1 files changed, 158 insertions, 119 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 47c15840a381..1415dc4598ae 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/completion.h>
-#include <linux/mnt_namespace.h>
 #include <linux/personality.h>
 #include <linux/mempolicy.h>
 #include <linux/sem.h>
@@ -50,6 +49,7 @@
 #include <linux/ftrace.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
+#include <linux/ksm.h>
 #include <linux/acct.h>
 #include <linux/tsacct_kern.h>
 #include <linux/cn_proc.h>
@@ -60,8 +60,11 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
-#include <trace/sched.h>
+#include <linux/fs_struct.h>
 #include <linux/magic.h>
+#include <linux/perf_event.h>
+#include <linux/posix-timers.h>
+#include <linux/user-return-notifier.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -70,6 +73,8 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+#include <trace/events/sched.h>
+
 /*
  * Protected counters by write_lock_irq(&tasklist_lock)
  */
@@ -82,14 +87,12 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
-DEFINE_TRACE(sched_process_fork);
-
 int nr_processes(void)
 {
         int cpu;
         int total = 0;
 
-        for_each_online_cpu(cpu)
+        for_each_possible_cpu(cpu)
                 total += per_cpu(process_counts, cpu);
 
         return total;
@@ -136,9 +139,17 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+static void account_kernel_stack(struct thread_info *ti, int account)
+{
+        struct zone *zone = page_zone(virt_to_page(ti));
+
+        mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+}
+
 void free_task(struct task_struct *tsk)
 {
         prop_local_destroy_single(&tsk->dirties);
+        account_kernel_stack(tsk->stack, -1);
         free_thread_info(tsk->stack);
         rt_mutex_debug_task_free(tsk);
         ftrace_graph_exit_task(tsk);
@@ -152,8 +163,7 @@ void __put_task_struct(struct task_struct *tsk)
         WARN_ON(atomic_read(&tsk->usage));
         WARN_ON(tsk == current);
 
-        put_cred(tsk->real_cred);
-        put_cred(tsk->cred);
+        exit_creds(tsk);
         delayacct_tsk_free(tsk);
 
         if (!profile_handoff_task(tsk))
@@ -177,7 +187,7 @@ void __init fork_init(unsigned long mempages)
         /* create a slab on which task_structs can be allocated */
         task_struct_cachep =
                 kmem_cache_create("task_struct", sizeof(struct task_struct),
-                        ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL);
+                        ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL);
 #endif
 
         /* do the arch specific task caches init */
@@ -240,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
                 goto out;
 
         setup_thread_stack(tsk, orig);
+        clear_user_return_notifier(tsk);
         stackend = end_of_stack(tsk);
         *stackend = STACK_END_MAGIC;    /* for overflow detection */
 
@@ -254,6 +265,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
         tsk->btrace_seq = 0;
 #endif
         tsk->splice_pipe = NULL;
+
+        account_kernel_stack(ti, 1);
+
         return tsk;
 
 out:
@@ -289,6 +303,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
         rb_link = &mm->mm_rb.rb_node;
         rb_parent = NULL;
         pprev = &mm->mmap;
+        retval = ksm_fork(mm, oldmm);
+        if (retval)
+                goto out;
 
         for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
                 struct file *file;
@@ -419,22 +436,30 @@ __setup("coredump_filter=", coredump_filter_setup);
 
 #include <linux/init_task.h>
 
+static void mm_init_aio(struct mm_struct *mm)
+{
+#ifdef CONFIG_AIO
+        spin_lock_init(&mm->ioctx_lock);
+        INIT_HLIST_HEAD(&mm->ioctx_list);
+#endif
+}
+
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
         atomic_set(&mm->mm_users, 1);
         atomic_set(&mm->mm_count, 1);
         init_rwsem(&mm->mmap_sem);
         INIT_LIST_HEAD(&mm->mmlist);
-        mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
+        mm->flags = (current->mm) ?
+                (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
         mm->core_state = NULL;
         mm->nr_ptes = 0;
         set_mm_counter(mm, file_rss, 0);
         set_mm_counter(mm, anon_rss, 0);
         spin_lock_init(&mm->page_table_lock);
-        spin_lock_init(&mm->ioctx_lock);
-        INIT_HLIST_HEAD(&mm->ioctx_list);
         mm->free_area_cache = TASK_UNMAPPED_BASE;
         mm->cached_hole_size = ~0UL;
+        mm_init_aio(mm);
         mm_init_owner(mm, p);
 
