Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

acpi,pc,pci fixes and enhancements

Most changes here are hotplug related:

This merges hotplug infrastructure changes by Igor,
some acpi related fixes, and PC fixes.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Mon 10 Feb 2014 09:13:26 GMT using RSA key ID D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream:
  ACPI: Remove commented-out code from HPET._CRS
  hw/pci: switch to a generic hotplug handling for PCIDevice
  pci/pcie: convert PCIE hotplug to use hotplug-handler API
  pci/shpc: convert SHPC hotplug to use hotplug-handler API
  acpi/piix4pm: convert ACPI PCI hotplug to use hotplug-handler API
  qdev:pci: refactor PCIDevice to use generic "hotpluggable" property
  hw/acpi: move typeinfo to the file end
  qdev: add "hotpluggable" property to Device
  qdev: add to BusState "hotplug-handler" link
  define hotplug interface
  loader: document that errno is set
  pc.c: better error message on initrd sizing failure
  pc_piix: enable legacy hotplug for Xen
  qtest: don't report signals if qtest driver enabled
  hw:piix4:acpi: reuse pcihp code for legacy PCI hotplug
  pcihp: remove unused AcpiPciHpPciStatus.device_present field
  pcihp: make pci_read() mmio calback compatible with legacy ACPI hotplug
  pcihp: make PCI hotplug mmio handlers indifferent to PCI_HOTPLUG_ADDR
  pcihp: replace enable|disable_device() with oneliners
  pcihp: reduce number of device check events

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

.travis.yml

@@ -16,6 +16,7 @@ env:
   matrix:
   - TARGETS=alpha-softmmu,alpha-linux-user
   - TARGETS=arm-softmmu,arm-linux-user
+  - TARGETS=aarch64-softmmu,aarch64-linux-user
   - TARGETS=cris-softmmu
   - TARGETS=i386-softmmu,x86_64-softmmu
   - TARGETS=lm32-softmmu

MAINTAINERS

@@ -610,6 +610,7 @@ F: hw/*/*vhost*
 
 virtio
 M: Anthony Liguori <aliguori@amazon.com>
+M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
 F: hw/*/virtio*
 
@@ -714,6 +715,7 @@ F: ui/
 
 Cocoa graphics
 M: Andreas Färber <andreas.faerber@web.de>
+M: Peter Maydell <peter.maydell@linaro.org>
 S: Odd Fixes
 F: ui/cocoa.m
 
@@ -935,6 +937,11 @@ M: Peter Lieven <pl@kamp.de>
 S: Supported
 F: block/iscsi.c
 
+NFS
+M: Peter Lieven <pl@kamp.de>
+S: Maintained
+F: block/nfs.c
+
 SSH
 M: Richard W.M. Jones <rjones@redhat.com>
 S: Supported

Makefile

@@ -290,7 +290,7 @@ common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr \
 bepo    cz
 
 ifdef INSTALL_BLOBS
-BLOBS=bios.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
+BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin \
 acpi-dsdt.aml q35-acpi-dsdt.aml \
 ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin \

Makefile.objs

@@ -43,7 +43,6 @@ libcacard-y += libcacard/vcardt.o
 ifeq ($(CONFIG_SOFTMMU),y)
 common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
 common-obj-y += net/
-common-obj-y += readline.o
 common-obj-y += qdev-monitor.o device-hotplug.o
 common-obj-$(CONFIG_WIN32) += os-win32.o
 common-obj-$(CONFIG_POSIX) += os-posix.o
@@ -51,6 +50,8 @@ common-obj-$(CONFIG_POSIX) += os-posix.o
 common-obj-$(CONFIG_LINUX) += fsdev/
 
 common-obj-y += migration.o migration-tcp.o
+common-obj-y += vmstate.o
+common-obj-y += qemu-file.o
 common-obj-$(CONFIG_RDMA) += migration-rdma.o
 common-obj-y += qemu-char.o #aio.o
 common-obj-y += block-migration.o

arch_init.c

@@ -48,7 +48,9 @@
 #include "qmp-commands.h"
 #include "trace.h"
 #include "exec/cpu-all.h"
+#include "exec/ram_addr.h"
 #include "hw/acpi/acpi.h"
+#include "qemu/host-utils.h"
 
 #ifdef DEBUG_ARCH_INIT
 #define DPRINTF(fmt, ...) \
@@ -162,20 +164,22 @@ static struct {
     uint8_t *encoded_buf;
     /* buffer for storing page content */
     uint8_t *current_buf;
-    /* buffer used for XBZRLE decoding */
-    uint8_t *decoded_buf;
     /* Cache for XBZRLE */
     PageCache *cache;
 } XBZRLE = {
     .encoded_buf = NULL,
     .current_buf = NULL,
-    .decoded_buf = NULL,
     .cache = NULL,
 };
-
+/* buffer used for XBZRLE decoding */
+static uint8_t *xbzrle_decoded_buf;
 
 int64_t xbzrle_cache_resize(int64_t new_size)
 {
+    if (new_size < TARGET_PAGE_SIZE) {
+        return -1;
+    }
+
     if (XBZRLE.cache != NULL) {
         return cache_resize(XBZRLE.cache, new_size / TARGET_PAGE_SIZE) *
             TARGET_PAGE_SIZE;
@@ -280,7 +284,9 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
 
     if (!cache_is_cached(XBZRLE.cache, current_addr)) {
         if (!last_stage) {
-            cache_insert(XBZRLE.cache, current_addr, current_data);
+            if (cache_insert(XBZRLE.cache, current_addr, current_data) == -1) {
+                return -1;
+            }
         }
         acct_info.xbzrle_cache_miss++;
         return -1;
@@ -359,11 +365,10 @@ ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
     return (next - base) << TARGET_PAGE_BITS;
 }
 
-static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
-                                              ram_addr_t offset)
+static inline bool migration_bitmap_set_dirty(ram_addr_t addr)
 {
     bool ret;
-    int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
+    int nr = addr >> TARGET_PAGE_BITS;
 
     ret = test_and_set_bit(nr, migration_bitmap);
 
@@ -373,12 +378,47 @@ static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
     return ret;
 }
 
+static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
+{
+    ram_addr_t addr;
+    unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
+
+    /* start address is aligned at the start of a word? */
+    if (((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) {
+        int k;
+        int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS);
+        unsigned long *src = ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION];
+
+        for (k = page; k < page + nr; k++) {
+            if (src[k]) {
+                unsigned long new_dirty;
+                new_dirty = ~migration_bitmap[k];
+                migration_bitmap[k] |= src[k];
+                new_dirty &= src[k];
+                migration_dirty_pages += ctpopl(new_dirty);
+                src[k] = 0;
+            }
+        }
+    } else {
+        for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) {
+            if (cpu_physical_memory_get_dirty(start + addr,
+                                              TARGET_PAGE_SIZE,
+                                              DIRTY_MEMORY_MIGRATION)) {
+                cpu_physical_memory_reset_dirty(start + addr,
+                                                TARGET_PAGE_SIZE,
+                                                DIRTY_MEMORY_MIGRATION);
+                migration_bitmap_set_dirty(start + addr);
+            }
+        }
+    }
+}
+
+
 /* Needs iothread lock! */
 
 static void migration_bitmap_sync(void)
 {
     RAMBlock *block;
-    ram_addr_t addr;
     uint64_t num_dirty_pages_init = migration_dirty_pages;
     MigrationState *s = migrate_get_current();
     static int64_t start_time;
@@ -399,13 +439,7 @@ static void migration_bitmap_sync(void)
     address_space_sync_dirty_bitmap(&address_space_memory);
 
     QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-        for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
-            if (memory_region_test_and_clear_dirty(block->mr,
-                                                   addr, TARGET_PAGE_SIZE,
-                                                   DIRTY_MEMORY_MIGRATION)) {
-                migration_bitmap_set_dirty(block->mr, addr);
-            }
-        }
+        migration_bitmap_sync_range(block->mr->ram_addr, block->length);
     }
     trace_migration_bitmap_sync_end(migration_dirty_pages
                                     - num_dirty_pages_init);
@@ -572,6 +606,12 @@ uint64_t ram_bytes_total(void)
     return total;
 }
 
+void free_xbzrle_decoded_buf(void)
+{
+    g_free(xbzrle_decoded_buf);
+    xbzrle_decoded_buf = NULL;
+}
+
 static void migration_end(void)
 {
     if (migration_bitmap) {
@@ -585,8 +625,9 @@ static void migration_end(void)
         g_free(XBZRLE.cache);
         g_free(XBZRLE.encoded_buf);
         g_free(XBZRLE.current_buf);
-        g_free(XBZRLE.decoded_buf);
         XBZRLE.cache = NULL;
+        XBZRLE.encoded_buf = NULL;
+        XBZRLE.current_buf = NULL;
     }
 }
 
@@ -625,8 +666,22 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
             DPRINTF("Error creating cache\n");
             return -1;
         }
-        XBZRLE.encoded_buf = g_malloc0(TARGET_PAGE_SIZE);
-        XBZRLE.current_buf = g_malloc(TARGET_PAGE_SIZE);
+
+        /* We prefer not to abort if there is no memory */
+        XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
+        if (!XBZRLE.encoded_buf) {
+            DPRINTF("Error allocating encoded_buf\n");
+            return -1;
+        }
+
+        XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
+        if (!XBZRLE.current_buf) {
+            DPRINTF("Error allocating current_buf\n");
+            g_free(XBZRLE.encoded_buf);
+            XBZRLE.encoded_buf = NULL;
+            return -1;
+        }
+
         acct_clear();
     }
 
@@ -777,8 +832,8 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
     unsigned int xh_len;
     int xh_flags;
 
-    if (!XBZRLE.decoded_buf) {
-        XBZRLE.decoded_buf = g_malloc(TARGET_PAGE_SIZE);
+    if (!xbzrle_decoded_buf) {
+        xbzrle_decoded_buf = g_malloc(TARGET_PAGE_SIZE);
     }
 
     /* extract RLE header */
@@ -795,10 +850,10 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
         return -1;
     }
     /* load data and decode */
-    qemu_get_buffer(f, XBZRLE.decoded_buf, xh_len);
+    qemu_get_buffer(f, xbzrle_decoded_buf, xh_len);
 
     /* decode RLE */
-    ret = xbzrle_decode_buffer(XBZRLE.decoded_buf, xh_len, host,
+    ret = xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
                                TARGET_PAGE_SIZE);
     if (ret == -1) {
         fprintf(stderr, "Failed to load XBZRLE page - decode error!\n");

audio/spiceaudio.c

@@ -25,8 +25,17 @@
 #include "audio.h"
 #include "audio_int.h"
 
-#define LINE_IN_SAMPLES 1024
-#define LINE_OUT_SAMPLES 1024
+#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
+#define LINE_OUT_SAMPLES (480 * 4)
+#else
+#define LINE_OUT_SAMPLES (256 * 4)
+#endif
+
+#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
+#define LINE_IN_SAMPLES (480 * 4)
+#else
+#define LINE_IN_SAMPLES (256 * 4)
+#endif
 
 typedef struct SpiceRateCtl {
     int64_t               start_ticks;
@@ -111,7 +120,11 @@ static int line_out_init (HWVoiceOut *hw, struct audsettings *as)
     SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
     struct audsettings settings;
 
+#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
+    settings.freq       = spice_server_get_best_playback_rate(NULL);
+#else
     settings.freq       = SPICE_INTERFACE_PLAYBACK_FREQ;
+#endif
     settings.nchannels  = SPICE_INTERFACE_PLAYBACK_CHAN;
     settings.fmt        = AUD_FMT_S16;
     settings.endianness = AUDIO_HOST_ENDIANNESS;
@@ -122,6 +135,9 @@ static int line_out_init (HWVoiceOut *hw, struct audsettings *as)
 
     out->sin.base.sif = &playback_sif.base;
     qemu_spice_add_interface (&out->sin.base);
+#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
+    spice_server_set_playback_rate(&out->sin, settings.freq);
+#endif
     return 0;
 }
 
@@ -232,7 +248,11 @@ static int line_in_init (HWVoiceIn *hw, struct audsettings *as)
     SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
     struct audsettings settings;
 
+#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
+    settings.freq       = spice_server_get_best_record_rate(NULL);
+#else
     settings.freq       = SPICE_INTERFACE_RECORD_FREQ;
+#endif
     settings.nchannels  = SPICE_INTERFACE_RECORD_CHAN;
     settings.fmt        = AUD_FMT_S16;
     settings.endianness = AUDIO_HOST_ENDIANNESS;
@@ -243,6 +263,9 @@ static int line_in_init (HWVoiceIn *hw, struct audsettings *as)
 
     in->sin.base.sif = &record_sif.base;
     qemu_spice_add_interface (&in->sin.base);
+#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
+    spice_server_set_record_rate(&in->sin, settings.freq);
+#endif
     return 0;
 }
 

backends/rng-random.c

@@ -123,15 +123,15 @@ static void rng_random_init(Object *obj)
                             NULL);
 
     s->filename = g_strdup("/dev/random");
+    s->fd = -1;
 }
 
 static void rng_random_finalize(Object *obj)
 {
     RndRandom *s = RNG_RANDOM(obj);
 
-    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-
     if (s->fd != -1) {
+        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
         qemu_close(s->fd);
     }
 

backends/rng.c

@@ -12,6 +12,7 @@
 
 #include "sysemu/rng.h"
 #include "qapi/qmp/qerror.h"
+#include "qom/object_interfaces.h"
 
 void rng_backend_request_entropy(RngBackend *s, size_t size,
                                  EntropyReceiveFunc *receive_entropy,
@@ -40,9 +41,9 @@ static bool rng_backend_prop_get_opened(Object *obj, Error **errp)
     return s->opened;
 }
 
-void rng_backend_open(RngBackend *s, Error **errp)
+static void rng_backend_complete(UserCreatable *uc, Error **errp)
 {
-    object_property_set_bool(OBJECT(s), true, "opened", errp);
+    object_property_set_bool(OBJECT(uc), true, "opened", errp);
 }
 
 static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
@@ -76,13 +77,25 @@ static void rng_backend_init(Object *obj)
                              NULL);
 }
 
+static void rng_backend_class_init(ObjectClass *oc, void *data)
+{
+    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
+
+    ucc->complete = rng_backend_complete;
+}
+
 static const TypeInfo rng_backend_info = {
     .name = TYPE_RNG_BACKEND,
     .parent = TYPE_OBJECT,
     .instance_size = sizeof(RngBackend),
     .instance_init = rng_backend_init,
     .class_size = sizeof(RngBackendClass),
+    .class_init = rng_backend_class_init,
     .abstract = true,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_USER_CREATABLE },
+        { }
+    }
 };
 
 static void register_types(void)

block/Makefile.objs

@@ -12,6 +12,7 @@ block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 ifeq ($(CONFIG_POSIX),y)
 block-obj-y += nbd.o nbd-client.o sheepdog.o
 block-obj-$(CONFIG_LIBISCSI) += iscsi.o
+block-obj-$(CONFIG_LIBNFS) += nfs.o
 block-obj-$(CONFIG_CURL) += curl.o
 block-obj-$(CONFIG_RBD) += rbd.o
 block-obj-$(CONFIG_GLUSTERFS) += gluster.o

block/backup.c

@@ -181,8 +181,13 @@ static int coroutine_fn backup_before_write_notify(
         void *opaque)
 {
     BdrvTrackedRequest *req = opaque;
+    int64_t sector_num = req->offset >> BDRV_SECTOR_BITS;
+    int nb_sectors = req->bytes >> BDRV_SECTOR_BITS;
 
-    return backup_do_cow(req->bs, req->sector_num, req->nb_sectors, NULL);
+    assert((req->offset & (BDRV_SECTOR_SIZE - 1)) == 0);
+    assert((req->bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
+
+    return backup_do_cow(req->bs, sector_num, nb_sectors, NULL);
 }
 
 static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)

block/blkdebug.c

@@ -186,6 +186,14 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
 
     [BLKDBG_FLUSH_TO_OS]                    = "flush_to_os",
     [BLKDBG_FLUSH_TO_DISK]                  = "flush_to_disk",
+
+    [BLKDBG_PWRITEV_RMW_HEAD]               = "pwritev_rmw.head",
+    [BLKDBG_PWRITEV_RMW_AFTER_HEAD]         = "pwritev_rmw.after_head",
+    [BLKDBG_PWRITEV_RMW_TAIL]               = "pwritev_rmw.tail",
+    [BLKDBG_PWRITEV_RMW_AFTER_TAIL]         = "pwritev_rmw.after_tail",
+    [BLKDBG_PWRITEV]                        = "pwritev",
+    [BLKDBG_PWRITEV_ZERO]                   = "pwritev_zero",
+    [BLKDBG_PWRITEV_DONE]                   = "pwritev_done",
 };
 
 static int get_event_by_name(const char *name, BlkDebugEvent *event)
@@ -271,19 +279,33 @@ static void remove_rule(BlkdebugRule *rule)
     g_free(rule);
 }
 
-static int read_config(BDRVBlkdebugState *s, const char *filename)
+static int read_config(BDRVBlkdebugState *s, const char *filename,
+                       QDict *options, Error **errp)
 {
-    FILE *f;
+    FILE *f = NULL;
     int ret;
     struct add_rule_data d;
+    Error *local_err = NULL;
 
+    if (filename) {
         f = fopen(filename, "r");
         if (f == NULL) {
+            error_setg_errno(errp, errno, "Could not read blkdebug config file");
             return -errno;
         }
 
         ret = qemu_config_parse(f, config_groups, filename);
         if (ret < 0) {
+            error_setg(errp, "Could not parse blkdebug config file");
+            ret = -EINVAL;
+            goto fail;
+        }
+    }
+
+    qemu_config_parse_qdict(options, config_groups, &local_err);
+    if (error_is_set(&local_err)) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
         goto fail;
     }
 
@@ -298,7 +320,9 @@ static int read_config(BDRVBlkdebugState *s, const char *filename)
 fail:
     qemu_opts_reset(&inject_error_opts);
     qemu_opts_reset(&set_state_opts);
+    if (f) {
         fclose(f);
+    }
     return ret;
 }
 
@@ -310,7 +334,9 @@ static void blkdebug_parse_filename(const char *filename, QDict *options,
 
     /* Parse the blkdebug: prefix */
     if (!strstart(filename, "blkdebug:", &filename)) {
-        error_setg(errp, "File name string must start with 'blkdebug:'");
+        /* There was no prefix; therefore, all options have to be already
+           present in the QDict (except for the filename) */
+        qdict_put(options, "x-image", qstring_from_str(filename));
         return;
     }
 
@@ -346,6 +372,11 @@ static QemuOptsList runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "[internal use only, will be removed]",
         },
+        {
+            .name = "align",
+            .type = QEMU_OPT_SIZE,
+            .help = "Required alignment in bytes",
+        },
         { /* end of list */ }
     },
 };
@@ -356,46 +387,52 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     BDRVBlkdebugState *s = bs->opaque;
     QemuOpts *opts;
     Error *local_err = NULL;
-    const char *filename, *config;
+    const char *config;
+    uint64_t align;
     int ret;
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
         ret = -EINVAL;
-        goto fail;
+        goto out;
     }
 
-    /* Read rules from config file */
+    /* Read rules from config file or command line options */
     config = qemu_opt_get(opts, "config");
-    if (config) {
-        ret = read_config(s, config);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not read blkdebug config file");
-            goto fail;
-        }
+    ret = read_config(s, config, options, errp);
+    if (ret) {
+        goto out;
     }
 
     /* Set initial state */
     s->state = 1;
 
     /* Open the backing file */
-    filename = qemu_opt_get(opts, "x-image");
-    if (filename == NULL) {
-        error_setg(errp, "Could not retrieve image file name");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    ret = bdrv_file_open(&bs->file, filename, NULL, flags, &local_err);
+    ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-image"), options, "image",
+                          flags, true, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
-        goto fail;
+        goto out;
+    }
+
+    /* Set request alignment */
+    align = qemu_opt_get_size(opts, "align", bs->request_alignment);
+    if (align > 0 && align < INT_MAX && !(align & (align - 1))) {
+        bs->request_alignment = align;
+    } else {
+        error_setg(errp, "Invalid alignment");
+        ret = -EINVAL;
+        goto fail_unref;
     }
 
     ret = 0;
-fail:
+    goto out;
+
+fail_unref:
+    bdrv_unref(bs->file);
+out:
     qemu_opts_del(opts);
     return ret;
 }

block/blkverify.c

@@ -78,7 +78,9 @@ static void blkverify_parse_filename(const char *filename, QDict *options,
 
     /* Parse the blkverify: prefix */
     if (!strstart(filename, "blkverify:", &filename)) {
-        error_setg(errp, "File name string must start with 'blkverify:'");
+        /* There was no prefix; therefore, all options have to be already
+           present in the QDict (except for the filename) */
+        qdict_put(options, "x-image", qstring_from_str(filename));
         return;
     }
 
@@ -122,10 +124,9 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
     BDRVBlkverifyState *s = bs->opaque;
     QemuOpts *opts;
     Error *local_err = NULL;
-    const char *filename, *raw;
     int ret;
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
@@ -133,33 +134,19 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    /* Parse the raw image filename */
-    raw = qemu_opt_get(opts, "x-raw");
-    if (raw == NULL) {
-        error_setg(errp, "Could not retrieve raw image filename");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    ret = bdrv_file_open(&bs->file, raw, NULL, flags, &local_err);
+    /* Open the raw file */
+    ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-raw"), options,
+                          "raw", flags, true, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto fail;
     }
 
     /* Open the test file */
-    filename = qemu_opt_get(opts, "x-image");
-    if (filename == NULL) {
-        error_setg(errp, "Could not retrieve test image filename");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    s->test_file = bdrv_new("");
-    ret = bdrv_open(s->test_file, filename, NULL, flags, NULL, &local_err);
+    ret = bdrv_open_image(&s->test_file, qemu_opt_get(opts, "x-image"), options,
+                          "test", flags, false, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
-        bdrv_unref(s->test_file);
         s->test_file = NULL;
         goto fail;
     }
@@ -417,7 +404,7 @@ static BlockDriver bdrv_blkverify = {
     .bdrv_aio_writev        = blkverify_aio_writev,
     .bdrv_aio_flush         = blkverify_aio_flush,
 
-    .bdrv_check_ext_snapshot = bdrv_check_ext_snapshot_forbidden,
+    .authorizations         = { true, false },
 };
 
 static void bdrv_blkverify_init(void)

block/commit.c

@@ -198,13 +198,7 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
         return;
     }
 
-    /* Once we support top == active layer, remove this check */
-    if (top == bs) {
-        error_setg(errp,
-                   "Top image as the active layer is currently unsupported");
-        return;
-    }
-
+    assert(top != bs);
     if (top == base) {
         error_setg(errp, "Invalid files for merge: top and base are the same");
         return;

block/cow.c

@@ -351,7 +351,8 @@ static int cow_create(const char *filename, QEMUOptionParameter *options,
         return ret;
     }
 
-    ret = bdrv_file_open(&cow_bs, filename, NULL, BDRV_O_RDWR, &local_err);
+    ret = bdrv_file_open(&cow_bs, filename, NULL, NULL, BDRV_O_RDWR,
+                         &local_err);
     if (ret < 0) {
         qerror_report_err(local_err);
         error_free(local_err);

block/curl.c

@@ -34,6 +34,11 @@
 #define DPRINTF(fmt, ...) do { } while (0)
 #endif
 
+#if LIBCURL_VERSION_NUM >= 0x071000
+/* The multi interface timer callback was introduced in 7.16.0 */
+#define NEED_CURL_TIMER_CALLBACK
+#endif
+
 #define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
                    CURLPROTO_FTP | CURLPROTO_FTPS | \
                    CURLPROTO_TFTP)
@@ -77,6 +82,7 @@ typedef struct CURLState
 
 typedef struct BDRVCURLState {
     CURLM *multi;
+    QEMUTimer timer;
     size_t len;
     CURLState states[CURL_NUM_STATES];
     char *url;
@@ -87,6 +93,23 @@ typedef struct BDRVCURLState {
 static void curl_clean_state(CURLState *s);
 static void curl_multi_do(void *arg);
 
