NAME

     rmlock, rm_init, rm_init_flags, rm_destroy, rm_rlock, rm_try_rlock, rm_wlock, rm_runlock,
     rm_wunlock, rm_wowned, RM_SYSINIT — kernel reader/writer lock optimized for mostly read
     access patterns

SYNOPSIS

     #include <sys/param.h>
     #include <sys/lock.h>
     #include <sys/rmlock.h>

     void
     rm_init(struct rmlock *rm, const char *name);

     void
     rm_init_flags(struct rmlock *rm, const char *name, int opts);

     void
     rm_destroy(struct rmlock *rm);

     void
     rm_rlock(struct rmlock *rm, struct rm_priotracker* tracker);

     int
     rm_try_rlock(struct rmlock *rm, struct rm_priotracker* tracker);

     void
     rm_wlock(struct rmlock *rm);

     void
     rm_runlock(struct rmlock *rm, struct rm_priotracker* tracker);

     void
     rm_wunlock(struct rmlock *rm);

     int
     rm_wowned(struct rmlock *rm);

     #include <sys/kernel.h>

     RM_SYSINIT(name, struct rmlock *rm, const char *desc, int opts);

DESCRIPTION

     Mostly reader locks allow shared access to protected data by multiple threads, or exclusive
     access by a single thread.  The threads with shared access are known as readers since they
     only read the protected data.  A thread with exclusive access is known as a writer since it
     can modify protected data.

     Read mostly locks are designed to be efficient for locks almost exclusively used as reader
     locks and as such should be used for protecting data that rarely changes.  Acquiring an
     exclusive lock after the lock had been locked for shared access is an expensive operation.

     Although reader/writer locks look very similar to sx(9) locks, their usage pattern is
     different.  Reader/writer locks can be treated as mutexes (see mutex(9)) with
     shared/exclusive semantics unless initialized with RM_SLEEPABLE.  Unlike sx(9), an rmlock
     can be locked while holding a non-spin mutex, and an rmlock cannot be held while sleeping,
     again unless initialized with RM_SLEEPABLE.  The rmlock locks have full priority propagation
     like mutexes.  The rm_priotracker structure argument supplied in rm_rlock() and rm_runlock()
     is used to keep track of the read owner(s).  Another important property is that shared
     holders of rmlock can recurse if the lock has been initialized with the LO_RECURSABLE
     option, however exclusive locks are not allowed to recurse.

   Macros and Functions
     rm_init(struct rmlock *rm, const char *name)
             Initialize structure located at rm as mostly reader lock, described by name.  The
             name description is used solely for debugging purposes.  This function must be
             called before any other operations on the lock.

     rm_init_flags(struct rmlock *rm, const char *name, int opts)
             Initialize the rm lock just like the rm_init() function, but specifying a set of
             optional flags to alter the behaviour of rm, through the opts argument.  It contains
             one or more of the following flags:

             RM_NOWITNESS  Instruct witness(4) to ignore this lock.

             RM_RECURSE    Allow threads to recursively acquire exclusive locks for rm.

             RM_SLEEPABLE  Allow writers to sleep while holding the lock.  Readers must not sleep
                           while holding the lock and can avoid to sleep on taking the lock by
                           using rm_try_rlock() instead of rm_rlock().

     rm_rlock(struct rmlock *rm, struct rm_priotracker* tracker)
             Lock rm as a reader.  Using tracker to track read owners of a lock for priority
             propagation.  This data structure is only used internally by rmlock and must persist
             until rm_runlock() has been called.  This data structure can be allocated on the
             stack since rmlocks cannot be held while sleeping.  If any thread holds this lock
             exclusively, the current thread blocks, and its priority is propagated to the
             exclusive holder.  If the lock was initialized with the LO_RECURSABLE option the
             rm_rlock() function can be called when the thread has already acquired reader access
             on rm.  This is called “recursing on a lock”.

     rm_try_rlock(struct rmlock *rm, struct rm_priotracker* tracker)
             Try to lock rm as a reader.  rm_try_rlock() will return 0 if the lock cannot be
             acquired immediately; otherwise the lock will be acquired and a non-zero value will
             be returned.  Note that rm_try_rlock() may fail even while the lock is not currently
             held by a writer.

     rm_wlock(struct rmlock *rm)
             Lock rm as a writer.  If there are any shared owners of the lock, the current thread
             blocks.  The rm_wlock() function cannot be called recursively.

     rm_runlock(struct rmlock *rm, struct rm_priotracker* tracker)
             This function releases a shared lock previously acquired by rm_rlock().  The tracker
             argument must match the tracker argument used for acquiring the shared lock

     rm_wunlock(struct rmlock *rm)
             This function releases an exclusive lock previously acquired by rm_wlock().

     rm_destroy(struct rmlock *rm)
             This functions destroys a lock previously initialized with rm_init().  The rm lock
             must be unlocked.

     rm_wowned(struct rmlock *rm)
             This function returns a non-zero value if the current thread owns an exclusive lock
             on rm.

SEE ALSO

     locking(9), mutex(9), panic(9), rwlock(9), sema(9), sx(9)

HISTORY

     These functions appeared in FreeBSD 7.0.

AUTHORS

     The rmlock facility was written by Stephan Uphoff.  This manual page was written by Gleb
     Smirnoff for rwlock and modified to reflect rmlock by Stephan Uphoff.

BUGS

     The rmlock implementation is currently not optimized for single processor systems.

     rm_try_rlock() can fail transiently even when there is no writer, while another reader
     updates the state on the local CPU.

     The rmlock implementation uses a single per CPU list shared by all rmlocks in the system.
     If rmlocks become popular, hashing to multiple per CPU queues may be needed to speed up the
     writer lock process.

     The rmlock can currently not be used as a lock argument for condition variable wait
     functions.