diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index 6c245582d8fb..627e23869bca 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -446,6 +446,12 @@ during mkdir. max_threshold_occupancy is a user configurable value to determine the occupancy at which an RMID can be freed. +The mon_llc_occupancy_limbo tracepoint gives the precise occupancy in bytes +for a subset of RMID that are not immediately available for allocation. +This can't be relied on to produce output every second, it may be necessary +to attempt to create an empty monitor group to force an update. Output may +only be produced if creation of a control or monitor group fails. + Schemata files - general concepts --------------------------------- Each line in the file describes one resource. The line starts with diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 19b4fdb94a36..a113d9aba553 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -56,14 +56,9 @@ int max_name_width, max_data_width; */ bool rdt_alloc_capable; -static void -mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, - struct rdt_resource *r); -static void -cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); -static void -mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, - struct rdt_resource *r); +static void mba_wrmsr_intel(struct msr_param *m); +static void cat_wrmsr(struct msr_param *m); +static void mba_wrmsr_amd(struct msr_param *m); #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains) @@ -309,12 +304,11 @@ static void rdt_get_cdp_l2_config(void) rdt_get_cdp_config(RDT_RESOURCE_L2); } -static void -mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) +static void mba_wrmsr_amd(struct msr_param *m) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom); unsigned int i; - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); @@ -334,25 +328,22 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) return r->default_ctrl; } -static void -mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, - struct rdt_resource *r) +static void mba_wrmsr_intel(struct msr_param *m) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom); unsigned int i; - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); /* Write the delay values for mba. */ for (i = m->low; i < m->high; i++) - wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r)); + wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res)); } -static void -cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) +static void cat_wrmsr(struct msr_param *m) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom); unsigned int i; - struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); for (i = m->low; i < m->high; i++) wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); @@ -362,6 +353,8 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) { struct rdt_domain *d; + lockdep_assert_cpus_held(); + list_for_each_entry(d, &r->domains, list) { /* Find the domain that contains this CPU */ if (cpumask_test_cpu(cpu, &d->cpu_mask)) @@ -378,19 +371,11 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r) void rdt_ctrl_update(void *arg) { + struct rdt_hw_resource *hw_res; struct msr_param *m = arg; - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res); - struct rdt_resource *r = m->res; - int cpu = smp_processor_id(); - struct rdt_domain *d; - d = get_domain_from_cpu(cpu, r); - if (d) { - hw_res->msr_update(d, m, r); - return; - } - pr_warn_once("cpu %d not found in any domain for resource %s\n", - cpu, r->name); + hw_res = resctrl_to_arch_res(m->res); + hw_res->msr_update(m); } /* @@ -463,9 +448,11 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) hw_dom->ctrl_val = dc; setup_default_ctrlval(r, dc); + m.res = r; + m.dom = d; m.low = 0; m.high = hw_res->num_closid; - hw_res->msr_update(d, &m, r); + hw_res->msr_update(&m); return 0; } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 7997b47743a2..b7291f60399c 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -272,22 +272,6 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type) } } -static bool apply_config(struct rdt_hw_domain *hw_dom, - struct resctrl_staged_config *cfg, u32 idx, - cpumask_var_t cpu_mask) -{ - struct rdt_domain *dom = &hw_dom->d_resctrl; - - if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) { - cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask); - hw_dom->ctrl_val[idx] = cfg->new_ctrl; - - return true; - } - - return false; -} - int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, u32 closid, enum resctrl_conf_type t, u32 cfg_val) { @@ -302,9 +286,10 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, hw_dom->ctrl_val[idx] = cfg_val; msr_param.res = r; + msr_param.dom = d; msr_param.low = idx; msr_param.high = idx + 1; - hw_res->msr_update(d, &msr_param, r); + hw_res->msr_update(&msr_param); return 0; } @@ -315,48 +300,39 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) struct rdt_hw_domain *hw_dom; struct msr_param msr_param; enum resctrl_conf_type t; - cpumask_var_t cpu_mask; struct rdt_domain *d; u32 idx; /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); - if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) - return -ENOMEM; - - msr_param.res = NULL; list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); + msr_param.res = NULL; for (t = 0; t < CDP_NUM_TYPES; t++) { cfg = &hw_dom->d_resctrl.staged_config[t]; if (!cfg->have_new_ctrl) continue; idx = get_config_index(closid, t); - if (!apply_config(hw_dom, cfg, idx, cpu_mask)) + if (cfg->new_ctrl == hw_dom->ctrl_val[idx]) continue; + hw_dom->ctrl_val[idx] = cfg->new_ctrl; if (!msr_param.res) { msr_param.low = idx; msr_param.high = msr_param.low + 1; msr_param.res = r; + msr_param.dom = d; } else { msr_param.low = min(msr_param.low, idx); msr_param.high = max(msr_param.high, idx + 1); } } + if (msr_param.res) + smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1); } - if (cpumask_empty(cpu_mask)) - goto done; - - /* Update resource control msr on all the CPUs. */ - on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1); - -done: - free_cpumask_var(cpu_mask); - return 0; } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 1a8687f8073a..f1d926832ec8 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -379,11 +379,13 @@ static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r) /** * struct msr_param - set a range of MSRs from a domain * @res: The resource to use + * @dom: The domain to update * @low: Beginning index from base MSR * @high: End index */ struct msr_param { struct rdt_resource *res; + struct rdt_domain *dom; u32 low; u32 high; }; @@ -443,8 +445,7 @@ struct rdt_hw_resource { struct rdt_resource r_resctrl; u32 num_closid; unsigned int msr_base; - void (*msr_update) (struct rdt_domain *d, struct msr_param *m, - struct rdt_resource *r); + void (*msr_update)(struct msr_param *m); unsigned int mon_scale; unsigned int mbm_width; unsigned int mbm_cfg_mask; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index c34a35ec0f03..2345e6836593 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -24,6 +24,7 @@ #include #include "internal.h" +#include "trace.h" /** * struct rmid_entry - dirty tracking for all RMID. @@ -354,6 +355,16 @@ void __check_limbo(struct rdt_domain *d, bool force_free) rmid_dirty = true; } else { rmid_dirty = (val >= resctrl_rmid_realloc_threshold); + + /* + * x86's CLOSID and RMID are independent numbers, so the entry's + * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the + * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't + * used to select the configuration. It is thus necessary to track both + * CLOSID and RMID because there may be dependencies between them + * on some architectures. + */ + trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->id, val); } if (force_free || !rmid_dirty) { diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 04584a76ceb4..aacf236dfe3b 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -31,7 +31,7 @@ #include "internal.h" #define CREATE_TRACE_POINTS -#include "pseudo_lock_event.h" +#include "trace.h" /* * The bits needed to disable hardware prefetching varies based on the diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 011e17efb1a6..02f213f1c51c 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2813,16 +2813,12 @@ static int reset_all_ctrls(struct rdt_resource *r) struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct rdt_hw_domain *hw_dom; struct msr_param msr_param; - cpumask_var_t cpu_mask; struct rdt_domain *d; int i; /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); - if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) - return -ENOMEM; - msr_param.res = r; msr_param.low = 0; msr_param.high = hw_res->num_closid; @@ -2834,17 +2830,13 @@ static int reset_all_ctrls(struct rdt_resource *r) */ list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); for (i = 0; i < hw_res->num_closid; i++) hw_dom->ctrl_val[i] = r->default_ctrl; + msr_param.dom = d; + smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1); } - /* Update CBM on all the CPUs in cpu_mask */ - on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1); - - free_cpumask_var(cpu_mask); - return 0; } diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h b/arch/x86/kernel/cpu/resctrl/trace.h similarity index 56% rename from arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h rename to arch/x86/kernel/cpu/resctrl/trace.h index 428ebbd4270b..2a506316b303 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h +++ b/arch/x86/kernel/cpu/resctrl/trace.h @@ -2,8 +2,8 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM resctrl -#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_PSEUDO_LOCK_H +#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RESCTRL_H #include @@ -35,9 +35,25 @@ TRACE_EVENT(pseudo_lock_l3, TP_printk("hits=%llu miss=%llu", __entry->l3_hits, __entry->l3_miss)); -#endif /* _TRACE_PSEUDO_LOCK_H */ +TRACE_EVENT(mon_llc_occupancy_limbo, + TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes), + TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes), + TP_STRUCT__entry(__field(u32, ctrl_hw_id) + __field(u32, mon_hw_id) + __field(int, domain_id) + __field(u64, llc_occupancy_bytes)), + TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id; + __entry->mon_hw_id = mon_hw_id; + __entry->domain_id = domain_id; + __entry->llc_occupancy_bytes = llc_occupancy_bytes;), + TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu", + __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id, + __entry->llc_occupancy_bytes) + ); + +#endif /* _TRACE_RESCTRL_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE pseudo_lock_event +#define TRACE_INCLUDE_FILE trace #include