diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 37674ba5ce66..041fcc8834ee 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6354,9 +6354,14 @@ Kernel parameters rdt= [HW,X86,RDT] Turn on/off individual RDT features. List is: cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, - mba, smba, bmec, abmc, sdciae. + mba, smba, bmec, abmc, sdciae, energy[:guid], + perf[:guid]. E.g. to turn on cmt and turn off mba use: rdt=cmt,!mba + To turn off all energy telemetry monitoring and ensure that + perf telemetry monitoring associated with guid 0x12345 + is enabled use: + rdt=!energy,perf:0x12345 reboot= [KNL] Format (x86 or x86_64): diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst index 5b27321f2313..ba609f8d4de5 100644 --- a/Documentation/filesystems/resctrl.rst +++ b/Documentation/filesystems/resctrl.rst @@ -252,13 +252,12 @@ with respect to allocation: bandwidth percentages are directly applied to the threads running on the core -If RDT monitoring is available there will be an "L3_MON" directory +If L3 monitoring is available there will be an "L3_MON" directory with the following files: "num_rmids": - The number of RMIDs available. This is the - upper bound for how many "CTRL_MON" + "MON" - groups can be created. + The number of RMIDs supported by hardware for + L3 monitoring events. "mon_features": Lists the monitoring events if @@ -484,6 +483,24 @@ with the following files: bytes) at which a previously used LLC_occupancy counter can be considered for reuse. +If telemetry monitoring is available there will be a "PERF_PKG_MON" directory +with the following files: + +"num_rmids": + The number of RMIDs for telemetry monitoring events. + + On Intel resctrl will not enable telemetry events if the number of + RMIDs that can be tracked concurrently is lower than the total number + of RMIDs supported. Telemetry events can be force-enabled with the + "rdt=" kernel parameter, but this may reduce the number of + monitoring groups that can be created. + +"mon_features": + Lists the telemetry monitoring events that are enabled on this system. + +The upper bound for how many "CTRL_MON" + "MON" can be created +is the smaller of the L3_MON and PERF_PKG_MON "num_rmids" values. + Finally, in the top level of the "info" directory there is a file named "last_cmd_status". This is reset with every "command" issued via the file system (making new directories or writing to any of the @@ -589,15 +606,40 @@ When control is enabled all CTRL_MON groups will also contain: When monitoring is enabled all MON groups will also contain: "mon_data": - This contains a set of files organized by L3 domain and by - RDT event. E.g. on a system with two L3 domains there will - be subdirectories "mon_L3_00" and "mon_L3_01". Each of these - directories have one file per event (e.g. "llc_occupancy", - "mbm_total_bytes", and "mbm_local_bytes"). In a MON group these - files provide a read out of the current value of the event for - all tasks in the group. In CTRL_MON groups these files provide - the sum for all tasks in the CTRL_MON group and all tasks in + This contains directories for each monitor domain. + + If L3 monitoring is enabled, there will be a "mon_L3_XX" directory for + each instance of an L3 cache. Each directory contains files for the enabled + L3 events (e.g. "llc_occupancy", "mbm_total_bytes", and "mbm_local_bytes"). + + If telemetry monitoring is enabled, there will be a "mon_PERF_PKG_YY" + directory for each physical processor package. Each directory contains + files for the enabled telemetry events (e.g. "core_energy". "activity", + "uops_retired", etc.) + + The info/`*`/mon_features files provide the full list of enabled + event/file names. + + "core energy" reports a floating point number for the energy (in Joules) + consumed by cores (registers, arithmetic units, TLB and L1/L2 caches) + during execution of instructions summed across all logical CPUs on a + package for the current monitoring group. + + "activity" also reports a floating point value (in Farads). This provides + an estimate of work done independent of the frequency that the CPUs used + for execution. + + Note that "core energy" and "activity" only measure energy/activity in the + "core" of the CPU (arithmetic units, TLB, L1 and L2 caches, etc.). They + do not include L3 cache, memory, I/O devices etc. + + All other events report decimal integer values. + + In a MON group these files provide a read out of the current value of + the event for all tasks in the group. In CTRL_MON groups these files + provide the sum for all tasks in the CTRL_MON group and all tasks in MON groups. Please see example section for more details on usage. + On systems with Sub-NUMA Cluster (SNC) enabled there are extra directories for each node (located within the "mon_L3_XX" directory for the L3 cache they occupy). These are named "mon_sub_L3_YY" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 731d9c2fdeb6..ae3a41f5e4de 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -541,6 +541,19 @@ config X86_CPU_RESCTRL Say N if unsure. +config X86_CPU_RESCTRL_INTEL_AET + bool "Intel Application Energy Telemetry" + depends on X86_64 && X86_CPU_RESCTRL && CPU_SUP_INTEL && INTEL_PMT_TELEMETRY=y && INTEL_TPMI=y + help + Enable per-RMID telemetry events in resctrl. + + Intel feature that collects per-RMID execution data + about energy consumption, measure of frequency independent + activity and other performance metrics. Data is aggregated + per package. + + Say N if unsure. + config X86_FRED bool "Flexible Return and Event Delivery" depends on X86_64 diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index d8a04b195da2..273ddfa30836 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o +obj-$(CONFIG_X86_CPU_RESCTRL_INTEL_AET) += intel_aet.o obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK) += pseudo_lock.o # To allow define_trace.h's recursive include: diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 6ebff44a3f75..7667cf7c4e94 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -100,14 +100,33 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = { .schema_fmt = RESCTRL_SCHEMA_RANGE, }, }, + [RDT_RESOURCE_PERF_PKG] = + { + .r_resctrl = { + .name = "PERF_PKG", + .mon_scope = RESCTRL_PACKAGE, + .mon_domains = mon_domain_init(RDT_RESOURCE_PERF_PKG), + }, + }, }; +/** + * resctrl_arch_system_num_rmid_idx - Compute number of supported RMIDs + * (minimum across all mon_capable resource) + * + * Return: Number of supported RMIDs at time of call. Note that mount time + * enumeration of resources may reduce the number. + */ u32 resctrl_arch_system_num_rmid_idx(void) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + u32 num_rmids = U32_MAX; + struct rdt_resource *r; + + for_each_mon_capable_rdt_resource(r) + num_rmids = min(num_rmids, r->mon.num_rmid); /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ - return r->mon.num_rmid; + return num_rmids == U32_MAX ? 0 : num_rmids; } struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) @@ -368,7 +387,7 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom) kfree(hw_dom); } -static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom) +static void l3_mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom) { int idx; @@ -401,11 +420,13 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain * } /** - * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM counters + * l3_mon_domain_mbm_alloc() - Allocate arch private storage for the MBM counters * @num_rmid: The size of the MBM counter array * @hw_dom: The domain that owns the allocated arrays + * + * Return: 0 for success, or -ENOMEM. */ -static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom) +static int l3_mon_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_domain *hw_dom) { size_t tsize = sizeof(*hw_dom->arch_mbm_states[0]); enum resctrl_event_id eventid; @@ -438,6 +459,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope) return get_cpu_cacheinfo_id(cpu, scope); case RESCTRL_L3_NODE: return cpu_to_node(cpu); + case RESCTRL_PACKAGE: + return topology_physical_package_id(cpu); default: break; } @@ -464,7 +487,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) hdr = resctrl_find_domain(&r->ctrl_domains, id, &add_pos); if (hdr) { - if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) + if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid)) return; d = container_of(hdr, struct rdt_ctrl_domain, hdr); @@ -481,6 +504,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) d = &hw_dom->d_resctrl; d->hdr.id = id; d->hdr.type = RESCTRL_CTRL_DOMAIN; + d->hdr.rid = r->rid; cpumask_set_cpu(cpu, &d->hdr.cpu_mask); rdt_domain_reconfigure_cdp(r); @@ -500,15 +524,52 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) } } +static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct list_head *add_pos) +{ + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; + struct cacheinfo *ci; + int err; + + hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); + if (!hw_dom) + return; + + d = &hw_dom->d_resctrl; + d->hdr.id = id; + d->hdr.type = RESCTRL_MON_DOMAIN; + d->hdr.rid = RDT_RESOURCE_L3; + ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + if (!ci) { + pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name); + l3_mon_domain_free(hw_dom); + return; + } + d->ci_id = ci->id; + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); + + arch_mon_domain_online(r, d); + + if (l3_mon_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) { + l3_mon_domain_free(hw_dom); + return; + } + + list_add_tail_rcu(&d->hdr.list, add_pos); + + err = resctrl_online_mon_domain(r, &d->hdr); + if (err) { + list_del_rcu(&d->hdr.list); + synchronize_rcu(); + l3_mon_domain_free(hw_dom); + } +} + static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) { int id = get_domain_id_from_scope(cpu, r->mon_scope); struct list_head *add_pos = NULL; - struct rdt_hw_mon_domain *hw_dom; struct rdt_domain_hdr *hdr; - struct rdt_mon_domain *d; - struct cacheinfo *ci; - int err; lockdep_assert_held(&domain_list_lock); @@ -519,52 +580,24 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) } hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos); - if (hdr) { - if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) - return; - d = container_of(hdr, struct rdt_mon_domain, hdr); + if (hdr) + cpumask_set_cpu(cpu, &hdr->cpu_mask); - cpumask_set_cpu(cpu, &d->hdr.cpu_mask); + switch (r->rid) { + case RDT_RESOURCE_L3: /* Update the mbm_assign_mode state for the CPU if supported */ if (r->mon.mbm_cntr_assignable) resctrl_arch_mbm_cntr_assign_set_one(r); - return; - } - - hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); - if (!hw_dom) - return; - - d = &hw_dom->d_resctrl; - d->hdr.id = id; - d->hdr.type = RESCTRL_MON_DOMAIN; - ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!ci) { - pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name); - mon_domain_free(hw_dom); - return; - } - d->ci_id = ci->id; - cpumask_set_cpu(cpu, &d->hdr.cpu_mask); - - /* Update the mbm_assign_mode state for the CPU if supported */ - if (r->mon.mbm_cntr_assignable) - resctrl_arch_mbm_cntr_assign_set_one(r); - - arch_mon_domain_online(r, d); - - if (arch_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) { - mon_domain_free(hw_dom); - return; - } - - list_add_tail_rcu(&d->hdr.list, add_pos); - - err = resctrl_online_mon_domain(r, d); - if (err) { - list_del_rcu(&d->hdr.list); - synchronize_rcu(); - mon_domain_free(hw_dom); + if (!hdr) + l3_mon_domain_setup(cpu, id, r, add_pos); + break; + case RDT_RESOURCE_PERF_PKG: + if (!hdr) + intel_aet_mon_domain_setup(cpu, id, r, add_pos); + break; + default: + pr_warn_once("Unknown resource rid=%d\n", r->rid); + break; } } @@ -598,36 +631,33 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r) return; } - if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) + cpumask_clear_cpu(cpu, &hdr->cpu_mask); + if (!cpumask_empty(&hdr->cpu_mask)) + return; + + if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid)) return; d = container_of(hdr, struct rdt_ctrl_domain, hdr); hw_dom = resctrl_to_arch_ctrl_dom(d); - cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); - if (cpumask_empty(&d->hdr.cpu_mask)) { - resctrl_offline_ctrl_domain(r, d); - list_del_rcu(&d->hdr.list); - synchronize_rcu(); + resctrl_offline_ctrl_domain(r, d); + list_del_rcu(&hdr->list); + synchronize_rcu(); - /* - * rdt_ctrl_domain "d" is going to be freed below, so clear - * its pointer from pseudo_lock_region struct. - */ - if (d->plr) - d->plr->d = NULL; - ctrl_domain_free(hw_dom); - - return; - } + /* + * rdt_ctrl_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + ctrl_domain_free(hw_dom); } static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) { int id = get_domain_id_from_scope(cpu, r->mon_scope); - struct rdt_hw_mon_domain *hw_dom; struct rdt_domain_hdr *hdr; - struct rdt_mon_domain *d; lockdep_assert_held(&domain_list_lock); @@ -644,20 +674,42 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) return; } - if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) + cpumask_clear_cpu(cpu, &hdr->cpu_mask); + if (!cpumask_empty(&hdr->cpu_mask)) return; - d = container_of(hdr, struct rdt_mon_domain, hdr); - hw_dom = resctrl_to_arch_mon_dom(d); + switch (r->rid) { + case RDT_RESOURCE_L3: { + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; - cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); - if (cpumask_empty(&d->hdr.cpu_mask)) { - resctrl_offline_mon_domain(r, d); - list_del_rcu(&d->hdr.list); + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + hw_dom = resctrl_to_arch_mon_dom(d); + resctrl_offline_mon_domain(r, hdr); + list_del_rcu(&hdr->list); synchronize_rcu(); - mon_domain_free(hw_dom); + l3_mon_domain_free(hw_dom); + break; + } + case RDT_RESOURCE_PERF_PKG: { + struct rdt_perf_pkg_mon_domain *pkgd; - return; + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_PERF_PKG)) + return; + + pkgd = container_of(hdr, struct rdt_perf_pkg_mon_domain, hdr); + resctrl_offline_mon_domain(r, hdr); + list_del_rcu(&hdr->list); + synchronize_rcu(); + kfree(pkgd); + break; + } + default: + pr_warn_once("Unknown resource rid=%d\n", r->rid); + break; } } @@ -712,6 +764,28 @@ static int resctrl_arch_offline_cpu(unsigned int cpu) return 0; } +void resctrl_arch_pre_mount(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl; + int cpu; + + if (!intel_aet_get_events()) + return; + + /* + * Late discovery of telemetry events means the domains for the + * resource were not built. Do that now. + */ + cpus_read_lock(); + mutex_lock(&domain_list_lock); + r->mon_capable = true; + rdt_mon_capable = true; + for_each_online_cpu(cpu) + domain_add_cpu_mon(cpu, r); + mutex_unlock(&domain_list_lock); + cpus_read_unlock(); +} + enum { RDT_FLAG_CMT, RDT_FLAG_MBM_TOTAL, @@ -767,6 +841,8 @@ static int __init set_rdt_options(char *str) force_off = *tok == '!'; if (force_off) tok++; + if (intel_handle_aet_option(force_off, tok)) + continue; for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { if (strcmp(tok, o->name) == 0) { if (force_off) @@ -889,15 +965,15 @@ static __init bool get_rdt_mon_resources(void) bool ret = false; if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) { - resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID); + resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0, NULL); ret = true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID); + resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0, NULL); ret = true; } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { - resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID); + resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0, NULL); ret = true; } if (rdt_cpu_has(X86_FEATURE_ABMC)) @@ -906,7 +982,7 @@ static __init bool get_rdt_mon_resources(void) if (!ret) return false; - return !rdt_get_mon_l3_config(r); + return !rdt_get_l3_mon_config(r); } static __init void __check_quirks_intel(void) @@ -1084,6 +1160,8 @@ late_initcall(resctrl_arch_late_init); static void __exit resctrl_arch_exit(void) { + intel_aet_exit(); + cpuhp_remove_state(rdt_online); resctrl_exit(); diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c new file mode 100644 index 000000000000..89b8b619d5d5 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Intel Application Energy Telemetry + * + * Copyright (C) 2025 Intel Corporation + * + * Author: + * Tony Luck + */ + +#define pr_fmt(fmt) "resctrl: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +/** + * struct pmt_event - Telemetry event. + * @id: Resctrl event id. + * @idx: Counter index within each per-RMID block of counters. + * @bin_bits: Zero for integer valued events, else number bits in fraction + * part of fixed-point. + */ +struct pmt_event { + enum resctrl_event_id id; + unsigned int idx; + unsigned int bin_bits; +}; + +#define EVT(_id, _idx, _bits) { .id = _id, .idx = _idx, .bin_bits = _bits } + +/** + * struct event_group - Events with the same feature type ("energy" or "perf") and GUID. + * @pfname: PMT feature name ("energy" or "perf") of this event group. + * Used by boot rdt= option. + * @pfg: Points to the aggregated telemetry space information + * returned by the intel_pmt_get_regions_by_feature() + * call to the INTEL_PMT_TELEMETRY driver that contains + * data for all telemetry regions of type @pfname. + * Valid if the system supports the event group, + * NULL otherwise. + * @force_off: True when "rdt" command line or architecture code disables + * this event group due to insufficient RMIDs. + * @force_on: True when "rdt" command line overrides disable of this + * event group. + * @guid: Unique number per XML description file. + * @num_rmid: Number of RMIDs supported by this group. May be + * adjusted downwards if enumeration from + * intel_pmt_get_regions_by_feature() indicates fewer + * RMIDs can be tracked simultaneously. + * @mmio_size: Number of bytes of MMIO registers for this group. + * @num_events: Number of events in this group. + * @evts: Array of event descriptors. + */ +struct event_group { + /* Data fields for additional structures to manage this group. */ + const char *pfname; + struct pmt_feature_group *pfg; + bool force_off, force_on; + + /* Remaining fields initialized from XML file. */ + u32 guid; + u32 num_rmid; + size_t mmio_size; + unsigned int num_events; + struct pmt_event evts[] __counted_by(num_events); +}; + +#define XML_MMIO_SIZE(num_rmids, num_events, num_extra_status) \ + (((num_rmids) * (num_events) + (num_extra_status)) * sizeof(u64)) + +/* + * Link: https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml + */ +static struct event_group energy_0x26696143 = { + .pfname = "energy", + .guid = 0x26696143, + .num_rmid = 576, + .mmio_size = XML_MMIO_SIZE(576, 2, 3), + .num_events = 2, + .evts = { + EVT(PMT_EVENT_ENERGY, 0, 18), + EVT(PMT_EVENT_ACTIVITY, 1, 18), + } +}; + +/* + * Link: https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-PERF/cwf_aggregator.xml + */ +static struct event_group perf_0x26557651 = { + .pfname = "perf", + .guid = 0x26557651, + .num_rmid = 576, + .mmio_size = XML_MMIO_SIZE(576, 7, 3), + .num_events = 7, + .evts = { + EVT(PMT_EVENT_STALLS_LLC_HIT, 0, 0), + EVT(PMT_EVENT_C1_RES, 1, 0), + EVT(PMT_EVENT_UNHALTED_CORE_CYCLES, 2, 0), + EVT(PMT_EVENT_STALLS_LLC_MISS, 3, 0), + EVT(PMT_EVENT_AUTO_C6_RES, 4, 0), + EVT(PMT_EVENT_UNHALTED_REF_CYCLES, 5, 0), + EVT(PMT_EVENT_UOPS_RETIRED, 6, 0), + } +}; + +static struct event_group *known_event_groups[] = { + &energy_0x26696143, + &perf_0x26557651, +}; + +#define for_each_event_group(_peg) \ + for (_peg = known_event_groups; \ + _peg < &known_event_groups[ARRAY_SIZE(known_event_groups)]; \ + _peg++) + +bool intel_handle_aet_option(bool force_off, char *tok) +{ + struct event_group **peg; + bool ret = false; + u32 guid = 0; + char *name; + + if (!tok) + return false; + + name = strsep(&tok, ":"); + if (tok && kstrtou32(tok, 16, &guid)) + return false; + + for_each_event_group(peg) { + if (strcmp(name, (*peg)->pfname)) + continue; + if (guid && (*peg)->guid != guid) + continue; + if (force_off) + (*peg)->force_off = true; + else + (*peg)->force_on = true; + ret = true; + } + + return ret; +} + +static bool skip_telem_region(struct telemetry_region *tr, struct event_group *e) +{ + if (tr->guid != e->guid) + return true; + if (tr->plat_info.package_id >= topology_max_packages()) { + pr_warn("Bad package %u in guid 0x%x\n", tr->plat_info.package_id, + tr->guid); + return true; + } + if (tr->size != e->mmio_size) { + pr_warn("MMIO space wrong size (%zu bytes) for guid 0x%x. Expected %zu bytes.