+#ifdef NEED_CURL_TIMER_CALLBACK
+static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
+{
+    BDRVCURLState *s = opaque;
+
+    DPRINTF("CURL: timer callback timeout_ms %ld\n", timeout_ms);
+    if (timeout_ms == -1) {
+        timer_del(&s->timer);
+    } else {
+        int64_t timeout_ns = (int64_t)timeout_ms * 1000 * 1000;
+        timer_mod(&s->timer,
+                  qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + timeout_ns);
+    }
+    return 0;
+}
+#endif
+
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
                         void *s, void *sp)
 {
@@ -209,20 +232,10 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
     return FIND_RET_NONE;
 }
 
-static void curl_multi_do(void *arg)
+static void curl_multi_read(BDRVCURLState *s)
 {
-    BDRVCURLState *s = (BDRVCURLState *)arg;
-    int running;
-    int r;
     int msgs_in_queue;
 
-    if (!s->multi)
-        return;
-
-    do {
-        r = curl_multi_socket_all(s->multi, &running);
-    } while(r == CURLM_CALL_MULTI_PERFORM);
-
     /* Try to find done transfers, so we can free the easy
      * handle again. */
     do {
@@ -266,6 +279,41 @@ static void curl_multi_do(void *arg)
     } while(msgs_in_queue);
 }
 
+static void curl_multi_do(void *arg)
+{
+    BDRVCURLState *s = (BDRVCURLState *)arg;
+    int running;
+    int r;
+
+    if (!s->multi) {
+        return;
+    }
+
+    do {
+        r = curl_multi_socket_all(s->multi, &running);
+    } while(r == CURLM_CALL_MULTI_PERFORM);
+
+    curl_multi_read(s);
+}
+
+static void curl_multi_timeout_do(void *arg)
+{
+#ifdef NEED_CURL_TIMER_CALLBACK
+    BDRVCURLState *s = (BDRVCURLState *)arg;
+    int running;
+
+    if (!s->multi) {
+        return;
+    }
+
+    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
+
+    curl_multi_read(s);
+#else
+    abort();
+#endif
+}
+
 static CURLState *curl_init_state(BDRVCURLState *s)
 {
     CURLState *state = NULL;
@@ -413,7 +461,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
         return -EROFS;
     }
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         qerror_report_err(local_err);
@@ -473,12 +521,20 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 
+    aio_timer_init(bdrv_get_aio_context(bs), &s->timer,
+                   QEMU_CLOCK_REALTIME, SCALE_NS,
+                   curl_multi_timeout_do, s);
+
     // Now we know the file exists and its size, so let's
     // initialize the multi interface!
 
     s->multi = curl_multi_init();
     curl_multi_setopt(s->multi, CURLMOPT_SOCKETDATA, s);
     curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
+#ifdef NEED_CURL_TIMER_CALLBACK
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
+#endif
     curl_multi_do(s);
 
     qemu_opts_del(opts);
@@ -597,6 +653,9 @@ static void curl_close(BlockDriverState *bs)
     }
     if (s->multi)
         curl_multi_cleanup(s->multi);
+
+    timer_del(&s->timer);
+
     g_free(s->url);
 }
 

block/gluster.c

@@ -21,19 +21,15 @@
 #include "qemu/uri.h"
 
 typedef struct GlusterAIOCB {
-    BlockDriverAIOCB common;
     int64_t size;
     int ret;
-    bool *finished;
     QEMUBH *bh;
+    Coroutine *coroutine;
 } GlusterAIOCB;
 
 typedef struct BDRVGlusterState {
     struct glfs *glfs;
-    int fds[2];
     struct glfs_fd *fd;
-    int event_reader_pos;
-    GlusterAIOCB *event_acb;
 } BDRVGlusterState;
 
 #define GLUSTER_FD_READ  0
@@ -231,46 +227,32 @@ out:
     return NULL;
 }
 
-static void qemu_gluster_complete_aio(GlusterAIOCB *acb, BDRVGlusterState *s)
+static void qemu_gluster_complete_aio(void *opaque)
 {
-    int ret;
-    bool *finished = acb->finished;
-    BlockDriverCompletionFunc *cb = acb->common.cb;
-    void *opaque = acb->common.opaque;
+    GlusterAIOCB *acb = (GlusterAIOCB *)opaque;
 
-    if (!acb->ret || acb->ret == acb->size) {
-        ret = 0; /* Success */
-    } else if (acb->ret < 0) {
-        ret = acb->ret; /* Read/Write failed */
+    qemu_bh_delete(acb->bh);
+    acb->bh = NULL;
+    qemu_coroutine_enter(acb->coroutine, NULL);
+}
+
+/*
+ * AIO callback routine called from GlusterFS thread.
+ */
+static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
+{
+    GlusterAIOCB *acb = (GlusterAIOCB *)arg;
+
+    if (!ret || ret == acb->size) {
+        acb->ret = 0; /* Success */
+    } else if (ret < 0) {
+        acb->ret = ret; /* Read/Write failed */
     } else {
-        ret = -EIO; /* Partial read/write - fail it */
+        acb->ret = -EIO; /* Partial read/write - fail it */
     }
 
-    qemu_aio_release(acb);
-    cb(opaque, ret);
-    if (finished) {
-        *finished = true;
-    }
-}
-
-static void qemu_gluster_aio_event_reader(void *opaque)
-{
-    BDRVGlusterState *s = opaque;
-    ssize_t ret;
-
-    do {
-        char *p = (char *)&s->event_acb;
-
-        ret = read(s->fds[GLUSTER_FD_READ], p + s->event_reader_pos,
-                   sizeof(s->event_acb) - s->event_reader_pos);
-        if (ret > 0) {
-            s->event_reader_pos += ret;
-            if (s->event_reader_pos == sizeof(s->event_acb)) {
-                s->event_reader_pos = 0;
-                qemu_gluster_complete_aio(s->event_acb, s);
-            }
-        }
-    } while (ret < 0 && errno == EINTR);
+    acb->bh = qemu_bh_new(qemu_gluster_complete_aio, acb);
+    qemu_bh_schedule(acb->bh);
 }
 
 /* TODO Convert to fine grained options */
@@ -298,7 +280,7 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
     Error *local_err = NULL;
     const char *filename;
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         qerror_report_err(local_err);
@@ -309,7 +291,6 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
 
     filename = qemu_opt_get(opts, "filename");
 
-
     s->glfs = qemu_gluster_init(gconf, filename);
     if (!s->glfs) {
         ret = -errno;
@@ -329,18 +310,8 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
     s->fd = glfs_open(s->glfs, gconf->image, open_flags);
     if (!s->fd) {
         ret = -errno;
-        goto out;
     }
 
-    ret = qemu_pipe(s->fds);
-    if (ret < 0) {
-        ret = -errno;
-        goto out;
-    }
-    fcntl(s->fds[GLUSTER_FD_READ], F_SETFL, O_NONBLOCK);
-    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ],
-        qemu_gluster_aio_event_reader, NULL, s);
-
 out:
     qemu_opts_del(opts);
     qemu_gluster_gconf_free(gconf);
@@ -356,12 +327,65 @@ out:
     return ret;
 }
 
+#ifdef CONFIG_GLUSTERFS_ZEROFILL
+static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
+{
+    int ret;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+    BDRVGlusterState *s = bs->opaque;
+    off_t size = nb_sectors * BDRV_SECTOR_SIZE;
+    off_t offset = sector_num * BDRV_SECTOR_SIZE;
+
+    acb->size = size;
+    acb->ret = 0;
+    acb->coroutine = qemu_coroutine_self();
+
+    ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
+    if (ret < 0) {
+        ret = -errno;
+        goto out;
+    }
+
+    qemu_coroutine_yield();
+    ret = acb->ret;
+
+out:
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
+}
+
+static inline bool gluster_supports_zerofill(void)
+{
+    return 1;
+}
+
+static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
+        int64_t size)
+{
+    return glfs_zerofill(fd, offset, size);
+}
+
+#else
+static inline bool gluster_supports_zerofill(void)
+{
+    return 0;
+}
+
+static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
+        int64_t size)
+{
+    return 0;
+}
+#endif
+
 static int qemu_gluster_create(const char *filename,
         QEMUOptionParameter *options, Error **errp)
 {
     struct glfs *glfs;
     struct glfs_fd *fd;
     int ret = 0;
+    int prealloc = 0;
     int64_t total_size = 0;
     GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
 
@@ -374,6 +398,19 @@ static int qemu_gluster_create(const char *filename,
     while (options && options->name) {
         if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
             total_size = options->value.n / BDRV_SECTOR_SIZE;
+        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
+            if (!options->value.s || !strcmp(options->value.s, "off")) {
+                prealloc = 0;
+            } else if (!strcmp(options->value.s, "full") &&
+                    gluster_supports_zerofill()) {
+                prealloc = 1;
+            } else {
+                error_setg(errp, "Invalid preallocation mode: '%s'"
+                    " or GlusterFS doesn't support zerofill API",
+                           options->value.s);
+                ret = -EINVAL;
+                goto out;
+            }
         }
         options++;
     }
@@ -383,9 +420,15 @@ static int qemu_gluster_create(const char *filename,
     if (!fd) {
         ret = -errno;
     } else {
-        if (glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
+        if (!glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE)) {
+            if (prealloc && qemu_gluster_zerofill(fd, 0,
+                    total_size * BDRV_SECTOR_SIZE)) {
                 ret = -errno;
             }
+        } else {
+            ret = -errno;
+        }
+
         if (glfs_close(fd) != 0) {
             ret = -errno;
         }
@@ -398,58 +441,18 @@ out:
     return ret;
 }
 
-static void qemu_gluster_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    GlusterAIOCB *acb = (GlusterAIOCB *)blockacb;
-    bool finished = false;
-
-    acb->finished = &finished;
-    while (!finished) {
-        qemu_aio_wait();
-    }
-}
-
-static const AIOCBInfo gluster_aiocb_info = {
-    .aiocb_size = sizeof(GlusterAIOCB),
-    .cancel = qemu_gluster_aio_cancel,
-};
-
-static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
-{
-    GlusterAIOCB *acb = (GlusterAIOCB *)arg;
-    BlockDriverState *bs = acb->common.bs;
-    BDRVGlusterState *s = bs->opaque;
-    int retval;
-
-    acb->ret = ret;
-    retval = qemu_write_full(s->fds[GLUSTER_FD_WRITE], &acb, sizeof(acb));
-    if (retval != sizeof(acb)) {
-        /*
-         * Gluster AIO callback thread failed to notify the waiting
-         * QEMU thread about IO completion.
-         */
-        error_report("Gluster AIO completion failed: %s", strerror(errno));
-        abort();
-    }
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_rw(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int write)
+static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int write)
 {
     int ret;
-    GlusterAIOCB *acb;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
     BDRVGlusterState *s = bs->opaque;
-    size_t size;
-    off_t offset;
+    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
+    off_t offset = sector_num * BDRV_SECTOR_SIZE;
 
-    offset = sector_num * BDRV_SECTOR_SIZE;
-    size = nb_sectors * BDRV_SECTOR_SIZE;
-
-    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
     acb->size = size;
     acb->ret = 0;
-    acb->finished = NULL;
+    acb->coroutine = qemu_coroutine_self();
 
     if (write) {
         ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
@@ -460,13 +463,16 @@ static BlockDriverAIOCB *qemu_gluster_aio_rw(BlockDriverState *bs,
     }
 
     if (ret < 0) {
+        ret = -errno;
         goto out;
     }
-    return &acb->common;
+
+    qemu_coroutine_yield();
+    ret = acb->ret;
 
 out:
-    qemu_aio_release(acb);
-    return NULL;
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
 }
 
 static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
@@ -482,71 +488,68 @@ static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
     return 0;
 }
 
-static BlockDriverAIOCB *qemu_gluster_aio_readv(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
+static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
 {
-    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
+    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 0);
 }
 
-static BlockDriverAIOCB *qemu_gluster_aio_writev(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
+static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
 {
-    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
+    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1);
 }
 
-static BlockDriverAIOCB *qemu_gluster_aio_flush(BlockDriverState *bs,
-        BlockDriverCompletionFunc *cb, void *opaque)
+static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
 {
     int ret;
-    GlusterAIOCB *acb;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
     BDRVGlusterState *s = bs->opaque;
 
-    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
     acb->size = 0;
     acb->ret = 0;
-    acb->finished = NULL;
+    acb->coroutine = qemu_coroutine_self();
 
     ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
     if (ret < 0) {
+        ret = -errno;
         goto out;
     }
-    return &acb->common;
+
+    qemu_coroutine_yield();
+    ret = acb->ret;
 
 out:
-    qemu_aio_release(acb);
-    return NULL;
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
 }
 
 #ifdef CONFIG_GLUSTERFS_DISCARD
-static BlockDriverAIOCB *qemu_gluster_aio_discard(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, BlockDriverCompletionFunc *cb,
-        void *opaque)
+static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors)
 {
     int ret;
-    GlusterAIOCB *acb;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
     BDRVGlusterState *s = bs->opaque;
-    size_t size;
-    off_t offset;
+    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
+    off_t offset = sector_num * BDRV_SECTOR_SIZE;
 
-    offset = sector_num * BDRV_SECTOR_SIZE;
-    size = nb_sectors * BDRV_SECTOR_SIZE;
-
-    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
     acb->size = 0;
     acb->ret = 0;
-    acb->finished = NULL;
+    acb->coroutine = qemu_coroutine_self();
 
     ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
     if (ret < 0) {
+        ret = -errno;
         goto out;
     }
-    return &acb->common;
+
+    qemu_coroutine_yield();
+    ret = acb->ret;
 
 out:
-    qemu_aio_release(acb);
-    return NULL;
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
 }
 #endif
 
@@ -581,10 +584,6 @@ static void qemu_gluster_close(BlockDriverState *bs)
 {
     BDRVGlusterState *s = bs->opaque;
 
-    close(s->fds[GLUSTER_FD_READ]);
-    close(s->fds[GLUSTER_FD_WRITE]);
-    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL);
-
     if (s->fd) {
         glfs_close(s->fd);
         s->fd = NULL;
@@ -604,6 +603,11 @@ static QEMUOptionParameter qemu_gluster_create_options[] = {
         .type = OPT_SIZE,
         .help = "Virtual disk size"
     },
+    {
+        .name = BLOCK_OPT_PREALLOC,
+        .type = OPT_STRING,
+        .help = "Preallocation mode (allowed values: off, full)"
+    },
     { NULL }
 };
 
@@ -618,12 +622,15 @@ static BlockDriver bdrv_gluster = {
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
+    .bdrv_co_readv                = qemu_gluster_co_readv,
+    .bdrv_co_writev               = qemu_gluster_co_writev,
+    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
     .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_aio_discard             = qemu_gluster_aio_discard,
+    .bdrv_co_discard              = qemu_gluster_co_discard,
+#endif
+#ifdef CONFIG_GLUSTERFS_ZEROFILL
+    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
     .create_options               = qemu_gluster_create_options,
 };
@@ -639,12 +646,15 @@ static BlockDriver bdrv_gluster_tcp = {
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
+    .bdrv_co_readv                = qemu_gluster_co_readv,
+    .bdrv_co_writev               = qemu_gluster_co_writev,
+    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
     .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_aio_discard             = qemu_gluster_aio_discard,
+    .bdrv_co_discard              = qemu_gluster_co_discard,
+#endif
+#ifdef CONFIG_GLUSTERFS_ZEROFILL
+    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
     .create_options               = qemu_gluster_create_options,
 };
@@ -660,12 +670,15 @@ static BlockDriver bdrv_gluster_unix = {
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
+    .bdrv_co_readv                = qemu_gluster_co_readv,
+    .bdrv_co_writev               = qemu_gluster_co_writev,
+    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
     .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_aio_discard             = qemu_gluster_aio_discard,
+    .bdrv_co_discard              = qemu_gluster_co_discard,
+#endif
+#ifdef CONFIG_GLUSTERFS_ZEROFILL
+    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
     .create_options               = qemu_gluster_create_options,
 };
@@ -681,12 +694,15 @@ static BlockDriver bdrv_gluster_rdma = {
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
     .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
+    .bdrv_co_readv                = qemu_gluster_co_readv,
+    .bdrv_co_writev               = qemu_gluster_co_writev,
+    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
     .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_aio_discard             = qemu_gluster_aio_discard,
+    .bdrv_co_discard              = qemu_gluster_co_discard,
+#endif
+#ifdef CONFIG_GLUSTERFS_ZEROFILL
+    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
     .create_options               = qemu_gluster_create_options,
 };

block/iscsi.c

@@ -68,6 +68,7 @@ typedef struct IscsiTask {
     int do_retry;
     struct scsi_task *task;
     Coroutine *co;
+    QEMUBH *bh;
 } IscsiTask;
 
 typedef struct IscsiAIOCB {
@@ -123,6 +124,13 @@ iscsi_schedule_bh(IscsiAIOCB *acb)
     qemu_bh_schedule(acb->bh);
 }
 
+static void iscsi_co_generic_bh_cb(void *opaque)
+{
+    struct IscsiTask *iTask = opaque;
+    qemu_bh_delete(iTask->bh);
+    qemu_coroutine_enter(iTask->co, NULL);
+}
+
 static void
 iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                         void *command_data, void *opaque)
@@ -147,7 +155,8 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
 
 out:
     if (iTask->co) {
-        qemu_coroutine_enter(iTask->co, NULL);
+        iTask->bh = qemu_bh_new(iscsi_co_generic_bh_cb, iTask);
+        qemu_bh_schedule(iTask->bh);
     }
 }
 
@@ -299,7 +308,7 @@ retry:
                                     iscsi_co_generic_cb, &iTask);
     if (iTask.task == NULL) {
         g_free(buf);
-        return -EIO;
+        return -ENOMEM;
     }
 #if defined(LIBISCSI_FEATURE_IOVECTOR)
     scsi_task_set_iov_out(iTask.task, (struct scsi_iovec *) iov->iov,
@@ -359,12 +368,15 @@ retry:
     default:
         iTask.task = iscsi_read10_task(iscsilun->iscsi, iscsilun->lun, lba,
                                        num_sectors * iscsilun->block_size,
-                                       iscsilun->block_size, 0, 0, 0, 0, 0,
+                                       iscsilun->block_size,
+#if !defined(CONFIG_LIBISCSI_1_4) /* API change from 1.4.0 to 1.5.0 */
+                                       0, 0, 0, 0, 0,
+#endif
                                        iscsi_co_generic_cb, &iTask);
         break;
     }
     if (iTask.task == NULL) {
-        return -EIO;
+        return -ENOMEM;
     }
 #if defined(LIBISCSI_FEATURE_IOVECTOR)
     scsi_task_set_iov_in(iTask.task, (struct scsi_iovec *) iov->iov, iov->niov);
@@ -407,7 +419,7 @@ static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
 retry:
     if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
                                       0, iscsi_co_generic_cb, &iTask) == NULL) {
-        return -EIO;
+        return -ENOMEM;
     }
 
     while (!iTask.complete) {
@@ -657,7 +669,7 @@ retry:
                                   sector_qemu2lun(sector_num, iscsilun),
                                   8 + 16, iscsi_co_generic_cb,
                                   &iTask) == NULL) {
-        ret = -EIO;
+        ret = -ENOMEM;
         goto out;
     }
 
@@ -741,7 +753,7 @@ coroutine_fn iscsi_co_discard(BlockDriverState *bs, int64_t sector_num,
 retry:
     if (iscsi_unmap_task(iscsilun->iscsi, iscsilun->lun, 0, 0, &list, 1,
                      iscsi_co_generic_cb, &iTask) == NULL) {
-        return -EIO;
+        return -ENOMEM;
     }
 
     while (!iTask.complete) {
@@ -810,7 +822,7 @@ retry:
                                iscsilun->zeroblock, iscsilun->block_size,
                                nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
                                0, 0, iscsi_co_generic_cb, &iTask) == NULL) {
-        return -EIO;
+        return -ENOMEM;
     }
 
     while (!iTask.complete) {
@@ -1109,7 +1121,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         qerror_report_err(local_err);
@@ -1205,6 +1217,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
         goto out;
     }
     bs->total_sectors = sector_lun2qemu(iscsilun->num_blocks, iscsilun);
+    bs->request_alignment = iscsilun->block_size;
 
     /* Medium changer or tape. We dont have any emulation for this so this must
      * be sg ioctl compatible. We force it to be sg, otherwise qemu will try
@@ -1253,23 +1266,6 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
                sizeof(struct scsi_inquiry_block_limits));
         scsi_free_scsi_task(task);
         task = NULL;
-
-        if (iscsilun->bl.max_unmap < 0xffffffff) {
-            bs->bl.max_discard = sector_lun2qemu(iscsilun->bl.max_unmap,
-                                                 iscsilun);
-        }
-        bs->bl.discard_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
-                                                   iscsilun);
-
-        if (iscsilun->bl.max_ws_len < 0xffffffff) {
-            bs->bl.max_write_zeroes = sector_lun2qemu(iscsilun->bl.max_ws_len,
-                                                      iscsilun);
-        }
-        bs->bl.write_zeroes_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
-                                                        iscsilun);
-
-        bs->bl.opt_transfer_length = sector_lun2qemu(iscsilun->bl.opt_xfer_len,
-                                                     iscsilun);
     }
 
 #if defined(LIBISCSI_FEATURE_NOP_COUNTER)
@@ -1314,6 +1310,40 @@ static void iscsi_close(BlockDriverState *bs)
     memset(iscsilun, 0, sizeof(IscsiLun));
 }
 
+static int iscsi_refresh_limits(BlockDriverState *bs)
+{
+    IscsiLun *iscsilun = bs->opaque;
+
+    /* We don't actually refresh here, but just return data queried in
+     * iscsi_open(): iscsi targets don't change their limits. */
+    if (iscsilun->lbp.lbpu || iscsilun->lbp.lbpws) {
+        if (iscsilun->bl.max_unmap < 0xffffffff) {
+            bs->bl.max_discard = sector_lun2qemu(iscsilun->bl.max_unmap,
+                                                 iscsilun);
+        }
+        bs->bl.discard_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
+                                                   iscsilun);
+
+        if (iscsilun->bl.max_ws_len < 0xffffffff) {
+            bs->bl.max_write_zeroes = sector_lun2qemu(iscsilun->bl.max_ws_len,
+                                                      iscsilun);
+        }
+        bs->bl.write_zeroes_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
+                                                        iscsilun);
+    }
+    bs->bl.opt_transfer_length = sector_lun2qemu(iscsilun->bl.opt_xfer_len,
+                                                 iscsilun);
+    return 0;
+}
+
+/* We have nothing to do for iSCSI reopen, stub just returns
+ * success */
+static int iscsi_reopen_prepare(BDRVReopenState *state,
+                                BlockReopenQueue *queue, Error **errp)
+{
+    return 0;
+}
+
 static int iscsi_truncate(BlockDriverState *bs, int64_t offset)
 {
     IscsiLun *iscsilun = bs->opaque;
@@ -1422,10 +1452,12 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_close      = iscsi_close,
     .bdrv_create     = iscsi_create,
     .create_options  = iscsi_create_options,
+    .bdrv_reopen_prepare  = iscsi_reopen_prepare,
 
