lttng-modules.git
8 years agoFix: add missing versions and init call for page_alloc wrapper
Mathieu Desnoyers [Fri, 12 Feb 2016 20:11:04 +0000 (15:11 -0500)] 
Fix: add missing versions and init call for page_alloc wrapper

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: Define lttng-tracer metadata only once
Michael Jeanson [Wed, 10 Feb 2016 16:08:14 +0000 (11:08 -0500)] 
Fix: Define lttng-tracer metadata only once

Fixes sysfs trying to create the lttng-tracer module version node
multiple times.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: Add CONFIG_LTTNG to modules_install target
Michael Jeanson [Tue, 9 Feb 2016 20:16:56 +0000 (15:16 -0500)] 
Fix: Add CONFIG_LTTNG to modules_install target

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: Use kbuild env instead of a custom var KERNELDIR
Michael Jeanson [Mon, 8 Feb 2016 21:33:17 +0000 (16:33 -0500)] 
Fix: Use kbuild env instead of a custom var KERNELDIR

We currently use the custom variables KERNELDIR and LTTNG_KERNELDIR
to pass the kernel source tree directory to helper scripts. We should
instead use the built-in Kbuild variable CURDIR which is available in
all sub makefiles and always points to the kernel sources.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoUpdate clock offset comment
Mathieu Desnoyers [Mon, 8 Feb 2016 21:58:32 +0000 (16:58 -0500)] 
Update clock offset comment

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoclock offset: print negative value in metadata
Mathieu Desnoyers [Mon, 8 Feb 2016 21:52:05 +0000 (16:52 -0500)] 
clock offset: print negative value in metadata

In the upcoming 2.8, we can print the negative value of clock offset in
the metadata, and expect users to update their viewers to correct any
bug that could prevent them from handling those negative values.

This happens only in cases where the system sets CLOCK_REALTIME to 0
after boot, thus leading to a negative clock offset value between
realtime and monotonic clocks.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: handle negative clock offset
Mathieu Desnoyers [Mon, 8 Feb 2016 21:38:46 +0000 (16:38 -0500)] 
Fix: handle negative clock offset

In the unlikely situation where a system sets its hardware clock
(CLOCK_REALTIME) to 0 (Epoch) after boot, the difference

  monotonic - realtime

becomes negative.

Fixup this situation by returning a 0 offset in this case.

This ensures that trace viewer implementations (e.g. babeltrace) which
currently cannot handle the negative offset (known bug) still work with
the generated traces.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: sched instrumentation for 4.1-rt11
Michael Jeanson [Fri, 5 Feb 2016 22:53:07 +0000 (17:53 -0500)] 
Fix: sched instrumentation for 4.1-rt11

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoAdd RT patch version macros
Michael Jeanson [Fri, 5 Feb 2016 22:53:06 +0000 (17:53 -0500)] 
Add RT patch version macros

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoExpect filter context identifiers starting with $ctx.
Mathieu Desnoyers [Thu, 4 Feb 2016 00:17:35 +0000 (19:17 -0500)] 
Expect filter context identifiers starting with $ctx.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoARM64: wire up compat system calls
Mathieu Desnoyers [Wed, 3 Feb 2016 14:29:15 +0000 (09:29 -0500)] 
ARM64: wire up compat system calls

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoAdd support for arm64 syscalls
Jan Willeke [Wed, 3 Feb 2016 13:04:12 +0000 (14:04 +0100)] 
Add support for arm64 syscalls

[ Edit by Mathieu Desnoyers: rename "x86_64" strings to "arm64" in
  comments. ]

Signed-off-by: Jan Willeke <jan.willeke@harman.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: Ubuntu kernel range for block_rq_complete
Michael Jeanson [Fri, 29 Jan 2016 22:46:03 +0000 (17:46 -0500)] 
Fix: Ubuntu kernel range for block_rq_complete

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: Ubuntu kernel range for mm_page_alloc_extfrag
Michael Jeanson [Fri, 29 Jan 2016 22:46:02 +0000 (17:46 -0500)] 
Fix: Ubuntu kernel range for mm_page_alloc_extfrag

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: update vmscan instrumentation for kernel 4.5
Mathieu Desnoyers [Mon, 25 Jan 2016 19:23:43 +0000 (14:23 -0500)] 
Fix: update vmscan instrumentation for kernel 4.5

