diff options
Diffstat (limited to 'block')
-rw-r--r-- | block/blkdebug.c | 2 | ||||
-rw-r--r-- | block/blkverify.c | 47 | ||||
-rw-r--r-- | block/curl.c | 192 | ||||
-rw-r--r-- | block/gluster.c | 7 | ||||
-rw-r--r-- | block/iscsi.c | 80 | ||||
-rw-r--r-- | block/linux-aio.c | 24 | ||||
-rw-r--r-- | block/nbd-client.c | 24 | ||||
-rw-r--r-- | block/nbd-client.h | 4 | ||||
-rw-r--r-- | block/nbd.c | 87 | ||||
-rw-r--r-- | block/nfs.c | 81 | ||||
-rw-r--r-- | block/qed-table.c | 8 | ||||
-rw-r--r-- | block/qed.c | 35 | ||||
-rw-r--r-- | block/quorum.c | 48 | ||||
-rw-r--r-- | block/raw-aio.h | 8 | ||||
-rw-r--r-- | block/raw-posix.c | 82 | ||||
-rw-r--r-- | block/raw-win32.c | 54 | ||||
-rw-r--r-- | block/rbd.c | 10 | ||||
-rw-r--r-- | block/sheepdog.c | 167 | ||||
-rw-r--r-- | block/ssh.c | 36 | ||||
-rw-r--r-- | block/vmdk.c | 23 | ||||
-rw-r--r-- | block/win32-aio.c | 27 |
21 files changed, 717 insertions, 329 deletions
diff --git a/block/blkdebug.c b/block/blkdebug.c index 380c736101..f51407de3f 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -471,7 +471,7 @@ static BlockDriverAIOCB *inject_error(BlockDriverState *bs, acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque); acb->ret = -error; - bh = qemu_bh_new(error_callback_bh, acb); + bh = aio_bh_new(bdrv_get_aio_context(bs), error_callback_bh, acb); acb->bh = bh; qemu_bh_schedule(bh); diff --git a/block/blkverify.c b/block/blkverify.c index e1c31171c3..621b78593b 100644 --- a/block/blkverify.c +++ b/block/blkverify.c @@ -39,12 +39,13 @@ struct BlkverifyAIOCB { static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb) { BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb; + AioContext *aio_context = bdrv_get_aio_context(blockacb->bs); bool finished = false; /* Wait until request completes, invokes its callback, and frees itself */ acb->finished = &finished; while (!finished) { - qemu_aio_wait(); + aio_poll(aio_context, true); } } @@ -228,7 +229,8 @@ static void blkverify_aio_cb(void *opaque, int ret) acb->verify(acb); } - acb->bh = qemu_bh_new(blkverify_aio_bh, acb); + acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs), + blkverify_aio_bh, acb); qemu_bh_schedule(acb->bh); break; } @@ -302,21 +304,40 @@ static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs, return bdrv_recurse_is_first_non_filter(s->test_file, candidate); } +/* Propagate AioContext changes to ->test_file */ +static void blkverify_detach_aio_context(BlockDriverState *bs) +{ + BDRVBlkverifyState *s = bs->opaque; + + bdrv_detach_aio_context(s->test_file); +} + +static void blkverify_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVBlkverifyState *s = bs->opaque; + + bdrv_attach_aio_context(s->test_file, new_context); +} + static BlockDriver bdrv_blkverify = { - .format_name = "blkverify", - .protocol_name = "blkverify", - .instance_size = sizeof(BDRVBlkverifyState), + .format_name = "blkverify", + .protocol_name = "blkverify", + .instance_size = sizeof(BDRVBlkverifyState), + + .bdrv_parse_filename = blkverify_parse_filename, + .bdrv_file_open = blkverify_open, + .bdrv_close = blkverify_close, + .bdrv_getlength = blkverify_getlength, - .bdrv_parse_filename = blkverify_parse_filename, - .bdrv_file_open = blkverify_open, - .bdrv_close = blkverify_close, - .bdrv_getlength = blkverify_getlength, + .bdrv_aio_readv = blkverify_aio_readv, + .bdrv_aio_writev = blkverify_aio_writev, + .bdrv_aio_flush = blkverify_aio_flush, - .bdrv_aio_readv = blkverify_aio_readv, - .bdrv_aio_writev = blkverify_aio_writev, - .bdrv_aio_flush = blkverify_aio_flush, + .bdrv_attach_aio_context = blkverify_attach_aio_context, + .bdrv_detach_aio_context = blkverify_detach_aio_context, - .is_filter = true, + .is_filter = true, .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter, }; diff --git a/block/curl.c b/block/curl.c index f491b0ba4c..8c84141ced 100644 --- a/block/curl.c +++ b/block/curl.c @@ -110,6 +110,7 @@ typedef struct BDRVCURLState { size_t readahead_size; bool sslverify; bool accept_range; + AioContext *aio_context; } BDRVCURLState; static void curl_clean_state(CURLState *s); @@ -134,25 +135,29 @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque) #endif static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action, - void *s, void *sp) + void *userp, void *sp) { + BDRVCURLState *s; CURLState *state = NULL; curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state); state->sock_fd = fd; + s = state->s; DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd); switch (action) { case CURL_POLL_IN: - qemu_aio_set_fd_handler(fd, curl_multi_read, NULL, state); + aio_set_fd_handler(s->aio_context, fd, curl_multi_read, + NULL, state); break; case CURL_POLL_OUT: - qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, state); + aio_set_fd_handler(s->aio_context, fd, NULL, curl_multi_do, state); break; case CURL_POLL_INOUT: - qemu_aio_set_fd_handler(fd, curl_multi_read, curl_multi_do, state); + aio_set_fd_handler(s->aio_context, fd, curl_multi_read, + curl_multi_do, state); break; case CURL_POLL_REMOVE: - qemu_aio_set_fd_handler(fd, NULL, NULL, NULL); + aio_set_fd_handler(s->aio_context, fd, NULL, NULL, NULL); break; } @@ -365,7 +370,7 @@ static CURLState *curl_init_state(BDRVCURLState *s) break; } if (!state) { - qemu_aio_wait(); + aio_poll(state->s->aio_context, true); } } while(!state); @@ -422,6 +427,51 @@ static void curl_parse_filename(const char *filename, QDict *options, qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename)); } +static void curl_detach_aio_context(BlockDriverState *bs) +{ + BDRVCURLState *s = bs->opaque; + int i; + + for (i = 0; i < CURL_NUM_STATES; i++) { + if (s->states[i].in_use) { + curl_clean_state(&s->states[i]); + } + if (s->states[i].curl) { + curl_easy_cleanup(s->states[i].curl); + s->states[i].curl = NULL; + } + if (s->states[i].orig_buf) { + g_free(s->states[i].orig_buf); + s->states[i].orig_buf = NULL; + } + } + if (s->multi) { + curl_multi_cleanup(s->multi); + s->multi = NULL; + } + + timer_del(&s->timer); +} + +static void curl_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVCURLState *s = bs->opaque; + + aio_timer_init(new_context, &s->timer, + QEMU_CLOCK_REALTIME, SCALE_NS, + curl_multi_timeout_do, s); + + assert(!s->multi); + s->multi = curl_multi_init(); + s->aio_context = new_context; + curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb); +#ifdef NEED_CURL_TIMER_CALLBACK + curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s); + curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb); +#endif +} + static QemuOptsList runtime_opts = { .name = "curl", .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head), @@ -491,6 +541,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags, } DPRINTF("CURL: Opening %s\n", file); + s->aio_context = bdrv_get_aio_context(bs); s->url = g_strdup(file); state = curl_init_state(s); if (!state) @@ -523,19 +574,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags, curl_easy_cleanup(state->curl); state->curl = NULL; - aio_timer_init(bdrv_get_aio_context(bs), &s->timer, - QEMU_CLOCK_REALTIME, SCALE_NS, - curl_multi_timeout_do, s); - - // Now we know the file exists and its size, so let's - // initialize the multi interface! - - s->multi = curl_multi_init(); - curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb); -#ifdef NEED_CURL_TIMER_CALLBACK - curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s); - curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb); -#endif + curl_attach_aio_context(bs, bdrv_get_aio_context(bs)); qemu_opts_del(opts); return 0; @@ -630,7 +669,7 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs, acb->sector_num = sector_num; acb->nb_sectors = nb_sectors; - acb->bh = qemu_bh_new(curl_readv_bh_cb, acb); + acb->bh = aio_bh_new(bdrv_get_aio_context(bs), curl_readv_bh_cb, acb); qemu_bh_schedule(acb->bh); return &acb->common; } @@ -638,25 +677,9 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs, static void curl_close(BlockDriverState *bs) { BDRVCURLState *s = bs->opaque; - int i; DPRINTF("CURL: Close\n"); - for (i=0; i<CURL_NUM_STATES; i++) { - if (s->states[i].in_use) - curl_clean_state(&s->states[i]); - if (s->states[i].curl) { - curl_easy_cleanup(s->states[i].curl); - s->states[i].curl = NULL; - } - if (s->states[i].orig_buf) { - g_free(s->states[i].orig_buf); - s->states[i].orig_buf = NULL; - } - } - if (s->multi) - curl_multi_cleanup(s->multi); - - timer_del(&s->timer); + curl_detach_aio_context(bs); g_free(s->url); } @@ -668,68 +691,83 @@ static int64_t curl_getlength(BlockDriverState *bs) } static BlockDriver bdrv_http = { - .format_name = "http", - .protocol_name = "http", + .format_name = "http", + .protocol_name = "http", + + .instance_size = sizeof(BDRVCURLState), + .bdrv_parse_filename = curl_parse_filename, + .bdrv_file_open = curl_open, + .bdrv_close = curl_close, + .bdrv_getlength = curl_getlength, - .instance_size = sizeof(BDRVCURLState), - .bdrv_parse_filename = curl_parse_filename, - .bdrv_file_open = curl_open, - .bdrv_close = curl_close, - .bdrv_getlength = curl_getlength, + .bdrv_aio_readv = curl_aio_readv, - .bdrv_aio_readv = curl_aio_readv, + .bdrv_detach_aio_context = curl_detach_aio_context, + .bdrv_attach_aio_context = curl_attach_aio_context, }; static BlockDriver bdrv_https = { - .format_name = "https", - .protocol_name = "https", + .format_name = "https", + .protocol_name = "https", - .instance_size = sizeof(BDRVCURLState), - .bdrv_parse_filename = curl_parse_filename, - .bdrv_file_open = curl_open, - .bdrv_close = curl_close, - .bdrv_getlength = curl_getlength, + .instance_size = sizeof(BDRVCURLState), + .bdrv_parse_filename = curl_parse_filename, + .bdrv_file_open = curl_open, + .bdrv_close = curl_close, + .bdrv_getlength = curl_getlength, - .bdrv_aio_readv = curl_aio_readv, + .bdrv_aio_readv = curl_aio_readv, + + .bdrv_detach_aio_context = curl_detach_aio_context, + .bdrv_attach_aio_context = curl_attach_aio_context, }; static BlockDriver bdrv_ftp = { - .format_name = "ftp", - .protocol_name = "ftp", + .format_name = "ftp", + .protocol_name = "ftp", + + .instance_size = sizeof(BDRVCURLState), + .bdrv_parse_filename = curl_parse_filename, + .bdrv_file_open = curl_open, + .bdrv_close = curl_close, + .bdrv_getlength = curl_getlength, - .instance_size = sizeof(BDRVCURLState), - .bdrv_parse_filename = curl_parse_filename, - .bdrv_file_open = curl_open, - .bdrv_close = curl_close, - .bdrv_getlength = curl_getlength, + .bdrv_aio_readv = curl_aio_readv, - .bdrv_aio_readv = curl_aio_readv, + .bdrv_detach_aio_context = curl_detach_aio_context, + .bdrv_attach_aio_context = curl_attach_aio_context, }; static BlockDriver bdrv_ftps = { - .format_name = "ftps", - .protocol_name = "ftps", + .format_name = "ftps", + .protocol_name = "ftps", - .instance_size = sizeof(BDRVCURLState), - .bdrv_parse_filename = curl_parse_filename, - .bdrv_file_open = curl_open, - .bdrv_close = curl_close, - .bdrv_getlength = curl_getlength, + .instance_size = sizeof(BDRVCURLState), + .bdrv_parse_filename = curl_parse_filename, + .bdrv_file_open = curl_open, + .bdrv_close = curl_close, + .bdrv_getlength = curl_getlength, - .bdrv_aio_readv = curl_aio_readv, + .bdrv_aio_readv = curl_aio_readv, + + .bdrv_detach_aio_context = curl_detach_aio_context, + .bdrv_attach_aio_context = curl_attach_aio_context, }; static BlockDriver bdrv_tftp = { - .format_name = "tftp", - .protocol_name = "tftp", + .format_name = "tftp", + .protocol_name = "tftp", + + .instance_size = sizeof(BDRVCURLState), + .bdrv_parse_filename = curl_parse_filename, + .bdrv_file_open = curl_open, + .bdrv_close = curl_close, + .bdrv_getlength = curl_getlength, - .instance_size = sizeof(BDRVCURLState), - .bdrv_parse_filename = curl_parse_filename, - .bdrv_file_open = curl_open, - .bdrv_close = curl_close, - .bdrv_getlength = curl_getlength, + .bdrv_aio_readv = curl_aio_readv, - .bdrv_aio_readv = curl_aio_readv, + .bdrv_detach_aio_context = curl_detach_aio_context, + .bdrv_attach_aio_context = curl_attach_aio_context, }; static void curl_block_init(void) diff --git a/block/gluster.c b/block/gluster.c index d0726ec92c..114689e441 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -16,6 +16,7 @@ typedef struct GlusterAIOCB { int ret; QEMUBH *bh; Coroutine *coroutine; + AioContext *aio_context; } GlusterAIOCB; typedef struct BDRVGlusterState { @@ -249,7 +250,7 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg) acb->ret = -EIO; /* Partial read/write - fail it */ } - acb->bh = qemu_bh_new(qemu_gluster_complete_aio, acb); + acb->bh = aio_bh_new(acb->aio_context, qemu_gluster_complete_aio, acb); qemu_bh_schedule(acb->bh); } @@ -436,6 +437,7 @@ static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs, acb->size = size; acb->ret = 0; acb->coroutine = qemu_coroutine_self(); + acb->aio_context = bdrv_get_aio_context(bs); ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb); if (ret < 0) { @@ -549,6 +551,7 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs, acb->size = size; acb->ret = 0; acb->coroutine = qemu_coroutine_self(); + acb->aio_context = bdrv_get_aio_context(bs); if (write) { ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0, @@ -605,6 +608,7 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs) acb->size = 0; acb->ret = 0; acb->coroutine = qemu_coroutine_self(); + acb->aio_context = bdrv_get_aio_context(bs); ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb); if (ret < 0) { @@ -633,6 +637,7 @@ static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs, acb->size = 0; acb->ret = 0; acb->coroutine = qemu_coroutine_self(); + acb->aio_context = bdrv_get_aio_context(bs); ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb); if (ret < 0) { diff --git a/block/iscsi.c b/block/iscsi.c index 3892cc551e..877b877cf2 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -49,6 +49,7 @@ typedef struct IscsiLun { struct iscsi_context *iscsi; + AioContext *aio_context; int lun; enum scsi_inquiry_peripheral_device_type type; int block_size; @@ -73,6 +74,7 @@ typedef struct IscsiTask { struct scsi_task *task; Coroutine *co; QEMUBH *bh; + IscsiLun *iscsilun; } IscsiTask; typedef struct IscsiAIOCB { @@ -133,7 +135,7 @@ iscsi_schedule_bh(IscsiAIOCB *acb) if (acb->bh) { return; } - acb->bh = qemu_bh_new(iscsi_bh_cb, acb); + acb->bh = aio_bh_new(acb->iscsilun->aio_context, iscsi_bh_cb, acb); qemu_bh_schedule(acb->bh); } @@ -169,7 +171,8 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status, out: if (iTask->co) { - iTask->bh = qemu_bh_new(iscsi_co_generic_bh_cb, iTask); + iTask->bh = aio_bh_new(iTask->iscsilun->aio_context, + iscsi_co_generic_bh_cb, iTask); qemu_bh_schedule(iTask->bh); } } @@ -177,8 +180,9 @@ out: static void iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask) { *iTask = (struct IscsiTask) { - .co = qemu_coroutine_self(), - .retries = ISCSI_CMD_RETRIES, + .co = qemu_coroutine_self(), + .retries = ISCSI_CMD_RETRIES, + .iscsilun = iscsilun, }; } @@ -209,7 +213,7 @@ iscsi_aio_cancel(BlockDriverAIOCB *blockacb) iscsi_abort_task_cb, acb); while (acb->status == -EINPROGRESS) { - qemu_aio_wait(); + aio_poll(iscsilun->aio_context, true); } } @@ -232,10 +236,11 @@ iscsi_set_events(IscsiLun *iscsilun) ev = POLLIN; ev |= iscsi_which_events(iscsi); if (ev != iscsilun->events) { - qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), - iscsi_process_read, - (ev & POLLOUT) ? iscsi_process_write : NULL, - iscsilun); + aio_set_fd_handler(iscsilun->aio_context, + iscsi_get_fd(iscsi), + iscsi_process_read, + (ev & POLLOUT) ? iscsi_process_write : NULL, + iscsilun); } @@ -791,7 +796,7 @@ static int iscsi_ioctl(BlockDriverState *bs, unsigned long int req, void *buf) iscsi_aio_ioctl(bs, req, buf, ioctl_cb, &status); while (status == -EINPROGRESS) { - qemu_aio_wait(); + aio_poll(iscsilun->aio_context, true); } return 0; @@ -1195,6 +1200,40 @@ fail_with_err: return NULL; } +static void iscsi_detach_aio_context(BlockDriverState *bs) +{ + IscsiLun *iscsilun = bs->opaque; + + aio_set_fd_handler(iscsilun->aio_context, + iscsi_get_fd(iscsilun->iscsi), + NULL, NULL, NULL); + iscsilun->events = 0; + + if (iscsilun->nop_timer) { + timer_del(iscsilun->nop_timer); + timer_free(iscsilun->nop_timer); + iscsilun->nop_timer = NULL; + } +} + +static void iscsi_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + IscsiLun *iscsilun = bs->opaque; + + iscsilun->aio_context = new_context; + iscsi_set_events(iscsilun); + +#if defined(LIBISCSI_FEATURE_NOP_COUNTER) + /* Set up a timer for sending out iSCSI NOPs */ + iscsilun->nop_timer = aio_timer_new(iscsilun->aio_context, + QEMU_CLOCK_REALTIME, SCALE_MS, + iscsi_nop_timed_event, iscsilun); + timer_mod(iscsilun->nop_timer, + qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL); +#endif +} + /* * We support iscsi url's on the form * iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun> @@ -1301,6 +1340,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags, } iscsilun->iscsi = iscsi; + iscsilun->aio_context = bdrv_get_aio_context(bs); iscsilun->lun = iscsi_url->lun; iscsilun->has_write_same = true; @@ -1374,11 +1414,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags, scsi_free_scsi_task(task); task = NULL; -#if defined(LIBISCSI_FEATURE_NOP_COUNTER) - /* Set up a timer for sending out iSCSI NOPs */ - iscsilun->nop_timer = timer_new_ms(QEMU_CLOCK_REALTIME, iscsi_nop_timed_event, iscsilun); - timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL); -#endif + iscsi_attach_aio_context(bs, iscsilun->aio_context); /* Guess the internal cluster (page) size of the iscsi target by the means * of opt_unmap_gran. Transfer the unmap granularity only if it has a @@ -1422,11 +1458,7 @@ static void iscsi_close(BlockDriverState *bs) IscsiLun *iscsilun = bs->opaque; struct iscsi_context *iscsi = iscsilun->iscsi; - if (iscsilun->nop_timer) { - timer_del(iscsilun->nop_timer); - timer_free(iscsilun->nop_timer); - } - qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), NULL, NULL, NULL); + iscsi_detach_aio_context(bs); iscsi_destroy_context(iscsi); g_free(iscsilun->zeroblock); g_free(iscsilun->allocationmap); @@ -1530,10 +1562,7 @@ static int iscsi_create(const char *filename, QEMUOptionParameter *options, if (ret != 0) { goto out; } - if (iscsilun->nop_timer) { - timer_del(iscsilun->nop_timer); - timer_free(iscsilun->nop_timer); - } + iscsi_detach_aio_context(bs); if (iscsilun->type != TYPE_DISK) { ret = -ENODEV; goto out; @@ -1604,6 +1633,9 @@ static BlockDriver bdrv_iscsi = { .bdrv_ioctl = iscsi_ioctl, .bdrv_aio_ioctl = iscsi_aio_ioctl, #endif + + .bdrv_detach_aio_context = iscsi_detach_aio_context, + .bdrv_attach_aio_context = iscsi_attach_aio_context, }; static QemuOptsList qemu_iscsi_opts = { diff --git a/block/linux-aio.c b/block/linux-aio.c index 53434e2df5..f0a2c087b2 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -177,6 +177,20 @@ out_free_aiocb: return NULL; } +void laio_detach_aio_context(void *s_, AioContext *old_context) +{ + struct qemu_laio_state *s = s_; + + aio_set_event_notifier(old_context, &s->e, NULL); +} + +void laio_attach_aio_context(void *s_, AioContext *new_context) +{ + struct qemu_laio_state *s = s_; + + aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb); +} + void *laio_init(void) { struct qemu_laio_state *s; @@ -190,8 +204,6 @@ void *laio_init(void) goto out_close_efd; } - qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb); - return s; out_close_efd: @@ -200,3 +212,11 @@ out_free_state: g_free(s); return NULL; } + +void laio_cleanup(void *s_) +{ + struct qemu_laio_state *s = s_; + + event_notifier_cleanup(&s->e); + g_free(s); +} diff --git a/block/nbd-client.c b/block/nbd-client.c index 7d698cb619..6e1c97cad0 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -49,7 +49,7 @@ static void nbd_teardown_connection(NbdClientSession *client) shutdown(client->sock, 2); nbd_recv_coroutines_enter_all(client); - qemu_aio_set_fd_handler(client->sock, NULL, NULL, NULL); + nbd_client_session_detach_aio_context(client); closesocket(client->sock); client->sock = -1; } @@ -103,11 +103,14 @@ static int nbd_co_send_request(NbdClientSession *s, struct nbd_request *request, QEMUIOVector *qiov, int offset) { + AioContext *aio_context; int rc, ret; qemu_co_mutex_lock(&s->send_mutex); s->send_coroutine = qemu_coroutine_self(); - qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s); + aio_context = bdrv_get_aio_context(s->bs); + aio_set_fd_handler(aio_context, s->sock, + nbd_reply_ready, nbd_restart_write, s); if (qiov) { if (!s->is_unix) { socket_set_cork(s->sock, 1); @@ -126,7 +129,7 @@ static int nbd_co_send_request(NbdClientSession *s, } else { rc = nbd_send_request(s->sock, request); } - qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s); + aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, s); s->send_coroutine = NULL; qemu_co_mutex_unlock(&s->send_mutex); return rc; @@ -335,6 +338,19 @@ int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num, } +void nbd_client_session_detach_aio_context(NbdClientSession *client) +{ + aio_set_fd_handler(bdrv_get_aio_context(client->bs), client->sock, + NULL, NULL, NULL); +} + +void nbd_client_session_attach_aio_context(NbdClientSession *client, + AioContext *new_context) +{ + aio_set_fd_handler(new_context, client->sock, + nbd_reply_ready, NULL, client); +} + void nbd_client_session_close(NbdClientSession *client) { struct nbd_request request = { @@ -381,7 +397,7 @@ int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs, /* Now that we're connected, set the socket to be non-blocking and * kick the reply mechanism. */ qemu_set_nonblock(sock); - qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, client); + nbd_client_session_attach_aio_context(client, bdrv_get_aio_context(bs)); logout("Established connection with NBD server\n"); return 0; diff --git a/block/nbd-client.h b/block/nbd-client.h index f2a63378bb..cd478f3a98 100644 --- a/block/nbd-client.h +++ b/block/nbd-client.h @@ -47,4 +47,8 @@ int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num, int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov); +void nbd_client_session_detach_aio_context(NbdClientSession *client); +void nbd_client_session_attach_aio_context(NbdClientSession *client, + AioContext *new_context); + #endif /* NBD_CLIENT_H */ diff --git a/block/nbd.c b/block/nbd.c index 613f2581ae..4eda0958d7 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -323,46 +323,67 @@ static int64_t nbd_getlength(BlockDriverState *bs) return s->client.size; } +static void nbd_detach_aio_context(BlockDriverState *bs) +{ + BDRVNBDState *s = bs->opaque; + + nbd_client_session_detach_aio_context(&s->client); +} + +static void nbd_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVNBDState *s = bs->opaque; + + nbd_client_session_attach_aio_context(&s->client, new_context); +} + static BlockDriver bdrv_nbd = { - .format_name = "nbd", - .protocol_name = "nbd", - .instance_size = sizeof(BDRVNBDState), - .bdrv_parse_filename = nbd_parse_filename, - .bdrv_file_open = nbd_open, - .bdrv_co_readv = nbd_co_readv, - .bdrv_co_writev = nbd_co_writev, - .bdrv_close = nbd_close, - .bdrv_co_flush_to_os = nbd_co_flush, - .bdrv_co_discard = nbd_co_discard, - .bdrv_getlength = nbd_getlength, + .format_name = "nbd", + .protocol_name = "nbd", + .instance_size = sizeof(BDRVNBDState), + .bdrv_parse_filename = nbd_parse_filename, + .bdrv_file_open = nbd_open, + .bdrv_co_readv = nbd_co_readv, + .bdrv_co_writev = nbd_co_writev, + .bdrv_close = nbd_close, + .bdrv_co_flush_to_os = nbd_co_flush, + .bdrv_co_discard = nbd_co_discard, + .bdrv_getlength = nbd_getlength, + .bdrv_detach_aio_context = nbd_detach_aio_context, + .bdrv_attach_aio_context = nbd_attach_aio_context, }; static BlockDriver bdrv_nbd_tcp = { - .format_name = "nbd", - .protocol_name = "nbd+tcp", - .instance_size = sizeof(BDRVNBDState), - .bdrv_parse_filename = nbd_parse_filename, - .bdrv_file_open = nbd_open, - .bdrv_co_readv = nbd_co_readv, - .bdrv_co_writev = nbd_co_writev, - .bdrv_close = nbd_close, - .bdrv_co_flush_to_os = nbd_co_flush, - .bdrv_co_discard = nbd_co_discard, - .bdrv_getlength = nbd_getlength, + .format_name = "nbd", + .protocol_name = "nbd+tcp", + .instance_size = sizeof(BDRVNBDState), + .bdrv_parse_filename = nbd_parse_filename, + .bdrv_file_open = nbd_open, + .bdrv_co_readv = nbd_co_readv, + .bdrv_co_writev = nbd_co_writev, + .bdrv_close = nbd_close, + .bdrv_co_flush_to_os = nbd_co_flush, + .bdrv_co_discard = nbd_co_discard, + .bdrv_getlength = nbd_getlength, + .bdrv_detach_aio_context = nbd_detach_aio_context, + .bdrv_attach_aio_context = nbd_attach_aio_context, }; static BlockDriver bdrv_nbd_unix = { - .format_name = "nbd", - .protocol_name = "nbd+unix", - .instance_size = sizeof(BDRVNBDState), - .bdrv_parse_filename = nbd_parse_filename, - .bdrv_file_open = nbd_open, - .bdrv_co_readv = nbd_co_readv, - .bdrv_co_writev = nbd_co_writev, - .bdrv_close = nbd_close, - .bdrv_co_flush_to_os = nbd_co_flush, - .bdrv_co_discard = nbd_co_discard, - .bdrv_getlength = nbd_getlength, + .format_name = "nbd", + .protocol_name = "nbd+unix", + .instance_size = sizeof(BDRVNBDState), + .bdrv_parse_filename = nbd_parse_filename, + .bdrv_file_open = nbd_open, + .bdrv_co_readv = nbd_co_readv, + .bdrv_co_writev = nbd_co_writev, + .bdrv_close = nbd_close, + .bdrv_co_flush_to_os = nbd_co_flush, + .bdrv_co_discard = nbd_co_discard, + .bdrv_getlength = nbd_getlength, + .bdrv_detach_aio_context = nbd_detach_aio_context, + .bdrv_attach_aio_context = nbd_attach_aio_context, }; static void bdrv_nbd_init(void) diff --git a/block/nfs.c b/block/nfs.c index 539bd951df..bd9177f3ae 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -40,6 +40,7 @@ typedef struct NFSClient { struct nfsfh *fh; int events; bool has_zero_init; + AioContext *aio_context; } NFSClient; typedef struct NFSRPC { @@ -49,6 +50,7 @@ typedef struct NFSRPC { struct stat *st; Coroutine *co; QEMUBH *bh; + NFSClient *client; } NFSRPC; static void nfs_process_read(void *arg); @@ -58,10 +60,11 @@ static void nfs_set_events(NFSClient *client) { int ev = nfs_which_events(client->context); if (ev != client->events) { - qemu_aio_set_fd_handler(nfs_get_fd(client->context), - (ev & POLLIN) ? nfs_process_read : NULL, - (ev & POLLOUT) ? nfs_process_write : NULL, - client); + aio_set_fd_handler(client->aio_context, + nfs_get_fd(client->context), + (ev & POLLIN) ? nfs_process_read : NULL, + (ev & POLLOUT) ? nfs_process_write : NULL, + client); } client->events = ev; @@ -84,7 +87,8 @@ static void nfs_process_write(void *arg) static void nfs_co_init_task(NFSClient *client, NFSRPC *task) { *task = (NFSRPC) { - .co = qemu_coroutine_self(), + .co = qemu_coroutine_self(), + .client = client, }; } @@ -116,7 +120,8 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data, error_report("NFS Error: %s", nfs_get_error(nfs)); } if (task->co) { - task->bh = qemu_bh_new(nfs_co_generic_bh_cb, task); + task->bh = aio_bh_new(task->client->aio_context, + nfs_co_generic_bh_cb, task); qemu_bh_schedule(task->bh); } } @@ -224,13 +229,34 @@ static QemuOptsList runtime_opts = { }, }; +static void nfs_detach_aio_context(BlockDriverState *bs) +{ + NFSClient *client = bs->opaque; + + aio_set_fd_handler(client->aio_context, + nfs_get_fd(client->context), + NULL, NULL, NULL); + client->events = 0; +} + +static void nfs_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + NFSClient *client = bs->opaque; + + client->aio_context = new_context; + nfs_set_events(client); +} + static void nfs_client_close(NFSClient *client) { if (client->context) { if (client->fh) { nfs_close(client->context, client->fh); } - qemu_aio_set_fd_handler(nfs_get_fd(client->context), NULL, NULL, NULL); + aio_set_fd_handler(client->aio_context, + nfs_get_fd(client->context), + NULL, NULL, NULL); nfs_destroy_context(client->context); } memset(client, 0, sizeof(NFSClient)); @@ -345,6 +371,8 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags, QemuOpts *opts; Error *local_err = NULL; + client->aio_context = bdrv_get_aio_context(bs); + opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &local_err); if (local_err) { @@ -368,6 +396,8 @@ static int nfs_file_create(const char *url, QEMUOptionParameter *options, int64_t total_size = 0; NFSClient *client = g_malloc0(sizeof(NFSClient)); + client->aio_context = qemu_get_aio_context(); + /* Read out options */ while (options && options->name) { if (!strcmp(options->name, "size")) { @@ -407,7 +437,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs) while (!task.complete) { nfs_set_events(client); - qemu_aio_wait(); + aio_poll(client->aio_context, true); } return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize); @@ -420,22 +450,25 @@ static int nfs_file_truncate(BlockDriverState *bs, int64_t offset) } static BlockDriver bdrv_nfs = { - .format_name = "nfs", - .protocol_name = "nfs", - - .instance_size = sizeof(NFSClient), - .bdrv_needs_filename = true, - .bdrv_has_zero_init = nfs_has_zero_init, - .bdrv_get_allocated_file_size = nfs_get_allocated_file_size, - .bdrv_truncate = nfs_file_truncate, - - .bdrv_file_open = nfs_file_open, - .bdrv_close = nfs_file_close, - .bdrv_create = nfs_file_create, - - .bdrv_co_readv = nfs_co_readv, - .bdrv_co_writev = nfs_co_writev, - .bdrv_co_flush_to_disk = nfs_co_flush, + .format_name = "nfs", + .protocol_name = "nfs", + + .instance_size = sizeof(NFSClient), + .bdrv_needs_filename = true, + .bdrv_has_zero_init = nfs_has_zero_init, + .bdrv_get_allocated_file_size = nfs_get_allocated_file_size, + .bdrv_truncate = nfs_file_truncate, + + .bdrv_file_open = nfs_file_open, + .bdrv_close = nfs_file_close, + .bdrv_create = nfs_file_create, + + .bdrv_co_readv = nfs_co_readv, + .bdrv_co_writev = nfs_co_writev, + .bdrv_co_flush_to_disk = nfs_co_flush, + + .bdrv_detach_aio_context = nfs_detach_aio_context, + .bdrv_attach_aio_context = nfs_attach_aio_context, }; static void nfs_block_init(void) diff --git a/block/qed-table.c b/block/qed-table.c index 76d2dcccf8..f61107a1cf 100644 --- a/block/qed-table.c +++ b/block/qed-table.c @@ -173,7 +173,7 @@ int qed_read_l1_table_sync(BDRVQEDState *s) qed_read_table(s, s->header.l1_table_offset, s->l1_table, qed_sync_cb, &ret); while (ret == -EINPROGRESS) { - qemu_aio_wait(); + aio_poll(bdrv_get_aio_context(s->bs), true); } return ret; @@ -194,7 +194,7 @@ int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index, qed_write_l1_table(s, index, n, qed_sync_cb, &ret); while (ret == -EINPROGRESS) { - qemu_aio_wait(); + aio_poll(bdrv_get_aio_context(s->bs), true); } return ret; @@ -267,7 +267,7 @@ int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset qed_read_l2_table(s, request, offset, qed_sync_cb, &ret); while (ret == -EINPROGRESS) { - qemu_aio_wait(); + aio_poll(bdrv_get_aio_context(s->bs), true); } return ret; @@ -289,7 +289,7 @@ int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request, qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret); while (ret == -EINPROGRESS) { - qemu_aio_wait(); + aio_poll(bdrv_get_aio_context(s->bs), true); } return ret; diff --git a/block/qed.c b/block/qed.c index c130e42d0d..79f5bd392a 100644 --- a/block/qed.c +++ b/block/qed.c @@ -21,12 +21,13 @@ static void qed_aio_cancel(BlockDriverAIOCB *blockacb) { QEDAIOCB *acb = (QEDAIOCB *)blockacb; + AioContext *aio_context = bdrv_get_aio_context(blockacb->bs); bool finished = false; /* Wait for the request to finish */ acb->finished = &finished; while (!finished) { - qemu_aio_wait(); + aio_poll(aio_context, true); } } @@ -373,6 +374,27 @@ static void bdrv_qed_rebind(BlockDriverState *bs) s->bs = bs; } +static void bdrv_qed_detach_aio_context(BlockDriverState *bs) +{ + BDRVQEDState *s = bs->opaque; + + qed_cancel_need_check_timer(s); + timer_free(s->need_check_timer); +} + +static void bdrv_qed_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVQEDState *s = bs->opaque; + + s->need_check_timer = aio_timer_new(new_context, + QEMU_CLOCK_VIRTUAL, SCALE_NS, + qed_need_check_timer_cb, s); + if (s->header.features & QED_F_NEED_CHECK) { + qed_start_need_check_timer(s); + } +} + static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { @@ -496,8 +518,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags, } } - s->need_check_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, - qed_need_check_timer_cb, s); + bdrv_qed_attach_aio_context(bs, bdrv_get_aio_context(bs)); out: if (ret) { @@ -528,8 +549,7 @@ static void bdrv_qed_close(BlockDriverState *bs) { BDRVQEDState *s = bs->opaque; - qed_cancel_need_check_timer(s); - timer_free(s->need_check_timer); + bdrv_qed_detach_aio_context(bs); /* Ensure writes reach stable storage */ bdrv_flush(bs->file); @@ -919,7 +939,8 @@ static void qed_aio_complete(QEDAIOCB *acb, int ret) /* Arrange for a bh to invoke the completion function */ acb->bh_ret = ret; - acb->bh = qemu_bh_new(qed_aio_complete_bh, acb); + acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs), + qed_aio_complete_bh, acb); qemu_bh_schedule(acb->bh); /* Start next allocating write request waiting behind this one. Note that @@ -1644,6 +1665,8 @@ static BlockDriver bdrv_qed = { .bdrv_change_backing_file = bdrv_qed_change_backing_file, .bdrv_invalidate_cache = bdrv_qed_invalidate_cache, .bdrv_check = bdrv_qed_check, + .bdrv_detach_aio_context = bdrv_qed_detach_aio_context, + .bdrv_attach_aio_context = bdrv_qed_attach_aio_context, }; static void bdrv_qed_init(void) diff --git a/block/quorum.c b/block/quorum.c index ecec3a5407..426077a520 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -848,25 +848,49 @@ static void quorum_close(BlockDriverState *bs) g_free(s->bs); } +static void quorum_detach_aio_context(BlockDriverState *bs) +{ + BDRVQuorumState *s = bs->opaque; + int i; + + for (i = 0; i < s->num_children; i++) { + bdrv_detach_aio_context(s->bs[i]); + } +} + +static void quorum_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVQuorumState *s = bs->opaque; + int i; + + for (i = 0; i < s->num_children; i++) { + bdrv_attach_aio_context(s->bs[i], new_context); + } +} + static BlockDriver bdrv_quorum = { - .format_name = "quorum", - .protocol_name = "quorum", + .format_name = "quorum", + .protocol_name = "quorum", + + .instance_size = sizeof(BDRVQuorumState), - .instance_size = sizeof(BDRVQuorumState), + .bdrv_file_open = quorum_open, + .bdrv_close = quorum_close, - .bdrv_file_open = quorum_open, - .bdrv_close = quorum_close, + .bdrv_co_flush_to_disk = quorum_co_flush, - .bdrv_co_flush_to_disk = quorum_co_flush, + .bdrv_getlength = quorum_getlength, - .bdrv_getlength = quorum_getlength, + .bdrv_aio_readv = quorum_aio_readv, + .bdrv_aio_writev = quorum_aio_writev, + .bdrv_invalidate_cache = quorum_invalidate_cache, - .bdrv_aio_readv = quorum_aio_readv, - .bdrv_aio_writev = quorum_aio_writev, - .bdrv_invalidate_cache = quorum_invalidate_cache, + .bdrv_detach_aio_context = quorum_detach_aio_context, + .bdrv_attach_aio_context = quorum_attach_aio_context, - .is_filter = true, - .