     .bdrv_getlength  = iscsi_getlength,
     .bdrv_get_info   = iscsi_get_info,
     .bdrv_truncate   = iscsi_truncate,
+    .bdrv_refresh_limits = iscsi_refresh_limits,
 
 #if defined(LIBISCSI_FEATURE_IOVECTOR)
     .bdrv_co_get_block_status = iscsi_co_get_block_status,

block/mirror.c

@@ -31,7 +31,8 @@ typedef struct MirrorBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *target;
-    MirrorSyncMode mode;
+    BlockDriverState *base;
+    bool is_none_mode;
     BlockdevOnError on_source_error, on_target_error;
     bool synced;
     bool should_complete;
@@ -95,6 +96,7 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
         bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
     }
 
+    qemu_iovec_destroy(&op->qiov);
     g_slice_free(MirrorOp, op);
     qemu_coroutine_enter(s->common.co, NULL);
 }
@@ -335,10 +337,9 @@ static void coroutine_fn mirror_run(void *opaque)
     sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
     mirror_free_init(s);
 
-    if (s->mode != MIRROR_SYNC_MODE_NONE) {
+    if (!s->is_none_mode) {
         /* First part, loop on the sectors and initialize the dirty bitmap.  */
-        BlockDriverState *base;
-        base = s->mode == MIRROR_SYNC_MODE_FULL ? NULL : bs->backing_hd;
+        BlockDriverState *base = s->base;
         for (sector_num = 0; sector_num < end; ) {
             int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
             ret = bdrv_is_allocated_above(bs, base,
@@ -481,8 +482,14 @@ immediate_exit:
             bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
         }
         bdrv_swap(s->target, s->common.bs);
+        if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
+            /* drop the bs loop chain formed by the swap: break the loop then
+             * trigger the unref from the top one */
+            BlockDriverState *p = s->base->backing_hd;
+            s->base->backing_hd = NULL;
+            bdrv_unref(p);
+        }
     }
-    bdrv_close(s->target);
     bdrv_unref(s->target);
     block_job_completed(&s->common, ret);
 }
@@ -536,12 +543,24 @@ static const BlockJobDriver mirror_job_driver = {
     .complete      = mirror_complete,
 };
 
-void mirror_start(BlockDriverState *bs, BlockDriverState *target,
-                  int64_t speed, int64_t granularity, int64_t buf_size,
-                  MirrorSyncMode mode, BlockdevOnError on_source_error,
+static const BlockJobDriver commit_active_job_driver = {
+    .instance_size = sizeof(MirrorBlockJob),
+    .job_type      = BLOCK_JOB_TYPE_COMMIT,
+    .set_speed     = mirror_set_speed,
+    .iostatus_reset
+                   = mirror_iostatus_reset,
+    .complete      = mirror_complete,
+};
+
+static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
+                            int64_t speed, int64_t granularity,
+                            int64_t buf_size,
+                            BlockdevOnError on_source_error,
                             BlockdevOnError on_target_error,
                             BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp)
+                            void *opaque, Error **errp,
+                            const BlockJobDriver *driver,
+                            bool is_none_mode, BlockDriverState *base)
 {
     MirrorBlockJob *s;
 
@@ -566,7 +585,8 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
         return;
     }
 
-    s = block_job_create(&mirror_job_driver, bs, speed, cb, opaque, errp);
+
+    s = block_job_create(driver, bs, speed, cb, opaque, errp);
     if (!s) {
         return;
     }
@@ -574,7 +594,8 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
     s->on_source_error = on_source_error;
     s->on_target_error = on_target_error;
     s->target = target;
-    s->mode = mode;
+    s->is_none_mode = is_none_mode;
+    s->base = base;
     s->granularity = granularity;
     s->buf_size = MAX(buf_size, granularity);
 
@@ -586,3 +607,73 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
     trace_mirror_start(bs, s, s->common.co, opaque);
     qemu_coroutine_enter(s->common.co, s);
 }
+
+void mirror_start(BlockDriverState *bs, BlockDriverState *target,
+                  int64_t speed, int64_t granularity, int64_t buf_size,
+                  MirrorSyncMode mode, BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
+                  BlockDriverCompletionFunc *cb,
+                  void *opaque, Error **errp)
+{
+    bool is_none_mode;
+    BlockDriverState *base;
+
+    is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
+    base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
+    mirror_start_job(bs, target, speed, granularity, buf_size,
+                     on_source_error, on_target_error, cb, opaque, errp,
+                     &mirror_job_driver, is_none_mode, base);
+}
+
+void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
+                         int64_t speed,
+                         BlockdevOnError on_error,
+                         BlockDriverCompletionFunc *cb,
+                         void *opaque, Error **errp)
+{
+    int64_t length, base_length;
+    int orig_base_flags;
+
+    orig_base_flags = bdrv_get_flags(base);
+
+    if (bdrv_reopen(base, bs->open_flags, errp)) {
+        return;
+    }
+
+    length = bdrv_getlength(bs);
+    if (length < 0) {
+        error_setg(errp, "Unable to determine length of %s", bs->filename);
+        goto error_restore_flags;
+    }
+
+    base_length = bdrv_getlength(base);
+    if (base_length < 0) {
+        error_setg(errp, "Unable to determine length of %s", base->filename);
+        goto error_restore_flags;
+    }
+
+    if (length > base_length) {
+        if (bdrv_truncate(base, length) < 0) {
+            error_setg(errp, "Top image %s is larger than base image %s, and "
+                             "resize of base image failed",
+                             bs->filename, base->filename);
+            goto error_restore_flags;
+        }
+    }
+
+    bdrv_ref(base);
+    mirror_start_job(bs, base, speed, 0, 0,
+                     on_error, on_error, cb, opaque, errp,
+                     &commit_active_job_driver, false, base);
+    if (error_is_set(errp)) {
+        goto error_restore_flags;
+    }
+
+    return;
+
+error_restore_flags:
+    /* ignore error and errp for bdrv_reopen, because we want to propagate
+     * the original error */
+    bdrv_reopen(base, orig_base_flags, NULL);
+    return;
+}

block/nbd.c

@@ -205,7 +205,8 @@ static int nbd_config(BDRVNBDState *s, QDict *options, char **export)
         return -EINVAL;
     }
 
-    s->socket_opts = qemu_opts_create_nofail(&socket_optslist);
+    s->socket_opts = qemu_opts_create(&socket_optslist, NULL, 0,
+                                      &error_abort);
 
     qemu_opts_absorb_qdict(s->socket_opts, options, &local_err);
     if (error_is_set(&local_err)) {

block/nfs.c

@@ -0,0 +1,439 @@
+/*
+ * QEMU Block driver for native access to files on NFS shares
+ *
+ * Copyright (c) 2014 Peter Lieven <pl@kamp.de>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "config-host.h"
+
+#include <poll.h>
+#include "qemu-common.h"
+#include "qemu/config-file.h"
+#include "qemu/error-report.h"
+#include "block/block_int.h"
+#include "trace.h"
+#include "qemu/iov.h"
+#include "qemu/uri.h"
+#include "sysemu/sysemu.h"
+#include <nfsc/libnfs.h>
+
+typedef struct NFSClient {
+    struct nfs_context *context;
+    struct nfsfh *fh;
+    int events;
+    bool has_zero_init;
+} NFSClient;
+
+typedef struct NFSRPC {
+    int ret;
+    int complete;
+    QEMUIOVector *iov;
+    struct stat *st;
+    Coroutine *co;
+    QEMUBH *bh;
+} NFSRPC;
+
+static void nfs_process_read(void *arg);
+static void nfs_process_write(void *arg);
+
+static void nfs_set_events(NFSClient *client)
+{
+    int ev = nfs_which_events(client->context);
+    if (ev != client->events) {
+        qemu_aio_set_fd_handler(nfs_get_fd(client->context),
+                      (ev & POLLIN) ? nfs_process_read : NULL,
+                      (ev & POLLOUT) ? nfs_process_write : NULL,
+                      client);
+
+    }
+    client->events = ev;
+}
+
+static void nfs_process_read(void *arg)
+{
+    NFSClient *client = arg;
+    nfs_service(client->context, POLLIN);
+    nfs_set_events(client);
+}
+
+static void nfs_process_write(void *arg)
+{
+    NFSClient *client = arg;
+    nfs_service(client->context, POLLOUT);
+    nfs_set_events(client);
+}
+
+static void nfs_co_init_task(NFSClient *client, NFSRPC *task)
+{
+    *task = (NFSRPC) {
+        .co         = qemu_coroutine_self(),
+    };
+}
+
+static void nfs_co_generic_bh_cb(void *opaque)
+{
+    NFSRPC *task = opaque;
+    qemu_bh_delete(task->bh);
+    qemu_coroutine_enter(task->co, NULL);
+}
+
+static void
+nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
+                  void *private_data)
+{
+    NFSRPC *task = private_data;
+    task->complete = 1;
+    task->ret = ret;
+    if (task->ret > 0 && task->iov) {
+        if (task->ret <= task->iov->size) {
+            qemu_iovec_from_buf(task->iov, 0, data, task->ret);
+        } else {
+            task->ret = -EIO;
+        }
+    }
+    if (task->ret == 0 && task->st) {
+        memcpy(task->st, data, sizeof(struct stat));
+    }
+    if (task->co) {
+        task->bh = qemu_bh_new(nfs_co_generic_bh_cb, task);
+        qemu_bh_schedule(task->bh);
+    }
+}
+
+static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
+                                     int64_t sector_num, int nb_sectors,
+                                     QEMUIOVector *iov)
+{
+    NFSClient *client = bs->opaque;
+    NFSRPC task;
+
+    nfs_co_init_task(client, &task);
+    task.iov = iov;
+
+    if (nfs_pread_async(client->context, client->fh,
+                        sector_num * BDRV_SECTOR_SIZE,
+                        nb_sectors * BDRV_SECTOR_SIZE,
+                        nfs_co_generic_cb, &task) != 0) {
+        return -ENOMEM;
+    }
+
+    while (!task.complete) {
+        nfs_set_events(client);
+        qemu_coroutine_yield();
+    }
+
+    if (task.ret < 0) {
+        return task.ret;
+    }
+
+    /* zero pad short reads */
+    if (task.ret < iov->size) {
+        qemu_iovec_memset(iov, task.ret, 0, iov->size - task.ret);
+    }
+
+    return 0;
+}
+
+static int coroutine_fn nfs_co_writev(BlockDriverState *bs,
+                                        int64_t sector_num, int nb_sectors,
+                                        QEMUIOVector *iov)
+{
+    NFSClient *client = bs->opaque;
+    NFSRPC task;
+    char *buf = NULL;
+
+    nfs_co_init_task(client, &task);
+
+    buf = g_malloc(nb_sectors * BDRV_SECTOR_SIZE);
+    qemu_iovec_to_buf(iov, 0, buf, nb_sectors * BDRV_SECTOR_SIZE);
+
+    if (nfs_pwrite_async(client->context, client->fh,
+                         sector_num * BDRV_SECTOR_SIZE,
+                         nb_sectors * BDRV_SECTOR_SIZE,
+                         buf, nfs_co_generic_cb, &task) != 0) {
+        g_free(buf);
+        return -ENOMEM;
+    }
+
+    while (!task.complete) {
+        nfs_set_events(client);
+        qemu_coroutine_yield();
+    }
+
+    g_free(buf);
+
+    if (task.ret != nb_sectors * BDRV_SECTOR_SIZE) {
+        return task.ret < 0 ? task.ret : -EIO;
+    }
+
+    return 0;
+}
+
+static int coroutine_fn nfs_co_flush(BlockDriverState *bs)
+{
+    NFSClient *client = bs->opaque;
+    NFSRPC task;
+
+    nfs_co_init_task(client, &task);
+
+    if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
+                        &task) != 0) {
+        return -ENOMEM;
+    }
+
+    while (!task.complete) {
+        nfs_set_events(client);
+        qemu_coroutine_yield();
+    }
+
+    return task.ret;
+}
+
+/* TODO Convert to fine grained options */
+static QemuOptsList runtime_opts = {
+    .name = "nfs",
+    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+    .desc = {
+        {
+            .name = "filename",
+            .type = QEMU_OPT_STRING,
+            .help = "URL to the NFS file",
+        },
+        { /* end of list */ }
+    },
+};
+
+static void nfs_client_close(NFSClient *client)
+{
+    if (client->context) {
+        if (client->fh) {
+            nfs_close(client->context, client->fh);
+        }
+        qemu_aio_set_fd_handler(nfs_get_fd(client->context), NULL, NULL, NULL);
+        nfs_destroy_context(client->context);
+    }
+    memset(client, 0, sizeof(NFSClient));
+}
+
+static void nfs_file_close(BlockDriverState *bs)
+{
+    NFSClient *client = bs->opaque;
+    nfs_client_close(client);
+}
+
+static int64_t nfs_client_open(NFSClient *client, const char *filename,
+                               int flags, Error **errp)
+{
+    int ret = -EINVAL, i;
+    struct stat st;
+    URI *uri;
+    QueryParams *qp = NULL;
+    char *file = NULL, *strp = NULL;
+
+    uri = uri_parse(filename);
+    if (!uri) {
+        error_setg(errp, "Invalid URL specified");
+        goto fail;
+    }
+    strp = strrchr(uri->path, '/');
+    if (strp == NULL) {
+        error_setg(errp, "Invalid URL specified");
+        goto fail;
+    }
+    file = g_strdup(strp);
+    *strp = 0;
+
+    client->context = nfs_init_context();
+    if (client->context == NULL) {
+        error_setg(errp, "Failed to init NFS context");
+        goto fail;
+    }
+
+    qp = query_params_parse(uri->query);
+    for (i = 0; i < qp->n; i++) {
+        if (!qp->p[i].value) {
+            error_setg(errp, "Value for NFS parameter expected: %s",
+                       qp->p[i].name);
+            goto fail;
+        }
+        if (!strncmp(qp->p[i].name, "uid", 3)) {
+            nfs_set_uid(client->context, atoi(qp->p[i].value));
+        } else if (!strncmp(qp->p[i].name, "gid", 3)) {
+            nfs_set_gid(client->context, atoi(qp->p[i].value));
+        } else if (!strncmp(qp->p[i].name, "tcp-syncnt", 10)) {
+            nfs_set_tcp_syncnt(client->context, atoi(qp->p[i].value));
+        } else {
+            error_setg(errp, "Unknown NFS parameter name: %s",
+                       qp->p[i].name);
+            goto fail;
+        }
+    }
+
+    ret = nfs_mount(client->context, uri->server, uri->path);
+    if (ret < 0) {
+        error_setg(errp, "Failed to mount nfs share: %s",
+                   nfs_get_error(client->context));
+        goto fail;
+    }
+
+    if (flags & O_CREAT) {
+        ret = nfs_creat(client->context, file, 0600, &client->fh);
+        if (ret < 0) {
+            error_setg(errp, "Failed to create file: %s",
+                       nfs_get_error(client->context));
+            goto fail;
+        }
+    } else {
+        ret = nfs_open(client->context, file, flags, &client->fh);
+        if (ret < 0) {
+            error_setg(errp, "Failed to open file : %s",
+                       nfs_get_error(client->context));
+            goto fail;
+        }
+    }
+
+    ret = nfs_fstat(client->context, client->fh, &st);
+    if (ret < 0) {
+        error_setg(errp, "Failed to fstat file: %s",
+                   nfs_get_error(client->context));
+        goto fail;
+    }
+
+    ret = DIV_ROUND_UP(st.st_size, BDRV_SECTOR_SIZE);
+    client->has_zero_init = S_ISREG(st.st_mode);
+    goto out;
+fail:
+    nfs_client_close(client);
+out:
+    if (qp) {
+        query_params_free(qp);
+    }
+    uri_free(uri);
+    g_free(file);
+    return ret;
+}
+
+static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
+                         Error **errp) {
+    NFSClient *client = bs->opaque;
+    int64_t ret;
+    QemuOpts *opts;
+    Error *local_err = NULL;
+
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (error_is_set(&local_err)) {
+        error_propagate(errp, local_err);
+        return -EINVAL;
+    }
+    ret = nfs_client_open(client, qemu_opt_get(opts, "filename"),
+                          (flags & BDRV_O_RDWR) ? O_RDWR : O_RDONLY,
+                          errp);
+    if (ret < 0) {
+        return ret;
+    }
+    bs->total_sectors = ret;
+    return 0;
+}
+
+static int nfs_file_create(const char *url, QEMUOptionParameter *options,
+                           Error **errp)
+{
+    int ret = 0;
+    int64_t total_size = 0;
+    NFSClient *client = g_malloc0(sizeof(NFSClient));
+
+    /* Read out options */
+    while (options && options->name) {
+        if (!strcmp(options->name, "size")) {
+            total_size = options->value.n;
+        }
+        options++;
+    }
+
+    ret = nfs_client_open(client, url, O_CREAT, errp);
+    if (ret < 0) {
+        goto out;
+    }
+    ret = nfs_ftruncate(client->context, client->fh, total_size);
+    nfs_client_close(client);
+out:
+    g_free(client);
+    return ret;
+}
+
+static int nfs_has_zero_init(BlockDriverState *bs)
+{
+    NFSClient *client = bs->opaque;
+    return client->has_zero_init;
+}
+
+static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
+{
+    NFSClient *client = bs->opaque;
+    NFSRPC task = {0};
+    struct stat st;
+
+    task.st = &st;
+    if (nfs_fstat_async(client->context, client->fh, nfs_co_generic_cb,
+                        &task) != 0) {
+        return -ENOMEM;
+    }
+
+    while (!task.complete) {
+        nfs_set_events(client);
+        qemu_aio_wait();
+    }
+
+    return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
+}
+
+static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
+{
+    NFSClient *client = bs->opaque;
+    return nfs_ftruncate(client->context, client->fh, offset);
+}
+
+static BlockDriver bdrv_nfs = {
+    .format_name     = "nfs",
+    .protocol_name   = "nfs",
+
+    .instance_size   = sizeof(NFSClient),
+    .bdrv_needs_filename = true,
+    .bdrv_has_zero_init = nfs_has_zero_init,
+    .bdrv_get_allocated_file_size = nfs_get_allocated_file_size,
+    .bdrv_truncate = nfs_file_truncate,
+
+    .bdrv_file_open  = nfs_file_open,
+    .bdrv_close      = nfs_file_close,
+    .bdrv_create     = nfs_file_create,
+
+    .bdrv_co_readv         = nfs_co_readv,
+    .bdrv_co_writev        = nfs_co_writev,
+    .bdrv_co_flush_to_disk = nfs_co_flush,
+};
+
+static void nfs_block_init(void)
+{
+    bdrv_register(&bdrv_nfs);
+}
+
+block_init(nfs_block_init);

block/qapi.c

@@ -29,6 +29,60 @@
 #include "qapi/qmp-output-visitor.h"
 #include "qapi/qmp/types.h"
 
+BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
+{
+    BlockDeviceInfo *info = g_malloc0(sizeof(*info));
+
+    info->file                   = g_strdup(bs->filename);
+    info->ro                     = bs->read_only;
+    info->drv                    = g_strdup(bs->drv->format_name);
+    info->encrypted              = bs->encrypted;
+    info->encryption_key_missing = bdrv_key_required(bs);
+
+    if (bs->node_name[0]) {
+        info->has_node_name = true;
+        info->node_name = g_strdup(bs->node_name);
+    }
+
+    if (bs->backing_file[0]) {
+        info->has_backing_file = true;
+        info->backing_file = g_strdup(bs->backing_file);
+    }
+
+    info->backing_file_depth = bdrv_get_backing_file_depth(bs);
+
+    if (bs->io_limits_enabled) {
+        ThrottleConfig cfg;
+        throttle_get_config(&bs->throttle_state, &cfg);
+        info->bps     = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
+        info->bps_rd  = cfg.buckets[THROTTLE_BPS_READ].avg;
+        info->bps_wr  = cfg.buckets[THROTTLE_BPS_WRITE].avg;
+
+        info->iops    = cfg.buckets[THROTTLE_OPS_TOTAL].avg;
+        info->iops_rd = cfg.buckets[THROTTLE_OPS_READ].avg;
+        info->iops_wr = cfg.buckets[THROTTLE_OPS_WRITE].avg;
+
+        info->has_bps_max     = cfg.buckets[THROTTLE_BPS_TOTAL].max;
+        info->bps_max         = cfg.buckets[THROTTLE_BPS_TOTAL].max;
+        info->has_bps_rd_max  = cfg.buckets[THROTTLE_BPS_READ].max;
+        info->bps_rd_max      = cfg.buckets[THROTTLE_BPS_READ].max;
+        info->has_bps_wr_max  = cfg.buckets[THROTTLE_BPS_WRITE].max;
+        info->bps_wr_max      = cfg.buckets[THROTTLE_BPS_WRITE].max;
+
+        info->has_iops_max    = cfg.buckets[THROTTLE_OPS_TOTAL].max;
+        info->iops_max        = cfg.buckets[THROTTLE_OPS_TOTAL].max;
+        info->has_iops_rd_max = cfg.buckets[THROTTLE_OPS_READ].max;
+        info->iops_rd_max     = cfg.buckets[THROTTLE_OPS_READ].max;
+        info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
+        info->iops_wr_max     = cfg.buckets[THROTTLE_OPS_WRITE].max;
+
+        info->has_iops_size = cfg.op_size;
+        info->iops_size = cfg.op_size;
+    }
+
+    return info;
+}
+
 /*
  * Returns 0 on success, with *p_list either set to describe snapshot
  * information, or NULL because there are no snapshots.  Returns -errno on
@@ -211,60 +265,7 @@ void bdrv_query_info(BlockDriverState *bs,
 
     if (bs->drv) {
         info->has_inserted = true;
-        info->inserted = g_malloc0(sizeof(*info->inserted));
-        info->inserted->file = g_strdup(bs->filename);
-        info->inserted->ro = bs->read_only;
-        info->inserted->drv = g_strdup(bs->drv->format_name);
-        info->inserted->encrypted = bs->encrypted;
-        info->inserted->encryption_key_missing = bdrv_key_required(bs);
-
-        if (bs->backing_file[0]) {
-            info->inserted->has_backing_file = true;
-            info->inserted->backing_file = g_strdup(bs->backing_file);
-        }
-
-        info->inserted->backing_file_depth = bdrv_get_backing_file_depth(bs);
-
-        if (bs->io_limits_enabled) {
-            ThrottleConfig cfg;
-            throttle_get_config(&bs->throttle_state, &cfg);
-            info->inserted->bps     = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
-            info->inserted->bps_rd  = cfg.buckets[THROTTLE_BPS_READ].avg;
-            info->inserted->bps_wr  = cfg.buckets[THROTTLE_BPS_WRITE].avg;
-
-            info->inserted->iops    = cfg.buckets[THROTTLE_OPS_TOTAL].avg;
-            info->inserted->iops_rd = cfg.buckets[THROTTLE_OPS_READ].avg;
-            info->inserted->iops_wr = cfg.buckets[THROTTLE_OPS_WRITE].avg;
-
-            info->inserted->has_bps_max     =
-                cfg.buckets[THROTTLE_BPS_TOTAL].max;
-            info->inserted->bps_max         =
-                cfg.buckets[THROTTLE_BPS_TOTAL].max;
-            info->inserted->has_bps_rd_max  =
-                cfg.buckets[THROTTLE_BPS_READ].max;
-            info->inserted->bps_rd_max      =
-                cfg.buckets[THROTTLE_BPS_READ].max;
-            info->inserted->has_bps_wr_max  =
-                cfg.buckets[THROTTLE_BPS_WRITE].max;
-            info->inserted->bps_wr_max      =
-                cfg.buckets[THROTTLE_BPS_WRITE].max;
-
-            info->inserted->has_iops_max    =
-                cfg.buckets[THROTTLE_OPS_TOTAL].max;
-            info->inserted->iops_max        =
-                cfg.buckets[THROTTLE_OPS_TOTAL].max;
-            info->inserted->has_iops_rd_max =
-                cfg.buckets[THROTTLE_OPS_READ].max;
-            info->inserted->iops_rd_max     =
-                cfg.buckets[THROTTLE_OPS_READ].max;
-            info->inserted->has_iops_wr_max =
-                cfg.buckets[THROTTLE_OPS_WRITE].max;
-            info->inserted->iops_wr_max     =
-                cfg.buckets[THROTTLE_OPS_WRITE].max;
-
-            info->inserted->has_iops_size = cfg.op_size;
-            info->inserted->iops_size = cfg.op_size;
-        }
+        info->inserted = bdrv_block_device_info(bs);
 
         bs0 = bs;
         p_image_info = &info->inserted->image;
@@ -318,6 +319,11 @@ BlockStats *bdrv_query_stats(const BlockDriverState *bs)
         s->parent = bdrv_query_stats(bs->file);
     }
 
