ui/console: add escape sequence \e[5, 6n

Add support of escape sequence "\e[5n" and "\e[6n" to console.
"\e[5n" reports status of console and it always succeed
in virtual console.
"\e[6n" reports now cursor position in console.

Signed-off-by: Ren Kimura <rkx1209dev@gmail.com>
Message-id: 1457466681-7714-2-git-send-email-rkx1209dev@gmail.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

MAINTAINERS

@@ -363,6 +363,7 @@ M: Dmitry Solodkiy <d.solodkiy@samsung.com>
 L: qemu-arm@nongnu.org
 S: Maintained
 F: hw/*/exynos*
+F: include/hw/arm/exynos4210.h
 
 Calxeda Highbank
 M: Rob Herring <robh@kernel.org>
@@ -390,6 +391,7 @@ L: qemu-arm@nongnu.org
 S: Odd fixes
 F: hw/*/imx*
 F: hw/arm/kzm.c
+F: include/hw/arm/fsl-imx31.h
 
 Integrator CP
 M: Peter Maydell <peter.maydell@linaro.org>
@@ -432,6 +434,7 @@ F: hw/arm/spitz.c
 F: hw/arm/tosa.c
 F: hw/arm/z2.c
 F: hw/*/pxa2xx*
+F: include/hw/arm/pxa.h
 
 Stellaris
 M: Peter Maydell <peter.maydell@linaro.org>
@@ -653,12 +656,6 @@ F: hw/*/grlib*
 
 S390 Machines
 -------------
-S390 Virtio
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: hw/s390x/s390-*.c
-X: hw/s390x/*pci*.[hc]
-
 S390 Virtio-ccw
 M: Cornelia Huck <cornelia.huck@de.ibm.com>
 M: Christian Borntraeger <borntraeger@de.ibm.com>
@@ -666,7 +663,6 @@ M: Alexander Graf <agraf@suse.de>
 S: Supported
 F: hw/char/sclp*.[hc]
 F: hw/s390x/
-X: hw/s390x/s390-virtio-bus.[ch]
 F: include/hw/s390x/
 F: pc-bios/s390-ccw/
 F: hw/watchdog/wdt_diag288.c
@@ -768,6 +764,7 @@ OMAP
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/*/omap*
+F: include/hw/arm/omap.h
 
 IPack
 M: Alberto Garcia <berto@igalia.com>
@@ -853,6 +850,10 @@ M: Gerd Hoffmann <kraxel@redhat.com>
 S: Maintained
 F: hw/usb/*
 F: tests/usb-*-test.c
+F: docs/usb2.txt
+F: docs/usb-storage.txt
+F: include/hw/usb.h
+F: include/hw/usb/
 
 USB (serial adapter)
 M: Gerd Hoffmann <kraxel@redhat.com>
@@ -920,6 +921,7 @@ M: Amit Shah <amit.shah@redhat.com>
 S: Supported
 F: hw/virtio/virtio-rng.c
 F: include/hw/virtio/virtio-rng.h
+F: include/sysemu/rng*.h
 F: backends/rng*.c
 
 nvme
@@ -1083,6 +1085,7 @@ SPICE
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Supported
 F: include/ui/qemu-spice.h
+F: include/ui/spice-display.h
 F: ui/spice-*.c
 F: audio/spiceaudio.c
 F: hw/display/qxl*
@@ -1091,6 +1094,7 @@ Graphics
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Odd Fixes
 F: ui/
+F: include/ui/
 
 Cocoa graphics
 M: Andreas Färber <andreas.faerber@web.de>
@@ -1241,6 +1245,7 @@ F: include/migration/
 F: migration/
 F: scripts/vmstate-static-checker.py
 F: tests/vmstate-static-checker-data/
+F: docs/migration.txt
 
 Seccomp
 M: Eduardo Otubo <eduardo.otubo@profitbricks.com>
@@ -1283,6 +1288,15 @@ S: Maintained
 F: include/qemu/sockets.h
 F: util/qemu-sockets.c
 
+Throttling infrastructure
+M: Alberto Garcia <berto@igalia.com>
+S: Supported
+F: block/throttle-groups.c
+F: include/block/throttle-groups.h
+F: include/qemu/throttle.h
+F: util/throttle.c
+L: qemu-block@nongnu.org
+
 Usermode Emulation
 ------------------
 Overall

Makefile

@@ -391,7 +391,7 @@ bepo    cz
 ifdef INSTALL_BLOBS
 BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin vgabios-virtio.bin \
-acpi-dsdt.aml q35-acpi-dsdt.aml \
+acpi-dsdt.aml \
 ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \

audio/audio.h

@@ -24,7 +24,6 @@
 #ifndef QEMU_AUDIO_H
 #define QEMU_AUDIO_H
 
-#include "config-host.h"
 #include "qemu/queue.h"
 
 typedef void (*audio_callback_fn) (void *opaque, int avail);

backends/baum.c

@@ -567,7 +567,7 @@ static CharDriverState *chr_baum_init(const char *id,
                                       ChardevReturn *ret,
                                       Error **errp)
 {
-    ChardevCommon *common = qapi_ChardevDummy_base(backend->u.braille);
+    ChardevCommon *common = backend->u.braille;
     BaumDriverState *baum;
     CharDriverState *chr;
     brlapi_handle_t *handle;

backends/msmouse.c

@@ -68,7 +68,7 @@ static CharDriverState *qemu_chr_open_msmouse(const char *id,
                                               ChardevReturn *ret,
                                               Error **errp)
 {
-    ChardevCommon *common = qapi_ChardevDummy_base(backend->u.msmouse);
+    ChardevCommon *common = backend->u.msmouse;
     CharDriverState *chr;
 
     chr = qemu_chr_alloc(common, errp);

backends/rng-egd.c

@@ -25,33 +25,12 @@ typedef struct RngEgd
 
     CharDriverState *chr;
     char *chr_name;
-
-    GSList *requests;
 } RngEgd;
 
-typedef struct RngRequest
+static void rng_egd_request_entropy(RngBackend *b, RngRequest *req)
-{
-    EntropyReceiveFunc *receive_entropy;
-    uint8_t *data;
-    void *opaque;
-    size_t offset;
-    size_t size;
-} RngRequest;
-
-static void rng_egd_request_entropy(RngBackend *b, size_t size,
-                                    EntropyReceiveFunc *receive_entropy,
-                                    void *opaque)
 {
     RngEgd *s = RNG_EGD(b);
-    RngRequest *req;
+    size_t size = req->size;
-
-    req = g_malloc(sizeof(*req));
-
-    req->offset = 0;
-    req->size = size;
-    req->receive_entropy = receive_entropy;
-    req->opaque = opaque;
-    req->data = g_malloc(req->size);
 
     while (size > 0) {
         uint8_t header[2];
@@ -65,14 +44,6 @@ static void rng_egd_request_entropy(RngBackend *b, size_t size,
 
         size -= len;
     }
-
-    s->requests = g_slist_append(s->requests, req);
-}
-
-static void rng_egd_free_request(RngRequest *req)
-{
-    g_free(req->data);
-    g_free(req);
 }
 
 static int rng_egd_chr_can_read(void *opaque)
@@ -81,7 +52,7 @@ static int rng_egd_chr_can_read(void *opaque)
     GSList *i;
     int size = 0;
 
-    for (i = s->requests; i; i = i->next) {
+    for (i = s->parent.requests; i; i = i->next) {
         RngRequest *req = i->data;
         size += req->size - req->offset;
     }
@@ -94,8 +65,8 @@ static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
     RngEgd *s = RNG_EGD(opaque);
     size_t buf_offset = 0;
 
-    while (size > 0 && s->requests) {
+    while (size > 0 && s->parent.requests) {
-        RngRequest *req = s->requests->data;
+        RngRequest *req = s->parent.requests->data;
         int len = MIN(size, req->size - req->offset);
 
         memcpy(req->data + req->offset, buf + buf_offset, len);
@@ -104,38 +75,13 @@ static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
         size -= len;
 
         if (req->offset == req->size) {
-            s->requests = g_slist_remove_link(s->requests, s->requests);
-
             req->receive_entropy(req->opaque, req->data, req->size);
 
-            rng_egd_free_request(req);
+            rng_backend_finalize_request(&s->parent, req);
         }
     }
 }
 
-static void rng_egd_free_requests(RngEgd *s)
-{
-    GSList *i;
-
-    for (i = s->requests; i; i = i->next) {
-        rng_egd_free_request(i->data);
-    }
-
-    g_slist_free(s->requests);
-    s->requests = NULL;
-}
-
-static void rng_egd_cancel_requests(RngBackend *b)
-{
-    RngEgd *s = RNG_EGD(b);
-
-    /* We simply delete the list of pending requests.  If there is data in the 
-     * queue waiting to be read, this is okay, because there will always be
-     * more data than we requested originally
-     */
-    rng_egd_free_requests(s);
-}
-
 static void rng_egd_opened(RngBackend *b, Error **errp)
 {
     RngEgd *s = RNG_EGD(b);
@@ -204,8 +150,6 @@ static void rng_egd_finalize(Object *obj)
     }
 
     g_free(s->chr_name);
-
-    rng_egd_free_requests(s);
 }
 
 static void rng_egd_class_init(ObjectClass *klass, void *data)
@@ -213,7 +157,6 @@ static void rng_egd_class_init(ObjectClass *klass, void *data)
     RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
 
     rbc->request_entropy = rng_egd_request_entropy;
-    rbc->cancel_requests = rng_egd_cancel_requests;
     rbc->opened = rng_egd_opened;
 }
 

backends/rng-random.c

@@ -22,10 +22,6 @@ struct RndRandom
 
     int fd;
     char *filename;
-
-    EntropyReceiveFunc *receive_func;
-    void *opaque;
-    size_t size;
 };
 
 /**
@@ -38,36 +34,35 @@ struct RndRandom
 static void entropy_available(void *opaque)
 {
     RndRandom *s = RNG_RANDOM(opaque);
-    uint8_t buffer[s->size];
-    ssize_t len;
 
-    len = read(s->fd, buffer, s->size);
+    while (s->parent.requests != NULL) {
-    if (len < 0 && errno == EAGAIN) {
+        RngRequest *req = s->parent.requests->data;
-        return;
+        ssize_t len;
+
+        len = read(s->fd, req->data, req->size);
+        if (len < 0 && errno == EAGAIN) {
+            return;
+        }
+        g_assert(len != -1);
+
+        req->receive_entropy(req->opaque, req->data, len);
+
+        rng_backend_finalize_request(&s->parent, req);
     }
-    g_assert(len != -1);
-
-    s->receive_func(s->opaque, buffer, len);
-    s->receive_func = NULL;
 
+    /* We've drained all requests, the fd handler can be reset. */
     qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
 }
 
-static void rng_random_request_entropy(RngBackend *b, size_t size,
+static void rng_random_request_entropy(RngBackend *b, RngRequest *req)
-                                        EntropyReceiveFunc *receive_entropy,
-                                        void *opaque)
 {
     RndRandom *s = RNG_RANDOM(b);
 
-    if (s->receive_func) {
+    if (s->parent.requests == NULL) {
-        s->receive_func(s->opaque, NULL, 0);
+        /* If there are no pending requests yet, we need to
+         * install our fd handler. */
+        qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
     }
-
-    s->receive_func = receive_entropy;
-    s->opaque = opaque;
-    s->size = size;
-
-    qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
 }
 
 static void rng_random_opened(RngBackend *b, Error **errp)

backends/rng.c

@@ -20,18 +20,20 @@ void rng_backend_request_entropy(RngBackend *s, size_t size,
                                  void *opaque)
 {
     RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
+    RngRequest *req;
 
     if (k->request_entropy) {
-        k->request_entropy(s, size, receive_entropy, opaque);
+        req = g_malloc(sizeof(*req));
-    }
-}
 
-void rng_backend_cancel_requests(RngBackend *s)
+        req->offset = 0;
-{
+        req->size = size;
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
+        req->receive_entropy = receive_entropy;
+        req->opaque = opaque;
+        req->data = g_malloc(req->size);
 
-    if (k->cancel_requests) {
+        k->request_entropy(s, req);
-        k->cancel_requests(s);
+
+        s->requests = g_slist_append(s->requests, req);
     }
 }
 
@@ -73,6 +75,30 @@ static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
     s->opened = true;
 }
 
+static void rng_backend_free_request(RngRequest *req)
+{
+    g_free(req->data);
+    g_free(req);
+}
+
+static void rng_backend_free_requests(RngBackend *s)
+{
+    GSList *i;
+
+    for (i = s->requests; i; i = i->next) {
+        rng_backend_free_request(i->data);
+    }
+
+    g_slist_free(s->requests);
+    s->requests = NULL;
+}
+
+void rng_backend_finalize_request(RngBackend *s, RngRequest *req)
+{
+    s->requests = g_slist_remove(s->requests, req);
+    rng_backend_free_request(req);
+}
+
 static void rng_backend_init(Object *obj)
 {
     object_property_add_bool(obj, "opened",
@@ -81,6 +107,13 @@ static void rng_backend_init(Object *obj)
                              NULL);
 }
 
+static void rng_backend_finalize(Object *obj)
+{
+    RngBackend *s = RNG_BACKEND(obj);
+
+    rng_backend_free_requests(s);
+}
+
 static void rng_backend_class_init(ObjectClass *oc, void *data)
 {
     UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
@@ -93,6 +126,7 @@ static const TypeInfo rng_backend_info = {
     .parent = TYPE_OBJECT,
     .instance_size = sizeof(RngBackend),
     .instance_init = rng_backend_init,
+    .instance_finalize = rng_backend_finalize,
     .class_size = sizeof(RngBackendClass),
     .class_init = rng_backend_class_init,
     .abstract = true,

block.c

@@ -1191,10 +1191,6 @@ static int bdrv_fill_options(QDict **options, const char *filename,
         }
     }
 
-    if (runstate_check(RUN_STATE_INMIGRATE)) {
-        *flags |= BDRV_O_INACTIVE;
-    }
-
     return 0;
 }
 

block/backup.c

@@ -21,10 +21,7 @@
 #include "qemu/ratelimit.h"
 #include "sysemu/block-backend.h"
 
-#define BACKUP_CLUSTER_BITS 16
+#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
-#define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
-#define BACKUP_SECTORS_PER_CLUSTER (BACKUP_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
-
 #define SLICE_TIME 100000000ULL /* ns */
 
 typedef struct CowRequest {
@@ -46,9 +43,16 @@ typedef struct BackupBlockJob {
     CoRwlock flush_rwlock;
     uint64_t sectors_read;
     HBitmap *bitmap;
+    int64_t cluster_size;
     QLIST_HEAD(, CowRequest) inflight_reqs;
 } BackupBlockJob;
 
+/* Size of a cluster in sectors, instead of bytes. */
+static inline int64_t cluster_size_sectors(BackupBlockJob *job)
+{
+  return job->cluster_size / BDRV_SECTOR_SIZE;
+}
+
 /* See if in-flight requests overlap and wait for them to complete */
 static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
                                                        int64_t start,
@@ -97,13 +101,14 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
     QEMUIOVector bounce_qiov;
     void *bounce_buffer = NULL;
     int ret = 0;
+    int64_t sectors_per_cluster = cluster_size_sectors(job);
     int64_t start, end;
     int n;
 
     qemu_co_rwlock_rdlock(&job->flush_rwlock);
 
-    start = sector_num / BACKUP_SECTORS_PER_CLUSTER;
+    start = sector_num / sectors_per_cluster;
-    end = DIV_ROUND_UP(sector_num + nb_sectors, BACKUP_SECTORS_PER_CLUSTER);
+    end = DIV_ROUND_UP(sector_num + nb_sectors, sectors_per_cluster);
 
     trace_backup_do_cow_enter(job, start, sector_num, nb_sectors);
 
@@ -118,12 +123,12 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
 
         trace_backup_do_cow_process(job, start);
 
-        n = MIN(BACKUP_SECTORS_PER_CLUSTER,
+        n = MIN(sectors_per_cluster,
                 job->common.len / BDRV_SECTOR_SIZE -
-                start * BACKUP_SECTORS_PER_CLUSTER);
+                start * sectors_per_cluster);
 
         if (!bounce_buffer) {
-            bounce_buffer = qemu_blockalign(bs, BACKUP_CLUSTER_SIZE);
+            bounce_buffer = qemu_blockalign(bs, job->cluster_size);
         }
         iov.iov_base = bounce_buffer;
         iov.iov_len = n * BDRV_SECTOR_SIZE;
@@ -131,10 +136,10 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
 
         if (is_write_notifier) {
             ret = bdrv_co_readv_no_serialising(bs,
-                                           start * BACKUP_SECTORS_PER_CLUSTER,
+                                           start * sectors_per_cluster,
                                            n, &bounce_qiov);
         } else {
-            ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
+            ret = bdrv_co_readv(bs, start * sectors_per_cluster, n,
                                 &bounce_qiov);
         }
         if (ret < 0) {
@@ -147,11 +152,11 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
 
         if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
             ret = bdrv_co_write_zeroes(job->target,
-                                       start * BACKUP_SECTORS_PER_CLUSTER,
+                                       start * sectors_per_cluster,
                                        n, BDRV_REQ_MAY_UNMAP);
         } else {
             ret = bdrv_co_writev(job->target,
-                                 start * BACKUP_SECTORS_PER_CLUSTER, n,
+                                 start * sectors_per_cluster, n,
                                  &bounce_qiov);
         }
         if (ret < 0) {
@@ -322,21 +327,22 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
     int64_t cluster;
     int64_t end;
     int64_t last_cluster = -1;
+    int64_t sectors_per_cluster = cluster_size_sectors(job);
     BlockDriverState *bs = job->common.bs;
     HBitmapIter hbi;
 
     granularity = bdrv_dirty_bitmap_granularity(job->sync_bitmap);
-    clusters_per_iter = MAX((granularity / BACKUP_CLUSTER_SIZE), 1);
+    clusters_per_iter = MAX((granularity / job->cluster_size), 1);
     bdrv_dirty_iter_init(job->sync_bitmap, &hbi);
 
     /* Find the next dirty sector(s) */
     while ((sector = hbitmap_iter_next(&hbi)) != -1) {
-        cluster = sector / BACKUP_SECTORS_PER_CLUSTER;
+        cluster = sector / sectors_per_cluster;
 
         /* Fake progress updates for any clusters we skipped */
         if (cluster != last_cluster + 1) {
             job->common.offset += ((cluster - last_cluster - 1) *
-                                   BACKUP_CLUSTER_SIZE);
+                                   job->cluster_size);
         }
 
         for (end = cluster + clusters_per_iter; cluster < end; cluster++) {
@@ -344,8 +350,8 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
                 if (yield_and_check(job)) {
                     return ret;
                 }
-                ret = backup_do_cow(bs, cluster * BACKUP_SECTORS_PER_CLUSTER,
+                ret = backup_do_cow(bs, cluster * sectors_per_cluster,
-                                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read,
+                                    sectors_per_cluster, &error_is_read,
                                     false);
                 if ((ret < 0) &&
                     backup_error_action(job, error_is_read, -ret) ==
@@ -357,17 +363,17 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
 
         /* If the bitmap granularity is smaller than the backup granularity,
          * we need to advance the iterator pointer to the next cluster. */
-        if (granularity < BACKUP_CLUSTER_SIZE) {
+        if (granularity < job->cluster_size) {
-            bdrv_set_dirty_iter(&hbi, cluster * BACKUP_SECTORS_PER_CLUSTER);
+            bdrv_set_dirty_iter(&hbi, cluster * sectors_per_cluster);
         }
 
         last_cluster = cluster - 1;
     }
 
     /* Play some final catchup with the progress meter */
-    end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
+    end = DIV_ROUND_UP(job->common.len, job->cluster_size);
     if (last_cluster + 1 < end) {
-        job->common.offset += ((end - last_cluster - 1) * BACKUP_CLUSTER_SIZE);
+        job->common.offset += ((end - last_cluster - 1) * job->cluster_size);
     }
 
     return ret;
@@ -384,13 +390,14 @@ static void coroutine_fn backup_run(void *opaque)
         .notify = backup_before_write_notify,
     };
     int64_t start, end;
+    int64_t sectors_per_cluster = cluster_size_sectors(job);
     int ret = 0;
 
     QLIST_INIT(&job->inflight_reqs);
     qemu_co_rwlock_init(&job->flush_rwlock);
 
     start = 0;
-    end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
+    end = DIV_ROUND_UP(job->common.len, job->cluster_size);
 
     job->bitmap = hbitmap_alloc(end, 0);
 
@@ -427,7 +434,7 @@ static void coroutine_fn backup_run(void *opaque)
                 /* Check to see if these blocks are already in the
                  * backing file. */
 
-                for (i = 0; i < BACKUP_SECTORS_PER_CLUSTER;) {
+                for (i = 0; i < sectors_per_cluster;) {
                     /* bdrv_is_allocated() only returns true/false based
                      * on the first set of sectors it comes across that
                      * are are all in the same state.
@@ -436,8 +443,8 @@ static void coroutine_fn backup_run(void *opaque)
                      * needed but at some point that is always the case. */
                     alloced =
                         bdrv_is_allocated(bs,
-                                start * BACKUP_SECTORS_PER_CLUSTER + i,
+                                start * sectors_per_cluster + i,
-                                BACKUP_SECTORS_PER_CLUSTER - i, &n);
+                                sectors_per_cluster - i, &n);
                     i += n;
 
                     if (alloced == 1 || n == 0) {
@@ -452,8 +459,8 @@ static void coroutine_fn backup_run(void *opaque)
                 }
             }
             /* FULL sync mode we copy the whole drive. */
-            ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
+            ret = backup_do_cow(bs, start * sectors_per_cluster,
-                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read, false);
+                                sectors_per_cluster, &error_is_read, false);
             if (ret < 0) {
                 /* Depending on error action, fail now or retry cluster */
                 BlockErrorAction action =
@@ -494,6 +501,8 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
                   BlockJobTxn *txn, Error **errp)
 {
     int64_t len;
+    BlockDriverInfo bdi;
+    int ret;
 
     assert(bs);
     assert(target);
@@ -563,14 +572,32 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
         goto error;
     }
 
-    bdrv_op_block_all(target, job->common.blocker);
-
     job->on_source_error = on_source_error;
     job->on_target_error = on_target_error;
     job->target = target;
     job->sync_mode = sync_mode;
     job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_INCREMENTAL ?
                        sync_bitmap : NULL;
+
+    /* If there is no backing file on the target, we cannot rely on COW if our
+     * backup cluster size is smaller than the target cluster size. Even for
+     * targets with a backing file, try to avoid COW if possible. */
+    ret = bdrv_get_info(job->target, &bdi);
+    if (ret < 0 && !target->backing) {
+        error_setg_errno(errp, -ret,
+            "Couldn't determine the cluster size of the target image, "
+            "which has no backing file");
+        error_append_hint(errp,
+            "Aborting, since this may create an unusable destination image\n");
+        goto error;
+    } else if (ret < 0 && target->backing) {
+        /* Not fatal; just trudge on ahead. */
+        job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT;
+    } else {
+        job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
+    }
+
+    bdrv_op_block_all(target, job->common.blocker);
     job->common.len = len;
     job->common.co = qemu_coroutine_create(backup_run);
     block_job_txn_add_job(txn, &job->common);

block/curl.c

@@ -27,6 +27,7 @@
 #include "block/block_int.h"
 #include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qstring.h"
+#include "crypto/secret.h"
 #include <curl/curl.h>
 
 // #define DEBUG_CURL
@@ -78,6 +79,10 @@ static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
 #define CURL_BLOCK_OPT_SSLVERIFY "sslverify"
 #define CURL_BLOCK_OPT_TIMEOUT "timeout"
 #define CURL_BLOCK_OPT_COOKIE    "cookie"
+#define CURL_BLOCK_OPT_USERNAME "username"
+#define CURL_BLOCK_OPT_PASSWORD_SECRET "password-secret"
+#define CURL_BLOCK_OPT_PROXY_USERNAME "proxy-username"
+#define CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET "proxy-password-secret"
 
 struct BDRVCURLState;
 
@@ -120,6 +125,10 @@ typedef struct BDRVCURLState {
     char *cookie;
     bool accept_range;
     AioContext *aio_context;
+    char *username;
+    char *password;
+    char *proxyusername;
+    char *proxypassword;
 } BDRVCURLState;
 
 static void curl_clean_state(CURLState *s);
@@ -419,6 +428,21 @@ static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
         curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
         curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
 
+        if (s->username) {
+            curl_easy_setopt(state->curl, CURLOPT_USERNAME, s->username);
+        }
+        if (s->password) {
+            curl_easy_setopt(state->curl, CURLOPT_PASSWORD, s->password);
+        }
+        if (s->proxyusername) {
+            curl_easy_setopt(state->curl,
+                             CURLOPT_PROXYUSERNAME, s->proxyusername);
+        }
+        if (s->proxypassword) {
+            curl_easy_setopt(state->curl,
+                             CURLOPT_PROXYPASSWORD, s->proxypassword);
+        }
+
         /* Restrict supported protocols to avoid security issues in the more
          * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
          * CVE-2013-0249.
@@ -525,10 +549,31 @@ static QemuOptsList runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "Pass the cookie or list of cookies with each request"
         },
+        {
+            .name = CURL_BLOCK_OPT_USERNAME,
+            .type = QEMU_OPT_STRING,
+            .help = "Username for HTTP auth"
+        },
+        {
+            .name = CURL_BLOCK_OPT_PASSWORD_SECRET,
+            .type = QEMU_OPT_STRING,
+            .help = "ID of secret used as password for HTTP auth",
+        },
+        {
+            .name = CURL_BLOCK_OPT_PROXY_USERNAME,
+            .type = QEMU_OPT_STRING,
+            .help = "Username for HTTP proxy auth"
+        },
+        {
+            .name = CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET,
+            .type = QEMU_OPT_STRING,
+            .help = "ID of secret used as password for HTTP proxy auth",
+        },
         { /* end of list */ }
     },
 };
 
+
 static int curl_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
 {
@@ -539,6 +584,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     const char *file;
     const char *cookie;
     double d;
+    const char *secretid;
 
     static int inited = 0;
 
@@ -580,6 +626,26 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
         goto out_noclean;
     }
 
+    s->username = g_strdup(qemu_opt_get(opts, CURL_BLOCK_OPT_USERNAME));
+    secretid = qemu_opt_get(opts, CURL_BLOCK_OPT_PASSWORD_SECRET);
+
+    if (secretid) {
+        s->password = qcrypto_secret_lookup_as_utf8(secretid, errp);
+        if (!s->password) {
+            goto out_noclean;
+        }
+    }
+
+    s->proxyusername = g_strdup(
+        qemu_opt_get(opts, CURL_BLOCK_OPT_PROXY_USERNAME));
+    secretid = qemu_opt_get(opts, CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET);
+    if (secretid) {
+        s->proxypassword = qcrypto_secret_lookup_as_utf8(secretid, errp);
+        if (!s->proxypassword) {
+            goto out_noclean;
+        }
+    }
+
     if (!inited) {
         curl_global_init(CURL_GLOBAL_ALL);
         inited = 1;

block/iscsi.c

@@ -39,6 +39,7 @@
 #include "sysemu/sysemu.h"
 #include "qmp-commands.h"
 #include "qapi/qmp/qstring.h"
+#include "crypto/secret.h"
 
 #include <iscsi/iscsi.h>
 #include <iscsi/scsi-lowlevel.h>
@@ -1080,6 +1081,8 @@ static void parse_chap(struct iscsi_context *iscsi, const char *target,
     QemuOpts *opts;
     const char *user = NULL;
     const char *password = NULL;
+    const char *secretid;
+    char *secret = NULL;
 
     list = qemu_find_opts("iscsi");
     if (!list) {
@@ -1099,8 +1102,20 @@ static void parse_chap(struct iscsi_context *iscsi, const char *target,
         return;
     }
 
+    secretid = qemu_opt_get(opts, "password-secret");
     password = qemu_opt_get(opts, "password");
-    if (!password) {
+    if (secretid && password) {
+        error_setg(errp, "'password' and 'password-secret' properties are "
+                   "mutually exclusive");
+        return;
+    }
+    if (secretid) {
+        secret = qcrypto_secret_lookup_as_utf8(secretid, errp);
+        if (!secret) {
+            return;
+        }
+        password = secret;
+    } else if (!password) {
         error_setg(errp, "CHAP username specified but no password was given");
         return;
     }
@@ -1108,6 +1123,8 @@ static void parse_chap(struct iscsi_context *iscsi, const char *target,
     if (iscsi_set_initiator_username_pwd(iscsi, user, password)) {
         error_setg(errp, "Failed to set initiator username and password");
     }
+
+    g_free(secret);
 }
 
 static void parse_header_digest(struct iscsi_context *iscsi, const char *target,
@@ -1857,6 +1874,11 @@ static QemuOptsList qemu_iscsi_opts = {
             .name = "password",
             .type = QEMU_OPT_STRING,
             .help = "password for CHAP authentication to target",
+        },{
+            .name = "password-secret",
+            .type = QEMU_OPT_STRING,
+            .help = "ID of the secret providing password for CHAP "
+                    "authentication to target",
         },{
             .name = "header-digest",
             .type = QEMU_OPT_STRING,

block/mirror.c

@@ -47,7 +47,6 @@ typedef struct MirrorBlockJob {
     BlockdevOnError on_source_error, on_target_error;
     bool synced;
     bool should_complete;
-    int64_t sector_num;
     int64_t granularity;
     size_t buf_size;
     int64_t bdev_length;
@@ -64,6 +63,8 @@ typedef struct MirrorBlockJob {
     int ret;
     bool unmap;
     bool waiting_for_io;
+    int target_cluster_sectors;
+    int max_iov;
 } MirrorBlockJob;
 
 typedef struct MirrorOp {
@@ -159,115 +160,84 @@ static void mirror_read_complete(void *opaque, int ret)
                     mirror_write_complete, op);
 }
 