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter, + .is_filter = true, + .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter, }; static void bdrv_quorum_init(void) diff --git a/block/raw-aio.h b/block/raw-aio.h index 7ad0a8a0a7..8cf084eeb5 100644 --- a/block/raw-aio.h +++ b/block/raw-aio.h @@ -34,19 +34,27 @@ /* linux-aio.c - Linux native implementation */ #ifdef CONFIG_LINUX_AIO void *laio_init(void); +void laio_cleanup(void *s); BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd, int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, BlockDriverCompletionFunc *cb, void *opaque, int type); +void laio_detach_aio_context(void *s, AioContext *old_context); +void laio_attach_aio_context(void *s, AioContext *new_context); #endif #ifdef _WIN32 typedef struct QEMUWin32AIOState QEMUWin32AIOState; QEMUWin32AIOState *win32_aio_init(void); +void win32_aio_cleanup(QEMUWin32AIOState *aio); int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile); BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs, QEMUWin32AIOState *aio, HANDLE hfile, int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, BlockDriverCompletionFunc *cb, void *opaque, int type); +void win32_aio_detach_aio_context(QEMUWin32AIOState *aio, + AioContext *old_context); +void win32_aio_attach_aio_context(QEMUWin32AIOState *aio, + AioContext *new_context); #endif #endif /* QEMU_RAW_AIO_H */ diff --git a/block/raw-posix.c b/block/raw-posix.c index b7f0f2624b..c2b30be3d3 100644 --- a/block/raw-posix.c +++ b/block/raw-posix.c @@ -307,6 +307,29 @@ static void raw_parse_flags(int bdrv_flags, int *open_flags) } } +static void raw_detach_aio_context(BlockDriverState *bs) +{ +#ifdef CONFIG_LINUX_AIO + BDRVRawState *s = bs->opaque; + + if (s->use_aio) { + laio_detach_aio_context(s->aio_ctx, bdrv_get_aio_context(bs)); + } +#endif +} + +static void raw_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ +#ifdef CONFIG_LINUX_AIO + BDRVRawState *s = bs->opaque; + + if (s->use_aio) { + laio_attach_aio_context(s->aio_ctx, new_context); + } +#endif +} + #ifdef CONFIG_LINUX_AIO static int raw_set_aio(void **aio_ctx, int *use_aio, int bdrv_flags) { @@ -447,6 +470,8 @@ static int raw_open_common(BlockDriverState *bs, QDict *options, } #endif + raw_attach_aio_context(bs, bdrv_get_aio_context(bs)); + ret = 0; fail: if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) { @@ -1059,6 +1084,14 @@ static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs, static void raw_close(BlockDriverState *bs) { BDRVRawState *s = bs->opaque; + + raw_detach_aio_context(bs); + +#ifdef CONFIG_LINUX_AIO + if (s->use_aio) { + laio_cleanup(s->aio_ctx); + } +#endif if (s->fd >= 0) { qemu_close(s->fd); s->fd = -1; @@ -1478,6 +1511,9 @@ static BlockDriver bdrv_file = { .bdrv_get_allocated_file_size = raw_get_allocated_file_size, + .bdrv_detach_aio_context = raw_detach_aio_context, + .bdrv_attach_aio_context = raw_attach_aio_context, + .create_options = raw_create_options, }; @@ -1878,6 +1914,9 @@ static BlockDriver bdrv_host_device = { .bdrv_get_allocated_file_size = raw_get_allocated_file_size, + .bdrv_detach_aio_context = raw_detach_aio_context, + .bdrv_attach_aio_context = raw_attach_aio_context, + /* generic scsi device */ #ifdef __linux__ .bdrv_ioctl = hdev_ioctl, @@ -2020,6 +2059,9 @@ static BlockDriver bdrv_host_floppy = { .bdrv_get_allocated_file_size = raw_get_allocated_file_size, + .bdrv_detach_aio_context = raw_detach_aio_context, + .bdrv_attach_aio_context = raw_attach_aio_context, + /* removable device support */ .bdrv_is_inserted = floppy_is_inserted, .bdrv_media_changed = floppy_media_changed, @@ -2145,6 +2187,9 @@ static BlockDriver bdrv_host_cdrom = { .bdrv_get_allocated_file_size = raw_get_allocated_file_size, + .bdrv_detach_aio_context = raw_detach_aio_context, + .bdrv_attach_aio_context = raw_attach_aio_context, + /* removable device support */ .bdrv_is_inserted = cdrom_is_inserted, .bdrv_eject = cdrom_eject, @@ -2276,6 +2321,9 @@ static BlockDriver bdrv_host_cdrom = { .bdrv_get_allocated_file_size = raw_get_allocated_file_size, + .bdrv_detach_aio_context = raw_detach_aio_context, + .bdrv_attach_aio_context = raw_attach_aio_context, + /* removable device support */ .bdrv_is_inserted = cdrom_is_inserted, .bdrv_eject = cdrom_eject, @@ -2283,40 +2331,6 @@ static BlockDriver bdrv_host_cdrom = { }; #endif /* __FreeBSD__ */ -#ifdef CONFIG_LINUX_AIO -/** - * Return the file descriptor for Linux AIO - * - * This function is a layering violation and should be removed when it becomes - * possible to call the block layer outside the global mutex. It allows the - * caller to hijack the file descriptor so I/O can be performed outside the - * block layer. - */ -int raw_get_aio_fd(BlockDriverState *bs) -{ - BDRVRawState *s; - - if (!bs->drv) { - return -ENOMEDIUM; - } - - if (bs->drv == bdrv_find_format("raw")) { - bs = bs->file; - } - - /* raw-posix has several protocols so just check for raw_aio_readv */ - if (bs->drv->bdrv_aio_readv != raw_aio_readv) { - return -ENOTSUP; - } - - s = bs->opaque; - if (!s->use_aio) { - return -ENOTSUP; - } - return s->fd; -} -#endif /* CONFIG_LINUX_AIO */ - static void bdrv_file_init(void) { /* diff --git a/block/raw-win32.c b/block/raw-win32.c index 064ea3123c..324e8187f5 100644 --- a/block/raw-win32.c +++ b/block/raw-win32.c @@ -36,8 +36,6 @@ #define FTYPE_CD 1 #define FTYPE_HARDDISK 2 -static QEMUWin32AIOState *aio; - typedef struct RawWin32AIOData { BlockDriverState *bs; HANDLE hfile; @@ -202,6 +200,25 @@ static int set_sparse(int fd) NULL, 0, NULL, 0, &returned, NULL); } +static void raw_detach_aio_context(BlockDriverState *bs) +{ + BDRVRawState *s = bs->opaque; + + if (s->aio) { + win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs)); + } +} + +static void raw_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVRawState *s = bs->opaque; + + if (s->aio) { + win32_aio_attach_aio_context(s->aio, new_context); + } +} + static void raw_probe_alignment(BlockDriverState *bs) { BDRVRawState *s = bs->opaque; @@ -300,15 +317,6 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, raw_parse_flags(flags, &access_flags, &overlapped); - if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) { - aio = win32_aio_init(); - if (aio == NULL) { - error_setg(errp, "Could not initialize AIO"); - ret = -EINVAL; - goto fail; - } - } - if (filename[0] && filename[1] == ':') { snprintf(s->drive_path, sizeof(s->drive_path), "%c:\\", filename[0]); } else if (filename[0] == '\\' && filename[1] == '\\') { @@ -335,13 +343,23 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, } if (flags & BDRV_O_NATIVE_AIO) { - ret = win32_aio_attach(aio, s->hfile); + s->aio = win32_aio_init(); + if (s->aio == NULL) { + CloseHandle(s->hfile); + error_setg(errp, "Could not initialize AIO"); + ret = -EINVAL; + goto fail; + } + + ret = win32_aio_attach(s->aio, s->hfile); if (ret < 0) { + win32_aio_cleanup(s->aio); CloseHandle(s->hfile); error_setg_errno(errp, -ret, "Could not enable AIO"); goto fail; } - s->aio = aio; + + win32_aio_attach_aio_context(s->aio, bdrv_get_aio_context(bs)); } raw_probe_alignment(bs); @@ -389,6 +407,13 @@ static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs, static