Currently ftrace_graph_ent{,_entry} and ftrace_graph_ret{,_entry} struct
can have padding bytes at the end due to alignment in 64-bit data type.
As these data are recorded so frequently, those paddings waste
non-negligible space. As the ring buffer maintains alignment properly
for each architecture, just to remove the extra padding using 'packed'
attribute.
ftrace_graph_ent_entry: 24 -> 20
ftrace_graph_ret_entry: 48 -> 44
Also I moved the 'overrun' field in struct ftrace_graph_ret to minimize
the padding in the middle.
Tested on x86_64 only.
Link: http://lkml.kernel.org/r/1467197808-13578-1-git-send-email-namhyung@kernel.org
Cc: Ingo Molnar <mingo@kernel.org>
Cc: linux-arch@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Commit 345ddcc882 ("ftrace: Have set_ftrace_pid use the bitmap like events
do") placed ftrace_init_tracefs into the instance creation, and encapsulated
the top level updating with an if conditional, as the top level only gets
updated at boot up. Unfortunately, this triggers section mismatch errors as
the init functions are called from a function that can be called later, and
the section mismatch logic is unaware of the if conditional that would
prevent it from happening at run time.
To make everyone happy, create a separate ftrace_init_tracefs_toplevel()
routine that only gets called by init functions, and this will be what calls
other init functions for the toplevel directory.
Link: http://lkml.kernel.org/r/20160704102139.19cbc0d9@gandalf.local.home
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 345ddcc882 ("ftrace: Have set_ftrace_pid use the bitmap like events do")
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Function graph tracer currently ignores filters if tracing_thresh is set.
For example, even if set_ftrace_pid is set, then its ignored if tracing_thresh
set, resulting in all processes being traced.
To fix this, we reuse the same entry function as when tracing_thresh is not
set and do everything as in the regular case except for writing the function entry
to the ring buffer.
Link: http://lkml.kernel.org/r/1466228694-2677-1-git-send-email-agnel.joel@gmail.com
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Joel Fernandes <agnel.joel@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
# echo 1 > options/stacktrace
# echo 1 > events/sched/sched_switch/enable
# cat trace
<idle>-0 [002] d..2 1982.525169: <stack trace>
=> save_stack_trace
=> __ftrace_trace_stack
=> trace_buffer_unlock_commit_regs
=> event_trigger_unlock_commit
=> trace_event_buffer_commit
=> trace_event_raw_event_sched_switch
=> __schedule
=> schedule
=> schedule_preempt_disabled
=> cpu_startup_entry
=> start_secondary
The above shows that we are seeing 6 functions before ever making it to the
caller of the sched_switch event.
# echo stacktrace > events/sched/sched_switch/trigger
# cat trace
<idle>-0 [002] d..3 2146.335208: <stack trace>
=> trace_event_buffer_commit
=> trace_event_raw_event_sched_switch
=> __schedule
=> schedule
=> schedule_preempt_disabled
=> cpu_startup_entry
=> start_secondary
The stacktrace trigger isn't as bad, because it adds its own skip to the
stacktracing, but still has two events extra.
One issue is that if the stacktrace passes its own "regs" then there should
be no addition to the skip, as the regs will not include the functions being
called. This was an issue that was fixed by commit 7717c6be69 ("tracing:
Fix stacktrace skip depth in trace_buffer_unlock_commit_regs()" as adding
the skip number for kprobes made the probes not have any stack at all.
But since this is only an issue when regs is being used, a skip should be
added if regs is NULL. Now we have:
# echo 1 > options/stacktrace
# echo 1 > events/sched/sched_switch/enable
# cat trace
<idle>-0 [000] d..2 1297.676333: <stack trace>
=> __schedule
=> schedule
=> schedule_preempt_disabled
=> cpu_startup_entry
=> rest_init
=> start_kernel
=> x86_64_start_reservations
=> x86_64_start_kernel
# echo stacktrace > events/sched/sched_switch/trigger
# cat trace
<idle>-0 [002] d..3 1370.759745: <stack trace>
=> __schedule
=> schedule
=> schedule_preempt_disabled
=> cpu_startup_entry
=> start_secondary
And kprobes are not touched.
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Previously, mmio_print_pcidev() put "user" addresses in the trace buffer.
On most architectures, these are the same as CPU physical addresses, but on
microblaze, mips, powerpc, and sparc, they may be something else, typically
a raw BAR value (a bus address as opposed to a CPU address).
Always expose the CPU physical address to avoid this arch-dependent
behavior.
This change should have no user-visible effect because this file currently
depends on CONFIG_HAVE_MMIOTRACE_SUPPORT, which is only defined for x86,
and pci_resource_to_user() is a no-op on x86.
Link: http://lkml.kernel.org/r/20160511190657.5898.4248.stgit@bhelgaas-glaptop2.roam.corp.google.com
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Because tracepoint callbacks are done with preemption enabled, the trace
events are always called with preempt disable due to the
rcu_read_lock_sched_notrace() in __DO_TRACE(). This causes the preempt count
shown in the recorded trace event to be inaccurate. It is always one more
that what the preempt_count was when the tracepoint was called.