\n", + tr->size, e->guid, e->mmio_size); + return true; + } + + return false; +} + +static bool group_has_usable_regions(struct event_group *e, struct pmt_feature_group *p) +{ + bool usable_regions = false; + + for (int i = 0; i < p->count; i++) { + if (skip_telem_region(&p->regions[i], e)) { + /* + * Clear the address field of regions that did not pass the checks in + * skip_telem_region() so they will not be used by intel_aet_read_event(). + * This is safe to do because intel_pmt_get_regions_by_feature() allocates + * a new pmt_feature_group structure to return to each caller and only makes + * use of the pmt_feature_group::kref field when intel_pmt_put_feature_group() + * returns the structure. + */ + p->regions[i].addr = NULL; + + continue; + } + usable_regions = true; + } + + return usable_regions; +} + +static bool all_regions_have_sufficient_rmid(struct event_group *e, struct pmt_feature_group *p) +{ + struct telemetry_region *tr; + + for (int i = 0; i < p->count; i++) { + if (!p->regions[i].addr) + continue; + tr = &p->regions[i]; + if (tr->num_rmids < e->num_rmid) { + e->force_off = true; + return false; + } + } + + return true; +} + +static bool enable_events(struct event_group *e, struct pmt_feature_group *p) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl; + int skipped_events = 0; + + if (e->force_off) + return false; + + if (!group_has_usable_regions(e, p)) + return false; + + /* + * Only enable event group with insufficient RMIDs if the user requested + * it from the kernel command line. + */ + if (!all_regions_have_sufficient_rmid(e, p) && !e->force_on) { + pr_info("%s %s:0x%x monitoring not enabled due to insufficient RMIDs\n", + r->name, e->pfname, e->guid); + return false; + } + + for (int i = 0; i < p->count; i++) { + if (!p->regions[i].addr) + continue; + /* + * e->num_rmid only adjusted lower if user (via rdt= kernel + * parameter) forces an event group with insufficient RMID + * to be enabled. + */ + e->num_rmid = min(e->num_rmid, p->regions[i].num_rmids); + } + + for (int j = 0; j < e->num_events; j++) { + if (!resctrl_enable_mon_event(e->evts[j].id, true, + e->evts[j].bin_bits, &e->evts[j])) + skipped_events++; + } + if (e->num_events == skipped_events) { + pr_info("No events enabled in %s %s:0x%x\n", r->name, e->pfname, e->guid); + return false; + } + + if (r->mon.num_rmid) + r->mon.num_rmid = min(r->mon.num_rmid, e->num_rmid); + else + r->mon.num_rmid = e->num_rmid; + + if (skipped_events) + pr_info("%s %s:0x%x monitoring detected (skipped %d events)\n", r->name, + e->pfname, e->guid, skipped_events); + else + pr_info("%s %s:0x%x monitoring detected\n", r->name, e->pfname, e->guid); + + return true; +} + +static enum pmt_feature_id lookup_pfid(const char *pfname) +{ + if (!strcmp(pfname, "energy")) + return FEATURE_PER_RMID_ENERGY_TELEM; + else if (!strcmp(pfname, "perf")) + return FEATURE_PER_RMID_PERF_TELEM; + + pr_warn("Unknown PMT feature name '%s'\n", pfname); + + return FEATURE_INVALID; +} + +/* + * Request a copy of struct pmt_feature_group for each event group. If there is + * one, the returned structure has an array of telemetry_region structures, + * each element of the array describes one telemetry aggregator. The + * telemetry aggregators may have different GUIDs so obtain duplicate struct + * pmt_feature_group for event groups with same feature type but different + * GUID. Post-processing ensures an event group can only use the telemetry + * aggregators that match its GUID. An event group keeps a pointer to its + * struct pmt_feature_group to indicate that its events are successfully + * enabled. + */ +bool intel_aet_get_events(void) +{ + struct pmt_feature_group *p; + enum pmt_feature_id pfid; + struct event_group **peg; + bool ret = false; + + for_each_event_group(peg) { + pfid = lookup_pfid((*peg)->pfname); + p = intel_pmt_get_regions_by_feature(pfid); + if (IS_ERR_OR_NULL(p)) + continue; + if (enable_events(*peg, p)) { + (*peg)->pfg = p; + ret = true; + } else { + intel_pmt_put_feature_group(p); + } + } + + return ret; +} + +void __exit intel_aet_exit(void) +{ + struct event_group **peg; + + for_each_event_group(peg) { + if ((*peg)->pfg) { + intel_pmt_put_feature_group((*peg)->pfg); + (*peg)->pfg = NULL; + } + } +} + +#define DATA_VALID BIT_ULL(63) +#define DATA_BITS GENMASK_ULL(62, 0) + +/* + * Read counter for an event on a domain (summing all aggregators on the + * domain). If an aggregator hasn't received any data for a specific RMID, + * the MMIO read indicates that data is not valid. Return success if at + * least one aggregator has valid data. + */ +int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val) +{ + struct pmt_event *pevt = arch_priv; + struct event_group *e; + bool valid = false; + u64 total = 0; + u64 evtcount; + void *pevt0; + u32 idx; + + pevt0 = pevt - pevt->idx; + e = container_of(pevt0, struct event_group, evts); + idx = rmid * e->num_events; + idx += pevt->idx; + + if (idx * sizeof(u64) + sizeof(u64) > e->mmio_size) { + pr_warn_once("MMIO index %u out of range\n", idx); + return -EIO; + } + + for (int i = 0; i < e->pfg->count; i++) { + if (!e->pfg->regions[i].addr) + continue; + if (e->pfg->regions[i].plat_info.package_id != domid) + continue; + evtcount = readq(e->pfg->regions[i].addr + idx * sizeof(u64)); + if (!(evtcount & DATA_VALID)) + continue; + total += evtcount & DATA_BITS; + valid = true; + } + + if (valid) + *val = total; + + return valid ? 0 : -EINVAL; +} + +void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos) +{ + struct rdt_perf_pkg_mon_domain *d; + int err; + + d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); + if (!d) + return; + + d->hdr.id = id; + d->hdr.type = RESCTRL_MON_DOMAIN; + d->hdr.rid = RDT_RESOURCE_PERF_PKG; + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); + list_add_tail_rcu(&d->hdr.list, add_pos); + + err = resctrl_online_mon_domain(r, &d->hdr); + if (err) { + list_del_rcu(&d->hdr.list); + synchronize_rcu(); + kfree(d); + } +} diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 79c18657ede0..e3cfa0c10e92 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -66,17 +66,17 @@ struct rdt_hw_ctrl_domain { }; /** - * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share - * a resource for a monitor function - * @d_resctrl: Properties exposed to the resctrl file system + * struct rdt_hw_l3_mon_domain - Arch private attributes of a set of CPUs sharing + * RDT_RESOURCE_L3 monitoring + * @d_resctrl: Properties exposed to the resctrl file system * @arch_mbm_states: Per-event pointer to the MBM event's saved state. * An MBM event's state is an array of struct arch_mbm_state * indexed by RMID on x86. * * Members of this structure are accessed via helpers that provide abstraction. */ -struct rdt_hw_mon_domain { - struct rdt_mon_domain d_resctrl; +struct rdt_hw_l3_mon_domain { + struct rdt_l3_mon_domain d_resctrl; struct arch_mbm_state *arch_mbm_states[QOS_NUM_L3_MBM_EVENTS]; }; @@ -85,11 +85,19 @@ static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctr return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl); } -static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r) +static inline struct rdt_hw_l3_mon_domain *resctrl_to_arch_mon_dom(struct rdt_l3_mon_domain *r) { - return container_of(r, struct rdt_hw_mon_domain, d_resctrl); + return container_of(r, struct rdt_hw_l3_mon_domain, d_resctrl); } +/** + * struct rdt_perf_pkg_mon_domain - CPUs sharing an package scoped resctrl monitor resource + * @hdr: common header for different domain types + */ +struct rdt_perf_pkg_mon_domain { + struct rdt_domain_hdr hdr; +}; + /** * struct msr_param - set a range of MSRs from a domain * @res: The resource to use @@ -143,7 +151,7 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r extern struct rdt_hw_resource rdt_resources_all[]; -void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d); +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d); /* CPUID.(EAX=10H, ECX=ResID=1).EAX */ union cpuid_0x10_1_eax { @@ -216,7 +224,7 @@ union l3_qos_abmc_cfg { void rdt_ctrl_update(void *arg); -int rdt_get_mon_l3_config(struct rdt_resource *r); +int rdt_get_l3_mon_config(struct rdt_resource *r); bool rdt_cpu_has(int flag); @@ -225,4 +233,24 @@ void __init intel_rdt_mbm_apply_quirk(void); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r); +#ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET +bool intel_aet_get_events(void); +void __exit intel_aet_exit(void); +int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val); +void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos); +bool intel_handle_aet_option(bool force_off, char *tok); +#else +static inline bool intel_aet_get_events(void) { return false; } +static inline void __exit intel_aet_exit(void) { } +static inline int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val) +{ + return -EINVAL; +} + +static inline void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos) { } +static inline bool intel_handle_aet_option(bool force_off, char *tok) { return false; } +#endif + #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index dffcc8307500..e6a154240b8d 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -109,7 +109,7 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) * * In RMID sharing mode there are fewer "logical RMID" values available * to accumulate data ("physical RMIDs" are divided evenly between SNC - * nodes that share an L3 cache). Linux creates an rdt_mon_domain for + * nodes that share an L3 cache). Linux creates an rdt_l3_mon_domain for * each SNC node. * * The value loaded into IA32_PQR_ASSOC is the "logical RMID". @@ -157,7 +157,7 @@ static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val) return 0; } -static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom, +static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_l3_mon_domain *hw_dom, u32 rmid, enum resctrl_event_id eventid) { @@ -171,11 +171,11 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do return state ? &state[rmid] : NULL; } -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 unused, u32 rmid, enum resctrl_event_id eventid) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); int cpu = cpumask_any(&d->hdr.cpu_mask); struct arch_mbm_state *am; u32 prmid; @@ -194,9 +194,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, * Assumes that hardware counters are also reset and thus that there is * no need to record initial non-zero counts. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d) +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); enum resctrl_event_id eventid; int idx; @@ -217,10 +217,10 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) return chunks >> shift; } -static u64 get_corrected_val(struct rdt_resource *r, struct rdt_mon_domain *d, +static u64 get_corrected_val(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 rmid, enum resctrl_event_id eventid, u64 msr_val) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct arch_mbm_state *am; u64 chunks; @@ -238,19 +238,29 @@ static u64 get_corrected_val(struct rdt_resource *r, struct rdt_mon_domain *d, return chunks * hw_res->mon_scale; } -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr, u32 unused, u32 rmid, enum resctrl_event_id eventid, - u64 *val, void *ignored) + void *arch_priv, u64 *val, void *ignored) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); - int cpu = cpumask_any(&d->hdr.cpu_mask); + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; struct arch_mbm_state *am; u64 msr_val; u32 prmid; + int cpu; int ret; resctrl_arch_rmid_read_context_check(); + if (r->rid == RDT_RESOURCE_PERF_PKG) + return intel_aet_read_event(hdr->id, rmid, arch_priv, val); + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return -EINVAL; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + hw_dom = resctrl_to_arch_mon_dom(d); + cpu = cpumask_any(&hdr->cpu_mask); prmid = logical_rmid_to_physical_rmid(cpu, rmid); ret = __rmid_read_phys(prmid, eventid, &msr_val); @@ -302,11 +312,11 @@ static int __cntr_id_read(u32 cntr_id, u64 *val) return 0; } -void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 unused, u32 rmid, int cntr_id, enum resctrl_event_id eventid) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); struct arch_mbm_state *am; am = get_arch_mbm_state(hw_dom, rmid, eventid); @@ -318,7 +328,7 @@ void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, } } -int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d, +int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 unused, u32 rmid, int cntr_id, enum resctrl_event_id eventid, u64 *val) { @@ -348,7 +358,7 @@ int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d, * must adjust RMID counter numbers based on SNC node. See * logical_rmid_to_physical_rmid() for