1 files changed, 160 insertions, 93 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index d4cb3183c99..f792000a28e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -15,13 +15,15 @@
 #include <linux/module.h>
 #include <linux/syscalls.h>
 #include <linux/pagemap.h>
+#include "read_write.h"
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 
 const struct file_operations generic_ro_fops = {
 	.llseek		= generic_file_llseek,
-	.read		= generic_file_read,
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
 	.mmap		= generic_file_readonly_mmap,
 	.sendfile	= generic_file_sendfile,
 };
@@ -227,14 +229,20 @@ static void wait_on_retry_sync_kiocb(struct kiocb *iocb)
 
 ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
+	struct iovec iov = { .iov_base = buf, .iov_len = len };
 	struct kiocb kiocb;
 	ssize_t ret;
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	while (-EIOCBRETRY ==
-		(ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos)))
+	kiocb.ki_left = len;
+
+	for (;;) {
+		ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
+		if (ret != -EIOCBRETRY)
+			break;
 		wait_on_retry_sync_kiocb(&kiocb);
+	}
 
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&kiocb);
@@ -279,14 +287,20 @@ EXPORT_SYMBOL(vfs_read);
 
 ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
 {
+	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
 	struct kiocb kiocb;
 	ssize_t ret;
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = *ppos;
-	while (-EIOCBRETRY ==
-	       (ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos)))
+	kiocb.ki_left = len;
+
+	for (;;) {
+		ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
+		if (ret != -EIOCBRETRY)
+			break;
 		wait_on_retry_sync_kiocb(&kiocb);
+	}
 
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&kiocb);
@@ -438,78 +452,155 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 
 EXPORT_UNUSED_SYMBOL(iov_shorten);  /*  June 2006  */
 
+ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
+		unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)
+{
+	struct kiocb kiocb;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	kiocb.ki_left = len;
+	kiocb.ki_nbytes = len;
+
+	for (;;) {
+		ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
+		if (ret != -EIOCBRETRY)
+			break;
+		wait_on_retry_sync_kiocb(&kiocb);
+	}
+
+	if (ret == -EIOCBQUEUED)
+		ret = wait_on_sync_kiocb(&kiocb);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
+/* Do it by hand, with file-ops */
+ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
+		unsigned long nr_segs, loff_t *ppos, io_fn_t fn)
+{
+	struct iovec *vector = iov;
+	ssize_t ret = 0;
+
+	while (nr_segs > 0) {
+		void __user *base;
+		size_t len;
+		ssize_t nr;
+
+		base = vector->iov_base;
+		len = vector->iov_len;
+		vector++;
+		nr_segs--;
+
+		nr = fn(filp, base, len, ppos);
+
+		if (nr < 0) {
+			if (!ret)
+				ret = nr;
+			break;
+		}
+		ret += nr;
+		if (nr != len)
+			break;
+	}
+
+	return ret;
+}
+
 /* A write operation does a read from user space and vice versa */
 #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
 
+ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
+			      unsigned long nr_segs, unsigned long fast_segs,
+			      struct iovec *fast_pointer,
+			      struct iovec **ret_pointer)
+  {
+	unsigned long seg;
+  	ssize_t ret;
+	struct iovec *iov = fast_pointer;
+
+  	/*
+  	 * SuS says "The readv() function *may* fail if the iovcnt argument
+  	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+  	 * traditionally returned zero for zero segments, so...
+  	 */
+	if (nr_segs == 0) {
+		ret = 0;
+  		goto out;
+	}
+
+  	/*
+  	 * First get the "struct iovec" from user memory and
+  	 * verify all the pointers
+  	 */
+	if (nr_segs > UIO_MAXIOV) {
+		ret = -EINVAL;
+  		goto out;
+	}
+	if (nr_segs > fast_segs) {
+  		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
+		if (iov == NULL) {
+			ret = -ENOMEM;
+  			goto out;
+		}
+  	}
+	if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
+		ret = -EFAULT;
+  		goto out;
+	}
+
+  	/*
+	 * According to the Single Unix Specification we should return EINVAL
+	 * if an element length is < 0 when cast to ssize_t or if the
+	 * total length would overflow the ssize_t return value of the
+	 * system call.
+  	 */
+	ret = 0;
+  	for (seg = 0; seg < nr_segs; seg++) {
+  		void __user *buf = iov[seg].iov_base;
+  		ssize_t len = (ssize_t)iov[seg].iov_len;
+
+		/* see if we we're about to use an invalid len or if
+		 * it's about to overflow ssize_t */
+		if (len < 0 || (ret + len < ret)) {
+			ret = -EINVAL;
+  			goto out;
+		}
+		if (unlikely(!access_ok(vrfy_dir(type), buf, len))) {
+			ret = -EFAULT;
+  			goto out;
+		}
+
+		ret += len;
+  	}
+out:
+	*ret_pointer = iov;
+	return ret;
+}
+
 static ssize_t do_readv_writev(int type, struct file *file,
 			       const struct iovec __user * uvector,
 			       unsigned long nr_segs, loff_t *pos)
 {
-	typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
-	typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *);
-
 	size_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov=iovstack, *vector;
+	struct iovec *iov = iovstack;
 	ssize_t ret;
-	int seg;
 	io_fn_t fn;
 	iov_fn_t fnv;
 
