| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <23f08379-301d-4ffc-bf6f-d6a7bb952724@nvidia.com>
Date: Thu, 15 Jan 2026 15:20:55 -0800
From: Fenghua Yu <fenghuay@...dia.com>
To: Ben Horgan <ben.horgan@....com>
Cc: amitsinght@...vell.com, baisheng.gao@...soc.com,
baolin.wang@...ux.alibaba.com, carl@...amperecomputing.com,
dave.martin@....com, david@...nel.org, dfustini@...libre.com,
gshan@...hat.com, james.morse@....com, jonathan.cameron@...wei.com,
kobak@...dia.com, lcherian@...vell.com,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
peternewman@...gle.com, punit.agrawal@....qualcomm.com,
quic_jiles@...cinc.com, reinette.chatre@...el.com, rohit.mathew@....com,
scott@...amperecomputing.com, sdonthineni@...dia.com,
tan.shaopeng@...itsu.com, xhao@...ux.alibaba.com, catalin.marinas@....com,
will@...nel.org, corbet@....net, maz@...nel.org, oupton@...nel.org,
joey.gouly@....com, suzuki.poulose@....com, kvmarm@...ts.linux.dev
Subject: Re: [PATCH v3 45/47] arm_mpam: Add workaround for T241-MPAM-4
Hi, Shanker and Ben,
On 1/12/26 08:59, Ben Horgan wrote:
> From: Shanker Donthineni <sdonthineni@...dia.com>
>
> In the T241 implementation of memory-bandwidth partitioning, in the absence
> of contention for bandwidth, the minimum bandwidth setting can affect the
> amount of achieved bandwidth. Specifically, the achieved bandwidth in the
> absence of contention can settle to any value between the values of
> MPAMCFG_MBW_MIN and MPAMCFG_MBW_MAX. Also, if MPAMCFG_MBW_MIN is set
> zero (below 0.78125%), once a core enters a throttled state, it will never
> leave that state.
>
> The first issue is not a concern if the MPAM software allows to program
> MPAMCFG_MBW_MIN through the sysfs interface. This patch ensures program
> MBW_MIN=1 (0.78125%) whenever MPAMCFG_MBW_MIN=0 is programmed.
When MBW_MIN=1, min mem bw can be very low when contention. This may
drop mem access performance. Is it possible to set MBW_MIN bigger so
that ensure the floor of mem access is high?
Thanks.
-Fenghua
>
> In the scenario where the resctrl doesn't support the MBW_MIN interface via
> sysfs, to achieve bandwidth closer to MBW_MAX in the absence of contention,
> software should configure a relatively narrow gap between MBW_MIN and
> MBW_MAX. The recommendation is to use a 5% gap to mitigate the problem.
>
> [ morse: Added as second quirk, adapted to use the new intermediate values
> in mpam_extend_config() ]
>
> Signed-off-by: Shanker Donthineni <sdonthineni@...dia.com>
> Signed-off-by: James Morse <james.morse@....com>
> Signed-off-by: Ben Horgan <ben.horgan@....com>
> ---
> Changes since rfc:
> MPAM_IIDR_NVIDIA_T421 -> MPAM_IIDR_NVIDIA_T241
> Handling when reset_mbw_min is set
> ---
> Documentation/arch/arm64/silicon-errata.rst | 2 ++
> drivers/resctrl/mpam_devices.c | 34 +++++++++++++++++++--
> drivers/resctrl/mpam_internal.h | 1 +
> 3 files changed, 34 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
> index 4e86b85fe3d6..b18bc704d4a1 100644
> --- a/Documentation/arch/arm64/silicon-errata.rst
> +++ b/Documentation/arch/arm64/silicon-errata.rst
> @@ -248,6 +248,8 @@ stable kernels.