The following tracepoint changes made their way into Linux 4.5-rc1:

commit 3aa2385111168187f24a6db04697c6fab0fab9b4
Author: yalin wang <yalin.wang2010@gmail.com>
Date:   Thu Jan 14 15:18:30 2016 -0800

    mm/vmscan.c: change trace_mm_vmscan_writepage() proto type

and

commit ba5e9579433aefcdccdec207601e124d3bdf2a71
Author: yalin wang <yalin.wang2010@gmail.com>
Date:   Thu Jan 14 15:18:48 2016 -0800

    mm: change mm_vmscan_lru_shrink_inactive() proto types

Update the lttng-modules instrumentation to match those changes.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: check reference counts for overflow
Mathieu Desnoyers [Tue, 19 Jan 2016 14:51:55 +0000 (09:51 -0500)] 
Fix: check reference counts for overflow

Linux kernel CVE-2016-0728 is a use-after-free based on overflow of the
reference counting mechanism.

Implement a kref wrapper in lttng that validates overflows, and use it
instead of kref_get(). Also check explicitly for overflows on file
fcount counters.

This should not be an issue in practice in lttng-modules because the ABI
is only exposed to root, but let's err on the safe side.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: RHEL 7.2 scsi instrumentation
Michael Jeanson [Thu, 14 Jan 2016 19:35:47 +0000 (14:35 -0500)] 
Fix: RHEL 7.2 scsi instrumentation

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: RHEL 7.2 kvm instrumentation
Michael Jeanson [Thu, 14 Jan 2016 19:35:46 +0000 (14:35 -0500)] 
Fix: RHEL 7.2 kvm instrumentation

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoKconfig: describe both module and in-kernel compilation options
Mathieu Desnoyers [Fri, 18 Dec 2015 21:44:05 +0000 (16:44 -0500)] 
Kconfig: describe both module and in-kernel compilation options

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoAdd comments and indentation to Makefile
Michael Jeanson [Fri, 11 Dec 2015 22:06:41 +0000 (17:06 -0500)] 
Add comments and indentation to Makefile

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoAdd support for built-in kernel build
Michael Jeanson [Fri, 11 Dec 2015 21:33:09 +0000 (16:33 -0500)] 
Add support for built-in kernel build

To build the LTTng modules as builtins in a kernel image, simply run
the "built-in.sh" script with the path to you kernel source directory
as an argument. Then configure your kernel build and add the "CONFIG_LTTNG"
option. Build as usual and voila!

This is an early implementation with a single configuration option that
enables or disables everything, We could add fine grained config options
for each modules or group of modules.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoRename sub makefiles to Kbuild
Michael Jeanson [Fri, 11 Dec 2015 21:26:22 +0000 (16:26 -0500)] 
Rename sub makefiles to Kbuild

This follows kbuild's convention and makes it clear that the make
command has to be run from the base directory.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoCleanup sub makefiles
Michael Jeanson [Fri, 11 Dec 2015 21:25:00 +0000 (16:25 -0500)] 
Cleanup sub makefiles

Remove unsused directives which are part of the main makefile, add
indentation and comments to conditions.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoMake goals configurable with CONFIG_LTTNG
Michael Jeanson [Fri, 11 Dec 2015 20:31:25 +0000 (15:31 -0500)] 
Make goals configurable with CONFIG_LTTNG

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: Use generic raw_irqs_disabled_flags
Michael Jeanson [Thu, 10 Dec 2015 16:26:29 +0000 (11:26 -0500)] 
Fix: Use generic raw_irqs_disabled_flags

instead of arch_irqs_disabled_flags, this fixes the build for kernel < 2.6.37

See linux commit df9ee29270c11dba7d0fe0b83ce47a4d8e8d2101 for more details.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
8 years agoFix: Use MAX_RT_PRIO offset in sched_wakeup_template
Antoine Busque [Fri, 4 Dec 2015 20:16:59 +0000 (15:16 -0500)] 
Fix: Use MAX_RT_PRIO offset in sched_wakeup_template

All other sched_* events with prio fields offset the task_struct's
prio value by subtracting MAX_RT_PRIO. This way the value corresponds
to that given by the kernel's task_prio function, and thus with the
prio context field.

This adds the same offset to sched_wakeup, sched_wakeup_new, and
sched_waking, via the sched_wakeup_template event class. This way
their value is comparable to other sched_* events, and the prio
context.

