123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730 |
- /*
- * linux/kernel/sys.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds
- */
- #include <linux/export.h>
- #include <linux/mm.h>
- #include <linux/utsname.h>
- #include <linux/mman.h>
- #include <linux/reboot.h>
- #include <linux/prctl.h>
- #include <linux/highuid.h>
- #include <linux/fs.h>
- #include <linux/kmod.h>
- #include <linux/perf_event.h>
- #include <linux/resource.h>
- #include <linux/kernel.h>
- #include <linux/kexec.h>
- #include <linux/workqueue.h>
- #include <linux/capability.h>
- #include <linux/device.h>
- #include <linux/key.h>
- #include <linux/times.h>
- #include <linux/posix-timers.h>
- #include <linux/security.h>
- #include <linux/dcookies.h>
- #include <linux/suspend.h>
- #include <linux/tty.h>
- #include <linux/signal.h>
- #include <linux/cn_proc.h>
- #include <linux/getcpu.h>
- #include <linux/task_io_accounting_ops.h>
- #include <linux/seccomp.h>
- #include <linux/cpu.h>
- #include <linux/personality.h>
- #include <linux/ptrace.h>
- #include <linux/fs_struct.h>
- #include <linux/file.h>
- #include <linux/mount.h>
- #include <linux/gfp.h>
- #include <linux/syscore_ops.h>
- #include <linux/version.h>
- #include <linux/ctype.h>
- #include <linux/mm.h>
- #include <linux/mempolicy.h>
- #include <linux/sched.h>
- #ifdef CONFIG_RESTART_REASON_SEC_PARAM
- #include <mach/sec_debug.h>
- #endif
- #include <linux/compat.h>
- #include <linux/syscalls.h>
- #include <linux/kprobes.h>
- #include <linux/user_namespace.h>
- #include <linux/binfmts.h>
- #include <linux/kmsg_dump.h>
- #ifdef CONFIG_SEC_DEBUG
- #include <mach/sec_debug.h>
- #endif
- /* Move somewhere else to avoid recompiling? */
- #include <generated/utsrelease.h>
- #include <asm/uaccess.h>
- #include <asm/io.h>
- #include <asm/unistd.h>
- /* Hardening for Spectre-v1 */
- #include <linux/nospec.h>
- #ifndef SET_UNALIGN_CTL
- # define SET_UNALIGN_CTL(a,b) (-EINVAL)
- #endif
- #ifndef GET_UNALIGN_CTL
- # define GET_UNALIGN_CTL(a,b) (-EINVAL)
- #endif
- #ifndef SET_FPEMU_CTL
- # define SET_FPEMU_CTL(a,b) (-EINVAL)
- #endif
- #ifndef GET_FPEMU_CTL
- # define GET_FPEMU_CTL(a,b) (-EINVAL)
- #endif
- #ifndef SET_FPEXC_CTL
- # define SET_FPEXC_CTL(a,b) (-EINVAL)
- #endif
- #ifndef GET_FPEXC_CTL
- # define GET_FPEXC_CTL(a,b) (-EINVAL)
- #endif
- #ifndef GET_ENDIAN
- # define GET_ENDIAN(a,b) (-EINVAL)
- #endif
- #ifndef SET_ENDIAN
- # define SET_ENDIAN(a,b) (-EINVAL)
- #endif
- #ifndef GET_TSC_CTL
- # define GET_TSC_CTL(a) (-EINVAL)
- #endif
- #ifndef SET_TSC_CTL
- # define SET_TSC_CTL(a) (-EINVAL)
- #endif
- /*
- * this is where the system-wide overflow UID and GID are defined, for
- * architectures that now have 32-bit UID/GID but didn't in the past
- */
- int overflowuid = DEFAULT_OVERFLOWUID;
- int overflowgid = DEFAULT_OVERFLOWGID;
- EXPORT_SYMBOL(overflowuid);
- EXPORT_SYMBOL(overflowgid);
- /*
- * the same as above, but for filesystems which can only store a 16-bit
- * UID and GID. as such, this is needed on all architectures
- */
- int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
- int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;
- EXPORT_SYMBOL(fs_overflowuid);
- EXPORT_SYMBOL(fs_overflowgid);
- /*
- * this indicates whether you can reboot with ctrl-alt-del: the default is yes
- */
- int C_A_D = 1;
- struct pid *cad_pid;
- EXPORT_SYMBOL(cad_pid);
- /*
- * If set, this is used for preparing the system to power off.
- */
- void (*pm_power_off_prepare)(void);
- #if defined CONFIG_SEC_RESTRICT_SETUID
- int sec_check_execpath(struct mm_struct *mm, char *denypath);
- #if defined CONFIG_SEC_RESTRICT_ROOTING_LOG
- #define PRINT_LOG(...) printk(KERN_ERR __VA_ARGS__)
- #else
- #define PRINT_LOG(...)
- #endif // End of CONFIG_SEC_RESTRICT_ROOTING_LOG
- static int sec_restrict_uid(void)
- {
- int ret = 0;
- struct task_struct *parent_tsk;
- const struct cred *parent_cred;
- read_lock(&tasklist_lock);
- parent_tsk = current->parent;
- if (!parent_tsk) {
- read_unlock(&tasklist_lock);
- return 0;
- }
- get_task_struct(parent_tsk);
- /* holding on to the task struct is enough so just release
- * the tasklist lock here */
- read_unlock(&tasklist_lock);
- parent_cred = get_task_cred(parent_tsk);
- if (!parent_cred)
- goto out;
- if (parent_cred->euid == 0 || parent_tsk->pid == 1) {
- ret = 0;
- } else if (sec_check_execpath(current->mm, "/system/bin/pppd")) {
- PRINT_LOG("VPN allowed to use root permission");
- ret = 0;
- } else {
- PRINT_LOG("Restricted changing UID. PID = %d(%s) PPID = %d(%s)\n",
- current->pid, current->comm,
- parent_tsk->pid, parent_tsk->comm);
- ret = 1;
- }
- put_cred(parent_cred);
- out:
- put_task_struct(parent_tsk);
- return ret;
- }
- #endif // End of CONFIG_SEC_RESTRICT_SETUID
- /*
- * Returns true if current's euid is same as p's uid or euid,
- * or has CAP_SYS_NICE to p's user_ns.
- *
- * Called with rcu_read_lock, creds are safe
- */
- static bool set_one_prio_perm(struct task_struct *p)
- {
- const struct cred *cred = current_cred(), *pcred = __task_cred(p);
- if (uid_eq(pcred->uid, cred->euid) ||
- uid_eq(pcred->euid, cred->euid))
- return true;
- if (ns_capable(pcred->user_ns, CAP_SYS_NICE))
- return true;
- return false;
- }
- /*
- * set the priority of a task
- * - the caller must hold the RCU read lock
- */
- static int set_one_prio(struct task_struct *p, int niceval, int error)
- {
- int no_nice;
- if (!set_one_prio_perm(p)) {
- error = -EPERM;
- goto out;
- }
- if (niceval < task_nice(p) && !can_nice(p, niceval)) {
- error = -EACCES;
- goto out;
- }
- no_nice = security_task_setnice(p, niceval);
- if (no_nice) {
- error = no_nice;
- goto out;
- }
- if (error == -ESRCH)
- error = 0;
- set_user_nice(p, niceval);
- out:
- return error;
- }
- SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
- {
- struct task_struct *g, *p;
- struct user_struct *user;
- const struct cred *cred = current_cred();
- int error = -EINVAL;
- struct pid *pgrp;
- kuid_t uid;
- if (which > PRIO_USER || which < PRIO_PROCESS)
- goto out;
- /* normalize: avoid signed division (rounding problems) */
- error = -ESRCH;
- if (niceval < -20)
- niceval = -20;
- if (niceval > 19)
- niceval = 19;
- rcu_read_lock();
- read_lock(&tasklist_lock);
- switch (which) {
- case PRIO_PROCESS:
- if (who)
- p = find_task_by_vpid(who);
- else
- p = current;
- if (p)
- error = set_one_prio(p, niceval, error);
- break;
- case PRIO_PGRP:
- if (who)
- pgrp = find_vpid(who);
- else
- pgrp = task_pgrp(current);
- do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
- error = set_one_prio(p, niceval, error);
- } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
- break;
- case PRIO_USER:
- uid = make_kuid(cred->user_ns, who);
- user = cred->user;
- if (!who)
- uid = cred->uid;
- else if (!uid_eq(uid, cred->uid) &&
- !(user = find_user(uid)))
- goto out_unlock; /* No processes for this user */
- do_each_thread(g, p) {
- if (uid_eq(task_uid(p), uid))
- error = set_one_prio(p, niceval, error);
- } while_each_thread(g, p);
- if (!uid_eq(uid, cred->uid))
- free_uid(user); /* For find_user() */
- break;
- }
- out_unlock:
- read_unlock(&tasklist_lock);
- rcu_read_unlock();
- out:
- return error;
- }
- /*
- * Ugh. To avoid negative return values, "getpriority()" will
- * not return the normal nice-value, but a negated value that
- * has been offset by 20 (ie it returns 40..1 instead of -20..19)
- * to stay compatible.
