#include <linux/proc_fs.h>
#include <linux/audit.h>
#include <linux/nsproxy.h>
+#include <linux/rwsem.h>
+#include <linux/memory.h>
+#include <linux/ipc_namespace.h>
#include <asm/unistd.h>
},
};
-static struct ipc_namespace *clone_ipc_ns(struct ipc_namespace *old_ns)
-{
- int err;
- struct ipc_namespace *ns;
+atomic_t nr_ipc_ns = ATOMIC_INIT(1);
- err = -ENOMEM;
- ns = kmalloc(sizeof(struct ipc_namespace), GFP_KERNEL);
- if (ns == NULL)
- goto err_mem;
-
- err = sem_init_ns(ns);
- if (err)
- goto err_sem;
- err = msg_init_ns(ns);
- if (err)
- goto err_msg;
- err = shm_init_ns(ns);
- if (err)
- goto err_shm;
-
- kref_init(&ns->kref);
- return ns;
-
-err_shm:
- msg_exit_ns(ns);
-err_msg:
- sem_exit_ns(ns);
-err_sem:
- kfree(ns);
-err_mem:
- return ERR_PTR(err);
-}
-struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns)
-{
- struct ipc_namespace *new_ns;
+#ifdef CONFIG_MEMORY_HOTPLUG
- BUG_ON(!ns);
- get_ipc_ns(ns);
+static void ipc_memory_notifier(struct work_struct *work)
+{
+ ipcns_notify(IPCNS_MEMCHANGED);
+}
- if (!(flags & CLONE_NEWIPC))
- return ns;
+static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier);
- new_ns = clone_ipc_ns(ns);
- put_ipc_ns(ns);
- return new_ns;
-}
-
-void free_ipc_ns(struct kref *kref)
+static int ipc_memory_callback(struct notifier_block *self,
+ unsigned long action, void *arg)
{
- struct ipc_namespace *ns;
+ switch (action) {
+ case MEM_ONLINE: /* memory successfully brought online */
+ case MEM_OFFLINE: /* or offline: it's time to recompute msgmni */
+ /*
+ * This is done by invoking the ipcns notifier chain with the
+ * IPC_MEMCHANGED event.
+ * In order not to keep the lock on the hotplug memory chain
+ * for too long, queue a work item that will, when waken up,
+ * activate the ipcns notification chain.
+ * No need to keep several ipc work items on the queue.
+ */
+ if (!work_pending(&ipc_memory_wq))
+ schedule_work(&ipc_memory_wq);
+ break;
+ case MEM_GOING_ONLINE:
+ case MEM_GOING_OFFLINE:
+ case MEM_CANCEL_ONLINE:
+ case MEM_CANCEL_OFFLINE:
+ default:
+ break;
+ }
- ns = container_of(kref, struct ipc_namespace, kref);
- sem_exit_ns(ns);
- msg_exit_ns(ns);
- shm_exit_ns(ns);
- kfree(ns);
+ return NOTIFY_OK;
}
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
/**
* ipc_init - initialise IPC subsystem
*
* The various system5 IPC resources (semaphores, messages and shared
* memory) are initialised
+ * A callback routine is registered into the memory hotplug notifier
+ * chain: since msgmni scales to lowmem this callback routine will be
+ * called upon successful memory add / remove to recompute msmgni.
*/
static int __init ipc_init(void)
sem_init();
msg_init();
shm_init();
+ hotplug_memory_notifier(ipc_memory_callback, IPC_CALLBACK_PRI);
+ register_ipcns_notifier(&init_ipc_ns);
return 0;
}
__initcall(ipc_init);
void ipc_init_ids(struct ipc_ids *ids)
{
- mutex_init(&ids->mutex);
+ init_rwsem(&ids->rw_mutex);
ids->in_use = 0;
ids->seq = 0;
{
int seq_limit = INT_MAX/SEQ_MULTIPLIER;
- if(seq_limit > USHRT_MAX)
- ids->seq_max = USHRT_MAX;
+ if (seq_limit > USHORT_MAX)
+ ids->seq_max = USHORT_MAX;
else
ids->seq_max = seq_limit;
}
iface->ids = ids;
iface->show = show;
- pde = create_proc_entry(path,
- S_IRUGO, /* world readable */
- NULL /* parent dir */);
- if (pde) {
- pde->data = iface;
- pde->proc_fops = &sysvipc_proc_fops;
- } else {
+ pde = proc_create_data(path,
+ S_IRUGO, /* world readable */
+ NULL, /* parent dir */
+ &sysvipc_proc_fops,
+ iface);
+ if (!pde) {
kfree(iface);
}
}
* @ids: Identifier set
* @key: The key to find
*
- * Requires ipc_ids.mutex locked.
