Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140/* * Performance events: * * Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */#ifndef _LINUX_PERF_EVENT_H#define _LINUX_PERF_EVENT_H
#include <uapi/linux/perf_event.h>#include <uapi/linux/bpf_perf_event.h>
/* * Kernel-internal data types and definitions: */
#ifdef CONFIG_PERF_EVENTS# include <asm/perf_event.h># include <asm/local64.h>#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT# include <linux/rhashtable-types.h># include <asm/hw_breakpoint.h>#endif
#include <linux/list.h>#include <linux/mutex.h>#include <linux/rculist.h>#include <linux/rcupdate.h>#include <linux/spinlock.h>#include <linux/hrtimer.h>#include <linux/fs.h>#include <linux/pid_namespace.h>#include <linux/workqueue.h>#include <linux/ftrace.h>#include <linux/cpu.h>#include <linux/irq_work.h>#include <linux/static_key.h>#include <linux/jump_label_ratelimit.h>#include <linux/atomic.h>#include <linux/sysfs.h>#include <linux/perf_regs.h>#include <linux/cgroup.h>#include <linux/refcount.h>#include <linux/security.h>#include <linux/static_call.h>#include <linux/lockdep.h>
#include <asm/local.h>
struct perf_callchain_entry { u64 nr; u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */};
struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed;};
typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len);
struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size;} __packed;
struct perf_raw_record { struct perf_raw_frag frag; u32 size;};
static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag){ return frag->pad < sizeof(u64);}
/* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */struct perf_branch_stack { u64 nr; u64 hw_idx; struct perf_branch_entry entries[];};
struct task_struct;
/* * extra PMU register associated with an event */struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */};
/** * hw_perf_event::flag values * * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */#define PERF_EVENT_FLAG_ARCH 0x0fffffff#define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000
static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0);
/** * struct hw_perf_event - performance event hardware details: */struct hw_perf_event {#ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 config1; u64 last_tag; u64 dyn_constraint; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags;
struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* aux / Intel-PT */ u64 aux_config; /* * For AUX area events, aux_paused cannot be a state * flag because it can be updated asynchronously to * state. */ unsigned int aux_paused; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; };#ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct rhlist_head bp_list; };#endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target;
/* * PMU would store hardware filter configuration * here. */ void *addr_filters;
/* Last sync'ed generation of filters */ unsigned long addr_filters_gen;
/* * hw_perf_event::state flags; used to track the PERF_EF_* state. */
/* the counter is stopped */#define PERF_HES_STOPPED 0x01
/* event->count up-to-date */#define PERF_HES_UPTODATE 0x02
#define PERF_HES_ARCH 0x04
int state;
/* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count;
/* * The period to start the next sample with. */ u64 sample_period;
union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period;
/* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; };
/* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts;
/* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp;#endif /* CONFIG_PERF_EVENTS */};
struct perf_event;struct perf_event_pmu_context;
/* * Common implementation detail of pmu::{start,commit,cancel}_txn */
/* txn to add/schedule event on PMU */#define PERF_PMU_TXN_ADD 0x1
/* txn to read event group from PMU */#define PERF_PMU_TXN_READ 0x2
/** * pmu::capabilities flags */#define PERF_PMU_CAP_NO_INTERRUPT 0x0001#define PERF_PMU_CAP_NO_NMI 0x0002#define PERF_PMU_CAP_AUX_NO_SG 0x0004#define PERF_PMU_CAP_EXTENDED_REGS 0x0008#define PERF_PMU_CAP_EXCLUSIVE 0x0010#define PERF_PMU_CAP_ITRACE 0x0020#define PERF_PMU_CAP_NO_EXCLUDE 0x0040#define PERF_PMU_CAP_AUX_OUTPUT 0x0080#define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100#define PERF_PMU_CAP_AUX_PAUSE 0x0200#define PERF_PMU_CAP_AUX_PREFER_LARGE 0x0400#define PERF_PMU_CAP_MEDIATED_VPMU 0x0800
/** * pmu::scope */enum perf_pmu_scope { PERF_PMU_SCOPE_NONE = 0, PERF_PMU_SCOPE_CORE, PERF_PMU_SCOPE_DIE, PERF_PMU_SCOPE_CLUSTER, PERF_PMU_SCOPE_PKG, PERF_PMU_SCOPE_SYS_WIDE, PERF_PMU_MAX_SCOPE,};
struct perf_output_handle;
#define PMU_NULL_DEV ((void *)(~0UL))
/** * struct pmu - generic performance monitoring unit */struct pmu { struct list_head entry;
spinlock_t events_lock; struct list_head events;
struct module *module; struct device *dev; struct device *parent; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type;
/* * various common per-pmu feature flags */ int capabilities;
/* * PMU scope */ unsigned int scope;