-static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
+/* Round sector_num and/or nb_sectors to target cluster if COW is needed, and
+ * return the offset of the adjusted tail sector against original. */
+static int mirror_cow_align(MirrorBlockJob *s,
+                            int64_t *sector_num,
+                            int *nb_sectors)
+{
+    bool need_cow;
+    int ret = 0;
+    int chunk_sectors = s->granularity >> BDRV_SECTOR_BITS;
+    int64_t align_sector_num = *sector_num;
+    int align_nb_sectors = *nb_sectors;
+    int max_sectors = chunk_sectors * s->max_iov;
+
+    need_cow = !test_bit(*sector_num / chunk_sectors, s->cow_bitmap);
+    need_cow |= !test_bit((*sector_num + *nb_sectors - 1) / chunk_sectors,
+                          s->cow_bitmap);
+    if (need_cow) {
+        bdrv_round_to_clusters(s->target, *sector_num, *nb_sectors,
+                               &align_sector_num, &align_nb_sectors);
+    }
+
+    if (align_nb_sectors > max_sectors) {
+        align_nb_sectors = max_sectors;
+        if (need_cow) {
+            align_nb_sectors = QEMU_ALIGN_DOWN(align_nb_sectors,
+                                               s->target_cluster_sectors);
+        }
+    }
+
+    ret = align_sector_num + align_nb_sectors - (*sector_num + *nb_sectors);
+    *sector_num = align_sector_num;
+    *nb_sectors = align_nb_sectors;
+    assert(ret >= 0);
+    return ret;
+}
+
+static inline void mirror_wait_for_io(MirrorBlockJob *s)
+{
+    assert(!s->waiting_for_io);
+    s->waiting_for_io = true;
+    qemu_coroutine_yield();
+    s->waiting_for_io = false;
+}
+
+/* Submit async read while handling COW.
+ * Returns: nb_sectors if no alignment is necessary, or
+ *          (new_end - sector_num) if tail is rounded up or down due to
+ *          alignment or buffer limit.
+ */
+static int mirror_do_read(MirrorBlockJob *s, int64_t sector_num,
+                          int nb_sectors)
 {
     BlockDriverState *source = s->common.bs;
-    int nb_sectors, sectors_per_chunk, nb_chunks, max_iov;
+    int sectors_per_chunk, nb_chunks;
-    int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
+    int ret = nb_sectors;
-    uint64_t delay_ns = 0;
     MirrorOp *op;
-    int pnum;
-    int64_t ret;
-    BlockDriverState *file;
 
-    max_iov = MIN(source->bl.max_iov, s->target->bl.max_iov);
-
-    s->sector_num = hbitmap_iter_next(&s->hbi);
-    if (s->sector_num < 0) {
-        bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
-        s->sector_num = hbitmap_iter_next(&s->hbi);
-        trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap));
-        assert(s->sector_num >= 0);
-    }
-
-    hbitmap_next_sector = s->sector_num;
-    sector_num = s->sector_num;
     sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
-    end = s->bdev_length / BDRV_SECTOR_SIZE;
 
-    /* Extend the QEMUIOVector to include all adjacent blocks that will
+    /* We can only handle as much as buf_size at a time. */
-     * be copied in this operation.
+    nb_sectors = MIN(s->buf_size >> BDRV_SECTOR_BITS, nb_sectors);
-     *
+    assert(nb_sectors);
-     * We have to do this if we have no backing file yet in the destination,
-     * and the cluster size is very large.  Then we need to do COW ourselves.
-     * The first time a cluster is copied, copy it entirely.  Note that,
-     * because both the granularity and the cluster size are powers of two,
-     * the number of sectors to copy cannot exceed one cluster.
-     *
-     * We also want to extend the QEMUIOVector to include more adjacent
-     * dirty blocks if possible, to limit the number of I/O operations and
-     * run efficiently even with a small granularity.
-     */
-    nb_chunks = 0;
-    nb_sectors = 0;
-    next_sector = sector_num;
-    next_chunk = sector_num / sectors_per_chunk;
 
-    /* Wait for I/O to this cluster (from a previous iteration) to be done.  */
+    if (s->cow_bitmap) {
-    while (test_bit(next_chunk, s->in_flight_bitmap)) {
+        ret += mirror_cow_align(s, &sector_num, &nb_sectors);
-        trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
-        s->waiting_for_io = true;
-        qemu_coroutine_yield();
-        s->waiting_for_io = false;
     }
+    assert(nb_sectors << BDRV_SECTOR_BITS <= s->buf_size);
+    /* The sector range must meet granularity because:
+     * 1) Caller passes in aligned values;
+     * 2) mirror_cow_align is used only when target cluster is larger. */
+    assert(!(nb_sectors % sectors_per_chunk));
+    assert(!(sector_num % sectors_per_chunk));
+    nb_chunks = nb_sectors / sectors_per_chunk;
 
-    do {
+    while (s->buf_free_count < nb_chunks) {
-        int added_sectors, added_chunks;
+        trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
-
+        mirror_wait_for_io(s);
-        if (!bdrv_get_dirty(source, s->dirty_bitmap, next_sector) ||
+    }
-            test_bit(next_chunk, s->in_flight_bitmap)) {
-            assert(nb_sectors > 0);
-            break;
-        }
-
-        added_sectors = sectors_per_chunk;
-        if (s->cow_bitmap && !test_bit(next_chunk, s->cow_bitmap)) {
-            bdrv_round_to_clusters(s->target,
-                                   next_sector, added_sectors,
-                                   &next_sector, &added_sectors);
-
-            /* On the first iteration, the rounding may make us copy
-             * sectors before the first dirty one.
-             */
-            if (next_sector < sector_num) {
-                assert(nb_sectors == 0);
-                sector_num = next_sector;
-                next_chunk = next_sector / sectors_per_chunk;
-            }
-        }
-
-        added_sectors = MIN(added_sectors, end - (sector_num + nb_sectors));
-        added_chunks = (added_sectors + sectors_per_chunk - 1) / sectors_per_chunk;
-
-        /* When doing COW, it may happen that there is not enough space for
-         * a full cluster.  Wait if that is the case.
-         */
-        while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
-            trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
-            s->waiting_for_io = true;
-            qemu_coroutine_yield();
-            s->waiting_for_io = false;
-        }
-        if (s->buf_free_count < nb_chunks + added_chunks) {
-            trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
-            break;
-        }
-        if (max_iov < nb_chunks + added_chunks) {
-            trace_mirror_break_iov_max(s, nb_chunks, added_chunks);
-            break;
-        }
-
-        /* We have enough free space to copy these sectors.  */
-        bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
-
-        nb_sectors += added_sectors;
-        nb_chunks += added_chunks;
-        next_sector += added_sectors;
-        next_chunk += added_chunks;
-        if (!s->synced && s->common.speed) {
-            delay_ns = ratelimit_calculate_delay(&s->limit, added_sectors);
-        }
-    } while (delay_ns == 0 && next_sector < end);
 
     /* Allocate a MirrorOp that is used as an AIO callback.  */
     op = g_new(MirrorOp, 1);
@@ -279,47 +249,151 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
      * from s->buf_free.
      */
     qemu_iovec_init(&op->qiov, nb_chunks);
-    next_sector = sector_num;
     while (nb_chunks-- > 0) {
         MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
-        size_t remaining = (nb_sectors * BDRV_SECTOR_SIZE) - op->qiov.size;
+        size_t remaining = nb_sectors * BDRV_SECTOR_SIZE - op->qiov.size;
 
         QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
         s->buf_free_count--;
         qemu_iovec_add(&op->qiov, buf, MIN(s->granularity, remaining));
-
-        /* Advance the HBitmapIter in parallel, so that we do not examine
-         * the same sector twice.
-         */
-        if (next_sector > hbitmap_next_sector
-            && bdrv_get_dirty(source, s->dirty_bitmap, next_sector)) {
-            hbitmap_next_sector = hbitmap_iter_next(&s->hbi);
-        }
-
-        next_sector += sectors_per_chunk;
     }
 
-    bdrv_reset_dirty_bitmap(s->dirty_bitmap, sector_num, nb_sectors);
-
     /* Copy the dirty cluster.  */
     s->in_flight++;
     s->sectors_in_flight += nb_sectors;
     trace_mirror_one_iteration(s, sector_num, nb_sectors);
 
-    ret = bdrv_get_block_status_above(source, NULL, sector_num,
+    bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
-                                      nb_sectors, &pnum, &file);
+                   mirror_read_complete, op);
-    if (ret < 0 || pnum < nb_sectors ||
+    return ret;
-            (ret & BDRV_BLOCK_DATA && !(ret & BDRV_BLOCK_ZERO))) {
+}
-        bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
+
-                       mirror_read_complete, op);
+static void mirror_do_zero_or_discard(MirrorBlockJob *s,
-    } else if (ret & BDRV_BLOCK_ZERO) {
+                                      int64_t sector_num,
+                                      int nb_sectors,
+                                      bool is_discard)
+{
+    MirrorOp *op;
+
+    /* Allocate a MirrorOp that is used as an AIO callback. The qiov is zeroed
+     * so the freeing in mirror_iteration_done is nop. */
+    op = g_new0(MirrorOp, 1);
+    op->s = s;
+    op->sector_num = sector_num;
+    op->nb_sectors = nb_sectors;
+
+    s->in_flight++;
+    s->sectors_in_flight += nb_sectors;
+    if (is_discard) {
+        bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
+                         mirror_write_complete, op);
+    } else {
         bdrv_aio_write_zeroes(s->target, sector_num, op->nb_sectors,
                               s->unmap ? BDRV_REQ_MAY_UNMAP : 0,
                               mirror_write_complete, op);
-    } else {
+    }
-        assert(!(ret & BDRV_BLOCK_DATA));
+}
-        bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
+
-                         mirror_write_complete, op);
+static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
+{
+    BlockDriverState *source = s->common.bs;
+    int64_t sector_num;
+    uint64_t delay_ns = 0;
+    /* At least the first dirty chunk is mirrored in one iteration. */
+    int nb_chunks = 1;
+    int64_t end = s->bdev_length / BDRV_SECTOR_SIZE;
+    int sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
+
+    sector_num = hbitmap_iter_next(&s->hbi);
+    if (sector_num < 0) {
+        bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
+        sector_num = hbitmap_iter_next(&s->hbi);
+        trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap));
+        assert(sector_num >= 0);
+    }
+
+    /* Find the number of consective dirty chunks following the first dirty
+     * one, and wait for in flight requests in them. */
+    while (nb_chunks * sectors_per_chunk < (s->buf_size >> BDRV_SECTOR_BITS)) {
+        int64_t hbitmap_next;
+        int64_t next_sector = sector_num + nb_chunks * sectors_per_chunk;
+        int64_t next_chunk = next_sector / sectors_per_chunk;
+        if (next_sector >= end ||
+            !bdrv_get_dirty(source, s->dirty_bitmap, next_sector)) {
+            break;
+        }
+        if (test_bit(next_chunk, s->in_flight_bitmap)) {
+            if (nb_chunks > 0) {
+                break;
+            }
+            trace_mirror_yield_in_flight(s, next_sector, s->in_flight);
+            mirror_wait_for_io(s);
+            /* Now retry.  */
+        } else {
+            hbitmap_next = hbitmap_iter_next(&s->hbi);
+            assert(hbitmap_next == next_sector);
+            nb_chunks++;
+        }
+    }
+
+    /* Clear dirty bits before querying the block status, because
+     * calling bdrv_get_block_status_above could yield - if some blocks are
+     * marked dirty in this window, we need to know.
+     */
+    bdrv_reset_dirty_bitmap(s->dirty_bitmap, sector_num,
+                            nb_chunks * sectors_per_chunk);
+    bitmap_set(s->in_flight_bitmap, sector_num / sectors_per_chunk, nb_chunks);
+    while (nb_chunks > 0 && sector_num < end) {
+        int ret;
+        int io_sectors;
+        BlockDriverState *file;
+        enum MirrorMethod {
+            MIRROR_METHOD_COPY,
+            MIRROR_METHOD_ZERO,
+            MIRROR_METHOD_DISCARD
+        } mirror_method = MIRROR_METHOD_COPY;
+
+        assert(!(sector_num % sectors_per_chunk));
+        ret = bdrv_get_block_status_above(source, NULL, sector_num,
+                                          nb_chunks * sectors_per_chunk,
+                                          &io_sectors, &file);
+        if (ret < 0) {
+            io_sectors = nb_chunks * sectors_per_chunk;
+        }
+
+        io_sectors -= io_sectors % sectors_per_chunk;
+        if (io_sectors < sectors_per_chunk) {
+            io_sectors = sectors_per_chunk;
+        } else if (ret >= 0 && !(ret & BDRV_BLOCK_DATA)) {
+            int64_t target_sector_num;
+            int target_nb_sectors;
+            bdrv_round_to_clusters(s->target, sector_num, io_sectors,
+                                   &target_sector_num, &target_nb_sectors);
+            if (target_sector_num == sector_num &&
+                target_nb_sectors == io_sectors) {
+                mirror_method = ret & BDRV_BLOCK_ZERO ?
+                                    MIRROR_METHOD_ZERO :
+                                    MIRROR_METHOD_DISCARD;
+            }
+        }
+
+        switch (mirror_method) {
+        case MIRROR_METHOD_COPY:
+            io_sectors = mirror_do_read(s, sector_num, io_sectors);
+            break;
+        case MIRROR_METHOD_ZERO:
+            mirror_do_zero_or_discard(s, sector_num, io_sectors, false);
+            break;
+        case MIRROR_METHOD_DISCARD:
+            mirror_do_zero_or_discard(s, sector_num, io_sectors, true);
+            break;
+        default:
+            abort();
+        }
+        assert(io_sectors);
+        sector_num += io_sectors;
+        nb_chunks -= io_sectors / sectors_per_chunk;
+        delay_ns += ratelimit_calculate_delay(&s->limit, io_sectors);
     }
     return delay_ns;
 }
@@ -344,9 +418,7 @@ static void mirror_free_init(MirrorBlockJob *s)
 static void mirror_drain(MirrorBlockJob *s)
 {
     while (s->in_flight > 0) {
-        s->waiting_for_io = true;
+        mirror_wait_for_io(s);
-        qemu_coroutine_yield();
-        s->waiting_for_io = false;
     }
 }
 
@@ -420,6 +492,7 @@ static void coroutine_fn mirror_run(void *opaque)
                                  checking for a NULL string */
     int ret = 0;
     int n;
+    int target_cluster_size = BDRV_SECTOR_SIZE;
 
     if (block_job_is_cancelled(&s->common)) {
         goto immediate_exit;
@@ -449,16 +522,16 @@ static void coroutine_fn mirror_run(void *opaque)
      */
     bdrv_get_backing_filename(s->target, backing_filename,
                               sizeof(backing_filename));
-    if (backing_filename[0] && !s->target->backing) {
+    if (!bdrv_get_info(s->target, &bdi) && bdi.cluster_size) {
-        ret = bdrv_get_info(s->target, &bdi);
+        target_cluster_size = bdi.cluster_size;
-        if (ret < 0) {
-            goto immediate_exit;
-        }
-        if (s->granularity < bdi.cluster_size) {
-            s->buf_size = MAX(s->buf_size, bdi.cluster_size);
-            s->cow_bitmap = bitmap_new(length);
-        }
     }
+    if (backing_filename[0] && !s->target->backing
+        && s->granularity < target_cluster_size) {
+        s->buf_size = MAX(s->buf_size, target_cluster_size);
+        s->cow_bitmap = bitmap_new(length);
+    }
+    s->target_cluster_sectors = target_cluster_size >> BDRV_SECTOR_BITS;
+    s->max_iov = MIN(s->common.bs->bl.max_iov, s->target->bl.max_iov);
 
     end = s->bdev_length / BDRV_SECTOR_SIZE;
     s->buf = qemu_try_blockalign(bs, s->buf_size);
@@ -533,9 +606,7 @@ static void coroutine_fn mirror_run(void *opaque)
             if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
                 (cnt == 0 && s->in_flight > 0)) {
                 trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
-                s->waiting_for_io = true;
+                mirror_wait_for_io(s);
-                qemu_coroutine_yield();
-                s->waiting_for_io = false;
                 continue;
             } else if (cnt != 0) {
                 delay_ns = mirror_iteration(s);

block/nbd.c

@@ -204,18 +204,20 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, char **export,
     saddr = g_new0(SocketAddress, 1);
 
     if (qdict_haskey(options, "path")) {
+        UnixSocketAddress *q_unix;
         saddr->type = SOCKET_ADDRESS_KIND_UNIX;
-        saddr->u.q_unix = g_new0(UnixSocketAddress, 1);
+        q_unix = saddr->u.q_unix = g_new0(UnixSocketAddress, 1);
-        saddr->u.q_unix->path = g_strdup(qdict_get_str(options, "path"));
+        q_unix->path = g_strdup(qdict_get_str(options, "path"));
         qdict_del(options, "path");
     } else {
+        InetSocketAddress *inet;
         saddr->type = SOCKET_ADDRESS_KIND_INET;
-        saddr->u.inet = g_new0(InetSocketAddress, 1);
+        inet = saddr->u.inet = g_new0(InetSocketAddress, 1);
-        saddr->u.inet->host = g_strdup(qdict_get_str(options, "host"));
+        inet->host = g_strdup(qdict_get_str(options, "host"));
         if (!qdict_get_try_str(options, "port")) {
-            saddr->u.inet->port = g_strdup_printf("%d", NBD_DEFAULT_PORT);
+            inet->port = g_strdup_printf("%d", NBD_DEFAULT_PORT);
         } else {
-            saddr->u.inet->port = g_strdup(qdict_get_str(options, "port"));
+            inet->port = g_strdup(qdict_get_str(options, "port"));
         }
         qdict_del(options, "host");
         qdict_del(options, "port");

block/nfs.c

@@ -36,6 +36,7 @@
 #include <nfsc/libnfs.h>
 
 #define QEMU_NFS_MAX_READAHEAD_SIZE 1048576
+#define QEMU_NFS_MAX_DEBUG_LEVEL 2
 
 typedef struct NFSClient {
     struct nfs_context *context;
@@ -333,6 +334,17 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
                 val = QEMU_NFS_MAX_READAHEAD_SIZE;
             }
             nfs_set_readahead(client->context, val);
+#endif
+#ifdef LIBNFS_FEATURE_DEBUG
+        } else if (!strcmp(qp->p[i].name, "debug")) {
+            /* limit the maximum debug level to avoid potential flooding
+             * of our log files. */
+            if (val > QEMU_NFS_MAX_DEBUG_LEVEL) {
+                error_report("NFS Warning: Limiting NFS debug level"
+                             " to %d", QEMU_NFS_MAX_DEBUG_LEVEL);
+                val = QEMU_NFS_MAX_DEBUG_LEVEL;
+            }
+            nfs_set_debug(client->context, val);
 #endif
         } else {
             error_setg(errp, "Unknown NFS parameter name: %s",

block/qapi.c

@@ -92,6 +92,26 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
         info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
         info->iops_wr_max     = cfg.buckets[THROTTLE_OPS_WRITE].max;
 
+        info->has_bps_max_length     = info->has_bps_max;
+        info->bps_max_length         =
+            cfg.buckets[THROTTLE_BPS_TOTAL].burst_length;
+        info->has_bps_rd_max_length  = info->has_bps_rd_max;
+        info->bps_rd_max_length      =
+            cfg.buckets[THROTTLE_BPS_READ].burst_length;
+        info->has_bps_wr_max_length  = info->has_bps_wr_max;
+        info->bps_wr_max_length      =
+            cfg.buckets[THROTTLE_BPS_WRITE].burst_length;
+
+        info->has_iops_max_length    = info->has_iops_max;
+        info->iops_max_length        =
+            cfg.buckets[THROTTLE_OPS_TOTAL].burst_length;
+        info->has_iops_rd_max_length = info->has_iops_rd_max;
+        info->iops_rd_max_length     =
+            cfg.buckets[THROTTLE_OPS_READ].burst_length;
+        info->has_iops_wr_max_length = info->has_iops_wr_max;
+        info->iops_wr_max_length     =
+            cfg.buckets[THROTTLE_OPS_WRITE].burst_length;
+
         info->has_iops_size = cfg.op_size;
         info->iops_size = cfg.op_size;
 

block/quorum.c

@@ -286,7 +286,8 @@ static void quorum_aio_cb(void *opaque, int ret)
 
     if (acb->is_read && s->read_pattern == QUORUM_READ_PATTERN_FIFO) {
         /* We try to read next child in FIFO order if we fail to read */
-        if (ret < 0 && ++acb->child_iter < s->num_children) {
+        if (ret < 0 && (acb->child_iter + 1) < s->num_children) {
+            acb->child_iter++;
             read_fifo_child(acb);
             return;
         }

block/rbd.c

@@ -16,6 +16,7 @@
 #include "qemu-common.h"
 #include "qemu/error-report.h"
 #include "block/block_int.h"
+#include "crypto/secret.h"
 
 #include <rbd/librbd.h>
 
@@ -228,6 +229,27 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
     return NULL;
 }
 
+
+static int qemu_rbd_set_auth(rados_t cluster, const char *secretid,
+                             Error **errp)
+{
+    if (secretid == 0) {
+        return 0;
+    }
+
+    gchar *secret = qcrypto_secret_lookup_as_base64(secretid,
+                                                    errp);
+    if (!secret) {
+        return -1;
+    }
+
+    rados_conf_set(cluster, "key", secret);
+    g_free(secret);
+
+    return 0;
+}
+
+
 static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
                              bool only_read_conf_file,
                              Error **errp)
@@ -299,10 +321,13 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
     char conf[RBD_MAX_CONF_SIZE];
     char clientname_buf[RBD_MAX_CONF_SIZE];
     char *clientname;
+    const char *secretid;
     rados_t cluster;
     rados_ioctx_t io_ctx;
     int ret;
 
+    secretid = qemu_opt_get(opts, "password-secret");
+
     if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                            snap_buf, sizeof(snap_buf),
                            name, sizeof(name),
@@ -350,6 +375,11 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
         return -EIO;
     }
 
+    if (qemu_rbd_set_auth(cluster, secretid, errp) < 0) {
+        rados_shutdown(cluster);
+        return -EIO;
+    }
+
     if (rados_connect(cluster) < 0) {
         error_setg(errp, "error connecting");
         rados_shutdown(cluster);
@@ -423,6 +453,11 @@ static QemuOptsList runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "Specification of the rbd image",
         },
+        {
+            .name = "password-secret",
+            .type = QEMU_OPT_STRING,
+            .help = "ID of secret providing the password",
+        },
         { /* end of list */ }
     },
 };
@@ -436,6 +471,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     char conf[RBD_MAX_CONF_SIZE];
     char clientname_buf[RBD_MAX_CONF_SIZE];
     char *clientname;
+    const char *secretid;
     QemuOpts *opts;
     Error *local_err = NULL;
     const char *filename;
@@ -450,6 +486,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     filename = qemu_opt_get(opts, "filename");
+    secretid = qemu_opt_get(opts, "password-secret");
 
     if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                            snap_buf, sizeof(snap_buf),
@@ -488,6 +525,11 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
         }
     }
 
+    if (qemu_rbd_set_auth(s->cluster, secretid, errp) < 0) {
+        r = -EIO;
+        goto failed_shutdown;
+    }
+
     /*
      * Fallback to more conservative semantics if setting cache
      * options fails. Ignore errors from setting rbd_cache because the
@@ -919,6 +961,11 @@ static QemuOptsList qemu_rbd_create_opts = {
             .type = QEMU_OPT_SIZE,
             .help = "RBD object size"
         },
+        {
+            .name = "password-secret",
+            .type = QEMU_OPT_STRING,
+            .help = "ID of secret providing the password",
+        },
         { /* end of list */ }
     }
 };

block/sheepdog.c

@@ -284,6 +284,12 @@ static inline bool is_snapshot(struct SheepdogInode *inode)
     return !!inode->snap_ctime;
 }
 
+static inline size_t count_data_objs(const struct SheepdogInode *inode)
+{
+    return DIV_ROUND_UP(inode->vdi_size,
+                        (1UL << inode->block_size_shift));
+}
+
 #undef DPRINTF
 #ifdef DEBUG_SDOG
 #define DPRINTF(fmt, args...)                                       \
@@ -2478,13 +2484,128 @@ out:
     return ret;
 }
 
+#define NR_BATCHED_DISCARD 128
+
+static bool remove_objects(BDRVSheepdogState *s)
+{
+    int fd, i = 0, nr_objs = 0;
+    Error *local_err = NULL;
+    int ret = 0;
+    bool result = true;
+    SheepdogInode *inode = &s->inode;
+
+    fd = connect_to_sdog(s, &local_err);
+    if (fd < 0) {
+        error_report_err(local_err);
+        return false;
+    }
+
+    nr_objs = count_data_objs(inode);
+    while (i < nr_objs) {
+        int start_idx, nr_filled_idx;
+
+        while (i < nr_objs && !inode->data_vdi_id[i]) {
+            i++;
+        }
+        start_idx = i;
+
+        nr_filled_idx = 0;
+        while (i < nr_objs && nr_filled_idx < NR_BATCHED_DISCARD) {
+            if (inode->data_vdi_id[i]) {
+                inode->data_vdi_id[i] = 0;
+                nr_filled_idx++;
+            }
+
+            i++;
+        }
+
+        ret = write_object(fd, s->aio_context,
+                           (char *)&inode->data_vdi_id[start_idx],
+                           vid_to_vdi_oid(s->inode.vdi_id), inode->nr_copies,
+                           (i - start_idx) * sizeof(uint32_t),
+                           offsetof(struct SheepdogInode,
+                                    data_vdi_id[start_idx]),
+                           false, s->cache_flags);
+        if (ret < 0) {
+            error_report("failed to discard snapshot inode.");
+            result = false;
+            goto out;
+        }
+    }
+
+out:
+    closesocket(fd);
+    return result;
+}
+
 static int sd_snapshot_delete(BlockDriverState *bs,
                               const char *snapshot_id,
                               const char *name,
                               Error **errp)
 {
-    /* FIXME: Delete specified snapshot id.  */
+    uint32_t snap_id = 0;
-    return 0;
+    char snap_tag[SD_MAX_VDI_TAG_LEN];
+    Error *local_err = NULL;
+    int fd, ret;
+    char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN];
+    BDRVSheepdogState *s = bs->opaque;
+    unsigned int wlen = SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN, rlen = 0;
+    uint32_t vid;
+    SheepdogVdiReq hdr = {
+        .opcode = SD_OP_DEL_VDI,
+        .data_length = wlen,
+        .flags = SD_FLAG_CMD_WRITE,
+    };
+    SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
+
+    if (!remove_objects(s)) {
+        return -1;
+    }
+
+    memset(buf, 0, sizeof(buf));
+    memset(snap_tag, 0, sizeof(snap_tag));
+    pstrcpy(buf, SD_MAX_VDI_LEN, s->name);
+    if (qemu_strtoul(snapshot_id, NULL, 10, (unsigned long *)&snap_id)) {
+        return -1;
+    }
+
+    if (snap_id) {
+        hdr.snapid = snap_id;
+    } else {
+        pstrcpy(snap_tag, sizeof(snap_tag), snapshot_id);
+        pstrcpy(buf + SD_MAX_VDI_LEN, SD_MAX_VDI_TAG_LEN, snap_tag);
+    }
+
+    ret = find_vdi_name(s, s->name, snap_id, snap_tag, &vid, true,
+                        &local_err);
+    if (ret) {
+        return ret;
+    }
+
+    fd = connect_to_sdog(s, &local_err);
+    if (fd < 0) {
+        error_report_err(local_err);
+        return -1;
+    }
+
+    ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
+                 buf, &wlen, &rlen);
+    closesocket(fd);
+    if (ret) {
+        return ret;
+    }
+
+    switch (rsp->result) {
+    case SD_RES_NO_VDI:
+        error_report("%s was already deleted", s->name);
+    case SD_RES_SUCCESS:
+        break;
+    default:
+        error_report("%s, %s", sd_strerror(rsp->result), s->name);
+        return -1;
+    }
+
+    return ret;
 }
 
 static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)

block/vhdx.c

@@ -264,10 +264,10 @@ static void vhdx_region_unregister_all(BDRVVHDXState *s)
 
 static void vhdx_set_shift_bits(BDRVVHDXState *s)
 {
-    s->logical_sector_size_bits = 31 - clz32(s->logical_sector_size);
+    s->logical_sector_size_bits = ctz32(s->logical_sector_size);
-    s->sectors_per_block_bits =   31 - clz32(s->sectors_per_block);
+    s->sectors_per_block_bits =   ctz32(s->sectors_per_block);
-    s->chunk_ratio_bits =         63 - clz64(s->chunk_ratio);
+    s->chunk_ratio_bits =         ctz64(s->chunk_ratio);
-    s->block_size_bits =          31 - clz32(s->block_size);
+    s->block_size_bits =          ctz32(s->block_size);
 }
 
 /*
@@ -857,14 +857,8 @@ static void vhdx_calc_bat_entries(BDRVVHDXState *s)
 {
     uint32_t data_blocks_cnt, bitmap_blocks_cnt;
 
-    data_blocks_cnt = s->virtual_disk_size >> s->block_size_bits;
+    data_blocks_cnt = DIV_ROUND_UP(s->virtual_disk_size, s->block_size);
-    if (s->virtual_disk_size - (data_blocks_cnt << s->block_size_bits)) {
+    bitmap_blocks_cnt = DIV_ROUND_UP(data_blocks_cnt, s->chunk_ratio);
-        data_blocks_cnt++;
-    }
-    bitmap_blocks_cnt = data_blocks_cnt >> s->chunk_ratio_bits;
-    if (data_blocks_cnt - (bitmap_blocks_cnt << s->chunk_ratio_bits)) {
-        bitmap_blocks_cnt++;
-    }
 
     if (s->parent_entries) {
         s->bat_entries = bitmap_blocks_cnt * (s->chunk_ratio + 1);

blockdev.c

@@ -343,29 +343,6 @@ static bool parse_stats_intervals(BlockAcctStats *stats, QList *intervals,
     return true;
 }
 
-static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
-{
-    if (throttle_conflicting(cfg)) {
-        error_setg(errp, "bps/iops/max total values and read/write values"
-                         " cannot be used at the same time");
-        return false;
-    }
-
-    if (!throttle_is_valid(cfg)) {
-        error_setg(errp, "bps/iops/max values must be within [0, %lld]",
-                   THROTTLE_VALUE_MAX);
-        return false;
-    }
-
-    if (throttle_max_is_missing_limit(cfg)) {
-        error_setg(errp, "bps_max/iops_max require corresponding"
-                         " bps/iops values");
-        return false;
-    }
-
-    return true;
-}
-
 typedef enum { MEDIA_DISK, MEDIA_CDROM } DriveMediaType;
 
