wireguard-openbsd - WireGuard implementation for the OpenBSD kernel

Age	Commit message (Collapse)	Author	Files	Lines
2021-03-26	Initialize error variable in dtread().	bluhm	1	-2/+2
	OK mpi@
2021-02-08	Simplify sleep_setup API to two operations in preparation for splitting	mpi	1	-5/+3
	the SCHED_LOCK(). Putting a thread on a sleep queue is reduce to the following: sleep_setup(); /* check condition or release lock */ sleep_finish(); Previous version ok cheloha@, jmatthew@, ok claudio@
2021-01-06	Add dt(4) TRACEPOINTs for pool_get() and pool_put(), this is simmilar to the	claudio	1	-1/+5
	ones added to malloc() and free(). Pass the struct pool pointer as argv1 since it is currently not possible to pass the pool name to btrace. OK mpi@
2020-12-31	Add trace points for malloc(9) and free(9). This makes them traceable	claudio	1	-1/+5
	via dt(4) and btrace(8). OK mpi@ millert@
2020-09-28	Add defines for the number of frames to skip on powerpc64.	kettenis	1	-1/+4
	ok mpi@
2020-09-14	add three static probes for vfs: cleaner, bufcache_take and bufcache_rel.	jasper	1	-1/+12
	while here, swap two lines in bufcache_release() to put a KASSERT() first following the pattern in bufcache_take() ok beck@ mpi@
2020-09-13	unbreak dt-enabled builds; it seems an unrelated change snuck in in -r1.3	jasper	1	-3/+2
	also noticed by semarie@
2020-09-12	Add tracepoints in the page fault handler and when entries are added to maps.	mpi	1	-3/+15
	ok kettenis@
2020-08-13	Always set `dtpr_size' to the total size required to hold all probe entries.	mpi	1	-5/+4

2020-07-04	Do the same as libc, store "-1" in the return value when a syscall failed.	mpi	2	-6/+9
	Simplify the logic by always exporting the return value and errno in the syscall profiler.
2020-07-04	It's been agreed upon that global locks should be expressed using	anton	2	-21/+21
	capital letters in locking annotations. Therefore harmonize the existing annotations. Also, if multiple locks are required they should be delimited using commas. ok mpi@
2020-06-27	Replace TAILQ concatenation loop with TAILQ_CONCAT	bket	1	-6/+2
	As a result remove unneeded variable OK kn@, millert@
2020-06-26	Interprets profile/interval value as a frequency and not a number of ticks.	mpi	1	-3/+3
	Matches the behavior of other dynamic tracing tools. From Yuichiro NAITO.
2020-03-28	Export the number of arguments exposed by a probe to userland.	mpi	3	-5/+8
	Also make the syscall provider exports the number of syscall arguments. This will allow for stricter checks when parsing `argN' and future `args->name'. This is an ABI change, don't forget to keep btrace(8) and your kernel in sync.
2020-03-25	Introduce stacktrace_save_at() and make use of it in dt(4).	mpi	5	-28/+40
	This variant of stacktrace_save() takes an aditionnal argument to skip an arbitrary number of frame. This allows to skip recording frames used to execute the profiling code and produces outputs easier to understand. Inputs from and ok visa@
2020-02-04	Replace msleep(9) by sleep_setup/setup_signal/finish() dance.	mpi	1	-5/+6
	This handrolled cond_wait() dealing with signals prevents a lock ordering problem when executing probes inside the scheduler code. That means we stop relying on a mutex for synchronisation and instead rely on the sleep_* internals, currently the SCHED_LOCK(). From kettenis@
2020-01-27	Improve use of SMR in dt(4) by changing the time when smr_barrier()	visa	1	-34/+9
	is invoked. This enables threads to continue gathering events without interruption when another thread starts or stops recording. OK mpi@
2020-01-24	New `kern.allowdt' button must be set to open(2) /dev/dt.	mpi	1	-1/+5
	dt(4) exposes kernel internals, addresses and content of states to userland. As such its interface shouldn't be available without enabling it consciously. ok millert@, deraadt@
2020-01-21	Import dt(4) a driver and framework for Dynamic Profiling.	mpi	5	-0/+1520
	The design is fairly simple: events, in the form of descriptors on a ring, are being produced in any kernel context and being consumed by a userland process reading /dev/dt. Code and hooks are all guarded under '#if NDT > 0' so this commit shouldn't introduce any change as long as dt(4) is disable in GENERIC. ok kettenis@, visa@, jasper@, deraadt@