- */
- SYSCALL_DEFINE2(getpriority, int, which, int, who)
- {
- struct task_struct *g, *p;
- struct user_struct *user;
- const struct cred *cred = current_cred();
- long niceval, retval = -ESRCH;
- struct pid *pgrp;
- kuid_t uid;
- if (which > PRIO_USER || which < PRIO_PROCESS)
- return -EINVAL;
- rcu_read_lock();
- read_lock(&tasklist_lock);
- switch (which) {
- case PRIO_PROCESS:
- if (who)
- p = find_task_by_vpid(who);
- else
- p = current;
- if (p) {
- niceval = 20 - task_nice(p);
- if (niceval > retval)
- retval = niceval;
- }
- break;
- case PRIO_PGRP:
- if (who)
- pgrp = find_vpid(who);
- else
- pgrp = task_pgrp(current);
- do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
- niceval = 20 - task_nice(p);
- if (niceval > retval)
- retval = niceval;
- } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
- break;
- case PRIO_USER:
- uid = make_kuid(cred->user_ns, who);
- user = cred->user;
- if (!who)
- uid = cred->uid;
- else if (!uid_eq(uid, cred->uid) &&
- !(user = find_user(uid)))
- goto out_unlock; /* No processes for this user */
- do_each_thread(g, p) {
- if (uid_eq(task_uid(p), uid)) {
- niceval = 20 - task_nice(p);
- if (niceval > retval)
- retval = niceval;
- }
- } while_each_thread(g, p);
- if (!uid_eq(uid, cred->uid))
- free_uid(user); /* for find_user() */
- break;
- }
- out_unlock:
- read_unlock(&tasklist_lock);
- rcu_read_unlock();
- return retval;
- }
- /**
- * emergency_restart - reboot the system
- *
- * Without shutting down any hardware or taking any locks
- * reboot the system. This is called when we know we are in
- * trouble so this is our best effort to reboot. This is
- * safe to call in interrupt context.
- */
- void emergency_restart(void)
- {
- kmsg_dump(KMSG_DUMP_EMERG);
- machine_emergency_restart();
- }
- EXPORT_SYMBOL_GPL(emergency_restart);
- void kernel_restart_prepare(char *cmd)
- {
- blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
- system_state = SYSTEM_RESTART;
- usermodehelper_disable();
- device_shutdown();
- }
- /**
- * register_reboot_notifier - Register function to be called at reboot time
- * @nb: Info about notifier function to be called
- *
- * Registers a function with the list of functions
- * to be called at reboot time.
- *
- * Currently always returns zero, as blocking_notifier_chain_register()
- * always returns zero.
- */
- int register_reboot_notifier(struct notifier_block *nb)
- {
- return blocking_notifier_chain_register(&reboot_notifier_list, nb);
- }
- EXPORT_SYMBOL(register_reboot_notifier);
- /**
- * unregister_reboot_notifier - Unregister previously registered reboot notifier
- * @nb: Hook to be unregistered
- *
- * Unregisters a previously registered reboot
- * notifier function.
- *
- * Returns zero on success, or %-ENOENT on failure.
- */
- int unregister_reboot_notifier(struct notifier_block *nb)
- {
- return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
- }
- EXPORT_SYMBOL(unregister_reboot_notifier);
- /* Add backwards compatibility for stable trees. */
- #ifndef PF_NO_SETAFFINITY
- #define PF_NO_SETAFFINITY PF_THREAD_BOUND
- #endif
- static void migrate_to_reboot_cpu(void)
- {
- /* The boot cpu is always logical cpu 0 */
- int cpu = 0;
- cpu_hotplug_disable();
- /* Make certain the cpu I'm about to reboot on is online */
- if (!cpu_online(cpu))
- cpu = cpumask_first(cpu_online_mask);
- /* Prevent races with other tasks migrating this task */
- current->flags |= PF_NO_SETAFFINITY;
- /* Make certain I only run on the appropriate processor */
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
- }
- /**
- * kernel_restart - reboot the system
- * @cmd: pointer to buffer containing command to execute for restart
- * or %NULL
- *
- * Shutdown everything and perform a clean reboot.
- * This is not safe to call in interrupt context.
- */
- void kernel_restart(char *cmd)
- {
- #ifdef CONFIG_RESTART_REASON_SEC_PARAM
- sec_param_restart_reason(cmd);
- #endif
- #ifdef CONFIG_SEC_MONITOR_BATTERY_REMOVAL
- kernel_sec_set_normal_pwroff(1);
- #endif
- kernel_restart_prepare(cmd);
- migrate_to_reboot_cpu();
- syscore_shutdown();
- if (!cmd)
- printk(KERN_EMERG "Restarting system.\n");
- else
- printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
- kmsg_dump(KMSG_DUMP_RESTART);
- machine_restart(cmd);
- }
- EXPORT_SYMBOL_GPL(kernel_restart);
- static void kernel_shutdown_prepare(enum system_states state)
- {
- blocking_notifier_call_chain(&reboot_notifier_list,
- (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
- system_state = state;
- usermodehelper_disable();
- device_shutdown();
- }
- /**
- * kernel_halt - halt the system
- *
- * Shutdown everything and perform a clean system halt.
- */
- void kernel_halt(void)
- {
- kernel_shutdown_prepare(SYSTEM_HALT);
- migrate_to_reboot_cpu();
- syscore_shutdown();
- printk(KERN_EMERG "System halted.\n");
- kmsg_dump(KMSG_DUMP_HALT);
- machine_halt();
- }
- EXPORT_SYMBOL_GPL(kernel_halt);
- /**
- * kernel_power_off - power_off the system
- *
- * Shutdown everything and perform a clean system power_off.
- */
- void kernel_power_off(void)
- {
- #ifdef CONFIG_SEC_MONITOR_BATTERY_REMOVAL
- kernel_sec_set_normal_pwroff(1);
- #endif
- kernel_shutdown_prepare(SYSTEM_POWER_OFF);
- if (pm_power_off_prepare)
- pm_power_off_prepare();
- migrate_to_reboot_cpu();
- syscore_shutdown();
- printk(KERN_EMERG "Power down.\n");
- kmsg_dump(KMSG_DUMP_POWEROFF);
- machine_power_off();
- }
- EXPORT_SYMBOL_GPL(kernel_power_off);
- static DEFINE_MUTEX(reboot_mutex);
- /*
- * Reboot system call: for obvious reasons only root may call it,
- * and even root needs to set up some magic numbers in the registers
- * so that some mistake won't make this reboot the whole machine.
- * You can also set the meaning of the ctrl-alt-del-key here.
- *
- * reboot doesn't sync: do that yourself before calling this.
- */
- SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
- void __user *, arg)
- {
- char buffer[256];
- int ret = 0;
- /* We only trust the superuser with rebooting the system. */
- if (!capable(CAP_SYS_BOOT))
- return -EPERM;
- /* For safety, we require "magic" arguments. */
- if (magic1 != LINUX_REBOOT_MAGIC1 ||
- (magic2 != LINUX_REBOOT_MAGIC2 &&
- magic2 != LINUX_REBOOT_MAGIC2A &&
- magic2 != LINUX_REBOOT_MAGIC2B &&
- magic2 != LINUX_REBOOT_MAGIC2C))
- return -EINVAL;
- /*
- * If pid namespaces are enabled and the current task is in a child
- * pid_namespace, the command is handled by reboot_pid_ns() which will
- * call do_exit().
- */
- ret = reboot_pid_ns(task_active_pid_ns(current), cmd);
- if (ret)
- return ret;
- /* Instead of trying to make the power_off code look like
- * halt when pm_power_off is not set do it the easy way.
- */
- if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
- cmd = LINUX_REBOOT_CMD_HALT;
- mutex_lock(&reboot_mutex);
- switch (cmd) {
- case LINUX_REBOOT_CMD_RESTART:
- kernel_restart(NULL);
- break;
- case LINUX_REBOOT_CMD_CAD_ON:
- C_A_D = 1;
- break;
- case LINUX_REBOOT_CMD_CAD_OFF:
- C_A_D = 0;
- break;
- case LINUX_REBOOT_CMD_HALT:
- kernel_halt();
- do_exit(0);
- panic("cannot halt.\n");
- case LINUX_REBOOT_CMD_POWER_OFF:
- kernel_power_off();
- do_exit(0);
- break;
- case LINUX_REBOOT_CMD_RESTART2:
- if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
- ret = -EFAULT;
- break;
- }
- buffer[sizeof(buffer) - 1] = '\0';
- kernel_restart(buffer);
- break;
- #ifdef CONFIG_KEXEC
- case LINUX_REBOOT_CMD_KEXEC:
- ret = kernel_kexec();
- break;
- #endif
- #ifdef CONFIG_HIBERNATION
- case LINUX_REBOOT_CMD_SW_SUSPEND:
- ret = hibernate();
- break;
- #endif
- default:
- ret = -EINVAL;
- break;
- }
- mutex_unlock(&reboot_mutex);
- return ret;
- }
- extern void do_emergency_remount(struct work_struct *work);
- static void deferred_cad(struct work_struct *dummy)
- {
- do_emergency_remount(NULL);
- kernel_restart(NULL);
- }
- /*
- * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
- * As it's called within an interrupt, it may NOT sync: the only choice
- * is whether to reboot at once, or just ignore the ctrl-alt-del.
- */
- void ctrl_alt_del(void)
- {
- static DECLARE_WORK(cad_work, deferred_cad);
- if (C_A_D)
- schedule_work(&cad_work);
- else
- kill_cad_pid(SIGINT, 1);
- }
-
- /*
- * Unprivileged users may change the real gid to the effective gid
- * or vice versa. (BSD-style)
- *
- * If you set the real gid at all, or set the effective gid to a value not
- * equal to the real gid, then the saved gid is set to the new effective gid.
