -- cgit v1.2.3-71-gd317 From 7bfe0b7116be207cf2204ae06335cc89d8f8ee02 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:08 -0400 Subject: tty: Track flip buffer memory limit atomically Lockless flip buffers require atomically updating the bytes-in-use watermark. The pty driver also peeks at the watermark value to limit memory consumption to a much lower value than the default; query the watermark with new fn, tty_buffer_space_avail(). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/pty.c | 10 +++------- drivers/tty/tty_buffer.c | 37 +++++++++++++++++++++++++++++++------ include/linux/tty.h | 3 +-- include/linux/tty_flip.h | 1 + 4 files changed, 36 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 1b39dd639ee9..b38a28bd9511 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -89,17 +89,13 @@ static void pty_unthrottle(struct tty_struct *tty) * pty_space - report space left for writing * @to: tty we are writing into * - * The tty buffers allow 64K but we sneak a peak and clip at 8K this - * allows a lot of overspill room for echo and other fun messes to - * be handled properly + * Limit the buffer space used by ptys to 8k. */ static int pty_space(struct tty_struct *to) { - int n = 8192 - to->port->buf.memory_used; - if (n < 0) - return 0; - return n; + int n = tty_buffer_space_avail(to->port); + return min(n, 8192); } /** diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 231b7a8710f1..5d5a56407aa8 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -22,6 +22,31 @@ #define MIN_TTYB_SIZE 256 #define TTYB_ALIGN_MASK 255 +/* + * Byte threshold to limit memory consumption for flip buffers. + * The actual memory limit is > 2x this amount. + */ +#define TTYB_MEM_LIMIT 65536 + + +/** + * tty_buffer_space_avail - return unused buffer space + * @port - tty_port owning the flip buffer + * + * Returns the # of bytes which can be written by the driver without + * reaching the buffer limit. + * + * Note: this does not guarantee that memory is available to write + * the returned # of bytes (use tty_prepare_flip_string_xxx() to + * pre-allocate if memory guarantee is required). + */ + +int tty_buffer_space_avail(struct tty_port *port) +{ + int space = TTYB_MEM_LIMIT - atomic_read(&port->buf.memory_used); + return max(space, 0); +} + static void tty_buffer_reset(struct tty_buffer *p, size_t size) { p->used = 0; @@ -59,7 +84,8 @@ void tty_buffer_free_all(struct tty_port *port) tty_buffer_reset(&buf->sentinel, 0); buf->head = &buf->sentinel; buf->tail = &buf->sentinel; - buf->memory_used = 0; + + atomic_set(&buf->memory_used, 0); } /** @@ -92,7 +118,7 @@ static struct tty_buffer *tty_buffer_alloc(struct tty_port *port, size_t size) /* Should possibly check if this fails for the largest buffer we have queued and recycle that ? */ - if (port->buf.memory_used + size > 65536) + if (atomic_read(&port->buf.memory_used) > TTYB_MEM_LIMIT) return NULL; p = kmalloc(sizeof(struct tty_buffer) + 2 * size, GFP_ATOMIC); if (p == NULL) @@ -100,7 +126,7 @@ static struct tty_buffer *tty_buffer_alloc(struct tty_port *port, size_t size) found: tty_buffer_reset(p, size); - port->buf.memory_used += size; + atomic_add(size, &port->buf.memory_used); return p; } @@ -118,8 +144,7 @@ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b) struct tty_bufhead *buf = &port->buf; /* Dumb strategy for now - should keep some stats */ - buf->memory_used -= b->size; - WARN_ON(buf->memory_used < 0); + WARN_ON(atomic_sub_return(b->size, &buf->memory_used) < 0); if (b->size > MIN_TTYB_SIZE) kfree(b); @@ -525,7 +550,7 @@ void tty_buffer_init(struct tty_port *port) buf->head = &buf->sentinel; buf->tail = &buf->sentinel; init_llist_head(&buf->free); - buf->memory_used = 0; + atomic_set(&buf->memory_used, 0); INIT_WORK(&buf->work, flush_to_ldisc); } diff --git a/include/linux/tty.h b/include/linux/tty.h index 2e93eb831c61..7c124541f011 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -71,8 +71,7 @@ struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ - int memory_used; /* Buffer space used excluding - free queue */ + atomic_t memory_used; /* In-use buffers excluding free list */ }; /* * When a break, frame error, or parity error happens, these codes are diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index ad0303994c32..6944ed2ce692 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -1,6 +1,7 @@ #ifndef _LINUX_TTY_FLIP_H #define _LINUX_TTY_FLIP_H +extern int tty_buffer_space_avail(struct tty_port *port); extern int tty_buffer_request_room(struct tty_port *port, size_t size); extern int tty_insert_flip_string_flags(struct tty_port *port, const unsigned char *chars, const char *flags, size_t size); -- cgit v1.2.3-71-gd317 From e9975fdec0138f1b2a85b9624e41660abd9865d4 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:10 -0400 Subject: tty: Ensure single-threaded flip buffer consumer with mutex The buffer work may race with parallel tty_buffer_flush. Use a mutex to guarantee exclusive modify access to the head flip buffer. Remove the unneeded spin lock. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/staging/dgrp/dgrp_tty.c | 2 ++ drivers/tty/tty_buffer.c | 40 +++++++++++++++++++--------------------- include/linux/tty.h | 2 +- 3 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/staging/dgrp/dgrp_tty.c b/drivers/staging/dgrp/dgrp_tty.c index 654f6010b473..0d52de3729c6 100644 --- a/drivers/staging/dgrp/dgrp_tty.c +++ b/drivers/staging/dgrp/dgrp_tty.c @@ -1120,7 +1120,9 @@ static void dgrp_tty_close(struct tty_struct *tty, struct file *file) if (!sent_printer_offstr) dgrp_tty_flush_buffer(tty); + spin_unlock_irqrestore(&nd->nd_lock, lock_flags); tty_ldisc_flush(tty); + spin_lock_irqsave(&nd->nd_lock, lock_flags); break; } diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 685757c6ce87..c3c606c52722 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -157,8 +157,6 @@ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b) * flush all the buffers containing receive data. Caller must * hold the buffer lock and must have ensured no parallel flush to * ldisc is running. - * - * Locking: Caller must hold tty->buf.lock */ static void __tty_buffer_flush(struct tty_port *port) @@ -182,29 +180,29 @@ static void __tty_buffer_flush(struct tty_port *port) * being processed by flush_to_ldisc then we defer the processing * to that function * - * Locking: none + * Locking: takes flush_mutex to ensure single-threaded flip buffer + * 'consumer' */ void tty_buffer_flush(struct tty_struct *tty) { struct tty_port *port = tty->port; struct tty_bufhead *buf = &port->buf; - unsigned long flags; - - spin_lock_irqsave(&buf->lock, flags); + mutex_lock(&buf->flush_mutex); /* If the data is being pushed to the tty layer then we can't process it here. Instead set a flag and the flush_to_ldisc path will process the flush request before it exits */ if (test_bit(TTYP_FLUSHING, &port->iflags)) { set_bit(TTYP_FLUSHPENDING, &port->iflags); - spin_unlock_irqrestore(&buf->lock, flags); + mutex_unlock(&buf->flush_mutex); wait_event(tty->read_wait, test_bit(TTYP_FLUSHPENDING, &port->iflags) == 0); return; - } else - __tty_buffer_flush(port); - spin_unlock_irqrestore(&buf->lock, flags); + } + + __tty_buffer_flush(port); + mutex_unlock(&buf->flush_mutex); } /** @@ -408,9 +406,10 @@ receive_buf(struct tty_struct *tty, struct tty_buffer *head, int count) * This routine is called out of the software interrupt to flush data * from the buffer chain to the line discipline. * - * Locking: holds tty->buf.lock to guard buffer list. Drops the lock - * while invoking the line discipline receive_buf method. The - * receive_buf method is single threaded for each tty instance. + * The receive_buf method is single threaded for each tty instance. + * + * Locking: takes flush_mutex to ensure single-threaded flip buffer + * 'consumer' */ static void flush_to_ldisc(struct work_struct *work) @@ -418,7 +417,6 @@ static void flush_to_ldisc(struct work_struct *work) struct tty_port *port = container_of(work, struct tty_port, buf.work); struct tty_bufhead *buf = &port->buf; struct tty_struct *tty; - unsigned long flags; struct tty_ldisc *disc; tty = port->itty; @@ -429,7 +427,7 @@ static void flush_to_ldisc(struct work_struct *work) if (disc == NULL) return; - spin_lock_irqsave(&buf->lock, flags); + mutex_lock(&buf->flush_mutex); if (!test_and_set_bit(TTYP_FLUSHING, &port->iflags)) { while (1) { @@ -444,11 +442,13 @@ static void flush_to_ldisc(struct work_struct *work) tty_buffer_free(port, head); continue; } - spin_unlock_irqrestore(&buf->lock, flags); + + mutex_unlock(&buf->flush_mutex); count = receive_buf(tty, head, count); - spin_lock_irqsave(&buf->lock, flags); + mutex_lock(&buf->flush_mutex); + /* Ldisc or user is trying to flush the buffers. We may have a deferred request to flush the input buffer, if so pull the chain under the lock @@ -464,7 +464,7 @@ static void flush_to_ldisc(struct work_struct *work) clear_bit(TTYP_FLUSHING, &port->iflags); } - spin_unlock_irqrestore(&buf->lock, flags); + mutex_unlock(&buf->flush_mutex); tty_ldisc_deref(disc); } @@ -514,15 +514,13 @@ EXPORT_SYMBOL(tty_flip_buffer_push); * * Set up the initial state of the buffer management for a tty device. * Must be called before the other tty buffer functions are used. - * - * Locking: none */ void tty_buffer_init(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; - spin_lock_init(&buf->lock); + mutex_init(&buf->flush_mutex); tty_buffer_reset(&buf->sentinel, 0); buf->head = &buf->sentinel; buf->tail = &buf->sentinel; diff --git a/include/linux/tty.h b/include/linux/tty.h index 7c124541f011..1c8fef0e3ff6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -66,7 +66,7 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct work_struct work; - spinlock_t lock; + struct mutex flush_mutex; struct tty_buffer sentinel; struct tty_buffer *head; /* Queue head */ struct tty_buffer *tail; /* Active buffer */ -- cgit v1.2.3-71-gd317 From d7a68be4f265be10e24be931c257af30ca55566b Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:11 -0400 Subject: tty: Only perform flip buffer flush from tty_buffer_flush() Now that dropping the buffer lock is not necessary (as result of converting the spin lock to a mutex), the flip buffer flush no longer needs to be handled by the buffer work. Simply signal a flush is required; the buffer work will exit the i/o loop, which allows tty_buffer_flush() to proceed. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 63 ++++++++++++++++-------------------------------- include/linux/tty.h | 1 - 2 files changed, 21 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index c3c606c52722..39cae611fe59 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -189,19 +189,11 @@ void tty_buffer_flush(struct tty_struct *tty) struct tty_port *port = tty->port; struct tty_bufhead *buf = &port->buf; - mutex_lock(&buf->flush_mutex); - /* If the data is being pushed to the tty layer then we can't - process it here. Instead set a flag and the flush_to_ldisc - path will process the flush request before it exits */ - if (test_bit(TTYP_FLUSHING, &port->iflags)) { - set_bit(TTYP_FLUSHPENDING, &port->iflags); - mutex_unlock(&buf->flush_mutex); - wait_event(tty->read_wait, - test_bit(TTYP_FLUSHPENDING, &port->iflags) == 0); - return; - } + set_bit(TTYP_FLUSHPENDING, &port->iflags); + mutex_lock(&buf->flush_mutex); __tty_buffer_flush(port); + clear_bit(TTYP_FLUSHPENDING, &port->iflags); mutex_unlock(&buf->flush_mutex); } @@ -429,39 +421,26 @@ static void flush_to_ldisc(struct work_struct *work) mutex_lock(&buf->flush_mutex); - if (!test_and_set_bit(TTYP_FLUSHING, &port->iflags)) { - while (1) { - struct tty_buffer *head = buf->head; - int count; - - count = head->commit - head->read; - if (!count) { - if (head->next == NULL) - break; - buf->head = head->next; - tty_buffer_free(port, head); - continue; - } - - mutex_unlock(&buf->flush_mutex); - - count = receive_buf(tty, head, count); - - mutex_lock(&buf->flush_mutex); - - /* Ldisc or user is trying to flush the buffers. - We may have a deferred request to flush the - input buffer, if so pull the chain under the lock - and empty the queue */ - if (test_bit(TTYP_FLUSHPENDING, &port->iflags)) { - __tty_buffer_flush(port); - clear_bit(TTYP_FLUSHPENDING, &port->iflags); - wake_up(&tty->read_wait); - break; - } else if (!count) + while (1) { + struct tty_buffer *head = buf->head; + int count; + + /* Ldisc or user is trying to flush the buffers. */ + if (test_bit(TTYP_FLUSHPENDING, &port->iflags)) + break; + + count = head->commit - head->read; + if (!count) { + if (head->next == NULL) break; + buf->head = head->next; + tty_buffer_free(port, head); + continue; } - clear_bit(TTYP_FLUSHING, &port->iflags); + + count = receive_buf(tty, head, count); + if (!count) + break; } mutex_unlock(&buf->flush_mutex); diff --git a/include/linux/tty.h b/include/linux/tty.h index 1c8fef0e3ff6..1d5bacca3652 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -213,7 +213,6 @@ struct tty_port { wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ unsigned long iflags; /* TTYP_ internal flags */ -#define TTYP_FLUSHING 1 /* Flushing to ldisc in progress */ #define TTYP_FLUSHPENDING 2 /* Queued buffer flush pending */ unsigned char console:1, /* port is a console */ low_latency:1; /* direct buffer flush */ -- cgit v1.2.3-71-gd317 From 8c1fb49ba107c7db9441ef6ec0ab5830d112cc2a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:12 -0400 Subject: tty: Avoid false-sharing flip buffer ptrs Separate the head and tail ptrs to avoid cache-line contention (so called 'false-sharing') between concurrent threads. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 1d5bacca3652..b8e8adf95bf3 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -65,13 +65,13 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { + struct tty_buffer *head; /* Queue head */ struct work_struct work; struct mutex flush_mutex; struct tty_buffer sentinel; - struct tty_buffer *head; /* Queue head */ - struct tty_buffer *tail; /* Active buffer */ struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ + struct tty_buffer *tail; /* Active buffer */ }; /* * When a break, frame error, or parity error happens, these codes are -- cgit v1.2.3-71-gd317 From 0f56bd2f6a97d8b0eb5c8f9bc04b83a6c16d1d48 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:13 -0400 Subject: tty: Use non-atomic state to signal flip buffer flush pending Atomic bit ops are no longer required to indicate a flip buffer flush is pending, as the flush_mutex is sufficient barrier. Remove the unnecessary port .iflags field and localize flip buffer state to struct tty_bufhead. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 7 ++++--- include/linux/tty.h | 3 +-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 39cae611fe59..fb042b9a8d68 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -189,11 +189,11 @@ void tty_buffer_flush(struct tty_struct *tty) struct tty_port *port = tty->port; struct tty_bufhead *buf = &port->buf; - set_bit(TTYP_FLUSHPENDING, &port->iflags); + buf->flushpending = 1; mutex_lock(&buf->flush_mutex); __tty_buffer_flush(port); - clear_bit(TTYP_FLUSHPENDING, &port->iflags); + buf->flushpending = 0; mutex_unlock(&buf->flush_mutex); } @@ -426,7 +426,7 @@ static void flush_to_ldisc(struct work_struct *work) int count; /* Ldisc or user is trying to flush the buffers. */ - if (test_bit(TTYP_FLUSHPENDING, &port->iflags)) + if (buf->flushpending) break; count = head->commit - head->read; @@ -505,6 +505,7 @@ void tty_buffer_init(struct tty_port *port) buf->tail = &buf->sentinel; init_llist_head(&buf->free); atomic_set(&buf->memory_used, 0); + buf->flushpending = 0; INIT_WORK(&buf->work, flush_to_ldisc); } diff --git a/include/linux/tty.h b/include/linux/tty.h index b8e8adf95bf3..991575fe3451 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -68,6 +68,7 @@ struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; struct mutex flush_mutex; + unsigned int flushpending:1; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ @@ -212,8 +213,6 @@ struct tty_port { wait_queue_head_t close_wait; /* Close waiters */ wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* TTY flags ASY_*/ - unsigned long iflags; /* TTYP_ internal flags */ -#define TTYP_FLUSHPENDING 2 /* Queued buffer flush pending */ unsigned char console:1, /* port is a console */ low_latency:1; /* direct buffer flush */ struct mutex mutex; /* Locking */ -- cgit v1.2.3-71-gd317 From a7c8d58c79853adeebf0a1ddc9c63e433b4d97f1 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:15 -0400 Subject: tty: Fix unsafe vt paste_selection() Convert the tty_buffer_flush() exclusion mechanism to a public interface - tty_buffer_lock/unlock_exclusive() - and use the interface to safely write the paste selection to the line discipline. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 61 ++++++++++++++++++++++++++++++++++++---------- drivers/tty/vt/selection.c | 4 ++- include/linux/tty.h | 4 +-- include/linux/tty_flip.h | 3 +++ 4 files changed, 56 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index dbe4a718e2dc..f22e116db105 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -29,6 +29,42 @@ #define TTYB_MEM_LIMIT 65536 +/** + * tty_buffer_lock_exclusive - gain exclusive access to buffer + * tty_buffer_unlock_exclusive - release exclusive access + * + * @port - tty_port owning the flip buffer + * + * Guarantees safe use of the line discipline's receive_buf() method by + * excluding the buffer work and any pending flush from using the flip + * buffer. Data can continue to be added concurrently to the flip buffer + * from the driver side. + * + * On release, the buffer work is restarted if there is data in the + * flip buffer + */ + +void tty_buffer_lock_exclusive(struct tty_port *port) +{ + struct tty_bufhead *buf = &port->buf; + + atomic_inc(&buf->priority); + mutex_lock(&buf->lock); +} + +void tty_buffer_unlock_exclusive(struct tty_port *port) +{ + struct tty_bufhead *buf = &port->buf; + int restart; + + restart = buf->head->commit != buf->head->read; + + atomic_dec(&buf->priority); + mutex_unlock(&buf->lock); + if (restart) + queue_work(system_unbound_wq, &buf->work); +} + /** * tty_buffer_space_avail - return unused buffer space * @port - tty_port owning the flip buffer @@ -158,7 +194,7 @@ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b) * being processed by flush_to_ldisc then we defer the processing * to that function * - * Locking: takes flush_mutex to ensure single-threaded flip buffer + * Locking: takes buffer lock to ensure single-threaded flip buffer * 'consumer' */ @@ -168,16 +204,16 @@ void tty_buffer_flush(struct tty_struct *tty) struct tty_bufhead *buf = &port->buf; struct tty_buffer *next; - buf->flushpending = 1; + atomic_inc(&buf->priority); - mutex_lock(&buf->flush_mutex); + mutex_lock(&buf->lock); while ((next = buf->head->next) != NULL) { tty_buffer_free(port, buf->head); buf->head = next; } buf->head->read = buf->head->commit; - buf->flushpending = 0; - mutex_unlock(&buf->flush_mutex); + atomic_dec(&buf->priority); + mutex_unlock(&buf->lock); } /** @@ -383,7 +419,7 @@ receive_buf(struct tty_struct *tty, struct tty_buffer *head, int count) * * The receive_buf method is single threaded for each tty instance. * - * Locking: takes flush_mutex to ensure single-threaded flip buffer + * Locking: takes buffer lock to ensure single-threaded flip buffer * 'consumer' */ @@ -402,14 +438,14 @@ static void flush_to_ldisc(struct work_struct *work) if (disc == NULL) return; - mutex_lock(&buf->flush_mutex); + mutex_lock(&buf->lock); while (1) { struct tty_buffer *head = buf->head; int count; - /* Ldisc or user is trying to flush the buffers. */ - if (buf->flushpending) + /* Ldisc or user is trying to gain exclusive access */ + if (atomic_read(&buf->priority)) break; count = head->commit - head->read; @@ -426,7 +462,7 @@ static void flush_to_ldisc(struct work_struct *work) break; } - mutex_unlock(&buf->flush_mutex); + mutex_unlock(&buf->lock); tty_ldisc_deref(disc); } @@ -482,13 +518,12 @@ void tty_buffer_init(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; - mutex_init(&buf->flush_mutex); + mutex_init(&buf->lock); tty_buffer_reset(&buf->sentinel, 0); buf->head = &buf->sentinel; buf->tail = &buf->sentinel; init_llist_head(&buf->free); atomic_set(&buf->memory_used, 0); - buf->flushpending = 0; + atomic_set(&buf->priority, 0); INIT_WORK(&buf->work, flush_to_ldisc); } - diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 2ca8d6b6514c..ea27804d87af 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -24,6 +24,7 @@ #include #include #include +#include /* Don't take this from : 011-015 on the screen aren't spaces */ #define isspace(c) ((c) == ' ') @@ -346,8 +347,8 @@ int paste_selection(struct tty_struct *tty) console_unlock(); ld = tty_ldisc_ref_wait(tty); + tty_buffer_lock_exclusive(&vc->port); - /* FIXME: this is completely unsafe */ add_wait_queue(&vc->paste_wait, &wait); while (sel_buffer && sel_buffer_lth > pasted) { set_current_state(TASK_INTERRUPTIBLE); @@ -363,6 +364,7 @@ int paste_selection(struct tty_struct *tty) remove_wait_queue(&vc->paste_wait, &wait); __set_current_state(TASK_RUNNING); + tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); return 0; } diff --git a/include/linux/tty.h b/include/linux/tty.h index 991575fe3451..7a9a3b0a6b5a 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -67,8 +67,8 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; - struct mutex flush_mutex; - unsigned int flushpending:1; + struct mutex lock; + atomic_t priority; struct tty_buffer sentinel; struct llist_head free; /* Free queue head */ atomic_t memory_used; /* In-use buffers excluding free list */ diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 6944ed2ce692..21ddd7d9ea1f 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -32,4 +32,7 @@ static inline int tty_insert_flip_string(struct tty_port *port, return tty_insert_flip_string_fixed_flag(port, chars, TTY_NORMAL, size); } +extern void tty_buffer_lock_exclusive(struct tty_port *port); +extern void tty_buffer_unlock_exclusive(struct tty_port *port); + #endif /* _LINUX_TTY_FLIP_H */ -- cgit v1.2.3-71-gd317 From 9114fe8ccf1871f630d2c14cd60e5f455b015459 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 09:36:16 -0400 Subject: tty: Remove private constant from global namespace TTY_BUFFER_PAGE is only used within drivers/tty/tty_buffer.c; relocate to that file scope. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 10 ++++++++++ include/linux/tty.h | 11 ----------- 2 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index f22e116db105..c043136fbe51 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -28,6 +28,16 @@ */ #define TTYB_MEM_LIMIT 65536 +/* + * We default to dicing tty buffer allocations to this many characters + * in order to avoid multiple page allocations. We know the size of + * tty_buffer itself but it must also be taken into account that the + * the buffer is 256 byte aligned. See tty_buffer_find for the allocation + * logic this must match + */ + +#define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF) + /** * tty_buffer_lock_exclusive - gain exclusive access to buffer diff --git a/include/linux/tty.h b/include/linux/tty.h index 7a9a3b0a6b5a..5fd5d6f1ebc4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -53,17 +53,6 @@ static inline char *flag_buf_ptr(struct tty_buffer *b, int ofs) return (char *)char_buf_ptr(b, ofs) + b->size; } -/* - * We default to dicing tty buffer allocations to this many characters - * in order to avoid multiple page allocations. We know the size of - * tty_buffer itself but it must also be taken into account that the - * the buffer is 256 byte aligned. See tty_buffer_find for the allocation - * logic this must match - */ - -#define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~0xFF) - - struct tty_bufhead { struct tty_buffer *head; /* Queue head */ struct work_struct work; -- cgit v1.2.3-71-gd317 From 40d5e0905a03601d40cd4e46b8690093c2355d03 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 15 Jun 2013 10:21:17 -0400 Subject: n_tty: Fix EOF push handling In canonical mode, an EOF which is not the first character of the line causes read() to complete and return the number of characters read so far (commonly referred to as EOF push). However, if the previous read() returned because the user buffer was full _and_ the next character is an EOF not at the beginning of the line, read() must not return 0, thus mistakenly indicating the end-of-file condition. The TTY_PUSH flag is used to indicate an EOF was received which is not at the beginning of the line. Because the EOF push condition is evaluated by a thread other than the read(), multiple EOF pushes can cause a premature end-of-file to be indicated. Instead, discover the 'EOF push as first read character' condition from the read() thread itself, and restart the i/o loop if detected. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 34 +++++++++++++++++----------------- drivers/tty/tty_io.c | 1 - include/linux/tty.h | 1 - 3 files changed, 17 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index d4d71350a71d..25aaf1afa221 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -113,6 +113,7 @@ struct n_tty_data { /* consumer-published */ size_t read_tail; + size_t line_start; /* protected by output lock */ unsigned int column; @@ -337,6 +338,7 @@ static void reset_buffer_flags(struct n_tty_data *ldata) { ldata->read_head = ldata->canon_head = ldata->read_tail = 0; ldata->echo_head = ldata->echo_tail = ldata->echo_commit = 0; + ldata->line_start = 0; ldata->erasing = 0; bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE); @@ -1396,8 +1398,6 @@ send_signal: if (c == EOF_CHAR(tty)) { if (read_cnt(ldata) >= N_TTY_BUF_SIZE) return; - if (ldata->canon_head != ldata->read_head) - set_bit(TTY_PUSH, &tty->flags); c = __DISABLED_CHAR; goto handle_newline; } @@ -1604,6 +1604,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) canon_change = (old->c_lflag ^ tty->termios.c_lflag) & ICANON; if (canon_change) { bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE); + ldata->line_start = 0; ldata->canon_head = ldata->read_tail; ldata->erasing = 0; ldata->lnext = 0; @@ -1837,6 +1838,7 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, size_t eol; size_t tail; int ret, found = 0; + bool eof_push = 0; /* N.B. avoid overrun if nr == 0 */ n = min(*nr, read_cnt(ldata)); @@ -1863,8 +1865,10 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, n = (found + eol + size) & (N_TTY_BUF_SIZE - 1); c = n; - if (found && read_buf(ldata, eol) == __DISABLED_CHAR) + if (found && read_buf(ldata, eol) == __DISABLED_CHAR) { n--; + eof_push = !n && ldata->read_tail != ldata->line_start; + } n_tty_trace("%s: eol:%zu found:%d n:%zu c:%zu size:%zu more:%zu\n", __func__, eol, found, n, c, size, more); @@ -1887,9 +1891,11 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, smp_mb__after_clear_bit(); ldata->read_tail += c; - if (found) + if (found) { + ldata->line_start = ldata->read_tail; tty_audit_push(tty); - return 0; + } + return eof_push ? -EAGAIN : 0; } extern ssize_t redirected_tty_write(struct file *, const char __user *, @@ -1964,12 +1970,10 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file, int c; int minimum, time; ssize_t retval = 0; - ssize_t size; long timeout; unsigned long flags; int packet; -do_it_again: c = job_control(tty, file); if (c < 0) return c; @@ -2076,7 +2080,10 @@ do_it_again: if (ldata->icanon && !L_EXTPROC(tty)) { retval = canon_copy_from_read_buf(tty, &b, &nr); - if (retval) + if (retval == -EAGAIN) { + retval = 0; + continue; + } else if (retval) break; } else { int uncopied; @@ -2104,15 +2111,8 @@ do_it_again: ldata->minimum_to_wake = minimum; __set_current_state(TASK_RUNNING); - size = b - buf; - if (size) { - retval = size; - if (nr) - clear_bit(TTY_PUSH, &tty->flags); - } else if (test_and_clear_bit(TTY_PUSH, &tty->flags)) { - up_read(&tty->termios_rwsem); - goto do_it_again; - } + if (b - buf) + retval = b - buf; n_tty_set_room(tty); up_read(&tty->termios_rwsem); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 1b32da6f6cdd..2174698dd6f7 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -664,7 +664,6 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session) spin_lock_irq(&tty->ctrl_lock); clear_bit(TTY_THROTTLED, &tty->flags); - clear_bit(TTY_PUSH, &tty->flags); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); put_pid(tty->session); put_pid(tty->pgrp); diff --git a/include/linux/tty.h b/include/linux/tty.h index 5fd5d6f1ebc4..554b732d8b55 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -304,7 +304,6 @@ struct tty_file_private { #define TTY_EXCLUSIVE 3 /* Exclusive open mode */ #define TTY_DEBUG 4 /* Debugging */ #define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ -#define TTY_PUSH 6 /* n_tty private */ #define TTY_CLOSING 7 /* ->close() in progress */ #define TTY_LDISC_OPEN 11 /* Line discipline is open */ #define TTY_PTY_LOCK 16 /* pty private */ -- cgit v1.2.3-71-gd317 From f484f7a6bc6f0f871627cc1f83f56077a5dc6e47 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 24 Jul 2013 10:26:42 +0200 Subject: regmap: irq: make flags bool and put them in a bitfield This patch makes mask/wake_invert bool and puts all flags into a bitfield for consistency and to save some space. Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 34ebe7778033..99b0f7cad75c 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -486,10 +486,10 @@ struct regmap_irq_chip { unsigned int ack_base; unsigned int wake_base; unsigned int irq_reg_stride; - bool init_ack_masked; - unsigned int mask_invert; - unsigned int wake_invert; - bool runtime_pm; + bool init_ack_masked:1; + bool mask_invert:1; + bool wake_invert:1; + bool runtime_pm:1; int num_regs; -- cgit v1.2.3-71-gd317 From 68622bdfefb969fd7cf710545d7e758a732ab01d Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 24 Jul 2013 10:26:48 +0200 Subject: regmap: irq: document mask/wake_invert flags Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 99b0f7cad75c..a3c68aad2381 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -471,6 +471,8 @@ struct regmap_irq { * @wake_base: Base address for wake enables. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * @init_ack_masked: Ack all masked interrupts once during initalization. + * @mask_invert: Inverted mask register: cleared bits are masked out. + * @wake_invert: Inverted wake register: cleared bits are wake enabled. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. -- cgit v1.2.3-71-gd317 From dee4a0be69c0e2996188e0c46478eadc280a8954 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Wed, 24 Jul 2013 16:43:51 -0400 Subject: tty: Fix lock order in tty_do_resize() Commits 6a1c0680cf3ba94356ecd58833e1540c93472a57 and 9356b535fcb71db494fc434acceb79f56d15bda2, respectively 'tty: Convert termios_mutex to termios_rwsem' and 'n_tty: Access termios values safely' introduced a circular lock dependency with console_lock and termios_rwsem. The lockdep report [1] shows that n_tty_write() will attempt to claim console_lock while holding the termios_rwsem, whereas tty_do_resize() may already hold the console_lock while claiming the termios_rwsem. Since n_tty_write() and tty_do_resize() do not contend over the same data -- the tty->winsize structure -- correct the lock dependency by introducing a new lock which specifically serializes access to tty->winsize only. [1] Lockdep report ====================================================== [ INFO: possible circular locking dependency detected ] 3.10.0-0+tip-xeon+lockdep #0+tip Not tainted ------------------------------------------------------- modprobe/277 is trying to acquire lock: (&tty->termios_rwsem){++++..}, at: [] tty_do_resize+0x36/0xe0 but task is already holding lock: ((fb_notifier_list).rwsem){.+.+.+}, at: [] __blocking_notifier_call_chain+0x56/0xc0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 ((fb_notifier_list).rwsem){.+.+.+}: [] lock_acquire+0x92/0x1f0 [] down_read+0x47/0x5c [] __blocking_notifier_call_chain+0x56/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] driver_register+0x77/0x170 [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b -> #1 (console_lock){+.+.+.}: [] lock_acquire+0x92/0x1f0 [] console_lock+0x77/0x80 [] con_flush_chars+0x31/0x50 [] n_tty_write+0x1ec/0x4d0 [] tty_write+0x159/0x2e0 [] redirected_tty_write+0xb5/0xc0 [] vfs_write+0xc5/0x1f0 [] SyS_write+0x55/0xa0 [] system_call_fastpath+0x16/0x1b -> #0 (&tty->termios_rwsem){++++..}: [] __lock_acquire+0x1c43/0x1d30 [] lock_acquire+0x92/0x1f0 [] down_write+0x44/0x70 [] tty_do_resize+0x36/0xe0 [] vc_do_resize+0x3e1/0x4c0 [] vc_resize+0x1f/0x30 [] fbcon_init+0x385/0x5a0 [] visual_init+0xbc/0x120 [] do_bind_con_driver+0x163/0x320 [] do_take_over_console+0x61/0x70 [] do_fbcon_takeover+0x63/0xc0 [] fbcon_event_notify+0x715/0x820 [] notifier_call_chain+0x5d/0x110 [] __blocking_notifier_call_chain+0x6c/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] driver_register+0x77/0x170 [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b other info that might help us debug this: Chain exists of: &tty->termios_rwsem --> console_lock --> (fb_notifier_list).rwsem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((fb_notifier_list).rwsem); lock(console_lock); lock((fb_notifier_list).rwsem); lock(&tty->termios_rwsem); *** DEADLOCK *** 7 locks held by modprobe/277: #0: (&__lockdep_no_validate__){......}, at: [] __driver_attach+0x5b/0xb0 #1: (&__lockdep_no_validate__){......}, at: [] __driver_attach+0x69/0xb0 #2: (drm_global_mutex){+.+.+.}, at: [] drm_get_pci_dev+0xbd/0x2a0 [drm] #3: (registration_lock){+.+.+.}, at: [] register_framebuffer+0x25/0x320 #4: (&fb_info->lock){+.+.+.}, at: [] lock_fb_info+0x26/0x60 #5: (console_lock){+.+.+.}, at: [] register_framebuffer+0x1d4/0x320 #6: ((fb_notifier_list).rwsem){.+.+.+}, at: [] __blocking_notifier_call_chain+0x56/0xc0 stack backtrace: CPU: 0 PID: 277 Comm: modprobe Not tainted 3.10.0-0+tip-xeon+lockdep #0+tip Hardware name: Dell Inc. Precision WorkStation T5400 /0RW203, BIOS A11 04/30/2012 ffffffff8213e5e0 ffff8802aa2fb298 ffffffff81755f19 ffff8802aa2fb2e8 ffffffff8174f506 ffff8802aa2fa000 ffff8802aa2fb378 ffff8802aa2ea8e8 ffff8802aa2ea910 ffff8802aa2ea8e8 0000000000000006 0000000000000007 Call Trace: [] dump_stack+0x19/0x1b [] print_circular_bug+0x1fb/0x20c [] __lock_acquire+0x1c43/0x1d30 [] ? mark_held_locks+0xae/0x120 [] ? trace_hardirqs_on_caller+0x105/0x1d0 [] lock_acquire+0x92/0x1f0 [] ? tty_do_resize+0x36/0xe0 [] down_write+0x44/0x70 [] ? tty_do_resize+0x36/0xe0 [] tty_do_resize+0x36/0xe0 [] vc_do_resize+0x3e1/0x4c0 [] vc_resize+0x1f/0x30 [] fbcon_init+0x385/0x5a0 [] visual_init+0xbc/0x120 [] do_bind_con_driver+0x163/0x320 [] do_take_over_console+0x61/0x70 [] do_fbcon_takeover+0x63/0xc0 [] fbcon_event_notify+0x715/0x820 [] notifier_call_chain+0x5d/0x110 [] __blocking_notifier_call_chain+0x6c/0xc0 [] blocking_notifier_call_chain+0x16/0x20 [] fb_notifier_call_chain+0x1b/0x20 [] register_framebuffer+0x1e2/0x320 [] drm_fb_helper_initial_config+0x371/0x540 [drm_kms_helper] [] ? kmemleak_alloc+0x5b/0xc0 [] ? kmem_cache_alloc_trace+0x104/0x290 [] ? drm_fb_helper_single_add_all_connectors+0x81/0xf0 [drm_kms_helper] [] nouveau_fbcon_init+0x105/0x140 [nouveau] [] nouveau_drm_load+0x43f/0x610 [nouveau] [] drm_get_pci_dev+0x17e/0x2a0 [drm] [] nouveau_drm_probe+0x25a/0x2a0 [nouveau] [] ? _raw_spin_unlock_irqrestore+0x42/0x80 [] local_pci_probe+0x4b/0x80 [] pci_device_probe+0x111/0x120 [] driver_probe_device+0x8b/0x3a0 [] __driver_attach+0xab/0xb0 [] ? driver_probe_device+0x3a0/0x3a0 [] bus_for_each_dev+0x5d/0xa0 [] driver_attach+0x1e/0x20 [] bus_add_driver+0x111/0x290 [] ? 0xffffffffa0229fff [] driver_register+0x77/0x170 [] ? 0xffffffffa0229fff [] __pci_register_driver+0x64/0x70 [] drm_pci_init+0x11a/0x130 [drm] [] ? 0xffffffffa0229fff [] ? 0xffffffffa0229fff [] nouveau_drm_init+0x4d/0x1000 [nouveau] [] do_one_initcall+0xea/0x1a0 [] load_module+0x123b/0x1bf0 [] ? ddebug_proc_open+0xb0/0xb0 [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] SyS_init_module+0xd7/0x120 [] system_call_fastpath+0x16/0x1b Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/pty.c | 4 ++-- drivers/tty/tty_io.c | 11 ++++++----- include/linux/tty.h | 3 ++- 3 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index b940127ba1c8..25c9bc783722 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -281,7 +281,7 @@ static int pty_resize(struct tty_struct *tty, struct winsize *ws) struct tty_struct *pty = tty->link; /* For a PTY we need to lock the tty side */ - down_write(&tty->termios_rwsem); + mutex_lock(&tty->winsize_mutex); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) goto done; @@ -308,7 +308,7 @@ static int pty_resize(struct tty_struct *tty, struct winsize *ws) tty->winsize = *ws; pty->winsize = *ws; /* Never used so will go away soon */ done: - up_write(&tty->termios_rwsem); + mutex_unlock(&tty->winsize_mutex); return 0; } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 2174698dd6f7..26bb78c30a00 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2229,7 +2229,7 @@ static int tiocsti(struct tty_struct *tty, char __user *p) * * Copies the kernel idea of the window size into the user buffer. * - * Locking: tty->termios_rwsem is taken to ensure the winsize data + * Locking: tty->winsize_mutex is taken to ensure the winsize data * is consistent. */ @@ -2237,9 +2237,9 @@ static int tiocgwinsz(struct tty_struct *tty, struct winsize __user *arg) { int err; - down_read(&tty->termios_rwsem); + mutex_lock(&tty->winsize_mutex); err = copy_to_user(arg, &tty->winsize, sizeof(*arg)); - up_read(&tty->termios_rwsem); + mutex_unlock(&tty->winsize_mutex); return err ? -EFAULT: 0; } @@ -2260,7 +2260,7 @@ int tty_do_resize(struct tty_struct *tty, struct winsize *ws) unsigned long flags; /* Lock the tty */ - down_write(&tty->termios_rwsem); + mutex_lock(&tty->winsize_mutex); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) goto done; /* Get the PID values and reference them so we can @@ -2275,7 +2275,7 @@ int tty_do_resize(struct tty_struct *tty, struct winsize *ws) tty->winsize = *ws; done: - up_write(&tty->termios_rwsem); + mutex_unlock(&tty->winsize_mutex); return 0; } EXPORT_SYMBOL(tty_do_resize); @@ -3016,6 +3016,7 @@ void initialize_tty_struct(struct tty_struct *tty, mutex_init(&tty->legacy_mutex); mutex_init(&tty->throttle_mutex); init_rwsem(&tty->termios_rwsem); + mutex_init(&tty->winsize_mutex); init_ldsem(&tty->ldisc_sem); init_waitqueue_head(&tty->write_wait); init_waitqueue_head(&tty->read_wait); diff --git a/include/linux/tty.h b/include/linux/tty.h index 554b732d8b55..64f864651d86 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -245,6 +245,7 @@ struct tty_struct { struct mutex legacy_mutex; struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; + struct mutex winsize_mutex; spinlock_t ctrl_lock; /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; @@ -254,7 +255,7 @@ struct tty_struct { struct pid *session; unsigned long flags; int count; - struct winsize winsize; /* termios rwsem */ + struct winsize winsize; /* winsize_mutex */ unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ -- cgit v1.2.3-71-gd317 From 10e232c597ac757e7f8600649f7e872e86de190f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 28 Jun 2013 09:38:12 +0800 Subject: USB: check sg buffer size in usb_submit_urb USB spec stats that short packet can only appear at the end of transfer. Because lost of HC(EHCI/UHCI/OHCI/...) can't build a full packet from discontinuous buffers, we introduce the limit in usb_submit_urb() to avoid such kind of bad sg buffers coming from driver. The limit might be a bit strict: - platform has iommu to do sg list mapping - some host controllers may support to build full packet from discontinuous buffers. But considered that most of HCs don't support that, and driver need work well or keep consistent on different HCs and ARCHs, we have to introduce the limit. Currently, only usbtest is reported to pass such sg buffers to HC, and other users(mass storage, usbfs) don't have the problem. We don't check it on USB wireless device, because: - wireless devices can't be attached to common USB bus(EHCI/UHCI/OHCI/...) - the max packet size of endpoint may be odd, and often can't devide 4KB which is a typical usage in usb mass storage application Reported-by: Konstantin Filatov Reported-by: Denis V. Lunev Cc: Felipe Balbi Acked-by: Alan Stern Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/urb.c | 8 ++++++++ include/linux/usb.h | 4 +++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index 16927fa88fbd..e75115a04a2e 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -7,6 +7,7 @@ #include #include #include +#include #define to_urb(d) container_of(d, struct urb, kref) @@ -413,6 +414,13 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags) urb->iso_frame_desc[n].status = -EXDEV; urb->iso_frame_desc[n].actual_length = 0; } + } else if (dev->speed != USB_SPEED_WIRELESS && urb->num_sgs) { + struct scatterlist *sg; + int i; + + for_each_sg(urb->sg, sg, urb->num_sgs - 1, i) + if (sg->length % max) + return -EINVAL; } /* the I/O buffer must be mapped/unmapped, except when length=0 */ diff --git a/include/linux/usb.h b/include/linux/usb.h index a232b7ece1f6..e99b2a114af4 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1258,7 +1258,9 @@ typedef void (*usb_complete_t)(struct urb *); * the device driver is saying that it provided this DMA address, * which the host controller driver should use in preference to the * transfer_buffer. - * @sg: scatter gather buffer list + * @sg: scatter gather buffer list, the buffer size of each element in + * the list (except the last) must be divisible by the endpoint's + * max packet size * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.3-71-gd317 From 3784b6d64dc52ed3fbebad61a85ab9b7a687a167 Mon Sep 17 00:00:00 2001 From: Robin Gong Date: Thu, 25 Jul 2013 11:33:18 +0800 Subject: regulator: pfuze100: add pfuze100 regulator driver Add pfuze100 regulator driver. Signed-off-by: Robin Gong Tested-by: Steffen Trumtrar Signed-off-by: Mark Brown --- .../devicetree/bindings/regulator/pfuze100.txt | 113 +++++ drivers/regulator/Kconfig | 7 + drivers/regulator/Makefile | 1 + drivers/regulator/pfuze100-regulator.c | 454 +++++++++++++++++++++ include/linux/regulator/pfuze100.h | 44 ++ 5 files changed, 619 insertions(+) create mode 100644 Documentation/devicetree/bindings/regulator/pfuze100.txt create mode 100644 drivers/regulator/pfuze100-regulator.c create mode 100644 include/linux/regulator/pfuze100.h (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt new file mode 100644 index 000000000000..22e1a48f7e83 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt @@ -0,0 +1,113 @@ +PFUZE100 family of regulators + +Required properties: +- compatible: "fsl,pfuze100" +- reg: I2C slave address +- regulators: This is the list of child nodes that specify the regulator + initialization data for defined regulators. Please refer to below doc + Documentation/devicetree/bindings/regulator/regulator.txt. + + The valid names for regulators are: + sw1ab,sw1c,sw2,sw3a,sw3b,sw4,swbst,vsnvs,vrefddr,vgen1~vgen6 + +Each regulator is defined using the standard binding for regulators. + +Example: + + pmic: pfuze100@08 { + compatible = "fsl,pfuze100"; + reg = <0x08>; + + regulators { + sw1a_reg: sw1ab { + regulator-min-microvolt = <300000>; + regulator-max-microvolt = <1875000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <6250>; + }; + + sw1c_reg: sw1c { + regulator-min-microvolt = <300000>; + regulator-max-microvolt = <1875000>; + regulator-boot-on; + regulator-always-on; + }; + + sw2_reg: sw2 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + sw3a_reg: sw3a { + regulator-min-microvolt = <400000>; + regulator-max-microvolt = <1975000>; + regulator-boot-on; + regulator-always-on; + }; + + sw3b_reg: sw3b { + regulator-min-microvolt = <400000>; + regulator-max-microvolt = <1975000>; + regulator-boot-on; + regulator-always-on; + }; + + sw4_reg: sw4 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <3300000>; + }; + + swbst_reg: swbst { + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5150000>; + }; + + snvs_reg: vsnvs { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3000000>; + regulator-boot-on; + regulator-always-on; + }; + + vref_reg: vrefddr { + regulator-boot-on; + regulator-always-on; + }; + + vgen1_reg: vgen1 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1550000>; + }; + + vgen2_reg: vgen2 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1550000>; + }; + + vgen3_reg: vgen3 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + }; + + vgen4_reg: vgen4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen5_reg: vgen5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen6_reg: vgen6 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + }; + }; diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 759b601b54ef..f9d02aabe306 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -355,6 +355,13 @@ config REGULATOR_PCF50633 Say Y here to support the voltage regulators and convertors on PCF50633 +config REGULATOR_PFUZE100 + tristate "Support regulators on Freescale PFUZE100 PMIC" + depends on I2C + help + Say y here to support the regulators found on the Freescale PFUZE100 + PMIC. + config REGULATOR_RC5T583 tristate "RICOH RC5T583 Power regulators" depends on MFD_RC5T583 diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index d240772d90ee..57838e2b0b8a 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o obj-$(CONFIG_REGULATOR_MC13XXX_CORE) += mc13xxx-regulator-core.o obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o +obj-$(CONFIG_REGULATOR_PFUZE100) += pfuze100-regulator.o obj-$(CONFIG_REGULATOR_TPS51632) += tps51632-regulator.o obj-$(CONFIG_REGULATOR_PCAP) += pcap-regulator.o obj-$(CONFIG_REGULATOR_PCF50633) += pcf50633-regulator.o diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c new file mode 100644 index 000000000000..fcc7cd0d25cc --- /dev/null +++ b/drivers/regulator/pfuze100-regulator.c @@ -0,0 +1,454 @@ +/* + * Copyright (C) 2011-2013 Freescale Semiconductor, Inc. All Rights Reserved. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define PFUZE_NUMREGS 128 +#define PFUZE100_VOL_OFFSET 0 +#define PFUZE100_STANDBY_OFFSET 1 +#define PFUZE100_MODE_OFFSET 3 +#define PFUZE100_CONF_OFFSET 4 + +#define PFUZE100_DEVICEID 0x0 +#define PFUZE100_REVID 0x3 +#define PFUZE100_FABID 0x3 + +#define PFUZE100_SW1ABVOL 0x20 +#define PFUZE100_SW1CVOL 0x2e +#define PFUZE100_SW2VOL 0x35 +#define PFUZE100_SW3AVOL 0x3c +#define PFUZE100_SW3BVOL 0x43 +#define PFUZE100_SW4VOL 0x4a +#define PFUZE100_SWBSTCON1 0x66 +#define PFUZE100_VREFDDRCON 0x6a +#define PFUZE100_VSNVSVOL 0x6b +#define PFUZE100_VGEN1VOL 0x6c +#define PFUZE100_VGEN2VOL 0x6d +#define PFUZE100_VGEN3VOL 0x6e +#define PFUZE100_VGEN4VOL 0x6f +#define PFUZE100_VGEN5VOL 0x70 +#define PFUZE100_VGEN6VOL 0x71 + +struct pfuze_regulator { + struct regulator_desc desc; + unsigned char stby_reg; + unsigned char stby_mask; +}; + +struct pfuze_chip { + struct regmap *regmap; + struct device *dev; + struct pfuze_regulator regulator_descs[PFUZE100_MAX_REGULATOR]; + struct regulator_dev *regulators[PFUZE100_MAX_REGULATOR]; +}; + +static const int pfuze100_swbst[] = { + 5000000, 5050000, 5100000, 5150000, +}; + +static const int pfuze100_vsnvs[] = { + 1000000, 1100000, 1200000, 1300000, 1500000, 1800000, 3000000, +}; + +static const struct i2c_device_id pfuze_device_id[] = { + {.name = "pfuze100"}, + {}, +}; +MODULE_DEVICE_TABLE(i2c, pfuze_device_id); + +static const struct of_device_id pfuze_dt_ids[] = { + { .compatible = "fsl,pfuze100" }, + {}, +}; +MODULE_DEVICE_TABLE(of, pfuze_dt_ids); + +static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) +{ + struct pfuze_chip *pfuze100 = rdev_get_drvdata(rdev); + int id = rdev->desc->id; + unsigned int val, ramp_bits, reg; + int ret; + + if (id < PFUZE100_SWBST) { + if (id == PFUZE100_SW1AB) + reg = PFUZE100_SW1ABVOL; + else + reg = PFUZE100_SW1CVOL + (id - PFUZE100_SW1C) * 7; + regmap_read(pfuze100->regmap, reg, &val); + + if (id <= PFUZE100_SW1C) + ramp_delay = 25000 / (2 * ramp_delay); + else if (val & 0x40) + ramp_delay = 50000 / (4 * ramp_delay); + else + ramp_delay = 25000 / (2 * ramp_delay); + + ramp_bits = (ramp_delay >> 1) - (ramp_delay >> 3); + ret = regmap_update_bits(pfuze100->regmap, reg + 4 , 0xc0, + ramp_bits << 6); + if (ret < 0) + dev_err(pfuze100->dev, "ramp failed, err %d\n", ret); + } else + ret = -EACCES; + + return ret; +} + +static struct regulator_ops pfuze100_ldo_regulator_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .list_voltage = regulator_list_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, +}; + +static struct regulator_ops pfuze100_fixed_regulator_ops = { + .list_voltage = regulator_list_voltage_linear, +}; + +static struct regulator_ops pfuze100_sw_regulator_ops = { + .list_voltage = regulator_list_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .set_ramp_delay = pfuze100_set_ramp_delay, +}; + +static struct regulator_ops pfuze100_swb_regulator_ops = { + .list_voltage = regulator_list_voltage_table, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + +}; + +#define PFUZE100_FIXED_REG(_name, base, voltage) \ + [PFUZE100_ ## _name] = { \ + .desc = { \ + .name = #_name, \ + .n_voltages = 1, \ + .ops = &pfuze100_fixed_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = PFUZE100_ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (voltage), \ + .enable_reg = (base), \ + .enable_mask = 0x10, \ + }, \ + } + +#define PFUZE100_SW_REG(_name, base, min, max, step) \ + [PFUZE100_ ## _name] = { \ + .desc = { \ + .name = #_name,\ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_sw_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = PFUZE100_ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base) + PFUZE100_VOL_OFFSET, \ + .vsel_mask = 0x3f, \ + }, \ + .stby_reg = (base) + PFUZE100_STANDBY_OFFSET, \ + .stby_mask = 0x3f, \ + } + +#define PFUZE100_SWB_REG(_name, base, mask, voltages) \ + [PFUZE100_ ## _name] = { \ + .desc = { \ + .name = #_name, \ + .n_voltages = ARRAY_SIZE(voltages), \ + .ops = &pfuze100_swb_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = PFUZE100_ ## _name, \ + .owner = THIS_MODULE, \ + .volt_table = voltages, \ + .vsel_reg = (base), \ + .vsel_mask = (mask), \ + }, \ + } + +#define PFUZE100_VGEN_REG(_name, base, min, max, step) \ + [PFUZE100_ ## _name] = { \ + .desc = { \ + .name = #_name, \ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_ldo_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = PFUZE100_ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base), \ + .vsel_mask = 0xf, \ + .enable_reg = (base), \ + .enable_mask = 0x10, \ + }, \ + .stby_reg = (base), \ + .stby_mask = 0x20, \ + } + +static struct pfuze_regulator pfuze100_regulators[] = { + PFUZE100_SW_REG(SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000), + PFUZE100_SW_REG(SW1C, PFUZE100_SW1CVOL, 300000, 1875000, 25000), + PFUZE100_SW_REG(SW2, PFUZE100_SW2VOL, 400000, 1975000, 25000), + PFUZE100_SW_REG(SW3A, PFUZE100_SW3AVOL, 400000, 1975000, 25000), + PFUZE100_SW_REG(SW3B, PFUZE100_SW3BVOL, 400000, 1975000, 25000), + PFUZE100_SW_REG(SW4, PFUZE100_SW4VOL, 400000, 1975000, 25000), + PFUZE100_SWB_REG(SWBST, PFUZE100_SWBSTCON1, 0x3 , pfuze100_swbst), + PFUZE100_SWB_REG(VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs), + PFUZE100_FIXED_REG(VREFDDR, PFUZE100_VREFDDRCON, 750000), + PFUZE100_VGEN_REG(VGEN1, PFUZE100_VGEN1VOL, 800000, 1550000, 50000), + PFUZE100_VGEN_REG(VGEN2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000), + PFUZE100_VGEN_REG(VGEN3, PFUZE100_VGEN3VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(VGEN4, PFUZE100_VGEN4VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(VGEN5, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000), +}; + +#ifdef CONFIG_OF +static struct of_regulator_match pfuze100_matches[] = { + { .name = "sw1ab", }, + { .name = "sw1c", }, + { .name = "sw2", }, + { .name = "sw3a", }, + { .name = "sw3b", }, + { .name = "sw4", }, + { .name = "swbst", }, + { .name = "vsnvs", }, + { .name = "vrefddr", }, + { .name = "vgen1", }, + { .name = "vgen2", }, + { .name = "vgen3", }, + { .name = "vgen4", }, + { .name = "vgen5", }, + { .name = "vgen6", }, +}; + +static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) +{ + struct device *dev = chip->dev; + struct device_node *np, *parent; + int ret; + + np = of_node_get(dev->parent->of_node); + if (!np) + return 0; + + parent = of_find_node_by_name(np, "regulators"); + if (!parent) { + dev_err(dev, "regulators node not found\n"); + return -EINVAL; + } + + ret = of_regulator_match(dev, parent, pfuze100_matches, + ARRAY_SIZE(pfuze100_matches)); + + of_node_put(parent); + if (ret < 0) { + dev_err(dev, "Error parsing regulator init data: %d\n", + ret); + return ret; + } + + return 0; +} + +static inline struct regulator_init_data *match_init_data(int index) +{ + return pfuze100_matches[index].init_data; +} + +static inline struct device_node *match_of_node(int index) +{ + return pfuze100_matches[index].of_node; +} +#else +static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) +{ + return NULL; +} + +static inline struct regulator_init_data *match_init_data(int index) +{ + return NULL; +} + +static inline struct device_node *match_of_node(int index) +{ + return NULL; +} +#endif + +static int pfuze_identify(struct pfuze_chip *pfuze_chip) +{ + unsigned int value; + int ret; + + ret = regmap_read(pfuze_chip->regmap, PFUZE100_DEVICEID, &value); + if (ret) + return ret; + + if (value & 0x0f) { + dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value); + return -ENODEV; + } + + ret = regmap_read(pfuze_chip->regmap, PFUZE100_REVID, &value); + if (ret) + return ret; + dev_info(pfuze_chip->dev, + "Full lay: %x, Metal lay: %x\n", + (value & 0xf0) >> 4, value & 0x0f); + + ret = regmap_read(pfuze_chip->regmap, PFUZE100_FABID, &value); + if (ret) + return ret; + dev_info(pfuze_chip->dev, "FAB: %x, FIN: %x\n", + (value & 0xc) >> 2, value & 0x3); + + return 0; +} + +static const struct regmap_config pfuze_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = PFUZE_NUMREGS, + .cache_type = REGCACHE_RBTREE, +}; + +static int pfuze100_regulator_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct pfuze_chip *pfuze_chip; + struct pfuze_regulator_platform_data *pdata = + dev_get_platdata(&client->dev); + struct regulator_config config = { }; + int i, ret; + + pfuze_chip = devm_kzalloc(&client->dev, sizeof(*pfuze_chip), + GFP_KERNEL); + if (!pfuze_chip) + return -ENOMEM; + + dev_set_drvdata(&client->dev, pfuze_chip); + + memcpy(pfuze_chip->regulator_descs, pfuze100_regulators, + sizeof(pfuze_chip->regulator_descs)); + + pfuze_chip->dev = &client->dev; + + pfuze_chip->regmap = devm_regmap_init_i2c(client, &pfuze_regmap_config); + if (IS_ERR(pfuze_chip->regmap)) { + ret = PTR_ERR(pfuze_chip->regmap); + dev_err(&client->dev, + "regmap allocation failed with err %d\n", ret); + return ret; + } + + ret = pfuze_identify(pfuze_chip); + if (ret) { + dev_err(&client->dev, "unrecognized pfuze chip ID!\n"); + return ret; + } + + ret = pfuze_parse_regulators_dt(pfuze_chip); + if (ret) + return ret; + + for (i = 0; i < PFUZE100_MAX_REGULATOR; i++) { + struct regulator_init_data *init_data; + int val; + + if (pdata) + init_data = pdata->init_data[i]; + else + init_data = match_init_data(i); + + /* SW2~SW4 high bit check and modify the voltage value table */ + if (i > PFUZE100_SW1C && i < PFUZE100_SWBST) { + regmap_read(pfuze_chip->regmap, PFUZE100_SW2VOL + + (i - PFUZE100_SW2) * 7, &val); + if (val & 0x40) { + pfuze_chip->regulator_descs[i].desc.min_uV + = 800000; + pfuze_chip->regulator_descs[i].desc.uV_step + = 50000; + } + } + + config.dev = &client->dev; + config.init_data = init_data; + config.driver_data = pfuze_chip; + config.of_node = match_of_node(i); + + pfuze_chip->regulators[i] = regulator_register(&pfuze_chip + ->regulator_descs[i].desc, &config); + if (IS_ERR(pfuze_chip->regulators[i])) { + dev_err(&client->dev, "register regulator%s failed\n", + pfuze100_regulators[i].desc.name); + ret = PTR_ERR(pfuze_chip->regulators[i]); + while (--i >= 0) + regulator_unregister(pfuze_chip->regulators[i]); + return ret; + } + } + + return 0; +} + +static int pfuze100_regulator_remove(struct i2c_client *client) +{ + int i; + struct pfuze_chip *pfuze_chip = dev_get_drvdata(&client->dev); + + for (i = 0; i < PFUZE100_MAX_REGULATOR; i++) + regulator_unregister(pfuze_chip->regulators[i]); + + return 0; +} + +static struct i2c_driver pfuze_driver = { + .id_table = pfuze_device_id, + .driver = { + .name = "pfuze100-regulator", + .owner = THIS_MODULE, + .of_match_table = pfuze_dt_ids, + }, + .probe = pfuze100_regulator_probe, + .remove = pfuze100_regulator_remove, +}; +module_i2c_driver(pfuze_driver); + +MODULE_AUTHOR("Robin Gong "); +MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100 PMIC"); +MODULE_ALIAS("pfuze100-regulator"); diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h new file mode 100644 index 000000000000..65d550bf3954 --- /dev/null +++ b/include/linux/regulator/pfuze100.h @@ -0,0 +1,44 @@ +/* + * Copyright (C) 2011-2013 Freescale Semiconductor, Inc. All Rights Reserved. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ +#ifndef __LINUX_REG_PFUZE100_H +#define __LINUX_REG_PFUZE100_H + +#define PFUZE100_SW1AB 0 +#define PFUZE100_SW1C 1 +#define PFUZE100_SW2 2 +#define PFUZE100_SW3A 3 +#define PFUZE100_SW3B 4 +#define PFUZE100_SW4 5 +#define PFUZE100_SWBST 6 +#define PFUZE100_VSNVS 7 +#define PFUZE100_VREFDDR 8 +#define PFUZE100_VGEN1 9 +#define PFUZE100_VGEN2 10 +#define PFUZE100_VGEN3 11 +#define PFUZE100_VGEN4 12 +#define PFUZE100_VGEN5 13 +#define PFUZE100_VGEN6 14 +#define PFUZE100_MAX_REGULATOR 15 + +struct regulator_init_data; + +struct pfuze_regulator_platform_data { + struct regulator_init_data *init_data[PFUZE100_MAX_REGULATOR]; +}; + +#endif /* __LINUX_REG_PFUZE100_H */ -- cgit v1.2.3-71-gd317 From 928bea964827d7824b548c1f8e06eccbbc4d0d7d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 22 Jul 2013 14:37:17 -0700 Subject: PCI: Delay enabling bridges until they're needed We currently enable PCI bridges after scanning a bus and assigning resources. This is often done in arch code. This patch changes this so we don't enable a bridge until necessary, i.e., until we enable a PCI device behind the bridge. We do this in the generic pci_enable_device() path, so this also removes the arch-specific code to enable bridges. [bhelgaas: changelog] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas --- arch/arm/kernel/bios32.c | 5 ----- arch/m68k/platform/coldfire/pci.c | 1 - arch/mips/pci/pci.c | 1 - arch/sh/drivers/pci/pci.c | 1 - drivers/acpi/pci_root.c | 3 --- drivers/parisc/lba_pci.c | 1 - drivers/pci/bus.c | 19 ------------------- drivers/pci/hotplug/acpiphp_glue.c | 1 - drivers/pci/pci.c | 20 ++++++++++++++++++++ drivers/pci/probe.c | 1 - drivers/pci/setup-bus.c | 10 +++------- drivers/pcmcia/cardbus.c | 1 - include/linux/pci.h | 1 - 13 files changed, 23 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 261fcc826169..88e14d74b6de 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -525,11 +525,6 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw) * Assign resources. */ pci_bus_assign_resources(bus); - - /* - * Enable bridges - */ - pci_enable_bridges(bus); } /* diff --git a/arch/m68k/platform/coldfire/pci.c b/arch/m68k/platform/coldfire/pci.c index b33f97a13e6d..df9679238b6d 100644 --- a/arch/m68k/platform/coldfire/pci.c +++ b/arch/m68k/platform/coldfire/pci.c @@ -319,7 +319,6 @@ static int __init mcf_pci_init(void) pci_fixup_irqs(pci_common_swizzle, mcf_pci_map_irq); pci_bus_size_bridges(rootbus); pci_bus_assign_resources(rootbus); - pci_enable_bridges(rootbus); return 0; } diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 594e60d6a43b..33e7aa52d9c4 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -113,7 +113,6 @@ static void pcibios_scanbus(struct pci_controller *hose) if (!pci_has_flag(PCI_PROBE_ONLY)) { pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); - pci_enable_bridges(bus); } } } diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index 102f5d58b037..60ed3e1c4b75 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -69,7 +69,6 @@ static void pcibios_scanbus(struct pci_channel *hose) pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); - pci_enable_bridges(bus); } else { pci_free_resource_list(&resources); } diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 5917839321b8..faa1d29c0261 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -527,9 +527,6 @@ static int acpi_pci_root_add(struct acpi_device *device, if (system_state != SYSTEM_BOOTING) { pcibios_resource_survey_bus(root->bus); pci_assign_unassigned_bus_resources(root->bus); - - /* need to after hot-added ioapic is registered */ - pci_enable_bridges(root->bus); } pci_bus_add_devices(root->bus); diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index 19f6f70c67d3..37e71ff6408d 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -1590,7 +1590,6 @@ lba_driver_probe(struct parisc_device *dev) lba_dump_res(&lba_dev->hba.lmmio_space, 2); #endif } - pci_enable_bridges(lba_bus); /* ** Once PCI register ops has walked the bus, access to config diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index b1ff02ab4f13..fc1b74013743 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -216,24 +216,6 @@ void pci_bus_add_devices(const struct pci_bus *bus) } } -void pci_enable_bridges(struct pci_bus *bus) -{ - struct pci_dev *dev; - int retval; - - list_for_each_entry(dev, &bus->devices, bus_list) { - if (dev->subordinate) { - if (!pci_is_enabled(dev)) { - retval = pci_enable_device(dev); - if (retval) - dev_err(&dev->dev, "Error enabling bridge (%d), continuing\n", retval); - pci_set_master(dev); - } - pci_enable_bridges(dev->subordinate); - } - } -} - /** pci_walk_bus - walk devices on/under bus, calling callback. * @top bus whose devices should be walked * @cb callback to be called for each device found @@ -301,4 +283,3 @@ EXPORT_SYMBOL(pci_bus_put); EXPORT_SYMBOL(pci_bus_alloc_resource); EXPORT_SYMBOL_GPL(pci_bus_add_device); EXPORT_SYMBOL(pci_bus_add_devices); -EXPORT_SYMBOL(pci_enable_bridges); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 59df8575a48c..52dee9d31e1c 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -723,7 +723,6 @@ static int __ref enable_device(struct acpiphp_slot *slot) acpiphp_sanitize_bus(bus); acpiphp_set_hpp_values(bus); acpiphp_set_acpi_region(slot); - pci_enable_bridges(bus); list_for_each_entry(dev, &bus->devices, bus_list) { /* Assume that newly added devices are powered on already. */ diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e37fea6e178d..44a1a8a0ad7b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1145,6 +1145,24 @@ int pci_reenable_device(struct pci_dev *dev) return 0; } +static void pci_enable_bridge(struct pci_dev *dev) +{ + int retval; + + if (!dev) + return; + + pci_enable_bridge(dev->bus->self); + + if (pci_is_enabled(dev)) + return; + retval = pci_enable_device(dev); + if (retval) + dev_err(&dev->dev, "Error enabling bridge (%d), continuing\n", + retval); + pci_set_master(dev); +} + static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags) { int err; @@ -1165,6 +1183,8 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags) if (atomic_inc_return(&dev->enable_cnt) > 1) return 0; /* already enabled */ + pci_enable_bridge(dev->bus->self); + /* only skip sriov related */ for (i = 0; i <= PCI_ROM_RESOURCE; i++) if (dev->resource[i].flags & flags) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 46ada5c098eb..85c114cd91cc 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1979,7 +1979,6 @@ unsigned int __ref pci_rescan_bus(struct pci_bus *bus) max = pci_scan_child_bus(bus); pci_assign_unassigned_bus_resources(bus); - pci_enable_bridges(bus); pci_bus_add_devices(bus); return max; diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 4d9ebb4ce015..8f86be13678f 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1440,7 +1440,7 @@ again: /* any device complain? */ if (list_empty(&fail_head)) - goto enable_and_dump; + goto dump; if (tried_times >= pci_try_num) { if (enable_local == undefined) @@ -1449,7 +1449,7 @@ again: dev_info(&bus->dev, "Automatically enabled pci realloc, if you have problem, try booting with pci=realloc=off\n"); free_list(&fail_head); - goto enable_and_dump; + goto dump; } dev_printk(KERN_DEBUG, &bus->dev, @@ -1482,10 +1482,7 @@ again: goto again; -enable_and_dump: - /* Depth last, update the hardware. */ - pci_enable_bridges(bus); - +dump: /* dump the resource on buses */ pci_bus_dump_resources(bus); } @@ -1556,7 +1553,6 @@ enable_all: if (retval) dev_err(&bridge->dev, "Error reenabling bridge (%d)\n", retval); pci_set_master(bridge); - pci_enable_bridges(parent); } EXPORT_SYMBOL_GPL(pci_assign_unassigned_bridge_resources); diff --git a/drivers/pcmcia/cardbus.c b/drivers/pcmcia/cardbus.c index 9d3ac998fc1f..b2a98cdbd0d2 100644 --- a/drivers/pcmcia/cardbus.c +++ b/drivers/pcmcia/cardbus.c @@ -91,7 +91,6 @@ int __ref cb_alloc(struct pcmcia_socket *s) if (s->tune_bridge) s->tune_bridge(s, bus); - pci_enable_bridges(bus); pci_bus_add_devices(bus); return 0; diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..8cd1e6f30acd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1043,7 +1043,6 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus, resource_size_t, resource_size_t), void *alignf_data); -void pci_enable_bridges(struct pci_bus *bus); /* Proper probing supporting hot-pluggable devices */ int __must_check __pci_register_driver(struct pci_driver *, struct module *, -- cgit v1.2.3-71-gd317 From 39772038ea93e85ea4f1307ec9c1f48a063d89a0 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 22 Jul 2013 14:37:18 -0700 Subject: PCI: Assign resources for hot-added host bridge more aggressively When hot-adding an ACPI host bridge, use pci_assign_unassigned_root_bus_resources() instead of pci_assign_unassigned_bus_resources(). The former is more aggressive and will release and reassign existing resources if necessary. This is safe at hot-add time because no drivers are bound to devices below the new host bridge yet. [bhelgaas: changelog, split __init changes out for reviewability] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas --- drivers/acpi/pci_root.c | 2 +- drivers/pci/setup-bus.c | 2 +- include/linux/pci.h | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index faa1d29c0261..ce04eb28e029 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -526,7 +526,7 @@ static int acpi_pci_root_add(struct acpi_device *device, if (system_state != SYSTEM_BOOTING) { pcibios_resource_survey_bus(root->bus); - pci_assign_unassigned_bus_resources(root->bus); + pci_assign_unassigned_root_bus_resources(root->bus); } pci_bus_add_devices(root->bus); diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 8d1e654256a8..94b777d108bb 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1395,7 +1395,7 @@ static enum enable_type pci_realloc_detect(struct pci_bus *bus, * second and later try will clear small leaf bridge res * will stop till to the max deepth if can not find good one */ -static void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus) +void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus) { LIST_HEAD(realloc_head); /* list of resources that want additional resources */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 8cd1e6f30acd..e494c90a00d1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1003,6 +1003,7 @@ int pci_claim_resource(struct pci_dev *, int); void pci_assign_unassigned_resources(void); void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge); void pci_assign_unassigned_bus_resources(struct pci_bus *bus); +void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus); void pdev_enable_device(struct pci_dev *); int pci_enable_resources(struct pci_dev *, int mask); void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), -- cgit v1.2.3-71-gd317 From 42189d854f174e7b29e0fdb4da9984ba63126a92 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 2 Jul 2013 10:50:15 +0300 Subject: usb: clamp bInterval to allowed range bInterval must be within the range 1 - 16 when running at High/Super speed, and within the range 1 - 255 when running at Full/Low speed. In order to catch drivers passing a too large bInterval on Super/High speed scenarios (thus overflowing urb->interval), let's clamp() the argument to the allowed ranges. Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e99b2a114af4..eb4252a0da7e 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1547,10 +1547,16 @@ static inline void usb_fill_int_urb(struct urb *urb, urb->transfer_buffer_length = buffer_length; urb->complete = complete_fn; urb->context = context; - if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) + + if (dev->speed == USB_SPEED_HIGH || dev->speed == USB_SPEED_SUPER) { + /* make sure interval is within allowed range */ + interval = clamp(interval, 1, 16); + urb->interval = 1 << (interval - 1); - else + } else { urb->interval = interval; + } + urb->start_frame = -1; } -- cgit v1.2.3-71-gd317 From 323f54ed0f3ce20e9946c961fc928ccdb80d9345 Mon Sep 17 00:00:00 2001 From: Tom Rini Date: Thu, 25 Jul 2013 14:26:10 -0400 Subject: numa: Mark __node_set() as __always_inline It is posible for some compilers to decide that __node_set() does not need to be made turned into an inline function. When the compiler does this on an __init function calling it on __initdata we get a section mismatch warning now. Use __always_inline to ensure that we will be inlined. Reported-by: Paul Bolle Cc: Jianpeng Ma Cc: Rusty Russell Cc: Lai Jiangshan Cc: Yasuaki Ishimatsu Cc: Wen Congyang Cc: Jiang Liu Cc: KOSAKI Motohiro Cc: Minchan Kim Cc: Mel Gorman Cc: David Rientjes Cc: Yinghai Lu Cc: Greg KH Signed-off-by: Tom Rini Link: http://lkml.kernel.org/r/1374776770-32361-1-git-send-email-trini@ti.com Signed-off-by: Ingo Molnar --- include/linux/nodemask.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4e2cbfa640b7..58b9a02c38d2 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -98,8 +98,17 @@ typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; +/* + * The inline keyword gives the compiler room to decide to inline, or + * not inline a function as it sees best. However, as these functions + * are called in both __init and non-__init functions, if they are not + * inlined we will end up with a section mis-match error (of the type of + * freeable items not being freed). So we must use __always_inline here + * to fix the problem. If other functions in the future also end up in + * this situation they will also need to be annotated as __always_inline + */ #define node_set(node, dst) __node_set((node), &(dst)) -static inline void __node_set(int node, volatile nodemask_t *dstp) +static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } -- cgit v1.2.3-71-gd317 From c817a67ecba7c3c2aaa104796d78f160af60920d Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 27 Jun 2013 15:06:14 +0100 Subject: kobject: delayed kobject release: help find buggy drivers Implement debugging for kobject release functions. kobjects are reference counted, so the drop of the last reference to them is not predictable. However, the common case is for the last reference to be the kobject's removal from a subsystem, which results in the release function being immediately called. This can hide subtle bugs, which can occur when another thread holds a reference to the kobject at the same time that a kobject is removed. This results in the release method being delayed. In order to make these kinds of problems more visible, the following patch implements a delayed release; this has the effect that the release function will be out of order with respect to the removal of the kobject in the same manner that it would be if a reference was being held. This provides us with an easy way to allow driver writers to debug their drivers and fix otherwise hidden problems. Signed-off-by: Russell King Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++++ lib/Kconfig.debug | 19 +++++++++++++++++++ lib/kobject.c | 22 +++++++++++++++++++--- 3 files changed, 42 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 939b11268c86..de6dcbcc6ef7 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -26,6 +26,7 @@ #include #include #include +#include #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 32 /* number of env pointers */ @@ -65,6 +66,9 @@ struct kobject { struct kobj_type *ktype; struct sysfs_dirent *sd; struct kref kref; +#ifdef CONFIG_DEBUG_KOBJECT_RELEASE + struct delayed_work release; +#endif unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1501aa553221..444e1c12fea9 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -981,6 +981,25 @@ config DEBUG_KOBJECT If you say Y here, some extra kobject debugging messages will be sent to the syslog. +config DEBUG_KOBJECT_RELEASE + bool "kobject release debugging" + depends on DEBUG_KERNEL + help + kobjects are reference counted objects. This means that their + last reference count put is not predictable, and the kobject can + live on past the point at which a driver decides to drop it's + initial reference to the kobject gained on allocation. An + example of this would be a struct device which has just been + unregistered. + + However, some buggy drivers assume that after such an operation, + the memory backing the kobject can be immediately freed. This + goes completely against the principles of a refcounted object. + + If you say Y here, the kernel will delay the release of kobjects + on the last reference count to improve the visibility of this + kind of kobject release bug. + config HAVE_DEBUG_BUGVERBOSE bool diff --git a/lib/kobject.c b/lib/kobject.c index 4a1f33d43548..1d46c151a4ae 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -545,8 +545,8 @@ static void kobject_cleanup(struct kobject *kobj) struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; - pr_debug("kobject: '%s' (%p): %s\n", - kobject_name(kobj), kobj, __func__); + pr_debug("kobject: '%s' (%p): %s, parent %p\n", + kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("kobject: '%s' (%p): does not have a release() " @@ -580,9 +580,25 @@ static void kobject_cleanup(struct kobject *kobj) } } +#ifdef CONFIG_DEBUG_KOBJECT_RELEASE +static void kobject_delayed_cleanup(struct work_struct *work) +{ + kobject_cleanup(container_of(to_delayed_work(work), + struct kobject, release)); +} +#endif + static void kobject_release(struct kref *kref) { - kobject_cleanup(container_of(kref, struct kobject, kref)); + struct kobject *kobj = container_of(kref, struct kobject, kref); +#ifdef CONFIG_DEBUG_KOBJECT_RELEASE + pr_debug("kobject: '%s' (%p): %s, parent %p (delayed)\n", + kobject_name(kobj), kobj, __func__, kobj->parent); + INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); + schedule_delayed_work(&kobj->release, HZ); +#else + kobject_cleanup(kobj); +#endif } /** -- cgit v1.2.3-71-gd317 From cffe4e0e7413eb29fb8bd035c8b12b33a4b8522a Mon Sep 17 00:00:00 2001 From: Stratos Karafotis Date: Wed, 5 Jun 2013 19:01:50 +0300 Subject: cpufreq: Remove unused function __cpufreq_driver_getavg() The target frequency calculation method in the ondemand governor has changed and it is now independent of the measured average frequency. Consequently, the __cpufreq_driver_getavg() function and getavg member of struct cpufreq_driver are not used any more, so drop them. [rjw: Changelog] Signed-off-by: Stratos Karafotis Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 12 ------------ include/linux/cpufreq.h | 6 ------ 2 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index a4ad7339588d..9a9d8ee9faec 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1593,18 +1593,6 @@ fail: } EXPORT_SYMBOL_GPL(cpufreq_driver_target); -int __cpufreq_driver_getavg(struct cpufreq_policy *policy, unsigned int cpu) -{ - if (cpufreq_disabled()) - return 0; - - if (!cpufreq_driver->getavg) - return 0; - - return cpufreq_driver->getavg(policy, cpu); -} -EXPORT_SYMBOL_GPL(__cpufreq_driver_getavg); - /* * when "event" is CPUFREQ_GOV_LIMITS */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 90d5a15120d5..e1fd215e16c9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -216,10 +216,6 @@ extern int cpufreq_driver_target(struct cpufreq_policy *policy, extern int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); - -extern int __cpufreq_driver_getavg(struct cpufreq_policy *policy, - unsigned int cpu); - int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); @@ -258,8 +254,6 @@ struct cpufreq_driver { unsigned int (*get) (unsigned int cpu); /* optional */ - unsigned int (*getavg) (struct cpufreq_policy *policy, - unsigned int cpu); int (*bios_limit) (int cpu, unsigned int *limit); int (*exit) (struct cpufreq_policy *policy); -- cgit v1.2.3-71-gd317 From 102c9323c35a83789ad5ebd3c45fa8fb389add88 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Jul 2013 17:07:27 -0400 Subject: tracing: Add __tracepoint_string() to export string pointers There are several tracepoints (mostly in RCU), that reference a string pointer and uses the print format of "%s" to display the string that exists in the kernel, instead of copying the actual string to the ring buffer (saves time and ring buffer space). But this has an issue with userspace tools that read the binary buffers that has the address of the string but has no access to what the string itself is. The end result is just output that looks like: rcu_dyntick: ffffffff818adeaa 1 0 rcu_dyntick: ffffffff818adeb5 0 140000000000000 rcu_dyntick: ffffffff818adeb5 0 140000000000000 rcu_utilization: ffffffff8184333b rcu_utilization: ffffffff8184333b The above is pretty useless when read by the userspace tools. Ideally we would want something that looks like this: rcu_dyntick: Start 1 0 rcu_dyntick: End 0 140000000000000 rcu_dyntick: Start 140000000000000 0 rcu_callback: rcu_preempt rhp=0xffff880037aff710 func=put_cred_rcu 0/4 rcu_callback: rcu_preempt rhp=0xffff880078961980 func=file_free_rcu 0/5 rcu_dyntick: End 0 1 The trace_printk() which also only stores the address of the string format instead of recording the string into the buffer itself, exports the mapping of kernel addresses to format strings via the printk_format file in the debugfs tracing directory. The tracepoint strings can use this same method and output the format to the same file and the userspace tools will be able to decipher the address without any modification. The tracepoint strings need its own section to save the strings because the trace_printk section will cause the trace_printk() buffers to be allocated if anything exists within the section. trace_printk() is only used for debugging and should never exist in the kernel, we can not use the trace_printk sections. Add a new tracepoint_str section that will also be examined by the output of the printk_format file. Cc: Paul E. McKenney Signed-off-by: Steven Rostedt --- include/asm-generic/vmlinux.lds.h | 7 ++++++- include/linux/ftrace_event.h | 34 ++++++++++++++++++++++++++++++++++ kernel/trace/trace.h | 3 +++ kernel/trace/trace_printk.c | 19 +++++++++++++++++++ 4 files changed, 62 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 69732d279e8b..83e2c31e8b00 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -122,8 +122,12 @@ #define TRACE_PRINTKS() VMLINUX_SYMBOL(__start___trace_bprintk_fmt) = .; \ *(__trace_printk_fmt) /* Trace_printk fmt' pointer */ \ VMLINUX_SYMBOL(__stop___trace_bprintk_fmt) = .; +#define TRACEPOINT_STR() VMLINUX_SYMBOL(__start___tracepoint_str) = .; \ + *(__tracepoint_str) /* Trace_printk fmt' pointer */ \ + VMLINUX_SYMBOL(__stop___tracepoint_str) = .; #else #define TRACE_PRINTKS() +#define TRACEPOINT_STR() #endif #ifdef CONFIG_FTRACE_SYSCALLS @@ -190,7 +194,8 @@ VMLINUX_SYMBOL(__stop___verbose) = .; \ LIKELY_PROFILE() \ BRANCH_PROFILE() \ - TRACE_PRINTKS() + TRACE_PRINTKS() \ + TRACEPOINT_STR() /* * Data section helpers diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4372658c73ae..81af18a75f4d 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -357,6 +357,40 @@ do { \ __trace_printk(ip, fmt, ##args); \ } while (0) +/** + * tracepoint_string - register constant persistent string to trace system + * @str - a constant persistent string that will be referenced in tracepoints + * + * If constant strings are being used in tracepoints, it is faster and + * more efficient to just save the pointer to the string and reference + * that with a printf "%s" instead of saving the string in the ring buffer + * and wasting space and time. + * + * The problem with the above approach is that userspace tools that read + * the binary output of the trace buffers do not have access to the string. + * Instead they just show the address of the string which is not very + * useful to users. + * + * With tracepoint_string(), the string will be registered to the tracing + * system and exported to userspace via the debugfs/tracing/printk_formats + * file that maps the string address to the string text. This way userspace + * tools that read the binary buffers have a way to map the pointers to + * the ASCII strings they represent. + * + * The @str used must be a constant string and persistent as it would not + * make sense to show a string that no longer exists. But it is still fine + * to be used with modules, because when modules are unloaded, if they + * had tracepoints, the ring buffers are cleared too. As long as the string + * does not change during the life of the module, it is fine to use + * tracepoint_string() within a module. + */ +#define tracepoint_string(str) \ + ({ \ + static const char *___tp_str __tracepoint_string = str; \ + ___tp_str; \ + }) +#define __tracepoint_string __attribute__((section("__tracepoint_str"))) + #ifdef CONFIG_PERF_EVENTS struct perf_event; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 4a4f6e1828b6..ba321f12df8c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1022,6 +1022,9 @@ extern struct list_head ftrace_events; extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; +extern const char *__start___tracepoint_str[]; +extern const char *__stop___tracepoint_str[]; + void trace_printk_init_buffers(void); void trace_printk_start_comm(void); int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index a9077c1b4ad3..2900817ba65c 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -244,12 +244,31 @@ static const char **find_next(void *v, loff_t *pos) { const char **fmt = v; int start_index; + int last_index; start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt; if (*pos < start_index) return __start___trace_bprintk_fmt + *pos; + /* + * The __tracepoint_str section is treated the same as the + * __trace_printk_fmt section. The difference is that the + * __trace_printk_fmt section should only be used by trace_printk() + * in a debugging environment, as if anything exists in that section + * the trace_prink() helper buffers are allocated, which would just + * waste space in a production environment. + * + * The __tracepoint_str sections on the other hand are used by + * tracepoints which need to map pointers to their strings to + * the ASCII text for userspace. + */ + last_index = start_index; + start_index = __stop___tracepoint_str - __start___tracepoint_str; + + if (*pos < last_index + start_index) + return __start___tracepoint_str + (*pos - last_index); + return find_next_mod_format(start_index, v, fmt, pos); } -- cgit v1.2.3-71-gd317 From 10d8b34a421716d55a4ff7c2d427c35e88b8fd60 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:17 +0400 Subject: serial: max310x: Driver rework This patch rework max310x driver. Major changes have been made: - Prepare driver to support ICs with more than one UART. - Prepare driver to support work with I2C-bus. The patch changes almost every function and can not be divided into parts. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 4 +- drivers/tty/serial/max310x.c | 918 +++++++++++++++++----------------- include/linux/platform_data/max310x.h | 5 +- 3 files changed, 454 insertions(+), 473 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 5e3d68917ffe..25772c15276d 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -291,9 +291,9 @@ config SERIAL_MAX3100 config SERIAL_MAX310X bool "MAX310X support" - depends on SPI + depends on SPI_MASTER select SERIAL_CORE - select REGMAP_SPI if SPI + select REGMAP_SPI if SPI_MASTER default n help This selects support for an advanced UART from Maxim (Dallas). diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 8941e6418942..4620289e9e49 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1,7 +1,7 @@ /* * Maxim (Dallas) MAX3107/8 serial driver * - * Copyright (C) 2012 Alexander Shiyan + * Copyright (C) 2012-2013 Alexander Shiyan * * Based on max3100.c, by Christian Pellegrin * Based on max3110.c, by Feng Tang @@ -17,7 +17,9 @@ /* TODO: MAX14830 support (Quad) */ #include +#include #include +#include #include #include #include @@ -25,8 +27,10 @@ #include #include #include + #include +#define MAX310X_NAME "max310x" #define MAX310X_MAJOR 204 #define MAX310X_MINOR 209 @@ -37,7 +41,8 @@ #define MAX310X_IRQSTS_REG (0x02) /* IRQ status */ #define MAX310X_LSR_IRQEN_REG (0x03) /* LSR IRQ enable */ #define MAX310X_LSR_IRQSTS_REG (0x04) /* LSR IRQ status */ -#define MAX310X_SPCHR_IRQEN_REG (0x05) /* Special char IRQ enable */ +#define MAX310X_REG_05 (0x05) +#define MAX310X_SPCHR_IRQEN_REG MAX310X_REG_05 /* Special char IRQ en */ #define MAX310X_SPCHR_IRQSTS_REG (0x06) /* Special char IRQ status */ #define MAX310X_STS_IRQEN_REG (0x07) /* Status IRQ enable */ #define MAX310X_STS_IRQSTS_REG (0x08) /* Status IRQ status */ @@ -63,8 +68,15 @@ #define MAX310X_BRGDIVLSB_REG (0x1c) /* Baud rate divisor LSB */ #define MAX310X_BRGDIVMSB_REG (0x1d) /* Baud rate divisor MSB */ #define MAX310X_CLKSRC_REG (0x1e) /* Clock source */ -/* Only present in MAX3107 */ -#define MAX3107_REVID_REG (0x1f) /* Revision identification */ +#define MAX310X_REG_1F (0x1f) + +#define MAX310X_REVID_REG MAX310X_REG_1F /* Revision ID */ + +#define MAX310X_GLOBALIRQ_REG MAX310X_REG_1F /* Global IRQ (RO) */ +#define MAX310X_GLOBALCMD_REG MAX310X_REG_1F /* Global Command (WO) */ + +/* Extended registers */ +#define MAX310X_REVID_EXTREG MAX310X_REG_05 /* Revision ID */ /* IRQ register bits */ #define MAX310X_IRQ_LSR_BIT (1 << 0) /* LSR interrupt */ @@ -246,58 +258,139 @@ #define MAX310X_CLKSRC_EXTCLK_BIT (1 << 4) /* External clock enable */ #define MAX310X_CLKSRC_CLK2RTS_BIT (1 << 7) /* Baud clk to RTS pin */ +/* Global commands */ +#define MAX310X_EXTREG_ENBL (0xce) +#define MAX310X_EXTREG_DSBL (0xcd) + /* Misc definitions */ #define MAX310X_FIFO_SIZE (128) +#define MAX310x_REV_MASK (0xfc) /* MAX3107 specific */ #define MAX3107_REV_ID (0xa0) -#define MAX3107_REV_MASK (0xfe) - -/* IRQ status bits definitions */ -#define MAX310X_IRQ_TX (MAX310X_IRQ_TXFIFO_BIT | \ - MAX310X_IRQ_TXEMPTY_BIT) -#define MAX310X_IRQ_RX (MAX310X_IRQ_RXFIFO_BIT | \ - MAX310X_IRQ_RXEMPTY_BIT) - -/* Supported chip types */ -enum { - MAX310X_TYPE_MAX3107 = 3107, - MAX310X_TYPE_MAX3108 = 3108, + +struct max310x_devtype { + char name[9]; + int nr; + int (*detect)(struct device *); + void (*power)(struct uart_port *, int); }; -struct max310x_port { - struct uart_driver uart; +struct max310x_one { struct uart_port port; + struct work_struct tx_work; +}; - const char *name; - int uartclk; - - unsigned int nr_gpio; +struct max310x_port { + struct uart_driver uart; + struct max310x_devtype *devtype; + struct regmap *regmap; + struct regmap_config regcfg; + struct mutex mutex; + struct max310x_pdata *pdata; + int gpio_used; #ifdef CONFIG_GPIOLIB struct gpio_chip gpio; #endif + struct max310x_one p[0]; +}; - struct regmap *regmap; - struct regmap_config regcfg; +static u8 max310x_port_read(struct uart_port *port, u8 reg) +{ + struct max310x_port *s = dev_get_drvdata(port->dev); + unsigned int val = 0; - struct workqueue_struct *wq; - struct work_struct tx_work; + regmap_read(s->regmap, port->iobase + reg, &val); - struct mutex max310x_mutex; + return val; +} - struct max310x_pdata *pdata; +static void max310x_port_write(struct uart_port *port, u8 reg, u8 val) +{ + struct max310x_port *s = dev_get_drvdata(port->dev); + + regmap_write(s->regmap, port->iobase + reg, val); +} + +static void max310x_port_update(struct uart_port *port, u8 reg, u8 mask, u8 val) +{ + struct max310x_port *s = dev_get_drvdata(port->dev); + + regmap_update_bits(s->regmap, port->iobase + reg, mask, val); +} + +static int max3107_detect(struct device *dev) +{ + struct max310x_port *s = dev_get_drvdata(dev); + unsigned int val = 0; + int ret; + + ret = regmap_read(s->regmap, MAX310X_REVID_REG, &val); + if (ret) + return ret; + + if (((val & MAX310x_REV_MASK) != MAX3107_REV_ID)) { + dev_err(dev, + "%s ID 0x%02x does not match\n", s->devtype->name, val); + return -ENODEV; + } + + return 0; +} + +static int max3108_detect(struct device *dev) +{ + struct max310x_port *s = dev_get_drvdata(dev); + unsigned int val = 0; + int ret; + + /* MAX3108 have not REV ID register, we just check default value + * from clocksource register to make sure everything works. + */ + ret = regmap_read(s->regmap, MAX310X_CLKSRC_REG, &val); + if (ret) + return ret; + + if (val != (MAX310X_CLKSRC_EXTCLK_BIT | MAX310X_CLKSRC_PLLBYP_BIT)) { + dev_err(dev, "%s not present\n", s->devtype->name); + return -ENODEV; + } + + return 0; +} + +static void max310x_power(struct uart_port *port, int on) +{ + max310x_port_update(port, MAX310X_MODE1_REG, + MAX310X_MODE1_FORCESLEEP_BIT, + on ? 0 : MAX310X_MODE1_FORCESLEEP_BIT); + if (on) + msleep(50); +} + +static const struct max310x_devtype max3107_devtype = { + .name = "MAX3107", + .nr = 1, + .detect = max3107_detect, + .power = max310x_power, }; -static bool max3107_8_reg_writeable(struct device *dev, unsigned int reg) +static const struct max310x_devtype max3108_devtype = { + .name = "MAX3108", + .nr = 1, + .detect = max3108_detect, + .power = max310x_power, +}; + +static bool max310x_reg_writeable(struct device *dev, unsigned int reg) { - switch (reg) { + switch (reg & 0x1f) { case MAX310X_IRQSTS_REG: case MAX310X_LSR_IRQSTS_REG: case MAX310X_SPCHR_IRQSTS_REG: case MAX310X_STS_IRQSTS_REG: case MAX310X_TXFIFOLVL_REG: case MAX310X_RXFIFOLVL_REG: - case MAX3107_REVID_REG: /* Only available on MAX3107 */ return false; default: break; @@ -308,7 +401,7 @@ static bool max3107_8_reg_writeable(struct device *dev, unsigned int reg) static bool max310x_reg_volatile(struct device *dev, unsigned int reg) { - switch (reg) { + switch (reg & 0x1f) { case MAX310X_RHR_REG: case MAX310X_IRQSTS_REG: case MAX310X_LSR_IRQSTS_REG: @@ -317,6 +410,9 @@ static bool max310x_reg_volatile(struct device *dev, unsigned int reg) case MAX310X_TXFIFOLVL_REG: case MAX310X_RXFIFOLVL_REG: case MAX310X_GPIODATA_REG: + case MAX310X_BRGDIVLSB_REG: + case MAX310X_REG_05: + case MAX310X_REG_1F: return true; default: break; @@ -327,7 +423,7 @@ static bool max310x_reg_volatile(struct device *dev, unsigned int reg) static bool max310x_reg_precious(struct device *dev, unsigned int reg) { - switch (reg) { + switch (reg & 0x1f) { case MAX310X_RHR_REG: case MAX310X_IRQSTS_REG: case MAX310X_SPCHR_IRQSTS_REG: @@ -340,42 +436,25 @@ static bool max310x_reg_precious(struct device *dev, unsigned int reg) return false; } -static void max310x_set_baud(struct max310x_port *s, int baud) +static void max310x_set_baud(struct uart_port *port, int baud) { - unsigned int mode = 0, div = s->uartclk / baud; + unsigned int mode = 0, div = port->uartclk / baud; if (!(div / 16)) { /* Mode x2 */ mode = MAX310X_BRGCFG_2XMODE_BIT; - div = (s->uartclk * 2) / baud; + div = (port->uartclk * 2) / baud; } if (!(div / 16)) { /* Mode x4 */ mode = MAX310X_BRGCFG_4XMODE_BIT; - div = (s->uartclk * 4) / baud; + div = (port->uartclk * 4) / baud; } - regmap_write(s->regmap, MAX310X_BRGDIVMSB_REG, - ((div / 16) >> 8) & 0xff); - regmap_write(s->regmap, MAX310X_BRGDIVLSB_REG, (div / 16) & 0xff); - regmap_write(s->regmap, MAX310X_BRGCFG_REG, (div % 16) | mode); -} - -static void max310x_wait_pll(struct max310x_port *s) -{ - int tryes = 1000; - - /* Wait for PLL only if crystal is used */ - if (!(s->pdata->driver_flags & MAX310X_EXT_CLK)) { - unsigned int sts = 0; - - while (tryes--) { - regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &sts); - if (sts & MAX310X_STS_CLKREADY_BIT) - break; - } - } + max310x_port_write(port, MAX310X_BRGDIVMSB_REG, (div / 16) >> 8); + max310x_port_write(port, MAX310X_BRGDIVLSB_REG, div / 16); + max310x_port_write(port, MAX310X_BRGCFG_REG, (div % 16) | mode); } static int max310x_update_best_err(unsigned long f, long *besterr) @@ -449,49 +528,49 @@ static int max310x_set_ref_clk(struct max310x_port *s) regmap_write(s->regmap, MAX310X_CLKSRC_REG, clksrc); - if (pllcfg) - max310x_wait_pll(s); - - dev_dbg(s->port.dev, "Reference clock set to %lu Hz\n", bestfreq); + /* Wait for crystal */ + if (pllcfg && !(s->pdata->driver_flags & MAX310X_EXT_CLK)) + msleep(10); return (int)bestfreq; } -static void max310x_handle_rx(struct max310x_port *s, unsigned int rxlen) +static void max310x_handle_rx(struct uart_port *port, unsigned int rxlen) { - unsigned int sts = 0, ch = 0, flag; + unsigned int sts, ch, flag; - if (unlikely(rxlen >= MAX310X_FIFO_SIZE)) { - dev_warn(s->port.dev, "Possible RX FIFO overrun %d\n", rxlen); + if (unlikely(rxlen >= port->fifosize)) { + dev_warn_ratelimited(port->dev, + "Port %i: Possible RX FIFO overrun\n", + port->line); + port->icount.buf_overrun++; /* Ensure sanity of RX level */ - rxlen = MAX310X_FIFO_SIZE; + rxlen = port->fifosize; } - dev_dbg(s->port.dev, "RX Len = %u\n", rxlen); - while (rxlen--) { - regmap_read(s->regmap, MAX310X_RHR_REG, &ch); - regmap_read(s->regmap, MAX310X_LSR_IRQSTS_REG, &sts); + ch = max310x_port_read(port, MAX310X_RHR_REG); + sts = max310x_port_read(port, MAX310X_LSR_IRQSTS_REG); sts &= MAX310X_LSR_RXPAR_BIT | MAX310X_LSR_FRERR_BIT | MAX310X_LSR_RXOVR_BIT | MAX310X_LSR_RXBRK_BIT; - s->port.icount.rx++; + port->icount.rx++; flag = TTY_NORMAL; if (unlikely(sts)) { if (sts & MAX310X_LSR_RXBRK_BIT) { - s->port.icount.brk++; - if (uart_handle_break(&s->port)) + port->icount.brk++; + if (uart_handle_break(port)) continue; } else if (sts & MAX310X_LSR_RXPAR_BIT) - s->port.icount.parity++; + port->icount.parity++; else if (sts & MAX310X_LSR_FRERR_BIT) - s->port.icount.frame++; + port->icount.frame++; else if (sts & MAX310X_LSR_RXOVR_BIT) - s->port.icount.overrun++; + port->icount.overrun++; - sts &= s->port.read_status_mask; + sts &= port->read_status_mask; if (sts & MAX310X_LSR_RXBRK_BIT) flag = TTY_BREAK; else if (sts & MAX310X_LSR_RXPAR_BIT) @@ -502,129 +581,129 @@ static void max310x_handle_rx(struct max310x_port *s, unsigned int rxlen) flag = TTY_OVERRUN; } - if (uart_handle_sysrq_char(s->port, ch)) + if (uart_handle_sysrq_char(port, ch)) continue; - if (sts & s->port.ignore_status_mask) + if (sts & port->ignore_status_mask) continue; - uart_insert_char(&s->port, sts, MAX310X_LSR_RXOVR_BIT, - ch, flag); + uart_insert_char(port, sts, MAX310X_LSR_RXOVR_BIT, ch, flag); } - tty_flip_buffer_push(&s->port.state->port); + tty_flip_buffer_push(&port->state->port); } -static void max310x_handle_tx(struct max310x_port *s) +static void max310x_handle_tx(struct uart_port *port) { - struct circ_buf *xmit = &s->port.state->xmit; - unsigned int txlen = 0, to_send; + struct circ_buf *xmit = &port->state->xmit; + unsigned int txlen, to_send; - if (unlikely(s->port.x_char)) { - regmap_write(s->regmap, MAX310X_THR_REG, s->port.x_char); - s->port.icount.tx++; - s->port.x_char = 0; + if (unlikely(port->x_char)) { + max310x_port_write(port, MAX310X_THR_REG, port->x_char); + port->icount.tx++; + port->x_char = 0; return; } - if (uart_circ_empty(xmit) || uart_tx_stopped(&s->port)) + if (uart_circ_empty(xmit) || uart_tx_stopped(port)) return; /* Get length of data pending in circular buffer */ to_send = uart_circ_chars_pending(xmit); if (likely(to_send)) { /* Limit to size of TX FIFO */ - regmap_read(s->regmap, MAX310X_TXFIFOLVL_REG, &txlen); - txlen = MAX310X_FIFO_SIZE - txlen; + txlen = max310x_port_read(port, MAX310X_TXFIFOLVL_REG); + txlen = port->fifosize - txlen; to_send = (to_send > txlen) ? txlen : to_send; - dev_dbg(s->port.dev, "TX Len = %u\n", to_send); - /* Add data to send */ - s->port.icount.tx += to_send; + port->icount.tx += to_send; while (to_send--) { - regmap_write(s->regmap, MAX310X_THR_REG, - xmit->buf[xmit->tail]); + max310x_port_write(port, MAX310X_THR_REG, + xmit->buf[xmit->tail]); xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); }; } if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) - uart_write_wakeup(&s->port); + uart_write_wakeup(port); } -static irqreturn_t max310x_ist(int irq, void *dev_id) +static void max310x_port_irq(struct max310x_port *s, int portno) { - struct max310x_port *s = (struct max310x_port *)dev_id; - unsigned int ists = 0, lsr = 0, rxlen = 0; + struct uart_port *port = &s->p[portno].port; - mutex_lock(&s->max310x_mutex); + do { + unsigned int ists, lsr, rxlen; - for (;;) { /* Read IRQ status & RX FIFO level */ - regmap_read(s->regmap, MAX310X_IRQSTS_REG, &ists); - regmap_read(s->regmap, MAX310X_LSR_IRQSTS_REG, &lsr); - regmap_read(s->regmap, MAX310X_RXFIFOLVL_REG, &rxlen); - if (!ists && !(lsr & MAX310X_LSR_RXTO_BIT) && !rxlen) + ists = max310x_port_read(port, MAX310X_IRQSTS_REG); + rxlen = max310x_port_read(port, MAX310X_RXFIFOLVL_REG); + if (!ists && !rxlen) break; - dev_dbg(s->port.dev, "IRQ status: 0x%02x\n", ists); - - if (rxlen) - max310x_handle_rx(s, rxlen); - if (ists & MAX310X_IRQ_TX) - max310x_handle_tx(s); - if (ists & MAX310X_IRQ_CTS_BIT) - uart_handle_cts_change(&s->port, + if (ists & MAX310X_IRQ_CTS_BIT) { + lsr = max310x_port_read(port, MAX310X_LSR_IRQSTS_REG); + uart_handle_cts_change(port, !!(lsr & MAX310X_LSR_CTS_BIT)); - } + } + if (rxlen) + max310x_handle_rx(port, rxlen); + if (ists & MAX310X_IRQ_TXEMPTY_BIT) { + mutex_lock(&s->mutex); + max310x_handle_tx(port); + mutex_unlock(&s->mutex); + } + } while (1); +} - mutex_unlock(&s->max310x_mutex); +static irqreturn_t max310x_ist(int irq, void *dev_id) +{ + struct max310x_port *s = (struct max310x_port *)dev_id; + + if (s->uart.nr > 1) { + do { + unsigned int val = ~0; + + WARN_ON_ONCE(regmap_read(s->regmap, + MAX310X_GLOBALIRQ_REG, &val)); + val = ((1 << s->uart.nr) - 1) & ~val; + if (!val) + break; + max310x_port_irq(s, fls(val) - 1); + } while (1); + } else + max310x_port_irq(s, 0); return IRQ_HANDLED; } static void max310x_wq_proc(struct work_struct *ws) { - struct max310x_port *s = container_of(ws, struct max310x_port, tx_work); + struct max310x_one *one = container_of(ws, struct max310x_one, tx_work); + struct max310x_port *s = dev_get_drvdata(one->port.dev); - mutex_lock(&s->max310x_mutex); - max310x_handle_tx(s); - mutex_unlock(&s->max310x_mutex); + mutex_lock(&s->mutex); + max310x_handle_tx(&one->port); + mutex_unlock(&s->mutex); } static void max310x_start_tx(struct uart_port *port) { - struct max310x_port *s = container_of(port, struct max310x_port, port); + struct max310x_one *one = container_of(port, struct max310x_one, port); - queue_work(s->wq, &s->tx_work); -} - -static void max310x_stop_tx(struct uart_port *port) -{ - /* Do nothing */ -} - -static void max310x_stop_rx(struct uart_port *port) -{ - /* Do nothing */ + if (!work_pending(&one->tx_work)) + schedule_work(&one->tx_work); } static unsigned int max310x_tx_empty(struct uart_port *port) { - unsigned int val = 0; - struct max310x_port *s = container_of(port, struct max310x_port, port); - - mutex_lock(&s->max310x_mutex); - regmap_read(s->regmap, MAX310X_TXFIFOLVL_REG, &val); - mutex_unlock(&s->max310x_mutex); + unsigned int lvl, sts; - return val ? 0 : TIOCSER_TEMT; -} + lvl = max310x_port_read(port, MAX310X_TXFIFOLVL_REG); + sts = max310x_port_read(port, MAX310X_IRQSTS_REG); -static void max310x_enable_ms(struct uart_port *port) -{ - /* Modem status not supported */ + return ((sts & MAX310X_IRQ_TXEMPTY_BIT) && !lvl) ? TIOCSER_TEMT : 0; } static unsigned int max310x_get_mctrl(struct uart_port *port) @@ -644,28 +723,20 @@ static void max310x_set_mctrl(struct uart_port *port, unsigned int mctrl) static void max310x_break_ctl(struct uart_port *port, int break_state) { - struct max310x_port *s = container_of(port, struct max310x_port, port); - - mutex_lock(&s->max310x_mutex); - regmap_update_bits(s->regmap, MAX310X_LCR_REG, - MAX310X_LCR_TXBREAK_BIT, - break_state ? MAX310X_LCR_TXBREAK_BIT : 0); - mutex_unlock(&s->max310x_mutex); + max310x_port_update(port, MAX310X_LCR_REG, + MAX310X_LCR_TXBREAK_BIT, + break_state ? MAX310X_LCR_TXBREAK_BIT : 0); } static void max310x_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { - struct max310x_port *s = container_of(port, struct max310x_port, port); unsigned int lcr, flow = 0; int baud; - mutex_lock(&s->max310x_mutex); - /* Mask termios capabilities we don't support */ termios->c_cflag &= ~CMSPAR; - termios->c_iflag &= ~IXANY; /* Word size */ switch (termios->c_cflag & CSIZE) { @@ -696,7 +767,7 @@ static void max310x_set_termios(struct uart_port *port, lcr |= MAX310X_LCR_STOPLEN_BIT; /* 2 stops */ /* Update LCR register */ - regmap_write(s->regmap, MAX310X_LCR_REG, lcr); + max310x_port_write(port, MAX310X_LCR_REG, lcr); /* Set read status mask */ port->read_status_mask = MAX310X_LSR_RXOVR_BIT; @@ -717,8 +788,8 @@ static void max310x_set_termios(struct uart_port *port, MAX310X_LSR_RXBRK_BIT; /* Configure flow control */ - regmap_write(s->regmap, MAX310X_XON1_REG, termios->c_cc[VSTART]); - regmap_write(s->regmap, MAX310X_XOFF1_REG, termios->c_cc[VSTOP]); + max310x_port_write(port, MAX310X_XON1_REG, termios->c_cc[VSTART]); + max310x_port_write(port, MAX310X_XOFF1_REG, termios->c_cc[VSTOP]); if (termios->c_cflag & CRTSCTS) flow |= MAX310X_FLOWCTRL_AUTOCTS_BIT | MAX310X_FLOWCTRL_AUTORTS_BIT; @@ -728,7 +799,7 @@ static void max310x_set_termios(struct uart_port *port, if (termios->c_iflag & IXOFF) flow |= MAX310X_FLOWCTRL_SWFLOW1_BIT | MAX310X_FLOWCTRL_SWFLOWEN_BIT; - regmap_write(s->regmap, MAX310X_FLOWCTRL_REG, flow); + max310x_port_write(port, MAX310X_FLOWCTRL_REG, flow); /* Get baud rate generator configuration */ baud = uart_get_baud_rate(port, termios, old, @@ -736,36 +807,30 @@ static void max310x_set_termios(struct uart_port *port, port->uartclk / 4); /* Setup baudrate generator */ - max310x_set_baud(s, baud); + max310x_set_baud(port, baud); /* Update timeout according to new baud rate */ uart_update_timeout(port, termios->c_cflag, baud); - - mutex_unlock(&s->max310x_mutex); } static int max310x_startup(struct uart_port *port) { unsigned int val, line = port->line; - struct max310x_port *s = container_of(port, struct max310x_port, port); + struct max310x_port *s = dev_get_drvdata(port->dev); - if (s->pdata->suspend) - s->pdata->suspend(0); - - mutex_lock(&s->max310x_mutex); + s->devtype->power(port, 1); /* Configure baud rate, 9600 as default */ - max310x_set_baud(s, 9600); + max310x_set_baud(port, 9600); /* Configure LCR register, 8N1 mode by default */ - val = MAX310X_LCR_WORD_LEN_8; - regmap_write(s->regmap, MAX310X_LCR_REG, val); + max310x_port_write(port, MAX310X_LCR_REG, MAX310X_LCR_WORD_LEN_8); /* Configure MODE1 register */ - regmap_update_bits(s->regmap, MAX310X_MODE1_REG, - MAX310X_MODE1_TRNSCVCTRL_BIT, - (s->pdata->uart_flags[line] & MAX310X_AUTO_DIR_CTRL) - ? MAX310X_MODE1_TRNSCVCTRL_BIT : 0); + max310x_port_update(port, MAX310X_MODE1_REG, + MAX310X_MODE1_TRNSCVCTRL_BIT, + (s->pdata->uart_flags[line] & MAX310X_AUTO_DIR_CTRL) + ? MAX310X_MODE1_TRNSCVCTRL_BIT : 0); /* Configure MODE2 register */ val = MAX310X_MODE2_RXEMPTINV_BIT; @@ -776,63 +841,40 @@ static int max310x_startup(struct uart_port *port) /* Reset FIFOs */ val |= MAX310X_MODE2_FIFORST_BIT; - regmap_write(s->regmap, MAX310X_MODE2_REG, val); - - /* Configure FIFO trigger level register */ - /* RX FIFO trigger for 16 words, TX FIFO trigger for 64 words */ - val = MAX310X_FIFOTRIGLVL_RX(16) | MAX310X_FIFOTRIGLVL_TX(64); - regmap_write(s->regmap, MAX310X_FIFOTRIGLVL_REG, val); + max310x_port_write(port, MAX310X_MODE2_REG, val); + max310x_port_update(port, MAX310X_MODE2_REG, + MAX310X_MODE2_FIFORST_BIT, 0); /* Configure flow control levels */ /* Flow control halt level 96, resume level 48 */ - val = MAX310X_FLOWLVL_RES(48) | MAX310X_FLOWLVL_HALT(96); - regmap_write(s->regmap, MAX310X_FLOWLVL_REG, val); - - /* Clear timeout register */ - regmap_write(s->regmap, MAX310X_RXTO_REG, 0); - - /* Configure LSR interrupt enable register */ - /* Enable RX timeout interrupt */ - val = MAX310X_LSR_RXTO_BIT; - regmap_write(s->regmap, MAX310X_LSR_IRQEN_REG, val); + max310x_port_write(port, MAX310X_FLOWLVL_REG, + MAX310X_FLOWLVL_RES(48) | MAX310X_FLOWLVL_HALT(96)); - /* Clear FIFO reset */ - regmap_update_bits(s->regmap, MAX310X_MODE2_REG, - MAX310X_MODE2_FIFORST_BIT, 0); + /* Clear IRQ status register */ + max310x_port_read(port, MAX310X_IRQSTS_REG); - /* Clear IRQ status register by reading it */ - regmap_read(s->regmap, MAX310X_IRQSTS_REG, &val); - - /* Configure interrupt enable register */ - /* Enable CTS change interrupt */ - val = MAX310X_IRQ_CTS_BIT; - /* Enable RX, TX interrupts */ - val |= MAX310X_IRQ_RX | MAX310X_IRQ_TX; - regmap_write(s->regmap, MAX310X_IRQEN_REG, val); - - mutex_unlock(&s->max310x_mutex); + /* Enable RX, TX, CTS change interrupts */ + val = MAX310X_IRQ_RXEMPTY_BIT | MAX310X_IRQ_TXEMPTY_BIT; + max310x_port_write(port, MAX310X_IRQEN_REG, val | MAX310X_IRQ_CTS_BIT); return 0; } static void max310x_shutdown(struct uart_port *port) { - struct max310x_port *s = container_of(port, struct max310x_port, port); + struct max310x_port *s = dev_get_drvdata(port->dev); /* Disable all interrupts */ - mutex_lock(&s->max310x_mutex); - regmap_write(s->regmap, MAX310X_IRQEN_REG, 0); - mutex_unlock(&s->max310x_mutex); + max310x_port_write(port, MAX310X_IRQEN_REG, 0); - if (s->pdata->suspend) - s->pdata->suspend(1); + s->devtype->power(port, 0); } static const char *max310x_type(struct uart_port *port) { - struct max310x_port *s = container_of(port, struct max310x_port, port); + struct max310x_port *s = dev_get_drvdata(port->dev); - return (port->type == PORT_MAX310X) ? s->name : NULL; + return (port->type == PORT_MAX310X) ? s->devtype->name : NULL; } static int max310x_request_port(struct uart_port *port) @@ -841,134 +883,100 @@ static int max310x_request_port(struct uart_port *port) return 0; } -static void max310x_release_port(struct uart_port *port) -{ - /* Do nothing */ -} - static void max310x_config_port(struct uart_port *port, int flags) { if (flags & UART_CONFIG_TYPE) port->type = PORT_MAX310X; } -static int max310x_verify_port(struct uart_port *port, struct serial_struct *ser) +static int max310x_verify_port(struct uart_port *port, struct serial_struct *s) { - if ((ser->type == PORT_UNKNOWN) || (ser->type == PORT_MAX310X)) - return 0; - if (ser->irq == port->irq) - return 0; + if ((s->type != PORT_UNKNOWN) && (s->type != PORT_MAX310X)) + return -EINVAL; + if (s->irq != port->irq) + return -EINVAL; - return -EINVAL; + return 0; } -static struct uart_ops max310x_ops = { +static void max310x_null_void(struct uart_port *port) +{ + /* Do nothing */ +} + +static const struct uart_ops max310x_ops = { .tx_empty = max310x_tx_empty, .set_mctrl = max310x_set_mctrl, .get_mctrl = max310x_get_mctrl, - .stop_tx = max310x_stop_tx, + .stop_tx = max310x_null_void, .start_tx = max310x_start_tx, - .stop_rx = max310x_stop_rx, - .enable_ms = max310x_enable_ms, + .stop_rx = max310x_null_void, + .enable_ms = max310x_null_void, .break_ctl = max310x_break_ctl, .startup = max310x_startup, .shutdown = max310x_shutdown, .set_termios = max310x_set_termios, .type = max310x_type, .request_port = max310x_request_port, - .release_port = max310x_release_port, + .release_port = max310x_null_void, .config_port = max310x_config_port, .verify_port = max310x_verify_port, }; -#ifdef CONFIG_PM_SLEEP - -static int max310x_suspend(struct device *dev) +static int __maybe_unused max310x_suspend(struct spi_device *spi, + pm_message_t state) { - int ret; - struct max310x_port *s = dev_get_drvdata(dev); - - dev_dbg(dev, "Suspend\n"); + struct max310x_port *s = dev_get_drvdata(&spi->dev); + int i; - ret = uart_suspend_port(&s->uart, &s->port); - - mutex_lock(&s->max310x_mutex); - - /* Enable sleep mode */ - regmap_update_bits(s->regmap, MAX310X_MODE1_REG, - MAX310X_MODE1_FORCESLEEP_BIT, - MAX310X_MODE1_FORCESLEEP_BIT); - - mutex_unlock(&s->max310x_mutex); - - if (s->pdata->suspend) - s->pdata->suspend(1); + for (i = 0; i < s->uart.nr; i++) { + uart_suspend_port(&s->uart, &s->p[i].port); + s->devtype->power(&s->p[i].port, 0); + } - return ret; + return 0; } -static int max310x_resume(struct device *dev) +static int __maybe_unused max310x_resume(struct spi_device *spi) { - struct max310x_port *s = dev_get_drvdata(dev); - - dev_dbg(dev, "Resume\n"); - - if (s->pdata->suspend) - s->pdata->suspend(0); - - mutex_lock(&s->max310x_mutex); + struct max310x_port *s = dev_get_drvdata(&spi->dev); + int i; - /* Disable sleep mode */ - regmap_update_bits(s->regmap, MAX310X_MODE1_REG, - MAX310X_MODE1_FORCESLEEP_BIT, - 0); - - max310x_wait_pll(s); - - mutex_unlock(&s->max310x_mutex); + for (i = 0; i < s->uart.nr; i++) { + s->devtype->power(&s->p[i].port, 1); + uart_resume_port(&s->uart, &s->p[i].port); + } - return uart_resume_port(&s->uart, &s->port); + return 0; } -static SIMPLE_DEV_PM_OPS(max310x_pm_ops, max310x_suspend, max310x_resume); -#define MAX310X_PM_OPS (&max310x_pm_ops) - -#else -#define MAX310X_PM_OPS NULL -#endif - #ifdef CONFIG_GPIOLIB static int max310x_gpio_get(struct gpio_chip *chip, unsigned offset) { - unsigned int val = 0; + unsigned int val; struct max310x_port *s = container_of(chip, struct max310x_port, gpio); + struct uart_port *port = &s->p[offset / 4].port; - mutex_lock(&s->max310x_mutex); - regmap_read(s->regmap, MAX310X_GPIODATA_REG, &val); - mutex_unlock(&s->max310x_mutex); + val = max310x_port_read(port, MAX310X_GPIODATA_REG); - return !!((val >> 4) & (1 << offset)); + return !!((val >> 4) & (1 << (offset % 4))); } static void max310x_gpio_set(struct gpio_chip *chip, unsigned offset, int value) { struct max310x_port *s = container_of(chip, struct max310x_port, gpio); + struct uart_port *port = &s->p[offset / 4].port; - mutex_lock(&s->max310x_mutex); - regmap_update_bits(s->regmap, MAX310X_GPIODATA_REG, 1 << offset, value ? - 1 << offset : 0); - mutex_unlock(&s->max310x_mutex); + max310x_port_update(port, MAX310X_GPIODATA_REG, 1 << (offset % 4), + value ? 1 << (offset % 4) : 0); } static int max310x_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { struct max310x_port *s = container_of(chip, struct max310x_port, gpio); + struct uart_port *port = &s->p[offset / 4].port; - mutex_lock(&s->max310x_mutex); - - regmap_update_bits(s->regmap, MAX310X_GPIOCFG_REG, 1 << offset, 0); - - mutex_unlock(&s->max310x_mutex); + max310x_port_update(port, MAX310X_GPIOCFG_REG, 1 << (offset % 4), 0); return 0; } @@ -977,74 +985,42 @@ static int max310x_gpio_direction_output(struct gpio_chip *chip, unsigned offset, int value) { struct max310x_port *s = container_of(chip, struct max310x_port, gpio); + struct uart_port *port = &s->p[offset / 4].port; - mutex_lock(&s->max310x_mutex); - - regmap_update_bits(s->regmap, MAX310X_GPIOCFG_REG, 1 << offset, - 1 << offset); - regmap_update_bits(s->regmap, MAX310X_GPIODATA_REG, 1 << offset, value ? - 1 << offset : 0); - - mutex_unlock(&s->max310x_mutex); + max310x_port_update(port, MAX310X_GPIODATA_REG, 1 << (offset % 4), + value ? 1 << (offset % 4) : 0); + max310x_port_update(port, MAX310X_GPIOCFG_REG, 1 << (offset % 4), + 1 << (offset % 4)); return 0; } #endif -/* Generic platform data */ -static struct max310x_pdata generic_plat_data = { - .driver_flags = MAX310X_EXT_CLK, - .uart_flags[0] = MAX310X_ECHO_SUPRESS, - .frequency = 26000000, -}; - -static int max310x_probe(struct spi_device *spi) +static int max310x_probe(struct device *dev, int is_spi, + struct max310x_devtype *devtype, int irq) { struct max310x_port *s; - struct device *dev = &spi->dev; - int chiptype = spi_get_device_id(spi)->driver_data; - struct max310x_pdata *pdata = dev->platform_data; - unsigned int val = 0; - int ret; + struct max310x_pdata *pdata = dev_get_platdata(dev); + int i, ret, uartclk; /* Check for IRQ */ - if (spi->irq <= 0) { + if (irq <= 0) { dev_err(dev, "No IRQ specified\n"); return -ENOTSUPP; } + if (!pdata) { + dev_err(dev, "No platform data supplied\n"); + return -EINVAL; + } + /* Alloc port structure */ - s = devm_kzalloc(dev, sizeof(struct max310x_port), GFP_KERNEL); + s = devm_kzalloc(dev, sizeof(*s) + + sizeof(struct max310x_one) * devtype->nr, GFP_KERNEL); if (!s) { dev_err(dev, "Error allocating port structure\n"); return -ENOMEM; } - dev_set_drvdata(dev, s); - - if (!pdata) { - dev_warn(dev, "No platform data supplied, using defaults\n"); - pdata = &generic_plat_data; - } - s->pdata = pdata; - - /* Individual chip settings */ - switch (chiptype) { - case MAX310X_TYPE_MAX3107: - s->name = "MAX3107"; - s->nr_gpio = 4; - s->uart.nr = 1; - s->regcfg.max_register = 0x1f; - break; - case MAX310X_TYPE_MAX3108: - s->name = "MAX3108"; - s->nr_gpio = 4; - s->uart.nr = 1; - s->regcfg.max_register = 0x1e; - break; - default: - dev_err(dev, "Unsupported chip type %i\n", chiptype); - return -ENOTSUPP; - } /* Check input frequency */ if ((pdata->driver_flags & MAX310X_EXT_CLK) && @@ -1055,13 +1031,11 @@ static int max310x_probe(struct spi_device *spi) ((pdata->frequency < 1000000) || (pdata->frequency > 4000000))) goto err_freq; - mutex_init(&s->max310x_mutex); + s->pdata = pdata; + s->devtype = devtype; + dev_set_drvdata(dev, s); - /* Setup SPI bus */ - spi->mode = SPI_MODE_0; - spi->bits_per_word = 8; - spi->max_speed_hz = 26000000; - spi_setup(spi); + mutex_init(&s->mutex); /* Setup regmap */ s->regcfg.reg_bits = 8; @@ -1069,109 +1043,100 @@ static int max310x_probe(struct spi_device *spi) s->regcfg.read_flag_mask = 0x00; s->regcfg.write_flag_mask = 0x80; s->regcfg.cache_type = REGCACHE_RBTREE; - s->regcfg.writeable_reg = max3107_8_reg_writeable; + s->regcfg.writeable_reg = max310x_reg_writeable; s->regcfg.volatile_reg = max310x_reg_volatile; s->regcfg.precious_reg = max310x_reg_precious; - s->regmap = devm_regmap_init_spi(spi, &s->regcfg); + s->regcfg.max_register = devtype->nr * 0x20 - 1; + + if (IS_ENABLED(CONFIG_SPI_MASTER) && is_spi) { + struct spi_device *spi = to_spi_device(dev); + + s->regmap = devm_regmap_init_spi(spi, &s->regcfg); + } else + return -ENOTSUPP; + if (IS_ERR(s->regmap)) { - ret = PTR_ERR(s->regmap); dev_err(dev, "Failed to initialize register map\n"); - goto err_out; - } - - /* Reset chip & check SPI function */ - ret = regmap_write(s->regmap, MAX310X_MODE2_REG, MAX310X_MODE2_RST_BIT); - if (ret) { - dev_err(dev, "SPI transfer failed\n"); - goto err_out; - } - /* Clear chip reset */ - regmap_write(s->regmap, MAX310X_MODE2_REG, 0); - - switch (chiptype) { - case MAX310X_TYPE_MAX3107: - /* Check REV ID to ensure we are talking to what we expect */ - regmap_read(s->regmap, MAX3107_REVID_REG, &val); - if (((val & MAX3107_REV_MASK) != MAX3107_REV_ID)) { - dev_err(dev, "%s ID 0x%02x does not match\n", - s->name, val); - ret = -ENODEV; - goto err_out; - } - break; - case MAX310X_TYPE_MAX3108: - /* MAX3108 have not REV ID register, we just check default value - * from clocksource register to make sure everything works. - */ - regmap_read(s->regmap, MAX310X_CLKSRC_REG, &val); - if (val != (MAX310X_CLKSRC_EXTCLK_BIT | - MAX310X_CLKSRC_PLLBYP_BIT)) { - dev_err(dev, "%s not present\n", s->name); - ret = -ENODEV; - goto err_out; - } - break; + return PTR_ERR(s->regmap); } /* Board specific configure */ - if (pdata->init) - pdata->init(); - if (pdata->suspend) - pdata->suspend(0); - - /* Calculate referecne clock */ - s->uartclk = max310x_set_ref_clk(s); - - /* Disable all interrupts */ - regmap_write(s->regmap, MAX310X_IRQEN_REG, 0); - - /* Setup MODE1 register */ - val = MAX310X_MODE1_IRQSEL_BIT; /* Enable IRQ pin */ - if (pdata->driver_flags & MAX310X_AUTOSLEEP) - val = MAX310X_MODE1_AUTOSLEEP_BIT; - regmap_write(s->regmap, MAX310X_MODE1_REG, val); - - /* Setup interrupt */ - ret = devm_request_threaded_irq(dev, spi->irq, NULL, max310x_ist, - IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - dev_name(dev), s); - if (ret) { - dev_err(dev, "Unable to reguest IRQ %i\n", spi->irq); - goto err_out; + if (s->pdata->init) + s->pdata->init(); + + /* Check device to ensure we are talking to what we expect */ + ret = devtype->detect(dev); + if (ret) + return ret; + + for (i = 0; i < devtype->nr; i++) { + unsigned int offs = i << 5; + + /* Reset port */ + regmap_write(s->regmap, MAX310X_MODE2_REG + offs, + MAX310X_MODE2_RST_BIT); + /* Clear port reset */ + regmap_write(s->regmap, MAX310X_MODE2_REG + offs, 0); + + /* Wait for port startup */ + do { + regmap_read(s->regmap, + MAX310X_BRGDIVLSB_REG + offs, &ret); + } while (ret != 0x01); + + regmap_update_bits(s->regmap, MAX310X_MODE1_REG + offs, + MAX310X_MODE1_AUTOSLEEP_BIT, + MAX310X_MODE1_AUTOSLEEP_BIT); } + uartclk = max310x_set_ref_clk(s); + dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk); + /* Register UART driver */ s->uart.owner = THIS_MODULE; - s->uart.driver_name = dev_name(dev); s->uart.dev_name = "ttyMAX"; s->uart.major = MAX310X_MAJOR; s->uart.minor = MAX310X_MINOR; + s->uart.nr = devtype->nr; ret = uart_register_driver(&s->uart); if (ret) { dev_err(dev, "Registering UART driver failed\n"); - goto err_out; + return ret; } - /* Initialize workqueue for start TX */ - s->wq = create_freezable_workqueue(dev_name(dev)); - INIT_WORK(&s->tx_work, max310x_wq_proc); - - /* Initialize UART port data */ - s->port.line = 0; - s->port.dev = dev; - s->port.irq = spi->irq; - s->port.type = PORT_MAX310X; - s->port.fifosize = MAX310X_FIFO_SIZE; - s->port.flags = UPF_SKIP_TEST | UPF_FIXED_TYPE; - s->port.iotype = UPIO_PORT; - s->port.membase = (void __iomem *)0xffffffff; /* Bogus value */ - s->port.uartclk = s->uartclk; - s->port.ops = &max310x_ops; - uart_add_one_port(&s->uart, &s->port); + for (i = 0; i < devtype->nr; i++) { + /* Initialize port data */ + s->p[i].port.line = i; + s->p[i].port.dev = dev; + s->p[i].port.irq = irq; + s->p[i].port.type = PORT_MAX310X; + s->p[i].port.fifosize = MAX310X_FIFO_SIZE; + s->p[i].port.flags = UPF_SKIP_TEST | UPF_FIXED_TYPE | + UPF_LOW_LATENCY; + s->p[i].port.iotype = UPIO_PORT; + s->p[i].port.iobase = i * 0x20; + s->p[i].port.membase = (void __iomem *)~0; + s->p[i].port.uartclk = uartclk; + s->p[i].port.ops = &max310x_ops; + /* Disable all interrupts */ + max310x_port_write(&s->p[i].port, MAX310X_IRQEN_REG, 0); + /* Clear IRQ status register */ + max310x_port_read(&s->p[i].port, MAX310X_IRQSTS_REG); + /* Enable IRQ pin */ + max310x_port_update(&s->p[i].port, MAX310X_MODE1_REG, + MAX310X_MODE1_IRQSEL_BIT, + MAX310X_MODE1_IRQSEL_BIT); + /* Initialize queue for start TX */ + INIT_WORK(&s->p[i].tx_work, max310x_wq_proc); + /* Register port */ + uart_add_one_port(&s->uart, &s->p[i].port); + /* Go to suspend mode */ + devtype->power(&s->p[i].port, 0); + } #ifdef CONFIG_GPIOLIB /* Setup GPIO cotroller */ - if (pdata->gpio_base) { + if (s->pdata->gpio_base) { s->gpio.owner = THIS_MODULE; s->gpio.dev = dev; s->gpio.label = dev_name(dev); @@ -1179,86 +1144,105 @@ static int max310x_probe(struct spi_device *spi) s->gpio.get = max310x_gpio_get; s->gpio.direction_output= max310x_gpio_direction_output; s->gpio.set = max310x_gpio_set; - s->gpio.base = pdata->gpio_base; - s->gpio.ngpio = s->nr_gpio; + s->gpio.base = s->pdata->gpio_base; + s->gpio.ngpio = devtype->nr * 4; s->gpio.can_sleep = 1; - if (gpiochip_add(&s->gpio)) { - /* Indicate that we should not call gpiochip_remove */ - s->gpio.base = 0; - } + if (!gpiochip_add(&s->gpio)) + s->gpio_used = 1; } else dev_info(dev, "GPIO support not enabled\n"); #endif - /* Go to suspend mode */ - if (pdata->suspend) - pdata->suspend(1); + /* Setup interrupt */ + ret = devm_request_threaded_irq(dev, irq, NULL, max310x_ist, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(dev), s); + if (ret) { + dev_err(dev, "Unable to reguest IRQ %i\n", irq); +#ifdef CONFIG_GPIOLIB + if (s->gpio_used) + WARN_ON(gpiochip_remove(&s->gpio)); +#endif + } - return 0; + return ret; err_freq: dev_err(dev, "Frequency parameter incorrect\n"); - ret = -EINVAL; - -err_out: - dev_set_drvdata(dev, NULL); - - return ret; + return -EINVAL; } -static int max310x_remove(struct spi_device *spi) +static int max310x_remove(struct device *dev) { - struct device *dev = &spi->dev; struct max310x_port *s = dev_get_drvdata(dev); - int ret = 0; - - dev_dbg(dev, "Removing port\n"); - - devm_free_irq(dev, s->port.irq, s); + int i, ret = 0; - destroy_workqueue(s->wq); - - uart_remove_one_port(&s->uart, &s->port); + for (i = 0; i < s->uart.nr; i++) { + cancel_work_sync(&s->p[i].tx_work); + uart_remove_one_port(&s->uart, &s->p[i].port); + s->devtype->power(&s->p[i].port, 0); + } uart_unregister_driver(&s->uart); #ifdef CONFIG_GPIOLIB - if (s->pdata->gpio_base) { + if (s->gpio_used) ret = gpiochip_remove(&s->gpio); - if (ret) - dev_err(dev, "Failed to remove gpio chip: %d\n", ret); - } #endif - dev_set_drvdata(dev, NULL); - - if (s->pdata->suspend) - s->pdata->suspend(1); if (s->pdata->exit) s->pdata->exit(); return ret; } +#ifdef CONFIG_SPI_MASTER +static int max310x_spi_probe(struct spi_device *spi) +{ + struct max310x_devtype *devtype = + (struct max310x_devtype *)spi_get_device_id(spi)->driver_data; + int ret; + + /* Setup SPI bus */ + spi->bits_per_word = 8; + spi->mode = spi->mode ? : SPI_MODE_0; + spi->max_speed_hz = spi->max_speed_hz ? : 26000000; + ret = spi_setup(spi); + if (ret) { + dev_err(&spi->dev, "SPI setup failed\n"); + return ret; + } + + return max310x_probe(&spi->dev, 1, devtype, spi->irq); +} + +static int max310x_spi_remove(struct spi_device *spi) +{ + return max310x_remove(&spi->dev); +} + +static SIMPLE_DEV_PM_OPS(max310x_pm_ops, max310x_suspend, max310x_resume); + static const struct spi_device_id max310x_id_table[] = { - { "max3107", MAX310X_TYPE_MAX3107 }, - { "max3108", MAX310X_TYPE_MAX3108 }, + { "max3107", (kernel_ulong_t)&max3107_devtype, }, + { "max3108", (kernel_ulong_t)&max3108_devtype, }, { } }; MODULE_DEVICE_TABLE(spi, max310x_id_table); -static struct spi_driver max310x_driver = { +static struct spi_driver max310x_uart_driver = { .driver = { - .name = "max310x", + .name = MAX310X_NAME, .owner = THIS_MODULE, - .pm = MAX310X_PM_OPS, + .pm = &max310x_pm_ops, }, - .probe = max310x_probe, - .remove = max310x_remove, + .probe = max310x_spi_probe, + .remove = max310x_spi_remove, .id_table = max310x_id_table, }; -module_spi_driver(max310x_driver); +module_spi_driver(max310x_uart_driver); +#endif -MODULE_LICENSE("GPL v2"); +MODULE_LICENSE("GPL"); MODULE_AUTHOR("Alexander Shiyan "); MODULE_DESCRIPTION("MAX310X serial driver"); diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 91648bf5fc5c..1aec0b620ac3 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -42,9 +42,8 @@ /* MAX310X platform data structure */ struct max310x_pdata { /* Flags global to driver */ - const u8 driver_flags:2; + const u8 driver_flags; #define MAX310X_EXT_CLK (0x00000001) /* External clock enable */ -#define MAX310X_AUTOSLEEP (0x00000002) /* Enable AutoSleep mode */ /* Flags global to UART port */ const u8 uart_flags[MAX310X_MAX_UARTS]; #define MAX310X_LOOPBACK (0x00000001) /* Loopback mode enable */ @@ -60,8 +59,6 @@ struct max310x_pdata { void (*init)(void); /* Called before finish */ void (*exit)(void); - /* Suspend callback */ - void (*suspend)(int do_suspend); }; #endif -- cgit v1.2.3-71-gd317 From 21fc509f1194c2fa06eff4c72238210089c29453 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:18 +0400 Subject: serial: max310x: Add MAX3109 support This patch adds support for MAX3109 (advanced dual universal asynchronous receiver-transmitter) into max310x driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 2 +- drivers/tty/serial/max310x.c | 35 +++++++++++++++++++++++++++++++---- include/linux/platform_data/max310x.h | 4 ++-- 3 files changed, 34 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 25772c15276d..8e1a9c53ad7f 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -297,7 +297,7 @@ config SERIAL_MAX310X default n help This selects support for an advanced UART from Maxim (Dallas). - Supported ICs are MAX3107, MAX3108. + Supported ICs are MAX3107, MAX3108, MAX3109. Each IC contains 128 words each of receive and transmit FIFO that can be controlled through I2C or high-speed SPI. diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 4620289e9e49..a6c46427363b 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8 serial driver + * Maxim (Dallas) MAX3107/8/9 serial driver * * Copyright (C) 2012-2013 Alexander Shiyan * @@ -13,9 +13,6 @@ * (at your option) any later version. */ -/* TODO: MAX3109 support (Dual) */ -/* TODO: MAX14830 support (Quad) */ - #include #include #include @@ -269,6 +266,9 @@ /* MAX3107 specific */ #define MAX3107_REV_ID (0xa0) +/* MAX3109 specific */ +#define MAX3109_REV_ID (0xc0) + struct max310x_devtype { char name[9]; int nr; @@ -359,6 +359,25 @@ static int max3108_detect(struct device *dev) return 0; } +static int max3109_detect(struct device *dev) +{ + struct max310x_port *s = dev_get_drvdata(dev); + unsigned int val = 0; + int ret; + + ret = regmap_read(s->regmap, MAX310X_REVID_REG, &val); + if (ret) + return ret; + + if (((val & MAX310x_REV_MASK) != MAX3109_REV_ID)) { + dev_err(dev, + "%s ID 0x%02x does not match\n", s->devtype->name, val); + return -ENODEV; + } + + return 0; +} + static void max310x_power(struct uart_port *port, int on) { max310x_port_update(port, MAX310X_MODE1_REG, @@ -382,6 +401,13 @@ static const struct max310x_devtype max3108_devtype = { .power = max310x_power, }; +static const struct max310x_devtype max3109_devtype = { + .name = "MAX3109", + .nr = 2, + .detect = max3109_detect, + .power = max310x_power, +}; + static bool max310x_reg_writeable(struct device *dev, unsigned int reg) { switch (reg & 0x1f) { @@ -1226,6 +1252,7 @@ static SIMPLE_DEV_PM_OPS(max310x_pm_ops, max310x_suspend, max310x_resume); static const struct spi_device_id max310x_id_table[] = { { "max3107", (kernel_ulong_t)&max3107_devtype, }, { "max3108", (kernel_ulong_t)&max3108_devtype, }, + { "max3109", (kernel_ulong_t)&max3109_devtype, }, { } }; MODULE_DEVICE_TABLE(spi, max310x_id_table); diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 1aec0b620ac3..4c128eda26ba 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8 serial driver + * Maxim (Dallas) MAX3107/8/9 serial driver * * Copyright (C) 2012 Alexander Shiyan * @@ -37,7 +37,7 @@ * }; */ -#define MAX310X_MAX_UARTS 1 +#define MAX310X_MAX_UARTS 2 /* MAX310X platform data structure */ struct max310x_pdata { -- cgit v1.2.3-71-gd317 From 003236d9ac4d02721867e47f7ad4371ab7f74689 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 29 Jun 2013 10:44:19 +0400 Subject: serial: max310x: Add MAX14830 support This patch adds support for MAX14830 (advanced quad universal asynchronous receiver-transmitter) into max310x driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 2 +- drivers/tty/serial/max310x.c | 45 ++++++++++++++++++++++++++++++++++- include/linux/platform_data/max310x.h | 4 ++-- 3 files changed, 47 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 8e1a9c53ad7f..bc486deeeae5 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -297,7 +297,7 @@ config SERIAL_MAX310X default n help This selects support for an advanced UART from Maxim (Dallas). - Supported ICs are MAX3107, MAX3108, MAX3109. + Supported ICs are MAX3107, MAX3108, MAX3109, MAX14830. Each IC contains 128 words each of receive and transmit FIFO that can be controlled through I2C or high-speed SPI. diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index a6c46427363b..4ab5b272a593 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8/9 serial driver + * Maxim (Dallas) MAX3107/8/9, MAX14830 serial driver * * Copyright (C) 2012-2013 Alexander Shiyan * @@ -269,6 +269,10 @@ /* MAX3109 specific */ #define MAX3109_REV_ID (0xc0) +/* MAX14830 specific */ +#define MAX14830_BRGCFG_CLKDIS_BIT (1 << 6) /* Clock Disable */ +#define MAX14830_REV_ID (0xb0) + struct max310x_devtype { char name[9]; int nr; @@ -387,6 +391,37 @@ static void max310x_power(struct uart_port *port, int on) msleep(50); } +static int max14830_detect(struct device *dev) +{ + struct max310x_port *s = dev_get_drvdata(dev); + unsigned int val = 0; + int ret; + + ret = regmap_write(s->regmap, MAX310X_GLOBALCMD_REG, + MAX310X_EXTREG_ENBL); + if (ret) + return ret; + + regmap_read(s->regmap, MAX310X_REVID_EXTREG, &val); + regmap_write(s->regmap, MAX310X_GLOBALCMD_REG, MAX310X_EXTREG_DSBL); + if (((val & MAX310x_REV_MASK) != MAX14830_REV_ID)) { + dev_err(dev, + "%s ID 0x%02x does not match\n", s->devtype->name, val); + return -ENODEV; + } + + return 0; +} + +static void max14830_power(struct uart_port *port, int on) +{ + max310x_port_update(port, MAX310X_BRGCFG_REG, + MAX14830_BRGCFG_CLKDIS_BIT, + on ? 0 : MAX14830_BRGCFG_CLKDIS_BIT); + if (on) + msleep(50); +} + static const struct max310x_devtype max3107_devtype = { .name = "MAX3107", .nr = 1, @@ -408,6 +443,13 @@ static const struct max310x_devtype max3109_devtype = { .power = max310x_power, }; +static const struct max310x_devtype max14830_devtype = { + .name = "MAX14830", + .nr = 4, + .detect = max14830_detect, + .power = max14830_power, +}; + static bool max310x_reg_writeable(struct device *dev, unsigned int reg) { switch (reg & 0x1f) { @@ -1253,6 +1295,7 @@ static const struct spi_device_id max310x_id_table[] = { { "max3107", (kernel_ulong_t)&max3107_devtype, }, { "max3108", (kernel_ulong_t)&max3108_devtype, }, { "max3109", (kernel_ulong_t)&max3109_devtype, }, + { "max14830", (kernel_ulong_t)&max14830_devtype, }, { } }; MODULE_DEVICE_TABLE(spi, max310x_id_table); diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h index 4c128eda26ba..dd11dcd1a184 100644 --- a/include/linux/platform_data/max310x.h +++ b/include/linux/platform_data/max310x.h @@ -1,5 +1,5 @@ /* - * Maxim (Dallas) MAX3107/8/9 serial driver + * Maxim (Dallas) MAX3107/8/9, MAX14830 serial driver * * Copyright (C) 2012 Alexander Shiyan * @@ -37,7 +37,7 @@ * }; */ -#define MAX310X_MAX_UARTS 2 +#define MAX310X_MAX_UARTS 4 /* MAX310X platform data structure */ struct max310x_pdata { -- cgit v1.2.3-71-gd317 From 12197de2cdb2ded83db7b5a3a06f4b275fb8e62c Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 16 Jul 2013 16:14:38 +0100 Subject: pci_ids.h: move PCI_VENDOR_ID_AMCC here PCI_VENDOR_ID_AMCC is defined locally in "drivers/staging/comedi/comedidev.h" for a few comedi hardware drivers, namely "adl_pci9118", "addi_apci_1500" and "addi_apci_3120" (also "addi_apci_1710" but that is not currently built and will probably be removed soon). Move the define into "include/linux/pci_ids.h" as it is shared by several drivers (albeit all comedi drivers currently). PCI_VENDOR_ID_AMCC happens to have the same value (0x10e8) as PCI_VENDOR_ID_ADDIDATA_OLD. The vendor ID is actually assigned to Applied Micro Circuits Corporation and Addi-Data were using device IDs assigned by AMCC on some of their earlier PCI boards. The PCI_VENDOR_ID_ADDIDATA_OLD define is still being used by the "8250_pci" PCI serial board driver. Signed-off-by: Ian Abbott Acked-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- drivers/staging/comedi/comedidev.h | 1 - include/linux/pci_ids.h | 4 +++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/staging/comedi/comedidev.h b/drivers/staging/comedi/comedidev.h index b75915f30f48..9f4f73fa652c 100644 --- a/drivers/staging/comedi/comedidev.h +++ b/drivers/staging/comedi/comedidev.h @@ -400,7 +400,6 @@ int comedi_driver_unregister(struct comedi_driver *); */ #define PCI_VENDOR_ID_KOLTER 0x1001 #define PCI_VENDOR_ID_ICP 0x104c -#define PCI_VENDOR_ID_AMCC 0x10e8 #define PCI_VENDOR_ID_DT 0x1116 #define PCI_VENDOR_ID_IOTECH 0x1616 #define PCI_VENDOR_ID_CONTEC 0x1221 diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bed2e89611b..9d9911926598 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1311,6 +1311,8 @@ #define PCI_DEVICE_ID_IMS_TT128 0x9128 #define PCI_DEVICE_ID_IMS_TT3D 0x9135 +#define PCI_VENDOR_ID_AMCC 0x10e8 + #define PCI_VENDOR_ID_INTERG 0x10ea #define PCI_DEVICE_ID_INTERG_1682 0x1682 #define PCI_DEVICE_ID_INTERG_2000 0x2000 @@ -2256,7 +2258,7 @@ /* * ADDI-DATA GmbH communication cards */ -#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 +#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 /* actually AMCC */ #define PCI_VENDOR_ID_ADDIDATA 0x15B8 #define PCI_DEVICE_ID_ADDIDATA_APCI7500 0x7000 #define PCI_DEVICE_ID_ADDIDATA_APCI7420 0x7001 -- cgit v1.2.3-71-gd317 From fee8bf4b74e37bfeb8998a349cb788680eb3f634 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Tue, 16 Jul 2013 16:14:41 +0100 Subject: pci_ids.h: remove PCI_VENDOR_ID_ADDIDATA_OLD and PCI_DEVICE_ID_ADDIDATA_APCI7800 These two defines are no longer used. They were only used by the PCI serial driver "8250_pci" to support the original ADDI-DATA APCI-7800 card. In that driver, PCI_VENDOR_ID_ADDIDATA_OLD has been replaced with PCI_VENDOR_ID_AMCC which has the same value (0x10e8), and PCI_DEVICE_ID_ADDIDATA_APCI7800 has been replaced with a local #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 with the same value (0x818e). Signed-off-by: Ian Abbott Acked-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 9d9911926598..6dec3d6abe0b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2258,12 +2258,10 @@ /* * ADDI-DATA GmbH communication cards */ -#define PCI_VENDOR_ID_ADDIDATA_OLD 0x10E8 /* actually AMCC */ #define PCI_VENDOR_ID_ADDIDATA 0x15B8 #define PCI_DEVICE_ID_ADDIDATA_APCI7500 0x7000 #define PCI_DEVICE_ID_ADDIDATA_APCI7420 0x7001 #define PCI_DEVICE_ID_ADDIDATA_APCI7300 0x7002 -#define PCI_DEVICE_ID_ADDIDATA_APCI7800 0x818E #define PCI_DEVICE_ID_ADDIDATA_APCI7500_2 0x7009 #define PCI_DEVICE_ID_ADDIDATA_APCI7420_2 0x700A #define PCI_DEVICE_ID_ADDIDATA_APCI7300_2 0x700B -- cgit v1.2.3-71-gd317 From cf940ebe98e693aec2d10f9af2fb84eb55234e3c Mon Sep 17 00:00:00 2001 From: Andreas Platschek Date: Fri, 26 Jul 2013 06:46:37 +0200 Subject: tty: Remove dead code -> The ledptrs[] array is never initialized. -> There is no place where kbd->ledmode is set to LED_SHOW_MEM therefore the if statement does not make much sense. -> Since LED_SHOW_MEM is not used, it can be removed from the header file as well. Signed-off-by: Andreas Platschek Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/keyboard.c | 21 +-------------------- include/linux/kbd_kern.h | 3 +-- 2 files changed, 2 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index a9af1b9ae160..d0e3a4497707 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -132,12 +132,6 @@ static int shift_state = 0; static unsigned char ledstate = 0xff; /* undefined */ static unsigned char ledioctl; -static struct ledptr { - unsigned int *addr; - unsigned int mask; - unsigned char valid:1; -} ledptrs[3]; - /* * Notifier list for console keyboard events */ @@ -994,24 +988,11 @@ void setledstate(struct kbd_struct *kbd, unsigned int led) static inline unsigned char getleds(void) { struct kbd_struct *kbd = kbd_table + fg_console; - unsigned char leds; - int i; if (kbd->ledmode == LED_SHOW_IOCTL) return ledioctl; - leds = kbd->ledflagstate; - - if (kbd->ledmode == LED_SHOW_MEM) { - for (i = 0; i < 3; i++) - if (ledptrs[i].valid) { - if (*ledptrs[i].addr & ledptrs[i].mask) - leds |= (1 << i); - else - leds &= ~(1 << i); - } - } - return leds; + return kbd->ledflagstate; } static int kbd_update_leds_helper(struct input_handle *handle, void *data) diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h index b7c8cdc1d422..cbfb171bbcba 100644 --- a/include/linux/kbd_kern.h +++ b/include/linux/kbd_kern.h @@ -36,10 +36,9 @@ struct kbd_struct { #define VC_CTRLRLOCK KG_CTRLR /* ctrlr lock mode */ unsigned char slockstate; /* for `sticky' Shift, Ctrl, etc. */ - unsigned char ledmode:2; /* one 2-bit value */ + unsigned char ledmode:1; #define LED_SHOW_FLAGS 0 /* traditional state */ #define LED_SHOW_IOCTL 1 /* only change leds upon ioctl */ -#define LED_SHOW_MEM 2 /* `heartbeat': peek into memory */ unsigned char ledflagstate:4; /* flags, not lights */ unsigned char default_ledflagstate:4; -- cgit v1.2.3-71-gd317 From 6741335bc7294548ac95cb1f4671991ff30da193 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Tue, 2 Jul 2013 10:31:30 -0700 Subject: Drivers: hv: util: Fix a bug in version negotiation code for util services The current code picked the highest version advertised by the host. WS2012 R2 has implemented a protocol version for KVP that is not compatible with prior protocol versions of KVP. Fix the bug in the current code by explicitly specifying the protocol version that the guest can support. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel_mgmt.c | 75 +++++++++++++++++++++++++++++++++-------------- drivers/hv/hv_kvp.c | 24 ++++++++++++++- drivers/hv/hv_snapshot.c | 18 ++++-------- drivers/hv/hv_util.c | 21 +++++++++++-- include/linux/hyperv.h | 10 ++++++- 5 files changed, 109 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 0df75908200e..12ec8c801b25 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -48,30 +48,39 @@ struct vmbus_channel_message_table_entry { * @negop is of type &struct icmsg_negotiate. * Set up and fill in default negotiate response message. * - * The max_fw_version specifies the maximum framework version that - * we can support and max _srv_version specifies the maximum service - * version we can support. A special value MAX_SRV_VER can be - * specified to indicate that we can handle the maximum version - * exposed by the host. + * The fw_version specifies the framework version that + * we can support and srv_version specifies the service + * version we can support. * * Mainly used by Hyper-V drivers. */ -void vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, +bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, struct icmsg_negotiate *negop, u8 *buf, - int max_fw_version, int max_srv_version) + int fw_version, int srv_version) { - int icframe_vercnt; - int icmsg_vercnt; + int icframe_major, icframe_minor; + int icmsg_major, icmsg_minor; + int fw_major, fw_minor; + int srv_major, srv_minor; int i; + bool found_match = false; icmsghdrp->icmsgsize = 0x10; + fw_major = (fw_version >> 16); + fw_minor = (fw_version & 0xFFFF); + + srv_major = (srv_version >> 16); + srv_minor = (srv_version & 0xFFFF); negop = (struct icmsg_negotiate *)&buf[ sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr)]; - icframe_vercnt = negop->icframe_vercnt; - icmsg_vercnt = negop->icmsg_vercnt; + icframe_major = negop->icframe_vercnt; + icframe_minor = 0; + + icmsg_major = negop->icmsg_vercnt; + icmsg_minor = 0; /* * Select the framework version number we will @@ -79,26 +88,48 @@ void vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, */ for (i = 0; i < negop->icframe_vercnt; i++) { - if (negop->icversion_data[i].major <= max_fw_version) - icframe_vercnt = negop->icversion_data[i].major; + if ((negop->icversion_data[i].major == fw_major) && + (negop->icversion_data[i].minor == fw_minor)) { + icframe_major = negop->icversion_data[i].major; + icframe_minor = negop->icversion_data[i].minor; + found_match = true; + } } + if (!found_match) + goto fw_error; + + found_match = false; + for (i = negop->icframe_vercnt; (i < negop->icframe_vercnt + negop->icmsg_vercnt); i++) { - if (negop->icversion_data[i].major <= max_srv_version) - icmsg_vercnt = negop->icversion_data[i].major; + if ((negop->icversion_data[i].major == srv_major) && + (negop->icversion_data[i].minor == srv_minor)) { + icmsg_major = negop->icversion_data[i].major; + icmsg_minor = negop->icversion_data[i].minor; + found_match = true; + } } /* - * Respond with the maximum framework and service + * Respond with the framework and service * version numbers we can support. */ - negop->icframe_vercnt = 1; - negop->icmsg_vercnt = 1; - negop->icversion_data[0].major = icframe_vercnt; - negop->icversion_data[0].minor = 0; - negop->icversion_data[1].major = icmsg_vercnt; - negop->icversion_data[1].minor = 0; + +fw_error: + if (!found_match) { + negop->icframe_vercnt = 0; + negop->icmsg_vercnt = 0; + } else { + negop->icframe_vercnt = 1; + negop->icmsg_vercnt = 1; + } + + negop->icversion_data[0].major = icframe_major; + negop->icversion_data[0].minor = icframe_minor; + negop->icversion_data[1].major = icmsg_major; + negop->icversion_data[1].minor = icmsg_minor; + return found_match; } EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp); diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index ed50e9e83c61..53127209a404 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -29,6 +29,16 @@ #include +/* + * Pre win8 version numbers used in ws2008 and ws 2008 r2 (win7) + */ +#define WIN7_SRV_MAJOR 3 +#define WIN7_SRV_MINOR 0 +#define WIN7_SRV_MAJOR_MINOR (WIN7_SRV_MAJOR << 16 | WIN7_SRV_MINOR) + +#define WIN8_SRV_MAJOR 4 +#define WIN8_SRV_MINOR 0 +#define WIN8_SRV_MAJOR_MINOR (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) /* * Global state maintained for transaction that is being processed. @@ -593,8 +603,19 @@ void hv_kvp_onchannelcallback(void *context) sizeof(struct vmbuspipe_hdr)]; if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { + /* + * We start with win8 version and if the host cannot + * support that we use the previous version. + */ + if (vmbus_prep_negotiate_resp(icmsghdrp, negop, + recv_buffer, UTIL_FW_MAJOR_MINOR, + WIN8_SRV_MAJOR_MINOR)) + goto done; + vmbus_prep_negotiate_resp(icmsghdrp, negop, - recv_buffer, MAX_SRV_VER, MAX_SRV_VER); + recv_buffer, UTIL_FW_MAJOR_MINOR, + WIN7_SRV_MAJOR_MINOR); + } else { kvp_msg = (struct hv_kvp_msg *)&recv_buffer[ sizeof(struct vmbuspipe_hdr) + @@ -626,6 +647,7 @@ void hv_kvp_onchannelcallback(void *context) return; } +done: icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 8ad5653ce447..e4572f3f2834 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -24,6 +24,10 @@ #include #include +#define VSS_MAJOR 5 +#define VSS_MINOR 0 +#define VSS_MAJOR_MINOR (VSS_MAJOR << 16 | VSS_MINOR) + /* @@ -186,18 +190,8 @@ void hv_vss_onchannelcallback(void *context) if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { vmbus_prep_negotiate_resp(icmsghdrp, negop, - recv_buffer, MAX_SRV_VER, MAX_SRV_VER); - /* - * We currently negotiate the highest number the - * host has presented. If this version is not - * atleast 5.0, reject. - */ - negop = (struct icmsg_negotiate *)&recv_buffer[ - sizeof(struct vmbuspipe_hdr) + - sizeof(struct icmsg_hdr)]; - - if (negop->icversion_data[1].major < 5) - negop->icframe_vercnt = 0; + recv_buffer, UTIL_FW_MAJOR_MINOR, + VSS_MAJOR_MINOR); } else { vss_msg = (struct hv_vss_msg *)&recv_buffer[ sizeof(struct vmbuspipe_hdr) + diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 2f561c5dfe24..c16164d4a28b 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -28,6 +28,18 @@ #include #include +#define SHUTDOWN_MAJOR 3 +#define SHUTDOWN_MINOR 0 +#define SHUTDOWN_MAJOR_MINOR (SHUTDOWN_MAJOR << 16 | SHUTDOWN_MINOR) + +#define TIMESYNCH_MAJOR 3 +#define TIMESYNCH_MINOR 0 +#define TIMESYNCH_MAJOR_MINOR (TIMESYNCH_MAJOR << 16 | TIMESYNCH_MINOR) + +#define HEARTBEAT_MAJOR 3 +#define HEARTBEAT_MINOR 0 +#define HEARTBEAT_MAJOR_MINOR (HEARTBEAT_MAJOR << 16 | HEARTBEAT_MINOR) + static void shutdown_onchannelcallback(void *context); static struct hv_util_service util_shutdown = { .util_cb = shutdown_onchannelcallback, @@ -87,7 +99,8 @@ static void shutdown_onchannelcallback(void *context) if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { vmbus_prep_negotiate_resp(icmsghdrp, negop, - shut_txf_buf, MAX_SRV_VER, MAX_SRV_VER); + shut_txf_buf, UTIL_FW_MAJOR_MINOR, + SHUTDOWN_MAJOR_MINOR); } else { shutdown_msg = (struct shutdown_msg_data *)&shut_txf_buf[ @@ -213,7 +226,8 @@ static void timesync_onchannelcallback(void *context) if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { vmbus_prep_negotiate_resp(icmsghdrp, NULL, time_txf_buf, - MAX_SRV_VER, MAX_SRV_VER); + UTIL_FW_MAJOR_MINOR, + TIMESYNCH_MAJOR_MINOR); } else { timedatap = (struct ictimesync_data *)&time_txf_buf[ sizeof(struct vmbuspipe_hdr) + @@ -253,7 +267,8 @@ static void heartbeat_onchannelcallback(void *context) if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { vmbus_prep_negotiate_resp(icmsghdrp, NULL, - hbeat_txf_buf, MAX_SRV_VER, MAX_SRV_VER); + hbeat_txf_buf, UTIL_FW_MAJOR_MINOR, + HEARTBEAT_MAJOR_MINOR); } else { heartbeat_msg = (struct heartbeat_msg_data *)&hbeat_txf_buf[ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fae8bac907ef..49949079cf47 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -27,6 +27,14 @@ #include +/* + * Framework version for util services. + */ + +#define UTIL_FW_MAJOR 3 +#define UTIL_FW_MINOR 0 +#define UTIL_FW_MAJOR_MINOR (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) + /* * Implementation of host controlled snapshot of the guest. @@ -1494,7 +1502,7 @@ struct hyperv_service_callback { }; #define MAX_SRV_VER 0x7ffffff -extern void vmbus_prep_negotiate_resp(struct icmsg_hdr *, +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, struct icmsg_negotiate *, u8 *, int, int); -- cgit v1.2.3-71-gd317 From 410aee70f06da60dd8f78c3ec3346cc74c9bed46 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Sun, 30 Jun 2013 15:27:26 +0300 Subject: usb: phy: protect against NULL phy pointers In order to decrease the amount of work done by PHY users, allow NULL phy pointers to be passed. Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index 44036808bf0f..6c0b1c513db7 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -142,7 +142,7 @@ extern void usb_remove_phy(struct usb_phy *); /* helpers for direct access thru low-level io interface */ static inline int usb_phy_io_read(struct usb_phy *x, u32 reg) { - if (x->io_ops && x->io_ops->read) + if (x && x->io_ops && x->io_ops->read) return x->io_ops->read(x, reg); return -EINVAL; @@ -150,7 +150,7 @@ static inline int usb_phy_io_read(struct usb_phy *x, u32 reg) static inline int usb_phy_io_write(struct usb_phy *x, u32 val, u32 reg) { - if (x->io_ops && x->io_ops->write) + if (x && x->io_ops && x->io_ops->write) return x->io_ops->write(x, val, reg); return -EINVAL; @@ -159,7 +159,7 @@ static inline int usb_phy_io_write(struct usb_phy *x, u32 val, u32 reg) static inline int usb_phy_init(struct usb_phy *x) { - if (x->init) + if (x && x->init) return x->init(x); return 0; @@ -168,14 +168,14 @@ usb_phy_init(struct usb_phy *x) static inline void usb_phy_shutdown(struct usb_phy *x) { - if (x->shutdown) + if (x && x->shutdown) x->shutdown(x); } static inline int usb_phy_vbus_on(struct usb_phy *x) { - if (!x->set_vbus) + if (!x || !x->set_vbus) return 0; return x->set_vbus(x, true); @@ -184,7 +184,7 @@ usb_phy_vbus_on(struct usb_phy *x) static inline int usb_phy_vbus_off(struct usb_phy *x) { - if (!x->set_vbus) + if (!x || !x->set_vbus) return 0; return x->set_vbus(x, false); @@ -258,7 +258,7 @@ usb_phy_set_power(struct usb_phy *x, unsigned mA) static inline int usb_phy_set_suspend(struct usb_phy *x, int suspend) { - if (x->set_suspend != NULL) + if (x && x->set_suspend != NULL) return x->set_suspend(x, suspend); else return 0; @@ -267,7 +267,7 @@ usb_phy_set_suspend(struct usb_phy *x, int suspend) static inline int usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) { - if (x->notify_connect) + if (x && x->notify_connect) return x->notify_connect(x, speed); else return 0; @@ -276,7 +276,7 @@ usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) static inline int usb_phy_notify_disconnect(struct usb_phy *x, enum usb_device_speed speed) { - if (x->notify_disconnect) + if (x && x->notify_disconnect) return x->notify_disconnect(x, speed); else return 0; -- cgit v1.2.3-71-gd317 From 1494a1f62bf7cf57345e9282c8189fe2a21fab64 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Sun, 30 Jun 2013 13:56:45 +0300 Subject: usb: common: introduce of_usb_get_maximum_speed() this helper will be used for controllers which want to work at a lower speed even though they support higher USB transfer rates. One such case is Texas Instruments' AM437x SoC where it uses a USB3 controller without a USB3 PHY, rendering the controller USB2-only. Signed-off-by: Felipe Balbi --- Documentation/devicetree/bindings/usb/generic.txt | 24 +++++++++++ drivers/usb/usb-common.c | 49 ++++++++++++++++++----- include/linux/usb/of.h | 8 ++++ 3 files changed, 70 insertions(+), 11 deletions(-) create mode 100644 Documentation/devicetree/bindings/usb/generic.txt (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/usb/generic.txt b/Documentation/devicetree/bindings/usb/generic.txt new file mode 100644 index 000000000000..477d5bb5e51c --- /dev/null +++ b/Documentation/devicetree/bindings/usb/generic.txt @@ -0,0 +1,24 @@ +Generic USB Properties + +Optional properties: + - maximum-speed: tells USB controllers we want to work up to a certain + speed. Valid arguments are "super-speed", "high-speed", + "full-speed" and "low-speed". In case this isn't passed + via DT, USB controllers should default to their maximum + HW capability. + - dr_mode: tells Dual-Role USB controllers that we want to work on a + particular mode. Valid arguments are "host", + "peripheral" and "otg". In case this attribute isn't + passed via DT, USB DRD controllers should default to + OTG. + +This is an attribute to a USB controller such as: + +dwc3@4a030000 { + compatible = "synopsys,dwc3"; + reg = <0x4a030000 0xcfff>; + interrupts = <0 92 4> + usb-phy = <&usb2_phy>, <&usb3,phy>; + maximum-speed = "super-speed"; + dr_mode = "otg"; +}; diff --git a/drivers/usb/usb-common.c b/drivers/usb/usb-common.c index 675384dabfe9..d771870a819e 100644 --- a/drivers/usb/usb-common.c +++ b/drivers/usb/usb-common.c @@ -43,20 +43,20 @@ const char *usb_otg_state_string(enum usb_otg_state state) } EXPORT_SYMBOL_GPL(usb_otg_state_string); +static const char *const speed_names[] = { + [USB_SPEED_UNKNOWN] = "UNKNOWN", + [USB_SPEED_LOW] = "low-speed", + [USB_SPEED_FULL] = "full-speed", + [USB_SPEED_HIGH] = "high-speed", + [USB_SPEED_WIRELESS] = "wireless", + [USB_SPEED_SUPER] = "super-speed", +}; + const char *usb_speed_string(enum usb_device_speed speed) { - static const char *const names[] = { - [USB_SPEED_UNKNOWN] = "UNKNOWN", - [USB_SPEED_LOW] = "low-speed", - [USB_SPEED_FULL] = "full-speed", - [USB_SPEED_HIGH] = "high-speed", - [USB_SPEED_WIRELESS] = "wireless", - [USB_SPEED_SUPER] = "super-speed", - }; - - if (speed < 0 || speed >= ARRAY_SIZE(names)) + if (speed < 0 || speed >= ARRAY_SIZE(speed_names)) speed = USB_SPEED_UNKNOWN; - return names[speed]; + return speed_names[speed]; } EXPORT_SYMBOL_GPL(usb_speed_string); @@ -112,6 +112,33 @@ enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np) return USB_DR_MODE_UNKNOWN; } EXPORT_SYMBOL_GPL(of_usb_get_dr_mode); + +/** + * of_usb_get_maximum_speed - Get maximum requested speed for a given USB + * controller. + * @np: Pointer to the given device_node + * + * The function gets the maximum speed string from property "maximum-speed", + * and returns the corresponding enum usb_device_speed. + */ +enum usb_device_speed of_usb_get_maximum_speed(struct device_node *np) +{ + const char *maximum_speed; + int err; + int i; + + err = of_property_read_string(np, "maximum-speed", &maximum_speed); + if (err < 0) + return USB_SPEED_UNKNOWN; + + for (i = 0; i < ARRAY_SIZE(speed_names); i++) + if (strcmp(maximum_speed, speed_names[i]) == 0) + return i; + + return USB_SPEED_UNKNOWN; +} +EXPORT_SYMBOL_GPL(of_usb_get_maximum_speed); + #endif MODULE_LICENSE("GPL"); diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index a0ef405368b8..5a7cb9ebf0ef 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -7,16 +7,24 @@ #ifndef __LINUX_USB_OF_H #define __LINUX_USB_OF_H +#include #include #include #if IS_ENABLED(CONFIG_OF) enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np); +enum usb_device_speed of_usb_get_maximum_speed(struct device_node *np); #else static inline enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np) { return USB_DR_MODE_UNKNOWN; } + +static inline enum usb_device_speed +of_usb_get_maximum_speed(struct device_node *np) +{ + return USB_SPEED_UNKNOWN; +} #endif #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_PHY) -- cgit v1.2.3-71-gd317 From 5702f75375aa9ecf8ad3431aef3fe6ce8c8dbd15 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Wed, 17 Jul 2013 11:09:49 +0300 Subject: usb: gadget: udc-core: move sysfs_notify() to a workqueue usb_gadget_set_state() will call sysfs_notify() which might sleep. Some users might want to call usb_gadget_set_state() from the very IRQ handler which actually changes the gadget state. Instead of having every UDC driver add their own workqueue for such a simple notification, we're adding it generically to our struct usb_gadget, so the details are hidden from all UDC drivers. Acked-by: Alan Stern Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc-core.c | 12 +++++++++++- include/linux/usb/gadget.h | 4 ++++ 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c index c28ac9872030..3122ab942f75 100644 --- a/drivers/usb/gadget/udc-core.c +++ b/drivers/usb/gadget/udc-core.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -105,11 +106,18 @@ EXPORT_SYMBOL_GPL(usb_gadget_unmap_request); /* ------------------------------------------------------------------------- */ +static void usb_gadget_state_work(struct work_struct *work) +{ + struct usb_gadget *gadget = work_to_gadget(work); + + sysfs_notify(&gadget->dev.kobj, NULL, "status"); +} + void usb_gadget_set_state(struct usb_gadget *gadget, enum usb_device_state state) { gadget->state = state; - sysfs_notify(&gadget->dev.kobj, NULL, "status"); + schedule_work(&gadget->work); } EXPORT_SYMBOL_GPL(usb_gadget_set_state); @@ -196,6 +204,7 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, goto err1; dev_set_name(&gadget->dev, "gadget"); + INIT_WORK(&gadget->work, usb_gadget_state_work); gadget->dev.parent = parent; #ifdef CONFIG_HAS_DMA @@ -315,6 +324,7 @@ found: usb_gadget_remove_driver(udc); kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE); + flush_work(&gadget->work); device_unregister(&udc->dev); device_unregister(&gadget->dev); } diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index f1b0dca60f12..942ef5e053bf 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -22,6 +22,7 @@ #include #include #include +#include #include struct usb_ep; @@ -475,6 +476,7 @@ struct usb_gadget_ops { /** * struct usb_gadget - represents a usb slave device + * @work: (internal use) Workqueue to be used for sysfs_notify() * @ops: Function pointers used to access hardware-specific operations. * @ep0: Endpoint zero, used when reading or writing responses to * driver setup() requests @@ -520,6 +522,7 @@ struct usb_gadget_ops { * device is acting as a B-Peripheral (so is_a_peripheral is false). */ struct usb_gadget { + struct work_struct work; /* readonly to gadget driver */ const struct usb_gadget_ops *ops; struct usb_ep *ep0; @@ -538,6 +541,7 @@ struct usb_gadget { unsigned out_epnum; unsigned in_epnum; }; +#define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) static inline void set_gadget_data(struct usb_gadget *gadget, void *data) { dev_set_drvdata(&gadget->dev, data); } -- cgit v1.2.3-71-gd317 From f5b8c8b6d3b4697f28b818d8784e3e4b2a290022 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Wed, 17 Jul 2013 10:37:49 +0300 Subject: usb: tegra: Use regulators instead of GPIOs for USB PHY VBUS The tegra ehci driver has enabled USB vbus regulators directly using GPIOs and the device tree attribute nvidia,vbus-gpio. This is ugly and causes error messages on boot when both the regulator driver and the ehci driver want access to the same GPIO. After this patch, usb vbus regulators for tegra usb phy devices are specified with the device tree attribute vbus-supply = <&x> where x is a regulator defined in the device tree. The old nvidia,vbus-gpio property is no longer supported. Signed-off-by: Mikko Perttunen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- drivers/usb/host/ehci-tegra.c | 34 +--------------------------------- drivers/usb/phy/phy-tegra-usb.c | 24 ++++++++++++++++++++++++ include/linux/usb/tegra_usb_phy.h | 1 + 3 files changed, 26 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c index 6ee7ef79b4f8..14c1f35a4b10 100644 --- a/drivers/usb/host/ehci-tegra.c +++ b/drivers/usb/host/ehci-tegra.c @@ -322,33 +322,6 @@ static void tegra_ehci_unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb) free_dma_aligned_buffer(urb); } -static int setup_vbus_gpio(struct platform_device *pdev, - struct tegra_ehci_platform_data *pdata) -{ - int err = 0; - int gpio; - - gpio = pdata->vbus_gpio; - if (!gpio_is_valid(gpio)) - gpio = of_get_named_gpio(pdev->dev.of_node, - "nvidia,vbus-gpio", 0); - if (!gpio_is_valid(gpio)) - return 0; - - err = gpio_request(gpio, "vbus_gpio"); - if (err) { - dev_err(&pdev->dev, "can't request vbus gpio %d", gpio); - return err; - } - err = gpio_direction_output(gpio, 1); - if (err) { - dev_err(&pdev->dev, "can't enable vbus\n"); - return err; - } - - return err; -} - static int tegra_ehci_probe(struct platform_device *pdev) { struct resource *res; @@ -376,14 +349,11 @@ static int tegra_ehci_probe(struct platform_device *pdev) if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - setup_vbus_gpio(pdev, pdata); - hcd = usb_create_hcd(&tegra_ehci_hc_driver, &pdev->dev, dev_name(&pdev->dev)); if (!hcd) { dev_err(&pdev->dev, "Unable to create HCD\n"); - err = -ENOMEM; - goto cleanup_vbus_gpio; + return -ENOMEM; } platform_set_drvdata(pdev, hcd); ehci = hcd_to_ehci(hcd); @@ -494,8 +464,6 @@ cleanup_clk_get: clk_put(tegra->clk); cleanup_hcd_create: usb_put_hcd(hcd); -cleanup_vbus_gpio: - /* FIXME: Undo setup_vbus_gpio() here */ return err; } diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 3ecd49871b88..d92a63a5b0c9 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -34,6 +34,7 @@ #include #include #include +#include #define ULPI_VIEWPORT 0x170 @@ -613,6 +614,9 @@ static void tegra_usb_phy_close(struct usb_phy *x) { struct tegra_usb_phy *phy = container_of(x, struct tegra_usb_phy, u_phy); + if (!IS_ERR(phy->vbus)) + regulator_disable(phy->vbus); + clk_disable_unprepare(phy->pll_u); } @@ -705,6 +709,16 @@ static int tegra_usb_phy_init(struct tegra_usb_phy *phy) goto fail; } + if (!IS_ERR(phy->vbus)) { + err = regulator_enable(phy->vbus); + if (err) { + dev_err(phy->dev, + "failed to enable usb vbus regulator: %d\n", + err); + goto fail; + } + } + if (phy->is_ulpi_phy) err = ulpi_open(phy); else @@ -896,6 +910,16 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) } else tegra_phy->mode = TEGRA_USB_PHY_MODE_OTG; + /* On some boards, the VBUS regulator doesn't need to be controlled */ + if (of_find_property(np, "vbus-supply", NULL)) { + tegra_phy->vbus = devm_regulator_get(&pdev->dev, "vbus"); + if (IS_ERR(tegra_phy->vbus)) + return PTR_ERR(tegra_phy->vbus); + } else { + dev_notice(&pdev->dev, "no vbus regulator"); + tegra_phy->vbus = ERR_PTR(-ENODEV); + } + tegra_phy->dev = &pdev->dev; err = tegra_usb_phy_init(tegra_phy); if (err < 0) diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d2ca919a5b73..2b5fa947980a 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -55,6 +55,7 @@ struct tegra_usb_phy { struct clk *clk; struct clk *pll_u; struct clk *pad_clk; + struct regulator *vbus; enum tegra_usb_phy_mode mode; void *config; struct usb_phy *ulpi; -- cgit v1.2.3-71-gd317 From 185d0fd570c121c0c3d4527842a097e50e3e7a79 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:01 +0300 Subject: usb: phy: tegra: Remove unnecessary 'dev' field struct usb_phy already has a field for the device pointer, so this unnecessary field can be removed. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-tegra-usb.c | 27 +++++++++++++++------------ include/linux/usb/tegra_usb_phy.h | 1 - 2 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index d92a63a5b0c9..311fe03f16e1 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -211,7 +211,7 @@ static void set_phcd(struct tegra_usb_phy *phy, bool enable) static int utmip_pad_open(struct tegra_usb_phy *phy) { - phy->pad_clk = devm_clk_get(phy->dev, "utmi-pads"); + phy->pad_clk = devm_clk_get(phy->u_phy.dev, "utmi-pads"); if (IS_ERR(phy->pad_clk)) { pr_err("%s: can't get utmip pad clock\n", __func__); return PTR_ERR(phy->pad_clk); @@ -540,13 +540,15 @@ static int ulpi_phy_power_on(struct tegra_usb_phy *phy) ret = gpio_direction_output(phy->reset_gpio, 0); if (ret < 0) { - dev_err(phy->dev, "gpio %d not set to 0\n", phy->reset_gpio); + dev_err(phy->u_phy.dev, "gpio %d not set to 0\n", + phy->reset_gpio); return ret; } msleep(5); ret = gpio_direction_output(phy->reset_gpio, 1); if (ret < 0) { - dev_err(phy->dev, "gpio %d not set to 1\n", phy->reset_gpio); + dev_err(phy->u_phy.dev, "gpio %d not set to 1\n", + phy->reset_gpio); return ret; } @@ -649,29 +651,30 @@ static int ulpi_open(struct tegra_usb_phy *phy) { int err; - phy->clk = devm_clk_get(phy->dev, "ulpi-link"); + phy->clk = devm_clk_get(phy->u_phy.dev, "ulpi-link"); if (IS_ERR(phy->clk)) { pr_err("%s: can't get ulpi clock\n", __func__); return PTR_ERR(phy->clk); } - err = devm_gpio_request(phy->dev, phy->reset_gpio, "ulpi_phy_reset_b"); + err = devm_gpio_request(phy->u_phy.dev, phy->reset_gpio, + "ulpi_phy_reset_b"); if (err < 0) { - dev_err(phy->dev, "request failed for gpio: %d\n", + dev_err(phy->u_phy.dev, "request failed for gpio: %d\n", phy->reset_gpio); return err; } err = gpio_direction_output(phy->reset_gpio, 0); if (err < 0) { - dev_err(phy->dev, "gpio %d direction not set to output\n", + dev_err(phy->u_phy.dev, "gpio %d direction not set to output\n", phy->reset_gpio); return err; } phy->ulpi = otg_ulpi_create(&ulpi_viewport_access_ops, 0); if (!phy->ulpi) { - dev_err(phy->dev, "otg_ulpi_create returned NULL\n"); + dev_err(phy->u_phy.dev, "otg_ulpi_create returned NULL\n"); err = -ENOMEM; return err; } @@ -686,7 +689,7 @@ static int tegra_usb_phy_init(struct tegra_usb_phy *phy) int i; int err; - phy->pll_u = devm_clk_get(phy->dev, "pll_u"); + phy->pll_u = devm_clk_get(phy->u_phy.dev, "pll_u"); if (IS_ERR(phy->pll_u)) { pr_err("Can't get pll_u clock\n"); return PTR_ERR(phy->pll_u); @@ -712,7 +715,7 @@ static int tegra_usb_phy_init(struct tegra_usb_phy *phy) if (!IS_ERR(phy->vbus)) { err = regulator_enable(phy->vbus); if (err) { - dev_err(phy->dev, + dev_err(phy->u_phy.dev, "failed to enable usb vbus regulator: %d\n", err); goto fail; @@ -920,7 +923,7 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) tegra_phy->vbus = ERR_PTR(-ENODEV); } - tegra_phy->dev = &pdev->dev; + tegra_phy->u_phy.dev = &pdev->dev; err = tegra_usb_phy_init(tegra_phy); if (err < 0) return err; @@ -953,7 +956,7 @@ static int tegra_usb_phy_match(struct device *dev, void *data) struct tegra_usb_phy *tegra_phy = dev_get_drvdata(dev); struct device_node *dn = data; - return (tegra_phy->dev->of_node == dn) ? 1 : 0; + return (tegra_phy->u_phy.dev->of_node == dn) ? 1 : 0; } struct usb_phy *tegra_usb_get_phy(struct device_node *dn) diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 2b5fa947980a..c2bc7106aaa8 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -60,7 +60,6 @@ struct tegra_usb_phy { void *config; struct usb_phy *ulpi; struct usb_phy u_phy; - struct device *dev; bool is_legacy_phy; bool is_ulpi_phy; int reset_gpio; -- cgit v1.2.3-71-gd317 From 5fed6828318119656e243c4f0a11955cefc8eebd Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:04 +0300 Subject: ARM: tegra: Remove USB platform data USB-related platform data is not used anymore in the Tegra USB drivers, so remove all of it. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Acked-by: Stephen Warren Signed-off-by: Felipe Balbi --- arch/arm/mach-tegra/tegra.c | 38 +-------------------------------- include/linux/platform_data/tegra_usb.h | 32 --------------------------- include/linux/usb/tegra_usb_phy.h | 5 ----- 3 files changed, 1 insertion(+), 74 deletions(-) delete mode 100644 include/linux/platform_data/tegra_usb.h (limited to 'include/linux') diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c index 0d1e4128d460..fc97cfd52769 100644 --- a/arch/arm/mach-tegra/tegra.c +++ b/arch/arm/mach-tegra/tegra.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include @@ -46,40 +45,6 @@ #include "fuse.h" #include "iomap.h" -static struct tegra_ehci_platform_data tegra_ehci1_pdata = { - .operating_mode = TEGRA_USB_OTG, - .power_down_on_bus_suspend = 1, - .vbus_gpio = -1, -}; - -static struct tegra_ulpi_config tegra_ehci2_ulpi_phy_config = { - .reset_gpio = -1, - .clk = "cdev2", -}; - -static struct tegra_ehci_platform_data tegra_ehci2_pdata = { - .phy_config = &tegra_ehci2_ulpi_phy_config, - .operating_mode = TEGRA_USB_HOST, - .power_down_on_bus_suspend = 1, - .vbus_gpio = -1, -}; - -static struct tegra_ehci_platform_data tegra_ehci3_pdata = { - .operating_mode = TEGRA_USB_HOST, - .power_down_on_bus_suspend = 1, - .vbus_gpio = -1, -}; - -static struct of_dev_auxdata tegra20_auxdata_lookup[] __initdata = { - OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5000000, "tegra-ehci.0", - &tegra_ehci1_pdata), - OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5004000, "tegra-ehci.1", - &tegra_ehci2_pdata), - OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5008000, "tegra-ehci.2", - &tegra_ehci3_pdata), - {} -}; - static void __init tegra_dt_init(void) { struct soc_device_attribute *soc_dev_attr; @@ -112,8 +77,7 @@ static void __init tegra_dt_init(void) * devices */ out: - of_platform_populate(NULL, of_default_bus_match_table, - tegra20_auxdata_lookup, parent); + of_platform_populate(NULL, of_default_bus_match_table, NULL, parent); } static void __init trimslice_init(void) diff --git a/include/linux/platform_data/tegra_usb.h b/include/linux/platform_data/tegra_usb.h deleted file mode 100644 index 66c673fef408..000000000000 --- a/include/linux/platform_data/tegra_usb.h +++ /dev/null @@ -1,32 +0,0 @@ -/* - * Copyright (C) 2010 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef _TEGRA_USB_H_ -#define _TEGRA_USB_H_ - -enum tegra_usb_operating_modes { - TEGRA_USB_DEVICE, - TEGRA_USB_HOST, - TEGRA_USB_OTG, -}; - -struct tegra_ehci_platform_data { - enum tegra_usb_operating_modes operating_mode; - /* power down the phy on bus suspend */ - int power_down_on_bus_suspend; - void *phy_config; - int vbus_gpio; -}; - -#endif /* _TEGRA_USB_H_ */ diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index c2bc7106aaa8..847415313ad2 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -28,11 +28,6 @@ struct tegra_utmip_config { u8 xcvr_lsrslew; }; -struct tegra_ulpi_config { - int reset_gpio; - const char *clk; -}; - enum tegra_usb_phy_port_speed { TEGRA_USB_PHY_PORT_SPEED_FULL = 0, TEGRA_USB_PHY_PORT_SPEED_LOW, -- cgit v1.2.3-71-gd317 From 3b102e8bc0e49d417c7d376af857537080335dbf Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:07 +0300 Subject: usb: phy: tegra: Remove custom PHY locating APIs The Tegra EHCI driver is no longer using these custom functions, so they can be removed. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-tegra-usb.c | 24 ------------------------ include/linux/usb/tegra_usb_phy.h | 2 -- 2 files changed, 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 441c306c050f..fb5bc8cea680 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -968,29 +968,5 @@ static struct platform_driver tegra_usb_phy_driver = { }; module_platform_driver(tegra_usb_phy_driver); -static int tegra_usb_phy_match(struct device *dev, void *data) -{ - struct tegra_usb_phy *tegra_phy = dev_get_drvdata(dev); - struct device_node *dn = data; - - return (tegra_phy->u_phy.dev->of_node == dn) ? 1 : 0; -} - -struct usb_phy *tegra_usb_get_phy(struct device_node *dn) -{ - struct device *dev; - struct tegra_usb_phy *tegra_phy; - - dev = driver_find_device(&tegra_usb_phy_driver.driver, NULL, dn, - tegra_usb_phy_match); - if (!dev) - return ERR_PTR(-EPROBE_DEFER); - - tegra_phy = dev_get_drvdata(dev); - - return &tegra_phy->u_phy; -} -EXPORT_SYMBOL_GPL(tegra_usb_get_phy); - MODULE_DESCRIPTION("Tegra USB PHY driver"); MODULE_LICENSE("GPL v2"); diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 847415313ad2..a095c98184d0 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -60,8 +60,6 @@ struct tegra_usb_phy { int reset_gpio; }; -struct usb_phy *tegra_usb_get_phy(struct device_node *dn); - void tegra_usb_phy_preresume(struct usb_phy *phy); void tegra_usb_phy_postresume(struct usb_phy *phy); -- cgit v1.2.3-71-gd317 From 6558d7edbe069df1220b525362d4aa854a65a8bc Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Thu, 25 Jul 2013 21:38:09 +0300 Subject: usb: phy: tegra: Use DT helpers for dr_mode Use the new of_usb_get_dr_mode helper function for parsing dr_mode from the device tree. Also replace the usage of the custom tegra_usb_phy_mode enum with the standard enum. Signed-off-by: Tuomas Tynkkynen Reviewed-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-tegra-usb.c | 24 ++++++++++++------------ include/linux/usb/tegra_usb_phy.h | 8 +------- 2 files changed, 13 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index fb469f1e8d10..01c30ff8874e 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -377,7 +377,7 @@ static int utmi_phy_power_on(struct tegra_usb_phy *phy) UTMIP_PLLU_ENABLE_DLY_COUNT(phy->freq->enable_delay); writel(val, base + UTMIP_PLL_CFG1); - if (phy->mode == TEGRA_USB_PHY_MODE_DEVICE) { + if (phy->mode == USB_DR_MODE_PERIPHERAL) { val = readl(base + USB_SUSP_CTRL); val &= ~(USB_WAKE_ON_CNNT_EN_DEV | USB_WAKE_ON_DISCON_EN_DEV); writel(val, base + USB_SUSP_CTRL); @@ -412,7 +412,7 @@ static int utmi_phy_power_on(struct tegra_usb_phy *phy) if (phy->is_legacy_phy) { val = readl(base + UTMIP_SPARE_CFG0); - if (phy->mode == TEGRA_USB_PHY_MODE_DEVICE) + if (phy->mode == USB_DR_MODE_PERIPHERAL) val &= ~FUSE_SETUP_SEL; else val |= FUSE_SETUP_SEL; @@ -453,7 +453,7 @@ static int utmi_phy_power_off(struct tegra_usb_phy *phy) utmi_phy_clk_disable(phy); - if (phy->mode == TEGRA_USB_PHY_MODE_DEVICE) { + if (phy->mode == USB_DR_MODE_PERIPHERAL) { val = readl(base + USB_SUSP_CTRL); val &= ~USB_WAKEUP_DEBOUNCE_COUNT(~0); val |= USB_WAKE_ON_CNNT_EN_DEV | USB_WAKEUP_DEBOUNCE_COUNT(5); @@ -907,15 +907,15 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) return -EINVAL; } - err = of_property_match_string(np, "dr_mode", "otg"); - if (err < 0) { - err = of_property_match_string(np, "dr_mode", "peripheral"); - if (err < 0) - tegra_phy->mode = TEGRA_USB_PHY_MODE_HOST; - else - tegra_phy->mode = TEGRA_USB_PHY_MODE_DEVICE; - } else - tegra_phy->mode = TEGRA_USB_PHY_MODE_OTG; + if (of_find_property(np, "dr_mode", NULL)) + tegra_phy->mode = of_usb_get_dr_mode(np); + else + tegra_phy->mode = USB_DR_MODE_HOST; + + if (tegra_phy->mode == USB_DR_MODE_UNKNOWN) { + dev_err(&pdev->dev, "dr_mode is invalid\n"); + return -EINVAL; + } /* On some boards, the VBUS regulator doesn't need to be controlled */ if (of_find_property(np, "vbus-supply", NULL)) { diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index a095c98184d0..d3db274610a1 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -34,12 +34,6 @@ enum tegra_usb_phy_port_speed { TEGRA_USB_PHY_PORT_SPEED_HIGH, }; -enum tegra_usb_phy_mode { - TEGRA_USB_PHY_MODE_DEVICE, - TEGRA_USB_PHY_MODE_HOST, - TEGRA_USB_PHY_MODE_OTG, -}; - struct tegra_xtal_freq; struct tegra_usb_phy { @@ -51,7 +45,7 @@ struct tegra_usb_phy { struct clk *pll_u; struct clk *pad_clk; struct regulator *vbus; - enum tegra_usb_phy_mode mode; + enum usb_dr_mode mode; void *config; struct usb_phy *ulpi; struct usb_phy u_phy; -- cgit v1.2.3-71-gd317 From 49834de234f3cf592c3d242c889ca603db8e7050 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 28 Jul 2013 14:47:02 +0100 Subject: spi: Provide core support for runtime PM during transfers Most SPI drivers that implement runtime PM support use identical code to do so: they acquire a runtime PM lock in prepare_transfer_hardware() and then they release it in unprepare_transfer_hardware(). The variations in this are mostly missing error checking and the choice to use autosuspend. Since these runtime PM calls are normally the only thing in the prepare and unprepare callbacks and the autosuspend API transparently does the right thing on devices with autosuspend disabled factor all of this out into the core with a flag to enable the behaviour. Signed-off-by: Mark Brown Reviewed-by: Stephen Warren Acked-by: Linus Walleij --- drivers/spi/spi.c | 16 ++++++++++++++++ include/linux/spi/spi.h | 5 +++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 978dda2c5239..361cced68069 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -553,6 +553,10 @@ static void spi_pump_messages(struct kthread_work *work) master->unprepare_transfer_hardware(master)) dev_err(&master->dev, "failed to unprepare transfer hardware\n"); + if (master->auto_runtime_pm) { + pm_runtime_mark_last_busy(master->dev.parent); + pm_runtime_put_autosuspend(master->dev.parent); + } return; } @@ -572,11 +576,23 @@ static void spi_pump_messages(struct kthread_work *work) master->busy = true; spin_unlock_irqrestore(&master->queue_lock, flags); + if (!was_busy && master->auto_runtime_pm) { + ret = pm_runtime_get_sync(master->dev.parent); + if (ret < 0) { + dev_err(&master->dev, "Failed to power device: %d\n", + ret); + return; + } + } + if (!was_busy && master->prepare_transfer_hardware) { ret = master->prepare_transfer_hardware(master); if (ret) { dev_err(&master->dev, "failed to prepare transfer hardware\n"); + + if (master->auto_runtime_pm) + pm_runtime_put(master->dev.parent); return; } } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..bf0204c00053 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -254,6 +254,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @busy: message pump is busy * @running: message pump is running * @rt: whether this queue is set to run as a realtime task + * @auto_runtime_pm: the core should ensure a runtime PM reference is held + * while the hardware is prepared, using the parent + * device for the spidev * @prepare_transfer_hardware: a message will soon arrive from the queue * so the subsystem requests the driver to prepare the transfer hardware * by issuing this call @@ -374,11 +377,13 @@ struct spi_master { bool busy; bool running; bool rt; + bool auto_runtime_pm; int (*prepare_transfer_hardware)(struct spi_master *master); int (*transfer_one_message)(struct spi_master *master, struct spi_message *mesg); int (*unprepare_transfer_hardware)(struct spi_master *master); + /* gpio chip select */ int *cs_gpios; }; -- cgit v1.2.3-71-gd317 From 055560b04a8cd063aea916fd083b7aec02c2adb8 Mon Sep 17 00:00:00 2001 From: Elen Song Date: Mon, 22 Jul 2013 16:30:29 +0800 Subject: serial: at91: distinguish usart and uart Distinguish usart and uart by read ip name register, The usart read name is "USAR", The uart and dbgu read name is "DBGU". Signed-off-by: Elen Song Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/atmel_serial.c | 37 +++++++++++++++++++++++++++++++++++++ include/linux/atmel_serial.h | 2 ++ 2 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 1db68713d656..8dbc3e67dfa4 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -97,6 +97,7 @@ static void atmel_stop_rx(struct uart_port *port); #define UART_PUT_BRGR(port,v) __raw_writel(v, (port)->membase + ATMEL_US_BRGR) #define UART_PUT_RTOR(port,v) __raw_writel(v, (port)->membase + ATMEL_US_RTOR) #define UART_PUT_TTGR(port, v) __raw_writel(v, (port)->membase + ATMEL_US_TTGR) +#define UART_GET_IP_NAME(port) __raw_readl((port)->membase + ATMEL_US_NAME) /* PDC registers */ #define UART_PUT_PTCR(port,v) __raw_writel(v, (port)->membase + ATMEL_PDC_PTCR) @@ -166,6 +167,7 @@ struct atmel_uart_port { struct serial_rs485 rs485; /* rs485 settings */ unsigned int tx_done_mask; + bool is_usart; /* usart or uart */ int (*prepare_rx)(struct uart_port *port); int (*prepare_tx)(struct uart_port *port); void (*schedule_rx)(struct uart_port *port); @@ -1477,6 +1479,34 @@ static void atmel_set_ops(struct uart_port *port) } } +/* + * Get ip name usart or uart + */ +static int atmel_get_ip_name(struct uart_port *port) +{ + struct atmel_uart_port *atmel_port = to_atmel_uart_port(port); + int name = UART_GET_IP_NAME(port); + int usart, uart; + /* usart and uart ascii */ + usart = 0x55534152; + uart = 0x44424755; + + atmel_port->is_usart = false; + + if (name == usart) { + dev_dbg(port->dev, "This is usart\n"); + atmel_port->is_usart = true; + } else if (name == uart) { + dev_dbg(port->dev, "This is uart\n"); + atmel_port->is_usart = false; + } else { + dev_err(port->dev, "Not supported ip name, set to uart\n"); + return -EINVAL; + } + + return 0; +} + /* * Perform initialization and enable port for reception */ @@ -2336,6 +2366,13 @@ static int atmel_serial_probe(struct platform_device *pdev) UART_PUT_CR(&port->uart, ATMEL_US_RTSEN); } + /* + * Get port name of usart or uart + */ + ret = atmel_get_ip_name(&port->uart); + if (ret < 0) + goto err_add_port; + return 0; err_add_port: diff --git a/include/linux/atmel_serial.h b/include/linux/atmel_serial.h index fd6833764d72..be201ca2990c 100644 --- a/include/linux/atmel_serial.h +++ b/include/linux/atmel_serial.h @@ -124,4 +124,6 @@ #define ATMEL_US_NER 0x44 /* Number of Errors Register */ #define ATMEL_US_IF 0x4c /* IrDA Filter Register */ +#define ATMEL_US_NAME 0xf0 /* Ip Name */ + #endif -- cgit v1.2.3-71-gd317 From e66c33d579ea566d10e8c8695a7168aae3e02992 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Jul 2013 16:50:28 -0400 Subject: rcu: Add const annotation to char * for RCU tracepoints and functions All the RCU tracepoints and functions that reference char pointers do so with just 'char *' even though they do not modify the contents of the string itself. This will cause warnings if a const char * is used in one of these functions. The RCU tracepoints store the pointer to the string to refer back to them when the trace output is displayed. As this can be minutes, hours or even days later, those strings had better be constant. This change also opens the door to allow the RCU tracepoint strings and their addresses to be exported so that userspace tracing tools can translate the contents of the pointers of the RCU tracepoints. Signed-off-by: Steven Rostedt --- include/linux/rcupdate.h | 4 +-- include/trace/events/rcu.h | 82 +++++++++++++++++++++++----------------------- kernel/rcu.h | 2 +- kernel/rcupdate.c | 2 +- kernel/rcutiny.c | 2 +- kernel/rcutiny_plugin.h | 2 +- kernel/rcutorture.c | 8 ++--- kernel/rcutree.c | 4 +-- kernel/rcutree.h | 2 +- 9 files changed, 54 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4b14bdc911d7..0c38abbe6e35 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,7 +52,7 @@ extern int rcutorture_runnable; /* for sysctl */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) extern void rcutorture_record_test_transition(void); extern void rcutorture_record_progress(unsigned long vernum); -extern void do_trace_rcu_torture_read(char *rcutorturename, +extern void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, @@ -65,7 +65,7 @@ static inline void rcutorture_record_progress(unsigned long vernum) { } #ifdef CONFIG_RCU_TRACE -extern void do_trace_rcu_torture_read(char *rcutorturename, +extern void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 59ebcc89f148..ee2376cfaab3 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -19,12 +19,12 @@ */ TRACE_EVENT(rcu_utilization, - TP_PROTO(char *s), + TP_PROTO(const char *s), TP_ARGS(s), TP_STRUCT__entry( - __field(char *, s) + __field(const char *, s) ), TP_fast_assign( @@ -51,14 +51,14 @@ TRACE_EVENT(rcu_utilization, */ TRACE_EVENT(rcu_grace_period, - TP_PROTO(char *rcuname, unsigned long gpnum, char *gpevent), + TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent), TP_ARGS(rcuname, gpnum, gpevent), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(unsigned long, gpnum) - __field(char *, gpevent) + __field(const char *, gpevent) ), TP_fast_assign( @@ -89,21 +89,21 @@ TRACE_EVENT(rcu_grace_period, */ TRACE_EVENT(rcu_future_grace_period, - TP_PROTO(char *rcuname, unsigned long gpnum, unsigned long completed, + TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed, unsigned long c, u8 level, int grplo, int grphi, - char *gpevent), + const char *gpevent), TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(unsigned long, gpnum) __field(unsigned long, completed) __field(unsigned long, c) __field(u8, level) __field(int, grplo) __field(int, grphi) - __field(char *, gpevent) + __field(const char *, gpevent) ), TP_fast_assign( @@ -132,13 +132,13 @@ TRACE_EVENT(rcu_future_grace_period, */ TRACE_EVENT(rcu_grace_period_init, - TP_PROTO(char *rcuname, unsigned long gpnum, u8 level, + TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level, int grplo, int grphi, unsigned long qsmask), TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(unsigned long, gpnum) __field(u8, level) __field(int, grplo) @@ -168,12 +168,12 @@ TRACE_EVENT(rcu_grace_period_init, */ TRACE_EVENT(rcu_preempt_task, - TP_PROTO(char *rcuname, int pid, unsigned long gpnum), + TP_PROTO(const char *rcuname, int pid, unsigned long gpnum), TP_ARGS(rcuname, pid, gpnum), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(unsigned long, gpnum) __field(int, pid) ), @@ -195,12 +195,12 @@ TRACE_EVENT(rcu_preempt_task, */ TRACE_EVENT(rcu_unlock_preempted_task, - TP_PROTO(char *rcuname, unsigned long gpnum, int pid), + TP_PROTO(const char *rcuname, unsigned long gpnum, int pid), TP_ARGS(rcuname, gpnum, pid), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(unsigned long, gpnum) __field(int, pid) ), @@ -224,14 +224,14 @@ TRACE_EVENT(rcu_unlock_preempted_task, */ TRACE_EVENT(rcu_quiescent_state_report, - TP_PROTO(char *rcuname, unsigned long gpnum, + TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long mask, unsigned long qsmask, u8 level, int grplo, int grphi, int gp_tasks), TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(unsigned long, gpnum) __field(unsigned long, mask) __field(unsigned long, qsmask) @@ -268,15 +268,15 @@ TRACE_EVENT(rcu_quiescent_state_report, */ TRACE_EVENT(rcu_fqs, - TP_PROTO(char *rcuname, unsigned long gpnum, int cpu, char *qsevent), + TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent), TP_ARGS(rcuname, gpnum, cpu, qsevent), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(unsigned long, gpnum) __field(int, cpu) - __field(char *, qsevent) + __field(const char *, qsevent) ), TP_fast_assign( @@ -308,12 +308,12 @@ TRACE_EVENT(rcu_fqs, */ TRACE_EVENT(rcu_dyntick, - TP_PROTO(char *polarity, long long oldnesting, long long newnesting), + TP_PROTO(const char *polarity, long long oldnesting, long long newnesting), TP_ARGS(polarity, oldnesting, newnesting), TP_STRUCT__entry( - __field(char *, polarity) + __field(const char *, polarity) __field(long long, oldnesting) __field(long long, newnesting) ), @@ -352,12 +352,12 @@ TRACE_EVENT(rcu_dyntick, */ TRACE_EVENT(rcu_prep_idle, - TP_PROTO(char *reason), + TP_PROTO(const char *reason), TP_ARGS(reason), TP_STRUCT__entry( - __field(char *, reason) + __field(const char *, reason) ), TP_fast_assign( @@ -376,13 +376,13 @@ TRACE_EVENT(rcu_prep_idle, */ TRACE_EVENT(rcu_callback, - TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen_lazy, + TP_PROTO(const char *rcuname, struct rcu_head *rhp, long qlen_lazy, long qlen), TP_ARGS(rcuname, rhp, qlen_lazy, qlen), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(void *, rhp) __field(void *, func) __field(long, qlen_lazy) @@ -412,13 +412,13 @@ TRACE_EVENT(rcu_callback, */ TRACE_EVENT(rcu_kfree_callback, - TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset, + TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset, long qlen_lazy, long qlen), TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(void *, rhp) __field(unsigned long, offset) __field(long, qlen_lazy) @@ -447,12 +447,12 @@ TRACE_EVENT(rcu_kfree_callback, */ TRACE_EVENT(rcu_batch_start, - TP_PROTO(char *rcuname, long qlen_lazy, long qlen, long blimit), + TP_PROTO(const char *rcuname, long qlen_lazy, long qlen, long blimit), TP_ARGS(rcuname, qlen_lazy, qlen, blimit), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(long, qlen_lazy) __field(long, qlen) __field(long, blimit) @@ -477,12 +477,12 @@ TRACE_EVENT(rcu_batch_start, */ TRACE_EVENT(rcu_invoke_callback, - TP_PROTO(char *rcuname, struct rcu_head *rhp), + TP_PROTO(const char *rcuname, struct rcu_head *rhp), TP_ARGS(rcuname, rhp), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(void *, rhp) __field(void *, func) ), @@ -506,12 +506,12 @@ TRACE_EVENT(rcu_invoke_callback, */ TRACE_EVENT(rcu_invoke_kfree_callback, - TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset), + TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset), TP_ARGS(rcuname, rhp, offset), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(void *, rhp) __field(unsigned long, offset) ), @@ -539,13 +539,13 @@ TRACE_EVENT(rcu_invoke_kfree_callback, */ TRACE_EVENT(rcu_batch_end, - TP_PROTO(char *rcuname, int callbacks_invoked, + TP_PROTO(const char *rcuname, int callbacks_invoked, bool cb, bool nr, bool iit, bool risk), TP_ARGS(rcuname, callbacks_invoked, cb, nr, iit, risk), TP_STRUCT__entry( - __field(char *, rcuname) + __field(const char *, rcuname) __field(int, callbacks_invoked) __field(bool, cb) __field(bool, nr) @@ -577,13 +577,13 @@ TRACE_EVENT(rcu_batch_end, */ TRACE_EVENT(rcu_torture_read, - TP_PROTO(char *rcutorturename, struct rcu_head *rhp, + TP_PROTO(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, unsigned long c), TP_ARGS(rcutorturename, rhp, secs, c_old, c), TP_STRUCT__entry( - __field(char *, rcutorturename) + __field(const char *, rcutorturename) __field(struct rcu_head *, rhp) __field(unsigned long, secs) __field(unsigned long, c_old) @@ -623,13 +623,13 @@ TRACE_EVENT(rcu_torture_read, */ TRACE_EVENT(rcu_barrier, - TP_PROTO(char *rcuname, char *s, int cpu, int cnt, unsigned long done), + TP_PROTO(const char *rcuname, const char *s, int cpu, int cnt, unsigned long done), TP_ARGS(rcuname, s, cpu, cnt, done), TP_STRUCT__entry( - __field(char *, rcuname) - __field(char *, s) + __field(const char *, rcuname) + __field(const char *, s) __field(int, cpu) __field(int, cnt) __field(unsigned long, done) diff --git a/kernel/rcu.h b/kernel/rcu.h index 7f8e7590e3e5..0a90ccc65bfb 100644 --- a/kernel/rcu.h +++ b/kernel/rcu.h @@ -94,7 +94,7 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) extern void kfree(const void *); -static inline bool __rcu_reclaim(char *rn, struct rcu_head *head) +static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) { unsigned long offset = (unsigned long)head->func; diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index cce6ba8bbace..14994d4e1a54 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -377,7 +377,7 @@ EXPORT_SYMBOL_GPL(rcuhead_debug_descr); #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE) -void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp, +void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, unsigned long c) { diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index aa344111de3e..9ed6075dc562 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -264,7 +264,7 @@ void rcu_check_callbacks(int cpu, int user) */ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) { - char *rn = NULL; + const char *rn = NULL; struct rcu_head *next, *list; unsigned long flags; RCU_TRACE(int cb_count = 0); diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 0cd385acccfa..280d06cae352 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -36,7 +36,7 @@ struct rcu_ctrlblk { RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */ RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */ RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */ - RCU_TRACE(char *name); /* Name of RCU type. */ + RCU_TRACE(const char *name); /* Name of RCU type. */ }; /* Definition for rcupdate control block. */ diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index f4871e52c546..3d936f0fbcd8 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -267,7 +267,7 @@ rcutorture_shutdown_notify(struct notifier_block *unused1, * Absorb kthreads into a kernel function that won't return, so that * they won't ever access module text or data again. */ -static void rcutorture_shutdown_absorb(char *title) +static void rcutorture_shutdown_absorb(const char *title) { if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { pr_notice( @@ -337,7 +337,7 @@ rcu_random(struct rcu_random_state *rrsp) } static void -rcu_stutter_wait(char *title) +rcu_stutter_wait(const char *title) { while (stutter_pause_test || !rcutorture_runnable) { if (rcutorture_runnable) @@ -366,7 +366,7 @@ struct rcu_torture_ops { int (*stats)(char *page); int irq_capable; int can_boost; - char *name; + const char *name; }; static struct rcu_torture_ops *cur_ops; @@ -1364,7 +1364,7 @@ rcu_torture_stutter(void *arg) } static inline void -rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag) +rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) { pr_alert("%s" TORTURE_FLAG "--- %s: nreaders=%d nfakewriters=%d " diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 068de3a93606..30201494560b 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1032,7 +1032,7 @@ static unsigned long rcu_cbs_completed(struct rcu_state *rsp, * rcu_nocb_wait_gp(). */ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c, char *s) + unsigned long c, const char *s) { trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, rnp->completed, c, rnp->level, @@ -2720,7 +2720,7 @@ static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy) * Helper function for _rcu_barrier() tracing. If tracing is disabled, * the compiler is expected to optimize this away. */ -static void _rcu_barrier_trace(struct rcu_state *rsp, char *s, +static void _rcu_barrier_trace(struct rcu_state *rsp, const char *s, int cpu, unsigned long done) { trace_rcu_barrier(rsp->name, s, cpu, diff --git a/kernel/rcutree.h b/kernel/rcutree.h index b3832581043c..cbdeac6cea9e 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -445,7 +445,7 @@ struct rcu_state { /* for CPU stalls. */ unsigned long gp_max; /* Maximum GP duration in */ /* jiffies. */ - char *name; /* Name of structure. */ + const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ struct irq_work wakeup_work; /* Postponed wakeups */ -- cgit v1.2.3-71-gd317 From 9cf7b244187bba5964d4bf7438946baa2a974466 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 30 Jul 2013 09:09:15 +0300 Subject: usb: of: fix build breakage caused by recent patches commit 052a11d (usb: phy: make PHY driver selection possible by controller drivers) changed the rules on how drivers/usb/phy/of.c would be compiled and failed to update include/linux/usb/of.h accordingly. Because of that, we can fall into situations where of_usb_get_phy_mode() is redefined. In order to fix the error, we update the IS_ENABLED() check in include/linux/usb/of.h to reflect the condition where of.c is built. Reported-by: Stephen Rothwell Signed-off-by: Felipe Balbi --- include/linux/usb/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index 5a7cb9ebf0ef..8c38aa26b3bb 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -27,7 +27,7 @@ of_usb_get_maximum_speed(struct device_node *np) } #endif -#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_PHY) +#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_SUPPORT) enum usb_phy_interface of_usb_get_phy_mode(struct device_node *np); #else static inline enum usb_phy_interface of_usb_get_phy_mode(struct device_node *np) -- cgit v1.2.3-71-gd317 From 1207637304990374231fe4e9aeb527904f4ec1e6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Jul 2013 08:30:16 -0400 Subject: workqueue: mark WQ_NON_REENTRANT deprecated dbf2576e37 ("workqueue: make all workqueues non-reentrant") made WQ_NON_REENTRANT no-op but the following patches didn't remove the flag or update the documentation. Let's mark the flag deprecated and update the documentation accordingly. Signed-off-by: Tejun Heo --- Documentation/workqueue.txt | 18 ++++++------------ include/linux/workqueue.h | 7 ++++++- 2 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt index a6ab4b62d926..67113f622880 100644 --- a/Documentation/workqueue.txt +++ b/Documentation/workqueue.txt @@ -100,8 +100,8 @@ Subsystems and drivers can create and queue work items through special workqueue API functions as they see fit. They can influence some aspects of the way the work items are executed by setting flags on the workqueue they are putting the work item on. These flags include -things like CPU locality, reentrancy, concurrency limits, priority and -more. To get a detailed overview refer to the API description of +things like CPU locality, concurrency limits, priority and more. To +get a detailed overview refer to the API description of alloc_workqueue() below. When a work item is queued to a workqueue, the target gcwq and @@ -166,16 +166,6 @@ resources, scheduled and executed. @flags: - WQ_NON_REENTRANT - - By default, a wq guarantees non-reentrance only on the same - CPU. A work item may not be executed concurrently on the same - CPU by multiple workers but is allowed to be executed - concurrently on multiple CPUs. This flag makes sure - non-reentrance is enforced across all CPUs. Work items queued - to a non-reentrant wq are guaranteed to be executed by at most - one worker system-wide at any given time. - WQ_UNBOUND Work items queued to an unbound wq are served by a special @@ -233,6 +223,10 @@ resources, scheduled and executed. This flag is meaningless for unbound wq. +Note that the flag WQ_NON_REENTRANT no longer exists as all workqueues +are now non-reentrant - any work item is guaranteed to be executed by +at most one worker system-wide at any given time. + @max_active: @max_active determines the maximum number of execution contexts per diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index a0ed78ab54d7..594521ba0d43 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -295,7 +295,12 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * Documentation/workqueue.txt. */ enum { - WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ + /* + * All wqs are now non-reentrant making the following flag + * meaningless. Will be removed. + */ + WQ_NON_REENTRANT = 1 << 0, /* DEPRECATED */ + WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ -- cgit v1.2.3-71-gd317 From 4bdfb2729c3a396fe7400c9332c49aee2b971bd8 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 29 Jul 2013 21:00:53 +0100 Subject: regulator: core: Add missing stub for regulator_get_exclusive() Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 3a76389c6aaa..60da4a62c402 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -211,6 +211,13 @@ static inline struct regulator *__must_check regulator_get(struct device *dev, return NULL; } +static inline struct regulator *__must_check +regulator_get_exclusive(struct device *dev, const char *id) +{ + return NULL; +} + + static inline struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id) { -- cgit v1.2.3-71-gd317 From de1dd9fd2156874b45803299b3b27e65d5defdd9 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 29 Jul 2013 21:42:42 +0100 Subject: regulator: core: Provide hints to the core about optional supplies While the majority of supplies on devices are mandatory and can't be physically omitted for electrical reasons some devices do have optional supplies and need to know if they are missing, MMC being the most common of these. Currently the core accurately reports all errors when regulators are requested since it does not know if the supply is one that must be provided even if by a regulator software does not know about or if it is one that may genuinely be disconnected. In order to allow this behaviour to be changed and stub regulators to be provided in the former case add a new regulator request function regulator_get_optional() which provides a hint to the core that the regulator may genuinely not be connected. Currently the implementation is identical to the current behaviour, future patches will add support in the core for returning stub regulators in the case where normal regulator_get() fails and the board has requested it. Signed-off-by: Mark Brown Acked-by: Chris Ball --- drivers/regulator/core.c | 59 ++++++++++++++++++++++++++++++++++++++ include/linux/regulator/consumer.h | 18 +++++++++++- 2 files changed, 76 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 288c75abc190..a27a5b6267dd 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1409,6 +1409,65 @@ struct regulator *regulator_get_exclusive(struct device *dev, const char *id) } EXPORT_SYMBOL_GPL(regulator_get_exclusive); +/** + * regulator_get_optional - obtain optional access to a regulator. + * @dev: device for regulator "consumer" + * @id: Supply name or regulator ID. + * + * Returns a struct regulator corresponding to the regulator producer, + * or IS_ERR() condition containing errno. Other consumers will be + * unable to obtain this reference is held and the use count for the + * regulator will be initialised to reflect the current state of the + * regulator. + * + * This is intended for use by consumers for devices which can have + * some supplies unconnected in normal use, such as some MMC devices. + * It can allow the regulator core to provide stub supplies for other + * supplies requested using normal regulator_get() calls without + * disrupting the operation of drivers that can handle absent + * supplies. + * + * Use of supply names configured via regulator_set_device_supply() is + * strongly encouraged. It is recommended that the supply name used + * should match the name used for the supply and/or the relevant + * device pins in the datasheet. + */ +struct regulator *regulator_get_optional(struct device *dev, const char *id) +{ + return _regulator_get(dev, id, 0); +} +EXPORT_SYMBOL_GPL(regulator_get_optional); + +/** + * devm_regulator_get_optional - Resource managed regulator_get_optional() + * @dev: device for regulator "consumer" + * @id: Supply name or regulator ID. + * + * Managed regulator_get_optional(). Regulators returned from this + * function are automatically regulator_put() on driver detach. See + * regulator_get_optional() for more information. + */ +struct regulator *devm_regulator_get_optional(struct device *dev, + const char *id) +{ + struct regulator **ptr, *regulator; + + ptr = devres_alloc(devm_regulator_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + regulator = regulator_get_optional(dev, id); + if (!IS_ERR(regulator)) { + *ptr = regulator; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return regulator; +} +EXPORT_SYMBOL_GPL(devm_regulator_get_optional); + /* Locks held by regulator_put() */ static void _regulator_put(struct regulator *regulator) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 60da4a62c402..e2bac6db4abc 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -137,6 +137,10 @@ struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id); struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id); +struct regulator *__must_check regulator_get_optional(struct device *dev, + const char *id); +struct regulator *__must_check devm_regulator_get_optional(struct device *dev, + const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -211,15 +215,27 @@ static inline struct regulator *__must_check regulator_get(struct device *dev, return NULL; } +static inline struct regulator *__must_check +devm_regulator_get(struct device *dev, const char *id) +{ + return NULL; +} + static inline struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id) { return NULL; } +static inline struct regulator *__must_check +regulator_get_optional(struct device *dev, const char *id) +{ + return NULL; +} + static inline struct regulator *__must_check -devm_regulator_get(struct device *dev, const char *id) +devm_regulator_get_optional(struct device *dev, const char *id) { return NULL; } -- cgit v1.2.3-71-gd317 From 6f4b7e632d78c2d91502211c430722cc66428492 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 16:18:36 +0800 Subject: cgroup: more naming cleanups Constantly use @cset for css_set variables and use @cgrp as cgroup variables. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 6 +++--- kernel/cgroup.c | 26 +++++++++++++------------- kernel/cpuset.c | 16 ++++++++-------- 3 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 297462b9f41a..00a7e07a1567 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -394,8 +394,8 @@ struct cgroup_map_cb { /* cftype->flags */ enum { - CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cg */ - CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cg */ + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ }; @@ -513,7 +513,7 @@ struct cftype_set { }; struct cgroup_scanner { - struct cgroup *cg; + struct cgroup *cgrp; int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); void (*process_task)(struct task_struct *p, struct cgroup_scanner *scan); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ed2104304833..9577bebe2546 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -466,7 +466,7 @@ static inline void put_css_set_taskexit(struct css_set *cset) * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * - * Returns true if "cg" matches "old_cg" except for the hierarchy + * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */ static bool compare_css_sets(struct css_set *cset, @@ -1839,7 +1839,7 @@ EXPORT_SYMBOL_GPL(task_cgroup_path_from_hierarchy); struct task_and_cgroup { struct task_struct *task; struct cgroup *cgrp; - struct css_set *cg; + struct css_set *cset; }; struct cgroup_taskset { @@ -2057,8 +2057,8 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, tc = flex_array_get(group, i); old_cset = task_css_set(tc->task); - tc->cg = find_css_set(old_cset, cgrp); - if (!tc->cg) { + tc->cset = find_css_set(old_cset, cgrp); + if (!tc->cset) { retval = -ENOMEM; goto out_put_css_set_refs; } @@ -2071,7 +2071,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, */ for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); - cgroup_task_migrate(tc->cgrp, tc->task, tc->cg); + cgroup_task_migrate(tc->cgrp, tc->task, tc->cset); } /* nothing is sensitive to fork() after this point. */ @@ -2091,9 +2091,9 @@ out_put_css_set_refs: if (retval) { for (i = 0; i < group_size; i++) { tc = flex_array_get(group, i); - if (!tc->cg) + if (!tc->cset) break; - put_css_set(tc->cg); + put_css_set(tc->cset); } } out_cancel_attach: @@ -2203,9 +2203,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) mutex_lock(&cgroup_mutex); for_each_active_root(root) { - struct cgroup *from_cg = task_cgroup_from_root(from, root); + struct cgroup *from_cgrp = task_cgroup_from_root(from, root); - retval = cgroup_attach_task(from_cg, tsk, false); + retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } @@ -3305,8 +3305,8 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) * guarantees forward progress and that we don't miss any tasks. */ heap->size = 0; - cgroup_iter_start(scan->cg, &it); - while ((p = cgroup_iter_next(scan->cg, &it))) { + cgroup_iter_start(scan->cgrp, &it); + while ((p = cgroup_iter_next(scan->cgrp, &it))) { /* * Only affect tasks that qualify per the caller's callback, * if he provided one @@ -3339,7 +3339,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) * the heap and wasn't inserted */ } - cgroup_iter_end(scan->cg, &it); + cgroup_iter_end(scan->cgrp, &it); if (heap->size) { for (i = 0; i < heap->size; i++) { @@ -3385,7 +3385,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { struct cgroup_scanner scan; - scan.cg = from; + scan.cgrp = from; scan.test_task = NULL; /* select all tasks in cgroup */ scan.process_task = cgroup_transfer_one_task; scan.heap = NULL; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 703bfd5a32a9..1b9c31549797 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -845,7 +845,7 @@ static void cpuset_change_cpumask(struct task_struct *tsk, { struct cpuset *cpus_cs; - cpus_cs = effective_cpumask_cpuset(cgroup_cs(scan->cg)); + cpus_cs = effective_cpumask_cpuset(cgroup_cs(scan->cgrp)); set_cpus_allowed_ptr(tsk, cpus_cs->cpus_allowed); } @@ -866,7 +866,7 @@ static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap) { struct cgroup_scanner scan; - scan.cg = cs->css.cgroup; + scan.cgrp = cs->css.cgroup; scan.test_task = NULL; scan.process_task = cpuset_change_cpumask; scan.heap = heap; @@ -1062,7 +1062,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, static void cpuset_change_nodemask(struct task_struct *p, struct cgroup_scanner *scan) { - struct cpuset *cs = cgroup_cs(scan->cg); + struct cpuset *cs = cgroup_cs(scan->cgrp); struct mm_struct *mm; int migrate; nodemask_t *newmems = scan->data; @@ -1102,7 +1102,7 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) guarantee_online_mems(mems_cs, &newmems); - scan.cg = cs->css.cgroup; + scan.cgrp = cs->css.cgroup; scan.test_task = NULL; scan.process_task = cpuset_change_nodemask; scan.heap = heap; @@ -1275,7 +1275,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) static void cpuset_change_flag(struct task_struct *tsk, struct cgroup_scanner *scan) { - cpuset_update_task_spread_flag(cgroup_cs(scan->cg), tsk); + cpuset_update_task_spread_flag(cgroup_cs(scan->cgrp), tsk); } /* @@ -1295,7 +1295,7 @@ static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap) { struct cgroup_scanner scan; - scan.cg = cs->css.cgroup; + scan.cgrp = cs->css.cgroup; scan.test_task = NULL; scan.process_task = cpuset_change_flag; scan.heap = heap; @@ -1971,7 +1971,7 @@ static int cpuset_css_online(struct cgroup *cgrp) struct cpuset *cs = cgroup_cs(cgrp); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; - struct cgroup *pos_cg; + struct cgroup *pos_cgrp; if (!parent) return 0; @@ -2003,7 +2003,7 @@ static int cpuset_css_online(struct cgroup *cgrp) * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); - cpuset_for_each_child(tmp_cs, pos_cg, parent) { + cpuset_for_each_child(tmp_cs, pos_cgrp, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; -- cgit v1.2.3-71-gd317 From 4e96ee8e981b5140a2bcc5fff0d5c0eef39a62ee Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:50:50 +0800 Subject: cgroup: convert cgroup_ida to cgroup_idr This enables us to lookup a cgroup by its id. v4: - add a comment for idr_remove() in cgroup_offline_fn(). v3: - on success, idr_alloc() returns the id but not 0, so fix the BUG_ON() in cgroup_init(). - pass the right value to idr_alloc() so that the id for dummy cgroup is 0. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 4 ++-- kernel/cgroup.c | 33 +++++++++++++++++++++++++++------ 2 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 00a7e07a1567..cca570e188fb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -161,7 +161,7 @@ struct cgroup_name { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - int id; /* ida allocated in-hierarchy ID */ + int id; /* idr allocated in-hierarchy ID */ /* * We link our 'sibling' struct into our parent's 'children'. @@ -322,7 +322,7 @@ struct cgroupfs_root { unsigned long flags; /* IDs for cgroups in this hierarchy */ - struct ida cgroup_ida; + struct idr cgroup_idr; /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 9577bebe2546..3f6593333525 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -866,8 +866,6 @@ static void cgroup_free_fn(struct work_struct *work) */ dput(cgrp->parent->dentry); - ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id); - /* * Drop the active superblock reference that we took when we * created the cgroup. This will free cgrp->root, if we are @@ -1379,6 +1377,7 @@ static void init_cgroup_root(struct cgroupfs_root *root) cgrp->root = root; RCU_INIT_POINTER(cgrp->name, &root_cgroup_name); init_cgroup_housekeeping(cgrp); + idr_init(&root->cgroup_idr); } static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end) @@ -1451,7 +1450,6 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts) */ root->subsys_mask = opts->subsys_mask; root->flags = opts->flags; - ida_init(&root->cgroup_ida); if (opts->release_agent) strcpy(root->release_agent_path, opts->release_agent); if (opts->name) @@ -1467,7 +1465,7 @@ static void cgroup_free_root(struct cgroupfs_root *root) /* hierarhcy ID shoulid already have been released */ WARN_ON_ONCE(root->hierarchy_id); - ida_destroy(&root->cgroup_ida); + idr_destroy(&root->cgroup_idr); kfree(root); } } @@ -1582,6 +1580,11 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, mutex_lock(&cgroup_mutex); mutex_lock(&cgroup_root_mutex); + root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp, + 0, 1, GFP_KERNEL); + if (root_cgrp->id < 0) + goto unlock_drop; + /* Check for name clashes with existing mounts */ ret = -EBUSY; if (strlen(root->name)) @@ -4253,7 +4256,11 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, goto err_free_cgrp; rcu_assign_pointer(cgrp->name, name); - cgrp->id = ida_simple_get(&root->cgroup_ida, 1, 0, GFP_KERNEL); + /* + * Temporarily set the pointer to NULL, so idr_find() won't return + * a half-baked cgroup. + */ + cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL); if (cgrp->id < 0) goto err_free_name; @@ -4351,6 +4358,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, } } + idr_replace(&root->cgroup_idr, cgrp, cgrp->id); + err = cgroup_addrm_files(cgrp, NULL, cgroup_base_files, true); if (err) goto err_destroy; @@ -4377,7 +4386,7 @@ err_free_all: /* Release the reference count that we took on the superblock */ deactivate_super(sb); err_free_id: - ida_simple_remove(&root->cgroup_ida, cgrp->id); + idr_remove(&root->cgroup_idr, cgrp->id); err_free_name: kfree(rcu_dereference_raw(cgrp->name)); err_free_cgrp: @@ -4570,6 +4579,14 @@ static void cgroup_offline_fn(struct work_struct *work) /* delete this cgroup from parent->children */ list_del_rcu(&cgrp->sibling); + /* + * We should remove the cgroup object from idr before its grace + * period starts, so we won't be looking up a cgroup while the + * cgroup is being freed. + */ + idr_remove(&cgrp->root->cgroup_idr, cgrp->id); + cgrp->id = -1; + dput(d); set_bit(CGRP_RELEASABLE, &parent->flags); @@ -4895,6 +4912,10 @@ int __init cgroup_init(void) BUG_ON(cgroup_init_root_id(&cgroup_dummy_root, 0, 1)); + err = idr_alloc(&cgroup_dummy_root.cgroup_idr, cgroup_dummy_top, + 0, 1, GFP_KERNEL); + BUG_ON(err < 0); + mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); -- cgit v1.2.3-71-gd317 From b414dc09a31d41d696093a4cce9fb2853a5ecd4e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:51:06 +0800 Subject: cgroup: document how cgroup IDs are assigned As cgroup id has been used in netprio cgroup and will be used in memcg, it's important to make it clear how a cgroup id is allocated. For example, in netprio cgroup, the id is used as index of anarray. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cca570e188fb..4dfcd0e1b73e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -161,7 +161,13 @@ struct cgroup_name { struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - int id; /* idr allocated in-hierarchy ID */ + /* + * idr allocated in-hierarchy ID. + * + * The ID of the root cgroup is always 0, and a new cgroup + * will be assigned with a smallest available ID. + */ + int id; /* * We link our 'sibling' struct into our parent's 'children'. -- cgit v1.2.3-71-gd317 From e14880f7bb7e0dc0933af304998371dd543ceb40 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 31 Jul 2013 09:51:31 +0800 Subject: cgroup: implement cgroup_from_id() This will be used as a replacement for css_lookup(). There's a difference with cgroup id and css id. cgroup id starts with 0, while css id starts with 1. v4: - also check if cggroup_mutex is held. - make it an inline function. Signed-off-by: Li Zefan Reviewed-by: Michal Hocko Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4dfcd0e1b73e..bbf4d89b56a8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -720,6 +720,24 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, return task_subsys_state(task, subsys_id)->cgroup; } +/** + * cgroup_from_id - lookup cgroup by id + * @ss: cgroup subsys to be looked into + * @id: the cgroup id + * + * Returns the cgroup if there's valid one with @id, otherwise returns NULL. + * Should be called under rcu_read_lock(). + */ +static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) +{ +#ifdef CONFIG_PROVE_RCU + rcu_lockdep_assert(rcu_read_lock_held() || + lockdep_is_held(&cgroup_mutex), + "cgroup_from_id() needs proper protection"); +#endif + return idr_find(&ss->root->cgroup_idr, id); +} + struct cgroup *cgroup_next_sibling(struct cgroup *pos); /** -- cgit v1.2.3-71-gd317 From d6b47b122473885abc882e337ac2d321bbcfb378 Mon Sep 17 00:00:00 2001 From: Ben Guthro Date: Tue, 30 Jul 2013 08:24:52 -0400 Subject: ACPI / sleep: Introduce acpi_os_prepare_extended_sleep() for extended sleep path Like acpi_os_prepare_sleep(), register a callback for use in systems like tboot, and xen, which have system specific requirements outside of ACPICA. This mirrors the functionality in acpi_os_prepare_sleep(), called from acpi_hw_sleep() Signed-off-by: Ben Guthro Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpica/hwesleep.c | 9 +++++++++ drivers/acpi/osl.c | 24 ++++++++++++++++++++++++ include/linux/acpi.h | 7 +++++++ 3 files changed, 40 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c index 5e5f76230f5e..414076818d40 100644 --- a/drivers/acpi/acpica/hwesleep.c +++ b/drivers/acpi/acpica/hwesleep.c @@ -43,6 +43,7 @@ */ #include +#include #include "accommon.h" #define _COMPONENT ACPI_HARDWARE @@ -128,6 +129,14 @@ acpi_status acpi_hw_extended_sleep(u8 sleep_state) ACPI_FLUSH_CPU_CACHE(); + status = acpi_os_prepare_extended_sleep(sleep_state, + acpi_gbl_sleep_type_a, + acpi_gbl_sleep_type_b); + if (ACPI_SKIP(status)) + return_ACPI_STATUS(AE_OK); + if (ACPI_FAILURE(status)) + return_ACPI_STATUS(status); + /* * Set the SLP_TYP and SLP_EN bits. * diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 6ab2c3505520..a934950ff7a0 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -79,6 +79,8 @@ extern char line_buf[80]; static int (*__acpi_os_prepare_sleep)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl); +static int (*__acpi_os_prepare_extended_sleep)(u8 sleep_state, u32 val_a, + u32 val_b); static acpi_osd_handler acpi_irq_handler; static void *acpi_irq_context; @@ -1779,6 +1781,28 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, __acpi_os_prepare_sleep = func; } +acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, + u32 val_b) +{ + int rc = 0; + if (__acpi_os_prepare_extended_sleep) + rc = __acpi_os_prepare_extended_sleep(sleep_state, + val_a, val_b); + if (rc < 0) + return AE_ERROR; + else if (rc > 0) + return AE_CTRL_SKIP; + + return AE_OK; +} + +void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, + u32 val_a, u32 val_b)) +{ + __acpi_os_prepare_extended_sleep = func; +} + + void alloc_acpi_hp_work(acpi_handle handle, u32 type, void *context, void (*func)(struct work_struct *work)) { diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 353ba256f368..a5db4aeefa36 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -481,6 +481,13 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); + +void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, + u32 val_a, u32 val_b)); + +acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, + u32 val_a, u32 val_b); + #ifdef CONFIG_X86 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else -- cgit v1.2.3-71-gd317 From 2816c551c796ec14620325b2c9ed75b9979d3125 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 29 Jul 2013 19:50:33 +0200 Subject: tracing: trace_remove_event_call() should fail if call/file is in use Change trace_remove_event_call(call) to return the error if this call is active. This is what the callers assume but can't verify outside of the tracing locks. Both trace_kprobe.c/trace_uprobe.c need the additional changes, unregister_trace_probe() should abort if trace_remove_event_call() fails. The caller is going to free this call/file so we must ensure that nobody can use them after trace_remove_event_call() succeeds. debugfs should be fine after the previous changes and event_remove() does TRACE_REG_UNREGISTER, but still there are 2 reasons why we need the additional checks: - There could be a perf_event(s) attached to this tp_event, so the patch checks ->perf_refcount. - TRACE_REG_UNREGISTER can be suppressed by FTRACE_EVENT_FL_SOFT_MODE, so we simply check FTRACE_EVENT_FL_ENABLED protected by event_mutex. Link: http://lkml.kernel.org/r/20130729175033.GB26284@redhat.com Reviewed-by: Masami Hiramatsu Signed-off-by: Oleg Nesterov Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 +- kernel/trace/trace_events.c | 35 +++++++++++++++++++++++++++++++++-- 2 files changed, 34 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4372658c73ae..f98ab063e95e 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -332,7 +332,7 @@ extern int trace_define_field(struct ftrace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type); extern int trace_add_event_call(struct ftrace_event_call *call); -extern void trace_remove_event_call(struct ftrace_event_call *call); +extern int trace_remove_event_call(struct ftrace_event_call *call); #define is_signed_type(type) (((type)(-1)) < (type)1) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a67c913e2f9f..ec04836273c0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1713,16 +1713,47 @@ static void __trace_remove_event_call(struct ftrace_event_call *call) destroy_preds(call); } +static int probe_remove_event_call(struct ftrace_event_call *call) +{ + struct trace_array *tr; + struct ftrace_event_file *file; + +#ifdef CONFIG_PERF_EVENTS + if (call->perf_refcount) + return -EBUSY; +#endif + do_for_each_event_file(tr, file) { + if (file->event_call != call) + continue; + /* + * We can't rely on ftrace_event_enable_disable(enable => 0) + * we are going to do, FTRACE_EVENT_FL_SOFT_MODE can suppress + * TRACE_REG_UNREGISTER. + */ + if (file->flags & FTRACE_EVENT_FL_ENABLED) + return -EBUSY; + break; + } while_for_each_event_file(); + + __trace_remove_event_call(call); + + return 0; +} + /* Remove an event_call */ -void trace_remove_event_call(struct ftrace_event_call *call) +int trace_remove_event_call(struct ftrace_event_call *call) { + int ret; + mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); down_write(&trace_event_sem); - __trace_remove_event_call(call); + ret = probe_remove_event_call(call); up_write(&trace_event_sem); mutex_unlock(&event_mutex); mutex_unlock(&trace_types_lock); + + return ret; } #define for_each_event(event, start, end) \ -- cgit v1.2.3-71-gd317 From 90efa75f7ab0be5677f0cca155dbf0b39eacdd03 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 31 Jul 2013 14:56:30 +0400 Subject: serial: sccnxp: Using CLK API for getting UART clock This patch removes "frequency" parameter from SCCNXP platform_data and uses CLK API for getting clock. If CLK ommited, default IC frequency will be used instead. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- arch/mips/sni/a20r.c | 1 - drivers/tty/serial/sccnxp.c | 36 ++++++++++++++++++----------- include/linux/platform_data/serial-sccnxp.h | 3 --- 3 files changed, 22 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index dd0ab982d77e..f9407e170476 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -122,7 +122,6 @@ static struct resource sc26xx_rsrc[] = { static struct sccnxp_pdata sccnxp_data = { .reg_shift = 2, - .frequency = 3686400, .mctrl_cfg[0] = MCTRL_SIG(DTR_OP, LINE_OP7) | MCTRL_SIG(RTS_OP, LINE_OP3) | MCTRL_SIG(DSR_IP, LINE_IP5) | diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c index 12a5c265f43a..81e70477e6fd 100644 --- a/drivers/tty/serial/sccnxp.c +++ b/drivers/tty/serial/sccnxp.c @@ -15,6 +15,7 @@ #define SUPPORT_SYSRQ #endif +#include #include #include #include @@ -783,9 +784,10 @@ static int sccnxp_probe(struct platform_device *pdev) struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); int chiptype = pdev->id_entry->driver_data; struct sccnxp_pdata *pdata = dev_get_platdata(&pdev->dev); - int i, ret, fifosize, freq_min, freq_max; + int i, ret, fifosize, freq_min, freq_max, uartclk; struct sccnxp_port *s; void __iomem *membase; + struct clk *clk; membase = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(membase)) @@ -898,11 +900,25 @@ static int sccnxp_probe(struct platform_device *pdev) } else if (PTR_ERR(s->regulator) == -EPROBE_DEFER) return -EPROBE_DEFER; - if (!pdata) { - dev_warn(&pdev->dev, - "No platform data supplied, using defaults\n"); - s->pdata.frequency = s->freq_std; + clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(clk)) { + if (PTR_ERR(clk) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto err_out; + } + dev_notice(&pdev->dev, "Using default clock frequency\n"); + uartclk = s->freq_std; } else + uartclk = clk_get_rate(clk); + + /* Check input frequency */ + if ((uartclk < freq_min) || (uartclk > freq_max)) { + dev_err(&pdev->dev, "Frequency out of bounds\n"); + ret = -EINVAL; + goto err_out; + } + + if (pdata) memcpy(&s->pdata, pdata, sizeof(struct sccnxp_pdata)); if (s->pdata.poll_time_us) { @@ -920,14 +936,6 @@ static int sccnxp_probe(struct platform_device *pdev) } } - /* Check input frequency */ - if ((s->pdata.frequency < freq_min) || - (s->pdata.frequency > freq_max)) { - dev_err(&pdev->dev, "Frequency out of bounds\n"); - ret = -EINVAL; - goto err_out; - } - s->uart.owner = THIS_MODULE; s->uart.dev_name = "ttySC"; s->uart.major = SCCNXP_MAJOR; @@ -959,7 +967,7 @@ static int sccnxp_probe(struct platform_device *pdev) s->port[i].mapbase = res->start; s->port[i].membase = membase; s->port[i].regshift = s->pdata.reg_shift; - s->port[i].uartclk = s->pdata.frequency; + s->port[i].uartclk = uartclk; s->port[i].ops = &sccnxp_ops; uart_add_one_port(&s->uart, &s->port[i]); /* Set direction to input */ diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index bdc510d03245..af0c8c3b89ae 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -60,7 +60,6 @@ * }; * * static struct sccnxp_pdata sc2892_info = { - * .frequency = 3686400, * .mctrl_cfg[0] = MCTRL_SIG(DIR_OP, LINE_OP0), * .mctrl_cfg[1] = MCTRL_SIG(DIR_OP, LINE_OP1), * }; @@ -78,8 +77,6 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { - /* Frequency (extrenal clock or crystal) */ - int frequency; /* Shift for A0 line */ const u8 reg_shift; /* Modem control lines configuration */ -- cgit v1.2.3-71-gd317 From 85c996907473e4ef824774b97b26499adf66521f Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 31 Jul 2013 14:55:45 +0400 Subject: serial: sccnxp: Add DT support Add DT support to the SCCNCP serial driver. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- .../bindings/tty/serial/sccnxp-serial.txt | 53 ++++++++++++++++++++++ drivers/tty/serial/sccnxp.c | 46 +++++++++++++++---- include/linux/platform_data/serial-sccnxp.h | 6 +-- 3 files changed, 93 insertions(+), 12 deletions(-) create mode 100644 Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt b/Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt new file mode 100644 index 000000000000..d18b1698133e --- /dev/null +++ b/Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt @@ -0,0 +1,53 @@ +* NXP (Philips) SCC+++(SCN+++) serial driver + +Required properties: +- compatible: Should be "nxp,". The supported ICs include sc2681, + sc2691, sc2692, sc2891, sc2892, sc28202, sc68681 and sc68692. +- reg: Address and length of the register set for the device. +- interrupts: Should contain the interrupt number. If omitted, + polling mode will be used instead, so "poll-interval" property should + be populated in this case. + +Optional properties: +- clocks: Phandle to input clock. If omitted, default IC frequency will be + used instead. +- poll-interval: Poll interval time in nanoseconds. +- vcc-supply: The regulator supplying the VCC to drive the chip. +- nxp,sccnxp-io-cfg: Array contains values for the emulated modem signals. + The number of values depends on the UART-number in the selected chip. + Each value should be composed according to the following rules: + (LINE1 << SIGNAL1) | ... | (LINEX << SIGNALX), where: + LINE - VALUE: + OP0 - 1 + OP1 - 2 + OP2 - 3 + OP3 - 4 + OP4 - 5 + OP5 - 6 + OP6 - 7 + OP7 - 8 + IP0 - 9 + IP1 - 10 + IP2 - 11 + IP3 - 12 + IP4 - 13 + IP5 - 14 + IP6 - 15 + SIGNAL - VALUE: + DTR - 0 + RTS - 4 + DSR - 8 + CTS - 12 + DCD - 16 + RNG - 20 + DIR - 24 + +Example (Dual UART with direction control on OP0 & OP1): +sc2892@10100000 { + compatible = "nxp,sc2892"; + reg = <0x10100000 0x10>; + poll-interval = <10000>; + clocks = <&sc2892_clk>; + vcc-supply = <&sc2892_reg>; + nxp,sccnxp-io-cfg = <0x01000000 0x02000000>; +}; diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c index 49e9bbfe6cab..67f73d1a8e7b 100644 --- a/drivers/tty/serial/sccnxp.c +++ b/drivers/tty/serial/sccnxp.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include #include #include @@ -853,10 +855,25 @@ static const struct platform_device_id sccnxp_id_table[] = { }; MODULE_DEVICE_TABLE(platform, sccnxp_id_table); +static const struct of_device_id sccnxp_dt_id_table[] = { + { .compatible = "nxp,sc2681", .data = &sc2681, }, + { .compatible = "nxp,sc2691", .data = &sc2691, }, + { .compatible = "nxp,sc2692", .data = &sc2692, }, + { .compatible = "nxp,sc2891", .data = &sc2891, }, + { .compatible = "nxp,sc2892", .data = &sc2892, }, + { .compatible = "nxp,sc28202", .data = &sc28202, }, + { .compatible = "nxp,sc68681", .data = &sc68681, }, + { .compatible = "nxp,sc68692", .data = &sc68692, }, + { } +}; +MODULE_DEVICE_TABLE(of, sccnxp_dt_id_table); + static int sccnxp_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct sccnxp_pdata *pdata = dev_get_platdata(&pdev->dev); + const struct of_device_id *of_id = + of_match_device(sccnxp_dt_id_table, &pdev->dev); int i, ret, uartclk; struct sccnxp_port *s; void __iomem *membase; @@ -875,7 +892,22 @@ static int sccnxp_probe(struct platform_device *pdev) spin_lock_init(&s->lock); - s->chip = (struct sccnxp_chip *)pdev->id_entry->driver_data; + if (of_id) { + s->chip = (struct sccnxp_chip *)of_id->data; + + of_property_read_u32(pdev->dev.of_node, "poll-interval", + &s->pdata.poll_time_us); + of_property_read_u32(pdev->dev.of_node, "reg-shift", + &s->pdata.reg_shift); + of_property_read_u32_array(pdev->dev.of_node, + "nxp,sccnxp-io-cfg", + s->pdata.mctrl_cfg, s->chip->nr); + } else { + s->chip = (struct sccnxp_chip *)pdev->id_entry->driver_data; + + if (pdata) + memcpy(&s->pdata, pdata, sizeof(struct sccnxp_pdata)); + } s->regulator = devm_regulator_get(&pdev->dev, "vcc"); if (!IS_ERR(s->regulator)) { @@ -906,16 +938,11 @@ static int sccnxp_probe(struct platform_device *pdev) goto err_out; } - if (pdata) - memcpy(&s->pdata, pdata, sizeof(struct sccnxp_pdata)); - if (s->pdata.poll_time_us) { dev_info(&pdev->dev, "Using poll mode, resolution %u usecs\n", s->pdata.poll_time_us); s->poll = 1; - } - - if (!s->poll) { + } else { s->irq = platform_get_irq(pdev, 0); if (s->irq < 0) { dev_err(&pdev->dev, "Missing irq resource data\n"); @@ -1016,8 +1043,9 @@ static int sccnxp_remove(struct platform_device *pdev) static struct platform_driver sccnxp_uart_driver = { .driver = { - .name = SCCNXP_NAME, - .owner = THIS_MODULE, + .name = SCCNXP_NAME, + .owner = THIS_MODULE, + .of_match_table = sccnxp_dt_id_table, }, .probe = sccnxp_probe, .remove = sccnxp_remove, diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index af0c8c3b89ae..98373d6add27 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -78,11 +78,11 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { /* Shift for A0 line */ - const u8 reg_shift; + u32 reg_shift; /* Modem control lines configuration */ - const u32 mctrl_cfg[SCCNXP_MAX_UARTS]; + u32 mctrl_cfg[SCCNXP_MAX_UARTS]; /* Timer value for polling mode (usecs) */ - const unsigned int poll_time_us; + u32 poll_time_us; }; #endif -- cgit v1.2.3-71-gd317 From cfc25993e81f3fa68481d062be634d33184d5eae Mon Sep 17 00:00:00 2001 From: Olaf Hering Date: Wed, 29 May 2013 11:29:07 +0200 Subject: Drivers: hv: remove HV_DRV_VERSION Remove HV_DRV_VERSION, it has no meaning for upstream drivers. Initially it was supposed to show the "Linux Integration Services" version, now it is not in sync anymore with the out-of-tree drivers available from the MSFT website. The only place where a version string is still required is the KVP command "IntegrationServicesVersion" which is handled by tools/hv/hv_kvp_daemon.c. To satisfy such KVP request from the host pass the current string to the daemon during KVP userland registration. Signed-off-by: Olaf Hering Acked-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-hyperv.c | 1 - drivers/hv/hv_balloon.c | 1 - drivers/hv/hv_kvp.c | 2 ++ drivers/hv/hv_util.c | 1 - drivers/hv/vmbus_drv.c | 1 - drivers/net/hyperv/netvsc_drv.c | 2 -- drivers/scsi/storvsc_drv.c | 1 - drivers/video/hyperv_fb.c | 1 - include/linux/hyperv.h | 21 --------------------- 9 files changed, 2 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 713217380b44..8fae6d1414cc 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -590,6 +590,5 @@ static void __exit mousevsc_exit(void) } MODULE_LICENSE("GPL"); -MODULE_VERSION(HV_DRV_VERSION); module_init(mousevsc_init); module_exit(mousevsc_exit); diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 2d094cfdb1e0..7e17a5495e02 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1526,5 +1526,4 @@ static int __init init_balloon_drv(void) module_init(init_balloon_drv); MODULE_DESCRIPTION("Hyper-V Balloon"); -MODULE_VERSION(HV_DRV_VERSION); MODULE_LICENSE("GPL"); diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index 53127209a404..28b03325b872 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -86,7 +86,9 @@ static u8 *recv_buffer; /* * Register the kernel component with the user-level daemon. * As part of this registration, pass the LIC version number. + * This number has no meaning, it satisfies the registration protocol. */ +#define HV_DRV_VERSION "3.1" static void kvp_register(int reg_value) diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index c16164d4a28b..cb82233541b1 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -395,5 +395,4 @@ module_init(init_hyperv_utils); module_exit(exit_hyperv_utils); MODULE_DESCRIPTION("Hyper-V Utilities"); -MODULE_VERSION(HV_DRV_VERSION); MODULE_LICENSE("GPL"); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index e8e071fc1d6d..f9fe46f52cfa 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -816,7 +816,6 @@ static void __exit vmbus_exit(void) MODULE_LICENSE("GPL"); -MODULE_VERSION(HV_DRV_VERSION); subsys_initcall(hv_acpi_init); module_exit(vmbus_exit); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 23a0fff0df52..524f713f6017 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -306,7 +306,6 @@ static void netvsc_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) { strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); - strlcpy(info->version, HV_DRV_VERSION, sizeof(info->version)); strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); } @@ -529,7 +528,6 @@ static int __init netvsc_drv_init(void) } MODULE_LICENSE("GPL"); -MODULE_VERSION(HV_DRV_VERSION); MODULE_DESCRIPTION("Microsoft Hyper-V network driver"); module_init(netvsc_drv_init); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 83ec1aa85964..1a28f5632797 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1879,7 +1879,6 @@ static void __exit storvsc_drv_exit(void) } MODULE_LICENSE("GPL"); -MODULE_VERSION(HV_DRV_VERSION); MODULE_DESCRIPTION("Microsoft Hyper-V virtual storage driver"); module_init(storvsc_drv_init); module_exit(storvsc_drv_exit); diff --git a/drivers/video/hyperv_fb.c b/drivers/video/hyperv_fb.c index d4d2c5fe2488..8ac99b87c07e 100644 --- a/drivers/video/hyperv_fb.c +++ b/drivers/video/hyperv_fb.c @@ -825,5 +825,4 @@ module_init(hvfb_drv_init); module_exit(hvfb_drv_exit); MODULE_LICENSE("GPL"); -MODULE_VERSION(HV_DRV_VERSION); MODULE_DESCRIPTION("Microsoft Hyper-V Synthetic Video Frame Buffer Driver"); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 49949079cf47..a3b8b2e2d244 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -463,27 +463,6 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, *read = dsize - *write; } - -/* - * We use the same version numbering for all Hyper-V modules. - * - * Definition of versioning is as follows; - * - * Major Number Changes for these scenarios; - * 1. When a new version of Windows Hyper-V - * is released. - * 2. A Major change has occurred in the - * Linux IC's. - * (For example the merge for the first time - * into the kernel) Every time the Major Number - * changes, the Revision number is reset to 0. - * Minor Number Changes when new functionality is added - * to the Linux IC's that is not a bug fix. - * - * 3.1 - Added completed hv_utils driver. Shutdown/Heartbeat/Timesync - */ -#define HV_DRV_VERSION "3.1" - /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. -- cgit v1.2.3-71-gd317 From 461a8ecb2d76fb6f3ac1a90eb886697db869d387 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Aug 2013 15:25:19 +0800 Subject: Revert "serial: sccnxp: Add DT support" This reverts commit 85c996907473e4ef824774b97b26499adf66521f. Alexander wishes to remove this patch as it is incorrect. Reported-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- .../bindings/tty/serial/sccnxp-serial.txt | 53 ---------------------- drivers/tty/serial/sccnxp.c | 46 ++++--------------- include/linux/platform_data/serial-sccnxp.h | 6 +-- 3 files changed, 12 insertions(+), 93 deletions(-) delete mode 100644 Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt b/Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt deleted file mode 100644 index d18b1698133e..000000000000 --- a/Documentation/devicetree/bindings/tty/serial/sccnxp-serial.txt +++ /dev/null @@ -1,53 +0,0 @@ -* NXP (Philips) SCC+++(SCN+++) serial driver - -Required properties: -- compatible: Should be "nxp,". The supported ICs include sc2681, - sc2691, sc2692, sc2891, sc2892, sc28202, sc68681 and sc68692. -- reg: Address and length of the register set for the device. -- interrupts: Should contain the interrupt number. If omitted, - polling mode will be used instead, so "poll-interval" property should - be populated in this case. - -Optional properties: -- clocks: Phandle to input clock. If omitted, default IC frequency will be - used instead. -- poll-interval: Poll interval time in nanoseconds. -- vcc-supply: The regulator supplying the VCC to drive the chip. -- nxp,sccnxp-io-cfg: Array contains values for the emulated modem signals. - The number of values depends on the UART-number in the selected chip. - Each value should be composed according to the following rules: - (LINE1 << SIGNAL1) | ... | (LINEX << SIGNALX), where: - LINE - VALUE: - OP0 - 1 - OP1 - 2 - OP2 - 3 - OP3 - 4 - OP4 - 5 - OP5 - 6 - OP6 - 7 - OP7 - 8 - IP0 - 9 - IP1 - 10 - IP2 - 11 - IP3 - 12 - IP4 - 13 - IP5 - 14 - IP6 - 15 - SIGNAL - VALUE: - DTR - 0 - RTS - 4 - DSR - 8 - CTS - 12 - DCD - 16 - RNG - 20 - DIR - 24 - -Example (Dual UART with direction control on OP0 & OP1): -sc2892@10100000 { - compatible = "nxp,sc2892"; - reg = <0x10100000 0x10>; - poll-interval = <10000>; - clocks = <&sc2892_clk>; - vcc-supply = <&sc2892_reg>; - nxp,sccnxp-io-cfg = <0x01000000 0x02000000>; -}; diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c index 67f73d1a8e7b..49e9bbfe6cab 100644 --- a/drivers/tty/serial/sccnxp.c +++ b/drivers/tty/serial/sccnxp.c @@ -20,8 +20,6 @@ #include #include #include -#include -#include #include #include #include @@ -855,25 +853,10 @@ static const struct platform_device_id sccnxp_id_table[] = { }; MODULE_DEVICE_TABLE(platform, sccnxp_id_table); -static const struct of_device_id sccnxp_dt_id_table[] = { - { .compatible = "nxp,sc2681", .data = &sc2681, }, - { .compatible = "nxp,sc2691", .data = &sc2691, }, - { .compatible = "nxp,sc2692", .data = &sc2692, }, - { .compatible = "nxp,sc2891", .data = &sc2891, }, - { .compatible = "nxp,sc2892", .data = &sc2892, }, - { .compatible = "nxp,sc28202", .data = &sc28202, }, - { .compatible = "nxp,sc68681", .data = &sc68681, }, - { .compatible = "nxp,sc68692", .data = &sc68692, }, - { } -}; -MODULE_DEVICE_TABLE(of, sccnxp_dt_id_table); - static int sccnxp_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct sccnxp_pdata *pdata = dev_get_platdata(&pdev->dev); - const struct of_device_id *of_id = - of_match_device(sccnxp_dt_id_table, &pdev->dev); int i, ret, uartclk; struct sccnxp_port *s; void __iomem *membase; @@ -892,22 +875,7 @@ static int sccnxp_probe(struct platform_device *pdev) spin_lock_init(&s->lock); - if (of_id) { - s->chip = (struct sccnxp_chip *)of_id->data; - - of_property_read_u32(pdev->dev.of_node, "poll-interval", - &s->pdata.poll_time_us); - of_property_read_u32(pdev->dev.of_node, "reg-shift", - &s->pdata.reg_shift); - of_property_read_u32_array(pdev->dev.of_node, - "nxp,sccnxp-io-cfg", - s->pdata.mctrl_cfg, s->chip->nr); - } else { - s->chip = (struct sccnxp_chip *)pdev->id_entry->driver_data; - - if (pdata) - memcpy(&s->pdata, pdata, sizeof(struct sccnxp_pdata)); - } + s->chip = (struct sccnxp_chip *)pdev->id_entry->driver_data; s->regulator = devm_regulator_get(&pdev->dev, "vcc"); if (!IS_ERR(s->regulator)) { @@ -938,11 +906,16 @@ static int sccnxp_probe(struct platform_device *pdev) goto err_out; } + if (pdata) + memcpy(&s->pdata, pdata, sizeof(struct sccnxp_pdata)); + if (s->pdata.poll_time_us) { dev_info(&pdev->dev, "Using poll mode, resolution %u usecs\n", s->pdata.poll_time_us); s->poll = 1; - } else { + } + + if (!s->poll) { s->irq = platform_get_irq(pdev, 0); if (s->irq < 0) { dev_err(&pdev->dev, "Missing irq resource data\n"); @@ -1043,9 +1016,8 @@ static int sccnxp_remove(struct platform_device *pdev) static struct platform_driver sccnxp_uart_driver = { .driver = { - .name = SCCNXP_NAME, - .owner = THIS_MODULE, - .of_match_table = sccnxp_dt_id_table, + .name = SCCNXP_NAME, + .owner = THIS_MODULE, }, .probe = sccnxp_probe, .remove = sccnxp_remove, diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index 98373d6add27..af0c8c3b89ae 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -78,11 +78,11 @@ /* SCCNXP platform data structure */ struct sccnxp_pdata { /* Shift for A0 line */ - u32 reg_shift; + const u8 reg_shift; /* Modem control lines configuration */ - u32 mctrl_cfg[SCCNXP_MAX_UARTS]; + const u32 mctrl_cfg[SCCNXP_MAX_UARTS]; /* Timer value for polling mode (usecs) */ - u32 poll_time_us; + const unsigned int poll_time_us; }; #endif -- cgit v1.2.3-71-gd317 From b6aa23ccaea1548cfb404b41129717f13443bccf Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Thu, 1 Aug 2013 16:08:57 -0600 Subject: spi: fix SPI_BIT_MASK so it always fits into 32-bits On a 64-bit platform, ~0UL fills 64-bits, which causes SPI_BIT_MASK(32) not to fit into 32 bits. This causes a warning when the result is assigned to a 32-bit variable. Use ~0U instead to prevent this. This fixes: drivers/spi/spi-gpio.c: In function 'spi_gpio_probe': drivers/spi/spi-gpio.c:446:2: warning: large integer implicitly truncated to unsigned type [-Woverflow] Reported-by: kbuild test robot Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 28e440be1c07..c920c2f4dad5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -309,7 +309,7 @@ struct spi_master { /* bitmask of supported bits_per_word for transfers */ u32 bits_per_word_mask; #define SPI_BPW_MASK(bits) BIT((bits) - 1) -#define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0UL : (BIT(bits) - 1)) +#define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0U : (BIT(bits) - 1)) #define SPI_BPW_RANGE_MASK(min, max) (SPI_BIT_MASK(max) - SPI_BIT_MASK(min - 1)) /* other constraints relevant to this driver */ -- cgit v1.2.3-71-gd317 From abe4c51afda02423c81da6f1eaaa50b733f1ecc2 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Fri, 2 Aug 2013 12:59:44 +0200 Subject: regulators: max8660: add DT bindings This patch adds devicetree bindings for max8660, along with some documentation. Signed-off-by: Daniel Mack Signed-off-by: Mark Brown --- .../devicetree/bindings/regulator/max8660.txt | 47 +++++++++++++ drivers/regulator/max8660.c | 82 +++++++++++++++++++++- include/linux/regulator/max8660.h | 2 +- 3 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 Documentation/devicetree/bindings/regulator/max8660.txt (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/regulator/max8660.txt b/Documentation/devicetree/bindings/regulator/max8660.txt new file mode 100644 index 000000000000..8ba994d8a142 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/max8660.txt @@ -0,0 +1,47 @@ +Maxim MAX8660 voltage regulator + +Required properties: +- compatible: must be one of "maxim,max8660", "maxim,max8661" +- reg: I2C slave address, usually 0x34 +- any required generic properties defined in regulator.txt + +Example: + + i2c_master { + max8660@34 { + compatible = "maxim,max8660"; + reg = <0x34>; + + regulators { + regulator@0 { + regulator-compatible= "V3(DCDC)"; + regulator-min-microvolt = <725000>; + regulator-max-microvolt = <1800000>; + }; + + regulator@1 { + regulator-compatible= "V4(DCDC)"; + regulator-min-microvolt = <725000>; + regulator-max-microvolt = <1800000>; + }; + + regulator@2 { + regulator-compatible= "V5(LDO)"; + regulator-min-microvolt = <1700000>; + regulator-max-microvolt = <2000000>; + }; + + regulator@3 { + regulator-compatible= "V6(LDO)"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + }; + + regulator@4 { + regulator-compatible= "V7(LDO)"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + }; + }; + }; + }; diff --git a/drivers/regulator/max8660.c b/drivers/regulator/max8660.c index 74c11aa00c8a..a4f2f1a38342 100644 --- a/drivers/regulator/max8660.c +++ b/drivers/regulator/max8660.c @@ -44,6 +44,9 @@ #include #include #include +#include +#include +#include #define MAX8660_DCDC_MIN_UV 725000 #define MAX8660_DCDC_MAX_UV 1800000 @@ -310,6 +313,63 @@ enum { MAX8661 = 1, }; +#ifdef CONFIG_OF +static const struct of_device_id max8660_dt_ids[] = { + { .compatible = "maxim,max8660", .data = (void *) MAX8660 }, + { .compatible = "maxim,max8661", .data = (void *) MAX8661 }, + { } +}; +MODULE_DEVICE_TABLE(of, max8660_dt_ids); + +static int max8660_pdata_from_dt(struct device *dev, + struct device_node **of_node, + struct max8660_platform_data *pdata) +{ + int matched, i; + struct device_node *np; + struct max8660_subdev_data *sub; + struct of_regulator_match rmatch[ARRAY_SIZE(max8660_reg)]; + + np = of_find_node_by_name(dev->of_node, "regulators"); + if (!np) { + dev_err(dev, "missing 'regulators' subnode in DT\n"); + return -EINVAL; + } + + for (i = 0; i < ARRAY_SIZE(rmatch); i++) + rmatch[i].name = max8660_reg[i].name; + + matched = of_regulator_match(dev, np, rmatch, ARRAY_SIZE(rmatch)); + if (matched <= 0) + return matched; + + pdata->subdevs = devm_kzalloc(dev, sizeof(struct max8660_subdev_data) * + matched, GFP_KERNEL); + if (!pdata->subdevs) + return -ENOMEM; + + pdata->num_subdevs = matched; + sub = pdata->subdevs; + + for (i = 0; i < matched; i++) { + sub->id = i; + sub->name = rmatch[i].name; + sub->platform_data = rmatch[i].init_data; + of_node[i] = rmatch[i].of_node; + sub++; + } + + return 0; +} +#else +static inline int max8660_pdata_from_dt(struct device *dev, + struct device_node **of_node, + struct max8660_platform_data **pdata) +{ + return 0; +} +#endif + static int max8660_probe(struct i2c_client *client, const struct i2c_device_id *i2c_id) { @@ -319,8 +379,28 @@ static int max8660_probe(struct i2c_client *client, struct regulator_config config = { }; struct max8660 *max8660; int boot_on, i, id, ret = -EINVAL; + struct device_node *of_node[MAX8660_V_END]; unsigned int type; + if (dev->of_node && !pdata) { + const struct of_device_id *id; + struct max8660_platform_data pdata_of; + + id = of_match_device(of_match_ptr(max8660_dt_ids), dev); + if (!id) + return -ENODEV; + + ret = max8660_pdata_from_dt(dev, of_node, &pdata_of); + if (ret < 0) + return ret; + + pdata = &pdata_of; + type = (unsigned int) id->data; + } else { + type = i2c_id->driver_data; + memset(of_node, 0, sizeof(of_node)); + } + if (pdata->num_subdevs > MAX8660_V_END) { dev_err(dev, "Too many regulators found!\n"); return -EINVAL; @@ -334,7 +414,6 @@ static int max8660_probe(struct i2c_client *client, max8660->client = client; rdev = max8660->rdev; - type = i2c_id->driver_data; if (pdata->en34_is_high) { /* Simulate always on */ @@ -407,6 +486,7 @@ static int max8660_probe(struct i2c_client *client, config.dev = dev; config.init_data = pdata->subdevs[i].platform_data; + config.of_node = of_node[i]; config.driver_data = max8660; rdev[i] = regulator_register(&max8660_reg[id], &config); diff --git a/include/linux/regulator/max8660.h b/include/linux/regulator/max8660.h index 9936763621c7..f8a6a4844864 100644 --- a/include/linux/regulator/max8660.h +++ b/include/linux/regulator/max8660.h @@ -39,7 +39,7 @@ enum { */ struct max8660_subdev_data { int id; - char *name; + const char *name; struct regulator_init_data *platform_data; }; -- cgit v1.2.3-71-gd317 From 5ef76da644bf346d29200007d8d3779e7009dabb Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 2 Aug 2013 14:05:20 +0200 Subject: fbdev: simplefb: add init through platform_data If we create proper platform-devices in x86 boot-code, we can use simplefb for VBE or EFI framebuffers, too. However, there is normally no OF support so we introduce a platform_data object so x86 boot-code can pass the parameters via plain old platform-data. This also removes the OF dependency as it is not needed. The headers provide proper dummies for the case OF is disabled. Furthermore, we move the FORMAT-definitions to the common platform header so initialization code can use it to transform "struct screen_info" to the right format-name. Signed-off-by: David Herrmann Link: http://lkml.kernel.org/r/1375445127-15480-2-git-send-email-dh.herrmann@gmail.com Reviewed-by: Stephen Warren Signed-off-by: H. Peter Anvin --- drivers/video/Kconfig | 5 ++- drivers/video/simplefb.c | 48 +++++++++++++++++++++-------- include/linux/platform_data/simplefb.h | 56 ++++++++++++++++++++++++++++++++++ 3 files changed, 93 insertions(+), 16 deletions(-) create mode 100644 include/linux/platform_data/simplefb.h (limited to 'include/linux') diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index 4cf1e1dd5621..34c3d960634d 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -2457,7 +2457,7 @@ config FB_HYPERV config FB_SIMPLE bool "Simple framebuffer support" - depends on (FB = y) && OF + depends on (FB = y) select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -2469,8 +2469,7 @@ config FB_SIMPLE pre-allocated frame buffer surface. Configuration re: surface address, size, and format must be provided - through device tree, or potentially plain old platform data in the - future. + through device tree, or plain old platform data. source "drivers/video/omap/Kconfig" source "drivers/video/omap2/Kconfig" diff --git a/drivers/video/simplefb.c b/drivers/video/simplefb.c index e2e9e3e61b72..588698986ce1 100644 --- a/drivers/video/simplefb.c +++ b/drivers/video/simplefb.c @@ -24,6 +24,7 @@ #include #include #include +#include #include static struct fb_fix_screeninfo simplefb_fix = { @@ -73,18 +74,7 @@ static struct fb_ops simplefb_ops = { .fb_imageblit = cfb_imageblit, }; -struct simplefb_format { - const char *name; - u32 bits_per_pixel; - struct fb_bitfield red; - struct fb_bitfield green; - struct fb_bitfield blue; - struct fb_bitfield transp; -}; - -static struct simplefb_format simplefb_formats[] = { - { "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0} }, -}; +static struct simplefb_format simplefb_formats[] = SIMPLEFB_FORMATS; struct simplefb_params { u32 width; @@ -139,6 +129,33 @@ static int simplefb_parse_dt(struct platform_device *pdev, return 0; } +static int simplefb_parse_pd(struct platform_device *pdev, + struct simplefb_params *params) +{ + struct simplefb_platform_data *pd = pdev->dev.platform_data; + int i; + + params->width = pd->width; + params->height = pd->height; + params->stride = pd->stride; + + params->format = NULL; + for (i = 0; i < ARRAY_SIZE(simplefb_formats); i++) { + if (strcmp(pd->format, simplefb_formats[i].name)) + continue; + + params->format = &simplefb_formats[i]; + break; + } + + if (!params->format) { + dev_err(&pdev->dev, "Invalid format value\n"); + return -EINVAL; + } + + return 0; +} + static int simplefb_probe(struct platform_device *pdev) { int ret; @@ -149,7 +166,12 @@ static int simplefb_probe(struct platform_device *pdev) if (fb_get_options("simplefb", NULL)) return -ENODEV; - ret = simplefb_parse_dt(pdev, ¶ms); + ret = -ENODEV; + if (pdev->dev.platform_data) + ret = simplefb_parse_pd(pdev, ¶ms); + else if (pdev->dev.of_node) + ret = simplefb_parse_dt(pdev, ¶ms); + if (ret) return ret; diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h new file mode 100644 index 000000000000..5fa2c5e02ab8 --- /dev/null +++ b/include/linux/platform_data/simplefb.h @@ -0,0 +1,56 @@ +/* + * simplefb.h - Simple Framebuffer Device + * + * Copyright (C) 2013 David Herrmann + * + * 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. + */ + +#ifndef __PLATFORM_DATA_SIMPLEFB_H__ +#define __PLATFORM_DATA_SIMPLEFB_H__ + +#include +#include +#include + +/* format array, use it to initialize a "struct simplefb_format" array */ +#define SIMPLEFB_FORMATS \ +{ \ + { "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 }, \ +} + +/* + * Data-Format for Simple-Framebuffers + * @name: unique 0-terminated name that can be used to identify the mode + * @red,green,blue: Offsets and sizes of the single RGB parts + * @transp: Offset and size of the alpha bits. length=0 means no alpha + * @fourcc: 32bit DRM four-CC code (see drm_fourcc.h) + */ +struct simplefb_format { + const char *name; + u32 bits_per_pixel; + struct fb_bitfield red; + struct fb_bitfield green; + struct fb_bitfield blue; + struct fb_bitfield transp; + u32 fourcc; +}; + +/* + * Simple-Framebuffer description + * If the arch-boot code creates simple-framebuffers without DT support, it + * can pass the width, height, stride and format via this platform-data object. + * The framebuffer location must be given as IORESOURCE_MEM resource. + * @format must be a format as described in "struct simplefb_format" above. + */ +struct simplefb_platform_data { + u32 width; + u32 height; + u32 stride; + const char *format; +}; + +#endif /* __PLATFORM_DATA_SIMPLEFB_H__ */ -- cgit v1.2.3-71-gd317 From 9a6a36d19c9d24479300511e23933876a4a9cf82 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 2 Aug 2013 14:05:24 +0200 Subject: fbdev: simplefb: add common x86 RGB formats 32bit XRGB and ARGB are used by modern x86 systems for EFI and VESA framebuffers. The other formats were reported by hpa to be most common. Add these so simplefb works on most common x86 systems. Signed-off-by: David Herrmann Link: http://lkml.kernel.org/r/1375445127-15480-6-git-send-email-dh.herrmann@gmail.com Signed-off-by: H. Peter Anvin --- include/linux/platform_data/simplefb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/simplefb.h b/include/linux/platform_data/simplefb.h index 5fa2c5e02ab8..53774b0cd8e9 100644 --- a/include/linux/platform_data/simplefb.h +++ b/include/linux/platform_data/simplefb.h @@ -20,6 +20,13 @@ #define SIMPLEFB_FORMATS \ { \ { "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 }, \ + { "x1r5g5b5", 16, {10, 5}, {5, 5}, {0, 5}, {0, 0}, DRM_FORMAT_XRGB1555 }, \ + { "a1r5g5b5", 16, {10, 5}, {5, 5}, {0, 5}, {15, 1}, DRM_FORMAT_ARGB1555 }, \ + { "r8g8b8", 24, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_RGB888 }, \ + { "x8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_XRGB8888 }, \ + { "a8r8g8b8", 32, {16, 8}, {8, 8}, {0, 8}, {24, 8}, DRM_FORMAT_ARGB8888 }, \ + { "x2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {0, 0}, DRM_FORMAT_XRGB2101010 }, \ + { "a2r10g10b10", 32, {20, 10}, {10, 10}, {0, 10}, {30, 2}, DRM_FORMAT_ARGB2101010 }, \ } /* -- cgit v1.2.3-71-gd317 From ed5467da0e369e65b247b99eb6403cb79172bcda Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Fri, 2 Aug 2013 21:16:43 +0400 Subject: tracing: Fix fields of struct trace_iterator that are zeroed by mistake tracing_read_pipe zeros all fields bellow "seq". The declaration contains a comment about that, but it doesn't help. The first field is "snapshot", it's true when current open file is snapshot. Looks obvious, that it should not be zeroed. The second field is "started". It was converted from cpumask_t to cpumask_var_t (v2.6.28-4983-g4462344), in other words it was converted from cpumask to pointer on cpumask. Currently the reference on "started" memory is lost after the first read from tracing_read_pipe and a proper object will never be freed. The "started" is never dereferenced for trace_pipe, because trace_pipe can't have the TRACE_FILE_ANNOTATE options. Link: http://lkml.kernel.org/r/1375463803-3085183-1-git-send-email-avagin@openvz.org Cc: stable@vger.kernel.org # 2.6.30 Signed-off-by: Andrew Vagin Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 10 ++++++---- kernel/trace/trace.c | 1 + 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index f98ab063e95e..120d57a1c3a5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -78,6 +78,11 @@ struct trace_iterator { /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; + cpumask_var_t started; + + /* it's true when current open file is snapshot */ + bool snapshot; + /* The below is zeroed out in pipe_read */ struct trace_seq seq; struct trace_entry *ent; @@ -90,10 +95,7 @@ struct trace_iterator { loff_t pos; long idx; - cpumask_var_t started; - - /* it's true when current open file is snapshot */ - bool snapshot; + /* All new field here will be zeroed out in pipe_read */ }; enum trace_iter_flags { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 882ec1dd1515..f5b35a5e852f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4151,6 +4151,7 @@ waitagain: memset(&iter->seq, 0, sizeof(struct trace_iterator) - offsetof(struct trace_iterator, seq)); + cpumask_clear(iter->started); iter->pos = -1; trace_event_read_lock(); -- cgit v1.2.3-71-gd317 From e67bc51e574ffe3c4bc1e09cab7658b1e780b4ce Mon Sep 17 00:00:00 2001 From: Dhaval Giani Date: Fri, 2 Aug 2013 14:47:29 -0400 Subject: tracing: Fix trace_dump_stack() proto when CONFIG_TRACING is not set When CONFIG_TRACING is not enabled, the stub prototype for trace_dump_stack() is incorrect. It has (void) when it should be (int). Link: http://lkml.kernel.org/r/CAPhKKr_H=ukFnBL4WgDOVT5ay2xeF-Ho+CA0DWZX0E2JW-=vSQ@mail.gmail.com Signed-off-by: Dhaval Giani Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3bef14c6586b..482ad2d84a32 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -629,7 +629,7 @@ extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); static inline void tracing_start(void) { } static inline void tracing_stop(void) { } static inline void ftrace_off_permanent(void) { } -static inline void trace_dump_stack(void) { } +static inline void trace_dump_stack(int skip) { } static inline void tracing_on(void) { } static inline void tracing_off(void) { } -- cgit v1.2.3-71-gd317 From 626f090c5cbbe557379978c7a9525011ad7fbbf6 Mon Sep 17 00:00:00 2001 From: Yacine Belkadi Date: Fri, 2 Aug 2013 20:10:04 +0200 Subject: usb: fix some scripts/kernel-doc warnings When building the htmldocs (in verbose mode), scripts/kernel-doc reports the following type of warnings: Warning(drivers/usb/core/usb.c:76): No description found for return value of 'usb_find_alt_setting' Fix them by: - adding some missing descriptions of return values - using "Return" sections for those descriptions Signed-off-by: Yacine Belkadi Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/buffer.c | 5 ++-- drivers/usb/core/driver.c | 22 +++++++++++++++-- drivers/usb/core/file.c | 2 +- drivers/usb/core/hcd-pci.c | 2 ++ drivers/usb/core/hcd.c | 37 ++++++++++++++++++++-------- drivers/usb/core/hub.c | 37 +++++++++++++++++++--------- drivers/usb/core/message.c | 49 ++++++++++++++++++++----------------- drivers/usb/core/urb.c | 34 ++++++++++++++++---------- drivers/usb/core/usb.c | 60 ++++++++++++++++++++++++++++------------------ include/linux/usb.h | 12 ++++++---- 10 files changed, 173 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index b0585e623ba9..23559746be92 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -43,10 +43,11 @@ static const size_t pool_max[HCD_BUFFER_POOLS] = { * * Call this as part of initializing a host controller that uses the dma * memory allocators. It initializes some pools of dma-coherent memory that - * will be shared by all drivers using that controller, or returns a negative - * errno value on error. + * will be shared by all drivers using that controller. * * Call hcd_buffer_destroy() to clean up after using those pools. + * + * Return: 0 if successful. A negative errno value otherwise. */ int hcd_buffer_create(struct usb_hcd *hcd) { diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 7609ac4aed1c..124bcc50b0b7 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -117,6 +117,8 @@ static DRIVER_ATTR(new_id, S_IRUGO | S_IWUSR, show_dynids, store_new_id); * @count: input size * * Removes a dynamic usb device ID from this driver. + * + * Return: @count on success. A negative error code otherwise. */ static ssize_t store_remove_id(struct device_driver *driver, const char *buf, size_t count) @@ -457,6 +459,8 @@ static int usb_unbind_interface(struct device *dev) * Callers must own the device lock, so driver probe() entries don't need * extra locking, but other call contexts may need to explicitly claim that * lock. + * + * Return: 0 on success. */ int usb_driver_claim_interface(struct usb_driver *driver, struct usb_interface *iface, void *priv) @@ -658,6 +662,8 @@ EXPORT_SYMBOL_GPL(usb_match_one_id); * These device tables are exported with MODULE_DEVICE_TABLE, through * modutils, to support the driver loading functionality of USB hotplugging. * + * Return: The first matching usb_device_id, or %NULL. + * * What Matches: * * The "match_flags" element in a usb_device_id controls which @@ -823,7 +829,8 @@ static int usb_uevent(struct device *dev, struct kobj_uevent_env *env) * Registers a USB device driver with the USB core. The list of * unattached devices will be rescanned whenever a new driver is * added, allowing the new driver to attach to any recognized devices. - * Returns a negative error code on failure and 0 on success. + * + * Return: A negative error code on failure and 0 on success. */ int usb_register_device_driver(struct usb_device_driver *new_udriver, struct module *owner) @@ -879,7 +886,8 @@ EXPORT_SYMBOL_GPL(usb_deregister_device_driver); * Registers a USB interface driver with the USB core. The list of * unattached interfaces will be rescanned whenever a new driver is * added, allowing the new driver to attach to any recognized interfaces. - * Returns a negative error code on failure and 0 on success. + * + * Return: A negative error code on failure and 0 on success. * * NOTE: if you want your driver to use the USB major number, you must call * usb_register_dev() to enable that functionality. This function no longer @@ -1213,6 +1221,8 @@ done: * unpredictable times. * * This routine can run only in process context. + * + * Return: 0 if the suspend succeeded. */ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg) { @@ -1294,6 +1304,8 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg) * unpredictable times. * * This routine can run only in process context. + * + * Return: 0 on success. */ static int usb_resume_both(struct usb_device *udev, pm_message_t msg) { @@ -1491,6 +1503,8 @@ void usb_autosuspend_device(struct usb_device *udev) * The caller must hold @udev's device lock. * * This routine can run only in process context. + * + * Return: 0 on success. A negative error code otherwise. */ int usb_autoresume_device(struct usb_device *udev) { @@ -1600,6 +1614,8 @@ EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend); * However if the autoresume fails then the counter is re-decremented. * * This routine can run only in process context. + * + * Return: 0 on success. */ int usb_autopm_get_interface(struct usb_interface *intf) { @@ -1633,6 +1649,8 @@ EXPORT_SYMBOL_GPL(usb_autopm_get_interface); * resumed. * * This routine can run in atomic context. + * + * Return: 0 on success. A negative error code otherwise. */ int usb_autopm_get_interface_async(struct usb_interface *intf) { diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c index 6a4c40766f0f..7421888087a3 100644 --- a/drivers/usb/core/file.c +++ b/drivers/usb/core/file.c @@ -153,7 +153,7 @@ void usb_major_cleanup(void) * usb_deregister_dev() must be called when the driver is done with * the minor numbers given out by this function. * - * Returns -EINVAL if something bad happens with trying to register a + * Return: -EINVAL if something bad happens with trying to register a * device, and 0 on success. */ int usb_register_dev(struct usb_interface *intf, diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index caeb8d6d39fb..b9d3c43e3859 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -171,6 +171,8 @@ static void ehci_wait_for_companions(struct pci_dev *pdev, struct usb_hcd *hcd, * through the hotplug entry's driver_data. * * Store this function in the HCD's struct pci_driver as probe(). + * + * Return: 0 if successful. */ int usb_hcd_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) { diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 014dc996b4f6..dc1346fee76c 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -378,9 +378,10 @@ MODULE_PARM_DESC(authorized_default, * @buf: Buffer for USB string descriptor (header + UTF-16LE) * @len: Length (in bytes; may be odd) of descriptor buffer. * - * The return value is the number of bytes filled in: 2 + 2*strlen(s) or - * buflen, whichever is less. + * Return: The number of bytes filled in: 2 + 2*strlen(s) or @len, + * whichever is less. * + * Note: * USB String descriptors can contain at most 126 characters; input * strings longer than that are truncated. */ @@ -416,7 +417,8 @@ ascii2desc(char const *s, u8 *buf, unsigned len) * * Produces either a manufacturer, product or serial number string for the * virtual root hub device. - * Returns the number of bytes filled in: the length of the descriptor or + * + * Return: The number of bytes filled in: the length of the descriptor or * of the provided buffer, whichever is less. */ static unsigned @@ -938,6 +940,8 @@ static void usb_bus_init (struct usb_bus *bus) * * Assigns a bus number, and links the controller into usbcore data * structures so that it can be seen by scanning the bus list. + * + * Return: 0 if successful. A negative error code otherwise. */ static int usb_register_bus(struct usb_bus *bus) { @@ -1002,6 +1006,8 @@ static void usb_deregister_bus (struct usb_bus *bus) * the device properly in the device tree and then calls usb_new_device() * to register the usb device. It also assigns the root hub's USB address * (always 1). + * + * Return: 0 if successful. A negative error code otherwise. */ static int register_root_hub(struct usb_hcd *hcd) { @@ -1108,7 +1114,9 @@ EXPORT_SYMBOL_GPL(usb_hcd_end_port_resume); * @isoc: true for isochronous transactions, false for interrupt ones * @bytecount: how many bytes in the transaction. * - * Returns approximate bus time in nanoseconds for a periodic transaction. + * Return: Approximate bus time in nanoseconds for a periodic transaction. + * + * Note: * See USB 2.0 spec section 5.11.3; only periodic transfers need to be * scheduled in software, this function is only used for such scheduling. */ @@ -1166,7 +1174,7 @@ EXPORT_SYMBOL_GPL(usb_calc_bus_time); * be disabled. The actions carried out here are required for URB * submission, as well as for endpoint shutdown and for usb_kill_urb. * - * Returns 0 for no error, otherwise a negative error code (in which case + * Return: 0 for no error, otherwise a negative error code (in which case * the enqueue() method must fail). If no error occurs but enqueue() fails * anyway, it must call usb_hcd_unlink_urb_from_ep() before releasing * the private spinlock and returning. @@ -1221,7 +1229,7 @@ EXPORT_SYMBOL_GPL(usb_hcd_link_urb_to_ep); * be disabled. The actions carried out here are required for making * sure than an unlink is valid. * - * Returns 0 for no error, otherwise a negative error code (in which case + * Return: 0 for no error, otherwise a negative error code (in which case * the dequeue() method must fail). The possible error codes are: * * -EIDRM: @urb was not submitted or has already completed. @@ -1784,7 +1792,7 @@ rescan: * pass in the current alternate interface setting in cur_alt, * and pass in the new alternate interface setting in new_alt. * - * Returns an error if the requested bandwidth change exceeds the + * Return: An error if the requested bandwidth change exceeds the * bus bandwidth or host controller internal resources. */ int usb_hcd_alloc_bandwidth(struct usb_device *udev, @@ -1954,9 +1962,12 @@ void usb_hcd_reset_endpoint(struct usb_device *udev, * @num_streams: number of streams to allocate. * @mem_flags: flags hcd should use to allocate memory. * - * Sets up a group of bulk endpoints to have num_streams stream IDs available. + * Sets up a group of bulk endpoints to have @num_streams stream IDs available. * Drivers may queue multiple transfers to different stream IDs, which may * complete in a different order than they were queued. + * + * Return: On success, the number of allocated streams. On failure, a negative + * error code. */ int usb_alloc_streams(struct usb_interface *interface, struct usb_host_endpoint **eps, unsigned int num_eps, @@ -2201,6 +2212,8 @@ EXPORT_SYMBOL_GPL(usb_hcd_resume_root_hub); * khubd identifying and possibly configuring the device. * This is needed by OTG controller drivers, where it helps meet * HNP protocol timing requirements for starting a port reset. + * + * Return: 0 if successful. */ int usb_bus_start_enum(struct usb_bus *bus, unsigned port_num) { @@ -2235,6 +2248,8 @@ EXPORT_SYMBOL_GPL(usb_bus_start_enum); * * If the controller isn't HALTed, calls the driver's irq handler. * Checks whether the controller is now dead. + * + * Return: %IRQ_HANDLED if the IRQ was handled. %IRQ_NONE otherwise. */ irqreturn_t usb_hcd_irq (int irq, void *__hcd) { @@ -2320,7 +2335,8 @@ EXPORT_SYMBOL_GPL (usb_hc_died); * HC driver's private data. Initialize the generic members of the * hcd structure. * - * If memory is unavailable, returns NULL. + * Return: On success, a pointer to the created and initialized HCD structure. + * On failure (e.g. if memory is unavailable), %NULL. */ struct usb_hcd *usb_create_shared_hcd(const struct hc_driver *driver, struct device *dev, const char *bus_name, @@ -2384,7 +2400,8 @@ EXPORT_SYMBOL_GPL(usb_create_shared_hcd); * HC driver's private data. Initialize the generic members of the * hcd structure. * - * If memory is unavailable, returns NULL. + * Return: On success, a pointer to the created and initialized HCD + * structure. On failure (e.g. if memory is unavailable), %NULL. */ struct usb_hcd *usb_create_hcd(const struct hc_driver *driver, struct device *dev, const char *bus_name) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 0416f835cfee..5d6d28a76e0a 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -734,6 +734,8 @@ static void hub_tt_work(struct work_struct *work) * * call this function to control port's power via setting or * clearing the port's PORT_POWER feature. + * + * Return: 0 if successful. A negative error code otherwise. */ int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, int port1, bool set) @@ -762,6 +764,8 @@ int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, * * It may not be possible for that hub to handle additional full (or low) * speed transactions until that state is fully cleared out. + * + * Return: 0 if successful. A negative error code otherwise. */ int usb_hub_clear_tt_buffer(struct urb *urb) { @@ -964,6 +968,8 @@ static void hub_port_logical_disconnect(struct usb_hub *hub, int port1) * see that the device has been disconnected. When the device is * physically unplugged and something is plugged in, the events will * be received and processed normally. + * + * Return: 0 if successful. A negative error code otherwise. */ int usb_remove_device(struct usb_device *udev) { @@ -2115,6 +2121,8 @@ static inline void announce_device(struct usb_device *udev) { } * @udev: newly addressed device (in ADDRESS state) * * Finish enumeration for On-The-Go devices + * + * Return: 0 if successful. A negative error code otherwise. */ static int usb_enumerate_device_otg(struct usb_device *udev) { @@ -2197,6 +2205,8 @@ fail: * If the device is WUSB and not authorized, we don't attempt to read * the string descriptors, as they will be errored out by the device * until it has been authorized. + * + * Return: 0 if successful. A negative error code otherwise. */ static int usb_enumerate_device(struct usb_device *udev) { @@ -2277,13 +2287,14 @@ static void set_usb_port_removable(struct usb_device *udev) * udev has already been installed, but udev is not yet visible through * sysfs or other filesystem code. * - * It will return if the device is configured properly or not. Zero if - * the interface was registered with the driver core; else a negative - * errno value. - * * This call is synchronous, and may not be used in an interrupt context. * * Only the hub driver or root-hub registrar should ever call this. + * + * Return: Whether the device is configured properly or not. Zero if the + * interface was registered with the driver core; else a negative errno + * value. + * */ int usb_new_device(struct usb_device *udev) { @@ -2391,6 +2402,8 @@ fail: * * We share a lock (that we have) with device_del(), so we need to * defer its call. + * + * Return: 0. */ int usb_deauthorize_device(struct usb_device *usb_dev) { @@ -5025,10 +5038,11 @@ static int descriptors_changed(struct usb_device *udev, * re-connected. All drivers will be unbound, and the device will be * re-enumerated and probed all over again. * - * Returns 0 if the reset succeeded, -ENODEV if the device has been + * Return: 0 if the reset succeeded, -ENODEV if the device has been * flagged for logical disconnection, or some other negative error code * if the reset wasn't even attempted. * + * Note: * The caller must own the device lock. For example, it's safe to use * this from a driver probe() routine after downloading new firmware. * For calls that might not occur during probe(), drivers should lock @@ -5184,8 +5198,9 @@ re_enumerate: * method), performs the port reset, and then lets the drivers know that * the reset is over (using their post_reset method). * - * Return value is the same as for usb_reset_and_verify_device(). + * Return: The same as for usb_reset_and_verify_device(). * + * Note: * The caller must own the device lock. For example, it's safe to use * this from a driver probe() routine after downloading new firmware. * For calls that might not occur during probe(), drivers should lock @@ -5323,7 +5338,7 @@ EXPORT_SYMBOL_GPL(usb_queue_reset_device); * USB drivers call this function to get hub's child device * pointer. * - * Return NULL if input param is invalid and + * Return: %NULL if input param is invalid and * child's usb_device pointer if non-NULL. */ struct usb_device *usb_hub_find_child(struct usb_device *hdev, @@ -5357,8 +5372,8 @@ void usb_set_hub_port_connect_type(struct usb_device *hdev, int port1, * @hdev: USB device belonging to the usb hub * @port1: port num of the port * - * Return connect type of the port and if input params are - * invalid, return USB_PORT_CONNECT_TYPE_UNKNOWN. + * Return: The connect type of the port if successful. Or + * USB_PORT_CONNECT_TYPE_UNKNOWN if input params are invalid. */ enum usb_port_connect_type usb_get_hub_port_connect_type(struct usb_device *hdev, int port1) @@ -5418,8 +5433,8 @@ void usb_hub_adjust_deviceremovable(struct usb_device *hdev, * @hdev: USB device belonging to the usb hub * @port1: port num of the port * - * Return port's acpi handle if successful, NULL if params are - * invaild. + * Return: Port's acpi handle if successful, %NULL if params are + * invalid. */ acpi_handle usb_get_hub_port_acpi_handle(struct usb_device *hdev, int port1) diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 6549a975b0c5..82927e1ed27d 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -119,15 +119,15 @@ static int usb_internal_control_msg(struct usb_device *usb_dev, * This function sends a simple control message to a specified endpoint and * waits for the message to complete, or timeout. * - * If successful, it returns the number of