#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/rhashtable.h>
#include <linux/uaccess.h>
#include "util.h"
struct shmid_kernel
{
struct kern_ipc_perm shm_perm;
struct file *shm_file;
unsigned long shm_nattch;
unsigned long shm_segsz;
time64_t shm_atim;
time64_t shm_dtim;
time64_t shm_ctim;
struct pid *shm_cprid;
struct pid *shm_lprid;
struct ucounts *mlock_ucounts;
struct task_struct *shm_creator;
struct list_head shm_clist;
struct ipc_namespace *ns;
} __randomize_layout;
#define SHM_DEST 01000 /* segment will be destroyed on last detach */
#define SHM_LOCKED 02000 /* segment will not be swapped */
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));
}
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;
ipc_set_key_private(&shm_ids(ns), &shp->shm_perm);
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);
rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht);
}
#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);
}
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
{
struct kern_ipc_perm *ipcp;
rcu_read_lock();
ipcp = ipc_obtain_object_idr(&shm_ids(ns), id);
if (IS_ERR(ipcp))
goto err;
ipc_lock_object(ipcp);
if (ipc_valid_object(ipcp)) {
return container_of(ipcp, struct shmid_kernel, shm_perm);
}
ipc_unlock_object(ipcp);
ipcp = ERR_PTR(-EIDRM);
err:
rcu_read_unlock();
return ERR_CAST(ipcp);
}
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 kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm,
rcu);
struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel,
shm_perm);
security_shm_free(&shp->shm_perm);
kfree(shp);
}
static inline void shm_clist_rm(struct shmid_kernel *shp)
{
struct task_struct *creator;
rcu_read_lock();
if (!list_empty(&shp->shm_clist)) {
creator = shp->shm_creator;
task_lock(creator);
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 shm_file_data *sfd)
{
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) {
shm_unlock(shp);
return -EINVAL;
}
shp->shm_atim = ktime_get_real_seconds();
ipc_update_pid(&shp->shm_lprid, task_tgid(current));
shp->shm_nattch++;
shm_unlock(shp);
return 0;
}
static void shm_open(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
int err;
if (sfd->vm_ops->open)
sfd->vm_ops->open(vma);
err = __shm_open(sfd);
WARN_ON_ONCE(err);
}
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_ucounts);
fput(shm_file);
ipc_update_pid(&shp->shm_cprid, NULL);
ipc_update_pid(&shp->shm_lprid, NULL);
ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
}
static bool shm_may_destroy(struct shmid_kernel *shp)
{
return (shp->shm_nattch == 0) &&
(shp->ns->shm_rmid_forced ||
(shp->shm_perm.mode & SHM_DEST));
}
static void __shm_close(struct shm_file_data *sfd)
{
struct shmid_kernel *shp;
struct ipc_namespace *ns = sfd->ns;
down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, sfd->id);
if (WARN_ON_ONCE(IS_ERR(shp)))
goto done;
ipc_update_pid(&shp->shm_lprid, task_tgid(current));
shp->shm_dtim = ktime_get_real_seconds();
shp->shm_nattch--;
if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
done:
up_write(&shm_ids(ns).rwsem);
}
static void shm_close(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
if (sfd->vm_ops->close)
sfd->vm_ops->close(vma);
__shm_close(sfd);
}
