Re: [PATCH v2 20/29] arm_mpam: Allow configuration to be applied and restored during cpu online
From: Fenghua Yu <fenghuay@nvidia.com>
Date: 2025-09-25 06:53:49
Also in:
linux-acpi, lkml
Hi, James, On 9/10/25 13:43, James Morse wrote:
quoted hunk ↗ jump to hunk
When CPUs come online the MSC's original configuration should be restored. Add struct mpam_config to hold the configuration. This has a bitmap of features that were modified. Once the maximum partid is known, allocate a configuration array for each component, and reprogram each RIS configuration from this. CC: Dave Martin <Dave.Martin@arm.com> Signed-off-by: James Morse <james.morse@arm.com> --- Changes since v1: * Switched entry_rcu to srcu versions. Changes since RFC: * Added a comment about the ordering around max_partid. * Allocate configurations after interrupts are registered to reduce churn. * Added mpam_assert_partid_sizes_fixed(); * Make reset use an all-ones instead of zero config. --- drivers/resctrl/mpam_devices.c | 269 +++++++++++++++++++++++++++++--- drivers/resctrl/mpam_internal.h | 29 +++- 2 files changed, 271 insertions(+), 27 deletions(-)diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c index ec1db5f8b05c..7fd149109c75 100644 --- a/drivers/resctrl/mpam_devices.c +++ b/drivers/resctrl/mpam_devices.c@@ -114,6 +114,16 @@ static LLIST_HEAD(mpam_garbage); /* When mpam is disabled, the printed reason to aid debugging */ static char *mpam_disable_reason; +/* + * Once mpam is enabled, new requestors cannot further reduce the available + * partid. Assert that the size is fixed, and new requestors will be turned + * away. + */ +static void mpam_assert_partid_sizes_fixed(void) +{ + WARN_ON_ONCE(!partid_max_published); +} + static u32 __mpam_read_reg(struct mpam_msc *msc, u16 reg) { WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &msc->accessibility));@@ -363,12 +373,16 @@ static void mpam_class_destroy(struct mpam_class *class) add_to_garbage(class); } +static void __destroy_component_cfg(struct mpam_component *comp); + static void mpam_comp_destroy(struct mpam_component *comp) { struct mpam_class *class = comp->class; lockdep_assert_held(&mpam_list_lock); + __destroy_component_cfg(comp); + list_del_rcu(&comp->class_list); add_to_garbage(comp);@@ -833,50 +847,105 @@ static void mpam_reset_msc_bitmap(struct mpam_msc *msc, u16 reg, u16 wd) __mpam_write_reg(msc, reg, bm); } -static void mpam_reset_ris_partid(struct mpam_msc_ris *ris, u16 partid) +/* 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) { struct mpam_msc *msc = ris->vmsc->msc; struct mpam_props *rprops = &ris->props; - mpam_assert_srcu_read_lock_held(); - mutex_lock(&msc->part_sel_lock); __mpam_part_sel(ris->ris_idx, partid, msc); - if (mpam_has_feature(mpam_feat_cpor_part, rprops)) - mpam_reset_msc_bitmap(msc, MPAMCFG_CPBM, rprops->cpbm_wd); + if (mpam_has_feature(mpam_feat_cpor_part, rprops) && + mpam_has_feature(mpam_feat_cpor_part, cfg)) { + if (cfg->reset_cpbm) + mpam_reset_msc_bitmap(msc, MPAMCFG_CPBM, + rprops->cpbm_wd); + else + mpam_write_partsel_reg(msc, CPBM, cfg->cpbm); + } - if (mpam_has_feature(mpam_feat_mbw_part, rprops)) - mpam_reset_msc_bitmap(msc, MPAMCFG_MBW_PBM, rprops->mbw_pbm_bits); + if (mpam_has_feature(mpam_feat_mbw_part, rprops) && + mpam_has_feature(mpam_feat_mbw_part, cfg)) { + if (cfg->reset_mbw_pbm) + mpam_reset_msc_bitmap(msc, MPAMCFG_MBW_PBM, + rprops->mbw_pbm_bits); + else + mpam_write_partsel_reg(msc, MBW_PBM, cfg->mbw_pbm); + } - if (mpam_has_feature(mpam_feat_mbw_min, rprops)) + if (mpam_has_feature(mpam_feat_mbw_min, rprops) && + mpam_has_feature(mpam_feat_mbw_min, cfg)) mpam_write_partsel_reg(msc, MBW_MIN, 0); - if (mpam_has_feature(mpam_feat_mbw_max, rprops)) - mpam_write_partsel_reg(msc, MBW_MAX, MPAMCFG_MBW_MAX_MAX); + if (mpam_has_feature(mpam_feat_mbw_max, rprops) && + mpam_has_feature(mpam_feat_mbw_max, cfg)) + mpam_write_partsel_reg(msc, MBW_MAX, cfg->mbw_max); - if (mpam_has_feature(mpam_feat_mbw_prop, rprops)) + if (mpam_has_feature(mpam_feat_mbw_prop, rprops) && + mpam_has_feature(mpam_feat_mbw_prop, cfg)) mpam_write_partsel_reg(msc, MBW_PROP, 0); mutex_unlock(&msc->part_sel_lock); } +struct reprogram_ris { + struct mpam_msc_ris *ris; + struct mpam_config *cfg; +}; + +/* Call with MSC lock held */ +static int mpam_reprogram_ris(void *_arg) +{ + u16 partid, partid_max; + struct reprogram_ris *arg = _arg; + struct mpam_msc_ris *ris = arg->ris; + struct mpam_config *cfg = arg->cfg; + + if (ris->in_reset_state) + return 0; + + spin_lock(&partid_max_lock); + partid_max = mpam_partid_max; + spin_unlock(&partid_max_lock); + for (partid = 0; partid <= partid_max; partid++) + mpam_reprogram_ris_partid(ris, partid, cfg); + + return 0; +} + +static void mpam_init_reset_cfg(struct mpam_config *reset_cfg) +{ + memset(reset_cfg, 0, sizeof(*reset_cfg)); + + reset_cfg->features = ~0; + reset_cfg->cpbm = ~0; + reset_cfg->mbw_pbm = ~0; + reset_cfg->mbw_max = MPAMCFG_MBW_MAX_MAX; + + reset_cfg->reset_cpbm = true; + reset_cfg->reset_mbw_pbm = true; +} + /* * Called via smp_call_on_cpu() to prevent migration, while still being * pre-emptible. */ static int mpam_reset_ris(void *arg) { - u16 partid, partid_max; + struct mpam_config reset_cfg; struct mpam_msc_ris *ris = arg; + struct reprogram_ris reprogram_arg; if (ris->in_reset_state) return 0; - spin_lock(&partid_max_lock); - partid_max = mpam_partid_max; - spin_unlock(&partid_max_lock); - for (partid = 0; partid < partid_max; partid++) - mpam_reset_ris_partid(ris, partid); + mpam_init_reset_cfg(&reset_cfg); + + reprogram_arg.ris = ris; + reprogram_arg.cfg = &reset_cfg; + + mpam_reprogram_ris(&reprogram_arg); return 0; }@@ -922,6 +991,40 @@ static void mpam_reset_msc(struct mpam_msc *msc, bool online) } } +static void mpam_reprogram_msc(struct mpam_msc *msc) +{ + u16 partid; + bool reset; + struct mpam_config *cfg; + struct mpam_msc_ris *ris; + + /* + * No lock for mpam_partid_max as partid_max_published has been + * set by mpam_enabled(), so the values can no longer change. + */ + mpam_assert_partid_sizes_fixed(); + + guard(srcu)(&mpam_srcu);
mpam_srcu is locked in caller mpam_cpu_online(). It's unnecessary to call guard(srcu)(&mpam_srcu) here again for simpler logic and less overhead.
quoted hunk ↗ jump to hunk
+ list_for_each_entry_srcu(ris, &msc->ris, msc_list, + srcu_read_lock_held(&mpam_srcu)) { + if (!mpam_is_enabled() && !ris->in_reset_state) { + mpam_touch_msc(msc, &mpam_reset_ris, ris); + ris->in_reset_state = true; + continue; + } + + reset = true; + for (partid = 0; partid <= mpam_partid_max; partid++) { + cfg = &ris->vmsc->comp->cfg[partid]; + if (cfg->features) + reset = false; + + mpam_reprogram_ris_partid(ris, partid, cfg); + } + ris->in_reset_state = reset; + } +} + static void _enable_percpu_irq(void *_irq) { int *irq = _irq;@@ -944,7 +1047,7 @@ static int mpam_cpu_online(unsigned int cpu) _enable_percpu_irq(&msc->reenable_error_ppi); if (atomic_fetch_inc(&msc->online_refs) == 0) - mpam_reset_msc(msc, true); + mpam_reprogram_msc(msc); } srcu_read_unlock(&mpam_srcu, idx);
[SNIP] Thanks. -Fenghua