diff options
Diffstat (limited to 'arch/x86/kernel/cpu/resctrl')
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/Makefile | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/core.c | 1047 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 490 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/internal.h | 632 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/monitor.c | 649 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 1594 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h | 43 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/rdtgroup.c | 3263 |
8 files changed, 7722 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile new file mode 100644 index 000000000..4a06c37b9 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o pseudo_lock.o +CFLAGS_pseudo_lock.o = -I$(src) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c new file mode 100644 index 000000000..4ccb9039f --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -0,0 +1,1047 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Cache Allocation code. + * + * Copyright (C) 2016 Intel Corporation + * + * Authors: + * Fenghua Yu <fenghua.yu@intel.com> + * Tony Luck <tony.luck@intel.com> + * Vikas Shivappa <vikas.shivappa@intel.com> + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#define pr_fmt(fmt) "resctrl: " fmt + +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/cacheinfo.h> +#include <linux/cpuhotplug.h> + +#include <asm/intel-family.h> +#include <asm/resctrl.h> +#include "internal.h" + +/* Mutex to protect rdtgroup access. */ +DEFINE_MUTEX(rdtgroup_mutex); + +/* + * The cached resctrl_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Functions which modify the state + * are called with interrupts disabled and no preemption, which + * is sufficient for the protection. + */ +DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state); + +/* + * Used to store the max resource name width and max resource data width + * to display the schemata in a tabular format + */ +int max_name_width, max_data_width; + +/* + * Global boolean for rdt_alloc which is true if any + * resource allocation is enabled. + */ +bool rdt_alloc_capable; + +static void +mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, + struct rdt_resource *r); +static void +cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); +static void +mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, + struct rdt_resource *r); + +#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) + +struct rdt_resource rdt_resources_all[] = { + [RDT_RESOURCE_L3] = + { + .rid = RDT_RESOURCE_L3, + .name = "L3", + .domains = domain_init(RDT_RESOURCE_L3), + .msr_base = MSR_IA32_L3_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 1, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, + [RDT_RESOURCE_L3DATA] = + { + .rid = RDT_RESOURCE_L3DATA, + .name = "L3DATA", + .domains = domain_init(RDT_RESOURCE_L3DATA), + .msr_base = MSR_IA32_L3_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, + [RDT_RESOURCE_L3CODE] = + { + .rid = RDT_RESOURCE_L3CODE, + .name = "L3CODE", + .domains = domain_init(RDT_RESOURCE_L3CODE), + .msr_base = MSR_IA32_L3_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 3, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 1, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, + [RDT_RESOURCE_L2] = + { + .rid = RDT_RESOURCE_L2, + .name = "L2", + .domains = domain_init(RDT_RESOURCE_L2), + .msr_base = MSR_IA32_L2_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 1, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, + [RDT_RESOURCE_L2DATA] = + { + .rid = RDT_RESOURCE_L2DATA, + .name = "L2DATA", + .domains = domain_init(RDT_RESOURCE_L2DATA), + .msr_base = MSR_IA32_L2_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 0, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, + [RDT_RESOURCE_L2CODE] = + { + .rid = RDT_RESOURCE_L2CODE, + .name = "L2CODE", + .domains = domain_init(RDT_RESOURCE_L2CODE), + .msr_base = MSR_IA32_L2_CBM_BASE, + .msr_update = cat_wrmsr, + .cache_level = 2, + .cache = { + .min_cbm_bits = 1, + .cbm_idx_mult = 2, + .cbm_idx_offset = 1, + }, + .parse_ctrlval = parse_cbm, + .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, + }, + [RDT_RESOURCE_MBA] = + { + .rid = RDT_RESOURCE_MBA, + .name = "MB", + .domains = domain_init(RDT_RESOURCE_MBA), + .cache_level = 3, + .parse_ctrlval = parse_bw, + .format_str = "%d=%*u", + .fflags = RFTYPE_RES_MB, + }, +}; + +static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) +{ + return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset; +} + +/* + * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs + * as they do not have CPUID enumeration support for Cache allocation. + * The check for Vendor/Family/Model is not enough to guarantee that + * the MSRs won't #GP fault because only the following SKUs support + * CAT: + * Intel(R) Xeon(R) CPU E5-2658 v3 @ 2.20GHz + * Intel(R) Xeon(R) CPU E5-2648L v3 @ 1.80GHz + * Intel(R) Xeon(R) CPU E5-2628L v3 @ 2.00GHz + * Intel(R) Xeon(R) CPU E5-2618L v3 @ 2.30GHz + * Intel(R) Xeon(R) CPU E5-2608L v3 @ 2.00GHz + * Intel(R) Xeon(R) CPU E5-2658A v3 @ 2.20GHz + * + * Probe by trying to write the first of the L3 cach mask registers + * and checking that the bits stick. Max CLOSids is always 4 and max cbm length + * is always 20 on hsw server parts. The minimum cache bitmask length + * allowed for HSW server is always 2 bits. Hardcode all of them. + */ +static inline void cache_alloc_hsw_probe(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + u32 l, h, max_cbm = BIT_MASK(20) - 1; + + if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0)) + return; + + rdmsr(MSR_IA32_L3_CBM_BASE, l, h); + + /* If all the bits were set in MSR, return success */ + if (l != max_cbm) + return; + + r->num_closid = 4; + r->default_ctrl = max_cbm; + r->cache.cbm_len = 20; + r->cache.shareable_bits = 0xc0000; + r->cache.min_cbm_bits = 2; + r->alloc_capable = true; + r->alloc_enabled = true; + + rdt_alloc_capable = true; +} + +bool is_mba_sc(struct rdt_resource *r) +{ + if (!r) + return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc; + + return r->membw.mba_sc; +} + +/* + * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values + * exposed to user interface and the h/w understandable delay values. + * + * The non-linear delay values have the granularity of power of two + * and also the h/w does not guarantee a curve for configured delay + * values vs. actual b/w enforced. + * Hence we need a mapping that is pre calibrated so the user can + * express the memory b/w as a percentage value. + */ +static inline bool rdt_get_mb_table(struct rdt_resource *r) +{ + /* + * There are no Intel SKUs as of now to support non-linear delay. + */ + pr_info("MBA b/w map not implemented for cpu:%d, model:%d", + boot_cpu_data.x86, boot_cpu_data.x86_model); + + return false; +} + +static bool __get_mem_config_intel(struct rdt_resource *r) +{ + union cpuid_0x10_3_eax eax; + union cpuid_0x10_x_edx edx; + u32 ebx, ecx, max_delay; + + cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full); + r->num_closid = edx.split.cos_max + 1; + max_delay = eax.split.max_delay + 1; + r->default_ctrl = MAX_MBA_BW; + r->membw.arch_needs_linear = true; + if (ecx & MBA_IS_LINEAR) { + r->membw.delay_linear = true; + r->membw.min_bw = MAX_MBA_BW - max_delay; + r->membw.bw_gran = MAX_MBA_BW - max_delay; + } else { + if (!rdt_get_mb_table(r)) + return false; + r->membw.arch_needs_linear = false; + } + r->data_width = 3; + + if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA)) + r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD; + else + r->membw.throttle_mode = THREAD_THROTTLE_MAX; + thread_throttle_mode_init(); + + r->alloc_capable = true; + r->alloc_enabled = true; + + return true; +} + +static bool __rdt_get_mem_config_amd(struct rdt_resource *r) +{ + union cpuid_0x10_3_eax eax; + union cpuid_0x10_x_edx edx; + u32 ebx, ecx; + + cpuid_count(0x80000020, 1, &eax.full, &ebx, &ecx, &edx.full); + r->num_closid = edx.split.cos_max + 1; + r->default_ctrl = MAX_MBA_BW_AMD; + + /* AMD does not use delay */ + r->membw.delay_linear = false; + r->membw.arch_needs_linear = false; + + /* + * AMD does not use memory delay throttle model to control + * the allocation like Intel does. + */ + r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED; + r->membw.min_bw = 0; + r->membw.bw_gran = 1; + /* Max value is 2048, Data width should be 4 in decimal */ + r->data_width = 4; + + r->alloc_capable = true; + r->alloc_enabled = true; + + return true; +} + +static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) +{ + union cpuid_0x10_1_eax eax; + union cpuid_0x10_x_edx edx; + u32 ebx, ecx; + + cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); + r->num_closid = edx.split.cos_max + 1; + r->cache.cbm_len = eax.split.cbm_len + 1; + r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->cache.shareable_bits = ebx & r->default_ctrl; + r->data_width = (r->cache.cbm_len + 3) / 4; + r->alloc_capable = true; + r->alloc_enabled = true; +} + +static void rdt_get_cdp_config(int level, int type) +{ + struct rdt_resource *r_l = &rdt_resources_all[level]; + struct rdt_resource *r = &rdt_resources_all[type]; + + r->num_closid = r_l->num_closid / 2; + r->cache.cbm_len = r_l->cache.cbm_len; + r->default_ctrl = r_l->default_ctrl; + r->cache.shareable_bits = r_l->cache.shareable_bits; + r->data_width = (r->cache.cbm_len + 3) / 4; + r->alloc_capable = true; + /* + * By default, CDP is disabled. CDP can be enabled by mount parameter + * "cdp" during resctrl file system mount time. + */ + r->alloc_enabled = false; +} + +static void rdt_get_cdp_l3_config(void) +{ + rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA); + rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3CODE); +} + +static void rdt_get_cdp_l2_config(void) +{ + rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA); + rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE); +} + +static void +mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) +{ + unsigned int i; + + for (i = m->low; i < m->high; i++) + wrmsrl(r->msr_base + i, d->ctrl_val[i]); +} + +/* + * Map the memory b/w percentage value to delay values + * that can be written to QOS_MSRs. + * There are currently no SKUs which support non linear delay values. + */ +u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) +{ + if (r->membw.delay_linear) + return MAX_MBA_BW - bw; + + pr_warn_once("Non Linear delay-bw map not supported but queried\n"); + return r->default_ctrl; +} + +static void +mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, + struct rdt_resource *r) +{ + unsigned int i; + + /* Write the delay values for mba. */ + for (i = m->low; i < m->high; i++) + wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r)); +} + +static void +cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) +{ + unsigned int i; + + for (i = m->low; i < m->high; i++) + wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]); +} + +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) +{ + struct rdt_domain *d; + + list_for_each_entry(d, &r->domains, list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->cpu_mask)) + return d; + } + + return NULL; +} + +void rdt_ctrl_update(void *arg) +{ + struct msr_param *m = arg; + struct rdt_resource *r = m->res; + int cpu = smp_processor_id(); + struct rdt_domain *d; + + d = get_domain_from_cpu(cpu, r); + if (d) { + r->msr_update(d, m, r); + return; + } + pr_warn_once("cpu %d not found in any domain for resource %s\n", + cpu, r->name); +} + +/* + * rdt_find_domain - Find a domain in a resource that matches input resource id + * + * Search resource r's domain list to find the resource id. If the resource + * id is found in a domain, return the domain. Otherwise, if requested by + * caller, return the first domain whose id is bigger than the input id. + * The domain list is sorted by id in ascending order. + */ +struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos) +{ + struct rdt_domain *d; + struct list_head *l; + + if (id < 0) + return ERR_PTR(-ENODEV); + + list_for_each(l, &r->domains) { + d = list_entry(l, struct rdt_domain, list); + /* When id is found, return its domain. */ + if (id == d->id) + return d; + /* Stop searching when finding id's position in sorted list. */ + if (id < d->id) + break; + } + + if (pos) + *pos = l; + + return NULL; +} + +void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) +{ + int i; + + /* + * Initialize the Control MSRs to having no control. + * For Cache Allocation: Set all bits in cbm + * For Memory Allocation: Set b/w requested to 100% + * and the bandwidth in MBps to U32_MAX + */ + for (i = 0; i < r->num_closid; i++, dc++, dm++) { + *dc = r->default_ctrl; + *dm = MBA_MAX_MBPS; + } +} + +static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) +{ + struct msr_param m; + u32 *dc, *dm; + + dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); + if (!dc) + return -ENOMEM; + + dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL); + if (!dm) { + kfree(dc); + return -ENOMEM; + } + + d->ctrl_val = dc; + d->mbps_val = dm; + setup_default_ctrlval(r, dc, dm); + + m.low = 0; + m.high = r->num_closid; + r->msr_update(d, &m, r); + return 0; +} + +static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) +{ + size_t tsize; + + if (is_llc_occupancy_enabled()) { + d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); + if (!d->rmid_busy_llc) + return -ENOMEM; + INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); + } + if (is_mbm_total_enabled()) { + tsize = sizeof(*d->mbm_total); + d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_total) { + bitmap_free(d->rmid_busy_llc); + return -ENOMEM; + } + } + if (is_mbm_local_enabled()) { + tsize = sizeof(*d->mbm_local); + d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_local) { + bitmap_free(d->rmid_busy_llc); + kfree(d->mbm_total); + return -ENOMEM; + } + } + + if (is_mbm_enabled()) { + INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + } + + return 0; +} + +/* + * domain_add_cpu - Add a cpu to a resource's domain list. + * + * If an existing domain in the resource r's domain list matches the cpu's + * resource id, add the cpu in the domain. + * + * Otherwise, a new domain is allocated and inserted into the right position + * in the domain list sorted by id in ascending order. + * + * The order in the domain list is visible to users when we print entries + * in the schemata file and schemata input is validated to have the same order + * as this list. + */ +static void domain_add_cpu(int cpu, struct rdt_resource *r) +{ + int id = get_cpu_cacheinfo_id(cpu, r->cache_level); + struct list_head *add_pos = NULL; + struct rdt_domain *d; + + d = rdt_find_domain(r, id, &add_pos); + if (IS_ERR(d)) { + pr_warn("Couldn't find cache id for CPU %d\n", cpu); + return; + } + + if (d) { + cpumask_set_cpu(cpu, &d->cpu_mask); + if (r->cache.arch_has_per_cpu_cfg) + rdt_domain_reconfigure_cdp(r); + return; + } + + d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); + if (!d) + return; + + d->id = id; + cpumask_set_cpu(cpu, &d->cpu_mask); + + rdt_domain_reconfigure_cdp(r); + + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { + kfree(d); + return; + } + + if (r->mon_capable && domain_setup_mon_state(r, d)) { + kfree(d->ctrl_val); + kfree(d->mbps_val); + kfree(d); + return; + } + + list_add_tail(&d->list, add_pos); + + /* + * If resctrl is mounted, add + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + mkdir_mondata_subdir_allrdtgrp(r, d); +} + +static void domain_remove_cpu(int cpu, struct rdt_resource *r) +{ + int id = get_cpu_cacheinfo_id(cpu, r->cache_level); + struct rdt_domain *d; + + d = rdt_find_domain(r, id, NULL); + if (IS_ERR_OR_NULL(d)) { + pr_warn("Couldn't find cache id for CPU %d\n", cpu); + return; + } + + cpumask_clear_cpu(cpu, &d->cpu_mask); + if (cpumask_empty(&d->cpu_mask)) { + /* + * If resctrl is mounted, remove all the + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + rmdir_mondata_subdir_allrdtgrp(r, d->id); + list_del(&d->list); + if (r->mon_capable && is_mbm_enabled()) + cancel_delayed_work(&d->mbm_over); + if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + /* + * When a package is going down, forcefully + * decrement rmid->ebusy. There is no way to know + * that the L3 was flushed and hence may lead to + * incorrect counts in rare scenarios, but leaving + * the RMID as busy creates RMID leaks if the + * package never comes back. + */ + __check_limbo(d, true); + cancel_delayed_work(&d->cqm_limbo); + } + + /* + * rdt_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + + kfree(d->ctrl_val); + kfree(d->mbps_val); + bitmap_free(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); + kfree(d); + return; + } + + if (r == &rdt_resources_all[RDT_RESOURCE_L3]) { + if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0); + } + if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && + has_busy_rmid(r, d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0); + } + } +} + +static void clear_closid_rmid(int cpu) +{ + struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); + + state->default_closid = 0; + state->default_rmid = 0; + state->cur_closid = 0; + state->cur_rmid = 0; + wrmsr(IA32_PQR_ASSOC, 0, 0); +} + +static int resctrl_online_cpu(unsigned int cpu) +{ + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + for_each_capable_rdt_resource(r) + domain_add_cpu(cpu, r); + /* The cpu is set in default rdtgroup after online. */ + cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + clear_closid_rmid(cpu); + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +{ + struct rdtgroup *cr; + + list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { + if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) { + break; + } + } +} + +static int resctrl_offline_cpu(unsigned int cpu) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + + mutex_lock(&rdtgroup_mutex); + for_each_capable_rdt_resource(r) + domain_remove_cpu(cpu, r); + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { + clear_childcpus(rdtgrp, cpu); + break; + } + } + clear_closid_rmid(cpu); + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +/* + * Choose a width for the resource name and resource data based on the + * resource that has widest name and cbm. + */ +static __init void rdt_init_padding(void) +{ + struct rdt_resource *r; + int cl; + + for_each_alloc_capable_rdt_resource(r) { + cl = strlen(r->name); + if (cl > max_name_width) + max_name_width = cl; + + if (r->data_width > max_data_width) + max_data_width = r->data_width; + } +} + +enum { + RDT_FLAG_CMT, + RDT_FLAG_MBM_TOTAL, + RDT_FLAG_MBM_LOCAL, + RDT_FLAG_L3_CAT, + RDT_FLAG_L3_CDP, + RDT_FLAG_L2_CAT, + RDT_FLAG_L2_CDP, + RDT_FLAG_MBA, +}; + +#define RDT_OPT(idx, n, f) \ +[idx] = { \ + .name = n, \ + .flag = f \ +} + +struct rdt_options { + char *name; + int flag; + bool force_off, force_on; +}; + +static struct rdt_options rdt_options[] __initdata = { + RDT_OPT(RDT_FLAG_CMT, "cmt", X86_FEATURE_CQM_OCCUP_LLC), + RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL), + RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL), + RDT_OPT(RDT_FLAG_L3_CAT, "l3cat", X86_FEATURE_CAT_L3), + RDT_OPT(RDT_FLAG_L3_CDP, "l3cdp", X86_FEATURE_CDP_L3), + RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2), + RDT_OPT(RDT_FLAG_L2_CDP, "l2cdp", X86_FEATURE_CDP_L2), + RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA), +}; +#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options) + +static int __init set_rdt_options(char *str) +{ + struct rdt_options *o; + bool force_off; + char *tok; + + if (*str == '=') + str++; + while ((tok = strsep(&str, ",")) != NULL) { + force_off = *tok == '!'; + if (force_off) + tok++; + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (strcmp(tok, o->name) == 0) { + if (force_off) + o->force_off = true; + else + o->force_on = true; + break; + } + } + } + return 1; +} +__setup("rdt", set_rdt_options); + +static bool __init rdt_cpu_has(int flag) +{ + bool ret = boot_cpu_has(flag); + struct rdt_options *o; + + if (!ret) + return ret; + + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (flag == o->flag) { + if (o->force_off) + ret = false; + if (o->force_on) + ret = true; + break; + } + } + return ret; +} + +static __init bool get_mem_config(void) +{ + if (!rdt_cpu_has(X86_FEATURE_MBA)) + return false; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return __get_mem_config_intel(&rdt_resources_all[RDT_RESOURCE_MBA]); + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return __rdt_get_mem_config_amd(&rdt_resources_all[RDT_RESOURCE_MBA]); + + return false; +} + +static __init bool get_rdt_alloc_resources(void) +{ + bool ret = false; + + if (rdt_alloc_capable) + return true; + + if (!boot_cpu_has(X86_FEATURE_RDT_A)) + return false; + + if (rdt_cpu_has(X86_FEATURE_CAT_L3)) { + rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]); + if (rdt_cpu_has(X86_FEATURE_CDP_L3)) + rdt_get_cdp_l3_config(); + ret = true; + } + if (rdt_cpu_has(X86_FEATURE_CAT_L2)) { + /* CPUID 0x10.2 fields are same format at 0x10.1 */ + rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]); + if (rdt_cpu_has(X86_FEATURE_CDP_L2)) + rdt_get_cdp_l2_config(); + ret = true; + } + + if (get_mem_config()) + ret = true; + + return ret; +} + +static __init bool get_rdt_mon_resources(void) +{ + if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) + rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID); + + if (!rdt_mon_features) + return false; + + return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]); +} + +static __init void __check_quirks_intel(void) +{ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_HASWELL_X: + if (!rdt_options[RDT_FLAG_L3_CAT].force_off) + cache_alloc_hsw_probe(); + break; + case INTEL_FAM6_SKYLAKE_X: + if (boot_cpu_data.x86_stepping <= 4) + set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); + else + set_rdt_options("!l3cat"); + } +} + +static __init void check_quirks(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + __check_quirks_intel(); +} + +static __init bool get_rdt_resources(void) +{ + rdt_alloc_capable = get_rdt_alloc_resources(); + rdt_mon_capable = get_rdt_mon_resources(); + + return (rdt_mon_capable || rdt_alloc_capable); +} + +static __init void rdt_init_res_defs_intel(void) +{ + struct rdt_resource *r; + + for_each_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_L3 || + r->rid == RDT_RESOURCE_L3DATA || + r->rid == RDT_RESOURCE_L3CODE || + r->rid == RDT_RESOURCE_L2 || + r->rid == RDT_RESOURCE_L2DATA || + r->rid == RDT_RESOURCE_L2CODE) { + r->cache.arch_has_sparse_bitmaps = false; + r->cache.arch_has_empty_bitmaps = false; + r->cache.arch_has_per_cpu_cfg = false; + } else if (r->rid == RDT_RESOURCE_MBA) { + r->msr_base = MSR_IA32_MBA_THRTL_BASE; + r->msr_update = mba_wrmsr_intel; + } + } +} + +static __init void rdt_init_res_defs_amd(void) +{ + struct rdt_resource *r; + + for_each_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_L3 || + r->rid == RDT_RESOURCE_L3DATA || + r->rid == RDT_RESOURCE_L3CODE || + r->rid == RDT_RESOURCE_L2 || + r->rid == RDT_RESOURCE_L2DATA || + r->rid == RDT_RESOURCE_L2CODE) { + r->cache.arch_has_sparse_bitmaps = true; + r->cache.arch_has_empty_bitmaps = true; + r->cache.arch_has_per_cpu_cfg = true; + } else if (r->rid == RDT_RESOURCE_MBA) { + r->msr_base = MSR_IA32_MBA_BW_BASE; + r->msr_update = mba_wrmsr_amd; + } + } +} + +static __init void rdt_init_res_defs(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + rdt_init_res_defs_intel(); + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + rdt_init_res_defs_amd(); +} + +static enum cpuhp_state rdt_online; + +/* Runs once on the BSP during boot. */ +void resctrl_cpu_detect(struct cpuinfo_x86 *c) +{ + if (!cpu_has(c, X86_FEATURE_CQM_LLC)) { + c->x86_cache_max_rmid = -1; + c->x86_cache_occ_scale = -1; + c->x86_cache_mbm_width_offset = -1; + return; + } + + /* will be overridden if occupancy monitoring exists */ + c->x86_cache_max_rmid = cpuid_ebx(0xf); + + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) || + cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) || + cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) { + u32 eax, ebx, ecx, edx; + + /* QoS sub-leaf, EAX=0Fh, ECX=1 */ + cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx); + + c->x86_cache_max_rmid = ecx; + c->x86_cache_occ_scale = ebx; + c->x86_cache_mbm_width_offset = eax & 0xff; + + if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; + } +} + +static int __init resctrl_late_init(void) +{ + struct rdt_resource *r; + int state, ret; + + /* + * Initialize functions(or definitions) that are different + * between vendors here. + */ + rdt_init_res_defs(); + + check_quirks(); + + if (!get_rdt_resources()) + return -ENODEV; + + rdt_init_padding(); + + state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "x86/resctrl/cat:online:", + resctrl_online_cpu, resctrl_offline_cpu); + if (state < 0) + return state; + + ret = rdtgroup_init(); + if (ret) { + cpuhp_remove_state(state); + return ret; + } + rdt_online = state; + + for_each_alloc_capable_rdt_resource(r) + pr_info("%s allocation detected\n", r->name); + + for_each_mon_capable_rdt_resource(r) + pr_info("%s monitoring detected\n", r->name); + + return 0; +} + +late_initcall(resctrl_late_init); + +static void __exit resctrl_exit(void) +{ + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); +} + +__exitcall(resctrl_exit); diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c new file mode 100644 index 000000000..c877642e8 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -0,0 +1,490 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Cache Allocation code. + * + * Copyright (C) 2016 Intel Corporation + * + * Authors: + * Fenghua Yu <fenghua.yu@intel.com> + * Tony Luck <tony.luck@intel.com> + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cpu.h> +#include <linux/kernfs.