On Mon, Oct 14, 2019 at 12:46:19PM -0700, Andi Kleen wrote: > > > We may need a COW operation for this (hopefully rare) case. > > > > so the jitted mmaps are inserted into the data file > > and processed during report where they can overload > > existing maps - thats detected before addition in: > > > > thread__insert_map > > map_groups__fixup_overlappings > > - which uses COW way -> map__clone(map, false); > > to create new map > > > > other fixups to maps are being done only for kernel maps, > > where we dont have a problem, because there's only one copy > > I assume the same is true for /tmp/perf-* processing? >
perf-*.map processing adds only symbol for dso, it does not touch maps, so we're fine dso__load -> dso__load_perf_map jirka