code that does this. */ -void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d) +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d) { if (snc_nodes_per_l3_cache > 1) msr_clear_bit(MSR_RMID_SNC_CONFIG, 0); @@ -418,7 +428,7 @@ static __init int snc_get_config(void) return ret; } -int __init rdt_get_mon_l3_config(struct rdt_resource *r) +int __init rdt_get_l3_mon_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); @@ -510,7 +520,7 @@ static void resctrl_abmc_set_one_amd(void *arg) */ static void _resctrl_abmc_enable(struct rdt_resource *r, bool enable) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; lockdep_assert_cpus_held(); @@ -549,11 +559,11 @@ static void resctrl_abmc_config_one_amd(void *info) /* * Send an IPI to the domain to assign the counter to RMID, event pair. */ -void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, enum resctrl_event_id evtid, u32 rmid, u32 closid, u32 cntr_id, bool assign) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); union l3_qos_abmc_cfg abmc_cfg = { 0 }; struct arch_mbm_state *am; diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index b2d178d3556e..cc4237c57cbe 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -551,8 +552,8 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id, } void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, - cpumask_t *cpumask, int evtid, int first) + struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, + cpumask_t *cpumask, struct mon_evt *evt, int first) { int cpu; @@ -563,21 +564,26 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, * Setup the parameters to pass to mon_event_count() to read the data. */ rr->rgrp = rdtgrp; - rr->evtid = evtid; + rr->evt = evt; rr->r = r; - rr->d = d; + rr->hdr = hdr; rr->first = first; if (resctrl_arch_mbm_cntr_assign_enabled(r) && - resctrl_is_mbm_event(evtid)) { + resctrl_is_mbm_event(evt->evtid)) { rr->is_mbm_cntr = true; } else { - rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid); + rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evt->evtid); if (IS_ERR(rr->arch_mon_ctx)) { rr->err = -EINVAL; return; } } + if (evt->any_cpu) { + mon_event_count(rr); + goto out_ctx_free; + } + cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU); /* @@ -591,22 +597,93 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, else smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); +out_ctx_free: if (rr->arch_mon_ctx) - resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx); + resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx); +} + +/* + * Decimal place precision to use for each number of fixed-point + * binary bits computed from ceil(binary_bits * log10(2)) except + * binary_bits == 0 which will print "value.0" + */ +static const unsigned int decplaces[MAX_BINARY_BITS + 1] = { + [0] = 1, + [1] = 1, + [2] = 1, + [3] = 1, + [4] = 2, + [5] = 2, + [6] = 2, + [7] = 3, + [8] = 3, + [9] = 3, + [10] = 4, + [11] = 4, + [12] = 4, + [13] = 4, + [14] = 5, + [15] = 5, + [16] = 5, + [17] = 6, + [18] = 6, + [19] = 6, + [20] = 7, + [21] = 7, + [22] = 7, + [23] = 7, + [24] = 8, + [25] = 8, + [26] = 8, + [27] = 9 +}; + +static void print_event_value(struct seq_file *m, unsigned int binary_bits, u64 val) +{ + unsigned long long frac = 0; + + if (binary_bits) { + /* Mask off the integer part of the fixed-point value. */ + frac = val & GENMASK_ULL(binary_bits - 1, 0); + + /* + * Multiply by 10^{desired decimal places}. The integer part of + * the fixed point value is now almost what is needed. + */ + frac *= int_pow(10ull, decplaces[binary_bits]); + + /* + * Round to nearest by adding a value that would be a "1" in the + * binary_bits + 1 place. Integer part of fixed point value is + * now the needed value. + */ + frac += 1ull << (binary_bits - 1); + + /* + * Extract the integer part of the value. This is the decimal + * representation of the original fixed-point fractional value. + */ + frac >>= binary_bits; + } + + /* + * "frac" is now in the range [0 .. 10^decplaces). I.e. string + * representation will fit into chosen number of decimal places. + */ + seq_printf(m, "%llu.%0*llu\n", val >> binary_bits, decplaces[binary_bits], frac); } int rdtgroup_mondata_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of = m->private; enum resctrl_res_level resid; - enum resctrl_event_id evtid; struct rdt_domain_hdr *hdr; struct rmid_read rr = {0}; - struct rdt_mon_domain *d; struct rdtgroup *rdtgrp; int domid, cpu, ret = 0; struct rdt_resource *r; struct cacheinfo *ci; + struct mon_evt *evt; struct mon_data *md; rdtgrp = rdtgroup_kn_lock_live(of->kn); @@ -623,10 +700,17 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) resid = md->rid; domid = md->domid; - evtid = md->evtid; + evt = md->evt; r = resctrl_arch_get_resource(resid); if (md->sum) { + struct rdt_l3_mon_domain *d; + + if (WARN_ON_ONCE(resid != RDT_RESOURCE_L3)) { + ret = -EINVAL; + goto out; + } + /* * This file requires summing across all domains that share * the L3 cache id that was provided in the "domid" field of the @@ -641,7 +725,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) continue; rr.ci = ci; mon_event_read(&rr, r, NULL, rdtgrp, - &ci->shared_cpu_map, evtid, false); + &ci->shared_cpu_map, evt, false); goto checkresult; } } @@ -653,12 +737,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) * the resource to find the domain with "domid". */ hdr = resctrl_find_domain(&r->mon_domains, domid, NULL); - if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) { + if (!hdr) { ret = -ENOENT; goto out; } - d = container_of(hdr, struct rdt_mon_domain, hdr); - mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false); + mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evt, false); } checkresult: @@ -673,6 +756,8 @@ checkresult: seq_puts(m, "Unavailable\n"); else if (rr.err == -ENOENT) seq_puts(m, "Unassigned\n"); + else if (evt->is_floating_point) + print_event_value(m, evt->binary_bits, rr.val); else seq_printf(m, "%llu\n", rr.val); diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index bff4a54ae333..1a9b29119f88 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -61,7 +61,14 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) * READS_TO_REMOTE_MEM) being tracked by @evtid. * Only valid if @evtid is an MBM event. * @configurable: true if the event is configurable + * @any_cpu: true if the event can be read from any CPU + * @is_floating_point: event values are displayed in floating point format + * @binary_bits: number of fixed-point binary bits from architecture, + * only valid if @is_floating_point is true * @enabled: true if the event is enabled + * @arch_priv: Architecture private data for this event. + * The @arch_priv provided by the architecture via + * resctrl_enable_mon_event(). */ struct mon_evt { enum resctrl_event_id evtid; @@ -69,7 +76,11 @@ struct mon_evt { char *name; u32 evt_cfg; bool configurable; + bool any_cpu; + bool is_floating_point; + unsigned int binary_bits; bool enabled; + void *arch_priv; }; extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; @@ -77,13 +88,16 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; #define for_each_mon_event(mevt) for (mevt = &mon_event_all[QOS_FIRST_EVENT]; \ mevt < &mon_event_all[QOS_NUM_EVENTS]; mevt++) +/* Limit for mon_evt::binary_bits */ +#define MAX_BINARY_BITS 27 + /** * struct mon_data - Monitoring details for each event file. * @list: Member of the global @mon_data_kn_priv_list list. * @rid: Resource id associated with the event file. - * @evtid: Event id associated with the event file. - * @sum: Set when event must be summed across multiple - * domains. + * @evt: Event structure associated with the event file. + * @sum: Set for RDT_RESOURCE_L3 when event must be summed + * across multiple domains. * @domid: When @sum is zero this is the domain to which * the event file belongs. When @sum is one this * is the id of the L3 cache that all domains to be @@ -95,7 +109,7 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; struct mon_data { struct list_head list; enum resctrl_res_level rid; - enum resctrl_event_id evtid; + struct mon_evt *evt; int domid; bool sum; }; @@ -106,25 +120,27 @@ struct mon_data { * resource group then its event count is summed with the count from all * its child resource groups. * @r: Resource describing the properties of the event being read. - * @d: Domain that the counter should be read from. If NULL then sum all - * domains in @r sharing L3 @ci.id - * @evtid: Which monitor event to read. + * @hdr: Header of domain that the counter should be read from. If NULL then + * sum all domains in @r sharing L3 @ci.id + * @evt: Which monitor event to read. * @first: Initialize MBM counter when true. - * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains. + * @ci: Cacheinfo for L3. Only set when @hdr is NULL. Used when summing + * domains. * @is_mbm_cntr: true if "mbm_event" counter assignment mode is enabled and it * is an MBM event. * @err: Error encountered when reading counter. - * @val: Returned value of event counter. If @rgrp is a parent resource group, - * @val includes the sum of event counts from its child resource groups. - * If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id, - * (summed across child resource groups if @rgrp is a parent resource group). + * @val: Returned value of event counter. If @rgrp is a parent resource + * group, @val includes the sum of event counts from its child + * resource groups. If @hdr is NULL, @val includes the sum of all + * domains in @r sharing @ci.id, (summed across child resource groups + * if @rgrp is a parent resource group). * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only). */ struct rmid_read { struct rdtgroup *rgrp; struct rdt_resource *r; - struct rdt_mon_domain *d; - enum resctrl_event_id evtid; + struct rdt_domain_hdr *hdr; + struct mon_evt *evt; bool first; struct cacheinfo *ci; bool is_mbm_cntr; @@ -243,6 +259,8 @@ struct rdtgroup { #define RFTYPE_ASSIGN_CONFIG BIT(11) +#define RFTYPE_RES_PERF_PKG BIT(12) + #define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) #define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) @@ -351,23 +369,27 @@ int closids_supported(void); void closid_free(int closid); +int setup_rmid_lru_list(void); + +void free_rmid_lru_list(void); + int alloc_rmid(u32 closid); void free_rmid(u32 closid, u32 rmid); -void resctrl_mon_resource_exit(void); +int resctrl_l3_mon_resource_init(void); + +void resctrl_l3_mon_resource_exit(void); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, - cpumask_t *cpumask, int evtid, int first); + struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, + cpumask_t *cpumask, struct mon_evt *evt, int first); -int resctrl_mon_resource_init(void); - -void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, +void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, int exclude_cpu); @@ -375,14 +397,14 @@ void mbm_handle_overflow(struct work_struct *work); bool is_mba_sc(struct rdt_resource *r); -void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, +void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, int