Commit Graph

52 Commits

Author SHA1 Message Date
Justin Hibbits
c757049235 Implement DTrace for PowerPC. This includes both 32-bit and 64-bit.
There is one known issue:  Some probes will display an error message along the
lines of:  "Invalid address (0)"

I tested this with both a simple dtrace probe and dtruss on a few different
binaries on 32-bit.  I only compiled 64-bit, did not run it, but I don't expect
problems without the modules loaded.  Volunteers are welcome.

MFC after:	1 month
2012-11-07 23:45:09 +00:00
George V. Neville-Neil
d638e8dcde Change UL to ULL since time is 32 bits.
Pointed out by: avg@
MFC after:	2 weeks
2012-07-17 14:36:40 +00:00
George V. Neville-Neil
57d025c338 Add support for walltimestamp in DTrace.
Submitted by:	Fabian Keil
MFC after:	2 weeks
2012-07-16 20:17:19 +00:00
Andriy Gapon
e0bc3c3d99 r237748 continuation: fix nopw (0f 1f) behavior with respect to modifiers
To do: proper merge with Illumos vendor area.

Reported by:	emaste
Tested by:	emaste
Obtained from:	Illumos commit 13442:4adbe6de60c8
MFC after:	5 days
2012-07-06 14:45:30 +00:00
Andriy Gapon
7e18e35b14 r237748 continuation: segment-override prefixes are not invalid in long mode
Update DTrace disassembler accordingly.  The code to treat the prefixes
as null prefixes was already in place.
Although in practice compilers seem to generate only cs-prefix for use
in long NOPs, the same treatment is applied to all of cs, ds, es, ss for
consistency.

Reported by:	emaste
Tested by:	emaste
Obtained from:	Illumos commit 13442:4adbe6de60c8 (+ local changes)
MFC after:	5 days
2012-07-06 14:41:02 +00:00
Andriy Gapon
f724c6a137 dtrace instruction decoder: add 0x0f 0x1f NOP opcode support
According to the AMD manual the whole range from 0x09 to 0x1f are NOPs.
Intel manual mentions only 0x1f.  Use only Intel one for now, it seems
to be the one actually generated by compilers.
Use gdb mnemonic for the operation: "nopw".

[1] AMD64 Architecture Programmer's Manual
    Volume 3: General-Purpose and System Instructions
[2] Software Optimization Guide for AMD Family 10h Processors
[3] Intel(R) 64 and IA-32 Architectures Software Developer’s Manual
    Volume 2 (2A, 2B & 2C): Instruction Set Reference, A-Z

Tested by:	Fabian Keil <freebsd-listen@fabiankeil.de> (earlier version)
MFC after:	3 days
2012-06-29 07:35:37 +00:00
George V. Neville-Neil
4737d389b0 Integrate a fix for a very odd signal delivery problem found
by Bryan Cantril and others in the Solaris/Illumos version of DTrace.

Obtained from: https://www.illumos.org/issues/789
MFC after:	2 weeks
2012-06-04 16:15:40 +00:00
Zachary Loafman
db5c7d363d Fix DTrace TSC skew calculation:
The skew calculation here is exactly backwards. We were able to repro
it on a multi-package ESX server running a FreeBSD VM, where the TSCs
can be pretty evil.

MFC after: 1 week

Submitted by: Jeff Ford <jeffrey.ford2@isilon.com>
Reviewed by: avg, gnn
2012-06-04 16:04:01 +00:00
Ryan Stone
9742410797 Instead of only iterating over the set of known SDT probes when sdt.ko is
loaded and unloaded, also have sdt.ko register callbacks with kern_sdt.c
that will be called when a newly loaded KLD module adds more probes or
a module with probes is unloaded.

This fixes two issues: first, if a module with SDT probes was loaded after
sdt.ko was loaded, those new probes would not be available in DTrace.
Second, if a module with SDT probes was unloaded while sdt.ko was loaded,
the kernel would panic the next time DTrace had cause to try and do
anything with the no-longer-existent probes.

