On Mon, 17 Jun 2024 10:46:28 +0900 "Masami Hiramatsu (Google)" <mhiramat@xxxxxxxxxx> wrote: > Hi, > > Here is the 11th version of the series to re-implement the fprobe on > function-graph tracer. The previous version is; > > https://lore.kernel.org/all/171509088006.162236.7227326999861366050.stgit@devnote2/ > > Most of the patches in the previous version (for multiple function graph > trace instance) are already merged via tracing/for-next. This version > is the remaining part, fprobe implement on fgraph. Basically just moves > on the updated fgraph implementation, and no major changes. > BTW, I've measured the performance improvement with this series using bpf bench. Before: kprobe-multi : 6.507 ± 0.065M/s kretprobe-multi: 3.518 ± 0.002M/s After: kprobe-multi : 6.183 ± 0.094M/s kretprobe-multi: 4.754 ± 0.004M/s So kprobe-multi (fprobe fentry probe) is slightly down (-5%), and kretprobe-multi (fprobe fexit probe) is improved (35%). I think this fentry probe regression may come from pushing all data on shadow stack. So it can be solved by using ftrace but not fgraph if fprobe does not have any fexit handler. Thank you, > Overview > -------- > This series rewrites the fprobe on this function-graph. > The purposes of this change are; > > 1) Remove dependency of the rethook from fprobe so that we can reduce > the return hook code and shadow stack. > > 2) Make 'ftrace_regs' the common trace interface for the function > boundary. > > 1) Currently we have 2(or 3) different function return hook codes, > the function-graph tracer and rethook (and legacy kretprobe). > But since this is redundant and needs double maintenance cost, > I would like to unify those. From the user's viewpoint, function- > graph tracer is very useful to grasp the execution path. For this > purpose, it is hard to use the rethook in the function-graph > tracer, but the opposite is possible. (Strictly speaking, kretprobe > can not use it because it requires 'pt_regs' for historical reasons.) > > 2) Now the fprobe provides the 'pt_regs' for its handler, but that is > wrong for the function entry and exit. Moreover, depending on the > architecture, there is no way to accurately reproduce 'pt_regs' > outside of interrupt or exception handlers. This means fprobe should > not use 'pt_regs' because it does not use such exceptions. > (Conversely, kprobe should use 'pt_regs' because it is an abstract > interface of the software breakpoint exception.) > > This series changes fprobe to use function-graph tracer for tracing > function entry and exit, instead of mixture of ftrace and rethook. > Unlike the rethook which is a per-task list of system-wide allocated > nodes, the function graph's ret_stack is a per-task shadow stack. > Thus it does not need to set 'nr_maxactive' (which is the number of > pre-allocated nodes). > Also the handlers will get the 'ftrace_regs' instead of 'pt_regs'. > Since eBPF mulit_kprobe/multi_kretprobe events still use 'pt_regs' as > their register interface, this changes it to convert 'ftrace_regs' to > 'pt_regs'. Of course this conversion makes an incomplete 'pt_regs', > so users must access only registers for function parameters or > return value. > > Design > ------ > Instead of using ftrace's function entry hook directly, the new fprobe > is built on top of the function-graph's entry and return callbacks > with 'ftrace_regs'. > > Since the fprobe requires access to 'ftrace_regs', the architecture > must support CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS and > CONFIG_HAVE_FTRACE_GRAPH_FUNC, which enables to call function-graph > entry callback with 'ftrace_regs', and also > CONFIG_HAVE_FUNCTION_GRAPH_FREGS, which passes the ftrace_regs to > return_to_handler. > > All fprobes share a single function-graph ops (means shares a common > ftrace filter) similar to the kprobe-on-ftrace. This needs another > layer to find corresponding fprobe in the common function-graph > callbacks, but has much better scalability, since the number of > registered function-graph ops is