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);
if (!list_empty(&shp->shm_clist))
return 0;
if (shm_may_destroy(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).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
up_write(&shm_ids(ns).rwsem);
}
void exit_shm(struct task_struct *task)
{
for (;;) {
struct shmid_kernel *shp;
struct ipc_namespace *ns;
task_lock(task);
if (list_empty(&task->sysvshm.shm_clist)) {
task_unlock(task);
break;
}
shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
shm_clist);
ns = shp->ns;
if (!ns->shm_rmid_forced)
goto unlink_continue;
ns = get_ipc_ns_not_zero(ns);
if (!ns) {
unlink_continue:
list_del_init(&shp->shm_clist);
task_unlock(task);
continue;
}
WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
list_del_init(&shp->shm_clist);
task_unlock(task);
down_write(&shm_ids(ns).rwsem);
shm_lock_by_ptr(shp);
ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
if (ipc_valid_object(&shp->shm_perm)) {
if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
} else {
shm_unlock(shp);
}
up_write(&shm_ids(ns).rwsem);
put_ipc_ns(ns);
}
}
static vm_fault_t shm_fault(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
return sfd->vm_ops->fault(vmf);
}
static int shm_may_split(struct vm_area_struct *vma, unsigned long addr)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
if (sfd->vm_ops->may_split)
return sfd->vm_ops->may_split(vma, addr);
return 0;
}
static unsigned long shm_pagesize(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
if (sfd->vm_ops->pagesize)
return sfd->vm_ops->pagesize(vma);
return PAGE_SIZE;
}
#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 = __shm_open(sfd);
if (ret)
return ret;
ret = call_mmap(sfd->file, vma);
if (ret) {
__shm_close(sfd);
return ret;
}
sfd->vm_ops = vma->vm_ops;
#ifdef CONFIG_MMU
WARN_ON(!sfd->vm_ops->fault);
#endif
vma->vm_ops = &shm_vm_ops;
return 0;
}
static int shm_release(struct inode *ino, struct file *file)
{
struct shm_file_data *sfd = shm_file_data(file);
put_ipc_ns(sfd->ns);
fput(sfd->file);
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 long shm_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
struct shm_file_data *sfd = shm_file_data(file);
if (!sfd->file->f_op->fallocate)
return -EOPNOTSUPP;
return sfd->file->f_op->fallocate(file, mode, offset, len);
}
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,
.get_unmapped_area = shm_get_unmapped_area,
.llseek = noop_llseek,
.fallocate = shm_fallocate,
};
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,
.fallocate = shm_fallocate,
};
bool 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,
.close = shm_close,
.fault = shm_fault,
.may_split = shm_may_split,
.pagesize = shm_pagesize,
#if defined(CONFIG_NUMA)
.set_policy = shm_set_policy,
.get_policy = shm_get_policy,
#endif
};
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;
size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
struct file *file;
char name[13];
vm_flags_t acctflag = 0;
if (size < SHMMIN || size > ns->shm_ctlmax)
return -EINVAL;
if (numpages << PAGE_SHIFT < size)
return -ENOSPC;
if (ns->shm_tot + numpages < ns->shm_tot ||
ns->shm_tot + numpages > ns->shm_ctlall)
return -ENOSPC;