bytes transferred, otherwise a - * negative error number. - * * Don't use this function from within an interrupt context, like a bottom half * handler. If you need an asynchronous message, or need to send a message * from within interrupt context, use usb_submit_urb(). * If a thread in your driver uses this call, make sure your disconnect() * method can wait for it to complete. Since you don't have a handle on the * URB used, you can't cancel the request. + * + * Return: If successful, the number of bytes transferred. Otherwise, a negative + * error number. */ int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, @@ -170,15 +170,16 @@ EXPORT_SYMBOL_GPL(usb_control_msg); * This function sends a simple interrupt message to a specified endpoint and * waits for the message to complete, or timeout. * - * If successful, it returns 0, otherwise a negative error number. The number - * of actual bytes transferred will be stored in the actual_length paramater. - * * Don't use this function from within an interrupt context, like a bottom half * handler. If you need an asynchronous message, or need to send a message * from within interrupt context, use usb_submit_urb() If a thread in your * driver uses this call, make sure your disconnect() method can wait for it to * complete. Since you don't have a handle on the URB used, you can't cancel * the request. + * + * Return: + * If successful, 0. Otherwise a negative error number. The number of actual + * bytes transferred will be stored in the @actual_length paramater. */ int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout) @@ -203,9 +204,6 @@ EXPORT_SYMBOL_GPL(usb_interrupt_msg); * This function sends a simple bulk message to a specified endpoint * and waits for the message to complete, or timeout. * - * If successful, it returns 0, otherwise a negative error number. The number - * of actual bytes transferred will be stored in the actual_length paramater. - * * Don't use this function from within an interrupt context, like a bottom half * handler. If you need an asynchronous message, or need to send a message * from within interrupt context, use usb_submit_urb() If a thread in your @@ -217,6 +215,11 @@ EXPORT_SYMBOL_GPL(usb_interrupt_msg); * users are forced to abuse this routine by using it to submit URBs for * interrupt endpoints. We will take the liberty of creating an interrupt URB * (with the default interval) if the target is an interrupt endpoint. + * + * Return: + * If successful, 0. Otherwise a negative error number. The number of actual + * bytes transferred will be stored in the @actual_length paramater. + * */ int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout) @@ -341,9 +344,9 @@ static void sg_complete(struct urb *urb) * send every byte identified in the list. * @mem_flags: SLAB_* flags affecting memory allocations in this call * - * Returns zero for success, else a negative errno value. This initializes a - * scatter/gather request, allocating resources such as I/O mappings and urb - * memory (except maybe memory used by USB controller drivers). + * This initializes a scatter/gather request, allocating resources such as + * I/O mappings and urb memory (except maybe memory used by USB controller + * drivers). * * The request must be issued using usb_sg_wait(), which waits for the I/O to * complete (or to be canceled) and then cleans up all resources allocated by @@ -351,6 +354,8 @@ static void sg_complete(struct urb *urb) * * The request may be canceled with usb_sg_cancel(), either before or after * usb_sg_wait() is called. + * + * Return: Zero for success, else a negative errno value. */ int usb_sg_init(struct usb_sg_request *io, struct usb_device *dev, unsigned pipe, unsigned period, struct scatterlist *sg, @@ -623,7 +628,7 @@ EXPORT_SYMBOL_GPL(usb_sg_cancel); * * This call is synchronous, and may not be used in an interrupt context. * - * Returns the number of bytes received on success, or else the status code + * Return: The number of bytes received on success, or else the status code * returned by the underlying usb_control_msg() call. */ int usb_get_descriptor(struct usb_device *dev, unsigned char type, @@ -671,7 +676,7 @@ EXPORT_SYMBOL_GPL(usb_get_descriptor); * * This call is synchronous, and may not be used in an interrupt context. * - * Returns the number of bytes received on success, or else the status code + * Return: The number of bytes received on success, or else the status code * returned by the underlying usb_control_msg() call. */ static int usb_get_string(struct usb_device *dev, unsigned short langid, @@ -805,7 +810,7 @@ static int usb_get_langid(struct usb_device *dev, unsigned char *tbuf) * * This call is synchronous, and may not be used in an interrupt context. * - * Returns length of the string (>= 0) or usb_control_msg status (< 0). + * Return: length of the string (>= 0) or usb_control_msg status (< 0). */ int usb_string(struct usb_device *dev, int index, char *buf, size_t size) { @@ -853,8 +858,8 @@ EXPORT_SYMBOL_GPL(usb_string); * @udev: the device whose string descriptor is being read * @index: the descriptor index * - * Returns a pointer to a kmalloc'ed buffer containing the descriptor string, - * or NULL if the index is 0 or the string could not be read. + * Return: A pointer to a kmalloc'ed buffer containing the descriptor string, + * or %NULL if the index is 0 or the string could not be read. */ char *usb_cache_string(struct usb_device *udev, int index) { @@ -894,7 +899,7 @@ char *usb_cache_string(struct usb_device *udev, int index) * * This call is synchronous, and may not be used in an interrupt context. * - * Returns the number of bytes received on success, or else the status code + * Return: The number of bytes received on success, or else the status code * returned by the underlying usb_control_msg() call. */ int usb_get_device_descriptor(struct usb_device *dev, unsigned int size) @@ -980,7 +985,7 @@ EXPORT_SYMBOL_GPL(usb_get_status); * * This call is synchronous, and may not be used in an interrupt context. * - * Returns zero on success, or else the status code returned by the + * Return: Zero on success, or else the status code returned by the * underlying usb_control_msg() call. */ int usb_clear_halt(struct usb_device *dev, int pipe) @@ -1277,7 +1282,7 @@ void usb_enable_interface(struct usb_device *dev, * endpoints in that interface; all such urbs must first be completed * (perhaps forced by unlinking). * - * Returns zero on success, or else the status code returned by the + * Return: Zero on success, or else the status code returned by the * underlying usb_control_msg() call. */ int usb_set_interface(struct usb_device *dev, int interface, int alternate) @@ -1431,7 +1436,7 @@ EXPORT_SYMBOL_GPL(usb_set_interface); * * The caller must own the device lock. * - * Returns zero on success, else a negative error code. + * Return: Zero on success, else a negative error code. */ int usb_reset_configuration(struct usb_device *dev) { @@ -1973,7 +1978,7 @@ static void cancel_async_set_config(struct usb_device *udev) * routine gets around the normal restrictions by using a work thread to * submit the change-config request. * - * Returns 0 if the request was successfully queued, error code otherwise. + * Return: 0 if the request was successfully queued, error code otherwise. * The caller has no way to know whether the queued request will eventually * succeed. */ diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index e75115a04a2e..4e7a311ff6d7 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -55,12 +55,12 @@ EXPORT_SYMBOL_GPL(usb_init_urb); * Creates an urb for the USB driver to use, initializes a few internal * structures, incrementes the usage counter, and returns a pointer to it. * - * If no memory is available, NULL is returned. - * * If the driver want to use this urb for interrupt, control, or bulk * endpoints, pass '0' as the number of iso packets. * * The driver must call usb_free_urb() when it is finished with the urb. + * + * Return: A pointer to the new urb, or %NULL if no memory is available. */ struct urb *usb_alloc_urb(int iso_packets, gfp_t mem_flags) { @@ -103,7 +103,7 @@ EXPORT_SYMBOL_GPL(usb_free_urb); * host controller driver. This allows proper reference counting to happen * for urbs. * - * A pointer to the urb with the incremented reference counter is returned. + * Return: A pointer to the urb with the incremented reference counter. */ struct urb *usb_get_urb(struct urb *urb) { @@ -200,13 +200,12 @@ EXPORT_SYMBOL_GPL(usb_unanchor_urb); * the particular kind of transfer, although they will not initialize * any transfer flags. * - * Successful submissions return 0; otherwise this routine returns a - * negative error number. If the submission is successful, the complete() - * callback from the URB will be called exactly once, when the USB core and - * Host Controller Driver (HCD) are finished with the URB. When the completion - * function is called, control of the URB is returned to the device - * driver which issued the request. The completion handler may then - * immediately free or reuse that URB. + * If the submission is successful, the complete() callback from the URB + * will be called exactly once, when the USB core and Host Controller Driver + * (HCD) are finished with the URB. When the completion function is called, + * control of the URB is returned to the device driver which issued the + * request. The completion handler may then immediately free or reuse that + * URB. * * With few exceptions, USB device drivers should never access URB fields * provided by usbcore or the HCD until its complete() is called. @@ -241,6 +240,9 @@ EXPORT_SYMBOL_GPL(usb_unanchor_urb); * that are standardized in the USB 2.0 specification. For bulk * endpoints, a synchronous usb_bulk_msg() call is available. * + * Return: + * 0 on successful submissions. A negative error number otherwise. + * * Request Queuing: * * URBs may be submitted to endpoints before previous ones complete, to @@ -572,6 +574,9 @@ EXPORT_SYMBOL_GPL(usb_submit_urb); * particular, when a driver calls this routine, it must insure that the * completion handler cannot deallocate the URB. * + * Return: -EINPROGRESS on success. See description for other values on + * failure. + * * Unlinking and Endpoint Queues: * * [The behaviors and guarantees described below do not apply to virtual @@ -846,6 +851,8 @@ EXPORT_SYMBOL_GPL(usb_unlink_anchored_urbs); * * Call this is you want to be sure all an anchor's * URBs have finished + * + * Return: Non-zero if the anchor became unused. Zero on timeout. */ int usb_wait_anchor_empty_timeout(struct usb_anchor *anchor, unsigned int timeout) @@ -859,8 +866,11 @@ EXPORT_SYMBOL_GPL(usb_wait_anchor_empty_timeout); * usb_get_from_anchor - get an anchor's oldest urb * @anchor: the anchor whose urb you want * - * this will take the oldest urb from an anchor, + * This will take the oldest urb from an anchor, * unanchor and return it + * + * Return: The oldest urb from @anchor, or %NULL if @anchor has no + * urbs associated with it. */ struct urb *usb_get_from_anchor(struct usb_anchor *anchor) { @@ -909,7 +919,7 @@ EXPORT_SYMBOL_GPL(usb_scuttle_anchored_urbs); * usb_anchor_empty - is an anchor empty * @anchor: the anchor you want to query * - * returns 1 if the anchor has no urbs associated with it + * Return: 1 if the anchor has no urbs associated with it. */ int usb_anchor_empty(struct usb_anchor *anchor) { diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 7dad603dde43..0a6ee2e70b25 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -68,6 +68,8 @@ MODULE_PARM_DESC(autosuspend, "default autosuspend delay"); * @alt_num: alternate interface setting number to search for. * * Search the configuration's interface cache for the given alt setting. + * + * Return: The alternate setting, if found. %NULL otherwise. */ struct usb_host_interface *usb_find_alt_setting( struct usb_host_config *config, @@ -103,8 +105,7 @@ EXPORT_SYMBOL_GPL(usb_find_alt_setting); * @ifnum: the desired interface * * This walks the device descriptor for the currently active configuration - * and returns a pointer to the interface with that particular interface - * number, or null. + * to find the interface object with the particular interface number. * * Note that configuration descriptors are not required to assign interface * numbers sequentially, so that it would be incorrect to assume that @@ -115,6 +116,9 @@ EXPORT_SYMBOL_GPL(usb_find_alt_setting); * * Don't call this function unless you are bound to one of the interfaces * on this device or you have locked the device! + * + * Return: A pointer to the interface that has @ifnum as interface number, + * if found. %NULL otherwise. */ struct usb_interface *usb_ifnum_to_if(const struct usb_device *dev, unsigned ifnum) @@ -139,8 +143,7 @@ EXPORT_SYMBOL_GPL(usb_ifnum_to_if); * @altnum: the desired alternate setting number * * This searches the altsetting array of the specified interface for - * an entry with the correct bAlternateSetting value and returns a pointer - * to that entry, or null. + * an entry with the correct bAlternateSetting value. * * Note that altsettings need not be stored sequentially by number, so * it would be incorrect to assume that the first altsetting entry in @@ -149,6 +152,9 @@ EXPORT_SYMBOL_GPL(usb_ifnum_to_if); * * Don't call this function unless you are bound to the intf interface * or you have locked the device! + * + * Return: A pointer to the entry of the altsetting array of @intf that + * has @altnum as the alternate setting number. %NULL if not found. */ struct usb_host_interface *usb_altnum_to_altsetting( const struct usb_interface *intf, @@ -191,6 +197,8 @@ static int __find_interface(struct device *dev, void *data) * This walks the bus device list and returns a pointer to the interface * with the matching minor and driver. Note, this only works for devices * that share the USB major number. + * + * Return: A pointer to the interface with the matching major and @minor. */ struct usb_interface *usb_find_interface(struct usb_driver *drv, int minor) { @@ -390,6 +398,9 @@ static unsigned usb_bus_is_wusb(struct usb_bus *bus) * controllers) should ever call this. * * This call may not be used in a non-sleeping context. + * + * Return: On success, a pointer to the allocated usb device. %NULL on + * failure. */ struct usb_device *usb_alloc_dev(struct usb_device *parent, struct usb_bus *bus, unsigned port1) @@ -501,7 +512,7 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent, * their probe() methods, when they bind to an interface, and release * them by calling usb_put_dev(), in their disconnect() methods. * - * A pointer to the device with the incremented reference counter is returned. + * Return: A pointer to the device with the incremented reference counter. */ struct usb_device *usb_get_dev(struct usb_device *dev) { @@ -535,8 +546,7 @@ EXPORT_SYMBOL_GPL(usb_put_dev); * their probe() methods, when they bind to an interface, and release * them by calling usb_put_intf(), in their disconnect() methods. * - * A pointer to the interface with the incremented reference counter is - * returned. + * Return: A pointer to the interface with the incremented reference counter. */ struct usb_interface *usb_get_intf(struct usb_interface *intf) { @@ -589,7 +599,7 @@ EXPORT_SYMBOL_GPL(usb_put_intf); * disconnect; in some drivers (such as usb-storage) the disconnect() * or suspend() method will block waiting for a device reset to complete. * - * Returns a negative error code for failure, otherwise 0. + * Return: A negative error code for failure, otherwise 0. */ int usb_lock_device_for_reset(struct usb_device *udev, const struct usb_interface *iface) @@ -628,14 +638,15 @@ EXPORT_SYMBOL_GPL(usb_lock_device_for_reset); * usb_get_current_frame_number - return current bus frame number * @dev: the device whose bus is being queried * - * Returns the current frame number for the USB host controller - * used with the given USB device. This can be used when scheduling + * Return: The current frame number for the USB host controller used + * with the given USB device. This can be used when scheduling * isochronous requests. * - * Note that different kinds of host controller have different - * "scheduling horizons". While one type might support scheduling only - * 32 frames into the future, others could support scheduling up to - * 1024 frames into the future. + * Note: Different kinds of host controller have different "scheduling + * horizons". While one type might support scheduling only 32 frames + * into the future, others could support scheduling up to 1024 frames + * into the future. + * */ int usb_get_current_frame_number(struct usb_device *dev) { @@ -685,11 +696,12 @@ EXPORT_SYMBOL_GPL(__usb_get_extra_descriptor); * @mem_flags: affect whether allocation may block * @dma: used to return DMA address of buffer * - * Return value is either null (indicating no buffer could be allocated), or - * the cpu-space pointer to a buffer that may be used to perform DMA to the + * Return: Either null (indicating no buffer could be allocated), or the + * cpu-space pointer to a buffer that may be used to perform DMA to the * specified device. Such cpu-space buffers are returned along with the DMA * address (through the pointer provided). * + * Note: * These buffers are used with URB_NO_xxx_DMA_MAP set in urb->transfer_flags * to avoid behaviors like using "DMA bounce buffers", or thrashing IOMMU * hardware during URB completion/resubmit. The implementation varies between @@ -735,17 +747,18 @@ EXPORT_SYMBOL_GPL(usb_free_coherent); * usb_buffer_map - create DMA mapping(s) for an urb * @urb: urb whose transfer_buffer/setup_packet will be mapped * - * Return value is either null (indicating no buffer could be mapped), or - * the parameter. URB_NO_TRANSFER_DMA_MAP is - * added to urb->transfer_flags if the operation succeeds. If the device - * is connected to this system through a non-DMA controller, this operation - * always succeeds. + * URB_NO_TRANSFER_DMA_MAP is added to urb->transfer_flags if the operation + * succeeds. If the device is connected to this system through a non-DMA + * controller, this operation always succeeds. * * This call would normally be used for an urb which is reused, perhaps * as the target of a large periodic transfer, with usb_buffer_dmasync() * calls to synchronize memory and dma state. * * Reverse the effect of this call with usb_buffer_unmap(). + * + * Return: Either %NULL (indicating no buffer could be mapped), or @urb. + * */ #if 0 struct urb *usb_buffer_map(struct urb *urb) @@ -850,9 +863,10 @@ EXPORT_SYMBOL_GPL(usb_buffer_unmap); * @sg: the scatterlist to map * @nents: the number of entries in the scatterlist * - * Return value is either < 0 (indicating no buffers could be mapped), or - * the number of DMA mapping array entries in the scatterlist. + * Return: Either < 0 (indicating no buffers could be mapped), or the + * number of DMA mapping array entries in the scatterlist. * + * Note: * The caller is responsible for placing the resulting DMA addresses from * the scatterlist into URB transfer buffer pointers, and for setting the * URB_NO_TRANSFER_DMA_MAP transfer flag in each of those URBs. diff --git a/include/linux/usb.h b/include/linux/usb.h index 6efdab089014..acb1b0aa77d8 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -708,7 +708,10 @@ extern int usb_driver_claim_interface(struct usb_driver *driver, * usb_interface_claimed - returns true iff an interface is claimed * @iface: the interface being checked * - * Returns true (nonzero) iff the interface is claimed, else false (zero). + * Return: %true (nonzero) iff the interface is claimed, else %false + * (zero). + * + * Note: * Callers must own the driver model's usb bus readlock. So driver * probe() entries don't need extra locking, but other call contexts * may need to explicitly claim that lock. @@ -745,8 +748,9 @@ extern struct usb_host_interface *usb_find_alt_setting( * @buf: where to put the string * @size: how big is "buf"? * - * Returns length of the string (> 0) or negative if size was too small. + * Return: Length of the string (> 0) or negative if size was too small. * + * Note: * This identifier is intended to be "stable", reflecting physical paths in * hardware such as physical bus addresses for host controllers or ports on * USB hubs. That makes it stay the same until systems are physically @@ -1578,7 +1582,7 @@ extern int usb_anchor_empty(struct usb_anchor *anchor); * usb_urb_dir_in - check if an URB describes an IN transfer * @urb: URB to be checked * - * Returns 1 if @urb describes an IN transfer (device-to-host), + * Return: 1 if @urb describes an IN transfer (device-to-host), * otherwise 0. */ static inline int usb_urb_dir_in(struct urb *urb) @@ -1590,7 +1594,7 @@ static inline int usb_urb_dir_in(struct urb *urb) * usb_urb_dir_out - check if an URB describes an OUT transfer * @urb: URB to be checked * - * Returns 1 if @urb describes an OUT transfer (host-to-device), + * Return: 1 if @urb describes an OUT transfer (host-to-device), * otherwise 0. */ static inline int usb_urb_dir_out(struct urb *urb) -- cgit v1.2.3-71-gd317 From 23cde4d65cc7d11e2048d2b240cdf13927ac50d0 Mon Sep 17 00:00:00 2001 From: Denis CIOCCA Date: Wed, 19 Jun 2013 09:28:00 +0100 Subject: iio: Added ST-sensors platform data to select the DRDY interrupt pin This patch add support to redirect the DRDY interrupt on INT1 or INT2 on accelerometer and pressure sensors. Signed-off-by: Denis Ciocca Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel.h | 11 ++++++- drivers/iio/accel/st_accel_core.c | 27 +++++++++++----- drivers/iio/accel/st_accel_i2c.c | 2 +- drivers/iio/accel/st_accel_spi.c | 2 +- drivers/iio/common/st_sensors/st_sensors_core.c | 41 ++++++++++++++++++++++--- drivers/iio/gyro/st_gyro.h | 11 ++++++- drivers/iio/gyro/st_gyro_core.c | 13 ++++---- drivers/iio/gyro/st_gyro_i2c.c | 3 +- drivers/iio/gyro/st_gyro_spi.c | 3 +- drivers/iio/magnetometer/st_magn.h | 3 +- drivers/iio/magnetometer/st_magn_core.c | 5 +-- drivers/iio/magnetometer/st_magn_i2c.c | 2 +- drivers/iio/magnetometer/st_magn_spi.c | 2 +- drivers/iio/pressure/st_pressure.h | 11 ++++++- drivers/iio/pressure/st_pressure_core.c | 15 ++++++--- drivers/iio/pressure/st_pressure_i2c.c | 2 +- drivers/iio/pressure/st_pressure_spi.c | 2 +- include/linux/iio/common/st_sensors.h | 14 +++++++-- include/linux/platform_data/st_sensors_pdata.h | 24 +++++++++++++++ 19 files changed, 153 insertions(+), 40 deletions(-) create mode 100644 include/linux/platform_data/st_sensors_pdata.h (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel.h b/drivers/iio/accel/st_accel.h index 37949b94377d..c3877630b2e4 100644 --- a/drivers/iio/accel/st_accel.h +++ b/drivers/iio/accel/st_accel.h @@ -25,7 +25,16 @@ #define LSM303DLM_ACCEL_DEV_NAME "lsm303dlm_accel" #define LSM330_ACCEL_DEV_NAME "lsm330_accel" -int st_accel_common_probe(struct iio_dev *indio_dev); +/** +* struct st_sensors_platform_data - default accel platform data +* @drdy_int_pin: default accel DRDY is available on INT1 pin. +*/ +static const struct st_sensors_platform_data default_accel_pdata = { + .drdy_int_pin = 1, +}; + +int st_accel_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata); void st_accel_common_remove(struct iio_dev *indio_dev); #ifdef CONFIG_IIO_BUFFER diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 4aec121261d7..aef3c9be7366 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -65,7 +65,8 @@ #define ST_ACCEL_1_BDU_ADDR 0x23 #define ST_ACCEL_1_BDU_MASK 0x80 #define ST_ACCEL_1_DRDY_IRQ_ADDR 0x22 -#define ST_ACCEL_1_DRDY_IRQ_MASK 0x10 +#define ST_ACCEL_1_DRDY_IRQ_INT1_MASK 0x10 +#define ST_ACCEL_1_DRDY_IRQ_INT2_MASK 0x08 #define ST_ACCEL_1_MULTIREAD_BIT true /* CUSTOM VALUES FOR SENSOR 2 */ @@ -89,7 +90,8 @@ #define ST_ACCEL_2_BDU_ADDR 0x23 #define ST_ACCEL_2_BDU_MASK 0x80 #define ST_ACCEL_2_DRDY_IRQ_ADDR 0x22 -#define ST_ACCEL_2_DRDY_IRQ_MASK 0x02 +#define ST_ACCEL_2_DRDY_IRQ_INT1_MASK 0x02 +#define ST_ACCEL_2_DRDY_IRQ_INT2_MASK 0x10 #define ST_ACCEL_2_MULTIREAD_BIT true /* CUSTOM VALUES FOR SENSOR 3 */ @@ -121,7 +123,8 @@ #define ST_ACCEL_3_BDU_ADDR 0x20 #define ST_ACCEL_3_BDU_MASK 0x08 #define ST_ACCEL_3_DRDY_IRQ_ADDR 0x23 -#define ST_ACCEL_3_DRDY_IRQ_MASK 0x80 +#define ST_ACCEL_3_DRDY_IRQ_INT1_MASK 0x80 +#define ST_ACCEL_3_DRDY_IRQ_INT2_MASK 0x00 #define ST_ACCEL_3_IG1_EN_ADDR 0x23 #define ST_ACCEL_3_IG1_EN_MASK 0x08 #define ST_ACCEL_3_MULTIREAD_BIT false @@ -224,7 +227,8 @@ static const struct st_sensors st_accel_sensors[] = { }, .drdy_irq = { .addr = ST_ACCEL_1_DRDY_IRQ_ADDR, - .mask = ST_ACCEL_1_DRDY_IRQ_MASK, + .mask_int1 = ST_ACCEL_1_DRDY_IRQ_INT1_MASK, + .mask_int2 = ST_ACCEL_1_DRDY_IRQ_INT2_MASK, }, .multi_read_bit = ST_ACCEL_1_MULTIREAD_BIT, .bootime = 2, @@ -285,7 +289,8 @@ static const struct st_sensors st_accel_sensors[] = { }, .drdy_irq = { .addr = ST_ACCEL_2_DRDY_IRQ_ADDR, - .mask = ST_ACCEL_2_DRDY_IRQ_MASK, + .mask_int1 = ST_ACCEL_2_DRDY_IRQ_INT1_MASK, + .mask_int2 = ST_ACCEL_2_DRDY_IRQ_INT2_MASK, }, .multi_read_bit = ST_ACCEL_2_MULTIREAD_BIT, .bootime = 2, @@ -358,7 +363,8 @@ static const struct st_sensors st_accel_sensors[] = { }, .drdy_irq = { .addr = ST_ACCEL_3_DRDY_IRQ_ADDR, - .mask = ST_ACCEL_3_DRDY_IRQ_MASK, + .mask_int1 = ST_ACCEL_3_DRDY_IRQ_INT1_MASK, + .mask_int2 = ST_ACCEL_3_DRDY_IRQ_INT2_MASK, .ig1 = { .en_addr = ST_ACCEL_3_IG1_EN_ADDR, .en_mask = ST_ACCEL_3_IG1_EN_MASK, @@ -443,7 +449,8 @@ static const struct iio_trigger_ops st_accel_trigger_ops = { #define ST_ACCEL_TRIGGER_OPS NULL #endif -int st_accel_common_probe(struct iio_dev *indio_dev) +int st_accel_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *plat_data) { int err; struct st_sensor_data *adata = iio_priv(indio_dev); @@ -465,7 +472,11 @@ int st_accel_common_probe(struct iio_dev *indio_dev) &adata->sensor->fs.fs_avl[0]; adata->odr = adata->sensor->odr.odr_avl[0].hz; - err = st_sensors_init_sensor(indio_dev); + if (!plat_data) + plat_data = + (struct st_sensors_platform_data *)&default_accel_pdata; + + err = st_sensors_init_sensor(indio_dev, plat_data); if (err < 0) goto st_accel_common_probe_error; diff --git a/drivers/iio/accel/st_accel_i2c.c b/drivers/iio/accel/st_accel_i2c.c index ffc9d097e484..58d164d90dca 100644 --- a/drivers/iio/accel/st_accel_i2c.c +++ b/drivers/iio/accel/st_accel_i2c.c @@ -36,7 +36,7 @@ static int st_accel_i2c_probe(struct i2c_client *client, st_sensors_i2c_configure(indio_dev, client, adata); - err = st_accel_common_probe(indio_dev); + err = st_accel_common_probe(indio_dev, client->dev.platform_data); if (err < 0) goto st_accel_common_probe_error; diff --git a/drivers/iio/accel/st_accel_spi.c b/drivers/iio/accel/st_accel_spi.c index 22b35bfea7d2..21ed9296311f 100644 --- a/drivers/iio/accel/st_accel_spi.c +++ b/drivers/iio/accel/st_accel_spi.c @@ -35,7 +35,7 @@ static int st_accel_spi_probe(struct spi_device *spi) st_sensors_spi_configure(indio_dev, spi, adata); - err = st_accel_common_probe(indio_dev); + err = st_accel_common_probe(indio_dev, spi->dev.platform_data); if (err < 0) goto st_accel_common_probe_error; diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 865b1781df66..965ee22d3ac8 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -22,7 +22,7 @@ static inline u32 st_sensors_get_unaligned_le24(const u8 *p) { - return ((s32)((p[0] | p[1] << 8 | p[2] << 16) << 8) >> 8); + return (s32)((p[0] | p[1] << 8 | p[2] << 16) << 8) >> 8; } static int st_sensors_write_data_with_mask(struct iio_dev *indio_dev, @@ -118,7 +118,7 @@ st_sensors_match_odr_error: } static int st_sensors_set_fullscale(struct iio_dev *indio_dev, - unsigned int fs) + unsigned int fs) { int err, i = 0; struct st_sensor_data *sdata = iio_priv(indio_dev); @@ -198,13 +198,39 @@ int st_sensors_set_axis_enable(struct iio_dev *indio_dev, u8 axis_enable) } EXPORT_SYMBOL(st_sensors_set_axis_enable); -int st_sensors_init_sensor(struct iio_dev *indio_dev) +int st_sensors_init_sensor(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata) { int err; struct st_sensor_data *sdata = iio_priv(indio_dev); mutex_init(&sdata->tb.buf_lock); + switch (pdata->drdy_int_pin) { + case 1: + if (sdata->sensor->drdy_irq.mask_int1 == 0) { + dev_err(&indio_dev->dev, + "DRDY on INT1 not available.\n"); + err = -EINVAL; + goto init_error; + } + sdata->drdy_int_pin = 1; + break; + case 2: + if (sdata->sensor->drdy_irq.mask_int2 == 0) { + dev_err(&indio_dev->dev, + "DRDY on INT2 not available.\n"); + err = -EINVAL; + goto init_error; + } + sdata->drdy_int_pin = 2; + break; + default: + dev_err(&indio_dev->dev, "DRDY on pdata not valid.\n"); + err = -EINVAL; + goto init_error; + } + err = st_sensors_set_enable(indio_dev, false); if (err < 0) goto init_error; @@ -234,6 +260,7 @@ EXPORT_SYMBOL(st_sensors_init_sensor); int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable) { int err; + u8 drdy_mask; struct st_sensor_data *sdata = iio_priv(indio_dev); /* Enable/Disable the interrupt generator 1. */ @@ -245,10 +272,14 @@ int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable) goto st_accel_set_dataready_irq_error; } + if (sdata->drdy_int_pin == 1) + drdy_mask = sdata->sensor->drdy_irq.mask_int1; + else + drdy_mask = sdata->sensor->drdy_irq.mask_int2; + /* Enable/Disable the interrupt generator for data ready. */ err = st_sensors_write_data_with_mask(indio_dev, - sdata->sensor->drdy_irq.addr, - sdata->sensor->drdy_irq.mask, (int)enable); + sdata->sensor->drdy_irq.addr, drdy_mask, (int)enable); st_accel_set_dataready_irq_error: return err; diff --git a/drivers/iio/gyro/st_gyro.h b/drivers/iio/gyro/st_gyro.h index 3ad9907bb154..f8f2bf84a5a2 100644 --- a/drivers/iio/gyro/st_gyro.h +++ b/drivers/iio/gyro/st_gyro.h @@ -23,7 +23,16 @@ #define L3G4IS_GYRO_DEV_NAME "l3g4is_ui" #define LSM330_GYRO_DEV_NAME "lsm330_gyro" -int st_gyro_common_probe(struct iio_dev *indio_dev); +/** + * struct st_sensors_platform_data - gyro platform data + * @drdy_int_pin: DRDY on gyros is available only on INT2 pin. + */ +static const struct st_sensors_platform_data gyro_pdata = { + .drdy_int_pin = 2, +}; + +int st_gyro_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata); void st_gyro_common_remove(struct iio_dev *indio_dev); #ifdef CONFIG_IIO_BUFFER diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index f9ed3488c314..85fa8d343bb2 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -60,7 +60,7 @@ #define ST_GYRO_1_BDU_ADDR 0x23 #define ST_GYRO_1_BDU_MASK 0x80 #define ST_GYRO_1_DRDY_IRQ_ADDR 0x22 -#define ST_GYRO_1_DRDY_IRQ_MASK 0x08 +#define ST_GYRO_1_DRDY_IRQ_INT2_MASK 0x08 #define ST_GYRO_1_MULTIREAD_BIT true /* CUSTOM VALUES FOR SENSOR 2 */ @@ -84,7 +84,7 @@ #define ST_GYRO_2_BDU_ADDR 0x23 #define ST_GYRO_2_BDU_MASK 0x80 #define ST_GYRO_2_DRDY_IRQ_ADDR 0x22 -#define ST_GYRO_2_DRDY_IRQ_MASK 0x08 +#define ST_GYRO_2_DRDY_IRQ_INT2_MASK 0x08 #define ST_GYRO_2_MULTIREAD_BIT true static const struct iio_chan_spec st_gyro_16bit_channels[] = { @@ -158,7 +158,7 @@ static const struct st_sensors st_gyro_sensors[] = { }, .drdy_irq = { .addr = ST_GYRO_1_DRDY_IRQ_ADDR, - .mask = ST_GYRO_1_DRDY_IRQ_MASK, + .mask_int2 = ST_GYRO_1_DRDY_IRQ_INT2_MASK, }, .multi_read_bit = ST_GYRO_1_MULTIREAD_BIT, .bootime = 2, @@ -221,7 +221,7 @@ static const struct st_sensors st_gyro_sensors[] = { }, .drdy_irq = { .addr = ST_GYRO_2_DRDY_IRQ_ADDR, - .mask = ST_GYRO_2_DRDY_IRQ_MASK, + .mask_int2 = ST_GYRO_2_DRDY_IRQ_INT2_MASK, }, .multi_read_bit = ST_GYRO_2_MULTIREAD_BIT, .bootime = 2, @@ -302,7 +302,8 @@ static const struct iio_trigger_ops st_gyro_trigger_ops = { #define ST_GYRO_TRIGGER_OPS NULL #endif -int st_gyro_common_probe(struct iio_dev *indio_dev) +int st_gyro_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata) { int err; struct st_sensor_data *gdata = iio_priv(indio_dev); @@ -324,7 +325,7 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) &gdata->sensor->fs.fs_avl[0]; gdata->odr = gdata->sensor->odr.odr_avl[0].hz; - err = st_sensors_init_sensor(indio_dev); + err = st_sensors_init_sensor(indio_dev, pdata); if (err < 0) goto st_gyro_common_probe_error; diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c index 8a310500573d..c7a29a4d7e82 100644 --- a/drivers/iio/gyro/st_gyro_i2c.c +++ b/drivers/iio/gyro/st_gyro_i2c.c @@ -36,7 +36,8 @@ static int st_gyro_i2c_probe(struct i2c_client *client, st_sensors_i2c_configure(indio_dev, client, gdata); - err = st_gyro_common_probe(indio_dev); + err = st_gyro_common_probe(indio_dev, + (struct st_sensors_platform_data *)&gyro_pdata); if (err < 0) goto st_gyro_common_probe_error; diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c index f3540390eb22..14b0762847f5 100644 --- a/drivers/iio/gyro/st_gyro_spi.c +++ b/drivers/iio/gyro/st_gyro_spi.c @@ -35,7 +35,8 @@ static int st_gyro_spi_probe(struct spi_device *spi) st_sensors_spi_configure(indio_dev, spi, gdata); - err = st_gyro_common_probe(indio_dev); + err = st_gyro_common_probe(indio_dev, + (struct st_sensors_platform_data *)&gyro_pdata); if (err < 0) goto st_gyro_common_probe_error; diff --git a/drivers/iio/magnetometer/st_magn.h b/drivers/iio/magnetometer/st_magn.h index 7e81d00ef0c3..694e33e0fb72 100644 --- a/drivers/iio/magnetometer/st_magn.h +++ b/drivers/iio/magnetometer/st_magn.h @@ -18,7 +18,8 @@ #define LSM303DLM_MAGN_DEV_NAME "lsm303dlm_magn" #define LIS3MDL_MAGN_DEV_NAME "lis3mdl" -int st_magn_common_probe(struct iio_dev *indio_dev); +int st_magn_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata); void st_magn_common_remove(struct iio_dev *indio_dev); #ifdef CONFIG_IIO_BUFFER diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index ebfe8f11a0c2..7cd784f522e5 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -345,7 +345,8 @@ static const struct iio_info magn_info = { .write_raw = &st_magn_write_raw, }; -int st_magn_common_probe(struct iio_dev *indio_dev) +int st_magn_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata) { int err; struct st_sensor_data *mdata = iio_priv(indio_dev); @@ -367,7 +368,7 @@ int st_magn_common_probe(struct iio_dev *indio_dev) &mdata->sensor->fs.fs_avl[0]; mdata->odr = mdata->sensor->odr.odr_avl[0].hz; - err = st_sensors_init_sensor(indio_dev); + err = st_sensors_init_sensor(indio_dev, pdata); if (err < 0) goto st_magn_common_probe_error; diff --git a/drivers/iio/magnetometer/st_magn_i2c.c b/drivers/iio/magnetometer/st_magn_i2c.c index e6adc4a86425..1bed117714c5 100644 --- a/drivers/iio/magnetometer/st_magn_i2c.c +++ b/drivers/iio/magnetometer/st_magn_i2c.c @@ -36,7 +36,7 @@ static int st_magn_i2c_probe(struct i2c_client *client, st_sensors_i2c_configure(indio_dev, client, mdata); - err = st_magn_common_probe(indio_dev); + err = st_magn_common_probe(indio_dev, NULL); if (err < 0) goto st_magn_common_probe_error; diff --git a/drivers/iio/magnetometer/st_magn_spi.c b/drivers/iio/magnetometer/st_magn_spi.c index 51adb797cb7d..a2333a1e6061 100644 --- a/drivers/iio/magnetometer/st_magn_spi.c +++ b/drivers/iio/magnetometer/st_magn_spi.c @@ -35,7 +35,7 @@ static int st_magn_spi_probe(struct spi_device *spi) st_sensors_spi_configure(indio_dev, spi, mdata); - err = st_magn_common_probe(indio_dev); + err = st_magn_common_probe(indio_dev, NULL); if (err < 0) goto st_magn_common_probe_error; diff --git a/drivers/iio/pressure/st_pressure.h b/drivers/iio/pressure/st_pressure.h index 414e45ac9b9b..b0b630688da6 100644 --- a/drivers/iio/pressure/st_pressure.h +++ b/drivers/iio/pressure/st_pressure.h @@ -16,7 +16,16 @@ #define LPS331AP_PRESS_DEV_NAME "lps331ap" -int st_press_common_probe(struct iio_dev *indio_dev); +/** + * struct st_sensors_platform_data - default press platform data + * @drdy_int_pin: default press DRDY is available on INT1 pin. + */ +static const struct st_sensors_platform_data default_press_pdata = { + .drdy_int_pin = 1, +}; + +int st_press_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata); void st_press_common_remove(struct iio_dev *indio_dev); #ifdef CONFIG_IIO_BUFFER diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index 3ffbc56917b4..81e2d5b030a6 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -58,7 +58,8 @@ #define ST_PRESS_1_BDU_ADDR 0x20 #define ST_PRESS_1_BDU_MASK 0x04 #define ST_PRESS_1_DRDY_IRQ_ADDR 0x22 -#define ST_PRESS_1_DRDY_IRQ_MASK 0x04 +#define ST_PRESS_1_DRDY_IRQ_INT1_MASK 0x04 +#define ST_PRESS_1_DRDY_IRQ_INT2_MASK 0x20 #define ST_PRESS_1_MULTIREAD_BIT true #define ST_PRESS_1_TEMP_OFFSET 42500 @@ -116,7 +117,8 @@ static const struct st_sensors st_press_sensors[] = { }, .drdy_irq = { .addr = ST_PRESS_1_DRDY_IRQ_ADDR, - .mask = ST_PRESS_1_DRDY_IRQ_MASK, + .mask_int1 = ST_PRESS_1_DRDY_IRQ_INT1_MASK, + .mask_int2 = ST_PRESS_1_DRDY_IRQ_INT2_MASK, }, .multi_read_bit = ST_PRESS_1_MULTIREAD_BIT, .bootime = 2, @@ -202,7 +204,8 @@ static const struct iio_trigger_ops st_press_trigger_ops = { #define ST_PRESS_TRIGGER_OPS NULL #endif -int st_press_common_probe(struct iio_dev *indio_dev) +int st_press_common_probe(struct iio_dev *indio_dev, + struct st_sensors_platform_data *plat_data) { int err; struct st_sensor_data *pdata = iio_priv(indio_dev); @@ -224,7 +227,11 @@ int st_press_common_probe(struct iio_dev *indio_dev) &pdata->sensor->fs.fs_avl[0]; pdata->odr = pdata->sensor->odr.odr_avl[0].hz; - err = st_sensors_init_sensor(indio_dev); + if (!plat_data) + plat_data = + (struct st_sensors_platform_data *)&default_press_pdata; + + err = st_sensors_init_sensor(indio_dev, plat_data); if (err < 0) goto st_press_common_probe_error; diff --git a/drivers/iio/pressure/st_pressure_i2c.c b/drivers/iio/pressure/st_pressure_i2c.c index 7cebcc73bfb0..306599307a96 100644 --- a/drivers/iio/pressure/st_pressure_i2c.c +++ b/drivers/iio/pressure/st_pressure_i2c.c @@ -36,7 +36,7 @@ static int st_press_i2c_probe(struct i2c_client *client, st_sensors_i2c_configure(indio_dev, client, pdata); - err = st_press_common_probe(indio_dev); + err = st_press_common_probe(indio_dev, client->dev.platform_data); if (err < 0) goto st_press_common_probe_error; diff --git a/drivers/iio/pressure/st_pressure_spi.c b/drivers/iio/pressure/st_pressure_spi.c index 17a14907940a..b2aded6d2108 100644 --- a/drivers/iio/pressure/st_pressure_spi.c +++ b/drivers/iio/pressure/st_pressure_spi.c @@ -35,7 +35,7 @@ static int st_press_spi_probe(struct spi_device *spi) st_sensors_spi_configure(indio_dev, spi, pdata); - err = st_press_common_probe(indio_dev); + err = st_press_common_probe(indio_dev, spi->dev.platform_data); if (err < 0) goto st_press_common_probe_error; diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 72b26940730d..e51f65480ea5 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -17,6 +17,8 @@ #include #include +#include + #define ST_SENSORS_TX_MAX_LENGTH 2 #define ST_SENSORS_RX_MAX_LENGTH 6 @@ -118,14 +120,16 @@ struct st_sensor_bdu { /** * struct st_sensor_data_ready_irq - ST sensor device data-ready interrupt * @addr: address of the register. - * @mask: mask to write the on/off value. + * @mask_int1: mask to enable/disable IRQ on INT1 pin. + * @mask_int2: mask to enable/disable IRQ on INT2 pin. * struct ig1 - represents the Interrupt Generator 1 of sensors. * @en_addr: address of the enable ig1 register. * @en_mask: mask to write the on/off value for enable. */ struct st_sensor_data_ready_irq { u8 addr; - u8 mask; + u8 mask_int1; + u8 mask_int2; struct { u8 en_addr; u8 en_mask; @@ -201,6 +205,7 @@ struct st_sensors { * @buffer_data: Data used by buffer part. * @odr: Output data rate of the sensor [Hz]. * num_data_channels: Number of data channels used in buffer. + * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). * @get_irq_data_ready: Function to get the IRQ used for data ready signal. * @tf: Transfer function structure used by I/O operations. * @tb: Transfer buffers and mutex used by I/O operations. @@ -219,6 +224,8 @@ struct st_sensor_data { unsigned int odr; unsigned int num_data_channels; + u8 drdy_int_pin; + unsigned int (*get_irq_data_ready) (struct iio_dev *indio_dev); const struct st_sensor_transfer_function *tf; @@ -249,7 +256,8 @@ static inline void st_sensors_deallocate_trigger(struct iio_dev *indio_dev) } #endif -int st_sensors_init_sensor(struct iio_dev *indio_dev); +int st_sensors_init_sensor(struct iio_dev *indio_dev, + struct st_sensors_platform_data *pdata); int st_sensors_set_enable(struct iio_dev *indio_dev, bool enable); diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h new file mode 100644 index 000000000000..753839187ba0 --- /dev/null +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -0,0 +1,24 @@ +/* + * STMicroelectronics sensors platform-data driver + * + * Copyright 2013 STMicroelectronics Inc. + * + * Denis Ciocca + * + * Licensed under the GPL-2. + */ + +#ifndef ST_SENSORS_PDATA_H +#define ST_SENSORS_PDATA_H + +/** + * struct st_sensors_platform_data - Platform data for the ST sensors + * @drdy_int_pin: Redirect DRDY on pin 1 (1) or pin 2 (2). + * Available only for accelerometer and pressure sensors. + * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). + */ +struct st_sensors_platform_data { + u8 drdy_int_pin; +}; + +#endif /* ST_SENSORS_PDATA_H */ -- cgit v1.2.3-71-gd317 From 60b188f0d679656a1a2603d3bc1fa005373f4b9c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 16 Jul 2013 16:08:00 +0100 Subject: iio: Remove IIO_DEV_ATTR_RESET macro There are no users of this macro left and we have come to the conclusion that it is not a good idea to expose the raw chip reset to userspace so the macro is very unlikely to be used in new drivers. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/sysfs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/sysfs.h b/include/linux/iio/sysfs.h index b7a934b9431b..2958c960003a 100644 --- a/include/linux/iio/sysfs.h +++ b/include/linux/iio/sysfs.h @@ -73,11 +73,6 @@ struct iio_const_attr { .dev_attr = __ATTR(_name, S_IRUGO, iio_read_const_attr, NULL)} /* Generic attributes of onetype or another */ -/** - * IIO_DEV_ATTR_RESET: resets the device - **/ -#define IIO_DEV_ATTR_RESET(_store) \ - IIO_DEVICE_ATTR(reset, S_IWUSR, NULL, _store, 0) /** * IIO_DEV_ATTR_SAMP_FREQ - sets any internal clock frequency -- cgit v1.2.3-71-gd317 From 9dabaf5eddbafa21aded7c063cb38d2e8936c237 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 18 Jul 2013 11:19:00 +0100 Subject: iio: core: implement devm_iio_device_alloc/devm_iio_device_free Add a resource managed devm_iio_device_alloc()/devm_iio_device_free() to automatically clean up any allocations made by IIO drivers, thus leading to simplified IIO drivers code. In addition, this will allow IIO drivers to use other devm_*() API (like devm_request_irq) and don't care about the race between iio_device_free() and the release of resources by Device core during driver removing. Signed-off-by: Grygorii Strashko Signed-off-by: Oleksandr Kravchenko Tested-by: Oleksandr Kravchenko Reviewed-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-core.c | 47 +++++++++++++++++++++++++++++++++++++++++ include/linux/iio/iio.h | 25 ++++++++++++++++++++++ 2 files changed, 72 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index e145931ef1b8..d56d1229e2d6 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -912,6 +912,53 @@ void iio_device_free(struct iio_dev *dev) } EXPORT_SYMBOL(iio_device_free); +static void devm_iio_device_release(struct device *dev, void *res) +{ + iio_device_free(*(struct iio_dev **)res); +} + +static int devm_iio_device_match(struct device *dev, void *res, void *data) +{ + struct iio_dev **r = res; + if (!r || !*r) { + WARN_ON(!r || !*r); + return 0; + } + return *r == data; +} + +struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv) +{ + struct iio_dev **ptr, *iio_dev; + + ptr = devres_alloc(devm_iio_device_release, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return NULL; + + /* use raw alloc_dr for kmalloc caller tracing */ + iio_dev = iio_device_alloc(sizeof_priv); + if (iio_dev) { + *ptr = iio_dev; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return iio_dev; +} +EXPORT_SYMBOL_GPL(devm_iio_device_alloc); + +void devm_iio_device_free(struct device *dev, struct iio_dev *iio_dev) +{ + int rc; + + rc = devres_release(dev, devm_iio_device_release, + devm_iio_device_match, iio_dev); + WARN_ON(rc); +} +EXPORT_SYMBOL_GPL(devm_iio_device_free); + /** * iio_chrdev_open() - chrdev file open for buffer access and ioctls **/ diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 3d35b7023591..61d220f89aca 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -531,6 +531,31 @@ static inline struct iio_dev *iio_priv_to_dev(void *priv) **/ void iio_device_free(struct iio_dev *indio_dev); +/** + * devm_iio_device_alloc - Resource-managed iio_device_alloc() + * @dev: Device to allocate iio_dev for + * @sizeof_priv: Space to allocate for private structure. + * + * Managed iio_device_alloc. iio_dev allocated with this function is + * automatically freed on driver detach. + * + * If an iio_dev allocated with this function needs to be freed separately, + * devm_iio_device_free() must be used. + * + * RETURNS: + * Pointer to allocated iio_dev on success, NULL on failure. + */ +struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); + +/** + * devm_iio_device_free - Resource-managed iio_device_free() + * @dev: Device this iio_dev belongs to + * @indio_dev: the iio_dev associated with the device + * + * Free indio_dev allocated with devm_iio_device_alloc(). + */ +void devm_iio_device_free(struct device *dev, struct iio_dev *iio_dev); + /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3-71-gd317 From 9bc541028b2b93962e0bebce62ce6e295aab2086 Mon Sep 17 00:00:00 2001 From: Peter Meerwald Date: Mon, 29 Jul 2013 22:35:00 +0100 Subject: iio: Fix documentation of devm_iio_device_free() Signed-off-by: Peter Meerwald Cc: Grygorii Strashko Cc: Oleksandr Kravchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 61d220f89aca..09ebe0a4d8e6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -552,9 +552,9 @@ struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); * @dev: Device this iio_dev belongs to * @indio_dev: the iio_dev associated with the device * - * Free indio_dev allocated with devm_iio_device_alloc(). + * Free iio_dev allocated with devm_iio_device_alloc(). */ -void devm_iio_device_free(struct device *dev, struct iio_dev *iio_dev); +void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); /** * iio_buffer_enabled() - helper function to test if the buffer is enabled -- cgit v1.2.3-71-gd317 From 6eee5b3b493824731ed34ade0299241f91f04096 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 11 Jun 2013 20:48:02 +0900 Subject: extcon: Add an API to get extcon device from dt node Added an API of_extcon_get_extcon_dev() to be used by drivers to get extcon device in the case of dt boot (this can be used instead of extcon_get_extcon_dev()). Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- drivers/extcon/Kconfig | 4 +++ drivers/extcon/Makefile | 2 ++ drivers/extcon/extcon-class.c | 3 +- drivers/extcon/of_extcon.c | 64 ++++++++++++++++++++++++++++++++++++++++ include/linux/extcon/of_extcon.h | 31 +++++++++++++++++++ 5 files changed, 103 insertions(+), 1 deletion(-) create mode 100644 drivers/extcon/of_extcon.c create mode 100644 include/linux/extcon/of_extcon.h (limited to 'include/linux') diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 63f454e20576..f1d54a3985bd 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -14,6 +14,10 @@ if EXTCON comment "Extcon Device Drivers" +config OF_EXTCON + def_tristate y + depends on OF + config EXTCON_GPIO tristate "GPIO extcon support" depends on GPIOLIB diff --git a/drivers/extcon/Makefile b/drivers/extcon/Makefile index 540e2c3a4431..759fdae46f95 100644 --- a/drivers/extcon/Makefile +++ b/drivers/extcon/Makefile @@ -2,6 +2,8 @@ # Makefile for external connector class (extcon) devices # +obj-$(CONFIG_OF_EXTCON) += of_extcon.o + obj-$(CONFIG_EXTCON) += extcon-class.o obj-$(CONFIG_EXTCON_GPIO) += extcon-gpio.o obj-$(CONFIG_EXTCON_ADC_JACK) += extcon-adc-jack.o diff --git a/drivers/extcon/extcon-class.c b/drivers/extcon/extcon-class.c index 18ccadef43fd..1446152bf2e9 100644 --- a/drivers/extcon/extcon-class.c +++ b/drivers/extcon/extcon-class.c @@ -602,7 +602,8 @@ int extcon_dev_register(struct extcon_dev *edev, struct device *dev) edev->dev->class = extcon_class; edev->dev->release = extcon_dev_release; - dev_set_name(edev->dev, "%s", edev->name ? edev->name : dev_name(dev)); + edev->name = edev->name ? edev->name : dev_name(dev); + dev_set_name(edev->dev, "%s", edev->name); if (edev->max_supported) { char buf[10]; diff --git a/drivers/extcon/of_extcon.c b/drivers/extcon/of_extcon.c new file mode 100644 index 000000000000..72173ecbb311 --- /dev/null +++ b/drivers/extcon/of_extcon.c @@ -0,0 +1,64 @@ +/* + * OF helpers for External connector (extcon) framework + * + * Copyright (C) 2013 Texas Instruments, Inc. + * Kishon Vijay Abraham I + * + * Copyright (C) 2013 Samsung Electronics + * Chanwoo Choi + * + * 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. + */ + +#include +#include +#include +#include +#include +#include +#include + +/* + * of_extcon_get_extcon_dev - Get the name of extcon device from devicetree + * @dev - instance to the given device + * @index - index into list of extcon_dev + * + * return the instance of extcon device + */ +struct extcon_dev *of_extcon_get_extcon_dev(struct device *dev, int index) +{ + struct device_node *node; + struct extcon_dev *edev; + struct platform_device *extcon_parent_dev; + + if (!dev->of_node) { + dev_dbg(dev, "device does not have a device node entry\n"); + return ERR_PTR(-EINVAL); + } + + node = of_parse_phandle(dev->of_node, "extcon", index); + if (!node) { + dev_dbg(dev, "failed to get phandle in %s node\n", + dev->of_node->full_name); + return ERR_PTR(-ENODEV); + } + + extcon_parent_dev = of_find_device_by_node(node); + if (!extcon_parent_dev) { + dev_dbg(dev, "unable to find device by node\n"); + return ERR_PTR(-EPROBE_DEFER); + } + + edev = extcon_get_extcon_dev(dev_name(&extcon_parent_dev->dev)); + if (!edev) { + dev_dbg(dev, "unable to get extcon device : %s\n", + dev_name(&extcon_parent_dev->dev)); + return ERR_PTR(-ENODEV); + } + + return edev; +} +EXPORT_SYMBOL_GPL(of_extcon_get_extcon_dev); diff --git a/include/linux/extcon/of_extcon.h b/include/linux/extcon/of_extcon.h new file mode 100644 index 000000000000..0ebfeff1b55d --- /dev/null +++ b/include/linux/extcon/of_extcon.h @@ -0,0 +1,31 @@ +/* + * OF helpers for External connector (extcon) framework + * + * Copyright (C) 2013 Texas Instruments, Inc. + * Kishon Vijay Abraham I + * + * Copyright (C) 2013 Samsung Electronics + * Chanwoo Choi + * + * 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. + */ + +#ifndef __LINUX_OF_EXTCON_H +#define __LINUX_OF_EXTCON_H + +#include + +#if IS_ENABLED(CONFIG_OF_EXTCON) +extern struct extcon_dev + *of_extcon_get_extcon_dev(struct device *dev, int index); +#else +static inline struct extcon_dev + *of_extcon_get_extcon_dev(struct device *dev, int index) +{ + return ERR_PTR(-ENOSYS); +} +#endif /* CONFIG_OF_EXTCON */ +#endif /* __LINUX_OF_EXTCON_H */ -- cgit v1.2.3-71-gd317 From 8061ad7239f3f97b477984660e95134ca684578c Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 8 Jul 2013 09:54:43 +0900 Subject: usb: dwc3: use extcon fwrk to receive connect/disconnect Modified dwc3-omap to receive connect and disconnect notification using extcon framework. Also did the necessary cleanups required after adapting to extcon framework. Signed-off-by: Kishon Vijay Abraham I Acked-by: Felipe Balbi Signed-off-by: Chanwoo Choi --- Documentation/devicetree/bindings/usb/omap-usb.txt | 5 + drivers/usb/dwc3/Kconfig | 1 + drivers/usb/dwc3/dwc3-omap.c | 125 +++++++++++++++++---- include/linux/usb/dwc3-omap.h | 30 ----- 4 files changed, 112 insertions(+), 49 deletions(-) delete mode 100644 include/linux/usb/dwc3-omap.h (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/usb/omap-usb.txt b/Documentation/devicetree/bindings/usb/omap-usb.txt index 57e71f6817d0..9088ab09e200 100644 --- a/Documentation/devicetree/bindings/usb/omap-usb.txt +++ b/Documentation/devicetree/bindings/usb/omap-usb.txt @@ -53,6 +53,11 @@ OMAP DWC3 GLUE It should be set to "1" for HW mode and "2" for SW mode. - ranges: the child address space are mapped 1:1 onto the parent address space +Optional Properties: + - extcon : phandle for the extcon device omap dwc3 uses to detect + connect/disconnect events. + - vbus-supply : phandle to the regulator device tree node if needed. + Sub-nodes: The dwc3 core should be added as subnode to omap dwc3 glue. - dwc3 : diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig index 2378958ea63e..4c855e598c84 100644 --- a/drivers/usb/dwc3/Kconfig +++ b/drivers/usb/dwc3/Kconfig @@ -1,6 +1,7 @@ config USB_DWC3 tristate "DesignWare USB3 DRD Core Support" depends on (USB || USB_GADGET) && GENERIC_HARDIRQS && HAS_DMA + depends on EXTCON select USB_XHCI_PLATFORM if USB_SUPPORT && USB_XHCI_HCD help Say Y or M here if your system has a Dual Role SuperSpeed diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c index 077f110bd746..b26c2a4b4fb5 100644 --- a/drivers/usb/dwc3/dwc3-omap.c +++ b/drivers/usb/dwc3/dwc3-omap.c @@ -43,13 +43,15 @@ #include #include #include -#include #include #include #include #include #include #include +#include +#include +#include #include @@ -155,9 +157,21 @@ struct dwc3_omap { u32 revision; u32 dma_status:1; + + struct extcon_specific_cable_nb extcon_vbus_dev; + struct extcon_specific_cable_nb extcon_id_dev; + struct notifier_block vbus_nb; + struct notifier_block id_nb; + + struct regulator *vbus_reg; }; -static struct dwc3_omap *_omap; +enum omap_dwc3_vbus_id_status { + OMAP_DWC3_ID_FLOAT, + OMAP_DWC3_ID_GROUND, + OMAP_DWC3_VBUS_OFF, + OMAP_DWC3_VBUS_VALID, +}; static inline u32 dwc3_omap_readl(void __iomem *base, u32 offset) { @@ -221,18 +235,24 @@ static void dwc3_omap_write_irq0_set(struct dwc3_omap *omap, u32 value) omap->irq0_offset, value); } -int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) +static void dwc3_omap_set_mailbox(struct dwc3_omap *omap, + enum omap_dwc3_vbus_id_status status) { - u32 val; - struct dwc3_omap *omap = _omap; - - if (!omap) - return -EPROBE_DEFER; + int ret; + u32 val; switch (status) { case OMAP_DWC3_ID_GROUND: dev_dbg(omap->dev, "ID GND\n"); + if (omap->vbus_reg) { + ret = regulator_enable(omap->vbus_reg); + if (ret) { + dev_dbg(omap->dev, "regulator enable failed\n"); + return; + } + } + val = dwc3_omap_read_utmi_status(omap); val &= ~(USBOTGSS_UTMI_OTG_STATUS_IDDIG | USBOTGSS_UTMI_OTG_STATUS_VBUSVALID @@ -255,6 +275,9 @@ int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) break; case OMAP_DWC3_ID_FLOAT: + if (omap->vbus_reg) + regulator_disable(omap->vbus_reg); + case OMAP_DWC3_VBUS_OFF: dev_dbg(omap->dev, "VBUS Disconnect\n"); @@ -268,12 +291,9 @@ int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) break; default: - dev_dbg(omap->dev, "ID float\n"); + dev_dbg(omap->dev, "invalid state\n"); } - - return 0; } -EXPORT_SYMBOL_GPL(dwc3_omap_mailbox); static irqreturn_t dwc3_omap_interrupt(int irq, void *_omap) { @@ -366,6 +386,32 @@ static void dwc3_omap_disable_irqs(struct dwc3_omap *omap) static u64 dwc3_omap_dma_mask = DMA_BIT_MASK(32); +static int dwc3_omap_id_notifier(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct dwc3_omap *omap = container_of(nb, struct dwc3_omap, id_nb); + + if (event) + dwc3_omap_set_mailbox(omap, OMAP_DWC3_ID_GROUND); + else + dwc3_omap_set_mailbox(omap, OMAP_DWC3_ID_FLOAT); + + return NOTIFY_DONE; +} + +static int dwc3_omap_vbus_notifier(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct dwc3_omap *omap = container_of(nb, struct dwc3_omap, vbus_nb); + + if (event) + dwc3_omap_set_mailbox(omap, OMAP_DWC3_VBUS_VALID); + else + dwc3_omap_set_mailbox(omap, OMAP_DWC3_VBUS_OFF); + + return NOTIFY_DONE; +} + static int dwc3_omap_probe(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; @@ -373,6 +419,8 @@ static int dwc3_omap_probe(struct platform_device *pdev) struct dwc3_omap *omap; struct resource *res; struct device *dev = &pdev->dev; + struct extcon_dev *edev; + struct regulator *vbus_reg = NULL; int ret = -ENOMEM; int irq; @@ -415,19 +463,22 @@ static int dwc3_omap_probe(struct platform_device *pdev) return -ENOMEM; } + if (of_property_read_bool(node, "vbus-supply")) { + vbus_reg = devm_regulator_get(dev, "vbus"); + if (IS_ERR(vbus_reg)) { + dev_err(dev, "vbus init failed\n"); + return PTR_ERR(vbus_reg); + } + } + spin_lock_init(&omap->lock); omap->dev = dev; omap->irq = irq; omap->base = base; + omap->vbus_reg = vbus_reg; dev->dma_mask = &dwc3_omap_dma_mask; - /* - * REVISIT if we ever have two instances of the wrapper, we will be - * in big trouble - */ - _omap = omap; - pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); if (ret < 0) { @@ -502,14 +553,46 @@ static int dwc3_omap_probe(struct platform_device *pdev) dwc3_omap_enable_irqs(omap); + if (of_property_read_bool(node, "extcon")) { + edev = of_extcon_get_extcon_dev(dev, 0); + if (IS_ERR(edev)) { + dev_vdbg(dev, "couldn't get extcon device\n"); + ret = PTR_ERR(edev); + goto err2; + } + + omap->vbus_nb.notifier_call = dwc3_omap_vbus_notifier; + ret = extcon_register_interest(&omap->extcon_vbus_dev, + edev->name, "USB", &omap->vbus_nb); + if (ret < 0) + dev_vdbg(dev, "failed to register notifier for USB\n"); + omap->id_nb.notifier_call = dwc3_omap_id_notifier; + ret = extcon_register_interest(&omap->extcon_id_dev, edev->name, + "USB-HOST", &omap->id_nb); + if (ret < 0) + dev_vdbg(dev, + "failed to register notifier for USB-HOST\n"); + + if (extcon_get_cable_state(edev, "USB") == true) + dwc3_omap_set_mailbox(omap, OMAP_DWC3_VBUS_VALID); + if (extcon_get_cable_state(edev, "USB-HOST") == true) + dwc3_omap_set_mailbox(omap, OMAP_DWC3_ID_GROUND); + } + ret = of_platform_populate(node, NULL, NULL, dev); if (ret) { dev_err(&pdev->dev, "failed to create dwc3 core\n"); - goto err2; + goto err3; } return 0; +err3: + if (omap->extcon_vbus_dev.edev) + extcon_unregister_interest(&omap->extcon_vbus_dev); + if (omap->extcon_id_dev.edev) + extcon_unregister_interest(&omap->extcon_id_dev); + err2: dwc3_omap_disable_irqs(omap); @@ -526,6 +609,10 @@ static int dwc3_omap_remove(struct platform_device *pdev) { struct dwc3_omap *omap = platform_get_drvdata(pdev); + if (omap->extcon_vbus_dev.edev) + extcon_unregister_interest(&omap->extcon_vbus_dev); + if (omap->extcon_id_dev.edev) + extcon_unregister_interest(&omap->extcon_id_dev); dwc3_omap_disable_irqs(omap); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); diff --git a/include/linux/usb/dwc3-omap.h b/include/linux/usb/dwc3-omap.h deleted file mode 100644 index 5615f4d82724..000000000000 --- a/include/linux/usb/dwc3-omap.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Copyright (C) 2013 by Texas Instruments - * - * The Inventra Controller Driver for Linux is free software; you - * can redistribute it and/or modify it under the terms of the GNU - * General Public License version 2 as published by the Free Software - * Foundation. - */ - -#ifndef __DWC3_OMAP_H__ -#define __DWC3_OMAP_H__ - -enum omap_dwc3_vbus_id_status { - OMAP_DWC3_UNKNOWN = 0, - OMAP_DWC3_ID_GROUND, - OMAP_DWC3_ID_FLOAT, - OMAP_DWC3_VBUS_VALID, - OMAP_DWC3_VBUS_OFF, -}; - -#if (defined(CONFIG_USB_DWC3) || defined(CONFIG_USB_DWC3_MODULE)) -extern int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status); -#else -static inline int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) -{ - return -ENODEV; -} -#endif - -#endif /* __DWC3_OMAP_H__ */ -- cgit v1.2.3-71-gd317 From 43e3f38892a6a521ff5901cdb97cf6985101badd Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 9 Jul 2013 18:34:21 +0530 Subject: extcon: palmas: remove unused member from palams_usb structure Remove unused member vbus_enable and set_vbus_work from palmas_usb as these members are not used in drivers. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- include/linux/mfd/palmas.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..03c22ca55446 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -371,16 +371,11 @@ struct palmas_usb { struct extcon_dev edev; - /* used to set vbus, in atomic path */ - struct work_struct set_vbus_work; - int id_otg_irq; int id_irq; int vbus_otg_irq; int vbus_irq; - int vbus_enable; - enum palmas_usb_state linkstat; }; -- cgit v1.2.3-71-gd317 From 7281e05aabee7484624d448da208932690ed62b3 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 10 Jul 2013 14:59:06 +0530 Subject: extcon: palmas: Option to disable ID/VBUS detection based on platform Based on system design, platform needs to detect the VBUS or ID or both. Provide option to select this through platform data to disable part of cable detection through palmas-usb. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Chanwoo Choi Signed-off-by: Myungjoo Ham --- .../devicetree/bindings/extcon/extcon-palmas.txt | 2 + drivers/extcon/extcon-palmas.c | 87 +++++++++++++--------- include/linux/mfd/palmas.h | 3 + 3 files changed, 57 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/extcon/extcon-palmas.txt b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt index f110e75fd0a1..7dab6a8f4a0e 100644 --- a/Documentation/devicetree/bindings/extcon/extcon-palmas.txt +++ b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt @@ -6,6 +6,8 @@ Required Properties: Optional Properties: - ti,wakeup : To enable the wakeup comparator in probe + - ti,enable-id-detection: Perform ID detection. + - ti,enable-vbus-detection: Perform VBUS detection. palmas-usb { compatible = "ti,twl6035-usb", "ti,palmas-usb"; diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c index d0ce0f16de70..89fdd05c5fd6 100644 --- a/drivers/extcon/extcon-palmas.c +++ b/drivers/extcon/extcon-palmas.c @@ -122,11 +122,14 @@ static void palmas_enable_irq(struct palmas_usb *palmas_usb) PALMAS_USB_ID_INT_EN_HI_SET_ID_GND | PALMAS_USB_ID_INT_EN_HI_SET_ID_FLOAT); - palmas_vbus_irq_handler(palmas_usb->vbus_irq, palmas_usb); + if (palmas_usb->enable_vbus_detection) + palmas_vbus_irq_handler(palmas_usb->vbus_irq, palmas_usb); /* cold plug for host mode needs this delay */ - msleep(30); - palmas_id_irq_handler(palmas_usb->id_irq, palmas_usb); + if (palmas_usb->enable_id_detection) { + msleep(30); + palmas_id_irq_handler(palmas_usb->id_irq, palmas_usb); + } } static int palmas_usb_probe(struct platform_device *pdev) @@ -137,21 +140,25 @@ static int palmas_usb_probe(struct platform_device *pdev) struct palmas_usb *palmas_usb; int status; - if (node && !pdata) { - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - - if (!pdata) - return -ENOMEM; - - pdata->wakeup = of_property_read_bool(node, "ti,wakeup"); - } else if (!pdata) { - return -EINVAL; - } - palmas_usb = devm_kzalloc(&pdev->dev, sizeof(*palmas_usb), GFP_KERNEL); if (!palmas_usb) return -ENOMEM; + if (node && !pdata) { + palmas_usb->wakeup = of_property_read_bool(node, "ti,wakeup"); + palmas_usb->enable_id_detection = of_property_read_bool(node, + "ti,enable-id-detection"); + palmas_usb->enable_vbus_detection = of_property_read_bool(node, + "ti,enable-vbus-detection"); + } else { + palmas_usb->wakeup = true; + palmas_usb->enable_id_detection = true; + palmas_usb->enable_vbus_detection = true; + + if (pdata) + palmas_usb->wakeup = pdata->wakeup; + } + palmas->usb = palmas_usb; palmas_usb->palmas = palmas; @@ -166,7 +173,7 @@ static int palmas_usb_probe(struct platform_device *pdev) palmas_usb->vbus_irq = regmap_irq_get_virq(palmas->irq_data, PALMAS_VBUS_IRQ); - palmas_usb_wakeup(palmas, pdata->wakeup); + palmas_usb_wakeup(palmas, palmas_usb->wakeup); platform_set_drvdata(pdev, palmas_usb); @@ -179,26 +186,32 @@ static int palmas_usb_probe(struct platform_device *pdev) return status; } - status = devm_request_threaded_irq(palmas_usb->dev, palmas_usb->id_irq, - NULL, palmas_id_irq_handler, - IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING | - IRQF_ONESHOT | IRQF_EARLY_RESUME, - "palmas_usb_id", palmas_usb); - if (status < 0) { - dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", + if (palmas_usb->enable_id_detection) { + status = devm_request_threaded_irq(palmas_usb->dev, + palmas_usb->id_irq, + NULL, palmas_id_irq_handler, + IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING | + IRQF_ONESHOT | IRQF_EARLY_RESUME, + "palmas_usb_id", palmas_usb); + if (status < 0) { + dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", palmas_usb->id_irq, status); - goto fail_extcon; + goto fail_extcon; + } } - status = devm_request_threaded_irq(palmas_usb->dev, - palmas_usb->vbus_irq, NULL, palmas_vbus_irq_handler, - IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING | - IRQF_ONESHOT | IRQF_EARLY_RESUME, - "palmas_usb_vbus", palmas_usb); - if (status < 0) { - dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", + if (palmas_usb->enable_vbus_detection) { + status = devm_request_threaded_irq(palmas_usb->dev, + palmas_usb->vbus_irq, NULL, + palmas_vbus_irq_handler, + IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING | + IRQF_ONESHOT | IRQF_EARLY_RESUME, + "palmas_usb_vbus", palmas_usb); + if (status < 0) { + dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", palmas_usb->vbus_irq, status); - goto fail_extcon; + goto fail_extcon; + } } palmas_enable_irq(palmas_usb); @@ -226,8 +239,10 @@ static int palmas_usb_suspend(struct device *dev) struct palmas_usb *palmas_usb = dev_get_drvdata(dev); if (device_may_wakeup(dev)) { - enable_irq_wake(palmas_usb->vbus_irq); - enable_irq_wake(palmas_usb->id_irq); + if (palmas_usb->enable_vbus_detection) + enable_irq_wake(palmas_usb->vbus_irq); + if (palmas_usb->enable_id_detection) + enable_irq_wake(palmas_usb->id_irq); } return 0; } @@ -237,8 +252,10 @@ static int palmas_usb_resume(struct device *dev) struct palmas_usb *palmas_usb = dev_get_drvdata(dev); if (device_may_wakeup(dev)) { - disable_irq_wake(palmas_usb->vbus_irq); - disable_irq_wake(palmas_usb->id_irq); + if (palmas_usb->enable_vbus_detection) + disable_irq_wake(palmas_usb->vbus_irq); + if (palmas_usb->enable_id_detection) + disable_irq_wake(palmas_usb->id_irq); } return 0; }; diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 03c22ca55446..cfc678ceb570 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -377,6 +377,9 @@ struct palmas_usb { int vbus_irq; enum palmas_usb_state linkstat; + int wakeup; + bool enable_vbus_detection; + bool enable_id_detection; }; #define comparator_to_palmas(x) container_of((x), struct palmas_usb, comparator) -- cgit v1.2.3-71-gd317 From 7d46daba8dd5df1aa45724518a041ef7163d3ad5 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 5 Aug 2013 16:05:32 +0300 Subject: mlx5: remove health handler plugin Remove this code, per Dave Miller's request, since it is not being used anywhere in the kernel. Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 29 +----------------------- include/linux/mlx5/driver.h | 3 --- 2 files changed, 1 insertion(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 748f10a155c4..3e6670c4a7cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -55,33 +55,9 @@ enum { }; static DEFINE_SPINLOCK(health_lock); - static LIST_HEAD(health_list); static struct work_struct health_work; -static health_handler_t reg_handler; -int mlx5_register_health_report_handler(health_handler_t handler) -{ - spin_lock_irq(&health_lock); - if (reg_handler) { - spin_unlock_irq(&health_lock); - return -EEXIST; - } - reg_handler = handler; - spin_unlock_irq(&health_lock); - - return 0; -} -EXPORT_SYMBOL(mlx5_register_health_report_handler); - -void mlx5_unregister_health_report_handler(void) -{ - spin_lock_irq(&health_lock); - reg_handler = NULL; - spin_unlock_irq(&health_lock); -} -EXPORT_SYMBOL(mlx5_unregister_health_report_handler); - static void health_care(struct work_struct *work) { struct mlx5_core_health *health, *n; @@ -98,11 +74,8 @@ static void health_care(struct work_struct *work) priv = container_of(health, struct mlx5_priv, health); dev = container_of(priv, struct mlx5_core_dev, priv); mlx5_core_warn(dev, "handling bad device here\n"); + /* nothing yet */ spin_lock_irq(&health_lock); - if (reg_handler) - reg_handler(dev->pdev, health->health, - sizeof(health->health)); - list_del_init(&health->list); spin_unlock_irq(&health_lock); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2aa258b0ced1..611e65e76b00 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -731,9 +731,6 @@ void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); -typedef void (*health_handler_t)(struct pci_dev *pdev, struct health_buffer __iomem *buf, int size); -int mlx5_register_health_report_handler(health_handler_t handler); -void mlx5_unregister_health_report_handler(void); const char *mlx5_command_str(int command); int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); -- cgit v1.2.3-71-gd317 From 49ccc142f9cbc33fdda18e8fa90c1c5b4a79c0ad Mon Sep 17 00:00:00 2001 From: Mateusz Krawczuk Date: Tue, 6 Aug 2013 18:34:40 +0200 Subject: regmap: Add missing header for !CONFIG_REGMAP stubs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit regmap.h requires linux/err.h if CONFIG_REGMAP is not defined. Without it I get error. CC drivers/media/platform/exynos4-is/fimc-reg.o In file included from drivers/media/platform/exynos4-is/fimc-reg.c:14:0: include/linux/regmap.h: In function ‘regmap_write’: include/linux/regmap.h:525:10: error: ‘EINVAL’ undeclared (first use in this function) include/linux/regmap.h:525:10: note: each undeclared identifier is reported only once for each function it appears in Signed-off-by: Mateusz Krawczuk Signed-off-by: Kyungmin Park Signed-off-by: Mark Brown Cc: stable@kernel.org --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 75981d0b57dc..580a5320cc96 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -15,6 +15,7 @@ #include #include +#include struct module; struct device; -- cgit v1.2.3-71-gd317 From b6c035d04e80b4244a143e34e51c84cf2181bd94 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 5 Aug 2013 15:02:48 -0700 Subject: x86, asmlinkage: Make dump_stack visible dump_stack is used from assembler code, so make it visible. Signed-off-by: Andi Kleen Link: http://lkml.kernel.org/r/1375740170-7446-15-git-send-email-andi@firstfloor.org Signed-off-by: H. Peter Anvin --- include/linux/printk.h | 2 +- lib/dump_stack.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 22c7052e9372..e6131a782481 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -200,7 +200,7 @@ static inline void show_regs_print_info(const char *log_lvl) } #endif -extern void dump_stack(void) __cold; +extern asmlinkage void dump_stack(void) __cold; #ifndef pr_fmt #define pr_fmt(fmt) fmt diff --git a/lib/dump_stack.c b/lib/dump_stack.c index c03154173cc7..f23b63f0a1c3 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -23,7 +23,7 @@ static void __dump_stack(void) #ifdef CONFIG_SMP static atomic_t dump_lock = ATOMIC_INIT(-1); -void dump_stack(void) +asmlinkage void dump_stack(void) { int was_locked; int old; @@ -55,7 +55,7 @@ retry: preempt_enable(); } #else -void dump_stack(void) +asmlinkage void dump_stack(void) { __dump_stack(); } -- cgit v1.2.3-71-gd317 From 36f8250e4d478429a393c20910dcd02772bd0839 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 7 Aug 2013 08:56:10 +0800 Subject: regulator: fan53555: Prevent multiple include of fan53555.h Add define for __FAN53555_H__ to prevent multiple include of the header file. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/fan53555.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/fan53555.h b/include/linux/regulator/fan53555.h index 5c45c85d52ca..f13880e84d85 100644 --- a/include/linux/regulator/fan53555.h +++ b/include/linux/regulator/fan53555.h @@ -11,6 +11,7 @@ */ #ifndef __FAN53555_H__ +#define __FAN53555_H__ /* VSEL ID */ enum { -- cgit v1.2.3-71-gd317 From 786615bc1ce84150ded80daea6bd9f6297f48e73 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 5 Aug 2013 16:04:47 -0400 Subject: SUNRPC: If the rpcbind channel is disconnected, fail the call to unregister If rpcbind causes our connection to the AF_LOCAL socket to close after we've registered a service, then we want to be careful about reconnecting since the mount namespace may have changed. By simply refusing to reconnect the AF_LOCAL socket in the case of unregister, we avoid the need to somehow save the mount namespace. While this may lead to some services not unregistering properly, it should be safe. Signed-off-by: Trond Myklebust Cc: Nix Cc: Jeff Layton Cc: stable@vger.kernel.org # 3.9.x --- include/linux/sunrpc/sched.h | 1 + net/sunrpc/clnt.c | 4 ++++ net/sunrpc/netns.h | 1 + net/sunrpc/rpcb_clnt.c | 40 +++++++++++++++++++++++++++------------- 4 files changed, 33 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 6d870353674a..1821445708d6 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -121,6 +121,7 @@ struct rpc_task_setup { #define RPC_TASK_SOFTCONN 0x0400 /* Fail if can't connect */ #define RPC_TASK_SENT 0x0800 /* message was sent */ #define RPC_TASK_TIMEOUT 0x1000 /* fail with ETIMEDOUT on timeout */ +#define RPC_TASK_NOCONNECT 0x2000 /* return ENOTCONN if not connected */ #define RPC_IS_ASYNC(t) ((t)->tk_flags & RPC_TASK_ASYNC) #define RPC_IS_SWAPPER(t) ((t)->tk_flags & RPC_TASK_SWAPPER) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 74f6a704e374..ecbc4e3d83ad 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1660,6 +1660,10 @@ call_connect(struct rpc_task *task) task->tk_action = call_connect_status; if (task->tk_status < 0) return; + if (task->tk_flags & RPC_TASK_NOCONNECT) { + rpc_exit(task, -ENOTCONN); + return; + } xprt_connect(task); } } diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h index 74d948f5d5a1..779742cfc1ff 100644 --- a/net/sunrpc/netns.h +++ b/net/sunrpc/netns.h @@ -23,6 +23,7 @@ struct sunrpc_net { struct rpc_clnt *rpcb_local_clnt4; spinlock_t rpcb_clnt_lock; unsigned int rpcb_users; + unsigned int rpcb_is_af_local : 1; struct mutex gssp_lock; wait_queue_head_t gssp_wq; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index b0f723227157..1891a1022c17 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -204,13 +204,15 @@ void rpcb_put_local(struct net *net) } static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, - struct rpc_clnt *clnt4) + struct rpc_clnt *clnt4, + bool is_af_local) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); /* Protected by rpcb_create_local_mutex */ sn->rpcb_local_clnt = clnt; sn->rpcb_local_clnt4 = clnt4; + sn->rpcb_is_af_local = is_af_local ? 1 : 0; smp_wmb(); sn->rpcb_users = 1; dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " @@ -271,7 +273,7 @@ static int rpcb_create_local_unix(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, true); out: return result; @@ -323,7 +325,7 @@ static int rpcb_create_local_net(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, false); out: return result; @@ -384,13 +386,16 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, return rpc_create(&args); } -static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg) +static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, struct rpc_message *msg, bool is_set) { - int result, error = 0; + int flags = RPC_TASK_NOCONNECT; + int error, result = 0; + if (is_set || !sn->rpcb_is_af_local) + flags = RPC_TASK_SOFTCONN; msg->rpc_resp = &result; - error = rpc_call_sync(clnt, msg, RPC_TASK_SOFTCONN); + error = rpc_call_sync(clnt, msg, flags); if (error < 0) { dprintk("RPC: failed to contact local rpcbind " "server (errno %d).\n", -error); @@ -447,16 +452,19 @@ int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short .rpc_argp = &map, }; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + bool is_set = false; dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " "rpcbind\n", (port ? "" : "un"), prog, vers, prot, port); msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET]; + is_set = true; + } - return rpcb_register_call(sn->rpcb_local_clnt, &msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt, &msg, is_set); } /* @@ -469,6 +477,7 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -479,10 +488,12 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -497,6 +508,7 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -507,10 +519,12 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -527,7 +541,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn, map->r_addr = ""; msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - return rpcb_register_call(sn->rpcb_local_clnt4, msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, false); } /** -- cgit v1.2.3-71-gd317 From 5ff0a268037d344f86df690ccb994d8bc015d2d9 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:03 +0530 Subject: cpufreq: Clean up header files included in the core This patch addresses the following issues in the header files in the cpufreq core: - Include headers in ascending order, so that we don't add same many times by mistake. - must be included after , so that they override whatever they need to. - Remove unnecessary includes. - Don't include files already included by cpufreq.h or cpufreq_governor.h. [rjw: Changelog] Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 19 ++++++------------- drivers/cpufreq/cpufreq_conservative.c | 12 ------------ drivers/cpufreq/cpufreq_governor.c | 6 ------ drivers/cpufreq/cpufreq_governor.h | 5 ++--- drivers/cpufreq/cpufreq_ondemand.c | 12 +----------- drivers/cpufreq/cpufreq_performance.c | 3 +-- drivers/cpufreq/cpufreq_powersave.c | 3 +-- drivers/cpufreq/cpufreq_stats.c | 9 +-------- drivers/cpufreq/freq_table.c | 4 +--- include/linux/cpufreq.h | 11 +++-------- 10 files changed, 16 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e34bd94e12b4..845837174878 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -17,24 +17,17 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include -#include -#include -#include +#include #include #include -#include -#include -#include #include -#include -#include -#include +#include +#include +#include #include +#include #include - +#include #include /** diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 0ceb2eff5a7e..841e25699656 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -11,19 +11,7 @@ * published by the Free Software Foundation. */ -#include -#include -#include -#include -#include -#include -#include -#include -#include #include -#include -#include - #include "cpufreq_governor.h" /* Conservative governor macros */ diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 7409dbd1d897..556064e9cc01 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -16,15 +16,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include #include #include -#include #include -#include -#include #include "cpufreq_governor.h" diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index 0e0dd4c82020..cf0b7a4425b0 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -18,10 +18,9 @@ #define _CPUFREQ_GOVERNOR_H #include -#include +#include +#include #include -#include -#include /* * The polling frequency depends on the capability of the processor. Default diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index a3c5574f9b3a..27c732eee431 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -12,20 +12,10 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include -#include -#include -#include -#include +#include #include #include -#include #include -#include -#include - #include "cpufreq_governor.h" /* On-demand governor macros */ diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index 9fef7d6e4e6a..cf117deb39b1 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -12,10 +12,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include #include #include +#include static int cpufreq_governor_performance(struct cpufreq_policy *policy, unsigned int event) diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index 32109a14f5dc..e3b874c235ea 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -12,10 +12,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include #include #include +#include static int cpufreq_governor_powersave(struct cpufreq_policy *policy, unsigned int event) diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index cb3841355454..a7143b0597af 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -9,17 +9,10 @@ * published by the Free Software Foundation. */ -#include -#include #include -#include #include #include -#include -#include -#include -#include -#include +#include #include static spinlock_t cpufreq_stats_lock; diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index f0d87412cc91..f111454a7aea 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -11,10 +11,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include #include +#include /********************************************************************* * FREQUENCY TABLE HELPERS * diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index e1fd215e16c9..97627bbbca82 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -11,16 +11,11 @@ #ifndef _LINUX_CPUFREQ_H #define _LINUX_CPUFREQ_H -#include -#include -#include -#include +#include +#include #include +#include #include -#include -#include -#include -#include #define CPUFREQ_NAME_LEN 16 /* Print length for names. Extra 1 space for accomodating '\n' in prints */ -- cgit v1.2.3-71-gd317 From 74aca95da74836a6807118f6590d8df8232c74a9 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:04 +0530 Subject: cpufreq: Re-arrange declarations in cpufreq.h They are pretty much mixed up. Although generic headers are present, definitions/declarations are present outside of them too ... This patch just moves stuff up and down to make it look better and consistent. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 373 +++++++++++++++++++++++------------------------- 1 file changed, 177 insertions(+), 196 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 97627bbbca82..0d3b0266bc98 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -17,60 +17,30 @@ #include #include -#define CPUFREQ_NAME_LEN 16 -/* Print length for names. Extra 1 space for accomodating '\n' in prints */ -#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) - /********************************************************************* - * CPUFREQ NOTIFIER INTERFACE * + * CPUFREQ INTERFACE * *********************************************************************/ - -#define CPUFREQ_TRANSITION_NOTIFIER (0) -#define CPUFREQ_POLICY_NOTIFIER (1) - -#ifdef CONFIG_CPU_FREQ -int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); -int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list); -extern void disable_cpufreq(void); -#else /* CONFIG_CPU_FREQ */ -static inline int cpufreq_register_notifier(struct notifier_block *nb, - unsigned int list) -{ - return 0; -} -static inline int cpufreq_unregister_notifier(struct notifier_block *nb, - unsigned int list) -{ - return 0; -} -static inline void disable_cpufreq(void) { } -#endif /* CONFIG_CPU_FREQ */ - -/* if (cpufreq_driver->target) exists, the ->governor decides what frequency - * within the limits is used. If (cpufreq_driver->setpolicy> exists, these - * two generic policies are available: - */ - -#define CPUFREQ_POLICY_POWERSAVE (1) -#define CPUFREQ_POLICY_PERFORMANCE (2) - -/* Frequency values here are CPU kHz so that hardware which doesn't run - * with some frequencies can complain without having to guess what per - * cent / per mille means. +/* + * Frequency values here are CPU kHz + * * Maximum transition latency is in nanoseconds - if it's unknown, * CPUFREQ_ETERNAL shall be used. */ +#define CPUFREQ_ETERNAL (-1) +#define CPUFREQ_NAME_LEN 16 +/* Print length for names. Extra 1 space for accomodating '\n' in prints */ +#define CPUFREQ_NAME_PLEN (CPUFREQ_NAME_LEN + 1) + struct cpufreq_governor; -/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ -extern struct kobject *cpufreq_global_kobject; -int cpufreq_get_global_kobject(void); -void cpufreq_put_global_kobject(void); -int cpufreq_sysfs_create_file(const struct attribute *attr); -void cpufreq_sysfs_remove_file(const struct attribute *attr); +struct cpufreq_freqs { + unsigned int cpu; /* cpu nr */ + unsigned int old; + unsigned int new; + u8 flags; /* flags of cpufreq_driver, see below. */ +}; -#define CPUFREQ_ETERNAL (-1) struct cpufreq_cpuinfo { unsigned int max_freq; unsigned int min_freq; @@ -117,111 +87,95 @@ struct cpufreq_policy { int transition_ongoing; /* Tracks transition status */ }; -#define CPUFREQ_ADJUST (0) -#define CPUFREQ_INCOMPATIBLE (1) -#define CPUFREQ_NOTIFY (2) -#define CPUFREQ_START (3) -#define CPUFREQ_UPDATE_POLICY_CPU (4) - /* Only for ACPI */ #define CPUFREQ_SHARED_TYPE_NONE (0) /* None */ #define CPUFREQ_SHARED_TYPE_HW (1) /* HW does needed coordination */ #define CPUFREQ_SHARED_TYPE_ALL (2) /* All dependent CPUs should set freq */ #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ +struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); +void cpufreq_cpu_put(struct cpufreq_policy *data); + static inline bool policy_is_shared(struct cpufreq_policy *policy) { return cpumask_weight(policy->cpus) > 1; } -/******************** cpufreq transition notifiers *******************/ - -#define CPUFREQ_PRECHANGE (0) -#define CPUFREQ_POSTCHANGE (1) -#define CPUFREQ_RESUMECHANGE (8) -#define CPUFREQ_SUSPENDCHANGE (9) +/* /sys/devices/system/cpu/cpufreq: entry point for global variables */ +extern struct kobject *cpufreq_global_kobject; +int cpufreq_get_global_kobject(void); +void cpufreq_put_global_kobject(void); +int cpufreq_sysfs_create_file(const struct attribute *attr); +void cpufreq_sysfs_remove_file(const struct attribute *attr); -struct cpufreq_freqs { - unsigned int cpu; /* cpu nr */ - unsigned int old; - unsigned int new; - u8 flags; /* flags of cpufreq_driver, see below. */ -}; +#ifdef CONFIG_CPU_FREQ +unsigned int cpufreq_get(unsigned int cpu); +unsigned int cpufreq_quick_get(unsigned int cpu); +unsigned int cpufreq_quick_get_max(unsigned int cpu); +void disable_cpufreq(void); -/** - * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch - * safe) - * @old: old value - * @div: divisor - * @mult: multiplier - * - * - * new = old * mult / div - */ -static inline unsigned long cpufreq_scale(unsigned long old, u_int div, - u_int mult) +u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); +int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); +int cpufreq_update_policy(unsigned int cpu); +bool have_governor_per_policy(void); +struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); +#else +static inline unsigned int cpufreq_get(unsigned int cpu) { -#if BITS_PER_LONG == 32 - - u64 result = ((u64) old) * ((u64) mult); - do_div(result, div); - return (unsigned long) result; - -#elif BITS_PER_LONG == 64 - - unsigned long result = old * ((u64) mult); - result /= div; - return result; - + return 0; +} +static inline unsigned int cpufreq_quick_get(unsigned int cpu) +{ + return 0; +} +static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) +{ + return 0; +} +static inline void disable_cpufreq(void) { } #endif -}; /********************************************************************* - * CPUFREQ GOVERNORS * + * CPUFREQ DRIVER INTERFACE * *********************************************************************/ -#define CPUFREQ_GOV_START 1 -#define CPUFREQ_GOV_STOP 2 -#define CPUFREQ_GOV_LIMITS 3 -#define CPUFREQ_GOV_POLICY_INIT 4 -#define CPUFREQ_GOV_POLICY_EXIT 5 +#define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */ +#define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */ -struct cpufreq_governor { - char name[CPUFREQ_NAME_LEN]; - int initialized; - int (*governor) (struct cpufreq_policy *policy, - unsigned int event); - ssize_t (*show_setspeed) (struct cpufreq_policy *policy, - char *buf); - int (*store_setspeed) (struct cpufreq_policy *policy, - unsigned int freq); - unsigned int max_transition_latency; /* HW must be able to switch to - next freq faster than this value in nano secs or we - will fallback to performance governor */ - struct list_head governor_list; - struct module *owner; +struct freq_attr { + struct attribute attr; + ssize_t (*show)(struct cpufreq_policy *, char *); + ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count); }; -/* - * Pass a target to the cpufreq driver. - */ -extern int cpufreq_driver_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); -extern int __cpufreq_driver_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); -int cpufreq_register_governor(struct cpufreq_governor *governor); -void cpufreq_unregister_governor(struct cpufreq_governor *governor); +#define cpufreq_freq_attr_ro(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) -/********************************************************************* - * CPUFREQ DRIVER INTERFACE * - *********************************************************************/ +#define cpufreq_freq_attr_ro_perm(_name, _perm) \ +static struct freq_attr _name = \ +__ATTR(_name, _perm, show_##_name, NULL) -#define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */ -#define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */ +#define cpufreq_freq_attr_rw(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) + +struct global_attr { + struct attribute attr; + ssize_t (*show)(struct kobject *kobj, + struct attribute *attr, char *buf); + ssize_t (*store)(struct kobject *a, struct attribute *b, + const char *c, size_t count); +}; + +#define define_one_global_ro(_name) \ +static struct global_attr _name = \ +__ATTR(_name, 0444, show_##_name, NULL) + +#define define_one_global_rw(_name) \ +static struct global_attr _name = \ +__ATTR(_name, 0644, show_##_name, store_##_name) -struct freq_attr; struct cpufreq_driver { struct module *owner; @@ -258,7 +212,6 @@ struct cpufreq_driver { }; /* flags */ - #define CPUFREQ_STICKY 0x01 /* the driver isn't removed even if * all ->init() calls failed */ #define CPUFREQ_CONST_LOOPS 0x02 /* loops_per_jiffy or other kernel @@ -270,8 +223,7 @@ struct cpufreq_driver { int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -void cpufreq_notify_transition(struct cpufreq_policy *policy, - struct cpufreq_freqs *freqs, unsigned int state); +const char *cpufreq_get_current_driver(void); static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max) @@ -289,86 +241,117 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, return; } -struct freq_attr { - struct attribute attr; - ssize_t (*show)(struct cpufreq_policy *, char *); - ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count); -}; - -#define cpufreq_freq_attr_ro(_name) \ -static struct freq_attr _name = \ -__ATTR(_name, 0444, show_##_name, NULL) - -#define cpufreq_freq_attr_ro_perm(_name, _perm) \ -static struct freq_attr _name = \ -__ATTR(_name, _perm, show_##_name, NULL) - -#define cpufreq_freq_attr_rw(_name) \ -static struct freq_attr _name = \ -__ATTR(_name, 0644, show_##_name, store_##_name) +/********************************************************************* + * CPUFREQ NOTIFIER INTERFACE * + *********************************************************************/ -struct global_attr { - struct attribute attr; - ssize_t (*show)(struct kobject *kobj, - struct attribute *attr, char *buf); - ssize_t (*store)(struct kobject *a, struct attribute *b, - const char *c, size_t count); -}; +#define CPUFREQ_TRANSITION_NOTIFIER (0) +#define CPUFREQ_POLICY_NOTIFIER (1) -#define define_one_global_ro(_name) \ -static struct global_attr _name = \ -__ATTR(_name, 0444, show_##_name, NULL) +/* Transition notifiers */ +#define CPUFREQ_PRECHANGE (0) +#define CPUFREQ_POSTCHANGE (1) +#define CPUFREQ_RESUMECHANGE (8) +#define CPUFREQ_SUSPENDCHANGE (9) -#define define_one_global_rw(_name) \ -static struct global_attr _name = \ -__ATTR(_name, 0644, show_##_name, store_##_name) +/* Policy Notifiers */ +#define CPUFREQ_ADJUST (0) +#define CPUFREQ_INCOMPATIBLE (1) +#define CPUFREQ_NOTIFY (2) +#define CPUFREQ_START (3) +#define CPUFREQ_UPDATE_POLICY_CPU (4) -struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); -void cpufreq_cpu_put(struct cpufreq_policy *data); -const char *cpufreq_get_current_driver(void); +#ifdef CONFIG_CPU_FREQ +int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); +int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list); -/********************************************************************* - * CPUFREQ 2.6. INTERFACE * - *********************************************************************/ -u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); -int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); -int cpufreq_update_policy(unsigned int cpu); -bool have_governor_per_policy(void); -struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); +void cpufreq_notify_transition(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, unsigned int state); -#ifdef CONFIG_CPU_FREQ -/* - * query the current CPU frequency (in kHz). If zero, cpufreq couldn't detect it - */ -unsigned int cpufreq_get(unsigned int cpu); -#else -static inline unsigned int cpufreq_get(unsigned int cpu) +#else /* CONFIG_CPU_FREQ */ +static inline int cpufreq_register_notifier(struct notifier_block *nb, + unsigned int list) { return 0; } -#endif - -/* - * query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it - */ -#ifdef CONFIG_CPU_FREQ -unsigned int cpufreq_quick_get(unsigned int cpu); -unsigned int cpufreq_quick_get_max(unsigned int cpu); -#else -static inline unsigned int cpufreq_quick_get(unsigned int cpu) +static inline int cpufreq_unregister_notifier(struct notifier_block *nb, + unsigned int list) { return 0; } -static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) +#endif /* !CONFIG_CPU_FREQ */ + +/** + * cpufreq_scale - "old * mult / div" calculation for large values (32-bit-arch + * safe) + * @old: old value + * @div: divisor + * @mult: multiplier + * + * + * new = old * mult / div + */ +static inline unsigned long cpufreq_scale(unsigned long old, u_int div, + u_int mult) { - return 0; -} +#if BITS_PER_LONG == 32 + u64 result = ((u64) old) * ((u64) mult); + do_div(result, div); + return (unsigned long) result; + +#elif BITS_PER_LONG == 64 + unsigned long result = old * ((u64) mult); + result /= div; + return result; #endif +} /********************************************************************* - * CPUFREQ DEFAULT GOVERNOR * + * CPUFREQ GOVERNORS * *********************************************************************/ +/* + * If (cpufreq_driver->target) exists, the ->governor decides what frequency + * within the limits is used. If (cpufreq_driver->setpolicy> exists, these + * two generic policies are available: + */ +#define CPUFREQ_POLICY_POWERSAVE (1) +#define CPUFREQ_POLICY_PERFORMANCE (2) + +/* Governor Events */ +#define CPUFREQ_GOV_START 1 +#define CPUFREQ_GOV_STOP 2 +#define CPUFREQ_GOV_LIMITS 3 +#define CPUFREQ_GOV_POLICY_INIT 4 +#define CPUFREQ_GOV_POLICY_EXIT 5 + +struct cpufreq_governor { + char name[CPUFREQ_NAME_LEN]; + int initialized; + int (*governor) (struct cpufreq_policy *policy, + unsigned int event); + ssize_t (*show_setspeed) (struct cpufreq_policy *policy, + char *buf); + int (*store_setspeed) (struct cpufreq_policy *policy, + unsigned int freq); + unsigned int max_transition_latency; /* HW must be able to switch to + next freq faster than this value in nano secs or we + will fallback to performance governor */ + struct list_head governor_list; + struct module *owner; +}; + +/* Pass a target to the cpufreq driver */ +int cpufreq_driver_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation); +int __cpufreq_driver_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation); +int cpufreq_register_governor(struct cpufreq_governor *governor); +void cpufreq_unregister_governor(struct cpufreq_governor *governor); + +/* CPUFREQ DEFAULT GOVERNOR */ /* * Performance governor is fallback governor if any other gov failed to auto * load due latency restrictions @@ -417,18 +400,16 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int relation, unsigned int *index); -/* the following 3 funtions are for cpufreq core use only */ +void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy); +ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); + +/* the following funtion is for cpufreq core use only */ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu); /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; - void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table, unsigned int cpu); -void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy); - void cpufreq_frequency_table_put_attr(unsigned int cpu); -ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); - #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3-71-gd317 From 3a3e9e06d0c11b8efa95933a88c9e67209fa4330 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:05 +0530 Subject: cpufreq: Give consistent names to cpufreq_policy objects They are called policy, cur_policy, new_policy, data, etc. Just call them policy wherever possible. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 200 ++++++++++++++++++------------------- drivers/cpufreq/cpufreq_governor.h | 2 +- drivers/cpufreq/cpufreq_ondemand.c | 10 +- drivers/cpufreq/cpufreq_stats.c | 12 +-- include/linux/cpufreq.h | 2 +- 5 files changed, 113 insertions(+), 113 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 845837174878..1793fe82595d 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -179,7 +179,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time); static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs) { - struct cpufreq_policy *data; + struct cpufreq_policy *policy; unsigned long flags; if (cpu >= nr_cpu_ids) @@ -195,16 +195,16 @@ static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs) goto err_out_unlock; /* get the CPU */ - data = per_cpu(cpufreq_cpu_data, cpu); + policy = per_cpu(cpufreq_cpu_data, cpu); - if (!data) + if (!policy) goto err_out_put_module; - if (!sysfs && !kobject_get(&data->kobj)) + if (!sysfs && !kobject_get(&policy->kobj)) goto err_out_put_module; read_unlock_irqrestore(&cpufreq_driver_lock, flags); - return data; + return policy; err_out_put_module: module_put(cpufreq_driver->owner); @@ -228,25 +228,25 @@ static struct cpufreq_policy *cpufreq_cpu_get_sysfs(unsigned int cpu) return __cpufreq_cpu_get(cpu, true); } -static void __cpufreq_cpu_put(struct cpufreq_policy *data, bool sysfs) +static void __cpufreq_cpu_put(struct cpufreq_policy *policy, bool sysfs) { if (!sysfs) - kobject_put(&data->kobj); + kobject_put(&policy->kobj); module_put(cpufreq_driver->owner); } -void cpufreq_cpu_put(struct cpufreq_policy *data) +void cpufreq_cpu_put(struct cpufreq_policy *policy) { if (cpufreq_disabled()) return; - __cpufreq_cpu_put(data, false); + __cpufreq_cpu_put(policy, false); } EXPORT_SYMBOL_GPL(cpufreq_cpu_put); -static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *data) +static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *policy) { - __cpufreq_cpu_put(data, true); + __cpufreq_cpu_put(policy, true); } /********************************************************************* @@ -453,8 +453,8 @@ show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); show_one(scaling_cur_freq, cur); -static int __cpufreq_set_policy(struct cpufreq_policy *data, - struct cpufreq_policy *policy); +static int __cpufreq_set_policy(struct cpufreq_policy *policy, + struct cpufreq_policy *new_policy); /** * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access @@ -1136,7 +1136,7 @@ static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu) CPUFREQ_UPDATE_POLICY_CPU, policy); } -static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *data, +static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy, unsigned int old_cpu, bool frozen) { struct device *cpu_dev; @@ -1144,27 +1144,27 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *data, int ret; /* first sibling now owns the new sysfs dir */ - cpu_dev = get_cpu_device(cpumask_first(data->cpus)); + cpu_dev = get_cpu_device(cpumask_first(policy->cpus)); /* Don't touch sysfs files during light-weight tear-down */ if (frozen) return cpu_dev->id; sysfs_remove_link(&cpu_dev->kobj, "cpufreq"); - ret = kobject_move(&data->kobj, &cpu_dev->kobj); + ret = kobject_move(&policy->kobj, &cpu_dev->kobj); if (ret) { pr_err("%s: Failed to move kobj: %d", __func__, ret); WARN_ON(lock_policy_rwsem_write(old_cpu)); - cpumask_set_cpu(old_cpu, data->cpus); + cpumask_set_cpu(old_cpu, policy->cpus); write_lock_irqsave(&cpufreq_driver_lock, flags); - per_cpu(cpufreq_cpu_data, old_cpu) = data; + per_cpu(cpufreq_cpu_data, old_cpu) = policy; write_unlock_irqrestore(&cpufreq_driver_lock, flags); unlock_policy_rwsem_write(old_cpu); - ret = sysfs_create_link(&cpu_dev->kobj, &data->kobj, + ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq"); return -EINVAL; @@ -1186,7 +1186,7 @@ static int __cpufreq_remove_dev(struct device *dev, unsigned int cpu = dev->id, cpus; int new_cpu; unsigned long flags; - struct cpufreq_policy *data; + struct cpufreq_policy *policy; struct kobject *kobj; struct completion *cmp; @@ -1194,44 +1194,44 @@ static int __cpufreq_remove_dev(struct device *dev, write_lock_irqsave(&cpufreq_driver_lock, flags); - data = per_cpu(cpufreq_cpu_data, cpu); + policy = per_cpu(cpufreq_cpu_data, cpu); per_cpu(cpufreq_cpu_data, cpu) = NULL; /* Save the policy somewhere when doing a light-weight tear-down */ if (frozen) - per_cpu(cpufreq_cpu_data_fallback, cpu) = data; + per_cpu(cpufreq_cpu_data_fallback, cpu) = policy; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - if (!data) { + if (!policy) { pr_debug("%s: No cpu_data found\n", __func__); return -EINVAL; } if (cpufreq_driver->target) - __cpufreq_governor(data, CPUFREQ_GOV_STOP); + __cpufreq_governor(policy, CPUFREQ_GOV_STOP); #ifdef CONFIG_HOTPLUG_CPU if (!cpufreq_driver->setpolicy) strncpy(per_cpu(cpufreq_cpu_governor, cpu), - data->governor->name, CPUFREQ_NAME_LEN); + policy->governor->name, CPUFREQ_NAME_LEN); #endif WARN_ON(lock_policy_rwsem_write(cpu)); - cpus = cpumask_weight(data->cpus); + cpus = cpumask_weight(policy->cpus); if (cpus > 1) - cpumask_clear_cpu(cpu, data->cpus); + cpumask_clear_cpu(cpu, policy->cpus); unlock_policy_rwsem_write(cpu); - if (cpu != data->cpu && !frozen) { + if (cpu != policy->cpu && !frozen) { sysfs_remove_link(&dev->kobj, "cpufreq"); } else if (cpus > 1) { - new_cpu = cpufreq_nominate_new_policy_cpu(data, cpu, frozen); + new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen); if (new_cpu >= 0) { WARN_ON(lock_policy_rwsem_write(cpu)); - update_policy_cpu(data, new_cpu); + update_policy_cpu(policy, new_cpu); unlock_policy_rwsem_write(cpu); if (!frozen) { @@ -1244,12 +1244,12 @@ static int __cpufreq_remove_dev(struct device *dev, /* If cpu is last user of policy, free policy */ if (cpus == 1) { if (cpufreq_driver->target) - __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT); + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); if (!frozen) { lock_policy_rwsem_read(cpu); - kobj = &data->kobj; - cmp = &data->kobj_unregister; + kobj = &policy->kobj; + cmp = &policy->kobj_unregister; unlock_policy_rwsem_read(cpu); kobject_put(kobj); @@ -1269,14 +1269,14 @@ static int __cpufreq_remove_dev(struct device *dev, * subsequent light-weight ->init() to succeed. */ if (cpufreq_driver->exit) - cpufreq_driver->exit(data); + cpufreq_driver->exit(policy); if (!frozen) - cpufreq_policy_free(data); + cpufreq_policy_free(policy); } else { if (cpufreq_driver->target) { - __cpufreq_governor(data, CPUFREQ_GOV_START); - __cpufreq_governor(data, CPUFREQ_GOV_LIMITS); + __cpufreq_governor(policy, CPUFREQ_GOV_START); + __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); } } @@ -1450,23 +1450,23 @@ static int cpufreq_bp_suspend(void) int ret = 0; int cpu = smp_processor_id(); - struct cpufreq_policy *cpu_policy; + struct cpufreq_policy *policy; pr_debug("suspending cpu %u\n", cpu); /* If there's no policy for the boot CPU, we have nothing to do. */ - cpu_policy = cpufreq_cpu_get(cpu); - if (!cpu_policy) + policy = cpufreq_cpu_get(cpu); + if (!policy) return 0; if (cpufreq_driver->suspend) { - ret = cpufreq_driver->suspend(cpu_policy); + ret = cpufreq_driver->suspend(policy); if (ret) printk(KERN_ERR "cpufreq: suspend failed in ->suspend " - "step on CPU %u\n", cpu_policy->cpu); + "step on CPU %u\n", policy->cpu); } - cpufreq_cpu_put(cpu_policy); + cpufreq_cpu_put(policy); return ret; } @@ -1488,28 +1488,28 @@ static void cpufreq_bp_resume(void) int ret = 0; int cpu = smp_processor_id(); - struct cpufreq_policy *cpu_policy; + struct cpufreq_policy *policy; pr_debug("resuming cpu %u\n", cpu); /* If there's no policy for the boot CPU, we have nothing to do. */ - cpu_policy = cpufreq_cpu_get(cpu); - if (!cpu_policy) + policy = cpufreq_cpu_get(cpu); + if (!policy) return; if (cpufreq_driver->resume) { - ret = cpufreq_driver->resume(cpu_policy); + ret = cpufreq_driver->resume(policy); if (ret) { printk(KERN_ERR "cpufreq: resume failed in ->resume " - "step on CPU %u\n", cpu_policy->cpu); + "step on CPU %u\n", policy->cpu); goto fail; } } - schedule_work(&cpu_policy->update); + schedule_work(&policy->update); fail: - cpufreq_cpu_put(cpu_policy); + cpufreq_cpu_put(policy); } static struct syscore_ops cpufreq_syscore_ops = { @@ -1829,95 +1829,95 @@ EXPORT_SYMBOL(cpufreq_get_policy); * data : current policy. * policy : policy to be set. */ -static int __cpufreq_set_policy(struct cpufreq_policy *data, - struct cpufreq_policy *policy) +static int __cpufreq_set_policy(struct cpufreq_policy *policy, + struct cpufreq_policy *new_policy) { int ret = 0, failed = 1; - pr_debug("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu, - policy->min, policy->max); + pr_debug("setting new policy for CPU %u: %u - %u kHz\n", new_policy->cpu, + new_policy->min, new_policy->max); - memcpy(&policy->cpuinfo, &data->cpuinfo, + memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(struct cpufreq_cpuinfo)); - if (policy->min > data->max || policy->max < data->min) { + if (new_policy->min > policy->max || new_policy->max < policy->min) { ret = -EINVAL; goto error_out; } /* verify the cpu speed can be set within this limit */ - ret = cpufreq_driver->verify(policy); + ret = cpufreq_driver->verify(new_policy); if (ret) goto error_out; /* adjust if necessary - all reasons */ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_ADJUST, policy); + CPUFREQ_ADJUST, new_policy); /* adjust if necessary - hardware incompatibility*/ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_INCOMPATIBLE, policy); + CPUFREQ_INCOMPATIBLE, new_policy); /* * verify the cpu speed can be set within this limit, which might be * different to the first one */ - ret = cpufreq_driver->verify(policy); + ret = cpufreq_driver->verify(new_policy); if (ret) goto error_out; /* notification of the new policy */ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_NOTIFY, policy); + CPUFREQ_NOTIFY, new_policy); - data->min = policy->min; - data->max = policy->max; + policy->min = new_policy->min; + policy->max = new_policy->max; pr_debug("new min and max freqs are %u - %u kHz\n", - data->min, data->max); + policy->min, policy->max); if (cpufreq_driver->setpolicy) { - data->policy = policy->policy; + policy->policy = new_policy->policy; pr_debug("setting range\n"); - ret = cpufreq_driver->setpolicy(policy); + ret = cpufreq_driver->setpolicy(new_policy); } else { - if (policy->governor != data->governor) { + if (new_policy->governor != policy->governor) { /* save old, working values */ - struct cpufreq_governor *old_gov = data->governor; + struct cpufreq_governor *old_gov = policy->governor; pr_debug("governor switch\n"); /* end old governor */ - if (data->governor) { - __cpufreq_governor(data, CPUFREQ_GOV_STOP); - unlock_policy_rwsem_write(policy->cpu); - __cpufreq_governor(data, + if (policy->governor) { + __cpufreq_governor(policy, CPUFREQ_GOV_STOP); + unlock_policy_rwsem_write(new_policy->cpu); + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - lock_policy_rwsem_write(policy->cpu); + lock_policy_rwsem_write(new_policy->cpu); } /* start new governor */ - data->governor = policy->governor; - if (!__cpufreq_governor(data, CPUFREQ_GOV_POLICY_INIT)) { - if (!__cpufreq_governor(data, CPUFREQ_GOV_START)) { + policy->governor = new_policy->governor; + if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) { + if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) { failed = 0; } else { - unlock_policy_rwsem_write(policy->cpu); - __cpufreq_governor(data, + unlock_policy_rwsem_write(new_policy->cpu); + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - lock_policy_rwsem_write(policy->cpu); + lock_policy_rwsem_write(new_policy->cpu); } } if (failed) { /* new governor failed, so re-start old one */ pr_debug("starting governor %s failed\n", - data->governor->name); + policy->governor->name); if (old_gov) { - data->governor = old_gov; - __cpufreq_governor(data, + policy->governor = old_gov; + __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT); - __cpufreq_governor(data, + __cpufreq_governor(policy, CPUFREQ_GOV_START); } ret = -EINVAL; @@ -1926,7 +1926,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, /* might be a policy change, too, so fall through */ } pr_debug("governor: change or update limits\n"); - __cpufreq_governor(data, CPUFREQ_GOV_LIMITS); + __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS); } error_out: @@ -1942,11 +1942,11 @@ error_out: */ int cpufreq_update_policy(unsigned int cpu) { - struct cpufreq_policy *data = cpufreq_cpu_get(cpu); - struct cpufreq_policy policy; + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct cpufreq_policy new_policy; int ret; - if (!data) { + if (!policy) { ret = -ENODEV; goto no_policy; } @@ -1957,34 +1957,34 @@ int cpufreq_update_policy(unsigned int cpu) } pr_debug("updating policy for CPU %u\n", cpu); - memcpy(&policy, data, sizeof(struct cpufreq_policy)); - policy.min = data->user_policy.min; - policy.max = data->user_policy.max; - policy.policy = data->user_policy.policy; - policy.governor = data->user_policy.governor; + memcpy(&new_policy, policy, sizeof(struct cpufreq_policy)); + new_policy.min = policy->user_policy.min; + new_policy.max = policy->user_policy.max; + new_policy.policy = policy->user_policy.policy; + new_policy.governor = policy->user_policy.governor; /* * BIOS might change freq behind our back * -> ask driver for current freq and notify governors about a change */ if (cpufreq_driver->get) { - policy.cur = cpufreq_driver->get(cpu); - if (!data->cur) { + new_policy.cur = cpufreq_driver->get(cpu); + if (!policy->cur) { pr_debug("Driver did not initialize current freq"); - data->cur = policy.cur; + policy->cur = new_policy.cur; } else { - if (data->cur != policy.cur && cpufreq_driver->target) - cpufreq_out_of_sync(cpu, data->cur, - policy.cur); + if (policy->cur != new_policy.cur && cpufreq_driver->target) + cpufreq_out_of_sync(cpu, policy->cur, + new_policy.cur); } } - ret = __cpufreq_set_policy(data, &policy); + ret = __cpufreq_set_policy(policy, &new_policy); unlock_policy_rwsem_write(cpu); fail: - cpufreq_cpu_put(data); + cpufreq_cpu_put(policy); no_policy: return ret; } diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index cf0b7a4425b0..264e509a9149 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -221,7 +221,7 @@ struct od_ops { void (*powersave_bias_init_cpu)(int cpu); unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy, unsigned int freq_next, unsigned int relation); - void (*freq_increase)(struct cpufreq_policy *p, unsigned int freq); + void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq); }; struct cs_ops { diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 27c732eee431..47d4b69be7c6 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -132,18 +132,18 @@ static void ondemand_powersave_bias_init(void) } } -static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq) +static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq) { - struct dbs_data *dbs_data = p->governor_data; + struct dbs_data *dbs_data = policy->governor_data; struct od_dbs_tuners *od_tuners = dbs_data->tuners; if (od_tuners->powersave_bias) - freq = od_ops.powersave_bias_target(p, freq, + freq = od_ops.powersave_bias_target(policy, freq, CPUFREQ_RELATION_H); - else if (p->cur == p->max) + else if (policy->cur == policy->max) return; - __cpufreq_driver_target(p, freq, od_tuners->powersave_bias ? + __cpufreq_driver_target(policy, freq, od_tuners->powersave_bias ? CPUFREQ_RELATION_L : CPUFREQ_RELATION_H); } diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index a7143b0597af..a17b14ee37d8 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -193,7 +193,7 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy, { unsigned int i, j, count = 0, ret = 0; struct cpufreq_stats *stat; - struct cpufreq_policy *data; + struct cpufreq_policy *current_policy; unsigned int alloc_size; unsigned int cpu = policy->cpu; if (per_cpu(cpufreq_stats_table, cpu)) @@ -202,13 +202,13 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy, if ((stat) == NULL) return -ENOMEM; - data = cpufreq_cpu_get(cpu); - if (data == NULL) { + current_policy = cpufreq_cpu_get(cpu); + if (current_policy == NULL) { ret = -EINVAL; goto error_get_fail; } - ret = sysfs_create_group(&data->kobj, &stats_attr_group); + ret = sysfs_create_group(¤t_policy->kobj, &stats_attr_group); if (ret) goto error_out; @@ -251,10 +251,10 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy, stat->last_time = get_jiffies_64(); stat->last_index = freq_table_get_index(stat, policy->cur); spin_unlock(&cpufreq_stats_lock); - cpufreq_cpu_put(data); + cpufreq_cpu_put(current_policy); return 0; error_out: - cpufreq_cpu_put(data); + cpufreq_cpu_put(current_policy); error_get_fail: kfree(stat); per_cpu(cpufreq_stats_table, cpu) = NULL; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 0d3b0266bc98..29208923c9d3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -94,7 +94,7 @@ struct cpufreq_policy { #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); -void cpufreq_cpu_put(struct cpufreq_policy *data); +void cpufreq_cpu_put(struct cpufreq_policy *policy); static inline bool policy_is_shared(struct cpufreq_policy *policy) { -- cgit v1.2.3-71-gd317 From 8742f229b635bf1c1c84a3dfe5e47c814c20b5c8 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 8 Aug 2013 18:55:32 +0200 Subject: userns: limit the maximum depth of user_namespace->parent chain Ensure that user_namespace->parent chain can't grow too much. Currently we use the hardroded 32 as limit. Reported-by: Andy Lutomirski Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- include/linux/user_namespace.h | 1 + kernel/user_namespace.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index b6b215f13b45..14105c26a836 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -23,6 +23,7 @@ struct user_namespace { struct uid_gid_map projid_map; atomic_t count; struct user_namespace *parent; + int level; kuid_t owner; kgid_t group; unsigned int proc_inum; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 6e50a44610ee..9064b919a406 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -62,6 +62,9 @@ int create_user_ns(struct cred *new) kgid_t group = new->egid; int ret; + if (parent_ns->level > 32) + return -EUSERS; + /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, @@ -92,6 +95,7 @@ int create_user_ns(struct cred *new) atomic_set(&ns->count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; + ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; -- cgit v1.2.3-71-gd317 From 8af01f56a03e9cbd91a55d688fce1315021efba8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:22 -0400 Subject: cgroup: s/cgroup_subsys_state/cgroup_css/ s/task_subsys_state/task_css/ The names of the two struct cgroup_subsys_state accessors - cgroup_subsys_state() and task_subsys_state() - are somewhat awkward. The former clashes with the type name and the latter doesn't even indicate it's somehow related to cgroup. We're about to revamp large portion of cgroup API, so, let's rename them so that they're less awkward. Most per-controller usages of the accessors are localized in accessor wrappers and given the amount of scheduled changes, this isn't gonna add any noticeable headache. Rename cgroup_subsys_state() to cgroup_css() and task_subsys_state() to task_css(). This patch is pure rename. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- block/blk-cgroup.h | 5 ++--- fs/bio.c | 2 +- include/linux/cgroup.h | 31 +++++++++++++++++++------------ include/net/cls_cgroup.h | 4 ++-- include/net/netprio_cgroup.h | 4 ++-- kernel/cgroup.c | 2 +- kernel/cgroup_freezer.c | 4 ++-- kernel/cpuset.c | 6 +++--- kernel/events/core.c | 6 +++--- kernel/sched/core.c | 4 ++-- kernel/sched/cpuacct.c | 4 ++-- kernel/sched/sched.h | 6 +++--- mm/hugetlb_cgroup.c | 6 ++---- mm/memcontrol.c | 5 ++--- mm/vmpressure.c | 2 +- net/core/netprio_cgroup.c | 2 +- net/sched/cls_cgroup.c | 4 ++-- security/device_cgroup.c | 4 ++-- 18 files changed, 52 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 8056c03a3382..628e50f6f8a8 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -181,14 +181,13 @@ void blkg_conf_finish(struct blkg_conf_ctx *ctx); static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { - return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id), + return container_of(cgroup_css(cgroup, blkio_subsys_id), struct blkcg, css); } static inline struct blkcg *task_blkcg(struct task_struct *tsk) { - return container_of(task_subsys_state(tsk, blkio_subsys_id), - struct blkcg, css); + return container_of(task_css(tsk, blkio_subsys_id), struct blkcg, css); } static inline struct blkcg *bio_blkcg(struct bio *bio) diff --git a/fs/bio.c b/fs/bio.c index 94bbc04dba77..8e0348f6e5bd 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1946,7 +1946,7 @@ int bio_associate_current(struct bio *bio) /* associate blkcg if exists */ rcu_read_lock(); - css = task_subsys_state(current, blkio_subsys_id); + css = task_css(current, blkio_subsys_id); if (css && css_tryget(css)) bio->bi_css = css; rcu_read_unlock(); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 44dd422d7e9b..552c5feef733 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -647,8 +647,15 @@ struct cgroup_subsys { #undef IS_SUBSYS_ENABLED #undef SUBSYS -static inline struct cgroup_subsys_state *cgroup_subsys_state( - struct cgroup *cgrp, int subsys_id) +/** + * cgroup_css - obtain a cgroup's css for the specified subsystem + * @cgrp: the cgroup of interest + * @subsys_id: the subsystem of interest + * + * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. + */ +static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, + int subsys_id) { return cgrp->subsys[subsys_id]; } @@ -678,7 +685,7 @@ extern struct mutex cgroup_mutex; #endif /** - * task_subsys_state_check - obtain css for (task, subsys) w/ extra access conds + * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() @@ -686,7 +693,7 @@ extern struct mutex cgroup_mutex; * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ -#define task_subsys_state_check(task, subsys_id, __c) \ +#define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** @@ -701,22 +708,22 @@ static inline struct css_set *task_css_set(struct task_struct *task) } /** - * task_subsys_state - obtain css for (task, subsys) + * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * - * See task_subsys_state_check(). + * See task_css_check(). */ -static inline struct cgroup_subsys_state * -task_subsys_state(struct task_struct *task, int subsys_id) +static inline struct cgroup_subsys_state *task_css(struct task_struct *task, + int subsys_id) { - return task_subsys_state_check(task, subsys_id, false); + return task_css_check(task, subsys_id, false); } -static inline struct cgroup* task_cgroup(struct task_struct *task, - int subsys_id) +static inline struct cgroup *task_cgroup(struct task_struct *task, + int subsys_id) { - return task_subsys_state(task, subsys_id)->cgroup; + return task_css(task, subsys_id)->cgroup; } /** diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 0fee0617fb7d..52adaa75dac9 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -35,7 +35,7 @@ static inline u32 task_cls_classid(struct task_struct *p) return 0; rcu_read_lock(); - classid = container_of(task_subsys_state(p, net_cls_subsys_id), + classid = container_of(task_css(p, net_cls_subsys_id), struct cgroup_cls_state, css)->classid; rcu_read_unlock(); @@ -51,7 +51,7 @@ static inline u32 task_cls_classid(struct task_struct *p) return 0; rcu_read_lock(); - css = task_subsys_state(p, net_cls_subsys_id); + css = task_css(p, net_cls_subsys_id); if (css) classid = container_of(css, struct cgroup_cls_state, css)->classid; diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index 50ab8c26ab59..8110fa7ae60a 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -39,7 +39,7 @@ static inline u32 task_netprioidx(struct task_struct *p) u32 idx; rcu_read_lock(); - css = task_subsys_state(p, net_prio_subsys_id); + css = task_css(p, net_prio_subsys_id); idx = css->cgroup->id; rcu_read_unlock(); return idx; @@ -53,7 +53,7 @@ static inline u32 task_netprioidx(struct task_struct *p) u32 idx = 0; rcu_read_lock(); - css = task_subsys_state(p, net_prio_subsys_id); + css = task_css(p, net_prio_subsys_id); if (css) idx = css->cgroup->id; rcu_read_unlock(); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ae4c46834633..0b3caa3220cb 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -81,7 +81,7 @@ */ #ifdef CONFIG_PROVE_RCU DEFINE_MUTEX(cgroup_mutex); -EXPORT_SYMBOL_GPL(cgroup_mutex); /* only for task_subsys_state_check() */ +EXPORT_SYMBOL_GPL(cgroup_mutex); /* only for lockdep */ #else static DEFINE_MUTEX(cgroup_mutex); #endif diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 75dda1ea5026..9d3f61566fec 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -47,13 +47,13 @@ struct freezer { static inline struct freezer *cgroup_freezer(struct cgroup *cgroup) { - return container_of(cgroup_subsys_state(cgroup, freezer_subsys_id), + return container_of(cgroup_css(cgroup, freezer_subsys_id), struct freezer, css); } static inline struct freezer *task_freezer(struct task_struct *task) { - return container_of(task_subsys_state(task, freezer_subsys_id), + return container_of(task_css(task, freezer_subsys_id), struct freezer, css); } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 1b9c31549797..be4512ba2c0c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -117,14 +117,14 @@ struct cpuset { /* Retrieve the cpuset for a cgroup */ static inline struct cpuset *cgroup_cs(struct cgroup *cgrp) { - return container_of(cgroup_subsys_state(cgrp, cpuset_subsys_id), + return container_of(cgroup_css(cgrp, cpuset_subsys_id), struct cpuset, css); } /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { - return container_of(task_subsys_state(task, cpuset_subsys_id), + return container_of(task_css(task, cpuset_subsys_id), struct cpuset, css); } @@ -2724,7 +2724,7 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v) goto out_free; rcu_read_lock(); - css = task_subsys_state(tsk, cpuset_subsys_id); + css = task_css(tsk, cpuset_subsys_id); retval = cgroup_path(css->cgroup, buf, PAGE_SIZE); rcu_read_unlock(); if (retval < 0) diff --git a/kernel/events/core.c b/kernel/events/core.c index 1833bc5a84a7..414c61f4d776 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -340,8 +340,8 @@ struct perf_cgroup { static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task) { - return container_of(task_subsys_state(task, perf_subsys_id), - struct perf_cgroup, css); + return container_of(task_css(task, perf_subsys_id), + struct perf_cgroup, css); } static inline bool @@ -7798,7 +7798,7 @@ static struct cgroup_subsys_state *perf_cgroup_css_alloc(struct cgroup *cont) static void perf_cgroup_css_free(struct cgroup *cont) { struct perf_cgroup *jc; - jc = container_of(cgroup_subsys_state(cont, perf_subsys_id), + jc = container_of(cgroup_css(cont, perf_subsys_id), struct perf_cgroup, css); free_percpu(jc->info); kfree(jc); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9b1f2e533b95..323d907eac1a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6761,7 +6761,7 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); - tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id, + tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id, lockdep_is_held(&tsk->sighand->siglock)), struct task_group, css); tg = autogroup_task_group(tsk, tg); @@ -7086,7 +7086,7 @@ int sched_rt_handler(struct ctl_table *table, int write, /* return corresponding task_group object of a cgroup */ static inline struct task_group *cgroup_tg(struct cgroup *cgrp) { - return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id), + return container_of(cgroup_css(cgrp, cpu_cgroup_subsys_id), struct task_group, css); } diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index dbb7e2cd95eb..4a210faaab77 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -36,14 +36,14 @@ struct cpuacct { /* return cpu accounting group corresponding to this container */ static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) { - return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), + return container_of(cgroup_css(cgrp, cpuacct_subsys_id), struct cpuacct, css); } /* return cpu accounting group to which this task belongs */ static inline struct cpuacct *task_ca(struct task_struct *tsk) { - return container_of(task_subsys_state(tsk, cpuacct_subsys_id), + return container_of(task_css(tsk, cpuacct_subsys_id), struct cpuacct, css); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ef0a7b2439dd..471a56db05ea 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -665,9 +665,9 @@ extern int group_balance_cpu(struct sched_group *sg); /* * Return the group to which this tasks belongs. * - * We cannot use task_subsys_state() and friends because the cgroup - * subsystem changes that value before the cgroup_subsys::attach() method - * is called, therefore we cannot pin it and might observe the wrong value. + * We cannot use task_css() and friends because the cgroup subsystem + * changes that value before the cgroup_subsys::attach() method is called, + * therefore we cannot pin it and might observe the wrong value. * * The same is true for autogroup's p->signal->autogroup->tg, the autogroup * core changes this before calling sched_move_task(). diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 9cea7de22ffb..50f213fc52c7 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -42,15 +42,13 @@ struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) static inline struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup) { - return hugetlb_cgroup_from_css(cgroup_subsys_state(cgroup, - hugetlb_subsys_id)); + return hugetlb_cgroup_from_css(cgroup_css(cgroup, hugetlb_subsys_id)); } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) { - return hugetlb_cgroup_from_css(task_subsys_state(task, - hugetlb_subsys_id)); + return hugetlb_cgroup_from_css(task_css(task, hugetlb_subsys_id)); } static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d12ca6f3c293..b47bd3ad3c2b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1037,8 +1037,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { - return mem_cgroup_from_css( - cgroup_subsys_state(cont, mem_cgroup_subsys_id)); + return mem_cgroup_from_css(cgroup_css(cont, mem_cgroup_subsys_id)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) @@ -1051,7 +1050,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) if (unlikely(!p)) return NULL; - return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id)); + return mem_cgroup_from_css(task_css(p, mem_cgroup_subsys_id)); } struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 736a6011c2c8..7f1654d3cec7 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -76,7 +76,7 @@ static struct vmpressure *work_to_vmpressure(struct work_struct *work) static struct vmpressure *cg_to_vmpressure(struct cgroup *cg) { - return css_to_vmpressure(cgroup_subsys_state(cg, mem_cgroup_subsys_id)); + return css_to_vmpressure(cgroup_css(cg, mem_cgroup_subsys_id)); } static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index e533259dce3c..ccf852311987 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -31,7 +31,7 @@ static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp) { - return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id), + return container_of(cgroup_css(cgrp, net_prio_subsys_id), struct cgroup_netprio_state, css); } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 3a294eb98d61..5ee72a001df0 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -25,13 +25,13 @@ static inline struct cgroup_cls_state *cgrp_cls_state(struct cgroup *cgrp) { - return container_of(cgroup_subsys_state(cgrp, net_cls_subsys_id), + return container_of(cgroup_css(cgrp, net_cls_subsys_id), struct cgroup_cls_state, css); } static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p) { - return container_of(task_subsys_state(p, net_cls_subsys_id), + return container_of(task_css(p, net_cls_subsys_id), struct cgroup_cls_state, css); } diff --git a/security/device_cgroup.c b/security/device_cgroup.c index e8aad69f0d69..87a0a037fbd6 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -58,12 +58,12 @@ static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s) static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup) { - return css_to_devcgroup(cgroup_subsys_state(cgroup, devices_subsys_id)); + return css_to_devcgroup(cgroup_css(cgroup, devices_subsys_id)); } static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) { - return css_to_devcgroup(task_subsys_state(task, devices_subsys_id)); + return css_to_devcgroup(task_css(task, devices_subsys_id)); } struct cgroup_subsys devices_subsys; -- cgit v1.2.3-71-gd317 From 72c97e54e0f043d33b246d7460ae0a36c4b8c643 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:22 -0400 Subject: cgroup: add subsystem pointer to cgroup_subsys_state Currently, given a cgroup_subsys_state, there's no way to find out which subsystem the css is for, which we'll need to convert the cgroup controller API to primarily use @css instead of @cgroup. This patch adds cgroup_subsys_state->ss which points to the subsystem the @css belongs to. While at it, remove the comment about accessing @css->cgroup to determine the hierarchy. cgroup core will provide API to traverse hierarchy of css'es and we don't want subsystems to directly walk cgroup hierarchies anymore. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 9 ++++----- kernel/cgroup.c | 1 + 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 552c5feef733..821678aae4db 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -66,13 +66,12 @@ enum cgroup_subsys_id { /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { - /* - * The cgroup that this subsystem is attached to. Useful - * for subsystems that want to know about the cgroup - * hierarchy structure - */ + /* the cgroup that this css is attached to */ struct cgroup *cgroup; + /* the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0b3caa3220cb..4234428f1014 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4186,6 +4186,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, struct cgroup *cgrp) { css->cgroup = cgrp; + css->ss = ss; css->flags = 0; css->id = NULL; if (cgrp == cgroup_dummy_top) -- cgit v1.2.3-71-gd317 From 6387698699afd72d6304566fb6ccf84bffe07c56 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: add css_parent() Currently, controllers have to explicitly follow the cgroup hierarchy to find the parent of a given css. cgroup is moving towards using cgroup_subsys_state as the main controller interface construct, so let's provide a way to climb the hierarchy using just csses. This patch implements css_parent() which, given a css, returns its parent. The function is guarnateed to valid non-NULL parent css as long as the target css is not at the top of the hierarchy. freezer, cpuset, cpu, cpuacct, hugetlb, memory, net_cls and devices are converted to use css_parent() instead of accessing cgroup->parent directly. * __parent_ca() is dropped from cpuacct and its usage is replaced with parent_ca(). The only difference between the two was NULL test on cgroup->parent which is now embedded in css_parent() making the distinction moot. Note that eventually a css->parent field will be added to css and the NULL check in css_parent() will go away. This patch shouldn't cause any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- block/blk-cgroup.h | 4 +--- include/linux/cgroup.h | 15 +++++++++++++++ kernel/cgroup_freezer.c | 8 ++------ kernel/cpuset.c | 6 +----- kernel/sched/core.c | 9 +++------ kernel/sched/cpuacct.c | 11 ++--------- mm/hugetlb_cgroup.c | 6 +----- mm/memcontrol.c | 39 +++++++++++---------------------------- net/sched/cls_cgroup.c | 8 +++++--- security/device_cgroup.c | 18 +++++------------- 10 files changed, 46 insertions(+), 78 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 8e5863e900bf..b6802c46d68f 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -209,9 +209,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { - struct cgroup *pcg = blkcg->css.cgroup->parent; - - return pcg ? cgroup_to_blkcg(pcg) : NULL; + return css_to_blkcg(css_parent(&blkcg->css)); } /** diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 821678aae4db..18112a3bb12b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -646,6 +646,21 @@ struct cgroup_subsys { #undef IS_SUBSYS_ENABLED #undef SUBSYS +/** + * css_parent - find the parent css + * @css: the target cgroup_subsys_state + * + * Return the parent css of @css. This function is guaranteed to return + * non-NULL parent as long as @css isn't the root. + */ +static inline +struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) +{ + struct cgroup *parent_cgrp = css->cgroup->parent; + + return parent_cgrp ? parent_cgrp->subsys[css->ss->subsys_id] : NULL; +} + /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 1db686e47a22..657a73cd44c4 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -62,11 +62,7 @@ static inline struct freezer *task_freezer(struct task_struct *task) static struct freezer *parent_freezer(struct freezer *freezer) { - struct cgroup *pcg = freezer->css.cgroup->parent; - - if (pcg) - return cgroup_freezer(pcg); - return NULL; + return css_freezer(css_parent(&freezer->css)); } bool cgroup_freezing(struct task_struct *task) @@ -234,7 +230,7 @@ static void freezer_fork(struct task_struct *task) * The root cgroup is non-freezable, so we can skip the * following check. */ - if (!freezer->css.cgroup->parent) + if (!parent_freezer(freezer)) goto out; spin_lock_irq(&freezer->lock); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 6e9cbdde25bd..259a4af37e69 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -133,11 +133,7 @@ static inline struct cpuset *task_cs(struct task_struct *task) static inline struct cpuset *parent_cs(struct cpuset *cs) { - struct cgroup *pcgrp = cs->css.cgroup->parent; - - if (pcgrp) - return cgroup_cs(pcgrp); - return NULL; + return css_cs(css_parent(&cs->css)); } #ifdef CONFIG_NUMA diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5bccb0277129..7a10742b389a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7114,13 +7114,10 @@ static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp) static int cpu_cgroup_css_online(struct cgroup *cgrp) { struct task_group *tg = cgroup_tg(cgrp); - struct task_group *parent; + struct task_group *parent = css_tg(css_parent(&tg->css)); - if (!cgrp->parent) - return 0; - - parent = cgroup_tg(cgrp->parent); - sched_online_group(tg, parent); + if (parent) + sched_online_group(tg, parent); return 0; } diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 8ccfa10cc89f..f6926a149a71 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -50,16 +50,9 @@ static inline struct cpuacct *task_ca(struct task_struct *tsk) return css_ca(task_css(tsk, cpuacct_subsys_id)); } -static inline struct cpuacct *__parent_ca(struct cpuacct *ca) -{ - return cgroup_ca(ca->css.cgroup->parent); -} - static inline struct cpuacct *parent_ca(struct cpuacct *ca) { - if (!ca->css.cgroup->parent) - return NULL; - return cgroup_ca(ca->css.cgroup->parent); + return css_ca(css_parent(&ca->css)); } static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); @@ -284,7 +277,7 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) while (ca != &root_cpuacct) { kcpustat = this_cpu_ptr(ca->cpustat); kcpustat->cpustat[index] += val; - ca = __parent_ca(ca); + ca = parent_ca(ca); } rcu_read_unlock(); } diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 95585a0b9c8d..57ecb5d2513f 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -59,11 +59,7 @@ static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) static inline struct hugetlb_cgroup * parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) { - struct cgroup *parent = h_cg->css.cgroup->parent; - - if (!parent) - return NULL; - return hugetlb_cgroup_from_cgroup(parent); + return hugetlb_cgroup_from_css(css_parent(&h_cg->css)); } static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 11d659e3b08e..69b3e520f921 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1524,10 +1524,8 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) int mem_cgroup_swappiness(struct mem_cgroup *memcg) { - struct cgroup *cgrp = memcg->css.cgroup; - /* root ? */ - if (cgrp->parent == NULL) + if (!css_parent(&memcg->css)) return vm_swappiness; return memcg->swappiness; @@ -5026,11 +5024,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, { int retval = 0; struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - struct cgroup *parent = cont->parent; - struct mem_cgroup *parent_memcg = NULL; - - if (parent) - parent_memcg = mem_cgroup_from_cont(parent); + struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css)); mutex_lock(&memcg_create_mutex); @@ -5282,18 +5276,15 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, unsigned long long *mem_limit, unsigned long long *memsw_limit) { - struct cgroup *cgroup; unsigned long long min_limit, min_memsw_limit, tmp; min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT); min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); - cgroup = memcg->css.cgroup; if (!memcg->use_hierarchy) goto out; - while (cgroup->parent) { - cgroup = cgroup->parent; - memcg = mem_cgroup_from_cont(cgroup); + while (css_parent(&memcg->css)) { + memcg = mem_cgroup_from_css(css_parent(&memcg->css)); if (!memcg->use_hierarchy) break; tmp = res_counter_read_u64(&memcg->res, RES_LIMIT); @@ -5523,16 +5514,11 @@ static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, u64 val) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); - struct mem_cgroup *parent; - - if (val > 100) - return -EINVAL; + struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); - if (cgrp->parent == NULL) + if (val > 100 || !parent) return -EINVAL; - parent = mem_cgroup_from_cont(cgrp->parent); - mutex_lock(&memcg_create_mutex); /* If under hierarchy, only empty-root can set this value */ @@ -5861,14 +5847,12 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, struct cftype *cft, u64 val) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); - struct mem_cgroup *parent; + struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); /* cannot set to root cgroup and only 0 and 1 are allowed */ - if (!cgrp->parent || !