Mathieu Desnoyers [Sat, 11 Mar 2017 18:46:10 +0000 (13:46 -0500)]
Fix: introduce LTTNG_SIZE_MAX for older kernels
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sat, 11 Mar 2017 13:44:42 +0000 (08:44 -0500)]
Use SIZE_MAX instead of -1ULL for size_t parameter
strutils_star_glob_match() receives a size_t. Passing -1ULL truncates
the value implicitly on systems where size_t is 32-bit. It is cleaner to
use SIZE_T.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sat, 11 Mar 2017 13:39:22 +0000 (08:39 -0500)]
filter: use SIZE_MAX for size_t
The backing type is a size_t, so use SIZE_MAX to represent infinity.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 10 Mar 2017 21:51:17 +0000 (16:51 -0500)]
Fix: out of bound array access in filter code
Fix ported from lttng-ust, initially found by Coverity.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Philippe Proulx [Sun, 19 Feb 2017 01:01:34 +0000 (20:01 -0500)]
Add support for star globbing patterns in event names
This patch adds support for full star-only globbing patterns used in
the event names (enabler names).
strutils_star_glob_match() is always used to perform the match when
the enabler is LTTNG_ENABLER_STAR_GLOB. This enabler is set when it is
detected that its name contains at least one non-escaped star with
strutils_is_star_glob_pattern().
The match is performed by strutils_star_glob_match(), the same function
that the filter interpreter uses.
Signed-off-by: Philippe Proulx <eeppeliteloop@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Philippe Proulx [Sun, 19 Feb 2017 01:04:11 +0000 (20:04 -0500)]
Filtering: add support for star-only globbing patterns
This patch adds the support for "full" star-only globbing patterns to be
used in filter literal strings. A star-only globbing pattern is a
globbing pattern with the star (`*`) being the only special character.
This means `?` and character sets (`[abc-k]`) are not supported here. We
cannot support them without a strategy to differentiate the globbing
pattern because `?` and `[` are not special characters in filter literal
strings right now. The eventual strategy to support them would probably
look like this:
filename =* "?sys*.[ch]"
The filter bytecode generator in LTTng-tools's session daemon creates
the new FILTER_OP_LOAD_STAR_GLOB_STRING operation when the interpreter
should load a star globbing pattern literal string. Even if both
"plain", or legacy strings and star globbing pattern strings are literal
strings, they do not represent the same thing, that is, the == and !=
operators act differently.
The validation process checks that:
1. There's no binary operator between two
FILTER_OP_LOAD_STAR_GLOB_STRING operations. It is illegal to compare
two star globbing patterns, as this is not trivial to implement, and
completely useless as far as I know.
2. Only the == and != binary operators are allowed between a
star globbing pattern and a string.
For the special case of star globbing patterns with a star at the end
only, the current behaviour is not changed to preserve a maximum of
backward compatibility. This is also why the ABI version is changed from
2.2 to 2.3, not to 3.0.
== or != operations between REG_STRING and REG_STAR_GLOB_STRING
registers is specialized to FILTER_OP_EQ_STAR_GLOB_STRING and
FILTER_OP_NE_STAR_GLOB_STRING. Which side is the actual globbing pattern
(the one with the REG_STAR_GLOB_STRING type) is checked at execution
time. The strutils_star_glob_match() function is used to perform the
match operation. See the implementation for more details.
Signed-off-by: Philippe Proulx <eeppeliteloop@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Philippe Proulx [Sun, 19 Feb 2017 01:00:33 +0000 (20:00 -0500)]
Add string utilities
The new lttng-string-utils.c file has a few utility functions to
manipulate and check strings. See lttng-string-utils.c for more details.
Signed-off-by: Philippe Proulx <eeppeliteloop@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Philippe Proulx [Sun, 19 Feb 2017 01:05:13 +0000 (20:05 -0500)]
lttng-abi.c: cleanup whitespaces
Signed-off-by: Philippe Proulx <eeppeliteloop@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Wed, 8 Mar 2017 19:32:31 +0000 (14:32 -0500)]
Fix: use of uninitialized ret value in lttng_abi_open_metadata_stream
Fixes the following compiler warning:
lttng-abi.c: In function ‘lttng_metadata_ioctl’:
lttng-abi.c:971:6: warning: ‘ret’ may be used uninitialized in this function [-Wmaybe-uninitialized]
int ret;
^
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Wed, 8 Mar 2017 04:37:30 +0000 (23:37 -0500)]
Fix: kref changes for kernel 4.11
The underlying type of `struct kref` changed in kernel 4.11 from an
atomic_t to a refcount_t. This change was introduced in kernel
commit:
10383ae. This commit also added a builtin overflow checks to
`kref_get()` so we use it.
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Wed, 8 Mar 2017 16:50:38 +0000 (11:50 -0500)]
Fix: atomic_add_unless() returns true/false rather than prior value
The previous implementation assumed that `atomic_add_unless` returned
the prior value of the atomic counter when in fact it returned if the
addition was performed (true) or not performed (false).