struct perf_cpu_pmu_context * __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms;
/* number of address filters this PMU can do */ unsigned int nr_addr_filters;
/* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */
/* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event);
/* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */
/* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */
/* start the counter when adding */#define PERF_EF_START 0x01
/* reload the counter when starting */#define PERF_EF_RELOAD 0x02
/* update the counter when stopping */#define PERF_EF_UPDATE 0x04
/* AUX area event, pause tracing */#define PERF_EF_PAUSE 0x08
/* AUX area event, resume tracing */#define PERF_EF_RESUME 0x10
/* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags);
/* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. * * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with * PERF_EF_RESUME. * * ->start() with PERF_EF_RESUME will start as simply as possible but * only if the counter is not otherwise stopped. Will not overlap * another ->start() with PERF_EF_RESUME nor ->stop() with * PERF_EF_PAUSE. * * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other * ->stop()/->start() invocations, just not itself. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags);
/* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event);
/* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu);
/* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to 0 (see * perf_event_idx_default). */ int (*event_idx) (struct perf_event *event); /*optional */
/* * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, struct task_struct *task, bool sched_in);
/* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache;
/* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */
/* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */
/* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size);
/* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */
/* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */
/* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */
/* * Skip programming this PMU on the given CPU. Typically needed for * big.LITTLE things. */ bool (*filter) (struct pmu *pmu, int cpu); /* optional */
/* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */};
enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER,};
/** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action;};
/** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters;};
struct perf_addr_filter_range { unsigned long start; unsigned long size;};
/* * The normal states are: * * ACTIVE --. * ^ | * | | * sched_{in,out}() | * | | * v | * ,---> INACTIVE --+ <-. * | | | * | {dis,en}able() * sched_in() | | * | OFF <--' --+ * | | * `---> ERROR ------' * * That is: * * sched_in: INACTIVE -> {ACTIVE,ERROR} * sched_out: ACTIVE -> INACTIVE * disable: {ACTIVE,INACTIVE} -> OFF * enable: {OFF,ERROR} -> INACTIVE * * Where {OFF,ERROR} are disabled states. * * Then we have the {EXIT,REVOKED,DEAD} states which are various shades of * defunct events: * * - EXIT means task that the even was assigned to died, but child events * still live, and further children can still be created. But the event * itself will never be active again. It can only transition to * {REVOKED,DEAD}; * * - REVOKED means the PMU the event was associated with is gone; all * functionality is stopped but the event is still alive. Can only * transition to DEAD; * * - DEAD event really is DYING tearing down state and freeing bits. * */enum perf_event_state { PERF_EVENT_STATE_DEAD = -5, PERF_EVENT_STATE_REVOKED = -4, /* pmu gone, must not touch */ PERF_EVENT_STATE_EXIT = -3, /* task died, still inherit */ PERF_EVENT_STATE_ERROR = -2, /* scheduling error, can enable */ PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1,};
struct file;struct perf_sample_data;
typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs);
/* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the * PMU scope where it is active. */#define PERF_EV_CAP_SOFTWARE BIT(0)#define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1)#define PERF_EV_CAP_SIBLING BIT(2)#define PERF_EV_CAP_READ_SCOPE BIT(3)
#define SWEVENT_HLIST_BITS 8#define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS)
struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head;};
#define PERF_ATTACH_CONTEXT 0x0001#define PERF_ATTACH_GROUP 0x0002#define PERF_ATTACH_TASK 0x0004#define PERF_ATTACH_TASK_DATA 0x0008#define PERF_ATTACH_GLOBAL_DATA 0x0010#define PERF_ATTACH_SCHED_CB 0x0020#define PERF_ATTACH_CHILD 0x0040#define PERF_ATTACH_EXCLUSIVE 0x0080#define PERF_ATTACH_CALLCHAIN 0x0100#define PERF_ATTACH_ITRACE 0x0200
struct bpf_prog;struct perf_cgroup;struct perf_buffer;
struct pmu_event_list { raw_spinlock_t lock; struct list_head list;};
/* * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex * as such iteration must hold either lock. However, since ctx->lock is an IRQ * safe lock, and is only held by the CPU doing the modification, having IRQs * disabled is sufficient since it will hold-off the IPIs. */#ifdef CONFIG_PROVE_LOCKING# define lockdep_assert_event_ctx(event) \ WARN_ON_ONCE(__lockdep_enabled && \ (this_cpu_read(hardirqs_enabled) && \ lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD))#else# define lockdep_assert_event_ctx(event)#endif
#define for_each_sibling_event(sibling, event) \ lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list)
/** * struct perf_event - performance event kernel representation: */struct perf_event {#ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry;
/* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry;
struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings;
/* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps;
unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. * Whereas event->pmu_ctx->pmu may point to other pmu when group of * different pmu events is created. */ struct pmu *pmu; void *pmu_private;
enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count;
/* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp;
struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw;
struct perf_event_context *ctx; /* * event->pmu_ctx points to perf_event_pmu_context in which the event * is added. This pmu_ctx can be of other pmu for sw event when that * sw event is part of a group which also contains non-sw events. */ struct perf_event_pmu_context *pmu_ctx; atomic_long_t refcount;
/* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running;
/* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent;
int oncpu; int cpu;
struct list_head owner_entry; struct task_struct *owner;
/* mmap bits */ struct mutex mmap_mutex; refcount_t mmap_count;
struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending;
/* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync;
/* delayed work for NMIs and such */ unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work;
atomic_t event_limit;
/* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen;
/* for aux_output events */ struct perf_event *aux_event;
void (*destroy)(struct perf_event *); struct rcu_head rcu_head;
struct pid_namespace *ns; u64 id;
atomic64_t lost_samples;
u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; struct bpf_prog *prog; u64 bpf_cookie;
#ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter;# ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops;# endif#endif
#ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */#endif
#ifdef CONFIG_SECURITY void *security;#endif struct list_head sb_list; struct list_head pmu_list;
/* * Certain events gets forwarded to another pmu internally by over- * writing kernel copy of event->attr.type without user being aware * of it. event->orig_type contains original 'type' requested by * user. */ u32 orig_type;#endif /* CONFIG_PERF_EVENTS */};
/* * ,-----------------------[1:n]------------------------. * V V * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event * | | * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed * (similar to perf_event_context). Locking is as if it were a member of * perf_event_context; specifically: * * modification, both: ctx->mutex && ctx->lock * reading, either: ctx->mutex || ctx->lock * * There is one exception to this; namely put_pmu_ctx() isn't always called * with ctx->mutex held; this means that as long as we can guarantee the epc * has events the above rules hold. * * Specificially, sys_perf_event_open()'s group_leader case depends on * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. * * perf_event holds a refcount on perf_event_context * perf_event holds a refcount on perf_event_pmu_context */struct perf_event_pmu_context { struct pmu *pmu; struct perf_event_context *ctx;
struct list_head pmu_ctx_entry;
struct list_head pinned_active; struct list_head flexible_active;
/* Used to identify the per-cpu perf_event_pmu_context */ unsigned int embedded : 1;
unsigned int nr_events; unsigned int nr_cgroups; unsigned int nr_freq;
atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head;
/* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to * events not necessary to be active due to scheduling constraints, * such as cgroups. */ int rotate_necessary;};
static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc){ return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active);}
struct perf_event_groups { struct rb_root tree; u64 index;};
struct perf_time_ctx { u64 time; u64 stamp; u64 offset;};
/** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */struct perf_event_context { /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex;
struct list_head pmu_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list;
int nr_events; int nr_user; int is_active;
int nr_stat; int nr_freq; int rotate_disable;
refcount_t refcount; /* event <-> ctx */ struct task_struct *task;
/* * Context clock, runs when context enabled. */ struct perf_time_ctx time;
/* * Context clock, runs when in the guest mode. */ struct perf_time_ctx timeguest;
/* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count;#ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */#endif struct rcu_head rcu_head;
/* * The count of events for which using the switch-out fast path * should be avoided. * * Sum (event->pending_work + events with * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ local_t nr_no_switch_fast;};
/** * struct perf_ctx_data - PMU specific data for a task * @rcu_head: To avoid the race on free PMU specific data * @refcount: To track users * @global: To track system-wide users * @ctx_cache: Kmem cache of PMU specific data * @data: PMU specific data * * Currently, the struct is only used in Intel LBR call stack mode to * save/restore the call stack of a task on context switches. * * The rcu_head is used to prevent the race on free the data. * The data only be allocated when Intel LBR call stack mode is enabled. * The data will be freed when the mode is disabled. * The content of the data will only be accessed in context switch, which * should be protected by rcu_read_lock(). * * Because of the alignment requirement of Intel Arch LBR, the Kmem cache * is used to allocate the PMU specific data. The ctx_cache is to track * the Kmem cache. * * Careful: Struct perf_ctx_data is added as a pointer in struct task_struct. * When system-wide Intel LBR call stack mode is enabled, a buffer with * constant size will be allocated for each task. * Also, system memory consumption can further grow when the size of * struct perf_ctx_data enlarges. */struct perf_ctx_data { struct rcu_head rcu_head; refcount_t refcount; int global; struct kmem_cache *ctx_cache; void *data;};
struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc;
struct list_head sched_cb_entry; int sched_cb_usage;
int active_oncpu; int exclusive; int pmu_disable_count;
raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active;};
/** * struct perf_event_cpu_context - per cpu event context structure */struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int online;
#ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp;#endif
/* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2];};
struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; union { u64 flags; /* perf_output*() */ u64 aux_flags; /* perf_aux_output*() */ struct { u64 skip_read : 1; }; }; union { void *addr; unsigned long head; }; int page;};
struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event;};
#ifdef CONFIG_CGROUP_PERF
/* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */struct perf_cgroup_info { struct perf_time_ctx time; struct perf_time_ctx timeguest; int active;};
struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info;};
/* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */static inline struct perf_cgroup *perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx){ return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css);}#endif /* CONFIG_CGROUP_PERF */
#ifdef CONFIG_PERF_EVENTS
extern struct perf_event_context *perf_cpu_task_ctx(void);
extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event);extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size);extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size);extern void *perf_get_aux(struct perf_output_handle *handle);extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);extern void perf_event_itrace_started(struct perf_event *event);
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);extern int perf_pmu_unregister(struct pmu *pmu);
extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task);extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next);extern int perf_event_init_task(struct task_struct *child, u64 clone_flags);extern void perf_event_exit_task(struct task_struct *child);extern void perf_event_free_task(struct task_struct *task);extern void perf_event_delayed_put(struct task_struct *task);extern struct file *perf_event_get(unsigned int fd);extern const struct perf_event *perf_get_event(struct file *file);extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);extern void perf_event_print_debug(void);extern void perf_pmu_disable(struct pmu *pmu);extern void perf_pmu_enable(struct pmu *pmu);extern void perf_sched_cb_dec(struct pmu *pmu);extern void perf_sched_cb_inc(struct pmu *pmu);extern int perf_event_task_disable(void);extern int perf_event_task_enable(void);
extern void perf_pmu_resched(struct pmu *pmu);
extern int perf_event_refresh(struct perf_event *event, int refresh);extern void perf_event_update_userpage(struct perf_event *event);extern int perf_event_release_kernel(struct perf_event *event);
extern struct perf_event *perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context);
extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu);extern int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running);extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running);
extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