+    if (bs->backing_hd) {
+        s->has_backing = true;
+        s->backing = bdrv_query_stats(bs->backing_hd);
+    }
+
     return s;
 }
 

block/qcow.c

@@ -691,7 +691,8 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options,
         return ret;
     }
 
-    ret = bdrv_file_open(&qcow_bs, filename, NULL, BDRV_O_RDWR, &local_err);
+    ret = bdrv_file_open(&qcow_bs, filename, NULL, NULL, BDRV_O_RDWR,
+                         &local_err);
     if (ret < 0) {
         qerror_report_err(local_err);
         error_free(local_err);

block/qcow2-cluster.c

@@ -1182,7 +1182,7 @@ fail:
  * Return 0 on success and -errno in error cases
  */
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m)
+    int *num, uint64_t *host_offset, QCowL2Meta **m)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t start, remaining;
@@ -1190,15 +1190,13 @@ int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
     uint64_t cur_bytes;
     int ret;
 
-    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset,
-                                      n_start, n_end);
+    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset, *num);
 
-    assert(n_start * BDRV_SECTOR_SIZE == offset_into_cluster(s, offset));
-    offset = start_of_cluster(s, offset);
+    assert((offset & ~BDRV_SECTOR_MASK) == 0);
 
 again:
-    start = offset + (n_start << BDRV_SECTOR_BITS);
-    remaining = (n_end - n_start) << BDRV_SECTOR_BITS;
+    start = offset;
+    remaining = *num << BDRV_SECTOR_BITS;
     cluster_offset = 0;
     *host_offset = 0;
     cur_bytes = 0;
@@ -1284,7 +1282,7 @@ again:
         }
     }
 
-    *num = (n_end - n_start) - (remaining >> BDRV_SECTOR_BITS);
+    *num -= remaining >> BDRV_SECTOR_BITS;
     assert(*num > 0);
     assert(*host_offset != 0);
 

block/qcow2-refcount.c

@@ -676,7 +676,13 @@ int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
     BDRVQcowState *s = bs->opaque;
     uint64_t cluster_index;
     uint64_t old_free_cluster_index;
-    int i, refcount, ret;
+    uint64_t i;
+    int refcount, ret;
+
+    assert(nb_clusters >= 0);
+    if (nb_clusters == 0) {
+        return 0;
+    }
 
     /* Check how many clusters there are free */
     cluster_index = offset >> s->cluster_bits;

block/qcow2.c

@@ -669,7 +669,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* Enable lazy_refcounts according to image and command line options */
-    opts = qemu_opts_create_nofail(&qcow2_runtime_opts);
+    opts = qemu_opts_create(&qcow2_runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
@@ -718,7 +718,6 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     qemu_opts_del(opts);
-    bs->bl.write_zeroes_alignment = s->cluster_sectors;
 
     if (s->use_lazy_refcounts && s->qcow_version < 3) {
         error_setg(errp, "Lazy refcounts require a qcow2 image with at least "
@@ -751,6 +750,15 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     return ret;
 }
 
+static int qcow2_refresh_limits(BlockDriverState *bs)
+{
+    BDRVQcowState *s = bs->opaque;
+
+    bs->bl.write_zeroes_alignment = s->cluster_sectors;
+
+    return 0;
+}
+
 static int qcow2_set_key(BlockDriverState *bs, const char *key)
 {
     BDRVQcowState *s = bs->opaque;
@@ -992,7 +1000,6 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
 {
     BDRVQcowState *s = bs->opaque;
     int index_in_cluster;
-    int n_end;
     int ret;
     int cur_nr_sectors; /* number of sectors in current iteration */
     uint64_t cluster_offset;
@@ -1016,14 +1023,16 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
 
         trace_qcow2_writev_start_part(qemu_coroutine_self());
         index_in_cluster = sector_num & (s->cluster_sectors - 1);
-        n_end = index_in_cluster + remaining_sectors;
+        cur_nr_sectors = remaining_sectors;
         if (s->crypt_method &&
-            n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors) {
-            n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
+            cur_nr_sectors >
+            QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors - index_in_cluster) {
+            cur_nr_sectors =
+                QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors - index_in_cluster;
         }
 
         ret = qcow2_alloc_cluster_offset(bs, sector_num << 9,
-            index_in_cluster, n_end, &cur_nr_sectors, &cluster_offset, &l2meta);
+            &cur_nr_sectors, &cluster_offset, &l2meta);
         if (ret < 0) {
             goto fail;
         }
@@ -1395,34 +1404,34 @@ static int preallocate(BlockDriverState *bs)
     int ret;
     QCowL2Meta *meta;
 
-    nb_sectors = bdrv_getlength(bs) >> 9;
+    nb_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
     offset = 0;
 
     while (nb_sectors) {
-        num = MIN(nb_sectors, INT_MAX >> 9);
-        ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num,
+        num = MIN(nb_sectors, INT_MAX >> BDRV_SECTOR_BITS);
+        ret = qcow2_alloc_cluster_offset(bs, offset, &num,
                                          &host_offset, &meta);
         if (ret < 0) {
             return ret;
         }
 
+        if (meta != NULL) {
             ret = qcow2_alloc_cluster_link_l2(bs, meta);
             if (ret < 0) {
-            qcow2_free_any_clusters(bs, meta->alloc_offset, meta->nb_clusters,
-                                    QCOW2_DISCARD_NEVER);
+                qcow2_free_any_clusters(bs, meta->alloc_offset,
+                                        meta->nb_clusters, QCOW2_DISCARD_NEVER);
                 return ret;
             }
 
-        /* There are no dependent requests, but we need to remove our request
-         * from the list of in-flight requests */
-        if (meta != NULL) {
+            /* There are no dependent requests, but we need to remove our
+             * request from the list of in-flight requests */
             QLIST_REMOVE(meta, next_in_flight);
         }
 
         /* TODO Preallocate data if requested */
 
         nb_sectors -= num;
-        offset += num << 9;
+        offset += num << BDRV_SECTOR_BITS;
     }
 
     /*
@@ -1431,9 +1440,10 @@ static int preallocate(BlockDriverState *bs)
      * EOF). Extend the image to the last allocated sector.
      */
     if (host_offset != 0) {
-        uint8_t buf[512];
-        memset(buf, 0, 512);
-        ret = bdrv_write(bs->file, (host_offset >> 9) + num - 1, buf, 1);
+        uint8_t buf[BDRV_SECTOR_SIZE];
+        memset(buf, 0, BDRV_SECTOR_SIZE);
+        ret = bdrv_write(bs->file, (host_offset >> BDRV_SECTOR_BITS) + num - 1,
+                         buf, 1);
         if (ret < 0) {
             return ret;
         }
@@ -1483,7 +1493,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         return ret;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR, &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         return ret;
@@ -1681,26 +1691,6 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options,
     return ret;
 }
 
-static int qcow2_make_empty(BlockDriverState *bs)
-{
-#if 0
-    /* XXX: not correct */
-    BDRVQcowState *s = bs->opaque;
-    uint32_t l1_length = s->l1_size * sizeof(uint64_t);
-    int ret;
-
-    memset(s->l1_table, 0, l1_length);
-    if (bdrv_pwrite(bs->file, s->l1_table_offset, s->l1_table, l1_length) < 0)
-        return -1;
-    ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
-    if (ret < 0)
-        return ret;
-
-    l2_cache_reset(bs);
-#endif
-    return 0;
-}
-
 static coroutine_fn int qcow2_co_write_zeroes(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
 {
@@ -2244,7 +2234,6 @@ static BlockDriver bdrv_qcow2 = {
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = qcow2_co_get_block_status,
     .bdrv_set_key       = qcow2_set_key,
-    .bdrv_make_empty    = qcow2_make_empty,
 
     .bdrv_co_readv          = qcow2_co_readv,
     .bdrv_co_writev         = qcow2_co_writev,
@@ -2268,6 +2257,7 @@ static BlockDriver bdrv_qcow2 = {
 
     .bdrv_change_backing_file   = qcow2_change_backing_file,
 
+    .bdrv_refresh_limits        = qcow2_refresh_limits,
     .bdrv_invalidate_cache      = qcow2_invalidate_cache,
 
     .create_options = qcow2_create_options,

block/qcow2.h

@@ -340,11 +340,11 @@ typedef enum QCow2MetadataOverlap {
 #define QCOW2_OL_ALL \
     (QCOW2_OL_CACHED | QCOW2_OL_INACTIVE_L2)
 
-#define L1E_OFFSET_MASK 0x00ffffffffffff00ULL
-#define L2E_OFFSET_MASK 0x00ffffffffffff00ULL
+#define L1E_OFFSET_MASK 0x00fffffffffffe00ULL
+#define L2E_OFFSET_MASK 0x00fffffffffffe00ULL
 #define L2E_COMPRESSED_OFFSET_SIZE_MASK 0x3fffffffffffffffULL
 
-#define REFT_OFFSET_MASK 0xffffffffffffff00ULL
+#define REFT_OFFSET_MASK 0xfffffffffffffe00ULL
 
 static inline int64_t start_of_cluster(BDRVQcowState *s, int64_t offset)
 {
@@ -468,7 +468,7 @@ void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
     int *num, uint64_t *cluster_offset);
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m);
+    int *num, uint64_t *host_offset, QCowL2Meta **m);
 uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                          uint64_t offset,
                                          int compressed_size);

block/qed.c

@@ -495,7 +495,6 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
         }
     }
 
-    bs->bl.write_zeroes_alignment = s->header.cluster_size >> BDRV_SECTOR_BITS;
     s->need_check_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
                                             qed_need_check_timer_cb, s);
 
@@ -507,6 +506,15 @@ out:
     return ret;
 }
 
+static int bdrv_qed_refresh_limits(BlockDriverState *bs)
+{
+    BDRVQEDState *s = bs->opaque;
+
+    bs->bl.write_zeroes_alignment = s->header.cluster_size >> BDRV_SECTOR_BITS;
+
+    return 0;
+}
+
 /* We have nothing to do for QED reopen, stubs just return
  * success */
 static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
@@ -563,8 +571,8 @@ static int qed_create(const char *filename, uint32_t cluster_size,
         return ret;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR | BDRV_O_CACHE_WB,
-                         &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, NULL,
+                         BDRV_O_RDWR | BDRV_O_CACHE_WB, &local_err);
     if (ret < 0) {
         qerror_report_err(local_err);
         error_free(local_err);
@@ -723,11 +731,6 @@ static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs,
     return cb.status;
 }
 
-static int bdrv_qed_make_empty(BlockDriverState *bs)
-{
-    return -ENOTSUP;
-}
-
 static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
 {
     return acb->common.bs->opaque;
@@ -1609,13 +1612,13 @@ static BlockDriver bdrv_qed = {
     .bdrv_create              = bdrv_qed_create,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_get_block_status = bdrv_qed_co_get_block_status,
-    .bdrv_make_empty          = bdrv_qed_make_empty,
     .bdrv_aio_readv           = bdrv_qed_aio_readv,
     .bdrv_aio_writev          = bdrv_qed_aio_writev,
     .bdrv_co_write_zeroes     = bdrv_qed_co_write_zeroes,
     .bdrv_truncate            = bdrv_qed_truncate,
     .bdrv_getlength           = bdrv_qed_getlength,
     .bdrv_get_info            = bdrv_qed_get_info,
+    .bdrv_refresh_limits      = bdrv_qed_refresh_limits,
     .bdrv_change_backing_file = bdrv_qed_change_backing_file,
     .bdrv_invalidate_cache    = bdrv_qed_invalidate_cache,
     .bdrv_check               = bdrv_qed_check,

block/raw-posix.c

@@ -127,6 +127,8 @@ typedef struct BDRVRawState {
     int fd;
     int type;
     int open_flags;
+    size_t buf_align;
+
 #if defined(__linux__)
     /* linux floppy specific */
     int64_t fd_open_time;
@@ -213,6 +215,76 @@ static int raw_normalize_devicepath(const char **filename)
 }
 #endif
 
+static void raw_probe_alignment(BlockDriverState *bs)
+{
+    BDRVRawState *s = bs->opaque;
+    char *buf;
+    unsigned int sector_size;
+
+    /* For /dev/sg devices the alignment is not really used.
+       With buffered I/O, we don't have any restrictions. */
+    if (bs->sg || !(s->open_flags & O_DIRECT)) {
+        bs->request_alignment = 1;
+        s->buf_align = 1;
+        return;
+    }
+
+    /* Try a few ioctls to get the right size */
+    bs->request_alignment = 0;
+    s->buf_align = 0;
+
+#ifdef BLKSSZGET
+    if (ioctl(s->fd, BLKSSZGET, &sector_size) >= 0) {
+        bs->request_alignment = sector_size;
+    }
+#endif
+#ifdef DKIOCGETBLOCKSIZE
+    if (ioctl(s->fd, DKIOCGETBLOCKSIZE, &sector_size) >= 0) {
+        bs->request_alignment = sector_size;
+    }
+#endif
+#ifdef DIOCGSECTORSIZE
+    if (ioctl(s->fd, DIOCGSECTORSIZE, &sector_size) >= 0) {
+        bs->request_alignment = sector_size;
+    }
+#endif
+#ifdef CONFIG_XFS
+    if (s->is_xfs) {
+        struct dioattr da;
+        if (xfsctl(NULL, s->fd, XFS_IOC_DIOINFO, &da) >= 0) {
+            bs->request_alignment = da.d_miniosz;
+            /* The kernel returns wrong information for d_mem */
+            /* s->buf_align = da.d_mem; */
+        }
+    }
+#endif
+
+    /* If we could not get the sizes so far, we can only guess them */
+    if (!s->buf_align) {
+        size_t align;
+        buf = qemu_memalign(MAX_BLOCKSIZE, 2 * MAX_BLOCKSIZE);
+        for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
+            if (pread(s->fd, buf + align, MAX_BLOCKSIZE, 0) >= 0) {
+                s->buf_align = align;
+                break;
+            }
+        }
+        qemu_vfree(buf);
+    }
+
+    if (!bs->request_alignment) {
+        size_t align;
+        buf = qemu_memalign(s->buf_align, MAX_BLOCKSIZE);
+        for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
+            if (pread(s->fd, buf, align, 0) >= 0) {
+                bs->request_alignment = align;
+                break;
+            }
+        }
+        qemu_vfree(buf);
+    }
+}
+
 static void raw_parse_flags(int bdrv_flags, int *open_flags)
 {
     assert(open_flags != NULL);
@@ -287,7 +359,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     int fd, ret;
     struct stat st;
 
-    opts = qemu_opts_create_nofail(&raw_runtime_opts);
+    opts = qemu_opts_create(&raw_runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
@@ -463,7 +535,6 @@ static int raw_reopen_prepare(BDRVReopenState *state,
     return ret;
 }
 
-
 static void raw_reopen_commit(BDRVReopenState *state)
 {
     BDRVRawReopenState *raw_s = state->opaque;
@@ -499,23 +570,15 @@ static void raw_reopen_abort(BDRVReopenState *state)
     state->opaque = NULL;
 }
 
-
-/* XXX: use host sector size if necessary with:
-#ifdef DIOCGSECTORSIZE
+static int raw_refresh_limits(BlockDriverState *bs)
 {
-            unsigned int sectorsize = 512;
-            if (!ioctl(fd, DIOCGSECTORSIZE, &sectorsize) &&
-                sectorsize > bufsize)
-                bufsize = sectorsize;
+    BDRVRawState *s = bs->opaque;
+
+    raw_probe_alignment(bs);
+    bs->bl.opt_mem_alignment = s->buf_align;
+
+    return 0;
 }
-#endif
-#ifdef CONFIG_COCOA
-        uint32_t blockSize = 512;
-        if ( !ioctl( fd, DKIOCGETBLOCKSIZE, &blockSize ) && blockSize > bufsize) {
-            bufsize = blockSize;
-        }
-#endif
-*/
 
 static ssize_t handle_aiocb_ioctl(RawPosixAIOData *aiocb)
 {
@@ -1363,6 +1426,7 @@ static BlockDriver bdrv_file = {
     .bdrv_aio_writev = raw_aio_writev,
     .bdrv_aio_flush = raw_aio_flush,
     .bdrv_aio_discard = raw_aio_discard,
+    .bdrv_refresh_limits = raw_refresh_limits,
 
     .bdrv_truncate = raw_truncate,
     .bdrv_getlength = raw_getlength,
@@ -1740,6 +1804,7 @@ static BlockDriver bdrv_host_device = {
     .bdrv_aio_writev	= raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_aio_discard   = hdev_aio_discard,
+    .bdrv_refresh_limits = raw_refresh_limits,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength	= raw_getlength,
@@ -1871,6 +1936,7 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
+    .bdrv_refresh_limits = raw_refresh_limits,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,
@@ -1981,6 +2047,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
+    .bdrv_refresh_limits = raw_refresh_limits,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,
@@ -2110,6 +2177,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
+    .bdrv_refresh_limits = raw_refresh_limits,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,

block/raw-win32.c

@@ -202,6 +202,35 @@ static int set_sparse(int fd)
 				 NULL, 0, NULL, 0, &returned, NULL);
 }
 
+static void raw_probe_alignment(BlockDriverState *bs)
+{
+    BDRVRawState *s = bs->opaque;
+    DWORD sectorsPerCluster, freeClusters, totalClusters, count;
+    DISK_GEOMETRY_EX dg;
+    BOOL status;
+
+    if (s->type == FTYPE_CD) {
+        bs->request_alignment = 2048;
+        return;
+    }
+    if (s->type == FTYPE_HARDDISK) {
+        status = DeviceIoControl(s->hfile, IOCTL_DISK_GET_DRIVE_GEOMETRY_EX,
+                                 NULL, 0, &dg, sizeof(dg), &count, NULL);
+        if (status != 0) {
+            bs->request_alignment = dg.Geometry.BytesPerSector;
+            return;
+        }
+        /* try GetDiskFreeSpace too */
+    }
+
+    if (s->drive_path[0]) {
+        GetDiskFreeSpace(s->drive_path, &sectorsPerCluster,
+                         &dg.Geometry.BytesPerSector,
+                         &freeClusters, &totalClusters);
+        bs->request_alignment = dg.Geometry.BytesPerSector;
+    }
+}
+
 static void raw_parse_flags(int flags, int *access_flags, DWORD *overlapped)
 {
     assert(access_flags != NULL);
@@ -248,7 +277,7 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->type = FTYPE_FILE;
 
-    opts = qemu_opts_create_nofail(&raw_runtime_opts);
+    opts = qemu_opts_create(&raw_runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
@@ -269,6 +298,17 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
         }
     }
 
+    if (filename[0] && filename[1] == ':') {
+        snprintf(s->drive_path, sizeof(s->drive_path), "%c:\\", filename[0]);
+    } else if (filename[0] == '\\' && filename[1] == '\\') {
+        s->drive_path[0] = 0;
+    } else {
+        /* Relative path.  */
+        char buf[MAX_PATH];
+        GetCurrentDirectory(MAX_PATH, buf);
+        snprintf(s->drive_path, sizeof(s->drive_path), "%c:\\", buf[0]);
+    }
+
     s->hfile = CreateFile(filename, access_flags,
                           FILE_SHARE_READ, NULL,
                           OPEN_EXISTING, overlapped, NULL);
@@ -293,6 +333,7 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
         s->aio = aio;
     }
 
+    raw_probe_alignment(bs);
     ret = 0;
 fail:
     qemu_opts_del(opts);
@@ -550,7 +591,8 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
     Error *local_err = NULL;
     const char *filename;
 
-    QemuOpts *opts = qemu_opts_create_nofail(&raw_runtime_opts);
+    QemuOpts *opts = qemu_opts_create(&raw_runtime_opts, NULL, 0,
+                                      &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);

block/raw_bsd.c

@@ -90,6 +90,12 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return bdrv_get_info(bs->file, bdi);
 }
 
+static int raw_refresh_limits(BlockDriverState *bs)
+{
+    bs->bl = bs->file->bl;
+    return 0;
+}
+
 static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
     return bdrv_truncate(bs->file, offset);
@@ -150,7 +156,6 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
     bs->sg = bs->file->sg;
-    bs->bl = bs->file->bl;
     return 0;
 }
 
@@ -182,6 +187,7 @@ static BlockDriver bdrv_raw = {
     .bdrv_getlength       = &raw_getlength,
     .has_variable_length  = true,
     .bdrv_get_info        = &raw_get_info,
+    .bdrv_refresh_limits  = &raw_refresh_limits,
     .bdrv_is_inserted     = &raw_is_inserted,
     .bdrv_media_changed   = &raw_media_changed,
     .bdrv_eject           = &raw_eject,

block/rbd.c

@@ -95,18 +95,13 @@ typedef struct RADOSCB {
 #define RBD_FD_WRITE 1
 
 typedef struct BDRVRBDState {
-    int fds[2];
     rados_t cluster;
     rados_ioctx_t io_ctx;
     rbd_image_t image;
     char name[RBD_MAX_IMAGE_NAME_SIZE];
     char *snap;
-    int event_reader_pos;
-    RADOSCB *event_rcb;
 } BDRVRBDState;
 
-static void rbd_aio_bh_cb(void *opaque);
-
 static int qemu_rbd_next_tok(char *dst, int dst_len,
                              char *src, char delim,
                              const char *name,
@@ -369,9 +364,8 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
 }
 
 /*
- * This aio completion is being called from qemu_rbd_aio_event_reader()
- * and runs in qemu context. It schedules a bh, but just in case the aio
- * was not cancelled before.
+ * This aio completion is being called from rbd_finish_bh() and runs in qemu
+ * BH context.
  */
 static void qemu_rbd_complete_aio(RADOSCB *rcb)
 {
@@ -401,37 +395,20 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
             acb->ret = r;
         }
     }
-    /* Note that acb->bh can be NULL in case where the aio was cancelled */
-    acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
-    qemu_bh_schedule(acb->bh);
+
     g_free(rcb);
+
+    if (acb->cmd == RBD_AIO_READ) {
+        qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
     }
+    qemu_vfree(acb->bounce);
+    acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
+    acb->status = 0;
 