exclude_cpu); void cqm_handle_limbo(struct work_struct *work); -bool has_busy_rmid(struct rdt_mon_domain *d); +bool has_busy_rmid(struct rdt_l3_mon_domain *d); -void __check_limbo(struct rdt_mon_domain *d, bool force_free); +void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free); void resctrl_file_fflags_init(const char *config, unsigned long fflags); diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 572a9925bd6c..0cd5476a483a 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -130,16 +130,18 @@ static void limbo_release_entry(struct rmid_entry *entry) * decrement the count. If the busy count gets to zero on an RMID, we * free the RMID */ -void __check_limbo(struct rdt_mon_domain *d, bool force_free) +void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free) { struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); u32 idx_limit = resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry; u32 idx, cur_idx = 1; void *arch_mon_ctx; + void *arch_priv; bool rmid_dirty; u64 val = 0; + arch_priv = mon_event_all[QOS_L3_OCCUP_EVENT_ID].arch_priv; arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID); if (IS_ERR(arch_mon_ctx)) { pr_warn_ratelimited("Failed to allocate monitor context: %ld", @@ -159,8 +161,8 @@ void __check_limbo(struct rdt_mon_domain *d, bool force_free) break; entry = __rmid_entry(idx); - if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, &val, + if (resctrl_arch_rmid_read(r, &d->hdr, entry->closid, entry->rmid, + QOS_L3_OCCUP_EVENT_ID, arch_priv, &val, arch_mon_ctx)) { rmid_dirty = true; } else { @@ -188,7 +190,7 @@ void __check_limbo(struct rdt_mon_domain *d, bool force_free) resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); } -bool has_busy_rmid(struct rdt_mon_domain *d) +bool has_busy_rmid(struct rdt_l3_mon_domain *d) { u32 idx_limit = resctrl_arch_system_num_rmid_idx(); @@ -289,7 +291,7 @@ int alloc_rmid(u32 closid) static void add_rmid_to_limbo(struct rmid_entry *entry) { struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; u32 idx; lockdep_assert_held(&rdtgroup_mutex); @@ -342,7 +344,7 @@ void free_rmid(u32 closid, u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } -static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid, +static struct mbm_state *get_mbm_state(struct rdt_l3_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id evtid) { u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); @@ -362,7 +364,7 @@ static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid, * Return: * Valid counter ID on success, or -ENOENT on failure. */ -static int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d, +static int mbm_cntr_get(struct rdt_resource *r, struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, enum resctrl_event_id evtid) { int cntr_id; @@ -389,7 +391,7 @@ static int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d, * Return: * Valid counter ID on success, or -ENOSPC on failure. */ -static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_mon_domain *d, +static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, enum resctrl_event_id evtid) { int cntr_id; @@ -408,24 +410,29 @@ static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_mon_domain *d, /* * mbm_cntr_free() - Clear the counter ID configuration details in the domain @d. */ -static void mbm_cntr_free(struct rdt_mon_domain *d, int cntr_id) +static void mbm_cntr_free(struct rdt_l3_mon_domain *d, int cntr_id) { memset(&d->cntr_cfg[cntr_id], 0, sizeof(*d->cntr_cfg)); } -static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) +static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) { int cpu = smp_processor_id(); u32 closid = rdtgrp->closid; u32 rmid = rdtgrp->mon.rmid; - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; int cntr_id = -ENOENT; struct mbm_state *m; - int err, ret; u64 tval = 0; + if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) { + rr->err = -EIO; + return -EINVAL; + } + d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); + if (rr->is_mbm_cntr) { - cntr_id = mbm_cntr_get(rr->r, rr->d, rdtgrp, rr->evtid); + cntr_id = mbm_cntr_get(rr->r, d, rdtgrp, rr->evt->evtid); if (cntr_id < 0) { rr->err = -ENOENT; return -EINVAL; @@ -434,31 +441,51 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) if (rr->first) { if (rr->is_mbm_cntr) - resctrl_arch_reset_cntr(rr->r, rr->d, closid, rmid, cntr_id, rr->evtid); + resctrl_arch_reset_cntr(rr->r, d, closid, rmid, cntr_id, rr->evt->evtid); else - resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid); - m = get_mbm_state(rr->d, closid, rmid, rr->evtid); + resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evt->evtid); + m = get_mbm_state(d, closid, rmid, rr->evt->evtid); if (m) memset(m, 0, sizeof(struct mbm_state)); return 0; } - if (rr->d) { - /* Reading a single domain, must be on a CPU in that domain. */ - if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask)) - return -EINVAL; - if (rr->is_mbm_cntr) - rr->err = resctrl_arch_cntr_read(rr->r, rr->d, closid, rmid, cntr_id, - rr->evtid, &tval); - else - rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, - rr->evtid, &tval, rr->arch_mon_ctx); - if (rr->err) - return rr->err; + /* Reading a single domain, must be on a CPU in that domain. */ + if (!cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) + return -EINVAL; + if (rr->is_mbm_cntr) + rr->err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id, + rr->evt->evtid, &tval); + else + rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid, + rr->evt->evtid, rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); + if (rr->err) + return rr->err; - rr->val += tval; + rr->val += tval; - return 0; + return 0; +} + +static int __l3_mon_event_count_sum(struct rdtgroup *rdtgrp, struct rmid_read *rr) +{ + int cpu = smp_processor_id(); + u32 closid = rdtgrp->closid; + u32 rmid = rdtgrp->mon.rmid; + struct rdt_l3_mon_domain *d; + u64 tval = 0; + int err, ret; + + /* + * Summing across domains is only done for systems that implement + * Sub-NUMA Cluster. There is no overlap with systems that support + * assignable counters. + */ + if (rr->is_mbm_cntr) { + pr_warn_once("Summing domains using assignable counters is not supported\n"); + rr->err = -EINVAL; + return -EINVAL; } /* Summing domains that share a cache, must be on a CPU for that cache. */ @@ -476,12 +503,9 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { if (d->ci_id != rr->ci->id) continue; - if (rr->is_mbm_cntr) - err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id, - rr->evtid, &tval); - else - err = resctrl_arch_rmid_read(rr->r, d, closid, rmid, - rr->evtid, &tval, rr->arch_mon_ctx); + err = resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid, + rr->evt->evtid, rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); if (!err) { rr->val += tval; ret = 0; @@ -494,6 +518,35 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) return ret; } +static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) +{ + switch (rr->r->rid) { + case RDT_RESOURCE_L3: + WARN_ON_ONCE(rr->evt->any_cpu); + if (rr->hdr) + return __l3_mon_event_count(rdtgrp, rr); + else + return __l3_mon_event_count_sum(rdtgrp, rr); + case RDT_RESOURCE_PERF_PKG: { + u64 tval = 0; + + rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, rdtgrp->closid, + rdtgrp->mon.rmid, rr->evt->evtid, + rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); + if (rr->err) + return rr->err; + + rr->val += tval; + + return 0; + } + default: + rr->err = -EINVAL; + return -EINVAL; + } +} + /* * mbm_bw_count() - Update bw count from values previously read by * __mon_event_count(). @@ -511,9 +564,13 @@ static void mbm_bw_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) u64 cur_bw, bytes, cur_bytes; u32 closid = rdtgrp->closid; u32 rmid = rdtgrp->mon.rmid; + struct rdt_l3_mon_domain *d; struct mbm_state *m; - m = get_mbm_state(rr->d, closid, rmid, rr->evtid); + if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); + m = get_mbm_state(d, closid, rmid, rr->evt->evtid); if (WARN_ON_ONCE(!m)) return; @@ -612,7 +669,7 @@ static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, * throttle MSRs already have low percentage values. To avoid * unnecessarily restricting such rdtgroups, we also increase the bandwidth. */ -static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) +static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_l3_mon_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; @@ -680,18 +737,18 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); } -static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d, +static void mbm_update_one_event(struct rdt_resource *r, struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, enum resctrl_event_id evtid) { struct rmid_read rr = {0}; rr.r = r; - rr.d = d; - rr.evtid = evtid; + rr.hdr = &d->hdr; + rr.evt = &mon_event_all[evtid]; if (resctrl_arch_mbm_cntr_assign_enabled(r)) { rr.is_mbm_cntr = true; } else { - rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, evtid); if (IS_ERR(rr.arch_mon_ctx)) { pr_warn_ratelimited("Failed to allocate monitor context: %ld", PTR_ERR(rr.arch_mon_ctx)); @@ -709,10 +766,10 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain * mbm_bw_count(rdtgrp, &rr); if (rr.arch_mon_ctx) - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); + resctrl_arch_mon_ctx_free(rr.r, evtid, rr.arch_mon_ctx); } -static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, +static void mbm_update(struct rdt_resource *r, struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp) { /* @@ -733,12 +790,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, void cqm_handle_limbo(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - d = container_of(work, struct rdt_mon_domain, cqm_limbo.work); + d = container_of(work, struct rdt_l3_mon_domain, cqm_limbo.work); __check_limbo(d, false); @@ -761,7 +818,7 @@ void cqm_handle_limbo(struct work_struct *work) * @exclude_cpu: Which CPU the handler should not run on, * RESCTRL_PICK_ANY_CPU to pick any CPU. */ -void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, +void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); @@ -778,7 +835,7 @@ void mbm_handle_overflow(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); struct rdtgroup *prgrp, *crgrp; - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; struct list_head *head; struct rdt_resource *r; @@ -793,7 +850,7 @@ void mbm_handle_overflow(struct work_struct *work) goto out_unlock; r = resctrl_arch_get_resource(RDT_RESOURCE_L3); - d = container_of(work, struct rdt_mon_domain, mbm_over.work); + d = container_of(work, struct rdt_l3_mon_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { mbm_update(r, d, prgrp); @@ -827,7 +884,7 @@ out_unlock: * @exclude_cpu: Which CPU the handler should not run on, * RESCTRL_PICK_ANY_CPU to pick any CPU. */ -void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, +void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); @@ -846,42 +903,29 @@ void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ schedule_delayed_work_on(cpu, &dom->mbm_over, delay); } -static int dom_data_init(struct