[PATCH] drivers: perf: ctr_get_width function for legacy is not defined

Atish Patra atishp at atishpatra.org
Mon Dec 4 18:47:16 PST 2023


On Mon, Nov 27, 2023 at 11:57 PM Atish Patra <atishp at atishpatra.org> wrote:
>
> On Mon, Nov 27, 2023 at 1:54 AM Vadim Shakirov
> <vadim.shakirov at syntacore.com> wrote:
> >
> > With parameters CONFIG_RISCV_PMU_LEGACY=y and CONFIG_RISCV_PMU_SBI=n
> > linux kernel crashes when you try perf record:
> >
> > $ perf record ls
> > [   46.749286] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
> > [   46.750199] Oops [#1]
> > [   46.750342] Modules linked in:
> > [   46.750608] CPU: 0 PID: 107 Comm: perf-exec Not tainted 6.6.0 #2
> > [   46.750906] Hardware name: riscv-virtio,qemu (DT)
> > [   46.751184] epc : 0x0
> > [   46.751430]  ra : arch_perf_update_userpage+0x54/0x13e
> > [   46.751680] epc : 0000000000000000 ra : ffffffff8072ee52 sp : ff2000000022b8f0
> > [   46.751958]  gp : ffffffff81505988 tp : ff6000000290d400 t0 : ff2000000022b9c0
> > [   46.752229]  t1 : 0000000000000001 t2 : 0000000000000003 s0 : ff2000000022b930
> > [   46.752451]  s1 : ff600000028fb000 a0 : 0000000000000000 a1 : ff600000028fb000
> > [   46.752673]  a2 : 0000000ae2751268 a3 : 00000000004fb708 a4 : 0000000000000004
> > [   46.752895]  a5 : 0000000000000000 a6 : 000000000017ffe3 a7 : 00000000000000d2
> > [   46.753117]  s2 : ff600000028fb000 s3 : 0000000ae2751268 s4 : 0000000000000000
> > [   46.753338]  s5 : ffffffff8153e290 s6 : ff600000863b9000 s7 : ff60000002961078
> > [   46.753562]  s8 : ff60000002961048 s9 : ff60000002961058 s10: 0000000000000001
> > [   46.753783]  s11: 0000000000000018 t3 : ffffffffffffffff t4 : ffffffffffffffff
> > [   46.754005]  t5 : ff6000000292270c t6 : ff2000000022bb30
> > [   46.754179] status: 0000000200000100 badaddr: 0000000000000000 cause: 000000000000000c
> > [   46.754653] Code: Unable to access instruction at 0xffffffffffffffec.
> > [   46.754939] ---[ end trace 0000000000000000 ]---
> > [   46.755131] note: perf-exec[107] exited with irqs disabled
> > [   46.755546] note: perf-exec[107] exited with preempt_count 4
> >
> > This happens because in the legacy case the ctr_get_width function was not
> > defined, but it is used in arch_perf_update_userpage.
> >
> > Fixes: cc4c07c89aad ("drivers: perf: Implement perf event mmap support in the SBI backend")
> > Signed-off-by: Vadim Shakirov <vadim.shakirov at syntacore.com>
>
> Legacy PMU shouldn't enable perf sampling in the first place. We need
> to set the capabilities accordingly.
>
> @@ -111,14 +116,17 @@ static void pmu_legacy_init(struct riscv_pmu *pmu)
>         pmu->ctr_stop = NULL;
>         pmu->event_map = pmu_legacy_event_map;
>         pmu->ctr_get_idx = pmu_legacy_ctr_get_idx;
>         pmu->ctr_get_width = NULL;
>         pmu->ctr_clear_idx = NULL;
>         pmu->ctr_read = pmu_legacy_read_ctr;
>         pmu->event_mapped = pmu_legacy_event_mapped;
>         pmu->event_unmapped = pmu_legacy_event_unmapped;
>         pmu->csr_index = pmu_legacy_csr_index;
>  +     pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
> +      pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
>         perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW);
>  }
>
>
>
> > ---
> >  drivers/perf/riscv_pmu_legacy.c | 8 +++++++-
> >  1 file changed, 7 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
> > index 79fdd667922e..a179ed6ac980 100644
> > --- a/drivers/perf/riscv_pmu_legacy.c
> > +++ b/drivers/perf/riscv_pmu_legacy.c
> > @@ -37,6 +37,12 @@ static int pmu_legacy_event_map(struct perf_event *event, u64 *config)
> >         return pmu_legacy_ctr_get_idx(event);
> >  }
> >
> > +/* cycle & instret are always 64 bit, one bit less according to SBI spec */
> > +static int pmu_legacy_ctr_get_width(int idx)
> > +{
> > +       return 63;
> > +}
> > +
>
> Having said that, there is no harm in defining the width function for
> legacy PMU.
> The common riscv_pmu.c fixes the counter width to 63 if ctr_get_width
> is not defined. We may be to get rid of that
> as both drivers will have a valid function pointer.
>

It would be great to merge these changes in the next merge window.
Let me know if you are busy and want me to respin the patches keeping
your authorship.

> >  static u64 pmu_legacy_read_ctr(struct perf_event *event)
> >  {
> >         struct hw_perf_event *hwc = &event->hw;
> > @@ -111,7 +117,7 @@ static void pmu_legacy_init(struct riscv_pmu *pmu)
> >         pmu->ctr_stop = NULL;
> >         pmu->event_map = pmu_legacy_event_map;
> >         pmu->ctr_get_idx = pmu_legacy_ctr_get_idx;
> > -       pmu->ctr_get_width = NULL;
> > +       pmu->ctr_get_width = pmu_legacy_ctr_get_width;
> >         pmu->ctr_clear_idx = NULL;
> >         pmu->ctr_read = pmu_legacy_read_ctr;
> >         pmu->event_mapped = pmu_legacy_event_mapped;
> > --
> > 2.34.1
> >
>
>
> --
> Regards,
> Atish



-- 
Regards,
Atish



More information about the linux-riscv mailing list