void raw_close(BlockDriverState *bs) { BDRVRawState *s = bs->opaque; + + if (s->aio) { + win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs)); + win32_aio_cleanup(s->aio); + s->aio = NULL; + } + CloseHandle(s->hfile); if (bs->open_flags & BDRV_O_TEMPORARY) { unlink(bs->filename); @@ -684,6 +709,9 @@ static BlockDriver bdrv_host_device = { .bdrv_aio_writev = raw_aio_writev, .bdrv_aio_flush = raw_aio_flush, + .bdrv_detach_aio_context = raw_detach_aio_context, + .bdrv_attach_aio_context = raw_attach_aio_context, + .bdrv_getlength = raw_getlength, .has_variable_length = true, diff --git a/block/rbd.c b/block/rbd.c index 09af48426e..93639f783c 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -555,7 +555,7 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb) acb->cancelled = 1; while (acb->status == -EINPROGRESS) { - qemu_aio_wait(); + aio_poll(bdrv_get_aio_context(acb->common.bs), true); } qemu_aio_release(acb); @@ -588,7 +588,8 @@ static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb) rcb->ret = rbd_aio_get_return_value(c); rbd_aio_release(c); - acb->bh = qemu_bh_new(rbd_finish_bh, rcb); + acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs), + rbd_finish_bh, rcb); qemu_bh_schedule(acb->bh); } @@ -684,13 +685,16 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs, } if (r < 0) { - goto failed; + goto failed_completion; } return &acb->common; +failed_completion: + rbd_aio_release(c); failed: g_free(rcb); + qemu_vfree(acb->bounce); qemu_aio_release(acb); return NULL; } diff --git a/block/sheepdog.c b/block/sheepdog.c index 4ecbf5f498..1fa19399f0 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -200,6 +200,8 @@ typedef struct SheepdogInode { uint32_t data_vdi_id[MAX_DATA_OBJS]; } SheepdogInode; +#define SD_INODE_HEADER_SIZE offsetof(SheepdogInode, data_vdi_id) + /* * 64 bit FNV-1a non-zero initial basis */ @@ -282,6 +284,7 @@ typedef struct AIOReq { unsigned int data_len; uint8_t flags; uint32_t id; + bool create; QLIST_ENTRY(AIOReq) aio_siblings; } AIOReq; @@ -314,6 +317,7 @@ struct SheepdogAIOCB { typedef struct BDRVSheepdogState { BlockDriverState *bs; + AioContext *aio_context; SheepdogInode inode; @@ -404,7 +408,7 @@ static const char * sd_strerror(int err) static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb, uint64_t oid, unsigned int data_len, - uint64_t offset, uint8_t flags, + uint64_t offset, uint8_t flags, bool create, uint64_t base_oid, unsigned int iov_offset) { AIOReq *aio_req; @@ -418,6 +422,7 @@ static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb, aio_req->data_len = data_len; aio_req->flags = flags; aio_req->id = s->aioreq_seq_num++; + aio_req->create = create; acb->nr_pending++; return aio_req; @@ -496,7 +501,7 @@ static void sd_aio_cancel(BlockDriverAIOCB *blockacb) sd_finish_aiocb(acb); return; } - qemu_aio_wait(); + aio_poll(s->aio_context, true); } } @@ -578,6 +583,7 @@ static void restart_co_req(void *opaque) typedef struct SheepdogReqCo { int sockfd; + AioContext *aio_context; SheepdogReq *hdr; void *data; unsigned int *wlen; @@ -598,14 +604,14 @@ static coroutine_fn void do_co_req(void *opaque) unsigned int *rlen = srco->rlen; co = qemu_coroutine_self(); - qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, co); + aio_set_fd_handler(srco->aio_context, sockfd, NULL, restart_co_req, co); ret = send_co_req(sockfd, hdr, data, wlen); if (ret < 0) { goto out; } - qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, co); + aio_set_fd_handler(srco->aio_context, sockfd, restart_co_req, NULL, co); ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr)); if (ret != sizeof(*hdr)) { @@ -630,18 +636,19 @@ static coroutine_fn void do_co_req(void *opaque) out: /* there is at most one request for this sockfd, so it is safe to * set each handler to NULL. */ - qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL); + aio_set_fd_handler(srco->aio_context, sockfd, NULL, NULL, NULL); srco->ret = ret; srco->finished = true; } -static int do_req(int sockfd, SheepdogReq *hdr, void *data, - unsigned int *wlen, unsigned int *rlen) +static int do_req(int sockfd, AioContext *aio_context, SheepdogReq *hdr, + void *data, unsigned int *wlen, unsigned int *rlen) { Coroutine *co; SheepdogReqCo srco = { .sockfd = sockfd, + .aio_context = aio_context, .hdr = hdr, .data = data, .wlen = wlen, @@ -656,7 +663,7 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data, co = qemu_coroutine_create(do_co_req); qemu_coroutine_enter(co, &srco); while (!srco.finished) { - qemu_aio_wait(); + aio_poll(aio_context, true); } } @@ -664,8 +671,8 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data, } static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req, - struct iovec *iov, int niov, bool create, - enum AIOCBState aiocb_type); + struct iovec *iov, int niov, + enum AIOCBState aiocb_type); static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req); static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag); static int get_sheep_fd(BDRVSheepdogState *s, Error **errp); @@ -698,7 +705,7 @@ static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid) /* move aio_req from pending list to inflight one */ QLIST_REMOVE(aio_req, aio_siblings); QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings); - add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, false, + add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, acb->aiocb_type); } } @@ -709,7 +716,7 @@ static coroutine_fn void reconnect_to_sdog(void *opaque) BDRVSheepdogState *s = opaque; AIOReq *aio_req, *next; - qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL); + aio_set_fd_handler(s->aio_context, s->fd, NULL, NULL, NULL); close(s->fd); s->fd = -1; @@ -797,7 +804,7 @@ static void coroutine_fn aio_read_response(void *opaque) } idx = data_oid_to_idx(aio_req->oid); - if (s->inode.data_vdi_id[idx] != s->inode.vdi_id) { + if (aio_req->create) { /* * If the object is newly created one, we need to update * the vdi object (metadata object). min_dirty_data_idx @@ -922,7 +929,7 @@ static int get_sheep_fd(BDRVSheepdogState *s, Error **errp) return fd; } - qemu_aio_set_fd_handler(fd, co_read_response, NULL, s); + aio_set_fd_handler(s->aio_context, fd, co_read_response, NULL, s); return fd; } @@ -1092,7 +1099,7 @@ static int find_vdi_name(BDRVSheepdogState *s, const char *filename, hdr.snapid = snapid; hdr.flags = SD_FLAG_CMD_WRITE; - ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen); + ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen); if (ret) { error_setg_errno(errp, -ret, "cannot get vdi info"); goto out; @@ -1117,8 +1124,8 @@ out: } static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req, - struct iovec *iov, int niov, bool create, - enum AIOCBState aiocb_type) + struct iovec *iov, int niov, + enum AIOCBState aiocb_type) { int nr_copies = s->inode.nr_copies; SheepdogObjReq hdr; @@ -1129,6 +1136,7 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req, uint64_t offset = aio_req->offset; uint8_t flags = aio_req->flags; uint64_t old_oid = aio_req->base_oid; + bool create = aio_req->create; if (!nr_copies) { error_report("bug"); @@ -1173,7 +1181,8 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req, 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, s); + aio_set_fd_handler(s->aio_context, s->fd, + co_read_response, co_write_request, s); socket_set_cork(s->fd, 1); /* send a header */ @@ -1191,12 +1200,13 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req, } out: socket_set_cork(s->fd, 0); - qemu_aio_set_fd_handler(s->fd, co_read_response, NULL, s); + aio_set_fd_handler(s->aio_context, s->fd, co_read_response, NULL, s); s->co_send = NULL; qemu_co_mutex_unlock(&s->lock); } -static int read_write_object(int fd, char *buf, uint64_t oid, uint8_t copies, +static int read_write_object(int fd, AioContext *aio_context, char *buf, + uint64_t oid, uint8_t copies, unsigned int datalen, uint64_t offset, bool write, bool create, uint32_t cache_flags) { @@ -1229,7 +1239,7 @@ static int read_write_object(int fd, char *buf, uint64_t oid, uint8_t copies, hdr.offset = offset; hdr.copies = copies; - ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen); + ret = do_req(fd, aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen); if (ret) { error_report("failed to send a request to the sheep"); return ret; @@ -1244,19 +1254,23 @@ static int read_write_object(int fd, char *buf, uint64_t oid, uint8_t