Signed-off-by: Antoine Busque <abusque@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: update sched instrumentation for kernel 4.4.0
Mathieu Desnoyers [Fri, 27 Nov 2015 19:57:44 +0000 (14:57 -0500)] 
Fix: update sched instrumentation for kernel 4.4.0

Due to upstream Linux kernel commit:

commit c73464b1c8434ad4cbfd5369c3e724f3e8ffe5a4
Author: Peter Zijlstra <peterz@infradead.org>
Date:   Mon Sep 28 18:06:56 2015 +0200

    sched/core: Fix trace_sched_switch()

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoBump version number for development branch
Julien Desfossez [Wed, 25 Nov 2015 17:54:03 +0000 (12:54 -0500)] 
Bump version number for development branch

Signed-off-by: Julien Desfossez <jdesfossez@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: interruptible context: reversed logic
Mathieu Desnoyers [Tue, 17 Nov 2015 19:29:08 +0000 (14:29 -0500)] 
Fix: interruptible context: reversed logic

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoContexts for RT debugging
Julien Desfossez [Thu, 12 Nov 2015 20:49:24 +0000 (15:49 -0500)] 
Contexts for RT debugging

Add the interruptible, preemptible, need_resched and migratable
contexts.

Signed-off-by: Julien Desfossez <jdesfossez@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: instrumentation: v4lv2 missing include
Mathieu Desnoyers [Tue, 10 Nov 2015 18:01:50 +0000 (13:01 -0500)] 
Fix: instrumentation: v4lv2 missing include

Starting at least with 4.3 kernel, we need to specifically include
media/videobuf2-core.h.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: header size larger than 256 bytes
Mathieu Desnoyers [Sun, 25 Oct 2015 15:23:31 +0000 (11:23 -0400)] 
Fix: header size larger than 256 bytes

When adding large context (e.g. callstack), headers larger than 256
bytes cause discrepancy between calculated size and size written into
the trace buffers. This generates a corrupted trace and triggers a
warning in ring buffer backend, which triggers a safety net disabling
tracing for the current channel.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoInstrument x86 page faults
Mathieu Desnoyers [Fri, 23 Oct 2015 23:29:34 +0000 (19:29 -0400)] 
Instrument x86 page faults

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: irq_vectors TRACE_SYSTEM name
Mathieu Desnoyers [Fri, 23 Oct 2015 22:44:39 +0000 (18:44 -0400)] 
Fix: irq_vectors TRACE_SYSTEM name

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoInstrument x86_irq_vectors
Mathieu Desnoyers [Fri, 23 Oct 2015 21:09:30 +0000 (17:09 -0400)] 
Instrument x86_irq_vectors

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: tracepoint listing misses last loaded probe
Mathieu Desnoyers [Fri, 23 Oct 2015 21:17:43 +0000 (17:17 -0400)] 
Fix: tracepoint listing misses last loaded probe

The seqfile iteration listing tracepoints operates on the probe list
directly, without going through the lttng_get_probe_list_head()
accessor which ensures that the lazy list of probes is moved to the
actual list of probes.

This causes an issue when loading a probe and then listing the
tracepoints when no tracing sessions are active: the last probe loaded
is missing from the listing.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: lttng trace-clock needs to disable preemption
Mathieu Desnoyers [Fri, 9 Oct 2015 16:24:23 +0000 (12:24 -0400)] 
Fix: lttng trace-clock needs to disable preemption

We use a per-cpu data structure, and some contexts (e.g. buffer create)
call this function with preemption enabled. This is the case also for
buffer flush operation.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoTracepoint event: add "TP_code_post()"
Mathieu Desnoyers [Fri, 9 Oct 2015 14:02:37 +0000 (10:02 -0400)] 
Tracepoint event: add "TP_code_post()"

Useful for probes that need to perform teardown after serialization,
e.g. allocate temporary memory in TP_code_pre() and free it in
TP_code_post(). Be careful to only use memory allocation from contexts
allowing it.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoImplement array and sequence bitfields
Mathieu Desnoyers [Thu, 8 Oct 2015 20:02:06 +0000 (16:02 -0400)] 
Implement array and sequence bitfields

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: kmem: add mm.h include
Mathieu Desnoyers [Sat, 3 Oct 2015 15:57:39 +0000 (11:57 -0400)] 
Fix: kmem: add mm.h include