rdt_resource *r) +int setup_rmid_lru_list(void) { - u32 idx_limit = resctrl_arch_system_num_rmid_idx(); - u32 num_closid = resctrl_arch_get_num_closid(r); struct rmid_entry *entry = NULL; - int err = 0, i; + u32 idx_limit; u32 idx; + int i; - mutex_lock(&rdtgroup_mutex); - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - u32 *tmp; + if (!resctrl_arch_mon_capable()) + return 0; - /* - * If the architecture hasn't provided a sanitised value here, - * this may result in larger arrays than necessary. Resctrl will - * use a smaller system wide value based on the resources in - * use. - */ - tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); - if (!tmp) { - err = -ENOMEM; - goto out_unlock; - } - - closid_num_dirty_rmid = tmp; - } + /* + * Called on every mount, but the number of RMIDs cannot change + * after the first mount, so keep using the same set of rmid_ptrs[] + * until resctrl_exit(). Note that the limbo handler continues to + * access rmid_ptrs[] after resctrl is unmounted. + */ + if (rmid_ptrs) + return 0; + idx_limit = resctrl_arch_system_num_rmid_idx(); rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); - if (!rmid_ptrs) { - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - kfree(closid_num_dirty_rmid); - closid_num_dirty_rmid = NULL; - } - err = -ENOMEM; - goto out_unlock; - } + if (!rmid_ptrs) + return -ENOMEM; for (i = 0; i < idx_limit; i++) { entry = &rmid_ptrs[i]; @@ -894,71 +938,76 @@ static int dom_data_init(struct rdt_resource *r) /* * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and * are always allocated. These are used for the rdtgroup_default - * control group, which will be setup later in resctrl_init(). + * control group, which was setup earlier in rdtgroup_setup_default(). */ idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID); entry = __rmid_entry(idx); list_del(&entry->list); -out_unlock: - mutex_unlock(&rdtgroup_mutex); - - return err; + return 0; } -static void dom_data_exit(struct rdt_resource *r) +void free_rmid_lru_list(void) { + if (!resctrl_arch_mon_capable()) + return; + mutex_lock(&rdtgroup_mutex); - - if (!r->mon_capable) - goto out_unlock; - - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - kfree(closid_num_dirty_rmid); - closid_num_dirty_rmid = NULL; - } - kfree(rmid_ptrs); rmid_ptrs = NULL; - -out_unlock: mutex_unlock(&rdtgroup_mutex); } +#define MON_EVENT(_eventid, _name, _res, _fp) \ + [_eventid] = { \ + .name = _name, \ + .evtid = _eventid, \ + .rid = _res, \ + .is_floating_point = _fp, \ +} + /* * All available events. Architecture code marks the ones that * are supported by a system using resctrl_enable_mon_event() * to set .enabled. */ struct mon_evt mon_event_all[QOS_NUM_EVENTS] = { - [QOS_L3_OCCUP_EVENT_ID] = { - .name = "llc_occupancy", - .evtid = QOS_L3_OCCUP_EVENT_ID, - .rid = RDT_RESOURCE_L3, - }, - [QOS_L3_MBM_TOTAL_EVENT_ID] = { - .name = "mbm_total_bytes", - .evtid = QOS_L3_MBM_TOTAL_EVENT_ID, - .rid = RDT_RESOURCE_L3, - }, - [QOS_L3_MBM_LOCAL_EVENT_ID] = { - .name = "mbm_local_bytes", - .evtid = QOS_L3_MBM_LOCAL_EVENT_ID, - .rid = RDT_RESOURCE_L3, - }, + MON_EVENT(QOS_L3_OCCUP_EVENT_ID, "llc_occupancy", RDT_RESOURCE_L3, false), + MON_EVENT(QOS_L3_MBM_TOTAL_EVENT_ID, "mbm_total_bytes", RDT_RESOURCE_L3, false), + MON_EVENT(QOS_L3_MBM_LOCAL_EVENT_ID, "mbm_local_bytes", RDT_RESOURCE_L3, false), + MON_EVENT(PMT_EVENT_ENERGY, "core_energy", RDT_RESOURCE_PERF_PKG, true), + MON_EVENT(PMT_EVENT_ACTIVITY, "activity", RDT_RESOURCE_PERF_PKG, true), + MON_EVENT(PMT_EVENT_STALLS_LLC_HIT, "stalls_llc_hit", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_C1_RES, "c1_res", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UNHALTED_CORE_CYCLES, "unhalted_core_cycles", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_STALLS_LLC_MISS, "stalls_llc_miss", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_AUTO_C6_RES, "c6_res", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UNHALTED_REF_CYCLES, "unhalted_ref_cycles", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UOPS_RETIRED, "uops_retired", RDT_RESOURCE_PERF_PKG, false), }; -void resctrl_enable_mon_event(enum resctrl_event_id eventid) +bool resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, + unsigned int binary_bits, void *arch_priv) { - if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS)) - return; + if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS || + binary_bits > MAX_BINARY_BITS)) + return false; if (mon_event_all[eventid].enabled) { pr_warn("Duplicate enable for event %d\n", eventid); - return; + return false; + } + if (binary_bits && !mon_event_all[eventid].is_floating_point) { + pr_warn("Event %d may not be floating point\n", eventid); + return false; } + mon_event_all[eventid].any_cpu = any_cpu; + mon_event_all[eventid].binary_bits = binary_bits; + mon_event_all[eventid].arch_priv = arch_priv; mon_event_all[eventid].enabled = true; + + return true; } bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid) @@ -1082,7 +1131,7 @@ out_unlock: * mbm_cntr_free_all() - Clear all the counter ID configuration details in the * domain @d. Called when mbm_assign_mode is changed. */ -static void mbm_cntr_free_all(struct rdt_resource *r, struct rdt_mon_domain *d) +static void mbm_cntr_free_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d) { memset(d->cntr_cfg, 0, sizeof(*d->cntr_cfg) * r->mon.num_mbm_cntrs); } @@ -1091,7 +1140,7 @@ static void mbm_cntr_free_all(struct rdt_resource *r, struct rdt_mon_domain *d) * resctrl_reset_rmid_all() - Reset all non-architecture states for all the * supported RMIDs. */ -static void resctrl_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d) +static void resctrl_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d) { u32 idx_limit = resctrl_arch_system_num_rmid_idx(); enum resctrl_event_id evt; @@ -1112,7 +1161,7 @@ static void resctrl_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain * Assign the counter if @assign is true else unassign the counter. Reset the * associated non-architectural state. */ -static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, +static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, enum resctrl_event_id evtid, u32 rmid, u32 closid, u32 cntr_id, bool assign) { @@ -1132,7 +1181,7 @@ static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain * * Return: * 0 on success, < 0 on failure. */ -static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, +static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, struct mon_evt *mevt) { int cntr_id; @@ -1167,7 +1216,7 @@ static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_mon_dom * Return: * 0 on success, < 0 on failure. */ -static int rdtgroup_assign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, +static int rdtgroup_assign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, struct mon_evt *mevt) { struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid); @@ -1217,7 +1266,7 @@ void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp) * rdtgroup_free_unassign_cntr() - Unassign and reset the counter ID configuration * for the event pointed to by @mevt within the domain @d and resctrl group @rdtgrp. */ -static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, +static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, struct mon_evt *mevt) { int cntr_id; @@ -1238,7 +1287,7 @@ static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_mon_d * the event structure @mevt from the domain @d and the group @rdtgrp. Unassign * the counters from all the domains if @d is NULL else unassign from @d. */ -static void rdtgroup_unassign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, +static void rdtgroup_unassign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, struct mon_evt *mevt) { struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid); @@ -1313,7 +1362,7 @@ next_config: static void rdtgroup_update_cntr_event(struct rdt_resource *r, struct rdtgroup *rdtgrp, enum resctrl_event_id evtid) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; int cntr_id; list_for_each_entry(d, &r->mon_domains, hdr.list) { @@ -1419,7 +1468,7 @@ ssize_t resctrl_mbm_assign_mode_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct rdt_resource *r = rdt_kn_parent_priv(of->kn); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; int ret = 0; bool enable; @@ -1492,7 +1541,7 @@ int resctrl_num_mbm_cntrs_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct rdt_resource *r = rdt_kn_parent_priv(of->kn); - struct rdt_mon_domain *dom; + struct rdt_l3_mon_domain *dom; bool sep = false; cpus_read_lock(); @@ -1516,7 +1565,7 @@ int resctrl_available_mbm_cntrs_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct rdt_resource *r = rdt_kn_parent_priv(of->kn); - struct rdt_mon_domain *dom; + struct rdt_l3_mon_domain *dom; bool sep = false; u32 cntrs, i; int ret = 0; @@ -1557,7 +1606,7 @@ out_unlock: int mbm_L3_assignments_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; struct rdtgroup *rdtgrp; struct mon_evt *mevt; int ret = 0; @@ -1620,7 +1669,7 @@ static struct mon_evt *mbm_get_mon_event_by_name(struct rdt_resource *r, char *n return NULL; } -static int rdtgroup_modify_assign_state(char *assign, struct rdt_mon_domain *d, +static int rdtgroup_modify_assign_state(char *assign, struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, struct mon_evt *mevt) { int ret = 0; @@ -1646,7 +1695,7 @@ static int rdtgroup_modify_assign_state(char *assign, struct rdt_mon_domain *d, static int resctrl_parse_mbm_assignment(struct rdt_resource *r, struct rdtgroup *rdtgrp, char *event, char *tok) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; unsigned long dom_id = 0; char *dom_str, *id_str; struct mon_evt *mevt; @@ -1741,19 +1790,59 @@ ssize_t mbm_L3_assignments_write(struct kernfs_open_file *of, char *buf, return ret ?: nbytes; } +static int closid_num_dirty_rmid_alloc(struct rdt_resource *r) +{ + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + u32 num_closid = resctrl_arch_get_num_closid(r); + u32 *tmp; + + /* For ARM memory ordering access to closid_num_dirty_rmid */ + mutex_lock(&rdtgroup_mutex); + + /* + * If the architecture hasn't provided a sanitised value here, + * this may result in larger arrays than necessary. Resctrl will + * use a smaller system wide value based on the resources in + * use. + */ + tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); + if (!tmp) { + mutex_unlock(&rdtgroup_mutex); + return -ENOMEM; + } + + closid_num_dirty_rmid = tmp; + + mutex_unlock(&rdtgroup_mutex); + } + + return 0; +} + +static void closid_num_dirty_rmid_free(void) +{ + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + mutex_lock(&rdtgroup_mutex); + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + mutex_unlock(&rdtgroup_mutex); + } +} + /** - * resctrl_mon_resource_init() - Initialise global monitoring structures. + * resctrl_l3_mon_resource_init() - Initialise global monitoring structures. * * Allocate and initialise global monitor resources that do not belong to a - * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists. + * specific domain. i.e. the