#include <linux/uprobes.h>
#include <linux/aio.h>
#include <linux/compiler.h>
+#include <linux/sysctl.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <trace/events/task.h>
/*
+ * Minimum number of threads to boot the kernel
+ */
+#define MIN_THREADS 20
+
+/*
+ * Maximum number of threads
+ */
+#define MAX_THREADS FUTEX_TID_MASK
+
+/*
* Protected counters by write_lock_irq(&tasklist_lock)
*/
unsigned long total_forks; /* Handle normal Linux uptimes. */
void __init __weak arch_task_cache_init(void) { }
-void __init fork_init(unsigned long mempages)
+/*
+ * set_max_threads
+ */
+static void set_max_threads(unsigned int max_threads_suggested)
+{
+ u64 threads;
+
+ /*
+ * The number of threads shall be limited such that the thread
+ * structures may only consume a small part of the available memory.
+ */
+ if (fls64(totalram_pages) + fls64(PAGE_SIZE) > 64)
+ threads = MAX_THREADS;
+ else
+ threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
+ (u64) THREAD_SIZE * 8UL);
+
+ if (threads > max_threads_suggested)
+ threads = max_threads_suggested;
+
+ max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
+}
+
+void __init fork_init(void)
{
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
/* do the arch specific task caches init */
arch_task_cache_init();
- /*
- * The default maximum number of threads is set to a safe
- * value: the thread structures can take up at most half
- * of memory.
- */
- max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE);
-
- /*
- * we need to allow at least 20 threads to boot a system
- */
- if (max_threads < 20)
- max_threads = 20;
+ set_max_threads(MAX_THREADS);
init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
*/
down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
+ /* No ordering required: file already has been exposed. */
+ RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+
mm->total_vm = oldmm->total_vm;
mm->shared_vm = oldmm->shared_vm;
mm->exec_vm = oldmm->exec_vm;
pgd_free(mm, mm->pgd);
}
#else
-#define dup_mmap(mm, oldmm) (0)
+static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+ down_write(&oldmm->mmap_sem);
+ RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+ up_write(&oldmm->mmap_sem);
+ return 0;
+}
#define mm_alloc_pgd(mm) (0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */
}
EXPORT_SYMBOL_GPL(mmput);
+/**
+ * set_mm_exe_file - change a reference to the mm's executable file
+ *
+ * This changes mm's executable file (shown as symlink /proc/[pid]/exe).
+ *
+ * Main users are mmput() and sys_execve(). Callers prevent concurrent
+ * invocations: in mmput() nobody alive left, in execve task is single
+ * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
+ * mm->exe_file, but does so without using set_mm_exe_file() in order
+ * to do avoid the need for any locks.
+ */
void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
+ struct file *old_exe_file;
+
+ /*
+ * It is safe to dereference the exe_file without RCU as
+ * this function is only called if nobody else can access
+ * this mm -- see comment above for justification.
+ */
+ old_exe_file = rcu_dereference_raw(mm->exe_file);
+
if (new_exe_file)
get_file(new_exe_file);
- if (mm->exe_file)
- fput(mm->exe_file);
- mm->exe_file = new_exe_file;
+ rcu_assign_pointer(mm->exe_file, new_exe_file);
+ if (old_exe_file)
+ fput(old_exe_file);
}
+/**
+ * get_mm_exe_file - acquire a reference to the mm's executable file
+ *
+ * Returns %NULL if mm has no associated executable file.
+ * User must release file via fput().
+ */
struct file *get_mm_exe_file(struct mm_struct *mm)
{
struct file *exe_file;
- /* We need mmap_sem to protect against races with removal of exe_file */
- down_read(&mm->mmap_sem);
- exe_file = mm->exe_file;
- if (exe_file)
- get_file(exe_file);
- up_read(&mm->mmap_sem);
+ rcu_read_lock();
+ exe_file = rcu_dereference(mm->exe_file);
+ if (exe_file && !get_file_rcu(exe_file))
+ exe_file = NULL;
+ rcu_read_unlock();
return exe_file;
}
-
-static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
-{
- /* It's safe to write the exe_file pointer without exe_file_lock because
- * this is called during fork when the task is not yet in /proc */
- newmm->exe_file = get_mm_exe_file(oldmm);
-}
+EXPORT_SYMBOL(get_mm_exe_file);
/**
* get_task_mm - acquire a reference to the task's mm
if (!mm_init(mm, tsk))
goto fail_nomem;
- dup_mm_exe_file(oldmm, mm);
-
err = dup_mmap(mm, oldmm);
if (err)
goto free_pt;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
- if (!try_module_get(task_thread_info(p)->exec_domain->module))
- goto bad_fork_cleanup_count;
-
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
p->flags |= PF_FORKNOEXEC;
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
- retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
- if (!pid)
+ if (IS_ERR(pid)) {
+ retval = PTR_ERR(pid);
goto bad_fork_cleanup_io;
+ }
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
if (clone_flags & CLONE_THREAD)
threadgroup_change_end(current);
delayacct_tsk_free(p);
- module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
exit_creds(p);
CLONE_NEWUSER|CLONE_NEWPID))
return -EINVAL;
/*
- * Not implemented, but pretend it works if there is nothing to
- * unshare. Note that unsharing CLONE_THREAD or CLONE_SIGHAND
- * needs to unshare vm.
+ * Not implemented, but pretend it works if there is nothing
+ * to unshare. Note that unsharing the address space or the
+ * signal handlers also need to unshare the signal queues (aka
+ * CLONE_THREAD).
*/
if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) {
- /* FIXME: get_task_mm() increments ->mm_users */
- if (atomic_read(¤t->mm->mm_users) > 1)
+ if (!thread_group_empty(current))
+ return -EINVAL;
+ }
+ if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) {
+ if (atomic_read(¤t->sighand->count) > 1)
+ return -EINVAL;
+ }
+ if (unshare_flags & CLONE_VM) {
+ if (!current_is_single_threaded())
return -EINVAL;
}
if (unshare_flags & CLONE_NEWUSER)
unshare_flags |= CLONE_THREAD | CLONE_FS;
/*
- * If unsharing a thread from a thread group, must also unshare vm.
- */
- if (unshare_flags & CLONE_THREAD)
- unshare_flags |= CLONE_VM;
- /*
* If unsharing vm, must also unshare signal handlers.
*/
if (unshare_flags & CLONE_VM)
unshare_flags |= CLONE_SIGHAND;
/*
+ * If unsharing a signal handlers, must also unshare the signal queues.
+ */
+ if (unshare_flags & CLONE_SIGHAND)
+ unshare_flags |= CLONE_THREAD;
+ /*
* If unsharing namespace, must also unshare filesystem information.
*/
if (unshare_flags & CLONE_NEWNS)
task_unlock(task);
return 0;
}
+
+int sysctl_max_threads(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table t;
+ int ret;
+ int threads = max_threads;
+ int min = MIN_THREADS;
+ int max = MAX_THREADS;
+
+ t = *table;
+ t.data = &threads;
+ t.extra1 = &min;
+ t.extra2 = &max;
+
+ ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
+ set_max_threads(threads);
+
+ return 0;
+}