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include "internal.h" + +/* + * Check whether MBA bandwidth percentage value is correct. The value is + * checked against the minimum and max bandwidth values specified by the + * hardware. The allocated bandwidth percentage is rounded to the next + * control step available on the hardware. + */ +static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) +{ + unsigned long bw; + int ret; + + /* + * Only linear delay values is supported for current Intel SKUs. + */ + if (!r->membw.delay_linear && r->membw.arch_needs_linear) { + rdt_last_cmd_puts("No support for non-linear MB domains\n"); + return false; + } + + ret = kstrtoul(buf, 10, &bw); + if (ret) { + rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); + return false; + } + + if ((bw < r->membw.min_bw || bw > r->default_ctrl) && + !is_mba_sc(r)) { + rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, + r->membw.min_bw, r->default_ctrl); + return false; + } + + *data = roundup(bw, (unsigned long)r->membw.bw_gran); + return true; +} + +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) +{ + unsigned long bw_val; + + if (d->have_new_ctrl) { + rdt_last_cmd_printf("Duplicate domain %d\n", d->id); + return -EINVAL; + } + + if (!bw_validate(data->buf, &bw_val, r)) + return -EINVAL; + d->new_ctrl = bw_val; + d->have_new_ctrl = true; + + return 0; +} + +/* + * Check whether a cache bit mask is valid. + * For Intel the SDM says: + * Please note that all (and only) contiguous '1' combinations + * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). + * Additionally Haswell requires at least two bits set. + * AMD allows non-contiguous bitmasks. + */ +static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) +{ + unsigned long first_bit, zero_bit, val; + unsigned int cbm_len = r->cache.cbm_len; + int ret; + + ret = kstrtoul(buf, 16, &val); + if (ret) { + rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf); + return false; + } + + if ((!r->cache.arch_has_empty_bitmaps && val == 0) || + val > r->default_ctrl) { + rdt_last_cmd_puts("Mask out of range\n"); + return false; + } + + first_bit = find_first_bit(&val, cbm_len); + zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); + + /* Are non-contiguous bitmaps allowed? */ + if (!r->cache.arch_has_sparse_bitmaps && + (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) { + rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val); + return false; + } + + if ((zero_bit - first_bit) < r->cache.min_cbm_bits) { + rdt_last_cmd_printf("Need at least %d bits in the mask\n", + r->cache.min_cbm_bits); + return false; + } + + *data = val; + return true; +} + +/* + * Read one cache bit mask (hex). Check that it is valid for the current + * resource type. + */ +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) +{ + struct rdtgroup *rdtgrp = data->rdtgrp; + u32 cbm_val; + + if (d->have_new_ctrl) { + rdt_last_cmd_printf("Duplicate domain %d\n", d->id); + return -EINVAL; + } + + /* + * Cannot set up more than one pseudo-locked region in a cache + * hierarchy. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + rdtgroup_pseudo_locked_in_hierarchy(d)) { + rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n"); + return -EINVAL; + } + + if (!cbm_validate(data->buf, &cbm_val, r)) + return -EINVAL; + + if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_SHAREABLE) && + rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) { + rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n"); + return -EINVAL; + } + + /* + * The CBM may not overlap with the CBM of another closid if + * either is exclusive. + */ + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) { + rdt_last_cmd_puts("Overlaps with exclusive group\n"); + return -EINVAL; + } + + if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) { + if (rdtgrp->mode == RDT_MODE_EXCLUSIVE || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + rdt_last_cmd_puts("Overlaps with other group\n"); + return -EINVAL; + } + } + + d->new_ctrl = cbm_val; + d->have_new_ctrl = true; + + return 0; +} + +/* + * For each domain in this resource we expect to find a series of: + * id=mask + * separated by ";". The "id" is in decimal, and must match one of + * the "id"s for this resource. + */ +static int parse_line(char *line, struct rdt_resource *r, + struct rdtgroup *rdtgrp) +{ + struct rdt_parse_data data; + char *dom = NULL, *id; + struct rdt_domain *d; + unsigned long dom_id; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + r->rid == RDT_RESOURCE_MBA) { + rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); + return -EINVAL; + } + +next: + if (!line || line[0] == '\0') + return 0; + dom = strsep(&line, ";"); + id = strsep(&dom, "="); + if (!dom || kstrtoul(id, 10, &dom_id)) { + rdt_last_cmd_puts("Missing '=' or non-numeric domain\n"); + return -EINVAL; + } + dom = strim(dom); + list_for_each_entry(d, &r->domains, list) { + if (d->id == dom_id) { + data.buf = dom; + data.rdtgrp = rdtgrp; + if (r->parse_ctrlval(&data, r, d)) + return -EINVAL; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * In pseudo-locking setup mode and just + * parsed a valid CBM that should be + * pseudo-locked. Only one locked region per + * resource group and domain so just do + * the required initialization for single + * region and return. + */ + rdtgrp->plr->r = r; + rdtgrp->plr->d = d; + rdtgrp->plr->cbm = d->new_ctrl; + d->plr = rdtgrp->plr; + return 0; + } + goto next; + } + } + return -EINVAL; +} + +int update_domains(struct rdt_resource *r, int closid) +{ + struct msr_param msr_param; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + bool mba_sc; + u32 *dc; + int cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + msr_param.low = closid; + msr_param.high = msr_param.low + 1; + msr_param.res = r; + + mba_sc = is_mba_sc(r); + list_for_each_entry(d, &r->domains, list) { + dc = !mba_sc ? d->ctrl_val : d->mbps_val; + if (d->have_new_ctrl && d->new_ctrl != dc[closid]) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + dc[closid] = d->new_ctrl; + } + } + + /* + * Avoid writing the control msr with control values when + * MBA software controller is enabled + */ + if (cpumask_empty(cpu_mask) || mba_sc) + goto done; + cpu = get_cpu(); + /* Update resource control msr on this CPU if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_ctrl_update(&msr_param); + /* Update resource control msr on other CPUs. */ + smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1); + put_cpu(); + +done: + free_cpumask_var(cpu_mask); + + return 0; +} + +static int rdtgroup_parse_resource(char *resname, char *tok, + struct rdtgroup *rdtgrp) +{ + struct rdt_resource *r; + + for_each_alloc_enabled_rdt_resource(r) { + if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid) + return parse_line(tok, r, rdtgrp); + } + rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname); + return -EINVAL; +} + +ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + struct rdt_domain *dom; + struct rdt_resource *r; + char *tok, *resname; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + cpus_read_lock(); + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + cpus_read_unlock(); + return -ENOENT; + } + rdt_last_cmd_clear(); + + /* + * No changes to pseudo-locked region allowed. It has to be removed + * and re-created instead. + */ + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = -EINVAL; + rdt_last_cmd_puts("Resource group is pseudo-locked\n"); + goto out; + } + + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(dom, &r->domains, list) + dom->have_new_ctrl = false; + } + + while ((tok = strsep(&buf, "\n")) != NULL) { + resname = strim(strsep(&tok, ":")); + if (!tok) { + rdt_last_cmd_puts("Missing ':'\n"); + ret = -EINVAL; + goto out; + } + if (tok[0] == '\0') { + rdt_last_cmd_printf("Missing '%s' value\n", resname); + ret = -EINVAL; + goto out; + } + ret = rdtgroup_parse_resource(resname, tok, rdtgrp); + if (ret) + goto out; + } + + for_each_alloc_enabled_rdt_resource(r) { + ret = update_domains(r, rdtgrp->closid); + if (ret) + goto out; + } + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * If pseudo-locking fails we keep the resource group in + * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service + * active and updated for just the domain the pseudo-locked + * region was requested for. + */ + ret = rdtgroup_pseudo_lock_create(rdtgrp); + } + +out: + rdtgroup_kn_unlock(of->kn); + cpus_read_unlock(); + return ret ?: nbytes; +} + +static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) +{ + struct rdt_domain *dom; + bool sep = false; + u32 ctrl_val; + + seq_printf(s, "%*s:", max_name_width, r->name); + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_puts(s, ";"); + + ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] : + dom->mbps_val[closid]); + seq_printf(s, r->format_str, dom->id, max_data_width, + ctrl_val); + sep = true; + } + seq_puts(s, "\n"); +} + +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + int ret = 0; + u32 closid; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + for_each_alloc_enabled_rdt_resource(r) + seq_printf(s, "%s:uninitialized\n", r->name); + } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%s:%d=%x\n", + rdtgrp->plr->r->name, + rdtgrp->plr->d->id, + rdtgrp->plr->cbm); + } + } else { + closid = rdtgrp->closid; + for_each_alloc_enabled_rdt_resource(r) { + if (closid < r->num_closid) + show_doms(s, r, closid); + } + } + } else { + ret = -ENOENT; + } + rdtgroup_kn_unlock(of->kn); + return ret; +} + +void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, + struct rdt_domain *d, struct rdtgroup *rdtgrp, + int evtid, int first) +{ + /* + * setup the parameters to send to the IPI to read the data. + */ + rr->rgrp = rdtgrp; + rr->evtid = evtid; + rr->r = r; + rr->d = d; + rr->val = 0; + rr->first = first; + + smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); +} + +int rdtgroup_mondata_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + u32 resid, evtid, domid; + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + union mon_data_bits md; + struct rdt_domain *d; + struct rmid_read rr; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } + + md.priv = of->kn->priv; + resid = md.u.rid; + domid = md.u.domid; + evtid = md.u.evtid; + + r = &rdt_resources_all[resid]; + d = rdt_find_domain(r, domid, NULL); + if (IS_ERR_OR_NULL(d)) { + ret = -ENOENT; + goto out; + } + + mon_event_read(&rr, r, d, rdtgrp, evtid, false); + + if (rr.val & RMID_VAL_ERROR) + seq_puts(m, "Error\n"); + else if (rr.val & RMID_VAL_UNAVAIL) + seq_puts(m, "Unavailable\n"); + else + seq_printf(m, "%llu\n", rr.val * r->mon_scale); + +out: + rdtgroup_kn_unlock(of->kn); + return ret; +} diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h new file mode 100644 index 000000000..f65d3c0db --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -0,0 +1,632 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_RESCTRL_INTERNAL_H +#define _ASM_X86_RESCTRL_INTERNAL_H + +#include <linux/sched.h> +#include <linux/kernfs.h> +#include <linux/fs_context.h> +#include <linux/jump_label.h> + +#define MSR_IA32_L3_QOS_CFG 0xc81 +#define MSR_IA32_L2_QOS_CFG 0xc82 +#define MSR_IA32_L3_CBM_BASE 0xc90 +#define MSR_IA32_L2_CBM_BASE 0xd10 +#define MSR_IA32_MBA_THRTL_BASE 0xd50 +#define MSR_IA32_MBA_BW_BASE 0xc0000200 + +#define MSR_IA32_QM_CTR 0x0c8e +#define MSR_IA32_QM_EVTSEL 0x0c8d + +#define L3_QOS_CDP_ENABLE 0x01ULL + +#define L2_QOS_CDP_ENABLE 0x01ULL + +/* + * Event IDs are used to program IA32_QM_EVTSEL before reading event + * counter from IA32_QM_CTR + */ +#define QOS_L3_OCCUP_EVENT_ID 0x01 +#define QOS_L3_MBM_TOTAL_EVENT_ID 0x02 +#define QOS_L3_MBM_LOCAL_EVENT_ID 0x03 + +#define CQM_LIMBOCHECK_INTERVAL 1000 + +#define MBM_CNTR_WIDTH_BASE 24 +#define MBM_OVERFLOW_INTERVAL 1000 +#define MAX_MBA_BW 100u +#define MBA_IS_LINEAR 0x4 +#define MBA_MAX_MBPS U32_MAX +#define MAX_MBA_BW_AMD 0x800 +#define MBM_CNTR_WIDTH_OFFSET_AMD 20 + +#define RMID_VAL_ERROR BIT_ULL(63) +#define RMID_VAL_UNAVAIL BIT_ULL(62) +/* + * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for + * data to be returned. The counter width is discovered from the hardware + * as an offset from MBM_CNTR_WIDTH_BASE. + */ +#define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE) + + +struct rdt_fs_context { + struct kernfs_fs_context kfc; + bool enable_cdpl2; + bool enable_cdpl3; + bool enable_mba_mbps; +}; + +static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) +{ + struct kernfs_fs_context *kfc = fc->fs_private; + + return container_of(kfc, struct rdt_fs_context, kfc); +} + +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); + +/** + * struct mon_evt - Entry in the event list of a resource + * @evtid: event id + * @name: name of the event + */ +struct mon_evt { + u32 evtid; + char *name; + struct list_head list; +}; + +/** + * struct mon_data_bits - Monitoring details for each event file + * @rid: Resource id associated with the event file. + * @evtid: Event id associated with the event file + * @domid: The domain to which the event file belongs + */ +union mon_data_bits { + void *priv; + struct { + unsigned int rid : 10; + unsigned int evtid : 8; + unsigned int domid : 14; + } u; +}; + +struct rmid_read { + struct rdtgroup *rgrp; + struct rdt_resource *r; + struct rdt_domain *d; + int evtid; + bool first; + u64 val; +}; + +extern unsigned int resctrl_cqm_threshold; +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; +extern unsigned int rdt_mon_features; + +enum rdt_group_type { + RDTCTRL_GROUP = 0, + RDTMON_GROUP, + RDT_NUM_GROUP, +}; + +/** + * enum rdtgrp_mode - Mode of a RDT resource group + * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations + * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed + * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking + * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations + * allowed AND the allocations are Cache Pseudo-Locked + * + * The mode of a resource group enables control over the allowed overlap + * between allocations associated with different resource groups (classes + * of service). User is able to modify the mode of a resource group by + * writing to the "mode" resctrl file associated with the resource group. + * + * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by + * writing the appropriate text to the "mode" file. A resource group enters + * "pseudo-locked" mode after the schemata is written while the resource + * group is in "pseudo-locksetup" mode. + */ +enum rdtgrp_mode { + RDT_MODE_SHAREABLE = 0, + RDT_MODE_EXCLUSIVE, + RDT_MODE_PSEUDO_LOCKSETUP, + RDT_MODE_PSEUDO_LOCKED, + + /* Must be last */ + RDT_NUM_MODES, +}; + +/** + * struct mongroup - store mon group's data in resctrl fs. + * @mon_data_kn kernlfs node for the mon_data directory + * @parent: parent rdtgrp + * @crdtgrp_list: child rdtgroup node list + * @rmid: rmid for this rdtgroup + */ +struct mongroup { + struct kernfs_node *mon_data_kn; + struct rdtgroup *parent; + struct list_head crdtgrp_list; + u32 rmid; +}; + +/** + * struct pseudo_lock_region - pseudo-lock region information + * @r: RDT resource to which this pseudo-locked region + * belongs + * @d: RDT domain to which this pseudo-locked region + * belongs + * @cbm: bitmask of the pseudo-locked region + * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread + * completion + * @thread_done: variable used by waitqueue to test if pseudo-locking + * thread completed + * @cpu: core associated with the cache on which the setup code + * will be run + * @line_size: size of the cache lines + * @size: size of pseudo-locked region in bytes + * @kmem: the kernel memory associated with pseudo-locked region + * @minor: minor number of character device associated with this + * region + * @debugfs_dir: pointer to this region's directory in the debugfs + * filesystem + * @pm_reqs: Power management QoS requests related to this region + */ +struct pseudo_lock_region { + struct rdt_resource *r; + struct rdt_domain *d; + u32 cbm; + wait_queue_head_t lock_thread_wq; + int thread_done; + int cpu; + unsigned int line_size; + unsigned int size; + void *kmem; + unsigned int minor; + struct dentry *debugfs_dir; + struct list_head pm_reqs; +}; + +/** + * struct rdtgroup - store rdtgroup's data in resctrl file system. + * @kn: kernfs node + * @rdtgroup_list: linked list for all rdtgroups + * @closid: closid for this rdtgroup + * @cpu_mask: CPUs assigned to this rdtgroup + * @flags: status bits + * @waitcount: how many cpus expect to find this + * group when they acquire rdtgroup_mutex + * @type: indicates type of this rdtgroup - either + * monitor only or ctrl_mon group + * @mon: mongroup related data + * @mode: mode of resource group + * @plr: pseudo-locked region + */ +struct rdtgroup { + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; + enum rdtgrp_mode mode; + struct pseudo_lock_region *plr; +}; + +/* rdtgroup.flags */ +#define RDT_DELETED 1 + +/* rftype.flags */ +#define RFTYPE_FLAGS_CPUS_LIST 1 + +/* + * Define the file type flags for base and info directories. + */ +#define RFTYPE_INFO BIT(0) +#define RFTYPE_BASE BIT(1) +#define RF_CTRLSHIFT 4 +#define RF_MONSHIFT 5 +#define RF_TOPSHIFT 6 +#define RFTYPE_CTRL BIT(RF_CTRLSHIFT) +#define RFTYPE_MON BIT(RF_MONSHIFT) +#define RFTYPE_TOP BIT(RF_TOPSHIFT) +#define RFTYPE_RES_CACHE BIT(8) +#define RFTYPE_RES_MB BIT(9) +#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) +#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON) +#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) +#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) + +/* List of all resource groups */ +extern struct list_head rdt_all_groups; + +extern int max_name_width, max_data_width; + +int __init rdtgroup_init(void); +void __exit rdtgroup_exit(void); + +/** + * struct rftype - describe each file in the resctrl file system + * @name: File name + * @mode: Access mode + * @kf_ops: File operations + * @flags: File specific RFTYPE_FLAGS_* flags + * @fflags: File specific RF_* or RFTYPE_* flags + * @seq_show: Show content of the file + * @write: Write to the file + */ +struct rftype { + char *name; + umode_t mode; + struct kernfs_ops *kf_ops; + unsigned long flags; + unsigned long fflags; + + int (*seq_show)(struct kernfs_open_file *of, + struct seq_file *sf, void *v); + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +}; + +/** + * struct mbm_state - status for each MBM counter in each domain + * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) + * @prev_msr Value of IA32_QM_CTR for this RMID last time we read it + * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting + * @prev_bw The most recent bandwidth in MBps + * @delta_bw Difference between the current and previous bandwidth + * @delta_comp Indicates whether to compute the delta_bw + */ +struct mbm_state { + u64 chunks; + u64 prev_msr; + u64 prev_bw_msr; + u32 prev_bw; + u32 delta_bw; + bool delta_comp; +}; + +/** + * struct rdt_domain - group of cpus sharing an RDT resource + * @list: all instances of this resource + * @id: unique id for this instance + * @cpu_mask: which cpus share this resource + * @rmid_busy_llc: + * bitmap of which limbo RMIDs are above threshold + * @mbm_total: saved state for MBM total bandwidth + * @mbm_local: saved state for MBM local bandwidth + * @mbm_over: worker to periodically read MBM h/w counters + * @cqm_limbo: worker to periodically read CQM h/w counters + * @mbm_work_cpu: + * worker cpu for MBM h/w counters + * @cqm_work_cpu: + * worker cpu for CQM h/w counters + * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) + * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps + * @new_ctrl: new ctrl value to be loaded + * @have_new_ctrl: did user provide new_ctrl for this domain + * @plr: pseudo-locked region (if any) associated with domain + */ +struct rdt_domain { + struct list_head list; + int id; + struct cpumask cpu_mask; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + u32 *ctrl_val; + u32 *mbps_val; + u32 new_ctrl; + bool have_new_ctrl; + struct pseudo_lock_region *plr; +}; + +/** + * struct msr_param - set a range of MSRs from a domain + * @res: The resource to use + * @low: Beginning index from base MSR + * @high: End index + */ +struct msr_param { + struct rdt_resource *res; + int low; + int high; +}; + +/** + * struct rdt_cache - Cache allocation related data + * @cbm_len: Length of the cache bit mask + * @min_cbm_bits: Minimum number of consecutive bits to be set + * @cbm_idx_mult: Multiplier of CBM index + * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: + * closid * cbm_idx_multi + cbm_idx_offset + * in a cache bit mask + * @shareable_bits: Bitmask of shareable resource with other + * executing entities + * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. + * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. + * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache + * level has CPU scope. + */ +struct rdt_cache { + unsigned int cbm_len; + unsigned int min_cbm_bits; + unsigned int cbm_idx_mult; + unsigned int cbm_idx_offset; + unsigned int shareable_bits; + bool arch_has_sparse_bitmaps; + bool arch_has_empty_bitmaps; + bool arch_has_per_cpu_cfg; +}; + +/** + * enum membw_throttle_mode - System's memory bandwidth throttling mode + * @THREAD_THROTTLE_UNDEFINED: Not relevant to the system + * @THREAD_THROTTLE_MAX: Memory bandwidth is throttled at the core + * always using smallest bandwidth percentage + * assigned to threads, aka "max throttling" + * @THREAD_THROTTLE_PER_THREAD: Memory bandwidth is throttled at the thread + */ +enum membw_throttle_mode { + THREAD_THROTTLE_UNDEFINED = 0, + THREAD_THROTTLE_MAX, + THREAD_THROTTLE_PER_THREAD, +}; + +/** + * struct rdt_membw - Memory bandwidth allocation related data + * @min_bw: Minimum memory bandwidth percentage user can request + * @bw_gran: Granularity at which the memory bandwidth is allocated + * @delay_linear: True if memory B/W delay is in linear scale + * @arch_needs_linear: True if we can't configure non-linear resources + * @throttle_mode: Bandwidth throttling mode when threads request + * different memory bandwidths + * @mba_sc: True if MBA software controller(mba_sc) is enabled + * @mb_map: Mapping of memory B/W percentage to memory B/W delay + */ +struct rdt_membw { + u32 min_bw; + u32 bw_gran; + u32 delay_linear; + bool arch_needs_linear; + enum membw_throttle_mode throttle_mode; + bool mba_sc; + u32 *mb_map; +}; + +static inline bool is_llc_occupancy_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID)); +} + +static inline bool is_mbm_total_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID)); +} + +static inline bool is_mbm_local_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID)); +} + +static inline bool is_mbm_enabled(void) +{ + return (is_mbm_total_enabled() || is_mbm_local_enabled()); +} + +static inline bool is_mbm_event(int e) +{ + return (e >= QOS_L3_MBM_TOTAL_EVENT_ID && + e <= QOS_L3_MBM_LOCAL_EVENT_ID); +} + +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + +/** + * struct rdt_resource - attributes of an RDT resource + * @rid: The index of the resource + * @alloc_enabled: Is allocation enabled on this machine + * @mon_enabled: Is monitoring enabled for this feature + * @alloc_capable: Is allocation available on this machine + * @mon_capable: Is monitor feature available on this machine + * @name: Name to use in "schemata" file + * @num_closid: Number of CLOSIDs available + * @cache_level: Which cache level defines scope of this resource + * @default_ctrl: Specifies default cache cbm or memory B/W percent. + * @msr_base: Base MSR address for CBMs + * @msr_update: Function pointer to update QOS MSRs + * @data_width: Character width of data when displaying + * @domains: All domains for this resource + * @cache: Cache allocation related data + * @format_str: Per resource format string to show domain value + * @parse_ctrlval: Per resource function pointer to parse control values + * @evt_list: List of monitoring events + * @num_rmid: Number of RMIDs available + * @mon_scale: cqm counter * mon_scale = occupancy in bytes + * @fflags: flags to choose base and info files + */ +struct rdt_resource { + int rid; + bool alloc_enabled; + bool mon_enabled; + bool alloc_capable; + bool mon_capable; + char *name; + int num_closid; + int cache_level; + u32 default_ctrl; + unsigned int msr_base; + void (*msr_update) (struct rdt_domain *d, struct msr_param *m, + struct rdt_resource *r); + int data_width; + struct list_head domains; + struct rdt_cache cache; + struct rdt_membw membw; + const char *format_str; + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); + struct list_head evt_list; + int num_rmid; + unsigned int mon_scale; + unsigned int mbm_width; + unsigned long fflags; +}; + +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); + +extern struct mutex rdtgroup_mutex; + +extern struct rdt_resource rdt_resources_all[]; +extern struct rdtgroup rdtgroup_default; +DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); + +extern struct dentry *debugfs_resctrl; + +enum { + RDT_RESOURCE_L3, + RDT_RESOURCE_L3DATA, + RDT_RESOURCE_L3CODE, + RDT_RESOURCE_L2, + RDT_RESOURCE_L2DATA, + RDT_RESOURCE_L2CODE, + RDT_RESOURCE_MBA, + + /* Must be the last */ + RDT_NUM_RESOURCES, +}; + +#define for_each_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) + +#define for_each_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_capable || r->mon_capable) + +#define for_each_alloc_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_capable) + +#define for_each_mon_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_capable) + +#define for_each_alloc_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_enabled) + +#define for_each_mon_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_enabled) + +/* CPUID.(EAX=10H, ECX=ResID=1).EAX */ +union cpuid_0x10_1_eax { + struct { + unsigned int cbm_len:5; + } split; + unsigned int full; +}; + +/* CPUID.(EAX=10H, ECX=ResID=3).EAX */ +union cpuid_0x10_3_eax { + struct { + unsigned int max_delay:12; + } split; + unsigned int full; +}; + +/* CPUID.(EAX=10H, ECX=ResID).EDX */ +union cpuid_0x10_x_edx { + struct { + unsigned int cos_max:16; + } split; + unsigned int full; +}; + +void rdt_last_cmd_clear(void); +void rdt_last_cmd_puts(const char *s); +void rdt_last_cmd_printf(const char *fmt, ...); + +void rdt_ctrl_update(void *arg); +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); +void rdtgroup_kn_unlock(struct kernfs_node *kn); +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name); +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask); +struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos); +ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive); +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm); +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); +int rdtgroup_tasks_assigned(struct rdtgroup *r); +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm); +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); +int rdt_pseudo_lock_init(void); +void rdt_pseudo_lock_release(void); +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int update_domains(struct rdt_resource *r, int closid); +int closids_supported(void); +void closid_free(int closid); +int alloc_rmid(void); +void free_rmid(u32 rmid); +int rdt_get_mon_l3_config(struct rdt_resource *r); +void mon_event_count(void *info); +int rdtgroup_mondata_show(struct seq_file *m, void *arg); +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + unsigned int dom_id); +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d); +void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, + struct rdt_domain *d, struct rdtgroup *rdtgrp, + int evtid, int first); +void mbm_setup_overflow_handler(struct rdt_domain *dom, + unsigned long delay_ms); +void mbm_handle_overflow(struct work_struct *work); +bool is_mba_sc(struct rdt_resource *r); +void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm); +u32 delay_bw_map(unsigned long bw, struct rdt_resource *r); +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); +void cqm_handle_limbo(struct work_struct *work); +bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); +void __check_limbo(struct rdt_domain *d, bool force_free); +void rdt_domain_reconfigure_cdp(struct rdt_resource *r); +void __init thread_throttle_mode_init(void); + +#endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c new file mode 100644 index 000000000..576f16a50 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -0,0 +1,649 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Monitoring code + * + * Copyright (C) 2017 Intel Corporation + * + * Author: + * Vikas Shivappa <vikas.shivappa@intel.com> + * + * This replaces the cqm.c based on perf but we reuse a lot of + * code and datastructures originally from Peter Zijlstra and Matt Fleming. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <asm/cpu_device_id.h> +#include "internal.h" + +struct rmid_entry { + u32 rmid; + int busy; + struct list_head list; +}; + +/** + * @rmid_free_lru A least recently used list of free RMIDs + * These RMIDs are guaranteed to have an occupancy less than the + * threshold occupancy + */ +static LIST_HEAD(rmid_free_lru); + +/** + * @rmid_limbo_count count of currently unused but (potentially) + * dirty RMIDs. + * This counts RMIDs that no one is currently using but that + * may have a occupancy value > intel_cqm_threshold. User can change + * the threshold occupancy value. + */ +static unsigned int rmid_limbo_count; + +/** + * @rmid_entry - The entry in the limbo and free lists. + */ +static struct rmid_entry *rmid_ptrs; + +/* + * Global boolean for rdt_monitor which is true if any + * resource monitoring is enabled. + */ +bool rdt_mon_capable; + +/* + * Global to indicate which monitoring events are enabled. + */ +unsigned int rdt_mon_features; + +/* + * This is the threshold cache occupancy at which we will consider an + * RMID available for re-allocation. + */ +unsigned int resctrl_cqm_threshold; + +static inline struct rmid_entry *__rmid_entry(u32 rmid) +{ + struct rmid_entry *entry; + + entry = &rmid_ptrs[rmid]; + WARN_ON(entry->rmid != rmid); + + return entry; +} + +static u64 __rmid_read(u32 rmid, u32 eventid) +{ + u64 val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, val); + + return val; +} + +static bool rmid_dirty(struct rmid_entry *entry) +{ + u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + + return val >= resctrl_cqm_threshold; +} + +/* + * Check the RMIDs that are marked as busy for this domain. If the + * reported LLC occupancy is below the threshold clear the busy bit and + * decrement the count. If the busy count gets to zero on an RMID, we + * free the RMID + */ +void __check_limbo(struct rdt_domain *d, bool force_free) +{ + struct rmid_entry *entry; + struct rdt_resource *r; + u32 crmid = 1, nrmid; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + /* + * Skip RMID 0 and start from RMID 1 and check all the RMIDs that + * are marked as busy for occupancy < threshold. If the occupancy + * is less than the threshold decrement the busy counter of the + * RMID and move it to the free list when the counter reaches 0. + */ + for (;;) { + nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid); + if (nrmid >= r->num_rmid) + break; + + entry = __rmid_entry(nrmid); + if (force_free || !rmid_dirty(entry)) { + clear_bit(entry->rmid, d->rmid_busy_llc); + if (!--entry->busy) { + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + } + } + crmid = nrmid + 1; + } +} + +bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) +{ + return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid; +} + +/* + * As of now the RMIDs allocation is global. + * However we keep track of which packages the RMIDs + * are used to optimize the limbo list management. + */ +int alloc_rmid(void) +{ + struct rmid_entry *entry; + + lockdep_assert_held(&rdtgroup_mutex); + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? -EBUSY : -ENOSPC; + + entry = list_first_entry(&rmid_free_lru, + struct rmid_entry, list); + list_del(&entry->list); + + return entry->rmid; +} + +static void add_rmid_to_limbo(struct rmid_entry *entry) +{ + struct rdt_resource *r; + struct rdt_domain *d; + int cpu; + u64 val; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + entry->busy = 0; + cpu = get_cpu(); + list_for_each_entry(d, &r->domains, list) { + if (cpumask_test_cpu(cpu, &d->cpu_mask)) { + val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + if (val <= resctrl_cqm_threshold) + continue; + } + + /* + * For the first limbo RMID in the domain, + * setup up the limbo worker. + */ + if (!has_busy_rmid(r, d)) + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); + set_bit(entry->rmid, d->rmid_busy_llc); + entry->busy++; + } + put_cpu(); + + if (entry->busy) + rmid_limbo_count++; + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +void free_rmid(u32 rmid) +{ + struct rmid_entry *entry; + + if (!rmid) + return; + + lockdep_assert_held(&rdtgroup_mutex); + + entry = __rmid_entry(rmid); + + if (is_llc_occupancy_enabled()) + add_rmid_to_limbo(entry); + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) +{ + u64 shift = 64 - width, chunks; + + chunks = (cur_msr << shift) - (prev_msr << shift); + return chunks >>= shift; +} + +static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) +{ + struct mbm_state *m; + u64 chunks, tval; + + tval = __rmid_read(rmid, rr->evtid); + if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { + return tval; + } + switch (rr->evtid) { + case QOS_L3_OCCUP_EVENT_ID: + rr->val += tval; + return 0; + case QOS_L3_MBM_TOTAL_EVENT_ID: + m = &rr->d->mbm_total[rmid]; + break; + case QOS_L3_MBM_LOCAL_EVENT_ID: + m = &rr->d->mbm_local[rmid]; + break; + default: + /* + * Code would never reach here because an invalid + * event id would fail the __rmid_read. + */ + return RMID_VAL_ERROR; + } + + if (rr->first) { + memset(m, 0, sizeof(struct mbm_state)); + m->prev_bw_msr = m->prev_msr = tval; + return 0; + } + + chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width); + m->chunks += chunks; + m->prev_msr = tval; + + rr->val += m->chunks; + return 0; +} + +/* + * Supporting function to calculate the memory bandwidth + * and delta bandwidth in MBps. + */ +static void mbm_bw_count(u32 rmid, struct rmid_read *rr) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + struct mbm_state *m = &rr->d->mbm_local[rmid]; + u64 tval, cur_bw, chunks; + + tval = __rmid_read(rmid, rr->evtid); + if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) + return; + + chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); + cur_bw = (chunks * r->mon_scale) >> 20; + + if (m->delta_comp) + m->delta_bw = abs(cur_bw - m->prev_bw); + m->delta_comp = false; + m->prev_bw = cur_bw; + m->prev_bw_msr = tval; +} + +/* + * This is called via IPI to read the CQM/MBM counters + * on a domain. + */ +void mon_event_count(void *info) +{ + struct rdtgroup *rdtgrp, *entry; + struct rmid_read *rr = info; + struct list_head *head; + u64 ret_val; + + rdtgrp = rr->rgrp; + + ret_val = __mon_event_count(rdtgrp->mon.rmid, rr); + + /* + * For Ctrl groups read data from child monitor groups and + * add them together. Count events which are read successfully. + * Discard the rmid_read's reporting errors. + */ + head = &rdtgrp->mon.crdtgrp_list; + + if (rdtgrp->type == RDTCTRL_GROUP) { + list_for_each_entry(entry, head, mon.crdtgrp_list) { + if (__mon_event_count(entry->mon.rmid, rr) == 0) + ret_val = 0; + } + } + + /* Report error if none of rmid_reads are successful */ + if (ret_val) + rr->val = ret_val; +} + +/* + * Feedback loop for MBA software controller (mba_sc) + * + * mba_sc is a feedback loop where we periodically read MBM counters and + * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so + * that: + * + * current bandwdith(cur_bw) < user specified bandwidth(user_bw) + * + * This uses the MBM counters to measure the bandwidth and MBA throttle + * MSRs to control the bandwidth for a particular rdtgrp. It builds on the + * fact that resctrl rdtgroups have both monitoring and control. + * + * The frequency of the checks is 1s and we just tag along the MBM overflow + * timer. Having 1s interval makes the calculation of bandwidth simpler. + * + * Although MBA's goal is to restrict the bandwidth to a maximum, there may + * be a need to increase the bandwidth to avoid uncecessarily restricting + * the L2 <-> L3 traffic. + * + * Since MBA controls the L2 external bandwidth where as MBM measures the + * L3 external bandwidth the following sequence could lead to such a + * situation. + * + * Consider an rdtgroup which had high L3 <-> memory traffic in initial + * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but + * after some time rdtgroup has mostly L2 <-> L3 traffic. + * + * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its + * 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_domain *dom_mbm) +{ + u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val; + struct mbm_state *pmbm_data, *cmbm_data; + u32 cur_bw, delta_bw, user_bw; + struct rdt_resource *r_mba; + struct rdt_domain *dom_mba; + struct list_head *head; + struct rdtgroup *entry; + + if (!is_mbm_local_enabled()) + return; + + r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; + closid = rgrp->closid; + rmid = rgrp->mon.rmid; + pmbm_data = &dom_mbm->mbm_local[rmid]; + + dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba); + if (!dom_mba) { + pr_warn_once("Failure to get domain for MBA update\n"); + return; + } + + cur_bw = pmbm_data->prev_bw; + user_bw = dom_mba->mbps_val[closid]; + delta_bw = pmbm_data->delta_bw; + cur_msr_val = dom_mba->ctrl_val[closid]; + + /* + * For Ctrl groups read data from child monitor groups. + */ + head = &rgrp->mon.crdtgrp_list; + list_for_each_entry(entry, head, mon.crdtgrp_list) { + cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cur_bw += cmbm_data->prev_bw; + delta_bw += cmbm_data->delta_bw; + } + + /* + * Scale up/down the bandwidth linearly for the ctrl group. The + * bandwidth step is the bandwidth granularity specified by the + * hardware. + * + * The delta_bw is used when increasing the bandwidth so that we + * dont alternately increase and decrease the control values + * continuously. + * + * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if + * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep + * switching between 90 and 110 continuously if we only check + * cur_bw < user_bw. + */ + if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { + new_msr_val = cur_msr_val - r_mba->membw.bw_gran; + } else if (cur_msr_val < MAX_MBA_BW && + (user_bw > (cur_bw + delta_bw))) { + new_msr_val = cur_msr_val + r_mba->membw.bw_gran; + } else { + return; + } + + cur_msr = r_mba->msr_base + closid; + wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba)); + dom_mba->ctrl_val[closid] = new_msr_val; + + /* + * Delta values are updated dynamically package wise for each + * rdtgrp everytime the throttle MSR changes value. + * + * This is because (1)the increase in bandwidth is not perfectly + * linear and only "approximately" linear even when the hardware + * says it is linear.(2)Also since MBA is a core specific + * mechanism, the delta values vary based on number of cores used + * by the rdtgrp. + */ + pmbm_data->delta_comp = true; + list_for_each_entry(entry, head, mon.crdtgrp_list) { + cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cmbm_data->delta_comp = true; + } +} + +static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) +{ + struct rmid_read rr; + + rr.first = false; + rr.r = r; + rr.d = d; + + /* + * This is protected from concurrent reads from user + * as both the user and we hold the global mutex. + */ + if (is_mbm_total_enabled()) { + rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; + __mon_event_count(rmid, &rr); + } + if (is_mbm_local_enabled()) { + rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); + + /* + * Call the MBA software controller only for the + * control groups and when user has enabled + * the software controller explicitly. + */ + if (is_mba_sc(NULL)) + mbm_bw_count(rmid, &rr); + } +} + +/* + * Handler to scan the limbo list and move the RMIDs + * to free list whose occupancy < threshold_occupancy. + */ +void cqm_handle_limbo(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); + int cpu = smp_processor_id(); + struct rdt_resource *r; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + d = container_of(work, struct rdt_domain, cqm_limbo.work); + + __check_limbo(d, false); + + if (has_busy_rmid(r, d)) + schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); + + mutex_unlock(&rdtgroup_mutex); +} + +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + int cpu; + + cpu = cpumask_any(&dom->cpu_mask); + dom->cqm_work_cpu = cpu; + + schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); +} + +void mbm_handle_overflow(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); + struct rdtgroup *prgrp, *crgrp; + int cpu = smp_processor_id(); + struct list_head *head; + struct rdt_resource *r; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + + if (!static_branch_likely(&rdt_mon_enable_key)) + goto out_unlock; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + d = container_of(work, struct rdt_domain, mbm_over.work); + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + mbm_update(r, d, prgrp->mon.rmid); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) + mbm_update(r, d, crgrp->mon.rmid); + + if (is_mba_sc(NULL)) + update_mba_bw(prgrp, d); + } + + schedule_delayed_work_on(cpu, &d->mbm_over, delay); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + int cpu; + + if (!static_branch_likely(&rdt_mon_enable_key)) + return; + cpu = cpumask_any(&dom->cpu_mask); + dom->mbm_work_cpu = cpu; + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); +} + +static int dom_data_init(struct rdt_resource *r) +{ + struct rmid_entry *entry = NULL; + int i, nr_rmids; + + nr_rmids = r->num_rmid; + rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL); + if (!rmid_ptrs) + return -ENOMEM; + + for (i = 0; i < nr_rmids; i++) { + entry = &rmid_ptrs[i]; + INIT_LIST_HEAD(&entry->list); + + entry->rmid = i; + list_add_tail(&entry->list, &rmid_free_lru); + } + + /* + * RMID 0 is special and is always allocated. It's used for all + * tasks that are not monitored. + */ + entry = __rmid_entry(0); + list_del(&entry->list); + + return 0; +} + +static struct mon_evt llc_occupancy_event = { + .name = "llc_occupancy", + .evtid = QOS_L3_OCCUP_EVENT_ID, +}; + +static struct mon_evt mbm_total_event = { + .name = "mbm_total_bytes", + .evtid = QOS_L3_MBM_TOTAL_EVENT_ID, +}; + +static struct mon_evt mbm_local_event = { + .name = "mbm_local_bytes", + .evtid = QOS_L3_MBM_LOCAL_EVENT_ID, +}; + +/* + * Initialize the event list for the resource. + * + * Note that MBM events are also part of RDT_RESOURCE_L3 resource + * because as per the SDM the total and local memory bandwidth + * are enumerated as part of L3 monitoring. + */ +static void l3_mon_evt_init(struct rdt_resource *r) +{ + INIT_LIST_HEAD(&r->evt_list); + + if (is_llc_occupancy_enabled()) + list_add_tail(&llc_occupancy_event.list, &r->evt_list); + if (is_mbm_total_enabled()) + list_add_tail(&mbm_total_event.list, &r->evt_list); + if (is_mbm_local_enabled()) + list_add_tail(&mbm_local_event.list, &r->evt_list); +} + +int rdt_get_mon_l3_config(struct rdt_resource *r) +{ + unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; + unsigned int cl_size = boot_cpu_data.x86_cache_size; + int ret; + + r->mon_scale = boot_cpu_data.x86_cache_occ_scale; + r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; + r->mbm_width = MBM_CNTR_WIDTH_BASE; + + if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX) + r->mbm_width += mbm_offset; + else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX) + pr_warn("Ignoring impossible MBM counter offset\n"); + + /* + * A reasonable upper limit on the max threshold is the number + * of lines tagged per RMID if all RMIDs have the same number of + * lines tagged in the LLC. + * + * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. + */ + resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid; + + /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ + resctrl_cqm_threshold /= r->mon_scale; + + ret = dom_data_init(r); + if (ret) + return ret; + + l3_mon_evt_init(r); + + r->mon_capable = true; + r->mon_enabled = true; + + return 0; +} diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c new file mode 100644 index 000000000..465dce141 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -0,0 +1,1594 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Resource Director Technology (RDT) + * + * Pseudo-locking support built on top of Cache Allocation Technology (CAT) + * + * Copyright (C) 2018 Intel Corporation + * + * Author: Reinette Chatre <reinette.chatre@intel.