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoAdd page frame number (pfn) to kmem page events
Mathieu Desnoyers [Sat, 3 Oct 2015 15:34:37 +0000 (11:34 -0400)] 
Add page frame number (pfn) to kmem page events

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoUse pfn rather than struct page in ring buffer array
Mathieu Desnoyers [Tue, 28 Apr 2015 14:55:37 +0000 (10:55 -0400)] 
Use pfn rather than struct page in ring buffer array

First step to support permanent memory (e.g. pmem) which does not have
struct page.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoImplement clock plugin support
Mathieu Desnoyers [Sun, 12 Oct 2014 11:47:15 +0000 (13:47 +0200)] 
Implement clock plugin support

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoCommand to regenerate the metadata of a session
Julien Desfossez [Fri, 7 Aug 2015 21:07:28 +0000 (17:07 -0400)] 
Command to regenerate the metadata of a session

Signed-off-by: Julien Desfossez <jdesfossez@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: writeback instrumentation update for 4.3 Linux kernel
Mathieu Desnoyers [Tue, 15 Sep 2015 19:46:01 +0000 (15:46 -0400)] 
Fix: writeback instrumentation update for 4.3 Linux kernel

Linux upstream commit:

commit 5634cc2aa9aebc77bc862992e7805469dcf83dac
Author: Tejun Heo <tj@kernel.org>
Date:   Tue Aug 18 14:54:56 2015 -0700

    writeback: update writeback tracepoints to report cgroup

Updated the tracepoint signatures for writeback probes. Follow this
change. Don't add extra data (cgroup information) yet.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: update sched wakeup instrumentation for 4.3 kernel
Mathieu Desnoyers [Mon, 14 Sep 2015 16:12:43 +0000 (12:12 -0400)] 
Fix: update sched wakeup instrumentation for 4.3 kernel

Change introduced in upstream Linux:

commit fbd705a0c6184580d0e2fbcbd47a37b6e5822511
Author: Peter Zijlstra <peterz@infradead.org>
Date:   Tue Jun 9 11:13:36 2015 +0200

    sched: Introduce the 'trace_sched_waking' tracepoint

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: lttng-test build failure for kernels < 3.0
Michael Jeanson [Fri, 11 Sep 2015 20:06:25 +0000 (16:06 -0400)] 
Fix: lttng-test build failure for kernels < 3.0

Fixes an undefined reference to kstrtouint_from_user.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoUse 3.18 syscall instrumentation for MIPS32
Lars Persson [Tue, 8 Sep 2015 13:31:46 +0000 (15:31 +0200)] 
Use 3.18 syscall instrumentation for MIPS32

Signed-off-by: Lars Persson <larper@axis.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoUpdate the MIPS32 syscall instrumentation to 3.18
Lars Persson [Tue, 8 Sep 2015 13:31:45 +0000 (15:31 +0200)] 
Update the MIPS32 syscall instrumentation to 3.18

Signed-off-by: Lars Persson <larper@axis.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: Move pipe override to the arch specific pointers_override.h
Lars Persson [Tue, 8 Sep 2015 13:20:15 +0000 (15:20 +0200)] 
Fix: Move pipe override to the arch specific pointers_override.h

The MIPS architecture has a non-standard calling convention for pipe()
and cannot use the provided override for the pipe event.

Signed-off-by: Lars Persson <larper@axis.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoImplement lttng test module
Mathieu Desnoyers [Fri, 4 Sep 2015 20:36:22 +0000 (16:36 -0400)] 
Implement lttng test module

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoCleanup: remove logically dead code
Mathieu Desnoyers [Fri, 4 Sep 2015 05:29:49 +0000 (01:29 -0400)] 
Cleanup: remove logically dead code

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: filter validator use after free
Mathieu Desnoyers [Fri, 4 Sep 2015 05:16:52 +0000 (01:16 -0400)] 
Fix: filter validator use after free

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: use after free in channel release
Mathieu Desnoyers [Fri, 4 Sep 2015 05:12:53 +0000 (01:12 -0400)] 
Fix: use after free in channel release

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: non-enabler events should be disabled by default
Mathieu Desnoyers [Wed, 2 Sep 2015 02:27:35 +0000 (22:27 -0400)] 
Fix: non-enabler events should be disabled by default

The session daemon expects that all events (enablers and events) are
disabled when created, so we can attach a filter before enabling them.

