1 files changed, 351 insertions, 60 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 7f0ab5ee948c..b373322ca497 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -108,8 +108,10 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
-void __put_task_struct(struct task_struct *tsk)
+void __put_task_struct_cb(struct rcu_head *rhp)
 {
+        struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
         WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE)));
         WARN_ON(atomic_read(&tsk->usage));
         WARN_ON(tsk == current);
@@ -446,6 +448,55 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
         }
 }
 
+/*
+ * Allocate a new mm structure and copy contents from the
+ * mm structure of the passed in task structure.
+ */
+static struct mm_struct *dup_mm(struct task_struct *tsk)
+{
+        struct mm_struct *mm, *oldmm = current->mm;
+        int err;
+
+        if (!oldmm)
+                return NULL;
+
+        mm = allocate_mm();
+        if (!mm)
+                goto fail_nomem;
+
+        memcpy(mm, oldmm, sizeof(*mm));
+
+        if (!mm_init(mm))
+                goto fail_nomem;
+
+        if (init_new_context(tsk, mm))
+                goto fail_nocontext;
+
+        err = dup_mmap(mm, oldmm);
+        if (err)
+                goto free_pt;
+
+        mm->hiwater_rss = get_mm_rss(mm);
+        mm->hiwater_vm = mm->total_vm;
+
+        return mm;
+
+free_pt:
+        mmput(mm);
+
+fail_nomem:
+        return NULL;
+
+fail_nocontext:
+        /*
+         * If init_new_context() failed, we cannot use mmput() to free the mm
+         * because it calls destroy_context()
+         */
+        mm_free_pgd(mm);
+        free_mm(mm);
+        return NULL;
+}
+
 static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
 {
         struct mm_struct * mm, *oldmm;
@@ -473,43 +524,17 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
         }
 
         retval = -ENOMEM;
-        mm = allocate_mm();
+        mm = dup_mm(tsk);
         if (!mm)
                 goto fail_nomem;
 
-        /* Copy the current MM stuff.. */
-        memcpy(mm, oldmm, sizeof(*mm));
-        if (!mm_init(mm))
-                goto fail_nomem;
-
-        if (init_new_context(tsk,mm))
-                goto fail_nocontext;
-
-        retval = dup_mmap(mm, oldmm);
-        if (retval)
-                goto free_pt;
-
-        mm->hiwater_rss = get_mm_rss(mm);
-        mm->hiwater_vm = mm->total_vm;
-
 good_mm:
         tsk->mm = mm;
         tsk->active_mm = mm;
         return 0;
 
-free_pt:
-        mmput(mm);
 fail_nomem:
         return retval;
-
-fail_nocontext:
-        /*
-         * If init_new_context() failed, we cannot use mmput() to free the mm
-         * because it calls destroy_context()
-         */
-        mm_free_pgd(mm);
-        free_mm(mm);
-        return retval;
 }
 
 static inline struct fs_struct *__copy_fs_struct(struct fs_struct *old)
@@ -597,32 +622,17 @@ out:
         return newf;
 }
 
-static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
+/*
+ * Allocate a new files structure and copy contents from the
+ * passed in files structure.
+ */
+static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 {
-        struct files_struct *oldf, *newf;
+        struct files_struct *newf;
         struct file **old_fds, **new_fds;
-        int open_files, size, i, error = 0, expand;
+        int open_files, size, i, expand;
         struct fdtable *old_fdt, *new_fdt;
 
-        /*
-         * A background process may not have any files ...
-         */
-        oldf = current->files;
-        if (!oldf)
-                goto out;
-
-        if (clone_flags & CLONE_FILES) {
-                atomic_inc(&oldf->count);
-                goto out;
-        }
-
-        /*
-         * Note: we may be using current for both targets (See exec.c)
-         * This works because we cache current->files (old) as oldf. Don't
-         * break this.
-         */
-        tsk->files = NULL;
-        error = -ENOMEM;
         newf = alloc_files();
         if (!newf)
                 goto out;
@@ -651,9 +661,9 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
         if (expand) {
                 spin_unlock(&oldf->file_lock);
                 spin_lock(&newf->file_lock);
-                error = expand_files(newf, open_files-1);
+                *errorp = expand_files(newf, open_files-1);
                 spin_unlock(&newf->file_lock);
-                if (error < 0)
+                if (*errorp < 0)
                         goto out_release;
                 new_fdt = files_fdtable(newf);
                 /*
@@ -702,10 +712,8 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
                 memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
         }
 
-        tsk->files = newf;
-        error = 0;
 out:
-        return error;
+        return newf;
 
 out_release:
         free_fdset (new_fdt->close_on_exec, new_fdt->max_fdset);
@@ -715,6 +723,40 @@ out_release:
         goto out;
 }
 
