path: root/ipc/shm.c

/*
 * linux/ipc/shm.c
 * Copyright (C) 1992, 1993 Krishna Balasubramanian
 *	 Many improvements/fixes by Bruno Haible.
 * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994.
 * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli.
 *
 * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
 * BIGMEM support, Andrea Arcangeli <andrea@suse.de>
 * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr>
 * HIGHMEM support, Ingo Molnar <mingo@redhat.com>
 * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com>
 * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com>
 * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.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>
 *
 * Better ipc lock (kern_ipc_perm.lock) handling
 * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013.
 */

#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/shmem_fs.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/ptrace.h>
#include <linux/seq_file.h>
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/mount.h>
#include <linux/ipc_namespace.h>

#include <linux/uaccess.h>

#include "util.h"

struct shm_file_data {
	int id;
	struct ipc_namespace *ns;
	struct file *file;
	const struct vm_operations_struct *vm_ops;
};

#define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data))

static const struct file_operations shm_file_operations;
static const struct vm_operations_struct shm_vm_ops;

#define shm_ids(ns)	((ns)->ids[IPC_SHM_IDS])

#define shm_unlock(shp)			\
	ipc_unlock(&(shp)->shm_perm)

static int newseg(struct ipc_namespace *, struct ipc_params *);
static void shm_open(struct vm_area_struct *vma);
static void shm_close(struct vm_area_struct *vma);
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp);
#ifdef CONFIG_PROC_FS
static int sysvipc_shm_proc_show(struct seq_file *s, void *it);
#endif

void shm_init_ns(struct ipc_namespace *ns)
{
	ns->shm_ctlmax = SHMMAX;
	ns->shm_ctlall = SHMALL;
	ns->shm_ctlmni = SHMMNI;
	ns->shm_rmid_forced = 0;
	ns->shm_tot = 0;
	ipc_init_ids(&shm_ids(ns));
}

/*
 * Called with shm_ids.rwsem (writer) and the shp structure locked.
 * Only shm_ids.rwsem remains locked on exit.
 */
static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
	struct shmid_kernel *shp;
	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
	WARN_ON(ns != shp->ns);

	if (shp->shm_nattch) {
		shp->shm_perm.mode |= SHM_DEST;
		/* Do not find it any more */
		shp->shm_perm.key = IPC_PRIVATE;
		shm_unlock(shp);
	} else
		shm_destroy(ns, shp);
}

#ifdef CONFIG_IPC_NS
void shm_exit_ns(struct ipc_namespace *ns)
{
	free_ipcs(ns, &shm_ids(ns), do_shm_rmid);
	idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr);
}
#endif

static int __init ipc_ns_init(void)
{
	shm_init_ns(&init_ipc_ns);
	return 0;
}

pure_initcall(ipc_ns_init);

void __init shm_init(void)
{
	ipc_init_proc_interface("sysvipc/shm",
#if BITS_PER_LONG <= 32
				"       key      shmid perms       size  cpid  lpid nattch   uid   gid  cuid  cgid      atime      dtime      ctime        rss       swap\n",
#else
				"       key      shmid perms                  size  cpid  lpid nattch   uid   gid  cuid  cgid      atime      dtime      ctime                   rss                  swap\n",
#endif
				IPC_SHM_IDS, sysvipc_shm_proc_show);
}

static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
{
	struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id);

	if (IS_ERR(ipcp))
		return ERR_CAST(ipcp);

	return container_of(ipcp, struct shmid_kernel, shm_perm);
}

static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
{
	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);

	if (IS_ERR(ipcp))
		return ERR_CAST(ipcp);

	return container_of(ipcp, struct shmid_kernel, shm_perm);
}

/*
 * shm_lock_(check_) routines are called in the paths where the rwsem
 * is not necessarily held.
 */
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
{
	struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id);

	/*
	 * Callers of shm_lock() must validate the status of the returned ipc
	 * object pointer (as returned by ipc_lock()), and error out as
	 * appropriate.
	 */
	if (IS_ERR(ipcp))
		return (void *)ipcp;
	return container_of(ipcp, struct shmid_kernel, shm_perm);
}

static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
{
	rcu_read_lock();
	ipc_lock_object(&ipcp->shm_perm);
}

static void shm_rcu_free(struct rcu_head *head)
{
	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
	struct shmid_kernel *shp = ipc_rcu_to_struct(p);

	security_shm_free(shp);
	ipc_rcu_free(head);
}

/*
 * It has to be called with shp locked.
 * It must be called before ipc_rmid()
 */
static inline void shm_clist_rm(struct shmid_kernel *shp)
{
	struct task_struct *creator;

	/* ensure that shm_creator does not disappear */
	rcu_read_lock();

	/*
	 * A concurrent exit_shm may do a list_del_init() as well.
	 * Just do nothing if exit_shm already did the work
	 */
	if (!list_empty(&shp->shm_clist)) {
		/*
		 * shp->shm_creator is guaranteed to be valid *only*
		 * if shp->shm_clist is not empty.
		 */
		creator = shp->shm_creator;

		task_lock(creator);
		/*
		 * list_del_init() is a nop if the entry was already removed
		 * from the list.
		 */
		list_del_init(&shp->shm_clist);
		task_unlock(creator);
	}
	rcu_read_unlock();
}

static inline void shm_rmid(struct shmid_kernel *s)
{
	shm_clist_rm(s);
	ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
}


static int __shm_open(struct vm_area_struct *vma)
{
	struct file *file = vma->vm_file;
	struct shm_file_data *sfd = shm_file_data(file);
	struct shmid_kernel *shp;

	shp = shm_lock(sfd->ns, sfd->id);

	if (IS_ERR(shp))
		return PTR_ERR(shp);

	if (shp->shm_file != sfd->file) {
		/* ID was reused */
		shm_unlock(shp);
		return -EINVAL;
	}

	shp->shm_atim = get_seconds();
	shp->shm_lprid = task_tgid_vnr(current);
	shp->shm_nattch++;
	shm_unlock(shp);
	return 0;
}

/* This is called by fork, once for every shm attach. */
static void shm_open(struct vm_area_struct *vma)
{
	int err = __shm_open(vma);
	/*
	 * We raced in the idr lookup or with shm_destroy().
	 * Either way, the ID is busted.
	 */
	WARN_ON_ONCE(err);
}

/*
 * shm_destroy - free the struct shmid_kernel
 *
 * @ns: namespace
 * @shp: struct to free
 *
 * It has to be called with shp and shm_ids.rwsem (writer) locked,
 * but returns with shp unlocked and freed.
 */
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
	struct file *shm_file;

	shm_file = shp->shm_file;
	shp->shm_file = NULL;
	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
	shm_rmid(shp);
	shm_unlock(shp);
	if (!is_file_hugepages(shm_file))
		shmem_lock(shm_file, 0, shp->mlock_user);
	else if (shp->mlock_user)
		user_shm_unlock(i_size_