+static ssize_t handle_aiocb_ioctl(struct qemu_paiocb *aiocb)
+{
+ int ret;
+
+ ret = ioctl(aiocb->aio_fildes, aiocb->aio_ioctl_cmd, aiocb->aio_ioctl_buf);
+ if (ret == -1)
+ return -errno;
+
+ /*
+ * This looks weird, but the aio code only consideres a request
+ * successful if it has written the number full number of bytes.
+ *
+ * Now we overload aio_nbytes as aio_ioctl_cmd for the ioctl command,
+ * so in fact we return the ioctl command here to make posix_aio_read()
+ * happy..
+ */
+ return aiocb->aio_nbytes;
+}
+
+static ssize_t handle_aiocb_flush(struct qemu_paiocb *aiocb)
+{
+ int ret;
+
+ ret = qemu_fdatasync(aiocb->aio_fildes);
+ if (ret == -1)
+ return -errno;
+ return 0;
+}
+
+#ifdef CONFIG_PREADV
+
+static ssize_t
+qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+ return preadv(fd, iov, nr_iov, offset);
+}
+
+static ssize_t
+qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+ return pwritev(fd, iov, nr_iov, offset);
+}
+
+#else
+
+static ssize_t
+qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+ return -ENOSYS;
+}
+
+static ssize_t
+qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
+{
+ return -ENOSYS;
+}
+
+#endif
+
+static ssize_t handle_aiocb_rw_vector(struct qemu_paiocb *aiocb)
+{
+ size_t offset = 0;
+ ssize_t len;
+
+ do {
+ if (aiocb->aio_type & QEMU_AIO_WRITE)
+ len = qemu_pwritev(aiocb->aio_fildes,
+ aiocb->aio_iov,
+ aiocb->aio_niov,
+ aiocb->aio_offset + offset);
+ else
+ len = qemu_preadv(aiocb->aio_fildes,
+ aiocb->aio_iov,
+ aiocb->aio_niov,
+ aiocb->aio_offset + offset);
+ } while (len == -1 && errno == EINTR);
+
+ if (len == -1)
+ return -errno;
+ return len;
+}
+
+static ssize_t handle_aiocb_rw_linear(struct qemu_paiocb *aiocb, char *buf)
+{
+ ssize_t offset = 0;
+ ssize_t len;
+
+ while (offset < aiocb->aio_nbytes) {
+ if (aiocb->aio_type & QEMU_AIO_WRITE)
+ len = pwrite(aiocb->aio_fildes,
+ (const char *)buf + offset,
+ aiocb->aio_nbytes - offset,
+ aiocb->aio_offset + offset);
+ else
+ len = pread(aiocb->aio_fildes,
+ buf + offset,
+ aiocb->aio_nbytes - offset,
+ aiocb->aio_offset + offset);
+
+ if (len == -1 && errno == EINTR)
+ continue;
+ else if (len == -1) {
+ offset = -errno;
+ break;
+ } else if (len == 0)
+ break;
+
+ offset += len;
+ }
+
+ return offset;
+}
+
+static ssize_t handle_aiocb_rw(struct qemu_paiocb *aiocb)
+{
+ ssize_t nbytes;
+ char *buf;
+
+ if (!(aiocb->aio_type & QEMU_AIO_MISALIGNED)) {
+ /*
+ * If there is just a single buffer, and it is properly aligned
+ * we can just use plain pread/pwrite without any problems.
+ */
+ if (aiocb->aio_niov == 1)
+ return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);
+
+ /*
+ * We have more than one iovec, and all are properly aligned.
+ *
+ * Try preadv/pwritev first and fall back to linearizing the
+ * buffer if it's not supported.
+ */
+ if (preadv_present) {
+ nbytes = handle_aiocb_rw_vector(aiocb);
+ if (nbytes == aiocb->aio_nbytes)
+ return nbytes;
+ if (nbytes < 0 && nbytes != -ENOSYS)
+ return nbytes;
+ preadv_present = 0;
+ }
+
+ /*
+ * XXX(hch): short read/write. no easy way to handle the reminder
+ * using these interfaces. For now retry using plain
+ * pread/pwrite?
+ */
+ }
+
+ /*
+ * Ok, we have to do it the hard way, copy all segments into
+ * a single aligned buffer.
+ */
+ buf = qemu_blockalign(aiocb->common.bs, aiocb->aio_nbytes);
+ if (aiocb->aio_type & QEMU_AIO_WRITE) {
+ char *p = buf;
+ int i;
+
+ for (i = 0; i < aiocb->aio_niov; ++i) {
+ memcpy(p, aiocb->aio_iov[i].iov_base, aiocb->aio_iov[i].iov_len);
+ p += aiocb->aio_iov[i].iov_len;
+ }
+ }
+
+ nbytes = handle_aiocb_rw_linear(aiocb, buf);
+ if (!(aiocb->aio_type & QEMU_AIO_WRITE)) {
+ char *p = buf;
+ size_t count = aiocb->aio_nbytes, copy;
+ int i;
+
+ for (i = 0; i < aiocb->aio_niov && count; ++i) {
+ copy = count;
+ if (copy > aiocb->aio_iov[i].iov_len)
+ copy = aiocb->aio_iov[i].iov_len;
+ memcpy(aiocb->aio_iov[i].iov_base, p, copy);
+ p += copy;
+ count -= copy;
+ }
+ }
+ qemu_vfree(buf);
+
+ return nbytes;
+}
+