If CONFIG_PREEMPT is enabled, subtract 1 from the preempt_count before
recording it in the trace buffer.
Link: http://lkml.kernel.org/r/20160525132537.GA10808@linutronix.de
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Add sample code to test trace_printk(). The trace_printk() functions should
never be used in production code. This makes testing it a bit more
difficult. Having a sample module that can test use cases of trace_printk()
can help out.
Currently it just tests trace_printk() where it will be converted into:
trace_bputs()
trace_puts()
trace_bprintk()
as well as staying as the normal _trace_printk().
It also tests its use in interrupt context as that will test the auxilery
buffers.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Currently, the trace_printk code chooses which static buffer to use based
on what type of atomic context (NMI, IRQ, etc) it's in. Simplify the
code and make it more robust: simply count the nesting depth and choose
a buffer based on the current nesting depth.
The new code will only drop an event if we nest more than 4 deep,
and the old code was guaranteed to malfunction if that happened.
Link: http://lkml.kernel.org/r/07ab03aecfba25fcce8f9a211b14c9c5e2865c58.1464289095.git.luto@kernel.org
Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
ftrace is very quick to give up on saving the task command line (see
`trace_save_cmdline()`). The workaround for events which really care
about the command line is to explicitly assign it as part of the entry.
However, this doesn't work for kprobe events, as there's no
straightforward way to get access to current->comm. Add a kprobe/uprobe
event variable $comm which provides exactly that.
Link: http://lkml.kernel.org/r/f59b472033b943a370f5f48d0af37698f409108f.1465435894.git.osandov@fb.com
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Convert set_ftrace_pid to use the bitmap like set_event_pid does. This
allows for instances to use the pid filtering as well, and will allow for
function-fork option to set if the children of a traced function should be
traced or not.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
The addition of PIDs into a pid_list via the write operation of
set_event_pid is a bit complex. The same operation will be needed for
function tracing pids. Move the code into its own generic function in
trace.c, so that we can avoid duplication of this code.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
To allow other aspects of ftrace to use the pid_list logic, we need to reuse
the seq_file functions. Making the generic part into functions that can be
called by other files will help in this regard.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
As the filtered_pid functions are going to be used by function tracer as
well as trace_events, move the code into the generic trace.c file.
The functions moved are:
trace_find_filtered_pid()
trace_ignore_this_task()
trace_filter_add_remove_task()
Kernel Doc text was also added.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Make the functions used for pid filtering global for tracing, such that the
function tracer can use the pid code as well.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
When histograms are not configured in the kernel, the ftracetest histogram
selftests should return "unsupported" and not "Failed". To detect this, the
test scripts have:
FEATURE=`grep hist events/sched/sched_process_fork/trigger`
if [ -z "$FEATURE" ]; then
echo "hist trigger is not supported"
exit_unsupported
fi
The problem is that '-e' is in effect and any error will cause the program
to terminate. The grep for 'hist' fails, because it is not compiled it (thus
unsupported), but because grep has an error code for failing to find the
string, it causes the program to terminate, and is marked as a failed test.
Namhyung Kim recommended to test for the "hist" file located in
events/sched/sched_process_fork/hist instead, as it is more inline with the
other checks. As the hist file is only created if the histogram feature is
enabled, that is a valid check.
Link: http://lkml.kernel.org/r/20160523151538.4ea9ce0c@gandalf.local.home
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Fixes: 76929ab51f ("kselftests/ftrace: Add hist trigger testcases")
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
If a task uses a non constant string for the format parameter in
trace_printk(), then the trace_printk_fmt variable is set to NULL. This
variable is then saved in the __trace_printk_fmt section.
The function hold_module_trace_bprintk_format() checks to see if duplicate
formats are used by modules, and reuses them if so (saves them to the list
if it is new). But this function calls lookup_format() that does a strcmp()
to the value (which is now NULL) and can cause a kernel oops.
This wasn't an issue till 3debb0a9dd ("tracing: Fix trace_printk() to print
when not using bprintk()") which added "__used" to the trace_printk_fmt
variable, and before that, the kernel simply optimized it out (no NULL value
was saved).
The fix is simply to handle the NULL pointer in lookup_format() and have the
caller ignore the value if it was NULL.
Link: http://lkml.kernel.org/r/1464769870-18344-1-git-send-email-zhengjun.xing@intel.com
Reported-by: xingzhen <zhengjun.xing@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Fixes: 3debb0a9dd ("tracing: Fix trace_printk() to print when not using bprintk()")
Cc: stable@vger.kernel.org # v3.5+
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Pull thermal management fixes from Zhang Rui:
- fix an ordering issue in cpu cooling that cooling device is
registered before it's ready (freq_table being populated).
(Lukasz Luba)
- fix a missing comment update (Caesar Wang)
* 'for-rc' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux:
thermal: add the note for set_trip_temp
thermal: cpu_cooling: fix improper order during initialization
Pull block layer fixes from Jens Axboe:
"A small collection of fixes for the current series. This contains:
- Two fixes for xen-blkfront, from Bob Liu.
- A bug fix for NVMe, releasing only the specific resources we
requested.
