[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 @@ static int locate_fd(struct files_struct *files,
 	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);