// SPDX-License-Identifier: GPL-2.0

  /*
   * 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>

   * (c) 2016 Davidlohr Bueso <dave@stgolabs.net>

   * 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 runtime 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())

   * - 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).

   * - 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/compat.h>

  #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/sched/wake_q.h>

  #include <linux/nospec.h>

  #include <linux/rhashtable.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).
  	 */

  	struct pid *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*/

  	time64_t	 sem_otime;	/* candidate for sem_otime */

  } ____cacheline_aligned_in_smp;
  
  /* One sem_array data structure for each set of semaphores in the system. */
  struct sem_array {
  	struct kern_ipc_perm	sem_perm;	/* permissions .. see ipc.h */
  	time64_t		sem_ctime;	/* create/last semctl() time */
  	struct list_head	pending_alter;	/* pending operations */
  						/* that alter the array */
  	struct list_head	pending_const;	/* pending complex operations */
  						/* that do not alter semvals */
  	struct list_head	list_id;	/* undo requests on this array */
  	int			sem_nsems;	/* no. of semaphores in array */
  	int			complex_count;	/* pending complex operations */
  	unsigned int		use_global_lock;/* >0: global lock required */
  
  	struct sem		sems[];
  } __randomize_layout;

  
  /* 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 */

  	struct pid		*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 */

  	bool			alter;	 /* does *sops alter the array? */
  	bool                    dupsop;	 /* sops on more than one sem_num */

  };
  
  /* 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 {

  	refcount_t		refcnt;

  	spinlock_t		lock;
  	struct list_head	list_proc;
  };

  #define sem_ids(ns)	((ns)->ids[IPC_SEM_IDS])

  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 */
  
  /*

   * Switching from the mode suitable for simple ops
   * to the mode for complex ops is costly. Therefore:
   * use some hysteresis
   */
  #define USE_GLOBAL_LOCK_HYSTERESIS	10
  
  /*

   * Locking:

   * a) global sem_lock() for read/write

   *	sem_undo.id_next,

   *	sem_array.complex_count,

   *	sem_array.pending{_alter,_const},
   *	sem_array.sem_undo

   *

   * b) global or semaphore sem_lock() for read/write:

   *	sem_array.sems[i].pending_{const,alter}:

   *
   * c) special:
   *	sem_undo_list.list_proc:
   *	* undo_list->lock for write
   *	* rcu for read

   *	use_global_lock:
   *	* global sem_lock() for write
   *	* either local or global sem_lock() for read.
   *
   * Memory ordering:
   * Most ordering is enforced by using spin_lock() and spin_unlock().

   *
   * Exceptions:
   * 1) use_global_lock: (SEM_BARRIER_1)

   * Setting it from non-zero to 0 is a RELEASE, this is ensured by

   * using smp_store_release(): Immediately after setting it to 0,
   * a simple op can start.

   * Testing if it is non-zero is an ACQUIRE, this is ensured by using
   * smp_load_acquire().
   * Setting it from 0 to non-zero must be ordered with regards to
   * this smp_load_acquire(), this is guaranteed because the smp_load_acquire()
   * is inside a spin_lock() and after a write from 0 to non-zero a
   * spin_lock()+spin_unlock() is done.

   * To prevent the compiler/cpu temporarily writing 0 to use_global_lock,
   * READ_ONCE()/WRITE_ONCE() is used.

   *
   * 2) queue.status: (SEM_BARRIER_2)
   * Initialization is done while holding sem_lock(), so no further barrier is
   * required.
   * Setting it to a result code is a RELEASE, this is ensured by both a
   * smp_store_release() (for case a) and while holding sem_lock()
   * (for case b).

   * The ACQUIRE when reading the result code without holding sem_lock() is

   * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep().
   * (case a above).
   * Reading the result code while holding sem_lock() needs no further barriers,
   * the locks inside sem_lock() enforce ordering (case b above)
   *
   * 3) current->state:
   * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock().
   * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may
   * happen immediately after calling wake_q_add. As wake_q_add_safe() is called
   * when holding sem_lock(), no further barriers are required.
   *
   * See also ipc/mqueue.c for more details on the covered races.

