diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a7b7e778a1f7a..f9618febb65ef 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5483,9 +5483,13 @@ rdt= [HW,X86,RDT] Turn on/off individual RDT features. List is: cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp, - mba, smba, bmec. + mba, smba, bmec, energy[:guid], perf[:guid]. E.g. to turn on cmt and turn off mba use: rdt=cmt,!mba + To turn off all energy telemetry monitoring and ensure that + perf telemetry monitoring associated with guid 0x12345 + is enabled use: + rdt=!energy,perf:0x12345 reboot= [KNL] Format (x86 or x86_64): diff --git a/Documentation/arch/x86/index.rst b/Documentation/arch/x86/index.rst index 8ac64d7de4dc9..00f9a99689fb8 100644 --- a/Documentation/arch/x86/index.rst +++ b/Documentation/arch/x86/index.rst @@ -31,7 +31,6 @@ x86-specific Documentation pti mds microcode - resctrl tsx_async_abort buslock usb-legacy-support diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index 09cade7eaefc8..f9e388fd8d000 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -109,6 +109,7 @@ Documentation for filesystem implementations. qnx6 ramfs-rootfs-initramfs relay + resctrl romfs smb/index spufs/index diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/filesystems/resctrl.rst similarity index 95% rename from Documentation/arch/x86/resctrl.rst rename to Documentation/filesystems/resctrl.rst index 6f07af4a885ec..2918c856cf978 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/filesystems/resctrl.rst @@ -1,9 +1,9 @@ .. SPDX-License-Identifier: GPL-2.0 .. include:: -=========================================== -User Interface for Resource Control feature -=========================================== +===================================================== +User Interface for Resource Control feature (resctrl) +===================================================== :Copyright: |copy| 2016 Intel Corporation :Authors: - Fenghua Yu @@ -167,13 +167,12 @@ with respect to allocation: bandwidth percentages are directly applied to the threads running on the core -If RDT monitoring is available there will be an "L3_MON" directory +If L3 monitoring is available there will be an "L3_MON" directory with the following files: "num_rmids": - The number of RMIDs available. This is the - upper bound for how many "CTRL_MON" + "MON" - groups can be created. + The number of RMIDs supported by hardware for + L3 monitoring events. "mon_features": Lists the monitoring events if @@ -261,6 +260,24 @@ with the following files: bytes) at which a previously used LLC_occupancy counter can be considered for re-use. +If telemetry monitoring is available there will be a "PERF_PKG_MON" directory +with the following files: + +"num_rmids": + The number of RMIDs for telemetry monitoring events. + + On Intel resctrl will not enable telemetry events if the number of + RMIDs that can be tracked concurrently is lower than the total number + of RMIDs supported. Telemetry events can be force-enabled with the + "rdt=" kernel parameter, but this may reduce the number of + monitoring groups that can be created. + +"mon_features": + Lists the telemetry monitoring events that are enabled on this system. + +The upper bound for how many "CTRL_MON" + "MON" can be created +is the smaller of the L3_MON and PERF_PKG_MON "num_rmids" values. + Finally, in the top level of the "info" directory there is a file named "last_cmd_status". This is reset with every "command" issued via the file system (making new directories or writing to any of the @@ -366,20 +383,51 @@ When control is enabled all CTRL_MON groups will also contain: When monitoring is enabled all MON groups will also contain: "mon_data": - This contains a set of files organized by L3 domain and by - RDT event. E.g. on a system with two L3 domains there will - be subdirectories "mon_L3_00" and "mon_L3_01". Each of these - directories have one file per event (e.g. "llc_occupancy", - "mbm_total_bytes", and "mbm_local_bytes"). In a MON group these - files provide a read out of the current value of the event for - all tasks in the group. In CTRL_MON groups these files provide - the sum for all tasks in the CTRL_MON group and all tasks in + This contains directories for each monitor domain. + + If L3 monitoring is enabled, there will be a "mon_L3_XX" directory for + each instance of an L3 cache. Each directory contains files for the enabled + L3 events (e.g. "llc_occupancy", "mbm_total_bytes", and "mbm_local_bytes"). + + If telemetry monitoring is enabled, there will be a "mon_PERF_PKG_YY" + directory for each physical processor package. Each directory contains + files for the enabled telemetry events (e.g. "core_energy". "activity", + "uops_retired", etc.) + + The info/`*`/mon_features files provide the full list of enabled + event/file names. + + "core energy" reports a floating point number for the energy (in Joules) + consumed by cores (registers, arithmetic units, TLB and L1/L2 caches) + during execution of instructions summed across all logical CPUs on a + package for the current monitoring group. + + "activity" also reports a floating point value (in Farads). This provides + an estimate of work done independent of the frequency that the CPUs used + for execution. + + Note that "core energy" and "activity" only measure energy/activity in the + "core" of the CPU (arithmetic units, TLB, L1 and L2 caches, etc.). They + do not include L3 cache, memory, I/O devices etc. + + All other events report decimal integer values. + + In a MON group these files provide a read out of the current value of + the event for all tasks in the group. In CTRL_MON groups these files + provide the sum for all tasks in the CTRL_MON group and all tasks in MON groups. Please see example section for more details on usage. + On systems with Sub-NUMA Cluster (SNC) enabled there are extra directories for each node (located within the "mon_L3_XX" directory for the L3 cache they occupy). These are named "mon_sub_L3_YY" where "YY" is the node number. + When the 'mbm_event' counter assignment mode is enabled, reading + an MBM event of a MON group returns 'Unassigned' if no hardware + counter is assigned to it. For CTRL_MON groups, 'Unassigned' is + returned if the MBM event does not have an assigned counter in the + CTRL_MON group nor in any of its associated MON groups. + "mon_hw_id": Available only with debug option. The identifier used by hardware for the monitor group. On x86 this is the RMID. diff --git a/MAINTAINERS b/MAINTAINERS index 26ab6e9e04c46..197994517db89 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18108,9 +18108,11 @@ M: Fenghua Yu M: Reinette Chatre L: linux-kernel@vger.kernel.org S: Supported -F: Documentation/arch/x86/resctrl* +F: Documentation/filesystems/resctrl.rst F: arch/x86/include/asm/resctrl.h F: arch/x86/kernel/cpu/resctrl/ +F: fs/resctrl/ +F: include/linux/resctrl*.h F: tools/testing/selftests/resctrl/ READ-COPY UPDATE (RCU) diff --git a/arch/Kconfig b/arch/Kconfig index 09603e0bc2cc1..cbdb9200284b2 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1333,6 +1333,14 @@ config STRICT_MODULE_RWX config ARCH_HAS_PHYS_TO_DMA bool +config ARCH_HAS_CPU_RESCTRL + bool + help + An architecture selects this option to indicate that the necessary + hooks are provided to support the common memory system usage + monitoring and control interfaces provided by the 'resctrl' + filesystem (see RESCTRL_FS). + config HAVE_ARCH_COMPILER_H bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b93fa32b52c9e..aa8bcd0a1b1bc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -482,8 +482,10 @@ config GOLDFISH config X86_CPU_RESCTRL bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) - select KERNFS - select PROC_CPU_RESCTRL if PROC_FS + depends on MISC_FILESYSTEMS + select ARCH_HAS_CPU_RESCTRL + select RESCTRL_FS + select RESCTRL_FS_PSEUDO_LOCK help Enable x86 CPU resource control support. @@ -500,6 +502,19 @@ config X86_CPU_RESCTRL Say N if unsure. +config X86_CPU_RESCTRL_INTEL_AET + bool "Intel Application Energy Telemetry" + depends on X86_64 && X86_CPU_RESCTRL && CPU_SUP_INTEL && INTEL_PMT_TELEMETRY=y && INTEL_TPMI=y + help + Enable per-RMID telemetry events in resctrl. + + Intel feature that collects per-RMID execution data + about energy consumption, measure of frequency independent + activity and other performance metrics. Data is aggregated + per package. + + Say N if unsure. + if X86_32 config X86_BIGSMP bool "Support for big SMP systems with more than 8 CPUs" diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 08faac3693972..d6bdef6194ae1 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6605,6 +6605,32 @@ static struct intel_uncore_type gnr_uncore_ubox = { .attr_update = uncore_alias_groups, }; +static struct uncore_event_desc gnr_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x01,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0, "event=0x05,umask=0xcf"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1, "event=0x06,umask=0xcf"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type gnr_uncore_imc = { + SPR_UNCORE_MMIO_COMMON_FORMAT(), + .name = "imc", + .fixed_ctr_bits = 48, + .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, + .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, + .event_descs = gnr_uncore_imc_events, +}; + static struct intel_uncore_type gnr_uncore_pciex8 = { SPR_UNCORE_PCI_COMMON_FORMAT(), .name = "pciex8", @@ -6652,7 +6678,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = { NULL, &spr_uncore_pcu, &gnr_uncore_ubox, - &spr_uncore_imc, + &gnr_uncore_imc, NULL, &gnr_uncore_upi, NULL, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index c21b60114384c..eb88f39b172b0 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -485,6 +485,7 @@ #define X86_FEATURE_TSA_L1_NO (21*32+12) /* "" AMD CPU not vulnerable to TSA-L1 */ #define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* "" Clear CPU buffers using VERW before VMRUN */ #define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */ +#define X86_FEATURE_ABMC (21*32+15) /* Assignable Bandwidth Monitoring Counters */ /* * BUG word(s) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 7bdbee2da3b60..0fa669ff32343 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -1234,6 +1234,8 @@ /* - AMD: */ #define MSR_IA32_MBA_BW_BASE 0xc0000200 #define MSR_IA32_SMBA_BW_BASE 0xc0000280 +#define MSR_IA32_L3_QOS_ABMC_CFG 0xc00003fd +#define MSR_IA32_L3_QOS_EXT_CFG 0xc00003ff #define MSR_IA32_EVT_CFG_BASE 0xc0000400 /* MSR_IA32_VMX_MISC bits */ diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 8b1b6ce1e51b2..089742970cc14 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -4,8 +4,10 @@ #ifdef CONFIG_X86_CPU_RESCTRL -#include #include +#include +#include +#include /* * This value can never be a valid CLOSID, and is used when mapping a @@ -96,8 +98,8 @@ static inline void resctrl_arch_disable_mon(void) static inline void __resctrl_sched_in(struct task_struct *tsk) { struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); - u32 closid = state->default_closid; - u32 rmid = state->default_rmid; + u32 closid = READ_ONCE(state->default_closid); + u32 rmid = READ_ONCE(state->default_rmid); u32 tmp; /* @@ -132,6 +134,13 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) return val * scale; } +static inline void resctrl_arch_set_cpu_default_closid_rmid(int cpu, u32 closid, + u32 rmid) +{ + WRITE_ONCE(per_cpu(pqr_state.default_closid, cpu), closid); + WRITE_ONCE(per_cpu(pqr_state.default_rmid, cpu), rmid); +} + static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk, u32 closid, u32 rmid) { @@ -150,7 +159,7 @@ static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored, return READ_ONCE(tsk->rmid) == rmid; } -static inline void resctrl_sched_in(struct task_struct *tsk) +static inline void resctrl_arch_sched_in(struct task_struct *tsk) { if (static_branch_likely(&rdt_enable_key)) __resctrl_sched_in(tsk); @@ -169,20 +178,22 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid) /* x86 can always read an rmid, nothing needs allocating */ struct rdt_resource; -static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) +static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, + enum resctrl_event_id evtid) { might_sleep(); return NULL; -}; +} -static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid, - void *ctx) { }; +static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, + enum resctrl_event_id evtid, + void *ctx) { } void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else -static inline void resctrl_sched_in(struct task_struct *tsk) {} +static inline void resctrl_arch_sched_in(struct task_struct *tsk) {} static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {} #endif /* CONFIG_X86_CPU_RESCTRL */ diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index 4a06c37b9cf11..273ddfa308366 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,4 +1,8 @@ # 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 +obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o +obj-$(CONFIG_X86_CPU_RESCTRL_INTEL_AET) += intel_aet.o +obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK) += pseudo_lock.o + +# To allow define_trace.h's recursive include: CFLAGS_pseudo_lock.o = -I$(src) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 9d364a91d0bad..18fef31e16e9a 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -21,7 +21,7 @@ #include #include -#include +#include #include #include "internal.h" @@ -43,12 +43,6 @@ static DEFINE_MUTEX(domain_list_lock); */ 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. @@ -62,19 +56,16 @@ static void mba_wrmsr_amd(struct msr_param *m); #define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains) #define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains) -struct rdt_hw_resource rdt_resources_all[] = { +struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = { [RDT_RESOURCE_L3] = { .r_resctrl = { - .rid = RDT_RESOURCE_L3, .name = "L3", .ctrl_scope = RESCTRL_L3_CACHE, .mon_scope = RESCTRL_L3_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L3), .mon_domains = mon_domain_init(RDT_RESOURCE_L3), - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, + .schema_fmt = RESCTRL_SCHEMA_BITMAP, }, .msr_base = MSR_IA32_L3_CBM_BASE, .msr_update = cat_wrmsr, @@ -82,13 +73,10 @@ struct rdt_hw_resource rdt_resources_all[] = { [RDT_RESOURCE_L2] = { .r_resctrl = { - .rid = RDT_RESOURCE_L2, .name = "L2", .ctrl_scope = RESCTRL_L2_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L2), - .parse_ctrlval = parse_cbm, - .format_str = "%d=%0*x", - .fflags = RFTYPE_RES_CACHE, + .schema_fmt = RESCTRL_SCHEMA_BITMAP, }, .msr_base = MSR_IA32_L2_CBM_BASE, .msr_update = cat_wrmsr, @@ -96,35 +84,56 @@ struct rdt_hw_resource rdt_resources_all[] = { [RDT_RESOURCE_MBA] = { .r_resctrl = { - .rid = RDT_RESOURCE_MBA, .name = "MB", .ctrl_scope = RESCTRL_L3_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_MBA), - .parse_ctrlval = parse_bw, - .format_str = "%d=%*u", - .fflags = RFTYPE_RES_MB, + .schema_fmt = RESCTRL_SCHEMA_RANGE, }, }, [RDT_RESOURCE_SMBA] = { .r_resctrl = { - .rid = RDT_RESOURCE_SMBA, .name = "SMBA", .ctrl_scope = RESCTRL_L3_CACHE, .ctrl_domains = ctrl_domain_init(RDT_RESOURCE_SMBA), - .parse_ctrlval = parse_bw, - .format_str = "%d=%*u", - .fflags = RFTYPE_RES_MB, + .schema_fmt = RESCTRL_SCHEMA_RANGE, + }, + }, + [RDT_RESOURCE_PERF_PKG] = + { + .r_resctrl = { + .name = "PERF_PKG", + .mon_scope = RESCTRL_PACKAGE, + .mon_domains = mon_domain_init(RDT_RESOURCE_PERF_PKG), }, }, }; +/** + * resctrl_arch_system_num_rmid_idx - Compute number of supported RMIDs + * (minimum across all mon_capable resource) + * + * Return: Number of supported RMIDs at time of call. Note that mount time + * enumeration of resources may reduce the number. + */ u32 resctrl_arch_system_num_rmid_idx(void) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + u32 num_rmids = U32_MAX; + struct rdt_resource *r; + + for_each_mon_capable_rdt_resource(r) + num_rmids = min(num_rmids, r->mon.num_rmid); /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ - return r->num_rmid; + return num_rmids == U32_MAX ? 0 : num_rmids; +} + +struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l) +{ + if (l >= RDT_NUM_RESOURCES) + return NULL; + + return &rdt_resources_all[l].r_resctrl; } /* @@ -161,7 +170,6 @@ static inline void cache_alloc_hsw_probe(void) return; hw_res->num_closid = 4; - r->default_ctrl = max_cbm; r->cache.cbm_len = 20; r->cache.shareable_bits = 0xc0000; r->cache.min_cbm_bits = 2; @@ -171,21 +179,6 @@ static inline void cache_alloc_hsw_probe(void) rdt_alloc_capable = true; } -bool is_mba_sc(struct rdt_resource *r) -{ - if (!r) - return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc; - - /* - * The software controller support is only applicable to MBA resource. - * Make sure to check for resource type. - */ - if (r->rid != RDT_RESOURCE_MBA) - return false; - - 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. @@ -217,7 +210,7 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r) cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full); hw_res->num_closid = edx.split.cos_max + 1; max_delay = eax.split.max_delay + 1; - r->default_ctrl = MAX_MBA_BW; + r->membw.max_bw = MAX_MBA_BW; r->membw.arch_needs_linear = true; if (ecx & MBA_IS_LINEAR) { r->membw.delay_linear = true; @@ -228,13 +221,11 @@ static __init bool __get_mem_config_intel(struct rdt_resource *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; @@ -254,7 +245,7 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx); hw_res->num_closid = edx + 1; - r->default_ctrl = 1 << eax; + r->membw.max_bw = 1 << eax; /* AMD does not use delay */ r->membw.delay_linear = false; @@ -267,8 +258,6 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) 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; @@ -281,14 +270,13 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) union cpuid_0x10_1_eax eax; union cpuid_0x10_x_ecx ecx; union cpuid_0x10_x_edx edx; - u32 ebx; + u32 ebx, default_ctrl; cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full); hw_res->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; + default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->cache.shareable_bits = ebx & default_ctrl; if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) r->cache.arch_has_sparse_bitmasks = ecx.split.noncont; r->alloc_capable = true; @@ -335,7 +323,7 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) return MAX_MBA_BW - bw; pr_warn_once("Non Linear delay-bw map not supported but queried\n"); - return r->default_ctrl; + return MAX_MBA_BW; } static void mba_wrmsr_intel(struct msr_param *m) @@ -359,36 +347,6 @@ static void cat_wrmsr(struct msr_param *m) wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]); } -struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r) -{ - struct rdt_ctrl_domain *d; - - lockdep_assert_cpus_held(); - - list_for_each_entry(d, &r->ctrl_domains, hdr.list) { - /* Find the domain that contains this CPU */ - if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) - return d; - } - - return NULL; -} - -struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r) -{ - struct rdt_mon_domain *d; - - lockdep_assert_cpus_held(); - - list_for_each_entry(d, &r->mon_domains, hdr.list) { - /* Find the domain that contains this CPU */ - if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) - return d; - } - - return NULL; -} - u32 resctrl_arch_get_num_closid(struct rdt_resource *r) { return resctrl_to_arch_res(r)->num_closid; @@ -403,36 +361,6 @@ void rdt_ctrl_update(void *arg) hw_res->msr_update(m); } -/* - * rdt_find_domain - Search for a domain id in a resource domain list. - * - * Search the domain list to find the domain id. If the domain id is - * found, return the domain. NULL otherwise. If the domain id is not - * found (and NULL returned) then the first domain with id bigger than - * the input id can be returned to the caller via @pos. - */ -struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id, - struct list_head **pos) -{ - struct rdt_domain_hdr *d; - struct list_head *l; - - list_for_each(l, h) { - d = list_entry(l, struct rdt_domain_hdr, 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; -} - static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); @@ -444,7 +372,7 @@ static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc) * For Memory Allocation: Set b/w requested to 100% */ for (i = 0; i < hw_res->num_closid; i++, dc++) - *dc = r->default_ctrl; + *dc = resctrl_get_default_ctrl(r); } static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom) @@ -453,10 +381,12 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom) kfree(hw_dom); } -static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom) +static void l3_mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom) { - kfree(hw_dom->arch_mbm_total); - kfree(hw_dom->arch_mbm_local); + int idx; + + for_each_mbm_idx(idx) + kfree(hw_dom->arch_mbm_states[idx]); kfree(hw_dom); } @@ -484,31 +414,35 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain * } /** - * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM counters + * l3_mon_domain_mbm_alloc() - Allocate arch private storage for the MBM counters * @num_rmid: The size of the MBM counter array * @hw_dom: The domain that owns the allocated arrays + * + * Return: 0 for success, or -ENOMEM. */ -static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom) +static int l3_mon_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_domain *hw_dom) { - size_t tsize; - - if (is_mbm_total_enabled()) { - tsize = sizeof(*hw_dom->arch_mbm_total); - hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL); - if (!hw_dom->arch_mbm_total) - return -ENOMEM; - } - if (is_mbm_local_enabled()) { - tsize = sizeof(*hw_dom->arch_mbm_local); - hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL); - if (!hw_dom->arch_mbm_local) { - kfree(hw_dom->arch_mbm_total); - hw_dom->arch_mbm_total = NULL; - return -ENOMEM; - } + size_t tsize = sizeof(*hw_dom->arch_mbm_states[0]); + enum resctrl_event_id eventid; + int idx; + + for_each_mbm_event_id(eventid) { + if (!resctrl_is_mon_event_enabled(eventid)) + continue; + idx = MBM_STATE_IDX(eventid); + hw_dom->arch_mbm_states[idx] = kcalloc(num_rmid, tsize, GFP_KERNEL); + if (!hw_dom->arch_mbm_states[idx]) + goto cleanup; } return 0; +cleanup: + for_each_mbm_idx(idx) { + kfree(hw_dom->arch_mbm_states[idx]); + hw_dom->arch_mbm_states[idx] = NULL; + } + + return -ENOMEM; } static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope) @@ -519,6 +453,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope) return get_cpu_cacheinfo_id(cpu, scope); case RESCTRL_L3_NODE: return cpu_to_node(cpu); + case RESCTRL_PACKAGE: + return topology_physical_package_id(cpu); default: break; } @@ -543,9 +479,9 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) return; } - hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos); + hdr = resctrl_find_domain(&r->ctrl_domains, id, &add_pos); if (hdr) { - if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) + if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid)) return; d = container_of(hdr, struct rdt_ctrl_domain, hdr); @@ -562,6 +498,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) d = &hw_dom->d_resctrl; d->hdr.id = id; d->hdr.type = RESCTRL_CTRL_DOMAIN; + d->hdr.rid = r->rid; cpumask_set_cpu(cpu, &d->hdr.cpu_mask); rdt_domain_reconfigure_cdp(r); @@ -581,34 +518,13 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r) } } -static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) +static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct list_head *add_pos) { - int id = get_domain_id_from_scope(cpu, r->mon_scope); - struct list_head *add_pos = NULL; - struct rdt_hw_mon_domain *hw_dom; - struct rdt_domain_hdr *hdr; - struct rdt_mon_domain *d; + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; struct cacheinfo *ci; int err; - lockdep_assert_held(&domain_list_lock); - - if (id < 0) { - pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n", - cpu, r->mon_scope, r->name); - return; - } - - hdr = rdt_find_domain(&r->mon_domains, id, &add_pos); - if (hdr) { - if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) - return; - d = container_of(hdr, struct rdt_mon_domain, hdr); - - cpumask_set_cpu(cpu, &d->hdr.cpu_mask); - return; - } - hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu)); if (!hw_dom) return; @@ -616,10 +532,11 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) d = &hw_dom->d_resctrl; d->hdr.id = id; d->hdr.type = RESCTRL_MON_DOMAIN; + d->hdr.rid = RDT_RESOURCE_L3; ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); if (!ci) { pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name); - mon_domain_free(hw_dom); + l3_mon_domain_free(hw_dom); return; } d->ci_id = ci->id; @@ -627,18 +544,54 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) arch_mon_domain_online(r, d); - if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) { - mon_domain_free(hw_dom); + if (l3_mon_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) { + l3_mon_domain_free(hw_dom); return; } list_add_tail_rcu(&d->hdr.list, add_pos); - err = resctrl_online_mon_domain(r, d); + err = resctrl_online_mon_domain(r, &d->hdr); if (err) { list_del_rcu(&d->hdr.list); synchronize_rcu(); - mon_domain_free(hw_dom); + l3_mon_domain_free(hw_dom); + } +} + +static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) +{ + int id = get_domain_id_from_scope(cpu, r->mon_scope); + struct list_head *add_pos = NULL; + struct rdt_domain_hdr *hdr; + + lockdep_assert_held(&domain_list_lock); + + if (id < 0) { + pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n", + cpu, r->mon_scope, r->name); + return; + } + + hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos); + if (hdr) + cpumask_set_cpu(cpu, &hdr->cpu_mask); + + switch (r->rid) { + case RDT_RESOURCE_L3: + /* Update the mbm_assign_mode state for the CPU if supported */ + if (r->mon.mbm_cntr_assignable) + resctrl_arch_mbm_cntr_assign_set_one(r); + if (!hdr) + l3_mon_domain_setup(cpu, id, r, add_pos); + break; + case RDT_RESOURCE_PERF_PKG: + if (!hdr) + intel_aet_mon_domain_setup(cpu, id, r, add_pos); + break; + default: + pr_warn_once("Unknown resource rid=%d\n", r->rid); + break; } } @@ -665,43 +618,40 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r) return; } - hdr = rdt_find_domain(&r->ctrl_domains, id, NULL); + hdr = resctrl_find_domain(&r->ctrl_domains, id, NULL); if (!hdr) { pr_warn("Can't find control domain for id=%d for CPU %d for resource %s\n", id, cpu, r->name); return; } - if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN)) + cpumask_clear_cpu(cpu, &hdr->cpu_mask); + if (!cpumask_empty(&hdr->cpu_mask)) + return; + + if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid)) return; d = container_of(hdr, struct rdt_ctrl_domain, hdr); hw_dom = resctrl_to_arch_ctrl_dom(d); - cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); - if (cpumask_empty(&d->hdr.cpu_mask)) { - resctrl_offline_ctrl_domain(r, d); - list_del_rcu(&d->hdr.list); - synchronize_rcu(); - - /* - * rdt_ctrl_domain "d" is going to be freed below, so clear - * its pointer from pseudo_lock_region struct. - */ - if (d->plr) - d->plr->d = NULL; - ctrl_domain_free(hw_dom); + resctrl_offline_ctrl_domain(r, d); + list_del_rcu(&hdr->list); + synchronize_rcu(); - return; - } + /* + * rdt_ctrl_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + ctrl_domain_free(hw_dom); } static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) { int id = get_domain_id_from_scope(cpu, r->mon_scope); - struct rdt_hw_mon_domain *hw_dom; struct rdt_domain_hdr *hdr; - struct rdt_mon_domain *d; lockdep_assert_held(&domain_list_lock); @@ -711,27 +661,49 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r) return; } - hdr = rdt_find_domain(&r->mon_domains, id, NULL); + hdr = resctrl_find_domain(&r->mon_domains, id, NULL); if (!hdr) { pr_warn("Can't find monitor domain for id=%d for CPU %d for resource %s\n", id, cpu, r->name); return; } - if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) + cpumask_clear_cpu(cpu, &hdr->cpu_mask); + if (!cpumask_empty(&hdr->cpu_mask)) return; - d = container_of(hdr, struct rdt_mon_domain, hdr); - hw_dom = resctrl_to_arch_mon_dom(d); + switch (r->rid) { + case RDT_RESOURCE_L3: { + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; - cpumask_clear_cpu(cpu, &d->hdr.cpu_mask); - if (cpumask_empty(&d->hdr.cpu_mask)) { - resctrl_offline_mon_domain(r, d); - list_del_rcu(&d->hdr.list); + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + hw_dom = resctrl_to_arch_mon_dom(d); + resctrl_offline_mon_domain(r, hdr); + list_del_rcu(&hdr->list); synchronize_rcu(); - mon_domain_free(hw_dom); + l3_mon_domain_free(hw_dom); + break; + } + case RDT_RESOURCE_PERF_PKG: { + struct rdt_perf_pkg_mon_domain *pkgd; - return; + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_PERF_PKG)) + return; + + pkgd = container_of(hdr, struct rdt_perf_pkg_mon_domain, hdr); + resctrl_offline_mon_domain(r, hdr); + list_del_rcu(&hdr->list); + synchronize_rcu(); + kfree(pkgd); + break; + } + default: + pr_warn_once("Unknown resource rid=%d\n", r->rid); + break; } } @@ -786,18 +758,26 @@ static int resctrl_arch_offline_cpu(unsigned int cpu) 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) +void resctrl_arch_pre_mount(void) { - struct rdt_resource *r; + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl; + int cpu; - for_each_alloc_capable_rdt_resource(r) { - if (r->data_width > max_data_width) - max_data_width = r->data_width; - } + if (!intel_aet_get_events()) + return; + + /* + * Late discovery of telemetry events means the domains for the + * resource were not built. Do that now. + */ + cpus_read_lock(); + mutex_lock(&domain_list_lock); + r->mon_capable = true; + rdt_mon_capable = true; + for_each_online_cpu(cpu) + domain_add_cpu_mon(cpu, r); + mutex_unlock(&domain_list_lock); + cpus_read_unlock(); } enum { @@ -825,7 +805,7 @@ struct rdt_options { bool force_off, force_on; }; -static struct rdt_options rdt_options[] __initdata = { +static struct rdt_options rdt_options[] __ro_after_init = { 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), @@ -851,6 +831,8 @@ static int __init set_rdt_options(char *str) force_off = *tok == '!'; if (force_off) tok++; + if (intel_handle_aet_option(force_off, tok)) + continue; for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { if (strcmp(tok, o->name) == 0) { if (force_off) @@ -865,7 +847,7 @@ static int __init set_rdt_options(char *str) } __setup("rdt", set_rdt_options); -bool __init rdt_cpu_has(int flag) +bool rdt_cpu_has(int flag) { bool ret = boot_cpu_has(flag); struct rdt_options *o; @@ -885,6 +867,21 @@ bool __init rdt_cpu_has(int flag) return ret; } +bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt) +{ + if (!rdt_cpu_has(X86_FEATURE_BMEC)) + return false; + + switch (evt) { + case QOS_L3_MBM_TOTAL_EVENT_ID: + return rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL); + case QOS_L3_MBM_LOCAL_EVENT_ID: + return rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL); + default: + return false; + } +} + static __init bool get_mem_config(void) { struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_MBA]; @@ -953,34 +950,43 @@ static __init bool get_rdt_alloc_resources(void) static __init bool get_rdt_mon_resources(void) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + bool ret = false; - 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_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) { + resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0, NULL); + ret = true; + } + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { + resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0, NULL); + ret = true; + } + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { + resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0, NULL); + ret = true; + } + if (rdt_cpu_has(X86_FEATURE_ABMC)) + ret = true; - if (!rdt_mon_features) + if (!ret) return false; - return !rdt_get_mon_l3_config(r); + return !rdt_get_l3_mon_config(r); } static __init void __check_quirks_intel(void) { - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_HASWELL_X: + switch (boot_cpu_data.x86_vfm) { + case INTEL_HASWELL_X: if (!rdt_options[RDT_FLAG_L3_CAT].force_off) cache_alloc_hsw_probe(); break; - case INTEL_FAM6_SKYLAKE_X: + case INTEL_SKYLAKE_X: if (boot_cpu_data.x86_stepping <= 4) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); else set_rdt_options("!l3cat"); fallthrough; - case INTEL_FAM6_BROADWELL_X: + case INTEL_BROADWELL_X: intel_rdt_mbm_apply_quirk(); break; } @@ -1056,7 +1062,7 @@ 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)) { + if (!cpu_has(c, X86_FEATURE_CQM_LLC) && !cpu_has(c, X86_FEATURE_ABMC)) { c->x86_cache_max_rmid = -1; c->x86_cache_occ_scale = -1; c->x86_cache_mbm_width_offset = -1; @@ -1068,7 +1074,8 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) 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)) { + cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL) || + cpu_has(c, X86_FEATURE_ABMC)) { u32 eax, ebx, ecx, edx; /* QoS sub-leaf, EAX=0Fh, ECX=1 */ @@ -1094,10 +1101,14 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) } } -static int __init resctrl_late_init(void) +static int __init resctrl_arch_late_init(void) { struct rdt_resource *r; - int state, ret; + int state, ret, i; + + /* for_each_rdt_resource() requires all rid to be initialised. */ + for (i = 0; i < RDT_NUM_RESOURCES; i++) + rdt_resources_all[i].r_resctrl.rid = i; /* * Initialize functions(or definitions) that are different @@ -1110,8 +1121,6 @@ static int __init resctrl_late_init(void) if (!get_rdt_resources()) return -ENODEV; - rdt_init_padding(); - state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/resctrl/cat:online:", resctrl_arch_online_cpu, @@ -1119,7 +1128,7 @@ static int __init resctrl_late_init(void) if (state < 0) return state; - ret = rdtgroup_init(); + ret = resctrl_init(); if (ret) { cpuhp_remove_state(state); return ret; @@ -1135,18 +1144,15 @@ static int __init resctrl_late_init(void) return 0; } -late_initcall(resctrl_late_init); +late_initcall(resctrl_arch_late_init); -static void __exit resctrl_exit(void) +static void __exit resctrl_arch_exit(void) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + intel_aet_exit(); cpuhp_remove_state(rdt_online); - rdtgroup_exit(); - - if (r->mon_capable) - rdt_put_mon_l3_config(); + resctrl_exit(); } -__exitcall(resctrl_exit); +__exitcall(resctrl_arch_exit); diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 57912f773b7f4..1189c0df4ad76 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -16,273 +16,15 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include -#include -#include -#include #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, u32 *data, struct rdt_resource *r) -{ - int ret; - u32 bw; - - /* - * 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 = kstrtou32(buf, 10, &bw); - if (ret) { - rdt_last_cmd_printf("Invalid MB value %s\n", buf); - return false; - } - - /* Nothing else to do if software controller is enabled. */ - if (is_mba_sc(r)) { - *data = bw; - return true; - } - - if (bw < r->membw.min_bw || bw > r->default_ctrl) { - rdt_last_cmd_printf("MB value %u 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 resctrl_schema *s, - struct rdt_ctrl_domain *d) -{ - struct resctrl_staged_config *cfg; - u32 closid = data->rdtgrp->closid; - struct rdt_resource *r = s->res; - u32 bw_val; - - cfg = &d->staged_config[s->conf_type]; - if (cfg->have_new_ctrl) { - rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id); - return -EINVAL; - } - - if (!bw_validate(data->buf, &bw_val, r)) - return -EINVAL; - - if (is_mba_sc(r)) { - d->mbps_val[closid] = bw_val; - return 0; - } - - cfg->new_ctrl = bw_val; - cfg->have_new_ctrl = true; - - return 0; -} - -/* - * Check whether a cache bit mask is valid. - * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID: - * - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1 - * - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1 - * - * Haswell does not support a non-contiguous 1s value and additionally - * 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.min_cbm_bits > 0 && 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 bitmasks allowed? */ - if (!r->cache.arch_has_sparse_bitmasks && - (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 resctrl_schema *s, - struct rdt_ctrl_domain *d) -{ - struct rdtgroup *rdtgrp = data->rdtgrp; - struct resctrl_staged_config *cfg; - struct rdt_resource *r = s->res; - u32 cbm_val; - - cfg = &d->staged_config[s->conf_type]; - if (cfg->have_new_ctrl) { - rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.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(s, d, cbm_val, rdtgrp->closid, true)) { - rdt_last_cmd_puts("Overlaps with exclusive group\n"); - return -EINVAL; - } - - if (rdtgroup_cbm_overlaps(s, 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; - } - } - - cfg->new_ctrl = cbm_val; - cfg->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 resctrl_schema *s, - struct rdtgroup *rdtgrp) -{ - enum resctrl_conf_type t = s->conf_type; - struct resctrl_staged_config *cfg; - struct rdt_resource *r = s->res; - struct rdt_parse_data data; - struct rdt_ctrl_domain *d; - char *dom = NULL, *id; - unsigned long dom_id; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && - (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) { - 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->ctrl_domains, hdr.list) { - if (d->hdr.id == dom_id) { - data.buf = dom; - data.rdtgrp = rdtgrp; - if (r->parse_ctrlval(&data, s, d)) - return -EINVAL; - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { - cfg = &d->staged_config[t]; - /* - * 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->s = s; - rdtgrp->plr->d = d; - rdtgrp->plr->cbm = cfg->new_ctrl; - d->plr = rdtgrp->plr; - return 0; - } - goto next; - } - } - return -EINVAL; -} - -static u32 get_config_index(u32 closid, enum resctrl_conf_type type) -{ - switch (type) { - default: - case CDP_NONE: - return closid; - case CDP_CODE: - return closid * 2 + 1; - case CDP_DATA: - return closid * 2; - } -} - int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type t, u32 cfg_val) { struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - u32 idx = get_config_index(closid, t); + u32 idx = resctrl_get_config_index(closid, t); struct msr_param msr_param; if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask)) @@ -319,7 +61,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) if (!cfg->have_new_ctrl) continue; - idx = get_config_index(closid, t); + idx = resctrl_get_config_index(closid, t); if (cfg->new_ctrl == hw_dom->ctrl_val[idx]) continue; hw_dom->ctrl_val[idx] = cfg->new_ctrl; @@ -341,292 +83,11 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) return 0; } -static int rdtgroup_parse_resource(char *resname, char *tok, - struct rdtgroup *rdtgrp) -{ - struct resctrl_schema *s; - - list_for_each_entry(s, &resctrl_schema_all, list) { - if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid) - return parse_line(tok, s, 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 resctrl_schema *s; - struct rdtgroup *rdtgrp; - 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'; - - rdtgrp = rdtgroup_kn_lock_live(of->kn); - if (!rdtgrp) { - rdtgroup_kn_unlock(of->kn); - 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; - } - - rdt_staged_configs_clear(); - - 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; - } - - list_for_each_entry(s, &resctrl_schema_all, list) { - r = s->res; - - /* - * Writes to mba_sc resources update the software controller, - * not the control MSR. - */ - if (is_mba_sc(r)) - continue; - - ret = resctrl_arch_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: - rdt_staged_configs_clear(); - rdtgroup_kn_unlock(of->kn); - return ret ?: nbytes; -} - u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type) { struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d); - u32 idx = get_config_index(closid, type); + u32 idx = resctrl_get_config_index(closid, type); return hw_dom->ctrl_val[idx]; } - -static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) -{ - struct rdt_resource *r = schema->res; - struct rdt_ctrl_domain *dom; - bool sep = false; - u32 ctrl_val; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - seq_printf(s, "%*s:", max_name_width, schema->name); - list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { - if (sep) - seq_puts(s, ";"); - - if (is_mba_sc(r)) - ctrl_val = dom->mbps_val[closid]; - else - ctrl_val = resctrl_arch_get_config(r, dom, closid, - schema->conf_type); - - seq_printf(s, r->format_str, dom->hdr.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 resctrl_schema *schema; - struct rdtgroup *rdtgrp; - int ret = 0; - u32 closid; - - rdtgrp = rdtgroup_kn_lock_live(of->kn); - if (rdtgrp) { - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { - list_for_each_entry(schema, &resctrl_schema_all, list) { - seq_printf(s, "%s:uninitialized\n", schema->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->s->res->name, - rdtgrp->plr->d->hdr.id, - rdtgrp->plr->cbm); - } - } else { - closid = rdtgrp->closid; - list_for_each_entry(schema, &resctrl_schema_all, list) { - if (closid < schema->num_closid) - show_doms(s, schema, closid); - } - } - } else { - ret = -ENOENT; - } - rdtgroup_kn_unlock(of->kn); - return ret; -} - -static int smp_mon_event_count(void *arg) -{ - mon_event_count(arg); - - return 0; -} - -void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, - cpumask_t *cpumask, int evtid, int first) -{ - int cpu; - - /* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - /* - * Setup the parameters to pass to mon_event_count() to read the data. - */ - rr->rgrp = rdtgrp; - rr->evtid = evtid; - rr->r = r; - rr->d = d; - rr->first = first; - rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid); - if (IS_ERR(rr->arch_mon_ctx)) { - rr->err = -EINVAL; - return; - } - - cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU); - - /* - * cpumask_any_housekeeping() prefers housekeeping CPUs, but - * are all the CPUs nohz_full? If yes, pick a CPU to IPI. - * MPAM's resctrl_arch_rmid_read() is unable to read the - * counters on some platforms if its called in IRQ context. - */ - if (tick_nohz_full_cpu(cpu)) - smp_call_function_any(cpumask, mon_event_count, rr, 1); - else - smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); - - resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx); -} - -int rdtgroup_mondata_show(struct seq_file *m, void *arg) -{ - struct kernfs_open_file *of = m->private; - struct rdt_domain_hdr *hdr; - struct rmid_read rr = {0}; - struct rdt_mon_domain *d; - u32 resid, evtid; - struct rdtgroup *rdtgrp; - int domid, cpu, ret = 0; - struct rdt_resource *r; - struct cacheinfo *ci; - union mon_data_bits md; - - 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].r_resctrl; - - if (md.u.sum) { - /* - * This file requires summing across all domains that share - * the L3 cache id that was provided in the "domid" field of the - * mon_data_bits union. Search all domains in the resource for - * one that matches this cache id. - */ - list_for_each_entry(d, &r->mon_domains, hdr.list) { - if (d->ci_id == domid) { - cpu = cpumask_any(&d->hdr.cpu_mask); - ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!ci) - continue; - rr.ci = ci; - mon_event_read(&rr, r, NULL, rdtgrp, - &ci->shared_cpu_map, evtid, false); - goto checkresult; - } - } - ret = -ENOENT; - goto out; - } else { - /* - * This file provides data from a single domain. Search - * the resource to find the domain with "domid". - */ - hdr = rdt_find_domain(&r->mon_domains, domid, NULL); - if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) { - ret = -ENOENT; - goto out; - } - d = container_of(hdr, struct rdt_mon_domain, hdr); - mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false); - } - -checkresult: - - if (rr.err == -EIO) - seq_puts(m, "Error\n"); - else if (rr.err == -EINVAL) - seq_puts(m, "Unavailable\n"); - else - seq_printf(m, "%llu\n", rr.val); - -out: - rdtgroup_kn_unlock(of->kn); - return ret; -} diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c new file mode 100644 index 0000000000000..89b8b619d5d53 --- /dev/null +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Intel Application Energy Telemetry + * + * Copyright (C) 2025 Intel Corporation + * + * Author: + * Tony Luck + */ + +#define pr_fmt(fmt) "resctrl: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +/** + * struct pmt_event - Telemetry event. + * @id: Resctrl event id. + * @idx: Counter index within each per-RMID block of counters. + * @bin_bits: Zero for integer valued events, else number bits in fraction + * part of fixed-point. + */ +struct pmt_event { + enum resctrl_event_id id; + unsigned int idx; + unsigned int bin_bits; +}; + +#define EVT(_id, _idx, _bits) { .id = _id, .idx = _idx, .bin_bits = _bits } + +/** + * struct event_group - Events with the same feature type ("energy" or "perf") and GUID. + * @pfname: PMT feature name ("energy" or "perf") of this event group. + * Used by boot rdt= option. + * @pfg: Points to the aggregated telemetry space information + * returned by the intel_pmt_get_regions_by_feature() + * call to the INTEL_PMT_TELEMETRY driver that contains + * data for all telemetry regions of type @pfname. + * Valid if the system supports the event group, + * NULL otherwise. + * @force_off: True when "rdt" command line or architecture code disables + * this event group due to insufficient RMIDs. + * @force_on: True when "rdt" command line overrides disable of this + * event group. + * @guid: Unique number per XML description file. + * @num_rmid: Number of RMIDs supported by this group. May be + * adjusted downwards if enumeration from + * intel_pmt_get_regions_by_feature() indicates fewer + * RMIDs can be tracked simultaneously. + * @mmio_size: Number of bytes of MMIO registers for this group. + * @num_events: Number of events in this group. + * @evts: Array of event descriptors. + */ +struct event_group { + /* Data fields for additional structures to manage this group. */ + const char *pfname; + struct pmt_feature_group *pfg; + bool force_off, force_on; + + /* Remaining fields initialized from XML file. */ + u32 guid; + u32 num_rmid; + size_t mmio_size; + unsigned int num_events; + struct pmt_event evts[] __counted_by(num_events); +}; + +#define XML_MMIO_SIZE(num_rmids, num_events, num_extra_status) \ + (((num_rmids) * (num_events) + (num_extra_status)) * sizeof(u64)) + +/* + * Link: https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml + */ +static struct event_group energy_0x26696143 = { + .pfname = "energy", + .guid = 0x26696143, + .num_rmid = 576, + .mmio_size = XML_MMIO_SIZE(576, 2, 3), + .num_events = 2, + .evts = { + EVT(PMT_EVENT_ENERGY, 0, 18), + EVT(PMT_EVENT_ACTIVITY, 1, 18), + } +}; + +/* + * Link: https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-PERF/cwf_aggregator.xml + */ +static struct event_group perf_0x26557651 = { + .pfname = "perf", + .guid = 0x26557651, + .num_rmid = 576, + .mmio_size = XML_MMIO_SIZE(576, 7, 3), + .num_events = 7, + .evts = { + EVT(PMT_EVENT_STALLS_LLC_HIT, 0, 0), + EVT(PMT_EVENT_C1_RES, 1, 0), + EVT(PMT_EVENT_UNHALTED_CORE_CYCLES, 2, 0), + EVT(PMT_EVENT_STALLS_LLC_MISS, 3, 0), + EVT(PMT_EVENT_AUTO_C6_RES, 4, 0), + EVT(PMT_EVENT_UNHALTED_REF_CYCLES, 5, 0), + EVT(PMT_EVENT_UOPS_RETIRED, 6, 0), + } +}; + +static struct event_group *known_event_groups[] = { + &energy_0x26696143, + &perf_0x26557651, +}; + +#define for_each_event_group(_peg) \ + for (_peg = known_event_groups; \ + _peg < &known_event_groups[ARRAY_SIZE(known_event_groups)]; \ + _peg++) + +bool intel_handle_aet_option(bool force_off, char *tok) +{ + struct event_group **peg; + bool ret = false; + u32 guid = 0; + char *name; + + if (!tok) + return false; + + name = strsep(&tok, ":"); + if (tok && kstrtou32(tok, 16, &guid)) + return false; + + for_each_event_group(peg) { + if (strcmp(name, (*peg)->pfname)) + continue; + if (guid && (*peg)->guid != guid) + continue; + if (force_off) + (*peg)->force_off = true; + else + (*peg)->force_on = true; + ret = true; + } + + return ret; +} + +static bool skip_telem_region(struct telemetry_region *tr, struct event_group *e) +{ + if (tr->guid != e->guid) + return true; + if (tr->plat_info.package_id >= topology_max_packages()) { + pr_warn("Bad package %u in guid 0x%x\n", tr->plat_info.package_id, + tr->guid); + return true; + } + if (tr->size != e->mmio_size) { + pr_warn("MMIO space wrong size (%zu bytes) for guid 0x%x. Expected %zu bytes.\n", + tr->size, e->guid, e->mmio_size); + return true; + } + + return false; +} + +static bool group_has_usable_regions(struct event_group *e, struct pmt_feature_group *p) +{ + bool usable_regions = false; + + for (int i = 0; i < p->count; i++) { + if (skip_telem_region(&p->regions[i], e)) { + /* + * Clear the address field of regions that did not pass the checks in + * skip_telem_region() so they will not be used by intel_aet_read_event(). + * This is safe to do because intel_pmt_get_regions_by_feature() allocates + * a new pmt_feature_group structure to return to each caller and only makes + * use of the pmt_feature_group::kref field when intel_pmt_put_feature_group() + * returns the structure. + */ + p->regions[i].addr = NULL; + + continue; + } + usable_regions = true; + } + + return usable_regions; +} + +static bool all_regions_have_sufficient_rmid(struct event_group *e, struct pmt_feature_group *p) +{ + struct telemetry_region *tr; + + for (int i = 0; i < p->count; i++) { + if (!p->regions[i].addr) + continue; + tr = &p->regions[i]; + if (tr->num_rmids < e->num_rmid) { + e->force_off = true; + return false; + } + } + + return true; +} + +static bool enable_events(struct event_group *e, struct pmt_feature_group *p) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl; + int skipped_events = 0; + + if (e->force_off) + return false; + + if (!group_has_usable_regions(e, p)) + return false; + + /* + * Only enable event group with insufficient RMIDs if the user requested + * it from the kernel command line. + */ + if (!all_regions_have_sufficient_rmid(e, p) && !e->force_on) { + pr_info("%s %s:0x%x monitoring not enabled due to insufficient RMIDs\n", + r->name, e->pfname, e->guid); + return false; + } + + for (int i = 0; i < p->count; i++) { + if (!p->regions[i].addr) + continue; + /* + * e->num_rmid only adjusted lower if user (via rdt= kernel + * parameter) forces an event group with insufficient RMID + * to be enabled. + */ + e->num_rmid = min(e->num_rmid, p->regions[i].num_rmids); + } + + for (int j = 0; j < e->num_events; j++) { + if (!resctrl_enable_mon_event(e->evts[j].id, true, + e->evts[j].bin_bits, &e->evts[j])) + skipped_events++; + } + if (e->num_events == skipped_events) { + pr_info("No events enabled in %s %s:0x%x\n", r->name, e->pfname, e->guid); + return false; + } + + if (r->mon.num_rmid) + r->mon.num_rmid = min(r->mon.num_rmid, e->num_rmid); + else + r->mon.num_rmid = e->num_rmid; + + if (skipped_events) + pr_info("%s %s:0x%x monitoring detected (skipped %d events)\n", r->name, + e->pfname, e->guid, skipped_events); + else + pr_info("%s %s:0x%x monitoring detected\n", r->name, e->pfname, e->guid); + + return true; +} + +static enum pmt_feature_id lookup_pfid(const char *pfname) +{ + if (!strcmp(pfname, "energy")) + return FEATURE_PER_RMID_ENERGY_TELEM; + else if (!strcmp(pfname, "perf")) + return FEATURE_PER_RMID_PERF_TELEM; + + pr_warn("Unknown PMT feature name '%s'\n", pfname); + + return FEATURE_INVALID; +} + +/* + * Request a copy of struct pmt_feature_group for each event group. If there is + * one, the returned structure has an array of telemetry_region structures, + * each element of the array describes one telemetry aggregator. The + * telemetry aggregators may have different GUIDs so obtain duplicate struct + * pmt_feature_group for event groups with same feature type but different + * GUID. Post-processing ensures an event group can only use the telemetry + * aggregators that match its GUID. An event group keeps a pointer to its + * struct pmt_feature_group to indicate that its events are successfully + * enabled. + */ +bool intel_aet_get_events(void) +{ + struct pmt_feature_group *p; + enum pmt_feature_id pfid; + struct event_group **peg; + bool ret = false; + + for_each_event_group(peg) { + pfid = lookup_pfid((*peg)->pfname); + p = intel_pmt_get_regions_by_feature(pfid); + if (IS_ERR_OR_NULL(p)) + continue; + if (enable_events(*peg, p)) { + (*peg)->pfg = p; + ret = true; + } else { + intel_pmt_put_feature_group(p); + } + } + + return ret; +} + +void __exit intel_aet_exit(void) +{ + struct event_group **peg; + + for_each_event_group(peg) { + if ((*peg)->pfg) { + intel_pmt_put_feature_group((*peg)->pfg); + (*peg)->pfg = NULL; + } + } +} + +#define DATA_VALID BIT_ULL(63) +#define DATA_BITS GENMASK_ULL(62, 0) + +/* + * Read counter for an event on a domain (summing all aggregators on the + * domain). If an aggregator hasn't received any data for a specific RMID, + * the MMIO read indicates that data is not valid. Return success if at + * least one aggregator has valid data. + */ +int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val) +{ + struct pmt_event *pevt = arch_priv; + struct event_group *e; + bool valid = false; + u64 total = 0; + u64 evtcount; + void *pevt0; + u32 idx; + + pevt0 = pevt - pevt->idx; + e = container_of(pevt0, struct event_group, evts); + idx = rmid * e->num_events; + idx += pevt->idx; + + if (idx * sizeof(u64) + sizeof(u64) > e->mmio_size) { + pr_warn_once("MMIO index %u out of range\n", idx); + return -EIO; + } + + for (int i = 0; i < e->pfg->count; i++) { + if (!e->pfg->regions[i].addr) + continue; + if (e->pfg->regions[i].plat_info.package_id != domid) + continue; + evtcount = readq(e->pfg->regions[i].addr + idx * sizeof(u64)); + if (!(evtcount & DATA_VALID)) + continue; + total += evtcount & DATA_BITS; + valid = true; + } + + if (valid) + *val = total; + + return valid ? 0 : -EINVAL; +} + +void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos) +{ + struct rdt_perf_pkg_mon_domain *d; + int err; + + d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu)); + if (!d) + return; + + d->hdr.id = id; + d->hdr.type = RESCTRL_MON_DOMAIN; + d->hdr.rid = RDT_RESOURCE_PERF_PKG; + cpumask_set_cpu(cpu, &d->hdr.cpu_mask); + list_add_tail_rcu(&d->hdr.list, add_pos); + + err = resctrl_online_mon_domain(r, &d->hdr); + if (err) { + list_del_rcu(&d->hdr.list); + synchronize_rcu(); + kfree(d); + } +} diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 168962166a918..2d76a02872e0c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -3,31 +3,24 @@ #define _ASM_X86_RESCTRL_INTERNAL_H #include -#include -#include -#include -#include -#include - -#include #define L3_QOS_CDP_ENABLE 0x01ULL #define L2_QOS_CDP_ENABLE 0x01ULL -#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 MBM_CNTR_WIDTH_OFFSET_AMD 20 /* Hygon MBM counter width as an offset from MBM_CNTR_WIDTH_BASE */ #define MBM_CNTR_WIDTH_OFFSET_HYGON 8 #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 @@ -35,341 +28,6 @@ */ #define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE) -/* Reads to Local DRAM Memory */ -#define READS_TO_LOCAL_MEM BIT(0) - -/* Reads to Remote DRAM Memory */ -#define READS_TO_REMOTE_MEM BIT(1) - -/* Non-Temporal Writes to Local Memory */ -#define NON_TEMP_WRITE_TO_LOCAL_MEM BIT(2) - -/* Non-Temporal Writes to Remote Memory */ -#define NON_TEMP_WRITE_TO_REMOTE_MEM BIT(3) - -/* Reads to Local Memory the system identifies as "Slow Memory" */ -#define READS_TO_LOCAL_S_MEM BIT(4) - -/* Reads to Remote Memory the system identifies as "Slow Memory" */ -#define READS_TO_REMOTE_S_MEM BIT(5) - -/* Dirty Victims to All Types of Memory */ -#define DIRTY_VICTIMS_TO_ALL_MEM BIT(6) - -/* Max event bits supported */ -#define MAX_EVT_CONFIG_BITS GENMASK(6, 0) - -/** - * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that - * aren't marked nohz_full - * @mask: The mask to pick a CPU from. - * @exclude_cpu:The CPU to avoid picking. - * - * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping - * CPUs that don't use nohz_full, these are preferred. Pass - * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs. - * - * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available. - */ -static inline unsigned int -cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu) -{ - unsigned int cpu, hk_cpu; - - if (exclude_cpu == RESCTRL_PICK_ANY_CPU) - cpu = cpumask_any(mask); - else - cpu = cpumask_any_but(mask, exclude_cpu); - - /* Only continue if tick_nohz_full_mask has been initialized. */ - if (!tick_nohz_full_enabled()) - return cpu; - - /* If the CPU picked isn't marked nohz_full nothing more needs doing. */ - if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu)) - return cpu; - - /* Try to find a CPU that isn't nohz_full to use in preference */ - hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask); - if (hk_cpu == exclude_cpu) - hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask); - - if (hk_cpu < nr_cpu_ids) - cpu = hk_cpu; - - return cpu; -} - -struct rdt_fs_context { - struct kernfs_fs_context kfc; - bool enable_cdpl2; - bool enable_cdpl3; - bool enable_mba_mbps; - bool enable_debug; -}; - -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); -} - -/** - * struct mon_evt - Entry in the event list of a resource - * @evtid: event id - * @name: name of the event - * @configurable: true if the event is configurable - * @list: entry in &rdt_resource->evt_list - */ -struct mon_evt { - enum resctrl_event_id evtid; - char *name; - bool configurable; - struct list_head list; -}; - -/** - * union mon_data_bits - Monitoring details for each event file. - * @priv: Used to store monitoring event data in @u - * as kernfs private data. - * @u.rid: Resource id associated with the event file. - * @u.evtid: Event id associated with the event file. - * @u.sum: Set when event must be summed across multiple - * domains. - * @u.domid: When @u.sum is zero this is the domain to which - * the event file belongs. When @sum is one this - * is the id of the L3 cache that all domains to be - * summed share. - * @u: Name of the bit fields struct. - */ -union mon_data_bits { - void *priv; - struct { - unsigned int rid : 10; - enum resctrl_event_id evtid : 7; - unsigned int sum : 1; - unsigned int domid : 14; - } u; -}; - -/** - * struct rmid_read - Data passed across smp_call*() to read event count. - * @rgrp: Resource group for which the counter is being read. If it is a parent - * resource group then its event count is summed with the count from all - * its child resource groups. - * @r: Resource describing the properties of the event being read. - * @d: Domain that the counter should be read from. If NULL then sum all - * domains in @r sharing L3 @ci.id - * @evtid: Which monitor event to read. - * @first: Initialize MBM counter when true. - * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains. - * @err: Error encountered when reading counter. - * @val: Returned value of event counter. If @rgrp is a parent resource group, - * @val includes the sum of event counts from its child resource groups. - * If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id, - * (summed across child resource groups if @rgrp is a parent resource group). - * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only). - */ -struct rmid_read { - struct rdtgroup *rgrp; - struct rdt_resource *r; - struct rdt_mon_domain *d; - enum resctrl_event_id evtid; - bool first; - struct cacheinfo *ci; - int err; - u64 val; - void *arch_mon_ctx; -}; - -extern unsigned int rdt_mon_features; -extern struct list_head resctrl_schema_all; -extern bool resctrl_mounted; - -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 - * @RDT_NUM_MODES: Total number of modes - * - * 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: kernfs 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 - * @s: Resctrl schema for the 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 resctrl_schema *s; - struct rdt_ctrl_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 RFTYPE_CTRL BIT(4) -#define RFTYPE_MON BIT(5) -#define RFTYPE_TOP BIT(6) -#define RFTYPE_RES_CACHE BIT(8) -#define RFTYPE_RES_MB BIT(9) -#define RFTYPE_DEBUG BIT(10) -#define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) -#define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) -#define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) -#define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) -#define RFTYPE_MON_BASE (RFTYPE_BASE | RFTYPE_MON) - -/* 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 RFTYPE_* flags - * @seq_show: Show content of the file - * @write: Write to the file - */ -struct rftype { - char *name; - umode_t mode; - const 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 - * @prev_bw_bytes: Previous bytes value read for bandwidth calculation - * @prev_bw: The most recent bandwidth in MBps - */ -struct mbm_state { - u64 prev_bw_bytes; - u32 prev_bw; -}; - /** * struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s * return value. @@ -382,6 +40,15 @@ struct arch_mbm_state { u64 prev_msr; }; +/* Setting bit 0 in L3_QOS_EXT_CFG enables the ABMC feature. */ +#define ABMC_ENABLE_BIT 0 + +/* + * Qos Event Identifiers. + */ +#define ABMC_EXTENDED_EVT_ID BIT(31) +#define ABMC_EVT_ID BIT(0) + /** * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share * a resource for a control function @@ -396,18 +63,18 @@ struct rdt_hw_ctrl_domain { }; /** - * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share - * a resource for a monitor function - * @d_resctrl: Properties exposed to the resctrl file system - * @arch_mbm_total: arch private state for MBM total bandwidth - * @arch_mbm_local: arch private state for MBM local bandwidth + * struct rdt_hw_l3_mon_domain - Arch private attributes of a set of CPUs sharing + * RDT_RESOURCE_L3 monitoring + * @d_resctrl: Properties exposed to the resctrl file system + * @arch_mbm_states: Per-event pointer to the MBM event's saved state. + * An MBM event's state is an array of struct arch_mbm_state + * indexed by RMID on x86. * * Members of this structure are accessed via helpers that provide abstraction. */ -struct rdt_hw_mon_domain { - struct rdt_mon_domain d_resctrl; - struct arch_mbm_state *arch_mbm_total; - struct arch_mbm_state *arch_mbm_local; +struct rdt_hw_l3_mon_domain { + struct rdt_l3_mon_domain d_resctrl; + struct arch_mbm_state *arch_mbm_states[QOS_NUM_L3_MBM_EVENTS]; }; static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r) @@ -415,11 +82,19 @@ static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctr return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl); } -static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r) +static inline struct rdt_hw_l3_mon_domain *resctrl_to_arch_mon_dom(struct rdt_l3_mon_domain *r) { - return container_of(r, struct rdt_hw_mon_domain, d_resctrl); + return container_of(r, struct rdt_hw_l3_mon_domain, d_resctrl); } +/** + * struct rdt_perf_pkg_mon_domain - CPUs sharing an package scoped resctrl monitor resource + * @hdr: common header for different domain types + */ +struct rdt_perf_pkg_mon_domain { + struct rdt_domain_hdr hdr; +}; + /** * struct msr_param - set a range of MSRs from a domain * @res: The resource to use @@ -434,37 +109,6 @@ struct msr_param { u32 high; }; -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_hw_resource - arch private attributes of a resctrl resource * @r_resctrl: Attributes of the resource used directly by resctrl. @@ -477,9 +121,8 @@ struct rdt_parse_data { * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. - * @mbm_cfg_mask: Bandwidth sources that can be tracked when Bandwidth - * Monitoring Event Configuration (BMEC) is supported. * @cdp_enabled: CDP state of this resource + * @mbm_cntr_assign_enabled: ABMC feature is enabled * * Members of this structure are either private to the architecture * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g. @@ -492,8 +135,8 @@ struct rdt_hw_resource { void (*msr_update)(struct msr_param *m); unsigned int mon_scale; unsigned int mbm_width; - unsigned int mbm_cfg_mask; bool cdp_enabled; + bool mbm_cntr_assign_enabled; }; static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r) @@ -501,64 +144,9 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r return container_of(r, struct rdt_hw_resource, r_resctrl); } -int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_ctrl_domain *d); -int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_ctrl_domain *d); - -extern struct mutex rdtgroup_mutex; - extern struct rdt_hw_resource rdt_resources_all[]; -extern struct rdtgroup rdtgroup_default; -extern struct dentry *debugfs_resctrl; - -enum resctrl_res_level { - RDT_RESOURCE_L3, - RDT_RESOURCE_L2, - RDT_RESOURCE_MBA, - RDT_RESOURCE_SMBA, - - /* Must be the last */ - RDT_NUM_RESOURCES, -}; - -static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res) -{ - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res); - - hw_res++; - return &hw_res->r_resctrl; -} - -static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l) -{ - return rdt_resources_all[l].cdp_enabled; -} - -int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); - -void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d); - -/* - * To return the common struct rdt_resource, which is contained in struct - * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource. - */ -#define for_each_rdt_resource(r) \ - for (r = &rdt_resources_all[0].r_resctrl; \ - r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl; \ - r = resctrl_inc(r)) - -#define for_each_capable_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->alloc_capable || r->mon_capable) -#define for_each_alloc_capable_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->alloc_capable) - -#define for_each_mon_capable_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->mon_capable) +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d); /* CPUID.