- Fix for a debugfs flags entry for nbd, from Josef.
- Plug fix from Omar, fixing up a case of code being switched between
two functions.
- A missing bio_put() for the new discard callers of
submit_bio_wait(), fixing a regression causing a leak of the bio.
From Shaun.
- Improve dirty limit calculation precision in the writeback code,
fixing a case where setting a limit lower than 1% of memory would
end up being zero. From Tejun"
* 'for-linus' of git://git.kernel.dk/linux-block:
NVMe: Only release requested regions
xen-blkfront: fix resume issues after a migration
xen-blkfront: don't call talk_to_blkback when already connected to blkback
nbd: pass the nbd pointer for flags debugfs
block: missing bio_put following submit_bio_wait
blk-mq: really fix plug list flushing for nomerge queues
writeback: use higher precision calculation in domain_dirty_limits()
Pull GPIO fixes from Linus Walleij:
"A new bunch of GPIO fixes for v4.7.
This time I am very grateful that Ricardo Ribalda Delgado went in and
fixed my stupid refcounting mistakes in the removal path for GPIO
chips. I had a feeling something was wrong here and so it was. It
exploded on OMAP and it fixes their problem. Now it should be (more)
solid.
The rest i compilation, Kconfig and driver fixes. Some tagged for
stable.
Summary:
- Fix a NULL pointer dereference when we are searching the GPIO
device list but one of the devices have been removed (struct
gpio_chip pointer is NULL).
- Fix unaligned reference counters: we were ending on +3 after all
said and done. It should be 0. Remove an extraneous get_device(),
and call cdev_del() followed by device_del() in gpiochip_remove()
instead and the count goes to zero and calls the release() function
properly.
- Fix a compile warning due to a missing #include in the OF/device
tree portions.
- Select ANON_INODES for GPIOLIB, we're using that for our character
device. Some randconfig tests disclosed the problem.
- Make sure the Zynq driver clock runs also without CONFIG_PM enabled
- Fix an off-by-one error in the 104-DIO-48E driver
- Fix warnings in bcm_kona_gpio_reset()"
* tag 'gpio-v4.7-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
gpio: bcm-kona: fix bcm_kona_gpio_reset() warnings
gpio: select ANON_INODES
gpio: include <linux/io-mapping.h> in gpiolib-of
gpiolib: Fix unaligned used of reference counters
gpiolib: Fix NULL pointer deference
gpio: zynq: initialize clock even without CONFIG_PM
gpio: 104-dio-48e: Fix control port offset computation off-by-one error
Pull SCSI fixes from James Bottomley:
"Two current fixes:
- one affects Qemu CD ROM emulation, which stopped working after the
updates in SCSI to require VPD pages from all conformant devices.
Fix temporarily by blacklisting Qemu (we can relax later when they
come into compliance).
- The other is a fix to the optimal transfer size. We set up a
minefield for ourselves by being confused about whether the limits
are in bytes or sectors (SCSI optimal is in blocks and the queue
parameter is in bytes).
This tries to fix the problem (wrong setting for queue limits
max_sectors) and make the problem more obvious by introducing a
wrapper function"
* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
sd: Fix rw_max for devices that report an optimal xfer size
scsi: Add QEMU CD-ROM to VPD Inquiry Blacklist
Pull i2c fixes from Wolfram Sang:
- a bigger fix for i801 to finally be able to be loaded on some
machines again
- smaller driver fixes
- documentation update because of a renamed file
* 'i2c/for-current' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
i2c: mux: reg: Provide of_match_table
i2c: mux: refer to i2c-mux.txt
i2c: octeon: Avoid printk after too long SMBUS message
i2c: octeon: Missing AAK flag in case of I2C_M_RECV_LEN
i2c: i801: Allow ACPI SystemIO OpRegion to conflict with PCI BAR
Pull DeviceTree fixes from Rob Herring:
- fix unflatten_dt_nodes when dad parameter is set.
- add vendor prefixes for TechNexion and UniWest
- documentation fix for Marvell BT
- OF IRQ kerneldoc fixes
- restrict CMA alignment adjustments to non dma-coherent
- a couple of warning fixes in reserved-memory code
- DT maintainers updates
* tag 'devicetree-fixes-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux:
drivers: of: add definition of early_init_dt_alloc_reserved_memory_arch
drivers/of: Fix depth for sub-tree blob in unflatten_dt_nodes()
drivers: of: Fix of_pci.h header guard
dt-bindings: Add vendor prefix for TechNexion
of: add vendor prefix for UniWest
dt: bindings: fix documentation for MARVELL's bt-sd8xxx wireless device
of: add missing const for of_parse_phandle_with_args() in !CONFIG_OF
of: silence warnings due to max() usage
drivers: of: of_reserved_mem: fixup the CMA alignment not to affect dma-coherent
of: irq: fix of_irq_get[_byname]() kernel-doc
MAINTAINERS: DeviceTree maintainer updates
Namhyung Kim
Tom Zanussi
Wei Yongjun
Steven Rostedt (Red Hat)
Joel Fernandes
Bjorn Helgaas
Andy Lutomirski
Omar Sandoval
Linus Torvalds