 /* All parameters but @opts are optional and may be set to NULL. */
@@ -410,7 +387,7 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
     }
 
     if (throttle_cfg) {
-        memset(throttle_cfg, 0, sizeof(*throttle_cfg));
+        throttle_config_init(throttle_cfg);
         throttle_cfg->buckets[THROTTLE_BPS_TOTAL].avg =
             qemu_opt_get_number(opts, "throttling.bps-total", 0);
         throttle_cfg->buckets[THROTTLE_BPS_READ].avg  =
@@ -437,10 +414,23 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
         throttle_cfg->buckets[THROTTLE_OPS_WRITE].max =
             qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
 
+        throttle_cfg->buckets[THROTTLE_BPS_TOTAL].burst_length =
+            qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_BPS_READ].burst_length  =
+            qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_BPS_WRITE].burst_length =
+            qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_TOTAL].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_READ].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_WRITE].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
+
         throttle_cfg->op_size =
             qemu_opt_get_number(opts, "throttling.iops-size", 0);
 
-        if (!check_throttle_config(throttle_cfg, errp)) {
+        if (!throttle_is_valid(throttle_cfg, errp)) {
             return;
         }
     }
@@ -610,6 +600,10 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
             qdict_put(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, qstring_from_str("on"));
         }
 
+        if (runstate_check(RUN_STATE_INMIGRATE)) {
+            bdrv_flags |= BDRV_O_INACTIVE;
+        }
+
         blk = blk_new_open(qemu_opts_id(opts), file, NULL, bs_opts, bdrv_flags,
                            errp);
         if (!blk) {
@@ -688,6 +682,10 @@ static BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp)
         goto fail;
     }
 
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        bdrv_flags |= BDRV_O_INACTIVE;
+    }
+
     bs = NULL;
     ret = bdrv_open(&bs, NULL, NULL, bs_opts, bdrv_flags, errp);
     if (ret < 0) {
@@ -1204,15 +1202,11 @@ void hmp_commit(Monitor *mon, const QDict *qdict)
     }
 }
 
-static void blockdev_do_action(TransactionActionKind type, void *data,
+static void blockdev_do_action(TransactionAction *action, Error **errp)
-                               Error **errp)
 {
-    TransactionAction action;
     TransactionActionList list;
 
-    action.type = type;
+    list.value = action;
-    action.u.data = data;
-    list.value = &action;
     list.next = NULL;
     qmp_transaction(&list, false, NULL, errp);
 }
@@ -1238,8 +1232,11 @@ void qmp_blockdev_snapshot_sync(bool has_device, const char *device,
         .has_mode = has_mode,
         .mode = mode,
     };
-    blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC,
+    TransactionAction action = {
-                       &snapshot, errp);
+        .type = TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC,
+        .u.blockdev_snapshot_sync = &snapshot,
+    };
+    blockdev_do_action(&action, errp);
 }
 
 void qmp_blockdev_snapshot(const char *node, const char *overlay,
@@ -1249,9 +1246,11 @@ void qmp_blockdev_snapshot(const char *node, const char *overlay,
         .node = (char *) node,
         .overlay = (char *) overlay
     };
-
+    TransactionAction action = {
-    blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT,
+        .type = TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT,
-                       &snapshot_data, errp);
+        .u.blockdev_snapshot = &snapshot_data,
+    };
+    blockdev_do_action(&action, errp);
 }
 
 void qmp_blockdev_snapshot_internal_sync(const char *device,
@@ -1262,9 +1261,11 @@ void qmp_blockdev_snapshot_internal_sync(const char *device,
         .device = (char *) device,
         .name = (char *) name
     };
-
+    TransactionAction action = {
-    blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_INTERNAL_SYNC,
+        .type = TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_INTERNAL_SYNC,
-                       &snapshot, errp);
+        .u.blockdev_snapshot_internal_sync = &snapshot,
+    };
+    blockdev_do_action(&action, errp);
 }
 
 SnapshotInfo *qmp_blockdev_snapshot_delete_internal_sync(const char *device,
@@ -2515,6 +2516,8 @@ void qmp_blockdev_change_medium(const char *device, const char *filename,
     }
 
     bdrv_flags = blk_get_open_flags_from_root_state(blk);
+    bdrv_flags &= ~(BDRV_O_TEMPORARY | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING |
+        BDRV_O_PROTOCOL);
 
     if (!has_read_only) {
         read_only = BLOCKDEV_CHANGE_READ_ONLY_MODE_RETAIN;
@@ -2600,6 +2603,18 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
                                int64_t iops_rd_max,
                                bool has_iops_wr_max,
                                int64_t iops_wr_max,
+                               bool has_bps_max_length,
+                               int64_t bps_max_length,
+                               bool has_bps_rd_max_length,
+                               int64_t bps_rd_max_length,
+                               bool has_bps_wr_max_length,
+                               int64_t bps_wr_max_length,
+                               bool has_iops_max_length,
+                               int64_t iops_max_length,
+                               bool has_iops_rd_max_length,
+                               int64_t iops_rd_max_length,
+                               bool has_iops_wr_max_length,
+                               int64_t iops_wr_max_length,
                                bool has_iops_size,
                                int64_t iops_size,
                                bool has_group,
@@ -2626,7 +2641,7 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         goto out;
     }
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     cfg.buckets[THROTTLE_BPS_TOTAL].avg = bps;
     cfg.buckets[THROTTLE_BPS_READ].avg  = bps_rd;
     cfg.buckets[THROTTLE_BPS_WRITE].avg = bps_wr;
@@ -2654,11 +2669,30 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         cfg.buckets[THROTTLE_OPS_WRITE].max = iops_wr_max;
     }
 
+    if (has_bps_max_length) {
+        cfg.buckets[THROTTLE_BPS_TOTAL].burst_length = bps_max_length;
+    }
+    if (has_bps_rd_max_length) {
+        cfg.buckets[THROTTLE_BPS_READ].burst_length = bps_rd_max_length;
+    }
+    if (has_bps_wr_max_length) {
+        cfg.buckets[THROTTLE_BPS_WRITE].burst_length = bps_wr_max_length;
+    }
+    if (has_iops_max_length) {
+        cfg.buckets[THROTTLE_OPS_TOTAL].burst_length = iops_max_length;
+    }
+    if (has_iops_rd_max_length) {
+        cfg.buckets[THROTTLE_OPS_READ].burst_length = iops_rd_max_length;
+    }
+    if (has_iops_wr_max_length) {
+        cfg.buckets[THROTTLE_OPS_WRITE].burst_length = iops_wr_max_length;
+    }
+
     if (has_iops_size) {
         cfg.op_size = iops_size;
     }
 
-    if (!check_throttle_config(&cfg, errp)) {
+    if (!throttle_is_valid(&cfg, errp)) {
         goto out;
     }
 
@@ -4086,6 +4120,30 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "throttling.bps-write-max",
             .type = QEMU_OPT_NUMBER,
             .help = "total bytes write burst",
+        },{
+            .name = "throttling.iops-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-total-max burst period, in seconds",
+        },{
+            .name = "throttling.iops-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-read-max burst period, in seconds",
+        },{
+            .name = "throttling.iops-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-write-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-total-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-read-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-write-max burst period, in seconds",
         },{
             .name = "throttling.iops-size",
             .type = QEMU_OPT_NUMBER,

bsd-user/i386/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 /* default linux values for the selectors */
 #define __USER_CS	(0x23)
 #define __USER_DS	(0x2B)
@@ -159,3 +162,4 @@ struct target_vm86plus_struct {
 
 #define UNAME_MACHINE "i386"
 
+#endif  /* TARGET_SYSCALL_H */

bsd-user/qemu.h

@@ -17,15 +17,12 @@
 #ifndef QEMU_H
 #define QEMU_H
 
-#include <signal.h>
-#include <string.h>
 
 #include "cpu.h"
 #include "exec/cpu_ldst.h"
 
 #undef DEBUG_REMAP
 #ifdef DEBUG_REMAP
-#include <stdlib.h>
 #endif /* DEBUG_REMAP */
 
 #include "exec/user/abitypes.h"
@@ -38,7 +35,7 @@ enum BSDType {
 extern enum BSDType bsd_type;
 
 #include "syscall_defs.h"
-#include "syscall.h"
+#include "target_syscall.h"
 #include "target_signal.h"
 #include "exec/gdbstub.h"
 

bsd-user/sparc/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 struct target_pt_regs {
 	abi_ulong psr;
 	abi_ulong pc;
@@ -7,3 +10,5 @@ struct target_pt_regs {
 };
 
 #define UNAME_MACHINE "sun4"
+
+#endif  /* TARGET_SYSCALL_H */

bsd-user/sparc64/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 struct target_pt_regs {
 	abi_ulong u_regs[16];
 	abi_ulong tstate;
@@ -8,3 +11,5 @@ struct target_pt_regs {
 };
 
 #define UNAME_MACHINE "sun4u"
+
+#endif  /* TARGET_SYSCALL_H */

bsd-user/x86_64/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 #define __USER_CS	(0x33)
 #define __USER_DS	(0x2B)
 
@@ -114,3 +117,5 @@ struct target_msqid64_ds {
 #define TARGET_ARCH_SET_FS 0x1002
 #define TARGET_ARCH_GET_FS 0x1003
 #define TARGET_ARCH_GET_GS 0x1004
+
+#endif  /* TARGET_SYSCALL_H */

configure

@@ -279,6 +279,7 @@ smartcard=""
 libusb=""
 usb_redir=""
 opengl=""
+opengl_dmabuf="no"
 zlib="yes"
 lzo=""
 snappy=""
@@ -3274,7 +3275,7 @@ libs_softmmu="$libs_softmmu $fdt_libs"
 # opengl probe (for sdl2, gtk, milkymist-tmu2)
 
 if test "$opengl" != "no" ; then
-  opengl_pkgs="epoxy"
+  opengl_pkgs="epoxy libdrm gbm"
   if $pkg_config $opengl_pkgs x11; then
     opengl_cflags="$($pkg_config --cflags $opengl_pkgs) $x11_cflags"
     opengl_libs="$($pkg_config --libs $opengl_pkgs) $x11_libs"
@@ -3292,6 +3293,18 @@ if test "$opengl" != "no" ; then
   fi
 fi
 
+if test "$opengl" = "yes"; then
+  cat > $TMPC << EOF
+#include <epoxy/egl.h>
+#ifndef EGL_MESA_image_dma_buf_export
+# error mesa/epoxy lacks support for dmabufs (mesa 10.6+)
+#endif
+int main(void) { return 0; }
+EOF
+  if compile_prog "" "" ; then
+    opengl_dmabuf=yes
+  fi
+fi
 
 ##########################################
 # archipelago probe
@@ -4752,6 +4765,7 @@ echo "smartcard support $smartcard"
 echo "libusb            $libusb"
 echo "usb net redir     $usb_redir"
 echo "OpenGL support    $opengl"
+echo "OpenGL dmabufs    $opengl_dmabuf"
 echo "libiscsi support  $libiscsi"
 echo "libnfs support    $libnfs"
 echo "build guest agent $guest_agent"
@@ -5050,6 +5064,7 @@ if test "$gtk" = "yes" ; then
   echo "CONFIG_GTK=y" >> $config_host_mak
   echo "CONFIG_GTKABI=$gtkabi" >> $config_host_mak
   echo "GTK_CFLAGS=$gtk_cflags" >> $config_host_mak
+  echo "GTK_LIBS=$gtk_libs" >> $config_host_mak
   if test "$gtk_gl" = "yes" ; then
     echo "CONFIG_GTK_GL=y" >> $config_host_mak
   fi
@@ -5158,6 +5173,9 @@ if test "$opengl" = "yes" ; then
   echo "CONFIG_OPENGL=y" >> $config_host_mak
   echo "OPENGL_CFLAGS=$opengl_cflags" >> $config_host_mak
   echo "OPENGL_LIBS=$opengl_libs" >> $config_host_mak
+  if test "$opengl_dmabuf" = "yes" ; then
+    echo "CONFIG_OPENGL_DMABUF=y" >> $config_host_mak
+  fi
 fi
 
 if test "$lzo" = "yes" ; then

contrib/ivshmem-client/ivshmem-client.h

@@ -19,7 +19,6 @@
  * purposes.
  */
 
-#include <limits.h>
 #include <sys/select.h>
 
 #include "qemu/queue.h"

contrib/ivshmem-server/ivshmem-server.h

@@ -26,10 +26,7 @@
  * associated to the ivshmem shared memory.
  */
 
-#include <limits.h>
 #include <sys/select.h>
-#include <stdint.h>
-#include <stdbool.h>
 
 #include "qemu/event_notifier.h"
 #include "qemu/queue.h"

disas/arm-a64.cc

@@ -17,12 +17,13 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "vixl/a64/disasm-a64.h"
-
 extern "C" {
+#include "qemu/osdep.h"
 #include "disas/bfd.h"
 }
 
+#include "vixl/a64/disasm-a64.h"
+
 using namespace vixl;
 
 static Decoder *vixl_decoder = NULL;

disas/mips.c

@@ -1405,6 +1405,10 @@ const struct mips_opcode mips_builtin_opcodes[] =
 {"cmp.sor.d",  "D,S,T", 0x46a00019, 0xffe0003f, RD_S|RD_T|WR_D|FP_D,  0, I32R6},
 {"cmp.sune.d", "D,S,T", 0x46a0001a, 0xffe0003f, RD_S|RD_T|WR_D|FP_D,  0, I32R6},
 {"cmp.sne.d",  "D,S,T", 0x46a0001b, 0xffe0003f, RD_S|RD_T|WR_D|FP_D,  0, I32R6},
+{"dvp",        "",      0x41600024, 0xffffffff, TRAP,                 0, I32R6},
+{"dvp",        "t",     0x41600024, 0xffe0ffff, TRAP|WR_t,            0, I32R6},
+{"evp",        "",      0x41600004, 0xffffffff, TRAP,                 0, I32R6},
+{"evp",        "t",     0x41600004, 0xffe0ffff, TRAP|WR_t,            0, I32R6},
 
 /* MSA */
 {"sll.b",   "+d,+e,+f", 0x7800000d, 0xffe0003f, WR_VD|RD_VS|RD_VT,  0, MSA},

docs/qapi-code-gen.txt

@@ -1,7 +1,7 @@
 = How to use the QAPI code generator =
 
 Copyright IBM Corp. 2011
-Copyright (C) 2012-2015 Red Hat, Inc.
+Copyright (C) 2012-2016 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.
@@ -52,7 +52,7 @@ schema.  The documentation is delimited between two lines of ##, then
 the first line names the expression, an optional overview is provided,
 then individual documentation about each member of 'data' is provided,
 and finally, a 'Since: x.y.z' tag lists the release that introduced
-the expression.  Optional fields are tagged with the phrase
+the expression.  Optional members are tagged with the phrase
 '#optional', often with their default value; and extensions added
 after the expression was first released are also given a '(since
 x.y.z)' comment.  For example:
@@ -108,15 +108,15 @@ user-defined type names, while built-in types are lowercase. Type
 definitions should not end in 'Kind', as this namespace is used for
 creating implicit C enums for visiting union types, or in 'List', as
 this namespace is used for creating array types.  Command names,
-and field names within a type, should be all lower case with words
+and member names within a type, should be all lower case with words
 separated by a hyphen.  However, some existing older commands and
 complex types use underscore; when extending such expressions,
 consistency is preferred over blindly avoiding underscore.  Event
-names should be ALL_CAPS with words separated by underscore.  Field
+names should be ALL_CAPS with words separated by underscore.  Member
 names cannot start with 'has-' or 'has_', as this is reserved for
-tracking optional fields.
+tracking optional members.
 
-Any name (command, event, type, field, or enum value) beginning with
+Any name (command, event, type, member, or enum value) beginning with
 "x-" is marked experimental, and may be withdrawn or changed
 incompatibly in a future release.  All names must begin with a letter,
 and contain only ASCII letters, digits, dash, and underscore.  There
@@ -127,7 +127,7 @@ the vendor), even if the rest of the name uses dash (example:
 __com.redhat_drive-mirror).  Names beginning with 'q_' are reserved
 for the generator: QMP names that resemble C keywords or other
 problematic strings will be munged in C to use this prefix.  For
-example, a field named "default" in qapi becomes "q_default" in the
+example, a member named "default" in qapi becomes "q_default" in the
 generated C code.
 
 In the rest of this document, usage lines are given for each
@@ -217,17 +217,18 @@ and must continue to work).
 
 On output structures (only mentioned in the 'returns' side of a command),
 changing from mandatory to optional is in general unsafe (older clients may be
-expecting the field, and could crash if it is missing), although it can be done
+expecting the member, and could crash if it is missing), although it
-if the only way that the optional argument will be omitted is when it is
+can be done if the only way that the optional argument will be omitted
-triggered by the presence of a new input flag to the command that older clients
+is when it is triggered by the presence of a new input flag to the
-don't know to send.  Changing from optional to mandatory is safe.
+command that older clients don't know to send.  Changing from optional
+to mandatory is safe.
 
 A structure that is used in both input and output of various commands
 must consider the backwards compatibility constraints of both directions
 of use.
 
 A struct definition can specify another struct as its base.
-In this case, the fields of the base type are included as top-level fields
+In this case, the members of the base type are included as top-level members
 of the new struct's dictionary in the Client JSON Protocol wire
 format. An example definition is:
 
@@ -237,7 +238,7 @@ format. An example definition is:
    'data': { '*backing': 'str' } }
 
 An example BlockdevOptionsGenericCOWFormat object on the wire could use
-both fields like this:
+both members like this:
 
  { "file": "/some/place/my-image",
    "backing": "/some/place/my-backing-file" }
@@ -262,7 +263,7 @@ The enum constants will be named by using a heuristic to turn the
 type name into a set of underscore separated words. For the example
 above, 'MyEnum' will turn into 'MY_ENUM' giving a constant name
 of 'MY_ENUM_VALUE1' for the first value. If the default heuristic
-does not result in a desirable name, the optional 'prefix' field
+does not result in a desirable name, the optional 'prefix' member
 can be used when defining the enum.
 
 The enumeration values are passed as strings over the Client JSON
@@ -275,9 +276,9 @@ converting between strings and enum values.  Since the wire format
 always passes by name, it is acceptable to reorder or add new
 enumeration members in any location without breaking clients of Client
 JSON Protocol; however, removing enum values would break
-compatibility.  For any struct that has a field that will only contain
+compatibility.  For any struct that has a member that will only contain
-a finite set of string values, using an enum type for that field is
+a finite set of string values, using an enum type for that member is
-better than open-coding the field to be type 'str'.
+better than open-coding the member to be type 'str'.
 
 
 === Union types ===
@@ -305,8 +306,8 @@ values to data types like in this example:
              'qcow2': 'Qcow2Options' } }
 
 In the Client JSON Protocol, a simple union is represented by a
-dictionary that contains the 'type' field as a discriminator, and a
+dictionary that contains the 'type' member as a discriminator, and a
-'data' field that is of the specified data type corresponding to the
+'data' member that is of the specified data type corresponding to the
 discriminator value, as in these examples:
 
  { "type": "file", "data" : { "filename": "/some/place/my-image" } }
@@ -321,14 +322,14 @@ enum.  The value for each branch can be of any type.
 
 A flat union definition specifies a struct as its base, and
 avoids nesting on the wire.  All branches of the union must be
-complex types, and the top-level fields of the union dictionary on
+complex types, and the top-level members of the union dictionary on
-the wire will be combination of fields from both the base type and the
+the wire will be combination of members from both the base type and the
 appropriate branch type (when merging two dictionaries, there must be
-no keys in common).  The 'discriminator' field must be the name of an
+no keys in common).  The 'discriminator' member must be the name of an
 enum-typed member of the base struct.
 
 The following example enhances the above simple union example by
-adding a common field 'readonly', renaming the discriminator to
+adding a common member 'readonly', renaming the discriminator to
 something more applicable, and reducing the number of {} required on
 the wire:
 
@@ -353,8 +354,8 @@ the user, but because it must map to a base member with enum type, the
 code generator can ensure that branches exist for all values of the
 enum (although the order of the keys need not match the declaration of
 the enum).  In the resulting generated C data types, a flat union is
-represented as a struct with the base member fields included directly,
+represented as a struct with the base members included directly, and
-and then a union of structures for each branch of the struct.
+then a union of structures for each branch of the struct.
 
 A simple union can always be re-written as a flat union where the base
 class has a single member named 'type', and where each branch of the
@@ -424,10 +425,10 @@ string name of a complex type, or a dictionary that declares an
 anonymous type with the same semantics as a 'struct' expression, with
 one exception noted below when 'gen' is used.
 
-The 'returns' member describes what will appear in the "return" field
+The 'returns' member describes what will appear in the "return" member
 of a Client JSON Protocol reply on successful completion of a command.
 The member is optional from the command declaration; if absent, the
-"return" field will be an empty dictionary.  If 'returns' is present,
+"return" member will be an empty dictionary.  If 'returns' is present,
 it must be the string name of a complex or built-in type, a
 one-element array containing the name of a complex or built-in type,
 with one exception noted below when 'gen' is used.  Although it is
@@ -435,7 +436,7 @@ permitted to have the 'returns' member name a built-in type or an
 array of built-in types, any command that does this cannot be extended
 to return additional information in the future; thus, new commands
 should strongly consider returning a dictionary-based type or an array
-of dictionaries, even if the dictionary only contains one field at the
+of dictionaries, even if the dictionary only contains one member at the
 present.
 
 All commands in Client JSON Protocol use a dictionary to report
@@ -478,7 +479,7 @@ response is not possible (although the command will still return a
 normal dictionary error on failure).  When a successful reply is not
 possible, the command expression should include the optional key
 'success-response' with boolean value false.  So far, only QGA makes
-use of this field.
+use of this member.
 
 
 === Events ===
@@ -656,7 +657,7 @@ Union types
 
     { "name": "BlockdevOptions", "meta-type": "object",
       "members": [
-          { "name": "kind", "type": "BlockdevOptionsKind" } ],
+          { "name": "type", "type": "BlockdevOptionsKind" } ],
       "tag": "type",
       "variants": [
           { "case": "file", "type": ":obj-FileOptions-wrapper" },
@@ -722,33 +723,38 @@ the names of built-in types.  Clients should examine member
 
 == Code generation ==
 
-Schemas are fed into four scripts to generate all the code/files that,
+Schemas are fed into five scripts to generate all the code/files that,
 paired with the core QAPI libraries, comprise everything required to
 take JSON commands read in by a Client JSON Protocol server, unmarshal
 the arguments into the underlying C types, call into the corresponding
-C function, and map the response back to a Client JSON Protocol
+C function, map the response back to a Client JSON Protocol response
-response to be returned to the user.
+to be returned to the user, and introspect the commands.
 
-As an example, we'll use the following schema, which describes a single
+As an example, we'll use the following schema, which describes a
-complex user-defined type (which will produce a C struct, along with a list
+single complex user-defined type, along with command which takes a
-node structure that can be used to chain together a list of such types in
+list of that type as a parameter, and returns a single element of that
-case we want to accept/return a list of this type with a command), and a
+type.  The user is responsible for writing the implementation of
-command which takes that type as a parameter and returns the same type:
+qmp_my_command(); everything else is produced by the generator.
 
     $ cat example-schema.json
     { 'struct': 'UserDefOne',
-      'data': { 'integer': 'int', 'string': 'str' } }
+      'data': { 'integer': 'int', '*string': 'str' } }
 
     { 'command': 'my-command',
-      'data':    {'arg1': 'UserDefOne'},
+      'data': { 'arg1': ['UserDefOne'] },
       'returns': 'UserDefOne' }
 
     { 'event': 'MY_EVENT' }
 
+For a more thorough look at generated code, the testsuite includes
+tests/qapi-schema/qapi-schema-tests.json that covers more examples of
+what the generator will accept, and compiles the resulting C code as
+part of 'make check-unit'.
+
 === scripts/qapi-types.py ===
 
-Used to generate the C types defined by a schema. The following files are
+Used to generate the C types defined by a schema, along with
-created:
+supporting code. The following files are created:
 
 $(prefix)qapi-types.h - C types corresponding to types defined in
                         the schema you pass in
@@ -763,38 +769,6 @@ Example:
 
     $ python scripts/qapi-types.py --output-dir="qapi-generated" \
     --prefix="example-" example-schema.json
-    $ cat qapi-generated/example-qapi-types.c
-[Uninteresting stuff omitted...]
-
-    void qapi_free_UserDefOne(UserDefOne *obj)
-    {
-        QapiDeallocVisitor *qdv;
-        Visitor *v;
-
-        if (!obj) {
-            return;
-        }
-
-        qdv = qapi_dealloc_visitor_new();
-        v = qapi_dealloc_get_visitor(qdv);
-        visit_type_UserDefOne(v, &obj, NULL, NULL);
-        qapi_dealloc_visitor_cleanup(qdv);
-    }
-
-    void qapi_free_UserDefOneList(UserDefOneList *obj)
-    {
-        QapiDeallocVisitor *qdv;
-        Visitor *v;
-
-        if (!obj) {
-            return;
-        }
-
-        qdv = qapi_dealloc_visitor_new();
-        v = qapi_dealloc_get_visitor(qdv);
-        visit_type_UserDefOneList(v, &obj, NULL, NULL);
-        qapi_dealloc_visitor_cleanup(qdv);
-    }
     $ cat qapi-generated/example-qapi-types.h
 [Uninteresting stuff omitted...]
 
@@ -809,29 +783,59 @@ Example:
 
     struct UserDefOne {
         int64_t integer;
+        bool has_string;
         char *string;
     };
 
     void qapi_free_UserDefOne(UserDefOne *obj);
 
     struct UserDefOneList {
-        union {
-            UserDefOne *value;
-            uint64_t padding;
-        };
         UserDefOneList *next;
+        UserDefOne *value;
     };
 
     void qapi_free_UserDefOneList(UserDefOneList *obj);
 
     #endif
+    $ cat qapi-generated/example-qapi-types.c
+[Uninteresting stuff omitted...]
+
+    void qapi_free_UserDefOne(UserDefOne *obj)
+    {
+        QapiDeallocVisitor *qdv;
+        Visitor *v;
+
+        if (!obj) {
+            return;
+        }
+
+        qdv = qapi_dealloc_visitor_new();
+        v = qapi_dealloc_get_visitor(qdv);
+        visit_type_UserDefOne(v, NULL, &obj, NULL);
+        qapi_dealloc_visitor_cleanup(qdv);
+    }
+
+    void qapi_free_UserDefOneList(UserDefOneList *obj)
+    {
+        QapiDeallocVisitor *qdv;
+        Visitor *v;
+
+        if (!obj) {
+            return;
+        }
+
+        qdv = qapi_dealloc_visitor_new();
+        v = qapi_dealloc_get_visitor(qdv);
+        visit_type_UserDefOneList(v, NULL, &obj, NULL);
+        qapi_dealloc_visitor_cleanup(qdv);
+    }
 
 === scripts/qapi-visit.py ===
 
-Used to generate the visitor functions used to walk through and convert
+Used to generate the visitor functions used to walk through and
-a QObject (as provided by QMP) to a native C data structure and
+convert between a native QAPI C data structure and some other format
-vice-versa, as well as the visitor function used to dealloc a complex
+(such as QObject); the generated functions are named visit_type_FOO()
-schema-defined C type.
+and visit_type_FOO_members().
 
 The following files are generated:
 
@@ -848,41 +852,62 @@ Example:
 
     $ python scripts/qapi-visit.py --output-dir="qapi-generated"
     --prefix="example-" example-schema.json
+    $ cat qapi-generated/example-qapi-visit.h
+[Uninteresting stuff omitted...]
+
+    #ifndef EXAMPLE_QAPI_VISIT_H
+    #define EXAMPLE_QAPI_VISIT_H
+
+[Visitors for built-in types omitted...]
+
+    void visit_type_UserDefOne_members(Visitor *v, UserDefOne *obj, Error **errp);
+    void visit_type_UserDefOne(Visitor *v, const char *name, UserDefOne **obj, Error **errp);
+    void visit_type_UserDefOneList(Visitor *v, const char *name, UserDefOneList **obj, Error **errp);
+
+    #endif
     $ cat qapi-generated/example-qapi-visit.c
 [Uninteresting stuff omitted...]
 
-    static void visit_type_UserDefOne_fields(Visitor *v, UserDefOne **obj, Error **errp)
+    void visit_type_UserDefOne_members(Visitor *v, UserDefOne *obj, Error **errp)
     {
         Error *err = NULL;
 
-        visit_type_int(v, &(*obj)->integer, "integer", &err);
+        visit_type_int(v, "integer", &obj->integer, &err);
         if (err) {
             goto out;
         }
-        visit_type_str(v, &(*obj)->string, "string", &err);
+        if (visit_optional(v, "string", &obj->has_string)) {
-        if (err) {
+            visit_type_str(v, "string", &obj->string, &err);
-            goto out;
+            if (err) {
+                goto out;
+            }
         }
 
     out:
         error_propagate(errp, err);
     }
 
-    void visit_type_UserDefOne(Visitor *v, UserDefOne **obj, const char *name, Error **errp)
+    void visit_type_UserDefOne(Visitor *v, const char *name, UserDefOne **obj, Error **errp)
     {
         Error *err = NULL;
 
-        visit_start_struct(v, (void **)obj, "UserDefOne", name, sizeof(UserDefOne), &err);
+        visit_start_struct(v, name, (void **)obj, sizeof(UserDefOne), &err);
-        if (!err) {
+        if (err) {
-            if (*obj) {
+            goto out;
-                visit_type_UserDefOne_fields(v, obj, errp);
-            }
-            visit_end_struct(v, &err);
         }
+        if (!*obj) {
+            goto out_obj;
+        }
+        visit_type_UserDefOne_members(v, *obj, &err);
+        error_propagate(errp, err);
+        err = NULL;
+    out_obj:
+        visit_end_struct(v, &err);
+    out:
         error_propagate(errp, err);
     }
 
-    void visit_type_UserDefOneList(Visitor *v, UserDefOneList **obj, const char *name, Error **errp)
+    void visit_type_UserDefOneList(Visitor *v, const char *name, UserDefOneList **obj, Error **errp)
     {
         Error *err = NULL;
         GenericList *i, **prev;
@@ -893,35 +918,24 @@ Example:
         }
 
         for (prev = (GenericList **)obj;
-             !err && (i = visit_next_list(v, prev, &err)) != NULL;
+             !err && (i = visit_next_list(v, prev, sizeof(**obj))) != NULL;
              prev = &i) {
             UserDefOneList *native_i = (UserDefOneList *)i;
-            visit_type_UserDefOne(v, &native_i->value, NULL, &err);
+            visit_type_UserDefOne(v, NULL, &native_i->value, &err);
         }
 
-        error_propagate(errp, err);
+        visit_end_list(v);
-        err = NULL;
-        visit_end_list(v, &err);
     out:
         error_propagate(errp, err);
     }
-    $ cat qapi-generated/example-qapi-visit.h
-[Uninteresting stuff omitted...]
-
-    #ifndef EXAMPLE_QAPI_VISIT_H
-    #define EXAMPLE_QAPI_VISIT_H
-
-[Visitors for built-in types omitted...]
-
-    void visit_type_UserDefOne(Visitor *v, UserDefOne **obj, const char *name, Error **errp);
-    void visit_type_UserDefOneList(Visitor *v, UserDefOneList **obj, const char *name, Error **errp);
-
-    #endif
 
 === scripts/qapi-commands.py ===
 
-Used to generate the marshaling/dispatch functions for the commands defined
+Used to generate the marshaling/dispatch functions for the commands
-in the schema. The following files are generated:
+defined in the schema. The generated code implements
+qmp_marshal_COMMAND() (mentioned in qmp-commands.hx, and registered
+automatically), and declares qmp_COMMAND() that the user must
+implement.  The following files are generated:
 
 $(prefix)qmp-marshal.c: command marshal/dispatch functions for each
                         QMP command defined in the schema. Functions
@@ -939,6 +953,19 @@ Example:
 
     $ python scripts/qapi-commands.py --output-dir="qapi-generated"
     --prefix="example-" example-schema.json
+    $ cat qapi-generated/example-qmp-commands.h
+[Uninteresting stuff omitted...]
+
+    #ifndef EXAMPLE_QMP_COMMANDS_H
+    #define EXAMPLE_QMP_COMMANDS_H
+
+    #include "example-qapi-types.h"
+    #include "qapi/qmp/qdict.h"
+    #include "qapi/error.h"
+
+    UserDefOne *qmp_my_command(UserDefOneList *arg1, Error **errp);
+
+    #endif
     $ cat qapi-generated/example-qmp-marshal.c
 [Uninteresting stuff omitted...]
 
