[PATCH v2 2/8] perf/arm_cspmu: nvidia: Add Tegra410 UCF PMU

[Jonathan Cameron]

On Wed, 18 Feb 2026 14:58:03 +0000
Besar Wicaksono <bwicaksono at nvidia.com> wrote:

> The Unified Coherence Fabric (UCF) contains last level cache
> and cache coherent interconnect in Tegra410 SOC. The PMU in
> this device can be used to capture events related to access
> to the last level cache and memory from different sources.
> 
> Reviewed-by: Ilkka Koskinen <ilkka at os.amperecomputing.com>
> Signed-off-by: Besar Wicaksono <bwicaksono at nvidia.com>
Trivial stuff inline...


> diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c
> index e06a06d3407b..c67667097a3c 100644
> --- a/drivers/perf/arm_cspmu/nvidia_cspmu.c
> +++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c
> @@ -1,6 +1,6 @@
>  // SPDX-License-Identifier: GPL-2.0
>  /*
> - * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
> + * Copyright (c) 2022-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
>   *
>   */
>  
> @@ -21,6 +21,13 @@
>  #define NV_CNVL_PORT_COUNT           4ULL
>  #define NV_CNVL_FILTER_ID_MASK       GENMASK_ULL(NV_CNVL_PORT_COUNT - 1, 0)
>  
> +#define NV_UCF_SRC_COUNT             3ULL
> +#define NV_UCF_DST_COUNT             4ULL
> +#define NV_UCF_FILTER_ID_MASK        GENMASK_ULL(11, 0)
> +#define NV_UCF_FILTER_SRC            GENMASK_ULL(2, 0)
> +#define NV_UCF_FILTER_DST            GENMASK_ULL(11, 8)
> +#define NV_UCF_FILTER_DEFAULT        (NV_UCF_FILTER_SRC | NV_UCF_FILTER_DST)
> +
>  #define NV_GENERIC_FILTER_ID_MASK    GENMASK_ULL(31, 0)
>  
>  #define NV_PRODID_MASK	(PMIIDR_PRODUCTID | PMIIDR_VARIANT | PMIIDR_REVISION)
> @@ -124,6 +131,37 @@ static struct attribute *mcf_pmu_event_attrs[] = {
>  	NULL,
>  };
>  
> +static struct attribute *ucf_pmu_event_attrs[] = {
> +	ARM_CSPMU_EVENT_ATTR(bus_cycles,            0x1D),
> +
> +	ARM_CSPMU_EVENT_ATTR(slc_allocate,          0xF0),
> +	ARM_CSPMU_EVENT_ATTR(slc_wb,                0xF3),
> +	ARM_CSPMU_EVENT_ATTR(slc_refill_rd,         0x109),
> +	ARM_CSPMU_EVENT_ATTR(slc_refill_wr,         0x10A),
> +	ARM_CSPMU_EVENT_ATTR(slc_hit_rd,            0x119),
> +
> +	ARM_CSPMU_EVENT_ATTR(slc_access_dataless,   0x183),
> +	ARM_CSPMU_EVENT_ATTR(slc_access_atomic,     0x184),
> +
> +	ARM_CSPMU_EVENT_ATTR(slc_access,            0xF2),
> +	ARM_CSPMU_EVENT_ATTR(slc_access_rd,         0x111),
> +	ARM_CSPMU_EVENT_ATTR(slc_access_wr,         0x112),
> +	ARM_CSPMU_EVENT_ATTR(slc_bytes_rd,          0x113),
> +	ARM_CSPMU_EVENT_ATTR(slc_bytes_wr,          0x114),
> +
> +	ARM_CSPMU_EVENT_ATTR(mem_access_rd,         0x121),
> +	ARM_CSPMU_EVENT_ATTR(mem_access_wr,         0x122),
> +	ARM_CSPMU_EVENT_ATTR(mem_bytes_rd,          0x123),
> +	ARM_CSPMU_EVENT_ATTR(mem_bytes_wr,          0x124),
> +
> +	ARM_CSPMU_EVENT_ATTR(local_snoop,           0x180),
> +	ARM_CSPMU_EVENT_ATTR(ext_snp_access,        0x181),
> +	ARM_CSPMU_EVENT_ATTR(ext_snp_evict,         0x182),
> +
> +	ARM_CSPMU_EVENT_ATTR(cycles, ARM_CSPMU_EVT_CYCLES_DEFAULT),
> +	NULL,
Whilst it's locally consistent.  In general commas after NULL terminators
are something that makes little sense.  The whole point of that terminator
is nothing will ever come after it...

I wouldn't have commented but...
> +};

>  enum nv_cspmu_name_fmt {
>  	NAME_FMT_GENERIC,
> @@ -342,6 +413,23 @@ static const struct nv_cspmu_match nv_cspmu_match[] = {
>  		.init_data = NULL
>  	  },
>  	},
> +	{
> +	  .prodid = 0x2CF20000,
> +	  .prodid_mask = NV_PRODID_MASK,
> +	  .name_pattern = "nvidia_ucf_pmu_%u",
> +	  .name_fmt = NAME_FMT_SOCKET,
> +	  .template_ctx = {
> +		.event_attr = ucf_pmu_event_attrs,
> +		.format_attr = ucf_pmu_format_attrs,
> +		.filter_mask = NV_UCF_FILTER_ID_MASK,
> +		.filter_default_val = NV_UCF_FILTER_DEFAULT,
> +		.filter2_mask = 0x0,
> +		.filter2_default_val = 0x0,
> +		.get_filter = ucf_pmu_event_filter,
> +		.get_filter2 = NULL,
> +		.init_data = NULL
Also locally consistent but generally considered a bad thing to do.
It is certainly possible that in future the template_ctx will gain another field
so the lack of a trailing comma here will then create unnecessary noise.

For this reason trailing commas are normally used in structure initialization.

Jonathan

> +	  },
> +	},
>  	{
>  	  .prodid = 0,
>  	  .prodid_mask = 0,