Merge remote-tracking branch 'remotes/stefanha-gitlab/tags/block-pull-request' into staging

Pull request

# gpg: Signature made Thu 08 Jul 2021 14:11:37 BST
# gpg:                using RSA key 8695A8BFD3F97CDAAC35775A9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <[email protected]>" [full]
# gpg:                 aka "Stefan Hajnoczi <[email protected]>" [full]
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha-gitlab/tags/block-pull-request:
  block/io: Merge discard request alignments
  block: Add backend_defaults property
  block/file-posix: Optimize for macOS
  util/async: print leaked BH name when AioContext finalizes
  util/async: add a human-readable name to BHs for debugging

Signed-off-by: Peter Maydell <[email protected]>

Author: pm215

block/file-posix.c

@@ -46,6 +46,7 @@
 #if defined(HAVE_HOST_BLOCK_DEVICE)
 #include <paths.h>
 #include <sys/param.h>
+#include <sys/mount.h>
 #include <IOKit/IOKitLib.h>
 #include <IOKit/IOBSD.h>
 #include <IOKit/storage/IOMediaBSDClient.h>
@@ -1254,6 +1255,15 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
         return;
     }
 
+#if defined(__APPLE__) && (__MACH__)
+    struct statfs buf;
+
+    if (!fstatfs(s->fd, &buf)) {
+        bs->bl.opt_transfer = buf.f_iosize;
+        bs->bl.pdiscard_alignment = buf.f_bsize;
+    }
+#endif
+
     if (bs->sg || S_ISBLK(st.st_mode)) {
         int ret = hdev_get_max_hw_transfer(s->fd, &st);
 
@@ -1591,6 +1601,7 @@ static int handle_aiocb_rw(void *opaque)
     }
 }
 
+#if defined(CONFIG_FALLOCATE) || defined(BLKZEROOUT) || defined(BLKDISCARD)
 static int translate_err(int err)
 {
     if (err == -ENODEV || err == -ENOSYS || err == -EOPNOTSUPP ||
@@ -1599,6 +1610,7 @@ static int translate_err(int err)
     }
     return err;
 }
+#endif
 
 #ifdef CONFIG_FALLOCATE
 static int do_fallocate(int fd, int mode, off_t offset, off_t len)
@@ -1811,16 +1823,27 @@ static int handle_aiocb_discard(void *opaque)
             }
         } while (errno == EINTR);
 
-        ret = -errno;
+        ret = translate_err(-errno);
 #endif
     } else {
 #ifdef CONFIG_FALLOCATE_PUNCH_HOLE
         ret = do_fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
                            aiocb->aio_offset, aiocb->aio_nbytes);
+        ret = translate_err(-errno);
+#elif defined(__APPLE__) && (__MACH__)
+        fpunchhole_t fpunchhole;
+        fpunchhole.fp_flags = 0;
+        fpunchhole.reserved = 0;
+        fpunchhole.fp_offset = aiocb->aio_offset;
+        fpunchhole.fp_length = aiocb->aio_nbytes;
+        if (fcntl(s->fd, F_PUNCHHOLE, &fpunchhole) == -1) {
+            ret = errno == ENODEV ? -ENOTSUP : -errno;
+        } else {
+            ret = 0;
+        }
 #endif
     }
 
-    ret = translate_err(ret);
     if (ret == -ENOTSUP) {
         s->has_discard = false;
     }

block/io.c

@@ -125,6 +125,8 @@ void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
 
 static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
 {
+    dst->pdiscard_alignment = MAX(dst->pdiscard_alignment,
+                                  src->pdiscard_alignment);
     dst->opt_transfer = MAX(dst->opt_transfer, src->opt_transfer);
     dst->max_transfer = MIN_NON_ZERO(dst->max_transfer, src->max_transfer);
     dst->max_hw_transfer = MIN_NON_ZERO(dst->max_hw_transfer,

hw/block/block.c

@@ -65,24 +65,58 @@ bool blkconf_blocksizes(BlockConf *conf, Error **errp)
 {
     BlockBackend *blk = conf->blk;
     BlockSizes blocksizes;
-    int backend_ret;
+    BlockDriverState *bs;
+    bool use_blocksizes;
+    bool use_bs;
+
+    switch (conf->backend_defaults) {
+    case ON_OFF_AUTO_AUTO:
+        use_blocksizes = !blk_probe_blocksizes(blk, &blocksizes);
+        use_bs = false;
+        break;
+
+    case ON_OFF_AUTO_ON:
+        use_blocksizes = !blk_probe_blocksizes(blk, &blocksizes);
+        bs = blk_bs(blk);
+        use_bs = bs;
+        break;
+
+    case ON_OFF_AUTO_OFF:
+        use_blocksizes = false;
+        use_bs = false;
+        break;
+
+    default:
+        abort();
+    }
 
