Skip to content
Snippets Groups Projects
sem.c 56.3 KiB
Newer Older
  • Learn to ignore specific revisions
  • Kenneth Johansson's avatar
    Kenneth Johansson committed
    1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000
    /*
     * linux/ipc/sem.c
     * Copyright (C) 1992 Krishna Balasubramanian
     * Copyright (C) 1995 Eric Schenk, Bruno Haible
     *
     * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
     *
     * SMP-threaded, sysctl's added
     * (c) 1999 Manfred Spraul <manfred@colorfullife.com>
     * Enforced range limit on SEM_UNDO
     * (c) 2001 Red Hat Inc
     * Lockless wakeup
     * (c) 2003 Manfred Spraul <manfred@colorfullife.com>
     * Further wakeup optimizations, documentation
     * (c) 2010 Manfred Spraul <manfred@colorfullife.com>
     *
     * support for audit of ipc object properties and permission changes
     * Dustin Kirkland <dustin.kirkland@us.ibm.com>
     *
     * namespaces support
     * OpenVZ, SWsoft Inc.
     * Pavel Emelianov <xemul@openvz.org>
     *
     * Implementation notes: (May 2010)
     * This file implements System V semaphores.
     *
     * User space visible behavior:
     * - FIFO ordering for semop() operations (just FIFO, not starvation
     *   protection)
     * - multiple semaphore operations that alter the same semaphore in
     *   one semop() are handled.
     * - sem_ctime (time of last semctl()) is updated in the IPC_SET, SETVAL and
     *   SETALL calls.
     * - two Linux specific semctl() commands: SEM_STAT, SEM_INFO.
     * - undo adjustments at process exit are limited to 0..SEMVMX.
     * - namespace are supported.
     * - SEMMSL, SEMMNS, SEMOPM and SEMMNI can be configured at runtine by writing
     *   to /proc/sys/kernel/sem.
     * - statistics about the usage are reported in /proc/sysvipc/sem.
     *
     * Internals:
     * - scalability:
     *   - all global variables are read-mostly.
     *   - semop() calls and semctl(RMID) are synchronized by RCU.
     *   - most operations do write operations (actually: spin_lock calls) to
     *     the per-semaphore array structure.
     *   Thus: Perfect SMP scaling between independent semaphore arrays.
     *         If multiple semaphores in one array are used, then cache line
     *         trashing on the semaphore array spinlock will limit the scaling.
     * - semncnt and semzcnt are calculated on demand in count_semcnt()
     * - the task that performs a successful semop() scans the list of all
     *   sleeping tasks and completes any pending operations that can be fulfilled.
     *   Semaphores are actively given to waiting tasks (necessary for FIFO).
     *   (see update_queue())
     * - To improve the scalability, the actual wake-up calls are performed after
     *   dropping all locks. (see wake_up_sem_queue_prepare(),
     *   wake_up_sem_queue_do())
     * - All work is done by the waker, the woken up task does not have to do
     *   anything - not even acquiring a lock or dropping a refcount.
     * - A woken up task may not even touch the semaphore array anymore, it may
     *   have been destroyed already by a semctl(RMID).
     * - The synchronizations between wake-ups due to a timeout/signal and a
     *   wake-up due to a completed semaphore operation is achieved by using an
     *   intermediate state (IN_WAKEUP).
     * - UNDO values are stored in an array (one per process and per
     *   semaphore array, lazily allocated). For backwards compatibility, multiple
     *   modes for the UNDO variables are supported (per process, per thread)
     *   (see copy_semundo, CLONE_SYSVSEM)
     * - There are two lists of the pending operations: a per-array list
     *   and per-semaphore list (stored in the array). This allows to achieve FIFO
     *   ordering without always scanning all pending operations.
     *   The worst-case behavior is nevertheless O(N^2) for N wakeups.
     */
    
    #include <linux/slab.h>
    #include <linux/spinlock.h>
    #include <linux/init.h>
    #include <linux/proc_fs.h>
    #include <linux/time.h>
    #include <linux/security.h>
    #include <linux/syscalls.h>
    #include <linux/audit.h>
    #include <linux/capability.h>
    #include <linux/seq_file.h>
    #include <linux/rwsem.h>
    #include <linux/nsproxy.h>
    #include <linux/ipc_namespace.h>
    
