diff --git a/fs/file.c b/fs/file.c
index 6c672ad..6f6eb2b 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -56,6 +56,9 @@
 	__free_fdtable(container_of(rcu, struct fdtable, rcu));
 }
 
+#define BITBIT_NR(nr)	BITS_TO_LONGS(BITS_TO_LONGS(nr))
+#define BITBIT_SIZE(nr)	(BITBIT_NR(nr) * sizeof(long))
+
 /*
  * Expand the fdset in the files_struct.  Called with the files spinlock
  * held for write.
@@ -77,6 +80,11 @@
 	memset((char *)(nfdt->open_fds) + cpy, 0, set);
 	memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
 	memset((char *)(nfdt->close_on_exec) + cpy, 0, set);
+
+	cpy = BITBIT_SIZE(ofdt->max_fds);
+	set = BITBIT_SIZE(nfdt->max_fds) - cpy;
+	memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
+	memset(cpy+(char *)nfdt->full_fds_bits, 0, set);
 }
 
 static struct fdtable * alloc_fdtable(unsigned int nr)
@@ -115,12 +123,14 @@
 	fdt->fd = data;
 
 	data = alloc_fdmem(max_t(size_t,
-				 2 * nr / BITS_PER_BYTE, L1_CACHE_BYTES));
+				 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES));
 	if (!data)
 		goto out_arr;
 	fdt->open_fds = data;
 	data += nr / BITS_PER_BYTE;
 	fdt->close_on_exec = data;
+	data += nr / BITS_PER_BYTE;
+	fdt->full_fds_bits = data;
 
 	return fdt;
 
@@ -229,14 +239,18 @@
 	__clear_bit(fd, fdt->close_on_exec);
 }
 
-static inline void __set_open_fd(int fd, struct fdtable *fdt)
+static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
 {
 	__set_bit(fd, fdt->open_fds);
+	fd /= BITS_PER_LONG;
+	if (!~fdt->open_fds[fd])
+		__set_bit(fd, fdt->full_fds_bits);
 }
 
-static inline void __clear_open_fd(int fd, struct fdtable *fdt)
+static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt)
 {
 	__clear_bit(fd, fdt->open_fds);
+	__clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits);
 }
 
 static int count_open_files(struct fdtable *fdt)
@@ -280,6 +294,7 @@
 	new_fdt->max_fds = NR_OPEN_DEFAULT;
 	new_fdt->close_on_exec = newf->close_on_exec_init;
 	new_fdt->open_fds = newf->open_fds_init;
+	new_fdt->full_fds_bits = newf->full_fds_bits_init;
 	new_fdt->fd = &newf->fd_array[0];
 
 	spin_lock(&oldf->file_lock);
@@ -323,6 +338,7 @@
 
 	memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8);
 	memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8);
+	memcpy(new_fdt->full_fds_bits, old_fdt->full_fds_bits, BITBIT_SIZE(open_files));
 
 	for (i = open_files; i != 0; i--) {
 		struct file *f = *old_fds++;
@@ -454,10 +470,25 @@
 		.fd		= &init_files.fd_array[0],
 		.close_on_exec	= init_files.close_on_exec_init,
 		.open_fds	= init_files.open_fds_init,
+		.full_fds_bits	= init_files.full_fds_bits_init,
 	},
 	.file_lock	= __SPIN_LOCK_UNLOCKED(init_files.file_lock),
 };
 
+static unsigned long find_next_fd(struct fdtable *fdt, unsigned long start)
+{
+	unsigned long maxfd = fdt->max_fds;
+	unsigned long maxbit = maxfd / BITS_PER_LONG;
+	unsigned long bitbit = start / BITS_PER_LONG;
+
+	bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG;
+	if (bitbit > maxfd)
+		return maxfd;
+	if (bitbit > start)
+		start = bitbit;
+	return find_next_zero_bit(fdt->open_fds, maxfd, start);
+}
+
 /*
  * allocate a file descriptor, mark it busy.
  */
@@ -476,7 +507,7 @@
 		fd = files->next_fd;
 
 	if (fd < fdt->max_fds)
-		fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd);
+		fd = find_next_fd(fdt, fd);
 
 	/*
 	 * N.B. For clone tasks sharing a files structure, this test
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 674e3e2..5295535 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -26,6 +26,7 @@
 	struct file __rcu **fd;      /* current fd array */
 	unsigned long *close_on_exec;
 	unsigned long *open_fds;
+	unsigned long *full_fds_bits;
 	struct rcu_head rcu;
 };
 
@@ -59,6 +60,7 @@
 	int next_fd;
 	unsigned long close_on_exec_init[1];
 	unsigned long open_fds_init[1];
+	unsigned long full_fds_bits_init[1];
 	struct file __rcu * fd_array[NR_OPEN_DEFAULT];
 };