From 6b0afc2a21726b2d6b6aa441af40cafaf5405cc8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 3 Feb 2014 14:03:01 -0500 Subject: kernfs, sysfs, driver-core: implement kernfs_remove_self() and its wrappers Sometimes it's necessary to implement a node which wants to delete nodes including itself. This isn't straightforward because of kernfs active reference. While a file operation is in progress, an active reference is held and kernfs_remove() waits for all such references to drain before completing. For a self-deleting node, this is a deadlock as kernfs_remove() ends up waiting for an active reference that itself is sitting on top of. This currently is worked around in the sysfs layer using sysfs_schedule_callback() which makes such removals asynchronous. While it works, it's rather cumbersome and inherently breaks synchronicity of the operation - the file operation which triggered the operation may complete before the removal is finished (or even started) and the removal may fail asynchronously. If a removal operation is immmediately followed by another operation which expects the specific name to be available (e.g. removal followed by rename onto the same name), there's no way to make the latter operation reliable. The thing is there's no inherent reason for this to be asynchrnous. All that's necessary to do this synchronous is a dedicated operation which drops its own active ref and deactivates self. This patch implements kernfs_remove_self() and its wrappers in sysfs and driver core. kernfs_remove_self() is to be called from one of the file operations, drops the active ref the task is holding, removes the self node, and restores active ref to the dead node so that the ref is balanced afterwards. __kernfs_remove() is updated so that it takes an early exit if the target node is already fully removed so that the active ref restored by kernfs_remove_self() after removal doesn't confuse the deactivation path. This makes implementing self-deleting nodes very easy. The normal removal path doesn't even need to be changed to use kernfs_remove_self() for the self-deleting node. The method can invoke kernfs_remove_self() on itself before proceeding the normal removal path. kernfs_remove() invoked on the node by the normal deletion path will simply be ignored. This will replace sysfs_schedule_callback(). A subtle feature of sysfs_schedule_callback() is that it collapses multiple invocations - even if multiple removals are triggered, the removal callback is run only once. An equivalent effect can be achieved by testing the return value of kernfs_remove_self() - only the one which gets %true return value should proceed with actual deletion. All other instances of kernfs_remove_self() will wait till the enclosing kernfs operation which invoked the winning instance of kernfs_remove_self() finishes and then return %false. This trivially makes all users of kernfs_remove_self() automatically show correct synchronous behavior even when there are multiple concurrent operations - all "echo 1 > delete" instances will finish only after the whole operation is completed by one of the instances. Note that manipulation of active ref is implemented in separate public functions - kernfs_[un]break_active_protection(). kernfs_remove_self() is the only user at the moment but this will be used to cater to more complex cases. v2: For !CONFIG_SYSFS, dummy version kernfs_remove_self() was missing and sysfs_remove_file_self() had incorrect return type. Fix it. Reported by kbuild test bot. v3: kernfs_[un]break_active_protection() separated out from kernfs_remove_self() and exposed as public API. Signed-off-by: Tejun Heo Cc: Alan Stern Cc: kbuild test robot Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/device.h') diff --git a/include/linux/device.h b/include/linux/device.h index 952b01033c32..1ff3f1697513 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -560,6 +560,8 @@ extern int device_create_file(struct device *device, const struct device_attribute *entry); extern void device_remove_file(struct device *dev, const struct device_attribute *attr); +extern bool device_remove_file_self(struct device *dev, + const struct device_attribute *attr); extern int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); extern void device_remove_bin_file(struct device *dev, -- cgit v1.2.3 From ce8b04aa6c9bdf211b921fdd18c040ea29516b97 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 3 Feb 2014 14:03:05 -0500 Subject: sysfs, driver-core: remove unused {sysfs|device}_schedule_callback_owner() All device_schedule_callback_owner() users are converted to use device_remove_file_self(). Remove now unused {sysfs|device}_schedule_callback_owner(). Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 33 ------------------ fs/sysfs/file.c | 92 -------------------------------------------------- include/linux/device.h | 11 +----- include/linux/sysfs.h | 9 ----- 4 files changed, 1 insertion(+), 144 deletions(-) (limited to 'include/linux/device.h') diff --git a/drivers/base/core.c b/drivers/base/core.c index 9db57afcf81f..4195364f9fdd 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -615,39 +615,6 @@ void device_remove_bin_file(struct device *dev, } EXPORT_SYMBOL_GPL(device_remove_bin_file); -/** - * device_schedule_callback_owner - helper to schedule a callback for a device - * @dev: device. - * @func: callback function to invoke later. - * @owner: module owning the callback routine - * - * Attribute methods must not unregister themselves or their parent device - * (which would amount to the same thing). Attempts to do so will deadlock, - * since unregistration is mutually exclusive with driver callbacks. - * - * Instead methods can call this routine, which will attempt to allocate - * and schedule a workqueue request to call back @func with @dev as its - * argument in the workqueue's process context. @dev will be pinned until - * @func returns. - * - * This routine is usually called via the inline device_schedule_callback(), - * which automatically sets @owner to THIS_MODULE. - * - * Returns 0 if the request was submitted, -ENOMEM if storage could not - * be allocated, -ENODEV if a reference to @owner isn't available. - * - * NOTE: This routine won't work if CONFIG_SYSFS isn't set! It uses an - * underlying sysfs routine (since it is intended for use by attribute - * methods), and if sysfs isn't available you'll get nothing but -ENOSYS. - */ -int device_schedule_callback_owner(struct device *dev, - void (*func)(struct device *), struct module *owner) -{ - return sysfs_schedule_callback(&dev->kobj, - (void (*)(void *)) func, dev, owner); -} -EXPORT_SYMBOL_GPL(device_schedule_callback_owner); - static void klist_children_get(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 1b8b91b67fdb..28cc1acd5439 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -453,95 +453,3 @@ void sysfs_remove_bin_file(struct kobject *kobj, kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); - -struct sysfs_schedule_callback_struct { - struct list_head workq_list; - struct kobject *kobj; - void (*func)(void *); - void *data; - struct module *owner; - struct work_struct work; -}; - -static struct workqueue_struct *sysfs_workqueue; -static DEFINE_MUTEX(sysfs_workq_mutex); -static LIST_HEAD(sysfs_workq); -static void sysfs_schedule_callback_work(struct work_struct *work) -{ - struct sysfs_schedule_callback_struct *ss = container_of(work, - struct sysfs_schedule_callback_struct, work); - - (ss->func)(ss->data); - kobject_put(ss->kobj); - module_put(ss->owner); - mutex_lock(&sysfs_workq_mutex); - list_del(&ss->workq_list); - mutex_unlock(&sysfs_workq_mutex); - kfree(ss); -} - -/** - * sysfs_schedule_callback - helper to schedule a callback for a kobject - * @kobj: object we're acting for. - * @func: callback function to invoke later. - * @data: argument to pass to @func. - * @owner: module owning the callback code - * - * sysfs attribute methods must not unregister themselves or their parent - * kobject (which would amount to the same thing). Attempts to do so will - * deadlock, since unregistration is mutually exclusive with driver - * callbacks. - * - * Instead methods can call this routine, which will attempt to allocate - * and schedule a workqueue request to call back @func with @data as its - * argument in the workqueue's process context. @kobj will be pinned - * until @func returns. - * - * Returns 0 if the request was submitted, -ENOMEM if storage could not - * be allocated, -ENODEV if a reference to @owner isn't available, - * -EAGAIN if a callback has already been scheduled for @kobj. - */ -int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), - void *data, struct module *owner) -{ - struct sysfs_schedule_callback_struct *ss, *tmp; - - if (!try_module_get(owner)) - return -ENODEV; - - mutex_lock(&sysfs_workq_mutex); - list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list) - if (ss->kobj == kobj) { - module_put(owner); - mutex_unlock(&sysfs_workq_mutex); - return -EAGAIN; - } - mutex_unlock(&sysfs_workq_mutex); - - if (sysfs_workqueue == NULL) { - sysfs_workqueue = create_singlethread_workqueue("sysfsd"); - if (sysfs_workqueue == NULL) { - module_put(owner); - return -ENOMEM; - } - } - - ss = kmalloc(sizeof(*ss), GFP_KERNEL); - if (!ss) { - module_put(owner); - return -ENOMEM; - } - kobject_get(kobj); - ss->kobj = kobj; - ss->func = func; - ss->data = data; - ss->owner = owner; - INIT_WORK(&ss->work, sysfs_schedule_callback_work); - INIT_LIST_HEAD(&ss->workq_list); - mutex_lock(&sysfs_workq_mutex); - list_add_tail(&ss->workq_list, &sysfs_workq); - mutex_unlock(&sysfs_workq_mutex); - queue_work(sysfs_workqueue, &ss->work); - return 0; -} -EXPORT_SYMBOL_GPL(sysfs_schedule_callback); diff --git a/include/linux/device.h b/include/linux/device.h index 1ff3f1697513..fb1ba13f7665 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -566,12 +566,6 @@ extern int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); extern void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); -extern int device_schedule_callback_owner(struct device *dev, - void (*func)(struct device *dev), struct module *owner); - -/* This is a macro to avoid include problems with THIS_MODULE */ -#define device_schedule_callback(dev, func) \ - device_schedule_callback_owner(dev, func, THIS_MODULE) /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); @@ -931,10 +925,7 @@ extern int device_online(struct device *dev); extern struct device *__root_device_register(const char *name, struct module *owner); -/* - * This is a macro to avoid include problems with THIS_MODULE, - * just as per what is done for device_schedule_callback() above. - */ +/* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index bd96c603ab6c..14df05415af9 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -178,9 +178,6 @@ struct sysfs_ops { #ifdef CONFIG_SYSFS -int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), - void *data, struct module *owner); - int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns); void sysfs_remove_dir(struct kobject *kobj); int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, @@ -249,12 +246,6 @@ int __must_check sysfs_init(void); #else /* CONFIG_SYSFS */ -static inline int sysfs_schedule_callback(struct kobject *kobj, - void (*func)(void *), void *data, struct module *owner) -{ - return -ENOSYS; -} - static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { return 0; -- cgit v1.2.3 From 72099304eeb316c4b00df3ae83efe4375729bd78 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 25 Mar 2014 20:54:57 -0700 Subject: Revert "sysfs, driver-core: remove unused {sysfs|device}_schedule_callback_owner()" This reverts commit d1ba277e79889085a2faec3b68b91ce89c63f888. As reported by Stephen, this patch breaks linux-next as a ppc patch suddenly (after 2 years) started using this old api call. So revert it for now, it will go away in 3.15-rc2 when we can change the PPC call to the new api. Reported-by: Stephen Rothwell Cc: Tejun Heo Cc: Stewart Smith Cc: Benjamin Herrenschmidt Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 33 ++++++++++++++++++ fs/sysfs/file.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/device.h | 11 +++++- include/linux/sysfs.h | 9 +++++ 4 files changed, 144 insertions(+), 1 deletion(-) (limited to 'include/linux/device.h') diff --git a/drivers/base/core.c b/drivers/base/core.c index 20da3ad1696b..0dd65281cc65 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -614,6 +614,39 @@ void device_remove_bin_file(struct device *dev, } EXPORT_SYMBOL_GPL(device_remove_bin_file); +/** + * device_schedule_callback_owner - helper to schedule a callback for a device + * @dev: device. + * @func: callback function to invoke later. + * @owner: module owning the callback routine + * + * Attribute methods must not unregister themselves or their parent device + * (which would amount to the same thing). Attempts to do so will deadlock, + * since unregistration is mutually exclusive with driver callbacks. + * + * Instead methods can call this routine, which will attempt to allocate + * and schedule a workqueue request to call back @func with @dev as its + * argument in the workqueue's process context. @dev will be pinned until + * @func returns. + * + * This routine is usually called via the inline device_schedule_callback(), + * which automatically sets @owner to THIS_MODULE. + * + * Returns 0 if the request was submitted, -ENOMEM if storage could not + * be allocated, -ENODEV if a reference to @owner isn't available. + * + * NOTE: This routine won't work if CONFIG_SYSFS isn't set! It uses an + * underlying sysfs routine (since it is intended for use by attribute + * methods), and if sysfs isn't available you'll get nothing but -ENOSYS. + */ +int device_schedule_callback_owner(struct device *dev, + void (*func)(struct device *), struct module *owner) +{ + return sysfs_schedule_callback(&dev->kobj, + (void (*)(void *)) func, dev, owner); +} +EXPORT_SYMBOL_GPL(device_schedule_callback_owner); + static void klist_children_get(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 28cc1acd5439..1b8b91b67fdb 