+static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
+{
+        struct files_struct *oldf, *newf;
+        int error = 0;
+
+        /*
+         * A background process may not have any files ...
+         */
+        oldf = current->files;
+        if (!oldf)
+                goto out;
+
+        if (clone_flags & CLONE_FILES) {
+                atomic_inc(&oldf->count);
+                goto out;
+        }
+
+        /*
+         * Note: we may be using current for both targets (See exec.c)
+         * This works because we cache current->files (old) as oldf. Don't
+         * break this.
+         */
+        tsk->files = NULL;
+        error = -ENOMEM;
+        newf = dup_fd(oldf, &error);
+        if (!newf)
+                goto out;
+
+        tsk->files = newf;
+        error = 0;
+out:
+        return error;
+}
+
 /*
  *      Helper to unshare the files of the current task.
  *      We don't want to expose copy_files internals to
@@ -1020,6 +1062,12 @@ static task_t *copy_process(unsigned long clone_flags,
         p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
 
         /*
+         * sigaltstack should be cleared when sharing the same VM
+         */
+        if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
+                p->sas_ss_sp = p->sas_ss_size = 0;
+
+        /*
          * Syscall tracing should be turned off in the child regardless
          * of CLONE_PTRACE.
          */
@@ -1083,8 +1131,8 @@ static task_t *copy_process(unsigned long clone_flags,
                 p->real_parent = current;
         p->parent = p->real_parent;
 
+        spin_lock(&current->sighand->siglock);
         if (clone_flags & CLONE_THREAD) {
-                spin_lock(&current->sighand->siglock);
                 /*
                  * Important: if an exit-all has been started then
                  * do not create this new thread - the whole thread
@@ -1122,8 +1170,6 @@ static task_t *copy_process(unsigned long clone_flags,
                          */
                         p->it_prof_expires = jiffies_to_cputime(1);
                 }
-
-                spin_unlock(&current->sighand->siglock);
         }
 
         /*
@@ -1135,8 +1181,6 @@ static task_t *copy_process(unsigned long clone_flags,
         if (unlikely(p->ptrace & PT_PTRACED))
                 __ptrace_link(p, current->parent);
 
-        attach_pid(p, PIDTYPE_PID, p->pid);
-        attach_pid(p, PIDTYPE_TGID, p->tgid);
         if (thread_group_leader(p)) {
                 p->signal->tty = current->signal->tty;
                 p->signal->pgrp = process_group(current);
@@ -1146,9 +1190,12 @@ static task_t *copy_process(unsigned long clone_flags,
                 if (p->pid)
                         __get_cpu_var(process_counts)++;
         }
+        attach_pid(p, PIDTYPE_TGID, p->tgid);
+        attach_pid(p, PIDTYPE_PID, p->pid);
 
