Linux Tegra architecture development
 help / color / mirror / Atom feed
From: Robin Murphy <robin.murphy@arm.com>
To: Besar Wicaksono <bwicaksono@nvidia.com>,
	will@kernel.org, ilkka@os.amperecomputing.com
Cc: linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, linux-tegra@vger.kernel.org,
	suzuki.poulose@arm.com, mark.rutland@arm.com, treding@nvidia.com,
	jonathanh@nvidia.com, vsethi@nvidia.com, rwiley@nvidia.com,
	sdonthineni@nvidia.com
Subject: Re: [PATCH v2 5/5] perf/arm_cspmu: nvidia: Add pmevfiltr2 support
Date: Fri, 26 Sep 2025 11:32:02 +0100	[thread overview]
Message-ID: <1ff12bce-1369-48e9-8807-3a7ecd8e1559@arm.com> (raw)
In-Reply-To: <20250923001840.1586078-6-bwicaksono@nvidia.com>

On 2025-09-23 1:18 am, Besar Wicaksono wrote:
> Support NVIDIA PMU that utilizes the optional event filter2 register.
> 
> Signed-off-by: Besar Wicaksono <bwicaksono@nvidia.com>
> ---
>   drivers/perf/arm_cspmu/nvidia_cspmu.c | 176 +++++++++++++++++++-------
>   1 file changed, 133 insertions(+), 43 deletions(-)
> 
> diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c
> index ac91dc46501d..e06a06d3407b 100644
> --- a/drivers/perf/arm_cspmu/nvidia_cspmu.c
> +++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c
> @@ -40,10 +40,21 @@
>   
>   struct nv_cspmu_ctx {
>   	const char *name;
> -	u32 filter_mask;
> -	u32 filter_default_val;
> +
>   	struct attribute **event_attr;
>   	struct attribute **format_attr;
> +
> +	u32 filter_mask;
> +	u32 filter_default_val;
> +	u32 filter2_mask;
> +	u32 filter2_default_val;
> +
> +	u32 (*get_filter)(const struct perf_event *event);
> +	u32 (*get_filter2)(const struct perf_event *event);

Callbacks for this seem like complete overkill - you already know 
whether a given implementation cares about each filter via 
.filter{,2}_mask being nonzero, so unless you intend to have wildly 
different event encodings across implementations, a simple conditional 
extension of the existing nv_cspmu_event_filter() logic should be all 
you need.

Thanks,
Robin.

> +
> +	void *data;
> +
> +	int (*init_data)(struct arm_cspmu *cspmu);
>   };
>   
>   static struct attribute *scf_pmu_event_attrs[] = {
> @@ -144,6 +155,7 @@ static struct attribute *cnvlink_pmu_format_attrs[] = {
>   static struct attribute *generic_pmu_format_attrs[] = {
>   	ARM_CSPMU_FORMAT_EVENT_ATTR,
>   	ARM_CSPMU_FORMAT_FILTER_ATTR,
> +	ARM_CSPMU_FORMAT_FILTER2_ATTR,
>   	NULL,
>   };
>   
> @@ -184,13 +196,36 @@ static u32 nv_cspmu_event_filter(const struct perf_event *event)
>   	return filter_val;
>   }
>   
> +static u32 nv_cspmu_event_filter2(const struct perf_event *event)
> +{
> +	const struct nv_cspmu_ctx *ctx =
> +		to_nv_cspmu_ctx(to_arm_cspmu(event->pmu));
> +
> +	const u32 filter_val = event->attr.config2 & ctx->filter2_mask;
> +
> +	if (filter_val == 0)
> +		return ctx->filter2_default_val;
> +
> +	return filter_val;
> +}
> +
>   static void nv_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