   */

  #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);

  	rhashtable_destroy(&ns->ids[IPC_SEM_IDS].key_ht);

  }

  #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
  ",

  				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->sems[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->sems[i];

  
  		list_splice_init(&sem->pending_alter, &sma->pending_alter);
  	}
  }

  static void sem_rcu_free(struct rcu_head *head)
  {

  	struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu);
  	struct sem_array *sma = container_of(p, struct sem_array, sem_perm);

  	security_sem_free(&sma->sem_perm);

  	kvfree(sma);

  }

  /*

   * 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->use_global_lock > 0)  {
  		/*
  		 * We are already in global lock mode.
  		 * Nothing to do, just reset the
  		 * counter until we return to simple mode.
  		 */

  		WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS);

  		return;
  	}

  	WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS);

  	for (i = 0; i < sma->sem_nsems; i++) {

  		sem = &sma->sems[i];

  		spin_lock(&sem->lock);
  		spin_unlock(&sem->lock);

  	}

  }
  
  /*
   * 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;
  	}

  	if (sma->use_global_lock == 1) {

  
  		/* See SEM_BARRIER_1 for purpose/pairing */

  		smp_store_release(&sma->use_global_lock, 0);
  	} else {

  		WRITE_ONCE(sma->use_global_lock,
  				sma->use_global_lock-1);

  	}

  }

  #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;

  	int idx;

  	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 use_global_mode.

  	 */

  	idx = array_index_nospec(sops->sem_num, sma->sem_nsems);
  	sem = &sma->sems[idx];

  	/*

  	 * Initial check for use_global_lock. Just an optimization,

  	 * no locking, no memory barrier.
  	 */

  	if (!READ_ONCE(sma->use_global_lock)) {

  		/*

  		 * It appears that no complex operation is around.
  		 * Acquire the per-semaphore lock.

  		 */

  		spin_lock(&sem->lock);

  		/* see SEM_BARRIER_1 for purpose/pairing */

  		if (!smp_load_acquire(&sma->use_global_lock)) {

  			/* 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->use_global_lock == 0) {
  		/*
  		 * The use_global_lock mode ended while we waited for
  		 * sma->sem_perm.lock. Thus we must switch to locking
  		 * with sem->lock.
  		 * Unlike in the fast path, there is no need to recheck
  		 * sma->use_global_lock after we have acquired sem->lock:
  		 * We own sma->sem_perm.lock, thus use_global_lock cannot
  		 * change.

  		 */
  		spin_lock(&sem->lock);

  		ipc_unlock_object(&sma->sem_perm);
  		return sops->sem_num;

  	} else {

  		/*
  		 * Not a false alarm, thus continue to use the global lock
  		 * mode. No need for complexmode_enter(), this was done by
  		 * the caller that has set use_global_mode to non-zero.

  		 */

  		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->sems[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_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_perm, sem_rcu_free);

  }

  static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
  {
  	ipc_rmid(&sem_ids(ns), &s->sem_perm);
  }

  static struct sem_array *sem_alloc(size_t nsems)
  {
  	struct sem_array *sma;

  
  	if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0]))
  		return NULL;

  	sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL_ACCOUNT);

  	if (unlikely(!sma))
  		return NULL;

  	return sma;
  }

  /**
   * 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 retval;
  	struct sem_array *sma;

  	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;

  	sma = sem_alloc(nsems);

  	if (!sma)

  		return -ENOMEM;

  	sma->sem_perm.mode = (semflg & S_IRWXUGO);
  	sma->sem_perm.key = key;
  
  	sma->sem_perm.security = NULL;

  	retval = security_sem_alloc(&sma->sem_perm);

  	if (retval) {

  		kvfree(sma);

  		return retval;
  	}

  	for (i = 0; i < nsems; i++) {

  		INIT_LIST_HEAD(&sma->sems[i].pending_alter);
  		INIT_LIST_HEAD(&sma->sems[i].pending_const);
  		spin_lock_init(&sma->sems[i].lock);