    #include <linux/uaccess.h>
    #include "util.h"
    
    /* One semaphore structure for each semaphore in the system. */
    struct sem {
    	int	semval;		/* current value */
    	/*
    	 * PID of the process that last modified the semaphore. For
    	 * Linux, specifically these are:
    	 *  - semop
    	 *  - semctl, via SETVAL and SETALL.
    	 *  - at task exit when performing undo adjustments (see exit_sem).
    	 */
    	int	sempid;
    	spinlock_t	lock;	/* spinlock for fine-grained semtimedop */
    	struct list_head pending_alter; /* pending single-sop operations */
    					/* that alter the semaphore */
    	struct list_head pending_const; /* pending single-sop operations */
    					/* that do not alter the semaphore*/
    	time_t	sem_otime;	/* candidate for sem_otime */
    } ____cacheline_aligned_in_smp;
    
    /* One queue for each sleeping process in the system. */
    struct sem_queue {
    	struct list_head	list;	 /* queue of pending operations */
    	struct task_struct	*sleeper; /* this process */
    	struct sem_undo		*undo;	 /* undo structure */
    	int			pid;	 /* process id of requesting process */
    	int			status;	 /* completion status of operation */
    	struct sembuf		*sops;	 /* array of pending operations */
    	struct sembuf		*blocking; /* the operation that blocked */
    	int			nsops;	 /* number of operations */
    	int			alter;	 /* does *sops alter the array? */
    };
    
    /* Each task has a list of undo requests. They are executed automatically
     * when the process exits.
     */
    struct sem_undo {
    	struct list_head	list_proc;	/* per-process list: *
    						 * all undos from one process
    						 * rcu protected */
    	struct rcu_head		rcu;		/* rcu struct for sem_undo */
    	struct sem_undo_list	*ulp;		/* back ptr to sem_undo_list */
    	struct list_head	list_id;	/* per semaphore array list:
    						 * all undos for one array */
    	int			semid;		/* semaphore set identifier */
    	short			*semadj;	/* array of adjustments */
    						/* one per semaphore */
    };
    
    /* sem_undo_list controls shared access to the list of sem_undo structures
     * that may be shared among all a CLONE_SYSVSEM task group.
     */
    struct sem_undo_list {
    	atomic_t		refcnt;
    	spinlock_t		lock;
    	struct list_head	list_proc;
    };
    
    
    #define sem_ids(ns)	((ns)->ids[IPC_SEM_IDS])
    
    #define sem_checkid(sma, semid)	ipc_checkid(&sma->sem_perm, semid)
    
    static int newary(struct ipc_namespace *, struct ipc_params *);
    static void freeary(struct ipc_namespace *, struct kern_ipc_perm *);
    #ifdef CONFIG_PROC_FS
    static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
    #endif
    
    #define SEMMSL_FAST	256 /* 512 bytes on stack */
    #define SEMOPM_FAST	64  /* ~ 372 bytes on stack */
    
    /*
     * Locking:
     * a) global sem_lock() for read/write
     *	sem_undo.id_next,
     *	sem_array.complex_count,
     *	sem_array.complex_mode
     *	sem_array.pending{_alter,_const},
     *	sem_array.sem_undo
     *
     * b) global or semaphore sem_lock() for read/write:
     *	sem_array.sem_base[i].pending_{const,alter}:
     *	sem_array.complex_mode (for read)
     *
     * c) special:
     *	sem_undo_list.list_proc:
     *	* undo_list->lock for write
     *	* rcu for read
     */
    
    #define sc_semmsl	sem_ctls[0]
    #define sc_semmns	sem_ctls[1]
    #define sc_semopm	sem_ctls[2]
    #define sc_semmni	sem_ctls[3]
    
    void sem_init_ns(struct ipc_namespace *ns)
    {
    	ns->sc_semmsl = SEMMSL;
    	ns->sc_semmns = SEMMNS;
    	ns->sc_semopm = SEMOPM;
    	ns->sc_semmni = SEMMNI;
    	ns->used_sems = 0;
    	ipc_init_ids(&ns->ids[IPC_SEM_IDS]);
    }
    