+ * Requires ipc_ids.rw_mutex locked.
* Returns the LOCKED pointer to the ipc structure if found or NULL
* if not.
- * If key is found ipc contains its ipc structure
+ * If key is found ipc points to the owning ipc structure
*/
static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
* ipc_get_maxid - get the last assigned id
* @ids: IPC identifier set
*
- * Called with ipc_ids.mutex held.
+ * Called with ipc_ids.rw_mutex held.
*/
int ipc_get_maxid(struct ipc_ids *ids)
* @new: new IPC permission set
* @size: limit for the number of used ids
*
- * Add an entry 'new' to the IPC idr. The permissions object is
+ * Add an entry 'new' to the IPC ids idr. The permissions object is
* initialised and the first free entry is set up and the id assigned
- * is returned. The list is returned in a locked state on success.
- * On failure the list is not locked and -1 is returned.
+ * is returned. The 'new' entry is returned in a locked state on success.
+ * On failure the entry is not locked and a negative err-code is returned.
*
- * Called with ipc_ids.mutex held.
+ * Called with ipc_ids.rw_mutex held as a writer.
*/
int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
{
+ uid_t euid;
+ gid_t egid;
int id, err;
- /*
- * rcu_dereference()() is not needed here since
- * ipc_ids.mutex is held
- */
if (size > IPCMNI)
size = IPCMNI;
if (ids->in_use >= size)
- return -1;
+ return -ENOSPC;
+
+ spin_lock_init(&new->lock);
+ new->deleted = 0;
+ rcu_read_lock();
+ spin_lock(&new->lock);
err = idr_get_new(&ids->ipcs_idr, new, &id);
- if (err)
- return -1;
+ if (err) {
+ spin_unlock(&new->lock);
+ rcu_read_unlock();
+ return err;
+ }
ids->in_use++;
- new->cuid = new->uid = current->euid;
- new->gid = new->cgid = current->egid;
+ current_euid_egid(&euid, &egid);
+ new->cuid = new->uid = euid;
+ new->gid = new->cgid = egid;
new->seq = ids->seq++;
if(ids->seq > ids->seq_max)
ids->seq = 0;
- spin_lock_init(&new->lock);
- new->deleted = 0;
- rcu_read_lock();
- spin_lock(&new->lock);
+ new->id = ipc_buildid(id, new->seq);
return id;
}
/**
* ipcget_new - create a new ipc object
* @ns: namespace
- * @ids: identifer set
+ * @ids: IPC identifer set
* @ops: the actual creation routine to call
* @params: its parameters
*
- * This routine is called sys_msgget, sys_semget() and sys_shmget() when
- * the key is IPC_PRIVATE
+ * This routine is called by sys_msgget, sys_semget() and sys_shmget()
+ * when the key is IPC_PRIVATE.
*/
-int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
+static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
struct ipc_ops *ops, struct ipc_params *params)
{
int err;
-
+retry:
err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL);
if (!err)
return -ENOMEM;
- mutex_lock(&ids->mutex);
+ down_write(&ids->rw_mutex);
err = ops->getnew(ns, params);
- mutex_unlock(&ids->mutex);
+ up_write(&ids->rw_mutex);
+
+ if (err == -EAGAIN)
+ goto retry;
return err;
}
/**
* ipc_check_perms - check security and permissions for an IPC
* @ipcp: ipc permission set
- * @ids: identifer set
* @ops: the actual security routine to call
* @params: its parameters
+ *
+ * This routine is called by sys_msgget(), sys_semget() and sys_shmget()
+ * when the key is not IPC_PRIVATE and that key already exists in the
+ * ids IDR.
+ *
+ * On success, the IPC id is returned.
+ *
+ * It is called with ipc_ids.rw_mutex and ipcp->lock held.
*/
static int ipc_check_perms(struct kern_ipc_perm *ipcp, struct ipc_ops *ops,
struct ipc_params *params)
/**
* ipcget_public - get an ipc object or create a new one
* @ns: namespace
- * @ids: identifer set
+ * @ids: IPC identifer set
* @ops: the actual creation routine to call
* @params: its parameters
*
- * This routine is called sys_msgget, sys_semget() and sys_shmget() when
- * the key is not IPC_PRIVATE
+ * This routine is called by sys_msgget, sys_semget() and sys_shmget()
+ * when the key is not IPC_PRIVATE.
