/*
* linux/ipc/sem.c
* Copyright (C) 1992 Krishna Balasubramanian
* Copyright (C) 1995 Eric Schenk, Bruno Haible
*
* IMPLEMENTATION NOTES ON CODE REWRITE (Eric Schenk, January 1995):
* This code underwent a massive rewrite in order to solve some problems
* with the original code. In particular the original code failed to
* wake up processes that were waiting for semval to go to 0 if the
* value went to 0 and was then incremented rapidly enough. In solving
* this problem I have also modified the implementation so that it
* processes pending operations in a FIFO manner, thus give a guarantee
* that processes waiting for a lock on the semaphore won't starve
* unless another locking process fails to unlock.
* In addition the following two changes in behavior have been introduced:
* - The original implementation of semop returned the value
* last semaphore element examined on success. This does not
* match the manual page specifications, and effectively
* allows the user to read the semaphore even if they do not
* have read permissions. The implementation now returns 0
* on success as stated in the manual page.
* - There is some confusion over whether the set of undo adjustments
* to be performed at exit should be done in an atomic manner.
* That is, if we are attempting to decrement the semval should we queue
* up and wait until we can do so legally?
* The original implementation attempted to do this.
* The current implementation does not do so. This is because I don't
* think it is the right thing (TM) to do, and because I couldn't
* see a clean way to get the old behavior with the new design.
* The POSIX standard and SVID should be consulted to determine
* what behavior is mandated.
*
* Further notes on refinement (Christoph Rohland, December 1998):
* - The POSIX standard says, that the undo adjustments simply should
* redo. So the current implementation is o.K.
* - The previous code had two flaws:
* 1) It actively gave the semaphore to the next waiting process
* sleeping on the semaphore. Since this process did not have the
* cpu this led to many unnecessary context switches and bad
* performance. Now we only check which process should be able to
* get the semaphore and if this process wants to reduce some
* semaphore value we simply wake it up without doing the
* operation. So it has to try to get it later. Thus e.g. the
* running process may reacquire the semaphore during the current
* time slice. If it only waits for zero or increases the semaphore,
* we do the operation in advance and wake it up.
* 2) It did not wake up all zero waiting processes. We try to do
* better but only get the semops right which only wait for zero or
* increase. If there are decrement operations in the operations
* array we do the same as before.
*
* With the incarnation of O(1) scheduler, it becomes unnecessary to perform
* check/retry algorithm for waking up blocked processes as the new scheduler
* is better at handling thread switch than the old one.
*
* /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 <alan@redhat.com>
* Lockless wakeup
* (c) 2003 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>
*/
#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 <asm/uaccess.h>
#include "util.h"
#define sem_ids(ns) ((ns)->ids[IPC_SEM_IDS])
#define sem_unlock(sma) ipc_unlock(&(sma)->sem_perm)
#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 */
/*
* linked list protection:
* sem_undo.id_next,
* sem_array.sem_pending{,last},
* sem_array.sem_undo: sem_lock() for read/write
* sem_undo.proc_next: only "current" is allowed to read/write that field.
*
*/
#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_semmn