[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>

include/linux/file.h

@@ -9,6 +9,7 @@
 #include <linux/posix_types.h>
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
+#include <linux/rcupdate.h>
 
 /*
  * The default fd array needs to be at least BITS_PER_LONG,
@@ -23,6 +24,9 @@ struct fdtable {
 	struct file ** fd;      /* current fd array */
 	fd_set *close_on_exec;
 	fd_set *open_fds;
+	struct rcu_head rcu;
+	struct files_struct *free_files;
+	struct fdtable *next;
 };
 
 /*
@@ -31,13 +35,14 @@ struct fdtable {
 struct files_struct {
         atomic_t count;
         spinlock_t file_lock;     /* Protects all the below members.  Nests inside tsk->alloc_lock */
+	struct fdtable *fdt;
 	struct fdtable fdtab;
         fd_set close_on_exec_init;
         fd_set open_fds_init;
         struct file * fd_array[NR_OPEN_DEFAULT];
 };
 
-#define files_fdtable(files) (&(files)->fdtab)
+#define files_fdtable(files) (rcu_dereference((files)->fdt))
 
 extern void FASTCALL(__fput(struct file *));
 extern void FASTCALL(fput(struct file *));
@@ -65,6 +70,8 @@ extern fd_set *alloc_fdset(int);
 extern void free_fdset(fd_set *, int);
 
 extern int expand_files(struct files_struct *, int nr);
+extern void free_fdtable(struct fdtable *fdt);
+extern void __init files_defer_init(void);
 
 static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd)
 {
@@ -72,7 +79,7 @@ static inline struct file * fcheck_files(struct files_struct *files, unsigned in
 	struct fdtable *fdt = files_fdtable(files);
 
 	if (fd < fdt->max_fds)
-		file = fdt->fd[fd];
+		file = rcu_dereference(fdt->fd[fd]);
 	return file;
 }
 

include/linux/fs.h

@@ -9,6 +9,7 @@
 #include <linux/config.h>
 #include <linux/limits.h>
 #include <linux/ioctl.h>
+#include <linux/rcuref.h>
 
 /*
  * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
@@ -597,12 +598,13 @@ struct file {
 	spinlock_t		f_ep_lock;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
+	struct rcu_head 	f_rcuhead;
 };
 extern spinlock_t files_lock;
 #define file_list_lock() spin_lock(&files_lock);
 #define file_list_unlock() spin_unlock(&files_lock);
 
-#define get_file(x)	atomic_inc(&(x)->f_count)
+#define get_file(x)	rcuref_inc(&(x)->f_count)
 #define file_count(x)	atomic_read(&(x)->f_count)
 
 #define	MAX_NON_LFS	((1UL<<31) - 1)

include/linux/init_task.h

@@ -2,6 +2,7 @@
 #define _LINUX__INIT_TASK_H
 
 #include <linux/file.h>
+#include <linux/rcupdate.h>
 
 #define INIT_FDTABLE \
 {							\
@@ -11,12 +12,16 @@
 	.fd		= &init_files.fd_array[0], 	\
 	.close_on_exec	= &init_files.close_on_exec_init, \
 	.open_fds	= &init_files.open_fds_init, 	\
+	.rcu		= RCU_HEAD_INIT, 		\
+	.free_files	= NULL,		 		\
+	.next		= NULL,		 		\
 }
 
 #define INIT_FILES \
 { 							\
 	.count		= ATOMIC_INIT(1), 		\
 	.file_lock	= SPIN_LOCK_UNLOCKED, 		\
+	.fdt		= &init_files.fdtab, 		\
 	.fdtab		= INIT_FDTABLE,			\
 	.close_on_exec_init = { { 0, } }, 		\
 	.open_fds_init	= { { 0, } }, 			\