- *
- * This makes it possible for a setgid program to completely drop its
- * privileges, which is often a useful assertion to make when you are doing
- * a security audit over a program.
- *
- * The general idea is that a program which uses just setregid() will be
- * 100% compatible with BSD. A program which uses just setgid() will be
- * 100% compatible with POSIX with saved IDs.
- *
- * SMP: There are not races, the GIDs are checked only by filesystem
- * operations (as far as semantic preservation is concerned).
- */
- SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
- {
- struct user_namespace *ns = current_user_ns();
- const struct cred *old;
- struct cred *new;
- int retval;
- kgid_t krgid, kegid;
- krgid = make_kgid(ns, rgid);
- kegid = make_kgid(ns, egid);
- if ((rgid != (gid_t) -1) && !gid_valid(krgid))
- return -EINVAL;
- if ((egid != (gid_t) -1) && !gid_valid(kegid))
- return -EINVAL;
- #if defined CONFIG_SEC_RESTRICT_SETUID
- if(rgid == 0 || egid == 0)
- {
- if(sec_restrict_uid())
- return -EACCES;
- }
- #endif // End of CONFIG_SEC_RESTRICT_SETUID
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
- old = current_cred();
- retval = -EPERM;
- if (rgid != (gid_t) -1) {
- if (gid_eq(old->gid, krgid) ||
- gid_eq(old->egid, krgid) ||
- nsown_capable(CAP_SETGID))
- new->gid = krgid;
- else
- goto error;
- }
- if (egid != (gid_t) -1) {
- if (gid_eq(old->gid, kegid) ||
- gid_eq(old->egid, kegid) ||
- gid_eq(old->sgid, kegid) ||
- nsown_capable(CAP_SETGID))
- new->egid = kegid;
- else
- goto error;
- }
- if (rgid != (gid_t) -1 ||
- (egid != (gid_t) -1 && !gid_eq(kegid, old->gid)))
- new->sgid = new->egid;
- new->fsgid = new->egid;
- return commit_creds(new);
- error:
- abort_creds(new);
- return retval;
- }
- /*
- * setgid() is implemented like SysV w/ SAVED_IDS
- *
- * SMP: Same implicit races as above.
- */
- SYSCALL_DEFINE1(setgid, gid_t, gid)
- {
- struct user_namespace *ns = current_user_ns();
- const struct cred *old;
- struct cred *new;
- int retval;
- kgid_t kgid;
- kgid = make_kgid(ns, gid);
- if (!gid_valid(kgid))
- return -EINVAL;
- #if defined CONFIG_SEC_RESTRICT_SETUID
- if(gid == 0)
- {
- if(sec_restrict_uid())
- return -EACCES;
- }
- #endif // End of CONFIG_SEC_RESTRICT_SETUID
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
- old = current_cred();
- retval = -EPERM;
- if (nsown_capable(CAP_SETGID))
- new->gid = new->egid = new->sgid = new->fsgid = kgid;
- else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
- new->egid = new->fsgid = kgid;
- else
- goto error;
- return commit_creds(new);
- error:
- abort_creds(new);
- return retval;
- }
- /*
- * change the user struct in a credentials set to match the new UID
- */
- static int set_user(struct cred *new)
- {
- struct user_struct *new_user;
- new_user = alloc_uid(new->uid);
- if (!new_user)
- return -EAGAIN;
- /*
- * We don't fail in case of NPROC limit excess here because too many
- * poorly written programs don't check set*uid() return code, assuming
- * it never fails if called by root. We may still enforce NPROC limit
- * for programs doing set*uid()+execve() by harmlessly deferring the
- * failure to the execve() stage.
- */
- if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
- new_user != INIT_USER)
- current->flags |= PF_NPROC_EXCEEDED;
- else
- current->flags &= ~PF_NPROC_EXCEEDED;
- free_uid(new->user);
- new->user = new_user;
- return 0;
- }
- /*
- * Unprivileged users may change the real uid to the effective uid
- * or vice versa. (BSD-style)
- *
- * If you set the real uid at all, or set the effective uid to a value not
- * equal to the real uid, then the saved uid is set to the new effective uid.
- *
- * This makes it possible for a setuid program to completely drop its
- * privileges, which is often a useful assertion to make when you are doing
- * a security audit over a program.
- *
- * The general idea is that a program which uses just setreuid() will be
- * 100% compatible with BSD. A program which uses just setuid() will be
- * 100% compatible with POSIX with saved IDs.
- */
- SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
- {
- struct user_namespace *ns = current_user_ns();
- const struct cred *old;
- struct cred *new;
- int retval;
- kuid_t kruid, keuid;
- kruid = make_kuid(ns, ruid);
- keuid = make_kuid(ns, euid);
- if ((ruid != (uid_t) -1) && !uid_valid(kruid))
- return -EINVAL;
- if ((euid != (uid_t) -1) && !uid_valid(keuid))
- return -EINVAL;
- #if defined CONFIG_SEC_RESTRICT_SETUID
- if(ruid == 0 || euid == 0)
- {
- if(sec_restrict_uid())
- return -EACCES;
- }
- #endif // End of CONFIG_SEC_RESTRICT_SETUID
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
- old = current_cred();
- retval = -EPERM;
- if (ruid != (uid_t) -1) {
- new->uid = kruid;
- if (!uid_eq(old->uid, kruid) &&
- !uid_eq(old->euid, kruid) &&
- !nsown_capable(CAP_SETUID))
- goto error;
- }
- if (euid != (uid_t) -1) {
- new->euid = keuid;
- if (!uid_eq(old->uid, keuid) &&
- !uid_eq(old->euid, keuid) &&
- !uid_eq(old->suid, keuid) &&
- !nsown_capable(CAP_SETUID))
- goto error;
- }
- if (!uid_eq(new->uid, old->uid)) {
- retval = set_user(new);
- if (retval < 0)
- goto error;
- }
- if (ruid != (uid_t) -1 ||
- (euid != (uid_t) -1 && !uid_eq(keuid, old->uid)))
- new->suid = new->euid;
- new->fsuid = new->euid;
- retval = security_task_fix_setuid(new, old, LSM_SETID_RE);
- if (retval < 0)
- goto error;
- return commit_creds(new);
- error:
- abort_creds(new);
- return retval;
- }
-
- /*
- * setuid() is implemented like SysV with SAVED_IDS
- *
- * Note that SAVED_ID's is deficient in that a setuid root program
- * like sendmail, for example, cannot set its uid to be a normal
- * user and then switch back, because if you're root, setuid() sets
- * the saved uid too. If you don't like this, blame the bright people
- * in the POSIX committee and/or USG. Note that the BSD-style setreuid()
- * will allow a root program to temporarily drop privileges and be able to
- * regain them by swapping the real and effective uid.
- */
- SYSCALL_DEFINE1(setuid, uid_t, uid)
- {
- struct user_namespace *ns = current_user_ns();
- const struct cred *old;
- struct cred *new;
- int retval;
- kuid_t kuid;
- kuid = make_kuid(ns, uid);
- if (!uid_valid(kuid))
- return -EINVAL;
- #if defined CONFIG_SEC_RESTRICT_SETUID
- if(uid == 0)
- {
- if(sec_restrict_uid())
- return -EACCES;
- }
- #endif // End of CONFIG_SEC_RESTRICT_SETUID
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
- old = current_cred();
- retval = -EPERM;
- if (nsown_capable(CAP_SETUID)) {
- new->suid = new->uid = kuid;
- if (!uid_eq(kuid, old->uid)) {
- retval = set_user(new);
- if (retval < 0)
- goto error;
- }
- } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) {
- goto error;
- }
- new->fsuid = new->euid = kuid;
- retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
- if (retval < 0)
- goto error;
- return commit_creds(new);
- error:
- abort_creds(new);
- return retval;
- }
- /*
- * This function implements a generic ability to update ruid, euid,
- * and suid. This allows you to implement the 4.4 compatible seteuid().
- */
- SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
- {
- struct user_namespace *ns = current_user_ns();
- const struct cred *old;
- struct cred *new;
- int retval;
- kuid_t kruid, keuid, ksuid;
- kruid = make_kuid(ns, ruid);
- keuid = make_kuid(ns, euid);
- ksuid = make_kuid(ns, suid);
- if ((ruid != (uid_t) -1) && !uid_valid(kruid))
- return -EINVAL;
- if ((euid != (uid_t) -1) && !uid_valid(keuid))
- return -EINVAL;
- if ((suid != (uid_t) -1) && !uid_valid(ksuid))
- return -EINVAL;
- #if defined CONFIG_SEC_RESTRICT_SETUID
- if(ruid == 0 || euid == 0 || suid == 0)
- {
- if(sec_restrict_uid())
- return -EACCES;
- }
- #endif // End of CONFIG_SEC_RESTRICT_SETUID
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
- old = current_cred();
- retval = -EPERM;
- if (!nsown_capable(CAP_SETUID)) {
- if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) &&
- !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid))
- goto error;
- if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) &&
- !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid))
- goto error;
- if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) &&
- !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid))
- goto error;
- }
- if (ruid != (uid_t) -1) {
- new->uid = kruid;
- if (!uid_eq(kruid, old->uid)) {
- retval = set_user(new);
- if (retval < 0)
- goto error;
- }
- }
- if (euid != (uid_t) -1)
- new->euid = keuid;
- if (suid != (uid_t) -1)
- new->suid = ksuid;
- new->fsuid = new->euid;
- retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
- if (retval < 0)
- goto error;
- return commit_creds(new);
- error:
- abort_creds(new);
- return retval;
- }
- SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp)
- {
- const struct cred *cred = current_cred();
- int retval;
- uid_t ruid, euid, suid;
- ruid = from_kuid_munged(cred->user_ns, cred->uid);
- euid = from_kuid_munged(cred->user_ns, cred->euid);
- suid = from_kuid_munged(cred->user_ns, cred->suid);
- if (!(retval = put_user(ruid, ruidp)) &&
- !(retval = put_user(euid, euidp)))
- retval = put_user(suid, suidp);
- return retval;
- }
- /*
- * Same as above, but for rgid, egid, sgid.