-/*
- * aio fd read handler. It runs in the qemu context and calls the
- * completion handling of completed rados aio operations.
- */
-static void qemu_rbd_aio_event_reader(void *opaque)
-{
-    BDRVRBDState *s = opaque;
-
-    ssize_t ret;
-
-    do {
-        char *p = (char *)&s->event_rcb;
-
-        /* now read the rcb pointer that was sent from a non qemu thread */
-        ret = read(s->fds[RBD_FD_READ], p + s->event_reader_pos,
-                   sizeof(s->event_rcb) - s->event_reader_pos);
-        if (ret > 0) {
-            s->event_reader_pos += ret;
-            if (s->event_reader_pos == sizeof(s->event_rcb)) {
-                s->event_reader_pos = 0;
-                qemu_rbd_complete_aio(s->event_rcb);
+    if (!acb->cancelled) {
+        qemu_aio_release(acb);
     }
 }
-    } while (ret < 0 && errno == EINTR);
-}
 
 /* TODO Convert to fine grained options */
 static QemuOptsList runtime_opts = {
@@ -461,7 +438,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     const char *filename;
     int r;
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         qerror_report_err(local_err);
@@ -538,23 +515,9 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
 
     bs->read_only = (s->snap != NULL);
 
-    s->event_reader_pos = 0;
-    r = qemu_pipe(s->fds);
-    if (r < 0) {
-        error_report("error opening eventfd");
-        goto failed;
-    }
-    fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
-    fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
-    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
-                            NULL, s);
-
-
     qemu_opts_del(opts);
     return 0;
 
-failed:
-    rbd_close(s->image);
 failed_open:
     rados_ioctx_destroy(s->io_ctx);
 failed_shutdown:
@@ -569,10 +532,6 @@ static void qemu_rbd_close(BlockDriverState *bs)
 {
     BDRVRBDState *s = bs->opaque;
 
-    close(s->fds[0]);
-    close(s->fds[1]);
-    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL, NULL, NULL);
-
     rbd_close(s->image);
     rados_ioctx_destroy(s->io_ctx);
     g_free(s->snap);
@@ -600,34 +559,11 @@ static const AIOCBInfo rbd_aiocb_info = {
     .cancel = qemu_rbd_aio_cancel,
 };
 
-static int qemu_rbd_send_pipe(BDRVRBDState *s, RADOSCB *rcb)
+static void rbd_finish_bh(void *opaque)
 {
-    int ret = 0;
-    while (1) {
-        fd_set wfd;
-        int fd = s->fds[RBD_FD_WRITE];
-
-        /* send the op pointer to the qemu thread that is responsible
-           for the aio/op completion. Must do it in a qemu thread context */
-        ret = write(fd, (void *)&rcb, sizeof(rcb));
-        if (ret >= 0) {
-            break;
-        }
-        if (errno == EINTR) {
-            continue;
-        }
-        if (errno != EAGAIN) {
-            break;
-        }
-
-        FD_ZERO(&wfd);
-        FD_SET(fd, &wfd);
-        do {
-            ret = select(fd + 1, NULL, &wfd, NULL, NULL);
-        } while (ret < 0 && errno == EINTR);
-    }
-
-    return ret;
+    RADOSCB *rcb = opaque;
+    qemu_bh_delete(rcb->acb->bh);
+    qemu_rbd_complete_aio(rcb);
 }
 
 /*
@@ -635,40 +571,18 @@ static int qemu_rbd_send_pipe(BDRVRBDState *s, RADOSCB *rcb)
  *
  * Note: this function is being called from a non qemu thread so
  * we need to be careful about what we do here. Generally we only
- * write to the block notification pipe, and do the rest of the
- * io completion handling from qemu_rbd_aio_event_reader() which
- * runs in a qemu context.
+ * schedule a BH, and do the rest of the io completion handling
+ * from rbd_finish_bh() which runs in a qemu context.
  */
 static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
 {
-    int ret;
+    RBDAIOCB *acb = rcb->acb;
+
     rcb->ret = rbd_aio_get_return_value(c);
     rbd_aio_release(c);
-    ret = qemu_rbd_send_pipe(rcb->s, rcb);
-    if (ret < 0) {
-        error_report("failed writing to acb->s->fds");
-        g_free(rcb);
-    }
-}
 
-/* Callback when all queued rbd_aio requests are complete */
-
-static void rbd_aio_bh_cb(void *opaque)
-{
-    RBDAIOCB *acb = opaque;
-
-    if (acb->cmd == RBD_AIO_READ) {
-        qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
-    }
-    qemu_vfree(acb->bounce);
-    acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
-    qemu_bh_delete(acb->bh);
-    acb->bh = NULL;
-    acb->status = 0;
-
-    if (!acb->cancelled) {
-        qemu_aio_release(acb);
-    }
+    acb->bh = qemu_bh_new(rbd_finish_bh, rcb);
+    qemu_bh_schedule(acb->bh);
 }
 
 static int rbd_aio_discard_wrapper(rbd_image_t image,

block/sheepdog.c

@@ -161,7 +161,7 @@ typedef struct SheepdogVdiReq {
     uint32_t id;
     uint32_t data_length;
     uint64_t vdi_size;
-    uint32_t vdi_id;
+    uint32_t base_vdi_id;
     uint8_t copies;
     uint8_t copy_policy;
     uint8_t reserved[2];
@@ -1383,7 +1383,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->bs = bs;
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         qerror_report_err(local_err);
@@ -1493,7 +1493,7 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
 
     memset(&hdr, 0, sizeof(hdr));
     hdr.opcode = SD_OP_NEW_VDI;
-    hdr.vdi_id = s->inode.vdi_id;
+    hdr.base_vdi_id = s->inode.vdi_id;
 
     wlen = SD_MAX_VDI_LEN;
 
@@ -1534,7 +1534,7 @@ static int sd_prealloc(const char *filename)
     Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR, &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
     if (ret < 0) {
         qerror_report_err(local_err);
         error_free(local_err);
@@ -1684,7 +1684,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
 
     if (backing_file) {
         BlockDriverState *bs;
-        BDRVSheepdogState *s;
+        BDRVSheepdogState *base;
         BlockDriver *drv;
 
         /* Currently, only Sheepdog backing image is supported. */
@@ -1695,22 +1695,22 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
             goto out;
         }
 
-        ret = bdrv_file_open(&bs, backing_file, NULL, 0, &local_err);
+        ret = bdrv_file_open(&bs, backing_file, NULL, NULL, 0, &local_err);
         if (ret < 0) {
             qerror_report_err(local_err);
             error_free(local_err);
             goto out;
         }
 
-        s = bs->opaque;
+        base = bs->opaque;
 
-        if (!is_snapshot(&s->inode)) {
+        if (!is_snapshot(&base->inode)) {
             error_report("cannot clone from a non snapshot vdi");
             bdrv_unref(bs);
             ret = -EINVAL;
             goto out;
         }
-
+        s->inode.vdi_id = base->inode.vdi_id;
         bdrv_unref(bs);
     }
 
@@ -1743,7 +1743,7 @@ static void sd_close(BlockDriverState *bs)
     memset(&hdr, 0, sizeof(hdr));
 
     hdr.opcode = SD_OP_RELEASE_VDI;
-    hdr.vdi_id = s->inode.vdi_id;
+    hdr.base_vdi_id = s->inode.vdi_id;
     wlen = strlen(s->name) + 1;
     hdr.data_length = wlen;
     hdr.flags = SD_FLAG_CMD_WRITE;
@@ -1846,7 +1846,7 @@ static bool sd_delete(BDRVSheepdogState *s)
     unsigned int wlen = SD_MAX_VDI_LEN, rlen = 0;
     SheepdogVdiReq hdr = {
         .opcode = SD_OP_DEL_VDI,
-        .vdi_id = s->inode.vdi_id,
+        .base_vdi_id = s->inode.vdi_id,
         .data_length = wlen,
         .flags = SD_FLAG_CMD_WRITE,
     };
@@ -2048,13 +2048,14 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
 {
     SheepdogAIOCB *acb;
     int ret;
+    int64_t offset = (sector_num + nb_sectors) * BDRV_SECTOR_SIZE;
+    BDRVSheepdogState *s = bs->opaque;
 
-    if (bs->growable && sector_num + nb_sectors > bs->total_sectors) {
-        ret = sd_truncate(bs, (sector_num + nb_sectors) * BDRV_SECTOR_SIZE);
+    if (bs->growable && offset > s->inode.vdi_size) {
+        ret = sd_truncate(bs, offset);
         if (ret < 0) {
             return ret;
         }
-        bs->total_sectors = sector_num + nb_sectors;
     }
 
     acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
@@ -2441,11 +2442,12 @@ sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
 {
     BDRVSheepdogState *s = bs->opaque;
     SheepdogInode *inode = &s->inode;
-    unsigned long start = sector_num * BDRV_SECTOR_SIZE / SD_DATA_OBJ_SIZE,
+    uint64_t offset = sector_num * BDRV_SECTOR_SIZE;
+    unsigned long start = offset / SD_DATA_OBJ_SIZE,
                   end = DIV_ROUND_UP((sector_num + nb_sectors) *
                                      BDRV_SECTOR_SIZE, SD_DATA_OBJ_SIZE);
     unsigned long idx;
-    int64_t ret = BDRV_BLOCK_DATA;
+    int64_t ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
 
     for (idx = start; idx < end; idx++) {
         if (inode->data_vdi_id[idx] == 0) {

block/stream.c

@@ -75,6 +75,8 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
         unused->backing_hd = NULL;
         bdrv_unref(unused);
     }
+
+    bdrv_refresh_limits(top);
 }
 
 static void coroutine_fn stream_run(void *opaque)

block/vhdx-log.c

@@ -706,7 +706,8 @@ exit:
  *
  * If read-only, we must replay the log in RAM (or refuse to open
  * a dirty VHDX file read-only) */
-int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed)
+int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed,
+                   Error **errp)
 {
     int ret = 0;
     VHDXHeader *hdr;
@@ -761,6 +762,16 @@ int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed)
     }
 
     if (logs.valid) {
+        if (bs->read_only) {
+            ret = -EPERM;
+            error_setg_errno(errp, EPERM,
+                             "VHDX image file '%s' opened read-only, but "
+                             "contains a log that needs to be replayed.  To "
+                             "replay the log, execute:\n qemu-img check -r "
+                             "all '%s'",
+                             bs->filename, bs->filename);
+            goto exit;
+        }
         /* now flush the log */
         ret = vhdx_log_flush(bs, s, &logs);
         if (ret < 0) {
@@ -954,7 +965,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
     cpu_to_le32s((uint32_t *)(buffer + 4));
 
     /* now write to the log */
-    vhdx_log_write_sectors(bs, &s->log, &sectors_written, buffer,
+    ret = vhdx_log_write_sectors(bs, &s->log, &sectors_written, buffer,
                                  desc_sectors + sectors);
     if (ret < 0) {
         goto exit;

block/vhdx.c

@@ -374,7 +374,7 @@ static int vhdx_update_header(BlockDriverState *bs, BDRVVHDXState *s,
         inactive_header->log_guid = *log_guid;
     }
 
-    vhdx_write_header(bs->file, inactive_header, header_offset, true);
+    ret = vhdx_write_header(bs->file, inactive_header, header_offset, true);
     if (ret < 0) {
         goto exit;
     }
@@ -878,7 +878,6 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
     int ret = 0;
     uint32_t i;
     uint64_t signature;
-    bool log_flushed = false;
 
 
     s->bat = NULL;
@@ -907,7 +906,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    ret = vhdx_parse_log(bs, s, &log_flushed);
+    ret = vhdx_parse_log(bs, s, &s->log_replayed_on_open, errp);
     if (ret < 0) {
         goto fail;
     }
@@ -1798,7 +1797,7 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
         goto exit;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR, &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto exit;
@@ -1811,13 +1810,13 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
     creator = g_utf8_to_utf16("QEMU v" QEMU_VERSION, -1, NULL,
                               &creator_items, NULL);
     signature = cpu_to_le64(VHDX_FILE_SIGNATURE);
-    bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature));
+    ret = bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature));
     if (ret < 0) {
         goto delete_and_exit;
     }
     if (creator) {
-        bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET + sizeof(signature), creator,
-                    creator_items * sizeof(gunichar2));
+        ret = bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET + sizeof(signature),
+                          creator, creator_items * sizeof(gunichar2));
         if (ret < 0) {
             goto delete_and_exit;
         }
@@ -1854,6 +1853,24 @@ exit:
     return ret;
 }
 
+/* If opened r/w, the VHDX driver will automatically replay the log,
+ * if one is present, inside the vhdx_open() call.
+ *
+ * If qemu-img check -r all is called, the image is automatically opened
+ * r/w and any log has already been replayed, so there is nothing (currently)
+ * for us to do here
+ */
+static int vhdx_check(BlockDriverState *bs, BdrvCheckResult *result,
+                       BdrvCheckMode fix)
+{
+    BDRVVHDXState *s = bs->opaque;
+
+    if (s->log_replayed_on_open) {
+        result->corruptions_fixed++;
+    }
+    return 0;
+}
+
 static QEMUOptionParameter vhdx_create_options[] = {
     {
         .name = BLOCK_OPT_SIZE,
@@ -1898,6 +1915,7 @@ static BlockDriver bdrv_vhdx = {
     .bdrv_co_writev         = vhdx_co_writev,
     .bdrv_create            = vhdx_create,
     .bdrv_get_info          = vhdx_get_info,
+    .bdrv_check             = vhdx_check,
 
     .create_options         = vhdx_create_options,
 };

block/vhdx.h

@@ -394,6 +394,8 @@ typedef struct BDRVVHDXState {
 
     Error *migration_blocker;
 
+    bool log_replayed_on_open;
+
     QLIST_HEAD(VHDXRegionHead, VHDXRegionEntry) regions;
 } BDRVVHDXState;
 
@@ -408,7 +410,8 @@ uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size,
 
 bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset);
 
-int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed);
+int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed,
+                   Error **errp);
 
 int vhdx_log_write_and_flush(BlockDriverState *bs, BDRVVHDXState *s,
                              void *data, uint32_t length, uint64_t offset);

block/vmdk.c

@@ -428,10 +428,6 @@ static int vmdk_add_extent(BlockDriverState *bs,
     extent->l2_size = l2_size;
     extent->cluster_sectors = flat ? sectors : cluster_sectors;
 
-    if (!flat) {
-        bs->bl.write_zeroes_alignment =
-            MAX(bs->bl.write_zeroes_alignment, cluster_sectors);
-    }
     if (s->num_extents > 1) {
         extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;
     } else {
@@ -640,6 +636,13 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
     if (le32_to_cpu(header.flags) & VMDK4_FLAG_RGD) {
         l1_backup_offset = le64_to_cpu(header.rgd_offset) << 9;
     }
+    if (bdrv_getlength(file) <
+            le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE) {
+        error_report("File truncated, expecting at least %lld bytes",
+                le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE);
+        return -EINVAL;
+    }
+
     ret = vmdk_add_extent(bs, file, false,
                           le64_to_cpu(header.capacity),
                           le64_to_cpu(header.gd_offset) << 9,
@@ -654,6 +657,10 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
     }
     extent->compressed =
         le16_to_cpu(header.compressAlgorithm) == VMDK4_COMPRESSION_DEFLATE;
+    if (extent->compressed) {
+        g_free(s->create_type);
+        s->create_type = g_strdup("streamOptimized");
+    }
     extent->has_marker = le32_to_cpu(header.flags) & VMDK4_FLAG_MARKER;
     extent->version = le32_to_cpu(header.version);
     extent->has_zero_grain = le32_to_cpu(header.flags) & VMDK4_FLAG_ZERO_GRAIN;
@@ -749,7 +756,12 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
                 return -EINVAL;
             }
         } else if (!strcmp(type, "VMFS")) {
+            if (ret == 4) {
                 flat_offset = 0;
+            } else {
+                error_setg(errp, "Invalid extent lines:\n%s", p);
+                return -EINVAL;
+            }
         } else if (ret != 4) {
             error_setg(errp, "Invalid extent lines:\n%s", p);
             return -EINVAL;
@@ -764,8 +776,8 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
 
         path_combine(extent_path, sizeof(extent_path),
                 desc_file_path, fname);
-        ret = bdrv_file_open(&extent_file, extent_path, NULL, bs->open_flags,
-                             errp);
+        ret = bdrv_file_open(&extent_file, extent_path, NULL, NULL,
+                             bs->open_flags, errp);
         if (ret) {
             return ret;
         }
@@ -886,6 +898,23 @@ fail:
     return ret;
 }
 
+
+static int vmdk_refresh_limits(BlockDriverState *bs)
+{
+    BDRVVmdkState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_extents; i++) {
+        if (!s->extents[i].flat) {
+            bs->bl.write_zeroes_alignment =
+                MAX(bs->bl.write_zeroes_alignment,
+                    s->extents[i].cluster_sectors);
+        }
+    }
+
+    return 0;
+}
+
 static int get_whole_cluster(BlockDriverState *bs,
                 VmdkExtent *extent,
                 uint64_t cluster_offset,
@@ -1320,8 +1349,8 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
 {
     BDRVVmdkState *s = bs->opaque;
     VmdkExtent *extent = NULL;
-    int n, ret;
-    int64_t index_in_cluster;
+    int ret;
+    int64_t index_in_cluster, n;
     uint64_t extent_begin_sector, extent_relative_sector_num;
     uint64_t cluster_offset;
     VmdkMetaData m_data;
@@ -1447,23 +1476,33 @@ static int coroutine_fn vmdk_co_write_zeroes(BlockDriverState *bs,
 }
 
 static int vmdk_create_extent(const char *filename, int64_t filesize,
-                              bool flat, bool compress, bool zeroed_grain)
+                              bool flat, bool compress, bool zeroed_grain,
+                              Error **errp)
 {
     int ret, i;
-    int fd = 0;
+    BlockDriverState *bs = NULL;
     VMDK4Header header;
-    uint32_t tmp, magic, grains, gd_size, gt_size, gt_count;
+    Error *local_err;
+    uint32_t tmp, magic, grains, gd_sectors, gt_size, gt_count;
+    uint32_t *gd_buf = NULL;
+    int gd_buf_size;
 
-    fd = qemu_open(filename,
-                   O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
-                   0644);
-    if (fd < 0) {
-        return -errno;
-    }
-    if (flat) {
-        ret = ftruncate(fd, filesize);
+    ret = bdrv_create_file(filename, NULL, &local_err);
     if (ret < 0) {
-            ret = -errno;
+        error_propagate(errp, local_err);
+        goto exit;
+    }
+
+    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+        goto exit;
+    }
+
+    if (flat) {
+        ret = bdrv_truncate(bs, filesize);
+        if (ret < 0) {
+            error_setg(errp, "Could not truncate file");
         }
         goto exit;
     }
@@ -1474,24 +1513,23 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
                    | (compress ? VMDK4_FLAG_COMPRESS | VMDK4_FLAG_MARKER : 0)
                    | (zeroed_grain ? VMDK4_FLAG_ZERO_GRAIN : 0);
     header.compressAlgorithm = compress ? VMDK4_COMPRESSION_DEFLATE : 0;
-    header.capacity = filesize / 512;
+    header.capacity = filesize / BDRV_SECTOR_SIZE;
     header.granularity = 128;
-    header.num_gtes_per_gt = 512;
+    header.num_gtes_per_gt = BDRV_SECTOR_SIZE;
 
-    grains = (filesize / 512 + header.granularity - 1) / header.granularity;
-    gt_size = ((header.num_gtes_per_gt * sizeof(uint32_t)) + 511) >> 9;
-    gt_count =
-        (grains + header.num_gtes_per_gt - 1) / header.num_gtes_per_gt;
-    gd_size = (gt_count * sizeof(uint32_t) + 511) >> 9;
+    grains = DIV_ROUND_UP(filesize / BDRV_SECTOR_SIZE, header.granularity);
+    gt_size = DIV_ROUND_UP(header.num_gtes_per_gt * sizeof(uint32_t),
+                           BDRV_SECTOR_SIZE);
+    gt_count = DIV_ROUND_UP(grains, header.num_gtes_per_gt);
+    gd_sectors = DIV_ROUND_UP(gt_count * sizeof(uint32_t), BDRV_SECTOR_SIZE);
 
     header.desc_offset = 1;
     header.desc_size = 20;
     header.rgd_offset = header.desc_offset + header.desc_size;
-    header.gd_offset = header.rgd_offset + gd_size + (gt_size * gt_count);
+    header.gd_offset = header.rgd_offset + gd_sectors + (gt_size * gt_count);
     header.grain_offset =
-       ((header.gd_offset + gd_size + (gt_size * gt_count) +
-         header.granularity - 1) / header.granularity) *
-        header.granularity;
+        ROUND_UP(header.gd_offset + gd_sectors + (gt_size * gt_count),
+                 header.granularity);
     /* swap endianness for all header fields */
     header.version = cpu_to_le32(header.version);
     header.flags = cpu_to_le32(header.flags);
@@ -1511,48 +1549,55 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
     header.check_bytes[3] = 0xa;
 
     /* write all the data */
-    ret = qemu_write_full(fd, &magic, sizeof(magic));
-    if (ret != sizeof(magic)) {
-        ret = -errno;
+    ret = bdrv_pwrite(bs, 0, &magic, sizeof(magic));
+    if (ret < 0) {
+        error_set(errp, QERR_IO_ERROR);
         goto exit;
     }
-    ret = qemu_write_full(fd, &header, sizeof(header));
-    if (ret != sizeof(header)) {
-        ret = -errno;
+    ret = bdrv_pwrite(bs, sizeof(magic), &header, sizeof(header));
+    if (ret < 0) {
+        error_set(errp, QERR_IO_ERROR);
         goto exit;
     }
 
-    ret = ftruncate(fd, le64_to_cpu(header.grain_offset) << 9);
+    ret = bdrv_truncate(bs, le64_to_cpu(header.grain_offset) << 9);
     if (ret < 0) {
-        ret = -errno;
+        error_setg(errp, "Could not truncate file");
         goto exit;
     }
 
     /* write grain directory */
-    lseek(fd, le64_to_cpu(header.rgd_offset) << 9, SEEK_SET);
-    for (i = 0, tmp = le64_to_cpu(header.rgd_offset) + gd_size;
+    gd_buf_size = gd_sectors * BDRV_SECTOR_SIZE;
+    gd_buf = g_malloc0(gd_buf_size);
+    for (i = 0, tmp = le64_to_cpu(header.rgd_offset) + gd_sectors;
          i < gt_count; i++, tmp += gt_size) {
-        ret = qemu_write_full(fd, &tmp, sizeof(tmp));
-        if (ret != sizeof(tmp)) {
-            ret = -errno;
-            goto exit;
+        gd_buf[i] = cpu_to_le32(tmp);
     }
+    ret = bdrv_pwrite(bs, le64_to_cpu(header.rgd_offset) * BDRV_SECTOR_SIZE,
+                      gd_buf, gd_buf_size);
+    if (ret < 0) {
+        error_set(errp, QERR_IO_ERROR);
+        goto exit;
     }
 
     /* write backup grain directory */
-    lseek(fd, le64_to_cpu(header.gd_offset) << 9, SEEK_SET);
-    for (i = 0, tmp = le64_to_cpu(header.gd_offset) + gd_size;
+    for (i = 0, tmp = le64_to_cpu(header.gd_offset) + gd_sectors;
          i < gt_count; i++, tmp += gt_size) {
-        ret = qemu_write_full(fd, &tmp, sizeof(tmp));
-        if (ret != sizeof(tmp)) {
-            ret = -errno;
-            goto exit;
+        gd_buf[i] = cpu_to_le32(tmp);
     }
+    ret = bdrv_pwrite(bs, le64_to_cpu(header.gd_offset) * BDRV_SECTOR_SIZE,
+                      gd_buf, gd_buf_size);
+    if (ret < 0) {
+        error_set(errp, QERR_IO_ERROR);
+        goto exit;
     }
 
     ret = 0;
 exit:
-    qemu_close(fd);
+    if (bs) {
+        bdrv_unref(bs);
+    }
+    g_free(gd_buf);
     return ret;
 }
 
