From: Jonathan Cameron <jonathan.cameron@huawei.com>
To: Ben Horgan <ben.horgan@arm.com>
Cc: <amitsinght@marvell.com>, <baisheng.gao@unisoc.com>,
<baolin.wang@linux.alibaba.com>, <carl@os.amperecomputing.com>,
<dave.martin@arm.com>, <david@kernel.org>,
<dfustini@baylibre.com>, <fenghuay@nvidia.com>,
<gshan@redhat.com>, <james.morse@arm.com>, <kobak@nvidia.com>,
<lcherian@marvell.com>, <linux-arm-kernel@lists.infradead.org>,
<linux-kernel@vger.kernel.org>, <peternewman@google.com>,
<punit.agrawal@oss.qualcomm.com>, <quic_jiles@quicinc.com>,
<reinette.chatre@intel.com>, <rohit.mathew@arm.com>,
<scott@os.amperecomputing.com>, <sdonthineni@nvidia.com>,
<tan.shaopeng@fujitsu.com>, <xhao@linux.alibaba.com>,
<catalin.marinas@arm.com>, <will@kernel.org>, <corbet@lwn.net>,
<maz@kernel.org>, <oupton@kernel.org>, <joey.gouly@arm.com>,
<suzuki.poulose@arm.com>, <kvmarm@lists.linux.dev>,
"Zeng Heng" <zengheng4@huawei.com>
Subject: Re: [PATCH v2 40/45] arm_mpam: Generate a configuration for min controls
Date: Tue, 6 Jan 2026 15:09:07 +0000 [thread overview]
Message-ID: <20260106150907.0000457b@huawei.com> (raw)
In-Reply-To: <20251219181147.3404071-41-ben.horgan@arm.com>
On Fri, 19 Dec 2025 18:11:42 +0000
Ben Horgan <ben.horgan@arm.com> wrote:
> From: James Morse <james.morse@arm.com>
>
> MPAM supports a minimum and maximum control for memory bandwidth. The
> purpose of the minimum control is to give priority to tasks that are below
> their minimum value. Resctrl only provides one value for the bandwidth
> configuration, which is used for the maximum.
>
> The minimum control is always programmed to zero on hardware that supports
> it.
>
> Generate a minimum bandwidth value that is 5% lower than the value provided
> by resctrl. This means tasks that are not receiving their target bandwidth
> can be prioritised by the hardware.
I'm not sure this policy make sense in general as there will be bandwidth
heavy background tasks where we want to make sure they only use up to X%
of bandwidth, but don't care if they don't get that. I guess maybe those
are always in the %5 or less category so maybe this policy is fine.
Ah well, can revisit later I guess as long as we keep this as the default
for any new controls.
>
> For component reset reuse the same calculation so that the default is a
> value resctrl can set.
>
> CC: Zeng Heng <zengheng4@huawei.com>
> Signed-off-by: James Morse <james.morse@arm.com>
> Signed-off-by: Ben Horgan <ben.horgan@arm.com>
Most, maybe all the other cases have split test from implementation. I'd
probably do that here just for consistency.
A few things inline.
J
> ---
> Add reset_mbw_min
> Clear min cfg when setting max
> use mpam_extend_config on component reset
> ---
> drivers/resctrl/mpam_devices.c | 76 +++++++++++++++++++++++++++--
> drivers/resctrl/mpam_internal.h | 3 ++
> drivers/resctrl/mpam_resctrl.c | 2 +
> drivers/resctrl/test_mpam_devices.c | 66 +++++++++++++++++++++++++
> 4 files changed, 142 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
> index c20b2757b86b..deea46c2a6c3 100644
> --- a/drivers/resctrl/mpam_devices.c
> +++ b/drivers/resctrl/mpam_devices.c
> @@ -721,6 +721,13 @@ static void mpam_ris_hw_probe(struct mpam_msc_ris *ris)
> mpam_set_feature(mpam_feat_mbw_part, props);
>
> props->bwa_wd = FIELD_GET(MPAMF_MBW_IDR_BWA_WD, mbw_features);
> +
> + /*
> + * The BWA_WD field can represent 0-63, but the control fields it
> + * describes have a maximum of 16 bits.
