Storing this value will help prevent unwinders from getting out of sync
with the function graph tracer ret_stack. Now instead of needing a
stateful iterator, they can compare the return address pointer to find
the right ret_stack entry.
Note that an array of 50 ftrace_ret_stack structs is allocated for every
task. So when an arch implements this, it will add either 200 or 400
bytes of memory usage per task (depending on whether it's a 32-bit or
64-bit platform).
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Byungchul Park <byungchul.park@lge.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nilay Vaish <nilayvaish@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a95cfcc39e8f26b89a430c56926af0bb217bc0a1.1471607358.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull MIPS updates from Ralf Baechle:
"This is the main pull request for 3.17. It contains:
- misc Cavium Octeon, BCM47xx, BCM63xx and Alchemy updates
- MIPS ptrace updates and cleanups
- various fixes that will also go to -stable
- a number of cleanups and small non-critical fixes.
- NUMA support for the Loongson 3.
- more support for MSA
- support for MAAR
- various FP enhancements and fixes"
* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (139 commits)
MIPS: jz4740: remove unnecessary null test before debugfs_remove
MIPS: Octeon: remove unnecessary null test before debugfs_remove_recursive
MIPS: ZBOOT: implement stack protector in compressed boot phase
MIPS: mipsreg: remove duplicate MIPS_CONF4_FTLBSETS_SHIFT
MIPS: Bonito64: remove a duplicate define
MIPS: Malta: initialise MAARs
MIPS: Initialise MAARs
MIPS: detect presence of MAARs
MIPS: define MAAR register accessors & bits
MIPS: mark MSA experimental
MIPS: Don't build MSA support unless it can be used
MIPS: consistently clear MSA flags when starting & copying threads
MIPS: 16 byte align MSA vector context
MIPS: disable preemption whilst initialising MSA
MIPS: ensure MSA gets disabled during boot
MIPS: fix read_msa_* & write_msa_* functions on non-MSA toolchains
MIPS: fix MSA context for tasks which don't use FP first
MIPS: init upper 64b of vector registers when MSA is first used
MIPS: save/disable MSA in lose_fpu
MIPS: preserve scalar FP CSR when switching vector context
...
Dynamic tracing of kernel modules is broken on 32-bit MIPS. When modules
are loaded, the kernel crashes when dynamic tracing is enabled with:
cd /sys/kernel/debug/tracing
echo > set_ftrace_filter
echo function > current_tracer
1) arch/mips/kernel/ftrace.c
When the kernel boots, or when a module is initialized, ftrace_make_nop()
modifies every _mcount call site to eliminate the ftrace overhead.
However, when ftrace is later enabled for a call site, ftrace_make_call()
does not currently restore the _mcount call correctly for module call sites.
Added ftrace_modify_code_2r() and modified ftrace_make_call() to fix this.
2) arch/mips/kernel/mcount.S
_mcount assembly routine is supposed to have the caller's _mcount call site
address in register a0. However, a0 is currently not calculated correctly for
module call sites. a0 should be (ra - 20) or (ra - 24), depending on whether
the kernel was built with KBUILD_MCOUNT_RA_ADDRESS or not.
This fix has been tested on Broadcom BMIPS5000 processor. Dynamic tracing
now works for both built-in functions and module functions.
Signed-off-by: Petri Gynther <pgynther@google.com>
Cc: linux-mips@linux-mips.org
Cc: rostedt@goodmis.org
Cc: alcooperx@gmail.com
Cc: cminyard@mvista.com
Patchwork: https://patchwork.linux-mips.org/patch/7476/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
ftrace_stop() is going away as it disables parts of function tracing
that affects users that should not be affected. But ftrace_graph_stop()
is built on ftrace_stop(). Here's another example of killing all of
function tracing because something went wrong with function graph
tracing.
Instead of disabling all users of function tracing on function graph
error, disable only function graph tracing. To do this, the arch code
must call ftrace_graph_is_dead() before it implements function graph.
Cc: Ralf Baechle <ralf@linux-mips.org>
Tested-by: James Hogan <james.hogan@imgtec.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
But there were a few features that were added.
Uprobes now work with event triggers and multi buffers.
Uprobes have support under ftrace and perf.