>   				   const struct perf_event *event)
>   {
> -	u32 filter = nv_cspmu_event_filter(event);
> -	u32 offset = PMEVFILTR + (4 * event->hw.idx);
> +	u32 filter, offset;
> +	const struct nv_cspmu_ctx *ctx =
> +		to_nv_cspmu_ctx(to_arm_cspmu(event->pmu));
> +	offset = 4 * event->hw.idx;
>   
> -	writel(filter, cspmu->base0 + offset);
> +	if (ctx->get_filter) {
> +		filter = ctx->get_filter(event);
> +		writel(filter, cspmu->base0 + PMEVFILTR + offset);
> +	}
> +
> +	if (ctx->get_filter2) {
> +		filter = ctx->get_filter2(event);
> +		writel(filter, cspmu->base0 + PMEVFILT2R + offset);
> +	}
>   }
>   
>   static void nv_cspmu_set_cc_filter(struct arm_cspmu *cspmu,
> @@ -210,74 +245,120 @@ enum nv_cspmu_name_fmt {
>   struct nv_cspmu_match {
>   	u32 prodid;
>   	u32 prodid_mask;
> -	u64 filter_mask;
> -	u32 filter_default_val;
>   	const char *name_pattern;
>   	enum nv_cspmu_name_fmt name_fmt;
> -	struct attribute **event_attr;
> -	struct attribute **format_attr;
> +	struct nv_cspmu_ctx template_ctx;
> +	struct arm_cspmu_impl_ops ops;
>   };
>   
>   static const struct nv_cspmu_match nv_cspmu_match[] = {
>   	{
>   	  .prodid = 0x10300000,
>   	  .prodid_mask = NV_PRODID_MASK,
> -	  .filter_mask = NV_PCIE_FILTER_ID_MASK,
> -	  .filter_default_val = NV_PCIE_FILTER_ID_MASK,
>   	  .name_pattern = "nvidia_pcie_pmu_%u",
>   	  .name_fmt = NAME_FMT_SOCKET,
> -	  .event_attr = mcf_pmu_event_attrs,
> -	  .format_attr = pcie_pmu_format_attrs
> +	  .template_ctx = {
> +		.event_attr = mcf_pmu_event_attrs,
> +		.format_attr = pcie_pmu_format_attrs,
> +		.filter_mask = NV_PCIE_FILTER_ID_MASK,
> +		.filter_default_val = NV_PCIE_FILTER_ID_MASK,
> +		.filter2_mask = 0x0,
> +		.filter2_default_val = 0x0,
> +		.get_filter = nv_cspmu_event_filter,
> +		.get_filter2 = NULL,
> +		.data = NULL,
> +		.init_data = NULL
> +	  },
>   	},
>   	{
>   	  .prodid = 0x10400000,
>   	  .prodid_mask = NV_PRODID_MASK,
> -	  .filter_mask = NV_NVL_C2C_FILTER_ID_MASK,
> -	  .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK,
>   	  .name_pattern = "nvidia_nvlink_c2c1_pmu_%u",
>   	  .name_fmt = NAME_FMT_SOCKET,
> -	  .event_attr = mcf_pmu_event_attrs,
> -	  .format_attr = nvlink_c2c_pmu_format_attrs
> +	  .template_ctx = {
> +		.event_attr = mcf_pmu_event_attrs,
> +		.format_attr = nvlink_c2c_pmu_format_attrs,
> +		.filter_mask = NV_NVL_C2C_FILTER_ID_MASK,
> +		.filter_default_val = NV_NVL_C2C_FILTER_ID_MASK,
> +		.filter2_mask = 0x0,
> +		.filter2_default_val = 0x0,
> +		.get_filter = nv_cspmu_event_filter,
> +		.get_filter2 = NULL,
> +		.data = NULL,
> +		.init_data = NULL
> +	  },
>   	},
>   	{
>   	  .prodid = 0x10500000,
>   	  .prodid_mask = NV_PRODID_MASK,
> -	  .filter_mask = NV_NVL_C2C_FILTER_ID_MASK,
> -	  .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK,
>   	  .name_pattern = "nvidia_nvlink_c2c0_pmu_%u",
>   	  .name_fmt = NAME_FMT_SOCKET,
> -	  .event_attr = mcf_pmu_event_attrs,
> -	  .format_attr = nvlink_c2c_pmu_format_attrs