I'm lost to why this only matters now! Feels like that makes sense way earlier
in the series. Particularly as that detail confused me no end in the bandwidth
/ percent calculation patches.
> + */
> + props->bwa_wd = min(props->bwa_wd, 16);
> +
> if (props->bwa_wd && FIELD_GET(MPAMF_MBW_IDR_HAS_MAX, mbw_features))
> mpam_set_feature(mpam_feat_mbw_max, props);
>
> +static void mpam_extend_config(struct mpam_class *class, struct mpam_config *cfg)
> +{
> + struct mpam_props *cprops = &class->props;
> + u16 min, min_hw_granule, delta;
> + u16 max_hw_value, res0_bits;
Probably makes sense to drag some of these into the scope below.
> +
> + /*
> + * MAX and MIN should be set together. If only one is provided,
> + * generate a configuration for the other. If only one control
> + * type is supported, the other value will be ignored.
> + *
> + * Resctrl can only configure the MAX.
> + */
> + if (mpam_has_feature(mpam_feat_mbw_max, cfg) &&
> + !mpam_has_feature(mpam_feat_mbw_min, cfg)) {
> + /*
> + * Calculate the values the 'min' control can hold.
> + * e.g. on a platform with bwa_wd = 8, min_hw_granule is 0x00ff
> + * because those bits are RES0. Configurations of this value
> + * are effectively zero. But configurations need to saturate
> + * at min_hw_granule on systems with mismatched bwa_wd, where
> + * the 'less than 0' values are implemented on some MSC, but
> + * not others.
> + */
> + res0_bits = 16 - cprops->bwa_wd;
> + max_hw_value = ((1 << cprops->bwa_wd) - 1) << res0_bits;
> + min_hw_granule = ~max_hw_value;
> +
> + delta = ((5 * MPAMCFG_MBW_MAX_MAX) / 100) - 1;
> + if (cfg->mbw_max > delta)
> + min = cfg->mbw_max - delta;
> + else
> + min = 0;
> +
> + cfg->mbw_min = max(min, min_hw_granule);
> + mpam_set_feature(mpam_feat_mbw_min, cfg);
> + }
> +}
> +
>
next prev parent reply other threads:[~2026-01-06 15:09 UTC|newest]
Thread overview: 120+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-12-19 18:11 [PATCH v2 00/45] arm_mpam: Add KVM/arm64 and resctrl glue code Ben Horgan
2025-12-19 18:11 ` [PATCH v2 01/45] arm_mpam: Stop using uninitialized variables in __ris_msmon_read() Ben Horgan
2025-12-23 11:58 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 02/45] arm_mpam: Remove duplicate linux/srcu.h header Ben Horgan
2025-12-23 12:10 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 03/45] arm_mpam: Use non-atomic bitops when modifying feature bitmap Ben Horgan
2026-01-05 16:34 ` Jonathan Cameron
2026-01-06 11:11 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 04/45] arm64/sysreg: Add MPAMSM_EL1 register Ben Horgan
2026-01-05 16:36 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 05/45] KVM: arm64: Preserve host MPAM configuration when changing traps Ben Horgan
2025-12-19 20:01 ` Oliver Upton
2026-01-02 11:43 ` Ben Horgan
2026-01-05 16:43 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 06/45] KVM: arm64: Make MPAMSM_EL1 accesses UNDEF Ben Horgan
2026-01-05 16:47 ` Jonathan Cameron
2026-01-05 16:57 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 07/45] arm64: mpam: Context switch the MPAM registers Ben Horgan
2026-01-05 17:04 ` Jonathan Cameron
2026-01-06 11:14 ` Ben Horgan
2026-01-06 14:03 ` Jonathan Cameron
2026-01-08 10:06 ` Shaopeng Tan (Fujitsu)
2026-01-09 9:28 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 08/45] arm64: mpam: Re-initialise MPAM regs when CPU comes online Ben Horgan
2026-01-05 17:06 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 09/45] arm64: mpam: Advertise the CPUs MPAM limits to the driver Ben Horgan
2026-01-05 17:08 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 10/45] arm64: mpam: Add cpu_pm notifier to restore MPAM sysregs Ben Horgan
