1 files changed, 105 insertions, 46 deletions

diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index 9e40b0c..9b12ee7 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -9,12 +9,12 @@
 #include "migration/qemu-file-types.h"
 #include "migration/vmstate.h"
 #include "scsi/constants.h"
-#include "sysemu/block-backend.h"
-#include "sysemu/blockdev.h"
-#include "sysemu/sysemu.h"
-#include "sysemu/runstate.h"
+#include "system/block-backend.h"
+#include "system/blockdev.h"
+#include "system/system.h"
+#include "system/runstate.h"
 #include "trace.h"
-#include "sysemu/dma.h"
+#include "system/dma.h"
 #include "qemu/cutils.h"
 
 static char *scsibus_get_dev_path(DeviceState *dev);
@@ -100,8 +100,15 @@ static void scsi_device_for_each_req_sync(SCSIDevice *s,
     assert(!runstate_is_running());
     assert(qemu_in_main_thread());
 
-    QTAILQ_FOREACH_SAFE(req, &s->requests, next, next_req) {
-        fn(req, opaque);
+    /*
+     * Locking is not necessary because the guest is stopped and no other
+     * threads can be accessing the requests list, but take the lock for
+     * consistency.
+     */
+    WITH_QEMU_LOCK_GUARD(&s->requests_lock) {
+        QTAILQ_FOREACH_SAFE(req, &s->requests, next, next_req) {
+            fn(req, opaque);
+        }
     }
 }
 
@@ -115,21 +122,29 @@ static void scsi_device_for_each_req_async_bh(void *opaque)
 {
     g_autofree SCSIDeviceForEachReqAsyncData *data = opaque;
     SCSIDevice *s = data->s;
-    AioContext *ctx;
-    SCSIRequest *req;
-    SCSIRequest *next;
+    g_autoptr(GList) reqs = NULL;
 
     /*
-     * The BB cannot have changed contexts between this BH being scheduled and
-     * now: BBs' AioContexts, when they have a node attached, can only be
-     * changed via bdrv_try_change_aio_context(), in a drained section.  While
-     * we have the in-flight counter incremented, that drain must block.
+     * Build a list of requests in this AioContext so fn() can be invoked later
+     * outside requests_lock.
      */
-    ctx = blk_get_aio_context(s->conf.blk);
-    assert(ctx == qemu_get_current_aio_context());
+    WITH_QEMU_LOCK_GUARD(&s->requests_lock) {
+        AioContext *ctx = qemu_get_current_aio_context();
+        SCSIRequest *req;
+        SCSIRequest *next;
 
-    QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) {
-        data->fn(req, data->fn_opaque);
+        QTAILQ_FOREACH_SAFE(req, &s->requests, next, next) {
+            if (req->ctx == ctx) {
+                scsi_req_ref(req); /* dropped after calling fn() */
+                reqs = g_list_prepend(reqs, req);
+            }
+        }
+    }
+
+    /* Call fn() on each request */
+    for (GList *elem = g_list_first(reqs); elem; elem = g_list_next(elem)) {
+        data->fn(elem->data, data->fn_opaque);
+        scsi_req_unref(elem->data);
     }
 
     /* Drop the reference taken by scsi_device_for_each_req_async() */
@@ -139,9 +154,35 @@ static void scsi_device_for_each_req_async_bh(void *opaque)
     blk_dec_in_flight(s->conf.blk);
 }
 
