[PATCH] files: files struct with RCU

Patch to eliminate struct files_struct.file_lock spinlock on the reader side
and use rcu refcounting rcuref_xxx api for the f_count refcounter.  The
updates to the fdtable are done by allocating a new fdtable structure and
setting files->fdt to point to the new structure.  The fdtable structure is
protected by RCU thereby allowing lock-free lookup.  For fd arrays/sets that
are vmalloced, we use keventd to free them since RCU callbacks can't sleep.  A
global list of fdtable to be freed is not scalable, so we use a per-cpu list.
If keventd is already handling the current cpu's work, we use a timer to defer
queueing of that work.

Since the last publication, this patch has been re-written to avoid using
explicit memory barriers and use rcu_assign_pointer(), rcu_dereference()
premitives instead.  This required that the fd information is kept in a
separate structure (fdtable) and updated atomically.

Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 29 insertions, 11 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index 43e9e1737de2..86ec8ae985b4 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -14,6 +14,7 @@
 #include <linux/fs.h>
 #include <linux/security.h>
 #include <linux/eventpoll.h>
+#include <linux/rcupdate.h>
 #include <linux/mount.h>
 #include <linux/cdev.h>
 #include <linux/fsnotify.h>
@@ -53,11 +54,17 @@ void filp_dtor(void * objp, struct kmem_cache_s *cachep, unsigned long dflags)
         spin_unlock_irqrestore(&filp_count_lock, flags);
 }
 
-static inline void file_free(struct file *f)
+static inline void file_free_rcu(struct rcu_head *head)
 {
+        struct file *f =  container_of(head, struct file, f_rcuhead);
         kmem_cache_free(filp_cachep, f);
 }
 
+static inline void file_free(struct file *f)
+{
+        call_rcu(&f->f_rcuhead, file_free_rcu);
+}
+
 /* Find an unused file structure and return a pointer to it.
  * Returns NULL, if there are no more free file structures or
  * we run out of memory.
@@ -110,7 +117,7 @@ EXPORT_SYMBOL(get_empty_filp);
 
 void fastcall fput(struct file *file)
 {
-        if (atomic_dec_and_test(&file->f_count))
+        if (rcuref_dec_and_test(&file->f_count))
                 __fput(file);
 }
 
@@ -156,11 +163,17 @@ struct file fastcall *fget(unsigned int fd)
         struct file *file;
         struct files_struct *files = current->files;
 
-        spin_lock(&files->file_lock);
+        rcu_read_lock();
         file = fcheck_files(files, fd);
-        if (file)
-                get_file(file);
-        spin_unlock(&files->file_lock);
+        if (file) {
+                if (!rcuref_inc_lf(&file->f_count)) {
+                        /* File object ref couldn't be taken */
+                        rcu_read_unlock();
+                        return NULL;
+                }
+        }
+        rcu_read_unlock();
+
         return file;
 }
 
@@ -182,21 +195,25 @@ struct file fastcall *fget_light(unsigned int fd, int *fput_needed)
         if (likely((atomic_read(&files->count) == 1))) {
                 file = fcheck_files(files, fd);
         } else {
-                spin_lock(&files->file_lock);
+                rcu_read_lock();
                 file = fcheck_files(files, fd);
                 if (file) {
-                        get_file(file);
-                        *fput_needed = 1;
+                        if (rcuref_inc_lf(&file->f_count))
+                                *fput_needed = 1;
+                        else
+                                /* Didn't get the reference, someone's freed */
+                                file = NULL;
                 }
-                spin_unlock(&files->file_lock);
+                rcu_read_unlock();
         }
+
         return file;
 }
 
 
 void put_filp(struct file *file)
 {
-        if (atomic_dec_and_test(&file->f_count)) {
+        if (rcuref_dec_and_test(&file->f_count)) {
                 security_file_free(file);
                 file_kill(file);
                 file_free(file);
@@ -257,4 +274,5 @@ void __init files_init(unsigned long mempages)
         files_stat.max_files = n; 
         if (files_stat.max_files < NR_FILE)
                 files_stat.max_files = NR_FILE;
+        files_defer_init();
 }