(EAX=10H, ECX=ResID=1).EAX */ union cpuid_0x10_1_eax { @@ -593,67 +181,71 @@ union cpuid_0x10_x_edx { unsigned int full; }; -void rdt_last_cmd_clear(void); -void rdt_last_cmd_puts(const char *s); -__printf(1, 2) -void rdt_last_cmd_printf(const char *fmt, ...); +/* + * ABMC counters are configured by writing to MSR_IA32_L3_QOS_ABMC_CFG. + * + * @bw_type : Event configuration that represents the memory + * transactions being tracked by the @cntr_id. + * @bw_src : Bandwidth source (RMID or CLOSID). + * @reserved1 : Reserved. + * @is_clos : @bw_src field is a CLOSID (not an RMID). + * @cntr_id : Counter identifier. + * @reserved : Reserved. + * @cntr_en : Counting enable bit. + * @cfg_en : Configuration enable bit. + * + * Configuration and counting: + * Counter can be configured across multiple writes to MSR. Configuration + * is applied only when @cfg_en = 1. Counter @cntr_id is reset when the + * configuration is applied. + * @cfg_en = 1, @cntr_en = 0 : Apply @cntr_id configuration but do not + * count events. + * @cfg_en = 1, @cntr_en = 1 : Apply @cntr_id configuration and start + * counting events. + */ +union l3_qos_abmc_cfg { + struct { + unsigned long bw_type :32, + bw_src :12, + reserved1: 3, + is_clos : 1, + cntr_id : 5, + reserved : 9, + cntr_en : 1, + cfg_en : 1; + } split; + unsigned long full; +}; 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_hdr *rdt_find_domain(struct list_head *h, 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 resctrl_schema *s, struct rdt_ctrl_domain *d, - unsigned long cbm, int closid, bool exclusive); -unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_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_ctrl_domain *d, unsigned long cbm); -bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_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_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r); -struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r); -int closids_supported(void); -void closid_free(int closid); -int alloc_rmid(u32 closid); -void free_rmid(u32 closid, u32 rmid); -int rdt_get_mon_l3_config(struct rdt_resource *r); -void __exit rdt_put_mon_l3_config(void); -bool __init rdt_cpu_has(int flag); -void mon_event_count(void *info); -int rdtgroup_mondata_show(struct seq_file *m, void *arg); -void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, - struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, - cpumask_t *cpumask, int evtid, int first); -void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, - unsigned long delay_ms, - int exclude_cpu); -void mbm_handle_overflow(struct work_struct *work); + +int rdt_get_l3_mon_config(struct rdt_resource *r); + +bool rdt_cpu_has(int flag); + void __init intel_rdt_mbm_apply_quirk(void); -bool is_mba_sc(struct rdt_resource *r); -void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, - int exclude_cpu); -void cqm_handle_limbo(struct work_struct *work); -bool has_busy_rmid(struct rdt_mon_domain *d); -void __check_limbo(struct rdt_mon_domain *d, bool force_free); + void rdt_domain_reconfigure_cdp(struct rdt_resource *r); -void __init thread_throttle_mode_init(void); -void __init mbm_config_rftype_init(const char *config); -void rdt_staged_configs_clear(void); -bool closid_allocated(unsigned int closid); -int resctrl_find_cleanest_closid(void); +void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r); + +#ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET +bool intel_aet_get_events(void); +void __exit intel_aet_exit(void); +int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val); +void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos); +bool intel_handle_aet_option(bool force_off, char *tok); +#else +static inline bool intel_aet_get_events(void) { return false; } +static inline void __exit intel_aet_exit(void) { } +static inline int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val) +{ + return -EINVAL; +} + +static inline void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r, + struct list_head *add_pos) { } +static inline bool intel_handle_aet_option(bool force_off, char *tok) { return false; } +#endif #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 879782df8c1b1..091a3dbd6aaf3 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -18,62 +18,11 @@ #define pr_fmt(fmt) "resctrl: " fmt #include -#include -#include -#include +#include #include -#include #include "internal.h" -#include "trace.h" - -/** - * struct rmid_entry - dirty tracking for all RMID. - * @closid: The CLOSID for this entry. - * @rmid: The RMID for this entry. - * @busy: The number of domains with cached data using this RMID. - * @list: Member of the rmid_free_lru list when busy == 0. - * - * Depending on the architecture the correct monitor is accessed using - * both @closid and @rmid, or @rmid only. - * - * Take the rdtgroup_mutex when accessing. - */ -struct rmid_entry { - u32 closid; - 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); - -/* - * @closid_num_dirty_rmid The number of dirty RMID each CLOSID has. - * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined. - * Indexed by CLOSID. Protected by rdtgroup_mutex. - */ -static u32 *closid_num_dirty_rmid; - -/* - * @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 > resctrl_rmid_realloc_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 @@ -81,28 +30,12 @@ static struct rmid_entry *rmid_ptrs; */ bool rdt_mon_capable; -/* - * Global to indicate which monitoring events are enabled. - */ -unsigned int rdt_mon_features; - -/* - * This is the threshold cache occupancy in bytes at which we will consider an - * RMID available for re-allocation. - */ -unsigned int resctrl_rmid_realloc_threshold; - -/* - * This is the maximum value for the reallocation threshold, in bytes. - */ -unsigned int resctrl_rmid_realloc_limit; - #define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5)) static int snc_nodes_per_l3_cache = 1; /* - * The correction factor table is documented in Documentation/arch/x86/resctrl.rst. + * The correction factor table is documented in Documentation/filesystems/resctrl.rst. * If rmid > rmid threshold, MBM total and local values should be multiplied * by the correction factor. * @@ -151,6 +84,7 @@ static const struct mbm_correction_factor_table { }; static u32 mbm_cf_rmidthreshold __read_mostly = UINT_MAX; + static u64 mbm_cf __read_mostly; static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) @@ -162,33 +96,6 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) return val; } -/* - * x86 and arm64 differ in their handling of monitoring. - * x86's RMID are independent numbers, there is only one source of traffic - * with an RMID value of '1'. - * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of - * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID - * value is no longer unique. - * To account for this, resctrl uses an index. On x86 this is just the RMID, - * on arm64 it encodes the CLOSID and RMID. This gives a unique number. - * - * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code - * must accept an attempt to read every index. - */ -static inline struct rmid_entry *__rmid_entry(u32 idx) -{ - struct rmid_entry *entry; - u32 closid, rmid; - - entry = &rmid_ptrs[idx]; - resctrl_arch_rmid_idx_decode(idx, &closid, &rmid); - - WARN_ON_ONCE(entry->closid != closid); - WARN_ON_ONCE(entry->rmid != rmid); - - return entry; -} - /* * When Sub-NUMA Cluster (SNC) mode is not enabled (as indicated by * "snc_nodes_per_l3_cache == 1") no translation of the RMID value is @@ -201,7 +108,7 @@ static inline struct rmid_entry *__rmid_entry(u32 idx) * * In RMID sharing mode there are fewer "logical RMID" values available * to accumulate data ("physical RMIDs" are divided evenly between SNC - * nodes that share an L3 cache). Linux creates an rdt_mon_domain for + * nodes that share an L3 cache). Linux creates an rdt_l3_mon_domain for * each SNC node. * * The value loaded into IA32_PQR_ASSOC is the "logical RMID". @@ -222,7 +129,7 @@ static int logical_rmid_to_physical_rmid(int cpu, int lrmid) if (snc_nodes_per_l3_cache == 1) return lrmid; - return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid; + return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->mon.num_rmid; } static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val) @@ -249,30 +156,25 @@ static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val) return 0; } -static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom, +static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_l3_mon_domain *hw_dom, u32 rmid, enum resctrl_event_id eventid) { - switch (eventid) { - case QOS_L3_OCCUP_EVENT_ID: + struct arch_mbm_state *state; + + if (!resctrl_is_mbm_event(eventid)) return NULL; - case QOS_L3_MBM_TOTAL_EVENT_ID: - return &hw_dom->arch_mbm_total[rmid]; - case QOS_L3_MBM_LOCAL_EVENT_ID: - return &hw_dom->arch_mbm_local[rmid]; - } - /* Never expect to get here */ - WARN_ON_ONCE(1); + state = hw_dom->arch_mbm_states[MBM_STATE_IDX(eventid)]; - return NULL; + return state ? &state[rmid] : NULL; } -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 unused, u32 rmid, enum resctrl_event_id eventid) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); int cpu = cpumask_any(&d->hdr.cpu_mask); struct arch_mbm_state *am; u32 prmid; @@ -291,17 +193,19 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, * Assumes that hardware counters are also reset and thus that there is * no need to record initial non-zero counts. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d) +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + enum resctrl_event_id eventid; + int idx; - if (is_mbm_total_enabled()) - memset(hw_dom->arch_mbm_total, 0, - sizeof(*hw_dom->arch_mbm_total) * r->num_rmid); - - if (is_mbm_local_enabled()) - memset(hw_dom->arch_mbm_local, 0, - sizeof(*hw_dom->arch_mbm_local) * r->num_rmid); + for_each_mbm_event_id(eventid) { + if (!resctrl_is_mon_event_enabled(eventid)) + continue; + idx = MBM_STATE_IDX(eventid); + memset(hw_dom->arch_mbm_states[idx], 0, + sizeof(*hw_dom->arch_mbm_states[0]) * r->mon.num_rmid); + } } static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) @@ -312,30 +216,15 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) return chunks >> shift; } -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, - u32 unused, u32 rmid, enum resctrl_event_id eventid, - u64 *val, void *ignored) +static u64 get_corrected_val(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + u32 rmid, enum resctrl_event_id eventid, u64 msr_val) { - struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - int cpu = cpumask_any(&d->hdr.cpu_mask); struct arch_mbm_state *am; - u64 msr_val, chunks; - u32 prmid; - int ret; - - resctrl_arch_rmid_read_context_check(); + u64 chunks; am = get_arch_mbm_state(hw_dom, rmid, eventid); - - prmid = logical_rmid_to_physical_rmid(cpu, rmid); - ret = __rmid_read_phys(prmid, eventid, &msr_val); - if (ret) { - if (am && ret == -EINVAL) - am->prev_msr = 0; - return ret; - } - if (am) { am->chunks += mbm_overflow_count(am->prev_msr, msr_val, hw_res->mbm_width); @@ -345,756 +234,113 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, chunks = msr_val; } - *val = chunks * hw_res->mon_scale; - - return 0; -} - -static void limbo_release_entry(struct rmid_entry *entry) -{ - lockdep_assert_held(&rdtgroup_mutex); - - rmid_limbo_count--; - list_add_tail(&entry->list, &rmid_free_lru); - - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) - closid_num_dirty_rmid[entry->closid]--; -} - -/* - * 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_mon_domain *d, bool force_free) -{ - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - u32 idx_limit = resctrl_arch_system_num_rmid_idx(); - struct rmid_entry *entry; - u32 idx, cur_idx = 1; - void *arch_mon_ctx; - bool rmid_dirty; - u64 val = 0; - - arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID); - if (IS_ERR(arch_mon_ctx)) { - pr_warn_ratelimited("Failed to allocate monitor context: %ld", - PTR_ERR(arch_mon_ctx)); - return; - } - - /* - * 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 (;;) { - idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx); - if (idx >= idx_limit) - break; - - entry = __rmid_entry(idx); - if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, &val, - arch_mon_ctx)) { - rmid_dirty = true; - } else { - rmid_dirty = (val >= resctrl_rmid_realloc_threshold); - - /* - * x86's CLOSID and RMID are independent numbers, so the entry's - * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the - * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't - * used to select the configuration. It is thus necessary to track both - * CLOSID and RMID because there may be dependencies between them - * on some architectures. - */ - trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val); - } - - if (force_free || !rmid_dirty) { - clear_bit(idx, d->rmid_busy_llc); - if (!--entry->busy) - limbo_release_entry(entry); - } - cur_idx = idx + 1; - } - - resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); -} - -bool has_busy_rmid(struct rdt_mon_domain *d) -{ - u32 idx_limit = resctrl_arch_system_num_rmid_idx(); - - return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit; -} - -static struct rmid_entry *resctrl_find_free_rmid(u32 closid) -{ - struct rmid_entry *itr; - u32 itr_idx, cmp_idx; - - if (list_empty(&rmid_free_lru)) - return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC); - - list_for_each_entry(itr, &rmid_free_lru, list) { - /* - * Get the index of this free RMID, and the index it would need - * to be if it were used with this CLOSID. - * If the CLOSID is irrelevant on this architecture, the two - * index values are always the same on every entry and thus the - * very first entry will be returned. - */ - itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid); - cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid); - - if (itr_idx == cmp_idx) - return itr; - } - - return ERR_PTR(-ENOSPC); -} - -/** - * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated - * RMID are clean, or the CLOSID that has - * the most clean RMID. - * - * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID - * may not be able to allocate clean RMID. To avoid this the allocator will - * choose the CLOSID with the most clean RMID. - * - * When the CLOSID and RMID are independent numbers, the first free CLOSID will - * be returned. - */ -int resctrl_find_cleanest_closid(void) -{ - u32 cleanest_closid = ~0; - int i = 0; - - lockdep_assert_held(&rdtgroup_mutex); - - if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) - return -EIO; - - for (i = 0; i < closids_supported(); i++) { - int num_dirty; - - if (closid_allocated(i)) - continue; - - num_dirty = closid_num_dirty_rmid[i]; - if (num_dirty == 0) - return i; - - if (cleanest_closid == ~0) - cleanest_closid = i; - - if (num_dirty < closid_num_dirty_rmid[cleanest_closid]) - cleanest_closid = i; - } - - if (cleanest_closid == ~0) - return -ENOSPC; - - return cleanest_closid; -} - -/* - * For MPAM the RMID value is not unique, and has to be considered with - * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which - * allows all domains to be managed by a single free list. - * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler. - */ -int alloc_rmid(u32 closid) -{ - struct rmid_entry *entry; - - lockdep_assert_held(&rdtgroup_mutex); - - entry = resctrl_find_free_rmid(closid); - if (IS_ERR(entry)) - return PTR_ERR(entry); - - list_del(&entry->list); - return entry->rmid; -} - -static void add_rmid_to_limbo(struct rmid_entry *entry) -{ - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - struct rdt_mon_domain *d; - u32 idx; - - lockdep_assert_held(&rdtgroup_mutex); - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); - - entry->busy = 0; - list_for_each_entry(d, &r->mon_domains, hdr.list) { - /* - * For the first limbo RMID in the domain, - * setup up the limbo worker. - */ - if (!has_busy_rmid(d)) - cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL, - RESCTRL_PICK_ANY_CPU); - set_bit(idx, d->rmid_busy_llc); - entry->busy++; - } - - rmid_limbo_count++; - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) - closid_num_dirty_rmid[entry->closid]++; -} - -void free_rmid(u32 closid, u32 rmid) -{ - u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); - struct rmid_entry *entry; - - lockdep_assert_held(&rdtgroup_mutex); - - /* - * Do not allow the default rmid to be free'd. Comparing by index - * allows architectures that ignore the closid parameter to avoid an - * unnecessary check. - */ - if (!resctrl_arch_mon_capable() || - idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, - RESCTRL_RESERVED_RMID)) - return; - - entry = __rmid_entry(idx); - - if (is_llc_occupancy_enabled()) - add_rmid_to_limbo(entry); - else - list_add_tail(&entry->list, &rmid_free_lru); -} - -static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid, - u32 rmid, enum resctrl_event_id evtid) -{ - u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); - - switch (evtid) { - case QOS_L3_MBM_TOTAL_EVENT_ID: - return &d->mbm_total[idx]; - case QOS_L3_MBM_LOCAL_EVENT_ID: - return &d->mbm_local[idx]; - default: - return NULL; - } -} - -static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) -{ - int cpu = smp_processor_id(); - struct rdt_mon_domain *d; - struct mbm_state *m; - int err, ret; - u64 tval = 0; - - if (rr->first) { - resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid); - m = get_mbm_state(rr->d, closid, rmid, rr->evtid); - if (m) - memset(m, 0, sizeof(struct mbm_state)); - return 0; - } - - if (rr->d) { - /* Reading a single domain, must be on a CPU in that domain. */ - if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask)) - return -EINVAL; - rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, - rr->evtid, &tval, rr->arch_mon_ctx); - if (rr->err) - return rr->err; - - rr->val += tval; - - return 0; - } - - /* Summing domains that share a cache, must be on a CPU for that cache. */ - if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map)) - return -EINVAL; - - /* - * Legacy files must report the sum of an event across all - * domains that share the same L3 cache instance. - * Report success if a read from any domain succeeds, -EINVAL - * (translated to "Unavailable" for user space) if reading from - * all domains fail for any reason. - */ - ret = -EINVAL; - list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { - if (d->ci_id != rr->ci->id) - continue; - err = resctrl_arch_rmid_read(rr->r, d, closid, rmid, - rr->evtid, &tval, rr->arch_mon_ctx); - if (!err) { - rr->val += tval; - ret = 0; - } - } - - if (ret) - rr->err = ret; - - return ret; + return chunks * hw_res->mon_scale; } -/* - * mbm_bw_count() - Update bw count from values previously read by - * __mon_event_count(). - * @closid: The closid used to identify the cached mbm_state. - * @rmid: The rmid used to identify the cached mbm_state. - * @rr: The struct rmid_read populated by __mon_event_count(). - * - * Supporting function to calculate the memory bandwidth - * and delta bandwidth in MBps. The chunks value previously read by - * __mon_event_count() is compared with the chunks value from the previous - * invocation. This must be called once per second to maintain values in MBps. - */ -static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) -{ - u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); - struct mbm_state *m = &rr->d->mbm_local[idx]; - u64 cur_bw, bytes, cur_bytes; - - cur_bytes = rr->val; - bytes = cur_bytes - m->prev_bw_bytes; - m->prev_bw_bytes = cur_bytes; - - cur_bw = bytes / SZ_1M; - - m->prev_bw = cur_bw; -} - -/* - * This is scheduled by mon_event_read() to read the CQM/MBM counters - * on a domain. - */ -void mon_event_count(void *info) +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr, + u32 unused, u32 rmid, enum resctrl_event_id eventid, + void *arch_priv, u64 *val, void *ignored) { - struct rdtgroup *rdtgrp, *entry; - struct rmid_read *rr = info; - struct list_head *head; + struct rdt_hw_l3_mon_domain *hw_dom; + struct rdt_l3_mon_domain *d; + struct arch_mbm_state *am; + u64 msr_val; + u32 prmid; + int cpu; int ret; - rdtgrp = rr->rgrp; - - ret = __mon_event_count(rdtgrp->closid, 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->closid, entry->mon.rmid, - rr) == 0) - ret = 0; - } - } - - /* - * __mon_event_count() calls for newly created monitor groups may - * report -EINVAL/Unavailable if the monitor hasn't seen any traffic. - * Discard error if any of the monitor event reads succeeded. - */ - if (ret == 0) - rr->err = 0; -} - -/* - * 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 bandwidth(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 unnecessarily 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_mon_domain *dom_mbm) -{ - u32 closid, rmid, cur_msr_val, new_msr_val; - struct mbm_state *pmbm_data, *cmbm_data; - struct rdt_ctrl_domain *dom_mba; - struct rdt_resource *r_mba; - u32 cur_bw, user_bw, idx; - struct list_head *head; - struct rdtgroup *entry; - - if (!is_mbm_local_enabled()) - return; - - r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; - - closid = rgrp->closid; - rmid = rgrp->mon.rmid; - idx = resctrl_arch_rmid_idx_encode(closid, rmid); - pmbm_data = &dom_mbm->mbm_local[idx]; - - dom_mba = get_ctrl_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]; - - /* MBA resource doesn't support CDP */ - cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); - - /* - * 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; - } - - /* - * Scale up/down the bandwidth linearly for the ctrl group. The - * bandwidth step is the bandwidth granularity specified by the - * hardware. - * Always increase throttling if current bandwidth is above the - * target set by user. - * But avoid thrashing up and down on every poll by checking - * whether a decrease in throttling is likely to push the group - * back over target. E.g. if currently throttling to 30% of bandwidth - * on a system with 10% granularity steps, check whether moving to - * 40% would go past the limit by multiplying current bandwidth by - * "(30 + 10) / 30". - */ - 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 * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { - new_msr_val = cur_msr_val + r_mba->membw.bw_gran; - } else { - return; - } - - resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); -} - -static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, - u32 closid, u32 rmid) -{ - struct rmid_read rr = {0}; - - 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; - rr.val = 0; - rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); - if (IS_ERR(rr.arch_mon_ctx)) { - pr_warn_ratelimited("Failed to allocate monitor context: %ld", - PTR_ERR(rr.arch_mon_ctx)); - return; - } - - __mon_event_count(closid, rmid, &rr); - - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); - } - if (is_mbm_local_enabled()) { - rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; - rr.val = 0; - rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); - if (IS_ERR(rr.arch_mon_ctx)) { - pr_warn_ratelimited("Failed to allocate monitor context: %ld", - PTR_ERR(rr.arch_mon_ctx)); - return; - } - - __mon_event_count(closid, 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(closid, rmid, &rr); - - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); - } -} - -/* - * 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); - struct rdt_mon_domain *d; + resctrl_arch_rmid_read_context_check(); - cpus_read_lock(); - mutex_lock(&rdtgroup_mutex); + if (r->rid == RDT_RESOURCE_PERF_PKG) + return intel_aet_read_event(hdr->id, rmid, arch_priv, val); - d = container_of(work, struct rdt_mon_domain, cqm_limbo.work); + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return -EINVAL; - __check_limbo(d, false); + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + hw_dom = resctrl_to_arch_mon_dom(d); + cpu = cpumask_any(&hdr->cpu_mask); + prmid = logical_rmid_to_physical_rmid(cpu, rmid); + ret = __rmid_read_phys(prmid, eventid, &msr_val); - if (has_busy_rmid(d)) { - d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask, - RESCTRL_PICK_ANY_CPU); - schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo, - delay); + if (!ret) { + *val = get_corrected_val(r, d, rmid, eventid, msr_val); + } else if (ret == -EINVAL) { + am = get_arch_mbm_state(hw_dom, rmid, eventid); + if (am) + am->prev_msr = 0; } - mutex_unlock(&rdtgroup_mutex); - cpus_read_unlock(); -} - -/** - * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this - * domain. - * @dom: The domain the limbo handler should run for. - * @delay_ms: How far in the future the handler should run. - * @exclude_cpu: Which CPU the handler should not run on, - * RESCTRL_PICK_ANY_CPU to pick any CPU. - */ -void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, - int exclude_cpu) -{ - unsigned long delay = msecs_to_jiffies(delay_ms); - int cpu; - - cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu); - dom->cqm_work_cpu = cpu; - - if (cpu < nr_cpu_ids) - schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); + return ret; } -void mbm_handle_overflow(struct work_struct *work) +static int __cntr_id_read(u32 cntr_id, u64 *val) { - unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); - struct rdtgroup *prgrp, *crgrp; - struct rdt_mon_domain *d; - struct list_head *head; - struct rdt_resource *r; - - cpus_read_lock(); - mutex_lock(&rdtgroup_mutex); - - /* - * If the filesystem has been unmounted this work no longer needs to - * run. - */ - if (!resctrl_mounted || !resctrl_arch_mon_capable()) - goto out_unlock; - - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - d = container_of(work, struct rdt_mon_domain, mbm_over.work); - - list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { - mbm_update(r, d, prgrp->closid, prgrp->mon.rmid); - - head = &prgrp->mon.crdtgrp_list; - list_for_each_entry(crgrp, head, mon.crdtgrp_list) - mbm_update(r, d, crgrp->closid, crgrp->mon.rmid); - - if (is_mba_sc(NULL)) - update_mba_bw(prgrp, d); - } + u64 msr_val; /* - * Re-check for housekeeping CPUs. This allows the overflow handler to - * move off a nohz_full CPU quickly. + * QM_EVTSEL Register definition: + * ======================================================= + * Bits Mnemonic Description + * ======================================================= + * 63:44 -- Reserved + * 43:32 RMID RMID or counter ID in ABMC mode + * when reading an MBM event + * 31 ExtendedEvtID Extended Event Identifier + * 30:8 -- Reserved + * 7:0 EvtID Event Identifier + * ======================================================= + * The contents of a specific counter can be read by setting the + * following fields in QM_EVTSEL.ExtendedEvtID(=1) and + * QM_EVTSEL.EvtID = L3CacheABMC (=1) and setting QM_EVTSEL.RMID + * to the desired counter ID. Reading the QM_CTR then returns the + * contents of the specified counter. The RMID_VAL_ERROR bit is set + * if the counter configuration is invalid, or if an invalid counter + * ID is set in the QM_EVTSEL.RMID field. The RMID_VAL_UNAVAIL bit + * is set if the counter data is unavailable. */ - d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask, - RESCTRL_PICK_ANY_CPU); - schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay); - -out_unlock: - mutex_unlock(&rdtgroup_mutex); - cpus_read_unlock(); -} - -/** - * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this - * domain. - * @dom: The domain the overflow handler should run for. - * @delay_ms: How far in the future the handler should run. - * @exclude_cpu: Which CPU the handler should not run on, - * RESCTRL_PICK_ANY_CPU to pick any CPU. - */ -void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms, - int exclude_cpu) -{ - unsigned long delay = msecs_to_jiffies(delay_ms); - int cpu; + wrmsr(MSR_IA32_QM_EVTSEL, ABMC_EXTENDED_EVT_ID | ABMC_EVT_ID, cntr_id); + rdmsrl(MSR_IA32_QM_CTR, msr_val); - /* - * When a domain comes online there is no guarantee the filesystem is - * mounted. If not, there is no need to catch counter overflow. - */ - if (!resctrl_mounted || !resctrl_arch_mon_capable()) - return; - cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu); - dom->mbm_work_cpu = cpu; + if (msr_val & RMID_VAL_ERROR) + return -EIO; + if (msr_val & RMID_VAL_UNAVAIL) + return -EINVAL; - if (cpu < nr_cpu_ids) - schedule_delayed_work_on(cpu, &dom->mbm_over, delay); + *val = msr_val; + return 0; } -static int dom_data_init(struct rdt_resource *r) +void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + u32 unused, u32 rmid, int cntr_id, + enum resctrl_event_id eventid) { - u32 idx_limit = resctrl_arch_system_num_rmid_idx(); - u32 num_closid = resctrl_arch_get_num_closid(r); - struct rmid_entry *entry = NULL; - int err = 0, i; - u32 idx; - - mutex_lock(&rdtgroup_mutex); - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - u32 *tmp; - - /* - * If the architecture hasn't provided a sanitised value here, - * this may result in larger arrays than necessary. Resctrl will - * use a smaller system wide value based on the resources in - * use. - */ - tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); - if (!tmp) { - err = -ENOMEM; - goto out_unlock; - } - - closid_num_dirty_rmid = tmp; - } - - rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); - if (!rmid_ptrs) { - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - kfree(closid_num_dirty_rmid); - closid_num_dirty_rmid = NULL; - } - err = -ENOMEM; - goto out_unlock; - } + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + struct arch_mbm_state *am; - for (i = 0; i < idx_limit; i++) { - entry = &rmid_ptrs[i]; - INIT_LIST_HEAD(&entry->list); + am = get_arch_mbm_state(hw_dom, rmid, eventid); + if (am) { + memset(am, 0, sizeof(*am)); - resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid); - list_add_tail(&entry->list, &rmid_free_lru); + /* Record any initial, non-zero count value. */ + __cntr_id_read(cntr_id, &am->prev_msr); } - - /* - * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and - * are always allocated. These are used for the rdtgroup_default - * control group, which will be setup later in rdtgroup_init(). - */ - idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, - RESCTRL_RESERVED_RMID); - entry = __rmid_entry(idx); - list_del(&entry->list); - -out_unlock: - mutex_unlock(&rdtgroup_mutex); - - return err; } -static void __exit dom_data_exit(void) +int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + u32 unused, u32 rmid, int cntr_id, + enum resctrl_event_id eventid, u64 *val) { - mutex_lock(&rdtgroup_mutex); - - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - kfree(closid_num_dirty_rmid); - closid_num_dirty_rmid = NULL; - } - - kfree(rmid_ptrs); - rmid_ptrs = NULL; - - mutex_unlock(&rdtgroup_mutex); -} - -static struct mon_evt llc_occupancy_event = { - .name = "llc_occupancy", - .evtid = QOS_L3_OCCUP_EVENT_ID, -}; + u64 msr_val; + int ret; -static struct mon_evt mbm_total_event = { - .name = "mbm_total_bytes", - .evtid = QOS_L3_MBM_TOTAL_EVENT_ID, -}; + ret = __cntr_id_read(cntr_id, &msr_val); + if (ret) + return ret; -static struct mon_evt mbm_local_event = { - .name = "mbm_local_bytes", - .evtid = QOS_L3_MBM_LOCAL_EVENT_ID, -}; + *val = get_corrected_val(r, d, rmid, eventid, msr_val); -/* - * 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); + return 0; } /* @@ -1111,7 +357,7 @@ static void l3_mon_evt_init(struct rdt_resource *r) * must adjust RMID counter numbers based on SNC node. See * logical_rmid_to_physical_rmid() for code that does this. */ -void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d) +void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d) { if (snc_nodes_per_l3_cache > 1) msr_clear_bit(MSR_RMID_SNC_CONFIG, 0); @@ -1124,6 +370,7 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, 0), X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, 0), X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, 0), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_DARKMONT_X, 0), {} }; @@ -1180,18 +427,18 @@ static __init int snc_get_config(void) return ret; } -int __init rdt_get_mon_l3_config(struct rdt_resource *r) +int __init rdt_get_l3_mon_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); unsigned int threshold; - int ret; + u32 eax, ebx, ecx, edx; snc_nodes_per_l3_cache = snc_get_config(); resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024; hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache; - r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache; + r->mon.num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache; hw_res->mbm_width = MBM_CNTR_WIDTH_BASE; if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX) @@ -1206,7 +453,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) * * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. */ - threshold = resctrl_rmid_realloc_limit / r->num_rmid; + threshold = resctrl_rmid_realloc_limit / r->mon.num_rmid; /* * Because num_rmid may not be a power of two, round the value @@ -1215,39 +462,33 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) */ resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold); - ret = dom_data_init(r); - if (ret) - return ret; - - if (rdt_cpu_has(X86_FEATURE_BMEC)) { - u32 eax, ebx, ecx, edx; - + if (rdt_cpu_has(X86_FEATURE_BMEC) || rdt_cpu_has(X86_FEATURE_ABMC)) { /* Detect list of bandwidth sources that can be tracked */ cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx); - hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; - - if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { - mbm_total_event.configurable = true; - mbm_config_rftype_init("mbm_total_bytes_config"); - } - if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { - mbm_local_event.configurable = true; - mbm_config_rftype_init("mbm_local_bytes_config"); - } + r->mon.mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; } - l3_mon_evt_init(r); + /* + * resctrl assumes a system that supports assignable counters can + * switch to "default" mode. Ensure that there is a "default" mode + * to switch to. This enforces a dependency between the independent + * X86_FEATURE_ABMC and X86_FEATURE_CQM_MBM_TOTAL/X86_FEATURE_CQM_MBM_LOCAL + * hardware features. + */ + if (rdt_cpu_has(X86_FEATURE_ABMC) && + (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL) || + rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))) { + r->mon.mbm_cntr_assignable = true; + cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx); + r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1; + hw_res->mbm_cntr_assign_enabled = true; + } r->mon_capable = true; return 0; } -void __exit rdt_put_mon_l3_config(void) -{ - dom_data_exit(); -} - void __init intel_rdt_mbm_apply_quirk(void) { int cf_index; @@ -1261,3 +502,91 @@ void __init intel_rdt_mbm_apply_quirk(void) mbm_cf_rmidthreshold = mbm_cf_table[cf_index].rmidthreshold; mbm_cf = mbm_cf_table[cf_index].cf; } + +static void resctrl_abmc_set_one_amd(void *arg) +{ + bool *enable = arg; + + if (*enable) + msr_set_bit(MSR_IA32_L3_QOS_EXT_CFG, ABMC_ENABLE_BIT); + else + msr_clear_bit(MSR_IA32_L3_QOS_EXT_CFG, ABMC_ENABLE_BIT); +} + +/* + * ABMC enable/disable requires update of L3_QOS_EXT_CFG MSR on all the CPUs + * associated with all monitor domains. + */ +static void _resctrl_abmc_enable(struct rdt_resource *r, bool enable) +{ + struct rdt_l3_mon_domain *d; + + lockdep_assert_cpus_held(); + + list_for_each_entry(d, &r->mon_domains, hdr.list) { + on_each_cpu_mask(&d->hdr.cpu_mask, resctrl_abmc_set_one_amd, + &enable, 1); + resctrl_arch_reset_rmid_all(r, d); + } +} + +int resctrl_arch_mbm_cntr_assign_set(struct rdt_resource *r, bool enable) +{ + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + + if (r->mon.mbm_cntr_assignable && + hw_res->mbm_cntr_assign_enabled != enable) { + _resctrl_abmc_enable(r, enable); + hw_res->mbm_cntr_assign_enabled = enable; + } + + return 0; +} + +bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r) +{ + return resctrl_to_arch_res(r)->mbm_cntr_assign_enabled; +} + +static void resctrl_abmc_config_one_amd(void *info) +{ + union l3_qos_abmc_cfg *abmc_cfg = info; + + wrmsrl(MSR_IA32_L3_QOS_ABMC_CFG, abmc_cfg->full); +} + +/* + * Send an IPI to the domain to assign the counter to RMID, event pair. + */ +void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + enum resctrl_event_id evtid, u32 rmid, u32 closid, + u32 cntr_id, bool assign) +{ + struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d); + union l3_qos_abmc_cfg abmc_cfg = { 0 }; + struct arch_mbm_state *am; + + abmc_cfg.split.cfg_en = 1; + abmc_cfg.split.cntr_en = assign ? 1 : 0; + abmc_cfg.split.cntr_id = cntr_id; + abmc_cfg.split.bw_src = rmid; + if (assign) + abmc_cfg.split.bw_type = resctrl_get_mon_evt_cfg(evtid); + + smp_call_function_any(&d->hdr.cpu_mask, resctrl_abmc_config_one_amd, &abmc_cfg, 1); + + /* + * The hardware counter is reset (because cfg_en == 1) so there is no + * need to record initial non-zero counts. + */ + am = get_arch_mbm_state(hw_dom, rmid, evtid); + if (am) + memset(am, 0, sizeof(*am)); +} + +void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r) +{ + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + + resctrl_abmc_set_one_amd(&hw_res->mbm_cntr_assign_enabled); +} diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 43c65f378998d..241d0d7e1cb5f 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -11,26 +11,21 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include -#include -#include -#include -#include #include #include -#include -#include +#include -#include -#include -#include +#include #include #include "../../events/perf_event.h" /* For X86_CONFIG() */ #include "internal.h" #define CREATE_TRACE_POINTS -#include "trace.h" + +#include "pseudo_lock_trace.h" /* * The bits needed to disable hardware prefetching varies based on the @@ -38,30 +33,9 @@ */ 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 char *pseudo_lock_devnode(const struct device *dev, umode_t *mode) -{ - const struct rdtgroup *rdtgrp; - - rdtgrp = dev_get_drvdata(dev); - if (mode) - *mode = 0600; - return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name); -} - -static const struct class pseudo_lock_class = { - .name = "pseudo_lock", - .devnode = pseudo_lock_devnode, -}; - /** - * get_prefetch_disable_bits - prefetch disable bits of supported platforms + * resctrl_arch_get_prefetch_disable_bits - prefetch disable bits of supported + * platforms * @void: It takes no parameters. * * Capture the list of platforms that have been validated to support @@ -75,20 +49,22 @@ static const struct class pseudo_lock_class = { * in the SDM. * * When adding a platform here also add support for its cache events to - * measure_cycles_perf_fn() + * resctrl_arch_measure_l*_residency() * * Return: * If platform is supported, the bits to disable hardware prefetchers, 0 * if platform is not supported. */ -static u64 get_prefetch_disable_bits(void) +u64 resctrl_arch_get_prefetch_disable_bits(void) { + prefetch_disable_bits = 0; + 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: + switch (boot_cpu_data.x86_vfm) { + case INTEL_BROADWELL_X: /* * SDM defines bits of MSR_MISC_FEATURE_CONTROL register * as: @@ -98,9 +74,10 @@ static u64 get_prefetch_disable_bits(void) * 3 DCU IP Prefetcher Disable (R/W) * 63:4 Reserved */ - return 0xF; - case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + prefetch_disable_bits = 0xF; + break; + case INTEL_ATOM_GOLDMONT: + case INTEL_ATOM_GOLDMONT_PLUS: /* * SDM defines bits of MSR_MISC_FEATURE_CONTROL register * as: @@ -109,307 +86,16 @@ static u64 get_prefetch_disable_bits(void) * 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; -} - -/** - * struct 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 - * @plr: Pseudo-locked region - * - * 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. - * - * Return: 0 on success, <0 on failure - */ -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->hdr.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->s = 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) -{ - enum resctrl_scope scope = plr->s->res->ctrl_scope; - struct cacheinfo *ci; - int ret; - - if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE)) - return -ENODEV; - - /* Pick the first cpu we find that is associated with the cache. */ - plr->cpu = cpumask_first(&plr->d->hdr.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_level(plr->cpu, scope); - if (ci) { - plr->line_size = ci->coherency_line_size; - plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm); - 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; + prefetch_disable_bits = 0x5; + break; } - 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; + return prefetch_disable_bits; } /** - * pseudo_lock_fn - Load kernel memory into cache - * @_rdtgrp: resource group to which pseudo-lock region belongs + * resctrl_arch_pseudo_lock_fn - Load kernel memory into cache + * @_plr: the pseudo-lock region descriptor * * This is the core pseudo-locking flow. * @@ -426,10 +112,9 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp) * * Return: 0. Waiter on waitqueue will be woken on completion. */ -static int pseudo_lock_fn(void *_rdtgrp) +int resctrl_arch_pseudo_lock_fn(void *_plr) { - struct rdtgroup *rdtgrp = _rdtgrp; - struct pseudo_lock_region *plr = rdtgrp->plr; + struct pseudo_lock_region *plr = _plr; u32 rmid_p, closid_p; unsigned long i; u64 saved_msr; @@ -489,7 +174,8 @@ static int pseudo_lock_fn(void *_rdtgrp) * pseudo-locked followed by reading of kernel memory to load it * into the cache. */ - __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid); + /* * Cache was flushed earlier. Now access kernel memory to read it * into cache region associated with just activated plr->closid. @@ -537,342 +223,8 @@ static int pseudo_lock_fn(void *_rdtgrp) } /** - * rdtgroup_monitor_in_progress - Test if monitoring in progress - * @rdtgrp: 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 (resctrl_arch_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 (resctrl_arch_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 (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) || - resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) { - 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->closid, 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 (resctrl_arch_mon_capable()) { - ret = alloc_rmid(rdtgrp->closid); - 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->closid, 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_ctrl_domain *d, unsigned long cbm) -{ - unsigned int cbm_len; - unsigned long cbm_b; - - if (d->plr) { - cbm_len = d->plr->s->res->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_ctrl_domain *d) -{ - struct rdt_ctrl_domain *d_i; - cpumask_var_t cpu_with_psl; - struct rdt_resource *r; - bool ret = false; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - 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_capable_rdt_resource(r) { - list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) { - if (d_i->plr) - cpumask_or(cpu_with_psl, cpu_with_psl, - &d_i->hdr.cpu_mask); - } - } - - /* - * Next test if new pseudo-locked region would intersect with - * existing region. - */ - if (cpumask_intersects(&d->hdr.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 + * resctrl_arch_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 @@ -885,7 +237,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d) * * Return: 0. Waiter on waitqueue will be woken on completion. */ -static int measure_cycles_lat_fn(void *_plr) +int resctrl_arch_measure_cycles_lat_fn(void *_plr) { struct pseudo_lock_region *plr = _plr; u32 saved_low, saved_high; @@ -1069,7 +421,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr, return 0; } -static int measure_l2_residency(void *_plr) +int resctrl_arch_measure_l2_residency(void *_plr) { struct pseudo_lock_region *plr = _plr; struct residency_counts counts = {0}; @@ -1082,9 +434,9 @@ static int measure_l2_residency(void *_plr) * L2_HIT 02H * L2_MISS 10H */ - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + switch (boot_cpu_data.x86_vfm) { + case INTEL_ATOM_GOLDMONT: + case INTEL_ATOM_GOLDMONT_PLUS: perf_miss_attr.config = X86_CONFIG(.event = 0xd1, .umask = 0x10); perf_hit_attr.config = X86_CONFIG(.event = 0xd1, @@ -1107,7 +459,7 @@ static int measure_l2_residency(void *_plr) return 0; } -static int measure_l3_residency(void *_plr) +int resctrl_arch_measure_l3_residency(void *_plr) { struct pseudo_lock_region *plr = _plr; struct residency_counts counts = {0}; @@ -1121,8 +473,8 @@ static int measure_l3_residency(void *_plr) * MISS 41H */ - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_BROADWELL_X: + switch (boot_cpu_data.x86_vfm) { + case INTEL_BROADWELL_X: /* On BDW the hit event counts references, not hits */ perf_hit_attr.config = X86_CONFIG(.event = 0x2e, .umask = 0x4f); @@ -1140,7 +492,7 @@ static int measure_l3_residency(void *_plr) */ counts.miss_after -= counts.miss_before; - if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) { + if (boot_cpu_data.x86_vfm == INTEL_BROADWELL_X) { /* * On BDW references and misses are counted, need to adjust. * Sometimes the "hits" counter is a bit more than the @@ -1162,441 +514,3 @@ static int measure_l3_residency(void *_plr) wake_up_interruptible(&plr->lock_thread_wq); return 0; } - -/** - * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region - * @rdtgrp: Resource group to which the pseudo-locked region belongs. - * @sel: Selector of which measurement to perform on a 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->hdr.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 dereference - * 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 asymmetry 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->hdr.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, -}; - -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; - - ret = class_register(&pseudo_lock_class); - if (ret) { - unregister_chrdev(pseudo_lock_major, "pseudo_lock"); - return ret; - } - - return 0; -} - -void rdt_pseudo_lock_release(void) -{ - class_unregister(&pseudo_lock_class); - unregister_chrdev(pseudo_lock_major, "pseudo_lock"); - pseudo_lock_major = 0; -} diff --git a/arch/x86/kernel/cpu/resctrl/trace.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h similarity index 56% rename from arch/x86/kernel/cpu/resctrl/trace.h rename to arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h index 2a506316b3034..7c8aef08010f1 100644 --- a/arch/x86/kernel/cpu/resctrl/trace.h +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h @@ -2,8 +2,8 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM resctrl -#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_RESCTRL_H +#if !defined(_X86_RESCTRL_PSEUDO_LOCK_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _X86_RESCTRL_PSEUDO_LOCK_TRACE_H #include @@ -35,25 +35,11 @@ TRACE_EVENT(pseudo_lock_l3, TP_printk("hits=%llu miss=%llu", __entry->l3_hits, __entry->l3_miss)); -TRACE_EVENT(mon_llc_occupancy_limbo, - TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes), - TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes), - TP_STRUCT__entry(__field(u32, ctrl_hw_id) - __field(u32, mon_hw_id) - __field(int, domain_id) - __field(u64, llc_occupancy_bytes)), - TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id; - __entry->mon_hw_id = mon_hw_id; - __entry->domain_id = domain_id; - __entry->llc_occupancy_bytes = llc_occupancy_bytes;), - TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu", - __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id, - __entry->llc_occupancy_bytes) - ); - -#endif /* _TRACE_RESCTRL_H */ +#endif /* _X86_RESCTRL_PSEUDO_LOCK_TRACE_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE trace + +#define TRACE_INCLUDE_FILE pseudo_lock_trace + #include diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5c993045b1a48..c7a7f0ae373ad 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -28,4208 +29,233 @@ #include -#include #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); - -/* Mutex to protect rdtgroup access. */ -DEFINE_MUTEX(rdtgroup_mutex); - -static struct kernfs_root *rdt_root; -struct rdtgroup rdtgroup_default; -LIST_HEAD(rdt_all_groups); - -/* list of entries for the schemata file */ -LIST_HEAD(resctrl_schema_all); - -/* The filesystem can only be mounted once. */ -bool resctrl_mounted; - -/* 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]; - -static int rdtgroup_setup_root(struct rdt_fs_context *ctx); -static void rdtgroup_destroy_root(void); - -struct dentry *debugfs_resctrl; - -static bool resctrl_debug; +DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); -void rdt_last_cmd_clear(void) -{ - lockdep_assert_held(&rdtgroup_mutex); - seq_buf_clear(&last_cmd_status); -} +DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); -void rdt_last_cmd_puts(const char *s) +/* + * This is safe against resctrl_arch_sched_in() called from __switch_to() + * because __switch_to() is executed with interrupts disabled. A local call + * from update_closid_rmid() is protected against __switch_to() because + * preemption is disabled. + */ +void resctrl_arch_sync_cpu_closid_rmid(void *info) { - lockdep_assert_held(&rdtgroup_mutex); - seq_buf_puts(&last_cmd_status, s); -} + struct resctrl_cpu_defaults *r = info; -void rdt_last_cmd_printf(const char *fmt, ...) -{ - va_list ap; + if (r) { + this_cpu_write(pqr_state.default_closid, r->closid); + this_cpu_write(pqr_state.default_rmid, r->rmid); + } - va_start(ap, fmt); - lockdep_assert_held(&rdtgroup_mutex); - seq_buf_vprintf(&last_cmd_status, fmt, ap); - va_end(ap); + /* + * We cannot unconditionally write the MSR because the current + * executing task might have its own closid selected. Just reuse + * the context switch code. + */ + resctrl_arch_sched_in(current); } -void rdt_staged_configs_clear(void) -{ - struct rdt_ctrl_domain *dom; - struct rdt_resource *r; - - lockdep_assert_held(&rdtgroup_mutex); - - for_each_alloc_capable_rdt_resource(r) { - list_for_each_entry(dom, &r->ctrl_domains, hdr.list) - memset(dom->staged_config, 0, sizeof(dom->staged_config)); - } -} +#define INVALID_CONFIG_INDEX UINT_MAX -/* - * Trivial allocator for CLOSIDs. Since h/w only supports a small number, - * we can keep a bitmap of free CLOSIDs in a single integer. +/** + * mon_event_config_index_get - get the hardware index for the + * configurable event + * @evtid: event id. * - * Using a global CLOSID across all resources has some advantages and - * some drawbacks: - * + We can simply set current's 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. + * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID + * 1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID + * INVALID_CONFIG_INDEX for invalid evtid */ -static unsigned long closid_free_map; -static int closid_free_map_len; - -int closids_supported(void) -{ - return closid_free_map_len; -} - -static void closid_init(void) +static inline unsigned int mon_event_config_index_get(u32 evtid) { - struct resctrl_schema *s; - u32 rdt_min_closid = 32; - - /* Compute rdt_min_closid across all resources */ - list_for_each_entry(s, &resctrl_schema_all, list) - rdt_min_closid = min(rdt_min_closid, s->num_closid); - - closid_free_map = BIT_MASK(rdt_min_closid) - 1; - - /* RESCTRL_RESERVED_CLOSID is always reserved for the default group */ - __clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map); - closid_free_map_len = rdt_min_closid; + switch (evtid) { + case QOS_L3_MBM_TOTAL_EVENT_ID: + return 0; + case QOS_L3_MBM_LOCAL_EVENT_ID: + return 1; + default: + /* Should never reach here */ + return INVALID_CONFIG_INDEX; + } } -static int closid_alloc(void) +void resctrl_arch_mon_event_config_read(void *_config_info) { - int cleanest_closid; - u32 closid; - - lockdep_assert_held(&rdtgroup_mutex); + struct resctrl_mon_config_info *config_info = _config_info; + unsigned int index; + u64 msrval; - if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { - cleanest_closid = resctrl_find_cleanest_closid(); - if (cleanest_closid < 0) - return cleanest_closid; - closid = cleanest_closid; - } else { - closid = ffs(closid_free_map); - if (closid == 0) - return -ENOSPC; - closid--; + index = mon_event_config_index_get(config_info->evtid); + if (index == INVALID_CONFIG_INDEX) { + pr_warn_once("Invalid event id %d\n", config_info->evtid); + return; } - __clear_bit(closid, &closid_free_map); - - return closid; -} - -void closid_free(int closid) -{ - lockdep_assert_held(&rdtgroup_mutex); + rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval); - __set_bit(closid, &closid_free_map); + /* Report only the valid event configuration bits */ + config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS; } -/** - * 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 - */ -bool closid_allocated(unsigned int closid) +void resctrl_arch_mon_event_config_write(void *_config_info) { - lockdep_assert_held(&rdtgroup_mutex); + struct resctrl_mon_config_info *config_info = _config_info; + unsigned int index; - return !test_bit(closid, &closid_free_map); + index = mon_event_config_index_get(config_info->evtid); + if (index == INVALID_CONFIG_INDEX) { + pr_warn_once("Invalid event id %d\n", config_info->evtid); + return; + } + wrmsr(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config, 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) +static void l3_qos_cfg_update(void *arg) { - struct rdtgroup *rdtgrp; - - list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { - if (rdtgrp->closid == closid) - return rdtgrp->mode; - } + bool *enable = arg; - return RDT_NUM_MODES; + wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL); } -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) +static void l2_qos_cfg_update(void *arg) { - if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES) - return "unknown"; + bool *enable = arg; - return rdt_mode_str[mode]; + wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL); } -/* set uid and gid of rdtgroup dirs and files to that of the creator */ -static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) +static int set_cache_qos_cfg(int level, bool enable) { - 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; + void (*update)(void *arg); + struct rdt_ctrl_domain *d; + struct rdt_resource *r_l; + cpumask_var_t cpu_mask; + int cpu; - return kernfs_setattr(kn, &iattr); -} + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); -static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) -{ - struct kernfs_node *kn; - int ret; + if (level == RDT_RESOURCE_L3) + update = l3_qos_cfg_update; + else if (level == RDT_RESOURCE_L2) + update = l2_qos_cfg_update; + else + return -EINVAL; - 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); + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; - ret = rdtgroup_kn_set_ugid(kn); - if (ret) { - kernfs_remove(kn); - return ret; + r_l = &rdt_resources_all[level].r_resctrl; + list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) { + if (r_l->cache.arch_has_per_cpu_cfg) + /* Pick all the CPUs in the domain instance */ + for_each_cpu(cpu, &d->hdr.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->hdr.cpu_mask), cpu_mask); } - return 0; -} + /* Update QOS_CFG MSR on all the CPUs in cpu_mask */ + on_each_cpu_mask(cpu_mask, update, &enable, 1); -static int rdtgroup_seqfile_show(struct seq_file *m, void *arg) -{ - struct kernfs_open_file *of = m->private; - struct rftype *rft = of->kn->priv; + free_cpumask_var(cpu_mask); - 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) +/* Restore the qos cfg state when a domain comes online */ +void rdt_domain_reconfigure_cdp(struct rdt_resource *r) { - struct rftype *rft = of->kn->priv; - - if (rft->write) - return rft->write(of, buf, nbytes, off); - - return -EINVAL; -} - -static const struct kernfs_ops rdtgroup_kf_single_ops = { - .atomic_write_len = PAGE_SIZE, - .write = rdtgroup_file_write, - .seq_show = rdtgroup_seqfile_show, -}; + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); -static const struct kernfs_ops kf_mondata_ops = { - .atomic_write_len = PAGE_SIZE, - .seq_show = rdtgroup_mondata_show, -}; + if (!r->cdp_capable) + return; -static bool is_cpu_list(struct kernfs_open_file *of) -{ - struct rftype *rft = of->kn->priv; + if (r->rid == RDT_RESOURCE_L2) + l2_qos_cfg_update(&hw_res->cdp_enabled); - return rft->flags & RFTYPE_FLAGS_CPUS_LIST; + if (r->rid == RDT_RESOURCE_L3) + l3_qos_cfg_update(&hw_res->cdp_enabled); } -static int rdtgroup_cpus_show(struct kernfs_open_file *of, - struct seq_file *s, void *v) +static int cdp_enable(int level) { - struct rdtgroup *rdtgrp; - struct cpumask *mask; - int ret = 0; + struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl; + int ret; - rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!r_l->alloc_capable) + return -EINVAL; - 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->hdr.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); + ret = set_cache_qos_cfg(level, true); + if (!ret) + rdt_resources_all[level].cdp_enabled = true; 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 protected against __switch_to() because - * preemption is disabled. - */ -static void update_cpu_closid_rmid(void *info) +static void cdp_disable(int level) { - struct rdtgroup *r = info; + struct rdt_hw_resource *r_hw = &rdt_resources_all[level]; - if (r) { - this_cpu_write(pqr_state.default_closid, r->closid); - this_cpu_write(pqr_state.default_rmid, r->mon.rmid); + if (r_hw->cdp_enabled) { + set_cache_qos_cfg(level, false); + r_hw->cdp_enabled = false; } - - /* - * 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) -{ - on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1); } -static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, - cpumask_var_t tmpmask) +int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable) { - struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp; - struct list_head *head; + struct rdt_hw_resource *hw_res = &rdt_resources_all[l]; - /* Check whether cpus belong to parent ctrl group */ - cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); - if (!cpumask_empty(tmpmask)) { - rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n"); + if (!hw_res->r_resctrl.cdp_capable) return -EINVAL; - } - - /* Check whether cpus are dropped from this group */ - cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (!cpumask_empty(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_empty(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); - } + if (enable) + return cdp_enable(l); - /* Done pushing/pulling - update this group with new mask */ - cpumask_copy(&rdtgrp->cpu_mask, newmask); + cdp_disable(l); return 0; } -static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m) +bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l) { - 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); + return rdt_resources_all[l].cdp_enabled; } -static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, - cpumask_var_t tmpmask, cpumask_var_t tmpmask1) +void resctrl_arch_reset_all_ctrls(struct rdt_resource *r) { - 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_empty(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); - } + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + struct rdt_hw_ctrl_domain *hw_dom; + struct msr_param msr_param; + struct rdt_ctrl_domain *d; + int i; - /* - * 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_empty(tmpmask)) { - list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { - if (r == rdtgrp) - continue; - cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); - if (!cpumask_empty(tmpmask1)) - cpumask_rdtgrp_clear(r, tmpmask1); - } - update_closid_rmid(tmpmask, rdtgrp); - } + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); - /* Done pushing/pulling - update this group with new mask */ - cpumask_copy(&rdtgrp->cpu_mask, newmask); + msr_param.res = r; + msr_param.low = 0; + msr_param.high = hw_res->num_closid; /* - * Clear child mon group masks since there is a new parent mask - * now and update the rmid for the cpus the child lost. + * Disable resource control for this resource by setting all + * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU + * from each domain to update the MSRs below. */ - 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; - } + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + hw_dom = resctrl_to_arch_ctrl_dom(d); - /* check that user didn't specify any offline cpus */ - cpumask_andnot(tmpmask, newmask, cpu_online_mask); - if (!cpumask_empty(tmpmask)) { - ret = -EINVAL; - rdt_last_cmd_puts("Can only assign online CPUs\n"); - goto unlock; + for (i = 0; i < hw_res->num_closid; i++) + hw_dom->ctrl_val[i] = resctrl_get_default_ctrl(r); + msr_param.dom = d; + smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1); } - 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 bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp) -{ - u32 closid, rmid = rdtgrp->mon.rmid; - - if (rdtgrp->type == RDTCTRL_GROUP) - closid = rdtgrp->closid; - else if (rdtgrp->type == RDTMON_GROUP) - closid = rdtgrp->mon.parent->closid; - else - return false; - - return resctrl_arch_match_closid(tsk, closid) && - resctrl_arch_match_rmid(tsk, closid, rmid); -} - -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 (task_in_rdtgroup(tsk, rdtgrp)) - 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 == RDTMON_GROUP && - !