closid_num_dirty_rmid[] used to find the CLOSID + * with the cleanest set of RMIDs. * Called once during boot after the struct rdt_resource's have been configured * but before the filesystem is mounted. * Resctrl's cpuhp callbacks may be called before this point to bring a domain * online. * - * Returns 0 for success, or -ENOMEM. + * Return: 0 for success, or -ENOMEM. */ -int resctrl_mon_resource_init(void) +int resctrl_l3_mon_resource_init(void) { struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); int ret; @@ -1761,7 +1850,7 @@ int resctrl_mon_resource_init(void) if (!r->mon_capable) return 0; - ret = dom_data_init(r); + ret = closid_num_dirty_rmid_alloc(r); if (ret) return ret; @@ -1803,9 +1892,12 @@ int resctrl_mon_resource_init(void) return 0; } -void resctrl_mon_resource_exit(void) +void resctrl_l3_mon_resource_exit(void) { struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); - dom_data_exit(r); + if (!r->mon_capable) + return; + + closid_num_dirty_rmid_free(); } diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 8e39dfda56bc..ba8d503551cd 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -1157,7 +1158,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of, { struct rdt_resource *r = rdt_kn_parent_priv(of->kn); - seq_printf(seq, "%d\n", r->mon.num_rmid); + seq_printf(seq, "%u\n", r->mon.num_rmid); return 0; } @@ -1640,7 +1641,7 @@ static void mondata_config_read(struct resctrl_mon_config_info *mon_info) static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid) { struct resctrl_mon_config_info mon_info; - struct rdt_mon_domain *dom; + struct rdt_l3_mon_domain *dom; bool sep = false; cpus_read_lock(); @@ -1688,7 +1689,7 @@ static int mbm_local_bytes_config_show(struct kernfs_open_file *of, } static void mbm_config_write_domain(struct rdt_resource *r, - struct rdt_mon_domain *d, u32 evtid, u32 val) + struct rdt_l3_mon_domain *d, u32 evtid, u32 val) { struct resctrl_mon_config_info mon_info = {0}; @@ -1729,8 +1730,8 @@ static void mbm_config_write_domain(struct rdt_resource *r, static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) { char *dom_str = NULL, *id_str; + struct rdt_l3_mon_domain *d; unsigned long dom_id, val; - struct rdt_mon_domain *d; /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); @@ -2395,6 +2396,8 @@ static unsigned long fflags_from_resource(struct rdt_resource *r) case RDT_RESOURCE_MBA: case RDT_RESOURCE_SMBA: return RFTYPE_RES_MB; + case RDT_RESOURCE_PERF_PKG: + return RFTYPE_RES_PERF_PKG; } return WARN_ON_ONCE(1); @@ -2781,10 +2784,12 @@ static int rdt_get_tree(struct fs_context *fc) { struct rdt_fs_context *ctx = rdt_fc2context(fc); unsigned long flags = RFTYPE_CTRL_BASE; - struct rdt_mon_domain *dom; + struct rdt_l3_mon_domain *dom; struct rdt_resource *r; int ret; + DO_ONCE_SLEEPABLE(resctrl_arch_pre_mount); + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* @@ -2795,6 +2800,10 @@ static int rdt_get_tree(struct fs_context *fc) goto out; } + ret = setup_rmid_lru_list(); + if (ret) + goto out; + ret = rdtgroup_setup_root(ctx); if (ret) goto out; @@ -3091,7 +3100,8 @@ static void rmdir_all_sub(void) * @rid: The resource id for the event file being created. * @domid: The domain id for the event file being created. * @mevt: The type of event file being created. - * @do_sum: Whether SNC summing monitors are being created. + * @do_sum: Whether SNC summing monitors are being created. Only set + * when @rid == RDT_RESOURCE_L3. */ static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid, struct mon_evt *mevt, @@ -3103,7 +3113,7 @@ static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid, list_for_each_entry(priv, &mon_data_kn_priv_list, list) { if (priv->rid == rid && priv->domid == domid && - priv->sum == do_sum && priv->evtid == mevt->evtid) + priv->sum == do_sum && priv->evt == mevt) return priv; } @@ -3114,7 +3124,7 @@ static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid, priv->rid = rid; priv->domid = domid; priv->sum = do_sum; - priv->evtid = mevt->evtid; + priv->evt = mevt; list_add_tail(&priv->list, &mon_data_kn_priv_list); return priv; @@ -3223,23 +3233,24 @@ static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subn } /* - * Remove all subdirectories of mon_data of ctrl_mon groups - * and monitor groups for the given domain. - * Remove files and directories containing "sum" of domain data - * when last domain being summed is removed. + * Remove files and directories for one SNC node. If it is the last node + * sharing an L3 cache, then remove the upper level directory containing + * the "sum" files too. */ -static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_mon_domain *d) +static void rmdir_mondata_subdir_allrdtgrp_snc(struct rdt_resource *r, + struct rdt_domain_hdr *hdr) { struct rdtgroup *prgrp, *crgrp; + struct rdt_l3_mon_domain *d; char subname[32]; - bool snc_mode; char name[32]; - snc_mode = r->mon_scope == RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); - if (snc_mode) - sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id); + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + sprintf(name, "mon_%s_%02d", r->name, d->ci_id); + sprintf(subname, "mon_sub_%s_%02d", r->name, hdr->id); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname); @@ -3249,47 +3260,89 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, } } -static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d, - struct rdt_resource *r, struct rdtgroup *prgrp, - bool do_sum) +/* + * Remove all subdirectories of mon_data of ctrl_mon groups + * and monitor groups for the given domain. + */ +static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain_hdr *hdr) +{ + struct rdtgroup *prgrp, *crgrp; + char name[32]; + + if (r->rid == RDT_RESOURCE_L3 && r->mon_scope == RESCTRL_L3_NODE) { + rmdir_mondata_subdir_allrdtgrp_snc(r, hdr); + return; + } + + sprintf(name, "mon_%s_%02d", r->name, hdr->id); + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + kernfs_remove_by_name(prgrp->mon.mon_data_kn, name); + + list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) + kernfs_remove_by_name(crgrp->mon.mon_data_kn, name); + } +} + +/* + * Create a directory for a domain and populate it with monitor files. Create + * summing monitors when @hdr is NULL. No need to initialize summing monitors. + */ +static struct kernfs_node *_mkdir_mondata_subdir(struct kernfs_node *parent_kn, char *name, + struct rdt_domain_hdr *hdr, + struct rdt_resource *r, + struct rdtgroup *prgrp, int domid) { struct rmid_read rr = {0}; + struct kernfs_node *kn; struct mon_data *priv; struct mon_evt *mevt; - int ret, domid; + int ret; + + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return kn; + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; for_each_mon_event(mevt) { if (mevt->rid != r->rid || !mevt->enabled) continue; - domid = do_sum ? d->ci_id : d->hdr.id; - priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum); - if (WARN_ON_ONCE(!priv)) - return -EINVAL; + priv = mon_get_kn_priv(r->rid, domid, mevt, !hdr); + if (WARN_ON_ONCE(!priv)) { + ret = -EINVAL; + goto out_destroy; + } ret = mon_addfile(kn, mevt->name, priv); if (ret) - return ret; + goto out_destroy; - if (!do_sum && resctrl_is_mbm_event(mevt->evtid)) - mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true); + if (hdr && resctrl_is_mbm_event(mevt->evtid)) + mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt, true); } - return 0; + return kn; +out_destroy: + kernfs_remove(kn); + return ERR_PTR(ret); } -static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, - struct rdt_mon_domain *d, - struct rdt_resource *r, struct rdtgroup *prgrp) +static int mkdir_mondata_subdir_snc(struct kernfs_node *parent_kn, + struct rdt_domain_hdr *hdr, + struct rdt_resource *r, struct rdtgroup *prgrp) { - struct kernfs_node *kn, *ckn; + struct kernfs_node *ckn, *kn; + struct rdt_l3_mon_domain *d; char name[32]; - bool snc_mode; - int ret = 0; - lockdep_assert_held(&rdtgroup_mutex); + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return -EINVAL; - snc_mode = r->mon_scope == RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + sprintf(name, "mon_%s_%02d", r->name, d->ci_id); kn = kernfs_find_and_get(parent_kn, name); if (kn) { /* @@ -3298,41 +3351,41 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, */ kernfs_put(kn); } else { - kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + kn = _mkdir_mondata_subdir(parent_kn, name, NULL, r, prgrp, d->ci_id); if (IS_ERR(kn)) return PTR_ERR(kn); - - ret = rdtgroup_kn_set_ugid(kn); - if (ret) - goto out_destroy; - ret = mon_add_all_files(kn, d, r, prgrp, snc_mode); - if (ret) - goto out_destroy; } - if (snc_mode) { - sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id); - ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp); - if (IS_ERR(ckn)) { - ret = -EINVAL; - goto out_destroy; - } - - ret = rdtgroup_kn_set_ugid(ckn); - if (ret) - goto out_destroy; - - ret = mon_add_all_files(ckn, d, r, prgrp, false); - if (ret) - goto out_destroy; + sprintf(name, "mon_sub_%s_%02d", r->name, hdr->id); + ckn = _mkdir_mondata_subdir(kn, name, hdr, r, prgrp, hdr->id); + if (IS_ERR(ckn)) { + kernfs_remove(kn); + return PTR_ERR(ckn); } kernfs_activate(kn); return 0; +} -out_destroy: - kernfs_remove(kn); - return ret; +static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, + struct rdt_domain_hdr *hdr, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + struct kernfs_node *kn; + char name[32]; + + lockdep_assert_held(&rdtgroup_mutex); + + if (r->rid == RDT_RESOURCE_L3 && r->mon_scope == RESCTRL_L3_NODE) + return mkdir_mondata_subdir_snc(parent_kn, hdr, r, prgrp); + + sprintf(name, "mon_%s_%02d", r->name, hdr->id); + kn = _mkdir_mondata_subdir(parent_kn, name, hdr, r, prgrp, hdr->id); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + kernfs_activate(kn); + return 0; } /* @@ -3340,7 +3393,7 @@ out_destroy: * and "monitor" groups with given domain id. */ static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_mon_domain *d) + struct rdt_domain_hdr *hdr) { struct kernfs_node *parent_kn; struct rdtgroup *prgrp, *crgrp; @@ -3348,12 +3401,12 @@ static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { parent_kn = prgrp->mon.mon_data_kn; - mkdir_mondata_subdir(parent_kn, d, r, prgrp); + mkdir_mondata_subdir(parent_kn, hdr, r, prgrp); head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) { parent_kn = crgrp->mon.mon_data_kn; - mkdir_mondata_subdir(parent_kn, d, r, crgrp); + mkdir_mondata_subdir(parent_kn, hdr, r, crgrp); } } } @@ -3362,14 +3415,14 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, struct rdt_resource *r, struct rdtgroup *prgrp) { - struct rdt_mon_domain *dom; + struct rdt_domain_hdr *hdr; int ret; /* Walking r->domains, ensure it can't race with cpuhp */ lockdep_assert_cpus_held(); - list_for_each_entry(dom, &r->mon_domains, hdr.list) { - ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); + list_for_each_entry(hdr, &r->mon_domains, list) { + ret = mkdir_mondata_subdir(parent_kn, hdr, r, prgrp); if (ret) return ret; } @@ -4231,7 +4284,7 @@ static void rdtgroup_setup_default(void) mutex_unlock(&rdtgroup_mutex); } -static