  	}

  
  	sma->complex_count = 0;

  	sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS;

  	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 = ktime_get_real_seconds();

  	/* ipc_addid() locks sma upon success. */

  	retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
  	if (retval < 0) {

  		ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);

  		return retval;

  	}
  	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 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;
  }

  long ksys_semget(key_t key, int nsems, int semflg)

  {

  	struct ipc_namespace *ns;

  	static const struct ipc_ops sem_ops = {
  		.getnew = newary,

  		.associate = security_sem_associate,

  		.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);

  }

  SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
  {
  	return ksys_semget(key, nsems, semflg);
  }

  /**

   * perform_atomic_semop[_slow] - Attempt to perform semaphore
   *                               operations on a given array.

   * @sma: semaphore array

   * @q: struct sem_queue that describes the operation

   *

   * Caller blocking are as follows, based the value
   * indicated by the semaphore operation (sem_op):
   *
   *  (1) >0 never blocks.
   *  (2)  0 (wait-for-zero operation): semval is non-zero.
   *  (3) <0 attempting to decrement semval to a value smaller than zero.
   *

   * Returns 0 if the operation was possible.
   * Returns 1 if the operation is impossible, the caller must sleep.

   * Returns <0 for error codes.

   */

  static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)

  {

  	int result, sem_op, nsops;
  	struct pid *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++) {

  		int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);
  		curr = &sma->sems[idx];

  		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) {

  		ipc_update_pid(&sma->sems[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->sems[sop->sem_num].semval -= sem_op;

  		if (sop->sem_flg & SEM_UNDO)
  			un->semadj[sop->sem_num] += sem_op;

  		sop--;
  	}
  
  	return result;
  }

  static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
  {
  	int result, sem_op, nsops;
  	struct sembuf *sop;
  	struct sem *curr;
  	struct sembuf *sops;
  	struct sem_undo *un;
  
  	sops = q->sops;
  	nsops = q->nsops;
  	un = q->undo;
  
  	if (unlikely(q->dupsop))
  		return perform_atomic_semop_slow(sma, q);
  
  	/*
  	 * We scan the semaphore set twice, first to ensure that the entire
  	 * operation can succeed, therefore avoiding any pointless writes
  	 * to shared memory and having to undo such changes in order to block
  	 * until the operations can go through.
  	 */
  	for (sop = sops; sop < sops + nsops; sop++) {

  		int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);
  
  		curr = &sma->sems[idx];

  		sem_op = sop->sem_op;
  		result = curr->semval;
  
  		if (!sem_op && result)
  			goto would_block; /* wait-for-zero */
  
  		result += sem_op;
  		if (result < 0)
  			goto would_block;
  
  		if (result > SEMVMX)
  			return -ERANGE;
  
  		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)
  				return -ERANGE;
  		}
  	}
  
  	for (sop = sops; sop < sops + nsops; sop++) {

  		curr = &sma->sems[sop->sem_num];

  		sem_op = sop->sem_op;
  		result = curr->semval;
  
  		if (sop->sem_flg & SEM_UNDO) {
  			int undo = un->semadj[sop->sem_num] - sem_op;
  
  			un->semadj[sop->sem_num] = undo;
  		}
  		curr->semval += sem_op;

  		ipc_update_pid(&curr->sempid, q->pid);

  	}
  
  	return 0;
  
  would_block:
  	q->blocking = sop;
  	return sop->sem_flg & IPC_NOWAIT ? -EAGAIN : 1;
  }

  static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error,
  					     struct wake_q_head *wake_q)

  {

  	struct task_struct *sleeper;
  
  	sleeper = get_task_struct(q->sleeper);

  	/* see SEM_BARRIER_2 for purpose/pairing */

  	smp_store_release(&q->status, error);

  	wake_q_add_safe(wake_q, sleeper);

  }

  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 inline 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 separately.

  	 * - 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.

   * @wake_q: lockless wake-queue head.