shp = kmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT);
if (unlikely(!shp))
return -ENOMEM;
shp->shm_perm.key = key;
shp->shm_perm.mode = (shmflg & S_IRWXUGO);
shp->mlock_ucounts = NULL;
shp->shm_perm.security = NULL;
error = security_shm_alloc(&shp->shm_perm);
if (error) {
kfree(shp);
return error;
}
sprintf(name, "SYSV%08x", key);
if (shmflg & SHM_HUGETLB) {
struct hstate *hs;
size_t hugesize;
hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
if (!hs) {
error = -EINVAL;
goto no_file;
}
hugesize = ALIGN(size, huge_page_size(hs));
if (shmflg & SHM_NORESERVE)
acctflag = VM_NORESERVE;
file = hugetlb_file_setup(name, hugesize, acctflag,
HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
} else {
if ((shmflg & SHM_NORESERVE) &&
sysctl_overcommit_memory != OVERCOMMIT_NEVER)
acctflag = VM_NORESERVE;
file = shmem_kernel_file_setup(name, size, acctflag);
}
error = PTR_ERR(file);
if (IS_ERR(file))
goto no_file;
shp->shm_cprid = get_pid(task_tgid(current));
shp->shm_lprid = NULL;
shp->shm_atim = shp->shm_dtim = 0;
shp->shm_ctim = ktime_get_real_seconds();
shp->shm_segsz = size;
shp->shm_nattch = 0;
shp->shm_file = file;
shp->shm_creator = current;
error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
if (error < 0)
goto no_id;
shp->ns = ns;
task_lock(current);
list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist);
task_unlock(current);
file_inode(file)->i_ino = shp->shm_perm.id;
ns->shm_tot += numpages;
error = shp->shm_perm.id;
ipc_unlock_object(&shp->shm_perm);
rcu_read_unlock();
return error;
no_id:
ipc_update_pid(&shp->shm_cprid, NULL);
ipc_update_pid(&shp->shm_lprid, NULL);
fput(file);
ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
return error;
no_file:
call_rcu(&shp->shm_perm.rcu, shm_rcu_free);
return error;
}
static 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;
}
long ksys_shmget(key_t key, size_t size, int shmflg)
{
struct ipc_namespace *ns;
static const struct ipc_ops shm_ops = {
.getnew = newseg,
.associate = security_shm_associate,
.more_checks = shm_more_checks,
};
struct ipc_params shm_params;
ns = current->nsproxy->ipc_ns;
shm_params.key = key;
shm_params.flg = shmflg;
shm_params.u.size = size;
return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params);
}
SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg)
{
return ksys_shmget(key, size, shmflg);
}
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;
}
}
static void shm_add_rss_swap(struct shmid_kernel *shp,
unsigned long *rss_add, unsigned long *swp_add)
{
struct inode *inode;
inode = file_inode(shp->shm_file);
if (is_file_hugepages(shp->shm_file)) {
struct address_space *mapping = inode->i_mapping;
struct hstate *h = hstate_file(shp->shm_file);
*rss_add += pages_per_huge_page(h) * mapping->nrpages;
} else {
#ifdef CONFIG_SHMEM
struct shmem_inode_info *info = SHMEM_I(inode);
spin_lock_irq(&info->lock);
*rss_add += inode->i_mapping->nrpages;
*swp_add += info->swapped;
spin_unlock_irq(&info->lock);
#else
*rss_add += inode->i_mapping->nrpages;
#endif
}
}
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
{
int next_id;
int total, in_use;
*rss = 0;
*swp = 0;
in_use = shm_ids(ns).in_use;
for (total = 0, next_id = 0; total < in_use; next_id++) {
