| 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: <1021cc11-de18-4208-8262-f9cba80e5a88@arm.com>
Date: Tue, 9 Dec 2025 16:58:06 +0000
From: Ben Horgan <ben.horgan@....com>
To: James Morse <james.morse@....com>, linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org
Cc: D Scott Phillips OS <scott@...amperecomputing.com>,
carl@...amperecomputing.com, lcherian@...vell.com,
bobo.shaobowang@...wei.com, tan.shaopeng@...itsu.com,
baolin.wang@...ux.alibaba.com, Jamie Iles <quic_jiles@...cinc.com>,
Xin Hao <xhao@...ux.alibaba.com>, peternewman@...gle.com,
dfustini@...libre.com, amitsinght@...vell.com,
David Hildenbrand <david@...nel.org>, Dave Martin <dave.martin@....com>,
Koba Ko <kobak@...dia.com>, Shanker Donthineni <sdonthineni@...dia.com>,
fenghuay@...dia.com, baisheng.gao@...soc.com,
Jonathan Cameron <jonathan.cameron@...wei.com>, Gavin Shan
<gshan@...hat.com>, rohit.mathew@....com, reinette.chatre@...el.com,
Punit Agrawal <punit.agrawal@....qualcomm.com>
Subject: Re: [RFC PATCH 36/38] arm_mpam: Add workaround for T241-MPAM-4
Hi James,
On 12/5/25 21:58, James Morse 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 cocern 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.
>
> In the scenario where the resctrl doesn't support the MBW_MIN
> interface via sysfs, to achieve bandwidth closer to MW_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.
>
> Signed-off-by: Shanker Donthineni <sdonthineni@...dia.com>
> [ morse: Added as second quirk, adapted to use the new intermediate values
> in mpam_extend_config() ]
> Signed-off-by: James Morse <james.morse@....com>
> ---
> Documentation/arch/arm64/silicon-errata.rst | 2 +
> drivers/resctrl/mpam_devices.c | 60 ++++++++++++++++-----
> drivers/resctrl/mpam_internal.h | 1 +
> 3 files changed, 49 insertions(+), 14 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 f1f03ceade0a..5ba0aa703807 100644
> --- a/drivers/resctrl/mpam_devices.c
> +++ b/drivers/resctrl/mpam_devices.c
> @@ -678,6 +678,12 @@ 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_T421,
> + .iidr_mask = MPAM_IIDR_MATCH_ONE,
> + .workaround = T241_FORCE_MBW_MIN_TO_ONE,
> + },
> { NULL }, /* Sentinel */
> };
>
> @@ -1622,6 +1628,22 @@ static void mpam_init_reset_cfg(struct mpam_config *reset_cfg)
> bitmap_fill(reset_cfg->features, MPAM_FEATURE_LAST);
> }
>
> +/*
> + * This is not part of mpam_init_reset_cfg() as high level callers have the
> + * class, and low level callers a ris.
> + */
> +static void mpam_wa_t241_force_mbw_min_to_one(struct mpam_config *cfg,
> + 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;
> +
> + cfg->mbw_min = min_hw_granule + 1;
> +}
> +
> /*
> * Called via smp_call_on_cpu() to prevent migration, while still being
> * pre-emptible. Caller must hold mpam_srcu.
> @@ -2524,7 +2546,8 @@ static void __destroy_component_cfg(struct mpam_component *comp)
> static void mpam_reset_component_cfg(struct mpam_component *comp)
> {
> int i;
> - struct mpam_props *cprops = &comp->class->props;
> + struct mpam_class *class = comp->class;
> + struct mpam_props *cprops = &class->props;
>
> mpam_assert_partid_sizes_fixed();
>
> @@ -2539,6 +2562,10 @@ static void mpam_reset_component_cfg(struct mpam_component *comp)
> comp->cfg[i].mbw_pbm = GENMASK(cprops->mbw_pbm_bits - 1, 0);
> if (cprops->bwa_wd)
> comp->cfg[i].mbw_max = GENMASK(15, 16 - cprops->bwa_wd);
> +
> + if (mpam_has_quirk(T241_FORCE_MBW_MIN_TO_ONE, class))
> + mpam_wa_t241_force_mbw_min_to_one(&comp->cfg[i],
> + &class->props);
> }
> }
Also need to consider the mbw_min in mpam_reset_ris() reset config.
>
> @@ -2825,6 +2852,18 @@ static void mpam_extend_config(struct mpam_class *class, struct mpam_config *cfg
> u16 min, min_hw_granule, delta;
> u16 max_hw_value, res0_bits;
>
> + /*
> + * 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;
> +
> /*
> * MAX and MIN should be set together. If only one is provided,
> * generate a configuration for the other. If only one control
> @@ -2834,19 +2873,6 @@ static void mpam_extend_config(struct mpam_class *class, struct mpam_config *cfg
> */
> 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;
> @@ -2856,6 +2882,12 @@ 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);
> + }
> }
>
> int mpam_apply_config(struct mpam_component *comp, u16 partid,
> diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h
> index 70b78cfd1f5b..01882f0acee2 100644
> --- a/drivers/resctrl/mpam_internal.h
> +++ b/drivers/resctrl/mpam_internal.h
> @@ -223,6 +223,7 @@ 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,
> };
>
Thanks,
Ben
Powered by blists - more mailing lists