Lines Matching +full:per +full:- +full:cpu

1 /* SPDX-License-Identifier: GPL-2.0 */
15  * The per-thread accumulated period storage node.
27  * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the
34 	list_for_each_entry_safe(item, tmp, &(evsel)->per_stream_periods, node)
41  * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
51 	* queues for each CPU (per-cpu tracing) or task (per-thread tracing).
56 	struct perf_cpu		 cpu;  member
59 	/* Guest machine pid and VCPU, valid only if machine_pid is non-zero */
64 	 * Per-thread, and global event counts are mutually exclusive:
68 	 * situation where a per-thread event is sampled as a global event;
70 	 * event is inherit + PERF_SAMPLE_READ will be per-thread. Any event
72 	 * will be read as per-thread. If such an event can also trigger a
75 	 * therefore will not expose the per-thread group members as global.
80 		 * (when period is not per-thread).
85 		 * (when period is per-thread).
94 	/** The commonly used cpu map of CPUs the event should be opened upon, etc. */
97 	 * The cpu map read from the PMU. For core PMUs this is the list of all
99 	 * cpu map for opening the event on, for example, the first CPU on a
111 	/* For events where the read_format value is per-thread rather than
112 	 * global, stores the per-thread cumulative period */
118 	 * system_wide is for events that need to be on every CPU, irrespective
121 	 * as software PMU events like dummy, have a CPU map that is empty.
125 	 * Some events, for example uncore events, require a CPU.
126 	 * i.e. it cannot be the 'any CPU' value of -1.