-    backend_ret = blk_probe_blocksizes(blk, &blocksizes);
     /* fill in detected values if they are not defined via qemu command line */
     if (!conf->physical_block_size) {
-        if (!backend_ret) {
+        if (use_blocksizes) {
            conf->physical_block_size = blocksizes.phys;
         } else {
             conf->physical_block_size = BDRV_SECTOR_SIZE;
         }
     }
     if (!conf->logical_block_size) {
-        if (!backend_ret) {
+        if (use_blocksizes) {
             conf->logical_block_size = blocksizes.log;
         } else {
             conf->logical_block_size = BDRV_SECTOR_SIZE;
         }
     }
+    if (use_bs) {
+        if (!conf->opt_io_size) {
+            conf->opt_io_size = bs->bl.opt_transfer;
+        }
+        if (conf->discard_granularity == -1) {
+            if (bs->bl.pdiscard_alignment) {
+                conf->discard_granularity = bs->bl.pdiscard_alignment;
+            } else if (bs->bl.request_alignment != 1) {
+                conf->discard_granularity = bs->bl.request_alignment;
+            }
+        }
+    }
 
     if (conf->logical_block_size > conf->physical_block_size) {
         error_setg(errp,

include/block/aio.h

@@ -291,20 +291,45 @@ void aio_context_acquire(AioContext *ctx);
 /* Relinquish ownership of the AioContext. */
 void aio_context_release(AioContext *ctx);
 
+/**
+ * aio_bh_schedule_oneshot_full: Allocate a new bottom half structure that will
+ * run only once and as soon as possible.
+ *
+ * @name: A human-readable identifier for debugging purposes.
+ */
+void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
+                                  const char *name);
+
 /**
  * aio_bh_schedule_oneshot: Allocate a new bottom half structure that will run
  * only once and as soon as possible.
+ *
+ * A convenience wrapper for aio_bh_schedule_oneshot_full() that uses cb as the
+ * name string.
  */
-void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
+#define aio_bh_schedule_oneshot(ctx, cb, opaque) \
+    aio_bh_schedule_oneshot_full((ctx), (cb), (opaque), (stringify(cb)))
 
 /**
- * aio_bh_new: Allocate a new bottom half structure.
+ * aio_bh_new_full: Allocate a new bottom half structure.
  *
  * Bottom halves are lightweight callbacks whose invocation is guaranteed
  * to be wait-free, thread-safe and signal-safe.  The #QEMUBH structure
  * is opaque and must be allocated prior to its use.
+ *
+ * @name: A human-readable identifier for debugging purposes.
+ */
+QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
+                        const char *name);
+
+/**
+ * aio_bh_new: Allocate a new bottom half structure
+ *
+ * A convenience wrapper for aio_bh_new_full() that uses the cb as the name
+ * string.
  */
-QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
+#define aio_bh_new(ctx, cb, opaque) \
+    aio_bh_new_full((ctx), (cb), (opaque), (stringify(cb)))
 
 /**
  * aio_notify: Force processing of pending events.

include/hw/block/block.h

@@ -19,6 +19,7 @@
 
 typedef struct BlockConf {
     BlockBackend *blk;
+    OnOffAuto backend_defaults;
     uint32_t physical_block_size;
     uint32_t logical_block_size;
     uint32_t min_io_size;
@@ -48,6 +49,8 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf)
 }
 
 #define DEFINE_BLOCK_PROPERTIES_BASE(_state, _conf)                     \
+    DEFINE_PROP_ON_OFF_AUTO("backend_defaults", _state,                 \
+                            _conf.backend_defaults, ON_OFF_AUTO_AUTO),  \
     DEFINE_PROP_BLOCKSIZE("logical_block_size", _state,                 \
                           _conf.logical_block_size),                    \
     DEFINE_PROP_BLOCKSIZE("physical_block_size", _state,                \

include/qemu/main-loop.h

@@ -294,7 +294,9 @@ void qemu_cond_timedwait_iothread(QemuCond *cond, int ms);
 
 void qemu_fd_register(int fd);
 
-QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque);
+#define qemu_bh_new(cb, opaque) \
+    qemu_bh_new_full((cb), (opaque), (stringify(cb)))
+QEMUBH *qemu_bh_new_full(QEMUBHFunc *cb, void *opaque, const char *name);
 void qemu_bh_schedule_idle(QEMUBH *bh);
 
 enum {