void domain_destroy_mon_state(struct rdt_mon_domain *d) +static void domain_destroy_l3_mon_state(struct rdt_l3_mon_domain *d) { int idx; @@ -4253,8 +4306,10 @@ void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain mutex_unlock(&rdtgroup_mutex); } -void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr) { + struct rdt_l3_mon_domain *d; + mutex_lock(&rdtgroup_mutex); /* @@ -4262,8 +4317,15 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d * per domain monitor data directories. */ if (resctrl_mounted && resctrl_arch_mon_capable()) - rmdir_mondata_subdir_allrdtgrp(r, d); + rmdir_mondata_subdir_allrdtgrp(r, hdr); + if (r->rid != RDT_RESOURCE_L3) + goto out_unlock; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + goto out_unlock; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); if (resctrl_is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(d)) { @@ -4279,13 +4341,13 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d cancel_delayed_work(&d->cqm_limbo); } - domain_destroy_mon_state(d); - + domain_destroy_l3_mon_state(d); +out_unlock: mutex_unlock(&rdtgroup_mutex); } /** - * domain_setup_mon_state() - Initialise domain monitoring structures. + * domain_setup_l3_mon_state() - Initialise domain monitoring structures. * @r: The resource for the newly online domain. * @d: The newly online domain. * @@ -4293,11 +4355,17 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d * Called when the first CPU of a domain comes online, regardless of whether * the filesystem is mounted. * During boot this may be called before global allocations have been made by - * resctrl_mon_resource_init(). + * resctrl_l3_mon_resource_init(). * - * Returns 0 for success, or -ENOMEM. + * Called during CPU online that may run as soon as CPU online callbacks + * are set up during resctrl initialization. The number of supported RMIDs + * may be reduced if additional mon_capable resources are enumerated + * at mount time. This means the rdt_l3_mon_domain::mbm_states[] and + * rdt_l3_mon_domain::rmid_busy_llc allocations may be larger than needed. + * + * Return: 0 for success, or -ENOMEM. */ -static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d) +static int domain_setup_l3_mon_state(struct rdt_resource *r, struct rdt_l3_mon_domain *d) { u32 idx_limit = resctrl_arch_system_num_rmid_idx(); size_t tsize = sizeof(*d->mbm_states[0]); @@ -4353,13 +4421,21 @@ int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d return err; } -int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr) { - int err; + struct rdt_l3_mon_domain *d; + int err = -EINVAL; mutex_lock(&rdtgroup_mutex); - err = domain_setup_mon_state(r, d); + if (r->rid != RDT_RESOURCE_L3) + goto mkdir; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + goto out_unlock; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + err = domain_setup_l3_mon_state(r, d); if (err) goto out_unlock; @@ -4372,6 +4448,8 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); +mkdir: + err = 0; /* * If the filesystem is not mounted then only the default resource group * exists. Creation of its directories is deferred until mount time @@ -4379,7 +4457,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) * If resctrl is mounted, add per domain monitor data directories. */ if (resctrl_mounted && resctrl_arch_mon_capable()) - mkdir_mondata_subdir_allrdtgrp(r, d); + mkdir_mondata_subdir_allrdtgrp(r, hdr); out_unlock: mutex_unlock(&rdtgroup_mutex); @@ -4405,10 +4483,10 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) } } -static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, - struct rdt_resource *r) +static struct rdt_l3_mon_domain *get_mon_domain_from_cpu(int cpu, + struct rdt_resource *r) { - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; lockdep_assert_cpus_held(); @@ -4424,7 +4502,7 @@ static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, void resctrl_offline_cpu(unsigned int cpu) { struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3); - struct rdt_mon_domain *d; + struct rdt_l3_mon_domain *d; struct rdtgroup *rdtgrp; mutex_lock(&rdtgroup_mutex); @@ -4476,13 +4554,13 @@ int resctrl_init(void) io_alloc_init(); - ret = resctrl_mon_resource_init(); + ret = resctrl_l3_mon_resource_init(); if (ret) return ret; ret = sysfs_create_mount_point(fs_kobj, "resctrl"); if (ret) { - resctrl_mon_resource_exit(); + resctrl_l3_mon_resource_exit(); return ret; } @@ -4517,7 +4595,7 @@ int resctrl_init(void) cleanup_mountpoint: sysfs_remove_mount_point(fs_kobj, "resctrl"); - resctrl_mon_resource_exit(); + resctrl_l3_mon_resource_exit(); return ret; } @@ -4553,7 +4631,7 @@ static bool resctrl_online_domains_exist(void) * When called by the architecture code, all CPUs and resctrl domains must be * offline. This ensures the limbo and overflow handlers are not scheduled to * run, meaning the data structures they access can be freed by - * resctrl_mon_resource_exit(). + * resctrl_l3_mon_resource_exit(). * * After resctrl_exit() returns, the architecture code should return an * error from all resctrl_arch_ functions that can do this. @@ -4580,5 +4658,6 @@ void resctrl_exit(void) * it can be used to umount resctrl. */ - resctrl_mon_resource_exit(); + resctrl_l3_mon_resource_exit(); + free_rmid_lru_list(); } diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 54701668b3df..006e57fd7ca5 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -53,6 +53,7 @@ enum resctrl_res_level { RDT_RESOURCE_L2, RDT_RESOURCE_MBA, RDT_RESOURCE_SMBA, + RDT_RESOURCE_PERF_PKG, /* Must be the last */ RDT_NUM_RESOURCES, @@ -131,15 +132,24 @@ enum resctrl_domain_type { * @list: all instances of this resource * @id: unique id for this instance * @type: type of this instance + * @rid: resource id for this instance * @cpu_mask: which CPUs share this resource */ struct rdt_domain_hdr { struct list_head list; int id; enum resctrl_domain_type type; + enum resctrl_res_level rid; struct cpumask cpu_mask; }; +static inline bool domain_header_is_valid(struct rdt_domain_hdr *hdr, + enum resctrl_domain_type type, + enum resctrl_res_level rid) +{ + return !WARN_ON_ONCE(hdr->type != type || hdr->rid != rid); +} + /** * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource * @hdr: common header for different domain types @@ -169,7 +179,7 @@ struct mbm_cntr_cfg { }; /** - * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource + * struct rdt_l3_mon_domain - group of CPUs sharing RDT_RESOURCE_L3 monitoring * @hdr: common header for different domain types * @ci_id: cache info id for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold @@ -183,7 +193,7 @@ struct mbm_cntr_cfg { * @cntr_cfg: array of assignable counters' configuration (indexed * by counter ID) */ -struct rdt_mon_domain { +struct rdt_l3_mon_domain { struct rdt_domain_hdr hdr; unsigned int ci_id; unsigned long *rmid_busy_llc; @@ -261,6 +271,7 @@ enum resctrl_scope { RESCTRL_L2_CACHE = 2, RESCTRL_L3_CACHE = 3, RESCTRL_L3_NODE, + RESCTRL_PACKAGE, }; /** @@ -284,7 +295,7 @@ enum resctrl_schema_fmt { * events of monitor groups created via mkdir. */ struct resctrl_mon { - int num_rmid; + u32 num_rmid; unsigned int mbm_cfg_mask; int num_mbm_cntrs; bool mbm_cntr_assignable; @@ -358,10 +369,10 @@ struct resctrl_cpu_defaults { }; struct resctrl_mon_config_info { - struct rdt_resource *r; - struct rdt_mon_domain *d; - u32 evtid; - u32 mon_config; + struct rdt_resource *r; + struct rdt_l3_mon_domain *d; + u32 evtid; + u32 mon_config; }; /** @@ -403,7 +414,8 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); -void resctrl_enable_mon_event(enum resctrl_event_id eventid); +bool resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, + unsigned int binary_bits, void *arch_priv); bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid); @@ -498,22 +510,31 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type); int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); -int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr); void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); -void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr); void resctrl_online_cpu(unsigned int cpu); void resctrl_offline_cpu(unsigned int cpu); +/* + * Architecture hook called at beginning of first file system mount attempt. + * No locks are held. + */ +void resctrl_arch_pre_mount(void); + /** * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid * for this resource and domain. * @r: resource that the counter should be read from. - * @d: domain that the counter should be read from. + * @hdr: Header of domain that the counter should be read from. * @closid: closid that matches the rmid. Depending on the architecture, the * counter may match traffic of both @closid and @rmid, or @rmid * only. * @rmid: rmid of the counter to read. * @eventid: eventid to read, e.g. L3 occupancy. + * @arch_priv: Architecture private data for this event. + * The @arch_priv provided by the architecture via + * resctrl_enable_mon_event(). * @val: result of the counter read in bytes. * @arch_mon_ctx: An architecture specific value from * resctrl_arch_mon_ctx_alloc(), for MPAM this identifies @@ -529,9 +550,9 @@ void resctrl_offline_cpu(unsigned int cpu); * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr, u32 closid, u32 rmid, enum resctrl_event_id eventid, - u64 *val, void *arch_mon_ctx); + void *arch_priv, u64 *val, void *arch_mon_ctx); /** * resctrl_arch_rmid_read_context_check() - warn about invalid contexts @@ -576,7 +597,7 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid); @@ -589,7 +610,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d); +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d); /** * resctrl_arch_reset_all_ctrls() - Reset the control for each CLOSID to its @@ -615,7 +636,7 @@ void resctrl_arch_reset_all_ctrls(struct rdt_resource *r); * * This can be called from any CPU. */ -void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, enum resctrl_event_id evtid, u32 rmid, u32 closid, u32 cntr_id, bool assign); @@ -638,7 +659,7 @@ void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ -int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d, +int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 closid, u32 rmid, int cntr_id, enum resctrl_event_id eventid, u64 *val); @@ -653,7 +674,7 @@ int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d, * * This can be called from any CPU. */ -void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 closid, u32 rmid, int cntr_id, enum resctrl_event_id eventid); diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h index acfe07860b34..a5f56faa18d2 100644 --- a/include/linux/resctrl_types.h +++ b/include/linux/resctrl_types.h @@ -50,6 +50,17 @@ enum resctrl_event_id { QOS_L3_MBM_TOTAL_EVENT_ID = 0x02, QOS_L3_MBM_LOCAL_EVENT_ID = 0x03, + /* Intel Telemetry Events */ + PMT_EVENT_ENERGY, + PMT_EVENT_ACTIVITY, + PMT_EVENT_STALLS_LLC_HIT, + PMT_EVENT_C1_RES, + PMT_EVENT_UNHALTED_CORE_CYCLES, + PMT_EVENT_STALLS_LLC_MISS, + PMT_EVENT_AUTO_C6_RES, + PMT_EVENT_UNHALTED_REF_CYCLES, + PMT_EVENT_UOPS_RETIRED, + /* Must be the last */ QOS_NUM_EVENTS, };