The big feature is that the function tracer can now be used within the
multi buffer instances. That is, you can now trace some functions
in one buffer, others in another buffer, all functions in a third buffer
and so on. They are basically agnostic from each other. This only
works for the function tracer and not for the function graph trace,
although you can have the function graph tracer running in the top level
buffer (or any tracer for that matter) and have different function tracing
going on in the sub buffers.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTOthtAAoJEKQekfcNnQGu5c8H/Ana/U+0tmksp1dbHkRHsKSH
+Fsv4Jeu8gf1NaFKHEhkUTcFtnzE6qAPV2VCrcJwXbhAhhwZm+LjrnWdoy3215S3
cQW4LftLEonh2cM36Cos74TulMEYN6XmL6dQZV+CILKQkDrWU4qJjQ64okXEkqrd
9iG3p/mSXyvJcmnyg61ALnMOhZDLsXY3djBhWBPhiTPGS6BRb9zh4Pmw6Zv0n2rJ
U93Gt/3AQrv1ybu73dUxqP0abp60oXOiWoF/R2jcbKqIM+K9RPJX79unCV3jq3u9
f+6jMlB9PgAMqQj6ihJdwxKDDuzwyrVdEPnsgvl4jarCBCtVVwhKedBaKN/KS8k=
=HdXY
-----END PGP SIGNATURE-----
Merge tag 'trace-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing updates from Steven Rostedt:
"Most of the changes were largely clean ups, and some documentation.
But there were a few features that were added:
Uprobes now work with event triggers and multi buffers and have
support under ftrace and perf.
The big feature is that the function tracer can now be used within the
multi buffer instances. That is, you can now trace some functions in
one buffer, others in another buffer, all functions in a third buffer
and so on. They are basically agnostic from each other. This only
works for the function tracer and not for the function graph trace,
although you can have the function graph tracer running in the top
level buffer (or any tracer for that matter) and have different
function tracing going on in the sub buffers"
* tag 'trace-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (45 commits)
tracing: Add BUG_ON when stack end location is over written
tracepoint: Remove unused API functions
Revert "tracing: Move event storage for array from macro to standalone function"
ftrace: Constify ftrace_text_reserved
tracepoints: API doc update to tracepoint_probe_register() return value
tracepoints: API doc update to data argument
ftrace: Fix compilation warning about control_ops_free
ftrace/x86: BUG when ftrace recovery fails
ftrace: Warn on error when modifying ftrace function
ftrace: Remove freelist from struct dyn_ftrace
ftrace: Do not pass data to ftrace_dyn_arch_init
ftrace: Pass retval through return in ftrace_dyn_arch_init()
ftrace: Inline the code from ftrace_dyn_table_alloc()
ftrace: Cleanup of global variables ftrace_new_pgs and ftrace_update_cnt
tracing: Evaluate len expression only once in __dynamic_array macro
tracing: Correctly expand len expressions from __dynamic_array macro
tracing/module: Replace include of tracepoint.h with jump_label.h in module.h
tracing: Fix event header migrate.h to include tracepoint.h
tracing: Fix event header writeback.h to include tracepoint.h
tracing: Warn if a tracepoint is not set via debugfs
...
When flushing the icache, make sure the address limit is correct
so the appropriate 'cache' instruction will be used. This has no
impact on cores operating in non-eva mode. However, when EVA is
enabled, we ensure that 'cache' will be used instead of 'cachee'.
Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
In 32-bit mode, the start address passed to flush_icache_range is
shifted by 4 bytes before the second safe_store_code() call.
This causes system crash from time to time because the first 4 bytes
might not be flushed properly. This bug exists since linux-3.8.
Also remove obsoleted comment while at it.
Signed-off-by: Viller Hsiao <villerhsiao@gmail.com>
Cc: linux-mips@linux-mips.org
Cc: rostedt@goodmis.org
Cc: fweisbec@gmail.com
Cc: mingo@redhat.com
Cc: Qais.Yousef@imgtec.com
Patchwork: https://patchwork.linux-mips.org/patch/6586/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
As the data parameter is not really used by any ftrace_dyn_arch_init,
remove that from ftrace_dyn_arch_init. This also removes the addr
local variable from ftrace_init which is now unused.
Note the documentation was imprecise as it did not suggest to set
(*data) to 0.
Link: http://lkml.kernel.org/r/1393268401-24379-4-git-send-email-jslaby@suse.cz
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: linux-arch@vger.kernel.org
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
No architecture uses the "data" parameter in ftrace_dyn_arch_init() in any
way, it just sets the value to 0. And this is used as a return value
in the caller -- ftrace_init, which just checks the retval against
zero.
Note there is also "return 0" in every ftrace_dyn_arch_init. So it is
enough to check the retval and remove all the indirect sets of data on
all archs.