+static void scsi_device_for_each_req_async_do_ctx(gpointer key, gpointer value,
+                                                  gpointer user_data)
+{
+    AioContext *ctx = key;
+    SCSIDeviceForEachReqAsyncData *params = user_data;
+    SCSIDeviceForEachReqAsyncData *data;
+
+    data = g_new(SCSIDeviceForEachReqAsyncData, 1);
+    data->s = params->s;
+    data->fn = params->fn;
+    data->fn_opaque = params->fn_opaque;
+
+    /*
+     * Hold a reference to the SCSIDevice until
+     * scsi_device_for_each_req_async_bh() finishes.
+     */
+    object_ref(OBJECT(data->s));
+
+    /* Paired with scsi_device_for_each_req_async_bh() */
+    blk_inc_in_flight(data->s->conf.blk);
+
+    aio_bh_schedule_oneshot(ctx, scsi_device_for_each_req_async_bh, data);
+}
+
 /*
  * Schedule @fn() to be invoked for each enqueued request in device @s. @fn()
- * runs in the AioContext that is executing the request.
+ * must be thread-safe because it runs concurrently in each AioContext that is
+ * executing a request.
+ *
  * Keeps the BlockBackend's in-flight counter incremented until everything is
  * done, so draining it will settle all scheduled @fn() calls.
  */
@@ -151,24 +192,26 @@ static void scsi_device_for_each_req_async(SCSIDevice *s,
 {
     assert(qemu_in_main_thread());
 
-    SCSIDeviceForEachReqAsyncData *data =
-        g_new(SCSIDeviceForEachReqAsyncData, 1);
-
-    data->s = s;
-    data->fn = fn;
-    data->fn_opaque = opaque;
-
-    /*
-     * Hold a reference to the SCSIDevice until
-     * scsi_device_for_each_req_async_bh() finishes.
-     */
-    object_ref(OBJECT(s));
+    /* The set of AioContexts where the requests are being processed */
+    g_autoptr(GHashTable) aio_contexts = g_hash_table_new(NULL, NULL);
+    WITH_QEMU_LOCK_GUARD(&s->requests_lock) {
+        SCSIRequest *req;
+        QTAILQ_FOREACH(req, &s->requests, next) {
+            g_hash_table_add(aio_contexts, req->ctx);
+        }
+    }
 
-    /* Paired with blk_dec_in_flight() in scsi_device_for_each_req_async_bh() */
-    blk_inc_in_flight(s->conf.blk);
-    aio_bh_schedule_oneshot(blk_get_aio_context(s->conf.blk),
-                            scsi_device_for_each_req_async_bh,
-                            data);
+    /* Schedule a BH for each AioContext */
+    SCSIDeviceForEachReqAsyncData params = {
+        .s = s,
+        .fn = fn,
+        .fn_opaque = opaque,
+    };
+    g_hash_table_foreach(
+            aio_contexts,
+            scsi_device_for_each_req_async_do_ctx,
+            &params
+    );
 }
 
 static void scsi_device_realize(SCSIDevice *s, Error **errp)
@@ -349,6 +392,7 @@ static void scsi_qdev_realize(DeviceState *qdev, Error **errp)
         dev->lun = lun;
     }
 
+    qemu_mutex_init(&dev->requests_lock);
     QTAILQ_INIT(&dev->requests);
     scsi_device_realize(dev, &local_err);
     if (local_err) {
@@ -356,7 +400,7 @@ static void scsi_qdev_realize(DeviceState *qdev, Error **errp)
         return;
     }
     dev->vmsentry = qdev_add_vm_change_state_handler(DEVICE(dev),
-            scsi_dma_restart_cb, dev);
+            scsi_dma_restart_cb, NULL, dev);
 }
 
 static void scsi_qdev_unrealize(DeviceState *qdev)
@@ -369,6 +413,8 @@ static void scsi_qdev_unrealize(DeviceState *qdev)
 
     scsi_device_purge_requests(dev, SENSE_CODE(NO_SENSE));
 
+    qemu_mutex_destroy(&dev->requests_lock);
+
     scsi_device_unrealize(dev);
 
     blockdev_mark_auto_del(dev->conf.blk);
@@ -384,6 +430,7 @@ SCSIDevice *scsi_bus_legacy_add_drive(SCSIBus *bus, BlockBackend *blk,
     DeviceState *dev;
     SCSIDevice *s;
     DriveInfo *dinfo;
+    Error *local_err = NULL;
 
     if (blk_is_sg(blk)) {
         driver = "scsi-generic";
@@ -403,6 +450,14 @@ SCSIDevice *scsi_bus_legacy_add_drive(SCSIBus *bus, BlockBackend *blk,
     s = SCSI_DEVICE(dev);
     s->conf = *conf;
 
