324 lines · plain
1===================================================2Adding reference counters (krefs) to kernel objects3===================================================4 5:Author: Corey Minyard <minyard@acm.org>6:Author: Thomas Hellstrom <thellstrom@vmware.com>7 8A lot of this was lifted from Greg Kroah-Hartman's 2004 OLS paper and9presentation on krefs, which can be found at:10 11 - http://www.kroah.com/linux/talks/ols_2004_kref_paper/Reprint-Kroah-Hartman-OLS2004.pdf12 - http://www.kroah.com/linux/talks/ols_2004_kref_talk/13 14Introduction15============16 17krefs allow you to add reference counters to your objects. If you18have objects that are used in multiple places and passed around, and19you don't have refcounts, your code is almost certainly broken. If20you want refcounts, krefs are the way to go.21 22To use a kref, add one to your data structures like::23 24 struct my_data25 {26 .27 .28 struct kref refcount;29 .30 .31 };32 33The kref can occur anywhere within the data structure.34 35Initialization36==============37 38You must initialize the kref after you allocate it. To do this, call39kref_init as so::40 41 struct my_data *data;42 43 data = kmalloc(sizeof(*data), GFP_KERNEL);44 if (!data)45 return -ENOMEM;46 kref_init(&data->refcount);47 48This sets the refcount in the kref to 1.49 50Kref rules51==========52 53Once you have an initialized kref, you must follow the following54rules:55 561) If you make a non-temporary copy of a pointer, especially if57 it can be passed to another thread of execution, you must58 increment the refcount with kref_get() before passing it off::59 60 kref_get(&data->refcount);61 62 If you already have a valid pointer to a kref-ed structure (the63 refcount cannot go to zero) you may do this without a lock.64 652) When you are done with a pointer, you must call kref_put()::66 67 kref_put(&data->refcount, data_release);68 69 If this is the last reference to the pointer, the release70 routine will be called. If the code never tries to get71 a valid pointer to a kref-ed structure without already72 holding a valid pointer, it is safe to do this without73 a lock.74 753) If the code attempts to gain a reference to a kref-ed structure76 without already holding a valid pointer, it must serialize access77 where a kref_put() cannot occur during the kref_get(), and the78 structure must remain valid during the kref_get().79 80For example, if you allocate some data and then pass it to another81thread to process::82 83 void data_release(struct kref *ref)84 {85 struct my_data *data = container_of(ref, struct my_data, refcount);86 kfree(data);87 }88 89 void more_data_handling(void *cb_data)90 {91 struct my_data *data = cb_data;92 .93 . do stuff with data here94 .95 kref_put(&data->refcount, data_release);96 }97 98 int my_data_handler(void)99 {100 int rv = 0;101 struct my_data *data;102 struct task_struct *task;103 data = kmalloc(sizeof(*data), GFP_KERNEL);104 if (!data)105 return -ENOMEM;106 kref_init(&data->refcount);107 108 kref_get(&data->refcount);109 task = kthread_run(more_data_handling, data, "more_data_handling");110 if (task == ERR_PTR(-ENOMEM)) {111 rv = -ENOMEM;112 kref_put(&data->refcount, data_release);113 goto out;114 }115 116 .117 . do stuff with data here118 .119 out:120 kref_put(&data->refcount, data_release);121 return rv;122 }123 124This way, it doesn't matter what order the two threads handle the125data, the kref_put() handles knowing when the data is not referenced126any more and releasing it. The kref_get() does not require a lock,127since we already have a valid pointer that we own a refcount for. The128put needs no lock because nothing tries to get the data without129already holding a pointer.130 131In the above example, kref_put() will be called 2 times in both success132and error paths. This is necessary because the reference count got133incremented 2 times by kref_init() and kref_get().134 135Note that the "before" in rule 1 is very important. You should never136do something like::137 138 task = kthread_run(more_data_handling, data, "more_data_handling");139 if (task == ERR_PTR(-ENOMEM)) {140 rv = -ENOMEM;141 goto out;142 } else143 /* BAD BAD BAD - get is after the handoff */144 kref_get(&data->refcount);145 146Don't assume you know what you are doing and use the above construct.147First of all, you may not know what you are doing. Second, you may148know what you are doing (there are some situations where locking is149involved where the above may be legal) but someone else who doesn't150know what they are doing may change the code or copy the code. It's151bad style. Don't do it.152 153There are some situations where you can optimize the gets and puts.154For instance, if you are done with an object and enqueuing it for155something else or passing it off to something else, there is no reason156to do