Merge branch 'akpm' (patches from Andrew Morton)

Merge first patch-bomb from Andrew Morton:
 - Some pidns/fork/exec tweaks
 - OCFS2 updates
 - Most of MM - there remain quite a few memcg parts which depend on
   pending core cgroups changes.  Which might have been already merged -
   I'll check tomorrow...
 - Various misc stuff all over the place
 - A few block bits which I never got around to sending to Jens -
   relatively minor things.
 - MAINTAINERS maintenance
 - A small number of lib/ updates
 - checkpatch updates
 - epoll
 - firmware/dmi-scan
 - Some kprobes work for S390
 - drivers/rtc updates
 - hfsplus feature work
 - vmcore feature work
 - rbtree upgrades
 - AOE updates
 - pktcdvd cleanups
 - PPS
 - memstick
 - w1
 - New "inittmpfs" feature, which does the obvious
 - More IPC work from Davidlohr.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (303 commits)
  lz4: fix compression/decompression signedness mismatch
  ipc: drop ipc_lock_check
  ipc, shm: drop shm_lock_check
  ipc: drop ipc_lock_by_ptr
  ipc, shm: guard against non-existant vma in shmdt(2)
  ipc: document general ipc locking scheme
  ipc,msg: drop msg_unlock
  ipc: rename ids->rw_mutex
  ipc,shm: shorten critical region for shmat
  ipc,shm: cleanup do_shmat pasta
  ipc,shm: shorten critical region for shmctl
  ipc,shm: make shmctl_nolock lockless
  ipc,shm: introduce shmctl_nolock
  ipc: drop ipcctl_pre_down
  ipc,shm: shorten critical region in shmctl_down
  ipc,shm: introduce lockless functions to obtain the ipc object
  initmpfs: use initramfs if rootfstype= or root= specified
  initmpfs: make rootfs use tmpfs when CONFIG_TMPFS enabled
  initmpfs: move rootfs code from fs/ramfs/ to init/
  initmpfs: move bdi setup from init_rootfs to init_ramfs
  ...

1 files changed, 30 insertions, 52 deletions

diff --git a/ipc/util.c b/ipc/util.c
index 4704223bfad..e829da9ed01 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -15,6 +15,14 @@
  * Jun 2006 - namespaces ssupport
  *            OpenVZ, SWsoft Inc.
  *            Pavel Emelianov <xemul@openvz.org>
+ *
+ * General sysv ipc locking scheme:
+ *  when doing ipc id lookups, take the ids->rwsem
+ *      rcu_read_lock()
+ *          obtain the ipc object (kern_ipc_perm)
+ *          perform security, capabilities, auditing and permission checks, etc.
+ *          acquire the ipc lock (kern_ipc_perm.lock) throught ipc_lock_object()
+ *             perform data updates (ie: SET, RMID, LOCK/UNLOCK commands)
  */
 
 #include <linux/mm.h>
@@ -119,7 +127,7 @@ __initcall(ipc_init);
  
 void ipc_init_ids(struct ipc_ids *ids)
 {
-	init_rwsem(&ids->rw_mutex);
+	init_rwsem(&ids->rwsem);
 
 	ids->in_use = 0;
 	ids->seq = 0;
@@ -174,7 +182,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
  *	@ids: Identifier set
  *	@key: The key to find
  *	
- *	Requires ipc_ids.rw_mutex locked.
+ *	Requires ipc_ids.rwsem locked.
  *	Returns the LOCKED pointer to the ipc structure if found or NULL
  *	if not.
  *	If key is found ipc points to the owning ipc structure
@@ -197,7 +205,8 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
 			continue;
 		}
 
-		ipc_lock_by_ptr(ipc);
+		rcu_read_lock();
+		ipc_lock_object(ipc);
 		return ipc;
 	}
 
@@ -208,7 +217,7 @@ 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.rw_mutex held.
+ *	Called with ipc_ids.rwsem held.
  */
 
 int ipc_get_maxid(struct ipc_ids *ids)
@@ -246,7 +255,7 @@ int ipc_get_maxid(struct ipc_ids *ids)
  *	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 writer ipc_ids.rw_mutex held.
+ *	Called with writer ipc_ids.rwsem held.
  */
 int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 {
@@ -312,9 +321,9 @@ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
 {
 	int err;
 
