[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>

fs/aio.c

@@ -29,6 +29,7 @@
 #include <linux/highmem.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
+#include <linux/rcuref.h>
 
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
@@ -499,7 +500,7 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	/* Must be done under the lock to serialise against cancellation.
 	 * Call this aio_fput as it duplicates fput via the fput_work.
 	 */
-	if (unlikely(atomic_dec_and_test(&req->ki_filp->f_count))) {
+	if (unlikely(rcuref_dec_and_test(&req->ki_filp->f_count))) {
 		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);

fs/fcntl.c

@@ -16,6 +16,7 @@
 #include <linux/security.h>
 #include <linux/ptrace.h>
 #include <linux/signal.h>
+#include <linux/rcupdate.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -64,8 +65,8 @@ static int locate_fd(struct files_struct *files,
 	if (orig_start >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
 		goto out;
 
-	fdt = files_fdtable(files);
 repeat:
+	fdt = files_fdtable(files);
 	/*
 	 * Someone might have closed fd's in the range
 	 * orig_start..fdt->next_fd
@@ -95,9 +96,15 @@ repeat:
 	if (error)
 		goto repeat;
 
+	/*
+	 * We reacquired files_lock, so we are safe as long as
+	 * we reacquire the fdtable pointer and use it while holding
+	 * the lock, no one can free it during that time.
+	 */
+	fdt = files_fdtable(files);
 	if (start <= fdt->next_fd)
 		fdt->next_fd = newfd + 1;
-	
+
 	error = newfd;
 	
 out:
@@ -163,7 +170,7 @@ asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
 	if (!tofree && FD_ISSET(newfd, fdt->open_fds))
 		goto out_fput;
 
-	fdt->fd[newfd] = file;
+	rcu_assign_pointer(fdt->fd[newfd], file);
 	FD_SET(newfd, fdt->open_fds);
 	FD_CLR(newfd, fdt->close_on_exec);
 	spin_unlock(&files->file_lock);

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();
 } 

fs/open.c

@@ -24,6 +24,7 @@
 #include <linux/personality.h>
 #include <linux/pagemap.h>
 #include <linux/syscalls.h>
+#include <linux/rcupdate.h>
 
 #include <asm/unistd.h>
 
@@ -930,9 +931,8 @@ void fastcall fd_install(unsigned int fd, struct file * file)
 	struct fdtable *fdt;
 	spin_lock(&files->file_lock);
 	fdt = files_fdtable(files);
-	if (unlikely(fdt->fd[fd] != NULL))
-		BUG();
-	fdt->fd[fd] = file;
+	BUG_ON(fdt->fd[fd] != NULL);
+	rcu_assign_pointer(fdt->fd[fd], file);
 	spin_unlock(&files->file_lock);
 }
 
@@ -1024,7 +1024,7 @@ asmlinkage long sys_close(unsigned int fd)
 	filp = fdt->fd[fd];
 	if (!filp)
 		goto out_unlock;
-	fdt->fd[fd] = NULL;
+	rcu_assign_pointer(fdt->fd[fd], NULL);
 	FD_CLR(fd, fdt->close_on_exec);
 	__put_unused_fd(files, fd);
 	spin_unlock(&files->file_lock);

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, } }, 			\

kernel/exit.c

@@ -411,15 +411,16 @@ void fastcall put_files_struct(struct files_struct *files)
 		close_files(files);
 		/*
 		 * Free the fd and fdset arrays if we expanded them.
+		 * If the fdtable was embedded, pass files for freeing
+		 * at the end of the RCU grace period. Otherwise,
+		 * you can free files immediately.
 		 */
 		fdt = files_fdtable(files);
-		if (fdt->fd != &files->fd_array[0])
-			free_fd_array(fdt->fd, fdt->max_fds);
-		if (fdt->max_fdset > __FD_SETSIZE) {
-			free_fdset(fdt->open_fds, fdt->max_fdset);
-			free_fdset(fdt->close_on_exec, fdt->max_fdset);
-		}
-		kmem_cache_free(files_cachep, files);
+		if (fdt == &files->fdtab)
+			fdt->free_files = files;
+		else
+			kmem_cache_free(files_cachep, files);
+		free_fdtable(fdt);
 	}
 }
 

kernel/fork.c

@@ -35,6 +35,7 @@
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
 #include <linux/futex.h>
+#include <linux/rcupdate.h>
 #include <linux/ptrace.h>
 #include <linux/mount.h>
 #include <linux/audit.h>
@@ -565,13 +566,12 @@ static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk)
 	return 0;
 }
 
-static int count_open_files(struct files_struct *files, int size)
+static int count_open_files(struct fdtable *fdt)
 {
+	int size = fdt->max_fdset;
 	int i;
-	struct fdtable *fdt;
 
 	/* Find the last open fd */
-	fdt = files_fdtable(files);
 	for (i = size/(8*sizeof(long)); i > 0; ) {
 		if (fdt->open_fds->fds_bits[--i])
 			break;
@@ -592,13 +592,17 @@ static struct files_struct *alloc_files(void)
 	atomic_set(&newf->count, 1);
 
 	spin_lock_init(&newf->file_lock);
-	fdt = files_fdtable(newf);
+	fdt = &newf->fdtab;
 	fdt->next_fd = 0;
 	fdt->max_fds = NR_OPEN_DEFAULT;
 	fdt->max_fdset = __FD_SETSIZE;
 	fdt->close_on_exec = &newf->close_on_exec_init;
 	fdt->open_fds = &newf->open_fds_init;
 	fdt->fd = &newf->fd_array[0];
+	INIT_RCU_HEAD(&fdt->rcu);
+	fdt->free_files = NULL;
+	fdt->next = NULL;
+	rcu_assign_pointer(newf->fdt, fdt);
 out:
 	return newf;
 }
@@ -637,7 +641,7 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 	old_fdt = files_fdtable(oldf);
 	new_fdt = files_fdtable(newf);
 	size = old_fdt->max_fdset;
-	open_files = count_open_files(oldf, old_fdt->max_fdset);
+	open_files = count_open_files(old_fdt);
 	expand = 0;
 
 	/*
@@ -661,7 +665,14 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 		spin_unlock(&newf->file_lock);
 		if (error < 0)
 			goto out_release;
+		new_fdt = files_fdtable(newf);
+		/*
+		 * Reacquire the oldf lock and a pointer to its fd table
+		 * who knows it may have a new bigger fd table. We need
+		 * the latest pointer.
+		 */
 		spin_lock(&oldf->file_lock);
+		old_fdt = files_fdtable(oldf);
 	}
 
 	old_fds = old_fdt->fd;
@@ -683,7 +694,7 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 			 */
 			FD_CLR(open_files - i, new_fdt->open_fds);
 		}
-		*new_fds++ = f;
+		rcu_assign_pointer(*new_fds++, f);
 	}
 	spin_unlock(&oldf->file_lock);