* 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>
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(&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 rw_mutex
* is not necessarily held.
down_write(&shm_ids(ns).rw_mutex);
rcu_read_lock();
- ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
- &shmid64.shm_perm, 0);
+ ipcp = ipcctl_pre_down_nolock(ns, &shm_ids(ns), shmid, cmd,
+ &shmid64.shm_perm, 0);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
- /* the ipc lock is not held upon failure */
goto out_unlock1;
}
err = security_shm_shmctl(shp, cmd);
if (err)
- goto out_unlock0;
+ goto out_unlock1;
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&shp->shm_perm);
/* do_shm_rmid unlocks the ipc object and rcu */
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;
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
out_unlock0:
return err;
}
-SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+static int shmctl_nolock(struct ipc_namespace *ns, int shmid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct shmid_kernel *shp;
- int err, version;
- struct ipc_namespace *ns;
- if (cmd < 0 || shmid < 0) {
- err = -EINVAL;
- goto out;
+ /* preliminary security checks for *_INFO */
+ if (cmd == IPC_INFO || cmd == SHM_INFO) {
+ err = security_shm_shmctl(NULL, cmd);
+ if (err)
+ return err;
}
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
-
- switch (cmd) { /* replace with proc interface ? */
+ switch (cmd) {
case IPC_INFO:
{
struct shminfo64 shminfo;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shminfo, 0, sizeof(shminfo));
shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni;
shminfo.shmmax = ns->shm_ctlmax;
{
struct shm_info shm_info;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shm_info, 0, sizeof(shm_info));
down_read(&shm_ids(ns).rw_mutex);
shm_info.used_ids = shm_ids(ns).in_use;
struct shmid64_ds tbuf;
int result;
+ rcu_read_lock();
if (cmd == SHM_STAT) {
- shp = shm_lock(ns, shmid);
+ shp = shm_obtain_object(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = shp->shm_perm.id;
} else {
- shp = shm_lock_check(ns, shmid);
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
goto out_unlock;
+
err = security_shm_shmctl(shp, cmd);
if (err)
goto out_unlock;
+
memset(&tbuf, 0, sizeof(tbuf));
kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm);
tbuf.shm_segsz = shp->shm_segsz;
tbuf.shm_cpid = shp->shm_cprid;
tbuf.shm_lpid = shp->shm_lprid;
tbuf.shm_nattch = shp->shm_nattch;
- shm_unlock(shp);
- if(copy_shmid_to_user (buf, &tbuf, version))
+ rcu_read_unlock();
+
+ if (copy_shmid_to_user(buf, &tbuf, version))
err = -EFAULT;
else
err = result;
goto out;
}
+ default:
+ return -EINVAL;
+ }
+
+out_unlock:
+ rcu_read_unlock();
+out:
+ return err;
+}
+
+SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+{
+ struct shmid_kernel *shp;
+ int err, version;
+ struct ipc_namespace *ns;
+
+ if (cmd < 0 || shmid < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case SHM_INFO:
+ case SHM_STAT:
+ case IPC_STAT:
+ return shmctl_nolock(ns, shmid, cmd, version, buf);
+ case IPC_RMID:
+ case IPC_SET:
+ return shmctl_down(ns, shmid, cmd, buf, version);
case SHM_LOCK:
case SHM_UNLOCK:
{
struct file *shm_file;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock1;
}
audit_ipc_obj(&(shp->shm_perm));
+ err = security_shm_shmctl(shp, cmd);
+ if (err)
+ goto out_unlock1;
+ ipc_lock_object(&shp->shm_perm);
if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
kuid_t euid = current_euid();
err = -EPERM;
if (!uid_eq(euid, shp->shm_perm.uid) &&
!uid_eq(euid, shp->shm_perm.cuid))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK))
- goto out_unlock;
+ goto out_unlock0;
}
- err = security_shm_shmctl(shp, cmd);
- if (err)
- goto out_unlock;
-
shm_file = shp->shm_file;
if (is_file_hugepages(shm_file))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK) {
struct user_struct *user = current_user();
shp->shm_perm.mode |= SHM_LOCKED;
shp->mlock_user = user;
}
- goto out_unlock;
+ goto out_unlock0;
}
/* SHM_UNLOCK */
if (!(shp->shm_perm.mode & SHM_LOCKED))
- goto out_unlock;
+ goto out_unlock0;
shmem_lock(shm_file, 0, shp->mlock_user);
shp->shm_perm.mode &= ~SHM_LOCKED;
shp->mlock_user = NULL;
get_file(shm_file);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
shmem_unlock_mapping(shm_file->f_mapping);
+
fput(shm_file);
- goto out;
- }
- case IPC_RMID:
- case IPC_SET:
- err = shmctl_down(ns, shmid, cmd, buf, version);
return err;
+ }
default:
return -EINVAL;
}
-out_unlock:
- shm_unlock(shp);
-out:
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
return err;
}
* additional creator id...
*/
ns = current->nsproxy->ipc_ns;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
err = -EACCES;
if (err)
goto out_unlock;
+ ipc_lock_object(&shp->shm_perm);
path = shp->shm_file->f_path;
path_get(&path);
shp->shm_nattch++;
size = i_size_read(path.dentry->d_inode);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
err = -ENOMEM;
sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
- if (!sfd)
- goto out_put_dentry;
+ if (!sfd) {
+ path_put(&path);
+ goto out_nattch;
+ }
file = alloc_file(&path, f_mode,
is_file_hugepages(shp->shm_file) ?
&shm_file_operations_huge :
&shm_file_operations);
err = PTR_ERR(file);
- if (IS_ERR(file))
- goto out_free;
+ if (IS_ERR(file)) {
+ kfree(sfd);
+ path_put(&path);
+ goto out_nattch;
+ }
file->private_data = sfd;
file->f_mapping = shp->shm_file->f_mapping;
addr > current->mm->start_stack - size - PAGE_SIZE * 5)
goto invalid;
}
-
+
addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
*raddr = addr;
err = 0;
else
shm_unlock(shp);
up_write(&shm_ids(ns).rw_mutex);
-
-out:
return err;
out_unlock:
- shm_unlock(shp);
- goto out;
-
-out_free:
- kfree(sfd);
-out_put_dentry:
- path_put(&path);
- goto out_nattch;
+ rcu_read_unlock();
+out:
+ return err;
}
SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)