Lines Matching +full:wait +full:- +full:on +full:- +full:write

1 .\"-
21 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
31 .Nd "SMP-friendly kernel counter implementation"
37 .Fn counter_u64_alloc "int wait"
76 can be used in any non-interrupt context.
81 update faster than simple arithmetic on the global variable.
84 is considered suitable for accounting in the performance-critical
86 .Bl -tag -width indent
87 .It Fn counter_u64_alloc wait
88 Allocate a new 64-bit unsigned counter.
90 .Fa wait
93 wait flag, should be either
117 section, while on other is a nop.
137 The function is a multiprocessor-friendly version of
142 Returns non-negative value if the rate is not yet reached during the current
144 If the limit was reached on previous second, but was just reset back to zero,
173 Any write to the oid zeroes it.
185 Any write to the oid zeroes it.
198 A read of the oid returns len-sized array of
202 Any write to the oid zeroes all array elements.
215 A read of the oid returns len-sized array of
219 Any write to the oid zeroes all array elements.
224 is implemented using per-CPU data fields that are specially aligned
225 in memory, to avoid inter-CPU bus traffic due to shared use
232 Fetch operation loops through all per-CPU fields and obtains a snapshot
238 operating on the private data for the current CPU,
243 The multi-instruction sequence provides the same guarantees as the
244 amd64 single-instruction implementation.
252 .Bd -literal -offset indent
273 .An -nosplit