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) { - rdt_last_cmd_puts("Can't move task to different control group\n"); - return -EINVAL; - } - - if (rdtgrp->type == RDTMON_GROUP) - resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid, - rdtgrp->mon.rmid); - else - resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid, - rdtgrp->mon.rmid); - - /* - * 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 (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) && - resctrl_arch_match_closid(t, r->closid)); -} - -static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) -{ - return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) && - resctrl_arch_match_rmid(t, r->mon.parent->closid, - 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; - char *pid_str; - int ret = 0; - pid_t pid; - - 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; - } - - while (buf && buf[0] != '\0' && buf[0] != '\n') { - pid_str = strim(strsep(&buf, ",")); - - if (kstrtoint(pid_str, 0, &pid)) { - rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str); - ret = -EINVAL; - break; - } - - if (pid < 0) { - rdt_last_cmd_printf("Invalid pid %d\n", pid); - ret = -EINVAL; - break; - } - - ret = rdtgroup_move_task(pid, rdtgrp, of); - if (ret) { - rdt_last_cmd_printf("Error while processing task %d\n", pid); - break; - } - } - -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; -} - -static int rdtgroup_closid_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) - seq_printf(s, "%u\n", rdtgrp->closid); - else - ret = -ENOENT; - rdtgroup_kn_unlock(of->kn); - - return ret; -} - -static int rdtgroup_rmid_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) - seq_printf(s, "%u\n", rdtgrp->mon.rmid); - 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 (!resctrl_mounted) { - 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 (!resctrl_arch_match_closid(tsk, rdtg->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 (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid, - 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 resctrl_schema *s = of->kn->parent->priv; - - seq_printf(seq, "%u\n", s->num_closid); - return 0; -} - -static int rdt_default_ctrl_show(struct kernfs_open_file *of, - struct seq_file *seq, void *v) -{ - struct resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - 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 resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - 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 resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - 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 resctrl_schema *s = 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_resource *r = s->res; - struct rdt_ctrl_domain *dom; - int i, hwb, swb, excl, psl; - enum rdtgrp_mode mode; - bool sep = false; - u32 ctrl_val; - - cpus_read_lock(); - mutex_lock(&rdtgroup_mutex); - hw_shareable = r->cache.shareable_bits; - list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { - if (sep) - seq_putc(seq, ';'); - sw_shareable = 0; - exclusive = 0; - seq_printf(seq, "%d=", dom->hdr.id); - for (i = 0; i < closids_supported(); i++) { - if (!closid_allocated(i)) - continue; - ctrl_val = resctrl_arch_get_config(r, dom, i, - s->conf_type); - mode = rdtgroup_mode_by_closid(i); - switch (mode) { - case RDT_MODE_SHAREABLE: - sw_shareable |= ctrl_val; - break; - case RDT_MODE_EXCLUSIVE: - exclusive |= ctrl_val; - 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); - cpus_read_unlock(); - return 0; -} - -static int rdt_min_bw_show(struct kernfs_open_file *of, - struct seq_file *seq, void *v) -{ - struct resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - 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); - if (mevt->configurable) - seq_printf(seq, "%s_config\n", mevt->name); - } - - return 0; -} - -static int rdt_bw_gran_show(struct kernfs_open_file *of, - struct seq_file *seq, void *v) -{ - struct resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - 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 resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - 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) -{ - seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold); - - return 0; -} - -static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, - struct seq_file *seq, void *v) -{ - struct resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - 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) -{ - unsigned int bytes; - int ret; - - ret = kstrtouint(buf, 0, &bytes); - if (ret) - return ret; - - if (bytes > resctrl_rmid_realloc_limit) - return -EINVAL; - - resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes); - - 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; -} - -static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) -{ - switch (my_type) { - case CDP_CODE: - return CDP_DATA; - case CDP_DATA: - return CDP_CODE; - default: - case CDP_NONE: - return CDP_NONE; - } -} - -static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, - struct seq_file *seq, void *v) -{ - struct resctrl_schema *s = of->kn->parent->priv; - struct rdt_resource *r = s->res; - - seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks); - - return 0; -} - -/** - * __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. - * @type: CDP type of @r. - * @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_ctrl_domain *d, - unsigned long cbm, int closid, - enum resctrl_conf_type type, bool exclusive) -{ - enum rdtgrp_mode mode; - unsigned long ctrl_b; - 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 */ - for (i = 0; i < closids_supported(); i++) { - ctrl_b = resctrl_arch_get_config(r, d, i, type); - 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 - * @s: Schema for the 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 resctrl_schema *s, struct rdt_ctrl_domain *d, - unsigned long cbm, int closid, bool exclusive) -{ - enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); - struct rdt_resource *r = s->res; - - if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type, - exclusive)) - return true; - - if (!resctrl_arch_get_cdp_enabled(r->rid)) - return false; - return __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive); -} - -/** - * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive - * @rdtgrp: Resource group identified through its closid. - * - * 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_ctrl_domain *d; - struct resctrl_schema *s; - struct rdt_resource *r; - bool has_cache = false; - u32 ctrl; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - list_for_each_entry(s, &resctrl_schema_all, list) { - r = s->res; - if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA) - continue; - has_cache = true; - list_for_each_entry(d, &r->ctrl_domains, hdr.list) { - ctrl = resctrl_arch_get_config(r, d, closid, - s->conf_type); - if (rdtgroup_cbm_overlaps(s, d, ctrl, 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_ctrl_domain *d, unsigned long cbm) -{ - unsigned int size = 0; - struct cacheinfo *ci; - int num_b; - - if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE)) - return size; - - num_b = bitmap_weight(&cbm, r->cache.cbm_len); - ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope); - if (ci) - size = ci->size / r->cache.cbm_len * num_b; - - 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 resctrl_schema *schema; - enum resctrl_conf_type type; - struct rdt_ctrl_domain *d; - struct rdtgroup *rdtgrp; - struct rdt_resource *r; - unsigned int size; - int ret = 0; - u32 closid; - 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->s->name); - size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res, - rdtgrp->plr->d, - rdtgrp->plr->cbm); - seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size); - } - goto out; - } - - closid = rdtgrp->closid; - - list_for_each_entry(schema, &resctrl_schema_all, list) { - r = schema->res; - type = schema->conf_type; - sep = false; - seq_printf(s, "%*s:", max_name_width, schema->name); - list_for_each_entry(d, &r->ctrl_domains, hdr.list) { - if (sep) - seq_putc(s, ';'); - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { - size = 0; - } else { - if (is_mba_sc(r)) - ctrl = d->mbps_val[closid]; - else - ctrl = resctrl_arch_get_config(r, d, - closid, - type); - if (r->rid == RDT_RESOURCE_MBA || - r->rid == RDT_RESOURCE_SMBA) - size = ctrl; - else - size = rdtgroup_cbm_to_size(r, d, ctrl); - } - seq_printf(s, "%d=%u", d->hdr.id, size); - sep = true; - } - seq_putc(s, '\n'); - } - -out: - rdtgroup_kn_unlock(of->kn); - - return ret; -} - -struct mon_config_info { - u32 evtid; - u32 mon_config; -}; - -#define INVALID_CONFIG_INDEX UINT_MAX - -/** - * mon_event_config_index_get - get the hardware index for the - * configurable event - * @evtid: event id. - * - * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID - * 1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID - * INVALID_CONFIG_INDEX for invalid evtid - */ -static inline unsigned int mon_event_config_index_get(u32 evtid) -{ - switch (evtid) { - case QOS_L3_MBM_TOTAL_EVENT_ID: - return 0; - case QOS_L3_MBM_LOCAL_EVENT_ID: - return 1; - default: - /* Should never reach here */ - return INVALID_CONFIG_INDEX; - } -} - -static void mon_event_config_read(void *info) -{ - struct mon_config_info *mon_info = info; - unsigned int index; - u64 msrval; - - index = mon_event_config_index_get(mon_info->evtid); - if (index == INVALID_CONFIG_INDEX) { - pr_warn_once("Invalid event id %d\n", mon_info->evtid); - return; - } - rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval); - - /* Report only the valid event configuration bits */ - mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS; -} - -static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info *mon_info) -{ - smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1); -} - -static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid) -{ - struct mon_config_info mon_info = {0}; - struct rdt_mon_domain *dom; - bool sep = false; - - cpus_read_lock(); - mutex_lock(&rdtgroup_mutex); - - list_for_each_entry(dom, &r->mon_domains, hdr.list) { - if (sep) - seq_puts(s, ";"); - - memset(&mon_info, 0, sizeof(struct mon_config_info)); - mon_info.evtid = evtid; - mondata_config_read(dom, &mon_info); - - seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config); - sep = true; - } - seq_puts(s, "\n"); - - mutex_unlock(&rdtgroup_mutex); - cpus_read_unlock(); - - return 0; -} - -static int mbm_total_bytes_config_show(struct kernfs_open_file *of, - struct seq_file *seq, void *v) -{ - struct rdt_resource *r = of->kn->parent->priv; - - mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID); - - return 0; -} - -static int mbm_local_bytes_config_show(struct kernfs_open_file *of, - struct seq_file *seq, void *v) -{ - struct rdt_resource *r = of->kn->parent->priv; - - mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID); - - return 0; -} - -static void mon_event_config_write(void *info) -{ - struct mon_config_info *mon_info = info; - unsigned int index; - - index = mon_event_config_index_get(mon_info->evtid); - if (index == INVALID_CONFIG_INDEX) { - pr_warn_once("Invalid event id %d\n", mon_info->evtid); - return; - } - wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0); -} - -static void mbm_config_write_domain(struct rdt_resource *r, - struct rdt_mon_domain *d, u32 evtid, u32 val) -{ - struct mon_config_info mon_info = {0}; - - /* - * Read the current config value first. If both are the same then - * no need to write it again. - */ - mon_info.evtid = evtid; - mondata_config_read(d, &mon_info); - if (mon_info.mon_config == val) - return; - - mon_info.mon_config = val; - - /* - * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the - * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE - * are scoped at the domain level. Writing any of these MSRs - * on one CPU is observed by all the CPUs in the domain. - */ - smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write, - &mon_info, 1); - - /* - * When an Event Configuration is changed, the bandwidth counters - * for all RMIDs and Events will be cleared by the hardware. The - * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for - * every RMID on the next read to any event for every RMID. - * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62) - * cleared while it is tracked by the hardware. Clear the - * mbm_local and mbm_total counts for all the RMIDs. - */ - resctrl_arch_reset_rmid_all(r, d); -} - -static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) -{ - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - char *dom_str = NULL, *id_str; - unsigned long dom_id, val; - struct rdt_mon_domain *d; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - -next: - if (!tok || tok[0] == '\0') - return 0; - - /* Start processing the strings for each domain */ - dom_str = strim(strsep(&tok, ";")); - id_str = strsep(&dom_str, "="); - - if (!id_str || kstrtoul(id_str, 10, &dom_id)) { - rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n"); - return -EINVAL; - } - - if (!dom_str || kstrtoul(dom_str, 16, &val)) { - rdt_last_cmd_puts("Non-numeric event configuration value\n"); - return -EINVAL; - } - - /* Value from user cannot be more than the supported set of events */ - if ((val & hw_res->mbm_cfg_mask) != val) { - rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", - hw_res->mbm_cfg_mask); - return -EINVAL; - } - - list_for_each_entry(d, &r->mon_domains, hdr.list) { - if (d->hdr.id == dom_id) { - mbm_config_write_domain(r, d, evtid, val); - goto next; - } - } - - return -EINVAL; -} - -static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, - loff_t off) -{ - struct rdt_resource *r = of->kn->parent->priv; - int ret; - - /* Valid input requires a trailing newline */ - if (nbytes == 0 || buf[nbytes - 1] != '\n') - return -EINVAL; - - cpus_read_lock(); - mutex_lock(&rdtgroup_mutex); - - rdt_last_cmd_clear(); - - buf[nbytes - 1] = '\0'; - - ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID); - - mutex_unlock(&rdtgroup_mutex); - cpus_read_unlock(); - - return ret ?: nbytes; -} - -static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, - loff_t off) -{ - struct rdt_resource *r = of->kn->parent->priv; - int ret; - - /* Valid input requires a trailing newline */ - if (nbytes == 0 || buf[nbytes - 1] != '\n') - return -EINVAL; - - cpus_read_lock(); - mutex_lock(&rdtgroup_mutex); - - rdt_last_cmd_clear(); - - buf[nbytes - 1] = '\0'; - - ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID); - - mutex_unlock(&rdtgroup_mutex); - cpus_read_unlock(); - - return ret ?: nbytes; -} - -/* 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 = RFTYPE_TOP_INFO, - }, - { - .name = "num_closids", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_num_closids_show, - .fflags = RFTYPE_CTRL_INFO, - }, - { - .name = "mon_features", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_mon_features_show, - .fflags = RFTYPE_MON_INFO, - }, - { - .name = "num_rmids", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_num_rmids_show, - .fflags = RFTYPE_MON_INFO, - }, - { - .name = "cbm_mask", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_default_ctrl_show, - .fflags = RFTYPE_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 = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, - }, - { - .name = "shareable_bits", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_shareable_bits_show, - .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, - }, - { - .name = "bit_usage", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_bit_usage_show, - .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, - }, - { - .name = "min_bandwidth", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_min_bw_show, - .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, - }, - { - .name = "bandwidth_gran", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_bw_gran_show, - .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, - }, - { - .name = "delay_linear", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_delay_linear_show, - .fflags = RFTYPE_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 = RFTYPE_MON_INFO | RFTYPE_RES_CACHE, - }, - { - .name = "mbm_total_bytes_config", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = mbm_total_bytes_config_show, - .write = mbm_total_bytes_config_write, - }, - { - .name = "mbm_local_bytes_config", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = mbm_local_bytes_config_show, - .write = mbm_local_bytes_config_write, - }, - { - .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 = "mon_hw_id", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdtgroup_rmid_show, - .fflags = RFTYPE_MON_BASE | RFTYPE_DEBUG, - }, - { - .name = "schemata", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_schemata_write, - .seq_show = rdtgroup_schemata_show, - .fflags = RFTYPE_CTRL_BASE, - }, - { - .name = "mode", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_mode_write, - .seq_show = rdtgroup_mode_show, - .fflags = RFTYPE_CTRL_BASE, - }, - { - .name = "size", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdtgroup_size_show, - .fflags = RFTYPE_CTRL_BASE, - }, - { - .name = "sparse_masks", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_has_sparse_bitmasks_show, - .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, - }, - { - .name = "ctrl_hw_id", - .mode = 0444, - .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdtgroup_closid_show, - .fflags = RFTYPE_CTRL_BASE | RFTYPE_DEBUG, - }, - -}; - -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); - - if (resctrl_debug) - fflags |= RFTYPE_DEBUG; - - 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 = RFTYPE_CTRL_INFO | RFTYPE_RES_MB; -} - -void __init mbm_config_rftype_init(const char *config) -{ - struct rftype *rft; - - rft = rdtgroup_get_rftype_by_name(config); - if (rft) - rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE; -} - -/** - * 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(void *priv, char *name, - unsigned long fflags) -{ - struct kernfs_node *kn_subdir; - int ret; - - kn_subdir = kernfs_create_dir(kn_info, name, - kn_info->mode, priv); - 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 resctrl_schema *s; - 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, RFTYPE_TOP_INFO); - if (ret) - goto out_destroy; - - /* loop over enabled controls, these are all alloc_capable */ - list_for_each_entry(s, &resctrl_schema_all, list) { - r = s->res; - fflags = r->fflags | RFTYPE_CTRL_INFO; - ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags); - if (ret) - goto out_destroy; - } - - for_each_mon_capable_rdt_resource(r) { - fflags = r->fflags | RFTYPE_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].r_resctrl.membw.delay_linear; -} - -static int set_cache_qos_cfg(int level, bool enable) -{ - void (*update)(void *arg); - struct rdt_ctrl_domain *d; - struct rdt_resource *r_l; - cpumask_var_t cpu_mask; - int cpu; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - 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].r_resctrl; - list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) { - if (r_l->cache.arch_has_per_cpu_cfg) - /* Pick all the CPUs in the domain instance */ - for_each_cpu(cpu, &d->hdr.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->hdr.cpu_mask), cpu_mask); - } - - /* Update QOS_CFG MSR on all the CPUs in cpu_mask */ - on_each_cpu_mask(cpu_mask, update, &enable, 1); - - 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) -{ - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - - if (!r->cdp_capable) - return; - - if (r->rid == RDT_RESOURCE_L2) - l2_qos_cfg_update(&hw_res->cdp_enabled); - - if (r->rid == RDT_RESOURCE_L3) - l3_qos_cfg_update(&hw_res->cdp_enabled); -} - -static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d) -{ - u32 num_closid = resctrl_arch_get_num_closid(r); - int cpu = cpumask_any(&d->hdr.cpu_mask); - int i; - - d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val), - GFP_KERNEL, cpu_to_node(cpu)); - if (!d->mbps_val) - return -ENOMEM; - - for (i = 0; i < num_closid; i++) - d->mbps_val[i] = MBA_MAX_MBPS; - - return 0; -} - -static void mba_sc_domain_destroy(struct rdt_resource *r, - struct rdt_ctrl_domain *d) -{ - kfree(d->mbps_val); - d->mbps_val = NULL; -} - -/* - * MBA software controller is supported only if - * MBM is supported and MBA is in linear scale, - * and the MBM monitor scope is the same as MBA - * control scope. - */ -static bool supports_mba_mbps(void) -{ - struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; - - return (is_mbm_local_enabled() && - r->alloc_capable && is_mba_linear() && - r->ctrl_scope == rmbm->mon_scope); -} - -/* - * Enable or disable the MBA software controller - * which helps user specify bandwidth in MBps. - */ -static int set_mba_sc(bool mba_sc) -{ - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; - u32 num_closid = resctrl_arch_get_num_closid(r); - struct rdt_ctrl_domain *d; - int i; - - if (!supports_mba_mbps() || mba_sc == is_mba_sc(r)) - return -EINVAL; - - r->membw.mba_sc = mba_sc; - - list_for_each_entry(d, &r->ctrl_domains, hdr.list) { - for (i = 0; i < num_closid; i++) - d->mbps_val[i] = MBA_MAX_MBPS; - } - - return 0; -} - -static int cdp_enable(int level) -{ - struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl; - int ret; - - if (!r_l->alloc_capable) - return -EINVAL; - - ret = set_cache_qos_cfg(level, true); - if (!ret) - rdt_resources_all[level].cdp_enabled = true; - - return ret; -} - -static void cdp_disable(int level) -{ - struct rdt_hw_resource *r_hw = &rdt_resources_all[level]; - - if (r_hw->cdp_enabled) { - set_cache_qos_cfg(level, false); - r_hw->cdp_enabled = false; - } -} - -int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable) -{ - struct rdt_hw_resource *hw_res = &rdt_resources_all[l]; - - if (!hw_res->r_resctrl.cdp_capable) - return -EINVAL; - - if (enable) - return cdp_enable(l); - - cdp_disable(l); - - return 0; -} - -/* - * 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; - } -} - -static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn) -{ - atomic_inc(&rdtgrp->waitcount); - kernfs_break_active_protection(kn); -} - -static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn) -{ - 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); - } -} - -struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) -{ - struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); - - if (!rdtgrp) - return NULL; - - rdtgroup_kn_get(rdtgrp, kn); - - cpus_read_lock(); - 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); - cpus_read_unlock(); - - rdtgroup_kn_put(rdtgrp, kn); -} - -static int mkdir_mondata_all(struct kernfs_node *parent_kn, - struct rdtgroup *prgrp, - struct kernfs_node **mon_data_kn); - -static void rdt_disable_ctx(void) -{ - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); - set_mba_sc(false); - - resctrl_debug = false; -} - -static int rdt_enable_ctx(struct rdt_fs_context *ctx) -{ - int ret = 0; - - if (ctx->enable_cdpl2) { - ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true); - if (ret) - goto out_done; - } - - if (ctx->enable_cdpl3) { - ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true); - if (ret) - goto out_cdpl2; - } - - if (ctx->enable_mba_mbps) { - ret = set_mba_sc(true); - if (ret) - goto out_cdpl3; - } - - if (ctx->enable_debug) - resctrl_debug = true; - - return 0; - -out_cdpl3: - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); -out_cdpl2: - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); -out_done: - return ret; -} - -static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type) -{ - struct resctrl_schema *s; - const char *suffix = ""; - int ret, cl; - - s = kzalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; - - s->res = r; - s->num_closid = resctrl_arch_get_num_closid(r); - if (resctrl_arch_get_cdp_enabled(r->rid)) - s->num_closid /= 2; - - s->conf_type = type; - switch (type) { - case CDP_CODE: - suffix = "CODE"; - break; - case CDP_DATA: - suffix = "DATA"; - break; - case CDP_NONE: - suffix = ""; - break; - } - - ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix); - if (ret >= sizeof(s->name)) { - kfree(s); - return -EINVAL; - } - - cl = strlen(s->name); - - /* - * If CDP is supported by this resource, but not enabled, - * include the suffix. This ensures the tabular format of the - * schemata file does not change between mounts of the filesystem. - */ - if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid)) - cl += 4; - - if (cl > max_name_width) - max_name_width = cl; - - INIT_LIST_HEAD(&s->list); - list_add(&s->list, &resctrl_schema_all); - - return 0; -} - -static int schemata_list_create(void) -{ - struct rdt_resource *r; - int ret = 0; - - for_each_alloc_capable_rdt_resource(r) { - if (resctrl_arch_get_cdp_enabled(r->rid)) { - ret = schemata_list_add(r, CDP_CODE); - if (ret) - break; - - ret = schemata_list_add(r, CDP_DATA); - } else { - ret = schemata_list_add(r, CDP_NONE); - } - - if (ret) - break; - } - - return ret; -} - -static void schemata_list_destroy(void) -{ - struct resctrl_schema *s, *tmp; - - list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) { - list_del(&s->list); - kfree(s); - } -} - -static int rdt_get_tree(struct fs_context *fc) -{ - struct rdt_fs_context *ctx = rdt_fc2context(fc); - unsigned long flags = RFTYPE_CTRL_BASE; - struct rdt_mon_domain *dom; - struct rdt_resource *r; - int ret; - - cpus_read_lock(); - mutex_lock(&rdtgroup_mutex); - /* - * resctrl file system can only be mounted once. - */ - if (resctrl_mounted) { - ret = -EBUSY; - goto out; - } - - ret = rdtgroup_setup_root(ctx); - if (ret) - goto out; - - ret = rdt_enable_ctx(ctx); - if (ret) - goto out_root; - - ret = schemata_list_create(); - if (ret) { - schemata_list_destroy(); - goto out_ctx; - } - - closid_init(); - - if (resctrl_arch_mon_capable()) - flags |= RFTYPE_MON; - - ret = rdtgroup_add_files(rdtgroup_default.kn, flags); - if (ret) - goto out_schemata_free; - - kernfs_activate(rdtgroup_default.kn); - - ret = rdtgroup_create_info_dir(rdtgroup_default.kn); - if (ret < 0) - goto out_schemata_free; - - if (resctrl_arch_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 (resctrl_arch_alloc_capable()) - resctrl_arch_enable_alloc(); - if (resctrl_arch_mon_capable()) - resctrl_arch_enable_mon(); - - if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable()) - resctrl_mounted = true; - - if (is_mbm_enabled()) { - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - list_for_each_entry(dom, &r->mon_domains, hdr.list) - mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL, - RESCTRL_PICK_ANY_CPU); - } - - goto out; - -out_psl: - rdt_pseudo_lock_release(); -out_mondata: - if (resctrl_arch_mon_capable()) - kernfs_remove(kn_mondata); -out_mongrp: - if (resctrl_arch_mon_capable()) - kernfs_remove(kn_mongrp); -out_info: - kernfs_remove(kn_info); -out_schemata_free: - schemata_list_destroy(); -out_ctx: - rdt_disable_ctx(); -out_root: - rdtgroup_destroy_root(); -out: - rdt_last_cmd_clear(); - mutex_unlock(&rdtgroup_mutex); - cpus_read_unlock(); - return ret; -} - -enum rdt_param { - Opt_cdp, - Opt_cdpl2, - Opt_mba_mbps, - Opt_debug, - 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), - fsparam_flag("debug", Opt_debug), - {} -}; - -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; - const char *msg; - 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: - msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope"; - if (!supports_mba_mbps()) - return invalfc(fc, msg); - ctx->enable_mba_mbps = true; - return 0; - case Opt_debug: - ctx->enable_debug = 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.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 rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - struct rdt_hw_ctrl_domain *hw_dom; - struct msr_param msr_param; - struct rdt_ctrl_domain *d; - int i; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - msr_param.res = r; - msr_param.low = 0; - msr_param.high = hw_res->num_closid; - - /* - * Disable resource control for this resource by setting all - * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU - * from each domain to update the MSRs below. - */ - list_for_each_entry(d, &r->ctrl_domains, hdr.list) { - hw_dom = resctrl_to_arch_ctrl_dom(d); - - for (i = 0; i < hw_res->num_closid; i++) - hw_dom->ctrl_val[i] = r->default_ctrl; - msr_param.dom = d; - smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1); - } - - 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)) { - resctrl_arch_set_closid_rmid(t, to->closid, - 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->closid, 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; - - /* - * 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); - - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || - rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - rdtgroup_pseudo_lock_remove(rdtgrp); - } else { - /* Pseudo-locked group's RMID is freed during setup. */ - free_rmid(rdtgrp->closid, 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); - - rdt_disable_ctx(); - - /*Put everything back to default values. */ - for_each_alloc_capable_rdt_resource(r) - reset_all_ctrls(r); - rmdir_all_sub(); - rdt_pseudo_lock_release(); - rdtgroup_default.mode = RDT_MODE_SHAREABLE; - schemata_list_destroy(); - rdtgroup_destroy_root(); - if (resctrl_arch_alloc_capable()) - resctrl_arch_disable_alloc(); - if (resctrl_arch_mon_capable()) - resctrl_arch_disable_mon(); - resctrl_mounted = false; - 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; -} - -static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname) -{ - struct kernfs_node *kn; - - kn = kernfs_find_and_get(pkn, name); - if (!kn) - return; - kernfs_put(kn); - - if (kn->dir.subdirs <= 1) - kernfs_remove(kn); - else - kernfs_remove_by_name(kn, subname); -} - -/* - * Remove all subdirectories of mon_data of ctrl_mon groups - * and monitor groups for the given domain. - * Remove files and directories containing "sum" of domain data - * when last domain being summed is removed. - */ -static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_mon_domain *d) -{ - struct rdtgroup *prgrp, *crgrp; - char subname[32]; - bool snc_mode; - char name[32]; - - snc_mode = r->mon_scope == RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); - if (snc_mode) - sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id); - - list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { - mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname); - - list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) - mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname); - } -} - -static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d, - struct rdt_resource *r, struct rdtgroup *prgrp, - bool do_sum) -{ - struct rmid_read rr = {0}; - union mon_data_bits priv; - struct mon_evt *mevt; - int ret; - - if (WARN_ON(list_empty(&r->evt_list))) - return -EPERM; - - priv.u.rid = r->rid; - priv.u.domid = do_sum ? d->ci_id : d->hdr.id; - priv.u.sum = do_sum; - list_for_each_entry(mevt, &r->evt_list, list) { - priv.u.evtid = mevt->evtid; - ret = mon_addfile(kn, mevt->name, priv.priv); - if (ret) - return ret; - - if (!do_sum && is_mbm_event(mevt->evtid)) - mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true); - } - - return 0; -} - -static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, - struct rdt_mon_domain *d, - struct rdt_resource *r, struct rdtgroup *prgrp) -{ - struct kernfs_node *kn, *ckn; - char name[32]; - bool snc_mode; - int ret = 0; - - lockdep_assert_held(&rdtgroup_mutex); - - snc_mode = r->mon_scope == RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); - kn = kernfs_find_and_get(parent_kn, name); - if (kn) { - /* - * rdtgroup_mutex will prevent this directory from being - * removed. No need to keep this hold. - */ - kernfs_put(kn); - } else { - 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; - ret = mon_add_all_files(kn, d, r, prgrp, snc_mode); - if (ret) - goto out_destroy; - } - - if (snc_mode) { - sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id); - ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp); - if (IS_ERR(ckn)) { - ret = -EINVAL; - goto out_destroy; - } - - ret = rdtgroup_kn_set_ugid(ckn); - if (ret) - goto out_destroy; - - ret = mon_add_all_files(ckn, d, r, prgrp, false); - if (ret) - goto out_destroy; - } - - 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. - */ -static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_mon_domain *d) -{ - struct kernfs_node *parent_kn; - struct rdtgroup *prgrp, *crgrp; - struct list_head *head; - - 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_mon_domain *dom; - int ret; - - /* Walking r->domains, ensure it can't race with cpuhp */ - lockdep_assert_cpus_held(); - - list_for_each_entry(dom, &r->mon_domains, hdr.list) { - ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); - 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 which are named - * in the format mon__. 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_capable_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_ctrl_domain *d, struct resctrl_schema *s, - u32 closid) -{ - enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); - enum resctrl_conf_type t = s->conf_type; - struct resctrl_staged_config *cfg; - struct rdt_resource *r = s->res; - u32 used_b = 0, unused_b = 0; - unsigned long tmp_cbm; - enum rdtgrp_mode mode; - u32 peer_ctl, ctrl_val; - int i; - - cfg = &d->staged_config[t]; - cfg->have_new_ctrl = false; - cfg->new_ctrl = r->cache.shareable_bits; - used_b = r->cache.shareable_bits; - for (i = 0; i < closids_supported(); i++) { - 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 (resctrl_arch_get_cdp_enabled(r->rid)) - peer_ctl = resctrl_arch_get_config(r, d, i, - peer_type); - else - peer_ctl = 0; - ctrl_val = resctrl_arch_get_config(r, d, i, - s->conf_type); - used_b |= ctrl_val | peer_ctl; - if (mode == RDT_MODE_SHAREABLE) - cfg->new_ctrl |= ctrl_val | 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; - cfg->new_ctrl |= unused_b; - /* - * Force the initial CBM to be valid, user can - * modify the CBM based on system availability. - */ - cfg->new_ctrl = cbm_ensure_valid(cfg->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 = cfg->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", s->name, d->hdr.id); - return -ENOSPC; - } - cfg->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 resctrl_schema *s, u32 closid) -{ - struct rdt_ctrl_domain *d; - int ret; - - list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) { - ret = __init_one_rdt_domain(d, s, closid); - if (ret < 0) - return ret; - } - - return 0; -} - -/* Initialize MBA resource with default values. */ -static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid) -{ - struct resctrl_staged_config *cfg; - struct rdt_ctrl_domain *d; - - list_for_each_entry(d, &r->ctrl_domains, hdr.list) { - if (is_mba_sc(r)) { - d->mbps_val[closid] = MBA_MAX_MBPS; - continue; - } - - cfg = &d->staged_config[CDP_NONE]; - cfg->new_ctrl = r->default_ctrl; - cfg->have_new_ctrl = true; - } -} - -/* Initialize the RDT group's allocations. */ -static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) -{ - struct resctrl_schema *s; - struct rdt_resource *r; - int ret = 0; - - rdt_staged_configs_clear(); - - list_for_each_entry(s, &resctrl_schema_all, list) { - r = s->res; - if (r->rid == RDT_RESOURCE_MBA || - r->rid == RDT_RESOURCE_SMBA) { - rdtgroup_init_mba(r, rdtgrp->closid); - if (is_mba_sc(r)) - continue; - } else { - ret = rdtgroup_init_cat(s, rdtgrp->closid); - if (ret < 0) - goto out; - } - - ret = resctrl_arch_update_domains(r, rdtgrp->closid); - if (ret < 0) { - rdt_last_cmd_puts("Failed to initialize allocations\n"); - goto out; - } - - } - - rdtgrp->mode = RDT_MODE_SHAREABLE; - -out: - rdt_staged_configs_clear(); - return ret; -} - -static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) -{ - int ret; - - if (!resctrl_arch_mon_capable()) - return 0; - - ret = alloc_rmid(rdtgrp->closid); - if (ret < 0) { - rdt_last_cmd_puts("Out of RMIDs\n"); - return ret; - } - rdtgrp->mon.rmid = ret; - - ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn); - if (ret) { - rdt_last_cmd_puts("kernfs subdir error\n"); - free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); - return ret; - } - - return 0; -} - -static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) -{ - if (resctrl_arch_mon_capable()) - free_rmid(rgrp->closid, rgrp->mon.rmid); -} - -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; - unsigned long files = 0; - struct kernfs_node *kn; - 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; - } - - if (rtype == RDTCTRL_GROUP) { - files = RFTYPE_BASE | RFTYPE_CTRL; - if (resctrl_arch_mon_capable()) - files |= RFTYPE_MON; - } else { - files = RFTYPE_BASE | RFTYPE_MON; - } - - ret = rdtgroup_add_files(kn, files); - if (ret) { - rdt_last_cmd_puts("kernfs fill error\n"); - goto out_destroy; - } - - /* - * The caller unlocks the parent_kn upon success. - */ - return 0; - -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); - 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; - - ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); - if (ret) { - mkdir_rdt_prepare_clean(rdtgrp); - goto out_unlock; - } - - kernfs_activate(rdtgrp->kn); - - /* - * 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); - -out_unlock: - 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 = mkdir_rdt_prepare_rmid_alloc(rdtgrp); - if (ret) - goto out_closid_free; - - kernfs_activate(rdtgrp->kn); - - ret = rdtgroup_init_alloc(rdtgrp); - if (ret < 0) - goto out_rmid_free; - - list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); - - if (resctrl_arch_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_rmid_free: - mkdir_rdt_prepare_rmid_free(rdtgrp); -out_closid_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 (resctrl_arch_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 (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name)) - return rdtgroup_mkdir_mon(parent_kn, name, mode); - - return -EPERM; -} - -static int rdtgroup_rmdir_mon(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->closid, 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 rdtgroup *rdtgrp) -{ - rdtgrp->flags = RDT_DELETED; - list_del(&rdtgrp->rdtgroup_list); - - kernfs_remove(rdtgrp->kn); - return 0; -} - -static int rdtgroup_rmdir_ctrl(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); - - free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); - closid_free(rdtgrp->closid); - - rdtgroup_ctrl_remove(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(rdtgrp); - } else { - ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask); - } - } else if (rdtgrp->type == RDTMON_GROUP && - is_mon_groups(parent_kn, kn->name)) { - ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask); - } else { - ret = -EPERM; - } - -out: - rdtgroup_kn_unlock(kn); - free_cpumask_var(tmpmask); - return ret; -} - -/** - * mongrp_reparent() - replace parent CTRL_MON group of a MON group - * @rdtgrp: the MON group whose parent should be replaced - * @new_prdtgrp: replacement parent CTRL_MON group for @rdtgrp - * @cpus: cpumask provided by the caller for use during this call - * - * Replaces the parent CTRL_MON group for a MON group, resulting in all member - * tasks' CLOSID immediately changing to that of the new parent group. - * Monitoring data for the group is unaffected by this operation. - */ -static void mongrp_reparent(struct rdtgroup *rdtgrp, - struct rdtgroup *new_prdtgrp, - cpumask_var_t cpus) -{ - struct rdtgroup *prdtgrp = rdtgrp->mon.parent; - - WARN_ON(rdtgrp->type != RDTMON_GROUP); - WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP); - - /* Nothing to do when simply renaming a MON group. */ - if (prdtgrp == new_prdtgrp) - return; - - WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); - list_move_tail(&rdtgrp->mon.crdtgrp_list, - &new_prdtgrp->mon.crdtgrp_list); - - rdtgrp->mon.parent = new_prdtgrp; - rdtgrp->closid = new_prdtgrp->closid; - - /* Propagate updated closid to all tasks in this group. */ - rdt_move_group_tasks(rdtgrp, rdtgrp, cpus); - - update_closid_rmid(cpus, NULL); -} - -static int rdtgroup_rename(struct kernfs_node *kn, - struct kernfs_node *new_parent, const char *new_name) -{ - struct rdtgroup *new_prdtgrp; - struct rdtgroup *rdtgrp; - cpumask_var_t tmpmask; - int ret; - - rdtgrp = kernfs_to_rdtgroup(kn); - new_prdtgrp = kernfs_to_rdtgroup(new_parent); - if (!rdtgrp || !new_prdtgrp) - return -ENOENT; - - /* Release both kernfs active_refs before obtaining rdtgroup mutex. */ - rdtgroup_kn_get(rdtgrp, kn); - rdtgroup_kn_get(new_prdtgrp, new_parent); - - mutex_lock(&rdtgroup_mutex); - - rdt_last_cmd_clear(); - - /* - * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if - * either kernfs_node is a file. - */ - if (kernfs_type(kn) != KERNFS_DIR || - kernfs_type(new_parent) != KERNFS_DIR) { - rdt_last_cmd_puts("Source and destination must be directories"); - ret = -EPERM; - goto out; - } - - if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) { - ret = -ENOENT; - goto out; - } - - if (rdtgrp->type != RDTMON_GROUP || !kn->parent || - !is_mon_groups(kn->parent, kn->name)) { - rdt_last_cmd_puts("Source must be a MON group\n"); - ret = -EPERM; - goto out; - } - - if (!is_mon_groups(new_parent, new_name)) { - rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n"); - ret = -EPERM; - goto out; - } - - /* - * If the MON group is monitoring CPUs, the CPUs must be assigned to the - * current parent CTRL_MON group and therefore cannot be assigned to - * the new parent, making the move illegal. - */ - if (!cpumask_empty(&rdtgrp->cpu_mask) && - rdtgrp->mon.parent != new_prdtgrp) { - rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n"); - ret = -EPERM; - goto out; - } - - /* - * Allocate the cpumask for use in mongrp_reparent() to avoid the - * possibility of failing to allocate it after kernfs_rename() has - * succeeded. - */ - if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) { - ret = -ENOMEM; - goto out; - } - - /* - * Perform all input validation and allocations needed to ensure - * mongrp_reparent() will succeed before calling kernfs_rename(), - * otherwise it would be necessary to revert this call if - * mongrp_reparent() failed. - */ - ret = kernfs_rename(kn, new_parent, new_name); - if (!ret) - mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask); - - free_cpumask_var(tmpmask); - -out: - mutex_unlock(&rdtgroup_mutex); - rdtgroup_kn_put(rdtgrp, kn); - rdtgroup_kn_put(new_prdtgrp, new_parent); - return ret; -} - -static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) -{ - if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) - seq_puts(seq, ",cdp"); - - if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) - seq_puts(seq, ",cdpl2"); - - if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl)) - seq_puts(seq, ",mba_MBps"); - - if (resctrl_debug) - seq_puts(seq, ",debug"); - - return 0; -} - -static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { - .mkdir = rdtgroup_mkdir, - .rmdir = rdtgroup_rmdir, - .rename = rdtgroup_rename, - .show_options = rdtgroup_show_options, -}; - -static int rdtgroup_setup_root(struct rdt_fs_context *ctx) -{ - 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); - - ctx->kfc.root = rdt_root; - rdtgroup_default.kn = kernfs_root_to_node(rdt_root); - - return 0; -} - -static void rdtgroup_destroy_root(void) -{ - kernfs_destroy_root(rdt_root); - rdtgroup_default.kn = NULL; -} - -static void __init rdtgroup_setup_default(void) -{ - mutex_lock(&rdtgroup_mutex); - - rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID; - rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID; - rdtgroup_default.type = RDTCTRL_GROUP; - INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); - - list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - - mutex_unlock(&rdtgroup_mutex); -} - -static void domain_destroy_mon_state(struct rdt_mon_domain *d) -{ - bitmap_free(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); -} - -void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d) -{ - mutex_lock(&rdtgroup_mutex); - - if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) - mba_sc_domain_destroy(r, d); - - mutex_unlock(&rdtgroup_mutex); -} - -void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) -{ - mutex_lock(&rdtgroup_mutex); - - /* - * If resctrl is mounted, remove all the - * per domain monitor data directories. - */ - if (resctrl_mounted && resctrl_arch_mon_capable()) - rmdir_mondata_subdir_allrdtgrp(r, d); - - if (is_mbm_enabled()) - cancel_delayed_work(&d->mbm_over); - if (is_llc_occupancy_enabled() && has_busy_rmid(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); - } - - domain_destroy_mon_state(d); - - mutex_unlock(&rdtgroup_mutex); -} - -static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d) -{ - u32 idx_limit = resctrl_arch_system_num_rmid_idx(); - size_t tsize; - - if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL); - if (!d->rmid_busy_llc) - return -ENOMEM; - } - if (is_mbm_total_enabled()) { - tsize = sizeof(*d->mbm_total); - d->mbm_total = kcalloc(idx_limit, 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(idx_limit, tsize, GFP_KERNEL); - if (!d->mbm_local) { - bitmap_free(d->rmid_busy_llc); - kfree(d->mbm_total); - return -ENOMEM; - } - } - - return 0; -} - -int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d) -{ - int err = 0; - - mutex_lock(&rdtgroup_mutex); - - if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) { - /* RDT_RESOURCE_MBA is never mon_capable */ - err = mba_sc_domain_allocate(r, d); - } - - mutex_unlock(&rdtgroup_mutex); - - return err; -} - -int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d) -{ - int err; - - mutex_lock(&rdtgroup_mutex); - - err = domain_setup_mon_state(r, d); - if (err) - goto out_unlock; - - if (is_mbm_enabled()) { - INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); - mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL, - RESCTRL_PICK_ANY_CPU); - } - - if (is_llc_occupancy_enabled()) - INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); - - /* - * If the filesystem is not mounted then only the default resource group - * exists. Creation of its directories is deferred until mount time - * by rdt_get_tree() calling mkdir_mondata_all(). - * If resctrl is mounted, add per domain monitor data directories. - */ - if (resctrl_mounted && resctrl_arch_mon_capable()) - mkdir_mondata_subdir_allrdtgrp(r, d); - -out_unlock: - mutex_unlock(&rdtgroup_mutex); - - return err; -} - -void resctrl_online_cpu(unsigned int cpu) -{ - mutex_lock(&rdtgroup_mutex); - /* The CPU is set in default rdtgroup after online. */ - cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); - mutex_unlock(&rdtgroup_mutex); -} - -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; - } -} - -void resctrl_offline_cpu(unsigned int cpu) -{ - struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; - struct rdt_mon_domain *d; - struct rdtgroup *rdtgrp; - - mutex_lock(&rdtgroup_mutex); - 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; - } - } - - if (!l3->mon_capable) - goto out_unlock; - - d = get_mon_domain_from_cpu(cpu, l3); - if (d) { - if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { - cancel_delayed_work(&d->mbm_over); - mbm_setup_overflow_handler(d, 0, cpu); - } - if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && - has_busy_rmid(d)) { - cancel_delayed_work(&d->cqm_limbo); - cqm_setup_limbo_handler(d, 0, cpu); - } - } - -out_unlock: - mutex_unlock(&rdtgroup_mutex); -} - -/* - * 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)); - - rdtgroup_setup_default(); - - ret = sysfs_create_mount_point(fs_kobj, "resctrl"); - if (ret) - return ret; - - 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"); - - return ret; -} - -void __exit rdtgroup_exit(void) -{ - debugfs_remove_recursive(debugfs_resctrl); - unregister_filesystem(&rdt_fs_type); - sysfs_remove_mount_point(fs_kobj, "resctrl"); + return; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 5adf08a2aca30..a2f075879776e 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -50,6 +50,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, + { X86_FEATURE_ABMC, CPUID_EBX, 5, 0x80000020, 0 }, { X86_FEATURE_AMD_WORKLOAD_CLASS, CPUID_EAX, 22, 0x80000021, 0 }, { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, { X86_FEATURE_TSA_L1_NO, CPUID_ECX, 2, 0x80000021, 0 }, diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 708c87b88cc15..619560eb9f94c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -212,7 +212,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) switch_fpu_finish(); /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(next_p); + resctrl_arch_sched_in(next_p); return prev_p; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index dd19a4db741af..fa04091e2f4eb 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -659,7 +659,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) } /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(next_p); + resctrl_arch_sched_in(next_p); return prev_p; } diff --git a/config.x86_64 b/config.x86_64 index adcdaca218081..e1edcb4700103 100644 --- a/config.x86_64 +++ b/config.x86_64 @@ -326,6 +326,7 @@ CONFIG_X86_X2APIC=y CONFIG_X86_MPPARSE=y # CONFIG_GOLDFISH is not set CONFIG_X86_CPU_RESCTRL=y +CONFIG_X86_CPU_RESCTRL_INTEL_AET=y # CONFIG_X86_EXTENDED_PLATFORM is not set CONFIG_X86_INTEL_LPSS=y CONFIG_X86_AMD_PLATFORM_DEVICE=y @@ -8187,10 +8188,10 @@ CONFIG_INTEL_IFS=m # CONFIG_INTEL_SAR_INT1092 is not set # CONFIG_INTEL_SKL_INT3472 is not set # CONFIG_INTEL_PMC_CORE is not set -CONFIG_INTEL_PMT_CLASS=m -CONFIG_INTEL_PMT_TELEMETRY=m +CONFIG_INTEL_PMT_CLASS=y +CONFIG_INTEL_PMT_TELEMETRY=y CONFIG_INTEL_PMT_CRASHLOG=m -CONFIG_INTEL_PMT_DISCOVERY=m +CONFIG_INTEL_PMT_DISCOVERY=y # # Intel Speed Select Technology interface support @@ -8217,10 +8218,10 @@ CONFIG_INTEL_OAKTRAIL=m # CONFIG_INTEL_PUNIT_IPC is not set CONFIG_INTEL_RST=m CONFIG_INTEL_SMARTCONNECT=m -CONFIG_INTEL_TPMI=m +CONFIG_INTEL_TPMI=y CONFIG_INTEL_PLR_TPMI=m # CONFIG_INTEL_TURBO_MAX_3 is not set -CONFIG_INTEL_VSEC=m +CONFIG_INTEL_VSEC=y # CONFIG_MSI_EC is not set CONFIG_MSI_LAPTOP=m CONFIG_MSI_WMI=m diff --git a/fs/Kconfig b/fs/Kconfig index 4bb2b0c3d63a2..336ec0a4812bf 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -332,6 +332,7 @@ source "fs/omfs/Kconfig" source "fs/hpfs/Kconfig" source "fs/qnx4/Kconfig" source "fs/qnx6/Kconfig" +source "fs/resctrl/Kconfig" source "fs/romfs/Kconfig" source "fs/pstore/Kconfig" source "fs/sysv/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index f9541f40be4e0..b62375770deed 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -129,3 +129,4 @@ obj-$(CONFIG_EFIVAR_FS) += efivarfs/ obj-$(CONFIG_EROFS_FS) += erofs/ obj-$(CONFIG_VBOXSF_FS) += vboxsf/ obj-$(CONFIG_ZONEFS_FS) += zonefs/ +obj-$(CONFIG_RESCTRL_FS) += resctrl/ diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index f6e2a4523f7e6..5f0d7e35463f8 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -15,9 +15,11 @@ #include #include +#include + #include "kernfs-internal.h" -static DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ +DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() @@ -51,22 +53,14 @@ static bool kernfs_lockdep(struct kernfs_node *kn) #endif } -static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) -{ - if (!kn) - return strlcpy(buf, "(null)", buflen); - - return strlcpy(buf, kn->parent ? kn->name : "/", buflen); -} - /* kernfs_node_depth - compute depth from @from to @to */ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; - while (to->parent && to != from) { + while (rcu_dereference(to->__parent) && to != from) { depth++; - to = to->parent; + to = rcu_dereference(to->__parent); } return depth; } @@ -84,18 +78,18 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, db = kernfs_depth(rb->kn, b); while (da > db) { - a = a->parent; + a = rcu_dereference(a->__parent); da--; } while (db > da) { - b = b->parent; + b = rcu_dereference(b->__parent); db--; } /* worst case b and a will be the same at root */ while (b != a) { - b = b->parent; - a = a->parent; + b = rcu_dereference(b->__parent); + a = rcu_dereference(a->__parent); } return a; @@ -168,10 +162,13 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { + const char *name; + for (kn = kn_to, j = 0; j < i; j++) - kn = kn->parent; + kn = rcu_dereference(kn->__parent); - len += scnprintf(buf + len, buflen - len, "/%s", kn->name); + name = rcu_dereference(kn->name); + len += scnprintf(buf + len, buflen - len, "/%s", name); } return len; @@ -184,24 +181,29 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, * @buflen: size of @buf * * Copies the name of @kn into @buf of @buflen bytes. The behavior is - * similar to strlcpy(). + * similar to strscpy(). * * Fills buffer with "(null)" if @kn is %NULL. * - * Return: the length of @kn's name and if @buf isn't long enough, - * it's filled up to @buflen-1 and nul terminated. + * Return: the resulting length of @buf. If @buf isn't long enough, + * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG. * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { - unsigned long flags; - int ret; + struct kernfs_node *kn_parent; - read_lock_irqsave(&kernfs_rename_lock, flags); - ret = kernfs_name_locked(kn, buf, buflen); - read_unlock_irqrestore(&kernfs_rename_lock, flags); - return ret; + if (!kn) + return strscpy(buf, "(null)", buflen); + + guard(rcu)(); + /* + * KERNFS_ROOT_INVARIANT_PARENT is ignored here. The name is RCU freed and + * the parent is either existing or not. + */ + kn_parent = rcu_dereference(kn->__parent); + return strscpy(buf, kn_parent ? rcu_dereference(kn->name) : "/", buflen); } /** @@ -223,13 +225,17 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, char *buf, size_t buflen) { - unsigned long flags; - int ret; + struct kernfs_root *root; - read_lock_irqsave(&kernfs_rename_lock, flags); - ret = kernfs_path_from_node_locked(to, from, buf, buflen); - read_unlock_irqrestore(&kernfs_rename_lock, flags); - return ret; + guard(rcu)(); + if (to) { + root = kernfs_root(to); + if (!