+ * It adds a new entry if the key is not found and does some permission
+ * / security checkings if the key is found.
+ *
+ * On success, the ipc id is returned.
*/
-int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
+static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
struct ipc_ops *ops, struct ipc_params *params)
{
struct kern_ipc_perm *ipcp;
int flg = params->flg;
int err;
-
+retry:
err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL);
- mutex_lock(&ids->mutex);
+ /*
+ * Take the lock as a writer since we are potentially going to add
+ * a new entry + read locks are not "upgradable"
+ */
+ down_write(&ids->rw_mutex);
ipcp = ipc_findkey(ids, params->key);
if (ipcp == NULL) {
/* key not used */
if (ops->more_checks)
err = ops->more_checks(ipcp, params);
if (!err)
+ /*
+ * ipc_check_perms returns the IPC id on
+ * success
+ */
err = ipc_check_perms(ipcp, ops, params);
}
ipc_unlock(ipcp);
}
- mutex_unlock(&ids->mutex);
+ up_write(&ids->rw_mutex);
+
+ if (err == -EAGAIN)
+ goto retry;
return err;
}
/**
* ipc_rmid - remove an IPC identifier
- * @ids: identifier set
- * @id: ipc perm structure containing the identifier to remove
+ * @ids: IPC identifier set
+ * @ipcp: ipc perm structure containing the identifier to remove
*
- * The identifier must be valid, and in use. The kernel will panic if
- * fed an invalid identifier. The entry is removed and internal
- * variables recomputed.
- * ipc_ids.mutex and the spinlock for this ID are held before this
- * function is called, and remain locked on the exit.
+ * ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held
+ * before this function is called, and remain locked on the exit.
*/
void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
*/
static void ipc_schedule_free(struct rcu_head *head)
{
- struct ipc_rcu_grace *grace =
- container_of(head, struct ipc_rcu_grace, rcu);
- struct ipc_rcu_sched *sched =
- container_of(&(grace->data[0]), struct ipc_rcu_sched, data[0]);
+ struct ipc_rcu_grace *grace;
+ struct ipc_rcu_sched *sched;
+
+ grace = container_of(head, struct ipc_rcu_grace, rcu);
+ sched = container_of(&(grace->data[0]), struct ipc_rcu_sched,
+ data[0]);
INIT_WORK(&sched->work, ipc_do_vfree);
schedule_work(&sched->work);
int ipcperms (struct kern_ipc_perm *ipcp, short flag)
{ /* flag will most probably be 0 or S_...UGO from <linux/stat.h> */
- int requested_mode, granted_mode, err;
+ uid_t euid = current_euid();
+ int requested_mode, granted_mode;
- if (unlikely((err = audit_ipc_obj(ipcp))))
- return err;
+ audit_ipc_obj(ipcp);
requested_mode = (flag >> 6) | (flag >> 3) | flag;
granted_mode = ipcp->mode;
- if (current->euid == ipcp->cuid || current->euid == ipcp->uid)
+ if (euid == ipcp->cuid ||
+ euid == ipcp->uid)
granted_mode >>= 6;
else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid))
granted_mode >>= 3;
}
/**
- * ipc64_perm_to_ipc_perm - convert old ipc permissions to new
+ * ipc64_perm_to_ipc_perm - convert new ipc permissions to old
* @in: new style IPC permissions
* @out: old style IPC permissions
*
out->seq = in->seq;
}
+/**
+ * ipc_lock - Lock an ipc structure without rw_mutex held
+ * @ids: IPC identifier set
+ * @id: ipc id to look for
+ *
+ * Look for an id in the ipc ids idr and lock the associated ipc object.
+ *
+ * The ipc object is locked on exit.
+ */
+
struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
{
struct kern_ipc_perm *out;
return out;
}
-int ipc_buildid(struct ipc_ids* ids, int id, int seq)
+struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
+{
+ struct kern_ipc_perm *out;
+
+ out = ipc_lock(ids, id);
+ if (IS_ERR(out))
+ return out;
+
+ if (ipc_checkid(out, id)) {
+ ipc_unlock(out);
+ return ERR_PTR(-EIDRM);
+ }
+
+ return out;
+}
+
+/**
+ * ipcget - Common sys_*get() code
+ * @ns : namsepace
+ * @ids : IPC identifier set
+ * @ops : operations to be called on ipc object creation, permission checks
+ * and further checks
+ * @params : the parameters needed by the previous operations.