   *
   * 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 @wake_q. 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 wake_q_head *wake_q)

  {

  	struct sem_queue *q, *tmp;

  	struct list_head *pending_list;
  	int semop_completed = 0;
  
  	if (semnum == -1)
  		pending_list = &sma->pending_const;
  	else

  		pending_list = &sma->sems[semnum].pending_const;

  	list_for_each_entry_safe(q, tmp, pending_list, list) {
  		int error = perform_atomic_semop(sma, q);

  		if (error > 0)
  			continue;
  		/* operation completed, remove from queue & wakeup */
  		unlink_queue(sma, q);

  		wake_up_sem_queue_prepare(q, error, wake_q);
  		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

   * @wake_q: lockless wake-queue head

   *

   * 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 wake_q_head *wake_q)

  {
  	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->sems[num].semval == 0) {

  				got_zero = 1;

  				semop_completed |= wake_const_ops(sma, num, wake_q);

  			}
  		}
  	} else {
  		/*
  		 * No sops means modified semaphores not known.
  		 * Assume all were changed.

  		 */

  		for (i = 0; i < sma->sem_nsems; i++) {

  			if (sma->sems[i].semval == 0) {

  				got_zero = 1;

  				semop_completed |= wake_const_ops(sma, i, wake_q);

  			}
  		}

  	}
  	/*

  	 * If one of the modified semaphores got 0,
  	 * then check the global queue, too.

  	 */

  	if (got_zero)

  		semop_completed |= wake_const_ops(sma, -1, wake_q);

  	return semop_completed;

  }

  
  /**

   * update_queue - look for tasks that can be completed.

   * @sma: semaphore array.
   * @semnum: semaphore that was modified.

   * @wake_q: lockless wake-queue head.

   *
   * 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 @wake_q. 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 wake_q_head *wake_q)

  {

  	struct sem_queue *q, *tmp;

  	struct list_head *pending_list;

  	int semop_completed = 0;

  	if (semnum == -1)

  		pending_list = &sma->pending_alter;

  	else

  		pending_list = &sma->sems[semnum].pending_alter;

  
  again:

  	list_for_each_entry_safe(q, tmp, pending_list, list) {

  		int error, restart;

  		/* 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->sems[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, wake_q);

  			restart = check_restart(sma, q);

  		}

  		wake_up_sem_queue_prepare(q, error, wake_q);

  		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->sems[0].sem_otime = ktime_get_real_seconds();

  	} else {

  		sma->sems[sops[0].sem_num].sem_otime =

  						ktime_get_real_seconds();

  	}
  }
  
  /**

   * do_smart_update - optimized update_queue

   * @sma: semaphore array
   * @sops: operations that were performed
   * @nsops: number of operations

   * @otime: force setting otime

   * @wake_q: lockless wake-queue head

   *

   * 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_q().

   * 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 wake_q_head *wake_q)

  {
  	int i;

  	otime |= do_smart_wakeup_zero(sma, sops, nsops, wake_q);

  	if (!list_empty(&sma->pending_alter)) {
  		/* semaphore array uses the global queue - just process it. */

  		otime |= update_queue(sma, -1, wake_q);

  	} else {
  		if (!sops) {
  			/*
  			 * No sops, thus the modified semaphores are not
  			 * known. Check all.
  			 */
  			for (i = 0; i < sma->sem_nsems; i++)

  				otime |= update_queue(sma, i, wake_q);

  		} else {
  			/*
  			 * Check the semaphores that were increased:
  			 * - No complex ops, thus all sleeping ops are
  			 *   decrease.
  			 * - if we decreased the value, then any sleeping

  			 *   semaphore ops won't be able to run: If the

  			 *   previous value was too small, then the new
  			 *   value will be too small, too.
  			 */
  			for (i = 0; i < nsops; i++) {
  				if (sops[i].sem_op > 0) {
  					otime |= update_queue(sma,

  							      sops[i].sem_num, wake_q);

  				}

  			}

  		}

  	}

  	if (otime)
  		set_semotime(sma, sops);

  }

  /*

   * check_qop: Test if a queued operation sleeps on the semaphore semnum

   */
  static int check_qop(struct sem_array *sma, int semnum, struct sem_queue *q,
  			bool count_zero)
  {

  	struct sembuf *sop = q->blocking;

