Message-ID:
 <OSZPR01MB8798C425E5A820C2E0AAA7BC8BC5A@OSZPR01MB8798.jpnprd01.prod.outlook.com>
Date: Wed, 5 Nov 2025 08:32:19 +0000
From: "Shaopeng Tan (Fujitsu)" <tan.shaopeng@...itsu.com>
To: 'James Morse' <james.morse@....com>, "linux-kernel@...r.kernel.org"
	<linux-kernel@...r.kernel.org>, "linux-arm-kernel@...ts.infradead.org"
	<linux-arm-kernel@...ts.infradead.org>, "linux-acpi@...r.kernel.org"
	<linux-acpi@...r.kernel.org>
CC: D Scott Phillips OS <scott@...amperecomputing.com>,
	"carl@...amperecomputing.com" <carl@...amperecomputing.com>,
	"lcherian@...vell.com" <lcherian@...vell.com>, "bobo.shaobowang@...wei.com"
	<bobo.shaobowang@...wei.com>, "baolin.wang@...ux.alibaba.com"
	<baolin.wang@...ux.alibaba.com>, Jamie Iles <quic_jiles@...cinc.com>, Xin Hao
	<xhao@...ux.alibaba.com>, "peternewman@...gle.com" <peternewman@...gle.com>,
	"dfustini@...libre.com" <dfustini@...libre.com>, "amitsinght@...vell.com"
	<amitsinght@...vell.com>, David Hildenbrand <david@...hat.com>, Dave Martin
	<dave.martin@....com>, Koba Ko <kobak@...dia.com>, Shanker Donthineni
	<sdonthineni@...dia.com>, "fenghuay@...dia.com" <fenghuay@...dia.com>,
	"baisheng.gao@...soc.com" <baisheng.gao@...soc.com>, Jonathan Cameron
	<jonathan.cameron@...wei.com>, Rob Herring <robh@...nel.org>, Rohit Mathew
	<rohit.mathew@....com>, Rafael Wysocki <rafael@...nel.org>, Len Brown
	<lenb@...nel.org>, Lorenzo Pieralisi <lpieralisi@...nel.org>, Hanjun Guo
	<guohanjun@...wei.com>, Sudeep Holla <sudeep.holla@....com>, Catalin Marinas
	<catalin.marinas@....com>, Will Deacon <will@...nel.org>, Greg Kroah-Hartman
	<gregkh@...uxfoundation.org>, Danilo Krummrich <dakr@...nel.org>, Jeremy
 Linton <jeremy.linton@....com>, Gavin Shan <gshan@...hat.com>
Subject: RE: [PATCH v3 23/29] arm_mpam: Add mpam_msmon_read() to read monitor
 value