    #ifdef CONFIG_IPC_NS
    void sem_exit_ns(struct ipc_namespace *ns)
    {
    	free_ipcs(ns, &sem_ids(ns), freeary);
    	idr_destroy(&ns->ids[IPC_SEM_IDS].ipcs_idr);
    }
    #endif
    
    void __init sem_init(void)
    {
    	sem_init_ns(&init_ipc_ns);
    	ipc_init_proc_interface("sysvipc/sem",
    				"       key      semid perms      nsems   uid   gid  cuid  cgid      otime      ctime\n",
    				IPC_SEM_IDS, sysvipc_sem_proc_show);
    }
    
    /**
     * unmerge_queues - unmerge queues, if possible.
     * @sma: semaphore array
     *
     * The function unmerges the wait queues if complex_count is 0.
     * It must be called prior to dropping the global semaphore array lock.
     */
    static void unmerge_queues(struct sem_array *sma)
    {
    	struct sem_queue *q, *tq;
    
    	/* complex operations still around? */
    	if (sma->complex_count)
    		return;
    	/*
    	 * We will switch back to simple mode.
    	 * Move all pending operation back into the per-semaphore
    	 * queues.
    	 */
    	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
    		struct sem *curr;
    		curr = &sma->sem_base[q->sops[0].sem_num];
    
    		list_add_tail(&q->list, &curr->pending_alter);
    	}
    	INIT_LIST_HEAD(&sma->pending_alter);
    }
    
    /**
     * merge_queues - merge single semop queues into global queue
     * @sma: semaphore array
     *
     * This function merges all per-semaphore queues into the global queue.
     * It is necessary to achieve FIFO ordering for the pending single-sop
     * operations when a multi-semop operation must sleep.
     * Only the alter operations must be moved, the const operations can stay.
     */
    static void merge_queues(struct sem_array *sma)
    {
    	int i;
    	for (i = 0; i < sma->sem_nsems; i++) {
    		struct sem *sem = sma->sem_base + i;
    
    		list_splice_init(&sem->pending_alter, &sma->pending_alter);
    	}
    }
    
    static void sem_rcu_free(struct rcu_head *head)
    {
    	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
    	struct sem_array *sma = ipc_rcu_to_struct(p);
    
    	security_sem_free(sma);
    	ipc_rcu_free(head);
    }
    
    /*
     * Enter the mode suitable for non-simple operations:
     * Caller must own sem_perm.lock.
     */
    static void complexmode_enter(struct sem_array *sma)
    {
    	int i;
    	struct sem *sem;
    
    	if (sma->complex_mode)  {
    		/* We are already in complex_mode. Nothing to do */
    		return;
    	}
    
    	/* We need a full barrier after seting complex_mode:
    	 * The write to complex_mode must be visible
    	 * before we read the first sem->lock spinlock state.
    	 */
    	smp_store_mb(sma->complex_mode, true);
    
    	for (i = 0; i < sma->sem_nsems; i++) {
    		sem = sma->sem_base + i;
    		spin_unlock_wait(&sem->lock);
    	}
    	/*
    	 * spin_unlock_wait() is not a memory barriers, it is only a
    	 * control barrier. The code must pair with spin_unlock(&sem->lock),
    	 * thus just the control barrier is insufficient.
    	 *
    	 * smp_rmb() is sufficient, as writes cannot pass the control barrier.
    	 */
    	smp_rmb();
    }
    
    /*
     * Try to leave the mode that disallows simple operations:
     * Caller must own sem_perm.lock.
     */
    static void complexmode_tryleave(struct sem_array *sma)
    {
    	if (sma->complex_count)  {
    		/* Complex ops are sleeping.
    		 * We must stay in complex mode
    		 */
    		return;
    	}
    	/*
    	 * Immediately after setting complex_mode to false,
    	 * a simple op can start. Thus: all memory writes
    	 * performed by the current operation must be visible
    	 * before we set complex_mode to false.
    	 */
    	smp_store_release(&sma->complex_mode, false);
    }
    