static inline bool branch_sample_no_flags(const struct perf_event *event){ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS;}
static inline bool branch_sample_no_cycles(const struct perf_event *event){ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES;}
static inline bool branch_sample_type(const struct perf_event *event){ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE;}
static inline bool branch_sample_hw_index(const struct perf_event *event){ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;}
static inline bool branch_sample_priv(const struct perf_event *event){ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;}
static inline bool branch_sample_counters(const struct perf_event *event){ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS;}
static inline bool branch_sample_call_stack(const struct perf_event *event){ return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;}
struct perf_sample_data { /* * Fields set by perf_sample_data_init() unconditionally, * group so as to minimize the cachelines touched. */ u64 sample_flags; u64 period; u64 dyn_size;
/* * Fields commonly set by __perf_event_header__init_id(), * group so as to minimize the cachelines touched. */ u64 type; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; struct { u32 cpu; u32 reserved; } cpu_entry;
/* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 ip; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 *br_stack_cntr; union perf_sample_weight weight; union perf_mem_data_src data_src; u64 txn;
struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size;
u64 stream_id; u64 cgroup; u64 addr; u64 phys_addr; u64 data_page_size; u64 code_page_size; u64 aux_size;} ____cacheline_aligned;
/* default value for data source */#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA) |\ PERF_MEM_S(LVLNUM, NA))
static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period){ /* remaining struct members initialized in perf_prepare_sample() */ data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; data->dyn_size = 0;
if (addr) { data->addr = addr; data->sample_flags |= PERF_SAMPLE_ADDR; }}
static inline void perf_sample_save_callchain(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs){ int size = 1;
if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) return;
data->callchain = perf_callchain(event, regs); size += data->callchain->nr;
data->dyn_size += size * sizeof(u64); data->sample_flags |= PERF_SAMPLE_CALLCHAIN;}
static inline void perf_sample_save_raw_data(struct perf_sample_data *data, struct perf_event *event, struct perf_raw_record *raw){ struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size;
if (!(event->attr.sample_type & PERF_SAMPLE_RAW)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW)) return;
do { sum += frag->size; if (perf_raw_frag_last(frag)) break; frag = frag->next; } while (1);
size = round_up(sum + sizeof(u32), sizeof(u64)); raw->size = size - sizeof(u32); frag->pad = raw->size - sum;
data->raw = raw; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_RAW;}
static inline bool has_branch_stack(struct perf_event *event){ return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;}
static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, u64 *brs_cntr){ int size = sizeof(u64); /* nr */
if (!has_branch_stack(event)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK)) return;
if (branch_sample_hw_index(event)) size += sizeof(u64);
brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr);
size += brs->nr * sizeof(struct perf_branch_entry);
/* * The extension space for counters is appended after the * struct perf_branch_stack. It is used to store the occurrences * of events of each branch. */ if (brs_cntr) size += brs->nr * sizeof(u64);
data->br_stack = brs; data->br_stack_cntr = brs_cntr; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;}
static inline u32 perf_sample_data_size(struct perf_sample_data *data, struct perf_event *event){ u32 size = sizeof(struct perf_event_header);
size += event->header_size + event->id_header_size; size += data->dyn_size;
return size;}
/* * Clear all bitfields in the perf_branch_entry. * The to and from fields are not cleared because they are * systematically modified by caller. */static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br){ br->mispred = 0; br->predicted = 0; br->in_tx = 0; br->abort = 0; br->cycles = 0; br->type = 0; br->spec = PERF_BR_SPEC_NA; br->reserved = 0;}
extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event);extern void perf_prepare_sample(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs);extern void perf_prepare_header(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs);
extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs);
extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs);extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs);extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs);
static inline boolis_default_overflow_handler(struct perf_event *event){ perf_overflow_handler_t overflow_handler = event->overflow_handler;