Hello James,

> Reading a monitor involves configuring what you want to monitor, and reading
> the value. Components made up of multiple MSC may need values from each
> MSC. MSCs may take time to configure, returning 'not ready'.
> The maximum 'not ready' time should have been provided by firmware.
> 
> Add mpam_msmon_read() to hide all this. If (one of) the MSC returns not ready,
> then wait the full timeout value before trying again.
> 
> CC: Shanker Donthineni <sdonthineni@...dia.com>
> Signed-off-by: James Morse <james.morse@....com>
> ---
> Changes since v2:
>  * Fixed ctl_val/flt_val assignment that led to always reading counter 0.
>  * switch to using guard() version of srcu_read_lock()
>  * Fixed use of rcu helpers when srcu is wanted.
>  * Use return instead of break.
>  * Moved variable declarations into the loop.
>  * Use struct assignment instead of memset().
>  * Whitespace.
> 
> Changes since v1:
>  * Added XCL support.
>  * Merged FLT/CTL constants.
>  * a spelling mistake in a comment.
>  * moved structrues around.
> ---
>  drivers/resctrl/mpam_devices.c  | 233
> ++++++++++++++++++++++++++++++++
> drivers/resctrl/mpam_internal.h |  19 +++
>  2 files changed, 252 insertions(+)
> 
> diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
> index a29f97cd176a..fb5414c6b3eb 100644
> --- a/drivers/resctrl/mpam_devices.c
> +++ b/drivers/resctrl/mpam_devices.c
> @@ -880,6 +880,239 @@ static int mpam_msc_hw_probe(struct mpam_msc
> *msc)
>  	return 0;
>  }
> 
> +struct mon_read {
> +	struct mpam_msc_ris		*ris;
> +	struct mon_cfg			*ctx;
> +	enum mpam_device_features	type;
> +	u64				*val;
> +	int				err;
> +};
> +
> +static void gen_msmon_ctl_flt_vals(struct mon_read *m, u32 *ctl_val,
> +				   u32 *flt_val)
> +{
> +	struct mon_cfg *ctx = m->ctx;
> +
> +	/*
> +	 * For CSU counters its implementation-defined what happens when
> not
> +	 * filtering by partid.
> +	 */
> +	*ctl_val = MSMON_CFG_x_CTL_MATCH_PARTID;
> +
> +	*flt_val = FIELD_PREP(MSMON_CFG_x_FLT_PARTID, ctx->partid);
> +
> +	if (m->ctx->match_pmg) {
> +		*ctl_val |= MSMON_CFG_x_CTL_MATCH_PMG;
> +		*flt_val |= FIELD_PREP(MSMON_CFG_x_FLT_PMG,
> ctx->pmg);
> +	}
> +
> +	switch (m->type) {
> +	case mpam_feat_msmon_csu:
> +		*ctl_val |= MSMON_CFG_CSU_CTL_TYPE_CSU;
> +
> +		if (mpam_has_feature(mpam_feat_msmon_csu_xcl,
> &m->ris->props))
> +			*flt_val |=
> FIELD_PREP(MSMON_CFG_CSU_FLT_XCL,
> +					       ctx->csu_exclude_clean);
> +
> +		break;
> +	case mpam_feat_msmon_mbwu:
> +		*ctl_val |= MSMON_CFG_MBWU_CTL_TYPE_MBWU;
> +
> +		if (mpam_has_feature(mpam_feat_msmon_mbwu_rwbw,
> &m->ris->props))
> +			*flt_val |=
> FIELD_PREP(MSMON_CFG_MBWU_FLT_RWBW, ctx->opts);
> +
