Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

[deliverable/linux.git] / kernel / fork.c

diff --git a/kernel/fork.c b/kernel/fork.c
index 8807a129711bf78053bd9b07ad6fe36bb9c2f592..03c1eaaa6ef56f56a670488eaf572eb8c6f58d4e 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -403,6 +403,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
         */
        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;
@@ -528,7 +531,13 @@ static inline void mm_free_pgd(struct mm_struct *mm)
        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 */
@@ -697,34 +706,53 @@ void mmput(struct mm_struct *mm)
 }
 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
@@ -887,8 +915,6 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
        if (!mm_init(mm, tsk))
                goto fail_nomem;
 
-       dup_mm_exe_file(oldmm, mm);
-
        err = dup_mmap(mm, oldmm);
        if (err)
                goto free_pt;