@@ -1599,7 +1644,9 @@ static int filename_decompose(const char *filename, char *path, char *prefix,
 static int vmdk_create(const char *filename, QEMUOptionParameter *options,
                        Error **errp)
 {
-    int fd, idx = 0;
+    int idx = 0;
+    BlockDriverState *new_bs = NULL;
+    Error *local_err;
     char *desc = NULL;
     int64_t total_size = 0, filesize;
     const char *adapter_type = NULL;
@@ -1616,6 +1663,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     uint32_t parent_cid = 0xffffffff;
     uint32_t number_heads = 16;
     bool zeroed_grain = false;
+    uint32_t desc_offset = 0, desc_len;
     const char desc_template[] =
         "# Disk DescriptorFile\n"
         "version=1\n"
@@ -1749,7 +1797,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
                 path, desc_filename);
 
         if (vmdk_create_extent(ext_filename, size,
-                               flat, compress, zeroed_grain)) {
+                               flat, compress, zeroed_grain, errp)) {
             ret = -EINVAL;
             goto exit;
         }
@@ -1757,7 +1805,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
 
         /* Format description line */
         snprintf(desc_line, sizeof(desc_line),
-                    desc_extent_line, size / 512, desc_filename);
+                    desc_extent_line, size / BDRV_SECTOR_SIZE, desc_filename);
         g_string_append(ext_desc_lines, desc_line);
     }
     /* generate descriptor file */
@@ -1768,36 +1816,43 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
                            parent_desc_line,
                            ext_desc_lines->str,
                            (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
-                           total_size / (int64_t)(63 * number_heads * 512),
+                           total_size /
+                               (int64_t)(63 * number_heads * BDRV_SECTOR_SIZE),
                            number_heads,
                            adapter_type);
-    if (split || flat) {
-        fd = qemu_open(filename,
-                       O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
-                       0644);
+    desc_len = strlen(desc);
+    /* the descriptor offset = 0x200 */
+    if (!split && !flat) {
+        desc_offset = 0x200;
     } else {
-        fd = qemu_open(filename,
-                       O_WRONLY | O_BINARY | O_LARGEFILE,
-                       0644);
-    }
-    if (fd < 0) {
-        ret = -errno;
+        ret = bdrv_create_file(filename, options, &local_err);
+        if (ret < 0) {
+            error_setg_errno(errp, -ret, "Could not create image file");
             goto exit;
         }
-    /* the descriptor offset = 0x200 */
-    if (!split && !flat && 0x200 != lseek(fd, 0x200, SEEK_SET)) {
-        ret = -errno;
-        goto close_exit;
     }
-    ret = qemu_write_full(fd, desc, strlen(desc));
-    if (ret != strlen(desc)) {
-        ret = -errno;
-        goto close_exit;
+    ret = bdrv_file_open(&new_bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not write description");
+        goto exit;
+    }
+    ret = bdrv_pwrite(new_bs, desc_offset, desc, desc_len);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not write description");
+        goto exit;
+    }
+    /* bdrv_pwrite write padding zeros to align to sector, we don't need that
+     * for description file */
+    if (desc_offset == 0) {
+        ret = bdrv_truncate(new_bs, desc_len);
+        if (ret < 0) {
+            error_setg(errp, "Could not truncate file");
+        }
     }
-    ret = 0;
-close_exit:
-    qemu_close(fd);
 exit:
+    if (new_bs) {
+        bdrv_unref(new_bs);
+    }
     g_free(desc);
     g_string_free(ext_desc_lines, true);
     return ret;
@@ -1887,6 +1942,53 @@ static ImageInfo *vmdk_get_extent_info(VmdkExtent *extent)
     return info;
 }
 
+static int vmdk_check(BlockDriverState *bs, BdrvCheckResult *result,
+                      BdrvCheckMode fix)
+{
+    BDRVVmdkState *s = bs->opaque;
+    VmdkExtent *extent = NULL;
+    int64_t sector_num = 0;
+    int64_t total_sectors = bdrv_getlength(bs) / BDRV_SECTOR_SIZE;
+    int ret;
+    uint64_t cluster_offset;
+
+    if (fix) {
+        return -ENOTSUP;
+    }
+
+    for (;;) {
+        if (sector_num >= total_sectors) {
+            return 0;
+        }
+        extent = find_extent(s, sector_num, extent);
+        if (!extent) {
+            fprintf(stderr,
+                    "ERROR: could not find extent for sector %" PRId64 "\n",
+                    sector_num);
+            break;
+        }
+        ret = get_cluster_offset(bs, extent, NULL,
+                                 sector_num << BDRV_SECTOR_BITS,
+                                 0, &cluster_offset);
+        if (ret == VMDK_ERROR) {
+            fprintf(stderr,
+                    "ERROR: could not get cluster_offset for sector %"
+                    PRId64 "\n", sector_num);
+            break;
+        }
+        if (ret == VMDK_OK && cluster_offset >= bdrv_getlength(extent->file)) {
+            fprintf(stderr,
+                    "ERROR: cluster offset for sector %"
+                    PRId64 " points after EOF\n", sector_num);
+            break;
+        }
+        sector_num += extent->cluster_sectors;
+    }
+
+    result->corruptions++;
+    return 0;
+}
+
 static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs)
 {
     int i;
@@ -1960,6 +2062,7 @@ static BlockDriver bdrv_vmdk = {
     .instance_size                = sizeof(BDRVVmdkState),
     .bdrv_probe                   = vmdk_probe,
     .bdrv_open                    = vmdk_open,
+    .bdrv_check                   = vmdk_check,
     .bdrv_reopen_prepare          = vmdk_reopen_prepare,
     .bdrv_read                    = vmdk_co_read,
     .bdrv_write                   = vmdk_co_write,
@@ -1971,6 +2074,7 @@ static BlockDriver bdrv_vmdk = {
     .bdrv_get_allocated_file_size = vmdk_get_allocated_file_size,
     .bdrv_has_zero_init           = vmdk_has_zero_init,
     .bdrv_get_specific_info       = vmdk_get_specific_info,
+    .bdrv_refresh_limits          = vmdk_refresh_limits,
 
     .create_options               = vmdk_create_options,
 };

block/vvfat.c

@@ -1083,7 +1083,7 @@ DLOG(if (stderr == NULL) {
     setbuf(stderr, NULL);
 })
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (error_is_set(&local_err)) {
         qerror_report_err(local_err);

blockdev.c

@@ -307,12 +307,11 @@ static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
 typedef enum { MEDIA_DISK, MEDIA_CDROM } DriveMediaType;
 
 /* Takes the ownership of bs_opts */
-static DriveInfo *blockdev_init(QDict *bs_opts,
+static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
                                 BlockInterfaceType type,
                                 Error **errp)
 {
     const char *buf;
-    const char *file = NULL;
     const char *serial;
     int ro = 0;
     int bdrv_flags = 0;
@@ -354,7 +353,6 @@ static DriveInfo *blockdev_init(QDict *bs_opts,
     ro = qemu_opt_get_bool(opts, "read-only", 0);
     copy_on_read = qemu_opt_get_bool(opts, "copy-on-read", false);
 
-    file = qemu_opt_get(opts, "file");
     serial = qemu_opt_get(opts, "serial");
 
     if ((buf = qemu_opt_get(opts, "discard")) != NULL) {
@@ -599,6 +597,10 @@ QemuOptsList qemu_legacy_drive_opts = {
             .name = "addr",
             .type = QEMU_OPT_STRING,
             .help = "pci address (virtio only)",
+        },{
+            .name = "file",
+            .type = QEMU_OPT_STRING,
+            .help = "file name",
         },
 
         /* Options that are passed on, but have special semantics with -drive */
@@ -629,6 +631,7 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
     const char *devaddr;
     bool read_only = false;
     bool copy_on_read;
+    const char *filename;
     Error *local_err = NULL;
 
     /* Change legacy command line options into QMP ones */
@@ -682,7 +685,8 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
     bs_opts = qdict_new();
     qemu_opts_to_qdict(all_opts, bs_opts);
 
-    legacy_opts = qemu_opts_create_nofail(&qemu_legacy_drive_opts);
+    legacy_opts = qemu_opts_create(&qemu_legacy_drive_opts, NULL, 0,
+                                   &error_abort);
     qemu_opts_absorb_qdict(legacy_opts, bs_opts, &local_err);
     if (error_is_set(&local_err)) {
         qerror_report_err(local_err);
@@ -853,7 +857,8 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
 
     if (type == IF_VIRTIO) {
         QemuOpts *devopts;
-        devopts = qemu_opts_create_nofail(qemu_find_opts("device"));
+        devopts = qemu_opts_create(qemu_find_opts("device"), NULL, 0,
+                                   &error_abort);
         if (arch_type == QEMU_ARCH_S390X) {
             qemu_opt_set(devopts, "driver", "virtio-blk-s390");
         } else {
@@ -865,8 +870,10 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
         }
     }
 
+    filename = qemu_opt_get(legacy_opts, "file");
+
     /* Actual block device init: Functionality shared with blockdev-add */
-    dinfo = blockdev_init(bs_opts, type, &local_err);
+    dinfo = blockdev_init(filename, bs_opts, type, &local_err);
     if (dinfo == NULL) {
         if (error_is_set(&local_err)) {
             qerror_report_err(local_err);
@@ -940,14 +947,22 @@ static void blockdev_do_action(int kind, void *data, Error **errp)
     qmp_transaction(&list, errp);
 }
 
-void qmp_blockdev_snapshot_sync(const char *device, const char *snapshot_file,
+void qmp_blockdev_snapshot_sync(bool has_device, const char *device,
+                                bool has_node_name, const char *node_name,
+                                const char *snapshot_file,
+                                bool has_snapshot_node_name,
+                                const char *snapshot_node_name,
                                 bool has_format, const char *format,
-                                bool has_mode, enum NewImageMode mode,
-                                Error **errp)
+                                bool has_mode, NewImageMode mode, Error **errp)
 {
     BlockdevSnapshot snapshot = {
+        .has_device = has_device,
         .device = (char *) device,
+        .has_node_name = has_node_name,
+        .node_name = (char *) node_name,
         .snapshot_file = (char *) snapshot_file,
+        .has_snapshot_node_name = has_snapshot_node_name,
+        .snapshot_node_name = (char *) snapshot_node_name,
         .has_format = has_format,
         .format = (char *) format,
         .has_mode = has_mode,
@@ -1185,8 +1200,14 @@ static void external_snapshot_prepare(BlkTransactionState *common,
 {
     BlockDriver *drv;
     int flags, ret;
+    QDict *options = NULL;
     Error *local_err = NULL;
+    bool has_device = false;
     const char *device;
+    bool has_node_name = false;
+    const char *node_name;
+    bool has_snapshot_node_name = false;
+    const char *snapshot_node_name;
     const char *new_image_file;
     const char *format = "qcow2";
     enum NewImageMode mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
@@ -1197,7 +1218,14 @@ static void external_snapshot_prepare(BlkTransactionState *common,
     /* get parameters */
     g_assert(action->kind == TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC);
 
+    has_device = action->blockdev_snapshot_sync->has_device;
     device = action->blockdev_snapshot_sync->device;
+    has_node_name = action->blockdev_snapshot_sync->has_node_name;
+    node_name = action->blockdev_snapshot_sync->node_name;
+    has_snapshot_node_name =
+        action->blockdev_snapshot_sync->has_snapshot_node_name;
+    snapshot_node_name = action->blockdev_snapshot_sync->snapshot_node_name;
+
     new_image_file = action->blockdev_snapshot_sync->snapshot_file;
     if (action->blockdev_snapshot_sync->has_format) {
         format = action->blockdev_snapshot_sync->format;
@@ -1213,9 +1241,21 @@ static void external_snapshot_prepare(BlkTransactionState *common,
         return;
     }
 
-    state->old_bs = bdrv_find(device);
-    if (!state->old_bs) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
+    state->old_bs = bdrv_lookup_bs(has_device ? device : NULL,
+                                   has_node_name ? node_name : NULL,
+                                   &local_err);
+    if (error_is_set(&local_err)) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    if (has_node_name && !has_snapshot_node_name) {
+        error_setg(errp, "New snapshot node name missing");
+        return;
+    }
+
+    if (has_snapshot_node_name && bdrv_find_node(snapshot_node_name)) {
+        error_setg(errp, "New snapshot node name already existing");
         return;
     }
 
@@ -1236,7 +1276,7 @@ static void external_snapshot_prepare(BlkTransactionState *common,
         }
     }
 
-    if (bdrv_check_ext_snapshot(state->old_bs) != EXT_SNAPSHOT_ALLOWED) {
+    if (!bdrv_is_first_non_filter(state->old_bs)) {
         error_set(errp, QERR_FEATURE_DISABLED, "snapshot");
         return;
     }
@@ -1255,15 +1295,23 @@ static void external_snapshot_prepare(BlkTransactionState *common,
         }
     }
 
+    if (has_snapshot_node_name) {
+        options = qdict_new();
+        qdict_put(options, "node-name",
+                  qstring_from_str(snapshot_node_name));
+    }
+
     /* We will manually add the backing_hd field to the bs later */
     state->new_bs = bdrv_new("");
     /* TODO Inherit bs->options or only take explicit options with an
      * extended QMP command? */
-    ret = bdrv_open(state->new_bs, new_image_file, NULL,
+    ret = bdrv_open(state->new_bs, new_image_file, options,
                     flags | BDRV_O_NO_BACKING, drv, &local_err);
     if (ret != 0) {
         error_propagate(errp, local_err);
     }
+
+    QDECREF(options);
 }
 
 static void external_snapshot_commit(BlkTransactionState *common)
@@ -1474,14 +1522,19 @@ void qmp_eject(const char *device, bool has_force, bool force, Error **errp)
     eject_device(bs, force, errp);
 }
 
-void qmp_block_passwd(const char *device, const char *password, Error **errp)
+void qmp_block_passwd(bool has_device, const char *device,
+                      bool has_node_name, const char *node_name,
+                      const char *password, Error **errp)
 {
+    Error *local_err = NULL;
     BlockDriverState *bs;
     int err;
 
-    bs = bdrv_find(device);
-    if (!bs) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
+    bs = bdrv_lookup_bs(has_device ? device : NULL,
+                        has_node_name ? node_name : NULL,
+                        &local_err);
+    if (error_is_set(&local_err)) {
+        error_propagate(errp, local_err);
         return;
     }
 
@@ -1671,14 +1724,24 @@ int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
     return 0;
 }
 
-void qmp_block_resize(const char *device, int64_t size, Error **errp)
+void qmp_block_resize(bool has_device, const char *device,
+                      bool has_node_name, const char *node_name,
+                      int64_t size, Error **errp)
 {
+    Error *local_err = NULL;
     BlockDriverState *bs;
     int ret;
 
-    bs = bdrv_find(device);
-    if (!bs) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
+    bs = bdrv_lookup_bs(has_device ? device : NULL,
+                        has_node_name ? node_name : NULL,
+                        &local_err);
+    if (error_is_set(&local_err)) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    if (!bdrv_is_first_non_filter(bs)) {
+        error_set(errp, QERR_FEATURE_DISABLED, "resize");
         return;
     }
 
@@ -1820,8 +1883,13 @@ void qmp_block_commit(const char *device,
         return;
     }
 
+    if (top_bs == bs) {
+        commit_active_start(bs, base_bs, speed, on_error, block_job_cb,
+                            bs, &local_err);
+    } else {
         commit_start(bs, base_bs, top_bs, speed, on_error, block_job_cb, bs,
                     &local_err);
+    }
     if (local_err != NULL) {
         error_propagate(errp, local_err);
         return;
@@ -1940,6 +2008,11 @@ void qmp_drive_backup(const char *device, const char *target,
     }
 }
 
+BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp)
+{
+    return bdrv_named_nodes_list();
+}
+
 #define DEFAULT_MIRROR_BUF_SIZE   (10 << 20)
 
 void qmp_drive_mirror(const char *device, const char *target,
@@ -2203,7 +2276,7 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
 
     qdict_flatten(qdict);
 
-    blockdev_init(qdict, IF_NONE, &local_err);
+    blockdev_init(NULL, qdict, IF_NONE, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
         goto fail;
@@ -2243,10 +2316,6 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "snapshot",
             .type = QEMU_OPT_BOOL,
             .help = "enable/disable snapshot mode",
-        },{
-            .name = "file",
-            .type = QEMU_OPT_STRING,
-            .help = "disk image",
         },{
             .name = "discard",
             .type = QEMU_OPT_STRING,

configure

@@ -251,11 +251,13 @@ vss_win32_sdk=""
 win_sdk="no"
 want_tools="yes"
 libiscsi=""
+libnfs=""
 coroutine=""
 coroutine_pool=""
 seccomp=""
 glusterfs=""
 glusterfs_discard="no"
+glusterfs_zerofill="no"
 virtio_blk_data_plane=""
 gtk=""
 gtkabi="2.0"
@@ -839,6 +841,10 @@ for opt do
   ;;
   --enable-libiscsi) libiscsi="yes"
   ;;
+  --disable-libnfs) libnfs="no"
+  ;;
+  --enable-libnfs) libnfs="yes"
+  ;;
   --enable-profiler) profiler="yes"
   ;;
   --disable-cocoa) cocoa="no"
@@ -1004,6 +1010,25 @@ for opt do
   esac
 done
 
+if ! has $python; then
+  error_exit "Python not found. Use --python=/path/to/python"
+fi
+
+# Note that if the Python conditional here evaluates True we will exit
+# with status 1 which is a shell 'false' value.
+if ! $python -c 'import sys; sys.exit(sys.version_info < (2,4) or sys.version_info >= (3,))'; then
+  error_exit "Cannot use '$python', Python 2.4 or later is required." \
+      "Note that Python 3 or later is not yet supported." \
+      "Use --python=/path/to/python to specify a supported Python."
+fi
+
+# The -B switch was added in Python 2.6.
+# If it is supplied, compiled files are not written.
+# Use it for Python versions which support it.
+if $python -B -c 'import sys; sys.exit(0)' 2>/dev/null; then
+  python="$python -B"
+fi
+
 case "$cpu" in
     ppc)
            CPU_CFLAGS="-m32"
@@ -1074,169 +1099,171 @@ cat << EOF
 Usage: configure [options]
 Options: [defaults in brackets after descriptions]
 