+ *
+ * Common routine called by sys_msgget(), sys_semget() and sys_shmget().
+ */
+int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
+ struct ipc_ops *ops, struct ipc_params *params)
+{
+ if (params->key == IPC_PRIVATE)
+ return ipcget_new(ns, ids, ops, params);
+ else
+ return ipcget_public(ns, ids, ops, params);
+}
+
+/**
+ * ipc_update_perm - update the permissions of an IPC.
+ * @in: the permission given as input.
+ * @out: the permission of the ipc to set.
+ */
+void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
+{
+ out->uid = in->uid;
+ out->gid = in->gid;
+ out->mode = (out->mode & ~S_IRWXUGO)
+ | (in->mode & S_IRWXUGO);
+}
+
+/**
+ * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * @ids: the table of ids where to look for the ipc
+ * @id: the id of the ipc to retrieve
+ * @cmd: the cmd to check
+ * @perm: the permission to set
+ * @extra_perm: one extra permission parameter used by msq
+ *
+ * This function does some common audit and permissions check for some IPC_XXX
+ * cmd and is called from semctl_down, shmctl_down and msgctl_down.
+ * It must be called without any lock held and
+ * - retrieves the ipc with the given id in the given table.
+ * - performs some audit and permission check, depending on the given cmd
+ * - returns the ipc with both ipc and rw_mutex locks held in case of success
+ * or an err-code without any lock held otherwise.
+ */
+struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
+ struct ipc64_perm *perm, int extra_perm)
{
- return SEQ_MULTIPLIER*seq + id;
+ struct kern_ipc_perm *ipcp;
+ uid_t euid;
+ int err;
+
+ down_write(&ids->rw_mutex);
+ ipcp = ipc_lock_check(ids, id);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_up;
+ }
+
+ audit_ipc_obj(ipcp);
+ if (cmd == IPC_SET)
+ audit_ipc_set_perm(extra_perm, perm->uid,
+ perm->gid, perm->mode);
+
+ euid = current_euid();
+ if (euid == ipcp->cuid ||
+ euid == ipcp->uid || capable(CAP_SYS_ADMIN))
+ return ipcp;
+
+ err = -EPERM;
+ ipc_unlock(ipcp);
+out_up:
+ up_write(&ids->rw_mutex);
+ return ERR_PTR(err);
}
#ifdef __ARCH_WANT_IPC_PARSE_VERSION
/*
* This routine locks the ipc structure found at least at position pos.
*/
-struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
- loff_t *new_pos)
+static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
+ loff_t *new_pos)
{
struct kern_ipc_perm *ipc;
int total, id;
if (ipc && ipc != SEQ_START_TOKEN)
ipc_unlock(ipc);
- return sysvipc_find_ipc(iter->ns->ids[iface->ids], *pos, pos);
+ return sysvipc_find_ipc(&iter->ns->ids[iface->ids], *pos, pos);
}
/*
- * File positions: pos 0 -> header, pos n -> ipc id + 1.
- * SeqFile iterator: iterator value locked shp or SEQ_TOKEN_START.
+ * File positions: pos 0 -> header, pos n -> ipc id = n - 1.
+ * SeqFile iterator: iterator value locked ipc pointer or SEQ_TOKEN_START.
*/
static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos)
{
struct ipc_proc_iface *iface = iter->iface;
struct ipc_ids *ids;
- ids = iter->ns->ids[iface->ids];
+ ids = &iter->ns->ids[iface->ids];
/*
* Take the lock - this will be released by the corresponding
* call to stop().
*/
- mutex_lock(&ids->mutex);
+ down_read(&ids->rw_mutex);
/* pos < 0 is invalid */
if (*pos < 0)
struct ipc_proc_iface *iface = iter->iface;
struct ipc_ids *ids;
- /* If we had a locked segment, release it */
+ /* If we had a locked structure, release it */
if (ipc && ipc != SEQ_START_TOKEN)
ipc_unlock(ipc);
- ids = iter->ns->ids[iface->ids];
+ ids = &iter->ns->ids[iface->ids];
/* Release the lock we took in start() */
- mutex_unlock(&ids->mutex);
+ up_read(&ids->rw_mutex);
}
static int sysvipc_proc_show(struct seq_file *s, void *it)
Code Review / linux-2.6.git / blobdiff