-	down_write(&ids->rw_mutex);
+	down_write(&ids->rwsem);
 	err = ops->getnew(ns, params);
-	up_write(&ids->rw_mutex);
+	up_write(&ids->rwsem);
 	return err;
 }
 
@@ -331,7 +340,7 @@ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
  *
  *	On success, the IPC id is returned.
  *
- *	It is called with ipc_ids.rw_mutex and ipcp->lock held.
+ *	It is called with ipc_ids.rwsem and ipcp->lock held.
  */
 static int ipc_check_perms(struct ipc_namespace *ns,
 			   struct kern_ipc_perm *ipcp,
@@ -376,7 +385,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
 	 * 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);
+	down_write(&ids->rwsem);
 	ipcp = ipc_findkey(ids, params->key);
 	if (ipcp == NULL) {
 		/* key not used */
@@ -402,7 +411,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
 		}
 		ipc_unlock(ipcp);
 	}
-	up_write(&ids->rw_mutex);
+	up_write(&ids->rwsem);
 
 	return err;
 }
@@ -413,7 +422,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
  *	@ids: IPC identifier set
  *	@ipcp: ipc perm structure containing the identifier to remove
  *
- *	ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held
+ *	ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
  *	before this function is called, and remain locked on the exit.
  */
  
@@ -621,7 +630,7 @@ struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id)
 }
 
 /**
- * ipc_lock - Lock an ipc structure without rw_mutex held
+ * ipc_lock - Lock an ipc structure without rwsem held
  * @ids: IPC identifier set
  * @id: ipc id to look for
  *
@@ -677,22 +686,6 @@ out:
 	return out;
 }
 
-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
@@ -733,7 +726,7 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
 }
 
 /**
- * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd
  * @ns:  the ipc namespace
  * @ids:  the table of ids where to look for the ipc
  * @id:   the id of the ipc to retrieve
@@ -746,29 +739,13 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
  * 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 the ipc lock held in case of success
- *    or an err-code without any lock held otherwise.
+ *  - returns a pointer to the ipc object or otherwise, the corresponding error.
  *
- * Call holding the both the rw_mutex and the rcu read lock.
+ * Call holding the both the rwsem and the rcu read lock.
  */
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
-				      struct ipc_ids *ids, int id, int cmd,
-				      struct ipc64_perm *perm, int extra_perm)
-{
-	struct kern_ipc_perm *ipcp;
-
-	ipcp = ipcctl_pre_down_nolock(ns, ids, id, cmd, perm, extra_perm);
-	if (IS_ERR(ipcp))
-		goto out;
-
-	spin_lock(&ipcp->lock);
-out:
-	return ipcp;
-}
-
 struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
-					     struct ipc_ids *ids, int id, int cmd,
-					     struct ipc64_perm *perm, int extra_perm)
+					struct ipc_ids *ids, int id, int cmd,
+					struct ipc64_perm *perm, int extra_perm)
 {
 	kuid_t euid;
 	int err = -EPERM;
@@ -846,7 +823,8 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
 		ipc = idr_find(&ids->ipcs_idr, pos);
 		if (ipc != NULL) {
 			*new_pos = pos + 1;
-			ipc_lock_by_ptr(ipc);
+			rcu_read_lock();
+			ipc_lock_object(ipc);
 			return ipc;
 		}
 	}
@@ -884,7 +862,7 @@ static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos)
 	 * Take the lock - this will be released by the corresponding
 	 * call to stop().
 	 */
-	down_read(&ids->rw_mutex);
+	down_read(&ids->rwsem);
 
 	/* pos < 0 is invalid */
 	if (*pos < 0)
@@ -911,7 +889,7 @@ static void sysvipc_proc_stop(struct seq_file *s, void *it)
 
 	ids = &iter->ns->ids[iface->ids];
 	/* Release the lock we took in start() */
-	up_read(&ids->rw_mutex);
+	up_read(&ids->rwsem);
 }
 
 static int sysvipc_proc_show(struct seq_file *s, void *it)