This makes it possible to create SDT probes in KLD modules, although there
are still two caveats: first, any SDT probes in a KLD module must be part
of a DTrace provider that is defined in that module.  At present DTrace
only destroys probes when the provider is destroyed, so you can still
panic the system if a KLD module creates new probes in a provider from a
different module(including the kernel) and then unload the the first module.

Second, the system will panic if you unload a module containing SDT probes
while there is an active D script that has enabled those probes.

MFC after:	1 month
2012-03-27 15:07:43 +00:00
Oleksandr Tymoshenko
683822338e - For o32 ABI get arguments from the stack
- Clear CPU_DTRACE_FAULT flag in userland backtrace routine. It just
   means we hit wrong memory region and should stop.
2012-03-26 21:47:06 +00:00
Oleksandr Tymoshenko
933fab9d73 Properly cast 64-bit dofhp_dof to pointer.
For i386 this change is no-op. For AMD64 it was tested with DTrace test
suite: results are the same from the test run before the change and after
2012-03-26 21:22:51 +00:00
Oleksandr Tymoshenko
4d18d83736 Use macroses to load/store pointers and increase indexes instead of
hardcoded MIPS64 instructions
2012-03-26 01:26:33 +00:00
Oleksandr Tymoshenko
c57e9d4e83 Add device part of DTrace/MIPS code 2012-03-24 05:14:37 +00:00
Ryan Stone
493b584dbd Correct the types of the arguments to return probes of the syscall
provider.  Previously we were erroneously supplying the argument types of
the corresponding entry probe.

Reviewed by:	rpaulo
MFC after:	1 week
2011-11-11 03:49:42 +00:00
Ryan Stone
cddcb8b4dc On i386, fbt probes are implemented by writing an invalid opcode over
certain instructions in a function prologue or epilogue.  DTrace has a
hook into the invalid opcode fault handler that checks whether the fault
was due to an probe and if so, runs the DTrace magic.

Upon returning from an invalid opcode fault caused by a probe, DTrace must
emulate the instruction that was replaced with the invalid opcode and then
return control to the instruction following the invalid opcode.

There were a pair of related bugs in the emulation for the leave
instruction.  The leave instruction is used to pop off a stack frame prior
to returning from a function.  The emulation for this instruction must
move the trap frame for the invalid opcode fault down the stack to the
bottom of the stack frame that is being removed, and then execute an iret.

At two points in this process, the emulation code was storing values above
the current value of the stack pointer.  This opened up a window in which
if we were two take an interrupt, the trap frame for the interrupt would
overwrite the values stored on the stack, causing the system to panic
later.

The first bug was that at one point the emulation code saves the new value
for $esp above the current stack pointer value.  The fix is to save this
value instead inside of the original trap frame.  At this point we do
not need the original trap frame so this is safe.

The second bug is that when the emulate code loads $esp from the stack, it
points part-way through the new trap frame instead of at its beginning.
The emulation code adjusts the stack pointer to the correct value
immediately afterwards, but this still leaves a one instruction window in
which an interrupt would corrupt this trap frame.  Fix this by adjusting
the stack frame value before loading it into $esp.

This fixes panics in invop_leave on i386 when using fbt return probes.

Reviewed by:	rpaulo, attilio
MFC after:	1 week
2011-11-10 22:03:35 +00:00
Ed Schouten
d745c852be Mark MALLOC_DEFINEs static that have no corresponding MALLOC_DECLAREs.
This means that their use is restricted to a single C file.
2011-11-07 06:44:47 +00:00
Marcel Moolenaar
ad4e66a63c Define dtrace_cmpset_long in terms of atomic_cmpset_long
and not by virtue of inline assembly. Now this file
compiles on all supported architectures.
2011-10-16 22:18:08 +00:00
Attilio Rao
ada5b73915 Remove pc_cpumask usage from dtrace MD support 2011-06-28 13:14:39 +00:00
Attilio Rao
7e7a34e520 MFC 2011-05-16 16:34:03 +00:00
Andriy Gapon
dd7498ae03 better integrate cyclic module with clocksource/eventtimer subsystem
Now in the case when one-shot timers are used cyclic events should fire
closer to theier scheduled times.  As the cyclic is currently used only
to drive DTrace profile provider, this is the area where the change
makes a difference.