struct kern_ipc_perm *ipc;
struct shmid_kernel *shp;
ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id);
if (ipc == NULL)
continue;
shp = container_of(ipc, struct shmid_kernel, shm_perm);
shm_add_rss_swap(shp, rss, swp);
total++;
}
}
static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
struct shmid64_ds *shmid64)
{
struct kern_ipc_perm *ipcp;
struct shmid_kernel *shp;
int err;
down_write(&shm_ids(ns).rwsem);
rcu_read_lock();
ipcp = ipcctl_obtain_check(ns, &shm_ids(ns), shmid, cmd,
&shmid64->shm_perm, 0);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
goto out_unlock1;
}
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
err = security_shm_shmctl(&shp->shm_perm, cmd);
if (err)
goto out_unlock1;
switch (cmd) {
case IPC_RMID:
ipc_lock_object(&shp->shm_perm);
do_shm_rmid(ns, ipcp);
goto out_up;
case IPC_SET:
ipc_lock_object(&shp->shm_perm);
err = ipc_update_perm(&shmid64->shm_perm, ipcp);
if (err)
goto out_unlock0;
shp->shm_ctim = ktime_get_real_seconds();
break;
default:
err = -EINVAL;
goto out_unlock1;
}
out_unlock0:
ipc_unlock_object(&shp->shm_perm);
out_unlock1:
rcu_read_unlock();
out_up:
up_write(&shm_ids(ns).rwsem);
return err;
}
static int shmctl_ipc_info(struct ipc_namespace *ns,
struct shminfo64 *shminfo)
{
int err = security_shm_shmctl(NULL, IPC_INFO);
if (!err) {
memset(shminfo, 0, sizeof(*shminfo));
shminfo->shmmni = shminfo->shmseg = ns->shm_ctlmni;
shminfo->shmmax = ns->shm_ctlmax;
shminfo->shmall = ns->shm_ctlall;
shminfo->shmmin = SHMMIN;
down_read(&shm_ids(ns).rwsem);
err = ipc_get_maxidx(&shm_ids(ns));
up_read(&shm_ids(ns).rwsem);
if (err < 0)
err = 0;
}
return err;
}
static int shmctl_shm_info(struct ipc_namespace *ns,
struct shm_info *shm_info)
{
int err = security_shm_shmctl(NULL, SHM_INFO);
if (!err) {
memset(shm_info, 0, sizeof(*shm_info));
down_read(&shm_ids(ns).rwsem);
shm_info->used_ids = shm_ids(ns).in_use;
shm_get_stat(ns, &shm_info->shm_rss, &shm_info->shm_swp);
shm_info->shm_tot = ns->shm_tot;
shm_info->swap_attempts = 0;
shm_info->swap_successes = 0;
err = ipc_get_maxidx(&shm_ids(ns));
up_read(&shm_ids(ns).rwsem);
if (err < 0)
err = 0;
}
return err;
}
static int shmctl_stat(struct ipc_namespace *ns, int shmid,
int cmd, struct shmid64_ds *tbuf)
{
struct shmid_kernel *shp;
int err;
memset(tbuf, 0, sizeof(*tbuf));
rcu_read_lock();
if (cmd == SHM_STAT || cmd == SHM_STAT_ANY) {
shp = shm_obtain_object(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
goto out_unlock;
}
} else {
shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
goto out_unlock;
}
}
if (cmd == SHM_STAT_ANY)
audit_ipc_obj(&shp->shm_perm);
else {
err = -EACCES;
if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
goto out_unlock;
}
err = security_shm_shmctl(&shp->shm_perm, cmd);
if (err)
goto out_unlock;
ipc_lock_object(&shp->shm_perm);
if (!ipc_valid_object(&shp->shm_perm)) {
ipc_unlock_object(&shp->shm_perm);
err = -EIDRM;
goto out_unlock;
}
kernel_to_ipc64_perm(&shp->shm_perm, &tbuf->shm_perm);
tbuf->shm_segsz = shp->shm_segsz;
tbuf->shm_atime = shp->shm_atim;
tbuf->shm_dtime = shp->shm_dtim;
tbuf->shm_ctime = shp->shm_ctim;
#ifndef CONFIG_64BIT
tbuf->shm_atime_high = shp->shm_atim >> 32;
tbuf->shm_dtime_high = shp->shm_dtim >> 32;