Since `atomic_add_unless` can not return INT_MAX, the `lttng_kref_get`
always returned that the call was successful.
This issue had a low likelihood of being triggered since the two refcounts
of the counters used with this call are both bounded by the maximum
number of file descriptors on the system.
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Tue, 7 Mar 2017 16:21:59 +0000 (11:21 -0500)]
Fix: timers cputime_t arguments replaced by ull in kernel 4.11
cputime_t was changed to ull in the kernel commit:
858cf3a
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Tue, 7 Mar 2017 16:16:47 +0000 (11:16 -0500)]
Fix: update scsi instrumentation for kernel 4.11
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Tue, 7 Mar 2017 15:35:21 +0000 (10:35 -0500)]
Fix: changes to the vm_op fault cb prototype in libringbuffer
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Tue, 7 Mar 2017 15:14:19 +0000 (10:14 -0500)]
Fix: update btrfs instrumentation for kernel 4.11
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Tue, 7 Mar 2017 14:48:08 +0000 (09:48 -0500)]
Fix: update mm_vmscan instrumentation for kernel 4.11
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Francis Deslauriers [Tue, 7 Mar 2017 14:12:31 +0000 (09:12 -0500)]
Fix: section mismatch warning caused by __exit annotation
lttng_logger_exit is used in a non-exit function so it should not be
annotated with `__exit`.
Signed-off-by: Francis Deslauriers <francis.deslauriers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Jan Willeke [Thu, 16 Feb 2017 13:42:51 +0000 (14:42 +0100)]
socketpair: extend syscall socketpair tracing information
Decode the socketpair vector pointer into two file descriptors.
This exposes the connected file descriptors to analyses.
As sockerpair is a sub syscall of socketcall in x86_32,
sockerpair override must be disabled for x86_32 and x86_compatmode
Signed-off-by: Jan Willeke <jan.willeke@harman.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sat, 25 Feb 2017 08:34:10 +0000 (09:34 +0100)]
Remove events/mainline unused headers
We can actually diff from Linux kernel headers directly instead of
keeping stale unused copies of those headers.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sat, 25 Feb 2017 08:33:42 +0000 (09:33 +0100)]
update event README
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 10 Feb 2017 01:46:44 +0000 (20:46 -0500)]
Fix: nmi-safe clock on 32-bit systems
On 32-bit systems, the algorithm within lttng-modules that ensures the
nmi-safe clock increases monotonically on a CPU assumes to have one
clock read per 32-bit LSB overflow period, which is not guaranteed. It
also has an issue on the first clock reads after module load, because
the initial value for the last LSB is 0. It can cause the time to stay
stuck at the same value for a few seconds at the beginning of the trace,
which is unfortunate for the first trace after module load, because this
is where the offset between realtime and trace_clock is sampled, which
prevents correlation of kernel and user-space traces for that session.
It only affects 32-bit systems with kernels >= 3.17.
Fix this by using the non-nmi-safe clock source on 32-bit systems.
While we are there, remove an implementation-defined c99 behavior
regarding casting u64 to long by using unsigned arithmetic instead:
turn:
if (((long) now - (long) last) < 0)
into:
if (U64_MAX / 2 < now - last)
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 23 Jan 2017 20:16:22 +0000 (15:16 -0500)]
Fix: only include linux/cpuhotplug.h for kernels >= 4.10
Kernels at least <= 4.4 did not have this header file.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 23 Jan 2017 17:34:07 +0000 (12:34 -0500)]
Fix: 4.10 hotplug adaptation backward compat
from /home/compudj/git/lttng-modules/lttng-context-perf-counters.c:23:
/home/compudj/git/lttng-modules/lttng-context-perf-counters.c: In function ‘lttng_add_perf_counter_to_ctx’:
/home/compudj/git/lttng-modules/lttng-context-perf-counters.c:353:22: error: ‘cpu’ undeclared (first use in this function)
for_each_online_cpu(cpu) {
^
./include/linux/cpumask.h:223:8: note: in definition of macro ‘for_each_cpu’
for ((cpu) = -1; \
^
/home/compudj/git/lttng-modules/lttng-context-perf-counters.c:353:2: note: in expansion of macro ‘for_each_online_cpu’
for_each_online_cpu(cpu) {
^
/home/compudj/git/lttng-modules/lttng-context-perf-counters.c:353:22: note: each undeclared identifier is reported only once for each function it appears in
for_each_online_cpu(cpu) {
^
./include/linux/cpumask.h:223:8: note: in definition of macro ‘for_each_cpu’
for ((cpu) = -1; \
^
/home/compudj/git/lttng-modules/lttng-context-perf-counters.c:353:2: note: in expansion of macro ‘for_each_online_cpu’
for_each_online_cpu(cpu) {
^
./include/linux/cpumask.h:224:38: warning: left-hand operand of comma expression has no effect [-Wunused-value]
(cpu) = cpumask_next((cpu), (mask)), \
^
./include/linux/cpumask.h:717:36: note: in expansion of macro ‘for_each_cpu’
#define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask)
^
/home/compudj/git/lttng-modules/lttng-context-perf-counters.c:353:2: note: in expansion of macro ‘for_each_online_cpu’
for_each_online_cpu(cpu) {
^
scripts/Makefile.build:289: recipe for target '/home/compudj/git/lttng-modules/lttng-context-perf-counters.o' failed
make[2]: *** [/home/compudj/git/lttng-modules/lttng-context-perf-counters.o] Error 1
make[2]: *** Waiting for unfinished jobs....