Also fix the kretprobe to ensure we can enable/disable both the entry
and return probe (--function instrumentation).

Fixes: #926
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: build failure on 2.6.36
Michael Jeanson [Mon, 31 Aug 2015 13:57:18 +0000 (09:57 -0400)] 
Fix: build failure on 2.6.36

Fixes build failure on the 2.6.36 kernel branch which misses the
vzalloc() function.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoCleanup: split bdi_dirty_ratelimit with ifdef into separate macros
Mathieu Desnoyers [Fri, 21 Aug 2015 16:28:44 +0000 (09:28 -0700)] 
Cleanup: split bdi_dirty_ratelimit with ifdef into separate macros

Makes the code easier to maintain in the long run.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: writeback instrumentation for 4.2 kernels
Michael Jeanson [Fri, 21 Aug 2015 02:23:15 +0000 (22:23 -0400)] 
Fix: writeback instrumentation for 4.2 kernels

Bandwidth related fields were moved by this commit:

commit a88a341a73be4ef035ca26170c849f002797da27
Author: Tejun Heo <tj@kernel.org>
Date:   Fri, 22 May 2015 17:13:28 -0400

    writeback: move bandwidth related fields from backing_dev_info into
    bdi_writeback

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: mm_page_alloc_extfrag instrumentation for kernel 3.18.10
Michael Jeanson [Fri, 14 Aug 2015 15:37:31 +0000 (11:37 -0400)] 
Fix: mm_page_alloc_extfrag instrumentation for kernel 3.18.10

The following commit has been backported from kernel 3.19.2 into
3.18.10, introducing a change to mm_page_alloc_extfrag and therefore
provoking a build failure on a 3.18.10 kernel:

commit a4f3f96f850db69890f47984c60606a2362bee89
Author: Vlastimil Babka <vbabka@suse.cz>
Date:   Wed Feb 11 15:28:15 2015 -0800

    mm: when stealing freepages, also take pages created by splitting buddy page

    commit 99592d598eca62bdbbf62b59941c189176dfc614 upstream.

This patch adds the proper version check to allow building on 3.18.y.

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoAdd stream instance id to the packet header
Julien Desfossez [Sat, 1 Aug 2015 04:06:03 +0000 (00:06 -0400)] 
Add stream instance id to the packet header

This new field allows the viewer to distinguish between trace files
belonging to the same packet stream (in LTTng: the same CPU in the same
channel).

Signed-off-by: Julien Desfossez <jdesfossez@efficios.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoAdd a packet sequence number
Julien Desfossez [Sat, 1 Aug 2015 04:02:33 +0000 (00:02 -0400)] 
Add a packet sequence number

This allows the viewer to identify the gaps between trace packets.

Signed-off-by: Julien Desfossez <jdesfossez@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: kmem probe with Ubuntu 3.13 kernels
Mathieu Desnoyers [Wed, 29 Jul 2015 17:00:04 +0000 (13:00 -0400)] 
Fix: kmem probe with Ubuntu 3.13 kernels

Fixes an undefined reference to get_pageblock_flags_mask.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: disable kvm probe if lapic.h isn't found
Chris J Arges [Fri, 24 Jul 2015 18:18:59 +0000 (13:18 -0500)] 
Fix: disable kvm probe if lapic.h isn't found

In a typical distribution if just linux-headers is installed, lapic.h
will not be installed. We should check if that file exists and not build
the module.

Signed-off-by: Chris J Arges <chris.j.arges@canonical.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: timer instrumentation for 4.2 kernels
Mathieu Desnoyers [Thu, 16 Jul 2015 17:02:44 +0000 (13:02 -0400)] 
Fix: timer instrumentation for 4.2 kernels

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: ext4 instrumentation for 4.2 kernels
Mathieu Desnoyers [Thu, 16 Jul 2015 17:02:23 +0000 (13:02 -0400)] 
Fix: ext4 instrumentation for 4.2 kernels

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: kvm instrumentation for 4.2 kernels
Mathieu Desnoyers [Thu, 16 Jul 2015 17:02:03 +0000 (13:02 -0400)] 
Fix: kvm instrumentation for 4.2 kernels

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: allow LTTng to be built within kernel tree
Mathieu Desnoyers [Thu, 16 Jul 2015 03:49:15 +0000 (23:49 -0400)] 
Fix: allow LTTng to be built within kernel tree

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoVersion 2.7.0-rc1 v2.7.0-rc1
Mathieu Desnoyers [Wed, 15 Jul 2015 18:42:51 +0000 (14:42 -0400)] 
Version 2.7.0-rc1

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: Building the event list fails on fragmented memory
Martin Leisener [Wed, 10 Jun 2015 13:17:37 +0000 (15:17 +0200)] 
Fix: Building the event list fails on fragmented memory

On a small arm imx6 solo with 256MB RAM it often happens that memory
becomes fragmented rather quickly, so that kmalloc will not be able to
get enough consecutive pages (enocuntered for example if you enable all
kernel events: lttng enable-event -k syscall --all).