> +	  .template_ctx = {
> +		.event_attr = mcf_pmu_event_attrs,
> +		.format_attr = nvlink_c2c_pmu_format_attrs,
> +		.filter_mask = NV_NVL_C2C_FILTER_ID_MASK,
> +		.filter_default_val = NV_NVL_C2C_FILTER_ID_MASK,
> +		.filter2_mask = 0x0,
> +		.filter2_default_val = 0x0,
> +		.get_filter = nv_cspmu_event_filter,
> +		.get_filter2 = NULL,
> +		.data = NULL,
> +		.init_data = NULL
> +	  },
>   	},
>   	{
>   	  .prodid = 0x10600000,
>   	  .prodid_mask = NV_PRODID_MASK,
> -	  .filter_mask = NV_CNVL_FILTER_ID_MASK,
> -	  .filter_default_val = NV_CNVL_FILTER_ID_MASK,
>   	  .name_pattern = "nvidia_cnvlink_pmu_%u",
>   	  .name_fmt = NAME_FMT_SOCKET,
> -	  .event_attr = mcf_pmu_event_attrs,
> -	  .format_attr = cnvlink_pmu_format_attrs
> +	  .template_ctx = {
> +		.event_attr = mcf_pmu_event_attrs,
> +		.format_attr = cnvlink_pmu_format_attrs,
> +		.filter_mask = NV_CNVL_FILTER_ID_MASK,
> +		.filter_default_val = NV_CNVL_FILTER_ID_MASK,
> +		.filter2_mask = 0x0,
> +		.filter2_default_val = 0x0,
> +		.get_filter = nv_cspmu_event_filter,
> +		.get_filter2 = NULL,
> +		.data = NULL,
> +		.init_data = NULL
> +	  },
>   	},
>   	{
>   	  .prodid = 0x2CF00000,
>   	  .prodid_mask = NV_PRODID_MASK,
> -	  .filter_mask = 0x0,
> -	  .filter_default_val = 0x0,
>   	  .name_pattern = "nvidia_scf_pmu_%u",
>   	  .name_fmt = NAME_FMT_SOCKET,
> -	  .event_attr = scf_pmu_event_attrs,
> -	  .format_attr = scf_pmu_format_attrs
> +	  .template_ctx = {
> +		.event_attr = scf_pmu_event_attrs,
> +		.format_attr = scf_pmu_format_attrs,
> +		.filter_mask = 0x0,
> +		.filter_default_val = 0x0,
> +		.filter2_mask = 0x0,
> +		.filter2_default_val = 0x0,
> +		.get_filter = nv_cspmu_event_filter,
> +		.get_filter2 = NULL,
> +		.data = NULL,
> +		.init_data = NULL
> +	  },
>   	},
>   	{
>   	  .prodid = 0,
>   	  .prodid_mask = 0,
> -	  .filter_mask = NV_GENERIC_FILTER_ID_MASK,
> -	  .filter_default_val = NV_GENERIC_FILTER_ID_MASK,
>   	  .name_pattern = "nvidia_uncore_pmu_%u",
>   	  .name_fmt = NAME_FMT_GENERIC,
> -	  .event_attr = generic_pmu_event_attrs,
> -	  .format_attr = generic_pmu_format_attrs
> +	  .template_ctx = {
> +		.event_attr = generic_pmu_event_attrs,
> +		.format_attr = generic_pmu_format_attrs,
> +		.filter_mask = NV_GENERIC_FILTER_ID_MASK,
> +		.filter_default_val = NV_GENERIC_FILTER_ID_MASK,
> +		.filter2_mask = NV_GENERIC_FILTER_ID_MASK,
> +		.filter2_default_val = NV_GENERIC_FILTER_ID_MASK,
> +		.get_filter = nv_cspmu_event_filter,
> +		.get_filter2 = nv_cspmu_event_filter2,
> +		.data = NULL,
> +		.init_data = NULL
> +	  },
>   	},
>   };
>   
> @@ -310,6 +391,14 @@ static char *nv_cspmu_format_name(const struct arm_cspmu *cspmu,
>   	return name;
>   }
>   
> +#define SET_OP(name, impl, match, default_op) \
> +	do { \
> +		if (match->ops.name) \
> +			impl->name = match->ops.name; \
> +		else if (default_op != NULL) \
> +			impl->name = default_op; \
> +	} while (false)
> +