limited. > > In the entry callback, the fprobe runs its entry_handler and saves the > address of 'fprobe' on the function-graph's shadow stack as data. The > return callback decodes the data to get the 'fprobe' address, and runs > the exit_handler. > > The fprobe introduces two hash-tables, one is for entry callback which > searches fprobes related to the given function address passed by entry > callback. The other is for a return callback which checks if the given > 'fprobe' data structure pointer is still valid. Note that it is > possible to unregister fprobe before the return callback runs. Thus > the address validation must be done before using it in the return > callback. > > Download > -------- > This series can be applied against the ftrace/for-next branch in > linux-trace tree. > > This series can also be found below branch. > > https://git.kernel.org/pub/scm/linux/kernel/git/mhiramat/linux.git/log/?h=topic/fprobe-on-fgraph > > Thank you, > > --- > > Masami Hiramatsu (Google) (18): > tracing: Add a comment about ftrace_regs definition > tracing: Rename ftrace_regs_return_value to ftrace_regs_get_return_value > function_graph: Pass ftrace_regs to entryfunc > function_graph: Replace fgraph_ret_regs with ftrace_regs > function_graph: Pass ftrace_regs to retfunc > fprobe: Use ftrace_regs in fprobe entry handler > fprobe: Use ftrace_regs in fprobe exit handler > tracing: Add ftrace_partial_regs() for converting ftrace_regs to pt_regs > tracing: Add ftrace_fill_perf_regs() for perf event > tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS > bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled > ftrace: Add CONFIG_HAVE_FTRACE_GRAPH_FUNC > fprobe: Rewrite fprobe on function-graph tracer > tracing/fprobe: Remove nr_maxactive from fprobe > selftests: ftrace: Remove obsolate maxactive syntax check > selftests/ftrace: Add a test case for repeating register/unregister fprobe > Documentation: probes: Update fprobe on function-graph tracer > fgraph: Skip recording calltime/rettime if it is not nneeded > > > Documentation/trace/fprobe.rst | 42 + > arch/arm64/Kconfig | 3 > arch/arm64/include/asm/ftrace.h | 47 + > arch/arm64/kernel/asm-offsets.c | 12 > arch/arm64/kernel/entry-ftrace.S | 32 + > arch/arm64/kernel/ftrace.c | 20 + > arch/loongarch/Kconfig | 4 > arch/loongarch/include/asm/ftrace.h | 32 - > arch/loongarch/kernel/asm-offsets.c | 12 > arch/loongarch/kernel/ftrace_dyn.c | 10 > arch/loongarch/kernel/mcount.S | 17 - > arch/loongarch/kernel/mcount_dyn.S | 14 > arch/powerpc/Kconfig | 1 > arch/powerpc/include/asm/ftrace.h | 15 > arch/powerpc/kernel/trace/ftrace.c | 2 > arch/powerpc/kernel/trace/ftrace_64_pg.c | 10 > arch/riscv/Kconfig | 3 > arch/riscv/include/asm/ftrace.h | 26 - > arch/riscv/kernel/ftrace.c | 17 + > arch/riscv/kernel/mcount.S | 24 - > arch/s390/Kconfig | 3 > arch/s390/include/asm/ftrace.h | 39 + > arch/s390/kernel/asm-offsets.c | 6 > arch/s390/kernel/mcount.S | 9 > arch/x86/Kconfig | 4 > arch/x86/include/asm/ftrace.h | 37 + > arch/x86/kernel/ftrace.c | 50 +- > arch/x86/kernel/ftrace_32.S | 15 > arch/x86/kernel/ftrace_64.S | 17 - > include/linux/fprobe.h | 57 +- > include/linux/ftrace.h | 136 ++++ > kernel/trace/Kconfig | 23 + > kernel/trace/bpf_trace.c | 19 - > kernel/trace/fgraph.c | 96 ++- > kernel/trace/fprobe.c | 637 ++++++++++++++------ > kernel/trace/ftrace.c | 6 > kernel/trace/trace.h | 6 > kernel/trace/trace_fprobe.c | 147 ++--- > kernel/trace/trace_functions_graph.c | 10 > kernel/trace/trace_irqsoff.c | 6 > kernel/trace/trace_probe_tmpl.h | 2 > kernel/trace/trace_sched_wakeup.c | 6 > kernel/trace/trace_selftest.c | 11 > lib/test_fprobe.c | 51 -- > samples/fprobe/fprobe_example.c | 4 > .../test.d/dynevent/add_remove_fprobe_repeat.tc | 19 + > .../ftrace/test.d/dynevent/fprobe_syntax_errors.tc | 4 > 47 files changed, 1145 insertions(+), 618 deletions(-) > create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_repeat.tc > > -- > Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx> > -- Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