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cacheinfo.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/debugfs.h> +#include <linux/kthread.h> +#include <linux/mman.h> +#include <linux/perf_event.h> +#include <linux/pm_qos.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + +#include <asm/cacheflush.h> +#include <asm/intel-family.h> +#include <asm/resctrl.h> +#include <asm/perf_event.h> + +#include "../../events/perf_event.h" /* For X86_CONFIG() */ +#include "internal.h" + +#define CREATE_TRACE_POINTS +#include "pseudo_lock_event.h" + +/* + * The bits needed to disable hardware prefetching varies based on the + * platform. During initialization we will discover which bits to use. + */ +static u64 prefetch_disable_bits; + +/* + * Major number assigned to and shared by all devices exposing + * pseudo-locked regions. + */ +static unsigned int pseudo_lock_major; +static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0); +static struct class *pseudo_lock_class; + +/** + * get_prefetch_disable_bits - prefetch disable bits of supported platforms + * + * Capture the list of platforms that have been validated to support + * pseudo-locking. This includes testing to ensure pseudo-locked regions + * with low cache miss rates can be created under variety of load conditions + * as well as that these pseudo-locked regions can maintain their low cache + * miss rates under variety of load conditions for significant lengths of time. + * + * After a platform has been validated to support pseudo-locking its + * hardware prefetch disable bits are included here as they are documented + * in the SDM. + * + * When adding a platform here also add support for its cache events to + * measure_cycles_perf_fn() + * + * Return: + * If platform is supported, the bits to disable hardware prefetchers, 0 + * if platform is not supported. + */ +static u64 get_prefetch_disable_bits(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return 0; + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 L2 Adjacent Cache Line Prefetcher Disable (R/W) + * 2 DCU Hardware Prefetcher Disable (R/W) + * 3 DCU IP Prefetcher Disable (R/W) + * 63:4 Reserved + */ + return 0xF; + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + /* + * SDM defines bits of MSR_MISC_FEATURE_CONTROL register + * as: + * 0 L2 Hardware Prefetcher Disable (R/W) + * 1 Reserved + * 2 DCU Hardware Prefetcher Disable (R/W) + * 63:3 Reserved + */ + return 0x5; + } + + return 0; +} + +/** + * pseudo_lock_minor_get - Obtain available minor number + * @minor: Pointer to where new minor number will be stored + * + * A bitmask is used to track available minor numbers. Here the next free + * minor number is marked as unavailable and returned. + * + * Return: 0 on success, <0 on failure. + */ +static int pseudo_lock_minor_get(unsigned int *minor) +{ + unsigned long first_bit; + + first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS); + + if (first_bit == MINORBITS) + return -ENOSPC; + + __clear_bit(first_bit, &pseudo_lock_minor_avail); + *minor = first_bit; + + return 0; +} + +/** + * pseudo_lock_minor_release - Return minor number to available + * @minor: The minor number made available + */ +static void pseudo_lock_minor_release(unsigned int minor) +{ + __set_bit(minor, &pseudo_lock_minor_avail); +} + +/** + * region_find_by_minor - Locate a pseudo-lock region by inode minor number + * @minor: The minor number of the device representing pseudo-locked region + * + * When the character device is accessed we need to determine which + * pseudo-locked region it belongs to. This is done by matching the minor + * number of the device to the pseudo-locked region it belongs. + * + * Minor numbers are assigned at the time a pseudo-locked region is associated + * with a cache instance. + * + * Return: On success return pointer to resource group owning the pseudo-locked + * region, NULL on failure. + */ +static struct rdtgroup *region_find_by_minor(unsigned int minor) +{ + struct rdtgroup *rdtgrp, *rdtgrp_match = NULL; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->plr && rdtgrp->plr->minor == minor) { + rdtgrp_match = rdtgrp; + break; + } + } + return rdtgrp_match; +} + +/** + * pseudo_lock_pm_req - A power management QoS request list entry + * @list: Entry within the @pm_reqs list for a pseudo-locked region + * @req: PM QoS request + */ +struct pseudo_lock_pm_req { + struct list_head list; + struct dev_pm_qos_request req; +}; + +static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req, *next; + + list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) { + dev_pm_qos_remove_request(&pm_req->req); + list_del(&pm_req->list); + kfree(pm_req); + } +} + +/** + * pseudo_lock_cstates_constrain - Restrict cores from entering C6 + * + * To prevent the cache from being affected by power management entering + * C6 has to be avoided. This is accomplished by requesting a latency + * requirement lower than lowest C6 exit latency of all supported + * platforms as found in the cpuidle state tables in the intel_idle driver. + * At this time it is possible to do so with a single latency requirement + * for all supported platforms. + * + * Since Goldmont is supported, which is affected by X86_BUG_MONITOR, + * the ACPI latencies need to be considered while keeping in mind that C2 + * may be set to map to deeper sleep states. In this case the latency + * requirement needs to prevent entering C2 also. + */ +static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr) +{ + struct pseudo_lock_pm_req *pm_req; + int cpu; + int ret; + + for_each_cpu(cpu, &plr->d->cpu_mask) { + pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL); + if (!pm_req) { + rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n"); + ret = -ENOMEM; + goto out_err; + } + ret = dev_pm_qos_add_request(get_cpu_device(cpu), + &pm_req->req, + DEV_PM_QOS_RESUME_LATENCY, + 30); + if (ret < 0) { + rdt_last_cmd_printf("Failed to add latency req CPU%d\n", + cpu); + kfree(pm_req); + ret = -1; + goto out_err; + } + list_add(&pm_req->list, &plr->pm_reqs); + } + + return 0; + +out_err: + pseudo_lock_cstates_relax(plr); + return ret; +} + +/** + * pseudo_lock_region_clear - Reset pseudo-lock region data + * @plr: pseudo-lock region + * + * All content of the pseudo-locked region is reset - any memory allocated + * freed. + * + * Return: void + */ +static void pseudo_lock_region_clear(struct pseudo_lock_region *plr) +{ + plr->size = 0; + plr->line_size = 0; + kfree(plr->kmem); + plr->kmem = NULL; + plr->r = NULL; + if (plr->d) + plr->d->plr = NULL; + plr->d = NULL; + plr->cbm = 0; + plr->debugfs_dir = NULL; +} + +/** + * pseudo_lock_region_init - Initialize pseudo-lock region information + * @plr: pseudo-lock region + * + * Called after user provided a schemata to be pseudo-locked. From the + * schemata the &struct pseudo_lock_region is on entry already initialized + * with the resource, domain, and capacity bitmask. Here the information + * required for pseudo-locking is deduced from this data and &struct + * pseudo_lock_region initialized further. This information includes: + * - size in bytes of the region to be pseudo-locked + * - cache line size to know the stride with which data needs to be accessed + * to be pseudo-locked + * - a cpu associated with the cache instance on which the pseudo-locking + * flow can be executed + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_init(struct pseudo_lock_region *plr) +{ + struct cpu_cacheinfo *ci; + int ret; + int i; + + /* Pick the first cpu we find that is associated with the cache. */ + plr->cpu = cpumask_first(&plr->d->cpu_mask); + + if (!cpu_online(plr->cpu)) { + rdt_last_cmd_printf("CPU %u associated with cache not online\n", + plr->cpu); + ret = -ENODEV; + goto out_region; + } + + ci = get_cpu_cacheinfo(plr->cpu); + + plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm); + + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == plr->r->cache_level) { + plr->line_size = ci->info_list[i].coherency_line_size; + return 0; + } + } + + ret = -1; + rdt_last_cmd_puts("Unable to determine cache line size\n"); +out_region: + pseudo_lock_region_clear(plr); + return ret; +} + +/** + * pseudo_lock_init - Initialize a pseudo-lock region + * @rdtgrp: resource group to which new pseudo-locked region will belong + * + * A pseudo-locked region is associated with a resource group. When this + * association is created the pseudo-locked region is initialized. The + * details of the pseudo-locked region are not known at this time so only + * allocation is done and association established. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_init(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr; + + plr = kzalloc(sizeof(*plr), GFP_KERNEL); + if (!plr) + return -ENOMEM; + + init_waitqueue_head(&plr->lock_thread_wq); + INIT_LIST_HEAD(&plr->pm_reqs); + rdtgrp->plr = plr; + return 0; +} + +/** + * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked + * @plr: pseudo-lock region + * + * Initialize the details required to set up the pseudo-locked region and + * allocate the contiguous memory that will be pseudo-locked to the cache. + * + * Return: 0 on success, <0 on failure. Descriptive error will be written + * to last_cmd_status buffer. + */ +static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr) +{ + int ret; + + ret = pseudo_lock_region_init(plr); + if (ret < 0) + return ret; + + /* + * We do not yet support contiguous regions larger than + * KMALLOC_MAX_SIZE. + */ + if (plr->size > KMALLOC_MAX_SIZE) { + rdt_last_cmd_puts("Requested region exceeds maximum size\n"); + ret = -E2BIG; + goto out_region; + } + + plr->kmem = kzalloc(plr->size, GFP_KERNEL); + if (!plr->kmem) { + rdt_last_cmd_puts("Unable to allocate memory\n"); + ret = -ENOMEM; + goto out_region; + } + + ret = 0; + goto out; +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * pseudo_lock_free - Free a pseudo-locked region + * @rdtgrp: resource group to which pseudo-locked region belonged + * + * The pseudo-locked region's resources have already been released, or not + * yet created at this point. Now it can be freed and disassociated from the + * resource group. + * + * Return: void + */ +static void pseudo_lock_free(struct rdtgroup *rdtgrp) +{ + pseudo_lock_region_clear(rdtgrp->plr); + kfree(rdtgrp->plr); + rdtgrp->plr = NULL; +} + +/** + * pseudo_lock_fn - Load kernel memory into cache + * @_rdtgrp: resource group to which pseudo-lock region belongs + * + * This is the core pseudo-locking flow. + * + * First we ensure that the kernel memory cannot be found in the cache. + * Then, while taking care that there will be as little interference as + * possible, the memory to be loaded is accessed while core is running + * with class of service set to the bitmask of the pseudo-locked region. + * After this is complete no future CAT allocations will be allowed to + * overlap with this bitmask. + * + * Local register variables are utilized to ensure that the memory region + * to be locked is the only memory access made during the critical locking + * loop. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int pseudo_lock_fn(void *_rdtgrp) +{ + struct rdtgroup *rdtgrp = _rdtgrp; + struct pseudo_lock_region *plr = rdtgrp->plr; + u32 rmid_p, closid_p; + unsigned long i; + u64 saved_msr; +#ifdef CONFIG_KASAN + /* + * The registers used for local register variables are also used + * when KASAN is active. When KASAN is active we use a regular + * variable to ensure we always use a valid pointer, but the cost + * is that this variable will enter the cache through evicting the + * memory we are trying to lock into the cache. Thus expect lower + * pseudo-locking success rate when KASAN is active. + */ + unsigned int line_size; + unsigned int size; + void *mem_r; +#else + register unsigned int line_size asm("esi"); + register unsigned int size asm("edi"); + register void *mem_r asm(_ASM_BX); +#endif /* CONFIG_KASAN */ + + /* + * Make sure none of the allocated memory is cached. If it is we + * will get a cache hit in below loop from outside of pseudo-locked + * region. + * wbinvd (as opposed to clflush/clflushopt) is required to + * increase likelihood that allocated cache portion will be filled + * with associated memory. + */ + native_wbinvd(); + + /* + * Always called with interrupts enabled. By disabling interrupts + * ensure that we will not be preempted during this critical section. + */ + local_irq_disable(); + + /* + * Call wrmsr and rdmsr as directly as possible to avoid tracing + * clobbering local register variables or affecting cache accesses. + * + * Disable the hardware prefetcher so that when the end of the memory + * being pseudo-locked is reached the hardware will not read beyond + * the buffer and evict pseudo-locked memory read earlier from the + * cache. + */ + saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL); + __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + closid_p = this_cpu_read(pqr_state.cur_closid); + rmid_p = this_cpu_read(pqr_state.cur_rmid); + mem_r = plr->kmem; + size = plr->size; + line_size = plr->line_size; + /* + * Critical section begin: start by writing the closid associated + * with the capacity bitmask of the cache region being + * pseudo-locked followed by reading of kernel memory to load it + * into the cache. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + /* + * Cache was flushed earlier. Now access kernel memory to read it + * into cache region associated with just activated plr->closid. + * Loop over data twice: + * - In first loop the cache region is shared with the page walker + * as it populates the paging structure caches (including TLB). + * - In the second loop the paging structure caches are used and + * cache region is populated with the memory being referenced. + */ + for (i = 0; i < size; i += PAGE_SIZE) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Critical section end: restore closid with capacity bitmask that + * does not overlap with pseudo-locked region. + */ + __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); + + /* Re-enable the hardware prefetcher(s) */ + wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr); + local_irq_enable(); + + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * rdtgroup_monitor_in_progress - Test if monitoring in progress + * @r: resource group being queried + * + * Return: 1 if monitor groups have been created for this resource + * group, 0 otherwise. + */ +static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp) +{ + return !list_empty(&rdtgrp->mon.crdtgrp_list); +} + +/** + * rdtgroup_locksetup_user_restrict - Restrict user access to group + * @rdtgrp: resource group needing access restricted + * + * A resource group used for cache pseudo-locking cannot have cpus or tasks + * assigned to it. This is communicated to the user by restricting access + * to all the files that can be used to make such changes. + * + * Permissions restored with rdtgroup_locksetup_user_restore() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restriction of access an attempt will be made to restore permissions but + * the state of the mode of these files will be uncertain when a failure + * occurs. + */ +static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); +err_cpus: + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); +err_tasks: + rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); +out: + return ret; +} + +/** + * rdtgroup_locksetup_user_restore - Restore user access to group + * @rdtgrp: resource group needing access restored + * + * Restore all file access previously removed using + * rdtgroup_locksetup_user_restrict() + * + * Return: 0 on success, <0 on failure. If a failure occurs during the + * restoration of access an attempt will be made to restrict permissions + * again but the state of the mode of these files will be uncertain when + * a failure occurs. + */ +static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) +{ + int ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777); + if (ret) + return ret; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777); + if (ret) + goto err_tasks; + + ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777); + if (ret) + goto err_cpus; + + if (rdt_mon_capable) { + ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); + if (ret) + goto err_cpus_list; + } + + ret = 0; + goto out; + +err_cpus_list: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list"); +err_cpus: + rdtgroup_kn_mode_restrict(rdtgrp, "cpus"); +err_tasks: + rdtgroup_kn_mode_restrict(rdtgrp, "tasks"); +out: + return ret; +} + +/** + * rdtgroup_locksetup_enter - Resource group enters locksetup mode + * @rdtgrp: resource group requested to enter locksetup mode + * + * A resource group enters locksetup mode to reflect that it would be used + * to represent a pseudo-locked region and is in the process of being set + * up to do so. A resource group used for a pseudo-locked region would + * lose the closid associated with it so we cannot allow it to have any + * tasks or cpus assigned nor permit tasks or cpus to be assigned in the + * future. Monitoring of a pseudo-locked region is not allowed either. + * + * The above and more restrictions on a pseudo-locked region are checked + * for and enforced before the resource group enters the locksetup mode. + * + * Returns: 0 if the resource group successfully entered locksetup mode, <0 + * on failure. On failure the last_cmd_status buffer is updated with text to + * communicate details of failure to the user. + */ +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) +{ + int ret; + + /* + * The default resource group can neither be removed nor lose the + * default closid associated with it. + */ + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("Cannot pseudo-lock default group\n"); + return -EINVAL; + } + + /* + * Cache Pseudo-locking not supported when CDP is enabled. + * + * Some things to consider if you would like to enable this + * support (using L3 CDP as example): + * - When CDP is enabled two separate resources are exposed, + * L3DATA and L3CODE, but they are actually on the same cache. + * The implication for pseudo-locking is that if a + * pseudo-locked region is created on a domain of one + * resource (eg. L3CODE), then a pseudo-locked region cannot + * be created on that same domain of the other resource + * (eg. L3DATA). This is because the creation of a + * pseudo-locked region involves a call to wbinvd that will + * affect all cache allocations on particular domain. + * - Considering the previous, it may be possible to only + * expose one of the CDP resources to pseudo-locking and + * hide the other. For example, we could consider to only + * expose L3DATA and since the L3 cache is unified it is + * still possible to place instructions there are execute it. + * - If only one region is exposed to pseudo-locking we should + * still keep in mind that availability of a portion of cache + * for pseudo-locking should take into account both resources. + * Similarly, if a pseudo-locked region is created in one + * resource, the portion of cache used by it should be made + * unavailable to all future allocations from both resources. + */ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled || + rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) { + rdt_last_cmd_puts("CDP enabled\n"); + return -EINVAL; + } + + /* + * Not knowing the bits to disable prefetching implies that this + * platform does not support Cache Pseudo-Locking. + */ + prefetch_disable_bits = get_prefetch_disable_bits(); + if (prefetch_disable_bits == 0) { + rdt_last_cmd_puts("Pseudo-locking not supported\n"); + return -EINVAL; + } + + if (rdtgroup_monitor_in_progress(rdtgrp)) { + rdt_last_cmd_puts("Monitoring in progress\n"); + return -EINVAL; + } + + if (rdtgroup_tasks_assigned(rdtgrp)) { + rdt_last_cmd_puts("Tasks assigned to resource group\n"); + return -EINVAL; + } + + if (!cpumask_empty(&rdtgrp->cpu_mask)) { + rdt_last_cmd_puts("CPUs assigned to resource group\n"); + return -EINVAL; + } + + if (rdtgroup_locksetup_user_restrict(rdtgrp)) { + rdt_last_cmd_puts("Unable to modify resctrl permissions\n"); + return -EIO; + } + + ret = pseudo_lock_init(rdtgrp); + if (ret) { + rdt_last_cmd_puts("Unable to init pseudo-lock region\n"); + goto out_release; + } + + /* + * If this system is capable of monitoring a rmid would have been + * allocated when the control group was created. This is not needed + * anymore when this group would be used for pseudo-locking. This + * is safe to call on platforms not capable of monitoring. + */ + free_rmid(rdtgrp->mon.rmid); + + ret = 0; + goto out; + +out_release: + rdtgroup_locksetup_user_restore(rdtgrp); +out: + return ret; +} + +/** + * rdtgroup_locksetup_exit - resource group exist locksetup mode + * @rdtgrp: resource group + * + * When a resource group exits locksetup mode the earlier restrictions are + * lifted. + * + * Return: 0 on success, <0 on failure + */ +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) +{ + int ret; + + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("Out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + } + + ret = rdtgroup_locksetup_user_restore(rdtgrp); + if (ret) { + free_rmid(rdtgrp->mon.rmid); + return ret; + } + + pseudo_lock_free(rdtgrp); + return 0; +} + +/** + * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked + * @d: RDT domain + * @cbm: CBM to test + * + * @d represents a cache instance and @cbm a capacity bitmask that is + * considered for it. Determine if @cbm overlaps with any existing + * pseudo-locked region on @d. + * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: true if @cbm overlaps with pseudo-locked region on @d, false + * otherwise. + */ +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm) +{ + unsigned int cbm_len; + unsigned long cbm_b; + + if (d->plr) { + cbm_len = d->plr->r->cache.cbm_len; + cbm_b = d->plr->cbm; + if (bitmap_intersects(&cbm, &cbm_b, cbm_len)) + return true; + } + return false; +} + +/** + * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy + * @d: RDT domain under test + * + * The setup of a pseudo-locked region affects all cache instances within + * the hierarchy of the region. It is thus essential to know if any + * pseudo-locked regions exist within a cache hierarchy to prevent any + * attempts to create new pseudo-locked regions in the same hierarchy. + * + * Return: true if a pseudo-locked region exists in the hierarchy of @d or + * if it is not possible to test due to memory allocation issue, + * false otherwise. + */ +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) +{ + cpumask_var_t cpu_with_psl; + struct rdt_resource *r; + struct rdt_domain *d_i; + bool ret = false; + + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) + return true; + + /* + * First determine which cpus have pseudo-locked regions + * associated with them. + */ + for_each_alloc_enabled_rdt_resource(r) { + list_for_each_entry(d_i, &r->domains, list) { + if (d_i->plr) + cpumask_or(cpu_with_psl, cpu_with_psl, + &d_i->cpu_mask); + } + } + + /* + * Next test if new pseudo-locked region would intersect with + * existing region. + */ + if (cpumask_intersects(&d->cpu_mask, cpu_with_psl)) + ret = true; + + free_cpumask_var(cpu_with_psl); + return ret; +} + +/** + * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory + * @_plr: pseudo-lock region to measure + * + * There is no deterministic way to test if a memory region is cached. One + * way is to measure how long it takes to read the memory, the speed of + * access is a good way to learn how close to the cpu the data was. Even + * more, if the prefetcher is disabled and the memory is read at a stride + * of half the cache line, then a cache miss will be easy to spot since the + * read of the first half would be significantly slower than the read of + * the second half. + * + * Return: 0. Waiter on waitqueue will be woken on completion. + */ +static int measure_cycles_lat_fn(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + u32 saved_low, saved_high; + unsigned long i; + u64 start, end; + void *mem_r; + + local_irq_disable(); + /* + * Disable hardware prefetchers. + */ + rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); + wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + mem_r = READ_ONCE(plr->kmem); + /* + * Dummy execute of the time measurement to load the needed + * instructions into the L1 instruction cache. + */ + start = rdtsc_ordered(); + for (i = 0; i < plr->size; i += 32) { + start = rdtsc_ordered(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + end = rdtsc_ordered(); + trace_pseudo_lock_mem_latency((u32)(end - start)); + } + wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); + local_irq_enable(); + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/* + * Create a perf_event_attr for the hit and miss perf events that will + * be used during the performance measurement. A perf_event maintains + * a pointer to its perf_event_attr so a unique attribute structure is + * created for each perf_event. + * + * The actual configuration of the event is set right before use in order + * to use the X86_CONFIG macro. + */ +static struct perf_event_attr perf_miss_attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 0, + .exclude_user = 1, +}; + +static struct perf_event_attr perf_hit_attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 0, + .exclude_user = 1, +}; + +struct residency_counts { + u64 miss_before, hits_before; + u64 miss_after, hits_after; +}; + +static int measure_residency_fn(struct perf_event_attr *miss_attr, + struct perf_event_attr *hit_attr, + struct pseudo_lock_region *plr, + struct residency_counts *counts) +{ + u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0; + struct perf_event *miss_event, *hit_event; + int hit_pmcnum, miss_pmcnum; + u32 saved_low, saved_high; + unsigned int line_size; + unsigned int size; + unsigned long i; + void *mem_r; + u64 tmp; + + miss_event = perf_event_create_kernel_counter(miss_attr, plr->cpu, + NULL, NULL, NULL); + if (IS_ERR(miss_event)) + goto out; + + hit_event = perf_event_create_kernel_counter(hit_attr, plr->cpu, + NULL, NULL, NULL); + if (IS_ERR(hit_event)) + goto out_miss; + + local_irq_disable(); + /* + * Check any possible error state of events used by performing + * one local read. + */ + if (perf_event_read_local(miss_event, &tmp, NULL, NULL)) { + local_irq_enable(); + goto out_hit; + } + if (perf_event_read_local(hit_event, &tmp, NULL, NULL)) { + local_irq_enable(); + goto out_hit; + } + + /* + * Disable hardware prefetchers. + */ + rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); + wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + + /* Initialize rest of local variables */ + /* + * Performance event has been validated right before this with + * interrupts disabled - it is thus safe to read the counter index. + */ + miss_pmcnum = x86_perf_rdpmc_index(miss_event); + hit_pmcnum = x86_perf_rdpmc_index(hit_event); + line_size = READ_ONCE(plr->line_size); + mem_r = READ_ONCE(plr->kmem); + size = READ_ONCE(plr->size); + + /* + * Read counter variables twice - first to load the instructions + * used in L1 cache, second to capture accurate value that does not + * include cache misses incurred because of instruction loads. + */ + rdpmcl(hit_pmcnum, hits_before); + rdpmcl(miss_pmcnum, miss_before); + /* + * From SDM: Performing back-to-back fast reads are not guaranteed + * to be monotonic. + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + rdpmcl(hit_pmcnum, hits_before); + rdpmcl(miss_pmcnum, miss_before); + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + rdpmcl(hit_pmcnum, hits_after); + rdpmcl(miss_pmcnum, miss_after); + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + /* Re-enable hardware prefetchers */ + wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); + local_irq_enable(); +out_hit: + perf_event_release_kernel(hit_event); +out_miss: + perf_event_release_kernel(miss_event); +out: + /* + * All counts will be zero on failure. + */ + counts->miss_before = miss_before; + counts->hits_before = hits_before; + counts->miss_after = miss_after; + counts->hits_after = hits_after; + return 0; +} + +static int measure_l2_residency(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + struct residency_counts counts = {0}; + + /* + * Non-architectural event for the Goldmont Microarchitecture + * from Intel x86 Architecture Software Developer Manual (SDM): + * MEM_LOAD_UOPS_RETIRED D1H (event number) + * Umask values: + * L2_HIT 02H + * L2_MISS 10H + */ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + perf_miss_attr.config = X86_CONFIG(.event = 0xd1, + .umask = 0x10); + perf_hit_attr.config = X86_CONFIG(.event = 0xd1, + .umask = 0x2); + break; + default: + goto out; + } + + measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts); + /* + * If a failure prevented the measurements from succeeding + * tracepoints will still be written and all counts will be zero. + */ + trace_pseudo_lock_l2(counts.hits_after - counts.hits_before, + counts.miss_after - counts.miss_before); +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +static int measure_l3_residency(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + struct residency_counts counts = {0}; + + /* + * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event + * has two "no fix" errata associated with it: BDM35 and BDM100. On + * this platform the following events are used instead: + * LONGEST_LAT_CACHE 2EH (Documented in SDM) + * REFERENCE 4FH + * MISS 41H + */ + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* On BDW the hit event counts references, not hits */ + perf_hit_attr.config = X86_CONFIG(.event = 0x2e, + .umask = 0x4f); + perf_miss_attr.config = X86_CONFIG(.event = 0x2e, + .umask = 0x41); + break; + default: + goto out; + } + + measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts); + /* + * If a failure prevented the measurements from succeeding + * tracepoints will still be written and all counts will be zero. + */ + + counts.miss_after -= counts.miss_before; + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) { + /* + * On BDW references and misses are counted, need to adjust. + * Sometimes the "hits" counter is a bit more than the + * references, for example, x references but x + 1 hits. + * To not report invalid hit values in this case we treat + * that as misses equal to references. + */ + /* First compute the number of cache references measured */ + counts.hits_after -= counts.hits_before; + /* Next convert references to cache hits */ + counts.hits_after -= min(counts.miss_after, counts.hits_after); + } else { + counts.hits_after -= counts.hits_before; + } + + trace_pseudo_lock_l3(counts.hits_after, counts.miss_after); +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +/** + * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region + * + * The measurement of latency to access a pseudo-locked region should be + * done from a cpu that is associated with that pseudo-locked region. + * Determine which cpu is associated with this region and start a thread on + * that cpu to perform the measurement, wait for that thread to complete. + * + * Return: 0 on success, <0 on failure + */ +static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int cpu; + int ret = -1; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out; + } + + if (!plr->d) { + ret = -ENODEV; + goto out; + } + + plr->thread_done = 0; + cpu = cpumask_first(&plr->d->cpu_mask); + if (!cpu_online(cpu)) { + ret = -ENODEV; + goto out; + } + + plr->cpu = cpu; + + if (sel == 1) + thread = kthread_create_on_node(measure_cycles_lat_fn, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 2) + thread = kthread_create_on_node(measure_l2_residency, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 3) + thread = kthread_create_on_node(measure_l3_residency, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else + goto out; + + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + goto out; + } + kthread_bind(thread, cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) + goto out; + + ret = 0; + +out: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +static ssize_t pseudo_lock_measure_trigger(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct rdtgroup *rdtgrp = file->private_data; + size_t buf_size; + char buf[32]; + int ret; + int sel; + + buf_size = min(count, (sizeof(buf) - 1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + ret = kstrtoint(buf, 10, &sel); + if (ret == 0) { + if (sel != 1 && sel != 2 && sel != 3) + return -EINVAL; + ret = debugfs_file_get(file->f_path.dentry); + if (ret) + return ret; + ret = pseudo_lock_measure_cycles(rdtgrp, sel); + if (ret == 0) + ret = count; + debugfs_file_put(file->f_path.dentry); + } + + return ret; +} + +static const struct file_operations pseudo_measure_fops = { + .write = pseudo_lock_measure_trigger, + .open = simple_open, + .llseek = default_llseek, +}; + +/** + * rdtgroup_pseudo_lock_create - Create a pseudo-locked region + * @rdtgrp: resource group to which pseudo-lock region belongs + * + * Called when a resource group in the pseudo-locksetup mode receives a + * valid schemata that should be pseudo-locked. Since the resource group is + * in pseudo-locksetup mode the &struct pseudo_lock_region has already been + * allocated and initialized with the essential information. If a failure + * occurs the resource group remains in the pseudo-locksetup mode with the + * &struct pseudo_lock_region associated with it, but cleared from all + * information and ready for the user to re-attempt pseudo-locking by + * writing the schemata again. + * + * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0 + * on failure. Descriptive error will be written to last_cmd_status buffer. + */ +int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + struct task_struct *thread; + unsigned int new_minor; + struct device *dev; + int ret; + + ret = pseudo_lock_region_alloc(plr); + if (ret < 0) + return ret; + + ret = pseudo_lock_cstates_constrain(plr); + if (ret < 0) { + ret = -EINVAL; + goto out_region; + } + + plr->thread_done = 0; + + thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp, + cpu_to_node(plr->cpu), + "pseudo_lock/%u", plr->cpu); + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + rdt_last_cmd_printf("Locking thread returned error %d\n", ret); + goto out_cstates; + } + + kthread_bind(thread, plr->cpu); + wake_up_process(thread); + + ret = wait_event_interruptible(plr->lock_thread_wq, + plr->thread_done == 1); + if (ret < 0) { + /* + * If the thread does not get on the CPU for whatever + * reason and the process which sets up the region is + * interrupted then this will leave the thread in runnable + * state and once it gets on the CPU it will derefence + * the cleared, but not freed, plr struct resulting in an + * empty pseudo-locking loop. + */ + rdt_last_cmd_puts("Locking thread interrupted\n"); + goto out_cstates; + } + + ret = pseudo_lock_minor_get(&new_minor); + if (ret < 0) { + rdt_last_cmd_puts("Unable to obtain a new minor number\n"); + goto out_cstates; + } + + /* + * Unlock access but do not release the reference. The + * pseudo-locked region will still be here on return. + * + * The mutex has to be released temporarily to avoid a potential + * deadlock with the mm->mmap_lock which is obtained in the + * device_create() and debugfs_create_dir() callpath below as well as + * before the mmap() callback is called. + */ + mutex_unlock(&rdtgroup_mutex); + + if (!IS_ERR_OR_NULL(debugfs_resctrl)) { + plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name, + debugfs_resctrl); + if (!IS_ERR_OR_NULL(plr->debugfs_dir)) + debugfs_create_file("pseudo_lock_measure", 0200, + plr->debugfs_dir, rdtgrp, + &pseudo_measure_fops); + } + + dev = device_create(pseudo_lock_class, NULL, + MKDEV(pseudo_lock_major, new_minor), + rdtgrp, "%s", rdtgrp->kn->name); + + mutex_lock(&rdtgroup_mutex); + + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + rdt_last_cmd_printf("Failed to create character device: %d\n", + ret); + goto out_debugfs; + } + + /* We released the mutex - check if group was removed while we did so */ + if (rdtgrp->flags & RDT_DELETED) { + ret = -ENODEV; + goto out_device; + } + + plr->minor = new_minor; + + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED; + closid_free(rdtgrp->closid); + rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444); + rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444); + + ret = 0; + goto out; + +out_device: + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor)); +out_debugfs: + debugfs_remove_recursive(plr->debugfs_dir); + pseudo_lock_minor_release(new_minor); +out_cstates: + pseudo_lock_cstates_relax(plr); +out_region: + pseudo_lock_region_clear(plr); +out: + return ret; +} + +/** + * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region + * @rdtgrp: resource group to which the pseudo-locked region belongs + * + * The removal of a pseudo-locked region can be initiated when the resource + * group is removed from user space via a "rmdir" from userspace or the + * unmount of the resctrl filesystem. On removal the resource group does + * not go back to pseudo-locksetup mode before it is removed, instead it is + * removed directly. There is thus assymmetry with the creation where the + * &struct pseudo_lock_region is removed here while it was not created in + * rdtgroup_pseudo_lock_create(). + * + * Return: void + */ +void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) +{ + struct pseudo_lock_region *plr = rdtgrp->plr; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + /* + * Default group cannot be a pseudo-locked region so we can + * free closid here. + */ + closid_free(rdtgrp->closid); + goto free; + } + + pseudo_lock_cstates_relax(plr); + debugfs_remove_recursive(rdtgrp->plr->debugfs_dir); + device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor)); + pseudo_lock_minor_release(plr->minor); + +free: + pseudo_lock_free(rdtgrp); +} + +static int pseudo_lock_dev_open(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = region_find_by_minor(iminor(inode)); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + filp->private_data = rdtgrp; + atomic_inc(&rdtgrp->waitcount); + /* Perform a non-seekable open - llseek is not supported */ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + + mutex_unlock(&rdtgroup_mutex); + + return 0; +} + +static int pseudo_lock_dev_release(struct inode *inode, struct file *filp) +{ + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + filp->private_data = NULL; + atomic_dec(&rdtgrp->waitcount); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static int pseudo_lock_dev_mremap(struct vm_area_struct *area) +{ + /* Not supported */ + return -EINVAL; +} + +static const struct vm_operations_struct pseudo_mmap_ops = { + .mremap = pseudo_lock_dev_mremap, +}; + +static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long vsize = vma->vm_end - vma->vm_start; + unsigned long off = vma->vm_pgoff << PAGE_SHIFT; + struct pseudo_lock_region *plr; + struct rdtgroup *rdtgrp; + unsigned long physical; + unsigned long psize; + + mutex_lock(&rdtgroup_mutex); + + rdtgrp = filp->private_data; + WARN_ON(!rdtgrp); + if (!rdtgrp) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + plr = rdtgrp->plr; + + if (!plr->d) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + + /* + * Task is required to run with affinity to the cpus associated + * with the pseudo-locked region. If this is not the case the task + * may be scheduled elsewhere and invalidate entries in the + * pseudo-locked region. + */ + if (!cpumask_subset(current->cpus_ptr, &plr->d->cpu_mask)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + physical = __pa(plr->kmem) >> PAGE_SHIFT; + psize = plr->size - off; + + if (off > plr->size) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + /* + * Ensure changes are carried directly to the memory being mapped, + * do not allow copy-on-write mapping. + */ + if (!(vma->vm_flags & VM_SHARED)) { + mutex_unlock(&rdtgroup_mutex); + return -EINVAL; + } + + if (vsize > psize) { + mutex_unlock(&rdtgroup_mutex); + return -ENOSPC; + } + + memset(plr->kmem + off, 0, vsize); + + if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff, + vsize, vma->vm_page_prot)) { + mutex_unlock(&rdtgroup_mutex); + return -EAGAIN; + } + vma->vm_ops = &pseudo_mmap_ops; + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static const struct file_operations pseudo_lock_dev_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = NULL, + .write = NULL, + .open = pseudo_lock_dev_open, + .release = pseudo_lock_dev_release, + .mmap = pseudo_lock_dev_mmap, +}; + +static char *pseudo_lock_devnode(struct device *dev, umode_t *mode) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = dev_get_drvdata(dev); + if (mode) + *mode = 0600; + return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name); +} + +int rdt_pseudo_lock_init(void) +{ + int ret; + + ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops); + if (ret < 0) + return ret; + + pseudo_lock_major = ret; + + pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock"); + if (IS_ERR(pseudo_lock_class)) { + ret = PTR_ERR(pseudo_lock_class); + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + return ret; + } + + pseudo_lock_class->devnode = pseudo_lock_devnode; + return 0; +} + +void rdt_pseudo_lock_release(void) +{ + class_destroy(pseudo_lock_class); + pseudo_lock_class = NULL; + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + pseudo_lock_major = 0; +} diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h new file mode 100644 index 000000000..428ebbd42 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM resctrl + +#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PSEUDO_LOCK_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(pseudo_lock_mem_latency, + TP_PROTO(u32 latency), + TP_ARGS(latency), + TP_STRUCT__entry(__field(u32, latency)), + TP_fast_assign(__entry->latency = latency), + TP_printk("latency=%u", __entry->latency) + ); + +TRACE_EVENT(pseudo_lock_l2, + TP_PROTO(u64 l2_hits, u64 l2_miss), + TP_ARGS(l2_hits, l2_miss), + TP_STRUCT__entry(__field(u64, l2_hits) + __field(u64, l2_miss)), + TP_fast_assign(__entry->l2_hits = l2_hits; + __entry->l2_miss = l2_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l2_hits, __entry->l2_miss)); + +TRACE_EVENT(pseudo_lock_l3, + TP_PROTO(u64 l3_hits, u64 l3_miss), + TP_ARGS(l3_hits, l3_miss), + TP_STRUCT__entry(__field(u64, l3_hits) + __field(u64, l3_miss)), + TP_fast_assign(__entry->l3_hits = l3_hits; + __entry->l3_miss = l3_miss;), + TP_printk("hits=%llu miss=%llu", + __entry->l3_hits, __entry->l3_miss)); + +#endif /* _TRACE_PSEUDO_LOCK_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE pseudo_lock_event +#include <trace/define_trace.h> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c new file mode 100644 index 000000000..1e73b6fae --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -0,0 +1,3263 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * User interface for Resource Alloction in Resource Director Technology(RDT) + * + * Copyright (C) 2016 Intel Corporation + * + * Author: Fenghua Yu <fenghua.yu@intel.com> + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cacheinfo.h> +#include <linux/cpu.h> +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/fs_parser.h> +#include <linux/sysfs.h> +#include <linux/kernfs.h> +#include <linux/seq_buf.h> +#include <linux/seq_file.