Merge tag 'for-upstream' of https://repo.or.cz/qemu/kevin into staging

Block layer patches

- ide/via: Fix BAR4 value in legacy mode
- export/vhost-user-blk: Fix consecutive drains
- vmdk: Don't corrupt desc file in vmdk_write_cid
- iotests: fix default machine type detection

# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmVl9GARHGt3b2xmQHJl
# ZGhhdC5jb20ACgkQfwmycsiPL9Y9KRAAx3ryUIdaVZX5RZbVC4ZmkgGIpSv+8dS+
# e98H+accyyVTVXlMNYWy0s7tP6sxhhlmGqfGLx/hDynvjJRxyS8VSOXXNIqYcHqN
# wGXcgLEgb+qxu7+Y8g3UhMeSmDyRhanOE/MxhMqGOKd/5nxfY1XdD7nkRwCsPAAi
# Tud/Jd7t0CSV0wUDfvMtBsQZCBSQyoSu3S3TjZ8I2CPjBaoYojj3XM+LKrlJu+B5
# zwgB5IURac1dOfsjYsX0M0zXxr6pTVNtkdNNwFoiNP+omoRjCXV3W9iTtyU+/zc3
# cnVzQQRE6XufQ/Q7IWHNE3/U5LvM3m+sjB+YryrMTRVItjpGUCgYGsrgodjZp7aj
# 4hmwxyZ8PN3+o96d5RWqhRXnY9fy5hzJZOhUMQV6lV/Z14wt8YYsJoqgi4wryoYf
# 7VdyZP2Szt2Sgl4+n0uSfPBoR+qMEwni1AxO8iK9OZbpewv7aBO3In4tOAvP/eB8
# VAoCZOfrILSXaR5aorlAPr6IOXanPvgOotmzNs0NaaqYnpfYr6KAH9FjyAm3DZqp
# b+/Ep+hrekq9XqnZGMblQsjlTFAc9mRWtqsHUrftl9FhRvSah4R+TyKov8lD23VZ
# bvw1etcc0p55Ws4RkUkGn8G5kRyhec3nkHdr4MODCR0s0uo0cBaITnoV0Ra9p7of
# K78WSodwZKQ=
# =ktlF
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 28 Nov 2023 09:08:32 EST
# 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

* tag 'for-upstream' of https://repo.or.cz/qemu/kevin:
  ide/via: Fix BAR4 value in legacy mode
  export/vhost-user-blk: Fix consecutive drains
  vmdk: Don't corrupt desc file in vmdk_write_cid
  iotests: fix default machine type detection

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

8 files changed, 77 insertions, 25 deletions

diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c
index fe2cee3..16f4838 100644
--- a/block/export/vhost-user-blk-server.c
+++ b/block/export/vhost-user-blk-server.c
@@ -283,6 +283,7 @@ static void vu_blk_drained_begin(void *opaque)
 {
     VuBlkExport *vexp = opaque;
 
+    vexp->vu_server.quiescing = true;
     vhost_user_server_detach_aio_context(&vexp->vu_server);
 }
 
@@ -291,19 +292,23 @@ static void vu_blk_drained_end(void *opaque)
 {
     VuBlkExport *vexp = opaque;
 
+    vexp->vu_server.quiescing = false;
     vhost_user_server_attach_aio_context(&vexp->vu_server, vexp->export.ctx);
 }
 
 /*
- * Ensures that bdrv_drained_begin() waits until in-flight requests complete.
+ * Ensures that bdrv_drained_begin() waits until in-flight requests complete
+ * and the server->co_trip coroutine has terminated. It will be restarted in
+ * vhost_user_server_attach_aio_context().
  *
  * Called with vexp->export.ctx acquired.
  */
 static bool vu_blk_drained_poll(void *opaque)
 {
     VuBlkExport *vexp = opaque;
+    VuServer *server = &vexp->vu_server;
 
-    return vhost_user_server_has_in_flight(&vexp->vu_server);
+    return server->co_trip || vhost_user_server_has_in_flight(server);
 }
 
 static const BlockDevOps vu_blk_dev_ops = {
diff --git a/block/vmdk.c b/block/vmdk.c
index d87f6d9..d6971c7 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -351,29 +351,41 @@ vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
     BDRVVmdkState *s = bs->opaque;
     int ret = 0;
 