tbuf->shm_ctime_high = shp->shm_ctim >> 32;
#endif
tbuf->shm_cpid = pid_vnr(shp->shm_cprid);
tbuf->shm_lpid = pid_vnr(shp->shm_lprid);
tbuf->shm_nattch = shp->shm_nattch;
if (cmd == IPC_STAT) {
err = 0;
} else {
err = shp->shm_perm.id;
}
ipc_unlock_object(&shp->shm_perm);
out_unlock:
rcu_read_unlock();
return err;
}
static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd)
{
struct shmid_kernel *shp;
struct file *shm_file;
int err;
rcu_read_lock();
shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
goto out_unlock1;
}
audit_ipc_obj(&(shp->shm_perm));
err = security_shm_shmctl(&shp->shm_perm, cmd);
if (err)
goto out_unlock1;
ipc_lock_object(&shp->shm_perm);
if (!ipc_valid_object(&shp->shm_perm)) {
err = -EIDRM;
goto out_unlock0;
}
if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
kuid_t euid = current_euid();
if (!uid_eq(euid, shp->shm_perm.uid) &&
!uid_eq(euid, shp->shm_perm.cuid)) {
err = -EPERM;
goto out_unlock0;
}
if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) {
err = -EPERM;
goto out_unlock0;
}
}
shm_file = shp->shm_file;
if (is_file_hugepages(shm_file))
goto out_unlock0;
if (cmd == SHM_LOCK) {
struct ucounts *ucounts = current_ucounts();
err = shmem_lock(shm_file, 1, ucounts);
if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) {
shp->shm_perm.mode |= SHM_LOCKED;
shp->mlock_ucounts = ucounts;
}
goto out_unlock0;
}
if (!(shp->shm_perm.mode & SHM_LOCKED))
goto out_unlock0;
shmem_lock(shm_file, 0, shp->mlock_ucounts);
shp->shm_perm.mode &= ~SHM_LOCKED;
shp->mlock_ucounts = NULL;
get_file(shm_file);
ipc_unlock_object(&shp->shm_perm);
rcu_read_unlock();
shmem_unlock_mapping(shm_file->f_mapping);
fput(shm_file);
return err;
out_unlock0:
ipc_unlock_object(&shp->shm_perm);
out_unlock1:
rcu_read_unlock();
return err;
}
static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int version)
{
int err;
struct ipc_namespace *ns;
struct shmid64_ds sem64;
if (cmd < 0 || shmid < 0)
return -EINVAL;
ns = current->nsproxy->ipc_ns;
switch (cmd) {
case IPC_INFO: {
struct shminfo64 shminfo;
err = shmctl_ipc_info(ns, &shminfo);
if (err < 0)
return err;
if (copy_shminfo_to_user(buf, &shminfo, version))
err = -EFAULT;
return err;
}
case SHM_INFO: {
struct shm_info shm_info;
err = shmctl_shm_info(ns, &shm_info);
if (err < 0)
return err;
if (copy_to_user(buf, &shm_info, sizeof(shm_info)))
err = -EFAULT;
return err;
}
case SHM_STAT:
case SHM_STAT_ANY:
case IPC_STAT: {
err = shmctl_stat(ns, shmid, cmd, &sem64);
if (err < 0)
return err;
if (copy_shmid_to_user(buf, &sem64, version))
err = -EFAULT;
return err;
}
case IPC_SET:
if (copy_shmid_from_user(&sem64, buf, version))
return -EFAULT;
fallthrough;
case IPC_RMID:
return shmctl_down(ns, shmid, cmd, &sem64);
case SHM_LOCK:
case SHM_UNLOCK:
return shmctl_do_lock(ns, shmid, cmd);
default:
return -EINVAL;
}
}
SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
{
return ksys_shmctl(shmid, cmd, buf, IPC_64);
}
#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf)
{
int version = ipc_parse_version(&cmd);
return ksys_shmctl(shmid, cmd, buf, version);
}
SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
{
return ksys_old_shmctl(shmid, cmd, buf);
}
#endif
#ifdef CONFIG_COMPAT