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)) { + guard(read_lock_irqsave)(&kernfs_rename_lock); + return kernfs_path_from_node_locked(to, from, buf, buflen); + } + } + return kernfs_path_from_node_locked(to, from, buf, buflen); } EXPORT_SYMBOL_GPL(kernfs_path_from_node); @@ -295,7 +301,7 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) unsigned long flags; read_lock_irqsave(&kernfs_rename_lock, flags); - parent = kn->parent; + parent = kernfs_parent(kn); kernfs_get(parent); read_unlock_irqrestore(&kernfs_rename_lock, flags); @@ -336,13 +342,13 @@ static int kernfs_name_compare(unsigned int hash, const char *name, return -1; if (ns > kn->ns) return 1; - return strcmp(name, kn->name); + return strcmp(name, kernfs_rcu_name(kn)); } static int kernfs_sd_compare(const struct kernfs_node *left, const struct kernfs_node *right) { - return kernfs_name_compare(left->hash, left->name, left->ns, right); + return kernfs_name_compare(left->hash, kernfs_rcu_name(left), left->ns, right); } /** @@ -360,8 +366,12 @@ static int kernfs_sd_compare(const struct kernfs_node *left, */ static int kernfs_link_sibling(struct kernfs_node *kn) { - struct rb_node **node = &kn->parent->dir.children.rb_node; struct rb_node *parent = NULL; + struct kernfs_node *kn_parent; + struct rb_node **node; + + kn_parent = kernfs_parent(kn); + node = &kn_parent->dir.children.rb_node; while (*node) { struct kernfs_node *pos; @@ -380,13 +390,13 @@ static int kernfs_link_sibling(struct kernfs_node *kn) /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); - rb_insert_color(&kn->rb, &kn->parent->dir.children); + rb_insert_color(&kn->rb, &kn_parent->dir.children); /* successfully added, account subdir number */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs++; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs++; + kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); return 0; @@ -407,16 +417,19 @@ static int kernfs_link_sibling(struct kernfs_node *kn) */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { + struct kernfs_node *kn_parent; + if (RB_EMPTY_NODE(&kn->rb)) return false; + kn_parent = kernfs_parent(kn); down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs--; - kernfs_inc_rev(kn->parent); + kn_parent->dir.subdirs--; + kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); - rb_erase(&kn->rb, &kn->parent->dir.children); + rb_erase(&kn->rb, &kn_parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } @@ -533,7 +546,8 @@ static void kernfs_free_rcu(struct rcu_head *rcu) { struct kernfs_node *kn = container_of(rcu, struct kernfs_node, rcu); - kfree_const(kn->name); + /* If the whole node goes away, then name can't be used outside */ + kfree_const(rcu_access_pointer(kn->name)); if (kn->iattr) { simple_xattrs_free(&kn->iattr->xattrs, NULL); @@ -562,11 +576,12 @@ void kernfs_put(struct kernfs_node *kn) * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ - parent = kn->parent; + parent = kernfs_parent(kn); WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", - parent ? parent->name : "", kn->name, atomic_read(&kn->active)); + parent ? rcu_dereference(parent->name) : "", + rcu_dereference(kn->name), atomic_read(&kn->active)); if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); @@ -643,7 +658,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); - kn->name = name; + rcu_assign_pointer(kn->name, name); kn->mode = mode; kn->flags = flags; @@ -701,7 +716,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); - kn->parent = parent; + rcu_assign_pointer(kn->__parent, parent); } return kn; } @@ -769,18 +784,20 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, */ int kernfs_add_one(struct kernfs_node *kn) { - struct kernfs_node *parent = kn->parent; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); struct kernfs_iattrs *ps_iattr; + struct kernfs_node *parent; bool has_ns; int ret; down_write(&root->kernfs_rwsem); + parent = kernfs_parent(kn); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", - has_ns ? "required" : "invalid", parent->name, kn->name)) + has_ns ? "required" : "invalid", + kernfs_rcu_name(parent), kernfs_rcu_name(kn))) goto out_unlock; if (kernfs_type(parent) != KERNFS_DIR) @@ -790,7 +807,7 @@ int kernfs_add_one(struct kernfs_node *kn) if (parent->flags & (KERNFS_REMOVING | KERNFS_EMPTY_DIR)) goto out_unlock; - kn->hash = kernfs_name_hash(kn->name, kn->ns); + kn->hash = kernfs_name_hash(kernfs_rcu_name(kn), kn->ns); ret = kernfs_link_sibling(kn); if (ret) @@ -846,7 +863,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", - has_ns ? "required" : "invalid", parent->name, name); + has_ns ? "required" : "invalid", kernfs_rcu_name(parent), name); return NULL; } @@ -871,16 +888,16 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, const unsigned char *path, const void *ns) { - size_t len; + ssize_t len; char *p, *name; lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem); spin_lock_irq(&kernfs_pr_cont_lock); - len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); + len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); - if (len >= sizeof(kernfs_pr_cont_buf)) { + if (len < 0) { spin_unlock_irq(&kernfs_pr_cont_lock); return NULL; } @@ -949,6 +966,11 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, return kn; } +unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ + return kernfs_root(kn)->flags; +} + /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy @@ -1111,7 +1133,7 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) { - struct kernfs_node *kn; + struct kernfs_node *kn, *parent; struct kernfs_root *root; if (flags & LOOKUP_RCU) @@ -1119,8 +1141,6 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) /* Negative hashed dentry? */ if (d_really_is_negative(dentry)) { - struct kernfs_node *parent; - /* If the kernfs parent node has changed discard and * proceed to ->lookup. * @@ -1162,16 +1182,17 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) if (!kernfs_active(kn)) goto out_bad; + parent = kernfs_parent(kn); /* The kernfs node has been moved? */ - if (kernfs_dentry_node(dentry->d_parent) != kn->parent) + if (kernfs_dentry_node(dentry->d_parent) != parent) goto out_bad; /* The kernfs node has been renamed */ - if (strcmp(dentry->d_name.name, kn->name) != 0) + if (strcmp(dentry->d_name.name, kernfs_rcu_name(kn)) != 0) goto out_bad; /* The kernfs node has been moved to a different namespace */ - if (kn->parent && kernfs_ns_enabled(kn->parent) && + if (parent && kernfs_ns_enabled(parent) && kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; @@ -1364,7 +1385,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ - return pos->parent; + return kernfs_parent(pos); } static void kernfs_activate_one(struct kernfs_node *kn) @@ -1376,7 +1397,7 @@ static void kernfs_activate_one(struct kernfs_node *kn) if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING))) return; - WARN_ON_ONCE(kn->parent && RB_EMPTY_NODE(&kn->rb)); + WARN_ON_ONCE(rcu_access_pointer(kn->__parent) && RB_EMPTY_NODE(&kn->rb)); WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &kn->active); @@ -1446,7 +1467,7 @@ void kernfs_show(struct kernfs_node *kn, bool show) static void __kernfs_remove(struct kernfs_node *kn) { - struct kernfs_node *pos; + struct kernfs_node *pos, *parent; /* Short-circuit if non-root @kn has already finished removal. */ if (!kn) @@ -1458,10 +1479,10 @@ static void __kernfs_remove(struct kernfs_node *kn) * This is for kernfs_remove_self() which plays with active ref * after removal. */ - if (kn->parent && RB_EMPTY_NODE(&kn->rb)) + if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb)) return; - pr_debug("kernfs %s: removing\n", kn->name); + pr_debug("kernfs %s: removing\n", kernfs_rcu_name(kn)); /* prevent new usage by marking all nodes removing and deactivating */ pos = NULL; @@ -1484,14 +1505,14 @@ static void __kernfs_remove(struct kernfs_node *kn) kernfs_get(pos); kernfs_drain(pos); - + parent = kernfs_parent(pos); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ - if (!pos->parent || kernfs_unlink_sibling(pos)) { + if (!parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = - pos->parent ? pos->parent->iattr : NULL; + parent ? parent->iattr : NULL; /* update timestamps on the parent */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); @@ -1718,11 +1739,11 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, { struct kernfs_node *old_parent; struct kernfs_root *root; - const char *old_name = NULL; + const char *old_name; int error; /* can't move or rename root */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return -EINVAL; root = kernfs_root(kn); @@ -1733,9 +1754,19 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; + old_parent = kernfs_parent(kn); + if (root->flags & KERNFS_ROOT_INVARIANT_PARENT) { + error = -EINVAL; + if (WARN_ON_ONCE(old_parent != new_parent)) + goto out; + } + error = 0; - if ((kn->parent == new_parent) && (kn->ns == new_ns) && - (strcmp(kn->name, new_name) == 0)) + old_name = kernfs_rcu_name(kn); + if (!new_name) + new_name = old_name; + if ((old_parent == new_parent) && (kn->ns == new_ns) && + (strcmp(old_name, new_name) == 0)) goto out; /* nothing to rename */ error = -EEXIST; @@ -1743,7 +1774,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, goto out; /* rename kernfs_node */ - if (strcmp(kn->name, new_name) != 0) { + if (strcmp(old_name, new_name) != 0) { error = -ENOMEM; new_name = kstrdup_const(new_name, GFP_KERNEL); if (!new_name) @@ -1756,27 +1787,32 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, * Move to the appropriate place in the appropriate directories rbtree. */ kernfs_unlink_sibling(kn); - kernfs_get(new_parent); - /* rename_lock protects ->parent and ->name accessors */ - write_lock_irq(&kernfs_rename_lock); + /* rename_lock protects ->parent accessors */ + if (old_parent != new_parent) { + kernfs_get(new_parent); + write_lock_irq(&kernfs_rename_lock); - old_parent = kn->parent; - kn->parent = new_parent; + rcu_assign_pointer(kn->__parent, new_parent); - kn->ns = new_ns; - if (new_name) { - old_name = kn->name; - kn->name = new_name; - } + kn->ns = new_ns; + if (new_name) + rcu_assign_pointer(kn->name, new_name); - write_unlock_irq(&kernfs_rename_lock); + write_unlock_irq(&kernfs_rename_lock); + kernfs_put(old_parent); + } else { + /* name assignment is RCU protected, parent is the same */ + kn->ns = new_ns; + if (new_name) + rcu_assign_pointer(kn->name, new_name); + } - kn->hash = kernfs_name_hash(kn->name, kn->ns); + kn->hash = kernfs_name_hash(new_name ?: old_name, kn->ns); kernfs_link_sibling(kn); - kernfs_put(old_parent); - kfree_const(old_name); + if (new_name && !is_kernel_rodata((unsigned long)old_name)) + kfree_rcu_mightsleep(old_name); error = 0; out: @@ -1795,7 +1831,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns, { if (pos) { int valid = kernfs_active(pos) && - pos->parent == parent && hash == pos->hash; + rcu_access_pointer(pos->__parent) == parent && + hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; @@ -1860,7 +1897,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos); pos; pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { - const char *name = pos->name; + const char *name = kernfs_rcu_name(pos); unsigned int type = fs_umode_to_dtype(pos->mode); int len = strlen(name); ino_t ino = kernfs_ino(pos); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 257ba5398387b..6a67650244aa2 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -703,11 +703,18 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * - * Both paths of the branch look the same. They're supposed to + * For similar reasons, writable and readonly files are given different + * lockdep key, because the writable file /sys/power/resume may call vfs + * lookup helpers for arbitrary paths and readonly files can be read by + * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. + * + * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); + else if (file->f_mode & FMODE_WRITE) + mutex_init(&of->mutex); else mutex_init(&of->mutex); @@ -924,6 +931,33 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) return ret; } +static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) +{ + struct kernfs_open_file *of = kernfs_of(file); + const struct kernfs_ops *ops; + loff_t ret; + + /* + * @of->mutex nests outside active ref and is primarily to ensure that + * the ops aren't called concurrently for the same open file. + */ + mutex_lock(&of->mutex); + if (!kernfs_get_active(of->kn)) { + mutex_unlock(&of->mutex); + return -ENODEV; + } + + ops = kernfs_ops(of->kn); + if (ops->llseek) + ret = ops->llseek(of, offset, whence); + else + ret = generic_file_llseek(file, offset, whence); + + kernfs_put_active(of->kn); + mutex_unlock(&of->mutex); + return ret; +} + static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; @@ -945,9 +979,11 @@ static void kernfs_notify_workfn(struct work_struct *work) /* kick fsnotify */ down_read(&root->kernfs_supers_rwsem); + down_read(&root->kernfs_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; + const char *kn_name; struct inode *inode; struct qstr name; @@ -961,7 +997,8 @@ static void kernfs_notify_workfn(struct work_struct *work) if (!inode) continue; - name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); + kn_name = kernfs_rcu_name(kn); + name = (struct qstr)QSTR_INIT(kn_name, strlen(kn_name)); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); @@ -981,6 +1018,7 @@ static void kernfs_notify_workfn(struct work_struct *work) iput(inode); } + up_read(&root->kernfs_rwsem); up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; @@ -1026,7 +1064,7 @@ EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read_iter = kernfs_fop_read_iter, .write_iter = kernfs_fop_write_iter, - .llseek = generic_file_llseek, + .llseek = kernfs_fop_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 210dac7e9ee25..3de6346e41e5e 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -19,6 +19,8 @@ #include #include +extern rwlock_t kernfs_rename_lock; + struct kernfs_iattrs { kuid_t ia_uid; kgid_t ia_gid; @@ -64,11 +66,14 @@ struct kernfs_root { * * Return: the kernfs_root @kn belongs to. */ -static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) +static inline struct kernfs_root *kernfs_root(const struct kernfs_node *kn) { + const struct kernfs_node *knp; /* if parent exists, it's always a dir; otherwise, @sd is a dir */ - if (kn->parent) - kn = kn->parent; + guard(rcu)(); + knp = rcu_dereference(kn->__parent); + if (knp) + kn = knp; return kn->dir.root; } @@ -97,6 +102,32 @@ struct kernfs_super_info { }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) +static inline bool kernfs_root_is_locked(const struct kernfs_node *kn) +{ + return lockdep_is_held(&kernfs_root(kn)->kernfs_rwsem); +} + +static inline const char *kernfs_rcu_name(const struct kernfs_node *kn) +{ + return rcu_dereference_check(kn->name, kernfs_root_is_locked(kn)); +} + +static inline struct kernfs_node *kernfs_parent(const struct kernfs_node *kn) +{ + /* + * The kernfs_node::__parent remains valid within a RCU section. The kn + * can be reparented (and renamed) which changes the entry. This can be + * avoided by locking kernfs_root::kernfs_rwsem or kernfs_rename_lock. + * Both locks can be used to obtain a reference on __parent. Once the + * reference count reaches 0 then the node is about to be freed + * and can not be renamed (or become a different parent) anymore. + */ + return rcu_dereference_check(kn->__parent, + kernfs_root_is_locked(kn) || + lockdep_is_held(&kernfs_rename_lock) || + !atomic_read(&kn->count)); +} + static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) { if (d_really_is_negative(dentry)) diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index c4bf26142eec9..385f6e25f3b42 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -147,8 +147,10 @@ static struct dentry *kernfs_fh_to_parent(struct super_block *sb, static struct dentry *kernfs_get_parent_dentry(struct dentry *child) { struct kernfs_node *kn = kernfs_dentry_node(child); + struct kernfs_root *root = kernfs_root(kn); - return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent)); + guard(rwsem_read)(&root->kernfs_rwsem); + return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn))); } static const struct export_operations kernfs_export_ops = { @@ -188,10 +190,10 @@ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child, return NULL; } - while (child->parent != parent) { - if (!child->parent) + while (kernfs_parent(child) != parent) { + child = kernfs_parent(child); + if (!child) return NULL; - child = child->parent; } return child; @@ -208,17 +210,28 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct super_block *sb) { struct dentry *dentry; - struct kernfs_node *knparent = NULL; + struct kernfs_node *knparent; + struct kernfs_root *root; BUG_ON(sb->s_op != &kernfs_sops); dentry = dget(sb->s_root); /* Check if this is the root kernfs_node */ - if (!kn->parent) + if (!rcu_access_pointer(kn->__parent)) return dentry; - knparent = find_next_ancestor(kn, NULL); + root = kernfs_root(kn); + /* + * As long as kn is valid, its parent can not vanish. This is cgroup's + * kn so it can't have its parent replaced. Therefore it is safe to use + * the ancestor node outside of the RCU or locked section. + */ + if (WARN_ON_ONCE(!(root->flags & KERNFS_ROOT_INVARIANT_PARENT))) + return ERR_PTR(-EINVAL); + scoped_guard(rcu) { + knparent = find_next_ancestor(kn, NULL); + } if (WARN_ON(!knparent)) { dput(dentry); return ERR_PTR(-EINVAL); @@ -227,17 +240,26 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, do { struct dentry *dtmp; struct kernfs_node *kntmp; + const char *name; if (kn == knparent) return dentry; - kntmp = find_next_ancestor(kn, knparent); - if (WARN_ON(!kntmp)) { + + scoped_guard(rwsem_read, &root->kernfs_rwsem) { + kntmp = find_next_ancestor(kn, knparent); + if (WARN_ON(!kntmp)) { + dput(dentry); + return ERR_PTR(-EINVAL); + } + name = kstrdup(kernfs_rcu_name(kntmp), GFP_KERNEL); + } + if (!name) { dput(dentry); - return ERR_PTR(-EINVAL); + return ERR_PTR(-ENOMEM); } - dtmp = lookup_positive_unlocked(kntmp->name, dentry, - strlen(kntmp->name)); + dtmp = lookup_positive_unlocked(name, dentry, strlen(name)); dput(dentry); + kfree(name); if (IS_ERR(dtmp)) return dtmp; knparent = kntmp; diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 45371a70caa71..0bd8a2143723d 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -62,10 +62,10 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* go up to the root, stop at the base */ base = parent; - while (base->parent) { - kn = target->parent; - while (kn->parent && base != kn) - kn = kn->parent; + while (kernfs_parent(base)) { + kn = kernfs_parent(target); + while (kernfs_parent(kn) && base != kn) + kn = kernfs_parent(kn); if (base == kn) break; @@ -75,14 +75,14 @@ static int kernfs_get_target_path(struct kernfs_node *parent, strcpy(s, "../"); s += 3; - base = base->parent; + base = kernfs_parent(base); } /* determine end of target string for reverse fillup */ kn = target; - while (kn->parent && kn != base) { - len += strlen(kn->name) + 1; - kn = kn->parent; + while (kernfs_parent(kn) && kn != base) { + len += strlen(kernfs_rcu_name(kn)) + 1; + kn = kernfs_parent(kn); } /* check limits */ @@ -94,15 +94,16 @@ static int kernfs_get_target_path(struct kernfs_node *parent, /* reverse fillup of target string from target to base */ kn = target; - while (kn->parent && kn != base) { - int slen = strlen(kn->name); + while (kernfs_parent(kn) && kn != base) { + const char *name = kernfs_rcu_name(kn); + int slen = strlen(name); len -= slen; - memcpy(s + len, kn->name, slen); + memcpy(s + len, name, slen); if (len) s[--len] = '/'; - kn = kn->parent; + kn = kernfs_parent(kn); } return 0; @@ -111,12 +112,13 @@ static int kernfs_get_target_path(struct kernfs_node *parent, static int kernfs_getlink(struct inode *inode, char *path) { struct kernfs_node *kn = inode->i_private; - struct kernfs_node *parent = kn->parent; + struct kernfs_node *parent; struct kernfs_node *target = kn->symlink.target_kn; - struct kernfs_root *root = kernfs_root(parent); + struct kernfs_root *root = kernfs_root(kn); int error; down_read(&root->kernfs_rwsem); + parent = kernfs_parent(kn); error = kernfs_get_target_path(parent, target, path); up_read(&root->kernfs_rwsem); diff --git a/fs/resctrl/Kconfig b/fs/resctrl/Kconfig new file mode 100644 index 0000000000000..21671301bd8a4 --- /dev/null +++ b/fs/resctrl/Kconfig @@ -0,0 +1,39 @@ +config RESCTRL_FS + bool "CPU Resource Control Filesystem (resctrl)" + depends on ARCH_HAS_CPU_RESCTRL + select KERNFS + select PROC_CPU_RESCTRL if PROC_FS + help + Some architectures provide hardware facilities to group tasks and + monitor and control their usage of memory system resources such as + caches and memory bandwidth. Examples of such facilities include + Intel's Resource Director Technology (Intel(R) RDT) and AMD's + Platform Quality of Service (AMD QoS). + + If your system has the necessary support and you want to be able to + assign tasks to groups and manipulate the associated resource + monitors and controls from userspace, say Y here to get a mountable + 'resctrl' filesystem that lets you do just that. + + If nothing mounts or prods the 'resctrl' filesystem, resource + controls and monitors are left in a quiescent, permissive state. + + On architectures where this can be disabled independently, it is + safe to say N. + + See for more information. + +config RESCTRL_FS_PSEUDO_LOCK + bool + depends on RESCTRL_FS + help + Software mechanism to pin data in a cache portion using + micro-architecture specific knowledge. + +config RESCTRL_RMID_DEPENDS_ON_CLOSID + bool + depends on RESCTRL_FS + help + Enabled by the architecture when the RMID values depend on the CLOSID. + This causes the CLOSID allocator to search for CLOSID with clean + RMID. diff --git a/fs/resctrl/Makefile b/fs/resctrl/Makefile new file mode 100644 index 0000000000000..e67f34d2236a2 --- /dev/null +++ b/fs/resctrl/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_RESCTRL_FS) += rdtgroup.o ctrlmondata.o monitor.o +obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK) += pseudo_lock.o + +# To allow define_trace.h's recursive include: +CFLAGS_monitor.o = -I$(src) diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c new file mode 100644 index 0000000000000..0c6f9a8230664 --- /dev/null +++ b/fs/resctrl/ctrlmondata.c @@ -0,0 +1,763 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Cache Allocation code. + * + * Copyright (C) 2016 Intel Corporation + * + * Authors: + * Fenghua Yu + * Tony Luck + * + * 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 +#include +#include +#include +#include +#include + +#include "internal.h" + +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + +typedef int (ctrlval_parser_t)(struct rdt_parse_data *data, + struct resctrl_schema *s, + struct rdt_ctrl_domain *d); + +/* + * 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, u32 *data, struct rdt_resource *r) +{ + int ret; + u32 bw; + + /* + * 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 = kstrtou32(buf, 10, &bw); + if (ret) { + rdt_last_cmd_printf("Invalid MB value %s\n", buf); + return false; + } + + /* Nothing else to do if software controller is enabled. */ + if (is_mba_sc(r)) { + *data = bw; + return true; + } + + if (bw < r->membw.min_bw || bw > r->membw.max_bw) { + rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n", + bw, r->membw.min_bw, r->membw.max_bw); + return false; + } + + *data = roundup(bw, (unsigned long)r->membw.bw_gran); + return true; +} + +static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, + struct rdt_ctrl_domain *d) +{ + struct resctrl_staged_config *cfg; + u32 closid = data->rdtgrp->closid; + struct rdt_resource *r = s->res; + u32 bw_val; + + cfg = &d->staged_config[s->conf_type]; + if (cfg->have_new_ctrl) { + rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id); + return -EINVAL; + } + + if (!bw_validate(data->buf, &bw_val, r)) + return -EINVAL; + + if (is_mba_sc(r)) { + d->mbps_val[closid] = bw_val; + return 0; + } + + cfg->new_ctrl = bw_val; + cfg->have_new_ctrl = true; + + return 0; +} + +/* + * Check whether a cache bit mask is valid. + * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID: + * - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1 + * - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1 + * + * Haswell does not support a non-contiguous 1s value and additionally + * requires at least two bits set. + * AMD allows non-contiguous bitmasks. + */ +static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) +{ + u32 supported_bits = BIT_MASK(r->cache.cbm_len) - 1; + unsigned int cbm_len = r->cache.cbm_len; + unsigned long first_bit, zero_bit, val; + 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.min_cbm_bits > 0 && val == 0) || val > supported_bits) { + 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 bitmasks allowed? */ + if (!r->cache.arch_has_sparse_bitmasks && + (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. + */ +static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, + struct rdt_ctrl_domain *d) +{ + struct rdtgroup *rdtgrp = data->rdtgrp; + struct resctrl_staged_config *cfg; + struct rdt_resource *r = s->res; + u32 cbm_val; + + cfg = &d->staged_config[s->conf_type]; + if (cfg->have_new_ctrl) { + rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.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(s, d, cbm_val, rdtgrp->closid, true)) { + rdt_last_cmd_puts("Overlaps with exclusive group\n"); + return -EINVAL; + } + + if (rdtgroup_cbm_overlaps(s, 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; + } + } + + cfg->new_ctrl = cbm_val; + cfg->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 resctrl_schema *s, + struct rdtgroup *rdtgrp) +{ + enum resctrl_conf_type t = s->conf_type; + ctrlval_parser_t *parse_ctrlval = NULL; + struct resctrl_staged_config *cfg; + struct rdt_resource *r = s->res; + struct rdt_parse_data data; + struct rdt_ctrl_domain *d; + char *dom = NULL, *id; + unsigned long dom_id; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + switch (r->schema_fmt) { + case RESCTRL_SCHEMA_BITMAP: + parse_ctrlval = &parse_cbm; + break; + case RESCTRL_SCHEMA_RANGE: + parse_ctrlval = &parse_bw; + break; + } + + if (WARN_ON_ONCE(!parse_ctrlval)) + return -EINVAL; + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) { + 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->ctrl_domains, hdr.list) { + if (d->hdr.id == dom_id) { + data.buf = dom; + data.rdtgrp = rdtgrp; + if (parse_ctrlval(&data, s, d)) + return -EINVAL; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + cfg = &d->staged_config[t]; + /* + * 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->s = s; + rdtgrp->plr->d = d; + rdtgrp->plr->cbm = cfg->new_ctrl; + d->plr = rdtgrp->plr; + return 0; + } + goto next; + } + } + return -EINVAL; +} + +static int rdtgroup_parse_resource(char *resname, char *tok, + struct rdtgroup *rdtgrp) +{ + struct resctrl_schema *s; + + list_for_each_entry(s, &resctrl_schema_all, list) { + if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid) + return parse_line(tok, s, 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 resctrl_schema *s; + struct rdtgroup *rdtgrp; + 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'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + 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; + } + + rdt_staged_configs_clear(); + + 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; + } + + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; + + /* + * Writes to mba_sc resources update the software controller, + * not the control MSR. + */ + if (is_mba_sc(r)) + continue; + + ret = resctrl_arch_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: + rdt_staged_configs_clear(); + rdtgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + +static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) +{ + struct rdt_resource *r = schema->res; + struct rdt_ctrl_domain *dom; + bool sep = false; + u32 ctrl_val; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + seq_printf(s, "%*s:", max_name_width, schema->name); + list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { + if (sep) + seq_puts(s, ";"); + + if (is_mba_sc(r)) + ctrl_val = dom->mbps_val[closid]; + else + ctrl_val = resctrl_arch_get_config(r, dom, closid, + schema->conf_type); + + seq_printf(s, schema->fmt_str, dom->hdr.id, ctrl_val); + sep = true; + } + seq_puts(s, "\n"); +} + +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct resctrl_schema *schema; + struct rdtgroup *rdtgrp; + int ret = 0; + u32 closid; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) { + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + list_for_each_entry(schema, &resctrl_schema_all, list) { + seq_printf(s, "%s:uninitialized\n", schema->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->s->res->name, + rdtgrp->plr->d->hdr.id, + rdtgrp->plr->cbm); + } + } else { + closid = rdtgrp->closid; + list_for_each_entry(schema, &resctrl_schema_all, list) { + if (closid < schema->num_closid) + show_doms(s, schema, closid); + } + } + } else { + ret = -ENOENT; + } + rdtgroup_kn_unlock(of->kn); + return ret; +} + +static int smp_mon_event_count(void *arg) +{ + mon_event_count(arg); + + return 0; +} + +ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + 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(); + + if (!strcmp(buf, "mbm_local_bytes")) { + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) + rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID; + else + ret = -EINVAL; + } else if (!strcmp(buf, "mbm_total_bytes")) { + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) + rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID; + else + ret = -EINVAL; + } else { + ret = -EINVAL; + } + + if (ret) + rdt_last_cmd_printf("Unsupported event id '%s'\n", buf); + + rdtgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +int rdtgroup_mba_mbps_event_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) { + switch (rdtgrp->mba_mbps_event) { + case QOS_L3_MBM_LOCAL_EVENT_ID: + seq_puts(s, "mbm_local_bytes\n"); + break; + case QOS_L3_MBM_TOTAL_EVENT_ID: + seq_puts(s, "mbm_total_bytes\n"); + break; + default: + pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event); + ret = -EINVAL; + break; + } + } else { + ret = -ENOENT; + } + + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id, + struct list_head **pos) +{ + struct rdt_domain_hdr *d; + struct list_head *l; + + list_for_each(l, h) { + d = list_entry(l, struct rdt_domain_hdr, 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 mon_event_read(struct rmid_read *rr, struct rdt_resource *r, + struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, + cpumask_t *cpumask, struct mon_evt *evt, int first) +{ + int cpu; + + /* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + /* + * Setup the parameters to pass to mon_event_count() to read the data. + */ + rr->rgrp = rdtgrp; + rr->evt = evt; + rr->r = r; + rr->hdr = hdr; + rr->first = first; + if (resctrl_arch_mbm_cntr_assign_enabled(r) && + resctrl_is_mbm_event(evt->evtid)) { + rr->is_mbm_cntr = true; + } else { + rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evt->evtid); + if (IS_ERR(rr->arch_mon_ctx)) { + rr->err = -EINVAL; + return; + } + } + + if (evt->any_cpu) { + mon_event_count(rr); + goto out_ctx_free; + } + + cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU); + + /* + * cpumask_any_housekeeping() prefers housekeeping CPUs, but + * are all the CPUs nohz_full? If yes, pick a CPU to IPI. + * MPAM's resctrl_arch_rmid_read() is unable to read the + * counters on some platforms if its called in IRQ context. + */ + if (tick_nohz_full_cpu(cpu)) + smp_call_function_any(cpumask, mon_event_count, rr, 1); + else + smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); + +out_ctx_free: + if (rr->arch_mon_ctx) + resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx); +} + +/* + * Decimal place precision to use for each number of fixed-point + * binary bits computed from ceil(binary_bits * log10(2)) except + * binary_bits == 0 which will print "value.0" + */ +static const unsigned int decplaces[MAX_BINARY_BITS + 1] = { + [0] = 1, + [1] = 1, + [2] = 1, + [3] = 1, + [4] = 2, + [5] = 2, + [6] = 2, + [7] = 3, + [8] = 3, + [9] = 3, + [10] = 4, + [11] = 4, + [12] = 4, + [13] = 4, + [14] = 5, + [15] = 5, + [16] = 5, + [17] = 6, + [18] = 6, + [19] = 6, + [20] = 7, + [21] = 7, + [22] = 7, + [23] = 7, + [24] = 8, + [25] = 8, + [26] = 8, + [27] = 9 +}; + +static void print_event_value(struct seq_file *m, unsigned int binary_bits, u64 val) +{ + unsigned long long frac = 0; + + if (binary_bits) { + /* Mask off the integer part of the fixed-point value. */ + frac = val & GENMASK_ULL(binary_bits - 1, 0); + + /* + * Multiply by 10^{desired decimal places}. The integer part of + * the fixed point value is now almost what is needed. + */ + frac *= int_pow(10ull, decplaces[binary_bits]); + + /* + * Round to nearest by adding a value that would be a "1" in the + * binary_bits + 1 place. Integer part of fixed point value is + * now the needed value. + */ + frac += 1ull << (binary_bits - 1); + + /* + * Extract the integer part of the value. This is the decimal + * representation of the original fixed-point fractional value. + */ + frac >>= binary_bits; + } + + /* + * "frac" is now in the range [0 .. 10^decplaces). I.e. string + * representation will fit into chosen number of decimal places. + */ + seq_printf(m, "%llu.%0*llu\n", val >> binary_bits, decplaces[binary_bits], frac); +} + +int rdtgroup_mondata_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + enum resctrl_res_level resid; + struct rdt_domain_hdr *hdr; + struct rmid_read rr = {0}; + struct rdtgroup *rdtgrp; + int domid, cpu, ret = 0; + struct rdt_resource *r; + struct cacheinfo *ci; + struct mon_evt *evt; + struct mon_data *md; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } + + md = of->kn->priv; + if (WARN_ON_ONCE(!md)) { + ret = -EIO; + goto out; + } + + resid = md->rid; + domid = md->domid; + evt = md->evt; + r = resctrl_arch_get_resource(resid); + + if (md->sum) { + struct rdt_l3_mon_domain *d; + + if (WARN_ON_ONCE(resid != RDT_RESOURCE_L3)) { + ret = -EINVAL; + goto out; + } + + /* + * This file requires summing across all domains that share + * the L3 cache id that was provided in the "domid" field of the + * struct mon_data. Search all domains in the resource for + * one that matches this cache id. + */ + list_for_each_entry(d, &r->mon_domains, hdr.list) { + if (d->ci_id == domid) { + cpu = cpumask_any(&d->hdr.cpu_mask); + ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + if (!ci) + continue; + rr.ci = ci; + mon_event_read(&rr, r, NULL, rdtgrp, + &ci->shared_cpu_map, evt, false); + goto checkresult; + } + } + ret = -ENOENT; + goto out; + } else { + /* + * This file provides data from a single domain. Search + * the resource to find the domain with "domid". + */ + hdr = resctrl_find_domain(&r->mon_domains, domid, NULL); + if (!hdr) { + ret = -ENOENT; + goto out; + } + mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evt, false); + } + +checkresult: + + /* + * -ENOENT is a special case, set only when "mbm_event" counter assignment + * mode is enabled and no counter has been assigned. + */ + if (rr.err == -EIO) + seq_puts(m, "Error\n"); + else if (rr.err == -EINVAL) + seq_puts(m, "Unavailable\n"); + else if (rr.err == -ENOENT) + seq_puts(m, "Unassigned\n"); + else if (evt->is_floating_point) + print_event_value(m, evt->binary_bits, rr.val); + else + seq_printf(m, "%llu\n", rr.val); + +out: + rdtgroup_kn_unlock(of->kn); + return ret; +} diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h new file mode 100644 index 0000000000000..15270fb757b26 --- /dev/null +++ b/fs/resctrl/internal.h @@ -0,0 +1,467 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _FS_RESCTRL_INTERNAL_H +#define _FS_RESCTRL_INTERNAL_H + +#include +#include +#include +#include + +#define CQM_LIMBOCHECK_INTERVAL 1000 + +/** + * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that + * aren't marked nohz_full + * @mask: The mask to pick a CPU from. + * @exclude_cpu:The CPU to avoid picking. + * + * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping + * CPUs that don't use nohz_full, these are preferred. Pass + * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs. + * + * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available. + */ +static inline unsigned int +cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu) +{ + unsigned int cpu; + + /* Try to find a CPU that isn't nohz_full to use in preference */ + if (tick_nohz_full_enabled()) { + cpu = cpumask_any_andnot_but(mask, tick_nohz_full_mask, exclude_cpu); + if (cpu < nr_cpu_ids) + return cpu; + } + + return cpumask_any_but(mask, exclude_cpu); +} + +struct rdt_fs_context { + struct kernfs_fs_context kfc; + bool enable_cdpl2; + bool enable_cdpl3; + bool enable_mba_mbps; + bool enable_debug; +}; + +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); +} + +/** + * struct mon_evt - Properties of a monitor event + * @evtid: event id + * @rid: resource id for this event + * @name: name of the event + * @evt_cfg: Event configuration value that represents the + * memory transactions (e.g., READS_TO_LOCAL_MEM, + * READS_TO_REMOTE_MEM) being tracked by @evtid. + * Only valid if @evtid is an MBM event. + * @configurable: true if the event is configurable + * @any_cpu: true if the event can be read from any CPU + * @is_floating_point: event values are displayed in floating point format + * @binary_bits: number of fixed-point binary bits from architecture, + * only valid if @is_floating_point is true + * @enabled: true if the event is enabled + * @arch_priv: Architecture private data for this event. + * The @arch_priv provided by the architecture via + * resctrl_enable_mon_event(). + */ +struct mon_evt { + enum resctrl_event_id evtid; + enum resctrl_res_level rid; + char *name; + u32 evt_cfg; + bool configurable; + bool any_cpu; + bool is_floating_point; + unsigned int binary_bits; + bool enabled; + void *arch_priv; +}; + +extern struct mon_evt mon_event_all[QOS_NUM_EVENTS]; + +#define for_each_mon_event(mevt) for (mevt = &mon_event_all[QOS_FIRST_EVENT]; \ + mevt < &mon_event_all[QOS_NUM_EVENTS]; mevt++) + +/* Limit for mon_evt::binary_bits */ +#define MAX_BINARY_BITS 27 + +/** + * struct mon_data - Monitoring details for each event file. + * @list: Member of the global @mon_data_kn_priv_list list. + * @rid: Resource id associated with the event file. + * @evt: Event structure associated with the event file. + * @sum: Set for RDT_RESOURCE_L3 when event must be summed + * across multiple domains. + * @domid: When @sum is zero this is the domain to which + * the event file belongs. When @sum is one this + * is the id of the L3 cache that all domains to be + * summed share. + * + * Pointed to by the kernfs kn->priv field of monitoring event files. + * Readers and writers must hold rdtgroup_mutex. + */ +struct mon_data { + struct list_head list; + enum resctrl_res_level rid; + struct mon_evt *evt; + int domid; + bool sum; +}; + +/** + * struct rmid_read - Data passed across smp_call*() to read event count. + * @rgrp: Resource group for which the counter is being read. If it is a parent + * resource group then its event count is summed with the count from all + * its child resource groups. + * @r: Resource describing the properties of the event being read. + * @hdr: Header of domain that the counter should be read from. If NULL then + * sum all domains in @r sharing L3 @ci.id + * @evt: Which monitor event to read. + * @first: Initialize MBM counter when true. + * @ci: Cacheinfo for L3. Only set when @hdr is NULL. Used when summing + * domains. + * @is_mbm_cntr: true if "mbm_event" counter assignment mode is enabled and it + * is an MBM event. + * @err: Error encountered when reading counter. + * @val: Returned value of event counter. If @rgrp is a parent resource + * group, @val includes the sum of event counts from its child + * resource groups. If @hdr is NULL, @val includes the sum of all + * domains in @r sharing @ci.id, (summed across child resource groups + * if @rgrp is a parent resource group). + * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only). + */ +struct rmid_read { + struct rdtgroup *rgrp; + struct rdt_resource *r; + struct rdt_domain_hdr *hdr; + struct mon_evt *evt; + bool first; + struct cacheinfo *ci; + bool is_mbm_cntr; + int err; + u64 val; + void *arch_mon_ctx; +}; + +extern struct list_head resctrl_schema_all; + +extern bool resctrl_mounted; + +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 + * @RDT_NUM_MODES: Total number of modes + * + * 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: kernfs 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 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 + * @mba_mbps_event: input monitoring event id when mba_sc is enabled + * @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; + enum resctrl_event_id mba_mbps_event; + 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 RFTYPE_CTRL BIT(4) + +#define RFTYPE_MON BIT(5) + +#define RFTYPE_TOP BIT(6) + +#define RFTYPE_RES_CACHE BIT(8) + +#define RFTYPE_RES_MB BIT(9) + +#define RFTYPE_DEBUG BIT(10) + +#define RFTYPE_RES_PERF_PKG BIT(12) + +#define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) + +#define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) + +#define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) + +#define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) + +#define RFTYPE_MON_BASE (RFTYPE_BASE | RFTYPE_MON) + +/* List of all resource groups */ +extern struct list_head rdt_all_groups; + +extern int max_name_width; + +/** + * 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 RFTYPE_* flags + * @seq_show: Show content of the file + * @write: Write to the file + */ +struct rftype { + char *name; + umode_t mode; + const 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 + * @prev_bw_bytes: Previous bytes value read for bandwidth calculation + * @prev_bw: The most recent bandwidth in MBps + */ +struct mbm_state { + u64 prev_bw_bytes; + u32 prev_bw; +}; + +extern struct mutex rdtgroup_mutex; + +static inline const char *rdt_kn_name(const struct kernfs_node *kn) +{ + return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex)); +} + +extern struct rdtgroup rdtgroup_default; + +extern struct dentry *debugfs_resctrl; + +extern enum resctrl_event_id mba_mbps_default_event; + +void rdt_last_cmd_clear(void); + +void rdt_last_cmd_puts(const char *s); + +__printf(1, 2) +void rdt_last_cmd_printf(const char *fmt, ...); + +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); + +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); + +ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); + +int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); + +bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d, + unsigned long cbm, int closid, bool exclusive); + +unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d, + unsigned long cbm); + +enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); + +int rdtgroup_tasks_assigned(struct rdtgroup *r); + +int closids_supported(void); + +void closid_free(int closid); + +int setup_rmid_lru_list(void); + +void free_rmid_lru_list(void); + +int alloc_rmid(u32 closid); + +void free_rmid(u32 closid, u32 rmid); + +int resctrl_l3_mon_resource_init(void); + +void resctrl_l3_mon_resource_exit(void); + +void mon_event_count(void *info); + +int rdtgroup_mondata_show(struct seq_file *m, void *arg); + +void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, + struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp, + cpumask_t *cpumask, struct mon_evt *evt, int first); + +void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, + unsigned long delay_ms, + int exclude_cpu); + +void mbm_handle_overflow(struct work_struct *work); + +bool is_mba_sc(struct rdt_resource *r); + +void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, + int exclude_cpu); + +void cqm_handle_limbo(struct work_struct *work); + +bool has_busy_rmid(struct rdt_l3_mon_domain *d); + +void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free); + +void resctrl_file_fflags_init(const char *config, unsigned long fflags); + +void rdt_staged_configs_clear(void); + +bool closid_allocated(unsigned int closid); + +int resctrl_find_cleanest_closid(void); + +void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp); + +void rdtgroup_unassign_cntrs(struct rdtgroup *rdtgrp); + +#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK +int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); + +int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); + +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm); + +bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_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); + +#else +static inline int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) +{ + return -EOPNOTSUPP; +} + +static inline int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) +{ + return -EOPNOTSUPP; +} + +static inline bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm) +{ + return false; +} + +static inline bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d) +{ + return false; +} + +static inline int rdt_pseudo_lock_init(void) { return 0; } +static inline void rdt_pseudo_lock_release(void) { } +static inline int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) +{ + return -EOPNOTSUPP; +} + +static inline void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) { } +#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */ + +#endif /* _FS_RESCTRL_INTERNAL_H */ diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c new file mode 100644 index 0000000000000..78dbc8c069ea8 --- /dev/null +++ b/fs/resctrl/monitor.c @@ -0,0 +1,1290 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Resource Director Technology(RDT) + * - Monitoring code + * + * Copyright (C) 2017 Intel Corporation + * + * Author: + * Vikas Shivappa + * + * 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. + */ + +#define pr_fmt(fmt) "resctrl: " fmt + +#include +#include +#include +#include + +#include "internal.h" + +#define CREATE_TRACE_POINTS + +#include "monitor_trace.h" + +/** + * struct rmid_entry - dirty tracking for all RMID. + * @closid: The CLOSID for this entry. + * @rmid: The RMID for this entry. + * @busy: The number of domains with cached data using this RMID. + * @list: Member of the rmid_free_lru list when busy == 0. + * + * Depending on the architecture the correct monitor is accessed using + * both @closid and @rmid, or @rmid only. + * + * Take the rdtgroup_mutex when accessing. + */ +struct rmid_entry { + u32 closid; + 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); + +/* + * @closid_num_dirty_rmid The number of dirty RMID each CLOSID has. + * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined. + * Indexed by CLOSID. Protected by rdtgroup_mutex. + */ +static u32 *closid_num_dirty_rmid; + +/* + * @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 > resctrl_rmid_realloc_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; + +/* + * This is the threshold cache occupancy in bytes at which we will consider an + * RMID available for re-allocation. + */ +unsigned int resctrl_rmid_realloc_threshold; + +/* + * This is the maximum value for the reallocation threshold, in bytes. + */ +unsigned int resctrl_rmid_realloc_limit; + +/* + * x86 and arm64 differ in their handling of monitoring. + * x86's RMID are independent numbers, there is only one source of traffic + * with an RMID value of '1'. + * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of + * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID + * value is no longer unique. + * To account for this, resctrl uses an index. On x86 this is just the RMID, + * on arm64 it encodes the CLOSID and RMID. This gives a unique number. + * + * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code + * must accept an attempt to read every index. + */ +static inline struct rmid_entry *__rmid_entry(u32 idx) +{ + struct rmid_entry *entry; + u32 closid, rmid; + + entry = &rmid_ptrs[idx]; + resctrl_arch_rmid_idx_decode(idx, &closid, &rmid); + + WARN_ON_ONCE(entry->closid != closid); + WARN_ON_ONCE(entry->rmid != rmid); + + return entry; +} + +static void limbo_release_entry(struct rmid_entry *entry) +{ + lockdep_assert_held(&rdtgroup_mutex); + + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]--; +} + +/* + * 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_l3_mon_domain *d, bool force_free) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + struct rmid_entry *entry; + u32 idx, cur_idx = 1; + void *arch_mon_ctx; + void *arch_priv; + bool rmid_dirty; + u64 val = 0; + + arch_priv = mon_event_all[QOS_L3_OCCUP_EVENT_ID].arch_priv; + arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID); + if (IS_ERR(arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(arch_mon_ctx)); + return; + } + + /* + * 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 (;;) { + idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx); + if (idx >= idx_limit) + break; + + entry = __rmid_entry(idx); + if (resctrl_arch_rmid_read(r, &d->hdr, entry->closid, entry->rmid, + QOS_L3_OCCUP_EVENT_ID, arch_priv, &val, + arch_mon_ctx)) { + rmid_dirty = true; + } else { + rmid_dirty = (val >= resctrl_rmid_realloc_threshold); + + /* + * x86's CLOSID and RMID are independent numbers, so the entry's + * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the + * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't + * used to select the configuration. It is thus necessary to track both + * CLOSID and RMID because there may be dependencies between them + * on some architectures. + */ + trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val); + } + + if (force_free || !rmid_dirty) { + clear_bit(idx, d->rmid_busy_llc); + if (!--entry->busy) + limbo_release_entry(entry); + } + cur_idx = idx + 1; + } + + resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); +} + +bool has_busy_rmid(struct rdt_l3_mon_domain *d) +{ + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + + return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit; +} + +static struct rmid_entry *resctrl_find_free_rmid(u32 closid) +{ + struct rmid_entry *itr; + u32 itr_idx, cmp_idx; + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC); + + list_for_each_entry(itr, &rmid_free_lru, list) { + /* + * Get the index of this free RMID, and the index it would need + * to be if it were used with this CLOSID. + * If the CLOSID is irrelevant on this architecture, the two + * index values are always the same on every entry and thus the + * very first entry will be returned. + */ + itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid); + cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid); + + if (itr_idx == cmp_idx) + return itr; + } + + return ERR_PTR(-ENOSPC); +} + +/** + * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated + * RMID are clean, or the CLOSID that has + * the most clean RMID. + * + * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID + * may not be able to allocate clean RMID. To avoid this the allocator will + * choose the CLOSID with the most clean RMID. + * + * When the CLOSID and RMID are independent numbers, the first free CLOSID will + * be returned. + */ +int resctrl_find_cleanest_closid(void) +{ + u32 cleanest_closid = ~0; + int i = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + return -EIO; + + for (i = 0; i < closids_supported(); i++) { + int num_dirty; + + if (closid_allocated(i)) + continue; + + num_dirty = closid_num_dirty_rmid[i]; + if (num_dirty == 0) + return i; + + if (cleanest_closid == ~0) + cleanest_closid = i; + + if (num_dirty < closid_num_dirty_rmid[cleanest_closid]) + cleanest_closid = i; + } + + if (cleanest_closid == ~0) + return -ENOSPC; + + return cleanest_closid; +} + +/* + * For MPAM the RMID value is not unique, and has to be considered with + * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which + * allows all domains to be managed by a single free list. + * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler. + */ +int alloc_rmid(u32 closid) +{ + struct rmid_entry *entry; + + lockdep_assert_held(&rdtgroup_mutex); + + entry = resctrl_find_free_rmid(closid); + if (IS_ERR(entry)) + return PTR_ERR(entry); + + list_del(&entry->list); + return entry->rmid; +} + +static void add_rmid_to_limbo(struct rmid_entry *entry) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + struct rdt_l3_mon_domain *d; + u32 idx; + + lockdep_assert_held(&rdtgroup_mutex); + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); + + entry->busy = 0; + list_for_each_entry(d, &r->mon_domains, hdr.list) { + /* + * For the first limbo RMID in the domain, + * setup up the limbo worker. + */ + if (!has_busy_rmid(d)) + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL, + RESCTRL_PICK_ANY_CPU); + set_bit(idx, d->rmid_busy_llc); + entry->busy++; + } + + rmid_limbo_count++; + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]++; +} + +void free_rmid(u32 closid, u32 rmid) +{ + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + struct rmid_entry *entry; + + lockdep_assert_held(&rdtgroup_mutex); + + /* + * Do not allow the default rmid to be free'd. Comparing by index + * allows architectures that ignore the closid parameter to avoid an + * unnecessary check. + */ + if (!resctrl_arch_mon_capable() || + idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID)) + return; + + entry = __rmid_entry(idx); + + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) + add_rmid_to_limbo(entry); + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +static struct mbm_state *get_mbm_state(struct rdt_l3_mon_domain *d, u32 closid, + u32 rmid, enum resctrl_event_id evtid) +{ + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + struct mbm_state *state; + + if (!resctrl_is_mbm_event(evtid)) + return NULL; + + state = d->mbm_states[MBM_STATE_IDX(evtid)]; + + return state ? &state[idx] : NULL; +} + +/* + * mbm_cntr_get() - Return the counter ID for the matching @evtid and @rdtgrp. + * + * Return: + * Valid counter ID on success, or -ENOENT on failure. + */ +static int mbm_cntr_get(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + struct rdtgroup *rdtgrp, enum resctrl_event_id evtid) +{ + int cntr_id; + + if (!r->mon.mbm_cntr_assignable) + return -ENOENT; + + if (!resctrl_is_mbm_event(evtid)) + return -ENOENT; + + for (cntr_id = 0; cntr_id < r->mon.num_mbm_cntrs; cntr_id++) { + if (d->cntr_cfg[cntr_id].rdtgrp == rdtgrp && + d->cntr_cfg[cntr_id].evtid == evtid) + return cntr_id; + } + + return -ENOENT; +} + +/* + * mbm_cntr_alloc() - Initialize and return a new counter ID in the domain @d. + * Caller must ensure that the specified event is not assigned already. + * + * Return: + * Valid counter ID on success, or -ENOSPC on failure. + */ +static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + struct rdtgroup *rdtgrp, enum resctrl_event_id evtid) +{ + int cntr_id; + + for (cntr_id = 0; cntr_id < r->mon.num_mbm_cntrs; cntr_id++) { + if (!d->cntr_cfg[cntr_id].rdtgrp) { + d->cntr_cfg[cntr_id].rdtgrp = rdtgrp; + d->cntr_cfg[cntr_id].evtid = evtid; + return cntr_id; + } + } + + return -ENOSPC; +} + +/* + * mbm_cntr_free() - Clear the counter ID configuration details in the domain @d. + */ +static void mbm_cntr_free(struct rdt_l3_mon_domain *d, int cntr_id) +{ + memset(&d->cntr_cfg[cntr_id], 0, sizeof(*d->cntr_cfg)); +} + +static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) +{ + int cpu = smp_processor_id(); + u32 closid = rdtgrp->closid; + u32 rmid = rdtgrp->mon.rmid; + struct rdt_l3_mon_domain *d; + int cntr_id = -ENOENT; + struct mbm_state *m; + u64 tval = 0; + + if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) { + rr->err = -EIO; + return -EINVAL; + } + d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); + + if (rr->is_mbm_cntr) { + cntr_id = mbm_cntr_get(rr->r, d, rdtgrp, rr->evt->evtid); + if (cntr_id < 0) { + rr->err = -ENOENT; + return -EINVAL; + } + } + + if (rr->first) { + if (rr->is_mbm_cntr) + resctrl_arch_reset_cntr(rr->r, d, closid, rmid, cntr_id, rr->evt->evtid); + else + resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evt->evtid); + m = get_mbm_state(d, closid, rmid, rr->evt->evtid); + if (m) + memset(m, 0, sizeof(struct mbm_state)); + return 0; + } + + /* Reading a single domain, must be on a CPU in that domain. */ + if (!cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) + return -EINVAL; + if (rr->is_mbm_cntr) + rr->err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id, + rr->evt->evtid, &tval); + else + rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid, + rr->evt->evtid, rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); + if (rr->err) + return rr->err; + + rr->val += tval; + + return 0; +} + +static int __l3_mon_event_count_sum(struct rdtgroup *rdtgrp, struct rmid_read *rr) +{ + int cpu = smp_processor_id(); + u32 closid = rdtgrp->closid; + u32 rmid = rdtgrp->mon.rmid; + struct rdt_l3_mon_domain *d; + u64 tval = 0; + int err, ret; + + /* + * Summing across domains is only done for systems that implement + * Sub-NUMA Cluster. There is no overlap with systems that support + * assignable counters. + */ + if (rr->is_mbm_cntr) { + pr_warn_once("Summing domains using assignable counters is not supported\n"); + rr->err = -EINVAL; + return -EINVAL; + } + + /* Summing domains that share a cache, must be on a CPU for that cache. */ + if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map)) + return -EINVAL; + + /* + * Legacy files must report the sum of an event across all + * domains that share the same L3 cache instance. + * Report success if a read from any domain succeeds, -EINVAL + * (translated to "Unavailable" for user space) if reading from + * all domains fail for any reason. + */ + ret = -EINVAL; + list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { + if (d->ci_id != rr->ci->id) + continue; + err = resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid, + rr->evt->evtid, rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); + if (!err) { + rr->val += tval; + ret = 0; + } + } + + if (ret) + rr->err = ret; + + return ret; +} + +static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) +{ + switch (rr->r->rid) { + case RDT_RESOURCE_L3: + WARN_ON_ONCE(rr->evt->any_cpu); + if (rr->hdr) + return __l3_mon_event_count(rdtgrp, rr); + else + return __l3_mon_event_count_sum(rdtgrp, rr); + case RDT_RESOURCE_PERF_PKG: { + u64 tval = 0; + + rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, rdtgrp->closid, + rdtgrp->mon.rmid, rr->evt->evtid, + rr->evt->arch_priv, + &tval, rr->arch_mon_ctx); + if (rr->err) + return rr->err; + + rr->val += tval; + + return 0; + } + default: + rr->err = -EINVAL; + return -EINVAL; + } +} + +/* + * mbm_bw_count() - Update bw count from values previously read by + * __mon_event_count(). + * @rdtgrp: resctrl group associated with the CLOSID and RMID to identify + * the cached mbm_state. + * @rr: The struct rmid_read populated by __mon_event_count(). + * + * Supporting function to calculate the memory bandwidth + * and delta bandwidth in MBps. The chunks value previously read by + * __mon_event_count() is compared with the chunks value from the previous + * invocation. This must be called once per second to maintain values in MBps. + */ +static void mbm_bw_count(struct rdtgroup *rdtgrp, struct rmid_read *rr) +{ + u64 cur_bw, bytes, cur_bytes; + u32 closid = rdtgrp->closid; + u32 rmid = rdtgrp->mon.rmid; + struct rdt_l3_mon_domain *d; + struct mbm_state *m; + + if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr); + m = get_mbm_state(d, closid, rmid, rr->evt->evtid); + if (WARN_ON_ONCE(!m)) + return; + + cur_bytes = rr->val; + bytes = cur_bytes - m->prev_bw_bytes; + m->prev_bw_bytes = cur_bytes; + + cur_bw = bytes / SZ_1M; + + m->prev_bw = cur_bw; +} + +/* + * This is scheduled by mon_event_read() 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; + int ret; + + rdtgrp = rr->rgrp; + + ret = __mon_event_count(rdtgrp, 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, rr) == 0) + ret = 0; + } + } + + /* + * __mon_event_count() calls for newly created monitor groups may + * report -EINVAL/Unavailable if the monitor hasn't seen any traffic. + * Discard error if any of the monitor event reads succeeded. + */ + if (ret == 0) + rr->err = 0; +} + +static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, + struct rdt_resource *r) +{ + struct rdt_ctrl_domain *d; + + lockdep_assert_cpus_held(); + + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) + return d; + } + + return NULL; +} + +/* + * 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 bandwidth(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 unnecessarily 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_l3_mon_domain *dom_mbm) +{ + u32 closid, rmid, cur_msr_val, new_msr_val; + struct mbm_state *pmbm_data, *cmbm_data; + struct rdt_ctrl_domain *dom_mba; + enum resctrl_event_id evt_id; + struct rdt_resource *r_mba; + struct list_head *head; + struct rdtgroup *entry; + u32 cur_bw, user_bw; + + r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA); + evt_id = rgrp->mba_mbps_event; + + closid = rgrp->closid; + rmid = rgrp->mon.rmid; + pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id); + if (WARN_ON_ONCE(!pmbm_data)) + return; + + dom_mba = get_ctrl_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]; + + /* MBA resource doesn't support CDP */ + cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); + + /* + * 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 = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id); + if (WARN_ON_ONCE(!cmbm_data)) + return; + cur_bw += cmbm_data->prev_bw; + } + + /* + * Scale up/down the bandwidth linearly for the ctrl group. The + * bandwidth step is the bandwidth granularity specified by the + * hardware. + * Always increase throttling if current bandwidth is above the + * target set by user. + * But avoid thrashing up and down on every poll by checking + * whether a decrease in throttling is likely to push the group + * back over target. E.g. if currently throttling to 30% of bandwidth + * on a system with 10% granularity steps, check whether moving to + * 40% would go past the limit by multiplying current bandwidth by + * "(30 + 10) / 30". + */ + 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 * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { + new_msr_val = cur_msr_val + r_mba->membw.bw_gran; + } else { + return; + } + + resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); +} + +static void mbm_update_one_event(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + struct rdtgroup *rdtgrp, enum resctrl_event_id evtid) +{ + struct rmid_read rr = {0}; + + rr.r = r; + rr.hdr = &d->hdr; + rr.evt = &mon_event_all[evtid]; + if (resctrl_arch_mbm_cntr_assign_enabled(r)) { + rr.is_mbm_cntr = true; + } else { + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + } + + __mon_event_count(rdtgrp, &rr); + + /* + * If the software controller is enabled, compute the + * bandwidth for this event id. + */ + if (is_mba_sc(NULL)) + mbm_bw_count(rdtgrp, &rr); + + if (rr.arch_mon_ctx) + resctrl_arch_mon_ctx_free(rr.r, evtid, rr.arch_mon_ctx); +} + +static void mbm_update(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + struct rdtgroup *rdtgrp) +{ + /* + * This is protected from concurrent reads from user as both + * the user and overflow handler hold the global mutex. + */ + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) + mbm_update_one_event(r, d, rdtgrp, QOS_L3_MBM_TOTAL_EVENT_ID); + + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) + mbm_update_one_event(r, d, rdtgrp, QOS_L3_MBM_LOCAL_EVENT_ID); +} + +/* + * 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); + struct rdt_l3_mon_domain *d; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + d = container_of(work, struct rdt_l3_mon_domain, cqm_limbo.work); + + __check_limbo(d, false); + + if (has_busy_rmid(d)) { + d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask, + RESCTRL_PICK_ANY_CPU); + schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo, + delay); + } + + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); +} + +/** + * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this + * domain. + * @dom: The domain the limbo handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, + int exclude_cpu) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + int cpu; + + cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu); + dom->cqm_work_cpu = cpu; + + if (cpu < nr_cpu_ids) + 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; + struct rdt_l3_mon_domain *d; + struct list_head *head; + struct rdt_resource *r; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + /* + * If the filesystem has been unmounted this work no longer needs to + * run. + */ + if (!resctrl_mounted || !resctrl_arch_mon_capable()) + goto out_unlock; + + r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + d = container_of(work, struct rdt_l3_mon_domain, mbm_over.work); + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + mbm_update(r, d, prgrp); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) + mbm_update(r, d, crgrp); + + if (is_mba_sc(NULL)) + update_mba_bw(prgrp, d); + } + + /* + * Re-check for housekeeping CPUs. This allows the overflow handler to + * move off a nohz_full CPU quickly. + */ + d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask, + RESCTRL_PICK_ANY_CPU); + schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); +} + +/** + * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this + * domain. + * @dom: The domain the overflow handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms, + int exclude_cpu) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + int cpu; + + /* + * When a domain comes online there is no guarantee the filesystem is + * mounted. If not, there is no need to catch counter overflow. + */ + if (!resctrl_mounted || !resctrl_arch_mon_capable()) + return; + cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu); + dom->mbm_work_cpu = cpu; + + if (cpu < nr_cpu_ids) + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); +} + +int setup_rmid_lru_list(void) +{ + struct rmid_entry *entry = NULL; + u32 idx_limit; + u32 idx; + int i; + + if (!resctrl_arch_mon_capable()) + return 0; + + /* + * Called on every mount, but the number of RMIDs cannot change + * after the first mount, so keep using the same set of rmid_ptrs[] + * until resctrl_exit(). Note that the limbo handler continues to + * access rmid_ptrs[] after resctrl is unmounted. + */ + if (rmid_ptrs) + return 0; + + idx_limit = resctrl_arch_system_num_rmid_idx(); + rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); + if (!rmid_ptrs) + return -ENOMEM; + + for (i = 0; i < idx_limit; i++) { + entry = &rmid_ptrs[i]; + INIT_LIST_HEAD(&entry->list); + + resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid); + list_add_tail(&entry->list, &rmid_free_lru); + } + + /* + * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and + * are always allocated. These are used for the rdtgroup_default + * control group, which was setup earlier in rdtgroup_setup_default(). + */ + idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID); + entry = __rmid_entry(idx); + list_del(&entry->list); + + return 0; +} + +void free_rmid_lru_list(void) +{ + if (!resctrl_arch_mon_capable()) + return; + + mutex_lock(&rdtgroup_mutex); + kfree(rmid_ptrs); + rmid_ptrs = NULL; + mutex_unlock(&rdtgroup_mutex); +} + +#define MON_EVENT(_eventid, _name, _res, _fp) \ + [_eventid] = { \ + .name = _name, \ + .evtid = _eventid, \ + .rid = _res, \ + .is_floating_point = _fp, \ +} + +/* + * All available events. Architecture code marks the ones that + * are supported by a system using resctrl_enable_mon_event() + * to set .enabled. + */ +struct mon_evt mon_event_all[QOS_NUM_EVENTS] = { + MON_EVENT(QOS_L3_OCCUP_EVENT_ID, "llc_occupancy", RDT_RESOURCE_L3, false), + MON_EVENT(QOS_L3_MBM_TOTAL_EVENT_ID, "mbm_total_bytes", RDT_RESOURCE_L3, false), + MON_EVENT(QOS_L3_MBM_LOCAL_EVENT_ID, "mbm_local_bytes", RDT_RESOURCE_L3, false), + MON_EVENT(PMT_EVENT_ENERGY, "core_energy", RDT_RESOURCE_PERF_PKG, true), + MON_EVENT(PMT_EVENT_ACTIVITY, "activity", RDT_RESOURCE_PERF_PKG, true), + MON_EVENT(PMT_EVENT_STALLS_LLC_HIT, "stalls_llc_hit", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_C1_RES, "c1_res", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UNHALTED_CORE_CYCLES, "unhalted_core_cycles", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_STALLS_LLC_MISS, "stalls_llc_miss", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_AUTO_C6_RES, "c6_res", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UNHALTED_REF_CYCLES, "unhalted_ref_cycles", RDT_RESOURCE_PERF_PKG, false), + MON_EVENT(PMT_EVENT_UOPS_RETIRED, "uops_retired", RDT_RESOURCE_PERF_PKG, false), +}; + +bool resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, + unsigned int binary_bits, void *arch_priv) +{ + if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS || + binary_bits > MAX_BINARY_BITS)) + return false; + if (mon_event_all[eventid].enabled) { + pr_warn("Duplicate enable for event %d\n", eventid); + return false; + } + if (binary_bits && !mon_event_all[eventid].is_floating_point) { + pr_warn("Event %d may not be floating point\n", eventid); + return false; + } + + mon_event_all[eventid].any_cpu = any_cpu; + mon_event_all[eventid].binary_bits = binary_bits; + mon_event_all[eventid].arch_priv = arch_priv; + mon_event_all[eventid].enabled = true; + + return true; +} + +bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid) +{ + return eventid >= QOS_FIRST_EVENT && eventid < QOS_NUM_EVENTS && + mon_event_all[eventid].enabled; +} + +u32 resctrl_get_mon_evt_cfg(enum resctrl_event_id evtid) +{ + return mon_event_all[evtid].evt_cfg; +} + +/* + * rdtgroup_assign_cntr() - Assign/unassign the counter ID for the event, RMID + * pair in the domain. + * + * Assign the counter if @assign is true else unassign the counter. Reset the + * associated non-architectural state. + */ +static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + enum resctrl_event_id evtid, u32 rmid, u32 closid, + u32 cntr_id, bool assign) +{ + struct mbm_state *m; + + resctrl_arch_config_cntr(r, d, evtid, rmid, closid, cntr_id, assign); + + m = get_mbm_state(d, closid, rmid, evtid); + if (m) + memset(m, 0, sizeof(*m)); +} + +/* + * rdtgroup_alloc_assign_cntr() - Allocate a counter ID and assign it to the event + * pointed to by @mevt and the resctrl group @rdtgrp within the domain @d. + * + * Return: + * 0 on success, < 0 on failure. + */ +static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + struct rdtgroup *rdtgrp, struct mon_evt *mevt) +{ + int cntr_id; + + /* No action required if the counter is assigned already. */ + cntr_id = mbm_cntr_get(r, d, rdtgrp, mevt->evtid); + if (cntr_id >= 0) + return 0; + + cntr_id = mbm_cntr_alloc(r, d, rdtgrp, mevt->evtid); + if (cntr_id < 0) { + rdt_last_cmd_printf("Failed to allocate counter for %s in domain %d\n", + mevt->name, d->hdr.id); + return cntr_id; + } + + rdtgroup_assign_cntr(r, d, mevt->evtid, rdtgrp->mon.rmid, rdtgrp->closid, cntr_id, true); + + return 0; +} + +/* + * rdtgroup_assign_cntr_event() - Assign a hardware counter for the event in + * @mevt to the resctrl group @rdtgrp. Assign counters to all domains if @d is + * NULL; otherwise, assign the counter to the specified domain @d. + * + * If all counters in a domain are already in use, rdtgroup_alloc_assign_cntr() + * will fail. The assignment process will abort at the first failure encountered + * during domain traversal, which may result in the event being only partially + * assigned. + * + * Return: + * 0 on success, < 0 on failure. + */ +static int rdtgroup_assign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, + struct mon_evt *mevt) +{ + struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid); + int ret = 0; + + if (!d) { + list_for_each_entry(d, &r->mon_domains, hdr.list) { + ret = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt); + if (ret) + return ret; + } + } else { + ret = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt); + } + + return ret; +} + +/* + * rdtgroup_assign_cntrs() - Assign counters to MBM events. Called when + * a new group is created. + * + * Each group can accommodate two counters per domain: one for the total + * event and one for the local event. Assignments may fail due to the limited + * number of counters. However, it is not necessary to fail the group creation + * and thus no failure is returned. Users have the option to modify the + * counter assignments after the group has been created. + */ +void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + + if (!r->mon_capable || !resctrl_arch_mbm_cntr_assign_enabled(r)) + return; + + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) + rdtgroup_assign_cntr_event(NULL, rdtgrp, + &mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID]); + + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) + rdtgroup_assign_cntr_event(NULL, rdtgrp, + &mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID]); +} + +/* + * rdtgroup_free_unassign_cntr() - Unassign and reset the counter ID configuration + * for the event pointed to by @mevt within the domain @d and resctrl group @rdtgrp. + */ +static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + struct rdtgroup *rdtgrp, struct mon_evt *mevt) +{ + int cntr_id; + + cntr_id = mbm_cntr_get(r, d, rdtgrp, mevt->evtid); + + /* If there is no cntr_id assigned, nothing to do */ + if (cntr_id < 0) + return; + + rdtgroup_assign_cntr(r, d, mevt->evtid, rdtgrp->mon.rmid, rdtgrp->closid, cntr_id, false); + + mbm_cntr_free(d, cntr_id); +} + +/* + * rdtgroup_unassign_cntr_event() - Unassign a hardware counter associated with + * the event structure @mevt from the domain @d and the group @rdtgrp. Unassign + * the counters from all the domains if @d is NULL else unassign from @d. + */ +static void rdtgroup_unassign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp, + struct mon_evt *mevt) +{ + struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid); + + if (!d) { + list_for_each_entry(d, &r->mon_domains, hdr.list) + rdtgroup_free_unassign_cntr(r, d, rdtgrp, mevt); + } else { + rdtgroup_free_unassign_cntr(r, d, rdtgrp, mevt); + } +} + +/* + * rdtgroup_unassign_cntrs() - Unassign the counters associated with MBM events. + * Called when a group is deleted. + */ +void rdtgroup_unassign_cntrs(struct rdtgroup *rdtgrp) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + + if (!r->mon_capable || !resctrl_arch_mbm_cntr_assign_enabled(r)) + return; + + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) + rdtgroup_unassign_cntr_event(NULL, rdtgrp, + &mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID]); + + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) + rdtgroup_unassign_cntr_event(NULL, rdtgrp, + &mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID]); +} + +static int closid_num_dirty_rmid_alloc(struct rdt_resource *r) +{ + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + u32 num_closid = resctrl_arch_get_num_closid(r); + u32 *tmp; + + /* For ARM memory ordering access to closid_num_dirty_rmid */ + mutex_lock(&rdtgroup_mutex); + + /* + * If the architecture hasn't provided a sanitised value here, + * this may result in larger arrays than necessary. Resctrl will + * use a smaller system wide value based on the resources in + * use. + */ + tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); + if (!tmp) { + mutex_unlock(&rdtgroup_mutex); + return -ENOMEM; + } + + closid_num_dirty_rmid = tmp; + + mutex_unlock(&rdtgroup_mutex); + } + + return 0; +} + +static void closid_num_dirty_rmid_free(void) +{ + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + mutex_lock(&rdtgroup_mutex); + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + mutex_unlock(&rdtgroup_mutex); + } +} + +/** + * resctrl_l3_mon_resource_init() - Initialise global monitoring structures. + * + * Allocate and initialise global monitor resources that do not belong to a + * specific domain. i.e. the closid_num_dirty_rmid[] used to find the CLOSID + * with the cleanest set of RMIDs. + * Called once during boot after the struct rdt_resource's have been configured + * but before the filesystem is mounted. + * Resctrl's cpuhp callbacks may be called before this point to bring a domain + * online. + * + * Return: 0 for success, or -ENOMEM. + */ +int resctrl_l3_mon_resource_init(void) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + int ret; + + if (!r->mon_capable) + return 0; + + ret = closid_num_dirty_rmid_alloc(r); + if (ret) + return ret; + + if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) { + mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable = true; + resctrl_file_fflags_init("mbm_total_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); + } + if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) { + mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].configurable = true; + resctrl_file_fflags_init("mbm_local_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); + } + + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) + mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID; + else if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) + mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID; + + if (r->mon.mbm_cntr_assignable) { + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) + mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask; + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) + mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask & + (READS_TO_LOCAL_MEM | + READS_TO_LOCAL_S_MEM | + NON_TEMP_WRITE_TO_LOCAL_MEM); + } + + return 0; +} + +void resctrl_l3_mon_resource_exit(void) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + + if (!r->mon_capable) + return; + + closid_num_dirty_rmid_free(); +} diff --git a/fs/resctrl/monitor_trace.h b/fs/resctrl/monitor_trace.h new file mode 100644 index 0000000000000..fdf49f22576a9 --- /dev/null +++ b/fs/resctrl/monitor_trace.