copies, } } -static int read_object(int fd, char *buf, uint64_t oid, uint8_t copies, +static int read_object(int fd, AioContext *aio_context, char *buf, + uint64_t oid, uint8_t copies, unsigned int datalen, uint64_t offset, uint32_t cache_flags) { - return read_write_object(fd, buf, oid, copies, datalen, offset, false, + return read_write_object(fd, aio_context, buf, oid, copies, + datalen, offset, false, false, cache_flags); } -static int write_object(int fd, char *buf, uint64_t oid, uint8_t copies, +static int write_object(int fd, AioContext *aio_context, 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, buf, oid, copies, datalen, offset, true, + return read_write_object(fd, aio_context, buf, oid, copies, + datalen, offset, true, create, cache_flags); } @@ -1275,7 +1289,7 @@ static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag) return -EIO; } - inode = g_malloc(sizeof(s->inode)); + inode = g_malloc(SD_INODE_HEADER_SIZE); ret = find_vdi_name(s, s->name, snapid, tag, &vid, false, &local_err); if (ret) { @@ -1284,14 +1298,15 @@ static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag) goto out; } - ret = read_object(fd, (char *)inode, vid_to_vdi_oid(vid), - s->inode.nr_copies, sizeof(*inode), 0, s->cache_flags); + ret = read_object(fd, s->aio_context, (char *)inode, vid_to_vdi_oid(vid), + s->inode.nr_copies, SD_INODE_HEADER_SIZE, 0, + s->cache_flags); if (ret < 0) { goto out; } if (inode->vdi_id != s->inode.vdi_id) { - memcpy(&s->inode, inode, sizeof(s->inode)); + memcpy(&s->inode, inode, SD_INODE_HEADER_SIZE); } out: @@ -1315,6 +1330,7 @@ static bool check_simultaneous_create(BDRVSheepdogState *s, AIOReq *aio_req) DPRINTF("simultaneous create to %" PRIx64 "\n", aio_req->oid); aio_req->flags = 0; aio_req->base_oid = 0; + aio_req->create = false; QLIST_REMOVE(aio_req, aio_siblings); QLIST_INSERT_HEAD(&s->pending_aio_head, aio_req, aio_siblings); return true; @@ -1327,7 +1343,8 @@ static bool check_simultaneous_create(BDRVSheepdogState *s, AIOReq *aio_req) static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req) { SheepdogAIOCB *acb = aio_req->aiocb; - bool create = false; + + aio_req->create = false; /* check whether this request becomes a CoW one */ if (acb->aiocb_type == AIOCB_WRITE_UDATA && is_data_obj(aio_req->oid)) { @@ -1345,20 +1362,36 @@ static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req) aio_req->base_oid = vid_to_data_oid(s->inode.data_vdi_id[idx], idx); aio_req->flags |= SD_FLAG_CMD_COW; } - create = true; + aio_req->create = true; } out: if (is_data_obj(aio_req->oid)) { - add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, create, + add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, acb->aiocb_type); } else { struct iovec iov; iov.iov_base = &s->inode; iov.iov_len = sizeof(s->inode); - add_aio_request(s, aio_req, &iov, 1, false, AIOCB_WRITE_UDATA); + add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA); } } +static void sd_detach_aio_context(BlockDriverState *bs) +{ + BDRVSheepdogState *s = bs->opaque; + + aio_set_fd_handler(s->aio_context, s->fd, NULL, NULL, NULL); +} + +static void sd_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVSheepdogState *s = bs->opaque; + + s->aio_context = new_context; + aio_set_fd_handler(new_context, s->fd, co_read_response, NULL, s); +} + /* TODO Convert to fine grained options */ static QemuOptsList runtime_opts = { .name = "sheepdog", @@ -1387,6 +1420,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags, const char *filename; s->bs = bs; + s->aio_context = bdrv_get_aio_context(bs); opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &local_err); @@ -1448,8 +1482,8 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags, } buf = g_malloc(SD_INODE_SIZE); - ret = read_object(fd, buf, vid_to_vdi_oid(vid), 0, SD_INODE_SIZE, 0, - s->cache_flags); + ret = read_object(fd, s->aio_context, buf, vid_to_vdi_oid(vid), + 0, SD_INODE_SIZE, 0, s->cache_flags); closesocket(fd); @@ -1469,7 +1503,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags, g_free(buf); return 0; out: - qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL); + aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd, NULL, NULL, NULL); if (s->fd >= 0) { closesocket(s->fd); } @@ -1512,7 +1546,7 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot, hdr.copy_policy = s->inode.copy_policy; hdr.copies = s->inode.nr_copies; - ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen); + ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen); closesocket(fd); @@ -1766,7 +1800,8 @@ static void sd_close(BlockDriverState *bs) hdr.data_length = wlen; hdr.flags = SD_FLAG_CMD_WRITE; - ret = do_req(fd, (SheepdogReq *)&hdr, s->name, &wlen, &rlen); + ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, + s->name, &wlen, &rlen); closesocket(fd); @@ -1775,7 +1810,7 @@ static void sd_close(BlockDriverState *bs) error_report("%s, %s", sd_strerror(rsp->result), s->name); } - qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL); + aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd, NULL, NULL, NULL); closesocket(s->fd); g_free(s->host_spec); } @@ -1812,8 +1847,9 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset) /* 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, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id), - s->inode.nr_copies, datalen, 0, false, s->cache_flags); + ret = write_object(fd, s->aio_context, (char *)&s->inode, + vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies, + datalen, 0, false, s->cache_flags); close(fd); if (ret < 0) { @@ -1849,9 +1885,9 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb) iov.iov_base = &s->inode; iov.iov_len = sizeof(s->inode); aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id), - data_len, offset, 0, 0, offset); + 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, false, AIOCB_WRITE_UDATA); + add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA); acb->aio_done_func = sd_finish_aiocb; acb->aiocb_type = AIOCB_WRITE_UDATA; @@ -1882,7 +1918,8 @@ static bool sd_delete(BDRVSheepdogState *s) return false; } - ret = do_req(fd, (SheepdogReq *)&hdr, s->name, &wlen, &rlen); + ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, + s->name, &wlen, &rlen); closesocket(fd); if (ret) { return false; @@ -1939,8 +1976,8 @@ static int sd_create_branch(BDRVSheepdogState *s) goto out; } - ret = read_object(fd, buf, vid_to_vdi_oid(vid), s->inode.nr_copies, - SD_INODE_SIZE, 0, s->cache_flags); + ret = read_object(fd, s->aio_context, buf, vid_to_vdi_oid(vid), + s->inode.nr_copies, SD_INODE_SIZE, 0, s->cache_flags); closesocket(fd); @@ -2049,7 +2086,8 @@ static int coroutine_fn sd_co_rw_vector(void *p) DPRINTF("new oid %" PRIx64 "\n", oid); } - aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, old_oid, done); + aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, create, + old_oid, done); QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings); if (create) { @@ -2058,7 +2096,7 @@ static int coroutine_fn sd_co_rw_vector(void *p) } } - add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, create, + add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, acb->aiocb_type); done: offset = 0; @@ -2138,9 +2176,9 @@ static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs) acb->aio_done_func = sd_finish_aiocb; aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id), - 0, 0, 0, 0, 0); + 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, false, acb->aiocb_type); + add_aio_request(s, aio_req, NULL, 0, acb->aiocb_type); qemu_coroutine_yield(); return acb->ret; @@ -2187,8 +2225,9 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) goto cleanup; } - ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id), - s->inode.nr_copies, datalen, 0, false, s->cache_flags); + ret = write_object(fd, s->aio_context, (char *)&s->inode, + vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies, + datalen, 0, false, s->cache_flags); if (ret < 0) { error_report("failed to write snapshot's inode."); goto cleanup; @@ -2203,8 +2242,9 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) goto cleanup; } - ret = read_object(fd, (char *)inode, vid_to_vdi_oid(new_vid), - s->inode.nr_copies, datalen, 0, s->cache_flags); + ret = read_object(fd, s->aio_context, (char *)inode, + vid_to_vdi_oid(new_vid), s->inode.nr_copies, datalen, 0, + s->cache_flags); if (ret < 0) { error_report("failed to read new inode