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 23 Jan 2017 17:32:17 +0000 (12:32 -0500)]
Fix: 4.10 btrfs instrumentation update backward compat
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 23 Jan 2017 17:18:35 +0000 (12:18 -0500)]
Update btrfs instrumentation for 4.10 kernel
Based on commit
92a1bf76 "Btrfs: add 'inode' for extent map tracepoint"
in the upstream Linux kernel.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 10 Jan 2017 16:19:51 +0000 (11:19 -0500)]
Adapt lttng-modules to Linux 4.10 cpu hotplug state machine
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 10 Jan 2017 16:41:11 +0000 (11:41 -0500)]
btrfs instrumentation: update to 4.10 kernel
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 10 Jan 2017 16:29:49 +0000 (11:29 -0500)]
timer instrumentation: adapt to ktime_t without union
Introduced in Linux upstream in 4.10.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Wed, 21 Dec 2016 22:55:26 +0000 (17:55 -0500)]
Add load/unload messages to kernel log
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Wed, 21 Dec 2016 22:47:18 +0000 (17:47 -0500)]
Update version to 2.10.0-pre
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Wed, 7 Dec 2016 19:17:33 +0000 (14:17 -0500)]
Fix: asoc instrumentation for RHEL 7.3
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Wed, 7 Dec 2016 16:09:31 +0000 (11:09 -0500)]
Fix: SCSI instrumentation for SLES12 SP2
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Wed, 7 Dec 2016 16:09:30 +0000 (11:09 -0500)]
Add SUSE Linux Enterprise kernel version tests
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 28 Nov 2016 17:39:48 +0000 (12:39 -0500)]
Filter code relicensing to MIT license
Relicense the filtering code to MIT license.
I am the principal author of this code. Julien Desfossez gave the
approval for his modifications.
Acked-by: Julien Desfossez <jdesfossez@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Thu, 24 Nov 2016 01:43:49 +0000 (20:43 -0500)]
Add task cpu in process statedump
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 21 Nov 2016 21:08:22 +0000 (16:08 -0500)]
Performance: add missing unlikely in reserve
Add missing branch prediction hints within lttng_event_reserve().
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 24 Oct 2016 17:27:01 +0000 (13:27 -0400)]
Fix: preemptible and migratable context error handling
When built against preempt-rt and preempt kernels, the "return 0" case
means success, but lttng-modules incorrectly prints an error in the
kernel log.
Given that we handle the -ENOSYS error in lttng_context_init, there is
no need to keep the ifdefs in that function.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Thu, 13 Oct 2016 13:50:21 +0000 (15:50 +0200)]
Fix: bump stable kernel version ranges for clock work-around
Linux commit
27727df240c7 ("Avoid taking lock in NMI path with
CONFIG_DEBUG_TIMEKEEPING"), changed the logic to open-code
the timekeeping_get_ns() function, but forgot to include
the unit conversion from cycles to nanoseconds, breaking the
function's output, which impacts LTTng.
We expected Linux commit
58bfea9532 "timekeeping: Fix
__ktime_get_fast_ns() regression" to make its way into stable
kernels promptly, but it appears new stable kernel releases were
done before the fix was cherry-picked from the master branch.
We therefore need to bump the version ranges for the work-around
in lttng-modules.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
CC: John Stultz <john.stultz@linaro.org>
Mathieu Desnoyers [Fri, 7 Oct 2016 19:19:52 +0000 (15:19 -0400)]
Version 2.9.0-rc1
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 7 Oct 2016 14:55:16 +0000 (10:55 -0400)]
Fix: i2c: support kernels < 3.15
i2c instrumentation has only been added in kernel 3.15.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Thu, 6 Oct 2016 11:45:35 +0000 (07:45 -0400)]
Fix: show warning for broken clock work-around
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 5 Oct 2016 16:47:58 +0000 (12:47 -0400)]
Bump minor ABI version
Command added: LTTNG_KERNEL_SESSION_STATEDUMP
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 5 Oct 2016 11:20:32 +0000 (07:20 -0400)]
Fix: work-around upstream Linux timekeeping bug
Linux commit
27727df240c7 ("Avoid taking lock in NMI path with
CONFIG_DEBUG_TIMEKEEPING"), changed the logic to open-code
the timekeeping_get_ns() function, but forgot to include
the unit conversion from cycles to nanoseconds, breaking the
function's output, which impacts LTTng.
The following kernel versions are affected: 4.8, 4.7.4+, 4.4.20+,
4.1.32+
We expect that the upstream fix will reach the master and stable
branches timely before the next releases, so we use 4.8.1, 4.7.7,
4.4.24, and 4.1.34 as upper bounds (exclusive).