2026-01-05 17:09 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 11/45] arm64: mpam: Initialise and context switch the MPAMSM_EL1 register Ben Horgan
2026-01-05 17:20 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 12/45] arm64: mpam: Add helpers to change a task or cpu's MPAM PARTID/PMG values Ben Horgan
2026-01-05 17:21 ` Jonathan Cameron
2026-01-08 10:18 ` Shaopeng Tan (Fujitsu)
2026-01-09 9:37 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 13/45] KVM: arm64: Force guest EL1 to use user-space's partid configuration Ben Horgan
2025-12-19 20:10 ` Oliver Upton
2026-01-02 11:48 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 14/45] KVM: arm64: Use kernel-space partid configuration for hypercalls Ben Horgan
2025-12-19 18:11 ` [PATCH v2 15/45] arm_mpam: resctrl: Add boilerplate cpuhp and domain allocation Ben Horgan
2026-01-05 17:40 ` Jonathan Cameron
2026-01-06 11:17 ` Ben Horgan
2026-01-08 10:36 ` Shaopeng Tan (Fujitsu)
2026-01-09 9:55 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 16/45] arm_mpam: resctrl: Sort the order of the domain lists Ben Horgan
2026-01-05 17:42 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 17/45] arm_mpam: resctrl: Pick the caches we will use as resctrl resources Ben Horgan
2026-01-05 17:46 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 18/45] arm_mpam: resctrl: Implement resctrl_arch_reset_all_ctrls() Ben Horgan
2026-01-05 17:51 ` Jonathan Cameron
2026-01-06 11:19 ` Ben Horgan
2026-01-09 3:45 ` Zeng Heng
2026-01-13 17:18 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 19/45] arm_mpam: resctrl: Add resctrl_arch_get_config() Ben Horgan
2026-01-05 17:53 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 20/45] arm_mpam: resctrl: Implement helpers to update configuration Ben Horgan
2026-01-05 17:58 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 21/45] arm_mpam: resctrl: Add plumbing against arm64 task and cpu hooks Ben Horgan
2026-01-05 18:02 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 22/45] arm_mpam: resctrl: Add CDP emulation Ben Horgan
2026-01-05 18:07 ` Jonathan Cameron
2026-01-06 11:21 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 23/45] arm_mpam: resctrl: Add rmid index helpers Ben Horgan
2026-01-06 11:21 ` Jonathan Cameron
2026-01-06 11:33 ` Ben Horgan
2026-01-06 14:04 ` Jonathan Cameron
2026-01-06 15:23 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 24/45] arm_mpam: resctrl: Convert to/from MPAMs fixed-point formats Ben Horgan
2026-01-06 11:55 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 25/45] arm_mpam: resctrl: Add support for 'MB' resource Ben Horgan
2025-12-27 8:10 ` [PATCH v2 0/45] arm_mpam: Add KVM/arm64 and resctrl glue code Zeng Heng
2026-01-06 12:19 ` [PATCH v2 25/45] arm_mpam: resctrl: Add support for 'MB' resource Jonathan Cameron
2026-01-07 14:21 ` Ben Horgan
2026-01-08 10:42 ` Shaopeng Tan (Fujitsu)
2026-01-12 16:45 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 26/45] arm_mpam: resctrl: Add kunit test for control format conversions Ben Horgan
2026-01-06 12:30 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 27/45] arm_mpam: resctrl: Add support for csu counters Ben Horgan
2026-01-06 12:40 ` Jonathan Cameron
2026-01-08 10:44 ` Shaopeng Tan (Fujitsu)
2026-01-08 10:52 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 28/45] arm_mpam: resctrl: Pick classes for use as mbm counters Ben Horgan
2026-01-06 14:01 ` Jonathan Cameron
2026-01-07 15:19 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 29/45] arm_mpam: resctrl: Pre-allocate free running monitors Ben Horgan
