8da3821ba5
This patch creates a section in the kernel called "__mcount_loc".
This will hold a list of pointers to the mcount relocation for
each call site of mcount.
For example:
objdump -dr init/main.o
[...]
Disassembly of section .text:
0000000000000000 <do_one_initcall>:
0: 55 push %rbp
[...]
000000000000017b <init_post>:
17b: 55 push %rbp
17c: 48 89 e5 mov %rsp,%rbp
17f: 53 push %rbx
180: 48 83 ec 08 sub $0x8,%rsp
184: e8 00 00 00 00 callq 189 <init_post+0xe>
185: R_X86_64_PC32 mcount+0xfffffffffffffffc
[...]
We will add a section to point to each function call.
.section __mcount_loc,"a",@progbits
[...]
.quad .text + 0x185
[...]
The offset to of the mcount call site in init_post is an offset from
the start of the section, and not the start of the function init_post.
The mcount relocation is at the call site 0x185 from the start of the
.text section.
.text + 0x185 == init_post + 0xa
We need a way to add this __mcount_loc section in a way that we do not
lose the relocations after final link. The .text section here will
be attached to all other .text sections after final link and the
offsets will be meaningless. We need to keep track of where these
.text sections are.
To do this, we use the start of the first function in the section.
do_one_initcall. We can make a tmp.s file with this function as a reference
to the start of the .text section.
.section __mcount_loc,"a",@progbits
[...]
.quad do_one_initcall + 0x185
[...]
Then we can compile the tmp.s into a tmp.o
gcc -c tmp.s -o tmp.o
And link it into back into main.o.
ld -r main.o tmp.o -o tmp_main.o
mv tmp_main.o main.o
But we have a problem. What happens if the first function in a section
is not exported, and is a static function. The linker will not let
the tmp.o use it. This case exists in main.o as well.
Disassembly of section .init.text:
0000000000000000 <set_reset_devices>:
0: 55 push %rbp
1: 48 89 e5 mov %rsp,%rbp
4: e8 00 00 00 00 callq 9 <set_reset_devices+0x9>
5: R_X86_64_PC32 mcount+0xfffffffffffffffc
The first function in .init.text is a static function.
00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 t set_reset_devices
The lowercase 't' means that set_reset_devices is local and is not exported.
If we simply try to link the tmp.o with the set_reset_devices we end
up with two symbols: one local and one global.
.section __mcount_loc,"a",@progbits
.quad set_reset_devices + 0x10
00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 t set_reset_devices
U set_reset_devices
We still have an undefined reference to set_reset_devices, and if we try
to compile the kernel, we will end up with an undefined reference to
set_reset_devices, or even worst, it could be exported someplace else,
and then we will have a reference to the wrong location.
To handle this case, we make an intermediate step using objcopy.
We convert set_reset_devices into a global exported symbol before linking
it with tmp.o and set it back afterwards.
00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 T set_reset_devices
00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 T set_reset_devices
00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 t set_reset_devices
Now we have a section in main.o called __mcount_loc that we can place
somewhere in the kernel using vmlinux.ld.S and access it to convert
all these locations that call mcount into nops before starting SMP
and thus, eliminating the need to do this with kstop_machine.
Note, A well documented perl script (scripts/recordmcount.pl) is used
to do all this in one location.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
145 lines
4.0 KiB
Plaintext
145 lines
4.0 KiB
Plaintext
#
|
|
# Architectures that offer an FTRACE implementation should select HAVE_FTRACE:
|
|
#
|
|
config HAVE_FTRACE
|
|
bool
|
|
|
|
config HAVE_DYNAMIC_FTRACE
|
|
bool
|
|
|
|
config HAVE_FTRACE_MCOUNT_RECORD
|
|
bool
|
|
|
|
config TRACER_MAX_TRACE
|
|
bool
|
|
|
|
config TRACING
|
|
bool
|
|
select DEBUG_FS
|
|
select STACKTRACE
|
|
select TRACEPOINTS
|
|
|
|
config FTRACE
|
|
bool "Kernel Function Tracer"
|
|
depends on HAVE_FTRACE
|
|
select FRAME_POINTER
|
|
select TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
help
|
|
Enable the kernel to trace every kernel function. This is done
|
|
by using a compiler feature to insert a small, 5-byte No-Operation
|
|
instruction to the beginning of every kernel function, which NOP
|
|
sequence is then dynamically patched into a tracer call when
|
|
tracing is enabled by the administrator. If it's runtime disabled
|
|
(the bootup default), then the overhead of the instructions is very
|
|
small and not measurable even in micro-benchmarks.
