[PATCH] Add vector AIO support

This work is initially done by Zach Brown to add support for vectored aio.
These are the core changes for AIO to support
IOCB_CMD_PREADV/IOCB_CMD_PWRITEV.

[akpm@osdl.org: huge build fix]
Signed-off-by: Zach Brown <zach.brown@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Acked-by: Benjamin LaHaise <bcrl@kvack.org>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 75 insertions, 54 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 4ed839bcb91c..f792000a28e6 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -511,6 +511,74 @@ ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
 /* 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)
@@ -519,64 +587,20 @@ static ssize_t do_readv_writev(int type, struct file *file,
         struct iovec iovstack[UIO_FASTIOV];
         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)
-                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)))
+        if (!file->f_op) {
+                ret = -EINVAL;
                 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;
+        ret = rw_copy_check_uvector(type, uvector, nr_segs,
+                        ARRAY_SIZE(iovstack), iovstack, &iov);
+        if (ret <= 0)
                 goto out;
-        }
 
+        tot_len = ret;
         ret = rw_verify_area(type, file, pos, tot_len);
         if (ret < 0)
                 goto out;
@@ -609,9 +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,