Intel OpenBMC Linux kernel source tree (mirror) https://git.radix-linux.su/BMC/Intel-BMC/linux.git/atom?h=dev-5.2 2019-04-22T05:44:57+00:00 2019-04-22T05:44:57+00:00 Guo Ren ren_guo@c-sky.com 2019-03-01T00:50:36+00:00 urn:sha1:28bb030f93334495ddc64ade0bff18721bf7023d Support dynamic ftrace including dynamic graph tracer. Gcc-csky with -pg will produce call site in every function prologue and we can use these call site to hook trace function. gcc with -pg origin call site: push lr jbsr _mcount nop32 nop32 If the (callee - caller)'s offset is in range of bsr instruction, we'll modify code with: push lr bsr _mcount nop32 nop32 Else if the (callee - caller)'s offset is out of bsr instrunction, we'll modify code with: push lr movih r26, ... ori r26, ... jsr r26 (r26 is reserved for jsr link reg in csky abiv2 spec.) Signed-off-by: Guo Ren <ren_guo@c-sky.com> 2018-12-31T15:17:23+00:00 Guo Ren ren_guo@c-sky.com 2018-12-15T13:04:27+00:00 urn:sha1:d7950be145c84ca5094c52bc1ad1e7f1893d0f19 With csky-gcc -pg -mbacktrace, ftrace call graph supported. Signed-off-by: Guo Ren <ren_guo@c-sky.com> 2018-12-31T15:16:46+00:00 Guo Ren ren_guo@c-sky.com 2018-12-09T06:29:59+00:00 urn:sha1:230c77a5e92a29bf21e98ee35e22b0537f61c55b When gcc with -pg, it'll add _mcount stub in every function. We need implement the _mcount in kernel and ftrace depends on stackstrace. To do: call-graph, dynamic ftrace Signed-off-by: Guo Ren <ren_guo@c-sky.com>