>   static int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
>   {
>   	struct nv_cspmu_ctx *ctx;
> @@ -330,20 +419,21 @@ static int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
>   			break;
>   	}
>   
> -	ctx->name		= nv_cspmu_format_name(cspmu, match);
> -	ctx->filter_mask	= match->filter_mask;
> -	ctx->filter_default_val = match->filter_default_val;
> -	ctx->event_attr		= match->event_attr;
> -	ctx->format_attr	= match->format_attr;
> +	/* Initialize the context with the matched template. */
> +	memcpy(ctx, &match->template_ctx, sizeof(struct nv_cspmu_ctx));
> +	ctx->name = nv_cspmu_format_name(cspmu, match);
>   
>   	cspmu->impl.ctx = ctx;
>   
>   	/* NVIDIA specific callbacks. */
> -	impl_ops->set_cc_filter			= nv_cspmu_set_cc_filter;
> -	impl_ops->set_ev_filter			= nv_cspmu_set_ev_filter;
> -	impl_ops->get_event_attrs		= nv_cspmu_get_event_attrs;
> -	impl_ops->get_format_attrs		= nv_cspmu_get_format_attrs;
> -	impl_ops->get_name			= nv_cspmu_get_name;
> +	SET_OP(set_cc_filter, impl_ops, match, nv_cspmu_set_cc_filter);
> +	SET_OP(set_ev_filter, impl_ops, match, nv_cspmu_set_ev_filter);
> +	SET_OP(get_event_attrs, impl_ops, match, nv_cspmu_get_event_attrs);
> +	SET_OP(get_format_attrs, impl_ops, match, nv_cspmu_get_format_attrs);
> +	SET_OP(get_name, impl_ops, match, nv_cspmu_get_name);
> +
> +	if (ctx->init_data)
> +		return ctx->init_data(cspmu);
>   
>   	return 0;
>   }

  parent reply	other threads:[~2025-09-26 10:32 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-23  0:18 [PATCH v2 0/5] perf/arm_cspmu: Preparatory patches for NVIDIA T410 PMU Besar Wicaksono
2025-09-23  0:18 ` [PATCH v2 1/5] perf/arm_cspmu: Add arm_cspmu_acpi_dev_get Besar Wicaksono
2025-09-24 20:05   ` Ilkka Koskinen
2025-09-25  8:30   ` Suzuki K Poulose
2025-09-25 17:13     ` Besar Wicaksono
2025-09-26 10:01       ` Suzuki K Poulose
2025-09-23  0:18 ` [PATCH v2 2/5] perf/arm_cspmu: Add callback to reset filter config Besar Wicaksono
2025-09-24 20:06   ` Ilkka Koskinen
2025-09-25  9:23   ` Suzuki K Poulose
2025-09-23  0:18 ` [PATCH v2 3/5] perf/arm_cspmu: Add pmpidr support Besar Wicaksono
2025-09-23  0:18 ` [PATCH v2 4/5] perf/arm_cspmu: nvidia: Add revision id matching Besar Wicaksono
2025-09-23  0:18 ` [PATCH v2 5/5] perf/arm_cspmu: nvidia: Add pmevfiltr2 support Besar Wicaksono
2025-09-24 20:10   ` Ilkka Koskinen
2025-09-26 10:32   ` Robin Murphy [this message]
2025-09-26 16:35     ` Besar Wicaksono

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1ff12bce-1369-48e9-8807-3a7ecd8e1559@arm.com \
    --to=robin.murphy@arm.com \
    --cc=bwicaksono@nvidia.com \
    --cc=ilkka@os.amperecomputing.com \
    --cc=jonathanh@nvidia.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tegra@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=rwiley@nvidia.com \
    --cc=sdonthineni@nvidia.com \
    --cc=suzuki.poulose@arm.com \
    --cc=treding@nvidia.com \
    --cc=vsethi@nvidia.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox