Messages in this thread | | | Date | Thu, 18 Feb 2016 12:45:47 +0100 | From | Borislav Petkov <> | Subject | Re: [PATCH V4 4/6] perf/amd/iommu: Introduce get_iommu_bnk_cnt_evt_idx |
| |
On Thu, Feb 11, 2016 at 04:15:25PM +0700, Suravee Suthikulpanit wrote: > Introduce a helper function to calculate bit-index for assigning > performance counter assignment. > > Signed-off-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com> > --- > arch/x86/events/amd/iommu.c | 19 ++++++++++++++----- > 1 file changed, 14 insertions(+), 5 deletions(-) > > diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c > index debf22d..812eff2 100644 > --- a/arch/x86/events/amd/iommu.c > +++ b/arch/x86/events/amd/iommu.c > @@ -145,18 +145,27 @@ static struct attribute_group amd_iommu_cpumask_group = { > > /*---------------------------------------------*/ > > +static inline > +int get_iommu_bnk_cnt_evt_idx(struct perf_amd_iommu *perf_iommu, > + int iommu_index, int bank_index, > + int cntr_index)
Align args at the opening brace.
> +{ > + int cntrs_per_iommu = perf_iommu->max_banks * perf_iommu->max_counters; > + int index = (perf_iommu->max_counters * bank_index) + cntr_index; > + > + return (cntrs_per_iommu * iommu_index) + index; > +} > + > static int get_next_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu) > { > unsigned long flags; > int shift, bank, cntr, retval; > - int max_banks = perf_iommu->max_banks; > - int max_cntrs = perf_iommu->max_counters; > > raw_spin_lock_irqsave(&perf_iommu->lock, flags); > > - for (bank = 0, shift = 0; bank < max_banks; bank++) { > - for (cntr = 0; cntr < max_cntrs; cntr++) { > - shift = bank + (bank*3) + cntr; > + for (bank = 0, shift = 0; bank < perf_iommu->max_banks; bank++) {
Please init that shift variable above in the function entry - it confuses unnecessarily here as if it had anything to do with the loop stride.
> + for (cntr = 0; cntr < perf_iommu->max_counters; cntr++) { > + shift = get_iommu_bnk_cnt_evt_idx(perf_iommu, 0, bank, cntr);
\n here
> if (perf_iommu->cntr_assign_mask & (1ULL<<shift)) { > continue; > } else { > -- > 2.5.0 > >
-- Regards/Gruss, Boris.
ECO tip #101: Trim your mails when you reply.
| |