Fall-back to the non-NMI-safe trace clock for those kernel versions.
We simply discard events from NMI context with a in_nmi() check,
as we did before Linux 3.17.
Link: http://lkml.kernel.org/r/1475636148-26539-1-git-send-email-john.stultz@linaro.org
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Simon Marchi [Tue, 4 Oct 2016 21:07:05 +0000 (17:07 -0400)]
Add support for i2c tracepoints
This patch teaches lttng-modules about the i2c tracepoints in the Linux
kernel.
It contains the following tracepoints:
* i2c_write
* i2c_read
* i2c_reply
* i2c_result
I translated the fields and assignments from the kernel's
include/trace/events/i2c.h as well as I could. I also tried building
this module against a kernel without CONFIG_I2C, and it built fine (the
required types are unconditionally defined). So I don't think any "#if
CONFIG_I2C" or similar are required.
A module parameter (extract_sensitive_payload) controls the extraction
of possibly sensitive data from events.
[ With edit by Mathieu Desnoyers. ]
Signed-off-by: Simon Marchi <simon.marchi@ericsson.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 3 Oct 2016 21:35:27 +0000 (17:35 -0400)]
Cleanup: makefile version checks with single "ge"
Version checks in makefiles should always be a disjunctive normal form
where the conjunctions consist of one or more "equals" comparisons and
at most a single greater-or-equal comparison.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 26 Sep 2016 17:37:50 +0000 (13:37 -0400)]
Performance: special-case NULL in lttng_strlen_user_inatomic
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 16:30:00 +0000 (12:30 -0400)]
Fix: lttng_inline_memcpy does not take a __user argument
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 16:27:01 +0000 (12:27 -0400)]
Performance: implement lttng_inline_memcpy
Because all length parameters received for serializing data coming from
applications go through a callback, they are never constant, and it
hurts performance to perform a call to memcpy each time.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 16:02:25 +0000 (12:02 -0400)]
Performance: cache the backend pages pointer in context
Getting the backend pages pointer requires pointer chasing through the
ring buffer backend tables. Cache the current value so it can be re-used
for all backend write operations writing fields for the same event.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 15:11:48 +0000 (11:11 -0400)]
Cleanup: libringbuffer: remove duplicate pointer chasing in slow paths
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 15:06:10 +0000 (11:06 -0400)]
Performance: Only dereference commit index once
The commit fast path should not dereference the commit counter index
repeatedly for performance reasons.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 15:01:29 +0000 (11:01 -0400)]
Performance: Mark channel and buffer event disabled check unlikely
Channel and buffer are typically enabled when tracing, else the probes
would not be connected. Ensure the compiler optimizes for the right
usual case.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 15:00:08 +0000 (11:00 -0400)]
Performance: Relax atomicity constraints for crash handling
Use a store rather than a cmpxchg() for the update of the
sequential commit counter. This speeds up commit. The downside
is that short race windows between the if() check to see if the
counter is larger than the new value and the update could result
in the counter going backwards, in unlikely preemption or signal
delivery scenarios.
Accept that we may lose a few events in a crash dump for the
benefit of tracing speed.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 14:46:44 +0000 (10:46 -0400)]
Performance: mark ring buffer do_copy callers always inline
The underlying copy operation is more efficient if the size is a
constant, which only happens if this function is inlined in the caller.
Otherwise, we end up calling memcpy for each field.
Force inlining for performance reasons for:
- lib_ring_buffer_do_strcpy,
- lib_ring_buffer_do_strcpy_from_user_inatomic,
- lib_ring_buffer_copy_from_user_inatomic.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sun, 25 Sep 2016 14:43:22 +0000 (10:43 -0400)]
Performance: mark lib_ring_buffer_write always inline
The underlying copy operation is more efficient if the size is a
constant, which only happens if this function is inlined in the caller.
Otherwise, we end up calling memcpy for each field.
Force inlining for performance reasons.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 20 Sep 2016 14:29:33 +0000 (10:29 -0400)]
Kconfig: select TRACEPOINTS when built-in
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 9 Sep 2016 21:01:18 +0000 (17:01 -0400)]
Performance: disable event counting by default
Performance improvement changelog from lttng-ust, ported back to
lttng-modules:
Disable event counting in the ring buffer, which can count the number of
events produced per ring-buffer, as well as the number of events
overwritten in overwrite mode.
This feature is currently unused anyway: it is not saved in the ring
buffer header, nor made available to lttng-tools.
This saves 70 ns/event in lttng-ust on the ARM32 Cubietruck.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Thu, 1 Sep 2016 22:08:15 +0000 (18:08 -0400)]
Fix: handle large number of pages or subbuffers per buffer
Do no trigger kernel console warnings when we try to allocate too many
pages, or a too large kmalloc area for page array (within a subbuffer),
or a sub-buffer array (within a buffer).
Use vmalloc/vfree for the "pages" local variable used only during
allocation, which is an array of nr_subbuf * nr_pages_per_subbuf
pointers. This ensures we do not limit the overall buffer size due to
kmalloc limitations.