    #define SEM_GLOBAL_LOCK	(-1)
    /*
     * If the request contains only one semaphore operation, and there are
     * no complex transactions pending, lock only the semaphore involved.
     * Otherwise, lock the entire semaphore array, since we either have
     * multiple semaphores in our own semops, or we need to look at
     * semaphores from other pending complex operations.
     */
    static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
    			      int nsops)
    {
    	struct sem *sem;
    
    	if (nsops != 1) {
    		/* Complex operation - acquire a full lock */
    		ipc_lock_object(&sma->sem_perm);
    
    		/* Prevent parallel simple ops */
    		complexmode_enter(sma);
    		return SEM_GLOBAL_LOCK;
    	}
    
    	/*
    	 * Only one semaphore affected - try to optimize locking.
    	 * Optimized locking is possible if no complex operation
    	 * is either enqueued or processed right now.
    	 *
    	 * Both facts are tracked by complex_mode.
    	 */
    	sem = sma->sem_base + sops->sem_num;
    
    	/*
    	 * Initial check for complex_mode. Just an optimization,
    	 * no locking, no memory barrier.
    	 */
    	if (!sma->complex_mode) {
    		/*
    		 * It appears that no complex operation is around.
    		 * Acquire the per-semaphore lock.
    		 */
    		spin_lock(&sem->lock);
    
    		/*
    		 * See 51d7d5205d33
    		 * ("powerpc: Add smp_mb() to arch_spin_is_locked()"):
    		 * A full barrier is required: the write of sem->lock
    		 * must be visible before the read is executed
    		 */
    		smp_mb();
    
    		if (!smp_load_acquire(&sma->complex_mode)) {
    			/* fast path successful! */
    			return sops->sem_num;
    		}
    		spin_unlock(&sem->lock);
    	}
    
    	/* slow path: acquire the full lock */
    	ipc_lock_object(&sma->sem_perm);
    
    	if (sma->complex_count == 0) {
    		/* False alarm:
    		 * There is no complex operation, thus we can switch
    		 * back to the fast path.
    		 */
    		spin_lock(&sem->lock);
    		ipc_unlock_object(&sma->sem_perm);
    		return sops->sem_num;
    	} else {
    		/* Not a false alarm, thus complete the sequence for a
    		 * full lock.
    		 */
    		complexmode_enter(sma);
    		return SEM_GLOBAL_LOCK;
    	}
    }
    
    static inline void sem_unlock(struct sem_array *sma, int locknum)
    {
    	if (locknum == SEM_GLOBAL_LOCK) {
    		unmerge_queues(sma);
    		complexmode_tryleave(sma);
    		ipc_unlock_object(&sma->sem_perm);
    	} else {
    		struct sem *sem = sma->sem_base + locknum;
    		spin_unlock(&sem->lock);
    	}
    }
    
    /*
     * sem_lock_(check_) routines are called in the paths where the rwsem
     * is not held.
     *
     * The caller holds the RCU read lock.
     */
    static inline struct sem_array *sem_obtain_lock(struct ipc_namespace *ns,
    			int id, struct sembuf *sops, int nsops, int *locknum)
    {
    	struct kern_ipc_perm *ipcp;
    	struct sem_array *sma;
    
    	ipcp = ipc_obtain_object_idr(&sem_ids(ns), id);
    	if (IS_ERR(ipcp))
    		return ERR_CAST(ipcp);
    
    	sma = container_of(ipcp, struct sem_array, sem_perm);
    	*locknum = sem_lock(sma, sops, nsops);
    
    	/* ipc_rmid() may have already freed the ID while sem_lock
    	 * was spinning: verify that the structure is still valid
    	 */
    	if (ipc_valid_object(ipcp))
    		return container_of(ipcp, struct sem_array, sem_perm);
    
    	sem_unlock(sma, *locknum);
    	return ERR_PTR(-EINVAL);
    }
    
    static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id)
    {
    	struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id);
    
    	if (IS_ERR(ipcp))
    		return ERR_CAST(ipcp);
    
    	return container_of(ipcp, struct sem_array, sem_perm);
    }
    
    static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns,
    							int id)
    {
    	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&sem_ids(ns), id);
    
    	if (IS_ERR(ipcp))
    		return ERR_CAST(ipcp);
    
    	return container_of(ipcp, struct sem_array, sem_perm);
    }
    
    static inline void sem_lock_and_putref(struct sem_array *sma)
    {
    	sem_lock(sma, NULL, -1);
    	ipc_rcu_putref(sma, sem_rcu_free);
    }
    
    static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
    {
    	ipc_rmid(&sem_ids(ns), &s->sem_perm);
    }
    
