/*
 * 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>
 */

#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 <asm/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.rw_mutex (writer) and the shp structure locked.
 * Only shm_ids.rw_mutex 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);

	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);
}

/*
 * shm_lock_(check_) routines are called in the paths where the rw_mutex
 * 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);

	if (IS_ERR(ipcp))
		return (struct shmid_kernel *)ipcp;

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

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

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

	if (IS_ERR(ipcp))
		return (struct shmid_kernel *)ipcp;

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

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


/* This is called by fork, once for every shm attach. */
static void 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);
	BUG_ON(IS_ERR(shp));
	shp->shm_atim = get_seconds();
	shp->shm_lprid = task_tgid_vnr(current);
	shp->shm_nattch++;
	shm_unlock(shp);
}

/*
 * shm_destroy - free the struct shmid_kernel
 *
 * @ns: namespace
 * @shp: struct to free
 *
 * It has to be called with shp and shm_ids.rw_mutex (writer) locked,
 * but returns with shp unlocked and freed.
 */
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
	shm_rmid(ns, shp);
	shm_unlock(shp);
	if (!is_file_hugepages(shp->shm_file))
		shmem_lock(shp->shm_file, 0, shp->mlock_user);
	else if (shp->mlock_user)
		user_shm_unlock(shp->shm_file->f_path.dentry->d_inode->i_size,
						shp->mlock_user);
	fput (shp->shm_file);
	security_shm_free(shp);
	ipc_rcu_putref(shp);
}

/*
 * shm_may_destroy - identifies whether shm segment should be destroyed now
 *
 * Returns true if and only if there are no active users of the segment and
 * one of the following is true:
 *
 * 1) shmctl(id, IPC_RMID, NULL) was called for this shp
 *
 * 2) sysctl kernel.shm_rmid_forced is set to 1.
 */
static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
	return (shp->shm_nattch == 0) &&
	       (ns->shm_rmid_forced ||
		(shp->shm_perm.mode & SHM_DEST));
}

/*
 * remove the attach descriptor vma.
 * free memory for segment if it is marked destroyed.
 * The descriptor has already been removed from the current->mm->mmap list
 * and will later be kfree()d.
 */
static void shm_close(struct vm_area_struct *vma)
{
	struct file * file = vma->vm_file;
	struct shm_file_data *sfd = shm_file_data(file);
	struct shmid_kernel *shp;
	struct ipc_namespace *ns = sfd->ns;

	down_write(&shm_ids(ns).rw_mutex);
	/* remove from the list of attaches of the shm segment */
	shp = shm_lock(ns, sfd->id);
	BUG_ON(IS_ERR(shp));
	shp->shm_lprid = task_tgid_vnr(current);
	shp->shm_dtim = get_seconds();
	shp->shm_nattch--;
	if (shm_may_destroy(ns, shp))
		shm_destroy(ns, shp);
	else
		shm_unlock(shp);
	up_write(&shm_ids(ns).rw_mutex);
}

/* Called with ns->shm_ids(ns).rw_mutex locked */
static int shm_try_destroy_current(int id, void *p, void *data)
{
	struct ipc_namespace *ns = data;
	struct kern_ipc_perm *ipcp = p;
	struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm);

	if (shp->shm_creator != current)
		return 0;

	/*
	 * Mark it as orphaned to destroy the segment when
	 * kernel.shm_rmid_forced is changed.
	 * It is noop if the following shm_may_destroy() returns true.
	 */
	shp->shm_creator = NULL;

	/*
	 * Don't even try to destroy it.  If shm_rmid_forced=0 and IPC_RMID
	 * is not set, it shouldn't be deleted here.
	 */
	if (!ns->shm_rmid_forced)
		return 0;

	if (shm_may_destroy(ns, shp)) {
		shm_lock_by_ptr(shp);
		shm_destroy(ns, shp);
	}
	return 0;
}

/* Called with ns->shm_ids(ns).rw_mutex locked */
static int shm_try_destroy_orphaned(int id, void *p, void *data)
{
	struct ipc_namespace *ns = data;
	struct kern_ipc_perm *ipcp = p;
	struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm);

	/*
	 * We want to destroy segments without users and with already
	 * exit'ed originating process.
	 *
	 * As shp->* are changed under rw_mutex, it's safe to skip shp locking.
	 */
	if (shp->shm_creator != NULL)
		return 0;

	if (shm_may_destroy(ns, shp)) {
		shm_lock_by_ptr(shp);
		shm_destroy(ns, shp);
	}
	return 0;
}

void shm_destroy_orphaned(struct ipc_namespace *ns)
{
	down_write(&shm_ids(ns).rw_mutex);
	if (shm_ids(ns).in_use)
		idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
	up_write(&shm_ids(ns).rw_mutex);
}


void exit_shm(struct task_struct *task)
{
	struct ipc_namespace *ns = task->nsproxy->ipc_ns;

	if (shm_ids(ns).in_use == 0)
		return;