@@ -950,7 +977,7 @@ Example:
         Visitor *v;
 
         v = qmp_output_get_visitor(qov);
-        visit_type_UserDefOne(v, &ret_in, "unused", &err);
+        visit_type_UserDefOne(v, "unused", &ret_in, &err);
         if (err) {
             goto out;
         }
@@ -961,7 +988,7 @@ Example:
         qmp_output_visitor_cleanup(qov);
         qdv = qapi_dealloc_visitor_new();
         v = qapi_dealloc_get_visitor(qdv);
-        visit_type_UserDefOne(v, &ret_in, "unused", NULL);
+        visit_type_UserDefOne(v, "unused", &ret_in, NULL);
         qapi_dealloc_visitor_cleanup(qdv);
     }
 
@@ -972,10 +999,10 @@ Example:
         QmpInputVisitor *qiv = qmp_input_visitor_new_strict(QOBJECT(args));
         QapiDeallocVisitor *qdv;
         Visitor *v;
-        UserDefOne *arg1 = NULL;
+        UserDefOneList *arg1 = NULL;
 
         v = qmp_input_get_visitor(qiv);
-        visit_type_UserDefOne(v, &arg1, "arg1", &err);
+        visit_type_UserDefOneList(v, "arg1", &arg1, &err);
         if (err) {
             goto out;
         }
@@ -992,7 +1019,7 @@ Example:
         qmp_input_visitor_cleanup(qiv);
         qdv = qapi_dealloc_visitor_new();
         v = qapi_dealloc_get_visitor(qdv);
-        visit_type_UserDefOne(v, &arg1, "arg1", NULL);
+        visit_type_UserDefOneList(v, "arg1", &arg1, NULL);
         qapi_dealloc_visitor_cleanup(qdv);
     }
 
@@ -1002,24 +1029,12 @@ Example:
     }
 
     qapi_init(qmp_init_marshal);
-    $ cat qapi-generated/example-qmp-commands.h
-[Uninteresting stuff omitted...]
-
-    #ifndef EXAMPLE_QMP_COMMANDS_H
-    #define EXAMPLE_QMP_COMMANDS_H
-
-    #include "example-qapi-types.h"
-    #include "qapi/qmp/qdict.h"
-    #include "qapi/error.h"
-
-    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
+Used to generate the event-related C code defined by a schema, with
-following files are created:
+implementations for qapi_event_send_FOO(). The following files are
+created:
 
 $(prefix)qapi-event.h - Function prototypes for each event type, plus an
                         enumeration of all event names
@@ -1029,6 +1044,27 @@ Example:
 
     $ python scripts/qapi-event.py --output-dir="qapi-generated"
     --prefix="example-" example-schema.json
+    $ 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);
+
+    typedef enum example_QAPIEvent {
+        EXAMPLE_QAPI_EVENT_MY_EVENT = 0,
+        EXAMPLE_QAPI_EVENT__MAX = 1,
+    } example_QAPIEvent;
+
+    extern const char *const example_QAPIEvent_lookup[];
+
+    #endif
     $ cat qapi-generated/example-qapi-event.c
 [Uninteresting stuff omitted...]
 
@@ -1054,27 +1090,6 @@ Example:
         [EXAMPLE_QAPI_EVENT_MY_EVENT] = "MY_EVENT",
         [EXAMPLE_QAPI_EVENT__MAX] = 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);
-
-    typedef enum example_QAPIEvent {
-        EXAMPLE_QAPI_EVENT_MY_EVENT = 0,
-        EXAMPLE_QAPI_EVENT__MAX = 1,
-    } example_QAPIEvent;
-
-    extern const char *const example_QAPIEvent_lookup[];
-
-    #endif
 
 === scripts/qapi-introspect.py ===
 
@@ -1089,17 +1104,6 @@ Example:
 
     $ python scripts/qapi-introspect.py --output-dir="qapi-generated"
     --prefix="example-" example-schema.json
-    $ cat qapi-generated/example-qmp-introspect.c
-[Uninteresting stuff omitted...]
-
-    const char example_qmp_schema_json[] = "["
-        "{\"arg-type\": \"0\", \"meta-type\": \"event\", \"name\": \"MY_EVENT\"}, "
-        "{\"arg-type\": \"1\", \"meta-type\": \"command\", \"name\": \"my-command\", \"ret-type\": \"2\"}, "
-        "{\"members\": [], \"meta-type\": \"object\", \"name\": \"0\"}, "
-        "{\"members\": [{\"name\": \"arg1\", \"type\": \"2\"}], \"meta-type\": \"object\", \"name\": \"1\"}, "
-        "{\"members\": [{\"name\": \"integer\", \"type\": \"int\"}, {\"name\": \"string\", \"type\": \"str\"}], \"meta-type\": \"object\", \"name\": \"2\"}, "
-        "{\"json-type\": \"int\", \"meta-type\": \"builtin\", \"name\": \"int\"}, "
-        "{\"json-type\": \"string\", \"meta-type\": \"builtin\", \"name\": \"str\"}]";
     $ cat qapi-generated/example-qmp-introspect.h
 [Uninteresting stuff omitted...]
 
@@ -1109,3 +1113,15 @@ Example:
     extern const char example_qmp_schema_json[];
 
     #endif
+    $ cat qapi-generated/example-qmp-introspect.c
+[Uninteresting stuff omitted...]
+
+    const char example_qmp_schema_json[] = "["
+        "{\"arg-type\": \"0\", \"meta-type\": \"event\", \"name\": \"MY_EVENT\"}, "
+        "{\"arg-type\": \"1\", \"meta-type\": \"command\", \"name\": \"my-command\", \"ret-type\": \"2\"}, "
+        "{\"members\": [], \"meta-type\": \"object\", \"name\": \"0\"}, "
+        "{\"members\": [{\"name\": \"arg1\", \"type\": \"[2]\"}], \"meta-type\": \"object\", \"name\": \"1\"}, "
+        "{\"members\": [{\"name\": \"integer\", \"type\": \"int\"}, {\"default\": null, \"name\": \"string\", \"type\": \"str\"}], \"meta-type\": \"object\", \"name\": \"2\"}, "
+        "{\"element-type\": \"2\", \"meta-type\": \"array\", \"name\": \"[2]\"}, "
+        "{\"json-type\": \"int\", \"meta-type\": \"builtin\", \"name\": \"int\"}, "
+        "{\"json-type\": \"string\", \"meta-type\": \"builtin\", \"name\": \"str\"}]";

docs/qmp-events.txt

@@ -220,6 +220,24 @@ Data:
   },
   "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
 
+DUMP_COMPLETED
+--------------
+
+Emitted when the guest has finished one memory dump.
+
+Data:
+
+- "result": DumpQueryResult type described in qapi-schema.json
+- "error": Error message when dump failed. This is only a
+  human-readable string provided when dump failed. It should not be
+  parsed in any way (json-string, optional)
+
+Example:
+
+{ "event": "DUMP_COMPLETED",
+  "data": {"result": {"total": 1090650112, "status": "completed",
+                      "completed": 1090650112} } }
+
 GUEST_PANICKED
 --------------
 

docs/qmp-spec.txt

@@ -3,7 +3,7 @@
 0. About This Document
 ======================
 
-Copyright (C) 2009-2015 Red Hat, Inc.
+Copyright (C) 2009-2016 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.
@@ -277,7 +277,7 @@ However, Clients must not assume any particular:
 - Amount of errors generated by a command, that is, new errors can be added
   to any existing command in newer versions of the Server
 
-Any command or field name beginning with "x-" is deemed experimental,
+Any command or member name beginning with "x-" is deemed experimental,
 and may be withdrawn or changed in an incompatible manner in a future
 release.
 

docs/specs/qcow2.txt

@@ -103,7 +103,18 @@ in the description of a field.
                     write to an image with unknown auto-clear features if it
                     clears the respective bits from this field first.
 
-                    Bits 0-63:  Reserved (set to 0)
+                    Bit 0:      Bitmaps extension bit
+                                This bit indicates consistency for the bitmaps
+                                extension data.
+
+                                It is an error if this bit is set without the
+                                bitmaps extension present.
+
+                                If the bitmaps extension is present but this
+                                bit is unset, the bitmaps extension data must be
+                                considered inconsistent.
+
+                    Bits 1-63:  Reserved (set to 0)
 
          96 -  99:  refcount_order
                     Describes the width of a reference count block entry (width
@@ -123,6 +134,7 @@ be stored. Each extension has a structure like the following:
                         0x00000000 - End of the header extension area
                         0xE2792ACA - Backing file format name
                         0x6803f857 - Feature name table
+                        0x23852875 - Bitmaps extension
                         other      - Unknown header extension, can be safely
                                      ignored
 
@@ -166,6 +178,36 @@ the header extension data. Each entry look like this:
                     terminated if it has full length)
 
 
+== Bitmaps extension ==
+
+The bitmaps extension is an optional header extension. It provides the ability
+to store bitmaps related to a virtual disk. For now, there is only one bitmap
+type: the dirty tracking bitmap, which tracks virtual disk changes from some
+point in time.
+
+The data of the extension should be considered consistent only if the
+corresponding auto-clear feature bit is set, see autoclear_features above.
+
+The fields of the bitmaps extension are:
+
+    Byte  0 -  3:  nb_bitmaps
+                   The number of bitmaps contained in the image. Must be
+                   greater than or equal to 1.
+
+                   Note: Qemu currently only supports up to 65535 bitmaps per
+                   image.
+
+          4 -  7:  Reserved, must be zero.
+
+          8 - 15:  bitmap_directory_size
+                   Size of the bitmap directory in bytes. It is the cumulative
+                   size of all (nb_bitmaps) bitmap headers.
+
+         16 - 23:  bitmap_directory_offset
+                   Offset into the image file at which the bitmap directory
+                   starts. Must be aligned to a cluster boundary.
+
+
 == Host cluster management ==
 
 qcow2 manages the allocation of host clusters by maintaining a reference count
@@ -360,3 +402,180 @@ Snapshot table entry:
 
         variable:   Padding to round up the snapshot table entry size to the
                     next multiple of 8.
+
+
+== Bitmaps ==
+
+As mentioned above, the bitmaps extension provides the ability to store bitmaps
+related to a virtual disk. This section describes how these bitmaps are stored.
+
+All stored bitmaps are related to the virtual disk stored in the same image, so
+each bitmap size is equal to the virtual disk size.
+
+Each bit of the bitmap is responsible for strictly defined range of the virtual
+disk. For bit number bit_nr the corresponding range (in bytes) will be:
+
+    [bit_nr * bitmap_granularity .. (bit_nr + 1) * bitmap_granularity - 1]
+
+Granularity is a property of the concrete bitmap, see below.
+
+
+=== Bitmap directory ===
+
+Each bitmap saved in the image is described in a bitmap directory entry. The
+bitmap directory is a contiguous area in the image file, whose starting offset
+and length are given by the header extension fields bitmap_directory_offset and
+bitmap_directory_size. The entries of the bitmap directory have variable
+length, depending on the lengths of the bitmap name and extra data. These
+entries are also called bitmap headers.
+
+Structure of a bitmap directory entry:
+
+    Byte 0 -  7:    bitmap_table_offset
+                    Offset into the image file at which the bitmap table
+                    (described below) for the bitmap starts. Must be aligned to
+                    a cluster boundary.
+
+         8 - 11:    bitmap_table_size
+                    Number of entries in the bitmap table of the bitmap.
+
+        12 - 15:    flags
+                    Bit
+                      0: in_use
+                         The bitmap was not saved correctly and may be
+                         inconsistent.
+
+                      1: auto
+                         The bitmap must reflect all changes of the virtual
+                         disk by any application that would write to this qcow2
+                         file (including writes, snapshot switching, etc.). The
+                         type of this bitmap must be 'dirty tracking bitmap'.
+
+                      2: extra_data_compatible
+                         This flags is meaningful when the extra data is
+                         unknown to the software (currently any extra data is
+                         unknown to Qemu).
+                         If it is set, the bitmap may be used as expected, extra
+                         data must be left as is.
+                         If it is not set, the bitmap must not be used, but
+                         both it and its extra data be left as is.
+
+                    Bits 3 - 31 are reserved and must be 0.
+
+             16:    type
+                    This field describes the sort of the bitmap.
+                    Values:
+                      1: Dirty tracking bitmap
+
+                    Values 0, 2 - 255 are reserved.
+
+             17:    granularity_bits
+                    Granularity bits. Valid values: 0 - 63.
+
+                    Note: Qemu currently doesn't support granularity_bits
+                    greater than 31.
+
+                    Granularity is calculated as
+                        granularity = 1 << granularity_bits
+
+                    A bitmap's granularity is how many bytes of the image
+                    accounts for one bit of the bitmap.
+
+        18 - 19:    name_size
+                    Size of the bitmap name. Must be non-zero.
+
+                    Note: Qemu currently doesn't support values greater than
+                    1023.
+
+        20 - 23:    extra_data_size
+                    Size of type-specific extra data.
+
+                    For now, as no extra data is defined, extra_data_size is
+                    reserved and should be zero. If it is non-zero the
+                    behavior is defined by extra_data_compatible flag.
+
+        variable:   extra_data
+                    Extra data for the bitmap, occupying extra_data_size bytes.
+                    Extra data must never contain references to clusters or in
+                    some other way allocate additional clusters.
+
+        variable:   name
+                    The name of the bitmap (not null terminated), occupying
+                    name_size bytes. Must be unique among all bitmap names
+                    within the bitmaps extension.
+
+        variable:   Padding to round up the bitmap directory entry size to the
+                    next multiple of 8. All bytes of the padding must be zero.
+
+
+=== Bitmap table ===
+
+Each bitmap is stored using a one-level structure (as opposed to two-level
+structures like for refcounts and guest clusters mapping) for the mapping of
+bitmap data to host clusters. This structure is called the bitmap table.
+
+Each bitmap table has a variable size (stored in the bitmap directory entry)
+and may use multiple clusters, however, it must be contiguous in the image
+file.
+
+Structure of a bitmap table entry:
+
+    Bit       0:    Reserved and must be zero if bits 9 - 55 are non-zero.
+                    If bits 9 - 55 are zero:
+                      0: Cluster should be read as all zeros.
+                      1: Cluster should be read as all ones.
+
+         1 -  8:    Reserved and must be zero.
+
+         9 - 55:    Bits 9 - 55 of the host cluster offset. Must be aligned to
+                    a cluster boundary. If the offset is 0, the cluster is
+                    unallocated; in that case, bit 0 determines how this
+                    cluster should be treated during reads.
+
+        56 - 63:    Reserved and must be zero.
+
+
+=== Bitmap data ===
+
+As noted above, bitmap data is stored in separate clusters, described by the
+bitmap table. Given an offset (in bytes) into the bitmap data, the offset into
+the image file can be obtained as follows:
+
+    image_offset(bitmap_data_offset) =
+        bitmap_table[bitmap_data_offset / cluster_size] +
+            (bitmap_data_offset % cluster_size)
+
+This offset is not defined if bits 9 - 55 of bitmap table entry are zero (see
+above).
+
+Given an offset byte_nr into the virtual disk and the bitmap's granularity, the
+bit offset into the image file to the corresponding bit of the bitmap can be
+calculated like this:
+
+    bit_offset(byte_nr) =
+        image_offset(byte_nr / granularity / 8) * 8 +
+            (byte_nr / granularity) % 8
+
+If the size of the bitmap data is not a multiple of the cluster size then the
+last cluster of the bitmap data contains some unused tail bits. These bits must
+be zero.
+
+
+=== Dirty tracking bitmaps ===
+
+Bitmaps with 'type' field equal to one are dirty tracking bitmaps.
+
+When the virtual disk is in use dirty tracking bitmap may be 'enabled' or
+'disabled'. While the bitmap is 'enabled', all writes to the virtual disk
+should be reflected in the bitmap. A set bit in the bitmap means that the
+corresponding range of the virtual disk (see above) was written to while the
+bitmap was 'enabled'. An unset bit means that this range was not written to.
+
+The software doesn't have to sync the bitmap in the image file with its
+representation in RAM after each write. Flag 'in_use' should be set while the
+bitmap is not synced.
+
+In the image file the 'enabled' state is reflected by the 'auto' flag. If this
+flag is set, the software must consider the bitmap as 'enabled' and start
+tracking virtual disk changes to this bitmap from the first write to the
+virtual disk. If this flag is not set then the bitmap is disabled.

docs/throttle.txt

@@ -0,0 +1,252 @@
+The QEMU throttling infrastructure
+==================================
+Copyright (C) 2016 Igalia, S.L.
+Author: Alberto Garcia <berto@igalia.com>
+
+This work is licensed under the terms of the GNU GPL, version 2 or
+later. See the COPYING file in the top-level directory.
+
+Introduction
+------------
+QEMU includes a throttling module that can be used to set limits to
+I/O operations. The code itself is generic and independent of the I/O
+units, but it is currenly used to limit the number of bytes per second
+and operations per second (IOPS) when performing disk I/O.
+
+This document explains how to use the throttling code in QEMU, and how
+it works internally. The implementation is in throttle.c.
+
+
+Using throttling to limit disk I/O
+----------------------------------
+Two aspects of the disk I/O can be limited: the number of bytes per
+second and the number of operations per second (IOPS). For each one of
+them the user can set a global limit or separate limits for read and
+write operations. This gives us a total of six different parameters.
+
+I/O limits can be set using the throttling.* parameters of -drive, or
+using the QMP 'block_set_io_throttle' command. These are the names of
+the parameters for both cases:
+
+|-----------------------+-----------------------|
+| -drive                | block_set_io_throttle |
+|-----------------------+-----------------------|
+| throttling.iops-total | iops                  |
+| throttling.iops-read  | iops_rd               |
+| throttling.iops-write | iops_wr               |
+| throttling.bps-total  | bps                   |
+| throttling.bps-read   | bps_rd                |
+| throttling.bps-write  | bps_wr                |
+|-----------------------+-----------------------|
+
+It is possible to set limits for both IOPS and bps and the same time,
+and for each case we can decide whether to have separate read and
+write limits or not, but note that if iops-total is set then neither
+iops-read nor iops-write can be set. The same applies to bps-total and
+bps-read/write.
+
+The default value of these parameters is 0, and it means 'unlimited'.
+
+In its most basic usage, the user can add a drive to QEMU with a limit
+of 100 IOPS with the following -drive line:
+
+   -drive file=hd0.qcow2,throttling.iops-total=100
+
+We can do the same using QMP. In this case all these parameters are
+mandatory, so we must set to 0 the ones that we don't want to limit:
+
+   { "execute": "block_set_io_throttle",
+     "arguments": {
+        "device": "virtio0",
+        "iops": 100,
+        "iops_rd": 0,
+        "iops_wr": 0,
+        "bps": 0,
+        "bps_rd": 0,
+        "bps_wr": 0
+     }
+   }
+
+
+I/O bursts
+----------
+In addition to the basic limits we have just seen, QEMU allows the
+user to do bursts of I/O for a configurable amount of time. A burst is
+an amount of I/O that can exceed the basic limit. Bursts are useful to
+allow better performance when there are peaks of activity (the OS
+boots, a service needs to be restarted) while keeping the average
+limits lower the rest of the time.
+
+Two parameters control bursts: their length and the maximum amount of
+I/O they allow. These two can be configured separately for each one of
+the six basic parameters described in the previous section, but in
+this section we'll use 'iops-total' as an example.
+
+The I/O limit during bursts is set using 'iops-total-max', and the
+maximum length (in seconds) is set with 'iops-total-max-length'. So if
+we want to configure a drive with a basic limit of 100 IOPS and allow
+bursts of 2000 IOPS for 60 seconds, we would do it like this (the line
+is split for clarity):
+
+   -drive file=hd0.qcow2,
+          throttling.iops-total=100,
+          throttling.iops-total-max=2000,
+          throttling.iops-total-max-length=60
+
+Or, with QMP:
+
+   { "execute": "block_set_io_throttle",
+     "arguments": {
+        "device": "virtio0",
+        "iops": 100,
+        "iops_rd": 0,
+        "iops_wr": 0,
+        "bps": 0,
+        "bps_rd": 0,
+        "bps_wr": 0,
+        "iops_max": 2000,
+        "iops_max_length": 60,
+     }
+   }
+
+With this, the user can perform I/O on hd0.qcow2 at a rate of 2000
+IOPS for 1 minute before it's throttled down to 100 IOPS.
+
+The user will be able to do bursts again if there's a sufficiently
+long period of time with unused I/O (see below for details).
+
+The default value for 'iops-total-max' is 0 and it means that bursts
+are not allowed. 'iops-total-max-length' can only be set if
+'iops-total-max' is set as well, and its default value is 1 second.
+
+Here's the complete list of parameters for configuring bursts:
+
+|----------------------------------+-----------------------|
+| -drive                           | block_set_io_throttle |
+|----------------------------------+-----------------------|
+| throttling.iops-total-max        | iops_max              |
+| throttling.iops-total-max-length | iops_max_length       |
+| throttling.iops-read-max         | iops_rd_max           |
+| throttling.iops-read-max-length  | iops_rd_max_length    |
+| throttling.iops-write-max        | iops_wr_max           |
+| throttling.iops-write-max-length | iops_wr_max_length    |
+| throttling.bps-total-max         | bps_max               |
+| throttling.bps-total-max-length  | bps_max_length        |
+| throttling.bps-read-max          | bps_rd_max            |
+| throttling.bps-read-max-length   | bps_rd_max_length     |
+| throttling.bps-write-max         | bps_wr_max            |
+| throttling.bps-write-max-length  | bps_wr_max_length     |
+|----------------------------------+-----------------------|
+
+
+Controlling the size of I/O operations
+--------------------------------------
+When applying IOPS limits all I/O operations are treated equally
+regardless of their size. This means that the user can take advantage
+of this in order to circumvent the limits and submit one huge I/O
+request instead of several smaller ones.
+
+QEMU provides a setting called throttling.iops-size to prevent this
+from happening. This setting specifies the size (in bytes) of an I/O
+request for accounting purposes. Larger requests will be counted
+proportionally to this size.
+
+For example, if iops-size is set to 4096 then an 8KB request will be
+counted as two, and a 6KB request will be counted as one and a
+half. This only applies to requests larger than iops-size: smaller
+requests will be always counted as one, no matter their size.
+
+The default value of iops-size is 0 and it means that the size of the
+requests is never taken into account when applying IOPS limits.
+
+
+Applying I/O limits to groups of disks
+--------------------------------------
+In all the examples so far we have seen how to apply limits to the I/O
+performed on individual drives, but QEMU allows grouping drives so
+they all share the same limits.
+
+The way it works is that each drive with I/O limits is assigned to a
+group named using the throttling.group parameter. If this parameter is
+not specified, then the device name (i.e. 'virtio0', 'ide0-hd0') will
+be used as the group name.
+
+Limits set using the throttling.* parameters discussed earlier in this
+document apply to the combined I/O of all members of a group.
+
+Consider this example:
+
+   -drive file=hd1.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd2.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd3.qcow2,throttling.iops-total=3000,throttling.group=bar
+   -drive file=hd4.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd5.qcow2,throttling.iops-total=3000,throttling.group=bar
+   -drive file=hd6.qcow2,throttling.iops-total=5000
+
+Here hd1, hd2 and hd4 are all members of a group named 'foo' with a
+combined IOPS limit of 6000, and hd3 and hd5 are members of 'bar'. hd6
+is left alone (technically it is part of a 1-member group).
+
+Limits are applied in a round-robin fashion so if there are concurrent
+I/O requests on several drives of the same group they will be
+distributed evenly.
+
+When I/O limits are applied to an existing drive using the QMP command
+'block_set_io_throttle', the following things need to be taken into
+account:
+
+   - I/O limits are shared within the same group, so new values will
+     affect all members and overwrite the previous settings. In other
+     words: if different limits are applied to members of the same
+     group, the last one wins.
+
+   - If 'group' is unset it is assumed to be the current group of that
+     drive. If the drive is not in a group yet, it will be added to a
+     group named after the device name.
+
+   - If 'group' is set then the drive will be moved to that group if
+     it was member of a different one. In this case the limits
+     specified in the parameters will be applied to the new group
+     only.
+
+   - I/O limits can be disabled by setting all of them to 0. In this
+     case the device will be removed from its group and the rest of
+     its members will not be affected. The 'group' parameter is
+     ignored.
+
+
+The Leaky Bucket algorithm
+--------------------------
+I/O limits in QEMU are implemented using the leaky bucket algorithm
+(specifically the "Leaky bucket as a meter" variant).
+
+This algorithm uses the analogy of a bucket that leaks water
+constantly. The water that gets into the bucket represents the I/O
+that has been performed, and no more I/O is allowed once the bucket is
+full.
+
+To see the way this corresponds to the throttling parameters in QEMU,
+consider the following values:
+
+  iops-total=100
+  iops-total-max=2000
+  iops-total-max-length=60
+
+  - Water leaks from the bucket at a rate of 100 IOPS.
+  - Water can be added to the bucket at a rate of 2000 IOPS.
+  - The size of the bucket is 2000 x 60 = 120000
+  - If 'iops-total-max-length' is unset then the bucket size is 100.
+
+The bucket is initially empty, therefore water can be added until it's
+full at a rate of 2000 IOPS (the burst rate). Once the bucket is full
+we can only add as much water as it leaks, therefore the I/O rate is
+reduced to 100 IOPS. If we add less water than it leaks then the
+bucket will start to empty, allowing for bursts again.
+
+Note that since water is leaking from the bucket even during bursts,
+it will take a bit more than 60 seconds at 2000 IOPS to fill it
+up. After those 60 seconds the bucket will have leaked 60 x 100 =
+6000, allowing for 3 more seconds of I/O at 2000 IOPS.
+
+Also, due to the way the algorithm works, longer burst can be done at
+a lower I/O rate, e.g. 1000 IOPS during 120 seconds.

docs/tracing.txt

@@ -172,9 +172,6 @@ source tree.  It may not be as powerful as platform-specific or third-party
 trace backends but it is portable.  This is the recommended trace backend
 unless you have specific needs for more advanced backends.
 
