mm: rcu-protected get_mm_exe_file()

This patch removes mm->mmap_sem from mm->exe_file read side.
Also it kills dup_mm_exe_file() and moves exe_file duplication into
dup_mmap() where both mmap_sems are locked.

[akpm@linux-foundation.org: fix comment typo]
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 37 insertions, 19 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 8807a129711b..259202637531 100644
--- 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 */
@@ -697,35 +706,46 @@ 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(), sys_execve() and sys_prctl(PR_SET_MM_MAP/EXE_FILE).
+ * Callers prevent concurrent invocations: in mmput() nobody alive left,
+ * in execve task is single-threaded, prctl holds mmap_sem exclusively.
+ */
 void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 {
+        struct file *old_exe_file = rcu_dereference_protected(mm->exe_file,
+                        !atomic_read(&mm->mm_users) || current->in_execve ||
+                        lockdep_is_held(&mm->mmap_sem));
+
         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);
-}
-
 /**
  * get_task_mm - acquire a reference to the task's mm
  *
@@ -887,8 +907,6 @@ 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;