Fixes #1031
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Jonathan Rajotte [Thu, 1 Sep 2016 21:52:09 +0000 (17:52 -0400)]
Fix: unregister cpu hotplug notifier on buffer alloc error
The cpu hotplug notifier needs to be unregistered in the error path of
buffer allocation, else it eventually causes kernel OOPS when the kernel
accesses freed memory of the notifier block.
Fixes #1031
Signed-off-by: Jonathan Rajotte <jonathan.rajotte-julien@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Jérémie Galarneau [Wed, 31 Aug 2016 04:21:14 +0000 (00:21 -0400)]
Fix: sa_family is of type unsigned short
sa_family is an unsigned short in sockaddr definitions. For instance,
the kernel's unix_getname() function sets addrlen to sizeof(short) as it
only returns the socket's family.
Signed-off-by: Jérémie Galarneau <jeremie.galarneau@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Jérémie Galarneau [Wed, 31 Aug 2016 04:18:29 +0000 (00:18 -0400)]
Fix: check for sizeof sa_family to save sa_family in accept and connect
The check of addrlen >= sizeof(struct sockaddr) is too restrictive
and causes sa_family to not be saved in the case of AF_UNIX sockets
as the addrlen returned by the syscall may be only sizeof(short).
Individual checks per socket family are performed anyhow in the
switch case, making this safe.
Signed-off-by: Jérémie Galarneau <jeremie.galarneau@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 30 Aug 2016 22:42:10 +0000 (18:42 -0400)]
Fix: use printk_once() for wrapper warning messages
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 30 Aug 2016 21:32:35 +0000 (17:32 -0400)]
Fix: btrfs instrumentation for 4.8 kernel
Note: there are missing events.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 30 Aug 2016 21:13:37 +0000 (17:13 -0400)]
Fix: update mm_vmscan instrumentation for kernel 4.8
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 30 Aug 2016 21:02:09 +0000 (17:02 -0400)]
Fix: napi instrumentation for 4.8 kernels
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Tue, 30 Aug 2016 20:59:13 +0000 (16:59 -0400)]
Fix: update block instrumentation to compile on 4.8 kernels
These 2 upstream Linux commits break the block instrumentation in lttng
modules master:
https://github.com/torvalds/linux/commit/
4e1b2d52a80d79296a5d899d73249748dea71a53
https://github.com/torvalds/linux/commit/
288dab8a35a0bde426a09870943c8d3ee3a50dab
The errors are :
lttng-modules/probes/../instrumentation/events/lttng-module/block.h:35:13:
error: ‘REQ_DISCARD’ undeclared (first use in this function)
lttng-modules/probes/../instrumentation/events/lttng-module/block.h:41:14:
error: ‘REQ_SECURE’ undeclared (first use in this function)
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Jérémie Galarneau [Mon, 29 Aug 2016 20:02:10 +0000 (16:02 -0400)]
Cleanup: reuse code in accept() and accept4() instrumentation
Signed-off-by: Jérémie Galarneau <jeremie.galarneau@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Jérémie Galarneau [Mon, 29 Aug 2016 20:02:09 +0000 (16:02 -0400)]
Add x86-64 override for accept4 syscall
This patch adds an instrumentation override for the accept4() syscall
which is almost identical to accept(), except for an additional
"flags" parameter.
A follow-up patch refactors both overrides to minimize code
duplication as is done for the select/pselect6 overrides.
Signed-off-by: Jérémie Galarneau <jeremie.galarneau@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Thu, 25 Aug 2016 21:39:47 +0000 (17:39 -0400)]
Fix: timer wrapper: support kernels >= 4.8
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Sat, 16 Jul 2016 14:07:55 +0000 (10:07 -0400)]
Performance: split check deliver fast/slow paths
Performance improvement changelog from lttng-ust, ported back to
lttng-modules:
On ARMv7l (Cubietruck), the compiler generates a function call for each
lib_ring_buffer_check_deliver, even though it typically only do an
unlikely check. Split it into an inline fast path, and a function call
for the slow path. This brings a performance gain of about 500ns/event
on the Cubietruck.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 19 Aug 2016 14:58:26 +0000 (10:58 -0400)]
Fix: x86-64 accept instrumentation
The ipv4/ipv6 addr are output parameters.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Fri, 29 Jul 2016 14:52:47 +0000 (10:52 -0400)]
Fix: Add support for 4.6.4-rt8 kernel
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Thu, 28 Jul 2016 16:12:37 +0000 (12:12 -0400)]
Fix: update scsi instrumentation for 4.7+ kernels
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Thu, 28 Jul 2016 16:12:11 +0000 (12:12 -0400)]
Fix: Use fs_initcall instead of rootfs_initcall
The rootfs_initcall for drivers built as modules was only introduced in
kernel 3.14 by commit
b46d0c46ccaa366a5bb8ac709fdf2bcaa76221fd. Use
fs_initcall instead which comes just before and exists in older kernels.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Anders Wallin [Fri, 22 Jul 2016 14:10:47 +0000 (16:10 +0200)]
Fix: Add kernel configuration for lttng clock plugin
Only one lttng clock plugin can be used when building the lttng-modules
in the kernel. To make it possible to use a custom clock plugin it must
be possible to unconfigure the test clock plugin
Signed-off-by: Anders Wallin <wallinux@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Anders Wallin [Fri, 22 Jul 2016 13:56:59 +0000 (15:56 +0200)]
Fix: the clock plugin must be initiated before first use of the clock
When building lttng inside the kernel the clock plugin must be initated
before the rest of the lttng code. Moved the module_init to
rootfs_initcall. The functionality will not change when built as a
module.
