Lines Matching defs:from
203 * Return non-zero if thread can migrate between "from" and "to"
207 pg_cmt_can_migrate(cpu_t *from, cpu_t *to)
209 if (from->cpu_physid->cpu_cacheid ==
326 * in the PG being promoted), and may be invoked from a context where one CPU's
799 * deconfiguring it from both lgroups and processor
824 * Remove the PG from the CPU's load balancing lineage
830 * group, and remove it's reference from it's siblings.
832 * our reference from a PG that we just eliminated.
850 * remove the CPU from all it's PGs (destroying any that become
860 * Deleting the CPU from the PG changes the CPU's
947 * Remove the PG from the bitset in the old partition
1071 * Remove the CPU from the CMT PGs active CPU group
1457 * from the CMT PG hierarchy.
1460 * in the PG being pruned), and may be invoked from a context where one CPU's
1494 * Find and eliminate the PG from the lineage.
1568 * Remove PG from it's group of siblings, if it's there.
1586 * Move PG's children from it's children set to it's parent's
1658 * Remove the PG from the CPU's group used for CMT
1704 * and the PG is of a grouping type who's definition is known to originate from
1706 * PG (and all other instances PG's sharing relationship type) from the CMT
1708 * be added. If the grouping definition doesn't originate from suspect
1733 * was unable to recover from (and set cmt_lineage_status along the way).
1861 * information is derived from buggy sources (for example, incorrect
1865 * groupings from the PG hierarchy, which means that we won't optimize
1883 * from the existing CMT PG hierarchy.
1928 * or we would have to prune out level derived from what we