block: add bdrv_co_discard and bdrv_aio_discard support

This similarly adds support for coroutine and asynchronous discard.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

5 files changed, 109 insertions, 17 deletions

diff --git a/block.c b/block.c
index 7b8b14d971..28508f21d1 100644
--- a/block.c
+++ b/block.c
@@ -1768,17 +1768,6 @@ int bdrv_has_zero_init(BlockDriverState *bs)
     return 1;
 }
 
-int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
-{
-    if (!bs->drv) {
-        return -ENOMEDIUM;
-    }
-    if (!bs->drv->bdrv_discard) {
-        return 0;
-    }
-    return bs->drv->bdrv_discard(bs, sector_num, nb_sectors);
-}
-
 /*
  * Returns true iff the specified sector is present in the disk image. Drivers
  * not implementing the functionality are assumed to not support backing files,
@@ -2754,6 +2743,34 @@ BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
     return &acb->common;
 }
 
+static void coroutine_fn bdrv_aio_discard_co_entry(void *opaque)
+{
+    BlockDriverAIOCBCoroutine *acb = opaque;
+    BlockDriverState *bs = acb->common.bs;
+
+    acb->req.error = bdrv_co_discard(bs, acb->req.sector, acb->req.nb_sectors);
+    acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
+    qemu_bh_schedule(acb->bh);
+}
+
+BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    Coroutine *co;
+    BlockDriverAIOCBCoroutine *acb;
+
+    trace_bdrv_aio_discard(bs, sector_num, nb_sectors, opaque);
+
+    acb = qemu_aio_get(&bdrv_em_co_aio_pool, bs, cb, opaque);
+    acb->req.sector = sector_num;
+    acb->req.nb_sectors = nb_sectors;
+    co = qemu_coroutine_create(bdrv_aio_discard_co_entry);
+    qemu_coroutine_enter(co, acb);
+
+    return &acb->common;
+}
+
 void bdrv_init(void)
 {
     module_call_init(MODULE_INIT_BLOCK);
@@ -2915,6 +2932,69 @@ int bdrv_flush(BlockDriverState *bs)
     return rwco.ret;
 }
 
+static void coroutine_fn bdrv_discard_co_entry(void *opaque)
+{
+    RwCo *rwco = opaque;
+
+    rwco->ret = bdrv_co_discard(rwco->bs, rwco->sector_num, rwco->nb_sectors);
+}
+
+int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
+                                 int nb_sectors)
+{
+    if (!bs->drv) {
+        return -ENOMEDIUM;
+    } else if (bdrv_check_request(bs, sector_num, nb_sectors)) {
+        return -EIO;
+    } else if (bs->read_only) {
+        return -EROFS;
+    } else if (bs->drv->bdrv_co_discard) {
+        return bs->drv->bdrv_co_discard(bs, sector_num, nb_sectors);
+    } else if (bs->drv->bdrv_aio_discard) {
+        BlockDriverAIOCB *acb;
+        CoroutineIOCompletion co = {
+            .coroutine = qemu_coroutine_self(),
+        };
+
+        acb = bs->drv->bdrv_aio_discard(bs, sector_num, nb_sectors,
+                                        bdrv_co_io_em_complete, &co);
+        if (acb == NULL) {
+            return -EIO;
+        } else {
+            qemu_coroutine_yield();
+            return co.ret;
+        }
+    } else if (bs->drv->bdrv_discard) {
+        return bs->drv->bdrv_discard(bs, sector_num, nb_sectors);
+    } else {
+        return 0;
+    }
+}
+
+int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
+{
+    Coroutine *co;
+    RwCo rwco = {
+        .bs = bs,
+        .sector_num = sector_num,
+        .nb_sectors = nb_sectors,
+        .ret = NOT_DONE,
+    };
+
+    if (qemu_in_coroutine()) {
+        /* Fast-path if already in coroutine context */
+        bdrv_discard_co_entry(&rwco);
+    } else {
+        co = qemu_coroutine_create(bdrv_discard_co_entry);
+        qemu_coroutine_enter(co, &rwco);
+        while (rwco.ret == NOT_DONE) {
+            qemu_aio_wait();
+        }
+    }
+
+    return rwco.ret;
+}
+
 /**************************************************************/
 /* removable device support */
 
diff --git a/block.h b/block.h
index 65c51663fa..5a042c96e7 100644
--- a/block.h
+++ b/block.h
@@ -166,6 +166,9 @@ BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
                                   BlockDriverCompletionFunc *cb, void *opaque);
 BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
                                  BlockDriverCompletionFunc *cb, void *opaque);
+BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
+                                   int64_t sector_num, int nb_sectors,
+                                   BlockDriverCompletionFunc *cb, void *opaque);
 void bdrv_aio_cancel(BlockDriverAIOCB *acb);
 