         if (likely(!mm_alloc_pgd(mm))) {
@@ -486,6 +511,7 @@ void mmput(struct mm_struct *mm)
 
         if (atomic_dec_and_test(&mm->mm_users)) {
                 exit_aio(mm);
+                ksm_exit(mm);
                 exit_mmap(mm);
                 set_mm_exe_file(mm, NULL);
                 if (!list_empty(&mm->mmlist)) {
@@ -494,6 +520,8 @@ void mmput(struct mm_struct *mm)
                         spin_unlock(&mmlist_lock);
                 }
                 put_swap_token(mm);
+                if (mm->binfmt)
+                        module_put(mm->binfmt->module);
                 mmdrop(mm);
         }
 }
@@ -544,12 +572,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 
         /* Get rid of any futexes when releasing the mm */
 #ifdef CONFIG_FUTEX
-        if (unlikely(tsk->robust_list))
+        if (unlikely(tsk->robust_list)) {
                 exit_robust_list(tsk);
+                tsk->robust_list = NULL;
+        }
 #ifdef CONFIG_COMPAT
-        if (unlikely(tsk->compat_robust_list))
+        if (unlikely(tsk->compat_robust_list)) {
                 compat_exit_robust_list(tsk);
+                tsk->compat_robust_list = NULL;
+        }
 #endif
+        if (unlikely(!list_empty(&tsk->pi_state_list)))
+                exit_pi_state_list(tsk);
 #endif
 
         /* Get rid of any cached register state */
@@ -567,18 +601,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
          * the value intact in a core dump, and to save the unnecessary
          * trouble otherwise.  Userland only wants this done for a sys_exit.
          */
-        if (tsk->clear_child_tid
-            && !(tsk->flags & PF_SIGNALED)
-            && atomic_read(&mm->mm_users) > 1) {
-                u32 __user * tidptr = tsk->clear_child_tid;
+        if (tsk->clear_child_tid) {
+                if (!(tsk->flags & PF_SIGNALED) &&
+                    atomic_read(&mm->mm_users) > 1) {
+                        /*
+                         * We don't check the error code - if userspace has
+                         * not set up a proper pointer then tough luck.
+                         */
+                        put_user(0, tsk->clear_child_tid);
+                        sys_futex(tsk->clear_child_tid, FUTEX_WAKE,
+                                        1, NULL, NULL, 0);
+                }
                 tsk->clear_child_tid = NULL;
-
-                /*
-                 * We don't check the error code - if userspace has
-                 * not set up a proper pointer then tough luck.
-                 */
-                put_user(0, tidptr);
-                sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0);
         }
 }
 
@@ -619,9 +653,14 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
         mm->hiwater_rss = get_mm_rss(mm);
         mm->hiwater_vm = mm->total_vm;
 
+        if (mm->binfmt && !try_module_get(mm->binfmt->module))
+                goto free_pt;
+
         return mm;
 
 free_pt:
+        /* don't put binfmt in mmput, we haven't got module yet */
+        mm->binfmt = NULL;
         mmput(mm);
 
 fail_nomem:
@@ -644,6 +683,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
 
         tsk->min_flt = tsk->maj_flt = 0;
         tsk->nvcsw = tsk->nivcsw = 0;
+#ifdef CONFIG_DETECT_HUNG_TASK
+        tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
+#endif
 
         tsk->mm = NULL;
         tsk->active_mm = NULL;
@@ -681,38 +723,21 @@ fail_nomem:
         return retval;
 }
 
