Re: [PATCH v2 05/10] riscv: Prepare for user-space perf event mmap support

[Alexandre Ghiti <alexghiti@rivosinc.com>]

On Fri, Jun 16, 2023 at 10:28 AM Atish Patra <atishp@atishpatra.org> wrote:
>
> On Fri, May 12, 2023 at 1:58 AM Alexandre Ghiti <alexghiti@rivosinc.com> wrote:
> >
> > Provide all the necessary bits in the generic riscv pmu driver to be
> > able to mmap perf events in userspace: the heavy lifting lies in the
> > driver backend, namely the legacy and sbi implementations.
> >
> > Note that arch_perf_update_userpage is almost a copy of arm64 code.
> >
> > Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> > ---
> >  arch/riscv/kernel/Makefile     |  2 +-
> >  arch/riscv/kernel/perf_event.c | 58 ++++++++++++++++++++++++++++++++++
> >  drivers/perf/riscv_pmu.c       | 41 ++++++++++++++++++++++++
> >  include/linux/perf/riscv_pmu.h |  4 +++
> >  4 files changed, 104 insertions(+), 1 deletion(-)
> >  create mode 100644 arch/riscv/kernel/perf_event.c
> >
> > diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
> > index 4cf303a779ab..0d215fd9860d 100644
> > --- a/arch/riscv/kernel/Makefile
> > +++ b/arch/riscv/kernel/Makefile
> > @@ -70,7 +70,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE)  += mcount-dyn.o
> >
> >  obj-$(CONFIG_TRACE_IRQFLAGS)   += trace_irq.o
> >
> > -obj-$(CONFIG_PERF_EVENTS)      += perf_callchain.o
> > +obj-$(CONFIG_PERF_EVENTS)      += perf_callchain.o perf_event.o
> >  obj-$(CONFIG_HAVE_PERF_REGS)   += perf_regs.o
> >  obj-$(CONFIG_RISCV_SBI)                += sbi.o
> >  ifeq ($(CONFIG_RISCV_SBI), y)
> > diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c
> > new file mode 100644
> > index 000000000000..94174a0fc251
> > --- /dev/null
> > +++ b/arch/riscv/kernel/perf_event.c
> > @@ -0,0 +1,58 @@
> > +// SPDX-License-Identifier: GPL-2.0-only
> > +#include <linux/sched_clock.h>
> > +
> > +void arch_perf_update_userpage(struct perf_event *event,
> > +                              struct perf_event_mmap_page *userpg, u64 now)
> > +{
> > +       struct clock_read_data *rd;
> > +       unsigned int seq;
> > +       u64 ns;
> > +
> > +       userpg->cap_user_time = 0;
> > +       userpg->cap_user_time_zero = 0;
> > +       userpg->cap_user_time_short = 0;
> > +       userpg->cap_user_rdpmc =
> > +               !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT);
> > +
> > +       userpg->pmc_width = 64;
> > +
>
> The counter width is 64 for cycle & instret. Other hpmcounter can have
> different width.
> This information should retrieved from counter info.

Yes, this is done in patch 7 when I adapt the perf SBI backend to
allow the user access.