((val == 0) || (val == 1))) + if (!parent || !((val == 0) || (val == 1))) return -EINVAL; - parent = mem_cgroup_from_cont(cgrp->parent); - mutex_lock(&memcg_create_mutex); /* oom-kill-disable is a flag for subhierarchy. */ if ((parent->use_hierarchy) || memcg_has_children(memcg)) { @@ -6266,15 +6250,14 @@ free_out: static int mem_cgroup_css_online(struct cgroup *cont) { - struct mem_cgroup *memcg, *parent; + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); int error = 0; - if (!cont->parent) + if (!parent) return 0; mutex_lock(&memcg_create_mutex); - memcg = mem_cgroup_from_cont(cont); - parent = mem_cgroup_from_cont(cont->parent); memcg->use_hierarchy = parent->use_hierarchy; memcg->oom_kill_disable = parent->oom_kill_disable; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index af412ab2b477..9e6b75e5efce 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -50,9 +50,11 @@ static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp) static int cgrp_css_online(struct cgroup *cgrp) { - if (cgrp->parent) - cgrp_cls_state(cgrp)->classid = - cgrp_cls_state(cgrp->parent)->classid; + struct cgroup_cls_state *cs = cgrp_cls_state(cgrp); + struct cgroup_cls_state *parent = css_cls_state(css_parent(&cs->css)); + + if (parent) + cs->classid = parent->classid; return 0; } diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 90953648c643..635a49db005d 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -198,13 +198,11 @@ static inline bool is_devcg_online(const struct dev_cgroup *devcg) */ static int devcgroup_online(struct cgroup *cgroup) { - struct dev_cgroup *dev_cgroup, *parent_dev_cgroup = NULL; + struct dev_cgroup *dev_cgroup = cgroup_to_devcgroup(cgroup); + struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css_parent(&dev_cgroup->css)); int ret = 0; mutex_lock(&devcgroup_mutex); - dev_cgroup = cgroup_to_devcgroup(cgroup); - if (cgroup->parent) - parent_dev_cgroup = cgroup_to_devcgroup(cgroup->parent); if (parent_dev_cgroup == NULL) dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW; @@ -394,12 +392,10 @@ static bool may_access(struct dev_cgroup *dev_cgroup, static int parent_has_perm(struct dev_cgroup *childcg, struct dev_exception_item *ex) { - struct cgroup *pcg = childcg->css.cgroup->parent; - struct dev_cgroup *parent; + struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css)); - if (!pcg) + if (!parent) return 1; - parent = cgroup_to_devcgroup(pcg); return may_access(parent, ex, childcg->behavior); } @@ -524,15 +520,11 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup, char temp[12]; /* 11 + 1 characters needed for a u32 */ int count, rc = 0; struct dev_exception_item ex; - struct cgroup *p = devcgroup->css.cgroup; - struct dev_cgroup *parent = NULL; + struct dev_cgroup *parent = css_to_devcgroup(css_parent(&devcgroup->css)); if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (p->parent) - parent = cgroup_to_devcgroup(p->parent); - memset(&ex, 0, sizeof(ex)); b = buffer; -- cgit v1.2.3-71-gd317 From eb95419b023abacb415e2a18fea899023ce7624d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Daniel Wagner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe Cc: Steven Rostedt --- block/blk-cgroup.c | 25 +++++++++++---------- include/linux/cgroup.h | 24 +++++++++++--------- kernel/cgroup.c | 57 ++++++++++++++++++++++++++++------------------- kernel/cgroup_freezer.c | 40 +++++++++++++++++---------------- kernel/cpuset.c | 39 +++++++++++++++++--------------- kernel/events/core.c | 18 ++++++++------- kernel/sched/core.c | 39 ++++++++++++++++---------------- kernel/sched/cpuacct.c | 9 ++++---- mm/hugetlb_cgroup.c | 19 ++++++++-------- mm/memcontrol.c | 38 +++++++++++++++---------------- net/core/netprio_cgroup.c | 20 ++++++++--------- net/sched/cls_cgroup.c | 18 ++++++++------- security/device_cgroup.c | 22 +++++++++--------- 13 files changed, 197 insertions(+), 171 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 290792a13e3c..79fd9f4fadb7 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -765,18 +765,18 @@ struct cftype blkcg_files[] = { /** * blkcg_css_offline - cgroup css_offline callback - * @cgroup: cgroup of interest + * @css: css of interest * - * This function is called when @cgroup is about to go away and responsible - * for shooting down all blkgs associated with @cgroup. blkgs should be + * This function is called when @css is about to go away and responsible + * for shooting down all blkgs associated with @css. blkgs should be * removed while holding both q and blkcg locks. As blkcg lock is nested * inside q lock, this function performs reverse double lock dancing. * * This is the blkcg counterpart of ioc_release_fn(). */ -static void blkcg_css_offline(struct cgroup *cgroup) +static void blkcg_css_offline(struct cgroup_subsys_state *css) { - struct blkcg *blkcg = cgroup_to_blkcg(cgroup); + struct blkcg *blkcg = css_to_blkcg(css); spin_lock_irq(&blkcg->lock); @@ -798,21 +798,21 @@ static void blkcg_css_offline(struct cgroup *cgroup) spin_unlock_irq(&blkcg->lock); } -static void blkcg_css_free(struct cgroup *cgroup) +static void blkcg_css_free(struct cgroup_subsys_state *css) { - struct blkcg *blkcg = cgroup_to_blkcg(cgroup); + struct blkcg *blkcg = css_to_blkcg(css); if (blkcg != &blkcg_root) kfree(blkcg); } -static struct cgroup_subsys_state *blkcg_css_alloc(struct cgroup *cgroup) +static struct cgroup_subsys_state * +blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { static atomic64_t id_seq = ATOMIC64_INIT(0); struct blkcg *blkcg; - struct cgroup *parent = cgroup->parent; - if (!parent) { + if (!parent_css) { blkcg = &blkcg_root; goto done; } @@ -883,14 +883,15 @@ void blkcg_exit_queue(struct request_queue *q) * of the main cic data structures. For now we allow a task to change * its cgroup only if it's the only owner of its ioc. */ -static int blkcg_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +static int blkcg_can_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) { struct task_struct *task; struct io_context *ioc; int ret = 0; /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, cgrp, tset) { + cgroup_taskset_for_each(task, css->cgroup, tset) { task_lock(task); ioc = task->io_context; if (ioc && atomic_read(&ioc->nr_tasks) > 1) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 18112a3bb12b..9c2b9dd9121d 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -579,18 +579,22 @@ int cgroup_taskset_size(struct cgroup_taskset *tset); */ struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup *cgrp); - int (*css_online)(struct cgroup *cgrp); - void (*css_offline)(struct cgroup *cgrp); - void (*css_free)(struct cgroup *cgrp); - - int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); - void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, + void (*exit)(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, struct task_struct *task); - void (*bind)(struct cgroup *root); + void (*bind)(struct cgroup_subsys_state *root_css); int subsys_id; int disabled; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4234428f1014..271d9a5cde5f 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -853,8 +853,11 @@ static void cgroup_free_fn(struct work_struct *work) /* * Release the subsystem state objects. */ - for_each_root_subsys(cgrp->root, ss) - ss->css_free(cgrp); + for_each_root_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + + ss->css_free(css); + } cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); @@ -1056,7 +1059,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) - ss->bind(cgrp); + ss->bind(cgrp->subsys[i]); /* refcount was already taken, and we're keeping it */ root->subsys_mask |= bit; @@ -1066,7 +1069,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]->cgroup != cgrp); if (ss->bind) - ss->bind(cgroup_dummy_top); + ss->bind(cgroup_dummy_top->subsys[i]); cgroup_dummy_top->subsys[i]->cgroup = cgroup_dummy_top; cgrp->subsys[i] = NULL; cgroup_subsys[i]->root = &cgroup_dummy_root; @@ -2049,8 +2052,10 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, * step 1: check that we can legitimately attach to the cgroup. */ for_each_root_subsys(root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + if (ss->can_attach) { - retval = ss->can_attach(cgrp, &tset); + retval = ss->can_attach(css, &tset); if (retval) { failed_ss = ss; goto out_cancel_attach; @@ -2089,8 +2094,10 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, * step 4: do subsystem attach callbacks. */ for_each_root_subsys(root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + if (ss->attach) - ss->attach(cgrp, &tset); + ss->attach(css, &tset); } /* @@ -2109,10 +2116,12 @@ out_put_css_set_refs: out_cancel_attach: if (retval) { for_each_root_subsys(root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + if (ss == failed_ss) break; if (ss->cancel_attach) - ss->cancel_attach(cgrp, &tset); + ss->cancel_attach(css, &tset); } } out_free_group_list: @@ -4206,14 +4215,15 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, /* invoke ->css_online() on a new CSS and mark it online if successful */ static int online_css(struct cgroup_subsys *ss, struct cgroup *cgrp) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; int ret = 0; lockdep_assert_held(&cgroup_mutex); if (ss->css_online) - ret = ss->css_online(cgrp); + ret = ss->css_online(css); if (!ret) - cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE; + css->flags |= CSS_ONLINE; return ret; } @@ -4228,9 +4238,9 @@ static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp) return; if (ss->css_offline) - ss->css_offline(cgrp); + ss->css_offline(css); - cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE; + css->flags &= ~CSS_ONLINE; } /* @@ -4305,7 +4315,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, for_each_root_subsys(root, ss) { struct cgroup_subsys_state *css; - css = ss->css_alloc(cgrp); + css = ss->css_alloc(parent->subsys[ss->subsys_id]); if (IS_ERR(css)) { err = PTR_ERR(css); goto err_free_all; @@ -4313,7 +4323,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, err = percpu_ref_init(&css->refcnt, css_release); if (err) { - ss->css_free(cgrp); + ss->css_free(css); goto err_free_all; } @@ -4386,7 +4396,7 @@ err_free_all: if (css) { percpu_ref_cancel_init(&css->refcnt); - ss->css_free(cgrp); + ss->css_free(css); } } mutex_unlock(&cgroup_mutex); @@ -4641,7 +4651,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) /* Create the top cgroup state for this subsystem */ list_add(&ss->sibling, &cgroup_dummy_root.subsys_list); ss->root = &cgroup_dummy_root; - css = ss->css_alloc(cgroup_dummy_top); + css = ss->css_alloc(cgroup_dummy_top->subsys[ss->subsys_id]); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_cgroup_css(css, ss, cgroup_dummy_top); @@ -4720,7 +4730,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) * struct, so this can happen first (i.e. before the dummy root * attachment). */ - css = ss->css_alloc(cgroup_dummy_top); + css = ss->css_alloc(cgroup_dummy_top->subsys[ss->subsys_id]); if (IS_ERR(css)) { /* failure case - need to deassign the cgroup_subsys[] slot. */ cgroup_subsys[ss->subsys_id] = NULL; @@ -4836,7 +4846,7 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) * the cgrp->subsys pointer to find their state. note that this * also takes care of freeing the css_id. */ - ss->css_free(cgroup_dummy_top); + ss->css_free(cgroup_dummy_top->subsys[ss->subsys_id]); cgroup_dummy_top->subsys[ss->subsys_id] = NULL; mutex_unlock(&cgroup_mutex); @@ -5192,10 +5202,10 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) */ for_each_builtin_subsys(ss, i) { if (ss->exit) { - struct cgroup *old_cgrp = cset->subsys[i]->cgroup; - struct cgroup *cgrp = task_cgroup(tsk, i); + struct cgroup_subsys_state *old_css = cset->subsys[i]; + struct cgroup_subsys_state *css = task_css(tsk, i); - ss->exit(cgrp, old_cgrp, tsk); + ss->exit(css, old_css, tsk); } } } @@ -5529,7 +5539,8 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id) } #ifdef CONFIG_CGROUP_DEBUG -static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +debug_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); @@ -5539,9 +5550,9 @@ static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cgrp) return css; } -static void debug_css_free(struct cgroup *cgrp) +static void debug_css_free(struct cgroup_subsys_state *css) { - kfree(cgrp->subsys[debug_subsys_id]); + kfree(css); } static u64 debug_taskcount_read(struct cgroup *cgrp, struct cftype *cft) diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 657a73cd44c4..f03a85719c3c 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -91,7 +91,8 @@ static const char *freezer_state_strs(unsigned int state) struct cgroup_subsys freezer_subsys; -static struct cgroup_subsys_state *freezer_css_alloc(struct cgroup *cgroup) +static struct cgroup_subsys_state * +freezer_css_alloc(struct cgroup_subsys_state *parent_css) { struct freezer *freezer; @@ -104,16 +105,16 @@ static struct cgroup_subsys_state *freezer_css_alloc(struct cgroup *cgroup) } /** - * freezer_css_online - commit creation of a freezer cgroup - * @cgroup: cgroup being created + * freezer_css_online - commit creation of a freezer css + * @css: css being created * - * We're committing to creation of @cgroup. Mark it online and inherit + * We're committing to creation of @css. Mark it online and inherit * parent's freezing state while holding both parent's and our * freezer->lock. */ -static int freezer_css_online(struct cgroup *cgroup) +static int freezer_css_online(struct cgroup_subsys_state *css) { - struct freezer *freezer = cgroup_freezer(cgroup); + struct freezer *freezer = css_freezer(css); struct freezer *parent = parent_freezer(freezer); /* @@ -140,15 +141,15 @@ static int freezer_css_online(struct cgroup *cgroup) } /** - * freezer_css_offline - initiate destruction of @cgroup - * @cgroup: cgroup being destroyed + * freezer_css_offline - initiate destruction of a freezer css + * @css: css being destroyed * - * @cgroup is going away. Mark it dead and decrement system_freezing_count - * if it was holding one. + * @css is going away. Mark it dead and decrement system_freezing_count if + * it was holding one. */ -static void freezer_css_offline(struct cgroup *cgroup) +static void freezer_css_offline(struct cgroup_subsys_state *css) { - struct freezer *freezer = cgroup_freezer(cgroup); + struct freezer *freezer = css_freezer(css); spin_lock_irq(&freezer->lock); @@ -160,9 +161,9 @@ static void freezer_css_offline(struct cgroup *cgroup) spin_unlock_irq(&freezer->lock); } -static void freezer_css_free(struct cgroup *cgroup) +static void freezer_css_free(struct cgroup_subsys_state *css) { - kfree(cgroup_freezer(cgroup)); + kfree(css_freezer(css)); } /* @@ -174,25 +175,26 @@ static void freezer_css_free(struct cgroup *cgroup) * @freezer->lock. freezer_attach() makes the new tasks conform to the * current state and all following state changes can see the new tasks. */ -static void freezer_attach(struct cgroup *new_cgrp, struct cgroup_taskset *tset) +static void freezer_attach(struct cgroup_subsys_state *new_css, + struct cgroup_taskset *tset) { - struct freezer *freezer = cgroup_freezer(new_cgrp); + struct freezer *freezer = css_freezer(new_css); struct task_struct *task; bool clear_frozen = false; spin_lock_irq(&freezer->lock); /* - * Make the new tasks conform to the current state of @new_cgrp. + * Make the new tasks conform to the current state of @new_css. * For simplicity, when migrating any task to a FROZEN cgroup, we * revert it to FREEZING and let update_if_frozen() determine the * correct state later. * - * Tasks in @tset are on @new_cgrp but may not conform to its + * Tasks in @tset are on @new_css but may not conform to its * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ - cgroup_taskset_for_each(task, new_cgrp, tset) { + cgroup_taskset_for_each(task, new_css->cgroup, tset) { if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 259a4af37e69..8ce3fdc3dfcc 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1455,9 +1455,10 @@ static int fmeter_getrate(struct fmeter *fmp) } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ -static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +static int cpuset_can_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); struct task_struct *task; int ret; @@ -1468,11 +1469,11 @@ static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) * flag is set. */ ret = -ENOSPC; - if (!cgroup_sane_behavior(cgrp) && + if (!cgroup_sane_behavior(css->cgroup) && (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; - cgroup_taskset_for_each(task, cgrp, tset) { + cgroup_taskset_for_each(task, css->cgroup, tset) { /* * Kthreads which disallow setaffinity shouldn't be moved * to a new cpuset; we don't want to change their cpu @@ -1501,11 +1502,11 @@ out_unlock: return ret; } -static void cpuset_cancel_attach(struct cgroup *cgrp, +static void cpuset_cancel_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { mutex_lock(&cpuset_mutex); - cgroup_cs(cgrp)->attach_in_progress--; + css_cs(css)->attach_in_progress--; mutex_unlock(&cpuset_mutex); } @@ -1516,7 +1517,8 @@ static void cpuset_cancel_attach(struct cgroup *cgrp, */ static cpumask_var_t cpus_attach; -static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +static void cpuset_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; @@ -1524,7 +1526,7 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) struct task_struct *task; struct task_struct *leader = cgroup_taskset_first(tset); struct cgroup *oldcgrp = cgroup_taskset_cur_cgroup(tset); - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); struct cpuset *oldcs = cgroup_cs(oldcgrp); struct cpuset *cpus_cs = effective_cpumask_cpuset(cs); struct cpuset *mems_cs = effective_nodemask_cpuset(cs); @@ -1539,7 +1541,7 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, cgrp, tset) { + cgroup_taskset_for_each(task, css->cgroup, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -1940,11 +1942,12 @@ static struct cftype files[] = { * cgrp: control group that the new cpuset will be part of */ -static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; - if (!cgrp->parent) + if (!parent_css) return &top_cpuset.css; cs = kzalloc(sizeof(*cs), GFP_KERNEL); @@ -1964,9 +1967,9 @@ static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cgrp) return &cs->css; } -static int cpuset_css_online(struct cgroup *cgrp) +static int cpuset_css_online(struct cgroup_subsys_state *css) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; struct cgroup *pos_cgrp; @@ -1984,7 +1987,7 @@ static int cpuset_css_online(struct cgroup *cgrp) number_of_cpusets++; - if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags)) + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; /* @@ -2024,9 +2027,9 @@ out_unlock: * will call rebuild_sched_domains_locked(). */ -static void cpuset_css_offline(struct cgroup *cgrp) +static void cpuset_css_offline(struct cgroup_subsys_state *css) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -2039,9 +2042,9 @@ static void cpuset_css_offline(struct cgroup *cgrp) mutex_unlock(&cpuset_mutex); } -static void cpuset_css_free(struct cgroup *cgrp) +static void cpuset_css_free(struct cgroup_subsys_state *css) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); free_cpumask_var(cs->cpus_allowed); kfree(cs); diff --git a/kernel/events/core.c b/kernel/events/core.c index 414c61f4d776..9705a0ed1dce 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7778,7 +7778,8 @@ unlock: device_initcall(perf_event_sysfs_init); #ifdef CONFIG_CGROUP_PERF -static struct cgroup_subsys_state *perf_cgroup_css_alloc(struct cgroup *cont) +static struct cgroup_subsys_state * +perf_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct perf_cgroup *jc; @@ -7795,11 +7796,10 @@ static struct cgroup_subsys_state *perf_cgroup_css_alloc(struct cgroup *cont) return &jc->css; } -static void perf_cgroup_css_free(struct cgroup *cont) +static void perf_cgroup_css_free(struct cgroup_subsys_state *css) { - struct perf_cgroup *jc; - jc = container_of(cgroup_css(cont, perf_subsys_id), - struct perf_cgroup, css); + struct perf_cgroup *jc = container_of(css, struct perf_cgroup, css); + free_percpu(jc->info); kfree(jc); } @@ -7811,15 +7811,17 @@ static int __perf_cgroup_move(void *info) return 0; } -static void perf_cgroup_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +static void perf_cgroup_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) { struct task_struct *task; - cgroup_taskset_for_each(task, cgrp, tset) + cgroup_taskset_for_each(task, css->cgroup, tset) task_function_call(task, __perf_cgroup_move, task); } -static void perf_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp, +static void perf_cgroup_exit(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, struct task_struct *task) { /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7a10742b389a..622b7efc5ade 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7094,16 +7094,17 @@ static inline struct task_group *cgroup_tg(struct cgroup *cgrp) return css_tg(cgroup_css(cgrp, cpu_cgroup_subsys_id)); } -static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { - struct task_group *tg, *parent; + struct task_group *parent = css_tg(parent_css); + struct task_group *tg; - if (!cgrp->parent) { + if (!parent) { /* This is early initialization for the top cgroup */ return &root_task_group.css; } - parent = cgroup_tg(cgrp->parent); tg = sched_create_group(parent); if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); @@ -7111,38 +7112,38 @@ static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp) return &tg->css; } -static int cpu_cgroup_css_online(struct cgroup *cgrp) +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) { - struct task_group *tg = cgroup_tg(cgrp); - struct task_group *parent = css_tg(css_parent(&tg->css)); + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css_parent(css)); if (parent) sched_online_group(tg, parent); return 0; } -static void cpu_cgroup_css_free(struct cgroup *cgrp) +static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); sched_destroy_group(tg); } -static void cpu_cgroup_css_offline(struct cgroup *cgrp) +static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); sched_offline_group(tg); } -static int cpu_cgroup_can_attach(struct cgroup *cgrp, +static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *task; - cgroup_taskset_for_each(task, cgrp, tset) { + cgroup_taskset_for_each(task, css->cgroup, tset) { #ifdef CONFIG_RT_GROUP_SCHED - if (!sched_rt_can_attach(cgroup_tg(cgrp), task)) + if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; #else /* We don't support RT-tasks being in separate groups */ @@ -7153,18 +7154,18 @@ static int cpu_cgroup_can_attach(struct cgroup *cgrp, return 0; } -static void cpu_cgroup_attach(struct cgroup *cgrp, +static void cpu_cgroup_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *task; - cgroup_taskset_for_each(task, cgrp, tset) + cgroup_taskset_for_each(task, css->cgroup, tset) sched_move_task(task); } -static void -cpu_cgroup_exit(struct cgroup *cgrp, struct cgroup *old_cgrp, - struct task_struct *task) +static void cpu_cgroup_exit(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task) { /* * cgroup_exit() is called in the copy_process() failure path. diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index f6926a149a71..1b784d9b3630 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -62,11 +62,12 @@ static struct cpuacct root_cpuacct = { }; /* create a new cpu accounting group */ -static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +cpuacct_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuacct *ca; - if (!cgrp->parent) + if (!parent_css) return &root_cpuacct.css; ca = kzalloc(sizeof(*ca), GFP_KERNEL); @@ -92,9 +93,9 @@ out: } /* destroy an existing cpu accounting group */ -static void cpuacct_css_free(struct cgroup *cgrp) +static void cpuacct_css_free(struct cgroup_subsys_state *css) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); free_percpu(ca->cpustat); free_percpu(ca->cpuusage); diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 57ecb5d2513f..e2132435060f 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -73,19 +73,18 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) return false; } -static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgroup) +static struct cgroup_subsys_state * +hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { + struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); + struct hugetlb_cgroup *h_cgroup; int idx; - struct cgroup *parent_cgroup; - struct hugetlb_cgroup *h_cgroup, *parent_h_cgroup; h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); - parent_cgroup = cgroup->parent; - if (parent_cgroup) { - parent_h_cgroup = hugetlb_cgroup_from_cgroup(parent_cgroup); + if (parent_h_cgroup) { for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) res_counter_init(&h_cgroup->hugepage[idx], &parent_h_cgroup->hugepage[idx]); @@ -97,11 +96,11 @@ static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgrou return &h_cgroup->css; } -static void hugetlb_cgroup_css_free(struct cgroup *cgroup) +static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cgroup; - h_cgroup = hugetlb_cgroup_from_cgroup(cgroup); + h_cgroup = hugetlb_cgroup_from_css(css); kfree(h_cgroup); } @@ -150,9 +149,9 @@ out: * Force the hugetlb cgroup to empty the hugetlb resources by moving them to * the parent cgroup. */ -static void hugetlb_cgroup_css_offline(struct cgroup *cgroup) +static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) { - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; int idx = 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 69b3e520f921..32cca0f0af0d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6211,7 +6211,7 @@ static void __init mem_cgroup_soft_limit_tree_init(void) } static struct cgroup_subsys_state * __ref -mem_cgroup_css_alloc(struct cgroup *cont) +mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct mem_cgroup *memcg; long error = -ENOMEM; @@ -6226,7 +6226,7 @@ mem_cgroup_css_alloc(struct cgroup *cont) goto free_out; /* root ? */ - if (cont->parent == NULL) { + if (parent_css == NULL) { root_mem_cgroup = memcg; res_counter_init(&memcg->res, NULL); res_counter_init(&memcg->memsw, NULL); @@ -6248,10 +6248,10 @@ free_out: } static int -mem_cgroup_css_online(struct cgroup *cont) +mem_cgroup_css_online(struct cgroup_subsys_state *css) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css)); int error = 0; if (!parent) @@ -6308,9 +6308,9 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg) mem_cgroup_iter_invalidate(root_mem_cgroup); } -static void mem_cgroup_css_offline(struct cgroup *cont) +static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); kmem_cgroup_css_offline(memcg); @@ -6319,9 +6319,9 @@ static void mem_cgroup_css_offline(struct cgroup *cont) mem_cgroup_destroy_all_caches(memcg); } -static void mem_cgroup_css_free(struct cgroup *cont) +static void mem_cgroup_css_free(struct cgroup_subsys_state *css) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); memcg_destroy_kmem(memcg); __mem_cgroup_free(memcg); @@ -6691,12 +6691,12 @@ static void mem_cgroup_clear_mc(void) mem_cgroup_end_move(from); } -static int mem_cgroup_can_attach(struct cgroup *cgroup, +static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); int ret = 0; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); unsigned long move_charge_at_immigrate; /* @@ -6738,7 +6738,7 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup *cgroup, +static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { mem_cgroup_clear_mc(); @@ -6886,7 +6886,7 @@ retry: up_read(&mm->mmap_sem); } -static void mem_cgroup_move_task(struct cgroup *cont, +static void mem_cgroup_move_task(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); @@ -6901,16 +6901,16 @@ static void mem_cgroup_move_task(struct cgroup *cont, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup *cgroup, +static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup *cgroup, +static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup *cont, +static void mem_cgroup_move_task(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { } @@ -6920,15 +6920,15 @@ static void mem_cgroup_move_task(struct cgroup *cont, * Cgroup retains root cgroups across [un]mount cycles making it necessary * to verify sane_behavior flag on each mount attempt. */ -static void mem_cgroup_bind(struct cgroup *root) +static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) { /* * use_hierarchy is forced with sane_behavior. cgroup core * guarantees that @root doesn't have any children, so turning it * on for the root memcg is enough. */ - if (cgroup_sane_behavior(root)) - mem_cgroup_from_cont(root)->use_hierarchy = true; + if (cgroup_sane_behavior(root_css->cgroup)) + mem_cgroup_from_css(root_css)->use_hierarchy = true; } struct cgroup_subsys mem_cgroup_subsys = { diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 5dfac8886e12..8d095b4c2f6f 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -126,7 +126,8 @@ static int netprio_set_prio(struct cgroup_subsys_state *css, return 0; } -static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css; @@ -137,16 +138,14 @@ static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp) return css; } -static int cgrp_css_online(struct cgroup *cgrp) +static int cgrp_css_online(struct cgroup_subsys_state *css) { - struct cgroup_subsys_state *css = cgroup_css(cgrp, net_prio_subsys_id); - struct cgroup_subsys_state *parent_css; + struct cgroup_subsys_state *parent_css = css_parent(css); struct net_device *dev; int ret = 0; - if (!cgrp->parent) + if (!parent_css) return 0; - parent_css = cgroup_css(cgrp->parent, net_prio_subsys_id); rtnl_lock(); /* @@ -164,9 +163,9 @@ static int cgrp_css_online(struct cgroup *cgrp) return ret; } -static void cgrp_css_free(struct cgroup *cgrp) +static void cgrp_css_free(struct cgroup_subsys_state *css) { - kfree(cgroup_css(cgrp, net_prio_subsys_id)); + kfree(css); } static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft) @@ -221,12 +220,13 @@ static int update_netprio(const void *v, struct file *file, unsigned n) return 0; } -static void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +static void net_prio_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) { struct task_struct *p; void *v; - cgroup_taskset_for_each(p, cgrp, tset) { + cgroup_taskset_for_each(p, css->cgroup, tset) { task_lock(p); v = (void *)(unsigned long)task_netprioidx(p); iterate_fd(p->files, 0, update_netprio, v); diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 9e6b75e5efce..dc3983835893 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -38,7 +38,8 @@ static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p) return css_cls_state(task_css(p, net_cls_subsys_id)); } -static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp) +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_cls_state *cs; @@ -48,19 +49,19 @@ static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp) return &cs->css; } -static int cgrp_css_online(struct cgroup *cgrp) +static int cgrp_css_online(struct cgroup_subsys_state *css) { - struct cgroup_cls_state *cs = cgrp_cls_state(cgrp); - struct cgroup_cls_state *parent = css_cls_state(css_parent(&cs->css)); + struct cgroup_cls_state *cs = css_cls_state(css); + struct cgroup_cls_state *parent = css_cls_state(css_parent(css)); if (parent) cs->classid = parent->classid; return 0; } -static void cgrp_css_free(struct cgroup *cgrp) +static void cgrp_css_free(struct cgroup_subsys_state *css) { - kfree(cgrp_cls_state(cgrp)); + kfree(css_cls_state(css)); } static int update_classid(const void *v, struct file *file, unsigned n) @@ -72,12 +73,13 @@ static int update_classid(const void *v, struct file *file, unsigned n) return 0; } -static void cgrp_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) +static void cgrp_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) { struct task_struct *p; void *v; - cgroup_taskset_for_each(p, cgrp, tset) { + cgroup_taskset_for_each(p, css->cgroup, tset) { task_lock(p); v = (void *)(unsigned long)task_cls_classid(p); iterate_fd(p->files, 0, update_classid, v); diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 635a49db005d..7293ac49ba7b 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -68,7 +68,7 @@ static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) struct cgroup_subsys devices_subsys; -static int devcgroup_can_attach(struct cgroup *new_cgrp, +static int devcgroup_can_attach(struct cgroup_subsys_state *new_css, struct cgroup_taskset *set) { struct task_struct *task = cgroup_taskset_first(set); @@ -193,13 +193,13 @@ static inline bool is_devcg_online(const struct dev_cgroup *devcg) /** * devcgroup_online - initializes devcgroup's behavior and exceptions based on * parent's - * @cgroup: cgroup getting online + * @css: css getting online * returns 0 in case of success, error code otherwise */ -static int devcgroup_online(struct cgroup *cgroup) +static int devcgroup_online(struct cgroup_subsys_state *css) { - struct dev_cgroup *dev_cgroup = cgroup_to_devcgroup(cgroup); - struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css_parent(&dev_cgroup->css)); + struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); + struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css_parent(css)); int ret = 0; mutex_lock(&devcgroup_mutex); @@ -217,9 +217,9 @@ static int devcgroup_online(struct cgroup *cgroup) return ret; } -static void devcgroup_offline(struct cgroup *cgroup) +static void devcgroup_offline(struct cgroup_subsys_state *css) { - struct dev_cgroup *dev_cgroup = cgroup_to_devcgroup(cgroup); + struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); mutex_lock(&devcgroup_mutex); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; @@ -229,7 +229,8 @@ static void devcgroup_offline(struct cgroup *cgroup) /* * called from kernel/cgroup.c with cgroup_lock() held. */ -static struct cgroup_subsys_state *devcgroup_css_alloc(struct cgroup *cgroup) +static struct cgroup_subsys_state * +devcgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct dev_cgroup *dev_cgroup; @@ -242,11 +243,10 @@ static struct cgroup_subsys_state *devcgroup_css_alloc(struct cgroup *cgroup) return &dev_cgroup->css; } -static void devcgroup_css_free(struct cgroup *cgroup) +static void devcgroup_css_free(struct cgroup_subsys_state *css) { - struct dev_cgroup *dev_cgroup; + struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); - dev_cgroup = cgroup_to_devcgroup(cgroup); __dev_exception_clean(dev_cgroup); kfree(dev_cgroup); } -- cgit v1.2.3-71-gd317 From 2bb566cb68dfafad328af666ebadf0e49accd6ca Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:23 -0400 Subject: cgroup: add subsys backlink pointer to cftype cgroup is transitioning to using css (cgroup_subsys_state) instead of cgroup as the primary subsystem handle. The cgroupfs file interface will be converted to use css's which requires finding out the subsystem from cftype so that the matching css can be determined from the cgroup. This patch adds cftype->ss which points to the subsystem the file belongs to. The field is initialized while a cftype is being registered. This makes it unnecessary to explicitly specify the subsystem for other cftype handling functions. @ss argument dropped from various cftype handling functions. This patch shouldn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Vivek Goyal Cc: Jens Axboe --- block/blk-cgroup.c | 2 +- include/linux/cgroup.h | 8 +++++- kernel/cgroup.c | 78 ++++++++++++++++++++++++++++---------------------- 3 files changed, 51 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 79fd9f4fadb7..34063739745b 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1128,7 +1128,7 @@ void blkcg_policy_unregister(struct blkcg_policy *pol) /* kill the intf files first */ if (pol->cftypes) - cgroup_rm_cftypes(&blkio_subsys, pol->cftypes); + cgroup_rm_cftypes(pol->cftypes); /* unregister and update blkgs */ blkcg_policy[pol->plid] = NULL; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9c2b9dd9121d..5db8138a0482 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -429,6 +429,12 @@ struct cftype { /* CFTYPE_* flags */ unsigned int flags; + /* + * The subsys this file belongs to. Initialized automatically + * during registration. NULL for cgroup core files. + */ + struct cgroup_subsys *ss; + int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, @@ -542,7 +548,7 @@ static inline const char *cgroup_name(const struct cgroup *cgrp) } int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(struct cftype *cfts); bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 271d9a5cde5f..c4bc8dac3b1d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -219,8 +219,8 @@ static struct cftype cgroup_base_files[]; static void cgroup_offline_fn(struct work_struct *work); static int cgroup_destroy_locked(struct cgroup *cgrp); -static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, - struct cftype cfts[], bool is_add); +static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], + bool is_add); /* convenient tests for these bits */ static inline bool cgroup_is_dead(const struct cgroup *cgrp) @@ -974,7 +974,7 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask) if (!test_bit(i, &subsys_mask)) continue; list_for_each_entry(set, &ss->cftsets, node) - cgroup_addrm_files(cgrp, NULL, set->cfts, false); + cgroup_addrm_files(cgrp, set->cfts, false); } } @@ -1623,7 +1623,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, */ cred = override_creds(&init_cred); - ret = cgroup_addrm_files(root_cgrp, NULL, cgroup_base_files, true); + ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true); if (ret) goto rm_base_files; @@ -1681,7 +1681,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, rm_base_files: free_cgrp_cset_links(&tmp_links); - cgroup_addrm_files(&root->top_cgroup, NULL, cgroup_base_files, false); + cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false); revert_creds(cred); unlock_drop: cgroup_exit_root_id(root); @@ -2694,8 +2694,7 @@ static umode_t cgroup_file_mode(const struct cftype *cft) return mode; } -static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, - struct cftype *cft) +static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) { struct dentry *dir = cgrp->dentry; struct cgroup *parent = __d_cgrp(dir); @@ -2705,8 +2704,8 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, umode_t mode; char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; - if (subsys && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { - strcpy(name, subsys->name); + if (cft->ss && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { + strcpy(name, cft->ss->name); strcat(name, "."); } strcat(name, cft->name); @@ -2743,17 +2742,16 @@ out: /** * cgroup_addrm_files - add or remove files to a cgroup directory * @cgrp: the target cgroup - * @subsys: the subsystem of files to be added * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. - * All @cfts should belong to @subsys. For removals, this function never - * fails. If addition fails, this function doesn't remove files already - * added. The caller is responsible for cleaning up. + * For removals, this function never fails. If addition fails, this + * function doesn't remove files already added. The caller is responsible + * for cleaning up. */ -static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, - struct cftype cfts[], bool is_add) +static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], + bool is_add) { struct cftype *cft; int ret; @@ -2771,7 +2769,7 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, continue; if (is_add) { - ret = cgroup_add_file(cgrp, subsys, cft); + ret = cgroup_add_file(cgrp, cft); if (ret) { pr_warn("cgroup_addrm_files: failed to add %s, err=%d\n", cft->name, ret); @@ -2796,11 +2794,11 @@ static void cgroup_cfts_prepare(void) mutex_lock(&cgroup_mutex); } -static int cgroup_cfts_commit(struct cgroup_subsys *ss, - struct cftype *cfts, bool is_add) +static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) __releases(&cgroup_mutex) { LIST_HEAD(pending); + struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *cgrp, *root = &ss->root->top_cgroup; struct super_block *sb = ss->root->sb; struct dentry *prev = NULL; @@ -2828,7 +2826,7 @@ static int cgroup_cfts_commit(struct cgroup_subsys *ss, inode = root->dentry->d_inode; mutex_lock(&inode->i_mutex); mutex_lock(&cgroup_mutex); - ret = cgroup_addrm_files(root, ss, cfts, is_add); + ret = cgroup_addrm_files(root, cfts, is_add); mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); @@ -2851,7 +2849,7 @@ static int cgroup_cfts_commit(struct cgroup_subsys *ss, mutex_lock(&inode->i_mutex); mutex_lock(&cgroup_mutex); if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp)) - ret = cgroup_addrm_files(cgrp, ss, cfts, is_add); + ret = cgroup_addrm_files(cgrp, cfts, is_add); mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); @@ -2883,51 +2881,56 @@ out_deact: int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype_set *set; + struct cftype *cft; int ret; set = kzalloc(sizeof(*set), GFP_KERNEL); if (!set) return -ENOMEM; + for (cft = cfts; cft->name[0] != '\0'; cft++) + cft->ss = ss; + cgroup_cfts_prepare(); set->cfts = cfts; list_add_tail(&set->node, &ss->cftsets); - ret = cgroup_cfts_commit(ss, cfts, true); + ret = cgroup_cfts_commit(cfts, true); if (ret) - cgroup_rm_cftypes(ss, cfts); + cgroup_rm_cftypes(cfts); return ret; } EXPORT_SYMBOL_GPL(cgroup_add_cftypes); /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem - * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * - * Unregister @cfts from @ss. Files described by @cfts are removed from - * all existing cgroups to which @ss is attached and all future cgroups - * won't have them either. This function can be called anytime whether @ss - * is attached or not. + * Unregister @cfts. Files described by @cfts are removed from all + * existing cgroups and all future cgroups won't have them either. This + * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not - * registered with @ss. + * registered. */ -int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) +int cgroup_rm_cftypes(struct cftype *cfts) { struct cftype_set *set; + if (!cfts || !cfts[0].ss) + return -ENOENT; + cgroup_cfts_prepare(); - list_for_each_entry(set, &ss->cftsets, node) { + list_for_each_entry(set, &cfts[0].ss->cftsets, node) { if (set->cfts == cfts) { list_del(&set->node); kfree(set); - cgroup_cfts_commit(ss, cfts, false); + cgroup_cfts_commit(cfts, false); return 0; } } - cgroup_cfts_commit(ss, NULL, false); + cgroup_cfts_commit(NULL, false); return -ENOENT; } @@ -4148,7 +4151,7 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask) continue; list_for_each_entry(set, &ss->cftsets, node) { - ret = cgroup_addrm_files(cgrp, ss, set->cfts, true); + ret = cgroup_addrm_files(cgrp, set->cfts, true); if (ret < 0) goto err; } @@ -4377,7 +4380,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, idr_replace(&root->cgroup_idr, cgrp, cgrp->id); - err = cgroup_addrm_files(cgrp, NULL, cgroup_base_files, true); + err = cgroup_addrm_files(cgrp, cgroup_base_files, true); if (err) goto err_destroy; @@ -4538,7 +4541,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) * but we aren't quite done with @cgrp yet, so hold onto it. */ cgroup_clear_dir(cgrp, cgrp->root->subsys_mask); - cgroup_addrm_files(cgrp, NULL, cgroup_base_files, false); + cgroup_addrm_files(cgrp, cgroup_base_files, false); dget(d); cgroup_d_remove_dir(d); @@ -4632,6 +4635,11 @@ static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss) * deregistration. */ if (ss->base_cftypes) { + struct cftype *cft; + + for (cft = ss->base_cftypes; cft->name[0] != '\0'; cft++) + cft->ss = ss; + ss->base_cftset.cfts = ss->base_cftypes; list_add_tail(&ss->base_cftset.node, &ss->cftsets); } -- cgit v1.2.3-71-gd317 From 67f4c36f83455b253445b2cb28ac9a2c4f85d99a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: add cgroup->dummy_css cgroup subsystem API is being converted to use css (cgroup_subsys_state) as the main handle, which makes things a bit awkward for subsystem agnostic core features - the "cgroup.*" interface files and various iterations - a bit awkward as they don't have a css to use. This patch adds cgroup->dummy_css which has NULL ->ss and whose only role is pointing back to the cgroup. This will be used to support subsystem agnostic features on the coming css based API. css_parent() is updated to handle dummy_css's. Note that css will soon grow its own ->parent field and css_parent() will be made trivial. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 11 ++++++++++- kernel/cgroup.c | 9 +++++---- 2 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5db8138a0482..b0d5f53ae5e1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -225,6 +225,9 @@ struct cgroup { struct list_head pidlists; struct mutex pidlist_mutex; + /* dummy css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state dummy_css; + /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; struct work_struct destroy_work; @@ -668,7 +671,13 @@ struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) { struct cgroup *parent_cgrp = css->cgroup->parent; - return parent_cgrp ? parent_cgrp->subsys[css->ss->subsys_id] : NULL; + if (!parent_cgrp) + return NULL; + + if (css->ss) + return parent_cgrp->subsys[css->ss->subsys_id]; + else + return &parent_cgrp->dummy_css; } /** diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 583f8f66a7e1..c049992f1ffa 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1365,6 +1365,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); + cgrp->dummy_css.cgroup = cgrp; INIT_LIST_HEAD(&cgrp->event_list); spin_lock_init(&cgrp->event_list_lock); simple_xattrs_init(&cgrp->xattrs); @@ -2285,7 +2286,7 @@ static struct cgroup_subsys_state *cgroup_file_css(struct cfent *cfe) if (cft->ss) return cgrp->subsys[cft->ss->subsys_id]; - return NULL; + return &cgrp->dummy_css; } /* A buffer size big enough for numbers or short strings */ @@ -2467,7 +2468,7 @@ static int cgroup_file_open(struct inode *inode, struct file *file) * unpinned either on open failure or release. This ensures that * @css stays alive for all file operations. */ - if (css && !css_tryget(css)) + if (css->ss && !css_tryget(css)) return -ENODEV; if (cft->read_map || cft->read_seq_string) { @@ -2477,7 +2478,7 @@ static int cgroup_file_open(struct inode *inode, struct file *file) err = cft->open(inode, file); } - if (css && err) + if (css->ss && err) css_put(css); return err; } @@ -2491,7 +2492,7 @@ static int cgroup_file_release(struct inode *inode, struct file *file) if (cft->release) ret = cft->release(inode, file); - if (css) + if (css->ss) css_put(css); return ret; } -- cgit v1.2.3-71-gd317 From 182446d087906de40e514573a92a97b203695f71 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: pass around cgroup_subsys_state instead of cgroup in file methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup. Please see the previous commit which converts the subsystem methods for rationale. This patch converts all cftype file operations to take @css instead of @cgroup. cftypes for the cgroup core files don't have their subsytem pointer set. These will automatically use the dummy_css added by the previous patch and can be converted the same way. Most subsystem conversions are straight forwards but there are some interesting ones. * freezer: update_if_frozen() is also converted to take @css instead of @cgroup for consistency. This will make the code look simpler too once iterators are converted to use css. * memory/vmpressure: mem_cgroup_from_css() needs to be exported to vmpressure while mem_cgroup_from_cont() can be made static. Updated accordingly. * cpu: cgroup_tg() doesn't have any user left. Removed. * cpuacct: cgroup_ca() doesn't have any user left. Removed. * hugetlb: hugetlb_cgroup_form_cgroup() doesn't have any user left. Removed. * net_cls: cgrp_cls_state() doesn't have any user left. Removed. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Daniel Wagner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe Cc: Steven Rostedt --- block/blk-cgroup.c | 6 +- block/blk-throttle.c | 32 ++++----- block/cfq-iosched.c | 90 ++++++++++++------------- include/linux/cgroup.h | 24 ++++--- include/linux/memcontrol.h | 2 +- kernel/cgroup.c | 162 +++++++++++++++++++++++---------------------- kernel/cgroup_freezer.c | 40 +++++------ kernel/cpuset.c | 35 +++++----- kernel/sched/core.c | 65 +++++++++--------- kernel/sched/cpuacct.c | 28 +++----- mm/hugetlb_cgroup.c | 26 +++----- mm/memcontrol.c | 88 ++++++++++++------------ mm/vmpressure.c | 4 +- net/core/netprio_cgroup.c | 10 ++- net/ipv4/tcp_memcontrol.c | 12 ++-- net/sched/cls_cgroup.c | 14 ++-- security/device_cgroup.c | 12 ++-- 17 files changed, 322 insertions(+), 328 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 34063739745b..f46f3c69179c 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -437,10 +437,10 @@ struct request_list *__blk_queue_next_rl(struct request_list *rl, return &blkg->rl; } -static int blkcg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, - u64 val) +static int blkcg_reset_stats(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 val) { - struct blkcg *blkcg = cgroup_to_blkcg(cgroup); + struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 08a32dfd3844..88bcfb651b0b 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1293,10 +1293,10 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf, return __blkg_prfill_rwstat(sf, pd, &rwstat); } -static int tg_print_cpu_rwstat(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int tg_print_cpu_rwstat(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); blkcg_print_blkgs(sf, blkcg, tg_prfill_cpu_rwstat, &blkcg_policy_throtl, cft->private, true); @@ -1325,26 +1325,26 @@ static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd, return __blkg_prfill_u64(sf, pd, v); } -static int tg_print_conf_u64(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int tg_print_conf_u64(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), tg_prfill_conf_u64, + blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_u64, &blkcg_policy_throtl, cft->private, false); return 0; } -static int tg_print_conf_uint(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int tg_print_conf_uint(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), tg_prfill_conf_uint, + blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_uint, &blkcg_policy_throtl, cft->private, false); return 0; } -static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf, - bool is_u64) +static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft, + const char *buf, bool is_u64) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); struct blkg_conf_ctx ctx; struct throtl_grp *tg; struct throtl_service_queue *sq; @@ -1403,16 +1403,16 @@ static int tg_set_conf(struct cgroup *cgrp, struct cftype *cft, const char *buf, return 0; } -static int tg_set_conf_u64(struct cgroup *cgrp, struct cftype *cft, +static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft, const char *buf) { - return tg_set_conf(cgrp, cft, buf, true); + return tg_set_conf(css, cft, buf, true); } -static int tg_set_conf_uint(struct cgroup *cgrp, struct cftype *cft, +static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft, const char *buf) { - return tg_set_conf(cgrp, cft, buf, false); + return tg_set_conf(css, cft, buf, false); } static struct cftype throtl_files[] = { diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index d5bbdcfd0dab..dabb9d02cf9a 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1607,12 +1607,11 @@ static u64 cfqg_prfill_weight_device(struct seq_file *sf, return __blkg_prfill_u64(sf, pd, cfqg->dev_weight); } -static int cfqg_print_weight_device(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int cfqg_print_weight_device(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), - cfqg_prfill_weight_device, &blkcg_policy_cfq, 0, - false); + blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_weight_device, + &blkcg_policy_cfq, 0, false); return 0; } @@ -1626,35 +1625,34 @@ static u64 cfqg_prfill_leaf_weight_device(struct seq_file *sf, return __blkg_prfill_u64(sf, pd, cfqg->dev_leaf_weight); } -static int cfqg_print_leaf_weight_device(struct cgroup *cgrp, +static int cfqg_print_leaf_weight_device(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *sf) { - blkcg_print_blkgs(sf, cgroup_to_blkcg(cgrp), - cfqg_prfill_leaf_weight_device, &blkcg_policy_cfq, 0, - false); + blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_leaf_weight_device, + &blkcg_policy_cfq, 0, false); return 0; } -static int cfq_print_weight(struct cgroup *cgrp, struct cftype *cft, +static int cfq_print_weight(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *sf) { - seq_printf(sf, "%u\n", cgroup_to_blkcg(cgrp)->cfq_weight); + seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_weight); return 0; } -static int cfq_print_leaf_weight(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int cfq_print_leaf_weight(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - seq_printf(sf, "%u\n", - cgroup_to_blkcg(cgrp)->cfq_leaf_weight); + seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_leaf_weight); return 0; } -static int __cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft, - const char *buf, bool is_leaf_weight) +static int __cfqg_set_weight_device(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buf, + bool is_leaf_weight) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); struct blkg_conf_ctx ctx; struct cfq_group *cfqg; int ret; @@ -1680,22 +1678,22 @@ static int __cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft, return ret; } -static int cfqg_set_weight_device(struct cgroup *cgrp, struct cftype *cft, - const char *buf) +static int cfqg_set_weight_device(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buf) { - return __cfqg_set_weight_device(cgrp, cft, buf, false); + return __cfqg_set_weight_device(css, cft, buf, false); } -static int cfqg_set_leaf_weight_device(struct cgroup *cgrp, struct cftype *cft, - const char *buf) +static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buf) { - return __cfqg_set_weight_device(cgrp, cft, buf, true); + return __cfqg_set_weight_device(css, cft, buf, true); } -static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val, - bool is_leaf_weight) +static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val, bool is_leaf_weight) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX) @@ -1727,30 +1725,32 @@ static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val, return 0; } -static int cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val) +static int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val) { - return __cfq_set_weight(cgrp, cft, val, false); + return __cfq_set_weight(css, cft, val, false); } -static int cfq_set_leaf_weight(struct cgroup *cgrp, struct cftype *cft, u64 val) +static int cfq_set_leaf_weight(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) { - return __cfq_set_weight(cgrp, cft, val, true); + return __cfq_set_weight(css, cft, val, true); } -static int cfqg_print_stat(struct cgroup *cgrp, struct cftype *cft, +static int cfqg_print_stat(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *sf) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); blkcg_print_blkgs(sf, blkcg, blkg_prfill_stat, &blkcg_policy_cfq, cft->private, false); return 0; } -static int cfqg_print_rwstat(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int cfqg_print_rwstat(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); blkcg_print_blkgs(sf, blkcg, blkg_prfill_rwstat, &blkcg_policy_cfq, cft->private, true); @@ -1773,20 +1773,20 @@ static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf, return __blkg_prfill_rwstat(sf, pd, &sum); } -static int cfqg_print_stat_recursive(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int cfqg_print_stat_recursive(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); blkcg_print_blkgs(sf, blkcg, cfqg_prfill_stat_recursive, &blkcg_policy_cfq, cft->private, false); return 0; } -static int cfqg_print_rwstat_recursive(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int cfqg_print_rwstat_recursive(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); blkcg_print_blkgs(sf, blkcg, cfqg_prfill_rwstat_recursive, &blkcg_policy_cfq, cft->private, true); @@ -1810,10 +1810,10 @@ static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf, } /* print avg_queue_size */ -static int cfqg_print_avg_queue_size(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *sf) +static int cfqg_print_avg_queue_size(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *sf) { - struct blkcg *blkcg = cgroup_to_blkcg(cgrp); + struct blkcg *blkcg = css_to_blkcg(css); blkcg_print_blkgs(sf, blkcg, cfqg_prfill_avg_queue_size, &blkcg_policy_cfq, 0, false); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b0d5f53ae5e1..0b91436c68ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -439,34 +439,34 @@ struct cftype { struct cgroup_subsys *ss; int (*open)(struct inode *inode, struct file *file); - ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*read)(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, char __user *buf, size_t nbytes, loff_t *ppos); /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ - u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft); + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ - s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft); + s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); /* * read_map() is used for defining a map of key/value * pairs. It should call cb->fill(cb, key, value) for each * entry. The key/value pairs (and their ordering) should not * change between reboots. */ - int (*read_map)(struct cgroup *cgrp, struct cftype *cft, + int (*read_map)(struct cgroup_subsys_state *css, struct cftype *cft, struct cgroup_map_cb *cb); /* * read_seq_string() is used for outputting a simple sequence * using seqfile. */ - int (*read_seq_string)(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *m); + int (*read_seq_string)(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m); - ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, + ssize_t (*write)(struct cgroup_subsys_state *css, struct cftype *cft, struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos); @@ -475,18 +475,20 @@ struct cftype { * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ - int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val); + int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val); /* * write_s64() is a signed version of write_u64() */ - int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val); + int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); /* * write_string() is passed a nul-terminated kernelspace * buffer of maximum length determined by max_write_len. * Returns 0 or -ve error code. */ - int (*write_string)(struct cgroup *cgrp, struct cftype *cft, + int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer); /* * trigger() callback can be used to get some kick from the @@ -494,7 +496,7 @@ struct cftype { * at all. The private field can be used to determine the * kick type for multiplexing. */ - int (*trigger)(struct cgroup *cgrp, unsigned int event); + int (*trigger)(struct cgroup_subsys_state *css, unsigned int event); int (*release)(struct inode *inode, struct file *file); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7b4d9d79570b..6c416092e324 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -85,7 +85,7 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm); extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont); +extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); static inline bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c049992f1ffa..6ee469837fda 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2235,34 +2235,38 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); -static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid) +static int cgroup_tasks_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 pid) { - return attach_task_by_pid(cgrp, pid, false); + return attach_task_by_pid(css->cgroup, pid, false); } -static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid) +static int cgroup_procs_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 tgid) { - return attach_task_by_pid(cgrp, tgid, true); + return attach_task_by_pid(css->cgroup, tgid, true); } -static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft, - const char *buffer) +static int cgroup_release_agent_write(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buffer) { - BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + BUILD_BUG_ON(sizeof(css->cgroup->root->release_agent_path) < PATH_MAX); if (strlen(buffer) >= PATH_MAX) return -EINVAL; - if (!cgroup_lock_live_group(cgrp)) + if (!cgroup_lock_live_group(css->cgroup)) return -ENODEV; mutex_lock(&cgroup_root_mutex); - strcpy(cgrp->root->release_agent_path, buffer); + strcpy(css->cgroup->root->release_agent_path, buffer); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); return 0; } -static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *seq) +static int cgroup_release_agent_show(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *seq) { + struct cgroup *cgrp = css->cgroup; + if (!cgroup_lock_live_group(cgrp)) return -ENODEV; seq_puts(seq, cgrp->root->release_agent_path); @@ -2271,10 +2275,10 @@ static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft, return 0; } -static int cgroup_sane_behavior_show(struct cgroup *cgrp, struct cftype *cft, - struct seq_file *seq) +static int cgroup_sane_behavior_show(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *seq) { - seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp)); + seq_printf(seq, "%d\n", cgroup_sane_behavior(css->cgroup)); return 0; } @@ -2292,10 +2296,10 @@ static struct cgroup_subsys_state *cgroup_file_css(struct cfent *cfe) /* A buffer size big enough for numbers or short strings */ #define CGROUP_LOCAL_BUFFER_SIZE 64 -static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft, - struct file *file, - const char __user *userbuf, - size_t nbytes, loff_t *unused_ppos) +static ssize_t cgroup_write_X64(struct cgroup_subsys_state *css, + struct cftype *cft, struct file *file, + const char __user *userbuf, size_t nbytes, + loff_t *unused_ppos) { char buffer[CGROUP_LOCAL_BUFFER_SIZE]; int retval = 0; @@ -2313,22 +2317,22 @@ static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft, u64 val = simple_strtoull(strstrip(buffer), &end, 0); if (*end) return -EINVAL; - retval = cft->write_u64(cgrp, cft, val); + retval = cft->write_u64(css, cft, val); } else { s64 val = simple_strtoll(strstrip(buffer), &end, 0); if (*end) return -EINVAL; - retval = cft->write_s64(cgrp, cft, val); + retval = cft->write_s64(css, cft, val); } if (!retval) retval = nbytes; return retval; } -static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft, - struct file *file, - const char __user *userbuf, - size_t nbytes, loff_t *unused_ppos) +static ssize_t cgroup_write_string(struct cgroup_subsys_state *css, + struct cftype *cft, struct file *file, + const char __user *userbuf, size_t nbytes, + loff_t *unused_ppos) { char local_buffer[CGROUP_LOCAL_BUFFER_SIZE]; int retval = 0; @@ -2351,7 +2355,7 @@ static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft, } buffer[nbytes] = 0; /* nul-terminate */ - retval = cft->write_string(cgrp, cft, strstrip(buffer)); + retval = cft->write_string(css, cft, strstrip(buffer)); if (!retval) retval = nbytes; out: @@ -2361,60 +2365,60 @@ out: } static ssize_t cgroup_file_write(struct file *file, const char __user *buf, - size_t nbytes, loff_t *ppos) + size_t nbytes, loff_t *ppos) { + struct cfent *cfe = __d_cfe(file->f_dentry); struct cftype *cft = __d_cft(file->f_dentry); - struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); + struct cgroup_subsys_state *css = cgroup_file_css(cfe); if (cft->write) - return cft->write(cgrp, cft, file, buf, nbytes, ppos); + return cft->write(css, cft, file, buf, nbytes, ppos); if (cft->write_u64 || cft->write_s64) - return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos); + return cgroup_write_X64(css, cft, file, buf, nbytes, ppos); if (cft->write_string) - return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos); + return cgroup_write_string(css, cft, file, buf, nbytes, ppos); if (cft->trigger) { - int ret = cft->trigger(cgrp, (unsigned int)cft->private); + int ret = cft->trigger(css, (unsigned int)cft->private); return ret ? ret : nbytes; } return -EINVAL; } -static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft, - struct file *file, - char __user *buf, size_t nbytes, - loff_t *ppos) +static ssize_t cgroup_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft, struct file *file, + char __user *buf, size_t nbytes, loff_t *ppos) { char tmp[CGROUP_LOCAL_BUFFER_SIZE]; - u64 val = cft->read_u64(cgrp, cft); + u64 val = cft->read_u64(css, cft); int len = sprintf(tmp, "%llu\n", (unsigned long long) val); return simple_read_from_buffer(buf, nbytes, ppos, tmp, len); } -static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft, - struct file *file, - char __user *buf, size_t nbytes, - loff_t *ppos) +static ssize_t cgroup_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft, struct file *file, + char __user *buf, size_t nbytes, loff_t *ppos) { char tmp[CGROUP_LOCAL_BUFFER_SIZE]; - s64 val = cft->read_s64(cgrp, cft); + s64 val = cft->read_s64(css, cft); int len = sprintf(tmp, "%lld\n", (long long) val); return simple_read_from_buffer(buf, nbytes, ppos, tmp, len); } static ssize_t cgroup_file_read(struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos) + size_t nbytes, loff_t *ppos) { + struct cfent *cfe = __d_cfe(file->f_dentry); struct cftype *cft = __d_cft(file->f_dentry); - struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); + struct cgroup_subsys_state *css = cgroup_file_css(cfe); if (cft->read) - return cft->read(cgrp, cft, file, buf, nbytes, ppos); + return cft->read(css, cft, file, buf, nbytes, ppos); if (cft->read_u64) - return cgroup_read_u64(cgrp, cft, file, buf, nbytes, ppos); + return cgroup_read_u64(css, cft, file, buf, nbytes, ppos); if (cft->read_s64) - return cgroup_read_s64(cgrp, cft, file, buf, nbytes, ppos); + return cgroup_read_s64(css, cft, file, buf, nbytes, ppos); return -EINVAL; } @@ -2433,16 +2437,16 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg) { struct cfent *cfe = m->private; struct cftype *cft = cfe->type; - struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent); + struct cgroup_subsys_state *css = cgroup_file_css(cfe); if (cft->read_map) { struct cgroup_map_cb cb = { .fill = cgroup_map_add, .state = m, }; - return cft->read_map(cgrp, cft, &cb); + return cft->read_map(css, cft, &cb); } - return cft->read_seq_string(cgrp, cft, m); + return cft->read_seq_string(css, cft, m); } static const struct file_operations cgroup_seqfile_operations = { @@ -3860,21 +3864,20 @@ static int cgroup_procs_open(struct inode *unused, struct file *file) return cgroup_pidlist_open(file, CGROUP_FILE_PROCS); } -static u64 cgroup_read_notify_on_release(struct cgroup *cgrp, - struct cftype *cft) +static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft) { - return notify_on_release(cgrp); + return notify_on_release(css->cgroup); } -static int cgroup_write_notify_on_release(struct cgroup *cgrp, - struct cftype *cft, - u64 val) +static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) { - clear_bit(CGRP_RELEASABLE, &cgrp->flags); + clear_bit(CGRP_RELEASABLE, &css->cgroup->flags); if (val) - set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); + set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else - clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); + clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); return 0; } @@ -3972,9 +3975,10 @@ static void cgroup_event_ptable_queue_proc(struct file *file, * Input must be in format ' '. * Interpretation of args is defined by control file implementation. */ -static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, - const char *buffer) +static int cgroup_write_event_control(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buffer) { + struct cgroup *cgrp = css->cgroup; struct cgroup_event *event; struct cgroup *cgrp_cfile; unsigned int efd, cfd; @@ -4082,20 +4086,19 @@ out_kfree: return ret; } -static u64 cgroup_clone_children_read(struct cgroup *cgrp, - struct cftype *cft) +static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); + return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); } -static int cgroup_clone_children_write(struct cgroup *cgrp, - struct cftype *cft, - u64 val) +static int cgroup_clone_children_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) { if (val) - set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); else - clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); + clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); return 0; } @@ -5585,17 +5588,19 @@ static void debug_css_free(struct cgroup_subsys_state *css) kfree(css); } -static u64 debug_taskcount_read(struct cgroup *cgrp, struct cftype *cft) +static u64 debug_taskcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - return cgroup_task_count(cgrp); + return cgroup_task_count(css->cgroup); } -static u64 current_css_set_read(struct cgroup *cgrp, struct cftype *cft) +static u64 current_css_set_read(struct cgroup_subsys_state *css, + struct cftype *cft) { return (u64)(unsigned long)current->cgroups; } -static u64 current_css_set_refcount_read(struct cgroup *cgrp, +static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, struct cftype *cft) { u64 count; @@ -5606,7 +5611,7 @@ static u64 current_css_set_refcount_read(struct cgroup *cgrp, return count; } -static int current_css_set_cg_links_read(struct cgroup *cgrp, +static int current_css_set_cg_links_read(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *seq) { @@ -5633,14 +5638,13 @@ static int current_css_set_cg_links_read(struct cgroup *cgrp, } #define MAX_TASKS_SHOWN_PER_CSS 25 -static int cgroup_css_links_read(struct cgroup *cgrp, - struct cftype *cft, - struct seq_file *seq) +static int cgroup_css_links_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *seq) { struct cgrp_cset_link *link; read_lock(&css_set_lock); - list_for_each_entry(link, &cgrp->cset_links, cset_link) { + list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { struct css_set *cset = link->cset; struct task_struct *task; int count = 0; @@ -5659,9 +5663,9 @@ static int cgroup_css_links_read(struct cgroup *cgrp, return 0; } -static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft) +static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) { - return test_bit(CGRP_RELEASABLE, &cgrp->flags); + return test_bit(CGRP_RELEASABLE, &css->cgroup->flags); } static struct cftype debug_files[] = { diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index f03a85719c3c..19613ba51444 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -245,7 +245,7 @@ out: /** * update_if_frozen - update whether a cgroup finished freezing - * @cgroup: cgroup of interest + * @css: css of interest * * Once FREEZING is initiated, transition to FROZEN is lazily updated by * calling this function. If the current state is FREEZING but not FROZEN, @@ -256,12 +256,12 @@ out: * update_if_frozen() on all descendants prior to invoking this function. * * Task states and freezer state might disagree while tasks are being - * migrated into or out of @cgroup, so we can't verify task states against + * migrated into or out of @css, so we can't verify task states against * @freezer state here. See freezer_attach() for details. */ -static void update_if_frozen(struct cgroup *cgroup) +static void update_if_frozen(struct cgroup_subsys_state *css) { - struct freezer *freezer = cgroup_freezer(cgroup); + struct freezer *freezer = css_freezer(css); struct cgroup *pos; struct cgroup_iter it; struct task_struct *task; @@ -275,7 +275,7 @@ static void update_if_frozen(struct cgroup *cgroup) goto out_unlock; /* are all (live) children frozen? */ - cgroup_for_each_child(pos, cgroup) { + cgroup_for_each_child(pos, css->cgroup) { struct freezer *child = cgroup_freezer(pos); if ((child->state & CGROUP_FREEZER_ONLINE) && @@ -284,9 +284,9 @@ static void update_if_frozen(struct cgroup *cgroup) } /* are all tasks frozen? */ - cgroup_iter_start(cgroup, &it); + cgroup_iter_start(css->cgroup, &it); - while ((task = cgroup_iter_next(cgroup, &it))) { + while ((task = cgroup_iter_next(css->cgroup, &it))) { if (freezing(task)) { /* * freezer_should_skip() indicates that the task @@ -301,12 +301,12 @@ static void update_if_frozen(struct cgroup *cgroup) freezer->state |= CGROUP_FROZEN; out_iter_end: - cgroup_iter_end(cgroup, &it); + cgroup_iter_end(css->cgroup, &it); out_unlock: spin_unlock_irq(&freezer->lock); } -static int freezer_read(struct cgroup *cgroup, struct cftype *cft, +static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *m) { struct cgroup *pos; @@ -314,13 +314,13 @@ static int freezer_read(struct cgroup *cgroup, struct cftype *cft, rcu_read_lock(); /* update states bottom-up */ - cgroup_for_each_descendant_post(pos, cgroup) - update_if_frozen(pos); - update_if_frozen(cgroup); + cgroup_for_each_descendant_post(pos, css->cgroup) + update_if_frozen(cgroup_css(pos, freezer_subsys_id)); + update_if_frozen(css); rcu_read_unlock(); - seq_puts(m, freezer_state_strs(cgroup_freezer(cgroup)->state)); + seq_puts(m, freezer_state_strs(css_freezer(css)->state)); seq_putc(m, '\n'); return 0; } @@ -426,7 +426,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) rcu_read_unlock(); } -static int freezer_write(struct cgroup *cgroup, struct cftype *cft, +static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer) { bool freeze; @@ -438,20 +438,22 @@ static int freezer_write(struct cgroup *cgroup, struct cftype *cft, else return -EINVAL; - freezer_change_state(cgroup_freezer(cgroup), freeze); + freezer_change_state(css_freezer(css), freeze); return 0; } -static u64 freezer_self_freezing_read(struct cgroup *cgroup, struct cftype *cft) +static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct freezer *freezer = cgroup_freezer(cgroup); + struct freezer *freezer = css_freezer(css); return (bool)(freezer->state & CGROUP_FREEZING_SELF); } -static u64 freezer_parent_freezing_read(struct cgroup *cgroup, struct cftype *cft) +static u64 freezer_parent_freezing_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct freezer *freezer = cgroup_freezer(cgroup); + struct freezer *freezer = css_freezer(css); return (bool)(freezer->state & CGROUP_FREEZING_PARENT); } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 8ce3fdc3dfcc..89b76e1d3aa1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1603,9 +1603,10 @@ typedef enum { FILE_SPREAD_SLAB, } cpuset_filetype_t; -static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val) +static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; @@ -1650,9 +1651,10 @@ out_unlock: return retval; } -static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val) +static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; @@ -1676,10 +1678,10 @@ out_unlock: /* * Common handling for a write to a "cpus" or "mems" file. */ -static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, - const char *buf) +static int cpuset_write_resmask(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buf) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); struct cpuset *trialcs; int retval = -ENODEV; @@ -1758,13 +1760,12 @@ static size_t cpuset_sprintf_memlist(char *page, struct cpuset *cs) return count; } -static ssize_t cpuset_common_file_read(struct cgroup *cgrp, - struct cftype *cft, - struct file *file, - char __user *buf, - size_t nbytes, loff_t *ppos) +static ssize_t cpuset_common_file_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct file *file, + char __user *buf, size_t nbytes, + loff_t *ppos) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; char *page; ssize_t retval = 0; @@ -1794,9 +1795,9 @@ out: return retval; } -static u64 cpuset_read_u64(struct cgroup *cgrp, struct cftype *cft) +static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_CPU_EXCLUSIVE: @@ -1825,9 +1826,9 @@ static u64 cpuset_read_u64(struct cgroup *cgrp, struct cftype *cft) return 0; } -static s64 cpuset_read_s64(struct cgroup *cgrp, struct cftype *cft) +static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { - struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 622b7efc5ade..cc9a49266382 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7088,12 +7088,6 @@ static inline struct task_group *css_tg(struct cgroup_subsys_state *css) return css ? container_of(css, struct task_group, css) : NULL; } -/* return corresponding task_group object of a cgroup */ -static inline struct task_group *cgroup_tg(struct cgroup *cgrp) -{ - return css_tg(cgroup_css(cgrp, cpu_cgroup_subsys_id)); -} - static struct cgroup_subsys_state * cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -7179,15 +7173,16 @@ static void cpu_cgroup_exit(struct cgroup_subsys_state *css, } #ifdef CONFIG_FAIR_GROUP_SCHED -static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, - u64 shareval) +static int cpu_shares_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 shareval) { - return sched_group_set_shares(cgroup_tg(cgrp), scale_load(shareval)); + return sched_group_set_shares(css_tg(css), scale_load(shareval)); } -static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); return (u64) scale_load_down(tg->shares); } @@ -7309,26 +7304,28 @@ long tg_get_cfs_period(struct task_group *tg) return cfs_period_us; } -static s64 cpu_cfs_quota_read_s64(struct cgroup *cgrp, struct cftype *cft) +static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) { - return tg_get_cfs_quota(cgroup_tg(cgrp)); + return tg_get_cfs_quota(css_tg(css)); } -static int cpu_cfs_quota_write_s64(struct cgroup *cgrp, struct cftype *cftype, - s64 cfs_quota_us) +static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css, + struct cftype *cftype, s64 cfs_quota_us) { - return tg_set_cfs_quota(cgroup_tg(cgrp), cfs_quota_us); + return tg_set_cfs_quota(css_tg(css), cfs_quota_us); } -static u64 cpu_cfs_period_read_u64(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - return tg_get_cfs_period(cgroup_tg(cgrp)); + return tg_get_cfs_period(css_tg(css)); } -static int cpu_cfs_period_write_u64(struct cgroup *cgrp, struct cftype *cftype, - u64 cfs_period_us) +static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 cfs_period_us) { - return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us); + return tg_set_cfs_period(css_tg(css), cfs_period_us); } struct cfs_schedulable_data { @@ -7409,10 +7406,10 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) return ret; } -static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft, +static int cpu_stats_show(struct cgroup_subsys_state *css, struct cftype *cft, struct cgroup_map_cb *cb) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; cb->fill(cb, "nr_periods", cfs_b->nr_periods); @@ -7425,26 +7422,28 @@ static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft, #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED -static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, - s64 val) +static int cpu_rt_runtime_write(struct cgroup_subsys_state *css, + struct cftype *cft, s64 val) { - return sched_group_set_rt_runtime(cgroup_tg(cgrp), val); + return sched_group_set_rt_runtime(css_tg(css), val); } -static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft) +static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - return sched_group_rt_runtime(cgroup_tg(cgrp)); + return sched_group_rt_runtime(css_tg(css)); } -static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype, - u64 rt_period_us) +static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 rt_period_us) { - return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us); + return sched_group_set_rt_period(css_tg(css), rt_period_us); } -static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, + struct cftype *cft) { - return sched_group_rt_period(cgroup_tg(cgrp)); + return sched_group_rt_period(css_tg(css)); } #endif /* CONFIG_RT_GROUP_SCHED */ diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index 1b784d9b3630..f64722ff0299 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -38,12 +38,6 @@ static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css) return css ? container_of(css, struct cpuacct, css) : NULL; } -/* return cpu accounting group corresponding to this container */ -static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) -{ - return css_ca(cgroup_css(cgrp, cpuacct_subsys_id)); -} - /* return cpu accounting group to which this task belongs */ static inline struct cpuacct *task_ca(struct task_struct *tsk) { @@ -138,9 +132,9 @@ static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) } /* return total cpu usage (in nanoseconds) of a group */ -static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) +static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); u64 totalcpuusage = 0; int i; @@ -150,10 +144,10 @@ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) return totalcpuusage; } -static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, - u64 reset) +static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft, + u64 reset) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); int err = 0; int i; @@ -169,10 +163,10 @@ out: return err; } -static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, - struct seq_file *m) +static int cpuacct_percpu_seq_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m) { - struct cpuacct *ca = cgroup_ca(cgroup); + struct cpuacct *ca = css_ca(css); u64 percpu; int i; @@ -189,10 +183,10 @@ static const char * const cpuacct_stat_desc[] = { [CPUACCT_STAT_SYSTEM] = "system", }; -static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, - struct cgroup_map_cb *cb) +static int cpuacct_stats_show(struct cgroup_subsys_state *css, + struct cftype *cft, struct cgroup_map_cb *cb) { - struct cpuacct *ca = cgroup_ca(cgrp); + struct cpuacct *ca = css_ca(css); int cpu; s64 val = 0; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index e2132435060f..bda8e44f6fde 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -39,12 +39,6 @@ struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) return s ? container_of(s, struct hugetlb_cgroup, css) : NULL; } -static inline -struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup) -{ - return hugetlb_cgroup_from_css(cgroup_css(cgroup, hugetlb_subsys_id)); -} - static inline struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) { @@ -248,14 +242,15 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, return; } -static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft, - struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos) +static ssize_t hugetlb_cgroup_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct file *file, + char __user *buf, size_t nbytes, + loff_t *ppos) { u64 val; char str[64]; int idx, name, len; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); idx = MEMFILE_IDX(cft->private); name = MEMFILE_ATTR(cft->private); @@ -265,12 +260,12 @@ static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft, return simple_read_from_buffer(buf, nbytes, ppos, str, len); } -static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, - const char *buffer) +static int hugetlb_cgroup_write(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buffer) { int idx, name, ret; unsigned long long val; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); idx = MEMFILE_IDX(cft->private); name = MEMFILE_ATTR(cft->private); @@ -295,10 +290,11 @@ static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, return ret; } -static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event) +static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css, + unsigned int event) { int idx, name, ret = 0; - struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); idx = MEMFILE_IDX(event); name = MEMFILE_ATTR(event); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 32cca0f0af0d..ab64dfc84f8c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -483,7 +483,6 @@ enum res_type { */ static DEFINE_MUTEX(memcg_create_mutex); -static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) { return s ? container_of(s, struct mem_cgroup, css) : NULL; @@ -1035,7 +1034,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) preempt_enable(); } -struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) +static inline struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) { return mem_cgroup_from_css(cgroup_css(cont, mem_cgroup_subsys_id)); } @@ -2951,10 +2950,10 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) } #ifdef CONFIG_SLABINFO -static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft, - struct seq_file *m) +static int mem_cgroup_slabinfo_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct memcg_cache_params *params; if (!memcg_can_account_kmem(memcg)) @@ -4999,9 +4998,10 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) return 0; } -static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) +static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css, + unsigned int event) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); int ret; if (mem_cgroup_is_root(memcg)) @@ -5014,16 +5014,17 @@ static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) } -static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft) +static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - return mem_cgroup_from_cont(cont)->use_hierarchy; + return mem_cgroup_from_css(css)->use_hierarchy; } -static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, - u64 val) +static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) { int retval = 0; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css)); mutex_lock(&memcg_create_mutex); @@ -5094,11 +5095,11 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) return val << PAGE_SHIFT; } -static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft, - struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos) +static ssize_t mem_cgroup_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct file *file, + char __user *buf, size_t nbytes, loff_t *ppos) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); char str[64]; u64 val; int name, len; @@ -5131,11 +5132,11 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft, return simple_read_from_buffer(buf, nbytes, ppos, str, len); } -static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) +static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val) { int ret = -EINVAL; #ifdef CONFIG_MEMCG_KMEM - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); /* * For simplicity, we won't allow this to be disabled. It also can't * be changed if the cgroup has children already, or if tasks had @@ -5151,7 +5152,7 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) mutex_lock(&memcg_create_mutex); mutex_lock(&set_limit_mutex); if (!memcg->kmem_account_flags && val != RESOURCE_MAX) { - if (cgroup_task_count(cont) || memcg_has_children(memcg)) { + if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) { ret = -EBUSY; goto out; } @@ -5221,10 +5222,10 @@ out: * The user of this function is... * RES_LIMIT. */ -static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, +static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); enum res_type type; int name; unsigned long long val; @@ -5248,7 +5249,7 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, else if (type == _MEMSWAP) ret = mem_cgroup_resize_memsw_limit(memcg, val); else if (type == _KMEM) - ret = memcg_update_kmem_limit(cont, val); + ret = memcg_update_kmem_limit(css, val); else return -EINVAL; break; @@ -5297,9 +5298,9 @@ out: *memsw_limit = min_memsw_limit; } -static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) +static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); int name; enum res_type type; @@ -5332,17 +5333,17 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) return 0; } -static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp, +static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, struct cftype *cft) { - return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate; + return mem_cgroup_from_css(css)->move_charge_at_immigrate; } #ifdef CONFIG_MMU -static int mem_cgroup_move_charge_write(struct cgroup *cgrp, +static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); if (val >= (1 << NR_MOVE_TYPE)) return -EINVAL; @@ -5357,7 +5358,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, return 0; } #else -static int mem_cgroup_move_charge_write(struct cgroup *cgrp, +static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { return -ENOSYS; @@ -5365,13 +5366,13 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, #endif #ifdef CONFIG_NUMA -static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft, - struct seq_file *m) +static int memcg_numa_stat_show(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m) { int nid; unsigned long total_nr, file_nr, anon_nr, unevictable_nr; unsigned long node_nr; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL); seq_printf(m, "total=%lu", total_nr); @@ -5416,10 +5417,10 @@ static inline void mem_cgroup_lru_names_not_uptodate(void) BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); } -static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, +static int memcg_stat_show(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *m) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *mi; unsigned int i; @@ -5503,17 +5504,18 @@ static int memcg_stat_show(struct cgroup *cont, struct cftype *cft, return 0; } -static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft) +static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); return mem_cgroup_swappiness(memcg); } -static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, - u64 val) +static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); if (val > 100 || !parent) @@ -5829,10 +5831,10 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, spin_unlock(&memcg_oom_lock); } -static int mem_cgroup_oom_control_read(struct cgroup *cgrp, +static int mem_cgroup_oom_control_read(struct cgroup_subsys_state *css, struct cftype *cft, struct cgroup_map_cb *cb) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); cb->fill(cb, "oom_kill_disable", memcg->oom_kill_disable); @@ -5843,10 +5845,10 @@ static int mem_cgroup_oom_control_read(struct cgroup *cgrp, return 0; } -static int mem_cgroup_oom_control_write(struct cgroup *cgrp, +static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css)); /* cannot set to root cgroup and only 0 and 1 are allowed */ diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 7f1654d3cec7..2a8a736e95cc 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -81,8 +81,8 @@ static struct vmpressure *cg_to_vmpressure(struct cgroup *cg) static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { - struct cgroup *cg = vmpressure_to_css(vmpr)->cgroup; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cg); + struct cgroup_subsys_state *css = vmpressure_to_css(vmpr); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); memcg = parent_mem_cgroup(memcg); if (!memcg) diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 8d095b4c2f6f..e00f60e5baea 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -168,15 +168,14 @@ static void cgrp_css_free(struct cgroup_subsys_state *css) kfree(css); } -static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft) +static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { - return cgrp->id; + return css->cgroup->id; } -static int read_priomap(struct cgroup *cont, struct cftype *cft, +static int read_priomap(struct cgroup_subsys_state *css, struct cftype *cft, struct cgroup_map_cb *cb) { - struct cgroup_subsys_state *css = cgroup_css(cont, net_prio_subsys_id); struct net_device *dev; rcu_read_lock(); @@ -186,10 +185,9 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft, return 0; } -static int write_priomap(struct cgroup *cgrp, struct cftype *cft, +static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer) { - struct cgroup_subsys_state *css = cgroup_css(cgrp, net_prio_subsys_id); char devname[IFNAMSIZ + 1]; struct net_device *dev; u32 prio; diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index da14436c1735..8a57d79b0b16 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -132,10 +132,10 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) return 0; } -static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft, +static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, const char *buffer) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); unsigned long long val; int ret = 0; @@ -180,9 +180,9 @@ static u64 tcp_read_usage(struct mem_cgroup *memcg) return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE); } -static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft) +static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); u64 val; switch (cft->private) { @@ -202,13 +202,13 @@ static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft) return val; } -static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event) +static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) { struct mem_cgroup *memcg; struct tcp_memcontrol *tcp; struct cg_proto *cg_proto; - memcg = mem_cgroup_from_cont(cont); + memcg = mem_cgroup_from_css(css); cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) return 0; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index dc3983835893..8ea1184cec92 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -28,11 +28,6 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state return css ? container_of(css, struct cgroup_cls_state, css) : NULL; } -static inline struct cgroup_cls_state *cgrp_cls_state(struct cgroup *cgrp) -{ - return css_cls_state(cgroup_css(cgrp, net_cls_subsys_id)); -} - static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p) { return css_cls_state(task_css(p, net_cls_subsys_id)); @@ -87,14 +82,15 @@ static void cgrp_attach(struct cgroup_subsys_state *css, } } -static u64 read_classid(struct cgroup *cgrp, struct cftype *cft) +static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) { - return cgrp_cls_state(cgrp)->classid; + return css_cls_state(css)->classid; } -static int write_classid(struct cgroup *cgrp, struct cftype *cft, u64 value) +static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, + u64 value) { - cgrp_cls_state(cgrp)->classid = (u32) value; + css_cls_state(css)->classid = (u32) value; return 0; } diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 7293ac49ba7b..e0ca464fa854 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -289,10 +289,10 @@ static void set_majmin(char *str, unsigned m) sprintf(str, "%u", m); } -static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft, - struct seq_file *m) +static int devcgroup_seq_read(struct cgroup_subsys_state *css, + struct cftype *cft, struct seq_file *m) { - struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup); + struct dev_cgroup *devcgroup = css_to_devcgroup(css); struct dev_exception_item *ex; char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN]; @@ -669,13 +669,13 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup, return rc; } -static int devcgroup_access_write(struct cgroup *cgrp, struct cftype *cft, - const char *buffer) +static int devcgroup_access_write(struct cgroup_subsys_state *css, + struct cftype *cft, const char *buffer) { int retval; mutex_lock(&devcgroup_mutex); - retval = devcgroup_update_access(cgroup_to_devcgroup(cgrp), + retval = devcgroup_update_access(css_to_devcgroup(css), cft->private, buffer); mutex_unlock(&devcgroup_mutex); return retval; -- cgit v1.2.3-71-gd317 From 3b287a505ef4024634beb12a93773254909d5dae Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: convert cgroup_next_sibling() to cgroup_next_child() cgroup is transitioning to using css (cgroup_subsys_state) as the main subsys interface handle instead of cgroup and the iterators will be updated to use css too. The iterators need to walk the cgroup hierarchy and return the css's matching the origin css, which is a bit cumbersome to open code. This patch converts cgroup_next_sibling() to cgroup_next_child() so that it can handle all steps of direct child iteration. This will be used to update iterators to take @css instead of @cgrp. In addition to the new iteration init handling, cgroup_next_child() is restructured so that the different branches share the end of iteration condition check. This patch doesn't change any behavior. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 4 ++-- kernel/cgroup.c | 59 +++++++++++++++++++++++++------------------------- 2 files changed, 32 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0b91436c68ef..5f9ba5881717 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -779,7 +779,7 @@ static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) return idr_find(&ss->root->cgroup_idr, id); } -struct cgroup *cgroup_next_sibling(struct cgroup *pos); +struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); /** * cgroup_for_each_child - iterate through children of a cgroup @@ -802,7 +802,7 @@ struct cgroup *cgroup_next_sibling(struct cgroup *pos); #define cgroup_for_each_child(pos, cgrp) \ for ((pos) = list_first_or_null_rcu(&(cgrp)->children, \ struct cgroup, sibling); \ - (pos); (pos) = cgroup_next_sibling((pos))) + (pos); (pos) = cgroup_next_child((pos), (cgrp))) struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 6ee469837fda..dd55244952bd 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3037,15 +3037,16 @@ static void cgroup_enable_task_cg_lists(void) } /** - * cgroup_next_sibling - find the next sibling of a given cgroup - * @pos: the current cgroup + * cgroup_next_child - find the next child of a given cgroup + * @pos: the current position (%NULL to initiate traversal) + * @cgrp: cgroup whose descendants to walk * - * This function returns the next sibling of @pos and should be called - * under RCU read lock. The only requirement is that @pos is accessible. - * The next sibling is guaranteed to be returned regardless of @pos's - * state. + * This function returns the next child of @cgrp and should be called under + * RCU read lock. The only requirement is that @cgrp and @pos are + * accessible. The next sibling is guaranteed to be returned regardless of + * their states. */ -struct cgroup *cgroup_next_sibling(struct cgroup *pos) +struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp) { struct cgroup *next; @@ -3061,30 +3062,30 @@ struct cgroup *cgroup_next_sibling(struct cgroup *pos) * safe to dereference from this RCU critical section. If * ->sibling.next is inaccessible, cgroup_is_dead() is guaranteed * to be visible as %true here. + * + * If @pos is dead, its next pointer can't be dereferenced; + * however, as each cgroup is given a monotonically increasing + * unique serial number and always appended to the sibling list, + * the next one can be found by walking the parent's children until + * we see a cgroup with higher serial number than @pos's. While + * this path can be slower, it's taken only when either the current + * cgroup is removed or iteration and removal race. */ - if (likely(!cgroup_is_dead(pos))) { + if (!pos) { + next = list_entry_rcu(cgrp->children.next, struct cgroup, sibling); + } else if (likely(!cgroup_is_dead(pos))) { next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling); - if (&next->sibling != &pos->parent->children) - return next; - return NULL; + } else { + list_for_each_entry_rcu(next, &cgrp->children, sibling) + if (next->serial_nr > pos->serial_nr) + break; } - /* - * Can't dereference the next pointer. Each cgroup is given a - * monotonically increasing unique serial number and always - * appended to the sibling list, so the next one can be found by - * walking the parent's children until we see a cgroup with higher - * serial number than @pos's. - * - * While this path can be slow, it's taken only when either the - * current cgroup is removed or iteration and removal race. - */ - list_for_each_entry_rcu(next, &pos->parent->children, sibling) - if (next->serial_nr > pos->serial_nr) - return next; + if (&next->sibling != &cgrp->children) + return next; return NULL; } -EXPORT_SYMBOL_GPL(cgroup_next_sibling); +EXPORT_SYMBOL_GPL(cgroup_next_child); /** * cgroup_next_descendant_pre - find the next descendant for pre-order walk @@ -3117,7 +3118,7 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, /* no child, visit my or the closest ancestor's next sibling */ while (pos != cgroup) { - next = cgroup_next_sibling(pos); + next = cgroup_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; @@ -3198,7 +3199,7 @@ struct cgroup *cgroup_next_descendant_post(struct cgroup *pos, } /* if there's an unvisited sibling, visit its leftmost descendant */ - next = cgroup_next_sibling(pos); + next = cgroup_next_child(pos, pos->parent); if (next) return cgroup_leftmost_descendant(next); @@ -4549,9 +4550,9 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) /* * Mark @cgrp dead. This prevents further task migration and child * creation by disabling cgroup_lock_live_group(). Note that - * CGRP_DEAD assertion is depended upon by cgroup_next_sibling() to + * CGRP_DEAD assertion is depended upon by cgroup_next_child() to * resume iteration after dropping RCU read lock. See - * cgroup_next_sibling() for details. + * cgroup_next_child() for details. */ set_bit(CGRP_DEAD, &cgrp->flags); -- cgit v1.2.3-71-gd317 From f48e3924dca268c677c4e338e5d91ad9e6fe6b9e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:24 -0400 Subject: cgroup: always use cgroup_next_child() to walk the children list There are several places where the children list is accessed directly. This patch converts those places to use cgroup_next_child(). This will help updating the hierarchy iterators to use @css instead of @cgrp. While cgroup_next_child() can be heavy in pathological cases - e.g. a lot of dead children, this shouldn't cause any noticeable behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 5 ++--- kernel/cgroup.c | 7 +++---- 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5f9ba5881717..c288bce428f8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -800,9 +800,8 @@ struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); * the start of the next iteration by, for example, bumping the css refcnt. */ #define cgroup_for_each_child(pos, cgrp) \ - for ((pos) = list_first_or_null_rcu(&(cgrp)->children, \ - struct cgroup, sibling); \ - (pos); (pos) = cgroup_next_child((pos), (cgrp))) + for ((pos) = cgroup_next_child(NULL, (cgrp)); (pos); \ + (pos) = cgroup_next_child((pos), (cgrp))) struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index dd55244952bd..2b7354faaca7 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3112,7 +3112,7 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, pos = cgroup; /* visit the first child if exists */ - next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling); + next = cgroup_next_child(NULL, pos); if (next) return next; @@ -3151,7 +3151,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos) last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; - list_for_each_entry_rcu(tmp, &last->children, sibling) + cgroup_for_each_child(tmp, last) pos = tmp; } while (pos); @@ -3165,8 +3165,7 @@ static struct cgroup *cgroup_leftmost_descendant(struct cgroup *pos) do { last = pos; - pos = list_first_or_null_rcu(&pos->children, struct cgroup, - sibling); + pos = cgroup_next_child(NULL, pos); } while (pos); return last; -- cgit v1.2.3-71-gd317 From 492eb21b98f88e411a8bb43d6edcd7d7022add10 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:25 -0400 Subject: cgroup: make hierarchy iterators deal with cgroup_subsys_state instead of cgroup cgroup is currently in the process of transitioning to using css (cgroup_subsys_state) as the primary handle instead of cgroup in subsystem API. For hierarchy iterators, this is beneficial because * In most cases, css is the only thing subsystems care about anyway. * On the planned unified hierarchy, iterations for different subsystems will need to skip over different subtrees of the hierarchy depending on which subsystems are enabled on each cgroup. Passing around css makes it unnecessary to explicitly specify the subsystem in question as css is intersection between cgroup and subsystem * For the planned unified hierarchy, css's would need to be created and destroyed dynamically independent from cgroup hierarchy. Having cgroup core manage css iteration makes enforcing deref rules a lot easier. Most subsystem conversions are straight-forward. Noteworthy changes are * blkio: cgroup_to_blkcg() is no longer used. Removed. * freezer: cgroup_freezer() is no longer used. Removed. * devices: cgroup_to_devcgroup() is no longer used. Removed. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley Cc: Jens Axboe --- block/blk-cgroup.c | 8 +-- block/blk-cgroup.h | 25 ++++----- block/blk-throttle.c | 8 +-- include/linux/cgroup.h | 88 ++++++++++++++++--------------- kernel/cgroup.c | 131 ++++++++++++++++++++++++++--------------------- kernel/cgroup_freezer.c | 25 ++++----- kernel/cpuset.c | 58 ++++++++++----------- mm/memcontrol.c | 20 ++++---- security/device_cgroup.c | 11 ++-- 9 files changed, 187 insertions(+), 187 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index f46f3c69179c..4b40640240a4 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -614,7 +614,7 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off) { struct blkcg_policy *pol = blkcg_policy[pd->plid]; struct blkcg_gq *pos_blkg; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; u64 sum; lockdep_assert_held(pd->blkg->q->queue_lock); @@ -622,7 +622,7 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off) sum = blkg_stat_read((void *)pd + off); rcu_read_lock(); - blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) { + blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) { struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol); struct blkg_stat *stat = (void *)pos_pd + off; @@ -649,7 +649,7 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd, { struct blkcg_policy *pol = blkcg_policy[pd->plid]; struct blkcg_gq *pos_blkg; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; struct blkg_rwstat sum; int i; @@ -658,7 +658,7 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd, sum = blkg_rwstat_read((void *)pd + off); rcu_read_lock(); - blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) { + blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) { struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol); struct blkg_rwstat *rwstat = (void *)pos_pd + off; struct blkg_rwstat tmp; diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index b6802c46d68f..855538630300 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -184,11 +184,6 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) return css ? container_of(css, struct blkcg, css) : NULL; } -static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) -{ - return css_to_blkcg(cgroup_css(cgroup, blkio_subsys_id)); -} - static inline struct blkcg *task_blkcg(struct task_struct *tsk) { return css_to_blkcg(task_css(tsk, blkio_subsys_id)); @@ -289,32 +284,31 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, /** * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant - * @pos_cgrp: used for iteration + * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU * read locked. If called under either blkcg or queue lock, the iteration * is guaranteed to include all and only online blkgs. The caller may - * update @pos_cgrp by calling cgroup_rightmost_descendant() to skip - * subtree. + * update @pos_css by calling css_rightmost_descendant() to skip subtree. */ -#define blkg_for_each_descendant_pre(d_blkg, pos_cgrp, p_blkg) \ - cgroup_for_each_descendant_pre((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \ - if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \ +#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ + css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ + if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) /** * blkg_for_each_descendant_post - post-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant - * @pos_cgrp: used for iteration + * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Similar to blkg_for_each_descendant_pre() but performs post-order * traversal instead. Synchronization rules are the same. */ -#define blkg_for_each_descendant_post(d_blkg, pos_cgrp, p_blkg) \ - cgroup_for_each_descendant_post((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \ - if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \ +#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ + css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ + if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) /** @@ -577,7 +571,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 88bcfb651b0b..8cefa7f8590e 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1349,7 +1349,7 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft, struct throtl_grp *tg; struct throtl_service_queue *sq; struct blkcg_gq *blkg; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; int ret; ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx); @@ -1380,7 +1380,7 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft, * blk-throttle. */ tg_update_has_rules(tg); - blkg_for_each_descendant_pre(blkg, pos_cgrp, ctx.blkg) + blkg_for_each_descendant_pre(blkg, pos_css, ctx.blkg) tg_update_has_rules(blkg_to_tg(blkg)); /* @@ -1623,7 +1623,7 @@ void blk_throtl_drain(struct request_queue *q) { struct throtl_data *td = q->td; struct blkcg_gq *blkg; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; struct bio *bio; int rw; @@ -1636,7 +1636,7 @@ void blk_throtl_drain(struct request_queue *q) * better to walk service_queue tree directly but blkg walk is * easier. */ - blkg_for_each_descendant_post(blkg, pos_cgrp, td->queue->root_blkg) + blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) tg_drain_bios(&blkg_to_tg(blkg)->service_queue); tg_drain_bios(&td_root_tg(td)->service_queue); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c288bce428f8..4bc22f4a1abb 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -779,68 +779,72 @@ static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) return idr_find(&ss->root->cgroup_idr, id); } -struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp); +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent); /** - * cgroup_for_each_child - iterate through children of a cgroup - * @pos: the cgroup * to use as the loop cursor - * @cgrp: cgroup whose children to walk + * css_for_each_child - iterate through children of a css + * @pos: the css * to use as the loop cursor + * @parent: css whose children to walk * - * Walk @cgrp's children. Must be called under rcu_read_lock(). A child - * cgroup which hasn't finished ->css_online() or already has finished + * Walk @parent's children. Must be called under rcu_read_lock(). A child + * css which hasn't finished ->css_online() or already has finished * ->css_offline() may show up during traversal and it's each subsystem's * responsibility to verify that each @pos is alive. * * If a subsystem synchronizes against the parent in its ->css_online() and - * before starting iterating, a cgroup which finished ->css_online() is + * before starting iterating, a css which finished ->css_online() is * guaranteed to be visible in the future iterations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ -#define cgroup_for_each_child(pos, cgrp) \ - for ((pos) = cgroup_next_child(NULL, (cgrp)); (pos); \ - (pos) = cgroup_next_child((pos), (cgrp))) +#define css_for_each_child(pos, parent) \ + for ((pos) = css_next_child(NULL, (parent)); (pos); \ + (pos) = css_next_child((pos), (parent))) -struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, - struct cgroup *cgroup); -struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); +struct cgroup_subsys_state * +css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); + +struct cgroup_subsys_state * +css_rightmost_descendant(struct cgroup_subsys_state *pos); /** - * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_pre - pre-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @root: css whose descendants to walk * - * Walk @cgroup's descendants. Must be called under rcu_read_lock(). A - * descendant cgroup which hasn't finished ->css_online() or already has + * Walk @root's descendants. Must be called under rcu_read_lock(). A + * descendant css which hasn't finished ->css_online() or already has * finished ->css_offline() may show up during traversal and it's each * subsystem's responsibility to verify that each @pos is alive. * * If a subsystem synchronizes against the parent in its ->css_online() and * before starting iterating, and synchronizes against @pos on each - * iteration, any descendant cgroup which finished ->css_online() is + * iteration, any descendant css which finished ->css_online() is * guaranteed to be visible in the future iterations. * * In other words, the following guarantees that a descendant can't escape * state updates of its ancestors. * - * my_online(@cgrp) + * my_online(@css) * { - * Lock @cgrp->parent and @cgrp; - * Inherit state from @cgrp->parent; + * Lock @css's parent and @css; + * Inherit state from the parent; * Unlock both. * } * - * my_update_state(@cgrp) + * my_update_state(@css) * { - * Lock @cgrp; - * Update @cgrp's state; - * Unlock @cgrp; + * Lock @css; + * Update @css's state; + * Unlock @css; * - * cgroup_for_each_descendant_pre(@pos, @cgrp) { + * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; - * Verify @pos is alive and inherit state from @pos->parent; + * Verify @pos is alive and inherit state from @pos's parent; * Unlock @pos; * } * } @@ -851,8 +855,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one - * inheritance happens for any cgroup after the latest update to its - * parent. + * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. @@ -865,25 +868,26 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ -#define cgroup_for_each_descendant_pre(pos, cgroup) \ - for (pos = cgroup_next_descendant_pre(NULL, (cgroup)); (pos); \ - pos = cgroup_next_descendant_pre((pos), (cgroup))) +#define css_for_each_descendant_pre(pos, css) \ + for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ + (pos) = css_next_descendant_pre((pos), (css))) -struct cgroup *cgroup_next_descendant_post(struct cgroup *pos, - struct cgroup *cgroup); +struct cgroup_subsys_state * +css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); /** - * cgroup_for_each_descendant_post - post-order walk of a cgroup's descendants - * @pos: the cgroup * to use as the loop cursor - * @cgroup: cgroup whose descendants to walk + * css_for_each_descendant_post - post-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @css: css whose descendants to walk * - * Similar to cgroup_for_each_descendant_pre() but performs post-order + * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. Note that the walk visibility guarantee described in * pre-order walk doesn't apply the same to post-order walks. */ -#define cgroup_for_each_descendant_post(pos, cgroup) \ - for (pos = cgroup_next_descendant_post(NULL, (cgroup)); (pos); \ - pos = cgroup_next_descendant_post((pos), (cgroup))) +#define css_for_each_descendant_post(pos, css) \ + for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ + (pos) = css_next_descendant_post((pos), (css))) /* A cgroup_iter should be treated as an opaque object */ struct cgroup_iter { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2b7354faaca7..91eac33fac86 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2814,8 +2814,8 @@ static void cgroup_cfts_prepare(void) /* * Thanks to the entanglement with vfs inode locking, we can't walk * the existing cgroups under cgroup_mutex and create files. - * Instead, we use cgroup_for_each_descendant_pre() and drop RCU - * read lock before calling cgroup_addrm_files(). + * Instead, we use css_for_each_descendant_pre() and drop RCU read + * lock before calling cgroup_addrm_files(). */ mutex_lock(&cgroup_mutex); } @@ -2825,10 +2825,11 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) { LIST_HEAD(pending); struct cgroup_subsys *ss = cfts[0].ss; - struct cgroup *cgrp, *root = &ss->root->top_cgroup; + struct cgroup *root = &ss->root->top_cgroup; struct super_block *sb = ss->root->sb; struct dentry *prev = NULL; struct inode *inode; + struct cgroup_subsys_state *css; u64 update_before; int ret = 0; @@ -2861,7 +2862,9 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) /* add/rm files for all cgroups created before */ rcu_read_lock(); - cgroup_for_each_descendant_pre(cgrp, root) { + css_for_each_descendant_pre(css, cgroup_css(root, ss->subsys_id)) { + struct cgroup *cgrp = css->cgroup; + if (cgroup_is_dead(cgrp)) continue; @@ -3037,17 +3040,21 @@ static void cgroup_enable_task_cg_lists(void) } /** - * cgroup_next_child - find the next child of a given cgroup - * @pos: the current position (%NULL to initiate traversal) - * @cgrp: cgroup whose descendants to walk + * css_next_child - find the next child of a given css + * @pos_css: the current position (%NULL to initiate traversal) + * @parent_css: css whose children to walk * - * This function returns the next child of @cgrp and should be called under - * RCU read lock. The only requirement is that @cgrp and @pos are - * accessible. The next sibling is guaranteed to be returned regardless of - * their states. + * This function returns the next child of @parent_css and should be called + * under RCU read lock. The only requirement is that @parent_css and + * @pos_css are accessible. The next sibling is guaranteed to be returned + * regardless of their states. */ -struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp) +struct cgroup_subsys_state * +css_next_child(struct cgroup_subsys_state *pos_css, + struct cgroup_subsys_state *parent_css) { + struct cgroup *pos = pos_css ? pos_css->cgroup : NULL; + struct cgroup *cgrp = parent_css->cgroup; struct cgroup *next; WARN_ON_ONCE(!rcu_read_lock_held()); @@ -3081,59 +3088,64 @@ struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp) break; } - if (&next->sibling != &cgrp->children) - return next; - return NULL; + if (&next->sibling == &cgrp->children) + return NULL; + + if (parent_css->ss) + return cgroup_css(next, parent_css->ss->subsys_id); + else + return &next->dummy_css; } -EXPORT_SYMBOL_GPL(cgroup_next_child); +EXPORT_SYMBOL_GPL(css_next_child); /** - * cgroup_next_descendant_pre - find the next descendant for pre-order walk + * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) - * @cgroup: cgroup whose descendants to walk + * @root: css whose descendants to walk * - * To be used by cgroup_for_each_descendant_pre(). Find the next - * descendant to visit for pre-order traversal of @cgroup's descendants. + * To be used by css_for_each_descendant_pre(). Find the next descendant + * to visit for pre-order traversal of @root's descendants. * * While this function requires RCU read locking, it doesn't require the * whole traversal to be contained in a single RCU critical section. This * function will return the correct next descendant as long as both @pos - * and @cgroup are accessible and @pos is a descendant of @cgroup. + * and @root are accessible and @pos is a descendant of @root. */ -struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, - struct cgroup *cgroup) +struct cgroup_subsys_state * +css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *root) { - struct cgroup *next; + struct cgroup_subsys_state *next; WARN_ON_ONCE(!rcu_read_lock_held()); - /* if first iteration, pretend we just visited @cgroup */ + /* if first iteration, pretend we just visited @root */ if (!pos) - pos = cgroup; + pos = root; /* visit the first child if exists */ - next = cgroup_next_child(NULL, pos); + next = css_next_child(NULL, pos); if (next) return next; /* no child, visit my or the closest ancestor's next sibling */ - while (pos != cgroup) { - next = cgroup_next_child(pos, pos->parent); + while (pos != root) { + next = css_next_child(pos, css_parent(pos)); if (next) return next; - pos = pos->parent; + pos = css_parent(pos); } return NULL; } -EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre); +EXPORT_SYMBOL_GPL(css_next_descendant_pre); /** - * cgroup_rightmost_descendant - return the rightmost descendant of a cgroup - * @pos: cgroup of interest + * css_rightmost_descendant - return the rightmost descendant of a css + * @pos: css of interest * - * Return the rightmost descendant of @pos. If there's no descendant, - * @pos is returned. This can be used during pre-order traversal to skip + * Return the rightmost descendant of @pos. If there's no descendant, @pos + * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires RCU read locking, it doesn't require the @@ -3141,9 +3153,10 @@ EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre); * function will return the correct rightmost descendant as long as @pos is * accessible. */ -struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos) +struct cgroup_subsys_state * +css_rightmost_descendant(struct cgroup_subsys_state *pos) { - struct cgroup *last, *tmp; + struct cgroup_subsys_state *last, *tmp; WARN_ON_ONCE(!rcu_read_lock_held()); @@ -3151,62 +3164,64 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos) last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; - cgroup_for_each_child(tmp, last) + css_for_each_child(tmp, last) pos = tmp; } while (pos); return last; } -EXPORT_SYMBOL_GPL(cgroup_rightmost_descendant); +EXPORT_SYMBOL_GPL(css_rightmost_descendant); -static struct cgroup *cgroup_leftmost_descendant(struct cgroup *pos) +static struct cgroup_subsys_state * +css_leftmost_descendant(struct cgroup_subsys_state *pos) { - struct cgroup *last; + struct cgroup_subsys_state *last; do { last = pos; - pos = cgroup_next_child(NULL, pos); + pos = css_next_child(NULL, pos); } while (pos); return last; } /** - * cgroup_next_descendant_post - find the next descendant for post-order walk + * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) - * @cgroup: cgroup whose descendants to walk + * @root: css whose descendants to walk * - * To be used by cgroup_for_each_descendant_post(). Find the next - * descendant to visit for post-order traversal of @cgroup's descendants. + * To be used by css_for_each_descendant_post(). Find the next descendant + * to visit for post-order traversal of @root's descendants. * * While this function requires RCU read locking, it doesn't require the * whole traversal to be contained in a single RCU critical section. This * function will return the correct next descendant as long as both @pos * and @cgroup are accessible and @pos is a descendant of @cgroup. */ -struct cgroup *cgroup_next_descendant_post(struct cgroup *pos, - struct cgroup *cgroup) +struct cgroup_subsys_state * +css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *root) { - struct cgroup *next; + struct cgroup_subsys_state *next; WARN_ON_ONCE(!rcu_read_lock_held()); /* if first iteration, visit the leftmost descendant */ if (!pos) { - next = cgroup_leftmost_descendant(cgroup); - return next != cgroup ? next : NULL; + next = css_leftmost_descendant(root); + return next != root ? next : NULL; } /* if there's an unvisited sibling, visit its leftmost descendant */ - next = cgroup_next_child(pos, pos->parent); + next = css_next_child(pos, css_parent(pos)); if (next) - return cgroup_leftmost_descendant(next); + return css_leftmost_descendant(next); /* no sibling left, visit parent */ - next = pos->parent; - return next != cgroup ? next : NULL; + next = css_parent(pos); + return next != root ? next : NULL; } -EXPORT_SYMBOL_GPL(cgroup_next_descendant_post); +EXPORT_SYMBOL_GPL(css_next_descendant_post); void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it) __acquires(css_set_lock) @@ -4549,9 +4564,9 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) /* * Mark @cgrp dead. This prevents further task migration and child * creation by disabling cgroup_lock_live_group(). Note that - * CGRP_DEAD assertion is depended upon by cgroup_next_child() to + * CGRP_DEAD assertion is depended upon by css_next_child() to * resume iteration after dropping RCU read lock. See - * cgroup_next_child() for details. + * css_next_child() for details. */ set_bit(CGRP_DEAD, &cgrp->flags); diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 19613ba51444..98ca48d9ceb4 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -50,11 +50,6 @@ static inline struct freezer *css_freezer(struct cgroup_subsys_state *css) return css ? container_of(css, struct freezer, css) : NULL; } -static inline struct freezer *cgroup_freezer(struct cgroup *cgroup) -{ - return css_freezer(cgroup_css(cgroup, freezer_subsys_id)); -} - static inline struct freezer *task_freezer(struct task_struct *task) { return css_freezer(task_css(task, freezer_subsys_id)); @@ -120,7 +115,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css) /* * The following double locking and freezing state inheritance * guarantee that @cgroup can never escape ancestors' freezing - * states. See cgroup_for_each_descendant_pre() for details. + * states. See css_for_each_descendant_pre() for details. */ if (parent) spin_lock_irq(&parent->lock); @@ -262,7 +257,7 @@ out: static void update_if_frozen(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); - struct cgroup *pos; + struct cgroup_subsys_state *pos; struct cgroup_iter it; struct task_struct *task; @@ -275,8 +270,8 @@ static void update_if_frozen(struct cgroup_subsys_state *css) goto out_unlock; /* are all (live) children frozen? */ - cgroup_for_each_child(pos, css->cgroup) { - struct freezer *child = cgroup_freezer(pos); + css_for_each_child(pos, css) { + struct freezer *child = css_freezer(pos); if ((child->state & CGROUP_FREEZER_ONLINE) && !