This patch switches the allocation to vmalloc. Tested for x86 on Ubuntu
12.04 Lts and on imx6 solo 256MB RAM

If this patch is not applied, you can identify low and/or fragmented
memory failures by looking at the kernel ring buffer (please ignore DMA,
it is due to some memory setup misconfiguration, should read Normal):

...
[  321.993820] lttng-sessiond: page allocation failure: order:4, mode:0x1040d0
...
[  321.994711] lowmem_reserve[]: 0 0 0
[  321.994727] DMA: 801*4kB (UEMC) 424*8kB (EMC) 355*16kB (UEMC) 344*32kB (MC) 340*64kB (C) 8*128kB (C) 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB 0*8192kB 0*16384kB 0*32768kB = 46068kB

[ Edit by Mathieu: use vzalloc() rather than vmalloc() + memset 0. ]

Signed-off-by: Martin Leisener <martin@leisener.de>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: use after free on metadata cache reallocation
Mathieu Desnoyers [Thu, 25 Jun 2015 13:10:52 +0000 (09:10 -0400)] 
Fix: use after free on metadata cache reallocation

When the metadata cache is expanded (reallocated) by
lttng_metadata_printf(), the metadata cache reader
(lttng_metadata_output_channel()) may use freed memory, because the
metadata cache is not protected from concurrent read accesses. The
metadata cache updates are protected from each other by the sessions
mutex, but metadata cache reads do not hold the sessions mutex.
Actually, the comment on top of lttng_metadata_output_channel() stating
"We have exclusive access to our metadata buffer (protected by the
sessions_mutex)" is simply wrong, because this mutex is never held when
calling lttng_metadata_output_channel().

Promote the per-stream lock to the metadata cache used by each of those
metadata streams, thus ensuring mutual exclusion between metadata cache
reallocation and readers.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: version checks for kernel 4.0
Michael Jeanson [Wed, 17 Jun 2015 20:28:02 +0000 (16:28 -0400)] 
Fix: version checks for kernel 4.0

Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: Incorrect Ubuntu kernel patchlevel
Mathieu Desnoyers [Mon, 15 Jun 2015 16:28:25 +0000 (12:28 -0400)] 
Fix: Incorrect Ubuntu kernel patchlevel

The kernel version used should be the one in Makefile and generated
version.h, not the one tweaked by Ubuntu as "0" in the built package.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: cpu-id context should use int type
Mathieu Desnoyers [Sat, 13 Jun 2015 09:14:17 +0000 (11:14 +0200)] 
Fix: cpu-id context should use int type

cycles_t makes no sense as type for cpu-id context.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoImplement cpu-id context
Mathieu Desnoyers [Thu, 11 Jun 2015 21:40:21 +0000 (23:40 +0200)] 
Implement cpu-id context

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoImplement cpu_id context for filtering
Mathieu Desnoyers [Thu, 11 Jun 2015 15:39:16 +0000 (17:39 +0200)] 
Implement cpu_id context for filtering

cpu_id context can now be used for filtering, e.g.:

lttng enable-event -k sched_switch --filter '$ctx.cpu_id==1'

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: context printk mismatch on error
Mathieu Desnoyers [Thu, 11 Jun 2015 15:38:46 +0000 (17:38 +0200)] 
Fix: context printk mismatch on error

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoCleanup: misleading comment about deferrable timer
Mathieu Desnoyers [Thu, 11 Jun 2015 08:09:49 +0000 (10:09 +0200)] 
Cleanup: misleading comment about deferrable timer

Timer in lttng-modules are not deferrable, because we cannot hook into
the Linux kernel CPU idle events, because no notifiers are exposed for
those.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: arm-32 build
Martin Leisener [Fri, 29 May 2015 20:29:44 +0000 (16:29 -0400)] 
Fix: arm-32 build

The current master branch of lttng-modules doesn't seem to compile for
arm-32 builds.

