procfs task exe symlink

The kernel implements readlink of /proc/pid/exe by getting the file from
the first executable VMA.  Then the path to the file is reconstructed and
reported as the result.

Because of the VMA walk the code is slightly different on nommu systems.
This patch avoids separate /proc/pid/exe code on nommu systems.  Instead of
walking the VMAs to find the first executable file-backed VMA we store a
reference to the exec'd file in the mm_struct.

That reference would prevent the filesystem holding the executable file
from being unmounted even after unmapping the VMAs.  So we track the number
of VM_EXECUTABLE VMAs and drop the new reference when the last one is
unmapped.  This avoids pinning the mounted filesystem.

[akpm@linux-foundation.org: improve comments]
[yamamoto@valinux.co.jp: fix dup_mmap]
Signed-off-by: Matt Helsley <matthltc@us.ibm.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: David Howells <dhowells@redhat.com>
Cc:"Eric W. Biederman" <ebiederm@xmission.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 38 insertions, 1 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fef602d82722..c31a9cd2a30e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1066,6 +1066,19 @@ extern void unlink_file_vma(struct vm_area_struct *);
 extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
 	unsigned long addr, unsigned long len, pgoff_t pgoff);
 extern void exit_mmap(struct mm_struct *);
+
+#ifdef CONFIG_PROC_FS
+/* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */
+extern void added_exe_file_vma(struct mm_struct *mm);
+extern void removed_exe_file_vma(struct mm_struct *mm);
+#else
+static inline void added_exe_file_vma(struct mm_struct *mm)
+{}
+
+static inline void removed_exe_file_vma(struct mm_struct *mm)
+{}
+#endif /* CONFIG_PROC_FS */
+
 extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
 extern int install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bc97bd54f606..eb7c16cc9559 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -229,6 +229,12 @@ struct mm_struct {
 	struct task_struct *owner;	/* The thread group leader that */
 					/* owns the mm_struct.		*/
 #endif
+
+#ifdef CONFIG_PROC_FS
+	/* store ref to file /proc/<pid>/exe symlink points to */
+	struct file *exe_file;
+	unsigned long num_exe_file_vmas;
+#endif
 };
 
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 9b6c935f69cf..65f2299b772b 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -9,7 +9,6 @@
 
 struct net;
 struct completion;
-
 /*
  * The proc filesystem constants/structures
  */
@@ -206,6 +205,12 @@ extern void proc_net_remove(struct net *net, const char *name);
 extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name,
 	struct proc_dir_entry *parent);
 
+/* While the {get|set|dup}_mm_exe_file functions are for mm_structs, they are
+ * only needed to implement /proc/<pid>|self/exe so we define them here. */
+extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
+extern struct file *get_mm_exe_file(struct mm_struct *mm);
+extern void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm);
+
 #else
 
 #define proc_root_driver NULL
@@ -255,6 +260,19 @@ static inline void pid_ns_release_proc(struct pid_namespace *ns)
 {
 }
 
+static inline void set_mm_exe_file(struct mm_struct *mm,
+				   struct file *new_exe_file)
+{}
+
+static inline struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+	return NULL;
+}
+
+static inline void dup_mm_exe_file(struct mm_struct *oldmm,
+	       			   struct mm_struct *newmm)
+{}
+
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)