Reviewed by:	mav (earlier version, a while ago)
X-MFC after:	clocksource/eventtimer subsystem
2011-05-16 15:29:59 +00:00
Attilio Rao
b68eda3b54 MFC 2011-05-10 15:54:37 +00:00
Andriy Gapon
d9b8935fb9 dtrace: remove unused code
Which is also useless, IMO.

MFC after:	5 days
2011-05-10 15:05:27 +00:00
Attilio Rao
71a19bdc64 Commit the support for removing cpumask_t and replacing it directly with
cpuset_t objects.
That is going to offer the underlying support for a simple bump of
MAXCPU and then support for number of cpus > 32 (as it is today).

Right now, cpumask_t is an int, 32 bits on all our supported architecture.
cpumask_t on the other side is implemented as an array of longs, and
easilly extendible by definition.

The architectures touched by this commit are the following:
- amd64
- i386
- pc98
- arm
- ia64
- XEN

while the others are still missing.
Userland is believed to be fully converted with the changes contained
here.

Some technical notes:
- This commit may be considered an ABI nop for all the architectures
  different from amd64 and ia64 (and sparc64 in the future)
- per-cpu members, which are now converted to cpuset_t, needs to be
  accessed avoiding migration, because the size of cpuset_t should be
  considered unknown
- size of cpuset_t objects is different from kernel and userland (this is
  primirally done in order to leave some more space in userland to cope
  with KBI extensions). If you need to access kernel cpuset_t from the
  userland please refer to example in this patch on how to do that
  correctly (kgdb may be a good source, for example).
- Support for other architectures is going to be added soon
- Only MAXCPU for amd64 is bumped now

The patch has been tested by sbruno and Nicholas Esborn on opteron
4 x 12 pack CPUs. More testing on big SMP is expected to came soon.
pluknet tested the patch with his 8-ways on both amd64 and i386.

Tested by:	pluknet, sbruno, gianni, Nicholas Esborn
Reviewed by:	jeff, jhb, sbruno
2011-05-05 14:39:14 +00:00
Artem Belevich
7a3f3cabb1 Stripped '32' suffix from linux systrace module name on i386.
Approved by: avg
2011-04-08 06:27:43 +00:00
Jung-uk Kim
3453537fa5 Use atomic load & store for TSC frequency. It may be overkill for amd64 but
safer for i386 because it can be easily over 4 GHz now.  More worse, it can
be easily changed by user with 'machdep.tsc_freq' tunable (directly) or
cpufreq(4) (indirectly).  Note it is intentionally not used in performance
critical paths to avoid performance regression (but we should, in theory).
Alternatively, we may add "virtual TSC" with lower frequency if maximum
frequency overflows 32 bits (and ignore possible incoherency as we do now).
2011-04-07 23:28:28 +00:00
Andriy Gapon
308bce2a0e add DTrace systrace support for linux32 and freebsd32 on amd64 syscalls
Add systrace_linux32 and systrace_freebsd32 modules which provide
support for tracing compat system calls in addition to native system
call tracing provided by systrace module.

Provided that all the systrace modules are loaded now you can select
what syscalls to trace in the following manner:

syscall::xxx:yyy - work on all system calls that match the specification
syscall:freebsd:xxx:yyy - only native system calls
syscall:linux32:xxx:yyy - linux32 compat system calls
syscall:freebsd32:xxx:yyy - freebsd32 compat system calls on amd64

PR:		kern/152822
Submitted by:	Artem Belevich <fbsdlist@src.cx>
Reviewed by:	jhb (earlier version)
MFC after:	3 weeks
2011-03-12 09:09:25 +00:00
Rebecca Cran
6bccea7c2b Fix typos - remove duplicate "the".
PR:	bin/154928
Submitted by:	Eitan Adler <lists at eitanadler.com>
MFC after: 	3 days
2011-02-21 09:01:34 +00:00
Andriy Gapon
dfe3a1b374 cyclic xcall: use smp_no_rendevous_barrier as setup function parameter
In this case we call target function only on a single CPU and do not
need any synchronization at the setup stage.

