Lines Matching refs:per
552 BL31 initializes the per-CPU data framework, which provides a cache of
553 frequently accessed per-CPU data optimised for fast, concurrent manipulation
554 on different CPUs. This buffer includes pointers to per-CPU contexts, crash
949 uses per-CPU data this must either be initialized for all CPUs during this call,
976 Function ID is passed in W0 from the lower exception level (as per the
994 and the state of the SVE hint bit per the SMCCCv1.3. The framework finally sets
1188 A dedicated per-CPU crash stack is maintained by BL31 and this is retrieved via
1189 the per-CPU pointer cache. The implementation attempts to minimise the memory
1425 entry is stored in per-CPU data by ``init_cpu_ops()`` so that it can be quickly
1433 retrieves ``cpu_ops`` pointer member of per-CPU data, and from that, further
1510 The errata status reporting function will be called once per CPU type/errata
2145 It is a characteristic of Lamport's Bakery algorithm that the volatile per-CPU
2148 Depending upon the data cache line size, the per-CPU fields of the
2150 These per-CPU fields can be read and written during lock contention by multiple
2157 CPU0 updates its per-CPU field with data cache enabled. This write updates a
2159 CPU1 updates its per-CPU field of the ``bakery_lock_t`` structure with data cache
2189 The ``bakery_info_t`` represents a single per-CPU field of one lock and
2198 | `bakery_info_t`| <-- Lock_0 per-CPU field
2201 | `bakery_info_t`| <-- Lock_1 per-CPU field
2206 | `bakery_info_t`| <-- Lock_N per-CPU field
2214 | `bakery_info_t`| <-- Lock_0 per-CPU field
2217 | `bakery_info_t`| <-- Lock_1 per-CPU field
2222 | `bakery_info_t`| <-- Lock_N per-CPU field
2519 PMF timestamps are stored in a per-service timestamp region. On a
2521 in a per-CPU cache line aligned memory region.