- */
- SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
- {
- struct user_namespace *ns = current_user_ns();
- const struct cred *old;
- struct cred *new;
- int retval;
- kgid_t krgid, kegid, ksgid;
- krgid = make_kgid(ns, rgid);
- kegid = make_kgid(ns, egid);
- ksgid = make_kgid(ns, sgid);
- if ((rgid != (gid_t) -1) && !gid_valid(krgid))
- return -EINVAL;
- if ((egid != (gid_t) -1) && !gid_valid(kegid))
- return -EINVAL;
- if ((sgid != (gid_t) -1) && !gid_valid(ksgid))
- return -EINVAL;
- #if defined CONFIG_SEC_RESTRICT_SETUID
- if(rgid == 0 || egid == 0 || sgid == 0)
- {
- if(sec_restrict_uid())
- return -EACCES;
- }
- #endif // End of CONFIG_SEC_RESTRICT_SETUID
- new = prepare_creds();
- if (!new)
- return -ENOMEM;
- old = current_cred();
- retval = -EPERM;
- if (!nsown_capable(CAP_SETGID)) {
- if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) &&
- !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
- goto error;
- if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) &&
- !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid))
- goto error;
- if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) &&
- !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid))
- goto error;
- }
- if (rgid != (gid_t) -1)
- new->gid = krgid;
- if (egid != (gid_t) -1)
- new->egid = kegid;
- if (sgid != (gid_t) -1)
- new->sgid = ksgid;
- new->fsgid = new->egid;
- return commit_creds(new);
- error:
- abort_creds(new);
- return retval;
- }
- SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp)
- {
- const struct cred *cred = current_cred();
- int retval;
- gid_t rgid, egid, sgid;
- rgid = from_kgid_munged(cred->user_ns, cred->gid);
- egid = from_kgid_munged(cred->user_ns, cred->egid);
- sgid = from_kgid_munged(cred->user_ns, cred->sgid);
- if (!(retval = put_user(rgid, rgidp)) &&
- !(retval = put_user(egid, egidp)))
- retval = put_user(sgid, sgidp);
- return retval;
- }
- /*
- * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This
- * is used for "access()" and for the NFS daemon (letting nfsd stay at
- * whatever uid it wants to). It normally shadows "euid", except when
- * explicitly set by setfsuid() or for access..
- */
- SYSCALL_DEFINE1(setfsuid, uid_t, uid)
- {
- const struct cred *old;
- struct cred *new;
- uid_t old_fsuid;
- kuid_t kuid;
- old = current_cred();
- old_fsuid = from_kuid_munged(old->user_ns, old->fsuid);
- kuid = make_kuid(old->user_ns, uid);
- if (!uid_valid(kuid))
- return old_fsuid;
- new = prepare_creds();
- if (!new)
- return old_fsuid;
- if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) ||
- uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) ||
- nsown_capable(CAP_SETUID)) {
- if (!uid_eq(kuid, old->fsuid)) {
- new->fsuid = kuid;
- if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
- goto change_okay;
- }
- }
- abort_creds(new);
- return old_fsuid;
- change_okay:
- commit_creds(new);
- return old_fsuid;
- }
- /*
- * Samma på svenska..
- */
- SYSCALL_DEFINE1(setfsgid, gid_t, gid)
- {
- const struct cred *old;
- struct cred *new;
- gid_t old_fsgid;
- kgid_t kgid;
- old = current_cred();
- old_fsgid = from_kgid_munged(old->user_ns, old->fsgid);
- kgid = make_kgid(old->user_ns, gid);
- if (!gid_valid(kgid))
- return old_fsgid;
- new = prepare_creds();
- if (!new)
- return old_fsgid;
- if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) ||
- gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
- nsown_capable(CAP_SETGID)) {
- if (!gid_eq(kgid, old->fsgid)) {
- new->fsgid = kgid;
- goto change_okay;
- }
- }
- abort_creds(new);
- return old_fsgid;
- change_okay:
- commit_creds(new);
- return old_fsgid;
- }
- void do_sys_times(struct tms *tms)
- {
- cputime_t tgutime, tgstime, cutime, cstime;
- spin_lock_irq(¤t->sighand->siglock);
- thread_group_cputime_adjusted(current, &tgutime, &tgstime);
- cutime = current->signal->cutime;
- cstime = current->signal->cstime;
- spin_unlock_irq(¤t->sighand->siglock);
- tms->tms_utime = cputime_to_clock_t(tgutime);
- tms->tms_stime = cputime_to_clock_t(tgstime);
- tms->tms_cutime = cputime_to_clock_t(cutime);
- tms->tms_cstime = cputime_to_clock_t(cstime);
- }
- SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
- {
- if (tbuf) {
- struct tms tmp;
- do_sys_times(&tmp);
- if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
- return -EFAULT;
- }
- force_successful_syscall_return();
- return (long) jiffies_64_to_clock_t(get_jiffies_64());
- }
- /*
- * This needs some heavy checking ...
- * I just haven't the stomach for it. I also don't fully
- * understand sessions/pgrp etc. Let somebody who does explain it.
- *
- * OK, I think I have the protection semantics right.... this is really
- * only important on a multi-user system anyway, to make sure one user
- * can't send a signal to a process owned by another. -TYT, 12/12/91
- *
- * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
- * LBT 04.03.94
- */
- SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
- {
- struct task_struct *p;
- struct task_struct *group_leader = current->group_leader;
- struct pid *pgrp;
- int err;
- if (!pid)
- pid = task_pid_vnr(group_leader);
- if (!pgid)
- pgid = pid;
- if (pgid < 0)
- return -EINVAL;
- rcu_read_lock();
- /* From this point forward we keep holding onto the tasklist lock
- * so that our parent does not change from under us. -DaveM
- */
- write_lock_irq(&tasklist_lock);
- err = -ESRCH;
- p = find_task_by_vpid(pid);
- if (!p)
- goto out;
- err = -EINVAL;
- if (!thread_group_leader(p))
- goto out;
- if (same_thread_group(p->real_parent, group_leader)) {
- err = -EPERM;
- if (task_session(p) != task_session(group_leader))
- goto out;
- err = -EACCES;
- if (p->did_exec)
- goto out;
- } else {
- err = -ESRCH;
- if (p != group_leader)
- goto out;
- }
- err = -EPERM;
- if (p->signal->leader)
- goto out;
- pgrp = task_pid(p);
- if (pgid != pid) {
- struct task_struct *g;
- pgrp = find_vpid(pgid);
- g = pid_task(pgrp, PIDTYPE_PGID);
- if (!g || task_session(g) != task_session(group_leader))
- goto out;
- }
- err = security_task_setpgid(p, pgid);
- if (err)
- goto out;
- if (task_pgrp(p) != pgrp)
- change_pid(p, PIDTYPE_PGID, pgrp);
- err = 0;
- out:
- /* All paths lead to here, thus we are safe. -DaveM */
- write_unlock_irq(&tasklist_lock);
- rcu_read_unlock();
- return err;
- }
- SYSCALL_DEFINE1(getpgid, pid_t, pid)
- {
- struct task_struct *p;
- struct pid *grp;
- int retval;
- rcu_read_lock();
- if (!pid)
- grp = task_pgrp(current);
- else {
- retval = -ESRCH;
- p = find_task_by_vpid(pid);
- if (!p)
- goto out;
- grp = task_pgrp(p);
- if (!grp)
- goto out;
- retval = security_task_getpgid(p);
- if (retval)
- goto out;
- }
- retval = pid_vnr(grp);
- out:
- rcu_read_unlock();
- return retval;
- }
- #ifdef __ARCH_WANT_SYS_GETPGRP
- SYSCALL_DEFINE0(getpgrp)
- {
- return sys_getpgid(0);
- }
- #endif
- SYSCALL_DEFINE1(getsid, pid_t, pid)
- {
- struct task_struct *p;
- struct pid *sid;
- int retval;
- rcu_read_lock();
- if (!pid)
- sid = task_session(current);
- else {
- retval = -ESRCH;
- p = find_task_by_vpid(pid);
- if (!p)
- goto out;
- sid = task_session(p);
- if (!sid)
- goto out;
- retval = security_task_getsid(p);
- if (retval)
- goto out;
- }
- retval = pid_vnr(sid);
- out:
- rcu_read_unlock();
- return retval;
- }
- SYSCALL_DEFINE0(setsid)
- {
- struct task_struct *group_leader = current->group_leader;
- struct pid *sid = task_pid(group_leader);
- pid_t session = pid_vnr(sid);
- int err = -EPERM;
- write_lock_irq(&tasklist_lock);
- /* Fail if I am already a session leader */
- if (group_leader->signal->leader)
- goto out;
- /* Fail if a process group id already exists that equals the
- * proposed session id.