> +		break;
> +	default:
> +		return;
> +	}
> +}
> +
> +static void read_msmon_ctl_flt_vals(struct mon_read *m, u32 *ctl_val,
> +				    u32 *flt_val)
> +{
> +	struct mpam_msc *msc = m->ris->vmsc->msc;
> +
> +	switch (m->type) {
> +	case mpam_feat_msmon_csu:
> +		*ctl_val = mpam_read_monsel_reg(msc, CFG_CSU_CTL);
> +		*flt_val = mpam_read_monsel_reg(msc, CFG_CSU_FLT);
> +		return;
> +	case mpam_feat_msmon_mbwu:
> +		*ctl_val = mpam_read_monsel_reg(msc, CFG_MBWU_CTL);
> +		*flt_val = mpam_read_monsel_reg(msc, CFG_MBWU_FLT);
> +		return;
> +	default:
> +		return;
> +	}
> +}
> +
> +/* Remove values set by the hardware to prevent apparent mismatches. */
> +static void clean_msmon_ctl_val(u32 *cur_ctl) {
> +	*cur_ctl &= ~MSMON_CFG_x_CTL_OFLOW_STATUS; }
> +
> +static void write_msmon_ctl_flt_vals(struct mon_read *m, u32 ctl_val,
> +				     u32 flt_val)
> +{
> +	struct mpam_msc *msc = m->ris->vmsc->msc;
> +
> +	/*
> +	 * Write the ctl_val with the enable bit cleared, reset the counter,
> +	 * then enable counter.
> +	 */
> +	switch (m->type) {
> +	case mpam_feat_msmon_csu:
> +		mpam_write_monsel_reg(msc, CFG_CSU_FLT, flt_val);
> +		mpam_write_monsel_reg(msc, CFG_CSU_CTL, ctl_val);
> +		mpam_write_monsel_reg(msc, CSU, 0);
> +		mpam_write_monsel_reg(msc, CFG_CSU_CTL, ctl_val |
> MSMON_CFG_x_CTL_EN);
> +		break;
> +	case mpam_feat_msmon_mbwu:
> +		mpam_write_monsel_reg(msc, CFG_MBWU_FLT, flt_val);
> +		mpam_write_monsel_reg(msc, CFG_MBWU_CTL, ctl_val);
> +		mpam_write_monsel_reg(msc, MBWU, 0);
> +		mpam_write_monsel_reg(msc, CFG_MBWU_CTL, ctl_val |
> MSMON_CFG_x_CTL_EN);
> +		break;
> +	default:
> +		return;
> +	}
> +}
> +
> +/* Call with MSC lock held */
> +static void __ris_msmon_read(void *arg) {
> +	u64 now;
> +	bool nrdy = false;
> +	struct mon_read *m = arg;
> +	struct mon_cfg *ctx = m->ctx;
> +	struct mpam_msc_ris *ris = m->ris;
> +	struct mpam_props *rprops = &ris->props;
> +	struct mpam_msc *msc = m->ris->vmsc->msc;
> +	u32 mon_sel, ctl_val, flt_val, cur_ctl, cur_flt;
> +
> +	if (!mpam_mon_sel_lock(msc)) {
> +		m->err = -EIO;
> +		return;
> +	}
> +	mon_sel = FIELD_PREP(MSMON_CFG_MON_SEL_MON_SEL,
> ctx->mon) |
> +		  FIELD_PREP(MSMON_CFG_MON_SEL_RIS, ris->ris_idx);
> +	mpam_write_monsel_reg(msc, CFG_MON_SEL, mon_sel);
> +
> +	/*
> +	 * Read the existing configuration to avoid re-writing the same values.
> +	 * This saves waiting for 'nrdy' on subsequent reads.
> +	 */
> +	read_msmon_ctl_flt_vals(m, &cur_ctl, &cur_flt);
> +	clean_msmon_ctl_val(&cur_ctl);
> +	gen_msmon_ctl_flt_vals(m, &ctl_val, &flt_val);
> +	if (cur_flt != flt_val || cur_ctl != (ctl_val | MSMON_CFG_x_CTL_EN))
> +		write_msmon_ctl_flt_vals(m, ctl_val, flt_val);

