Re: [PATCH v5 13/17] powerpc64/ftrace: Support .text larger than 32MB with out-of-line stubs

[Masahiro Yamada]

On Mon, Sep 16, 2024 at 5:58 AM Hari Bathini <hbathini@xxxxxxxxxxxxx> wrote:
>
> From: Naveen N Rao <naveen@xxxxxxxxxx>
>
> We are restricted to a .text size of ~32MB when using out-of-line
> function profile sequence. Allow this to be extended up to the previous
> limit of ~64MB by reserving space in the middle of .text.
>
> A new config option CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE is
> introduced to specify the number of function stubs that are reserved in
> .text. On boot, ftrace utilizes stubs from this area first before using
> the stub area at the end of .text.
>
> A ppc64le defconfig has ~44k functions that can be traced. A more
> conservative value of 32k functions is chosen as the default value of
> PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE so that we do not allot more space
> than necessary by default. If building a kernel that only has 32k
> trace-able functions, we won't allot any more space at the end of .text
> during the pass on vmlinux.o. Otherwise, only the remaining functions
> get space for stubs at the end of .text. This default value should help
> cover a .text size of ~48MB in total (including space reserved at the
> end of .text which can cover up to 32MB), which should be sufficient for
> most common builds. For a very small kernel build, this can be set to 0.
> Or, this can be bumped up to a larger value to support vmlinux .text
> size up to ~64MB.
>
> Signed-off-by: Naveen N Rao <naveen@xxxxxxxxxx>
> Signed-off-by: Hari Bathini <hbathini@xxxxxxxxxxxxx>
> ---
>
> Changes in v5:
> * num_ool_stubs_text_end used for setting up ftrace_ool_stub_text_end
>   set to zero instead of computing to some random negative value when
>   not required.
>
>  arch/powerpc/Kconfig                       | 12 ++++++++++++
>  arch/powerpc/include/asm/ftrace.h          |  6 ++++--
>  arch/powerpc/kernel/trace/ftrace.c         | 21 +++++++++++++++++----
>  arch/powerpc/kernel/trace/ftrace_entry.S   |  8 ++++++++
>  arch/powerpc/tools/Makefile                |  2 +-
>  arch/powerpc/tools/ftrace-gen-ool-stubs.sh | 16 ++++++++++++----
>  6 files changed, 54 insertions(+), 11 deletions(-)
>
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index bae96b65f295..a0ce00368bab 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -573,6 +573,18 @@ config PPC_FTRACE_OUT_OF_LINE
>         depends on PPC64
>         select ARCH_WANTS_PRE_LINK_VMLINUX
>
> +config PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE
> +       int "Number of ftrace out-of-line stubs to reserve within .text"
> +       default 32768 if PPC_FTRACE_OUT_OF_LINE
> +       default 0

This entry is meaningless when CONFIG_PPC_FTRACE_OUT_OF_LINE=n.