if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false;}
extern voidperf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event);extern voidperf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample);
extern voidperf_log_lost_samples(struct perf_event *event, u64 lost);
static inline bool event_has_any_exclude_flag(struct perf_event *event){ struct perf_event_attr *attr = &event->attr;
return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host;}
static inline bool is_sampling_event(struct perf_event *event){ return event->attr.sample_period != 0;}
/* * Return 1 for a software event, 0 for a hardware event */static inline int is_software_event(struct perf_event *event){ return event->event_caps & PERF_EV_CAP_SOFTWARE;}
/* * Return 1 for event in sw context, 0 for event in hw context */static inline int in_software_context(struct perf_event *event){ return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context;}
static inline int is_exclusive_pmu(struct pmu *pmu){ return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE;}
extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
#ifndef perf_arch_fetch_caller_regsstatic inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }#endif
/* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */static inline void perf_fetch_caller_regs(struct pt_regs *regs){ perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);}
static __always_inline voidperf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr){ if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr);}
DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
/* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr){ struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr);}
extern struct static_key_false perf_sched_events;
static __always_inline bool __perf_sw_enabled(int swevt){ return static_key_false(&perf_swevent_enabled[swevt]);}
static inline void perf_event_task_migrate(struct task_struct *task){ if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS)) task->sched_migrated = 1;}
static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task){ if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task);
if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) && task->sched_migrated) { __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); task->sched_migrated = 0; }}
static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next){ if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
#ifdef CONFIG_CGROUP_PERF if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && perf_cgroup_from_task(prev, NULL) != perf_cgroup_from_task(next, NULL)) __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0);#endif
if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next);}
extern void perf_event_mmap(struct vm_area_struct *vma);
extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym);extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags);
#define PERF_GUEST_ACTIVE 0x01#define PERF_GUEST_USER 0x02
struct perf_guest_info_callbacks { unsigned int (*state)(void); unsigned long (*get_ip)(void); unsigned int (*handle_intel_pt_intr)(void);
void (*handle_mediated_pmi)(void);};
#ifdef CONFIG_GUEST_PERF_EVENTS
extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs;
DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state);DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip);DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr);DECLARE_STATIC_CALL(__perf_guest_handle_mediated_pmi, *perf_guest_cbs->handle_mediated_pmi);
static inline unsigned int perf_guest_state(void){ return static_call(__perf_guest_state)();}
static inline unsigned long perf_guest_get_ip(void){ return static_call(__perf_guest_get_ip)();}
static inline unsigned int perf_guest_handle_intel_pt_intr(void){ return static_call(__perf_guest_handle_intel_pt_intr)();}
static inline void perf_guest_handle_mediated_pmi(void){ static_call(__perf_guest_handle_mediated_pmi)();}
extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
#else /* !CONFIG_GUEST_PERF_EVENTS: */
static inline unsigned int perf_guest_state(void) { return 0; }static inline unsigned long perf_guest_get_ip(void) { return 0; }static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; }
#endif /* !CONFIG_GUEST_PERF_EVENTS */
extern void perf_event_exec(void);extern void perf_event_comm(struct task_struct *tsk, bool exec);extern void perf_event_namespaces(struct task_struct *tsk);extern void perf_event_fork(struct task_struct *tsk);extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len);
/* Callchains */DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);extern struct perf_callchain_entry *get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark, u64 defer_cookie);extern int get_callchain_buffers(int max_stack);extern void put_callchain_buffers(void);extern struct perf_callchain_entry *get_callchain_entry(int *rctx);extern void put_callchain_entry(int rctx);