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM resctrl + +#if !defined(_FS_RESCTRL_MONITOR_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _FS_RESCTRL_MONITOR_TRACE_H + +#include + +TRACE_EVENT(mon_llc_occupancy_limbo, + TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes), + TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes), + TP_STRUCT__entry(__field(u32, ctrl_hw_id) + __field(u32, mon_hw_id) + __field(int, domain_id) + __field(u64, llc_occupancy_bytes)), + TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id; + __entry->mon_hw_id = mon_hw_id; + __entry->domain_id = domain_id; + __entry->llc_occupancy_bytes = llc_occupancy_bytes;), + TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu", + __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id, + __entry->llc_occupancy_bytes) + ); + +#endif /* _FS_RESCTRL_MONITOR_TRACE_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . + +#define TRACE_INCLUDE_FILE monitor_trace + +#include diff --git a/fs/resctrl/pseudo_lock.c b/fs/resctrl/pseudo_lock.c new file mode 100644 index 0000000000000..6a358fc7124d9 --- /dev/null +++ b/fs/resctrl/pseudo_lock.c @@ -0,0 +1,1102 @@ +// 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 + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +/* + * 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 char *pseudo_lock_devnode(const struct device *dev, umode_t *mode) +{ + const struct rdtgroup *rdtgrp; + + rdtgrp = dev_get_drvdata(dev); + if (mode) + *mode = 0600; + guard(mutex)(&rdtgroup_mutex); + return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn)); +} + +static const struct class pseudo_lock_class = { + .name = "pseudo_lock", + .devnode = pseudo_lock_devnode, +}; + +/** + * 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; +} + +/** + * struct 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 + * @plr: Pseudo-locked region + * + * 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. + * + * Return: 0 on success, <0 on failure + */ +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->hdr.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->s = 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) +{ + enum resctrl_scope scope = plr->s->res->ctrl_scope; + struct cacheinfo *ci; + int ret; + + if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE)) + return -ENODEV; + + /* Pick the first cpu we find that is associated with the cache. */ + plr->cpu = cpumask_first(&plr->d->hdr.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_level(plr->cpu, scope); + if (ci) { + plr->line_size = ci->coherency_line_size; + plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm); + 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; +} + +/** + * rdtgroup_monitor_in_progress - Test if monitoring in progress + * @rdtgrp: 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 (resctrl_arch_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 (resctrl_arch_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 (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) || + resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) { + 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. + */ + if (resctrl_arch_get_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->closid, 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 (resctrl_arch_mon_capable()) { + ret = alloc_rmid(rdtgrp->closid); + 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->closid, 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_ctrl_domain *d, unsigned long cbm) +{ + unsigned int cbm_len; + unsigned long cbm_b; + + if (d->plr) { + cbm_len = d->plr->s->res->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_ctrl_domain *d) +{ + struct rdt_ctrl_domain *d_i; + cpumask_var_t cpu_with_psl; + struct rdt_resource *r; + bool ret = false; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + 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_capable_rdt_resource(r) { + list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) { + if (d_i->plr) + cpumask_or(cpu_with_psl, cpu_with_psl, + &d_i->hdr.cpu_mask); + } + } + + /* + * Next test if new pseudo-locked region would intersect with + * existing region. + */ + if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl)) + ret = true; + + free_cpumask_var(cpu_with_psl); + return ret; +} + +/** + * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region + * @rdtgrp: Resource group to which the pseudo-locked region belongs. + * @sel: Selector of which measurement to perform on a 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->hdr.cpu_mask); + if (!cpu_online(cpu)) { + ret = -ENODEV; + goto out; + } + + plr->cpu = cpu; + + if (sel == 1) + thread = kthread_run_on_cpu(resctrl_arch_measure_cycles_lat_fn, + plr, cpu, "pseudo_lock_measure/%u"); + else if (sel == 2) + thread = kthread_run_on_cpu(resctrl_arch_measure_l2_residency, + plr, cpu, "pseudo_lock_measure/%u"); + else if (sel == 3) + thread = kthread_run_on_cpu(resctrl_arch_measure_l3_residency, + plr, cpu, "pseudo_lock_measure/%u"); + else + goto out; + + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + goto out; + } + + 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 = pseudo_lock_measure_cycles(rdtgrp, sel); + if (ret == 0) + ret = count; + } + + 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; + char *kn_name __free(kfree) = NULL; + 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; + } + kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL); + if (!kn_name) { + ret = -ENOMEM; + goto out_cstates; + } + + plr->thread_done = 0; + + thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, plr, + plr->cpu, "pseudo_lock/%u"); + if (IS_ERR(thread)) { + ret = PTR_ERR(thread); + rdt_last_cmd_printf("Locking thread returned error %d\n", ret); + goto out_cstates; + } + + 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 dereference + * 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(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", 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 asymmetry 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->hdr.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, +}; + +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; + + ret = class_register(&pseudo_lock_class); + if (ret) { + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + return ret; + } + + return 0; +} + +void rdt_pseudo_lock_release(void) +{ + class_unregister(&pseudo_lock_class); + unregister_chrdev(pseudo_lock_major, "pseudo_lock"); + pseudo_lock_major = 0; +} diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c new file mode 100644 index 0000000000000..fd6877eb58171 --- /dev/null +++ b/fs/resctrl/rdtgroup.c @@ -0,0 +1,4445 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * User interface for Resource Allocation in Resource Director Technology(RDT) + * + * Copyright (C) 2016 Intel Corporation + * + * Author: Fenghua Yu + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" + +/* Mutex to protect rdtgroup access. */ +DEFINE_MUTEX(rdtgroup_mutex); + +static struct kernfs_root *rdt_root; + +struct rdtgroup rdtgroup_default; + +LIST_HEAD(rdt_all_groups); + +/* list of entries for the schemata file */ +LIST_HEAD(resctrl_schema_all); + +/* + * List of struct mon_data containing private data of event files for use by + * rdtgroup_mondata_show(). Protected by rdtgroup_mutex. + */ +static LIST_HEAD(mon_data_kn_priv_list); + +/* The filesystem can only be mounted once. */ +bool resctrl_mounted; + +/* 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; + +/* + * Used to store the max resource name width to display the schemata names in + * a tabular format. + */ +int max_name_width; + +static struct seq_buf last_cmd_status; + +static char last_cmd_status_buf[512]; + +static int rdtgroup_setup_root(struct rdt_fs_context *ctx); + +static void rdtgroup_destroy_root(void); + +struct dentry *debugfs_resctrl; + +/* + * Memory bandwidth monitoring event to use for the default CTRL_MON group + * and each new CTRL_MON group created by the user. Only relevant when + * the filesystem is mounted with the "mba_MBps" option so it does not + * matter that it remains uninitialized on systems that do not support + * the "mba_MBps" option. + */ +enum resctrl_event_id mba_mbps_default_event; + +static bool resctrl_debug; + +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); +} + +void rdt_staged_configs_clear(void) +{ + struct rdt_ctrl_domain *dom; + struct rdt_resource *r; + + lockdep_assert_held(&rdtgroup_mutex); + + for_each_alloc_capable_rdt_resource(r) { + list_for_each_entry(dom, &r->ctrl_domains, hdr.list) + memset(dom->staged_config, 0, sizeof(dom->staged_config)); + } +} + +static bool resctrl_is_mbm_enabled(void) +{ + return (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID) || + resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)); +} + +/* + * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap + * of free CLOSIDs. + * + * Using a global CLOSID across all resources has some advantages and + * some drawbacks: + * + We can simply set current's 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 unsigned long *closid_free_map; + +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} + +static int closid_init(void) +{ + struct resctrl_schema *s; + u32 rdt_min_closid = ~0; + + /* Monitor only platforms still call closid_init() */ + if (list_empty(&resctrl_schema_all)) + return 0; + + /* Compute rdt_min_closid across all resources */ + list_for_each_entry(s, &resctrl_schema_all, list) + rdt_min_closid = min(rdt_min_closid, s->num_closid); + + closid_free_map = bitmap_alloc(rdt_min_closid, GFP_KERNEL); + if (!closid_free_map) + return -ENOMEM; + bitmap_fill(closid_free_map, rdt_min_closid); + + /* RESCTRL_RESERVED_CLOSID is always reserved for the default group */ + __clear_bit(RESCTRL_RESERVED_CLOSID, closid_free_map); + closid_free_map_len = rdt_min_closid; + + return 0; +} + +static void closid_exit(void) +{ + bitmap_free(closid_free_map); + closid_free_map = NULL; +} + +static int closid_alloc(void) +{ + int cleanest_closid; + u32 closid; + + lockdep_assert_held(&rdtgroup_mutex); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) && + resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) { + cleanest_closid = resctrl_find_cleanest_closid(); + if (cleanest_closid < 0) + return cleanest_closid; + closid = cleanest_closid; + } else { + closid = find_first_bit(closid_free_map, closid_free_map_len); + if (closid == closid_free_map_len) + return -ENOSPC; + } + __clear_bit(closid, closid_free_map); + + return closid; +} + +void closid_free(int closid) +{ + lockdep_assert_held(&rdtgroup_mutex); + + __set_bit(closid, closid_free_map); +} + +/** + * 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 + */ +bool closid_allocated(unsigned int closid) +{ + lockdep_assert_held(&rdtgroup_mutex); + + return !test_bit(closid, closid_free_map); +} + +/** + * 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 const struct kernfs_ops rdtgroup_kf_single_ops = { + .atomic_write_len = PAGE_SIZE, + .write = rdtgroup_file_write, + .seq_show = rdtgroup_seqfile_show, +}; + +static const 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->hdr.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; +} + +/* + * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, + * + * Per task closids/rmids must have been set up before calling this function. + * @r may be NULL. + */ +static void +update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r) +{ + struct resctrl_cpu_defaults defaults, *p = NULL; + + if (r) { + defaults.closid = r->closid; + defaults.rmid = r->mon.rmid; + p = &defaults; + } + + on_each_cpu_mask(cpu_mask, resctrl_arch_sync_cpu_closid_rmid, p, 1); +} + +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_empty(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_empty(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_empty(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_empty(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_empty(tmpmask)) { + list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { + if (r == rdtgrp) + continue; + cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); + if (!cpumask_empty(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; + } + + 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; + } + + 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_empty(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_arch_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 bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp) +{ + u32 closid, rmid = rdtgrp->mon.rmid; + + if (rdtgrp->type == RDTCTRL_GROUP) + closid = rdtgrp->closid; + else if (rdtgrp->type == RDTMON_GROUP) + closid = rdtgrp->mon.parent->closid; + else + return false; + + return resctrl_arch_match_closid(tsk, closid) && + resctrl_arch_match_rmid(tsk, closid, rmid); +} + +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 (task_in_rdtgroup(tsk, rdtgrp)) + 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 == RDTMON_GROUP && + !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; + } + + if (rdtgrp->type == RDTMON_GROUP) + resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid, + rdtgrp->mon.rmid); + else + resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid, + rdtgrp->mon.rmid); + + /* + * 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_arch_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 (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) && + resctrl_arch_match_closid(t, r->closid)); +} + +static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) && + resctrl_arch_match_rmid(t, r->mon.parent->closid, + 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; + char *pid_str; + int ret = 0; + pid_t pid; + + 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; + } + + while (buf && buf[0] != '\0' && buf[0] != '\n') { + pid_str = strim(strsep(&buf, ",")); + + if (kstrtoint(pid_str, 0, &pid)) { + rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str); + ret = -EINVAL; + break; + } + + if (pid < 0) { + rdt_last_cmd_printf("Invalid pid %d\n", pid); + ret = -EINVAL; + break; + } + + ret = rdtgroup_move_task(pid, rdtgrp, of); + if (ret) { + rdt_last_cmd_printf("Error while processing task %d\n", pid); + break; + } + } + +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; +} + +static int rdtgroup_closid_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) + seq_printf(s, "%u\n", rdtgrp->closid); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +static int rdtgroup_rmid_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) + seq_printf(s, "%u\n", rdtgrp->mon.rmid); + 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 (!resctrl_mounted) { + 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 (!resctrl_arch_match_closid(tsk, rdtg->closid)) + continue; + + seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", + rdt_kn_name(rdtg->kn)); + seq_puts(s, "mon:"); + list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, + mon.crdtgrp_list) { + if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid, + crg->mon.rmid)) + continue; + seq_printf(s, "%s", rdt_kn_name(crg->kn)); + 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 void *rdt_kn_parent_priv(struct kernfs_node *kn) +{ + /* + * The parent pointer is only valid within RCU section since it can be + * replaced. + */ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + +static int rdt_num_closids_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + + seq_printf(seq, "%u\n", s->num_closid); + return 0; +} + +static int rdt_default_ctrl_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r)); + return 0; +} + +static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + 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 resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + 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 resctrl_schema *s = rdt_kn_parent_priv(of->kn); + /* + * 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_resource *r = s->res; + struct rdt_ctrl_domain *dom; + int i, hwb, swb, excl, psl; + enum rdtgrp_mode mode; + bool sep = false; + u32 ctrl_val; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + hw_shareable = r->cache.shareable_bits; + list_for_each_entry(dom, &r->ctrl_domains, hdr.list) { + if (sep) + seq_putc(seq, ';'); + sw_shareable = 0; + exclusive = 0; + seq_printf(seq, "%d=", dom->hdr.id); + for (i = 0; i < closids_supported(); i++) { + if (!closid_allocated(i)) + continue; + ctrl_val = resctrl_arch_get_config(r, dom, i, + s->conf_type); + mode = rdtgroup_mode_by_closid(i); + switch (mode) { + case RDT_MODE_SHAREABLE: + sw_shareable |= ctrl_val; + break; + case RDT_MODE_EXCLUSIVE: + exclusive |= ctrl_val; + 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); + cpus_read_unlock(); + return 0; +} + +static int rdt_min_bw_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + 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 = rdt_kn_parent_priv(of->kn); + + seq_printf(seq, "%u\n", r->mon.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 = rdt_kn_parent_priv(of->kn); + struct mon_evt *mevt; + + for_each_mon_event(mevt) { + if (mevt->rid != r->rid || !mevt->enabled) + continue; + seq_printf(seq, "%s\n", mevt->name); + if (mevt->configurable) + seq_printf(seq, "%s_config\n", mevt->name); + } + + return 0; +} + +static int rdt_bw_gran_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + 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 resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + 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) +{ + seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold); + + return 0; +} + +static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + switch (r->membw.throttle_mode) { + case THREAD_THROTTLE_PER_THREAD: + seq_puts(seq, "per-thread\n"); + return 0; + case THREAD_THROTTLE_MAX: + seq_puts(seq, "max\n"); + return 0; + case THREAD_THROTTLE_UNDEFINED: + seq_puts(seq, "undefined\n"); + return 0; + } + + WARN_ON_ONCE(1); + + return 0; +} + +static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + unsigned int bytes; + int ret; + + ret = kstrtouint(buf, 0, &bytes); + if (ret) + return ret; + + if (bytes > resctrl_rmid_realloc_limit) + return -EINVAL; + + resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes); + + 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; +} + +static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) +{ + switch (my_type) { + case CDP_CODE: + return CDP_DATA; + case CDP_DATA: + return CDP_CODE; + default: + case CDP_NONE: + return CDP_NONE; + } +} + +static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + + seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks); + + return 0; +} + +/** + * __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. + * @type: CDP type of @r. + * @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_ctrl_domain *d, + unsigned long cbm, int closid, + enum resctrl_conf_type type, bool exclusive) +{ + enum rdtgrp_mode mode; + unsigned long ctrl_b; + 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 */ + for (i = 0; i < closids_supported(); i++) { + ctrl_b = resctrl_arch_get_config(r, d, i, type); + 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 + * @s: Schema for the 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 resctrl_schema *s, struct rdt_ctrl_domain *d, + unsigned long cbm, int closid, bool exclusive) +{ + enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); + struct rdt_resource *r = s->res; + + if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type, + exclusive)) + return true; + + if (!resctrl_arch_get_cdp_enabled(r->rid)) + return false; + return __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive); +} + +/** + * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * @rdtgrp: Resource group identified through its closid. + * + * 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_ctrl_domain *d; + struct resctrl_schema *s; + struct rdt_resource *r; + bool has_cache = false; + u32 ctrl; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; + if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA) + continue; + has_cache = true; + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + ctrl = resctrl_arch_get_config(r, d, closid, + s->conf_type); + if (rdtgroup_cbm_overlaps(s, d, ctrl, 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 (IS_ENABLED(CONFIG_RESCTRL_FS_PSEUDO_LOCK) && + !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_ctrl_domain *d, unsigned long cbm) +{ + unsigned int size = 0; + struct cacheinfo *ci; + int num_b; + + if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE)) + return size; + + num_b = bitmap_weight(&cbm, r->cache.cbm_len); + ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope); + if (ci) + size = ci->size / r->cache.cbm_len * num_b; + + return size; +} + +bool is_mba_sc(struct rdt_resource *r) +{ + if (!r) + r = resctrl_arch_get_resource(RDT_RESOURCE_MBA); + + /* + * The software controller support is only applicable to MBA resource. + * Make sure to check for resource type. + */ + if (r->rid != RDT_RESOURCE_MBA) + return false; + + return r->membw.mba_sc; +} + +/* + * 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 resctrl_schema *schema; + enum resctrl_conf_type type; + struct rdt_ctrl_domain *d; + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + unsigned int size; + int ret = 0; + u32 closid; + 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->s->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size); + } + goto out; + } + + closid = rdtgrp->closid; + + list_for_each_entry(schema, &resctrl_schema_all, list) { + r = schema->res; + type = schema->conf_type; + sep = false; + seq_printf(s, "%*s:", max_name_width, schema->name); + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + if (sep) + seq_putc(s, ';'); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { + size = 0; + } else { + if (is_mba_sc(r)) + ctrl = d->mbps_val[closid]; + else + ctrl = resctrl_arch_get_config(r, d, + closid, + type); + if (r->rid == RDT_RESOURCE_MBA || + r->rid == RDT_RESOURCE_SMBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); + } + seq_printf(s, "%d=%u", d->hdr.id, size); + sep = true; + } + seq_putc(s, '\n'); + } + +out: + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +static void mondata_config_read(struct resctrl_mon_config_info *mon_info) +{ + smp_call_function_any(&mon_info->d->hdr.cpu_mask, + resctrl_arch_mon_event_config_read, mon_info, 1); +} + +static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid) +{ + struct resctrl_mon_config_info mon_info; + struct rdt_l3_mon_domain *dom; + bool sep = false; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + list_for_each_entry(dom, &r->mon_domains, hdr.list) { + if (sep) + seq_puts(s, ";"); + + memset(&mon_info, 0, sizeof(struct resctrl_mon_config_info)); + mon_info.r = r; + mon_info.d = dom; + mon_info.evtid = evtid; + mondata_config_read(&mon_info); + + seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config); + sep = true; + } + seq_puts(s, "\n"); + + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + + return 0; +} + +static int mbm_total_bytes_config_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); + + mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID); + + return 0; +} + +static int mbm_local_bytes_config_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); + + mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID); + + return 0; +} + +static void mbm_config_write_domain(struct rdt_resource *r, + struct rdt_l3_mon_domain *d, u32 evtid, u32 val) +{ + struct resctrl_mon_config_info mon_info = {0}; + + /* + * Read the current config value first. If both are the same then + * no need to write it again. + */ + mon_info.r = r; + mon_info.d = d; + mon_info.evtid = evtid; + mondata_config_read(&mon_info); + if (mon_info.mon_config == val) + return; + + mon_info.mon_config = val; + + /* + * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the + * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE + * are scoped at the domain level. Writing any of these MSRs + * on one CPU is observed by all the CPUs in the domain. + */ + smp_call_function_any(&d->hdr.cpu_mask, resctrl_arch_mon_event_config_write, + &mon_info, 1); + + /* + * When an Event Configuration is changed, the bandwidth counters + * for all RMIDs and Events will be cleared by the hardware. The + * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for + * every RMID on the next read to any event for every RMID. + * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62) + * cleared while it is tracked by the hardware. Clear the + * mbm_local and mbm_total counts for all the RMIDs. + */ + resctrl_arch_reset_rmid_all(r, d); +} + +static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) +{ + char *dom_str = NULL, *id_str; + struct rdt_l3_mon_domain *d; + unsigned long dom_id, val; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + +next: + if (!tok || tok[0] == '\0') + return 0; + + /* Start processing the strings for each domain */ + dom_str = strim(strsep(&tok, ";")); + id_str = strsep(&dom_str, "="); + + if (!id_str || kstrtoul(id_str, 10, &dom_id)) { + rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n"); + return -EINVAL; + } + + if (!dom_str || kstrtoul(dom_str, 16, &val)) { + rdt_last_cmd_puts("Non-numeric event configuration value\n"); + return -EINVAL; + } + + /* Value from user cannot be more than the supported set of events */ + if ((val & r->mon.mbm_cfg_mask) != val) { + rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", + r->mon.mbm_cfg_mask); + return -EINVAL; + } + + list_for_each_entry(d, &r->mon_domains, hdr.list) { + if (d->hdr.id == dom_id) { + mbm_config_write_domain(r, d, evtid, val); + goto next; + } + } + + return -EINVAL; +} + +static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); + int ret; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + buf[nbytes - 1] = '\0'; + + ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID); + + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + + return ret ?: nbytes; +} + +static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + struct rdt_resource *r = rdt_kn_parent_priv(of->kn); + int ret; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + buf[nbytes - 1] = '\0'; + + ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID); + + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + + return ret ?: nbytes; +} + +/* 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 = RFTYPE_TOP_INFO, + }, + { + .name = "num_closids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_closids_show, + .fflags = RFTYPE_CTRL_INFO, + }, + { + .name = "mon_features", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_mon_features_show, + .fflags = RFTYPE_MON_INFO, + }, + { + .name = "num_rmids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_rmids_show, + .fflags = RFTYPE_MON_INFO, + }, + { + .name = "cbm_mask", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_default_ctrl_show, + .fflags = RFTYPE_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 = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "shareable_bits", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_shareable_bits_show, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "bit_usage", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bit_usage_show, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "min_bandwidth", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_min_bw_show, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, + }, + { + .name = "bandwidth_gran", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_bw_gran_show, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, + }, + { + .name = "delay_linear", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_delay_linear_show, + .fflags = RFTYPE_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 = RFTYPE_MON_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "mbm_total_bytes_config", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = mbm_total_bytes_config_show, + .write = mbm_total_bytes_config_write, + }, + { + .name = "mbm_local_bytes_config", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = mbm_local_bytes_config_show, + .write = mbm_local_bytes_config_write, + }, + { + .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 = "mon_hw_id", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_rmid_show, + .fflags = RFTYPE_MON_BASE | RFTYPE_DEBUG, + }, + { + .name = "schemata", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_schemata_write, + .seq_show = rdtgroup_schemata_show, + .fflags = RFTYPE_CTRL_BASE, + }, + { + .name = "mba_MBps_event", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mba_mbps_event_write, + .seq_show = rdtgroup_mba_mbps_event_show, + }, + { + .name = "mode", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mode_write, + .seq_show = rdtgroup_mode_show, + .fflags = RFTYPE_CTRL_BASE, + }, + { + .name = "size", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_size_show, + .fflags = RFTYPE_CTRL_BASE, + }, + { + .name = "sparse_masks", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_has_sparse_bitmasks_show, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "ctrl_hw_id", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_closid_show, + .fflags = RFTYPE_CTRL_BASE | RFTYPE_DEBUG, + }, +}; + +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); + + if (resctrl_debug) + fflags |= RFTYPE_DEBUG; + + 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; +} + +static void thread_throttle_mode_init(void) +{ + enum membw_throttle_mode throttle_mode = THREAD_THROTTLE_UNDEFINED; + struct rdt_resource *r_mba, *r_smba; + + r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA); + if (r_mba->alloc_capable && + r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED) + throttle_mode = r_mba->membw.throttle_mode; + + r_smba = resctrl_arch_get_resource(RDT_RESOURCE_SMBA); + if (r_smba->alloc_capable && + r_smba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED) + throttle_mode = r_smba->membw.throttle_mode; + + if (throttle_mode == THREAD_THROTTLE_UNDEFINED) + return; + + resctrl_file_fflags_init("thread_throttle_mode", + RFTYPE_CTRL_INFO | RFTYPE_RES_MB); +} + +void resctrl_file_fflags_init(const char *config, unsigned long fflags) +{ + struct rftype *rft; + + rft = rdtgroup_get_rftype_by_name(config); + if (rft) + rft->fflags = fflags; +} + +/** + * 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(void *priv, char *name, + unsigned long fflags) +{ + struct kernfs_node *kn_subdir; + int ret; + + kn_subdir = kernfs_create_dir(kn_info, name, + kn_info->mode, priv); + 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 unsigned long fflags_from_resource(struct rdt_resource *r) +{ + switch (r->rid) { + case RDT_RESOURCE_L3: + case RDT_RESOURCE_L2: + return RFTYPE_RES_CACHE; + case RDT_RESOURCE_MBA: + case RDT_RESOURCE_SMBA: + return RFTYPE_RES_MB; + case RDT_RESOURCE_PERF_PKG: + return RFTYPE_RES_PERF_PKG; + } + + return WARN_ON_ONCE(1); +} + +static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) +{ + struct resctrl_schema *s; + 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, RFTYPE_TOP_INFO); + if (ret) + goto out_destroy; + + /* loop over enabled controls, these are all alloc_capable */ + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; + fflags = fflags_from_resource(r) | RFTYPE_CTRL_INFO; + ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags); + if (ret) + goto out_destroy; + } + + for_each_mon_capable_rdt_resource(r) { + fflags = fflags_from_resource(r) | RFTYPE_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 inline bool is_mba_linear(void) +{ + return resctrl_arch_get_resource(RDT_RESOURCE_MBA)->membw.delay_linear; +} + +static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d) +{ + u32 num_closid = resctrl_arch_get_num_closid(r); + int cpu = cpumask_any(&d->hdr.cpu_mask); + int i; + + d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val), + GFP_KERNEL, cpu_to_node(cpu)); + if (!d->mbps_val) + return -ENOMEM; + + for (i = 0; i < num_closid; i++) + d->mbps_val[i] = MBA_MAX_MBPS; + + return 0; +} + +static void mba_sc_domain_destroy(struct rdt_resource *r, + struct rdt_ctrl_domain *d) +{ + kfree(d->mbps_val); + d->mbps_val = NULL; +} + +/* + * MBA software controller is supported only if + * MBM is supported and MBA is in linear scale, + * and the MBM monitor scope is the same as MBA + * control scope. + */ +static bool supports_mba_mbps(void) +{ + struct rdt_resource *rmbm = resctrl_arch_get_resource(RDT_RESOURCE_L3); + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA); + + return (resctrl_is_mbm_enabled() && + r->alloc_capable && is_mba_linear() && + r->ctrl_scope == rmbm->mon_scope); +} + +/* + * Enable or disable the MBA software controller + * which helps user specify bandwidth in MBps. + */ +static int set_mba_sc(bool mba_sc) +{ + struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA); + u32 num_closid = resctrl_arch_get_num_closid(r); + struct rdt_ctrl_domain *d; + unsigned long fflags; + int i; + + if (!supports_mba_mbps() || mba_sc == is_mba_sc(r)) + return -EINVAL; + + r->membw.mba_sc = mba_sc; + + rdtgroup_default.mba_mbps_event = mba_mbps_default_event; + + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + for (i = 0; i < num_closid; i++) + d->mbps_val[i] = MBA_MAX_MBPS; + } + + fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0; + resctrl_file_fflags_init("mba_MBps_event", fflags); + + return 0; +} + +/* + * 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 || + rcu_access_pointer(kn->__parent) == kn_info) + return NULL; + else + return kn->priv; + } else { + return rdt_kn_parent_priv(kn); + } +} + +static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn) +{ + atomic_inc(&rdtgrp->waitcount); + kernfs_break_active_protection(kn); +} + +static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn) +{ + 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); + } +} + +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) +{ + struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); + + if (!rdtgrp) + return NULL; + + rdtgroup_kn_get(rdtgrp, kn); + + cpus_read_lock(); + 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); + cpus_read_unlock(); + + rdtgroup_kn_put(rdtgrp, kn); +} + +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **mon_data_kn); + +static void rdt_disable_ctx(void) +{ + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); + set_mba_sc(false); + + resctrl_debug = false; +} + +static int rdt_enable_ctx(struct rdt_fs_context *ctx) +{ + int ret = 0; + + if (ctx->enable_cdpl2) { + ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true); + if (ret) + goto out_done; + } + + if (ctx->enable_cdpl3) { + ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true); + if (ret) + goto out_cdpl2; + } + + if (ctx->enable_mba_mbps) { + ret = set_mba_sc(true); + if (ret) + goto out_cdpl3; + } + + if (ctx->enable_debug) + resctrl_debug = true; + + return 0; + +out_cdpl3: + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); +out_cdpl2: + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); +out_done: + return ret; +} + +static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type) +{ + struct resctrl_schema *s; + const char *suffix = ""; + int ret, cl; + + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + s->res = r; + s->num_closid = resctrl_arch_get_num_closid(r); + if (resctrl_arch_get_cdp_enabled(r->rid)) + s->num_closid /= 2; + + s->conf_type = type; + switch (type) { + case CDP_CODE: + suffix = "CODE"; + break; + case CDP_DATA: + suffix = "DATA"; + break; + case CDP_NONE: + suffix = ""; + break; + } + + ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix); + if (ret >= sizeof(s->name)) { + kfree(s); + return -EINVAL; + } + + cl = strlen(s->name); + + /* + * If CDP is supported by this resource, but not enabled, + * include the suffix. This ensures the tabular format of the + * schemata file does not change between mounts of the filesystem. + */ + if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid)) + cl += 4; + + if (cl > max_name_width) + max_name_width = cl; + + switch (r->schema_fmt) { + case RESCTRL_SCHEMA_BITMAP: + s->fmt_str = "%d=%x"; + break; + case RESCTRL_SCHEMA_RANGE: + s->fmt_str = "%d=%u"; + break; + } + + if (WARN_ON_ONCE(!s->fmt_str)) { + kfree(s); + return -EINVAL; + } + + INIT_LIST_HEAD(&s->list); + list_add(&s->list, &resctrl_schema_all); + + return 0; +} + +static int schemata_list_create(void) +{ + struct rdt_resource *r; + int ret = 0; + + for_each_alloc_capable_rdt_resource(r) { + if (resctrl_arch_get_cdp_enabled(r->rid)) { + ret = schemata_list_add(r, CDP_CODE); + if (ret) + break; + + ret = schemata_list_add(r, CDP_DATA); + } else { + ret = schemata_list_add(r, CDP_NONE); + } + + if (ret) + break; + } + + return ret; +} + +static void schemata_list_destroy(void) +{ + struct resctrl_schema *s, *tmp; + + list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) { + list_del(&s->list); + kfree(s); + } +} + +static int rdt_get_tree(struct fs_context *fc) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + unsigned long flags = RFTYPE_CTRL_BASE; + struct rdt_l3_mon_domain *dom; + struct rdt_resource *r; + int ret; + + DO_ONCE_SLEEPABLE(resctrl_arch_pre_mount); + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + /* + * resctrl file system can only be mounted once. + */ + if (resctrl_mounted) { + ret = -EBUSY; + goto out; + } + + ret = setup_rmid_lru_list(); + if (ret) + goto out; + + ret = rdtgroup_setup_root(ctx); + if (ret) + goto out; + + ret = rdt_enable_ctx(ctx); + if (ret) + goto out_root; + + ret = schemata_list_create(); + if (ret) + goto out_schemata_free; + + ret = closid_init(); + if (ret) + goto out_schemata_free; + + if (resctrl_arch_mon_capable()) + flags |= RFTYPE_MON; + + ret = rdtgroup_add_files(rdtgroup_default.kn, flags); + if (ret) + goto out_closid_exit; + + kernfs_activate(rdtgroup_default.kn); + + ret = rdtgroup_create_info_dir(rdtgroup_default.kn); + if (ret < 0) + goto out_closid_exit; + + if (resctrl_arch_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 (resctrl_arch_alloc_capable()) + resctrl_arch_enable_alloc(); + if (resctrl_arch_mon_capable()) + resctrl_arch_enable_mon(); + + if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable()) + resctrl_mounted = true; + + if (resctrl_is_mbm_enabled()) { + r = resctrl_arch_get_resource(RDT_RESOURCE_L3); + list_for_each_entry(dom, &r->mon_domains, hdr.list) + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); + } + + goto out; + +out_psl: + rdt_pseudo_lock_release(); +out_mondata: + if (resctrl_arch_mon_capable()) + kernfs_remove(kn_mondata); +out_mongrp: + if (resctrl_arch_mon_capable()) + kernfs_remove(kn_mongrp); +out_info: + kernfs_remove(kn_info); +out_closid_exit: + closid_exit(); +out_schemata_free: + schemata_list_destroy(); + rdt_disable_ctx(); +out_root: + rdtgroup_destroy_root(); +out: + rdt_last_cmd_clear(); + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + return ret; +} + +enum rdt_param { + Opt_cdp, + Opt_cdpl2, + Opt_mba_mbps, + Opt_debug, + 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), + fsparam_flag("debug", Opt_debug), + {} +}; + +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; + const char *msg; + 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: + msg = "mba_MBps requires MBM and linear scale MBA at L3 scope"; + if (!supports_mba_mbps()) + return invalfc(fc, msg); + ctx->enable_mba_mbps = true; + return 0; + case Opt_debug: + ctx->enable_debug = 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(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + 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; +} + +/* + * 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)) { + resctrl_arch_set_closid_rmid(t, to->closid, + 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_arch_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->closid, 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; + + /* + * 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); + + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || + rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + rdtgroup_pseudo_lock_remove(rdtgrp); + } else { + /* Pseudo-locked group's RMID is freed during setup. */ + free_rmid(rdtgrp->closid, 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); +} + +/** + * mon_get_kn_priv() - Get the mon_data priv data for this event. + * + * The same values are used across the mon_data directories of all control and + * monitor groups for the same event in the same domain. Keep a list of + * allocated structures and re-use an existing one with the same values for + * @rid, @domid, etc. + * + * @rid: The resource id for the event file being created. + * @domid: The domain id for the event file being created. + * @mevt: The type of event file being created. + * @do_sum: Whether SNC summing monitors are being created. Only set + * when @rid == RDT_RESOURCE_L3. + */ +static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid, + struct mon_evt *mevt, + bool do_sum) +{ + struct mon_data *priv; + + lockdep_assert_held(&rdtgroup_mutex); + + list_for_each_entry(priv, &mon_data_kn_priv_list, list) { + if (priv->rid == rid && priv->domid == domid && + priv->sum == do_sum && priv->evt == mevt) + return priv; + } + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return NULL; + + priv->rid = rid; + priv->domid = domid; + priv->sum = do_sum; + priv->evt = mevt; + list_add_tail(&priv->list, &mon_data_kn_priv_list); + + return priv; +} + +/** + * mon_put_kn_priv() - Free all allocated mon_data structures. + * + * Called when resctrl file system is unmounted. + */ +static void mon_put_kn_priv(void) +{ + struct mon_data *priv, *tmp; + + lockdep_assert_held(&rdtgroup_mutex); + + list_for_each_entry_safe(priv, tmp, &mon_data_kn_priv_list, list) { + list_del(&priv->list); + kfree(priv); + } +} + +static void resctrl_fs_teardown(void) +{ + lockdep_assert_held(&rdtgroup_mutex); + + /* Cleared by rdtgroup_destroy_root() */ + if (!rdtgroup_default.kn) + return; + + rmdir_all_sub(); + mon_put_kn_priv(); + rdt_pseudo_lock_release(); + rdtgroup_default.mode = RDT_MODE_SHAREABLE; + closid_exit(); + schemata_list_destroy(); + rdtgroup_destroy_root(); +} + +static void rdt_kill_sb(struct super_block *sb) +{ + struct rdt_resource *r; + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + rdt_disable_ctx(); + + /* Put everything back to default values. */ + for_each_alloc_capable_rdt_resource(r) + resctrl_arch_reset_all_ctrls(r); + + resctrl_fs_teardown(); + if (resctrl_arch_alloc_capable()) + resctrl_arch_disable_alloc(); + if (resctrl_arch_mon_capable()) + resctrl_arch_disable_mon(); + resctrl_mounted = false; + 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; +} + +static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname) +{ + struct kernfs_node *kn; + + kn = kernfs_find_and_get(pkn, name); + if (!kn) + return; + kernfs_put(kn); + + if (kn->dir.subdirs <= 1) + kernfs_remove(kn); + else + kernfs_remove_by_name(kn, subname); +} + +/* + * Remove files and directories for one SNC node. If it is the last node + * sharing an L3 cache, then remove the upper level directory containing + * the "sum" files too. + */ +static void rmdir_mondata_subdir_allrdtgrp_snc(struct rdt_resource *r, + struct rdt_domain_hdr *hdr) +{ + struct rdtgroup *prgrp, *crgrp; + struct rdt_l3_mon_domain *d; + char subname[32]; + char name[32]; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + sprintf(name, "mon_%s_%02d", r->name, d->ci_id); + sprintf(subname, "mon_sub_%s_%02d", r->name, hdr->id); + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname); + + list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) + mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname); + } +} + +/* + * Remove all subdirectories of mon_data of ctrl_mon groups + * and monitor groups for the given domain. + */ +static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain_hdr *hdr) +{ + struct rdtgroup *prgrp, *crgrp; + char name[32]; + + if (r->rid == RDT_RESOURCE_L3 && r->mon_scope == RESCTRL_L3_NODE) { + rmdir_mondata_subdir_allrdtgrp_snc(r, hdr); + return; + } + + sprintf(name, "mon_%s_%02d", r->name, hdr->id); + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + kernfs_remove_by_name(prgrp->mon.mon_data_kn, name); + + list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) + kernfs_remove_by_name(crgrp->mon.mon_data_kn, name); + } +} + +/* + * Create a directory for a domain and populate it with monitor files. Create + * summing monitors when @hdr is NULL. No need to initialize summing monitors. + */ +static struct kernfs_node *_mkdir_mondata_subdir(struct kernfs_node *parent_kn, char *name, + struct rdt_domain_hdr *hdr, + struct rdt_resource *r, + struct rdtgroup *prgrp, int domid) +{ + struct rmid_read rr = {0}; + struct kernfs_node *kn; + struct mon_data *priv; + struct mon_evt *mevt; + int ret; + + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return kn; + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + for_each_mon_event(mevt) { + if (mevt->rid != r->rid || !mevt->enabled) + continue; + priv = mon_get_kn_priv(r->rid, domid, mevt, !hdr); + if (WARN_ON_ONCE(!priv)) { + ret = -EINVAL; + goto out_destroy; + } + + ret = mon_addfile(kn, mevt->name, priv); + if (ret) + goto out_destroy; + + if (hdr && resctrl_is_mbm_event(mevt->evtid)) + mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt, true); + } + + return kn; +out_destroy: + kernfs_remove(kn); + return ERR_PTR(ret); +} + +static int mkdir_mondata_subdir_snc(struct kernfs_node *parent_kn, + struct rdt_domain_hdr *hdr, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + struct kernfs_node *ckn, *kn; + struct rdt_l3_mon_domain *d; + char name[32]; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + return -EINVAL; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + sprintf(name, "mon_%s_%02d", r->name, d->ci_id); + kn = kernfs_find_and_get(parent_kn, name); + if (kn) { + /* + * rdtgroup_mutex will prevent this directory from being + * removed. No need to keep this hold. + */ + kernfs_put(kn); + } else { + kn = _mkdir_mondata_subdir(parent_kn, name, NULL, r, prgrp, d->ci_id); + if (IS_ERR(kn)) + return PTR_ERR(kn); + } + + sprintf(name, "mon_sub_%s_%02d", r->name, hdr->id); + ckn = _mkdir_mondata_subdir(kn, name, hdr, r, prgrp, hdr->id); + if (IS_ERR(ckn)) { + kernfs_remove(kn); + return PTR_ERR(ckn); + } + + kernfs_activate(kn); + return 0; +} + +static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, + struct rdt_domain_hdr *hdr, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + struct kernfs_node *kn; + char name[32]; + + lockdep_assert_held(&rdtgroup_mutex); + + if (r->rid == RDT_RESOURCE_L3 && r->mon_scope == RESCTRL_L3_NODE) + return mkdir_mondata_subdir_snc(parent_kn, hdr, r, prgrp); + + sprintf(name, "mon_%s_%02d", r->name, hdr->id); + kn = _mkdir_mondata_subdir(parent_kn, name, hdr, r, prgrp, hdr->id); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + kernfs_activate(kn); + return 0; +} + +/* + * Add all subdirectories of mon_data for "ctrl_mon" groups + * and "monitor" groups with given domain id. + */ +static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain_hdr *hdr) +{ + struct kernfs_node *parent_kn; + struct rdtgroup *prgrp, *crgrp; + struct list_head *head; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + parent_kn = prgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, hdr, r, prgrp); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + parent_kn = crgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, hdr, r, crgrp); + } + } +} + +static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, + struct rdt_resource *r, + struct rdtgroup *prgrp) +{ + struct rdt_domain_hdr *hdr; + int ret; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + list_for_each_entry(hdr, &r->mon_domains, list) { + ret = mkdir_mondata_subdir(parent_kn, hdr, 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 which are named + * in the format mon__. 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_capable_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; + + if (!