Signed-off-by: Anders Wallin <wallinux@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 15 Jul 2016 15:29:33 +0000 (11:29 -0400)]
Fix: tests/Kbuild for older kernels
Older kernels (e.g. 2.6.38.8) don't seem to handle subdirectory in the
same way as recent kernels (e.g. 4.6). As a result, building LTTng
out-of-tree within a kernel modified to have LTTng as a built-in addon
fails with CONFIG_LTTNG=m.
$ make all O=../kernel_builddir
.....
CC [M] lttng/probes/lttng-kprobes.o
CC [M] lttng/probes/lttng-kretprobes.o
LD lttng/tests/built-in.o
CC [M] lttng/tests/probes/lttng-test.o
Assembler messages:
Fatal error: can't create lttng/tests/probes/lttng-test.o: No such
file or directory
/media/awallin/sda1/home/awallin/src/lttng-test/linux-2.6/scripts/Makefile.build:264:
recipe for target 'lttng/tests/probes/lttng-test.o' failed
make[3]: *** [lttng/tests/probes/lttng-test.o] Error 2
/media/awallin/sda1/home/awallin/src/lttng-test/linux-2.6/scripts/Makefile.build:403:
recipe for target 'lttng/tests' failed
make[2]: *** [lttng/tests] Error 2
/media/awallin/sda1/home/awallin/src/lttng-test/linux-2.6/Makefile:946:
recipe for target 'lttng' failed
make[1]: *** [lttng] Error 2
make[1]: Leaving directory
'/media/awallin/sda1/home/awallin/src/lttng-test/kernel_builddir'
Makefile:146: recipe for target 'sub-make' failed
make: *** [sub-make] Error 2
$tree ../kernel_builddir/lttng/tests/
../kernel_builddir/lttng/tests/
└── built-in.o
Reported-by: Anders Wallin <anders.wallin@windriver.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 15 Jul 2016 15:25:29 +0000 (11:25 -0400)]
Cleanup: __dynamic_len_idx set but not used warning
__dynamic_len_idx can be set but not used, which causes gcc to
emit a warning. Mark it as possibly unused.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Thu, 14 Jul 2016 15:56:12 +0000 (11:56 -0400)]
Cleanup: coding style and comments of net.h
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Geneviève Bastien [Tue, 12 Jul 2016 17:26:14 +0000 (13:26 -0400)]
net: Add TCP header data to net_* tracepoints
This patch adds the transport header variant field in the network types IPv4
and IPv6 using the corresponding next protocol field in both types. It adds
the detailed fields of the TCP header. Other transport headers are empty.
Example output from babeltrace:
[13:21:04.
392017771] (+0.
000588730) qemulttng0 net_dev_queue: { cpu_id = 1 },
{ skbaddr = 0xFFFF88003C8390E8, len = 370, name = "ens3",
network_header_type = ( "_ipv4" : container = 1 ),
network_header = { ipv4 = { version = 4, ihl = 5, tos = 16, tot_len = 356,
id = 0xFA2F, frag_off = 16384, ttl = 64,
protocol = ( "_tcp" : container = 6 ), checksum = 0x173C,
saddr_padding = { }, saddr = [ [0] = 10, [1] = 0, [2] = 10, [3] = 24 ],
daddr_padding = { }, daddr = [ [0] = 10, [1] = 0, [2] = 10, [3] = 1 ],
transport_header = { tcp = { source_port = 22, dest_port = 47500,
seq =
2784866942, ack_seq =
3750103494, data_offset = 8, reserved = 0,
flags = 0x11, window_size = 305, checksum = 0x296F, urg_ptr = 0 }
} } } }
[13:21:04.
429861105] (+0.
037671848) qemulttng0 net_dev_queue: { cpu_id = 1 },
{ skbaddr = 0xFFFF88003DBFC800, len = 86, name = "ens3",
network_header_type = ( "_ipv6" : container = 2 ),
network_header = { ipv6 = { version = 6, prio = 0, flow_lbl_padding = { },
flow_lbl = [ [0] = 0x84, [1] = 0x41, [2] = 0x6F ], payload_len = 32,
nexthdr = ( "_tcp" : container = 6 ), hop_limit = 64,
saddr_padding = { }, saddr = [ [0] = 0xFE80, [1] = 0x0, [2] = 0x0, [3] = 0x0,
[4] = 0x5054, [5] = 0xFF, [6] = 0xFE12, [7] = 0x3456 ],
daddr_padding = { }, daddr = [ [0] = 0xFE80, [1] = 0x0, [2] = 0x0, [3] = 0x0,
[4] = 0x5054, [5] = 0xFF, [6] = 0xFE22, [7] = 0x3344 ],
transport_header = { tcp = { source_port = 36972, dest_port = 22,
seq =
3750103494, ack_seq =
2784866942, data_offset = 0, reserved = 0,
flags = 0x11, window_size = 256, checksum = 0x39F, urg_ptr = 0 }
} } } }
[13:21:08.