- */
- if (pid_task(sid, PIDTYPE_PGID))
- goto out;
- group_leader->signal->leader = 1;
- __set_special_pids(sid);
- proc_clear_tty(group_leader);
- err = session;
- out:
- write_unlock_irq(&tasklist_lock);
- if (err > 0) {
- proc_sid_connector(group_leader);
- sched_autogroup_create_attach(group_leader);
- }
- return err;
- }
- DECLARE_RWSEM(uts_sem);
- #ifdef COMPAT_UTS_MACHINE
- #define override_architecture(name) \
- (personality(current->personality) == PER_LINUX32 && \
- copy_to_user(name->machine, COMPAT_UTS_MACHINE, \
- sizeof(COMPAT_UTS_MACHINE)))
- #else
- #define override_architecture(name) 0
- #endif
- /*
- * Work around broken programs that cannot handle "Linux 3.0".
- * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
- */
- static int override_release(char __user *release, size_t len)
- {
- int ret = 0;
- if (current->personality & UNAME26) {
- const char *rest = UTS_RELEASE;
- char buf[65] = { 0 };
- int ndots = 0;
- unsigned v;
- size_t copy;
- while (*rest) {
- if (*rest == '.' && ++ndots >= 3)
- break;
- if (!isdigit(*rest) && *rest != '.')
- break;
- rest++;
- }
- v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
- copy = clamp_t(size_t, len, 1, sizeof(buf));
- copy = scnprintf(buf, copy, "2.6.%u%s", v, rest);
- ret = copy_to_user(release, buf, copy + 1);
- }
- return ret;
- }
- SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
- {
- int errno = 0;
- down_read(&uts_sem);
- if (copy_to_user(name, utsname(), sizeof *name))
- errno = -EFAULT;
- up_read(&uts_sem);
- if (!errno && override_release(name->release, sizeof(name->release)))
- errno = -EFAULT;
- if (!errno && override_architecture(name))
- errno = -EFAULT;
- return errno;
- }
- #ifdef __ARCH_WANT_SYS_OLD_UNAME
- /*
- * Old cruft
- */
- SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)
- {
- int error = 0;
- if (!name)
- return -EFAULT;
- down_read(&uts_sem);
- if (copy_to_user(name, utsname(), sizeof(*name)))
- error = -EFAULT;
- up_read(&uts_sem);
- if (!error && override_release(name->release, sizeof(name->release)))
- error = -EFAULT;
- if (!error && override_architecture(name))
- error = -EFAULT;
- return error;
- }
- SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name)
- {
- int error;
- if (!name)
- return -EFAULT;
- if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname)))
- return -EFAULT;
- down_read(&uts_sem);
- error = __copy_to_user(&name->sysname, &utsname()->sysname,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->sysname + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->nodename, &utsname()->nodename,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->nodename + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->release, &utsname()->release,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->release + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->version, &utsname()->version,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->version + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->machine, &utsname()->machine,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->machine + __OLD_UTS_LEN);
- up_read(&uts_sem);
- if (!error && override_architecture(name))
- error = -EFAULT;
- if (!error && override_release(name->release, sizeof(name->release)))
- error = -EFAULT;
- return error ? -EFAULT : 0;
- }
- #endif
- SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
- {
- int errno;
- char tmp[__NEW_UTS_LEN];
- if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
- return -EPERM;
- if (len < 0 || len > __NEW_UTS_LEN)
- return -EINVAL;
- down_write(&uts_sem);
- errno = -EFAULT;
- if (!copy_from_user(tmp, name, len)) {
- struct new_utsname *u = utsname();
- memcpy(u->nodename, tmp, len);
- memset(u->nodename + len, 0, sizeof(u->nodename) - len);
- errno = 0;
- uts_proc_notify(UTS_PROC_HOSTNAME);
- }
- up_write(&uts_sem);
- return errno;
- }
- #ifdef __ARCH_WANT_SYS_GETHOSTNAME
- SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
- {
- int i, errno;
- struct new_utsname *u;
- if (len < 0)
- return -EINVAL;
- down_read(&uts_sem);
- u = utsname();
- i = 1 + strlen(u->nodename);
- if (i > len)
- i = len;
- errno = 0;
- if (copy_to_user(name, u->nodename, i))
- errno = -EFAULT;
- up_read(&uts_sem);
- return errno;
- }
- #endif
- /*
- * Only setdomainname; getdomainname can be implemented by calling
- * uname()
- */
- SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
- {
- int errno;
- char tmp[__NEW_UTS_LEN];
- if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
- return -EPERM;
- if (len < 0 || len > __NEW_UTS_LEN)
- return -EINVAL;
- down_write(&uts_sem);
- errno = -EFAULT;
- if (!copy_from_user(tmp, name, len)) {
- struct new_utsname *u = utsname();
- memcpy(u->domainname, tmp, len);
- memset(u->domainname + len, 0, sizeof(u->domainname) - len);
- errno = 0;
- uts_proc_notify(UTS_PROC_DOMAINNAME);
- }
- up_write(&uts_sem);
- return errno;
- }
- SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
- {
- struct rlimit value;
- int ret;
- ret = do_prlimit(current, resource, NULL, &value);
- if (!ret)
- ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
- return ret;
- }
- #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
- /*
- * Back compatibility for getrlimit. Needed for some apps.
- */
-
- SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
- struct rlimit __user *, rlim)
- {
- struct rlimit x;
- if (resource >= RLIM_NLIMITS)
- return -EINVAL;
- resource = array_index_nospec(resource, RLIM_NLIMITS);
- task_lock(current->group_leader);
- x = current->signal->rlim[resource];
- task_unlock(current->group_leader);
- if (x.rlim_cur > 0x7FFFFFFF)
- x.rlim_cur = 0x7FFFFFFF;
- if (x.rlim_max > 0x7FFFFFFF)
- x.rlim_max = 0x7FFFFFFF;
- return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
- }
- #endif
- static inline bool rlim64_is_infinity(__u64 rlim64)
- {
- #if BITS_PER_LONG < 64
- return rlim64 >= ULONG_MAX;
- #else
- return rlim64 == RLIM64_INFINITY;
- #endif
- }
- static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64)
- {
- if (rlim->rlim_cur == RLIM_INFINITY)
- rlim64->rlim_cur = RLIM64_INFINITY;
- else
- rlim64->rlim_cur = rlim->rlim_cur;
- if (rlim->rlim_max == RLIM_INFINITY)
- rlim64->rlim_max = RLIM64_INFINITY;
- else
- rlim64->rlim_max = rlim->rlim_max;
- }
- static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim)
- {
- if (rlim64_is_infinity(rlim64->rlim_cur))
- rlim->rlim_cur = RLIM_INFINITY;
- else
- rlim->rlim_cur = (unsigned long)rlim64->rlim_cur;
- if (rlim64_is_infinity(rlim64->rlim_max))
- rlim->rlim_max = RLIM_INFINITY;
- else
- rlim->rlim_max = (unsigned long)rlim64->rlim_max;
- }
- /* make sure you are allowed to change @tsk limits before calling this */
- int do_prlimit(struct task_struct *tsk, unsigned int resource,
- struct rlimit *new_rlim, struct rlimit *old_rlim)
- {
- struct rlimit *rlim;
- int retval = 0;
- if (resource >= RLIM_NLIMITS)
- return -EINVAL;
- if (new_rlim) {
- if (new_rlim->rlim_cur > new_rlim->rlim_max)
- return -EINVAL;
- if (resource == RLIMIT_NOFILE &&
- new_rlim->rlim_max > sysctl_nr_open)
- return -EPERM;
- }
- /* protect tsk->signal and tsk->sighand from disappearing */
- read_lock(&tasklist_lock);
- if (!tsk->sighand) {
- retval = -ESRCH;
- goto out;
- }
- rlim = tsk->signal->rlim + resource;
- task_lock(tsk->group_leader);
- if (new_rlim) {
- /* Keep the capable check against init_user_ns until
- cgroups can contain all limits */
- if (new_rlim->rlim_max > rlim->rlim_max &&
- !capable(CAP_SYS_RESOURCE))
- retval = -EPERM;
- if (!retval)
- retval = security_task_setrlimit(tsk->group_leader,
- resource, new_rlim);
- if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) {
- /*
- * The caller is asking for an immediate RLIMIT_CPU
- * expiry. But we use the zero value to mean "it was
- * never set". So let's cheat and make it one second
- * instead
- */
- new_rlim->rlim_cur = 1;
- }
- }
- if (!retval) {
- if (old_rlim)
- *old_rlim = *rlim;
- if (new_rlim)
- *rlim = *new_rlim;
- }
- task_unlock(tsk->group_leader);
- /*
- * RLIMIT_CPU handling. Note that the kernel fails to return an error
- * code if it rejected the user's attempt to set RLIMIT_CPU. This is a
- * very long-standing error, and fixing it now risks breakage of
- * applications, so we live with it
- */
- if (!retval && new_rlim && resource == RLIMIT_CPU &&
- new_rlim->rlim_cur != RLIM_INFINITY)
- update_rlimit_cpu(tsk, new_rlim->rlim_cur);
- out:
- read_unlock(&tasklist_lock);
- return retval;
- }
- /* rcu lock must be held */
- static int check_prlimit_permission(struct task_struct *task)
- {
- const struct cred *cred = current_cred(), *tcred;
- if (current == task)
- return 0;
- tcred = __task_cred(task);
- if (uid_eq(cred->uid, tcred->euid) &&
- uid_eq(cred->uid, tcred->suid) &&
- uid_eq(cred->uid, tcred->uid) &&
- gid_eq(cred->gid, tcred->egid) &&
- gid_eq(cred->gid, tcred->sgid) &&
- gid_eq(cred->gid, tcred->gid))
- return 0;
- if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE))
- return 0;
- return -EPERM;
- }
- SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
- const struct rlimit64 __user *, new_rlim,
- struct rlimit64 __user *, old_rlim)
- {
- struct rlimit64 old64, new64;
- struct rlimit old, new;
- struct task_struct *tsk;
- int ret;
- if (new_rlim) {
- if (copy_from_user(&new64, new_rlim, sizeof(new64)))
- return -EFAULT;
- rlim64_to_rlim(&new64, &new);
- }
- rcu_read_lock();
- tsk = pid ? find_task_by_vpid(pid) : current;
- if (!tsk) {
- rcu_read_unlock();
- return -ESRCH;
- }
- ret = check_prlimit_permission(tsk);
- if (ret) {
- rcu_read_unlock();
- return ret;
- }
- get_task_struct(tsk);
- rcu_read_unlock();
- ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL,
- old_rlim ? &old : NULL);
- if (!ret && old_rlim) {
- rlim_to_rlim64(&old, &old64);
- if (copy_to_user(old_rlim, &old64, sizeof(old64)))
- ret = -EFAULT;
- }
- put_task_struct(tsk);
- return ret;
- }
- SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
- {
- struct rlimit new_rlim;
- if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
- return -EFAULT;
- return do_prlimit(current, resource, &new_rlim, NULL);
- }
- /*
- * It would make sense to put struct rusage in the task_struct,
- * except that would make the task_struct be *really big*. After
- * task_struct gets moved into malloc'ed memory, it would
- * make sense to do this. It will make moving the rest of the information
- * a lot simpler! (Which we're not doing right now because we're not
- * measuring them yet).