    /*
     * Lockless wakeup algorithm:
     * Without the check/retry algorithm a lockless wakeup is possible:
     * - queue.status is initialized to -EINTR before blocking.
     * - wakeup is performed by
     *	* unlinking the queue entry from the pending list
     *	* setting queue.status to IN_WAKEUP
     *	  This is the notification for the blocked thread that a
     *	  result value is imminent.
     *	* call wake_up_process
     *	* set queue.status to the final value.
     * - the previously blocked thread checks queue.status:
     *	* if it's IN_WAKEUP, then it must wait until the value changes
     *	* if it's not -EINTR, then the operation was completed by
     *	  update_queue. semtimedop can return queue.status without
     *	  performing any operation on the sem array.
     *	* otherwise it must acquire the spinlock and check what's up.
     *
     * The two-stage algorithm is necessary to protect against the following
     * races:
     * - if queue.status is set after wake_up_process, then the woken up idle
     *   thread could race forward and try (and fail) to acquire sma->lock
     *   before update_queue had a chance to set queue.status
     * - if queue.status is written before wake_up_process and if the
     *   blocked process is woken up by a signal between writing
     *   queue.status and the wake_up_process, then the woken up
     *   process could return from semtimedop and die by calling
     *   sys_exit before wake_up_process is called. Then wake_up_process
     *   will oops, because the task structure is already invalid.
     *   (yes, this happened on s390 with sysv msg).
     *
     */
    #define IN_WAKEUP	1
    
    /**
     * newary - Create a new semaphore set
     * @ns: namespace
     * @params: ptr to the structure that contains key, semflg and nsems
     *
     * Called with sem_ids.rwsem held (as a writer)
     */
    static int newary(struct ipc_namespace *ns, struct ipc_params *params)
    {
    	int id;
    	int retval;
    	struct sem_array *sma;
    	int size;
    	key_t key = params->key;
    	int nsems = params->u.nsems;
    	int semflg = params->flg;
    	int i;
    
    	if (!nsems)
    		return -EINVAL;
    	if (ns->used_sems + nsems > ns->sc_semmns)
    		return -ENOSPC;
    
    	size = sizeof(*sma) + nsems * sizeof(struct sem);
    	sma = ipc_rcu_alloc(size);
    	if (!sma)
    		return -ENOMEM;
    
    	memset(sma, 0, size);
    
    	sma->sem_perm.mode = (semflg & S_IRWXUGO);
    	sma->sem_perm.key = key;
    
    	sma->sem_perm.security = NULL;
    	retval = security_sem_alloc(sma);
    	if (retval) {
    		ipc_rcu_putref(sma, ipc_rcu_free);
    		return retval;
    	}
    
    	sma->sem_base = (struct sem *) &sma[1];
    
    	for (i = 0; i < nsems; i++) {
    		INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
    		INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
    		spin_lock_init(&sma->sem_base[i].lock);
    	}
    
    	sma->complex_count = 0;
    	sma->complex_mode = true; /* dropped by sem_unlock below */
    	INIT_LIST_HEAD(&sma->pending_alter);
    	INIT_LIST_HEAD(&sma->pending_const);
    	INIT_LIST_HEAD(&sma->list_id);
    	sma->sem_nsems = nsems;
    	sma->sem_ctime = get_seconds();
    
    	id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
    	if (id < 0) {
    		ipc_rcu_putref(sma, sem_rcu_free);
    		return id;
    	}
    	ns->used_sems += nsems;
    
    	sem_unlock(sma, -1);
    	rcu_read_unlock();
    
    	return sma->sem_perm.id;
    }
    
    
    /*
     * Called with sem_ids.rwsem and ipcp locked.
     */
    static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
    {
    	struct sem_array *sma;
    
    	sma = container_of(ipcp, struct sem_array, sem_perm);
    	return security_sem_associate(sma, semflg);
    }
    
    /*
     * Called with sem_ids.rwsem and ipcp locked.
     */
    static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
    				struct ipc_params *params)
    {
    	struct sem_array *sma;
    
    	sma = container_of(ipcp, struct sem_array, sem_perm);
    	if (params->u.nsems > sma->sem_nsems)
    		return -EINVAL;
    
    	return 0;
    }
    
    SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
    {
    	struct ipc_namespace *ns;
    	static const struct ipc_ops sem_ops = {
    		.getnew = newary,
    		.associate = sem_security,
    		.more_checks = sem_more_checks,
    	};
    	struct ipc_params sem_params;
    
    	ns = current->nsproxy->ipc_ns;
    
    	if (nsems < 0 || nsems > ns->sc_semmsl)
    		return -EINVAL;
    
    	sem_params.key = key;
    	sem_params.flg = semflg;
    	sem_params.u.nsems = nsems;
    
    	return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
    }
    
    /**
     * perform_atomic_semop - Perform (if possible) a semaphore operation
     * @sma: semaphore array
     * @q: struct sem_queue that describes the operation
     *
     * Returns 0 if the operation was possible.
     * Returns 1 if the operation is impossible, the caller must sleep.
     * Negative values are error codes.
     */
    static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
    {
    	int result, sem_op, nsops, pid;
    	struct sembuf *sop;
    	struct sem *curr;
    	struct sembuf *sops;
    	struct sem_undo *un;
    
    	sops = q->sops;
    	nsops = q->nsops;
    	un = q->undo;
    
    	for (sop = sops; sop < sops + nsops; sop++) {
    		curr = sma->sem_base + sop->sem_num;
    		sem_op = sop->sem_op;
    		result = curr->semval;
    
    		if (!sem_op && result)
    			goto would_block;
    
    		result += sem_op;
    		if (result < 0)
    			goto would_block;
    		if (result > SEMVMX)
    			goto out_of_range;
    
    		if (sop->sem_flg & SEM_UNDO) {
    			int undo = un->semadj[sop->sem_num] - sem_op;
    			/* Exceeding the undo range is an error. */
    			if (undo < (-SEMAEM - 1) || undo > SEMAEM)
    				goto out_of_range;
    			un->semadj[sop->sem_num] = undo;
    		}
    
    		curr->semval = result;
    	}
    
    	sop--;
    	pid = q->pid;
    	while (sop >= sops) {
    		sma->sem_base[sop->sem_num].sempid = pid;
    		sop--;
    	}
    
    	return 0;
    
    out_of_range:
    	result = -ERANGE;
    	goto undo;
    
    would_block:
    	q->blocking = sop;
    
    	if (sop->sem_flg & IPC_NOWAIT)
    		result = -EAGAIN;
    	else
    		result = 1;
    
    undo:
    	sop--;
    	while (sop >= sops) {
    		sem_op = sop->sem_op;
    		sma->sem_base[sop->sem_num].semval -= sem_op;
    		if (sop->sem_flg & SEM_UNDO)
    			un->semadj[sop->sem_num] += sem_op;
    		sop--;
    	}
    
    	return result;
    }
    
    /** wake_up_sem_queue_prepare(q, error): Prepare wake-up
     * @q: queue entry that must be signaled
     * @error: Error value for the signal
     *
     * Prepare the wake-up of the queue entry q.
     */
    static void wake_up_sem_queue_prepare(struct list_head *pt,
    				struct sem_queue *q, int error)
    {
    	if (list_empty(pt)) {
    		/*
    		 * Hold preempt off so that we don't get preempted and have the
    		 * wakee busy-wait until we're scheduled back on.
    		 */
    		preempt_disable();
    	}
    	q->status = IN_WAKEUP;
    	q->pid = error;
    
