Lines Matching full:ipi

12  * A) Userspace thread execution after IPI vs membarrier's memory
13  *    barrier before sending the IPI
22  * CPU1 after the IPI-induced memory barrier:
29  *           b: send IPI                       IPI-induced mb
46  * before the IPI-induced memory barrier on CPU1.
48  * B) Userspace thread execution before IPI vs membarrier's memory
49  *    barrier after completing the IPI
68  *           b: send IPI                       IPI-induced mb
80  * after the IPI-induced memory barrier on CPU1.
177 	 * ensure that memory on remote CPUs that occur before the IPI  in ipi_sync_core()
196 	 * time we've already sent an IPI, the cost of the extra smp_mb()  in ipi_rseq()
307 	 * waiting for the last IPI. Matches memory barriers before  in membarrier_global_expedited()
428 	 * waiting for the last IPI. Matches memory barriers before  in membarrier_private_expedited()