-static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
-{
-        struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
-        /* We don't need to lock fs - think why ;-) */
-        if (fs) {
-                atomic_set(&fs->count, 1);
-                rwlock_init(&fs->lock);
-                fs->umask = old->umask;
-                read_lock(&old->lock);
-                fs->root = old->root;
-                path_get(&old->root);
-                fs->pwd = old->pwd;
-                path_get(&old->pwd);
-                read_unlock(&old->lock);
-        }
-        return fs;
-}
-
-struct fs_struct *copy_fs_struct(struct fs_struct *old)
-{
-        return __copy_fs_struct(old);
-}
-
-EXPORT_SYMBOL_GPL(copy_fs_struct);
-
 static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 {
+        struct fs_struct *fs = current->fs;
         if (clone_flags & CLONE_FS) {
-                atomic_inc(&current->fs->count);
+                /* tsk->fs is already what we want */
+                write_lock(&fs->lock);
+                if (fs->in_exec) {
+                        write_unlock(&fs->lock);
+                        return -EAGAIN;
+                }
+                fs->users++;
+                write_unlock(&fs->lock);
                 return 0;
         }
-        tsk->fs = __copy_fs_struct(current->fs);
+        tsk->fs = copy_fs_struct(fs);
         if (!tsk->fs)
                 return -ENOMEM;
         return 0;
@@ -803,16 +828,22 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
         thread_group_cputime_init(sig);
 
         /* Expiration times and increments. */
-        sig->it_virt_expires = cputime_zero;
-        sig->it_virt_incr = cputime_zero;
-        sig->it_prof_expires = cputime_zero;
-        sig->it_prof_incr = cputime_zero;
+        sig->it[CPUCLOCK_PROF].expires = cputime_zero;
+        sig->it[CPUCLOCK_PROF].incr = cputime_zero;
+        sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
+        sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
 
         /* Cached expiration times. */
         sig->cputime_expires.prof_exp = cputime_zero;
         sig->cputime_expires.virt_exp = cputime_zero;
         sig->cputime_expires.sched_exp = 0;
 
+        if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
+                sig->cputime_expires.prof_exp =
+                        secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+                sig->cputimer.running = 1;
+        }
+
         /* The timer lists. */
         INIT_LIST_HEAD(&sig->cpu_timers[0]);
         INIT_LIST_HEAD(&sig->cpu_timers[1]);
@@ -823,16 +854,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
         struct signal_struct *sig;
 
-        if (clone_flags & CLONE_THREAD) {
-                atomic_inc(&current->signal->count);
-                atomic_inc(&current->signal->live);
+        if (clone_flags & CLONE_THREAD)
                 return 0;
-        }
-        sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
-
-        if (sig)
-                posix_cpu_timers_init_group(sig);
 
+        sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
         tsk->signal = sig;
         if (!sig)
                 return -ENOMEM;
@@ -841,6 +866,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         atomic_set(&sig->live, 1);
         init_waitqueue_head(&sig->wait_chldexit);
         sig->flags = 0;
+        if (clone_flags & CLONE_NEWPID)
+                sig->flags |= SIGNAL_UNKILLABLE;
         sig->group_exit_code = 0;
         sig->group_exit_task = NULL;
         sig->group_stop_count = 0;
@@ -859,9 +886,13 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
         sig->gtime = cputime_zero;
         sig->cgtime = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+        sig->prev_utime = sig->prev_stime = cputime_zero;
+#endif
         sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
         sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
         sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
+        sig->maxrss = sig->cmaxrss = 0;
         task_io_accounting_init(&sig->ioac);
         sig->sum_sched_runtime = 0;
         taskstats_tgid_init(sig);
@@ -870,10 +901,14 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
         task_unlock(current->group_leader);
 
+        posix_cpu_timers_init_group(sig);
+
         acct_init_pacct(&sig->pacct);
 
         tty_audit_fork(sig);
 
+        sig->oom_adj = current->signal->oom_adj;
+
         return 0;
 }
 
@@ -884,16 +919,6 @@ void __cleanup_signal(struct signal_struct *sig)
         kmem_cache_free(signal_cachep, sig);
 }
 
-static void cleanup_signal(struct task_struct *tsk)
-{
-        struct signal_struct *sig = tsk->signal;
-
-        atomic_dec(&sig->live);
-
-        if (atomic_dec_and_test(&sig->count))
-                __cleanup_signal(sig);
-}
-
 static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 {
         unsigned long new_flags = p->flags;
@@ -979,6 +1004,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
                 return ERR_PTR(-EINVAL);
 