>
> > +       do {
> > +               rd = sched_clock_read_begin(&seq);
> > +
> > +               userpg->time_mult = rd->mult;
> > +               userpg->time_shift = rd->shift;
> > +               userpg->time_zero = rd->epoch_ns;
> > +               userpg->time_cycles = rd->epoch_cyc;
> > +               userpg->time_mask = rd->sched_clock_mask;
> > +
> > +               /*
> > +                * Subtract the cycle base, such that software that
> > +                * doesn't know about cap_user_time_short still 'works'
> > +                * assuming no wraps.
> > +                */
> > +               ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
> > +               userpg->time_zero -= ns;
> > +
> > +       } while (sched_clock_read_retry(seq));
> > +
> > +       userpg->time_offset = userpg->time_zero - now;
> > +
> > +       /*
> > +        * time_shift is not expected to be greater than 31 due to
> > +        * the original published conversion algorithm shifting a
> > +        * 32-bit value (now specifies a 64-bit value) - refer
> > +        * perf_event_mmap_page documentation in perf_event.h.
> > +        */
> > +       if (userpg->time_shift == 32) {
> > +               userpg->time_shift = 31;
> > +               userpg->time_mult >>= 1;
> > +       }
> > +
> > +       /*
> > +        * Internal timekeeping for enabled/running/stopped times
> > +        * is always computed with the sched_clock.
> > +        */
> > +       userpg->cap_user_time = 1;
> > +       userpg->cap_user_time_zero = 1;
> > +       userpg->cap_user_time_short = 1;
> > +}
> > diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
> > index ebca5eab9c9b..af69da268246 100644
> > --- a/drivers/perf/riscv_pmu.c
> > +++ b/drivers/perf/riscv_pmu.c
> > @@ -171,6 +171,8 @@ int riscv_pmu_event_set_period(struct perf_event *event)
> >
> >         local64_set(&hwc->prev_count, (u64)-left);
> >
> > +       perf_event_update_userpage(event);
> > +
> >         return overflow;
> >  }
> >
> > @@ -267,6 +269,9 @@ static int riscv_pmu_event_init(struct perf_event *event)
> >         hwc->idx = -1;
> >         hwc->event_base = mapped_event;
> >
> > +       if (rvpmu->event_init)
> > +               rvpmu->event_init(event);
> > +
> >         if (!is_sampling_event(event)) {
> >                 /*
> >                  * For non-sampling runs, limit the sample_period to half
> > @@ -283,6 +288,39 @@ static int riscv_pmu_event_init(struct perf_event *event)
> >         return 0;
> >  }
> >
> > +static int riscv_pmu_event_idx(struct perf_event *event)
> > +{
> > +       struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
> > +
> > +       if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT))
> > +               return 0;
> > +
> > +       if (rvpmu->csr_index)
> > +               return rvpmu->csr_index(event) + 1;
> > +
> > +       return 0;
> > +}
> > +
> > +static void riscv_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
> > +{
> > +       struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
> > +
> > +       if (rvpmu->event_mapped) {
> > +               rvpmu->event_mapped(event, mm);
> > +               perf_event_update_userpage(event);
> > +       }
> > +}
> > +
> > +static void riscv_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
> > +{
> > +       struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
> > +
> > +       if (rvpmu->event_unmapped) {
> > +               rvpmu->event_unmapped(event, mm);
> > +               perf_event_update_userpage(event);
> > +       }
> > +}
> > +
> >  struct riscv_pmu *riscv_pmu_alloc(void)
> >  {
> >         struct riscv_pmu *pmu;
> > @@ -307,6 +345,9 @@ struct riscv_pmu *riscv_pmu_alloc(void)
> >         }
> >         pmu->pmu = (struct pmu) {
> >                 .event_init     = riscv_pmu_event_init,
> > +               .event_mapped   = riscv_pmu_event_mapped,
> > +               .event_unmapped = riscv_pmu_event_unmapped,
> > +               .event_idx      = riscv_pmu_event_idx,
> >                 .add            = riscv_pmu_add,
> >                 .del            = riscv_pmu_del,
> >                 .start          = riscv_pmu_start,
> > diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h
> > index 9f70d94942e0..1452c8af3b67 100644
> > --- a/include/linux/perf/riscv_pmu.h
> > +++ b/include/linux/perf/riscv_pmu.h
> > @@ -55,6 +55,10 @@ struct riscv_pmu {
> >         void            (*ctr_start)(struct perf_event *event, u64 init_val);
> >         void            (*ctr_stop)(struct perf_event *event, unsigned long flag);
> >         int             (*event_map)(struct perf_event *event, u64 *config);
> > +       void            (*event_init)(struct perf_event *event);
> > +       void            (*event_mapped)(struct perf_event *event, struct mm_struct *mm);
> > +       void            (*event_unmapped)(struct perf_event *event, struct mm_struct *mm);
> > +       uint8_t         (*csr_index)(struct perf_event *event);
> >
> >         struct cpu_hw_events    __percpu *hw_events;
> >         struct hlist_node       node;
> > --
> > 2.37.2
> >
>
>
> --
> Regards,
> Atish