-The "simple" backend currently does not capture string arguments, it simply
-records the char* pointer value instead of the string that is pointed to.
-
 === Ftrace ===
 
 The "ftrace" backend writes trace data to ftrace marker. This effectively
@@ -347,3 +344,44 @@ This will immediately call:
 and will generate the TCG code to call:
 
     void trace_foo(uint8_t a1, uint32_t a2);
+
+=== "vcpu" ===
+
+Identifies events that trace vCPU-specific information. It implicitly adds a
+"CPUState*" argument, and extends the tracing print format to show the vCPU
+information. If used together with the "tcg" property, it adds a second
+"TCGv_env" argument that must point to the per-target global TCG register that
+points to the vCPU when guest code is executed (usually the "cpu_env" variable).
+
+The following example events:
+
+    foo(uint32_t a) "a=%x"
+    vcpu bar(uint32_t a) "a=%x"
+    tcg vcpu baz(uint32_t a) "a=%x", "a=%x"
+
+Can be used as:
+
+    #include "trace-tcg.h"
+    
+    CPUArchState *env;
+    TCGv_ptr cpu_env;
+    
+    void some_disassembly_func(...)
+    {
+        /* trace emitted at this point */
+        trace_foo(0xd1);
+        /* trace emitted at this point */
+        trace_bar(ENV_GET_CPU(env), 0xd2);
+        /* trace emitted at this point (env) and when guest code is executed (cpu_env) */
+        trace_baz_tcg(ENV_GET_CPU(env), cpu_env, 0xd3);
+    }
+
+If the translating vCPU has address 0xc1 and code is later executed by vCPU
+0xc2, this would be an example output:
+
+    // at guest code translation
+    foo a=0xd1
+    bar cpu=0xc1 a=0xd2
+    baz_trans cpu=0xc1 a=0xd3
+    // at guest code execution
+    baz_exec cpu=0xc2 a=0xd3

dump.c

@@ -25,6 +25,7 @@
 #include "sysemu/cpus.h"
 #include "qapi/qmp/qerror.h"
 #include "qmp-commands.h"
+#include "qapi-event.h"
 
 #include <zlib.h>
 #ifdef CONFIG_LZO
@@ -82,12 +83,6 @@ static int dump_cleanup(DumpState *s)
     return 0;
 }
 
-static void dump_error(DumpState *s, const char *reason, Error **errp)
-{
-    dump_cleanup(s);
-    error_setg(errp, "%s", reason);
-}
-
 static int fd_write_vmcore(const void *buf, size_t size, void *opaque)
 {
     DumpState *s = opaque;
@@ -128,7 +123,7 @@ static void write_elf64_header(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write elf header", errp);
+        error_setg(errp, "dump: failed to write elf header");
     }
 }
 
@@ -159,7 +154,7 @@ static void write_elf32_header(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write elf header", errp);
+        error_setg(errp, "dump: failed to write elf header");
     }
 }
 
@@ -182,7 +177,7 @@ static void write_elf64_load(DumpState *s, MemoryMapping *memory_mapping,
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf64_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -205,7 +200,7 @@ static void write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf32_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -225,7 +220,7 @@ static void write_elf64_note(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf64_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -245,7 +240,7 @@ static void write_elf64_notes(WriteCoreDumpFunction f, DumpState *s,
         id = cpu_index(cpu);
         ret = cpu_write_elf64_note(f, cpu, id, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write elf notes", errp);
+            error_setg(errp, "dump: failed to write elf notes");
             return;
         }
     }
@@ -253,7 +248,7 @@ static void write_elf64_notes(WriteCoreDumpFunction f, DumpState *s,
     CPU_FOREACH(cpu) {
         ret = cpu_write_elf64_qemunote(f, cpu, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write CPU status", errp);
+            error_setg(errp, "dump: failed to write CPU status");
             return;
         }
     }
@@ -275,7 +270,7 @@ static void write_elf32_note(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf32_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -290,7 +285,7 @@ static void write_elf32_notes(WriteCoreDumpFunction f, DumpState *s,
         id = cpu_index(cpu);
         ret = cpu_write_elf32_note(f, cpu, id, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write elf notes", errp);
+            error_setg(errp, "dump: failed to write elf notes");
             return;
         }
     }
@@ -298,7 +293,7 @@ static void write_elf32_notes(WriteCoreDumpFunction f, DumpState *s,
     CPU_FOREACH(cpu) {
         ret = cpu_write_elf32_qemunote(f, cpu, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write CPU status", errp);
+            error_setg(errp, "dump: failed to write CPU status");
             return;
         }
     }
@@ -326,7 +321,7 @@ static void write_elf_section(DumpState *s, int type, Error **errp)
 
     ret = fd_write_vmcore(&shdr, shdr_size, s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write section header table", errp);
+        error_setg(errp, "dump: failed to write section header table");
     }
 }
 
@@ -336,7 +331,9 @@ static void write_data(DumpState *s, void *buf, int length, Error **errp)
 
     ret = fd_write_vmcore(buf, length, s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to save memory", errp);
+        error_setg(errp, "dump: failed to save memory");
+    } else {
+        s->written_size += length;
     }
 }
 
@@ -568,11 +565,6 @@ static void dump_begin(DumpState *s, Error **errp)
     }
 }
 
-static void dump_completed(DumpState *s)
-{
-    dump_cleanup(s);
-}
-
 static int get_next_block(DumpState *s, GuestPhysBlock *block)
 {
     while (1) {
@@ -624,8 +616,6 @@ static void dump_iterate(DumpState *s, Error **errp)
         }
 
     } while (!get_next_block(s, block));
-
-    dump_completed(s);
 }
 
 static void create_vmcore(DumpState *s, Error **errp)
@@ -765,7 +755,7 @@ static void create_header32(DumpState *s, Error **errp)
     dh->status = cpu_to_dump32(s, status);
 
     if (write_buffer(s->fd, 0, dh, size) < 0) {
-        dump_error(s, "dump: failed to write disk dump header", errp);
+        error_setg(errp, "dump: failed to write disk dump header");
         goto out;
     }
 
@@ -784,7 +774,7 @@ static void create_header32(DumpState *s, Error **errp)
 
     if (write_buffer(s->fd, DISKDUMP_HEADER_BLOCKS *
                      block_size, kh, size) < 0) {
-        dump_error(s, "dump: failed to write kdump sub header", errp);
+        error_setg(errp, "dump: failed to write kdump sub header");
         goto out;
     }
 
@@ -800,7 +790,7 @@ static void create_header32(DumpState *s, Error **errp)
     }
     if (write_buffer(s->fd, offset_note, s->note_buf,
                      s->note_size) < 0) {
-        dump_error(s, "dump: failed to write notes", errp);
+        error_setg(errp, "dump: failed to write notes");
         goto out;
     }
 
@@ -865,7 +855,7 @@ static void create_header64(DumpState *s, Error **errp)
     dh->status = cpu_to_dump32(s, status);
 
     if (write_buffer(s->fd, 0, dh, size) < 0) {
-        dump_error(s, "dump: failed to write disk dump header", errp);
+        error_setg(errp, "dump: failed to write disk dump header");
         goto out;
     }
 
@@ -884,7 +874,7 @@ static void create_header64(DumpState *s, Error **errp)
 
     if (write_buffer(s->fd, DISKDUMP_HEADER_BLOCKS *
                      block_size, kh, size) < 0) {
-        dump_error(s, "dump: failed to write kdump sub header", errp);
+        error_setg(errp, "dump: failed to write kdump sub header");
         goto out;
     }
 
@@ -901,7 +891,7 @@ static void create_header64(DumpState *s, Error **errp)
 
     if (write_buffer(s->fd, offset_note, s->note_buf,
                      s->note_size) < 0) {
-        dump_error(s, "dump: failed to write notes", errp);
+        error_setg(errp, "dump: failed to write notes");
         goto out;
     }
 
@@ -1087,7 +1077,7 @@ static void write_dump_bitmap(DumpState *s, Error **errp)
     while (get_next_page(&block_iter, &pfn, NULL, s)) {
         ret = set_dump_bitmap(last_pfn, pfn, true, dump_bitmap_buf, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to set dump_bitmap", errp);
+            error_setg(errp, "dump: failed to set dump_bitmap");
             goto out;
         }
 
@@ -1104,7 +1094,7 @@ static void write_dump_bitmap(DumpState *s, Error **errp)
         ret = set_dump_bitmap(last_pfn, last_pfn + bits_per_buf, false,
                               dump_bitmap_buf, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to sync dump_bitmap", errp);
+            error_setg(errp, "dump: failed to sync dump_bitmap");
             goto out;
         }
     }
@@ -1237,7 +1227,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
     ret = write_cache(&page_data, buf, s->dump_info.page_size, false);
     g_free(buf);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write page data (zero page)", errp);
+        error_setg(errp, "dump: failed to write page data (zero page)");
         goto out;
     }
 
@@ -1253,7 +1243,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
             ret = write_cache(&page_desc, &pd_zero, sizeof(PageDescriptor),
                               false);
             if (ret < 0) {
-                dump_error(s, "dump: failed to write page desc", errp);
+                error_setg(errp, "dump: failed to write page desc");
                 goto out;
             }
         } else {
@@ -1278,7 +1268,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
 #ifdef CONFIG_LZO
@@ -1291,7 +1281,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
 #endif
@@ -1305,7 +1295,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
 #endif
@@ -1321,7 +1311,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
                 ret = write_cache(&page_data, buf,
                                   s->dump_info.page_size, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
             }
@@ -1333,20 +1323,21 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
             ret = write_cache(&page_desc, &pd, sizeof(PageDescriptor), false);
             if (ret < 0) {
-                dump_error(s, "dump: failed to write page desc", errp);
+                error_setg(errp, "dump: failed to write page desc");
                 goto out;
             }
         }
+        s->written_size += s->dump_info.page_size;
     }
 
     ret = write_cache(&page_desc, NULL, 0, true);
     if (ret < 0) {
-        dump_error(s, "dump: failed to sync cache for page_desc", errp);
+        error_setg(errp, "dump: failed to sync cache for page_desc");
         goto out;
     }
     ret = write_cache(&page_data, NULL, 0, true);
     if (ret < 0) {
-        dump_error(s, "dump: failed to sync cache for page_data", errp);
+        error_setg(errp, "dump: failed to sync cache for page_data");
         goto out;
     }
 
@@ -1390,7 +1381,7 @@ static void create_kdump_vmcore(DumpState *s, Error **errp)
 
     ret = write_start_flat_header(s->fd);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write start flat header", errp);
+        error_setg(errp, "dump: failed to write start flat header");
         return;
     }
 
@@ -1414,11 +1405,9 @@ static void create_kdump_vmcore(DumpState *s, Error **errp)
 
     ret = write_end_flat_header(s->fd);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write end flat header", errp);
+        error_setg(errp, "dump: failed to write end flat header");
         return;
     }
-
-    dump_completed(s);
 }
 
 static ram_addr_t get_start_block(DumpState *s)
@@ -1457,6 +1446,44 @@ static void get_max_mapnr(DumpState *s)
     s->max_mapnr = dump_paddr_to_pfn(s, last_block->target_end);
 }
 
+static DumpState dump_state_global = { .status = DUMP_STATUS_NONE };
+
+static void dump_state_prepare(DumpState *s)
+{
+    /* zero the struct, setting status to active */
+    *s = (DumpState) { .status = DUMP_STATUS_ACTIVE };
+}
+
+bool dump_in_progress(void)
+{
+    DumpState *state = &dump_state_global;
+    return (atomic_read(&state->status) == DUMP_STATUS_ACTIVE);
+}
+
+/* calculate total size of memory to be dumped (taking filter into
+ * acoount.) */
+static int64_t dump_calculate_size(DumpState *s)
+{
+    GuestPhysBlock *block;
+    int64_t size = 0, total = 0, left = 0, right = 0;
+
+    QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+        if (s->has_filter) {
+            /* calculate the overlapped region. */
+            left = MAX(s->begin, block->target_start);
+            right = MIN(s->begin + s->length, block->target_end);
+            size = right - left;
+            size = size > 0 ? size : 0;
+        } else {
+            /* count the whole region in */
+            size = (block->target_end - block->target_start);
+        }
+        total += size;
+    }
+
+    return total;
+}
+
 static void dump_init(DumpState *s, int fd, bool has_format,
                       DumpGuestMemoryFormat format, bool paging, bool has_filter,
                       int64_t begin, int64_t length, Error **errp)
@@ -1466,6 +1493,10 @@ static void dump_init(DumpState *s, int fd, bool has_format,
     Error *err = NULL;
     int ret;
 
+    s->has_format = has_format;
+    s->format = format;
+    s->written_size = 0;
+
     /* kdump-compressed is conflict with paging and filter */
     if (has_format && format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
         assert(!paging && !has_filter);
@@ -1496,6 +1527,10 @@ static void dump_init(DumpState *s, int fd, bool has_format,
 
     guest_phys_blocks_init(&s->guest_phys_blocks);
     guest_phys_blocks_append(&s->guest_phys_blocks);
+    s->total_size = dump_calculate_size(s);
+#ifdef DEBUG_DUMP_GUEST_MEMORY
+    fprintf(stderr, "DUMP: total memory to dump: %lu\n", s->total_size);
+#endif
 
     s->start = get_start_block(s);
     if (s->start == -1) {
@@ -1624,8 +1659,60 @@ cleanup:
     dump_cleanup(s);
 }
 
-void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
+/* this operation might be time consuming. */
-                           int64_t begin, bool has_length,
+static void dump_process(DumpState *s, Error **errp)
+{
+    Error *local_err = NULL;
+    DumpQueryResult *result = NULL;
+
+    if (s->has_format && s->format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
+        create_kdump_vmcore(s, &local_err);
+    } else {
+        create_vmcore(s, &local_err);
+    }
+
+    /* make sure status is written after written_size updates */
+    smp_wmb();
+    atomic_set(&s->status,
+               (local_err ? DUMP_STATUS_FAILED : DUMP_STATUS_COMPLETED));
+
+    /* send DUMP_COMPLETED message (unconditionally) */
+    result = qmp_query_dump(NULL);
+    /* should never fail */
+    assert(result);
+    qapi_event_send_dump_completed(result, !!local_err, (local_err ? \
+                                   error_get_pretty(local_err) : NULL),
+                                   &error_abort);
+    qapi_free_DumpQueryResult(result);
+
+    error_propagate(errp, local_err);
+    dump_cleanup(s);
+}
+
+static void *dump_thread(void *data)
+{
+    Error *err = NULL;
+    DumpState *s = (DumpState *)data;
+    dump_process(s, &err);
+    error_free(err);
+    return NULL;
+}
+
+DumpQueryResult *qmp_query_dump(Error **errp)
+{
+    DumpQueryResult *result = g_new(DumpQueryResult, 1);
+    DumpState *state = &dump_state_global;
+    result->status = atomic_read(&state->status);
+    /* make sure we are reading status and written_size in order */
+    smp_rmb();
+    result->completed = state->written_size;
+    result->total = state->total_size;
+    return result;
+}
+
+void qmp_dump_guest_memory(bool paging, const char *file,
+                           bool has_detach, bool detach,
+                           bool has_begin, int64_t begin, bool has_length,
                            int64_t length, bool has_format,
                            DumpGuestMemoryFormat format, Error **errp)
 {
@@ -1633,6 +1720,19 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
     int fd = -1;
     DumpState *s;
     Error *local_err = NULL;
+    bool detach_p = false;
+
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        error_setg(errp, "Dump not allowed during incoming migration.");
+        return;
+    }
+
+    /* if there is a dump in background, we should wait until the dump
+     * finished */
+    if (dump_in_progress()) {
+        error_setg(errp, "There is a dump in process, please wait.");
+        return;
+    }
 
     /*
      * kdump-compressed format need the whole memory dumped, so paging or
@@ -1652,6 +1752,9 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
         error_setg(errp, QERR_MISSING_PARAMETER, "begin");
         return;
     }
+    if (has_detach) {
+        detach_p = detach;
+    }
 
     /* check whether lzo/snappy is supported */
 #ifndef CONFIG_LZO
@@ -1690,23 +1793,25 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
         return;
     }
 
-    s = g_malloc0(sizeof(DumpState));
+    s = &dump_state_global;
+    dump_state_prepare(s);
 
     dump_init(s, fd, has_format, format, paging, has_begin,
               begin, length, &local_err);
     if (local_err) {
-        g_free(s);
         error_propagate(errp, local_err);
+        atomic_set(&s->status, DUMP_STATUS_FAILED);
         return;
     }
 
-    if (has_format && format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
+    if (detach_p) {
-        create_kdump_vmcore(s, errp);
+        /* detached dump */
+        qemu_thread_create(&s->dump_thread, "dump_thread", dump_thread,
+                           s, QEMU_THREAD_DETACHED);
     } else {
-        create_vmcore(s, errp);
+        /* sync dump */
+        dump_process(s, errp);
     }
-
-    g_free(s);
 }
 
 DumpGuestMemoryCapability *qmp_query_dump_guest_memory_capability(Error **errp)

exec.c

@@ -1717,6 +1717,8 @@ ram_addr_t qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
         error_propagate(errp, local_err);
         return -1;
     }
+
+    mr->ram_block = new_block;
     return addr;
 }
 
@@ -1866,9 +1868,13 @@ void *qemu_get_ram_block_host_ptr(ram_addr_t addr)
  *
  * Called within RCU critical section.
  */
-void *qemu_get_ram_ptr(ram_addr_t addr)
+void *qemu_get_ram_ptr(RAMBlock *ram_block, ram_addr_t addr)
 {
-    RAMBlock *block = qemu_get_ram_block(addr);
+    RAMBlock *block = ram_block;
+
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+    }
 
     if (xen_enabled() && block->host == NULL) {
         /* We need to check if the requested address is in the RAM
@@ -1889,15 +1895,18 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
  *
  * Called within RCU critical section.
  */
-static void *qemu_ram_ptr_length(ram_addr_t addr, hwaddr *size)
+static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
+                                 hwaddr *size)
 {
-    RAMBlock *block;
+    RAMBlock *block = ram_block;
     ram_addr_t offset_inside_block;
     if (*size == 0) {
         return NULL;
     }
 
-    block = qemu_get_ram_block(addr);
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+    }
     offset_inside_block = addr - block->offset;
     *size = MIN(*size, block->max_length - offset_inside_block);
 
@@ -2025,13 +2034,13 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
     }
     switch (size) {
     case 1:
-        stb_p(qemu_get_ram_ptr(ram_addr), val);
+        stb_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     case 2:
-        stw_p(qemu_get_ram_ptr(ram_addr), val);
+        stw_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     case 4:
-        stl_p(qemu_get_ram_ptr(ram_addr), val);
+        stl_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     default:
         abort();
@@ -2607,7 +2616,7 @@ static MemTxResult address_space_write_continue(AddressSpace *as, hwaddr addr,
         } else {
             addr1 += memory_region_get_ram_addr(mr);
             /* RAM case */
-            ptr = qemu_get_ram_ptr(addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
             memcpy(ptr, buf, l);
             invalidate_and_set_dirty(mr, addr1, l);
         }
@@ -2698,7 +2707,7 @@ MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
             }
         } else {
             /* RAM case */
-            ptr = qemu_get_ram_ptr(mr->ram_addr + addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, mr->ram_addr + addr1);
             memcpy(buf, ptr, l);
         }
 
@@ -2783,7 +2792,7 @@ static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as,
         } else {
             addr1 += memory_region_get_ram_addr(mr);
             /* ROM/RAM case */
-            ptr = qemu_get_ram_ptr(addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
             switch (type) {
             case WRITE_DATA:
                 memcpy(ptr, buf, l);
@@ -2995,7 +3004,7 @@ void *address_space_map(AddressSpace *as,
 
     memory_region_ref(mr);
     *plen = done;
-    ptr = qemu_ram_ptr_length(raddr + base, plen);
+    ptr = qemu_ram_ptr_length(mr->ram_block, raddr + base, plen);
     rcu_read_unlock();
 
     return ptr;
@@ -3079,7 +3088,8 @@ static inline uint32_t address_space_ldl_internal(AddressSpace *as, hwaddr addr,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3174,7 +3184,8 @@ static inline uint64_t address_space_ldq_internal(AddressSpace *as, hwaddr addr,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3289,7 +3300,8 @@ static inline uint32_t address_space_lduw_internal(AddressSpace *as,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3374,7 +3386,7 @@ void address_space_stl_notdirty(AddressSpace *as, hwaddr addr, uint32_t val,
         r = memory_region_dispatch_write(mr, addr1, val, 4, attrs);
     } else {
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         stl_p(ptr, val);
 
         dirty_log_mask = memory_region_get_dirty_log_mask(mr);
@@ -3429,7 +3441,7 @@ static inline void address_space_stl_internal(AddressSpace *as,
     } else {
         /* RAM case */
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             stl_le_p(ptr, val);
@@ -3539,7 +3551,7 @@ static inline void address_space_stw_internal(AddressSpace *as,
     } else {
         /* RAM case */
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             stw_le_p(ptr, val);

fsdev/file-op-9p.h

@@ -12,11 +12,8 @@
  */
 #ifndef _FILEOP_H
 #define _FILEOP_H
-#include <sys/types.h>
 #include <dirent.h>
-#include <sys/time.h>
 #include <utime.h>
-#include <sys/stat.h>
 #include <sys/uio.h>
 #include <sys/vfs.h>
 

hmp-commands-info.hx

@@ -784,6 +784,20 @@ STEXI
 @item info skeys @var{address}
 @findex skeys
 Display the value of a storage key (s390 only)
+ETEXI
+
+    {
+        .name       = "dump",
+        .args_type  = "",
+        .params     = "",
+        .help       = "Display the latest dump status",
+        .mhandler.cmd = hmp_info_dump,
+    },
+
+STEXI
+@item info dump
+@findex dump
+Display the latest dump status.
 ETEXI
 
 STEXI

hmp-commands.hx

@@ -1056,10 +1056,11 @@ ETEXI
 
     {
         .name       = "dump-guest-memory",
-        .args_type  = "paging:-p,zlib:-z,lzo:-l,snappy:-s,filename:F,begin:i?,length:i?",
+        .args_type  = "paging:-p,detach:-d,zlib:-z,lzo:-l,snappy:-s,filename:F,begin:i?,length:i?",
-        .params     = "[-p] [-z|-l|-s] filename [begin length]",
+        .params     = "[-p] [-d] [-z|-l|-s] filename [begin length]",
         .help       = "dump guest memory into file 'filename'.\n\t\t\t"
                       "-p: do paging to get guest's memory mapping.\n\t\t\t"
+                      "-d: return immediately (do not wait for completion).\n\t\t\t"
                       "-z: dump in kdump-compressed format, with zlib compression.\n\t\t\t"
                       "-l: dump in kdump-compressed format, with lzo compression.\n\t\t\t"
                       "-s: dump in kdump-compressed format, with snappy compression.\n\t\t\t"

hmp.c

@@ -1414,6 +1414,18 @@ void hmp_block_set_io_throttle(Monitor *mon, const QDict *qdict)
                               0,
                               false,
                               0,
+                              false, /* no burst length via HMP */
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
                               false, /* No default I/O size */
                               0,
                               false,
@@ -1587,8 +1599,10 @@ void hmp_dump_guest_memory(Monitor *mon, const QDict *qdict)
     const char *file = qdict_get_str(qdict, "filename");
     bool has_begin = qdict_haskey(qdict, "begin");
     bool has_length = qdict_haskey(qdict, "length");
+    bool has_detach = qdict_haskey(qdict, "detach");
     int64_t begin = 0;
     int64_t length = 0;
+    bool detach = false;
     enum DumpGuestMemoryFormat dump_format = DUMP_GUEST_MEMORY_FORMAT_ELF;
     char *prot;
 
@@ -1616,11 +1630,14 @@ void hmp_dump_guest_memory(Monitor *mon, const QDict *qdict)
     if (has_length) {
         length = qdict_get_int(qdict, "length");
     }
+    if (has_detach) {
+        detach = qdict_get_bool(qdict, "detach");
+    }
 
     prot = g_strconcat("file:", file, NULL);
 
-    qmp_dump_guest_memory(paging, prot, has_begin, begin, has_length, length,
+    qmp_dump_guest_memory(paging, prot, true, detach, has_begin, begin,
-                          true, dump_format, &err);
+                          has_length, length, true, dump_format, &err);
     hmp_handle_error(mon, &err);
     g_free(prot);
 }
@@ -2346,3 +2363,20 @@ void hmp_rocker_of_dpa_groups(Monitor *mon, const QDict *qdict)
 
     qapi_free_RockerOfDpaGroupList(list);
 }
+
+void hmp_info_dump(Monitor *mon, const QDict *qdict)
+{
+    DumpQueryResult *result = qmp_query_dump(NULL);
+
+    assert(result && result->status < DUMP_STATUS__MAX);
+    monitor_printf(mon, "Status: %s\n", DumpStatus_lookup[result->status]);
+
+    if (result->status == DUMP_STATUS_ACTIVE) {
+        float percent = 0;
+        assert(result->total != 0);
+        percent = 100.0 * result->completed / result->total;
+        monitor_printf(mon, "Finished: %.2f %%\n", percent);
+    }
+
+    qapi_free_DumpQueryResult(result);
+}

hmp.h

@@ -131,5 +131,6 @@ void hmp_rocker(Monitor *mon, const QDict *qdict);
 void hmp_rocker_ports(Monitor *mon, const QDict *qdict);
 void hmp_rocker_of_dpa_flows(Monitor *mon, const QDict *qdict);
 void hmp_rocker_of_dpa_groups(Monitor *mon, const QDict *qdict);
+void hmp_info_dump(Monitor *mon, const QDict *qdict);
 
 #endif

hw/9pfs/9p-synth.h

@@ -13,9 +13,6 @@
 #ifndef HW_9PFS_SYNTH_H
 #define HW_9PFS_SYNTH_H 1
 
-#include <unistd.h>
-#include <sys/types.h>
-#include <limits.h>
 
 typedef struct V9fsSynthNode V9fsSynthNode;
 typedef ssize_t (*v9fs_synth_read)(void *buf, int len, off_t offset,

hw/9pfs/9p.h

@@ -1,9 +1,7 @@
 #ifndef _QEMU_9P_H
 #define _QEMU_9P_H
 
-#include <sys/types.h>
 #include <dirent.h>
-#include <sys/time.h>
 #include <utime.h>
 #include <sys/resource.h>
 #include <glib.h>

hw/acpi/aml-build.c

@@ -1451,7 +1451,7 @@ build_header(GArray *linker, GArray *table_data,
     h->checksum = 0;
     /* Checksum to be filled in by Guest linker */
     bios_linker_loader_add_checksum(linker, ACPI_BUILD_TABLE_FILE,
-                                    table_data->data, h, len, &h->checksum);
+                                    table_data, h, len, &h->checksum);
 }
 
 void *acpi_data_push(GArray *table_data, unsigned size)

hw/acpi/bios-linker-loader.c

@@ -25,6 +25,13 @@
 
 #include "qemu/bswap.h"
 
+/*
+ * Linker/loader is a paravirtualized interface that passes commands to guest.
+ * The commands can be used to request guest to
+ * - allocate memory chunks and initialize them from QEMU FW CFG files
+ * - link allocated chunks by storing pointer to one chunk into another
+ * - calculate ACPI checksum of part of the chunk and store into same chunk
+ */
 #define BIOS_LINKER_LOADER_FILESZ FW_CFG_MAX_FILE_PATH
 
 struct BiosLinkerLoaderEntry {
@@ -88,6 +95,12 @@ enum {
     BIOS_LINKER_LOADER_ALLOC_ZONE_FSEG = 0x2,
 };
 
+/*
+ * bios_linker_loader_init: allocate a new linker file blob array.
+ *
+ * After initialization, linker commands can be added, and will
+ * be stored in the array.
+ */
 GArray *bios_linker_loader_init(void)
 {
     return g_array_new(false, true /* clear */, 1);
@@ -99,6 +112,16 @@ void *bios_linker_loader_cleanup(GArray *linker)
     return g_array_free(linker, false);
 }
 
+/*
+ * bios_linker_loader_alloc: ask guest to load file into guest memory.
+ *
+ * @linker: linker file blob array
+ * @file: file to be loaded
+ * @alloc_align: required minimal alignment in bytes. Must be a power of 2.
+ * @alloc_fseg: request allocation in FSEG zone (useful for the RSDP ACPI table)
+ *
+ * Note: this command must precede any other linker command using this file.
+ */
 void bios_linker_loader_alloc(GArray *linker,
                               const char *file,
                               uint32_t alloc_align,
@@ -106,6 +129,8 @@ void bios_linker_loader_alloc(GArray *linker,
 {
     BiosLinkerLoaderEntry entry;
 
+    assert(!(alloc_align & (alloc_align - 1)));
+
     memset(&entry, 0, sizeof entry);
     strncpy(entry.alloc.file, file, sizeof entry.alloc.file - 1);
     entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ALLOCATE);
@@ -118,23 +143,77 @@ void bios_linker_loader_alloc(GArray *linker,
     g_array_prepend_vals(linker, &entry, sizeof entry);
 }
 
+/*
+ * bios_linker_loader_add_checksum: ask guest to add checksum of file data
+ * into (same) file at the specified pointer.
+ *
+ * Checksum calculation simply sums -X for each byte X in the range
+ * using 8-bit math (i.e. ACPI checksum).
+ *
+ * @linker: linker file blob array
+ * @file: file that includes the checksum to be calculated
+ *        and the data to be checksummed
+ * @table: @file blob contents
+ * @start, @size: range of data to checksum
+ * @checksum: location of the checksum to be patched within file blob
+ *
+ * Notes:
+ * - checksum byte initial value must have been pushed into @table
+ *   and reside at address @checksum.
+ * - @size bytes must have been pushed into @table and reside at address
+ *   @start.
+ * - Guest calculates checksum of specified range of data, result is added to
+ *   initial value at @checksum into copy of @file in Guest memory.
+ * - Range might include the checksum itself.
+ * - To avoid confusion, caller must always put 0x0 at @checksum.
+ * - @file must be loaded into Guest memory using bios_linker_loader_alloc
+ */
 void bios_linker_loader_add_checksum(GArray *linker, const char *file,
-                                     void *table,
+                                     GArray *table,
                                      void *start, unsigned size,
                                      uint8_t *checksum)
 {
     BiosLinkerLoaderEntry entry;
+    ptrdiff_t checksum_offset = (gchar *)checksum - table->data;
+    ptrdiff_t start_offset = (gchar *)start - table->data;
+
+    assert(checksum_offset >= 0);
+    assert(start_offset >= 0);
+    assert(checksum_offset + 1 <= table->len);
+    assert(start_offset + size <= table->len);
+    assert(*checksum == 0x0);
 
     memset(&entry, 0, sizeof entry);
     strncpy(entry.cksum.file, file, sizeof entry.cksum.file - 1);
     entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ADD_CHECKSUM);
-    entry.cksum.offset = cpu_to_le32(checksum - (uint8_t *)table);
+    entry.cksum.offset = cpu_to_le32(checksum_offset);
-    entry.cksum.start = cpu_to_le32((uint8_t *)start - (uint8_t *)table);
+    entry.cksum.start = cpu_to_le32(start_offset);
     entry.cksum.length = cpu_to_le32(size);
 
     g_array_append_vals(linker, &entry, sizeof entry);
 }
 
+/*
+ * bios_linker_loader_add_pointer: ask guest to add address of source file
+ * into destination file at the specified pointer.
+ *
+ * @linker: linker file blob array
+ * @dest_file: destination file that must be changed
+ * @src_file: source file who's address must be taken
+ * @table: @dest_file blob contents array
+ * @pointer: location of the pointer to be patched within destination file blob
+ * @pointer_size: size of pointer to be patched, in bytes
+ *
+ * Notes:
+ * - @pointer_size bytes must have been pushed into @table
+ *   and reside at address @pointer.
+ * - Guest address is added to initial value at @pointer
+ *   into copy of @dest_file in Guest memory.
+ *   e.g. to get start of src_file in guest memory, put 0x0 there
+ *   to get address of a field at offset 0x10 in src_file, put 0x10 there
+ * - Both @dest_file and @src_file must be
+ *   loaded into Guest memory using bios_linker_loader_alloc
+ */
 void bios_linker_loader_add_pointer(GArray *linker,
                                     const char *dest_file,
                                     const char *src_file,
@@ -142,7 +221,10 @@ void bios_linker_loader_add_pointer(GArray *linker,
                                     uint8_t pointer_size)
 {
     BiosLinkerLoaderEntry entry;
-    size_t offset = (gchar *)pointer - table->data;
+    ptrdiff_t offset = (gchar *)pointer - table->data;
+
+    assert(offset >= 0);
+    assert(offset + pointer_size <= table->len);
 
     memset(&entry, 0, sizeof entry);
     strncpy(entry.pointer.dest_file, dest_file,
@@ -150,7 +232,6 @@ void bios_linker_loader_add_pointer(GArray *linker,
     strncpy(entry.pointer.src_file, src_file,
             sizeof entry.pointer.src_file - 1);
     entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ADD_POINTER);
-    assert(table->len >= offset + pointer_size);
     entry.pointer.offset = cpu_to_le32(offset);
     entry.pointer.size = pointer_size;
     assert(pointer_size == 1 || pointer_size == 2 ||

hw/acpi/core.c

@@ -26,7 +26,6 @@
 #include "hw/nvram/fw_cfg.h"
 #include "qemu/config-file.h"
 #include "qapi/opts-visitor.h"
-#include "qapi/dealloc-visitor.h"
 #include "qapi-visit.h"
 #include "qapi-event.h"
 
@@ -297,15 +296,7 @@ void acpi_table_add(const QemuOpts *opts, Error **errp)
 out:
     g_free(blob);
     g_strfreev(pathnames);
-
+    qapi_free_AcpiTableOptions(hdrs);
-    if (hdrs != NULL) {
-        QapiDeallocVisitor *dv;
-
-        dv = qapi_dealloc_visitor_new();
-        visit_type_AcpiTableOptions(qapi_dealloc_get_visitor(dv), NULL, &hdrs,
-                                    NULL);
-        qapi_dealloc_visitor_cleanup(dv);
-    }
 
     error_propagate(errp, err);
 }

hw/acpi/ich9.c

@@ -240,7 +240,7 @@ static void pm_powerdown_req(Notifier *n, void *opaque)
 }
 
 void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
-                  bool smm_enabled, bool enable_tco,
+                  bool smm_enabled,
                   qemu_irq sci_irq)
 {
     memory_region_init(&pm->io, OBJECT(lpc_pci), "ich9-pm", ICH9_PMIO_SIZE);
@@ -264,10 +264,8 @@ void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
 
     pm->smm_enabled = smm_enabled;
 
-    pm->enable_tco = enable_tco;
+    pm->enable_tco = true;
-    if (pm->enable_tco) {
+    acpi_pm_tco_init(&pm->tco_regs, &pm->io);
-        acpi_pm_tco_init(&pm->tco_regs, &pm->io);
-    }
 
     pm->irq = sci_irq;
     qemu_register_reset(pm_reset, pm);

hw/alpha/dp264.c

@@ -111,7 +111,7 @@ static void clipper_init(MachineState *machine)
     }
     size = load_elf(palcode_filename, cpu_alpha_superpage_to_phys,
                     NULL, &palcode_entry, &palcode_low, &palcode_high,
-                    0, EM_ALPHA, 0);
+                    0, EM_ALPHA, 0, 0);
     if (size < 0) {
         error_report("could not load palcode '%s'", palcode_filename);
         exit(1);
@@ -131,7 +131,7 @@ static void clipper_init(MachineState *machine)
 
         size = load_elf(kernel_filename, cpu_alpha_superpage_to_phys,
                         NULL, &kernel_entry, &kernel_low, &kernel_high,
-                        0, EM_ALPHA, 0);
+                        0, EM_ALPHA, 0, 0);
         if (size < 0) {
             error_report("could not load kernel '%s'", kernel_filename);
             exit(1);

hw/arm/armv7m.c

@@ -211,7 +211,7 @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq,
 
     if (kernel_filename) {
         image_size = load_elf(kernel_filename, NULL, NULL, &entry, &lowaddr,
-                              NULL, big_endian, EM_ARM, 1);
+                              NULL, big_endian, EM_ARM, 1, 0);
         if (image_size < 0) {
             image_size = load_image_targphys(kernel_filename, 0, mem_size);
             lowaddr = 0;

hw/arm/bcm2835_peripherals.c

@@ -182,6 +182,13 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhci), 0,
         qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
                                INTERRUPT_ARASANSDIO));
+    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->sdhci), "sd-bus",
+                              &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
 }
 
 static void bcm2835_peripherals_class_init(ObjectClass *oc, void *data)

hw/arm/bcm2836.c

@@ -73,6 +73,13 @@ static void bcm2836_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->peripherals),
+                              "sd-bus", &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
     sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->peripherals), 0,
                             BCM2836_PERI_BASE, 1);
 

hw/arm/boot.c

@@ -518,9 +518,34 @@ static void do_cpu_reset(void *opaque)
     cpu_reset(cs);
     if (info) {
         if (!info->is_linux) {
+            int i;
             /* Jump to the entry point.  */
             uint64_t entry = info->entry;
 
+            switch (info->endianness) {
+            case ARM_ENDIANNESS_LE:
+                env->cp15.sctlr_el[1] &= ~SCTLR_E0E;
+                for (i = 1; i < 4; ++i) {
+                    env->cp15.sctlr_el[i] &= ~SCTLR_EE;
+                }
+                env->uncached_cpsr &= ~CPSR_E;
+                break;
+            case ARM_ENDIANNESS_BE8:
+                env->cp15.sctlr_el[1] |= SCTLR_E0E;
+                for (i = 1; i < 4; ++i) {
+                    env->cp15.sctlr_el[i] |= SCTLR_EE;
+                }
+                env->uncached_cpsr |= CPSR_E;
+                break;
+            case ARM_ENDIANNESS_BE32:
+                env->cp15.sctlr_el[1] |= SCTLR_B;
+                break;
+            case ARM_ENDIANNESS_UNKNOWN:
+                break; /* Board's decision */
+            default:
+                g_assert_not_reached();
+            }
+
             if (!env->aarch64) {
                 env->thumb = info->entry & 1;
                 entry &= 0xfffffffe;
@@ -638,6 +663,62 @@ static int do_arm_linux_init(Object *obj, void *opaque)
     return 0;
 }
 
+static uint64_t arm_load_elf(struct arm_boot_info *info, uint64_t *pentry,
+                             uint64_t *lowaddr, uint64_t *highaddr,
+                             int elf_machine)
+{
+    bool elf_is64;
+    union {
+        Elf32_Ehdr h32;
+        Elf64_Ehdr h64;
+    } elf_header;
+    int data_swab = 0;
+    bool big_endian;
+    uint64_t ret = -1;
+    Error *err = NULL;
+
+
+    load_elf_hdr(info->kernel_filename, &elf_header, &elf_is64, &err);
+    if (err) {
+        return ret;
+    }
+
+    if (elf_is64) {
+        big_endian = elf_header.h64.e_ident[EI_DATA] == ELFDATA2MSB;
+        info->endianness = big_endian ? ARM_ENDIANNESS_BE8
+                                      : ARM_ENDIANNESS_LE;
+    } else {
+        big_endian = elf_header.h32.e_ident[EI_DATA] == ELFDATA2MSB;
+        if (big_endian) {
+            if (bswap32(elf_header.h32.e_flags) & EF_ARM_BE8) {
+                info->endianness = ARM_ENDIANNESS_BE8;
+            } else {
+                info->endianness = ARM_ENDIANNESS_BE32;
+                /* In BE32, the CPU has a different view of the per-byte
+                 * address map than the rest of the system. BE32 ELF files
+                 * are organised such that they can be programmed through
+                 * the CPU's per-word byte-reversed view of the world. QEMU
+                 * however loads ELF files independently of the CPU. So
+                 * tell the ELF loader to byte reverse the data for us.
+                 */
+                data_swab = 2;
+            }
+        } else {
+            info->endianness = ARM_ENDIANNESS_LE;
+        }
+    }
+
+    ret = load_elf(info->kernel_filename, NULL, NULL,
+                   pentry, lowaddr, highaddr, big_endian, elf_machine,
+                   1, data_swab);
+    if (ret <= 0) {
+        /* The header loaded but the image didn't */
+        exit(1);
+    }
+
+    return ret;
+}
+
 static void arm_load_kernel_notify(Notifier *notifier, void *data)
 {
     CPUState *cs;
@@ -647,7 +728,6 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
     uint64_t elf_entry, elf_low_addr, elf_high_addr;
     int elf_machine;
     hwaddr entry, kernel_load_offset;
-    int big_endian;
     static const ARMInsnFixup *primary_loader;
     ArmLoadKernelNotifier *n = DO_UPCAST(ArmLoadKernelNotifier,
                                          notifier, notifier);
@@ -733,12 +813,6 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
     if (info->nb_cpus == 0)
         info->nb_cpus = 1;
 
-#ifdef TARGET_WORDS_BIGENDIAN
-    big_endian = 1;
-#else
-    big_endian = 0;
-#endif
-
     /* We want to put the initrd far enough into RAM that when the
      * kernel is uncompressed it will not clobber the initrd. However
      * on boards without much RAM we must ensure that we still leave
@@ -753,9 +827,8 @@ static void arm_load_kernel_notify(Notifier *notifier, void *data)
         MIN(info->ram_size / 2, 128 * 1024 * 1024);
 
     /* Assume that raw images are linux kernels, and ELF images are not.  */
-    kernel_size = load_elf(info->kernel_filename, NULL, NULL, &elf_entry,
+    kernel_size = arm_load_elf(info, &elf_entry, &elf_low_addr,
-                           &elf_low_addr, &elf_high_addr, big_endian,
+                               &elf_high_addr, elf_machine);
-                           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.

hw/arm/raspi.c

@@ -113,6 +113,10 @@ static void setup_boot(MachineState *machine, int version, size_t ram_size)
 static void raspi2_init(MachineState *machine)
 {
     RasPiState *s = g_new0(RasPiState, 1);
+    DriveInfo *di;
+    BlockBackend *blk;
+    BusState *bus;
+    DeviceState *carddev;
 
     object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM2836);
     object_property_add_child(OBJECT(machine), "soc", OBJECT(&s->soc),
@@ -133,6 +137,18 @@ static void raspi2_init(MachineState *machine)
                             &error_abort);
     object_property_set_bool(OBJECT(&s->soc), true, "realized", &error_abort);
 
+    /* Create and plug in the SD cards */
+    di = drive_get_next(IF_SD);
+    blk = di ? blk_by_legacy_dinfo(di) : NULL;
+    bus = qdev_get_child_bus(DEVICE(&s->soc), "sd-bus");
+    if (bus == NULL) {
+        error_report("No SD bus found in SOC object");
+        exit(1);
+    }
+    carddev = qdev_create(bus, TYPE_SD_CARD);
+    qdev_prop_set_drive(carddev, "drive", blk, &error_fatal);
+    object_property_set_bool(OBJECT(carddev), true, "realized", &error_fatal);
+
     setup_boot(machine, 2, machine->ram_size);
 }
 

hw/arm/virt-acpi-build.c

@@ -359,7 +359,8 @@ build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt)
     rsdp->checksum = 0;
     /* Checksum to be filled by Guest linker */
     bios_linker_loader_add_checksum(linker, ACPI_BUILD_RSDP_FILE,
-                                    rsdp, rsdp, sizeof *rsdp, &rsdp->checksum);
+                                    rsdp_table, rsdp, sizeof *rsdp,
+                                    &rsdp->checksum);
 
     return rsdp_table;
 }

hw/arm/virt.c

@@ -73,6 +73,7 @@ typedef struct VirtBoardInfo {
     uint32_t clock_phandle;
     uint32_t gic_phandle;
     uint32_t v2m_phandle;
+    bool using_psci;
 } VirtBoardInfo;
 
 typedef struct {
@@ -95,6 +96,23 @@ typedef struct {
 #define VIRT_MACHINE_CLASS(klass) \
     OBJECT_CLASS_CHECK(VirtMachineClass, klass, TYPE_VIRT_MACHINE)
 
+/* RAM limit in GB. Since VIRT_MEM starts at the 1GB mark, this means
+ * RAM can go up to the 256GB mark, leaving 256GB of the physical
+ * address space unallocated and free for future use between 256G and 512G.
+ * If we need to provide more RAM to VMs in the future then we need to:
+ *  * allocate a second bank of RAM starting at 2TB and working up
+ *  * fix the DT and ACPI table generation code in QEMU to correctly
+ *    report two split lumps of RAM to the guest
+ *  * fix KVM in the host kernel to allow guests with >40 bit address spaces
+ * (We don't want to fill all the way up to 512GB with RAM because
+ * we might want it for non-RAM purposes later. Conversely it seems
+ * reasonable to assume that anybody configuring a VM with a quarter
+ * of a terabyte of RAM will be doing it on a host with more than a
+ * terabyte of physical address space.)
+ */
+#define RAMLIMIT_GB 255
+#define RAMLIMIT_BYTES (RAMLIMIT_GB * 1024ULL * 1024 * 1024)
+
 /* Addresses and sizes of our components.
  * 0..128MB is space for a flash device so we can run bootrom code such as UEFI.
  * 128MB..256MB is used for miscellaneous device I/O.
@@ -127,10 +145,11 @@ static const MemMapEntry a15memmap[] = {
     [VIRT_MMIO] =               { 0x0a000000, 0x00000200 },
     /* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */
     [VIRT_PLATFORM_BUS] =       { 0x0c000000, 0x02000000 },
+    [VIRT_SECURE_MEM] =         { 0x0e000000, 0x01000000 },
     [VIRT_PCIE_MMIO] =          { 0x10000000, 0x2eff0000 },
     [VIRT_PCIE_PIO] =           { 0x3eff0000, 0x00010000 },
     [VIRT_PCIE_ECAM] =          { 0x3f000000, 0x01000000 },
-    [VIRT_MEM] =                { 0x40000000, 30ULL * 1024 * 1024 * 1024 },
+    [VIRT_MEM] =                { 0x40000000, RAMLIMIT_BYTES },
     /* Second PCIe window, 512GB wide at the 512GB boundary */
     [VIRT_PCIE_MMIO_HIGH] =   { 0x8000000000ULL, 0x8000000000ULL },
 };
@@ -230,6 +249,10 @@ static void fdt_add_psci_node(const VirtBoardInfo *vbi)
     void *fdt = vbi->fdt;
     ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(0));
 
+    if (!vbi->using_psci) {
+        return;
+    }
+
     qemu_fdt_add_subnode(fdt, "/psci");
     if (armcpu->psci_version == 2) {
         const char comp[] = "arm,psci-0.2\0arm,psci";
@@ -341,7 +364,7 @@ static void fdt_add_cpu_nodes(const VirtBoardInfo *vbi)
         qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible",
                                     armcpu->dtb_compatible);
 
-        if (vbi->smp_cpus > 1) {
+        if (vbi->using_psci && vbi->smp_cpus > 1) {
             qemu_fdt_setprop_string(vbi->fdt, nodename,
                                         "enable-method", "psci");
         }
@@ -678,13 +701,15 @@ static void create_virtio_devices(const VirtBoardInfo *vbi, qemu_irq *pic)
 }
 
 static void create_one_flash(const char *name, hwaddr flashbase,
-                             hwaddr flashsize)
+                             hwaddr flashsize, const char *file,
+                             MemoryRegion *sysmem)
 {
     /* 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");
+    SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
     const uint64_t sectorlength = 256 * 1024;
 
     if (dinfo) {
@@ -704,19 +729,10 @@ static void create_one_flash(const char *name, hwaddr flashbase,
     qdev_prop_set_string(dev, "name", name);
     qdev_init_nofail(dev);
 
-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, flashbase);
+    memory_region_add_subregion(sysmem, flashbase,
-}
+                                sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0));
 
-static void create_flash(const VirtBoardInfo *vbi)
+    if (file) {
-{
-    /* 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) {
         char *fn;
         int image_size;
 
@@ -726,30 +742,73 @@ static void create_flash(const VirtBoardInfo *vbi)
                          "but you cannot use both options at once");
             exit(1);
         }
-        fn = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
+        fn = qemu_find_file(QEMU_FILE_TYPE_BIOS, file);
         if (!fn) {
-            error_report("Could not find ROM image '%s'", bios_name);
+            error_report("Could not find ROM image '%s'", file);
             exit(1);
         }
-        image_size = load_image_targphys(fn, flashbase, flashsize);
+        image_size = load_image_mr(fn, sysbus_mmio_get_region(sbd, 0));
         g_free(fn);
         if (image_size < 0) {
-            error_report("Could not load ROM image '%s'", bios_name);
+            error_report("Could not load ROM image '%s'", file);
             exit(1);
         }
     }
+}
 
-    create_one_flash("virt.flash0", flashbase, flashsize);
+static void create_flash(const VirtBoardInfo *vbi,
-    create_one_flash("virt.flash1", flashbase + flashsize, flashsize);
+                         MemoryRegion *sysmem,
+                         MemoryRegion *secure_sysmem)
+{
+    /* Create two flash devices to fill the VIRT_FLASH space in the memmap.
+     * Any file passed via -bios goes in the first of these.
+     * sysmem is the system memory space. secure_sysmem is the secure view
+     * of the system, and the first flash device should be made visible only
+     * there. The second flash device is visible to both secure and nonsecure.
+     * If sysmem == secure_sysmem this means there is no separate Secure
+     * address space and both flash devices are generally visible.
+     */
+    hwaddr flashsize = vbi->memmap[VIRT_FLASH].size / 2;
+    hwaddr flashbase = vbi->memmap[VIRT_FLASH].base;
+    char *nodename;
 
-    nodename = g_strdup_printf("/flash@%" PRIx64, flashbase);
+    create_one_flash("virt.flash0", flashbase, flashsize,
-    qemu_fdt_add_subnode(vbi->fdt, nodename);
+                     bios_name, secure_sysmem);
-    qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash");
+    create_one_flash("virt.flash1", flashbase + flashsize, flashsize,
-    qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
+                     NULL, sysmem);
-                                 2, flashbase, 2, flashsize,
+
-                                 2, flashbase + flashsize, 2, flashsize);
+    if (sysmem == secure_sysmem) {
-    qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
+        /* Report both flash devices as a single node in the DT */
-    g_free(nodename);
+        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);
+    } else {
+        /* Report the devices as separate nodes so we can mark one as
+         * only visible to the secure world.
+         */
+        nodename = g_strdup_printf("/secflash@%" 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);
+        qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
+        qemu_fdt_setprop_string(vbi->fdt, nodename, "status", "disabled");
+        qemu_fdt_setprop_string(vbi->fdt, nodename, "secure-status", "okay");
+        g_free(nodename);
+
+        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 + flashsize, 2, flashsize);
+        qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
+        g_free(nodename);
+    }
 }
 
 static void create_fw_cfg(const VirtBoardInfo *vbi, AddressSpace *as)
@@ -960,6 +1019,27 @@ static void create_platform_bus(VirtBoardInfo *vbi, qemu_irq *pic)
                                 sysbus_mmio_get_region(s, 0));
 }
 
+static void create_secure_ram(VirtBoardInfo *vbi, MemoryRegion *secure_sysmem)
+{
+    MemoryRegion *secram = g_new(MemoryRegion, 1);
+    char *nodename;
+    hwaddr base = vbi->memmap[VIRT_SECURE_MEM].base;
+    hwaddr size = vbi->memmap[VIRT_SECURE_MEM].size;
+
+    memory_region_init_ram(secram, NULL, "virt.secure-ram", size, &error_fatal);
+    vmstate_register_ram_global(secram);
+    memory_region_add_subregion(secure_sysmem, base, secram);
+
+    nodename = g_strdup_printf("/secram@%" PRIx64, base);
+    qemu_fdt_add_subnode(vbi->fdt, nodename);
+    qemu_fdt_setprop_string(vbi->fdt, nodename, "device_type", "memory");
+    qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", 2, base, 2, size);
+    qemu_fdt_setprop_string(vbi->fdt, nodename, "status", "disabled");
+    qemu_fdt_setprop_string(vbi->fdt, nodename, "secure-status", "okay");
+
+    g_free(nodename);
+}
+
 static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size)
 {
     const VirtBoardInfo *board = (const VirtBoardInfo *)binfo;
@@ -1020,6 +1100,7 @@ static void machvirt_init(MachineState *machine)
     VirtGuestInfoState *guest_info_state = g_malloc0(sizeof *guest_info_state);
     VirtGuestInfo *guest_info = &guest_info_state->info;
     char **cpustr;
+    bool firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
 
     if (!cpu_model) {
         cpu_model = "cortex-a15";
@@ -1047,6 +1128,15 @@ static void machvirt_init(MachineState *machine)
         exit(1);
     }
 
+    /* If we have an EL3 boot ROM then the assumption is that it will
+     * implement PSCI itself, so disable QEMU's internal implementation
+     * so it doesn't get in the way. Instead of starting secondary
+     * CPUs in PSCI powerdown state we will start them all running and
+     * let the boot ROM sort them out.
+     * The usual case is that we do use QEMU's PSCI implementation.
+     */
+    vbi->using_psci = !(vms->secure && firmware_loaded);
+
     /* The maximum number of CPUs depends on the GIC version, or on how
      * many redistributors we can fit into the memory map.
      */
@@ -1066,7 +1156,7 @@ static void machvirt_init(MachineState *machine)
     vbi->smp_cpus = smp_cpus;
 
     if (machine->ram_size > vbi->memmap[VIRT_MEM].size) {
-        error_report("mach-virt: cannot model more than 30GB RAM");
+        error_report("mach-virt: cannot model more than %dGB RAM", RAMLIMIT_GB);
         exit(1);
     }
 
@@ -1114,12 +1204,15 @@ static void machvirt_init(MachineState *machine)
             object_property_set_bool(cpuobj, false, "has_el3", NULL);
         }
 
-        object_property_set_int(cpuobj, QEMU_PSCI_CONDUIT_HVC, "psci-conduit",
+        if (vbi->using_psci) {
-                                NULL);
+            object_property_set_int(cpuobj, QEMU_PSCI_CONDUIT_HVC,
+                                    "psci-conduit", NULL);
 
-        /* Secondary CPUs start in PSCI powered-down state */
+            /* Secondary CPUs start in PSCI powered-down state */
-        if (n > 0) {
+            if (n > 0) {
-            object_property_set_bool(cpuobj, true, "start-powered-off", NULL);
+                object_property_set_bool(cpuobj, true,
+                                         "start-powered-off", NULL);
+            }
         }
 
         if (object_property_find(cpuobj, "reset-cbar", NULL)) {
@@ -1145,13 +1238,14 @@ static void machvirt_init(MachineState *machine)
                                          machine->ram_size);
     memory_region_add_subregion(sysmem, vbi->memmap[VIRT_MEM].base, ram);
 
-    create_flash(vbi);
+    create_flash(vbi, sysmem, secure_sysmem ? secure_sysmem : sysmem);
 
     create_gic(vbi, pic, gic_version, vms->secure);
 
     create_uart(vbi, pic, VIRT_UART, sysmem);
 
     if (vms->secure) {
+        create_secure_ram(vbi, secure_sysmem);
         create_uart(vbi, pic, VIRT_SECURE_UART, secure_sysmem);
     }
 
@@ -1187,7 +1281,7 @@ static void machvirt_init(MachineState *machine)
     vbi->bootinfo.board_id = -1;
     vbi->bootinfo.loader_start = vbi->memmap[VIRT_MEM].base;
     vbi->bootinfo.get_dtb = machvirt_dtb;
-    vbi->bootinfo.firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
+    vbi->bootinfo.firmware_loaded = firmware_loaded;
     arm_load_kernel(ARM_CPU(first_cpu), &vbi->bootinfo);
 
     /*

hw/audio/gusemu.h

@@ -34,7 +34,6 @@
  typedef signed char GUSchar;
  typedef signed short GUSsample;
 #else
- #include <stdint.h>
  typedef int8_t GUSchar;
  typedef uint8_t GUSbyte;
  typedef uint16_t GUSword;

hw/block/dataplane/virtio-blk.c

@@ -18,8 +18,6 @@
 #include "qemu/thread.h"
 #include "qemu/error-report.h"
 #include "hw/virtio/virtio-access.h"
-#include "hw/virtio/dataplane/vring.h"
-#include "hw/virtio/dataplane/vring-accessors.h"
 #include "sysemu/block-backend.h"
 #include "hw/virtio/virtio-blk.h"
 #include "virtio-blk.h"
@@ -28,7 +26,6 @@
 #include "qom/object_interfaces.h"
 
 struct VirtIOBlockDataPlane {
-    bool started;
     bool starting;
     bool stopping;
     bool disabled;
@@ -36,7 +33,7 @@ struct VirtIOBlockDataPlane {
     VirtIOBlkConf *conf;
 
     VirtIODevice *vdev;
-    Vring vring;                    /* virtqueue vring */
+    VirtQueue *vq;                  /* virtqueue vring */
     EventNotifier *guest_notifier;  /* irq */
     QEMUBH *bh;                     /* bh for guest notification */
 
@@ -49,93 +46,26 @@ struct VirtIOBlockDataPlane {
      */
     IOThread *iothread;
     AioContext *ctx;
-    EventNotifier host_notifier;    /* doorbell */
 
     /* Operation blocker on BDS */
     Error *blocker;
-    void (*saved_complete_request)(struct VirtIOBlockReq *req,
-                                   unsigned char status);
 };
 
 /* Raise an interrupt to signal guest, if necessary */
-static void notify_guest(VirtIOBlockDataPlane *s)
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s)
 {
-    if (!vring_should_notify(s->vdev, &s->vring)) {
+    qemu_bh_schedule(s->bh);
-        return;
-    }
-
-    event_notifier_set(s->guest_notifier);
 }
 
 static void notify_guest_bh(void *opaque)
 {
     VirtIOBlockDataPlane *s = opaque;
 
-    notify_guest(s);
+    if (!virtio_should_notify(s->vdev, s->vq)) {
-}
+        return;
-
-static void complete_request_vring(VirtIOBlockReq *req, unsigned char status)
-{
-    VirtIOBlockDataPlane *s = req->dev->dataplane;
-    stb_p(&req->in->status, status);
-
-    vring_push(s->vdev, &req->dev->dataplane->vring, &req->elem, req->in_len);
-
-    /* Suppress notification to guest by BH and its scheduled
-     * flag because requests are completed as a batch after io
-     * plug & unplug is introduced, and the BH can still be
-     * executed in dataplane aio context even after it is
-     * stopped, so needn't worry about notification loss with BH.
-     */
-    qemu_bh_schedule(s->bh);
-}
-
-static void handle_notify(EventNotifier *e)
-{
-    VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
-                                           host_notifier);
-    VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
-
-    event_notifier_test_and_clear(&s->host_notifier);
-    blk_io_plug(s->conf->conf.blk);
-    for (;;) {
-        MultiReqBuffer mrb = {};
-
-        /* Disable guest->host notifies to avoid unnecessary vmexits */
-        vring_disable_notification(s->vdev, &s->vring);
-
-        for (;;) {
-            VirtIOBlockReq *req = vring_pop(s->vdev, &s->vring,
-                                            sizeof(VirtIOBlockReq));
-
-            if (req == NULL) {
-                break; /* no more requests */
-            }
-
-            virtio_blk_init_request(vblk, req);
-            trace_virtio_blk_data_plane_process_request(s, req->elem.out_num,
-                                                        req->elem.in_num,
-                                                        req->elem.index);
-
-            virtio_blk_handle_request(req, &mrb);
-        }
-
-        if (mrb.num_reqs) {
-            virtio_blk_submit_multireq(s->conf->conf.blk, &mrb);
-        }
-
-        if (likely(!vring_more_avail(s->vdev, &s->vring))) { /* vring emptied */
-            /* Re-enable guest->host notifies and stop processing the vring.
-             * But if the guest has snuck in more descriptors, keep processing.
-             */
-            if (vring_enable_notification(s->vdev, &s->vring)) {
-                break;
-            }
-        } else { /* fatal error */
-            break;
-        }
     }
-    blk_io_unplug(s->conf->conf.blk);
+
+    event_notifier_set(s->guest_notifier);
 }
 
 static void data_plane_set_up_op_blockers(VirtIOBlockDataPlane *s)
@@ -260,23 +190,14 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
-    VirtQueue *vq;
     int r;
 
-    if (s->started || s->disabled) {
+    if (vblk->dataplane_started || s->starting) {
-        return;
-    }
-
-    if (s->starting) {
         return;
     }
 
     s->starting = true;
-
+    s->vq = virtio_get_queue(s->vdev, 0);
-    vq = virtio_get_queue(s->vdev, 0);
-    if (!vring_setup(&s->vring, s->vdev, 0)) {
-        goto fail_vring;
-    }
 
     /* Set up guest notifier (irq) */
     r = k->set_guest_notifiers(qbus->parent, 1, true);
@@ -285,7 +206,7 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
                 "ensure -enable-kvm is set\n", r);
         goto fail_guest_notifiers;
     }
-    s->guest_notifier = virtio_queue_get_guest_notifier(vq);
+    s->guest_notifier = virtio_queue_get_guest_notifier(s->vq);
 
     /* Set up virtqueue notify */
     r = k->set_host_notifier(qbus->parent, 0, true);
@@ -293,34 +214,28 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
         fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
         goto fail_host_notifier;
     }
-    s->host_notifier = *virtio_queue_get_host_notifier(vq);
-
-    s->saved_complete_request = vblk->complete_request;
-    vblk->complete_request = complete_request_vring;
 
     s->starting = false;
-    s->started = true;
+    vblk->dataplane_started = true;
     trace_virtio_blk_data_plane_start(s);
 
     blk_set_aio_context(s->conf->conf.blk, s->ctx);
 
     /* Kick right away to begin processing requests already in vring */
-    event_notifier_set(virtio_queue_get_host_notifier(vq));
+    event_notifier_set(virtio_queue_get_host_notifier(s->vq));
 
     /* Get this show started by hooking up our callbacks */
     aio_context_acquire(s->ctx);
-    aio_set_event_notifier(s->ctx, &s->host_notifier, true,
+    virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx, true, true);
-                           handle_notify);
     aio_context_release(s->ctx);
     return;
 
   fail_host_notifier:
     k->set_guest_notifiers(qbus->parent, 1, false);
   fail_guest_notifiers:
-    vring_teardown(&s->vring, s->vdev, 0);
     s->disabled = true;
-  fail_vring:
     s->starting = false;
+    vblk->dataplane_started = true;
 }
 
 /* Context: QEMU global mutex held */
@@ -330,39 +245,34 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
 
+    if (!vblk->dataplane_started || s->stopping) {
+        return;
+    }
 
     /* Better luck next time. */
     if (s->disabled) {
         s->disabled = false;
-        return;
+        vblk->dataplane_started = false;
-    }
-    if (!s->started || s->stopping) {
         return;
     }
     s->stopping = true;
-    vblk->complete_request = s->saved_complete_request;
     trace_virtio_blk_data_plane_stop(s);
 
     aio_context_acquire(s->ctx);
 
     /* Stop notifications for new requests from guest */
-    aio_set_event_notifier(s->ctx, &s->host_notifier, true, NULL);
+    virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx, false, false);
 
     /* Drain and switch bs back to the QEMU main loop */
     blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());
 
     aio_context_release(s->ctx);
 