The patch below repairs the build for arm (and still builds on a x86)
(tested on Ubuntu 12.04 LTS x86 + imx6 solo)

Signed-off-by: Martin Leisener <martin@leisener.de>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: Update kmem event for Ubuntu's 3.16 kernel
Alexandre Montplaisir [Tue, 26 May 2015 20:12:00 +0000 (16:12 -0400)] 
Fix: Update kmem event for Ubuntu's 3.16 kernel

The upstream patch in question in commit 72906e1 was cherry-picked into
Ubuntu's 3.16 kernel backport branch (called lts-utopic). The version
check should also include this branch.

The other backport branch, lts-vivid, and all following ones will be
covered by the standard

  LINUX_VERSION_CODE >= KERNEL_VERSION(3,19,2)

check, so should not require other workarounds.

References #889.

Signed-off-by: Alexandre Montplaisir <alexmonthy@voxpopuli.im>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: RHEL 7.1 block instrumentation
Mathieu Desnoyers [Wed, 27 May 2015 16:56:05 +0000 (12:56 -0400)] 
Fix: RHEL 7.1 block instrumentation

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: add RHEL version macros
Mathieu Desnoyers [Wed, 27 May 2015 16:19:01 +0000 (12:19 -0400)] 
Fix: add RHEL version macros

RHEL 7.1 has backported upstream patches that change the kvm.h
tracepoint prototype. Add version check specific to RHEL to handle this
case.

RHEL 7.x has the required fixes backported that allow removing the 3.10
blacklist check for them, so take this into account.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: add missing parenthesis in ubuntu version check
Mathieu Desnoyers [Wed, 27 May 2015 16:13:32 +0000 (12:13 -0400)] 
Fix: add missing parenthesis in ubuntu version check

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: remove regmap instrumentation for kernels < 4.1
Mathieu Desnoyers [Tue, 26 May 2015 19:22:01 +0000 (15:22 -0400)] 
Fix: remove regmap instrumentation for kernels < 4.1

Modifications to regmap.h instrumentation in mainline Linux kernel has
been no less than erratic. First, the public instrumentation header
regmap.h include a private driver header in Linux 4.0. Then, regmap.h
is moved to the private driver directory in Linux 4.1. To make things
worse, the 4.0 commit has been picked into stable branches of the Linux
kernel.

Since this does not appear to be an instrumentation of utmost
importance, only build this instrumentation probe if the private header
is found in the driver directory (need full kernel sources).

This removes regmap instrumentation for older kernels.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: Update kmem event for recent Ubuntu kernel
Alexandre Montplaisir [Fri, 22 May 2015 18:36:53 +0000 (14:36 -0400)] 
Fix: Update kmem event for recent Ubuntu kernel

Ubuntu backported a patch into their 3.13 (Trusty) branch which
changes kmem event definition.

Upstream commit
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=99592d598eca62bdbbf62b59941c189176dfc614
first appears in 4.0 (and was later backported to 3.19.2).
We already have the proper check for this.

This corresponds to Ubuntu commit
http://kernel.ubuntu.com/git/ubuntu/ubuntu-trusty.git/commit/?id=d938e4bff1089a1f4757ed94a5cace803c6a363b
which was first released with 3.13.0-50.82.
This required adding a new check specifically for the
Ubuntu version.

Signed-off-by: Alexandre Montplaisir <alexmonthy@voxpopuli.im>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: missing statedump end event when block device listing available
Mathieu Desnoyers [Thu, 14 May 2015 22:29:58 +0000 (18:29 -0400)] 
Fix: missing statedump end event when block device listing available

Incorrect handling of lttng_enumerate_block_devices() return value of 0
(which means "ok"), causing do_lttng_statedump() to return early.

To causes missing "lttng_statedump_end" in traces where block device
enumeration is available (CONFIG_KALLSYMS=y).