	/* Destroy all already created segments, but not mapped yet */
	down_write(&shm_ids(ns).rw_mutex);
	if (shm_ids(ns).in_use)
		idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
	up_write(&shm_ids(ns).rw_mutex);
}

static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct file *file = vma->vm_file;
	struct shm_file_data *sfd = shm_file_data(file);

	return sfd->vm_ops->fault(vma, vmf);
}

#ifdef CONFIG_NUMA
static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
{
	struct file *file = vma->vm_file;
	struct shm_file_data *sfd = shm_file_data(file);
	int err = 0;
	if (sfd->vm_ops->set_policy)
		err = sfd->vm_ops->set_policy(vma, new);
	return err;
}

static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
					unsigned long addr)
{
	struct file *file = vma->vm_file;
	struct shm_file_data *sfd = shm_file_data(file);
	struct mempolicy *pol = NULL;

	if (sfd->vm_ops->get_policy)
		pol = sfd->vm_ops->get_policy(vma, addr);
	else if (vma->vm_policy)
		pol = vma->vm_policy;

	return pol;
}
#endif

static int shm_mmap(struct file * file, struct vm_area_struct * vma)
{
	struct shm_file_data *sfd = shm_file_data(file);
	int ret;

	ret = sfd->file->f_op->mmap(sfd->file, vma);
	if (ret != 0)
		return ret;
	sfd->vm_ops = vma->vm_ops;
#ifdef CONFIG_MMU
	BUG_ON(!sfd->vm_ops->fault);
#endif
	vma->vm_ops = &shm_vm_ops;
	shm_open(vma);

	return ret;
}

static int shm_release(struct inode *ino, struct file *file)
{
	struct shm_file_data *sfd = shm_file_data(file);

	put_ipc_ns(sfd->ns);
	shm_file_data(file) = NULL;
	kfree(sfd);
	return 0;
}

static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
	struct shm_file_data *sfd = shm_file_data(file);

	if (!sfd->file->f_op->fsync)
		return -EINVAL;
	return sfd->file->f_op->fsync(sfd->file, start, end, datasync);
}

static unsigned long shm_get_unmapped_area(struct file *file,
	unsigned long addr, unsigned long len, unsigned long pgoff,
	unsigned long flags)
{
	struct shm_file_data *sfd = shm_file_data(file);
	return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len,
						pgoff, flags);
}

static const struct file_operations shm_file_operations = {
	.mmap		= shm_mmap,
	.fsync		= shm_fsync,
	.release	= shm_release,
#ifndef CONFIG_MMU
	.get_unmapped_area	= shm_get_unmapped_area,
#endif
	.llseek		= noop_llseek,
};

static const struct file_operations shm_file_operations_huge = {
	.mmap		= shm_mmap,
	.fsync		= shm_fsync,
	.release	= shm_release,
	.get_unmapped_area	= shm_get_unmapped_area,
	.llseek		= noop_llseek,
};

int is_file_shm_hugepages(struct file *file)
{
	return file->f_op == &shm_file_operations_huge;
}

static const struct vm_operations_struct shm_vm_ops = {
	.open	= shm_open,	/* callback for a new vm-area open */
	.close	= shm_close,	/* callback for when the vm-area is released */
	.fault	= shm_fault,
#if defined(CONFIG_NUMA)
	.set_policy = shm_set_policy,
	.get_policy = shm_get_policy,
#endif
};

/**
 * newseg - Create a new shared memory segment
 * @ns: namespace
 * @params: ptr to the structure that contains key, size and shmflg
 *
 * Called with shm_ids.rw_mutex held as a writer.
 */

static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
{
	key_t key = params->key;
	int shmflg = params->flg;
	size_t size = params->u.size;
	int error;
	struct shmid_kernel *shp;
	int numpages = (size + PAGE_SIZE -1) >> PAGE_SHIFT;
	struct file * file;
	char name[13];
	int id;
	vm_flags_t acctflag = 0;

	if (size < SHMMIN || size > ns->shm_ctlmax)
		return -EINVAL;

	if (ns->shm_tot + numpages > ns->shm_ctlall)
		return -ENOSPC;

	shp = ipc_rcu_alloc(sizeof(*shp));
	if (!shp)
		return -ENOMEM;

	shp->shm_perm.key = key;
	shp->shm_perm.mode = (shmflg & S_IRWXUGO);
	shp->mlock_user = NULL;

	shp->shm_perm.security = NULL;
	error = security_shm_alloc(shp);
	if (error) {
		ipc_rcu_putref(shp);
		return error;
	}

	sprintf (name, "SYSV%08x", key);
	if (shmflg & SHM_HUGETLB) {
		/* hugetlb_file_setup applies strict accounting */
		if (shmflg & SHM_NORESERVE)
			acctflag = VM_NORESERVE;
		file = hugetlb_file_setup(name, size, acctflag,
					&shp->mlock_user, HUGETLB_SHMFS_INODE);
	} else {
		/*
		 * Do not allow no accounting for OVERCOMMIT_NEVER, even
	 	 * if it's asked for.
		 */
		if  ((shmflg & SHM_NORESERVE) &&
				sysctl_overcommit_memory != OVERCOMMIT_NEVER)
			acctflag = VM_NORESERVE;
		file = shmem_file_setup(name, size, acctflag);
	}
	error = PTR_ERR(file);
	if (IS_ERR(file))
		goto no_file;

