123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439 |
- // SPDX-License-Identifier: GPL-2.0-or-later
- /*
- * fs/eventpoll.c (Efficient event retrieval implementation)
- * Copyright (C) 2001,...,2009 Davide Libenzi
- *
- * Davide Libenzi <davidel@xmailserver.org>
- */
- #include <linux/init.h>
- #include <linux/kernel.h>
- #include <linux/sched/signal.h>
- #include <linux/fs.h>
- #include <linux/file.h>
- #include <linux/signal.h>
- #include <linux/errno.h>
- #include <linux/mm.h>
- #include <linux/slab.h>
- #include <linux/poll.h>
- #include <linux/string.h>
- #include <linux/list.h>
- #include <linux/hash.h>
- #include <linux/spinlock.h>
- #include <linux/syscalls.h>
- #include <linux/rbtree.h>
- #include <linux/wait.h>
- #include <linux/eventpoll.h>
- #include <linux/mount.h>
- #include <linux/bitops.h>
- #include <linux/mutex.h>
- #include <linux/anon_inodes.h>
- #include <linux/device.h>
- #include <linux/freezer.h>
- #include <linux/uaccess.h>
- #include <asm/io.h>
- #include <asm/mman.h>
- #include <linux/atomic.h>
- #include <linux/proc_fs.h>
- #include <linux/seq_file.h>
- #include <linux/compat.h>
- #include <linux/rculist.h>
- #include <net/busy_poll.h>
- #include <trace/hooks/fs.h>
- /*
- * LOCKING:
- * There are three level of locking required by epoll :
- *
- * 1) epmutex (mutex)
- * 2) ep->mtx (mutex)
- * 3) ep->lock (rwlock)
- *
- * The acquire order is the one listed above, from 1 to 3.
- * We need a rwlock (ep->lock) because we manipulate objects
- * from inside the poll callback, that might be triggered from
- * a wake_up() that in turn might be called from IRQ context.
- * So we can't sleep inside the poll callback and hence we need
- * a spinlock. During the event transfer loop (from kernel to
- * user space) we could end up sleeping due a copy_to_user(), so
- * we need a lock that will allow us to sleep. This lock is a
- * mutex (ep->mtx). It is acquired during the event transfer loop,
- * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file().
- * Then we also need a global mutex to serialize eventpoll_release_file()
- * and ep_free().
- * This mutex is acquired by ep_free() during the epoll file
- * cleanup path and it is also acquired by eventpoll_release_file()
- * if a file has been pushed inside an epoll set and it is then
- * close()d without a previous call to epoll_ctl(EPOLL_CTL_DEL).
- * It is also acquired when inserting an epoll fd onto another epoll
- * fd. We do this so that we walk the epoll tree and ensure that this
- * insertion does not create a cycle of epoll file descriptors, which
- * could lead to deadlock. We need a global mutex to prevent two
- * simultaneous inserts (A into B and B into A) from racing and
- * constructing a cycle without either insert observing that it is
- * going to.
- * It is necessary to acquire multiple "ep->mtx"es at once in the
- * case when one epoll fd is added to another. In this case, we
- * always acquire the locks in the order of nesting (i.e. after
- * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired
- * before e2->mtx). Since we disallow cycles of epoll file
- * descriptors, this ensures that the mutexes are well-ordered. In
- * order to communicate this nesting to lockdep, when walking a tree
- * of epoll file descriptors, we use the current recursion depth as
- * the lockdep subkey.
- * It is possible to drop the "ep->mtx" and to use the global
- * mutex "epmutex" (together with "ep->lock") to have it working,
- * but having "ep->mtx" will make the interface more scalable.
- * Events that require holding "epmutex" are very rare, while for
- * normal operations the epoll private "ep->mtx" will guarantee
- * a better scalability.
- */
- /* Epoll private bits inside the event mask */
- #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
- #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT)
- #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \
- EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE)
- /* Maximum number of nesting allowed inside epoll sets */
- #define EP_MAX_NESTS 4
- #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
- #define EP_UNACTIVE_PTR ((void *) -1L)
- #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry))
- struct epoll_filefd {
- struct file *file;
- int fd;
- } __packed;
- /*
- * Structure used to track possible nested calls, for too deep recursions
- * and loop cycles.
- */
- struct nested_call_node {
- struct list_head llink;
- void *cookie;
- void *ctx;
- };
- /*
- * This structure is used as collector for nested calls, to check for
- * maximum recursion dept and loop cycles.
- */
- struct nested_calls {
- struct list_head tasks_call_list;
- spinlock_t lock;
- };
- /*
- * Each file descriptor added to the eventpoll interface will
- * have an entry of this type linked to the "rbr" RB tree.
- * Avoid increasing the size of this struct, there can be many thousands
- * of these on a server and we do not want this to take another cache line.
- */
- struct epitem {
- union {
- /* RB tree node links this structure to the eventpoll RB tree */
- struct rb_node rbn;
- /* Used to free the struct epitem */
- struct rcu_head rcu;
- };
- /* List header used to link this structure to the eventpoll ready list */
- struct list_head rdllink;
- /*
- * Works together "struct eventpoll"->ovflist in keeping the
- * single linked chain of items.
- */
- struct epitem *next;
- /* The file descriptor information this item refers to */
- struct epoll_filefd ffd;
- /* Number of active wait queue attached to poll operations */
- int nwait;
- /* List containing poll wait queues */
- struct list_head pwqlist;
- /* The "container" of this item */
- struct eventpoll *ep;
- /* List header used to link this item to the "struct file" items list */
- struct list_head fllink;
- /* wakeup_source used when EPOLLWAKEUP is set */
- struct wakeup_source __rcu *ws;
- /* The structure that describe the interested events and the source fd */
- struct epoll_event event;
- };
- /*
- * This structure is stored inside the "private_data" member of the file
- * structure and represents the main data structure for the eventpoll
- * interface.
- */
- struct eventpoll {
- /*
- * This mutex is used to ensure that files are not removed
- * while epoll is using them. This is held during the event
- * collection loop, the file cleanup path, the epoll file exit
- * code and the ctl operations.
- */
- struct mutex mtx;
- /* Wait queue used by sys_epoll_wait() */
- wait_queue_head_t wq;
- /* Wait queue used by file->poll() */
- wait_queue_head_t poll_wait;
- /* List of ready file descriptors */
- struct list_head rdllist;
- /* Lock which protects rdllist and ovflist */
- rwlock_t lock;
- /* RB tree root used to store monitored fd structs */
- struct rb_root_cached rbr;
- /*
- * This is a single linked list that chains all the "struct epitem" that
- * happened while transferring ready events to userspace w/out
- * holding ->lock.
- */
- struct epitem *ovflist;
- /* wakeup_source used when ep_scan_ready_list is running */
- struct wakeup_source *ws;
- /* The user that created the eventpoll descriptor */
- struct user_struct *user;
- struct file *file;
- /* used to optimize loop detection check */
- u64 gen;
- #ifdef CONFIG_NET_RX_BUSY_POLL
- /* used to track busy poll napi_id */
- unsigned int napi_id;
- #endif
- #ifdef CONFIG_DEBUG_LOCK_ALLOC
- /* tracks wakeup nests for lockdep validation */
- u8 nests;
- #endif
- };
- /* Wait structure used by the poll hooks */
- struct eppoll_entry {
- /* List header used to link this structure to the "struct epitem" */
- struct list_head llink;
- /* The "base" pointer is set to the container "struct epitem" */
- struct epitem *base;
- /*
- * Wait queue item that will be linked to the target file wait
- * queue head.
- */
- wait_queue_entry_t wait;
- /* The wait queue head that linked the "wait" wait queue item */
- wait_queue_head_t *whead;
- };
- /* Wrapper struct used by poll queueing */
- struct ep_pqueue {
- poll_table pt;
- struct epitem *epi;
- };
- /* Used by the ep_send_events() function as callback private data */
- struct ep_send_events_data {
- int maxevents;
- struct epoll_event __user *events;
- int res;
- };
- /*
- * Configuration options available inside /proc/sys/fs/epoll/
- */
- /* Maximum number of epoll watched descriptors, per user */
- static long max_user_watches __read_mostly;
- /*
- * This mutex is used to serialize ep_free() and eventpoll_release_file().
- */
- static DEFINE_MUTEX(epmutex);
- static u64 loop_check_gen = 0;
- /* Used to check for epoll file descriptor inclusion loops */
- static struct nested_calls poll_loop_ncalls;
- /* Slab cache used to allocate "struct epitem" */
- static struct kmem_cache *epi_cache __read_mostly;
- /* Slab cache used to allocate "struct eppoll_entry" */
- static struct kmem_cache *pwq_cache __read_mostly;
- /*
- * List of files with newly added links, where we may need to limit the number
- * of emanating paths. Protected by the epmutex.
