/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_RESCTRL_INTERNAL_H #define _ASM_X86_RESCTRL_INTERNAL_H #include <linux/resctrl.h> #include <linux/sched.h> #include <linux/kernfs.h> #include <linux/fs_context.h> #include <linux/jump_label.h> #include <linux/tick.h> #include <asm/resctrl.h> #define L3_QOS_CDP_ENABLE … #define L2_QOS_CDP_ENABLE … #define CQM_LIMBOCHECK_INTERVAL … #define MBM_CNTR_WIDTH_BASE … #define MBM_OVERFLOW_INTERVAL … #define MAX_MBA_BW … #define MBA_IS_LINEAR … #define MBM_CNTR_WIDTH_OFFSET_AMD … #define RMID_VAL_ERROR … #define RMID_VAL_UNAVAIL … /* * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for * data to be returned. The counter width is discovered from the hardware * as an offset from MBM_CNTR_WIDTH_BASE. */ #define MBM_CNTR_WIDTH_OFFSET_MAX … /* Reads to Local DRAM Memory */ #define READS_TO_LOCAL_MEM … /* Reads to Remote DRAM Memory */ #define READS_TO_REMOTE_MEM … /* Non-Temporal Writes to Local Memory */ #define NON_TEMP_WRITE_TO_LOCAL_MEM … /* Non-Temporal Writes to Remote Memory */ #define NON_TEMP_WRITE_TO_REMOTE_MEM … /* Reads to Local Memory the system identifies as "Slow Memory" */ #define READS_TO_LOCAL_S_MEM … /* Reads to Remote Memory the system identifies as "Slow Memory" */ #define READS_TO_REMOTE_S_MEM … /* Dirty Victims to All Types of Memory */ #define DIRTY_VICTIMS_TO_ALL_MEM … /* Max event bits supported */ #define MAX_EVT_CONFIG_BITS … /** * 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) { … } struct rdt_fs_context { … }; static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) { … } /** * 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 { … }; /** * 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. */ mon_data_bits; /** * 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 { … }; extern unsigned int rdt_mon_features; extern struct list_head resctrl_schema_all; extern bool resctrl_mounted; enum rdt_group_type { … }; /** * 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 { … }; /** * 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 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 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 { … }; /* rdtgroup.flags */ #define RDT_DELETED … /* rftype.flags */ #define RFTYPE_FLAGS_CPUS_LIST … /* * Define the file type flags for base and info directories. */ #define RFTYPE_INFO … #define RFTYPE_BASE … #define RFTYPE_CTRL … #define RFTYPE_MON … #define RFTYPE_TOP … #define RFTYPE_RES_CACHE … #define RFTYPE_RES_MB … #define RFTYPE_DEBUG … #define RFTYPE_CTRL_INFO … #define RFTYPE_MON_INFO … #define RFTYPE_TOP_INFO … #define RFTYPE_CTRL_BASE … #define RFTYPE_MON_BASE … /* 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 { … }; /** * 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 { … }; /** * struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s * return value. * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) * @prev_msr: Value of IA32_QM_CTR last time it was read for the RMID used to * find this struct. */ struct arch_mbm_state { … }; /** * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share * a resource for a control function * @d_resctrl: Properties exposed to the resctrl file system * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) * * Members of this structure are accessed via helpers that provide abstraction. */ 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 * * Members of this structure are accessed via helpers that provide abstraction. */ struct rdt_hw_mon_domain { … }; static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r) { … } static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r) { … } /** * struct msr_param - set a range of MSRs from a domain * @res: The resource to use * @dom: The domain to update * @low: Beginning index from base MSR * @high: End index */ struct msr_param { … }; static inline bool is_llc_occupancy_enabled(void) { … } static inline bool is_mbm_total_enabled(void) { … } static inline bool is_mbm_local_enabled(void) { … } static inline bool is_mbm_enabled(void) { … } static inline bool is_mbm_event(int e) { … } struct rdt_parse_data { … }; /** * struct rdt_hw_resource - arch private attributes of a resctrl resource * @r_resctrl: Attributes of the resource used directly by resctrl. * @num_closid: Maximum number of closid this hardware can support, * regardless of CDP. This is exposed via * resctrl_arch_get_num_closid() to avoid confusion * with struct resctrl_schema's property of the same name, * which has been corrected for features like CDP. * @msr_base: Base MSR address for CBMs * @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 * * Members of this structure are either private to the architecture * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g. * msr_update and msr_base. */ struct rdt_hw_resource { … }; static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r) { … } 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 { … }; static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res) { … } static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l) { … } 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) … #define for_each_capable_rdt_resource(r) … #define for_each_alloc_capable_rdt_resource(r) … #define for_each_mon_capable_rdt_resource(r) … /* CPUID.(EAX=10H, ECX=ResID=1).EAX */ cpuid_0x10_1_eax; /* CPUID.(EAX=10H, ECX=ResID=3).EAX */ cpuid_0x10_3_eax; /* CPUID.(EAX=10H, ECX=ResID).ECX */ cpuid_0x10_x_ecx; /* CPUID.(EAX=10H, ECX=ResID).EDX */ cpuid_0x10_x_edx; 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, ...); 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); 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); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */