add input-send-event command

Which allows specification of absolute/relative,
up/down and console parameters.

Suggested by Gerd Hoffman.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

.travis.yml

@@ -12,7 +12,7 @@ notifications:
     on_failure: always
 env:
   global:
-    - TEST_CMD="make check"
+    - TEST_CMD=""
     - EXTRA_CONFIG=""
     # Development packages, EXTRA_PKGS saved for additional builds
     - CORE_PKGS="libusb-1.0-0-dev libiscsi-dev librados-dev libncurses5-dev"
@@ -20,31 +20,51 @@ env:
     - GUI_PKGS="libgtk-3-dev libvte-2.90-dev libsdl1.2-dev libpng12-dev libpixman-1-dev"
     - EXTRA_PKGS=""
   matrix:
+    # Group major targets together with their linux-user counterparts
     - TARGETS=alpha-softmmu,alpha-linux-user
-    - TARGETS=arm-softmmu,arm-linux-user
-    - TARGETS=aarch64-softmmu,aarch64-linux-user
-    - TARGETS=cris-softmmu
-    - TARGETS=i386-softmmu,x86_64-softmmu
-    - TARGETS=lm32-softmmu
-    - TARGETS=m68k-softmmu
-    - TARGETS=microblaze-softmmu,microblazeel-softmmu
+    - TARGETS=arm-softmmu,arm-linux-user,armeb-linux-user,aarch64-softmmu,aarch64-linux-user
+    - TARGETS=cris-softmmu,cris-linux-user
+    - TARGETS=i386-softmmu,i386-linux-user,x86_64-softmmu,x86_64-linux-user
+    - TARGETS=m68k-softmmu,m68k-linux-user
+    - TARGETS=microblaze-softmmu,microblazeel-softmmu,microblaze-linux-user,microblazeel-linux-user
     - TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu
-    - TARGETS=moxie-softmmu
-    - TARGETS=or32-softmmu,
-    - TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu
-    - TARGETS=s390x-softmmu
-    - TARGETS=sh4-softmmu,sh4eb-softmmu
-    - TARGETS=sparc-softmmu,sparc64-softmmu
-    - TARGETS=unicore32-softmmu
-    - TARGETS=xtensa-softmmu,xtensaeb-softmmu
+    - TARGETS=mips-linux-user,mips64-linux-user,mips64el-linux-user,mipsel-linux-user,mipsn32-linux-user,mipsn32el-linux-user
+    - TARGETS=or32-softmmu,or32-linux-user
+    - TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,ppc-linux-user,ppc64-linux-user,ppc64abi32-linux-user,ppc64le-linux-user
+    - TARGETS=s390x-softmmu,s390x-linux-user
+    - TARGETS=sh4-softmmu,sh4eb-softmmu,sh4-linux-user sh4eb-linux-user
+    - TARGETS=sparc-softmmu,sparc64-softmmu,sparc-linux-user,sparc32plus-linux-user,sparc64-linux-user
+    - TARGETS=unicore32-softmmu,unicore32-linux-user
+    # Group remaining softmmu only targets into one build
+    - TARGETS=lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,xtensaeb-softmmu
+git:
+  # we want to do this ourselves
+  submodules: false
 before_install:
+  - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
   - git submodule update --init --recursive
   - sudo apt-get update -qq
   - sudo apt-get install -qq ${CORE_PKGS} ${NET_PKGS} ${GUI_PKGS} ${EXTRA_PKGS}
-script: "./configure --target-list=${TARGETS} ${EXTRA_CONFIG} && make && ${TEST_CMD}"
+before_script:
+  - ./configure --target-list=${TARGETS} --enable-debug-tcg ${EXTRA_CONFIG}
+script:
+  - make -j2 && ${TEST_CMD}
 matrix:
   # We manually include a number of additional build for non-standard bits
   include:
+    # Make check target (we only do this once)
+    - env:
+        - TARGETS=alpha-softmmu,arm-softmmu,aarch64-softmmu,cris-softmmu,
+                  i386-softmmu,x86_64-softmmu,m68k-softmmu,microblaze-softmmu,
+                  microblazeel-softmmu,mips-softmmu,mips64-softmmu,
+                  mips64el-softmmu,mipsel-softmmu,or32-softmmu,ppc-softmmu,
+                  ppc64-softmmu,ppcemb-softmmu,s390x-softmmu,sh4-softmmu,
+                  sh4eb-softmmu,sparc-softmmu,sparc64-softmmu,
+                  unicore32-softmmu,unicore32-linux-user,
+                  lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,
+                  xtensaeb-softmmu
+          TEST_CMD="make check"
+      compiler: gcc
     # Debug related options
     - env: TARGETS=i386-softmmu,x86_64-softmmu
            EXTRA_CONFIG="--enable-debug"
@@ -73,7 +93,6 @@ matrix:
       compiler: gcc
     - env: TARGETS=i386-softmmu,x86_64-softmmu
            EXTRA_CONFIG="--enable-trace-backends=ftrace"
-           TEST_CMD=""
       compiler: gcc
     - env: TARGETS=i386-softmmu,x86_64-softmmu
           EXTRA_PKGS="liblttng-ust-dev liburcu-dev"

MAINTAINERS

@@ -980,7 +980,7 @@ S: Supported
 F: block/rbd.c
 
 Sheepdog
-M: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
+M: Hitoshi Mitake <mitake.hitoshi@lab.ntt.co.jp>
 M: Liu Yuan <namei.unix@gmail.com>
 L: sheepdog@lists.wpkg.org
 S: Supported

Makefile

@@ -418,6 +418,7 @@ endif
 	set -e; for x in $(KEYMAPS); do \
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(qemu_datadir)/keymaps"; \
 	done
+	$(INSTALL_DATA) $(SRC_PATH)/trace-events "$(DESTDIR)$(qemu_datadir)/trace-events"
 	for d in $(TARGET_DIRS); do \
 	$(MAKE) $(SUBDIR_MAKEFLAGS) TARGET_DIR=$$d/ -C $$d $@ || exit 1 ; \
         done

aio-win32.c

@@ -283,9 +283,9 @@ bool aio_poll(AioContext *ctx, bool blocking)
     int count;
     int timeout;
 
-    if (aio_prepare(ctx)) {
+    have_select_revents = aio_prepare(ctx);
+    if (have_select_revents) {
         blocking = false;
-        have_select_revents = true;
     }
 
     was_dispatching = ctx->dispatching;
@@ -335,6 +335,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
         event = NULL;
         if ((DWORD) (ret - WAIT_OBJECT_0) < count) {
             event = events[ret - WAIT_OBJECT_0];
+            events[ret - WAIT_OBJECT_0] = events[--count];
         } else if (!have_select_revents) {
             break;
         }
@@ -343,9 +344,6 @@ bool aio_poll(AioContext *ctx, bool blocking)
         blocking = false;
 
         progress |= aio_dispatch_handlers(ctx, event);
-
-        /* Try again, but only call each handler once.  */
-        events[ret - WAIT_OBJECT_0] = events[--count];
     }
 
     progress |= timerlistgroup_run_timers(&ctx->tlg);

async.c

@@ -289,18 +289,24 @@ static void aio_rfifolock_cb(void *opaque)
     aio_notify(opaque);
 }
 
-AioContext *aio_context_new(void)
+AioContext *aio_context_new(Error **errp)
 {
+    int ret;
     AioContext *ctx;
     ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
+    ret = event_notifier_init(&ctx->notifier, false);
+    if (ret < 0) {
+        g_source_destroy(&ctx->source);
+        error_setg_errno(errp, -ret, "Failed to initialize event notifier");
+        return NULL;
+    }
+    aio_set_event_notifier(ctx, &ctx->notifier,
+                           (EventNotifierHandler *)
+                           event_notifier_test_and_clear);
     ctx->pollfds = g_array_new(FALSE, FALSE, sizeof(GPollFD));
     ctx->thread_pool = NULL;
     qemu_mutex_init(&ctx->bh_lock);
     rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
-    event_notifier_init(&ctx->notifier, false);
-    aio_set_event_notifier(ctx, &ctx->notifier, 
-                           (EventNotifierHandler *)
-                           event_notifier_test_and_clear);
     timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
 
     return ctx;

backends/baum.c

@@ -629,7 +629,7 @@ fail_handle:
 
 static void register_types(void)
 {
-    register_char_driver_qapi("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL);
+    register_char_driver("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL);
 }
 
 type_init(register_types);

backends/hostmem-ram.c

@@ -27,7 +27,7 @@ ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
 
     path = object_get_canonical_path_component(OBJECT(backend));
     memory_region_init_ram(&backend->mr, OBJECT(backend), path,
-                           backend->size);
+                           backend->size, errp);
     g_free(path);
 }
 

backends/msmouse.c

@@ -79,7 +79,7 @@ CharDriverState *qemu_chr_open_msmouse(void)
 
 static void register_types(void)
 {
-    register_char_driver_qapi("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL);
+    register_char_driver("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL);
 }
 
 type_init(register_types);

backends/rng-egd.c

@@ -169,6 +169,7 @@ static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
     if (b->opened) {
         error_set(errp, QERR_PERMISSION_DENIED);
     } else {
+        g_free(s->chr_name);
         s->chr_name = g_strdup(value);
     }
 }

backends/testdev.c

@@ -125,7 +125,7 @@ CharDriverState *chr_testdev_init(void)
 
 static void register_types(void)
 {
-    register_char_driver_qapi("testdev", CHARDEV_BACKEND_KIND_TESTDEV, NULL);
+    register_char_driver("testdev", CHARDEV_BACKEND_KIND_TESTDEV, NULL);
 }
 
 type_init(register_types);

block.c

@@ -29,6 +29,7 @@
 #include "qemu/module.h"
 #include "qapi/qmp/qjson.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/blockdev.h"    /* FIXME layering violation */
 #include "qemu/notify.h"
 #include "block/coroutine.h"
 #include "block/qapi.h"
@@ -334,19 +335,30 @@ void bdrv_register(BlockDriver *bdrv)
     QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
 }
 
+static bool bdrv_is_valid_name(const char *name)
+{
+    return qemu_opts_id_wellformed(name);
+}
+
 /* create a new block device (by default it is empty) */
 BlockDriverState *bdrv_new(const char *device_name, Error **errp)
 {
     BlockDriverState *bs;
     int i;
 
+    if (*device_name && !bdrv_is_valid_name(device_name)) {
+        error_setg(errp, "Invalid device name");
+        return NULL;
+    }
+
     if (bdrv_find(device_name)) {
         error_setg(errp, "Device with id '%s' already exists",
                    device_name);
         return NULL;
     }
     if (bdrv_find_node(device_name)) {
-        error_setg(errp, "Device with node-name '%s' already exists",
+        error_setg(errp,
+                   "Device name '%s' conflicts with an existing node name",
                    device_name);
         return NULL;
     }
@@ -861,9 +873,9 @@ static void bdrv_assign_node_name(BlockDriverState *bs,
         return;
     }
 
-    /* empty string node name is invalid */
-    if (node_name[0] == '\0') {
-        error_setg(errp, "Empty node name");
+    /* Check for empty string or invalid characters */
+    if (!bdrv_is_valid_name(node_name)) {
+        error_setg(errp, "Invalid node name");
         return;
     }
 
@@ -2110,6 +2122,7 @@ static void bdrv_delete(BlockDriverState *bs)
     /* remove from list, if necessary */
     bdrv_make_anon(bs);
 
+    drive_info_del(drive_get_by_blockdev(bs));
     g_free(bs);
 }
 
@@ -2246,7 +2259,7 @@ int bdrv_commit(BlockDriverState *bs)
 
     if (!drv)
         return -ENOMEDIUM;
-    
+
     if (!bs->backing_hd) {
         return -ENOTSUP;
     }
@@ -3363,9 +3376,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
 
     bdrv_set_dirty(bs, sector_num, nb_sectors);
 
-    if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
-        bs->wr_highest_sector = sector_num + nb_sectors - 1;
-    }
+    block_acct_highest_sector(&bs->stats, sector_num, nb_sectors);
+
     if (bs->growable && ret >= 0) {
         bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
     }
@@ -3639,6 +3651,19 @@ BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int e
     }
 }
 
+static void send_qmp_error_event(BlockDriverState *bs,
+                                 BlockErrorAction action,
+                                 bool is_read, int error)
+{
+    BlockErrorAction ac;
+
+    ac = is_read ? IO_OPERATION_TYPE_READ : IO_OPERATION_TYPE_WRITE;
+    qapi_event_send_block_io_error(bdrv_get_device_name(bs), ac, action,
+                                   bdrv_iostatus_is_enabled(bs),
+                                   error == ENOSPC, strerror(error),
+                                   &error_abort);
+}
+
 /* This is done by device models because, while the block layer knows
  * about the error, it does not know whether an operation comes from
  * the device or the block layer (from a job, for example).
@@ -3664,16 +3689,10 @@ void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
          * also ensures that the STOP/RESUME pair of events is emitted.
          */
         qemu_system_vmstop_request_prepare();
-        qapi_event_send_block_io_error(bdrv_get_device_name(bs),
-                                       is_read ? IO_OPERATION_TYPE_READ :
-                                       IO_OPERATION_TYPE_WRITE,
-                                       action, &error_abort);
+        send_qmp_error_event(bs, action, is_read, error);
         qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
     } else {
-        qapi_event_send_block_io_error(bdrv_get_device_name(bs),
-                                       is_read ? IO_OPERATION_TYPE_READ :
-                                       IO_OPERATION_TYPE_WRITE,
-                                       action, &error_abort);
+        send_qmp_error_event(bs, action, is_read, error);
     }
 }
 
@@ -4634,7 +4653,28 @@ int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs, int num_reqs)
 
 void bdrv_aio_cancel(BlockDriverAIOCB *acb)
 {
-    acb->aiocb_info->cancel(acb);
+    qemu_aio_ref(acb);
+    bdrv_aio_cancel_async(acb);
+    while (acb->refcnt > 1) {
+        if (acb->aiocb_info->get_aio_context) {
+            aio_poll(acb->aiocb_info->get_aio_context(acb), true);
+        } else if (acb->bs) {
+            aio_poll(bdrv_get_aio_context(acb->bs), true);
+        } else {
+            abort();
+        }
+    }
+    qemu_aio_unref(acb);
+}
+
+/* Async version of aio cancel. The caller is not blocked if the acb implements
+ * cancel_async, otherwise we do nothing and let the request normally complete.
+ * In either case the completion callback must be called. */
+void bdrv_aio_cancel_async(BlockDriverAIOCB *acb)
+{
+    if (acb->aiocb_info->cancel_async) {
+        acb->aiocb_info->cancel_async(acb);
+    }
 }
 
 /**************************************************************/
@@ -4650,18 +4690,8 @@ typedef struct BlockDriverAIOCBSync {
     int is_write;
 } BlockDriverAIOCBSync;
 
-static void bdrv_aio_cancel_em(BlockDriverAIOCB *blockacb)
-{
-    BlockDriverAIOCBSync *acb =
-        container_of(blockacb, BlockDriverAIOCBSync, common);
-    qemu_bh_delete(acb->bh);
-    acb->bh = NULL;
-    qemu_aio_release(acb);
-}
-
 static const AIOCBInfo bdrv_em_aiocb_info = {
     .aiocb_size         = sizeof(BlockDriverAIOCBSync),
-    .cancel             = bdrv_aio_cancel_em,
 };
 
 static void bdrv_aio_bh_cb(void *opaque)
@@ -4675,7 +4705,7 @@ static void bdrv_aio_bh_cb(void *opaque)
     acb->common.cb(acb->common.opaque, acb->ret);
     qemu_bh_delete(acb->bh);
     acb->bh = NULL;
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 }
 
 static BlockDriverAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
@@ -4732,22 +4762,8 @@ typedef struct BlockDriverAIOCBCoroutine {
     QEMUBH* bh;
 } BlockDriverAIOCBCoroutine;
 
-static void bdrv_aio_co_cancel_em(BlockDriverAIOCB *blockacb)
-{
-    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
-    BlockDriverAIOCBCoroutine *acb =
-        container_of(blockacb, BlockDriverAIOCBCoroutine, common);
-    bool done = false;
-
-    acb->done = &done;
-    while (!done) {
-        aio_poll(aio_context, true);
-    }
-}
-
 static const AIOCBInfo bdrv_em_co_aiocb_info = {
     .aiocb_size         = sizeof(BlockDriverAIOCBCoroutine),
-    .cancel             = bdrv_aio_co_cancel_em,
 };
 
 static void bdrv_co_em_bh(void *opaque)
@@ -4756,12 +4772,8 @@ static void bdrv_co_em_bh(void *opaque)
 
     acb->common.cb(acb->common.opaque, acb->req.error);
 
-    if (acb->done) {
-        *acb->done = true;
-    }
-
     qemu_bh_delete(acb->bh);
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 }
 
 /* Invoke bdrv_co_do_readv/bdrv_co_do_writev */
@@ -4800,7 +4812,6 @@ static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
     acb->req.qiov = qiov;
     acb->req.flags = flags;
     acb->is_write = is_write;
-    acb->done = NULL;
 
     co = qemu_coroutine_create(bdrv_co_do_rw);
     qemu_coroutine_enter(co, acb);
@@ -4827,7 +4838,6 @@ BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
     BlockDriverAIOCBCoroutine *acb;
 
     acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
-    acb->done = NULL;
 
     co = qemu_coroutine_create(bdrv_aio_flush_co_entry);
     qemu_coroutine_enter(co, acb);
@@ -4857,7 +4867,6 @@ BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
     acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
     acb->req.sector = sector_num;
     acb->req.nb_sectors = nb_sectors;
-    acb->done = NULL;
     co = qemu_coroutine_create(bdrv_aio_discard_co_entry);
     qemu_coroutine_enter(co, acb);
 
@@ -4885,13 +4894,23 @@ void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs,
     acb->bs = bs;
     acb->cb = cb;
     acb->opaque = opaque;
+    acb->refcnt = 1;
     return acb;
 }
 
-void qemu_aio_release(void *p)
+void qemu_aio_ref(void *p)
 {
     BlockDriverAIOCB *acb = p;
-    g_slice_free1(acb->aiocb_info->aiocb_size, acb);
+    acb->refcnt++;
+}
+
+void qemu_aio_unref(void *p)
+{
+    BlockDriverAIOCB *acb = p;
+    assert(acb->refcnt > 0);
+    if (--acb->refcnt == 0) {
+        g_slice_free1(acb->aiocb_info->aiocb_size, acb);
+    }
 }
 
 /**************************************************************/
@@ -5566,27 +5585,6 @@ void bdrv_iostatus_set_err(BlockDriverState *bs, int error)
     }
 }
 
-void
-bdrv_acct_start(BlockDriverState *bs, BlockAcctCookie *cookie, int64_t bytes,
-        enum BlockAcctType type)
-{
-    assert(type < BDRV_MAX_IOTYPE);
-
-    cookie->bytes = bytes;
-    cookie->start_time_ns = get_clock();
-    cookie->type = type;
-}
-
-void
-bdrv_acct_done(BlockDriverState *bs, BlockAcctCookie *cookie)
-{
-    assert(cookie->type < BDRV_MAX_IOTYPE);
-
-    bs->nr_bytes[cookie->type] += cookie->bytes;
-    bs->nr_ops[cookie->type]++;
-    bs->total_time_ns[cookie->type] += get_clock() - cookie->start_time_ns;
-}
-
 void bdrv_img_create(const char *filename, const char *fmt,
                      const char *base_filename, const char *base_fmt,
                      char *options, uint64_t img_size, int flags,
@@ -6103,3 +6101,14 @@ void bdrv_refresh_filename(BlockDriverState *bs)
         QDECREF(json);
     }
 }
+
+/* This accessor function purpose is to allow the device models to access the
+ * BlockAcctStats structure embedded inside a BlockDriverState without being
+ * aware of the BlockDriverState structure layout.
+ * It will go away when the BlockAcctStats structure will be moved inside
+ * the device models.
+ */
+BlockAcctStats *bdrv_get_stats(BlockDriverState *bs)
+{
+    return &bs->stats;
+}

block/Makefile.objs

@@ -1,4 +1,4 @@
-block-obj-y += raw_bsd.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
+block-obj-y += raw_bsd.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
 block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
@@ -9,6 +9,7 @@ block-obj-y += snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
 block-obj-$(CONFIG_POSIX) += raw-posix.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
+block-obj-y += null.o
 
 block-obj-y += nbd.o nbd-client.o sheepdog.o
 block-obj-$(CONFIG_LIBISCSI) += iscsi.o
@@ -18,6 +19,7 @@ block-obj-$(CONFIG_RBD) += rbd.o
 block-obj-$(CONFIG_GLUSTERFS) += gluster.o
 block-obj-$(CONFIG_ARCHIPELAGO) += archipelago.o
 block-obj-$(CONFIG_LIBSSH2) += ssh.o
+block-obj-y += accounting.o
 
 common-obj-y += stream.o
 common-obj-y += commit.o

block/accounting.c

@@ -0,0 +1,54 @@
+/*
+ * QEMU System Emulator block accounting
+ *
+ * Copyright (c) 2011 Christoph Hellwig
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "block/accounting.h"
+#include "block/block_int.h"
+
+void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
+                      int64_t bytes, enum BlockAcctType type)
+{
+    assert(type < BLOCK_MAX_IOTYPE);
+
+    cookie->bytes = bytes;
+    cookie->start_time_ns = get_clock();
+    cookie->type = type;
+}
+
+void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)
+{
+    assert(cookie->type < BLOCK_MAX_IOTYPE);
+
+    stats->nr_bytes[cookie->type] += cookie->bytes;
+    stats->nr_ops[cookie->type]++;
+    stats->total_time_ns[cookie->type] += get_clock() - cookie->start_time_ns;
+}
+
+
+void block_acct_highest_sector(BlockAcctStats *stats, int64_t sector_num,
+                               unsigned int nb_sectors)
+{
+    if (stats->wr_highest_sector < sector_num + nb_sectors - 1) {
+        stats->wr_highest_sector = sector_num + nb_sectors - 1;
+    }
+}

block/archipelago.c

@@ -57,13 +57,12 @@
 #include "qapi/qmp/qint.h"
 #include "qapi/qmp/qstring.h"
 #include "qapi/qmp/qjson.h"
+#include "qemu/atomic.h"
 
 #include <inttypes.h>
 #include <xseg/xseg.h>
 #include <xseg/protocol.h>
 
-#define ARCHIP_FD_READ      0
-#define ARCHIP_FD_WRITE     1
 #define MAX_REQUEST_SIZE    524288
 
 #define ARCHIPELAGO_OPT_VOLUME      "volume"
@@ -83,6 +82,7 @@ typedef enum {
     ARCHIP_OP_WRITE,
     ARCHIP_OP_FLUSH,
     ARCHIP_OP_VOLINFO,
+    ARCHIP_OP_TRUNCATE,
 } ARCHIPCmd;
 
 typedef struct ArchipelagoAIOCB {
@@ -91,7 +91,6 @@ typedef struct ArchipelagoAIOCB {
     struct BDRVArchipelagoState *s;
     QEMUIOVector *qiov;
     ARCHIPCmd cmd;
-    bool cancelled;
     int status;
     int64_t size;
     int64_t ret;
@@ -214,7 +213,7 @@ static void xseg_request_handler(void *state)
 
                 xseg_put_request(s->xseg, req, s->srcport);
 
-                if ((__sync_add_and_fetch(&segreq->ref, -1)) == 0) {
+                if (atomic_fetch_dec(&segreq->ref) == 1) {
                     if (!segreq->failed) {
                         reqdata->aio_cb->ret = segreq->count;
                         archipelago_finish_aiocb(reqdata);
@@ -233,7 +232,7 @@ static void xseg_request_handler(void *state)
                 segreq->count += req->serviced;
                 xseg_put_request(s->xseg, req, s->srcport);
 
-                if ((__sync_add_and_fetch(&segreq->ref, -1)) == 0) {
+                if (atomic_fetch_dec(&segreq->ref) == 1) {
                     if (!segreq->failed) {
                         reqdata->aio_cb->ret = segreq->count;
                         archipelago_finish_aiocb(reqdata);
@@ -247,6 +246,7 @@ static void xseg_request_handler(void *state)
                 }
                 break;
             case ARCHIP_OP_VOLINFO:
+            case ARCHIP_OP_TRUNCATE:
                 s->is_signaled = true;
                 qemu_cond_signal(&s->archip_cond);
                 break;
@@ -317,9 +317,7 @@ static void qemu_archipelago_complete_aio(void *opaque)
     aio_cb->common.cb(aio_cb->common.opaque, aio_cb->ret);
     aio_cb->status = 0;
 
-    if (!aio_cb->cancelled) {
-        qemu_aio_release(aio_cb);
-    }
+    qemu_aio_unref(aio_cb);
     g_free(reqdata);
 }
 
@@ -707,7 +705,8 @@ static int qemu_archipelago_create(const char *filename,
 
     parse_filename_opts(filename, errp, &volname, &segment_name, &mport,
                         &vport);
-    total_size = qemu_opt_get_size_del(options, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(options, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     if (segment_name == NULL) {
         segment_name = g_strdup("archipelago");
@@ -723,19 +722,8 @@ static int qemu_archipelago_create(const char *filename,
     return ret;
 }
 
-static void qemu_archipelago_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    ArchipelagoAIOCB *aio_cb = (ArchipelagoAIOCB *) blockacb;
-    aio_cb->cancelled = true;
-    while (aio_cb->status == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(aio_cb->common.bs), true);
-    }
-    qemu_aio_release(aio_cb);
-}
-
 static const AIOCBInfo archipelago_aiocb_info = {
     .aiocb_size = sizeof(ArchipelagoAIOCB),
-    .cancel = qemu_archipelago_aio_cancel,
 };
 
 static int archipelago_submit_request(BDRVArchipelagoState *s,
@@ -824,78 +812,47 @@ static int archipelago_aio_segmented_rw(BDRVArchipelagoState *s,
                                         ArchipelagoAIOCB *aio_cb,
                                         int op)
 {
-    int i, ret, segments_nr, last_segment_size;
+    int ret, segments_nr;
+    size_t pos = 0;
     ArchipelagoSegmentedRequest *segreq;
 
-    segreq = g_new(ArchipelagoSegmentedRequest, 1);
+    segreq = g_new0(ArchipelagoSegmentedRequest, 1);
 
     if (op == ARCHIP_OP_FLUSH) {
         segments_nr = 1;
-        segreq->ref = segments_nr;
-        segreq->total = count;
-        segreq->count = 0;
-        segreq->failed = 0;
-        ret = archipelago_submit_request(s, 0, count, offset, aio_cb,
-                                           segreq, ARCHIP_OP_FLUSH);
-        if (ret < 0) {
-            goto err_exit;
-        }
-        return 0;
+    } else {
+        segments_nr = (int)(count / MAX_REQUEST_SIZE) + \
+                      ((count % MAX_REQUEST_SIZE) ? 1 : 0);
     }
-
-    segments_nr = (int)(count / MAX_REQUEST_SIZE) + \
-                  ((count % MAX_REQUEST_SIZE) ? 1 : 0);
-    last_segment_size = (int)(count % MAX_REQUEST_SIZE);
-
-    segreq->ref = segments_nr;
     segreq->total = count;
-    segreq->count = 0;
-    segreq->failed = 0;
+    atomic_mb_set(&segreq->ref, segments_nr);
 
-    for (i = 0; i < segments_nr - 1; i++) {
-        ret = archipelago_submit_request(s, i * MAX_REQUEST_SIZE,
-                                           MAX_REQUEST_SIZE,
-                                           offset + i * MAX_REQUEST_SIZE,
-                                           aio_cb, segreq, op);
+    while (segments_nr > 1) {
+        ret = archipelago_submit_request(s, pos,
+                                            MAX_REQUEST_SIZE,
+                                            offset + pos,
+                                            aio_cb, segreq, op);
 
         if (ret < 0) {
             goto err_exit;
         }
+        count -= MAX_REQUEST_SIZE;
+        pos += MAX_REQUEST_SIZE;
+        segments_nr--;
     }
-
-    if ((segments_nr > 1) && last_segment_size) {
-        ret = archipelago_submit_request(s, i * MAX_REQUEST_SIZE,
-                                           last_segment_size,
-                                           offset + i * MAX_REQUEST_SIZE,
-                                           aio_cb, segreq, op);
-    } else if ((segments_nr > 1) && !last_segment_size) {
-        ret = archipelago_submit_request(s, i * MAX_REQUEST_SIZE,
-                                           MAX_REQUEST_SIZE,
-                                           offset + i * MAX_REQUEST_SIZE,
-                                           aio_cb, segreq, op);
-    } else if (segments_nr == 1) {
-            ret = archipelago_submit_request(s, 0, count, offset, aio_cb,
-                                               segreq, op);
-    }
+    ret = archipelago_submit_request(s, pos, count, offset + pos,
+                                     aio_cb, segreq, op);
 
     if (ret < 0) {
         goto err_exit;
     }
-
     return 0;
 
 err_exit:
-    __sync_add_and_fetch(&segreq->failed, 1);
-    if (segments_nr == 1) {
-        if (__sync_add_and_fetch(&segreq->ref, -1) == 0) {
-            g_free(segreq);
-        }
-    } else {
-        if ((__sync_add_and_fetch(&segreq->ref, -segments_nr + i)) == 0) {
-            g_free(segreq);
-        }
+    segreq->failed = 1;
+    if (atomic_fetch_sub(&segreq->ref, segments_nr) == segments_nr) {
+        g_free(segreq);
     }
-
     return ret;
 }
 
@@ -918,7 +875,6 @@ static BlockDriverAIOCB *qemu_archipelago_aio_rw(BlockDriverState *bs,
 
     aio_cb->ret = 0;
     aio_cb->s = s;
-    aio_cb->cancelled = false;
     aio_cb->status = -EINPROGRESS;
 
     off = sector_num * BDRV_SECTOR_SIZE;
@@ -934,7 +890,7 @@ static BlockDriverAIOCB *qemu_archipelago_aio_rw(BlockDriverState *bs,
 
 err_exit:
     error_report("qemu_archipelago_aio_rw(): I/O Error\n");
-    qemu_aio_release(aio_cb);
+    qemu_aio_unref(aio_cb);
     return NULL;
 }
 
@@ -1025,6 +981,64 @@ static int64_t qemu_archipelago_getlength(BlockDriverState *bs)
     return ret;
 }
 
+static int qemu_archipelago_truncate(BlockDriverState *bs, int64_t offset)
+{
+    int ret, targetlen;
+    struct xseg_request *req;
+    BDRVArchipelagoState *s = bs->opaque;
+    AIORequestData *reqdata = g_new(AIORequestData, 1);
+
+    const char *volname = s->volname;
+    targetlen = strlen(volname);
+    req = xseg_get_request(s->xseg, s->srcport, s->mportno, X_ALLOC);
+    if (!req) {
+        archipelagolog("Cannot get XSEG request\n");
+        goto err_exit2;
+    }
+
+    ret = xseg_prep_request(s->xseg, req, targetlen, 0);
+    if (ret < 0) {
+        archipelagolog("Cannot prepare XSEG request\n");
+        goto err_exit;
+    }
+    char *target = xseg_get_target(s->xseg, req);
+    if (!target) {
+        archipelagolog("Cannot get XSEG target\n");
+        goto err_exit;
+    }
+    memcpy(target, volname, targetlen);
+    req->offset = offset;
+    req->op = X_TRUNCATE;
+
+    reqdata->op = ARCHIP_OP_TRUNCATE;
+    reqdata->volname = volname;
+
+    xseg_set_req_data(s->xseg, req, reqdata);
+
+    xport p = xseg_submit(s->xseg, req, s->srcport, X_ALLOC);
+    if (p == NoPort) {
+        archipelagolog("Cannot submit XSEG request\n");
+        goto err_exit;
+    }
+
+    xseg_signal(s->xseg, p);
+    qemu_mutex_lock(&s->archip_mutex);
+    while (!s->is_signaled) {
+        qemu_cond_wait(&s->archip_cond, &s->archip_mutex);
+    }
+    s->is_signaled = false;
+    qemu_mutex_unlock(&s->archip_mutex);
+    xseg_put_request(s->xseg, req, s->srcport);
+    g_free(reqdata);
+    return 0;
+
+err_exit:
+    xseg_put_request(s->xseg, req, s->srcport);
+err_exit2:
+    g_free(reqdata);
+    return -EIO;
+}
+
 static QemuOptsList qemu_archipelago_create_opts = {
     .name = "archipelago-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(qemu_archipelago_create_opts.head),
@@ -1054,6 +1068,7 @@ static BlockDriver bdrv_archipelago = {
     .bdrv_close          = qemu_archipelago_close,
     .bdrv_create         = qemu_archipelago_create,
     .bdrv_getlength      = qemu_archipelago_getlength,
+    .bdrv_truncate       = qemu_archipelago_truncate,
     .bdrv_aio_readv      = qemu_archipelago_aio_readv,
     .bdrv_aio_writev     = qemu_archipelago_aio_writev,
     .bdrv_aio_flush      = qemu_archipelago_aio_flush,

block/blkdebug.c

@@ -52,11 +52,8 @@ typedef struct BlkdebugSuspendedReq {
     QLIST_ENTRY(BlkdebugSuspendedReq) next;
 } BlkdebugSuspendedReq;
 
-static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb);
-
 static const AIOCBInfo blkdebug_aiocb_info = {
-    .aiocb_size = sizeof(BlkdebugAIOCB),
-    .cancel     = blkdebug_aio_cancel,
+    .aiocb_size    = sizeof(BlkdebugAIOCB),
 };
 
 enum {
@@ -217,6 +214,7 @@ static int get_event_by_name(const char *name, BlkDebugEvent *event)
 struct add_rule_data {
     BDRVBlkdebugState *s;
     int action;
+    Error **errp;
 };
 
 static int add_rule(QemuOpts *opts, void *opaque)
@@ -229,7 +227,11 @@ static int add_rule(QemuOpts *opts, void *opaque)
 
     /* Find the right event for the rule */
     event_name = qemu_opt_get(opts, "event");
-    if (!event_name || get_event_by_name(event_name, &event) < 0) {
+    if (!event_name) {
+        error_setg(d->errp, "Missing event name for rule");
+        return -1;
+    } else if (get_event_by_name(event_name, &event) < 0) {
+        error_setg(d->errp, "Invalid event name \"%s\"", event_name);
         return -1;
     }
 
@@ -315,10 +317,21 @@ static int read_config(BDRVBlkdebugState *s, const char *filename,
 
     d.s = s;
     d.action = ACTION_INJECT_ERROR;
-    qemu_opts_foreach(&inject_error_opts, add_rule, &d, 0);
+    d.errp = &local_err;
+    qemu_opts_foreach(&inject_error_opts, add_rule, &d, 1);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto fail;
+    }
 
     d.action = ACTION_SET_STATE;
-    qemu_opts_foreach(&set_state_opts, add_rule, &d, 0);
+    qemu_opts_foreach(&set_state_opts, add_rule, &d, 1);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto fail;
+    }
 
     ret = 0;
 fail:
@@ -447,17 +460,7 @@ static void error_callback_bh(void *opaque)
     struct BlkdebugAIOCB *acb = opaque;
     qemu_bh_delete(acb->bh);
     acb->common.cb(acb->common.opaque, acb->ret);
-    qemu_aio_release(acb);
-}
-
-static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    BlkdebugAIOCB *acb = container_of(blockacb, BlkdebugAIOCB, common);
-    if (acb->bh) {
-        qemu_bh_delete(acb->bh);
-        acb->bh = NULL;
-    }
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 }
 
 static BlockDriverAIOCB *inject_error(BlockDriverState *bs,

block/blkverify.c

@@ -29,7 +29,6 @@ struct BlkverifyAIOCB {
 
     int ret;                    /* first completed request's result */
     unsigned int done;          /* completion counter */
-    bool *finished;             /* completion signal for cancel */
 
     QEMUIOVector *qiov;         /* user I/O vector */
     QEMUIOVector raw_qiov;      /* cloned I/O vector for raw file */
@@ -38,22 +37,8 @@ struct BlkverifyAIOCB {
     void (*verify)(BlkverifyAIOCB *acb);
 };
 
-static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb;
-    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
-    bool finished = false;
-
-    /* Wait until request completes, invokes its callback, and frees itself */
-    acb->finished = &finished;
-    while (!finished) {
-        aio_poll(aio_context, true);
-    }
-}
-
 static const AIOCBInfo blkverify_aiocb_info = {
     .aiocb_size         = sizeof(BlkverifyAIOCB),
-    .cancel             = blkverify_aio_cancel,
 };
 
 static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
@@ -194,7 +179,6 @@ static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
     acb->qiov = qiov;
     acb->buf = NULL;
     acb->verify = NULL;
-    acb->finished = NULL;
     return acb;
 }
 
@@ -208,10 +192,7 @@ static void blkverify_aio_bh(void *opaque)
         qemu_vfree(acb->buf);
     }
     acb->common.cb(acb->common.opaque, acb->ret);
-    if (acb->finished) {
-        *acb->finished = true;
-    }
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 }
 
 static void blkverify_aio_cb(void *opaque, int ret)

block/cow.c

@@ -1,432 +0,0 @@
-/*
- * Block driver for the COW format
- *
- * Copyright (c) 2004 Fabrice Bellard
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-#include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-
-/**************************************************************/
-/* COW block driver using file system holes */
-
-/* user mode linux compatible COW file */
-#define COW_MAGIC 0x4f4f4f4d  /* MOOO */
-#define COW_VERSION 2
-
-struct cow_header_v2 {
-    uint32_t magic;
-    uint32_t version;
-    char backing_file[1024];
-    int32_t mtime;
-    uint64_t size;
-    uint32_t sectorsize;
-};
-
-typedef struct BDRVCowState {
-    CoMutex lock;
-    int64_t cow_sectors_offset;
-} BDRVCowState;
-
-static int cow_probe(const uint8_t *buf, int buf_size, const char *filename)
-{
-    const struct cow_header_v2 *cow_header = (const void *)buf;
-
-    if (buf_size >= sizeof(struct cow_header_v2) &&
-        be32_to_cpu(cow_header->magic) == COW_MAGIC &&
-        be32_to_cpu(cow_header->version) == COW_VERSION)
-        return 100;
-    else
-        return 0;
-}
-
-static int cow_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
-{
-    BDRVCowState *s = bs->opaque;
-    struct cow_header_v2 cow_header;
-    int bitmap_size;
-    int64_t size;
-    int ret;
-
-    /* see if it is a cow image */
-    ret = bdrv_pread(bs->file, 0, &cow_header, sizeof(cow_header));
-    if (ret < 0) {
-        goto fail;
-    }
-
-    if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
-        error_setg(errp, "Image not in COW format");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    if (be32_to_cpu(cow_header.version) != COW_VERSION) {
-        char version[64];
-        snprintf(version, sizeof(version),
-               "COW version %" PRIu32, cow_header.version);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-            bs->device_name, "cow", version);
-        ret = -ENOTSUP;
-        goto fail;
-    }
-
-    /* cow image found */
-    size = be64_to_cpu(cow_header.size);
-    bs->total_sectors = size / 512;
-
-    pstrcpy(bs->backing_file, sizeof(bs->backing_file),
-            cow_header.backing_file);
-
-    bitmap_size = ((bs->total_sectors + 7) >> 3) + sizeof(cow_header);
-    s->cow_sectors_offset = (bitmap_size + 511) & ~511;
-    qemu_co_mutex_init(&s->lock);
-    return 0;
- fail:
-    return ret;
-}
-
-static inline void cow_set_bits(uint8_t *bitmap, int start, int64_t nb_sectors)
-{
-    int64_t bitnum = start, last = start + nb_sectors;
-    while (bitnum < last) {
-        if ((bitnum & 7) == 0 && bitnum + 8 <= last) {
-            bitmap[bitnum / 8] = 0xFF;
-            bitnum += 8;
-            continue;
-        }
-        bitmap[bitnum/8] |= (1 << (bitnum % 8));
-        bitnum++;
-    }
-}
-
-#define BITS_PER_BITMAP_SECTOR (512 * 8)
-
-/* Cannot use bitmap.c on big-endian machines.  */
-static int cow_test_bit(int64_t bitnum, const uint8_t *bitmap)
-{
-    return (bitmap[bitnum / 8] & (1 << (bitnum & 7))) != 0;
-}
-
-static int cow_find_streak(const uint8_t *bitmap, int value, int start, int nb_sectors)
-{
-    int streak_value = value ? 0xFF : 0;
-    int last = MIN(start + nb_sectors, BITS_PER_BITMAP_SECTOR);
-    int bitnum = start;
-    while (bitnum < last) {
-        if ((bitnum & 7) == 0 && bitmap[bitnum / 8] == streak_value) {
-            bitnum += 8;
-            continue;
-        }
-        if (cow_test_bit(bitnum, bitmap) == value) {
-            bitnum++;
-            continue;
-        }
-        break;
-    }
-    return MIN(bitnum, last) - start;
-}
-
-/* Return true if first block has been changed (ie. current version is
- * in COW file).  Set the number of continuous blocks for which that
- * is true. */
-static int coroutine_fn cow_co_is_allocated(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *num_same)
-{
-    int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
-    uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
-    bool first = true;
-    int changed = 0, same = 0;
-
-    do {
-        int ret;
-        uint8_t bitmap[BDRV_SECTOR_SIZE];
-
-        bitnum &= BITS_PER_BITMAP_SECTOR - 1;
-        int sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
-
-        ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
-        }
-
-        if (first) {
-            changed = cow_test_bit(bitnum, bitmap);
-            first = false;
-        }
-
-        same += cow_find_streak(bitmap, changed, bitnum, nb_sectors);
-
-        bitnum += sector_bits;
-        nb_sectors -= sector_bits;
-        offset += BDRV_SECTOR_SIZE;
-    } while (nb_sectors);
-
-    *num_same = same;
-    return changed;
-}
-
-static int64_t coroutine_fn cow_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *num_same)
-{
-    BDRVCowState *s = bs->opaque;
-    int ret = cow_co_is_allocated(bs, sector_num, nb_sectors, num_same);
-    int64_t offset = s->cow_sectors_offset + (sector_num << BDRV_SECTOR_BITS);
-    if (ret < 0) {
-        return ret;
-    }
-    return (ret ? BDRV_BLOCK_DATA : 0) | offset | BDRV_BLOCK_OFFSET_VALID;
-}
-
-static int cow_update_bitmap(BlockDriverState *bs, int64_t sector_num,
-        int nb_sectors)
-{
-    int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
-    uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
-    bool first = true;
-    int sector_bits;
-
-    for ( ; nb_sectors;
-            bitnum += sector_bits,
-            nb_sectors -= sector_bits,
-            offset += BDRV_SECTOR_SIZE) {
-        int ret, set;
-        uint8_t bitmap[BDRV_SECTOR_SIZE];
-
-        bitnum &= BITS_PER_BITMAP_SECTOR - 1;
-        sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
-
-        ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
-        }
-
-        /* Skip over any already set bits */
-        set = cow_find_streak(bitmap, 1, bitnum, sector_bits);
-        bitnum += set;
-        sector_bits -= set;
-        nb_sectors -= set;
-        if (!sector_bits) {
-            continue;
-        }
-
-        if (first) {
-            ret = bdrv_flush(bs->file);
-            if (ret < 0) {
-                return ret;
-            }
-            first = false;
-        }
-
-        cow_set_bits(bitmap, bitnum, sector_bits);
-
-        ret = bdrv_pwrite(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
-        }
-    }
-
-    return 0;
-}
-
-static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
-                                 uint8_t *buf, int nb_sectors)
-{
-    BDRVCowState *s = bs->opaque;
-    int ret, n;
-
-    while (nb_sectors > 0) {
-        ret = cow_co_is_allocated(bs, sector_num, nb_sectors, &n);
-        if (ret < 0) {
-            return ret;
-        }
-        if (ret) {
-            ret = bdrv_pread(bs->file,
-                        s->cow_sectors_offset + sector_num * 512,
-                        buf, n * 512);
-            if (ret < 0) {
-                return ret;
-            }
-        } else {
-            if (bs->backing_hd) {
-                /* read from the base image */
-                ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
-                if (ret < 0) {
-                    return ret;
-                }
-            } else {
-                memset(buf, 0, n * 512);
-            }
-        }
-        nb_sectors -= n;
-        sector_num += n;
-        buf += n * 512;
-    }
-    return 0;
-}
-
-static coroutine_fn int cow_co_read(BlockDriverState *bs, int64_t sector_num,
-                                    uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVCowState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = cow_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
-static int cow_write(BlockDriverState *bs, int64_t sector_num,
-                     const uint8_t *buf, int nb_sectors)
-{
-    BDRVCowState *s = bs->opaque;
-    int ret;
-
-    ret = bdrv_pwrite(bs->file, s->cow_sectors_offset + sector_num * 512,
-                      buf, nb_sectors * 512);
-    if (ret < 0) {
-        return ret;
-    }
-
-    return cow_update_bitmap(bs, sector_num, nb_sectors);
-}
-
-static coroutine_fn int cow_co_write(BlockDriverState *bs, int64_t sector_num,
-                                     const uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVCowState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = cow_write(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
-static void cow_close(BlockDriverState *bs)
-{
-}
-
-static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
-{
-    struct cow_header_v2 cow_header;
-    struct stat st;
-    int64_t image_sectors = 0;
-    char *image_filename = NULL;
-    Error *local_err = NULL;
-    int ret;
-    BlockDriverState *cow_bs = NULL;
-
-    /* Read out options */
-    image_sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
-    image_filename = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
-    }
-
-    ret = bdrv_open(&cow_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
-    }
-
-    memset(&cow_header, 0, sizeof(cow_header));
-    cow_header.magic = cpu_to_be32(COW_MAGIC);
-    cow_header.version = cpu_to_be32(COW_VERSION);
-    if (image_filename) {
-        /* Note: if no file, we put a dummy mtime */
-        cow_header.mtime = cpu_to_be32(0);
-
-        if (stat(image_filename, &st) != 0) {
-            goto mtime_fail;
-        }
-        cow_header.mtime = cpu_to_be32(st.st_mtime);
-    mtime_fail:
-        pstrcpy(cow_header.backing_file, sizeof(cow_header.backing_file),
-                image_filename);
-    }
-    cow_header.sectorsize = cpu_to_be32(512);
-    cow_header.size = cpu_to_be64(image_sectors * 512);
-    ret = bdrv_pwrite(cow_bs, 0, &cow_header, sizeof(cow_header));
-    if (ret < 0) {
-        goto exit;
-    }
-
-    /* resize to include at least all the bitmap */
-    ret = bdrv_truncate(cow_bs,
-        sizeof(cow_header) + ((image_sectors + 7) >> 3));
-    if (ret < 0) {
-        goto exit;
-    }
-
-exit:
-    g_free(image_filename);
-    if (cow_bs) {
-        bdrv_unref(cow_bs);
-    }
-    return ret;
-}
-
-static QemuOptsList cow_create_opts = {
-    .name = "cow-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(cow_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        { /* end of list */ }
-    }
-};
-
-static BlockDriver bdrv_cow = {
-    .format_name    = "cow",
-    .instance_size  = sizeof(BDRVCowState),
-
-    .bdrv_probe     = cow_probe,
-    .bdrv_open      = cow_open,
-    .bdrv_close     = cow_close,
-    .bdrv_create    = cow_create,
-    .bdrv_has_zero_init     = bdrv_has_zero_init_1,
-    .supports_backing       = true,
-
-    .bdrv_read              = cow_co_read,
-    .bdrv_write             = cow_co_write,
-    .bdrv_co_get_block_status   = cow_co_get_block_status,
-
-    .create_opts    = &cow_create_opts,
-};
-
-static void bdrv_cow_init(void)
-{
-    bdrv_register(&bdrv_cow);
-}
-
-block_init(bdrv_cow_init);

block/curl.c

@@ -212,7 +212,7 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
             qemu_iovec_from_buf(acb->qiov, 0, s->orig_buf + acb->start,
                                 acb->end - acb->start);
             acb->common.cb(acb->common.opaque, 0);
-            qemu_aio_release(acb);
+            qemu_aio_unref(acb);
             s->acb[i] = NULL;
         }
     }
@@ -304,7 +304,7 @@ static void curl_multi_check_completion(BDRVCURLState *s)
                     }
 
                     acb->common.cb(acb->common.opaque, -EIO);
-                    qemu_aio_release(acb);
+                    qemu_aio_unref(acb);
                     state->acb[i] = NULL;
                 }
             }
@@ -613,14 +613,8 @@ out_noclean:
     return -EINVAL;
 }
 
-static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    // Do we have to implement canceling? Seems to work without...
-}
-
 static const AIOCBInfo curl_aiocb_info = {
     .aiocb_size         = sizeof(CURLAIOCB),
-    .cancel             = curl_aio_cancel,
 };
 
 
@@ -642,7 +636,7 @@ static void curl_readv_bh_cb(void *p)
     // we can just call the callback and be done.
     switch (curl_find_buf(s, start, acb->nb_sectors * SECTOR_SIZE, acb)) {
         case FIND_RET_OK:
-            qemu_aio_release(acb);
+            qemu_aio_unref(acb);
             // fall through
         case FIND_RET_WAIT:
             return;
@@ -654,7 +648,7 @@ static void curl_readv_bh_cb(void *p)
     state = curl_init_state(acb->common.bs, s);
     if (!state) {
         acb->common.cb(acb->common.opaque, -EIO);
-        qemu_aio_release(acb);
+        qemu_aio_unref(acb);
         return;
     }
 
@@ -670,7 +664,7 @@ static void curl_readv_bh_cb(void *p)
     if (state->buf_len && state->orig_buf == NULL) {
         curl_clean_state(state);
         acb->common.cb(acb->common.opaque, -ENOMEM);
-        qemu_aio_release(acb);
+        qemu_aio_unref(acb);
         return;
     }
     state->acb[0] = acb;

block/gluster.c

@@ -494,8 +494,8 @@ static int qemu_gluster_create(const char *filename,
         goto out;
     }
 
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
     if (!tmp || !strcmp(tmp, "off")) {
@@ -516,9 +516,8 @@ static int qemu_gluster_create(const char *filename,
     if (!fd) {
         ret = -errno;
     } else {
-        if (!glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE)) {
-            if (prealloc && qemu_gluster_zerofill(fd, 0,
-                    total_size * BDRV_SECTOR_SIZE)) {
+        if (!glfs_ftruncate(fd, total_size)) {
+            if (prealloc && qemu_gluster_zerofill(fd, 0, total_size)) {
                 ret = -errno;
             }
         } else {

block/iscsi.c

@@ -34,7 +34,6 @@
 #include "qemu/bitops.h"
 #include "qemu/bitmap.h"
 #include "block/block_int.h"
-#include "trace.h"
 #include "block/scsi.h"
 #include "qemu/iov.h"
 #include "sysemu/sysemu.h"
@@ -88,7 +87,6 @@ typedef struct IscsiAIOCB {
     struct scsi_task *task;
     uint8_t *buf;
     int status;
-    int canceled;
     int64_t sector_num;
     int nb_sectors;
 #ifdef __linux__
@@ -120,16 +118,14 @@ iscsi_bh_cb(void *p)
     g_free(acb->buf);
     acb->buf = NULL;
 
-    if (acb->canceled == 0) {
-        acb->common.cb(acb->common.opaque, acb->status);
-    }
+    acb->common.cb(acb->common.opaque, acb->status);
 
     if (acb->task != NULL) {
         scsi_free_scsi_task(acb->task);
         acb->task = NULL;
     }
 
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 }
 
 static void
@@ -240,20 +236,15 @@ iscsi_aio_cancel(BlockDriverAIOCB *blockacb)
         return;
     }
 
-    acb->canceled = 1;
-
     /* send a task mgmt call to the target to cancel the task on the target */
     iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
                                      iscsi_abort_task_cb, acb);
 
-    while (acb->status == -EINPROGRESS) {
-        aio_poll(iscsilun->aio_context, true);
-    }
 }
 
 static const AIOCBInfo iscsi_aiocb_info = {
     .aiocb_size         = sizeof(IscsiAIOCB),
-    .cancel             = iscsi_aio_cancel,
+    .cancel_async       = iscsi_aio_cancel,
 };
 
 
@@ -638,10 +629,6 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
     g_free(acb->buf);
     acb->buf = NULL;
 
-    if (acb->canceled != 0) {
-        return;
-    }
-
     acb->status = 0;
     if (status < 0) {
         error_report("Failed to ioctl(SG_IO) to iSCSI lun. %s",
@@ -683,7 +670,6 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
     acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
 
     acb->iscsilun = iscsilun;
-    acb->canceled    = 0;
     acb->bh          = NULL;
     acb->status      = -EINPROGRESS;
     acb->buf         = NULL;
@@ -693,7 +679,7 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
     if (acb->task == NULL) {
         error_report("iSCSI: Failed to allocate task for scsi command. %s",
                      iscsi_get_error(iscsi));
-        qemu_aio_release(acb);
+        qemu_aio_unref(acb);
         return NULL;
     }
     memset(acb->task, 0, sizeof(struct scsi_task));
@@ -731,7 +717,7 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
                                  (data.size > 0) ? &data : NULL,
                                  acb) != 0) {
         scsi_free_scsi_task(acb->task);
-        qemu_aio_release(acb);
+        qemu_aio_unref(acb);
         return NULL;
     }
 
@@ -1531,8 +1517,8 @@ static int iscsi_create(const char *filename, QemuOpts *opts, Error **errp)
     bs = bdrv_new("", &error_abort);
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = DIV_ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                              BDRV_SECTOR_SIZE);
     bs->opaque = g_new0(struct IscsiLun, 1);
     iscsilun = bs->opaque;
 

block/linux-aio.c

@@ -85,11 +85,10 @@ static void qemu_laio_process_completion(struct qemu_laio_state *s,
                 ret = -EINVAL;
             }
         }
-
-        laiocb->common.cb(laiocb->common.opaque, ret);
     }
+    laiocb->common.cb(laiocb->common.opaque, ret);
 
-    qemu_aio_release(laiocb);
+    qemu_aio_unref(laiocb);
 }
 
 /* The completion BH fetches completed I/O requests and invokes their
@@ -153,35 +152,22 @@ static void laio_cancel(BlockDriverAIOCB *blockacb)
     struct io_event event;
     int ret;
 
-    if (laiocb->ret != -EINPROGRESS)
+    if (laiocb->ret != -EINPROGRESS) {
         return;
-
-    /*
-     * Note that as of Linux 2.6.31 neither the block device code nor any
-     * filesystem implements cancellation of AIO request.
-     * Thus the polling loop below is the normal code path.
-     */
+    }
     ret = io_cancel(laiocb->ctx->ctx, &laiocb->iocb, &event);
-    if (ret == 0) {
-        laiocb->ret = -ECANCELED;
+    laiocb->ret = -ECANCELED;
+    if (ret != 0) {
+        /* iocb is not cancelled, cb will be called by the event loop later */
         return;
     }
 
-    /*
-     * We have to wait for the iocb to finish.
-     *
-     * The only way to get the iocb status update is by polling the io context.
-     * We might be able to do this slightly more optimal by removing the
-     * O_NONBLOCK flag.
-     */
-    while (laiocb->ret == -EINPROGRESS) {
-        qemu_laio_completion_cb(&laiocb->ctx->e);
-    }
+    laiocb->common.cb(laiocb->common.opaque, laiocb->ret);
 }
 
 static const AIOCBInfo laio_aiocb_info = {
     .aiocb_size         = sizeof(struct qemu_laiocb),
-    .cancel             = laio_cancel,
+    .cancel_async       = laio_cancel,
 };
 
 static void ioq_init(LaioQueue *io_q)
@@ -300,7 +286,7 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
     return &laiocb->common;
 
 out_free_aiocb:
-    qemu_aio_release(laiocb);
+    qemu_aio_unref(laiocb);
     return NULL;
 }
 

block/nfs.c

@@ -418,7 +418,8 @@ static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
     client->aio_context = qemu_get_aio_context();
 
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     ret = nfs_client_open(client, url, O_CREAT, errp);
     if (ret < 0) {

block/null.c

@@ -0,0 +1,168 @@
+/*
+ * Null block driver
+ *
+ * Authors:
+ *  Fam Zheng <famz@redhat.com>
+ *
+ * Copyright (C) 2014 Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "block/block_int.h"
+
+typedef struct {
+    int64_t length;
+} BDRVNullState;
+
+static QemuOptsList runtime_opts = {
+    .name = "null",
+    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+    .desc = {
+        {
+            .name = "filename",
+            .type = QEMU_OPT_STRING,
+            .help = "",
+        },
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "size of the null block",
+        },
+        { /* end of list */ }
+    },
+};
+
+static int null_file_open(BlockDriverState *bs, QDict *options, int flags,
+                          Error **errp)
+{
+    QemuOpts *opts;
+    BDRVNullState *s = bs->opaque;
+
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &error_abort);
+    s->length =
+        qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 1 << 30);
+    qemu_opts_del(opts);
+    return 0;
+}
+
+static void null_close(BlockDriverState *bs)
+{
+}
+
+static int64_t null_getlength(BlockDriverState *bs)
+{
+    BDRVNullState *s = bs->opaque;
+    return s->length;
+}
+
+static coroutine_fn int null_co_readv(BlockDriverState *bs,
+                                      int64_t sector_num, int nb_sectors,
+                                      QEMUIOVector *qiov)
+{
+    return 0;
+}
+
+static coroutine_fn int null_co_writev(BlockDriverState *bs,
+                                       int64_t sector_num, int nb_sectors,
+                                       QEMUIOVector *qiov)
+{
+    return 0;
+}
+
+static coroutine_fn int null_co_flush(BlockDriverState *bs)
+{
+    return 0;
+}
+
+typedef struct {
+    BlockDriverAIOCB common;
+    QEMUBH *bh;
+} NullAIOCB;
+
+static const AIOCBInfo null_aiocb_info = {
+    .aiocb_size = sizeof(NullAIOCB),
+};
+
+static void null_bh_cb(void *opaque)
+{
+    NullAIOCB *acb = opaque;
+    acb->common.cb(acb->common.opaque, 0);
+    qemu_bh_delete(acb->bh);
+    qemu_aio_unref(acb);
+}
+
+static inline BlockDriverAIOCB *null_aio_common(BlockDriverState *bs,
+                                                BlockDriverCompletionFunc *cb,
+                                                void *opaque)
+{
+    NullAIOCB *acb;
+
+    acb = qemu_aio_get(&null_aiocb_info, bs, cb, opaque);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), null_bh_cb, acb);
+    qemu_bh_schedule(acb->bh);
+    return &acb->common;
+}
+
+static BlockDriverAIOCB *null_aio_readv(BlockDriverState *bs,
+                                        int64_t sector_num, QEMUIOVector *qiov,
+                                        int nb_sectors,
+                                        BlockDriverCompletionFunc *cb,
+                                        void *opaque)
+{
+    return null_aio_common(bs, cb, opaque);
+}
+
+static BlockDriverAIOCB *null_aio_writev(BlockDriverState *bs,
+                                         int64_t sector_num, QEMUIOVector *qiov,
+                                         int nb_sectors,
+                                         BlockDriverCompletionFunc *cb,
+                                         void *opaque)
+{
+    return null_aio_common(bs, cb, opaque);
+}
+
+static BlockDriverAIOCB *null_aio_flush(BlockDriverState *bs,
+                                        BlockDriverCompletionFunc *cb,
+                                        void *opaque)
+{
+    return null_aio_common(bs, cb, opaque);
+}
+
+static BlockDriver bdrv_null_co = {
+    .format_name            = "null-co",
+    .protocol_name          = "null-co",
+    .instance_size          = sizeof(BDRVNullState),
+
+    .bdrv_file_open         = null_file_open,
+    .bdrv_close             = null_close,
+    .bdrv_getlength         = null_getlength,
+
+    .bdrv_co_readv          = null_co_readv,
+    .bdrv_co_writev         = null_co_writev,
+    .bdrv_co_flush_to_disk  = null_co_flush,
+};
+
+static BlockDriver bdrv_null_aio = {
+    .format_name            = "null-aio",
+    .protocol_name          = "null-aio",
+    .instance_size          = sizeof(BDRVNullState),
+
+    .bdrv_file_open         = null_file_open,
+    .bdrv_close             = null_close,
+    .bdrv_getlength         = null_getlength,
+
+    .bdrv_aio_readv         = null_aio_readv,
+    .bdrv_aio_writev        = null_aio_writev,
+    .bdrv_aio_flush         = null_aio_flush,
+};
+
+static void bdrv_null_init(void)
+{
+    bdrv_register(&bdrv_null_co);
+    bdrv_register(&bdrv_null_aio);
+}
+
+block_init(bdrv_null_init);

block/qapi.c

@@ -333,15 +333,16 @@ static BlockStats *bdrv_query_stats(const BlockDriverState *bs)
     }
 
     s->stats = g_malloc0(sizeof(*s->stats));
-    s->stats->rd_bytes = bs->nr_bytes[BDRV_ACCT_READ];
-    s->stats->wr_bytes = bs->nr_bytes[BDRV_ACCT_WRITE];
-    s->stats->rd_operations = bs->nr_ops[BDRV_ACCT_READ];
-    s->stats->wr_operations = bs->nr_ops[BDRV_ACCT_WRITE];
-    s->stats->wr_highest_offset = bs->wr_highest_sector * BDRV_SECTOR_SIZE;
-    s->stats->flush_operations = bs->nr_ops[BDRV_ACCT_FLUSH];
-    s->stats->wr_total_time_ns = bs->total_time_ns[BDRV_ACCT_WRITE];
-    s->stats->rd_total_time_ns = bs->total_time_ns[BDRV_ACCT_READ];
-    s->stats->flush_total_time_ns = bs->total_time_ns[BDRV_ACCT_FLUSH];
+    s->stats->rd_bytes = bs->stats.nr_bytes[BLOCK_ACCT_READ];
+    s->stats->wr_bytes = bs->stats.nr_bytes[BLOCK_ACCT_WRITE];
+    s->stats->rd_operations = bs->stats.nr_ops[BLOCK_ACCT_READ];
+    s->stats->wr_operations = bs->stats.nr_ops[BLOCK_ACCT_WRITE];
+    s->stats->wr_highest_offset =
+        bs->stats.wr_highest_sector * BDRV_SECTOR_SIZE;
+    s->stats->flush_operations = bs->stats.nr_ops[BLOCK_ACCT_FLUSH];
+    s->stats->wr_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_WRITE];
+    s->stats->rd_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_READ];
+    s->stats->flush_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_FLUSH];
 
     if (bs->file) {
         s->has_parent = true;

block/qcow.c

@@ -725,7 +725,8 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     BlockDriverState *qcow_bs;
 
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
         flags |= BLOCK_FLAG_ENCRYPT;
@@ -753,7 +754,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     memset(&header, 0, sizeof(header));
     header.magic = cpu_to_be32(QCOW_MAGIC);
     header.version = cpu_to_be32(QCOW_VERSION);
-    header.size = cpu_to_be64(total_size * 512);
+    header.size = cpu_to_be64(total_size);
     header_size = sizeof(header);
     backing_filename_len = 0;
     if (backing_file) {
@@ -775,7 +776,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
     header_size = (header_size + 7) & ~7;
     shift = header.cluster_bits + header.l2_bits;
-    l1_size = ((total_size * 512) + (1LL << shift) - 1) >> shift;
+    l1_size = (total_size + (1LL << shift) - 1) >> shift;
 
     header.l1_table_offset = cpu_to_be64(header_size);
     if (flags & BLOCK_FLAG_ENCRYPT) {

block/qcow2-cluster.c

@@ -486,6 +486,13 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
         goto out;
     }
 
+    if (offset_into_cluster(s, l2_offset)) {
+        qcow2_signal_corruption(bs, true, -1, -1, "L2 table offset %#" PRIx64
+                                " unaligned (L1 index: %#" PRIx64 ")",
+                                l2_offset, l1_index);
+        return -EIO;
+    }
+
     /* load the l2 table in memory */
 
     ret = l2_load(bs, l2_offset, &l2_table);
@@ -508,8 +515,11 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
         break;
     case QCOW2_CLUSTER_ZERO:
         if (s->qcow_version < 3) {
-            qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-            return -EIO;
+            qcow2_signal_corruption(bs, true, -1, -1, "Zero cluster entry found"
+                                    " in pre-v3 image (L2 offset: %#" PRIx64
+                                    ", L2 index: %#x)", l2_offset, l2_index);
+            ret = -EIO;
+            goto fail;
         }
         c = count_contiguous_clusters(nb_clusters, s->cluster_size,
                 &l2_table[l2_index], QCOW_OFLAG_ZERO);
@@ -525,6 +535,14 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
         c = count_contiguous_clusters(nb_clusters, s->cluster_size,
                 &l2_table[l2_index], QCOW_OFLAG_ZERO);
         *cluster_offset &= L2E_OFFSET_MASK;
+        if (offset_into_cluster(s, *cluster_offset)) {
+            qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset %#"
+                                    PRIx64 " unaligned (L2 offset: %#" PRIx64
+                                    ", L2 index: %#x)", *cluster_offset,
+                                    l2_offset, l2_index);
+            ret = -EIO;
+            goto fail;
+        }
         break;
     default:
         abort();
@@ -541,6 +559,10 @@ out:
     *num = nb_available - index_in_cluster;
 
     return ret;
+
+fail:
+    qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
+    return ret;
 }
 
 /*
@@ -576,6 +598,12 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
 
     assert(l1_index < s->l1_size);
     l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
+    if (offset_into_cluster(s, l2_offset)) {
+        qcow2_signal_corruption(bs, true, -1, -1, "L2 table offset %#" PRIx64
+                                " unaligned (L1 index: %#" PRIx64 ")",
+                                l2_offset, l1_index);
+        return -EIO;
+    }
 
     /* seek the l2 table of the given l2 offset */
 
@@ -948,6 +976,15 @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
         bool offset_matches =
             (cluster_offset & L2E_OFFSET_MASK) == *host_offset;
 
+        if (offset_into_cluster(s, cluster_offset & L2E_OFFSET_MASK)) {
+            qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset "
+                                    "%#llx unaligned (guest offset: %#" PRIx64
+                                    ")", cluster_offset & L2E_OFFSET_MASK,
+                                    guest_offset);
+            ret = -EIO;
+            goto out;
+        }
+
         if (*host_offset != 0 && !offset_matches) {
             *bytes = 0;
             ret = 0;
@@ -979,7 +1016,7 @@ out:
 
     /* Only return a host offset if we actually made progress. Otherwise we
      * would make requirements for handle_alloc() that it can't fulfill */
-    if (ret) {
+    if (ret > 0) {
         *host_offset = (cluster_offset & L2E_OFFSET_MASK)
                      + offset_into_cluster(s, guest_offset);
     }

block/qcow2-refcount.c

@@ -26,8 +26,6 @@
 #include "block/block_int.h"
 #include "block/qcow2.h"
 #include "qemu/range.h"
-#include "qapi/qmp/types.h"
-#include "qapi-event.h"
 
 static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
@@ -110,6 +108,13 @@ static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
     if (!refcount_block_offset)
         return 0;
 
+    if (offset_into_cluster(s, refcount_block_offset)) {
+        qcow2_signal_corruption(bs, true, -1, -1, "Refblock offset %#" PRIx64
+                                " unaligned (reftable index: %#" PRIx64 ")",
+                                refcount_block_offset, refcount_table_index);
+        return -EIO;
+    }
+
     ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
         (void**) &refcount_block);
     if (ret < 0) {
@@ -183,6 +188,14 @@ static int alloc_refcount_block(BlockDriverState *bs,
 
         /* If it's already there, we're done */
         if (refcount_block_offset) {
+            if (offset_into_cluster(s, refcount_block_offset)) {
+                qcow2_signal_corruption(bs, true, -1, -1, "Refblock offset %#"
+                                        PRIx64 " unaligned (reftable index: "
+                                        "%#x)", refcount_block_offset,
+                                        refcount_table_index);
+                return -EIO;
+            }
+
              return load_refcount_block(bs, refcount_block_offset,
                  (void**) refcount_block);
         }
@@ -838,8 +851,14 @@ void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
     case QCOW2_CLUSTER_NORMAL:
     case QCOW2_CLUSTER_ZERO:
         if (l2_entry & L2E_OFFSET_MASK) {
-            qcow2_free_clusters(bs, l2_entry & L2E_OFFSET_MASK,
-                                nb_clusters << s->cluster_bits, type);
+            if (offset_into_cluster(s, l2_entry & L2E_OFFSET_MASK)) {
+                qcow2_signal_corruption(bs, false, -1, -1,
+                                        "Cannot free unaligned cluster %#llx",
+                                        l2_entry & L2E_OFFSET_MASK);
+            } else {
+                qcow2_free_clusters(bs, l2_entry & L2E_OFFSET_MASK,
+                                    nb_clusters << s->cluster_bits, type);
+            }
         }
         break;
     case QCOW2_CLUSTER_UNALLOCATED:
@@ -903,6 +922,14 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
             old_l2_offset = l2_offset;
             l2_offset &= L1E_OFFSET_MASK;
 
+            if (offset_into_cluster(s, l2_offset)) {
+                qcow2_signal_corruption(bs, true, -1, -1, "L2 table offset %#"
+                                        PRIx64 " unaligned (L1 index: %#x)",
+                                        l2_offset, i);
+                ret = -EIO;
+                goto fail;
+            }
+
             ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset,
                 (void**) &l2_table);
             if (ret < 0) {
@@ -935,6 +962,17 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
 
                     case QCOW2_CLUSTER_NORMAL:
                     case QCOW2_CLUSTER_ZERO:
+                        if (offset_into_cluster(s, offset & L2E_OFFSET_MASK)) {
+                            qcow2_signal_corruption(bs, true, -1, -1, "Data "
+                                                    "cluster offset %#llx "
+                                                    "unaligned (L2 offset: %#"
+                                                    PRIx64 ", L2 index: %#x)",
+                                                    offset & L2E_OFFSET_MASK,
+                                                    l2_offset, j);
+                            ret = -EIO;
+                            goto fail;
+                        }
+
                         cluster_index = (offset & L2E_OFFSET_MASK) >> s->cluster_bits;
                         if (!cluster_index) {
                             /* unallocated */
@@ -1838,26 +1876,11 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
         return ret;
     } else if (ret > 0) {
         int metadata_ol_bitnr = ffs(ret) - 1;
-        char *message;
-
         assert(metadata_ol_bitnr < QCOW2_OL_MAX_BITNR);
 
-        fprintf(stderr, "qcow2: Preventing invalid write on metadata (overlaps "
-                "with %s); image marked as corrupt.\n",
-                metadata_ol_names[metadata_ol_bitnr]);
-        message = g_strdup_printf("Prevented %s overwrite",
-                metadata_ol_names[metadata_ol_bitnr]);
-        qapi_event_send_block_image_corrupted(bdrv_get_device_name(bs),
-                                              message,
-                                              true,
-                                              offset,
-                                              true,
-                                              size,
-                                              &error_abort);
-        g_free(message);
-
-        qcow2_mark_corrupt(bs);
-        bs->drv = NULL; /* make BDS unusable */
+        qcow2_signal_corruption(bs, true, offset, size, "Preventing invalid "
+                                "write on metadata (overlaps with %s)",
+                                metadata_ol_names[metadata_ol_bitnr]);
         return -EIO;
     }
 

block/qcow2.c

@@ -30,6 +30,9 @@
 #include "qemu/error-report.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qbool.h"
+#include "qapi/util.h"
+#include "qapi/qmp/types.h"
+#include "qapi-event.h"
 #include "trace.h"
 #include "qemu/option_int.h"
 
@@ -402,6 +405,12 @@ static QemuOptsList qcow2_runtime_opts = {
             .help = "Selects which overlap checks to perform from a range of "
                     "templates (none, constant, cached, all)",
         },
+        {
+            .name = QCOW2_OPT_OVERLAP_TEMPLATE,
+            .type = QEMU_OPT_STRING,
+            .help = "Selects which overlap checks to perform from a range of "
+                    "templates (none, constant, cached, all)",
+        },
         {
             .name = QCOW2_OPT_OVERLAP_MAIN_HEADER,
             .type = QEMU_OPT_BOOL,
@@ -535,11 +544,11 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     unsigned int len, i;
     int ret = 0;
     QCowHeader header;
-    QemuOpts *opts;
+    QemuOpts *opts = NULL;
     Error *local_err = NULL;
     uint64_t ext_end;
     uint64_t l1_vm_state_index;
-    const char *opt_overlap_check;
+    const char *opt_overlap_check, *opt_overlap_check_template;
     int overlap_check_template = 0;
     uint64_t l2_cache_size, refcount_cache_size;
 
@@ -919,7 +928,21 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     s->discard_passthrough[QCOW2_DISCARD_OTHER] =
         qemu_opt_get_bool(opts, QCOW2_OPT_DISCARD_OTHER, false);
 
-    opt_overlap_check = qemu_opt_get(opts, "overlap-check") ?: "cached";
+    opt_overlap_check = qemu_opt_get(opts, QCOW2_OPT_OVERLAP);
+    opt_overlap_check_template = qemu_opt_get(opts, QCOW2_OPT_OVERLAP_TEMPLATE);
+    if (opt_overlap_check_template && opt_overlap_check &&
+        strcmp(opt_overlap_check_template, opt_overlap_check))
+    {
+        error_setg(errp, "Conflicting values for qcow2 options '"
+                   QCOW2_OPT_OVERLAP "' ('%s') and '" QCOW2_OPT_OVERLAP_TEMPLATE
+                   "' ('%s')", opt_overlap_check, opt_overlap_check_template);
+        ret = -EINVAL;
+        goto fail;
+    }
+    if (!opt_overlap_check) {
+        opt_overlap_check = opt_overlap_check_template ?: "cached";
+    }
+
     if (!strcmp(opt_overlap_check, "none")) {
         overlap_check_template = 0;
     } else if (!strcmp(opt_overlap_check, "constant")) {
@@ -932,7 +955,6 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         error_setg(errp, "Unsupported value '%s' for qcow2 option "
                    "'overlap-check'. Allowed are either of the following: "
                    "none, constant, cached, all", opt_overlap_check);
-        qemu_opts_del(opts);
         ret = -EINVAL;
         goto fail;
     }
@@ -947,6 +969,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     qemu_opts_del(opts);
+    opts = NULL;
 
     if (s->use_lazy_refcounts && s->qcow_version < 3) {
         error_setg(errp, "Lazy refcounts require a qcow2 image with at least "
@@ -964,6 +987,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     return ret;
 
  fail:
+    qemu_opts_del(opts);
     g_free(s->unknown_header_fields);
     cleanup_unknown_header_ext(bs);
     qcow2_free_snapshots(bs);
@@ -1738,7 +1762,7 @@ static int preallocate(BlockDriverState *bs)
 
 static int qcow2_create2(const char *filename, int64_t total_size,
                          const char *backing_file, const char *backing_format,
-                         int flags, size_t cluster_size, int prealloc,
+                         int flags, size_t cluster_size, PreallocMode prealloc,
                          QemuOpts *opts, int version,
                          Error **errp)
 {
@@ -1771,6 +1795,56 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     Error *local_err = NULL;
     int ret;
 
+    if (prealloc == PREALLOC_MODE_FULL || prealloc == PREALLOC_MODE_FALLOC) {
+        int64_t meta_size = 0;
+        uint64_t nreftablee, nrefblocke, nl1e, nl2e;
+        int64_t aligned_total_size = align_offset(total_size, cluster_size);
+
+        /* header: 1 cluster */
+        meta_size += cluster_size;
+
+        /* total size of L2 tables */
+        nl2e = aligned_total_size / cluster_size;
+        nl2e = align_offset(nl2e, cluster_size / sizeof(uint64_t));
+        meta_size += nl2e * sizeof(uint64_t);
+
+        /* total size of L1 tables */
+        nl1e = nl2e * sizeof(uint64_t) / cluster_size;
+        nl1e = align_offset(nl1e, cluster_size / sizeof(uint64_t));
+        meta_size += nl1e * sizeof(uint64_t);
+
+        /* total size of refcount blocks
+         *
+         * note: every host cluster is reference-counted, including metadata
+         * (even refcount blocks are recursively included).
+         * Let:
+         *   a = total_size (this is the guest disk size)
+         *   m = meta size not including refcount blocks and refcount tables
+         *   c = cluster size
+         *   y1 = number of refcount blocks entries
+         *   y2 = meta size including everything
+         * then,
+         *   y1 = (y2 + a)/c
+         *   y2 = y1 * sizeof(u16) + y1 * sizeof(u16) * sizeof(u64) / c + m
+         * we can get y1:
+         *   y1 = (a + m) / (c - sizeof(u16) - sizeof(u16) * sizeof(u64) / c)
+         */
+        nrefblocke = (aligned_total_size + meta_size + cluster_size) /
+            (cluster_size - sizeof(uint16_t) -
+             1.0 * sizeof(uint16_t) * sizeof(uint64_t) / cluster_size);
+        nrefblocke = align_offset(nrefblocke, cluster_size / sizeof(uint16_t));
+        meta_size += nrefblocke * sizeof(uint16_t);
+
+        /* total size of refcount tables */
+        nreftablee = nrefblocke * sizeof(uint16_t) / cluster_size;
+        nreftablee = align_offset(nreftablee, cluster_size / sizeof(uint64_t));
+        meta_size += nreftablee * sizeof(uint64_t);
+
+        qemu_opt_set_number(opts, BLOCK_OPT_SIZE,
+                            aligned_total_size + meta_size);
+        qemu_opt_set(opts, BLOCK_OPT_PREALLOC, PreallocMode_lookup[prealloc]);
+    }
+
     ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
@@ -1859,7 +1933,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     /* Okay, now that we have a valid image, let's give it the right size */
-    ret = bdrv_truncate(bs, total_size * BDRV_SECTOR_SIZE);
+    ret = bdrv_truncate(bs, total_size);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not resize image");
         goto out;
@@ -1876,7 +1950,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     /* And if we're supposed to preallocate metadata, do that now */
-    if (prealloc) {
+    if (prealloc != PREALLOC_MODE_OFF) {
         BDRVQcowState *s = bs->opaque;
         qemu_co_mutex_lock(&s->lock);
         ret = preallocate(bs);
@@ -1912,16 +1986,17 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
     char *backing_file = NULL;
     char *backing_fmt = NULL;
     char *buf = NULL;
-    uint64_t sectors = 0;
+    uint64_t size = 0;
     int flags = 0;
     size_t cluster_size = DEFAULT_CLUSTER_SIZE;
-    int prealloc = 0;
+    PreallocMode prealloc;
     int version = 3;
     Error *local_err = NULL;
     int ret;
 
     /* Read out options */
-    sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                    BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
     if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
@@ -1930,12 +2005,11 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
     cluster_size = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE,
                                          DEFAULT_CLUSTER_SIZE);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    if (!buf || !strcmp(buf, "off")) {
-        prealloc = 0;
-    } else if (!strcmp(buf, "metadata")) {
-        prealloc = 1;
-    } else {
-        error_setg(errp, "Invalid preallocation mode: '%s'", buf);
+    prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
+                               PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
+                               &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
         ret = -EINVAL;
         goto finish;
     }
@@ -1957,7 +2031,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
         flags |= BLOCK_FLAG_LAZY_REFCOUNTS;
     }
 
-    if (backing_file && prealloc) {
+    if (backing_file && prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Backing file and preallocation cannot be used at "
                    "the same time");
         ret = -EINVAL;
@@ -1971,7 +2045,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
         goto finish;
     }
 
-    ret = qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
+    ret = qcow2_create2(filename, size, backing_file, backing_fmt, flags,
                         cluster_size, prealloc, opts, version, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -2478,6 +2552,52 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts)
     return 0;
 }
 
+/*
+ * If offset or size are negative, respectively, they will not be included in
+ * the BLOCK_IMAGE_CORRUPTED event emitted.
+ * fatal will be ignored for read-only BDS; corruptions found there will always
+ * be considered non-fatal.
+ */
+void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset,
+                             int64_t size, const char *message_format, ...)
+{
+    BDRVQcowState *s = bs->opaque;
+    char *message;
+    va_list ap;
+
+    fatal = fatal && !bs->read_only;
+
+    if (s->signaled_corruption &&
+        (!fatal || (s->incompatible_features & QCOW2_INCOMPAT_CORRUPT)))
+    {
+        return;
+    }
+
+    va_start(ap, message_format);
+    message = g_strdup_vprintf(message_format, ap);
+    va_end(ap);
+
+    if (fatal) {
+        fprintf(stderr, "qcow2: Marking image as corrupt: %s; further "
+                "corruption events will be suppressed\n", message);
+    } else {
+        fprintf(stderr, "qcow2: Image is corrupt: %s; further non-fatal "
+                "corruption events will be suppressed\n", message);
+    }
+
+    qapi_event_send_block_image_corrupted(bdrv_get_device_name(bs), message,
+                                          offset >= 0, offset, size >= 0, size,
+                                          fatal, &error_abort);
+    g_free(message);
+
+    if (fatal) {
+        qcow2_mark_corrupt(bs);
+        bs->drv = NULL; /* make BDS unusable */
+    }
+
+    s->signaled_corruption = true;
+}
+
 static QemuOptsList qcow2_create_opts = {
     .name = "qcow2-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(qcow2_create_opts.head),
@@ -2517,7 +2637,8 @@ static QemuOptsList qcow2_create_opts = {
         {
             .name = BLOCK_OPT_PREALLOC,
             .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode (allowed values: off, metadata)"
+            .help = "Preallocation mode (allowed values: off, metadata, "
+                    "falloc, full)"
         },
         {
             .name = BLOCK_OPT_LAZY_REFCOUNTS,

block/qcow2.h

@@ -83,6 +83,7 @@
 #define QCOW2_OPT_DISCARD_SNAPSHOT "pass-discard-snapshot"
 #define QCOW2_OPT_DISCARD_OTHER "pass-discard-other"
 #define QCOW2_OPT_OVERLAP "overlap-check"
+#define QCOW2_OPT_OVERLAP_TEMPLATE "overlap-check.template"
 #define QCOW2_OPT_OVERLAP_MAIN_HEADER "overlap-check.main-header"
 #define QCOW2_OPT_OVERLAP_ACTIVE_L1 "overlap-check.active-l1"
 #define QCOW2_OPT_OVERLAP_ACTIVE_L2 "overlap-check.active-l2"
@@ -261,6 +262,7 @@ typedef struct BDRVQcowState {
     bool discard_passthrough[QCOW2_DISCARD_MAX];
 
     int overlap_check; /* bitmask of Qcow2MetadataOverlap values */
+    bool signaled_corruption;
 
     uint64_t incompatible_features;
     uint64_t compatible_features;
@@ -477,6 +479,10 @@ int qcow2_mark_corrupt(BlockDriverState *bs);
 int qcow2_mark_consistent(BlockDriverState *bs);
 int qcow2_update_header(BlockDriverState *bs);
 
+void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset,
+                             int64_t size, const char *message_format, ...)
+                             GCC_FMT_ATTR(5, 6);
+
 /* qcow2-refcount.c functions */
 int qcow2_refcount_init(BlockDriverState *bs);
 void qcow2_refcount_close(BlockDriverState *bs);

block/qed.c

@@ -18,22 +18,8 @@
 #include "qapi/qmp/qerror.h"
 #include "migration/migration.h"
 
-static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    QEDAIOCB *acb = (QEDAIOCB *)blockacb;
-    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
-    bool finished = false;
-
-    /* Wait for the request to finish */
-    acb->finished = &finished;
-    while (!finished) {
-        aio_poll(aio_context, true);
-    }
-}
-
 static const AIOCBInfo qed_aiocb_info = {
     .aiocb_size         = sizeof(QEDAIOCB),
-    .cancel             = qed_aio_cancel,
 };
 
 static int bdrv_qed_probe(const uint8_t *buf, int buf_size,
@@ -648,7 +634,8 @@ static int bdrv_qed_create(const char *filename, QemuOpts *opts, Error **errp)
     char *backing_fmt = NULL;
     int ret;
 
-    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
     cluster_size = qemu_opt_get_size_del(opts,
@@ -918,18 +905,12 @@ static void qed_aio_complete_bh(void *opaque)
     BlockDriverCompletionFunc *cb = acb->common.cb;
     void *user_opaque = acb->common.opaque;
     int ret = acb->bh_ret;
-    bool *finished = acb->finished;
 
     qemu_bh_delete(acb->bh);
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 
     /* Invoke callback */
     cb(user_opaque, ret);
-
-    /* Signal cancel completion */
-    if (finished) {
-        *finished = true;
-    }
 }
 
 static void qed_aio_complete(QEDAIOCB *acb, int ret)
@@ -1396,7 +1377,6 @@ static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
                         opaque, flags);
 
     acb->flags = flags;
-    acb->finished = NULL;
     acb->qiov = qiov;
     acb->qiov_offset = 0;
     acb->cur_pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;

block/quorum.c

@@ -138,16 +138,15 @@ static void quorum_aio_cancel(BlockDriverAIOCB *blockacb)
 
     /* cancel all callbacks */
     for (i = 0; i < s->num_children; i++) {
-        bdrv_aio_cancel(acb->qcrs[i].aiocb);
+        if (acb->qcrs[i].aiocb) {
+            bdrv_aio_cancel_async(acb->qcrs[i].aiocb);
+        }
     }
-
-    g_free(acb->qcrs);
-    qemu_aio_release(acb);
 }
 
 static AIOCBInfo quorum_aiocb_info = {
     .aiocb_size         = sizeof(QuorumAIOCB),
-    .cancel             = quorum_aio_cancel,
+    .cancel_async       = quorum_aio_cancel,
 };
 
 static void quorum_aio_finalize(QuorumAIOCB *acb)
@@ -169,7 +168,7 @@ static void quorum_aio_finalize(QuorumAIOCB *acb)
     }
 
     g_free(acb->qcrs);
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 }
 
 static bool quorum_sha256_compare(QuorumVoteValue *a, QuorumVoteValue *b)

block/raw-posix.c

@@ -30,6 +30,7 @@
 #include "block/thread-pool.h"
 #include "qemu/iov.h"
 #include "raw-aio.h"
+#include "qapi/util.h"
 
 #if defined(__APPLE__) && (__MACH__)
 #include <paths.h>
@@ -1365,44 +1366,102 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
     int result = 0;
     int64_t total_size = 0;
     bool nocow = false;
+    PreallocMode prealloc;
+    char *buf = NULL;
+    Error *local_err = NULL;
 
     strstart(filename, "file:", &filename);
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     nocow = qemu_opt_get_bool(opts, BLOCK_OPT_NOCOW, false);
+    buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
+    prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
+                               PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
+                               &local_err);
+    g_free(buf);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        result = -EINVAL;
+        goto out;
+    }
 
     fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                    0644);
     if (fd < 0) {
         result = -errno;
         error_setg_errno(errp, -result, "Could not create file");
-    } else {
-        if (nocow) {
-#ifdef __linux__
-            /* Set NOCOW flag to solve performance issue on fs like btrfs.
-             * This is an optimisation. The FS_IOC_SETFLAGS ioctl return value
-             * will be ignored since any failure of this operation should not
-             * block the left work.
-             */
-            int attr;
-            if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
-                attr |= FS_NOCOW_FL;
-                ioctl(fd, FS_IOC_SETFLAGS, &attr);
-            }
-#endif
-        }
-
-        if (ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
-            result = -errno;
-            error_setg_errno(errp, -result, "Could not resize file");
-        }
-        if (qemu_close(fd) != 0) {
-            result = -errno;
-            error_setg_errno(errp, -result, "Could not close the new file");
-        }
+        goto out;
     }
+
+    if (nocow) {
+#ifdef __linux__
+        /* Set NOCOW flag to solve performance issue on fs like btrfs.
+         * This is an optimisation. The FS_IOC_SETFLAGS ioctl return value
+         * will be ignored since any failure of this operation should not
+         * block the left work.
+         */
+        int attr;
+        if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
+            attr |= FS_NOCOW_FL;
+            ioctl(fd, FS_IOC_SETFLAGS, &attr);
+        }
+#endif
+    }
+
+    if (ftruncate(fd, total_size) != 0) {
+        result = -errno;
+        error_setg_errno(errp, -result, "Could not resize file");
+        goto out_close;
+    }
+
+    switch (prealloc) {
+#ifdef CONFIG_POSIX_FALLOCATE
+    case PREALLOC_MODE_FALLOC:
+        /* posix_fallocate() doesn't set errno. */
+        result = -posix_fallocate(fd, 0, total_size);
+        if (result != 0) {
+            error_setg_errno(errp, -result,
+                             "Could not preallocate data for the new file");
+        }
+        break;
+#endif
+    case PREALLOC_MODE_FULL:
+    {
+        int64_t num = 0, left = total_size;
+        buf = g_malloc0(65536);
+
+        while (left > 0) {
+            num = MIN(left, 65536);
+            result = write(fd, buf, num);
+            if (result < 0) {
+                result = -errno;
+                error_setg_errno(errp, -result,
+                                 "Could not write to the new file");
+                break;
+            }
+            left -= num;
+        }
+        fsync(fd);
+        g_free(buf);
+        break;
+    }
+    case PREALLOC_MODE_OFF:
+        break;
+    default:
+        result = -EINVAL;
+        error_setg(errp, "Unsupported preallocation mode: %s",
+                   PreallocMode_lookup[prealloc]);
+        break;
+    }
+
+out_close:
+    if (qemu_close(fd) != 0 && result == 0) {
+        result = -errno;
+        error_setg_errno(errp, -result, "Could not close the new file");
+    }
+out:
     return result;
 }
 
@@ -1585,6 +1644,11 @@ static QemuOptsList raw_create_opts = {
             .type = QEMU_OPT_BOOL,
             .help = "Turn off copy-on-write (valid only on btrfs)"
         },
+        {
+            .name = BLOCK_OPT_PREALLOC,
+            .type = QEMU_OPT_STRING,
+            .help = "Preallocation mode (allowed values: off, falloc, full)"
+        },
         { /* end of list */ }
     }
 };
@@ -1966,8 +2030,8 @@ static int hdev_create(const char *filename, QemuOpts *opts,
     (void)has_prefix;
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     fd = qemu_open(filename, O_WRONLY | O_BINARY);
     if (fd < 0) {
@@ -1983,7 +2047,7 @@ static int hdev_create(const char *filename, QemuOpts *opts,
         error_setg(errp,
                    "The given file is neither a block nor a character device");
         ret = -ENODEV;
-    } else if (lseek(fd, 0, SEEK_END) < total_size * BDRV_SECTOR_SIZE) {
+    } else if (lseek(fd, 0, SEEK_END) < total_size) {
         error_setg(errp, "Device is too small");
         ret = -ENOSPC;
     }

block/raw-win32.c

@@ -511,8 +511,8 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
     strstart(filename, "file:", &filename);
 
     /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
 
     fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                    0644);
@@ -521,7 +521,7 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
         return -EIO;
     }
     set_sparse(fd);
-    ftruncate(fd, total_size * 512);
+    ftruncate(fd, total_size);
     qemu_close(fd);
     return 0;
 }

block/rbd.c

@@ -77,7 +77,6 @@ typedef struct RBDAIOCB {
     int64_t sector_num;
     int error;
     struct BDRVRBDState *s;
-    int cancelled;
     int status;
 } RBDAIOCB;
 
@@ -314,7 +313,8 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     /* Read out options */
-    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                     BDRV_SECTOR_SIZE);
     objsize = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE, 0);
     if (objsize) {
         if ((objsize - 1) & objsize) {    /* not a power of 2? */
@@ -407,9 +407,7 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
     acb->status = 0;
 
-    if (!acb->cancelled) {
-        qemu_aio_release(acb);
-    }
+    qemu_aio_unref(acb);
 }
 
 /* TODO Convert to fine grained options */
@@ -538,25 +536,8 @@ static void qemu_rbd_close(BlockDriverState *bs)
     rados_shutdown(s->cluster);
 }
 
-/*
- * Cancel aio. Since we don't reference acb in a non qemu threads,
- * it is safe to access it here.
- */
-static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    RBDAIOCB *acb = (RBDAIOCB *) blockacb;
-    acb->cancelled = 1;
-
-    while (acb->status == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(acb->common.bs), true);
-    }
-
-    qemu_aio_release(acb);
-}
-
 static const AIOCBInfo rbd_aiocb_info = {
     .aiocb_size = sizeof(RBDAIOCB),
-    .cancel = qemu_rbd_aio_cancel,
 };
 
 static void rbd_finish_bh(void *opaque)
@@ -639,7 +620,6 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     acb->ret = 0;
     acb->error = 0;
     acb->s = s;
-    acb->cancelled = 0;
     acb->bh = NULL;
     acb->status = -EINPROGRESS;
 
@@ -691,7 +671,7 @@ failed_completion:
 failed:
     g_free(rcb);
     qemu_vfree(acb->bounce);
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
     return NULL;
 }
 

block/sheepdog.c

@@ -315,7 +315,6 @@ struct SheepdogAIOCB {
     void (*aio_done_func)(SheepdogAIOCB *);
 
     bool cancelable;
-    bool *finished;
     int nr_pending;
 };
 
@@ -446,10 +445,7 @@ static inline void free_aio_req(BDRVSheepdogState *s, AIOReq *aio_req)
 static void coroutine_fn sd_finish_aiocb(SheepdogAIOCB *acb)
 {
     qemu_coroutine_enter(acb->coroutine, NULL);
-    if (acb->finished) {
-        *acb->finished = true;
-    }
-    qemu_aio_release(acb);
+    qemu_aio_unref(acb);
 }
 
 /*
@@ -482,36 +478,33 @@ static void sd_aio_cancel(BlockDriverAIOCB *blockacb)
     SheepdogAIOCB *acb = (SheepdogAIOCB *)blockacb;
     BDRVSheepdogState *s = acb->common.bs->opaque;
     AIOReq *aioreq, *next;
-    bool finished = false;
 
-    acb->finished = &finished;
-    while (!finished) {
-        if (sd_acb_cancelable(acb)) {
-            /* Remove outstanding requests from pending and failed queues.  */
-            QLIST_FOREACH_SAFE(aioreq, &s->pending_aio_head, aio_siblings,
-                               next) {
-                if (aioreq->aiocb == acb) {
-                    free_aio_req(s, aioreq);
-                }
+    if (sd_acb_cancelable(acb)) {
+        /* Remove outstanding requests from pending and failed queues.  */
+        QLIST_FOREACH_SAFE(aioreq, &s->pending_aio_head, aio_siblings,
+                           next) {
+            if (aioreq->aiocb == acb) {
+                free_aio_req(s, aioreq);
             }
-            QLIST_FOREACH_SAFE(aioreq, &s->failed_aio_head, aio_siblings,
-                               next) {
-                if (aioreq->aiocb == acb) {
-                    free_aio_req(s, aioreq);
-                }
-            }
-
-            assert(acb->nr_pending == 0);
-            sd_finish_aiocb(acb);
-            return;
         }
-        aio_poll(s->aio_context, true);
+        QLIST_FOREACH_SAFE(aioreq, &s->failed_aio_head, aio_siblings,
+                           next) {
+            if (aioreq->aiocb == acb) {
+                free_aio_req(s, aioreq);
+            }
+        }
+
+        assert(acb->nr_pending == 0);
+        if (acb->common.cb) {
+            acb->common.cb(acb->common.opaque, -ECANCELED);
+        }
+        sd_finish_aiocb(acb);
     }
 }
 
 static const AIOCBInfo sd_aiocb_info = {
-    .aiocb_size = sizeof(SheepdogAIOCB),
-    .cancel = sd_aio_cancel,
+    .aiocb_size     = sizeof(SheepdogAIOCB),
+    .cancel_async   = sd_aio_cancel,
 };
 
 static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
@@ -528,7 +521,6 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
 
     acb->aio_done_func = NULL;
     acb->cancelable = true;
-    acb->finished = NULL;
     acb->coroutine = qemu_coroutine_self();
     acb->ret = 0;
     acb->nr_pending = 0;
@@ -1702,7 +1694,8 @@ static int sd_create(const char *filename, QemuOpts *opts,
         goto out;
     }
 
-    s->inode.vdi_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    s->inode.vdi_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                                 BDRV_SECTOR_SIZE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
     if (!buf || !strcmp(buf, "off")) {
@@ -2137,7 +2130,7 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
 
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
-        qemu_aio_release(acb);
+        qemu_aio_unref(acb);
         return ret;
     }
 
@@ -2158,7 +2151,7 @@ static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
 
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
-        qemu_aio_release(acb);
+        qemu_aio_unref(acb);
         return ret;
     }
 
@@ -2517,7 +2510,7 @@ static coroutine_fn int sd_co_discard(BlockDriverState *bs, int64_t sector_num,
 
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
-        qemu_aio_release(acb);
+        qemu_aio_unref(acb);
         return ret;
     }
 

block/ssh.c

@@ -700,7 +700,8 @@ static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
     ssh_state_init(&s);
 
     /* Get desired file size. */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     DPRINTF("total_size=%" PRIi64, total_size);
 
     uri_options = qdict_new();

block/vdi.c

@@ -700,7 +700,8 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
     logout("\n");
 
     /* Read out options. */
-    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                     BDRV_SECTOR_SIZE);
 #if defined(CONFIG_VDI_BLOCK_SIZE)
     /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
     block_size = qemu_opt_get_size_del(opts,

block/vhdx.c

@@ -99,7 +99,8 @@ static const MSGUID logical_sector_guid = { .data1 = 0x8141bf1d,
 /* Each parent type must have a valid GUID; this is for parent images
  * of type 'VHDX'.  If we were to allow e.g. a QCOW2 parent, we would
  * need to make up our own QCOW2 GUID type */
-static const MSGUID parent_vhdx_guid = { .data1 = 0xb04aefb7,
+static const MSGUID parent_vhdx_guid __attribute__((unused))
+                                     = { .data1 = 0xb04aefb7,
                                          .data2 = 0xd19e,
                                          .data3 = 0x4a81,
                                          .data4 = { 0xb7, 0x89, 0x25, 0xb8,
@@ -1407,6 +1408,12 @@ exit:
     return ret;
 }
 
+#define VHDX_METADATA_ENTRY_BUFFER_SIZE \
+                                    (sizeof(VHDXFileParameters)               +\
+                                     sizeof(VHDXVirtualDiskSize)              +\
+                                     sizeof(VHDXPage83Data)                   +\
+                                     sizeof(VHDXVirtualDiskLogicalSectorSize) +\
+                                     sizeof(VHDXVirtualDiskPhysicalSectorSize))
 
 /*
  * Create the Metadata entries.
@@ -1445,11 +1452,7 @@ static int vhdx_create_new_metadata(BlockDriverState *bs,
     VHDXVirtualDiskLogicalSectorSize  *mt_log_sector_size;
     VHDXVirtualDiskPhysicalSectorSize *mt_phys_sector_size;
 
-    entry_buffer = g_malloc0(sizeof(VHDXFileParameters)               +
-                             sizeof(VHDXVirtualDiskSize)              +
-                             sizeof(VHDXPage83Data)                   +
-                             sizeof(VHDXVirtualDiskLogicalSectorSize) +
-                             sizeof(VHDXVirtualDiskPhysicalSectorSize));
+    entry_buffer = g_malloc0(VHDX_METADATA_ENTRY_BUFFER_SIZE);
 
     mt_file_params = entry_buffer;
     offset += sizeof(VHDXFileParameters);
@@ -1530,7 +1533,7 @@ static int vhdx_create_new_metadata(BlockDriverState *bs,
     }
 
     ret = bdrv_pwrite(bs, metadata_offset + (64 * KiB), entry_buffer,
-                      VHDX_HEADER_BLOCK_SIZE);
+                      VHDX_METADATA_ENTRY_BUFFER_SIZE);
     if (ret < 0) {
         goto exit;
     }
@@ -1593,7 +1596,7 @@ static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s,
                 bdrv_has_zero_init(bs) == 0) {
         /* for a fixed file, the default BAT entry is not zero */
         s->bat = g_try_malloc0(length);
-        if (length && s->bat != NULL) {
+        if (length && s->bat == NULL) {
             ret = -ENOMEM;
             goto exit;
         }
@@ -1725,7 +1728,6 @@ static int vhdx_create_new_region_table(BlockDriverState *bs,
         goto exit;
     }
 
-
 exit:
     g_free(s);
     g_free(buffer);
@@ -1766,7 +1768,8 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     VHDXImageType image_type;
     Error *local_err = NULL;
 
-    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0);
     block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0);
     type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
@@ -1875,7 +1878,6 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
 
-
 delete_and_exit:
     bdrv_unref(bs);
 exit:

block/vmdk.c

@@ -834,6 +834,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
             ret = vmdk_add_extent(bs, extent_file, true, sectors,
                             0, 0, 0, 0, 0, &extent, errp);
             if (ret < 0) {
+                bdrv_unref(extent_file);
                 return ret;
             }
             extent->flat_start_offset = flat_offset << 9;
@@ -845,14 +846,15 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
             } else {
                 ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf, errp);
             }
+            g_free(buf);
             if (ret) {
-                g_free(buf);
                 bdrv_unref(extent_file);
                 return ret;
             }
             extent = &s->extents[s->num_extents - 1];
         } else {
             error_setg(errp, "Unsupported extent type '%s'", type);
+            bdrv_unref(extent_file);
             return -ENOTSUP;
         }
         extent->type = g_strdup(type);
@@ -1805,7 +1807,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
         goto exit;
     }
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     adapter_type = qemu_opt_get_del(opts, BLOCK_OPT_ADAPTER_TYPE);
     backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
     if (qemu_opt_get_bool_del(opts, BLOCK_OPT_COMPAT6, false)) {

block/vpc.c

@@ -207,7 +207,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
             "incorrect.\n", bs->filename);
 
     /* Write 'checksum' back to footer, or else will leave it with zero. */
-    footer->checksum = be32_to_cpu(checksum);
+    footer->checksum = cpu_to_be32(checksum);
 
     // The visible size of a image in Virtual PC depends on the geometry
     // rather than on the size stored in the footer (the size in the footer
@@ -472,7 +472,7 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
 
     // Write BAT entry to disk
     bat_offset = s->bat_offset + (4 * index);
-    bat_value = be32_to_cpu(s->pagetable[index]);
+    bat_value = cpu_to_be32(s->pagetable[index]);
     ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4);
     if (ret < 0)
         goto fail;
@@ -489,7 +489,7 @@ static int vpc_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     BDRVVPCState *s = (BDRVVPCState *)bs->opaque;
     VHDFooter *footer = (VHDFooter *) s->footer_buf;
 
-    if (cpu_to_be32(footer->type) != VHD_FIXED) {
+    if (be32_to_cpu(footer->type) != VHD_FIXED) {
         bdi->cluster_size = s->block_size;
     }
 
@@ -506,7 +506,7 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
     int64_t sectors, sectors_per_block;
     VHDFooter *footer = (VHDFooter *) s->footer_buf;
 
-    if (cpu_to_be32(footer->type) == VHD_FIXED) {
+    if (be32_to_cpu(footer->type) == VHD_FIXED) {
         return bdrv_read(bs->file, sector_num, buf, nb_sectors);
     }
     while (nb_sectors > 0) {
@@ -555,7 +555,7 @@ static int vpc_write(BlockDriverState *bs, int64_t sector_num,
     int ret;
     VHDFooter *footer =  (VHDFooter *) s->footer_buf;
 
-    if (cpu_to_be32(footer->type) == VHD_FIXED) {
+    if (be32_to_cpu(footer->type) == VHD_FIXED) {
         return bdrv_write(bs->file, sector_num, buf, nb_sectors);
     }
     while (nb_sectors > 0) {
@@ -699,13 +699,13 @@ static int create_dynamic_disk(BlockDriverState *bs, uint8_t *buf,
      * Note: The spec is actually wrong here for data_offset, it says
      * 0xFFFFFFFF, but MS tools expect all 64 bits to be set.
      */
-    dyndisk_header->data_offset = be64_to_cpu(0xFFFFFFFFFFFFFFFFULL);
-    dyndisk_header->table_offset = be64_to_cpu(3 * 512);
-    dyndisk_header->version = be32_to_cpu(0x00010000);
-    dyndisk_header->block_size = be32_to_cpu(block_size);
-    dyndisk_header->max_table_entries = be32_to_cpu(num_bat_entries);
+    dyndisk_header->data_offset = cpu_to_be64(0xFFFFFFFFFFFFFFFFULL);
+    dyndisk_header->table_offset = cpu_to_be64(3 * 512);
+    dyndisk_header->version = cpu_to_be32(0x00010000);
+    dyndisk_header->block_size = cpu_to_be32(block_size);
+    dyndisk_header->max_table_entries = cpu_to_be32(num_bat_entries);
 
-    dyndisk_header->checksum = be32_to_cpu(vpc_checksum(buf, 1024));
+    dyndisk_header->checksum = cpu_to_be32(vpc_checksum(buf, 1024));
 
     // Write the header
     offset = 512;
@@ -757,7 +757,8 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
     BlockDriverState *bs = NULL;
 
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     disk_type_param = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
     if (disk_type_param) {
         if (!strcmp(disk_type_param, "dynamic")) {
@@ -809,36 +810,36 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
     memcpy(footer->creator_app, "qemu", 4);
     memcpy(footer->creator_os, "Wi2k", 4);
 
-    footer->features = be32_to_cpu(0x02);
-    footer->version = be32_to_cpu(0x00010000);
+    footer->features = cpu_to_be32(0x02);
+    footer->version = cpu_to_be32(0x00010000);
     if (disk_type == VHD_DYNAMIC) {
-        footer->data_offset = be64_to_cpu(HEADER_SIZE);
+        footer->data_offset = cpu_to_be64(HEADER_SIZE);
     } else {
-        footer->data_offset = be64_to_cpu(0xFFFFFFFFFFFFFFFFULL);
+        footer->data_offset = cpu_to_be64(0xFFFFFFFFFFFFFFFFULL);
     }
-    footer->timestamp = be32_to_cpu(time(NULL) - VHD_TIMESTAMP_BASE);
+    footer->timestamp = cpu_to_be32(time(NULL) - VHD_TIMESTAMP_BASE);
 
     /* Version of Virtual PC 2007 */
-    footer->major = be16_to_cpu(0x0005);
-    footer->minor = be16_to_cpu(0x0003);
+    footer->major = cpu_to_be16(0x0005);
+    footer->minor = cpu_to_be16(0x0003);
     if (disk_type == VHD_DYNAMIC) {
-        footer->orig_size = be64_to_cpu(total_sectors * 512);
-        footer->size = be64_to_cpu(total_sectors * 512);
+        footer->orig_size = cpu_to_be64(total_sectors * 512);
+        footer->size = cpu_to_be64(total_sectors * 512);
     } else {
-        footer->orig_size = be64_to_cpu(total_size);
-        footer->size = be64_to_cpu(total_size);
+        footer->orig_size = cpu_to_be64(total_size);
+        footer->size = cpu_to_be64(total_size);
     }
-    footer->cyls = be16_to_cpu(cyls);
+    footer->cyls = cpu_to_be16(cyls);
     footer->heads = heads;
     footer->secs_per_cyl = secs_per_cyl;
 
-    footer->type = be32_to_cpu(disk_type);
+    footer->type = cpu_to_be32(disk_type);
 
 #if defined(CONFIG_UUID)
     uuid_generate(footer->uuid);
 #endif
 
-    footer->checksum = be32_to_cpu(vpc_checksum(buf, HEADER_SIZE));
+    footer->checksum = cpu_to_be32(vpc_checksum(buf, HEADER_SIZE));
 
     if (disk_type == VHD_DYNAMIC) {
         ret = create_dynamic_disk(bs, buf, total_sectors);
@@ -857,7 +858,7 @@ static int vpc_has_zero_init(BlockDriverState *bs)
     BDRVVPCState *s = bs->opaque;
     VHDFooter *footer =  (VHDFooter *) s->footer_buf;
 
-    if (cpu_to_be32(footer->type) == VHD_FIXED) {
+    if (be32_to_cpu(footer->type) == VHD_FIXED) {
         return bdrv_has_zero_init(bs->file);
     } else {
         return 1;

block/win32-aio.c

@@ -88,7 +88,7 @@ static void win32_aio_process_completion(QEMUWin32AIOState *s,
 
 
     waiocb->common.cb(waiocb->common.opaque, ret);
-    qemu_aio_release(waiocb);
+    qemu_aio_unref(waiocb);
 }
 
 static void win32_aio_completion_cb(EventNotifier *e)
@@ -106,22 +106,8 @@ static void win32_aio_completion_cb(EventNotifier *e)
     }
 }
 
-static void win32_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    QEMUWin32AIOCB *waiocb = (QEMUWin32AIOCB *)blockacb;
-
-    /*
-     * CancelIoEx is only supported in Vista and newer.  For now, just
-     * wait for completion.
-     */
-    while (!HasOverlappedIoCompleted(&waiocb->ov)) {
-        aio_poll(bdrv_get_aio_context(blockacb->bs), true);
-    }
-}
-
 static const AIOCBInfo win32_aiocb_info = {
     .aiocb_size         = sizeof(QEMUWin32AIOCB),
-    .cancel             = win32_aio_cancel,
 };
 
 BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
@@ -172,7 +158,7 @@ BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
 out_dec_count:
     aio->count--;
 out:
-    qemu_aio_release(waiocb);
+    qemu_aio_unref(waiocb);
     return NULL;
 }
 

blockdev.c

@@ -39,6 +39,7 @@
 #include "qapi/qmp/types.h"
 #include "qapi-visit.h"
 #include "qapi/qmp-output-visitor.h"
+#include "qapi/util.h"
 #include "sysemu/sysemu.h"
 #include "block/block_int.h"
 #include "qmp-commands.h"
@@ -215,11 +216,17 @@ static void bdrv_format_print(void *opaque, const char *name)
 
 void drive_del(DriveInfo *dinfo)
 {
+    bdrv_unref(dinfo->bdrv);
+}
+
+void drive_info_del(DriveInfo *dinfo)
+{
+    if (!dinfo) {
+        return;
+    }
     if (dinfo->opts) {
         qemu_opts_del(dinfo->opts);
     }
-
-    bdrv_unref(dinfo->bdrv);
     g_free(dinfo->id);
     QTAILQ_REMOVE(&drives, dinfo, next);
     g_free(dinfo->serial);
@@ -274,25 +281,6 @@ static int parse_block_error_action(const char *buf, bool is_read, Error **errp)
     }
 }
 
-static inline int parse_enum_option(const char *lookup[], const char *buf,
-                                    int max, int def, Error **errp)
-{
-    int i;
-
-    if (!buf) {
-        return def;
-    }
-
-    for (i = 0; i < max; i++) {
-        if (!strcmp(buf, lookup[i])) {
-            return i;
-        }
-    }
-
-    error_setg(errp, "invalid parameter value: %s", buf);
-    return def;
-}
-
 static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
 {
     if (throttle_conflicting(cfg)) {
@@ -319,6 +307,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     int ro = 0;
     int bdrv_flags = 0;
     int on_read_error, on_write_error;
+    BlockDriverState *bs;
     DriveInfo *dinfo;
     ThrottleConfig cfg;
     int snapshot = 0;
@@ -456,11 +445,11 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     }
 
     detect_zeroes =
-        parse_enum_option(BlockdevDetectZeroesOptions_lookup,
-                          qemu_opt_get(opts, "detect-zeroes"),
-                          BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
-                          BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
-                          &error);
+        qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
+                        qemu_opt_get(opts, "detect-zeroes"),
+                        BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
+                        BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
+                        &error);
     if (error) {
         error_propagate(errp, error);
         goto early_err;
@@ -474,26 +463,27 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     }
 
     /* init */
-    dinfo = g_malloc0(sizeof(*dinfo));
-    dinfo->id = g_strdup(qemu_opts_id(opts));
-    dinfo->bdrv = bdrv_new(dinfo->id, &error);
-    if (error) {
-        error_propagate(errp, error);
-        goto bdrv_new_err;
+    bs = bdrv_new(qemu_opts_id(opts), errp);
+    if (!bs) {
+        goto early_err;
     }
-    dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
-    dinfo->bdrv->read_only = ro;
-    dinfo->bdrv->detect_zeroes = detect_zeroes;
-    QTAILQ_INSERT_TAIL(&drives, dinfo, next);
+    bs->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
+    bs->read_only = ro;
+    bs->detect_zeroes = detect_zeroes;
 
-    bdrv_set_on_error(dinfo->bdrv, on_read_error, on_write_error);
+    bdrv_set_on_error(bs, on_read_error, on_write_error);
 
     /* disk I/O throttling */
     if (throttle_enabled(&cfg)) {
-        bdrv_io_limits_enable(dinfo->bdrv);
-        bdrv_set_io_limits(dinfo->bdrv, &cfg);
+        bdrv_io_limits_enable(bs);
+        bdrv_set_io_limits(bs, &cfg);
     }
 
+    dinfo = g_malloc0(sizeof(*dinfo));
+    dinfo->id = g_strdup(qemu_opts_id(opts));
+    dinfo->bdrv = bs;
+    QTAILQ_INSERT_TAIL(&drives, dinfo, next);
+
     if (!file || !*file) {
         if (has_driver_specific_opts) {
             file = NULL;
@@ -520,7 +510,8 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     bdrv_flags |= ro ? 0 : BDRV_O_RDWR;
 
     QINCREF(bs_opts);
-    ret = bdrv_open(&dinfo->bdrv, file, NULL, bs_opts, bdrv_flags, drv, &error);
+    ret = bdrv_open(&bs, file, NULL, bs_opts, bdrv_flags, drv, &error);
+    assert(bs == dinfo->bdrv);
 
     if (ret < 0) {
         error_setg(errp, "could not open disk image %s: %s",
@@ -529,8 +520,9 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
         goto err;
     }
 
-    if (bdrv_key_required(dinfo->bdrv))
+    if (bdrv_key_required(bs)) {
         autostart = 0;
+    }
 
     QDECREF(bs_opts);
     qemu_opts_del(opts);
@@ -538,11 +530,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     return dinfo;
 
 err:
-    bdrv_unref(dinfo->bdrv);
-    QTAILQ_REMOVE(&drives, dinfo, next);
-bdrv_new_err:
-    g_free(dinfo->id);
-    g_free(dinfo);
+    bdrv_unref(bs);
 early_err:
     qemu_opts_del(opts);
 err_no_opts:
@@ -550,12 +538,18 @@ err_no_opts:
     return NULL;
 }
 
-static void qemu_opt_rename(QemuOpts *opts, const char *from, const char *to)
+static void qemu_opt_rename(QemuOpts *opts, const char *from, const char *to,
+                            Error **errp)
 {
     const char *value;
 
     value = qemu_opt_get(opts, from);
     if (value) {
+        if (qemu_opt_find(opts, to)) {
+            error_setg(errp, "'%s' and its alias '%s' can't be used at the "
+                       "same time", to, from);
+            return;
+        }
         qemu_opt_set(opts, to, value);
         qemu_opt_unset(opts, from);
     }
@@ -659,28 +653,43 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
     const char *serial;
     const char *filename;
     Error *local_err = NULL;
+    int i;
 
     /* Change legacy command line options into QMP ones */
-    qemu_opt_rename(all_opts, "iops", "throttling.iops-total");
-    qemu_opt_rename(all_opts, "iops_rd", "throttling.iops-read");
-    qemu_opt_rename(all_opts, "iops_wr", "throttling.iops-write");
+    static const struct {
+        const char *from;
+        const char *to;
+    } opt_renames[] = {
+        { "iops",           "throttling.iops-total" },
+        { "iops_rd",        "throttling.iops-read" },
+        { "iops_wr",        "throttling.iops-write" },
 
-    qemu_opt_rename(all_opts, "bps", "throttling.bps-total");
-    qemu_opt_rename(all_opts, "bps_rd", "throttling.bps-read");
-    qemu_opt_rename(all_opts, "bps_wr", "throttling.bps-write");
+        { "bps",            "throttling.bps-total" },
+        { "bps_rd",         "throttling.bps-read" },
+        { "bps_wr",         "throttling.bps-write" },
 
-    qemu_opt_rename(all_opts, "iops_max", "throttling.iops-total-max");
-    qemu_opt_rename(all_opts, "iops_rd_max", "throttling.iops-read-max");
-    qemu_opt_rename(all_opts, "iops_wr_max", "throttling.iops-write-max");
+        { "iops_max",       "throttling.iops-total-max" },
+        { "iops_rd_max",    "throttling.iops-read-max" },
+        { "iops_wr_max",    "throttling.iops-write-max" },
 
-    qemu_opt_rename(all_opts, "bps_max", "throttling.bps-total-max");
-    qemu_opt_rename(all_opts, "bps_rd_max", "throttling.bps-read-max");
-    qemu_opt_rename(all_opts, "bps_wr_max", "throttling.bps-write-max");
+        { "bps_max",        "throttling.bps-total-max" },
+        { "bps_rd_max",     "throttling.bps-read-max" },
+        { "bps_wr_max",     "throttling.bps-write-max" },
 
-    qemu_opt_rename(all_opts,
-                    "iops_size", "throttling.iops-size");
+        { "iops_size",      "throttling.iops-size" },
 
-    qemu_opt_rename(all_opts, "readonly", "read-only");
+        { "readonly",       "read-only" },
+    };
+
+    for (i = 0; i < ARRAY_SIZE(opt_renames); i++) {
+        qemu_opt_rename(all_opts, opt_renames[i].from, opt_renames[i].to,
+                        &local_err);
+        if (local_err) {
+            error_report("%s", error_get_pretty(local_err));
+            error_free(local_err);
+            return NULL;
+        }
+    }
 
     value = qemu_opt_get(all_opts, "cache");
     if (value) {
@@ -1757,6 +1766,7 @@ int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
 {
     const char *id = qdict_get_str(qdict, "id");
     BlockDriverState *bs;
+    DriveInfo *dinfo;
     AioContext *aio_context;
     Error *local_err = NULL;
 
@@ -1766,6 +1776,13 @@ int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
         return -1;
     }
 
+    dinfo = drive_get_by_blockdev(bs);
+    if (dinfo && !dinfo->enable_auto_del) {
+        error_report("Deleting device added with blockdev-add"
+                     " is not supported");
+        return -1;
+    }
+
     aio_context = bdrv_get_aio_context(bs);
     aio_context_acquire(aio_context);
 
@@ -1793,7 +1810,7 @@ int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
         bdrv_set_on_error(bs, BLOCKDEV_ON_ERROR_REPORT,
                           BLOCKDEV_ON_ERROR_REPORT);
     } else {
-        drive_del(drive_get_by_blockdev(bs));
+        drive_del(dinfo);
     }
 
     aio_context_release(aio_context);

configure

@@ -327,7 +327,6 @@ glusterfs=""
 glusterfs_discard="no"
 glusterfs_zerofill="no"
 archipelago=""
-virtio_blk_data_plane=""
 gtk=""
 gtkabi=""
 vte=""
@@ -389,6 +388,7 @@ cpp="${CPP-$cc -E}"
 objcopy="${OBJCOPY-${cross_prefix}objcopy}"
 ld="${LD-${cross_prefix}ld}"
 libtool="${LIBTOOL-${cross_prefix}libtool}"
+nm="${NM-${cross_prefix}nm}"
 strip="${STRIP-${cross_prefix}strip}"
 windres="${WINDRES-${cross_prefix}windres}"
 pkg_config_exe="${PKG_CONFIG-${cross_prefix}pkg-config}"
@@ -1092,9 +1092,8 @@ for opt do
   ;;
   --enable-archipelago) archipelago="yes"
   ;;
-  --disable-virtio-blk-data-plane) virtio_blk_data_plane="no"
-  ;;
-  --enable-virtio-blk-data-plane) virtio_blk_data_plane="yes"
+  --disable-virtio-blk-data-plane|--enable-virtio-blk-data-plane)
+      echo "$0: $opt is obsolete, virtio-blk data-plane is always on" >&2
   ;;
   --disable-gtk) gtk="no"
   ;;
@@ -1349,7 +1348,7 @@ Advanced options (experts only):
   --enable-linux-aio       enable Linux AIO support
   --disable-cap-ng         disable libcap-ng support
   --enable-cap-ng          enable libcap-ng support
-  --disable-attr           disables attr and xattr support
+  --disable-attr           disable attr and xattr support
   --enable-attr            enable attr and xattr support
   --disable-blobs          disable installing provided firmware blobs
   --enable-docs            enable documentation build
@@ -1380,7 +1379,7 @@ Advanced options (experts only):
   --with-vss-sdk=SDK-path  enable Windows VSS support in QEMU Guest Agent
   --with-win-sdk=SDK-path  path to Windows Platform SDK (to build VSS .tlb)
   --disable-seccomp        disable seccomp support
-  --enable-seccomp         enables seccomp support
+  --enable-seccomp         enable seccomp support
   --with-coroutine=BACKEND coroutine backend. Supported options:
                            gthread, ucontext, sigaltstack, windows
   --disable-coroutine-pool disable coroutine freelist (worse performance)
@@ -1395,7 +1394,7 @@ Advanced options (experts only):
   --enable-tpm             enable TPM support
   --disable-libssh2        disable ssh block device support
   --enable-libssh2         enable ssh block device support
-  --disable-vhdx           disables support for the Microsoft VHDX image format
+  --disable-vhdx           disable support for the Microsoft VHDX image format
   --enable-vhdx            enable support for the Microsoft VHDX image format
   --disable-quorum         disable quorum block filter support
   --enable-quorum          enable quorum block filter support
@@ -2716,6 +2715,12 @@ for i in $glib_modules; do
     fi
 done
 
+# g_test_trap_subprocess added in 2.38. Used by some tests.
+glib_subprocess=yes
+if ! $pkg_config --atleast-version=2.38 glib-2.0; then
+    glib_subprocess=no
+fi
+
 ##########################################
 # SHA command probe for modules
 if test "$modules" = yes; then
@@ -2737,7 +2742,7 @@ fi
 if test "$pixman" = ""; then
   if test "$want_tools" = "no" -a "$softmmu" = "no"; then
     pixman="none"
-  elif $pkg_config pixman-1 > /dev/null 2>&1; then
+  elif $pkg_config --atleast-version=0.21.8 pixman-1 > /dev/null 2>&1; then
     pixman="system"
   else
     pixman="internal"
@@ -2753,11 +2758,12 @@ if test "$pixman" = "none"; then
   pixman_cflags=
   pixman_libs=
 elif test "$pixman" = "system"; then
+  # pixman version has been checked above
   pixman_cflags=`$pkg_config --cflags pixman-1`
   pixman_libs=`$pkg_config --libs pixman-1`
 else
   if test ! -d ${source_path}/pixman/pixman; then
-    error_exit "pixman not present. Your options:" \
+    error_exit "pixman >= 0.21.8 not present. Your options:" \
         "  (1) Preferred: Install the pixman devel package (any recent" \
         "      distro should have packages as Xorg needs pixman too)." \
         "  (2) Fetch the pixman submodule, using:" \
@@ -2935,16 +2941,6 @@ else
   tpm_passthrough=no
 fi
 
-##########################################
-# adjust virtio-blk-data-plane based on linux-aio
-
-if test "$virtio_blk_data_plane" = "yes" -a \
-	"$linux_aio" != "yes" ; then
-  error_exit "virtio-blk-data-plane requires Linux AIO, please try --enable-linux-aio"
-elif test -z "$virtio_blk_data_plane" ; then
-  virtio_blk_data_plane=$linux_aio
-fi
-
 ##########################################
 # attr probe
 
@@ -3312,6 +3308,21 @@ if compile_prog "" "" ; then
   fallocate_punch_hole=yes
 fi
 
+# check for posix_fallocate
+posix_fallocate=no
+cat > $TMPC << EOF
+#include <fcntl.h>
+
+int main(void)
+{
+    posix_fallocate(0, 0, 0);
+    return 0;
+}
+EOF
+if compile_prog "" "" ; then
+    posix_fallocate=yes
+fi
+
 # check for sync_file_range
 sync_file_range=no
 cat > $TMPC << EOF
@@ -3960,12 +3971,11 @@ else
 fi
 
 ########################################
-# check if we have valgrind/valgrind.h and valgrind/memcheck.h
+# check if we have valgrind/valgrind.h
 
 valgrind_h=no
 cat > $TMPC << EOF
 #include <valgrind/valgrind.h>
-#include <valgrind/memcheck.h>
 int main(void) {
   return 0;
 }
@@ -4319,7 +4329,6 @@ echo "coroutine backend $coroutine"
 echo "coroutine pool    $coroutine_pool"
 echo "GlusterFS support $glusterfs"
 echo "Archipelago support $archipelago"
-echo "virtio-blk-data-plane $virtio_blk_data_plane"
 echo "gcov              $gcov_tool"
 echo "gcov enabled      $gcov"
 echo "TPM support       $tpm"
@@ -4528,6 +4537,9 @@ fi
 if test "$fallocate_punch_hole" = "yes" ; then
   echo "CONFIG_FALLOCATE_PUNCH_HOLE=y" >> $config_host_mak
 fi
+if test "$posix_fallocate" = "yes" ; then
+  echo "CONFIG_POSIX_FALLOCATE=y" >> $config_host_mak
+fi
 if test "$sync_file_range" = "yes" ; then
   echo "CONFIG_SYNC_FILE_RANGE=y" >> $config_host_mak
 fi
@@ -4585,6 +4597,9 @@ if test "$bluez" = "yes" ; then
   echo "CONFIG_BLUEZ=y" >> $config_host_mak
   echo "BLUEZ_CFLAGS=$bluez_cflags" >> $config_host_mak
 fi
+if test "glib_subprocess" = "yes" ; then
+  echo "CONFIG_HAS_GLIB_SUBPROCESS_TESTS=y" >> $config_host_mak
+fi
 echo "GLIB_CFLAGS=$glib_cflags" >> $config_host_mak
 if test "$gtk" = "yes" ; then
   echo "CONFIG_GTK=y" >> $config_host_mak
@@ -4778,10 +4793,6 @@ if test "$quorum" = "yes" ; then
   echo "CONFIG_QUORUM=y" >> $config_host_mak
 fi
 
-if test "$virtio_blk_data_plane" = "yes" ; then
-  echo 'CONFIG_VIRTIO_BLK_DATA_PLANE=$(CONFIG_VIRTIO)' >> $config_host_mak
-fi
-
 if test "$vhdx" = "yes" ; then
   echo "CONFIG_VHDX=y" >> $config_host_mak
 fi
@@ -4888,6 +4899,7 @@ echo "AS=$as" >> $config_host_mak
 echo "CPP=$cpp" >> $config_host_mak
 echo "OBJCOPY=$objcopy" >> $config_host_mak
 echo "LD=$ld" >> $config_host_mak
+echo "NM=$nm" >> $config_host_mak
 echo "WINDRES=$windres" >> $config_host_mak
 echo "LIBTOOL=$libtool" >> $config_host_mak
 echo "CFLAGS=$CFLAGS" >> $config_host_mak
@@ -5016,7 +5028,7 @@ case "$target_name" in
   aarch64)
     TARGET_BASE_ARCH=arm
     bflt="yes"
-    gdb_xml_files="aarch64-core.xml aarch64-fpu.xml"
+    gdb_xml_files="aarch64-core.xml aarch64-fpu.xml arm-core.xml arm-vfp.xml arm-vfp3.xml arm-neon.xml"
   ;;
   cris)
   ;;

cpu-exec.c

@@ -295,16 +295,10 @@ static inline TranslationBlock *tb_find_fast(CPUArchState *env)
     return tb;
 }
 
-static CPUDebugExcpHandler *debug_excp_handler;
-
-void cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)
-{
-    debug_excp_handler = handler;
-}
-
 static void cpu_handle_debug_exception(CPUArchState *env)
 {
     CPUState *cpu = ENV_GET_CPU(env);
+    CPUClass *cc = CPU_GET_CLASS(cpu);
     CPUWatchpoint *wp;
 
     if (!cpu->watchpoint_hit) {
@@ -312,9 +306,8 @@ static void cpu_handle_debug_exception(CPUArchState *env)
             wp->flags &= ~BP_WATCHPOINT_HIT;
         }
     }
-    if (debug_excp_handler) {
-        debug_excp_handler(env);
-    }
+
+    cc->debug_excp_handler(cpu);
 }
 
 /* main execution loop */
@@ -324,10 +317,7 @@ volatile sig_atomic_t exit_request;
 int cpu_exec(CPUArchState *env)
 {
     CPUState *cpu = ENV_GET_CPU(env);
-#if !(defined(CONFIG_USER_ONLY) && \
-      (defined(TARGET_M68K) || defined(TARGET_PPC) || defined(TARGET_S390X)))
     CPUClass *cc = CPU_GET_CLASS(cpu);
-#endif
 #ifdef TARGET_I386
     X86CPU *x86_cpu = X86_CPU(cpu);
 #endif
@@ -362,36 +352,7 @@ int cpu_exec(CPUArchState *env)
         cpu->exit_request = 1;
     }
 
-#if defined(TARGET_I386)
-    /* put eflags in CPU temporary format */
-    CC_SRC = env->eflags & (CC_O | CC_S | CC_Z | CC_A | CC_P | CC_C);
-    env->df = 1 - (2 * ((env->eflags >> 10) & 1));
-    CC_OP = CC_OP_EFLAGS;
-    env->eflags &= ~(DF_MASK | CC_O | CC_S | CC_Z | CC_A | CC_P | CC_C);
-#elif defined(TARGET_SPARC)
-#elif defined(TARGET_M68K)
-    env->cc_op = CC_OP_FLAGS;
-    env->cc_dest = env->sr & 0xf;
-    env->cc_x = (env->sr >> 4) & 1;
-#elif defined(TARGET_ALPHA)
-#elif defined(TARGET_ARM)
-#elif defined(TARGET_UNICORE32)
-#elif defined(TARGET_PPC)
-    env->reserve_addr = -1;
-#elif defined(TARGET_LM32)
-#elif defined(TARGET_MICROBLAZE)
-#elif defined(TARGET_MIPS)
-#elif defined(TARGET_MOXIE)
-#elif defined(TARGET_OPENRISC)
-#elif defined(TARGET_SH4)
-#elif defined(TARGET_CRIS)
-#elif defined(TARGET_S390X)
-#elif defined(TARGET_XTENSA)
-#elif defined(TARGET_TRICORE)
-    /* XXXXX */
-#else
-#error unsupported target CPU
-#endif
+    cc->cpu_exec_enter(cpu);
     cpu->exception_index = -1;
 
     /* Calculate difference between guest clock and host clock.
@@ -443,17 +404,12 @@ int cpu_exec(CPUArchState *env)
                         cpu->exception_index = EXCP_DEBUG;
                         cpu_loop_exit(cpu);
                     }
-#if defined(TARGET_ARM) || defined(TARGET_SPARC) || defined(TARGET_MIPS) || \
-    defined(TARGET_PPC) || defined(TARGET_ALPHA) || defined(TARGET_CRIS) || \
-    defined(TARGET_MICROBLAZE) || defined(TARGET_LM32) ||                   \
-    defined(TARGET_UNICORE32) || defined(TARGET_TRICORE)
                     if (interrupt_request & CPU_INTERRUPT_HALT) {
                         cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
                         cpu->halted = 1;
                         cpu->exception_index = EXCP_HLT;
                         cpu_loop_exit(cpu);
                     }
-#endif
 #if defined(TARGET_I386)
                     if (interrupt_request & CPU_INTERRUPT_INIT) {
                         cpu_svm_check_intercept_param(env, SVM_EXIT_INIT, 0);
@@ -466,257 +422,15 @@ int cpu_exec(CPUArchState *env)
                         cpu_reset(cpu);
                     }
 #endif
-#if defined(TARGET_I386)
-#if !defined(CONFIG_USER_ONLY)
-                    if (interrupt_request & CPU_INTERRUPT_POLL) {
-                        cpu->interrupt_request &= ~CPU_INTERRUPT_POLL;
-                        apic_poll_irq(x86_cpu->apic_state);
-                    }
-#endif
-                    if (interrupt_request & CPU_INTERRUPT_SIPI) {
-                            do_cpu_sipi(x86_cpu);
-                    } else if (env->hflags2 & HF2_GIF_MASK) {
-                        if ((interrupt_request & CPU_INTERRUPT_SMI) &&
-                            !(env->hflags & HF_SMM_MASK)) {
-                            cpu_svm_check_intercept_param(env, SVM_EXIT_SMI,
-                                                          0);
-                            cpu->interrupt_request &= ~CPU_INTERRUPT_SMI;
-                            do_smm_enter(x86_cpu);
-                            next_tb = 0;
-                        } else if ((interrupt_request & CPU_INTERRUPT_NMI) &&
-                                   !(env->hflags2 & HF2_NMI_MASK)) {
-                            cpu->interrupt_request &= ~CPU_INTERRUPT_NMI;
-                            env->hflags2 |= HF2_NMI_MASK;
-                            do_interrupt_x86_hardirq(env, EXCP02_NMI, 1);
-                            next_tb = 0;
-                        } else if (interrupt_request & CPU_INTERRUPT_MCE) {
-                            cpu->interrupt_request &= ~CPU_INTERRUPT_MCE;
-                            do_interrupt_x86_hardirq(env, EXCP12_MCHK, 0);
-                            next_tb = 0;
-                        } else if ((interrupt_request & CPU_INTERRUPT_HARD) &&
-                                   (((env->hflags2 & HF2_VINTR_MASK) && 
-                                     (env->hflags2 & HF2_HIF_MASK)) ||
-                                    (!(env->hflags2 & HF2_VINTR_MASK) && 
-                                     (env->eflags & IF_MASK && 
-                                      !(env->hflags & HF_INHIBIT_IRQ_MASK))))) {
-                            int intno;
-                            cpu_svm_check_intercept_param(env, SVM_EXIT_INTR,
-                                                          0);
-                            cpu->interrupt_request &= ~(CPU_INTERRUPT_HARD |
-                                                        CPU_INTERRUPT_VIRQ);
-                            intno = cpu_get_pic_interrupt(env);
-                            qemu_log_mask(CPU_LOG_TB_IN_ASM, "Servicing hardware INT=0x%02x\n", intno);
-                            do_interrupt_x86_hardirq(env, intno, 1);
-                            /* ensure that no TB jump will be modified as
-                               the program flow was changed */
-                            next_tb = 0;
-#if !defined(CONFIG_USER_ONLY)
-                        } else if ((interrupt_request & CPU_INTERRUPT_VIRQ) &&
-                                   (env->eflags & IF_MASK) && 
-                                   !(env->hflags & HF_INHIBIT_IRQ_MASK)) {
-                            int intno;
-                            /* FIXME: this should respect TPR */
-                            cpu_svm_check_intercept_param(env, SVM_EXIT_VINTR,
-                                                          0);
-                            intno = ldl_phys(cpu->as,
-                                             env->vm_vmcb
-                                             + offsetof(struct vmcb,
-                                                        control.int_vector));
-                            qemu_log_mask(CPU_LOG_TB_IN_ASM, "Servicing virtual hardware INT=0x%02x\n", intno);
-                            do_interrupt_x86_hardirq(env, intno, 1);
-                            cpu->interrupt_request &= ~CPU_INTERRUPT_VIRQ;
-                            next_tb = 0;
-#endif
-                        }
-                    }
-#elif defined(TARGET_PPC)
-                    if (interrupt_request & CPU_INTERRUPT_HARD) {
-                        ppc_hw_interrupt(env);
-                        if (env->pending_interrupts == 0) {
-                            cpu->interrupt_request &= ~CPU_INTERRUPT_HARD;
-                        }
+                    /* The target hook has 3 exit conditions:
+                       False when the interrupt isn't processed,
+                       True when it is, and we should restart on a new TB,
+                       and via longjmp via cpu_loop_exit.  */
+                    if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
                         next_tb = 0;
                     }
-#elif defined(TARGET_LM32)
-                    if ((interrupt_request & CPU_INTERRUPT_HARD)
-                        && (env->ie & IE_IE)) {
-                        cpu->exception_index = EXCP_IRQ;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_MICROBLAZE)
-                    if ((interrupt_request & CPU_INTERRUPT_HARD)
-                        && (env->sregs[SR_MSR] & MSR_IE)
-                        && !(env->sregs[SR_MSR] & (MSR_EIP | MSR_BIP))
-                        && !(env->iflags & (D_FLAG | IMM_FLAG))) {
-                        cpu->exception_index = EXCP_IRQ;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_MIPS)
-                    if ((interrupt_request & CPU_INTERRUPT_HARD) &&
-                        cpu_mips_hw_interrupts_pending(env)) {
-                        /* Raise it */
-                        cpu->exception_index = EXCP_EXT_INTERRUPT;
-                        env->error_code = 0;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_TRICORE)
-                    if ((interrupt_request & CPU_INTERRUPT_HARD)) {
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-
-#elif defined(TARGET_OPENRISC)
-                    {
-                        int idx = -1;
-                        if ((interrupt_request & CPU_INTERRUPT_HARD)
-                            && (env->sr & SR_IEE)) {
-                            idx = EXCP_INT;
-                        }
-                        if ((interrupt_request & CPU_INTERRUPT_TIMER)
-                            && (env->sr & SR_TEE)) {
-                            idx = EXCP_TICK;
-                        }
-                        if (idx >= 0) {
-                            cpu->exception_index = idx;
-                            cc->do_interrupt(cpu);
-                            next_tb = 0;
-                        }
-                    }
-#elif defined(TARGET_SPARC)
-                    if (interrupt_request & CPU_INTERRUPT_HARD) {
-                        if (cpu_interrupts_enabled(env) &&
-                            env->interrupt_index > 0) {
-                            int pil = env->interrupt_index & 0xf;
-                            int type = env->interrupt_index & 0xf0;
-
-                            if (((type == TT_EXTINT) &&
-                                  cpu_pil_allowed(env, pil)) ||
-                                  type != TT_EXTINT) {
-                                cpu->exception_index = env->interrupt_index;
-                                cc->do_interrupt(cpu);
-                                next_tb = 0;
-                            }
-                        }
-                    }
-#elif defined(TARGET_ARM)
-                    if (interrupt_request & CPU_INTERRUPT_FIQ
-                        && !(env->daif & PSTATE_F)) {
-                        cpu->exception_index = EXCP_FIQ;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-                    /* ARMv7-M interrupt return works by loading a magic value
-                       into the PC.  On real hardware the load causes the
-                       return to occur.  The qemu implementation performs the
-                       jump normally, then does the exception return when the
-                       CPU tries to execute code at the magic address.
-                       This will cause the magic PC value to be pushed to
-                       the stack if an interrupt occurred at the wrong time.
-                       We avoid this by disabling interrupts when
-                       pc contains a magic address.  */
-                    if (interrupt_request & CPU_INTERRUPT_HARD
-                        && ((IS_M(env) && env->regs[15] < 0xfffffff0)
-                            || !(env->daif & PSTATE_I))) {
-                        cpu->exception_index = EXCP_IRQ;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_UNICORE32)
-                    if (interrupt_request & CPU_INTERRUPT_HARD
-                        && !(env->uncached_asr & ASR_I)) {
-                        cpu->exception_index = UC32_EXCP_INTR;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_SH4)
-                    if (interrupt_request & CPU_INTERRUPT_HARD) {
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_ALPHA)
-                    {
-                        int idx = -1;
-                        /* ??? This hard-codes the OSF/1 interrupt levels.  */
-                        switch (env->pal_mode ? 7 : env->ps & PS_INT_MASK) {
-                        case 0 ... 3:
-                            if (interrupt_request & CPU_INTERRUPT_HARD) {
-                                idx = EXCP_DEV_INTERRUPT;
-                            }
-                            /* FALLTHRU */
-                        case 4:
-                            if (interrupt_request & CPU_INTERRUPT_TIMER) {
-                                idx = EXCP_CLK_INTERRUPT;
-                            }
-                            /* FALLTHRU */
-                        case 5:
-                            if (interrupt_request & CPU_INTERRUPT_SMP) {
-                                idx = EXCP_SMP_INTERRUPT;
-                            }
-                            /* FALLTHRU */
-                        case 6:
-                            if (interrupt_request & CPU_INTERRUPT_MCHK) {
-                                idx = EXCP_MCHK;
-                            }
-                        }
-                        if (idx >= 0) {
-                            cpu->exception_index = idx;
-                            env->error_code = 0;
-                            cc->do_interrupt(cpu);
-                            next_tb = 0;
-                        }
-                    }
-#elif defined(TARGET_CRIS)
-                    if (interrupt_request & CPU_INTERRUPT_HARD
-                        && (env->pregs[PR_CCS] & I_FLAG)
-                        && !env->locked_irq) {
-                        cpu->exception_index = EXCP_IRQ;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-                    if (interrupt_request & CPU_INTERRUPT_NMI) {
-                        unsigned int m_flag_archval;
-                        if (env->pregs[PR_VR] < 32) {
-                            m_flag_archval = M_FLAG_V10;
-                        } else {
-                            m_flag_archval = M_FLAG_V32;
-                        }
-                        if ((env->pregs[PR_CCS] & m_flag_archval)) {
-                            cpu->exception_index = EXCP_NMI;
-                            cc->do_interrupt(cpu);
-                            next_tb = 0;
-                        }
-                    }
-#elif defined(TARGET_M68K)
-                    if (interrupt_request & CPU_INTERRUPT_HARD
-                        && ((env->sr & SR_I) >> SR_I_SHIFT)
-                            < env->pending_level) {
-                        /* Real hardware gets the interrupt vector via an
-                           IACK cycle at this point.  Current emulated
-                           hardware doesn't rely on this, so we
-                           provide/save the vector when the interrupt is
-                           first signalled.  */
-                        cpu->exception_index = env->pending_vector;
-                        do_interrupt_m68k_hardirq(env);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_S390X) && !defined(CONFIG_USER_ONLY)
-                    if ((interrupt_request & CPU_INTERRUPT_HARD) &&
-                        (env->psw.mask & PSW_MASK_EXT)) {
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#elif defined(TARGET_XTENSA)
-                    if (interrupt_request & CPU_INTERRUPT_HARD) {
-                        cpu->exception_index = EXC_IRQ;
-                        cc->do_interrupt(cpu);
-                        next_tb = 0;
-                    }
-#endif
-                   /* Don't use the cached interrupt_request value,
-                      do_interrupt may have updated the EXITTB flag. */
+                    /* Don't use the cached interrupt_request value,
+                       do_interrupt may have updated the EXITTB flag. */
                     if (cpu->interrupt_request & CPU_INTERRUPT_EXITTB) {
                         cpu->interrupt_request &= ~CPU_INTERRUPT_EXITTB;
                         /* ensure that no TB jump will be modified as
@@ -822,10 +536,7 @@ int cpu_exec(CPUArchState *env)
              * local variables as longjmp is marked 'noreturn'. */
             cpu = current_cpu;
             env = cpu->env_ptr;
-#if !(defined(CONFIG_USER_ONLY) && \
-      (defined(TARGET_M68K) || defined(TARGET_PPC) || defined(TARGET_S390X)))
             cc = CPU_GET_CLASS(cpu);
-#endif
 #ifdef TARGET_I386
             x86_cpu = X86_CPU(cpu);
 #endif
@@ -836,36 +547,7 @@ int cpu_exec(CPUArchState *env)
         }
     } /* for(;;) */
 
-
-#if defined(TARGET_I386)
-    /* restore flags in standard format */
-    env->eflags = env->eflags | cpu_cc_compute_all(env, CC_OP)
-        | (env->df & DF_MASK);
-#elif defined(TARGET_ARM)
-    /* XXX: Save/restore host fpu exception state?.  */
-#elif defined(TARGET_UNICORE32)
-#elif defined(TARGET_SPARC)
-#elif defined(TARGET_PPC)
-#elif defined(TARGET_LM32)
-#elif defined(TARGET_M68K)
-    cpu_m68k_flush_flags(env, env->cc_op);
-    env->cc_op = CC_OP_FLAGS;
-    env->sr = (env->sr & 0xffe0)
-              | env->cc_dest | (env->cc_x << 4);
-#elif defined(TARGET_MICROBLAZE)
-#elif defined(TARGET_MIPS)
-#elif defined(TARGET_TRICORE)
-#elif defined(TARGET_MOXIE)
-#elif defined(TARGET_OPENRISC)
-#elif defined(TARGET_SH4)
-#elif defined(TARGET_ALPHA)
-#elif defined(TARGET_CRIS)
-#elif defined(TARGET_S390X)
-#elif defined(TARGET_XTENSA)
-    /* XXXXX */
-#else
-#error unsupported target CPU
-#endif
+    cc->cpu_exec_exit(cpu);
 
     /* fail safe : never use current_cpu outside cpu_exec() */
     current_cpu = NULL;

cpus.c

@@ -493,13 +493,17 @@ static const VMStateDescription vmstate_timers = {
     }
 };
 
+void cpu_ticks_init(void)
+{
+    seqlock_init(&timers_state.vm_clock_seqlock, NULL);
+    vmstate_register(NULL, 0, &vmstate_timers, &timers_state);
+}
+
 void configure_icount(QemuOpts *opts, Error **errp)
 {
     const char *option;
     char *rem_str = NULL;
 
-    seqlock_init(&timers_state.vm_clock_seqlock, NULL);
-    vmstate_register(NULL, 0, &vmstate_timers, &timers_state);
     option = qemu_opt_get(opts, "shift");
     if (!option) {
         if (qemu_opt_get(opts, "align") != NULL) {
@@ -589,6 +593,15 @@ void cpu_synchronize_all_post_init(void)
     }
 }
 
+void cpu_clean_all_dirty(void)
+{
+    CPUState *cpu;
+
+    CPU_FOREACH(cpu) {
+        cpu_clean_state(cpu);
+    }
+}
+
 static int do_vm_stop(RunState state)
 {
     int ret = 0;

default-configs/ppc-softmmu.mak

@@ -45,8 +45,8 @@ CONFIG_PREP=y
 CONFIG_MAC=y
 CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
+CONFIG_ETSEC=y
+CONFIG_LIBDECNUMBER=y
 # For PReP
 CONFIG_MC146818RTC=y
-CONFIG_ETSEC=y
 CONFIG_ISA_TESTDEV=y
-CONFIG_LIBDECNUMBER=y

default-configs/ppc64-softmmu.mak

@@ -46,6 +46,8 @@ CONFIG_PREP=y
 CONFIG_MAC=y
 CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
+CONFIG_ETSEC=y
+CONFIG_LIBDECNUMBER=y
 # For pSeries
 CONFIG_XICS=$(CONFIG_PSERIES)
 CONFIG_XICS_KVM=$(and $(CONFIG_PSERIES),$(CONFIG_KVM))
@@ -58,4 +60,3 @@ CONFIG_I82374=y
 CONFIG_I8257=y
 CONFIG_MC146818RTC=y
 CONFIG_ISA_TESTDEV=y
-CONFIG_LIBDECNUMBER=y

dma-helpers.c

@@ -73,7 +73,6 @@ typedef struct {
     QEMUSGList *sg;
     uint64_t sector_num;
     DMADirection dir;
-    bool in_cancel;
     int sg_cur_index;
     dma_addr_t sg_cur_byte;
     QEMUIOVector iov;
@@ -125,12 +124,7 @@ static void dma_complete(DMAAIOCB *dbs, int ret)
         qemu_bh_delete(dbs->bh);
         dbs->bh = NULL;
     }
-    if (!dbs->in_cancel) {
-        /* Requests may complete while dma_aio_cancel is in progress.  In
-         * this case, the AIOCB should not be released because it is still
-         * referenced by dma_aio_cancel.  */
-        qemu_aio_release(dbs);
-    }
+    qemu_aio_unref(dbs);
 }
 
 static void dma_bdrv_cb(void *opaque, int ret)
@@ -186,19 +180,14 @@ static void dma_aio_cancel(BlockDriverAIOCB *acb)
     trace_dma_aio_cancel(dbs);
 
     if (dbs->acb) {
-        BlockDriverAIOCB *acb = dbs->acb;
-        dbs->acb = NULL;
-        dbs->in_cancel = true;
-        bdrv_aio_cancel(acb);
-        dbs->in_cancel = false;
+        bdrv_aio_cancel_async(dbs->acb);
     }
-    dbs->common.cb = NULL;
-    dma_complete(dbs, 0);
 }
 
+
 static const AIOCBInfo dma_aiocb_info = {
     .aiocb_size         = sizeof(DMAAIOCB),
-    .cancel             = dma_aio_cancel,
+    .cancel_async       = dma_aio_cancel,
 };
 
 BlockDriverAIOCB *dma_bdrv_io(
@@ -217,7 +206,6 @@ BlockDriverAIOCB *dma_bdrv_io(
     dbs->sg_cur_index = 0;
     dbs->sg_cur_byte = 0;
     dbs->dir = dir;
-    dbs->in_cancel = false;
     dbs->io_func = io_func;
     dbs->bh = NULL;
     qemu_iovec_init(&dbs->iov, sg->nsg);
@@ -277,5 +265,5 @@ uint64_t dma_buf_write(uint8_t *ptr, int32_t len, QEMUSGList *sg)
 void dma_acct_start(BlockDriverState *bs, BlockAcctCookie *cookie,
                     QEMUSGList *sg, enum BlockAcctType type)
 {
-    bdrv_acct_start(bs, cookie, sg->size, type);
+    block_acct_start(bdrv_get_stats(bs), cookie, sg->size, type);
 }

docs/blkdebug.txt

@@ -0,0 +1,161 @@
+Block I/O error injection using blkdebug
+----------------------------------------
+Copyright (C) 2014 Red Hat Inc
+
+This work is licensed under the terms of the GNU GPL, version 2 or later.  See
+the COPYING file in the top-level directory.
+
+The blkdebug block driver is a rule-based error injection engine.  It can be
+used to exercise error code paths in block drivers including ENOSPC (out of
+space) and EIO.
+
+This document gives an overview of the features available in blkdebug.
+
+Background
+----------
+Block drivers have many error code paths that handle I/O errors.  Image formats
+are especially complex since metadata I/O errors during cluster allocation or
+while updating tables happen halfway through request processing and require
+discipline to keep image files consistent.
+
+Error injection allows test cases to trigger I/O errors at specific points.
+This way, all error paths can be tested to make sure they are correct.
+
+Rules
+-----
+The blkdebug block driver takes a list of "rules" that tell the error injection
+engine when to fail an I/O request.
+
+Each I/O request is evaluated against the rules.  If a rule matches the request
+then its "action" is executed.
+
+Rules can be placed in a configuration file; the configuration file
+follows the same .ini-like format used by QEMU's -readconfig option, and
+each section of the file represents a rule.
+
+The following configuration file defines a single rule:
+
+  $ cat blkdebug.conf
+  [inject-error]
+  event = "read_aio"
+  errno = "28"
+
+This rule fails all aio read requests with ENOSPC (28).  Note that the errno
+value depends on the host.  On Linux, see
+/usr/include/asm-generic/errno-base.h for errno values.
+
+Invoke QEMU as follows:
+
+  $ qemu-system-x86_64
+        -drive if=none,cache=none,file=blkdebug:blkdebug.conf:test.img,id=drive0 \
+        -device virtio-blk-pci,drive=drive0,id=virtio-blk-pci0
+
+Rules support the following attributes:
+
+  event - which type of operation to match (e.g. read_aio, write_aio,
+          flush_to_os, flush_to_disk).  See the "Events" section for
+          information on events.
+
+  state - (optional) the engine must be in this state number in order for this
+          rule to match.  See the "State transitions" section for information
+          on states.
+
+  errno - the numeric errno value to return when a request matches this rule.
+          The errno values depend on the host since the numeric values are not
+          standarized in the POSIX specification.
+
+  sector - (optional) a sector number that the request must overlap in order to
+           match this rule
+
+  once - (optional, default "off") only execute this action on the first
+         matching request
+
+  immediately - (optional, default "off") return a NULL BlockDriverAIOCB
+                pointer and fail without an errno instead.  This exercises the
+                code path where BlockDriverAIOCB fails and the caller's
+                BlockDriverCompletionFunc is not invoked.
+
+Events
+------
+Block drivers provide information about the type of I/O request they are about
+to make so rules can match specific types of requests.  For example, the qcow2
+block driver tells blkdebug when it accesses the L1 table so rules can match
+only L1 table accesses and not other metadata or guest data requests.
+
+The core events are:
+
+  read_aio - guest data read
+
+  write_aio - guest data write
+
+  flush_to_os - write out unwritten block driver state (e.g. cached metadata)
+
+  flush_to_disk - flush the host block device's disk cache
+
+See block/blkdebug.c:event_names[] for the full list of events.  You may need
+to grep block driver source code to understand the meaning of specific events.
+
+State transitions
+-----------------
+There are cases where more power is needed to match a particular I/O request in
+a longer sequence of requests.  For example:
+
+  write_aio
+  flush_to_disk
+  write_aio
+
+How do we match the 2nd write_aio but not the first?  This is where state
+transitions come in.
+
+The error injection engine has an integer called the "state" that always starts
+initialized to 1.  The state integer is internal to blkdebug and cannot be
+observed from outside but rules can interact with it for powerful matching
+behavior.
+
+Rules can be conditional on the current state and they can transition to a new
+state.
+
+When a rule's "state" attribute is non-zero then the current state must equal
+the attribute in order for the rule to match.
+
+For example, to match the 2nd write_aio:
+
+  [set-state]
+  event = "write_aio"
+  state = "1"
+  new_state = "2"
+
+  [inject-error]
+  event = "write_aio"
+  state = "2"
+  errno = "5"
+
+The first write_aio request matches the set-state rule and transitions from
+state 1 to state 2.  Once state 2 has been entered, the set-state rule no
+longer matches since it requires state 1.  But the inject-error rule now
+matches the next write_aio request and injects EIO (5).
+
+State transition rules support the following attributes:
+
+  event - which type of operation to match (e.g. read_aio, write_aio,
+          flush_to_os, flush_to_disk).  See the "Events" section for
+          information on events.
+
+  state - (optional) the engine must be in this state number in order for this
+          rule to match
+
+  new_state - transition to this state number
+
+Suspend and resume
+------------------
+Exercising code paths in block drivers may require specific ordering amongst
+concurrent requests.  The "breakpoint" feature allows requests to be halted on
+a blkdebug event and resumed later.  This makes it possible to achieve
+deterministic ordering when multiple requests are in flight.
+
+Breakpoints on blkdebug events are associated with a user-defined "tag" string.
+This tag serves as an identifier by which the request can be resumed at a later
+point.
+
+See the qemu-io(1) break, resume, remove_break, and wait_break commands for
+details.

docs/image-fuzzer.txt

@@ -125,7 +125,8 @@ If a fuzzer configuration is specified, then it has the next interpretation:
     will be always fuzzed for every test. This case is useful for regression
     testing.
 
-For now only header fields, header extensions and L1/L2 tables are generated.
+The generator can create header fields, header extensions, L1/L2 tables and
+refcount table and blocks.
 
 Module interfaces
 -----------------

docs/qapi-code-gen.txt

@@ -1,10 +1,5 @@
 = How to use the QAPI code generator =
 
-* Note: as of this writing, QMP does not use QAPI. Eventually QMP
-commands will be converted to use QAPI internally. The following
-information describes QMP/QAPI as it will exist after the
-conversion.
-
 QAPI is a native C API within QEMU which provides management-level
 functionality to internal/external users. For external
 users/processes, this interface is made available by a JSON-based
@@ -19,7 +14,7 @@ marshaling/dispatch code for the guest agent server running in the
 guest.
 
 This document will describe how the schemas, scripts, and resulting
-code is used.
+code are used.
 
 
 == QMP/Guest agent schema ==
@@ -234,6 +229,7 @@ Resulting in this JSON object:
   "data": { "b": "test string" },
   "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
 
+
 == Code generation ==
 
 Schemas are fed into 3 scripts to generate all the code/files that, paired
@@ -256,6 +252,8 @@ command which takes that type as a parameter and returns the same type:
       'data':    {'arg1': 'UserDefOne'},
       'returns': 'UserDefOne' }
 
+    { 'event': 'MY_EVENT' }
+
 === scripts/qapi-types.py ===
 
 Used to generate the C types defined by a schema. The following files are
@@ -277,7 +275,7 @@ Example:
     $ cat qapi-generated/example-qapi-types.c
 [Uninteresting stuff omitted...]
 
-    void qapi_free_UserDefOneList(UserDefOneList * obj)
+    void qapi_free_UserDefOneList(UserDefOneList *obj)
     {
         QapiDeallocVisitor *md;
         Visitor *v;
@@ -292,7 +290,7 @@ Example:
         qapi_dealloc_visitor_cleanup(md);
     }
 
-    void qapi_free_UserDefOne(UserDefOne * obj)
+    void qapi_free_UserDefOne(UserDefOne *obj)
     {
         QapiDeallocVisitor *md;
         Visitor *v;
@@ -331,11 +329,11 @@ Example:
     struct UserDefOne
     {
         int64_t integer;
-        char * string;
+        char *string;
     };
 
-    void qapi_free_UserDefOneList(UserDefOneList * obj);
-    void qapi_free_UserDefOne(UserDefOne * obj);
+    void qapi_free_UserDefOneList(UserDefOneList *obj);
+    void qapi_free_UserDefOne(UserDefOne *obj);
 
     #endif
 
@@ -364,7 +362,7 @@ Example:
     $ cat qapi-generated/example-qapi-visit.c
 [Uninteresting stuff omitted...]
 
-    static void visit_type_UserDefOne_fields(Visitor *m, UserDefOne ** obj, Error **errp)
+    static void visit_type_UserDefOne_fields(Visitor *m, UserDefOne **obj, Error **errp)
     {
         Error *err = NULL;
         visit_type_int(m, &(*obj)->integer, "integer", &err);
@@ -380,7 +378,7 @@ Example:
         error_propagate(errp, err);
     }
 
-    void visit_type_UserDefOne(Visitor *m, UserDefOne ** obj, const char *name, Error **errp)
+    void visit_type_UserDefOne(Visitor *m, UserDefOne **obj, const char *name, Error **errp)
     {
         Error *err = NULL;
 
@@ -394,7 +392,7 @@ Example:
         error_propagate(errp, err);
     }
 
-    void visit_type_UserDefOneList(Visitor *m, UserDefOneList ** obj, const char *name, Error **errp)
+    void visit_type_UserDefOneList(Visitor *m, UserDefOneList **obj, const char *name, Error **errp)
     {
         Error *err = NULL;
         GenericList *i, **prev;
@@ -427,8 +425,8 @@ Example:
 
 [Visitors for builtin types omitted...]
 
-    void visit_type_UserDefOne(Visitor *m, UserDefOne ** obj, const char *name, Error **errp);
-    void visit_type_UserDefOneList(Visitor *m, UserDefOneList ** obj, const char *name, Error **errp);
+    void visit_type_UserDefOne(Visitor *m, UserDefOne **obj, const char *name, Error **errp);
+    void visit_type_UserDefOneList(Visitor *m, UserDefOneList **obj, const char *name, Error **errp);
 
     #endif
 
@@ -451,10 +449,12 @@ $(prefix)qmp-commands.h: Function prototypes for the QMP commands
 
 Example:
 
+    $ python scripts/qapi-commands.py --output-dir="qapi-generated"
+    --prefix="example-" --input-file=example-schema.json
     $ cat qapi-generated/example-qmp-marshal.c
 [Uninteresting stuff omitted...]
 
-    static void qmp_marshal_output_my_command(UserDefOne * ret_in, QObject **ret_out, Error **errp)
+    static void qmp_marshal_output_my_command(UserDefOne *ret_in, QObject **ret_out, Error **errp)
     {
         Error *local_err = NULL;
         QmpOutputVisitor *mo = qmp_output_visitor_new();
@@ -480,11 +480,11 @@ Example:
     static void qmp_marshal_input_my_command(QDict *args, QObject **ret, Error **errp)
     {
         Error *local_err = NULL;
-        UserDefOne * retval = NULL;
+        UserDefOne *retval = NULL;
         QmpInputVisitor *mi = qmp_input_visitor_new_strict(QOBJECT(args));
         QapiDeallocVisitor *md;
         Visitor *v;
-        UserDefOne * arg1 = NULL;
+        UserDefOne *arg1 = NULL;
 
         v = qmp_input_get_visitor(mi);
         visit_type_UserDefOne(v, &arg1, "arg1", &local_err);
@@ -525,6 +525,66 @@ Example:
     #include "qapi/qmp/qdict.h"
     #include "qapi/error.h"
 
-    UserDefOne * qmp_my_command(UserDefOne * arg1, Error **errp);
+    UserDefOne *qmp_my_command(UserDefOne *arg1, Error **errp);
+
+    #endif
+
+=== scripts/qapi-event.py ===
+
+Used to generate the event-related C code defined by a schema. The
+following files are created:
+
+$(prefix)qapi-event.h - Function prototypes for each event type, plus an
+                        enumeration of all event names
+$(prefix)qapi-event.c - Implementation of functions to send an event
+
+Example:
+
+    $ python scripts/qapi-event.py --output-dir="qapi-generated"
+    --prefix="example-" --input-file=example-schema.json
+    $ cat qapi-generated/example-qapi-event.c
+[Uninteresting stuff omitted...]
+
+    void qapi_event_send_my_event(Error **errp)
+    {
+        QDict *qmp;
+        Error *local_err = NULL;
+        QMPEventFuncEmit emit;
+        emit = qmp_event_get_func_emit();
+        if (!emit) {
+            return;
+        }
+
+        qmp = qmp_event_build_dict("MY_EVENT");
+
+        emit(EXAMPLE_QAPI_EVENT_MY_EVENT, qmp, &local_err);
+
+        error_propagate(errp, local_err);
+        QDECREF(qmp);
+    }
+
+    const char *EXAMPLE_QAPIEvent_lookup[] = {
+        "MY_EVENT",
+        NULL,
+    };
+    $ cat qapi-generated/example-qapi-event.h
+[Uninteresting stuff omitted...]
+
+    #ifndef EXAMPLE_QAPI_EVENT_H
+    #define EXAMPLE_QAPI_EVENT_H
+
+    #include "qapi/error.h"
+    #include "qapi/qmp/qdict.h"
+    #include "example-qapi-types.h"
+
+
+    void qapi_event_send_my_event(Error **errp);
+
+    extern const char *EXAMPLE_QAPIEvent_lookup[];
+    typedef enum EXAMPLE_QAPIEvent
+    {
+        EXAMPLE_QAPI_EVENT_MY_EVENT = 0,
+        EXAMPLE_QAPI_EVENT_MAX = 1,
+    } EXAMPLE_QAPIEvent;
 
     #endif

docs/rdma.txt

@@ -18,7 +18,7 @@ Contents:
 * RDMA Migration Protocol Description
 * Versioning and Capabilities
 * QEMUFileRDMA Interface
-* Migration of pc.ram
+* Migration of VM's ram
 * Error handling
 * TODO
 
@@ -149,7 +149,7 @@ The only difference between a SEND message and an RDMA
 message is that SEND messages cause notifications
 to be posted to the completion queue (CQ) on the
 infiniband receiver side, whereas RDMA messages (used
-for pc.ram) do not (to behave like an actual DMA).
+for VM's ram) do not (to behave like an actual DMA).
 
 Messages in infiniband require two things:
 
@@ -355,7 +355,7 @@ If the buffer is empty, then we follow the same steps
 listed above and issue another "QEMU File" protocol command,
 asking for a new SEND message to re-fill the buffer.
 
-Migration of pc.ram:
+Migration of VM's ram:
 ====================
 
 At the beginning of the migration, (migration-rdma.c),

docs/tracing.txt

@@ -23,7 +23,7 @@ for debugging, profiling, and observing execution.
 
 4. Pretty-print the binary trace file:
 
-    ./scripts/simpletrace.py trace-events trace-*
+    ./scripts/simpletrace.py trace-events trace-* # Override * with QEMU <pid>
 
 == Trace events ==
 

exec.c

@@ -430,15 +430,50 @@ static int cpu_common_post_load(void *opaque, int version_id)
     return 0;
 }
 
+static int cpu_common_pre_load(void *opaque)
+{
+    CPUState *cpu = opaque;
+
+    cpu->exception_index = 0;
+
+    return 0;
+}
+
+static bool cpu_common_exception_index_needed(void *opaque)
+{
+    CPUState *cpu = opaque;
+
+    return cpu->exception_index != 0;
+}
+
+static const VMStateDescription vmstate_cpu_common_exception_index = {
+    .name = "cpu_common/exception_index",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32(exception_index, CPUState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 const VMStateDescription vmstate_cpu_common = {
     .name = "cpu_common",
     .version_id = 1,
     .minimum_version_id = 1,
+    .pre_load = cpu_common_pre_load,
     .post_load = cpu_common_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT32(halted, CPUState),
         VMSTATE_UINT32(interrupt_request, CPUState),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (VMStateSubsection[]) {
+        {
+            .vmsd = &vmstate_cpu_common_exception_index,
+            .needed = cpu_common_exception_index_needed,
+        } , {
+            /* empty */
+        }
     }
 };
 
@@ -537,6 +572,16 @@ void cpu_watchpoint_remove_all(CPUState *cpu, int mask)
 {
 }
 
+int cpu_watchpoint_remove(CPUState *cpu, vaddr addr, vaddr len,
+                          int flags)
+{
+    return -ENOSYS;
+}
+
+void cpu_watchpoint_remove_by_ref(CPUState *cpu, CPUWatchpoint *watchpoint)
+{
+}
+
 int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len,
                           int flags, CPUWatchpoint **watchpoint)
 {
@@ -547,12 +592,10 @@ int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len,
 int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len,
                           int flags, CPUWatchpoint **watchpoint)
 {
-    vaddr len_mask = ~(len - 1);
     CPUWatchpoint *wp;
 
-    /* sanity checks: allow power-of-2 lengths, deny unaligned watchpoints */
-    if ((len & (len - 1)) || (addr & ~len_mask) ||
-            len == 0 || len > TARGET_PAGE_SIZE) {
+    /* forbid ranges which are empty or run off the end of the address space */
+    if (len == 0 || (addr + len - 1) < addr) {
         error_report("tried to set invalid watchpoint at %"
                      VADDR_PRIx ", len=%" VADDR_PRIu, addr, len);
         return -EINVAL;
@@ -560,7 +603,7 @@ int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len,
     wp = g_malloc(sizeof(*wp));
 
     wp->vaddr = addr;
-    wp->len_mask = len_mask;
+    wp->len = len;
     wp->flags = flags;
 
     /* keep all GDB-injected watchpoints in front */
@@ -581,11 +624,10 @@ int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len,
 int cpu_watchpoint_remove(CPUState *cpu, vaddr addr, vaddr len,
                           int flags)
 {
-    vaddr len_mask = ~(len - 1);
     CPUWatchpoint *wp;
 
     QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
-        if (addr == wp->vaddr && len_mask == wp->len_mask
+        if (addr == wp->vaddr && len == wp->len
                 && flags == (wp->flags & ~BP_WATCHPOINT_HIT)) {
             cpu_watchpoint_remove_by_ref(cpu, wp);
             return 0;
@@ -615,6 +657,27 @@ void cpu_watchpoint_remove_all(CPUState *cpu, int mask)
         }
     }
 }
+
+/* Return true if this watchpoint address matches the specified
+ * access (ie the address range covered by the watchpoint overlaps
+ * partially or completely with the address range covered by the
+ * access).
+ */
+static inline bool cpu_watchpoint_address_matches(CPUWatchpoint *wp,
+                                                  vaddr addr,
+                                                  vaddr len)
+{
+    /* We know the lengths are non-zero, but a little caution is
+     * required to avoid errors in the case where the range ends
+     * exactly at the top of the address space and so addr + len
+     * wraps round to zero.
+     */
+    vaddr wpend = wp->vaddr + wp->len - 1;
+    vaddr addrend = addr + len - 1;
+
+    return !(addr > wpend || wp->vaddr > addrend);
+}
+
 #endif
 
 /* Add a breakpoint.  */
@@ -826,7 +889,7 @@ hwaddr memory_region_section_get_iotlb(CPUState *cpu,
     /* Make accesses to pages with watchpoints go via the
        watchpoint trap routines.  */
     QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
-        if (vaddr == (wp->vaddr & TARGET_PAGE_MASK)) {
+        if (cpu_watchpoint_address_matches(wp, vaddr, TARGET_PAGE_SIZE)) {
             /* Avoid trapping reads of pages with a write breakpoint. */
             if ((prot & PAGE_WRITE) || (wp->flags & BP_MEM_READ)) {
                 iotlb = PHYS_SECTION_WATCH + paddr;
@@ -996,7 +1059,7 @@ void qemu_mutex_unlock_ramlist(void)
 
 #define HUGETLBFS_MAGIC       0x958458f6
 
-static long gethugepagesize(const char *path)
+static long gethugepagesize(const char *path, Error **errp)
 {
     struct statfs fs;
     int ret;
@@ -1006,7 +1069,8 @@ static long gethugepagesize(const char *path)
     } while (ret != 0 && errno == EINTR);
 
     if (ret != 0) {
-        perror(path);
+        error_setg_errno(errp, errno, "failed to get page size of file %s",
+                         path);
         return 0;
     }
 
@@ -1024,17 +1088,22 @@ static void *file_ram_alloc(RAMBlock *block,
     char *filename;
     char *sanitized_name;
     char *c;
-    void *area;
+    void *area = NULL;
     int fd;
-    unsigned long hpagesize;
+    uint64_t hpagesize;
+    Error *local_err = NULL;
 
-    hpagesize = gethugepagesize(path);
-    if (!hpagesize) {
+    hpagesize = gethugepagesize(path, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
         goto error;
     }
 
     if (memory < hpagesize) {
-        return NULL;
+        error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
+                   "or larger than huge page size 0x%" PRIx64,
+                   memory, hpagesize);
+        goto error;
     }
 
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
@@ -1095,6 +1164,7 @@ static void *file_ram_alloc(RAMBlock *block,
 
 error:
     if (mem_prealloc) {
+        error_report("%s\n", error_get_pretty(*errp));
         exit(1);
     }
     return NULL;
@@ -1224,7 +1294,7 @@ static int memory_try_enable_merging(void *addr, size_t len)
     return qemu_madvise(addr, len, QEMU_MADV_MERGEABLE);
 }
 
-static ram_addr_t ram_block_add(RAMBlock *new_block)
+static ram_addr_t ram_block_add(RAMBlock *new_block, Error **errp)
 {
     RAMBlock *block;
     ram_addr_t old_ram_size, new_ram_size;
@@ -1241,9 +1311,11 @@ static ram_addr_t ram_block_add(RAMBlock *new_block)
         } else {
             new_block->host = phys_mem_alloc(new_block->length);
             if (!new_block->host) {
-                fprintf(stderr, "Cannot set up guest memory '%s': %s\n",
-                        memory_region_name(new_block->mr), strerror(errno));
-                exit(1);
+                error_setg_errno(errp, errno,
+                                 "cannot set up guest memory '%s'",
+                                 memory_region_name(new_block->mr));
+                qemu_mutex_unlock_ramlist();
+                return -1;
             }
             memory_try_enable_merging(new_block->host, new_block->length);
         }
@@ -1294,6 +1366,8 @@ ram_addr_t qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
                                     Error **errp)
 {
     RAMBlock *new_block;
+    ram_addr_t addr;
+    Error *local_err = NULL;
 
     if (xen_enabled()) {
         error_setg(errp, "-mem-path not supported with Xen");
@@ -1323,14 +1397,22 @@ ram_addr_t qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
         return -1;
     }
 
-    return ram_block_add(new_block);
+    addr = ram_block_add(new_block, &local_err);
+    if (local_err) {
+        g_free(new_block);
+        error_propagate(errp, local_err);
+        return -1;
+    }
+    return addr;
 }
 #endif
 
 ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
-                                   MemoryRegion *mr)
+                                   MemoryRegion *mr, Error **errp)
 {
     RAMBlock *new_block;
+    ram_addr_t addr;
+    Error *local_err = NULL;
 
     size = TARGET_PAGE_ALIGN(size);
     new_block = g_malloc0(sizeof(*new_block));
@@ -1341,12 +1423,18 @@ ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
     if (host) {
         new_block->flags |= RAM_PREALLOC;
     }
-    return ram_block_add(new_block);
+    addr = ram_block_add(new_block, &local_err);
+    if (local_err) {
+        g_free(new_block);
+        error_propagate(errp, local_err);
+        return -1;
+    }
+    return addr;
 }
 
-ram_addr_t qemu_ram_alloc(ram_addr_t size, MemoryRegion *mr)
+ram_addr_t qemu_ram_alloc(ram_addr_t size, MemoryRegion *mr, Error **errp)
 {
-    return qemu_ram_alloc_from_ptr(size, NULL, mr);
+    return qemu_ram_alloc_from_ptr(size, NULL, mr, errp);
 }
 
 void qemu_ram_free_from_ptr(ram_addr_t addr)
@@ -1590,7 +1678,7 @@ static const MemoryRegionOps notdirty_mem_ops = {
 };
 
 /* Generate a debug exception if a watchpoint has been hit.  */
-static void check_watchpoint(int offset, int len_mask, int flags)
+static void check_watchpoint(int offset, int len, int flags)
 {
     CPUState *cpu = current_cpu;
     CPUArchState *env = cpu->env_ptr;
@@ -1608,9 +1696,14 @@ static void check_watchpoint(int offset, int len_mask, int flags)
     }
     vaddr = (cpu->mem_io_vaddr & TARGET_PAGE_MASK) + offset;
     QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
-        if ((vaddr == (wp->vaddr & len_mask) ||
-             (vaddr & wp->len_mask) == wp->vaddr) && (wp->flags & flags)) {
-            wp->flags |= BP_WATCHPOINT_HIT;
+        if (cpu_watchpoint_address_matches(wp, vaddr, len)
+            && (wp->flags & flags)) {
+            if (flags == BP_MEM_READ) {
+                wp->flags |= BP_WATCHPOINT_HIT_READ;
+            } else {
+                wp->flags |= BP_WATCHPOINT_HIT_WRITE;
+            }
+            wp->hitaddr = vaddr;
             if (!cpu->watchpoint_hit) {
                 cpu->watchpoint_hit = wp;
                 tb_check_watchpoint(cpu);
@@ -1635,7 +1728,7 @@ static void check_watchpoint(int offset, int len_mask, int flags)
 static uint64_t watch_mem_read(void *opaque, hwaddr addr,
                                unsigned size)
 {
-    check_watchpoint(addr & ~TARGET_PAGE_MASK, ~(size - 1), BP_MEM_READ);
+    check_watchpoint(addr & ~TARGET_PAGE_MASK, size, BP_MEM_READ);
     switch (size) {
     case 1: return ldub_phys(&address_space_memory, addr);
     case 2: return lduw_phys(&address_space_memory, addr);
@@ -1647,7 +1740,7 @@ static uint64_t watch_mem_read(void *opaque, hwaddr addr,
 static void watch_mem_write(void *opaque, hwaddr addr,
                             uint64_t val, unsigned size)
 {
-    check_watchpoint(addr & ~TARGET_PAGE_MASK, ~(size - 1), BP_MEM_WRITE);
+    check_watchpoint(addr & ~TARGET_PAGE_MASK, size, BP_MEM_WRITE);
     switch (size) {
     case 1:
         stb_phys(&address_space_memory, addr, val);

gdbstub.c

@@ -1707,7 +1707,7 @@ int gdbserver_start(const char *device)
         qemu_add_vm_change_state_handler(gdb_vm_state_change, NULL);
 
         /* Initialize a monitor terminal for gdb */
-        mon_chr = g_malloc0(sizeof(*mon_chr));
+        mon_chr = qemu_chr_alloc();
         mon_chr->chr_write = gdb_monitor_write;
         monitor_init(mon_chr, 0);
     } else {

hmp-commands.hx

@@ -1778,6 +1778,8 @@ show qdev device model list
 show roms
 @item info tpm
 show the TPM device
+@item info memory-devices
+show the memory devices
 @end table
 ETEXI
 

hmp.c

@@ -679,6 +679,8 @@ void hmp_info_block_jobs(Monitor *mon, const QDict *qdict)
         }
         list = list->next;
     }
+
+    qapi_free_BlockJobInfoList(list);
 }
 
 void hmp_info_tpm(Monitor *mon, const QDict *qdict)
@@ -1718,3 +1720,41 @@ void hmp_info_memdev(Monitor *mon, const QDict *qdict)
 
     qapi_free_MemdevList(memdev_list);
 }
+
+void hmp_info_memory_devices(Monitor *mon, const QDict *qdict)
+{
+    Error *err = NULL;
+    MemoryDeviceInfoList *info_list = qmp_query_memory_devices(&err);
+    MemoryDeviceInfoList *info;
+    MemoryDeviceInfo *value;
+    PCDIMMDeviceInfo *di;
+
+    for (info = info_list; info; info = info->next) {
+        value = info->value;
+
+        if (value) {
+            switch (value->kind) {
+            case MEMORY_DEVICE_INFO_KIND_DIMM:
+                di = value->dimm;
+
+                monitor_printf(mon, "Memory device [%s]: \"%s\"\n",
+                               MemoryDeviceInfoKind_lookup[value->kind],
+                               di->id ? di->id : "");
+                monitor_printf(mon, "  addr: 0x%" PRIx64 "\n", di->addr);
+                monitor_printf(mon, "  slot: %" PRId64 "\n", di->slot);
+                monitor_printf(mon, "  node: %" PRId64 "\n", di->node);
+                monitor_printf(mon, "  size: %" PRIu64 "\n", di->size);
+                monitor_printf(mon, "  memdev: %s\n", di->memdev);
+                monitor_printf(mon, "  hotplugged: %s\n",
+                               di->hotplugged ? "true" : "false");
+                monitor_printf(mon, "  hotpluggable: %s\n",
+                               di->hotpluggable ? "true" : "false");
+                break;
+            default:
+                break;
+            }
+        }
+    }
+
+    qapi_free_MemoryDeviceInfoList(info_list);
+}

hmp.h

@@ -94,6 +94,7 @@ void hmp_cpu_add(Monitor *mon, const QDict *qdict);
 void hmp_object_add(Monitor *mon, const QDict *qdict);
 void hmp_object_del(Monitor *mon, const QDict *qdict);
 void hmp_info_memdev(Monitor *mon, const QDict *qdict);
+void hmp_info_memory_devices(Monitor *mon, const QDict *qdict);
 void object_add_completion(ReadLineState *rs, int nb_args, const char *str);
 void object_del_completion(ReadLineState *rs, int nb_args, const char *str);
 void device_add_completion(ReadLineState *rs, int nb_args, const char *str);

hw/alpha/typhoon.c

@@ -844,7 +844,8 @@ PCIBus *typhoon_init(ram_addr_t ram_size, ISABus **isa_bus,
 
     /* Main memory region, 0x00.0000.0000.  Real hardware supports 32GB,
        but the address space hole reserved at this point is 8TB.  */
-    memory_region_init_ram(&s->ram_region, OBJECT(s), "ram", ram_size);
+    memory_region_init_ram(&s->ram_region, OBJECT(s), "ram", ram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->ram_region);
     memory_region_add_subregion(addr_space, 0, &s->ram_region);
 

hw/arm/armv7m.c

@@ -210,11 +210,12 @@ qemu_irq *armv7m_init(MemoryRegion *system_memory,
 #endif
 
     /* Flash programming is done via the SCU, so pretend it is ROM.  */
-    memory_region_init_ram(flash, NULL, "armv7m.flash", flash_size);
+    memory_region_init_ram(flash, NULL, "armv7m.flash", flash_size,
+                           &error_abort);
     vmstate_register_ram_global(flash);
     memory_region_set_readonly(flash, true);
     memory_region_add_subregion(system_memory, 0, flash);
-    memory_region_init_ram(sram, NULL, "armv7m.sram", sram_size);
+    memory_region_init_ram(sram, NULL, "armv7m.sram", sram_size, &error_abort);
     vmstate_register_ram_global(sram);
     memory_region_add_subregion(system_memory, 0x20000000, sram);
     armv7m_bitband_init();
@@ -255,7 +256,7 @@ qemu_irq *armv7m_init(MemoryRegion *system_memory,
     /* Hack to map an additional page of ram at the top of the address
        space.  This stops qemu complaining about executing code outside RAM
        when returning from an exception.  */
-    memory_region_init_ram(hack, NULL, "armv7m.hack", 0x1000);
+    memory_region_init_ram(hack, NULL, "armv7m.hack", 0x1000, &error_abort);
     vmstate_register_ram_global(hack);
     memory_region_add_subregion(system_memory, 0xfffff000, hack);
 

hw/arm/boot.c

@@ -312,7 +312,26 @@ static void set_kernel_args_old(const struct arm_boot_info *info)
     }
 }
 
-static int load_dtb(hwaddr addr, const struct arm_boot_info *binfo)
+/**
+ * load_dtb() - load a device tree binary image into memory
+ * @addr:       the address to load the image at
+ * @binfo:      struct describing the boot environment
+ * @addr_limit: upper limit of the available memory area at @addr
+ *
+ * Load a device tree supplied by the machine or by the user  with the
+ * '-dtb' command line option, and put it at offset @addr in target
+ * memory.
+ *
+ * If @addr_limit contains a meaningful value (i.e., it is strictly greater
+ * than @addr), the device tree is only loaded if its size does not exceed
+ * the limit.
+ *
+ * Returns: the size of the device tree image on success,
+ *          0 if the image size exceeds the limit,
+ *          -1 on errors.
+ */
+static int load_dtb(hwaddr addr, const struct arm_boot_info *binfo,
+                    hwaddr addr_limit)
 {
     void *fdt = NULL;
     int size, rc;
@@ -341,6 +360,15 @@ static int load_dtb(hwaddr addr, const struct arm_boot_info *binfo)
         }
     }
 
+    if (addr_limit > addr && size > (addr_limit - addr)) {
+        /* Installing the device tree blob at addr would exceed addr_limit.
+         * Whether this constitutes failure is up to the caller to decide,
+         * so just return 0 as size, i.e., no error.
+         */
+        g_free(fdt);
+        return 0;
+    }
+
     acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells");
     scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells");
     if (acells == 0 || scells == 0) {
@@ -396,11 +424,14 @@ static int load_dtb(hwaddr addr, const struct arm_boot_info *binfo)
 
     qemu_fdt_dumpdtb(fdt, size);
 
-    cpu_physical_memory_write(addr, fdt, size);
+    /* Put the DTB into the memory map as a ROM image: this will ensure
+     * the DTB is copied again upon reset, even if addr points into RAM.
+     */
+    rom_add_blob_fixed("dtb", fdt, size, addr);
 
     g_free(fdt);
 
-    return 0;
+    return size;
 
 fail:
     g_free(fdt);
@@ -451,7 +482,7 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info)
     int kernel_size;
     int initrd_size;
     int is_linux = 0;
-    uint64_t elf_entry;
+    uint64_t elf_entry, elf_low_addr, elf_high_addr;
     int elf_machine;
     hwaddr entry, kernel_load_offset;
     int big_endian;
@@ -459,6 +490,16 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info)
 
     /* Load the kernel.  */
     if (!info->kernel_filename) {
+
+        if (have_dtb(info)) {
+            /* If we have a device tree blob, but no kernel to supply it to,
+             * copy it to the base of RAM for a bootloader to pick up.
+             */
+            if (load_dtb(info->loader_start, info, 0) < 0) {
+                exit(1);
+            }
+        }
+
         /* If no kernel specified, do nothing; we will start from address 0
          * (typically a boot ROM image) in the same way as hardware.
          */
@@ -508,7 +549,25 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info)
 
     /* Assume that raw images are linux kernels, and ELF images are not.  */
     kernel_size = load_elf(info->kernel_filename, NULL, NULL, &elf_entry,
-                           NULL, NULL, big_endian, elf_machine, 1);
+                           &elf_low_addr, &elf_high_addr, big_endian,
+                           elf_machine, 1);
+    if (kernel_size > 0 && have_dtb(info)) {
+        /* If there is still some room left at the base of RAM, try and put
+         * the DTB there like we do for images loaded with -bios or -pflash.
+         */
+        if (elf_low_addr > info->loader_start
+            || elf_high_addr < info->loader_start) {
+            /* Pass elf_low_addr as address limit to load_dtb if it may be
+             * pointing into RAM, otherwise pass '0' (no limit)
+             */
+            if (elf_low_addr < info->loader_start) {
+                elf_low_addr = 0;
+            }
+            if (load_dtb(info->loader_start, info, elf_low_addr) < 0) {
+                exit(1);
+            }
+        }
+    }
     entry = elf_entry;
     if (kernel_size < 0) {
         kernel_size = load_uimage(info->kernel_filename, &entry, NULL,
@@ -569,7 +628,7 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info)
              */
             hwaddr dtb_start = QEMU_ALIGN_UP(info->initrd_start + initrd_size,
                                              4096);
-            if (load_dtb(dtb_start, info)) {
+            if (load_dtb(dtb_start, info, 0) < 0) {
                 exit(1);
             }
             fixupcontext[FIXUP_ARGPTR] = dtb_start;

hw/arm/cubieboard.c

@@ -64,7 +64,7 @@ static void cubieboard_init(MachineState *machine)
     }
 
     memory_region_init_ram(&s->sdram, NULL, "cubieboard.ram",
-                           machine->ram_size);
+                           machine->ram_size, &error_abort);
     vmstate_register_ram_global(&s->sdram);
     memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE,
                                 &s->sdram);

hw/arm/digic_boards.c

@@ -51,7 +51,7 @@ typedef struct DigicBoard {
 
 static void digic4_board_setup_ram(DigicBoardState *s, hwaddr ram_size)
 {
-    memory_region_init_ram(&s->ram, NULL, "ram", ram_size);
+    memory_region_init_ram(&s->ram, NULL, "ram", ram_size, &error_abort);
     memory_region_add_subregion(get_system_memory(), 0, &s->ram);
     vmstate_register_ram_global(&s->ram);
 }

hw/arm/exynos4210.c

@@ -248,7 +248,7 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
 
     /* Internal ROM */
     memory_region_init_ram(&s->irom_mem, NULL, "exynos4210.irom",
-                           EXYNOS4210_IROM_SIZE);
+                           EXYNOS4210_IROM_SIZE, &error_abort);
     vmstate_register_ram_global(&s->irom_mem);
     memory_region_set_readonly(&s->irom_mem, true);
     memory_region_add_subregion(system_mem, EXYNOS4210_IROM_BASE_ADDR,
@@ -264,7 +264,7 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
 
     /* Internal RAM */
     memory_region_init_ram(&s->iram_mem, NULL, "exynos4210.iram",
-                           EXYNOS4210_IRAM_SIZE);
+                           EXYNOS4210_IRAM_SIZE, &error_abort);
     vmstate_register_ram_global(&s->iram_mem);
     memory_region_add_subregion(system_mem, EXYNOS4210_IRAM_BASE_ADDR,
                                 &s->iram_mem);
@@ -273,13 +273,14 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
     mem_size = ram_size;
     if (mem_size > EXYNOS4210_DRAM_MAX_SIZE) {
         memory_region_init_ram(&s->dram1_mem, NULL, "exynos4210.dram1",
-                mem_size - EXYNOS4210_DRAM_MAX_SIZE);
+                mem_size - EXYNOS4210_DRAM_MAX_SIZE, &error_abort);
         vmstate_register_ram_global(&s->dram1_mem);
         memory_region_add_subregion(system_mem, EXYNOS4210_DRAM1_BASE_ADDR,
                 &s->dram1_mem);
         mem_size = EXYNOS4210_DRAM_MAX_SIZE;
     }
-    memory_region_init_ram(&s->dram0_mem, NULL, "exynos4210.dram0", mem_size);
+    memory_region_init_ram(&s->dram0_mem, NULL, "exynos4210.dram0", mem_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->dram0_mem);
     memory_region_add_subregion(system_mem, EXYNOS4210_DRAM0_BASE_ADDR,
             &s->dram0_mem);

hw/arm/highbank.c

@@ -255,12 +255,13 @@ static void calxeda_init(MachineState *machine, enum cxmachines machine_id)
 
     sysmem = get_system_memory();
     dram = g_new(MemoryRegion, 1);
-    memory_region_init_ram(dram, NULL, "highbank.dram", ram_size);
+    memory_region_init_ram(dram, NULL, "highbank.dram", ram_size, &error_abort);
     /* SDRAM at address zero.  */
     memory_region_add_subregion(sysmem, 0, dram);
 
     sysram = g_new(MemoryRegion, 1);
-    memory_region_init_ram(sysram, NULL, "highbank.sysram", 0x8000);
+    memory_region_init_ram(sysram, NULL, "highbank.sysram", 0x8000,
+                           &error_abort);
     memory_region_add_subregion(sysmem, 0xfff88000, sysram);
     if (bios_name != NULL) {
         sysboot_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);

hw/arm/integratorcp.c

@@ -264,7 +264,8 @@ static int integratorcm_init(SysBusDevice *dev)
     s->cm_init = 0x00000112;
     s->cm_refcnt_offset = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), 24,
                                    1000);
-    memory_region_init_ram(&s->flash, OBJECT(s), "integrator.flash", 0x100000);
+    memory_region_init_ram(&s->flash, OBJECT(s), "integrator.flash", 0x100000,
+                           &error_abort);
     vmstate_register_ram_global(&s->flash);
 
     memory_region_init_io(&s->iomem, OBJECT(s), &integratorcm_ops, s,
@@ -485,7 +486,7 @@ static void integratorcp_init(MachineState *machine)
         exit(1);
     }
 
-    memory_region_init_ram(ram, NULL, "integrator.ram", ram_size);
+    memory_region_init_ram(ram, NULL, "integrator.ram", ram_size, &error_abort);
     vmstate_register_ram_global(ram);
     /* ??? On a real system the first 1Mb is mapped as SSRAM or boot flash.  */
     /* ??? RAM should repeat to fill physical memory space.  */

hw/arm/kzm.c

@@ -97,14 +97,14 @@ static void kzm_init(MachineState *machine)
 
     /* On a real system, the first 16k is a `secure boot rom' */
 
-    memory_region_init_ram(ram, NULL, "kzm.ram", ram_size);
+    memory_region_init_ram(ram, NULL, "kzm.ram", ram_size, &error_abort);
     vmstate_register_ram_global(ram);
     memory_region_add_subregion(address_space_mem, KZM_RAMADDRESS, ram);
 
     memory_region_init_alias(ram_alias, NULL, "ram.alias", ram, 0, ram_size);
     memory_region_add_subregion(address_space_mem, 0x88000000, ram_alias);
 
-    memory_region_init_ram(sram, NULL, "kzm.sram", 0x4000);
+    memory_region_init_ram(sram, NULL, "kzm.sram", 0x4000, &error_abort);
     memory_region_add_subregion(address_space_mem, 0x1FFFC000, sram);
 
     dev = sysbus_create_varargs("imx_avic", 0x68000000,

hw/arm/mainstone.c

@@ -123,7 +123,8 @@ static void mainstone_common_init(MemoryRegion *address_space_mem,
 
     /* Setup CPU & memory */
     mpu = pxa270_init(address_space_mem, mainstone_binfo.ram_size, cpu_model);
-    memory_region_init_ram(rom, NULL, "mainstone.rom", MAINSTONE_ROM);
+    memory_region_init_ram(rom, NULL, "mainstone.rom", MAINSTONE_ROM,
+                           &error_abort);
     vmstate_register_ram_global(rom);
     memory_region_set_readonly(rom, true);
     memory_region_add_subregion(address_space_mem, 0, rom);

hw/arm/musicpal.c

@@ -1601,11 +1601,13 @@ static void musicpal_init(MachineState *machine)
     }
 
     /* For now we use a fixed - the original - RAM size */
-    memory_region_init_ram(ram, NULL, "musicpal.ram", MP_RAM_DEFAULT_SIZE);
+    memory_region_init_ram(ram, NULL, "musicpal.ram", MP_RAM_DEFAULT_SIZE,
+                           &error_abort);
     vmstate_register_ram_global(ram);
     memory_region_add_subregion(address_space_mem, 0, ram);
 
-    memory_region_init_ram(sram, NULL, "musicpal.sram", MP_SRAM_SIZE);
+    memory_region_init_ram(sram, NULL, "musicpal.sram", MP_SRAM_SIZE,
+                           &error_abort);
     vmstate_register_ram_global(sram);
     memory_region_add_subregion(address_space_mem, MP_SRAM_BASE, sram);
 

hw/arm/omap1.c

@@ -3854,10 +3854,12 @@ struct omap_mpu_state_s *omap310_mpu_init(MemoryRegion *system_memory,
     omap_clk_init(s);
 
     /* Memory-mapped stuff */
-    memory_region_init_ram(&s->emiff_ram, NULL, "omap1.dram", s->sdram_size);
+    memory_region_init_ram(&s->emiff_ram, NULL, "omap1.dram", s->sdram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->emiff_ram);
     memory_region_add_subregion(system_memory, OMAP_EMIFF_BASE, &s->emiff_ram);
-    memory_region_init_ram(&s->imif_ram, NULL, "omap1.sram", s->sram_size);
+    memory_region_init_ram(&s->imif_ram, NULL, "omap1.sram", s->sram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->imif_ram);
     memory_region_add_subregion(system_memory, OMAP_IMIF_BASE, &s->imif_ram);
 

hw/arm/omap2.c

@@ -2266,10 +2266,12 @@ struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sysmem,
     omap_clk_init(s);
 
     /* Memory-mapped stuff */
-    memory_region_init_ram(&s->sdram, NULL, "omap2.dram", s->sdram_size);
+    memory_region_init_ram(&s->sdram, NULL, "omap2.dram", s->sdram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->sdram);
     memory_region_add_subregion(sysmem, OMAP2_Q2_BASE, &s->sdram);
-    memory_region_init_ram(&s->sram, NULL, "omap2.sram", s->sram_size);
+    memory_region_init_ram(&s->sram, NULL, "omap2.sram", s->sram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->sram);
     memory_region_add_subregion(sysmem, OMAP2_SRAM_BASE, &s->sram);
 

hw/arm/omap_sx1.c

@@ -122,7 +122,8 @@ static void sx1_init(MachineState *machine, const int version)
                            machine->cpu_model);
 
     /* External Flash (EMIFS) */
-    memory_region_init_ram(flash, NULL, "omap_sx1.flash0-0", flash_size);
+    memory_region_init_ram(flash, NULL, "omap_sx1.flash0-0", flash_size,
+                           &error_abort);
     vmstate_register_ram_global(flash);
     memory_region_set_readonly(flash, true);
     memory_region_add_subregion(address_space, OMAP_CS0_BASE, flash);
@@ -164,7 +165,8 @@ static void sx1_init(MachineState *machine, const int version)
 
     if ((version == 1) &&
             (dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) {
-        memory_region_init_ram(flash_1, NULL, "omap_sx1.flash1-0", flash1_size);
+        memory_region_init_ram(flash_1, NULL, "omap_sx1.flash1-0", flash1_size,
+                               &error_abort);
         vmstate_register_ram_global(flash_1);
         memory_region_set_readonly(flash_1, true);
         memory_region_add_subregion(address_space, OMAP_CS1_BASE, flash_1);

hw/arm/palm.c

@@ -212,7 +212,8 @@ static void palmte_init(MachineState *machine)
     mpu = omap310_mpu_init(address_space_mem, sdram_size, cpu_model);
 
     /* External Flash (EMIFS) */
-    memory_region_init_ram(flash, NULL, "palmte.flash", flash_size);
+    memory_region_init_ram(flash, NULL, "palmte.flash", flash_size,
+                           &error_abort);
     vmstate_register_ram_global(flash);
     memory_region_set_readonly(flash, true);
     memory_region_add_subregion(address_space_mem, OMAP_CS0_BASE, flash);

hw/arm/pxa2xx.c

@@ -2055,10 +2055,12 @@ PXA2xxState *pxa270_init(MemoryRegion *address_space,
     s->reset = qemu_allocate_irq(pxa2xx_reset, s, 0);
 
     /* SDRAM & Internal Memory Storage */
-    memory_region_init_ram(&s->sdram, NULL, "pxa270.sdram", sdram_size);
+    memory_region_init_ram(&s->sdram, NULL, "pxa270.sdram", sdram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->sdram);
     memory_region_add_subregion(address_space, PXA2XX_SDRAM_BASE, &s->sdram);
-    memory_region_init_ram(&s->internal, NULL, "pxa270.internal", 0x40000);
+    memory_region_init_ram(&s->internal, NULL, "pxa270.internal", 0x40000,
+                           &error_abort);
     vmstate_register_ram_global(&s->internal);
     memory_region_add_subregion(address_space, PXA2XX_INTERNAL_BASE,
                                 &s->internal);
@@ -2186,11 +2188,12 @@ PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size)
     s->reset = qemu_allocate_irq(pxa2xx_reset, s, 0);
 
     /* SDRAM & Internal Memory Storage */
-    memory_region_init_ram(&s->sdram, NULL, "pxa255.sdram", sdram_size);
+    memory_region_init_ram(&s->sdram, NULL, "pxa255.sdram", sdram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->sdram);
     memory_region_add_subregion(address_space, PXA2XX_SDRAM_BASE, &s->sdram);
     memory_region_init_ram(&s->internal, NULL, "pxa255.internal",
-                           PXA2XX_INTERNAL_SIZE);
+                           PXA2XX_INTERNAL_SIZE, &error_abort);
     vmstate_register_ram_global(&s->internal);
     memory_region_add_subregion(address_space, PXA2XX_INTERNAL_BASE,
                                 &s->internal);

hw/arm/realview.c

@@ -137,12 +137,14 @@ static void realview_init(MachineState *machine,
         /* Core tile RAM.  */
         low_ram_size = ram_size - 0x20000000;
         ram_size = 0x20000000;
-        memory_region_init_ram(ram_lo, NULL, "realview.lowmem", low_ram_size);
+        memory_region_init_ram(ram_lo, NULL, "realview.lowmem", low_ram_size,
+                               &error_abort);
         vmstate_register_ram_global(ram_lo);
         memory_region_add_subregion(sysmem, 0x20000000, ram_lo);
     }
 
-    memory_region_init_ram(ram_hi, NULL, "realview.highmem", ram_size);
+    memory_region_init_ram(ram_hi, NULL, "realview.highmem", ram_size,
+                           &error_abort);
     vmstate_register_ram_global(ram_hi);
     low_ram_size = ram_size;
     if (low_ram_size > 0x10000000)
@@ -337,7 +339,8 @@ static void realview_init(MachineState *machine,
        startup code.  I guess this works on real hardware because the
        BootROM happens to be in ROM/flash or in memory that isn't clobbered
        until after Linux boots the secondary CPUs.  */
-    memory_region_init_ram(ram_hack, NULL, "realview.hack", 0x1000);
+    memory_region_init_ram(ram_hack, NULL, "realview.hack", 0x1000,
+                           &error_abort);
     vmstate_register_ram_global(ram_hack);
     memory_region_add_subregion(sysmem, SMP_BOOT_ADDR, ram_hack);
 

hw/arm/spitz.c

@@ -912,7 +912,7 @@ static void spitz_common_init(MachineState *machine,
 
     sl_flash_register(mpu, (model == spitz) ? FLASH_128M : FLASH_1024M);
 
-    memory_region_init_ram(rom, NULL, "spitz.rom", SPITZ_ROM);
+    memory_region_init_ram(rom, NULL, "spitz.rom", SPITZ_ROM, &error_abort);
     vmstate_register_ram_global(rom);
     memory_region_set_readonly(rom, true);
     memory_region_add_subregion(address_space_mem, 0, rom);

hw/arm/strongarm.c

@@ -1604,7 +1604,8 @@ StrongARMState *sa1110_init(MemoryRegion *sysmem,
         exit(1);
     }
 
-    memory_region_init_ram(&s->sdram, NULL, "strongarm.sdram", sdram_size);
+    memory_region_init_ram(&s->sdram, NULL, "strongarm.sdram", sdram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->sdram);
     memory_region_add_subregion(sysmem, SA_SDCS0, &s->sdram);
 

hw/arm/tosa.c

@@ -228,7 +228,7 @@ static void tosa_init(MachineState *machine)
 
     mpu = pxa255_init(address_space_mem, tosa_binfo.ram_size);
 
-    memory_region_init_ram(rom, NULL, "tosa.rom", TOSA_ROM);
+    memory_region_init_ram(rom, NULL, "tosa.rom", TOSA_ROM, &error_abort);
     vmstate_register_ram_global(rom);
     memory_region_set_readonly(rom, true);
     memory_region_add_subregion(address_space_mem, 0, rom);

hw/arm/versatilepb.c

@@ -198,7 +198,8 @@ static void versatile_init(MachineState *machine, int board_id)
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
     }
-    memory_region_init_ram(ram, NULL, "versatile.ram", machine->ram_size);
+    memory_region_init_ram(ram, NULL, "versatile.ram", machine->ram_size,
+                           &error_abort);
     vmstate_register_ram_global(ram);
     /* ??? RAM should repeat to fill physical memory space.  */
     /* SDRAM at address zero.  */

hw/arm/vexpress.c

@@ -252,7 +252,8 @@ static void a9_daughterboard_init(const VEDBoardInfo *daughterboard,
         exit(1);
     }
 
-    memory_region_init_ram(ram, NULL, "vexpress.highmem", ram_size);
+    memory_region_init_ram(ram, NULL, "vexpress.highmem", ram_size,
+                           &error_abort);
     vmstate_register_ram_global(ram);
     low_ram_size = ram_size;
     if (low_ram_size > 0x4000000) {
@@ -346,7 +347,8 @@ static void a15_daughterboard_init(const VEDBoardInfo *daughterboard,
         }
     }
 
-    memory_region_init_ram(ram, NULL, "vexpress.highmem", ram_size);
+    memory_region_init_ram(ram, NULL, "vexpress.highmem", ram_size,
+                           &error_abort);
     vmstate_register_ram_global(ram);
     /* RAM is from 0x80000000 upwards; there is no low-memory alias for it. */
     memory_region_add_subregion(sysmem, 0x80000000, ram);
@@ -364,7 +366,8 @@ static void a15_daughterboard_init(const VEDBoardInfo *daughterboard,
     /* 0x2b060000: SP805 watchdog: not modelled */
     /* 0x2b0a0000: PL341 dynamic memory controller: not modelled */
     /* 0x2e000000: system SRAM */
-    memory_region_init_ram(sram, NULL, "vexpress.a15sram", 0x10000);
+    memory_region_init_ram(sram, NULL, "vexpress.a15sram", 0x10000,
+                           &error_abort);
     vmstate_register_ram_global(sram);
     memory_region_add_subregion(sysmem, 0x2e000000, sram);
 
@@ -634,12 +637,14 @@ static void vexpress_common_init(VEDBoardInfo *daughterboard,
     }
 
     sram_size = 0x2000000;
-    memory_region_init_ram(sram, NULL, "vexpress.sram", sram_size);
+    memory_region_init_ram(sram, NULL, "vexpress.sram", sram_size,
+                           &error_abort);
     vmstate_register_ram_global(sram);
     memory_region_add_subregion(sysmem, map[VE_SRAM], sram);
 
     vram_size = 0x800000;
-    memory_region_init_ram(vram, NULL, "vexpress.vram", vram_size);
+    memory_region_init_ram(vram, NULL, "vexpress.vram", vram_size,
+                           &error_abort);
     vmstate_register_ram_global(vram);
     memory_region_add_subregion(sysmem, map[VE_VIDEORAM], vram);
 

hw/arm/virt.c

@@ -37,6 +37,7 @@
 #include "sysemu/sysemu.h"
 #include "sysemu/kvm.h"
 #include "hw/boards.h"
+#include "hw/loader.h"
 #include "exec/address-spaces.h"
 #include "qemu/bitops.h"
 #include "qemu/error-report.h"
@@ -371,11 +372,13 @@ static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic)
                                      2, base, 2, size);
     qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupts",
                                GIC_FDT_IRQ_TYPE_SPI, irq,
-                               GIC_FDT_IRQ_FLAGS_EDGE_LO_HI);
+                               GIC_FDT_IRQ_FLAGS_LEVEL_HI);
     qemu_fdt_setprop_cells(vbi->fdt, nodename, "clocks",
                                vbi->clock_phandle, vbi->clock_phandle);
     qemu_fdt_setprop(vbi->fdt, nodename, "clock-names",
                          clocknames, sizeof(clocknames));
+
+    qemu_fdt_setprop_string(vbi->fdt, "/chosen", "linux,stdout-path", nodename);
     g_free(nodename);
 }
 
@@ -396,7 +399,7 @@ static void create_rtc(const VirtBoardInfo *vbi, qemu_irq *pic)
                                  2, base, 2, size);
     qemu_fdt_setprop_cells(vbi->fdt, nodename, "interrupts",
                            GIC_FDT_IRQ_TYPE_SPI, irq,
-                           GIC_FDT_IRQ_FLAGS_EDGE_LO_HI);
+                           GIC_FDT_IRQ_FLAGS_LEVEL_HI);
     qemu_fdt_setprop_cell(vbi->fdt, nodename, "clocks", vbi->clock_phandle);
     qemu_fdt_setprop_string(vbi->fdt, nodename, "clock-names", "apb_pclk");
     g_free(nodename);
@@ -437,6 +440,73 @@ static void create_virtio_devices(const VirtBoardInfo *vbi, qemu_irq *pic)
     }
 }
 
+static void create_one_flash(const char *name, hwaddr flashbase,
+                             hwaddr flashsize)
+{
+    /* Create and map a single flash device. We use the same
+     * parameters as the flash devices on the Versatile Express board.
+     */
+    DriveInfo *dinfo = drive_get_next(IF_PFLASH);
+    DeviceState *dev = qdev_create(NULL, "cfi.pflash01");
+    const uint64_t sectorlength = 256 * 1024;
+
+    if (dinfo && qdev_prop_set_drive(dev, "drive", dinfo->bdrv)) {
+        abort();
+    }
+
+    qdev_prop_set_uint32(dev, "num-blocks", flashsize / sectorlength);
+    qdev_prop_set_uint64(dev, "sector-length", sectorlength);
+    qdev_prop_set_uint8(dev, "width", 4);
+    qdev_prop_set_uint8(dev, "device-width", 2);
+    qdev_prop_set_uint8(dev, "big-endian", 0);
+    qdev_prop_set_uint16(dev, "id0", 0x89);
+    qdev_prop_set_uint16(dev, "id1", 0x18);
+    qdev_prop_set_uint16(dev, "id2", 0x00);
+    qdev_prop_set_uint16(dev, "id3", 0x00);
+    qdev_prop_set_string(dev, "name", name);
+    qdev_init_nofail(dev);
+
+    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, flashbase);
+}
+
+static void create_flash(const VirtBoardInfo *vbi)
+{
+    /* Create two flash devices to fill the VIRT_FLASH space in the memmap.
+     * Any file passed via -bios goes in the first of these.
+     */
+    hwaddr flashsize = vbi->memmap[VIRT_FLASH].size / 2;
+    hwaddr flashbase = vbi->memmap[VIRT_FLASH].base;
+    char *nodename;
+
+    if (bios_name) {
+        const char *fn;
+
+        if (drive_get(IF_PFLASH, 0, 0)) {
+            error_report("The contents of the first flash device may be "
+                         "specified with -bios or with -drive if=pflash... "
+                         "but you cannot use both options at once");
+            exit(1);
+        }
+        fn = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
+        if (!fn || load_image_targphys(fn, flashbase, flashsize) < 0) {
+            error_report("Could not load ROM image '%s'", bios_name);
+            exit(1);
+        }
+    }
+
+    create_one_flash("virt.flash0", flashbase, flashsize);
+    create_one_flash("virt.flash1", flashbase + flashsize, flashsize);
+
+    nodename = g_strdup_printf("/flash@%" PRIx64, flashbase);
+    qemu_fdt_add_subnode(vbi->fdt, nodename);
+    qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash");
+    qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
+                                 2, flashbase, 2, flashsize,
+                                 2, flashbase + flashsize, 2, flashsize);
+    qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
+    g_free(nodename);
+}
+
 static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size)
 {
     const VirtBoardInfo *board = (const VirtBoardInfo *)binfo;
@@ -510,10 +580,13 @@ static void machvirt_init(MachineState *machine)
     fdt_add_cpu_nodes(vbi);
     fdt_add_psci_node(vbi);
 
-    memory_region_init_ram(ram, NULL, "mach-virt.ram", machine->ram_size);
+    memory_region_init_ram(ram, NULL, "mach-virt.ram", machine->ram_size,
+                           &error_abort);
     vmstate_register_ram_global(ram);
     memory_region_add_subregion(sysmem, vbi->memmap[VIRT_MEM].base, ram);
 
+    create_flash(vbi);
+
     create_gic(vbi, pic);
 
     create_uart(vbi, pic);

hw/arm/xilinx_zynq.c

@@ -149,12 +149,14 @@ static void zynq_init(MachineState *machine)
     }
 
     /* DDR remapped to address zero.  */
-    memory_region_init_ram(ext_ram, NULL, "zynq.ext_ram", ram_size);
+    memory_region_init_ram(ext_ram, NULL, "zynq.ext_ram", ram_size,
+                           &error_abort);
     vmstate_register_ram_global(ext_ram);
     memory_region_add_subregion(address_space_mem, 0, ext_ram);
 
     /* 256K of on-chip memory */
-    memory_region_init_ram(ocm_ram, NULL, "zynq.ocm_ram", 256 << 10);
+    memory_region_init_ram(ocm_ram, NULL, "zynq.ocm_ram", 256 << 10,
+                           &error_abort);
     vmstate_register_ram_global(ocm_ram);
     memory_region_add_subregion(address_space_mem, 0xFFFC0000, ocm_ram);
 

hw/block/Makefile.objs

@@ -12,4 +12,4 @@ common-obj-$(CONFIG_NVME_PCI) += nvme.o
 obj-$(CONFIG_SH4) += tc58128.o
 
 obj-$(CONFIG_VIRTIO) += virtio-blk.o
-obj-$(CONFIG_VIRTIO_BLK_DATA_PLANE) += dataplane/
+obj-$(CONFIG_VIRTIO) += dataplane/

hw/block/dataplane/virtio-blk.c

@@ -164,8 +164,8 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
      * block jobs that can conflict.
      */
     if (bdrv_op_is_blocked(blk->conf.bs, BLOCK_OP_TYPE_DATAPLANE, &local_err)) {
-        error_report("cannot start dataplane thread: %s",
-                      error_get_pretty(local_err));
+        error_setg(errp, "cannot start dataplane thread: %s",
+                   error_get_pretty(local_err));
         error_free(local_err);
         return;
     }

hw/block/fdc.c

@@ -695,10 +695,34 @@ static const VMStateDescription vmstate_fdrive_media_rate = {
     }
 };
 
+static bool fdrive_perpendicular_needed(void *opaque)
+{
+    FDrive *drive = opaque;
+
+    return drive->perpendicular != 0;
+}
+
+static const VMStateDescription vmstate_fdrive_perpendicular = {
+    .name = "fdrive/perpendicular",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT8(perpendicular, FDrive),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static int fdrive_post_load(void *opaque, int version_id)
+{
+    fd_revalidate(opaque);
+    return 0;
+}
+
 static const VMStateDescription vmstate_fdrive = {
     .name = "fdrive",
     .version_id = 1,
     .minimum_version_id = 1,
+    .post_load = fdrive_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT8(head, FDrive),
         VMSTATE_UINT8(track, FDrive),
@@ -712,6 +736,9 @@ static const VMStateDescription vmstate_fdrive = {
         } , {
             .vmsd = &vmstate_fdrive_media_rate,
             .needed = &fdrive_media_rate_needed,
+        } , {
+            .vmsd = &vmstate_fdrive_perpendicular,
+            .needed = &fdrive_perpendicular_needed,
         } , {
             /* empty */
         }
@@ -734,6 +761,40 @@ static int fdc_post_load(void *opaque, int version_id)
     return 0;
 }
 
+static bool fdc_reset_sensei_needed(void *opaque)
+{
+    FDCtrl *s = opaque;
+
+    return s->reset_sensei != 0;
+}
+
+static const VMStateDescription vmstate_fdc_reset_sensei = {
+    .name = "fdc/reset_sensei",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32(reset_sensei, FDCtrl),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool fdc_result_timer_needed(void *opaque)
+{
+    FDCtrl *s = opaque;
+
+    return timer_pending(s->result_timer);
+}
+
+static const VMStateDescription vmstate_fdc_result_timer = {
+    .name = "fdc/result_timer",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_TIMER(result_timer, FDCtrl),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_fdc = {
     .name = "fdc",
     .version_id = 2,
@@ -770,6 +831,17 @@ static const VMStateDescription vmstate_fdc = {
         VMSTATE_STRUCT_ARRAY(drives, FDCtrl, MAX_FD, 1,
                              vmstate_fdrive, FDrive),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (VMStateSubsection[]) {
+        {
+            .vmsd = &vmstate_fdc_reset_sensei,
+            .needed = fdc_reset_sensei_needed,
+        } , {
+            .vmsd = &vmstate_fdc_result_timer,
+            .needed = fdc_result_timer_needed,
+        } , {
+            /* empty */
+        }
     }
 };
 
@@ -844,6 +916,8 @@ static void fdctrl_reset(FDCtrl *fdctrl, int do_irq)
     fdctrl->dor = FD_DOR_nRESET;
     fdctrl->dor |= (fdctrl->dma_chann != -1) ? FD_DOR_DMAEN : 0;
     fdctrl->msr = FD_MSR_RQM;
+    fdctrl->reset_sensei = 0;
+    timer_del(fdctrl->result_timer);
     /* FIFO state */
     fdctrl->data_pos = 0;
     fdctrl->data_len = 0;

hw/block/nvme.c

@@ -197,7 +197,7 @@ static void nvme_rw_cb(void *opaque, int ret)
     NvmeCtrl *n = sq->ctrl;
     NvmeCQueue *cq = n->cq[sq->cqid];
 
-    bdrv_acct_done(n->conf.bs, &req->acct);
+    block_acct_done(bdrv_get_stats(n->conf.bs), &req->acct);
     if (!ret) {
         req->status = NVME_SUCCESS;
     } else {
@@ -232,7 +232,7 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     assert((nlb << data_shift) == req->qsg.size);
 
     dma_acct_start(n->conf.bs, &req->acct, &req->qsg, is_write ?
-        BDRV_ACCT_WRITE : BDRV_ACCT_READ);
+        BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
     req->aiocb = is_write ?
         dma_bdrv_write(n->conf.bs, &req->qsg, aio_slba, nvme_rw_cb, req) :
         dma_bdrv_read(n->conf.bs, &req->qsg, aio_slba, nvme_rw_cb, req);

hw/block/onenand.c

@@ -789,7 +789,7 @@ static int onenand_initfn(SysBusDevice *sbd)
     s->otp = memset(g_malloc((64 + 2) << PAGE_SHIFT),
                     0xff, (64 + 2) << PAGE_SHIFT);
     memory_region_init_ram(&s->ram, OBJECT(s), "onenand.ram",
-                           0xc000 << s->shift);
+                           0xc000 << s->shift, &error_abort);
     vmstate_register_ram_global(&s->ram);
     ram = memory_region_get_ram_ptr(&s->ram);
     s->boot[0] = ram + (0x0000 << s->shift);

hw/block/pflash_cfi01.c

@@ -94,10 +94,13 @@ struct pflash_t {
     void *storage;
 };
 
+static int pflash_post_load(void *opaque, int version_id);
+
 static const VMStateDescription vmstate_pflash = {
     .name = "pflash_cfi01",
     .version_id = 1,
     .minimum_version_id = 1,
+    .post_load = pflash_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT8(wcycle, pflash_t),
         VMSTATE_UINT8(cmd, pflash_t),
@@ -209,11 +212,11 @@ static uint32_t pflash_devid_query(pflash_t *pfl, hwaddr offset)
     switch (boff & 0xFF) {
     case 0:
         resp = pfl->ident0;
-        DPRINTF("%s: Manufacturer Code %04x\n", __func__, ret);
+        DPRINTF("%s: Manufacturer Code %04x\n", __func__, resp);
         break;
     case 1:
         resp = pfl->ident1;
-        DPRINTF("%s: Device ID Code %04x\n", __func__, ret);
+        DPRINTF("%s: Device ID Code %04x\n", __func__, resp);
         break;
     default:
         DPRINTF("%s: Read Device Information offset=%x\n", __func__,
@@ -750,6 +753,7 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
     int ret;
     uint64_t blocks_per_device, device_len;
     int num_devices;
+    Error *local_err = NULL;
 
     total_len = pfl->sector_len * pfl->nb_blocs;
 
@@ -770,7 +774,12 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
     memory_region_init_rom_device(
         &pfl->mem, OBJECT(dev),
         pfl->be ? &pflash_cfi01_ops_be : &pflash_cfi01_ops_le, pfl,
-        pfl->name, total_len);
+        pfl->name, total_len, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
     vmstate_register_ram(&pfl->mem, DEVICE(pfl));
     pfl->storage = memory_region_get_ram_ptr(&pfl->mem);
     sysbus_init_mmio(SYS_BUS_DEVICE(dev), &pfl->mem);
@@ -982,3 +991,14 @@ MemoryRegion *pflash_cfi01_get_memory(pflash_t *fl)
 {
     return &fl->mem;
 }
+
+static int pflash_post_load(void *opaque, int version_id)
+{
+    pflash_t *pfl = opaque;
+
+    if (!pfl->ro) {
+        DPRINTF("%s: updating bdrv for %s\n", __func__, pfl->name);
+        pflash_update(pfl, 0, pfl->sector_len * pfl->nb_blocs);
+    }
+    return 0;
+}

hw/block/pflash_cfi02.c

@@ -597,6 +597,7 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
     pflash_t *pfl = CFI_PFLASH02(dev);
     uint32_t chip_len;
     int ret;
+    Error *local_err = NULL;
 
     chip_len = pfl->sector_len * pfl->nb_blocs;
     /* XXX: to be fixed */
@@ -608,7 +609,12 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
 
     memory_region_init_rom_device(&pfl->orig_mem, OBJECT(pfl), pfl->be ?
                                   &pflash_cfi02_ops_be : &pflash_cfi02_ops_le,
-                                  pfl, pfl->name, chip_len);
+                                  pfl, pfl->name, chip_len, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
     vmstate_register_ram(&pfl->orig_mem, DEVICE(pfl));
     pfl->storage = memory_region_get_ram_ptr(&pfl->orig_mem);
     pfl->chip_len = chip_len;

hw/block/virtio-blk.c

@@ -18,10 +18,8 @@
 #include "hw/block/block.h"
 #include "sysemu/blockdev.h"
 #include "hw/virtio/virtio-blk.h"
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
-# include "dataplane/virtio-blk.h"
-# include "migration/migration.h"
-#endif
+#include "dataplane/virtio-blk.h"
+#include "migration/migration.h"
 #include "block/scsi.h"
 #ifdef __linux__
 # include <scsi/sg.h>
@@ -74,7 +72,7 @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
         s->rq = req;
     } else if (action == BLOCK_ERROR_ACTION_REPORT) {
         virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
-        bdrv_acct_done(s->bs, &req->acct);
+        block_acct_done(bdrv_get_stats(s->bs), &req->acct);
         virtio_blk_free_request(req);
     }
 
@@ -96,7 +94,7 @@ static void virtio_blk_rw_complete(void *opaque, int ret)
     }
 
     virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
-    bdrv_acct_done(req->dev->bs, &req->acct);
+    block_acct_done(bdrv_get_stats(req->dev->bs), &req->acct);
     virtio_blk_free_request(req);
 }
 
@@ -111,7 +109,7 @@ static void virtio_blk_flush_complete(void *opaque, int ret)
     }
 
     virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
-    bdrv_acct_done(req->dev->bs, &req->acct);
+    block_acct_done(bdrv_get_stats(req->dev->bs), &req->acct);
     virtio_blk_free_request(req);
 }
 
@@ -279,7 +277,8 @@ void virtio_submit_multiwrite(BlockDriverState *bs, MultiReqBuffer *mrb)
 
 static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
 {
-    bdrv_acct_start(req->dev->bs, &req->acct, 0, BDRV_ACCT_FLUSH);
+    block_acct_start(bdrv_get_stats(req->dev->bs), &req->acct, 0,
+                     BLOCK_ACCT_FLUSH);
 
     /*
      * Make sure all outstanding writes are posted to the backing device.
@@ -322,7 +321,8 @@ static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb)
         return;
     }
 
-    bdrv_acct_start(req->dev->bs, &req->acct, req->qiov.size, BDRV_ACCT_WRITE);
+    block_acct_start(bdrv_get_stats(req->dev->bs), &req->acct, req->qiov.size,
+                     BLOCK_ACCT_WRITE);
 
     if (mrb->num_writes == 32) {
         virtio_submit_multiwrite(req->dev->bs, mrb);
@@ -353,7 +353,8 @@ static void virtio_blk_handle_read(VirtIOBlockReq *req)
         return;
     }
 
-    bdrv_acct_start(req->dev->bs, &req->acct, req->qiov.size, BDRV_ACCT_READ);
+    block_acct_start(bdrv_get_stats(req->dev->bs), &req->acct, req->qiov.size,
+                     BLOCK_ACCT_READ);
     bdrv_aio_readv(req->dev->bs, sector, &req->qiov,
                    req->qiov.size / BDRV_SECTOR_SIZE,
                    virtio_blk_rw_complete, req);
@@ -432,7 +433,6 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
         .num_writes = 0,
     };
 
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
      * dataplane here instead of waiting for .set_status().
      */
@@ -440,7 +440,6 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
         virtio_blk_data_plane_start(s->dataplane);
         return;
     }
-#endif
 
     while ((req = virtio_blk_get_request(s))) {
         virtio_blk_handle_request(req, &mrb);
@@ -497,11 +496,9 @@ static void virtio_blk_reset(VirtIODevice *vdev)
 {
     VirtIOBlock *s = VIRTIO_BLK(vdev);
 
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     if (s->dataplane) {
         virtio_blk_data_plane_stop(s->dataplane);
     }
-#endif
 
     /*
      * This should cancel pending requests, but can't do nicely until there
@@ -591,12 +588,10 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
     VirtIOBlock *s = VIRTIO_BLK(vdev);
     uint32_t features;
 
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     if (s->dataplane && !(status & (VIRTIO_CONFIG_S_DRIVER |
                                     VIRTIO_CONFIG_S_DRIVER_OK))) {
         virtio_blk_data_plane_stop(s->dataplane);
     }
-#endif
 
     if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
         return;
@@ -691,7 +686,6 @@ static const BlockDevOps virtio_block_ops = {
     .resize_cb = virtio_blk_resize,
 };
 
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
 /* Disable dataplane thread during live migration since it does not
  * update the dirty memory bitmap yet.
  */
@@ -722,7 +716,6 @@ static void virtio_blk_migration_state_changed(Notifier *notifier, void *data)
         }
     }
 }
-#endif /* CONFIG_VIRTIO_BLK_DATA_PLANE */
 
 static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
 {
@@ -759,7 +752,6 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
 
     s->vq = virtio_add_queue(vdev, 128, virtio_blk_handle_output);
     s->complete_request = virtio_blk_complete_request;
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     virtio_blk_data_plane_create(vdev, blk, &s->dataplane, &err);
     if (err != NULL) {
         error_propagate(errp, err);
@@ -768,7 +760,6 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     }
     s->migration_state_notifier.notify = virtio_blk_migration_state_changed;
     add_migration_state_change_notifier(&s->migration_state_notifier);
-#endif
 
     s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
     register_savevm(dev, "virtio-blk", virtio_blk_id++, 2,
@@ -786,11 +777,9 @@ static void virtio_blk_device_unrealize(DeviceState *dev, Error **errp)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOBlock *s = VIRTIO_BLK(dev);
 
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     remove_migration_state_change_notifier(&s->migration_state_notifier);
     virtio_blk_data_plane_destroy(s->dataplane);
     s->dataplane = NULL;
-#endif
     qemu_del_vm_change_state_handler(s->change);
     unregister_savevm(dev, "virtio-blk", s);
     blockdev_mark_auto_del(s->bs);
@@ -815,9 +804,7 @@ static Property virtio_blk_properties[] = {
 #ifdef __linux__
     DEFINE_PROP_BIT("scsi", VirtIOBlock, blk.scsi, 0, true),
 #endif
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     DEFINE_PROP_BIT("x-data-plane", VirtIOBlock, blk.data_plane, 0, false),
-#endif
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/block/xen_disk.c

@@ -493,7 +493,7 @@ static void qemu_aio_complete(void *opaque, int ret)
             break;
         }
     case BLKIF_OP_READ:
-        bdrv_acct_done(ioreq->blkdev->bs, &ioreq->acct);
+        block_acct_done(bdrv_get_stats(ioreq->blkdev->bs), &ioreq->acct);
         break;
     case BLKIF_OP_DISCARD:
     default:
@@ -518,7 +518,8 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
 
     switch (ioreq->req.operation) {
     case BLKIF_OP_READ:
-        bdrv_acct_start(blkdev->bs, &ioreq->acct, ioreq->v.size, BDRV_ACCT_READ);
+        block_acct_start(bdrv_get_stats(blkdev->bs), &ioreq->acct,
+                         ioreq->v.size, BLOCK_ACCT_READ);
         ioreq->aio_inflight++;
         bdrv_aio_readv(blkdev->bs, ioreq->start / BLOCK_SIZE,
                        &ioreq->v, ioreq->v.size / BLOCK_SIZE,
@@ -530,7 +531,8 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
             break;
         }
 
-        bdrv_acct_start(blkdev->bs, &ioreq->acct, ioreq->v.size, BDRV_ACCT_WRITE);
+        block_acct_start(bdrv_get_stats(blkdev->bs), &ioreq->acct,
+                         ioreq->v.size, BLOCK_ACCT_WRITE);
         ioreq->aio_inflight++;
         bdrv_aio_writev(blkdev->bs, ioreq->start / BLOCK_SIZE,
                         &ioreq->v, ioreq->v.size / BLOCK_SIZE,
@@ -852,28 +854,25 @@ static int blk_connect(struct XenDevice *xendev)
     blkdev->dinfo = drive_get(IF_XEN, 0, index);
     if (!blkdev->dinfo) {
         Error *local_err = NULL;
+        BlockDriver *drv;
+
         /* setup via xenbus -> create new block driver instance */
         xen_be_printf(&blkdev->xendev, 2, "create new bdrv (xenbus setup)\n");
-        blkdev->bs = bdrv_new(blkdev->dev, &local_err);
-        if (local_err) {
-            blkdev->bs = NULL;
-        }
-        if (blkdev->bs) {
-            BlockDriver *drv = bdrv_find_whitelisted_format(blkdev->fileproto,
-                                                           readonly);
-            if (bdrv_open(&blkdev->bs, blkdev->filename, NULL, NULL, qflags,
-                          drv, &local_err) != 0)
-            {
-                xen_be_printf(&blkdev->xendev, 0, "error: %s\n",
-                              error_get_pretty(local_err));
-                error_free(local_err);
-                bdrv_unref(blkdev->bs);
-                blkdev->bs = NULL;
-            }
-        }
+        blkdev->bs = bdrv_new(blkdev->dev, NULL);
         if (!blkdev->bs) {
             return -1;
         }
+
+        drv = bdrv_find_whitelisted_format(blkdev->fileproto, readonly);
+        if (bdrv_open(&blkdev->bs, blkdev->filename, NULL, NULL, qflags,
+                      drv, &local_err) != 0) {
+            xen_be_printf(&blkdev->xendev, 0, "error: %s\n",
+                          error_get_pretty(local_err));
+            error_free(local_err);
+            bdrv_unref(blkdev->bs);
+            blkdev->bs = NULL;
+            return -1;
+        }
     } else {
         /* setup via qemu cmdline -> already setup for us */
         xen_be_printf(&blkdev->xendev, 2, "get configured bdrv (cmdline setup)\n");

hw/char/parallel.c

@@ -477,6 +477,23 @@ static const MemoryRegionPortio isa_parallel_portio_sw_list[] = {
     PORTIO_END_OF_LIST(),
 };
 
+
+static const VMStateDescription vmstate_parallel_isa = {
+    .name = "parallel_isa",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields      = (VMStateField[]) {
+        VMSTATE_UINT8(state.dataw, ISAParallelState),
+        VMSTATE_UINT8(state.datar, ISAParallelState),
+        VMSTATE_UINT8(state.status, ISAParallelState),
+        VMSTATE_UINT8(state.control, ISAParallelState),
+        VMSTATE_INT32(state.irq_pending, ISAParallelState),
+        VMSTATE_INT32(state.epp_timeout, ISAParallelState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+
 static void parallel_isa_realizefn(DeviceState *dev, Error **errp)
 {
     static int index;
@@ -606,6 +623,7 @@ static void parallel_isa_class_initfn(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     dc->realize = parallel_isa_realizefn;
+    dc->vmsd = &vmstate_parallel_isa;
     dc->props = parallel_isa_properties;
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
 }

hw/char/serial.c

@@ -272,6 +272,36 @@ static gboolean serial_xmit(GIOChannel *chan, GIOCondition cond, void *opaque)
 }
 
 
+/* Setter for FCR.
+   is_load flag means, that value is set while loading VM state
+   and interrupt should not be invoked */
+static void serial_write_fcr(SerialState *s, uint8_t val)
+{
+    /* Set fcr - val only has the bits that are supposed to "stick" */
+    s->fcr = val;
+
+    if (val & UART_FCR_FE) {
+        s->iir |= UART_IIR_FE;
+        /* Set recv_fifo trigger Level */
+        switch (val & 0xC0) {
+        case UART_FCR_ITL_1:
+            s->recv_fifo_itl = 1;
+            break;
+        case UART_FCR_ITL_2:
+            s->recv_fifo_itl = 4;
+            break;
+        case UART_FCR_ITL_3:
+            s->recv_fifo_itl = 8;
+            break;
+        case UART_FCR_ITL_4:
+            s->recv_fifo_itl = 14;
+            break;
+        }
+    } else {
+        s->iir &= ~UART_IIR_FE;
+    }
+}
+
 static void serial_ioport_write(void *opaque, hwaddr addr, uint64_t val,
                                 unsigned size)
 {
@@ -327,20 +357,16 @@ static void serial_ioport_write(void *opaque, hwaddr addr, uint64_t val,
         }
         break;
     case 2:
-        val = val & 0xFF;
-
-        if (s->fcr == val)
-            break;
-
         /* Did the enable/disable flag change? If so, make sure FIFOs get flushed */
-        if ((val ^ s->fcr) & UART_FCR_FE)
+        if ((val ^ s->fcr) & UART_FCR_FE) {
             val |= UART_FCR_XFR | UART_FCR_RFR;
+        }
 
         /* FIFO clear */
 
         if (val & UART_FCR_RFR) {
             timer_del(s->fifo_timeout_timer);
-            s->timeout_ipending=0;
+            s->timeout_ipending = 0;
             fifo8_reset(&s->recv_fifo);
         }
 
@@ -348,28 +374,7 @@ static void serial_ioport_write(void *opaque, hwaddr addr, uint64_t val,
             fifo8_reset(&s->xmit_fifo);
         }
 
-        if (val & UART_FCR_FE) {
-            s->iir |= UART_IIR_FE;
-            /* Set recv_fifo trigger Level */
-            switch (val & 0xC0) {
-            case UART_FCR_ITL_1:
-                s->recv_fifo_itl = 1;
-                break;
-            case UART_FCR_ITL_2:
-                s->recv_fifo_itl = 4;
-                break;
-            case UART_FCR_ITL_3:
-                s->recv_fifo_itl = 8;
-                break;
-            case UART_FCR_ITL_4:
-                s->recv_fifo_itl = 14;
-                break;
-            }
-        } else
-            s->iir &= ~UART_IIR_FE;
-
-        /* Set fcr - or at least the bits in it that are supposed to "stick" */
-        s->fcr = val & 0xC9;
+        serial_write_fcr(s, val & 0xC9);
         serial_update_irq(s);
         break;
     case 3:
@@ -590,6 +595,14 @@ static void serial_pre_save(void *opaque)
     s->fcr_vmstate = s->fcr;
 }
 
+static int serial_pre_load(void *opaque)
+{
+    SerialState *s = opaque;
+    s->thr_ipending = -1;
+    s->poll_msl = -1;
+    return 0;
+}
+
 static int serial_post_load(void *opaque, int version_id)
 {
     SerialState *s = opaque;
@@ -597,17 +610,139 @@ static int serial_post_load(void *opaque, int version_id)
     if (version_id < 3) {
         s->fcr_vmstate = 0;
     }
+    if (s->thr_ipending == -1) {
+        s->thr_ipending = ((s->iir & UART_IIR_ID) == UART_IIR_THRI);
+    }
+    s->last_break_enable = (s->lcr >> 6) & 1;
     /* Initialize fcr via setter to perform essential side-effects */
-    serial_ioport_write(s, 0x02, s->fcr_vmstate, 1);
+    serial_write_fcr(s, s->fcr_vmstate);
     serial_update_parameters(s);
     return 0;
 }
 
+static bool serial_thr_ipending_needed(void *opaque)
+{
+    SerialState *s = opaque;
+    bool expected_value = ((s->iir & UART_IIR_ID) == UART_IIR_THRI);
+    return s->thr_ipending != expected_value;
+}
+
+const VMStateDescription vmstate_serial_thr_ipending = {
+    .name = "serial/thr_ipending",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32(thr_ipending, SerialState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool serial_tsr_needed(void *opaque)
+{
+    SerialState *s = (SerialState *)opaque;
+    return s->tsr_retry != 0;
+}
+
+const VMStateDescription vmstate_serial_tsr = {
+    .name = "serial/tsr",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32(tsr_retry, SerialState),
+        VMSTATE_UINT8(thr, SerialState),
+        VMSTATE_UINT8(tsr, SerialState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool serial_recv_fifo_needed(void *opaque)
+{
+    SerialState *s = (SerialState *)opaque;
+    return !fifo8_is_empty(&s->recv_fifo);
+
+}
+
+const VMStateDescription vmstate_serial_recv_fifo = {
+    .name = "serial/recv_fifo",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_STRUCT(recv_fifo, SerialState, 1, vmstate_fifo8, Fifo8),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool serial_xmit_fifo_needed(void *opaque)
+{
+    SerialState *s = (SerialState *)opaque;
+    return !fifo8_is_empty(&s->xmit_fifo);
+}
+
+const VMStateDescription vmstate_serial_xmit_fifo = {
+    .name = "serial/xmit_fifo",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_STRUCT(xmit_fifo, SerialState, 1, vmstate_fifo8, Fifo8),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool serial_fifo_timeout_timer_needed(void *opaque)
+{
+    SerialState *s = (SerialState *)opaque;
+    return timer_pending(s->fifo_timeout_timer);
+}
+
+const VMStateDescription vmstate_serial_fifo_timeout_timer = {
+    .name = "serial/fifo_timeout_timer",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_TIMER(fifo_timeout_timer, SerialState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool serial_timeout_ipending_needed(void *opaque)
+{
+    SerialState *s = (SerialState *)opaque;
+    return s->timeout_ipending != 0;
+}
+
+const VMStateDescription vmstate_serial_timeout_ipending = {
+    .name = "serial/timeout_ipending",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32(timeout_ipending, SerialState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool serial_poll_needed(void *opaque)
+{
+    SerialState *s = (SerialState *)opaque;
+    return s->poll_msl >= 0;
+}
+
+const VMStateDescription vmstate_serial_poll = {
+    .name = "serial/poll",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32(poll_msl, SerialState),
+        VMSTATE_TIMER(modem_status_poll, SerialState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 const VMStateDescription vmstate_serial = {
     .name = "serial",
     .version_id = 3,
     .minimum_version_id = 2,
     .pre_save = serial_pre_save,
+    .pre_load = serial_pre_load,
     .post_load = serial_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT16_V(divider, SerialState, 2),
@@ -621,6 +756,32 @@ const VMStateDescription vmstate_serial = {
         VMSTATE_UINT8(scr, SerialState),
         VMSTATE_UINT8_V(fcr_vmstate, SerialState, 3),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (VMStateSubsection[]) {
+        {
+            .vmsd = &vmstate_serial_thr_ipending,
+            .needed = &serial_thr_ipending_needed,
+        } , {
+            .vmsd = &vmstate_serial_tsr,
+            .needed = &serial_tsr_needed,
+        } , {
+            .vmsd = &vmstate_serial_recv_fifo,
+            .needed = &serial_recv_fifo_needed,
+        } , {
+            .vmsd = &vmstate_serial_xmit_fifo,
+            .needed = &serial_xmit_fifo_needed,
+        } , {
+            .vmsd = &vmstate_serial_fifo_timeout_timer,
+            .needed = &serial_fifo_timeout_timer_needed,
+        } , {
+            .vmsd = &vmstate_serial_timeout_ipending,
+            .needed = &serial_timeout_ipending_needed,
+        } , {
+            .vmsd = &vmstate_serial_poll,
+            .needed = &serial_poll_needed,
+        } , {
+            /* empty */
+        }
     }
 };
 
@@ -642,6 +803,10 @@ static void serial_reset(void *opaque)
     s->char_transmit_time = (get_ticks_per_sec() / 9600) * 10;
     s->poll_msl = 0;
 
+    s->timeout_ipending = 0;
+    timer_del(s->fifo_timeout_timer);
+    timer_del(s->modem_status_poll);
+
     fifo8_reset(&s->recv_fifo);
     fifo8_reset(&s->xmit_fifo);
 
@@ -650,6 +815,9 @@ static void serial_reset(void *opaque)
     s->thr_ipending = 0;
     s->last_break_enable = 0;
     qemu_irq_lower(s->irq);
+
+    serial_update_msl(s);
+    s->msr &= ~UART_MSR_ANY_DELTA;
 }
 
 void serial_realize_core(SerialState *s, Error **errp)
@@ -668,6 +836,7 @@ void serial_realize_core(SerialState *s, Error **errp)
                           serial_event, s);
     fifo8_create(&s->recv_fifo, UART_FIFO_LENGTH);
     fifo8_create(&s->xmit_fifo, UART_FIFO_LENGTH);
+    serial_reset(s);
 }
 
 void serial_exit_core(SerialState *s)
@@ -779,7 +948,5 @@ SerialState *serial_mm_init(MemoryRegion *address_space,
     memory_region_init_io(&s->io, NULL, &serial_mm_ops[end], s,
                           "serial", 8 << it_shift);
     memory_region_add_subregion(address_space, base, &s->io);
-
-    serial_update_msl(s);
     return s;
 }

hw/core/loader.c

@@ -89,6 +89,27 @@ int load_image(const char *filename, uint8_t *addr)
     return size;
 }
 
+/* return the size or -1 if error */
+ssize_t load_image_size(const char *filename, void *addr, size_t size)
+{
+    int fd;
+    ssize_t actsize;
+
+    fd = open(filename, O_RDONLY | O_BINARY);
+    if (fd < 0) {
+        return -1;
+    }
+
+    actsize = read(fd, addr, size);
+    if (actsize < 0) {
+        close(fd);
+        return -1;
+    }
+    close(fd);
+
+    return actsize;
+}
+
 /* read()-like version */
 ssize_t read_targphys(const char *name,
                       int fd, hwaddr dst_addr, size_t nbytes)
@@ -680,7 +701,7 @@ static void *rom_set_mr(Rom *rom, Object *owner, const char *name)
     void *data;
 
     rom->mr = g_malloc(sizeof(*rom->mr));
-    memory_region_init_ram(rom->mr, owner, name, rom->datasize);
+    memory_region_init_ram(rom->mr, owner, name, rom->datasize, &error_abort);
     memory_region_set_readonly(rom->mr, true);
     vmstate_register_ram_global(rom->mr);
 

hw/core/machine.c

@@ -24,6 +24,7 @@ static void machine_set_accel(Object *obj, const char *value, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->accel);
     ms->accel = g_strdup(value);
 }
 
@@ -79,6 +80,7 @@ static void machine_set_kernel(Object *obj, const char *value, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->kernel_filename);
     ms->kernel_filename = g_strdup(value);
 }
 
@@ -93,6 +95,7 @@ static void machine_set_initrd(Object *obj, const char *value, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->initrd_filename);
     ms->initrd_filename = g_strdup(value);
 }
 
@@ -107,6 +110,7 @@ static void machine_set_append(Object *obj, const char *value, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->kernel_cmdline);
     ms->kernel_cmdline = g_strdup(value);
 }
 
@@ -121,6 +125,7 @@ static void machine_set_dtb(Object *obj, const char *value, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->dtb);
     ms->dtb = g_strdup(value);
 }
 
@@ -135,6 +140,7 @@ static void machine_set_dumpdtb(Object *obj, const char *value, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->dumpdtb);
     ms->dumpdtb = g_strdup(value);
 }
 
@@ -176,6 +182,7 @@ static void machine_set_dt_compatible(Object *obj, const char *value, Error **er
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->dt_compatible);
     ms->dt_compatible = g_strdup(value);
 }
 
@@ -232,6 +239,7 @@ static void machine_set_firmware(Object *obj, const char *value, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
 
+    g_free(ms->firmware);
     ms->firmware = g_strdup(value);
 }
 

hw/core/qdev-properties-system.c

@@ -388,28 +388,12 @@ void qdev_set_nic_properties(DeviceState *dev, NICInfo *nd)
 static int qdev_add_one_global(QemuOpts *opts, void *opaque)
 {
     GlobalProperty *g;
-    ObjectClass *oc;
 
     g = g_malloc0(sizeof(*g));
     g->driver   = qemu_opt_get(opts, "driver");
     g->property = qemu_opt_get(opts, "property");
     g->value    = qemu_opt_get(opts, "value");
-    oc = object_class_dynamic_cast(object_class_by_name(g->driver),
-                                   TYPE_DEVICE);
-    if (oc) {
-        DeviceClass *dc = DEVICE_CLASS(oc);
-
-        if (dc->hotpluggable) {
-            /* If hotpluggable then skip not_used checking. */
-            g->not_used = false;
-        } else {
-            /* Maybe a typo. */
-            g->not_used = true;
-        }
-    } else {
-        /* Maybe a typo. */
-        g->not_used = true;
-    }
+    g->user_provided = true;
     qdev_prop_register_global(g);
     return 0;
 }

hw/core/qdev-properties.c

@@ -955,19 +955,35 @@ void qdev_prop_register_global_list(GlobalProperty *props)
     }
 }
 
-int qdev_prop_check_global(void)
+int qdev_prop_check_globals(void)
 {
     GlobalProperty *prop;
     int ret = 0;
 
     QTAILQ_FOREACH(prop, &global_props, next) {
-        if (!prop->not_used) {
+        ObjectClass *oc;
+        DeviceClass *dc;
+        if (prop->used) {
+            continue;
+        }
+        if (!prop->user_provided) {
+            continue;
+        }
+        oc = object_class_by_name(prop->driver);
+        oc = object_class_dynamic_cast(oc, TYPE_DEVICE);
+        if (!oc) {
+            error_report("Warning: global %s.%s has invalid class name",
+                       prop->driver, prop->property);
+            ret = 1;
+            continue;
+        }
+        dc = DEVICE_CLASS(oc);
+        if (!dc->hotpluggable && !prop->used) {
+            error_report("Warning: global %s.%s=%s not used",
+                       prop->driver, prop->property, prop->value);
+            ret = 1;
             continue;
         }
-        ret = 1;
-        error_report("Warning: \"-global %s.%s=%s\" not used",
-                     prop->driver, prop->property, prop->value);
-
     }
     return ret;
 }
@@ -983,7 +999,7 @@ void qdev_prop_set_globals_for_type(DeviceState *dev, const char *typename,
         if (strcmp(typename, prop->driver) != 0) {
             continue;
         }
-        prop->not_used = false;
+        prop->used = true;
         object_property_parse(OBJECT(dev), prop->value, prop->property, &err);
         if (err != NULL) {
             error_propagate(errp, err);

hw/cris/axis_dev88.c

@@ -270,13 +270,15 @@ void axisdev88_init(MachineState *machine)
     env = &cpu->env;
 
     /* allocate RAM */
-    memory_region_init_ram(phys_ram, NULL, "axisdev88.ram", ram_size);
+    memory_region_init_ram(phys_ram, NULL, "axisdev88.ram", ram_size,
+                           &error_abort);
     vmstate_register_ram_global(phys_ram);
     memory_region_add_subregion(address_space_mem, 0x40000000, phys_ram);
 
     /* The ETRAX-FS has 128Kb on chip ram, the docs refer to it as the 
        internal memory.  */
-    memory_region_init_ram(phys_intmem, NULL, "axisdev88.chipram", INTMEM_SIZE);
+    memory_region_init_ram(phys_intmem, NULL, "axisdev88.chipram", INTMEM_SIZE,
+                           &error_abort);
     vmstate_register_ram_global(phys_intmem);
     memory_region_add_subregion(address_space_mem, 0x38000000, phys_intmem);
 

hw/display/blizzard.c

@@ -134,14 +134,6 @@ static const int blizzard_iformat_bpp[0x10] = {
     0, 0, 0, 0, 0, 0,
 };
 
-static inline void blizzard_rgb2yuv(int r, int g, int b,
-                int *y, int *u, int *v)
-{
-    *y = 0x10 + ((0x838 * r + 0x1022 * g + 0x322 * b) >> 13);
-    *u = 0x80 + ((0xe0e * b - 0x04c1 * r - 0x94e * g) >> 13);
-    *v = 0x80 + ((0xe0e * r - 0x0bc7 * g - 0x247 * b) >> 13);
-}
-
 static void blizzard_window(BlizzardState *s)
 {
     DisplaySurface *surface = qemu_console_surface(s->con);

hw/display/cg3.c

@@ -279,7 +279,8 @@ static void cg3_initfn(Object *obj)
     SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
     CG3State *s = CG3(obj);
 
-    memory_region_init_ram(&s->rom, NULL, "cg3.prom", FCODE_MAX_ROM_SIZE);
+    memory_region_init_ram(&s->rom, NULL, "cg3.prom", FCODE_MAX_ROM_SIZE,
+                           &error_abort);
     memory_region_set_readonly(&s->rom, true);
     sysbus_init_mmio(sbd, &s->rom);
 
@@ -306,7 +307,8 @@ static void cg3_realizefn(DeviceState *dev, Error **errp)
         }
     }
 
-    memory_region_init_ram(&s->vram_mem, NULL, "cg3.vram", s->vram_size);
+    memory_region_init_ram(&s->vram_mem, NULL, "cg3.vram", s->vram_size,
+                           &error_abort);
     vmstate_register_ram_global(&s->vram_mem);
     sysbus_init_mmio(sbd, &s->vram_mem);