195490138] (+3.
765629033) qemulttng0 net_if_receive_skb: { cpu_id = 0 },
{ skbaddr = 0xFFFF88003C0B8C00, len = 72, name = "ens3",
network_header_type = ( "_ipv6" : container = 2 ),
network_header = { ipv6 = { version = 6, prio = 0, flow_lbl_padding = { },
flow_lbl = [ [0] = 0x84, [1] = 0xCB, [2] = 0x7F ], payload_len = 32,
nexthdr = ( "_unknown" : container = 58 ), hop_limit = 255,
saddr_padding = { }, saddr = [ [0] = 0xFE80, [1] = 0x0, [2] = 0x0, [3] = 0x0,
[4] = 0x40C, [5] = 0xA9FF, [6] = 0xFEB5, [7] = 0xA75B ],
daddr_padding = { }, daddr = [ [0] = 0xFE80, [1] = 0x0, [2] = 0x0, [3] = 0x0,
[4] = 0x5054, [5] = 0xFF, [6] = 0xFE12, [7] = 0x3456 ],
transport_header = { unknown = { }
} } } }
Signed-off-by: Geneviève Bastien <gbastien+lttng@versatic.net>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Geneviève Bastien [Mon, 11 Jul 2016 13:34:02 +0000 (09:34 -0400)]
net: Add IPv4/IPv6 header data to net_* tracepoints
This patch adds an enum field for the type of network header and a variant
field for the details of IPv4 and IPv6 headers. Any other network header is
empty.
Example babeltrace output:
[16:04:07.
443810277] (+0.
110633000) host0 net_dev_queue: { cpu_id = 0 },
{ skbaddr = 0xFFFF88003D9F4B00, len = 1462, name = "ens3",
network_header_type = ( "_ipv4" : container = 1 ),
network_header = { ipv4 = { version = 4, ihl = 5, tos = 0, tot_len = 1448,
id = 0x0, frag_off = 16384, ttl = 64, protocol = 6, checksum = 0xB04,
saddr_padding = { }, saddr = [ [0] = 10, [1] = 0, [2] = 10, [3] = 24 ],
daddr_padding = { }, daddr = [ [0] = 10, [1] = 0, [2] = 12, [3] = 42 ] }
} }
[16:04:10.
452192462] (+0.
000283214) host0 net_if_receive_skb: { cpu_id = 0 },
{ skbaddr = 0xFFFF88003D9F4900, len = 118, name = "ens3",
network_header_type = ( "_ipv6" : container = 2 ),
network_header = { ipv6 = { version = 6, prio = 0, flow_lbl_padding = { },
flow_lbl = [ [0] = 0x88, [1] = 0x41, [2] = 0x6F ], payload_len = 64,
nexthdr = 58, hop_limit = 64, saddr_padding = { },
saddr = [ [0] = 0xFE80, [1] = 0x0, [2] = 0x0, [3] = 0x0, [4] = 0x5054,
[5] = 0xFF, [6] = 0xFE12, [7] = 0x3456 ],
daddr_padding = { },
daddr = [ [0] = 0xFE80, [1] = 0x0, [2] = 0x0, [3] = 0x0, [4] = 0x40C,
[5] = 0xA9FF, [6] = 0xFEB5, [7] = 0xA75B ] }
} }
Signed-off-by: Geneviève Bastien <gbastien+lttng@versatic.net>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Geneviève Bastien [Tue, 12 Jul 2016 16:21:51 +0000 (12:21 -0400)]
Fix: endianness for the container type of enum
If the endianness is specified for an enumeration, it should be written
in the metadata like for any other integer type.
Signed-off-by: Geneviève Bastien <gbastien+lttng@versatic.net>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 4 Jul 2016 22:46:16 +0000 (18:46 -0400)]
enumeration autoincrement: use if/else logic
Use if/else logic rather than "continue" on loop for clarity.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Philippe Proulx [Mon, 4 Jul 2016 19:16:10 +0000 (15:16 -0400)]
Cleanup trailing whitespaces
Signed-off-by: Philippe Proulx <eeppeliteloop@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Philippe Proulx [Mon, 4 Jul 2016 19:29:11 +0000 (15:29 -0400)]
lttng-test probe: test ctf_enum_auto()
Signed-off-by: Philippe Proulx <eeppeliteloop@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Philippe Proulx [Mon, 4 Jul 2016 19:14:54 +0000 (15:14 -0400)]
Add ctf_enum_auto() for autoincrementing enumeration values
Signed-off-by: Philippe Proulx <eeppeliteloop@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Thu, 14 Apr 2016 19:41:15 +0000 (15:41 -0400)]
Implement session statedump command
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 15 Jun 2016 18:39:41 +0000 (14:39 -0400)]
Fix: annotate bytecode interpreter for kernel stack validator
With gcc 6.1.1, kernel 4.6, with
CONFIG_STACK_VALIDATION=y, building lttng-modules master
at commit
6c09dd94 gives this warning:
lttng-modules/lttng-filter-interpreter.o: warning: objtool:
lttng_filter_interpret_bytecode()+0x58: sibling call from
callable instruction with changed frame pointer
This object implements a bytecode interpreter using an explicit
jump table.