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -453,3 +453,95 @@ void sysfs_remove_bin_file(struct kobject *kobj, kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); + +struct sysfs_schedule_callback_struct { + struct list_head workq_list; + struct kobject *kobj; + void (*func)(void *); + void *data; + struct module *owner; + struct work_struct work; +}; + +static struct workqueue_struct *sysfs_workqueue; +static DEFINE_MUTEX(sysfs_workq_mutex); +static LIST_HEAD(sysfs_workq); +static void sysfs_schedule_callback_work(struct work_struct *work) +{ + struct sysfs_schedule_callback_struct *ss = container_of(work, + struct sysfs_schedule_callback_struct, work); + + (ss->func)(ss->data); + kobject_put(ss->kobj); + module_put(ss->owner); + mutex_lock(&sysfs_workq_mutex); + list_del(&ss->workq_list); + mutex_unlock(&sysfs_workq_mutex); + kfree(ss); +} + +/** + * sysfs_schedule_callback - helper to schedule a callback for a kobject + * @kobj: object we're acting for. + * @func: callback function to invoke later. + * @data: argument to pass to @func. + * @owner: module owning the callback code + * + * sysfs attribute methods must not unregister themselves or their parent + * kobject (which would amount to the same thing). Attempts to do so will + * deadlock, since unregistration is mutually exclusive with driver + * callbacks. + * + * Instead methods can call this routine, which will attempt to allocate + * and schedule a workqueue request to call back @func with @data as its + * argument in the workqueue's process context. @kobj will be pinned + * until @func returns. + * + * Returns 0 if the request was submitted, -ENOMEM if storage could not + * be allocated, -ENODEV if a reference to @owner isn't available, + * -EAGAIN if a callback has already been scheduled for @kobj. + */ +int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), + void *data, struct module *owner) +{ + struct sysfs_schedule_callback_struct *ss, *tmp; + + if (!try_module_get(owner)) + return -ENODEV; + + mutex_lock(&sysfs_workq_mutex); + list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list) + if (ss->kobj == kobj) { + module_put(owner); + mutex_unlock(&sysfs_workq_mutex); + return -EAGAIN; + } + mutex_unlock(&sysfs_workq_mutex); + + if (sysfs_workqueue == NULL) { + sysfs_workqueue = create_singlethread_workqueue("sysfsd"); + if (sysfs_workqueue == NULL) { + module_put(owner); + return -ENOMEM; + } + } + + ss = kmalloc(sizeof(*ss), GFP_KERNEL); + if (!ss) { + module_put(owner); + return -ENOMEM; + } + kobject_get(kobj); + ss->kobj = kobj; + ss->func = func; + ss->data = data; + ss->owner = owner; + INIT_WORK(&ss->work, sysfs_schedule_callback_work); + INIT_LIST_HEAD(&ss->workq_list); + mutex_lock(&sysfs_workq_mutex); + list_add_tail(&ss->workq_list, &sysfs_workq); + mutex_unlock(&sysfs_workq_mutex); + queue_work(sysfs_workqueue, &ss->work); + return 0; +} +EXPORT_SYMBOL_GPL(sysfs_schedule_callback); diff --git a/include/linux/device.h b/include/linux/device.h index fb1ba13f7665..1ff3f1697513 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -566,6 +566,12 @@ extern int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); extern void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); +extern int device_schedule_callback_owner(struct device *dev, + void (*func)(struct device *dev), struct module *owner); + +/* This is a macro to avoid include problems with THIS_MODULE */ +#define device_schedule_callback(dev, func) \ + device_schedule_callback_owner(dev, func, THIS_MODULE) /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); @@ -925,7 +931,10 @@ extern int device_online(struct device *dev); extern struct device *__root_device_register(const char *name, struct module *owner); -/* This is a macro to avoid include problems with THIS_MODULE */ +/* + * This is a macro to avoid include problems with THIS_MODULE, + * just as per what is done for device_schedule_callback() above. + */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index fdaa0c6fc7a2..e0bf210ddffd 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -178,6 +178,9 @@ struct sysfs_ops { #ifdef CONFIG_SYSFS +int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), + void *data, struct module *owner); + int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns); void sysfs_remove_dir(struct kobject *kobj); int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, @@ -251,6 +254,12 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn) #else /* CONFIG_SYSFS */ +static inline int sysfs_schedule_callback(struct kobject *kobj, + void (*func)(void *), void *data, struct module *owner) +{ + return -ENOSYS; +} + static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { return 0; -- cgit v1.2.3