_val || r->cache.arch_has_sparse_bitmasks) + return _val; + + val = _val; + 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_ctrl_domain *d, struct resctrl_schema *s, + u32 closid) +{ + enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type); + enum resctrl_conf_type t = s->conf_type; + struct resctrl_staged_config *cfg; + struct rdt_resource *r = s->res; + u32 used_b = 0, unused_b = 0; + unsigned long tmp_cbm; + enum rdtgrp_mode mode; + u32 peer_ctl, ctrl_val; + int i; + + cfg = &d->staged_config[t]; + cfg->have_new_ctrl = false; + cfg->new_ctrl = r->cache.shareable_bits; + used_b = r->cache.shareable_bits; + for (i = 0; i < closids_supported(); i++) { + 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 (resctrl_arch_get_cdp_enabled(r->rid)) + peer_ctl = resctrl_arch_get_config(r, d, i, + peer_type); + else + peer_ctl = 0; + ctrl_val = resctrl_arch_get_config(r, d, i, + s->conf_type); + used_b |= ctrl_val | peer_ctl; + if (mode == RDT_MODE_SHAREABLE) + cfg->new_ctrl |= ctrl_val | 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; + cfg->new_ctrl |= unused_b; + /* + * Force the initial CBM to be valid, user can + * modify the CBM based on system availability. + */ + cfg->new_ctrl = cbm_ensure_valid(cfg->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 = cfg->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", s->name, d->hdr.id); + return -ENOSPC; + } + cfg->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 resctrl_schema *s, u32 closid) +{ + struct rdt_ctrl_domain *d; + int ret; + + list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) { + ret = __init_one_rdt_domain(d, s, closid); + if (ret < 0) + return ret; + } + + return 0; +} + +/* Initialize MBA resource with default values. */ +static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid) +{ + struct resctrl_staged_config *cfg; + struct rdt_ctrl_domain *d; + + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + if (is_mba_sc(r)) { + d->mbps_val[closid] = MBA_MAX_MBPS; + continue; + } + + cfg = &d->staged_config[CDP_NONE]; + cfg->new_ctrl = resctrl_get_default_ctrl(r); + cfg->have_new_ctrl = true; + } +} + +/* Initialize the RDT group's allocations. */ +static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) +{ + struct resctrl_schema *s; + struct rdt_resource *r; + int ret = 0; + + rdt_staged_configs_clear(); + + list_for_each_entry(s, &resctrl_schema_all, list) { + r = s->res; + if (r->rid == RDT_RESOURCE_MBA || + r->rid == RDT_RESOURCE_SMBA) { + rdtgroup_init_mba(r, rdtgrp->closid); + if (is_mba_sc(r)) + continue; + } else { + ret = rdtgroup_init_cat(s, rdtgrp->closid); + if (ret < 0) + goto out; + } + + ret = resctrl_arch_update_domains(r, rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("Failed to initialize allocations\n"); + goto out; + } + } + + rdtgrp->mode = RDT_MODE_SHAREABLE; + +out: + rdt_staged_configs_clear(); + return ret; +} + +static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) +{ + int ret; + + if (!resctrl_arch_mon_capable()) + return 0; + + ret = alloc_rmid(rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("Out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); + return ret; + } + + return 0; +} + +static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) +{ + if (resctrl_arch_mon_capable()) + free_rmid(rgrp->closid, rgrp->mon.rmid); +} + +/* + * 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(rdt_kn_name(kn), "mon_groups") && + strcmp(name, "mon_groups")); +} + +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; + unsigned long files = 0; + struct kernfs_node *kn; + int ret; + + prdtgrp = rdtgroup_kn_lock_live(parent_kn); + if (!prdtgrp) { + ret = -ENODEV; + goto out_unlock; + } + + rdt_last_cmd_clear(); + + /* + * Check that the parent directory for a monitor group is a "mon_groups" + * directory. + */ + if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) { + ret = -EPERM; + 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; + } + + if (rtype == RDTCTRL_GROUP) { + files = RFTYPE_BASE | RFTYPE_CTRL; + if (resctrl_arch_mon_capable()) + files |= RFTYPE_MON; + } else { + files = RFTYPE_BASE | RFTYPE_MON; + } + + ret = rdtgroup_add_files(kn, files); + if (ret) { + rdt_last_cmd_puts("kernfs fill error\n"); + goto out_destroy; + } + + /* + * The caller unlocks the parent_kn upon success. + */ + return 0; + +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); + 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; + + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) { + mkdir_rdt_prepare_clean(rdtgrp); + goto out_unlock; + } + + kernfs_activate(rdtgrp->kn); + + /* + * 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); + +out_unlock: + 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 = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) + goto out_closid_free; + + kernfs_activate(rdtgrp->kn); + + ret = rdtgroup_init_alloc(rdtgrp); + if (ret < 0) + goto out_rmid_free; + + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + + if (resctrl_arch_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; + } + if (is_mba_sc(NULL)) + rdtgrp->mba_mbps_event = mba_mbps_default_event; + } + + goto out_unlock; + +out_del_list: + list_del(&rdtgrp->rdtgroup_list); +out_rmid_free: + mkdir_rdt_prepare_rmid_free(rdtgrp); +out_closid_free: + closid_free(closid); +out_common_fail: + mkdir_rdt_prepare_clean(rdtgrp); +out_unlock: + rdtgroup_kn_unlock(parent_kn); + return ret; +} + +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 (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn) + return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); + + /* Else, attempt to add a monitoring subdirectory. */ + if (resctrl_arch_mon_capable()) + return rdtgroup_mkdir_mon(parent_kn, name, mode); + + return -EPERM; +} + +static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + u32 closid, rmid; + int cpu; + + /* Give any tasks back to the parent group */ + rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask); + + /* + * Update per cpu closid/rmid of the moved CPUs first. + * Note: the closid will not change, but the arch code still needs it. + */ + closid = prdtgrp->closid; + rmid = prdtgrp->mon.rmid; + for_each_cpu(cpu, &rdtgrp->cpu_mask) + resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, 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->closid, 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 rdtgroup *rdtgrp) +{ + rdtgrp->flags = RDT_DELETED; + list_del(&rdtgrp->rdtgroup_list); + + kernfs_remove(rdtgrp->kn); + return 0; +} + +static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) +{ + u32 closid, rmid; + 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 */ + closid = rdtgroup_default.closid; + rmid = rdtgroup_default.mon.rmid; + for_each_cpu(cpu, &rdtgrp->cpu_mask) + resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, 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); + + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); + closid_free(rdtgrp->closid); + + rdtgroup_ctrl_remove(rdtgrp); + + /* + * Free all the child monitor group rmids. + */ + free_all_child_rdtgrp(rdtgrp); + + return 0; +} + +static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn) +{ + /* + * Valid within the RCU section it was obtained or while rdtgroup_mutex + * is held. + */ + return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex)); +} + +static int rdtgroup_rmdir(struct kernfs_node *kn) +{ + struct kernfs_node *parent_kn; + 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; + } + parent_kn = rdt_kn_parent(kn); + + /* + * 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(rdtgrp); + } else { + ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask); + } + } else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, rdt_kn_name(kn))) { + ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask); + } else { + ret = -EPERM; + } + +out: + rdtgroup_kn_unlock(kn); + free_cpumask_var(tmpmask); + return ret; +} + +/** + * mongrp_reparent() - replace parent CTRL_MON group of a MON group + * @rdtgrp: the MON group whose parent should be replaced + * @new_prdtgrp: replacement parent CTRL_MON group for @rdtgrp + * @cpus: cpumask provided by the caller for use during this call + * + * Replaces the parent CTRL_MON group for a MON group, resulting in all member + * tasks' CLOSID immediately changing to that of the new parent group. + * Monitoring data for the group is unaffected by this operation. + */ +static void mongrp_reparent(struct rdtgroup *rdtgrp, + struct rdtgroup *new_prdtgrp, + cpumask_var_t cpus) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + + WARN_ON(rdtgrp->type != RDTMON_GROUP); + WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP); + + /* Nothing to do when simply renaming a MON group. */ + if (prdtgrp == new_prdtgrp) + return; + + WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); + list_move_tail(&rdtgrp->mon.crdtgrp_list, + &new_prdtgrp->mon.crdtgrp_list); + + rdtgrp->mon.parent = new_prdtgrp; + rdtgrp->closid = new_prdtgrp->closid; + + /* Propagate updated closid to all tasks in this group. */ + rdt_move_group_tasks(rdtgrp, rdtgrp, cpus); + + update_closid_rmid(cpus, NULL); +} + +static int rdtgroup_rename(struct kernfs_node *kn, + struct kernfs_node *new_parent, const char *new_name) +{ + struct kernfs_node *kn_parent; + struct rdtgroup *new_prdtgrp; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + int ret; + + rdtgrp = kernfs_to_rdtgroup(kn); + new_prdtgrp = kernfs_to_rdtgroup(new_parent); + if (!rdtgrp || !new_prdtgrp) + return -ENOENT; + + /* Release both kernfs active_refs before obtaining rdtgroup mutex. */ + rdtgroup_kn_get(rdtgrp, kn); + rdtgroup_kn_get(new_prdtgrp, new_parent); + + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + + /* + * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if + * either kernfs_node is a file. + */ + if (kernfs_type(kn) != KERNFS_DIR || + kernfs_type(new_parent) != KERNFS_DIR) { + rdt_last_cmd_puts("Source and destination must be directories"); + ret = -EPERM; + goto out; + } + + if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) { + ret = -ENOENT; + goto out; + } + + kn_parent = rdt_kn_parent(kn); + if (rdtgrp->type != RDTMON_GROUP || !kn_parent || + !is_mon_groups(kn_parent, rdt_kn_name(kn))) { + rdt_last_cmd_puts("Source must be a MON group\n"); + ret = -EPERM; + goto out; + } + + if (!is_mon_groups(new_parent, new_name)) { + rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n"); + ret = -EPERM; + goto out; + } + + /* + * If the MON group is monitoring CPUs, the CPUs must be assigned to the + * current parent CTRL_MON group and therefore cannot be assigned to + * the new parent, making the move illegal. + */ + if (!cpumask_empty(&rdtgrp->cpu_mask) && + rdtgrp->mon.parent != new_prdtgrp) { + rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n"); + ret = -EPERM; + goto out; + } + + /* + * Allocate the cpumask for use in mongrp_reparent() to avoid the + * possibility of failing to allocate it after kernfs_rename() has + * succeeded. + */ + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) { + ret = -ENOMEM; + goto out; + } + + /* + * Perform all input validation and allocations needed to ensure + * mongrp_reparent() will succeed before calling kernfs_rename(), + * otherwise it would be necessary to revert this call if + * mongrp_reparent() failed. + */ + ret = kernfs_rename(kn, new_parent, new_name); + if (!ret) + mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask); + + free_cpumask_var(tmpmask); + +out: + mutex_unlock(&rdtgroup_mutex); + rdtgroup_kn_put(rdtgrp, kn); + rdtgroup_kn_put(new_prdtgrp, new_parent); + return ret; +} + +static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) +{ + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) + seq_puts(seq, ",cdp"); + + if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) + seq_puts(seq, ",cdpl2"); + + if (is_mba_sc(resctrl_arch_get_resource(RDT_RESOURCE_MBA))) + seq_puts(seq, ",mba_MBps"); + + if (resctrl_debug) + seq_puts(seq, ",debug"); + + return 0; +} + +static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { + .mkdir = rdtgroup_mkdir, + .rmdir = rdtgroup_rmdir, + .rename = rdtgroup_rename, + .show_options = rdtgroup_show_options, +}; + +static int rdtgroup_setup_root(struct rdt_fs_context *ctx) +{ + 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); + + ctx->kfc.root = rdt_root; + rdtgroup_default.kn = kernfs_root_to_node(rdt_root); + + return 0; +} + +static void rdtgroup_destroy_root(void) +{ + lockdep_assert_held(&rdtgroup_mutex); + + kernfs_destroy_root(rdt_root); + rdtgroup_default.kn = NULL; +} + +static void rdtgroup_setup_default(void) +{ + mutex_lock(&rdtgroup_mutex); + + rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID; + rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID; + rdtgroup_default.type = RDTCTRL_GROUP; + INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); + + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); + + mutex_unlock(&rdtgroup_mutex); +} + +static void domain_destroy_l3_mon_state(struct rdt_l3_mon_domain *d) +{ + int idx; + + kfree(d->cntr_cfg); + bitmap_free(d->rmid_busy_llc); + for_each_mbm_idx(idx) { + kfree(d->mbm_states[idx]); + d->mbm_states[idx] = NULL; + } +} + +void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d) +{ + mutex_lock(&rdtgroup_mutex); + + if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) + mba_sc_domain_destroy(r, d); + + mutex_unlock(&rdtgroup_mutex); +} + +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr) +{ + struct rdt_l3_mon_domain *d; + + mutex_lock(&rdtgroup_mutex); + + /* + * If resctrl is mounted, remove all the + * per domain monitor data directories. + */ + if (resctrl_mounted && resctrl_arch_mon_capable()) + rmdir_mondata_subdir_allrdtgrp(r, hdr); + + if (r->rid != RDT_RESOURCE_L3) + goto out_unlock; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + goto out_unlock; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + if (resctrl_is_mbm_enabled()) + cancel_delayed_work(&d->mbm_over); + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(d)) { + /* + * 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); + } + + domain_destroy_l3_mon_state(d); +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +/** + * domain_setup_l3_mon_state() - Initialise domain monitoring structures. + * @r: The resource for the newly online domain. + * @d: The newly online domain. + * + * Allocate monitor resources that belong to this domain. + * Called when the first CPU of a domain comes online, regardless of whether + * the filesystem is mounted. + * During boot this may be called before global allocations have been made by + * resctrl_l3_mon_resource_init(). + * + * Called during CPU online that may run as soon as CPU online callbacks + * are set up during resctrl initialization. The number of supported RMIDs + * may be reduced if additional mon_capable resources are enumerated + * at mount time. This means the rdt_l3_mon_domain::mbm_states[] and + * rdt_l3_mon_domain::rmid_busy_llc allocations may be larger than needed. + * + * Return: 0 for success, or -ENOMEM. + */ +static int domain_setup_l3_mon_state(struct rdt_resource *r, struct rdt_l3_mon_domain *d) +{ + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + size_t tsize = sizeof(*d->mbm_states[0]); + enum resctrl_event_id eventid; + int idx; + + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) { + d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL); + if (!d->rmid_busy_llc) + return -ENOMEM; + } + + for_each_mbm_event_id(eventid) { + if (!resctrl_is_mon_event_enabled(eventid)) + continue; + idx = MBM_STATE_IDX(eventid); + d->mbm_states[idx] = kcalloc(idx_limit, tsize, GFP_KERNEL); + if (!d->mbm_states[idx]) + goto cleanup; + } + + if (resctrl_is_mbm_enabled() && r->mon.mbm_cntr_assignable) { + tsize = sizeof(*d->cntr_cfg); + d->cntr_cfg = kcalloc(r->mon.num_mbm_cntrs, tsize, GFP_KERNEL); + if (!d->cntr_cfg) + goto cleanup; + } + + return 0; +cleanup: + bitmap_free(d->rmid_busy_llc); + for_each_mbm_idx(idx) { + kfree(d->mbm_states[idx]); + d->mbm_states[idx] = NULL; + } + + return -ENOMEM; +} + +int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d) +{ + int err = 0; + + mutex_lock(&rdtgroup_mutex); + + if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) { + /* RDT_RESOURCE_MBA is never mon_capable */ + err = mba_sc_domain_allocate(r, d); + } + + mutex_unlock(&rdtgroup_mutex); + + return err; +} + +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr) +{ + struct rdt_l3_mon_domain *d; + int err = -EINVAL; + + mutex_lock(&rdtgroup_mutex); + + if (r->rid != RDT_RESOURCE_L3) + goto mkdir; + + if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) + goto out_unlock; + + d = container_of(hdr, struct rdt_l3_mon_domain, hdr); + err = domain_setup_l3_mon_state(r, d); + if (err) + goto out_unlock; + + if (resctrl_is_mbm_enabled()) { + INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); + } + + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) + INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); + +mkdir: + err = 0; + /* + * If the filesystem is not mounted then only the default resource group + * exists. Creation of its directories is deferred until mount time + * by rdt_get_tree() calling mkdir_mondata_all(). + * If resctrl is mounted, add per domain monitor data directories. + */ + if (resctrl_mounted && resctrl_arch_mon_capable()) + mkdir_mondata_subdir_allrdtgrp(r, hdr); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); + + return err; +} + +void resctrl_online_cpu(unsigned int cpu) +{ + mutex_lock(&rdtgroup_mutex); + /* The CPU is set in default rdtgroup after online. */ + cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + mutex_unlock(&rdtgroup_mutex); +} + +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 struct rdt_l3_mon_domain *get_mon_domain_from_cpu(int cpu, + struct rdt_resource *r) +{ + struct rdt_l3_mon_domain *d; + + lockdep_assert_cpus_held(); + + list_for_each_entry(d, &r->mon_domains, hdr.list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask)) + return d; + } + + return NULL; +} + +void resctrl_offline_cpu(unsigned int cpu) +{ + struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3); + struct rdt_l3_mon_domain *d; + struct rdtgroup *rdtgrp; + + mutex_lock(&rdtgroup_mutex); + 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; + } + } + + if (!l3->mon_capable) + goto out_unlock; + + d = get_mon_domain_from_cpu(cpu, l3); + if (d) { + if (resctrl_is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0, cpu); + } + if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && + cpu == d->cqm_work_cpu && has_busy_rmid(d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0, cpu); + } + } + +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +/* + * resctrl_init - resctrl filesystem initialization + * + * Setup resctrl file system including set up root, create mount point, + * register resctrl filesystem, and initialize files under root directory. + * + * Return: 0 on success or -errno + */ +int resctrl_init(void) +{ + int ret = 0; + + seq_buf_init(&last_cmd_status, last_cmd_status_buf, + sizeof(last_cmd_status_buf)); + + rdtgroup_setup_default(); + + thread_throttle_mode_init(); + + ret = resctrl_l3_mon_resource_init(); + if (ret) + return ret; + + ret = sysfs_create_mount_point(fs_kobj, "resctrl"); + if (ret) { + resctrl_l3_mon_resource_exit(); + return ret; + } + + 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"); + resctrl_l3_mon_resource_exit(); + + return ret; +} + +static bool resctrl_online_domains_exist(void) +{ + struct rdt_resource *r; + + /* + * Only walk capable resources to allow resctrl_arch_get_resource() + * to return dummy 'not capable' resources. + */ + for_each_alloc_capable_rdt_resource(r) { + if (!list_empty(&r->ctrl_domains)) + return true; + } + + for_each_mon_capable_rdt_resource(r) { + if (!list_empty(&r->mon_domains)) + return true; + } + + return false; +} + +/** + * resctrl_exit() - Remove the resctrl filesystem and free resources. + * + * Called by the architecture code in response to a fatal error. + * Removes resctrl files and structures from kernfs to prevent further + * configuration. + * + * When called by the architecture code, all CPUs and resctrl domains must be + * offline. This ensures the limbo and overflow handlers are not scheduled to + * run, meaning the data structures they access can be freed by + * resctrl_l3_mon_resource_exit(). + * + * After resctrl_exit() returns, the architecture code should return an + * error from all resctrl_arch_ functions that can do this. + * resctrl_arch_get_resource() must continue to return struct rdt_resources + * with the correct rid field to ensure the filesystem can be unmounted. + */ +void resctrl_exit(void) +{ + cpus_read_lock(); + WARN_ON_ONCE(resctrl_online_domains_exist()); + + mutex_lock(&rdtgroup_mutex); + resctrl_fs_teardown(); + mutex_unlock(&rdtgroup_mutex); + + cpus_read_unlock(); + + debugfs_remove_recursive(debugfs_resctrl); + debugfs_resctrl = NULL; + unregister_filesystem(&rdt_fs_type); + + /* + * Do not remove the sysfs mount point added by resctrl_init() so that + * it can be used to umount resctrl. + */ + + resctrl_l3_mon_resource_exit(); + free_rmid_lru_list(); +} diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index b6b6796e16160..2e7b9cb2788e2 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -123,7 +123,7 @@ int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, new_parent = new_parent_kobj && new_parent_kobj->sd ? new_parent_kobj->sd : sysfs_root_kn; - return kernfs_rename_ns(kn, new_parent, kn->name, new_ns); + return kernfs_rename_ns(kn, new_parent, NULL, new_ns); } /** diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 833dd3f5a3f20..a8ab89946776d 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -19,13 +19,19 @@ #include "sysfs.h" +static struct kobject *sysfs_file_kobj(struct kernfs_node *kn) +{ + guard(rcu)(); + return rcu_dereference(kn->__parent)->priv; +} + /* * Determine ktype->sysfs_ops for the given kernfs_node. This function * must be called while holding an active reference. */ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) { - struct kobject *kobj = kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(kn); if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); @@ -40,7 +46,7 @@ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn) static int sysfs_kf_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); const struct sysfs_ops *ops = sysfs_file_ops(of->kn); ssize_t count; char *buf; @@ -78,7 +84,7 @@ static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); loff_t size = file_inode(of->file)->i_size; if (!count) @@ -102,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); ssize_t len; /* @@ -132,7 +138,7 @@ static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); if (!count) return 0; @@ -145,7 +151,7 @@ static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf, size_t count, loff_t pos) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); loff_t size = file_inode(of->file)->i_size; if (size) { @@ -166,11 +172,23 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of, struct vm_area_struct *vma) { struct bin_attribute *battr = of->kn->priv; - struct kobject *kobj = of->kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); return battr->mmap(of->file, kobj, battr, vma); } +static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset, + int whence) +{ + struct bin_attribute *battr = of->kn->priv; + struct kobject *kobj = sysfs_file_kobj(of->kn); + + if (battr->llseek) + return battr->llseek(of->file, kobj, battr, offset, whence); + else + return generic_file_llseek(of->file, offset, whence); +} + static int sysfs_kf_bin_open(struct kernfs_open_file *of) { struct bin_attribute *battr = of->kn->priv; @@ -253,6 +271,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = { .write = sysfs_kf_bin_write, .mmap = sysfs_kf_bin_mmap, .open = sysfs_kf_bin_open, + .llseek = sysfs_kf_bin_llseek, }; int sysfs_add_file_mode_ns(struct kernfs_node *parent, @@ -473,7 +492,7 @@ EXPORT_SYMBOL_GPL(sysfs_break_active_protection); */ void sysfs_unbreak_active_protection(struct kernfs_node *kn) { - struct kobject *kobj = kn->parent->priv; + struct kobject *kobj = sysfs_file_kobj(kn); kernfs_unbreak_active_protection(kn); kernfs_put(kn); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 729ec2453149f..9278b2fa6f381 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -52,6 +52,7 @@ struct device; * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits * bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap + * bitmap_weight_andnot(src1, src2, nbits) Hamming Weight of andnot'ed bitmap * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area @@ -171,6 +172,8 @@ bool __bitmap_subset(const unsigned long *bitmap1, unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); +unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -466,6 +469,15 @@ unsigned long bitmap_weight_and(const unsigned long *src1, return __bitmap_weight_and(src1, src2, nbits); } +static __always_inline +unsigned long bitmap_weight_andnot(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return hweight_long(*src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)); + return __bitmap_weight_andnot(src1, src2, nbits); +} + static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 115fd469bac37..afd540f321012 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -4,7 +4,7 @@ /* * Cpumasks provide a bitmap suitable for representing the - * set of CPU's in a system, one bit position per CPU number. In general, + * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include @@ -41,7 +41,7 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; extern unsigned int nr_cpu_ids; #endif -static inline void set_nr_cpu_ids(unsigned int nr) +static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); @@ -97,7 +97,7 @@ static inline void set_nr_cpu_ids(unsigned int nr) * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * - * The cpu_possible_mask is fixed at boot time, as the set of CPU id's + * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And @@ -112,7 +112,7 @@ static inline void set_nr_cpu_ids(unsigned int nr) * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: - * 1) UP arch's (NR_CPUS == 1, CONFIG_SMP not defined) hardcode + * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() @@ -155,9 +155,9 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu) * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * - * Returns >= nr_cpu_ids if no cpus set. + * Return: >= nr_cpu_ids if no cpus set. */ -static inline unsigned int cpumask_first(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -166,9 +166,9 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * - * Returns >= nr_cpu_ids if all cpus are set. + * Return: >= nr_cpu_ids if all cpus are set. */ -static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -178,33 +178,63 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) * @srcp1: the first input * @srcp2: the second input * - * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). + * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ -static inline +static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } +/** + * cpumask_first_andnot - return the first cpu from *srcp1 & ~*srcp2 + * @srcp1: the first input + * @srcp2: the second input + * + * Return: >= nr_cpu_ids if no such cpu found. + */ +static __always_inline +unsigned int cpumask_first_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) +{ + return find_first_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); +} + +/** + * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 + * @srcp1: the first input + * @srcp2: the second input + * @srcp3: the third input + * + * Return: >= nr_cpu_ids if no cpus set in all. + */ +static __always_inline +unsigned int cpumask_first_and_and(const struct cpumask *srcp1, + const struct cpumask *srcp2, + const struct cpumask *srcp3) +{ + return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + cpumask_bits(srcp3), small_cpumask_bits); +} + /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * - * Returns >= nr_cpumask_bits if no CPUs set. + * Return: >= nr_cpumask_bits if no CPUs set. */ -static inline unsigned int cpumask_last(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask - * @n: the cpu prior to the place to search (ie. return will be > @n) + * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * - * Returns >= nr_cpu_ids if no further cpus set. + * Return: >= nr_cpu_ids if no further cpus set. */ -static inline +static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ @@ -215,12 +245,13 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) /** * cpumask_next_zero - get the next unset cpu in a cpumask - * @n: the cpu prior to the place to search (ie. return will be > @n) + * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * - * Returns >= nr_cpu_ids if no further cpus unset. + * Return: >= nr_cpu_ids if no further cpus unset. */ -static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) @@ -230,18 +261,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ -static inline unsigned int cpumask_local_spread(unsigned int i, int node) +static __always_inline +unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } -static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } -static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } @@ -254,15 +288,15 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp); /** * cpumask_next_and - get the next cpu in *src1p & *src2p - * @n: the cpu prior to the place to search (ie. return will be > @n) + * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * - * Returns >= nr_cpu_ids if no further cpus set in both. + * Return: >= nr_cpu_ids if no further cpus set in both. */ -static inline +static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, - const struct cpumask *src2p) + const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) @@ -271,6 +305,25 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, small_cpumask_bits, n + 1); } +/** + * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p + * @n: the cpu prior to the place to search (i.e. return will be > @n) + * @src1p: the first cpumask pointer + * @src2p: the second cpumask pointer + * + * Return: >= nr_cpu_ids if no further cpus set in both. + */ +static __always_inline +unsigned int cpumask_next_andnot(int n, const struct cpumask *src1p, + const struct cpumask *src2p) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p), + small_cpumask_bits, n + 1); +} + /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator @@ -282,7 +335,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 -static inline +static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); @@ -373,14 +426,18 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. - * Returns >= nr_cpu_ids if no cpus set. + * If @cpu == -1, the function is equivalent to cpumask_any(). + * Return: >= nr_cpu_ids if no cpus set. */ -static inline -unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) +static __always_inline +unsigned int cpumask_any_but(const struct cpumask *mask, int cpu) { unsigned int i; - cpumask_check(cpu); + /* -1 is a legal arg here. */ + if (cpu != -1) + cpumask_check(cpu); + for_each_cpu(i, mask) if (i != cpu) break; @@ -388,26 +445,81 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) } /** - * cpumask_nth - get the first cpu in a cpumask + * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one. + * @mask1: the first input cpumask + * @mask2: the second input cpumask + * @cpu: the cpu to ignore + * + * If @cpu == -1, the function is equivalent to cpumask_any_and(). + * Returns >= nr_cpu_ids if no cpus set. + */ +static __always_inline +unsigned int cpumask_any_and_but(const struct cpumask *mask1, + const struct cpumask *mask2, + int cpu) +{ + unsigned int i; + + /* -1 is a legal arg here. */ + if (cpu != -1) + cpumask_check(cpu); + + i = cpumask_first_and(mask1, mask2); + if (i != cpu) + return i; + + return cpumask_next_and(cpu, mask1, mask2); +} + +/** + * cpumask_any_andnot_but - pick an arbitrary cpu from *mask1 & ~*mask2, but not this one. + * @mask1: the first input cpumask + * @mask2: the second input cpumask + * @cpu: the cpu to ignore + * + * If @cpu == -1, the function returns the first matching cpu. + * Returns >= nr_cpu_ids if no cpus set. + */ +static __always_inline +unsigned int cpumask_any_andnot_but(const struct cpumask *mask1, + const struct cpumask *mask2, + int cpu) +{ + unsigned int i; + + /* -1 is a legal arg here. */ + if (cpu != -1) + cpumask_check(cpu); + + i = cpumask_first_andnot(mask1, mask2); + if (i != cpu) + return i; + + return cpumask_next_andnot(cpu, mask1, mask2); +} + +/** + * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer - * @cpu: the N'th cpu to find, starting from 0 + * @cpu: the Nth cpu to find, starting from 0 * - * Returns >= nr_cpu_ids if such cpu doesn't exist. + * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** - * cpumask_nth_and - get the first cpu in 2 cpumasks + * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer - * @cpu: the N'th cpu to find, starting from 0 + * @cpu: the Nth cpu to find, starting from 0 * - * Returns >= nr_cpu_ids if such cpu doesn't exist. + * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -416,14 +528,14 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, } /** - * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd. + * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer - * @cpu: the N'th cpu to find, starting from 0 + * @cpu: the Nth cpu to find, starting from 0 * - * Returns >= nr_cpu_ids if such cpu doesn't exist. + * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -436,9 +548,9 @@ unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer - * @cpu: the N'th cpu to find, starting from 0 + * @cpu: the Nth cpu to find, starting from 0 * - * Returns >= nr_cpu_ids if such cpu doesn't exist. + * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, @@ -466,12 +578,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -497,9 +611,10 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns true if @cpu is set in @cpumask, else returns false + * Return: true if @cpu is set in @cpumask, else returns false */ -static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline +bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -509,11 +624,12 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns true if @cpu is set in old bitmap of @cpumask, else returns false - * * test_and_set_bit wrapper for cpumasks. + * + * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -523,11 +639,12 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns true if @cpu is set in old bitmap of @cpumask, else returns false - * * test_and_clear_bit wrapper for cpumasks. + * + * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -536,7 +653,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask * * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_setall(struct cpumask *dstp) +static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); @@ -549,7 +666,7 @@ static inline void cpumask_setall(struct cpumask *dstp) * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_clear(struct cpumask *dstp) +static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } @@ -560,11 +677,11 @@ static inline void cpumask_clear(struct cpumask *dstp) * @src1p: the first input * @src2p: the second input * - * If *@dstp is empty, returns false, else returns true + * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_and(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -576,8 +693,9 @@ static inline bool cpumask_and(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -589,9 +707,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_xor(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -603,11 +721,11 @@ static inline void cpumask_xor(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input * - * If *@dstp is empty, returns false, else returns true + * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_andnot(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -617,9 +735,11 @@ static inline bool cpumask_andnot(struct cpumask *dstp, * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input + * + * Return: true if the cpumasks are equal, false if not */ -static inline bool cpumask_equal(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -630,10 +750,13 @@ static inline bool cpumask_equal(const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input * @src3p: the third input + * + * Return: true if first cpumask ORed with second cpumask == third cpumask, + * otherwise false */ -static inline bool cpumask_or_equal(const struct cpumask *src1p, - const struct cpumask *src2p, - const struct cpumask *src3p) +static __always_inline +bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, + const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); @@ -643,9 +766,12 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p, * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input + * + * Return: true if first cpumask ANDed with second cpumask is non-empty, + * otherwise false */ -static inline bool cpumask_intersects(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -656,10 +782,10 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input * - * Returns true if *@src1p is a subset of *@src2p, else returns false + * Return: true if *@src1p is a subset of *@src2p, else returns false */ -static inline bool cpumask_subset(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -668,8 +794,10 @@ static inline bool cpumask_subset(const struct cpumask *src1p, /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. + * + * Return: true if srcp is empty (has no bits set), else false */ -static inline bool cpumask_empty(const struct cpumask *srcp) +static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } @@ -677,8 +805,10 @@ static inline bool cpumask_empty(const struct cpumask *srcp) /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. + * + * Return: true if srcp is full (has all bits set), else false */ -static inline bool cpumask_full(const struct cpumask *srcp) +static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } @@ -686,8 +816,10 @@ static inline bool cpumask_full(const struct cpumask *srcp) /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. + * + * Return: count of bits set in *srcp */ -static inline unsigned int cpumask_weight(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } @@ -696,21 +828,37 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. + * + * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } +/** + * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) + * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. + * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. + * + * Return: count of bits set in both *srcp1 and *srcp2 + */ +static __always_inline +unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); +} + /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_right(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); @@ -722,8 +870,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_left(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); @@ -734,8 +882,8 @@ static inline void cpumask_shift_left(struct cpumask *dstp, * @dstp: the result * @srcp: the input cpumask */ -static inline void cpumask_copy(struct cpumask *dstp, - const struct cpumask *srcp) +static __always_inline +void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } @@ -744,7 +892,7 @@ static inline void cpumask_copy(struct cpumask *dstp, * cpumask_any - pick a "random" cpu from *srcp * @srcp: the input cpumask * - * Returns >= nr_cpu_ids if no cpus set. + * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) @@ -753,7 +901,7 @@ static inline void cpumask_copy(struct cpumask *dstp, * @mask1: the first input cpumask * @mask2: the second input cpumask * - * Returns >= nr_cpu_ids if no cpus set. + * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) @@ -769,10 +917,10 @@ static inline void cpumask_copy(struct cpumask *dstp, * @len: the length of the buffer * @dstp: the cpumask to set. * - * Returns -errno, or 0 for success. + * Return: -errno, or 0 for success. */ -static inline int cpumask_parse_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } @@ -783,10 +931,10 @@ static inline int cpumask_parse_user(const char __user *buf, int len, * @len: the length of the buffer * @dstp: the cpumask to set. * - * Returns -errno, or 0 for success. + * Return: -errno, or 0 for success. */ -static inline int cpumask_parselist_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); @@ -797,9 +945,9 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, * @buf: the buffer to extract from * @dstp: the cpumask to set. * - * Returns -errno, or 0 for success. + * Return: -errno, or 0 for success. */ -static inline int cpumask_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } @@ -809,17 +957,19 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) * @buf: the buffer to extract from * @dstp: the cpumask to set. * - * Returns -errno, or 0 for success. + * Return: -errno, or 0 for success. */ -static inline int cpulist_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** - * cpumask_size - size to allocate for a 'struct cpumask' in bytes + * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes + * + * Return: size to allocate for a &struct cpumask in bytes */ -static inline unsigned int cpumask_size(void) +static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } @@ -831,7 +981,7 @@ static inline unsigned int cpumask_size(void) * little more difficult, we typedef cpumask_var_t to an array or a * pointer: doing &mask on an array is a noop, so it still works. * - * ie. + * i.e. * cpumask_var_t tmpmask; * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) * return -ENOMEM; @@ -872,7 +1022,7 @@ typedef struct cpumask *cpumask_var_t; bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -static inline +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); @@ -887,14 +1037,16 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) * a nop returning a constant 1 (in ). * * See alloc_cpumask_var_node. + * + * Return: %true if allocation succeeded, %false if not */ -static inline +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } -static inline +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); @@ -904,7 +1056,7 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } @@ -915,43 +1067,43 @@ typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly -static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } -static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } -static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } -static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } -static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) +static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } -static inline void free_cpumask_var(cpumask_var_t mask) +static __always_inline void free_cpumask_var(cpumask_var_t mask) { } -static inline void free_bootmem_cpumask_var(cpumask_var_t mask) +static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } @@ -997,7 +1149,7 @@ static inline void reset_cpu_possible_mask(void) void set_cpu_online(unsigned int cpu, bool online); /** - * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * + * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and @@ -1010,7 +1162,7 @@ void set_cpu_online(unsigned int cpu, bool online); ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) -static inline int __check_is_bitmap(const unsigned long *bitmap) +static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } @@ -1025,7 +1177,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap) extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; -static inline const struct cpumask *get_cpu_mask(unsigned int cpu) +static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; @@ -1040,6 +1192,8 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. + * + * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { @@ -1049,27 +1203,27 @@ static __always_inline unsigned int num_online_cpus(void) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } @@ -1081,27 +1235,27 @@ static inline bool cpu_dying(unsigned int cpu) #define num_present_cpus() 1U #define num_active_cpus() 1U -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return false; } @@ -1132,10 +1286,10 @@ static inline bool cpu_dying(unsigned int cpu) * @mask: the cpumask to copy * @buf: the buffer to copy into * - * Returns the length of the (null-terminated) @buf string, zero if + * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ -static inline ssize_t +static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), @@ -1155,12 +1309,12 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * - * Returns the length of how many bytes have been copied, excluding + * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; @@ -1176,10 +1330,13 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. + * + * Return: the length of how many bytes have been copied, excluding + * terminating '\0'. */ -static inline ssize_t -cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; diff --git a/include/linux/find.h b/include/linux/find.h index 5e4f39ef2e72c..96b8410a7cf76 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -29,6 +29,10 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); +unsigned long _find_first_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size); +unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, + const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -345,6 +349,54 @@ unsigned long find_first_and_bit(const unsigned long *addr1, } #endif +/** + * find_first_andnot_bit - find the first bit set in 1st memory region and unset in 2nd + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the first set bit + * If no bits are set, returns >= @size. + */ +static __always_inline +unsigned long find_first_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_andnot_bit(addr1, addr2, size); +} + +/** + * find_first_and_and_bit - find the first set bit in 3 memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @addr3: The third address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the first set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_and_bit(addr1, addr2, addr3, size); +} + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5a952d00ea159..0264556d2b58f 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -147,6 +147,11 @@ enum kernfs_root_flag { * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, + + /* + * Renames must not change the parent node. + */ + KERNFS_ROOT_INVARIANT_PARENT = 0x0010, }; /* type-specific structures for kernfs_node union members */ @@ -199,8 +204,8 @@ struct kernfs_node { * never moved to a different parent, it is safe to access the * parent directly. */ - struct kernfs_node *parent; - const char *name; + struct kernfs_node __rcu *__parent; + const char __rcu *name; struct rb_node rb; @@ -318,6 +323,7 @@ struct kernfs_ops { struct poll_table_struct *pt); int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); + loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence); }; /* @@ -394,7 +400,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); -int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, +int kernfs_path_from_node(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); @@ -415,6 +421,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); +unsigned int kernfs_root_flags(struct kernfs_node *kn); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, @@ -513,6 +520,8 @@ kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } +static inline unsigned int kernfs_root_flags(struct kernfs_node *kn) +{ return 0; } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index dd2547601921c..7a5bb93599ca2 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -6,6 +6,11 @@ #include #include #include +#include + +#ifdef CONFIG_ARCH_HAS_CPU_RESCTRL +#include +#endif /* CLOSID, RMID value used by the default control group */ #define RESCTRL_RESERVED_CLOSID 0 @@ -25,6 +30,35 @@ int proc_resctrl_show(struct seq_file *m, /* max value for struct rdt_domain's mbps_val */ #define MBA_MAX_MBPS U32_MAX +/* Walk all possible resources, with variants for only controls or monitors. */ +#define for_each_rdt_resource(_r) \ + for ((_r) = resctrl_arch_get_resource(0); \ + (_r) && (_r)->rid < RDT_NUM_RESOURCES; \ + (_r) = resctrl_arch_get_resource((_r)->rid + 1)) + +#define for_each_capable_rdt_resource(r) \ + for_each_rdt_resource((r)) \ + if ((r)->alloc_capable || (r)->mon_capable) + +#define for_each_alloc_capable_rdt_resource(r) \ + for_each_rdt_resource((r)) \ + if ((r)->alloc_capable) + +#define for_each_mon_capable_rdt_resource(r) \ + for_each_rdt_resource((r)) \ + if ((r)->mon_capable) + +enum resctrl_res_level { + RDT_RESOURCE_L3, + RDT_RESOURCE_L2, + RDT_RESOURCE_MBA, + RDT_RESOURCE_SMBA, + RDT_RESOURCE_PERF_PKG, + + /* Must be the last */ + RDT_NUM_RESOURCES, +}; + /** * enum resctrl_conf_type - The type of configuration. * @CDP_NONE: No prioritisation, both code and data are controlled or monitored. @@ -40,13 +74,42 @@ enum resctrl_conf_type { #define CDP_NUM_TYPES (CDP_DATA + 1) /* - * Event IDs, the values match those used to program IA32_QM_EVTSEL before - * reading IA32_QM_CTR on RDT systems. + * struct pseudo_lock_region - pseudo-lock region information + * @s: Resctrl schema for the resource to which this + * pseudo-locked region belongs + * @closid: The closid that this pseudo-locked region uses + * @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 */ -enum resctrl_event_id { - QOS_L3_OCCUP_EVENT_ID = 0x01, - QOS_L3_MBM_TOTAL_EVENT_ID = 0x02, - QOS_L3_MBM_LOCAL_EVENT_ID = 0x03, +struct pseudo_lock_region { + struct resctrl_schema *s; + u32 closid; + struct rdt_ctrl_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; }; /** @@ -69,15 +132,24 @@ enum resctrl_domain_type { * @list: all instances of this resource * @id: unique id for this instance * @type: type of this instance + * @rid: resource id for this instance * @cpu_mask: which CPUs share this resource */ struct rdt_domain_hdr { struct list_head list; int id; enum resctrl_domain_type type; + enum resctrl_res_level rid; struct cpumask cpu_mask; }; +static inline bool domain_header_is_valid(struct rdt_domain_hdr *hdr, + enum resctrl_domain_type type, + enum resctrl_res_level rid) +{ + return !WARN_ON_ONCE(hdr->type != type || hdr->rid != rid); +} + /** * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource * @hdr: common header for different domain types @@ -95,27 +167,42 @@ struct rdt_ctrl_domain { }; /** - * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource + * struct mbm_cntr_cfg - Assignable counter configuration. + * @evtid: MBM event to which the counter is assigned. Only valid + * if @rdtgroup is not NULL. + * @rdtgrp: resctrl group assigned to the counter. NULL if the + * counter is free. + */ +struct mbm_cntr_cfg { + enum resctrl_event_id evtid; + struct rdtgroup *rdtgrp; +}; + +/** + * struct rdt_l3_mon_domain - group of CPUs sharing RDT_RESOURCE_L3 monitoring * @hdr: common header for different domain types * @ci_id: cache info id for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold - * @mbm_total: saved state for MBM total bandwidth - * @mbm_local: saved state for MBM local bandwidth + * @mbm_states: Per-event pointer to the MBM event's saved state. + * An MBM event's state is an array of struct mbm_state + * indexed by RMID on x86 or combined CLOSID, RMID on Arm. * @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 + * @cntr_cfg: array of assignable counters' configuration (indexed + * by counter ID) */ -struct rdt_mon_domain { +struct rdt_l3_mon_domain { struct rdt_domain_hdr hdr; unsigned int ci_id; unsigned long *rmid_busy_llc; - struct mbm_state *mbm_total; - struct mbm_state *mbm_local; + struct mbm_state *mbm_states[QOS_NUM_L3_MBM_EVENTS]; struct delayed_work mbm_over; struct delayed_work cqm_limbo; int mbm_work_cpu; int cqm_work_cpu; + struct mbm_cntr_cfg *cntr_cfg; }; /** @@ -155,6 +242,7 @@ enum membw_throttle_mode { /** * struct resctrl_membw - Memory bandwidth allocation related data * @min_bw: Minimum memory bandwidth percentage user can request + * @max_bw: Maximum memory bandwidth value, used as the reset value * @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 @@ -165,6 +253,7 @@ enum membw_throttle_mode { */ struct resctrl_membw { u32 min_bw; + u32 max_bw; u32 bw_gran; u32 delay_linear; bool arch_needs_linear; @@ -173,13 +262,38 @@ struct resctrl_membw { u32 *mb_map; }; -struct rdt_parse_data; struct resctrl_schema; enum resctrl_scope { RESCTRL_L2_CACHE = 2, RESCTRL_L3_CACHE = 3, RESCTRL_L3_NODE, + RESCTRL_PACKAGE, +}; + +/** + * enum resctrl_schema_fmt - The format user-space provides for a schema. + * @RESCTRL_SCHEMA_BITMAP: The schema is a bitmap in hex. + * @RESCTRL_SCHEMA_RANGE: The schema is a decimal number. + */ +enum resctrl_schema_fmt { + RESCTRL_SCHEMA_BITMAP, + RESCTRL_SCHEMA_RANGE, +}; + +/** + * struct resctrl_mon - Monitoring related data of a resctrl resource. + * @num_rmid: Number of RMIDs available. + * @mbm_cfg_mask: Memory transactions that can be tracked when bandwidth + * monitoring events can be configured. + * @num_mbm_cntrs: Number of assignable counters. + * @mbm_cntr_assignable:Is system capable of supporting counter assignment? + */ +struct resctrl_mon { + u32 num_rmid; + unsigned int mbm_cfg_mask; + int num_mbm_cntrs; + bool mbm_cntr_assignable; }; /** @@ -187,50 +301,46 @@ enum resctrl_scope { * @rid: The index of the resource * @alloc_capable: Is allocation available on this machine * @mon_capable: Is monitor feature available on this machine - * @num_rmid: Number of RMIDs available * @ctrl_scope: Scope of this resource for control functions * @mon_scope: Scope of this resource for monitor functions * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. + * @mon: Monitoring related data. * @ctrl_domains: RCU list of all control domains for this resource * @mon_domains: RCU list of all monitor domains for this resource * @name: Name to use in "schemata" file. - * @data_width: Character width of data when displaying - * @default_ctrl: Specifies default cache cbm or memory B/W percent. - * @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 - * @fflags: flags to choose base and info files + * @schema_fmt: Which format string and parser is used for this schema. * @cdp_capable: Is the CDP feature available on this resource */ struct rdt_resource { int rid; bool alloc_capable; bool mon_capable; - int num_rmid; enum resctrl_scope ctrl_scope; enum resctrl_scope mon_scope; struct resctrl_cache cache; struct resctrl_membw membw; + struct resctrl_mon mon; struct list_head ctrl_domains; struct list_head mon_domains; char *name; - int data_width; - u32 default_ctrl; - const char *format_str; - int (*parse_ctrlval)(struct rdt_parse_data *data, - struct resctrl_schema *s, - struct rdt_ctrl_domain *d); - struct list_head evt_list; - unsigned long fflags; + enum resctrl_schema_fmt schema_fmt; bool cdp_capable; }; +/* + * Get the resource that exists at this level. If the level is not supported + * a dummy/not-capable resource can be returned. Levels >= RDT_NUM_RESOURCES + * will return NULL. + */ +struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l); + /** * struct resctrl_schema - configuration abilities of a resource presented to * user-space * @list: Member of resctrl_schema_all. * @name: The name to use in the "schemata" file. + * @fmt_str: Format string to show domain value. * @conf_type: Whether this schema is specific to code/data. * @res: The resource structure exported by the architecture to describe * the hardware that is configured by this schema. @@ -241,16 +351,149 @@ struct rdt_resource { struct resctrl_schema { struct list_head list; char name[8]; + const char *fmt_str; enum resctrl_conf_type conf_type; struct rdt_resource *res; u32 num_closid; }; +struct resctrl_cpu_defaults { + u32 closid; + u32 rmid; +}; + +struct resctrl_mon_config_info { + struct rdt_resource *r; + struct rdt_l3_mon_domain *d; + u32 evtid; + u32 mon_config; +}; + +/** + * resctrl_arch_sync_cpu_closid_rmid() - Refresh this CPU's CLOSID and RMID. + * Call via IPI. + * @info: If non-NULL, a pointer to a struct resctrl_cpu_defaults + * specifying the new CLOSID and RMID for tasks in the default + * resctrl ctrl and mon group when running on this CPU. If NULL, + * this CPU is not re-assigned to a different default group. + * + * Propagates reassignment of CPUs and/or tasks to different resctrl groups + * when requested by the resctrl core code. + * + * This function records the per-cpu defaults specified by @info (if any), + * and then reconfigures the CPU's hardware CLOSID and RMID for subsequent + * execution based on @current, in the same way as during a task switch. + */ +void resctrl_arch_sync_cpu_closid_rmid(void *info); + +/** + * resctrl_get_default_ctrl() - Return the default control value for this + * resource. + * @r: The resource whose default control type is queried. + */ +static inline u32 resctrl_get_default_ctrl(struct rdt_resource *r) +{ + switch (r->schema_fmt) { + case RESCTRL_SCHEMA_BITMAP: + return BIT_MASK(r->cache.cbm_len) - 1; + case RESCTRL_SCHEMA_RANGE: + return r->membw.max_bw; + } + + return WARN_ON_ONCE(1); +} + /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); +bool resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, + unsigned int binary_bits, void *arch_priv); + +bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid); + +bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt); + +static inline bool resctrl_is_mbm_event(enum resctrl_event_id eventid) +{ + return (eventid >= QOS_L3_MBM_TOTAL_EVENT_ID && + eventid <= QOS_L3_MBM_LOCAL_EVENT_ID); +} + +u32 resctrl_get_mon_evt_cfg(enum resctrl_event_id eventid); + +/* Iterate over all memory bandwidth events */ +#define for_each_mbm_event_id(eventid) \ + for (eventid = QOS_L3_MBM_TOTAL_EVENT_ID; \ + eventid <= QOS_L3_MBM_LOCAL_EVENT_ID; eventid++) + +/* Iterate over memory bandwidth arrays in domain structures */ +#define for_each_mbm_idx(idx) \ + for (idx = 0; idx < QOS_NUM_L3_MBM_EVENTS; idx++) + +/** + * resctrl_arch_mon_event_config_write() - Write the config for an event. + * @config_info: struct resctrl_mon_config_info describing the resource, domain + * and event. + * + * Reads resource, domain and eventid from @config_info and writes the + * event config_info->mon_config into hardware. + * + * Called via IPI to reach a CPU that is a member of the specified domain. + */ +void resctrl_arch_mon_event_config_write(void *config_info); + +/** + * resctrl_arch_mon_event_config_read() - Read the config for an event. + * @config_info: struct resctrl_mon_config_info describing the resource, domain + * and event. + * + * Reads resource, domain and eventid from @config_info and reads the + * hardware config value into config_info->mon_config. + * + * Called via IPI to reach a CPU that is a member of the specified domain. + */ +void resctrl_arch_mon_event_config_read(void *config_info); + +/* For use by arch code to remap resctrl's smaller CDP CLOSID range */ +static inline u32 resctrl_get_config_index(u32 closid, + enum resctrl_conf_type type) +{ + switch (type) { + default: + case CDP_NONE: + return closid; + case CDP_CODE: + return closid * 2 + 1; + case CDP_DATA: + return closid * 2; + } +} + +bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l); +int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); + +/** + * resctrl_arch_mbm_cntr_assign_enabled() - Check if MBM counter assignment + * mode is enabled. + * @r: Pointer to the resource structure. + * + * Return: + * true if the assignment mode is enabled, false otherwise. + */ +bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r); + +/** + * resctrl_arch_mbm_cntr_assign_set() - Configure the MBM counter assignment mode. + * @r: Pointer to the resource structure. + * @enable: Set to true to enable, false to disable the assignment mode. + * + * Return: + * 0 on success, < 0 on error. + */ +int resctrl_arch_mbm_cntr_assign_set(struct rdt_resource *r, bool enable); + /* * Update the ctrl_val and apply this config right now. * Must be called on one of the domain's CPUs. @@ -261,22 +504,31 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type); int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); -int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr); void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); -void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr); void resctrl_online_cpu(unsigned int cpu); void resctrl_offline_cpu(unsigned int cpu); +/* + * Architecture hook called at beginning of first file system mount attempt. + * No locks are held. + */ +void resctrl_arch_pre_mount(void); + /** * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid * for this resource and domain. * @r: resource that the counter should be read from. - * @d: domain that the counter should be read from. + * @hdr: Header of domain that the counter should be read from. * @closid: closid that matches the rmid. Depending on the architecture, the * counter may match traffic of both @closid and @rmid, or @rmid * only. * @rmid: rmid of the counter to read. * @eventid: eventid to read, e.g. L3 occupancy. + * @arch_priv: Architecture private data for this event. + * The @arch_priv provided by the architecture via + * resctrl_enable_mon_event(). * @val: result of the counter read in bytes. * @arch_mon_ctx: An architecture specific value from * resctrl_arch_mon_ctx_alloc(), for MPAM this identifies @@ -292,9 +544,9 @@ void resctrl_offline_cpu(unsigned int cpu); * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr, u32 closid, u32 rmid, enum resctrl_event_id eventid, - u64 *val, void *arch_mon_ctx); + void *arch_priv, u64 *val, void *arch_mon_ctx); /** * resctrl_arch_rmid_read_context_check() - warn about invalid contexts @@ -313,6 +565,20 @@ static inline void resctrl_arch_rmid_read_context_check(void) might_sleep(); } +/** + * resctrl_find_domain() - Search for a domain id in a resource domain list. + * @h: The domain list to search. + * @id: The domain id to search for. + * @pos: A pointer to position in the list id should be inserted. + * + * Search the domain list to find the domain id. If the domain id is + * found, return the domain. NULL otherwise. If the domain id is not + * found (and NULL returned) then the first domain with id bigger than + * the input id can be returned to the caller via @pos. + */ +struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id, + struct list_head **pos); + /** * resctrl_arch_reset_rmid() - Reset any private state associated with rmid * and eventid. @@ -325,7 +591,7 @@ static inline void resctrl_arch_rmid_read_context_check(void) * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid); @@ -338,9 +604,91 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d); +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d); + +/** + * resctrl_arch_reset_all_ctrls() - Reset the control for each CLOSID to its + * default. + * @r: The resctrl resource to reset. + * + * This can be called from any CPU. + */ +void resctrl_arch_reset_all_ctrls(struct rdt_resource *r); + +/** + * resctrl_arch_config_cntr() - Configure the counter with its new RMID + * and event details. + * @r: Resource structure. + * @d: The domain in which counter with ID @cntr_id should be configured. + * @evtid: Monitoring event type (e.g., QOS_L3_MBM_TOTAL_EVENT_ID + * or QOS_L3_MBM_LOCAL_EVENT_ID). + * @rmid: RMID. + * @closid: CLOSID. + * @cntr_id: Counter ID to configure. + * @assign: True to assign the counter or update an existing assignment, + * false to unassign the counter. + * + * This can be called from any CPU. + */ +void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + enum resctrl_event_id evtid, u32 rmid, u32 closid, + u32 cntr_id, bool assign); + +/** + * resctrl_arch_cntr_read() - Read the event data corresponding to the counter ID + * assigned to the RMID, event pair for this resource + * and domain. + * @r: Resource that the counter should be read from. + * @d: Domain that the counter should be read from. + * @closid: CLOSID that matches the RMID. + * @rmid: The RMID to which @cntr_id is assigned. + * @cntr_id: The counter to read. + * @eventid: The MBM event to which @cntr_id is assigned. + * @val: Result of the counter read in bytes. + * + * Called on a CPU that belongs to domain @d when "mbm_event" mode is enabled. + * Called from a non-migrateable process context via smp_call_on_cpu() unless all + * CPUs are nohz_full, in which case it is called via IPI (smp_call_function_any()). + * + * Return: + * 0 on success, or -EIO, -EINVAL etc on error. + */ +int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + u32 closid, u32 rmid, int cntr_id, + enum resctrl_event_id eventid, u64 *val); + +/** + * resctrl_arch_reset_cntr() - Reset any private state associated with counter ID. + * @r: The domain's resource. + * @d: The counter ID's domain. + * @closid: CLOSID that matches the RMID. + * @rmid: The RMID to which @cntr_id is assigned. + * @cntr_id: The counter to reset. + * @eventid: The MBM event to which @cntr_id is assigned. + * + * This can be called from any CPU. + */ +void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d, + u32 closid, u32 rmid, int cntr_id, + enum resctrl_event_id eventid); extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; +int resctrl_init(void); +void resctrl_exit(void); + +#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK +u64 resctrl_arch_get_prefetch_disable_bits(void); +int resctrl_arch_pseudo_lock_fn(void *_plr); +int resctrl_arch_measure_cycles_lat_fn(void *_plr); +int resctrl_arch_measure_l2_residency(void *_plr); +int resctrl_arch_measure_l3_residency(void *_plr); +#else +static inline u64 resctrl_arch_get_prefetch_disable_bits(void) { return 0; } +static inline int resctrl_arch_pseudo_lock_fn(void *_plr) { return 0; } +static inline int resctrl_arch_measure_cycles_lat_fn(void *_plr) { return 0; } +static inline int resctrl_arch_measure_l2_residency(void *_plr) { return 0; } +static inline int resctrl_arch_measure_l3_residency(void *_plr) { return 0; } +#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */ #endif /* _RESCTRL_H */ diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h new file mode 100644 index 0000000000000..6838b02d5ca3a --- /dev/null +++ b/include/linux/resctrl_types.