-    desc = g_malloc0(DESC_SIZE);
-    tmp_desc = g_malloc0(DESC_SIZE);
-    ret = bdrv_co_pread(bs->file, s->desc_offset, DESC_SIZE, desc, 0);
+    size_t desc_buf_size;
+
+    if (s->desc_offset == 0) {
+        desc_buf_size = bdrv_getlength(bs->file->bs);
+        if (desc_buf_size > 16ULL << 20) {
+            error_report("VMDK description file too big");
+            return -EFBIG;
+        }
+    } else {
+        desc_buf_size = DESC_SIZE;
+    }
+
+    desc = g_malloc0(desc_buf_size);
+    tmp_desc = g_malloc0(desc_buf_size);
+    ret = bdrv_co_pread(bs->file, s->desc_offset, desc_buf_size, desc, 0);
     if (ret < 0) {
         goto out;
     }
 
-    desc[DESC_SIZE - 1] = '\0';
+    desc[desc_buf_size - 1] = '\0';
     tmp_str = strstr(desc, "parentCID");
     if (tmp_str == NULL) {
         ret = -EINVAL;
         goto out;
     }
 
-    pstrcpy(tmp_desc, DESC_SIZE, tmp_str);
+    pstrcpy(tmp_desc, desc_buf_size, tmp_str);
     p_name = strstr(desc, "CID");
     if (p_name != NULL) {
         p_name += sizeof("CID");
-        snprintf(p_name, DESC_SIZE - (p_name - desc), "%" PRIx32 "\n", cid);
-        pstrcat(desc, DESC_SIZE, tmp_desc);
+        snprintf(p_name, desc_buf_size - (p_name - desc), "%" PRIx32 "\n", cid);
+        pstrcat(desc, desc_buf_size, tmp_desc);
     }
 
-    ret = bdrv_co_pwrite_sync(bs->file, s->desc_offset, DESC_SIZE, desc, 0);
+    ret = bdrv_co_pwrite_sync(bs->file, s->desc_offset, desc_buf_size, desc, 0);
 
 out:
     g_free(desc);
diff --git a/hw/ide/via.c b/hw/ide/via.c
index 2d3124e..3f3c484 100644
--- a/hw/ide/via.c
+++ b/hw/ide/via.c
@@ -163,14 +163,19 @@ static uint32_t via_ide_cfg_read(PCIDevice *pd, uint32_t addr, int len)
     uint32_t val = pci_default_read_config(pd, addr, len);
     uint8_t mode = pd->config[PCI_CLASS_PROG];
 
-    if ((mode & 0xf) == 0xa && ranges_overlap(addr, len,
-                                              PCI_BASE_ADDRESS_0, 16)) {
-        /* BARs always read back zero in legacy mode */
-        for (int i = addr; i < addr + len; i++) {
-            if (i >= PCI_BASE_ADDRESS_0 && i < PCI_BASE_ADDRESS_0 + 16) {
-                val &= ~(0xffULL << ((i - addr) << 3));
+    if ((mode & 0xf) == 0xa) {
+        if (ranges_overlap(addr, len, PCI_BASE_ADDRESS_0, 16)) {
+            /* BARs 0-3 always read back zero in legacy mode */
+            for (int i = addr; i < addr + len; i++) {
+                if (i >= PCI_BASE_ADDRESS_0 && i < PCI_BASE_ADDRESS_0 + 16) {
+                    val &= ~(0xffULL << ((i - addr) << 3));
+                }
             }
         }
+        if (addr == PCI_BASE_ADDRESS_4 && val == PCI_BASE_ADDRESS_SPACE_IO) {
+            /* BAR4 default value if unset */
+            val = 0xcc00 | PCI_BASE_ADDRESS_SPACE_IO;
+        }
     }
 
     return val;
diff --git a/include/qemu/vhost-user-server.h b/include/qemu/vhost-user-server.h
index 64ad701..0417ec0 100644
--- a/include/qemu/vhost-user-server.h
+++ b/include/qemu/vhost-user-server.h
@@ -45,6 +45,7 @@ typedef struct {
     /* Protected by ctx lock */
     bool in_qio_channel_yield;
     bool wait_idle;
+    bool quiescing;
     VuDev vu_dev;
     QIOChannel *ioc; /* The I/O channel with the client */
     QIOChannelSocket *sioc; /* The underlying data channel with the client */
diff --git a/tests/qemu-iotests/059 b/tests/qemu-iotests/059
index 2bcb1f7..0634c7b 100755
--- a/tests/qemu-iotests/059
+++ b/tests/qemu-iotests/059
@@ -84,6 +84,8 @@ echo
 echo "=== Testing big twoGbMaxExtentFlat ==="
 _make_test_img -o "subformat=twoGbMaxExtentFlat" 1000G
 _img_info --format-specific | _filter_img_info --format-specific
+$QEMU_IO -c "write 990G 512 -P 89" "$TEST_IMG" | _filter_qemu_io
+$QEMU_IO -c "read 990G 512 -P 89" "$TEST_IMG" | _filter_qemu_io
 _cleanup_test_img
 