- */
- static LIST_HEAD(tfile_check_list);
- #ifdef CONFIG_SYSCTL
- #include <linux/sysctl.h>
- static long long_zero;
- static long long_max = LONG_MAX;
- struct ctl_table epoll_table[] = {
- {
- .procname = "max_user_watches",
- .data = &max_user_watches,
- .maxlen = sizeof(max_user_watches),
- .mode = 0644,
- .proc_handler = proc_doulongvec_minmax,
- .extra1 = &long_zero,
- .extra2 = &long_max,
- },
- { }
- };
- #endif /* CONFIG_SYSCTL */
- static const struct file_operations eventpoll_fops;
- static inline int is_file_epoll(struct file *f)
- {
- return f->f_op == &eventpoll_fops;
- }
- /* Setup the structure that is used as key for the RB tree */
- static inline void ep_set_ffd(struct epoll_filefd *ffd,
- struct file *file, int fd)
- {
- ffd->file = file;
- ffd->fd = fd;
- }
- /* Compare RB tree keys */
- static inline int ep_cmp_ffd(struct epoll_filefd *p1,
- struct epoll_filefd *p2)
- {
- return (p1->file > p2->file ? +1:
- (p1->file < p2->file ? -1 : p1->fd - p2->fd));
- }
- /* Tells us if the item is currently linked */
- static inline int ep_is_linked(struct epitem *epi)
- {
- return !list_empty(&epi->rdllink);
- }
- static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p)
- {
- return container_of(p, struct eppoll_entry, wait);
- }
- /* Get the "struct epitem" from a wait queue pointer */
- static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
- {
- return container_of(p, struct eppoll_entry, wait)->base;
- }
- /* Get the "struct epitem" from an epoll queue wrapper */
- static inline struct epitem *ep_item_from_epqueue(poll_table *p)
- {
- return container_of(p, struct ep_pqueue, pt)->epi;
- }
- /* Initialize the poll safe wake up structure */
- static void ep_nested_calls_init(struct nested_calls *ncalls)
- {
- INIT_LIST_HEAD(&ncalls->tasks_call_list);
- spin_lock_init(&ncalls->lock);
- }
- /**
- * ep_events_available - Checks if ready events might be available.
- *
- * @ep: Pointer to the eventpoll context.
- *
- * Returns: Returns a value different than zero if ready events are available,
- * or zero otherwise.
- */
- static inline int ep_events_available(struct eventpoll *ep)
- {
- return !list_empty_careful(&ep->rdllist) ||
- READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR;
- }
- #ifdef CONFIG_NET_RX_BUSY_POLL
- static bool ep_busy_loop_end(void *p, unsigned long start_time)
- {
- struct eventpoll *ep = p;
- return ep_events_available(ep) || busy_loop_timeout(start_time);
- }
- /*
- * Busy poll if globally on and supporting sockets found && no events,
- * busy loop will return if need_resched or ep_events_available.
- *
- * we must do our busy polling with irqs enabled
- */
- static void ep_busy_loop(struct eventpoll *ep, int nonblock)
- {
- unsigned int napi_id = READ_ONCE(ep->napi_id);
- if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
- napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
- }
- static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
- {
- if (ep->napi_id)
- ep->napi_id = 0;
- }
- /*
- * Set epoll busy poll NAPI ID from sk.
- */
- static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
- {
- struct eventpoll *ep;
- unsigned int napi_id;
- struct socket *sock;
- struct sock *sk;
- int err;
- if (!net_busy_loop_on())
- return;
- sock = sock_from_file(epi->ffd.file, &err);
- if (!sock)
- return;
- sk = sock->sk;
- if (!sk)
- return;
- napi_id = READ_ONCE(sk->sk_napi_id);
- ep = epi->ep;
- /* Non-NAPI IDs can be rejected
- * or
- * Nothing to do if we already have this ID
- */
- if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
- return;
- /* record NAPI ID for use in next busy poll */
- ep->napi_id = napi_id;
- }
- #else
- static inline void ep_busy_loop(struct eventpoll *ep, int nonblock)
- {
- }
- static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
- {
- }
- static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
- {
- }
- #endif /* CONFIG_NET_RX_BUSY_POLL */
- /**
- * ep_call_nested - Perform a bound (possibly) nested call, by checking
- * that the recursion limit is not exceeded, and that
- * the same nested call (by the meaning of same cookie) is
- * no re-entered.
- *
- * @ncalls: Pointer to the nested_calls structure to be used for this call.
- * @nproc: Nested call core function pointer.
- * @priv: Opaque data to be passed to the @nproc callback.
- * @cookie: Cookie to be used to identify this nested call.
- * @ctx: This instance context.
- *
- * Returns: Returns the code returned by the @nproc callback, or -1 if
- * the maximum recursion limit has been exceeded.
- */
- static int ep_call_nested(struct nested_calls *ncalls,
- int (*nproc)(void *, void *, int), void *priv,
- void *cookie, void *ctx)
- {
- int error, call_nests = 0;
- unsigned long flags;
- struct list_head *lsthead = &ncalls->tasks_call_list;
- struct nested_call_node *tncur;
- struct nested_call_node tnode;
- spin_lock_irqsave(&ncalls->lock, flags);
- /*
- * Try to see if the current task is already inside this wakeup call.
- * We use a list here, since the population inside this set is always
- * very much limited.
- */
- list_for_each_entry(tncur, lsthead, llink) {
- if (tncur->ctx == ctx &&
- (tncur->cookie == cookie || ++call_nests > EP_MAX_NESTS)) {
- /*
- * Ops ... loop detected or maximum nest level reached.
- * We abort this wake by breaking the cycle itself.
- */
- error = -1;
- goto out_unlock;
- }
- }
- /* Add the current task and cookie to the list */
- tnode.ctx = ctx;
- tnode.cookie = cookie;
- list_add(&tnode.llink, lsthead);
- spin_unlock_irqrestore(&ncalls->lock, flags);
- /* Call the nested function */
- error = (*nproc)(priv, cookie, call_nests);
- /* Remove the current task from the list */
- spin_lock_irqsave(&ncalls->lock, flags);
- list_del(&tnode.llink);
- out_unlock:
- spin_unlock_irqrestore(&ncalls->lock, flags);
- return error;
- }
- /*
- * As described in commit 0ccf831cb lockdep: annotate epoll
- * the use of wait queues used by epoll is done in a very controlled
- * manner. Wake ups can nest inside each other, but are never done
- * with the same locking. For example:
- *
- * dfd = socket(...);
- * efd1 = epoll_create();
- * efd2 = epoll_create();
- * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...);
- * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...);
- *
- * When a packet arrives to the device underneath "dfd", the net code will
- * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a
- * callback wakeup entry on that queue, and the wake_up() performed by the
- * "dfd" net code will end up in ep_poll_callback(). At this point epoll
- * (efd1) notices that it may have some event ready, so it needs to wake up
- * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake()
- * that ends up in another wake_up(), after having checked about the
- * recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to
- * avoid stack blasting.
- *
- * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle
- * this special case of epoll.
- */
- #ifdef CONFIG_DEBUG_LOCK_ALLOC
- static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi)
- {
- struct eventpoll *ep_src;
- unsigned long flags;
- u8 nests = 0;
- /*
- * To set the subclass or nesting level for spin_lock_irqsave_nested()
- * it might be natural to create a per-cpu nest count. However, since
- * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can
- * schedule() in the -rt kernel, the per-cpu variable are no longer
- * protected. Thus, we are introducing a per eventpoll nest field.
- * If we are not being call from ep_poll_callback(), epi is NULL and
- * we are at the first level of nesting, 0. Otherwise, we are being
- * called from ep_poll_callback() and if a previous wakeup source is
- * not an epoll file itself, we are at depth 1 since the wakeup source
- * is depth 0. If the wakeup source is a previous epoll file in the
- * wakeup chain then we use its nests value and record ours as
- * nests + 1. The previous epoll file nests value is stable since its
- * already holding its own poll_wait.lock.
- */
- if (epi) {
- if ((is_file_epoll(epi->ffd.file))) {
- ep_src = epi->ffd.file->private_data;
- nests = ep_src->nests;
- } else {
- nests = 1;
- }
- }
- spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests);
- ep->nests = nests + 1;
- wake_up_locked_poll(&ep->poll_wait, EPOLLIN);
- ep->nests = 0;
- spin_unlock_irqrestore(&ep->poll_wait.lock, flags);
- }
- #else
- static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi)
- {
- wake_up_poll(&ep->poll_wait, EPOLLIN);
- }
- #endif
- static void ep_remove_wait_queue(struct eppoll_entry *pwq)
- {
- wait_queue_head_t *whead;
- rcu_read_lock();
- /*
- * If it is cleared by POLLFREE, it should be rcu-safe.
- * If we read NULL we need a barrier paired with
- * smp_store_release() in ep_poll_callback(), otherwise
- * we rely on whead->lock.
- */
- whead = smp_load_acquire(&pwq->whead);
- if (whead)
- remove_wait_queue(whead, &pwq->wait);
- rcu_read_unlock();
- }
- /*
- * This function unregisters poll callbacks from the associated file
- * descriptor. Must be called with "mtx" held (or "epmutex" if called from
- * ep_free).
- */
- static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
- {
- struct list_head *lsthead = &epi->pwqlist;
- struct eppoll_entry *pwq;
- while (!list_empty(lsthead)) {
- pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
- list_del(&pwq->llink);
- ep_remove_wait_queue(pwq);
- kmem_cache_free(pwq_cache, pwq);
- }
- }
- /* call only when ep->mtx is held */
- static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi)
- {
- return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx));
- }
- /* call only when ep->mtx is held */
- static inline void ep_pm_stay_awake(struct epitem *epi)
- {
- struct wakeup_source *ws = ep_wakeup_source(epi);
- if (ws)
- __pm_stay_awake(ws);
- }
- static inline bool ep_has_wakeup_source(struct epitem *epi)
- {
- return rcu_access_pointer(epi->ws) ? true : false;
- }
- /* call when ep->mtx cannot be held (ep_poll_callback) */
- static inline void ep_pm_stay_awake_rcu(struct epitem *epi)
- {
- struct wakeup_source *ws;
- rcu_read_lock();
- ws = rcu_dereference(epi->ws);
- if (ws)
- __pm_stay_awake(ws);
- rcu_read_unlock();
- }
- /**
- * ep_scan_ready_list - Scans the ready list in a way that makes possible for
- * the scan code, to call f_op->poll(). Also allows for
- * O(NumReady) performance.
- *
- * @ep: Pointer to the epoll private data structure.
- * @sproc: Pointer to the scan callback.
- * @priv: Private opaque data passed to the @sproc callback.
- * @depth: The current depth of recursive f_op->poll calls.
- * @ep_locked: caller already holds ep->mtx
- *
- * Returns: The same integer error code returned by the @sproc callback.
- */
- static __poll_t ep_scan_ready_list(struct eventpoll *ep,
- __poll_t (*sproc)(struct eventpoll *,
- struct list_head *, void *),
- void *priv, int depth, bool ep_locked)
- {
- __poll_t res;
- struct epitem *epi, *nepi;
- LIST_HEAD(txlist);
- lockdep_assert_irqs_enabled();
- /*
- * We need to lock this because we could be hit by
- * eventpoll_release_file() and epoll_ctl().
- */
- if (!ep_locked)
- mutex_lock_nested(&ep->mtx, depth);
- /*
- * Steal the ready list, and re-init the original one to the
- * empty list. Also, set ep->ovflist to NULL so that events
- * happening while looping w/out locks, are not lost. We cannot
- * have the poll callback to queue directly on ep->rdllist,
- * because we want the "sproc" callback to be able to do it
- * in a lockless way.
- */
- write_lock_irq(&ep->lock);
- list_splice_init(&ep->rdllist, &txlist);
- WRITE_ONCE(ep->ovflist, NULL);
- write_unlock_irq(&ep->lock);
- /*
- * Now call the callback function.
- */
- res = (*sproc)(ep, &txlist, priv);
- write_lock_irq(&ep->lock);
- /*
- * During the time we spent inside the "sproc" callback, some
- * other events might have been queued by the poll callback.
- * We re-insert them inside the main ready-list here.
- */
- for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL;
- nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
- /*
- * We need to check if the item is already in the list.
- * During the "sproc" callback execution time, items are
- * queued into ->ovflist but the "txlist" might already
- * contain them, and the list_splice() below takes care of them.
- */
- if (!ep_is_linked(epi)) {
- /*
- * ->ovflist is LIFO, so we have to reverse it in order
- * to keep in FIFO.
- */
- list_add(&epi->rdllink, &ep->rdllist);
- ep_pm_stay_awake(epi);
- }
- }
- /*
- * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
- * releasing the lock, events will be queued in the normal way inside
- * ep->rdllist.
- */
- WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR);
- /*
- * Quickly re-inject items left on "txlist".
- */
- list_splice(&txlist, &ep->rdllist);
- __pm_relax(ep->ws);
- if (!list_empty(&ep->rdllist)) {
- if (waitqueue_active(&ep->wq))
- wake_up(&ep->wq);
- }
- write_unlock_irq(&ep->lock);
- if (!ep_locked)
- mutex_unlock(&ep->mtx);
- return res;
- }
- static void epi_rcu_free(struct rcu_head *head)
- {
- struct epitem *epi = container_of(head, struct epitem, rcu);
- kmem_cache_free(epi_cache, epi);
- }
- /*
- * Removes a "struct epitem" from the eventpoll RB tree and deallocates
- * all the associated resources. Must be called with "mtx" held.
- */
- static int ep_remove(struct eventpoll *ep, struct epitem *epi)
- {
- struct file *file = epi->ffd.file;
- lockdep_assert_irqs_enabled();
- /*
- * Removes poll wait queue hooks.
- */
- ep_unregister_pollwait(ep, epi);
- /* Remove the current item from the list of epoll hooks */
- spin_lock(&file->f_lock);
- list_del_rcu(&epi->fllink);
- spin_unlock(&file->f_lock);
- rb_erase_cached(&epi->rbn, &ep->rbr);
- write_lock_irq(&ep->lock);
- if (ep_is_linked(epi))
- list_del_init(&epi->rdllink);
- write_unlock_irq(&ep->lock);
- wakeup_source_unregister(ep_wakeup_source(epi));
- /*
- * At this point it is safe to free the eventpoll item. Use the union
- * field epi->rcu, since we are trying to minimize the size of
- * 'struct epitem'. The 'rbn' field is no longer in use. Protected by
- * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make
- * use of the rbn field.
- */
- call_rcu(&epi->rcu, epi_rcu_free);
- atomic_long_dec(&ep->user->epoll_watches);
- return 0;
- }
- static void ep_free(struct eventpoll *ep)
- {
- struct rb_node *rbp;
- struct epitem *epi;
- /* We need to release all tasks waiting for these file */
- if (waitqueue_active(&ep->poll_wait))
- ep_poll_safewake(ep, NULL);
- /*
- * We need to lock this because we could be hit by
- * eventpoll_release_file() while we're freeing the "struct eventpoll".
- * We do not need to hold "ep->mtx" here because the epoll file
- * is on the way to be removed and no one has references to it
- * anymore. The only hit might come from eventpoll_release_file() but
- * holding "epmutex" is sufficient here.
- */
- mutex_lock(&epmutex);
- /*
- * Walks through the whole tree by unregistering poll callbacks.
- */
- for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
- epi = rb_entry(rbp, struct epitem, rbn);
- ep_unregister_pollwait(ep, epi);
- cond_resched();
- }
- /*
- * Walks through the whole tree by freeing each "struct epitem". At this
- * point we are sure no poll callbacks will be lingering around, and also by
- * holding "epmutex" we can be sure that no file cleanup code will hit
- * us during this operation. So we can avoid the lock on "ep->lock".
- * We do not need to lock ep->mtx, either, we only do it to prevent
- * a lockdep warning.
- */
- mutex_lock(&ep->mtx);
- while ((rbp = rb_first_cached(&ep->rbr)) != NULL) {
- epi = rb_entry(rbp, struct epitem, rbn);
- ep_remove(ep, epi);
- cond_resched();
- }
- mutex_unlock(&ep->mtx);
- mutex_unlock(&epmutex);
- mutex_destroy(&ep->mtx);
- free_uid(ep->user);
- wakeup_source_unregister(ep->ws);
- kfree(ep);
- }
- static int ep_eventpoll_release(struct inode *inode, struct file *file)
- {
- struct eventpoll *ep = file->private_data;
- if (ep)
- ep_free(ep);
- return 0;
- }
- static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
- void *priv);
- static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
- poll_table *pt);
- /*
- * Differs from ep_eventpoll_poll() in that internal callers already have
- * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
- * is correctly annotated.
- */
- static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
- int depth)
- {
- struct eventpoll *ep;
- bool locked;
- pt->_key = epi->event.events;
- if (!is_file_epoll(epi->ffd.file))
- return vfs_poll(epi->ffd.file, pt) & epi->event.events;
- ep = epi->ffd.file->private_data;
- poll_wait(epi->ffd.file, &ep->poll_wait, pt);
- locked = pt && (pt->_qproc == ep_ptable_queue_proc);
- return ep_scan_ready_list(epi->ffd.file->private_data,
- ep_read_events_proc, &depth, depth,
- locked) & epi->event.events;
- }
- static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
- void *priv)
- {
- struct epitem *epi, *tmp;
- poll_table pt;
- int depth = *(int *)priv;
- init_poll_funcptr(&pt, NULL);
- depth++;
- list_for_each_entry_safe(epi, tmp, head, rdllink) {
- if (ep_item_poll(epi, &pt, depth)) {
- return EPOLLIN | EPOLLRDNORM;
- } else {
- /*
- * Item has been dropped into the ready list by the poll
- * callback, but it's not actually ready, as far as
- * caller requested events goes. We can remove it here.
- */
- __pm_relax(ep_wakeup_source(epi));
- list_del_init(&epi->rdllink);
- }
- }
- return 0;
- }
- static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
- {
- struct eventpoll *ep = file->private_data;
- int depth = 0;
- /* Insert inside our poll wait queue */
- poll_wait(file, &ep->poll_wait, wait);
- /*
- * Proceed to find out if wanted events are really available inside
- * the ready list.
- */
- return ep_scan_ready_list(ep, ep_read_events_proc,
- &depth, depth, false);
- }
- #ifdef CONFIG_PROC_FS
- static void ep_show_fdinfo(struct seq_file *m, struct file *f)
- {
- struct eventpoll *ep = f->private_data;
- struct rb_node *rbp;
- mutex_lock(&ep->mtx);
- for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
- struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
- struct inode *inode = file_inode(epi->ffd.file);
- seq_printf(m, "tfd: %8d events: %8x data: %16llx "
- " pos:%lli ino:%lx sdev:%x\n",
- epi->ffd.fd, epi->event.events,
- (long long)epi->event.data,
- (long long)epi->ffd.file->f_pos,
- inode->i_ino, inode->i_sb->s_dev);
- if (seq_has_overflowed(m))
- break;
- }
- mutex_unlock(&ep->mtx);
- }
- #endif
- /* File callbacks that implement the eventpoll file behaviour */
- static const struct file_operations eventpoll_fops = {
- #ifdef CONFIG_PROC_FS
- .show_fdinfo = ep_show_fdinfo,
- #endif
- .release = ep_eventpoll_release,
- .poll = ep_eventpoll_poll,
- .llseek = noop_llseek,
- };
- /*
- * This is called from eventpoll_release() to unlink files from the eventpoll
- * interface. We need to have this facility to cleanup correctly files that are
- * closed without being removed from the eventpoll interface.
- */
- void eventpoll_release_file(struct file *file)
- {
- struct eventpoll *ep;
- struct epitem *epi, *next;
- /*
- * We don't want to get "file->f_lock" because it is not
- * necessary. It is not necessary because we're in the "struct file"
- * cleanup path, and this means that no one is using this file anymore.
- * So, for example, epoll_ctl() cannot hit here since if we reach this
- * point, the file counter already went to zero and fget() would fail.
- * The only hit might come from ep_free() but by holding the mutex
- * will correctly serialize the operation. We do need to acquire
- * "ep->mtx" after "epmutex" because ep_remove() requires it when called
- * from anywhere but ep_free().
- *
- * Besides, ep_remove() acquires the lock, so we can't hold it here.
- */
- mutex_lock(&epmutex);
- list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
- ep = epi->ep;
- mutex_lock_nested(&ep->mtx, 0);
- ep_remove(ep, epi);
- mutex_unlock(&ep->mtx);
- }
- mutex_unlock(&epmutex);
- }
- static int ep_alloc(struct eventpoll **pep)
- {
- int error;
- struct user_struct *user;
- struct eventpoll *ep;
- user = get_current_user();
- error = -ENOMEM;
- ep = kzalloc(sizeof(*ep), GFP_KERNEL);
- if (unlikely(!ep))
- goto free_uid;
- mutex_init(&ep->mtx);
- rwlock_init(&ep->lock);
- init_waitqueue_head(&ep->wq);
- init_waitqueue_head(&ep->poll_wait);
- INIT_LIST_HEAD(&ep->rdllist);
- ep->rbr = RB_ROOT_CACHED;
- ep->ovflist = EP_UNACTIVE_PTR;
- ep->user = user;
- *pep = ep;
- return 0;
- free_uid:
- free_uid(user);
- return error;
- }
- /*
- * Search the file inside the eventpoll tree. The RB tree operations
- * are protected by the "mtx" mutex, and ep_find() must be called with
- * "mtx" held.
- */
- static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
- {
- int kcmp;
- struct rb_node *rbp;
- struct epitem *epi, *epir = NULL;
- struct epoll_filefd ffd;
- ep_set_ffd(&ffd, file, fd);
- for (rbp = ep->rbr.rb_root.rb_node; rbp; ) {
- epi = rb_entry(rbp, struct epitem, rbn);
- kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
- if (kcmp > 0)
- rbp = rbp->rb_right;
- else if (kcmp < 0)
- rbp = rbp->rb_left;
- else {
- epir = epi;
- break;
- }
- }
- return epir;
- }
- #ifdef CONFIG_KCMP
- static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
- {
- struct rb_node *rbp;
- struct epitem *epi;
- for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
- epi = rb_entry(rbp, struct epitem, rbn);
- if (epi->ffd.fd == tfd) {
- if (toff == 0)
- return epi;
- else
- toff--;
- }
- cond_resched();
- }
- return NULL;
- }
- struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
- unsigned long toff)
- {
- struct file *file_raw;
- struct eventpoll *ep;
- struct epitem *epi;
- if (!is_file_epoll(file))
- return ERR_PTR(-EINVAL);
- ep = file->private_data;
- mutex_lock(&ep->mtx);
- epi = ep_find_tfd(ep, tfd, toff);
- if (epi)
- file_raw = epi->ffd.file;
- else
- file_raw = ERR_PTR(-ENOENT);
- mutex_unlock(&ep->mtx);
- return file_raw;
- }
- #endif /* CONFIG_KCMP */
- /**
- * Adds a new entry to the tail of the list in a lockless way, i.e.
- * multiple CPUs are allowed to call this function concurrently.
- *
- * Beware: it is necessary to prevent any other modifications of the
- * existing list until all changes are completed, in other words
- * concurrent list_add_tail_lockless() calls should be protected
- * with a read lock, where write lock acts as a barrier which
- * makes sure all list_add_tail_lockless() calls are fully
- * completed.
- *
- * Also an element can be locklessly added to the list only in one
- * direction i.e. either to the tail either to the head, otherwise
- * concurrent access will corrupt the list.
- *
- * Returns %false if element has been already added to the list, %true
- * otherwise.
- */
- static inline bool list_add_tail_lockless(struct list_head *new,
- struct list_head *head)
- {
- struct list_head *prev;
- /*
- * This is simple 'new->next = head' operation, but cmpxchg()
- * is used in order to detect that same element has been just
- * added to the list from another CPU: the winner observes
- * new->next == new.
- */
- if (cmpxchg(&new->next, new, head) != new)
- return false;
- /*
- * Initially ->next of a new element must be updated with the head
- * (we are inserting to the tail) and only then pointers are atomically
- * exchanged. XCHG guarantees memory ordering, thus ->next should be
- * updated before pointers are actually swapped and pointers are
- * swapped before prev->next is updated.
- */
- prev = xchg(&head->prev, new);
- /*
- * It is safe to modify prev->next and new->prev, because a new element
- * is added only to the tail and new->next is updated before XCHG.
- */
- prev->next = new;
- new->prev = prev;
- return true;
- }
- /**
- * Chains a new epi entry to the tail of the ep->ovflist in a lockless way,
- * i.e. multiple CPUs are allowed to call this function concurrently.
- *
- * Returns %false if epi element has been already chained, %true otherwise.
- */
- static inline bool chain_epi_lockless(struct epitem *epi)
- {
- struct eventpoll *ep = epi->ep;
- /* Fast preliminary check */
- if (epi->next != EP_UNACTIVE_PTR)
- return false;
- /* Check that the same epi has not been just chained from another CPU */
- if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
- return false;
- /* Atomically exchange tail */
- epi->next = xchg(&ep->ovflist, epi);
- return true;
- }
- /*
- * This is the callback that is passed to the wait queue wakeup
- * mechanism. It is called by the stored file descriptors when they
- * have events to report.
- *
- * This callback takes a read lock in order not to content with concurrent
- * events from another file descriptors, thus all modifications to ->rdllist
- * or ->ovflist are lockless. Read lock is paired with the write lock from
- * ep_scan_ready_list(), which stops all list modifications and guarantees
- * that lists state is seen correctly.
- *
- * Another thing worth to mention is that ep_poll_callback() can be called
- * concurrently for the same @epi from different CPUs if poll table was inited
- * with several wait queues entries. Plural wakeup from different CPUs of a
- * single wait queue is serialized by wq.lock, but the case when multiple wait
- * queues are used should be detected accordingly. This is detected using
- * cmpxchg() operation.
