Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches

- NBD server: Fix crashes related to switching between AioContexts
- file-posix: Workaround for discard/write_zeroes on buggy filesystems
- Follow-up fixes for the reopen vs. permission changes
- quorum: Fix error handling for flush
- block-copy: Refactor copy_range handling
- docs: Describe how to use 'null-co' block driver

# gpg: Signature made Wed 02 Jun 2021 14:44:15 BST
# gpg:                using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg:                issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream:
  docs/secure-coding-practices: Describe how to use 'null-co' block driver
  block-copy: refactor copy_range handling
  block-copy: fix block_copy_task_entry() progress update
  nbd/server: Use drained block ops to quiesce the server
  block-backend: add drained_poll
  block: improve permission conflict error message
  block: simplify bdrv_child_user_desc()
  block/vvfat: inherit child_vvfat_qcow from child_of_bds
  block: improve bdrv_child_get_parent_desc()
  block-backend: improve blk_root_get_parent_desc()
  block: document child argument of bdrv_attach_child_common()
  block/file-posix: Try other fallbacks after invalid FALLOC_FL_ZERO_RANGE
  block/file-posix: Fix problem with fallocate(PUNCH_HOLE) on GPFS
  block: drop BlockBackendRootState::read_only
  block: drop BlockDriverState::read_only
  block: consistently use bdrv_is_read_only()
  block/vvfat: fix vvfat_child_perm crash
  block/vvfat: child_vvfat_qcow: add .get_parent_aio_context, fix crash
  qemu-io-cmds: assert that we don't have .perm requested in no-blk case
  block/quorum: Provide .bdrv_co_flush instead of .bdrv_co_flush_to_disk

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 61 insertions, 21 deletions

diff --git a/nbd/server.c b/nbd/server.c
index 86a44a9b41..b60ebc3ab6 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -1513,6 +1513,11 @@ static void nbd_request_put(NBDRequestData *req)
     g_free(req);
 
     client->nb_requests--;
+
+    if (client->quiescing && client->nb_requests == 0) {
+        aio_wait_kick();
+    }
+
     nbd_client_receive_next_request(client);
 
     nbd_client_put(client);
@@ -1530,49 +1535,68 @@ static void blk_aio_attached(AioContext *ctx, void *opaque)
     QTAILQ_FOREACH(client, &exp->clients, next) {
         qio_channel_attach_aio_context(client->ioc, ctx);
 
+        assert(client->nb_requests == 0);
         assert(client->recv_coroutine == NULL);
         assert(client->send_coroutine == NULL);
-
-        if (client->quiescing) {
-            client->quiescing = false;
-            nbd_client_receive_next_request(client);
-        }
     }
 }
 
-static void nbd_aio_detach_bh(void *opaque)
+static void blk_aio_detach(void *opaque)
 {
     NBDExport *exp = opaque;
     NBDClient *client;
 
+    trace_nbd_blk_aio_detach(exp->name, exp->common.ctx);
+
     QTAILQ_FOREACH(client, &exp->clients, next) {
         qio_channel_detach_aio_context(client->ioc);
+    }
+
+    exp->common.ctx = NULL;
+}
+
+static void nbd_drained_begin(void *opaque)
+{
+    NBDExport *exp = opaque;
+    NBDClient *client;
+
+    QTAILQ_FOREACH(client, &exp->clients, next) {
         client->quiescing = true;
+    }
+}
 
-        if (client->recv_coroutine) {
-            if (client->read_yielding) {
-                qemu_aio_coroutine_enter(exp->common.ctx,
-                                         client->recv_coroutine);
-            } else {
-                AIO_WAIT_WHILE(exp->common.ctx, client->recv_coroutine != NULL);
-            }
-        }
+static void nbd_drained_end(void *opaque)
+{
+    NBDExport *exp = opaque;
+    NBDClient *client;
 
-        if (client->send_coroutine) {
-            AIO_WAIT_WHILE(exp->common.ctx, client->send_coroutine != NULL);
-        }
+    QTAILQ_FOREACH(client, &exp->clients, next) {
+        client->quiescing = false;
+        nbd_client_receive_next_request(client);
     }
 }
 
-static void blk_aio_detach(void *opaque)
+static bool nbd_drained_poll(void *opaque)
 {
     NBDExport *exp = opaque;
+    NBDClient *client;
 
-    trace_nbd_blk_aio_detach(exp->name, exp->common.ctx);
+    QTAILQ_FOREACH(client, &exp->clients, next) {
+        if (client->nb_requests != 0) {
+            /*
+             * If there's a coroutine waiting for a request on nbd_read_eof()
+             * enter it here so we don't depend on the client to wake it up.
+             */
+            if (client->recv_coroutine != NULL && client->read_yielding) {
+                qemu_aio_coroutine_enter(exp->common.ctx,
+                                         client->recv_coroutine);
+            }
 
-    aio_wait_bh_oneshot(exp->common.ctx, nbd_aio_detach_bh, exp);
+            return true;
+        }
+    }
 
-    exp->common.ctx = NULL;
+    return false;
 }
 
 static void nbd_eject_notifier(Notifier *n, void *data)
@@ -1594,6 +1618,12 @@ void nbd_export_set_on_eject_blk(BlockExport *exp, BlockBackend *blk)
     blk_add_remove_bs_notifier(blk, &nbd_exp->eject_notifier);
 }
 
+static const BlockDevOps nbd_block_ops = {
+    .drained_begin = nbd_drained_begin,
+    .drained_end = nbd_drained_end,
+    .drained_poll = nbd_drained_poll,
+};
+
 static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args,
                              Error **errp)
 {
@@ -1715,8 +1745,17 @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args,
 
     exp->allocation_depth = arg->allocation_depth;
 
+    /*
+     * We need to inhibit request queuing in the block layer to ensure we can
+     * be properly quiesced when entering a drained section, as our coroutines
+     * servicing pending requests might enter blk_pread().
+     */
+    blk_set_disable_request_queuing(blk, true);
+
     blk_add_aio_context_notifier(blk, blk_aio_attached, blk_aio_detach, exp);
 
+    blk_set_dev_ops(blk, &nbd_block_ops, exp);
+
     QTAILQ_INSERT_TAIL(&exports, exp, next);
 
     return 0;
@@ -1788,6 +1827,7 @@ static void nbd_export_delete(BlockExport *blk_exp)
         }
         blk_remove_aio_context_notifier(exp->common.blk, blk_aio_attached,
                                         blk_aio_detach, exp);
+        blk_set_disable_request_queuing(exp->common.blk, false);
     }
 
     for (i = 0; i < exp->nr_export_bitmaps; i++) {