 echo
diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out
index 2b83c0c..275ee7c 100644
--- a/tests/qemu-iotests/059.out
+++ b/tests/qemu-iotests/059.out
@@ -2032,6 +2032,10 @@ Format specific information:
             virtual size: 2147483648
             filename: TEST_DIR/t-f500.IMGFMT
             format: FLAT
+wrote 512/512 bytes at offset 1063004405760
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 512/512 bytes at offset 1063004405760
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
 === Testing malformed VMFS extent description line ===
 qemu-img: Could not open 'TEST_DIR/t.IMGFMT': Invalid extent line: RW 12582912 VMFS "dummy.IMGFMT" 1
diff --git a/tests/qemu-iotests/testenv.py b/tests/qemu-iotests/testenv.py
index e67ebd2..3ff38f2 100644
--- a/tests/qemu-iotests/testenv.py
+++ b/tests/qemu-iotests/testenv.py
@@ -40,7 +40,7 @@ def get_default_machine(qemu_prog: str) -> str:
 
     machines = outp.split('\n')
     try:
-        default_machine = next(m for m in machines if m.endswith(' (default)'))
+        default_machine = next(m for m in machines if ' (default)' in m)
     except StopIteration:
         return ''
     default_machine = default_machine.split(' ', 1)[0]
diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c
index 5ccc6d2..a9a48ff 100644
--- a/util/vhost-user-server.c
+++ b/util/vhost-user-server.c
@@ -132,8 +132,7 @@ vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg)
                     qio_channel_yield(ioc, G_IO_IN);
                     server->in_qio_channel_yield = false;
                 } else {
-                    /* Wait until attached to an AioContext again */
-                    qemu_coroutine_yield();
+                    return false;
                 }
                 continue;
             } else {
@@ -201,8 +200,16 @@ static coroutine_fn void vu_client_trip(void *opaque)
     VuServer *server = opaque;
     VuDev *vu_dev = &server->vu_dev;
 
-    while (!vu_dev->broken && vu_dispatch(vu_dev)) {
-        /* Keep running */
+    while (!vu_dev->broken) {
+        if (server->quiescing) {
+            server->co_trip = NULL;
+            aio_wait_kick();
+            return;
+        }
+        /* vu_dispatch() returns false if server->ctx went away */
+        if (!vu_dispatch(vu_dev) && server->ctx) {
+            break;
+        }
     }
 
     if (vhost_user_server_has_in_flight(server)) {
@@ -353,8 +360,7 @@ static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc,
 
     qio_channel_set_follow_coroutine_ctx(server->ioc, true);
 
-    server->co_trip = qemu_coroutine_create(vu_client_trip, server);
-
+    /* Attaching the AioContext starts the vu_client_trip coroutine */
     aio_context_acquire(server->ctx);
     vhost_user_server_attach_aio_context(server, server->ctx);
     aio_context_release(server->ctx);
@@ -413,8 +419,25 @@ void vhost_user_server_attach_aio_context(VuServer *server, AioContext *ctx)
                            NULL, NULL, vu_fd_watch);
     }
 
-    assert(!server->in_qio_channel_yield);
-    aio_co_schedule(ctx, server->co_trip);
+    if (server->co_trip) {
+        /*
+         * The caller didn't fully shut down co_trip (this can happen on
+         * non-polling drains like in bdrv_graph_wrlock()). This is okay as long
+         * as it no longer tries to shut it down and we're guaranteed to still
+         * be in the same AioContext as before.
+         *
+         * co_ctx can still be NULL if we get multiple calls and only just
+         * scheduled a new coroutine in the else branch.
+         */
+        AioContext *co_ctx = qemu_coroutine_get_aio_context(server->co_trip);
+
+        assert(!server->quiescing);
+        assert(!co_ctx || co_ctx == ctx);
+    } else {
+        server->co_trip = qemu_coroutine_create(vu_client_trip, server);
+        assert(!server->in_qio_channel_yield);
+        aio_co_schedule(ctx, server->co_trip);
+    }
 }
 
 /* Called with server->ctx acquired */