- */
- static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
- {
- int pwake = 0;
- struct epitem *epi = ep_item_from_wait(wait);
- struct eventpoll *ep = epi->ep;
- __poll_t pollflags = key_to_poll(key);
- unsigned long flags;
- int ewake = 0;
- read_lock_irqsave(&ep->lock, flags);
- ep_set_busy_poll_napi_id(epi);
- /*
- * If the event mask does not contain any poll(2) event, we consider the
- * descriptor to be disabled. This condition is likely the effect of the
- * EPOLLONESHOT bit that disables the descriptor when an event is received,
- * until the next EPOLL_CTL_MOD will be issued.
- */
- if (!(epi->event.events & ~EP_PRIVATE_BITS))
- goto out_unlock;
- /*
- * Check the events coming with the callback. At this stage, not
- * every device reports the events in the "key" parameter of the
- * callback. We need to be able to handle both cases here, hence the
- * test for "key" != NULL before the event match test.
- */
- if (pollflags && !(pollflags & epi->event.events))
- goto out_unlock;
- /*
- * If we are transferring events to userspace, we can hold no locks
- * (because we're accessing user memory, and because of linux f_op->poll()
- * semantics). All the events that happen during that period of time are
- * chained in ep->ovflist and requeued later on.
- */
- if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
- if (chain_epi_lockless(epi))
- ep_pm_stay_awake_rcu(epi);
- } else if (!ep_is_linked(epi)) {
- /* In the usual case, add event to ready list. */
- if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
- ep_pm_stay_awake_rcu(epi);
- }
- /*
- * Wake up ( if active ) both the eventpoll wait list and the ->poll()
- * wait list.
- */
- if (waitqueue_active(&ep->wq)) {
- if ((epi->event.events & EPOLLEXCLUSIVE) &&
- !(pollflags & POLLFREE)) {
- switch (pollflags & EPOLLINOUT_BITS) {
- case EPOLLIN:
- if (epi->event.events & EPOLLIN)
- ewake = 1;
- break;
- case EPOLLOUT:
- if (epi->event.events & EPOLLOUT)
- ewake = 1;
- break;
- case 0:
- ewake = 1;
- break;
- }
- }
- wake_up(&ep->wq);
- }
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
- out_unlock:
- read_unlock_irqrestore(&ep->lock, flags);
- /* We have to call this outside the lock */
- if (pwake)
- ep_poll_safewake(ep, epi);
- if (!(epi->event.events & EPOLLEXCLUSIVE))
- ewake = 1;
- if (pollflags & POLLFREE) {
- /*
- * If we race with ep_remove_wait_queue() it can miss
- * ->whead = NULL and do another remove_wait_queue() after
- * us, so we can't use __remove_wait_queue().
- */
- list_del_init(&wait->entry);
- /*
- * ->whead != NULL protects us from the race with ep_free()
- * or ep_remove(), ep_remove_wait_queue() takes whead->lock
- * held by the caller. Once we nullify it, nothing protects
- * ep/epi or even wait.
- */
- smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
- }
- return ewake;
- }
- /*
- * This is the callback that is used to add our wait queue to the
- * target file wakeup lists.
- */
- static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
- poll_table *pt)
- {
- struct epitem *epi = ep_item_from_epqueue(pt);
- struct eppoll_entry *pwq;
- if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
- init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
- pwq->whead = whead;
- pwq->base = epi;
- if (epi->event.events & EPOLLEXCLUSIVE)
- add_wait_queue_exclusive(whead, &pwq->wait);
- else
- add_wait_queue(whead, &pwq->wait);
- list_add_tail(&pwq->llink, &epi->pwqlist);
- epi->nwait++;
- } else {
- /* We have to signal that an error occurred */
- epi->nwait = -1;
- }
- }
- static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
- {
- int kcmp;
- struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL;
- struct epitem *epic;
- bool leftmost = true;
- while (*p) {
- parent = *p;
- epic = rb_entry(parent, struct epitem, rbn);
- kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd);
- if (kcmp > 0) {
- p = &parent->rb_right;
- leftmost = false;
- } else
- p = &parent->rb_left;
- }
- rb_link_node(&epi->rbn, parent, p);
- rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost);
- }
- #define PATH_ARR_SIZE 5
- /*
- * These are the number paths of length 1 to 5, that we are allowing to emanate
- * from a single file of interest. For example, we allow 1000 paths of length
- * 1, to emanate from each file of interest. This essentially represents the
- * potential wakeup paths, which need to be limited in order to avoid massive
- * uncontrolled wakeup storms. The common use case should be a single ep which
- * is connected to n file sources. In this case each file source has 1 path
- * of length 1. Thus, the numbers below should be more than sufficient. These
- * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify
- * and delete can't add additional paths. Protected by the epmutex.
- */
- static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 };
- static int path_count[PATH_ARR_SIZE];
- static int path_count_inc(int nests)
- {
- /* Allow an arbitrary number of depth 1 paths */
- if (nests == 0)
- return 0;
- if (++path_count[nests] > path_limits[nests])
- return -1;
- return 0;
- }
- static void path_count_init(void)
- {
- int i;
- for (i = 0; i < PATH_ARR_SIZE; i++)
- path_count[i] = 0;
- }
- static int reverse_path_check_proc(void *priv, void *cookie, int call_nests)
- {
- int error = 0;
- struct file *file = priv;
- struct file *child_file;
- struct epitem *epi;
- /* CTL_DEL can remove links here, but that can't increase our count */
- rcu_read_lock();
- list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
- child_file = epi->ep->file;
- if (is_file_epoll(child_file)) {
- if (list_empty(&child_file->f_ep_links)) {
- if (path_count_inc(call_nests)) {
- error = -1;
- break;
- }
- } else {
- error = ep_call_nested(&poll_loop_ncalls,
- reverse_path_check_proc,
- child_file, child_file,
- current);
- }
- if (error != 0)
- break;
- } else {
- printk(KERN_ERR "reverse_path_check_proc: "
- "file is not an ep!\n");
- }
- }
- rcu_read_unlock();
- return error;
- }
- /**
- * reverse_path_check - The tfile_check_list is list of file *, which have
- * links that are proposed to be newly added. We need to
- * make sure that those added links don't add too many
- * paths such that we will spend all our time waking up
- * eventpoll objects.
- *
- * Returns: Returns zero if the proposed links don't create too many paths,
- * -1 otherwise.
- */
- static int reverse_path_check(void)
- {
- int error = 0;
- struct file *current_file;
- /* let's call this for all tfiles */
- list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) {
- path_count_init();
- error = ep_call_nested(&poll_loop_ncalls,
- reverse_path_check_proc, current_file,
- current_file, current);
- if (error)
- break;
- }
- return error;
- }
- static int ep_create_wakeup_source(struct epitem *epi)
- {
- struct name_snapshot n;
- struct wakeup_source *ws;
- char ws_name[64];
- strlcpy(ws_name, "eventpoll", sizeof(ws_name));
- trace_android_vh_ep_create_wakeup_source(ws_name, sizeof(ws_name));
- if (!epi->ep->ws) {
- epi->ep->ws = wakeup_source_register(NULL, ws_name);
- if (!epi->ep->ws)
- return -ENOMEM;
- }
- take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry);
- strlcpy(ws_name, n.name.name, sizeof(ws_name));
- trace_android_vh_ep_create_wakeup_source(ws_name, sizeof(ws_name));
- ws = wakeup_source_register(NULL, ws_name);
- release_dentry_name_snapshot(&n);
- if (!ws)
- return -ENOMEM;
- rcu_assign_pointer(epi->ws, ws);
- return 0;
- }
- /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */
- static noinline void ep_destroy_wakeup_source(struct epitem *epi)
- {
- struct wakeup_source *ws = ep_wakeup_source(epi);
- RCU_INIT_POINTER(epi->ws, NULL);
- /*
- * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is
- * used internally by wakeup_source_remove, too (called by
- * wakeup_source_unregister), so we cannot use call_rcu
- */
- synchronize_rcu();
- wakeup_source_unregister(ws);
- }
- /*
- * Must be called with "mtx" held.