extern int sysctl_perf_event_max_stack;extern int sysctl_perf_event_max_contexts_per_stack;
static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip){ if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ }}
static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip){ if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ }}
extern int sysctl_perf_event_paranoid;extern int sysctl_perf_event_sample_rate;
extern void perf_sample_event_took(u64 sample_len_ns);
/* Access to perf_event_open(2) syscall. */#define PERF_SECURITY_OPEN 0
/* Finer grained perf_event_open(2) access control. */#define PERF_SECURITY_CPU 1#define PERF_SECURITY_KERNEL 2#define PERF_SECURITY_TRACEPOINT 3
static inline int perf_is_paranoid(void){ return sysctl_perf_event_paranoid > -1;}
extern int perf_allow_kernel(void);
static inline int perf_allow_cpu(void){ if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES;
return security_perf_event_open(PERF_SECURITY_CPU);}
static inline int perf_allow_tracepoint(void){ if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM;
return security_perf_event_open(PERF_SECURITY_TRACEPOINT);}
extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs);
extern void perf_event_init(void);extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task);extern void perf_bp_event(struct perf_event *event, void *data);
extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs);extern unsigned long perf_instruction_pointer(struct perf_event *event, struct pt_regs *regs);
#ifndef perf_arch_misc_flags# define perf_arch_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)# define perf_arch_instruction_pointer(regs) instruction_pointer(regs)#endif#ifndef perf_arch_bpf_user_pt_regs# define perf_arch_bpf_user_pt_regs(regs) regs#endif
#ifndef perf_arch_guest_misc_flagsstatic inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs){ unsigned long guest_state = perf_guest_state();
if (!(guest_state & PERF_GUEST_ACTIVE)) return 0;
if (guest_state & PERF_GUEST_USER) return PERF_RECORD_MISC_GUEST_USER; else return PERF_RECORD_MISC_GUEST_KERNEL;}# define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs)#endif
static inline bool needs_branch_stack(struct perf_event *event){ return event->attr.branch_sample_type != 0;}
static inline bool has_aux(struct perf_event *event){ return event->pmu && event->pmu->setup_aux;}
static inline bool has_aux_action(struct perf_event *event){ return event->attr.aux_sample_size || event->attr.aux_pause || event->attr.aux_resume;}
static inline bool is_write_backward(struct perf_event *event){ return !!event->attr.write_backward;}
static inline bool has_addr_filter(struct perf_event *event){ return event->pmu->nr_addr_filters;}
/* * An inherited event uses parent's filters */static inline struct perf_addr_filters_head *perf_event_addr_filters(struct perf_event *event){ struct perf_addr_filters_head *ifh = &event->addr_filters;
if (event->parent) ifh = &event->parent->addr_filters;
return ifh;}
static inline struct fasync_struct **perf_event_fasync(struct perf_event *event){ /* Only the parent has fasync state */ if (event->parent) event = event->parent; return &event->fasync;}
extern void perf_event_addr_filters_sync(struct perf_event *event);extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id);
extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size);extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size);extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len);extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len);extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to);extern int perf_swevent_get_recursion_context(void);extern void perf_swevent_put_recursion_context(int rctx);extern u64 perf_swevent_set_period(struct perf_event *event);extern void perf_event_enable(struct perf_event *event);extern void perf_event_disable(struct perf_event *event);extern void perf_event_disable_local(struct perf_event *event);extern void perf_event_disable_inatomic(struct perf_event *event);extern void perf_event_task_tick(void);extern int perf_event_account_interrupt(struct perf_event *event);extern int perf_event_period(struct perf_event *event, u64 value);extern u64 perf_event_pause(struct perf_event *event, bool reset);
#ifdef CONFIG_PERF_GUEST_MEDIATED_PMUint perf_create_mediated_pmu(void);void perf_release_mediated_pmu(void);void perf_load_guest_context(void);void perf_put_guest_context(void);#endif
#else /* !CONFIG_PERF_EVENTS: */