	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
	if (id < 0) {
		error = id;
		goto no_id;
	}

	shp->shm_cprid = task_tgid_vnr(current);
	shp->shm_lprid = 0;
	shp->shm_atim = shp->shm_dtim = 0;
	shp->shm_ctim = get_seconds();
	shp->shm_segsz = size;
	shp->shm_nattch = 0;
	shp->shm_file = file;
	shp->shm_creator = current;
	/*
	 * shmid gets reported as "inode#" in /proc/pid/maps.
	 * proc-ps tools use this. Changing this will break them.
	 */
	file->f_dentry->d_inode->i_ino = shp->shm_perm.id;

	ns->shm_tot += numpages;
	error = shp->shm_perm.id;
	shm_unlock(shp);
	return error;

no_id:
	if (is_file_hugepages(file) && shp->mlock_user)
		user_shm_unlock(size, shp->mlock_user);
	fput(file);
no_file:
	security_shm_free(shp);
	ipc_rcu_putref(shp);
	return error;
}

/*
 * Called with shm_ids.rw_mutex and ipcp locked.
 */
static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
{
	struct shmid_kernel *shp;

	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
	return security_shm_associate(shp, shmflg);
}

/*
 * Called with shm_ids.rw_mutex and ipcp locked.
 */
static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
				struct ipc_params *params)
{
	struct shmid_kernel *shp;

	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
	if (shp->shm_segsz < params->u.size)
		return -EINVAL;

	return 0;
}

SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg)
{
	struct ipc_namespace *ns;
	struct ipc_ops shm_ops;
	struct ipc_params shm_params;

	ns = current->nsproxy->ipc_ns;

	shm_ops.getnew = newseg;
	shm_ops.associate = shm_security;
	shm_ops.more_checks = shm_more_checks;

	shm_params.key = key;
	shm_params.flg = shmflg;
	shm_params.u.size = size;

	return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params);
}

static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version)
{
	switch(version) {
	case IPC_64:
		return copy_to_user(buf, in, sizeof(*in));
	case IPC_OLD:
	    {
		struct shmid_ds out;

		memset(&out, 0, sizeof(out));
		ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm);
		out.shm_segsz	= in->shm_segsz;
		out.shm_atime	= in->shm_atime;
		out.shm_dtime	= in->shm_dtime;
		out.shm_ctime	= in->shm_ctime;
		out.shm_cpid	= in->shm_cpid;
		out.shm_lpid	= in->shm_lpid;
		out.shm_nattch	= in->shm_nattch;

		return copy_to_user(buf, &out, sizeof(out));
	    }
	default:
		return -EINVAL;
	}
}

static inline unsigned long
copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version)
{
	switch(version) {
	case IPC_64:
		if (copy_from_user(out, buf, sizeof(*out)))
			return -EFAULT;
		return 0;
	case IPC_OLD:
	    {
		struct shmid_ds tbuf_old;

		if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
			return -EFAULT;

		out->shm_perm.uid	= tbuf_old.shm_perm.uid;
		out->shm_perm.gid	= tbuf_old.shm_perm.gid;
		out->shm_perm.mode	= tbuf_old.shm_perm.mode;

		return 0;
	    }
	default:
		return -EINVAL;
	}
}

static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version)
{
	switch(version) {
	case IPC_64:
		return copy_to_user(buf, in, sizeof(*in));
	case IPC_OLD:
	    {
		struct shminfo out;

		if(in->shmmax > INT_MAX)
			out.shmmax = INT_MAX;
		else
			out.shmmax = (int)in->shmmax;

		out.shmmin	= in->shmmin;
		out.shmmni	= in->shmmni;
		out.shmseg	= in->shmseg;
		out.shmall	= in->shmall; 

		return copy_to_user(buf, &out, sizeof(out));
	    }
	default:
		return -EINVAL;
	}
}

/*
 * Calculate and add used RSS and swap pages of a shm.
 * Called with shm_ids.rw_mutex held as a reader
 */
static void shm_add_rss_swap(struct shmid_kernel *shp,
	unsigned long *rss_add, unsigned long *swp_add)
{
	struct inode *inode;

	inode = shp->shm_file->f_path.dentry->d_inode;