On Thu, Apr 24, 2025 at 9:29 AM Andrii Nakryiko <andrii.nakryiko@xxxxxxxxx> wrote: > > On Thu, Apr 24, 2025 at 5:49 AM Jiri Olsa <olsajiri@xxxxxxxxx> wrote: > > > > On Wed, Apr 23, 2025 at 10:33:18AM -0700, Andrii Nakryiko wrote: > > > On Mon, Apr 21, 2025 at 2:46 PM Jiri Olsa <jolsa@xxxxxxxxxx> wrote: > > > > > > > > Using 5-byte nop for x86 usdt probes so we can switch > > > > to optimized uprobe them. > > > > > > > > Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx> > > > > --- > > > > tools/testing/selftests/bpf/sdt.h | 9 ++++++++- > > > > 1 file changed, 8 insertions(+), 1 deletion(-) > > > > > > > > > > So sdt.h is an exact copy/paste from systemtap-sdt sources. I'd prefer > > > to not modify it unnecessarily. > > > > > > How about we copy/paste usdt.h ([0]) and use *that* for your > > > benchmarks? I've already anticipated the need to change nop > > > instruction, so you won't even need to modify the usdt.h file itself, > > > just > > > > > > #define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00 > > > > > > before #include "usdt.h" > > > > > > sounds good, but it seems we need bit more changes for that, > > so far I ended up with: > > > > - __usdt_asm1(990: USDT_NOP) \ > > + __usdt_asm5(990: USDT_NOP) \ > > > > but it still won't compile, will need to spend more time on that, > > unless you have better solution > > > > Use > > #define USDT_NOP .ascii "\x0F\x1F\x44\x00\x00" > > for now, I'll need to improve macro magic to handle instructions with > commas in them... Ok, fixed in [0]. If you get the latest version, the .byte approach will work (I have tests in CI now to validate this). [0] https://github.com/libbpf/usdt/pull/12 > > > thanks, > > jirka > > > > > > > > > > > [0] https://github.com/libbpf/usdt/blob/main/usdt.h > > > > > > > diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h > > > > index 1fcfa5160231..1d62c06f5ddc 100644 > > > > --- a/tools/testing/selftests/bpf/sdt.h > > > > +++ b/tools/testing/selftests/bpf/sdt.h > > > > @@ -236,6 +236,13 @@ __extension__ extern unsigned long long __sdt_unsp; > > > > #define _SDT_NOP nop > > > > #endif > > > > > > > > +/* Use 5 byte nop for x86_64 to allow optimizing uprobes. */ > > > > +#if defined(__x86_64__) > > > > +# define _SDT_DEF_NOP _SDT_ASM_5(990: .byte 0x0f, 0x1f, 0x44, 0x00, 0x00) > > > > +#else > > > > +# define _SDT_DEF_NOP _SDT_ASM_1(990: _SDT_NOP) > > > > +#endif > > > > + > > > > #define _SDT_NOTE_NAME "stapsdt" > > > > #define _SDT_NOTE_TYPE 3 > > > > > > > > @@ -288,7 +295,7 @@ __extension__ extern unsigned long long __sdt_unsp; > > > > > > > > #define _SDT_ASM_BODY(provider, name, pack_args, args, ...) \ > > > > _SDT_DEF_MACROS \ > > > > - _SDT_ASM_1(990: _SDT_NOP) \ > > > > + _SDT_DEF_NOP \ > > > > _SDT_ASM_3( .pushsection .note.stapsdt,_SDT_ASM_AUTOGROUP,"note") \ > > > > _SDT_ASM_1( .balign 4) \ > > > > _SDT_ASM_3( .4byte 992f-991f, 994f-993f, _SDT_NOTE_TYPE) \ > > > > -- > > > > 2.49.0 > > > >
