linux/kernel/trace
Steven Rostedt (Red Hat) 6224beb12e tracing: Have branch tracer use recursive field of task struct
Fengguang Wu's tests triggered a bug in the branch tracer's start up
test when CONFIG_DEBUG_PREEMPT set. This was because that config
adds some debug logic in the per cpu field, which calls back into
the branch tracer.

The branch tracer has its own recursive checks, but uses a per cpu
variable to implement it. If retrieving the per cpu variable calls
back into the branch tracer, you can see how things will break.

Instead of using a per cpu variable, use the trace_recursion field
of the current task struct. Simply set a bit when entering the
branch tracing and clear it when leaving. If the bit is set on
entry, just don't do the tracing.

There's also the case with lockdep, as the local_irq_save() called
before the recursion can also trigger code that can call back into
the function. Changing that to a raw_local_irq_save() will protect
that as well.

This prevents the recursion and the inevitable crash that follows.

Link: http://lkml.kernel.org/r/20150630141803.GA28071@wfg-t540p.sh.intel.com

Cc: stable@vger.kernel.org # 3.10+
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Tested-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-07-08 11:53:45 -04:00
..
blktrace.c This patch series contains several clean ups and even a new trace clock 2015-06-26 14:02:43 -07:00
bpf_trace.c bpf: let kprobe programs use bpf_get_smp_processor_id() helper 2015-06-15 15:53:50 -07:00
ftrace.c Some clean ups and small fixes, but the biggest change is the addition 2015-04-14 10:49:03 -07:00
Kconfig Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2015-04-14 14:37:47 -07:00
Makefile bpf: Fix the build on BPF_SYSCALL=y && !CONFIG_TRACING kernels, make it more configurable 2015-04-02 16:28:06 +02:00
power-traces.c PM / sleep: export suspend_resume trace event 2015-01-30 02:10:41 +01:00
ring_buffer.c ring-buffer: Add enum names for the context levels 2015-05-29 10:39:08 -04:00
ring_buffer_benchmark.c This patch series contains several clean ups and even a new trace clock 2015-06-26 14:02:43 -07:00
rpm-traces.c PM / Runtime: Introduce trace points for tracing rpm_* functions 2011-09-27 22:53:27 +02:00
trace.c tracing: Rename FTRACE_EVENT_FL_* flags to EVENT_FILE_FL_* 2015-05-13 15:24:57 -04:00
trace.h tracing: Have branch tracer use recursive field of task struct 2015-07-08 11:53:45 -04:00
trace_benchmark.c tracing: Only calculate stats of tracepoint benchmarks for 2^32 times 2014-06-06 00:41:38 -04:00
trace_benchmark.h tracing: Add tracepoint benchmark tracepoint 2014-05-29 22:49:54 -04:00
trace_branch.c tracing: Have branch tracer use recursive field of task struct 2015-07-08 11:53:45 -04:00
trace_clock.c tracing: Export tracing clock functions 2015-05-12 15:56:57 -04:00
trace_entries.h tracing: %pF is only for function pointers 2015-03-25 08:57:22 -04:00
trace_event_perf.c tracing: Rename ftrace_event_{call,class} to trace_event_{call,class} 2015-05-13 14:06:10 -04:00
trace_events.c tracing: Rename FTRACE_EVENT_FL_* flags to EVENT_FILE_FL_* 2015-05-13 15:24:57 -04:00
trace_events_filter.c This patch series contains several clean ups and even a new trace clock 2015-06-26 14:02:43 -07:00
trace_events_filter_test.h tracing/filter: Add startup tests for events filter 2011-08-19 14:35:59 -04:00
trace_events_trigger.c tracing: Rename ftrace_raw_##call event structures to trace_event_raw_##call 2015-05-13 21:48:40 -04:00
trace_export.c tracing: Rename ftrace_event_{call,class} to trace_event_{call,class} 2015-05-13 14:06:10 -04:00
trace_functions.c tracing/trivial: Fix typos and make an int into a bool 2014-11-20 10:05:36 -05:00
trace_functions_graph.c tracing: Rename ftrace_event_{call,class} to trace_event_{call,class} 2015-05-13 14:06:10 -04:00
trace_irqsoff.c tracing: Remove unneeded includes of debugfs.h and fs.h 2015-01-22 11:19:48 -05:00
trace_kdb.c KGDB/KDB fixes and cleanups 2015-01-09 20:51:10 -08:00
trace_kprobe.c tracing: Rename ftrace_trigger_soft_disabled() to trace_trigger_soft_disabled() 2015-05-13 15:25:39 -04:00
trace_mmiotrace.c tracing: Rename ftrace_event_{call,class} to trace_event_{call,class} 2015-05-13 14:06:10 -04:00
trace_nop.c tracing: Remove unneeded includes of debugfs.h and fs.h 2015-01-22 11:19:48 -05:00
trace_output.c tracing: Rename ftrace_event_name() to trace_event_name() 2015-05-13 14:20:14 -04:00
trace_output.h tracing: Rename (un)register_ftrace_event() to (un)register_trace_event() 2015-05-13 14:05:14 -04:00
trace_printk.c tracing: Use IS_ERR() check for return value of tracing_init_dentry() 2015-01-22 11:19:49 -05:00
trace_probe.c trace: Don't use __weak in header files 2015-03-25 08:57:23 -04:00
trace_probe.h tracing: Rename ftrace_event_{call,class} to trace_event_{call,class} 2015-05-13 14:06:10 -04:00
trace_sched_switch.c tracing: Remove unneeded includes of debugfs.h and fs.h 2015-01-22 11:19:48 -05:00
trace_sched_wakeup.c tracing: Rename ftrace_event_{call,class} to trace_event_{call,class} 2015-05-13 14:06:10 -04:00
trace_selftest.c Seems that Peter Zijlstra added a new check that is making old 2014-10-12 07:28:55 -04:00
trace_selftest_dynamic.c
trace_seq.c tracing: use %*pb[l] to print bitmaps including cpumasks and nodemasks 2015-02-13 21:21:37 -08:00
trace_stack.c tracing: remove use of seq_printf return value 2015-04-15 16:35:25 -07:00
trace_stat.c tracing: Convert the tracing facility over to use tracefs 2015-02-03 12:48:41 -05:00
trace_stat.h
trace_syscalls.c tracing: Rename ftrace_trigger_soft_disabled() to trace_trigger_soft_disabled() 2015-05-13 15:25:39 -04:00
trace_uprobe.c tracing: Rename ftrace_trigger_soft_disabled() to trace_trigger_soft_disabled() 2015-05-13 15:25:39 -04:00