a get then a put::157 158 /* Silly extra get and put */159 kref_get(&obj->ref);160 enqueue(obj);161 kref_put(&obj->ref, obj_cleanup);162 163Just do the enqueue. A comment about this is always welcome::164 165 enqueue(obj);166 /* We are done with obj, so we pass our refcount off167 to the queue. DON'T TOUCH obj AFTER HERE! */168 169The last rule (rule 3) is the nastiest one to handle. Say, for170instance, you have a list of items that are each kref-ed, and you wish171to get the first one. You can't just pull the first item off the list172and kref_get() it. That violates rule 3 because you are not already173holding a valid pointer. You must add a mutex (or some other lock).174For instance::175 176 static DEFINE_MUTEX(mutex);177 static LIST_HEAD(q);178 struct my_data179 {180 struct kref refcount;181 struct list_head link;182 };183 184 static struct my_data *get_entry()185 {186 struct my_data *entry = NULL;187 mutex_lock(&mutex);188 if (!list_empty(&q)) {189 entry = container_of(q.next, struct my_data, link);190 kref_get(&entry->refcount);191 }192 mutex_unlock(&mutex);193 return entry;194 }195 196 static void release_entry(struct kref *ref)197 {198 struct my_data *entry = container_of(ref, struct my_data, refcount);199 200 list_del(&entry->link);201 kfree(entry);202 }203 204 static void put_entry(struct my_data *entry)205 {206 mutex_lock(&mutex);207 kref_put(&entry->refcount, release_entry);208 mutex_unlock(&mutex);209 }210 211The kref_put() return value is useful if you do not want to hold the212lock during the whole release operation. Say you didn't want to call213kfree() with the lock held in the example above (since it is kind of214pointless to do so). You could use kref_put() as follows::215 216 static void release_entry(struct kref *ref)217 {218 /* All work is done after the return from kref_put(). */219 }220 221 static void put_entry(struct my_data *entry)222 {223 mutex_lock(&mutex);224 if (kref_put(&entry->refcount, release_entry)) {225 list_del(&entry->link);226 mutex_unlock(&mutex);227 kfree(entry);228 } else229 mutex_unlock(&mutex);230 }231 232This is really more useful if you have to call other routines as part233of the free operations that could take a long time or might claim the234same lock. Note that doing everything in the release routine is still235preferred as it is a little neater.236 237The above example could also be optimized using kref_get_unless_zero() in238the following way::239 240 static struct my_data *get_entry()241 {242 struct my_data *entry = NULL;243 mutex_lock(&mutex);244 if (!list_empty(&q)) {245 entry = container_of(q.next, struct my_data, link);246 if (!kref_get_unless_zero(&entry->refcount))247 entry = NULL;248 }249 mutex_unlock(&mutex);250 return entry;251 }252 253 static void release_entry(struct kref *ref)254 {255 struct my_data *entry = container_of(ref, struct my_data, refcount);256 257 mutex_lock(&mutex);258 list_del(&entry->link);259 mutex_unlock(&mutex);260 kfree(entry);261 }262 263 static void put_entry(struct my_data *entry)264 {265 kref_put(&entry->refcount, release_entry);266 }267 268Which is useful to remove the mutex lock around kref_put() in put_entry(), but269it's important that kref_get_unless_zero is enclosed in the same critical270section that finds the entry in the lookup table,271otherwise kref_get_unless_zero may reference already freed memory.272Note that it is illegal to use kref_get_unless_zero without checking its273return value. If you are sure (by already having a valid pointer) that274kref_get_unless_zero() will return true, then use kref_get() instead.275 276Krefs and RCU277=============278 279The function kref_get_unless_zero also makes it possible to use rcu280locking for lookups in the above example::281 282 struct my_data283 {284 struct rcu_head rhead;285 .286 struct kref refcount;287 .288 .289 };290 291 static struct my_data *get_entry_rcu()292 {293 struct my_data *entry = NULL;294 rcu_read_lock();295 if (!list_empty(&q)) {296 entry = container_of(q.next, struct my_data, link);297 if (!kref_get_unless_zero(&entry->refcount))298 entry = NULL;299 }300 rcu_read_unlock();301 return entry;302 }303 304 static void release_entry_rcu(struct kref *ref)305 {306 struct my_data *entry = container_of(ref, struct my_data, refcount);307 308 mutex_lock(&mutex);309 list_del_rcu(&entry->link);310 mutex_unlock(&mutex);311 kfree_rcu(entry, rhead);312 }313 314 static void put_entry(struct my_data *entry)315 {316 kref_put(&entry->refcount, release_entry_rcu);317 }318 319But note that the struct kref member needs to remain in valid memory for a320rcu grace period after release_entry_rcu was called. That can be accomplished321by using kfree_rcu(entry, rhead) as done above, or by calling synchronize_rcu()322before using kfree, but note that synchronize_rcu() may sleep for a323substantial amount of time.324