It's a bit non-obvious but setup function of NULL means that
smp_rendezvous_cpus waits for all CPUs to arrive at the rendezvous
point, but without doing any actual setup.  While using
smp_no_rendevous_barrier means that each CPU proceeds on its own
schedule without any synchronization whatsoever.

MFC after:	3 weeks
2010-12-17 18:22:50 +00:00
Andriy Gapon
58f61ce4eb opensolaris cyclic: fix deadlock and make a little bit closer to upstream
The dealock was caused in the following way:
- thread T1 on CPU C1 holds a spin mutex, IPIs CPU C2 and waits for the
  IPI to be handled
- C2 executes timer interrupt filter, thus has interrupts disabled, and
  gets blocked on the spin mutex held by T1
The problem seems to have been introduced by simplifications made to
OpenSolaris code during porting.
The problem is fixed by reorganizing the code to more closely resemble
the upstream version.  Interrupt filter (cyclic_fire) now doesn't
acquire any locks, all per-CPU data accesses are performed on a
target CPU with preemption and interrupts disabled thus precluding
concurrent access to the data.
cyp_mtx spin mutex is used to disable preemtion and interrupts; it's not
used for classical mutual exclusion, because xcall already serializes
calls to a CPU.  It's an emulation of OpenSolaris
cyb_set_level(CY_HIGH_LEVEL) call, the spin mutexes could probably be
reduced to just a spinlock_enter()/_exit() pair.

Diff with upstream version is now reduced by ~500 lines, however it still
remains quite large - many things that are not needed (at the moment) or
are irrelevant on FreeBSD were simply ripped out during porting.
Examples of such things:
- support for CPU onlining/offlining
- support for suspend/resume
- support for running callouts at soft interrupt levels
- support for callout rebinding from CPU to CPU
- support for CPU partitions

Tested by:	Artem Belevich <fbsdlist@src.cx>
MFC after:	3 weeks
X-MFC with:	r216252
2010-12-07 12:25:26 +00:00
Andriy Gapon
a10b0e67d9 opensolaris cyclic xcall: no need for special handling of curcpu
smp_rendezvous_cpus already properly handles current CPU case
and non-SMP case.

MFC after:	3 weeks
2010-12-07 12:04:06 +00:00
Andriy Gapon
fe8c7b3d77 dtrace_xcall: no need for special handling of curcpu
smp_rendezvous_cpus alreadt does the right thing in a very similar
fashion, so the code was kind of duplicating that.

MFC after:	3 weeks
2010-12-07 09:19:47 +00:00
Andriy Gapon
7becfa95b9 dtrace_gethrtime_init: pin to master while examining other CPUs
Also use pc_cpumask to be future-friendly.

Reviewed by:	jhb
MFC after:	2 weeks
2010-12-07 09:03:17 +00:00
Rui Paulo
ea950d20f6 Make the /dev/dtrace/helper node have the mode 0660. This allows
programs that refuse to run as root (pgsql) to install probes when their
user is part of the wheel group.

Sponsored by:	The FreeBSD Foundation
2010-09-01 12:08:32 +00:00
Rui Paulo
de788cde7b Destroy the helper device when unloading.
Sponsored by:	The FreeBSD Foundation
2010-08-22 11:05:37 +00:00
Rui Paulo
6c44520886 Add more compatibility structure members needed by the upcoming fasttrap
DTrace device.

Sponsored by:	The FreeBSD Foundation
2010-08-22 11:04:43 +00:00
Rui Paulo
c6f5742f90 Kernel DTrace support for:
o uregs  (sson@)
o ustack (sson@)
o /dev/dtrace/helper device (needed for USDT probes)

The work done by me was:
Sponsored by:	The FreeBSD Foundation
2010-08-22 10:53:32 +00:00
Rui Paulo
58f668bba5 Add a function compatibility function dtrace_instr_size_isa() that on
FreeBSD does the same as dtrace_dis_isize().