-    /* Sync vring state back to virtqueue so that non-dataplane request
-     * processing can continue when we disable the host notifier below.
-     */
-    vring_teardown(&s->vring, s->vdev, 0);
-
     k->set_host_notifier(qbus->parent, 0, false);
 
     /* Clean up guest notifier (irq) */
     k->set_guest_notifiers(qbus->parent, 1, false);
 
-    s->started = false;
+    vblk->dataplane_started = false;
     s->stopping = false;
 }

hw/block/dataplane/virtio-blk.h

@@ -26,5 +26,6 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_drain(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s);
 
 #endif /* HW_DATAPLANE_VIRTIO_BLK_H */

hw/block/virtio-blk.c

@@ -21,7 +21,6 @@
 #include "sysemu/blockdev.h"
 #include "hw/virtio/virtio-blk.h"
 #include "dataplane/virtio-blk.h"
-#include "migration/migration.h"
 #include "block/scsi.h"
 #ifdef __linux__
 # include <scsi/sg.h>
@@ -45,8 +44,7 @@ void virtio_blk_free_request(VirtIOBlockReq *req)
     }
 }
 
-static void virtio_blk_complete_request(VirtIOBlockReq *req,
+static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
-                                        unsigned char status)
 {
     VirtIOBlock *s = req->dev;
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
@@ -55,12 +53,11 @@ static void virtio_blk_complete_request(VirtIOBlockReq *req,
 
     stb_p(&req->in->status, status);
     virtqueue_push(s->vq, &req->elem, req->in_len);
-    virtio_notify(vdev, s->vq);
+    if (s->dataplane) {
-}
+        virtio_blk_data_plane_notify(s->dataplane);
-
+    } else {
-static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
+        virtio_notify(vdev, s->vq);
-{
+    }
-    req->dev->complete_request(req, status);
 }
 
 static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
@@ -589,7 +586,7 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
     /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
      * dataplane here instead of waiting for .set_status().
      */
-    if (s->dataplane) {
+    if (s->dataplane && !s->dataplane_started) {
         virtio_blk_data_plane_start(s->dataplane);
         return;
     }
@@ -852,36 +849,6 @@ static const BlockDevOps virtio_block_ops = {
     .resize_cb = virtio_blk_resize,
 };
 
-/* Disable dataplane thread during live migration since it does not
- * update the dirty memory bitmap yet.
- */
-static void virtio_blk_migration_state_changed(Notifier *notifier, void *data)
-{
-    VirtIOBlock *s = container_of(notifier, VirtIOBlock,
-                                  migration_state_notifier);
-    MigrationState *mig = data;
-    Error *err = NULL;
-
-    if (migration_in_setup(mig)) {
-        if (!s->dataplane) {
-            return;
-        }
-        virtio_blk_data_plane_destroy(s->dataplane);
-        s->dataplane = NULL;
-    } else if (migration_has_finished(mig) ||
-               migration_has_failed(mig)) {
-        if (s->dataplane) {
-            return;
-        }
-        blk_drain_all(); /* complete in-flight non-dataplane requests */
-        virtio_blk_data_plane_create(VIRTIO_DEVICE(s), &s->conf,
-                                     &s->dataplane, &err);
-        if (err != NULL) {
-            error_report_err(err);
-        }
-    }
-}
-
 static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
@@ -916,15 +883,12 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1;
 
     s->vq = virtio_add_queue(vdev, 128, virtio_blk_handle_output);
-    s->complete_request = virtio_blk_complete_request;
     virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
     if (err != NULL) {
         error_propagate(errp, err);
         virtio_cleanup(vdev);
         return;
     }
-    s->migration_state_notifier.notify = virtio_blk_migration_state_changed;
-    add_migration_state_change_notifier(&s->migration_state_notifier);
 
     s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
     register_savevm(dev, "virtio-blk", virtio_blk_id++, 2,
@@ -940,7 +904,6 @@ static void virtio_blk_device_unrealize(DeviceState *dev, Error **errp)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOBlock *s = VIRTIO_BLK(dev);
 
-    remove_migration_state_change_notifier(&s->migration_state_notifier);
     virtio_blk_data_plane_destroy(s->dataplane);
     s->dataplane = NULL;
     qemu_del_vm_change_state_handler(s->change);

hw/char/escc.c

@@ -842,14 +842,16 @@ static void sunkbd_handle_event(DeviceState *dev, QemuConsole *src,
 {
     ChannelState *s = (ChannelState *)dev;
     int qcode, keycode;
+    InputKeyEvent *key;
 
     assert(evt->type == INPUT_EVENT_KIND_KEY);
-    qcode = qemu_input_key_value_to_qcode(evt->u.key->key);
+    key = evt->u.key;
+    qcode = qemu_input_key_value_to_qcode(key->key);
     trace_escc_sunkbd_event_in(qcode, QKeyCode_lookup[qcode],
-                               evt->u.key->down);
+                               key->down);
 
     if (qcode == Q_KEY_CODE_CAPS_LOCK) {
-        if (evt->u.key->down) {
+        if (key->down) {
             s->caps_lock_mode ^= 1;
             if (s->caps_lock_mode == 2) {
                 return; /* Drop second press */
@@ -863,7 +865,7 @@ static void sunkbd_handle_event(DeviceState *dev, QemuConsole *src,
     }
 
     if (qcode == Q_KEY_CODE_NUM_LOCK) {
-        if (evt->u.key->down) {
+        if (key->down) {
             s->num_lock_mode ^= 1;
             if (s->num_lock_mode == 2) {
                 return; /* Drop second press */
@@ -877,7 +879,7 @@ static void sunkbd_handle_event(DeviceState *dev, QemuConsole *src,
     }
 
     keycode = qcode_to_keycode[qcode];
-    if (!evt->u.key->down) {
+    if (!key->down) {
         keycode |= 0x80;
     }
     trace_escc_sunkbd_event_out(keycode);

hw/core/loader.c

@@ -147,6 +147,28 @@ int load_image_targphys(const char *filename,
     return size;
 }
 
+int load_image_mr(const char *filename, MemoryRegion *mr)
+{
+    int size;
+
+    if (!memory_access_is_direct(mr, false)) {
+        /* Can only load an image into RAM or ROM */
+        return -1;
+    }
+
+    size = get_image_size(filename);
+
+    if (size > memory_region_size(mr)) {
+        return -1;
+    }
+    if (size > 0) {
+        if (rom_add_file_mr(filename, mr, -1) < 0) {
+            return -1;
+        }
+    }
+    return size;
+}
+
 void pstrcpy_targphys(const char *name, hwaddr dest, int buf_size,
                       const char *source)
 {
@@ -332,10 +354,66 @@ const char *load_elf_strerror(int error)
     }
 }
 
+void load_elf_hdr(const char *filename, void *hdr, bool *is64, Error **errp)
+{
+    int fd;
+    uint8_t e_ident_local[EI_NIDENT];
+    uint8_t *e_ident;
+    size_t hdr_size, off;
+    bool is64l;
+
+    if (!hdr) {
+        hdr = e_ident_local;
+    }
+    e_ident = hdr;
+
+    fd = open(filename, O_RDONLY | O_BINARY);
+    if (fd < 0) {
+        error_setg_errno(errp, errno, "Failed to open file: %s", filename);
+        return;
+    }
+    if (read(fd, hdr, EI_NIDENT) != EI_NIDENT) {
+        error_setg_errno(errp, errno, "Failed to read file: %s", filename);
+        goto fail;
+    }
+    if (e_ident[0] != ELFMAG0 ||
+        e_ident[1] != ELFMAG1 ||
+        e_ident[2] != ELFMAG2 ||
+        e_ident[3] != ELFMAG3) {
+        error_setg(errp, "Bad ELF magic");
+        goto fail;
+    }
+
+    is64l = e_ident[EI_CLASS] == ELFCLASS64;
+    hdr_size = is64l ? sizeof(Elf64_Ehdr) : sizeof(Elf32_Ehdr);
+    if (is64) {
+        *is64 = is64l;
+    }
+
+    off = EI_NIDENT;
+    while (hdr != e_ident_local && off < hdr_size) {
+        size_t br = read(fd, hdr + off, hdr_size - off);
+        switch (br) {
+        case 0:
+            error_setg(errp, "File too short: %s", filename);
+            goto fail;
+        case -1:
+            error_setg_errno(errp, errno, "Failed to read file: %s",
+                             filename);
+            goto fail;
+        }
+        off += br;
+    }
+
+fail:
+    close(fd);
+}
+
 /* return < 0 if error, otherwise the number of bytes loaded in memory */
 int load_elf(const char *filename, uint64_t (*translate_fn)(void *, uint64_t),
              void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
-             uint64_t *highaddr, int big_endian, int elf_machine, int clear_lsb)
+             uint64_t *highaddr, int big_endian, int elf_machine,
+             int clear_lsb, int data_swab)
 {
     int fd, data_order, target_data_order, must_swab, ret = ELF_LOAD_FAILED;
     uint8_t e_ident[EI_NIDENT];
@@ -374,10 +452,12 @@ int load_elf(const char *filename, uint64_t (*translate_fn)(void *, uint64_t),
     lseek(fd, 0, SEEK_SET);
     if (e_ident[EI_CLASS] == ELFCLASS64) {
         ret = load_elf64(filename, fd, translate_fn, translate_opaque, must_swab,
-                         pentry, lowaddr, highaddr, elf_machine, clear_lsb);
+                         pentry, lowaddr, highaddr, elf_machine, clear_lsb,
+                         data_swab);
     } else {
         ret = load_elf32(filename, fd, translate_fn, translate_opaque, must_swab,
-                         pentry, lowaddr, highaddr, elf_machine, clear_lsb);
+                         pentry, lowaddr, highaddr, elf_machine, clear_lsb,
+                         data_swab);
     }
 
  fail:
@@ -751,7 +831,7 @@ static void *rom_set_mr(Rom *rom, Object *owner, const char *name)
 
 int rom_add_file(const char *file, const char *fw_dir,
                  hwaddr addr, int32_t bootindex,
-                 bool option_rom)
+                 bool option_rom, MemoryRegion *mr)
 {
     MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
     Rom *rom;
@@ -818,7 +898,12 @@ int rom_add_file(const char *file, const char *fw_dir,
 
         fw_cfg_add_file(fw_cfg, fw_file_name, data, rom->romsize);
     } else {
-        snprintf(devpath, sizeof(devpath), "/rom@" TARGET_FMT_plx, addr);
+        if (mr) {
+            rom->mr = mr;
+            snprintf(devpath, sizeof(devpath), "/rom@%s", file);
+        } else {
+            snprintf(devpath, sizeof(devpath), "/rom@" TARGET_FMT_plx, addr);
+        }
     }
 
     add_boot_device_path(bootindex, NULL, devpath);
@@ -892,12 +977,12 @@ int rom_add_elf_program(const char *name, void *data, size_t datasize,
 
 int rom_add_vga(const char *file)
 {
-    return rom_add_file(file, "vgaroms", 0, -1, true);
+    return rom_add_file(file, "vgaroms", 0, -1, true, NULL);
 }
 
 int rom_add_option(const char *file, int32_t bootindex)
 {
-    return rom_add_file(file, "genroms", 0, bootindex, true);
+    return rom_add_file(file, "genroms", 0, bootindex, true, NULL);
 }
 
 static void rom_reset(void *unused)

hw/core/machine.c

@@ -312,6 +312,21 @@ static bool machine_get_suppress_vmdesc(Object *obj, Error **errp)
     return ms->suppress_vmdesc;
 }
 
+static void machine_set_enforce_config_section(Object *obj, bool value,
+                                             Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->enforce_config_section = value;
+}
+
+static bool machine_get_enforce_config_section(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->enforce_config_section;
+}
+
 static int error_on_sysbus_device(SysBusDevice *sbdev, void *opaque)
 {
     error_report("Option '-device %s' cannot be handled by this machine",
@@ -467,6 +482,12 @@ static void machine_initfn(Object *obj)
     object_property_set_description(obj, "suppress-vmdesc",
                                     "Set on to disable self-describing migration",
                                     NULL);
+    object_property_add_bool(obj, "enforce-config-section",
+                             machine_get_enforce_config_section,
+                             machine_set_enforce_config_section, NULL);
+    object_property_set_description(obj, "enforce-config-section",
+                                    "Set on to enforce configuration section migration",
+                                    NULL);
 
     /* Register notifier when init is done for sysbus sanity checks */
     ms->sysbus_notifier.notify = machine_init_notify;

hw/cpu/a15mpcore.c

@@ -109,7 +109,7 @@ static void a15mp_priv_realize(DeviceState *dev, Error **errp)
     /* Memory map (addresses are offsets from PERIPHBASE):
      *  0x0000-0x0fff -- reserved
      *  0x1000-0x1fff -- GIC Distributor
-     *  0x2000-0x2fff -- GIC CPU interface
+     *  0x2000-0x3fff -- GIC CPU interface
      *  0x4000-0x4fff -- GIC virtual interface control (not modelled)
      *  0x5000-0x5fff -- GIC virtual interface control (not modelled)
      *  0x6000-0x7fff -- GIC virtual CPU interface (not modelled)

hw/cris/boot.c

@@ -73,7 +73,7 @@ void cris_load_image(CRISCPU *cpu, struct cris_load_info *li)
     /* Boots a kernel elf binary, os/linux-2.6/vmlinux from the axis 
        devboard SDK.  */
     image_size = load_elf(li->image_filename, translate_kernel_address, NULL,
-                          &entry, NULL, &high, 0, EM_CRIS, 0);
+                          &entry, NULL, &high, 0, EM_CRIS, 0, 0);
     li->entry = entry;
     if (image_size < 0) {
         /* Takes a kimage from the axis devboard SDK.  */

hw/display/cirrus_vga.c

@@ -276,14 +276,14 @@ static bool blit_region_is_unsafe(struct CirrusVGAState *s,
             + ((int64_t)s->cirrus_blt_height-1) * pitch;
         int32_t max = addr
             + s->cirrus_blt_width;
-        if (min < 0 || max >= s->vga.vram_size) {
+        if (min < 0 || max > s->vga.vram_size) {
             return true;
         }
     } else {
         int64_t max = addr
             + ((int64_t)s->cirrus_blt_height-1) * pitch
             + s->cirrus_blt_width;
-        if (max >= s->vga.vram_size) {
+        if (max > s->vga.vram_size) {
             return true;
         }
     }

hw/display/qxl.c

@@ -1156,7 +1156,9 @@ static void qxl_soft_reset(PCIQXLDevice *d)
     trace_qxl_soft_reset(d->id);
     qxl_check_state(d);
     qxl_clear_guest_bug(d);
+    qemu_mutex_lock(&d->async_lock);
     d->current_async = QXL_UNDEFINED_IO;
+    qemu_mutex_unlock(&d->async_lock);
 
     if (d->id == 0) {
         qxl_enter_vga_mode(d);

hw/display/vga_int.h

@@ -25,7 +25,6 @@
 #define HW_VGA_INT_H 1
 
 #include <hw/hw.h>
-#include "qapi/error.h"
 #include "exec/memory.h"
 
 #define ST01_V_RETRACE      0x08

hw/gpio/pl061.c

@@ -60,6 +60,7 @@ typedef struct PL061State {
     qemu_irq irq;
     qemu_irq out[8];
     const unsigned char *id;
+    uint32_t rsvd_start; /* reserved area: [rsvd_start, 0xfcc] */
 } PL061State;
 
 static const VMStateDescription vmstate_pl061 = {
@@ -152,12 +153,15 @@ static uint64_t pl061_read(void *opaque, hwaddr offset,
 {
     PL061State *s = (PL061State *)opaque;
 
-    if (offset >= 0xfd0 && offset < 0x1000) {
-        return s->id[(offset - 0xfd0) >> 2];
-    }
     if (offset < 0x400) {
         return s->data & (offset >> 2);
     }
+    if (offset >= s->rsvd_start && offset <= 0xfcc) {
+        goto err_out;
+    }
+    if (offset >= 0xfd0 && offset < 0x1000) {
+        return s->id[(offset - 0xfd0) >> 2];
+    }
     switch (offset) {
     case 0x400: /* Direction */
         return s->dir;
@@ -198,10 +202,12 @@ static uint64_t pl061_read(void *opaque, hwaddr offset,
     case 0x528: /* Analog mode select */
         return s->amsel;
     default:
-        qemu_log_mask(LOG_GUEST_ERROR,
+        break;
-                      "pl061_read: Bad offset %x\n", (int)offset);
-        return 0;
     }
+err_out:
+    qemu_log_mask(LOG_GUEST_ERROR,
+                  "pl061_read: Bad offset %x\n", (int)offset);
+    return 0;
 }
 
 static void pl061_write(void *opaque, hwaddr offset,
@@ -216,6 +222,9 @@ static void pl061_write(void *opaque, hwaddr offset,
         pl061_update(s);
         return;
     }
+    if (offset >= s->rsvd_start) {
+        goto err_out;
+    }
     switch (offset) {
     case 0x400: /* Direction */
         s->dir = value & 0xff;
@@ -274,10 +283,13 @@ static void pl061_write(void *opaque, hwaddr offset,
         s->amsel = value & 0xff;
         break;
     default:
-        qemu_log_mask(LOG_GUEST_ERROR,
+        goto err_out;
-                      "pl061_write: Bad offset %x\n", (int)offset);
     }
     pl061_update(s);
+    return;
+err_out:
+    qemu_log_mask(LOG_GUEST_ERROR,
+                  "pl061_write: Bad offset %x\n", (int)offset);
 }
 
 static void pl061_reset(DeviceState *dev)
@@ -347,6 +359,7 @@ static void pl061_luminary_init(Object *obj)
     PL061State *s = PL061(obj);
 
     s->id = pl061_id_luminary;
+    s->rsvd_start = 0x52c;
 }
 
 static void pl061_init(Object *obj)
@@ -354,6 +367,7 @@ static void pl061_init(Object *obj)
     PL061State *s = PL061(obj);
 
     s->id = pl061_id;
+    s->rsvd_start = 0x424;
 }
 
 static void pl061_class_init(ObjectClass *klass, void *data)

hw/i386/acpi-build.c

@@ -2532,7 +2532,8 @@ build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt)
     rsdp->checksum = 0;
     /* Checksum to be filled by Guest linker */
     bios_linker_loader_add_checksum(linker, ACPI_BUILD_RSDP_FILE,
-                                    rsdp, rsdp, sizeof *rsdp, &rsdp->checksum);
+                                    rsdp_table, rsdp, sizeof *rsdp,
+                                    &rsdp->checksum);
 
     return rsdp_table;
 }

hw/i386/multiboot.c

@@ -196,7 +196,8 @@ int load_multiboot(FWCfgState *fw_cfg,
         }
 
         kernel_size = load_elf(kernel_filename, NULL, NULL, &elf_entry,
-                               &elf_low, &elf_high, 0, I386_ELF_MACHINE, 0);
+                               &elf_low, &elf_high, 0, I386_ELF_MACHINE,
+                               0, 0);
         if (kernel_size < 0) {
             fprintf(stderr, "Error while loading elf kernel\n");
             exit(1);

hw/i386/pc_q35.c

@@ -81,11 +81,9 @@ static void pc_q35_init(MachineState *machine)
      * If it doesn't, we need to split it in chunks below and above 4G.
      * In any case, try to make sure that guest addresses aligned at
      * 1G boundaries get mapped to host addresses aligned at 1G boundaries.
-     * For old machine types, use whatever split we used historically to avoid
-     * breaking migration.
      */
     if (machine->ram_size >= 0xb0000000) {
-        lowmem = pcmc->gigabyte_align ? 0x80000000 : 0xb0000000;
+        lowmem = 0x80000000;
     } else {
         lowmem = 0xb0000000;
     }
@@ -116,10 +114,6 @@ static void pc_q35_init(MachineState *machine)
     }
 
     pc_cpus_init(pcms);
-    if (!pcmc->has_acpi_build) {
-        /* only machine types 1.7 & older need this */
-        pc_acpi_init("q35-acpi-dsdt.aml");
-    }
 
     kvmclock_create();
 
@@ -225,7 +219,7 @@ static void pc_q35_init(MachineState *machine)
                          (pcms->vmport != ON_OFF_AUTO_ON), 0xff0104);
 
     /* connect pm stuff to lpc */
-    ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pcms), !mc->no_tco);
+    ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pcms));
 
     /* ahci and SATA device, for q35 1 ahci controller is built-in */
     ahci = pci_create_simple_multifunction(host_bus,
@@ -259,62 +253,6 @@ static void pc_q35_init(MachineState *machine)
     }
 }
 
-/* Looking for a pc_compat_2_4() function? It doesn't exist.
- * pc_compat_*() functions that run on machine-init time and
- * change global QEMU state are deprecated. Please don't create
- * one, and implement any pc-*-2.4 (and newer) compat code in
- * HW_COMPAT_*, PC_COMPAT_*, or * pc_*_machine_options().
- */
-
-static void pc_compat_2_3(MachineState *machine)
-{
-    PCMachineState *pcms = PC_MACHINE(machine);
-    savevm_skip_section_footers();
-    if (kvm_enabled()) {
-        pcms->smm = ON_OFF_AUTO_OFF;
-    }
-    global_state_set_optional();
-    savevm_skip_configuration();
-}
-
-static void pc_compat_2_2(MachineState *machine)
-{
-    pc_compat_2_3(machine);
-    machine->suppress_vmdesc = true;
-}
-
-static void pc_compat_2_1(MachineState *machine)
-{
-    pc_compat_2_2(machine);
-    x86_cpu_change_kvm_default("svm", NULL);
-}
-
-static void pc_compat_2_0(MachineState *machine)
-{
-    pc_compat_2_1(machine);
-}
-
-static void pc_compat_1_7(MachineState *machine)
-{
-    pc_compat_2_0(machine);
-    x86_cpu_change_kvm_default("x2apic", NULL);
-}
-
-static void pc_compat_1_6(MachineState *machine)
-{
-    pc_compat_1_7(machine);
-}
-
-static void pc_compat_1_5(MachineState *machine)
-{
-    pc_compat_1_6(machine);
-}
-
-static void pc_compat_1_4(MachineState *machine)
-{
-    pc_compat_1_5(machine);
-}
-
 #define DEFINE_Q35_MACHINE(suffix, name, compatfn, optionfn) \
     static void pc_init_##suffix(MachineState *machine) \
     { \
@@ -336,7 +274,6 @@ static void pc_q35_machine_options(MachineClass *m)
     m->default_machine_opts = "firmware=bios-256k.bin";
     m->default_display = "std";
     m->no_floppy = 1;
-    m->no_tco = 0;
 }
 
 static void pc_q35_2_6_machine_options(MachineClass *m)
@@ -371,112 +308,3 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
 
 DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL,
                    pc_q35_2_4_machine_options);
-
-
-static void pc_q35_2_3_machine_options(MachineClass *m)
-{
-    pc_q35_2_4_machine_options(m);
-    m->hw_version = "2.3.0";
-    m->no_floppy = 0;
-    m->no_tco = 1;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_3);
-}
-
-DEFINE_Q35_MACHINE(v2_3, "pc-q35-2.3", pc_compat_2_3,
-                   pc_q35_2_3_machine_options);
-
-
-static void pc_q35_2_2_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_3_machine_options(m);
-    m->hw_version = "2.2.0";
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_2);
-    pcmc->rsdp_in_ram = false;
-}
-
-DEFINE_Q35_MACHINE(v2_2, "pc-q35-2.2", pc_compat_2_2,
-                   pc_q35_2_2_machine_options);
-
-
-static void pc_q35_2_1_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_2_machine_options(m);
-    m->hw_version = "2.1.0";
-    m->default_display = NULL;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_1);
-    pcmc->smbios_uuid_encoded = false;
-    pcmc->enforce_aligned_dimm = false;
-}
-
-DEFINE_Q35_MACHINE(v2_1, "pc-q35-2.1", pc_compat_2_1,
-                   pc_q35_2_1_machine_options);
-
-
-static void pc_q35_2_0_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_1_machine_options(m);
-    m->hw_version = "2.0.0";
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_0);
-    pcmc->has_reserved_memory = false;
-    pcmc->smbios_legacy_mode = true;
-    pcmc->acpi_data_size = 0x10000;
-}
-
-DEFINE_Q35_MACHINE(v2_0, "pc-q35-2.0", pc_compat_2_0,
-                   pc_q35_2_0_machine_options);
-
-
-static void pc_q35_1_7_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_0_machine_options(m);
-    m->hw_version = "1.7.0";
-    m->default_machine_opts = NULL;
-    m->option_rom_has_mr = true;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_7);
-    pcmc->smbios_defaults = false;
-    pcmc->gigabyte_align = false;
-}
-
-DEFINE_Q35_MACHINE(v1_7, "pc-q35-1.7", pc_compat_1_7,
-                   pc_q35_1_7_machine_options);
-
-
-static void pc_q35_1_6_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_machine_options(m);
-    m->hw_version = "1.6.0";
-    m->rom_file_has_mr = false;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_6);
-    pcmc->has_acpi_build = false;
-}
-
-DEFINE_Q35_MACHINE(v1_6, "pc-q35-1.6", pc_compat_1_6,
-                   pc_q35_1_6_machine_options);
-
-
-static void pc_q35_1_5_machine_options(MachineClass *m)
-{
-    pc_q35_1_6_machine_options(m);
-    m->hw_version = "1.5.0";
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_5);
-}
-
-DEFINE_Q35_MACHINE(v1_5, "pc-q35-1.5", pc_compat_1_5,
-                   pc_q35_1_5_machine_options);
-
-
-static void pc_q35_1_4_machine_options(MachineClass *m)
-{
-    pc_q35_1_5_machine_options(m);
-    m->hw_version = "1.4.0";
-    m->hot_add_cpu = NULL;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_4);
-}
-
-DEFINE_Q35_MACHINE(v1_4, "pc-q35-1.4", pc_compat_1_4,
-                   pc_q35_1_4_machine_options);

hw/input/hid.c

@@ -116,37 +116,42 @@ static void hid_pointer_event(DeviceState *dev, QemuConsole *src,
     };
     HIDState *hs = (HIDState *)dev;
     HIDPointerEvent *e;
+    InputMoveEvent *move;
+    InputBtnEvent *btn;
 
     assert(hs->n < QUEUE_LENGTH);
     e = &hs->ptr.queue[(hs->head + hs->n) & QUEUE_MASK];
 
     switch (evt->type) {
     case INPUT_EVENT_KIND_REL:
-        if (evt->u.rel->axis == INPUT_AXIS_X) {
+        move = evt->u.rel;
-            e->xdx += evt->u.rel->value;
+        if (move->axis == INPUT_AXIS_X) {
-        } else if (evt->u.rel->axis == INPUT_AXIS_Y) {
+            e->xdx += move->value;
-            e->ydy += evt->u.rel->value;
+        } else if (move->axis == INPUT_AXIS_Y) {
+            e->ydy += move->value;
         }
         break;
 
     case INPUT_EVENT_KIND_ABS:
-        if (evt->u.rel->axis == INPUT_AXIS_X) {
+        move = evt->u.abs;
-            e->xdx = evt->u.rel->value;
+        if (move->axis == INPUT_AXIS_X) {
-        } else if (evt->u.rel->axis == INPUT_AXIS_Y) {
+            e->xdx = move->value;
-            e->ydy = evt->u.rel->value;
+        } else if (move->axis == INPUT_AXIS_Y) {
+            e->ydy = move->value;
         }
         break;
 
     case INPUT_EVENT_KIND_BTN:
-        if (evt->u.btn->down) {
+        btn = evt->u.btn;
-            e->buttons_state |= bmap[evt->u.btn->button];
+        if (btn->down) {
-            if (evt->u.btn->button == INPUT_BUTTON_WHEELUP) {
+            e->buttons_state |= bmap[btn->button];
+            if (btn->button == INPUT_BUTTON_WHEEL_UP) {
                 e->dz--;
-            } else if (evt->u.btn->button == INPUT_BUTTON_WHEELDOWN) {
+            } else if (btn->button == INPUT_BUTTON_WHEEL_DOWN) {
                 e->dz++;
             }
         } else {
-            e->buttons_state &= ~bmap[evt->u.btn->button];
+            e->buttons_state &= ~bmap[btn->button];
         }
         break;
 
@@ -223,9 +228,10 @@ static void hid_keyboard_event(DeviceState *dev, QemuConsole *src,
     HIDState *hs = (HIDState *)dev;
     int scancodes[3], i, count;
     int slot;
+    InputKeyEvent *key = evt->u.key;
 
-    count = qemu_input_key_value_to_scancode(evt->u.key->key,
+    count = qemu_input_key_value_to_scancode(key->key,
-                                             evt->u.key->down,
+                                             key->down,
                                              scancodes);
     if (hs->n + count > QUEUE_LENGTH) {
         fprintf(stderr, "usb-kbd: warning: key event queue full\n");

hw/input/ps2.c

@@ -182,10 +182,11 @@ static void ps2_keyboard_event(DeviceState *dev, QemuConsole *src,
 {
     PS2KbdState *s = (PS2KbdState *)dev;
     int scancodes[3], i, count;
+    InputKeyEvent *key = evt->u.key;
 
     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
-    count = qemu_input_key_value_to_scancode(evt->u.key->key,
+    count = qemu_input_key_value_to_scancode(key->key,
-                                             evt->u.key->down,
+                                             key->down,
                                              scancodes);
     for (i = 0; i < count; i++) {
         ps2_put_keycode(s, scancodes[i]);
@@ -389,6 +390,8 @@ static void ps2_mouse_event(DeviceState *dev, QemuConsole *src,
         [INPUT_BUTTON_RIGHT]  = MOUSE_EVENT_RBUTTON,
     };
     PS2MouseState *s = (PS2MouseState *)dev;
+    InputMoveEvent *move;
+    InputBtnEvent *btn;
 