struct compat_shmid_ds {
struct compat_ipc_perm shm_perm;
int shm_segsz;
old_time32_t shm_atime;
old_time32_t shm_dtime;
old_time32_t shm_ctime;
compat_ipc_pid_t shm_cpid;
compat_ipc_pid_t shm_lpid;
unsigned short shm_nattch;
unsigned short shm_unused;
compat_uptr_t shm_unused2;
compat_uptr_t shm_unused3;
};
struct compat_shminfo64 {
compat_ulong_t shmmax;
compat_ulong_t shmmin;
compat_ulong_t shmmni;
compat_ulong_t shmseg;
compat_ulong_t shmall;
compat_ulong_t __unused1;
compat_ulong_t __unused2;
compat_ulong_t __unused3;
compat_ulong_t __unused4;
};
struct compat_shm_info {
compat_int_t used_ids;
compat_ulong_t shm_tot, shm_rss, shm_swp;
compat_ulong_t swap_attempts, swap_successes;
};
static int copy_compat_shminfo_to_user(void __user *buf, struct shminfo64 *in,
int version)
{
if (in->shmmax > INT_MAX)
in->shmmax = INT_MAX;
if (version == IPC_64) {
struct compat_shminfo64 info;
memset(&info, 0, sizeof(info));
info.shmmax = in->shmmax;
info.shmmin = in->shmmin;
info.shmmni = in->shmmni;
info.shmseg = in->shmseg;
info.shmall = in->shmall;
return copy_to_user(buf, &info, sizeof(info));
} else {
struct shminfo info;
memset(&info, 0, sizeof(info));
info.shmmax = in->shmmax;
info.shmmin = in->shmmin;
info.shmmni = in->shmmni;
info.shmseg = in->shmseg;
info.shmall = in->shmall;
return copy_to_user(buf, &info, sizeof(info));
}
}
static int put_compat_shm_info(struct shm_info *ip,
struct compat_shm_info __user *uip)
{
struct compat_shm_info info;
memset(&info, 0, sizeof(info));
info.used_ids = ip->used_ids;
info.shm_tot = ip->shm_tot;
info.shm_rss = ip->shm_rss;
info.shm_swp = ip->shm_swp;
info.swap_attempts = ip->swap_attempts;
info.swap_successes = ip->swap_successes;
return copy_to_user(uip, &info, sizeof(info));
}
static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in,
int version)
{
if (version == IPC_64) {
struct compat_shmid64_ds v;
memset(&v, 0, sizeof(v));
to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm);
v.shm_atime = lower_32_bits(in->shm_atime);
v.shm_atime_high = upper_32_bits(in->shm_atime);
v.shm_dtime = lower_32_bits(in->shm_dtime);
v.shm_dtime_high = upper_32_bits(in->shm_dtime);
v.shm_ctime = lower_32_bits(in->shm_ctime);
v.shm_ctime_high = upper_32_bits(in->shm_ctime);
v.shm_segsz = in->shm_segsz;
v.shm_nattch = in->shm_nattch;
v.shm_cpid = in->shm_cpid;
v.shm_lpid = in->shm_lpid;
return copy_to_user(buf, &v, sizeof(v));
} else {
struct compat_shmid_ds v;
memset(&v, 0, sizeof(v));
to_compat_ipc_perm(&v.shm_perm, &in->shm_perm);
v.shm_perm.key = in->shm_perm.key;
v.shm_atime = in->shm_atime;
v.shm_dtime = in->shm_dtime;
v.shm_ctime = in->shm_ctime;
v.shm_segsz = in->shm_segsz;
v.shm_nattch = in->shm_nattch;
v.shm_cpid = in->shm_cpid;
v.shm_lpid = in->shm_lpid;
return copy_to_user(buf, &v, sizeof(v));
}
}
static int copy_compat_shmid_from_user(struct shmid64_ds *out, void __user *buf,
int version)
{
memset(out, 0, sizeof(*out));
if (version == IPC_64) {
struct compat_shmid64_ds __user *p = buf;
return get_compat_ipc64_perm(&out->shm_perm, &p->shm_perm);
} else {
struct compat_shmid_ds __user *p = buf;
return get_compat_ipc_perm(&out->shm_perm, &p->shm_perm);
}
}
static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int version)