Sponsored by:	The FreeBSD Foundation
2010-08-22 10:40:15 +00:00
John Baldwin
3aa6d94e0c Update several places that iterate over CPUs to use CPU_FOREACH(). 2010-06-11 18:46:34 +00:00
Konstantin Belousov
afe1a68827 Reorganize syscall entry and leave handling.
Extend struct sysvec with three new elements:
sv_fetch_syscall_args - the method to fetch syscall arguments from
  usermode into struct syscall_args. The structure is machine-depended
  (this might be reconsidered after all architectures are converted).
sv_set_syscall_retval - the method to set a return value for usermode
  from the syscall. It is a generalization of
  cpu_set_syscall_retval(9) to allow ABIs to override the way to set a
  return value.
sv_syscallnames - the table of syscall names.

Use sv_set_syscall_retval in kern_sigsuspend() instead of hardcoding
the call to cpu_set_syscall_retval().

The new functions syscallenter(9) and syscallret(9) are provided that
use sv_*syscall* pointers and contain the common repeated code from
the syscall() implementations for the architecture-specific syscall
trap handlers.

Syscallenter() fetches arguments, calls syscall implementation from
ABI sysent table, and set up return frame. The end of syscall
bookkeeping is done by syscallret().

Take advantage of single place for MI syscall handling code and
implement ptrace_lwpinfo pl_flags PL_FLAG_SCE, PL_FLAG_SCX and
PL_FLAG_EXEC. The SCE and SCX flags notify the debugger that the
thread is stopped at syscall entry or return point respectively.  The
EXEC flag augments SCX and notifies debugger that the process address
space was changed by one of exec(2)-family syscalls.

The i386, amd64, sparc64, sun4v, powerpc and ia64 syscall()s are
changed to use syscallenter()/syscallret(). MIPS and arm are not
converted and use the mostly unchanged syscall() implementation.

Reviewed by:	jhb, marcel, marius, nwhitehorn, stas
Tested by:	marcel (ia64), marius (sparc64), nwhitehorn (powerpc),
	stas (mips)
MFC after:	1 month
2010-05-23 18:32:02 +00:00
Rui Paulo
ff569d8436 Rename the cyclic global variable lapic_cyclic_clock_func to just
cyclic_clock_func. This will make more sense when we start developing non
x86 cyclic version.
2010-04-20 17:03:30 +00:00
Rui Paulo
b527a2a4dc The amd64 version of the cyclic dtrace module is a verbatim copy of the
i386 version, so instead having a copy of the same file, use Makefile
foo to include the i386 version on amd64.
2010-04-20 16:30:17 +00:00
Andriy Gapon
b064b6d1cd dtrace_gethrtime: improve scaling of TSC ticks to nanoseconds
Currently dtrace_gethrtime uses formula similar to the following for
converting TSC ticks to nanoseconds:
rdtsc() * 10^9 / tsc_freq
The dividend overflows 64-bit type and wraps-around every 2^64/10^9 =
18446744073 ticks which is just a few seconds on modern machines.

Now we instead use precalculated scaling factor of
10^9*2^N/tsc_freq < 2^32 and perform TSC value multiplication separately
for each 32-bit half.  This allows to avoid overflow of the dividend
described above.
The idea is taken from OpenSolaris.
This has an added feature of always scaling TSC with invariant value
regardless of TSC frequency changes. Thus the timestamps will not be
accurate if TSC actually changes, but they are always proportional to
TSC ticks and thus monotonic. This should be much better than current
formula which produces wildly different non-monotonic results on when
tsc_freq changes.

Also drop write-only 'cp' variable from amd64 dtrace_gethrtime_init()
to make it identical to the i386 twin.

PR:		kern/127441
Tested by:	Thomas Backman <serenity@exscape.org>
Reviewed by:	jhb
Discussed with:	current@, bde, gnn
Silence from:	jb
Approved by:	re (gnn)
MFC after:	1 week
2009-07-15 17:07:39 +00:00
Andriy Gapon
f340e9fe71 dtrace/amd64: fix virtual address checks
On amd64 KERNBASE/kernbase does not mean start of kernel memory.
This should fix a KASSERT panic in dtrace_copycheck when copyin*()
is used in D program.
Also make checks for user memory a bit stricter.