+        /*
+         * Siblings of global init remain as zombies on exit since they are
+         * not reaped by their parent (swapper). To solve this and to avoid
+         * multi-rooted process trees, prevent global and container-inits
+         * from creating siblings.
+         */
+        if ((clone_flags & CLONE_PARENT) &&
+                                current->signal->flags & SIGNAL_UNKILLABLE)
+                return ERR_PTR(-EINVAL);
+
         retval = security_task_create(clone_flags);
         if (retval)
                 goto fork_out;
@@ -988,6 +1023,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (!p)
                 goto fork_out;
 
+        ftrace_graph_init_task(p);
+
         rt_mutex_init_task(p);
 
 #ifdef CONFIG_PROVE_LOCKING
@@ -1018,22 +1055,15 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (!try_module_get(task_thread_info(p)->exec_domain->module))
                 goto bad_fork_cleanup_count;
 
-        if (p->binfmt && !try_module_get(p->binfmt->module))
-                goto bad_fork_cleanup_put_domain;
-
         p->did_exec = 0;
         delayacct_tsk_init(p);  /* Must remain after dup_task_struct() */
         copy_flags(clone_flags, p);
         INIT_LIST_HEAD(&p->children);
         INIT_LIST_HEAD(&p->sibling);
-#ifdef CONFIG_PREEMPT_RCU
-        p->rcu_read_lock_nesting = 0;
-        p->rcu_flipctr_idx = 0;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
+        rcu_copy_process(p);
         p->vfork_done = NULL;
         spin_lock_init(&p->alloc_lock);
 
-        clear_tsk_thread_flag(p, TIF_SIGPENDING);
         init_sigpending(&p->pending);
 
         p->utime = cputime_zero;
@@ -1041,16 +1071,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         p->gtime = cputime_zero;
         p->utimescaled = cputime_zero;
         p->stimescaled = cputime_zero;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
         p->prev_utime = cputime_zero;
         p->prev_stime = cputime_zero;
+#endif
 
         p->default_timer_slack_ns = current->timer_slack_ns;
 
-#ifdef CONFIG_DETECT_SOFTLOCKUP
-        p->last_switch_count = 0;
-        p->last_switch_timestamp = 0;
-#endif
-
         task_io_accounting_init(&p->ioac);
         acct_clear_integrals(p);
 
@@ -1100,12 +1127,18 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
         p->blocked_on = NULL; /* not blocked yet */
 #endif
-        if (unlikely(current->ptrace))
-                ptrace_fork(p, clone_flags);
+
+        p->bts = NULL;
+
+        p->stack_start = stack_start;
 
         /* Perform scheduler related setup. Assign this task to a CPU. */
         sched_fork(p, clone_flags);
 
+        retval = perf_event_init_task(p);
+        if (retval)
+                goto bad_fork_cleanup_policy;
+
         if ((retval = audit_alloc(p)))
                 goto bad_fork_cleanup_policy;
         /* copy all the process information */
@@ -1125,7 +1158,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 goto bad_fork_cleanup_mm;
         if ((retval = copy_io(clone_flags, p)))
                 goto bad_fork_cleanup_namespaces;
-        retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
+        retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
         if (retval)
                 goto bad_fork_cleanup_io;
 
@@ -1142,8 +1175,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 }
         }
 
-        ftrace_graph_init_task(p);
-
         p->pid = pid_nr(pid);
         p->tgid = p->pid;
         if (clone_flags & CLONE_THREAD)
@@ -1152,7 +1183,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (current->nsproxy != p->nsproxy) {
                 retval = ns_cgroup_clone(p, pid);
                 if (retval)
-                        goto bad_fork_free_graph;
+                        goto bad_fork_free_pid;
         }
 
         p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -1244,10 +1275,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 spin_unlock(&current->sighand->siglock);
                 write_unlock_irq(&tasklist_lock);
                 retval = -ERESTARTNOINTR;
-                goto bad_fork_free_graph;
+                goto bad_fork_free_pid;
         }
 
         if (clone_flags & CLONE_THREAD) {
+                atomic_inc(&current->signal->count);
+                atomic_inc(&current->signal->live);
                 p->group_leader = current->group_leader;
                 list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
         }
@@ -1263,8 +1296,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                         p->signal->leader_pid = pid;
                         tty_kref_put(p->signal->tty);
                         p->signal->tty = tty_kref_get(current->signal->tty);
-                        set_task_pgrp(p, task_pgrp_nr(current));
-                        set_task_session(p, task_session_nr(current));
                         attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
                         attach_pid(p, PIDTYPE_SID, task_session(current));
                         list_add_tail_rcu(&p->tasks, &init_task.tasks);
@@ -1279,22 +1310,23 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         write_unlock_irq(&tasklist_lock);
         proc_fork_connector(p);
         cgroup_post_fork(p);
+        perf_event_fork(p);
         return p;
 