           depends on PPC_FTRACE_OUT_OF_LINE
           default 32768




> +       help
> +         Number of stubs to reserve for use by ftrace. This space is
> +         reserved within .text, and is distinct from any additional space
> +         added at the end of .text before the final vmlinux link. Set to
> +         zero to have stubs only be generated at the end of vmlinux (only
> +         if the size of vmlinux is less than 32MB). Set to a higher value
> +         if building vmlinux larger than 48MB.
> +
>  config HOTPLUG_CPU
>         bool "Support for enabling/disabling CPUs"
>         depends on SMP && (PPC_PSERIES || \
> diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
> index bdbafc668b20..28f3590ca780 100644
> --- a/arch/powerpc/include/asm/ftrace.h
> +++ b/arch/powerpc/include/asm/ftrace.h
> @@ -138,8 +138,10 @@ extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
>  struct ftrace_ool_stub {
>         u32     insn[4];
>  };
> -extern struct ftrace_ool_stub ftrace_ool_stub_text_end[], ftrace_ool_stub_inittext[];
> -extern unsigned int ftrace_ool_stub_text_end_count, ftrace_ool_stub_inittext_count;
> +extern struct ftrace_ool_stub ftrace_ool_stub_text_end[], ftrace_ool_stub_text[],
> +                             ftrace_ool_stub_inittext[];
> +extern unsigned int ftrace_ool_stub_text_end_count, ftrace_ool_stub_text_count,
> +                   ftrace_ool_stub_inittext_count;
>  #endif
>  void ftrace_free_init_tramp(void);
>  unsigned long ftrace_call_adjust(unsigned long addr);
> diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
> index 1fee074388cc..bee2c54a8c04 100644
> --- a/arch/powerpc/kernel/trace/ftrace.c
> +++ b/arch/powerpc/kernel/trace/ftrace.c
> @@ -168,7 +168,7 @@ static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_
>  static int ftrace_init_ool_stub(struct module *mod, struct dyn_ftrace *rec)
>  {
>  #ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
> -       static int ool_stub_text_end_index, ool_stub_inittext_index;
> +       static int ool_stub_text_index, ool_stub_text_end_index, ool_stub_inittext_index;
>         int ret = 0, ool_stub_count, *ool_stub_index;
>         ppc_inst_t inst;
>         /*
> @@ -191,9 +191,22 @@ static int ftrace_init_ool_stub(struct module *mod, struct dyn_ftrace *rec)
>                 ool_stub_index = &ool_stub_inittext_index;
>                 ool_stub_count = ftrace_ool_stub_inittext_count;
>         } else if (is_kernel_text(rec->ip)) {
> -               ool_stub = ftrace_ool_stub_text_end;
> -               ool_stub_index = &ool_stub_text_end_index;
> -               ool_stub_count = ftrace_ool_stub_text_end_count;
> +               /*
> +                * ftrace records are sorted, so we first use up the stub area within .text
> +                * (ftrace_ool_stub_text) before using the area at the end of .text
> +                * (ftrace_ool_stub_text_end), unless the stub is out of range of the record.
> +                */
> +               if (ool_stub_text_index >= ftrace_ool_stub_text_count ||
> +                   !is_offset_in_branch_range((long)rec->ip -
> +                                              (long)&ftrace_ool_stub_text[ool_stub_text_index])) {
> +                       ool_stub = ftrace_ool_stub_text_end;
> +                       ool_stub_index = &ool_stub_text_end_index;
> +                       ool_stub_count = ftrace_ool_stub_text_end_count;
> +               } else {
> +                       ool_stub = ftrace_ool_stub_text;
> +                       ool_stub_index = &ool_stub_text_index;
> +                       ool_stub_count = ftrace_ool_stub_text_count;
> +               }
>  #ifdef CONFIG_MODULES
>         } else if (mod) {
>                 ool_stub = mod->arch.ool_stubs;
> diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
> index 5b2fc6483dce..a6bf7f841040 100644
> --- a/arch/powerpc/kernel/trace/ftrace_entry.S
> +++ b/arch/powerpc/kernel/trace/ftrace_entry.S
> @@ -374,6 +374,14 @@ _GLOBAL(return_to_handler)
>         blr
>  #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
>
> +#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
> +SYM_DATA(ftrace_ool_stub_text_count, .long CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE)
> +
> +SYM_CODE_START(ftrace_ool_stub_text)
> +       .space CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE * FTRACE_OOL_STUB_SIZE
> +SYM_CODE_END(ftrace_ool_stub_text)
> +#endif
> +
>  .pushsection ".tramp.ftrace.text","aw",@progbits;
>  .globl ftrace_tramp_text
>  ftrace_tramp_text:
> diff --git a/arch/powerpc/tools/Makefile b/arch/powerpc/tools/Makefile
> index 3a389526498e..9eeb6edf02fe 100644
> --- a/arch/powerpc/tools/Makefile
> +++ b/arch/powerpc/tools/Makefile
> @@ -1,7 +1,7 @@
>  # SPDX-License-Identifier: GPL-2.0-or-later
>
>  quiet_cmd_gen_ftrace_ool_stubs = GEN     $@
> -      cmd_gen_ftrace_ool_stubs = $< vmlinux.o $@
> +      cmd_gen_ftrace_ool_stubs = $< $(CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE) vmlinux.o $@
>
>  $(obj)/.vmlinux.arch.S: $(src)/ftrace-gen-ool-stubs.sh vmlinux.o FORCE
>         $(call if_changed,gen_ftrace_ool_stubs)
> diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
> index 8e0a6d4ea202..d6bd834e0868 100755
> --- a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
> +++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
> @@ -8,8 +8,9 @@ is_enabled() {
>         grep -q "^$1=y" include/config/auto.conf
>  }
>
> -vmlinux_o=${1}
> -arch_vmlinux_S=${2}
> +vmlinux_o=${2}
> +arch_vmlinux_S=${3}
> +arch_vmlinux_o=$(dirname ${arch_vmlinux_S})/$(basename ${arch_vmlinux_S} .S).o


arch_vmlinux_o is not used in this script. Delete it.






>
>  RELOCATION=R_PPC64_ADDR64
>  if is_enabled CONFIG_PPC32; then
> @@ -21,15 +22,22 @@ num_ool_stubs_text=$(${CROSS_COMPILE}objdump -r -j __patchable_function_entries
>  num_ool_stubs_inittext=$(${CROSS_COMPILE}objdump -r -j __patchable_function_entries ${vmlinux_o} |
>                          grep ".init.text" | grep "${RELOCATION}" | wc -l)
>
> +num_ool_stubs_text_builtin=${1}
> +if [ ${num_ool_stubs_text} -gt ${num_ool_stubs_text_builtin} ]; then
> +       num_ool_stubs_text_end=$(expr ${num_ool_stubs_text} - ${num_ool_stubs_text_builtin})
> +else
> +       num_ool_stubs_text_end=0
> +fi
> +
>  cat > ${arch_vmlinux_S} <<EOF
>  #include <asm/asm-offsets.h>
>  #include <linux/linkage.h>
>
>  .pushsection .tramp.ftrace.text,"aw"
> -SYM_DATA(ftrace_ool_stub_text_end_count, .long ${num_ool_stubs_text})
> +SYM_DATA(ftrace_ool_stub_text_end_count, .long ${num_ool_stubs_text_end})
>
>  SYM_CODE_START(ftrace_ool_stub_text_end)
> -       .space ${num_ool_stubs_text} * FTRACE_OOL_STUB_SIZE
> +       .space ${num_ool_stubs_text_end} * FTRACE_OOL_STUB_SIZE
>  SYM_CODE_END(ftrace_ool_stub_text_end)
>  .popsection
>
> --
> 2.46.0
>


--
Best Regards
Masahiro Yamada