Documentation/locking/hwspinlock.rst

12 For example, OMAP4 has dual Cortex-A9, dual Cortex-M3 and a C64x+ DSP,
14 is usually running Linux and the slave processors, the M3 and the DSP,
17 A generic hwspinlock framework allows platform-independent drivers to use
22 This is necessary, for example, for Inter-processor communications:
23 on OMAP4, cpu-intensive multimedia tasks are offloaded by the host to the
24 remote M3 and/or C64x+ slave processors (by an IPC subsystem called Syslink).
26 To achieve fast message-based communications, a minimal kernel support
35 A common hwspinlock interface makes it possible to have generic, platform-
67 Retrieve the global lock id for an OF phandle-based specific lock.
72 The function returns a lock id number on success, -EPROBE_DEFER if
82 Free a previously-assigned hwspinlock; returns 0 on success, or an
83 appropriate error code on failure (e.g. -EINVAL if the hwspinlock
94 (e.g. -EOPNOTSUPP if the bust operation is not defined for the specific
103 Lock a previously-assigned hwspinlock with a timeout limit (specified in
112 notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
119 Lock a previously-assigned hwspinlock with a timeout limit (specified in
127 notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
135 Lock a previously-assigned hwspinlock with a timeout limit (specified in
144 notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
152 Lock a previously-assigned hwspinlock with a timeout limit (specified in
157 or spinlock to avoid dead-lock, that will let user can do some time-consuming
161 notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
169 Lock a previously-assigned hwspinlock with a timeout limit (specified in
177 notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
186 Attempt to lock a previously-assigned hwspinlock, but immediately fail if
195 notably -EBUSY if the hwspinlock was already taken).
203 Attempt to lock a previously-assigned hwspinlock, but immediately fail if
211 notably -EBUSY if the hwspinlock was already taken).
219 Attempt to lock a previously-assigned hwspinlock, but immediately fail if
228 notably -EBUSY if the hwspinlock was already taken).
235 Attempt to lock a previously-assigned hwspinlock, but immediately fail if
239 or spinlock to avoid dead-lock, that will let user can do some time-consuming
243 notably -EBUSY if the hwspinlock was already taken).
250 Attempt to lock a previously-assigned hwspinlock, but immediately fail if
256 notably -EBUSY if the hwspinlock was already taken).
263 Unlock a previously-locked hwspinlock. Always succeed, and can be called
275 Unlock a previously-locked hwspinlock and enable local interrupts.
287 Unlock a previously-locked hwspinlock.
299 Unlock a previously-locked hwspinlock.
309 Unlock a previously-locked hwspinlock.
324 Returns the hwspinlock id number, or -EINVAL if hwlock is null.
373 		* assign a specific hwspinlock id - this should be called early
384 			return -EBUSY;
411 To be called from the underlying platform-specific implementation, in
422 To be called from the underlying vendor-specific implementation, in order
441 	* struct hwspinlock_device - a device which usually spans numerous hwspinlocks
443 	* @ops: platform-specific hwspinlock handlers
460 	* struct hwspinlock - this struct represents a single hwspinlock instance
463 	* @priv: private data, owned by the underlying platform-specific hwspinlock drv
488 The ->trylock() callback should make a single attempt to take the lock, and
491 The ->unlock() callback releases the lock. It always succeed, and it, too,
494 The ->relax() callback is optional. It is called by hwspinlock core while
496 a delay between two successive invocations of ->trylock(). It may **not** sleep.