     /* check if deltas are recorded when disabled */
     if (!(s->mouse_status & MOUSE_STATUS_ENABLED))
@@ -396,23 +399,25 @@ static void ps2_mouse_event(DeviceState *dev, QemuConsole *src,
 
     switch (evt->type) {
     case INPUT_EVENT_KIND_REL:
-        if (evt->u.rel->axis == INPUT_AXIS_X) {
+        move = evt->u.rel;
-            s->mouse_dx += evt->u.rel->value;
+        if (move->axis == INPUT_AXIS_X) {
-        } else if (evt->u.rel->axis == INPUT_AXIS_Y) {
+            s->mouse_dx += move->value;
-            s->mouse_dy -= evt->u.rel->value;
+        } else if (move->axis == INPUT_AXIS_Y) {
+            s->mouse_dy -= move->value;
         }
         break;
 
     case INPUT_EVENT_KIND_BTN:
-        if (evt->u.btn->down) {
+        btn = evt->u.btn;
-            s->mouse_buttons |= bmap[evt->u.btn->button];
+        if (btn->down) {
-            if (evt->u.btn->button == INPUT_BUTTON_WHEELUP) {
+            s->mouse_buttons |= bmap[btn->button];
+            if (btn->button == INPUT_BUTTON_WHEEL_UP) {
                 s->mouse_dz--;
-            } else if (evt->u.btn->button == INPUT_BUTTON_WHEELDOWN) {
+            } else if (btn->button == INPUT_BUTTON_WHEEL_DOWN) {
                 s->mouse_dz++;
             }
         } else {
-            s->mouse_buttons &= ~bmap[evt->u.btn->button];
+            s->mouse_buttons &= ~bmap[btn->button];
         }
         break;
 

hw/input/virtio-input-hid.c

@@ -143,8 +143,8 @@ static const unsigned int keymap_button[INPUT_BUTTON__MAX] = {
     [INPUT_BUTTON_LEFT]              = BTN_LEFT,
     [INPUT_BUTTON_RIGHT]             = BTN_RIGHT,
     [INPUT_BUTTON_MIDDLE]            = BTN_MIDDLE,
-    [INPUT_BUTTON_WHEELUP]           = BTN_GEAR_UP,
+    [INPUT_BUTTON_WHEEL_UP]          = BTN_GEAR_UP,
-    [INPUT_BUTTON_WHEELDOWN]         = BTN_GEAR_DOWN,
+    [INPUT_BUTTON_WHEEL_DOWN]        = BTN_GEAR_DOWN,
 };
 
 static const unsigned int axismap_rel[INPUT_AXIS__MAX] = {
@@ -191,46 +191,53 @@ static void virtio_input_handle_event(DeviceState *dev, QemuConsole *src,
     VirtIOInput *vinput = VIRTIO_INPUT(dev);
     virtio_input_event event;
     int qcode;
+    InputKeyEvent *key;
+    InputMoveEvent *move;
+    InputBtnEvent *btn;
 
     switch (evt->type) {
     case INPUT_EVENT_KIND_KEY:
-        qcode = qemu_input_key_value_to_qcode(evt->u.key->key);
+        key = evt->u.key;
+        qcode = qemu_input_key_value_to_qcode(key->key);
         if (qcode && keymap_qcode[qcode]) {
             event.type  = cpu_to_le16(EV_KEY);
             event.code  = cpu_to_le16(keymap_qcode[qcode]);
-            event.value = cpu_to_le32(evt->u.key->down ? 1 : 0);
+            event.value = cpu_to_le32(key->down ? 1 : 0);
             virtio_input_send(vinput, &event);
         } else {
-            if (evt->u.key->down) {
+            if (key->down) {
                 fprintf(stderr, "%s: unmapped key: %d [%s]\n", __func__,
                         qcode, QKeyCode_lookup[qcode]);
             }
         }
         break;
     case INPUT_EVENT_KIND_BTN:
-        if (keymap_button[evt->u.btn->button]) {
+        btn = evt->u.btn;
+        if (keymap_button[btn->button]) {
             event.type  = cpu_to_le16(EV_KEY);
-            event.code  = cpu_to_le16(keymap_button[evt->u.btn->button]);
+            event.code  = cpu_to_le16(keymap_button[btn->button]);
-            event.value = cpu_to_le32(evt->u.btn->down ? 1 : 0);
+            event.value = cpu_to_le32(btn->down ? 1 : 0);
             virtio_input_send(vinput, &event);
         } else {
-            if (evt->u.btn->down) {
+            if (btn->down) {
                 fprintf(stderr, "%s: unmapped button: %d [%s]\n", __func__,
-                        evt->u.btn->button,
+                        btn->button,
-                        InputButton_lookup[evt->u.btn->button]);
+                        InputButton_lookup[btn->button]);
             }
         }
         break;
     case INPUT_EVENT_KIND_REL:
+        move = evt->u.rel;
         event.type  = cpu_to_le16(EV_REL);
-        event.code  = cpu_to_le16(axismap_rel[evt->u.rel->axis]);
+        event.code  = cpu_to_le16(axismap_rel[move->axis]);
-        event.value = cpu_to_le32(evt->u.rel->value);
+        event.value = cpu_to_le32(move->value);
         virtio_input_send(vinput, &event);
         break;
     case INPUT_EVENT_KIND_ABS:
+        move = evt->u.abs;
         event.type  = cpu_to_le16(EV_ABS);
-        event.code  = cpu_to_le16(axismap_abs[evt->u.abs->axis]);
+        event.code  = cpu_to_le16(axismap_abs[move->axis]);
-        event.value = cpu_to_le32(evt->u.abs->value);
+        event.value = cpu_to_le32(move->value);
         virtio_input_send(vinput, &event);
         break;
     default:

hw/intc/arm_gic.c

@@ -500,6 +500,41 @@ static uint8_t gic_get_running_priority(GICState *s, int cpu, MemTxAttrs attrs)
     }
 }
 
+/* Return true if we should split priority drop and interrupt deactivation,
+ * ie whether the relevant EOIMode bit is set.
+ */
+static bool gic_eoi_split(GICState *s, int cpu, MemTxAttrs attrs)
+{
+    if (s->revision != 2) {
+        /* Before GICv2 prio-drop and deactivate are not separable */
+        return false;
+    }
+    if (s->security_extn && !attrs.secure) {
+        return s->cpu_ctlr[cpu] & GICC_CTLR_EOIMODE_NS;
+    }
+    return s->cpu_ctlr[cpu] & GICC_CTLR_EOIMODE;
+}
+
+static void gic_deactivate_irq(GICState *s, int cpu, int irq, MemTxAttrs attrs)
+{
+    int cm = 1 << cpu;
+    int group = gic_has_groups(s) && GIC_TEST_GROUP(irq, cm);
+
+    if (!gic_eoi_split(s, cpu, attrs)) {
+        /* This is UNPREDICTABLE; we choose to ignore it */
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "gic_deactivate_irq: GICC_DIR write when EOIMode clear");
+        return;
+    }
+
+    if (s->security_extn && !attrs.secure && !group) {
+        DPRINTF("Non-secure DI for Group0 interrupt %d ignored\n", irq);
+        return;
+    }
+
+    GIC_CLEAR_ACTIVE(irq, cm);
+}
+
 void gic_complete_irq(GICState *s, int cpu, int irq, MemTxAttrs attrs)
 {
     int cm = 1 << cpu;
@@ -544,7 +579,11 @@ void gic_complete_irq(GICState *s, int cpu, int irq, MemTxAttrs attrs)
      */
 
     gic_drop_prio(s, cpu, group);
-    GIC_CLEAR_ACTIVE(irq, cm);
+
+    /* In GICv2 the guest can choose to split priority-drop and deactivate */
+    if (!gic_eoi_split(s, cpu, attrs)) {
+        GIC_CLEAR_ACTIVE(irq, cm);
+    }
     gic_update(s);
 }
 
@@ -1210,6 +1249,10 @@ static MemTxResult gic_cpu_write(GICState *s, int cpu, int offset,
         s->nsapr[regno][cpu] = value;
         break;
     }
+    case 0x1000:
+        /* GICC_DIR */
+        gic_deactivate_irq(s, cpu, value & 0x3ff, attrs);
+        break;
     default:
         qemu_log_mask(LOG_GUEST_ERROR,
                       "gic_cpu_write: Bad offset %x\n", (int)offset);

hw/intc/arm_gic_common.c

@@ -121,7 +121,7 @@ void gic_init_irqs_and_mmio(GICState *s, qemu_irq_handler handler,
          * neither it can use KVM.
          */
         memory_region_init_io(&s->cpuiomem[0], OBJECT(s), ops ? &ops[1] : NULL,
-                              s, "gic_cpu", s->revision == 2 ? 0x1000 : 0x100);
+                              s, "gic_cpu", s->revision == 2 ? 0x2000 : 0x100);
         sysbus_init_mmio(sbd, &s->cpuiomem[0]);
     }
 }

hw/intc/xics.c

@@ -712,7 +712,7 @@ static int ics_find_free_block(ICSState *ics, int num, int alignnum)
     return -1;
 }
 
-int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi)
+int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi, Error **errp)
 {
     ICSState *ics = &icp->ics[src];
     int irq;
@@ -720,14 +720,14 @@ int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi)
     if (irq_hint) {
         assert(src == xics_find_source(icp, irq_hint));
         if (!ICS_IRQ_FREE(ics, irq_hint - ics->offset)) {
-            trace_xics_alloc_failed_hint(src, irq_hint);
+            error_setg(errp, "can't allocate IRQ %d: already in use", irq_hint);
             return -1;
         }
         irq = irq_hint;
     } else {
         irq = ics_find_free_block(ics, 1, 1);
         if (irq < 0) {
-            trace_xics_alloc_failed_no_left(src);
+            error_setg(errp, "can't allocate IRQ: no IRQ left");
             return -1;
         }
         irq += ics->offset;
@@ -743,7 +743,8 @@ int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi)
  * Allocate block of consecutive IRQs, and return the number of the first IRQ in the block.
  * If align==true, aligns the first IRQ number to num.
  */
-int xics_alloc_block(XICSState *icp, int src, int num, bool lsi, bool align)
+int xics_alloc_block(XICSState *icp, int src, int num, bool lsi, bool align,
+                     Error **errp)
 {
     int i, first = -1;
     ICSState *ics = &icp->ics[src];
@@ -763,6 +764,10 @@ int xics_alloc_block(XICSState *icp, int src, int num, bool lsi, bool align)
     } else {
         first = ics_find_free_block(ics, num, 1);
     }
+    if (first < 0) {
+        error_setg(errp, "can't find a free %d-IRQ block", num);
+        return -1;
+    }
 
     if (first >= 0) {
         for (i = first; i < first + num; ++i) {

hw/isa/lpc_ich9.c

@@ -369,13 +369,13 @@ static void ich9_set_sci(void *opaque, int irq_num, int level)
     }
 }
 
-void ich9_lpc_pm_init(PCIDevice *lpc_pci, bool smm_enabled, bool enable_tco)
+void ich9_lpc_pm_init(PCIDevice *lpc_pci, bool smm_enabled)
 {
     ICH9LPCState *lpc = ICH9_LPC_DEVICE(lpc_pci);
     qemu_irq sci_irq;
 
     sci_irq = qemu_allocate_irq(ich9_set_sci, lpc, 0);
-    ich9_pm_init(lpc_pci, &lpc->pm, smm_enabled, enable_tco, sci_irq);
+    ich9_pm_init(lpc_pci, &lpc->pm, smm_enabled, sci_irq);
     ich9_lpc_reset(&lpc->d.qdev);
 }
 

hw/lm32/lm32_boards.c

@@ -143,7 +143,7 @@ static void lm32_evr_init(MachineState *machine)
         int kernel_size;
 
         kernel_size = load_elf(kernel_filename, NULL, NULL, &entry, NULL, NULL,
-                               1, EM_LATTICEMICO32, 0);
+                               1, EM_LATTICEMICO32, 0, 0);
         reset_info->bootstrap_pc = entry;
 
         if (kernel_size < 0) {
@@ -245,7 +245,7 @@ static void lm32_uclinux_init(MachineState *machine)
         int kernel_size;
 
         kernel_size = load_elf(kernel_filename, NULL, NULL, &entry, NULL, NULL,
-                               1, EM_LATTICEMICO32, 0);
+                               1, EM_LATTICEMICO32, 0, 0);
         reset_info->bootstrap_pc = entry;
 
         if (kernel_size < 0) {

hw/lm32/milkymist.c

@@ -177,7 +177,7 @@ milkymist_init(MachineState *machine)
 
         /* Boots a kernel elf binary.  */
         kernel_size = load_elf(kernel_filename, NULL, NULL, &entry, NULL, NULL,
-                               1, EM_LATTICEMICO32, 0);
+                               1, EM_LATTICEMICO32, 0, 0);
         reset_info->bootstrap_pc = entry;
 
         if (kernel_size < 0) {

hw/m68k/an5206.c

@@ -73,7 +73,7 @@ static void an5206_init(MachineState *machine)
     }
 
     kernel_size = load_elf(kernel_filename, NULL, NULL, &elf_entry,
-                           NULL, NULL, 1, EM_68K, 0);
+                           NULL, NULL, 1, EM_68K, 0, 0);
     entry = elf_entry;
     if (kernel_size < 0) {
         kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL,

hw/m68k/dummy_m68k.c

@@ -50,7 +50,7 @@ static void dummy_m68k_init(MachineState *machine)
     /* Load kernel.  */
     if (kernel_filename) {
         kernel_size = load_elf(kernel_filename, NULL, NULL, &elf_entry,
-                               NULL, NULL, 1, EM_68K, 0);
+                               NULL, NULL, 1, EM_68K, 0, 0);
         entry = elf_entry;
         if (kernel_size < 0) {
             kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL,

hw/m68k/mcf5208.c

@@ -276,7 +276,7 @@ static void mcf5208evb_init(MachineState *machine)
     }
 
     kernel_size = load_elf(kernel_filename, NULL, NULL, &elf_entry,
-                           NULL, NULL, 1, EM_68K, 0);
+                           NULL, NULL, 1, EM_68K, 0, 0);
     entry = elf_entry;
     if (kernel_size < 0) {
         kernel_size = load_uimage(kernel_filename, &entry, NULL, NULL,

hw/mem/pc-dimm.c

@@ -192,32 +192,6 @@ int qmp_pc_dimm_device_list(Object *obj, void *opaque)
     return 0;
 }
 
-ram_addr_t get_current_ram_size(void)
-{
-    MemoryDeviceInfoList *info_list = NULL;
-    MemoryDeviceInfoList **prev = &info_list;
-    MemoryDeviceInfoList *info;
-    ram_addr_t size = ram_size;
-
-    qmp_pc_dimm_device_list(qdev_get_machine(), &prev);
-    for (info = info_list; info; info = info->next) {
-        MemoryDeviceInfo *value = info->value;
-
-        if (value) {
-            switch (value->type) {
-            case MEMORY_DEVICE_INFO_KIND_DIMM:
-                size += value->u.dimm->size;
-                break;
-            default:
-                break;
-            }
-        }
-    }
-    qapi_free_MemoryDeviceInfoList(info_list);
-
-    return size;
-}
-
 static int pc_dimm_slot2bitmap(Object *obj, void *opaque)
 {
     unsigned long *bitmap = opaque;

hw/microblaze/boot.c

@@ -142,12 +142,12 @@ void microblaze_load_kernel(MicroBlazeCPU *cpu, hwaddr ddr_base,
         /* Boots a kernel elf binary.  */
         kernel_size = load_elf(kernel_filename, NULL, NULL,
                                &entry, &low, &high,
-                               big_endian, EM_MICROBLAZE, 0);
+                               big_endian, EM_MICROBLAZE, 0, 0);
         base32 = entry;
         if (base32 == 0xc0000000) {
             kernel_size = load_elf(kernel_filename, translate_kernel_address,
                                    NULL, &entry, NULL, NULL,
-                                   big_endian, EM_MICROBLAZE, 0);
+                                   big_endian, EM_MICROBLAZE, 0, 0);
         }
         /* Always boot into physical ram.  */
         boot_info.bootstrap_pc = (uint32_t)entry;

hw/mips/mips_fulong2e.c

@@ -117,7 +117,7 @@ static int64_t load_kernel (CPUMIPSState *env)
 
     if (load_elf(loaderparams.kernel_filename, cpu_mips_kseg0_to_phys, NULL,
                  (uint64_t *)&kernel_entry, (uint64_t *)&kernel_low,
-                 (uint64_t *)&kernel_high, 0, EM_MIPS, 1) < 0) {
+                 (uint64_t *)&kernel_high, 0, EM_MIPS, 1, 0) < 0) {
         fprintf(stderr, "qemu: could not load kernel '%s'\n",
                 loaderparams.kernel_filename);
         exit(1);

hw/mips/mips_malta.c

@@ -796,7 +796,7 @@ static int64_t load_kernel (void)
 
     if (load_elf(loaderparams.kernel_filename, cpu_mips_kseg0_to_phys, NULL,
                  (uint64_t *)&kernel_entry, NULL, (uint64_t *)&kernel_high,
-                 big_endian, EM_MIPS, 1) < 0) {
+                 big_endian, EM_MIPS, 1, 0) < 0) {
         fprintf(stderr, "qemu: could not load kernel '%s'\n",
                 loaderparams.kernel_filename);
         exit(1);

hw/mips/mips_mipssim.c

@@ -70,7 +70,7 @@ static int64_t load_kernel(void)
     kernel_size = load_elf(loaderparams.kernel_filename, cpu_mips_kseg0_to_phys,
                            NULL, (uint64_t *)&entry, NULL,
                            (uint64_t *)&kernel_high, big_endian,
-                           EM_MIPS, 1);
+                           EM_MIPS, 1, 0);
     if (kernel_size >= 0) {
         if ((entry & ~0x7fffffffULL) == 0x80000000)
             entry = (int32_t)entry;

hw/mips/mips_r4k.c

@@ -88,7 +88,7 @@ static int64_t load_kernel(void)
     kernel_size = load_elf(loaderparams.kernel_filename, cpu_mips_kseg0_to_phys,
                            NULL, (uint64_t *)&entry, NULL,
                            (uint64_t *)&kernel_high, big_endian,
-                           EM_MIPS, 1);
+                           EM_MIPS, 1, 0);
     if (kernel_size >= 0) {
         if ((entry & ~0x7fffffffULL) == 0x80000000)
             entry = (int32_t)entry;

hw/misc/bcm2835_mbox.c

@@ -98,7 +98,7 @@ static void bcm2835_mbox_update(BCM2835MboxState *s)
      */
     for (n = 0; n < MBOX_CHAN_COUNT; n++) {
         while (s->available[n] && !(s->mbox[0].status & ARM_MS_FULL)) {
-            value = ldl_phys(&s->mbox_as, n << MBOX_AS_CHAN_SHIFT);
+            value = ldl_le_phys(&s->mbox_as, n << MBOX_AS_CHAN_SHIFT);
             assert(value != MBOX_INVALID_DATA); /* Pending interrupt but no data */
             mbox_push(&s->mbox[0], value);
         }
@@ -207,12 +207,12 @@ static void bcm2835_mbox_write(void *opaque, hwaddr offset,
             ch = value & 0xf;
             if (ch < MBOX_CHAN_COUNT) {
                 childaddr = ch << MBOX_AS_CHAN_SHIFT;
-                if (ldl_phys(&s->mbox_as, childaddr + MBOX_AS_PENDING)) {
+                if (ldl_le_phys(&s->mbox_as, childaddr + MBOX_AS_PENDING)) {
                     /* Child busy, push delayed. Push it in the arm->vc mbox */
                     mbox_push(&s->mbox[1], value);
                 } else {
                     /* Push it directly to the child device */
-                    stl_phys(&s->mbox_as, childaddr, value);
+                    stl_le_phys(&s->mbox_as, childaddr, value);
                 }
             } else {
                 /* Invalid channel number */

hw/misc/bcm2835_property.c

@@ -22,20 +22,20 @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value)
 
     s->addr = value;
 
-    tot_len = ldl_phys(&s->dma_as, value);
+    tot_len = ldl_le_phys(&s->dma_as, value);
 
     /* @(addr + 4) : Buffer response code */
     value = s->addr + 8;
     while (value + 8 <= s->addr + tot_len) {
-        tag = ldl_phys(&s->dma_as, value);
+        tag = ldl_le_phys(&s->dma_as, value);
-        bufsize = ldl_phys(&s->dma_as, value + 4);
+        bufsize = ldl_le_phys(&s->dma_as, value + 4);
         /* @(value + 8) : Request/response indicator */
         resplen = 0;
         switch (tag) {
         case 0x00000000: /* End tag */
             break;
         case 0x00000001: /* Get firmware revision */
-            stl_phys(&s->dma_as, value + 12, 346337);
+            stl_le_phys(&s->dma_as, value + 12, 346337);
             resplen = 4;
             break;
         case 0x00010001: /* Get board model */
@@ -44,7 +44,7 @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value)
             resplen = 4;
             break;
         case 0x00010002: /* Get board revision */
-            stl_phys(&s->dma_as, value + 12, s->board_rev);
+            stl_le_phys(&s->dma_as, value + 12, s->board_rev);
             resplen = 4;
             break;
         case 0x00010003: /* Get board MAC address */
@@ -58,24 +58,24 @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value)
             break;
         case 0x00010005: /* Get ARM memory */
             /* base */
-            stl_phys(&s->dma_as, value + 12, 0);
+            stl_le_phys(&s->dma_as, value + 12, 0);
             /* size */
-            stl_phys(&s->dma_as, value + 16, s->ram_size);
+            stl_le_phys(&s->dma_as, value + 16, s->ram_size);
             resplen = 8;
             break;
         case 0x00028001: /* Set power state */
             /* Assume that whatever device they asked for exists,
              * and we'll just claim we set it to the desired state
              */
-            tmp = ldl_phys(&s->dma_as, value + 16);
+            tmp = ldl_le_phys(&s->dma_as, value + 16);
-            stl_phys(&s->dma_as, value + 16, (tmp & 1));
+            stl_le_phys(&s->dma_as, value + 16, (tmp & 1));
             resplen = 8;
             break;
 
         /* Clocks */
 
         case 0x00030001: /* Get clock state */
-            stl_phys(&s->dma_as, value + 16, 0x1);
+            stl_le_phys(&s->dma_as, value + 16, 0x1);
             resplen = 8;
             break;
 
@@ -88,15 +88,15 @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value)
         case 0x00030002: /* Get clock rate */
         case 0x00030004: /* Get max clock rate */
         case 0x00030007: /* Get min clock rate */
-            switch (ldl_phys(&s->dma_as, value + 12)) {
+            switch (ldl_le_phys(&s->dma_as, value + 12)) {
             case 1: /* EMMC */
-                stl_phys(&s->dma_as, value + 16, 50000000);
+                stl_le_phys(&s->dma_as, value + 16, 50000000);
                 break;
             case 2: /* UART */
-                stl_phys(&s->dma_as, value + 16, 3000000);
+                stl_le_phys(&s->dma_as, value + 16, 3000000);
                 break;
             default:
-                stl_phys(&s->dma_as, value + 16, 700000000);
+                stl_le_phys(&s->dma_as, value + 16, 700000000);
                 break;
             }
             resplen = 8;
@@ -113,19 +113,19 @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value)
         /* Temperature */
 
         case 0x00030006: /* Get temperature */
-            stl_phys(&s->dma_as, value + 16, 25000);
+            stl_le_phys(&s->dma_as, value + 16, 25000);
             resplen = 8;
             break;
 
         case 0x0003000A: /* Get max temperature */
-            stl_phys(&s->dma_as, value + 16, 99000);
+            stl_le_phys(&s->dma_as, value + 16, 99000);
             resplen = 8;
             break;
 
 
         case 0x00060001: /* Get DMA channels */
             /* channels 2-5 */
-            stl_phys(&s->dma_as, value + 12, 0x003C);
+            stl_le_phys(&s->dma_as, value + 12, 0x003C);
             resplen = 4;
             break;
 
@@ -143,12 +143,12 @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value)
             break;
         }
 
-        stl_phys(&s->dma_as, value + 8, (1 << 31) | resplen);
+        stl_le_phys(&s->dma_as, value + 8, (1 << 31) | resplen);
         value += bufsize + 12;
     }
 
     /* Buffer response code */
-    stl_phys(&s->dma_as, s->addr + 4, (1 << 31));
+    stl_le_phys(&s->dma_as, s->addr + 4, (1 << 31));
 }
 
 static uint64_t bcm2835_property_read(void *opaque, hwaddr offset,

hw/misc/macio/mac_dbdma.c

@@ -557,11 +557,13 @@ void DBDMA_register_channel(void *dbdma, int nchan, qemu_irq irq,
 
     DBDMA_DPRINTF("DBDMA_register_channel 0x%x\n", nchan);
 
+    assert(rw);
+    assert(flush);
+
     ch->irq = irq;
     ch->rw = rw;
     ch->flush = flush;
     ch->io.opaque = opaque;
-    ch->io.channel = ch;
 }
 
 static void
@@ -775,6 +777,20 @@ static void dbdma_reset(void *opaque)
         memset(s->channels[i].regs, 0, DBDMA_SIZE);
 }
 
+static void dbdma_unassigned_rw(DBDMA_io *io)
+{
+    DBDMA_channel *ch = io->channel;
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: use of unassigned channel %d\n",
+                  __func__, ch->channel);
+}
+
+static void dbdma_unassigned_flush(DBDMA_io *io)
+{
+    DBDMA_channel *ch = io->channel;
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: use of unassigned channel %d\n",
+                  __func__, ch->channel);
+}
+
 void* DBDMA_init (MemoryRegion **dbdma_mem)
 {
     DBDMAState *s;
@@ -784,8 +800,13 @@ void* DBDMA_init (MemoryRegion **dbdma_mem)
 
     for (i = 0; i < DBDMA_CHANNELS; i++) {
         DBDMA_io *io = &s->channels[i].io;
+        DBDMA_channel *ch = &s->channels[i];
         qemu_iovec_init(&io->iov, 1);
-        s->channels[i].channel = i;
+
+        ch->rw = dbdma_unassigned_rw;
+        ch->flush = dbdma_unassigned_flush;
+        ch->channel = i;
+        ch->io.channel = ch;
     }
 
     memory_region_init_io(&s->mem, NULL, &dbdma_ops, s, "dbdma", 0x1000);

hw/moxie/moxiesim.c

@@ -54,7 +54,8 @@ static void load_kernel(MoxieCPU *cpu, LoaderParams *loader_params)
     ram_addr_t initrd_offset;
 
     kernel_size = load_elf(loader_params->kernel_filename,  NULL, NULL,
-                           &entry, &kernel_low, &kernel_high, 1, EM_MOXIE, 0);
+                           &entry, &kernel_low, &kernel_high, 1, EM_MOXIE,
+                           0, 0);
 
     if (kernel_size <= 0) {
         fprintf(stderr, "qemu: could not load kernel '%s'\n",

hw/net/fsl_etsec/registers.h

@@ -24,7 +24,6 @@
 #ifndef _ETSEC_REGISTERS_H_
 #define _ETSEC_REGISTERS_H_
 
-#include <stdint.h>
 
 enum eTSEC_Register_Access_Type {
     ACC_RW      = 1,            /* Read/Write */

hw/nvram/fw_cfg.c

@@ -778,17 +778,19 @@ FWCfgState *fw_cfg_init_io_dma(uint32_t iobase, uint32_t dma_iobase,
     DeviceState *dev;
     FWCfgState *s;
     uint32_t version = FW_CFG_VERSION;
-    bool dma_enabled = dma_iobase && dma_as;
+    bool dma_requested = dma_iobase && dma_as;
 
     dev = qdev_create(NULL, TYPE_FW_CFG_IO);
     qdev_prop_set_uint32(dev, "iobase", iobase);
     qdev_prop_set_uint32(dev, "dma_iobase", dma_iobase);
-    qdev_prop_set_bit(dev, "dma_enabled", dma_enabled);
+    if (!dma_requested) {
+        qdev_prop_set_bit(dev, "dma_enabled", false);
+    }
 
     fw_cfg_init1(dev);
     s = FW_CFG(dev);
 
-    if (dma_enabled) {
+    if (s->dma_enabled) {
         /* 64 bits for the address field */
         s->dma_as = dma_as;
         s->dma_addr = 0;
@@ -814,11 +816,13 @@ FWCfgState *fw_cfg_init_mem_wide(hwaddr ctl_addr,
     SysBusDevice *sbd;
     FWCfgState *s;
     uint32_t version = FW_CFG_VERSION;
-    bool dma_enabled = dma_addr && dma_as;
+    bool dma_requested = dma_addr && dma_as;
 
     dev = qdev_create(NULL, TYPE_FW_CFG_MEM);
     qdev_prop_set_uint32(dev, "data_width", data_width);
-    qdev_prop_set_bit(dev, "dma_enabled", dma_enabled);
+    if (!dma_requested) {
+        qdev_prop_set_bit(dev, "dma_enabled", false);
+    }
 
     fw_cfg_init1(dev);
 
@@ -828,7 +832,7 @@ FWCfgState *fw_cfg_init_mem_wide(hwaddr ctl_addr,
 
     s = FW_CFG(dev);
 
-    if (dma_enabled) {
+    if (s->dma_enabled) {
         s->dma_as = dma_as;
         s->dma_addr = 0;
         sysbus_mmio_map(sbd, 2, dma_addr);
@@ -873,7 +877,7 @@ static Property fw_cfg_io_properties[] = {
     DEFINE_PROP_UINT32("iobase", FWCfgIoState, iobase, -1),
     DEFINE_PROP_UINT32("dma_iobase", FWCfgIoState, dma_iobase, -1),
     DEFINE_PROP_BOOL("dma_enabled", FWCfgIoState, parent_obj.dma_enabled,
-                     false),
+                     true),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -913,7 +917,7 @@ static const TypeInfo fw_cfg_io_info = {
 static Property fw_cfg_mem_properties[] = {
     DEFINE_PROP_UINT32("data_width", FWCfgMemState, data_width, -1),
     DEFINE_PROP_BOOL("dma_enabled", FWCfgMemState, parent_obj.dma_enabled,
-                     false),
+                     true),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/openrisc/openrisc_sim.c

@@ -69,7 +69,8 @@ static void cpu_openrisc_load_kernel(ram_addr_t ram_size,
 
     if (kernel_filename && !qtest_enabled()) {
         kernel_size = load_elf(kernel_filename, NULL, NULL,
-                               &elf_entry, NULL, NULL, 1, EM_OPENRISC, 1);
+                               &elf_entry, NULL, NULL, 1, EM_OPENRISC,
+                               1, 0);
         entry = elf_entry;
         if (kernel_size < 0) {
             kernel_size = load_uimage(kernel_filename,

hw/pci-host/prep.c

@@ -313,7 +313,7 @@ static void raven_realize(PCIDevice *d, Error **errp)
         if (filename) {
             if (s->elf_machine != EM_NONE) {
                 bios_size = load_elf(filename, NULL, NULL, NULL,
-                                     NULL, NULL, 1, s->elf_machine, 0);
+                                     NULL, NULL, 1, s->elf_machine, 0, 0);
             }
             if (bios_size < 0) {
                 bios_size = get_image_size(filename);