(child->state & CGROUP_FROZEN)) @@ -309,13 +304,13 @@ out_unlock: static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft, struct seq_file *m) { - struct cgroup *pos; + struct cgroup_subsys_state *pos; rcu_read_lock(); /* update states bottom-up */ - cgroup_for_each_descendant_post(pos, css->cgroup) - update_if_frozen(cgroup_css(pos, freezer_subsys_id)); + css_for_each_descendant_post(pos, css) + update_if_frozen(pos); update_if_frozen(css); rcu_read_unlock(); @@ -396,7 +391,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze, */ static void freezer_change_state(struct freezer *freezer, bool freeze) { - struct cgroup *pos; + struct cgroup_subsys_state *pos; /* update @freezer */ spin_lock_irq(&freezer->lock); @@ -409,8 +404,8 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) * CGROUP_FREEZING_PARENT. */ rcu_read_lock(); - cgroup_for_each_descendant_pre(pos, freezer->css.cgroup) { - struct freezer *pos_f = cgroup_freezer(pos); + css_for_each_descendant_pre(pos, &freezer->css) { + struct freezer *pos_f = css_freezer(pos); struct freezer *parent = parent_freezer(pos_f); /* diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 89b76e1d3aa1..be4f5036ea5e 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -210,29 +210,29 @@ static struct cpuset top_cpuset = { /** * cpuset_for_each_child - traverse online children of a cpuset * @child_cs: loop cursor pointing to the current child - * @pos_cgrp: used for iteration + * @pos_css: used for iteration * @parent_cs: target cpuset to walk children of * * Walk @child_cs through the online children of @parent_cs. Must be used * with RCU read locked. */ -#define cpuset_for_each_child(child_cs, pos_cgrp, parent_cs) \ - cgroup_for_each_child((pos_cgrp), (parent_cs)->css.cgroup) \ - if (is_cpuset_online(((child_cs) = cgroup_cs((pos_cgrp))))) +#define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ + css_for_each_child((pos_css), &(parent_cs)->css) \ + if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) /** * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants * @des_cs: loop cursor pointing to the current descendant - * @pos_cgrp: used for iteration + * @pos_css: used for iteration * @root_cs: target cpuset to walk ancestor of * * Walk @des_cs through the online descendants of @root_cs. Must be used - * with RCU read locked. The caller may modify @pos_cgrp by calling - * cgroup_rightmost_descendant() to skip subtree. + * with RCU read locked. The caller may modify @pos_css by calling + * css_rightmost_descendant() to skip subtree. */ -#define cpuset_for_each_descendant_pre(des_cs, pos_cgrp, root_cs) \ - cgroup_for_each_descendant_pre((pos_cgrp), (root_cs)->css.cgroup) \ - if (is_cpuset_online(((des_cs) = cgroup_cs((pos_cgrp))))) +#define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ + css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ + if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* * There are two global mutexes guarding cpuset structures - cpuset_mutex @@ -430,7 +430,7 @@ static void free_trial_cpuset(struct cpuset *trial) static int validate_change(struct cpuset *cur, struct cpuset *trial) { - struct cgroup *cgrp; + struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret; @@ -438,7 +438,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) /* Each of our child cpusets must be a subset of us */ ret = -EBUSY; - cpuset_for_each_child(c, cgrp, cur) + cpuset_for_each_child(c, css, cur) if (!is_cpuset_subset(c, trial)) goto out; @@ -459,7 +459,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) * overlap */ ret = -EINVAL; - cpuset_for_each_child(c, cgrp, par) { + cpuset_for_each_child(c, css, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) @@ -508,13 +508,13 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *root_cs) { struct cpuset *cp; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; rcu_read_lock(); - cpuset_for_each_descendant_pre(cp, pos_cgrp, root_cs) { + cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { - pos_cgrp = cgroup_rightmost_descendant(pos_cgrp); + pos_css = css_rightmost_descendant(pos_css); continue; } @@ -589,7 +589,7 @@ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; doms = NULL; dattr = NULL; @@ -618,7 +618,7 @@ static int generate_sched_domains(cpumask_var_t **domains, csn = 0; rcu_read_lock(); - cpuset_for_each_descendant_pre(cp, pos_cgrp, &top_cpuset) { + cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { /* * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The @@ -635,7 +635,7 @@ static int generate_sched_domains(cpumask_var_t **domains, csa[csn++] = cp; /* skip @cp's subtree */ - pos_cgrp = cgroup_rightmost_descendant(pos_cgrp); + pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); @@ -886,16 +886,16 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs, bool update_root, struct ptr_heap *heap) { struct cpuset *cp; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; if (update_root) update_tasks_cpumask(root_cs, heap); rcu_read_lock(); - cpuset_for_each_descendant_pre(cp, pos_cgrp, root_cs) { + cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp have some CPU */ if (!cpumask_empty(cp->cpus_allowed)) { - pos_cgrp = cgroup_rightmost_descendant(pos_cgrp); + pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget(&cp->css)) @@ -1143,16 +1143,16 @@ static void update_tasks_nodemask_hier(struct cpuset *root_cs, bool update_root, struct ptr_heap *heap) { struct cpuset *cp; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; if (update_root) update_tasks_nodemask(root_cs, heap); rcu_read_lock(); - cpuset_for_each_descendant_pre(cp, pos_cgrp, root_cs) { + cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp have some CPU */ if (!nodes_empty(cp->mems_allowed)) { - pos_cgrp = cgroup_rightmost_descendant(pos_cgrp); + pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget(&cp->css)) @@ -1973,7 +1973,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; if (!parent) return 0; @@ -2005,7 +2005,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); - cpuset_for_each_child(tmp_cs, pos_cgrp, parent) { + cpuset_for_each_child(tmp_cs, pos_css, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; @@ -2252,10 +2252,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work) /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; - struct cgroup *pos_cgrp; + struct cgroup_subsys_state *pos_css; rcu_read_lock(); - cpuset_for_each_descendant_pre(cs, pos_cgrp, &top_cpuset) { + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!css_tryget(&cs->css)) continue; rcu_read_unlock(); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ab64dfc84f8c..2285319e23a9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1082,7 +1082,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, struct mem_cgroup *last_visited) { - struct cgroup *prev_cgroup, *next_cgroup; + struct cgroup_subsys_state *prev_css, *next_css; /* * Root is not visited by cgroup iterators so it needs an @@ -1091,11 +1091,9 @@ static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, if (!last_visited) return root; - prev_cgroup = (last_visited == root) ? NULL - : last_visited->css.cgroup; + prev_css = (last_visited == root) ? NULL : &last_visited->css; skip_node: - next_cgroup = cgroup_next_descendant_pre( - prev_cgroup, root->css.cgroup); + next_css = css_next_descendant_pre(prev_css, &root->css); /* * Even if we found a group we have to make sure it is @@ -1104,13 +1102,13 @@ skip_node: * last_visited css is safe to use because it is * protected by css_get and the tree walk is rcu safe. */ - if (next_cgroup) { - struct mem_cgroup *mem = mem_cgroup_from_cont( - next_cgroup); + if (next_css) { + struct mem_cgroup *mem = mem_cgroup_from_css(next_css); + if (css_tryget(&mem->css)) return mem; else { - prev_cgroup = next_cgroup; + prev_css = next_css; goto skip_node; } } @@ -4939,10 +4937,10 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) */ static inline bool __memcg_has_children(struct mem_cgroup *memcg) { - struct cgroup *pos; + struct cgroup_subsys_state *pos; /* bounce at first found */ - cgroup_for_each_child(pos, memcg->css.cgroup) + css_for_each_child(pos, &memcg->css) return true; return false; } diff --git a/security/device_cgroup.c b/security/device_cgroup.c index e0ca464fa854..9bf230aa28b0 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -56,11 +56,6 @@ static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s) return s ? container_of(s, struct dev_cgroup, css) : NULL; } -static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup) -{ - return css_to_devcgroup(cgroup_css(cgroup, devices_subsys_id)); -} - static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) { return css_to_devcgroup(task_css(task, devices_subsys_id)); @@ -447,13 +442,13 @@ static void revalidate_active_exceptions(struct dev_cgroup *devcg) static int propagate_exception(struct dev_cgroup *devcg_root, struct dev_exception_item *ex) { - struct cgroup *root = devcg_root->css.cgroup, *pos; + struct cgroup_subsys_state *pos; int rc = 0; rcu_read_lock(); - cgroup_for_each_descendant_pre(pos, root) { - struct dev_cgroup *devcg = cgroup_to_devcgroup(pos); + css_for_each_descendant_pre(pos, &devcg_root->css) { + struct dev_cgroup *devcg = css_to_devcgroup(pos); /* * Because devcgroup_mutex is held, no devcg will become -- cgit v1.2.3-71-gd317 From 0942eeeef68f9493c1bcb1a52baf612b73fcf9fb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: rename cgroup_iter to cgroup_task_iter cgroup now has multiple iterators and it's quite confusing to have something which walks over tasks of a single cgroup named cgroup_iter. Let's rename it to cgroup_task_iter. While at it, reformat / update comments and replace the overview comment above the interface function decls with proper function comments. Such overview can be useful but function comments should be more than enough here. This is pure rename and doesn't introduce any functional changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 31 ++++--------- kernel/cgroup.c | 114 ++++++++++++++++++++++++++++++++---------------- kernel/cgroup_freezer.c | 24 +++++----- mm/memcontrol.c | 10 ++--- 4 files changed, 102 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4bc22f4a1abb..ea439794bd9b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -889,31 +889,16 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) -/* A cgroup_iter should be treated as an opaque object */ -struct cgroup_iter { - struct list_head *cset_link; - struct list_head *task; +/* A cgroup_task_iter should be treated as an opaque object */ +struct cgroup_task_iter { + struct list_head *cset_link; + struct list_head *task; }; -/* - * To iterate across the tasks in a cgroup: - * - * 1) call cgroup_iter_start to initialize an iterator - * - * 2) call cgroup_iter_next() to retrieve member tasks until it - * returns NULL or until you want to end the iteration - * - * 3) call cgroup_iter_end() to destroy the iterator. - * - * Or, call cgroup_scan_tasks() to iterate through every task in a - * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling - * the test_task() callback, but not while calling the process_task() - * callback. - */ -void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it); -struct task_struct *cgroup_iter_next(struct cgroup *cgrp, - struct cgroup_iter *it); -void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); +void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); +struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, + struct cgroup_task_iter *it); +void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d56d9363d4b3..15c93f9c9e57 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -367,9 +367,11 @@ static struct cgrp_cset_link init_cgrp_cset_link; static int cgroup_init_idr(struct cgroup_subsys *ss, struct cgroup_subsys_state *css); -/* css_set_lock protects the list of css_set objects, and the - * chain of tasks off each css_set. Nests outside task->alloc_lock - * due to cgroup_iter_start() */ +/* + * css_set_lock protects the list of css_set objects, and the chain of + * tasks off each css_set. Nests outside task->alloc_lock due to + * cgroup_task_iter_start(). + */ static DEFINE_RWLOCK(css_set_lock); static int css_set_count; @@ -394,10 +396,12 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) return key; } -/* We don't maintain the lists running through each css_set to its - * task until after the first call to cgroup_iter_start(). This - * reduces the fork()/exit() overhead for people who have cgroups - * compiled into their kernel but not actually in use */ +/* + * We don't maintain the lists running through each css_set to its task + * until after the first call to cgroup_task_iter_start(). This reduces + * the fork()/exit() overhead for people who have cgroups compiled into + * their kernel but not actually in use. + */ static int use_task_css_set_links __read_mostly; static void __put_css_set(struct css_set *cset, int taskexit) @@ -2982,10 +2986,10 @@ int cgroup_task_count(const struct cgroup *cgrp) } /* - * To reduce the fork() overhead for systems that are not actually - * using their cgroups capability, we don't maintain the lists running - * through each css_set to its tasks until we see the list actually - * used - in other words after the first call to cgroup_iter_start(). + * To reduce the fork() overhead for systems that are not actually using + * their cgroups capability, we don't maintain the lists running through + * each css_set to its tasks until we see the list actually used - in other + * words after the first call to cgroup_task_iter_start(). */ static void cgroup_enable_task_cg_lists(void) { @@ -3199,11 +3203,15 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, } EXPORT_SYMBOL_GPL(css_next_descendant_post); -/* - * Advance a list_head iterator. The iterator should be positioned at - * the start of a css_set +/** + * cgroup_advance_task_iter - advance a task itererator to the next css_set + * @cgrp: the cgroup to walk tasks of + * @it: the iterator to advance + * + * Advance @it to the next css_set to walk. */ -static void cgroup_advance_iter(struct cgroup *cgrp, struct cgroup_iter *it) +static void cgroup_advance_task_iter(struct cgroup *cgrp, + struct cgroup_task_iter *it) { struct list_head *l = it->cset_link; struct cgrp_cset_link *link; @@ -3223,7 +3231,21 @@ static void cgroup_advance_iter(struct cgroup *cgrp, struct cgroup_iter *it) it->task = cset->tasks.next; } -void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it) +/** + * cgroup_task_iter_start - initiate task iteration + * @cgrp: the cgroup to walk tasks of + * @it: the task iterator to use + * + * Initiate iteration through the tasks of @cgrp. The caller can call + * cgroup_task_iter_next() to walk through the tasks until the function + * returns NULL. On completion of iteration, cgroup_task_iter_end() must + * be called. + * + * Note that this function acquires a lock which is released when the + * iteration finishes. The caller can't sleep while iteration is in + * progress. + */ +void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it) __acquires(css_set_lock) { /* @@ -3236,11 +3258,20 @@ void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it) read_lock(&css_set_lock); it->cset_link = &cgrp->cset_links; - cgroup_advance_iter(cgrp, it); + cgroup_advance_task_iter(cgrp, it); } -struct task_struct *cgroup_iter_next(struct cgroup *cgrp, - struct cgroup_iter *it) +/** + * cgroup_task_iter_next - return the next task for the iterator + * @cgrp: the cgroup to walk tasks of + * @it: the task iterator being iterated + * + * The "next" function for task iteration. @it should have been + * initialized via cgroup_task_iter_start(). Returns NULL when the + * iteration reaches the end. + */ +struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, + struct cgroup_task_iter *it) { struct task_struct *res; struct list_head *l = it->task; @@ -3254,16 +3285,25 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, l = l->next; link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link); if (l == &link->cset->tasks) { - /* We reached the end of this task list - move on to - * the next cg_cgroup_link */ - cgroup_advance_iter(cgrp, it); + /* + * We reached the end of this task list - move on to the + * next cgrp_cset_link. + */ + cgroup_advance_task_iter(cgrp, it); } else { it->task = l; } return res; } -void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it) +/** + * cgroup_task_iter_end - finish task iteration + * @cgrp: the cgroup to walk tasks of + * @it: the task iterator to finish + * + * Finish task iteration started by cgroup_task_iter_start(). + */ +void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it) __releases(css_set_lock) { read_unlock(&css_set_lock); @@ -3312,7 +3352,7 @@ static inline int started_after(void *p1, void *p2) * Iterate through all the tasks in a cgroup, calling test_task() for each, * and if it returns true, call process_task() for it also. * The test_task pointer may be NULL, meaning always true (select all tasks). - * Effectively duplicates cgroup_iter_{start,next,end}() + * Effectively duplicates cgroup_task_iter_{start,next,end}() * but does not lock css_set_lock for the call to process_task(). * The struct cgroup_scanner may be embedded in any structure of the caller's * creation. @@ -3333,7 +3373,7 @@ static inline int started_after(void *p1, void *p2) int cgroup_scan_tasks(struct cgroup_scanner *scan) { int retval, i; - struct cgroup_iter it; + struct cgroup_task_iter it; struct task_struct *p, *dropped; /* Never dereference latest_task, since it's not refcounted */ struct task_struct *latest_task = NULL; @@ -3368,8 +3408,8 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) * guarantees forward progress and that we don't miss any tasks. */ heap->size = 0; - cgroup_iter_start(scan->cgrp, &it); - while ((p = cgroup_iter_next(scan->cgrp, &it))) { + cgroup_task_iter_start(scan->cgrp, &it); + while ((p = cgroup_task_iter_next(scan->cgrp, &it))) { /* * Only affect tasks that qualify per the caller's callback, * if he provided one @@ -3402,7 +3442,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) * the heap and wasn't inserted */ } - cgroup_iter_end(scan->cgrp, &it); + cgroup_task_iter_end(scan->cgrp, &it); if (heap->size) { for (i = 0; i < heap->size; i++) { @@ -3608,7 +3648,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, pid_t *array; int length; int pid, n = 0; /* used for populating the array */ - struct cgroup_iter it; + struct cgroup_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; @@ -3623,8 +3663,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, if (!array) return -ENOMEM; /* now, populate the array */ - cgroup_iter_start(cgrp, &it); - while ((tsk = cgroup_iter_next(cgrp, &it))) { + cgroup_task_iter_start(cgrp, &it); + while ((tsk = cgroup_task_iter_next(cgrp, &it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ @@ -3635,7 +3675,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } - cgroup_iter_end(cgrp, &it); + cgroup_task_iter_end(cgrp, &it); length = n; /* now sort & (if procs) strip out duplicates */ sort(array, length, sizeof(pid_t), cmppid, NULL); @@ -3669,7 +3709,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { int ret = -EINVAL; struct cgroup *cgrp; - struct cgroup_iter it; + struct cgroup_task_iter it; struct task_struct *tsk; /* @@ -3683,8 +3723,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) ret = 0; cgrp = dentry->d_fsdata; - cgroup_iter_start(cgrp, &it); - while ((tsk = cgroup_iter_next(cgrp, &it))) { + cgroup_task_iter_start(cgrp, &it); + while ((tsk = cgroup_task_iter_next(cgrp, &it))) { switch (tsk->state) { case TASK_RUNNING: stats->nr_running++; @@ -3704,7 +3744,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) break; } } - cgroup_iter_end(cgrp, &it); + cgroup_task_iter_end(cgrp, &it); err: return ret; @@ -5137,7 +5177,7 @@ void cgroup_fork(struct task_struct *child) * Adds the task to the list running through its css_set if necessary and * call the subsystem fork() callbacks. Has to be after the task is * visible on the task list in case we race with the first call to - * cgroup_iter_start() - to guarantee that the new task ends up on its + * cgroup_task_iter_start() - to guarantee that the new task ends up on its * list. */ void cgroup_post_fork(struct task_struct *child) diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 98ca48d9ceb4..c9177f8fc661 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -258,7 +258,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); struct cgroup_subsys_state *pos; - struct cgroup_iter it; + struct cgroup_task_iter it; struct task_struct *task; WARN_ON_ONCE(!rcu_read_lock_held()); @@ -279,9 +279,9 @@ static void update_if_frozen(struct cgroup_subsys_state *css) } /* are all tasks frozen? */ - cgroup_iter_start(css->cgroup, &it); + cgroup_task_iter_start(css->cgroup, &it); - while ((task = cgroup_iter_next(css->cgroup, &it))) { + while ((task = cgroup_task_iter_next(css->cgroup, &it))) { if (freezing(task)) { /* * freezer_should_skip() indicates that the task @@ -296,7 +296,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css) freezer->state |= CGROUP_FROZEN; out_iter_end: - cgroup_iter_end(css->cgroup, &it); + cgroup_task_iter_end(css->cgroup, &it); out_unlock: spin_unlock_irq(&freezer->lock); } @@ -323,25 +323,25 @@ static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft, static void freeze_cgroup(struct freezer *freezer) { struct cgroup *cgroup = freezer->css.cgroup; - struct cgroup_iter it; + struct cgroup_task_iter it; struct task_struct *task; - cgroup_iter_start(cgroup, &it); - while ((task = cgroup_iter_next(cgroup, &it))) + cgroup_task_iter_start(cgroup, &it); + while ((task = cgroup_task_iter_next(cgroup, &it))) freeze_task(task); - cgroup_iter_end(cgroup, &it); + cgroup_task_iter_end(cgroup, &it); } static void unfreeze_cgroup(struct freezer *freezer) { struct cgroup *cgroup = freezer->css.cgroup; - struct cgroup_iter it; + struct cgroup_task_iter it; struct task_struct *task; - cgroup_iter_start(cgroup, &it); - while ((task = cgroup_iter_next(cgroup, &it))) + cgroup_task_iter_start(cgroup, &it); + while ((task = cgroup_task_iter_next(cgroup, &it))) __thaw_task(task); - cgroup_iter_end(cgroup, &it); + cgroup_task_iter_end(cgroup, &it); } /** diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2285319e23a9..00b055dd1d3d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1800,11 +1800,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; for_each_mem_cgroup_tree(iter, memcg) { struct cgroup *cgroup = iter->css.cgroup; - struct cgroup_iter it; + struct cgroup_task_iter it; struct task_struct *task; - cgroup_iter_start(cgroup, &it); - while ((task = cgroup_iter_next(cgroup, &it))) { + cgroup_task_iter_start(cgroup, &it); + while ((task = cgroup_task_iter_next(cgroup, &it))) { switch (oom_scan_process_thread(task, totalpages, NULL, false)) { case OOM_SCAN_SELECT: @@ -1817,7 +1817,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, case OOM_SCAN_CONTINUE: continue; case OOM_SCAN_ABORT: - cgroup_iter_end(cgroup, &it); + cgroup_task_iter_end(cgroup, &it); mem_cgroup_iter_break(memcg, iter); if (chosen) put_task_struct(chosen); @@ -1834,7 +1834,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, get_task_struct(chosen); } } - cgroup_iter_end(cgroup, &it); + cgroup_task_iter_end(cgroup, &it); } if (!chosen) -- cgit v1.2.3-71-gd317 From c59cd3d840b1b0a8f996cbbd9132128dcaabbeb9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make cgroup_task_iter remember the cgroup being iterated Currently all cgroup_task_iter functions require @cgrp to be passed in, which is superflous and increases chance of usage error. Make cgroup_task_iter remember the cgroup being iterated and drop @cgrp argument from next and end functions. This patch doesn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 6 +++--- kernel/cgroup.c | 32 +++++++++++++++----------------- kernel/cgroup_freezer.c | 12 ++++++------ mm/memcontrol.c | 6 +++--- 4 files changed, 27 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ea439794bd9b..0287fccd0f54 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -891,14 +891,14 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, /* A cgroup_task_iter should be treated as an opaque object */ struct cgroup_task_iter { + struct cgroup *origin_cgrp; struct list_head *cset_link; struct list_head *task; }; void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); -struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, - struct cgroup_task_iter *it); -void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it); +struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); +void cgroup_task_iter_end(struct cgroup_task_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 15c93f9c9e57..abc62ea1303c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3205,13 +3205,11 @@ EXPORT_SYMBOL_GPL(css_next_descendant_post); /** * cgroup_advance_task_iter - advance a task itererator to the next css_set - * @cgrp: the cgroup to walk tasks of * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ -static void cgroup_advance_task_iter(struct cgroup *cgrp, - struct cgroup_task_iter *it) +static void cgroup_advance_task_iter(struct cgroup_task_iter *it) { struct list_head *l = it->cset_link; struct cgrp_cset_link *link; @@ -3220,7 +3218,7 @@ static void cgroup_advance_task_iter(struct cgroup *cgrp, /* Advance to the next non-empty css_set */ do { l = l->next; - if (l == &cgrp->cset_links) { + if (l == &it->origin_cgrp->cset_links) { it->cset_link = NULL; return; } @@ -3257,21 +3255,22 @@ void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it) cgroup_enable_task_cg_lists(); read_lock(&css_set_lock); + + it->origin_cgrp = cgrp; it->cset_link = &cgrp->cset_links; - cgroup_advance_task_iter(cgrp, it); + + cgroup_advance_task_iter(it); } /** * cgroup_task_iter_next - return the next task for the iterator - * @cgrp: the cgroup to walk tasks of * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via cgroup_task_iter_start(). Returns NULL when the * iteration reaches the end. */ -struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, - struct cgroup_task_iter *it) +struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it) { struct task_struct *res; struct list_head *l = it->task; @@ -3289,7 +3288,7 @@ struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, * We reached the end of this task list - move on to the * next cgrp_cset_link. */ - cgroup_advance_task_iter(cgrp, it); + cgroup_advance_task_iter(it); } else { it->task = l; } @@ -3298,12 +3297,11 @@ struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp, /** * cgroup_task_iter_end - finish task iteration - * @cgrp: the cgroup to walk tasks of * @it: the task iterator to finish * * Finish task iteration started by cgroup_task_iter_start(). */ -void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it) +void cgroup_task_iter_end(struct cgroup_task_iter *it) __releases(css_set_lock) { read_unlock(&css_set_lock); @@ -3409,7 +3407,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) */ heap->size = 0; cgroup_task_iter_start(scan->cgrp, &it); - while ((p = cgroup_task_iter_next(scan->cgrp, &it))) { + while ((p = cgroup_task_iter_next(&it))) { /* * Only affect tasks that qualify per the caller's callback, * if he provided one @@ -3442,7 +3440,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) * the heap and wasn't inserted */ } - cgroup_task_iter_end(scan->cgrp, &it); + cgroup_task_iter_end(&it); if (heap->size) { for (i = 0; i < heap->size; i++) { @@ -3664,7 +3662,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, return -ENOMEM; /* now, populate the array */ cgroup_task_iter_start(cgrp, &it); - while ((tsk = cgroup_task_iter_next(cgrp, &it))) { + while ((tsk = cgroup_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ @@ -3675,7 +3673,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } - cgroup_task_iter_end(cgrp, &it); + cgroup_task_iter_end(&it); length = n; /* now sort & (if procs) strip out duplicates */ sort(array, length, sizeof(pid_t), cmppid, NULL); @@ -3724,7 +3722,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) cgrp = dentry->d_fsdata; cgroup_task_iter_start(cgrp, &it); - while ((tsk = cgroup_task_iter_next(cgrp, &it))) { + while ((tsk = cgroup_task_iter_next(&it))) { switch (tsk->state) { case TASK_RUNNING: stats->nr_running++; @@ -3744,7 +3742,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) break; } } - cgroup_task_iter_end(cgrp, &it); + cgroup_task_iter_end(&it); err: return ret; diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index c9177f8fc661..e0ab9bfd679a 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -281,7 +281,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css) /* are all tasks frozen? */ cgroup_task_iter_start(css->cgroup, &it); - while ((task = cgroup_task_iter_next(css->cgroup, &it))) { + while ((task = cgroup_task_iter_next(&it))) { if (freezing(task)) { /* * freezer_should_skip() indicates that the task @@ -296,7 +296,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css) freezer->state |= CGROUP_FROZEN; out_iter_end: - cgroup_task_iter_end(css->cgroup, &it); + cgroup_task_iter_end(&it); out_unlock: spin_unlock_irq(&freezer->lock); } @@ -327,9 +327,9 @@ static void freeze_cgroup(struct freezer *freezer) struct task_struct *task; cgroup_task_iter_start(cgroup, &it); - while ((task = cgroup_task_iter_next(cgroup, &it))) + while ((task = cgroup_task_iter_next(&it))) freeze_task(task); - cgroup_task_iter_end(cgroup, &it); + cgroup_task_iter_end(&it); } static void unfreeze_cgroup(struct freezer *freezer) @@ -339,9 +339,9 @@ static void unfreeze_cgroup(struct freezer *freezer) struct task_struct *task; cgroup_task_iter_start(cgroup, &it); - while ((task = cgroup_task_iter_next(cgroup, &it))) + while ((task = cgroup_task_iter_next(&it))) __thaw_task(task); - cgroup_task_iter_end(cgroup, &it); + cgroup_task_iter_end(&it); } /** diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 00b055dd1d3d..5a5f4dc649f0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1804,7 +1804,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, struct task_struct *task; cgroup_task_iter_start(cgroup, &it); - while ((task = cgroup_task_iter_next(cgroup, &it))) { + while ((task = cgroup_task_iter_next(&it))) { switch (oom_scan_process_thread(task, totalpages, NULL, false)) { case OOM_SCAN_SELECT: @@ -1817,7 +1817,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, case OOM_SCAN_CONTINUE: continue; case OOM_SCAN_ABORT: - cgroup_task_iter_end(cgroup, &it); + cgroup_task_iter_end(&it); mem_cgroup_iter_break(memcg, iter); if (chosen) put_task_struct(chosen); @@ -1834,7 +1834,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, get_task_struct(chosen); } } - cgroup_task_iter_end(cgroup, &it); + cgroup_task_iter_end(&it); } if (!chosen) -- cgit v1.2.3-71-gd317 From e535837b1dae17b5a2d76ea1bc22ac1a79354624 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: remove struct cgroup_scanner cgroup_scan_tasks() takes a pointer to struct cgroup_scanner as its sole argument and the only function of that struct is packing the arguments of the function call which are consisted of five fields. It's not too unusual to pack parameters into a struct when the number of arguments gets excessive or the whole set needs to be passed around a lot, but neither holds here making it just weird. Drop struct cgroup_scanner and pass the params directly to cgroup_scan_tasks(). Note that struct cpuset_change_nodemask_arg was added to cpuset.c to pass both ->cs and ->newmems pointer to cpuset_change_nodemask() using single data pointer. This doesn't make any functional differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 16 ++++----- kernel/cgroup.c | 93 +++++++++++++++++++++++--------------------------- kernel/cpuset.c | 63 ++++++++++++++-------------------- 3 files changed, 75 insertions(+), 97 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0287fccd0f54..8472ed576b64 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -528,15 +528,6 @@ struct cftype_set { struct cftype *cfts; }; -struct cgroup_scanner { - struct cgroup *cgrp; - int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); - void (*process_task)(struct task_struct *p, - struct cgroup_scanner *scan); - struct ptr_heap *heap; - void *data; -}; - /* * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This * function can be called as long as @cgrp is accessible. @@ -899,7 +890,12 @@ struct cgroup_task_iter { void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); void cgroup_task_iter_end(struct cgroup_task_iter *it); -int cgroup_scan_tasks(struct cgroup_scanner *scan); + +int cgroup_scan_tasks(struct cgroup *cgrp, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap); + int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index abc62ea1303c..7b16ddb2569b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3343,32 +3343,37 @@ static inline int started_after(void *p1, void *p2) /** * cgroup_scan_tasks - iterate though all the tasks in a cgroup - * @scan: struct cgroup_scanner containing arguments for the scan + * @cgrp: the cgroup to iterate tasks of + * @test: optional test callback + * @process: process callback + * @data: data passed to @test and @process + * @heap: optional pre-allocated heap used for task iteration * - * Arguments include pointers to callback functions test_task() and - * process_task(). - * Iterate through all the tasks in a cgroup, calling test_task() for each, - * and if it returns true, call process_task() for it also. - * The test_task pointer may be NULL, meaning always true (select all tasks). - * Effectively duplicates cgroup_task_iter_{start,next,end}() - * but does not lock css_set_lock for the call to process_task(). - * The struct cgroup_scanner may be embedded in any structure of the caller's - * creation. - * It is guaranteed that process_task() will act on every task that - * is a member of the cgroup for the duration of this call. This - * function may or may not call process_task() for tasks that exit - * or move to a different cgroup during the call, or are forked or - * move into the cgroup during the call. + * Iterate through all the tasks in a cgroup, calling @test for each, and + * if it returns %true, call @process for it also. * - * Note that test_task() may be called with locks held, and may in some - * situations be called multiple times for the same task, so it should - * be cheap. - * If the heap pointer in the struct cgroup_scanner is non-NULL, a heap has been - * pre-allocated and will be used for heap operations (and its "gt" member will - * be overwritten), else a temporary heap will be used (allocation of which - * may cause this function to fail). + * @test may be NULL, meaning always true (select all tasks), which + * effectively duplicates cgroup_task_iter_{start,next,end}() but does not + * lock css_set_lock for the call to @process. + * + * It is guaranteed that @process will act on every task that is a member + * of @cgrp for the duration of this call. This function may or may not + * call @process for tasks that exit or move to a different cgroup during + * the call, or are forked or move into the cgroup during the call. + * + * Note that @test may be called with locks held, and may in some + * situations be called multiple times for the same task, so it should be + * cheap. + * + * If @heap is non-NULL, a heap has been pre-allocated and will be used for + * heap operations (and its "gt" member will be overwritten), else a + * temporary heap will be used (allocation of which may cause this function + * to fail). */ -int cgroup_scan_tasks(struct cgroup_scanner *scan) +int cgroup_scan_tasks(struct cgroup *cgrp, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap) { int retval, i; struct cgroup_task_iter it; @@ -3376,12 +3381,10 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) /* Never dereference latest_task, since it's not refcounted */ struct task_struct *latest_task = NULL; struct ptr_heap tmp_heap; - struct ptr_heap *heap; struct timespec latest_time = { 0, 0 }; - if (scan->heap) { + if (heap) { /* The caller supplied our heap and pre-allocated its memory */ - heap = scan->heap; heap->gt = &started_after; } else { /* We need to allocate our own heap memory */ @@ -3394,25 +3397,24 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) again: /* - * Scan tasks in the cgroup, using the scanner's "test_task" callback - * to determine which are of interest, and using the scanner's - * "process_task" callback to process any of them that need an update. - * Since we don't want to hold any locks during the task updates, - * gather tasks to be processed in a heap structure. - * The heap is sorted by descending task start time. - * If the statically-sized heap fills up, we overflow tasks that - * started later, and in future iterations only consider tasks that - * started after the latest task in the previous pass. This + * Scan tasks in the cgroup, using the @test callback to determine + * which are of interest, and invoking @process callback on the + * ones which need an update. Since we don't want to hold any + * locks during the task updates, gather tasks to be processed in a + * heap structure. The heap is sorted by descending task start + * time. If the statically-sized heap fills up, we overflow tasks + * that started later, and in future iterations only consider tasks + * that started after the latest task in the previous pass. This * guarantees forward progress and that we don't miss any tasks. */ heap->size = 0; - cgroup_task_iter_start(scan->cgrp, &it); + cgroup_task_iter_start(cgrp, &it); while ((p = cgroup_task_iter_next(&it))) { /* * Only affect tasks that qualify per the caller's callback, * if he provided one */ - if (scan->test_task && !scan->test_task(p, scan)) + if (test && !test(p, data)) continue; /* * Only process tasks that started after the last task @@ -3450,7 +3452,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) latest_task = q; } /* Process the task per the caller's callback */ - scan->process_task(q, scan); + process(q, data); put_task_struct(q); } /* @@ -3467,10 +3469,9 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) return 0; } -static void cgroup_transfer_one_task(struct task_struct *task, - struct cgroup_scanner *scan) +static void cgroup_transfer_one_task(struct task_struct *task, void *data) { - struct cgroup *new_cgroup = scan->data; + struct cgroup *new_cgroup = data; mutex_lock(&cgroup_mutex); cgroup_attach_task(new_cgroup, task, false); @@ -3484,15 +3485,7 @@ static void cgroup_transfer_one_task(struct task_struct *task, */ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { - struct cgroup_scanner scan; - - scan.cgrp = from; - scan.test_task = NULL; /* select all tasks in cgroup */ - scan.process_task = cgroup_transfer_one_task; - scan.heap = NULL; - scan.data = to; - - return cgroup_scan_tasks(&scan); + return cgroup_scan_tasks(from, NULL, cgroup_transfer_one_task, to, NULL); } /* diff --git a/kernel/cpuset.c b/kernel/cpuset.c index be4f5036ea5e..6fe23f2ac742 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -830,7 +830,7 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs) /** * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's * @tsk: task to test - * @scan: struct cgroup_scanner containing the cgroup of the task + * @data: cpuset to @tsk belongs to * * Called by cgroup_scan_tasks() for each task in a cgroup whose * cpus_allowed mask needs to be changed. @@ -838,12 +838,11 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs) * We don't need to re-check for the cgroup/cpuset membership, since we're * holding cpuset_mutex at this point. */ -static void cpuset_change_cpumask(struct task_struct *tsk, - struct cgroup_scanner *scan) +static void cpuset_change_cpumask(struct task_struct *tsk, void *data) { - struct cpuset *cpus_cs; + struct cpuset *cs = data; + struct cpuset *cpus_cs = effective_cpumask_cpuset(cs); - cpus_cs = effective_cpumask_cpuset(cgroup_cs(scan->cgrp)); set_cpus_allowed_ptr(tsk, cpus_cs->cpus_allowed); } @@ -862,13 +861,8 @@ static void cpuset_change_cpumask(struct task_struct *tsk, */ static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap) { - struct cgroup_scanner scan; - - scan.cgrp = cs->css.cgroup; - scan.test_task = NULL; - scan.process_task = cpuset_change_cpumask; - scan.heap = heap; - cgroup_scan_tasks(&scan); + cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_cpumask, cs, + heap); } /* @@ -1052,20 +1046,24 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, task_unlock(tsk); } +struct cpuset_change_nodemask_arg { + struct cpuset *cs; + nodemask_t *newmems; +}; + /* * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy * of it to cpuset's new mems_allowed, and migrate pages to new nodes if * memory_migrate flag is set. Called with cpuset_mutex held. */ -static void cpuset_change_nodemask(struct task_struct *p, - struct cgroup_scanner *scan) +static void cpuset_change_nodemask(struct task_struct *p, void *data) { - struct cpuset *cs = cgroup_cs(scan->cgrp); + struct cpuset_change_nodemask_arg *arg = data; + struct cpuset *cs = arg->cs; struct mm_struct *mm; int migrate; - nodemask_t *newmems = scan->data; - cpuset_change_task_nodemask(p, newmems); + cpuset_change_task_nodemask(p, arg->newmems); mm = get_task_mm(p); if (!mm) @@ -1075,7 +1073,7 @@ static void cpuset_change_nodemask(struct task_struct *p, mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) - cpuset_migrate_mm(mm, &cs->old_mems_allowed, newmems); + cpuset_migrate_mm(mm, &cs->old_mems_allowed, arg->newmems); mmput(mm); } @@ -1093,19 +1091,14 @@ static void *cpuset_being_rebound; static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) { static nodemask_t newmems; /* protected by cpuset_mutex */ - struct cgroup_scanner scan; struct cpuset *mems_cs = effective_nodemask_cpuset(cs); + struct cpuset_change_nodemask_arg arg = { .cs = cs, + .newmems = &newmems }; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(mems_cs, &newmems); - scan.cgrp = cs->css.cgroup; - scan.test_task = NULL; - scan.process_task = cpuset_change_nodemask; - scan.heap = heap; - scan.data = &newmems; - /* * The mpol_rebind_mm() call takes mmap_sem, which we couldn't * take while holding tasklist_lock. Forks can happen - the @@ -1116,7 +1109,8 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ - cgroup_scan_tasks(&scan); + cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_nodemask, &arg, + heap); /* * All the tasks' nodemasks have been updated, update @@ -1263,17 +1257,18 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) /* * cpuset_change_flag - make a task's spread flags the same as its cpuset's * @tsk: task to be updated - * @scan: struct cgroup_scanner containing the cgroup of the task + * @data: cpuset to @tsk belongs to * * Called by cgroup_scan_tasks() for each task in a cgroup. * * We don't need to re-check for the cgroup/cpuset membership, since we're * holding cpuset_mutex at this point. */ -static void cpuset_change_flag(struct task_struct *tsk, - struct cgroup_scanner *scan) +static void cpuset_change_flag(struct task_struct *tsk, void *data) { - cpuset_update_task_spread_flag(cgroup_cs(scan->cgrp), tsk); + struct cpuset *cs = data; + + cpuset_update_task_spread_flag(cs, tsk); } /* @@ -1291,13 +1286,7 @@ static void cpuset_change_flag(struct task_struct *tsk, */ static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap) { - struct cgroup_scanner scan; - - scan.cgrp = cs->css.cgroup; - scan.test_task = NULL; - scan.process_task = cpuset_change_flag; - scan.heap = heap; - cgroup_scan_tasks(&scan); + cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_flag, cs, heap); } /* -- cgit v1.2.3-71-gd317 From 72ec7029937f0518eff21b8762743c31591684f5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make task iterators deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. This patch converts task iterators to deal with css instead of cgroup. Note that under unified hierarchy, different sets of tasks will be considered belonging to a given cgroup depending on the subsystem in question and making the iterators deal with css instead cgroup provides them with enough information about the iteration. While at it, fix several function comment formats in cpuset.c. This patch doesn't introduce any behavior differences. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Balbir Singh Cc: Matt Helsley --- include/linux/cgroup.h | 21 ++++----- kernel/cgroup.c | 112 ++++++++++++++++++++++++------------------------ kernel/cgroup_freezer.c | 26 ++++++----- kernel/cpuset.c | 41 ++++++++---------- mm/memcontrol.c | 11 +++-- 5 files changed, 104 insertions(+), 107 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8472ed576b64..cd105fce089c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -880,21 +880,22 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) -/* A cgroup_task_iter should be treated as an opaque object */ -struct cgroup_task_iter { - struct cgroup *origin_cgrp; +/* A css_task_iter should be treated as an opaque object */ +struct css_task_iter { + struct cgroup_subsys_state *origin_css; struct list_head *cset_link; struct list_head *task; }; -void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it); -struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it); -void cgroup_task_iter_end(struct cgroup_task_iter *it); +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it); +struct task_struct *css_task_iter_next(struct css_task_iter *it); +void css_task_iter_end(struct css_task_iter *it); -int cgroup_scan_tasks(struct cgroup *cgrp, - bool (*test)(struct task_struct *, void *), - void (*process)(struct task_struct *, void *), - void *data, struct ptr_heap *heap); +int css_scan_tasks(struct cgroup_subsys_state *css, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7b16ddb2569b..8c57301d0561 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -370,7 +370,7 @@ static int cgroup_init_idr(struct cgroup_subsys *ss, /* * css_set_lock protects the list of css_set objects, and the chain of * tasks off each css_set. Nests outside task->alloc_lock due to - * cgroup_task_iter_start(). + * css_task_iter_start(). */ static DEFINE_RWLOCK(css_set_lock); static int css_set_count; @@ -398,9 +398,9 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) /* * We don't maintain the lists running through each css_set to its task - * until after the first call to cgroup_task_iter_start(). This reduces - * the fork()/exit() overhead for people who have cgroups compiled into - * their kernel but not actually in use. + * until after the first call to css_task_iter_start(). This reduces the + * fork()/exit() overhead for people who have cgroups compiled into their + * kernel but not actually in use. */ static int use_task_css_set_links __read_mostly; @@ -2989,7 +2989,7 @@ int cgroup_task_count(const struct cgroup *cgrp) * To reduce the fork() overhead for systems that are not actually using * their cgroups capability, we don't maintain the lists running through * each css_set to its tasks until we see the list actually used - in other - * words after the first call to cgroup_task_iter_start(). + * words after the first call to css_task_iter_start(). */ static void cgroup_enable_task_cg_lists(void) { @@ -3204,12 +3204,12 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, EXPORT_SYMBOL_GPL(css_next_descendant_post); /** - * cgroup_advance_task_iter - advance a task itererator to the next css_set + * css_advance_task_iter - advance a task itererator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ -static void cgroup_advance_task_iter(struct cgroup_task_iter *it) +static void css_advance_task_iter(struct css_task_iter *it) { struct list_head *l = it->cset_link; struct cgrp_cset_link *link; @@ -3218,7 +3218,7 @@ static void cgroup_advance_task_iter(struct cgroup_task_iter *it) /* Advance to the next non-empty css_set */ do { l = l->next; - if (l == &it->origin_cgrp->cset_links) { + if (l == &it->origin_css->cgroup->cset_links) { it->cset_link = NULL; return; } @@ -3230,47 +3230,48 @@ static void cgroup_advance_task_iter(struct cgroup_task_iter *it) } /** - * cgroup_task_iter_start - initiate task iteration - * @cgrp: the cgroup to walk tasks of + * css_task_iter_start - initiate task iteration + * @css: the css to walk tasks of * @it: the task iterator to use * - * Initiate iteration through the tasks of @cgrp. The caller can call - * cgroup_task_iter_next() to walk through the tasks until the function - * returns NULL. On completion of iteration, cgroup_task_iter_end() must - * be called. + * Initiate iteration through the tasks of @css. The caller can call + * css_task_iter_next() to walk through the tasks until the function + * returns NULL. On completion of iteration, css_task_iter_end() must be + * called. * * Note that this function acquires a lock which is released when the * iteration finishes. The caller can't sleep while iteration is in * progress. */ -void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it) +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it) __acquires(css_set_lock) { /* - * The first time anyone tries to iterate across a cgroup, - * we need to enable the list linking each css_set to its - * tasks, and fix up all existing tasks. + * The first time anyone tries to iterate across a css, we need to + * enable the list linking each css_set to its tasks, and fix up + * all existing tasks. */ if (!use_task_css_set_links) cgroup_enable_task_cg_lists(); read_lock(&css_set_lock); - it->origin_cgrp = cgrp; - it->cset_link = &cgrp->cset_links; + it->origin_css = css; + it->cset_link = &css->cgroup->cset_links; - cgroup_advance_task_iter(it); + css_advance_task_iter(it); } /** - * cgroup_task_iter_next - return the next task for the iterator + * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been - * initialized via cgroup_task_iter_start(). Returns NULL when the - * iteration reaches the end. + * initialized via css_task_iter_start(). Returns NULL when the iteration + * reaches the end. */ -struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it) +struct task_struct *css_task_iter_next(struct css_task_iter *it) { struct task_struct *res; struct list_head *l = it->task; @@ -3288,7 +3289,7 @@ struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it) * We reached the end of this task list - move on to the * next cgrp_cset_link. */ - cgroup_advance_task_iter(it); + css_advance_task_iter(it); } else { it->task = l; } @@ -3296,12 +3297,12 @@ struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it) } /** - * cgroup_task_iter_end - finish task iteration + * css_task_iter_end - finish task iteration * @it: the task iterator to finish * - * Finish task iteration started by cgroup_task_iter_start(). + * Finish task iteration started by css_task_iter_start(). */ -void cgroup_task_iter_end(struct cgroup_task_iter *it) +void css_task_iter_end(struct css_task_iter *it) __releases(css_set_lock) { read_unlock(&css_set_lock); @@ -3342,24 +3343,24 @@ static inline int started_after(void *p1, void *p2) } /** - * cgroup_scan_tasks - iterate though all the tasks in a cgroup - * @cgrp: the cgroup to iterate tasks of + * css_scan_tasks - iterate though all the tasks in a css + * @css: the css to iterate tasks of * @test: optional test callback * @process: process callback * @data: data passed to @test and @process * @heap: optional pre-allocated heap used for task iteration * - * Iterate through all the tasks in a cgroup, calling @test for each, and - * if it returns %true, call @process for it also. + * Iterate through all the tasks in @css, calling @test for each, and if it + * returns %true, call @process for it also. * * @test may be NULL, meaning always true (select all tasks), which - * effectively duplicates cgroup_task_iter_{start,next,end}() but does not + * effectively duplicates css_task_iter_{start,next,end}() but does not * lock css_set_lock for the call to @process. * * It is guaranteed that @process will act on every task that is a member - * of @cgrp for the duration of this call. This function may or may not - * call @process for tasks that exit or move to a different cgroup during - * the call, or are forked or move into the cgroup during the call. + * of @css for the duration of this call. This function may or may not + * call @process for tasks that exit or move to a different css during the + * call, or are forked or move into the css during the call. * * Note that @test may be called with locks held, and may in some * situations be called multiple times for the same task, so it should be @@ -3370,13 +3371,13 @@ static inline int started_after(void *p1, void *p2) * temporary heap will be used (allocation of which may cause this function * to fail). */ -int cgroup_scan_tasks(struct cgroup *cgrp, - bool (*test)(struct task_struct *, void *), - void (*process)(struct task_struct *, void *), - void *data, struct ptr_heap *heap) +int css_scan_tasks(struct cgroup_subsys_state *css, + bool (*test)(struct task_struct *, void *), + void (*process)(struct task_struct *, void *), + void *data, struct ptr_heap *heap) { int retval, i; - struct cgroup_task_iter it; + struct css_task_iter it; struct task_struct *p, *dropped; /* Never dereference latest_task, since it's not refcounted */ struct task_struct *latest_task = NULL; @@ -3397,7 +3398,7 @@ int cgroup_scan_tasks(struct cgroup *cgrp, again: /* - * Scan tasks in the cgroup, using the @test callback to determine + * Scan tasks in the css, using the @test callback to determine * which are of interest, and invoking @process callback on the * ones which need an update. Since we don't want to hold any * locks during the task updates, gather tasks to be processed in a @@ -3408,8 +3409,8 @@ int cgroup_scan_tasks(struct cgroup *cgrp, * guarantees forward progress and that we don't miss any tasks. */ heap->size = 0; - cgroup_task_iter_start(cgrp, &it); - while ((p = cgroup_task_iter_next(&it))) { + css_task_iter_start(css, &it); + while ((p = css_task_iter_next(&it))) { /* * Only affect tasks that qualify per the caller's callback, * if he provided one @@ -3442,7 +3443,7 @@ int cgroup_scan_tasks(struct cgroup *cgrp, * the heap and wasn't inserted */ } - cgroup_task_iter_end(&it); + css_task_iter_end(&it); if (heap->size) { for (i = 0; i < heap->size; i++) { @@ -3485,7 +3486,8 @@ static void cgroup_transfer_one_task(struct task_struct *task, void *data) */ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { - return cgroup_scan_tasks(from, NULL, cgroup_transfer_one_task, to, NULL); + return css_scan_tasks(&from->dummy_css, NULL, cgroup_transfer_one_task, + to, NULL); } /* @@ -3639,7 +3641,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, pid_t *array; int length; int pid, n = 0; /* used for populating the array */ - struct cgroup_task_iter it; + struct css_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; @@ -3654,8 +3656,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, if (!array) return -ENOMEM; /* now, populate the array */ - cgroup_task_iter_start(cgrp, &it); - while ((tsk = cgroup_task_iter_next(&it))) { + css_task_iter_start(&cgrp->dummy_css, &it); + while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ @@ -3666,7 +3668,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } - cgroup_task_iter_end(&it); + css_task_iter_end(&it); length = n; /* now sort & (if procs) strip out duplicates */ sort(array, length, sizeof(pid_t), cmppid, NULL); @@ -3700,7 +3702,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { int ret = -EINVAL; struct cgroup *cgrp; - struct cgroup_task_iter it; + struct css_task_iter it; struct task_struct *tsk; /* @@ -3714,8 +3716,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) ret = 0; cgrp = dentry->d_fsdata; - cgroup_task_iter_start(cgrp, &it); - while ((tsk = cgroup_task_iter_next(&it))) { + css_task_iter_start(&cgrp->dummy_css, &it); + while ((tsk = css_task_iter_next(&it))) { switch (tsk->state) { case TASK_RUNNING: stats->nr_running++; @@ -3735,7 +3737,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) break; } } - cgroup_task_iter_end(&it); + css_task_iter_end(&it); err: return ret; diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index e0ab9bfd679a..5cd2b6d55243 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -258,7 +258,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); struct cgroup_subsys_state *pos; - struct cgroup_task_iter it; + struct css_task_iter it; struct task_struct *task; WARN_ON_ONCE(!rcu_read_lock_held()); @@ -279,9 +279,9 @@ static void update_if_frozen(struct cgroup_subsys_state *css) } /* are all tasks frozen? */ - cgroup_task_iter_start(css->cgroup, &it); + css_task_iter_start(css, &it); - while ((task = cgroup_task_iter_next(&it))) { + while ((task = css_task_iter_next(&it))) { if (freezing(task)) { /* * freezer_should_skip() indicates that the task @@ -296,7 +296,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css) freezer->state |= CGROUP_FROZEN; out_iter_end: - cgroup_task_iter_end(&it); + css_task_iter_end(&it); out_unlock: spin_unlock_irq(&freezer->lock); } @@ -322,26 +322,24 @@ static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft, static void freeze_cgroup(struct freezer *freezer) { - struct cgroup *cgroup = freezer->css.cgroup; - struct cgroup_task_iter it; + struct css_task_iter it; struct task_struct *task; - cgroup_task_iter_start(cgroup, &it); - while ((task = cgroup_task_iter_next(&it))) + css_task_iter_start(&freezer->css, &it); + while ((task = css_task_iter_next(&it))) freeze_task(task); - cgroup_task_iter_end(&it); + css_task_iter_end(&it); } static void unfreeze_cgroup(struct freezer *freezer) { - struct cgroup *cgroup = freezer->css.cgroup; - struct cgroup_task_iter it; + struct css_task_iter it; struct task_struct *task; - cgroup_task_iter_start(cgroup, &it); - while ((task = cgroup_task_iter_next(&it))) + css_task_iter_start(&freezer->css, &it); + while ((task = css_task_iter_next(&it))) __thaw_task(task); - cgroup_task_iter_end(&it); + css_task_iter_end(&it); } /** diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 6fe23f2ac742..39e52175f4af 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -832,8 +832,8 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs) * @tsk: task to test * @data: cpuset to @tsk belongs to * - * Called by cgroup_scan_tasks() for each task in a cgroup whose - * cpus_allowed mask needs to be changed. + * Called by css_scan_tasks() for each task in a cgroup whose cpus_allowed + * mask needs to be changed. * * We don't need to re-check for the cgroup/cpuset membership, since we're * holding cpuset_mutex at this point. @@ -849,27 +849,26 @@ static void cpuset_change_cpumask(struct task_struct *tsk, void *data) /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed - * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() + * @heap: if NULL, defer allocating heap memory to css_scan_tasks() * * Called with cpuset_mutex held * - * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, + * The css_scan_tasks() function will scan all the tasks in a cgroup, * calling callback functions for each. * - * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0 + * No return value. It's guaranteed that css_scan_tasks() always returns 0 * if @heap != NULL. */ static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap) { - cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_cpumask, cs, - heap); + css_scan_tasks(&cs->css, NULL, cpuset_change_cpumask, cs, heap); } /* * update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy. * @root_cs: the root cpuset of the hierarchy * @update_root: update root cpuset or not? - * @heap: the heap used by cgroup_scan_tasks() + * @heap: the heap used by css_scan_tasks() * * This will update cpumasks of tasks in @root_cs and all other empty cpusets * which take on cpumask of @root_cs. @@ -1082,11 +1081,10 @@ static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed - * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() + * @heap: if NULL, defer allocating heap memory to css_scan_tasks() * - * Called with cpuset_mutex held - * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0 - * if @heap != NULL. + * Called with cpuset_mutex held. No return value. It's guaranteed that + * css_scan_tasks() always returns 0 if @heap != NULL. */ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) { @@ -1109,8 +1107,7 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ - cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_nodemask, &arg, - heap); + css_scan_tasks(&cs->css, NULL, cpuset_change_nodemask, &arg, heap); /* * All the tasks' nodemasks have been updated, update @@ -1126,7 +1123,7 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap) * update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy. * @cs: the root cpuset of the hierarchy * @update_root: update the root cpuset or not? - * @heap: the heap used by cgroup_scan_tasks() + * @heap: the heap used by css_scan_tasks() * * This will update nodemasks of tasks in @root_cs and all other empty cpusets * which take on nodemask of @root_cs. @@ -1254,12 +1251,12 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) return 0; } -/* +/** * cpuset_change_flag - make a task's spread flags the same as its cpuset's * @tsk: task to be updated * @data: cpuset to @tsk belongs to * - * Called by cgroup_scan_tasks() for each task in a cgroup. + * Called by css_scan_tasks() for each task in a cgroup. * * We don't need to re-check for the cgroup/cpuset membership, since we're * holding cpuset_mutex at this point. @@ -1271,22 +1268,22 @@ static void cpuset_change_flag(struct task_struct *tsk, void *data) cpuset_update_task_spread_flag(cs, tsk); } -/* +/** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed - * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() + * @heap: if NULL, defer allocating heap memory to css_scan_tasks() * * Called with cpuset_mutex held * - * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, + * The css_scan_tasks() function will scan all the tasks in a cgroup, * calling callback functions for each. * - * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0 + * No return value. It's guaranteed that css_scan_tasks() always returns 0 * if @heap != NULL. */ static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap) { - cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_flag, cs, heap); + css_scan_tasks(&cs->css, NULL, cpuset_change_flag, cs, heap); } /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5a5f4dc649f0..95106a993777 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1799,12 +1799,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1; for_each_mem_cgroup_tree(iter, memcg) { - struct cgroup *cgroup = iter->css.cgroup; - struct cgroup_task_iter it; + struct css_task_iter it; struct task_struct *task; - cgroup_task_iter_start(cgroup, &it); - while ((task = cgroup_task_iter_next(&it))) { + css_task_iter_start(&iter->css, &it); + while ((task = css_task_iter_next(&it))) { switch (oom_scan_process_thread(task, totalpages, NULL, false)) { case OOM_SCAN_SELECT: @@ -1817,7 +1816,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, case OOM_SCAN_CONTINUE: continue; case OOM_SCAN_ABORT: - cgroup_task_iter_end(&it); + css_task_iter_end(&it); mem_cgroup_iter_break(memcg, iter); if (chosen) put_task_struct(chosen); @@ -1834,7 +1833,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, get_task_struct(chosen); } } - cgroup_task_iter_end(&it); + css_task_iter_end(&it); } if (!chosen) -- cgit v1.2.3-71-gd317 From 81eeaf0411204f52af8ef78ff107cfca2fcfec1d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:26 -0400 Subject: cgroup: make cftype->[un]register_event() deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. cftype->[un]register_event() is among the remaining couple interfaces which still use struct cgroup. Convert it to cgroup_subsys_state. The conversion is mostly mechanical and removes the last users of mem_cgroup_from_cont() and cg_to_vmpressure(), which are removed. v2: indentation update as suggested by Li Zefan. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Balbir Singh --- include/linux/cgroup.h | 10 ++++++---- include/linux/vmpressure.h | 6 ++++-- kernel/cgroup.c | 15 ++++++++------- mm/memcontrol.c | 21 ++++++++------------- mm/vmpressure.c | 21 +++++++++------------ 5 files changed, 35 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cd105fce089c..b065d24486e6 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -506,16 +506,18 @@ struct cftype { * you want to provide this functionality. Use eventfd_signal() * on eventfd to send notification to userspace. */ - int (*register_event)(struct cgroup *cgrp, struct cftype *cft, - struct eventfd_ctx *eventfd, const char *args); + int (*register_event)(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd, + const char *args); /* * unregister_event() callback will be called when userspace * closes the eventfd or on cgroup removing. * This callback must be implemented, if you want provide * notification functionality. */ - void (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, - struct eventfd_ctx *eventfd); + void (*unregister_event)(struct cgroup_subsys_state *css, + struct cftype *cft, + struct eventfd_ctx *eventfd); }; /* diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 76be077340ea..b239482bd39d 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -33,10 +33,12 @@ extern void vmpressure_init(struct vmpressure *vmpr); extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg); extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr); extern struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css); -extern int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, +extern int vmpressure_register_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd, const char *args); -extern void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft, +extern void vmpressure_unregister_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd); #else static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8c57301d0561..a71f2e0f9711 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -159,9 +159,9 @@ struct css_id { */ struct cgroup_event { /* - * Cgroup which the event belongs to. + * css which the event belongs to. */ - struct cgroup *cgrp; + struct cgroup_subsys_state *css; /* * Control file which the event associated. */ @@ -3955,11 +3955,12 @@ static void cgroup_event_remove(struct work_struct *work) { struct cgroup_event *event = container_of(work, struct cgroup_event, remove); - struct cgroup *cgrp = event->cgrp; + struct cgroup_subsys_state *css = event->css; + struct cgroup *cgrp = css->cgroup; remove_wait_queue(event->wqh, &event->wait); - event->cft->unregister_event(cgrp, event->cft, event->eventfd); + event->cft->unregister_event(css, event->cft, event->eventfd); /* Notify userspace the event is going away. */ eventfd_signal(event->eventfd, 1); @@ -3979,7 +3980,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode, { struct cgroup_event *event = container_of(wait, struct cgroup_event, wait); - struct cgroup *cgrp = event->cgrp; + struct cgroup *cgrp = event->css->cgroup; unsigned long flags = (unsigned long)key; if (flags & POLLHUP) { @@ -4048,7 +4049,7 @@ static int cgroup_write_event_control(struct cgroup_subsys_state *css, event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) return -ENOMEM; - event->cgrp = cgrp; + event->css = css; INIT_LIST_HEAD(&event->list); init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc); init_waitqueue_func_entry(&event->wait, cgroup_event_wake); @@ -4099,7 +4100,7 @@ static int cgroup_write_event_control(struct cgroup_subsys_state *css, goto out_put_cfile; } - ret = event->cft->register_event(cgrp, event->cft, + ret = event->cft->register_event(css, event->cft, event->eventfd, buffer); if (ret) goto out_put_cfile; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 95106a993777..2885e3e85047 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1034,11 +1034,6 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) preempt_enable(); } -static inline struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) -{ - return mem_cgroup_from_css(cgroup_css(cont, mem_cgroup_subsys_id)); -} - struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) { /* @@ -5620,10 +5615,10 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg) mem_cgroup_oom_notify_cb(iter); } -static int mem_cgroup_usage_register_event(struct cgroup *cgrp, +static int mem_cgroup_usage_register_event(struct cgroup_subsys_state *css, struct cftype *cft, struct eventfd_ctx *eventfd, const char *args) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; enum res_type type = MEMFILE_TYPE(cft->private); @@ -5703,10 +5698,10 @@ unlock: return ret; } -static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp, +static void mem_cgroup_usage_unregister_event(struct cgroup_subsys_state *css, struct cftype *cft, struct eventfd_ctx *eventfd) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_thresholds *thresholds; struct mem_cgroup_threshold_ary *new; enum res_type type = MEMFILE_TYPE(cft->private); @@ -5782,10 +5777,10 @@ unlock: mutex_unlock(&memcg->thresholds_lock); } -static int mem_cgroup_oom_register_event(struct cgroup *cgrp, +static int mem_cgroup_oom_register_event(struct cgroup_subsys_state *css, struct cftype *cft, struct eventfd_ctx *eventfd, const char *args) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_eventfd_list *event; enum res_type type = MEMFILE_TYPE(cft->private); @@ -5807,10 +5802,10 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp, return 0; } -static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, +static void mem_cgroup_oom_unregister_event(struct cgroup_subsys_state *css, struct cftype *cft, struct eventfd_ctx *eventfd) { - struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_eventfd_list *ev, *tmp; enum res_type type = MEMFILE_TYPE(cft->private); diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 2a8a736e95cc..13489b1f4ee3 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -74,11 +74,6 @@ static struct vmpressure *work_to_vmpressure(struct work_struct *work) return container_of(work, struct vmpressure, work); } -static struct vmpressure *cg_to_vmpressure(struct cgroup *cg) -{ - return css_to_vmpressure(cgroup_css(cg, mem_cgroup_subsys_id)); -} - static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) { struct cgroup_subsys_state *css = vmpressure_to_css(vmpr); @@ -283,7 +278,7 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) /** * vmpressure_register_event() - Bind vmpressure notifications to an eventfd - * @cg: cgroup that is interested in vmpressure notifications + * @css: css that is interested in vmpressure notifications * @cft: cgroup control files handle * @eventfd: eventfd context to link notifications with * @args: event arguments (used to set up a pressure level threshold) @@ -298,10 +293,11 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) * cftype).register_event, and then cgroup core will handle everything by * itself. */ -int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, - struct eventfd_ctx *eventfd, const char *args) +int vmpressure_register_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd, + const char *args) { - struct vmpressure *vmpr = cg_to_vmpressure(cg); + struct vmpressure *vmpr = css_to_vmpressure(css); struct vmpressure_event *ev; int level; @@ -329,7 +325,7 @@ int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, /** * vmpressure_unregister_event() - Unbind eventfd from vmpressure - * @cg: cgroup handle + * @css: css handle * @cft: cgroup control files handle * @eventfd: eventfd context that was used to link vmpressure with the @cg * @@ -341,10 +337,11 @@ int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, * cftype).unregister_event, and then cgroup core will handle everything * by itself. */ -void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft, +void vmpressure_unregister_event(struct cgroup_subsys_state *css, + struct cftype *cft, struct eventfd_ctx *eventfd) { - struct vmpressure *vmpr = cg_to_vmpressure(cg); + struct vmpressure *vmpr = css_to_vmpressure(css); struct vmpressure_event *ev; mutex_lock(&vmpr->events_lock); -- cgit v1.2.3-71-gd317 From d99c8727e7bbc01b70e2c57e6127bfab26b868fd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: make cgroup_taskset deal with cgroup_subsys_state instead of cgroup cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway. cgroup_taskset which is used by the subsystem attach methods is the last cgroup subsystem API which isn't using css as the handle. Update cgroup_taskset_cur_cgroup() to cgroup_taskset_cur_css() and cgroup_taskset_for_each() to take @skip_css instead of @skip_cgrp. The conversions are pretty mechanical. One exception is cpuset::cgroup_cs(), which lost its last user and got removed. This patch shouldn't introduce any functional changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Daniel Wagner Cc: Ingo Molnar Cc: Matt Helsley Cc: Steven Rostedt --- block/blk-cgroup.c | 2 +- include/linux/cgroup.h | 12 +++++++----- kernel/cgroup.c | 16 +++++++++------- kernel/cgroup_freezer.c | 2 +- kernel/cpuset.c | 15 +++++---------- kernel/events/core.c | 2 +- kernel/sched/core.c | 4 ++-- net/core/netprio_cgroup.c | 2 +- net/sched/cls_cgroup.c | 2 +- 9 files changed, 28 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4b40640240a4..54ad00292edf 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -891,7 +891,7 @@ static int blkcg_can_attach(struct cgroup_subsys_state *css, int ret = 0; /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, css->cgroup, tset) { + cgroup_taskset_for_each(task, css, tset) { task_lock(task); ioc = task->io_context; if (ioc && atomic_read(&ioc->nr_tasks) > 1) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b065d24486e6..d9a970568be9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -562,20 +562,22 @@ int cgroup_task_count(const struct cgroup *cgrp); struct cgroup_taskset; struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); -struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset); +struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset, + int subsys_id); int cgroup_taskset_size(struct cgroup_taskset *tset); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor - * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all + * @skip_css: skip if task's css matches this, %NULL to iterate through all * @tset: taskset to iterate */ -#define cgroup_taskset_for_each(task, skip_cgrp, tset) \ +#define cgroup_taskset_for_each(task, skip_css, tset) \ for ((task) = cgroup_taskset_first((tset)); (task); \ (task) = cgroup_taskset_next((tset))) \ - if (!(skip_cgrp) || \ - cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp)) + if (!(skip_css) || \ + cgroup_taskset_cur_css((tset), \ + (skip_css)->ss->subsys_id) != (skip_css)) /* * Control Group subsystem type. diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a71f2e0f9711..e5bfb2a81dcb 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1907,18 +1907,20 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) EXPORT_SYMBOL_GPL(cgroup_taskset_next); /** - * cgroup_taskset_cur_cgroup - return the matching cgroup for the current task + * cgroup_taskset_cur_css - return the matching css for the current task * @tset: taskset of interest + * @subsys_id: the ID of the target subsystem * - * Return the cgroup for the current (last returned) task of @tset. This - * function must be preceded by either cgroup_taskset_first() or - * cgroup_taskset_next(). + * Return the css for the current (last returned) task of @tset for + * subsystem specified by @subsys_id. This function must be preceded by + * either cgroup_taskset_first() or cgroup_taskset_next(). */ -struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset) +struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset, + int subsys_id) { - return tset->cur_cgrp; + return cgroup_css(tset->cur_cgrp, subsys_id); } -EXPORT_SYMBOL_GPL(cgroup_taskset_cur_cgroup); +EXPORT_SYMBOL_GPL(cgroup_taskset_cur_css); /** * cgroup_taskset_size - return the number of tasks in taskset diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 5cd2b6d55243..224da9aa27f5 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -189,7 +189,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ - cgroup_taskset_for_each(task, new_css->cgroup, tset) { + cgroup_taskset_for_each(task, new_css, tset) { if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 39e52175f4af..bf69717325b4 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -119,12 +119,6 @@ static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) return css ? container_of(css, struct cpuset, css) : NULL; } -/* Retrieve the cpuset for a cgroup */ -static inline struct cpuset *cgroup_cs(struct cgroup *cgrp) -{ - return css_cs(cgroup_css(cgrp, cpuset_subsys_id)); -} - /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { @@ -1459,7 +1453,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css, (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; - cgroup_taskset_for_each(task, css->cgroup, tset) { + cgroup_taskset_for_each(task, css, tset) { /* * Kthreads which disallow setaffinity shouldn't be moved * to a new cpuset; we don't want to change their cpu @@ -1511,9 +1505,10 @@ static void cpuset_attach(struct cgroup_subsys_state *css, struct mm_struct *mm; struct task_struct *task; struct task_struct *leader = cgroup_taskset_first(tset); - struct cgroup *oldcgrp = cgroup_taskset_cur_cgroup(tset); + struct cgroup_subsys_state *oldcss = cgroup_taskset_cur_css(tset, + cpuset_subsys_id); struct cpuset *cs = css_cs(css); - struct cpuset *oldcs = cgroup_cs(oldcgrp); + struct cpuset *oldcs = css_cs(oldcss); struct cpuset *cpus_cs = effective_cpumask_cpuset(cs); struct cpuset *mems_cs = effective_nodemask_cpuset(cs); @@ -1527,7 +1522,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, css->cgroup, tset) { + cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here diff --git a/kernel/events/core.c b/kernel/events/core.c index 9705a0ed1dce..c199c4f24910 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7816,7 +7816,7 @@ static void perf_cgroup_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css->cgroup, tset) + cgroup_taskset_for_each(task, css, tset) task_function_call(task, __perf_cgroup_move, task); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index cc9a49266382..a7122d5b8310 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7135,7 +7135,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css->cgroup, tset) { + cgroup_taskset_for_each(task, css, tset) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; @@ -7153,7 +7153,7 @@ static void cpu_cgroup_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css->cgroup, tset) + cgroup_taskset_for_each(task, css, tset) sched_move_task(task); } diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index e00f60e5baea..d9cd627e6a16 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -224,7 +224,7 @@ static void net_prio_attach(struct cgroup_subsys_state *css, struct task_struct *p; void *v; - cgroup_taskset_for_each(p, css->cgroup, tset) { + cgroup_taskset_for_each(p, css, tset) { task_lock(p); v = (void *)(unsigned long)task_netprioidx(p); iterate_fd(p->files, 0, update_netprio, v); diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 8ea1184cec92..867b4a3e3980 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -74,7 +74,7 @@ static void cgrp_attach(struct cgroup_subsys_state *css, struct task_struct *p; void *v; - cgroup_taskset_for_each(p, css->cgroup, tset) { + cgroup_taskset_for_each(p, css, tset) { task_lock(p); v = (void *)(unsigned long)task_cls_classid(p); iterate_fd(p->files, 0, update_classid, v); -- cgit v1.2.3-71-gd317 From 95109b627ba6a043c181fa5fa45d1c754dd44fbc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: unexport cgroup_css() cgroup_css() no longer has any user left outside cgroup.c proper and we don't want subsystems to grow new usages of the function. cgroup core should always provide the css to use to the subsystems, which will make dynamic creation and destruction of css's across the lifetime of a cgroup much more manageable than exposing the cgroup directly to subsystems and let them dereference css's from it. Make cgroup_css() a static function in cgroup.c. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 13 ------------- kernel/cgroup.c | 13 +++++++++++++ 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index d9a970568be9..c40e508d54e9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -677,19 +677,6 @@ struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) return &parent_cgrp->dummy_css; } -/** - * cgroup_css - obtain a cgroup's css for the specified subsystem - * @cgrp: the cgroup of interest - * @subsys_id: the subsystem of interest - * - * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. - */ -static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, - int subsys_id) -{ - return cgrp->subsys[subsys_id]; -} - /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e5bfb2a81dcb..c02a288a4e3d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -222,6 +222,19 @@ static int cgroup_destroy_locked(struct cgroup *cgrp); static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], bool is_add); +/** + * cgroup_css - obtain a cgroup's css for the specified subsystem + * @cgrp: the cgroup of interest + * @subsys_id: the subsystem of interest + * + * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. + */ +static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, + int subsys_id) +{ + return cgrp->subsys[subsys_id]; +} + /* convenient tests for these bits */ static inline bool cgroup_is_dead(const struct cgroup *cgrp) { -- cgit v1.2.3-71-gd317 From bd8815a6d802fc16a7a106e170593aa05dc17e72 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 8 Aug 2013 20:11:27 -0400 Subject: cgroup: make css_for_each_descendant() and friends include the origin css in the iteration Previously, all css descendant iterators didn't include the origin (root of subtree) css in the iteration. The reasons were maintaining consistency with css_for_each_child() and that at the time of introduction more use cases needed skipping the origin anyway; however, given that css_is_descendant() considers self to be a descendant, omitting the origin css has become more confusing and looking at the accumulated use cases rather clearly indicates that including origin would result in simpler code overall. While this is a change which can easily lead to subtle bugs, cgroup API including the iterators has recently gone through major restructuring and no out-of-tree changes will be applicable without adjustments making this a relatively acceptable opportunity for this type of change. The conversions are mostly straight-forward. If the iteration block had explicit origin handling before or after, it's moved inside the iteration. If not, if (pos == origin) continue; is added. Some conversions add extra reference get/put around origin handling by consolidating origin handling and the rest. While the extra ref operations aren't strictly necessary, this shouldn't cause any noticeable difference. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Vivek Goyal Acked-by: Aristeu Rozanski Acked-by: Michal Hocko Cc: Jens Axboe Cc: Matt Helsley Cc: Johannes Weiner Cc: Balbir Singh --- block/blk-cgroup.c | 8 ++------ block/blk-cgroup.h | 4 +++- block/blk-throttle.c | 3 --- include/linux/cgroup.h | 17 +++++++++-------- kernel/cgroup.c | 29 +++++++++++------------------ kernel/cgroup_freezer.c | 29 ++++++++++++++++------------- kernel/cpuset.c | 42 ++++++++++++++++++++++++++---------------- mm/memcontrol.c | 9 +-------- security/device_cgroup.c | 2 +- 9 files changed, 69 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 54ad00292edf..e90c7c164c83 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -615,12 +615,10 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off) struct blkcg_policy *pol = blkcg_policy[pd->plid]; struct blkcg_gq *pos_blkg; struct cgroup_subsys_state *pos_css; - u64 sum; + u64 sum = 0; lockdep_assert_held(pd->blkg->q->queue_lock); - sum = blkg_stat_read((void *)pd + off); - rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) { struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol); @@ -650,13 +648,11 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd, struct blkcg_policy *pol = blkcg_policy[pd->plid]; struct blkcg_gq *pos_blkg; struct cgroup_subsys_state *pos_css; - struct blkg_rwstat sum; + struct blkg_rwstat sum = { }; int i; lockdep_assert_held(pd->blkg->q->queue_lock); - sum = blkg_rwstat_read((void *)pd + off); - rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) { struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol); diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 855538630300..ae6969a7ffd4 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -291,6 +291,7 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, * read locked. If called under either blkcg or queue lock, the iteration * is guaranteed to include all and only online blkgs. The caller may * update @pos_css by calling css_rightmost_descendant() to skip subtree. + * @p_blkg is included in the iteration and the first node to be visited. */ #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ @@ -304,7 +305,8 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, * @p_blkg: target blkg to walk descendants of * * Similar to blkg_for_each_descendant_pre() but performs post-order - * traversal instead. Synchronization rules are the same. + * traversal instead. Synchronization rules are the same. @p_blkg is + * included in the iteration and the last node to be visited. */ #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 8cefa7f8590e..8331aba9426f 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1379,7 +1379,6 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft, * restrictions in the whole hierarchy and allows them to bypass * blk-throttle. */ - tg_update_has_rules(tg); blkg_for_each_descendant_pre(blkg, pos_css, ctx.blkg) tg_update_has_rules(blkg_to_tg(blkg)); @@ -1639,8 +1638,6 @@ void blk_throtl_drain(struct request_queue *q) blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) tg_drain_bios(&blkg_to_tg(blkg)->service_queue); - tg_drain_bios(&td_root_tg(td)->service_queue); - /* finally, transfer bios from top-level tg's into the td */ tg_drain_bios(&td->service_queue); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c40e508d54e9..8ec5b0f38292 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -798,7 +798,8 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * - * Walk @root's descendants. Must be called under rcu_read_lock(). A + * Walk @root's descendants. @root is included in the iteration and the + * first node to be visited. Must be called under rcu_read_lock(). A * descendant css which hasn't finished ->css_online() or already has * finished ->css_offline() may show up during traversal and it's each * subsystem's responsibility to verify that each @pos is alive. @@ -820,13 +821,12 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos); * * my_update_state(@css) * { - * Lock @css; - * Update @css's state; - * Unlock @css; - * * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; - * Verify @pos is alive and inherit state from @pos's parent; + * if (@pos == @css) + * Update @css's state; + * else + * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } @@ -864,8 +864,9 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order - * traversal instead. Note that the walk visibility guarantee described in - * pre-order walk doesn't apply the same to post-order walks. + * traversal instead. @root is included in the iteration and the last + * node to be visited. Note that the walk visibility guarantee described + * in pre-order walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c02a288a4e3d..52f0498db946 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2868,17 +2868,6 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) mutex_unlock(&cgroup_mutex); - /* @root always needs to be updated */ - inode = root->dentry->d_inode; - mutex_lock(&inode->i_mutex); - mutex_lock(&cgroup_mutex); - ret = cgroup_addrm_files(root, cfts, is_add); - mutex_unlock(&cgroup_mutex); - mutex_unlock(&inode->i_mutex); - - if (ret) - goto out_deact; - /* add/rm files for all cgroups created before */ rcu_read_lock(); css_for_each_descendant_pre(css, cgroup_css(root, ss->subsys_id)) { @@ -2907,7 +2896,6 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) } rcu_read_unlock(); dput(prev); -out_deact: deactivate_super(sb); return ret; } @@ -3099,7 +3087,8 @@ EXPORT_SYMBOL_GPL(css_next_child); * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant - * to visit for pre-order traversal of @root's descendants. + * to visit for pre-order traversal of @root's descendants. @root is + * included in the iteration and the first node to be visited. * * While this function requires RCU read locking, it doesn't require the * whole traversal to be contained in a single RCU critical section. This @@ -3114,9 +3103,9 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos, WARN_ON_ONCE(!rcu_read_lock_held()); - /* if first iteration, pretend we just visited @root */ + /* if first iteration, visit @root */ if (!pos) - pos = root; + return root; /* visit the first child if exists */ next = css_next_child(NULL, pos); @@ -3186,7 +3175,8 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant - * to visit for post-order traversal of @root's descendants. + * to visit for post-order traversal of @root's descendants. @root is + * included in the iteration and the last node to be visited. * * While this function requires RCU read locking, it doesn't require the * whole traversal to be contained in a single RCU critical section. This @@ -3207,14 +3197,17 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, return next != root ? next : NULL; } + /* if we visited @root, we're done */ + if (pos == root) + return NULL; + /* if there's an unvisited sibling, visit its leftmost descendant */ next = css_next_child(pos, css_parent(pos)); if (next) return css_leftmost_descendant(next); /* no sibling left, visit parent */ - next = css_parent(pos); - return next != root ? next : NULL; + return css_parent(pos); } EXPORT_SYMBOL_GPL(css_next_descendant_post); diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 224da9aa27f5..f0ff64d0ebaa 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -311,7 +311,6 @@ static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft, /* update states bottom-up */ css_for_each_descendant_post(pos, css) update_if_frozen(pos); - update_if_frozen(css); rcu_read_unlock(); @@ -391,11 +390,6 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) { struct cgroup_subsys_state *pos; - /* update @freezer */ - spin_lock_irq(&freezer->lock); - freezer_apply_state(freezer, freeze, CGROUP_FREEZING_SELF); - spin_unlock_irq(&freezer->lock); - /* * Update all its descendants in pre-order traversal. Each * descendant will try to inherit its parent's FREEZING state as @@ -406,14 +400,23 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) struct freezer *pos_f = css_freezer(pos); struct freezer *parent = parent_freezer(pos_f); - /* - * Our update to @parent->state is already visible which is - * all we need. No need to lock @parent. For more info on - * synchronization, see freezer_post_create(). - */ spin_lock_irq(&pos_f->lock); - freezer_apply_state(pos_f, parent->state & CGROUP_FREEZING, - CGROUP_FREEZING_PARENT); + + if (pos_f == freezer) { + freezer_apply_state(pos_f, freeze, + CGROUP_FREEZING_SELF); + } else { + /* + * Our update to @parent->state is already visible + * which is all we need. No need to lock @parent. + * For more info on synchronization, see + * freezer_post_create(). + */ + freezer_apply_state(pos_f, + parent->state & CGROUP_FREEZING, + CGROUP_FREEZING_PARENT); + } + spin_unlock_irq(&pos_f->lock); } rcu_read_unlock(); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index bf69717325b4..72a0383f382f 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -222,7 +222,8 @@ static struct cpuset top_cpuset = { * * Walk @des_cs through the online descendants of @root_cs. Must be used * with RCU read locked. The caller may modify @pos_css by calling - * css_rightmost_descendant() to skip subtree. + * css_rightmost_descendant() to skip subtree. @root_cs is included in the + * iteration and the first node to be visited. */ #define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ @@ -506,6 +507,9 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { + if (cp == root_cs) + continue; + /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); @@ -613,6 +617,8 @@ static int generate_sched_domains(cpumask_var_t **domains, rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { + if (cp == &top_cpuset) + continue; /* * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The @@ -875,15 +881,17 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs, struct cpuset *cp; struct cgroup_subsys_state *pos_css; - if (update_root) - update_tasks_cpumask(root_cs, heap); - rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { - /* skip the whole subtree if @cp have some CPU */ - if (!cpumask_empty(cp->cpus_allowed)) { - pos_css = css_rightmost_descendant(pos_css); - continue; + if (cp == root_cs) { + if (!update_root) + continue; + } else { + /* skip the whole subtree if @cp have some CPU */ + if (!cpumask_empty(cp->cpus_allowed)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } } if (!css_tryget(&cp->css)) continue; @@ -1130,15 +1138,17 @@ static void update_tasks_nodemask_hier(struct cpuset *root_cs, struct cpuset *cp; struct cgroup_subsys_state *pos_css; - if (update_root) - update_tasks_nodemask(root_cs, heap); - rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { - /* skip the whole subtree if @cp have some CPU */ - if (!nodes_empty(cp->mems_allowed)) { - pos_css = css_rightmost_descendant(pos_css); - continue; + if (cp == root_cs) { + if (!update_root) + continue; + } else { + /* skip the whole subtree if @cp have some CPU */ + if (!nodes_empty(cp->mems_allowed)) { + pos_css = css_rightmost_descendant(pos_css); + continue; + } } if (!css_tryget(&cp->css)) continue; @@ -2237,7 +2247,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { - if (!css_tryget(&cs->css)) + if (cs == &top_cpuset || !css_tryget(&cs->css)) continue; rcu_read_unlock(); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2885e3e85047..b89d4cbc0c08 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1079,14 +1079,7 @@ static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, { struct cgroup_subsys_state *prev_css, *next_css; - /* - * Root is not visited by cgroup iterators so it needs an - * explicit visit. - */ - if (!last_visited) - return root; - - prev_css = (last_visited == root) ? NULL : &last_visited->css; + prev_css = last_visited ? &last_visited->css : NULL; skip_node: next_css = css_next_descendant_pre(prev_css, &root->css); diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 9bf230aa28b0..c123628d3f84 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -456,7 +456,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root, * methods), and online ones are safe to access outside RCU * read lock without bumping refcnt. */ - if (!is_devcg_online(devcg)) + if (pos == &devcg_root->css || !is_devcg_online(devcg)) continue; rcu_read_unlock(); -- cgit v1.2.3-71-gd317 From 3fa4d7344be0afebd80382ffeea6b1787cccf971 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 26 Jul 2013 12:16:42 +0200 Subject: usb: phy: rename nop_usb_xceiv => usb_phy_gen_xceiv The "nop" driver isn't a do-nothing-stub but supports a couple functions like clock on/off or is able to use a voltage regulator. This patch simply renames the driver to "generic" since it is easy possible to extend it by a simple function istead of writing a complete driver. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi --- arch/arm/mach-omap2/board-omap3beagle.c | 4 +- arch/arm/mach-omap2/board-omap3evm.c | 4 +- arch/arm/mach-omap2/board-omap3pandora.c | 2 +- arch/arm/mach-omap2/usb-host.c | 10 +- drivers/usb/dwc3/dwc3-exynos.c | 8 +- drivers/usb/dwc3/dwc3-pci.c | 8 +- drivers/usb/musb/am35x.c | 2 +- drivers/usb/musb/blackfin.c | 2 +- drivers/usb/musb/da8xx.c | 2 +- drivers/usb/musb/davinci.c | 2 +- drivers/usb/musb/musb_dsps.c | 2 +- drivers/usb/musb/tusb6010.c | 2 +- drivers/usb/phy/Makefile | 2 +- drivers/usb/phy/phy-generic.c | 292 +++++++++++++++++++++++++++++++ drivers/usb/phy/phy-nop.c | 292 ------------------------------- include/linux/usb/nop-usb-xceiv.h | 29 --- include/linux/usb/usb_phy_gen_xceiv.h | 29 +++ 17 files changed, 346 insertions(+), 346 deletions(-) create mode 100644 drivers/usb/phy/phy-generic.c delete mode 100644 drivers/usb/phy/phy-nop.c delete mode 100644 include/linux/usb/nop-usb-xceiv.h create mode 100644 include/linux/usb/usb_phy_gen_xceiv.h (limited to 'include/linux') diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c index 04c116555412..1c6ae5f5bae7 100644 --- a/arch/arm/mach-omap2/board-omap3beagle.c +++ b/arch/arm/mach-omap2/board-omap3beagle.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include @@ -279,7 +279,7 @@ static struct regulator_consumer_supply beagle_vsim_supply[] = { static struct gpio_led gpio_leds[]; /* PHY's VCC regulator might be added later, so flag that we need it */ -static struct nop_usb_xceiv_platform_data hsusb2_phy_data = { +static struct usb_phy_gen_xceiv_platform_data hsusb2_phy_data = { .needs_vcc = true, }; diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c index 8c026269baca..52bdddd41e0e 100644 --- a/arch/arm/mach-omap2/board-omap3evm.c +++ b/arch/arm/mach-omap2/board-omap3evm.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include @@ -468,7 +468,7 @@ struct wl12xx_platform_data omap3evm_wlan_data __initdata = { static struct regulator_consumer_supply omap3evm_vaux2_supplies[] = { REGULATOR_SUPPLY("VDD_CSIPHY1", "omap3isp"), /* OMAP ISP */ REGULATOR_SUPPLY("VDD_CSIPHY2", "omap3isp"), /* OMAP ISP */ - REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"), /* hsusb port 2 */ + REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"), /* hsusb port 2 */ REGULATOR_SUPPLY("vaux2", NULL), }; diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c index b1547a0edfcd..d2b455e70486 100644 --- a/arch/arm/mach-omap2/board-omap3pandora.c +++ b/arch/arm/mach-omap2/board-omap3pandora.c @@ -352,7 +352,7 @@ static struct regulator_consumer_supply pandora_vcc_lcd_supply[] = { }; static struct regulator_consumer_supply pandora_usb_phy_supply[] = { - REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"), /* hsusb port 2 */ + REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"), /* hsusb port 2 */ }; /* ads7846 on SPI and 2 nub controllers on I2C */ diff --git a/arch/arm/mach-omap2/usb-host.c b/arch/arm/mach-omap2/usb-host.c index 2eb19d4d0aa1..e83a6a4b184a 100644 --- a/arch/arm/mach-omap2/usb-host.c +++ b/arch/arm/mach-omap2/usb-host.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include "soc.h" #include "omap_device.h" @@ -349,7 +349,7 @@ static struct fixed_voltage_config hsusb_reg_config = { /* .init_data filled later */ }; -static const char *nop_name = "nop_usb_xceiv"; /* NOP PHY driver */ +static const char *nop_name = "usb_phy_gen_xceiv"; /* NOP PHY driver */ static const char *reg_name = "reg-fixed-voltage"; /* Regulator driver */ /** @@ -460,9 +460,9 @@ int usbhs_init_phys(struct usbhs_phy_data *phy, int num_phys) pdevinfo.name = nop_name; pdevinfo.id = phy->port; pdevinfo.data = phy->platform_data; - pdevinfo.size_data = sizeof(struct nop_usb_xceiv_platform_data); - - scnprintf(phy_id, MAX_STR, "nop_usb_xceiv.%d", + pdevinfo.size_data = + sizeof(struct usb_phy_gen_xceiv_platform_data); + scnprintf(phy_id, MAX_STR, "usb_phy_gen_xceiv.%d", phy->port); pdev = platform_device_register_full(&pdevinfo); if (IS_ERR(pdev)) { diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 8ce9d7fd6cfc..a179c5a54b39 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include @@ -34,13 +34,13 @@ struct dwc3_exynos { static int dwc3_exynos_register_phys(struct dwc3_exynos *exynos) { - struct nop_usb_xceiv_platform_data pdata; + struct usb_phy_gen_xceiv_platform_data pdata; struct platform_device *pdev; int ret; memset(&pdata, 0x00, sizeof(pdata)); - pdev = platform_device_alloc("nop_usb_xceiv", PLATFORM_DEVID_AUTO); + pdev = platform_device_alloc("usb_phy_gen_xceiv", PLATFORM_DEVID_AUTO); if (!pdev) return -ENOMEM; @@ -51,7 +51,7 @@ static int dwc3_exynos_register_phys(struct dwc3_exynos *exynos) if (ret) goto err1; - pdev = platform_device_alloc("nop_usb_xceiv", PLATFORM_DEVID_AUTO); + pdev = platform_device_alloc("usb_phy_gen_xceiv", PLATFORM_DEVID_AUTO); if (!pdev) { ret = -ENOMEM; goto err1; diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index ed07ec04a962..87ea3d503fc5 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -43,7 +43,7 @@ #include #include -#include +#include /* FIXME define these in */ #define PCI_VENDOR_ID_SYNOPSYS 0x16c3 @@ -58,13 +58,13 @@ struct dwc3_pci { static int dwc3_pci_register_phys(struct dwc3_pci *glue) { - struct nop_usb_xceiv_platform_data pdata; + struct usb_phy_gen_xceiv_platform_data pdata; struct platform_device *pdev; int ret; memset(&pdata, 0x00, sizeof(pdata)); - pdev = platform_device_alloc("nop_usb_xceiv", 0); + pdev = platform_device_alloc("usb_phy_gen_xceiv", 0); if (!pdev) return -ENOMEM; @@ -75,7 +75,7 @@ static int dwc3_pci_register_phys(struct dwc3_pci *glue) if (ret) goto err1; - pdev = platform_device_alloc("nop_usb_xceiv", 1); + pdev = platform_device_alloc("usb_phy_gen_xceiv", 1); if (!pdev) { ret = -ENOMEM; goto err1; diff --git a/drivers/usb/musb/am35x.c b/drivers/usb/musb/am35x.c index 2231850c0625..5733a209ab95 100644 --- a/drivers/usb/musb/am35x.c +++ b/drivers/usb/musb/am35x.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include "musb_core.h" diff --git a/drivers/usb/musb/blackfin.c b/drivers/usb/musb/blackfin.c index 6ba8439bd5a6..195e96674fff 100644 --- a/drivers/usb/musb/blackfin.c +++ b/drivers/usb/musb/blackfin.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c index 0da6f648a9fe..ccc6b63bc380 100644 --- a/drivers/usb/musb/da8xx.c +++ b/drivers/usb/musb/da8xx.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c index f8aeaf2e2cd1..91f300e93cf4 100644 --- a/drivers/usb/musb/davinci.c +++ b/drivers/usb/musb/davinci.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 5233804d66b1..55fe3c292cd2 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -36,7 +36,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c index 2c06a8969a9f..20f182c6184a 100644 --- a/drivers/usb/musb/tusb6010.c +++ b/drivers/usb/musb/tusb6010.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include "musb_core.h" diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile index 070eca3af18b..24c5816409fd 100644 --- a/drivers/usb/phy/Makefile +++ b/drivers/usb/phy/Makefile @@ -14,7 +14,7 @@ phy-fsl-usb2-objs := phy-fsl-usb.o phy-fsm-usb.o obj-$(CONFIG_FSL_USB2_OTG) += phy-fsl-usb2.o obj-$(CONFIG_ISP1301_OMAP) += phy-isp1301-omap.o obj-$(CONFIG_MV_U3D_PHY) += phy-mv-u3d-usb.o -obj-$(CONFIG_NOP_USB_XCEIV) += phy-nop.o +obj-$(CONFIG_NOP_USB_XCEIV) += phy-generic.o obj-$(CONFIG_OMAP_CONTROL_USB) += phy-omap-control.o obj-$(CONFIG_OMAP_USB2) += phy-omap-usb2.o obj-$(CONFIG_OMAP_USB3) += phy-omap-usb3.o diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c new file mode 100644 index 000000000000..f379b7ded037 --- /dev/null +++ b/drivers/usb/phy/phy-generic.c @@ -0,0 +1,292 @@ +/* + * drivers/usb/otg/nop-usb-xceiv.c + * + * NOP USB transceiver for all USB transceiver which are either built-in + * into USB IP or which are mostly autonomous. + * + * Copyright (C) 2009 Texas Instruments Inc + * Author: Ajay Kumar Gupta + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Current status: + * This provides a "nop" transceiver for PHYs which are + * autonomous such as isp1504, isp1707, etc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct usb_phy_gen_xceiv { + struct usb_phy phy; + struct device *dev; + struct clk *clk; + struct regulator *vcc; + struct regulator *reset; +}; + +static struct platform_device *pd; + +void usb_nop_xceiv_register(void) +{ + if (pd) + return; + pd = platform_device_register_simple("usb_phy_gen_xceiv", -1, NULL, 0); + if (!pd) { + pr_err("Unable to register generic usb transceiver\n"); + return; + } +} +EXPORT_SYMBOL(usb_nop_xceiv_register); + +void usb_nop_xceiv_unregister(void) +{ + platform_device_unregister(pd); + pd = NULL; +} +EXPORT_SYMBOL(usb_nop_xceiv_unregister); + +static int nop_set_suspend(struct usb_phy *x, int suspend) +{ + return 0; +} + +static int nop_init(struct usb_phy *phy) +{ + struct usb_phy_gen_xceiv *nop = dev_get_drvdata(phy->dev); + + if (!IS_ERR(nop->vcc)) { + if (regulator_enable(nop->vcc)) + dev_err(phy->dev, "Failed to enable power\n"); + } + + if (!IS_ERR(nop->clk)) + clk_enable(nop->clk); + + if (!IS_ERR(nop->reset)) { + /* De-assert RESET */ + if (regulator_enable(nop->reset)) + dev_err(phy->dev, "Failed to de-assert reset\n"); + } + + return 0; +} + +static void nop_shutdown(struct usb_phy *phy) +{ + struct usb_phy_gen_xceiv *nop = dev_get_drvdata(phy->dev); + + if (!IS_ERR(nop->reset)) { + /* Assert RESET */ + if (regulator_disable(nop->reset)) + dev_err(phy->dev, "Failed to assert reset\n"); + } + + if (!IS_ERR(nop->clk)) + clk_disable(nop->clk); + + if (!IS_ERR(nop->vcc)) { + if (regulator_disable(nop->vcc)) + dev_err(phy->dev, "Failed to disable power\n"); + } +} + +static int nop_set_peripheral(struct usb_otg *otg, struct usb_gadget *gadget) +{ + if (!otg) + return -ENODEV; + + if (!gadget) { + otg->gadget = NULL; + return -ENODEV; + } + + otg->gadget = gadget; + otg->phy->state = OTG_STATE_B_IDLE; + return 0; +} + +static int nop_set_host(struct usb_otg *otg, struct usb_bus *host) +{ + if (!otg) + return -ENODEV; + + if (!host) { + otg->host = NULL; + return -ENODEV; + } + + otg->host = host; + return 0; +} + +static int usb_phy_gen_xceiv_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct usb_phy_gen_xceiv_platform_data *pdata = pdev->dev.platform_data; + struct usb_phy_gen_xceiv *nop; + enum usb_phy_type type = USB_PHY_TYPE_USB2; + int err; + u32 clk_rate = 0; + bool needs_vcc = false; + bool needs_reset = false; + + nop = devm_kzalloc(&pdev->dev, sizeof(*nop), GFP_KERNEL); + if (!nop) + return -ENOMEM; + + nop->phy.otg = devm_kzalloc(&pdev->dev, sizeof(*nop->phy.otg), + GFP_KERNEL); + if (!nop->phy.otg) + return -ENOMEM; + + if (dev->of_node) { + struct device_node *node = dev->of_node; + + if (of_property_read_u32(node, "clock-frequency", &clk_rate)) + clk_rate = 0; + + needs_vcc = of_property_read_bool(node, "vcc-supply"); + needs_reset = of_property_read_bool(node, "reset-supply"); + + } else if (pdata) { + type = pdata->type; + clk_rate = pdata->clk_rate; + needs_vcc = pdata->needs_vcc; + needs_reset = pdata->needs_reset; + } + + nop->clk = devm_clk_get(&pdev->dev, "main_clk"); + if (IS_ERR(nop->clk)) { + dev_dbg(&pdev->dev, "Can't get phy clock: %ld\n", + PTR_ERR(nop->clk)); + } + + if (!IS_ERR(nop->clk) && clk_rate) { + err = clk_set_rate(nop->clk, clk_rate); + if (err) { + dev_err(&pdev->dev, "Error setting clock rate\n"); + return err; + } + } + + if (!IS_ERR(nop->clk)) { + err = clk_prepare(nop->clk); + if (err) { + dev_err(&pdev->dev, "Error preparing clock\n"); + return err; + } + } + + nop->vcc = devm_regulator_get(&pdev->dev, "vcc"); + if (IS_ERR(nop->vcc)) { + dev_dbg(&pdev->dev, "Error getting vcc regulator: %ld\n", + PTR_ERR(nop->vcc)); + if (needs_vcc) + return -EPROBE_DEFER; + } + + nop->reset = devm_regulator_get(&pdev->dev, "reset"); + if (IS_ERR(nop->reset)) { + dev_dbg(&pdev->dev, "Error getting reset regulator: %ld\n", + PTR_ERR(nop->reset)); + if (needs_reset) + return -EPROBE_DEFER; + } + + nop->dev = &pdev->dev; + nop->phy.dev = nop->dev; + nop->phy.label = "nop-xceiv"; + nop->phy.set_suspend = nop_set_suspend; + nop->phy.init = nop_init; + nop->phy.shutdown = nop_shutdown; + nop->phy.state = OTG_STATE_UNDEFINED; + nop->phy.type = type; + + nop->phy.otg->phy = &nop->phy; + nop->phy.otg->set_host = nop_set_host; + nop->phy.otg->set_peripheral = nop_set_peripheral; + + err = usb_add_phy_dev(&nop->phy); + if (err) { + dev_err(&pdev->dev, "can't register transceiver, err: %d\n", + err); + goto err_add; + } + + platform_set_drvdata(pdev, nop); + + ATOMIC_INIT_NOTIFIER_HEAD(&nop->phy.notifier); + + return 0; + +err_add: + if (!IS_ERR(nop->clk)) + clk_unprepare(nop->clk); + return err; +} + +static int usb_phy_gen_xceiv_remove(struct platform_device *pdev) +{ + struct usb_phy_gen_xceiv *nop = platform_get_drvdata(pdev); + + if (!IS_ERR(nop->clk)) + clk_unprepare(nop->clk); + + usb_remove_phy(&nop->phy); + + return 0; +} + +static const struct of_device_id nop_xceiv_dt_ids[] = { + { .compatible = "usb-nop-xceiv" }, + { } +}; + +MODULE_DEVICE_TABLE(of, nop_xceiv_dt_ids); + +static struct platform_driver usb_phy_gen_xceiv_driver = { + .probe = usb_phy_gen_xceiv_probe, + .remove = usb_phy_gen_xceiv_remove, + .driver = { + .name = "usb_phy_gen_xceiv", + .owner = THIS_MODULE, + .of_match_table = nop_xceiv_dt_ids, + }, +}; + +static int __init usb_phy_gen_xceiv_init(void) +{ + return platform_driver_register(&usb_phy_gen_xceiv_driver); +} +subsys_initcall(usb_phy_gen_xceiv_init); + +static void __exit usb_phy_gen_xceiv_exit(void) +{ + platform_driver_unregister(&usb_phy_gen_xceiv_driver); +} +module_exit(usb_phy_gen_xceiv_exit); + +MODULE_ALIAS("platform:usb_phy_gen_xceiv"); +MODULE_AUTHOR("Texas Instruments Inc"); +MODULE_DESCRIPTION("NOP USB Transceiver driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/usb/phy/phy-nop.c b/drivers/usb/phy/phy-nop.c deleted file mode 100644 index 55445e5d72e5..000000000000 --- a/drivers/usb/phy/phy-nop.c +++ /dev/null @@ -1,292 +0,0 @@ -/* - * drivers/usb/otg/nop-usb-xceiv.c - * - * NOP USB transceiver for all USB transceiver which are either built-in - * into USB IP or which are mostly autonomous. - * - * Copyright (C) 2009 Texas Instruments Inc - * Author: Ajay Kumar Gupta - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * Current status: - * This provides a "nop" transceiver for PHYs which are - * autonomous such as isp1504, isp1707, etc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct nop_usb_xceiv { - struct usb_phy phy; - struct device *dev; - struct clk *clk; - struct regulator *vcc; - struct regulator *reset; -}; - -static struct platform_device *pd; - -void usb_nop_xceiv_register(void) -{ - if (pd) - return; - pd = platform_device_register_simple("nop_usb_xceiv", -1, NULL, 0); - if (!pd) { - printk(KERN_ERR "Unable to register usb nop transceiver\n"); - return; - } -} -EXPORT_SYMBOL(usb_nop_xceiv_register); - -void usb_nop_xceiv_unregister(void) -{ - platform_device_unregister(pd); - pd = NULL; -} -EXPORT_SYMBOL(usb_nop_xceiv_unregister); - -static int nop_set_suspend(struct usb_phy *x, int suspend) -{ - return 0; -} - -static int nop_init(struct usb_phy *phy) -{ - struct nop_usb_xceiv *nop = dev_get_drvdata(phy->dev); - - if (!IS_ERR(nop->vcc)) { - if (regulator_enable(nop->vcc)) - dev_err(phy->dev, "Failed to enable power\n"); - } - - if (!IS_ERR(nop->clk)) - clk_enable(nop->clk); - - if (!IS_ERR(nop->reset)) { - /* De-assert RESET */ - if (regulator_enable(nop->reset)) - dev_err(phy->dev, "Failed to de-assert reset\n"); - } - - return 0; -} - -static void nop_shutdown(struct usb_phy *phy) -{ - struct nop_usb_xceiv *nop = dev_get_drvdata(phy->dev); - - if (!IS_ERR(nop->reset)) { - /* Assert RESET */ - if (regulator_disable(nop->reset)) - dev_err(phy->dev, "Failed to assert reset\n"); - } - - if (!IS_ERR(nop->clk)) - clk_disable(nop->clk); - - if (!IS_ERR(nop->vcc)) { - if (regulator_disable(nop->vcc)) - dev_err(phy->dev, "Failed to disable power\n"); - } -} - -static int nop_set_peripheral(struct usb_otg *otg, struct usb_gadget *gadget) -{ - if (!otg) - return -ENODEV; - - if (!gadget) { - otg->gadget = NULL; - return -ENODEV; - } - - otg->gadget = gadget; - otg->phy->state = OTG_STATE_B_IDLE; - return 0; -} - -static int nop_set_host(struct usb_otg *otg, struct usb_bus *host) -{ - if (!otg) - return -ENODEV; - - if (!host) { - otg->host = NULL; - return -ENODEV; - } - - otg->host = host; - return 0; -} - -static int nop_usb_xceiv_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct nop_usb_xceiv_platform_data *pdata = pdev->dev.platform_data; - struct nop_usb_xceiv *nop; - enum usb_phy_type type = USB_PHY_TYPE_USB2; - int err; - u32 clk_rate = 0; - bool needs_vcc = false; - bool needs_reset = false; - - nop = devm_kzalloc(&pdev->dev, sizeof(*nop), GFP_KERNEL); - if (!nop) - return -ENOMEM; - - nop->phy.otg = devm_kzalloc(&pdev->dev, sizeof(*nop->phy.otg), - GFP_KERNEL); - if (!nop->phy.otg) - return -ENOMEM; - - if (dev->of_node) { - struct device_node *node = dev->of_node; - - if (of_property_read_u32(node, "clock-frequency", &clk_rate)) - clk_rate = 0; - - needs_vcc = of_property_read_bool(node, "vcc-supply"); - needs_reset = of_property_read_bool(node, "reset-supply"); - - } else if (pdata) { - type = pdata->type; - clk_rate = pdata->clk_rate; - needs_vcc = pdata->needs_vcc; - needs_reset = pdata->needs_reset; - } - - nop->clk = devm_clk_get(&pdev->dev, "main_clk"); - if (IS_ERR(nop->clk)) { - dev_dbg(&pdev->dev, "Can't get phy clock: %ld\n", - PTR_ERR(nop->clk)); - } - - if (!IS_ERR(nop->clk) && clk_rate) { - err = clk_set_rate(nop->clk, clk_rate); - if (err) { - dev_err(&pdev->dev, "Error setting clock rate\n"); - return err; - } - } - - if (!IS_ERR(nop->clk)) { - err = clk_prepare(nop->clk); - if (err) { - dev_err(&pdev->dev, "Error preparing clock\n"); - return err; - } - } - - nop->vcc = devm_regulator_get(&pdev->dev, "vcc"); - if (IS_ERR(nop->vcc)) { - dev_dbg(&pdev->dev, "Error getting vcc regulator: %ld\n", - PTR_ERR(nop->vcc)); - if (needs_vcc) - return -EPROBE_DEFER; - } - - nop->reset = devm_regulator_get(&pdev->dev, "reset"); - if (IS_ERR(nop->reset)) { - dev_dbg(&pdev->dev, "Error getting reset regulator: %ld\n", - PTR_ERR(nop->reset)); - if (needs_reset) - return -EPROBE_DEFER; - } - - nop->dev = &pdev->dev; - nop->phy.dev = nop->dev; - nop->phy.label = "nop-xceiv"; - nop->phy.set_suspend = nop_set_suspend; - nop->phy.init = nop_init; - nop->phy.shutdown = nop_shutdown; - nop->phy.state = OTG_STATE_UNDEFINED; - nop->phy.type = type; - - nop->phy.otg->phy = &nop->phy; - nop->phy.otg->set_host = nop_set_host; - nop->phy.otg->set_peripheral = nop_set_peripheral; - - err = usb_add_phy_dev(&nop->phy); - if (err) { - dev_err(&pdev->dev, "can't register transceiver, err: %d\n", - err); - goto err_add; - } - - platform_set_drvdata(pdev, nop); - - ATOMIC_INIT_NOTIFIER_HEAD(&nop->phy.notifier); - - return 0; - -err_add: - if (!IS_ERR(nop->clk)) - clk_unprepare(nop->clk); - return err; -} - -static int nop_usb_xceiv_remove(struct platform_device *pdev) -{ - struct nop_usb_xceiv *nop = platform_get_drvdata(pdev); - - if (!IS_ERR(nop->clk)) - clk_unprepare(nop->clk); - - usb_remove_phy(&nop->phy); - - return 0; -} - -static const struct of_device_id nop_xceiv_dt_ids[] = { - { .compatible = "usb-nop-xceiv" }, - { } -}; - -MODULE_DEVICE_TABLE(of, nop_xceiv_dt_ids); - -static struct platform_driver nop_usb_xceiv_driver = { - .probe = nop_usb_xceiv_probe, - .remove = nop_usb_xceiv_remove, - .driver = { - .name = "nop_usb_xceiv", - .owner = THIS_MODULE, - .of_match_table = nop_xceiv_dt_ids, - }, -}; - -static int __init nop_usb_xceiv_init(void) -{ - return platform_driver_register(&nop_usb_xceiv_driver); -} -subsys_initcall(nop_usb_xceiv_init); - -static void __exit nop_usb_xceiv_exit(void) -{ - platform_driver_unregister(&nop_usb_xceiv_driver); -} -module_exit(nop_usb_xceiv_exit); - -MODULE_ALIAS("platform:nop_usb_xceiv"); -MODULE_AUTHOR("Texas Instruments Inc"); -MODULE_DESCRIPTION("NOP USB Transceiver driver"); -MODULE_LICENSE("GPL"); diff --git a/include/linux/usb/nop-usb-xceiv.h b/include/linux/usb/nop-usb-xceiv.h deleted file mode 100644 index 148d35171aac..000000000000 --- a/include/linux/usb/nop-usb-xceiv.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __LINUX_USB_NOP_XCEIV_H -#define __LINUX_USB_NOP_XCEIV_H - -#include - -struct nop_usb_xceiv_platform_data { - enum usb_phy_type type; - unsigned long clk_rate; - - /* if set fails with -EPROBE_DEFER if can't get regulator */ - unsigned int needs_vcc:1; - unsigned int needs_reset:1; -}; - -#if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) -/* sometimes transceivers are accessed only through e.g. ULPI */ -extern void usb_nop_xceiv_register(void); -extern void usb_nop_xceiv_unregister(void); -#else -static inline void usb_nop_xceiv_register(void) -{ -} - -static inline void usb_nop_xceiv_unregister(void) -{ -} -#endif - -#endif /* __LINUX_USB_NOP_XCEIV_H */ diff --git a/include/linux/usb/usb_phy_gen_xceiv.h b/include/linux/usb/usb_phy_gen_xceiv.h new file mode 100644 index 000000000000..f9a7e7bc925b --- /dev/null +++ b/include/linux/usb/usb_phy_gen_xceiv.h @@ -0,0 +1,29 @@ +#ifndef __LINUX_USB_NOP_XCEIV_H +#define __LINUX_USB_NOP_XCEIV_H + +#include + +struct usb_phy_gen_xceiv_platform_data { + enum usb_phy_type type; + unsigned long clk_rate; + + /* if set fails with -EPROBE_DEFER if can't get regulator */ + unsigned int needs_vcc:1; + unsigned int needs_reset:1; +}; + +#if IS_ENABLED(CONFIG_NOP_USB_XCEIV) +/* sometimes transceivers are accessed only through e.g. ULPI */ +extern void usb_nop_xceiv_register(void); +extern void usb_nop_xceiv_unregister(void); +#else +static inline void usb_nop_xceiv_register(void) +{ +} + +static inline void usb_nop_xceiv_unregister(void) +{ +} +#endif + +#endif /* __LINUX_USB_NOP_XCEIV_H */ -- cgit v1.2.3-71-gd317 From 86f8973c1053cb03e1b1b45989a4e144e05b1735 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 8 Aug 2013 16:09:50 +0200 Subject: spi: new controller driver for efm32 SoCs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Uwe Kleine-König Signed-off-by: Mark Brown --- .../devicetree/bindings/spi/efm32-spi.txt | 34 ++ drivers/spi/Kconfig | 7 + drivers/spi/Makefile | 1 + drivers/spi/spi-efm32.c | 517 +++++++++++++++++++++ include/linux/platform_data/efm32-spi.h | 14 + 5 files changed, 573 insertions(+) create mode 100644 Documentation/devicetree/bindings/spi/efm32-spi.txt create mode 100644 drivers/spi/spi-efm32.c create mode 100644 include/linux/platform_data/efm32-spi.h (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/spi/efm32-spi.txt b/Documentation/devicetree/bindings/spi/efm32-spi.txt new file mode 100644 index 000000000000..a590ca51be75 --- /dev/null +++ b/Documentation/devicetree/bindings/spi/efm32-spi.txt @@ -0,0 +1,34 @@ +* Energy Micro EFM32 SPI + +Required properties: +- #address-cells: see spi-bus.txt +- #size-cells: see spi-bus.txt +- compatible: should be "efm32,spi" +- reg: Offset and length of the register set for the controller +- interrupts: pair specifying rx and tx irq +- clocks: phandle to the spi clock +- cs-gpios: see spi-bus.txt +- location: Value to write to the ROUTE register's LOCATION bitfield to configure the pinmux for the device, see datasheet for values. + +Example: + +spi1: spi@0x4000c400 { /* USART1 */ + #address-cells = <1>; + #size-cells = <0>; + compatible = "efm32,spi"; + reg = <0x4000c400 0x400>; + interrupts = <15 16>; + clocks = <&cmu 20>; + cs-gpios = <&gpio 51 1>; // D3 + location = <1>; + status = "ok"; + + ks8851@0 { + compatible = "ks8851"; + spi-max-frequency = <6000000>; + reg = <0>; + interrupt-parent = <&boardfpga>; + interrupts = <4>; + status = "ok"; + }; +}; diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 89cbbabaff44..f84a77c816bc 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -157,6 +157,13 @@ config SPI_DAVINCI help SPI master controller for DaVinci/DA8x/OMAP-L/AM1x SPI modules. +config SPI_EFM32 + tristate "EFM32 SPI controller" + depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST) + select SPI_BITBANG + help + Driver for the spi controller found on Energy Micro's EFM32 SoCs. + config SPI_EP93XX tristate "Cirrus Logic EP93xx SPI controller" depends on ARCH_EP93XX diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile index 33f9c09561e7..4a1cfb247292 100644 --- a/drivers/spi/Makefile +++ b/drivers/spi/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_SPI_DESIGNWARE) += spi-dw.o obj-$(CONFIG_SPI_DW_MMIO) += spi-dw-mmio.o obj-$(CONFIG_SPI_DW_PCI) += spi-dw-midpci.o spi-dw-midpci-objs := spi-dw-pci.o spi-dw-mid.o +obj-$(CONFIG_SPI_EFM32) += spi-efm32.o obj-$(CONFIG_SPI_EP93XX) += spi-ep93xx.o obj-$(CONFIG_SPI_FALCON) += spi-falcon.o obj-$(CONFIG_SPI_FSL_CPM) += spi-fsl-cpm.o diff --git a/drivers/spi/spi-efm32.c b/drivers/spi/spi-efm32.c new file mode 100644 index 000000000000..ba38452f646f --- /dev/null +++ b/drivers/spi/spi-efm32.c @@ -0,0 +1,517 @@ +/* + * Copyright (C) 2012-2013 Uwe Kleine-Koenig for Pengutronix + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRIVER_NAME "efm32-spi" + +#define MASK_VAL(mask, val) ((val << __ffs(mask)) & mask) + +#define REG_CTRL 0x00 +#define REG_CTRL_SYNC 0x0001 +#define REG_CTRL_CLKPOL 0x0100 +#define REG_CTRL_CLKPHA 0x0200 +#define REG_CTRL_MSBF 0x0400 +#define REG_CTRL_TXBIL 0x1000 + +#define REG_FRAME 0x04 +#define REG_FRAME_DATABITS__MASK 0x000f +#define REG_FRAME_DATABITS(n) ((n) - 3) + +#define REG_CMD 0x0c +#define REG_CMD_RXEN 0x0001 +#define REG_CMD_RXDIS 0x0002 +#define REG_CMD_TXEN 0x0004 +#define REG_CMD_TXDIS 0x0008 +#define REG_CMD_MASTEREN 0x0010 + +#define REG_STATUS 0x10 +#define REG_STATUS_TXENS 0x0002 +#define REG_STATUS_TXC 0x0020 +#define REG_STATUS_TXBL 0x0040 +#define REG_STATUS_RXDATAV 0x0080 + +#define REG_CLKDIV 0x14 + +#define REG_RXDATAX 0x18 +#define REG_RXDATAX_RXDATA__MASK 0x01ff +#define REG_RXDATAX_PERR 0x4000 +#define REG_RXDATAX_FERR 0x8000 + +#define REG_TXDATA 0x34 + +#define REG_IF 0x40 +#define REG_IF_TXBL 0x0002 +#define REG_IF_RXDATAV 0x0004 + +#define REG_IFS 0x44 +#define REG_IFC 0x48 +#define REG_IEN 0x4c + +#define REG_ROUTE 0x54 +#define REG_ROUTE_RXPEN 0x0001 +#define REG_ROUTE_TXPEN 0x0002 +#define REG_ROUTE_CLKPEN 0x0008 +#define REG_ROUTE_LOCATION__MASK 0x0700 +#define REG_ROUTE_LOCATION(n) MASK_VAL(REG_ROUTE_LOCATION__MASK, (n)) + +struct efm32_spi_ddata { + struct spi_bitbang bitbang; + + spinlock_t lock; + + struct clk *clk; + void __iomem *base; + unsigned int rxirq, txirq; + struct efm32_spi_pdata pdata; + + /* irq data */ + struct completion done; + const u8 *tx_buf; + u8 *rx_buf; + unsigned tx_len, rx_len; + + /* chip selects */ + unsigned csgpio[]; +}; + +#define ddata_to_dev(ddata) (&(ddata->bitbang.master->dev)) +#define efm32_spi_vdbg(ddata, format, arg...) \ + dev_vdbg(ddata_to_dev(ddata), format, ##arg) + +static void efm32_spi_write32(struct efm32_spi_ddata *ddata, + u32 value, unsigned offset) +{ + writel_relaxed(value, ddata->base + offset); +} + +static u32 efm32_spi_read32(struct efm32_spi_ddata *ddata, unsigned offset) +{ + return readl_relaxed(ddata->base + offset); +} + +static void efm32_spi_chipselect(struct spi_device *spi, int is_on) +{ + struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master); + int value = !(spi->mode & SPI_CS_HIGH) == !(is_on == BITBANG_CS_ACTIVE); + + gpio_set_value(ddata->csgpio[spi->chip_select], value); +} + +static int efm32_spi_setup_transfer(struct spi_device *spi, + struct spi_transfer *t) +{ + struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master); + + unsigned bpw = t->bits_per_word ?: spi->bits_per_word; + unsigned speed = t->speed_hz ?: spi->max_speed_hz; + unsigned long clkfreq = clk_get_rate(ddata->clk); + u32 clkdiv; + + efm32_spi_write32(ddata, REG_CTRL_SYNC | REG_CTRL_MSBF | + (spi->mode & SPI_CPHA ? REG_CTRL_CLKPHA : 0) | + (spi->mode & SPI_CPOL ? REG_CTRL_CLKPOL : 0), REG_CTRL); + + efm32_spi_write32(ddata, + REG_FRAME_DATABITS(bpw), REG_FRAME); + + if (2 * speed >= clkfreq) + clkdiv = 0; + else + clkdiv = 64 * (DIV_ROUND_UP(2 * clkfreq, speed) - 4); + + if (clkdiv > (1U << 21)) + return -EINVAL; + + efm32_spi_write32(ddata, clkdiv, REG_CLKDIV); + efm32_spi_write32(ddata, REG_CMD_MASTEREN, REG_CMD); + efm32_spi_write32(ddata, REG_CMD_RXEN | REG_CMD_TXEN, REG_CMD); + + return 0; +} + +static void efm32_spi_tx_u8(struct efm32_spi_ddata *ddata) +{ + u8 val = 0; + + if (ddata->tx_buf) { + val = *ddata->tx_buf; + ddata->tx_buf++; + } + + ddata->tx_len--; + efm32_spi_write32(ddata, val, REG_TXDATA); + efm32_spi_vdbg(ddata, "%s: tx 0x%x\n", __func__, val); +} + +static void efm32_spi_rx_u8(struct efm32_spi_ddata *ddata) +{ + u32 rxdata = efm32_spi_read32(ddata, REG_RXDATAX); + efm32_spi_vdbg(ddata, "%s: rx 0x%x\n", __func__, rxdata); + + if (ddata->rx_buf) { + *ddata->rx_buf = rxdata; + ddata->rx_buf++; + } + + ddata->rx_len--; +} + +static void efm32_spi_filltx(struct efm32_spi_ddata *ddata) +{ + while (ddata->tx_len && + ddata->tx_len + 2 > ddata->rx_len && + efm32_spi_read32(ddata, REG_STATUS) & REG_STATUS_TXBL) { + efm32_spi_tx_u8(ddata); + } +} + +static int efm32_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) +{ + struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master); + int ret = -EBUSY; + + spin_lock_irq(&ddata->lock); + + if (ddata->tx_buf || ddata->rx_buf) + goto out_unlock; + + ddata->tx_buf = t->tx_buf; + ddata->rx_buf = t->rx_buf; + ddata->tx_len = ddata->rx_len = + t->len * DIV_ROUND_UP(t->bits_per_word, 8); + + efm32_spi_filltx(ddata); + + init_completion(&ddata->done); + + efm32_spi_write32(ddata, REG_IF_TXBL | REG_IF_RXDATAV, REG_IEN); + + spin_unlock_irq(&ddata->lock); + + wait_for_completion(&ddata->done); + + spin_lock_irq(&ddata->lock); + + ret = t->len - max(ddata->tx_len, ddata->rx_len); + + efm32_spi_write32(ddata, 0, REG_IEN); + ddata->tx_buf = ddata->rx_buf = NULL; + +out_unlock: + spin_unlock_irq(&ddata->lock); + + return ret; +} + +static irqreturn_t efm32_spi_rxirq(int irq, void *data) +{ + struct efm32_spi_ddata *ddata = data; + irqreturn_t ret = IRQ_NONE; + + spin_lock(&ddata->lock); + + while (ddata->rx_len > 0 && + efm32_spi_read32(ddata, REG_STATUS) & + REG_STATUS_RXDATAV) { + efm32_spi_rx_u8(ddata); + + ret = IRQ_HANDLED; + } + + if (!ddata->rx_len) { + u32 ien = efm32_spi_read32(ddata, REG_IEN); + + ien &= ~REG_IF_RXDATAV; + + efm32_spi_write32(ddata, ien, REG_IEN); + + complete(&ddata->done); + } + + spin_unlock(&ddata->lock); + + return ret; +} + +static irqreturn_t efm32_spi_txirq(int irq, void *data) +{ + struct efm32_spi_ddata *ddata = data; + + efm32_spi_vdbg(ddata, + "%s: txlen = %u, rxlen = %u, if=0x%08x, stat=0x%08x\n", + __func__, ddata->tx_len, ddata->rx_len, + efm32_spi_read32(ddata, REG_IF), + efm32_spi_read32(ddata, REG_STATUS)); + + spin_lock(&ddata->lock); + + efm32_spi_filltx(ddata); + + efm32_spi_vdbg(ddata, "%s: txlen = %u, rxlen = %u\n", + __func__, ddata->tx_len, ddata->rx_len); + + if (!ddata->tx_len) { + u32 ien = efm32_spi_read32(ddata, REG_IEN); + + ien &= ~REG_IF_TXBL; + + efm32_spi_write32(ddata, ien, REG_IEN); + efm32_spi_vdbg(ddata, "disable TXBL\n"); + } + + spin_unlock(&ddata->lock); + + return IRQ_HANDLED; +} + +static const struct efm32_spi_pdata efm32_spi_pdata_default = { + .location = 1, +}; + +static u32 efm32_spi_get_configured_location(struct efm32_spi_ddata *ddata) +{ + u32 reg = efm32_spi_read32(ddata, REG_ROUTE); + + return (reg & REG_ROUTE_LOCATION__MASK) >> __ffs(REG_ROUTE_LOCATION__MASK); +} + +static int efm32_spi_probe_dt(struct platform_device *pdev, + struct spi_master *master, struct efm32_spi_ddata *ddata) +{ + struct device_node *np = pdev->dev.of_node; + u32 location; + int ret; + + if (!np) + return 1; + + ret = of_property_read_u32(np, "location", &location); + if (!ret) { + dev_dbg(&pdev->dev, "using location %u\n", location); + } else { + /* default to location configured in hardware */ + location = efm32_spi_get_configured_location(ddata); + + dev_info(&pdev->dev, "fall back to location %u\n", location); + } + + ddata->pdata.location = location; + + /* spi core takes care about the bus number using an alias */ + master->bus_num = -1; + + return 0; +} + +static int efm32_spi_probe(struct platform_device *pdev) +{ + struct efm32_spi_ddata *ddata; + struct resource *res; + int ret; + struct spi_master *master; + struct device_node *np = pdev->dev.of_node; + unsigned int num_cs, i; + + num_cs = of_gpio_named_count(np, "cs-gpios"); + + master = spi_alloc_master(&pdev->dev, + sizeof(*ddata) + num_cs * sizeof(unsigned)); + if (!master) { + dev_dbg(&pdev->dev, + "failed to allocate spi master controller\n"); + return -ENOMEM; + } + platform_set_drvdata(pdev, master); + + master->dev.of_node = pdev->dev.of_node; + + master->num_chipselect = num_cs; + master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH; + master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16); + + ddata = spi_master_get_devdata(master); + + ddata->bitbang.master = spi_master_get(master); + ddata->bitbang.chipselect = efm32_spi_chipselect; + ddata->bitbang.setup_transfer = efm32_spi_setup_transfer; + ddata->bitbang.txrx_bufs = efm32_spi_txrx_bufs; + + spin_lock_init(&ddata->lock); + + ddata->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(ddata->clk)) { + ret = PTR_ERR(ddata->clk); + dev_err(&pdev->dev, "failed to get clock: %d\n", ret); + goto err; + } + + for (i = 0; i < num_cs; ++i) { + ret = of_get_named_gpio(np, "cs-gpios", i); + if (ret < 0) { + dev_err(&pdev->dev, "failed to get csgpio#%u (%d)\n", + i, ret); + goto err; + } + ddata->csgpio[i] = ret; + dev_dbg(&pdev->dev, "csgpio#%u = %u\n", i, ddata->csgpio[i]); + ret = devm_gpio_request_one(&pdev->dev, ddata->csgpio[i], + GPIOF_OUT_INIT_LOW, DRIVER_NAME); + if (ret < 0) { + dev_err(&pdev->dev, + "failed to configure csgpio#%u (%d)\n", + i, ret); + goto err; + } + } + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + ret = -ENODEV; + dev_err(&pdev->dev, "failed to determine base address\n"); + goto err; + } + + if (resource_size(res) < 60) { + ret = -EINVAL; + dev_err(&pdev->dev, "memory resource too small\n"); + goto err; + } + + ddata->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ddata->base)) { + ret = PTR_ERR(ddata->base); + dev_err(&pdev->dev, "failed to remap memory\n"); + goto err; + } + + ret = platform_get_irq(pdev, 0); + if (ret <= 0) { + dev_err(&pdev->dev, "failed to get rx irq (%d)\n", ret); + goto err; + } + + ddata->rxirq = ret; + + ret = platform_get_irq(pdev, 1); + if (ret <= 0) + ret = ddata->rxirq + 1; + + ddata->txirq = ret; + + ret = clk_prepare_enable(ddata->clk); + if (ret < 0) { + dev_err(&pdev->dev, "failed to enable clock (%d)\n", ret); + goto err; + } + + ret = efm32_spi_probe_dt(pdev, master, ddata); + if (ret > 0) { + /* not created by device tree */ + const struct efm32_spi_pdata *pdata = + dev_get_platdata(&pdev->dev); + + if (pdata) + ddata->pdata = *pdata; + else + ddata->pdata.location = + efm32_spi_get_configured_location(ddata); + + master->bus_num = pdev->id; + + } else if (ret < 0) { + goto err_disable_clk; + } + + efm32_spi_write32(ddata, 0, REG_IEN); + efm32_spi_write32(ddata, REG_ROUTE_TXPEN | REG_ROUTE_RXPEN | + REG_ROUTE_CLKPEN | + REG_ROUTE_LOCATION(ddata->pdata.location), REG_ROUTE); + + ret = request_irq(ddata->rxirq, efm32_spi_rxirq, + 0, DRIVER_NAME " rx", ddata); + if (ret) { + dev_err(&pdev->dev, "failed to register rxirq (%d)\n", ret); + goto err_disable_clk; + } + + ret = request_irq(ddata->txirq, efm32_spi_txirq, + 0, DRIVER_NAME " tx", ddata); + if (ret) { + dev_err(&pdev->dev, "failed to register txirq (%d)\n", ret); + goto err_free_rx_irq; + } + + ret = spi_bitbang_start(&ddata->bitbang); + if (ret) { + dev_err(&pdev->dev, "spi_bitbang_start failed (%d)\n", ret); + + free_irq(ddata->txirq, ddata); +err_free_rx_irq: + free_irq(ddata->rxirq, ddata); +err_disable_clk: + clk_disable_unprepare(ddata->clk); +err: + spi_master_put(master); + kfree(master); + } + + return ret; +} + +static int efm32_spi_remove(struct platform_device *pdev) +{ + struct spi_master *master = platform_get_drvdata(pdev); + struct efm32_spi_ddata *ddata = spi_master_get_devdata(master); + + efm32_spi_write32(ddata, 0, REG_IEN); + + free_irq(ddata->txirq, ddata); + free_irq(ddata->rxirq, ddata); + clk_disable_unprepare(ddata->clk); + spi_master_put(master); + kfree(master); + + return 0; +} + +static const struct of_device_id efm32_spi_dt_ids[] = { + { + .compatible = "efm32,spi", + }, { + /* sentinel */ + } +}; +MODULE_DEVICE_TABLE(of, efm32_uart_dt_ids); + +static struct platform_driver efm32_spi_driver = { + .probe = efm32_spi_probe, + .remove = efm32_spi_remove, + + .driver = { + .name = DRIVER_NAME, + .owner = THIS_MODULE, + .of_match_table = efm32_spi_dt_ids, + }, +}; +module_platform_driver(efm32_spi_driver); + +MODULE_AUTHOR("Uwe Kleine-Koenig "); +MODULE_DESCRIPTION("EFM32 SPI driver"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/include/linux/platform_data/efm32-spi.h b/include/linux/platform_data/efm32-spi.h new file mode 100644 index 000000000000..31b19ca1d73a --- /dev/null +++ b/include/linux/platform_data/efm32-spi.h @@ -0,0 +1,14 @@ +#ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ +#define __LINUX_PLATFORM_DATA_EFM32_SPI_H__ + +#include + +/** + * struct efm32_spi_pdata + * @location: pinmux location for the I/O pins (to be written to the ROUTE + * register) + */ +struct efm32_spi_pdata { + u8 location; +}; +#endif /* ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ */ -- cgit v1.2.3-71-gd317 From 64e8674fbe6bc848333a9b7e19f8cc019dde9eab Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:24 -0600 Subject: PCI: Add pci_reset_bridge_secondary_bus() Move the secondary bus reset code from pci_parent_bus_reset() into its own function. Export it as we'll later be calling it from hotplug controllers and elsewhere. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 32 +++++++++++++++++++++++--------- include/linux/pci.h | 1 + 2 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e37fea6e178d..d46860898e1f 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3215,9 +3215,30 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) return 0; } -static int pci_parent_bus_reset(struct pci_dev *dev, int probe) +/** + * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge. + * @dev: Bridge device + * + * Use the bridge control register to assert reset on the secondary bus. + * Devices on the secondary bus are left in power-on state. + */ +void pci_reset_bridge_secondary_bus(struct pci_dev *dev) { u16 ctrl; + + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + msleep(100); + + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + msleep(100); +} +EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus); + +static int pci_parent_bus_reset(struct pci_dev *dev, int probe) +{ struct pci_dev *pdev; if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) @@ -3230,14 +3251,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) if (probe) return 0; - pci_read_config_word(dev->bus->self, PCI_BRIDGE_CONTROL, &ctrl); - ctrl |= PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(dev->bus->self, PCI_BRIDGE_CONTROL, ctrl); - msleep(100); - - ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(dev->bus->self, PCI_BRIDGE_CONTROL, ctrl); - msleep(100); + pci_reset_bridge_secondary_bus(dev->bus->self); return 0; } diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..35c1bc4909f3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,6 +924,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); -- cgit v1.2.3-71-gd317 From c88a1f8b96e7384627b918dfabbfc0c615a4a914 Mon Sep 17 00:00:00 2001 From: Lukasz Majewski Date: Tue, 6 Aug 2013 22:53:08 +0530 Subject: cpufreq: Store cpufreq policies in a list Policies available in the cpufreq framework are now linked together. They are accessible via cpufreq_policy_list defined in the cpufreq core. [rjw: Fix from Yinghai Lu folded in] Signed-off-by: Lukasz Majewski Signed-off-by: Myungjoo Ham Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 12 ++++++++++++ include/linux/cpufreq.h | 1 + 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 9e83d9142072..75c5bd424d59 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -40,6 +40,7 @@ static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback); static DEFINE_RWLOCK(cpufreq_driver_lock); static DEFINE_MUTEX(cpufreq_governor_lock); +static LIST_HEAD(cpufreq_policy_list); #ifdef CONFIG_HOTPLUG_CPU /* This one keeps track of the previously set governor of a removed CPU */ @@ -952,6 +953,7 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void) if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) goto err_free_cpumask; + INIT_LIST_HEAD(&policy->policy_list); return policy; err_free_cpumask: @@ -964,6 +966,12 @@ err_free_policy: static void cpufreq_policy_free(struct cpufreq_policy *policy) { + unsigned long flags; + + write_lock_irqsave(&cpufreq_driver_lock, flags); + list_del(&policy->policy_list); + write_unlock_irqrestore(&cpufreq_driver_lock, flags); + free_cpumask_var(policy->related_cpus); free_cpumask_var(policy->cpus); kfree(policy); @@ -1077,6 +1085,10 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, ret = cpufreq_add_dev_interface(policy, dev); if (ret) goto err_out_unregister; + + write_lock_irqsave(&cpufreq_driver_lock, flags); + list_add(&policy->policy_list, &cpufreq_policy_list); + write_unlock_irqrestore(&cpufreq_driver_lock, flags); } cpufreq_init_policy(policy); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 29208923c9d3..431a05d4b4c9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -82,6 +82,7 @@ struct cpufreq_policy { struct cpufreq_real_policy user_policy; + struct list_head policy_list; struct kobject kobj; struct completion kobj_unregister; int transition_ongoing; /* Tracks transition status */ -- cgit v1.2.3-71-gd317 From adc97d6a735dbb1e94cb4f1bf0b55f258b349941 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Aug 2013 22:53:12 +0530 Subject: cpufreq: Drop the owner field from struct cpufreq_driver We don't need to set .owner = THIS_MODULE any more in cpufreq drivers as this field isn't used any more by the cpufreq core. This patch removes it and updates all dependent drivers accordingly. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- Documentation/cpu-freq/cpu-drivers.txt | 2 -- drivers/cpufreq/acpi-cpufreq.c | 1 - drivers/cpufreq/at32ap-cpufreq.c | 1 - drivers/cpufreq/blackfin-cpufreq.c | 1 - drivers/cpufreq/cpufreq-nforce2.c | 1 - drivers/cpufreq/cris-artpec3-cpufreq.c | 1 - drivers/cpufreq/cris-etraxfs-cpufreq.c | 1 - drivers/cpufreq/e_powersaver.c | 1 - drivers/cpufreq/elanfreq.c | 1 - drivers/cpufreq/gx-suspmod.c | 1 - drivers/cpufreq/ia64-acpi-cpufreq.c | 1 - drivers/cpufreq/intel_pstate.c | 1 - drivers/cpufreq/kirkwood-cpufreq.c | 1 - drivers/cpufreq/longhaul.c | 1 - drivers/cpufreq/longrun.c | 1 - drivers/cpufreq/loongson2_cpufreq.c | 1 - drivers/cpufreq/maple-cpufreq.c | 1 - drivers/cpufreq/p4-clockmod.c | 1 - drivers/cpufreq/pasemi-cpufreq.c | 1 - drivers/cpufreq/pcc-cpufreq.c | 1 - drivers/cpufreq/pmac32-cpufreq.c | 1 - drivers/cpufreq/pmac64-cpufreq.c | 1 - drivers/cpufreq/powernow-k6.c | 1 - drivers/cpufreq/powernow-k7.c | 1 - drivers/cpufreq/powernow-k8.c | 1 - drivers/cpufreq/ppc-corenet-cpufreq.c | 1 - drivers/cpufreq/ppc_cbe_cpufreq.c | 1 - drivers/cpufreq/s3c2416-cpufreq.c | 1 - drivers/cpufreq/s3c64xx-cpufreq.c | 1 - drivers/cpufreq/sc520_freq.c | 1 - drivers/cpufreq/sh-cpufreq.c | 1 - drivers/cpufreq/sparc-us2e-cpufreq.c | 1 - drivers/cpufreq/sparc-us3-cpufreq.c | 1 - drivers/cpufreq/speedstep-centrino.c | 1 - drivers/cpufreq/speedstep-ich.c | 1 - drivers/cpufreq/speedstep-smi.c | 1 - include/linux/cpufreq.h | 1 - 37 files changed, 38 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt index 19fa98e07bf7..40282e617913 100644 --- a/Documentation/cpu-freq/cpu-drivers.txt +++ b/Documentation/cpu-freq/cpu-drivers.txt @@ -50,8 +50,6 @@ What shall this struct cpufreq_driver contain? cpufreq_driver.name - The name of this driver. -cpufreq_driver.owner - THIS_MODULE; - cpufreq_driver.init - A pointer to the per-CPU initialization function. diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 44758ce9936d..9b5d1b1a9c03 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -936,7 +936,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .exit = acpi_cpufreq_cpu_exit, .resume = acpi_cpufreq_resume, .name = "acpi-cpufreq", - .owner = THIS_MODULE, .attr = acpi_cpufreq_attr, }; diff --git a/drivers/cpufreq/at32ap-cpufreq.c b/drivers/cpufreq/at32ap-cpufreq.c index 654488723cb5..e0c38d938997 100644 --- a/drivers/cpufreq/at32ap-cpufreq.c +++ b/drivers/cpufreq/at32ap-cpufreq.c @@ -108,7 +108,6 @@ static int __init at32_cpufreq_driver_init(struct cpufreq_policy *policy) static struct cpufreq_driver at32_driver = { .name = "at32ap", - .owner = THIS_MODULE, .init = at32_cpufreq_driver_init, .verify = at32_verify_speed, .target = at32_set_target, diff --git a/drivers/cpufreq/blackfin-cpufreq.c b/drivers/cpufreq/blackfin-cpufreq.c index 9cdbbd278a80..ef05978a7237 100644 --- a/drivers/cpufreq/blackfin-cpufreq.c +++ b/drivers/cpufreq/blackfin-cpufreq.c @@ -225,7 +225,6 @@ static struct cpufreq_driver bfin_driver = { .get = bfin_getfreq_khz, .init = __bfin_cpu_init, .name = "bfin cpufreq", - .owner = THIS_MODULE, .attr = bfin_freq_attr, }; diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c index af1542d41440..b83d45f68574 100644 --- a/drivers/cpufreq/cpufreq-nforce2.c +++ b/drivers/cpufreq/cpufreq-nforce2.c @@ -379,7 +379,6 @@ static struct cpufreq_driver nforce2_driver = { .get = nforce2_get, .init = nforce2_cpu_init, .exit = nforce2_cpu_exit, - .owner = THIS_MODULE, }; #ifdef MODULE diff --git a/drivers/cpufreq/cris-artpec3-cpufreq.c b/drivers/cpufreq/cris-artpec3-cpufreq.c index ee142c490575..cb8276dd19ca 100644 --- a/drivers/cpufreq/cris-artpec3-cpufreq.c +++ b/drivers/cpufreq/cris-artpec3-cpufreq.c @@ -111,7 +111,6 @@ static struct cpufreq_driver cris_freq_driver = { .init = cris_freq_cpu_init, .exit = cris_freq_cpu_exit, .name = "cris_freq", - .owner = THIS_MODULE, .attr = cris_freq_attr, }; diff --git a/drivers/cpufreq/cris-etraxfs-cpufreq.c b/drivers/cpufreq/cris-etraxfs-cpufreq.c index 12952235d5db..72328f77dc53 100644 --- a/drivers/cpufreq/cris-etraxfs-cpufreq.c +++ b/drivers/cpufreq/cris-etraxfs-cpufreq.c @@ -108,7 +108,6 @@ static struct cpufreq_driver cris_freq_driver = { .init = cris_freq_cpu_init, .exit = cris_freq_cpu_exit, .name = "cris_freq", - .owner = THIS_MODULE, .attr = cris_freq_attr, }; diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c index de974be6b773..09f64cc83019 100644 --- a/drivers/cpufreq/e_powersaver.c +++ b/drivers/cpufreq/e_powersaver.c @@ -436,7 +436,6 @@ static struct cpufreq_driver eps_driver = { .exit = eps_cpu_exit, .get = eps_get, .name = "e_powersaver", - .owner = THIS_MODULE, .attr = eps_attr, }; diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c index 658d860344b0..823a400d98fd 100644 --- a/drivers/cpufreq/elanfreq.c +++ b/drivers/cpufreq/elanfreq.c @@ -274,7 +274,6 @@ static struct cpufreq_driver elanfreq_driver = { .init = elanfreq_cpu_init, .exit = elanfreq_cpu_exit, .name = "elanfreq", - .owner = THIS_MODULE, .attr = elanfreq_attr, }; diff --git a/drivers/cpufreq/gx-suspmod.c b/drivers/cpufreq/gx-suspmod.c index 4f25fb63c097..ef5fee7dc0b3 100644 --- a/drivers/cpufreq/gx-suspmod.c +++ b/drivers/cpufreq/gx-suspmod.c @@ -446,7 +446,6 @@ static struct cpufreq_driver gx_suspmod_driver = { .target = cpufreq_gx_target, .init = cpufreq_gx_cpu_init, .name = "gx-suspmod", - .owner = THIS_MODULE, }; static int __init cpufreq_gx_init(void) diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c index 08792dd4d62a..3e14f0317175 100644 --- a/drivers/cpufreq/ia64-acpi-cpufreq.c +++ b/drivers/cpufreq/ia64-acpi-cpufreq.c @@ -409,7 +409,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .init = acpi_cpufreq_cpu_init, .exit = acpi_cpufreq_cpu_exit, .name = "acpi-cpufreq", - .owner = THIS_MODULE, .attr = acpi_cpufreq_attr, }; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 7cde885011ed..6efd96c196b2 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -665,7 +665,6 @@ static struct cpufreq_driver intel_pstate_driver = { .init = intel_pstate_cpu_init, .exit = intel_pstate_cpu_exit, .name = "intel_pstate", - .owner = THIS_MODULE, }; static int __initdata no_load; diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c index c233ea617366..45e4d7fc261d 100644 --- a/drivers/cpufreq/kirkwood-cpufreq.c +++ b/drivers/cpufreq/kirkwood-cpufreq.c @@ -158,7 +158,6 @@ static struct cpufreq_driver kirkwood_cpufreq_driver = { .init = kirkwood_cpufreq_cpu_init, .exit = kirkwood_cpufreq_cpu_exit, .name = "kirkwood-cpufreq", - .owner = THIS_MODULE, .attr = kirkwood_cpufreq_attr, }; diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 8c49261df57d..4ada1cccb052 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -948,7 +948,6 @@ static struct cpufreq_driver longhaul_driver = { .init = longhaul_cpu_init, .exit = longhaul_cpu_exit, .name = "longhaul", - .owner = THIS_MODULE, .attr = longhaul_attr, }; diff --git a/drivers/cpufreq/longrun.c b/drivers/cpufreq/longrun.c index 0fe041d1f77f..5aa031612d53 100644 --- a/drivers/cpufreq/longrun.c +++ b/drivers/cpufreq/longrun.c @@ -286,7 +286,6 @@ static struct cpufreq_driver longrun_driver = { .get = longrun_get, .init = longrun_cpu_init, .name = "longrun", - .owner = THIS_MODULE, }; static const struct x86_cpu_id longrun_ids[] = { diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c index bb838b985077..e65de91b534b 100644 --- a/drivers/cpufreq/loongson2_cpufreq.c +++ b/drivers/cpufreq/loongson2_cpufreq.c @@ -157,7 +157,6 @@ static struct freq_attr *loongson2_table_attr[] = { }; static struct cpufreq_driver loongson2_cpufreq_driver = { - .owner = THIS_MODULE, .name = "loongson2", .init = loongson2_cpufreq_cpu_init, .verify = loongson2_cpufreq_verify, diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c index cdd62915efaf..41c601f4631e 100644 --- a/drivers/cpufreq/maple-cpufreq.c +++ b/drivers/cpufreq/maple-cpufreq.c @@ -190,7 +190,6 @@ static int maple_cpufreq_cpu_init(struct cpufreq_policy *policy) static struct cpufreq_driver maple_cpufreq_driver = { .name = "maple", - .owner = THIS_MODULE, .flags = CPUFREQ_CONST_LOOPS, .init = maple_cpufreq_cpu_init, .verify = maple_cpufreq_verify, diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c index 9ee78170ff86..2f0a2a65c37f 100644 --- a/drivers/cpufreq/p4-clockmod.c +++ b/drivers/cpufreq/p4-clockmod.c @@ -279,7 +279,6 @@ static struct cpufreq_driver p4clockmod_driver = { .exit = cpufreq_p4_cpu_exit, .get = cpufreq_p4_get, .name = "p4-clockmod", - .owner = THIS_MODULE, .attr = p4clockmod_attr, }; diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index b704da404067..534e43a60d1f 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -297,7 +297,6 @@ static int pas_cpufreq_target(struct cpufreq_policy *policy, static struct cpufreq_driver pas_cpufreq_driver = { .name = "pas-cpufreq", - .owner = THIS_MODULE, .flags = CPUFREQ_CONST_LOOPS, .init = pas_cpufreq_cpu_init, .exit = pas_cpufreq_cpu_exit, diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 1581fcc4cf4a..d81c4e5ea0ad 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -587,7 +587,6 @@ static struct cpufreq_driver pcc_cpufreq_driver = { .init = pcc_cpufreq_cpu_init, .exit = pcc_cpufreq_cpu_exit, .name = "pcc-cpufreq", - .owner = THIS_MODULE, }; static int __init pcc_cpufreq_init(void) diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index 3104fad82480..38cdc63c38da 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -477,7 +477,6 @@ static struct cpufreq_driver pmac_cpufreq_driver = { .flags = CPUFREQ_PM_NO_WARN, .attr = pmac_cpu_freqs_attr, .name = "powermac", - .owner = THIS_MODULE, }; diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c index 4d7799b7af86..b6850d97f0d5 100644 --- a/drivers/cpufreq/pmac64-cpufreq.c +++ b/drivers/cpufreq/pmac64-cpufreq.c @@ -371,7 +371,6 @@ static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy) static struct cpufreq_driver g5_cpufreq_driver = { .name = "powermac", - .owner = THIS_MODULE, .flags = CPUFREQ_CONST_LOOPS, .init = g5_cpufreq_cpu_init, .verify = g5_cpufreq_verify, diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c index ea8e10382ec5..85f1c8c25ddc 100644 --- a/drivers/cpufreq/powernow-k6.c +++ b/drivers/cpufreq/powernow-k6.c @@ -207,7 +207,6 @@ static struct cpufreq_driver powernow_k6_driver = { .exit = powernow_k6_cpu_exit, .get = powernow_k6_get, .name = "powernow-k6", - .owner = THIS_MODULE, .attr = powernow_k6_attr, }; diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c index 4687d40d0219..14ce480be8ab 100644 --- a/drivers/cpufreq/powernow-k7.c +++ b/drivers/cpufreq/powernow-k7.c @@ -716,7 +716,6 @@ static struct cpufreq_driver powernow_driver = { .init = powernow_cpu_init, .exit = powernow_cpu_exit, .name = "powernow-k7", - .owner = THIS_MODULE, .attr = powernow_table_attr, }; diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index 3f3c6cae91d0..2344a9ed17f3 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -1240,7 +1240,6 @@ static struct cpufreq_driver cpufreq_amd64_driver = { .exit = powernowk8_cpu_exit, .get = powernowk8_get, .name = "powernow-k8", - .owner = THIS_MODULE, .attr = powernow_k8_attr, }; diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c index 3cae4529f959..60e81d524ea8 100644 --- a/drivers/cpufreq/ppc-corenet-cpufreq.c +++ b/drivers/cpufreq/ppc-corenet-cpufreq.c @@ -300,7 +300,6 @@ static struct freq_attr *corenet_cpufreq_attr[] = { static struct cpufreq_driver ppc_corenet_cpufreq_driver = { .name = "ppc_cpufreq", - .owner = THIS_MODULE, .flags = CPUFREQ_CONST_LOOPS, .init = corenet_cpufreq_cpu_init, .exit = __exit_p(corenet_cpufreq_cpu_exit), diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c index 5936f8d6f2cc..2e448f0bbdc5 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq.c @@ -181,7 +181,6 @@ static struct cpufreq_driver cbe_cpufreq_driver = { .init = cbe_cpufreq_cpu_init, .exit = cbe_cpufreq_cpu_exit, .name = "cbe-cpufreq", - .owner = THIS_MODULE, .flags = CPUFREQ_CONST_LOOPS, }; diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c index ce5b9fca9c18..22dcb81ef9d0 100644 --- a/drivers/cpufreq/s3c2416-cpufreq.c +++ b/drivers/cpufreq/s3c2416-cpufreq.c @@ -524,7 +524,6 @@ static struct freq_attr *s3c2416_cpufreq_attr[] = { }; static struct cpufreq_driver s3c2416_cpufreq_driver = { - .owner = THIS_MODULE, .flags = 0, .verify = s3c2416_cpufreq_verify_speed, .target = s3c2416_cpufreq_set_target, diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c index 13bb4bae64ee..8a72b0c555f8 100644 --- a/drivers/cpufreq/s3c64xx-cpufreq.c +++ b/drivers/cpufreq/s3c64xx-cpufreq.c @@ -263,7 +263,6 @@ static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy) } static struct cpufreq_driver s3c64xx_cpufreq_driver = { - .owner = THIS_MODULE, .flags = 0, .verify = s3c64xx_cpufreq_verify_speed, .target = s3c64xx_cpufreq_set_target, diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c index 77a210975fc4..d6f6c6f4efa7 100644 --- a/drivers/cpufreq/sc520_freq.c +++ b/drivers/cpufreq/sc520_freq.c @@ -147,7 +147,6 @@ static struct cpufreq_driver sc520_freq_driver = { .init = sc520_freq_cpu_init, .exit = sc520_freq_cpu_exit, .name = "sc520_freq", - .owner = THIS_MODULE, .attr = sc520_freq_attr, }; diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c index 73adb64651e8..ffc6d24b0cfb 100644 --- a/drivers/cpufreq/sh-cpufreq.c +++ b/drivers/cpufreq/sh-cpufreq.c @@ -160,7 +160,6 @@ static struct freq_attr *sh_freq_attr[] = { }; static struct cpufreq_driver sh_cpufreq_driver = { - .owner = THIS_MODULE, .name = "sh", .get = sh_cpufreq_get, .target = sh_cpufreq_target, diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c index 7c43a725e5da..cf5bc2ca16fa 100644 --- a/drivers/cpufreq/sparc-us2e-cpufreq.c +++ b/drivers/cpufreq/sparc-us2e-cpufreq.c @@ -365,7 +365,6 @@ static int __init us2e_freq_init(void) driver->target = us2e_freq_target; driver->get = us2e_freq_get; driver->exit = us2e_freq_cpu_exit; - driver->owner = THIS_MODULE, strcpy(driver->name, "UltraSPARC-IIe"); cpufreq_us2e_driver = driver; diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c index 7f500c140bc3..ac76b489979d 100644 --- a/drivers/cpufreq/sparc-us3-cpufreq.c +++ b/drivers/cpufreq/sparc-us3-cpufreq.c @@ -226,7 +226,6 @@ static int __init us3_freq_init(void) driver->target = us3_freq_target; driver->get = us3_freq_get; driver->exit = us3_freq_cpu_exit; - driver->owner = THIS_MODULE, strcpy(driver->name, "UltraSPARC-III"); cpufreq_us3_driver = driver; diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c index 0915e712fbdc..f897d5105842 100644 --- a/drivers/cpufreq/speedstep-centrino.c +++ b/drivers/cpufreq/speedstep-centrino.c @@ -575,7 +575,6 @@ static struct cpufreq_driver centrino_driver = { .target = centrino_target, .get = get_cur_freq, .attr = centrino_attr, - .owner = THIS_MODULE, }; /* diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c index e2e5aa971452..5355abb69afc 100644 --- a/drivers/cpufreq/speedstep-ich.c +++ b/drivers/cpufreq/speedstep-ich.c @@ -378,7 +378,6 @@ static struct cpufreq_driver speedstep_driver = { .init = speedstep_cpu_init, .exit = speedstep_cpu_exit, .get = speedstep_get, - .owner = THIS_MODULE, .attr = speedstep_attr, }; diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c index f5a6b70ee6c0..abfba4f731eb 100644 --- a/drivers/cpufreq/speedstep-smi.c +++ b/drivers/cpufreq/speedstep-smi.c @@ -375,7 +375,6 @@ static struct cpufreq_driver speedstep_driver = { .exit = speedstep_cpu_exit, .get = speedstep_get, .resume = speedstep_resume, - .owner = THIS_MODULE, .attr = speedstep_attr, }; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 431a05d4b4c9..d568f3975eeb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -179,7 +179,6 @@ __ATTR(_name, 0644, show_##_name, store_##_name) struct cpufreq_driver { - struct module *owner; char name[CPUFREQ_NAME_LEN]; u8 flags; /* -- cgit v1.2.3-71-gd317 From 77409d9bcc0ee3fc309a3d6fd18553f6ec5a9aa6 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 12 Aug 2013 14:21:14 +0530 Subject: regulator: palmas: model SMPS10 as two regulators SMPS10 has two outputs OUT1 and OUT2 and have one input IN1. SMPS10-OUT2 is connected to SMPS10-IN1 and can be configured either in BOOST mode or BYPASS mode. regulator_enable of SMPS10-OUT2 configures it in BOOST mode. For BYPASS mode regulator_allow_bypass() API can be used. SMPS10-OUT1 is connected to SMPS10-OUT2 and can be enabled using regulator_enable(). [ axel.lin@ingics.com : Simplify regulator_desc setting for SMPS10_[OUT1|OUT2] Signed-off-by: J Keerthy Signed-off-by: Laxman Dewangan Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- drivers/regulator/palmas-regulator.c | 30 ++++++++++++++++++++++++------ include/linux/mfd/palmas.h | 9 +++++---- 2 files changed, 29 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index d0c87856dd25..40ed92ba03f4 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -97,10 +97,15 @@ static const struct regs_info palmas_regs_info[] = { .ctrl_addr = PALMAS_SMPS9_CTRL, }, { - .name = "SMPS10", + .name = "SMPS10_OUT2", .sname = "smps10-in", .ctrl_addr = PALMAS_SMPS10_CTRL, }, + { + .name = "SMPS10_OUT1", + .sname = "smps10-out2", + .ctrl_addr = PALMAS_SMPS10_CTRL, + }, { .name = "LDO1", .sname = "ldo1-in", @@ -487,6 +492,8 @@ static struct regulator_ops palmas_ops_smps10 = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, + .set_bypass = regulator_set_bypass_regmap, + .get_bypass = regulator_get_bypass_regmap, }; static int palmas_is_enabled_ldo(struct regulator_dev *dev) @@ -538,7 +545,8 @@ static int palmas_smps_init(struct palmas *palmas, int id, return ret; switch (id) { - case PALMAS_REG_SMPS10: + case PALMAS_REG_SMPS10_OUT1: + case PALMAS_REG_SMPS10_OUT2: reg &= ~PALMAS_SMPS10_CTRL_MODE_SLEEP_MASK; if (reg_init->mode_sleep) reg |= reg_init->mode_sleep << @@ -681,7 +689,8 @@ static struct of_regulator_match palmas_matches[] = { { .name = "smps7", }, { .name = "smps8", }, { .name = "smps9", }, - { .name = "smps10", }, + { .name = "smps10_out2", }, + { .name = "smps10_out1", }, { .name = "ldo1", }, { .name = "ldo2", }, { .name = "ldo3", }, @@ -838,7 +847,8 @@ static int palmas_regulators_probe(struct platform_device *pdev) continue; ramp_delay_support = true; break; - case PALMAS_REG_SMPS10: + case PALMAS_REG_SMPS10_OUT1: + case PALMAS_REG_SMPS10_OUT2: if (!PALMAS_PMIC_HAS(palmas, SMPS10_BOOST)) continue; } @@ -872,7 +882,8 @@ static int palmas_regulators_probe(struct platform_device *pdev) pmic->desc[id].id = id; switch (id) { - case PALMAS_REG_SMPS10: + case PALMAS_REG_SMPS10_OUT1: + case PALMAS_REG_SMPS10_OUT2: pmic->desc[id].n_voltages = PALMAS_SMPS10_NUM_VOLTAGES; pmic->desc[id].ops = &palmas_ops_smps10; pmic->desc[id].vsel_reg = @@ -882,7 +893,14 @@ static int palmas_regulators_probe(struct platform_device *pdev) pmic->desc[id].enable_reg = PALMAS_BASE_TO_REG(PALMAS_SMPS_BASE, PALMAS_SMPS10_CTRL); - pmic->desc[id].enable_mask = SMPS10_BOOST_EN; + if (id == PALMAS_REG_SMPS10_OUT1) + pmic->desc[id].enable_mask = SMPS10_SWITCH_EN; + else + pmic->desc[id].enable_mask = SMPS10_BOOST_EN; + pmic->desc[id].bypass_reg = + PALMAS_BASE_TO_REG(PALMAS_SMPS_BASE, + PALMAS_SMPS10_CTRL); + pmic->desc[id].bypass_mask = SMPS10_BYPASS_EN; pmic->desc[id].min_uV = 3750000; pmic->desc[id].uV_step = 1250000; break; diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 1a8dd7afe084..c06d78af3342 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -160,7 +160,8 @@ enum palmas_regulators { PALMAS_REG_SMPS7, PALMAS_REG_SMPS8, PALMAS_REG_SMPS9, - PALMAS_REG_SMPS10, + PALMAS_REG_SMPS10_OUT2, + PALMAS_REG_SMPS10_OUT1, /* LDO regulators */ PALMAS_REG_LDO1, PALMAS_REG_LDO2, @@ -355,9 +356,9 @@ struct palmas_pmic { int smps123; int smps457; - int range[PALMAS_REG_SMPS10]; - unsigned int ramp_delay[PALMAS_REG_SMPS10]; - unsigned int current_reg_mode[PALMAS_REG_SMPS10]; + int range[PALMAS_REG_SMPS10_OUT1]; + unsigned int ramp_delay[PALMAS_REG_SMPS10_OUT1]; + unsigned int current_reg_mode[PALMAS_REG_SMPS10_OUT1]; }; struct palmas_resource { -- cgit v1.2.3-71-gd317 From 5c19e95216b93b0d29c6a4887e69a980edc6fc81 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Mon, 5 Aug 2013 14:40:44 +0200 Subject: OF: Add helper for matching against linux,stdout-path devicetrees may have a linux,stdout-path property in the chosen node describing the console device. This adds a helper function to match a device against this property so a driver can call add_preferred_console for a matching device. Signed-off-by: Sascha Hauer Acked-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/base.c | 26 ++++++++++++++++++++++++++ include/linux/of.h | 7 +++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index 5c5427918eb2..1c3c79c79742 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -32,6 +32,7 @@ struct device_node *of_allnodes; EXPORT_SYMBOL(of_allnodes); struct device_node *of_chosen; struct device_node *of_aliases; +static struct device_node *of_stdout; DEFINE_MUTEX(of_aliases_mutex); @@ -1595,6 +1596,15 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)) of_chosen = of_find_node_by_path("/chosen"); if (of_chosen == NULL) of_chosen = of_find_node_by_path("/chosen@0"); + + if (of_chosen) { + const char *name; + + name = of_get_property(of_chosen, "linux,stdout-path", NULL); + if (name) + of_stdout = of_find_node_by_path(name); + } + of_aliases = of_find_node_by_path("/aliases"); if (!of_aliases) return; @@ -1703,3 +1713,19 @@ const char *of_prop_next_string(struct property *prop, const char *cur) return curv; } EXPORT_SYMBOL_GPL(of_prop_next_string); + +/** + * of_device_is_stdout_path - check if a device node matches the + * linux,stdout-path property + * + * Check if this device node matches the linux,stdout-path property + * in the chosen node. return true if yes, false otherwise. + */ +int of_device_is_stdout_path(struct device_node *dn) +{ + if (!of_stdout) + return false; + + return of_stdout == dn; +} +EXPORT_SYMBOL_GPL(of_device_is_stdout_path); diff --git a/include/linux/of.h b/include/linux/of.h index 1fd08ca23106..429e16801858 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -343,6 +343,8 @@ const char *of_prop_next_string(struct property *prop, const char *cur); s; \ s = of_prop_next_string(prop, s)) +int of_device_is_stdout_path(struct device_node *dn); + #else /* CONFIG_OF */ static inline const char* of_node_full_name(struct device_node *np) @@ -505,6 +507,11 @@ static inline int of_machine_is_compatible(const char *compat) return 0; } +static inline int of_device_is_stdout_path(struct device_node *dn) +{ + return 0; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #define of_property_for_each_u32(np, propname, prop, p, u) \ -- cgit v1.2.3-71-gd317 From 3e635202ce40e4d7ff3fafc18db70c5d28cc6622 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Mon, 12 Aug 2013 16:06:51 +0300 Subject: usb: phy: tegra: Tegra30 support The Tegra30 USB PHY is a bit different than the Tegra20 PHY: - The EHCI controller supports the HOSTPC register extension, and some of the fields that the PHY needs to modify (PHCD and PTS) have moved to the new HOSTPC register. - Some of the UTMI PLL configuration registers have moved from the USB register space to the Clock-And-Reset controller space. In Tegra30 the clock driver is responsible for configuring the UTMI PLL. - The USBMODE register must be explicitly written to enter host mode. - Certain PHY parameters need to be programmed for optimal signal quality. Support for this will be added in the next patch. The new tegra_phy_soc_config structure is added to describe the differences between the SoCs. Signed-off-by: Tuomas Tynkkynen Tested-by: Stephen Warren Reviewed-by: Stephen Warren Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-tegra-usb.c | 121 +++++++++++++++++++++++++++++--------- include/linux/usb/tegra_usb_phy.h | 19 ++++++ 2 files changed, 112 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index ebbf85fdfc7f..1ad184af7601 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -39,11 +40,16 @@ #define ULPI_VIEWPORT 0x170 -/* PORTSC registers */ +/* PORTSC PTS/PHCD bits, Tegra20 only */ #define TEGRA_USB_PORTSC1 0x184 #define TEGRA_USB_PORTSC1_PTS(x) (((x) & 0x3) << 30) #define TEGRA_USB_PORTSC1_PHCD (1 << 23) +/* HOSTPC1 PTS/PHCD bits, Tegra30 and above */ +#define TEGRA_USB_HOSTPC1_DEVLC 0x1b4 +#define TEGRA_USB_HOSTPC1_DEVLC_PTS(x) (((x) & 0x7) << 29) +#define TEGRA_USB_HOSTPC1_DEVLC_PHCD (1 << 22) + /* Bits of PORTSC1, which will get cleared by writing 1 into them */ #define TEGRA_PORTSC1_RWC_BITS (PORT_CSC | PORT_PEC | PORT_OCC) @@ -141,6 +147,12 @@ #define UTMIP_BIAS_CFG1 0x83c #define UTMIP_BIAS_PDTRK_COUNT(x) (((x) & 0x1f) << 3) +/* For Tegra30 and above only, the address is different in Tegra20 */ +#define USB_USBMODE 0x1f8 +#define USB_USBMODE_MASK (3 << 0) +#define USB_USBMODE_HOST (3 << 0) +#define USB_USBMODE_DEVICE (2 << 0) + static DEFINE_SPINLOCK(utmip_pad_lock); static int utmip_pad_count; @@ -193,10 +205,17 @@ static void set_pts(struct tegra_usb_phy *phy, u8 pts_val) void __iomem *base = phy->regs; unsigned long val; - val = readl(base + TEGRA_USB_PORTSC1) & ~TEGRA_PORTSC1_RWC_BITS; - val &= ~TEGRA_USB_PORTSC1_PTS(3); - val |= TEGRA_USB_PORTSC1_PTS(pts_val & 3); - writel(val, base + TEGRA_USB_PORTSC1); + if (phy->soc_config->has_hostpc) { + val = readl(base + TEGRA_USB_HOSTPC1_DEVLC); + val &= ~TEGRA_USB_HOSTPC1_DEVLC_PTS(~0); + val |= TEGRA_USB_HOSTPC1_DEVLC_PTS(pts_val); + writel(val, base + TEGRA_USB_HOSTPC1_DEVLC); + } else { + val = readl(base + TEGRA_USB_PORTSC1) & ~TEGRA_PORTSC1_RWC_BITS; + val &= ~TEGRA_USB_PORTSC1_PTS(~0); + val |= TEGRA_USB_PORTSC1_PTS(pts_val); + writel(val, base + TEGRA_USB_PORTSC1); + } } static void set_phcd(struct tegra_usb_phy *phy, bool enable) @@ -204,12 +223,21 @@ static void set_phcd(struct tegra_usb_phy *phy, bool enable) void __iomem *base = phy->regs; unsigned long val; - val = readl(base + TEGRA_USB_PORTSC1) & ~TEGRA_PORTSC1_RWC_BITS; - if (enable) - val |= TEGRA_USB_PORTSC1_PHCD; - else - val &= ~TEGRA_USB_PORTSC1_PHCD; - writel(val, base + TEGRA_USB_PORTSC1); + if (phy->soc_config->has_hostpc) { + val = readl(base + TEGRA_USB_HOSTPC1_DEVLC); + if (enable) + val |= TEGRA_USB_HOSTPC1_DEVLC_PHCD; + else + val &= ~TEGRA_USB_HOSTPC1_DEVLC_PHCD; + writel(val, base + TEGRA_USB_HOSTPC1_DEVLC); + } else { + val = readl(base + TEGRA_USB_PORTSC1) & ~PORT_RWC_BITS; + if (enable) + val |= TEGRA_USB_PORTSC1_PHCD; + else + val &= ~TEGRA_USB_PORTSC1_PHCD; + writel(val, base + TEGRA_USB_PORTSC1); + } } static int utmip_pad_open(struct tegra_usb_phy *phy) @@ -367,17 +395,21 @@ static int utmi_phy_power_on(struct tegra_usb_phy *phy) val &= ~UTMIP_SUSPEND_EXIT_ON_EDGE; writel(val, base + UTMIP_MISC_CFG0); - val = readl(base + UTMIP_MISC_CFG1); - val &= ~(UTMIP_PLL_ACTIVE_DLY_COUNT(~0) | UTMIP_PLLU_STABLE_COUNT(~0)); - val |= UTMIP_PLL_ACTIVE_DLY_COUNT(phy->freq->active_delay) | - UTMIP_PLLU_STABLE_COUNT(phy->freq->stable_count); - writel(val, base + UTMIP_MISC_CFG1); - - val = readl(base + UTMIP_PLL_CFG1); - val &= ~(UTMIP_XTAL_FREQ_COUNT(~0) | UTMIP_PLLU_ENABLE_DLY_COUNT(~0)); - val |= UTMIP_XTAL_FREQ_COUNT(phy->freq->xtal_freq_count) | - UTMIP_PLLU_ENABLE_DLY_COUNT(phy->freq->enable_delay); - writel(val, base + UTMIP_PLL_CFG1); + if (!phy->soc_config->utmi_pll_config_in_car_module) { + val = readl(base + UTMIP_MISC_CFG1); + val &= ~(UTMIP_PLL_ACTIVE_DLY_COUNT(~0) | + UTMIP_PLLU_STABLE_COUNT(~0)); + val |= UTMIP_PLL_ACTIVE_DLY_COUNT(phy->freq->active_delay) | + UTMIP_PLLU_STABLE_COUNT(phy->freq->stable_count); + writel(val, base + UTMIP_MISC_CFG1); + + val = readl(base + UTMIP_PLL_CFG1); + val &= ~(UTMIP_XTAL_FREQ_COUNT(~0) | + UTMIP_PLLU_ENABLE_DLY_COUNT(~0)); + val |= UTMIP_XTAL_FREQ_COUNT(phy->freq->xtal_freq_count) | + UTMIP_PLLU_ENABLE_DLY_COUNT(phy->freq->enable_delay); + writel(val, base + UTMIP_PLL_CFG1); + } if (phy->mode == USB_DR_MODE_PERIPHERAL) { val = readl(base + USB_SUSP_CTRL); @@ -448,6 +480,16 @@ static int utmi_phy_power_on(struct tegra_usb_phy *phy) utmi_phy_clk_enable(phy); + if (phy->soc_config->requires_usbmode_setup) { + val = readl(base + USB_USBMODE); + val &= ~USB_USBMODE_MASK; + if (phy->mode == USB_DR_MODE_HOST) + val |= USB_USBMODE_HOST; + else + val |= USB_USBMODE_DEVICE; + writel(val, base + USB_USBMODE); + } + if (!phy->is_legacy_phy) set_pts(phy, 0); @@ -864,8 +906,30 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, return 0; } +static const struct tegra_phy_soc_config tegra20_soc_config = { + .utmi_pll_config_in_car_module = false, + .has_hostpc = false, + .requires_usbmode_setup = false, + .requires_extra_tuning_parameters = false, +}; + +static const struct tegra_phy_soc_config tegra30_soc_config = { + .utmi_pll_config_in_car_module = true, + .has_hostpc = true, + .requires_usbmode_setup = true, + .requires_extra_tuning_parameters = true, +}; + +static struct of_device_id tegra_usb_phy_id_table[] = { + { .compatible = "nvidia,tegra30-usb-phy", .data = &tegra30_soc_config }, + { .compatible = "nvidia,tegra20-usb-phy", .data = &tegra20_soc_config }, + { }, +}; +MODULE_DEVICE_TABLE(of, tegra_usb_phy_id_table); + static int tegra_usb_phy_probe(struct platform_device *pdev) { + const struct of_device_id *match; struct resource *res; struct tegra_usb_phy *tegra_phy = NULL; struct device_node *np = pdev->dev.of_node; @@ -878,6 +942,13 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) return -ENOMEM; } + match = of_match_device(tegra_usb_phy_id_table, &pdev->dev); + if (!match) { + dev_err(&pdev->dev, "Error: No device match found\n"); + return -ENODEV; + } + tegra_phy->soc_config = match->data; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(&pdev->dev, "Failed to get I/O memory\n"); @@ -968,12 +1039,6 @@ static int tegra_usb_phy_remove(struct platform_device *pdev) return 0; } -static struct of_device_id tegra_usb_phy_id_table[] = { - { .compatible = "nvidia,tegra20-usb-phy", }, - { }, -}; -MODULE_DEVICE_TABLE(of, tegra_usb_phy_id_table); - static struct platform_driver tegra_usb_phy_driver = { .probe = tegra_usb_phy_probe, .remove = tegra_usb_phy_remove, diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d3db274610a1..d3a63c354db9 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -18,6 +18,24 @@ #include #include +/* + * utmi_pll_config_in_car_module: true if the UTMI PLL configuration registers + * should be set up by clk-tegra, false if by the PHY code + * has_hostpc: true if the USB controller has the HOSTPC extension, which + * changes the location of the PHCD and PTS fields + * requires_usbmode_setup: true if the USBMODE register needs to be set to + * enter host mode + * requires_extra_tuning_parameters: true if xcvr_hsslew, hssquelch_level + * and hsdiscon_level should be set for adequate signal quality + */ + +struct tegra_phy_soc_config { + bool utmi_pll_config_in_car_module; + bool has_hostpc; + bool requires_usbmode_setup; + bool requires_extra_tuning_parameters; +}; + struct tegra_utmip_config { u8 hssync_start_delay; u8 elastic_limit; @@ -47,6 +65,7 @@ struct tegra_usb_phy { struct regulator *vbus; enum usb_dr_mode mode; void *config; + const struct tegra_phy_soc_config *soc_config; struct usb_phy *ulpi; struct usb_phy u_phy; bool is_legacy_phy; -- cgit v1.2.3-71-gd317 From e497a24d8e18af510879b2ae059ee20a4a58eae8 Mon Sep 17 00:00:00 2001 From: Tuomas Tynkkynen Date: Mon, 12 Aug 2013 16:06:53 +0300 Subject: usb: phy: tegra: Program new PHY parameters The Tegra30 TRM recommends configuration of certain PHY parameters for optimal quality. Program the following registers based on device tree parameters: - UTMIP_XCVR_HSSLEW: HS slew rate control. - UTMIP_HSSQUELCH_LEVEL: HS squelch detector level - UTMIP_HSDISCON_LEVEL: HS disconnect detector level. These registers exist in Tegra20, but programming them hasn't been necessary, so these parameters won't be set on Tegra20 to keep the device trees backward compatible. Additionally, the UTMIP_XCVR_SETUP parameter can be set from fuses instead of a software-programmed value, as the optimal value can vary between invidual boards. The boolean property nvidia,xcvr-setup-use-fuses can be used to enable this behaviour. Signed-off-by: Tuomas Tynkkynen Tested-by: Stephen Warren Reviewed-by: Stephen Warren Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-tegra-usb.c | 81 ++++++++++++++++++++++++++++++--------- include/linux/usb/tegra_usb_phy.h | 4 ++ 2 files changed, 67 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 1ad184af7601..3bfb3d1957c1 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -99,11 +99,15 @@ #define UTMIP_FORCE_PD2_POWERDOWN (1 << 16) #define UTMIP_FORCE_PDZI_POWERDOWN (1 << 18) #define UTMIP_XCVR_LSBIAS_SEL (1 << 21) -#define UTMIP_XCVR_HSSLEW_MSB(x) (((x) & 0x7f) << 25) +#define UTMIP_XCVR_HSSLEW(x) (((x) & 0x3) << 4) +#define UTMIP_XCVR_HSSLEW_MSB(x) ((((x) & 0x1fc) >> 2) << 25) #define UTMIP_BIAS_CFG0 0x80c #define UTMIP_OTGPD (1 << 11) #define UTMIP_BIASPD (1 << 10) +#define UTMIP_HSSQUELCH_LEVEL(x) (((x) & 0x3) << 0) +#define UTMIP_HSDISCON_LEVEL(x) (((x) & 0x3) << 2) +#define UTMIP_HSDISCON_LEVEL_MSB(x) ((((x) & 0x4) >> 2) << 24) #define UTMIP_HSRX_CFG0 0x810 #define UTMIP_ELASTIC_LIMIT(x) (((x) & 0x1f) << 10) @@ -255,6 +259,7 @@ static void utmip_pad_power_on(struct tegra_usb_phy *phy) { unsigned long val, flags; void __iomem *base = phy->pad_regs; + struct tegra_utmip_config *config = phy->config; clk_prepare_enable(phy->pad_clk); @@ -263,6 +268,16 @@ static void utmip_pad_power_on(struct tegra_usb_phy *phy) if (utmip_pad_count++ == 0) { val = readl(base + UTMIP_BIAS_CFG0); val &= ~(UTMIP_OTGPD | UTMIP_BIASPD); + + if (phy->soc_config->requires_extra_tuning_parameters) { + val &= ~(UTMIP_HSSQUELCH_LEVEL(~0) | + UTMIP_HSDISCON_LEVEL(~0) | + UTMIP_HSDISCON_LEVEL_MSB(~0)); + + val |= UTMIP_HSSQUELCH_LEVEL(config->hssquelch_level); + val |= UTMIP_HSDISCON_LEVEL(config->hsdiscon_level); + val |= UTMIP_HSDISCON_LEVEL_MSB(config->hsdiscon_level); + } writel(val, base + UTMIP_BIAS_CFG0); } @@ -431,12 +446,20 @@ static int utmi_phy_power_on(struct tegra_usb_phy *phy) val &= ~(UTMIP_FORCE_PD_POWERDOWN | UTMIP_FORCE_PD2_POWERDOWN | UTMIP_FORCE_PDZI_POWERDOWN | UTMIP_XCVR_LSBIAS_SEL | UTMIP_XCVR_SETUP(~0) | UTMIP_XCVR_SETUP_MSB(~0) | - UTMIP_XCVR_LSFSLEW(~0) | UTMIP_XCVR_LSRSLEW(~0) | - UTMIP_XCVR_HSSLEW_MSB(~0)); - val |= UTMIP_XCVR_SETUP(config->xcvr_setup); - val |= UTMIP_XCVR_SETUP_MSB(config->xcvr_setup); + UTMIP_XCVR_LSFSLEW(~0) | UTMIP_XCVR_LSRSLEW(~0)); + + if (!config->xcvr_setup_use_fuses) { + val |= UTMIP_XCVR_SETUP(config->xcvr_setup); + val |= UTMIP_XCVR_SETUP_MSB(config->xcvr_setup); + } val |= UTMIP_XCVR_LSFSLEW(config->xcvr_lsfslew); val |= UTMIP_XCVR_LSRSLEW(config->xcvr_lsrslew); + + if (phy->soc_config->requires_extra_tuning_parameters) { + val &= ~(UTMIP_XCVR_HSSLEW(~0) | UTMIP_XCVR_HSSLEW_MSB(~0)); + val |= UTMIP_XCVR_HSSLEW(config->xcvr_hsslew); + val |= UTMIP_XCVR_HSSLEW_MSB(config->xcvr_hsslew); + } writel(val, base + UTMIP_XCVR_CFG0); val = readl(base + UTMIP_XCVR_CFG1); @@ -450,14 +473,14 @@ static int utmi_phy_power_on(struct tegra_usb_phy *phy) val |= UTMIP_BIAS_PDTRK_COUNT(0x5); writel(val, base + UTMIP_BIAS_CFG1); - if (phy->is_legacy_phy) { - val = readl(base + UTMIP_SPARE_CFG0); - if (phy->mode == USB_DR_MODE_PERIPHERAL) - val &= ~FUSE_SETUP_SEL; - else - val |= FUSE_SETUP_SEL; - writel(val, base + UTMIP_SPARE_CFG0); - } else { + val = readl(base + UTMIP_SPARE_CFG0); + if (config->xcvr_setup_use_fuses) + val |= FUSE_SETUP_SEL; + else + val &= ~FUSE_SETUP_SEL; + writel(val, base + UTMIP_SPARE_CFG0); + + if (!phy->is_legacy_phy) { val = readl(base + USB_SUSP_CTRL); val |= UTMIP_PHY_ENABLE; writel(val, base + USB_SUSP_CTRL); @@ -888,11 +911,6 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, if (err < 0) return err; - err = read_utmi_param(pdev, "nvidia,xcvr-setup", - &config->xcvr_setup); - if (err < 0) - return err; - err = read_utmi_param(pdev, "nvidia,xcvr-lsfslew", &config->xcvr_lsfslew); if (err < 0) @@ -903,6 +921,33 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, if (err < 0) return err; + if (tegra_phy->soc_config->requires_extra_tuning_parameters) { + err = read_utmi_param(pdev, "nvidia,xcvr-hsslew", + &config->xcvr_hsslew); + if (err < 0) + return err; + + err = read_utmi_param(pdev, "nvidia,hssquelch-level", + &config->hssquelch_level); + if (err < 0) + return err; + + err = read_utmi_param(pdev, "nvidia,hsdiscon-level", + &config->hsdiscon_level); + if (err < 0) + return err; + } + + config->xcvr_setup_use_fuses = of_property_read_bool( + pdev->dev.of_node, "nvidia,xcvr-setup-use-fuses"); + + if (!config->xcvr_setup_use_fuses) { + err = read_utmi_param(pdev, "nvidia,xcvr-setup", + &config->xcvr_setup); + if (err < 0) + return err; + } + return 0; } diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index d3a63c354db9..1de16c324ec8 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -41,9 +41,13 @@ struct tegra_utmip_config { u8 elastic_limit; u8 idle_wait_delay; u8 term_range_adj; + bool xcvr_setup_use_fuses; u8 xcvr_setup; u8 xcvr_lsfslew; u8 xcvr_lsrslew; + u8 xcvr_hsslew; + u8 hssquelch_level; + u8 hsdiscon_level; }; enum tegra_usb_phy_port_speed { -- cgit v1.2.3-71-gd317 From 94dfd7edfd5c9b605caf7b562de7a813d216e011 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 3 Jul 2013 22:53:07 +0800 Subject: USB: HCD: support giveback of URB in tasklet context This patch implements the mechanism of giveback of URB in tasklet context, so that hardware interrupt handling time for usb host controller can be saved much, and HCD interrupt handling can be simplified. Motivations: 1), on some arch(such as ARM), DMA mapping/unmapping is a bit time-consuming, for example: when accessing usb mass storage via EHCI on pandaboard, the common length of transfer buffer is 120KB, the time consumed on DMA unmapping may reach hundreds of microseconds; even on A15 based box, the time is still about scores of microseconds 2), on some arch, reading DMA coherent memoery is very time-consuming, the most common example is usb video class driver[1] 3), driver's complete() callback may do much things which is driver specific, so the time is consumed unnecessarily in hardware irq context. 4), running driver's complete() callback in hardware irq context causes that host controller driver has to release its lock in interrupt handler, so reacquiring the lock after return may busy wait a while and increase interrupt handling time. More seriously, releasing the HCD lock makes HCD becoming quite complicated to deal with introduced races. So the patch proposes to run giveback of URB in tasklet context, then time consumed in HCD irq handling doesn't depend on drivers' complete and DMA mapping/unmapping any more, also we can simplify HCD since the HCD lock isn't needed to be released during irq handling. The patch should be reasonable and doable: 1), for drivers, they don't care if the complete() is called in hard irq context or softirq context 2), the biggest change is the situation in which usb_submit_urb() is called in complete() callback, so the introduced tasklet schedule delay might be a con, but it shouldn't be a big deal: - control/bulk asynchronous transfer isn't sensitive to schedule delay - the patch schedules giveback of periodic URBs using tasklet_hi_schedule, so the introduced delay should be very small - for ISOC transfer, generally, drivers submit several URBs concurrently to avoid interrupt delay, so it is OK with the little schedule delay. - for interrupt transfer, generally, drivers only submit one URB at the same time, but interrupt transfer is often used in event report, polling, ... situations, and a little delay should be OK. Considered that HCDs may optimize on submitting URB in complete(), the patch may cause the optimization not working, so introduces one flag to mark if the HCD supports to run giveback URB in tasklet context. When all HCDs are ready, the flag can be removed. [1], http://marc.info/?t=136438111600010&r=1&w=2 Cc: Oliver Neukum Acked-by: Alan Stern Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 147 ++++++++++++++++++++++++++++++++++++++---------- include/linux/usb/hcd.h | 17 ++++++ 2 files changed, 134 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index dc1346fee76c..0ffe016f4036 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -696,15 +696,7 @@ error: /* any errors get returned through the urb completion */ spin_lock_irq(&hcd_root_hub_lock); usb_hcd_unlink_urb_from_ep(hcd, urb); - - /* This peculiar use of spinlocks echoes what real HC drivers do. - * Avoiding calls to local_irq_disable/enable makes the code - * RT-friendly. - */ - spin_unlock(&hcd_root_hub_lock); usb_hcd_giveback_urb(hcd, urb, status); - spin_lock(&hcd_root_hub_lock); - spin_unlock_irq(&hcd_root_hub_lock); return 0; } @@ -744,9 +736,7 @@ void usb_hcd_poll_rh_status(struct usb_hcd *hcd) memcpy(urb->transfer_buffer, buffer, length); usb_hcd_unlink_urb_from_ep(hcd, urb); - spin_unlock(&hcd_root_hub_lock); usb_hcd_giveback_urb(hcd, urb, 0); - spin_lock(&hcd_root_hub_lock); } else { length = 0; set_bit(HCD_FLAG_POLL_PENDING, &hcd->flags); @@ -836,10 +826,7 @@ static int usb_rh_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) if (urb == hcd->status_urb) { hcd->status_urb = NULL; usb_hcd_unlink_urb_from_ep(hcd, urb); - - spin_unlock(&hcd_root_hub_lock); usb_hcd_giveback_urb(hcd, urb, status); - spin_lock(&hcd_root_hub_lock); } } done: @@ -1656,6 +1643,72 @@ int usb_hcd_unlink_urb (struct urb *urb, int status) /*-------------------------------------------------------------------------*/ +static void __usb_hcd_giveback_urb(struct urb *urb) +{ + struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); + int status = urb->unlinked; + unsigned long flags; + + urb->hcpriv = NULL; + if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && + urb->actual_length < urb->transfer_buffer_length && + !status)) + status = -EREMOTEIO; + + unmap_urb_for_dma(hcd, urb); + usbmon_urb_complete(&hcd->self, urb, status); + usb_unanchor_urb(urb); + + /* pass ownership to the completion handler */ + urb->status = status; + + /* + * We disable local IRQs here avoid possible deadlock because + * drivers may call spin_lock() to hold lock which might be + * acquired in one hard interrupt handler. + * + * The local_irq_save()/local_irq_restore() around complete() + * will be removed if current USB drivers have been cleaned up + * and no one may trigger the above deadlock situation when + * running complete() in tasklet. + */ + local_irq_save(flags); + urb->complete(urb); + local_irq_restore(flags); + + atomic_dec(&urb->use_count); + if (unlikely(atomic_read(&urb->reject))) + wake_up(&usb_kill_urb_queue); + usb_put_urb(urb); +} + +static void usb_giveback_urb_bh(unsigned long param) +{ + struct giveback_urb_bh *bh = (struct giveback_urb_bh *)param; + struct list_head local_list; + + spin_lock_irq(&bh->lock); + bh->running = true; + restart: + list_replace_init(&bh->head, &local_list); + spin_unlock_irq(&bh->lock); + + while (!list_empty(&local_list)) { + struct urb *urb; + + urb = list_entry(local_list.next, struct urb, urb_list); + list_del_init(&urb->urb_list); + __usb_hcd_giveback_urb(urb); + } + + /* check if there are new URBs to giveback */ + spin_lock_irq(&bh->lock); + if (!list_empty(&bh->head)) + goto restart; + bh->running = false; + spin_unlock_irq(&bh->lock); +} + /** * usb_hcd_giveback_urb - return URB from HCD to device driver * @hcd: host controller returning the URB @@ -1675,25 +1728,37 @@ int usb_hcd_unlink_urb (struct urb *urb, int status) */ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status) { - urb->hcpriv = NULL; - if (unlikely(urb->unlinked)) - status = urb->unlinked; - else if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && - urb->actual_length < urb->transfer_buffer_length && - !status)) - status = -EREMOTEIO; + struct giveback_urb_bh *bh; + bool running, high_prio_bh; - unmap_urb_for_dma(hcd, urb); - usbmon_urb_complete(&hcd->self, urb, status); - usb_unanchor_urb(urb); + /* pass status to tasklet via unlinked */ + if (likely(!urb->unlinked)) + urb->unlinked = status; - /* pass ownership to the completion handler */ - urb->status = status; - urb->complete (urb); - atomic_dec (&urb->use_count); - if (unlikely(atomic_read(&urb->reject))) - wake_up (&usb_kill_urb_queue); - usb_put_urb (urb); + if (!hcd_giveback_urb_in_bh(hcd) && !is_root_hub(urb->dev)) { + __usb_hcd_giveback_urb(urb); + return; + } + + if (usb_pipeisoc(urb->pipe) || usb_pipeint(urb->pipe)) { + bh = &hcd->high_prio_bh; + high_prio_bh = true; + } else { + bh = &hcd->low_prio_bh; + high_prio_bh = false; + } + + spin_lock(&bh->lock); + list_add_tail(&urb->urb_list, &bh->head); + running = bh->running; + spin_unlock(&bh->lock); + + if (running) + ; + else if (high_prio_bh) + tasklet_hi_schedule(&bh->bh); + else + tasklet_schedule(&bh->bh); } EXPORT_SYMBOL_GPL(usb_hcd_giveback_urb); @@ -2322,6 +2387,14 @@ EXPORT_SYMBOL_GPL (usb_hc_died); /*-------------------------------------------------------------------------*/ +static void init_giveback_urb_bh(struct giveback_urb_bh *bh) +{ + + spin_lock_init(&bh->lock); + INIT_LIST_HEAD(&bh->head); + tasklet_init(&bh->bh, usb_giveback_urb_bh, (unsigned long)bh); +} + /** * usb_create_shared_hcd - create and initialize an HCD structure * @driver: HC driver that will use this hcd @@ -2590,6 +2663,10 @@ int usb_add_hcd(struct usb_hcd *hcd, && device_can_wakeup(&hcd->self.root_hub->dev)) dev_dbg(hcd->self.controller, "supports USB remote wakeup\n"); + /* initialize tasklets */ + init_giveback_urb_bh(&hcd->high_prio_bh); + init_giveback_urb_bh(&hcd->low_prio_bh); + /* enable irqs just before we start the controller, * if the BIOS provides legacy PCI irqs. */ @@ -2698,6 +2775,16 @@ void usb_remove_hcd(struct usb_hcd *hcd) usb_disconnect(&rhdev); /* Sets rhdev to NULL */ mutex_unlock(&usb_bus_list_lock); + /* + * tasklet_kill() isn't needed here because: + * - driver's disconnect() called from usb_disconnect() should + * make sure its URBs are completed during the disconnect() + * callback + * + * - it is too late to run complete() here since driver may have + * been removed already now + */ + /* Prevent any more root-hub status calls from the timer. * The HCD might still restart the timer (if a port status change * interrupt occurs), but usb_hcd_poll_rh_status() won't invoke diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 1e88377e22f4..a9c7d44bd2ed 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -22,6 +22,7 @@ #ifdef __KERNEL__ #include +#include #define MAX_TOPO_LEVEL 6 @@ -67,6 +68,13 @@ /*-------------------------------------------------------------------------*/ +struct giveback_urb_bh { + bool running; + spinlock_t lock; + struct list_head head; + struct tasklet_struct bh; +}; + struct usb_hcd { /* @@ -139,6 +147,9 @@ struct usb_hcd { resource_size_t rsrc_len; /* memory/io resource length */ unsigned power_budget; /* in mA, 0 = no limit */ + struct giveback_urb_bh high_prio_bh; + struct giveback_urb_bh low_prio_bh; + /* bandwidth_mutex should be taken before adding or removing * any new bus bandwidth constraints: * 1. Before adding a configuration for a new device. @@ -221,6 +232,7 @@ struct hc_driver { #define HCD_USB25 0x0030 /* Wireless USB 1.0 (USB 2.5)*/ #define HCD_USB3 0x0040 /* USB 3.0 */ #define HCD_MASK 0x0070 +#define HCD_BH 0x0100 /* URB complete in BH context */ /* called to init HCD and root hub */ int (*reset) (struct usb_hcd *hcd); @@ -361,6 +373,11 @@ struct hc_driver { int (*find_raw_port_number)(struct usb_hcd *, int); }; +static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd) +{ + return hcd->driver->flags & HCD_BH; +} + extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); extern int usb_hcd_check_unlink_urb(struct usb_hcd *hcd, struct urb *urb, int status); -- cgit v1.2.3-71-gd317 From bcc48f1a7a0d40ae2e5a26aff72c2b674fd8b596 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 8 Aug 2013 21:48:22 +0800 Subject: USB: introduce usb_device_no_sg_constraint() helper Some host controllers(such as xHCI) can support building packet from discontinuous buffers, so introduce one flag and helper for this kind of host controllers, then the feature can help some applications(such as usbnet) by supporting arbitrary length of sg buffers. Acked-by: Alan Stern Signed-off-by: Ming Lei Reviewed-by: Eric Dumazet Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/urb.c | 3 ++- include/linux/usb.h | 8 +++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index 4e7a311ff6d7..c12bc790a6a7 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -416,7 +416,8 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags) urb->iso_frame_desc[n].status = -EXDEV; urb->iso_frame_desc[n].actual_length = 0; } - } else if (dev->speed != USB_SPEED_WIRELESS && urb->num_sgs) { + } else if (urb->num_sgs && !urb->dev->bus->no_sg_constraint && + dev->speed != USB_SPEED_WIRELESS) { struct scatterlist *sg; int i; diff --git a/include/linux/usb.h b/include/linux/usb.h index acb1b0aa77d8..001629cd1a97 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -337,6 +337,7 @@ struct usb_bus { * the ep queue on a short transfer * with the URB_SHORT_NOT_OK flag set. */ + unsigned no_sg_constraint:1; /* no sg constraint */ unsigned sg_tablesize; /* 0 or largest number of sg list entries */ int devnum_next; /* Next open device number in @@ -684,6 +685,11 @@ static inline bool usb_device_supports_ltm(struct usb_device *udev) return udev->bos->ss_cap->bmAttributes & USB_LTM_SUPPORT; } +static inline bool usb_device_no_sg_constraint(struct usb_device *udev) +{ + return udev && udev->bus && udev->bus->no_sg_constraint; +} + /*-------------------------------------------------------------------------*/ @@ -1253,7 +1259,7 @@ typedef void (*usb_complete_t)(struct urb *); * transfer_buffer. * @sg: scatter gather buffer list, the buffer size of each element in * the list (except the last) must be divisible by the endpoint's - * max packet size + * max packet size if no_sg_constraint isn't set in 'struct usb_bus' * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.3-71-gd317 From 638c5115a794981441246fa8fa5d95c1875af5ba Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 8 Aug 2013 21:48:24 +0800 Subject: USBNET: support DMA SG This patch introduces support of DMA SG if the USB host controller which usbnet device is attached to is capable of building packet from discontinuous buffers. The patch supports passing the skb fragment buffers to usb stack directly via urb->sg. Cc: Ben Hutchings Cc: Grant Grundler Cc: Freddy Xin Cc: Alan Stern Acked-by: Oliver Neukum Signed-off-by: Ming Lei Reviewed-by: Eric Dumazet Acked-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/usb/usbnet.c | 45 ++++++++++++++++++++++++++++++++++++++++++--- include/linux/usb/usbnet.h | 1 + 2 files changed, 43 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 06ee82f557d4..27a00b006033 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1197,6 +1197,37 @@ EXPORT_SYMBOL_GPL(usbnet_tx_timeout); /*-------------------------------------------------------------------------*/ +static int build_dma_sg(const struct sk_buff *skb, struct urb *urb) +{ + unsigned num_sgs, total_len = 0; + int i, s = 0; + + num_sgs = skb_shinfo(skb)->nr_frags + 1; + if (num_sgs == 1) + return 0; + + urb->sg = kmalloc(num_sgs * sizeof(struct scatterlist), GFP_ATOMIC); + if (!urb->sg) + return -ENOMEM; + + urb->num_sgs = num_sgs; + sg_init_table(urb->sg, urb->num_sgs); + + sg_set_buf(&urb->sg[s++], skb->data, skb_headlen(skb)); + total_len += skb_headlen(skb); + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + struct skb_frag_struct *f = &skb_shinfo(skb)->frags[i]; + + total_len += skb_frag_size(f); + sg_set_page(&urb->sg[i + s], f->page.p, f->size, + f->page_offset); + } + urb->transfer_buffer_length = total_len; + + return 1; +} + netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, struct net_device *net) { @@ -1223,7 +1254,6 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, goto drop; } } - length = skb->len; if (!(urb = usb_alloc_urb (0, GFP_ATOMIC))) { netif_dbg(dev, tx_err, dev->net, "no urb\n"); @@ -1233,10 +1263,14 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, entry = (struct skb_data *) skb->cb; entry->urb = urb; entry->dev = dev; - entry->length = length; usb_fill_bulk_urb (urb, dev->udev, dev->out, skb->data, skb->len, tx_complete, skb); + if (dev->can_dma_sg) { + if (build_dma_sg(skb, urb) < 0) + goto drop; + } + entry->length = length = urb->transfer_buffer_length; /* don't assume the hardware handles USB_ZERO_PACKET * NOTE: strictly conforming cdc-ether devices should expect @@ -1305,7 +1339,10 @@ drop: not_drop: if (skb) dev_kfree_skb_any (skb); - usb_free_urb (urb); + if (urb) { + kfree(urb->sg); + usb_free_urb(urb); + } } else netif_dbg(dev, tx_queued, dev->net, "> tx, len %d, type 0x%x\n", length, skb->protocol); @@ -1356,6 +1393,7 @@ static void usbnet_bh (unsigned long param) rx_process (dev, skb); continue; case tx_done: + kfree(entry->urb->sg); case rx_cleanup: usb_free_urb (entry->urb); dev_kfree_skb (skb); @@ -1689,6 +1727,7 @@ int usbnet_resume (struct usb_interface *intf) retval = usb_submit_urb(res, GFP_ATOMIC); if (retval < 0) { dev_kfree_skb_any(skb); + kfree(res->sg); usb_free_urb(res); usb_autopm_put_interface_async(dev->intf); } else { diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index f18d64129f99..2b47e6364e36 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -34,6 +34,7 @@ struct usbnet { struct mutex phy_mutex; unsigned char suspend_count; unsigned char pkt_cnt, pkt_err; + unsigned can_dma_sg:1; /* i/o info: pipes etc */ unsigned in, out; -- cgit v1.2.3-71-gd317 From 3775a209d38aa3a0c7ed89a7d0f529e0230f280e Mon Sep 17 00:00:00 2001 From: Casey Leedom Date: Tue, 6 Aug 2013 15:48:36 +0530 Subject: PCI: Add pci_wait_for_pending_transaction() New routine to avoid duplication of code to wait for pending PCI transactions to complete. Signed-off-by: Casey Leedom Signed-off-by: Vipul Pandya Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 38 +++++++++++++++++++++++++------------- include/linux/pci.h | 1 + 2 files changed, 26 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e37fea6e178d..10ab64e8878e 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3098,19 +3098,17 @@ int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask) } EXPORT_SYMBOL(pci_set_dma_seg_boundary); -static int pcie_flr(struct pci_dev *dev, int probe) +/** + * pci_wait_for_pending_transaction - waits for pending transaction + * @dev: the PCI device to operate on + * + * Return 0 if transaction is pending 1 otherwise. + */ +int pci_wait_for_pending_transaction(struct pci_dev *dev) { int i; - u32 cap; u16 status; - pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); - if (!(cap & PCI_EXP_DEVCAP_FLR)) - return -ENOTTY; - - if (probe) - return 0; - /* Wait for Transaction Pending bit clean */ for (i = 0; i < 4; i++) { if (i) @@ -3118,13 +3116,27 @@ static int pcie_flr(struct pci_dev *dev, int probe) pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &status); if (!(status & PCI_EXP_DEVSTA_TRPND)) - goto clear; + return 1; } - dev_err(&dev->dev, "transaction is not cleared; " - "proceeding with reset anyway\n"); + return 0; +} +EXPORT_SYMBOL(pci_wait_for_pending_transaction); + +static int pcie_flr(struct pci_dev *dev, int probe) +{ + u32 cap; + + pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); + if (!(cap & PCI_EXP_DEVCAP_FLR)) + return -ENOTTY; + + if (probe) + return 0; + + if (!pci_wait_for_pending_transaction(dev)) + dev_err(&dev->dev, "transaction is not cleared; proceeding with reset anyway\n"); -clear: pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR); msleep(100); diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..e6470016c718 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -914,6 +914,7 @@ bool pci_check_and_unmask_intx(struct pci_dev *dev); void pci_msi_off(struct pci_dev *dev); int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size); int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask); +int pci_wait_for_pending_transaction(struct pci_dev *dev); int pcix_get_max_mmrbc(struct pci_dev *dev); int pcix_get_mmrbc(struct pci_dev *dev); int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc); -- cgit v1.2.3-71-gd317 From fa6fdb33b486a8afc5439c504da8d581e142c77d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:55 -0700 Subject: driver core: bus_type: add dev_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add dev_groups to struct bus_type which should be used instead of dev_attrs. dev_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 5 +++++ drivers/base/bus.c | 6 ++++++ drivers/base/core.c | 7 +++---- include/linux/device.h | 4 +++- 4 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/base.h b/drivers/base/base.h index b8bdfe61daa6..fccf954f82fd 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -119,6 +119,11 @@ static inline int driver_match_device(struct device_driver *drv, return drv->bus->match ? drv->bus->match(dev, drv) : 1; } +extern int device_add_groups(struct device *dev, + const struct attribute_group **groups); +extern void device_remove_groups(struct device *dev, + const struct attribute_group **groups); + extern char *make_class_name(const char *name, struct kobject *kobj); extern int devres_release_all(struct device *dev); diff --git a/drivers/base/bus.c b/drivers/base/bus.c index d414331b480e..7b2dc5ba7d79 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -499,6 +499,9 @@ int bus_add_device(struct device *dev) error = device_add_attrs(bus, dev); if (error) goto out_put; + error = device_add_groups(dev, bus->dev_groups); + if (error) + goto out_groups; error = sysfs_create_link(&bus->p->devices_kset->kobj, &dev->kobj, dev_name(dev)); if (error) @@ -513,6 +516,8 @@ int bus_add_device(struct device *dev) out_subsys: sysfs_remove_link(&bus->p->devices_kset->kobj, dev_name(dev)); +out_groups: + device_remove_groups(dev, bus->dev_groups); out_id: device_remove_attrs(bus, dev); out_put: @@ -575,6 +580,7 @@ void bus_remove_device(struct device *dev) sysfs_remove_link(&dev->bus->p->devices_kset->kobj, dev_name(dev)); device_remove_attrs(dev->bus, dev); + device_remove_groups(dev, dev->bus->dev_groups); if (klist_node_attached(&dev->p->knode_bus)) klist_del(&dev->p->knode_bus); diff --git a/drivers/base/core.c b/drivers/base/core.c index e51c78782933..09a99d609644 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -491,8 +491,7 @@ static void device_remove_bin_attributes(struct device *dev, device_remove_bin_file(dev, &attrs[i]); } -static int device_add_groups(struct device *dev, - const struct attribute_group **groups) +int device_add_groups(struct device *dev, const struct attribute_group **groups) { int error = 0; int i; @@ -511,8 +510,8 @@ static int device_add_groups(struct device *dev, return error; } -static void device_remove_groups(struct device *dev, - const struct attribute_group **groups) +void device_remove_groups(struct device *dev, + const struct attribute_group **groups) { int i; diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..3aec4a68b1d4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,6 +66,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @bus_attrs: Default attributes of the bus. * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. + * @dev_groups: Default attributes of the devices on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver * is added for this bus. It should return a nonzero value if the * given device can be handled by the given driver. @@ -104,8 +105,9 @@ struct bus_type { const char *dev_name; struct device *dev_root; struct bus_attribute *bus_attrs; - struct device_attribute *dev_attrs; + struct device_attribute *dev_attrs; /* use dev_groups instead */ struct driver_attribute *drv_attrs; + const struct attribute_group **dev_groups; int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.2.3-71-gd317 From ed0617b5c0bcd7fd04053568aa0cc19a977a1f26 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:56 -0700 Subject: driver core: bus_type: add drv_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add drv_groups to struct bus_type which should be used instead of drv_attrs. drv_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 5 +++++ drivers/base/bus.c | 5 +++++ drivers/base/driver.c | 8 ++++---- include/linux/device.h | 4 +++- 4 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/base.h b/drivers/base/base.h index fccf954f82fd..2cbc6774f4cd 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -119,6 +119,11 @@ static inline int driver_match_device(struct device_driver *drv, return drv->bus->match ? drv->bus->match(dev, drv) : 1; } +extern int driver_add_groups(struct device_driver *drv, + const struct attribute_group **groups); +extern void driver_remove_groups(struct device_driver *drv, + const struct attribute_group **groups); + extern int device_add_groups(struct device *dev, const struct attribute_group **groups); extern void device_remove_groups(struct device *dev, diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 7b2dc5ba7d79..de5ce22df306 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -725,6 +725,10 @@ int bus_add_driver(struct device_driver *drv) printk(KERN_ERR "%s: driver_add_attrs(%s) failed\n", __func__, drv->name); } + error = driver_add_groups(drv, bus->drv_groups); + if (error) + printk(KERN_ERR "%s: driver_create_groups(%s) failed\n", + __func__, drv->name); if (!drv->suppress_bind_attrs) { error = add_bind_files(drv); @@ -762,6 +766,7 @@ void bus_remove_driver(struct device_driver *drv) if (!drv->suppress_bind_attrs) remove_bind_files(drv); driver_remove_attrs(drv->bus, drv); + driver_remove_groups(drv, drv->bus->drv_groups); driver_remove_file(drv, &driver_attr_uevent); klist_remove(&drv->p->knode_bus); pr_debug("bus: '%s': remove driver %s\n", drv->bus->name, drv->name); diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 974e301a1ef0..89db726ebb98 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -123,8 +123,8 @@ void driver_remove_file(struct device_driver *drv, } EXPORT_SYMBOL_GPL(driver_remove_file); -static int driver_add_groups(struct device_driver *drv, - const struct attribute_group **groups) +int driver_add_groups(struct device_driver *drv, + const struct attribute_group **groups) { int error = 0; int i; @@ -143,8 +143,8 @@ static int driver_add_groups(struct device_driver *drv, return error; } -static void driver_remove_groups(struct device_driver *drv, - const struct attribute_group **groups) +void driver_remove_groups(struct device_driver *drv, + const struct attribute_group **groups) { int i; diff --git a/include/linux/device.h b/include/linux/device.h index 3aec4a68b1d4..94d987f128bb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -67,6 +67,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. * @dev_groups: Default attributes of the devices on the bus. + * @drv_groups: Default attributes of the device drivers on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver * is added for this bus. It should return a nonzero value if the * given device can be handled by the given driver. @@ -106,8 +107,9 @@ struct bus_type { struct device *dev_root; struct bus_attribute *bus_attrs; struct device_attribute *dev_attrs; /* use dev_groups instead */ - struct driver_attribute *drv_attrs; + struct driver_attribute *drv_attrs; /* use drv_groups instead */ const struct attribute_group **dev_groups; + const struct attribute_group **drv_groups; int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.2.3-71-gd317 From 12478ba077adf8b53be6101b80dd8a65e4df9ea6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Aug 2013 15:22:57 -0700 Subject: driver core: bus_type: add bus_groups attribute groups are much more flexible than just a list of attributes, due to their support for visibility of the attributes, and binary attributes. Add bus_groups to struct bus_type which should be used instead of bus_attrs. bus_attrs will be removed from the structure soon. Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 37 +++++++++++++++++++++++++++++++++++++ include/linux/device.h | 4 +++- 2 files changed, 40 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index de5ce22df306..5ee5d3c1d74b 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -881,6 +881,37 @@ static void bus_remove_attrs(struct bus_type *bus) } } +static int bus_add_groups(struct bus_type *bus, + const struct attribute_group **groups) +{ + int error = 0; + int i; + + if (groups) { + for (i = 0; groups[i]; i++) { + error = sysfs_create_group(&bus->p->subsys.kobj, + groups[i]); + if (error) { + while (--i >= 0) + sysfs_remove_group(&bus->p->subsys.kobj, + groups[i]); + break; + } + } + } + return error; +} + +static void bus_remove_groups(struct bus_type *bus, + const struct attribute_group **groups) +{ + int i; + + if (groups) + for (i = 0; groups[i]; i++) + sysfs_remove_group(&bus->p->subsys.kobj, groups[i]); +} + static void klist_devices_get(struct klist_node *n) { struct device_private *dev_prv = to_device_private_bus(n); @@ -973,10 +1004,15 @@ int bus_register(struct bus_type *bus) retval = bus_add_attrs(bus); if (retval) goto bus_attrs_fail; + retval = bus_add_groups(bus, bus->bus_groups); + if (retval) + goto bus_groups_fail; pr_debug("bus: '%s': registered\n", bus->name); return 0; +bus_groups_fail: + bus_remove_attrs(bus); bus_attrs_fail: remove_probe_files(bus); bus_probe_files_fail: @@ -1007,6 +1043,7 @@ void bus_unregister(struct bus_type *bus) if (bus->dev_root) device_unregister(bus->dev_root); bus_remove_attrs(bus); + bus_remove_groups(bus, bus->bus_groups); remove_probe_files(bus); kset_unregister(bus->p->drivers_kset); kset_unregister(bus->p->devices_kset); diff --git a/include/linux/device.h b/include/linux/device.h index 94d987f128bb..26e23b22ed0a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -66,6 +66,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * @bus_attrs: Default attributes of the bus. * @dev_attrs: Default attributes of the devices on the bus. * @drv_attrs: Default attributes of the device drivers on the bus. + * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. * @match: Called, perhaps multiple times, whenever a new device or driver @@ -105,9 +106,10 @@ struct bus_type { const char *name; const char *dev_name; struct device *dev_root; - struct bus_attribute *bus_attrs; + struct bus_attribute *bus_attrs; /* use bus_groups instead */ struct device_attribute *dev_attrs; /* use dev_groups instead */ struct driver_attribute *drv_attrs; /* use drv_groups instead */ + const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; -- cgit v1.2.3-71-gd317 From 2d854e5738cded368a0759f85b1197f5c044513d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 19:02:30 +0200 Subject: context_tracing: Fix guest accounting with native vtime 1) If context tracking is enabled with native vtime accounting (which combo is useless except for dev testing), we call vtime_guest_enter() and vtime_guest_exit() on host <-> guest switches. But those are stubs in this configurations. As a result, cputime is not correctly flushed on kvm context switches. 2) If context tracking runs but is disabled on some CPUs, those CPUs end up calling __guest_enter/__guest_exit which in turn call vtime_account_system(). We don't want to call this because we run in tick based accounting for these CPUs. Refactor the guest_enter/guest_exit code such that all combinations finally work. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 52 +++++++++++++++++----------------------- kernel/context_tracking.c | 6 +++-- 2 files changed, 26 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index fc09d7b0dacf..5984f2556d13 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -20,25 +20,6 @@ struct context_tracking { } state; }; -static inline void __guest_enter(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags |= PF_VCPU; -} - -static inline void __guest_exit(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags &= ~PF_VCPU; -} #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); @@ -56,9 +37,6 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); -extern void guest_enter(void); -extern void guest_exit(void); - static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; @@ -81,21 +59,35 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } +static inline enum ctx_state exception_enter(void) { return 0; } +static inline void exception_exit(enum ctx_state prev_ctx) { } +static inline void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) { } +#endif /* !CONFIG_CONTEXT_TRACKING */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void guest_enter(void); +extern void guest_exit(void); +#else static inline void guest_enter(void) { - __guest_enter(); + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags |= PF_VCPU; } static inline void guest_exit(void) { - __guest_exit(); + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags &= ~PF_VCPU; } - -static inline enum ctx_state exception_enter(void) { return 0; } -static inline void exception_exit(enum ctx_state prev_ctx) { } -static inline void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) { } -#endif /* !CONFIG_CONTEXT_TRACKING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ #endif diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 942835c12ae5..1f47119c5b09 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -141,12 +141,13 @@ void user_exit(void) local_irq_restore(flags); } +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN void guest_enter(void) { if (vtime_accounting_enabled()) vtime_guest_enter(current); else - __guest_enter(); + current->flags |= PF_VCPU; } EXPORT_SYMBOL_GPL(guest_enter); @@ -155,9 +156,10 @@ void guest_exit(void) if (vtime_accounting_enabled()) vtime_guest_exit(current); else - __guest_exit(); + current->flags &= ~PF_VCPU; } EXPORT_SYMBOL_GPL(guest_exit); +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ /** -- cgit v1.2.3-71-gd317 From 5b206d48e58204e84d249c4eb18651a1ff7a1274 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 19:05:14 +0200 Subject: vtime: Update a few comments Update a stale comment from the old vtime era and document some locking that might be non obvious. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 10 ++++------ kernel/sched/cputime.c | 7 +++++++ 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 5984f2556d13..d883ff0dd8fc 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -72,8 +72,9 @@ extern void guest_exit(void); static inline void guest_enter(void) { /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. + * This is running in ioctl context so its safe + * to assume that it's the stime pending cputime + * to flush. */ vtime_account_system(current); current->flags |= PF_VCPU; @@ -81,10 +82,7 @@ static inline void guest_enter(void) static inline void guest_exit(void) { - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ + /* Flush the guest cputime we spent on the guest */ vtime_account_system(current); current->flags &= ~PF_VCPU; } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index a7959e05a9d5..223a35efa0a6 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -712,6 +712,13 @@ void vtime_user_enter(struct task_struct *tsk) void vtime_guest_enter(struct task_struct *tsk) { + /* + * The flags must be updated under the lock with + * the vtime_snap flush and update. + * That enforces a right ordering and update sequence + * synchronization against the reader (task_gtime()) + * that can thus safely catch up with a tickless delta. + */ write_seqlock(&tsk->vtime_seqlock); __vtime_account_system(tsk); current->flags |= PF_VCPU; -- cgit v1.2.3-71-gd317 From 2e70933866ace52091a3c11a5c104c063ab0c445 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 00:55:25 +0200 Subject: nohz: Only enable context tracking on full dynticks CPUs The context tracking subsystem has the ability to selectively enable the tracking on any defined subset of CPU. This means that we can define a CPU range that doesn't run the context tracking and another range that does. Now what we want in practice is to enable the tracking on full dynticks CPUs only. In order to perform this, we just need to pass our full dynticks CPU range selection from the full dynticks subsystem to the context tracking. This way we can spare the overhead of RCU user extended quiescent state and vtime maintainance on the CPUs that are outside the full dynticks range. Just keep in mind the raw context tracking itself is still necessary everywhere. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 2 ++ kernel/context_tracking.c | 5 +++++ kernel/time/tick-sched.c | 6 ++++++ 3 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d883ff0dd8fc..1ae37c708c63 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -34,6 +34,8 @@ static inline bool context_tracking_active(void) return __this_cpu_read(context_tracking.active); } +extern void context_tracking_cpu_set(int cpu); + extern void user_enter(void); extern void user_exit(void); diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 7b095de356c5..72bcb2570d3e 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -26,6 +26,11 @@ DEFINE_PER_CPU(struct context_tracking, context_tracking) = { #endif }; +void context_tracking_cpu_set(int cpu) +{ + per_cpu(context_tracking.active, cpu) = true; +} + /** * user_enter - Inform the context tracking that the CPU is going to * enter userspace mode. diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9563c744dad2..91a2528b5f44 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -344,11 +345,16 @@ static int tick_nohz_init_all(void) void __init tick_nohz_init(void) { + int cpu; + if (!have_nohz_full_mask) { if (tick_nohz_init_all() < 0) return; } + for_each_cpu(cpu, nohz_full_mask) + context_tracking_cpu_set(cpu); + cpu_notifier(tick_nohz_cpu_down_callback, 0); cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask); pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); -- cgit v1.2.3-71-gd317 From b9d10be7a8e88fdcb12540387c219cdde87b0795 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Mon, 12 Aug 2013 09:45:53 -0600 Subject: ACPI / processor: Acquire writer lock to update CPU maps CPU system maps are protected with reader/writer locks. The reader lock, get_online_cpus(), assures that the maps are not updated while holding the lock. The writer lock, cpu_hotplug_begin(), is used to udpate the cpu maps along with cpu_maps_update_begin(). However, the ACPI processor handler updates the cpu maps without holding the the writer lock. acpi_map_lsapic() is called from acpi_processor_hotadd_init() to update cpu_possible_mask and cpu_present_mask. acpi_unmap_lsapic() is called from acpi_processor_remove() to update cpu_possible_mask. Currently, they are either unprotected or protected with the reader lock, which is not correct. For example, the get_online_cpus() below is supposed to assure that cpu_possible_mask is not changed while the code is iterating with for_each_possible_cpu(). get_online_cpus(); for_each_possible_cpu(cpu) { : } put_online_cpus(); However, this lock has no protection with CPU hotplug since the ACPI processor handler does not use the writer lock when it updates cpu_possible_mask. The reader lock does not serialize within the readers. This patch protects them with the writer lock with cpu_hotplug_begin() along with cpu_maps_update_begin(), which must be held before calling cpu_hotplug_begin(). It also protects arch_register_cpu() / arch_unregister_cpu(), which creates / deletes a sysfs cpu device interface. For this purpose it changes cpu_hotplug_begin() and cpu_hotplug_done() to global and exports them in cpu.h. Signed-off-by: Toshi Kani Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpi_processor.c | 21 ++++++++++++++++----- include/linux/cpu.h | 4 ++++ kernel/cpu.c | 9 +++------ 3 files changed, 23 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 5a74a9c1e42c..f29e06efa479 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -178,14 +178,17 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr) if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT)) return -ENODEV; + cpu_maps_update_begin(); + cpu_hotplug_begin(); + ret = acpi_map_lsapic(pr->handle, &pr->id); if (ret) - return ret; + goto out; ret = arch_register_cpu(pr->id); if (ret) { acpi_unmap_lsapic(pr->id); - return ret; + goto out; } /* @@ -195,7 +198,11 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr) */ pr_info("CPU%d has been hot-added\n", pr->id); pr->flags.need_hotplug_init = 1; - return 0; + +out: + cpu_hotplug_done(); + cpu_maps_update_done(); + return ret; } #else static inline int acpi_processor_hotadd_init(struct acpi_processor *pr) @@ -452,11 +459,15 @@ static void acpi_processor_remove(struct acpi_device *device) per_cpu(processor_device_array, pr->id) = NULL; per_cpu(processors, pr->id) = NULL; + cpu_maps_update_begin(); + cpu_hotplug_begin(); + /* Remove the CPU. */ - get_online_cpus(); arch_unregister_cpu(pr->id); acpi_unmap_lsapic(pr->id); - put_online_cpus(); + + cpu_hotplug_done(); + cpu_maps_update_done(); try_offline_node(cpu_to_node(pr->id)); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ab0eade73039..956c0a16566f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -172,6 +172,8 @@ extern struct bus_type cpu_subsys; #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ +extern void cpu_hotplug_begin(void); +extern void cpu_hotplug_done(void); extern void get_online_cpus(void); extern void put_online_cpus(void); extern void cpu_hotplug_disable(void); @@ -197,6 +199,8 @@ static inline void cpu_hotplug_driver_unlock(void) #else /* CONFIG_HOTPLUG_CPU */ +static inline void cpu_hotplug_begin(void) {} +static inline void cpu_hotplug_done(void) {} #define get_online_cpus() do { } while (0) #define put_online_cpus() do { } while (0) #define cpu_hotplug_disable() do { } while (0) diff --git a/kernel/cpu.c b/kernel/cpu.c index b2b227b82123..d7f07a2da5a6 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -113,7 +113,7 @@ EXPORT_SYMBOL_GPL(put_online_cpus); * get_online_cpus() not an api which is called all that often. * */ -static void cpu_hotplug_begin(void) +void cpu_hotplug_begin(void) { cpu_hotplug.active_writer = current; @@ -127,7 +127,7 @@ static void cpu_hotplug_begin(void) } } -static void cpu_hotplug_done(void) +void cpu_hotplug_done(void) { cpu_hotplug.active_writer = NULL; mutex_unlock(&cpu_hotplug.lock); @@ -154,10 +154,7 @@ void cpu_hotplug_enable(void) cpu_maps_update_done(); } -#else /* #if CONFIG_HOTPLUG_CPU */ -static void cpu_hotplug_begin(void) {} -static void cpu_hotplug_done(void) {} -#endif /* #else #if CONFIG_HOTPLUG_CPU */ +#endif /* CONFIG_HOTPLUG_CPU */ /* Need to know about CPUs going up/down? */ int __ref register_cpu_notifier(struct notifier_block *nb) -- cgit v1.2.3-71-gd317 From 35ef10da65d43211f4cd7e7822cbb3becdfc0ae1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:54 -0400 Subject: cgroup: rename cgroup_subsys_state->dput_work and its callback function css (cgroup_subsys_state) will become RCU protected and there will be two stages which require punting to work item during release. To prepare for using the work item for multiple times, rename css->dput_work to css->destroy_work and css_dput_fn() to css_free_work_fn() and move work item initialization from css init to right before the actual usage. This reorganization doesn't introduce any behavior change. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- kernel/cgroup.c | 21 ++++++++++----------- 2 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8ec5b0f38292..12d66fee26f8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -80,7 +80,7 @@ struct cgroup_subsys_state { struct css_id __rcu *id; /* Used to put @cgroup->dentry on the last css_put() */ - struct work_struct dput_work; + struct work_struct destroy_work; }; /* bits in struct cgroup_subsys_state flags field */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 49ad96ee08e1..0b280978f097 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4259,10 +4259,10 @@ err: return ret; } -static void css_dput_fn(struct work_struct *work) +static void css_free_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = - container_of(work, struct cgroup_subsys_state, dput_work); + container_of(work, struct cgroup_subsys_state, destroy_work); cgroup_dput(css->cgroup); } @@ -4272,7 +4272,14 @@ static void css_release(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); - schedule_work(&css->dput_work); + /* + * css holds an extra ref to @cgrp->dentry which is put on the last + * css_put(). dput() requires process context, which css_put() may + * be called without. @css->destroy_work will be used to invoke + * dput() asynchronously from css_put(). + */ + INIT_WORK(&css->destroy_work, css_free_work_fn); + schedule_work(&css->destroy_work); } static void init_cgroup_css(struct cgroup_subsys_state *css, @@ -4287,14 +4294,6 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, css->flags |= CSS_ROOT; BUG_ON(cgroup_css(cgrp, ss->subsys_id)); cgrp->subsys[ss->subsys_id] = css; - - /* - * css holds an extra ref to @cgrp->dentry which is put on the last - * css_put(). dput() requires process context, which css_put() may - * be called without. @css->dput_work will be used to invoke - * dput() asynchronously from css_put(). - */ - INIT_WORK(&css->dput_work, css_dput_fn); } /* invoke ->css_online() on a new CSS and mark it online if successful */ -- cgit v1.2.3-71-gd317 From 0ae78e0bf10ac38ab53548e18383afc9997eca22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:54 -0400 Subject: cgroup: add cgroup_subsys_state->parent With the planned unified hierarchy, css's (cgroup_subsys_state) will be RCU protected and allowed to be attached and detached dynamically over the course of a cgroup's lifetime. This means that css's will stay accessible after being detached from its cgroup - the matching pointer in cgroup->subsys[] cleared - for ref draining and RCU grace period. cgroup core still wants to guarantee that the parent css is never destroyed before its children and css_parent() always returns the parent regardless of the state of the child css as long as it's accessible. This patch makes css's hold onto their parents and adds css->parent so that the parent css is never detroyed before its children and can be determined without consulting the cgroups. cgroup->dummy_css is also updated to point to the parent dummy_css; however, it doesn't need to worry about object lifetime as the parent cgroup is already pinned by the child. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 13 ++++--------- kernel/cgroup.c | 18 +++++++++++++++--- 2 files changed, 19 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 12d66fee26f8..8a5dc91fbaad 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -75,6 +75,9 @@ struct cgroup_subsys_state { /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; + /* the parent css */ + struct cgroup_subsys_state *parent; + unsigned long flags; /* ID for this css, if possible */ struct css_id __rcu *id; @@ -666,15 +669,7 @@ struct cgroup_subsys { static inline struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css) { - struct cgroup *parent_cgrp = css->cgroup->parent; - - if (!parent_cgrp) - return NULL; - - if (css->ss) - return parent_cgrp->subsys[css->ss->subsys_id]; - else - return &parent_cgrp->dummy_css; + return css->parent; } /** diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0b280978f097..5c6dd7ed26a7 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4264,6 +4264,9 @@ static void css_free_work_fn(struct work_struct *work) struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); + if (css->parent) + css_put(css->parent); + cgroup_dput(css->cgroup); } @@ -4290,8 +4293,12 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, css->ss = ss; css->flags = 0; css->id = NULL; - if (cgrp == cgroup_dummy_top) + + if (cgrp->parent) + css->parent = cgroup_css(cgrp->parent, ss->subsys_id); + else css->flags |= CSS_ROOT; + BUG_ON(cgroup_css(cgrp, ss->subsys_id)); cgrp->subsys[ss->subsys_id] = css; } @@ -4388,6 +4395,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, cgrp->dentry = dentry; cgrp->parent = parent; + cgrp->dummy_css.parent = &parent->dummy_css; cgrp->root = parent->root; if (notify_on_release(parent)) @@ -4436,9 +4444,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children); root->number_of_cgroups++; - /* each css holds a ref to the cgroup's dentry */ - for_each_root_subsys(root, ss) + /* each css holds a ref to the cgroup's dentry and the parent css */ + for_each_root_subsys(root, ss) { + struct cgroup_subsys_state *css = cgroup_css(cgrp, ss->subsys_id); + dget(dentry); + percpu_ref_get(&css->parent->refcnt); + } /* hold a ref to the parent's dentry */ dget(parent->dentry); -- cgit v1.2.3-71-gd317 From 73e80ed8007fc48a6deeb295ba37159fad274bd2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 11:01:55 -0400 Subject: cgroup: add __rcu modifier to cgroup->subsys[] For the planned unified hierarchy, each css (cgroup_subsys_state) will be RCU protected so that it can be created and destroyed individually while allowing RCU accesses. Previous changes ensured that all cgroup->subsys[] accesses use the cgroup_css() accessor. This patch adds __rcu modifier to cgroup->subsys[], add matching RCU dereference in cgroup_css() and convert all assignments to either rcu_assign_pointer() or RCU_INIT_POINTER(). This change prepares for the actual RCUfication of css's and doesn't introduce any visible behavior change. The conversion is verified with sparse and all accesses are properly RCU annotated. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- kernel/cgroup.c | 19 ++++++++++++++----- 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8a5dc91fbaad..eb200b5794e7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -204,7 +204,7 @@ struct cgroup { struct cgroup_name __rcu *name; /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; struct cgroupfs_root *root; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d63beffd41e1..c27101622567 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -229,11 +229,16 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], * @subsys_id: the subsystem of interest * * Return @cgrp's css (cgroup_subsys_state) associated with @subsys_id. + * This function must be called either under cgroup_mutex or + * rcu_read_lock() and the caller is responsible for pinning the returned + * css if it wants to keep accessing it outside the said locks. This + * function may return %NULL if @cgrp doesn't have @subsys_id enabled. */ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, int subsys_id) { - return cgrp->subsys[subsys_id]; + return rcu_dereference_check(cgrp->subsys[subsys_id], + lockdep_is_held(&cgroup_mutex)); } /* convenient tests for these bits */ @@ -1072,8 +1077,10 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(!cgroup_css(cgroup_dummy_top, i)); BUG_ON(cgroup_css(cgroup_dummy_top, i)->cgroup != cgroup_dummy_top); - cgrp->subsys[i] = cgroup_dummy_top->subsys[i]; + rcu_assign_pointer(cgrp->subsys[i], + cgroup_css(cgroup_dummy_top, i)); cgroup_css(cgrp, i)->cgroup = cgrp; + list_move(&ss->sibling, &root->subsys_list); ss->root = root; if (ss->bind) @@ -1088,8 +1095,10 @@ static int rebind_subsystems(struct cgroupfs_root *root, if (ss->bind) ss->bind(cgroup_css(cgroup_dummy_top, i)); + cgroup_css(cgroup_dummy_top, i)->cgroup = cgroup_dummy_top; - cgrp->subsys[i] = NULL; + RCU_INIT_POINTER(cgrp->subsys[i], NULL); + cgroup_subsys[i]->root = &cgroup_dummy_root; list_move(&ss->sibling, &cgroup_dummy_root.subsys_list); @@ -4314,7 +4323,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, css->flags |= CSS_ROOT; BUG_ON(cgroup_css(cgrp, ss->subsys_id)); - cgrp->subsys[ss->subsys_id] = css; + rcu_assign_pointer(cgrp->subsys[ss->subsys_id], css); } /* invoke ->css_online() on a new CSS and mark it online if successful */ @@ -4962,7 +4971,7 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) * also takes care of freeing the css_id. */ ss->css_free(cgroup_css(cgroup_dummy_top, ss->subsys_id)); - cgroup_dummy_top->subsys[ss->subsys_id] = NULL; + RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL); mutex_unlock(&cgroup_mutex); } -- cgit v1.2.3-71-gd317 From e0acd0a68ec7dbf6b7a81a87a867ebd7ac9b76c4 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 12 Aug 2013 18:14:00 +0200 Subject: sched: fix the theoretical signal_wake_up() vs schedule() race This is only theoretical, but after try_to_wake_up(p) was changed to check p->state under p->pi_lock the code like __set_current_state(TASK_INTERRUPTIBLE); schedule(); can miss a signal. This is the special case of wait-for-condition, it relies on try_to_wake_up/schedule interaction and thus it does not need mb() between __set_current_state() and if(signal_pending). However, this __set_current_state() can move into the critical section protected by rq->lock, now that try_to_wake_up() takes another lock we need to ensure that it can't be reordered with "if (signal_pending(current))" check inside that section. The patch is actually one-liner, it simply adds smp_wmb() before spin_lock_irq(rq->lock). This is what try_to_wake_up() already does by the same reason. We turn this wmb() into the new helper, smp_mb__before_spinlock(), for better documentation and to allow the architectures to change the default implementation. While at it, kill smp_mb__after_lock(), it has no callers. Perhaps we can also add smp_mb__before/after_spinunlock() for prepare_to_wait(). Signed-off-by: Oleg Nesterov Acked-by: Peter Zijlstra Signed-off-by: Linus Torvalds --- arch/x86/include/asm/spinlock.h | 4 ---- include/linux/spinlock.h | 14 +++++++++++--- kernel/sched/core.c | 14 +++++++++++++- 3 files changed, 24 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 33692eaabab5..e3ddd7db723f 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -233,8 +233,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() -/* The {read|write|spin}_lock() on x86 are full memory barriers. */ -static inline void smp_mb__after_lock(void) { } -#define ARCH_HAS_SMP_MB_AFTER_LOCK - #endif /* _ASM_X86_SPINLOCK_H */ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 7d537ced949a..75f34949d9ab 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -117,9 +117,17 @@ do { \ #endif /*arch_spin_is_contended*/ #endif -/* The lock does not imply full memory barrier. */ -#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK -static inline void smp_mb__after_lock(void) { smp_mb(); } +/* + * Despite its name it doesn't necessarily has to be a full barrier. + * It should only guarantee that a STORE before the critical section + * can not be reordered with a LOAD inside this section. + * spin_lock() is the one-way barrier, this LOAD can not escape out + * of the region. So the default implementation simply ensures that + * a STORE can not move into the critical section, smp_wmb() should + * serialize it with another STORE done by spin_lock(). + */ +#ifndef smp_mb__before_spinlock +#define smp_mb__before_spinlock() smp_wmb() #endif /** diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b7c32cb7bfeb..ef51b0ef4bdc 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1491,7 +1491,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) unsigned long flags; int cpu, success = 0; - smp_wmb(); + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + smp_mb__before_spinlock(); raw_spin_lock_irqsave(&p->pi_lock, flags); if (!(p->state & state)) goto out; @@ -2394,6 +2400,12 @@ need_resched: if (sched_feat(HRTICK)) hrtick_clear(rq); + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + */ + smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); switch_count = &prev->nivcsw; -- cgit v1.2.3-71-gd317 From f20104de55a212a9742d8df1807f1f29dc95b748 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:50 -0400 Subject: cgroup: replace cgroup->css_kill_cnt with ->nr_css Currently, css (cgroup_subsys_state) lifetime is tied to that of the associated cgroup. With the planned unified hierarchy, css's will be dynamically created and destroyed within the lifetime of a cgroup. To enable such usages, css's will be individually RCU protected instead of being tied to the cgroup. cgroup->css_kill_cnt is used during cgroup destruction to wait for css reference count disable; however, this model doesn't work once css's lifetimes are managed separately from cgroup's. This patch replaces it with cgroup->nr_css which is an cgroup_mutex protected integer counting the number of attached css's. The count is incremented from online_css() and decremented after refcnt kill is confirmed. If the count reaches zero and the cgroup is marked dead, the second stage of cgroup destruction is kicked off. If a cgroup doesn't have any css attached at the time of rmdir, cgroup_destroy_locked() now invokes the second stage directly as no css kill confirmation would happen. cgroup_offline_fn() - the second step of cgroup destruction - is renamed to cgroup_destroy_css_killed() and now expects to be called with cgroup_mutex held. While this patch changes how css destruction is punted to work items, it shouldn't change any visible behavior. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 4 +++- kernel/cgroup.c | 52 +++++++++++++++++++++++++++----------------------- 2 files changed, 31 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index eb200b5794e7..80dca872f4d4 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -171,6 +171,9 @@ struct cgroup { */ int id; + /* the number of attached css's */ + int nr_css; + /* * We link our 'sibling' struct into our parent's 'children'. * Our children link their 'sibling' into our 'children'. @@ -234,7 +237,6 @@ struct cgroup { /* For css percpu_ref killing and RCU-protected deletion */ struct rcu_head rcu_head; struct work_struct destroy_work; - atomic_t css_kill_cnt; /* List of events which userspace want to receive */ struct list_head event_list; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 398ffbbee32f..174f4c3d72ef 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -218,7 +218,7 @@ static int need_forkexit_callback __read_mostly; static struct cftype cgroup_base_files[]; -static void cgroup_offline_fn(struct work_struct *work); +static void cgroup_destroy_css_killed(struct cgroup *cgrp); static int cgroup_destroy_locked(struct cgroup *cgrp); static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], bool is_add); @@ -4335,6 +4335,7 @@ static int online_css(struct cgroup_subsys_state *css) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; + css->cgroup->nr_css++; rcu_assign_pointer(css->cgroup->subsys[ss->subsys_id], css); } return ret; @@ -4545,16 +4546,6 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) return cgroup_create(c_parent, dentry, mode | S_IFDIR); } -static void cgroup_css_killed(struct cgroup *cgrp) -{ - if (!atomic_dec_and_test(&cgrp->css_kill_cnt)) - return; - - /* percpu ref's of all css's are killed, kick off the next step */ - INIT_WORK(&cgrp->destroy_work, cgroup_offline_fn); - schedule_work(&cgrp->destroy_work); -} - /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget() is now guaranteed to fail. @@ -4565,7 +4556,17 @@ static void css_killed_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup *cgrp = css->cgroup; - cgroup_css_killed(cgrp); + mutex_lock(&cgroup_mutex); + + /* + * If @cgrp is marked dead, it's waiting for refs of all css's to + * be disabled before proceeding to the second phase of cgroup + * destruction. If we are the last one, kick it off. + */ + if (!--cgrp->nr_css && cgroup_is_dead(cgrp)) + cgroup_destroy_css_killed(cgrp); + + mutex_unlock(&cgroup_mutex); } /* css kill confirmation processing requires process context, bounce */ @@ -4634,11 +4635,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) * Use percpu_ref_kill_and_confirm() to get notifications as each * css is confirmed to be seen as killed on all CPUs. The * notification callback keeps track of the number of css's to be - * killed and schedules cgroup_offline_fn() to perform the rest of - * destruction once the percpu refs of all css's are confirmed to - * be killed. + * killed and invokes cgroup_destroy_css_killed() to perform the + * rest of destruction once the percpu refs of all css's are + * confirmed to be killed. */ - atomic_set(&cgrp->css_kill_cnt, 1); for_each_root_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgroup_css(cgrp, ss->subsys_id); @@ -4648,10 +4648,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) */ percpu_ref_get(&css->refcnt); - atomic_inc(&cgrp->css_kill_cnt); percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); } - cgroup_css_killed(cgrp); /* * Mark @cgrp dead. This prevents further task migration and child @@ -4668,6 +4666,15 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) list_del_init(&cgrp->release_list); raw_spin_unlock(&release_list_lock); + /* + * If @cgrp has css's attached, the second stage of cgroup + * destruction is kicked off from css_killed_work_fn() after the + * refs of all attached css's are killed. If @cgrp doesn't have + * any css, we kick it off here. + */ + if (!cgrp->nr_css) + cgroup_destroy_css_killed(cgrp); + /* * Clear and remove @cgrp directory. The removal puts the base ref * but we aren't quite done with @cgrp yet, so hold onto it. @@ -4693,7 +4700,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) }; /** - * cgroup_offline_fn - the second step of cgroup destruction + * cgroup_destroy_css_killed - the second step of cgroup destruction * @work: cgroup->destroy_free_work * * This function is invoked from a work item for a cgroup which is being @@ -4702,14 +4709,13 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) * is the second step of destruction described in the comment above * cgroup_destroy_locked(). */ -static void cgroup_offline_fn(struct work_struct *work) +static void cgroup_destroy_css_killed(struct cgroup *cgrp) { - struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work); struct cgroup *parent = cgrp->parent; struct dentry *d = cgrp->dentry; struct cgroup_subsys *ss; - mutex_lock(&cgroup_mutex); + lockdep_assert_held(&cgroup_mutex); /* * css_tryget() is guaranteed to fail now. Tell subsystems to @@ -4743,8 +4749,6 @@ static void cgroup_offline_fn(struct work_struct *work) set_bit(CGRP_RELEASABLE, &parent->flags); check_for_release(parent); - - mutex_unlock(&cgroup_mutex); } static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) -- cgit v1.2.3-71-gd317 From 09a503ea3a816b285b0b402b7f785eaec0c7a7e1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:50 -0400 Subject: cgroup: decouple cgroup_subsys_state destruction from cgroup destruction Currently, css (cgroup_subsys_state) lifetime is tied to that of the associated cgroup. css's are created when the associated cgroup is created and destroyed when it gets destroyed. Also, individual css's aren't RCU protected but the whole cgroup is. With the planned unified hierarchy, css's will need to be dynamically created and destroyed within the lifetime of a cgroup. To enable such usages, this patch decouples css destruction from cgroup destruction - offline_css() invocation and the final css_put() are moved from cgroup_destroy_css_killed() to css_killed_work_fn(). Now each css is individually offlined and put as its reference count is killed instead of waiting for all css's attached to the cgroup to finish refcnt killing and then proceeding to offlining and putting them together. While this changes the order of destruction operations, the changes shouldn't be noticeable to cgroup subsystems or userland. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 2 +- kernel/cgroup.c | 52 +++++++++++++++++++++++--------------------------- 2 files changed, 25 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 80dca872f4d4..71e77e7cdb6f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -82,7 +82,7 @@ struct cgroup_subsys_state { /* ID for this css, if possible */ struct css_id __rcu *id; - /* Used to put @cgroup->dentry on the last css_put() */ + /* percpu_ref killing and putting dentry on the last css_put() */ struct work_struct destroy_work; }; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 174f4c3d72ef..3c4c4b01ffe5 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4355,6 +4355,7 @@ static void offline_css(struct cgroup_subsys_state *css) ss->css_offline(css); css->flags &= ~CSS_ONLINE; + css->cgroup->nr_css--; } /* @@ -4558,15 +4559,30 @@ static void css_killed_work_fn(struct work_struct *work) mutex_lock(&cgroup_mutex); + /* + * css_tryget() is guaranteed to fail now. Tell subsystems to + * initate destruction. + */ + offline_css(css); + /* * If @cgrp is marked dead, it's waiting for refs of all css's to * be disabled before proceeding to the second phase of cgroup * destruction. If we are the last one, kick it off. */ - if (!--cgrp->nr_css && cgroup_is_dead(cgrp)) + if (!cgrp->nr_css && cgroup_is_dead(cgrp)) cgroup_destroy_css_killed(cgrp); mutex_unlock(&cgroup_mutex); + + /* + * Put the css refs from kill_css(). Each css holds an extra + * reference to the cgroup's dentry and cgroup removal proceeds + * regardless of css refs. On the last put of each css, whenever + * that may be, the extra dentry ref is put so that dentry + * destruction happens only after all css's are released. + */ + css_put(css); } /* css kill confirmation processing requires process context, bounce */ @@ -4633,11 +4649,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) * as killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each - * css is confirmed to be seen as killed on all CPUs. The - * notification callback keeps track of the number of css's to be - * killed and invokes cgroup_destroy_css_killed() to perform the - * rest of destruction once the percpu refs of all css's are - * confirmed to be killed. + * css is confirmed to be seen as killed on all CPUs. + * cgroup_destroy_css_killed() will be invoked to perform the rest + * of destruction once the percpu refs of all css's are confirmed + * to be killed. */ for_each_root_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgroup_css(cgrp, ss->subsys_id); @@ -4704,36 +4719,17 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) * @work: cgroup->destroy_free_work * * This function is invoked from a work item for a cgroup which is being - * destroyed after the percpu refcnts of all css's are guaranteed to be - * seen as killed on all CPUs, and performs the rest of destruction. This - * is the second step of destruction described in the comment above - * cgroup_destroy_locked(). + * destroyed after all css's are offlined and performs the rest of + * destruction. This is the second step of destruction described in the + * comment above cgroup_destroy_locked(). */ static void cgroup_destroy_css_killed(struct cgroup *cgrp) { struct cgroup *parent = cgrp->parent; struct dentry *d = cgrp->dentry; - struct cgroup_subsys *ss; lockdep_assert_held(&cgroup_mutex); - /* - * css_tryget() is guaranteed to fail now. Tell subsystems to - * initate destruction. - */ - for_each_root_subsys(cgrp->root, ss) - offline_css(cgroup_css(cgrp, ss->subsys_id)); - - /* - * Put the css refs from cgroup_destroy_locked(). Each css holds - * an extra reference to the cgroup's dentry and cgroup removal - * proceeds regardless of css refs. On the last put of each css, - * whenever that may be, the extra dentry ref is put so that dentry - * destruction happens only after all css's are released. - */ - for_each_root_subsys(cgrp->root, ss) - css_put(cgroup_css(cgrp, ss->subsys_id)); - /* delete this cgroup from parent->children */ list_del_rcu(&cgrp->sibling); -- cgit v1.2.3-71-gd317 From 0c21ead136a900c36f1ab74fd7d09a306dc31324 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Aug 2013 20:22:51 -0400 Subject: cgroup: RCU protect each cgroup_subsys_state release With the planned unified hierarchy, individual css's will be created and destroyed dynamically across the lifetime of a cgroup. To enable such usages, css destruction is being decoupled from cgroup destruction. Most of the destruction path has been decoupled but the actual free of css still depends on cgroup free path. When all css refs are drained, css_release() kicks off css_free_work_fn() which puts the cgroup. When the cgroup refcnt reaches zero, cgroup_diput() is invoked which in turn schedules RCU free of the cgroup. After a grace period, all css's are freed along with the cgroup itself. This patch moves the RCU grace period and css freeing from cgroup release path to css release path. css_release(), instead of kicking off css_free_work_fn() directly, schedules RCU callback css_free_rcu_fn() which in turn kicks off css_free_work_fn() after a RCU grace period. css_free_work_fn() is updated to free the css directly. The five-way punting - percpu ref kill confirmation, a work item, percpu ref release, RCU grace period, and again a work item - is quite hairy but the work items are there only to provide process context and the actual sequence is kill confirm -> release -> RCU free, which isn't simple but not too crazy. This removes cgroup_css() usage after offline_css() allowing clearing cgroup->subsys[] from offline_css(), which makes it consistent with online_css() and brings it closer to proper lifetime management for individual css's. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 3 ++- kernel/cgroup.c | 53 +++++++++++++++++++++++++++++++++++--------------- 2 files changed, 39 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 71e77e7cdb6f..c24bd0b9f93a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -82,7 +82,8 @@ struct cgroup_subsys_state { /* ID for this css, if possible */ struct css_id __rcu *id; - /* percpu_ref killing and putting dentry on the last css_put() */ + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; struct work_struct destroy_work; }; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3137e38995b0..66d01078eebe 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -869,18 +869,8 @@ static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry) static void cgroup_free_fn(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work); - struct cgroup_subsys *ss; mutex_lock(&cgroup_mutex); - /* - * Release the subsystem state objects. - */ - for_each_root_subsys(cgrp->root, ss) { - struct cgroup_subsys_state *css = cgroup_css(cgrp, ss->subsys_id); - - ss->css_free(css); - } - cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); @@ -4281,32 +4271,62 @@ err: return ret; } +/* + * css destruction is four-stage process. + * + * 1. Destruction starts. Killing of the percpu_ref is initiated. + * Implemented in kill_css(). + * + * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs + * and thus css_tryget() is guaranteed to fail, the css can be offlined + * by invoking offline_css(). After offlining, the base ref is put. + * Implemented in css_killed_work_fn(). + * + * 3. When the percpu_ref reaches zero, the only possible remaining + * accessors are inside RCU read sections. css_release() schedules the + * RCU callback. + * + * 4. After the grace period, the css can be freed. Implemented in + * css_free_work_fn(). + * + * It is actually hairier because both step 2 and 4 require process context + * and thus involve punting to css->destroy_work adding two additional + * steps to the already complex sequence. + */ static void css_free_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); + struct cgroup *cgrp = css->cgroup; if (css->parent) css_put(css->parent); - cgroup_dput(css->cgroup); + css->ss->css_free(css); + cgroup_dput(cgrp); } -static void css_release(struct percpu_ref *ref) +static void css_free_rcu_fn(struct rcu_head *rcu_head) { struct cgroup_subsys_state *css = - container_of(ref, struct cgroup_subsys_state, refcnt); + container_of(rcu_head, struct cgroup_subsys_state, rcu_head); /* * css holds an extra ref to @cgrp->dentry which is put on the last - * css_put(). dput() requires process context, which css_put() may - * be called without. @css->destroy_work will be used to invoke - * dput() asynchronously from css_put(). + * css_put(). dput() requires process context which we don't have. */ INIT_WORK(&css->destroy_work, css_free_work_fn); schedule_work(&css->destroy_work); } +static void css_release(struct percpu_ref *ref) +{ + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + + call_rcu(&css->rcu_head, css_free_rcu_fn); +} + static void init_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { @@ -4356,6 +4376,7 @@ static void offline_css(struct cgroup_subsys_state *css) css->flags &= ~CSS_ONLINE; css->cgroup->nr_css--; + RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css); } /* -- cgit v1.2.3-71-gd317 From 179ef71cbc085252e3fe6b8159263a7ed1d88ea4 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Tue, 13 Aug 2013 16:00:49 -0700 Subject: mm: save soft-dirty bits on swapped pages Andy Lutomirski reported that if a page with _PAGE_SOFT_DIRTY bit set get swapped out, the bit is getting lost and no longer available when pte read back. To resolve this we introduce _PTE_SWP_SOFT_DIRTY bit which is saved in pte entry for the page being swapped out. When such page is to be read back from a swap cache we check for bit presence and if it's there we clear it and restore the former _PAGE_SOFT_DIRTY bit back. One of the problem was to find a place in pte entry where we can save the _PTE_SWP_SOFT_DIRTY bit while page is in swap. The _PAGE_PSE was chosen for that, it doesn't intersect with swap entry format stored in pte. Reported-by: Andy Lutomirski Signed-off-by: Cyrill Gorcunov Acked-by: Pavel Emelyanov Cc: Matt Mackall Cc: Xiao Guangrong Cc: Marcelo Tosatti Cc: KOSAKI Motohiro Cc: Stephen Rothwell Cc: Peter Zijlstra Cc: "Aneesh Kumar K.V" Reviewed-by: Minchan Kim Reviewed-by: Wanpeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 15 +++++++++++++++ arch/x86/include/asm/pgtable_types.h | 13 +++++++++++++ fs/proc/task_mmu.c | 21 +++++++++++++++------ include/asm-generic/pgtable.h | 15 +++++++++++++++ include/linux/swapops.h | 2 ++ mm/memory.c | 2 ++ mm/rmap.c | 6 +++++- mm/swapfile.c | 19 +++++++++++++++++-- 8 files changed, 84 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 7dc305a46058..bd0518a7f197 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -314,6 +314,21 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); +} + +static inline int pte_swp_soft_dirty(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); +} + /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index c98ac63aae48..5e8442f178f9 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -67,6 +67,19 @@ #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0)) #endif +/* + * Tracking soft dirty bit when a page goes to a swap is tricky. + * We need a bit which can be stored in pte _and_ not conflict + * with swap entry format. On x86 bits 6 and 7 are *not* involved + * into swap entry computation, but bit 6 is used for nonlinear + * file mapping, so we borrow bit 7 for soft dirty tracking. + */ +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE +#else +#define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0)) +#endif + #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) #else diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index dbf61f6174f0..e2d9bdce5e7e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -730,8 +730,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, * of how soft-dirty works. */ pte_t ptent = *pte; - ptent = pte_wrprotect(ptent); - ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + + if (pte_present(ptent)) { + ptent = pte_wrprotect(ptent); + ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + } else if (is_swap_pte(ptent)) { + ptent = pte_swp_clear_soft_dirty(ptent); + } + set_pte_at(vma->vm_mm, addr, pte, ptent); #endif } @@ -752,14 +758,15 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = *pte; - if (!pte_present(ptent)) - continue; if (cp->type == CLEAR_REFS_SOFT_DIRTY) { clear_soft_dirty(vma, addr, pte); continue; } + if (!pte_present(ptent)) + continue; + page = vm_normal_page(vma, addr, ptent); if (!page) continue; @@ -930,8 +937,10 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, flags = PM_PRESENT; page = vm_normal_page(vma, addr, pte); } else if (is_swap_pte(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - + swp_entry_t entry; + if (pte_swp_soft_dirty(pte)) + flags2 |= __PM_SOFT_DIRTY; + entry = pte_to_swp_entry(pte); frame = swp_type(entry) | (swp_offset(entry) << MAX_SWAPFILES_SHIFT); flags = PM_SWAP; diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 2f47ade1b567..2a7e0d10ad9a 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -417,6 +417,21 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd; } + +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_soft_dirty(pte_t pte) +{ + return 0; +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return pte; +} #endif #ifndef __HAVE_PFNMAP_TRACKING diff --git a/include/linux/swapops.h b/include/linux/swapops.h index c5fd30d2a415..8d4fa82bfb91 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -67,6 +67,8 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) swp_entry_t arch_entry; BUG_ON(pte_file(pte)); + if (pte_swp_soft_dirty(pte)) + pte = pte_swp_clear_soft_dirty(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } diff --git a/mm/memory.c b/mm/memory.c index 1ce2e2a734fc..e98ecad2b9c8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3115,6 +3115,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, exclusive = 1; } flush_icache_page(vma, page); + if (pte_swp_soft_dirty(orig_pte)) + pte = pte_mksoft_dirty(pte); set_pte_at(mm, address, page_table, pte); if (page == swapcache) do_page_add_anon_rmap(page, vma, address, exclusive); diff --git a/mm/rmap.c b/mm/rmap.c index cd356df4f71a..83325b80142b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1236,6 +1236,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_entry_to_pte(make_hwpoison_entry(page))); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; + pte_t swp_pte; if (PageSwapCache(page)) { /* @@ -1264,7 +1265,10 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION); entry = make_migration_entry(page, pte_write(pteval)); } - set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(mm, address, pte, swp_pte); BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (TTU_ACTION(flags) == TTU_MIGRATION)) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 36af6eeaa67e..6cf2e60983b7 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -866,6 +866,21 @@ unsigned int count_swap_pages(int type, int free) } #endif /* CONFIG_HIBERNATION */ +static inline int maybe_same_pte(pte_t pte, pte_t swp_pte) +{ +#ifdef CONFIG_MEM_SOFT_DIRTY + /* + * When pte keeps soft dirty bit the pte generated + * from swap entry does not has it, still it's same + * pte from logical point of view. + */ + pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte); + return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty); +#else + return pte_same(pte, swp_pte); +#endif +} + /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to @@ -892,7 +907,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { + if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) { mem_cgroup_cancel_charge_swapin(memcg); ret = 0; goto out; @@ -947,7 +962,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * swapoff spends a _lot_ of time in this loop! * Test inline before going to call unuse_pte. */ - if (unlikely(pte_same(*pte, swp_pte))) { + if (unlikely(maybe_same_pte(*pte, swp_pte))) { pte_unmap(pte); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret) -- cgit v1.2.3-71-gd317 From dfa9771a7c4784bafd0673bc7abcee3813088b77 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Tue, 13 Aug 2013 16:00:53 -0700 Subject: microblaze: fix clone syscall Fix inadvertent breakage in the clone syscall ABI for Microblaze that was introduced in commit f3268edbe6fe ("microblaze: switch to generic fork/vfork/clone"). The Microblaze syscall ABI for clone takes the parent tid address in the 4th argument; the third argument slot is used for the stack size. The incorrectly-used CLONE_BACKWARDS type assigned parent tid to the 3rd slot. This commit restores the original ABI so that existing userspace libc code will work correctly. All kernel versions from v3.8-rc1 were affected. Signed-off-by: Michal Simek Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/Kconfig | 6 ++++++ arch/microblaze/Kconfig | 2 +- include/linux/syscalls.h | 5 +++++ kernel/fork.c | 6 ++++++ 4 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 8d2ae24b9f4a..1feb169274fe 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -407,6 +407,12 @@ config CLONE_BACKWARDS2 help Architecture has the first two arguments of clone(2) swapped. +config CLONE_BACKWARDS3 + bool + help + Architecture has tls passed as the 3rd argument of clone(2), + not the 5th one. + config ODD_RT_SIGACTION bool help diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index d22a4ecffff4..4fab52294d98 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -28,7 +28,7 @@ config MICROBLAZE select GENERIC_CLOCKEVENTS select GENERIC_IDLE_POLL_SETUP select MODULES_USE_ELF_RELA - select CLONE_BACKWARDS + select CLONE_BACKWARDS3 config SWAP def_bool n diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4147d700a293..84662ecc7b51 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -802,9 +802,14 @@ asmlinkage long sys_vfork(void); asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int, int __user *); #else +#ifdef CONFIG_CLONE_BACKWARDS3 +asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *, + int __user *, int); +#else asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int __user *, int); #endif +#endif asmlinkage long sys_execve(const char __user *filename, const char __user *const __user *argv, diff --git a/kernel/fork.c b/kernel/fork.c index 403d2bb8a968..e23bb19e2a3e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1679,6 +1679,12 @@ SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val) +#elif defined(CONFIG_CLONE_BACKWARDS3) +SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, + int, stack_size, + int __user *, parent_tidptr, + int __user *, child_tidptr, + int, tls_val) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, -- cgit v1.2.3-71-gd317 From df54d6fa54275ce59660453e29d1228c2b45a826 Mon Sep 17 00:00:00 2001 From: Radu Caragea Date: Tue, 13 Aug 2013 16:00:59 -0700 Subject: x86 get_unmapped_area(): use proper mmap base for bottom-up direction When the stack is set to unlimited, the bottomup direction is used for mmap-ings but the mmap_base is not used and thus effectively renders ASLR for mmapings along with PIE useless. Cc: Michel Lespinasse Cc: Oleg Nesterov Reviewed-by: Rik van Riel Acked-by: Ingo Molnar Cc: Adrian Sendroiu Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/sys_x86_64.c | 2 +- arch/x86/mm/mmap.c | 2 +- include/linux/sched.h | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index dbded5aedb81..48f8375e4c6b 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = TASK_UNMAPPED_BASE; + *begin = mmap_legacy_base(); *end = TASK_SIZE; } } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 62c29a5bfe26..f63778cb2363 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -98,7 +98,7 @@ static unsigned long mmap_base(void) * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 * does, but not when emulating X86_32 */ -static unsigned long mmap_legacy_base(void) +unsigned long mmap_legacy_base(void) { if (mmap_is_ia32()) return TASK_UNMAPPED_BASE; diff --git a/include/linux/sched.h b/include/linux/sched.h index d722490da030..923dd6ea4a0e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -314,6 +314,7 @@ struct nsproxy; struct user_namespace; #ifdef CONFIG_MMU +extern unsigned long mmap_legacy_base(void); extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, -- cgit v1.2.3-71-gd317 From 65f382fd0c8fa483713c0971de9f1dfb4cf1ad9c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 11 Jul 2013 19:12:32 +0200 Subject: context_tracking: Ground setup for static key use Prepare for using a static key in the context tracking subsystem. This will help optimizing the off case on its many users: * user_enter, user_exit, exception_enter, exception_exit, guest_enter, guest_exit, vtime_*() Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 10 ++++++++++ init/main.c | 2 ++ kernel/context_tracking.c | 23 +++++++++++++++++------ 3 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 1ae37c708c63..c138c24bad1a 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -4,6 +4,7 @@ #include #include #include +#include #include struct context_tracking { @@ -22,6 +23,7 @@ struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING +extern struct static_key context_tracking_enabled; DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_in_user(void) @@ -67,6 +69,14 @@ static inline void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ + +#ifdef CONFIG_CONTEXT_TRACKING_FORCE +extern void context_tracking_init(void); +#else +static inline void context_tracking_init(void) { } +#endif /* CONFIG_CONTEXT_TRACKING_FORCE */ + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void guest_enter(void); extern void guest_exit(void); diff --git a/init/main.c b/init/main.c index d03d2ec2eacf..af310afbef28 100644 --- a/init/main.c +++ b/init/main.c @@ -75,6 +75,7 @@ #include #include #include +#include #include #include @@ -545,6 +546,7 @@ asmlinkage void __init start_kernel(void) idr_init_cache(); rcu_init(); tick_nohz_init(); + context_tracking_init(); radix_tree_init(); /* init some links before init_ISA_irqs() */ early_irq_init(); diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 72bcb2570d3e..839d377d0da5 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -20,15 +20,16 @@ #include #include -DEFINE_PER_CPU(struct context_tracking, context_tracking) = { -#ifdef CONFIG_CONTEXT_TRACKING_FORCE - .active = true, -#endif -}; +struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE; + +DEFINE_PER_CPU(struct context_tracking, context_tracking); void context_tracking_cpu_set(int cpu) { - per_cpu(context_tracking.active, cpu) = true; + if (!per_cpu(context_tracking.active, cpu)) { + per_cpu(context_tracking.active, cpu) = true; + static_key_slow_inc(&context_tracking_enabled); + } } /** @@ -202,3 +203,13 @@ void context_tracking_task_switch(struct task_struct *prev, clear_tsk_thread_flag(prev, TIF_NOHZ); set_tsk_thread_flag(next, TIF_NOHZ); } + +#ifdef CONFIG_CONTEXT_TRACKING_FORCE +void __init context_tracking_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + context_tracking_cpu_set(cpu); +} +#endif -- cgit v1.2.3-71-gd317 From ad65782fba507d91a0a98f519b59e79cac1b474c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 02:44:35 +0200 Subject: context_tracking: Optimize main APIs off case with static key Optimize user and exception entry/exit APIs with static keys. This minimize the overhead for those who enable CONFIG_NO_HZ_FULL without always using it. Having no range passed to nohz_full= should result in the probes to be nopped (at least we hope so...). If this proves not be enough in the long term, we'll need to bring an exception slow path by re-routing the exception handlers. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 27 ++++++++++++++++++++++----- kernel/context_tracking.c | 12 ++++++------ 2 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index c138c24bad1a..38ab60b3f3a6 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -38,23 +38,40 @@ static inline bool context_tracking_active(void) extern void context_tracking_cpu_set(int cpu); -extern void user_enter(void); -extern void user_exit(void); +extern void context_tracking_user_enter(void); +extern void context_tracking_user_exit(void); + +static inline void user_enter(void) +{ + if (static_key_false(&context_tracking_enabled)) + context_tracking_user_enter(); + +} +static inline void user_exit(void) +{ + if (static_key_false(&context_tracking_enabled)) + context_tracking_user_exit(); +} static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; + if (!static_key_false(&context_tracking_enabled)) + return 0; + prev_ctx = this_cpu_read(context_tracking.state); - user_exit(); + context_tracking_user_exit(); return prev_ctx; } static inline void exception_exit(enum ctx_state prev_ctx) { - if (prev_ctx == IN_USER) - user_enter(); + if (static_key_false(&context_tracking_enabled)) { + if (prev_ctx == IN_USER) + context_tracking_user_enter(); + } } extern void context_tracking_task_switch(struct task_struct *prev, diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 839d377d0da5..6e89e094c80e 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -33,15 +33,15 @@ void context_tracking_cpu_set(int cpu) } /** - * user_enter - Inform the context tracking that the CPU is going to - * enter userspace mode. + * context_tracking_user_enter - Inform the context tracking that the CPU is going to + * enter userspace mode. * * This function must be called right before we switch from the kernel * to userspace, when it's guaranteed the remaining kernel instructions * to execute won't use any RCU read side critical section because this * function sets RCU in extended quiescent state. */ -void user_enter(void) +void context_tracking_user_enter(void) { unsigned long flags; @@ -131,8 +131,8 @@ EXPORT_SYMBOL_GPL(preempt_schedule_context); #endif /* CONFIG_PREEMPT */ /** - * user_exit - Inform the context tracking that the CPU is - * exiting userspace mode and entering the kernel. + * context_tracking_user_exit - Inform the context tracking that the CPU is + * exiting userspace mode and entering the kernel. * * This function must be called after we entered the kernel from userspace * before any use of RCU read side critical section. This potentially include @@ -141,7 +141,7 @@ EXPORT_SYMBOL_GPL(preempt_schedule_context); * This call supports re-entrancy. This way it can be called from any exception * handler without needing to know if we came from userspace or not. */ -void user_exit(void) +void context_tracking_user_exit(void) { unsigned long flags; -- cgit v1.2.3-71-gd317 From 48d6a816a8bf36e2a197c322697323003bdc1cfe Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 02:44:35 +0200 Subject: context_tracking: Optimize guest APIs off case with static key Optimize guest entry/exit APIs with static keys. This minimize the overhead for those who enable CONFIG_NO_HZ_FULL without always using it. Having no range passed to nohz_full= should result in the probes overhead to be minimized. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 19 +++++++++++++++++-- kernel/context_tracking.c | 23 ++--------------------- kernel/sched/cputime.c | 2 ++ 3 files changed, 21 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 38ab60b3f3a6..8854eadb2142 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -95,8 +95,23 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void guest_enter(void); -extern void guest_exit(void); +static inline void guest_enter(void) +{ + if (static_key_false(&context_tracking_enabled) && + vtime_accounting_enabled()) + vtime_guest_enter(current); + else + current->flags |= PF_VCPU; +} + +static inline void guest_exit(void) +{ + if (static_key_false(&context_tracking_enabled) && + vtime_accounting_enabled()) + vtime_guest_exit(current); + else + current->flags &= ~PF_VCPU; +} #else static inline void guest_enter(void) { diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 6e89e094c80e..b6a186c4b886 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -21,8 +21,10 @@ #include struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(context_tracking_enabled); DEFINE_PER_CPU(struct context_tracking, context_tracking); +EXPORT_SYMBOL_GPL(context_tracking); void context_tracking_cpu_set(int cpu) { @@ -163,27 +165,6 @@ void context_tracking_user_exit(void) local_irq_restore(flags); } -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -void guest_enter(void) -{ - if (vtime_accounting_enabled()) - vtime_guest_enter(current); - else - current->flags |= PF_VCPU; -} -EXPORT_SYMBOL_GPL(guest_enter); - -void guest_exit(void) -{ - if (vtime_accounting_enabled()) - vtime_guest_exit(current); - else - current->flags &= ~PF_VCPU; -} -EXPORT_SYMBOL_GPL(guest_exit); -#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ - - /** * context_tracking_task_switch - context switch the syscall callbacks * @prev: the task that is being switched out diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 223a35efa0a6..bb6b29a3067c 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -724,6 +724,7 @@ void vtime_guest_enter(struct task_struct *tsk) current->flags |= PF_VCPU; write_sequnlock(&tsk->vtime_seqlock); } +EXPORT_SYMBOL_GPL(vtime_guest_enter); void vtime_guest_exit(struct task_struct *tsk) { @@ -732,6 +733,7 @@ void vtime_guest_exit(struct task_struct *tsk) current->flags &= ~PF_VCPU; write_sequnlock(&tsk->vtime_seqlock); } +EXPORT_SYMBOL_GPL(vtime_guest_exit); void vtime_account_idle(struct task_struct *tsk) { -- cgit v1.2.3-71-gd317 From 73d424f9af7b571276e6284617cb59726d47bf12 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 11 Jul 2013 19:42:13 +0200 Subject: context_tracking: Optimize context switch off case with static keys No need for syscall slowpath if no CPU is full dynticks, rather nop this in this case. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 11 +++++++++-- kernel/context_tracking.c | 6 +++--- 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 8854eadb2142..e070ea5dadac 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -40,6 +40,8 @@ extern void context_tracking_cpu_set(int cpu); extern void context_tracking_user_enter(void); extern void context_tracking_user_exit(void); +extern void __context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next); static inline void user_enter(void) { @@ -74,8 +76,12 @@ static inline void exception_exit(enum ctx_state prev_ctx) } } -extern void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next); +static inline void context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) +{ + if (static_key_false(&context_tracking_enabled)) + __context_tracking_task_switch(prev, next); +} #else static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } @@ -112,6 +118,7 @@ static inline void guest_exit(void) else current->flags &= ~PF_VCPU; } + #else static inline void guest_enter(void) { diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index b6a186c4b886..c17822673c39 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -166,7 +166,7 @@ void context_tracking_user_exit(void) } /** - * context_tracking_task_switch - context switch the syscall callbacks + * __context_tracking_task_switch - context switch the syscall callbacks * @prev: the task that is being switched out * @next: the task that is being switched in * @@ -178,8 +178,8 @@ void context_tracking_user_exit(void) * migrate to some CPU that doesn't do the context tracking. As such the TIF * flag may not be desired there. */ -void context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) +void __context_tracking_task_switch(struct task_struct *prev, + struct task_struct *next) { clear_tsk_thread_flag(prev, TIF_NOHZ); set_tsk_thread_flag(next, TIF_NOHZ); -- cgit v1.2.3-71-gd317 From e7358b3bc0d7fcec0e7a724477f06db2b0c68e21 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 02:15:49 +0200 Subject: context_tracking: Split low level state headers We plan to use the context tracking static key on inline vtime APIs. For this we need to include the context tracking headers from those of vtime. However vtime headers need to stay low level because they are included in hardirq.h that mostly contains standalone definitions. But context_tracking.h includes sched.h for a few task_struct references, therefore it wouldn't be sensible to include it from vtime.h To solve this, lets split the context tracking headers and move out the pure state definitions that only require a few low level headers. We can safely include that small part in vtime.h later. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 31 +-------------------------- include/linux/context_tracking_state.h | 39 ++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 30 deletions(-) create mode 100644 include/linux/context_tracking_state.h (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index e070ea5dadac..82ec4870e064 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -2,40 +2,12 @@ #define _LINUX_CONTEXT_TRACKING_H #include -#include #include -#include +#include #include -struct context_tracking { - /* - * When active is false, probes are unset in order - * to minimize overhead: TIF flags are cleared - * and calls to user_enter/exit are ignored. This - * may be further optimized using static keys. - */ - bool active; - enum ctx_state { - IN_KERNEL = 0, - IN_USER, - } state; -}; - #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key context_tracking_enabled; -DECLARE_PER_CPU(struct context_tracking, context_tracking); - -static inline bool context_tracking_in_user(void) -{ - return __this_cpu_read(context_tracking.state) == IN_USER; -} - -static inline bool context_tracking_active(void) -{ - return __this_cpu_read(context_tracking.active); -} - extern void context_tracking_cpu_set(int cpu); extern void context_tracking_user_enter(void); @@ -83,7 +55,6 @@ static inline void context_tracking_task_switch(struct task_struct *prev, __context_tracking_task_switch(prev, next); } #else -static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } static inline enum ctx_state exception_enter(void) { return 0; } diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h new file mode 100644 index 000000000000..0f1979d0674f --- /dev/null +++ b/include/linux/context_tracking_state.h @@ -0,0 +1,39 @@ +#ifndef _LINUX_CONTEXT_TRACKING_STATE_H +#define _LINUX_CONTEXT_TRACKING_STATE_H + +#include +#include + +struct context_tracking { + /* + * When active is false, probes are unset in order + * to minimize overhead: TIF flags are cleared + * and calls to user_enter/exit are ignored. This + * may be further optimized using static keys. + */ + bool active; + enum ctx_state { + IN_KERNEL = 0, + IN_USER, + } state; +}; + +#ifdef CONFIG_CONTEXT_TRACKING +extern struct static_key context_tracking_enabled; +DECLARE_PER_CPU(struct context_tracking, context_tracking); + +static inline bool context_tracking_in_user(void) +{ + return __this_cpu_read(context_tracking.state) == IN_USER; +} + +static inline bool context_tracking_active(void) +{ + return __this_cpu_read(context_tracking.active); +} +#else +static inline bool context_tracking_in_user(void) { return false; } +static inline bool context_tracking_active(void) { return false; } +#endif /* CONFIG_CONTEXT_TRACKING */ + +#endif -- cgit v1.2.3-71-gd317 From 2d4b84739f0acf61f37267b4e80c5bd85fb90a7e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 29 Jul 2013 20:29:43 +0200 Subject: hardirq: Split preempt count mask definitions In order to use static keys with vtime APIs, we'll need to add static keys headers to vtime.h hardirq.h then becomes a problem because it needs vtime.h for irqtime accounting in irq_enter/irq_exit, but it's often included just to get the irq mask definitions in the task preempt_count field and the APIs that come along: in_interrupt(), in_hardirq(), etc... Some very low level arch headers sometimes need these masks and APIs such as arch/m68k/include/asm/irqflags.h for example. But they don't want to include hardirq.h if vtime.h, jump_label.h and even workqueue.h come along. Including such bloated high level header from arch headers can quickly result in circular headers dependency that crash the build. So let's split hardirq.h in two parts: * preempt_mask.h that gathers all the preempt_count definitions and the APIs associated. This one is considered low level and can be safely included anywhere. * hardirq.h that includes the previous one. It defines the irq entry/exit APIs. To avoid future circular headers dependencies, the preempt_mask.h inclusion can replace hardirq.h on files that don't implement irq low level handlers but just need the atomic/context check APIs. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/hardirq.h | 117 +---------------------------------------- include/linux/preempt_mask.h | 122 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 123 insertions(+), 116 deletions(-) create mode 100644 include/linux/preempt_mask.h (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 05bcc0903766..ccfe17c5c8da 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -1,126 +1,11 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H -#include +#include #include #include #include -#include -/* - * We put the hardirq and softirq counter into the preemption - * counter. The bitmask has the following meaning: - * - * - bits 0-7 are the preemption count (max preemption depth: 256) - * - bits 8-15 are the softirq count (max # of softirqs: 256) - * - * The hardirq count can in theory reach the same as NR_IRQS. - * In reality, the number of nested IRQS is limited to the stack - * size as well. For archs with over 1000 IRQS it is not practical - * to expect that they will all nest. We give a max of 10 bits for - * hardirq nesting. An arch may choose to give less than 10 bits. - * m68k expects it to be 8. - * - * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) - * - bit 26 is the NMI_MASK - * - bit 27 is the PREEMPT_ACTIVE flag - * - * PREEMPT_MASK: 0x000000ff - * SOFTIRQ_MASK: 0x0000ff00 - * HARDIRQ_MASK: 0x03ff0000 - * NMI_MASK: 0x04000000 - */ -#define PREEMPT_BITS 8 -#define SOFTIRQ_BITS 8 -#define NMI_BITS 1 - -#define MAX_HARDIRQ_BITS 10 - -#ifndef HARDIRQ_BITS -# define HARDIRQ_BITS MAX_HARDIRQ_BITS -#endif - -#if HARDIRQ_BITS > MAX_HARDIRQ_BITS -#error HARDIRQ_BITS too high! -#endif - -#define PREEMPT_SHIFT 0 -#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) -#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) - -#define __IRQ_MASK(x) ((1UL << (x))-1) - -#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) -#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) -#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) -#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) - -#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) -#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) -#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) -#define NMI_OFFSET (1UL << NMI_SHIFT) - -#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) - -#ifndef PREEMPT_ACTIVE -#define PREEMPT_ACTIVE_BITS 1 -#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) -#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) -#endif - -#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) -#error PREEMPT_ACTIVE is too low! -#endif - -#define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define softirq_count() (preempt_count() & SOFTIRQ_MASK) -#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ - | NMI_MASK)) - -/* - * Are we doing bottom half or hardware interrupt processing? - * Are we in a softirq context? Interrupt context? - * in_softirq - Are we currently processing softirq or have bh disabled? - * in_serving_softirq - Are we currently processing softirq? - */ -#define in_irq() (hardirq_count()) -#define in_softirq() (softirq_count()) -#define in_interrupt() (irq_count()) -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) - -/* - * Are we in NMI context? - */ -#define in_nmi() (preempt_count() & NMI_MASK) - -#if defined(CONFIG_PREEMPT_COUNT) -# define PREEMPT_CHECK_OFFSET 1 -#else -# define PREEMPT_CHECK_OFFSET 0 -#endif - -/* - * Are we running in atomic context? WARNING: this macro cannot - * always detect atomic context; in particular, it cannot know about - * held spinlocks in non-preemptible kernels. Thus it should not be - * used in the general case to determine whether sleeping is possible. - * Do not use in_atomic() in driver code. - */ -#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) - -/* - * Check whether we were atomic before we did preempt_disable(): - * (used by the scheduler, *after* releasing the kernel lock) - */ -#define in_atomic_preempt_off() \ - ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) - -#ifdef CONFIG_PREEMPT_COUNT -# define preemptible() (preempt_count() == 0 && !irqs_disabled()) -#else -# define preemptible() 0 -#endif #if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS) extern void synchronize_irq(unsigned int irq); diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h new file mode 100644 index 000000000000..931bc616219f --- /dev/null +++ b/include/linux/preempt_mask.h @@ -0,0 +1,122 @@ +#ifndef LINUX_PREEMPT_MASK_H +#define LINUX_PREEMPT_MASK_H + +#include +#include + +/* + * We put the hardirq and softirq counter into the preemption + * counter. The bitmask has the following meaning: + * + * - bits 0-7 are the preemption count (max preemption depth: 256) + * - bits 8-15 are the softirq count (max # of softirqs: 256) + * + * The hardirq count can in theory reach the same as NR_IRQS. + * In reality, the number of nested IRQS is limited to the stack + * size as well. For archs with over 1000 IRQS it is not practical + * to expect that they will all nest. We give a max of 10 bits for + * hardirq nesting. An arch may choose to give less than 10 bits. + * m68k expects it to be 8. + * + * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) + * - bit 26 is the NMI_MASK + * - bit 27 is the PREEMPT_ACTIVE flag + * + * PREEMPT_MASK: 0x000000ff + * SOFTIRQ_MASK: 0x0000ff00 + * HARDIRQ_MASK: 0x03ff0000 + * NMI_MASK: 0x04000000 + */ +#define PREEMPT_BITS 8 +#define SOFTIRQ_BITS 8 +#define NMI_BITS 1 + +#define MAX_HARDIRQ_BITS 10 + +#ifndef HARDIRQ_BITS +# define HARDIRQ_BITS MAX_HARDIRQ_BITS +#endif + +#if HARDIRQ_BITS > MAX_HARDIRQ_BITS +#error HARDIRQ_BITS too high! +#endif + +#define PREEMPT_SHIFT 0 +#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) +#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) + +#define __IRQ_MASK(x) ((1UL << (x))-1) + +#define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) +#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) +#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) + +#define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) +#define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) +#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) +#define NMI_OFFSET (1UL << NMI_SHIFT) + +#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) + +#ifndef PREEMPT_ACTIVE +#define PREEMPT_ACTIVE_BITS 1 +#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) +#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) +#endif + +#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS)) +#error PREEMPT_ACTIVE is too low! +#endif + +#define hardirq_count() (preempt_count() & HARDIRQ_MASK) +#define softirq_count() (preempt_count() & SOFTIRQ_MASK) +#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) + +/* + * Are we doing bottom half or hardware interrupt processing? + * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? + */ +#define in_irq() (hardirq_count()) +#define in_softirq() (softirq_count()) +#define in_interrupt() (irq_count()) +#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + +/* + * Are we in NMI context? + */ +#define in_nmi() (preempt_count() & NMI_MASK) + +#if defined(CONFIG_PREEMPT_COUNT) +# define PREEMPT_CHECK_OFFSET 1 +#else +# define PREEMPT_CHECK_OFFSET 0 +#endif + +/* + * Are we running in atomic context? WARNING: this macro cannot + * always detect atomic context; in particular, it cannot know about + * held spinlocks in non-preemptible kernels. Thus it should not be + * used in the general case to determine whether sleeping is possible. + * Do not use in_atomic() in driver code. + */ +#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) + +/* + * Check whether we were atomic before we did preempt_disable(): + * (used by the scheduler, *after* releasing the kernel lock) + */ +#define in_atomic_preempt_off() \ + ((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET) + +#ifdef CONFIG_PREEMPT_COUNT +# define preemptible() (preempt_count() == 0 && !irqs_disabled()) +#else +# define preemptible() 0 +#endif + +#endif /* LINUX_PREEMPT_MASK_H */ -- cgit v1.2.3-71-gd317 From a5725ac23bf4ff79656ac2c317c323e261327fb3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 16 Jul 2013 18:50:52 +0200 Subject: vtime: Describe overriden functions in dedicated arch headers If the arch overrides some generic vtime APIs, let it describe these on a dedicated and standalone header. This way it becomes convenient to include it in vtime generic headers without irrelevant stuff in such a low level header. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman Cc: Martin Schwidefsky Cc: Heiko Carstens --- arch/ia64/include/asm/Kbuild | 1 + arch/powerpc/include/asm/Kbuild | 1 + arch/s390/include/asm/cputime.h | 3 --- arch/s390/include/asm/vtime.h | 7 +++++++ arch/s390/kernel/vtime.c | 1 + include/asm-generic/vtime.h | 0 include/linux/vtime.h | 4 ++++ 7 files changed, 14 insertions(+), 3 deletions(-) create mode 100644 arch/s390/include/asm/vtime.h create mode 100644 include/asm-generic/vtime.h (limited to 'include/linux') diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 05b03ecd7933..a3456f34f672 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -3,3 +3,4 @@ generic-y += clkdev.h generic-y += exec.h generic-y += kvm_para.h generic-y += trace_clock.h +generic-y += vtime.h \ No newline at end of file diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 650757c300db..704e6f10ae80 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -2,3 +2,4 @@ generic-y += clkdev.h generic-y += rwsem.h generic-y += trace_clock.h +generic-y += vtime.h \ No newline at end of file diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index d2ff41370c0c..f65bd3634519 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -13,9 +13,6 @@ #include -#define __ARCH_HAS_VTIME_ACCOUNT -#define __ARCH_HAS_VTIME_TASK_SWITCH - /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ typedef unsigned long long __nocast cputime_t; diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h new file mode 100644 index 000000000000..af9896c53eb3 --- /dev/null +++ b/arch/s390/include/asm/vtime.h @@ -0,0 +1,7 @@ +#ifndef _S390_VTIME_H +#define _S390_VTIME_H + +#define __ARCH_HAS_VTIME_ACCOUNT +#define __ARCH_HAS_VTIME_TASK_SWITCH + +#endif /* _S390_VTIME_H */ diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 9b9c1b78ec67..abcfab55f99b 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include "entry.h" diff --git a/include/asm-generic/vtime.h b/include/asm-generic/vtime.h new file mode 100644 index 000000000000..e69de29bb2d1 diff --git a/include/linux/vtime.h b/include/linux/vtime.h index b1dd2db80076..2ad073915e8c 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -1,6 +1,10 @@ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +#include +#endif + struct task_struct; #ifdef CONFIG_VIRT_CPU_ACCOUNTING -- cgit v1.2.3-71-gd317 From b04934061330a4a449cfce703c97d887c3e11cd7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Jul 2013 03:10:15 +0200 Subject: vtime: Optimize full dynticks accounting off case with static keys If no CPU is in the full dynticks range, we can avoid the full dynticks cputime accounting through generic vtime along with its overhead and use the traditional tick based accounting instead. Let's do this and nope the off case with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/context_tracking.h | 6 ++-- include/linux/vtime.h | 70 ++++++++++++++++++++++++++++++++++------ kernel/sched/cputime.c | 22 +++---------- 3 files changed, 67 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 82ec4870e064..158158704c30 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -74,8 +74,7 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static inline void guest_enter(void) { - if (static_key_false(&context_tracking_enabled) && - vtime_accounting_enabled()) + if (vtime_accounting_enabled()) vtime_guest_enter(current); else current->flags |= PF_VCPU; @@ -83,8 +82,7 @@ static inline void guest_enter(void) static inline void guest_exit(void) { - if (static_key_false(&context_tracking_enabled) && - vtime_accounting_enabled()) + if (vtime_accounting_enabled()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 2ad073915e8c..f5b72b364bda 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -1,22 +1,68 @@ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H +#include #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include #endif + struct task_struct; +/* + * vtime_accounting_enabled() definitions/declarations + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +static inline bool vtime_accounting_enabled(void) { return true; } +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +static inline bool vtime_accounting_enabled(void) +{ + if (static_key_false(&context_tracking_enabled)) { + if (context_tracking_active()) + return true; + } + + return false; +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING +static inline bool vtime_accounting_enabled(void) { return false; } +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ + + +/* + * Common vtime APIs + */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING + +#ifdef __ARCH_HAS_VTIME_TASK_SWITCH extern void vtime_task_switch(struct task_struct *prev); +#else +extern void vtime_common_task_switch(struct task_struct *prev); +static inline void vtime_task_switch(struct task_struct *prev) +{ + if (vtime_accounting_enabled()) + vtime_common_task_switch(prev); +} +#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ + extern void vtime_account_system(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); extern void vtime_account_user(struct task_struct *tsk); -extern void vtime_account_irq_enter(struct task_struct *tsk); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -static inline bool vtime_accounting_enabled(void) { return true; } -#endif +#ifdef __ARCH_HAS_VTIME_ACCOUNT +extern void vtime_account_irq_enter(struct task_struct *tsk); +#else +extern void vtime_common_account_irq_enter(struct task_struct *tsk); +static inline void vtime_account_irq_enter(struct task_struct *tsk) +{ + if (vtime_accounting_enabled()) + vtime_common_account_irq_enter(tsk); +} +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ @@ -24,14 +70,20 @@ static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_system(struct task_struct *tsk) { } static inline void vtime_account_user(struct task_struct *tsk) { } static inline void vtime_account_irq_enter(struct task_struct *tsk) { } -static inline bool vtime_accounting_enabled(void) { return false; } -#endif +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); -extern void vtime_account_irq_exit(struct task_struct *tsk); -extern bool vtime_accounting_enabled(void); +extern void vtime_gen_account_irq_exit(struct task_struct *tsk); + +static inline void vtime_account_irq_exit(struct task_struct *tsk) +{ + if (vtime_accounting_enabled()) + vtime_gen_account_irq_exit(tsk); +} + extern void vtime_user_enter(struct task_struct *tsk); + static inline void vtime_user_exit(struct task_struct *tsk) { vtime_account_user(tsk); @@ -39,7 +91,7 @@ static inline void vtime_user_exit(struct task_struct *tsk) extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); -#else +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ static inline void vtime_account_irq_exit(struct task_struct *tsk) { /* On hard|softirq exit we always account to hard|softirq cputime */ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index b62d5c027c7e..0831b06aab97 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -378,11 +378,8 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_ #ifdef CONFIG_VIRT_CPU_ACCOUNTING #ifndef __ARCH_HAS_VTIME_TASK_SWITCH -void vtime_task_switch(struct task_struct *prev) +void vtime_common_task_switch(struct task_struct *prev) { - if (!vtime_accounting_enabled()) - return; - if (is_idle_task(prev)) vtime_account_idle(prev); else @@ -404,11 +401,8 @@ void vtime_task_switch(struct task_struct *prev) * vtime_account(). */ #ifndef __ARCH_HAS_VTIME_ACCOUNT -void vtime_account_irq_enter(struct task_struct *tsk) +void vtime_common_account_irq_enter(struct task_struct *tsk) { - if (!vtime_accounting_enabled()) - return; - if (!in_interrupt()) { /* * If we interrupted user, context_tracking_in_user() @@ -428,7 +422,7 @@ void vtime_account_irq_enter(struct task_struct *tsk) } vtime_account_system(tsk); } -EXPORT_SYMBOL_GPL(vtime_account_irq_enter); +EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ #endif /* CONFIG_VIRT_CPU_ACCOUNTING */ @@ -669,11 +663,8 @@ void vtime_account_system(struct task_struct *tsk) write_sequnlock(&tsk->vtime_seqlock); } -void vtime_account_irq_exit(struct task_struct *tsk) +void vtime_gen_account_irq_exit(struct task_struct *tsk) { - if (!vtime_accounting_enabled()) - return; - write_seqlock(&tsk->vtime_seqlock); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; @@ -732,11 +723,6 @@ void vtime_account_idle(struct task_struct *tsk) account_idle_time(delta_cpu); } -bool vtime_accounting_enabled(void) -{ - return context_tracking_active(); -} - void arch_vtime_task_switch(struct task_struct *prev) { write_seqlock(&prev->vtime_seqlock); -- cgit v1.2.3-71-gd317 From 460775df4680b4593d8449bc171008578625a850 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks state checks with static keys These APIs are frequenctly accessed and priority is given to optimize the full dynticks off-case in order to let distros enable this feature without suffering from significant performance regressions. Let's inline these APIs and optimize them with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/tick.h | 25 +++++++++++++++++++++++-- kernel/time/tick-sched.c | 14 ++------------ 2 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 9180f4b85e6d..c60b079e1b37 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -10,6 +10,8 @@ #include #include #include +#include +#include #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -158,15 +160,34 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } # endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL +extern bool tick_nohz_full_running; +extern cpumask_var_t tick_nohz_full_mask; + +static inline bool tick_nohz_full_enabled(void) +{ + if (!static_key_false(&context_tracking_enabled)) + return false; + + return tick_nohz_full_running; +} + +static inline bool tick_nohz_full_cpu(int cpu) +{ + if (!tick_nohz_full_enabled()) + return false; + + return cpumask_test_cpu(cpu, tick_nohz_full_mask); +} + extern void tick_nohz_init(void); -extern int tick_nohz_full_cpu(int cpu); extern void tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); extern void tick_nohz_task_switch(struct task_struct *tsk); #else static inline void tick_nohz_init(void) { } -static inline int tick_nohz_full_cpu(int cpu) { return 0; } +static inline bool tick_nohz_full_enabled(void) { return false; } +static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index b28dee43e644..0b7887389bd2 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -149,7 +149,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) } #ifdef CONFIG_NO_HZ_FULL -static cpumask_var_t tick_nohz_full_mask; +cpumask_var_t tick_nohz_full_mask; bool tick_nohz_full_running; static bool can_stop_full_tick(void) @@ -270,14 +270,6 @@ out: local_irq_restore(flags); } -int tick_nohz_full_cpu(int cpu) -{ - if (!tick_nohz_full_running) - return 0; - - return cpumask_test_cpu(cpu, tick_nohz_full_mask); -} - /* Parse the boot-time nohz CPU list from the kernel parameters. */ static int __init tick_nohz_full_setup(char *str) { @@ -359,8 +351,6 @@ void __init tick_nohz_init(void) cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask); pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); } -#else -#define tick_nohz_full_running (0) #endif /* @@ -738,7 +728,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (tick_nohz_full_running) { + if (tick_nohz_full_enabled()) { /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around -- cgit v1.2.3-71-gd317 From d13508f9440e46dccac6a2dd48d51a73b2207482 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks's sched hooks with static keys Scheduler IPIs and task context switches are serious fast path. Let's try to hide as much as we can the impact of full dynticks APIs' off case that are called on these sites through the use of static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- include/linux/tick.h | 20 ++++++++++++++++---- kernel/time/tick-sched.c | 8 ++++---- 2 files changed, 20 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index c60b079e1b37..a7ef1d6fceb6 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -180,20 +180,32 @@ static inline bool tick_nohz_full_cpu(int cpu) } extern void tick_nohz_init(void); -extern void tick_nohz_full_check(void); +extern void __tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); -extern void tick_nohz_task_switch(struct task_struct *tsk); +extern void __tick_nohz_task_switch(struct task_struct *tsk); #else static inline void tick_nohz_init(void) { } static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } -static inline void tick_nohz_full_check(void) { } +static inline void __tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } -static inline void tick_nohz_task_switch(struct task_struct *tsk) { } +static inline void __tick_nohz_task_switch(struct task_struct *tsk) { } #endif +static inline void tick_nohz_full_check(void) +{ + if (tick_nohz_full_enabled()) + __tick_nohz_full_check(); +} + +static inline void tick_nohz_task_switch(struct task_struct *tsk) +{ + if (tick_nohz_full_enabled()) + __tick_nohz_task_switch(tsk); +} + # ifdef CONFIG_CPU_IDLE_GOV_MENU extern void menu_hrtimer_cancel(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 0b7887389bd2..0ff6ae710161 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -198,7 +198,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now); * Re-evaluate the need for the tick on the current CPU * and restart it if necessary. */ -void tick_nohz_full_check(void) +void __tick_nohz_full_check(void) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); @@ -212,7 +212,7 @@ void tick_nohz_full_check(void) static void nohz_full_kick_work_func(struct irq_work *work) { - tick_nohz_full_check(); + __tick_nohz_full_check(); } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { @@ -231,7 +231,7 @@ void tick_nohz_full_kick(void) static void nohz_full_kick_ipi(void *info) { - tick_nohz_full_check(); + __tick_nohz_full_check(); } /* @@ -254,7 +254,7 @@ void tick_nohz_full_kick_all(void) * It might need the tick due to per task/process properties: * perf events, posix cpu timers, ... */ -void tick_nohz_task_switch(struct task_struct *tsk) +void __tick_nohz_task_switch(struct task_struct *tsk) { unsigned long flags; -- cgit v1.2.3-71-gd317 From 1542d9c35d8166c54e0616574954a0f48449f331 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:03 +0300 Subject: usb: chipidea: move vbus regulator operation to core The vbus regulator is a common element for USB vbus operation, So, move it from glue layer to core. Tested-by: Marek Vasut Signed-off-by: Michael Grzeschik Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/ci_hdrc_imx.c | 26 ++------------------------ drivers/usb/chipidea/core.c | 23 +++++++++++++++++++++++ include/linux/usb/chipidea.h | 1 + 3 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 005ad5f11b69..30fdc2fd8771 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -19,7 +19,6 @@ #include #include #include -#include #include "ci.h" #include "ci_hdrc_imx.h" @@ -28,7 +27,6 @@ struct ci_hdrc_imx_data { struct usb_phy *phy; struct platform_device *ci_pdev; struct clk *clk; - struct regulator *reg_vbus; }; static const struct usbmisc_ops *usbmisc_ops; @@ -131,20 +129,6 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) goto err_clk; } - /* we only support host now, so enable vbus here */ - data->reg_vbus = devm_regulator_get(&pdev->dev, "vbus"); - if (!IS_ERR(data->reg_vbus)) { - ret = regulator_enable(data->reg_vbus); - if (ret) { - dev_err(&pdev->dev, - "Failed to enable vbus regulator, err=%d\n", - ret); - goto err_clk; - } - } else { - data->reg_vbus = NULL; - } - pdata.phy = data->phy; if (!pdev->dev.dma_mask) @@ -157,7 +141,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "usbmisc init failed, ret=%d\n", ret); - goto err; + goto err_clk; } } @@ -169,7 +153,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Can't register ci_hdrc platform device, err=%d\n", ret); - goto err; + goto err_clk; } if (usbmisc_ops && usbmisc_ops->post) { @@ -190,9 +174,6 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) disable_device: ci_hdrc_remove_device(data->ci_pdev); -err: - if (data->reg_vbus) - regulator_disable(data->reg_vbus); err_clk: clk_disable_unprepare(data->clk); return ret; @@ -205,9 +186,6 @@ static int ci_hdrc_imx_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); ci_hdrc_remove_device(data->ci_pdev); - if (data->reg_vbus) - regulator_disable(data->reg_vbus); - if (data->phy) usb_phy_shutdown(data->phy); diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 5bb3e8154f87..13dbd511f59a 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -65,6 +65,7 @@ #include #include #include +#include #include "ci.h" #include "udc.h" @@ -342,6 +343,24 @@ static irqreturn_t ci_irq(int irq, void *data) return ret; } +static int ci_get_platdata(struct device *dev, + struct ci_hdrc_platform_data *platdata) +{ + /* Get the vbus regulator */ + platdata->reg_vbus = devm_regulator_get(dev, "vbus"); + if (PTR_ERR(platdata->reg_vbus) == -EPROBE_DEFER) { + return -EPROBE_DEFER; + } else if (PTR_ERR(platdata->reg_vbus) == -ENODEV) { + platdata->reg_vbus = NULL; /* no vbus regualator is needed */ + } else if (IS_ERR(platdata->reg_vbus)) { + dev_err(dev, "Getting regulator error: %ld\n", + PTR_ERR(platdata->reg_vbus)); + return PTR_ERR(platdata->reg_vbus); + } + + return 0; +} + static DEFINE_IDA(ci_ida); struct platform_device *ci_hdrc_add_device(struct device *dev, @@ -351,6 +370,10 @@ struct platform_device *ci_hdrc_add_device(struct device *dev, struct platform_device *pdev; int id, ret; + ret = ci_get_platdata(dev, platdata); + if (ret) + return ERR_PTR(ret); + id = ida_simple_get(&ci_ida, 0, 0, GFP_KERNEL); if (id < 0) return ERR_PTR(id); diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 25629948c842..ce4e1aa071b3 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -24,6 +24,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 void (*notify_event) (struct ci_hdrc *ci, unsigned event); + struct regulator *reg_vbus; }; /* Default offset of capability registers */ -- cgit v1.2.3-71-gd317 From 577b232fc9caba1b6f7a3bb9901c00b10e0ca1ba Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:08 +0300 Subject: usb: chipidea: add flag CI_HDRC_DUAL_ROLE_NOT_OTG Since we need otgsc to know vbus's status at some chipidea controllers even it is peripheral-only mode. Besides, some SoCs (eg, AR9331 SoC) don't have otgsc register even the DCCPARAMS_DC and DCCPARAMS_HC are both 1 at CAP_DCCPARAMS. We inroduce flag CI_HDRC_DUAL_ROLE_NOT_OTG to indicate if the controller is dual role, but not supports OTG. If this flag is not set, we follow the rule that if DCCPARAMS_DC and DCCPARAMS_HC are both 1 at CAP_DCCPARAMS, then this controller is otg capable. Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/core.c | 37 ++++++++++++++++++++++++++++++------- include/linux/usb/chipidea.h | 5 +++++ 2 files changed, 35 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 75afc524b659..ab01e18bc2f8 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -426,6 +426,18 @@ static inline void ci_role_destroy(struct ci_hdrc *ci) ci_hdrc_host_destroy(ci); } +static void ci_get_otg_capable(struct ci_hdrc *ci) +{ + if (ci->platdata->flags & CI_HDRC_DUAL_ROLE_NOT_OTG) + ci->is_otg = false; + else + ci->is_otg = (hw_read(ci, CAP_DCCPARAMS, + DCCPARAMS_DC | DCCPARAMS_HC) + == (DCCPARAMS_DC | DCCPARAMS_HC)); + if (ci->is_otg) + dev_dbg(ci->dev, "It is OTG capable controller\n"); +} + static int ci_hdrc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -480,6 +492,8 @@ static int ci_hdrc_probe(struct platform_device *pdev) return -ENODEV; } + ci_get_otg_capable(ci); + if (!ci->platdata->phy_mode) ci->platdata->phy_mode = of_usb_get_phy_mode(of_node); @@ -512,10 +526,22 @@ static int ci_hdrc_probe(struct platform_device *pdev) } if (ci->roles[CI_ROLE_HOST] && ci->roles[CI_ROLE_GADGET]) { - ci->is_otg = true; - /* ID pin needs 1ms debouce time, we delay 2ms for safe */ - mdelay(2); - ci->role = ci_otg_role(ci); + if (ci->is_otg) { + /* + * ID pin needs 1ms debouce time, + * we delay 2ms for safe. + */ + mdelay(2); + ci->role = ci_otg_role(ci); + ci_hdrc_otg_init(ci); + } else { + /* + * If the controller is not OTG capable, but support + * role switch, the defalt role is gadget, and the + * user can switch it through debugfs. + */ + ci->role = CI_ROLE_GADGET; + } } else { ci->role = ci->roles[CI_ROLE_HOST] ? CI_ROLE_HOST @@ -534,9 +560,6 @@ static int ci_hdrc_probe(struct platform_device *pdev) if (ret) goto stop; - if (ci->is_otg) - ci_hdrc_otg_init(ci); - ret = dbg_create_files(ci); if (!ret) return 0; diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index ce4e1aa071b3..10a607ce9090 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -20,6 +20,11 @@ struct ci_hdrc_platform_data { #define CI_HDRC_REQUIRE_TRANSCEIVER BIT(1) #define CI_HDRC_PULLUP_ON_VBUS BIT(2) #define CI_HDRC_DISABLE_STREAMING BIT(3) + /* + * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1, + * but otg is not supported (no register otgsc). + */ +#define CI_HDRC_DUAL_ROLE_NOT_OTG BIT(4) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 -- cgit v1.2.3-71-gd317 From d268e9bc23f5df4a2f4167da246d277c2a468d3d Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 14 Aug 2013 12:44:14 +0300 Subject: usb: chipidea: retire flag CI_HDRC_PULLUP_ON_VBUS Currently, the controller only runs when the ci->vbus_active is true. So the flag CI_HDRC_PULLUP_ON_VBUS is useless no longer. If the user doesn't have otgsc, he/she needs to change ci_handle_vbus_change to update ci->vbus_active. Signed-off-by: Peter Chen Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/ci_hdrc_imx.c | 1 - drivers/usb/chipidea/ci_hdrc_msm.c | 1 - drivers/usb/chipidea/udc.c | 24 ++++++------------------ include/linux/usb/chipidea.h | 1 - 4 files changed, 6 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 30fdc2fd8771..cc53e63c9ce9 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -88,7 +88,6 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) .name = "ci_hdrc_imx", .capoffset = DEF_CAPOFFSET, .flags = CI_HDRC_REQUIRE_TRANSCEIVER | - CI_HDRC_PULLUP_ON_VBUS | CI_HDRC_DISABLE_STREAMING, }; int ret; diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index fb657ef50a9c..2d51d852b474 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -49,7 +49,6 @@ static struct ci_hdrc_platform_data ci_hdrc_msm_platdata = { .name = "ci_hdrc_msm", .flags = CI_HDRC_REGS_SHARED | CI_HDRC_REQUIRE_TRANSCEIVER | - CI_HDRC_PULLUP_ON_VBUS | CI_HDRC_DISABLE_STREAMING, .notify_event = ci_hdrc_msm_notify_event, diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 45abf4d46a71..90c3572bd1b0 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1448,9 +1448,6 @@ static int ci_udc_vbus_session(struct usb_gadget *_gadget, int is_active) unsigned long flags; int gadget_ready = 0; - if (!(ci->platdata->flags & CI_HDRC_PULLUP_ON_VBUS)) - return -EOPNOTSUPP; - spin_lock_irqsave(&ci->lock, flags); ci->vbus_active = is_active; if (ci->driver) @@ -1635,13 +1632,11 @@ static int ci_udc_start(struct usb_gadget *gadget, ci->driver = driver; pm_runtime_get_sync(&ci->gadget.dev); - if (ci->platdata->flags & CI_HDRC_PULLUP_ON_VBUS) { - if (ci->vbus_active) { - hw_device_reset(ci, USBMODE_CM_DC); - } else { - pm_runtime_put_sync(&ci->gadget.dev); - goto done; - } + if (ci->vbus_active) { + hw_device_reset(ci, USBMODE_CM_DC); + } else { + pm_runtime_put_sync(&ci->gadget.dev); + goto done; } retval = hw_device_state(ci, ci->ep0out->qh.dma); @@ -1664,8 +1659,7 @@ static int ci_udc_stop(struct usb_gadget *gadget, spin_lock_irqsave(&ci->lock, flags); - if (!(ci->platdata->flags & CI_HDRC_PULLUP_ON_VBUS) || - ci->vbus_active) { + if (ci->vbus_active) { hw_device_state(ci, 0); if (ci->platdata->notify_event) ci->platdata->notify_event(ci, @@ -1800,12 +1794,6 @@ static int udc_start(struct ci_hdrc *ci) } } - if (!(ci->platdata->flags & CI_HDRC_PULLUP_ON_VBUS)) { - retval = hw_device_reset(ci, USBMODE_CM_DC); - if (retval) - goto put_transceiver; - } - if (ci->transceiver) { retval = otg_set_peripheral(ci->transceiver->otg, &ci->gadget); diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 10a607ce9090..7d399671a566 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -18,7 +18,6 @@ struct ci_hdrc_platform_data { unsigned long flags; #define CI_HDRC_REGS_SHARED BIT(0) #define CI_HDRC_REQUIRE_TRANSCEIVER BIT(1) -#define CI_HDRC_PULLUP_ON_VBUS BIT(2) #define CI_HDRC_DISABLE_STREAMING BIT(3) /* * Only set it when DCCPARAMS.DC==1 and DCCPARAMS.HC==1, -- cgit v1.2.3-71-gd317 From 5c32b35b004f5ef70dcf62bbc42b8bed1e50b471 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:31 -0600 Subject: PCI: Add hotplug_slot_ops.reset_slot() This optional callback allows hotplug controllers to perform slot specific resets. These may be necessary in cases where a normal secondary bus reset can interact with controller logic and expose spurious hotplugs. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci_hotplug.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 8db71dcd6337..bd32109e607e 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -63,6 +63,9 @@ enum pcie_link_width { * @get_adapter_status: Called to get see if an adapter is present in the slot or not. * If this field is NULL, the value passed in the struct hotplug_slot_info * will be used when this value is requested by a user. + * @reset_slot: Optional interface to allow override of a bus reset for the + * slot for cases where a secondary bus reset can result in spurious + * hotplug events or where a slot can be reset independent of the bus. * * The table of function pointers that is passed to the hotplug pci core by a * hotplug pci driver. These functions are called by the hotplug pci core when @@ -80,6 +83,7 @@ struct hotplug_slot_ops { int (*get_attention_status) (struct hotplug_slot *slot, u8 *value); int (*get_latch_status) (struct hotplug_slot *slot, u8 *value); int (*get_adapter_status) (struct hotplug_slot *slot, u8 *value); + int (*reset_slot) (struct hotplug_slot *slot, int probe); }; /** -- cgit v1.2.3-71-gd317 From 090a3c5322e900f468b3205b76d0837003ad57b2 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 8 Aug 2013 14:09:55 -0600 Subject: PCI: Add pci_reset_slot() and pci_reset_bus() Sometimes pci_reset_function() is not sufficient. We have cases where devices do not support any kind of reset, but there might be multiple functions on the bus preventing pci_reset_function() from doing a secondary bus reset. We also have cases where a device will advertise that it supports a PM reset, but really does nothing on D3hot->D0 (graphics cards are notorious for this). These devices often also have more than one function, so even blacklisting PM reset for them wouldn't allow a secondary bus reset through pci_reset_function(). If a driver supports multiple devices it should have the ability to induce a bus reset when it needs to. This patch provides that ability through pci_reset_slot() and pci_reset_bus(). It's the caller's responsibility when using these interfaces to understand that all of the devices in or below the slot (or on or below the bus) will be reset and therefore should be under control of the caller. PCI state of all the affected devices is saved and restored around these resets, but internal state of all of the affected devices is reset (which should be the intention). Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 209 ++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 2 + 2 files changed, 211 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d48d9febc241..12fccc24925c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3460,6 +3460,215 @@ int pci_reset_function(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_reset_function); +/* Lock devices from the top of the tree down */ +static void pci_bus_lock(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + pci_dev_lock(dev); + if (dev->subordinate) + pci_bus_lock(dev->subordinate); + } +} + +/* Unlock devices from the bottom of the tree up */ +static void pci_bus_unlock(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->subordinate) + pci_bus_unlock(dev->subordinate); + pci_dev_unlock(dev); + } +} + +/* Lock devices from the top of the tree down */ +static void pci_slot_lock(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + pci_dev_lock(dev); + if (dev->subordinate) + pci_bus_lock(dev->subordinate); + } +} + +/* Unlock devices from the bottom of the tree up */ +static void pci_slot_unlock(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (dev->subordinate) + pci_bus_unlock(dev->subordinate); + pci_dev_unlock(dev); + } +} + +/* Save and disable devices from the top of the tree down */ +static void pci_bus_save_and_disable(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + pci_dev_save_and_disable(dev); + if (dev->subordinate) + pci_bus_save_and_disable(dev->subordinate); + } +} + +/* + * Restore devices from top of the tree down - parent bridges need to be + * restored before we can get to subordinate devices. + */ +static void pci_bus_restore(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + pci_dev_restore(dev); + if (dev->subordinate) + pci_bus_restore(dev->subordinate); + } +} + +/* Save and disable devices from the top of the tree down */ +static void pci_slot_save_and_disable(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + pci_dev_save_and_disable(dev); + if (dev->subordinate) + pci_bus_save_and_disable(dev->subordinate); + } +} + +/* + * Restore devices from top of the tree down - parent bridges need to be + * restored before we can get to subordinate devices. + */ +static void pci_slot_restore(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + pci_dev_restore(dev); + if (dev->subordinate) + pci_bus_restore(dev->subordinate); + } +} + +static int pci_slot_reset(struct pci_slot *slot, int probe) +{ + int rc; + + if (!slot) + return -ENOTTY; + + if (!probe) + pci_slot_lock(slot); + + might_sleep(); + + rc = pci_reset_hotplug_slot(slot->hotplug, probe); + + if (!probe) + pci_slot_unlock(slot); + + return rc; +} + +/** + * pci_reset_slot - reset a PCI slot + * @slot: PCI slot to reset + * + * A PCI bus may host multiple slots, each slot may support a reset mechanism + * independent of other slots. For instance, some slots may support slot power + * control. In the case of a 1:1 bus to slot architecture, this function may + * wrap the bus reset to avoid spurious slot related events such as hotplug. + * Generally a slot reset should be attempted before a bus reset. All of the + * function of the slot and any subordinate buses behind the slot are reset + * through this function. PCI config space of all devices in the slot and + * behind the slot is saved before and restored after reset. + * + * Return 0 on success, non-zero on error. + */ +int pci_reset_slot(struct pci_slot *slot) +{ + int rc; + + rc = pci_slot_reset(slot, 1); + if (rc) + return rc; + + pci_slot_save_and_disable(slot); + + rc = pci_slot_reset(slot, 0); + + pci_slot_restore(slot); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_reset_slot); + +static int pci_bus_reset(struct pci_bus *bus, int probe) +{ + if (!bus->self) + return -ENOTTY; + + if (probe) + return 0; + + pci_bus_lock(bus); + + might_sleep(); + + pci_reset_bridge_secondary_bus(bus->self); + + pci_bus_unlock(bus); + + return 0; +} + +/** + * pci_reset_bus - reset a PCI bus + * @bus: top level PCI bus to reset + * + * Do a bus reset on the given bus and any subordinate buses, saving + * and restoring state of all devices. + * + * Return 0 on success, non-zero on error. + */ +int pci_reset_bus(struct pci_bus *bus) +{ + int rc; + + rc = pci_bus_reset(bus, 1); + if (rc) + return rc; + + pci_bus_save_and_disable(bus); + + rc = pci_bus_reset(bus, 0); + + pci_bus_restore(bus); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_reset_bus); + /** * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count * @dev: PCI device to query diff --git a/include/linux/pci.h b/include/linux/pci.h index 35c1bc4909f3..1a8fd3464daf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,6 +924,8 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_reset_slot(struct pci_slot *slot); +int pci_reset_bus(struct pci_bus *bus); void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); -- cgit v1.2.3-71-gd317 From 3f0fa9a808f98fa10a18ba2a73f13d65fda990fb Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Wed, 14 Aug 2013 16:05:02 -0700 Subject: regmap: Add another missing header for !CONFIG_REGMAP stubs The use of WARN_ON() needs the definitions from bug.h, without it you can get: include/linux/regmap.h: In function 'regmap_write': include/linux/regmap.h:525:2: error: implicit declaration of function 'WARN_ONCE' [-Werror=implicit-function-declaration] Signed-off-by: Kevin Hilman Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 580a5320cc96..6d91fcb4c5cb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -16,6 +16,7 @@ #include #include #include +#include struct module; struct device; -- cgit v1.2.3-71-gd317 From 9a3d2b9beefd5b07c1d8f70ded01b88f203ee304 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 14 Aug 2013 14:06:05 -0600 Subject: PCI: Add pci_probe_reset_slot() and pci_probe_reset_bus() Users of pci_reset_bus() and pci_reset_slot() need a way to probe whether the bus or slot supports reset. Add trivial helper functions and export them as vfio-pci will make use of these. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 24 ++++++++++++++++++++++++ include/linux/pci.h | 2 ++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index ea5e70486174..7f89372483dd 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3609,6 +3609,18 @@ static int pci_slot_reset(struct pci_slot *slot, int probe) return rc; } +/** + * pci_probe_reset_slot - probe whether a PCI slot can be reset + * @slot: PCI slot to probe + * + * Return 0 if slot can be reset, negative if a slot reset is not supported. + */ +int pci_probe_reset_slot(struct pci_slot *slot) +{ + return pci_slot_reset(slot, 1); +} +EXPORT_SYMBOL_GPL(pci_probe_reset_slot); + /** * pci_reset_slot - reset a PCI slot * @slot: PCI slot to reset @@ -3661,6 +3673,18 @@ static int pci_bus_reset(struct pci_bus *bus, int probe) return 0; } +/** + * pci_probe_reset_bus - probe whether a PCI bus can be reset + * @bus: PCI bus to probe + * + * Return 0 if bus can be reset, negative if a bus reset is not supported. + */ +int pci_probe_reset_bus(struct pci_bus *bus) +{ + return pci_bus_reset(bus, 1); +} +EXPORT_SYMBOL_GPL(pci_probe_reset_bus); + /** * pci_reset_bus - reset a PCI bus * @bus: top level PCI bus to reset diff --git a/include/linux/pci.h b/include/linux/pci.h index 1a8fd3464daf..daf40cd851df 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -924,7 +924,9 @@ int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); +int pci_probe_reset_slot(struct pci_slot *slot); int pci_reset_slot(struct pci_slot *slot); +int pci_probe_reset_bus(struct pci_bus *bus); int pci_reset_bus(struct pci_bus *bus); void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); -- cgit v1.2.3-71-gd317 From 0a324f3189ed9c78b1aaf48d88e93cb18643c655 Mon Sep 17 00:00:00 2001 From: Moshe Lazer Date: Wed, 14 Aug 2013 17:46:48 +0300 Subject: net/mlx5_core: Support MANAGE_PAGES and QUERY_PAGES firmware command changes In the previous QUERY_PAGES command version we used one command to get the required amount of boot, init and post init pages. The new version uses the op_mod field to specify whether the query is for the required amount of boot, init or post init pages. In addition the output field size for the required amount of pages increased from 16 to 32 bits. In MANAGE_PAGES command the input_num_entries and output_num_entries fields sizes changed from 16 to 32 bits and the PAS tables offset changed to 0x10. In the pages request event the num_pages field also changed to 32 bits. In the HCA-capabilities-layout the size and location of max_qp_mcg field has been changed to support 24 bits. This patch isn't compatible with firmware versions < 5; however, it turns out that the first GA firmware we will publish will not support previous versions so this should be OK. Signed-off-by: Moshe Lazer Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 2 +- .../net/ethernet/mellanox/mlx5/core/pagealloc.c | 58 ++++++++++------------ include/linux/mlx5/device.h | 22 ++++---- include/linux/mlx5/driver.h | 4 +- 6 files changed, 41 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index c571de85d0f9..5472cbd34028 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -46,7 +46,7 @@ #include "mlx5_core.h" enum { - CMD_IF_REV = 4, + CMD_IF_REV = 5, }; enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index c02cbcfd0fb8..443cc4d7b024 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -268,7 +268,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq) case MLX5_EVENT_TYPE_PAGE_REQUEST: { u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id); - s16 npages = be16_to_cpu(eqe->data.req_pages.num_pages); + s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages); mlx5_core_dbg(dev, "page request for func 0x%x, napges %d\n", func_id, npages); mlx5_core_req_pages_handler(dev, func_id, npages); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 72a5222447f5..f012658b6a92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -113,7 +113,7 @@ int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev, caps->log_max_srq = out->hca_cap.log_max_srqs & 0x1f; caps->local_ca_ack_delay = out->hca_cap.local_ca_ack_delay & 0x1f; caps->log_max_mcg = out->hca_cap.log_max_mcg; - caps->max_qp_mcg = be16_to_cpu(out->hca_cap.max_qp_mcg); + caps->max_qp_mcg = be32_to_cpu(out->hca_cap.max_qp_mcg) & 0xffffff; caps->max_ra_res_qp = 1 << (out->hca_cap.log_max_ra_res_qp & 0x3f); caps->max_ra_req_qp = 1 << (out->hca_cap.log_max_ra_req_qp & 0x3f); caps->max_srq_wqes = 1 << out->hca_cap.log_max_srq_sz; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 4a3e137931a3..3a2408d44820 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -43,10 +43,16 @@ enum { MLX5_PAGES_TAKE = 2 }; +enum { + MLX5_BOOT_PAGES = 1, + MLX5_INIT_PAGES = 2, + MLX5_POST_INIT_PAGES = 3 +}; + struct mlx5_pages_req { struct mlx5_core_dev *dev; u32 func_id; - s16 npages; + s32 npages; struct work_struct work; }; @@ -64,27 +70,23 @@ struct mlx5_query_pages_inbox { struct mlx5_query_pages_outbox { struct mlx5_outbox_hdr hdr; - __be16 num_boot_pages; + __be16 rsvd; __be16 func_id; - __be16 init_pages; - __be16 num_pages; + __be32 num_pages; }; struct mlx5_manage_pages_inbox { struct mlx5_inbox_hdr hdr; - __be16 rsvd0; + __be16 rsvd; __be16 func_id; - __be16 rsvd1; - __be16 num_entries; - u8 rsvd2[16]; + __be32 num_entries; __be64 pas[0]; }; struct mlx5_manage_pages_outbox { struct mlx5_outbox_hdr hdr; - u8 rsvd0[2]; - __be16 num_entries; - u8 rsvd1[20]; + __be32 num_entries; + u8 rsvd[4]; __be64 pas[0]; }; @@ -146,7 +148,7 @@ static struct page *remove_page(struct mlx5_core_dev *dev, u64 addr) } static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id, - s16 *pages, s16 *init_pages, u16 *boot_pages) + s32 *npages, int boot) { struct mlx5_query_pages_inbox in; struct mlx5_query_pages_outbox out; @@ -155,6 +157,8 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id, memset(&in, 0, sizeof(in)); memset(&out, 0, sizeof(out)); in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_PAGES); + in.hdr.opmod = boot ? cpu_to_be16(MLX5_BOOT_PAGES) : cpu_to_be16(MLX5_INIT_PAGES); + err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); if (err) return err; @@ -162,15 +166,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id, if (out.hdr.status) return mlx5_cmd_status_to_err(&out.hdr); - if (pages) - *pages = be16_to_cpu(out.num_pages); - - if (init_pages) - *init_pages = be16_to_cpu(out.init_pages); - - if (boot_pages) - *boot_pages = be16_to_cpu(out.num_boot_pages); - + *npages = be32_to_cpu(out.num_pages); *func_id = be16_to_cpu(out.func_id); return err; @@ -224,7 +220,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES); in->hdr.opmod = cpu_to_be16(MLX5_PAGES_GIVE); in->func_id = cpu_to_be16(func_id); - in->num_entries = cpu_to_be16(npages); + in->num_entries = cpu_to_be32(npages); err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out)); mlx5_core_dbg(dev, "err %d\n", err); if (err) { @@ -292,7 +288,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES); in.hdr.opmod = cpu_to_be16(MLX5_PAGES_TAKE); in.func_id = cpu_to_be16(func_id); - in.num_entries = cpu_to_be16(npages); + in.num_entries = cpu_to_be32(npages); mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen); err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen); if (err) { @@ -306,7 +302,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, goto out_free; } - num_claimed = be16_to_cpu(out->num_entries); + num_claimed = be32_to_cpu(out->num_entries); if (nclaimed) *nclaimed = num_claimed; @@ -345,7 +341,7 @@ static void pages_work_handler(struct work_struct *work) } void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, - s16 npages) + s32 npages) { struct mlx5_pages_req *req; @@ -364,20 +360,18 @@ void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot) { - u16 uninitialized_var(boot_pages); - s16 uninitialized_var(init_pages); u16 uninitialized_var(func_id); + s32 uninitialized_var(npages); int err; - err = mlx5_cmd_query_pages(dev, &func_id, NULL, &init_pages, - &boot_pages); + err = mlx5_cmd_query_pages(dev, &func_id, &npages, boot); if (err) return err; + mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n", + npages, boot ? "boot" : "init", func_id); - mlx5_core_dbg(dev, "requested %d init pages and %d boot pages for func_id 0x%x\n", - init_pages, boot_pages, func_id); - return give_pages(dev, func_id, boot ? boot_pages : init_pages, 0); + return give_pages(dev, func_id, npages, 0); } static int optimal_reclaimed_pages(void) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 737685e9e852..68029b30c3dc 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -309,21 +309,20 @@ struct mlx5_hca_cap { __be16 max_desc_sz_rq; u8 rsvd21[2]; __be16 max_desc_sz_sq_dc; - u8 rsvd22[4]; - __be16 max_qp_mcg; - u8 rsvd23; + __be32 max_qp_mcg; + u8 rsvd22[3]; u8 log_max_mcg; - u8 rsvd24; + u8 rsvd23; u8 log_max_pd; - u8 rsvd25; + u8 rsvd24; u8 log_max_xrcd; - u8 rsvd26[42]; + u8 rsvd25[42]; __be16 log_uar_page_sz; - u8 rsvd27[28]; + u8 rsvd26[28]; u8 log_msx_atomic_size_qp; - u8 rsvd28[2]; + u8 rsvd27[2]; u8 log_msx_atomic_size_dc; - u8 rsvd29[76]; + u8 rsvd28[76]; }; @@ -472,9 +471,8 @@ struct mlx5_eqe_cmd { struct mlx5_eqe_page_req { u8 rsvd0[2]; __be16 func_id; - u8 rsvd1[2]; - __be16 num_pages; - __be32 rsvd2[5]; + __be32 num_pages; + __be32 rsvd1[5]; }; union ev_data { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 611e65e76b00..8888381fc150 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -358,7 +358,7 @@ struct mlx5_caps { u32 reserved_lkey; u8 local_ca_ack_delay; u8 log_max_mcg; - u16 max_qp_mcg; + u32 max_qp_mcg; int min_page_sz; }; @@ -691,7 +691,7 @@ void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); int mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, - s16 npages); + s32 npages); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); -- cgit v1.2.3-71-gd317 From 98d4f93c79b002f85480320fe63fefaa31d58b6c Mon Sep 17 00:00:00 2001 From: Jens Frederich Date: Thu, 15 Aug 2013 21:34:55 +0200 Subject: Staging: olpc_dcon: replace some magic numbers This patch replace some magic numbers. I believe it makes the driver more readable. The magic number 0x26 is the XO system embedded controller (EC) command 'DCON power enable/disable'. Number 0x41, and 0x42 are special memory controller settings register. The 0x41 initialize bit sequence 0x101 means: enable memory power down function and special SDRAM clock delay for synchronize SDRAM output and clock signal. The 0x42 initialize squence 0x101 is wrong. According to the specification Bit 8 is reserved, thus not in use. I removed it. Signed-off-by: Jens Frederich Signed-off-by: Greg Kroah-Hartman --- drivers/staging/olpc_dcon/olpc_dcon.c | 13 +++++++------ drivers/staging/olpc_dcon/olpc_dcon.h | 27 ++++++++++++++++++--------- include/linux/olpc-ec.h | 1 + 3 files changed, 26 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/staging/olpc_dcon/olpc_dcon.c b/drivers/staging/olpc_dcon/olpc_dcon.c index 7c460f2c0d23..5ca4fa4fd246 100644 --- a/drivers/staging/olpc_dcon/olpc_dcon.c +++ b/drivers/staging/olpc_dcon/olpc_dcon.c @@ -90,9 +90,10 @@ static int dcon_hw_init(struct dcon_priv *dcon, int is_init) /* SDRAM setup/hold time */ dcon_write(dcon, 0x3a, 0xc040); - dcon_write(dcon, 0x41, 0x0000); - dcon_write(dcon, 0x41, 0x0101); - dcon_write(dcon, 0x42, 0x0101); + dcon_write(dcon, DCON_REG_MEM_OPT_A, 0x0000); /* clear option bits */ + dcon_write(dcon, DCON_REG_MEM_OPT_A, + MEM_DLL_CLOCK_DELAY | MEM_POWER_DOWN); + dcon_write(dcon, DCON_REG_MEM_OPT_B, MEM_SOFT_RESET); /* Colour swizzle, AA, no passthrough, backlight */ if (is_init) { @@ -126,7 +127,7 @@ static int dcon_bus_stabilize(struct dcon_priv *dcon, int is_powered_down) power_up: if (is_powered_down) { x = 1; - x = olpc_ec_cmd(0x26, (unsigned char *)&x, 1, NULL, 0); + x = olpc_ec_cmd(EC_DCON_POWER_MODE, (u8 *)&x, 1, NULL, 0); if (x) { pr_warn("unable to force dcon to power up: %d!\n", x); return x; @@ -144,7 +145,7 @@ power_up: pr_err("unable to stabilize dcon's smbus, reasserting power and praying.\n"); BUG_ON(olpc_board_at_least(olpc_board(0xc2))); x = 0; - olpc_ec_cmd(0x26, (unsigned char *)&x, 1, NULL, 0); + olpc_ec_cmd(EC_DCON_POWER_MODE, (u8 *)&x, 1, NULL, 0); msleep(100); is_powered_down = 1; goto power_up; /* argh, stupid hardware.. */ @@ -208,7 +209,7 @@ static void dcon_sleep(struct dcon_priv *dcon, bool sleep) if (sleep) { x = 0; - x = olpc_ec_cmd(0x26, (unsigned char *)&x, 1, NULL, 0); + x = olpc_ec_cmd(EC_DCON_POWER_MODE, (u8 *)&x, 1, NULL, 0); if (x) pr_warn("unable to force dcon to power down: %d!\n", x); else diff --git a/drivers/staging/olpc_dcon/olpc_dcon.h b/drivers/staging/olpc_dcon/olpc_dcon.h index 997bded2949f..524ee49fbacb 100644 --- a/drivers/staging/olpc_dcon/olpc_dcon.h +++ b/drivers/staging/olpc_dcon/olpc_dcon.h @@ -22,15 +22,24 @@ #define MODE_DEBUG (1<<14) #define MODE_SELFTEST (1<<15) -#define DCON_REG_HRES 2 -#define DCON_REG_HTOTAL 3 -#define DCON_REG_HSYNC_WIDTH 4 -#define DCON_REG_VRES 5 -#define DCON_REG_VTOTAL 6 -#define DCON_REG_VSYNC_WIDTH 7 -#define DCON_REG_TIMEOUT 8 -#define DCON_REG_SCAN_INT 9 -#define DCON_REG_BRIGHT 10 +#define DCON_REG_HRES 0x2 +#define DCON_REG_HTOTAL 0x3 +#define DCON_REG_HSYNC_WIDTH 0x4 +#define DCON_REG_VRES 0x5 +#define DCON_REG_VTOTAL 0x6 +#define DCON_REG_VSYNC_WIDTH 0x7 +#define DCON_REG_TIMEOUT 0x8 +#define DCON_REG_SCAN_INT 0x9 +#define DCON_REG_BRIGHT 0x10 +#define DCON_REG_MEM_OPT_A 0x41 +#define DCON_REG_MEM_OPT_B 0x42 + +/* Load Delay Locked Loop (DLL) settings for clock delay */ +#define MEM_DLL_CLOCK_DELAY (1<<0) +/* Memory controller power down function */ +#define MEM_POWER_DOWN (1<<8) +/* Memory controller software reset */ +#define MEM_SOFT_RESET (1<<0) /* Status values */ diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h index 5bb6e760aa61..2925df3ce78a 100644 --- a/include/linux/olpc-ec.h +++ b/include/linux/olpc-ec.h @@ -6,6 +6,7 @@ #define EC_WRITE_SCI_MASK 0x1b #define EC_WAKE_UP_WLAN 0x24 #define EC_WLAN_LEAVE_RESET 0x25 +#define EC_DCON_POWER_MODE 0x26 #define EC_READ_EB_MODE 0x2a #define EC_SET_SCI_INHIBIT 0x32 #define EC_SET_SCI_INHIBIT_RELEASE 0x34 -- cgit v1.2.3-71-gd317 From 6d33f7bb8c3863e54f8bdede0a2bf97a3585ac20 Mon Sep 17 00:00:00 2001 From: Thomas Pugliese Date: Thu, 15 Aug 2013 12:21:30 -0500 Subject: USB: WUSBCORE: clear RPIPE stall for control endpoints When the HWA encounters a STALL on a control endpoint, it should clear the RPIPE_STALL feature on the RPIPE before processing the next transfer request. Otherwise, all transfer requests on that endpoint after the first STALL will fail because the RPIPE is still in the halted state. This also removes the unneccessary call to spin_lock_irqsave for a nested lock that was present in the first patch. Signed-off-by: Thomas Pugliese Signed-off-by: Greg Kroah-Hartman --- drivers/usb/wusbcore/wa-hc.h | 15 +++++++- drivers/usb/wusbcore/wa-rpipe.c | 21 +++++++++++ drivers/usb/wusbcore/wa-xfer.c | 84 ++++++++++++++++++++++++++++++++++++----- include/linux/usb/wusb-wa.h | 1 + 4 files changed, 109 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/wusbcore/wa-hc.h b/drivers/usb/wusbcore/wa-hc.h index d6bea3e0b54a..cf250c21e946 100644 --- a/drivers/usb/wusbcore/wa-hc.h +++ b/drivers/usb/wusbcore/wa-hc.h @@ -91,6 +91,7 @@ struct wusbhc; struct wahc; extern void wa_urb_enqueue_run(struct work_struct *ws); +extern void wa_process_errored_transfers_run(struct work_struct *ws); /** * RPipe instance @@ -190,8 +191,14 @@ struct wahc { struct list_head xfer_list; struct list_head xfer_delayed_list; + struct list_head xfer_errored_list; + /* + * lock for the above xfer lists. Can be taken while a xfer->lock is + * held but not in the reverse order. + */ spinlock_t xfer_list_lock; - struct work_struct xfer_work; + struct work_struct xfer_enqueue_work; + struct work_struct xfer_error_work; atomic_t xfer_id_count; }; @@ -244,8 +251,10 @@ static inline void wa_init(struct wahc *wa) edc_init(&wa->dti_edc); INIT_LIST_HEAD(&wa->xfer_list); INIT_LIST_HEAD(&wa->xfer_delayed_list); + INIT_LIST_HEAD(&wa->xfer_errored_list); spin_lock_init(&wa->xfer_list_lock); - INIT_WORK(&wa->xfer_work, wa_urb_enqueue_run); + INIT_WORK(&wa->xfer_enqueue_work, wa_urb_enqueue_run); + INIT_WORK(&wa->xfer_error_work, wa_process_errored_transfers_run); atomic_set(&wa->xfer_id_count, 1); } @@ -269,6 +278,8 @@ static inline void rpipe_put(struct wa_rpipe *rpipe) } extern void rpipe_ep_disable(struct wahc *, struct usb_host_endpoint *); +extern void rpipe_clear_feature_stalled(struct wahc *, + struct usb_host_endpoint *); extern int wa_rpipes_create(struct wahc *); extern void wa_rpipes_destroy(struct wahc *); static inline void rpipe_avail_dec(struct wa_rpipe *rpipe) diff --git a/drivers/usb/wusbcore/wa-rpipe.c b/drivers/usb/wusbcore/wa-rpipe.c index 9a595c1ed867..fd4f1ce6256a 100644 --- a/drivers/usb/wusbcore/wa-rpipe.c +++ b/drivers/usb/wusbcore/wa-rpipe.c @@ -527,3 +527,24 @@ void rpipe_ep_disable(struct wahc *wa, struct usb_host_endpoint *ep) mutex_unlock(&wa->rpipe_mutex); } EXPORT_SYMBOL_GPL(rpipe_ep_disable); + +/* Clear the stalled status of an RPIPE. */ +void rpipe_clear_feature_stalled(struct wahc *wa, struct usb_host_endpoint *ep) +{ + struct wa_rpipe *rpipe; + + mutex_lock(&wa->rpipe_mutex); + rpipe = ep->hcpriv; + if (rpipe != NULL) { + u16 index = le16_to_cpu(rpipe->descr.wRPipeIndex); + + usb_control_msg( + wa->usb_dev, usb_rcvctrlpipe(wa->usb_dev, 0), + USB_REQ_CLEAR_FEATURE, + USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_RPIPE, + RPIPE_STALL, index, NULL, 0, 1000); + } + mutex_unlock(&wa->rpipe_mutex); +} +EXPORT_SYMBOL_GPL(rpipe_clear_feature_stalled); + diff --git a/drivers/usb/wusbcore/wa-xfer.c b/drivers/usb/wusbcore/wa-xfer.c index f5c81afc6e96..d74fe1ae16ac 100644 --- a/drivers/usb/wusbcore/wa-xfer.c +++ b/drivers/usb/wusbcore/wa-xfer.c @@ -1100,7 +1100,7 @@ error_xfer_submit: */ void wa_urb_enqueue_run(struct work_struct *ws) { - struct wahc *wa = container_of(ws, struct wahc, xfer_work); + struct wahc *wa = container_of(ws, struct wahc, xfer_enqueue_work); struct wa_xfer *xfer, *next; struct urb *urb; LIST_HEAD(tmp_list); @@ -1125,6 +1125,49 @@ void wa_urb_enqueue_run(struct work_struct *ws) } EXPORT_SYMBOL_GPL(wa_urb_enqueue_run); +/* + * Process the errored transfers on the Wire Adapter outside of interrupt. + */ +void wa_process_errored_transfers_run(struct work_struct *ws) +{ + struct wahc *wa = container_of(ws, struct wahc, xfer_error_work); + struct wa_xfer *xfer, *next; + LIST_HEAD(tmp_list); + + pr_info("%s: Run delayed STALL processing.\n", __func__); + + /* Create a copy of the wa->xfer_errored_list while holding the lock */ + spin_lock_irq(&wa->xfer_list_lock); + list_cut_position(&tmp_list, &wa->xfer_errored_list, + wa->xfer_errored_list.prev); + spin_unlock_irq(&wa->xfer_list_lock); + + /* + * run rpipe_clear_feature_stalled from temp list without list lock + * held. + */ + list_for_each_entry_safe(xfer, next, &tmp_list, list_node) { + struct usb_host_endpoint *ep; + unsigned long flags; + struct wa_rpipe *rpipe; + + spin_lock_irqsave(&xfer->lock, flags); + ep = xfer->ep; + rpipe = ep->hcpriv; + spin_unlock_irqrestore(&xfer->lock, flags); + + /* clear RPIPE feature stalled without holding a lock. */ + rpipe_clear_feature_stalled(wa, ep); + + /* complete the xfer. This removes it from the tmp list. */ + wa_xfer_completion(xfer); + + /* check for work. */ + wa_xfer_delayed_run(rpipe); + } +} +EXPORT_SYMBOL_GPL(wa_process_errored_transfers_run); + /* * Submit a transfer to the Wire Adapter in a delayed way * @@ -1180,7 +1223,7 @@ int wa_urb_enqueue(struct wahc *wa, struct usb_host_endpoint *ep, spin_lock_irqsave(&wa->xfer_list_lock, my_flags); list_add_tail(&xfer->list_node, &wa->xfer_delayed_list); spin_unlock_irqrestore(&wa->xfer_list_lock, my_flags); - queue_work(wusbd, &wa->xfer_work); + queue_work(wusbd, &wa->xfer_enqueue_work); } else { wa_urb_enqueue_b(xfer); } @@ -1222,7 +1265,8 @@ int wa_urb_dequeue(struct wahc *wa, struct urb *urb) xfer = urb->hcpriv; if (xfer == NULL) { - /* NOthing setup yet enqueue will see urb->status != + /* + * Nothing setup yet enqueue will see urb->status != * -EINPROGRESS (by hcd layer) and bail out with * error, no need to do completion */ @@ -1360,7 +1404,7 @@ static int wa_xfer_status_to_errno(u8 status) * * inbound transfers: need to schedule a DTI read * - * FIXME: this functio needs to be broken up in parts + * FIXME: this function needs to be broken up in parts */ static void wa_xfer_result_chew(struct wahc *wa, struct wa_xfer *xfer) { @@ -1482,17 +1526,37 @@ error_submit_buf_in: seg->result = result; kfree(wa->buf_in_urb->sg); error_sg_alloc: + __wa_xfer_abort(xfer); error_complete: seg->status = WA_SEG_ERROR; xfer->segs_done++; rpipe_ready = rpipe_avail_inc(rpipe); - __wa_xfer_abort(xfer); done = __wa_xfer_is_done(xfer); - spin_unlock_irqrestore(&xfer->lock, flags); - if (done) - wa_xfer_completion(xfer); - if (rpipe_ready) - wa_xfer_delayed_run(rpipe); + /* + * queue work item to clear STALL for control endpoints. + * Otherwise, let endpoint_reset take care of it. + */ + if (((usb_status & 0x3f) == WA_XFER_STATUS_HALTED) && + usb_endpoint_xfer_control(&xfer->ep->desc) && + done) { + + dev_info(dev, "Control EP stall. Queue delayed work.\n"); + spin_lock_irq(&wa->xfer_list_lock); + /* remove xfer from xfer_list. */ + list_del(&xfer->list_node); + /* add xfer to xfer_errored_list. */ + list_add_tail(&xfer->list_node, &wa->xfer_errored_list); + spin_unlock_irq(&wa->xfer_list_lock); + spin_unlock_irqrestore(&xfer->lock, flags); + queue_work(wusbd, &wa->xfer_error_work); + } else { + spin_unlock_irqrestore(&xfer->lock, flags); + if (done) + wa_xfer_completion(xfer); + if (rpipe_ready) + wa_xfer_delayed_run(rpipe); + } + return; error_bad_seg: diff --git a/include/linux/usb/wusb-wa.h b/include/linux/usb/wusb-wa.h index 6be985b2a434..4ff744e2b678 100644 --- a/include/linux/usb/wusb-wa.h +++ b/include/linux/usb/wusb-wa.h @@ -66,6 +66,7 @@ enum { WA_ENABLE = 0x01, WA_RESET = 0x02, RPIPE_PAUSE = 0x1, + RPIPE_STALL = 0x2, }; /* Responses from Get Status request ([WUSB] section 8.3.1.6) */ -- cgit v1.2.3-71-gd317 From d536321df392ee0db6a5e92d98f0303020315f40 Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Fri, 16 Aug 2013 14:11:00 +0100 Subject: iio: trigger: implement devm_iio_trigger_alloc/devm_iio_triger_free Add a resource managed devm_iio_trigger_alloc()/devm_iio_triger_free() to automatically clean up triggers allocated by IIO drivers, thus leading to simplified IIO drivers code. Signed-off-by: Jacek Anaszewski Signed-off-by: Kyunmin Park Signed-off-by: Jonathan Cameron --- Documentation/driver-model/devres.txt | 2 + drivers/iio/industrialio-trigger.c | 72 +++++++++++++++++++++++++++++++++-- include/linux/iio/iio.h | 29 ++++++++++++++ 3 files changed, 99 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt index 1d3233292989..fb57d85e7316 100644 --- a/Documentation/driver-model/devres.txt +++ b/Documentation/driver-model/devres.txt @@ -240,6 +240,8 @@ MEM IIO devm_iio_device_alloc() devm_iio_device_free() + devm_iio_trigger_alloc() + devm_iio_trigger_free() IO region devm_request_region() diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index 0dd9bb873130..bf5e70a32d3f 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -424,9 +424,8 @@ static void iio_trig_subirqunmask(struct irq_data *d) trig->subirqs[d->irq - trig->subirq_base].enabled = true; } -struct iio_trigger *iio_trigger_alloc(const char *fmt, ...) +static struct iio_trigger *viio_trigger_alloc(const char *fmt, va_list vargs) { - va_list vargs; struct iio_trigger *trig; trig = kzalloc(sizeof *trig, GFP_KERNEL); if (trig) { @@ -444,9 +443,8 @@ struct iio_trigger *iio_trigger_alloc(const char *fmt, ...) kfree(trig); return NULL; } - va_start(vargs, fmt); + trig->name = kvasprintf(GFP_KERNEL, fmt, vargs); - va_end(vargs); if (trig->name == NULL) { irq_free_descs(trig->subirq_base, CONFIG_IIO_CONSUMERS_PER_TRIGGER); @@ -467,6 +465,19 @@ struct iio_trigger *iio_trigger_alloc(const char *fmt, ...) } get_device(&trig->dev); } + + return trig; +} + +struct iio_trigger *iio_trigger_alloc(const char *fmt, ...) +{ + struct iio_trigger *trig; + va_list vargs; + + va_start(vargs, fmt); + trig = viio_trigger_alloc(fmt, vargs); + va_end(vargs); + return trig; } EXPORT_SYMBOL(iio_trigger_alloc); @@ -478,6 +489,59 @@ void iio_trigger_free(struct iio_trigger *trig) } EXPORT_SYMBOL(iio_trigger_free); +static void devm_iio_trigger_release(struct device *dev, void *res) +{ + iio_trigger_free(*(struct iio_trigger **)res); +} + +static int devm_iio_trigger_match(struct device *dev, void *res, void *data) +{ + struct iio_trigger **r = res; + + if (!r || !*r) { + WARN_ON(!r || !*r); + return 0; + } + + return *r == data; +} + +struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, + const char *fmt, ...) +{ + struct iio_trigger **ptr, *trig; + va_list vargs; + + ptr = devres_alloc(devm_iio_trigger_release, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return NULL; + + /* use raw alloc_dr for kmalloc caller tracing */ + va_start(vargs, fmt); + trig = viio_trigger_alloc(fmt, vargs); + va_end(vargs); + if (trig) { + *ptr = trig; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return trig; +} +EXPORT_SYMBOL_GPL(devm_iio_trigger_alloc); + +void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig) +{ + int rc; + + rc = devres_release(dev, devm_iio_trigger_release, + devm_iio_trigger_match, iio_trig); + WARN_ON(rc); +} +EXPORT_SYMBOL_GPL(devm_iio_trigger_free); + void iio_device_register_trigger_consumer(struct iio_dev *indio_dev) { indio_dev->groups[indio_dev->groupcounter++] = diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 09ebe0a4d8e6..2103cc32a5fb 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -556,6 +556,35 @@ struct iio_dev *devm_iio_device_alloc(struct device *dev, int sizeof_priv); */ void devm_iio_device_free(struct device *dev, struct iio_dev *indio_dev); +/** + * devm_iio_trigger_alloc - Resource-managed iio_trigger_alloc() + * @dev: Device to allocate iio_trigger for + * @fmt: trigger name format. If it includes format + * specifiers, the additional arguments following + * format are formatted and inserted in the resulting + * string replacing their respective specifiers. + * + * Managed iio_trigger_alloc. iio_trigger allocated with this function is + * automatically freed on driver detach. + * + * If an iio_trigger allocated with this function needs to be freed separately, + * devm_iio_trigger_free() must be used. + * + * RETURNS: + * Pointer to allocated iio_trigger on success, NULL on failure. + */ +struct iio_trigger *devm_iio_trigger_alloc(struct device *dev, + const char *fmt, ...); + +/** + * devm_iio_trigger_free - Resource-managed iio_trigger_free() + * @dev: Device this iio_dev belongs to + * @iio_trig: the iio_trigger associated with the device + * + * Free iio_trigger allocated with devm_iio_trigger_alloc(). + */ +void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); + /** * iio_buffer_enabled() - helper function to test if the buffer is enabled * @indio_dev: IIO device structure for device -- cgit v1.2.3-71-gd317 From b778ae25366e6f3891fe51306f56a3bca211975d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 23 Apr 2013 12:51:11 -0700 Subject: debugobjects: Make debug_object_activate() return status In order to better respond to things like duplicate invocations of call_rcu(), RCU needs to see the status of a call to debug_object_activate(). This would allow RCU to leak the callback in order to avoid adding freelist-reuse mischief to the duplicate invoations. This commit therefore makes debug_object_activate() return status, zero for success and -EINVAL for failure. Signed-off-by: Paul E. McKenney Cc: Mathieu Desnoyers Cc: Sedat Dilek Cc: Davidlohr Bueso Cc: Rik van Riel Cc: Thomas Gleixner Cc: Linus Torvalds Tested-by: Sedat Dilek Reviewed-by: Josh Triplett --- include/linux/debugobjects.h | 6 +++--- lib/debugobjects.c | 20 ++++++++++++++------ 2 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 0e5f5785d9f2..98ffcbd4888e 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -63,7 +63,7 @@ struct debug_obj_descr { extern void debug_object_init (void *addr, struct debug_obj_descr *descr); extern void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr); -extern void debug_object_activate (void *addr, struct debug_obj_descr *descr); +extern int debug_object_activate (void *addr, struct debug_obj_descr *descr); extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr); extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr); extern void debug_object_free (void *addr, struct debug_obj_descr *descr); @@ -85,8 +85,8 @@ static inline void debug_object_init (void *addr, struct debug_obj_descr *descr) { } static inline void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { } -static inline void -debug_object_activate (void *addr, struct debug_obj_descr *descr) { } +static inline int +debug_object_activate (void *addr, struct debug_obj_descr *descr) { return 0; } static inline void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { } static inline void diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 37061ede8b81..bf2c8b1043d8 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -381,19 +381,21 @@ void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) * debug_object_activate - debug checks when an object is activated * @addr: address of the object * @descr: pointer to an object specific debug description structure + * Returns 0 for success, -EINVAL for check failed. */ -void debug_object_activate(void *addr, struct debug_obj_descr *descr) +int debug_object_activate(void *addr, struct debug_obj_descr *descr) { enum debug_obj_state state; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; + int ret; struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; if (!debug_objects_enabled) - return; + return 0; db = get_bucket((unsigned long) addr); @@ -405,23 +407,26 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr) case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_ACTIVE; + ret = 0; break; case ODEBUG_STATE_ACTIVE: debug_print_object(obj, "activate"); state = obj->state; raw_spin_unlock_irqrestore(&db->lock, flags); - debug_object_fixup(descr->fixup_activate, addr, state); - return; + ret = debug_object_fixup(descr->fixup_activate, addr, state); + return ret ? -EINVAL : 0; case ODEBUG_STATE_DESTROYED: debug_print_object(obj, "activate"); + ret = -EINVAL; break; default: + ret = 0; break; } raw_spin_unlock_irqrestore(&db->lock, flags); - return; + return ret; } raw_spin_unlock_irqrestore(&db->lock, flags); @@ -431,8 +436,11 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr) * true or not. */ if (debug_object_fixup(descr->fixup_activate, addr, - ODEBUG_STATE_NOTAVAILABLE)) + ODEBUG_STATE_NOTAVAILABLE)) { debug_print_object(&o, "activate"); + return -EINVAL; + } + return 0; } /** -- cgit v1.2.3-71-gd317 From c34ac00caefbe49d40058ae7200bd58725cebb45 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 28 Jun 2013 10:34:48 -0700 Subject: rculist: list_first_or_null_rcu() should use list_entry_rcu() list_first_or_null() should test whether the list is empty and return pointer to the first entry if not in a RCU safe manner. It's broken in several ways. * It compares __kernel @__ptr with __rcu @__next triggering the following sparse warning. net/core/dev.c:4331:17: error: incompatible types in comparison expression (different address spaces) * It doesn't perform rcu_dereference*() and computes the entry address using container_of() directly from the __rcu pointer which is inconsitent with other rculist interface. As a result, all three in-kernel users - net/core/dev.c, macvlan, cgroup - are buggy. They dereference the pointer w/o going through read barrier. * While ->next dereference passes through list_next_rcu(), the compiler is still free to fetch ->next more than once and thus nullify the "__ptr != __next" condition check. Fix it by making list_first_or_null_rcu() dereference ->next directly using ACCESS_ONCE() and then use list_entry_rcu() on it like other rculist accessors. v2: Paul pointed out that the compiler may fetch the pointer more than once nullifying the condition check. ACCESS_ONCE() added on ->next dereference. v3: Restored () around macro param which was accidentally removed. Spotted by Paul. Signed-off-by: Tejun Heo Reported-by: Fengguang Wu Cc: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Cc: Li Zefan Cc: Patrick McHardy Cc: stable@vger.kernel.org Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rculist.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index f4b1001a4676..4106721c4e5e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -267,8 +267,9 @@ static inline void list_splice_init_rcu(struct list_head *list, */ #define list_first_or_null_rcu(ptr, type, member) \ ({struct list_head *__ptr = (ptr); \ - struct list_head __rcu *__next = list_next_rcu(__ptr); \ - likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \ + struct list_head *__next = ACCESS_ONCE(__ptr->next); \ + likely(__ptr != __next) ? \ + list_entry_rcu(__next, type, member) : NULL; \ }) /** -- cgit v1.2.3-71-gd317 From feed66ed26a53e700ca02ce1744fed7d0c647292 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 9 May 2013 08:55:54 -0700 Subject: rcu: Eliminate unused APIs intended for adaptive ticks The rcu_user_enter_after_irq() and rcu_user_exit_after_irq() functions were intended for use by adaptive ticks, but changes in implementation have rendered them unnecessary. This commit therefore removes them. Reported-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 4 ---- kernel/rcutree.c | 43 ------------------------------------------- 2 files changed, 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0c38abbe6e35..30bea9c25735 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -229,13 +229,9 @@ extern void rcu_irq_exit(void); #ifdef CONFIG_RCU_USER_QS extern void rcu_user_enter(void); extern void rcu_user_exit(void); -extern void rcu_user_enter_after_irq(void); -extern void rcu_user_exit_after_irq(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } -static inline void rcu_user_enter_after_irq(void) { } -static inline void rcu_user_exit_after_irq(void) { } static inline void rcu_user_hooks_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* CONFIG_RCU_USER_QS */ diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 338f1d1c1c66..8807019138c6 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -444,27 +444,6 @@ void rcu_user_enter(void) { rcu_eqs_enter(1); } - -/** - * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace - * after the current irq returns. - * - * This is similar to rcu_user_enter() but in the context of a non-nesting - * irq. After this call, RCU enters into idle mode when the interrupt - * returns. - */ -void rcu_user_enter_after_irq(void) -{ - unsigned long flags; - struct rcu_dynticks *rdtp; - - local_irq_save(flags); - rdtp = &__get_cpu_var(rcu_dynticks); - /* Ensure this irq is interrupting a non-idle RCU state. */ - WARN_ON_ONCE(!(rdtp->dynticks_nesting & DYNTICK_TASK_MASK)); - rdtp->dynticks_nesting = 1; - local_irq_restore(flags); -} #endif /* CONFIG_RCU_USER_QS */ /** @@ -581,28 +560,6 @@ void rcu_user_exit(void) { rcu_eqs_exit(1); } - -/** - * rcu_user_exit_after_irq - inform RCU that we won't resume to userspace - * idle mode after the current non-nesting irq returns. - * - * This is similar to rcu_user_exit() but in the context of an irq. - * This is called when the irq has interrupted a userspace RCU idle mode - * context. When the current non-nesting interrupt returns after this call, - * the CPU won't restore the RCU idle mode. - */ -void rcu_user_exit_after_irq(void) -{ - unsigned long flags; - struct rcu_dynticks *rdtp; - - local_irq_save(flags); - rdtp = &__get_cpu_var(rcu_dynticks); - /* Ensure we are interrupting an RCU idle mode. */ - WARN_ON_ONCE(rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK); - rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE; - local_irq_restore(flags); -} #endif /* CONFIG_RCU_USER_QS */ /** -- cgit v1.2.3-71-gd317 From 1cb650b91ba582f6737457b7d22e368585596d2c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 19 Aug 2013 10:05:24 +0800 Subject: cgroup: change cgroup_from_id() to css_from_id() Now we want cgroup core to always provide the css to use to the subsystems, so change this API to css_from_id(). Uninline css_from_id(), because it's getting bigger and cgroup_css() has been unexported. While at it, remove the #ifdef, and shuffle the order of the args. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 20 ++------------------ kernel/cgroup.c | 22 ++++++++++++++++++++++ 2 files changed, 24 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c24bd0b9f93a..b685955d4b29 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -741,27 +741,11 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } -/** - * cgroup_from_id - lookup cgroup by id - * @ss: cgroup subsys to be looked into - * @id: the cgroup id - * - * Returns the cgroup if there's valid one with @id, otherwise returns NULL. - * Should be called under rcu_read_lock(). - */ -static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id) -{ -#ifdef CONFIG_PROVE_RCU - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&cgroup_mutex), - "cgroup_from_id() needs proper protection"); -#endif - return idr_find(&ss->root->cgroup_idr, id); -} - struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); + /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b69b572131e5..ff7d642a070a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -5717,6 +5717,28 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id) return css ? css : ERR_PTR(-ENOENT); } +/** + * css_from_id - lookup css by id + * @id: the cgroup id + * @ss: cgroup subsys to be looked into + * + * Returns the css if there's valid one with @id, otherwise returns NULL. + * Should be called under rcu_read_lock(). + */ +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) +{ + struct cgroup *cgrp; + + rcu_lockdep_assert(rcu_read_lock_held() || + lockdep_is_held(&cgroup_mutex), + "css_from_id() needs proper protection"); + + cgrp = idr_find(&ss->root->cgroup_idr, id); + if (cgrp) + return cgroup_css(cgrp, ss->subsys_id); + return NULL; +} + #ifdef CONFIG_CGROUP_DEBUG static struct cgroup_subsys_state * debug_css_alloc(struct cgroup_subsys_state *parent_css) -- cgit v1.2.3-71-gd317 From b3b515bbd689ba3937cac2dd3fc55057f8c50329 Mon Sep 17 00:00:00 2001 From: Aruna Balakrishnaiah Date: Fri, 16 Aug 2013 13:52:47 -0700 Subject: pstore: Add new argument 'compressed' in pstore write callback Addition of new argument 'compressed' in the write call back will help the backend to know if the data passed from pstore is compressed or not (In case where compression fails.). If compressed, the backend can add a tag indicating the data is compressed while writing to persistent store. Signed-off-by: Aruna Balakrishnaiah Reviewed-by: Kees Cook Signed-off-by: Tony Luck --- arch/powerpc/platforms/pseries/nvram.c | 4 ++-- drivers/acpi/apei/erst.c | 4 ++-- drivers/firmware/efi/efi-pstore.c | 2 +- fs/pstore/platform.c | 7 ++++--- fs/pstore/ram.c | 2 +- include/linux/pstore.h | 4 ++-- 6 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index b966458e9b21..dbe5dadb5fcc 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -554,7 +554,7 @@ static int nvram_pstore_open(struct pstore_info *psi) * @part: pstore writes data to registered buffer in parts, * part number will indicate the same. * @count: Indicates oops count - * @hsize: Size of header added by pstore + * @compressed: Flag to indicate the log is compressed * @size: number of bytes written to the registered buffer * @psi: registered pstore_info structure * @@ -565,7 +565,7 @@ static int nvram_pstore_open(struct pstore_info *psi) static int nvram_pstore_write(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, - size_t hsize, size_t size, + bool compressed, size_t size, struct pstore_info *psi) { int rc; diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 6885809abcd8..bcdf8cefcb9e 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -937,7 +937,7 @@ static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, struct pstore_info *psi); static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, size_t hsize, + u64 *id, unsigned int part, int count, bool compressed, size_t size, struct pstore_info *psi); static int erst_clearer(enum pstore_type_id type, u64 id, int count, struct timespec time, struct pstore_info *psi); @@ -1057,7 +1057,7 @@ out: } static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, size_t hsize, + u64 *id, unsigned int part, int count, bool compressed, size_t size, struct pstore_info *psi) { struct cper_pstore_record *rcd = (struct cper_pstore_record *) diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index 73de5a9c2247..fab6892f7053 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -103,7 +103,7 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, static int efi_pstore_write(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, int count, size_t hsize, size_t size, + unsigned int part, int count, bool compressed, size_t size, struct pstore_info *psi) { char name[DUMP_NAME_LEN]; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 422962ae9fc2..20fa686f80fa 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -149,6 +149,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, unsigned long size; int hsize; size_t len; + bool compressed = false; dst = psinfo->buf; hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); @@ -159,7 +160,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, break; ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - oopscount, hsize, hsize + len, psinfo); + oopscount, compressed, hsize + len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; @@ -221,10 +222,10 @@ static void pstore_register_console(void) {} static int pstore_write_compat(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, - size_t hsize, size_t size, + bool compressed, size_t size, struct pstore_info *psi) { - return psi->write_buf(type, reason, id, part, psinfo->buf, hsize, + return psi->write_buf(type, reason, id, part, psinfo->buf, compressed, size, psi); } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index a6119f9469e2..fe7188f742b7 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -196,7 +196,7 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, const char *buf, - size_t hsize, size_t size, + bool compressed, size_t size, struct pstore_info *psi) { struct ramoops_context *cxt = psi->data; diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 4aa80ba830a2..abfca4f59422 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -58,11 +58,11 @@ struct pstore_info { struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, int count, size_t hsize, + unsigned int part, int count, bool compressed, size_t size, struct pstore_info *psi); int (*write_buf)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, const char *buf, size_t hsize, + unsigned int part, const char *buf, bool compressed, size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, int count, struct timespec time, -- cgit v1.2.3-71-gd317 From 9a4e1398208d147a9240731a1f8cfe7d8cc4c553 Mon Sep 17 00:00:00 2001 From: Aruna Balakrishnaiah Date: Fri, 16 Aug 2013 13:53:19 -0700 Subject: pstore: Introduce new argument 'compressed' in the read callback Backends will set the flag 'compressed' after reading the log from persistent store to indicate the data being returned to pstore is compressed or not. Signed-off-by: Aruna Balakrishnaiah Reviewed-by: Kees Cook Signed-off-by: Tony Luck --- arch/powerpc/platforms/pseries/nvram.c | 2 +- drivers/acpi/apei/erst.c | 4 ++-- drivers/firmware/efi/efi-pstore.c | 3 ++- fs/pstore/platform.c | 4 +++- fs/pstore/ram.c | 3 ++- include/linux/pstore.h | 2 +- 6 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index dbe5dadb5fcc..6c4dc52ac0b5 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -598,7 +598,7 @@ static int nvram_pstore_write(enum pstore_type_id type, */ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi) + bool *compressed, struct pstore_info *psi) { struct oops_log_info *oops_hdr; unsigned int err_type, id_no, size = 0; diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index bcdf8cefcb9e..b412e9137e36 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -935,7 +935,7 @@ static int erst_open_pstore(struct pstore_info *psi); static int erst_close_pstore(struct pstore_info *psi); static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi); + bool *compressed, struct pstore_info *psi); static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, bool compressed, size_t size, struct pstore_info *psi); @@ -991,7 +991,7 @@ static int erst_close_pstore(struct pstore_info *psi) static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi) + bool *compressed, struct pstore_info *psi) { int rc; ssize_t len = 0; diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index fab6892f7053..9a5425f3f885 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -87,7 +87,8 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data) static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *timespec, - char **buf, struct pstore_info *psi) + char **buf, bool *compressed, + struct pstore_info *psi) { struct pstore_read_data data; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 56218cb35267..6418eb77d64b 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -428,6 +428,7 @@ void pstore_get_records(int quiet) enum pstore_type_id type; struct timespec time; int failed = 0, rc; + bool compressed; if (!psi) return; @@ -436,7 +437,8 @@ void pstore_get_records(int quiet) if (psi->open && psi->open(psi)) goto out; - while ((size = psi->read(&id, &type, &count, &time, &buf, psi)) > 0) { + while ((size = psi->read(&id, &type, &count, &time, &buf, &compressed, + psi)) > 0) { rc = pstore_mkfile(type, psi->name, id, count, buf, (size_t)size, time, psi); kfree(buf); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index fe7188f742b7..292722327811 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -133,7 +133,8 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, - char **buf, struct pstore_info *psi) + char **buf, bool *compressed, + struct pstore_info *psi) { ssize_t size; ssize_t ecc_notice_size; diff --git a/include/linux/pstore.h b/include/linux/pstore.h index abfca4f59422..abd437d0a8a7 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -55,7 +55,7 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi); + bool *compressed, struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, bool compressed, -- cgit v1.2.3-71-gd317 From bd0eae4e1cd5c4ff7c2a9ebcb3e78ea4631251ef Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 24 Jul 2013 15:05:19 -0700 Subject: PPS: convert class code to use dev_groups The dev_attrs field of struct class is going away soon, dev_groups should be used instead. This converts the pps class code to use the correct field. Cc: Rodolfo Giometti Signed-off-by: Greg Kroah-Hartman --- drivers/pps/pps.c | 2 +- drivers/pps/sysfs.c | 55 +++++++++++++++++++++++++++++----------------- include/linux/pps_kernel.h | 2 +- 3 files changed, 37 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 7173e3ad475d..2f07cd615665 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -406,7 +406,7 @@ static int __init pps_init(void) pr_err("failed to allocate class\n"); return PTR_ERR(pps_class); } - pps_class->dev_attrs = pps_attrs; + pps_class->dev_groups = pps_groups; err = alloc_chrdev_region(&pps_devt, 0, PPS_MAX_SOURCES, "pps"); if (err < 0) { diff --git a/drivers/pps/sysfs.c b/drivers/pps/sysfs.c index ef0978c71eee..aefb75d67094 100644 --- a/drivers/pps/sysfs.c +++ b/drivers/pps/sysfs.c @@ -29,8 +29,8 @@ * Attribute functions */ -static ssize_t pps_show_assert(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t assert_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct pps_device *pps = dev_get_drvdata(dev); @@ -41,9 +41,10 @@ static ssize_t pps_show_assert(struct device *dev, (long long) pps->assert_tu.sec, pps->assert_tu.nsec, pps->assert_sequence); } +static DEVICE_ATTR_RO(assert); -static ssize_t pps_show_clear(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t clear_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct pps_device *pps = dev_get_drvdata(dev); @@ -54,45 +55,59 @@ static ssize_t pps_show_clear(struct device *dev, (long long) pps->clear_tu.sec, pps->clear_tu.nsec, pps->clear_sequence); } +static DEVICE_ATTR_RO(clear); -static ssize_t pps_show_mode(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t mode_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct pps_device *pps = dev_get_drvdata(dev); return sprintf(buf, "%4x\n", pps->info.mode); } +static DEVICE_ATTR_RO(mode); -static ssize_t pps_show_echo(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t echo_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct pps_device *pps = dev_get_drvdata(dev); return sprintf(buf, "%d\n", !!pps->info.echo); } +static DEVICE_ATTR_RO(echo); -static ssize_t pps_show_name(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t name_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct pps_device *pps = dev_get_drvdata(dev); return sprintf(buf, "%s\n", pps->info.name); } +static DEVICE_ATTR_RO(name); -static ssize_t pps_show_path(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t path_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct pps_device *pps = dev_get_drvdata(dev); return sprintf(buf, "%s\n", pps->info.path); } +static DEVICE_ATTR_RO(path); + +static struct attribute *pps_attrs[] = { + &dev_attr_assert.attr, + &dev_attr_clear.attr, + &dev_attr_mode.attr, + &dev_attr_echo.attr, + &dev_attr_name.attr, + &dev_attr_path.attr, + NULL, +}; + +static const struct attribute_group pps_group = { + .attrs = pps_attrs, +}; -struct device_attribute pps_attrs[] = { - __ATTR(assert, S_IRUGO, pps_show_assert, NULL), - __ATTR(clear, S_IRUGO, pps_show_clear, NULL), - __ATTR(mode, S_IRUGO, pps_show_mode, NULL), - __ATTR(echo, S_IRUGO, pps_show_echo, NULL), - __ATTR(name, S_IRUGO, pps_show_name, NULL), - __ATTR(path, S_IRUGO, pps_show_path, NULL), - __ATTR_NULL, +const struct attribute_group *pps_groups[] = { + &pps_group, + NULL, }; diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 7db3eb93a079..1d2cd21242e8 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -80,7 +80,7 @@ struct pps_device { * Global variables */ -extern struct device_attribute pps_attrs[]; +extern const struct attribute_group *pps_groups[]; /* * Internal functions. -- cgit v1.2.3-71-gd317 From f46078cfcd77fa5165bf849f5e568a7ac5fa569c Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 16 Aug 2013 13:30:07 +0200 Subject: ipv6: drop packets with multiple fragmentation headers It is not allowed for an ipv6 packet to contain multiple fragmentation headers. So discard packets which were already reassembled by fragmentation logic and send back a parameter problem icmp. The updates for RFC 6980 will come in later, I have to do a bit more research here. Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + net/ipv6/reassembly.c | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 850e95bc766c..b8b7dc755752 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -101,6 +101,7 @@ struct inet6_skb_parm { #define IP6SKB_FORWARDED 2 #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 +#define IP6SKB_FRAGMENTED 16 }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 790d9f4b8b0b..1aeb473b2cc6 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -490,6 +490,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, ipv6_hdr(head)->payload_len = htons(payload_len); ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); IP6CB(head)->nhoff = nhoff; + IP6CB(head)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (head->ip_summed == CHECKSUM_COMPLETE) @@ -524,6 +525,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct net *net = dev_net(skb_dst(skb)->dev); int evicted; + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) + goto fail_hdr; + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ @@ -544,6 +548,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS); IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; return 1; } -- cgit v1.2.3-71-gd317 From 5a581b367b5df0531265311fc681c2abd377e5e6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 27 Jul 2013 03:53:54 -0700 Subject: jiffies: Avoid undefined behavior from signed overflow According to the C standard 3.4.3p3, overflow of a signed integer results in undefined behavior. This commit therefore changes the definitions of time_after(), time_after_eq(), time_after64(), and time_after_eq64() to avoid this undefined behavior. The trick is that the subtraction is done using unsigned arithmetic, which according to 6.2.5p9 cannot overflow because it is defined as modulo arithmetic. This has the added (though admittedly quite small) benefit of shortening four lines of code by four characters each. Note that the C standard considers the cast from unsigned to signed to be implementation-defined, see 6.3.1.3p3. However, on a two's-complement system, an implementation that defines anything other than a reinterpretation of the bits is free to come to me, and I will be happy to act as a witness for its being committed to an insane asylum. (Although I have nothing against saturating arithmetic or signals in some cases, these things really should not be the default when compiling an operating-system kernel.) Signed-off-by: Paul E. McKenney Cc: John Stultz Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Ingo Molnar Cc: Linus Torvalds Cc: Eric Dumazet Cc: Kevin Easton [ paulmck: Included time_after64() and time_after_eq64(), as suggested by Eric Dumazet, also fixed commit message.] Reviewed-by: Josh Triplett --- include/linux/jiffies.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 97ba4e78a37e..d235e88cfd7c 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -101,13 +101,13 @@ static inline u64 get_jiffies_64(void) #define time_after(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ - ((long)(b) - (long)(a) < 0)) + ((long)((b) - (a)) < 0)) #define time_before(a,b) time_after(b,a) #define time_after_eq(a,b) \ (typecheck(unsigned long, a) && \ typecheck(unsigned long, b) && \ - ((long)(a) - (long)(b) >= 0)) + ((long)((a) - (b)) >= 0)) #define time_before_eq(a,b) time_after_eq(b,a) /* @@ -130,13 +130,13 @@ static inline u64 get_jiffies_64(void) #define time_after64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ - ((__s64)(b) - (__s64)(a) < 0)) + ((__s64)((b) - (a)) < 0)) #define time_before64(a,b) time_after64(b,a) #define time_after_eq64(a,b) \ (typecheck(__u64, a) && \ typecheck(__u64, b) && \ - ((__s64)(a) - (__s64)(b) >= 0)) + ((__s64)((a) - (b)) >= 0)) #define time_before_eq64(a,b) time_after_eq64(b,a) #define time_in_range64(a, b, c) \ -- cgit v1.2.3-71-gd317 From 6853152689d47b4a1eb9f38a25a18f3f8b7a60de Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 20 Aug 2013 16:48:54 -0700 Subject: sysfs.h: fix __BIN_ATTR_RW() __BIN_ATTR_RW() wasn't passing in the _size field. As it would break the build if this macro was ever used, it's obvious no one had ever tried to use it before. Fix it so that it can be used. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 9e8a9b555ad6..0f04958623d7 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -153,7 +153,7 @@ struct bin_attribute { #define __BIN_ATTR_RW(_name, _size) __BIN_ATTR(_name, \ (S_IWUSR | S_IRUGO), _name##_read, \ - _name##_write) + _name##_write, _size) #define __BIN_ATTR_NULL __ATTR_NULL -- cgit v1.2.3-71-gd317 From 183912d352a242a276a7877852f107459a13aff9 Mon Sep 17 00:00:00 2001 From: Sudeep KarkadaNagesha Date: Thu, 15 Aug 2013 14:01:40 +0100 Subject: of: move of_get_cpu_node implementation to DT core library This patch moves the generalized implementation of of_get_cpu_node from PowerPC to DT core library, thereby adding support for retrieving cpu node for a given logical cpu index on any architecture. The CPU subsystem can now use this function to assign of_node in the cpu device while registering CPUs. It is recommended to use these helper function only in pre-SMP/early initialisation stages to retrieve CPU device node pointers in logical ordering. Once the cpu devices are registered, it can be retrieved easily from cpu device of_node which avoids unnecessary parsing and matching. Cc: Benjamin Herrenschmidt Cc: Grant Likely Acked-by: Rob Herring Signed-off-by: Sudeep KarkadaNagesha --- arch/powerpc/include/asm/prom.h | 3 -- arch/powerpc/kernel/prom.c | 57 ------------------------- drivers/of/base.c | 95 +++++++++++++++++++++++++++++++++++++++++ include/linux/cpu.h | 1 + include/linux/of.h | 7 +++ 5 files changed, 103 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index bc2da154f68b..ac204e022922 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -43,9 +43,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, extern void kdump_move_device_tree(void); -/* CPU OF node matching */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); - /* cache lookup */ struct device_node *of_find_next_cache_node(struct device_node *np); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f7b8c0be982e..1c14cd4a5e05 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -870,63 +870,6 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id) return (int)phys_id == get_hard_smp_processor_id(cpu); } -static bool __of_find_n_match_cpu_property(struct device_node *cpun, - const char *prop_name, int cpu, unsigned int *thread) -{ - const __be32 *cell; - int ac, prop_len, tid; - u64 hwid; - - ac = of_n_addr_cells(cpun); - cell = of_get_property(cpun, prop_name, &prop_len); - if (!cell) - return false; - prop_len /= sizeof(*cell); - for (tid = 0; tid < prop_len; tid++) { - hwid = of_read_number(cell, ac); - if (arch_match_cpu_phys_id(cpu, hwid)) { - if (thread) - *thread = tid; - return true; - } - cell += ac; - } - return false; -} - -/* Find the device node for a given logical cpu number, also returns the cpu - * local thread number (index in ibm,interrupt-server#s) if relevant and - * asked for (non NULL) - */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) -{ - struct device_node *cpun, *cpus; - - cpus = of_find_node_by_path("/cpus"); - if (!cpus) { - pr_warn("Missing cpus node, bailing out\n"); - return NULL; - } - - for_each_child_of_node(cpus, cpun) { - if (of_node_cmp(cpun->type, "cpu")) - continue; - - /* Check for non-standard "ibm,ppc-interrupt-server#s" property - * for thread ids on PowerPC. If it doesn't exist fallback to - * standard "reg" property. - */ - if (__of_find_n_match_cpu_property(cpun, - "ibm,ppc-interrupt-server#s", cpu, thread)) - return cpun; - - if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread)) - return cpun; - } - return NULL; -} -EXPORT_SYMBOL(of_get_cpu_node); - #if defined(CONFIG_DEBUG_FS) && defined(DEBUG) static struct debugfs_blob_wrapper flat_dt_blob; diff --git a/drivers/of/base.c b/drivers/of/base.c index 5c5427918eb2..605afa9fbe5e 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -18,6 +18,7 @@ * 2 of the License, or (at your option) any later version. */ #include +#include #include #include #include @@ -230,6 +231,100 @@ const void *of_get_property(const struct device_node *np, const char *name, } EXPORT_SYMBOL(of_get_property); +/* + * arch_match_cpu_phys_id - Match the given logical CPU and physical id + * + * @cpu: logical cpu index of a core/thread + * @phys_id: physical identifier of a core/thread + * + * CPU logical to physical index mapping is architecture specific. + * However this __weak function provides a default match of physical + * id to logical cpu index. phys_id provided here is usually values read + * from the device tree which must match the hardware internal registers. + * + * Returns true if the physical identifier and the logical cpu index + * correspond to the same core/thread, false otherwise. + */ +bool __weak arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return (u32)phys_id == cpu; +} + +/** + * Checks if the given "prop_name" property holds the physical id of the + * core/thread corresponding to the logical cpu 'cpu'. If 'thread' is not + * NULL, local thread number within the core is returned in it. + */ +static bool __of_find_n_match_cpu_property(struct device_node *cpun, + const char *prop_name, int cpu, unsigned int *thread) +{ + const __be32 *cell; + int ac, prop_len, tid; + u64 hwid; + + ac = of_n_addr_cells(cpun); + cell = of_get_property(cpun, prop_name, &prop_len); + if (!cell) + return false; + prop_len /= sizeof(*cell); + for (tid = 0; tid < prop_len; tid++) { + hwid = of_read_number(cell, ac); + if (arch_match_cpu_phys_id(cpu, hwid)) { + if (thread) + *thread = tid; + return true; + } + cell += ac; + } + return false; +} + +/** + * of_get_cpu_node - Get device node associated with the given logical CPU + * + * @cpu: CPU number(logical index) for which device node is required + * @thread: if not NULL, local thread number within the physical core is + * returned + * + * The main purpose of this function is to retrieve the device node for the + * given logical CPU index. It should be used to initialize the of_node in + * cpu device. Once of_node in cpu device is populated, all the further + * references can use that instead. + * + * CPU logical to physical index mapping is architecture specific and is built + * before booting secondary cores. This function uses arch_match_cpu_phys_id + * which can be overridden by architecture specific implementation. + * + * Returns a node pointer for the logical cpu if found, else NULL. + */ +struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) +{ + struct device_node *cpun, *cpus; + + cpus = of_find_node_by_path("/cpus"); + if (!cpus) { + pr_warn("Missing cpus node, bailing out\n"); + return NULL; + } + + for_each_child_of_node(cpus, cpun) { + if (of_node_cmp(cpun->type, "cpu")) + continue; + /* Check for non-standard "ibm,ppc-interrupt-server#s" property + * for thread ids on PowerPC. If it doesn't exist fallback to + * standard "reg" property. + */ + if (IS_ENABLED(CONFIG_PPC) && + __of_find_n_match_cpu_property(cpun, + "ibm,ppc-interrupt-server#s", cpu, thread)) + return cpun; + if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread)) + return cpun; + } + return NULL; +} +EXPORT_SYMBOL(of_get_cpu_node); + /** Checks if the given "compat" string matches one of the strings in * the device's "compatible" property */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ab0eade73039..3dfed2b9ae2e 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -28,6 +28,7 @@ struct cpu { extern int register_cpu(struct cpu *cpu, int num); extern struct device *get_cpu_device(unsigned cpu); extern bool cpu_is_hotpluggable(unsigned cpu); +extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id); extern int cpu_add_dev_attr(struct device_attribute *attr); extern void cpu_remove_dev_attr(struct device_attribute *attr); diff --git a/include/linux/of.h b/include/linux/of.h index 1fd08ca23106..c0bb2f188048 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -266,6 +266,7 @@ extern int of_device_is_available(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); +extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) @@ -459,6 +460,12 @@ static inline const void *of_get_property(const struct device_node *node, return NULL; } +static inline struct device_node *of_get_cpu_node(int cpu, + unsigned int *thread) +{ + return NULL; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { -- cgit v1.2.3-71-gd317 From bd00860e960e52658cebfd65eeb4748ed6ff039f Mon Sep 17 00:00:00 2001 From: Sudeep KarkadaNagesha Date: Thu, 18 Jul 2013 11:22:04 +0100 Subject: of/device: add helper to get cpu device node from logical cpu index Multiple drivers need to get the cpu device node from the cpu logical index and then access the of_node. This patch adds helper function to fetch the device node directly. Acked-by: Rob Herring Signed-off-by: Sudeep KarkadaNagesha --- include/linux/of_device.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 9d27475feec1..82ce324fdce7 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -1,6 +1,7 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H +#include #include #include /* temporary until merge */ @@ -43,6 +44,15 @@ static inline void of_device_node_put(struct device *dev) of_node_put(dev->of_node); } +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + struct device *cpu_dev; + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return NULL; + return of_node_get(cpu_dev->of_node); +} + #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -67,6 +77,11 @@ static inline const struct of_device_id *of_match_device( { return NULL; } + +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + return NULL; +} #endif /* CONFIG_OF */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3-71-gd317 From 37a7bd6255b415afe197489b5cd1f9568a7ae058 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 20 Aug 2013 12:13:01 -0500 Subject: drivers: base: reduce add_memory_section() for boot-time only Now that add_memory_section() is only called from boot time, reduce the logic and remove the enum. Signed-off-by: Seth Jennings Signed-off-by: Greg Kroah-Hartman --- drivers/base/memory.c | 41 ++++++++++++++--------------------------- include/linux/memory.h | 1 - 2 files changed, 14 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 2e9a68c64679..a9e9c0902cce 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -602,40 +602,29 @@ static int init_memory_block(struct memory_block **memory, return ret; } -static int add_memory_section(int nid, struct mem_section *section, - struct memory_block **mem_p, - unsigned long state, enum mem_add_context context) +static int add_memory_section(struct mem_section *section, + struct memory_block **mem_p) { struct memory_block *mem = NULL; int scn_nr = __section_nr(section); int ret = 0; - if (context == BOOT) { - /* same memory block ? */ - if (mem_p && *mem_p) - if (scn_nr >= (*mem_p)->start_section_nr && - scn_nr <= (*mem_p)->end_section_nr) { - mem = *mem_p; - get_device(&mem->dev); - } - } else - mem = find_memory_block(section); + if (mem_p && *mem_p) { + if (scn_nr >= (*mem_p)->start_section_nr && + scn_nr <= (*mem_p)->end_section_nr) { + mem = *mem_p; + get_device(&mem->dev); + } + } if (mem) { mem->section_count++; put_device(&mem->dev); } else { - ret = init_memory_block(&mem, section, state); + ret = init_memory_block(&mem, section, MEM_ONLINE); /* store memory_block pointer for next loop */ - if (!ret && context == BOOT) - if (mem_p) - *mem_p = mem; - } - - if (!ret) { - if (context == HOTPLUG && - mem->section_count == sections_per_block) - ret = register_mem_sect_under_node(mem, nid); + if (!ret && mem_p) + *mem_p = mem; } return ret; @@ -764,10 +753,8 @@ int __init memory_dev_init(void) if (!present_section_nr(i)) continue; /* don't need to reuse memory_block if only one per block */ - err = add_memory_section(0, __nr_to_section(i), - (sections_per_block == 1) ? NULL : &mem, - MEM_ONLINE, - BOOT); + err = add_memory_section(__nr_to_section(i), + (sections_per_block == 1) ? NULL : &mem); if (!ret) ret = err; } diff --git a/include/linux/memory.h b/include/linux/memory.h index 85c31a8e2904..4c89fb0c8f4c 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -125,7 +125,6 @@ extern struct memory_block *find_memory_block_hinted(struct mem_section *, struct memory_block *); extern struct memory_block *find_memory_block(struct mem_section *); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Tue, 20 Aug 2013 16:05:05 -0500 Subject: drivers: base: use standard device online/offline for state change There are two ways to set the online/offline state for a memory block: echo 0|1 > online and echo online|online_kernel|online_movable|offline > state. The state attribute can online a memory block with extra data, the "online type", where the online attribute uses a default online type of ONLINE_KEEP, same as echo online > state. Currently there is a state_mutex that provides consistency between the memory block state and the underlying memory. The problem is that this code does a lot of things that the common device layer can do for us, such as the serialization of the online/offline handlers using the device lock, setting the dev->offline field, and calling kobject_uevent(). This patch refactors the online/offline code to allow the common device_[online|offline] functions to be used. The result is a simpler and more common code path for the two state setting mechanisms. It also removes the state_mutex from the struct memory_block as the memory block device lock provides the state consistency. No functional change is intended by this patch. Signed-off-by: Seth Jennings Signed-off-by: Greg Kroah-Hartman --- drivers/base/memory.c | 127 +++++++++++++++++++++---------------------------- include/linux/memory.h | 13 ++--- 2 files changed, 58 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 0187fe483d7c..2a38cd2da2e5 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -261,9 +260,8 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t return ret; } -static int __memory_block_change_state(struct memory_block *mem, - unsigned long to_state, unsigned long from_state_req, - int online_type) +static int memory_block_change_state(struct memory_block *mem, + unsigned long to_state, unsigned long from_state_req) { int ret = 0; @@ -273,105 +271,91 @@ static int __memory_block_change_state(struct memory_block *mem, if (to_state == MEM_OFFLINE) mem->state = MEM_GOING_OFFLINE; - ret = memory_block_action(mem->start_section_nr, to_state, online_type); + ret = memory_block_action(mem->start_section_nr, to_state, + mem->online_type); + mem->state = ret ? from_state_req : to_state; + return ret; } +/* The device lock serializes operations on memory_subsys_[online|offline] */ static int memory_subsys_online(struct device *dev) { struct memory_block *mem = container_of(dev, struct memory_block, dev); int ret; - mutex_lock(&mem->state_mutex); + if (mem->state == MEM_ONLINE) + return 0; - ret = mem->state == MEM_ONLINE ? 0 : - __memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, - ONLINE_KEEP); + /* + * If we are called from store_mem_state(), online_type will be + * set >= 0 Otherwise we were called from the device online + * attribute and need to set the online_type. + */ + if (mem->online_type < 0) + mem->online_type = ONLINE_KEEP; + + ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); + + /* clear online_type */ + mem->online_type = -1; - mutex_unlock(&mem->state_mutex); return ret; } static int memory_subsys_offline(struct device *dev) { struct memory_block *mem = container_of(dev, struct memory_block, dev); - int ret; - mutex_lock(&mem->state_mutex); - - ret = mem->state == MEM_OFFLINE ? 0 : - __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1); - - mutex_unlock(&mem->state_mutex); - return ret; -} + if (mem->state == MEM_OFFLINE) + return 0; -static int __memory_block_change_state_uevent(struct memory_block *mem, - unsigned long to_state, unsigned long from_state_req, - int online_type) -{ - int ret = __memory_block_change_state(mem, to_state, from_state_req, - online_type); - if (!ret) { - switch (mem->state) { - case MEM_OFFLINE: - kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE); - break; - case MEM_ONLINE: - kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE); - break; - default: - break; - } - } - return ret; + return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); } -static int memory_block_change_state(struct memory_block *mem, - unsigned long to_state, unsigned long from_state_req, - int online_type) -{ - int ret; - - mutex_lock(&mem->state_mutex); - ret = __memory_block_change_state_uevent(mem, to_state, from_state_req, - online_type); - mutex_unlock(&mem->state_mutex); - - return ret; -} static ssize_t store_mem_state(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct memory_block *mem; - bool offline; - int ret = -EINVAL; + int ret, online_type; mem = container_of(dev, struct memory_block, dev); lock_device_hotplug(); - if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) { - offline = false; - ret = memory_block_change_state(mem, MEM_ONLINE, - MEM_OFFLINE, ONLINE_KERNEL); - } else if (!strncmp(buf, "online_movable", min_t(int, count, 14))) { - offline = false; - ret = memory_block_change_state(mem, MEM_ONLINE, - MEM_OFFLINE, ONLINE_MOVABLE); - } else if (!strncmp(buf, "online", min_t(int, count, 6))) { - offline = false; - ret = memory_block_change_state(mem, MEM_ONLINE, - MEM_OFFLINE, ONLINE_KEEP); - } else if(!strncmp(buf, "offline", min_t(int, count, 7))) { - offline = true; - ret = memory_block_change_state(mem, MEM_OFFLINE, - MEM_ONLINE, -1); + if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) + online_type = ONLINE_KERNEL; + else if (!strncmp(buf, "online_movable", min_t(int, count, 14))) + online_type = ONLINE_MOVABLE; + else if (!strncmp(buf, "online", min_t(int, count, 6))) + online_type = ONLINE_KEEP; + else if (!strncmp(buf, "offline", min_t(int, count, 7))) + online_type = -1; + else + return -EINVAL; + + switch (online_type) { + case ONLINE_KERNEL: + case ONLINE_MOVABLE: + case ONLINE_KEEP: + /* + * mem->online_type is not protected so there can be a + * race here. However, when racing online, the first + * will succeed and the second will just return as the + * block will already be online. The online type + * could be either one, but that is expected. + */ + mem->online_type = online_type; + ret = device_online(&mem->dev); + break; + case -1: + ret = device_offline(&mem->dev); + break; + default: + ret = -EINVAL; /* should never happen */ } - if (!ret) - dev->offline = offline; unlock_device_hotplug(); @@ -592,7 +576,6 @@ static int init_memory_block(struct memory_block **memory, mem->end_section_nr = mem->start_section_nr + sections_per_block - 1; mem->state = state; mem->section_count++; - mutex_init(&mem->state_mutex); start_pfn = section_nr_to_pfn(mem->start_section_nr); mem->phys_device = arch_get_memory_phys_device(start_pfn); diff --git a/include/linux/memory.h b/include/linux/memory.h index 4c89fb0c8f4c..9a6bbf76452d 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -25,16 +25,9 @@ struct memory_block { unsigned long start_section_nr; unsigned long end_section_nr; - unsigned long state; - int section_count; - - /* - * This serializes all state change requests. It isn't - * held during creation because the control files are - * created long after the critical areas during - * initialization. - */ - struct mutex state_mutex; + unsigned long state; /* serialized by the dev->lock */ + int section_count; /* serialized by mem_sysfs_mutex */ + int online_type; /* for passing data to online routine */ int phys_device; /* to which fru does this belong? */ void *hw; /* optional pointer to fw/hw data */ int (*phys_callback)(struct memory_block *); -- cgit v1.2.3-71-gd317 From 3e9b2bae8369661070622d05570cbcdfa01770e6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Aug 2013 13:47:50 -0700 Subject: sysfs: add sysfs_create/remove_groups() These functions are being open-coded in 3 different places in the driver core, and other driver subsystems will want to start doing this as well, so move it to the sysfs core to keep it all in one place, where we know it is written properly. Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 23 ++-------------------- drivers/base/core.c | 22 ++------------------- drivers/base/driver.c | 22 ++------------------- fs/sysfs/group.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sysfs.h | 4 ++++ 5 files changed, 64 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 5ee5d3c1d74b..f099af0b41af 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -884,32 +884,13 @@ static void bus_remove_attrs(struct bus_type *bus) static int bus_add_groups(struct bus_type *bus, const struct attribute_group **groups) { - int error = 0; - int i; - - if (groups) { - for (i = 0; groups[i]; i++) { - error = sysfs_create_group(&bus->p->subsys.kobj, - groups[i]); - if (error) { - while (--i >= 0) - sysfs_remove_group(&bus->p->subsys.kobj, - groups[i]); - break; - } - } - } - return error; + return sysfs_create_groups(&bus->p->subsys.kobj, groups); } static void bus_remove_groups(struct bus_type *bus, const struct attribute_group **groups) { - int i; - - if (groups) - for (i = 0; groups[i]; i++) - sysfs_remove_group(&bus->p->subsys.kobj, groups[i]); + sysfs_remove_groups(&bus->p->subsys.kobj, groups); } static void klist_devices_get(struct klist_node *n) diff --git a/drivers/base/core.c b/drivers/base/core.c index af646afa5b7e..d743dcee1e77 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -493,31 +493,13 @@ static void device_remove_bin_attributes(struct device *dev, int device_add_groups(struct device *dev, const struct attribute_group **groups) { - int error = 0; - int i; - - if (groups) { - for (i = 0; groups[i]; i++) { - error = sysfs_create_group(&dev->kobj, groups[i]); - if (error) { - while (--i >= 0) - sysfs_remove_group(&dev->kobj, - groups[i]); - break; - } - } - } - return error; + return sysfs_create_groups(&dev->kobj, groups); } void device_remove_groups(struct device *dev, const struct attribute_group **groups) { - int i; - - if (groups) - for (i = 0; groups[i]; i++) - sysfs_remove_group(&dev->kobj, groups[i]); + sysfs_remove_groups(&dev->kobj, groups); } static int device_add_attrs(struct device *dev) diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 89db726ebb98..c7efccb6f3bb 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -126,31 +126,13 @@ EXPORT_SYMBOL_GPL(driver_remove_file); int driver_add_groups(struct device_driver *drv, const struct attribute_group **groups) { - int error = 0; - int i; - - if (groups) { - for (i = 0; groups[i]; i++) { - error = sysfs_create_group(&drv->p->kobj, groups[i]); - if (error) { - while (--i >= 0) - sysfs_remove_group(&drv->p->kobj, - groups[i]); - break; - } - } - } - return error; + return sysfs_create_groups(&drv->p->kobj, groups); } void driver_remove_groups(struct device_driver *drv, const struct attribute_group **groups) { - int i; - - if (groups) - for (i = 0; groups[i]; i++) - sysfs_remove_group(&drv->p->kobj, groups[i]); + sysfs_remove_groups(&drv->p->kobj, groups); } /** diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 09a1a25cd145..68baf8501552 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -130,6 +130,40 @@ int sysfs_create_group(struct kobject *kobj, return internal_create_group(kobj, 0, grp); } +/** + * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups + * @kobj: The kobject to create the group on + * @groups: The attribute groups to create, NULL terminated + * + * This function creates a bunch of attribute groups. If an error occurs when + * creating a group, all previously created groups will be removed, unwinding + * everything back to the original state when this function was called. + * It will explicitly warn and error if any of the attribute files being + * created already exist. + * + * Returns 0 on success or error code from sysfs_create_groups on error. + */ +int sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + int error = 0; + int i; + + if (!groups) + return 0; + + for (i = 0; groups[i]; i++) { + error = sysfs_create_group(kobj, groups[i]); + if (error) { + while (--i >= 0) + sysfs_remove_group(kobj, groups[i]); + break; + } + } + return error; +} +EXPORT_SYMBOL_GPL(sysfs_create_groups); + /** * sysfs_update_group - given a directory kobject, update an attribute group * @kobj: The kobject to update the group on @@ -178,6 +212,26 @@ void sysfs_remove_group(struct kobject * kobj, sysfs_put(sd); } +/** + * sysfs_remove_groups - remove a list of groups + * + * kobj: The kobject for the groups to be removed from + * groups: NULL terminated list of groups to be removed + * + * If groups is not NULL, the all groups will be removed from the kobject + */ +void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + int i; + + if (!groups) + return; + for (i = 0; groups[i]; i++) + sysfs_remove_group(kobj, groups[i]); +} +EXPORT_SYMBOL_GPL(sysfs_remove_groups); + /** * sysfs_merge_group - merge files into a pre-existing attribute group. * @kobj: The kobject containing the group. diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 0f04958623d7..4dbb9d31daa8 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -215,10 +215,14 @@ void sysfs_delete_link(struct kobject *dir, struct kobject *targ, int __must_check sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp); +int __must_check sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups); int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp); void sysfs_remove_group(struct kobject *kobj, const struct attribute_group *grp); +void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups); int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group); void sysfs_remove_file_from_group(struct kobject *kobj, -- cgit v1.2.3-71-gd317 From 5da5c9c899dc456d6eb43aae3e8d4e853b7f5306 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Aug 2013 17:47:05 -0700 Subject: sysfs: fix up minor coding style issues in sysfs.h As long as we are cleaning up sysfs coding style issues, don't forget the main sysfs.h file, so fix up the space issues there as well. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 4dbb9d31daa8..a864b8d918ee 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -51,9 +51,9 @@ do { \ static struct lock_class_key __key; \ \ (attr)->key = &__key; \ -} while(0) +} while (0) #else -#define sysfs_attr_init(attr) do {} while(0) +#define sysfs_attr_init(attr) do {} while (0) #endif struct attribute_group { @@ -69,7 +69,7 @@ struct attribute_group { * for examples.. */ -#define __ATTR(_name,_mode,_show,_store) { \ +#define __ATTR(_name, _mode, _show, _store) { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ @@ -119,7 +119,7 @@ struct bin_attribute { void *private; ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - ssize_t (*write)(struct file *,struct kobject *, struct bin_attribute *, + ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, struct vm_area_struct *vma); @@ -168,8 +168,8 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_RO(_name, _size) struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size) struct sysfs_ops { - ssize_t (*show)(struct kobject *, struct attribute *,char *); - ssize_t (*store)(struct kobject *,struct attribute *,const char *, size_t); + ssize_t (*show)(struct kobject *, struct attribute *, char *); + ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); const void *(*namespace)(struct kobject *, const struct attribute *); }; -- cgit v1.2.3-71-gd317 From f477b7fb13df2b843997559ff34e87d054ba6538 Mon Sep 17 00:00:00 2001 From: wangyuhang Date: Sun, 11 Aug 2013 18:15:17 +0800 Subject: spi: DUAL and QUAD support fix the previous patch some mistake below: 1. DT in slave node, use "spi-tx-nbits = <1/2/4>" in place of using "spi-tx-dual, spi-tx-quad" directly, same to rx. So correct the previous way to get the property in @of_register_spi_devices(). 2. Change the value of transfer bit macro(SPI_NBITS_SINGLE, SPI_NBITS_DUAL SPI_NBITS_QUAD) to 0x01, 0x02 and 0x04 to match the actual wires. 3. Add the following check (1)keep the tx_nbits and rx_nbits in spi_transfer is not beyond the single, dual and quad. (2)keep tx_nbits and rx_nbits are contained by @spi_device->mode example: if @spi_device->mode = DUAL, then tx/rx_nbits can not be set to QUAD(SPI_NBITS_QUAD) (3)if "@spi_device->mode & SPI_3WIRE", then tx/rx_nbits should be in single(SPI_NBITS_SINGLE) Signed-off-by: wangyuhang Signed-off-by: Mark Brown --- drivers/spi/spi.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/spi/spi.h | 22 ++++++++++-- 2 files changed, 116 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 2a20c32c8277..39d38756e984 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -869,6 +869,51 @@ static void of_register_spi_devices(struct spi_master *master) if (of_find_property(nc, "spi-3wire", NULL)) spi->mode |= SPI_3WIRE; + /* Device DUAL/QUAD mode */ + prop = of_get_property(nc, "spi-tx-nbits", &len); + if (!prop || len < sizeof(*prop)) { + dev_err(&master->dev, "%s has no 'spi-tx-nbits' property\n", + nc->full_name); + spi_dev_put(spi); + continue; + } + switch (be32_to_cpup(prop)) { + case SPI_NBITS_SINGLE: + break; + case SPI_NBITS_DUAL: + spi->mode |= SPI_TX_DUAL; + break; + case SPI_NBITS_QUAD: + spi->mode |= SPI_TX_QUAD; + break; + default: + dev_err(&master->dev, "spi-tx-nbits value is not supported\n"); + spi_dev_put(spi); + continue; + } + + prop = of_get_property(nc, "spi-rx-nbits", &len); + if (!prop || len < sizeof(*prop)) { + dev_err(&master->dev, "%s has no 'spi-rx-nbits' property\n", + nc->full_name); + spi_dev_put(spi); + continue; + } + switch (be32_to_cpup(prop)) { + case SPI_NBITS_SINGLE: + break; + case SPI_NBITS_DUAL: + spi->mode |= SPI_RX_DUAL; + break; + case SPI_NBITS_QUAD: + spi->mode |= SPI_RX_QUAD; + break; + default: + dev_err(&master->dev, "spi-rx-nbits value is not supported\n"); + spi_dev_put(spi); + continue; + } + /* Device speed */ prop = of_get_property(nc, "spi-max-frequency", &len); if (!prop || len < sizeof(*prop)) { @@ -1316,6 +1361,19 @@ int spi_setup(struct spi_device *spi) unsigned bad_bits; int status = 0; + /* check mode to prevent that DUAL and QUAD set at the same time + */ + if (((spi->mode & SPI_TX_DUAL) && (spi->mode & SPI_TX_QUAD)) || + ((spi->mode & SPI_RX_DUAL) && (spi->mode & SPI_RX_QUAD))) { + dev_err(&spi->dev, + "setup: can not select dual and quad at the same time\n"); + return -EINVAL; + } + /* if it is SPI_3WIRE mode, DUAL and QUAD should be forbidden + */ + if ((spi->mode & SPI_3WIRE) && (spi->mode & + (SPI_TX_DUAL | SPI_TX_QUAD | SPI_RX_DUAL | SPI_RX_QUAD))) + return -EINVAL; /* help drivers fail *cleanly* when they need options * that aren't supported with their current master */ @@ -1378,6 +1436,8 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message) /** * Set transfer bits_per_word and max speed as spi device default if * it is not set for this transfer. + * Set transfer tx_nbits and rx_nbits as single transfer default + * (SPI_NBITS_SINGLE) if it is not set for this transfer. */ list_for_each_entry(xfer, &message->transfers, transfer_list) { if (!xfer->bits_per_word) @@ -1403,6 +1463,42 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message) return -EINVAL; if (xfer->speed_hz && master->max_speed_hz && xfer->speed_hz > master->max_speed_hz) + + if (xfer->tx_buf && !xfer->tx_nbits) + xfer->tx_nbits = SPI_NBITS_SINGLE; + if (xfer->rx_buf && !xfer->rx_nbits) + xfer->rx_nbits = SPI_NBITS_SINGLE; + /* check transfer tx/rx_nbits: + * 1. keep the value is not out of single, dual and quad + * 2. keep tx/rx_nbits is contained by mode in spi_device + * 3. if SPI_3WIRE, tx/rx_nbits should be in single + */ + if (xfer->tx_nbits != SPI_NBITS_SINGLE && + xfer->tx_nbits != SPI_NBITS_DUAL && + xfer->tx_nbits != SPI_NBITS_QUAD) + return -EINVAL; + if ((xfer->tx_nbits == SPI_NBITS_DUAL) && + !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD))) + return -EINVAL; + if ((xfer->tx_nbits == SPI_NBITS_QUAD) && + !(spi->mode & SPI_TX_QUAD)) + return -EINVAL; + if ((spi->mode & SPI_3WIRE) && + (xfer->tx_nbits != SPI_NBITS_SINGLE)) + return -EINVAL; + /* check transfer rx_nbits */ + if (xfer->rx_nbits != SPI_NBITS_SINGLE && + xfer->rx_nbits != SPI_NBITS_DUAL && + xfer->rx_nbits != SPI_NBITS_QUAD) + return -EINVAL; + if ((xfer->rx_nbits == SPI_NBITS_DUAL) && + !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD))) + return -EINVAL; + if ((xfer->rx_nbits == SPI_NBITS_QUAD) && + !(spi->mode & SPI_RX_QUAD)) + return -EINVAL; + if ((spi->mode & SPI_3WIRE) && + (xfer->rx_nbits != SPI_NBITS_SINGLE)) return -EINVAL; } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index cdf668156154..ccd7840c4507 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -74,7 +74,7 @@ struct spi_device { struct spi_master *master; u32 max_speed_hz; u8 chip_select; - u8 mode; + u16 mode; #define SPI_CPHA 0x01 /* clock phase */ #define SPI_CPOL 0x02 /* clock polarity */ #define SPI_MODE_0 (0|0) /* (original MicroWire) */ @@ -87,6 +87,10 @@ struct spi_device { #define SPI_LOOP 0x20 /* loopback mode */ #define SPI_NO_CS 0x40 /* 1 dev/bus, no chipselect */ #define SPI_READY 0x80 /* slave pulls low to pause */ +#define SPI_TX_DUAL 0x100 /* transmit with 2 wires */ +#define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ +#define SPI_RX_DUAL 0x400 /* receive with 2 wires */ +#define SPI_RX_QUAD 0x800 /* receive with 4 wires */ u8 bits_per_word; int irq; void *controller_state; @@ -454,6 +458,10 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * @rx_buf: data to be read (dma-safe memory), or NULL * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped + * @tx_nbits: number of bits used for writting. If 0 the default + * (SPI_NBITS_SINGLE) is used. + * @rx_nbits: number of bits used for reading. If 0 the default + * (SPI_NBITS_SINGLE) is used. * @len: size of rx and tx buffers (in bytes) * @speed_hz: Select a speed other than the device default for this * transfer. If 0 the default (from @spi_device) is used. @@ -508,6 +516,11 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum); * by the results of previous messages and where the whole transaction * ends when the chipselect goes intactive. * + * When SPI can transfer in 1x,2x or 4x. It can get this tranfer information + * from device through @tx_nbits and @rx_nbits. In Bi-direction, these + * two should both be set. User can set transfer mode with SPI_NBITS_SINGLE(1x) + * SPI_NBITS_DUAL(2x) and SPI_NBITS_QUAD(4x) to support these three transfer. + * * The code that submits an spi_message (and its spi_transfers) * to the lower layers is responsible for managing its memory. * Zero-initialize every field you don't set up explicitly, to @@ -528,6 +541,11 @@ struct spi_transfer { dma_addr_t rx_dma; unsigned cs_change:1; + u8 tx_nbits; + u8 rx_nbits; +#define SPI_NBITS_SINGLE 0x01 /* 1bit transfer */ +#define SPI_NBITS_DUAL 0x02 /* 2bits transfer */ +#define SPI_NBITS_QUAD 0x04 /* 4bits transfer */ u8 bits_per_word; u16 delay_usecs; u32 speed_hz; @@ -875,7 +893,7 @@ struct spi_board_info { /* mode becomes spi_device.mode, and is essential for chips * where the default of SPI_CS_HIGH = 0 is wrong. */ - u8 mode; + u16 mode; /* ... may need additional spi_device chip config data here. * avoid stuff protocol drivers can set; but include stuff -- cgit v1.2.3-71-gd317 From d79ff142624e1be080ad8d09101f7004d79c36e1 Mon Sep 17 00:00:00 2001 From: Martin Peschke Date: Thu, 22 Aug 2013 17:45:36 +0200 Subject: [SCSI] zfcp: fix lock imbalance by reworking request queue locking This patch adds wait_event_interruptible_lock_irq_timeout(), which is a straight-forward descendant of wait_event_interruptible_timeout() and wait_event_interruptible_lock_irq(). The zfcp driver used to call wait_event_interruptible_timeout() in combination with some intricate and error-prone locking. Using wait_event_interruptible_lock_irq_timeout() as a replacement nicely cleans up that locking. This rework removes a situation that resulted in a locking imbalance in zfcp_qdio_sbal_get(): BUG: workqueue leaked lock or atomic: events/1/0xffffff00/10 last function: zfcp_fc_wka_port_offline+0x0/0xa0 [zfcp] It was introduced by commit c2af7545aaff3495d9bf9a7608c52f0af86fb194 "[SCSI] zfcp: Do not wait for SBALs on stopped queue", which had a new code path related to ZFCP_STATUS_ADAPTER_QDIOUP that took an early exit without a required lock being held. The problem occured when a special, non-SCSI I/O request was being submitted in process context, when the adapter's queues had been torn down. In this case the bug surfaced when the Fibre Channel port connection for a well-known address was closed during a concurrent adapter shut-down procedure, which is a rare constellation. This patch also fixes these warnings from the sparse tool (make C=1): drivers/s390/scsi/zfcp_qdio.c:224:12: warning: context imbalance in 'zfcp_qdio_sbal_check' - wrong count at exit drivers/s390/scsi/zfcp_qdio.c:244:5: warning: context imbalance in 'zfcp_qdio_sbal_get' - unexpected unlock Last but not least, we get rid of that crappy lock-unlock-lock sequence at the beginning of the critical section. It is okay to call zfcp_erp_adapter_reopen() with req_q_lock held. Reported-by: Mikulas Patocka Reported-by: Heiko Carstens Signed-off-by: Martin Peschke Cc: stable@vger.kernel.org #2.6.35+ Signed-off-by: Steffen Maier Signed-off-by: James Bottomley --- drivers/s390/scsi/zfcp_qdio.c | 8 ++---- include/linux/wait.h | 57 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c index 665e3cfaaf85..de0598eaacd2 100644 --- a/drivers/s390/scsi/zfcp_qdio.c +++ b/drivers/s390/scsi/zfcp_qdio.c @@ -224,11 +224,9 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, static int zfcp_qdio_sbal_check(struct zfcp_qdio *qdio) { - spin_lock_irq(&qdio->req_q_lock); if (atomic_read(&qdio->req_q_free) || !(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP)) return 1; - spin_unlock_irq(&qdio->req_q_lock); return 0; } @@ -246,9 +244,8 @@ int zfcp_qdio_sbal_get(struct zfcp_qdio *qdio) { long ret; - spin_unlock_irq(&qdio->req_q_lock); - ret = wait_event_interruptible_timeout(qdio->req_q_wq, - zfcp_qdio_sbal_check(qdio), 5 * HZ); + ret = wait_event_interruptible_lock_irq_timeout(qdio->req_q_wq, + zfcp_qdio_sbal_check(qdio), qdio->req_q_lock, 5 * HZ); if (!(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP)) return -EIO; @@ -262,7 +259,6 @@ int zfcp_qdio_sbal_get(struct zfcp_qdio *qdio) zfcp_erp_adapter_reopen(qdio->adapter, 0, "qdsbg_1"); } - spin_lock_irq(&qdio->req_q_lock); return -EIO; } diff --git a/include/linux/wait.h b/include/linux/wait.h index f487a4750b7f..a67fc1635592 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -811,6 +811,63 @@ do { \ __ret; \ }) +#define __wait_event_interruptible_lock_irq_timeout(wq, condition, \ + lock, ret) \ +do { \ + DEFINE_WAIT(__wait); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + spin_unlock_irq(&lock); \ + ret = schedule_timeout(ret); \ + spin_lock_irq(&lock); \ + if (!ret) \ + break; \ + } \ + finish_wait(&wq, &__wait); \ +} while (0) + +/** + * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets true or a timeout elapses. + * The condition is checked under the lock. This is expected + * to be called with the lock taken. + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @lock: a locked spinlock_t, which will be released before schedule() + * and reacquired afterwards. + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or signal is received. The @condition is + * checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * This is supposed to be called while holding the lock. The lock is + * dropped before going to sleep and is reacquired afterwards. + * + * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it + * was interrupted by a signal, and the remaining jiffies otherwise + * if the condition evaluated to true before the timeout elapsed. + */ +#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock, \ + timeout) \ +({ \ + int __ret = timeout; \ + \ + if (!(condition)) \ + __wait_event_interruptible_lock_irq_timeout( \ + wq, condition, lock, __ret); \ + __ret; \ +}) + /* * These are the old interfaces to sleep waiting for an event. -- cgit v1.2.3-71-gd317 From a58674ff8383f5b8f6a77f03c48f6a47840b9325 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 22 Aug 2013 11:24:44 +0800 Subject: PCI: Simplify pcie_bus_configure_settings() interface Based on a patch by Jon Mason (see URL below). All users of pcie_bus_configure_settings() pass arguments of the form "bus, bus->self->pcie_mpss". The "mpss" argument is redundant since we can easily look it up internally. In addition, all callers check "bus->self" for NULL, which we can also do internally. This patch simplifies the interface and the callers. No functional change. Reference: http://lkml.kernel.org/r/1317048850-30728-2-git-send-email-mason@myri.com Signed-off-by: Bjorn Helgaas --- arch/powerpc/kernel/pci-common.c | 8 ++------ arch/tile/kernel/pci_gx.c | 9 ++------- arch/x86/pci/acpi.c | 9 ++------- drivers/pci/hotplug/pcihp_slot.c | 5 ++--- drivers/pci/probe.c | 7 +++++-- include/linux/pci.h | 2 +- 6 files changed, 14 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f46914a0f33e..d35ec34de1b4 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1672,12 +1672,8 @@ void pcibios_scan_phb(struct pci_controller *hose) /* Configure PCI Express settings */ if (bus && !pci_has_flag(PCI_PROBE_ONLY)) { struct pci_bus *child; - list_for_each_entry(child, &bus->children, node) { - struct pci_dev *self = child->self; - if (!self) - continue; - pcie_bus_configure_settings(child, self->pcie_mpss); - } + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); } } diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c index 11425633b2d7..6640e7bbeaa2 100644 --- a/arch/tile/kernel/pci_gx.c +++ b/arch/tile/kernel/pci_gx.c @@ -508,13 +508,8 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller) rc_dev_cap.word); /* Configure PCI Express MPS setting. */ - list_for_each_entry(child, &root_bus->children, node) { - struct pci_dev *self = child->self; - if (!self) - continue; - - pcie_bus_configure_settings(child, self->pcie_mpss); - } + list_for_each_entry(child, &root_bus->children, node) + pcie_bus_configure_settings(child); /* * Set the mac_config register in trio based on the MPS/MRS of the link. diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index d641897a1f4e..b30e937689d6 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -568,13 +568,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) */ if (bus) { struct pci_bus *child; - list_for_each_entry(child, &bus->children, node) { - struct pci_dev *self = child->self; - if (!self) - continue; - - pcie_bus_configure_settings(child, self->pcie_mpss); - } + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); } if (bus && node != -1) { diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c index fec2d5b75440..16f920352317 100644 --- a/drivers/pci/hotplug/pcihp_slot.c +++ b/drivers/pci/hotplug/pcihp_slot.c @@ -160,9 +160,8 @@ void pci_configure_slot(struct pci_dev *dev) (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) return; - if (dev->bus && dev->bus->self) - pcie_bus_configure_settings(dev->bus, - dev->bus->self->pcie_mpss); + if (dev->bus) + pcie_bus_configure_settings(dev->bus); memset(&hpp, 0, sizeof(hpp)); ret = pci_get_hp_params(dev, &hpp); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 9a334301a8f4..ecae7f290647 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1607,10 +1607,13 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data) * parents then children fashion. If this changes, then this code will not * work as designed. */ -void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss) +void pcie_bus_configure_settings(struct pci_bus *bus) { u8 smpss; + if (!bus->self) + return; + if (!pci_is_pcie(bus->self)) return; @@ -1625,7 +1628,7 @@ void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss) smpss = 0; if (pcie_bus_config == PCIE_BUS_SAFE) { - smpss = mpss; + smpss = bus->self->pcie_mpss; pcie_find_smpss(bus->self, &smpss); pci_walk_bus(bus, pcie_find_smpss, &smpss); diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..57062b7a20ba 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -675,7 +675,7 @@ struct pci_driver { /* these external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI -void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); +void pcie_bus_configure_settings(struct pci_bus *bus); enum pcie_bus_config_types { PCIE_BUS_TUNE_OFF, -- cgit v1.2.3-71-gd317 From 5ea80f76a56605a190a7ea16846c82aa63dbd0aa Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 22 Aug 2013 09:13:06 -0700 Subject: Revert "x86 get_unmapped_area(): use proper mmap base for bottom-up direction" This reverts commit df54d6fa54275ce59660453e29d1228c2b45a826. The commit isn't necessarily wrong, but because it recalculates the random mmap_base every time, it seems to confuse user memory allocators that expect contiguous mmap allocations even when the mmap address isn't specified. In particular, the MATLAB Java runtime seems to be unhappy. See https://bugzilla.kernel.org/show_bug.cgi?id=60774 So we'll want to apply the random offset only once, and Radu has a patch for that. Revert this older commit in order to apply the other one. Reported-by: Jeff Shorey Cc: Radu Caragea Cc: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/sys_x86_64.c | 2 +- arch/x86/mm/mmap.c | 2 +- include/linux/sched.h | 1 - 3 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 48f8375e4c6b..dbded5aedb81 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = mmap_legacy_base(); + *begin = TASK_UNMAPPED_BASE; *end = TASK_SIZE; } } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index f63778cb2363..62c29a5bfe26 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -98,7 +98,7 @@ static unsigned long mmap_base(void) * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 * does, but not when emulating X86_32 */ -unsigned long mmap_legacy_base(void) +static unsigned long mmap_legacy_base(void) { if (mmap_is_ia32()) return TASK_UNMAPPED_BASE; diff --git a/include/linux/sched.h b/include/linux/sched.h index e9995eb5985c..078066daffd4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -314,7 +314,6 @@ struct nsproxy; struct user_namespace; #ifdef CONFIG_MMU -extern unsigned long mmap_legacy_base(void); extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, -- cgit v1.2.3-71-gd317 From 41aacc1eea645c99edbe8fbcf78a97dc9b862adc Mon Sep 17 00:00:00 2001 From: Radu Caragea Date: Wed, 21 Aug 2013 20:55:59 +0300 Subject: x86 get_unmapped_area: Access mmap_legacy_base through mm_struct member This is the updated version of df54d6fa5427 ("x86 get_unmapped_area(): use proper mmap base for bottom-up direction") that only randomizes the mmap base address once. Signed-off-by: Radu Caragea Reported-and-tested-by: Jeff Shorey Cc: Andrew Morton Cc: Michel Lespinasse Cc: Oleg Nesterov Cc: Rik van Riel Cc: Ingo Molnar Cc: Adrian Sendroiu Cc: Greg KH Cc: Kamal Mostafa Signed-off-by: Linus Torvalds --- arch/x86/kernel/sys_x86_64.c | 2 +- arch/x86/mm/mmap.c | 6 ++++-- include/linux/mm_types.h | 1 + 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index dbded5aedb81..30277e27431a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = TASK_UNMAPPED_BASE; + *begin = current->mm->mmap_legacy_base; *end = TASK_SIZE; } } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 62c29a5bfe26..25e7e1372bb2 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -112,11 +112,13 @@ static unsigned long mmap_legacy_base(void) */ void arch_pick_mmap_layout(struct mm_struct *mm) { + mm->mmap_legacy_base = mmap_legacy_base(); + mm->mmap_base = mmap_base(); + if (mmap_is_legacy()) { - mm->mmap_base = mmap_legacy_base(); + mm->mmap_base = mm->mmap_legacy_base; mm->get_unmapped_area = arch_get_unmapped_area; } else { - mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index fb425aa16c01..faf4b7c1ad12 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -332,6 +332,7 @@ struct mm_struct { unsigned long pgoff, unsigned long flags); #endif unsigned long mmap_base; /* base of mmap area */ + unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ unsigned long task_size; /* size of task vm space */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; -- cgit v1.2.3-71-gd317 From 3e1026b3fa2f61d33ce6a9e42a22398cc4ab8e58 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 22 Aug 2013 10:25:34 -0700 Subject: sysfs.h: remove attr_name() macro Gotta love a macro that doesn't reduce the typing you have to do. Also, only the driver core, and one network driver uses this. The driver core functions will be going away soon, and I'll convert the network driver soon to not need this as well, so delete it for now before anyone else gets some bright ideas and wants to use it. Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 12 ++++++------ drivers/base/class.c | 4 ++-- drivers/base/core.c | 8 ++++---- drivers/net/ethernet/sun/niu.c | 2 +- include/linux/sysfs.h | 2 -- 5 files changed, 13 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index f099af0b41af..235e2b06ac05 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -460,7 +460,7 @@ static int device_add_attrs(struct bus_type *bus, struct device *dev) if (!bus->dev_attrs) return 0; - for (i = 0; attr_name(bus->dev_attrs[i]); i++) { + for (i = 0; bus->dev_attrs[i].attr.name; i++) { error = device_create_file(dev, &bus->dev_attrs[i]); if (error) { while (--i >= 0) @@ -476,7 +476,7 @@ static void device_remove_attrs(struct bus_type *bus, struct device *dev) int i; if (bus->dev_attrs) { - for (i = 0; attr_name(bus->dev_attrs[i]); i++) + for (i = 0; bus->dev_attrs[i].attr.name; i++) device_remove_file(dev, &bus->dev_attrs[i]); } } @@ -596,7 +596,7 @@ static int driver_add_attrs(struct bus_type *bus, struct device_driver *drv) int i; if (bus->drv_attrs) { - for (i = 0; attr_name(bus->drv_attrs[i]); i++) { + for (i = 0; bus->drv_attrs[i].attr.name; i++) { error = driver_create_file(drv, &bus->drv_attrs[i]); if (error) goto err; @@ -616,7 +616,7 @@ static void driver_remove_attrs(struct bus_type *bus, int i; if (bus->drv_attrs) { - for (i = 0; attr_name(bus->drv_attrs[i]); i++) + for (i = 0; bus->drv_attrs[i].attr.name; i++) driver_remove_file(drv, &bus->drv_attrs[i]); } } @@ -857,7 +857,7 @@ static int bus_add_attrs(struct bus_type *bus) int i; if (bus->bus_attrs) { - for (i = 0; attr_name(bus->bus_attrs[i]); i++) { + for (i = 0; bus->bus_attrs[i].attr.name; i++) { error = bus_create_file(bus, &bus->bus_attrs[i]); if (error) goto err; @@ -876,7 +876,7 @@ static void bus_remove_attrs(struct bus_type *bus) int i; if (bus->bus_attrs) { - for (i = 0; attr_name(bus->bus_attrs[i]); i++) + for (i = 0; bus->bus_attrs[i].attr.name; i++) bus_remove_file(bus, &bus->bus_attrs[i]); } } diff --git a/drivers/base/class.c b/drivers/base/class.c index 3ce845471327..8b7818b80056 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -135,7 +135,7 @@ static int add_class_attrs(struct class *cls) int error = 0; if (cls->class_attrs) { - for (i = 0; attr_name(cls->class_attrs[i]); i++) { + for (i = 0; cls->class_attrs[i].attr.name; i++) { error = class_create_file(cls, &cls->class_attrs[i]); if (error) goto error; @@ -154,7 +154,7 @@ static void remove_class_attrs(struct class *cls) int i; if (cls->class_attrs) { - for (i = 0; attr_name(cls->class_attrs[i]); i++) + for (i = 0; cls->class_attrs[i].attr.name; i++) class_remove_file(cls, &cls->class_attrs[i]); } } diff --git a/drivers/base/core.c b/drivers/base/core.c index d743dcee1e77..ae1acdf21bd3 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -440,7 +440,7 @@ static int device_add_attributes(struct device *dev, int i; if (attrs) { - for (i = 0; attr_name(attrs[i]); i++) { + for (i = 0; attrs[i].attr.name; i++) { error = device_create_file(dev, &attrs[i]); if (error) break; @@ -458,7 +458,7 @@ static void device_remove_attributes(struct device *dev, int i; if (attrs) - for (i = 0; attr_name(attrs[i]); i++) + for (i = 0; attrs[i].attr.name; i++) device_remove_file(dev, &attrs[i]); } @@ -469,7 +469,7 @@ static int device_add_bin_attributes(struct device *dev, int i; if (attrs) { - for (i = 0; attr_name(attrs[i]); i++) { + for (i = 0; attrs[i].attr.name; i++) { error = device_create_bin_file(dev, &attrs[i]); if (error) break; @@ -487,7 +487,7 @@ static void device_remove_bin_attributes(struct device *dev, int i; if (attrs) - for (i = 0; attr_name(attrs[i]); i++) + for (i = 0; attrs[i].attr.name; i++) device_remove_bin_file(dev, &attrs[i]); } diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index fa322409bff3..52b2adf63cbf 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9478,7 +9478,7 @@ static struct niu_parent *niu_new_parent(struct niu *np, if (IS_ERR(plat_dev)) return NULL; - for (i = 0; attr_name(niu_parent_attributes[i]); i++) { + for (i = 0; niu_parent_attributes[i].attr.name; i++) { int err = device_create_file(&plat_dev->dev, &niu_parent_attributes[i]); if (err) diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index a864b8d918ee..b5a9d9b26bd4 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -108,8 +108,6 @@ static const struct attribute_group _name##_group = { \ }; \ __ATTRIBUTE_GROUPS(_name) -#define attr_name(_attr) (_attr).attr.name - struct file; struct vm_area_struct; -- cgit v1.2.3-71-gd317 From 699c1985587aad3432c5ae19801efb4186db8b7a Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 20 Aug 2013 16:41:02 +0200 Subject: PCI: Add pcibios_pm_ops for optional arch-specific hibernate functionality Platforms may want to provide architecture-specific functionality when a PCI device is doing a hibernate transition. Add a weak symbol pcibios_pm_ops that architectures can override to do so. [bhelgaas: fold in return value checks from v2 patch] Signed-off-by: Sebastian Ott Signed-off-by: Bjorn Helgaas --- drivers/pci/pci-driver.c | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 4 ++++ 2 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index e6515e21afa3..98f7b9b89507 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -763,6 +763,13 @@ static int pci_pm_resume(struct device *dev) #ifdef CONFIG_HIBERNATE_CALLBACKS + +/* + * pcibios_pm_ops - provide arch-specific hooks when a PCI device is doing + * a hibernate transition + */ +struct dev_pm_ops __weak pcibios_pm_ops; + static int pci_pm_freeze(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); @@ -786,6 +793,9 @@ static int pci_pm_freeze(struct device *dev) return error; } + if (pcibios_pm_ops.freeze) + return pcibios_pm_ops.freeze(dev); + return 0; } @@ -811,6 +821,9 @@ static int pci_pm_freeze_noirq(struct device *dev) pci_pm_set_unknown_state(pci_dev); + if (pcibios_pm_ops.freeze_noirq) + return pcibios_pm_ops.freeze_noirq(dev); + return 0; } @@ -820,6 +833,12 @@ static int pci_pm_thaw_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; + if (pcibios_pm_ops.thaw_noirq) { + error = pcibios_pm_ops.thaw_noirq(dev); + if (error) + return error; + } + if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); @@ -837,6 +856,12 @@ static int pci_pm_thaw(struct device *dev) const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int error = 0; + if (pcibios_pm_ops.thaw) { + error = pcibios_pm_ops.thaw(dev); + if (error) + return error; + } + if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume(dev); @@ -878,6 +903,9 @@ static int pci_pm_poweroff(struct device *dev) Fixup: pci_fixup_device(pci_fixup_suspend, pci_dev); + if (pcibios_pm_ops.poweroff) + return pcibios_pm_ops.poweroff(dev); + return 0; } @@ -911,6 +939,9 @@ static int pci_pm_poweroff_noirq(struct device *dev) if (pci_dev->class == PCI_CLASS_SERIAL_USB_EHCI) pci_write_config_word(pci_dev, PCI_COMMAND, 0); + if (pcibios_pm_ops.poweroff_noirq) + return pcibios_pm_ops.poweroff_noirq(dev); + return 0; } @@ -920,6 +951,12 @@ static int pci_pm_restore_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; + if (pcibios_pm_ops.restore_noirq) { + error = pcibios_pm_ops.restore_noirq(dev); + if (error) + return error; + } + pci_pm_default_resume_early(pci_dev); if (pci_has_legacy_pm_support(pci_dev)) @@ -937,6 +974,12 @@ static int pci_pm_restore(struct device *dev) const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int error = 0; + if (pcibios_pm_ops.restore) { + error = pcibios_pm_ops.restore(dev); + if (error) + return error; + } + /* * This is necessary for the hibernation error path in which restore is * called without restoring the standard config registers of the device. diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..89ed12379f2f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1648,6 +1648,10 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, int pcibios_add_device(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); +#ifdef CONFIG_HIBERNATE_CALLBACKS +extern struct dev_pm_ops pcibios_pm_ops; +#endif + #ifdef CONFIG_PCI_MMCONFIG void __init pci_mmcfg_early_init(void); void __init pci_mmcfg_late_init(void); -- cgit v1.2.3-71-gd317 From 4a5a8aa6c966eafc106543bd955ae388230420e5 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 21 Aug 2013 21:09:47 -0700 Subject: ipv4: expose IPV4_DEVCONF IP sends device configuration (see inet_fill_link_af) as an array in the netlink information, but the indices in that array are not exposed to userspace through any current santized header file. It was available back in 2.6.32 (in /usr/include/linux/sysctl.h) but was broken by: commit 02291680ffba92e5b5865bc0c5e7d1f3056b80ec Author: Eric W. Biederman Date: Sun Feb 14 03:25:51 2010 +0000 net ipv4: Decouple ipv4 interface parameters from binary sysctl numbers Eric was solving the sysctl problem but then the indices were re-exposed by a later addition of devconf support for IPV4 commit 9f0f7272ac9506f4c8c05cc597b7e376b0b9f3e4 Author: Thomas Graf Date: Tue Nov 16 04:32:48 2010 +0000 ipv4: AF_INET link address family Putting them in /usr/include/linux/ip.h seemed the logical match for the DEVCONF_ definitions for IPV6 in /usr/include/linux/ip6.h Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 34 +--------------------------------- include/uapi/linux/ip.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index b99cd23f3474..79640e015a86 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -5,45 +5,13 @@ #include #include +#include #include #include #include #include #include -enum -{ - IPV4_DEVCONF_FORWARDING=1, - IPV4_DEVCONF_MC_FORWARDING, - IPV4_DEVCONF_PROXY_ARP, - IPV4_DEVCONF_ACCEPT_REDIRECTS, - IPV4_DEVCONF_SECURE_REDIRECTS, - IPV4_DEVCONF_SEND_REDIRECTS, - IPV4_DEVCONF_SHARED_MEDIA, - IPV4_DEVCONF_RP_FILTER, - IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE, - IPV4_DEVCONF_BOOTP_RELAY, - IPV4_DEVCONF_LOG_MARTIANS, - IPV4_DEVCONF_TAG, - IPV4_DEVCONF_ARPFILTER, - IPV4_DEVCONF_MEDIUM_ID, - IPV4_DEVCONF_NOXFRM, - IPV4_DEVCONF_NOPOLICY, - IPV4_DEVCONF_FORCE_IGMP_VERSION, - IPV4_DEVCONF_ARP_ANNOUNCE, - IPV4_DEVCONF_ARP_IGNORE, - IPV4_DEVCONF_PROMOTE_SECONDARIES, - IPV4_DEVCONF_ARP_ACCEPT, - IPV4_DEVCONF_ARP_NOTIFY, - IPV4_DEVCONF_ACCEPT_LOCAL, - IPV4_DEVCONF_SRC_VMARK, - IPV4_DEVCONF_PROXY_ARP_PVLAN, - IPV4_DEVCONF_ROUTE_LOCALNET, - __IPV4_DEVCONF_MAX -}; - -#define IPV4_DEVCONF_MAX (__IPV4_DEVCONF_MAX - 1) - struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 6cf06bfd841b..2fee45bdec0a 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -133,4 +133,38 @@ struct ip_beet_phdr { __u8 reserved; }; +/* index values for the variables in ipv4_devconf */ +enum +{ + IPV4_DEVCONF_FORWARDING=1, + IPV4_DEVCONF_MC_FORWARDING, + IPV4_DEVCONF_PROXY_ARP, + IPV4_DEVCONF_ACCEPT_REDIRECTS, + IPV4_DEVCONF_SECURE_REDIRECTS, + IPV4_DEVCONF_SEND_REDIRECTS, + IPV4_DEVCONF_SHARED_MEDIA, + IPV4_DEVCONF_RP_FILTER, + IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE, + IPV4_DEVCONF_BOOTP_RELAY, + IPV4_DEVCONF_LOG_MARTIANS, + IPV4_DEVCONF_TAG, + IPV4_DEVCONF_ARPFILTER, + IPV4_DEVCONF_MEDIUM_ID, + IPV4_DEVCONF_NOXFRM, + IPV4_DEVCONF_NOPOLICY, + IPV4_DEVCONF_FORCE_IGMP_VERSION, + IPV4_DEVCONF_ARP_ANNOUNCE, + IPV4_DEVCONF_ARP_IGNORE, + IPV4_DEVCONF_PROMOTE_SECONDARIES, + IPV4_DEVCONF_ARP_ACCEPT, + IPV4_DEVCONF_ARP_NOTIFY, + IPV4_DEVCONF_ACCEPT_LOCAL, + IPV4_DEVCONF_SRC_VMARK, + IPV4_DEVCONF_PROXY_ARP_PVLAN, + IPV4_DEVCONF_ROUTE_LOCALNET, + __IPV4_DEVCONF_MAX +}; + +#define IPV4_DEVCONF_MAX (__IPV4_DEVCONF_MAX - 1) + #endif /* _UAPI_LINUX_IP_H */ -- cgit v1.2.3-71-gd317 From f1bc1e4c44b1b78fe34431936c60759b5aad5e3f Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Fri, 23 Aug 2013 10:17:54 +0800 Subject: ata: acpi: rework the ata acpi bind support Binding ACPI handle to SCSI device has several drawbacks, namely: 1 During ATA device initialization time, ACPI handle will be needed while SCSI devices are not created yet. So each time ACPI handle is needed, instead of retrieving the handle by ACPI_HANDLE macro, a namespace scan is performed to find the handle for the corresponding ATA device. This is inefficient, and also expose a restriction on calling path not holding any lock. 2 The binding to SCSI device tree makes code complex, while at the same time doesn't bring us any benefit. All ACPI handlings are still done in ATA module, not in SCSI. Rework the ATA ACPI binding code to bind ACPI handle to ATA transport devices(ATA port and ATA device). The binding needs to be done only once, since the ATA transport devices do not go away with hotplug. And due to this, the flush_work call in hotplug handler for ATA bay is no longer needed. Tested on an Intel test platform for binding and runtime power off for ODD(ZPODD) and hard disk; on an ASUS S400C for binding and normal boot and S3, where its SATA port node has _SDD and _GTF control methods when configured as an AHCI controller and its PATA device node has _GTF control method when configured as an IDE controller. SATA PMP binding and ATA hotplug is not tested. Signed-off-by: Aaron Lu Tested-by: Dirk Griesbach Signed-off-by: Tejun Heo --- drivers/ata/libata-acpi.c | 278 ++++++++++++----------------------------- drivers/ata/libata-core.c | 5 - drivers/ata/libata-scsi.c | 13 +- drivers/ata/libata-transport.c | 2 + drivers/ata/libata-zpodd.c | 12 +- drivers/ata/libata.h | 16 ++- drivers/ata/pata_acpi.c | 4 +- drivers/scsi/scsi_lib.c | 22 ---- include/linux/libata.h | 2 - 9 files changed, 106 insertions(+), 248 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index cf4e7020adac..2377a32861dc 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -34,62 +34,25 @@ struct ata_acpi_gtf { u8 tf[REGS_PER_GTF]; /* regs. 0x1f1 - 0x1f7 */ } __packed; -/* - * Helper - belongs in the PCI layer somewhere eventually - */ -static int is_pci_dev(struct device *dev) -{ - return (dev->bus == &pci_bus_type); -} - static void ata_acpi_clear_gtf(struct ata_device *dev) { kfree(dev->gtf_cache); dev->gtf_cache = NULL; } -/** - * ata_ap_acpi_handle - provide the acpi_handle for an ata_port - * @ap: the acpi_handle returned will correspond to this port - * - * Returns the acpi_handle for the ACPI namespace object corresponding to - * the ata_port passed into the function, or NULL if no such object exists - */ -acpi_handle ata_ap_acpi_handle(struct ata_port *ap) -{ - if (ap->flags & ATA_FLAG_ACPI_SATA) - return NULL; - - return ap->scsi_host ? - DEVICE_ACPI_HANDLE(&ap->scsi_host->shost_gendev) : NULL; -} -EXPORT_SYMBOL(ata_ap_acpi_handle); - /** * ata_dev_acpi_handle - provide the acpi_handle for an ata_device - * @dev: the acpi_device returned will correspond to this port + * @dev: the acpi_handle returned will correspond to this device * * Returns the acpi_handle for the ACPI namespace object corresponding to * the ata_device passed into the function, or NULL if no such object exists + * or ACPI is disabled for this device due to consecutive errors. */ acpi_handle ata_dev_acpi_handle(struct ata_device *dev) { - acpi_integer adr; - struct ata_port *ap = dev->link->ap; - - if (libata_noacpi || dev->flags & ATA_DFLAG_ACPI_DISABLED) - return NULL; - - if (ap->flags & ATA_FLAG_ACPI_SATA) { - if (!sata_pmp_attached(ap)) - adr = SATA_ADR(ap->port_no, NO_PORT_MULT); - else - adr = SATA_ADR(ap->port_no, dev->link->pmp); - return acpi_get_child(DEVICE_ACPI_HANDLE(ap->host->dev), adr); - } else - return acpi_get_child(ata_ap_acpi_handle(ap), dev->devno); + return dev->flags & ATA_DFLAG_ACPI_DISABLED ? + NULL : ACPI_HANDLE(&dev->tdev); } -EXPORT_SYMBOL(ata_dev_acpi_handle); /* @ap and @dev are the same as ata_acpi_handle_hotplug() */ static void ata_acpi_detach_device(struct ata_port *ap, struct ata_device *dev) @@ -156,10 +119,8 @@ static void ata_acpi_handle_hotplug(struct ata_port *ap, struct ata_device *dev, spin_unlock_irqrestore(ap->lock, flags); - if (wait) { + if (wait) ata_port_wait_eh(ap); - flush_work(&ap->hotplug_task.work); - } } static void ata_acpi_dev_notify_dock(acpi_handle handle, u32 event, void *data) @@ -216,37 +177,55 @@ static const struct acpi_dock_ops ata_acpi_ap_dock_ops = { .uevent = ata_acpi_ap_uevent, }; -void ata_acpi_hotplug_init(struct ata_host *host) +/* bind acpi handle to pata port */ +void ata_acpi_bind_port(struct ata_port *ap) { - int i; + acpi_handle host_handle = ACPI_HANDLE(ap->host->dev); - for (i = 0; i < host->n_ports; i++) { - struct ata_port *ap = host->ports[i]; - acpi_handle handle; - struct ata_device *dev; + if (libata_noacpi || ap->flags & ATA_FLAG_ACPI_SATA || !host_handle) + return; - if (!ap) - continue; + ACPI_HANDLE_SET(&ap->tdev, acpi_get_child(host_handle, ap->port_no)); - handle = ata_ap_acpi_handle(ap); - if (handle) { - /* we might be on a docking station */ - register_hotplug_dock_device(handle, - &ata_acpi_ap_dock_ops, ap, - NULL, NULL); - } + if (ata_acpi_gtm(ap, &ap->__acpi_init_gtm) == 0) + ap->pflags |= ATA_PFLAG_INIT_GTM_VALID; - ata_for_each_dev(dev, &ap->link, ALL) { - handle = ata_dev_acpi_handle(dev); - if (!handle) - continue; + /* we might be on a docking station */ + register_hotplug_dock_device(ACPI_HANDLE(&ap->tdev), + &ata_acpi_ap_dock_ops, ap, NULL, NULL); +} - /* we might be on a docking station */ - register_hotplug_dock_device(handle, - &ata_acpi_dev_dock_ops, - dev, NULL, NULL); - } +void ata_acpi_bind_dev(struct ata_device *dev) +{ + struct ata_port *ap = dev->link->ap; + acpi_handle port_handle = ACPI_HANDLE(&ap->tdev); + acpi_handle host_handle = ACPI_HANDLE(ap->host->dev); + acpi_handle parent_handle; + u64 adr; + + /* + * For both sata/pata devices, host handle is required. + * For pata device, port handle is also required. + */ + if (libata_noacpi || !host_handle || + (!(ap->flags & ATA_FLAG_ACPI_SATA) && !port_handle)) + return; + + if (ap->flags & ATA_FLAG_ACPI_SATA) { + if (!sata_pmp_attached(ap)) + adr = SATA_ADR(ap->port_no, NO_PORT_MULT); + else + adr = SATA_ADR(ap->port_no, dev->link->pmp); + parent_handle = host_handle; + } else { + adr = dev->devno; + parent_handle = port_handle; } + + ACPI_HANDLE_SET(&dev->tdev, acpi_get_child(parent_handle, adr)); + + register_hotplug_dock_device(ata_dev_acpi_handle(dev), + &ata_acpi_dev_dock_ops, dev, NULL, NULL); } /** @@ -270,18 +249,34 @@ void ata_acpi_dissociate(struct ata_host *host) struct ata_port *ap = host->ports[i]; const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap); - if (ata_ap_acpi_handle(ap) && gtm) + if (ACPI_HANDLE(&ap->tdev) && gtm) ata_acpi_stm(ap, gtm); } } -static int __ata_acpi_gtm(struct ata_port *ap, acpi_handle handle, - struct ata_acpi_gtm *gtm) +/** + * ata_acpi_gtm - execute _GTM + * @ap: target ATA port + * @gtm: out parameter for _GTM result + * + * Evaluate _GTM and store the result in @gtm. + * + * LOCKING: + * EH context. + * + * RETURNS: + * 0 on success, -ENOENT if _GTM doesn't exist, -errno on failure. + */ +int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *gtm) { struct acpi_buffer output = { .length = ACPI_ALLOCATE_BUFFER }; union acpi_object *out_obj; acpi_status status; int rc = 0; + acpi_handle handle = ACPI_HANDLE(&ap->tdev); + + if (!handle) + return -EINVAL; status = acpi_evaluate_object(handle, "_GTM", NULL, &output); @@ -317,27 +312,6 @@ static int __ata_acpi_gtm(struct ata_port *ap, acpi_handle handle, return rc; } -/** - * ata_acpi_gtm - execute _GTM - * @ap: target ATA port - * @gtm: out parameter for _GTM result - * - * Evaluate _GTM and store the result in @gtm. - * - * LOCKING: - * EH context. - * - * RETURNS: - * 0 on success, -ENOENT if _GTM doesn't exist, -errno on failure. - */ -int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *gtm) -{ - if (ata_ap_acpi_handle(ap)) - return __ata_acpi_gtm(ap, ata_ap_acpi_handle(ap), gtm); - else - return -EINVAL; -} - EXPORT_SYMBOL_GPL(ata_acpi_gtm); /** @@ -374,8 +348,8 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm) input.count = 3; input.pointer = in_params; - status = acpi_evaluate_object(ata_ap_acpi_handle(ap), "_STM", &input, - NULL); + status = acpi_evaluate_object(ACPI_HANDLE(&ap->tdev), "_STM", + &input, NULL); if (status == AE_NOT_FOUND) return -ENOENT; @@ -850,7 +824,7 @@ void ata_acpi_on_resume(struct ata_port *ap) const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap); struct ata_device *dev; - if (ata_ap_acpi_handle(ap) && gtm) { + if (ACPI_HANDLE(&ap->tdev) && gtm) { /* _GTM valid */ /* restore timing parameters */ @@ -894,8 +868,7 @@ static int ata_acpi_choose_suspend_state(struct ata_device *dev, bool runtime) d_max_in = ACPI_STATE_D3_HOT; out: - return acpi_pm_device_sleep_state(&dev->sdev->sdev_gendev, - NULL, d_max_in); + return acpi_pm_device_sleep_state(&dev->tdev, NULL, d_max_in); } static void sata_acpi_set_state(struct ata_port *ap, pm_message_t state) @@ -932,7 +905,7 @@ static void pata_acpi_set_state(struct ata_port *ap, pm_message_t state) struct ata_device *dev; acpi_handle port_handle; - port_handle = ata_ap_acpi_handle(ap); + port_handle = ACPI_HANDLE(&ap->tdev); if (!port_handle) return; @@ -1063,109 +1036,16 @@ void ata_acpi_on_disable(struct ata_device *dev) ata_acpi_clear_gtf(dev); } -static int compat_pci_ata(struct ata_port *ap) -{ - struct device *dev = ap->tdev.parent; - struct pci_dev *pdev; - - if (!is_pci_dev(dev)) - return 0; - - pdev = to_pci_dev(dev); - - if ((pdev->class >> 8) != PCI_CLASS_STORAGE_SATA && - (pdev->class >> 8) != PCI_CLASS_STORAGE_IDE) - return 0; - - return 1; -} - -static int ata_acpi_bind_host(struct ata_port *ap, acpi_handle *handle) -{ - if (libata_noacpi || ap->flags & ATA_FLAG_ACPI_SATA) - return -ENODEV; - - *handle = acpi_get_child(DEVICE_ACPI_HANDLE(ap->tdev.parent), - ap->port_no); - - if (!*handle) - return -ENODEV; - - if (__ata_acpi_gtm(ap, *handle, &ap->__acpi_init_gtm) == 0) - ap->pflags |= ATA_PFLAG_INIT_GTM_VALID; - - return 0; -} - -static int ata_acpi_bind_device(struct ata_port *ap, struct scsi_device *sdev, - acpi_handle *handle) -{ - struct ata_device *ata_dev; - - if (ap->flags & ATA_FLAG_ACPI_SATA) { - if (!sata_pmp_attached(ap)) - ata_dev = &ap->link.device[sdev->id]; - else - ata_dev = &ap->pmp_link[sdev->channel].device[sdev->id]; - } - else { - ata_dev = &ap->link.device[sdev->id]; - } - - *handle = ata_dev_acpi_handle(ata_dev); - - if (!*handle) - return -ENODEV; - - return 0; -} - -static int is_ata_port(const struct device *dev) -{ - return dev->type == &ata_port_type; -} - -static struct ata_port *dev_to_ata_port(struct device *dev) -{ - while (!is_ata_port(dev)) { - if (!dev->parent) - return NULL; - dev = dev->parent; - } - return to_ata_port(dev); -} - -static int ata_acpi_find_device(struct device *dev, acpi_handle *handle) -{ - struct ata_port *ap = dev_to_ata_port(dev); - - if (!ap) - return -ENODEV; - - if (!compat_pci_ata(ap)) - return -ENODEV; - - if (scsi_is_host_device(dev)) - return ata_acpi_bind_host(ap, handle); - else if (scsi_is_sdev_device(dev)) { - struct scsi_device *sdev = to_scsi_device(dev); - - return ata_acpi_bind_device(ap, sdev, handle); - } else - return -ENODEV; -} - -static struct acpi_bus_type ata_acpi_bus = { - .name = "ATA", - .find_device = ata_acpi_find_device, -}; - -int ata_acpi_register(void) +void ata_scsi_acpi_bind(struct ata_device *dev) { - return scsi_register_acpi_bus_type(&ata_acpi_bus); + acpi_handle handle = ata_dev_acpi_handle(dev); + if (handle) + acpi_dev_pm_add_dependent(handle, &dev->sdev->sdev_gendev); } -void ata_acpi_unregister(void) +void ata_scsi_acpi_unbind(struct ata_device *dev) { - scsi_unregister_acpi_bus_type(&ata_acpi_bus); + acpi_handle handle = ata_dev_acpi_handle(dev); + if (handle) + acpi_dev_pm_remove_dependent(handle, &dev->sdev->sdev_gendev); } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index c24354d44f3d..39e78e4524a3 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -6150,8 +6150,6 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) if (rc) goto err_tadd; - ata_acpi_hotplug_init(host); - /* set cable, sata_spd_limit and report */ for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; @@ -6632,8 +6630,6 @@ static int __init ata_init(void) ata_parse_force_param(); - ata_acpi_register(); - rc = ata_sff_init(); if (rc) { kfree(ata_force_tbl); @@ -6660,7 +6656,6 @@ static void __exit ata_exit(void) ata_release_transport(ata_scsi_transport_template); libata_transport_exit(); ata_sff_exit(); - ata_acpi_unregister(); kfree(ata_force_tbl); } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 83c08907e042..f177ad6bfd09 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -49,7 +49,6 @@ #include #include #include -#include #include #include "libata.h" @@ -3665,9 +3664,7 @@ void ata_scsi_scan_host(struct ata_port *ap, int sync) if (!IS_ERR(sdev)) { dev->sdev = sdev; scsi_device_put(sdev); - if (zpodd_dev_enabled(dev)) - dev_pm_qos_expose_flags( - &sdev->sdev_gendev, 0); + ata_scsi_acpi_bind(dev); } else { dev->sdev = NULL; } @@ -3755,6 +3752,8 @@ static void ata_scsi_remove_dev(struct ata_device *dev) struct scsi_device *sdev; unsigned long flags; + ata_scsi_acpi_unbind(dev); + /* Alas, we need to grab scan_mutex to ensure SCSI device * state doesn't change underneath us and thus * scsi_device_get() always succeeds. The mutex locking can @@ -3764,9 +3763,6 @@ static void ata_scsi_remove_dev(struct ata_device *dev) mutex_lock(&ap->scsi_host->scan_mutex); spin_lock_irqsave(ap->lock, flags); - if (zpodd_dev_enabled(dev)) - zpodd_exit(dev); - /* clearing dev->sdev is protected by host lock */ sdev = dev->sdev; dev->sdev = NULL; @@ -3816,6 +3812,9 @@ static void ata_scsi_handle_link_detach(struct ata_link *link) dev->flags &= ~ATA_DFLAG_DETACHED; spin_unlock_irqrestore(ap->lock, flags); + if (zpodd_dev_enabled(dev)) + zpodd_exit(dev); + ata_scsi_remove_dev(dev); } } diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index 077a856f5fd0..150a917f0c3c 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -287,6 +287,7 @@ int ata_tport_add(struct device *parent, dev->release = ata_tport_release; dev_set_name(dev, "ata%d", ap->print_id); transport_setup_device(dev); + ata_acpi_bind_port(ap); error = device_add(dev); if (error) { goto tport_err; @@ -644,6 +645,7 @@ static int ata_tdev_add(struct ata_device *ata_dev) dev_set_name(dev, "dev%d.%d.0", ap->print_id, link->pmp); transport_setup_device(dev); + ata_acpi_bind_dev(ata_dev); error = device_add(dev); if (error) { ata_tdev_free(ata_dev); diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c index cd8daf47188b..68f9e3293e9c 100644 --- a/drivers/ata/libata-zpodd.c +++ b/drivers/ata/libata-zpodd.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include "libata.h" @@ -190,8 +191,8 @@ void zpodd_enable_run_wake(struct ata_device *dev) sdev_disable_disk_events(dev->sdev); zpodd->powered_off = true; - device_set_run_wake(&dev->sdev->sdev_gendev, true); - acpi_pm_device_run_wake(&dev->sdev->sdev_gendev, true); + device_set_run_wake(&dev->tdev, true); + acpi_pm_device_run_wake(&dev->tdev, true); } /* Disable runtime wake capability if it is enabled */ @@ -200,8 +201,8 @@ void zpodd_disable_run_wake(struct ata_device *dev) struct zpodd *zpodd = dev->zpodd; if (zpodd->powered_off) { - acpi_pm_device_run_wake(&dev->sdev->sdev_gendev, false); - device_set_run_wake(&dev->sdev->sdev_gendev, false); + acpi_pm_device_run_wake(&dev->tdev, false); + device_set_run_wake(&dev->tdev, false); } } @@ -262,7 +263,7 @@ static void ata_acpi_add_pm_notifier(struct ata_device *dev) static void ata_acpi_remove_pm_notifier(struct ata_device *dev) { - acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->sdev->sdev_gendev); + acpi_handle handle = ata_dev_acpi_handle(dev); acpi_remove_notify_handler(handle, ACPI_SYSTEM_NOTIFY, zpodd_wake_dev); } @@ -290,6 +291,7 @@ void zpodd_init(struct ata_device *dev) ata_acpi_add_pm_notifier(dev); zpodd->dev = dev; dev->zpodd = zpodd; + dev_pm_qos_expose_flags(&dev->tdev, 0); } void zpodd_exit(struct ata_device *dev) diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index cc8a6e879dfb..3e9cc95a0222 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -118,9 +118,11 @@ extern void ata_acpi_on_resume(struct ata_port *ap); extern int ata_acpi_on_devcfg(struct ata_device *dev); extern void ata_acpi_on_disable(struct ata_device *dev); extern void ata_acpi_set_state(struct ata_port *ap, pm_message_t state); -extern int ata_acpi_register(void); -extern void ata_acpi_unregister(void); -extern void ata_acpi_hotplug_init(struct ata_host *host); +extern void ata_acpi_bind_port(struct ata_port *ap); +extern void ata_acpi_bind_dev(struct ata_device *dev); +extern acpi_handle ata_dev_acpi_handle(struct ata_device *dev); +extern void ata_scsi_acpi_bind(struct ata_device *dev); +extern void ata_scsi_acpi_unbind(struct ata_device *dev); #else static inline void ata_acpi_dissociate(struct ata_host *host) { } static inline int ata_acpi_on_suspend(struct ata_port *ap) { return 0; } @@ -129,9 +131,11 @@ static inline int ata_acpi_on_devcfg(struct ata_device *dev) { return 0; } static inline void ata_acpi_on_disable(struct ata_device *dev) { } static inline void ata_acpi_set_state(struct ata_port *ap, pm_message_t state) { } -static inline int ata_acpi_register(void) { return 0; } -static inline void ata_acpi_unregister(void) { } -static inline void ata_acpi_hotplug_init(struct ata_host *host) {} +static inline void ata_acpi_bind_port(struct ata_port *ap) {} +static inline void ata_acpi_bind_dev(struct ata_device *dev) {} +static inline acpi_handle ata_dev_acpi_handle(struct ata_device *dev) { return NULL; } +static inline void ata_scsi_acpi_bind(struct ata_device *dev) {} +static inline void ata_scsi_acpi_unbind(struct ata_device *dev) {} #endif /* libata-scsi.c */ diff --git a/drivers/ata/pata_acpi.c b/drivers/ata/pata_acpi.c index 09723b76beac..73212c9c6d5b 100644 --- a/drivers/ata/pata_acpi.c +++ b/drivers/ata/pata_acpi.c @@ -39,7 +39,7 @@ static int pacpi_pre_reset(struct ata_link *link, unsigned long deadline) { struct ata_port *ap = link->ap; struct pata_acpi *acpi = ap->private_data; - if (ata_ap_acpi_handle(ap) == NULL || ata_acpi_gtm(ap, &acpi->gtm) < 0) + if (ACPI_HANDLE(&ap->tdev) == NULL || ata_acpi_gtm(ap, &acpi->gtm) < 0) return -ENODEV; return ata_sff_prereset(link, deadline); @@ -195,7 +195,7 @@ static int pacpi_port_start(struct ata_port *ap) struct pci_dev *pdev = to_pci_dev(ap->host->dev); struct pata_acpi *acpi; - if (ata_ap_acpi_handle(ap) == NULL) + if (ACPI_HANDLE(&ap->tdev) == NULL) return -ENODEV; acpi = ap->private_data = devm_kzalloc(&pdev->dev, sizeof(struct pata_acpi), GFP_KERNEL); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 124392f3091e..f0ddc7dd06d3 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -68,28 +68,6 @@ static struct scsi_host_sg_pool scsi_sg_pools[] = { struct kmem_cache *scsi_sdb_cache; -#ifdef CONFIG_ACPI -#include - -static bool acpi_scsi_bus_match(struct device *dev) -{ - return dev->bus == &scsi_bus_type; -} - -int scsi_register_acpi_bus_type(struct acpi_bus_type *bus) -{ - bus->match = acpi_scsi_bus_match; - return register_acpi_bus_type(bus); -} -EXPORT_SYMBOL_GPL(scsi_register_acpi_bus_type); - -void scsi_unregister_acpi_bus_type(struct acpi_bus_type *bus) -{ - unregister_acpi_bus_type(bus); -} -EXPORT_SYMBOL_GPL(scsi_unregister_acpi_bus_type); -#endif - /* * When to reinvoke queueing after a resource shortage. It's 3 msecs to * not change behaviour from the previous unplug mechanism, experimentation diff --git a/include/linux/libata.h b/include/linux/libata.h index 283d66bc603c..3198617905e1 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1244,8 +1244,6 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm); int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm); unsigned long ata_acpi_gtm_xfermask(struct ata_device *dev, const struct ata_acpi_gtm *gtm); -acpi_handle ata_ap_acpi_handle(struct ata_port *ap); -acpi_handle ata_dev_acpi_handle(struct ata_device *dev); int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm); #else static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) -- cgit v1.2.3-71-gd317 From abec1a806e0c3cf168999667d5fb6218398ef12a Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Aug 2013 19:01:58 +0000 Subject: percpu: Make __verify_pcu_ptr handle per cpu pointers to arrays __verify_pcpu_ptr() will cause a compilation failure if the type of the pointer is a pointer to a fixed array of objects. Adding zero to the pointer converts the type of pointer to that pointing to a single object of the array. Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/percpu-defs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 27ef6b190ea6..57e890abe1f0 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -22,9 +22,12 @@ * Macro which verifies @ptr is a percpu pointer without evaluating * @ptr. This is to be used in percpu accessors to verify that the * input parameter is a percpu pointer. + * + * + 0 is required in order to convert the pointer type from a + * potential array type to a pointer to a single item of the array. */ #define __verify_pcpu_ptr(ptr) do { \ - const void __percpu *__vpp_verify = (typeof(ptr))NULL; \ + const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL; \ (void)__vpp_verify; \ } while (0) -- cgit v1.2.3-71-gd317 From a65fcce75a75c0d41b938f86d09d42b6f1733309 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 23 Aug 2013 15:02:01 -0700 Subject: sysfs: create __ATTR_WO() This creates the macro __ATTR_WO() for write-only attributes, instead of having to "open define" them. Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b5a9d9b26bd4..69c1ff003628 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -80,6 +80,11 @@ struct attribute_group { .show = _name##_show, \ } +#define __ATTR_WO(_name) { \ + .attr = { .name = __stringify(_name), .mode = S_IWUSR }, \ + .store = _name##_store, \ +} + #define __ATTR_RW(_name) __ATTR(_name, (S_IWUSR | S_IRUGO), \ _name##_show, _name##_store) -- cgit v1.2.3-71-gd317 From 1130c55c757660ac83bd2de220f08580c56b6855 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 23 Aug 2013 15:02:56 -0700 Subject: driver core: create write-only attribute macros for devices and drivers This creates the macros DRIVER_ATTR_WO() and DEVICE_ATTR_WO() for write-only attributes for drivers and devices. Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 26e23b22ed0a..0ed94b5f67fc 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -277,6 +277,8 @@ struct driver_attribute { struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) #define DRIVER_ATTR_RO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_RO(_name) +#define DRIVER_ATTR_WO(_name) \ + struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) extern int __must_check driver_create_file(struct device_driver *driver, const struct driver_attribute *attr); @@ -534,6 +536,8 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, struct device_attribute dev_attr_##_name = __ATTR_RW(_name) #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) +#define DEVICE_ATTR_WO(_name) \ + struct device_attribute dev_attr_##_name = __ATTR_WO(_name) #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } -- cgit v1.2.3-71-gd317 From 118b23022512eb2f41ce42db70dc0568d00be4ba Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 24 Aug 2013 12:08:17 -0400 Subject: cope with potentially long ->d_dname() output for shmem/hugetlb dynamic_dname() is both too much and too little for those - the output may be well in excess of 64 bytes dynamic_dname() assumes to be enough (thanks to ashmem feeding really long names to shmem_file_setup()) and vsnprintf() is an overkill for those guys. Signed-off-by: Al Viro --- fs/dcache.c | 11 +++++++++++ fs/hugetlbfs/inode.c | 8 +------- include/linux/dcache.h | 1 + mm/shmem.c | 8 +------- 4 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/dcache.c b/fs/dcache.c index 87bdb5329c3c..83cfb834db03 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2724,6 +2724,17 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen, return memcpy(buffer, temp, sz); } +char *simple_dname(struct dentry *dentry, char *buffer, int buflen) +{ + char *end = buffer + buflen; + /* these dentries are never renamed, so d_lock is not needed */ + if (prepend(&end, &buflen, " (deleted)", 11) || + prepend_name(&end, &buflen, &dentry->d_name) || + prepend(&end, &buflen, "/", 1)) + end = ERR_PTR(-ENAMETOOLONG); + return end; +} + /* * Write full pathname from the root of the filesystem into the buffer. */ diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 34423978b170..d19b30ababf1 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -926,14 +926,8 @@ static int get_hstate_idx(int page_size_log) return h - hstates; } -static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen) -{ - return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)", - dentry->d_name.name); -} - static struct dentry_operations anon_ops = { - .d_dname = hugetlb_dname + .d_dname = simple_dname }; /* diff --git a/include/linux/dcache.h b/include/linux/dcache.h index b90337c9d468..4a12532da8c4 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -336,6 +336,7 @@ extern int d_validate(struct dentry *, struct dentry *); * helper function for dentry_operations.d_dname() members */ extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); +extern char *simple_dname(struct dentry *, char *, int); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); diff --git a/mm/shmem.c b/mm/shmem.c index 8335dbd3fc35..e43dc555069d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2909,14 +2909,8 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); /* common code */ -static char *shmem_dname(struct dentry *dentry, char *buffer, int buflen) -{ - return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)", - dentry->d_name.name); -} - static struct dentry_operations anon_ops = { - .d_dname = shmem_dname + .d_dname = simple_dname }; /** -- cgit v1.2.3-71-gd317 From 8be5ad9acb7c11b9d717bcdbe3d6de0dab081a39 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:48 -0700 Subject: libata: Populate host-to-device FIS "auxiliary" field SATA 3.1 added an "auxiliary" field to the host-to-device FIS. Populate the host-to-device FIS with the new field via the taskfile struct. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 10 ++++++---- include/linux/libata.h | 4 ++++ 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 39e78e4524a3..2b4e92568850 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -546,6 +546,8 @@ int atapi_cmd_type(u8 opcode) */ void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis) { + const __le32 aux = cpu_to_le32(tf->auxiliary); + fis[0] = 0x27; /* Register - Host to Device FIS */ fis[1] = pmp & 0xf; /* Port multiplier number*/ if (is_cmd) @@ -569,10 +571,10 @@ void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis) fis[14] = 0; fis[15] = tf->ctl; - fis[16] = 0; - fis[17] = 0; - fis[18] = 0; - fis[19] = 0; + fis[16] = aux & 0xff; + fis[17] = (aux >> 8) & 0xff; + fis[18] = (aux >> 16) & 0xff; + fis[19] = (aux >> 24) & 0xff; } /** diff --git a/include/linux/libata.h b/include/linux/libata.h index 3198617905e1..9b6ba196179f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -555,6 +555,10 @@ struct ata_taskfile { u8 device; u8 command; /* IO operation */ + + u32 auxiliary; /* auxiliary field */ + /* from SATA 3.1 and */ + /* ATA-8 ACS-3 */ }; #ifdef CONFIG_ATA_SFF -- cgit v1.2.3-71-gd317 From 40fb59e75ad197a1c4ca2fbccef85432d8d103f8 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:49 -0700 Subject: libata: Add H2D FIS "auxiliary" port flag Add a new port flag, ATA_FLAG_FPDMA_AUX, used to indicate support for transmission of the H2D FIS 'auxiliary' field. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- drivers/ata/ahci.c | 8 ++++++++ include/linux/libata.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 5064f3ea20f1..8d41c57fd969 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1288,6 +1288,14 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ if (!(hpriv->flags & AHCI_HFLAG_NO_FPDMA_AA)) pi.flags |= ATA_FLAG_FPDMA_AA; + + /* + * All AHCI controllers should be forward-compatible + * with the new auxiliary field. This code should be + * conditionalized if any buggy AHCI controllers are + * encountered. + */ + pi.flags |= ATA_FLAG_FPDMA_AUX; } if (hpriv->cap & HOST_CAP_PMP) diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b6ba196179f..578f98c3ff57 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -223,6 +223,7 @@ enum { ATA_FLAG_ACPI_SATA = (1 << 17), /* need native SATA ACPI layout */ ATA_FLAG_AN = (1 << 18), /* controller supports AN */ ATA_FLAG_PMP = (1 << 19), /* controller supports PMP */ + ATA_FLAG_FPDMA_AUX = (1 << 20), /* controller supports H2DFIS aux field */ ATA_FLAG_EM = (1 << 21), /* driver supports enclosure * management */ ATA_FLAG_SW_ACTIVITY = (1 << 22), /* driver supports sw activity -- cgit v1.2.3-71-gd317 From ed36911c747c18525691c0aa0fbe6b918c8eac19 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:50 -0700 Subject: libata: Add support for SEND/RECEIVE FPDMA QUEUED Add support for the following ATA opcodes, which are present in SATA 3.1 and T13 ATA ACS-3: SEND FPDMA QUEUED RECEIVE FPDMA QUEUED Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 16 ++++++++++++++++ include/linux/ata.h | 21 +++++++++++++++++++++ include/linux/libata.h | 4 ++++ 3 files changed, 41 insertions(+) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 2b4e92568850..a044be99841a 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2141,6 +2141,22 @@ static int ata_dev_config_ncq(struct ata_device *dev, else snprintf(desc, desc_sz, "NCQ (depth %d/%d)%s", hdepth, ddepth, aa_desc); + + if ((ap->flags & ATA_FLAG_FPDMA_AUX) && + ata_id_has_ncq_send_and_recv(dev->id)) { + err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_SEND_RECV, + 0, ap->sector_buf, 1); + if (err_mask) { + ata_dev_dbg(dev, + "failed to get NCQ Send/Recv Log Emask 0x%x\n", + err_mask); + } else { + dev->flags |= ATA_DFLAG_NCQ_SEND_RECV; + memcpy(dev->ncq_send_recv_cmds, ap->sector_buf, + ATA_LOG_NCQ_SEND_RECV_SIZE); + } + } + return 0; } diff --git a/include/linux/ata.h b/include/linux/ata.h index f63fb1afc5cc..bf4c69ca76df 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -239,6 +239,8 @@ enum { ATA_CMD_WRITE_QUEUED_FUA_EXT = 0x3E, ATA_CMD_FPDMA_READ = 0x60, ATA_CMD_FPDMA_WRITE = 0x61, + ATA_CMD_FPDMA_SEND = 0x64, + ATA_CMD_FPDMA_RECV = 0x65, ATA_CMD_PIO_READ = 0x20, ATA_CMD_PIO_READ_EXT = 0x24, ATA_CMD_PIO_WRITE = 0x30, @@ -293,8 +295,13 @@ enum { /* marked obsolete in the ATA/ATAPI-7 spec */ ATA_CMD_RESTORE = 0x10, + /* Subcmds for ATA_CMD_FPDMA_SEND */ + ATA_SUBCMD_FPDMA_SEND_DSM = 0x00, + ATA_SUBCMD_FPDMA_SEND_WR_LOG_DMA_EXT = 0x02, + /* READ_LOG_EXT pages */ ATA_LOG_SATA_NCQ = 0x10, + ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_SATA_ID_DEV_DATA = 0x30, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_DEVSLP_OFFSET = 0x30, @@ -305,6 +312,15 @@ enum { ATA_LOG_DEVSLP_VALID = 0x07, ATA_LOG_DEVSLP_VALID_MASK = 0x80, + /* NCQ send and receive log */ + ATA_LOG_NCQ_SEND_RECV_SUBCMDS_OFFSET = 0x00, + ATA_LOG_NCQ_SEND_RECV_SUBCMDS_DSM = (1 << 0), + ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET = 0x04, + ATA_LOG_NCQ_SEND_RECV_DSM_TRIM = (1 << 0), + ATA_LOG_NCQ_SEND_RECV_RD_LOG_OFFSET = 0x08, + ATA_LOG_NCQ_SEND_RECV_WR_LOG_OFFSET = 0x0C, + ATA_LOG_NCQ_SEND_RECV_SIZE = 0x10, + /* READ/WRITE LONG (obsolete) */ ATA_CMD_READ_LONG = 0x22, ATA_CMD_READ_LONG_ONCE = 0x23, @@ -772,6 +788,11 @@ static inline int ata_id_rotation_rate(const u16 *id) return val; } +static inline bool ata_id_has_ncq_send_and_recv(const u16 *id) +{ + return id[ATA_ID_SATA_CAPABILITY_2] & BIT(6); +} + static inline bool ata_id_has_trim(const u16 *id) { if (ata_id_major_version(id) >= 7 && diff --git a/include/linux/libata.h b/include/linux/libata.h index 578f98c3ff57..a988c2d7d0e8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -172,6 +172,7 @@ enum { ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ + ATA_DFLAG_NCQ_SEND_RECV = (1 << 19), /* device supports NCQ SEND and RECV */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), @@ -704,6 +705,9 @@ struct ata_device { /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; + /* NCQ send and receive log subcommand support */ + u8 ncq_send_recv_cmds[ATA_LOG_NCQ_SEND_RECV_SIZE]; + /* error history */ int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ -- cgit v1.2.3-71-gd317 From 87fb6c31b9ef9ccab9a822b01fc3911f026a29bb Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Sat, 24 Aug 2013 23:22:51 -0700 Subject: libata: Add support for queued DSM TRIM Some new SSDs support the queued version of the DSM TRIM command. Let the driver use the new command if supported. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo --- drivers/ata/libata-scsi.c | 25 +++++++++++++++++++------ include/linux/libata.h | 7 +++++++ 2 files changed, 26 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index f177ad6bfd09..58026106fcd9 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3097,12 +3097,25 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc) buf = page_address(sg_page(scsi_sglist(scmd))); size = ata_set_lba_range_entries(buf, 512, block, n_block); - tf->protocol = ATA_PROT_DMA; - tf->hob_feature = 0; - tf->feature = ATA_DSM_TRIM; - tf->hob_nsect = (size / 512) >> 8; - tf->nsect = size / 512; - tf->command = ATA_CMD_DSM; + if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) { + /* Newer devices support queued TRIM commands */ + tf->protocol = ATA_PROT_NCQ; + tf->command = ATA_CMD_FPDMA_SEND; + tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f; + tf->nsect = qc->tag << 3; + tf->hob_feature = (size / 512) >> 8; + tf->feature = size / 512; + + tf->auxiliary = 1; + } else { + tf->protocol = ATA_PROT_DMA; + tf->hob_feature = 0; + tf->feature = ATA_DSM_TRIM; + tf->hob_nsect = (size / 512) >> 8; + tf->nsect = size / 512; + tf->command = ATA_CMD_DSM; + } + tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48 | ATA_TFLAG_WRITE; diff --git a/include/linux/libata.h b/include/linux/libata.h index a988c2d7d0e8..0e23c26485f4 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1606,6 +1606,13 @@ static inline int ata_ncq_enabled(struct ata_device *dev) ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ; } +static inline bool ata_fpdma_dsm_supported(struct ata_device *dev) +{ + return (dev->flags & ATA_DFLAG_NCQ_SEND_RECV) && + (dev->ncq_send_recv_cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] & + ATA_LOG_NCQ_SEND_RECV_DSM_TRIM); +} + static inline void ata_qc_set_polling(struct ata_queued_cmd *qc) { qc->tf.ctl |= ATA_NIEN; -- cgit v1.2.3-71-gd317 From 35cf083619da5677f83e9a8eae813f0b413d7082 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 26 Aug 2013 18:40:56 -0400 Subject: cgroup: rename cgroup_css_from_dir() to css_from_dir() and update its syntax cgroup_css_from_dir() will grow another user. In preparation, make the following changes. * All css functions are prefixed with just "css_", rename it to css_from_dir(). * Take dentry * instead of file * as dentry is what ultimately identifies a cgroup and file may not always be available. Note that the function now checkes whether @dentry->d_inode is NULL as the caller now may specify a negative dentry. * Make it take cgroup_subsys * instead of integer subsys_id. This simplifies the function and allows specifying no subsystem for cgroup->dummy_css. * Make return section a bit less verbose. This patch doesn't introduce any behavior changes. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Kirill A. Shutemov Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar --- include/linux/cgroup.h | 3 ++- kernel/cgroup.c | 26 ++++++++++---------------- kernel/events/core.c | 2 +- 3 files changed, 13 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b685955d4b29..21ba29869eb8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -903,7 +903,8 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg, /* Get id and depth of css */ unsigned short css_id(struct cgroup_subsys_state *css); -struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id); +struct cgroup_subsys_state *css_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss); #else /* !CONFIG_CGROUPS */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index ef43e3f453ef..921b1387c944 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -5700,34 +5700,28 @@ struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id) EXPORT_SYMBOL_GPL(css_lookup); /** - * cgroup_css_from_dir - get corresponding css from file open on cgroup dir - * @f: directory file of interest - * @id: subsystem id of interest + * css_from_dir - get corresponding css from the dentry of a cgroup dir + * @dentry: directory dentry of interest + * @ss: subsystem of interest * * Must be called under RCU read lock. The caller is responsible for * pinning the returned css if it needs to be accessed outside the RCU * critical section. */ -struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id) +struct cgroup_subsys_state *css_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss) { struct cgroup *cgrp; - struct inode *inode; - struct cgroup_subsys_state *css; WARN_ON_ONCE(!rcu_read_lock_held()); - inode = file_inode(f); - /* check in cgroup filesystem dir */ - if (inode->i_op != &cgroup_dir_inode_operations) + /* is @dentry a cgroup dir? */ + if (!dentry->d_inode || + dentry->d_inode->i_op != &cgroup_dir_inode_operations) return ERR_PTR(-EBADF); - if (id < 0 || id >= CGROUP_SUBSYS_COUNT) - return ERR_PTR(-EINVAL); - - /* get cgroup */ - cgrp = __d_cgrp(f->f_dentry); - css = cgroup_css(cgrp, id); - return css ? css : ERR_PTR(-ENOENT); + cgrp = __d_cgrp(dentry); + return cgroup_css(cgrp, ss->subsys_id) ?: ERR_PTR(-ENOENT); } /** diff --git a/kernel/events/core.c b/kernel/events/core.c index 23261f957713..b59ab6632f30 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -593,7 +593,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, rcu_read_lock(); - css = cgroup_css_from_dir(f.file, perf_subsys_id); + css = css_from_dir(f.file->f_dentry, &perf_subsys); if (IS_ERR(css)) { ret = PTR_ERR(css); goto out; -- cgit v1.2.3-71-gd317 From 9fa4db334c7d9570aec7a5121e84fae99aae1d04 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 26 Aug 2013 18:40:56 -0400 Subject: cgroup: implement CFTYPE_NO_PREFIX When cgroup files are created, cgroup core automatically prepends the name of the subsystem as prefix. This patch adds CFTYPE_NO_ which disables the automatic prefix. This is to work around historical baggages and shouldn't be used for new files. This will be used to move "cgroup.event_control" from cgroup core to memcg. Signed-off-by: Tejun Heo Acked-by: Li Zefan Acked-by: Kirill A. Shutemov Cc: Glauber Costa --- include/linux/cgroup.h | 1 + kernel/cgroup.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 21ba29869eb8..3561d305b1e0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -411,6 +411,7 @@ enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ }; #define MAX_CFTYPE_NAME 64 diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7516668d8325..a41dc87cd07e 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2756,7 +2756,8 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) umode_t mode; char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; - if (cft->ss && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { + if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && + !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { strcpy(name, cft->ss->name); strcat(name, "."); } -- cgit v1.2.3-71-gd317 From c2b1df2eb42978073ec27c99cc199d20ae48b849 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 22 Aug 2013 11:39:16 -0700 Subject: Rename nsproxy.pid_ns to nsproxy.pid_ns_for_children nsproxy.pid_ns is *not* the task's pid namespace. The name should clarify that. This makes it more obvious that setns on a pid namespace is weird -- it won't change the pid namespace shown in procfs. Signed-off-by: Andy Lutomirski Reviewed-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/nsproxy.h | 6 +++++- kernel/fork.c | 5 +++-- kernel/nsproxy.c | 27 ++++++++++++++------------- kernel/pid_namespace.c | 4 ++-- 4 files changed, 24 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 10e5947491c7..b4ec59d159ac 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -14,6 +14,10 @@ struct fs_struct; * A structure to contain pointers to all per-process * namespaces - fs (mount), uts, network, sysvipc, etc. * + * The pid namespace is an exception -- it's accessed using + * task_active_pid_ns. The pid namespace here is the + * namespace that children will use. + * * 'count' is the number of tasks holding a reference. * The count for each namespace, then, will be the number * of nsproxies pointing to it, not the number of tasks. @@ -27,7 +31,7 @@ struct nsproxy { struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; - struct pid_namespace *pid_ns; + struct pid_namespace *pid_ns_for_children; struct net *net_ns; }; extern struct nsproxy init_nsproxy; diff --git a/kernel/fork.c b/kernel/fork.c index e23bb19e2a3e..bf46287c91a4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1177,7 +1177,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, * don't allow the creation of threads. */ if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) && - (task_active_pid_ns(current) != current->nsproxy->pid_ns)) + (task_active_pid_ns(current) != + current->nsproxy->pid_ns_for_children)) return ERR_PTR(-EINVAL); retval = security_task_create(clone_flags); @@ -1351,7 +1352,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (pid != &init_struct_pid) { retval = -ENOMEM; - pid = alloc_pid(p->nsproxy->pid_ns); + pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (!pid) goto bad_fork_cleanup_io; } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 364ceab15f0c..997cbb951a3b 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -29,15 +29,15 @@ static struct kmem_cache *nsproxy_cachep; struct nsproxy init_nsproxy = { - .count = ATOMIC_INIT(1), - .uts_ns = &init_uts_ns, + .count = ATOMIC_INIT(1), + .uts_ns = &init_uts_ns, #if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) - .ipc_ns = &init_ipc_ns, + .ipc_ns = &init_ipc_ns, #endif - .mnt_ns = NULL, - .pid_ns = &init_pid_ns, + .mnt_ns = NULL, + .pid_ns_for_children = &init_pid_ns, #ifdef CONFIG_NET - .net_ns = &init_net, + .net_ns = &init_net, #endif }; @@ -85,9 +85,10 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_ipc; } - new_nsp->pid_ns = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns); - if (IS_ERR(new_nsp->pid_ns)) { - err = PTR_ERR(new_nsp->pid_ns); + new_nsp->pid_ns_for_children = + copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children); + if (IS_ERR(new_nsp->pid_ns_for_children)) { + err = PTR_ERR(new_nsp->pid_ns_for_children); goto out_pid; } @@ -100,8 +101,8 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, return new_nsp; out_net: - if (new_nsp->pid_ns) - put_pid_ns(new_nsp->pid_ns); + if (new_nsp->pid_ns_for_children) + put_pid_ns(new_nsp->pid_ns_for_children); out_pid: if (new_nsp->ipc_ns) put_ipc_ns(new_nsp->ipc_ns); @@ -174,8 +175,8 @@ void free_nsproxy(struct nsproxy *ns) put_uts_ns(ns->uts_ns); if (ns->ipc_ns) put_ipc_ns(ns->ipc_ns); - if (ns->pid_ns) - put_pid_ns(ns->pid_ns); + if (ns->pid_ns_for_children) + put_pid_ns(ns->pid_ns_for_children); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); } diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 6917e8edb48e..601bb361c235 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -349,8 +349,8 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns) if (ancestor != active) return -EINVAL; - put_pid_ns(nsproxy->pid_ns); - nsproxy->pid_ns = get_pid_ns(new); + put_pid_ns(nsproxy->pid_ns_for_children); + nsproxy->pid_ns_for_children = get_pid_ns(new); return 0; } -- cgit v1.2.3-71-gd317 From f799878000c5a9a1e6a311dfd4faa50601dcb1f8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Aug 2013 17:24:49 -0700 Subject: sysfs: add sysfs_create/remove_groups for when SYSFS is not enabled We need these functions for when CONFIG_SYSFS=n. Reported-by: Fengguang Wu Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 69c1ff003628..e647a1aa0723 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -350,6 +350,11 @@ static inline int sysfs_create_group(struct kobject *kobj, return 0; } +static inline int sysfs_create_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ +} + static inline int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp) { @@ -361,6 +366,11 @@ static inline void sysfs_remove_group(struct kobject *kobj, { } +static inline void sysfs_remove_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ +} + static inline int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { -- cgit v1.2.3-71-gd317 From 3159269ef484954985cbbf1ff89976f090a18b24 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 26 Aug 2013 09:58:30 +0200 Subject: debugfs: provide debugfs_create_x64() when disabled commit 15b0beaa332b3923cc ("Add x64 support to debugfs") added debugfs_create_x64(), but forgot to provide it when debugfs is disabled, causing problems when code tries to use it even then. Provide the appropriate static inline. Cc: Huang Ying Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index d68b4ea7343c..263489d0788d 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -192,6 +192,13 @@ static inline struct dentry *debugfs_create_x32(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_x64(const char *name, umode_t mode, + struct dentry *parent, + u64 *value) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) -- cgit v1.2.3-71-gd317 From 574979c617eb9593f8dfbb804da3f0e00f8bf28e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Aug 2013 09:51:41 -0700 Subject: sysfs: sysfs_create_groups returns a value. When I included the "empty" function for sysfs_create_groups() when CONFIG_SYSFS=n, I forgot to return a value for it, so things blew up the build. This patch fixes that, stupid me. Reported-by: kbuild test robot Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index e647a1aa0723..11baec7c9b26 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -353,6 +353,7 @@ static inline int sysfs_create_group(struct kobject *kobj, static inline int sysfs_create_groups(struct kobject *kobj, const struct attribute_group **groups) { + return 0; } static inline int sysfs_update_group(struct kobject *kobj, -- cgit v1.2.3-71-gd317 From 8ef2d6511f7eba89ef5fe41cc83008ae63368aa2 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Tue, 27 Aug 2013 17:47:34 +0300 Subject: dev-core: fix build break when DEBUG is enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When DEBUG is defined, dev_dbg_ratelimited uses dynamic debug data structures even when CONFIG_DYNAMIC_DEBUG is not defined. It leads to build break. For example, when I try to use dev_dbg_ratelimited in USB code and CONFIG_USB_DEBUG is enabled, but CONFIG_DYNAMIC_DEBUG is not, I get: CC [M] drivers/usb/host/xhci-ring.o drivers/usb/host/xhci-ring.c: In function ‘xhci_queue_intr_tx’: drivers/usb/host/xhci-ring.c:3059:3: error: implicit declaration of function ‘DEFINE_DYNAMIC_DEBUG_METADATA’ [-Werror=implicit-function-declaration] drivers/usb/host/xhci-ring.c:3059:3: error: ‘descriptor’ undeclared (first use in this function) drivers/usb/host/xhci-ring.c:3059:3: note: each undeclared identifier is reported only once for each function it appears in drivers/usb/host/xhci-ring.c:3059:3: error: implicit declaration of function ‘__dynamic_pr_debug’ [-Werror=implicit-function-declaration] drivers/usb/host/xhci-ring.c: In function ‘xhci_queue_isoc_tx_prepare’: drivers/usb/host/xhci-ring.c:3847:3: error: ‘descriptor’ undeclared (first use in this function) cc1: some warnings being treated as errors make[2]: *** [drivers/usb/host/xhci-ring.o] Error 1 make[1]: *** [drivers/usb/host] Error 2 make: *** [drivers/usb/] Error 2 This patch separates definition for CONFIG_DYNAMIC_DEBUG and DEBUG cases. [Note, Sarah moved the comment above the macro to avoid checkpatch warnings.] Signed-off-by: Dmitry Kasatkin Signed-off-by: Sarah Sharp Acked-by: Greg Kroah-Hartman --- include/linux/device.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..7d960d581e9c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1099,7 +1099,8 @@ do { \ dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__) #define dev_info_ratelimited(dev, fmt, ...) \ dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) || defined(DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) +/* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define dev_dbg_ratelimited(dev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ @@ -1108,8 +1109,17 @@ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ __ratelimit(&_rs)) \ - __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ - ##__VA_ARGS__); \ + __dynamic_dev_dbg(&descriptor, dev, fmt, \ + ##__VA_ARGS__); \ +} while (0) +#elif defined(DEBUG) +#define dev_dbg_ratelimited(dev, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ -- cgit v1.2.3-71-gd317 From 0f8f2aaaab0b0f9c13635cb02e7d19bdaa9aa1bb Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 28 Aug 2013 18:13:26 -0700 Subject: Add new lockref infrastructure reference implementation This introduces a new "lockref" structure that supports the concept of lockless updates of reference counts that still honor an attached spinlock. NOTE! This reference implementation is not the optimized lockless version, rather it is the fallback implementation using standard spinlocks. The actual optimized versions will be merged into 3.12, but I wanted to get the infrastructure in place and document the new interfaces. [ Also note that this particular commit is drastically cut-down minimal version of the original patch by Waiman. In order to properly credit the original author I'm marking Waiman as the author here, but in the end this patch bears little resemblance to the patch by Waiman. So blame any errors on me editing things down to the point where I can introduce the infrastructure before the merge window for 3.12 actually opens. - Linus ] Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 71 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 include/linux/lockref.h (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h new file mode 100644 index 000000000000..01233e01627a --- /dev/null +++ b/include/linux/lockref.h @@ -0,0 +1,71 @@ +#ifndef __LINUX_LOCKREF_H +#define __LINUX_LOCKREF_H + +/* + * Locked reference counts. + * + * These are different from just plain atomic refcounts in that they + * are atomic with respect to the spinlock that goes with them. In + * particular, there can be implementations that don't actually get + * the spinlock for the common decrement/increment operations, but they + * still have to check that the operation is done semantically as if + * the spinlock had been taken (using a cmpxchg operation that covers + * both the lock and the count word, or using memory transactions, for + * example). + */ + +#include + +struct lockref { + spinlock_t lock; + unsigned int count; +}; + +/** + * lockref_get - Increments reference count unconditionally + * @lockcnt: pointer to lockref structure + * + * This operation is only valid if you already hold a reference + * to the object, so you know the count cannot be zero. + */ +static inline void lockref_get(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + lockref->count++; + spin_unlock(&lockref->lock); +} + +/** + * lockref_get_not_zero - Increments count unless the count is 0 + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count is 0 + */ +static inline int lockref_get_not_zero(struct lockref *lockref) +{ + int retval = 0; + + spin_lock(&lockref->lock); + if (lockref->count) { + lockref->count++; + retval = 1; + } + spin_unlock(&lockref->lock); + return retval; +} + +/** + * lockref_put_or_lock - decrements count unless count <= 1 before decrement + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken + */ +static inline int lockref_put_or_lock(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + if (lockref->count <= 1) + return 0; + lockref->count--; + spin_unlock(&lockref->lock); + return 1; +} + +#endif /* __LINUX_LOCKREF_H */ -- cgit v1.2.3-71-gd317 From 98474236f72e5a8b89c14cd7c74f0bb77a4b1a99 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 28 Aug 2013 18:24:59 -0700 Subject: vfs: make the dentry cache use the lockref infrastructure This just replaces the dentry count/lock combination with the lockref structure that contains both a count and a spinlock, and does the mechanical conversion to use the lockref infrastructure. There are no semantic changes here, it's purely syntactic. The reference lockref implementation uses the spinlock exactly the same way that the old dcache code did, and the bulk of this patch is just expanding the internal "d_count" use in the dcache code to use "d_lockref.count" instead. This is purely preparation for the real change to make the reference count updates be lockless during the 3.12 merge window. [ As with the previous commit, this is a rewritten version of a concept originally from Waiman, so credit goes to him, blame for any errors goes to me. Waiman's patch had some semantic differences for taking advantage of the lockless update in dget_parent(), while this patch is intentionally a pure search-and-replace change with no semantic changes. - Linus ] Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- fs/dcache.c | 57 ++++++++++++++++++++------------------------------ fs/namei.c | 6 +++--- include/linux/dcache.h | 19 ++++++++--------- 3 files changed, 35 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/fs/dcache.c b/fs/dcache.c index 83cfb834db03..b949af850cd6 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -229,7 +229,7 @@ static void __d_free(struct rcu_head *head) */ static void d_free(struct dentry *dentry) { - BUG_ON(dentry->d_count); + BUG_ON(dentry->d_lockref.count); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); @@ -467,7 +467,7 @@ relock: } if (ref) - dentry->d_count--; + dentry->d_lockref.count--; /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. @@ -513,15 +513,10 @@ void dput(struct dentry *dentry) return; repeat: - if (dentry->d_count == 1) + if (dentry->d_lockref.count == 1) might_sleep(); - spin_lock(&dentry->d_lock); - BUG_ON(!dentry->d_count); - if (dentry->d_count > 1) { - dentry->d_count--; - spin_unlock(&dentry->d_lock); + if (lockref_put_or_lock(&dentry->d_lockref)) return; - } if (dentry->d_flags & DCACHE_OP_DELETE) { if (dentry->d_op->d_delete(dentry)) @@ -535,7 +530,7 @@ repeat: dentry->d_flags |= DCACHE_REFERENCED; dentry_lru_add(dentry); - dentry->d_count--; + dentry->d_lockref.count--; spin_unlock(&dentry->d_lock); return; @@ -590,7 +585,7 @@ int d_invalidate(struct dentry * dentry) * We also need to leave mountpoints alone, * directory or not. */ - if (dentry->d_count > 1 && dentry->d_inode) { + if (dentry->d_lockref.count > 1 && dentry->d_inode) { if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) { spin_unlock(&dentry->d_lock); return -EBUSY; @@ -606,14 +601,12 @@ EXPORT_SYMBOL(d_invalidate); /* This must be called with d_lock held */ static inline void __dget_dlock(struct dentry *dentry) { - dentry->d_count++; + dentry->d_lockref.count++; } static inline void __dget(struct dentry *dentry) { - spin_lock(&dentry->d_lock); - __dget_dlock(dentry); - spin_unlock(&dentry->d_lock); + lockref_get(&dentry->d_lockref); } struct dentry *dget_parent(struct dentry *dentry) @@ -634,8 +627,8 @@ repeat: goto repeat; } rcu_read_unlock(); - BUG_ON(!ret->d_count); - ret->d_count++; + BUG_ON(!ret->d_lockref.count); + ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } @@ -718,7 +711,7 @@ restart: spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); - if (!dentry->d_count) { + if (!dentry->d_lockref.count) { __dget_dlock(dentry); __d_drop(dentry); spin_unlock(&dentry->d_lock); @@ -763,12 +756,8 @@ static void try_prune_one_dentry(struct dentry *dentry) /* Prune ancestors. */ dentry = parent; while (dentry) { - spin_lock(&dentry->d_lock); - if (dentry->d_count > 1) { - dentry->d_count--; - spin_unlock(&dentry->d_lock); + if (lockref_put_or_lock(&dentry->d_lockref)) return; - } dentry = dentry_kill(dentry, 1); } } @@ -793,7 +782,7 @@ static void shrink_dentry_list(struct list_head *list) * the LRU because of laziness during lookup. Do not free * it - just keep it off the LRU list. */ - if (dentry->d_count) { + if (dentry->d_lockref.count) { dentry_lru_del(dentry); spin_unlock(&dentry->d_lock); continue; @@ -913,7 +902,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) dentry_lru_del(dentry); __d_shrink(dentry); - if (dentry->d_count != 0) { + if (dentry->d_lockref.count != 0) { printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%s}" " still in use (%d)" @@ -922,7 +911,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry->d_name.name, - dentry->d_count, + dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); BUG(); @@ -933,7 +922,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) list_del(&dentry->d_u.d_child); } else { parent = dentry->d_parent; - parent->d_count--; + parent->d_lockref.count--; list_del(&dentry->d_u.d_child); } @@ -981,7 +970,7 @@ void shrink_dcache_for_umount(struct super_block *sb) dentry = sb->s_root; sb->s_root = NULL; - dentry->d_count--; + dentry->d_lockref.count--; shrink_dcache_for_umount_subtree(dentry); while (!hlist_bl_empty(&sb->s_anon)) { @@ -1147,7 +1136,7 @@ resume: * loop in shrink_dcache_parent() might not make any progress * and loop forever. */ - if (dentry->d_count) { + if (dentry->d_lockref.count) { dentry_lru_del(dentry); } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { dentry_lru_move_list(dentry, dispose); @@ -1269,7 +1258,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) smp_wmb(); dentry->d_name.name = dname; - dentry->d_count = 1; + dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_init(&dentry->d_seq); @@ -1970,7 +1959,7 @@ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) goto next; } - dentry->d_count++; + dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; @@ -2069,7 +2058,7 @@ again: spin_lock(&dentry->d_lock); inode = dentry->d_inode; isdir = S_ISDIR(inode->i_mode); - if (dentry->d_count == 1) { + if (dentry->d_lockref.count == 1) { if (!spin_trylock(&inode->i_lock)) { spin_unlock(&dentry->d_lock); cpu_relax(); @@ -2948,7 +2937,7 @@ resume: } if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; - dentry->d_count--; + dentry->d_lockref.count--; } spin_unlock(&dentry->d_lock); } @@ -2956,7 +2945,7 @@ resume: struct dentry *child = this_parent; if (!(this_parent->d_flags & DCACHE_GENOCIDE)) { this_parent->d_flags |= DCACHE_GENOCIDE; - this_parent->d_count--; + this_parent->d_lockref.count--; } this_parent = try_to_ascend(this_parent, locked, seq); if (!this_parent) diff --git a/fs/namei.c b/fs/namei.c index 8b61d103a8a7..7720fbd5277b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -536,8 +536,8 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) * a reference at this point. */ BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent); - BUG_ON(!parent->d_count); - parent->d_count++; + BUG_ON(!parent->d_lockref.count); + parent->d_lockref.count++; spin_unlock(&dentry->d_lock); } spin_unlock(&parent->d_lock); @@ -3327,7 +3327,7 @@ void dentry_unhash(struct dentry *dentry) { shrink_dcache_parent(dentry); spin_lock(&dentry->d_lock); - if (dentry->d_count == 1) + if (dentry->d_lockref.count == 1) __d_drop(dentry); spin_unlock(&dentry->d_lock); } diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 4a12532da8c4..efdc94434c30 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -9,6 +9,7 @@ #include #include #include +#include struct nameidata; struct path; @@ -100,6 +101,8 @@ extern unsigned int full_name_hash(const unsigned char *, unsigned int); # endif #endif +#define d_lock d_lockref.lock + struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ @@ -112,8 +115,7 @@ struct dentry { unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ /* Ref lookup also touches following */ - unsigned int d_count; /* protected by d_lock */ - spinlock_t d_lock; /* per dentry lock */ + struct lockref d_lockref; /* per-dentry lock and refcount */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ @@ -318,7 +320,7 @@ static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) assert_spin_locked(&dentry->d_lock); if (!read_seqcount_retry(&dentry->d_seq, seq)) { ret = 1; - dentry->d_count++; + dentry->d_lockref.count++; } return ret; @@ -326,7 +328,7 @@ static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) static inline unsigned d_count(const struct dentry *dentry) { - return dentry->d_count; + return dentry->d_lockref.count; } /* validate "insecure" dentry pointer */ @@ -357,17 +359,14 @@ extern char *dentry_path(struct dentry *, char *, int); static inline struct dentry *dget_dlock(struct dentry *dentry) { if (dentry) - dentry->d_count++; + dentry->d_lockref.count++; return dentry; } static inline struct dentry *dget(struct dentry *dentry) { - if (dentry) { - spin_lock(&dentry->d_lock); - dget_dlock(dentry); - spin_unlock(&dentry->d_lock); - } + if (dentry) + lockref_get(&dentry->d_lockref); return dentry; } -- cgit v1.2.3-71-gd317 From 9efdd27678ef5e22c27c230a08a211b702768f3a Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Sun, 25 Aug 2013 17:54:13 +0200 Subject: regulator: Add devm_regulator_get_exclusive() Add a resource managed regulator_get_exclusive() Signed-off-by: Matthias Kaehlcke Signed-off-by: Mark Brown --- drivers/regulator/core.c | 30 ++++++++++++++++++++++++++++++ include/linux/regulator/consumer.h | 2 ++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index a27a5b6267dd..4b9039b43b6c 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1493,6 +1493,36 @@ static void _regulator_put(struct regulator *regulator) module_put(rdev->owner); } +/** + * devm_regulator_get_exclusive - Resource managed regulator_get_exclusive() + * @dev: device for regulator "consumer" + * @id: Supply name or regulator ID. + * + * Managed regulator_get_exclusive(). Regulators returned from this function + * are automatically regulator_put() on driver detach. See regulator_get() for + * more information. + */ +struct regulator *devm_regulator_get_exclusive(struct device *dev, + const char *id) +{ + struct regulator **ptr, *regulator; + + ptr = devres_alloc(devm_regulator_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + regulator = _regulator_get(dev, id, 1); + if (!IS_ERR(regulator)) { + *ptr = regulator; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return regulator; +} +EXPORT_SYMBOL_GPL(devm_regulator_get_exclusive); + /** * regulator_put - "free" the regulator source * @regulator: regulator source diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index e2bac6db4abc..91aca11198d8 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -137,6 +137,8 @@ struct regulator *__must_check devm_regulator_get(struct device *dev, const char *id); struct regulator *__must_check regulator_get_exclusive(struct device *dev, const char *id); +struct regulator *__must_check devm_regulator_get_exclusive(struct device *dev, + const char *id); struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id); struct regulator *__must_check devm_regulator_get_optional(struct device *dev, -- cgit v1.2.3-71-gd317 From 5e33bc4165f3edd558d9633002465a95230effc1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 28 Aug 2013 21:41:01 +0200 Subject: driver core / ACPI: Avoid device hot remove locking issues device_hotplug_lock is held around the acpi_bus_trim() call in acpi_scan_hot_remove() which generally removes devices (it removes ACPI device objects at least, but it may also remove "physical" device objects through .detach() callbacks of ACPI scan handlers). Thus, potentially, device sysfs attributes are removed under that lock and to remove those attributes it is necessary to hold the s_active references of their directory entries for writing. On the other hand, the execution of a .show() or .store() callback from a sysfs attribute is carried out with that attribute's s_active reference held for reading. Consequently, if any device sysfs attribute that may be removed from within acpi_scan_hot_remove() through acpi_bus_trim() has a .store() or .show() callback which acquires device_hotplug_lock, the execution of that callback may deadlock with the removal of the attribute. [Unfortunately, the "online" device attribute of CPUs and memory blocks is one of them.] To avoid such deadlocks, make all of the sysfs attribute callbacks that need to lock device hotplug, for example store_online(), use a special function, lock_device_hotplug_sysfs(), to lock device hotplug and return the result of that function immediately if it is not zero. This will cause the s_active reference of the directory entry in question to be released and the syscall to be restarted if device_hotplug_lock cannot be acquired. [show_online() actually doesn't need to lock device hotplug, but it is useful to serialize it with respect to device_offline() and device_online() for the same device (in case user space attempts to run them concurrently) which can be done with the help of device_lock().] Reported-by: Yasuaki Ishimatsu Reported-and-tested-by: Gu Zheng Suggested-by: Tejun Heo Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Toshi Kani --- drivers/base/core.c | 43 ++++++++++++++++++++++++++++--------------- drivers/base/memory.c | 4 +++- include/linux/device.h | 1 + 3 files changed, 32 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 8856d74545d9..ac419a15fcd4 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -49,6 +49,28 @@ static struct kobject *dev_kobj; struct kobject *sysfs_dev_char_kobj; struct kobject *sysfs_dev_block_kobj; +static DEFINE_MUTEX(device_hotplug_lock); + +void lock_device_hotplug(void) +{ + mutex_lock(&device_hotplug_lock); +} + +void unlock_device_hotplug(void) +{ + mutex_unlock(&device_hotplug_lock); +} + +int lock_device_hotplug_sysfs(void) +{ + if (mutex_trylock(&device_hotplug_lock)) + return 0; + + /* Avoid busy looping (5 ms of sleep should do). */ + msleep(5); + return restart_syscall(); +} + #ifdef CONFIG_BLOCK static inline int device_is_not_partition(struct device *dev) { @@ -408,9 +430,9 @@ static ssize_t show_online(struct device *dev, struct device_attribute *attr, { bool val; - lock_device_hotplug(); + device_lock(dev); val = !dev->offline; - unlock_device_hotplug(); + device_unlock(dev); return sprintf(buf, "%u\n", val); } @@ -424,7 +446,10 @@ static ssize_t store_online(struct device *dev, struct device_attribute *attr, if (ret < 0) return ret; - lock_device_hotplug(); + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; + ret = val ? device_online(dev) : device_offline(dev); unlock_device_hotplug(); return ret < 0 ? ret : count; @@ -1479,18 +1504,6 @@ EXPORT_SYMBOL_GPL(put_device); EXPORT_SYMBOL_GPL(device_create_file); EXPORT_SYMBOL_GPL(device_remove_file); -static DEFINE_MUTEX(device_hotplug_lock); - -void lock_device_hotplug(void) -{ - mutex_lock(&device_hotplug_lock); -} - -void unlock_device_hotplug(void) -{ - mutex_unlock(&device_hotplug_lock); -} - static int device_check_offline(struct device *dev, void *not_used) { int ret; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 2b7813ec6d02..6f4c99ff1ce7 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -351,7 +351,9 @@ store_mem_state(struct device *dev, mem = container_of(dev, struct memory_block, dev); - lock_device_hotplug(); + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) { offline = false; diff --git a/include/linux/device.h b/include/linux/device.h index 22b546a58591..545a04285120 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -895,6 +895,7 @@ static inline bool device_supports_offline(struct device *dev) extern void lock_device_hotplug(void); extern void unlock_device_hotplug(void); +extern int lock_device_hotplug_sysfs(void); extern int device_offline(struct device *dev); extern int device_online(struct device *dev); /* -- cgit v1.2.3-71-gd317 From 9120c0bea999cc26c3493486828d34138a7ac901 Mon Sep 17 00:00:00 2001 From: Josh Wu Date: Tue, 27 Aug 2013 12:28:00 +0100 Subject: iio: at91: Use different prescal, startup mask in MR for different IP For at91 boards, there are different IPs for adc. Different IPs has different STARTUP & PRESCAL mask in ADC_MR. Signed-off-by: Josh Wu Acked-by: Maxime Ripard Signed-off-by: Jonathan Cameron --- arch/arm/mach-at91/include/mach/at91_adc.h | 7 +++++-- drivers/iio/adc/at91_adc.c | 11 +++++++++-- include/linux/platform_data/at91_adc.h | 4 ++++ 3 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-at91/include/mach/at91_adc.h b/arch/arm/mach-at91/include/mach/at91_adc.h index bea1a2021d1e..048a57f76bd3 100644 --- a/arch/arm/mach-at91/include/mach/at91_adc.h +++ b/arch/arm/mach-at91/include/mach/at91_adc.h @@ -28,9 +28,12 @@ #define AT91_ADC_TRGSEL_EXTERNAL (6 << 1) #define AT91_ADC_LOWRES (1 << 4) /* Low Resolution */ #define AT91_ADC_SLEEP (1 << 5) /* Sleep Mode */ -#define AT91_ADC_PRESCAL (0x3f << 8) /* Prescalar Rate Selection */ +#define AT91_ADC_PRESCAL_9260 (0x3f << 8) /* Prescalar Rate Selection */ +#define AT91_ADC_PRESCAL_9G45 (0xff << 8) #define AT91_ADC_PRESCAL_(x) ((x) << 8) -#define AT91_ADC_STARTUP (0x1f << 16) /* Startup Up Time */ +#define AT91_ADC_STARTUP_9260 (0x1f << 16) /* Startup Up Time */ +#define AT91_ADC_STARTUP_9G45 (0x7f << 16) +#define AT91_ADC_STARTUP_9X5 (0xf << 16) #define AT91_ADC_STARTUP_(x) ((x) << 16) #define AT91_ADC_SHTIM (0xf << 24) /* Sample & Hold Time */ #define AT91_ADC_SHTIM_(x) ((x) << 24) diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index ed5eebc93bb7..84be63bdf038 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -672,8 +672,8 @@ static int at91_adc_probe(struct platform_device *pdev) shtim = round_up((st->sample_hold_time * adc_clk / 1000000) - 1, 1); - reg = AT91_ADC_PRESCAL_(prsc) & AT91_ADC_PRESCAL; - reg |= AT91_ADC_STARTUP_(ticks) & AT91_ADC_STARTUP; + reg = AT91_ADC_PRESCAL_(prsc) & st->registers->mr_prescal_mask; + reg |= AT91_ADC_STARTUP_(ticks) & st->registers->mr_startup_mask; if (st->low_res) reg |= AT91_ADC_LOWRES; if (st->sleep_mode) @@ -746,6 +746,8 @@ static struct at91_adc_caps at91sam9260_caps = { .drdy_mask = AT91_ADC_DRDY, .status_register = AT91_ADC_SR, .trigger_register = AT91_ADC_TRGR_9260, + .mr_prescal_mask = AT91_ADC_PRESCAL_9260, + .mr_startup_mask = AT91_ADC_STARTUP_9260, }, }; @@ -755,6 +757,8 @@ static struct at91_adc_caps at91sam9g45_caps = { .drdy_mask = AT91_ADC_DRDY, .status_register = AT91_ADC_SR, .trigger_register = AT91_ADC_TRGR_9G45, + .mr_prescal_mask = AT91_ADC_PRESCAL_9G45, + .mr_startup_mask = AT91_ADC_STARTUP_9G45, }, }; @@ -764,6 +768,9 @@ static struct at91_adc_caps at91sam9x5_caps = { .drdy_mask = AT91_ADC_SR_DRDY_9X5, .status_register = AT91_ADC_SR_9X5, .trigger_register = AT91_ADC_TRGR_9X5, + /* prescal mask is same as 9G45 */ + .mr_prescal_mask = AT91_ADC_PRESCAL_9G45, + .mr_startup_mask = AT91_ADC_STARTUP_9X5, }, }; diff --git a/include/linux/platform_data/at91_adc.h b/include/linux/platform_data/at91_adc.h index e15745b4f3a5..b3ca1e94e0c8 100644 --- a/include/linux/platform_data/at91_adc.h +++ b/include/linux/platform_data/at91_adc.h @@ -14,12 +14,16 @@ (Interruptions registers mostly) * @status_register: Offset of the Interrupt Status Register * @trigger_register: Offset of the Trigger setup register + * @mr_prescal_mask: Mask of the PRESCAL field in the adc MR register + * @mr_startup_mask: Mask of the STARTUP field in the adc MR register */ struct at91_adc_reg_desc { u8 channel_base; u32 drdy_mask; u8 status_register; u8 trigger_register; + u32 mr_prescal_mask; + u32 mr_startup_mask; }; /** -- cgit v1.2.3-71-gd317 From 6290d60656e9f4f5a0071bafa798370ab35978a0 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Fri, 30 Aug 2013 18:06:06 +0800 Subject: regulator: tps65217: Convert to use linear ranges Below is the equation in original code: tps65217_uv1_ranges: 0 ... 24: uV = vsel * 25000 + 900000; 25 ... 52: uV = (vsel - 24) * 50000 + 1500000; = (vsel - 25) * 50000 + 1550000; 53 ... 55: uV = (vsel - 52) * 100000 + 2900000; = (vsel - 53) * 100000 + 3000000; 56 ... 62: uV = 3300000; tps65217_uv2_ranges: 0 ... 8: uV = vsel * 50000 + 1500000; 9 ... 13: uV = (vsel - 8) * 100000 + 1900000; = (vsel - 9) * 100000 + 2000000; 14 ... 31: uV = (vsel - 13) * 50000 + 2400000; = (vsel - 14) * 50000 + 2450000; The voltage tables are composed of linear ranges. This patch converts this driver to use multiple linear ranges APIs. In original code, voltage range for DCDC1 is 900000 ~ 1800000 and voltage range for DCDC3 is 900000 ~ 1500000. This patch separates the range 25~52 in tps65217_uv1_ranges table to two linear ranges: 25~30 and 31~52. This change makes it possible to reuse the same linear_ranges table for DCDCx. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- drivers/regulator/tps65217-regulator.c | 182 +++++++-------------------------- include/linux/mfd/tps65217.h | 19 ---- 2 files changed, 37 insertions(+), 164 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c index 2df4616621f5..90861d68a0b0 100644 --- a/drivers/regulator/tps65217-regulator.c +++ b/drivers/regulator/tps65217-regulator.c @@ -27,7 +27,7 @@ #include #include -#define TPS65217_REGULATOR(_name, _id, _ops, _n, _vr, _vm, _em, _t) \ +#define TPS65217_REGULATOR(_name, _id, _ops, _n, _vr, _vm, _em, _t, _lr, _nlr) \ { \ .name = _name, \ .id = _id, \ @@ -40,17 +40,10 @@ .enable_reg = TPS65217_REG_ENABLE, \ .enable_mask = _em, \ .volt_table = _t, \ + .linear_ranges = _lr, \ + .n_linear_ranges = _nlr, \ } \ -#define TPS65217_INFO(_nm, _min, _max, _f1, _f2) \ - { \ - .name = _nm, \ - .min_uV = _min, \ - .max_uV = _max, \ - .vsel_to_uv = _f1, \ - .uv_to_vsel = _f2, \ - } - static const unsigned int LDO1_VSEL_table[] = { 1000000, 1100000, 1200000, 1250000, 1300000, 1350000, 1400000, 1500000, @@ -58,88 +51,26 @@ static const unsigned int LDO1_VSEL_table[] = { 2800000, 3000000, 3100000, 3300000, }; -static int tps65217_vsel_to_uv1(unsigned int vsel) -{ - int uV = 0; - - if (vsel > 63) - return -EINVAL; - - if (vsel <= 24) - uV = vsel * 25000 + 900000; - else if (vsel <= 52) - uV = (vsel - 24) * 50000 + 1500000; - else if (vsel < 56) - uV = (vsel - 52) * 100000 + 2900000; - else - uV = 3300000; - - return uV; -} - -static int tps65217_uv_to_vsel1(int uV, unsigned int *vsel) -{ - if (uV < 0 || uV > 3300000) - return -EINVAL; - - if (uV <= 1500000) - *vsel = DIV_ROUND_UP(uV - 900000, 25000); - else if (uV <= 2900000) - *vsel = 24 + DIV_ROUND_UP(uV - 1500000, 50000); - else if (uV < 3300000) - *vsel = 52 + DIV_ROUND_UP(uV - 2900000, 100000); - else - *vsel = 56; - - return 0; -} - -static int tps65217_vsel_to_uv2(unsigned int vsel) -{ - int uV = 0; - - if (vsel > 31) - return -EINVAL; - - if (vsel <= 8) - uV = vsel * 50000 + 1500000; - else if (vsel <= 13) - uV = (vsel - 8) * 100000 + 1900000; - else - uV = (vsel - 13) * 50000 + 2400000; - - return uV; -} - -static int tps65217_uv_to_vsel2(int uV, unsigned int *vsel) -{ - if (uV < 0 || uV > 3300000) - return -EINVAL; - - if (uV <= 1900000) - *vsel = DIV_ROUND_UP(uV - 1500000, 50000); - else if (uV <= 2400000) - *vsel = 8 + DIV_ROUND_UP(uV - 1900000, 100000); - else - *vsel = 13 + DIV_ROUND_UP(uV - 2400000, 50000); - - return 0; -} +static const struct regulator_linear_range tps65217_uv1_ranges[] = { + { .min_uV = 900000, .max_uV = 1500000, .min_sel = 0, .max_sel = 24, + .uV_step = 25000 }, + { .min_uV = 1550000, .max_uV = 1800000, .min_sel = 25, .max_sel = 30, + .uV_step = 50000 }, + { .min_uV = 1850000, .max_uV = 2900000, .min_sel = 31, .max_sel = 52, + .uV_step = 50000 }, + { .min_uV = 3000000, .max_uV = 3200000, .min_sel = 53, .max_sel = 55, + .uV_step = 100000 }, + { .min_uV = 3300000, .max_uV = 3300000, .min_sel = 56, .max_sel = 62, + .uV_step = 0 }, +}; -static struct tps_info tps65217_pmic_regs[] = { - TPS65217_INFO("DCDC1", 900000, 1800000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1), - TPS65217_INFO("DCDC2", 900000, 3300000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1), - TPS65217_INFO("DCDC3", 900000, 1500000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1), - TPS65217_INFO("LDO1", 1000000, 3300000, NULL, NULL), - TPS65217_INFO("LDO2", 900000, 3300000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1), - TPS65217_INFO("LDO3", 1800000, 3300000, tps65217_vsel_to_uv2, - tps65217_uv_to_vsel2), - TPS65217_INFO("LDO4", 1800000, 3300000, tps65217_vsel_to_uv2, - tps65217_uv_to_vsel2), +static const struct regulator_linear_range tps65217_uv2_ranges[] = { + { .min_uV = 1500000, .max_uV = 1900000, .min_sel = 0, .max_sel = 8, + .uV_step = 50000 }, + { .min_uV = 2000000, .max_uV = 2400000, .min_sel = 9, .max_sel = 13, + .uV_step = 100000 }, + { .min_uV = 2450000, .max_uV = 3300000, .min_sel = 14, .max_sel = 31, + .uV_step = 50000 }, }; static int tps65217_pmic_enable(struct regulator_dev *dev) @@ -192,49 +123,6 @@ static int tps65217_pmic_set_voltage_sel(struct regulator_dev *dev, return ret; } -static int tps65217_pmic_map_voltage(struct regulator_dev *dev, - int min_uV, int max_uV) -{ - - struct tps65217 *tps = rdev_get_drvdata(dev); - unsigned int sel, rid = rdev_get_id(dev); - int ret; - - /* LDO1 uses regulator_map_voltage_iterate() */ - if (rid == TPS65217_LDO_1) - return -EINVAL; - - if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4) - return -EINVAL; - - if (min_uV < tps->info[rid]->min_uV) - min_uV = tps->info[rid]->min_uV; - - if (max_uV < tps->info[rid]->min_uV || min_uV > tps->info[rid]->max_uV) - return -EINVAL; - - ret = tps->info[rid]->uv_to_vsel(min_uV, &sel); - if (ret) - return ret; - - return sel; -} - -static int tps65217_pmic_list_voltage(struct regulator_dev *dev, - unsigned selector) -{ - struct tps65217 *tps = rdev_get_drvdata(dev); - unsigned int rid = rdev_get_id(dev); - - if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4) - return -EINVAL; - - if (selector >= dev->desc->n_voltages) - return -EINVAL; - - return tps->info[rid]->vsel_to_uv(selector); -} - /* Operations permitted on DCDCx, LDO2, LDO3 and LDO4 */ static struct regulator_ops tps65217_pmic_ops = { .is_enabled = regulator_is_enabled_regmap, @@ -242,8 +130,8 @@ static struct regulator_ops tps65217_pmic_ops = { .disable = tps65217_pmic_disable, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = tps65217_pmic_set_voltage_sel, - .list_voltage = tps65217_pmic_list_voltage, - .map_voltage = tps65217_pmic_map_voltage, + .list_voltage = regulator_list_voltage_linear_range, + .map_voltage = regulator_map_voltage_linear_range, }; /* Operations permitted on LDO1 */ @@ -259,27 +147,33 @@ static struct regulator_ops tps65217_pmic_ldo1_ops = { static const struct regulator_desc regulators[] = { TPS65217_REGULATOR("DCDC1", TPS65217_DCDC_1, tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC1, TPS65217_DEFDCDCX_DCDC_MASK, - TPS65217_ENABLE_DC1_EN, NULL), + TPS65217_ENABLE_DC1_EN, NULL, tps65217_uv1_ranges, + 2), /* DCDC1 voltage range: 900000 ~ 1800000 */ TPS65217_REGULATOR("DCDC2", TPS65217_DCDC_2, tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC2, TPS65217_DEFDCDCX_DCDC_MASK, - TPS65217_ENABLE_DC2_EN, NULL), + TPS65217_ENABLE_DC2_EN, NULL, tps65217_uv1_ranges, + ARRAY_SIZE(tps65217_uv1_ranges)), TPS65217_REGULATOR("DCDC3", TPS65217_DCDC_3, tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC3, TPS65217_DEFDCDCX_DCDC_MASK, - TPS65217_ENABLE_DC3_EN, NULL), + TPS65217_ENABLE_DC3_EN, NULL, tps65217_uv1_ranges, + 1), /* DCDC3 voltage range: 900000 ~ 1500000 */ TPS65217_REGULATOR("LDO1", TPS65217_LDO_1, tps65217_pmic_ldo1_ops, 16, TPS65217_REG_DEFLDO1, TPS65217_DEFLDO1_LDO1_MASK, - TPS65217_ENABLE_LDO1_EN, LDO1_VSEL_table), + TPS65217_ENABLE_LDO1_EN, LDO1_VSEL_table, NULL, 0), TPS65217_REGULATOR("LDO2", TPS65217_LDO_2, tps65217_pmic_ops, 64, TPS65217_REG_DEFLDO2, TPS65217_DEFLDO2_LDO2_MASK, - TPS65217_ENABLE_LDO2_EN, NULL), + TPS65217_ENABLE_LDO2_EN, NULL, tps65217_uv1_ranges, + ARRAY_SIZE(tps65217_uv1_ranges)), TPS65217_REGULATOR("LDO3", TPS65217_LDO_3, tps65217_pmic_ops, 32, TPS65217_REG_DEFLS1, TPS65217_DEFLDO3_LDO3_MASK, TPS65217_ENABLE_LS1_EN | TPS65217_DEFLDO3_LDO3_EN, - NULL), + NULL, tps65217_uv2_ranges, + ARRAY_SIZE(tps65217_uv2_ranges)), TPS65217_REGULATOR("LDO4", TPS65217_LDO_4, tps65217_pmic_ops, 32, TPS65217_REG_DEFLS2, TPS65217_DEFLDO4_LDO4_MASK, TPS65217_ENABLE_LS2_EN | TPS65217_DEFLDO4_LDO4_EN, - NULL), + NULL, tps65217_uv2_ranges, + ARRAY_SIZE(tps65217_uv2_ranges)), }; #ifdef CONFIG_OF @@ -368,8 +262,6 @@ static int tps65217_regulator_probe(struct platform_device *pdev) continue; /* Register the regulators */ - tps->info[i] = &tps65217_pmic_regs[i]; - config.dev = tps->dev; config.init_data = reg_data; config.driver_data = tps; diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index 29eab2bd3dfa..a5a7f0130e96 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -243,24 +243,6 @@ struct tps65217_board { struct tps65217_bl_pdata *bl_pdata; }; -/** - * struct tps_info - packages regulator constraints - * @name: Voltage regulator name - * @min_uV: minimum micro volts - * @max_uV: minimum micro volts - * @vsel_to_uv: Function pointer to get voltage from selector - * @uv_to_vsel: Function pointer to get selector from voltage - * - * This data is used to check the regualtor voltage limits while setting. - */ -struct tps_info { - const char *name; - int min_uV; - int max_uV; - int (*vsel_to_uv)(unsigned int vsel); - int (*uv_to_vsel)(int uV, unsigned int *vsel); -}; - /** * struct tps65217 - tps65217 sub-driver chip access routines * @@ -273,7 +255,6 @@ struct tps65217 { unsigned int id; struct regulator_desc desc[TPS65217_NUM_REGULATOR]; struct regulator_dev *rdev[TPS65217_NUM_REGULATOR]; - struct tps_info *info[TPS65217_NUM_REGULATOR]; struct regmap *regmap; }; -- cgit v1.2.3-71-gd317 From 9d8924297cd9c256c23c02abae40202563452453 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 30 Aug 2013 10:46:00 -0400 Subject: USB: fix build error when CONFIG_PM_SLEEP isn't enabled This patch fixes a build error that occurs when CONFIG_PM is enabled and CONFIG_PM_SLEEP isn't: >> drivers/usb/host/ohci-pci.c:294:10: error: 'usb_hcd_pci_pm_ops' undeclared here (not in a function) .pm = &usb_hcd_pci_pm_ops Since the usb_hcd_pci_pm_ops structure is defined and used when CONFIG_PM is enabled, its declaration should not be protected by CONFIG_PM_SLEEP. Signed-off-by: Alan Stern Reported-by: kbuild test robot CC: Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index a9c7d44bd2ed..75efc45eaa2f 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -428,7 +428,7 @@ extern int usb_hcd_pci_probe(struct pci_dev *dev, extern void usb_hcd_pci_remove(struct pci_dev *dev); extern void usb_hcd_pci_shutdown(struct pci_dev *dev); -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif #endif /* CONFIG_PCI */ -- cgit v1.2.3-71-gd317 From 0edd1b1784cbdad55aca2c1293be018f53c0ab1d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Jun 2013 16:37:22 -0700 Subject: nohz_full: Add full-system-idle state machine This commit adds the state machine that takes the per-CPU idle data as input and produces a full-system-idle indication as output. This state machine is driven out of RCU's quiescent-state-forcing mechanism, which invokes rcu_sysidle_check_cpu() to collect per-CPU idle state and then rcu_sysidle_report() to drive the state machine. The full-system-idle state is sampled using rcu_sys_is_idle(), which also drives the state machine if RCU is idle (and does so by forcing RCU to become non-idle). This function returns true if all but the timekeeping CPU (tick_do_timer_cpu) are idle and have been idle long enough to avoid memory contention on the full_sysidle_state state variable. The rcu_sysidle_force_exit() may be called externally to reset the state machine back into non-idle state. For large systems the state machine is driven out of RCU's force-quiescent-state logic, which provides good scalability at the price of millisecond-scale latencies on the transition to full-system-idle state. This is not so good for battery-powered systems, which are usually small enough that they don't need to care about scalability, but which do care deeply about energy efficiency. Small systems therefore drive the state machine directly out of the idle-entry code. The number of CPUs in a "small" system is defined by a new NO_HZ_FULL_SYSIDLE_SMALL Kconfig parameter, which defaults to 8. Note that this is a build-time definition. Signed-off-by: Paul E. McKenney Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Lai Jiangshan [ paulmck: Use true and false for boolean constants per Lai Jiangshan. ] Reviewed-by: Josh Triplett [ paulmck: Simplify logic and provide better comments for memory barriers, based on review comments and questions by Lai Jiangshan. ] --- include/linux/rcupdate.h | 18 +++ kernel/rcutree.c | 16 ++- kernel/rcutree.h | 5 + kernel/rcutree_plugin.h | 296 ++++++++++++++++++++++++++++++++++++++++++++++- kernel/time/Kconfig | 27 +++++ 5 files changed, 355 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 30bea9c25735..f1f1bc39346b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1011,4 +1011,22 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +/* Only for use by adaptive-ticks code. */ +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE +extern bool rcu_sys_is_idle(void); +extern void rcu_sysidle_force_exit(void); +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + +static inline bool rcu_sys_is_idle(void) +{ + return false; +} + +static inline void rcu_sysidle_force_exit(void) +{ +} + +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ + + #endif /* __LINUX_RCUPDATE_H */ diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 7b5be56d95ae..eca70f4469c1 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -734,6 +734,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, bool *isidle, unsigned long *maxj) { rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks); + rcu_sysidle_check_cpu(rdp, isidle, maxj); return (rdp->dynticks_snap & 0x1) == 0; } @@ -1373,11 +1374,17 @@ int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) rsp->n_force_qs++; if (fqs_state == RCU_SAVE_DYNTICK) { /* Collect dyntick-idle snapshots. */ + if (is_sysidle_rcu_state(rsp)) { + isidle = 1; + maxj = jiffies - ULONG_MAX / 4; + } force_qs_rnp(rsp, dyntick_save_progress_counter, &isidle, &maxj); + rcu_sysidle_report_gp(rsp, isidle, maxj); fqs_state = RCU_FORCE_QS; } else { /* Handle dyntick-idle and offline CPUs. */ + isidle = 0; force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); } /* Clear flag to prevent immediate re-entry. */ @@ -2103,9 +2110,12 @@ static void force_qs_rnp(struct rcu_state *rsp, cpu = rnp->grplo; bit = 1; for (; cpu <= rnp->grphi; cpu++, bit <<= 1) { - if ((rnp->qsmask & bit) != 0 && - f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) - mask |= bit; + if ((rnp->qsmask & bit) != 0) { + if ((rnp->qsmaskinit & bit) != 0) + *isidle = 0; + if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) + mask |= bit; + } } if (mask != 0) { diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 9dd8b177f1ac..6fd3659cf01a 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -555,6 +555,11 @@ static void rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq); static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq); +static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, + unsigned long *maxj); +static bool is_sysidle_rcu_state(struct rcu_state *rsp); +static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, + unsigned long maxj); static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index a7419ceb19ad..45ebba747af4 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -28,7 +28,7 @@ #include #include #include -#include +#include "time/tick-internal.h" #define RCU_KTHREAD_PRIO 1 @@ -2382,12 +2382,12 @@ static void rcu_kick_nohz_cpu(int cpu) * most active flavor of RCU. */ #ifdef CONFIG_PREEMPT_RCU -static struct rcu_state __maybe_unused *rcu_sysidle_state = &rcu_preempt_state; +static struct rcu_state *rcu_sysidle_state = &rcu_preempt_state; #else /* #ifdef CONFIG_PREEMPT_RCU */ -static struct rcu_state __maybe_unused *rcu_sysidle_state = &rcu_sched_state; +static struct rcu_state *rcu_sysidle_state = &rcu_sched_state; #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ -static int __maybe_unused full_sysidle_state; /* Current system-idle state. */ +static int full_sysidle_state; /* Current system-idle state. */ #define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ #define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ #define RCU_SYSIDLE_LONG 2 /* All CPUs idle for long enough. */ @@ -2430,6 +2430,38 @@ static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq) WARN_ON_ONCE(atomic_read(&rdtp->dynticks_idle) & 0x1); } +/* + * Unconditionally force exit from full system-idle state. This is + * invoked when a normal CPU exits idle, but must be called separately + * for the timekeeping CPU (tick_do_timer_cpu). The reason for this + * is that the timekeeping CPU is permitted to take scheduling-clock + * interrupts while the system is in system-idle state, and of course + * rcu_sysidle_exit() has no way of distinguishing a scheduling-clock + * interrupt from any other type of interrupt. + */ +void rcu_sysidle_force_exit(void) +{ + int oldstate = ACCESS_ONCE(full_sysidle_state); + int newoldstate; + + /* + * Each pass through the following loop attempts to exit full + * system-idle state. If contention proves to be a problem, + * a trylock-based contention tree could be used here. + */ + while (oldstate > RCU_SYSIDLE_SHORT) { + newoldstate = cmpxchg(&full_sysidle_state, + oldstate, RCU_SYSIDLE_NOT); + if (oldstate == newoldstate && + oldstate == RCU_SYSIDLE_FULL_NOTED) { + rcu_kick_nohz_cpu(tick_do_timer_cpu); + return; /* We cleared it, done! */ + } + oldstate = newoldstate; + } + smp_mb(); /* Order initial oldstate fetch vs. later non-idle work. */ +} + /* * Invoked to note entry to irq or task transition from idle. Note that * usermode execution does -not- count as idle here! The caller must @@ -2463,6 +2495,247 @@ static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq) atomic_inc(&rdtp->dynticks_idle); smp_mb__after_atomic_inc(); WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks_idle) & 0x1)); + + /* + * If we are the timekeeping CPU, we are permitted to be non-idle + * during a system-idle state. This must be the case, because + * the timekeeping CPU has to take scheduling-clock interrupts + * during the time that the system is transitioning to full + * system-idle state. This means that the timekeeping CPU must + * invoke rcu_sysidle_force_exit() directly if it does anything + * more than take a scheduling-clock interrupt. + */ + if (smp_processor_id() == tick_do_timer_cpu) + return; + + /* Update system-idle state: We are clearly no longer fully idle! */ + rcu_sysidle_force_exit(); +} + +/* + * Check to see if the current CPU is idle. Note that usermode execution + * does not count as idle. The caller must have disabled interrupts. + */ +static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, + unsigned long *maxj) +{ + int cur; + unsigned long j; + struct rcu_dynticks *rdtp = rdp->dynticks; + + /* + * If some other CPU has already reported non-idle, if this is + * not the flavor of RCU that tracks sysidle state, or if this + * is an offline or the timekeeping CPU, nothing to do. + */ + if (!*isidle || rdp->rsp != rcu_sysidle_state || + cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) + return; + /* WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); */ + + /* Pick up current idle and NMI-nesting counter and check. */ + cur = atomic_read(&rdtp->dynticks_idle); + if (cur & 0x1) { + *isidle = false; /* We are not idle! */ + return; + } + smp_mb(); /* Read counters before timestamps. */ + + /* Pick up timestamps. */ + j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies); + /* If this CPU entered idle more recently, update maxj timestamp. */ + if (ULONG_CMP_LT(*maxj, j)) + *maxj = j; +} + +/* + * Is this the flavor of RCU that is handling full-system idle? + */ +static bool is_sysidle_rcu_state(struct rcu_state *rsp) +{ + return rsp == rcu_sysidle_state; +} + +/* + * Return a delay in jiffies based on the number of CPUs, rcu_node + * leaf fanout, and jiffies tick rate. The idea is to allow larger + * systems more time to transition to full-idle state in order to + * avoid the cache thrashing that otherwise occur on the state variable. + * Really small systems (less than a couple of tens of CPUs) should + * instead use a single global atomically incremented counter, and later + * versions of this will automatically reconfigure themselves accordingly. + */ +static unsigned long rcu_sysidle_delay(void) +{ + if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) + return 0; + return DIV_ROUND_UP(nr_cpu_ids * HZ, rcu_fanout_leaf * 1000); +} + +/* + * Advance the full-system-idle state. This is invoked when all of + * the non-timekeeping CPUs are idle. + */ +static void rcu_sysidle(unsigned long j) +{ + /* Check the current state. */ + switch (ACCESS_ONCE(full_sysidle_state)) { + case RCU_SYSIDLE_NOT: + + /* First time all are idle, so note a short idle period. */ + ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_SHORT; + break; + + case RCU_SYSIDLE_SHORT: + + /* + * Idle for a bit, time to advance to next state? + * cmpxchg failure means race with non-idle, let them win. + */ + if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) + (void)cmpxchg(&full_sysidle_state, + RCU_SYSIDLE_SHORT, RCU_SYSIDLE_LONG); + break; + + case RCU_SYSIDLE_LONG: + + /* + * Do an additional check pass before advancing to full. + * cmpxchg failure means race with non-idle, let them win. + */ + if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay())) + (void)cmpxchg(&full_sysidle_state, + RCU_SYSIDLE_LONG, RCU_SYSIDLE_FULL); + break; + + default: + break; + } +} + +/* + * Found a non-idle non-timekeeping CPU, so kick the system-idle state + * back to the beginning. + */ +static void rcu_sysidle_cancel(void) +{ + smp_mb(); + ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT; +} + +/* + * Update the sysidle state based on the results of a force-quiescent-state + * scan of the CPUs' dyntick-idle state. + */ +static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, + unsigned long maxj, bool gpkt) +{ + if (rsp != rcu_sysidle_state) + return; /* Wrong flavor, ignore. */ + if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) + return; /* Running state machine from timekeeping CPU. */ + if (isidle) + rcu_sysidle(maxj); /* More idle! */ + else + rcu_sysidle_cancel(); /* Idle is over. */ +} + +/* + * Wrapper for rcu_sysidle_report() when called from the grace-period + * kthread's context. + */ +static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, + unsigned long maxj) +{ + rcu_sysidle_report(rsp, isidle, maxj, true); +} + +/* Callback and function for forcing an RCU grace period. */ +struct rcu_sysidle_head { + struct rcu_head rh; + int inuse; +}; + +static void rcu_sysidle_cb(struct rcu_head *rhp) +{ + struct rcu_sysidle_head *rshp; + + /* + * The following memory barrier is needed to replace the + * memory barriers that would normally be in the memory + * allocator. + */ + smp_mb(); /* grace period precedes setting inuse. */ + + rshp = container_of(rhp, struct rcu_sysidle_head, rh); + ACCESS_ONCE(rshp->inuse) = 0; +} + +/* + * Check to see if the system is fully idle, other than the timekeeping CPU. + * The caller must have disabled interrupts. + */ +bool rcu_sys_is_idle(void) +{ + static struct rcu_sysidle_head rsh; + int rss = ACCESS_ONCE(full_sysidle_state); + + if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu)) + return false; + + /* Handle small-system case by doing a full scan of CPUs. */ + if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) { + int oldrss = rss - 1; + + /* + * One pass to advance to each state up to _FULL. + * Give up if any pass fails to advance the state. + */ + while (rss < RCU_SYSIDLE_FULL && oldrss < rss) { + int cpu; + bool isidle = true; + unsigned long maxj = jiffies - ULONG_MAX / 4; + struct rcu_data *rdp; + + /* Scan all the CPUs looking for nonidle CPUs. */ + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rcu_sysidle_state->rda, cpu); + rcu_sysidle_check_cpu(rdp, &isidle, &maxj); + if (!isidle) + break; + } + rcu_sysidle_report(rcu_sysidle_state, + isidle, maxj, false); + oldrss = rss; + rss = ACCESS_ONCE(full_sysidle_state); + } + } + + /* If this is the first observation of an idle period, record it. */ + if (rss == RCU_SYSIDLE_FULL) { + rss = cmpxchg(&full_sysidle_state, + RCU_SYSIDLE_FULL, RCU_SYSIDLE_FULL_NOTED); + return rss == RCU_SYSIDLE_FULL; + } + + smp_mb(); /* ensure rss load happens before later caller actions. */ + + /* If already fully idle, tell the caller (in case of races). */ + if (rss == RCU_SYSIDLE_FULL_NOTED) + return true; + + /* + * If we aren't there yet, and a grace period is not in flight, + * initiate a grace period. Either way, tell the caller that + * we are not there yet. We use an xchg() rather than an assignment + * to make up for the memory barriers that would otherwise be + * provided by the memory allocator. + */ + if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && + !rcu_gp_in_progress(rcu_sysidle_state) && + !rsh.inuse && xchg(&rsh.inuse, 1) == 0) + call_rcu(&rsh.rh, rcu_sysidle_cb); + return false; } /* @@ -2483,6 +2756,21 @@ static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq) { } +static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, + unsigned long *maxj) +{ +} + +static bool is_sysidle_rcu_state(struct rcu_state *rsp) +{ + return false; +} + +static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, + unsigned long maxj) +{ +} + static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp) { } diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index c7d2fd67799e..3381f098070f 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -157,6 +157,33 @@ config NO_HZ_FULL_SYSIDLE Say N if you are unsure. +config NO_HZ_FULL_SYSIDLE_SMALL + int "Number of CPUs above which large-system approach is used" + depends on NO_HZ_FULL_SYSIDLE + range 1 NR_CPUS + default 8 + help + The full-system idle detection mechanism takes a lazy approach + on large systems, as is required to attain decent scalability. + However, on smaller systems, scalability is not anywhere near as + large a concern as is energy efficiency. The sysidle subsystem + therefore uses a fast but non-scalable algorithm for small + systems and a lazier but scalable algorithm for large systems. + This Kconfig parameter defines the number of CPUs in the largest + system that will be considered to be "small". + + The default value will be fine in most cases. Battery-powered + systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger + numbers of CPUs, and (3) are suffering from battery-lifetime + problems due to long sysidle latencies might wish to experiment + with larger values for this Kconfig parameter. On the other + hand, they might be even better served by disabling NO_HZ_FULL + entirely, given that NO_HZ_FULL is intended for HPC and + real-time workloads that at present do not tend to be run on + battery-powered systems. + + Take the default if you are unsure. + config NO_HZ bool "Old Idle dynticks config" depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS -- cgit v1.2.3-71-gd317 From 274481de6cb69abdb49403ff32abb63c23743413 Mon Sep 17 00:00:00 2001 From: Vince Weaver Date: Fri, 23 Aug 2013 15:51:03 -0400 Subject: perf: Export struct perf_branch_entry to userspace If PERF_SAMPLE_BRANCH_STACK is enabled then samples are returned with the format { u64 from, to, flags } but the flags layout is not specified. This field has the type struct perf_branch_entry; move this definition into include/uapi/linux/perf_event.h so users can access these fields. This is similar to the existing inclusion of perf_mem_data_src in the include/uapi/linux/perf_event.h file. Signed-off-by: Vince Weaver Acked-by: Stephane Eranian Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1308231544420.1889@vincent-weaver-1.um.maine.edu Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 24 ------------------------ include/uapi/linux/perf_event.h | 24 ++++++++++++++++++++++++ 2 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c43f6eabad5b..4019d82c3d03 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -63,30 +63,6 @@ struct perf_raw_record { void *data; }; -/* - * single taken branch record layout: - * - * from: source instruction (may not always be a branch insn) - * to: branch target - * mispred: branch target was mispredicted - * predicted: branch target was predicted - * - * support for mispred, predicted is optional. In case it - * is not supported mispred = predicted = 0. - * - * in_tx: running in a hardware transaction - * abort: aborting a hardware transaction - */ -struct perf_branch_entry { - __u64 from; - __u64 to; - __u64 mispred:1, /* target mispredicted */ - predicted:1,/* target predicted */ - in_tx:1, /* in transaction */ - abort:1, /* transaction abort */ - reserved:60; -}; - /* * branch stack layout: * nr: number of taken branches stored in entries[] diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index a77f43af72b8..408b8c730731 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -757,4 +757,28 @@ union perf_mem_data_src { #define PERF_MEM_S(a, s) \ (((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) +/* + * single taken branch record layout: + * + * from: source instruction (may not always be a branch insn) + * to: branch target + * mispred: branch target was mispredicted + * predicted: branch target was predicted + * + * support for mispred, predicted is optional. In case it + * is not supported mispred = predicted = 0. + * + * in_tx: running in a hardware transaction + * abort: aborting a hardware transaction + */ +struct perf_branch_entry { + __u64 from; + __u64 to; + __u64 mispred:1, /* target mispredicted */ + predicted:1,/* target predicted */ + in_tx:1, /* in transaction */ + abort:1, /* transaction abort */ + reserved:60; +}; + #endif /* _UAPI_LINUX_PERF_EVENT_H */ -- cgit v1.2.3-71-gd317 From b3abd80250c13414bc258b53e57242feb159af91 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:14:19 -0700 Subject: lockref: add 'lockref_get_or_lock() helper This behaves like "lockref_get_not_zero()", but instead of doing nothing if the count was zero, it returns with the lock held. This allows callers to revalidate the lockref-protected data structure if required even if the count was zero to begin with, and possibly increment the count if it passes muster. In particular, the dentry code wants this when it wants to turn an RCU-protected dentry into a stable refcounted one: if the dentry count it zero, but the sequence number still validates the dentry, we can take a reference to it. Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 01233e01627a..0ea026092d1d 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -53,6 +53,22 @@ static inline int lockref_get_not_zero(struct lockref *lockref) return retval; } +/** + * lockref_get_or_lock - Increments count unless the count is 0 + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count was zero + * and we got the lock instead. + */ +static inline int lockref_get_or_lock(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + if (!lockref->count) + return 0; + lockref->count++; + spin_unlock(&lockref->lock); + return 1; +} + /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockcnt: pointer to lockref structure -- cgit v1.2.3-71-gd317 From 15570086b590a69d59183b08a7770e316cca20a7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:38:06 -0700 Subject: vfs: reimplement d_rcu_to_refcount() using lockref_get_or_lock() This moves __d_rcu_to_refcount() from into fs/namei.c and re-implements it using the lockref infrastructure instead. It also adds a lot of comments about what is actually going on, because turning a dentry that was looked up using RCU into a long-lived reference counted entry is one of the more subtle parts of the rcu walk. We also used to be _particularly_ subtle in unlazy_walk() where we re-validate both the dentry and its parent using the same sequence count. We used to do it by nesting the locks and then verifying the sequence count just once. That was silly, because nested locking is expensive, but the sequence count check is not. So this just re-validates the dentry and the parent separately, avoiding the nested locking, and making the lockref lookup possible. Acked-by: Waiman Long Signed-off-by: Linus Torvalds --- fs/dcache.c | 2 +- fs/namei.c | 90 +++++++++++++++++++++++++++++++++++--------------- include/linux/dcache.h | 22 ------------ 3 files changed, 65 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/fs/dcache.c b/fs/dcache.c index 2d244227999d..96655f4f4574 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1786,7 +1786,7 @@ static noinline enum slow_d_compare slow_dentry_cmp( * without taking d_lock and checking d_seq sequence count against @seq * returned here. * - * A refcount may be taken on the found dentry with the __d_rcu_to_refcount + * A refcount may be taken on the found dentry with the d_rcu_to_refcount * function. * * Alternatively, __d_lookup_rcu may be called again to look up the child of diff --git a/fs/namei.c b/fs/namei.c index 7720fbd5277b..2c30c84d4ea1 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -494,6 +494,50 @@ static inline void unlock_rcu_walk(void) br_read_unlock(&vfsmount_lock); } +/* + * When we move over from the RCU domain to properly refcounted + * long-lived dentries, we need to check the sequence numbers + * we got before lookup very carefully. + * + * We cannot blindly increment a dentry refcount - even if it + * is not locked - if it is zero, because it may have gone + * through the final d_kill() logic already. + * + * So for a zero refcount, we need to get the spinlock (which is + * safe even for a dead dentry because the de-allocation is + * RCU-delayed), and check the sequence count under the lock. + * + * Once we have checked the sequence count, we know it is live, + * and since we hold the spinlock it cannot die from under us. + * + * In contrast, if the reference count wasn't zero, we can just + * increment the lockref without having to take the spinlock. + * Even if the sequence number ends up being stale, we haven't + * gone through the final dput() and killed the dentry yet. + */ +static inline int d_rcu_to_refcount(struct dentry *dentry, seqcount_t *validate, unsigned seq) +{ + int gotref; + + gotref = lockref_get_or_lock(&dentry->d_lockref); + + /* Does the sequence number still match? */ + if (read_seqcount_retry(validate, seq)) { + if (gotref) + dput(dentry); + else + spin_unlock(&dentry->d_lock); + return -ECHILD; + } + + /* Get the ref now, if we couldn't get it originally */ + if (!gotref) { + dentry->d_lockref.count++; + spin_unlock(&dentry->d_lock); + } + return 0; +} + /** * unlazy_walk - try to switch to ref-walk mode. * @nd: nameidata pathwalk data @@ -518,29 +562,28 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) nd->root.dentry != fs->root.dentry) goto err_root; } - spin_lock(&parent->d_lock); + + /* + * For a negative lookup, the lookup sequence point is the parents + * sequence point, and it only needs to revalidate the parent dentry. + * + * For a positive lookup, we need to move both the parent and the + * dentry from the RCU domain to be properly refcounted. And the + * sequence number in the dentry validates *both* dentry counters, + * since we checked the sequence number of the parent after we got + * the child sequence number. So we know the parent must still + * be valid if the child sequence number is still valid. + */ if (!dentry) { - if (!__d_rcu_to_refcount(parent, nd->seq)) - goto err_parent; + if (d_rcu_to_refcount(parent, &parent->d_seq, nd->seq) < 0) + goto err_root; BUG_ON(nd->inode != parent->d_inode); } else { - if (dentry->d_parent != parent) + if (d_rcu_to_refcount(dentry, &dentry->d_seq, nd->seq) < 0) + goto err_root; + if (d_rcu_to_refcount(parent, &dentry->d_seq, nd->seq) < 0) goto err_parent; - spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - if (!__d_rcu_to_refcount(dentry, nd->seq)) - goto err_child; - /* - * If the sequence check on the child dentry passed, then - * the child has not been removed from its parent. This - * means the parent dentry must be valid and able to take - * a reference at this point. - */ - BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent); - BUG_ON(!parent->d_lockref.count); - parent->d_lockref.count++; - spin_unlock(&dentry->d_lock); } - spin_unlock(&parent->d_lock); if (want_root) { path_get(&nd->root); spin_unlock(&fs->lock); @@ -551,10 +594,8 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) nd->flags &= ~LOOKUP_RCU; return 0; -err_child: - spin_unlock(&dentry->d_lock); err_parent: - spin_unlock(&parent->d_lock); + dput(dentry); err_root: if (want_root) spin_unlock(&fs->lock); @@ -585,14 +626,11 @@ static int complete_walk(struct nameidata *nd) nd->flags &= ~LOOKUP_RCU; if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; - spin_lock(&dentry->d_lock); - if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) { - spin_unlock(&dentry->d_lock); + + if (d_rcu_to_refcount(dentry, &dentry->d_seq, nd->seq) < 0) { unlock_rcu_walk(); return -ECHILD; } - BUG_ON(nd->inode != dentry->d_inode); - spin_unlock(&dentry->d_lock); mntget(nd->path.mnt); unlock_rcu_walk(); } diff --git a/include/linux/dcache.h b/include/linux/dcache.h index efdc94434c30..9169b91ea2d2 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -304,28 +304,6 @@ extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); -/** - * __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok - * @dentry: dentry to take a ref on - * @seq: seqcount to verify against - * Returns: 0 on failure, else 1. - * - * __d_rcu_to_refcount operates on a dentry,seq pair that was returned - * by __d_lookup_rcu, to get a reference on an rcu-walk dentry. - */ -static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) -{ - int ret = 0; - - assert_spin_locked(&dentry->d_lock); - if (!read_seqcount_retry(&dentry->d_seq, seq)) { - ret = 1; - dentry->d_lockref.count++; - } - - return ret; -} - static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; -- cgit v1.2.3-71-gd317 From 2f4f12e571c4e2f50f3818a3c2544929145f75dd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 11:58:20 -0700 Subject: lockref: uninline lockref helper functions They aren't very good to inline, since they already call external functions (the spinlock code), and we're going to create rather more complicated versions of them that can do the reference count updates locklessly. Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 66 +++------------------------------------------- lib/Makefile | 1 + lib/lockref.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 74 insertions(+), 62 deletions(-) create mode 100644 lib/lockref.c (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 0ea026092d1d..4c0af31c8d47 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -21,67 +21,9 @@ struct lockref { unsigned int count; }; -/** - * lockref_get - Increments reference count unconditionally - * @lockcnt: pointer to lockref structure - * - * This operation is only valid if you already hold a reference - * to the object, so you know the count cannot be zero. - */ -static inline void lockref_get(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - lockref->count++; - spin_unlock(&lockref->lock); -} - -/** - * lockref_get_not_zero - Increments count unless the count is 0 - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count is 0 - */ -static inline int lockref_get_not_zero(struct lockref *lockref) -{ - int retval = 0; - - spin_lock(&lockref->lock); - if (lockref->count) { - lockref->count++; - retval = 1; - } - spin_unlock(&lockref->lock); - return retval; -} - -/** - * lockref_get_or_lock - Increments count unless the count is 0 - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count was zero - * and we got the lock instead. - */ -static inline int lockref_get_or_lock(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - if (!lockref->count) - return 0; - lockref->count++; - spin_unlock(&lockref->lock); - return 1; -} - -/** - * lockref_put_or_lock - decrements count unless count <= 1 before decrement - * @lockcnt: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken - */ -static inline int lockref_put_or_lock(struct lockref *lockref) -{ - spin_lock(&lockref->lock); - if (lockref->count <= 1) - return 0; - lockref->count--; - spin_unlock(&lockref->lock); - return 1; -} +extern void lockref_get(struct lockref *); +extern int lockref_get_not_zero(struct lockref *); +extern int lockref_get_or_lock(struct lockref *); +extern int lockref_put_or_lock(struct lockref *); #endif /* __LINUX_LOCKREF_H */ diff --git a/lib/Makefile b/lib/Makefile index 7baccfd8a4e9..f2cb3082697c 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -20,6 +20,7 @@ lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-y += kobject.o klist.o +obj-y += lockref.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ diff --git a/lib/lockref.c b/lib/lockref.c new file mode 100644 index 000000000000..a9a4f4e1eff5 --- /dev/null +++ b/lib/lockref.c @@ -0,0 +1,69 @@ +#include +#include + +/** + * lockref_get - Increments reference count unconditionally + * @lockcnt: pointer to lockref structure + * + * This operation is only valid if you already hold a reference + * to the object, so you know the count cannot be zero. + */ +void lockref_get(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + lockref->count++; + spin_unlock(&lockref->lock); +} +EXPORT_SYMBOL(lockref_get); + +/** + * lockref_get_not_zero - Increments count unless the count is 0 + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count was zero + */ +int lockref_get_not_zero(struct lockref *lockref) +{ + int retval = 0; + + spin_lock(&lockref->lock); + if (lockref->count) { + lockref->count++; + retval = 1; + } + spin_unlock(&lockref->lock); + return retval; +} +EXPORT_SYMBOL(lockref_get_not_zero); + +/** + * lockref_get_or_lock - Increments count unless the count is 0 + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count was zero + * and we got the lock instead. + */ +int lockref_get_or_lock(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + if (!lockref->count) + return 0; + lockref->count++; + spin_unlock(&lockref->lock); + return 1; +} +EXPORT_SYMBOL(lockref_get_or_lock); + +/** + * lockref_put_or_lock - decrements count unless count <= 1 before decrement + * @lockcnt: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken + */ +int lockref_put_or_lock(struct lockref *lockref) +{ + spin_lock(&lockref->lock); + if (lockref->count <= 1) + return 0; + lockref->count--; + spin_unlock(&lockref->lock); + return 1; +} +EXPORT_SYMBOL(lockref_put_or_lock); -- cgit v1.2.3-71-gd317 From bc08b449ee14ace4d869adaa1bb35a44ce68d775 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 2 Sep 2013 12:12:15 -0700 Subject: lockref: implement lockless reference count updates using cmpxchg() Instead of taking the spinlock, the lockless versions atomically check that the lock is not taken, and do the reference count update using a cmpxchg() loop. This is semantically identical to doing the reference count update protected by the lock, but avoids the "wait for lock" contention that you get when accesses to the reference count are contended. Note that a "lockref" is absolutely _not_ equivalent to an atomic_t. Even when the lockref reference counts are updated atomically with cmpxchg, the fact that they also verify the state of the spinlock means that the lockless updates can never happen while somebody else holds the spinlock. So while "lockref_put_or_lock()" looks a lot like just another name for "atomic_dec_and_lock()", and both optimize to lockless updates, they are fundamentally different: the decrement done by atomic_dec_and_lock() is truly independent of any lock (as long as it doesn't decrement to zero), so a locked region can still see the count change. The lockref structure, in contrast, really is a *locked* reference count. If you hold the spinlock, the reference count will be stable and you can modify the reference count without using atomics, because even the lockless updates will see and respect the state of the lock. In order to enable the cmpxchg lockless code, the architecture needs to do three things: (1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit in an aligned u64, and have a "cmpxchg()" implementation that works on such a u64 data type. (2) define a helper function to test for a spinlock being unlocked ("arch_spin_value_unlocked()") (3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its Kconfig file. This enables it for x86-64 (but not 32-bit, we'd need to make sure cmpxchg() turns into the proper cmpxchg8b in order to enable it for 32-bit mode). Signed-off-by: Linus Torvalds --- arch/x86/Kconfig | 1 + arch/x86/include/asm/spinlock.h | 5 ++++ include/linux/lockref.h | 11 ++++++-- lib/Kconfig | 10 +++++++ lib/lockref.c | 60 ++++++++++++++++++++++++++++++++++++++++- 5 files changed, 84 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b32ebf92b0ce..67e00740531c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -16,6 +16,7 @@ config X86_64 def_bool y depends on 64BIT select X86_DEV_DMA_OPS + select ARCH_USE_CMPXCHG_LOCKREF ### Arch settings config X86 diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index e3ddd7db723f..e0e668422c75 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -34,6 +34,11 @@ # define UNLOCK_LOCK_PREFIX #endif +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.tickets.head == lock.tickets.tail; +} + /* * Ticket locks are conceptually two parts, one indicating the current head of * the queue, and the other indicating the current tail. The lock is acquired diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 4c0af31c8d47..ca07b5028b01 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -17,8 +17,15 @@ #include struct lockref { - spinlock_t lock; - unsigned int count; + union { +#ifdef CONFIG_CMPXCHG_LOCKREF + aligned_u64 lock_count; +#endif + struct { + spinlock_t lock; + unsigned int count; + }; + }; }; extern void lockref_get(struct lockref *); diff --git a/lib/Kconfig b/lib/Kconfig index 71d9f81f6eed..65561716c16c 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -48,6 +48,16 @@ config STMP_DEVICE config PERCPU_RWSEM boolean +config ARCH_USE_CMPXCHG_LOCKREF + bool + +config CMPXCHG_LOCKREF + def_bool y if ARCH_USE_CMPXCHG_LOCKREF + depends on SMP + depends on !GENERIC_LOCKBREAK + depends on !DEBUG_SPINLOCK + depends on !DEBUG_LOCK_ALLOC + config CRC_CCITT tristate "CRC-CCITT functions" help diff --git a/lib/lockref.c b/lib/lockref.c index a9a4f4e1eff5..7819c2d1d315 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -1,6 +1,33 @@ #include #include +#ifdef CONFIG_CMPXCHG_LOCKREF + +/* + * Note that the "cmpxchg()" reloads the "old" value for the + * failure case. + */ +#define CMPXCHG_LOOP(CODE, SUCCESS) do { \ + struct lockref old; \ + BUILD_BUG_ON(sizeof(old) != 8); \ + old.lock_count = ACCESS_ONCE(lockref->lock_count); \ + while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ + struct lockref new = old, prev = old; \ + CODE \ + old.lock_count = cmpxchg(&lockref->lock_count, \ + old.lock_count, new.lock_count); \ + if (likely(old.lock_count == prev.lock_count)) { \ + SUCCESS; \ + } \ + } \ +} while (0) + +#else + +#define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) + +#endif + /** * lockref_get - Increments reference count unconditionally * @lockcnt: pointer to lockref structure @@ -10,6 +37,12 @@ */ void lockref_get(struct lockref *lockref) { + CMPXCHG_LOOP( + new.count++; + , + return; + ); + spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); @@ -23,9 +56,18 @@ EXPORT_SYMBOL(lockref_get); */ int lockref_get_not_zero(struct lockref *lockref) { - int retval = 0; + int retval; + + CMPXCHG_LOOP( + new.count++; + if (!old.count) + return 0; + , + return 1; + ); spin_lock(&lockref->lock); + retval = 0; if (lockref->count) { lockref->count++; retval = 1; @@ -43,6 +85,14 @@ EXPORT_SYMBOL(lockref_get_not_zero); */ int lockref_get_or_lock(struct lockref *lockref) { + CMPXCHG_LOOP( + new.count++; + if (!old.count) + break; + , + return 1; + ); + spin_lock(&lockref->lock); if (!lockref->count) return 0; @@ -59,6 +109,14 @@ EXPORT_SYMBOL(lockref_get_or_lock); */ int lockref_put_or_lock(struct lockref *lockref) { + CMPXCHG_LOOP( + new.count--; + if (old.count <= 1) + break; + , + return 1; + ); + spin_lock(&lockref->lock); if (lockref->count <= 1) return 0; -- cgit v1.2.3-71-gd317