+ 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;
+}
+
+#ifdef CONFIG_XFS
+static int xfs_discard(BDRVRawState *s, int64_t offset, uint64_t bytes)
+{
+ struct xfs_flock64 fl;
+
+ memset(&fl, 0, sizeof(fl));
+ fl.l_whence = SEEK_SET;
+ fl.l_start = offset;
+ fl.l_len = bytes;
+
+ if (xfsctl(NULL, s->fd, XFS_IOC_UNRESVSP64, &fl) < 0) {
+ DEBUG_BLOCK_PRINT("cannot punch hole (%s)\n", strerror(errno));
+ return -errno;
+ }
+
+ return 0;
+}
+#endif
+
+static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
+{
+ int ret = -EOPNOTSUPP;
+ BDRVRawState *s = aiocb->bs->opaque;
+
+ if (s->has_discard == 0) {
+ return 0;
+ }
+
+ if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
+#ifdef BLKDISCARD
+ do {
+ uint64_t range[2] = { aiocb->aio_offset, aiocb->aio_nbytes };
+ if (ioctl(aiocb->aio_fildes, BLKDISCARD, range) == 0) {
+ return 0;
+ }
+ } while (errno == EINTR);
+
+ ret = -errno;
+#endif
+ } else {
+#ifdef CONFIG_XFS
+ if (s->is_xfs) {
+ return xfs_discard(s, aiocb->aio_offset, aiocb->aio_nbytes);
+ }
+#endif
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+ do {
+ if (fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+ aiocb->aio_offset, aiocb->aio_nbytes) == 0) {
+ return 0;
+ }
+ } while (errno == EINTR);
+
+ ret = -errno;
+#endif
+ }
+
+ if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
+ ret == -ENOTTY) {
+ s->has_discard = 0;
+ ret = 0;
+ }
+ return ret;
+}
+
+static int aio_worker(void *arg)
+{
+ RawPosixAIOData *aiocb = arg;
+ ssize_t ret = 0;
+
+ switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
+ case QEMU_AIO_READ:
+ ret = handle_aiocb_rw(aiocb);
+ if (ret >= 0 && ret < aiocb->aio_nbytes && aiocb->bs->growable) {
+ iov_memset(aiocb->aio_iov, aiocb->aio_niov, ret,
+ 0, aiocb->aio_nbytes - ret);
+
+ ret = aiocb->aio_nbytes;
+ }
+ if (ret == aiocb->aio_nbytes) {
+ ret = 0;
+ } else if (ret >= 0 && ret < aiocb->aio_nbytes) {
+ ret = -EINVAL;
+ }
+ break;
+ case QEMU_AIO_WRITE:
+ ret = handle_aiocb_rw(aiocb);
+ if (ret == aiocb->aio_nbytes) {
+ ret = 0;
+ } else if (ret >= 0 && ret < aiocb->aio_nbytes) {
+ ret = -EINVAL;
+ }
+ break;
+ case QEMU_AIO_FLUSH:
+ ret = handle_aiocb_flush(aiocb);
+ break;
+ case QEMU_AIO_IOCTL:
+ ret = handle_aiocb_ioctl(aiocb);
+ break;
+ case QEMU_AIO_DISCARD:
+ ret = handle_aiocb_discard(aiocb);
+ break;
+ default:
+ fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
+ ret = -EINVAL;
+ break;
+ }
+
+ g_slice_free(RawPosixAIOData, aiocb);
+ return ret;
+}
+
+static BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque, int type)
+{
+ RawPosixAIOData *acb = g_slice_new(RawPosixAIOData);
+ ThreadPool *pool;
+
+ acb->bs = bs;
+ acb->aio_type = type;
+ acb->aio_fildes = fd;
+
+ if (qiov) {
+ acb->aio_iov = qiov->iov;
+ acb->aio_niov = qiov->niov;
+ }
+ acb->aio_nbytes = nb_sectors * 512;
+ acb->aio_offset = sector_num * 512;
+
+ trace_paio_submit(acb, opaque, sector_num, nb_sectors, type);
+ pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
+ return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
projects / qemu.git / blobdiff