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Arm Ltd. + * Based on arch/x86/kernel/cpu/resctrl/internal.h + */ + +#ifndef __LINUX_RESCTRL_TYPES_H +#define __LINUX_RESCTRL_TYPES_H + +#define MAX_MBA_BW 100u +#define MBM_OVERFLOW_INTERVAL 1000 + +/* Reads to Local DRAM Memory */ +#define READS_TO_LOCAL_MEM BIT(0) + +/* Reads to Remote DRAM Memory */ +#define READS_TO_REMOTE_MEM BIT(1) + +/* Non-Temporal Writes to Local Memory */ +#define NON_TEMP_WRITE_TO_LOCAL_MEM BIT(2) + +/* Non-Temporal Writes to Remote Memory */ +#define NON_TEMP_WRITE_TO_REMOTE_MEM BIT(3) + +/* Reads to Local Memory the system identifies as "Slow Memory" */ +#define READS_TO_LOCAL_S_MEM BIT(4) + +/* Reads to Remote Memory the system identifies as "Slow Memory" */ +#define READS_TO_REMOTE_S_MEM BIT(5) + +/* Dirty Victims to All Types of Memory */ +#define DIRTY_VICTIMS_TO_ALL_MEM BIT(6) + +/* Max event bits supported */ +#define MAX_EVT_CONFIG_BITS GENMASK(6, 0) + +/* Event IDs */ +enum resctrl_event_id { + /* Must match value of first event below */ + QOS_FIRST_EVENT = 0x01, + + /* + * These values match those used to program IA32_QM_EVTSEL before + * reading IA32_QM_CTR on RDT systems. + */ + QOS_L3_OCCUP_EVENT_ID = 0x01, + QOS_L3_MBM_TOTAL_EVENT_ID = 0x02, + QOS_L3_MBM_LOCAL_EVENT_ID = 0x03, + + /* Intel Telemetry Events */ + PMT_EVENT_ENERGY, + PMT_EVENT_ACTIVITY, + PMT_EVENT_STALLS_LLC_HIT, + PMT_EVENT_C1_RES, + PMT_EVENT_UNHALTED_CORE_CYCLES, + PMT_EVENT_STALLS_LLC_MISS, + PMT_EVENT_AUTO_C6_RES, + PMT_EVENT_UNHALTED_REF_CYCLES, + PMT_EVENT_UOPS_RETIRED, + + /* Must be the last */ + QOS_NUM_EVENTS, +}; + +#define QOS_NUM_L3_MBM_EVENTS (QOS_L3_MBM_LOCAL_EVENT_ID - QOS_L3_MBM_TOTAL_EVENT_ID + 1) +#define MBM_STATE_IDX(evt) ((evt) - QOS_L3_MBM_TOTAL_EVENT_ID) + +#endif /* __LINUX_RESCTRL_TYPES_H */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 2bbf0057322f5..a42642b277dd0 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -220,6 +220,8 @@ struct bin_attribute { char *, loff_t, size_t); ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); + loff_t (*llseek)(struct file *, struct kobject *, struct bin_attribute *, + loff_t, int); int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, struct vm_area_struct *vma); }; diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 2588543c8e4ae..bab4c6b408ef4 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -836,7 +836,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; - if (kn->parent != new_parent) + if (rcu_access_pointer(kn->__parent) != new_parent) return -EIO; /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 9c980cae478eb..fbd0fc56c70f9 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -654,9 +654,22 @@ int cgroup_task_count(const struct cgroup *cgrp) return count; } +static struct cgroup *kn_priv(struct kernfs_node *kn) +{ + struct kernfs_node *parent; + /* + * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT. + * Therefore it is always safe to dereference this pointer outside of a + * RCU section. + */ + parent = rcu_dereference_check(kn->__parent, + kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT); + return parent->priv; +} + struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { - struct cgroup *cgrp = of->kn->parent->priv; + struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); /* @@ -1631,7 +1644,7 @@ void cgroup_kn_unlock(struct kernfs_node *kn) if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else - cgrp = kn->parent->priv; + cgrp = kn_priv(kn); cgroup_unlock(); @@ -1663,7 +1676,7 @@ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else - cgrp = kn->parent->priv; + cgrp = kn_priv(kn); /* * We're gonna grab cgroup_mutex which nests outside kernfs @@ -2101,7 +2114,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | - KERNFS_ROOT_SUPPORT_USER_XATTR, + KERNFS_ROOT_SUPPORT_USER_XATTR | + KERNFS_ROOT_INVARIANT_PARENT, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); @@ -4076,7 +4090,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; - struct cgroup *cgrp = of->kn->parent->priv; + struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; diff --git a/lib/bitmap.c b/lib/bitmap.c index ddb31015e38ae..4bd5fb263b1d9 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -359,6 +359,13 @@ unsigned int __bitmap_weight_and(const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_weight_and); +unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits); +} +EXPORT_SYMBOL(__bitmap_weight_andnot); + void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); diff --git a/lib/cpumask.c b/lib/cpumask.c index 34335c1e72653..e77ee9d46f71b 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -14,7 +14,7 @@ * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * - * Returns >= nr_cpu_ids on completion + * Return: >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. @@ -48,8 +48,9 @@ EXPORT_SYMBOL(cpumask_next_wrap); * @node: memory node from which to allocate or %NUMA_NO_NODE * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is - * a nop returning a constant 1 (in ) - * Returns TRUE if memory allocation succeeded, FALSE otherwise. + * a nop returning a constant 1 (in ). + * + * Return: TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if @@ -115,7 +116,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) * @i: index number * @node: local numa_node * - * Returns online CPU according to a numa aware policy; local cpus are returned + * Return: online CPU according to a numa aware policy; local cpus are returned * first, followed by non-local ones, then it wraps around. * * For those who wants to enumerate all CPUs based on their NUMA distances, @@ -163,7 +164,7 @@ static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. * - * Returns >= nr_cpu_ids if the intersection is empty. + * Return: >= nr_cpu_ids if the intersection is empty. */ unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) @@ -182,6 +183,12 @@ unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, } EXPORT_SYMBOL(cpumask_any_and_distribute); +/** + * cpumask_any_distribute - Return an arbitrary cpu from srcp + * @srcp: &cpumask for selection + * + * Return: >= nr_cpu_ids if the intersection is empty. + */ unsigned int cpumask_any_distribute(const struct cpumask *srcp) { unsigned int next, prev; diff --git a/lib/find_bit.c b/lib/find_bit.c index 32f99e9a670e6..79c36041694a8 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -116,6 +116,29 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, EXPORT_SYMBOL(_find_first_and_bit); #endif +/* + * Find the first bit set in 1st memory region and unset in 2nd. + */ +unsigned long _find_first_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + return FIND_FIRST_BIT(addr1[idx] & ~addr2[idx], /* nop */, size); +} +EXPORT_SYMBOL(_find_first_andnot_bit); + +/* + * Find the first set bit in three memory regions. + */ +unsigned long _find_first_and_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size) +{ + return FIND_FIRST_BIT(addr1[idx] & addr2[idx] & addr3[idx], /* nop */, size); +} +EXPORT_SYMBOL(_find_first_and_and_bit); + #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e82113fc85b5c..757ff227d61d4 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3591,10 +3591,13 @@ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, newsid = tsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); + const char *kn_name; struct qstr q; - q.name = kn->name; - q.hash_len = hashlen_string(kn_dir, kn->name); + /* kn is fresh, can't be renamed, name goes not away */ + kn_name = rcu_dereference_check(kn->name, true); + q.name = kn_name; + q.hash_len = hashlen_string(kn_dir, kn_name); rc = security_transition_sid(tsec->sid, parent_sid, secclass, &q, diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index f799d87e87002..cf5d64af07cf4 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -225,7 +225,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, barrier_var(filepart_length); payload += filepart_length; } - cgroup_node = BPF_CORE_READ(cgroup_node, parent); + cgroup_node = BPF_CORE_READ(cgroup_node, __parent); } return payload; } diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index ad7b97e16f37e..5cc84e0e78617 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -57,6 +57,7 @@ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #endif +#if defined(__i386__) || defined(__x86_64__) /* arch */ /* * gcc cpuid.h provides __cpuid_count() since v4.4. * Clang/LLVM cpuid.h provides __cpuid_count() since v3.4.0. @@ -71,6 +72,7 @@ : "=a" (a), "=b" (b), "=c" (c), "=d" (d) \ : "0" (level), "2" (count)) #endif +#endif /* end arch */ /* define kselftest exit codes */ #define KSFT_PASS 0 diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index 021863f86053a..bad806e0a4f4e 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -8,5 +8,6 @@ TEST_GEN_PROGS := resctrl_tests LOCAL_HDRS += $(wildcard *.h) include ../lib.mk +CFLAGS += -I$(top_srcdir)/tools/include $(OUTPUT)/resctrl_tests: $(wildcard *.c) diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 601ab78dbf421..df9bea584a2d4 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -3,106 +3,52 @@ #include #include "resctrl.h" -struct read_format { - __u64 nr; /* The number of events */ - struct { - __u64 value; /* The value of the event */ - } values[2]; -}; - -static struct perf_event_attr pea_llc_miss; -static struct read_format rf_cqm; -static int fd_lm; char llc_occup_path[1024]; -static void initialize_perf_event_attr(void) -{ - pea_llc_miss.type = PERF_TYPE_HARDWARE; - pea_llc_miss.size = sizeof(struct perf_event_attr); - pea_llc_miss.read_format = PERF_FORMAT_GROUP; - pea_llc_miss.exclude_kernel = 1; - pea_llc_miss.exclude_hv = 1; - pea_llc_miss.exclude_idle = 1; - pea_llc_miss.exclude_callchain_kernel = 1; - pea_llc_miss.inherit = 1; - pea_llc_miss.exclude_guest = 1; - pea_llc_miss.disabled = 1; -} - -static void ioctl_perf_event_ioc_reset_enable(void) -{ - ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0); - ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0); -} - -static int perf_event_open_llc_miss(pid_t pid, int cpu_no) -{ - fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, - PERF_FLAG_FD_CLOEXEC); - if (fd_lm == -1) { - ksft_perror("Error opening leader"); - ctrlc_handler(0, NULL, NULL); - return -1; - } - - return 0; -} - -static void initialize_llc_perf(void) +void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config) { - memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); - memset(&rf_cqm, 0, sizeof(struct read_format)); - - /* Initialize perf_event_attr structures for HW_CACHE_MISSES */ - initialize_perf_event_attr(); - - pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES; - - rf_cqm.nr = 1; + memset(pea, 0, sizeof(*pea)); + pea->type = PERF_TYPE_HARDWARE; + pea->size = sizeof(*pea); + pea->exclude_kernel = 1; + pea->exclude_hv = 1; + pea->exclude_idle = 1; + pea->exclude_callchain_kernel = 1; + pea->inherit = 1; + pea->exclude_guest = 1; + pea->disabled = 1; + pea->config = config; } -static int reset_enable_llc_perf(pid_t pid, int cpu_no) +/* Start counters to log values */ +int perf_event_reset_enable(int pe_fd) { - int ret = 0; + int ret; - ret = perf_event_open_llc_miss(pid, cpu_no); + ret = ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0); if (ret < 0) return ret; - /* Start counters to log values */ - ioctl_perf_event_ioc_reset_enable(); + ret = ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0); + if (ret < 0) + return ret; return 0; } -/* - * get_llc_perf: llc cache miss through perf events - * @llc_perf_miss: LLC miss counter that is filled on success - * - * Perf events like HW_CACHE_MISSES could be used to validate number of - * cache lines allocated. - * - * Return: =0 on success. <0 on failure. - */ -static int get_llc_perf(unsigned long *llc_perf_miss) +int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no) { - __u64 total_misses; - int ret; + int pe_fd; - /* Stop counters after one span to get miss rate */ - - ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0); - - ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); - if (ret == -1) { - ksft_perror("Could not get llc misses through perf"); + pe_fd = perf_event_open(pea, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); + if (pe_fd == -1) { + ksft_perror("Unable to set up performance monitoring"); return -1; } - total_misses = rf_cqm.values[0].value; - *llc_perf_miss = total_misses; + perf_event_reset_enable(pe_fd); - return 0; + return pe_fd; } /* @@ -126,7 +72,7 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy) if (!fp) { ksft_perror("Failed to open results file"); - return errno; + return -1; } if (fscanf(fp, "%lu", llc_occupancy) <= 0) { ksft_perror("Could not get llc occupancy"); @@ -146,163 +92,104 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy) * @llc_value: perf miss value / * llc occupancy value reported by resctrl FS * - * Return: 0 on success. non-zero on failure. + * Return: 0 on success, < 0 on error. */ -static int print_results_cache(char *filename, int bm_pid, - unsigned long llc_value) +static int print_results_cache(const char *filename, pid_t bm_pid, __u64 llc_value) { FILE *fp; if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) { - printf("Pid: %d \t LLC_value: %lu\n", bm_pid, - llc_value); + printf("Pid: %d \t LLC_value: %llu\n", (int)bm_pid, llc_value); } else { fp = fopen(filename, "a"); if (!fp) { ksft_perror("Cannot open results file"); - return errno; + return -1; } - fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value); + fprintf(fp, "Pid: %d \t llc_value: %llu\n", (int)bm_pid, llc_value); fclose(fp); } return 0; } -int measure_cache_vals(struct resctrl_val_param *param, int bm_pid) +/* + * perf_event_measure - Measure perf events + * @filename: Filename for writing the results + * @bm_pid: PID that runs the benchmark + * + * Measures perf events (e.g., cache misses) and writes the results into + * @filename. @bm_pid is written to the results file along with the measured + * value. + * + * Return: =0 on success. <0 on failure. + */ +int perf_event_measure(int pe_fd, const char *filename, pid_t bm_pid) { - unsigned long llc_perf_miss = 0, llc_occu_resc = 0, llc_value = 0; + __u64 value; int ret; - /* - * Measure cache miss from perf. - */ - if (!strncmp(param->resctrl_val, CAT_STR, sizeof(CAT_STR))) { - ret = get_llc_perf(&llc_perf_miss); - if (ret < 0) - return ret; - llc_value = llc_perf_miss; - } + /* Stop counters after one span to get miss rate */ + ret = ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0); + if (ret < 0) + return ret; - /* - * Measure llc occupancy from resctrl. - */ - if (!strncmp(param->resctrl_val, CMT_STR, sizeof(CMT_STR))) { - ret = get_llc_occu_resctrl(&llc_occu_resc); - if (ret < 0) - return ret; - llc_value = llc_occu_resc; + ret = read(pe_fd, &value, sizeof(value)); + if (ret == -1) { + ksft_perror("Could not get perf value"); + return -1; } - ret = print_results_cache(param->filename, bm_pid, llc_value); - if (ret) - return ret; - return 0; + return print_results_cache(filename, bm_pid, value); } /* - * cache_val: execute benchmark and measure LLC occupancy resctrl - * and perf cache miss for the benchmark - * @param: parameters passed to cache_val() - * @span: buffer size for the benchmark + * measure_llc_resctrl - Measure resctrl LLC value from resctrl + * @filename: Filename for writing the results + * @bm_pid: PID that runs the benchmark * - * Return: 0 on success. non-zero on failure. + * Measures LLC occupancy from resctrl and writes the results into @filename. + * @bm_pid is written to the results file along with the measured value. + * + * Return: =0 on success. <0 on failure. */ -int cat_val(struct resctrl_val_param *param, size_t span) +int measure_llc_resctrl(const char *filename, pid_t bm_pid) { - int memflush = 1, operation = 0, ret = 0; - char *resctrl_val = param->resctrl_val; - pid_t bm_pid; - - if (strcmp(param->filename, "") == 0) - sprintf(param->filename, "stdio"); - - bm_pid = getpid(); - - /* Taskset benchmark to specified cpu */ - ret = taskset_benchmark(bm_pid, param->cpu_no); - if (ret) - return ret; + unsigned long llc_occu_resc = 0; + int ret; - /* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/ - ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, - resctrl_val); - if (ret) + ret = get_llc_occu_resctrl(&llc_occu_resc); + if (ret < 0) return ret; - initialize_llc_perf(); - - /* Test runs until the callback setup() tells the test to stop. */ - while (1) { - ret = param->setup(param); - if (ret == END_OF_TESTS) { - ret = 0; - break; - } - if (ret < 0) - break; - ret = reset_enable_llc_perf(bm_pid, param->cpu_no); - if (ret) - break; - - if (run_fill_buf(span, memflush, operation, true)) { - fprintf(stderr, "Error-running fill buffer\n"); - ret = -1; - goto pe_close; - } - - sleep(1); - ret = measure_cache_vals(param, bm_pid); - if (ret) - goto pe_close; - } - - return ret; - -pe_close: - close(fd_lm); - return ret; + return print_results_cache(filename, bm_pid, llc_occu_resc); } /* - * show_cache_info: show cache test result information - * @sum_llc_val: sum of LLC cache result data - * @no_of_bits: number of bits - * @cache_span: cache span in bytes for CMT or in lines for CAT - * @max_diff: max difference - * @max_diff_percent: max difference percentage - * @num_of_runs: number of runs - * @platform: show test information on this platform - * @cmt: CMT test or CAT test - * - * Return: 0 on success. non-zero on failure. + * Reduce L2 allocation to minimum when testing L3 cache allocation. */ -int show_cache_info(unsigned long sum_llc_val, int no_of_bits, - size_t cache_span, unsigned long max_diff, - unsigned long max_diff_percent, unsigned long num_of_runs, - bool platform, bool cmt) +int minimize_l2_occupancy(const struct resctrl_test *test, + const struct user_params *uparams, + const struct resctrl_val_param *param) { - unsigned long avg_llc_val = 0; - float diff_percent; - long avg_diff = 0; - int ret; + if (!strcmp(test->resource, "L3") && resctrl_resource_exists("L2")) + return write_schemata(param->ctrlgrp, "0x1", uparams->cpu, "L2"); - avg_llc_val = sum_llc_val / num_of_runs; - avg_diff = (long)abs(cache_span - avg_llc_val); - diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; - - ret = platform && abs((int)diff_percent) > max_diff_percent && - (cmt ? (abs(avg_diff) > max_diff) : true); - - ksft_print_msg("%s Check cache miss rate within %d%%\n", - ret ? "Fail:" : "Pass:", max_diff_percent); + return 0; +} - ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); +/* + * show_cache_info - Show generic cache test information + * @no_of_bits: Number of bits + * @avg_llc_val: Average of LLC cache result data + * @cache_span: Cache span + * @lines: @cache_span in lines or bytes + */ +void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines) +{ ksft_print_msg("Number of bits: %d\n", no_of_bits); - ksft_print_msg("Average LLC val: %lu\n", avg_llc_val); - ksft_print_msg("Cache span (%s): %zu\n", cmt ? "bytes" : "lines", + ksft_print_msg("Average LLC val: %llu\n", avg_llc_val); + ksft_print_msg("Cache span (%s): %zu\n", lines ? "lines" : "bytes", cache_span); - - return ret; } diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 9bb8ba93f4335..371a2f26dc47b 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -11,41 +11,48 @@ #include "resctrl.h" #include -#define RESULT_FILE_NAME1 "result_cat1" -#define RESULT_FILE_NAME2 "result_cat2" +#define RESULT_FILE_NAME "result_cat" #define NUM_OF_RUNS 5 -#define MAX_DIFF_PERCENT 4 -#define MAX_DIFF 1000000 -/* - * Change schemata. Write schemata to specified - * con_mon grp, mon_grp in resctrl FS. - * Run 5 times in order to get average values. - */ -static int cat_setup(struct resctrl_val_param *p) +static int show_results_info(__u64 sum_llc_val, int no_of_bits, + unsigned long cache_span, + unsigned long num_of_runs, bool platform, + __s64 *prev_avg_llc_val) { - char schemata[64]; + __u64 avg_llc_val = 0; int ret = 0; - /* Run NUM_OF_RUNS times */ - if (p->num_of_runs >= NUM_OF_RUNS) - return END_OF_TESTS; + avg_llc_val = sum_llc_val / num_of_runs; + if (*prev_avg_llc_val) { + ret = platform && (avg_llc_val < *prev_avg_llc_val); - if (p->num_of_runs == 0) { - sprintf(schemata, "%lx", p->mask); - ret = write_schemata(p->ctrlgrp, schemata, p->cpu_no, - p->resctrl_val); + ksft_print_msg("%s Check cache miss rate increased\n", + ret ? "Fail:" : "Pass:"); } - p->num_of_runs++; + *prev_avg_llc_val = avg_llc_val; + + show_cache_info(no_of_bits, avg_llc_val, cache_span, true); return ret; } -static int check_results(struct resctrl_val_param *param, size_t span) +/* Remove the highest bits from CBM */ +static unsigned long next_mask(unsigned long current_mask) +{ + return current_mask & (current_mask >> 2); +} + +static int check_results(struct resctrl_val_param *param, const char *cache_type, + unsigned long cache_total_size, unsigned long full_cache_mask, + unsigned long current_mask) { char *token_array[8], temp[512]; - unsigned long sum_llc_perf_miss = 0; - int runs = 0, no_of_bits = 0; + __u64 sum_llc_perf_miss = 0; + __s64 prev_avg_llc_val = 0; + unsigned long alloc_size; + int runs = 0; + int fail = 0; + int ret; FILE *fp; ksft_print_msg("Checking for pass/fail\n"); @@ -53,66 +60,182 @@ static int check_results(struct resctrl_val_param *param, size_t span) if (!fp) { ksft_perror("Cannot open file"); - return errno; + return -1; } while (fgets(temp, sizeof(temp), fp)) { char *token = strtok(temp, ":\t"); int fields = 0; + int bits; while (token) { token_array[fields++] = token; token = strtok(NULL, ":\t"); } - /* - * Discard the first value which is inaccurate due to monitoring - * setup transition phase. - */ - if (runs > 0) - sum_llc_perf_miss += strtoul(token_array[3], NULL, 0); + + sum_llc_perf_miss += strtoull(token_array[3], NULL, 0); runs++; + + if (runs < NUM_OF_RUNS) + continue; + + if (!current_mask) { + ksft_print_msg("Unexpected empty cache mask\n"); + break; + } + + alloc_size = cache_portion_size(cache_total_size, current_mask, full_cache_mask); + + bits = count_bits(current_mask); + + ret = show_results_info(sum_llc_perf_miss, bits, + alloc_size / 64, + runs, get_vendor() == ARCH_INTEL, + &prev_avg_llc_val); + if (ret) + fail = 1; + + runs = 0; + sum_llc_perf_miss = 0; + current_mask = next_mask(current_mask); } fclose(fp); - no_of_bits = count_bits(param->mask); - return show_cache_info(sum_llc_perf_miss, no_of_bits, span / 64, - MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, - get_vendor() == ARCH_INTEL, false); + return fail; +} + +static void cat_test_cleanup(void) +{ + remove(RESULT_FILE_NAME); } -void cat_test_cleanup(void) +/* + * cat_test - Execute CAT benchmark and measure cache misses + * @test: Test information structure + * @uparams: User supplied parameters + * @param: Parameters passed to cat_test() + * @span: Buffer size for the benchmark + * @current_mask Start mask for the first iteration + * + * Run CAT selftest by varying the allocated cache portion and comparing the + * impact on cache misses (the result analysis is done in check_results() + * and show_results_info(), not in this function). + * + * One bit is removed from the CAT allocation bit mask (in current_mask) for + * each subsequent test which keeps reducing the size of the allocated cache + * portion. A single test flushes the buffer, reads it to warm up the cache, + * and reads the buffer again. The cache misses are measured during the last + * read pass. + * + * Return: 0 when the test was run, < 0 on error. + */ +static int cat_test(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *param, + size_t span, unsigned long current_mask) { - remove(RESULT_FILE_NAME1); - remove(RESULT_FILE_NAME2); + struct perf_event_attr pea; + cpu_set_t old_affinity; + unsigned char *buf; + char schemata[64]; + int ret, i, pe_fd; + pid_t bm_pid; + + if (strcmp(param->filename, "") == 0) + sprintf(param->filename, "stdio"); + + bm_pid = getpid(); + + /* Taskset benchmark to specified cpu */ + ret = taskset_benchmark(bm_pid, uparams->cpu, &old_affinity); + if (ret) + return ret; + + /* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/ + ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp); + if (ret) + goto reset_affinity; + + ret = minimize_l2_occupancy(test, uparams, param); + if (ret) + goto reset_affinity; + + perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES); + pe_fd = perf_open(&pea, bm_pid, uparams->cpu); + if (pe_fd < 0) { + ret = -1; + goto reset_affinity; + } + + buf = alloc_buffer(span, 1); + if (!buf) { + ret = -1; + goto pe_close; + } + + while (current_mask) { + snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret) + goto free_buf; + snprintf(schemata, sizeof(schemata), "%lx", current_mask); + ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource); + if (ret) + goto free_buf; + + for (i = 0; i < NUM_OF_RUNS; i++) { + mem_flush(buf, span); + fill_cache_read(buf, span, true); + + ret = perf_event_reset_enable(pe_fd); + if (ret) + goto free_buf; + + fill_cache_read(buf, span, true); + + ret = perf_event_measure(pe_fd, param->filename, bm_pid); + if (ret) + goto free_buf; + } + current_mask = next_mask(current_mask); + } + +free_buf: + free(buf); +pe_close: + close(pe_fd); +reset_affinity: + taskset_restore(bm_pid, &old_affinity); + + return ret; } -int cat_perf_miss_val(int cpu_no, int n, char *cache_type) +static int cat_run_test(const struct resctrl_test *test, const struct user_params *uparams) { - unsigned long l_mask, l_mask_1; - int ret, pipefd[2], sibling_cpu_no; - unsigned long cache_size = 0; - unsigned long long_mask; - char cbm_mask[256]; + unsigned long long_mask, start_mask, full_cache_mask; + unsigned long cache_total_size = 0; + int n = uparams->bits; + unsigned int start; int count_of_bits; - char pipe_message; size_t span; + int ret; - /* Get default cbm mask for L3/L2 cache */ - ret = get_cbm_mask(cache_type, cbm_mask); + ret = get_full_cbm(test->resource, &full_cache_mask); + if (ret) + return ret; + /* Get the largest contiguous exclusive portion of the cache */ + ret = get_mask_no_shareable(test->resource, &long_mask); if (ret) return ret; - - long_mask = strtoul(cbm_mask, NULL, 16); /* Get L3/L2 cache size */ - ret = get_cache_size(cpu_no, cache_type, &cache_size); + ret = get_cache_size(uparams->cpu, test->resource, &cache_total_size); if (ret) return ret; - ksft_print_msg("Cache size :%lu\n", cache_size); + ksft_print_msg("Cache size :%lu\n", cache_total_size); - /* Get max number of bits from default-cabm mask */ - count_of_bits = count_bits(long_mask); + count_of_bits = count_contiguous_bits(long_mask, &start); if (!n) n = count_of_bits / 2; @@ -123,89 +246,138 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) count_of_bits - 1); return -1; } - - /* Get core id from same socket for running another thread */ - sibling_cpu_no = get_core_sibling(cpu_no); - if (sibling_cpu_no < 0) - return -1; + start_mask = create_bit_mask(start, n); struct resctrl_val_param param = { - .resctrl_val = CAT_STR, - .cpu_no = cpu_no, - .setup = cat_setup, + .ctrlgrp = "c1", + .filename = RESULT_FILE_NAME, + .num_of_runs = 0, }; + param.mask = long_mask; + span = cache_portion_size(cache_total_size, start_mask, full_cache_mask); - l_mask = long_mask >> n; - l_mask_1 = ~l_mask & long_mask; + remove(param.filename); - /* Set param values for parent thread which will be allocated bitmask - * with (max_bits - n) bits - */ - span = cache_size * (count_of_bits - n) / count_of_bits; - strcpy(param.ctrlgrp, "c2"); - strcpy(param.mongrp, "m2"); - strcpy(param.filename, RESULT_FILE_NAME2); - param.mask = l_mask; - param.num_of_runs = 0; - - if (pipe(pipefd)) { - ksft_perror("Unable to create pipe"); - return errno; - } + ret = cat_test(test, uparams, ¶m, span, start_mask); + if (ret) + return ret; - fflush(stdout); - bm_pid = fork(); + ret = check_results(¶m, test->resource, + cache_total_size, full_cache_mask, start_mask); + return ret; +} - /* Set param values for child thread which will be allocated bitmask - * with n bits - */ - if (bm_pid == 0) { - param.mask = l_mask_1; - strcpy(param.ctrlgrp, "c1"); - strcpy(param.mongrp, "m1"); - span = cache_size * n / count_of_bits; - strcpy(param.filename, RESULT_FILE_NAME1); - param.num_of_runs = 0; - param.cpu_no = sibling_cpu_no; +static bool arch_supports_noncont_cat(const struct resctrl_test *test) +{ + unsigned int vendor_id = get_vendor(); + + /* AMD and Hygon always support non-contiguous CBM. */ + if (vendor_id == ARCH_AMD || vendor_id == ARCH_HYGON) + return true; + +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax, ebx, ecx, edx; + /* Intel support for non-contiguous CBM needs to be discovered. */ + if (!strcmp(test->resource, "L3")) + __cpuid_count(0x10, 1, eax, ebx, ecx, edx); + else if (!strcmp(test->resource, "L2")) + __cpuid_count(0x10, 2, eax, ebx, ecx, edx); + else + return false; + + return ((ecx >> 3) & 1); +#endif /* end arch */ + + return false; +} + +static int noncont_cat_run_test(const struct resctrl_test *test, + const struct user_params *uparams) +{ + unsigned long full_cache_mask, cont_mask, noncont_mask; + unsigned int sparse_masks; + int bit_center, ret; + char schemata[64]; + + /* Check to compare sparse_masks content to CPUID output. */ + ret = resource_info_unsigned_get(test->resource, "sparse_masks", &sparse_masks); + if (ret) + return ret; + + if (arch_supports_noncont_cat(test) != sparse_masks) { + ksft_print_msg("Hardware and kernel differ on non-contiguous CBM support!\n"); + return 1; } - remove(param.filename); + /* Write checks initialization. */ + ret = get_full_cbm(test->resource, &full_cache_mask); + if (ret < 0) + return ret; + bit_center = count_bits(full_cache_mask) / 2; - ret = cat_val(¶m, span); - if (ret == 0) - ret = check_results(¶m, span); - - if (bm_pid == 0) { - /* Tell parent that child is ready */ - close(pipefd[0]); - pipe_message = 1; - if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) < - sizeof(pipe_message)) - /* - * Just print the error message. - * Let while(1) run and wait for itself to be killed. - */ - ksft_perror("Failed signaling parent process"); - - close(pipefd[1]); - while (1) - ; - } else { - /* Parent waits for child to be ready. */ - close(pipefd[1]); - pipe_message = 0; - while (pipe_message != 1) { - if (read(pipefd[0], &pipe_message, - sizeof(pipe_message)) < sizeof(pipe_message)) { - ksft_perror("Failed reading from child process"); - break; - } - } - close(pipefd[0]); - kill(bm_pid, SIGKILL); + /* + * The bit_center needs to be at least 3 to properly calculate the CBM + * hole in the noncont_mask. If it's smaller return an error since the + * cache mask is too short and that shouldn't happen. + */ + if (bit_center < 3) + return -EINVAL; + cont_mask = full_cache_mask >> bit_center; + + /* Contiguous mask write check. */ + snprintf(schemata, sizeof(schemata), "%lx", cont_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret) { + ksft_print_msg("Write of contiguous CBM failed\n"); + return 1; } - cat_test_cleanup(); + /* + * Non-contiguous mask write check. CBM has a 0xf hole approximately in the middle. + * Output is compared with support information to catch any edge case errors. + */ + noncont_mask = ~(0xfUL << (bit_center - 2)) & full_cache_mask; + snprintf(schemata, sizeof(schemata), "%lx", noncont_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret && sparse_masks) + ksft_print_msg("Non-contiguous CBMs supported but write of non-contiguous CBM failed\n"); + else if (ret && !sparse_masks) + ksft_print_msg("Non-contiguous CBMs not supported and write of non-contiguous CBM failed as expected\n"); + else if (!ret && !sparse_masks) + ksft_print_msg("Non-contiguous CBMs not supported but write of non-contiguous CBM succeeded\n"); + + return !ret == !sparse_masks; +} - return ret; +static bool noncont_cat_feature_check(const struct resctrl_test *test) +{ + if (!resctrl_resource_exists(test->resource)) + return false; + + return resource_info_file_exists(test->resource, "sparse_masks"); } + +struct resctrl_test l3_cat_test = { + .name = "L3_CAT", + .group = "CAT", + .resource = "L3", + .feature_check = test_resource_feature_check, + .run_test = cat_run_test, + .cleanup = cat_test_cleanup, +}; + +struct resctrl_test l3_noncont_cat_test = { + .name = "L3_NONCONT_CAT", + .group = "CAT", + .resource = "L3", + .feature_check = noncont_cat_feature_check, + .run_test = noncont_cat_run_test, +}; + +struct resctrl_test l2_noncont_cat_test = { + .name = "L2_NONCONT_CAT", + .group = "CAT", + .resource = "L2", + .feature_check = noncont_cat_feature_check, + .run_test = noncont_cat_run_test, +}; diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 16fc0488e0a54..ccb6fe881a948 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -16,7 +16,48 @@ #define MAX_DIFF 2000000 #define MAX_DIFF_PERCENT 15 -static int cmt_setup(struct resctrl_val_param *p) +#define CON_MON_LCC_OCCUP_PATH \ + "%s/%s/mon_data/mon_L3_%02d/llc_occupancy" + +/* + * Initialize capacity bitmasks (CBMs) of: + * - control group being tested per test parameters, + * - default resource group as inverse of control group being tested to prevent + * other tasks from interfering with test, + * - L2 resource of control group being tested to minimize allocations into + * L2 if possible to better predict L3 occupancy. + */ +static int cmt_init(const struct resctrl_test *test, + const struct user_params *uparams, + const struct resctrl_val_param *param, int domain_id) +{ + unsigned long full_mask; + char schemata[64]; + int ret; + + sprintf(llc_occup_path, CON_MON_LCC_OCCUP_PATH, RESCTRL_PATH, + param->ctrlgrp, domain_id); + + ret = get_full_cbm(test->resource, &full_mask); + if (ret) + return ret; + + snprintf(schemata, sizeof(schemata), "%lx", ~param->mask & full_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret) + return ret; + + snprintf(schemata, sizeof(schemata), "%lx", param->mask); + ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource); + if (ret) + return ret; + + return minimize_l2_occupancy(test, uparams, param); +} + +static int cmt_setup(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *p) { /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) @@ -27,6 +68,40 @@ static int cmt_setup(struct resctrl_val_param *p) return 0; } +static int cmt_measure(const struct user_params *uparams, + struct resctrl_val_param *param, pid_t bm_pid) +{ + sleep(1); + return measure_llc_resctrl(param->filename, bm_pid); +} + +static int show_results_info(unsigned long sum_llc_val, int no_of_bits, + unsigned long cache_span, unsigned long max_diff, + unsigned long max_diff_percent, unsigned long num_of_runs, + bool platform) +{ + unsigned long avg_llc_val = 0; + float diff_percent; + long avg_diff = 0; + int ret; + + avg_llc_val = sum_llc_val / num_of_runs; + avg_diff = (long)(cache_span - avg_llc_val); + diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; + + ret = platform && abs((int)diff_percent) > max_diff_percent && + labs(avg_diff) > max_diff; + + ksft_print_msg("%s Check cache miss rate within %lu%%\n", + ret ? "Fail:" : "Pass:", max_diff_percent); + + ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); + + show_cache_info(no_of_bits, avg_llc_val, cache_span, false); + + return ret; +} + static int check_results(struct resctrl_val_param *param, size_t span, int no_of_bits) { char *token_array[8], temp[512]; @@ -39,7 +114,7 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of if (!fp) { ksft_perror("Error in opening file"); - return errno; + return -1; } while (fgets(temp, sizeof(temp), fp)) { @@ -52,44 +127,38 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of } /* Field 3 is llc occ resc value */ - if (runs > 0) - sum_llc_occu_resc += strtoul(token_array[3], NULL, 0); + sum_llc_occu_resc += strtoul(token_array[3], NULL, 0); runs++; } fclose(fp); - return show_cache_info(sum_llc_occu_resc, no_of_bits, span, - MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, - true, true); + return show_results_info(sum_llc_occu_resc, no_of_bits, span, + MAX_DIFF, MAX_DIFF_PERCENT, runs, true); } -void cmt_test_cleanup(void) +static void cmt_test_cleanup(void) { remove(RESULT_FILE_NAME); } -int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) +static int cmt_run_test(const struct resctrl_test *test, const struct user_params *uparams) { - const char * const *cmd = benchmark_cmd; - const char *new_cmd[BENCHMARK_ARGS]; - unsigned long cache_size = 0; + struct fill_buf_param fill_buf = {}; + unsigned long cache_total_size = 0; + int n = uparams->bits ? : 5; unsigned long long_mask; - char *span_str = NULL; - char cbm_mask[256]; int count_of_bits; size_t span; - int ret, i; + int ret; - ret = get_cbm_mask("L3", cbm_mask); + ret = get_full_cbm("L3", &long_mask); if (ret) return ret; - long_mask = strtoul(cbm_mask, NULL, 16); - - ret = get_cache_size(cpu_no, "L3", &cache_size); + ret = get_cache_size(uparams->cpu, "L3", &cache_total_size); if (ret) return ret; - ksft_print_msg("Cache size :%lu\n", cache_size); + ksft_print_msg("Cache size :%lu\n", cache_total_size); count_of_bits = count_bits(long_mask); @@ -100,42 +169,50 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) } struct resctrl_val_param param = { - .resctrl_val = CMT_STR, .ctrlgrp = "c1", - .mongrp = "m1", - .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, .mask = ~(long_mask << n) & long_mask, .num_of_runs = 0, + .init = cmt_init, .setup = cmt_setup, + .measure = cmt_measure, }; - span = cache_size * n / count_of_bits; - - if (strcmp(cmd[0], "fill_buf") == 0) { - /* Duplicate the command to be able to replace span in it */ - for (i = 0; benchmark_cmd[i]; i++) - new_cmd[i] = benchmark_cmd[i]; - new_cmd[i] = NULL; + span = cache_portion_size(cache_total_size, param.mask, long_mask); - ret = asprintf(&span_str, "%zu", span); - if (ret < 0) - return -1; - new_cmd[1] = span_str; - cmd = new_cmd; + if (uparams->fill_buf) { + fill_buf.buf_size = span * 2; + fill_buf.memflush = uparams->fill_buf->memflush; + param.fill_buf = &fill_buf; + } else if (!uparams->benchmark_cmd[0]) { + fill_buf.buf_size = span * 2; + fill_buf.memflush = true; + param.fill_buf = &fill_buf; } remove(RESULT_FILE_NAME); - ret = resctrl_val(cmd, ¶m); + ret = resctrl_val(test, uparams, ¶m); if (ret) - goto out; + return ret; ret = check_results(¶m, span, n); - -out: - cmt_test_cleanup(); - free(span_str); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } + +static bool cmt_feature_check(const struct resctrl_test *test) +{ + return test_resource_feature_check(test) && + resctrl_mon_feature_exists("L3_MON", "llc_occupancy"); +} + +struct resctrl_test cmt_test = { + .name = "CMT", + .resource = "L3", + .feature_check = cmt_feature_check, + .run_test = cmt_run_test, + .cleanup = cmt_test_cleanup, +}; diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index a85ae8148db84..b9fa7968cd6e1 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -38,7 +38,7 @@ static void cl_flush(void *p) #endif } -static void mem_flush(unsigned char *buf, size_t buf_size) +void mem_flush(unsigned char *buf, size_t buf_size) { unsigned char *cp = buf; size_t i = 0; @@ -51,37 +51,46 @@ static void mem_flush(unsigned char *buf, size_t buf_size) sb(); } +/* + * Buffer index step advance to workaround HW prefetching interfering with + * the measurements. + * + * Must be a prime to step through all indexes of the buffer. + * + * Some primes work better than others on some architectures (from MBA/MBM + * result stability point of view). + */ +#define FILL_IDX_MULT 23 + static int fill_one_span_read(unsigned char *buf, size_t buf_size) { - unsigned char *end_ptr = buf + buf_size; - unsigned char sum, *p; - - sum = 0; - p = buf; - while (p < end_ptr) { - sum += *p; - p += (CL_SIZE / 2); + unsigned int size = buf_size / (CL_SIZE / 2); + unsigned int i, idx = 0; + unsigned char sum = 0; + + /* + * Read the buffer in an order that is unexpected by HW prefetching + * optimizations to prevent them interfering with the caching pattern. + * + * The read order is (in terms of halves of cachelines): + * i * FILL_IDX_MULT % size + * The formula is open-coded below to avoiding modulo inside the loop + * as it improves MBA/MBM result stability on some architectures. + */ + for (i = 0; i < size; i++) { + sum += buf[idx * (CL_SIZE / 2)]; + + idx += FILL_IDX_MULT; + while (idx >= size) + idx -= size; } return sum; } -static void fill_one_span_write(unsigned char *buf, size_t buf_size) -{ - unsigned char *end_ptr = buf + buf_size; - unsigned char *p; - - p = buf; - while (p < end_ptr) { - *p = '1'; - p += (CL_SIZE / 2); - } -} - -static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once) +void fill_cache_read(unsigned char *buf, size_t buf_size, bool once) { int ret = 0; - FILE *fp; while (1) { ret = fill_one_span_read(buf, buf_size); @@ -90,29 +99,10 @@ static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once) } /* Consume read result so that reading memory is not optimized out. */ - fp = fopen("/dev/null", "w"); - if (!fp) { - ksft_perror("Unable to write to /dev/null"); - return -1; - } - fprintf(fp, "Sum: %d ", ret); - fclose(fp); - - return 0; -} - -static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once) -{ - while (1) { - fill_one_span_write(buf, buf_size); - if (once) - break; - } - - return 0; + *value_sink = ret; } -static unsigned char *alloc_buffer(size_t buf_size, int memflush) +unsigned char *alloc_buffer(size_t buf_size, bool memflush) { void *buf = NULL; uint64_t *p64; @@ -140,24 +130,15 @@ static unsigned char *alloc_buffer(size_t buf_size, int memflush) return buf; } -int run_fill_buf(size_t buf_size, int memflush, int op, bool once) +ssize_t get_fill_buf_size(int cpu_no, const char *cache_type) { - unsigned char *buf; + unsigned long cache_total_size = 0; int ret; - buf = alloc_buffer(buf_size, memflush); - if (!buf) - return -1; - - if (op == 0) - ret = fill_cache_read(buf, buf_size, once); - else - ret = fill_cache_write(buf, buf_size, once); - free(buf); - if (ret) { - printf("\n Error in fill cache\n"); - return -1; - } + ret = get_cache_size(cpu_no, cache_type, &cache_total_size); + if (ret) + return ret; - return 0; + return cache_total_size * 4 > MINIMUM_SPAN ? + cache_total_size * 4 : MINIMUM_SPAN; } diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 4988b93add6a7..39cee98983592 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -12,19 +12,37 @@ #define RESULT_FILE_NAME "result_mba" #define NUM_OF_RUNS 5 -#define MAX_DIFF_PERCENT 8 +#define MAX_DIFF_PERCENT 15 #define ALLOCATION_MAX 100 #define ALLOCATION_MIN 10 #define ALLOCATION_STEP 10 +static int mba_init(const struct resctrl_test *test, + const struct user_params *uparams, + const struct resctrl_val_param *param, int domain_id) +{ + int ret; + + ret = initialize_read_mem_bw_imc(); + if (ret) + return ret; + + initialize_mem_bw_resctrl(param, domain_id); + + return 0; +} + /* * Change schemata percentage from 100 to 10%. Write schemata to specified * con_mon grp, mon_grp in resctrl FS. * For each allocation, run 5 times in order to get average values. */ -static int mba_setup(struct resctrl_val_param *p) +static int mba_setup(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *p) { - static int runs_per_allocation, allocation = 100; + static unsigned int allocation = ALLOCATION_MIN; + static int runs_per_allocation; char allocation_str[64]; int ret; @@ -35,47 +53,56 @@ static int mba_setup(struct resctrl_val_param *p) if (runs_per_allocation++ != 0) return 0; - if (allocation < ALLOCATION_MIN || allocation > ALLOCATION_MAX) + if (allocation > ALLOCATION_MAX) return END_OF_TESTS; sprintf(allocation_str, "%d", allocation); - ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, - p->resctrl_val); + ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu, test->resource); if (ret < 0) return ret; - allocation -= ALLOCATION_STEP; + allocation += ALLOCATION_STEP; return 0; } +static int mba_measure(const struct user_params *uparams, + struct resctrl_val_param *param, pid_t bm_pid) +{ + return measure_read_mem_bw(uparams, param, bm_pid); +} + static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) { - int allocation, runs; + unsigned int allocation; bool ret = false; + int runs; ksft_print_msg("Results are displayed in (MB)\n"); /* Memory bandwidth from 100% down to 10% */ for (allocation = 0; allocation < ALLOCATION_MAX / ALLOCATION_STEP; allocation++) { - unsigned long avg_bw_imc, avg_bw_resc; unsigned long sum_bw_imc = 0, sum_bw_resc = 0; + long avg_bw_imc, avg_bw_resc; int avg_diff_per; float avg_diff; - /* - * The first run is discarded due to inaccurate value from - * phase transition. - */ - for (runs = NUM_OF_RUNS * allocation + 1; + for (runs = NUM_OF_RUNS * allocation; runs < NUM_OF_RUNS * allocation + NUM_OF_RUNS ; runs++) { sum_bw_imc += bw_imc[runs]; sum_bw_resc += bw_resc[runs]; } - avg_bw_imc = sum_bw_imc / (NUM_OF_RUNS - 1); - avg_bw_resc = sum_bw_resc / (NUM_OF_RUNS - 1); + avg_bw_imc = sum_bw_imc / NUM_OF_RUNS; + avg_bw_resc = sum_bw_resc / NUM_OF_RUNS; + if (avg_bw_imc < THROTTLE_THRESHOLD || avg_bw_resc < THROTTLE_THRESHOLD) { + ksft_print_msg("Bandwidth below threshold (%d MiB). Dropping results from MBA schemata %u.\n", + THROTTLE_THRESHOLD, + ALLOCATION_MIN + ALLOCATION_STEP * allocation); + continue; + } + avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc; avg_diff_per = (int)(avg_diff * 100); @@ -83,7 +110,7 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) avg_diff_per > MAX_DIFF_PERCENT ? "Fail:" : "Pass:", MAX_DIFF_PERCENT, - ALLOCATION_MAX - ALLOCATION_STEP * allocation); + ALLOCATION_MIN + ALLOCATION_STEP * allocation); ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per); ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc); @@ -102,8 +129,9 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) static int check_results(void) { + unsigned long bw_resc[NUM_OF_RUNS * ALLOCATION_MAX / ALLOCATION_STEP]; + unsigned long bw_imc[NUM_OF_RUNS * ALLOCATION_MAX / ALLOCATION_STEP]; char *token_array[8], output[] = RESULT_FILE_NAME, temp[512]; - unsigned long bw_imc[1024], bw_resc[1024]; int runs; FILE *fp; @@ -111,7 +139,7 @@ static int check_results(void) if (!fp) { ksft_perror(output); - return errno; + return -1; } runs = 0; @@ -136,34 +164,62 @@ static int check_results(void) return show_mba_info(bw_imc, bw_resc); } -void mba_test_cleanup(void) +static void mba_test_cleanup(void) { remove(RESULT_FILE_NAME); } -int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd) +static int mba_run_test(const struct resctrl_test *test, const struct user_params *uparams) { struct resctrl_val_param param = { - .resctrl_val = MBA_STR, .ctrlgrp = "c1", - .mongrp = "m1", - .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, - .bw_report = "reads", - .setup = mba_setup + .init = mba_init, + .setup = mba_setup, + .measure = mba_measure, }; + struct fill_buf_param fill_buf = {}; int ret; remove(RESULT_FILE_NAME); - ret = resctrl_val(benchmark_cmd, ¶m); + if (uparams->fill_buf) { + fill_buf.buf_size = uparams->fill_buf->buf_size; + fill_buf.memflush = uparams->fill_buf->memflush; + param.fill_buf = &fill_buf; + } else if (!uparams->benchmark_cmd[0]) { + ssize_t buf_size; + + buf_size = get_fill_buf_size(uparams->cpu, "L3"); + if (buf_size < 0) + return buf_size; + fill_buf.buf_size = buf_size; + fill_buf.memflush = true; + param.fill_buf = &fill_buf; + } + + ret = resctrl_val(test, uparams, ¶m); if (ret) - goto out; + return ret; ret = check_results(); - -out: - mba_test_cleanup(); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } + +static bool mba_feature_check(const struct resctrl_test *test) +{ + return test_resource_feature_check(test) && + resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes"); +} + +struct resctrl_test mba_test = { + .name = "MBA", + .resource = "MB", + .vendor_specific = ARCH_INTEL, + .feature_check = mba_feature_check, + .run_test = mba_run_test, + .cleanup = mba_test_cleanup, +}; diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index eb488aabb9ae6..6dbbc3b760033 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -11,28 +11,24 @@ #include "resctrl.h" #define RESULT_FILE_NAME "result_mbm" -#define MAX_DIFF_PERCENT 8 +#define MAX_DIFF_PERCENT 15 #define NUM_OF_RUNS 5 static int show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span) { - unsigned long avg_bw_imc = 0, avg_bw_resc = 0; unsigned long sum_bw_imc = 0, sum_bw_resc = 0; + long avg_bw_imc = 0, avg_bw_resc = 0; int runs, ret, avg_diff_per; float avg_diff = 0; - /* - * Discard the first value which is inaccurate due to monitoring setup - * transition phase. - */ - for (runs = 1; runs < NUM_OF_RUNS ; runs++) { + for (runs = 0; runs < NUM_OF_RUNS; runs++) { sum_bw_imc += bw_imc[runs]; sum_bw_resc += bw_resc[runs]; } - avg_bw_imc = sum_bw_imc / 4; - avg_bw_resc = sum_bw_resc / 4; + avg_bw_imc = sum_bw_imc / NUM_OF_RUNS; + avg_bw_resc = sum_bw_resc / NUM_OF_RUNS; avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc; avg_diff_per = (int)(avg_diff * 100); @@ -40,7 +36,8 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span) ksft_print_msg("%s Check MBM diff within %d%%\n", ret ? "Fail:" : "Pass:", MAX_DIFF_PERCENT); ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per); - ksft_print_msg("Span (MB): %zu\n", span / MB); + if (span) + ksft_print_msg("Span (MB): %zu\n", span / MB); ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc); ksft_print_msg("avg_bw_resc: %lu\n", avg_bw_resc); @@ -61,7 +58,7 @@ static int check_results(size_t span) if (!fp) { ksft_perror(output); - return errno; + return -1; } runs = 0; @@ -86,7 +83,24 @@ static int check_results(size_t span) return ret; } -static int mbm_setup(struct resctrl_val_param *p) +static int mbm_init(const struct resctrl_test *test, + const struct user_params *uparams, + const struct resctrl_val_param *param, int domain_id) +{ + int ret; + + ret = initialize_read_mem_bw_imc(); + if (ret) + return ret; + + initialize_mem_bw_resctrl(param, domain_id); + + return 0; +} + +static int mbm_setup(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *p) { int ret = 0; @@ -95,43 +109,76 @@ static int mbm_setup(struct resctrl_val_param *p) return END_OF_TESTS; /* Set up shemata with 100% allocation on the first run. */ - if (p->num_of_runs == 0) - ret = write_schemata(p->ctrlgrp, "100", p->cpu_no, - p->resctrl_val); + if (p->num_of_runs == 0 && resctrl_resource_exists("MB")) + ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, test->resource); p->num_of_runs++; return ret; } -void mbm_test_cleanup(void) +static int mbm_measure(const struct user_params *uparams, + struct resctrl_val_param *param, pid_t bm_pid) +{ + return measure_read_mem_bw(uparams, param, bm_pid); +} + +static void mbm_test_cleanup(void) { remove(RESULT_FILE_NAME); } -int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd) +static int mbm_run_test(const struct resctrl_test *test, const struct user_params *uparams) { struct resctrl_val_param param = { - .resctrl_val = MBM_STR, .ctrlgrp = "c1", - .mongrp = "m1", - .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, - .bw_report = "reads", - .setup = mbm_setup + .init = mbm_init, + .setup = mbm_setup, + .measure = mbm_measure, }; + struct fill_buf_param fill_buf = {}; int ret; remove(RESULT_FILE_NAME); - ret = resctrl_val(benchmark_cmd, ¶m); - if (ret) - goto out; + if (uparams->fill_buf) { + fill_buf.buf_size = uparams->fill_buf->buf_size; + fill_buf.memflush = uparams->fill_buf->memflush; + param.fill_buf = &fill_buf; + } else if (!uparams->benchmark_cmd[0]) { + ssize_t buf_size; + + buf_size = get_fill_buf_size(uparams->cpu, "L3"); + if (buf_size < 0) + return buf_size; + fill_buf.buf_size = buf_size; + fill_buf.memflush = true; + param.fill_buf = &fill_buf; + } - ret = check_results(DEFAULT_SPAN); + ret = resctrl_val(test, uparams, ¶m); + if (ret) + return ret; -out: - mbm_test_cleanup(); + ret = check_results(param.fill_buf ? param.fill_buf->buf_size : 0); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } + +static bool mbm_feature_check(const struct resctrl_test *test) +{ + return resctrl_mon_feature_exists("L3_MON", "mbm_total_bytes") && + resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes"); +} + +struct resctrl_test mbm_test = { + .name = "MBM", + .resource = "MB", + .vendor_specific = ARCH_INTEL, + .feature_check = mbm_feature_check, + .run_test = mbm_run_test, + .cleanup = mbm_test_cleanup, +}; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index a848e9c755787..df624890e3da1 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -21,6 +22,8 @@ #include #include #include +#include +#include #include "../kselftest.h" #define MB (1024 * 1024) @@ -28,92 +31,216 @@ #define PHYS_ID_PATH "/sys/devices/system/cpu/cpu" #define INFO_PATH "/sys/fs/resctrl/info" -#define ARCH_INTEL 1 -#define ARCH_AMD 2 +/* + * CPU vendor IDs + * + * Define as bits because they're used for vendor_specific bitmask in + * the struct resctrl_test. + */ +#define ARCH_INTEL BIT(0) +#define ARCH_AMD BIT(1) +#define ARCH_HYGON BIT(2) #define END_OF_TESTS 1 #define BENCHMARK_ARGS 64 -#define DEFAULT_SPAN (250 * MB) +#define MINIMUM_SPAN (250 * MB) -#define PARENT_EXIT() \ - do { \ - kill(ppid, SIGKILL); \ - umount_resctrlfs(); \ - exit(EXIT_FAILURE); \ - } while (0) +/* + * Memory bandwidth (in MiB) below which the bandwidth comparisons + * between iMC and resctrl are considered unreliable. For example RAS + * features or memory performance features that generate memory traffic + * may drive accesses that are counted differently by performance counters + * and MBM respectively, for instance generating "overhead" traffic which + * is not counted against any specific RMID. + */ +#define THROTTLE_THRESHOLD 2500 + +/* + * fill_buf_param: "fill_buf" benchmark parameters + * @buf_size: Size (in bytes) of buffer used in benchmark. + * "fill_buf" allocates and initializes buffer of + * @buf_size. User can change value via command line. + * @memflush: If false the buffer will not be flushed after + * allocation and initialization, otherwise the + * buffer will be flushed. User can change value via + * command line (via integers with 0 interpreted as + * false and anything else as true). + */ +struct fill_buf_param { + size_t buf_size; + bool memflush; +}; + +/* + * user_params: User supplied parameters + * @cpu: CPU number to which the benchmark will be bound to + * @bits: Number of bits used for cache allocation size + * @benchmark_cmd: Benchmark command to run during (some of the) tests + * @fill_buf: Pointer to user provided parameters for "fill_buf", + * NULL if user did not provide parameters and test + * specific defaults should be used. + */ +struct user_params { + int cpu; + int bits; + const char *benchmark_cmd[BENCHMARK_ARGS]; + const struct fill_buf_param *fill_buf; +}; + +/* + * resctrl_test: resctrl test definition + * @name: Test name + * @group: Test group - a common name for tests that share some characteristic + * (e.g., L3 CAT test belongs to the CAT group). Can be NULL + * @resource: Resource to test (e.g., MB, L3, L2, etc.) + * @vendor_specific: Bitmask for vendor-specific tests (can be 0 for universal tests) + * @disabled: Test is disabled + * @feature_check: Callback to check required resctrl features + * @run_test: Callback to run the test + * @cleanup: Callback to cleanup after the test + */ +struct resctrl_test { + const char *name; + const char *group; + const char *resource; + unsigned int vendor_specific; + bool disabled; + bool (*feature_check)(const struct resctrl_test *test); + int (*run_test)(const struct resctrl_test *test, + const struct user_params *uparams); + void (*cleanup)(void); +}; /* * resctrl_val_param: resctrl test parameters - * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) * @ctrlgrp: Name of the control monitor group (con_mon grp) * @mongrp: Name of the monitor group (mon grp) - * @cpu_no: CPU number to which the benchmark would be binded * @filename: Name of file to which the o/p should be written - * @bw_report: Bandwidth report type (reads vs writes) - * @setup: Call back function to setup test environment + * @init: Callback function to initialize test environment + * @setup: Callback function to setup per test run environment + * @measure: Callback that performs the measurement (a single test) + * @fill_buf: Parameters for default "fill_buf" benchmark. + * Initialized with user provided parameters, possibly + * adapted to be relevant to the test. If user does + * not provide parameters for "fill_buf" nor a + * replacement benchmark then initialized with defaults + * appropriate for test. NULL if user provided + * benchmark. */ struct resctrl_val_param { - char *resctrl_val; - char ctrlgrp[64]; - char mongrp[64]; - int cpu_no; - char filename[64]; - char *bw_report; - unsigned long mask; - int num_of_runs; - int (*setup)(struct resctrl_val_param *param); + const char *ctrlgrp; + const char *mongrp; + char filename[64]; + unsigned long mask; + int num_of_runs; + int (*init)(const struct resctrl_test *test, + const struct user_params *uparams, + const struct resctrl_val_param *param, + int domain_id); + int (*setup)(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *param); + int (*measure)(const struct user_params *uparams, + struct resctrl_val_param *param, + pid_t bm_pid); + struct fill_buf_param *fill_buf; }; -#define MBM_STR "mbm" -#define MBA_STR "mba" -#define CMT_STR "cmt" -#define CAT_STR "cat" +/* + * Memory location that consumes values compiler must not optimize away. + * Volatile ensures writes to this location cannot be optimized away by + * compiler. + */ +extern volatile int *value_sink; -extern pid_t bm_pid, ppid; +extern int snc_unreliable; extern char llc_occup_path[1024]; -int get_vendor(void); +int snc_nodes_per_l3_cache(void); +unsigned int get_vendor(void); bool check_resctrlfs_support(void); int filter_dmesg(void); -int get_resource_id(int cpu_no, int *resource_id); +int get_domain_id(const char *resource, int cpu_no, int *domain_id); int mount_resctrlfs(void); int umount_resctrlfs(void); -int validate_bw_report_request(char *bw_report); -bool validate_resctrl_feature_request(const char *resource, const char *feature); +bool resctrl_resource_exists(const char *resource); +bool resctrl_mon_feature_exists(const char *resource, const char *feature); +bool resource_info_file_exists(const char *resource, const char *file); +bool test_resource_feature_check(const struct resctrl_test *test); char *fgrep(FILE *inf, const char *str); -int taskset_benchmark(pid_t bm_pid, int cpu_no); -int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, - char *resctrl_val); -int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, - char *resctrl_val); +int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity); +int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity); +int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no, + const char *resource); +int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp, const char *mongrp); int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags); -int run_fill_buf(size_t buf_size, int memflush, int op, bool once); -int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param); -int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd); -void tests_cleanup(void); -void mbm_test_cleanup(void); -int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); -void mba_test_cleanup(void); -int get_cbm_mask(char *cache_type, char *cbm_mask); -int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size); +unsigned char *alloc_buffer(size_t buf_size, bool memflush); +void mem_flush(unsigned char *buf, size_t buf_size); +void fill_cache_read(unsigned char *buf, size_t buf_size, bool once); +ssize_t get_fill_buf_size(int cpu_no, const char *cache_type); +int initialize_read_mem_bw_imc(void); +int measure_read_mem_bw(const struct user_params *uparams, + struct resctrl_val_param *param, pid_t bm_pid); +void initialize_mem_bw_resctrl(const struct resctrl_val_param *param, + int domain_id); +int resctrl_val(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *param); +unsigned long create_bit_mask(unsigned int start, unsigned int len); +unsigned int count_contiguous_bits(unsigned long val, unsigned int *start); +int get_full_cbm(const char *cache_type, unsigned long *mask); +int get_mask_no_shareable(const char *cache_type, unsigned long *mask); +int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size); +int resource_info_unsigned_get(const char *resource, const char *filename, unsigned int *val); void ctrlc_handler(int signum, siginfo_t *info, void *ptr); -int signal_handler_register(void); +int signal_handler_register(const struct resctrl_test *test); void signal_handler_unregister(void); -int cat_val(struct resctrl_val_param *param, size_t span); -void cat_test_cleanup(void); -int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type); -int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd); unsigned int count_bits(unsigned long n); -void cmt_test_cleanup(void); -int get_core_sibling(int cpu_no); -int measure_cache_vals(struct resctrl_val_param *param, int bm_pid); -int show_cache_info(unsigned long sum_llc_val, int no_of_bits, - size_t cache_span, unsigned long max_diff, - unsigned long max_diff_percent, unsigned long num_of_runs, - bool platform, bool cmt); +int snc_kernel_support(void); + +void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config); +int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no); +int perf_event_reset_enable(int pe_fd); +int perf_event_measure(int pe_fd, const char *filename, pid_t bm_pid); +int measure_llc_resctrl(const char *filename, pid_t bm_pid); +int minimize_l2_occupancy(const struct resctrl_test *test, + const struct user_params *uparams, + const struct resctrl_val_param *param); +void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines); + +/* + * cache_portion_size - Calculate the size of a cache portion + * @cache_size: Total cache size in bytes + * @portion_mask: Cache portion mask + * @full_cache_mask: Full Cache Bit Mask (CBM) for the cache + * + * Return: The size of the cache portion in bytes. + */ +static inline unsigned long cache_portion_size(unsigned long cache_size, + unsigned long portion_mask, + unsigned long full_cache_mask) +{ + unsigned int bits = count_bits(full_cache_mask); + + /* + * With no bits the full CBM, assume cache cannot be split into + * smaller portions. To avoid divide by zero, return cache_size. + */ + if (!bits) + return cache_size; + + return cache_size * count_bits(portion_mask) / bits; +} + +extern struct resctrl_test mbm_test; +extern struct resctrl_test mba_test; +extern struct resctrl_test cmt_test; +extern struct resctrl_test l3_cat_test; +extern struct resctrl_test l3_noncont_cat_test; +extern struct resctrl_test l2_noncont_cat_test; #endif /* RESCTRL_H */ diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 31373b69e675d..dbcd5eea9fbc9 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -10,16 +10,37 @@ */ #include "resctrl.h" -static int detect_vendor(void) +/* Volatile memory sink to prevent compiler optimizations */ +static volatile int sink_target; +volatile int *value_sink = &sink_target; + +static struct resctrl_test *resctrl_tests[] = { + &mbm_test, + &mba_test, + &cmt_test, + &l3_cat_test, + &l3_noncont_cat_test, + &l2_noncont_cat_test, +}; + +static unsigned int detect_vendor(void) { - FILE *inf = fopen("/proc/cpuinfo", "r"); - int vendor_id = 0; + static unsigned int vendor_id; + static bool initialized; char *s = NULL; + FILE *inf; char *res; - if (!inf) + if (initialized) return vendor_id; + inf = fopen("/proc/cpuinfo", "r"); + if (!inf) { + vendor_id = 0; + initialized = true; + return vendor_id; + } + res = fgrep(inf, "vendor_id"); if (res) @@ -29,18 +50,22 @@ static int detect_vendor(void) vendor_id = ARCH_INTEL; else if (s && !strcmp(s, ": AuthenticAMD\n")) vendor_id = ARCH_AMD; + else if (s && !strcmp(s, ": HygonGenuine\n")) + vendor_id = ARCH_HYGON; fclose(inf); free(res); + + initialized = true; return vendor_id; } -int get_vendor(void) +unsigned int get_vendor(void) { - static int vendor = -1; + unsigned int vendor; + + vendor = detect_vendor(); - if (vendor == -1) - vendor = detect_vendor(); if (vendor == 0) ksft_print_msg("Can not get vendor info...\n"); @@ -49,29 +74,30 @@ int get_vendor(void) static void cmd_help(void) { - printf("usage: resctrl_tests [-h] [-b \"benchmark_cmd [options]\"] [-t test list] [-n no_of_bits]\n"); - printf("\t-b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CMT\n"); + int i; + + printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n"); + printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n"); printf("\t default benchmark is builtin fill_buf\n"); - printf("\t-t test list: run tests specified in the test list, "); + printf("\t-t test list: run tests/groups specified by the list, "); printf("e.g. -t mbm,mba,cmt,cat\n"); + printf("\t\tSupported tests (group):\n"); + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) { + if (resctrl_tests[i]->group) + printf("\t\t\t%s (%s)\n", resctrl_tests[i]->name, resctrl_tests[i]->group); + else + printf("\t\t\t%s\n", resctrl_tests[i]->name); + } printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n"); printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n"); printf("\t-h: help\n"); } -void tests_cleanup(void) -{ - mbm_test_cleanup(); - mba_test_cleanup(); - cmt_test_cleanup(); - cat_test_cleanup(); -} - -static int test_prepare(void) +static int test_prepare(const struct resctrl_test *test) { int res; - res = signal_handler_register(); + res = signal_handler_register(test); if (res) { ksft_print_msg("Failed to register signal handler\n"); return res; @@ -86,159 +112,196 @@ static int test_prepare(void) return 0; } -static void test_cleanup(void) +static void test_cleanup(const struct resctrl_test *test) { + if (test->cleanup) + test->cleanup(); umount_resctrlfs(); signal_handler_unregister(); } -static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no) +static bool test_vendor_specific_check(const struct resctrl_test *test) { - int res; - - ksft_print_msg("Starting MBM BW change ...\n"); + if (!test->vendor_specific) + return true; - if (test_prepare()) { - ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); - return; - } - - if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") || - !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || - (get_vendor() != ARCH_INTEL)) { - ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n"); - goto cleanup; - } - - res = mbm_bw_change(cpu_no, benchmark_cmd); - ksft_test_result(!res, "MBM: bw change\n"); - if ((get_vendor() == ARCH_INTEL) && res) - ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); - -cleanup: - test_cleanup(); + return get_vendor() & test->vendor_specific; } -static void run_mba_test(const char * const *benchmark_cmd, int cpu_no) +static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams) { - int res; + int ret, snc_mode; - ksft_print_msg("Starting MBA Schemata change ...\n"); + if (test->disabled) + return; - if (test_prepare()) { - ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); + if (!test_vendor_specific_check(test)) { + ksft_test_result_skip("Hardware does not support %s\n", test->name); return; } - if (!validate_resctrl_feature_request("MB", NULL) || - !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || - (get_vendor() != ARCH_INTEL)) { - ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n"); - goto cleanup; - } + snc_mode = snc_nodes_per_l3_cache(); - res = mba_schemata_change(cpu_no, benchmark_cmd); - ksft_test_result(!res, "MBA: schemata change\n"); + ksft_print_msg("Starting %s test ...\n", test->name); -cleanup: - test_cleanup(); -} - -static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no) -{ - int res; - - ksft_print_msg("Starting CMT test ...\n"); + if (snc_mode == 1 && snc_unreliable && get_vendor() == ARCH_INTEL) { + ksft_test_result_skip("SNC detection unreliable due to offline CPUs. Test results may not be accurate if SNC enabled.