- */
- static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
- struct file *tfile, int fd, int full_check)
- {
- int error, pwake = 0;
- __poll_t revents;
- long user_watches;
- struct epitem *epi;
- struct ep_pqueue epq;
- lockdep_assert_irqs_enabled();
- user_watches = atomic_long_read(&ep->user->epoll_watches);
- if (unlikely(user_watches >= max_user_watches))
- return -ENOSPC;
- if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
- return -ENOMEM;
- /* Item initialization follow here ... */
- INIT_LIST_HEAD(&epi->rdllink);
- INIT_LIST_HEAD(&epi->fllink);
- INIT_LIST_HEAD(&epi->pwqlist);
- epi->ep = ep;
- ep_set_ffd(&epi->ffd, tfile, fd);
- epi->event = *event;
- epi->nwait = 0;
- epi->next = EP_UNACTIVE_PTR;
- if (epi->event.events & EPOLLWAKEUP) {
- error = ep_create_wakeup_source(epi);
- if (error)
- goto error_create_wakeup_source;
- } else {
- RCU_INIT_POINTER(epi->ws, NULL);
- }
- /* Add the current item to the list of active epoll hook for this file */
- spin_lock(&tfile->f_lock);
- list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links);
- spin_unlock(&tfile->f_lock);
- /*
- * Add the current item to the RB tree. All RB tree operations are
- * protected by "mtx", and ep_insert() is called with "mtx" held.
- */
- ep_rbtree_insert(ep, epi);
- /* now check if we've created too many backpaths */
- error = -EINVAL;
- if (full_check && reverse_path_check())
- goto error_remove_epi;
- /* Initialize the poll table using the queue callback */
- epq.epi = epi;
- init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
- /*
- * Attach the item to the poll hooks and get current event bits.
- * We can safely use the file* here because its usage count has
- * been increased by the caller of this function. Note that after
- * this operation completes, the poll callback can start hitting
- * the new item.
- */
- revents = ep_item_poll(epi, &epq.pt, 1);
- /*
- * We have to check if something went wrong during the poll wait queue
- * install process. Namely an allocation for a wait queue failed due
- * high memory pressure.
- */
- error = -ENOMEM;
- if (epi->nwait < 0)
- goto error_unregister;
- /* We have to drop the new item inside our item list to keep track of it */
- write_lock_irq(&ep->lock);
- /* record NAPI ID of new item if present */
- ep_set_busy_poll_napi_id(epi);
- /* If the file is already "ready" we drop it inside the ready list */
- if (revents && !ep_is_linked(epi)) {
- list_add_tail(&epi->rdllink, &ep->rdllist);
- ep_pm_stay_awake(epi);
- /* Notify waiting tasks that events are available */
- if (waitqueue_active(&ep->wq))
- wake_up(&ep->wq);
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
- }
- write_unlock_irq(&ep->lock);
- atomic_long_inc(&ep->user->epoll_watches);
- /* We have to call this outside the lock */
- if (pwake)
- ep_poll_safewake(ep, NULL);
- return 0;
- error_unregister:
- ep_unregister_pollwait(ep, epi);
- error_remove_epi:
- spin_lock(&tfile->f_lock);
- list_del_rcu(&epi->fllink);
- spin_unlock(&tfile->f_lock);
- rb_erase_cached(&epi->rbn, &ep->rbr);
- /*
- * We need to do this because an event could have been arrived on some
- * allocated wait queue. Note that we don't care about the ep->ovflist
- * list, since that is used/cleaned only inside a section bound by "mtx".
- * And ep_insert() is called with "mtx" held.
- */
- write_lock_irq(&ep->lock);
- if (ep_is_linked(epi))
- list_del_init(&epi->rdllink);
- write_unlock_irq(&ep->lock);
- wakeup_source_unregister(ep_wakeup_source(epi));
- error_create_wakeup_source:
- kmem_cache_free(epi_cache, epi);
- return error;
- }
- /*
- * Modify the interest event mask by dropping an event if the new mask
- * has a match in the current file status. Must be called with "mtx" held.
- */
- static int ep_modify(struct eventpoll *ep, struct epitem *epi,
- const struct epoll_event *event)
- {
- int pwake = 0;
- poll_table pt;
- lockdep_assert_irqs_enabled();
- init_poll_funcptr(&pt, NULL);
- /*
- * Set the new event interest mask before calling f_op->poll();
- * otherwise we might miss an event that happens between the
- * f_op->poll() call and the new event set registering.
- */
- epi->event.events = event->events; /* need barrier below */
- epi->event.data = event->data; /* protected by mtx */
- if (epi->event.events & EPOLLWAKEUP) {
- if (!ep_has_wakeup_source(epi))
- ep_create_wakeup_source(epi);
- } else if (ep_has_wakeup_source(epi)) {
- ep_destroy_wakeup_source(epi);
- }
- /*
- * The following barrier has two effects:
- *
- * 1) Flush epi changes above to other CPUs. This ensures
- * we do not miss events from ep_poll_callback if an
- * event occurs immediately after we call f_op->poll().
- * We need this because we did not take ep->lock while
- * changing epi above (but ep_poll_callback does take
- * ep->lock).
- *
- * 2) We also need to ensure we do not miss _past_ events
- * when calling f_op->poll(). This barrier also
- * pairs with the barrier in wq_has_sleeper (see
- * comments for wq_has_sleeper).
- *
- * This barrier will now guarantee ep_poll_callback or f_op->poll
- * (or both) will notice the readiness of an item.
- */
- smp_mb();
- /*
- * Get current event bits. We can safely use the file* here because
- * its usage count has been increased by the caller of this function.
- * If the item is "hot" and it is not registered inside the ready
- * list, push it inside.
- */
- if (ep_item_poll(epi, &pt, 1)) {
- write_lock_irq(&ep->lock);
- if (!ep_is_linked(epi)) {
- list_add_tail(&epi->rdllink, &ep->rdllist);
- ep_pm_stay_awake(epi);
- /* Notify waiting tasks that events are available */
- if (waitqueue_active(&ep->wq))
- wake_up(&ep->wq);
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
- }
- write_unlock_irq(&ep->lock);
- }
- /* We have to call this outside the lock */
- if (pwake)
- ep_poll_safewake(ep, NULL);
- return 0;
- }
- static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
- void *priv)
- {
- struct ep_send_events_data *esed = priv;
- __poll_t revents;
- struct epitem *epi, *tmp;
- struct epoll_event __user *uevent = esed->events;
- struct wakeup_source *ws;
- poll_table pt;
- init_poll_funcptr(&pt, NULL);
- esed->res = 0;
- /*
- * We can loop without lock because we are passed a task private list.
- * Items cannot vanish during the loop because ep_scan_ready_list() is
- * holding "mtx" during this call.
- */
- lockdep_assert_held(&ep->mtx);
- list_for_each_entry_safe(epi, tmp, head, rdllink) {
- if (esed->res >= esed->maxevents)
- break;
- /*
- * Activate ep->ws before deactivating epi->ws to prevent
- * triggering auto-suspend here (in case we reactive epi->ws
- * below).
- *
- * This could be rearranged to delay the deactivation of epi->ws
- * instead, but then epi->ws would temporarily be out of sync
- * with ep_is_linked().
- */
- ws = ep_wakeup_source(epi);
- if (ws) {
- if (ws->active)
- __pm_stay_awake(ep->ws);
- __pm_relax(ws);
- }
- list_del_init(&epi->rdllink);
- /*
- * If the event mask intersect the caller-requested one,
- * deliver the event to userspace. Again, ep_scan_ready_list()
- * is holding ep->mtx, so no operations coming from userspace
- * can change the item.
- */
- revents = ep_item_poll(epi, &pt, 1);
- if (!revents)
- continue;
- if (__put_user(revents, &uevent->events) ||
- __put_user(epi->event.data, &uevent->data)) {
- list_add(&epi->rdllink, head);
- ep_pm_stay_awake(epi);
- if (!esed->res)
- esed->res = -EFAULT;
- return 0;
- }
- esed->res++;
- uevent++;
- if (epi->event.events & EPOLLONESHOT)
- epi->event.events &= EP_PRIVATE_BITS;
- else if (!(epi->event.events & EPOLLET)) {
- /*
- * If this file has been added with Level
- * Trigger mode, we need to insert back inside
- * the ready list, so that the next call to
- * epoll_wait() will check again the events
- * availability. At this point, no one can insert
- * into ep->rdllist besides us. The epoll_ctl()
- * callers are locked out by
- * ep_scan_ready_list() holding "mtx" and the
- * poll callback will queue them in ep->ovflist.
- */
- list_add_tail(&epi->rdllink, &ep->rdllist);
- ep_pm_stay_awake(epi);
- }
- }
- return 0;
- }
- static int ep_send_events(struct eventpoll *ep,
- struct epoll_event __user *events, int maxevents)
- {
- struct ep_send_events_data esed;
- esed.maxevents = maxevents;
- esed.events = events;
- ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false);
- return esed.res;
- }
- static inline struct timespec64 ep_set_mstimeout(long ms)
- {
- struct timespec64 now, ts = {
- .tv_sec = ms / MSEC_PER_SEC,
- .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
- };
- ktime_get_ts64(&now);
- return timespec64_add_safe(now, ts);
- }
- /**
- * ep_poll - Retrieves ready events, and delivers them to the caller supplied
- * event buffer.
