enum AIOCBState aiocb_type;
Coroutine *coroutine;
- void (*aio_done_func)(SheepdogAIOCB *);
-
- bool cancelable;
int nr_pending;
uint32_t min_affect_data_idx;
*
* 1. In sd_co_rw_vector, we send the I/O requests to the server and
* link the requests to the inflight_list in the
- * BDRVSheepdogState. The function exits without waiting for
+ * BDRVSheepdogState. The function yields while waiting for
* receiving the response.
*
* 2. We receive the response in aio_read_response, the fd handler to
- * the sheepdog connection. If metadata update is needed, we send
- * the write request to the vdi object in sd_write_done, the write
- * completion function. We switch back to sd_co_readv/writev after
- * all the requests belonging to the AIOCB are finished.
+ * the sheepdog connection. We switch back to sd_co_readv/sd_writev
+ * after all the requests belonging to the AIOCB are finished. If
+ * needed, sd_co_writev will send another requests for the vdi object.
*/
static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
{
SheepdogAIOCB *acb = aio_req->aiocb;
- acb->cancelable = false;
QLIST_REMOVE(aio_req, aio_siblings);
g_free(aio_req);
acb->nr_pending--;
}
-static void coroutine_fn sd_finish_aiocb(SheepdogAIOCB *acb)
-{
- qemu_coroutine_enter(acb->coroutine);
- qemu_aio_unref(acb);
-}
-
-/*
- * Check whether the specified acb can be canceled
- *
- * We can cancel aio when any request belonging to the acb is:
- * - Not processed by the sheepdog server.
- * - Not linked to the inflight queue.
- */
-static bool sd_acb_cancelable(const SheepdogAIOCB *acb)
-{
- BDRVSheepdogState *s = acb->common.bs->opaque;
- AIOReq *aioreq;
-
- if (!acb->cancelable) {
- return false;
- }
-
- QLIST_FOREACH(aioreq, &s->inflight_aio_head, aio_siblings) {
- if (aioreq->aiocb == acb) {
- return false;
- }
- }
-
- return true;
-}
-
-static void sd_aio_cancel(BlockAIOCB *blockacb)
-{
- SheepdogAIOCB *acb = (SheepdogAIOCB *)blockacb;
- BDRVSheepdogState *s = acb->common.bs->opaque;
- AIOReq *aioreq, *next;
-
- if (sd_acb_cancelable(acb)) {
- /* Remove outstanding requests from failed queue. */
- QLIST_FOREACH_SAFE(aioreq, &s->failed_aio_head, aio_siblings,
- next) {
- if (aioreq->aiocb == acb) {
- free_aio_req(s, aioreq);
- }
- }
-
- assert(acb->nr_pending == 0);
- if (acb->common.cb) {
- acb->common.cb(acb->common.opaque, -ECANCELED);
- }
- sd_finish_aiocb(acb);
- }
-}
-
static const AIOCBInfo sd_aiocb_info = {
.aiocb_size = sizeof(SheepdogAIOCB),
- .cancel_async = sd_aio_cancel,
};
static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
acb->sector_num = sector_num;
acb->nb_sectors = nb_sectors;
- acb->aio_done_func = NULL;
- acb->cancelable = true;
acb->coroutine = qemu_coroutine_self();
acb->ret = 0;
acb->nr_pending = 0;
typedef struct SheepdogReqCo {
int sockfd;
+ BlockDriverState *bs;
AioContext *aio_context;
SheepdogReq *hdr;
void *data;
co = qemu_coroutine_self();
aio_set_fd_handler(srco->aio_context, sockfd, false,
- NULL, restart_co_req, co);
+ NULL, restart_co_req, NULL, co);
ret = send_co_req(sockfd, hdr, data, wlen);
if (ret < 0) {
}
aio_set_fd_handler(srco->aio_context, sockfd, false,
- restart_co_req, NULL, co);
+ restart_co_req, NULL, NULL, co);
ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr));
if (ret != sizeof(*hdr)) {
/* there is at most one request for this sockfd, so it is safe to
* set each handler to NULL. */
aio_set_fd_handler(srco->aio_context, sockfd, false,
- NULL, NULL, NULL);
+ NULL, NULL, NULL, NULL);
srco->ret = ret;
srco->finished = true;
+ if (srco->bs) {
+ bdrv_wakeup(srco->bs);
+ }
}
/*
*
* Return 0 on success, -errno in case of error.
