Lines Matching full:trace

11  * Coresight trace ID allocation API
13  * With multi cpu systems, and more additional trace sources a scalable
14  * trace ID reservation system is required.
25  * Trace ID maps will be created and initialised to prevent architecturally
29  * different sets of cpus trace into different independent sinks.
50  * Trace ID map.
55  * @pend_rel_ids: CPU IDs that have been released by the trace source but not
64 /* Allocate and release IDs for a single default trace ID map */
67  * Read and optionally allocate a CoreSight trace ID and associate with a CPU.
69  * Function will read the current trace ID for the associated CPU,
77  * return: CoreSight trace ID or -EINVAL if allocation impossible.
82  * Release an allocated trace ID associated with the CPU.
84  * This will release the CoreSight trace ID associated with the CPU,
90  * @cpu: The CPU index to release the associated trace ID.
95  * Read the current allocated CoreSight Trace ID value for the CPU.
101  * be changing, when perf starts and event on a core and outputs the Trace ID
115  * Allocate a CoreSight trace ID for a system component.
117  * Unconditionally allocates a Trace ID, without associating the ID with a CPU.
119  * Used to allocate IDs for system trace sources such as STM.
121  * return: Trace ID or -EINVAL if allocation is impossible.
126  * Release an allocated system trace ID.
128  * Unconditionally release a trace ID allocated to a system component.
130  * @id: value of trace ID allocated.
137  * Notify the Trace ID allocator that a perf session is starting.
140  * a trace event.
142  * This reference count is used by the ID allocator to ensure that trace IDs
151  * if this causes the count to go to zero, then all Trace IDs marked as pending