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/slab.h> +#include <linux/task_work.h> +#include <linux/user_namespace.h> + +#include <uapi/linux/magic.h> + +#include <asm/resctrl.h> +#include "internal.h" + +DEFINE_STATIC_KEY_FALSE(rdt_enable_key); +DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); +DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); +static struct kernfs_root *rdt_root; +struct rdtgroup rdtgroup_default; +LIST_HEAD(rdt_all_groups); + +/* Kernel fs node for "info" directory under root */ +static struct kernfs_node *kn_info; + +/* Kernel fs node for "mon_groups" directory under root */ +static struct kernfs_node *kn_mongrp; + +/* Kernel fs node for "mon_data" directory under root */ +static struct kernfs_node *kn_mondata; + +static struct seq_buf last_cmd_status; +static char last_cmd_status_buf[512]; + +struct dentry *debugfs_resctrl; + +void rdt_last_cmd_clear(void) +{ + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_clear(&last_cmd_status); +} + +void rdt_last_cmd_puts(const char *s) +{ + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_puts(&last_cmd_status, s); +} + +void rdt_last_cmd_printf(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_vprintf(&last_cmd_status, fmt, ap); + va_end(ap); +} + +/* + * Trivial allocator for CLOSIDs. Since h/w only supports a small number, + * we can keep a bitmap of free CLOSIDs in a single integer. + * + * Using a global CLOSID across all resources has some advantages and + * some drawbacks: + * + We can simply set "current->closid" to assign a task to a resource + * group. + * + Context switch code can avoid extra memory references deciding which + * CLOSID to load into the PQR_ASSOC MSR + * - We give up some options in configuring resource groups across multi-socket + * systems. + * - Our choices on how to configure each resource become progressively more + * limited as the number of resources grows. + */ +static int closid_free_map; +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} + +static void closid_init(void) +{ + struct rdt_resource *r; + int rdt_min_closid = 32; + + /* Compute rdt_min_closid across all resources */ + for_each_alloc_enabled_rdt_resource(r) + rdt_min_closid = min(rdt_min_closid, r->num_closid); + + closid_free_map = BIT_MASK(rdt_min_closid) - 1; + + /* CLOSID 0 is always reserved for the default group */ + closid_free_map &= ~1; + closid_free_map_len = rdt_min_closid; +} + +static int closid_alloc(void) +{ + u32 closid = ffs(closid_free_map); + + if (closid == 0) + return -ENOSPC; + closid--; + closid_free_map &= ~(1 << closid); + + return closid; +} + +void closid_free(int closid) +{ + closid_free_map |= 1 << closid; +} + +/** + * closid_allocated - test if provided closid is in use + * @closid: closid to be tested + * + * Return: true if @closid is currently associated with a resource group, + * false if @closid is free + */ +static bool closid_allocated(unsigned int closid) +{ + return (closid_free_map & (1 << closid)) == 0; +} + +/** + * rdtgroup_mode_by_closid - Return mode of resource group with closid + * @closid: closid if the resource group + * + * Each resource group is associated with a @closid. Here the mode + * of a resource group can be queried by searching for it using its closid. + * + * Return: mode as &enum rdtgrp_mode of resource group with closid @closid + */ +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid) +{ + struct rdtgroup *rdtgrp; + + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (rdtgrp->closid == closid) + return rdtgrp->mode; + } + + return RDT_NUM_MODES; +} + +static const char * const rdt_mode_str[] = { + [RDT_MODE_SHAREABLE] = "shareable", + [RDT_MODE_EXCLUSIVE] = "exclusive", + [RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup", + [RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked", +}; + +/** + * rdtgroup_mode_str - Return the string representation of mode + * @mode: the resource group mode as &enum rdtgroup_mode + * + * Return: string representation of valid mode, "unknown" otherwise + */ +static const char *rdtgroup_mode_str(enum rdtgrp_mode mode) +{ + if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES) + return "unknown"; + + return rdt_mode_str[mode]; +} + +/* set uid and gid of rdtgroup dirs and files to that of the creator */ +static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) +{ + struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = current_fsuid(), + .ia_gid = current_fsgid(), }; + + if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && + gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) + return 0; + + return kernfs_setattr(kn, &iattr); +} + +static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) +{ + struct kernfs_node *kn; + int ret; + + kn = __kernfs_create_file(parent_kn, rft->name, rft->mode, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, + 0, rft->kf_ops, rft, NULL, NULL); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } + + return 0; +} + +static int rdtgroup_seqfile_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + struct rftype *rft = of->kn->priv; + + if (rft->seq_show) + return rft->seq_show(of, m, arg); + return 0; +} + +static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct rftype *rft = of->kn->priv; + + if (rft->write) + return rft->write(of, buf, nbytes, off); + + return -EINVAL; +} + +static struct kernfs_ops rdtgroup_kf_single_ops = { + .atomic_write_len = PAGE_SIZE, + .write = rdtgroup_file_write, + .seq_show = rdtgroup_seqfile_show, +}; + +static struct kernfs_ops kf_mondata_ops = { + .atomic_write_len = PAGE_SIZE, + .seq_show = rdtgroup_mondata_show, +}; + +static bool is_cpu_list(struct kernfs_open_file *of) +{ + struct rftype *rft = of->kn->priv; + + return rft->flags & RFTYPE_FLAGS_CPUS_LIST; +} + +static int rdtgroup_cpus_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct cpumask *mask; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + if (rdtgrp) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + mask = &rdtgrp->plr->d->cpu_mask; + seq_printf(s, is_cpu_list(of) ? + "%*pbl\n" : "%*pb\n", + cpumask_pr_args(mask)); + } + } else { + seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", + cpumask_pr_args(&rdtgrp->cpu_mask)); + } + } else { + ret = -ENOENT; + } + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +/* + * This is safe against resctrl_sched_in() called from __switch_to() + * because __switch_to() is executed with interrupts disabled. A local call + * from update_closid_rmid() is proteced against __switch_to() because + * preemption is disabled. + */ +static void update_cpu_closid_rmid(void *info) +{ + struct rdtgroup *r = info; + + if (r) { + this_cpu_write(pqr_state.default_closid, r->closid); + this_cpu_write(pqr_state.default_rmid, r->mon.rmid); + } + + /* + * We cannot unconditionally write the MSR because the current + * executing task might have its own closid selected. Just reuse + * the context switch code. + */ + resctrl_sched_in(current); +} + +/* + * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, + * + * Per task closids/rmids must have been set up before calling this function. + */ +static void +update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r) +{ + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, cpu_mask)) + update_cpu_closid_rmid(r); + smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1); + put_cpu(); +} + +static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp; + struct list_head *head; + + /* Check whether cpus belong to parent ctrl group */ + cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n"); + return -EINVAL; + } + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Give any dropped cpus to parent rdtgroup */ + cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask); + update_closid_rmid(tmpmask, prgrp); + } + + /* + * If we added cpus, remove them from previous group that owned them + * and update per-cpu rmid + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + if (crgrp == rdtgrp) + continue; + cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask, + tmpmask); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + return 0; +} + +static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m) +{ + struct rdtgroup *crgrp; + + cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m); + /* update the child mon group masks as well*/ + list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list) + cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask); +} + +static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask, cpumask_var_t tmpmask1) +{ + struct rdtgroup *r, *crgrp; + struct list_head *head; + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Can't drop from default group */ + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("Can't drop CPUs from default group\n"); + return -EINVAL; + } + + /* Give any dropped cpus to rdtgroup_default */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, tmpmask); + update_closid_rmid(tmpmask, &rdtgroup_default); + } + + /* + * If we added cpus, remove them from previous group and + * the prev group's child groups that owned them + * and update per-cpu closid/rmid. + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { + if (r == rdtgrp) + continue; + cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); + if (cpumask_weight(tmpmask1)) + cpumask_rdtgrp_clear(r, tmpmask1); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + /* + * Clear child mon group masks since there is a new parent mask + * now and update the rmid for the cpus the child lost. + */ + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask); + update_closid_rmid(tmpmask, rdtgrp); + cpumask_clear(&crgrp->cpu_mask); + } + + return 0; +} + +static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + cpumask_var_t tmpmask, newmask, tmpmask1; + struct rdtgroup *rdtgrp; + int ret; + + if (!buf) + return -EINVAL; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) { + free_cpumask_var(tmpmask); + return -ENOMEM; + } + if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) { + free_cpumask_var(tmpmask); + free_cpumask_var(newmask); + return -ENOMEM; + } + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto unlock; + } + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("Pseudo-locking in progress\n"); + goto unlock; + } + + if (is_cpu_list(of)) + ret = cpulist_parse(buf, newmask); + else + ret = cpumask_parse(buf, newmask); + + if (ret) { + rdt_last_cmd_puts("Bad CPU list/mask\n"); + goto unlock; + } + + /* check that user didn't specify any offline cpus */ + cpumask_andnot(tmpmask, newmask, cpu_online_mask); + if (cpumask_weight(tmpmask)) { + ret = -EINVAL; + rdt_last_cmd_puts("Can only assign online CPUs\n"); + goto unlock; + } + + if (rdtgrp->type == RDTCTRL_GROUP) + ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1); + else if (rdtgrp->type == RDTMON_GROUP) + ret = cpus_mon_write(rdtgrp, newmask, tmpmask); + else + ret = -EINVAL; + +unlock: + rdtgroup_kn_unlock(of->kn); + free_cpumask_var(tmpmask); + free_cpumask_var(newmask); + free_cpumask_var(tmpmask1); + + return ret ?: nbytes; +} + +/** + * rdtgroup_remove - the helper to remove resource group safely + * @rdtgrp: resource group to remove + * + * On resource group creation via a mkdir, an extra kernfs_node reference is + * taken to ensure that the rdtgroup structure remains accessible for the + * rdtgroup_kn_unlock() calls where it is removed. + * + * Drop the extra reference here, then free the rdtgroup structure. + * + * Return: void + */ +static void rdtgroup_remove(struct rdtgroup *rdtgrp) +{ + kernfs_put(rdtgrp->kn); + kfree(rdtgrp); +} + +static void _update_task_closid_rmid(void *task) +{ + /* + * If the task is still current on this CPU, update PQR_ASSOC MSR. + * Otherwise, the MSR is updated when the task is scheduled in. + */ + if (task == current) + resctrl_sched_in(task); +} + +static void update_task_closid_rmid(struct task_struct *t) +{ + if (IS_ENABLED(CONFIG_SMP) && task_curr(t)) + smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1); + else + _update_task_closid_rmid(t); +} + +static int __rdtgroup_move_task(struct task_struct *tsk, + struct rdtgroup *rdtgrp) +{ + /* If the task is already in rdtgrp, no need to move the task. */ + if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && + tsk->rmid == rdtgrp->mon.rmid) || + (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && + tsk->closid == rdtgrp->mon.parent->closid)) + return 0; + + /* + * Set the task's closid/rmid before the PQR_ASSOC MSR can be + * updated by them. + * + * For ctrl_mon groups, move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. + */ + + if (rdtgrp->type == RDTCTRL_GROUP) { + WRITE_ONCE(tsk->closid, rdtgrp->closid); + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) { + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; + } + } + + /* + * Ensure the task's closid and rmid are written before determining if + * the task is current that will decide if it will be interrupted. + * This pairs with the full barrier between the rq->curr update and + * resctrl_sched_in() during context switch. + */ + smp_mb(); + + /* + * By now, the task's closid and rmid are set. If the task is current + * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource + * group go into effect. If the task is not current, the MSR will be + * updated when the task is scheduled in. + */ + update_task_closid_rmid(tsk); + + return 0; +} + +static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_alloc_capable && + (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); +} + +static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_mon_capable && + (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); +} + +/** + * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group + * @r: Resource group + * + * Return: 1 if tasks have been assigned to @r, 0 otherwise + */ +int rdtgroup_tasks_assigned(struct rdtgroup *r) +{ + struct task_struct *p, *t; + int ret = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + rcu_read_lock(); + for_each_process_thread(p, t) { + if (is_closid_match(t, r) || is_rmid_match(t, r)) { + ret = 1; + break; + } + } + rcu_read_unlock(); + + return ret; +} + +static int rdtgroup_task_write_permission(struct task_struct *task, + struct kernfs_open_file *of) +{ + const struct cred *tcred = get_task_cred(task); + const struct cred *cred = current_cred(); + int ret = 0; + + /* + * Even if we're attaching all tasks in the thread group, we only + * need to check permissions on one of them. + */ + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) { + rdt_last_cmd_printf("No permission to move task %d\n", task->pid); + ret = -EPERM; + } + + put_cred(tcred); + return ret; +} + +static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp, + struct kernfs_open_file *of) +{ + struct task_struct *tsk; + int ret; + + rcu_read_lock(); + if (pid) { + tsk = find_task_by_vpid(pid); + if (!tsk) { + rcu_read_unlock(); + rdt_last_cmd_printf("No task %d\n", pid); + return -ESRCH; + } + } else { + tsk = current; + } + + get_task_struct(tsk); + rcu_read_unlock(); + + ret = rdtgroup_task_write_permission(tsk, of); + if (!ret) + ret = __rdtgroup_move_task(tsk, rdtgrp); + + put_task_struct(tsk); + return ret; +} + +static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + pid_t pid; + + if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) + return -EINVAL; + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + rdt_last_cmd_clear(); + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = -EINVAL; + rdt_last_cmd_puts("Pseudo-locking in progress\n"); + goto unlock; + } + + ret = rdtgroup_move_task(pid, rdtgrp, of); + +unlock: + rdtgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) +{ + struct task_struct *p, *t; + pid_t pid; + + rcu_read_lock(); + for_each_process_thread(p, t) { + if (is_closid_match(t, r) || is_rmid_match(t, r)) { + pid = task_pid_vnr(t); + if (pid) + seq_printf(s, "%d\n", pid); + } + } + rcu_read_unlock(); +} + +static int rdtgroup_tasks_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + show_rdt_tasks(rdtgrp, s); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +#ifdef CONFIG_PROC_CPU_RESCTRL + +/* + * A task can only be part of one resctrl control group and of one monitor + * group which is associated to that control group. + * + * 1) res: + * mon: + * + * resctrl is not available. + * + * 2) res:/ + * mon: + * + * Task is part of the root resctrl control group, and it is not associated + * to any monitor group. + * + * 3) res:/ + * mon:mon0 + * + * Task is part of the root resctrl control group and monitor group mon0. + * + * 4) res:group0 + * mon: + * + * Task is part of resctrl control group group0, and it is not associated + * to any monitor group. + * + * 5) res:group0 + * mon:mon1 + * + * Task is part of resctrl control group group0 and monitor group mon1. + */ +int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + struct rdtgroup *rdtg; + int ret = 0; + + mutex_lock(&rdtgroup_mutex); + + /* Return empty if resctrl has not been mounted. */ + if (!static_branch_unlikely(&rdt_enable_key)) { + seq_puts(s, "res:\nmon:\n"); + goto unlock; + } + + list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) { + struct rdtgroup *crg; + + /* + * Task information is only relevant for shareable + * and exclusive groups. + */ + if (rdtg->mode != RDT_MODE_SHAREABLE && + rdtg->mode != RDT_MODE_EXCLUSIVE) + continue; + + if (rdtg->closid != tsk->closid) + continue; + + seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", + rdtg->kn->name); + seq_puts(s, "mon:"); + list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, + mon.crdtgrp_list) { + if (tsk->rmid != crg->mon.rmid) + continue; + seq_printf(s, "%s", crg->kn->name); + break; + } + seq_putc(s, '\n'); + goto unlock; + } + /* + * The above search should succeed. Otherwise return + * with an error. + */ + ret = -ENOENT; +unlock: + mutex_unlock(&rdtgroup_mutex); + + return ret; +} +#endif + +static int rdt_last_cmd_status_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + int len; + + mutex_lock(&rdtgroup_mutex); + len = seq_buf_used(&last_cmd_status); + if (len) + seq_printf(seq, "%.*s", len, last_cmd_status_buf); + else + seq_puts(seq, "ok\n"); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static int rdt_num_closids_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->num_closid); + return 0; +} + +static int rdt_default_ctrl_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%x\n", r->default_ctrl); + return 0; +} + +static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", r->cache.min_cbm_bits); + return 0; +} + +static int rdt_shareable_bits_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%x\n", r->cache.shareable_bits); + return 0; +} + +/** + * rdt_bit_usage_show - Display current usage of resources + * + * A domain is a shared resource that can now be allocated differently. Here + * we display the current regions of the domain as an annotated bitmask. + * For each domain of this resource its allocation bitmask + * is annotated as below to indicate the current usage of the corresponding bit: + * 0 - currently unused + * X - currently available for sharing and used by software and hardware + * H - currently used by hardware only but available for software use + * S - currently used and shareable by software only + * E - currently used exclusively by one resource group + * P - currently pseudo-locked by one resource group + */ +static int rdt_bit_usage_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + /* + * Use unsigned long even though only 32 bits are used to ensure + * test_bit() is used safely. + */ + unsigned long sw_shareable = 0, hw_shareable = 0; + unsigned long exclusive = 0, pseudo_locked = 0; + struct rdt_domain *dom; + int i, hwb, swb, excl, psl; + enum rdtgrp_mode mode; + bool sep = false; + u32 *ctrl; + + mutex_lock(&rdtgroup_mutex); + hw_shareable = r->cache.shareable_bits; + list_for_each_entry(dom, &r->domains, list) { + if (sep) + seq_putc(seq, ';'); + ctrl = dom->ctrl_val; + sw_shareable = 0; + exclusive = 0; + seq_printf(seq, "%d=", dom->id); + for (i = 0; i < closids_supported(); i++, ctrl++) { + if (!closid_allocated(i)) + continue; + mode = rdtgroup_mode_by_closid(i); + switch (mode) { + case RDT_MODE_SHAREABLE: + sw_shareable |= *ctrl; + break; + case RDT_MODE_EXCLUSIVE: + exclusive |= *ctrl; + break; + case RDT_MODE_PSEUDO_LOCKSETUP: + /* + * RDT_MODE_PSEUDO_LOCKSETUP is possible + * here but not included since the CBM + * associated with this CLOSID in this mode + * is not initialized and no task or cpu can be + * assigned this CLOSID. + */ + break; + case RDT_MODE_PSEUDO_LOCKED: + case RDT_NUM_MODES: + WARN(1, + "invalid mode for closid %d\n", i); + break; + } + } + for (i = r->cache.cbm_len - 1; i >= 0; i--) { + pseudo_locked = dom->plr ? dom->plr->cbm : 0; + hwb = test_bit(i, &hw_shareable); + swb = test_bit(i, &sw_shareable); + excl = test_bit(i, &exclusive); + psl = test_bit(i, &pseudo_locked); + if (hwb && swb) + seq_putc(seq, 'X'); + else if (hwb && !swb) + seq_putc(seq, 'H'); + else if (!hwb && swb) + seq_putc(seq, 'S'); + else if (excl) + seq_putc(seq, 'E'); + else if (psl) + seq_putc(seq, 'P'); + else /* Unused bits remain */ + seq_putc(seq, '0'); + } + sep = true; + } + seq_putc(seq, '\n'); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + +static int rdt_min_bw_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", r->membw.min_bw); + return 0; +} + +static int rdt_num_rmids_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->num_rmid); + + return 0; +} + +static int rdt_mon_features_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + struct mon_evt *mevt; + + list_for_each_entry(mevt, &r->evt_list, list) + seq_printf(seq, "%s\n", mevt->name); + + return 0; +} + +static int rdt_bw_gran_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", r->membw.bw_gran); + return 0; +} + +static int rdt_delay_linear_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", r->membw.delay_linear); + return 0; +} + +static int max_threshold_occ_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", resctrl_cqm_threshold * r->mon_scale); + + return 0; +} + +static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD) + seq_puts(seq, "per-thread\n"); + else + seq_puts(seq, "max\n"); + + return 0; +} + +static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdt_resource *r = of->kn->parent->priv; + unsigned int bytes; + int ret; + + ret = kstrtouint(buf, 0, &bytes); + if (ret) + return ret; + + if (bytes > (boot_cpu_data.x86_cache_size * 1024)) + return -EINVAL; + + resctrl_cqm_threshold = bytes / r->mon_scale; + + return nbytes; +} + +/* + * rdtgroup_mode_show - Display mode of this resource group + */ +static int rdtgroup_mode_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode)); + + rdtgroup_kn_unlock(of->kn); + return 0; +} + +/** + * rdt_cdp_peer_get - Retrieve CDP peer if it exists + * @r: RDT resource to which RDT domain @d belongs + * @d: Cache instance for which a CDP peer is requested + * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer) + * Used to return the result. + * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer) + * Used to return the result. + * + * RDT resources are managed independently and by extension the RDT domains + * (RDT resource instances) are managed independently also. The Code and + * Data Prioritization (CDP) RDT resources, while managed independently, + * could refer to the same underlying hardware. For example, + * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache. + * + * When provided with an RDT resource @r and an instance of that RDT + * resource @d rdt_cdp_peer_get() will return if there is a peer RDT + * resource and the exact instance that shares the same hardware. + * + * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists. + * If a CDP peer was found, @r_cdp will point to the peer RDT resource + * and @d_cdp will point to the peer RDT domain. + */ +static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, + struct rdt_resource **r_cdp, + struct rdt_domain **d_cdp) +{ + struct rdt_resource *_r_cdp = NULL; + struct rdt_domain *_d_cdp = NULL; + int ret = 0; + + switch (r->rid) { + case RDT_RESOURCE_L3DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + break; + case RDT_RESOURCE_L3CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + break; + case RDT_RESOURCE_L2DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE]; + break; + case RDT_RESOURCE_L2CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA]; + break; + default: + ret = -ENOENT; + goto out; + } + + /* + * When a new CPU comes online and CDP is enabled then the new + * RDT domains (if any) associated with both CDP RDT resources + * are added in the same CPU online routine while the + * rdtgroup_mutex is held. It should thus not happen for one + * RDT domain to exist and be associated with its RDT CDP + * resource but there is no RDT domain associated with the + * peer RDT CDP resource. Hence the WARN. + */ + _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); + if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { + _r_cdp = NULL; + _d_cdp = NULL; + ret = -EINVAL; + } + +out: + *r_cdp = _r_cdp; + *d_cdp = _d_cdp; + + return ret; +} + +/** + * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Checks if provided @cbm intended to be used for @closid on domain + * @d overlaps with any other closids or other hardware usage associated + * with this domain. If @exclusive is true then only overlaps with + * resource groups in exclusive mode will be considered. If @exclusive + * is false then overlaps with any resource group or hardware entities + * will be considered. + * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: false if CBM does not overlap, true if it does. + */ +static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) +{ + enum rdtgrp_mode mode; + unsigned long ctrl_b; + u32 *ctrl; + int i; + + /* Check for any overlap with regions used by hardware directly */ + if (!exclusive) { + ctrl_b = r->cache.shareable_bits; + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) + return true; + } + + /* Check for overlap with other resource groups */ + ctrl = d->ctrl_val; + for (i = 0; i < closids_supported(); i++, ctrl++) { + ctrl_b = *ctrl; + mode = rdtgroup_mode_by_closid(i); + if (closid_allocated(i) && i != closid && + mode != RDT_MODE_PSEUDO_LOCKSETUP) { + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) { + if (exclusive) { + if (mode == RDT_MODE_EXCLUSIVE) + return true; + continue; + } + return true; + } + } + } + + return false; +} + +/** + * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Resources that can be allocated using a CBM can use the CBM to control + * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test + * for overlap. Overlap test is not limited to the specific resource for + * which the CBM is intended though - when dealing with CDP resources that + * share the underlying hardware the overlap check should be performed on + * the CDP resource sharing the hardware also. + * + * Refer to description of __rdtgroup_cbm_overlaps() for the details of the + * overlap test. + * + * Return: true if CBM overlap detected, false if there is no overlap + */ +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) +{ + struct rdt_resource *r_cdp; + struct rdt_domain *d_cdp; + + if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive)) + return true; + + if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0) + return false; + + return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive); +} + +/** + * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * + * An exclusive resource group implies that there should be no sharing of + * its allocated resources. At the time this group is considered to be + * exclusive this test can determine if its current schemata supports this + * setting by testing for overlap with all other resource groups. + * + * Return: true if resource group can be exclusive, false if there is overlap + * with allocations of other resource groups and thus this resource group + * cannot be exclusive. + */ +static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) +{ + int closid = rdtgrp->closid; + struct rdt_resource *r; + bool has_cache = false; + struct rdt_domain *d; + + for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) + continue; + has_cache = true; + list_for_each_entry(d, &r->domains, list) { + if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], + rdtgrp->closid, false)) { + rdt_last_cmd_puts("Schemata overlaps\n"); + return false; + } + } + } + + if (!has_cache) { + rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n"); + return false; + } + + return true; +} + +/** + * rdtgroup_mode_write - Modify the resource group's mode + * + */ +static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + enum rdtgrp_mode mode; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + rdt_last_cmd_clear(); + + mode = rdtgrp->mode; + + if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) || + (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) || + (!strcmp(buf, "pseudo-locksetup") && + mode == RDT_MODE_PSEUDO_LOCKSETUP) || + (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED)) + goto out; + + if (mode == RDT_MODE_PSEUDO_LOCKED) { + rdt_last_cmd_puts("Cannot change pseudo-locked group\n"); + ret = -EINVAL; + goto out; + } + + if (!strcmp(buf, "shareable")) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_SHAREABLE; + } else if (!strcmp(buf, "exclusive")) { + if (!rdtgroup_mode_test_exclusive(rdtgrp)) { + ret = -EINVAL; + goto out; + } + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + ret = rdtgroup_locksetup_exit(rdtgrp); + if (ret) + goto out; + } + rdtgrp->mode = RDT_MODE_EXCLUSIVE; + } else if (!strcmp(buf, "pseudo-locksetup")) { + ret = rdtgroup_locksetup_enter(rdtgrp); + if (ret) + goto out; + rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP; + } else { + rdt_last_cmd_puts("Unknown or unsupported mode\n"); + ret = -EINVAL; + } + +out: + rdtgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +/** + * rdtgroup_cbm_to_size - Translate CBM to size in bytes + * @r: RDT resource to which @d belongs. + * @d: RDT domain instance. + * @cbm: bitmask for which the size should be computed. + * + * The bitmask provided associated with the RDT domain instance @d will be + * translated into how many bytes it represents. The size in bytes is + * computed by first dividing the total cache size by the CBM length to + * determine how many bytes each bit in the bitmask represents. The result + * is multiplied with the number of bits set in the bitmask. + * + * @cbm is unsigned long, even if only 32 bits are used to make the + * bitmap functions work correctly. + */ +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, + struct rdt_domain *d, unsigned long cbm) +{ + struct cpu_cacheinfo *ci; + unsigned int size = 0; + int num_b, i; + + num_b = bitmap_weight(&cbm, r->cache.cbm_len); + ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); + for (i = 0; i < ci->num_leaves; i++) { + if (ci->info_list[i].level == r->cache_level) { + size = ci->info_list[i].size / r->cache.cbm_len * num_b; + break; + } + } + + return size; +} + +/** + * rdtgroup_size_show - Display size in bytes of allocated regions + * + * The "size" file mirrors the layout of the "schemata" file, printing the + * size in bytes of each region instead of the capacity bitmask. + * + */ +static int rdtgroup_size_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + struct rdt_domain *d; + unsigned int size; + int ret = 0; + bool sep; + u32 ctrl; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%*s:", max_name_width, + rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + } + goto out; + } + + for_each_alloc_enabled_rdt_resource(r) { + sep = false; + seq_printf(s, "%*s:", max_name_width, r->name); + list_for_each_entry(d, &r->domains, list) { + if (sep) + seq_putc(s, ';'); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + size = 0; + } else { + ctrl = (!is_mba_sc(r) ? + d->ctrl_val[rdtgrp->closid] : + d->mbps_val[rdtgrp->closid]); + if (r->rid == RDT_RESOURCE_MBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); + } + seq_printf(s, "%d=%u", d->id, size); + sep = true; + } + seq_putc(s, '\n'); + } + +out: + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +/* rdtgroup information files for one cache resource. */ +static struct rftype res_common_files[] = { + { + .name = "last_cmd_status", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_last_cmd_status_show, + .fflags = RF_TOP_INFO, + }, + { + .name = "num_closids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_closids_show, + .fflags = RF_CTRL_INFO, + }, + { + .name = "mon_features", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_mon_features_show, + .fflags = RF_MON_INFO, + }, + { + .name = "num_rmids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_rmids_show, + .fflags = RF_MON_INFO, + }, + { + .name = "cbm_mask", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_default_ctrl_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "min_cbm_bits", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_min_cbm_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "shareable_bits", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_shareable_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "bit_usage", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bit_usage_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "min_bandwidth", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_min_bw_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + }, + { + .name = "bandwidth_gran", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bw_gran_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + }, + { + .name = "delay_linear", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_delay_linear_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + }, + /* + * Platform specific which (if any) capabilities are provided by + * thread_throttle_mode. Defer "fflags" initialization to platform + * discovery. + */ + { + .name = "thread_throttle_mode", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_thread_throttle_mode_show, + }, + { + .name = "max_threshold_occupancy", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = max_threshold_occ_write, + .seq_show = max_threshold_occ_show, + .fflags = RF_MON_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "cpus", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "cpus_list", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .flags = RFTYPE_FLAGS_CPUS_LIST, + .fflags = RFTYPE_BASE, + }, + { + .name = "tasks", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_tasks_write, + .seq_show = rdtgroup_tasks_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "schemata", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_schemata_write, + .seq_show = rdtgroup_schemata_show, + .fflags = RF_CTRL_BASE, + }, + { + .name = "mode", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mode_write, + .seq_show = rdtgroup_mode_show, + .fflags = RF_CTRL_BASE, + }, + { + .name = "size", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_size_show, + .fflags = RF_CTRL_BASE, + }, + +}; + +static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) +{ + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + lockdep_assert_held(&rdtgroup_mutex); + + for (rft = rfts; rft < rfts + len; rft++) { + if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) { + ret = rdtgroup_add_file(kn, rft); + if (ret) + goto error; + } + } + + return 0; +error: + pr_warn("Failed to add %s, err=%d\n", rft->name, ret); + while (--rft >= rfts) { + if ((fflags & rft->fflags) == rft->fflags) + kernfs_remove_by_name(kn, rft->name); + } + return ret; +} + +static struct rftype *rdtgroup_get_rftype_by_name(const char *name) +{ + struct rftype *rfts, *rft; + int len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + for (rft = rfts; rft < rfts + len; rft++) { + if (!strcmp(rft->name, name)) + return rft; + } + + return NULL; +} + +void __init thread_throttle_mode_init(void) +{ + struct rftype *rft; + + rft = rdtgroup_get_rftype_by_name("thread_throttle_mode"); + if (!rft) + return; + + rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB; +} + +/** + * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * + * The permissions of named resctrl file, directory, or link are modified + * to not allow read, write, or execute by any user. + * + * WARNING: This function is intended to communicate to the user that the + * resctrl file has been locked down - that it is not relevant to the + * particular state the system finds itself in. It should not be relied + * on to protect from user access because after the file's permissions + * are restricted the user can still change the permissions using chmod + * from the command line. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn; + int ret = 0; + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + iattr.ia_mode = S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode = S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode = S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + +/** + * rdtgroup_kn_mode_restore - Restore user access to named resctrl file + * @r: The resource group with which the file is associated. + * @name: Name of the file + * @mask: Mask of permissions that should be restored + * + * Restore the permissions of the named file. If @name is a directory the + * permissions of its parent will be used. + * + * Return: 0 on success, <0 on failure. + */ +int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name, + umode_t mask) +{ + struct iattr iattr = {.ia_valid = ATTR_MODE,}; + struct kernfs_node *kn, *parent; + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + for (rft = rfts; rft < rfts + len; rft++) { + if (!strcmp(rft->name, name)) + iattr.ia_mode = rft->mode & mask; + } + + kn = kernfs_find_and_get_ns(r->kn, name, NULL); + if (!kn) + return -ENOENT; + + switch (kernfs_type(kn)) { + case KERNFS_DIR: + parent = kernfs_get_parent(kn); + if (parent) { + iattr.ia_mode |= parent->mode; + kernfs_put(parent); + } + iattr.ia_mode |= S_IFDIR; + break; + case KERNFS_FILE: + iattr.ia_mode |= S_IFREG; + break; + case KERNFS_LINK: + iattr.ia_mode |= S_IFLNK; + break; + } + + ret = kernfs_setattr(kn, &iattr); + kernfs_put(kn); + return ret; +} + +static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, + unsigned long fflags) +{ + struct kernfs_node *kn_subdir; + int ret; + + kn_subdir = kernfs_create_dir(kn_info, name, + kn_info->mode, r); + if (IS_ERR(kn_subdir)) + return PTR_ERR(kn_subdir); + + ret = rdtgroup_kn_set_ugid(kn_subdir); + if (ret) + return ret; + + ret = rdtgroup_add_files(kn_subdir, fflags); + if (!ret) + kernfs_activate(kn_subdir); + + return ret; +} + +static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) +{ + struct rdt_resource *r; + unsigned long fflags; + char name[32]; + int ret; + + /* create the directory */ + kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); + if (IS_ERR(kn_info)) + return PTR_ERR(kn_info); + + ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); + if (ret) + goto out_destroy; + + for_each_alloc_enabled_rdt_resource(r) { + fflags = r->fflags | RF_CTRL_INFO; + ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags); + if (ret) + goto out_destroy; + } + + for_each_mon_enabled_rdt_resource(r) { + fflags = r->fflags | RF_MON_INFO; + sprintf(name, "%s_MON", r->name); + ret = rdtgroup_mkdir_info_resdir(r, name, fflags); + if (ret) + goto out_destroy; + } + + ret = rdtgroup_kn_set_ugid(kn_info); + if (ret) + goto out_destroy; + + kernfs_activate(kn_info); + + return 0; + +out_destroy: + kernfs_remove(kn_info); + return ret; +} + +static int +mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, + char *name, struct kernfs_node **dest_kn) +{ + struct kernfs_node *kn; + int ret; + + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + if (dest_kn) + *dest_kn = kn; + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + kernfs_activate(kn); + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +static void l3_qos_cfg_update(void *arg) +{ + bool *enable = arg; + + wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL); +} + +static void l2_qos_cfg_update(void *arg) +{ + bool *enable = arg; + + wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL); +} + +static inline bool is_mba_linear(void) +{ + return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear; +} + +static int set_cache_qos_cfg(int level, bool enable) +{ + void (*update)(void *arg); + struct rdt_resource *r_l; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int cpu; + + if (level == RDT_RESOURCE_L3) + update = l3_qos_cfg_update; + else if (level == RDT_RESOURCE_L2) + update = l2_qos_cfg_update; + else + return -EINVAL; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + r_l = &rdt_resources_all[level]; + list_for_each_entry(d, &r_l->domains, list) { + if (r_l->cache.arch_has_per_cpu_cfg) + /* Pick all the CPUs in the domain instance */ + for_each_cpu(cpu, &d->cpu_mask) + cpumask_set_cpu(cpu, cpu_mask); + else + /* Pick one CPU from each domain instance to update MSR */ + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + } + cpu = get_cpu(); + /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + update(&enable); + /* Update QOS_CFG MSR on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, update, &enable, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +/* Restore the qos cfg state when a domain comes online */ +void rdt_domain_reconfigure_cdp(struct rdt_resource *r) +{ + if (!r->alloc_capable) + return; + + if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) + l2_qos_cfg_update(&r->alloc_enabled); + + if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) + l3_qos_cfg_update(&r->alloc_enabled); +} + +/* + * Enable or disable the MBA software controller + * which helps user specify bandwidth in MBps. + * MBA software controller is supported only if + * MBM is supported and MBA is in linear scale. + */ +static int set_mba_sc(bool mba_sc) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA]; + struct rdt_domain *d; + + if (!is_mbm_enabled() || !is_mba_linear() || + mba_sc == is_mba_sc(r)) + return -EINVAL; + + r->membw.mba_sc = mba_sc; + list_for_each_entry(d, &r->domains, list) + setup_default_ctrlval(r, d->ctrl_val, d->mbps_val); + + return 0; +} + +static int cdp_enable(int level, int data_type, int code_type) +{ + struct rdt_resource *r_ldata = &rdt_resources_all[data_type]; + struct rdt_resource *r_lcode = &rdt_resources_all[code_type]; + struct rdt_resource *r_l = &rdt_resources_all[level]; + int ret; + + if (!r_l->alloc_capable || !r_ldata->alloc_capable || + !r_lcode->alloc_capable) + return -EINVAL; + + ret = set_cache_qos_cfg(level, true); + if (!ret) { + r_l->alloc_enabled = false; + r_ldata->alloc_enabled = true; + r_lcode->alloc_enabled = true; + } + return ret; +} + +static int cdpl3_enable(void) +{ + return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, + RDT_RESOURCE_L3CODE); +} + +static int cdpl2_enable(void) +{ + return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, + RDT_RESOURCE_L2CODE); +} + +static void cdp_disable(int level, int data_type, int code_type) +{ + struct rdt_resource *r = &rdt_resources_all[level]; + + r->alloc_enabled = r->alloc_capable; + + if (rdt_resources_all[data_type].alloc_enabled) { + rdt_resources_all[data_type].alloc_enabled = false; + rdt_resources_all[code_type].alloc_enabled = false; + set_cache_qos_cfg(level, false); + } +} + +static void cdpl3_disable(void) +{ + cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE); +} + +static void cdpl2_disable(void) +{ + cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE); +} + +static void cdp_disable_all(void) +{ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) + cdpl3_disable(); + if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + cdpl2_disable(); +} + +/* + * We don't allow rdtgroup directories to be created anywhere + * except the root directory. Thus when looking for the rdtgroup + * structure for a kernfs node we are either looking at a directory, + * in which case the rdtgroup structure is pointed at by the "priv" + * field, otherwise we have a file, and need only look to the parent + * to find the rdtgroup. + */ +static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) +{ + if (kernfs_type(kn) == KERNFS_DIR) { + /* + * All the resource directories use "kn->priv" + * to point to the "struct rdtgroup" for the + * resource. "info" and its subdirectories don't + * have rdtgroup structures, so return NULL here. + */ + if (kn == kn_info || kn->parent == kn_info) + return NULL; + else + return kn->priv; + } else { + return kn->parent->priv; + } +} + +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) +{ + struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); + + if (!rdtgrp) + return NULL; + + atomic_inc(&rdtgrp->waitcount); + kernfs_break_active_protection(kn); + + mutex_lock(&rdtgroup_mutex); + + /* Was this group deleted while we waited? */ + if (rdtgrp->flags & RDT_DELETED) + return NULL; + + return rdtgrp; +} + +void rdtgroup_kn_unlock(struct kernfs_node *kn) +{ + struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); + + if (!rdtgrp) + return; + + mutex_unlock(&rdtgroup_mutex); + + if (atomic_dec_and_test(&rdtgrp->waitcount) && + (rdtgrp->flags & RDT_DELETED)) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + kernfs_unbreak_active_protection(kn); + rdtgroup_remove(rdtgrp); + } else { + kernfs_unbreak_active_protection(kn); + } +} + +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **mon_data_kn); + +static int rdt_enable_ctx(struct rdt_fs_context *ctx) +{ + int ret = 0; + + if (ctx->enable_cdpl2) + ret = cdpl2_enable(); + + if (!ret && ctx->enable_cdpl3) + ret = cdpl3_enable(); + + if (!ret && ctx->enable_mba_mbps) + ret = set_mba_sc(true); + + return ret; +} + +static int rdt_get_tree(struct fs_context *fc) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + struct rdt_domain *dom; + struct rdt_resource *r; + int ret; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + /* + * resctrl file system can only be mounted once. + */ + if (static_branch_unlikely(&rdt_enable_key)) { + ret = -EBUSY; + goto out; + } + + ret = rdt_enable_ctx(ctx); + if (ret < 0) + goto out_cdp; + + closid_init(); + + ret = rdtgroup_create_info_dir(rdtgroup_default.kn); + if (ret < 0) + goto out_mba; + + if (rdt_mon_capable) { + ret = mongroup_create_dir(rdtgroup_default.kn, + &rdtgroup_default, "mon_groups", + &kn_mongrp); + if (ret < 0) + goto out_info; + + ret = mkdir_mondata_all(rdtgroup_default.kn, + &rdtgroup_default, &kn_mondata); + if (ret < 0) + goto out_mongrp; + rdtgroup_default.mon.mon_data_kn = kn_mondata; + } + + ret = rdt_pseudo_lock_init(); + if (ret) + goto out_mondata; + + ret = kernfs_get_tree(fc); + if (ret < 0) + goto out_psl; + + if (rdt_alloc_capable) + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); + if (rdt_mon_capable) + static_branch_enable_cpuslocked(&rdt_mon_enable_key); + + if (rdt_alloc_capable || rdt_mon_capable) + static_branch_enable_cpuslocked(&rdt_enable_key); + + if (is_mbm_enabled()) { + r = &rdt_resources_all[RDT_RESOURCE_L3]; + list_for_each_entry(dom, &r->domains, list) + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); + } + + goto out; + +out_psl: + rdt_pseudo_lock_release(); +out_mondata: + if (rdt_mon_capable) + kernfs_remove(kn_mondata); +out_mongrp: + if (rdt_mon_capable) + kernfs_remove(kn_mongrp); +out_info: + kernfs_remove(kn_info); +out_mba: + if (ctx->enable_mba_mbps) + set_mba_sc(false); +out_cdp: + cdp_disable_all(); +out: + rdt_last_cmd_clear(); + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +enum rdt_param { + Opt_cdp, + Opt_cdpl2, + Opt_mba_mbps, + nr__rdt_params +}; + +static const struct fs_parameter_spec rdt_fs_parameters[] = { + fsparam_flag("cdp", Opt_cdp), + fsparam_flag("cdpl2", Opt_cdpl2), + fsparam_flag("mba_MBps", Opt_mba_mbps), + {} +}; + +static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, rdt_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_cdp: + ctx->enable_cdpl3 = true; + return 0; + case Opt_cdpl2: + ctx->enable_cdpl2 = true; + return 0; + case Opt_mba_mbps: + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return -EINVAL; + ctx->enable_mba_mbps = true; + return 0; + } + + return -EINVAL; +} + +static void rdt_fs_context_free(struct fs_context *fc) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + + kernfs_free_fs_context(fc); + kfree(ctx); +} + +static const struct fs_context_operations rdt_fs_context_ops = { + .free = rdt_fs_context_free, + .parse_param = rdt_parse_param, + .get_tree = rdt_get_tree, +}; + +static int rdt_init_fs_context(struct fs_context *fc) +{ + struct rdt_fs_context *ctx; + + ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->kfc.root = rdt_root; + ctx->kfc.magic = RDTGROUP_SUPER_MAGIC; + fc->fs_private = &ctx->kfc; + fc->ops = &rdt_fs_context_ops; + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(&init_user_ns); + fc->global = true; + return 0; +} + +static int reset_all_ctrls(struct rdt_resource *r) +{ + struct msr_param msr_param; + cpumask_var_t cpu_mask; + struct rdt_domain *d; + int i, cpu; + + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + + msr_param.res = r; + msr_param.low = 0; + msr_param.high = r->num_closid; + + /* + * Disable resource control for this resource by setting all + * CBMs in all domains to the maximum mask value. Pick one CPU + * from each domain to update the MSRs below. + */ + list_for_each_entry(d, &r->domains, list) { + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + + for (i = 0; i < r->num_closid; i++) + d->ctrl_val[i] = r->default_ctrl; + } + cpu = get_cpu(); + /* Update CBM on this cpu if it's in cpu_mask. */ + if (cpumask_test_cpu(cpu, cpu_mask)) + rdt_ctrl_update(&msr_param); + /* Update CBM on all other cpus in cpu_mask. */ + smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1); + put_cpu(); + + free_cpumask_var(cpu_mask); + + return 0; +} + +/* + * Move tasks from one to the other group. If @from is NULL, then all tasks + * in the systems are moved unconditionally (used for teardown). + * + * If @mask is not NULL the cpus on which moved tasks are running are set + * in that mask so the update smp function call is restricted to affected + * cpus. + */ +static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, + struct cpumask *mask) +{ + struct task_struct *p, *t; + + read_lock(&tasklist_lock); + for_each_process_thread(p, t) { + if (!from || is_closid_match(t, from) || + is_rmid_match(t, from)) { + WRITE_ONCE(t->closid, to->closid); + WRITE_ONCE(t->rmid, to->mon.rmid); + + /* + * Order the closid/rmid stores above before the loads + * in task_curr(). This pairs with the full barrier + * between the rq->curr update and resctrl_sched_in() + * during context switch. + */ + smp_mb(); + + /* + * If the task is on a CPU, set the CPU in the mask. + * The detection is inaccurate as tasks might move or + * schedule before the smp function call takes place. + * In such a case the function call is pointless, but + * there is no other side effect. + */ + if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t)) + cpumask_set_cpu(task_cpu(t), mask); + } + } + read_unlock(&tasklist_lock); +} + +static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) +{ + struct rdtgroup *sentry, *stmp; + struct list_head *head; + + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { + free_rmid(sentry->mon.rmid); + list_del(&sentry->mon.crdtgrp_list); + + if (atomic_read(&sentry->waitcount) != 0) + sentry->flags = RDT_DELETED; + else + rdtgroup_remove(sentry); + } +} + +/* + * Forcibly remove all of subdirectories under root. + */ +static void rmdir_all_sub(void) +{ + struct rdtgroup *rdtgrp, *tmp; + + /* Move all tasks to the default resource group */ + rdt_move_group_tasks(NULL, &rdtgroup_default, NULL); + + list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) { + /* Free any child rmids */ + free_all_child_rdtgrp(rdtgrp); + + /* Remove each rdtgroup other than root */ + if (rdtgrp == &rdtgroup_default) + continue; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) + rdtgroup_pseudo_lock_remove(rdtgrp); + + /* + * Give any CPUs back to the default group. We cannot copy + * cpu_online_mask because a CPU might have executed the + * offline callback already, but is still marked online. + */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + + free_rmid(rdtgrp->mon.rmid); + + kernfs_remove(rdtgrp->kn); + list_del(&rdtgrp->rdtgroup_list); + + if (atomic_read(&rdtgrp->waitcount) != 0) + rdtgrp->flags = RDT_DELETED; + else + rdtgroup_remove(rdtgrp); + } + /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ + update_closid_rmid(cpu_online_mask, &rdtgroup_default); + + kernfs_remove(kn_info); + kernfs_remove(kn_mongrp); + kernfs_remove(kn_mondata); +} + +static void rdt_kill_sb(struct super_block *sb) +{ + struct rdt_resource *r; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + set_mba_sc(false); + + /*Put everything back to default values. */ + for_each_alloc_enabled_rdt_resource(r) + reset_all_ctrls(r); + cdp_disable_all(); + rmdir_all_sub(); + rdt_pseudo_lock_release(); + rdtgroup_default.mode = RDT_MODE_SHAREABLE; + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_disable_cpuslocked(&rdt_enable_key); + kernfs_kill_sb(sb); + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); +} + +static struct file_system_type rdt_fs_type = { + .name = "resctrl", + .init_fs_context = rdt_init_fs_context, + .parameters = rdt_fs_parameters, + .kill_sb = rdt_kill_sb, +}; + +static int mon_addfile(struct kernfs_node *parent_kn, const char *name, + void *priv) +{ + struct kernfs_node *kn; + int ret = 0; + + kn = __kernfs_create_file(parent_kn, name, 0444, + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, + &kf_mondata_ops, priv, NULL, NULL); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } + + return ret; +} + +/* + * Remove all subdirectories of mon_data of ctrl_mon groups + * and monitor groups with given domain id. + */ +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id) +{ + struct rdtgroup *prgrp, *crgrp; + char name[32]; + + if (!r->mon_enabled) + return; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + sprintf(name, "mon_%s_%02d", r->name, dom_id); + 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); + } +} + +static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, + struct rdt_domain *d, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + union mon_data_bits priv; + struct kernfs_node *kn; + struct mon_evt *mevt; + struct rmid_read rr; + char name[32]; + int ret; + + sprintf(name, "mon_%s_%02d", r->name, d->id); + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + if (WARN_ON(list_empty(&r->evt_list))) { + ret = -EPERM; + goto out_destroy; + } + + priv.u.rid = r->rid; + priv.u.domid = d->id; + list_for_each_entry(mevt, &r->evt_list, list) { + priv.u.evtid = mevt->evtid; + ret = mon_addfile(kn, mevt->name, priv.priv); + if (ret) + goto out_destroy; + + if (is_mbm_event(mevt->evtid)) + mon_event_read(&rr, r, d, prgrp, mevt->evtid, true); + } + kernfs_activate(kn); + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +/* + * Add all subdirectories of mon_data for "ctrl_mon" groups + * and "monitor" groups with given domain id. + */ +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d) +{ + struct kernfs_node *parent_kn; + struct rdtgroup *prgrp, *crgrp; + struct list_head *head; + + if (!r->mon_enabled) + return; + + 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); + + 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); + } + } +} + +static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, + struct rdt_resource *r, + struct rdtgroup *prgrp) +{ + struct rdt_domain *dom; + int ret; + + list_for_each_entry(dom, &r->domains, list) { + ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); + if (ret) + return ret; + } + + return 0; +} + +/* + * This creates a directory mon_data which contains the monitored data. + * + * mon_data has one directory for each domain whic are named + * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data + * with L3 domain looks as below: + * ./mon_data: + * mon_L3_00 + * mon_L3_01 + * mon_L3_02 + * ... + * + * Each domain directory has one file per event: + * ./mon_L3_00/: + * llc_occupancy + * + */ +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **dest_kn) +{ + struct rdt_resource *r; + struct kernfs_node *kn; + int ret; + + /* + * Create the mon_data directory first. + */ + ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn); + if (ret) + return ret; + + if (dest_kn) + *dest_kn = kn; + + /* + * Create the subdirectories for each domain. Note that all events + * in a domain like L3 are grouped into a resource whose domain is L3 + */ + for_each_mon_enabled_rdt_resource(r) { + ret = mkdir_mondata_subdir_alldom(kn, r, prgrp); + if (ret) + goto out_destroy; + } + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +/** + * cbm_ensure_valid - Enforce validity on provided CBM + * @_val: Candidate CBM + * @r: RDT resource to which the CBM belongs + * + * The provided CBM represents all cache portions available for use. This + * may be represented by a bitmap that does not consist of contiguous ones + * and thus be an invalid CBM. + * Here the provided CBM is forced to be a valid CBM by only considering + * the first set of contiguous bits as valid and clearing all bits. + * The intention here is to provide a valid default CBM with which a new + * resource group is initialized. The user can follow this with a + * modification to the CBM if the default does not satisfy the + * requirements. + */ +static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r) +{ + unsigned int cbm_len = r->cache.cbm_len; + unsigned long first_bit, zero_bit; + unsigned long val = _val; + + if (!val) + return 0; + + first_bit = find_first_bit(&val, cbm_len); + zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); + + /* Clear any remaining bits to ensure contiguous region */ + bitmap_clear(&val, zero_bit, cbm_len - zero_bit); + return (u32)val; +} + +/* + * Initialize cache resources per RDT domain + * + * Set the RDT domain up to start off with all usable allocations. That is, + * all shareable and unused bits. All-zero CBM is invalid. + */ +static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r, + u32 closid) +{ + struct rdt_resource *r_cdp = NULL; + struct rdt_domain *d_cdp = NULL; + u32 used_b = 0, unused_b = 0; + unsigned long tmp_cbm; + enum rdtgrp_mode mode; + u32 peer_ctl, *ctrl; + int i; + + rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); + d->have_new_ctrl = false; + d->new_ctrl = r->cache.shareable_bits; + used_b = r->cache.shareable_bits; + ctrl = d->ctrl_val; + for (i = 0; i < closids_supported(); i++, ctrl++) { + if (closid_allocated(i) && i != closid) { + mode = rdtgroup_mode_by_closid(i); + if (mode == RDT_MODE_PSEUDO_LOCKSETUP) + /* + * ctrl values for locksetup aren't relevant + * until the schemata is written, and the mode + * becomes RDT_MODE_PSEUDO_LOCKED. + */ + continue; + /* + * If CDP is active include peer domain's + * usage to ensure there is no overlap + * with an exclusive group. + */ + if (d_cdp) + peer_ctl = d_cdp->ctrl_val[i]; + else + peer_ctl = 0; + used_b |= *ctrl | peer_ctl; + if (mode == RDT_MODE_SHAREABLE) + d->new_ctrl |= *ctrl | peer_ctl; + } + } + if (d->plr && d->plr->cbm > 0) + used_b |= d->plr->cbm; + unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1); + unused_b &= BIT_MASK(r->cache.cbm_len) - 1; + d->new_ctrl |= unused_b; + /* + * Force the initial CBM to be valid, user can + * modify the CBM based on system availability. + */ + d->new_ctrl = cbm_ensure_valid(d->new_ctrl, r); + /* + * Assign the u32 CBM to an unsigned long to ensure that + * bitmap_weight() does not access out-of-bound memory. + */ + tmp_cbm = d->new_ctrl; + if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) { + rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id); + return -ENOSPC; + } + d->have_new_ctrl = true; + + return 0; +} + +/* + * Initialize cache resources with default values. + * + * A new RDT group is being created on an allocation capable (CAT) + * supporting system. Set this group up to start off with all usable + * allocations. + * + * If there are no more shareable bits available on any domain then + * the entire allocation will fail. + */ +static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid) +{ + struct rdt_domain *d; + int ret; + + list_for_each_entry(d, &r->domains, list) { + ret = __init_one_rdt_domain(d, r, closid); + if (ret < 0) + return ret; + } + + return 0; +} + +/* Initialize MBA resource with default values. */ +static void rdtgroup_init_mba(struct rdt_resource *r) +{ + struct rdt_domain *d; + + list_for_each_entry(d, &r->domains, list) { + d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl; + d->have_new_ctrl = true; + } +} + +/* Initialize the RDT group's allocations. */ +static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) +{ + struct rdt_resource *r; + int ret; + + for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) { + rdtgroup_init_mba(r); + } else { + ret = rdtgroup_init_cat(r, rdtgrp->closid); + if (ret < 0) + return ret; + } + + ret = update_domains(r, rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("Failed to initialize allocations\n"); + return ret; + } + + } + + rdtgrp->mode = RDT_MODE_SHAREABLE; + + return 0; +} + +static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, + const char *name, umode_t mode, + enum rdt_group_type rtype, struct rdtgroup **r) +{ + struct rdtgroup *prdtgrp, *rdtgrp; + struct kernfs_node *kn; + uint files = 0; + int ret; + + prdtgrp = rdtgroup_kn_lock_live(parent_kn); + if (!prdtgrp) { + ret = -ENODEV; + goto out_unlock; + } + + if (rtype == RDTMON_GROUP && + (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) { + ret = -EINVAL; + rdt_last_cmd_puts("Pseudo-locking in progress\n"); + goto out_unlock; + } + + /* allocate the rdtgroup. */ + rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); + if (!rdtgrp) { + ret = -ENOSPC; + rdt_last_cmd_puts("Kernel out of memory\n"); + goto out_unlock; + } + *r = rdtgrp; + rdtgrp->mon.parent = prdtgrp; + rdtgrp->type = rtype; + INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list); + + /* kernfs creates the directory for rdtgrp */ + kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); + rdt_last_cmd_puts("kernfs create error\n"); + goto out_free_rgrp; + } + rdtgrp->kn = kn; + + /* + * kernfs_remove() will drop the reference count on "kn" which + * will free it. But we still need it to stick around for the + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped by kernfs_put() in rdtgroup_remove(). + */ + kernfs_get(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + rdt_last_cmd_puts("kernfs perm error\n"); + goto out_destroy; + } + + files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype); + ret = rdtgroup_add_files(kn, files); + if (ret) { + rdt_last_cmd_puts("kernfs fill error\n"); + goto out_destroy; + } + + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("Out of RMIDs\n"); + goto out_destroy; + } + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + goto out_idfree; + } + } + kernfs_activate(kn); + + /* + * The caller unlocks the parent_kn upon success. + */ + return 0; + +out_idfree: + free_rmid(rdtgrp->mon.rmid); +out_destroy: + kernfs_put(rdtgrp->kn); + kernfs_remove(rdtgrp->kn); +out_free_rgrp: + kfree(rdtgrp); +out_unlock: + rdtgroup_kn_unlock(parent_kn); + return ret; +} + +static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) +{ + kernfs_remove(rgrp->kn); + free_rmid(rgrp->mon.rmid); + rdtgroup_remove(rgrp); +} + +/* + * Create a monitor group under "mon_groups" directory of a control + * and monitor group(ctrl_mon). This is a resource group + * to monitor a subset of tasks and cpus in its parent ctrl_mon group. + */ +static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, + const char *name, umode_t mode) +{ + struct rdtgroup *rdtgrp, *prgrp; + int ret; + + ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp); + if (ret) + return ret; + + prgrp = rdtgrp->mon.parent; + rdtgrp->closid = prgrp->closid; + + /* + * Add the rdtgrp to the list of rdtgrps the parent + * ctrl_mon group has to track. + */ + list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); + + rdtgroup_kn_unlock(parent_kn); + return ret; +} + +/* + * These are rdtgroups created under the root directory. Can be used + * to allocate and monitor resources. + */ +static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, + const char *name, umode_t mode) +{ + struct rdtgroup *rdtgrp; + struct kernfs_node *kn; + u32 closid; + int ret; + + ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp); + if (ret) + return ret; + + kn = rdtgrp->kn; + ret = closid_alloc(); + if (ret < 0) { + rdt_last_cmd_puts("Out of CLOSIDs\n"); + goto out_common_fail; + } + closid = ret; + ret = 0; + + rdtgrp->closid = closid; + ret = rdtgroup_init_alloc(rdtgrp); + if (ret < 0) + goto out_id_free; + + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + + if (rdt_mon_capable) { + /* + * Create an empty mon_groups directory to hold the subset + * of tasks and cpus to monitor. + */ + ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + goto out_del_list; + } + } + + goto out_unlock; + +out_del_list: + list_del(&rdtgrp->rdtgroup_list); +out_id_free: + closid_free(closid); +out_common_fail: + mkdir_rdt_prepare_clean(rdtgrp); +out_unlock: + rdtgroup_kn_unlock(parent_kn); + return ret; +} + +/* + * We allow creating mon groups only with in a directory called "mon_groups" + * which is present in every ctrl_mon group. Check if this is a valid + * "mon_groups" directory. + * + * 1. The directory should be named "mon_groups". + * 2. The mon group itself should "not" be named "mon_groups". + * This makes sure "mon_groups" directory always has a ctrl_mon group + * as parent. + */ +static bool is_mon_groups(struct kernfs_node *kn, const char *name) +{ + return (!strcmp(kn->name, "mon_groups") && + strcmp(name, "mon_groups")); +} + +static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + /* Do not accept '\n' to avoid unparsable situation. */ + if (strchr(name, '\n')) + return -EINVAL; + + /* + * If the parent directory is the root directory and RDT + * allocation is supported, add a control and monitoring + * subdirectory + */ + if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) + return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); + + /* + * If RDT monitoring is supported and the parent directory is a valid + * "mon_groups" directory, add a monitoring subdirectory. + */ + if (rdt_mon_capable && is_mon_groups(parent_kn, name)) + return rdtgroup_mkdir_mon(parent_kn, name, mode); + + return -EPERM; +} + +static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + int cpu; + + /* Give any tasks back to the parent group */ + rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask); + + /* Update per cpu rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) + per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid; + /* + * Update the MSR on moved CPUs and CPUs which have moved + * task running on them. + */ + cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); + update_closid_rmid(tmpmask, NULL); + + rdtgrp->flags = RDT_DELETED; + free_rmid(rdtgrp->mon.rmid); + + /* + * Remove the rdtgrp from the parent ctrl_mon group's list + */ + WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); + list_del(&rdtgrp->mon.crdtgrp_list); + + kernfs_remove(rdtgrp->kn); + + return 0; +} + +static int rdtgroup_ctrl_remove(struct kernfs_node *kn, + struct rdtgroup *rdtgrp) +{ + rdtgrp->flags = RDT_DELETED; + list_del(&rdtgrp->rdtgroup_list); + + kernfs_remove(rdtgrp->kn); + return 0; +} + +static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + int cpu; + + /* Give any tasks back to the default group */ + rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask); + + /* Give any CPUs back to the default group */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + + /* Update per cpu closid and rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) { + per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid; + per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid; + } + + /* + * Update the MSR on moved CPUs and CPUs which have moved + * task running on them. + */ + cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); + update_closid_rmid(tmpmask, NULL); + + closid_free(rdtgrp->closid); + free_rmid(rdtgrp->mon.rmid); + + rdtgroup_ctrl_remove(kn, rdtgrp); + + /* + * Free all the child monitor group rmids. + */ + free_all_child_rdtgrp(rdtgrp); + + return 0; +} + +static int rdtgroup_rmdir(struct kernfs_node *kn) +{ + struct kernfs_node *parent_kn = kn->parent; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + int ret = 0; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + + rdtgrp = rdtgroup_kn_lock_live(kn); + if (!rdtgrp) { + ret = -EPERM; + goto out; + } + + /* + * If the rdtgroup is a ctrl_mon group and parent directory + * is the root directory, remove the ctrl_mon group. + * + * If the rdtgroup is a mon group and parent directory + * is a valid "mon_groups" directory, remove the mon group. + */ + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn && + rdtgrp != &rdtgroup_default) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + ret = rdtgroup_ctrl_remove(kn, rdtgrp); + } else { + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + } + } else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) { + ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); + } else { + ret = -EPERM; + } + +out: + rdtgroup_kn_unlock(kn); + free_cpumask_var(tmpmask); + return ret; +} + +static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) +{ + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) + seq_puts(seq, ",cdp"); + + if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + seq_puts(seq, ",cdpl2"); + + if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA])) + seq_puts(seq, ",mba_MBps"); + + return 0; +} + +static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { + .mkdir = rdtgroup_mkdir, + .rmdir = rdtgroup_rmdir, + .show_options = rdtgroup_show_options, +}; + +static int __init rdtgroup_setup_root(void) +{ + int ret; + + rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, + KERNFS_ROOT_CREATE_DEACTIVATED | + KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, + &rdtgroup_default); + if (IS_ERR(rdt_root)) + return PTR_ERR(rdt_root); + + mutex_lock(&rdtgroup_mutex); + + rdtgroup_default.closid = 0; + rdtgroup_default.mon.rmid = 0; + rdtgroup_default.type = RDTCTRL_GROUP; + INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); + + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); + + ret = rdtgroup_add_files(rdt_root->kn, RF_CTRL_BASE); + if (ret) { + kernfs_destroy_root(rdt_root); + goto out; + } + + rdtgroup_default.kn = rdt_root->kn; + kernfs_activate(rdtgroup_default.kn); + +out: + mutex_unlock(&rdtgroup_mutex); + + return ret; +} + +/* + * rdtgroup_init - rdtgroup initialization + * + * Setup resctrl file system including set up root, create mount point, + * register rdtgroup filesystem, and initialize files under root directory. + * + * Return: 0 on success or -errno + */ +int __init rdtgroup_init(void) +{ + int ret = 0; + + seq_buf_init(&last_cmd_status, last_cmd_status_buf, + sizeof(last_cmd_status_buf)); + + ret = rdtgroup_setup_root(); + if (ret) + return ret; + + ret = sysfs_create_mount_point(fs_kobj, "resctrl"); + if (ret) + goto cleanup_root; + + ret = register_filesystem(&rdt_fs_type); + if (ret) + goto cleanup_mountpoint; + + /* + * Adding the resctrl debugfs directory here may not be ideal since + * it would let the resctrl debugfs directory appear on the debugfs + * filesystem before the resctrl filesystem is mounted. + * It may also be ok since that would enable debugging of RDT before + * resctrl is mounted. + * The reason why the debugfs directory is created here and not in + * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and + * during the debugfs directory creation also &sb->s_type->i_mutex_key + * (the lockdep class of inode->i_rwsem). Other filesystem + * interactions (eg. SyS_getdents) have the lock ordering: + * &sb->s_type->i_mutex_key --> &mm->mmap_lock + * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex + * is taken, thus creating dependency: + * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause + * issues considering the other two lock dependencies. + * By creating the debugfs directory here we avoid a dependency + * that may cause deadlock (even though file operations cannot + * occur until the filesystem is mounted, but I do not know how to + * tell lockdep that). + */ + debugfs_resctrl = debugfs_create_dir("resctrl", NULL); + + return 0; + +cleanup_mountpoint: + sysfs_remove_mount_point(fs_kobj, "resctrl"); +cleanup_root: + kernfs_destroy_root(rdt_root); + + return ret; +} + +void __exit rdtgroup_exit(void) +{ + debugfs_remove_recursive(debugfs_resctrl); + unregister_filesystem(&rdt_fs_type); + sysfs_remove_mount_point(fs_kobj, "resctrl"); + kernfs_destroy_root(rdt_root); +} |