Link: http://lkml.kernel.org/r/1393268401-24379-3-git-send-email-jslaby@suse.cz
Cc: linux-arch@vger.kernel.org
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
This gets us rid of the hard to maintain table of the number of syscall
arguments and paves the way for further restructuring of the syscall
code.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
arch_ftrace_update_code and ftrace_modify_all_code are only
available if CONFIG_DYNAMIC_FTRACE is selected.
Fixes the following build problem on MIPS randconfig:
arch/mips/kernel/ftrace.c: In function 'arch_ftrace_update_code':
arch/mips/kernel/ftrace.c:31:2: error: implicit declaration of function
'ftrace_modify_all_code' [-Werror=implicit-function-declaration]
Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Acked-by: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/5435/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Having received another series of whitespace patches I decided to do this
once and for all rather than dealing with this kind of patches trickling
in forever.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Function tracing is currently broken for all 32 bit MIPS platforms.
When tracing is enabled, the kernel immediately hangs on boot.
This is a result of commit b732d439cb
that changes the kernel/trace/Kconfig file so that is no longer
forces FRAME_POINTER when FUNCTION_TRACING is enabled.
MIPS frame pointers are generally considered to be useless because
they cannot be used to unwind the stack. Unfortunately the MIPS
function tracing code has bugs that are masked by the use of frame
pointers. This commit fixes the bugs so that MIPS frame pointers
don't need to be enabled.
The bugs are a result of the odd calling sequence used to call the trace
routine. This calling sequence is inserted into every traceable function
when the tracing CONFIG option is enabled. This sequence is generated
for 32bit MIPS platforms by the compiler via the "-pg" flag.
Part of the sequence is "addiu sp,sp,-8" in the delay slot after every
call to the trace routine "_mcount" (some legacy thing where 2 arguments
used to be pushed on the stack). The _mcount routine is expected to
adjust the sp by +8 before returning. So when not disabled, the original
jalr and addiu will be there, so _mcount has to adjust sp.
The problem is that when tracing is disabled for a function, the
"jalr _mcount" instruction is replaced with a nop, but the
"addiu sp,sp,-8" is still executed and the stack pointer is left
trashed. When frame pointers are enabled the problem is masked
because any access to the stack is done through the frame
pointer and the stack pointer is restored from the frame pointer when
the function returns.
This patch writes two nops starting at the address of the "jalr _mcount"
instruction whenever tracing is disabled. This means that the
"addiu sp,sp.-8" will be converted to a nop along with the "jalr". When
disabled, there will be two nops.
This is SMP safe because the first time this happens is during
ftrace_init() which is before any other processor has been started.
Subsequent calls to enable/disable tracing when other CPUs ARE running
will still be safe because the enable will only change the first nop
to a "jalr" and the disable, while writing 2 nops, will only be changing
the "jalr". This patch also stops using stop_machine() to call the
tracer enable/disable routines and calls them directly because the
routines are SMP safe.
When the kernel first boots we have to be able to handle the gcc
generated jalr, addui sequence until ftrace_init gets a chance to run
and change the sequence. At this point mcount just adjusts the stack
and returns. When ftrace_init runs, we convert the jalr/addui to nops.
Then whenever tracing is enabled we convert the first nop to a "jalr
mcount+8". The mcount+8 entry point skips the stack adjust.
[ralf@linux-mips.org: Folded in Steven Rostedt's build fix.]
Signed-off-by: Al Cooper <alcooperx@gmail.com>
Cc: rostedt@goodmis.org
Cc: ddaney.cavm@gmail.com
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/4806/
Patchwork: https://patchwork.linux-mips.org/patch/4841/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
arch/mips/kernel/ftrace.c: In function ‘ftrace_get_parent_ra_addr’:
arch/mips/kernel/ftrace.c:212: error: implicit declaration of function ‘in_kernel_space’
arch/mips/kernel/ftrace.c: In function ‘prepare_ftrace_return’:
arch/mips/kernel/ftrace.c:314: error: ‘MCOUNT_OFFSET_INSNS’ undeclared (first use in this function)
arch/mips/kernel/ftrace.c:314: error: (Each undeclared identifier is reported only once
arch/mips/kernel/ftrace.c:314: error: for each function it appears in.)
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
To: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2634/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The current code is abusing the uasm interface by passing jump target
addresses with high bits set. Mask the addresses to avoid annoying
messages at boot time.