\n"); + return; + } - if (test_prepare()) { + if (test_prepare(test)) { ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; } - if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") || - !validate_resctrl_feature_request("L3", NULL)) { - ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n"); + if (!test->feature_check(test)) { + ksft_test_result_skip("Hardware does not support %s or %s is disabled\n", + test->name, test->name); goto cleanup; } - res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd); - ksft_test_result(!res, "CMT: test\n"); - if ((get_vendor() == ARCH_INTEL) && res) - ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + ret = test->run_test(test, uparams); + ksft_test_result(!ret, "%s: test\n", test->name); cleanup: - test_cleanup(); + test_cleanup(test); } -static void run_cat_test(int cpu_no, int no_of_bits) +/* + * Allocate and initialize a struct fill_buf_param with user provided + * (via "-b fill_buf ") parameters. + * + * Use defaults (that may not be appropriate for all tests) for any + * fill_buf parameters omitted by the user. + * + * Historically it may have been possible for user space to provide + * additional parameters, "operation" ("read" vs "write") in + * benchmark_cmd[3] and "once" (run "once" or until terminated) in + * benchmark_cmd[4]. Changing these parameters have never been + * supported with the default of "read" operation and running until + * terminated built into the tests. Any unsupported values for + * (original) "fill_buf" parameters are treated as failure. + * + * Return: On failure, forcibly exits the test on any parsing failure, + * returns NULL if no parsing needed (user did not actually provide + * "-b fill_buf"). + * On success, returns pointer to newly allocated and fully + * initialized struct fill_buf_param that caller must free. + */ +static struct fill_buf_param *alloc_fill_buf_param(struct user_params *uparams) { - int res; + struct fill_buf_param *fill_param = NULL; + char *endptr = NULL; + + if (!uparams->benchmark_cmd[0] || strcmp(uparams->benchmark_cmd[0], "fill_buf")) + return NULL; + + fill_param = malloc(sizeof(*fill_param)); + if (!fill_param) + ksft_exit_skip("Unable to allocate memory for fill_buf parameters.\n"); + + if (uparams->benchmark_cmd[1] && *uparams->benchmark_cmd[1] != '\0') { + errno = 0; + fill_param->buf_size = strtoul(uparams->benchmark_cmd[1], &endptr, 10); + if (errno || *endptr != '\0') { + free(fill_param); + ksft_exit_skip("Unable to parse benchmark buffer size.\n"); + } + } else { + fill_param->buf_size = MINIMUM_SPAN; + } - ksft_print_msg("Starting CAT test ...\n"); + if (uparams->benchmark_cmd[2] && *uparams->benchmark_cmd[2] != '\0') { + errno = 0; + fill_param->memflush = strtol(uparams->benchmark_cmd[2], &endptr, 10) != 0; + if (errno || *endptr != '\0') { + free(fill_param); + ksft_exit_skip("Unable to parse benchmark memflush parameter.\n"); + } + } else { + fill_param->memflush = true; + } - if (test_prepare()) { - ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); - return; + if (uparams->benchmark_cmd[3] && *uparams->benchmark_cmd[3] != '\0') { + if (strcmp(uparams->benchmark_cmd[3], "0")) { + free(fill_param); + ksft_exit_skip("Only read operations supported.\n"); + } } - if (!validate_resctrl_feature_request("L3", NULL)) { - ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n"); - goto cleanup; + if (uparams->benchmark_cmd[4] && *uparams->benchmark_cmd[4] != '\0') { + if (strcmp(uparams->benchmark_cmd[4], "false")) { + free(fill_param); + ksft_exit_skip("fill_buf is required to run until termination.\n"); + } } - res = cat_perf_miss_val(cpu_no, no_of_bits, "L3"); - ksft_test_result(!res, "CAT: test\n"); + return fill_param; +} -cleanup: - test_cleanup(); +static void init_user_params(struct user_params *uparams) +{ + memset(uparams, 0, sizeof(*uparams)); + + uparams->cpu = 1; + uparams->bits = 0; } int main(int argc, char **argv) { - bool has_ben = false, mbm_test = true, mba_test = true, cmt_test = true; - int c, cpu_no = 1, argc_new = argc, i, no_of_bits = 0; - const char *benchmark_cmd[BENCHMARK_ARGS]; - int ben_ind, ben_count, tests = 0; - char *span_str = NULL; - bool cat_test = true; - int ret; - - for (i = 0; i < argc; i++) { - if (strcmp(argv[i], "-b") == 0) { - ben_ind = i + 1; - ben_count = argc - ben_ind; - argc_new = ben_ind - 1; - has_ben = true; - break; - } - } + struct fill_buf_param *fill_param = NULL; + int tests = ARRAY_SIZE(resctrl_tests); + bool test_param_seen = false; + struct user_params uparams; + int c, i; - while ((c = getopt(argc_new, argv, "ht:b:n:p:")) != -1) { + init_user_params(&uparams); + + while ((c = getopt(argc, argv, "ht:b:n:p:")) != -1) { char *token; switch (c) { + case 'b': + /* + * First move optind back to the (first) optarg and + * then build the benchmark command using the + * remaining arguments. + */ + optind--; + if (argc - optind >= BENCHMARK_ARGS) + ksft_exit_fail_msg("Too long benchmark command"); + + /* Extract benchmark command from command line. */ + for (i = 0; i < argc - optind; i++) + uparams.benchmark_cmd[i] = argv[i + optind]; + uparams.benchmark_cmd[i] = NULL; + + goto last_arg; case 't': token = strtok(optarg, ","); - mbm_test = false; - mba_test = false; - cmt_test = false; - cat_test = false; + if (!test_param_seen) { + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) + resctrl_tests[i]->disabled = true; + tests = 0; + test_param_seen = true; + } while (token) { - if (!strncmp(token, MBM_STR, sizeof(MBM_STR))) { - mbm_test = true; - tests++; - } else if (!strncmp(token, MBA_STR, sizeof(MBA_STR))) { - mba_test = true; - tests++; - } else if (!strncmp(token, CMT_STR, sizeof(CMT_STR))) { - cmt_test = true; - tests++; - } else if (!strncmp(token, CAT_STR, sizeof(CAT_STR))) { - cat_test = true; - tests++; - } else { - printf("invalid argument\n"); + bool found = false; + + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) { + if (!strcasecmp(token, resctrl_tests[i]->name) || + (resctrl_tests[i]->group && + !strcasecmp(token, resctrl_tests[i]->group))) { + if (resctrl_tests[i]->disabled) + tests++; + resctrl_tests[i]->disabled = false; + found = true; + } + } + + if (!found) { + printf("invalid test: %s\n", token); return -1; } @@ -246,11 +309,11 @@ int main(int argc, char **argv) } break; case 'p': - cpu_no = atoi(optarg); + uparams.cpu = atoi(optarg); break; case 'n': - no_of_bits = atoi(optarg); - if (no_of_bits <= 0) { + uparams.bits = atoi(optarg); + if (uparams.bits <= 0) { printf("Bail out! invalid argument for no_of_bits\n"); return -1; } @@ -265,6 +328,11 @@ int main(int argc, char **argv) return -1; } } +last_arg: + + fill_param = alloc_fill_buf_param(&uparams); + if (fill_param) + uparams.fill_buf = fill_param; ksft_print_header(); @@ -274,51 +342,21 @@ int main(int argc, char **argv) * 2. We execute perf commands */ if (geteuid() != 0) - return ksft_exit_skip("Not running as root. Skipping...\n"); - - if (has_ben) { - if (argc - ben_ind >= BENCHMARK_ARGS) - ksft_exit_fail_msg("Too long benchmark command.\n"); - - /* Extract benchmark command from command line. */ - for (i = 0; i < argc - ben_ind; i++) - benchmark_cmd[i] = argv[i + ben_ind]; - benchmark_cmd[ben_count] = NULL; - } else { - /* If no benchmark is given by "-b" argument, use fill_buf. */ - benchmark_cmd[0] = "fill_buf"; - ret = asprintf(&span_str, "%u", DEFAULT_SPAN); - if (ret < 0) - ksft_exit_fail_msg("Out of memory!\n"); - benchmark_cmd[1] = span_str; - benchmark_cmd[2] = "1"; - benchmark_cmd[3] = "0"; - benchmark_cmd[4] = "false"; - benchmark_cmd[5] = NULL; - } + ksft_exit_skip("Not running as root. Skipping...\n"); if (!check_resctrlfs_support()) - return ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n"); + ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n"); if (umount_resctrlfs()) - return ksft_exit_skip("resctrl FS unmount failed.\n"); + ksft_exit_skip("resctrl FS unmount failed.\n"); filter_dmesg(); - ksft_set_plan(tests ? : 4); - - if (mbm_test) - run_mbm_test(benchmark_cmd, cpu_no); - - if (mba_test) - run_mba_test(benchmark_cmd, cpu_no); - - if (cmt_test) - run_cmt_test(benchmark_cmd, cpu_no); + ksft_set_plan(tests); - if (cat_test) - run_cat_test(cpu_no, no_of_bits); + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) + run_single_test(resctrl_tests[i], &uparams); - free(span_str); + free(fill_param); ksft_finished(); } diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 710058eb25407..f20d2194c35fb 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -11,38 +11,15 @@ #include "resctrl.h" #define UNCORE_IMC "uncore_imc" -#define READ_FILE_NAME "events/cas_count_read" -#define WRITE_FILE_NAME "events/cas_count_write" +#define READ_FILE_NAME "cas_count_read" #define DYN_PMU_PATH "/sys/bus/event_source/devices" #define SCALE 0.00006103515625 -#define MAX_IMCS 20 +#define MAX_IMCS 40 #define MAX_TOKENS 5 -#define READ 0 -#define WRITE 1 -#define CON_MON_MBM_LOCAL_BYTES_PATH \ - "%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes" #define CON_MBM_LOCAL_BYTES_PATH \ "%s/%s/mon_data/mon_L3_%02d/mbm_local_bytes" -#define MON_MBM_LOCAL_BYTES_PATH \ - "%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes" - -#define MBM_LOCAL_BYTES_PATH \ - "%s/mon_data/mon_L3_%02d/mbm_local_bytes" - -#define CON_MON_LCC_OCCUP_PATH \ - "%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy" - -#define CON_LCC_OCCUP_PATH \ - "%s/%s/mon_data/mon_L3_%02d/llc_occupancy" - -#define MON_LCC_OCCUP_PATH \ - "%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy" - -#define LCC_OCCUP_PATH \ - "%s/mon_data/mon_L3_%02d/llc_occupancy" - struct membw_read_format { __u64 value; /* The value of the event */ __u64 time_enabled; /* if PERF_FORMAT_TOTAL_TIME_ENABLED */ @@ -55,49 +32,48 @@ struct imc_counter_config { __u64 event; __u64 umask; struct perf_event_attr pe; - struct membw_read_format return_value; int fd; }; static char mbm_total_path[1024]; static int imcs; -static struct imc_counter_config imc_counters_config[MAX_IMCS][2]; +static struct imc_counter_config imc_counters_config[MAX_IMCS]; +static const struct resctrl_test *current_test; -void membw_initialize_perf_event_attr(int i, int j) +static void read_mem_bw_initialize_perf_event_attr(int i) { - memset(&imc_counters_config[i][j].pe, 0, + memset(&imc_counters_config[i].pe, 0, sizeof(struct perf_event_attr)); - imc_counters_config[i][j].pe.type = imc_counters_config[i][j].type; - imc_counters_config[i][j].pe.size = sizeof(struct perf_event_attr); - imc_counters_config[i][j].pe.disabled = 1; - imc_counters_config[i][j].pe.inherit = 1; - imc_counters_config[i][j].pe.exclude_guest = 0; - imc_counters_config[i][j].pe.config = - imc_counters_config[i][j].umask << 8 | - imc_counters_config[i][j].event; - imc_counters_config[i][j].pe.sample_type = PERF_SAMPLE_IDENTIFIER; - imc_counters_config[i][j].pe.read_format = + imc_counters_config[i].pe.type = imc_counters_config[i].type; + imc_counters_config[i].pe.size = sizeof(struct perf_event_attr); + imc_counters_config[i].pe.disabled = 1; + imc_counters_config[i].pe.inherit = 1; + imc_counters_config[i].pe.exclude_guest = 0; + imc_counters_config[i].pe.config = + imc_counters_config[i].umask << 8 | + imc_counters_config[i].event; + imc_counters_config[i].pe.sample_type = PERF_SAMPLE_IDENTIFIER; + imc_counters_config[i].pe.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; } -void membw_ioctl_perf_event_ioc_reset_enable(int i, int j) +static void read_mem_bw_ioctl_perf_event_ioc_reset_enable(int i) { - ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_RESET, 0); - ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_ENABLE, 0); + ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_RESET, 0); + ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_ENABLE, 0); } -void membw_ioctl_perf_event_ioc_disable(int i, int j) +static void read_mem_bw_ioctl_perf_event_ioc_disable(int i) { - ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_DISABLE, 0); + ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_DISABLE, 0); } /* - * get_event_and_umask: Parse config into event and umask + * get_read_event_and_umask: Parse config into event and umask * @cas_count_cfg: Config * @count: iMC number - * @op: Operation (read/write) */ -void get_event_and_umask(char *cas_count_cfg, int count, bool op) +static void get_read_event_and_umask(char *cas_count_cfg, unsigned int count) { char *token[MAX_TOKENS]; int i = 0; @@ -110,34 +86,22 @@ void get_event_and_umask(char *cas_count_cfg, int count, bool op) for (i = 0; i < MAX_TOKENS - 1; i++) { if (!token[i]) break; - if (strcmp(token[i], "event") == 0) { - if (op == READ) - imc_counters_config[count][READ].event = - strtol(token[i + 1], NULL, 16); - else - imc_counters_config[count][WRITE].event = - strtol(token[i + 1], NULL, 16); - } - if (strcmp(token[i], "umask") == 0) { - if (op == READ) - imc_counters_config[count][READ].umask = - strtol(token[i + 1], NULL, 16); - else - imc_counters_config[count][WRITE].umask = - strtol(token[i + 1], NULL, 16); - } + if (strcmp(token[i], "event") == 0) + imc_counters_config[count].event = strtol(token[i + 1], NULL, 16); + if (strcmp(token[i], "umask") == 0) + imc_counters_config[count].umask = strtol(token[i + 1], NULL, 16); } } -static int open_perf_event(int i, int cpu_no, int j) +static int open_perf_read_event(int i, int cpu_no) { - imc_counters_config[i][j].fd = - perf_event_open(&imc_counters_config[i][j].pe, -1, cpu_no, -1, + imc_counters_config[i].fd = + perf_event_open(&imc_counters_config[i].pe, -1, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); - if (imc_counters_config[i][j].fd == -1) { + if (imc_counters_config[i].fd == -1) { fprintf(stderr, "Error opening leader %llx\n", - imc_counters_config[i][j].pe.config); + imc_counters_config[i].pe.config); return -1; } @@ -145,75 +109,126 @@ static int open_perf_event(int i, int cpu_no, int j) return 0; } -/* Get type and config (read and write) of an iMC counter */ -static int read_from_imc_dir(char *imc_dir, int count) +static int parse_imc_read_bw_events(char *imc_dir, unsigned int type, + unsigned int *count) { - char cas_count_cfg[1024], imc_counter_cfg[1024], imc_counter_type[1024]; + char imc_events_dir[PATH_MAX], imc_counter_cfg[PATH_MAX]; + unsigned int orig_count = *count; + char cas_count_cfg[1024]; + struct dirent *ep; + int path_len; + int ret = -1; + int num_cfg; FILE *fp; + DIR *dp; - /* Get type of iMC counter */ - sprintf(imc_counter_type, "%s%s", imc_dir, "type"); - fp = fopen(imc_counter_type, "r"); - if (!fp) { - ksft_perror("Failed to open iMC counter type file"); - + path_len = snprintf(imc_events_dir, sizeof(imc_events_dir), "%sevents", + imc_dir); + if (path_len >= sizeof(imc_events_dir)) { + ksft_print_msg("Unable to create path to %sevents\n", imc_dir); return -1; } - if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) { - ksft_perror("Could not get iMC type"); - fclose(fp); + dp = opendir(imc_events_dir); + if (!dp) { + ksft_perror("Unable to open PMU events directory"); return -1; } - fclose(fp); - - imc_counters_config[count][WRITE].type = - imc_counters_config[count][READ].type; - /* Get read config */ - sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME); - fp = fopen(imc_counter_cfg, "r"); - if (!fp) { - ksft_perror("Failed to open iMC config file"); - - return -1; - } - if (fscanf(fp, "%1023s", cas_count_cfg) <= 0) { - ksft_perror("Could not get iMC cas count read"); + while ((ep = readdir(dp))) { + /* + * Parse all event files with READ_FILE_NAME prefix that + * contain the event number and umask. Skip files containing + * "." that contain unused properties of event. + */ + if (!strstr(ep->d_name, READ_FILE_NAME) || + strchr(ep->d_name, '.')) + continue; + + path_len = snprintf(imc_counter_cfg, sizeof(imc_counter_cfg), + "%s/%s", imc_events_dir, ep->d_name); + if (path_len >= sizeof(imc_counter_cfg)) { + ksft_print_msg("Unable to create path to %s/%s\n", + imc_events_dir, ep->d_name); + goto out_close; + } + fp = fopen(imc_counter_cfg, "r"); + if (!fp) { + ksft_perror("Failed to open iMC config file"); + goto out_close; + } + num_cfg = fscanf(fp, "%1023s", cas_count_cfg); fclose(fp); + if (num_cfg <= 0) { + ksft_perror("Could not get iMC cas count read"); + goto out_close; + } + if (*count >= MAX_IMCS) { + ksft_print_msg("Maximum iMC count exceeded\n"); + goto out_close; + } - return -1; + imc_counters_config[*count].type = type; + get_read_event_and_umask(cas_count_cfg, *count); + /* Do not fail after incrementing *count. */ + *count += 1; } - fclose(fp); - - get_event_and_umask(cas_count_cfg, count, READ); + if (*count == orig_count) { + ksft_print_msg("Unable to find events in %s\n", imc_events_dir); + goto out_close; + } + ret = 0; +out_close: + closedir(dp); + return ret; +} - /* Get write config */ - sprintf(imc_counter_cfg, "%s%s", imc_dir, WRITE_FILE_NAME); - fp = fopen(imc_counter_cfg, "r"); - if (!fp) { - ksft_perror("Failed to open iMC config file"); +/* Get type and config of an iMC counter's read event. */ +static int read_from_imc_dir(char *imc_dir, unsigned int *count) +{ + char imc_counter_type[PATH_MAX]; + unsigned int type; + int path_len; + FILE *fp; + int ret; + /* Get type of iMC counter */ + path_len = snprintf(imc_counter_type, sizeof(imc_counter_type), + "%s%s", imc_dir, "type"); + if (path_len >= sizeof(imc_counter_type)) { + ksft_print_msg("Unable to create path to %s%s\n", + imc_dir, "type"); return -1; } - if (fscanf(fp, "%1023s", cas_count_cfg) <= 0) { - ksft_perror("Could not get iMC cas count write"); - fclose(fp); + fp = fopen(imc_counter_type, "r"); + if (!fp) { + ksft_perror("Failed to open iMC counter type file"); return -1; } + ret = fscanf(fp, "%u", &type); fclose(fp); - - get_event_and_umask(cas_count_cfg, count, WRITE); + if (ret <= 0) { + ksft_perror("Could not get iMC type"); + return -1; + } + ret = parse_imc_read_bw_events(imc_dir, type, count); + if (ret) { + ksft_print_msg("Unable to parse bandwidth event and umask\n"); + return ret; + } return 0; } /* * A system can have 'n' number of iMC (Integrated Memory Controller) - * counters, get that 'n'. For each iMC counter get it's type and config. - * Also, each counter has two configs, one for read and the other for write. - * A config again has two parts, event and umask. + * counters, get that 'n'. Discover the properties of the available + * counters in support of needed performance measurement via perf. + * For each iMC counter get it's type and config. Also obtain each + * counter's event and umask for the memory read events that will be + * measured. + * * Enumerate all these details into an array of structures. * * Return: >= 0 on success. < 0 on failure. @@ -250,13 +265,12 @@ static int num_of_imcs(void) if (temp[0] >= '0' && temp[0] <= '9') { sprintf(imc_dir, "%s/%s/", DYN_PMU_PATH, ep->d_name); - ret = read_from_imc_dir(imc_dir, count); + ret = read_from_imc_dir(imc_dir, &count); if (ret) { closedir(dp); return ret; } - count++; } } closedir(dp); @@ -274,214 +288,159 @@ static int num_of_imcs(void) return count; } -static int initialize_mem_bw_imc(void) +int initialize_read_mem_bw_imc(void) { - int imc, j; + int imc; imcs = num_of_imcs(); if (imcs <= 0) return imcs; /* Initialize perf_event_attr structures for all iMC's */ - for (imc = 0; imc < imcs; imc++) { - for (j = 0; j < 2; j++) - membw_initialize_perf_event_attr(imc, j); - } + for (imc = 0; imc < imcs; imc++) + read_mem_bw_initialize_perf_event_attr(imc); return 0; } -static void perf_close_imc_mem_bw(void) +static void perf_close_imc_read_mem_bw(void) { int mc; for (mc = 0; mc < imcs; mc++) { - if (imc_counters_config[mc][READ].fd != -1) - close(imc_counters_config[mc][READ].fd); - if (imc_counters_config[mc][WRITE].fd != -1) - close(imc_counters_config[mc][WRITE].fd); + if (imc_counters_config[mc].fd != -1) + close(imc_counters_config[mc].fd); } } /* - * get_mem_bw_imc: Memory band width as reported by iMC counters - * @cpu_no: CPU number that the benchmark PID is binded to - * @bw_report: Bandwidth report type (reads, writes) - * - * Memory B/W utilized by a process on a socket can be calculated using - * iMC counters. Perf events are used to read these counters. + * perf_open_imc_read_mem_bw - Open perf fds for IMCs + * @cpu_no: CPU number that the benchmark PID is bound to * * Return: = 0 on success. < 0 on failure. */ -static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc) +static int perf_open_imc_read_mem_bw(int cpu_no) { - float reads, writes, of_mul_read, of_mul_write; int imc, ret; - for (imc = 0; imc < imcs; imc++) { - imc_counters_config[imc][READ].fd = -1; - imc_counters_config[imc][WRITE].fd = -1; - } + for (imc = 0; imc < imcs; imc++) + imc_counters_config[imc].fd = -1; - /* Start all iMC counters to log values (both read and write) */ - reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1; for (imc = 0; imc < imcs; imc++) { - ret = open_perf_event(imc, cpu_no, READ); - if (ret) - goto close_fds; - ret = open_perf_event(imc, cpu_no, WRITE); + ret = open_perf_read_event(imc, cpu_no); if (ret) goto close_fds; - - membw_ioctl_perf_event_ioc_reset_enable(imc, READ); - membw_ioctl_perf_event_ioc_reset_enable(imc, WRITE); } + return 0; + +close_fds: + perf_close_imc_read_mem_bw(); + return -1; +} + +/* + * do_imc_read_mem_bw_test - Perform memory bandwidth test + * + * Runs memory bandwidth test over one second period. Also, handles starting + * and stopping of the IMC perf counters around the test. + */ +static void do_imc_read_mem_bw_test(void) +{ + int imc; + + for (imc = 0; imc < imcs; imc++) + read_mem_bw_ioctl_perf_event_ioc_reset_enable(imc); + sleep(1); - /* Stop counters after a second to get results (both read and write) */ - for (imc = 0; imc < imcs; imc++) { - membw_ioctl_perf_event_ioc_disable(imc, READ); - membw_ioctl_perf_event_ioc_disable(imc, WRITE); - } + /* Stop counters after a second to get results. */ + for (imc = 0; imc < imcs; imc++) + read_mem_bw_ioctl_perf_event_ioc_disable(imc); +} + +/* + * get_read_mem_bw_imc - Memory read bandwidth as reported by iMC counters + * + * Memory read bandwidth utilized by a process on a socket can be calculated + * using iMC counters' read events. Perf events are used to read these + * counters. + * + * Return: = 0 on success. < 0 on failure. + */ +static int get_read_mem_bw_imc(float *bw_imc) +{ + float reads = 0, of_mul_read = 1; + int imc; /* - * Get results which are stored in struct type imc_counter_config - * Take over flow into consideration before calculating total b/w + * Log read event values from all iMC counters into + * struct imc_counter_config. + * Take overflow into consideration before calculating total bandwidth. */ for (imc = 0; imc < imcs; imc++) { + struct membw_read_format measurement; struct imc_counter_config *r = - &imc_counters_config[imc][READ]; - struct imc_counter_config *w = - &imc_counters_config[imc][WRITE]; - - if (read(r->fd, &r->return_value, - sizeof(struct membw_read_format)) == -1) { - ksft_perror("Couldn't get read b/w through iMC"); - goto close_fds; - } + &imc_counters_config[imc]; - if (read(w->fd, &w->return_value, - sizeof(struct membw_read_format)) == -1) { - ksft_perror("Couldn't get write bw through iMC"); - goto close_fds; + if (read(r->fd, &measurement, sizeof(measurement)) == -1) { + ksft_perror("Couldn't get read bandwidth through iMC"); + return -1; } - __u64 r_time_enabled = r->return_value.time_enabled; - __u64 r_time_running = r->return_value.time_running; + __u64 r_time_enabled = measurement.time_enabled; + __u64 r_time_running = measurement.time_running; if (r_time_enabled != r_time_running) of_mul_read = (float)r_time_enabled / (float)r_time_running; - __u64 w_time_enabled = w->return_value.time_enabled; - __u64 w_time_running = w->return_value.time_running; - - if (w_time_enabled != w_time_running) - of_mul_write = (float)w_time_enabled / - (float)w_time_running; - reads += r->return_value.value * of_mul_read * SCALE; - writes += w->return_value.value * of_mul_write * SCALE; - } - - perf_close_imc_mem_bw(); - - if (strcmp(bw_report, "reads") == 0) { - *bw_imc = reads; - return 0; - } - - if (strcmp(bw_report, "writes") == 0) { - *bw_imc = writes; - return 0; + reads += measurement.value * of_mul_read * SCALE; } - *bw_imc = reads + writes; + *bw_imc = reads; return 0; - -close_fds: - perf_close_imc_mem_bw(); - return -1; } -void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id) +/* + * initialize_mem_bw_resctrl: Appropriately populate "mbm_total_path" + * @param: Parameters passed to resctrl_val() + * @domain_id: Domain ID (cache ID; for MB, L3 cache ID) + */ +void initialize_mem_bw_resctrl(const struct resctrl_val_param *param, + int domain_id) { - if (ctrlgrp && mongrp) - sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH, - RESCTRL_PATH, ctrlgrp, mongrp, resource_id); - else if (!ctrlgrp && mongrp) - sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, - mongrp, resource_id); - else if (ctrlgrp && !mongrp) - sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, - ctrlgrp, resource_id); - else if (!ctrlgrp && !mongrp) - sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, - resource_id); + sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, + param->ctrlgrp, domain_id); } /* - * initialize_mem_bw_resctrl: Appropriately populate "mbm_total_path" - * @ctrlgrp: Name of the control monitor group (con_mon grp) - * @mongrp: Name of the monitor group (mon grp) - * @cpu_no: CPU number that the benchmark PID is binded to - * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) + * Open file to read MBM local bytes from resctrl FS */ -static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp, - int cpu_no, char *resctrl_val) +static FILE *open_mem_bw_resctrl(const char *mbm_bw_file) { - int resource_id; - - if (get_resource_id(cpu_no, &resource_id) < 0) { - ksft_print_msg("Could not get resource_id\n"); - return; - } + FILE *fp; - if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) - set_mbm_path(ctrlgrp, mongrp, resource_id); + fp = fopen(mbm_bw_file, "r"); + if (!fp) + ksft_perror("Failed to open total memory bandwidth file"); - if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { - if (ctrlgrp) - sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, - RESCTRL_PATH, ctrlgrp, resource_id); - else - sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, - RESCTRL_PATH, resource_id); - } + return fp; } /* * Get MBM Local bytes as reported by resctrl FS - * For MBM, - * 1. If con_mon grp and mon grp are given, then read from con_mon grp's mon grp - * 2. If only con_mon grp is given, then read from con_mon grp - * 3. If both are not given, then read from root con_mon grp - * For MBA, - * 1. If con_mon grp is given, then read from it - * 2. If con_mon grp is not given, then read from root con_mon grp */ -static int get_mem_bw_resctrl(unsigned long *mbm_total) +static int get_mem_bw_resctrl(FILE *fp, unsigned long *mbm_total) { - FILE *fp; - - fp = fopen(mbm_total_path, "r"); - if (!fp) { - ksft_perror("Failed to open total bw file"); - + if (fscanf(fp, "%lu\n", mbm_total) <= 0) { + ksft_perror("Could not get MBM local bytes"); return -1; } - if (fscanf(fp, "%lu", mbm_total) <= 0) { - ksft_perror("Could not get mbm local bytes"); - fclose(fp); - - return -1; - } - fclose(fp); - return 0; } -pid_t bm_pid, ppid; +static pid_t bm_pid; void ctrlc_handler(int signum, siginfo_t *info, void *ptr) { @@ -489,7 +448,8 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr) if (bm_pid) kill(bm_pid, SIGKILL); umount_resctrlfs(); - tests_cleanup(); + if (current_test && current_test->cleanup) + current_test->cleanup(); ksft_print_msg("Ending\n\n"); exit(EXIT_SUCCESS); @@ -499,13 +459,14 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr) * Register CTRL-C handler for parent, as it has to kill * child process before exiting. */ -int signal_handler_register(void) +int signal_handler_register(const struct resctrl_test *test) { struct sigaction sigact = {}; int ret = 0; bm_pid = 0; + current_test = test; sigact.sa_sigaction = ctrlc_handler; sigemptyset(&sigact.sa_mask); sigact.sa_flags = SA_SIGINFO; @@ -527,6 +488,7 @@ void signal_handler_unregister(void) { struct sigaction sigact = {}; + current_test = NULL; sigact.sa_handler = SIG_DFL; sigemptyset(&sigact.sa_mask); if (sigaction(SIGINT, &sigact, NULL) || @@ -543,30 +505,30 @@ void signal_handler_unregister(void) * @bw_imc: perf imc counter value * @bw_resc: memory bandwidth value * - * Return: 0 on success. non-zero on failure. + * Return: 0 on success, < 0 on error. */ -static int print_results_bw(char *filename, int bm_pid, float bw_imc, +static int print_results_bw(char *filename, pid_t bm_pid, float bw_imc, unsigned long bw_resc) { unsigned long diff = fabs(bw_imc - bw_resc); FILE *fp; if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) { - printf("Pid: %d \t Mem_BW_iMC: %f \t ", bm_pid, bw_imc); + printf("Pid: %d \t Mem_BW_iMC: %f \t ", (int)bm_pid, bw_imc); printf("Mem_BW_resc: %lu \t Difference: %lu\n", bw_resc, diff); } else { fp = fopen(filename, "a"); if (!fp) { ksft_perror("Cannot open results file"); - return errno; + return -1; } if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n", - bm_pid, bw_imc, bw_resc, diff) <= 0) { + (int)bm_pid, bw_imc, bw_resc, diff) <= 0) { ksft_print_msg("Could not log results\n"); fclose(fp); - return errno; + return -1; } fclose(fp); } @@ -574,273 +536,157 @@ static int print_results_bw(char *filename, int bm_pid, float bw_imc, return 0; } -static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num) -{ - if (strlen(ctrlgrp) && strlen(mongrp)) - sprintf(llc_occup_path, CON_MON_LCC_OCCUP_PATH, RESCTRL_PATH, - ctrlgrp, mongrp, sock_num); - else if (!strlen(ctrlgrp) && strlen(mongrp)) - sprintf(llc_occup_path, MON_LCC_OCCUP_PATH, RESCTRL_PATH, - mongrp, sock_num); - else if (strlen(ctrlgrp) && !strlen(mongrp)) - sprintf(llc_occup_path, CON_LCC_OCCUP_PATH, RESCTRL_PATH, - ctrlgrp, sock_num); - else if (!strlen(ctrlgrp) && !strlen(mongrp)) - sprintf(llc_occup_path, LCC_OCCUP_PATH, RESCTRL_PATH, sock_num); -} - /* - * initialize_llc_occu_resctrl: Appropriately populate "llc_occup_path" - * @ctrlgrp: Name of the control monitor group (con_mon grp) - * @mongrp: Name of the monitor group (mon grp) - * @cpu_no: CPU number that the benchmark PID is binded to - * @resctrl_val: Resctrl feature (Eg: cat, cmt.. etc) + * measure_read_mem_bw - Measures read memory bandwidth numbers while benchmark runs + * @uparams: User supplied parameters + * @param: Parameters passed to resctrl_val() + * @bm_pid: PID that runs the benchmark + * + * Measure memory bandwidth from resctrl and from another source which is + * perf imc value or could be something else if perf imc event is not + * available. Compare the two values to validate resctrl value. It takes + * 1 sec to measure the data. + * resctrl does not distinguish between read and write operations so + * its data includes all memory operations. */ -static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp, - int cpu_no, char *resctrl_val) +int measure_read_mem_bw(const struct user_params *uparams, + struct resctrl_val_param *param, pid_t bm_pid) { - int resource_id; - - if (get_resource_id(cpu_no, &resource_id) < 0) { - ksft_print_msg("Could not get resource_id\n"); - return; - } - - if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - set_cmt_path(ctrlgrp, mongrp, resource_id); -} - -static int -measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start) -{ - unsigned long bw_resc, bw_resc_end; + unsigned long bw_resc, bw_resc_start, bw_resc_end; + FILE *mem_bw_fp; float bw_imc; int ret; - /* - * Measure memory bandwidth from resctrl and from - * another source which is perf imc value or could - * be something else if perf imc event is not available. - * Compare the two values to validate resctrl value. - * It takes 1sec to measure the data. - */ - ret = get_mem_bw_imc(param->cpu_no, param->bw_report, &bw_imc); + mem_bw_fp = open_mem_bw_resctrl(mbm_total_path); + if (!mem_bw_fp) + return -1; + + ret = perf_open_imc_read_mem_bw(uparams->cpu); if (ret < 0) - return ret; + goto close_fp; - ret = get_mem_bw_resctrl(&bw_resc_end); + ret = get_mem_bw_resctrl(mem_bw_fp, &bw_resc_start); if (ret < 0) - return ret; + goto close_imc; - bw_resc = (bw_resc_end - *bw_resc_start) / MB; - ret = print_results_bw(param->filename, bm_pid, bw_imc, bw_resc); - if (ret) - return ret; + rewind(mem_bw_fp); - *bw_resc_start = bw_resc_end; + do_imc_read_mem_bw_test(); - return 0; -} + ret = get_mem_bw_resctrl(mem_bw_fp, &bw_resc_end); + if (ret < 0) + goto close_imc; -/* - * run_benchmark - Run a specified benchmark or fill_buf (default benchmark) - * in specified signal. Direct benchmark stdio to /dev/null. - * @signum: signal number - * @info: signal info - * @ucontext: user context in signal handling - */ -static void run_benchmark(int signum, siginfo_t *info, void *ucontext) -{ - int operation, ret, memflush; - char **benchmark_cmd; - size_t span; - bool once; - FILE *fp; + ret = get_read_mem_bw_imc(&bw_imc); + if (ret < 0) + goto close_imc; - benchmark_cmd = info->si_ptr; + perf_close_imc_read_mem_bw(); + fclose(mem_bw_fp); - /* - * Direct stdio of child to /dev/null, so that only parent writes to - * stdio (console) - */ - fp = freopen("/dev/null", "w", stdout); - if (!fp) { - ksft_perror("Unable to direct benchmark status to /dev/null"); - PARENT_EXIT(); - } + bw_resc = (bw_resc_end - bw_resc_start) / MB; - if (strcmp(benchmark_cmd[0], "fill_buf") == 0) { - /* Execute default fill_buf benchmark */ - span = strtoul(benchmark_cmd[1], NULL, 10); - memflush = atoi(benchmark_cmd[2]); - operation = atoi(benchmark_cmd[3]); - if (!strcmp(benchmark_cmd[4], "true")) { - once = true; - } else if (!strcmp(benchmark_cmd[4], "false")) { - once = false; - } else { - ksft_print_msg("Invalid once parameter\n"); - PARENT_EXIT(); - } + return print_results_bw(param->filename, bm_pid, bw_imc, bw_resc); - if (run_fill_buf(span, memflush, operation, once)) - fprintf(stderr, "Error in running fill buffer\n"); - } else { - /* Execute specified benchmark */ - ret = execvp(benchmark_cmd[0], benchmark_cmd); - if (ret) - ksft_perror("execvp"); - } - - fclose(stdout); - ksft_print_msg("Unable to run specified benchmark\n"); - PARENT_EXIT(); +close_imc: + perf_close_imc_read_mem_bw(); +close_fp: + fclose(mem_bw_fp); + return ret; } /* * resctrl_val: execute benchmark and measure memory bandwidth on * the benchmark - * @benchmark_cmd: benchmark command and its arguments + * @test: test information structure + * @uparams: user supplied parameters * @param: parameters passed to resctrl_val() * - * Return: 0 on success. non-zero on failure. + * Return: 0 when the test was run, < 0 on error. */ -int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param) +int resctrl_val(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *param) { - char *resctrl_val = param->resctrl_val; - unsigned long bw_resc_start = 0; - struct sigaction sigact; - int ret = 0, pipefd[2]; - char pipe_message = 0; - union sigval value; + unsigned char *buf = NULL; + cpu_set_t old_affinity; + int domain_id; + int ret = 0; + pid_t ppid; if (strcmp(param->filename, "") == 0) sprintf(param->filename, "stdio"); - if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) || - !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) { - ret = validate_bw_report_request(param->bw_report); - if (ret) - return ret; + ret = get_domain_id(test->resource, uparams->cpu, &domain_id); + if (ret < 0) { + ksft_print_msg("Could not get domain ID\n"); + return ret; } - /* - * If benchmark wasn't successfully started by child, then child should - * kill parent, so save parent's pid - */ ppid = getpid(); - if (pipe(pipefd)) { - ksft_perror("Unable to create pipe"); + /* Taskset test to specified CPU. */ + ret = taskset_benchmark(ppid, uparams->cpu, &old_affinity); + if (ret) + return ret; + + /* Write test to specified control & monitoring group in resctrl FS. */ + ret = write_bm_pid_to_resctrl(ppid, param->ctrlgrp, param->mongrp); + if (ret) + goto reset_affinity; - return -1; + if (param->init) { + ret = param->init(test, uparams, param, domain_id); + if (ret) + goto reset_affinity; } /* - * Fork to start benchmark, save child's pid so that it can be killed - * when needed + * If not running user provided benchmark, run the default + * "fill_buf". First phase of "fill_buf" is to prepare the + * buffer that the benchmark will operate on. No measurements + * are needed during this phase and prepared memory will be + * passed to next part of benchmark via copy-on-write thus + * no impact on the benchmark that relies on reading from + * memory only. */ + if (param->fill_buf) { + buf = alloc_buffer(param->fill_buf->buf_size, + param->fill_buf->memflush); + if (!buf) { + ret = -ENOMEM; + goto reset_affinity; + } + } + fflush(stdout); bm_pid = fork(); if (bm_pid == -1) { + ret = -errno; ksft_perror("Unable to fork"); - - return -1; - } - - if (bm_pid == 0) { - /* - * Mask all signals except SIGUSR1, parent uses SIGUSR1 to - * start benchmark - */ - sigfillset(&sigact.sa_mask); - sigdelset(&sigact.sa_mask, SIGUSR1); - - sigact.sa_sigaction = run_benchmark; - sigact.sa_flags = SA_SIGINFO; - - /* Register for "SIGUSR1" signal from parent */ - if (sigaction(SIGUSR1, &sigact, NULL)) { - ksft_perror("Can't register child for signal"); - PARENT_EXIT(); - } - - /* Tell parent that child is ready */ - close(pipefd[0]); - pipe_message = 1; - if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) < - sizeof(pipe_message)) { - ksft_perror("Failed signaling parent process"); - close(pipefd[1]); - return -1; - } - close(pipefd[1]); - - /* Suspend child until delivery of "SIGUSR1" from parent */ - sigsuspend(&sigact.sa_mask); - - ksft_perror("Child is done"); - PARENT_EXIT(); + goto free_buf; } - ksft_print_msg("Benchmark PID: %d\n", bm_pid); - /* - * The cast removes constness but nothing mutates benchmark_cmd within - * the context of this process. At the receiving process, it becomes - * argv, which is mutable, on exec() but that's after fork() so it - * doesn't matter for the process running the tests. + * What needs to be measured runs in separate process until + * terminated. */ - value.sival_ptr = (void *)benchmark_cmd; - - /* Taskset benchmark to specified cpu */ - ret = taskset_benchmark(bm_pid, param->cpu_no); - if (ret) - goto out; - - /* Write benchmark to specified control&monitoring grp in resctrl FS */ - ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, - resctrl_val); - if (ret) - goto out; - - if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || - !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { - ret = initialize_mem_bw_imc(); - if (ret) - goto out; - - initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp, - param->cpu_no, resctrl_val); - } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp, - param->cpu_no, resctrl_val); - - /* Parent waits for child to be ready. */ - close(pipefd[1]); - while (pipe_message != 1) { - if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) < - sizeof(pipe_message)) { - ksft_perror("Failed reading message from child process"); - close(pipefd[0]); - goto out; - } + if (bm_pid == 0) { + if (param->fill_buf) + fill_cache_read(buf, param->fill_buf->buf_size, false); + else if (uparams->benchmark_cmd[0]) + execvp(uparams->benchmark_cmd[0], (char **)uparams->benchmark_cmd); + exit(EXIT_SUCCESS); } - close(pipefd[0]); - /* Signal child to start benchmark */ - if (sigqueue(bm_pid, SIGUSR1, value) == -1) { - ksft_perror("sigqueue SIGUSR1 to child"); - ret = errno; - goto out; - } + ksft_print_msg("Benchmark PID: %d\n", (int)bm_pid); - /* Give benchmark enough time to fully run */ + /* Give benchmark enough time to fully run. */ sleep(1); /* Test runs until the callback setup() tells the test to stop. */ while (1) { - ret = param->setup(param); + ret = param->setup(test, uparams, param); if (ret == END_OF_TESTS) { ret = 0; break; @@ -848,21 +694,15 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par if (ret < 0) break; - if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || - !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { - ret = measure_vals(param, &bw_resc_start); - if (ret) - break; - } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) { - sleep(1); - ret = measure_cache_vals(param, bm_pid); - if (ret) - break; - } + ret = param->measure(uparams, param, bm_pid); + if (ret) + break; } -out: kill(bm_pid, SIGKILL); - +free_buf: + free(buf); +reset_affinity: + taskset_restore(ppid, &old_affinity); return ret; } diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index fe3241799841b..b9c1bfb6cc029 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -8,10 +8,13 @@ * Sai Praneeth Prakhya , * Fenghua Yu */ +#include #include #include "resctrl.h" +int snc_unreliable; + static int find_resctrl_mount(char *buffer) { FILE *mounts; @@ -55,7 +58,7 @@ static int find_resctrl_mount(char *buffer) * Mounts resctrl FS. Fails if resctrl FS is already mounted to avoid * pre-existing settings interfering with the test results. * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ int mount_resctrlfs(void) { @@ -87,39 +90,65 @@ int umount_resctrlfs(void) if (umount(mountpoint)) { ksft_perror("Unable to umount resctrl"); - return errno; + return -1; } return 0; } /* - * get_resource_id - Get socket number/l3 id for a specified CPU + * get_cache_level - Convert cache level from string to integer + * @cache_type: Cache level as string + * + * Return: cache level as integer or -1 if @cache_type is invalid. + */ +static int get_cache_level(const char *cache_type) +{ + if (!strcmp(cache_type, "L3")) + return 3; + if (!strcmp(cache_type, "L2")) + return 2; + + ksft_print_msg("Invalid cache level\n"); + return -1; +} + +static int get_resource_cache_level(const char *resource) +{ + /* "MB" use L3 (LLC) as resource */ + if (!strcmp(resource, "MB")) + return 3; + return get_cache_level(resource); +} + +/* + * get_domain_id - Get resctrl domain ID for a specified CPU + * @resource: resource name * @cpu_no: CPU number - * @resource_id: Socket number or l3_id + * @domain_id: domain ID (cache ID; for MB, L3 cache ID) * * Return: >= 0 on success, < 0 on failure. */ -int get_resource_id(int cpu_no, int *resource_id) +int get_domain_id(const char *resource, int cpu_no, int *domain_id) { char phys_pkg_path[1024]; + int cache_num; FILE *fp; - if (get_vendor() == ARCH_AMD) - sprintf(phys_pkg_path, "%s%d/cache/index3/id", - PHYS_ID_PATH, cpu_no); - else - sprintf(phys_pkg_path, "%s%d/topology/physical_package_id", - PHYS_ID_PATH, cpu_no); + cache_num = get_resource_cache_level(resource); + if (cache_num < 0) + return cache_num; + + sprintf(phys_pkg_path, "%s%d/cache/index%d/id", PHYS_ID_PATH, cpu_no, cache_num); fp = fopen(phys_pkg_path, "r"); if (!fp) { - ksft_perror("Failed to open physical_package_id"); + ksft_perror("Failed to open cache id file"); return -1; } - if (fscanf(fp, "%d", resource_id) <= 0) { - ksft_perror("Could not get socket number or l3 id"); + if (fscanf(fp, "%d", domain_id) <= 0) { + ksft_perror("Could not get domain ID"); fclose(fp); return -1; @@ -129,6 +158,108 @@ int get_resource_id(int cpu_no, int *resource_id) return 0; } +/* + * Count number of CPUs in a /sys bitmap + */ +static unsigned int count_sys_bitmap_bits(char *name) +{ + FILE *fp = fopen(name, "r"); + int count = 0, c; + + if (!fp) + return 0; + + while ((c = fgetc(fp)) != EOF) { + if (!isxdigit(c)) + continue; + switch (c) { + case 'f': + count++; + fallthrough; + case '7': case 'b': case 'd': case 'e': + count++; + fallthrough; + case '3': case '5': case '6': case '9': case 'a': case 'c': + count++; + fallthrough; + case '1': case '2': case '4': case '8': + count++; + break; + } + } + fclose(fp); + + return count; +} + +static bool cpus_offline_empty(void) +{ + char offline_cpus_str[64]; + FILE *fp; + + fp = fopen("/sys/devices/system/cpu/offline", "r"); + if (!fp) { + ksft_perror("Could not open /sys/devices/system/cpu/offline"); + return 0; + } + + if (fscanf(fp, "%63s", offline_cpus_str) < 0) { + if (!errno) { + fclose(fp); + return 1; + } + ksft_perror("Could not read /sys/devices/system/cpu/offline"); + } + + fclose(fp); + + return 0; +} + +/* + * Detect SNC by comparing #CPUs in node0 with #CPUs sharing LLC with CPU0. + * If any CPUs are offline declare the detection as unreliable. + */ +int snc_nodes_per_l3_cache(void) +{ + int node_cpus, cache_cpus; + static int snc_mode; + + if (!snc_mode) { + snc_mode = 1; + if (!cpus_offline_empty()) { + ksft_print_msg("Runtime SNC detection unreliable due to offline CPUs.\n"); + ksft_print_msg("Setting SNC mode to disabled.\n"); + snc_unreliable = 1; + return snc_mode; + } + node_cpus = count_sys_bitmap_bits("/sys/devices/system/node/node0/cpumap"); + cache_cpus = count_sys_bitmap_bits("/sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_map"); + + if (!node_cpus || !cache_cpus) { + ksft_print_msg("Could not determine Sub-NUMA Cluster mode.\n"); + snc_unreliable = 1; + return snc_mode; + } + snc_mode = cache_cpus / node_cpus; + + /* + * On some platforms (e.g. Hygon), + * cache_cpus < node_cpus, the calculated snc_mode is 0. + * + * Set snc_mode = 1 to indicate that SNC mode is not + * supported on the platform. + */ + if (!snc_mode) + snc_mode = 1; + + if (snc_mode > 1) + ksft_print_msg("SNC-%d mode discovered.\n", snc_mode); + } + + return snc_mode; +} + /* * get_cache_size - Get cache size for a specified CPU * @cpu_no: CPU number @@ -137,20 +268,15 @@ int get_resource_id(int cpu_no, int *resource_id) * * Return: = 0 on success, < 0 on failure. */ -int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size) +int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size) { char cache_path[1024], cache_str[64]; int length, i, cache_num; FILE *fp; - if (!strcmp(cache_type, "L3")) { - cache_num = 3; - } else if (!strcmp(cache_type, "L2")) { - cache_num = 2; - } else { - ksft_print_msg("Invalid cache level\n"); - return -1; - } + cache_num = get_cache_level(cache_type); + if (cache_num < 0) + return cache_num; sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size", cpu_no, cache_num); @@ -189,36 +315,46 @@ int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size) break; } + /* + * The amount of cache represented by each bit in the masks + * in the schemata file is reduced by a factor equal to SNC + * nodes per L3 cache. + * E.g. on a SNC-2 system with a 100MB L3 cache a test that + * allocates memory from its local SNC node (default behavior + * without using libnuma) will only see 50 MB llc_occupancy + * with a fully populated L3 mask in the schemata file. + */ + if (cache_num == 3) + *cache_size /= snc_nodes_per_l3_cache(); return 0; } #define CORE_SIBLINGS_PATH "/sys/bus/cpu/devices/cpu" /* - * get_cbm_mask - Get cbm mask for given cache - * @cache_type: Cache level L2/L3 - * @cbm_mask: cbm_mask returned as a string + * get_bit_mask - Get bit mask from given file + * @filename: File containing the mask + * @mask: The bit mask returned as unsigned long * * Return: = 0 on success, < 0 on failure. */ -int get_cbm_mask(char *cache_type, char *cbm_mask) +static int get_bit_mask(const char *filename, unsigned long *mask) { - char cbm_mask_path[1024]; FILE *fp; - if (!cbm_mask) + if (!filename || !mask) return -1; - sprintf(cbm_mask_path, "%s/%s/cbm_mask", INFO_PATH, cache_type); - - fp = fopen(cbm_mask_path, "r"); + fp = fopen(filename, "r"); if (!fp) { - ksft_perror("Failed to open cache level"); - + ksft_print_msg("Failed to open bit mask file '%s': %s\n", + filename, strerror(errno)); return -1; } - if (fscanf(fp, "%s", cbm_mask) <= 0) { - ksft_perror("Could not get max cbm_mask"); + + if (fscanf(fp, "%lx", mask) <= 0) { + ksft_print_msg("Could not read bit mask file '%s': %s\n", + filename, strerror(errno)); fclose(fp); return -1; @@ -229,58 +365,177 @@ int get_cbm_mask(char *cache_type, char *cbm_mask) } /* - * get_core_sibling - Get sibling core id from the same socket for given CPU - * @cpu_no: CPU number + * resource_info_unsigned_get - Read an unsigned value from + * /sys/fs/resctrl/info/@resource/@filename + * @resource: Resource name that matches directory name in + * /sys/fs/resctrl/info + * @filename: File in /sys/fs/resctrl/info/@resource + * @val: Contains read value on success. * - * Return: > 0 on success, < 0 on failure. + * Return: = 0 on success, < 0 on failure. On success the read + * value is saved into @val. */ -int get_core_sibling(int cpu_no) +int resource_info_unsigned_get(const char *resource, const char *filename, + unsigned int *val) { - char core_siblings_path[1024], cpu_list_str[64]; - int sibling_cpu_no = -1; + char file_path[PATH_MAX]; FILE *fp; - sprintf(core_siblings_path, "%s%d/topology/core_siblings_list", - CORE_SIBLINGS_PATH, cpu_no); + snprintf(file_path, sizeof(file_path), "%s/%s/%s", INFO_PATH, resource, + filename); - fp = fopen(core_siblings_path, "r"); + fp = fopen(file_path, "r"); if (!fp) { - ksft_perror("Failed to open core siblings path"); - + ksft_print_msg("Error opening %s: %m\n", file_path); return -1; } - if (fscanf(fp, "%s", cpu_list_str) <= 0) { - ksft_perror("Could not get core_siblings list"); - fclose(fp); + if (fscanf(fp, "%u", val) <= 0) { + ksft_print_msg("Could not get contents of %s: %m\n", file_path); + fclose(fp); return -1; } + fclose(fp); + return 0; +} - char *token = strtok(cpu_list_str, "-,"); +/* + * create_bit_mask- Create bit mask from start, len pair + * @start: LSB of the mask + * @len Number of bits in the mask + */ +unsigned long create_bit_mask(unsigned int start, unsigned int len) +{ + return ((1UL << len) - 1UL) << start; +} - while (token) { - sibling_cpu_no = atoi(token); - /* Skipping core 0 as we don't want to run test on core 0 */ - if (sibling_cpu_no != 0 && sibling_cpu_no != cpu_no) - break; - token = strtok(NULL, "-,"); +/* + * count_contiguous_bits - Returns the longest train of bits in a bit mask + * @val A bit mask + * @start The location of the least-significant bit of the longest train + * + * Return: The length of the contiguous bits in the longest train of bits + */ +unsigned int count_contiguous_bits(unsigned long val, unsigned int *start) +{ + unsigned long last_val; + unsigned int count = 0; + + while (val) { + last_val = val; + val &= (val >> 1); + count++; } - return sibling_cpu_no; + if (start) { + if (count) + *start = ffsl(last_val) - 1; + else + *start = 0; + } + + return count; +} + +/* + * get_full_cbm - Get full Cache Bit Mask (CBM) + * @cache_type: Cache type as "L2" or "L3" + * @mask: Full cache bit mask representing the maximal portion of cache + * available for allocation, returned as unsigned long. + * + * Return: = 0 on success, < 0 on failure. + */ +int get_full_cbm(const char *cache_type, unsigned long *mask) +{ + char cbm_path[PATH_MAX]; + int ret; + + if (!cache_type) + return -1; + + snprintf(cbm_path, sizeof(cbm_path), "%s/%s/cbm_mask", + INFO_PATH, cache_type); + + ret = get_bit_mask(cbm_path, mask); + if (ret || !*mask) + return -1; + + return 0; +} + +/* + * get_shareable_mask - Get shareable mask from shareable_bits + * @cache_type: Cache type as "L2" or "L3" + * @shareable_mask: Shareable mask returned as unsigned long + * + * Return: = 0 on success, < 0 on failure. + */ +static int get_shareable_mask(const char *cache_type, unsigned long *shareable_mask) +{ + char mask_path[PATH_MAX]; + + if (!cache_type) + return -1; + + snprintf(mask_path, sizeof(mask_path), "%s/%s/shareable_bits", + INFO_PATH, cache_type); + + return get_bit_mask(mask_path, shareable_mask); +} + +/* + * get_mask_no_shareable - Get Cache Bit Mask (CBM) without shareable bits + * @cache_type: Cache type as "L2" or "L3" + * @mask: The largest exclusive portion of the cache out of the + * full CBM, returned as unsigned long + * + * Parts of a cache may be shared with other devices such as GPU. This function + * calculates the largest exclusive portion of the cache where no other devices + * besides CPU have access to the cache portion. + * + * Return: = 0 on success, < 0 on failure. + */ +int get_mask_no_shareable(const char *cache_type, unsigned long *mask) +{ + unsigned long full_mask, shareable_mask; + unsigned int start, len; + + if (get_full_cbm(cache_type, &full_mask) < 0) + return -1; + if (get_shareable_mask(cache_type, &shareable_mask) < 0) + return -1; + + len = count_contiguous_bits(full_mask & ~shareable_mask, &start); + if (!len) + return -1; + + *mask = create_bit_mask(start, len); + + return 0; } /* * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu - * @bm_pid: PID that should be binded - * @cpu_no: CPU number at which the PID would be binded + * @bm_pid: PID that should be binded + * @cpu_no: CPU number at which the PID would be binded + * @old_affinity: When not NULL, set to old CPU affinity * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ -int taskset_benchmark(pid_t bm_pid, int cpu_no) +int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity) { cpu_set_t my_set; + if (old_affinity) { + CPU_ZERO(old_affinity); + if (sched_getaffinity(bm_pid, sizeof(*old_affinity), + old_affinity)) { + ksft_perror("Unable to read CPU affinity"); + return -1; + } + } + CPU_ZERO(&my_set); CPU_SET(cpu_no, &my_set); @@ -293,13 +548,33 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no) return 0; } +/* + * taskset_restore - Taskset PID to the earlier CPU affinity + * @bm_pid: PID that should be reset + * @old_affinity: The old CPU affinity to restore + * + * Return: 0 on success, < 0 on error. + */ +int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity) +{ + if (sched_setaffinity(bm_pid, sizeof(*old_affinity), old_affinity)) { + ksft_perror("Unable to restore CPU affinity"); + return -1; + } + + return 0; +} + /* * create_grp - Create a group only if one doesn't exist * @grp_name: Name of the group * @grp: Full path and name of the group * @parent_grp: Full path and name of the parent group * - * Return: 0 on success, non-zero on failure + * Creates a group @grp_name if it does not exist yet. If @grp_name is NULL, + * it is interpreted as the root group which always results in success. + * + * Return: 0 on success, < 0 on error. */ static int create_grp(const char *grp_name, char *grp, const char *parent_grp) { @@ -307,12 +582,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp) struct dirent *ep; DIR *dp; - /* - * At this point, we are guaranteed to have resctrl FS mounted and if - * length of grp_name == 0, it means, user wants to use root con_mon - * grp, so do nothing - */ - if (strlen(grp_name) == 0) + if (!grp_name) return 0; /* Check if requested grp exists or not */ @@ -351,7 +621,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid) return -1; } - if (fprintf(fp, "%d\n", pid) < 0) { + if (fprintf(fp, "%d\n", (int)pid) < 0) { ksft_print_msg("Failed to write pid to tasks file\n"); fclose(fp); @@ -367,7 +637,6 @@ static int write_pid_to_tasks(char *tasks, pid_t pid) * @bm_pid: PID that should be written * @ctrlgrp: Name of the control monitor group (con_mon grp) * @mongrp: Name of the monitor group (mon grp) - * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) * * If a con_mon grp is requested, create it and write pid to it, otherwise * write pid to root con_mon grp. @@ -375,16 +644,15 @@ static int write_pid_to_tasks(char *tasks, pid_t pid) * pid is not written, this means that pid is in con_mon grp and hence * should consult con_mon grp's mon_data directory for results. * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ -int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, - char *resctrl_val) +int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp, const char *mongrp) { char controlgroup[128], monitorgroup[512], monitorgroup_p[256]; char tasks[1024]; int ret = 0; - if (strlen(ctrlgrp)) + if (ctrlgrp) sprintf(controlgroup, "%s/%s", RESCTRL_PATH, ctrlgrp); else sprintf(controlgroup, "%s", RESCTRL_PATH); @@ -398,22 +666,19 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, if (ret) goto out; - /* Create mon grp and write pid into it for "mbm" and "cmt" test */ - if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)) || - !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) { - if (strlen(mongrp)) { - sprintf(monitorgroup_p, "%s/mon_groups", controlgroup); - sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp); - ret = create_grp(mongrp, monitorgroup, monitorgroup_p); - if (ret) - goto out; - - sprintf(tasks, "%s/mon_groups/%s/tasks", - controlgroup, mongrp); - ret = write_pid_to_tasks(tasks, bm_pid); - if (ret) - goto out; - } + /* Create monitor group and write pid into if it is used */ + if (mongrp) { + sprintf(monitorgroup_p, "%s/mon_groups", controlgroup); + sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp); + ret = create_grp(mongrp, monitorgroup, monitorgroup_p); + if (ret) + goto out; + + sprintf(tasks, "%s/mon_groups/%s/tasks", + controlgroup, mongrp); + ret = write_pid_to_tasks(tasks, bm_pid); + if (ret) + goto out; } out: @@ -429,24 +694,18 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, * @ctrlgrp: Name of the con_mon grp * @schemata: Schemata that should be updated to * @cpu_no: CPU number that the benchmark PID is binded to - * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) + * @resource: Resctrl resource (Eg: MB, L3, L2, etc.) * - * Update schemata of a con_mon grp *only* if requested resctrl feature is + * Update schemata of a con_mon grp *only* if requested resctrl resource is * allocation type * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ -int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) +int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no, + const char *resource) { - char controlgroup[1024], schema[1024], reason[64]; - int resource_id, ret = 0; - FILE *fp; - - if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) && - strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) && - strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) && - strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - return -ENOENT; + char controlgroup[1024], reason[128], schema[1024] = {}; + int domain_id, fd, schema_len, ret = 0; if (!schemata) { ksft_print_msg("Skipping empty schemata update\n"); @@ -454,42 +713,47 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) return -1; } - if (get_resource_id(cpu_no, &resource_id) < 0) { - sprintf(reason, "Failed to get resource id"); + if (get_domain_id(resource, cpu_no, &domain_id) < 0) { + sprintf(reason, "Failed to get domain ID"); ret = -1; goto out; } - if (strlen(ctrlgrp) != 0) + if (ctrlgrp) sprintf(controlgroup, "%s/%s/schemata", RESCTRL_PATH, ctrlgrp); else sprintf(controlgroup, "%s/schemata", RESCTRL_PATH); - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) || - !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - sprintf(schema, "%s%d%c%s", "L3:", resource_id, '=', schemata); - if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) || - !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) - sprintf(schema, "%s%d%c%s", "MB:", resource_id, '=', schemata); - - fp = fopen(controlgroup, "w"); - if (!fp) { - sprintf(reason, "Failed to open control group"); + schema_len = snprintf(schema, sizeof(schema), "%s:%d=%s\n", + resource, domain_id, schemata); + if (schema_len < 0 || schema_len >= sizeof(schema)) { + snprintf(reason, sizeof(reason), + "snprintf() failed with return value : %d", schema_len); ret = -1; - goto out; } - if (fprintf(fp, "%s\n", schema) < 0) { - sprintf(reason, "Failed to write schemata in control group"); - fclose(fp); + fd = open(controlgroup, O_WRONLY); + if (fd < 0) { + snprintf(reason, sizeof(reason), + "open() failed : %s", strerror(errno)); ret = -1; - goto out; + goto err_schema_not_empty; } - fclose(fp); + if (write(fd, schema, schema_len) < 0) { + snprintf(reason, sizeof(reason), + "write() failed : %s", strerror(errno)); + close(fd); + ret = -1; + + goto err_schema_not_empty; + } + close(fd); +err_schema_not_empty: + schema[schema_len - 1] = 0; out: ksft_print_msg("Write schema \"%s\" to resctrl FS%s%s\n", schema, ret ? " # " : "", @@ -553,20 +817,16 @@ char *fgrep(FILE *inf, const char *str) } /* - * validate_resctrl_feature_request - Check if requested feature is valid. - * @resource: Required resource (e.g., MB, L3, L2, L3_MON, etc.) - * @feature: Required monitor feature (in mon_features file). Can only be - * set for L3_MON. Must be NULL for all other resources. + * resctrl_resource_exists - Check if a resource is supported. + * @resource: Resctrl resource (e.g., MB, L3, L2, L3_MON, etc.) * - * Return: True if the resource/feature is supported, else false. False is + * Return: True if the resource is supported, else false. False is * also returned if resctrl FS is not mounted. */ -bool validate_resctrl_feature_request(const char *resource, const char *feature) +bool resctrl_resource_exists(const char *resource) { char res_path[PATH_MAX]; struct stat statbuf; - char *res; - FILE *inf; int ret; if (!resource) @@ -581,8 +841,25 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature) if (stat(res_path, &statbuf)) return false; - if (!feature) - return true; + return true; +} + +/* + * resctrl_mon_feature_exists - Check if requested monitoring feature is valid. + * @resource: Resource that uses the mon_features file. Currently only L3_MON + * is valid. + * @feature: Required monitor feature (in mon_features file). + * + * Return: True if the feature is supported, else false. + */ +bool resctrl_mon_feature_exists(const char *resource, const char *feature) +{ + char res_path[PATH_MAX]; + char *res; + FILE *inf; + + if (!feature || !resource) + return false; snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource); inf = fopen(res_path, "r"); @@ -596,6 +873,36 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature) return !!res; } +/* + * resource_info_file_exists - Check if a file is present inside + * /sys/fs/resctrl/info/@resource. + * @resource: Required resource (Eg: MB, L3, L2, etc.) + * @file: Required file. + * + * Return: True if the /sys/fs/resctrl/info/@resource/@file exists, else false. + */ +bool resource_info_file_exists(const char *resource, const char *file) +{ + char res_path[PATH_MAX]; + struct stat statbuf; + + if (!file || !resource) + return false; + + snprintf(res_path, sizeof(res_path), "%s/%s/%s", INFO_PATH, resource, + file); + + if (stat(res_path, &statbuf)) + return false; + + return true; +} + +bool test_resource_feature_check(const struct resctrl_test *test) +{ + return resctrl_resource_exists(test->resource); +} + int filter_dmesg(void) { char line[1024]; @@ -639,24 +946,6 @@ int filter_dmesg(void) return 0; } -int validate_bw_report_request(char *bw_report) -{ - if (strcmp(bw_report, "reads") == 0) - return 0; - if (strcmp(bw_report, "writes") == 0) - return 0; - if (strcmp(bw_report, "nt-writes") == 0) { - strcpy(bw_report, "writes"); - return 0; - } - if (strcmp(bw_report, "total") == 0) - return 0; - - fprintf(stderr, "Requested iMC B/W report type unavailable\n"); - - return -1; -} - int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags) { @@ -678,3 +967,35 @@ unsigned int count_bits(unsigned long n) return count; } + +/** + * snc_kernel_support - Check for existence of mon_sub_L3_00 file that indicates + * SNC resctrl support on the kernel side. + * + * Return: 0 if not supported, 1 if SNC is disabled or SNC discovery is + * unreliable or SNC is both enabled and supported. + */ +int snc_kernel_support(void) +{ + char node_path[PATH_MAX]; + struct stat statbuf; + int ret; + + ret = snc_nodes_per_l3_cache(); + /* + * If SNC is disabled then its kernel support isn't important. If SNC + * got disabled because the discovery process was unreliable the + * snc_unreliable variable was set. It can be used to verify the SNC + * discovery reliability elsewhere in the selftest. + */ + if (ret == 1) + return ret; + + snprintf(node_path, sizeof(node_path), "%s/%s", RESCTRL_PATH, + "mon_data/mon_L3_00/mon_sub_L3_00"); + + if (!stat(node_path, &statbuf)) + return 1; + + return 0; +}