Merge branch 'master' into for-next

Fast-forward merge with Linus to be able to merge patches
based on more recent version of the tree.

3 files changed, 212 insertions, 66 deletions

diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 56410faa455..00fba2bab87 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -31,12 +31,37 @@ static int proc_ipc_dointvec(ctl_table *table, int write,
         void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         struct ctl_table ipc_table;
+
         memcpy(&ipc_table, table, sizeof(ipc_table));
         ipc_table.data = get_ipc(table);
 
         return proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
 }
 
+static int proc_ipc_dointvec_minmax(ctl_table *table, int write,
+        void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+        struct ctl_table ipc_table;
+
+        memcpy(&ipc_table, table, sizeof(ipc_table));
+        ipc_table.data = get_ipc(table);
+
+        return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+}
+
+static int proc_ipc_dointvec_minmax_orphans(ctl_table *table, int write,
+        void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+        struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+        int err = proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+        if (err < 0)
+                return err;
+        if (ns->shm_rmid_forced)
+                shm_destroy_orphaned(ns);
+        return err;
+}
+
 static int proc_ipc_callback_dointvec(ctl_table *table, int write,
         void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -125,6 +150,8 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 #else
 #define proc_ipc_doulongvec_minmax NULL
 #define proc_ipc_dointvec          NULL
+#define proc_ipc_dointvec_minmax   NULL
+#define proc_ipc_dointvec_minmax_orphans   NULL
 #define proc_ipc_callback_dointvec NULL
 #define proc_ipcauto_dointvec_minmax NULL
 #endif
@@ -155,6 +182,15 @@ static struct ctl_table ipc_kern_table[] = {
                 .proc_handler   = proc_ipc_dointvec,
         },
         {
+                .procname       = "shm_rmid_forced",
+                .data           = &init_ipc_ns.shm_rmid_forced,
+                .maxlen         = sizeof(init_ipc_ns.shm_rmid_forced),
+                .mode           = 0644,
+                .proc_handler   = proc_ipc_dointvec_minmax_orphans,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+        {
                 .procname       = "msgmax",
                 .data           = &init_ipc_ns.msg_ctlmax,
                 .maxlen         = sizeof (init_ipc_ns.msg_ctlmax),
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 14fb6d67e6a..ed049ea568f 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -113,72 +113,75 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 {
         struct user_struct *u = current_user();
         struct inode *inode;
+        int ret = -ENOMEM;
 
         inode = new_inode(sb);
-        if (inode) {
-                inode->i_ino = get_next_ino();
-                inode->i_mode = mode;
-                inode->i_uid = current_fsuid();
-                inode->i_gid = current_fsgid();
-                inode->i_mtime = inode->i_ctime = inode->i_atime =
-                                CURRENT_TIME;
+        if (!inode)
+                goto err;
 
-                if (S_ISREG(mode)) {
-                        struct mqueue_inode_info *info;
-                        struct task_struct *p = current;
-                        unsigned long mq_bytes, mq_msg_tblsz;
-
-                        inode->i_fop = &mqueue_file_operations;
-                        inode->i_size = FILENT_SIZE;
-                        /* mqueue specific info */
-                        info = MQUEUE_I(inode);
-                        spin_lock_init(&info->lock);
-                        init_waitqueue_head(&info->wait_q);
-                        INIT_LIST_HEAD(&info->e_wait_q[0].list);
-                        INIT_LIST_HEAD(&info->e_wait_q[1].list);
-                        info->notify_owner = NULL;
-                        info->qsize = 0;
-                        info->user = NULL;      /* set when all is ok */
-                        memset(&info->attr, 0, sizeof(info->attr));
-                        info->attr.mq_maxmsg = ipc_ns->mq_msg_max;
-                        info->attr.mq_msgsize = ipc_ns->mq_msgsize_max;
-                        if (attr) {
-                                info->attr.mq_maxmsg = attr->mq_maxmsg;
-                                info->attr.mq_msgsize = attr->mq_msgsize;
-                        }
-                        mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *);
-                        info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
-                        if (!info->messages)
-                                goto out_inode;
-
-                        mq_bytes = (mq_msg_tblsz +
-                                (info->attr.mq_maxmsg * info->attr.mq_msgsize));
-
-                        spin_lock(&mq_lock);
-                        if (u->mq_bytes + mq_bytes < u->mq_bytes ||
-                            u->mq_bytes + mq_bytes >
-                            task_rlimit(p, RLIMIT_MSGQUEUE)) {
-                                spin_unlock(&mq_lock);
-                                /* mqueue_evict_inode() releases info->messages */
-                                goto out_inode;
-                        }
-                        u->mq_bytes += mq_bytes;
-                        spin_unlock(&mq_lock);
+        inode->i_ino = get_next_ino();
+        inode->i_mode = mode;
+        inode->i_uid = current_fsuid();
+        inode->i_gid = current_fsgid();
+        inode->i_mtime = inode->i_ctime = inode->i_atime = CURRENT_TIME;
+
+        if (S_ISREG(mode)) {
+                struct mqueue_inode_info *info;
+                struct task_struct *p = current;
+                unsigned long mq_bytes, mq_msg_tblsz;
+
+                inode->i_fop = &mqueue_file_operations;
+                inode->i_size = FILENT_SIZE;
+                /* mqueue specific info */
+                info = MQUEUE_I(inode);
+                spin_lock_init(&info->lock);
+                init_waitqueue_head(&info->wait_q);
+                INIT_LIST_HEAD(&info->e_wait_q[0].list);
+                INIT_LIST_HEAD(&info->e_wait_q[1].list);
+                info->notify_owner = NULL;
+                info->qsize = 0;
+                info->user = NULL;      /* set when all is ok */
+                memset(&info->attr, 0, sizeof(info->attr));
+                info->attr.mq_maxmsg = ipc_ns->mq_msg_max;
+                info->attr.mq_msgsize = ipc_ns->mq_msgsize_max;
+                if (attr) {
+                        info->attr.mq_maxmsg = attr->mq_maxmsg;
+                        info->attr.mq_msgsize = attr->mq_msgsize;
+                }
+                mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *);
+                info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
+                if (!info->messages)
+                        goto out_inode;
 