         nr_threads++;
         total_forks++;
+        spin_unlock(&current->sighand->siglock);
         write_unlock_irq(&tasklist_lock);
         proc_fork_connector(p);
         return p;
@@ -1323,3 +1370,247 @@ void __init proc_caches_init(void)
                         sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
                         SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
 }
+
+
+/*
+ * Check constraints on flags passed to the unshare system call and
+ * force unsharing of additional process context as appropriate.
+ */
+static inline void check_unshare_flags(unsigned long *flags_ptr)
+{
+        /*
+         * If unsharing a thread from a thread group, must also
+         * unshare vm.
+         */
+        if (*flags_ptr & CLONE_THREAD)
+                *flags_ptr |= CLONE_VM;
+
+        /*
+         * If unsharing vm, must also unshare signal handlers.
+         */
+        if (*flags_ptr & CLONE_VM)
+                *flags_ptr |= CLONE_SIGHAND;
+
+        /*
+         * If unsharing signal handlers and the task was created
+         * using CLONE_THREAD, then must unshare the thread
+         */
+        if ((*flags_ptr & CLONE_SIGHAND) &&
+            (atomic_read(&current->signal->count) > 1))
+                *flags_ptr |= CLONE_THREAD;
+
+        /*
+         * If unsharing namespace, must also unshare filesystem information.
+         */
+        if (*flags_ptr & CLONE_NEWNS)
+                *flags_ptr |= CLONE_FS;
+}
+
+/*
+ * Unsharing of tasks created with CLONE_THREAD is not supported yet
+ */
+static int unshare_thread(unsigned long unshare_flags)
+{
+        if (unshare_flags & CLONE_THREAD)
+                return -EINVAL;
+
+        return 0;
+}
+
+/*
+ * Unshare the filesystem structure if it is being shared
+ */
+static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
+{
+        struct fs_struct *fs = current->fs;
+
+        if ((unshare_flags & CLONE_FS) &&
+            (fs && atomic_read(&fs->count) > 1)) {
+                *new_fsp = __copy_fs_struct(current->fs);
+                if (!*new_fsp)
+                        return -ENOMEM;
+        }
+
+        return 0;
+}
+
+/*
+ * Unshare the namespace structure if it is being shared
+ */
+static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs)
+{
+        struct namespace *ns = current->namespace;
+
+        if ((unshare_flags & CLONE_NEWNS) &&
+            (ns && atomic_read(&ns->count) > 1)) {
+                if (!capable(CAP_SYS_ADMIN))
+                        return -EPERM;
+
+                *new_nsp = dup_namespace(current, new_fs ? new_fs : current->fs);
+                if (!*new_nsp)
+                        return -ENOMEM;
+        }
+
+        return 0;
+}
+
+/*
+ * Unsharing of sighand for tasks created with CLONE_SIGHAND is not
+ * supported yet
+ */
+static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp)
+{
+        struct sighand_struct *sigh = current->sighand;
+
+        if ((unshare_flags & CLONE_SIGHAND) &&
+            (sigh && atomic_read(&sigh->count) > 1))
+                return -EINVAL;
+        else
+                return 0;
+}
+
+/*
+ * Unshare vm if it is being shared
+ */
+static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
+{
+        struct mm_struct *mm = current->mm;
+
+        if ((unshare_flags & CLONE_VM) &&
+            (mm && atomic_read(&mm->mm_users) > 1)) {
+                return -EINVAL;
+        }
+
+        return 0;
+}
+
+/*
+ * Unshare file descriptor table if it is being shared
+ */
+static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
+{
+        struct files_struct *fd = current->files;
+        int error = 0;
+
+        if ((unshare_flags & CLONE_FILES) &&
+            (fd && atomic_read(&fd->count) > 1)) {
+                *new_fdp = dup_fd(fd, &error);
+                if (!*new_fdp)
+                        return error;
+        }
+
+        return 0;
+}
+
+/*
+ * Unsharing of semundo for tasks created with CLONE_SYSVSEM is not
+ * supported yet
+ */
+static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **new_ulistp)
+{
+        if (unshare_flags & CLONE_SYSVSEM)
+                return -EINVAL;
+
+        return 0;
+}
+
+/*
+ * unshare allows a process to 'unshare' part of the process
+ * context which was originally shared using clone.  copy_*
+ * functions used by do_fork() cannot be used here directly
+ * because they modify an inactive task_struct that is being
+ * constructed. Here we are modifying the current, active,
+ * task_struct.
+ */
+asmlinkage long sys_unshare(unsigned long unshare_flags)
+{
+        int err = 0;
+        struct fs_struct *fs, *new_fs = NULL;
+        struct namespace *ns, *new_ns = NULL;
+        struct sighand_struct *sigh, *new_sigh = NULL;
+        struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
+        struct files_struct *fd, *new_fd = NULL;
+        struct sem_undo_list *new_ulist = NULL;
+
+        check_unshare_flags(&unshare_flags);
+
+        if ((err = unshare_thread(unshare_flags)))
+                goto bad_unshare_out;
+        if ((err = unshare_fs(unshare_flags, &new_fs)))
+                goto bad_unshare_cleanup_thread;
+        if ((err = unshare_namespace(unshare_flags, &new_ns, new_fs)))
+                goto bad_unshare_cleanup_fs;
+        if ((err = unshare_sighand(unshare_flags, &new_sigh)))
+                goto bad_unshare_cleanup_ns;
+        if ((err = unshare_vm(unshare_flags, &new_mm)))
+                goto bad_unshare_cleanup_sigh;
+        if ((err = unshare_fd(unshare_flags, &new_fd)))
+                goto bad_unshare_cleanup_vm;
+        if ((err = unshare_semundo(unshare_flags, &new_ulist)))
+                goto bad_unshare_cleanup_fd;
+
+        if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist) {
+
+                task_lock(current);
+
+                if (new_fs) {
+                        fs = current->fs;
+                        current->fs = new_fs;
+                        new_fs = fs;
+                }
+
+                if (new_ns) {
+                        ns = current->namespace;
+                        current->namespace = new_ns;
+                        new_ns = ns;
+                }
+
+                if (new_sigh) {
+                        sigh = current->sighand;
+                        rcu_assign_pointer(current->sighand, new_sigh);
+                        new_sigh = sigh;
+                }
+
+                if (new_mm) {
+                        mm = current->mm;
+                        active_mm = current->active_mm;
+                        current->mm = new_mm;
+                        current->active_mm = new_mm;
+                        activate_mm(active_mm, new_mm);
+                        new_mm = mm;
+                }
+
+                if (new_fd) {
+                        fd = current->files;
+                        current->files = new_fd;
+                        new_fd = fd;
+                }
+
+                task_unlock(current);
+        }
+
+bad_unshare_cleanup_fd:
+        if (new_fd)
+                put_files_struct(new_fd);
+
+bad_unshare_cleanup_vm:
+        if (new_mm)
+                mmput(new_mm);
+
+bad_unshare_cleanup_sigh:
+        if (new_sigh)
+                if (atomic_dec_and_test(&new_sigh->count))
+                        kmem_cache_free(sighand_cachep, new_sigh);
+
+bad_unshare_cleanup_ns:
+        if (new_ns)
+                put_namespace(new_ns);
+
+bad_unshare_cleanup_fs:
+        if (new_fs)
+                put_fs_struct(new_fs);
+
+bad_unshare_cleanup_thread:
+bad_unshare_out:
+        return err;
+}