2026-01-06 14:22 ` Jonathan Cameron
2026-01-08 14:25 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 30/45] arm_mpam: resctrl: Pre-allocate assignable monitors Ben Horgan
2026-01-06 14:29 ` Jonathan Cameron
2026-01-08 14:33 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 31/45] arm_mpam: resctrl: Add kunit test for ABMC/CDP interactions Ben Horgan
2025-12-19 18:11 ` [PATCH v2 32/45] arm_mpam: resctrl: Add resctrl_arch_config_cntr() for ABMC use Ben Horgan
2026-01-06 14:33 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 33/45] arm_mpam: resctrl: Allow resctrl to allocate monitors Ben Horgan
2026-01-06 14:37 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 34/45] arm_mpam: resctrl: Add resctrl_arch_rmid_read() and resctrl_arch_reset_rmid() Ben Horgan
2026-01-06 14:43 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 35/45] arm_mpam: resctrl: Add resctrl_arch_cntr_read() & resctrl_arch_reset_cntr() Ben Horgan
2026-01-06 14:44 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 36/45] arm_mpam: resctrl: Update the rmid reallocation limit Ben Horgan
2026-01-06 14:46 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 37/45] arm_mpam: resctrl: Add empty definitions for assorted resctrl functions Ben Horgan
2026-01-06 14:48 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 38/45] arm64: mpam: Select ARCH_HAS_CPU_RESCTRL Ben Horgan
2026-01-06 14:49 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 39/45] arm_mpam: resctrl: Call resctrl_init() on platforms that can support resctrl Ben Horgan
2026-01-06 14:58 ` Jonathan Cameron
2026-01-08 14:53 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 40/45] arm_mpam: Generate a configuration for min controls Ben Horgan
2026-01-06 15:09 ` Jonathan Cameron [this message]
2026-01-08 15:35 ` Ben Horgan
2025-12-19 18:11 ` [PATCH v2 41/45] arm_mpam: Add quirk framework Ben Horgan
2026-01-06 15:14 ` Jonathan Cameron
2026-01-06 15:15 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 42/45] arm_mpam: Add workaround for T241-MPAM-1 Ben Horgan
2025-12-19 18:11 ` [PATCH v2 43/45] arm_mpam: Add workaround for T241-MPAM-4 Ben Horgan
2026-01-06 15:20 ` Jonathan Cameron
2025-12-19 18:11 ` [PATCH v2 44/45] arm_mpam: Add workaround for T241-MPAM-6 Ben Horgan
2025-12-19 18:11 ` [PATCH v2 45/45] arm_mpam: Quirk CMN-650's CSU NRDY behaviour Ben Horgan
2026-01-08 19:22 ` (subset) [PATCH v2 00/45] arm_mpam: Add KVM/arm64 and resctrl glue code Catalin Marinas
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=20260106150907.0000457b@huawei.com \
--to=jonathan.cameron@huawei.com \
--cc=amitsinght@marvell.com \
--cc=baisheng.gao@unisoc.com \
--cc=baolin.wang@linux.alibaba.com \
--cc=ben.horgan@arm.com \
--cc=carl@os.amperecomputing.com \
--cc=catalin.marinas@arm.com \
--cc=corbet@lwn.net \
--cc=dave.martin@arm.com \
--cc=david@kernel.org \
--cc=dfustini@baylibre.com \
--cc=fenghuay@nvidia.com \
--cc=gshan@redhat.com \
--cc=james.morse@arm.com \
--cc=joey.gouly@arm.com \
--cc=kobak@nvidia.com \
--cc=kvmarm@lists.linux.dev \
--cc=lcherian@marvell.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maz@kernel.org \
--cc=oupton@kernel.org \
--cc=peternewman@google.com \
--cc=punit.agrawal@oss.qualcomm.com \
--cc=quic_jiles@quicinc.com \
--cc=reinette.chatre@intel.com \
--cc=rohit.mathew@arm.com \
--cc=scott@os.amperecomputing.com \
--cc=sdonthineni@nvidia.com \
--cc=suzuki.poulose@arm.com \
--cc=tan.shaopeng@fujitsu.com \
--cc=will@kernel.org \
--cc=xhao@linux.alibaba.com \
--cc=zengheng4@huawei.com \
/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