    	list_add_tail(&q->list, pt);
    }
    
    /**
     * wake_up_sem_queue_do - do the actual wake-up
     * @pt: list of tasks to be woken up
     *
     * Do the actual wake-up.
     * The function is called without any locks held, thus the semaphore array
     * could be destroyed already and the tasks can disappear as soon as the
     * status is set to the actual return code.
     */
    static void wake_up_sem_queue_do(struct list_head *pt)
    {
    	struct sem_queue *q, *t;
    	int did_something;
    
    	did_something = !list_empty(pt);
    	list_for_each_entry_safe(q, t, pt, list) {
    		wake_up_process(q->sleeper);
    		/* q can disappear immediately after writing q->status. */
    		smp_wmb();
    		q->status = q->pid;
    	}
    	if (did_something)
    		preempt_enable();
    }
    
    static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
    {
    	list_del(&q->list);
    	if (q->nsops > 1)
    		sma->complex_count--;
    }
    
    /** check_restart(sma, q)
     * @sma: semaphore array
     * @q: the operation that just completed
     *
     * update_queue is O(N^2) when it restarts scanning the whole queue of
     * waiting operations. Therefore this function checks if the restart is
     * really necessary. It is called after a previously waiting operation
     * modified the array.
     * Note that wait-for-zero operations are handled without restart.
     */
    static int check_restart(struct sem_array *sma, struct sem_queue *q)
    {
    	/* pending complex alter operations are too difficult to analyse */
    	if (!list_empty(&sma->pending_alter))
    		return 1;
    
    	/* we were a sleeping complex operation. Too difficult */
    	if (q->nsops > 1)
    		return 1;
    
    	/* It is impossible that someone waits for the new value:
    	 * - complex operations always restart.
    	 * - wait-for-zero are handled seperately.
    	 * - q is a previously sleeping simple operation that
    	 *   altered the array. It must be a decrement, because
    	 *   simple increments never sleep.
    	 * - If there are older (higher priority) decrements
    	 *   in the queue, then they have observed the original
    	 *   semval value and couldn't proceed. The operation
    	 *   decremented to value - thus they won't proceed either.
    	 */
    	return 0;
    }
    
    /**
     * wake_const_ops - wake up non-alter tasks
     * @sma: semaphore array.
     * @semnum: semaphore that was modified.
     * @pt: list head for the tasks that must be woken up.
     *
     * wake_const_ops must be called after a semaphore in a semaphore array
     * was set to 0. If complex const operations are pending, wake_const_ops must
     * be called with semnum = -1, as well as with the number of each modified
     * semaphore.
     * The tasks that must be woken up are added to @pt. The return code
     * is stored in q->pid.
     * The function returns 1 if at least one operation was completed successfully.
     */
    static int wake_const_ops(struct sem_array *sma, int semnum,
    				struct list_head *pt)
    {
    	struct sem_queue *q;
    	struct list_head *walk;
    	struct list_head *pending_list;
    	int semop_completed = 0;
    
    	if (semnum == -1)
    		pending_list = &sma->pending_const;
    	else
    		pending_list = &sma->sem_base[semnum].pending_const;
    
    	walk = pending_list->next;
    	while (walk != pending_list) {
    		int error;
    
    		q = container_of(walk, struct sem_queue, list);
    		walk = walk->next;
    
    		error = perform_atomic_semop(sma, q);
    
    		if (error <= 0) {
    			/* operation completed, remove from queue & wakeup */
    
    			unlink_queue(sma, q);
    
    			wake_up_sem_queue_prepare(pt, q, error);
    			if (error == 0)
    				semop_completed = 1;
    		}
    	}
    	return semop_completed;
    }
    
    /**
     * do_smart_wakeup_zero - wakeup all wait for zero tasks
     * @sma: semaphore array
     * @sops: operations that were performed
     * @nsops: number of operations
     * @pt: list head of the tasks that must be woken up.
     *
     * Checks all required queue for wait-for-zero operations, based
     * on the actual changes that were performed on the semaphore array.
     * The function returns 1 if at least one operation was completed successfully.
     */
    static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
    					int nsops, struct list_head *pt)
    {
    	int i;
    	int semop_completed = 0;
    	int got_zero = 0;
    