  	/*
  	 * Linux always (since 0.99.10) reported a task as sleeping on all
  	 * semaphores. This violates SUS, therefore it was changed to the
  	 * standard compliant behavior.
  	 * Give the administrators a chance to notice that an application
  	 * might misbehave because it relies on the Linux behavior.
  	 */
  	pr_info_once("semctl(GETNCNT/GETZCNT) is since 3.16 Single Unix Specification compliant.
  "
  			"The task %s (%d) triggered the difference, watch for misbehavior.
  ",
  			current->comm, task_pid_nr(current));

  	if (sop->sem_num != semnum)
  		return 0;

  	if (count_zero && sop->sem_op == 0)
  		return 1;
  	if (!count_zero && sop->sem_op < 0)
  		return 1;
  
  	return 0;

  }

  /* The following counts are associated to each semaphore:
   *   semncnt        number of tasks waiting on semval being nonzero
   *   semzcnt        number of tasks waiting on semval being zero

   *
   * Per definition, a task waits only on the semaphore of the first semop
   * that cannot proceed, even if additional operation would block, too.

   */

  static int count_semcnt(struct sem_array *sma, ushort semnum,
  			bool count_zero)

  {

  	struct list_head *l;

  	struct sem_queue *q;

  	int semcnt;

  	semcnt = 0;
  	/* First: check the simple operations. They are easy to evaluate */
  	if (count_zero)

  		l = &sma->sems[semnum].pending_const;

  	else

  		l = &sma->sems[semnum].pending_alter;

  	list_for_each_entry(q, l, list) {
  		/* all task on a per-semaphore list sleep on exactly
  		 * that semaphore
  		 */
  		semcnt++;

  	}

  	/* Then: check the complex operations. */

  	list_for_each_entry(q, &sma->pending_alter, list) {

  		semcnt += check_qop(sma, semnum, q, count_zero);
  	}
  	if (count_zero) {
  		list_for_each_entry(q, &sma->pending_const, list) {
  			semcnt += check_qop(sma, semnum, q, count_zero);
  		}

  	}

  	return semcnt;

  }

  /* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
   * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem

   * remains locked on exit.

   */

  static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)

  {

  	struct sem_undo *un, *tu;
  	struct sem_queue *q, *tq;

  	struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm);

  	int i;

  	DEFINE_WAKE_Q(wake_q);

  	/* Free the existing undo structures for this semaphore set.  */

  	ipc_assert_locked_object(&sma->sem_perm);

  	list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
  		list_del(&un->list_id);
  		spin_lock(&un->ulp->lock);

  		un->semid = -1;

  		list_del_rcu(&un->list_proc);
  		spin_unlock(&un->ulp->lock);

  		kvfree_rcu(un, rcu);

  	}

  
  	/* Wake up all pending processes and let them fail with EIDRM. */

  	list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
  		unlink_queue(sma, q);

  		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);

  	}
  
  	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {

  		unlink_queue(sma, q);

  		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);

  	}

  	for (i = 0; i < sma->sem_nsems; i++) {

  		struct sem *sem = &sma->sems[i];

  		list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
  			unlink_queue(sma, q);

  			wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);

  		}
  		list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {

  			unlink_queue(sma, q);

  			wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);

  		}

  		ipc_update_pid(&sem->sempid, NULL);

  	}

  	/* Remove the semaphore set from the IDR */
  	sem_rmid(ns, sma);

  	sem_unlock(sma, -1);

  	rcu_read_unlock();

  	wake_up_q(&wake_q);

  	ns->used_sems -= sma->sem_nsems;

  	ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);

  }
  
  static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
  {

  	switch (version) {

  	case IPC_64:
  		return copy_to_user(buf, in, sizeof(*in));
  	case IPC_OLD:
  	    {
  		struct semid_ds out;

  		memset(&out, 0, sizeof(out));