{
struct ipc_namespace *ns;
struct shmid64_ds sem64;
int err;
ns = current->nsproxy->ipc_ns;
if (cmd < 0 || shmid < 0)
return -EINVAL;
switch (cmd) {
case IPC_INFO: {
struct shminfo64 shminfo;
err = shmctl_ipc_info(ns, &shminfo);
if (err < 0)
return err;
if (copy_compat_shminfo_to_user(uptr, &shminfo, version))
err = -EFAULT;
return err;
}
case SHM_INFO: {
struct shm_info shm_info;
err = shmctl_shm_info(ns, &shm_info);
if (err < 0)
return err;
if (put_compat_shm_info(&shm_info, uptr))
err = -EFAULT;
return err;
}
case IPC_STAT:
case SHM_STAT_ANY:
case SHM_STAT:
err = shmctl_stat(ns, shmid, cmd, &sem64);
if (err < 0)
return err;
if (copy_compat_shmid_to_user(uptr, &sem64, version))
err = -EFAULT;
return err;
case IPC_SET:
if (copy_compat_shmid_from_user(&sem64, uptr, version))
return -EFAULT;
fallthrough;
case IPC_RMID:
return shmctl_down(ns, shmid, cmd, &sem64);
case SHM_LOCK:
case SHM_UNLOCK:
return shmctl_do_lock(ns, shmid, cmd);
default:
return -EINVAL;
}
return err;
}
COMPAT_SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, void __user *, uptr)
{
return compat_ksys_shmctl(shmid, cmd, uptr, IPC_64);
}
#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION
long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr)
{
int version = compat_ipc_parse_version(&cmd);
return compat_ksys_shmctl(shmid, cmd, uptr, version);
}
COMPAT_SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, void __user *, uptr)
{
return compat_ksys_old_shmctl(shmid, cmd, uptr);
}
#endif
#endif
long do_shmat(int shmid, char __user *shmaddr, int shmflg,
ulong *raddr, unsigned long shmlba)
{
struct shmid_kernel *shp;
unsigned long addr = (unsigned long)shmaddr;
unsigned long size;
struct file *file, *base;
int err;
unsigned long flags = MAP_SHARED;
unsigned long prot;
int acc_mode;
struct ipc_namespace *ns;
struct shm_file_data *sfd;
int f_flags;
unsigned long populate = 0;
err = -EINVAL;
if (shmid < 0)
goto out;
if (addr) {
if (addr & (shmlba - 1)) {
if (shmflg & SHM_RND) {
addr &= ~(shmlba - 1);
if (!addr && (shmflg & SHM_REMAP))
goto out;
} else
#ifndef __ARCH_FORCE_SHMLBA
if (addr & ~PAGE_MASK)
#endif
goto out;
}
flags |= MAP_FIXED;
} else if ((shmflg & SHM_REMAP))
goto out;
if (shmflg & SHM_RDONLY) {
prot = PROT_READ;
acc_mode = S_IRUGO;
f_flags = O_RDONLY;
} else {
prot = PROT_READ | PROT_WRITE;
acc_mode = S_IRUGO | S_IWUGO;
f_flags = O_RDWR;
}
if (shmflg & SHM_EXEC) {
prot |= PROT_EXEC;
acc_mode |= S_IXUGO;
}
ns = current->nsproxy->ipc_ns;
rcu_read_lock();
shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
goto out_unlock;
}
err = -EACCES;
if (ipcperms(ns, &shp->shm_perm, acc_mode))
goto out_unlock;
err = security_shm_shmat(&shp->shm_perm, shmaddr, shmflg);
if (err)
goto out_unlock;
ipc_lock_object(&shp->shm_perm);
if (!ipc_valid_object(&shp->shm_perm)) {
ipc_unlock_object(&shp->shm_perm);
err = -EIDRM;
goto out_unlock;
}
base = get_file(shp->shm_file);
shp->shm_nattch++;
size = i_size_read(file_inode(base));
ipc_unlock_object(&shp->shm_perm);
rcu_read_unlock();
err = -ENOMEM;
sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
if (!sfd) {
fput(base);
goto out_nattch;
}
file = alloc_file_clone(base, f_flags,
is_file_hugepages(base) ?