    	/* first: the per-semaphore queues, if known */
    	if (sops) {
    		for (i = 0; i < nsops; i++) {
    			int num = sops[i].sem_num;
    
    			if (sma->sem_base[num].semval == 0) {
    				got_zero = 1;
    				semop_completed |= wake_const_ops(sma, num, pt);
    			}
    		}
    	} else {
    		/*
    		 * No sops means modified semaphores not known.
    		 * Assume all were changed.
    		 */
    		for (i = 0; i < sma->sem_nsems; i++) {
    			if (sma->sem_base[i].semval == 0) {
    				got_zero = 1;
    				semop_completed |= wake_const_ops(sma, i, pt);
    			}
    		}
    	}
    	/*
    	 * If one of the modified semaphores got 0,
    	 * then check the global queue, too.
    	 */
    	if (got_zero)
    		semop_completed |= wake_const_ops(sma, -1, pt);
    
    	return semop_completed;
    }
    
    
    /**
     * update_queue - look for tasks that can be completed.
     * @sma: semaphore array.
     * @semnum: semaphore that was modified.
     * @pt: list head for the tasks that must be woken up.
     *
     * update_queue must be called after a semaphore in a semaphore array
     * was modified. If multiple semaphores were modified, update_queue must
     * be called with semnum = -1, as well as with the number of each modified
     * semaphore.
     * The tasks that must be woken up are added to @pt. The return code
     * is stored in q->pid.
     * The function internally checks if const operations can now succeed.
     *
     * The function return 1 if at least one semop was completed successfully.
     */
    static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
    {
    	struct sem_queue *q;
    	struct list_head *walk;
    	struct list_head *pending_list;
    	int semop_completed = 0;
    
    	if (semnum == -1)
    		pending_list = &sma->pending_alter;
    	else
    		pending_list = &sma->sem_base[semnum].pending_alter;
    
    again:
    	walk = pending_list->next;
    	while (walk != pending_list) {
    		int error, restart;
    
    		q = container_of(walk, struct sem_queue, list);
    		walk = walk->next;
    
    		/* If we are scanning the single sop, per-semaphore list of
    		 * one semaphore and that semaphore is 0, then it is not
    		 * necessary to scan further: simple increments
    		 * that affect only one entry succeed immediately and cannot
    		 * be in the  per semaphore pending queue, and decrements
    		 * cannot be successful if the value is already 0.
    		 */
    		if (semnum != -1 && sma->sem_base[semnum].semval == 0)
    			break;
    
    		error = perform_atomic_semop(sma, q);
    
    		/* Does q->sleeper still need to sleep? */
    		if (error > 0)
    			continue;
    
    		unlink_queue(sma, q);
    
    		if (error) {
    			restart = 0;
    		} else {
    			semop_completed = 1;
    			do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
    			restart = check_restart(sma, q);
    		}
    
    		wake_up_sem_queue_prepare(pt, q, error);
    		if (restart)
    			goto again;
    	}
    	return semop_completed;
    }
    
    /**
     * set_semotime - set sem_otime
     * @sma: semaphore array
     * @sops: operations that modified the array, may be NULL
     *
     * sem_otime is replicated to avoid cache line trashing.
     * This function sets one instance to the current time.
     */
    static void set_semotime(struct sem_array *sma, struct sembuf *sops)
    {
    	if (sops == NULL) {
    		sma->sem_base[0].sem_otime = get_seconds();
    	} else {
    		sma->sem_base[sops[0].sem_num].sem_otime =
    							get_seconds();
    	}
    }
    
    /**
     * do_smart_update - optimized update_queue
     * @sma: semaphore array
     * @sops: operations that were performed
     * @nsops: number of operations
     * @otime: force setting otime
     * @pt: list head of the tasks that must be woken up.
     *
     * do_smart_update() does the required calls to update_queue and wakeup_zero,
     * based on the actual changes that were performed on the semaphore array.
     * Note that the function does not do the actual wake-up: the caller is
     * responsible for calling wake_up_sem_queue_do(@pt).
     * It is safe to perform this call after dropping all locks.
     */
    static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsops,
    			int otime, struct list_head *pt)
    {
    	int i;
    
    	otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);