  		ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm);
  
  		out.sem_otime	= in->sem_otime;
  		out.sem_ctime	= in->sem_ctime;
  		out.sem_nsems	= in->sem_nsems;
  
  		return copy_to_user(buf, &out, sizeof(out));
  	    }
  	default:
  		return -EINVAL;
  	}
  }

  static time64_t get_semotime(struct sem_array *sma)

  {
  	int i;

  	time64_t res;

  	res = sma->sems[0].sem_otime;

  	for (i = 1; i < sma->sem_nsems; i++) {

  		time64_t to = sma->sems[i].sem_otime;

  
  		if (to > res)
  			res = to;
  	}
  	return res;
  }

  static int semctl_stat(struct ipc_namespace *ns, int semid,
  			 int cmd, struct semid64_ds *semid64)

  {

  	struct sem_array *sma;

  	time64_t semotime;

  	int err;

  	memset(semid64, 0, sizeof(*semid64));

  	rcu_read_lock();

  	if (cmd == SEM_STAT || cmd == SEM_STAT_ANY) {

  		sma = sem_obtain_object(ns, semid);
  		if (IS_ERR(sma)) {
  			err = PTR_ERR(sma);
  			goto out_unlock;
  		}

  	} else { /* IPC_STAT */

  		sma = sem_obtain_object_check(ns, semid);
  		if (IS_ERR(sma)) {
  			err = PTR_ERR(sma);
  			goto out_unlock;

  		}

  	}

  	/* see comment for SHM_STAT_ANY */
  	if (cmd == SEM_STAT_ANY)
  		audit_ipc_obj(&sma->sem_perm);
  	else {
  		err = -EACCES;
  		if (ipcperms(ns, &sma->sem_perm, S_IRUGO))
  			goto out_unlock;
  	}

  	err = security_sem_semctl(&sma->sem_perm, cmd);

  	if (err)
  		goto out_unlock;

  	ipc_lock_object(&sma->sem_perm);
  
  	if (!ipc_valid_object(&sma->sem_perm)) {
  		ipc_unlock_object(&sma->sem_perm);
  		err = -EIDRM;
  		goto out_unlock;
  	}

  	kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm);

  	semotime = get_semotime(sma);
  	semid64->sem_otime = semotime;

  	semid64->sem_ctime = sma->sem_ctime;

  #ifndef CONFIG_64BIT
  	semid64->sem_otime_high = semotime >> 32;
  	semid64->sem_ctime_high = sma->sem_ctime >> 32;
  #endif

  	semid64->sem_nsems = sma->sem_nsems;

  	if (cmd == IPC_STAT) {
  		/*
  		 * As defined in SUS:
  		 * Return 0 on success
  		 */
  		err = 0;
  	} else {
  		/*
  		 * SEM_STAT and SEM_STAT_ANY (both Linux specific)
  		 * Return the full id, including the sequence number
  		 */
  		err = sma->sem_perm.id;
  	}

  	ipc_unlock_object(&sma->sem_perm);

  out_unlock:

  	rcu_read_unlock();

  	return err;
  }

  static int semctl_info(struct ipc_namespace *ns, int semid,
  			 int cmd, void __user *p)
  {
  	struct seminfo seminfo;

  	int max_idx;

  	int err;
  
  	err = security_sem_semctl(NULL, cmd);
  	if (err)
  		return err;
  
  	memset(&seminfo, 0, sizeof(seminfo));
  	seminfo.semmni = ns->sc_semmni;
  	seminfo.semmns = ns->sc_semmns;
  	seminfo.semmsl = ns->sc_semmsl;
  	seminfo.semopm = ns->sc_semopm;
  	seminfo.semvmx = SEMVMX;
  	seminfo.semmnu = SEMMNU;
  	seminfo.semmap = SEMMAP;
  	seminfo.semume = SEMUME;
  	down_read(&sem_ids(ns).rwsem);
  	if (cmd == SEM_INFO) {
  		seminfo.semusz = sem_ids(ns).in_use;
  		seminfo.semaem = ns->used_sems;
  	} else {
  		seminfo.semusz = SEMUSZ;
  		seminfo.semaem = SEMAEM;
  	}

  	max_idx = ipc_get_maxidx(&sem_ids(ns));

  	up_read(&sem_ids(ns).rwsem);
  	if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
  		return -EFAULT;

  	return (max_idx < 0) ? 0 : max_idx;

