wireguard-openbsd/sys/kern/subr_prof.c, branch jd/queueboosts WireGuard implementation for the OpenBSD kernel https://git.zx2c4.com/wireguard-openbsd/atom/sys/kern/subr_prof.c?h=jd%2Fqueueboosts 2016-09-04T09:22:28Z Introduce Dynamic Profiling, a ddb(4) based & gprof compatible kernel 2016-09-04T09:22:28Z mpi mpi@openbsd.org 2016-09-04T09:22:28Z urn:sha1:6950c8e205c43756d30d56ca678aa8205e9896fa profiling framework. Code patching is used to enable probes when entering functions. The probes will call a mcount()-like function to match the behavior of a GPROF kernel. Currently only available on amd64 and guarded under DDBPROF. Support for other archs will follow soon. A new sysctl knob, ddb.console, need to be set to 1 in securelevel 0 to be able to use this feature. Inputs and ok guenther@ remove stale lint annotations 2015-12-05T10:11:53Z tedu tedu@openbsd.org 2015-12-05T10:11:53Z urn:sha1:52dd740aa1a28091e4c82673a517619f381b2a58 Remove some includes include-what-you-use claims don't 2015-03-14T03:38:46Z jsg jsg@openbsd.org 2015-03-14T03:38:46Z urn:sha1:21dab745d772244ad59a415114e48be2888cfbc8 have any direct symbols used. Tested for indirect use by compiling amd64/i386/sparc64 kernels. ok tedu@ deraadt@ Fix profiling (GPROF) build. 2014-08-30T08:48:23Z mpi mpi@openbsd.org 2014-08-30T08:48:23Z urn:sha1:ba54b0bb2c5c2c6e03b53dac7f0be7cf9bc8f05d decouple struct uvmexp into a new file, so that uvm_extern.h and sysctl.h 2014-07-08T17:19:21Z deraadt deraadt@openbsd.org 2014-07-08T17:19:21Z urn:sha1:e6c6495d62998a12dd778aed8d40dc250167a61c don't need to be married. ok guenther miod beck jsing kettenis do not include machine/cpu.h from a .c file; it is the responsibility of 2013-03-28T16:55:25Z deraadt deraadt@openbsd.org 2013-03-28T16:55:25Z urn:sha1:2f3604859555061972cebc45aec406747df860c1 .h files to pull it in, if needed ok tedu Fix kernel profiling on MP systems by using per-CPU buffers and teach 2013-03-12T09:37:16Z mpi mpi@openbsd.org 2013-03-12T09:37:16Z urn:sha1:6377c2eaf8ad0c2174b64c6ffe780441bba1d2d3 kgmon(8) to deal with them, this time without public header changes. Previously various CPUs were iterating over the same global buffer at the same time to modify it and never ended. This diff includes some ideas submited by Thor Simon to NetBSD via miod@. ok deraadt@, mikeb@, haesbaert@ Back out per-CPU kernel profiling, it shouldn't modify a public header 2013-02-12T08:06:22Z mpi mpi@openbsd.org 2013-02-12T08:06:22Z urn:sha1:0f28845859d090da9ecb82dee27886e2614e132f at this moment. Fix kernel profiling on MP systems by using per-CPU buffer. Previously 2013-02-11T17:05:25Z mpi mpi@openbsd.org 2013-02-11T17:05:25Z urn:sha1:fea2fea8dbf45c041f0e1660772024377fc193ba various CPUs were iterating over the same global buffer at the same time to modify it and never ended. This diff includes some ideas submited by Thor Simon to NetBSD via miod@. ok mikeb@, haesbaert@ Apply profiling to all threads instead of just the thread that called 2012-08-02T03:18:48Z guenther guenther@openbsd.org 2012-08-02T03:18:48Z urn:sha1:18914fdf6bf023a7446c7d0d18ef21f99bafd895 profil() by moving P_PROFIL from proc->p_flag to process->ps_flags with matching adjustment in fork1() and exit1() ok matthew@