+    check_boot_index(conf->bootindex, &local_err);
+    if (local_err) {
+        object_unparent(OBJECT(dev));
+        error_propagate(errp, local_err);
+        return NULL;
+    }
+    add_boot_device_path(conf->bootindex, dev, NULL);
+
     qdev_prop_set_uint32(dev, "scsi-id", unit);
     if (object_property_find(OBJECT(dev), "removable")) {
         qdev_prop_set_bit(dev, "removable", removable);
@@ -859,6 +914,7 @@ invalid_opcode:
         }
     }
 
+    req->ctx = qemu_get_current_aio_context();
     req->cmd = cmd;
     req->residual = req->cmd.xfer;
 
@@ -955,7 +1011,10 @@ static void scsi_req_enqueue_internal(SCSIRequest *req)
         req->sg = NULL;
     }
     req->enqueued = true;
-    QTAILQ_INSERT_TAIL(&req->dev->requests, req, next);
+
+    WITH_QEMU_LOCK_GUARD(&req->dev->requests_lock) {
+        QTAILQ_INSERT_TAIL(&req->dev->requests, req, next);
+    }
 }
 
 int32_t scsi_req_enqueue(SCSIRequest *req)
@@ -975,7 +1034,9 @@ static void scsi_req_dequeue(SCSIRequest *req)
     trace_scsi_req_dequeue(req->dev->id, req->lun, req->tag);
     req->retry = false;
     if (req->enqueued) {
-        QTAILQ_REMOVE(&req->dev->requests, req, next);
+        WITH_QEMU_LOCK_GUARD(&req->dev->requests_lock) {
+            QTAILQ_REMOVE(&req->dev->requests, req, next);
+        }
         req->enqueued = false;
         scsi_req_unref(req);
     }
@@ -1934,14 +1995,13 @@ const VMStateDescription vmstate_scsi_device = {
     }
 };
 
-static Property scsi_props[] = {
+static const Property scsi_props[] = {
     DEFINE_PROP_UINT32("channel", SCSIDevice, channel, 0),
     DEFINE_PROP_UINT32("scsi-id", SCSIDevice, id, -1),
     DEFINE_PROP_UINT32("lun", SCSIDevice, lun, -1),
-    DEFINE_PROP_END_OF_LIST(),
 };
 
-static void scsi_device_class_init(ObjectClass *klass, void *data)
+static void scsi_device_class_init(ObjectClass *klass, const void *data)
 {
     DeviceClass *k = DEVICE_CLASS(klass);
     set_bit(DEVICE_CATEGORY_STORAGE, k->categories);
@@ -1953,8 +2013,7 @@ static void scsi_device_class_init(ObjectClass *klass, void *data)
 
 static void scsi_dev_instance_init(Object *obj)
 {
-    DeviceState *dev = DEVICE(obj);
-    SCSIDevice *s = SCSI_DEVICE(dev);
+    SCSIDevice *s = SCSI_DEVICE(obj);
 
     device_add_bootindex_property(obj, &s->conf.bootindex,
                                   "bootindex", NULL,
@@ -1971,7 +2030,7 @@ static const TypeInfo scsi_device_type_info = {
     .instance_init = scsi_dev_instance_init,
 };
 
-static void scsi_bus_class_init(ObjectClass *klass, void *data)
+static void scsi_bus_class_init(ObjectClass *klass, const void *data)
 {
     BusClass *k = BUS_CLASS(klass);
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass);
@@ -1987,7 +2046,7 @@ static const TypeInfo scsi_bus_info = {
     .parent = TYPE_BUS,
     .instance_size = sizeof(SCSIBus),
     .class_init = scsi_bus_class_init,
-    .interfaces = (InterfaceInfo[]) {
+    .interfaces = (const InterfaceInfo[]) {
         { TYPE_HOTPLUG_HANDLER },
         { }
     }