When reading the CSU counter of a different control group, the counter is cleared to 0 by the write_msmon_ctl_flt_vals().

> +	switch (m->type) {
> +	case mpam_feat_msmon_csu:
> +		now = mpam_read_monsel_reg(msc, CSU);
> +		if (mpam_has_feature(mpam_feat_msmon_csu_hw_nrdy,
> rprops))
> +			nrdy = now & MSMON___NRDY;
> +		break;

The first time read the counter(MSMON_CSU), all bits except nrdy are 0.

This means when check the cache monitoring value the first time,
cat mon_data/mon_L3_0*/llc_occupancy
the result will be 0.
>From the second time, the result will return to normal.

Best regards,
Shaopeng TAN


> +	case mpam_feat_msmon_mbwu:
> +		now = mpam_read_monsel_reg(msc, MBWU);
> +		if (mpam_has_feature(mpam_feat_msmon_mbwu_hw_nrdy,
> rprops))
> +			nrdy = now & MSMON___NRDY;
> +		break;
> +	default:
> +		m->err = -EINVAL;
> +		break;
> +	}
> +	mpam_mon_sel_unlock(msc);
> +
> +	if (nrdy) {
> +		m->err = -EBUSY;
> +		return;
> +	}
> +
> +	now = FIELD_GET(MSMON___VALUE, now);
> +	*m->val += now;
> +}
> +
> +static int _msmon_read(struct mpam_component *comp, struct mon_read
> +*arg) {
> +	int err,  any_err = 0;
> +	struct mpam_vmsc *vmsc;
> +
> +	guard(srcu)(&mpam_srcu);
> +	list_for_each_entry_srcu(vmsc, &comp->vmsc, comp_list,
> +				 srcu_read_lock_held(&mpam_srcu)) {
> +		struct mpam_msc *msc = vmsc->msc;
> +		struct mpam_msc_ris *ris;
> +
> +		list_for_each_entry_srcu(ris, &vmsc->ris, vmsc_list,
> +
> srcu_read_lock_held(&mpam_srcu)) {
> +			arg->ris = ris;
> +
> +			err = smp_call_function_any(&msc->accessibility,
> +						    __ris_msmon_read, arg,
> +						    true);
> +			if (!err && arg->err)
> +				err = arg->err;
> +
> +			/*
> +			 * Save one error to be returned to the caller, but
> +			 * keep reading counters so that get reprogrammed.
> On
> +			 * platforms with NRDY this lets us wait once.
> +			 */
> +			if (err)
> +				any_err = err;
> +		}
> +	}
> +
> +	return any_err;
> +}
> +
> +int mpam_msmon_read(struct mpam_component *comp, struct mon_cfg
> *ctx,
> +		    enum mpam_device_features type, u64 *val) {
> +	int err;
> +	struct mon_read arg;
> +	u64 wait_jiffies = 0;
> +	struct mpam_props *cprops = &comp->class->props;
> +
> +	might_sleep();
> +
> +	if (!mpam_is_enabled())
> +		return -EIO;
> +
> +	if (!mpam_has_feature(type, cprops))
> +		return -EOPNOTSUPP;
> +
> +	arg = (struct mon_read) {
> +		.ctx = ctx,
> +		.type = type,
> +		.val = val,
> +	};
> +	*val = 0;
> +
> +	err = _msmon_read(comp, &arg);
> +	if (err == -EBUSY && comp->class->nrdy_usec)
> +		wait_jiffies = usecs_to_jiffies(comp->class->nrdy_usec);
> +
> +	while (wait_jiffies)
> +		wait_jiffies = schedule_timeout_uninterruptible(wait_jiffies);
> +
> +	if (err == -EBUSY) {
> +		arg = (struct mon_read) {
> +			.ctx = ctx,
> +			.type = type,
> +			.val = val,
> +		};
> +		*val = 0;
> +
> +		err = _msmon_read(comp, &arg);
> +	}
> +
> +	return err;
> +}
> +
>  static void mpam_reset_msc_bitmap(struct mpam_msc *msc, u16 reg, u16
> wd)  {
>  	u32 num_words, msb;
> diff --git a/drivers/resctrl/mpam_internal.h
> b/drivers/resctrl/mpam_internal.h index 96a02ea95583..0c84e945c891 100644
> --- a/drivers/resctrl/mpam_internal.h
> +++ b/drivers/resctrl/mpam_internal.h
> @@ -183,6 +183,22 @@ struct mpam_props {
>  #define mpam_set_feature(_feat, x)	set_bit(_feat, (x)->features)
>  #define mpam_clear_feature(_feat, x)	clear_bit(_feat, (x)->features)
> 
> +/* The values for MSMON_CFG_MBWU_FLT.RWBW */ enum
> mon_filter_options {
> +	COUNT_BOTH	= 0,
> +	COUNT_WRITE	= 1,
> +	COUNT_READ	= 2,
> +};
> +
> +struct mon_cfg {
> +	u16                     mon;
> +	u8                      pmg;
> +	bool                    match_pmg;
> +	bool			csu_exclude_clean;
> +	u32                     partid;
> +	enum mon_filter_options opts;
> +};
> +
>  struct mpam_class {
>  	/* mpam_components in this class */
>  	struct list_head	components;
> @@ -325,6 +341,9 @@ void mpam_disable(struct work_struct *work);  int
> mpam_apply_config(struct mpam_component *comp, u16 partid,
>  		      struct mpam_config *cfg);
> 
> +int mpam_msmon_read(struct mpam_component *comp, struct mon_cfg
> *ctx,
> +		    enum mpam_device_features, u64 *val);
> +
>  int mpam_get_cpumask_from_cache_id(unsigned long cache_id, u32
> cache_level,
>  				   cpumask_t *affinity);
> 
> --
> 2.39.5

Powered by blists - more mailing lists