Signed-off-by: David Daney <ddaney@caviumnetworks.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Patchwork: https://patchwork.linux-mips.org/patch/1922/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
trace.func should be set to the recorded ip of the mcount calling site
in the __mcount_loc section to filter the function entries configured
through the tracing/set_graph_function interface, but before, this is
set to the self_ra(the return address of mcount), which has made
set_graph_function not work as expected.
This fixes it via calculating the right recorded ip in the __mcount_loc
section and assign it to trace.func.
Reported-by: Zhiping Zhong <xzhong86@163.com>
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Sergei Shtylyov <sshtylyov@mvista.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2017/
Signed-off-by: Ralf Baechle <ralf@duck.linux-mips.net>
This moves the comments out of ftrace_make_nop() and cleans it. At the
same time, a macro MCOUNT_OFFSET_INSNS is defined for sharing with the
next patch.
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2008/
Signed-off-by: Ralf Baechle <ralf@duck.linux-mips.net>
The old prepare_ftrace_return() for MIPS is confused and have introduced
some problem. This patch cleans up the names of the arguments, variables
and related functions.
For MIPS, the 2nd argument of prepare_ftrace_return() is not really the
'selfpc' described in ftrace-design.txt but instead it is the self
return address. This did break the compatibility of the generic
interface but really reduced one unneeded calculation for to get the
current function name, the parent return address and the self return
address are enough, no need to tranform the self return address to the
self address.
But set_graph_function of function graph tracer is an exception, it does
need the 2nd argument of prepare_ftrace_return() as 'selfpc', for it
will use 'selfpc' to match user's configuration of function graph
entries, but in reality, it doesn't need the 'selfpc' but the recorded
ip address of the mcount calling site in the __mcount_loc section. So,
the 2nd argument of prepare_ftrace_return() is not important, the real
requirement is the right recorded ip address should be calculated and
assign to trace.func, this will be fixed in the next patches.
Reported-by: Zhiping Zhong <xzhong86@163.com>
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2007/
Signed-off-by: Ralf Baechle <ralf@duck.linux-mips.net>
The old in_module() may not work in some situations(e.g. when module &
kernel are in the same address space when CONFIG_MAPPED_KERNEL=y), The
in_kernel_space() is more generic and it is also easy to be implemented
via cloning the existing core_kernel_text(), so, replace the in_module()
with in_kernel_space().
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2005/
Signed-off-by: Ralf Baechle <ralf@duck.linux-mips.net>
This simply moves the "ip-=4" statement down to the end of the do { ...
} while (...); loop, which reduces one unneeded subtration and the
subsequent memory loading and comparison.
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/2006/
Signed-off-by: Ralf Baechle <ralf@duck.linux-mips.net>
This patch adds an inline function in_module() to check which space the
instruction pointer in, kernel space or module space.
Note: This will not work when the kernel space and module space are the
same. If they are the same, we need to modify scripts/recordmcount.pl,
ftrace_make_nop/call() and the other related parts to ensure the
enabling/disabling of the calling site to _mcount is right for both
kernel and module.
[Ralf: It also is still incorrect for some 64-bit kernels.]
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: linux-mips <linux-mips@linux-mips.org>
Cc: David Daney <david.s.daney@gmail.com>
Patchwork: http://patchwork.linux-mips.org/patch/1232/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
With the help of uasm this patch encodes the instructions of the dynamic
function tracer in ftrace_dyn_arch_init() when initializing it.
As a result we can remove the dynamic encoding of instructions in
ftrace_make_nop()/call(), ftrace_enable_ftrace_graph_caller() and remove
the macro jump_insn_encode() and at last this reduce the overhead of
dynamic Function Tracer. This also is cleaner.
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: linux-mips <linux-mips@linux-mips.org>
Cc: David Daney <david.s.daney@gmail.com>
Patchwork: http://patchwork.linux-mips.org/patch/1230/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This patch adds some cleanups of the instructions:
o use macros instead of magic numbers
o use macros instead of variables to reduce some overhead
o add new macro for the jal instruction
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: linux-mips <linux-mips@linux-mips.org>
Cc: David Daney <david.s.daney@gmail.com>
Patchwork: http://patchwork.linux-mips.org/patch/1229/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
For 32-bit kernel the -mmcount-ra-address option of gcc 4.5 emits one
extra instruction before calling to _mcount so we need to use a different
"b 1f" for it.
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: linux-mips <linux-mips@linux-mips.org>
Cc: David Daney <david.s.daney@gmail.com>
Patchwork: http://patchwork.linux-mips.org/patch/1228/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
That thread "MIPS: Add option to pass return address location to
_mcount" from "David Daney <ddaney@caviumnetworks.com>" have added a new
option -mmcount-ra-address to gcc(4.5) for MIPS to transfer the location
of the return address to _mcount.
Benefit from this new feature, function graph tracer on MIPS will be
easier and safer to hijack the return address of the kernel function,
which will save some overhead and make the whole thing more reliable.
In this patch, at first, try to enable the option -mmcount-ra-address in
arch/mips/Makefile with cc-option, if gcc support it, it will be
enabled, otherwise, no side effect.
and then, we need to support this new option of gcc 4.5 and also support
the old gcc versions.
with _mcount in the old gcc versions, it's not easy to get the location
of return address(tracing: add function graph tracer support for MIPS),
so, we do it in a C function: ftrace_get_parent_addr(ftrace.c), but
with -mmcount-ra-address, only several instructions need to get what
we want, so, I put into asm(mcount.S). and also, as the $12(t0) is
used by -mmcount-ra-address for transferring the localtion of return
address to _mcount, we need to save it into the stack and restore it
when enabled dynamic function tracer, 'Cause we have called
"ftrace_call" before "ftrace_graph_caller", which may destroy
$12(t0).
(Thanks to David for providing that -mcount-ra-address and giving the
idea of KBUILD_MCOUNT_RA_ADDRESS, both of them have made the whole
thing more beautiful!)
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: zhangfx@lemote.com
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/681/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
When remove the -fno-omit-frame-pointer, gcc will not save the frame
pointer for us, we need to save one ourselves.
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: zhangfx@lemote.com
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/679/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This patch make function graph tracer work with dynamic function tracer.
To share the source code of dynamic function tracer(MCOUNT_SAVE_REGS),
and avoid restoring the whole saved registers, we need to restore the ra
register from the stack.
(NOTE: This not work with 32bit! need to ensure why!)
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: zhangfx@lemote.com
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/678/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The implementation of function graph tracer for MIPS is a little
different from X86.
in MIPS, gcc(with -pg) only transfer the caller's return address(at) and
the _mcount's return address(ra) to us.
For the kernel part without -mlong-calls:
move at, ra
jal _mcount
For the module part with -mlong-calls:
lui v1, hi16bit_of_mcount
addiu v1, v1, low16bit_of_mcount
move at, ra
jal _mcount
Without -mlong-calls,
if the function is a leaf, it will not save the return address(ra):
ffffffff80101298 <au1k_wait>:
ffffffff80101298: 67bdfff0 daddiu sp,sp,-16
ffffffff8010129c: ffbe0008 sd s8,8(sp)
ffffffff801012a0: 03a0f02d move s8,sp
ffffffff801012a4: 03e0082d move at,ra
ffffffff801012a8: 0c042930 jal ffffffff8010a4c0 <_mcount>
ffffffff801012ac: 00020021 nop
so, we can hijack it directly in _mcount, but if the function is non-leaf, the
return address is saved in the stack.
ffffffff80133030 <copy_process>:
ffffffff80133030: 67bdff50 daddiu sp,sp,-176
ffffffff80133034: ffbe00a0 sd s8,160(sp)
ffffffff80133038: 03a0f02d move s8,sp
ffffffff8013303c: ffbf00a8 sd ra,168(sp)
ffffffff80133040: ffb70098 sd s7,152(sp)
ffffffff80133044: ffb60090 sd s6,144(sp)
ffffffff80133048: ffb50088 sd s5,136(sp)
ffffffff8013304c: ffb40080 sd s4,128(sp)
ffffffff80133050: ffb30078 sd s3,120(sp)
ffffffff80133054: ffb20070 sd s2,112(sp)
ffffffff80133058: ffb10068 sd s1,104(sp)
ffffffff8013305c: ffb00060 sd s0,96(sp)
ffffffff80133060: 03e0082d move at,ra
ffffffff80133064: 0c042930 jal ffffffff8010a4c0 <_mcount>
ffffffff80133068: 00020021 nop
but we can not get the exact stack address(which saved ra) directly in
_mcount, we need to search the content of at register in the stack space
or search the "s{d,w} ra, offset(sp)" instruction in the text. 'Cause we
can not prove there is only a match in the stack space, so, we search
the text instead.
as we can see, if the first instruction above "move at, ra" is not a
store instruction, there should be a leaf function, so we hijack the at
register directly via putting &return_to_handler into it, otherwise, we
search the "s{d,w} ra, offset(sp)" instruction to get the stack offset,
and then the stack address. we use the above copy_process() as an
example, we at last find "ffbf00a8", 0xa8 is the stack offset, we plus
it with s8(fp), that is the stack address, we hijack the content via
writing the &return_to_handler in.