*/
-static int do_req(int sockfd, AioContext *aio_context, SheepdogReq *hdr,
+static int do_req(int sockfd, BlockDriverState *bs, SheepdogReq *hdr,
void *data, unsigned int *wlen, unsigned int *rlen)
{
Coroutine *co;
SheepdogReqCo srco = {
.sockfd = sockfd,
- .aio_context = aio_context,
+ .aio_context = bs ? bdrv_get_aio_context(bs) : qemu_get_aio_context(),
+ .bs = bs,
.hdr = hdr,
.data = data,
.wlen = wlen,
do_co_req(&srco);
} else {
co = qemu_coroutine_create(do_co_req, &srco);
- qemu_coroutine_enter(co);
- while (!srco.finished) {
- aio_poll(aio_context, true);
+ if (bs) {
+ qemu_coroutine_enter(co);
+ BDRV_POLL_WHILE(bs, !srco.finished);
+ } else {
+ qemu_coroutine_enter(co);
+ while (!srco.finished) {
+ aio_poll(qemu_get_aio_context(), true);
+ }
}
}
AIOReq *aio_req, *next;
aio_set_fd_handler(s->aio_context, s->fd, false, NULL,
- NULL, NULL);
+ NULL, NULL, NULL);
close(s->fd);
s->fd = -1;
switch (acb->aiocb_type) {
case AIOCB_WRITE_UDATA:
- /* this coroutine context is no longer suitable for co_recv
- * because we may send data to update vdi objects */
- s->co_recv = NULL;
if (!is_data_obj(aio_req->oid)) {
break;
}
}
}
+ /* No more data for this aio_req (reload_inode below uses its own file
+ * descriptor handler which doesn't use co_recv).
+ */
+ s->co_recv = NULL;
+
switch (rsp.result) {
case SD_RES_SUCCESS:
break;
aio_req->oid = vid_to_vdi_oid(s->inode.vdi_id);
}
resend_aioreq(s, aio_req);
- goto out;
+ return;
default:
acb->ret = -EIO;
error_report("%s", sd_strerror(rsp.result));
* We've finished all requests which belong to the AIOCB, so
* we can switch back to sd_co_readv/writev now.
*/
- acb->aio_done_func(acb);
+ qemu_coroutine_enter(acb->coroutine);
}
-out:
- s->co_recv = NULL;
+
return;
+
err:
- s->co_recv = NULL;
reconnect_to_sdog(opaque);
}
}
aio_set_fd_handler(s->aio_context, fd, false,
- co_read_response, NULL, s);
+ co_read_response, NULL, NULL, s);
return fd;
}
const char *host_spec, *vdi_spec;
int nr_sep, ret;
- strstart(filename, "sheepdog:", (const char **)&filename);
+ strstart(filename, "sheepdog:", &filename);
p = q = g_strdup(filename);
/* count the number of separators */
hdr.snapid = snapid;
hdr.flags = SD_FLAG_CMD_WRITE;
- ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
+ ret = do_req(fd, s->bs, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
if (ret) {
error_setg_errno(errp, -ret, "cannot get vdi info");
goto out;
qemu_co_mutex_lock(&s->lock);
s->co_send = qemu_coroutine_self();
aio_set_fd_handler(s->aio_context, s->fd, false,
- co_read_response, co_write_request, s);
+ co_read_response, co_write_request, NULL, s);
socket_set_cork(s->fd, 1);
/* send a header */
out:
socket_set_cork(s->fd, 0);
aio_set_fd_handler(s->aio_context, s->fd, false,
- co_read_response, NULL, s);
+ co_read_response, NULL, NULL, s);
s->co_send = NULL;
qemu_co_mutex_unlock(&s->lock);
}
-static int read_write_object(int fd, AioContext *aio_context, char *buf,
+static int read_write_object(int fd, BlockDriverState *bs, char *buf,
uint64_t oid, uint8_t copies,
unsigned int datalen, uint64_t offset,
bool write, bool create, uint32_t cache_flags)
hdr.offset = offset;
hdr.copies = copies;
- ret = do_req(fd, aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
+ ret = do_req(fd, bs, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
if (ret) {
error_report("failed to send a request to the sheep");
return ret;
}
}
-static int read_object(int fd, AioContext *aio_context, char *buf,
+static int read_object(int fd, BlockDriverState *bs, char *buf,
uint64_t oid, uint8_t copies,
unsigned int datalen, uint64_t offset,
uint32_t cache_flags)
{
- return read_write_object(fd, aio_context, buf, oid, copies,
+ return read_write_object(fd, bs, buf, oid, copies,
datalen, offset, false,
false, cache_flags);
}
-static int write_object(int fd, AioContext *aio_context, char *buf,
+static int write_object(int fd, BlockDriverState *bs, char *buf,
uint64_t oid, uint8_t copies,
unsigned int datalen, uint64_t offset, bool create,
uint32_t cache_flags)
{
- return read_write_object(fd, aio_context, buf, oid, copies,
+ return read_write_object(fd, bs, buf, oid, copies,
datalen, offset, true,
create, cache_flags);
}
goto out;
}
- ret = read_object(fd, s->aio_context, (char *)inode, vid_to_vdi_oid(vid),
+ ret = read_object(fd, s->bs, (char *)inode, vid_to_vdi_oid(vid),
s->inode.nr_copies, SD_INODE_HEADER_SIZE, 0,
s->cache_flags);
if (ret < 0) {
BDRVSheepdogState *s = bs->opaque;
aio_set_fd_handler(s->aio_context, s->fd, false, NULL,
- NULL, NULL);
+ NULL, NULL, NULL);
}
static void sd_attach_aio_context(BlockDriverState *bs,
s->aio_context = new_context;
aio_set_fd_handler(new_context, s->fd, false,
- co_read_response, NULL, s);
+ co_read_response, NULL, NULL, s);
}
/* TODO Convert to fine grained options */
}
buf = g_malloc(SD_INODE_SIZE);
- ret = read_object(fd, s->aio_context, buf, vid_to_vdi_oid(vid),
+ ret = read_object(fd, s->bs, buf, vid_to_vdi_oid(vid),
0, SD_INODE_SIZE, 0, s->cache_flags);
closesocket(fd);
return 0;
out:
aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd,
- false, NULL, NULL, NULL);
+ false, NULL, NULL, NULL, NULL);
if (s->fd >= 0) {
closesocket(s->fd);
}
if (s->fd) {
aio_set_fd_handler(s->aio_context, s->fd, false,
- NULL, NULL, NULL);
+ NULL, NULL, NULL, NULL);
closesocket(s->fd);
}
if (re_s->fd) {
aio_set_fd_handler(s->aio_context, re_s->fd, false,
- NULL, NULL, NULL);
+ NULL, NULL, NULL, NULL);
closesocket(re_s->fd);
}
hdr.copies = s->inode.nr_copies;
hdr.block_size_shift = s->inode.block_size_shift;
- ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
+ ret = do_req(fd, NULL, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
closesocket(fd);
hdr.opcode = SD_OP_GET_CLUSTER_DEFAULT;
hdr.proto_ver = SD_PROTO_VER;
- ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
+ ret = do_req(fd, NULL, (SheepdogReq *)&hdr,
NULL, &wlen, &rlen);
closesocket(fd);
if (ret) {
hdr.data_length = wlen;
hdr.flags = SD_FLAG_CMD_WRITE;
- ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
+ ret = do_req(fd, s->bs, (SheepdogReq *)&hdr,
s->name, &wlen, &rlen);
closesocket(fd);
}
aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd,
- false, NULL, NULL, NULL);
+ false, NULL, NULL, NULL, NULL);
closesocket(s->fd);
g_free(s->host_spec);
}
/* we don't need to update entire object */
datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
s->inode.vdi_size = offset;
- ret = write_object(fd, s->aio_context, (char *)&s->inode,
+ ret = write_object(fd, s->bs, (char *)&s->inode,
vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies,
datalen, 0, false, s->cache_flags);
close(fd);
/*
* This function is called after writing data objects. If we need to
* update metadata, this sends a write request to the vdi object.
- * Otherwise, this switches back to sd_co_readv/writev.
*/
static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
{
mx = acb->max_dirty_data_idx;
if (mn <= mx) {
/* we need to update the vdi object. */
+ ++acb->nr_pending;
offset = sizeof(s->inode) - sizeof(s->inode.data_vdi_id) +
mn * sizeof(s->inode.data_vdi_id[0]);
data_len = (mx - mn + 1) * sizeof(s->inode.data_vdi_id[0]);
data_len, offset, 0, false, 0, offset);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA);
-
- acb->aio_done_func = sd_finish_aiocb;
- acb->aiocb_type = AIOCB_WRITE_UDATA;
- return;
+ if (--acb->nr_pending) {
+ qemu_coroutine_yield();
+ }
}
-
- sd_finish_aiocb(acb);
}
/* Delete current working VDI on the snapshot chain */
return false;
}
- ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
+ ret = do_req(fd, s->bs, (SheepdogReq *)&hdr,
s->name, &wlen, &rlen);
closesocket(fd);
if (ret) {
goto out;
}
- ret = read_object(fd, s->aio_context, buf, vid_to_vdi_oid(vid),
+ ret = read_object(fd, s->bs, buf, vid_to_vdi_oid(vid),
s->inode.nr_copies, SD_INODE_SIZE, 0, s->cache_flags);
closesocket(fd);
* Returns 1 when we need to wait a response, 0 when there is no sent
* request and -errno in error cases.
*/
-static int coroutine_fn sd_co_rw_vector(void *p)
+static void coroutine_fn sd_co_rw_vector(void *p)
{
SheepdogAIOCB *acb = p;
int ret = 0;
ret = sd_create_branch(s);
if (ret) {
acb->ret = -EIO;
- goto out;
+ return;
}
}
idx++;
done += len;
}
-out:
- if (!--acb->nr_pending) {
- return acb->ret;
+ if (--acb->nr_pending) {
+ qemu_coroutine_yield();
}
- return 1;
}
static bool check_overlapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *aiocb)
}
acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
- acb->aio_done_func = sd_write_done;
acb->aiocb_type = AIOCB_WRITE_UDATA;
retry:
goto retry;
}
- ret = sd_co_rw_vector(acb);
- if (ret <= 0) {
- QLIST_REMOVE(acb, aiocb_siblings);
- qemu_co_queue_restart_all(&s->overlapping_queue);
- qemu_aio_unref(acb);
- return ret;
- }
-
- qemu_coroutine_yield();
+ sd_co_rw_vector(acb);
+ sd_write_done(acb);
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
-
- return acb->ret;
+ ret = acb->ret;
+ qemu_aio_unref(acb);
+ return ret;
}
static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
acb->aiocb_type = AIOCB_READ_UDATA;
- acb->aio_done_func = sd_finish_aiocb;
retry:
if (check_overlapping_aiocb(s, acb)) {
goto retry;
}
- ret = sd_co_rw_vector(acb);
- if (ret <= 0) {
- QLIST_REMOVE(acb, aiocb_siblings);
- qemu_co_queue_restart_all(&s->overlapping_queue);
- qemu_aio_unref(acb);
- return ret;
- }
-
- qemu_coroutine_yield();
+ sd_co_rw_vector(acb);
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
- return acb->ret;
+ ret = acb->ret;
+ qemu_aio_unref(acb);
+ return ret;
}
static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
{
BDRVSheepdogState *s = bs->opaque;
SheepdogAIOCB *acb;
+ int ret;
AIOReq *aio_req;
if (s->cache_flags != SD_FLAG_CMD_CACHE) {
acb = sd_aio_setup(bs, NULL, 0, 0);
acb->aiocb_type = AIOCB_FLUSH_CACHE;
- acb->aio_done_func = sd_finish_aiocb;
+ acb->nr_pending++;
aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
0, 0, 0, false, 0, 0);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
add_aio_request(s, aio_req, NULL, 0, acb->aiocb_type);
- qemu_coroutine_yield();
- return acb->ret;
+ if (--acb->nr_pending) {
+ qemu_coroutine_yield();
+ }
+ ret = acb->ret;
+ qemu_aio_unref(acb);
+ return ret;
}
static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
goto cleanup;
}
- ret = write_object(fd, s->aio_context, (char *)&s->inode,
+ ret = write_object(fd, s->bs, (char *)&s->inode,
vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies,
datalen, 0, false, s->cache_flags);
if (ret < 0) {
goto cleanup;
}
- ret = read_object(fd, s->aio_context, (char *)inode,
+ ret = read_object(fd, s->bs, (char *)inode,
vid_to_vdi_oid(new_vid), s->inode.nr_copies, datalen, 0,
s->cache_flags);
i++;
}
- ret = write_object(fd, s->aio_context,
+ ret = write_object(fd, s->bs,
(char *)&inode->data_vdi_id[start_idx],
vid_to_vdi_oid(s->inode.vdi_id), inode->nr_copies,
(i - start_idx) * sizeof(uint32_t),
return -1;
}
- ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
+ ret = do_req(fd, s->bs, (SheepdogReq *)&hdr,
buf, &wlen, &rlen);
closesocket(fd);
if (ret) {
req.opcode = SD_OP_READ_VDIS;
req.data_length = max;
- ret = do_req(fd, s->aio_context, (SheepdogReq *)&req,
- vdi_inuse, &wlen, &rlen);
+ ret = do_req(fd, s->bs, &req, vdi_inuse, &wlen, &rlen);
closesocket(fd);
if (ret) {
}
/* we don't need to read entire object */
- ret = read_object(fd, s->aio_context, (char *)&inode,
+ ret = read_object(fd, s->bs, (char *)&inode,
vid_to_vdi_oid(vid),
0, SD_INODE_SIZE - sizeof(inode.data_vdi_id), 0,
s->cache_flags);
create = (offset == 0);
if (load) {
- ret = read_object(fd, s->aio_context, (char *)data, vmstate_oid,
+ ret = read_object(fd, s->bs, (char *)data, vmstate_oid,
s->inode.nr_copies, data_len, offset,
s->cache_flags);
} else {
- ret = write_object(fd, s->aio_context, (char *)data, vmstate_oid,
+ ret = write_object(fd, s->bs, (char *)data, vmstate_oid,
s->inode.nr_copies, data_len, offset, create,
s->cache_flags);
}
iov.iov_len = sizeof(zero);
discard_iov.iov = &iov;
discard_iov.niov = 1;
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((count & (BDRV_SECTOR_SIZE - 1)) == 0);
+ if (!QEMU_IS_ALIGNED(offset | count, BDRV_SECTOR_SIZE)) {
+ return -ENOTSUP;
+ }
acb = sd_aio_setup(bs, &discard_iov, offset >> BDRV_SECTOR_BITS,
count >> BDRV_SECTOR_BITS);
acb->aiocb_type = AIOCB_DISCARD_OBJ;
- acb->aio_done_func = sd_finish_aiocb;
retry:
if (check_overlapping_aiocb(s, acb)) {
goto retry;
}
- ret = sd_co_rw_vector(acb);
- if (ret <= 0) {
- QLIST_REMOVE(acb, aiocb_siblings);
- qemu_co_queue_restart_all(&s->overlapping_queue);
- qemu_aio_unref(acb);
- return ret;
- }
-
- qemu_coroutine_yield();
+ sd_co_rw_vector(acb);
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
-
- return acb->ret;
+ ret = acb->ret;
+ qemu_aio_unref(acb);
+ return ret;
}
static coroutine_fn int64_t
projects / mirror_qemu.git / blobdiff