Reported-by: Antoine Busque <abusque@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: don't generate incorrect macros for debian/ubuntu version check
Mathieu Desnoyers [Thu, 14 May 2015 15:33:47 +0000 (11:33 -0400)] 
Fix: don't generate incorrect macros for debian/ubuntu version check

When the debian/ubuntu macros are unset, we end up generating macros
that have no right hand operand to "+", which seems to break compilation
on some compilers, even though it will always be optimized away.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoRevert "Fix: build against Ubuntu kernels"
Mathieu Desnoyers [Thu, 14 May 2015 15:24:20 +0000 (11:24 -0400)] 
Revert "Fix: build against Ubuntu kernels"

This reverts commit a748963b76f353d459a3faf85eecc96f52811eee.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: build against Ubuntu kernels
Mathieu Desnoyers [Thu, 14 May 2015 13:13:49 +0000 (09:13 -0400)] 
Fix: build against Ubuntu kernels

Recent Ubuntu kernels appear to define DEBIAN_API_VERSION, but they are
not really a Debian kernel per-se: the abi-debian-version.sh cannot find
the expected Debian kernel version string layout.

Therefore, change the conditional check to use directly the
LTTNG_DEBIAN_VERSION_CODE define, which is defined only when the
abi-debian-version.sh script figures out it builds against a Debian
kernel.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoAdd namespace info in sched_fork and statedump
Sebastien Lorrain [Wed, 15 Apr 2015 15:53:53 +0000 (11:53 -0400)] 
Add namespace info in sched_fork and statedump

Modifications to sched_fork : Add a field for parent and child pid
namespace inode (as in /proc/$PID/ns/pid). Also add a field for the
child VTID.

Modifications to lttng_statedump_process_state : Add a field for the pid
namespace inode of the task.

Signed-off-by: Sebastien Lorrain <sebastien.lorrain01@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: ext4 instrumentation: flags parameter did not exist prior to 3.11
Mathieu Desnoyers [Tue, 5 May 2015 19:54:24 +0000 (15:54 -0400)] 
Fix: ext4 instrumentation: flags parameter did not exist prior to 3.11

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: printk instrumentation: remove "condition" tracepoints
Mathieu Desnoyers [Tue, 5 May 2015 19:42:37 +0000 (15:42 -0400)] 
Fix: printk instrumentation: remove "condition" tracepoints

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: regmap build against kernel 4.0 kernel headers
Mathieu Desnoyers [Mon, 27 Apr 2015 22:58:51 +0000 (18:58 -0400)] 
Fix: regmap build against kernel 4.0 kernel headers

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoAdd mmu_valid_gen field to mmutrace events
Mathieu Desnoyers [Mon, 27 Apr 2015 21:47:53 +0000 (17:47 -0400)] 
Add mmu_valid_gen field to mmutrace events

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: add missing x86 mmutrace kernel header include
Mathieu Desnoyers [Mon, 27 Apr 2015 21:33:47 +0000 (17:33 -0400)] 
Fix: add missing x86 mmutrace kernel header include

Needed to ensure the compiler checks prototypes of lttng-modules probe
against the kernel prototypes.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: x86 mmutrace event extra field for kernels >= 3.11
Mathieu Desnoyers [Mon, 27 Apr 2015 21:32:54 +0000 (17:32 -0400)] 
Fix: x86 mmutrace event extra field for kernels >= 3.11

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: remove execute flag from kvm.h file
Mathieu Desnoyers [Mon, 27 Apr 2015 21:23:16 +0000 (17:23 -0400)] 
Fix: remove execute flag from kvm.h file

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: build x86 kvm probes on kernels >= 4.1-rc1
Mathieu Desnoyers [Mon, 27 Apr 2015 21:20:28 +0000 (17:20 -0400)] 
Fix: build x86 kvm probes on kernels >= 4.1-rc1

iodev.h has moved to include/kvm/.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: compilation on 4.1-rc1 kernel, remove unused WB_WORK_REASON
Mathieu Desnoyers [Mon, 27 Apr 2015 20:50:31 +0000 (16:50 -0400)] 
Fix: compilation on 4.1-rc1 kernel, remove unused WB_WORK_REASON

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: 4.1-rc1 Linux build and regmap instrumentation
Mathieu Desnoyers [Mon, 27 Apr 2015 20:44:11 +0000 (16:44 -0400)] 
Fix: 4.1-rc1 Linux build and regmap instrumentation

regmap header has been privatized.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
9 years agoFix: don't clash with older Debian kernel versions
Mathieu Desnoyers [Mon, 27 Apr 2015 19:30:03 +0000 (15:30 -0400)] 
Fix: don't clash with older Debian kernel versions

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
This page took 0.045198 seconds and 4 git commands to generate.