&shm_file_operations_huge :
&shm_file_operations);
err = PTR_ERR(file);
if (IS_ERR(file)) {
kfree(sfd);
fput(base);
goto out_nattch;
}
sfd->id = shp->shm_perm.id;
sfd->ns = get_ipc_ns(ns);
sfd->file = base;
sfd->vm_ops = NULL;
file->private_data = sfd;
err = security_mmap_file(file, prot, flags);
if (err)
goto out_fput;
if (mmap_write_lock_killable(current->mm)) {
err = -EINTR;
goto out_fput;
}
if (addr && !(shmflg & SHM_REMAP)) {
err = -EINVAL;
if (addr + size < addr)
goto invalid;
if (find_vma_intersection(current->mm, addr, addr + size))
goto invalid;
}
addr = do_mmap(file, addr, size, prot, flags, 0, 0, &populate, NULL);
*raddr = addr;
err = 0;
if (IS_ERR_VALUE(addr))
err = (long)addr;
invalid:
mmap_write_unlock(current->mm);
if (populate)
mm_populate(addr, populate);
out_fput:
fput(file);
out_nattch:
down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, shmid);
shp->shm_nattch--;
if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
up_write(&shm_ids(ns).rwsem);
return err;
out_unlock:
rcu_read_unlock();
out:
return err;
}
SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
{
unsigned long ret;
long err;
err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA);
if (err)
return err;
force_successful_syscall_return();
return (long)ret;
}
#ifdef CONFIG_COMPAT
#ifndef COMPAT_SHMLBA
#define COMPAT_SHMLBA SHMLBA
#endif
COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg)
{
unsigned long ret;
long err;
err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret, COMPAT_SHMLBA);
if (err)
return err;
force_successful_syscall_return();
return (long)ret;
}
#endif
long ksys_shmdt(char __user *shmaddr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long addr = (unsigned long)shmaddr;
int retval = -EINVAL;
#ifdef CONFIG_MMU
loff_t size = 0;
struct file *file;
VMA_ITERATOR(vmi, mm, addr);
#endif
if (addr & ~PAGE_MASK)
return retval;
if (mmap_write_lock_killable(mm))
return -EINTR;
#ifdef CONFIG_MMU
for_each_vma(vmi, vma) {
if ((vma->vm_ops == &shm_vm_ops) &&
(vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) {
file = vma->vm_file;
size = i_size_read(file_inode(vma->vm_file));
do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end,
NULL, false);
retval = 0;
vma = vma_next(&vmi);
break;
}
}
size = PAGE_ALIGN(size);
while (vma && (loff_t)(vma->vm_end - addr) <= size) {
if ((vma->vm_ops == &shm_vm_ops) &&
((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) &&
(vma->vm_file == file)) {
do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end,
NULL, false);
}
vma = vma_next(&vmi);
}
#else /* CONFIG_MMU */
vma = vma_lookup(mm, addr);
if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
retval = 0;
}
#endif
mmap_write_unlock(mm);
return retval;
}
SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
{
return ksys_shmdt(shmaddr);
}
#ifdef CONFIG_PROC_FS
static int sysvipc_shm_proc_show(struct seq_file *s, void *it)
{
struct pid_namespace *pid_ns = ipc_seq_pid_ns(s);
struct user_namespace *user_ns = seq_user_ns(s);
struct kern_ipc_perm *ipcp = it;
struct shmid_kernel *shp;
unsigned long rss = 0, swp = 0;
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
shm_add_rss_swap(shp, &rss, &swp);
#if BITS_PER_LONG <= 32
#define SIZE_SPEC "%10lu"
#else
#define SIZE_SPEC "%21lu"
#endif
seq_printf(s,
"%10d %10d %4o " SIZE_SPEC " %5u %5u "
"%5lu %5u %5u %5u %5u %10llu %10llu %10llu "
SIZE_SPEC " " SIZE_SPEC "\n",
shp->shm_perm.key,
shp->shm_perm.id,
shp->shm_perm.mode,
shp->shm_segsz,
pid_nr_ns(shp->shm_cprid, pid_ns),
pid_nr_ns(shp->shm_lprid, pid_ns),
shp->shm_nattch,
from_kuid_munged(user_ns, shp->shm_perm.uid),
from_kgid_munged(user_ns, shp->shm_perm.gid),
from_kuid_munged(user_ns, shp->shm_perm.cuid),
from_kgid_munged(user_ns, shp->shm_perm.cgid),
shp->shm_atim,
shp->shm_dtim,
shp->shm_ctim,
rss * PAGE_SIZE,
swp * PAGE_SIZE);
return 0;
}
#endif