Reported by:	Thomas Backman <serenity@exscape.org>
Submitted by:	wxs (kaddr part)
Tested by:	Thomas Backman (prototype), wxs
Reviewed by:	alc (concept), jhb, current@
Aprroved by:	jb (concept)
MFC after:	2 weeks
PR:		kern/134408
2009-06-24 16:03:57 +00:00
Stacey Son
a5aedd68b4 Add the OpenSolaris dtrace lockstat provider. The lockstat provider
adds probes for mutexes, reader/writer and shared/exclusive locks to
gather contention statistics and other locking information for
dtrace scripts, the lockstat(1M) command and other potential
consumers.

Reviewed by:	attilio jhb jb
Approved by:	gnn (mentor)
2009-05-26 20:28:22 +00:00
Robert Watson
455f3aa24f Move dtnfsclient.c in the cddl tree to nfs_kdtrace.c in the nfsclient
directory, since it's under a BSD license, and this keeps NFS internals-
aware tracing parts close to NFS.

MFC after:	1 month
Suggested by:	jhb
2009-03-25 17:47:22 +00:00
Robert Watson
10263f0832 Add DTrace probes to the NFS access and attribute caches. Access cache
events are:

  nfsclient:accesscache:flush:done
  nfsclient:accesscache:get:hit
  nfsclient:accesscache:get:miss
  nfsclient:accesscache:load:done

They pass the vnode, uid, and requested or loaded access mode (if any);
the load event may also report a load error if the RPC fails.

The attribute cache events are:

  nfsclient:attrcache:flush:done
  nfsclient:attrcache:get:hit
  nfsclient:attrcache:get:miss
  nfsclient:attrcache:load:done

They pass the vnode, optionally the vattr if one is present (hit or load),
and in the case of a load event, also a possible RPC error.

MFC after:	1 month
Sponsored by:	Google, Inc.
2009-03-24 17:14:34 +00:00
Robert Watson
47294818f9 Add dtnfsclient, a first cut at an NFSv2/v3 client reuest DTrace
provider.  The NFS client exposes 'start' and 'done' probes for NFSv2
and NFSv3 RPCs when using the new RPC implementation, passing in the
vnode, mbuf chain, credential, and NFSv2 or NFSv3 procedure number.
For 'done' probes, the error number is also available.

Probes are named in the following way:

  ...
  nfsclient:nfs2:write:start
  nfsclient:nfs2:write:done
  ...
  nfsclient:nfs3:access:start
  nfsclient:nfs3:access:done
  ...

Access to the unmarshalled arguments is not easily available at this
point in the stack, but the passed probe arguments are sufficient to
to a lot of interesting things in practice.  Technically, these probes
may cover multiple RPC retransmits, and even transactions if the
transaction ID change as a result of authentication failure or a
jukebox error from the server, but usefully capture the intent of a
single NFS request, such as access, getattr, write, etc.

Typical use might involve profiling RPC latency by system call, number
of RPCs, how often a getattr leads to a call to access, when failed
access control checks occur, etc.  More detailed RPC information might
best be provided by adding a krpc provider.  It would also be useful
to add NFS client probes for events such as the access cache or
attribute cache satisfying requests without an RPC.

Sponsored by:	Google, Inc.
MFC after:	1 month
2009-03-22 22:07:52 +00:00
Ganbold Tsagaankhuu
79dae0aa0b Remove unused variable.
Found with:     Coverity Prevent(tm)
CID: 3669,3671

Approved by: jb
2008-11-25 19:25:54 +00:00
Craig Rodrigues
f5a97d1bcb Merge latest DTrace changes from Perforce. 2008-11-05 19:39:11 +00:00
Ed Schouten
d3ce832719 Remove unit2minor() use from kernel code.
When I changed kern_conf.c three months ago I made device unit numbers
equal to (unneeded) device minor numbers. We used to require
bitshifting, because there were eight bits in the middle that were
reserved for a device major number. Not very long after I turned
dev2unit(), minor(), unit2minor() and minor2unit() into macro's.
The unit2minor() and minor2unit() macro's were no-ops.

We'd better not remove these four macro's from the kernel, because there
is a lot of (external) code that may still depend on them. For now it's
harmless to remove all invocations of unit2minor() and minor2unit().

Reviewed by:	kib
2008-09-26 14:19:52 +00:00