[PATCH v4 09/10] tools: lib: perf: Implement riscv mmap support

[Alexandre Ghiti]

On Mon, Jul 31, 2023 at 12:15 PM Alexandre Ghiti <alexghiti at rivosinc.com> wrote:
>
> Hi Ian,
>
> On Fri, Jul 28, 2023 at 7:53 PM Ian Rogers <irogers at google.com> wrote:
> >
> > On Thu, Jul 27, 2023 at 7:28 AM Alexandre Ghiti <alexghiti at rivosinc.com> wrote:
> > >
> > > riscv now supports mmaping hardware counters so add what's needed to
> > > take advantage of that in libperf.
> > >
> > > Signed-off-by: Alexandre Ghiti <alexghiti at rivosinc.com>
> > > Reviewed-by: Andrew Jones <ajones at ventanamicro.com>
> > > Reviewed-by: Atish Patra <atishp at rivosinc.com>
> > > ---
> > >  tools/lib/perf/mmap.c | 65 +++++++++++++++++++++++++++++++++++++++++++
> > >  1 file changed, 65 insertions(+)
> > >
> > > diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
> > > index 0d1634cedf44..378a163f0554 100644
> > > --- a/tools/lib/perf/mmap.c
> > > +++ b/tools/lib/perf/mmap.c
> > > @@ -392,6 +392,71 @@ static u64 read_perf_counter(unsigned int counter)
> > >
> > >  static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); }
> > >
> > > +#elif __riscv_xlen == 64
> >
> > This is something of an odd guard, perhaps:
> > #elif defined(__riscv) && __riscv_xlen == 64
> >
> > That way it is more intention revealing that this is riscv code. Could
> > you add a comment relating to the __riscv_xlen ?
>
> I guess Andrew answered that already.
>
> >
> > > +
> > > +/* TODO: implement rv32 support */
> > > +
> > > +#define CSR_CYCLE      0xc00
> > > +#define CSR_TIME       0xc01
> > > +
> > > +#define csr_read(csr)                                          \
> > > +({                                                             \
> > > +       register unsigned long __v;                             \
> > > +               __asm__ __volatile__ ("csrr %0, " #csr          \
> > > +                : "=r" (__v) :                                 \
> > > +                : "memory");                                   \
> >
> > To avoid the macro pasting that could potentially go weird, could this be:
> >
> > __asm__ __volatile__ ("csrr %0, %1",
> >   : "=r"(__v) /* outputs */
> >   : "i"(csr) /* inputs */
> >   : "memory" /* clobbers */)

Forgot to answer this one: it compiles, but I have to admit that I
don't understand the difference and if that's correct (all macros in
arch/riscv/include/asm/csr.h use # to do this) and what benefits it
brings. Can you elaborate more on things that could "go weird"?

Thanks again,

Alex

> >
> > Also, why is this clobbering memory? Worth adding a comment.
>
> No idea, I see that it is also done this way in
> arch/riscv/include/asm/csr.h. @Atish Kumar Patra , @Palmer Dabbelt ?
>
> Thanks for your comments!
>
> Alex
>
> >
> > Thanks,
> > Ian
> >
> > > +                __v;                                           \
> > > +})
> > > +
> > > +static unsigned long csr_read_num(int csr_num)
> > > +{
> > > +#define switchcase_csr_read(__csr_num, __val)           {\
> > > +       case __csr_num:                                 \
> > > +               __val = csr_read(__csr_num);            \
> > > +               break; }
> > > +#define switchcase_csr_read_2(__csr_num, __val)         {\
> > > +       switchcase_csr_read(__csr_num + 0, __val)        \
> > > +       switchcase_csr_read(__csr_num + 1, __val)}
> > > +#define switchcase_csr_read_4(__csr_num, __val)         {\
> > > +       switchcase_csr_read_2(__csr_num + 0, __val)      \
> > > +       switchcase_csr_read_2(__csr_num + 2, __val)}
> > > +#define switchcase_csr_read_8(__csr_num, __val)         {\
> > > +       switchcase_csr_read_4(__csr_num + 0, __val)      \
> > > +       switchcase_csr_read_4(__csr_num + 4, __val)}
> > > +#define switchcase_csr_read_16(__csr_num, __val)        {\
> > > +       switchcase_csr_read_8(__csr_num + 0, __val)      \
> > > +       switchcase_csr_read_8(__csr_num + 8, __val)}
> > > +#define switchcase_csr_read_32(__csr_num, __val)        {\
> > > +       switchcase_csr_read_16(__csr_num + 0, __val)     \
> > > +       switchcase_csr_read_16(__csr_num + 16, __val)}
> > > +
> > > +       unsigned long ret = 0;
> > > +
> > > +       switch (csr_num) {
> > > +       switchcase_csr_read_32(CSR_CYCLE, ret)
> > > +       default:
> > > +               break;
> > > +       }
> > > +
> > > +       return ret;
> > > +#undef switchcase_csr_read_32
> > > +#undef switchcase_csr_read_16
> > > +#undef switchcase_csr_read_8
> > > +#undef switchcase_csr_read_4
> > > +#undef switchcase_csr_read_2
> > > +#undef switchcase_csr_read
> > > +}
> > > +
> > > +static u64 read_perf_counter(unsigned int counter)
> > > +{
> > > +       return csr_read_num(CSR_CYCLE + counter);
> > > +}
> > > +
> > > +static u64 read_timestamp(void)
> > > +{
> > > +       return csr_read_num(CSR_TIME);
> > > +}
> > > +
> > >  #else
> > >  static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
> > >  static u64 read_timestamp(void) { return 0; }
> > > --
> > > 2.39.2
> > >