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	ret = 0;
-	if (nr_segs == 0)
+	if (!file->f_op) {
+		ret = -EINVAL;
 		goto out;
+	}
 
-	/*
-	 * First get the "struct iovec" from user memory and
-	 * verify all the pointers
-	 */
-	ret = -EINVAL;
-	if (nr_segs > UIO_MAXIOV)
-		goto out;
-	if (!file->f_op)
-		goto out;
-	if (nr_segs > UIO_FASTIOV) {
-		ret = -ENOMEM;
-		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
-		if (!iov)
-			goto out;
-	}
-	ret = -EFAULT;
-	if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector)))
+	ret = rw_copy_check_uvector(type, uvector, nr_segs,
+			ARRAY_SIZE(iovstack), iovstack, &iov);
+	if (ret <= 0)
 		goto out;
 
-	/*
-	 * Single unix specification:
-	 * We should -EINVAL if an element length is not >= 0 and fitting an
-	 * ssize_t.  The total length is fitting an ssize_t
-	 *
-	 * Be careful here because iov_len is a size_t not an ssize_t
-	 */
-	tot_len = 0;
-	ret = -EINVAL;
-	for (seg = 0; seg < nr_segs; seg++) {
-		void __user *buf = iov[seg].iov_base;
-		ssize_t len = (ssize_t)iov[seg].iov_len;
-
-		if (len < 0)	/* size_t not fitting an ssize_t .. */
-			goto out;
-		if (unlikely(!access_ok(vrfy_dir(type), buf, len)))
-			goto Efault;
-		tot_len += len;
-		if ((ssize_t)tot_len < 0) /* maths overflow on the ssize_t */
-			goto out;
-	}
-	if (tot_len == 0) {
-		ret = 0;
-		goto out;
-	}
-
+	tot_len = ret;
 	ret = rw_verify_area(type, file, pos, tot_len);
 	if (ret < 0)
 		goto out;
@@ -520,39 +611,18 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	fnv = NULL;
 	if (type == READ) {
 		fn = file->f_op->read;
-		fnv = file->f_op->readv;
+		fnv = file->f_op->aio_read;
 	} else {
 		fn = (io_fn_t)file->f_op->write;
-		fnv = file->f_op->writev;
+		fnv = file->f_op->aio_write;
 	}
-	if (fnv) {
-		ret = fnv(file, iov, nr_segs, pos);
-		goto out;
-	}
-
-	/* Do it by hand, with file-ops */
-	ret = 0;
-	vector = iov;
-	while (nr_segs > 0) {
-		void __user * base;
-		size_t len;
-		ssize_t nr;
 
-		base = vector->iov_base;
-		len = vector->iov_len;
-		vector++;
-		nr_segs--;
-
-		nr = fn(file, base, len, pos);
+	if (fnv)
+		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
+						pos, fnv);
+	else
+		ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
 
-		if (nr < 0) {
-			if (!ret) ret = nr;
-			break;
-		}
-		ret += nr;
-		if (nr != len)
-			break;
-	}
 out:
 	if (iov != iovstack)
 		kfree(iov);
@@ -563,9 +633,6 @@ out:
 			fsnotify_modify(file->f_dentry);
 	}
 	return ret;
-Efault:
-	ret = -EFAULT;
-	goto out;
 }
 
 ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
@@ -573,7 +640,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 {
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
-	if (!file->f_op || (!file->f_op->readv && !file->f_op->read))
+	if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
 		return -EINVAL;
 
 	return do_readv_writev(READ, file, vec, vlen, pos);
@@ -586,7 +653,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
 {
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
-	if (!file->f_op || (!file->f_op->writev && !file->f_op->write))
+	if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
 		return -EINVAL;
 
 	return do_readv_writev(WRITE, file, vec, vlen, pos);