- *
- * When sampling multiple threads for RUSAGE_SELF, under SMP we might have
- * races with threads incrementing their own counters. But since word
- * reads are atomic, we either get new values or old values and we don't
- * care which for the sums. We always take the siglock to protect reading
- * the c* fields from p->signal from races with exit.c updating those
- * fields when reaping, so a sample either gets all the additions of a
- * given child after it's reaped, or none so this sample is before reaping.
- *
- * Locking:
- * We need to take the siglock for CHILDEREN, SELF and BOTH
- * for the cases current multithreaded, non-current single threaded
- * non-current multithreaded. Thread traversal is now safe with
- * the siglock held.
- * Strictly speaking, we donot need to take the siglock if we are current and
- * single threaded, as no one else can take our signal_struct away, no one
- * else can reap the children to update signal->c* counters, and no one else
- * can race with the signal-> fields. If we do not take any lock, the
- * signal-> fields could be read out of order while another thread was just
- * exiting. So we should place a read memory barrier when we avoid the lock.
- * On the writer side, write memory barrier is implied in __exit_signal
- * as __exit_signal releases the siglock spinlock after updating the signal->
- * fields. But we don't do this yet to keep things simple.
- *
- */
- static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r)
- {
- r->ru_nvcsw += t->nvcsw;
- r->ru_nivcsw += t->nivcsw;
- r->ru_minflt += t->min_flt;
- r->ru_majflt += t->maj_flt;
- r->ru_inblock += task_io_get_inblock(t);
- r->ru_oublock += task_io_get_oublock(t);
- }
- static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
- {
- struct task_struct *t;
- unsigned long flags;
- cputime_t tgutime, tgstime, utime, stime;
- unsigned long maxrss = 0;
- memset((char *) r, 0, sizeof *r);
- utime = stime = 0;
- if (who == RUSAGE_THREAD) {
- task_cputime_adjusted(current, &utime, &stime);
- accumulate_thread_rusage(p, r);
- maxrss = p->signal->maxrss;
- goto out;
- }
- if (!lock_task_sighand(p, &flags))
- return;
- switch (who) {
- case RUSAGE_BOTH:
- case RUSAGE_CHILDREN:
- utime = p->signal->cutime;
- stime = p->signal->cstime;
- r->ru_nvcsw = p->signal->cnvcsw;
- r->ru_nivcsw = p->signal->cnivcsw;
- r->ru_minflt = p->signal->cmin_flt;
- r->ru_majflt = p->signal->cmaj_flt;
- r->ru_inblock = p->signal->cinblock;
- r->ru_oublock = p->signal->coublock;
- maxrss = p->signal->cmaxrss;
- if (who == RUSAGE_CHILDREN)
- break;
- case RUSAGE_SELF:
- thread_group_cputime_adjusted(p, &tgutime, &tgstime);
- utime += tgutime;
- stime += tgstime;
- r->ru_nvcsw += p->signal->nvcsw;
- r->ru_nivcsw += p->signal->nivcsw;
- r->ru_minflt += p->signal->min_flt;
- r->ru_majflt += p->signal->maj_flt;
- r->ru_inblock += p->signal->inblock;
- r->ru_oublock += p->signal->oublock;
- if (maxrss < p->signal->maxrss)
- maxrss = p->signal->maxrss;
- t = p;
- do {
- accumulate_thread_rusage(t, r);
- t = next_thread(t);
- } while (t != p);
- break;
- default:
- BUG();
- }
- unlock_task_sighand(p, &flags);
- out:
- cputime_to_timeval(utime, &r->ru_utime);
- cputime_to_timeval(stime, &r->ru_stime);
- if (who != RUSAGE_CHILDREN) {
- struct mm_struct *mm = get_task_mm(p);
- if (mm) {
- setmax_mm_hiwater_rss(&maxrss, mm);
- mmput(mm);
- }
- }
- r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
- }
- int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
- {
- struct rusage r;
- k_getrusage(p, who, &r);
- return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
- }
- SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
- {
- if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
- who != RUSAGE_THREAD)
- return -EINVAL;
- return getrusage(current, who, ru);
- }
- SYSCALL_DEFINE1(umask, int, mask)
- {
- mask = xchg(¤t->fs->umask, mask & S_IRWXUGO);
- return mask;
- }
- static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
- {
- struct file *exe_file;
- struct dentry *dentry;
- int err, fput_needed;
- exe_file = fget_light(fd, &fput_needed);
- if (!exe_file)
- return -EBADF;
- dentry = exe_file->f_path.dentry;
- /*
- * Because the original mm->exe_file points to executable file, make
- * sure that this one is executable as well, to avoid breaking an
- * overall picture.
- */
- err = -EACCES;
- if (!S_ISREG(dentry->d_inode->i_mode) ||
- exe_file->f_path.mnt->mnt_flags & MNT_NOEXEC)
- goto exit;
- err = inode_permission(dentry->d_inode, MAY_EXEC);
- if (err)
- goto exit;
- down_write(&mm->mmap_sem);
- /*
- * Forbid mm->exe_file change if old file still mapped.
- */
- err = -EBUSY;
- if (mm->exe_file) {
- struct vm_area_struct *vma;
- for (vma = mm->mmap; vma; vma = vma->vm_next)
- if (vma->vm_file &&
- path_equal(&vma->vm_file->f_path,
- &mm->exe_file->f_path))
- goto exit_unlock;
- }
- err = 0;
- set_mm_exe_file(mm, exe_file); /* this grabs a reference to exe_file */
- exit_unlock:
- up_write(&mm->mmap_sem);
- exit:
- fput_light(exe_file, fput_needed);
- return err;
- }
- #ifdef CONFIG_CHECKPOINT_RESTORE
- /*
- * WARNING: we don't require any capability here so be very careful
- * in what is allowed for modification from userspace.
- */
- static int validate_prctl_map(struct prctl_mm_map *prctl_map)
- {
- unsigned long mmap_max_addr = TASK_SIZE;
- struct mm_struct *mm = current->mm;
- int error = -EINVAL, i;
- static const unsigned char offsets[] = {
- offsetof(struct prctl_mm_map, start_code),
- offsetof(struct prctl_mm_map, end_code),
- offsetof(struct prctl_mm_map, start_data),
- offsetof(struct prctl_mm_map, end_data),
- offsetof(struct prctl_mm_map, start_brk),
- offsetof(struct prctl_mm_map, brk),
- offsetof(struct prctl_mm_map, start_stack),
- offsetof(struct prctl_mm_map, arg_start),
- offsetof(struct prctl_mm_map, arg_end),
- offsetof(struct prctl_mm_map, env_start),
- offsetof(struct prctl_mm_map, env_end),
- };
- /*
- * Make sure the members are not somewhere outside
- * of allowed address space.
- */
- for (i = 0; i < ARRAY_SIZE(offsets); i++) {
- u64 val = *(u64 *)((char *)prctl_map + offsets[i]);
- if ((unsigned long)val >= mmap_max_addr ||
- (unsigned long)val < mmap_min_addr)
- goto out;
- }
- /*
- * Make sure the pairs are ordered.
- */
- #define __prctl_check_order(__m1, __op, __m2) \
- ((unsigned long)prctl_map->__m1 __op \
- (unsigned long)prctl_map->__m2) ? 0 : -EINVAL
- error = __prctl_check_order(start_code, <, end_code);
- error |= __prctl_check_order(start_data,<=, end_data);
- error |= __prctl_check_order(start_brk, <=, brk);
- error |= __prctl_check_order(arg_start, <=, arg_end);
- error |= __prctl_check_order(env_start, <=, env_end);
- if (error)
- goto out;
- #undef __prctl_check_order
- error = -EINVAL;
- /*
- * @brk should be after @end_data in traditional maps.
- */
- if (prctl_map->start_brk <= prctl_map->end_data ||
- prctl_map->brk <= prctl_map->end_data)
- goto out;
- /*
- * Neither we should allow to override limits if they set.