- *
- * @ep: Pointer to the eventpoll context.
- * @events: Pointer to the userspace buffer where the ready events should be
- * stored.
- * @maxevents: Size (in terms of number of events) of the caller event buffer.
- * @timeout: Maximum timeout for the ready events fetch operation, in
- * milliseconds. If the @timeout is zero, the function will not block,
- * while if the @timeout is less than zero, the function will block
- * until at least one event has been retrieved (or an error
- * occurred).
- *
- * Returns: Returns the number of ready events which have been fetched, or an
- * error code, in case of error.
- */
- static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
- int maxevents, long timeout)
- {
- int res = 0, eavail, timed_out = 0;
- u64 slack = 0;
- wait_queue_entry_t wait;
- ktime_t expires, *to = NULL;
- lockdep_assert_irqs_enabled();
- if (timeout > 0) {
- struct timespec64 end_time = ep_set_mstimeout(timeout);
- slack = select_estimate_accuracy(&end_time);
- to = &expires;
- *to = timespec64_to_ktime(end_time);
- } else if (timeout == 0) {
- /*
- * Avoid the unnecessary trip to the wait queue loop, if the
- * caller specified a non blocking operation. We still need
- * lock because we could race and not see an epi being added
- * to the ready list while in irq callback. Thus incorrectly
- * returning 0 back to userspace.
- */
- timed_out = 1;
- write_lock_irq(&ep->lock);
- eavail = ep_events_available(ep);
- write_unlock_irq(&ep->lock);
- goto send_events;
- }
- fetch_events:
- if (!ep_events_available(ep))
- ep_busy_loop(ep, timed_out);
- eavail = ep_events_available(ep);
- if (eavail)
- goto send_events;
- /*
- * Busy poll timed out. Drop NAPI ID for now, we can add
- * it back in when we have moved a socket with a valid NAPI
- * ID onto the ready list.
- */
- ep_reset_busy_poll_napi_id(ep);
- do {
- /*
- * Internally init_wait() uses autoremove_wake_function(),
- * thus wait entry is removed from the wait queue on each
- * wakeup. Why it is important? In case of several waiters
- * each new wakeup will hit the next waiter, giving it the
- * chance to harvest new event. Otherwise wakeup can be
- * lost. This is also good performance-wise, because on
- * normal wakeup path no need to call __remove_wait_queue()
- * explicitly, thus ep->lock is not taken, which halts the
- * event delivery.
- */
- init_wait(&wait);
- write_lock_irq(&ep->lock);
- /*
- * Barrierless variant, waitqueue_active() is called under
- * the same lock on wakeup ep_poll_callback() side, so it
- * is safe to avoid an explicit barrier.
- */
- __set_current_state(TASK_INTERRUPTIBLE);
- /*
- * Do the final check under the lock. ep_scan_ready_list()
- * plays with two lists (->rdllist and ->ovflist) and there
- * is always a race when both lists are empty for short
- * period of time although events are pending, so lock is
- * important.
- */
- eavail = ep_events_available(ep);
- if (!eavail) {
- if (signal_pending(current))
- res = -EINTR;
- else
- __add_wait_queue_exclusive(&ep->wq, &wait);
- }
- write_unlock_irq(&ep->lock);
- if (!eavail && !res)
- timed_out = !freezable_schedule_hrtimeout_range(to, slack,
- HRTIMER_MODE_ABS);
- /*
- * We were woken up, thus go and try to harvest some events.
- * If timed out and still on the wait queue, recheck eavail
- * carefully under lock, below.
- */
- eavail = 1;
- } while (0);
- __set_current_state(TASK_RUNNING);
- if (!list_empty_careful(&wait.entry)) {
- write_lock_irq(&ep->lock);
- /*
- * If the thread timed out and is not on the wait queue, it
- * means that the thread was woken up after its timeout expired
- * before it could reacquire the lock. Thus, when wait.entry is
- * empty, it needs to harvest events.
- */
- if (timed_out)
- eavail = list_empty(&wait.entry);
- __remove_wait_queue(&ep->wq, &wait);
- write_unlock_irq(&ep->lock);
- }
- send_events:
- if (fatal_signal_pending(current)) {
- /*
- * Always short-circuit for fatal signals to allow
- * threads to make a timely exit without the chance of
- * finding more events available and fetching
- * repeatedly.
- */
- res = -EINTR;
- }
- /*
- * Try to transfer events to user space. In case we get 0 events and
- * there's still timeout left over, we go trying again in search of
- * more luck.
- */
- if (!res && eavail &&
- !(res = ep_send_events(ep, events, maxevents)) && !timed_out)
- goto fetch_events;
- return res;
- }
- /**
- * ep_loop_check_proc - Callback function to be passed to the @ep_call_nested()
- * API, to verify that adding an epoll file inside another
- * epoll structure, does not violate the constraints, in
- * terms of closed loops, or too deep chains (which can
- * result in excessive stack usage).
- *
- * @priv: Pointer to the epoll file to be currently checked.
- * @cookie: Original cookie for this call. This is the top-of-the-chain epoll
- * data structure pointer.
- * @call_nests: Current dept of the @ep_call_nested() call stack.
- *
- * Returns: Returns zero if adding the epoll @file inside current epoll
- * structure @ep does not violate the constraints, or -1 otherwise.
- */
- static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
- {
- int error = 0;
- struct file *file = priv;
- struct eventpoll *ep = file->private_data;
- struct eventpoll *ep_tovisit;
- struct rb_node *rbp;
- struct epitem *epi;
- mutex_lock_nested(&ep->mtx, call_nests + 1);
- ep->gen = loop_check_gen;
- for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
- epi = rb_entry(rbp, struct epitem, rbn);
- if (unlikely(is_file_epoll(epi->ffd.file))) {
- ep_tovisit = epi->ffd.file->private_data;
- if (ep_tovisit->gen == loop_check_gen)
- continue;
- error = ep_call_nested(&poll_loop_ncalls,
- ep_loop_check_proc, epi->ffd.file,
- ep_tovisit, current);
- if (error != 0)
- break;
- } else {
- /*
- * If we've reached a file that is not associated with
- * an ep, then we need to check if the newly added
- * links are going to add too many wakeup paths. We do
- * this by adding it to the tfile_check_list, if it's
- * not already there, and calling reverse_path_check()
- * during ep_insert().
- */
- if (list_empty(&epi->ffd.file->f_tfile_llink)) {
- if (get_file_rcu(epi->ffd.file))
- list_add(&epi->ffd.file->f_tfile_llink,
- &tfile_check_list);
- }
- }
- }
- mutex_unlock(&ep->mtx);
- return error;
- }
- /**
- * ep_loop_check - Performs a check to verify that adding an epoll file (@file)
- * another epoll file (represented by @ep) does not create
- * closed loops or too deep chains.
- *
- * @ep: Pointer to the epoll private data structure.
- * @file: Pointer to the epoll file to be checked.
- *
- * Returns: Returns zero if adding the epoll @file inside current epoll
- * structure @ep does not violate the constraints, or -1 otherwise.
- */
- static int ep_loop_check(struct eventpoll *ep, struct file *file)
- {
- return ep_call_nested(&poll_loop_ncalls,
- ep_loop_check_proc, file, ep, current);
- }
- static void clear_tfile_check_list(void)
- {
- struct file *file;
- /* first clear the tfile_check_list */
- while (!list_empty(&tfile_check_list)) {
- file = list_first_entry(&tfile_check_list, struct file,
- f_tfile_llink);
- list_del_init(&file->f_tfile_llink);
- fput(file);
- }
- INIT_LIST_HEAD(&tfile_check_list);
- }
- /*
- * Open an eventpoll file descriptor.
- */
- static int do_epoll_create(int flags)
- {
- int error, fd;
- struct eventpoll *ep = NULL;
- struct file *file;
- /* Check the EPOLL_* constant for consistency. */
- BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
- if (flags & ~EPOLL_CLOEXEC)
- return -EINVAL;
- /*
- * Create the internal data structure ("struct eventpoll").
- */
- error = ep_alloc(&ep);
- if (error < 0)
- return error;
- /*
- * Creates all the items needed to setup an eventpoll file. That is,
- * a file structure and a free file descriptor.