 typedef struct BlockRequest {
@@ -196,6 +199,7 @@ void bdrv_flush_all(void);
 void bdrv_close_all(void);
 
 int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors);
+int bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors);
 int bdrv_has_zero_init(BlockDriverState *bs);
 int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                       int *pnum);
diff --git a/block/raw.c b/block/raw.c
index 39a3a9afae..33cc4716d3 100644
--- a/block/raw.c
+++ b/block/raw.c
@@ -45,9 +45,10 @@ static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
    return 1; /* everything can be opened as raw image */
 }
 
-static int raw_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
+static int coroutine_fn raw_co_discard(BlockDriverState *bs,
+                                       int64_t sector_num, int nb_sectors)
 {
-    return bdrv_discard(bs->file, sector_num, nb_sectors);
+    return bdrv_co_discard(bs->file, sector_num, nb_sectors);
 }
 
 static int raw_is_inserted(BlockDriverState *bs)
@@ -109,15 +110,16 @@ static BlockDriver bdrv_raw = {
 
     .bdrv_open          = raw_open,
     .bdrv_close         = raw_close,
+
     .bdrv_co_readv      = raw_co_readv,
     .bdrv_co_writev     = raw_co_writev,
     .bdrv_co_flush      = raw_co_flush,
+    .bdrv_co_discard    = raw_co_discard,
+
     .bdrv_probe         = raw_probe,
     .bdrv_getlength     = raw_getlength,
     .bdrv_truncate      = raw_truncate,
 
-    .bdrv_discard       = raw_discard,
-
     .bdrv_is_inserted   = raw_is_inserted,
     .bdrv_media_changed = raw_media_changed,
     .bdrv_eject         = raw_eject,
diff --git a/block_int.h b/block_int.h
index 9cb536d392..384598ff02 100644
--- a/block_int.h
+++ b/block_int.h
@@ -63,6 +63,8 @@ struct BlockDriver {
     void (*bdrv_close)(BlockDriverState *bs);
     int (*bdrv_create)(const char *filename, QEMUOptionParameter *options);
     int (*bdrv_flush)(BlockDriverState *bs);
+    int (*bdrv_discard)(BlockDriverState *bs, int64_t sector_num,
+                        int nb_sectors);
     int (*bdrv_is_allocated)(BlockDriverState *bs, int64_t sector_num,
                              int nb_sectors, int *pnum);
     int (*bdrv_set_key)(BlockDriverState *bs, const char *key);
@@ -76,14 +78,17 @@ struct BlockDriver {
         BlockDriverCompletionFunc *cb, void *opaque);
     BlockDriverAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
         BlockDriverCompletionFunc *cb, void *opaque);
-    int (*bdrv_discard)(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors);
+    BlockDriverAIOCB *(*bdrv_aio_discard)(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque);
 
     int coroutine_fn (*bdrv_co_readv)(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
     int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
     int coroutine_fn (*bdrv_co_flush)(BlockDriverState *bs);
+    int coroutine_fn (*bdrv_co_discard)(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors);
 
     int (*bdrv_aio_multiwrite)(BlockDriverState *bs, BlockRequest *reqs,
         int num_reqs);
diff --git a/trace-events b/trace-events
index 7f9cec4071..49ac1c170b 100644
--- a/trace-events
+++ b/trace-events
@@ -61,6 +61,7 @@ multiwrite_cb(void *mcb, int ret) "mcb %p ret %d"
 bdrv_aio_multiwrite(void *mcb, int num_callbacks, int num_reqs) "mcb %p num_callbacks %d num_reqs %d"
 bdrv_aio_multiwrite_earlyfail(void *mcb) "mcb %p"
 bdrv_aio_multiwrite_latefail(void *mcb, int i) "mcb %p i %d"
+bdrv_aio_discard(void *bs, int64_t sector_num, int nb_sectors, void *opaque) "bs %p sector_num %"PRId64" nb_sectors %d opaque %p"
 bdrv_aio_flush(void *bs, void *opaque) "bs %p opaque %p"
 bdrv_aio_readv(void *bs, int64_t sector_num, int nb_sectors, void *opaque) "bs %p sector_num %"PRId64" nb_sectors %d opaque %p"
 bdrv_aio_writev(void *bs, int64_t sector_num, int nb_sectors, void *opaque) "bs %p sector_num %"PRId64" nb_sectors %d opaque %p"