|
|
|
|
config IRQSOFF_TRACER
|
|
bool "Interrupts-off Latency Tracer"
|
|
default n
|
|
depends on TRACE_IRQFLAGS_SUPPORT
|
|
depends on GENERIC_TIME
|
|
depends on HAVE_FTRACE
|
|
select TRACE_IRQFLAGS
|
|
select TRACING
|
|
select TRACER_MAX_TRACE
|
|
help
|
|
This option measures the time spent in irqs-off critical
|
|
sections, with microsecond accuracy.
|
|
|
|
The default measurement method is a maximum search, which is
|
|
disabled by default and can be runtime (re-)started
|
|
via:
|
|
|
|
echo 0 > /debugfs/tracing/tracing_max_latency
|
|
|
|
(Note that kernel size and overhead increases with this option
|
|
enabled. This option and the preempt-off timing option can be
|
|
used together or separately.)
|
|
|
|
config PREEMPT_TRACER
|
|
bool "Preemption-off Latency Tracer"
|
|
default n
|
|
depends on GENERIC_TIME
|
|
depends on PREEMPT
|
|
depends on HAVE_FTRACE
|
|
select TRACING
|
|
select TRACER_MAX_TRACE
|
|
help
|
|
This option measures the time spent in preemption off critical
|
|
sections, with microsecond accuracy.
|
|
|
|
The default measurement method is a maximum search, which is
|
|
disabled by default and can be runtime (re-)started
|
|
via:
|
|
|
|
echo 0 > /debugfs/tracing/tracing_max_latency
|
|
|
|
(Note that kernel size and overhead increases with this option
|
|
enabled. This option and the irqs-off timing option can be
|
|
used together or separately.)
|
|
|
|
config SYSPROF_TRACER
|
|
bool "Sysprof Tracer"
|
|
depends on X86
|
|
select TRACING
|
|
help
|
|
This tracer provides the trace needed by the 'Sysprof' userspace
|
|
tool.
|
|
|
|
config SCHED_TRACER
|
|
bool "Scheduling Latency Tracer"
|
|
depends on HAVE_FTRACE
|
|
select TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
select TRACER_MAX_TRACE
|
|
help
|
|
This tracer tracks the latency of the highest priority task
|
|
to be scheduled in, starting from the point it has woken up.
|
|
|
|
config CONTEXT_SWITCH_TRACER
|
|
bool "Trace process context switches"
|
|
depends on HAVE_FTRACE
|
|
select TRACING
|
|
select MARKERS
|
|
help
|
|
This tracer gets called from the context switch and records
|
|
all switching of tasks.
|
|
|
|
config DYNAMIC_FTRACE
|
|
bool "enable/disable ftrace tracepoints dynamically"
|
|
depends on FTRACE
|
|
depends on HAVE_DYNAMIC_FTRACE
|
|
default y
|
|
help
|
|
This option will modify all the calls to ftrace dynamically
|
|
(will patch them out of the binary image and replaces them
|
|
with a No-Op instruction) as they are called. A table is
|
|
created to dynamically enable them again.
|
|
|
|
This way a CONFIG_FTRACE kernel is slightly larger, but otherwise
|
|
has native performance as long as no tracing is active.
|
|
|
|
The changes to the code are done by a kernel thread that
|
|
wakes up once a second and checks to see if any ftrace calls
|
|
were made. If so, it runs stop_machine (stops all CPUS)
|
|
and modifies the code to jump over the call to ftrace.
|
|
|
|
config FTRACE_MCOUNT_RECORD
|
|
def_bool y
|
|
depends on DYNAMIC_FTRACE
|
|
depends on HAVE_FTRACE_MCOUNT_RECORD
|
|
|
|
config FTRACE_SELFTEST
|
|
bool
|
|
|
|
config FTRACE_STARTUP_TEST
|
|
bool "Perform a startup test on ftrace"
|
|
depends on TRACING
|
|
select FTRACE_SELFTEST
|
|
help
|
|
This option performs a series of startup tests on ftrace. On bootup
|
|
a series of tests are made to verify that the tracer is
|
|
functioning properly. It will do tests on all the configured
|
|
tracers of ftrace.
|