-                        /* all is ok */
-                        info->user = get_uid(u);
-                } else if (S_ISDIR(mode)) {
-                        inc_nlink(inode);
-                        /* Some things misbehave if size == 0 on a directory */
-                        inode->i_size = 2 * DIRENT_SIZE;
-                        inode->i_op = &mqueue_dir_inode_operations;
-                        inode->i_fop = &simple_dir_operations;
+                mq_bytes = (mq_msg_tblsz +
+                        (info->attr.mq_maxmsg * info->attr.mq_msgsize));
+
+                spin_lock(&mq_lock);
+                if (u->mq_bytes + mq_bytes < u->mq_bytes ||
+                    u->mq_bytes + mq_bytes > task_rlimit(p, RLIMIT_MSGQUEUE)) {
+                        spin_unlock(&mq_lock);
+                        /* mqueue_evict_inode() releases info->messages */
+                        ret = -EMFILE;
+                        goto out_inode;
                 }
+                u->mq_bytes += mq_bytes;
+                spin_unlock(&mq_lock);
+
+                /* all is ok */
+                info->user = get_uid(u);
+        } else if (S_ISDIR(mode)) {
+                inc_nlink(inode);
+                /* Some things misbehave if size == 0 on a directory */
+                inode->i_size = 2 * DIRENT_SIZE;
+                inode->i_op = &mqueue_dir_inode_operations;
+                inode->i_fop = &simple_dir_operations;
         }
+
         return inode;
 out_inode:
         iput(inode);
-        return NULL;
+err:
+        return ERR_PTR(ret);
 }
 
 static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
@@ -194,8 +197,8 @@ static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
 
         inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO,
                                 NULL);
-        if (!inode) {
-                error = -ENOMEM;
+        if (IS_ERR(inode)) {
+                error = PTR_ERR(inode);
                 goto out;
         }
 
@@ -315,8 +318,8 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry,
         spin_unlock(&mq_lock);
 
         inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr);
-        if (!inode) {
-                error = -ENOMEM;
+        if (IS_ERR(inode)) {
+                error = PTR_ERR(inode);
                 spin_lock(&mq_lock);
                 ipc_ns->mq_queues_count--;
                 goto out_unlock;
diff --git a/ipc/shm.c b/ipc/shm.c
index 27884adb1a9..02ecf2c078f 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -74,6 +74,7 @@ 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));
 }
@@ -104,9 +105,16 @@ void shm_exit_ns(struct ipc_namespace *ns)
 }
 #endif
 
-void __init shm_init (void)
+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",
@@ -130,6 +138,12 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
         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)
 {
@@ -187,6 +201,23 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *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
@@ -206,14 +237,90 @@ static void shm_close(struct vm_area_struct *vma)
         shp->shm_lprid = task_tgid_vnr(current);
         shp->shm_dtim = get_seconds();
         shp->shm_nattch--;
-        if(shp->shm_nattch == 0 &&
-           shp->shm_perm.mode & SHM_DEST)
+        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;
@@ -404,6 +511,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
         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.
@@ -950,8 +1058,7 @@ out_nattch:
         shp = shm_lock(ns, shmid);
         BUG_ON(IS_ERR(shp));
         shp->shm_nattch--;
-        if(shp->shm_nattch == 0 &&
-           shp->shm_perm.mode & SHM_DEST)
+        if (shm_may_destroy(ns, shp))
                 shm_destroy(ns, shp);
         else
                 shm_unlock(shp);