If we define "INTERPRETER_USE_SWITCH" at the top of the file,
thus using the switch-case fallback implementation, the
warning vanishes.
We use an explicit jump table rather than a switch case whenever
possible for performance reasons.
Unfortunately objtool doesn't know how to validate this type of jump
table. So to avoid the warning we need to add an annotation to tell
objtool to ignore it.
Kernel developers has to annotate __bpf_prog_run() in the kernel for the
same reason.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Tue, 24 May 2016 20:11:11 +0000 (16:11 -0400)]
Update version to 2.9.0-pre
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 20 May 2016 01:32:06 +0000 (21:32 -0400)]
Fix: ring buffer: honor switch parameter type in remote switch
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 20 May 2016 01:31:07 +0000 (21:31 -0400)]
Fix: only flush non-metadata channels
Issue introduced by commit
"Fix: do not generate packet at destroy after stop".
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Fri, 20 May 2016 00:30:07 +0000 (20:30 -0400)]
Fix: don't perform extra flush on metadata channel
The metadata channel requires that the LTTng client layer and the ring
buffer keep a notion of the amount of data produced in the channel.
This issue has been introduced recently by commit
"Fix: flush empty packets on snapshot channel".
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Julien Desfossez [Mon, 16 May 2016 19:36:11 +0000 (15:36 -0400)]
select, poll and epoll_wait overrides on ARM 32-bit
The syscalls select, poll and epoll_wait exist on ARM 32-bit as well,
the overrides work on this platform.
Signed-off-by: Julien Desfossez <jdesfossez@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 18 May 2016 01:24:46 +0000 (21:24 -0400)]
Fix: flush empty packets on snapshot channel
Snapshot operation on a non-stopped stream should use a "final" flush to
ensure empty packets are flushed, so we gather timestamps at the moment
where the snapshot is taken. This is important for streams that have a
low amount of activity.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 18 May 2016 01:23:24 +0000 (21:23 -0400)]
Fix: do not generate packet at destroy after stop
In the following scenario:
- create, enable events (kernel),
- start
- ...
- stop (await for data_pending to complete)
- destroy
- rm the trace directory
We would expect that the "rm" operation would not conflict with the
consumer daemon trying to output data into the trace files, since the
"stop" operation ensured that there was no data_pending.
However, the "destroy" operation currently generates an extra packet
after the data_pending check. This causes the consumer daemon to try to
perform trace file rotation concurrently with the trace directory
removal in the scenario above, which triggers errors. The main reason
why this empty packet is generated by "destroy" is to deal with trace
start/stop scenario which would otherwise generate a completely empty
stream.
Therefore, introduce the concept of a "quiescent stream". It is
initialized at false on stream creation (first packet is empty). When
tracing is started, it is set to false (for cases of start/stop/start).
When tracing is stopped, if the stream is not quiescent, perform a
"final" flush (which will generate an empty packet if the current packet
was empty), and set quiescent to true. On "destroy" stream: if the
stream is not quiescent, perform a "final" flush, and set the quiescent
state to true.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 18 May 2016 01:16:22 +0000 (21:16 -0400)]
Fix: compat ioctl for flush/get metadata version
Unlike the non-compat version, the compat ioctl lttng ABI code for the
ring buffer flush operation does not invoke
lttng_metadata_output_channel before calling the ring buffer operation.
This could lead to incomplete metadata on 64-bit kernels running with
32-bit lttng userland.
There is also a discrepancy between the non-compat and compat code: the
GET_METADATA_VERSION operation is performed before calling the ring
buffer code. Ensure both non-compat and compat code are alike.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 16 May 2016 20:45:24 +0000 (16:45 -0400)]
Fix: ctf_string() should handle NULL pointers
The regmap instrumentation can send a NULL string (e.g. on ARM32).
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Mon, 16 May 2016 19:08:02 +0000 (15:08 -0400)]
Fix: portability: no arith on void pointer
Reported by cppcheck.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 11 May 2016 23:35:06 +0000 (19:35 -0400)]
Fix: add missing tests/Kbuild
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Mathieu Desnoyers [Wed, 11 May 2016 14:10:17 +0000 (10:10 -0400)]
Test clock override plugin
Fixes: #939
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
This page took 0.04572 seconds and 4 git commands to generate.