> +----------------+-----------------+-----------------+-----------------------------+
> | NVIDIA | T241 MPAM | T241-MPAM-1 | N/A |
> +----------------+-----------------+-----------------+-----------------------------+
> +| NVIDIA | T241 MPAM | T241-MPAM-4 | N/A |
> ++----------------+-----------------+-----------------+-----------------------------+
> +----------------+-----------------+-----------------+-----------------------------+
> | Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 |
> +----------------+-----------------+-----------------+-----------------------------+
> diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
> index bdf13a22d98f..884ca6a6d8f3 100644
> --- a/drivers/resctrl/mpam_devices.c
> +++ b/drivers/resctrl/mpam_devices.c
> @@ -679,6 +679,12 @@ static const struct mpam_quirk mpam_quirks[] = {
> .iidr_mask = MPAM_IIDR_MATCH_ONE,
> .workaround = T241_SCRUB_SHADOW_REGS,
> },
> + {
> + /* NVIDIA t241 erratum T241-MPAM-4 */
> + .iidr = MPAM_IIDR_NVIDIA_T241,
> + .iidr_mask = MPAM_IIDR_MATCH_ONE,
> + .workaround = T241_FORCE_MBW_MIN_TO_ONE,
> + },
> { NULL } /* Sentinel */
> };
>
> @@ -1464,6 +1470,17 @@ static void mpam_quirk_post_config_change(struct mpam_msc_ris *ris, u16 partid,
> mpam_apply_t241_erratum(ris, partid);
> }
>
> +static u16 mpam_wa_t241_force_mbw_min_to_one(struct mpam_props *props)
> +{
> + u16 max_hw_value, min_hw_granule, res0_bits;
> +
> + res0_bits = 16 - props->bwa_wd;
> + max_hw_value = ((1 << props->bwa_wd) - 1) << res0_bits;
> + min_hw_granule = ~max_hw_value;
> +
> + return min_hw_granule + 1;
> +}
> +
> /* Called via IPI. Call while holding an SRCU reference */
> static void mpam_reprogram_ris_partid(struct mpam_msc_ris *ris, u16 partid,
> struct mpam_config *cfg)
> @@ -1508,10 +1525,15 @@ static void mpam_reprogram_ris_partid(struct mpam_msc_ris *ris, u16 partid,
>
> if (mpam_has_feature(mpam_feat_mbw_min, rprops) &&
> mpam_has_feature(mpam_feat_mbw_min, cfg)) {
> - if (cfg->reset_mbw_min)
> - mpam_write_partsel_reg(msc, MBW_MIN, 0);
> - else
> + if (cfg->reset_mbw_min) {
> + u16 reset = 0;
> +
> + if (mpam_has_quirk(T241_FORCE_MBW_MIN_TO_ONE, msc))
> + reset = mpam_wa_t241_force_mbw_min_to_one(rprops);
> + mpam_write_partsel_reg(msc, MBW_MIN, reset);
> + } else {
> mpam_write_partsel_reg(msc, MBW_MIN, cfg->mbw_min);
> + }
> }
>
> if (mpam_has_feature(mpam_feat_mbw_max, rprops) &&
> @@ -2570,6 +2592,12 @@ static void mpam_extend_config(struct mpam_class *class, struct mpam_config *cfg
> cfg->mbw_min = max(min, min_hw_granule);
> mpam_set_feature(mpam_feat_mbw_min, cfg);
> }
> +
> + if (mpam_has_quirk(T241_FORCE_MBW_MIN_TO_ONE, class) &&
> + cfg->mbw_min <= min_hw_granule) {
> + cfg->mbw_min = min_hw_granule + 1;
> + mpam_set_feature(mpam_feat_mbw_min, cfg);
> + }
> }
>
> static void mpam_reset_component_cfg(struct mpam_component *comp)
> diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h
> index 9d15d37d4b5a..7b4566814945 100644
> --- a/drivers/resctrl/mpam_internal.h
> +++ b/drivers/resctrl/mpam_internal.h
> @@ -224,6 +224,7 @@ struct mpam_props {
> /* Workaround bits for msc->quirks */
> enum mpam_device_quirks {
> T241_SCRUB_SHADOW_REGS,
> + T241_FORCE_MBW_MIN_TO_ONE,
> MPAM_QUIRK_LAST
> };
>
Powered by blists - more mailing lists