  }

  static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,

  		int val)

  {
  	struct sem_undo *un;
  	struct sem_array *sma;

  	struct sem *curr;

  	int err;

  	DEFINE_WAKE_Q(wake_q);

  	if (val > SEMVMX || val < 0)
  		return -ERANGE;

  	rcu_read_lock();
  	sma = sem_obtain_object_check(ns, semid);
  	if (IS_ERR(sma)) {
  		rcu_read_unlock();
  		return PTR_ERR(sma);
  	}
  
  	if (semnum < 0 || semnum >= sma->sem_nsems) {
  		rcu_read_unlock();
  		return -EINVAL;
  	}
  
  
  	if (ipcperms(ns, &sma->sem_perm, S_IWUGO)) {
  		rcu_read_unlock();
  		return -EACCES;
  	}

  	err = security_sem_semctl(&sma->sem_perm, SETVAL);

  	if (err) {
  		rcu_read_unlock();
  		return -EACCES;
  	}

  	sem_lock(sma, NULL, -1);

  	if (!ipc_valid_object(&sma->sem_perm)) {

  		sem_unlock(sma, -1);
  		rcu_read_unlock();
  		return -EIDRM;
  	}

  	semnum = array_index_nospec(semnum, sma->sem_nsems);

  	curr = &sma->sems[semnum];

  	ipc_assert_locked_object(&sma->sem_perm);

  	list_for_each_entry(un, &sma->list_id, list_id)
  		un->semadj[semnum] = 0;
  
  	curr->semval = val;

  	ipc_update_pid(&curr->sempid, task_tgid(current));

  	sma->sem_ctime = ktime_get_real_seconds();

  	/* maybe some queued-up processes were waiting for this */

  	do_smart_update(sma, NULL, 0, 0, &wake_q);

  	sem_unlock(sma, -1);

  	rcu_read_unlock();

  	wake_up_q(&wake_q);

  	return 0;

  }

  static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,

  		int cmd, void __user *p)

  {
  	struct sem_array *sma;

  	struct sem *curr;

  	int err, nsems;

  	ushort fast_sem_io[SEMMSL_FAST];

  	ushort *sem_io = fast_sem_io;

  	DEFINE_WAKE_Q(wake_q);

  
  	rcu_read_lock();
  	sma = sem_obtain_object_check(ns, semid);
  	if (IS_ERR(sma)) {
  		rcu_read_unlock();

  		return PTR_ERR(sma);

  	}

  
  	nsems = sma->sem_nsems;

  	err = -EACCES;

  	if (ipcperms(ns, &sma->sem_perm, cmd == SETALL ? S_IWUGO : S_IRUGO))
  		goto out_rcu_wakeup;

  	err = security_sem_semctl(&sma->sem_perm, cmd);

  	if (err)
  		goto out_rcu_wakeup;

  
  	err = -EACCES;
  	switch (cmd) {
  	case GETALL:
  	{

  		ushort __user *array = p;

  		int i;

  		sem_lock(sma, NULL, -1);

  		if (!ipc_valid_object(&sma->sem_perm)) {

  			err = -EIDRM;
  			goto out_unlock;
  		}

  		if (nsems > SEMMSL_FAST) {

  			if (!ipc_rcu_getref(&sma->sem_perm)) {

  				err = -EIDRM;

  				goto out_unlock;

  			}
  			sem_unlock(sma, -1);

  			rcu_read_unlock();

  			sem_io = kvmalloc_array(nsems, sizeof(ushort),
  						GFP_KERNEL);

  			if (sem_io == NULL) {

  				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);

  				return -ENOMEM;
  			}

  			rcu_read_lock();

  			sem_lock_and_putref(sma);

  			if (!ipc_valid_object(&sma->sem_perm)) {

  				err = -EIDRM;

  				goto out_unlock;

  			}