- */
- if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk,
- prctl_map->start_brk, prctl_map->end_data,
- prctl_map->start_data))
- goto out;
- /*
- * Someone is trying to cheat the auxv vector.
- */
- if (prctl_map->auxv_size) {
- if (!prctl_map->auxv || prctl_map->auxv_size > sizeof(mm->saved_auxv))
- goto out;
- }
- /*
- * Finally, make sure the caller has the rights to
- * change /proc/pid/exe link: only local sys admin should
- * be allowed to.
- */
- if (prctl_map->exe_fd != (u32)-1) {
- if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
- goto out;
- }
- error = 0;
- out:
- return error;
- }
- static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size)
- {
- struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, };
- unsigned long user_auxv[AT_VECTOR_SIZE];
- struct mm_struct *mm = current->mm;
- int error;
- BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
- BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256);
- if (opt == PR_SET_MM_MAP_SIZE)
- return put_user((unsigned int)sizeof(prctl_map),
- (unsigned int __user *)addr);
- if (data_size != sizeof(prctl_map))
- return -EINVAL;
- if (copy_from_user(&prctl_map, addr, sizeof(prctl_map)))
- return -EFAULT;
- error = validate_prctl_map(&prctl_map);
- if (error)
- return error;
- if (prctl_map.auxv_size) {
- memset(user_auxv, 0, sizeof(user_auxv));
- if (copy_from_user(user_auxv,
- (const void __user *)prctl_map.auxv,
- prctl_map.auxv_size))
- return -EFAULT;
- /* Last entry must be AT_NULL as specification requires */
- user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL;
- user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
- }
- down_write(&mm->mmap_sem);
- if (prctl_map.exe_fd != (u32)-1)
- error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd);
- downgrade_write(&mm->mmap_sem);
- if (error)
- goto out;
- /*
- * We don't validate if these members are pointing to
- * real present VMAs because application may have correspond
- * VMAs already unmapped and kernel uses these members for statistics
- * output in procfs mostly, except
- *
- * - @start_brk/@brk which are used in do_brk but kernel lookups
- * for VMAs when updating these memvers so anything wrong written
- * here cause kernel to swear at userspace program but won't lead
- * to any problem in kernel itself
- */
- mm->start_code = prctl_map.start_code;
- mm->end_code = prctl_map.end_code;
- mm->start_data = prctl_map.start_data;
- mm->end_data = prctl_map.end_data;
- mm->start_brk = prctl_map.start_brk;
- mm->brk = prctl_map.brk;
- mm->start_stack = prctl_map.start_stack;
- mm->arg_start = prctl_map.arg_start;
- mm->arg_end = prctl_map.arg_end;
- mm->env_start = prctl_map.env_start;
- mm->env_end = prctl_map.env_end;
- /*
- * Note this update of @saved_auxv is lockless thus
- * if someone reads this member in procfs while we're
- * updating -- it may get partly updated results. It's
- * known and acceptable trade off: we leave it as is to
- * not introduce additional locks here making the kernel
- * more complex.
- */
- if (prctl_map.auxv_size)
- memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
- error = 0;
- out:
- up_read(&mm->mmap_sem);
- return error;
- }
- #endif /* CONFIG_CHECKPOINT_RESTORE */
- static int prctl_set_mm(int opt, unsigned long addr,
- unsigned long arg4, unsigned long arg5)
- {
- unsigned long rlim = rlimit(RLIMIT_DATA);
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- int error;
- if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV &&
- opt != PR_SET_MM_MAP &&
- opt != PR_SET_MM_MAP_SIZE)))
- return -EINVAL;
- #ifdef CONFIG_CHECKPOINT_RESTORE
- if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE)
- return prctl_set_mm_map(opt, (const void __user *)addr, arg4);
- #endif
- if (!capable(CAP_SYS_RESOURCE))
- return -EPERM;
- if (opt == PR_SET_MM_EXE_FILE)
- return prctl_set_mm_exe_file(mm, (unsigned int)addr);
- if (addr >= TASK_SIZE || addr < mmap_min_addr)
- return -EINVAL;
- error = -EINVAL;
- down_read(&mm->mmap_sem);
- vma = find_vma(mm, addr);
- switch (opt) {
- case PR_SET_MM_START_CODE:
- mm->start_code = addr;
- break;
- case PR_SET_MM_END_CODE:
- mm->end_code = addr;
- break;
- case PR_SET_MM_START_DATA:
- mm->start_data = addr;
- break;
- case PR_SET_MM_END_DATA:
- mm->end_data = addr;
- break;
- case PR_SET_MM_START_BRK:
- if (addr <= mm->end_data)
- goto out;
- if (rlim < RLIM_INFINITY &&
- (mm->brk - addr) +
- (mm->end_data - mm->start_data) > rlim)
- goto out;
- mm->start_brk = addr;
- break;
- case PR_SET_MM_BRK:
- if (addr <= mm->end_data)
- goto out;
- if (rlim < RLIM_INFINITY &&
- (addr - mm->start_brk) +
- (mm->end_data - mm->start_data) > rlim)
- goto out;
- mm->brk = addr;
- break;
- /*
- * If command line arguments and environment
- * are placed somewhere else on stack, we can
- * set them up here, ARG_START/END to setup
- * command line argumets and ENV_START/END
- * for environment.
- */
- case PR_SET_MM_START_STACK:
- case PR_SET_MM_ARG_START:
- case PR_SET_MM_ARG_END:
- case PR_SET_MM_ENV_START:
- case PR_SET_MM_ENV_END:
- if (!vma) {
- error = -EFAULT;
- goto out;
- }
- if (opt == PR_SET_MM_START_STACK)
- mm->start_stack = addr;
- else if (opt == PR_SET_MM_ARG_START)
- mm->arg_start = addr;
- else if (opt == PR_SET_MM_ARG_END)
- mm->arg_end = addr;
- else if (opt == PR_SET_MM_ENV_START)
- mm->env_start = addr;
- else if (opt == PR_SET_MM_ENV_END)
- mm->env_end = addr;
- break;
- /*
- * This doesn't move auxiliary vector itself
- * since it's pinned to mm_struct, but allow
- * to fill vector with new values. It's up
- * to a caller to provide sane values here
- * otherwise user space tools which use this
- * vector might be unhappy.
- */
- case PR_SET_MM_AUXV: {
- unsigned long user_auxv[AT_VECTOR_SIZE];
- if (arg4 > sizeof(user_auxv))
- goto out;
- up_read(&mm->mmap_sem);
- if (copy_from_user(user_auxv, (const void __user *)addr, arg4))
- return -EFAULT;
- /* Make sure the last entry is always AT_NULL */
- user_auxv[AT_VECTOR_SIZE - 2] = 0;
- user_auxv[AT_VECTOR_SIZE - 1] = 0;
- BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
- task_lock(current);
- memcpy(mm->saved_auxv, user_auxv, arg4);
- task_unlock(current);
- return 0;
- }
- default:
- goto out;
- }
- error = 0;
- out:
- up_read(&mm->mmap_sem);
- return error;
- }
- #ifdef CONFIG_CHECKPOINT_RESTORE
- static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
- {
- return put_user(me->clear_child_tid, tid_addr);
- }
- #else
- static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
- {
- return -EINVAL;
- }
- #endif
- static int prctl_update_vma_anon_name(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
- unsigned long start, unsigned long end,
- const char __user *name_addr)
- {
- struct mm_struct * mm = vma->vm_mm;
- int error = 0;
- pgoff_t pgoff;
- if (name_addr == vma_get_anon_name(vma)) {
- *prev = vma;
- goto out;
- }
- pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
- *prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma,
- vma->vm_file, pgoff, vma_policy(vma),
- name_addr);
- if (*prev) {
- vma = *prev;
- goto success;
- }
- *prev = vma;
- if (start != vma->vm_start) {
- error = split_vma(mm, vma, start, 1);
- if (error)
- goto out;
- }
- if (end != vma->vm_end) {
- error = split_vma(mm, vma, end, 0);
- if (error)
- goto out;
- }
- success:
- if (!vma->vm_file)
- vma->shared.anon_name = name_addr;
- out:
- if (error == -ENOMEM)
- error = -EAGAIN;
- return error;
- }
- static int prctl_set_vma_anon_name(unsigned long start, unsigned long end,
- unsigned long arg)
- {
- unsigned long tmp;
- struct vm_area_struct * vma, *prev;
- int unmapped_error = 0;
- int error = -EINVAL;
- /*
- * If the interval [start,end) covers some unmapped address
- * ranges, just ignore them, but return -ENOMEM at the end.
- * - this matches the handling in madvise.
- */
- vma = find_vma_prev(current->mm, start, &prev);
- if (vma && start > vma->vm_start)
- prev = vma;
- for (;;) {
- /* Still start < end. */
- error = -ENOMEM;
- if (!vma)
- return error;
- /* Here start < (end|vma->vm_end). */
- if (start < vma->vm_start) {
- unmapped_error = -ENOMEM;
- start = vma->vm_start;
- if (start >= end)
- return error;
- }
- /* Here vma->vm_start <= start < (end|vma->vm_end) */
- tmp = vma->vm_end;
- if (end < tmp)
- tmp = end;
- /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
- error = prctl_update_vma_anon_name(vma, &prev, start, tmp,
- (const char __user *)arg);
- if (error)
- return error;
- start = tmp;
- if (prev && start < prev->vm_end)
- start = prev->vm_end;
- error = unmapped_error;
- if (start >= end)
- return error;
- if (prev)
- vma = prev->vm_next;
- else /* madvise_remove dropped mmap_sem */
- vma = find_vma(current->mm, start);
- }
- }
- static int prctl_set_vma(unsigned long opt, unsigned long start,
- unsigned long len_in, unsigned long arg)
- {
- struct mm_struct *mm = current->mm;
- int error;
- unsigned long len;
- unsigned long end;
- if (start & ~PAGE_MASK)
- return -EINVAL;
- len = (len_in + ~PAGE_MASK) & PAGE_MASK;
- /* Check to see whether len was rounded up from small -ve to zero */
- if (len_in && !len)
- return -EINVAL;
- end = start + len;
- if (end < start)
- return -EINVAL;
- if (end == start)
- return 0;
- down_write(&mm->mmap_sem);
- switch (opt) {
- case PR_SET_VMA_ANON_NAME:
- error = prctl_set_vma_anon_name(start, end, arg);
- break;
- default:
- error = -EINVAL;
- }
- up_write(&mm->mmap_sem);
- return error;
- }
- SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
- unsigned long, arg4, unsigned long, arg5)
- {
- struct task_struct *me = current;
- #ifndef CONFIG_SEC_H_PROJECT
- struct task_struct *tsk;
- #endif
- unsigned char comm[sizeof(me->comm)];
- long error;
- error = security_task_prctl(option, arg2, arg3, arg4, arg5);
- if (error != -ENOSYS)
- return error;
- error = 0;
- switch (option) {
- case PR_SET_PDEATHSIG:
- if (!valid_signal(arg2)) {
- error = -EINVAL;
- break;
- }
- me->pdeath_signal = arg2;
- break;
- case PR_GET_PDEATHSIG:
- error = put_user(me->pdeath_signal, (int __user *)arg2);
- break;
- case PR_GET_DUMPABLE:
- error = get_dumpable(me->mm);
- break;
- case PR_SET_DUMPABLE:
- if (arg2 != SUID_DUMP_DISABLE &&
- arg2 != SUID_DUMP_USER) {
- error = -EINVAL;
- break;
- }
- set_dumpable(me->mm, arg2);
- break;
- case PR_SET_UNALIGN:
- error = SET_UNALIGN_CTL(me, arg2);
- break;
- case PR_GET_UNALIGN:
- error = GET_UNALIGN_CTL(me, arg2);
- break;
- case PR_SET_FPEMU:
- error = SET_FPEMU_CTL(me, arg2);
- break;
- case PR_GET_FPEMU:
- error = GET_FPEMU_CTL(me, arg2);
- break;
- case PR_SET_FPEXC:
- error = SET_FPEXC_CTL(me, arg2);
- break;
- case PR_GET_FPEXC:
- error = GET_FPEXC_CTL(me, arg2);
- break;
- case PR_GET_TIMING:
- error = PR_TIMING_STATISTICAL;
- break;
- case PR_SET_TIMING:
- if (arg2 != PR_TIMING_STATISTICAL)
- error = -EINVAL;
- break;
- case PR_SET_NAME:
- comm[sizeof(me->comm)-1] = 0;
- if (strncpy_from_user(comm, (char __user *)arg2,
- sizeof(me->comm) - 1) < 0)
- return -EFAULT;
- set_task_comm(me, comm);
- proc_comm_connector(me);
- break;
- case PR_GET_NAME:
- get_task_comm(comm, me);
- if (copy_to_user((char __user *)arg2, comm,
- sizeof(comm)))
- return -EFAULT;
- break;
- case PR_GET_ENDIAN:
- error = GET_ENDIAN(me, arg2);
- break;
- case PR_SET_ENDIAN:
- error = SET_ENDIAN(me, arg2);
- break;
- case PR_GET_SECCOMP:
- error = prctl_get_seccomp();
- break;
- case PR_SET_SECCOMP:
- error = prctl_set_seccomp(arg2, (char __user *)arg3);
- break;
- case PR_GET_TSC:
- error = GET_TSC_CTL(arg2);
- break;
- case PR_SET_TSC:
- error = SET_TSC_CTL(arg2);
- break;
- case PR_TASK_PERF_EVENTS_DISABLE:
- error = perf_event_task_disable();
- break;
- case PR_TASK_PERF_EVENTS_ENABLE:
- error = perf_event_task_enable();
- break;
- case PR_GET_TIMERSLACK:
- error = current->timer_slack_ns;
- break;
- case PR_SET_TIMERSLACK:
- if (arg2 <= 0)
- current->timer_slack_ns =
- current->default_timer_slack_ns;
- else
- current->timer_slack_ns = arg2;
- break;
- case PR_MCE_KILL:
- if (arg4 | arg5)
- return -EINVAL;
- switch (arg2) {
- case PR_MCE_KILL_CLEAR:
- if (arg3 != 0)
- return -EINVAL;
- current->flags &= ~PF_MCE_PROCESS;
- break;
- case PR_MCE_KILL_SET:
- current->flags |= PF_MCE_PROCESS;
- if (arg3 == PR_MCE_KILL_EARLY)
- current->flags |= PF_MCE_EARLY;
- else if (arg3 == PR_MCE_KILL_LATE)
- current->flags &= ~PF_MCE_EARLY;
- else if (arg3 == PR_MCE_KILL_DEFAULT)
- current->flags &=
- ~(PF_MCE_EARLY|PF_MCE_PROCESS);
- else
- return -EINVAL;
- break;
- default:
- return -EINVAL;
- }
- break;
- case PR_MCE_KILL_GET:
- if (arg2 | arg3 | arg4 | arg5)
- return -EINVAL;
- if (current->flags & PF_MCE_PROCESS)
- error = (current->flags & PF_MCE_EARLY) ?
- PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE;
- else
- error = PR_MCE_KILL_DEFAULT;
- break;
- case PR_SET_MM:
- error = prctl_set_mm(arg2, arg3, arg4, arg5);
- break;
- case PR_GET_TID_ADDRESS:
- error = prctl_get_tid_address(me, (int __user **)arg2);
- break;
- case PR_SET_CHILD_SUBREAPER:
- me->signal->is_child_subreaper = !!arg2;
- break;
- case PR_GET_CHILD_SUBREAPER:
- error = put_user(me->signal->is_child_subreaper,
- (int __user *) arg2);
- break;
- case PR_SET_VMA:
- error = prctl_set_vma(arg2, arg3, arg4, arg5);
- break;
- /* remove this case because of sidesync call mute for H-projects */
- #ifndef CONFIG_SEC_H_PROJECT
- case PR_SET_TIMERSLACK_PID:
- if (task_pid_vnr(current) != (pid_t)arg3 &&
- !capable(CAP_SYS_NICE))
- return -EPERM;
- rcu_read_lock();
- tsk = find_task_by_vpid((pid_t)arg3);
- if (tsk == NULL) {
- rcu_read_unlock();
- return -EINVAL;
- }
- get_task_struct(tsk);
- rcu_read_unlock();
- if (arg2 <= 0)
- tsk->timer_slack_ns =
- tsk->default_timer_slack_ns;
- else
- tsk->timer_slack_ns = arg2;
- put_task_struct(tsk);
- error = 0;
- break;
- #endif
- case PR_SET_NO_NEW_PRIVS:
- if (arg2 != 1 || arg3 || arg4 || arg5)
- return -EINVAL;
- task_set_no_new_privs(current);
- break;
- case PR_GET_NO_NEW_PRIVS:
- if (arg2 || arg3 || arg4 || arg5)
- return -EINVAL;
- return task_no_new_privs(current) ? 1 : 0;
- default:
- error = -EINVAL;
- break;
- }
- return error;
- }
- SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
- struct getcpu_cache __user *, unused)
- {
- int err = 0;
- int cpu = raw_smp_processor_id();
- if (cpup)
- err |= put_user(cpu, cpup);
- if (nodep)
- err |= put_user(cpu_to_node(cpu), nodep);
- return err ? -EFAULT : 0;
- }
- char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
- static int __orderly_poweroff(bool force)
- {
- char **argv;
- static char *envp[] = {
- "HOME=/",
- "PATH=/sbin:/bin:/usr/sbin:/usr/bin",
- NULL
- };
- int ret;
- argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
- if (argv) {
- ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
- argv_free(argv);
- } else {
- printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
- __func__, poweroff_cmd);
- ret = -ENOMEM;
- }
- if (ret && force) {
- printk(KERN_WARNING "Failed to start orderly shutdown: "
- "forcing the issue\n");
- /*
- * I guess this should try to kick off some daemon to sync and
- * poweroff asap. Or not even bother syncing if we're doing an
- * emergency shutdown?
- */
- emergency_sync();
- kernel_power_off();
- }
- return ret;
- }
- static bool poweroff_force;
- static void poweroff_work_func(struct work_struct *work)
- {
- __orderly_poweroff(poweroff_force);
- }
- static DECLARE_WORK(poweroff_work, poweroff_work_func);
- /**
- * orderly_poweroff - Trigger an orderly system poweroff
- * @force: force poweroff if command execution fails
- *
- * This may be called from any context to trigger a system shutdown.
- * If the orderly shutdown fails, it will force an immediate shutdown.
- */
- int orderly_poweroff(bool force)
- {
- if (force) /* do not override the pending "true" */
- poweroff_force = true;
- schedule_work(&poweroff_work);
- return 0;
- }
- EXPORT_SYMBOL_GPL(orderly_poweroff);
|