* 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_semncnt() and
- * count_semzcnt()
+ * - 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).
#include <linux/nsproxy.h>
#include <linux/ipc_namespace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include "util.h"
/* One semaphore structure for each semaphore in the system. */
* sem_array.pending{_alter,_cont},
* sem_array.sem_undo: global sem_lock() for read/write
* sem_undo.proc_next: only "current" is allowed to read/write that field.
- *
+ *
* sem_array.sem_base[i].pending_{const,alter}:
* global or semaphore sem_lock() for read/write
*/
SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
{
struct ipc_namespace *ns;
- struct ipc_ops sem_ops;
+ 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_ops.getnew = newary;
- sem_ops.associate = sem_security;
- sem_ops.more_checks = sem_more_checks;
-
sem_params.key = key;
sem_params.flg = semflg;
sem_params.u.nsems = nsems;
set_semotime(sma, sops);
}
+/*
+ * check_qop: Test how often 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 *sops = q->sops;
+ int nsops = q->nsops;
+ int i, semcnt;
+
+ semcnt = 0;
+
+ for (i = 0; i < nsops; i++) {
+ if (sops[i].sem_num != semnum)
+ continue;
+ if (sops[i].sem_flg & IPC_NOWAIT)
+ continue;
+ if (count_zero && sops[i].sem_op == 0)
+ semcnt++;
+ if (!count_zero && sops[i].sem_op < 0)
+ semcnt++;
+ }
+ return semcnt;
+}
+
/* 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
* The counts we return here are a rough approximation, but still
* warrant that semncnt+semzcnt>0 if the task is on the pending queue.
*/
-static int count_semncnt(struct sem_array *sma, ushort semnum)
+static int count_semcnt(struct sem_array *sma, ushort semnum,
+ bool count_zero)
{
- int semncnt;
+ struct list_head *l;
struct sem_queue *q;
+ int semcnt;
- semncnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].pending_alter, list) {
- struct sembuf *sops = q->sops;
- BUG_ON(sops->sem_num != semnum);
- if ((sops->sem_op < 0) && !(sops->sem_flg & IPC_NOWAIT))
- semncnt++;
- }
+ semcnt = 0;
+ /* First: check the simple operations. They are easy to evaluate */
+ if (count_zero)
+ l = &sma->sem_base[semnum].pending_const;
+ else
+ l = &sma->sem_base[semnum].pending_alter;
- list_for_each_entry(q, &sma->pending_alter, list) {
- struct sembuf *sops = q->sops;
- int nsops = q->nsops;
- int i;
- for (i = 0; i < nsops; i++)
- if (sops[i].sem_num == semnum
- && (sops[i].sem_op < 0)
- && !(sops[i].sem_flg & IPC_NOWAIT))
- semncnt++;
+ list_for_each_entry(q, l, list) {
+ /* all task on a per-semaphore list sleep on exactly
+ * that semaphore
+ */
+ semcnt++;
}
- return semncnt;
-}
-
-static int count_semzcnt(struct sem_array *sma, ushort semnum)
-{
- int semzcnt;
- struct sem_queue *q;
- semzcnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].pending_const, list) {
- struct sembuf *sops = q->sops;
- BUG_ON(sops->sem_num != semnum);
- if ((sops->sem_op == 0) && !(sops->sem_flg & IPC_NOWAIT))
- semzcnt++;
+ /* Then: check the complex operations. */
+ list_for_each_entry(q, &sma->pending_alter, list) {
+ semcnt += check_qop(sma, semnum, q, count_zero);
}
-
- list_for_each_entry(q, &sma->pending_const, list) {
- struct sembuf *sops = q->sops;
- int nsops = q->nsops;
- int i;
- for (i = 0; i < nsops; i++)
- if (sops[i].sem_num == semnum
- && (sops[i].sem_op == 0)
- && !(sops[i].sem_flg & IPC_NOWAIT))
- semzcnt++;
+ if (count_zero) {
+ list_for_each_entry(q, &sma->pending_const, list) {
+ semcnt += check_qop(sma, semnum, q, count_zero);
+ }
}
- return semzcnt;
+ return semcnt;
}
/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
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;
}
max_id = ipc_get_maxid(&sem_ids(ns));
up_read(&sem_ids(ns).rwsem);
- if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
+ if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
return -EFAULT;
return (max_id < 0) ? 0 : max_id;
}
err = curr->sempid;
goto out_unlock;
case GETNCNT:
- err = count_semncnt(sma, semnum);
+ err = count_semcnt(sma, semnum, 0);
goto out_unlock;
case GETZCNT:
- err = count_semzcnt(sma, semnum);
+ err = count_semcnt(sma, semnum, 1);
goto out_unlock;
}
/* We need to sleep on this operation, so we put the current
* task into the pending queue and go to sleep.
*/
-
+
queue.sops = sops;
queue.nsops = nsops;
queue.undo = un;
return error;
atomic_inc(&undo_list->refcnt);
tsk->sysvsem.undo_list = undo_list;
- } else
+ } else
tsk->sysvsem.undo_list = NULL;
return 0;