- */
- fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
- if (fd < 0) {
- error = fd;
- goto out_free_ep;
- }
- file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
- O_RDWR | (flags & O_CLOEXEC));
- if (IS_ERR(file)) {
- error = PTR_ERR(file);
- goto out_free_fd;
- }
- ep->file = file;
- fd_install(fd, file);
- return fd;
- out_free_fd:
- put_unused_fd(fd);
- out_free_ep:
- ep_free(ep);
- return error;
- }
- SYSCALL_DEFINE1(epoll_create1, int, flags)
- {
- return do_epoll_create(flags);
- }
- SYSCALL_DEFINE1(epoll_create, int, size)
- {
- if (size <= 0)
- return -EINVAL;
- return do_epoll_create(0);
- }
- static inline int epoll_mutex_lock(struct mutex *mutex, int depth,
- bool nonblock)
- {
- if (!nonblock) {
- mutex_lock_nested(mutex, depth);
- return 0;
- }
- if (mutex_trylock(mutex))
- return 0;
- return -EAGAIN;
- }
- int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
- bool nonblock)
- {
- int error;
- int full_check = 0;
- struct fd f, tf;
- struct eventpoll *ep;
- struct epitem *epi;
- struct eventpoll *tep = NULL;
- error = -EBADF;
- f = fdget(epfd);
- if (!f.file)
- goto error_return;
- /* Get the "struct file *" for the target file */
- tf = fdget(fd);
- if (!tf.file)
- goto error_fput;
- /* The target file descriptor must support poll */
- error = -EPERM;
- if (!file_can_poll(tf.file))
- goto error_tgt_fput;
- /* Check if EPOLLWAKEUP is allowed */
- if (ep_op_has_event(op))
- ep_take_care_of_epollwakeup(epds);
- /*
- * We have to check that the file structure underneath the file descriptor
- * the user passed to us _is_ an eventpoll file. And also we do not permit
- * adding an epoll file descriptor inside itself.
- */
- error = -EINVAL;
- if (f.file == tf.file || !is_file_epoll(f.file))
- goto error_tgt_fput;
- /*
- * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only,
- * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
- * Also, we do not currently supported nested exclusive wakeups.
- */
- if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) {
- if (op == EPOLL_CTL_MOD)
- goto error_tgt_fput;
- if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
- (epds->events & ~EPOLLEXCLUSIVE_OK_BITS)))
- goto error_tgt_fput;
- }
- /*
- * At this point it is safe to assume that the "private_data" contains
- * our own data structure.
- */
- ep = f.file->private_data;
- /*
- * When we insert an epoll file descriptor, inside another epoll file
- * descriptor, there is the change of creating closed loops, which are
- * better be handled here, than in more critical paths. While we are
- * checking for loops we also determine the list of files reachable
- * and hang them on the tfile_check_list, so we can check that we
- * haven't created too many possible wakeup paths.
- *
- * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when
- * the epoll file descriptor is attaching directly to a wakeup source,
- * unless the epoll file descriptor is nested. The purpose of taking the
- * 'epmutex' on add is to prevent complex toplogies such as loops and
- * deep wakeup paths from forming in parallel through multiple
- * EPOLL_CTL_ADD operations.
- */
- error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
- if (error)
- goto error_tgt_fput;
- if (op == EPOLL_CTL_ADD) {
- if (!list_empty(&f.file->f_ep_links) ||
- ep->gen == loop_check_gen ||
- is_file_epoll(tf.file)) {
- mutex_unlock(&ep->mtx);
- error = epoll_mutex_lock(&epmutex, 0, nonblock);
- if (error)
- goto error_tgt_fput;
- loop_check_gen++;
- full_check = 1;
- if (is_file_epoll(tf.file)) {
- error = -ELOOP;
- if (ep_loop_check(ep, tf.file) != 0)
- goto error_tgt_fput;
- } else {
- get_file(tf.file);
- list_add(&tf.file->f_tfile_llink,
- &tfile_check_list);
- }
- error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
- if (error)
- goto error_tgt_fput;
- if (is_file_epoll(tf.file)) {
- tep = tf.file->private_data;
- error = epoll_mutex_lock(&tep->mtx, 1, nonblock);
- if (error) {
- mutex_unlock(&ep->mtx);
- goto error_tgt_fput;
- }
- }
- }
- }
- /*
- * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
- * above, we can be sure to be able to use the item looked up by
- * ep_find() till we release the mutex.
- */
- epi = ep_find(ep, tf.file, fd);
- error = -EINVAL;
- switch (op) {
- case EPOLL_CTL_ADD:
- if (!epi) {
- epds->events |= EPOLLERR | EPOLLHUP;
- error = ep_insert(ep, epds, tf.file, fd, full_check);
- } else
- error = -EEXIST;
- break;
- case EPOLL_CTL_DEL:
- if (epi)
- error = ep_remove(ep, epi);
- else
- error = -ENOENT;
- break;
- case EPOLL_CTL_MOD:
- if (epi) {
- if (!(epi->event.events & EPOLLEXCLUSIVE)) {
- epds->events |= EPOLLERR | EPOLLHUP;
- error = ep_modify(ep, epi, epds);
- }
- } else
- error = -ENOENT;
- break;
- }
- if (tep != NULL)
- mutex_unlock(&tep->mtx);
- mutex_unlock(&ep->mtx);
- error_tgt_fput:
- if (full_check) {
- clear_tfile_check_list();
- loop_check_gen++;
- mutex_unlock(&epmutex);
- }
- fdput(tf);
- error_fput:
- fdput(f);
- error_return:
- return error;
- }
- /*
- * The following function implements the controller interface for
- * the eventpoll file that enables the insertion/removal/change of
- * file descriptors inside the interest set.
- */
- SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
- struct epoll_event __user *, event)
- {
- struct epoll_event epds;
- if (ep_op_has_event(op) &&
- copy_from_user(&epds, event, sizeof(struct epoll_event)))
- return -EFAULT;
- return do_epoll_ctl(epfd, op, fd, &epds, false);
- }
- /*
- * Implement the event wait interface for the eventpoll file. It is the kernel
- * part of the user space epoll_wait(2).
- */
- static int do_epoll_wait(int epfd, struct epoll_event __user *events,
- int maxevents, int timeout)
- {
- int error;
- struct fd f;
- struct eventpoll *ep;
- /* The maximum number of event must be greater than zero */
- if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
- return -EINVAL;
- /* Verify that the area passed by the user is writeable */
- if (!access_ok(events, maxevents * sizeof(struct epoll_event)))
- return -EFAULT;
- /* Get the "struct file *" for the eventpoll file */
- f = fdget(epfd);
- if (!f.file)
- return -EBADF;
- /*
- * We have to check that the file structure underneath the fd
- * the user passed to us _is_ an eventpoll file.
- */
- error = -EINVAL;
- if (!is_file_epoll(f.file))
- goto error_fput;
- /*
- * At this point it is safe to assume that the "private_data" contains
- * our own data structure.
- */
- ep = f.file->private_data;
- /* Time to fish for events ... */
- error = ep_poll(ep, events, maxevents, timeout);
- error_fput:
- fdput(f);
- return error;
- }
- SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
- int, maxevents, int, timeout)
- {
- return do_epoll_wait(epfd, events, maxevents, timeout);
- }
- /*
- * Implement the event wait interface for the eventpoll file. It is the kernel
- * part of the user space epoll_pwait(2).
- */
- SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
- int, maxevents, int, timeout, const sigset_t __user *, sigmask,
- size_t, sigsetsize)
- {
- int error;
- /*
- * If the caller wants a certain signal mask to be set during the wait,
- * we apply it here.
- */
- error = set_user_sigmask(sigmask, sigsetsize);
- if (error)
- return error;
- error = do_epoll_wait(epfd, events, maxevents, timeout);
- restore_saved_sigmask_unless(error == -EINTR);
- return error;
- }
- #ifdef CONFIG_COMPAT
- COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd,
- struct epoll_event __user *, events,
- int, maxevents, int, timeout,
- const compat_sigset_t __user *, sigmask,
- compat_size_t, sigsetsize)
- {
- long err;
- /*
- * If the caller wants a certain signal mask to be set during the wait,
- * we apply it here.
- */
- err = set_compat_user_sigmask(sigmask, sigsetsize);
- if (err)
- return err;
- err = do_epoll_wait(epfd, events, maxevents, timeout);
- restore_saved_sigmask_unless(err == -EINTR);
- return err;
- }
- #endif
- static int __init eventpoll_init(void)
- {
- struct sysinfo si;
- si_meminfo(&si);
- /*
- * Allows top 4% of lomem to be allocated for epoll watches (per user).
- */
- max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
- EP_ITEM_COST;
- BUG_ON(max_user_watches < 0);
- /*
- * Initialize the structure used to perform epoll file descriptor
- * inclusion loops checks.
- */
- ep_nested_calls_init(&poll_loop_ncalls);
- /*
- * We can have many thousands of epitems, so prevent this from
- * using an extra cache line on 64-bit (and smaller) CPUs
- */
- BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128);
- /* Allocates slab cache used to allocate "struct epitem" items */
- epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
- 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
- /* Allocates slab cache used to allocate "struct eppoll_entry" */
- pwq_cache = kmem_cache_create("eventpoll_pwq",
- sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
- return 0;
- }
- fs_initcall(eventpoll_init);
|