If with -mlong-calls, since there are two more instructions above "move
at, ra", so, we can move the pointer to the position above "lui v1,
hi16bit_of_mcount".
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: zhangfx@lemote.com
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/677/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
With dynamic function tracer, by default, _mcount is defined as an
"empty" function, it returns directly without any more action . When
enabling it in user-space, it will jump to a real tracing
function(ftrace_caller), and do the real job for us.
Differ from the static function tracer, dynamic function tracer provides
two functions ftrace_make_call()/ftrace_make_nop() to enable/disable the
tracing of some indicated kernel functions(set_ftrace_filter).
In the -v4 version, the implementation of this support is basically the same as
X86 version does: _mcount is implemented as an empty function and ftrace_caller
is implemented as a real tracing function respectively.
But in this version, to support module tracing with the help of
-mlong-calls in arch/mips/Makefile:
MODFLAGS += -mlong-calls.
The stuff becomes a little more complex. We need to cope with two
different type of calling to _mcount.
For the kernel part, the calling to _mcount(result of "objdump -hdr
vmlinux"). is like this:
108: 03e0082d move at,ra
10c: 0c000000 jal 0 <fpcsr_pending>
10c: R_MIPS_26 _mcount
10c: R_MIPS_NONE *ABS*
10c: R_MIPS_NONE *ABS*
110: 00020021 nop
For the module with -mlong-calls, it looks like this:
c: 3c030000 lui v1,0x0
c: R_MIPS_HI16 _mcount
c: R_MIPS_NONE *ABS*
c: R_MIPS_NONE *ABS*
10: 64630000 daddiu v1,v1,0
10: R_MIPS_LO16 _mcount
10: R_MIPS_NONE *ABS*
10: R_MIPS_NONE *ABS*
14: 03e0082d move at,ra
18: 0060f809 jalr v1
In the kernel version, there is only one "_mcount" string for every
kernel function, so, we just need to match this one in mcount_regex of
scripts/recordmcount.pl, but in the module version, we need to choose
one of the two to match. Herein, I choose the first one with
"R_MIPS_HI16 _mcount".
and In the kernel verion, without module tracing support, we just need
to replace "jal _mcount" by "jal ftrace_caller" to do real tracing, and
filter the tracing of some kernel functions via replacing it by a nop
instruction.
but as we have described before, the instruction "jal ftrace_caller" only left
32bit length for the address of ftrace_caller, it will fail when calling from
the module space. so, herein, we must replace something else.
the basic idea is loading the address of ftrace_caller to v1 via changing these
two instructions:
lui v1,0x0
addiu v1,v1,0
If we want to enable the tracing, we need to replace the above instructions to:
lui v1, HI_16BIT_ftrace_caller
addiu v1, v1, LOW_16BIT_ftrace_caller
If we want to stop the tracing of the indicated kernel functions, we
just need to replace the "jalr v1" to a nop instruction. but we need to
replace two instructions and encode the above two instructions
oursevles.
Is there a simpler solution? Yes! Here it is, in this version, we put _mcount
and ftrace_caller together, which means the address of _mcount and
ftrace_caller is the same:
_mcount:
ftrace_caller:
j ftrace_stub
nop
...(do real tracing here)...
ftrace_stub:
jr ra
move ra, at
By default, the kernel functions call _mcount, and then jump to ftrace_stub and
return. and when we want to do real tracing, we just need to remove that "j
ftrace_stub", and it will run through the two "nop" instructions and then do
the real tracing job.
what about filtering job? we just need to do this:
lui v1, hi_16bit_of_mcount <--> b 1f (0x10000004)
addiu v1, v1, low_16bit_of_mcount
move at, ra
jalr v1
nop
1f: (rec->ip + 12)
In linux-mips64, there will be some local symbols, whose name are
prefixed by $L, which need to be filtered. thanks goes to Steven for
writing the mips64-specific function_regex.
In a conclusion, with RISC, things becomes easier with such a "stupid"
trick, RISC is something like K.I.S.S, and also, there are lots of
"simple" tricks in the whole ftrace support, thanks goes to Steven and
the other folks for providing such a wonderful tracing framework!
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Nicholas Mc Guire <der.herr@hofr.at>
Cc: zhangfx@lemote.com
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/675/
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