static inline void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; }static inline voidperf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { }static inline intperf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; }static inline void *perf_get_aux(struct perf_output_handle *handle) { return NULL; }static inline voidperf_event_task_migrate(struct task_struct *task) { }static inline voidperf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { }static inline voidperf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { }static inline int perf_event_init_task(struct task_struct *child, u64 clone_flags) { return 0; }static inline void perf_event_exit_task(struct task_struct *child) { }static inline void perf_event_free_task(struct task_struct *task) { }static inline void perf_event_delayed_put(struct task_struct *task) { }static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }static inline const struct perf_event *perf_get_event(struct file *file){ return ERR_PTR(-EINVAL);}static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event){ return ERR_PTR(-EINVAL);}static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running){ return -EINVAL;}static inline void perf_event_print_debug(void) { }static inline int perf_event_task_disable(void) { return -EINVAL; }static inline int perf_event_task_enable(void) { return -EINVAL; }static inline int perf_event_refresh(struct perf_event *event, int refresh){ return -EINVAL;}
static inline voidperf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { }static inline voidperf_bp_event(struct perf_event *event, void *data) { }
static inline void perf_event_mmap(struct vm_area_struct *vma) { }
typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data);static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { }static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { }static inline void perf_event_exec(void) { }static inline void perf_event_comm(struct task_struct *tsk, bool exec) { }static inline void perf_event_namespaces(struct task_struct *tsk) { }static inline void perf_event_fork(struct task_struct *tsk) { }static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { }static inline void perf_event_init(void) { }static inline int perf_swevent_get_recursion_context(void) { return -1; }static inline void perf_swevent_put_recursion_context(int rctx) { }static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; }static inline void perf_event_enable(struct perf_event *event) { }static inline void perf_event_disable(struct perf_event *event) { }static inline int __perf_event_disable(void *info) { return -1; }static inline void perf_event_task_tick(void) { }static inline int perf_event_release_kernel(struct perf_event *event) { return 0; }static inline intperf_event_period(struct perf_event *event, u64 value) { return -EINVAL; }static inline u64perf_event_pause(struct perf_event *event, bool reset) { return 0; }static inline intperf_exclude_event(struct perf_event *event, struct pt_regs *regs) { return 0; }
#endif /* !CONFIG_PERF_EVENTS */
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)extern void perf_restore_debug_store(void);#elsestatic inline void perf_restore_debug_store(void) { }#endif
#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))
struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str;};
struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht;};
struct perf_pmu_events_hybrid_attr { struct device_attribute attr; u64 id; const char *event_str; u64 pmu_type;};
struct perf_pmu_format_hybrid_attr { struct device_attribute attr; u64 pmu_type;};
ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page);
#define PMU_EVENT_ATTR(_name, _var, _id, _show) \static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \};
#define PMU_EVENT_ATTR_STRING(_name, _var, _str) \static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \};
#define PMU_EVENT_ATTR_ID(_name, _show, _id) \ (&((struct perf_pmu_events_attr[]) { \ { .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, } \ })[0].attr.attr)
#define PMU_FORMAT_ATTR_SHOW(_name, _format) \static ssize_t \_name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \{ \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \} \
#define PMU_FORMAT_ATTR(_name, _format) \ PMU_FORMAT_ATTR_SHOW(_name, _format) \ \static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
/* Performance counter hotplug functions */#ifdef CONFIG_PERF_EVENTSextern int perf_event_init_cpu(unsigned int cpu);extern int perf_event_exit_cpu(unsigned int cpu);#else# define perf_event_init_cpu NULL# define perf_event_exit_cpu NULL#endif
extern void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now);
/* * Snapshot branch stack on software events. * * Branch stack can be very useful in understanding software events. For * example, when a long function, e.g. sys_perf_event_open, returns an * errno, it is not obvious why the function failed. Branch stack could * provide very helpful information in this type of scenarios. * * On software event, it is necessary to stop the hardware branch recorder * fast. Otherwise, the hardware register/buffer will be flushed with * entries of the triggering event. Therefore, static call is used to * stop the hardware recorder. */
/* * cnt is the number of entries allocated for entries. * Return number of entries copied to . */typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt);DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
#ifndef PERF_NEEDS_LOPWR_CBstatic inline void perf_lopwr_cb(bool mode){}#endif
#endif /* _LINUX_PERF_EVENT_H */