info. %s", strerror(errno)); @@ -2311,7 +2351,8 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab) req.opcode = SD_OP_READ_VDIS; req.data_length = max; - ret = do_req(fd, (SheepdogReq *)&req, vdi_inuse, &wlen, &rlen); + ret = do_req(fd, s->aio_context, (SheepdogReq *)&req, + vdi_inuse, &wlen, &rlen); closesocket(fd); if (ret) { @@ -2338,7 +2379,8 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab) } /* we don't need to read entire object */ - ret = read_object(fd, (char *)&inode, vid_to_vdi_oid(vid), + ret = read_object(fd, s->aio_context, (char *)&inode, + vid_to_vdi_oid(vid), 0, SD_INODE_SIZE - sizeof(inode.data_vdi_id), 0, s->cache_flags); @@ -2403,11 +2445,11 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data, create = (offset == 0); if (load) { - ret = read_object(fd, (char *)data, vmstate_oid, + ret = read_object(fd, s->aio_context, (char *)data, vmstate_oid, s->inode.nr_copies, data_len, offset, s->cache_flags); } else { - ret = write_object(fd, (char *)data, vmstate_oid, + ret = write_object(fd, s->aio_context, (char *)data, vmstate_oid, s->inode.nr_copies, data_len, offset, create, s->cache_flags); } @@ -2580,6 +2622,9 @@ static BlockDriver bdrv_sheepdog = { .bdrv_save_vmstate = sd_save_vmstate, .bdrv_load_vmstate = sd_load_vmstate, + .bdrv_detach_aio_context = sd_detach_aio_context, + .bdrv_attach_aio_context = sd_attach_aio_context, + .create_options = sd_create_options, }; @@ -2610,6 +2655,9 @@ static BlockDriver bdrv_sheepdog_tcp = { .bdrv_save_vmstate = sd_save_vmstate, .bdrv_load_vmstate = sd_load_vmstate, + .bdrv_detach_aio_context = sd_detach_aio_context, + .bdrv_attach_aio_context = sd_attach_aio_context, + .create_options = sd_create_options, }; @@ -2640,6 +2688,9 @@ static BlockDriver bdrv_sheepdog_unix = { .bdrv_save_vmstate = sd_save_vmstate, .bdrv_load_vmstate = sd_load_vmstate, + .bdrv_detach_aio_context = sd_detach_aio_context, + .bdrv_attach_aio_context = sd_attach_aio_context, + .create_options = sd_create_options, }; diff --git a/block/ssh.c b/block/ssh.c index b2129714bc..9779eac2bd 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -773,7 +773,7 @@ static void restart_coroutine(void *opaque) qemu_coroutine_enter(co, NULL); } -static coroutine_fn void set_fd_handler(BDRVSSHState *s) +static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs) { int r; IOHandler *rd_handler = NULL, *wr_handler = NULL; @@ -791,24 +791,26 @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s) DPRINTF("s->sock=%d rd_handler=%p wr_handler=%p", s->sock, rd_handler, wr_handler); - qemu_aio_set_fd_handler(s->sock, rd_handler, wr_handler, co); + aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, + rd_handler, wr_handler, co); } -static coroutine_fn void clear_fd_handler(BDRVSSHState *s) +static coroutine_fn void clear_fd_handler(BDRVSSHState *s, + BlockDriverState *bs) { DPRINTF("s->sock=%d", s->sock); - qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL); + aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, NULL, NULL, NULL); } /* A non-blocking call returned EAGAIN, so yield, ensuring the * handlers are set up so that we'll be rescheduled when there is an * interesting event on the socket. */ -static coroutine_fn void co_yield(BDRVSSHState *s) +static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs) { - set_fd_handler(s); + set_fd_handler(s, bs); qemu_coroutine_yield(); - clear_fd_handler(s); + clear_fd_handler(s, bs); } /* SFTP has a function `libssh2_sftp_seek64' which seeks to a position @@ -838,7 +840,7 @@ static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags) } } -static coroutine_fn int ssh_read(BDRVSSHState *s, +static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs, int64_t offset, size_t size, QEMUIOVector *qiov) { @@ -871,7 +873,7 @@ static coroutine_fn int ssh_read(BDRVSSHState *s, DPRINTF("sftp_read returned %zd", r); if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) { - co_yield(s); + co_yield(s, bs); goto again; } if (r < 0) { @@ -906,14 +908,14 @@ static coroutine_fn int ssh_co_readv(BlockDriverState *bs, int ret; qemu_co_mutex_lock(&s->lock); - ret = ssh_read(s, sector_num * BDRV_SECTOR_SIZE, + ret = ssh_read(s, bs, sector_num * BDRV_SECTOR_SIZE, nb_sectors * BDRV_SECTOR_SIZE, qiov); qemu_co_mutex_unlock(&s->lock); return ret; } -static int ssh_write(BDRVSSHState *s, +static int ssh_write(BDRVSSHState *s, BlockDriverState *bs, int64_t offset, size_t size, QEMUIOVector *qiov) { @@ -941,7 +943,7 @@ static int ssh_write(BDRVSSHState *s, DPRINTF("sftp_write returned %zd", r); if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) { - co_yield(s); + co_yield(s, bs); goto again; } if (r < 0) { @@ -960,7 +962,7 @@ static int ssh_write(BDRVSSHState *s, */ if (r == 0) { ssh_seek(s, offset + written, SSH_SEEK_WRITE|SSH_SEEK_FORCE); - co_yield(s); + co_yield(s, bs); goto again; } @@ -988,7 +990,7 @@ static coroutine_fn int ssh_co_writev(BlockDriverState *bs, int ret; qemu_co_mutex_lock(&s->lock); - ret = ssh_write(s, sector_num * BDRV_SECTOR_SIZE, + ret = ssh_write(s, bs, sector_num * BDRV_SECTOR_SIZE, nb_sectors * BDRV_SECTOR_SIZE, qiov); qemu_co_mutex_unlock(&s->lock); @@ -1009,7 +1011,7 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what) #ifdef HAS_LIBSSH2_SFTP_FSYNC -static coroutine_fn int ssh_flush(BDRVSSHState *s) +static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs) { int r; @@ -1017,7 +1019,7 @@ static coroutine_fn int ssh_flush(BDRVSSHState *s) again: r = libssh2_sftp_fsync(s->sftp_handle); if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) { - co_yield(s); + co_yield(s, bs); goto again; } if (r == LIBSSH2_ERROR_SFTP_PROTOCOL && @@ -1039,7 +1041,7 @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs) int ret; qemu_co_mutex_lock(&s->lock); - ret = ssh_flush(s); + ret = ssh_flush(s, bs); qemu_co_mutex_unlock(&s->lock); return ret; diff --git a/block/vmdk.c b/block/vmdk.c index 2b38f61fcd..b8a476278a 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -2096,6 +2096,27 @@ static int vmdk_get_info(BlockDriverState *bs, BlockDriverInfo *bdi) return 0; } +static void vmdk_detach_aio_context(BlockDriverState *bs) +{ + BDRVVmdkState *s = bs->opaque; + int i; + + for (i = 0; i < s->num_extents; i++) { + bdrv_detach_aio_context(s->extents[i].file); + } +} + +static void vmdk_attach_aio_context(BlockDriverState *bs, + AioContext *new_context) +{ + BDRVVmdkState *s = bs->opaque; + int i; + + for (i = 0; i < s->num_extents; i++) { + bdrv_attach_aio_context(s->extents[i].file, new_context); + } +} + static QEMUOptionParameter vmdk_create_options[] = { { .name = BLOCK_OPT_SIZE, @@ -2153,6 +2174,8 @@ static BlockDriver bdrv_vmdk = { .bdrv_get_specific_info = vmdk_get_specific_info, .bdrv_refresh_limits = vmdk_refresh_limits, .bdrv_get_info = vmdk_get_info, + .bdrv_detach_aio_context = vmdk_detach_aio_context, + .bdrv_attach_aio_context = vmdk_attach_aio_context, .create_options = vmdk_create_options, }; diff --git a/block/win32-aio.c b/block/win32-aio.c index 5d1d199b61..8e417f70ae 100644 --- a/block/win32-aio.c +++ b/block/win32-aio.c @@ -40,6 +40,7 @@ struct QEMUWin32AIOState { HANDLE hIOCP; EventNotifier e; int count; + bool is_aio_context_attached; }; typedef struct QEMUWin32AIOCB { @@ -114,7 +115,7 @@ static void win32_aio_cancel(BlockDriverAIOCB *blockacb) * wait for completion. */ while (!HasOverlappedIoCompleted(&waiocb->ov)) { - qemu_aio_wait(); + aio_poll(bdrv_get_aio_context(blockacb->bs), true); } } @@ -180,6 +181,20 @@ int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile) } } +void win32_aio_detach_aio_context(QEMUWin32AIOState *aio, + AioContext *old_context) +{ + aio_set_event_notifier(old_context, &aio->e, NULL); + aio->is_aio_context_attached = false; +} + +void win32_aio_attach_aio_context(QEMUWin32AIOState *aio, + AioContext *new_context) +{ + aio->is_aio_context_attached = true; + aio_set_event_notifier(new_context, &aio->e, win32_aio_completion_cb); +} + QEMUWin32AIOState *win32_aio_init(void) { QEMUWin32AIOState *s; @@ -194,8 +209,6 @@ QEMUWin32AIOState *win32_aio_init(void) goto out_close_efd; } - qemu_aio_set_event_notifier(&s->e, win32_aio_completion_cb); - return s; out_close_efd: @@ -204,3 +217,11 @@ out_free_state: g_free(s); return NULL; } + +void win32_aio_cleanup(QEMUWin32AIOState *aio) +{ + assert(!aio->is_aio_context_attached); + CloseHandle(aio->hIOCP); + event_notifier_cleanup(&aio->e); + g_free(aio); +} |