-bad_fork_free_graph:
-        ftrace_graph_exit_task(p);
 bad_fork_free_pid:
         if (pid != &init_struct_pid)
                 free_pid(pid);
 bad_fork_cleanup_io:
-        put_io_context(p->io_context);
+        if (p->io_context)
+                exit_io_context(p);
 bad_fork_cleanup_namespaces:
         exit_task_namespaces(p);
 bad_fork_cleanup_mm:
         if (p->mm)
                 mmput(p->mm);
 bad_fork_cleanup_signal:
-        cleanup_signal(p);
+        if (!(clone_flags & CLONE_THREAD))
+                __cleanup_signal(p->signal);
 bad_fork_cleanup_sighand:
         __cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:
@@ -1306,20 +1338,17 @@ bad_fork_cleanup_semundo:
 bad_fork_cleanup_audit:
         audit_free(p);
 bad_fork_cleanup_policy:
+        perf_event_free_task(p);
 #ifdef CONFIG_NUMA
         mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
 #endif
         cgroup_exit(p, cgroup_callbacks_done);
         delayacct_tsk_free(p);
-        if (p->binfmt)
-                module_put(p->binfmt->module);
-bad_fork_cleanup_put_domain:
         module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
         atomic_dec(&p->cred->user->processes);
-        put_cred(p->real_cred);
-        put_cred(p->cred);
+        exit_creds(p);
 bad_fork_free:
         free_task(p);
 fork_out:
@@ -1422,7 +1451,7 @@ long do_fork(unsigned long clone_flags,
                 }
 
                 audit_finish_fork(p);
-                tracehook_report_clone(trace, regs, clone_flags, nr, p);
+                tracehook_report_clone(regs, clone_flags, nr, p);
 
                 /*
                  * We set PF_STARTING at creation in case tracing wants to
@@ -1474,20 +1503,21 @@ void __init proc_caches_init(void)
 {
         sighand_cachep = kmem_cache_create("sighand_cache",
                         sizeof(struct sighand_struct), 0,
-                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU,
-                        sighand_ctor);
+                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
+                        SLAB_NOTRACK, sighand_ctor);
         signal_cachep = kmem_cache_create("signal_cache",
                         sizeof(struct signal_struct), 0,
-                        SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
         files_cachep = kmem_cache_create("files_cache",
                         sizeof(struct files_struct), 0,
-                        SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
         fs_cachep = kmem_cache_create("fs_cache",
                         sizeof(struct fs_struct), 0,
-                        SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
         mm_cachep = kmem_cache_create("mm_struct",
                         sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
-                        SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+                        SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+        vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
         mmap_init();
 }
 
@@ -1543,12 +1573,16 @@ 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;
-        }
+        if (!(unshare_flags & CLONE_FS) || !fs)
+                return 0;
+
+        /* don't need lock here; in the worst case we'll do useless copy */
+        if (fs->users == 1)
+                return 0;
+
+        *new_fsp = copy_fs_struct(fs);
+        if (!*new_fsp)
+                return -ENOMEM;
 
         return 0;
 }
@@ -1664,8 +1698,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 
                 if (new_fs) {
                         fs = current->fs;
+                        write_lock(&fs->lock);
                         current->fs = new_fs;
-                        new_fs = fs;
+                        if (--fs->users)
+                                new_fs = NULL;
+                        else
+                                new_fs = fs;
+                        write_unlock(&fs->lock);
                 }
 
                 if (new_mm) {
@@ -1704,7 +1743,7 @@ bad_unshare_cleanup_sigh:
 
 bad_unshare_cleanup_fs:
         if (new_fs)
-                put_fs_struct(new_fs);
+                free_fs_struct(new_fs);
 
 bad_unshare_cleanup_thread:
 bad_unshare_out: