*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu-common.h"
* 20 - 31 (12 bits): reserved data object space
* 32 - 55 (24 bits): vdi object space
* 56 - 59 ( 4 bits): reserved vdi object space
- * 60 - 63 ( 4 bits): object type indentifier space
+ * 60 - 63 ( 4 bits): object type identifier space
*/
#define VDI_SPACE_SHIFT 32
int ret;
enum AIOCBState aiocb_type;
- QEMUBH *bh;
+ Coroutine *coroutine;
void (*aio_done_func)(SheepdogAIOCB *);
int canceled;
char *port;
int fd;
+ CoMutex lock;
+ Coroutine *co_send;
+ Coroutine *co_recv;
+
uint32_t aioreq_seq_num;
QLIST_HEAD(outstanding_aio_head, AIOReq) outstanding_aio_head;
} BDRVSheepdogState;
/*
* Sheepdog I/O handling:
*
- * 1. In the sd_aio_readv/writev, read/write requests are added to the
- * QEMU Bottom Halves.
- *
- * 2. In sd_readv_writev_bh_cb, the callbacks of BHs, we send the I/O
- * requests to the server and link the requests to the
- * outstanding_list in the BDRVSheepdogState. we exits the
- * function without waiting for receiving the response.
+ * 1. In sd_co_rw_vector, we send the I/O requests to the server and
+ * link the requests to the outstanding_list in the
+ * BDRVSheepdogState. The function exits without waiting for
+ * receiving the response.
*
- * 3. We receive the response in aio_read_response, the fd handler to
+ * 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. The AIOCB callback is not called until all
- * the requests belonging to the AIOCB are finished.
+ * completion function. We switch back to sd_co_readv/writev after
+ * all the requests belonging to the AIOCB are finished.
*/
static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
return !QLIST_EMPTY(&acb->aioreq_head);
}
-static void sd_finish_aiocb(SheepdogAIOCB *acb)
+static void coroutine_fn sd_finish_aiocb(SheepdogAIOCB *acb)
{
if (!acb->canceled) {
- acb->common.cb(acb->common.opaque, acb->ret);
+ qemu_coroutine_enter(acb->coroutine, NULL);
}
qemu_aio_release(acb);
}
* Sheepdog cannot cancel the requests which are already sent to
* the servers, so we just complete the request with -EIO here.
*/
- acb->common.cb(acb->common.opaque, -EIO);
+ acb->ret = -EIO;
+ qemu_coroutine_enter(acb->coroutine, NULL);
acb->canceled = 1;
}
acb->aio_done_func = NULL;
acb->canceled = 0;
- acb->bh = NULL;
+ acb->coroutine = qemu_coroutine_self();
acb->ret = 0;
QLIST_INIT(&acb->aioreq_head);
return acb;
}
-static int sd_schedule_bh(QEMUBHFunc *cb, SheepdogAIOCB *acb)
-{
- if (acb->bh) {
- error_report("bug: %d %d", acb->aiocb_type, acb->aiocb_type);
- return -EIO;
- }
-
- acb->bh = qemu_bh_new(cb, acb);
- qemu_bh_schedule(acb->bh);
- return 0;
-}
-
-#ifdef _WIN32
-
-struct msghdr {
- struct iovec *msg_iov;
- size_t msg_iovlen;
-};
-
-static ssize_t sendmsg(int s, const struct msghdr *msg, int flags)
-{
- size_t size = 0;
- char *buf, *p;
- int i, ret;
-
- /* count the msg size */
- for (i = 0; i < msg->msg_iovlen; i++) {
- size += msg->msg_iov[i].iov_len;
- }
- buf = g_malloc(size);
-
- p = buf;
- for (i = 0; i < msg->msg_iovlen; i++) {
- memcpy(p, msg->msg_iov[i].iov_base, msg->msg_iov[i].iov_len);
- p += msg->msg_iov[i].iov_len;
- }
-
- ret = send(s, buf, size, flags);
-
- g_free(buf);
- return ret;
-}
-
-static ssize_t recvmsg(int s, struct msghdr *msg, int flags)
-{
- size_t size = 0;
- char *buf, *p;
- int i, ret;
-
- /* count the msg size */
- for (i = 0; i < msg->msg_iovlen; i++) {
- size += msg->msg_iov[i].iov_len;
- }
- buf = g_malloc(size);
-
- ret = qemu_recv(s, buf, size, flags);
- if (ret < 0) {
- goto out;
- }
-
- p = buf;
- for (i = 0; i < msg->msg_iovlen; i++) {
- memcpy(msg->msg_iov[i].iov_base, p, msg->msg_iov[i].iov_len);
- p += msg->msg_iov[i].iov_len;
- }
-out:
- g_free(buf);
- return ret;
-}
-
-#endif
-
-/*
- * Send/recv data with iovec buffers
- *
- * This function send/recv data from/to the iovec buffer directly.
- * The first `offset' bytes in the iovec buffer are skipped and next
- * `len' bytes are used.
- *
- * For example,
- *
- * do_send_recv(sockfd, iov, len, offset, 1);
- *
- * is equals to
- *
- * char *buf = malloc(size);
- * iov_to_buf(iov, iovcnt, buf, offset, size);
- * send(sockfd, buf, size, 0);
- * free(buf);
- */
-static int do_send_recv(int sockfd, struct iovec *iov, int len, int offset,
- int write)
-{
- struct msghdr msg;
- int ret, diff;
-
- memset(&msg, 0, sizeof(msg));
- msg.msg_iov = iov;
- msg.msg_iovlen = 1;
-
- len += offset;
-
- while (iov->iov_len < len) {
- len -= iov->iov_len;
-
- iov++;
- msg.msg_iovlen++;
- }
-
- diff = iov->iov_len - len;
- iov->iov_len -= diff;
-
- while (msg.msg_iov->iov_len <= offset) {
- offset -= msg.msg_iov->iov_len;
-
- msg.msg_iov++;
- msg.msg_iovlen--;
- }
-
- msg.msg_iov->iov_base = (char *) msg.msg_iov->iov_base + offset;
- msg.msg_iov->iov_len -= offset;
-
- if (write) {
- ret = sendmsg(sockfd, &msg, 0);
- } else {
- ret = recvmsg(sockfd, &msg, 0);
- }
-
- msg.msg_iov->iov_base = (char *) msg.msg_iov->iov_base - offset;
- msg.msg_iov->iov_len += offset;
-
- iov->iov_len += diff;
- return ret;
-}
-
static int connect_to_sdog(const char *addr, const char *port)
{
char hbuf[NI_MAXHOST], sbuf[NI_MAXSERV];
return fd;
}
-static int do_readv_writev(int sockfd, struct iovec *iov, int len,
- int iov_offset, int write)
-{
- int ret;
-again:
- ret = do_send_recv(sockfd, iov, len, iov_offset, write);
- if (ret < 0) {
- if (errno == EINTR || errno == EAGAIN) {
- goto again;
- }
- error_report("failed to recv a rsp, %s", strerror(errno));
- return 1;
- }
-
- iov_offset += ret;
- len -= ret;
- if (len) {
- goto again;
- }
-
- return 0;
-}
-
-static int do_readv(int sockfd, struct iovec *iov, int len, int iov_offset)
-{
- return do_readv_writev(sockfd, iov, len, iov_offset, 0);
-}
-
-static int do_writev(int sockfd, struct iovec *iov, int len, int iov_offset)
-{
- return do_readv_writev(sockfd, iov, len, iov_offset, 1);
-}
-
-static int do_read_write(int sockfd, void *buf, int len, int write)
-{
- struct iovec iov;
-
- iov.iov_base = buf;
- iov.iov_len = len;
-
- return do_readv_writev(sockfd, &iov, len, 0, write);
-}
-
-static int do_read(int sockfd, void *buf, int len)
-{
- return do_read_write(sockfd, buf, len, 0);
-}
-
-static int do_write(int sockfd, void *buf, int len)
-{
- return do_read_write(sockfd, buf, len, 1);
-}
-
static int send_req(int sockfd, SheepdogReq *hdr, void *data,
unsigned int *wlen)
{
int ret;
- struct iovec iov[2];
-
- iov[0].iov_base = hdr;
- iov[0].iov_len = sizeof(*hdr);
- if (*wlen) {
- iov[1].iov_base = data;
- iov[1].iov_len = *wlen;
+ ret = qemu_send_full(sockfd, hdr, sizeof(*hdr), 0);
+ if (ret < sizeof(*hdr)) {
+ error_report("failed to send a req, %s", strerror(errno));
}
- ret = do_writev(sockfd, iov, sizeof(*hdr) + *wlen, 0);
- if (ret) {
+ ret = qemu_send_full(sockfd, data, *wlen, 0);
+ if (ret < *wlen) {
error_report("failed to send a req, %s", strerror(errno));
- ret = -1;
}
return ret;
{
int ret;
+ socket_set_block(sockfd);
ret = send_req(sockfd, hdr, data, wlen);
- if (ret) {
- ret = -1;
+ if (ret < 0) {
goto out;
}
- ret = do_read(sockfd, hdr, sizeof(*hdr));
- if (ret) {
+ ret = qemu_recv_full(sockfd, hdr, sizeof(*hdr), 0);
+ if (ret < sizeof(*hdr)) {
error_report("failed to get a rsp, %s", strerror(errno));
- ret = -1;
goto out;
}
}
if (*rlen) {
- ret = do_read(sockfd, data, *rlen);
- if (ret) {
+ ret = qemu_recv_full(sockfd, data, *rlen, 0);
+ if (ret < *rlen) {
error_report("failed to get the data, %s", strerror(errno));
- ret = -1;
goto out;
}
}
ret = 0;
out:
+ socket_set_nonblock(sockfd);
return ret;
}
-static int add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
+static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
struct iovec *iov, int niov, int create,
enum AIOCBState aiocb_type);
* This function searchs pending requests to the object `oid', and
* sends them.
*/
-static void send_pending_req(BDRVSheepdogState *s, uint64_t oid, uint32_t id)
+static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid, uint32_t id)
{
AIOReq *aio_req, *next;
SheepdogAIOCB *acb;
* This function is registered as a fd handler, and called from the
* main loop when s->fd is ready for reading responses.
*/
-static void aio_read_response(void *opaque)
+static void coroutine_fn aio_read_response(void *opaque)
{
SheepdogObjRsp rsp;
BDRVSheepdogState *s = opaque;
unsigned long idx;
if (QLIST_EMPTY(&s->outstanding_aio_head)) {
- return;
+ goto out;
}
/* read a header */
- ret = do_read(fd, &rsp, sizeof(rsp));
- if (ret) {
+ ret = qemu_co_recv(fd, &rsp, sizeof(rsp));
+ if (ret < 0) {
error_report("failed to get the header, %s", strerror(errno));
- return;
+ goto out;
}
/* find the right aio_req from the outstanding_aio list */
}
if (!aio_req) {
error_report("cannot find aio_req %x", rsp.id);
- return;
+ goto out;
}
acb = aio_req->aiocb;
}
break;
case AIOCB_READ_UDATA:
- ret = do_readv(fd, acb->qiov->iov, rsp.data_length,
- aio_req->iov_offset);
- if (ret) {
+ ret = qemu_co_recvv(fd, acb->qiov->iov, rsp.data_length,
+ aio_req->iov_offset);
+ if (ret < 0) {
error_report("failed to get the data, %s", strerror(errno));
- return;
+ goto out;
}
break;
}
if (!rest) {
/*
* We've finished all requests which belong to the AIOCB, so
- * we can call the callback now.
+ * we can switch back to sd_co_readv/writev now.
*/
acb->aio_done_func(acb);
}
+out:
+ s->co_recv = NULL;
}
-static int aio_flush_request(void *opaque)
+static void co_read_response(void *opaque)
{
BDRVSheepdogState *s = opaque;
- return !QLIST_EMPTY(&s->outstanding_aio_head);
-}
+ if (!s->co_recv) {
+ s->co_recv = qemu_coroutine_create(aio_read_response);
+ }
-#if !defined(SOL_TCP) || !defined(TCP_CORK)
+ qemu_coroutine_enter(s->co_recv, opaque);
+}
-static int set_cork(int fd, int v)
+static void co_write_request(void *opaque)
{
- return 0;
-}
+ BDRVSheepdogState *s = opaque;
-#else
+ qemu_coroutine_enter(s->co_send, NULL);
+}
-static int set_cork(int fd, int v)
+static int aio_flush_request(void *opaque)
{
- return setsockopt(fd, SOL_TCP, TCP_CORK, &v, sizeof(v));
-}
+ BDRVSheepdogState *s = opaque;
-#endif
+ return !QLIST_EMPTY(&s->outstanding_aio_head);
+}
static int set_nodelay(int fd)
{
return -1;
}
- qemu_aio_set_fd_handler(fd, aio_read_response, NULL, aio_flush_request,
+ qemu_aio_set_fd_handler(fd, co_read_response, NULL, aio_flush_request,
NULL, s);
return fd;
}
return ret;
}
-static int add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
+static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
struct iovec *iov, int niov, int create,
enum AIOCBState aiocb_type)
{
hdr.id = aio_req->id;
- set_cork(s->fd, 1);
+ qemu_co_mutex_lock(&s->lock);
+ s->co_send = qemu_coroutine_self();
+ qemu_aio_set_fd_handler(s->fd, co_read_response, co_write_request,
+ aio_flush_request, NULL, s);
+ socket_set_cork(s->fd, 1);
/* send a header */
- ret = do_write(s->fd, &hdr, sizeof(hdr));
- if (ret) {
+ ret = qemu_co_send(s->fd, &hdr, sizeof(hdr));
+ if (ret < 0) {
+ qemu_co_mutex_unlock(&s->lock);
error_report("failed to send a req, %s", strerror(errno));
return -EIO;
}
if (wlen) {
- ret = do_writev(s->fd, iov, wlen, aio_req->iov_offset);
- if (ret) {
+ ret = qemu_co_sendv(s->fd, iov, wlen, aio_req->iov_offset);
+ if (ret < 0) {
+ qemu_co_mutex_unlock(&s->lock);
error_report("failed to send a data, %s", strerror(errno));
return -EIO;
}
}
- set_cork(s->fd, 0);
+ socket_set_cork(s->fd, 0);
+ qemu_aio_set_fd_handler(s->fd, co_read_response, NULL,
+ aio_flush_request, NULL, s);
+ qemu_co_mutex_unlock(&s->lock);
return 0;
}
bs->total_sectors = s->inode.vdi_size / SECTOR_SIZE;
strncpy(s->name, vdi, sizeof(s->name));
+ qemu_co_mutex_init(&s->lock);
g_free(buf);
return 0;
out:
/*
* 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 calls the AIOCB callback.
+ * Otherwise, this switches back to sd_co_readv/writev.
*/
-static void sd_write_done(SheepdogAIOCB *acb)
+static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
{
int ret;
BDRVSheepdogState *s = acb->common.bs->opaque;
* waiting the response. The responses are received in the
* `aio_read_response' function which is called from the main loop as
* a fd handler.
+ *
+ * Returns 1 when we need to wait a response, 0 when there is no sent
+ * request and -errno in error cases.
*/
-static void sd_readv_writev_bh_cb(void *p)
+static int coroutine_fn sd_co_rw_vector(void *p)
{
SheepdogAIOCB *acb = p;
int ret = 0;
SheepdogInode *inode = &s->inode;
AIOReq *aio_req;
- qemu_bh_delete(acb->bh);
- acb->bh = NULL;
-
if (acb->aiocb_type == AIOCB_WRITE_UDATA && s->is_snapshot) {
/*
* In the case we open the snapshot VDI, Sheepdog creates the
}
out:
if (QLIST_EMPTY(&acb->aioreq_head)) {
- sd_finish_aiocb(acb);
+ return acb->ret;
}
+ return 1;
}
-static BlockDriverAIOCB *sd_aio_writev(BlockDriverState *bs, int64_t sector_num,
- QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb,
- void *opaque)
+static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov)
{
SheepdogAIOCB *acb;
+ int ret;
if (bs->growable && sector_num + nb_sectors > bs->total_sectors) {
/* TODO: shouldn't block here */
if (sd_truncate(bs, (sector_num + nb_sectors) * SECTOR_SIZE) < 0) {
- return NULL;
+ return -EIO;
}
bs->total_sectors = sector_num + nb_sectors;
}
- acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, cb, opaque);
+ acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
acb->aio_done_func = sd_write_done;
acb->aiocb_type = AIOCB_WRITE_UDATA;
- sd_schedule_bh(sd_readv_writev_bh_cb, acb);
- return &acb->common;
+ ret = sd_co_rw_vector(acb);
+ if (ret <= 0) {
+ qemu_aio_release(acb);
+ return ret;
+ }
+
+ qemu_coroutine_yield();
+
+ return acb->ret;
}
-static BlockDriverAIOCB *sd_aio_readv(BlockDriverState *bs, int64_t sector_num,
- QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb,
- void *opaque)
+static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov)
{
SheepdogAIOCB *acb;
- int i;
+ int i, ret;
- acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, cb, opaque);
+ acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
acb->aiocb_type = AIOCB_READ_UDATA;
acb->aio_done_func = sd_finish_aiocb;
memset(qiov->iov[i].iov_base, 0, qiov->iov[i].iov_len);
}
- sd_schedule_bh(sd_readv_writev_bh_cb, acb);
- return &acb->common;
+ ret = sd_co_rw_vector(acb);
+ if (ret <= 0) {
+ qemu_aio_release(acb);
+ return ret;
+ }
+
+ qemu_coroutine_yield();
+
+ return acb->ret;
}
static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
.bdrv_getlength = sd_getlength,
.bdrv_truncate = sd_truncate,
- .bdrv_aio_readv = sd_aio_readv,
- .bdrv_aio_writev = sd_aio_writev,
+ .bdrv_co_readv = sd_co_readv,
+ .bdrv_co_writev = sd_co_writev,
.bdrv_snapshot_create = sd_snapshot_create,
.bdrv_snapshot_goto = sd_snapshot_goto,
projects / qemu.git / blobdiff