+Standard options:
+  --help                   print this message
+  --prefix=PREFIX          install in PREFIX [$prefix]
+  --interp-prefix=PREFIX   where to find shared libraries, etc.
+                           use %M for cpu name [$interp_prefix]
+  --target-list=LIST       set target list (default: build everything)
+$(echo Available targets: $default_target_list | \
+  fold -s -w 53 | sed -e 's/^/                           /')
+
+Advanced options (experts only):
+  --source-path=PATH       path of source code [$source_path]
+  --cross-prefix=PREFIX    use PREFIX for compile tools [$cross_prefix]
+  --cc=CC                  use C compiler CC [$cc]
+  --iasl=IASL              use ACPI compiler IASL [$iasl]
+  --host-cc=CC             use C compiler CC [$host_cc] for code run at
+                           build time
+  --cxx=CXX                use C++ compiler CXX [$cxx]
+  --objcc=OBJCC            use Objective-C compiler OBJCC [$objcc]
+  --extra-cflags=CFLAGS    append extra C compiler flags QEMU_CFLAGS
+  --extra-ldflags=LDFLAGS  append extra linker flags LDFLAGS
+  --make=MAKE              use specified make [$make]
+  --install=INSTALL        use specified install [$install]
+  --python=PYTHON          use specified python [$python]
+  --smbd=SMBD              use specified smbd [$smbd]
+  --static                 enable static build [$static]
+  --mandir=PATH            install man pages in PATH
+  --datadir=PATH           install firmware in PATH$confsuffix
+  --docdir=PATH            install documentation in PATH$confsuffix
+  --bindir=PATH            install binaries in PATH
+  --libdir=PATH            install libraries in PATH
+  --sysconfdir=PATH        install config in PATH$confsuffix
+  --localstatedir=PATH     install local state in PATH (set at runtime on win32)
+  --with-confsuffix=SUFFIX suffix for QEMU data inside datadir and sysconfdir [$confsuffix]
+  --enable-debug-tcg       enable TCG debugging
+  --disable-debug-tcg      disable TCG debugging (default)
+  --enable-debug-info       enable debugging information (default)
+  --disable-debug-info      disable debugging information
+  --enable-debug           enable common debug build options
+  --enable-sparse          enable sparse checker
+  --disable-sparse         disable sparse checker (default)
+  --disable-strip          disable stripping binaries
+  --disable-werror         disable compilation abort on warning
+  --disable-sdl            disable SDL
+  --enable-sdl             enable SDL
+  --disable-gtk            disable gtk UI
+  --enable-gtk             enable gtk UI
+  --disable-virtfs         disable VirtFS
+  --enable-virtfs          enable VirtFS
+  --disable-vnc            disable VNC
+  --enable-vnc             enable VNC
+  --disable-cocoa          disable Cocoa (Mac OS X only)
+  --enable-cocoa           enable Cocoa (default on Mac OS X)
+  --audio-drv-list=LIST    set audio drivers list:
+                           Available drivers: $audio_possible_drivers
+  --block-drv-whitelist=L  Same as --block-drv-rw-whitelist=L
+  --block-drv-rw-whitelist=L
+                           set block driver read-write whitelist
+                           (affects only QEMU, not qemu-img)
+  --block-drv-ro-whitelist=L
+                           set block driver read-only whitelist
+                           (affects only QEMU, not qemu-img)
+  --disable-xen            disable xen backend driver support
+  --enable-xen             enable xen backend driver support
+  --disable-xen-pci-passthrough
+  --enable-xen-pci-passthrough
+  --disable-brlapi         disable BrlAPI
+  --enable-brlapi          enable BrlAPI
+  --disable-vnc-tls        disable TLS encryption for VNC server
+  --enable-vnc-tls         enable TLS encryption for VNC server
+  --disable-vnc-sasl       disable SASL encryption for VNC server
+  --enable-vnc-sasl        enable SASL encryption for VNC server
+  --disable-vnc-jpeg       disable JPEG lossy compression for VNC server
+  --enable-vnc-jpeg        enable JPEG lossy compression for VNC server
+  --disable-vnc-png        disable PNG compression for VNC server (default)
+  --enable-vnc-png         enable PNG compression for VNC server
+  --disable-vnc-ws         disable Websockets support for VNC server
+  --enable-vnc-ws          enable Websockets support for VNC server
+  --disable-curses         disable curses output
+  --enable-curses          enable curses output
+  --disable-curl           disable curl connectivity
+  --enable-curl            enable curl connectivity
+  --disable-fdt            disable fdt device tree
+  --enable-fdt             enable fdt device tree
+  --disable-bluez          disable bluez stack connectivity
+  --enable-bluez           enable bluez stack connectivity
+  --disable-slirp          disable SLIRP userspace network connectivity
+  --disable-kvm            disable KVM acceleration support
+  --enable-kvm             enable KVM acceleration support
+  --disable-rdma           disable RDMA-based migration support
+  --enable-rdma            enable RDMA-based migration support
+  --enable-tcg-interpreter enable TCG with bytecode interpreter (TCI)
+  --enable-system          enable all system emulation targets
+  --disable-system         disable all system emulation targets
+  --enable-user            enable supported user emulation targets
+  --disable-user           disable all user emulation targets
+  --enable-linux-user      enable all linux usermode emulation targets
+  --disable-linux-user     disable all linux usermode emulation targets
+  --enable-bsd-user        enable all BSD usermode emulation targets
+  --disable-bsd-user       disable all BSD usermode emulation targets
+  --enable-guest-base      enable GUEST_BASE support for usermode
+                           emulation targets
+  --disable-guest-base     disable GUEST_BASE support
+  --enable-pie             build Position Independent Executables
+  --disable-pie            do not build Position Independent Executables
+  --fmod-lib               path to FMOD library
+  --fmod-inc               path to FMOD includes
+  --oss-lib                path to OSS library
+  --enable-uname-release=R Return R for uname -r in usermode emulation
+  --cpu=CPU                Build for host CPU [$cpu]
+  --disable-uuid           disable uuid support
+  --enable-uuid            enable uuid support
+  --disable-vde            disable support for vde network
+  --enable-vde             enable support for vde network
+  --disable-netmap         disable support for netmap network
+  --enable-netmap          enable support for netmap network
+  --disable-linux-aio      disable Linux AIO support
+  --enable-linux-aio       enable Linux AIO support
+  --disable-cap-ng         disable libcap-ng support
+  --enable-cap-ng          enable libcap-ng support
+  --disable-attr           disables attr and xattr support
+  --enable-attr            enable attr and xattr support
+  --disable-blobs          disable installing provided firmware blobs
+  --enable-docs            enable documentation build
+  --disable-docs           disable documentation build
+  --disable-vhost-net      disable vhost-net acceleration support
+  --enable-vhost-net       enable vhost-net acceleration support
+  --enable-trace-backend=B Set trace backend
+                           Available backends: $($python $source_path/scripts/tracetool.py --list-backends)
+  --with-trace-file=NAME   Full PATH,NAME of file to store traces
+                           Default:trace-<pid>
+  --disable-spice          disable spice
+  --enable-spice           enable spice
+  --enable-rbd             enable building the rados block device (rbd)
+  --disable-libiscsi       disable iscsi support
+  --enable-libiscsi        enable iscsi support
+  --disable-libnfs         disable nfs support
+  --enable-libnfs          enable nfs support
+  --disable-smartcard-nss  disable smartcard nss support
+  --enable-smartcard-nss   enable smartcard nss support
+  --disable-libusb         disable libusb (for usb passthrough)
+  --enable-libusb          enable libusb (for usb passthrough)
+  --disable-usb-redir      disable usb network redirection support
+  --enable-usb-redir       enable usb network redirection support
+  --disable-guest-agent    disable building of the QEMU Guest Agent
+  --enable-guest-agent     enable building of the QEMU Guest Agent
+  --with-vss-sdk=SDK-path  enable Windows VSS support in QEMU Guest Agent
+  --with-win-sdk=SDK-path  path to Windows Platform SDK (to build VSS .tlb)
+  --disable-seccomp        disable seccomp support
+  --enable-seccomp         enables seccomp support
+  --with-coroutine=BACKEND coroutine backend. Supported options:
+                           gthread, ucontext, sigaltstack, windows
+  --disable-coroutine-pool disable coroutine freelist (worse performance)
+  --enable-coroutine-pool  enable coroutine freelist (better performance)
+  --enable-glusterfs       enable GlusterFS backend
+  --disable-glusterfs      disable GlusterFS backend
+  --enable-gcov            enable test coverage analysis with gcov
+  --gcov=GCOV              use specified gcov [$gcov_tool]
+  --enable-tpm             enable TPM support
+  --disable-libssh2        disable ssh block device support
+  --enable-libssh2         enable ssh block device support
+  --disable-vhdx           disables support for the Microsoft VHDX image format
+  --enable-vhdx            enable support for the Microsoft VHDX image format
+
+NOTE: The object files are built at the place where configure is launched
 EOF
-echo "Standard options:"
-echo "  --help                   print this message"
-echo "  --prefix=PREFIX          install in PREFIX [$prefix]"
-echo "  --interp-prefix=PREFIX   where to find shared libraries, etc."
-echo "                           use %M for cpu name [$interp_prefix]"
-echo "  --target-list=LIST       set target list (default: build everything)"
-echo "Available targets: $default_target_list" | \
-    fold -s -w 53 | sed -e 's/^/                           /'
-echo ""
-echo "Advanced options (experts only):"
-echo "  --source-path=PATH       path of source code [$source_path]"
-echo "  --cross-prefix=PREFIX    use PREFIX for compile tools [$cross_prefix]"
-echo "  --cc=CC                  use C compiler CC [$cc]"
-echo "  --iasl=IASL              use ACPI compiler IASL [$iasl]"
-echo "  --host-cc=CC             use C compiler CC [$host_cc] for code run at"
-echo "                           build time"
-echo "  --cxx=CXX                use C++ compiler CXX [$cxx]"
-echo "  --objcc=OBJCC            use Objective-C compiler OBJCC [$objcc]"
-echo "  --extra-cflags=CFLAGS    append extra C compiler flags QEMU_CFLAGS"
-echo "  --extra-ldflags=LDFLAGS  append extra linker flags LDFLAGS"
-echo "  --make=MAKE              use specified make [$make]"
-echo "  --install=INSTALL        use specified install [$install]"
-echo "  --python=PYTHON          use specified python [$python]"
-echo "  --smbd=SMBD              use specified smbd [$smbd]"
-echo "  --static                 enable static build [$static]"
-echo "  --mandir=PATH            install man pages in PATH"
-echo "  --datadir=PATH           install firmware in PATH$confsuffix"
-echo "  --docdir=PATH            install documentation in PATH$confsuffix"
-echo "  --bindir=PATH            install binaries in PATH"
-echo "  --libdir=PATH            install libraries in PATH"
-echo "  --sysconfdir=PATH        install config in PATH$confsuffix"
-echo "  --localstatedir=PATH     install local state in PATH (set at runtime on win32)"
-echo "  --with-confsuffix=SUFFIX suffix for QEMU data inside datadir and sysconfdir [$confsuffix]"
-echo "  --enable-debug-tcg       enable TCG debugging"
-echo "  --disable-debug-tcg      disable TCG debugging (default)"
-echo "  --enable-debug-info       enable debugging information (default)"
-echo "  --disable-debug-info      disable debugging information"
-echo "  --enable-debug           enable common debug build options"
-echo "  --enable-sparse          enable sparse checker"
-echo "  --disable-sparse         disable sparse checker (default)"
-echo "  --disable-strip          disable stripping binaries"
-echo "  --disable-werror         disable compilation abort on warning"
-echo "  --disable-sdl            disable SDL"
-echo "  --enable-sdl             enable SDL"
-echo "  --disable-gtk            disable gtk UI"
-echo "  --enable-gtk             enable gtk UI"
-echo "  --disable-virtfs         disable VirtFS"
-echo "  --enable-virtfs          enable VirtFS"
-echo "  --disable-vnc            disable VNC"
-echo "  --enable-vnc             enable VNC"
-echo "  --disable-cocoa          disable Cocoa (Mac OS X only)"
-echo "  --enable-cocoa           enable Cocoa (default on Mac OS X)"
-echo "  --audio-drv-list=LIST    set audio drivers list:"
-echo "                           Available drivers: $audio_possible_drivers"
-echo "  --block-drv-whitelist=L  Same as --block-drv-rw-whitelist=L"
-echo "  --block-drv-rw-whitelist=L"
-echo "                           set block driver read-write whitelist"
-echo "                           (affects only QEMU, not qemu-img)"
-echo "  --block-drv-ro-whitelist=L"
-echo "                           set block driver read-only whitelist"
-echo "                           (affects only QEMU, not qemu-img)"
-echo "  --disable-xen            disable xen backend driver support"
-echo "  --enable-xen             enable xen backend driver support"
-echo "  --disable-xen-pci-passthrough"
-echo "  --enable-xen-pci-passthrough"
-echo "  --disable-brlapi         disable BrlAPI"
-echo "  --enable-brlapi          enable BrlAPI"
-echo "  --disable-vnc-tls        disable TLS encryption for VNC server"
-echo "  --enable-vnc-tls         enable TLS encryption for VNC server"
-echo "  --disable-vnc-sasl       disable SASL encryption for VNC server"
-echo "  --enable-vnc-sasl        enable SASL encryption for VNC server"
-echo "  --disable-vnc-jpeg       disable JPEG lossy compression for VNC server"
-echo "  --enable-vnc-jpeg        enable JPEG lossy compression for VNC server"
-echo "  --disable-vnc-png        disable PNG compression for VNC server (default)"
-echo "  --enable-vnc-png         enable PNG compression for VNC server"
-echo "  --disable-vnc-ws         disable Websockets support for VNC server"
-echo "  --enable-vnc-ws          enable Websockets support for VNC server"
-echo "  --disable-curses         disable curses output"
-echo "  --enable-curses          enable curses output"
-echo "  --disable-curl           disable curl connectivity"
-echo "  --enable-curl            enable curl connectivity"
-echo "  --disable-fdt            disable fdt device tree"
-echo "  --enable-fdt             enable fdt device tree"
-echo "  --disable-bluez          disable bluez stack connectivity"
-echo "  --enable-bluez           enable bluez stack connectivity"
-echo "  --disable-slirp          disable SLIRP userspace network connectivity"
-echo "  --disable-kvm            disable KVM acceleration support"
-echo "  --enable-kvm             enable KVM acceleration support"
-echo "  --disable-rdma           disable RDMA-based migration support"
-echo "  --enable-rdma            enable RDMA-based migration support"
-echo "  --enable-tcg-interpreter enable TCG with bytecode interpreter (TCI)"
-echo "  --enable-system          enable all system emulation targets"
-echo "  --disable-system         disable all system emulation targets"
-echo "  --enable-user            enable supported user emulation targets"
-echo "  --disable-user           disable all user emulation targets"
-echo "  --enable-linux-user      enable all linux usermode emulation targets"
-echo "  --disable-linux-user     disable all linux usermode emulation targets"
-echo "  --enable-bsd-user        enable all BSD usermode emulation targets"
-echo "  --disable-bsd-user       disable all BSD usermode emulation targets"
-echo "  --enable-guest-base      enable GUEST_BASE support for usermode"
-echo "                           emulation targets"
-echo "  --disable-guest-base     disable GUEST_BASE support"
-echo "  --enable-pie             build Position Independent Executables"
-echo "  --disable-pie            do not build Position Independent Executables"
-echo "  --fmod-lib               path to FMOD library"
-echo "  --fmod-inc               path to FMOD includes"
-echo "  --oss-lib                path to OSS library"
-echo "  --enable-uname-release=R Return R for uname -r in usermode emulation"
-echo "  --cpu=CPU                Build for host CPU [$cpu]"
-echo "  --disable-uuid           disable uuid support"
-echo "  --enable-uuid            enable uuid support"
-echo "  --disable-vde            disable support for vde network"
-echo "  --enable-vde             enable support for vde network"
-echo "  --disable-netmap         disable support for netmap network"
-echo "  --enable-netmap          enable support for netmap network"
-echo "  --disable-linux-aio      disable Linux AIO support"
-echo "  --enable-linux-aio       enable Linux AIO support"
-echo "  --disable-cap-ng         disable libcap-ng support"
-echo "  --enable-cap-ng          enable libcap-ng support"
-echo "  --disable-attr           disables attr and xattr support"
-echo "  --enable-attr            enable attr and xattr support"
-echo "  --disable-blobs          disable installing provided firmware blobs"
-echo "  --enable-docs            enable documentation build"
-echo "  --disable-docs           disable documentation build"
-echo "  --disable-vhost-net      disable vhost-net acceleration support"
-echo "  --enable-vhost-net       enable vhost-net acceleration support"
-echo "  --enable-trace-backend=B Set trace backend"
-echo "                           Available backends:" $($python "$source_path"/scripts/tracetool.py --list-backends)
-echo "  --with-trace-file=NAME   Full PATH,NAME of file to store traces"
-echo "                           Default:trace-<pid>"
-echo "  --disable-spice          disable spice"
-echo "  --enable-spice           enable spice"
-echo "  --enable-rbd             enable building the rados block device (rbd)"
-echo "  --disable-libiscsi       disable iscsi support"
-echo "  --enable-libiscsi        enable iscsi support"
-echo "  --disable-smartcard-nss  disable smartcard nss support"
-echo "  --enable-smartcard-nss   enable smartcard nss support"
-echo "  --disable-libusb         disable libusb (for usb passthrough)"
-echo "  --enable-libusb          enable libusb (for usb passthrough)"
-echo "  --disable-usb-redir      disable usb network redirection support"
-echo "  --enable-usb-redir       enable usb network redirection support"
-echo "  --disable-guest-agent    disable building of the QEMU Guest Agent"
-echo "  --enable-guest-agent     enable building of the QEMU Guest Agent"
-echo "  --with-vss-sdk=SDK-path  enable Windows VSS support in QEMU Guest Agent"
-echo "  --with-win-sdk=SDK-path  path to Windows Platform SDK (to build VSS .tlb)"
-echo "  --disable-seccomp        disable seccomp support"
-echo "  --enable-seccomp         enables seccomp support"
-echo "  --with-coroutine=BACKEND coroutine backend. Supported options:"
-echo "                           gthread, ucontext, sigaltstack, windows"
-echo "  --disable-coroutine-pool disable coroutine freelist (worse performance)"
-echo "  --enable-coroutine-pool  enable coroutine freelist (better performance)"
-echo "  --enable-glusterfs       enable GlusterFS backend"
-echo "  --disable-glusterfs      disable GlusterFS backend"
-echo "  --enable-gcov            enable test coverage analysis with gcov"
-echo "  --gcov=GCOV              use specified gcov [$gcov_tool]"
-echo "  --enable-tpm             enable TPM support"
-echo "  --disable-libssh2        disable ssh block device support"
-echo "  --enable-libssh2         enable ssh block device support"
-echo "  --disable-vhdx           disables support for the Microsoft VHDX image format"
-echo "  --enable-vhdx            enable support for the Microsoft VHDX image format"
-echo ""
-echo "NOTE: The object files are built at the place where configure is launched"
 exit 1
 fi
 
@@ -1419,25 +1446,6 @@ if test "$solaris" = "yes" ; then
   fi
 fi
 
-if ! has $python; then
-  error_exit "Python not found. Use --python=/path/to/python"
-fi
-
-# Note that if the Python conditional here evaluates True we will exit
-# with status 1 which is a shell 'false' value.
-if ! $python -c 'import sys; sys.exit(sys.version_info < (2,4) or sys.version_info >= (3,))'; then
-  error_exit "Cannot use '$python', Python 2.4 or later is required." \
-      "Note that Python 3 or later is not yet supported." \
-      "Use --python=/path/to/python to specify a supported Python."
-fi
-
-# The -B switch was added in Python 2.6.
-# If it is supplied, compiled files are not written.
-# Use it for Python versions which support it.
-if $python -B -c 'import sys; sys.exit(0)' 2>/dev/null; then
-  python="$python -B"
-fi
-
 if test -z "${target_list+xxx}" ; then
     target_list="$default_target_list"
 else
@@ -2701,6 +2709,9 @@ if test "$glusterfs" != "no" ; then
     if $pkg_config --atleast-version=5 glusterfs-api; then
       glusterfs_discard="yes"
     fi
+    if $pkg_config --atleast-version=6 glusterfs-api; then
+      glusterfs_zerofill="yes"
+    fi
   else
     if test "$glusterfs" = "yes" ; then
       feature_not_found "GlusterFS backend support"
@@ -3078,6 +3089,21 @@ EOF
   fi
 fi
 
+# We also need to know the API version because there was an
+# API change from 1.4.0 to 1.5.0.
+if test "$libiscsi" = "yes"; then
+  cat >$TMPC <<EOF
+#include <iscsi/iscsi.h>
+int main(void)
+{
+  iscsi_read10_task(0, 0, 0, 0, 0, 0, 0);
+  return 0;
+}
+EOF
+  if compile_prog "" "-liscsi"; then
+    libiscsi_version="1.4.0"
+  fi
+fi
 
 ##########################################
 # Do we need libm
@@ -3581,6 +3607,20 @@ elif test "$debug" = "no" ; then
   CFLAGS="-O2 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 $CFLAGS"
 fi
 
+##########################################
+# Do we have libnfs
+if test "$libnfs" != "no" ; then
+  if $pkg_config --atleast-version=1.9.2 libnfs; then
+    libnfs="yes"
+    libnfs_libs=$($pkg_config --libs libnfs)
+    LIBS="$LIBS $libnfs_libs"
+  else
+    if test "$libnfs" = "yes" ; then
+      feature_not_found "libnfs"
+    fi
+    libnfs="no"
+  fi
+fi
 
 # Disable zero malloc errors for official releases unless explicitly told to
 # enable/disable
@@ -3805,7 +3845,12 @@ echo "nss used          $smartcard_nss"
 echo "libusb            $libusb"
 echo "usb net redir     $usb_redir"
 echo "GLX support       $glx"
+if test "$libiscsi_version" = "1.4.0"; then
+echo "libiscsi support  $libiscsi (1.4.0)"
+else
 echo "libiscsi support  $libiscsi"
+fi
+echo "libnfs support    $libnfs"
 echo "build guest agent $guest_agent"
 echo "QGA VSS support   $guest_agent_with_vss"
 echo "seccomp support   $seccomp"
@@ -4137,6 +4182,13 @@ fi
 
 if test "$libiscsi" = "yes" ; then
   echo "CONFIG_LIBISCSI=y" >> $config_host_mak
+  if test "$libiscsi_version" = "1.4.0"; then
+    echo "CONFIG_LIBISCSI_1_4=y" >> $config_host_mak
+  fi
+fi
+
+if test "$libnfs" = "yes" ; then
+  echo "CONFIG_LIBNFS=y" >> $config_host_mak
 fi
 
 if test "$seccomp" = "yes"; then
@@ -4207,6 +4259,10 @@ if test "$glusterfs_discard" = "yes" ; then
   echo "CONFIG_GLUSTERFS_DISCARD=y" >> $config_host_mak
 fi
 
+if test "$glusterfs_zerofill" = "yes" ; then
+  echo "CONFIG_GLUSTERFS_ZEROFILL=y" >> $config_host_mak
+fi
+
 if test "$libssh2" = "yes" ; then
   echo "CONFIG_LIBSSH2=y" >> $config_host_mak
 fi
@@ -4611,6 +4667,10 @@ for i in $ARCH $TARGET_BASE_ARCH ; do
   arm)
     echo "CONFIG_ARM_DIS=y"  >> $config_target_mak
     echo "CONFIG_ARM_DIS=y"  >> config-all-disas.mak
+    if test -n "${cxx}"; then
+      echo "CONFIG_ARM_A64_DIS=y"  >> $config_target_mak
+      echo "CONFIG_ARM_A64_DIS=y"  >> config-all-disas.mak
+    fi
   ;;
   cris)
     echo "CONFIG_CRIS_DIS=y"  >> $config_target_mak
@@ -4744,6 +4804,10 @@ for bios_file in \
 do
     FILES="$FILES pc-bios/`basename $bios_file`"
 done
+for test_file in `find $source_path/tests/acpi-test-data -type f`
+do
+    FILES="$FILES tests/acpi-test-data`echo $test_file | sed -e 's/.*acpi-test-data//'`"
+done
 mkdir -p $DIRS
 for f in $FILES ; do
     if [ -e "$source_path/$f" ] && [ "$source_path" != `pwd` ]; then

cpu-exec.c

@@ -53,7 +53,25 @@ void cpu_resume_from_signal(CPUArchState *env, void *puc)
 static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, uint8_t *tb_ptr)
 {
     CPUArchState *env = cpu->env_ptr;
-    uintptr_t next_tb = tcg_qemu_tb_exec(env, tb_ptr);
+    uintptr_t next_tb;
+
+#if defined(DEBUG_DISAS)
+    if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) {
+#if defined(TARGET_I386)
+        log_cpu_state(cpu, CPU_DUMP_CCOP);
+#elif defined(TARGET_M68K)
+        /* ??? Should not modify env state for dumping.  */
+        cpu_m68k_flush_flags(env, env->cc_op);
+        env->cc_op = CC_OP_FLAGS;
+        env->sr = (env->sr & 0xffe0) | env->cc_dest | (env->cc_x << 4);
+        log_cpu_state(cpu, 0);
+#else
+        log_cpu_state(cpu, 0);
+#endif
+    }
+#endif /* DEBUG_DISAS */
+
+    next_tb = tcg_qemu_tb_exec(env, tb_ptr);
     if ((next_tb & TB_EXIT_MASK) > TB_EXIT_IDX1) {
         /* We didn't start executing this TB (eg because the instruction
          * counter hit zero); we must restore the guest PC to the address
@@ -377,7 +395,10 @@ int cpu_exec(CPUArchState *env)
                             /* FIXME: this should respect TPR */
                             cpu_svm_check_intercept_param(env, SVM_EXIT_VINTR,
                                                           0);
-                            intno = ldl_phys(env->vm_vmcb + offsetof(struct vmcb, control.int_vector));
+                            intno = ldl_phys(cpu->as,
+                                             env->vm_vmcb
+                                             + offsetof(struct vmcb,
+                                                        control.int_vector));
                             qemu_log_mask(CPU_LOG_TB_IN_ASM, "Servicing virtual hardware INT=0x%02x\n", intno);
                             do_interrupt_x86_hardirq(env, intno, 1);
                             cpu->interrupt_request &= ~CPU_INTERRUPT_VIRQ;
@@ -582,22 +603,6 @@ int cpu_exec(CPUArchState *env)
                     env->exception_index = EXCP_INTERRUPT;
                     cpu_loop_exit(env);
                 }
-#if defined(DEBUG_DISAS)
-                if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) {
-                    /* restore flags in standard format */
-#if defined(TARGET_I386)
-                    log_cpu_state(cpu, CPU_DUMP_CCOP);
-#elif defined(TARGET_M68K)
-                    cpu_m68k_flush_flags(env, env->cc_op);
-                    env->cc_op = CC_OP_FLAGS;
-                    env->sr = (env->sr & 0xffe0)
-                              | env->cc_dest | (env->cc_x << 4);
-                    log_cpu_state(cpu, 0);
-#else
-                    log_cpu_state(cpu, 0);
-#endif
-                }
-#endif /* DEBUG_DISAS */
                 spin_lock(&tcg_ctx.tb_ctx.tb_lock);
                 tb = tb_find_fast(env);
                 /* Note: we do it here to avoid a gcc bug on Mac OS X when

cpus.c

@@ -1119,6 +1119,8 @@ void resume_all_vcpus(void)
 
 static void qemu_tcg_init_vcpu(CPUState *cpu)
 {
+    tcg_cpu_address_space_init(cpu, cpu->as);
+
     /* share a single thread for all cpus with TCG */
     if (!tcg_cpu_thread) {
         cpu->thread = g_malloc0(sizeof(QemuThread));

cputlb.c

@@ -26,6 +26,7 @@
 #include "exec/cputlb.h"
 
 #include "exec/memory-internal.h"
+#include "exec/ram_addr.h"
 
 //#define DEBUG_TLB
 //#define DEBUG_TLB_CHECK
@@ -112,9 +113,8 @@ void tlb_flush_page(CPUArchState *env, target_ulong addr)
    can be detected */
 void tlb_protect_code(ram_addr_t ram_addr)
 {
-    cpu_physical_memory_reset_dirty(ram_addr,
-                                    ram_addr + TARGET_PAGE_SIZE,
-                                    CODE_DIRTY_FLAG);
+    cpu_physical_memory_reset_dirty(ram_addr, TARGET_PAGE_SIZE,
+                                    DIRTY_MEMORY_CODE);
 }
 
 /* update the TLB so that writes in physical page 'phys_addr' are no longer
@@ -122,7 +122,7 @@ void tlb_protect_code(ram_addr_t ram_addr)
 void tlb_unprotect_code_phys(CPUArchState *env, ram_addr_t ram_addr,
                              target_ulong vaddr)
 {
-    cpu_physical_memory_set_dirty_flags(ram_addr, CODE_DIRTY_FLAG);
+    cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_CODE);
 }
 
 static bool tlb_is_dirty_ram(CPUTLBEntry *tlbe)
@@ -232,6 +232,7 @@ void tlb_set_page(CPUArchState *env, target_ulong vaddr,
     uintptr_t addend;
     CPUTLBEntry *te;
     hwaddr iotlb, xlat, sz;
+    CPUState *cpu = ENV_GET_CPU(env);
 
     assert(size >= TARGET_PAGE_SIZE);
     if (size != TARGET_PAGE_SIZE) {
@@ -239,7 +240,7 @@ void tlb_set_page(CPUArchState *env, target_ulong vaddr,
     }
 
     sz = size;
-    section = address_space_translate_for_iotlb(&address_space_memory, paddr,
+    section = address_space_translate_for_iotlb(cpu->as, paddr,
                                                 &xlat, &sz);
     assert(sz >= TARGET_PAGE_SIZE);
 
@@ -284,7 +285,8 @@ void tlb_set_page(CPUArchState *env, target_ulong vaddr,
             /* Write access calls the I/O callback.  */
             te->addr_write = address | TLB_MMIO;
         } else if (memory_region_is_ram(section->mr)
-                   && !cpu_physical_memory_is_dirty(section->mr->ram_addr + xlat)) {
+                   && cpu_physical_memory_is_clean(section->mr->ram_addr
+                                                   + xlat)) {
             te->addr_write = address | TLB_NOTDIRTY;
         } else {
             te->addr_write = address;
@@ -304,6 +306,7 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
     int mmu_idx, page_index, pd;
     void *p;
     MemoryRegion *mr;
+    CPUState *cpu = ENV_GET_CPU(env1);
 
     page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     mmu_idx = cpu_mmu_index(env1);
@@ -312,9 +315,8 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
         cpu_ldub_code(env1, addr);
     }
     pd = env1->iotlb[mmu_idx][page_index] & ~TARGET_PAGE_MASK;
-    mr = iotlb_to_region(pd);
+    mr = iotlb_to_region(cpu->as, pd);
     if (memory_region_is_unassigned(mr)) {
-        CPUState *cpu = ENV_GET_CPU(env1);
         CPUClass *cc = CPU_GET_CLASS(cpu);
 
         if (cc->do_unassigned_access) {

default-configs/aarch64-linux-user.mak

@@ -0,0 +1,3 @@
+# Default configuration for aarch64-linux-user
+
+CONFIG_GDBSTUB_XML=y

default-configs/arm-softmmu.mak

@@ -27,6 +27,7 @@ CONFIG_SSI_SD=y
 CONFIG_SSI_M25P80=y
 CONFIG_LAN9118=y
 CONFIG_SMC91C111=y
+CONFIG_ALLWINNER_EMAC=y
 CONFIG_DS1338=y
 CONFIG_PFLASH_CFI01=y
 CONFIG_PFLASH_CFI02=y

default-configs/ppc-softmmu.mak

@@ -41,6 +41,7 @@ CONFIG_I8259=y
 CONFIG_XILINX=y
 CONFIG_XILINX_ETHLITE=y
 CONFIG_OPENPIC=y
+CONFIG_PREP=y
 CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
 # For PReP

default-configs/ppc64-softmmu.mak

@@ -42,6 +42,7 @@ CONFIG_XILINX=y
 CONFIG_XILINX_ETHLITE=y
 CONFIG_OPENPIC=y
 CONFIG_PSERIES=y
+CONFIG_PREP=y
 CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
 # For pSeries

default-configs/ppcemb-softmmu.mak

@@ -10,11 +10,9 @@ CONFIG_VGA=y
 CONFIG_VGA_PCI=y
 CONFIG_SERIAL=y
 CONFIG_I8254=y
-CONFIG_PCKBD=y
 CONFIG_FDC=y
 CONFIG_I8257=y
 CONFIG_OPENPIC=y
-CONFIG_PREP_PCI=y
 CONFIG_MACIO=y
 CONFIG_CUDA=y
 CONFIG_ADB=y
@@ -38,6 +36,3 @@ CONFIG_XILINX_ETHLITE=y
 CONFIG_OPENPIC=y
 CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
-# For PReP
-CONFIG_MC146818RTC=y
-CONFIG_ISA_TESTDEV=y

disas.c

@@ -190,7 +190,7 @@ static int print_insn_od_target(bfd_vma pc, disassemble_info *info)
 /* Disassemble this for me please... (debugging). 'flags' has the following
    values:
     i386 - 1 means 16 bit code, 2 means 64 bit code
-    arm  - bit 0 = thumb, bit 1 = reverse endian
+    arm  - bit 0 = thumb, bit 1 = reverse endian, bit 2 = A64
     ppc  - nonzero means little endian
     other targets - unused
  */
@@ -225,7 +225,15 @@ void target_disas(FILE *out, CPUArchState *env, target_ulong code,
     }
     print_insn = print_insn_i386;
 #elif defined(TARGET_ARM)
-    if (flags & 1) {
+    if (flags & 4) {
+        /* We might not be compiled with the A64 disassembler
+         * because it needs a C++ compiler; in that case we will
+         * fall through to the default print_insn_od case.
+         */
+#if defined(CONFIG_ARM_A64_DIS)
+        print_insn = print_insn_arm_a64;
+#endif
+    } else if (flags & 1) {
         print_insn = print_insn_thumb1;
     } else {
         print_insn = print_insn_arm;
@@ -356,6 +364,8 @@ void disas(FILE *out, void *code, unsigned long size)
 #elif defined(_ARCH_PPC)
     s.info.disassembler_options = (char *)"any";
     print_insn = print_insn_ppc;
+#elif defined(__aarch64__) && defined(CONFIG_ARM_A64_DIS)
+    print_insn = print_insn_arm_a64;
 #elif defined(__alpha__)
     print_insn = print_insn_alpha;
 #elif defined(__sparc__)

disas/Makefile.objs

@@ -1,5 +1,10 @@
+
 common-obj-$(CONFIG_ALPHA_DIS) += alpha.o
 common-obj-$(CONFIG_ARM_DIS) += arm.o
+common-obj-$(CONFIG_ARM_A64_DIS) += arm-a64.o
+common-obj-$(CONFIG_ARM_A64_DIS) += libvixl/
+libvixldir = $(SRC_PATH)/disas/libvixl
+$(obj)/arm-a64.o: QEMU_CFLAGS += -I$(libvixldir)
 common-obj-$(CONFIG_CRIS_DIS) += cris.o
 common-obj-$(CONFIG_HPPA_DIS) += hppa.o
 common-obj-$(CONFIG_I386_DIS) += i386.o

disas/arm-a64.cc

@@ -0,0 +1,87 @@
+/*
+ * ARM A64 disassembly output wrapper to libvixl
+ * Copyright (c) 2013 Linaro Limited
+ * Written by Claudio Fontana
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "a64/disasm-a64.h"
+
+extern "C" {
+#include "disas/bfd.h"
+}
+
+using namespace vixl;
+
+static Decoder *vixl_decoder = NULL;
+static Disassembler *vixl_disasm = NULL;
+
+/* We don't use libvixl's PrintDisassembler because its output
+ * is a little unhelpful (trailing newlines, for example).
+ * Instead we use our own very similar variant so we have
+ * control over the format.
+ */
+class QEMUDisassembler : public Disassembler {
+public:
+    explicit QEMUDisassembler(FILE *stream) : stream_(stream) { }
+    ~QEMUDisassembler() { }
+
+protected:
+    void ProcessOutput(Instruction *instr) {
+        fprintf(stream_, "%08" PRIx32 "      %s",
+                instr->InstructionBits(), GetOutput());
+    }
+
+private:
+    FILE *stream_;
+};
+
+static int vixl_is_initialized(void)
+{
+    return vixl_decoder != NULL;
+}
+
+static void vixl_init(FILE *f) {
+    vixl_decoder = new Decoder();
+    vixl_disasm = new QEMUDisassembler(f);
+    vixl_decoder->AppendVisitor(vixl_disasm);
+}
+
+#define INSN_SIZE 4
+
+/* Disassemble ARM A64 instruction. This is our only entry
+ * point from QEMU's C code.
+ */
+int print_insn_arm_a64(uint64_t addr, disassemble_info *info)
+{
+    uint8_t bytes[INSN_SIZE];
+    uint32_t instr;
+    int status;
+
+    status = info->read_memory_func(addr, bytes, INSN_SIZE, info);
+    if (status != 0) {
+        info->memory_error_func(status, addr, info);
+        return -1;
+    }
+
+    if (!vixl_is_initialized()) {
+        vixl_init(info->stream);
+    }
+
+    instr = bytes[0] | bytes[1] << 8 | bytes[2] << 16 | bytes[3] << 24;
+    vixl_decoder->Decode(reinterpret_cast<Instruction*>(&instr));
+
+    return INSN_SIZE;
+}

disas/i386.c

@@ -2632,17 +2632,17 @@ static const struct dis386 prefix_user_table[][4] = {
 
   /* PREGRP87 */
   {
+    { "movbe",	{ Gv, Ev } },
     { "(bad)",	{ XX } },
-    { "(bad)",	{ XX } },
-    { "(bad)",	{ XX } },
+    { "movbe",	{ Gv, Ev } },
     { "crc32",	{ Gdq, { CRC32_Fixup, b_mode } } },
   },
 
   /* PREGRP88 */
   {
+    { "movbe",	{ Ev, Gv } },
     { "(bad)",	{ XX } },
-    { "(bad)",	{ XX } },
-    { "(bad)",	{ XX } },
+    { "movbe",	{ Ev, Gv } },
     { "crc32",	{ Gdq, { CRC32_Fixup, v_mode } } },
   },
 

disas/libvixl/LICENCE

@@ -0,0 +1,30 @@
+LICENCE
+=======
+
+The software in this repository is covered by the following licence.
+
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

disas/libvixl/Makefile.objs

@@ -0,0 +1,8 @@
+libvixl_OBJS = utils.o \
+               a64/instructions-a64.o \
+               a64/decoder-a64.o \
+               a64/disasm-a64.o
+
+$(addprefix $(obj)/,$(libvixl_OBJS)): QEMU_CFLAGS += -I$(SRC_PATH)/disas/libvixl
+
+common-obj-$(CONFIG_ARM_A64_DIS) += $(libvixl_OBJS)

disas/libvixl/README

@@ -0,0 +1,12 @@
+
+The code in this directory is a subset of libvixl:
+ https://github.com/armvixl/vixl
+(specifically, it is the set of files needed for disassembly only,
+taken from libvixl 1.1).
+Bugfixes should preferably be sent upstream initially.
+
+The disassembler does not currently support the entire A64 instruction
+set. Notably:
+ * No Advanced SIMD support.
+ * Limited support for system instructions.
+ * A few miscellaneous integer and floating point instructions are missing.

disas/libvixl/a64/cpu-a64.h

@@ -0,0 +1,56 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef VIXL_CPU_A64_H
+#define VIXL_CPU_A64_H
+
+#include "globals.h"
+
+namespace vixl {
+
+class CPU {
+ public:
+  // Initialise CPU support.
+  static void SetUp();
+
+  // Ensures the data at a given address and with a given size is the same for
+  // the I and D caches. I and D caches are not automatically coherent on ARM
+  // so this operation is required before any dynamically generated code can
+  // safely run.
+  static void EnsureIAndDCacheCoherency(void *address, size_t length);
+
+ private:
+  // Return the content of the cache type register.
+  static uint32_t GetCacheType();
+
+  // I and D cache line size in bytes.
+  static unsigned icache_line_size_;
+  static unsigned dcache_line_size_;
+};
+
+}  // namespace vixl
+
+#endif  // VIXL_CPU_A64_H

disas/libvixl/a64/decoder-a64.cc

@@ -0,0 +1,712 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#include "globals.h"
+#include "utils.h"
+#include "a64/decoder-a64.h"
+
+namespace vixl {
+// Top-level instruction decode function.
+void Decoder::Decode(Instruction *instr) {
+  if (instr->Bits(28, 27) == 0) {
+    VisitUnallocated(instr);
+  } else {
+    switch (instr->Bits(27, 24)) {
+      // 0:   PC relative addressing.
+      case 0x0: DecodePCRelAddressing(instr); break;
+
+      // 1:   Add/sub immediate.
+      case 0x1: DecodeAddSubImmediate(instr); break;
+
+      // A:   Logical shifted register.
+      //      Add/sub with carry.
+      //      Conditional compare register.
+      //      Conditional compare immediate.
+      //      Conditional select.
+      //      Data processing 1 source.
+      //      Data processing 2 source.
+      // B:   Add/sub shifted register.
+      //      Add/sub extended register.
+      //      Data processing 3 source.
+      case 0xA:
+      case 0xB: DecodeDataProcessing(instr); break;
+
+      // 2:   Logical immediate.
+      //      Move wide immediate.
+      case 0x2: DecodeLogical(instr); break;
+
+      // 3:   Bitfield.
+      //      Extract.
+      case 0x3: DecodeBitfieldExtract(instr); break;
+
+      // 4:   Unconditional branch immediate.
+      //      Exception generation.
+      //      Compare and branch immediate.
+      // 5:   Compare and branch immediate.
+      //      Conditional branch.
+      //      System.
+      // 6,7: Unconditional branch.
+      //      Test and branch immediate.
+      case 0x4:
+      case 0x5:
+      case 0x6:
+      case 0x7: DecodeBranchSystemException(instr); break;
+
+      // 8,9: Load/store register pair post-index.
+      //      Load register literal.
+      //      Load/store register unscaled immediate.
+      //      Load/store register immediate post-index.
+      //      Load/store register immediate pre-index.
+      //      Load/store register offset.
+      //      Load/store exclusive.
+      // C,D: Load/store register pair offset.
+      //      Load/store register pair pre-index.
+      //      Load/store register unsigned immediate.
+      //      Advanced SIMD.
+      case 0x8:
+      case 0x9:
+      case 0xC:
+      case 0xD: DecodeLoadStore(instr); break;
+
+      // E:   FP fixed point conversion.
+      //      FP integer conversion.
+      //      FP data processing 1 source.
+      //      FP compare.
+      //      FP immediate.
+      //      FP data processing 2 source.
+      //      FP conditional compare.
+      //      FP conditional select.
+      //      Advanced SIMD.
+      // F:   FP data processing 3 source.
+      //      Advanced SIMD.
+      case 0xE:
+      case 0xF: DecodeFP(instr); break;
+    }
+  }
+}
+
+void Decoder::AppendVisitor(DecoderVisitor* new_visitor) {
+  visitors_.remove(new_visitor);
+  visitors_.push_front(new_visitor);
+}
+
+
+void Decoder::PrependVisitor(DecoderVisitor* new_visitor) {
+  visitors_.remove(new_visitor);
+  visitors_.push_back(new_visitor);
+}
+
+
+void Decoder::InsertVisitorBefore(DecoderVisitor* new_visitor,
+                                  DecoderVisitor* registered_visitor) {
+  visitors_.remove(new_visitor);
+  std::list<DecoderVisitor*>::iterator it;
+  for (it = visitors_.begin(); it != visitors_.end(); it++) {
+    if (*it == registered_visitor) {
+      visitors_.insert(it, new_visitor);
+      return;
+    }
+  }
+  // We reached the end of the list. The last element must be
+  // registered_visitor.
+  ASSERT(*it == registered_visitor);
+  visitors_.insert(it, new_visitor);
+}
+
+
+void Decoder::InsertVisitorAfter(DecoderVisitor* new_visitor,
+                                 DecoderVisitor* registered_visitor) {
+  visitors_.remove(new_visitor);
+  std::list<DecoderVisitor*>::iterator it;
+  for (it = visitors_.begin(); it != visitors_.end(); it++) {
+    if (*it == registered_visitor) {
+      it++;
+      visitors_.insert(it, new_visitor);
+      return;
+    }
+  }
+  // We reached the end of the list. The last element must be
+  // registered_visitor.
+  ASSERT(*it == registered_visitor);
+  visitors_.push_back(new_visitor);
+}
+
+
+void Decoder::RemoveVisitor(DecoderVisitor* visitor) {
+  visitors_.remove(visitor);
+}
+
+
+void Decoder::DecodePCRelAddressing(Instruction* instr) {
+  ASSERT(instr->Bits(27, 24) == 0x0);
+  // We know bit 28 is set, as <b28:b27> = 0 is filtered out at the top level
+  // decode.
+  ASSERT(instr->Bit(28) == 0x1);
+  VisitPCRelAddressing(instr);
+}
+
+
+void Decoder::DecodeBranchSystemException(Instruction* instr) {
+  ASSERT((instr->Bits(27, 24) == 0x4) ||
+         (instr->Bits(27, 24) == 0x5) ||
+         (instr->Bits(27, 24) == 0x6) ||
+         (instr->Bits(27, 24) == 0x7) );
+
+  switch (instr->Bits(31, 29)) {
+    case 0:
+    case 4: {
+      VisitUnconditionalBranch(instr);
+      break;
+    }
+    case 1:
+    case 5: {
+      if (instr->Bit(25) == 0) {
+        VisitCompareBranch(instr);
+      } else {
+        VisitTestBranch(instr);
+      }
+      break;
+    }
+    case 2: {
+      if (instr->Bit(25) == 0) {
+        if ((instr->Bit(24) == 0x1) ||
+            (instr->Mask(0x01000010) == 0x00000010)) {
+          VisitUnallocated(instr);
+        } else {
+          VisitConditionalBranch(instr);
+        }
+      } else {
+        VisitUnallocated(instr);
+      }
+      break;
+    }
+    case 6: {
+      if (instr->Bit(25) == 0) {
+        if (instr->Bit(24) == 0) {
+          if ((instr->Bits(4, 2) != 0) ||
+              (instr->Mask(0x00E0001D) == 0x00200001) ||
+              (instr->Mask(0x00E0001D) == 0x00400001) ||
+              (instr->Mask(0x00E0001E) == 0x00200002) ||
+              (instr->Mask(0x00E0001E) == 0x00400002) ||
+              (instr->Mask(0x00E0001C) == 0x00600000) ||
+              (instr->Mask(0x00E0001C) == 0x00800000) ||
+              (instr->Mask(0x00E0001F) == 0x00A00000) ||
+              (instr->Mask(0x00C0001C) == 0x00C00000)) {
+            VisitUnallocated(instr);
+          } else {
+            VisitException(instr);
+          }
+        } else {
+          if (instr->Bits(23, 22) == 0) {
+            const Instr masked_003FF0E0 = instr->Mask(0x003FF0E0);
+            if ((instr->Bits(21, 19) == 0x4) ||
+                (masked_003FF0E0 == 0x00033000) ||
+                (masked_003FF0E0 == 0x003FF020) ||
+                (masked_003FF0E0 == 0x003FF060) ||
+                (masked_003FF0E0 == 0x003FF0E0) ||
+                (instr->Mask(0x00388000) == 0x00008000) ||
+                (instr->Mask(0x0038E000) == 0x00000000) ||
+                (instr->Mask(0x0039E000) == 0x00002000) ||
+                (instr->Mask(0x003AE000) == 0x00002000) ||
+                (instr->Mask(0x003CE000) == 0x00042000) ||
+                (instr->Mask(0x003FFFC0) == 0x000320C0) ||
+                (instr->Mask(0x003FF100) == 0x00032100) ||
+                (instr->Mask(0x003FF200) == 0x00032200) ||
+                (instr->Mask(0x003FF400) == 0x00032400) ||
+                (instr->Mask(0x003FF800) == 0x00032800) ||
+                (instr->Mask(0x0038F000) == 0x00005000) ||
+                (instr->Mask(0x0038E000) == 0x00006000)) {
+              VisitUnallocated(instr);
+            } else {
+              VisitSystem(instr);
+            }
+          } else {
+            VisitUnallocated(instr);
+          }
+        }
+      } else {
+        if ((instr->Bit(24) == 0x1) ||
+            (instr->Bits(20, 16) != 0x1F) ||
+            (instr->Bits(15, 10) != 0) ||
+            (instr->Bits(4, 0) != 0) ||
+            (instr->Bits(24, 21) == 0x3) ||
+            (instr->Bits(24, 22) == 0x3)) {
+          VisitUnallocated(instr);
+        } else {
+          VisitUnconditionalBranchToRegister(instr);
+        }
+      }
+      break;
+    }
+    case 3:
+    case 7: {
+      VisitUnallocated(instr);
+      break;
+    }
+  }
+}
+
+
+void Decoder::DecodeLoadStore(Instruction* instr) {
+  ASSERT((instr->Bits(27, 24) == 0x8) ||
+         (instr->Bits(27, 24) == 0x9) ||
+         (instr->Bits(27, 24) == 0xC) ||
+         (instr->Bits(27, 24) == 0xD) );
+
+  if (instr->Bit(24) == 0) {
+    if (instr->Bit(28) == 0) {
+      if (instr->Bit(29) == 0) {
+        if (instr->Bit(26) == 0) {
+          // TODO: VisitLoadStoreExclusive.
+          VisitUnimplemented(instr);
+        } else {
+          DecodeAdvSIMDLoadStore(instr);
+        }
+      } else {
+        if ((instr->Bits(31, 30) == 0x3) ||
+            (instr->Mask(0xC4400000) == 0x40000000)) {
+          VisitUnallocated(instr);
+        } else {
+          if (instr->Bit(23) == 0) {
+            if (instr->Mask(0xC4400000) == 0xC0400000) {
+              VisitUnallocated(instr);
+            } else {
+              VisitLoadStorePairNonTemporal(instr);
+            }
+          } else {
+            VisitLoadStorePairPostIndex(instr);
+          }
+        }
+      }
+    } else {
+      if (instr->Bit(29) == 0) {
+        if (instr->Mask(0xC4000000) == 0xC4000000) {
+          VisitUnallocated(instr);
+        } else {
+          VisitLoadLiteral(instr);
+        }
+      } else {
+        if ((instr->Mask(0x84C00000) == 0x80C00000) ||
+            (instr->Mask(0x44800000) == 0x44800000) ||
+            (instr->Mask(0x84800000) == 0x84800000)) {
+          VisitUnallocated(instr);
+        } else {
+          if (instr->Bit(21) == 0) {
+            switch (instr->Bits(11, 10)) {
+              case 0: {
+                VisitLoadStoreUnscaledOffset(instr);
+                break;
+              }
+              case 1: {
+                if (instr->Mask(0xC4C00000) == 0xC0800000) {
+                  VisitUnallocated(instr);
+                } else {
+                  VisitLoadStorePostIndex(instr);
+                }
+                break;
+              }
+              case 2: {
+                // TODO: VisitLoadStoreRegisterOffsetUnpriv.
+                VisitUnimplemented(instr);
+                break;
+              }
+              case 3: {
+                if (instr->Mask(0xC4C00000) == 0xC0800000) {
+                  VisitUnallocated(instr);
+                } else {
+                  VisitLoadStorePreIndex(instr);
+                }
+                break;
+              }
+            }
+          } else {
+            if (instr->Bits(11, 10) == 0x2) {
+              if (instr->Bit(14) == 0) {
+                VisitUnallocated(instr);
+              } else {
+                VisitLoadStoreRegisterOffset(instr);
+              }
+            } else {
+              VisitUnallocated(instr);
+            }
+          }
+        }
+      }
+    }
+  } else {
+    if (instr->Bit(28) == 0) {
+      if (instr->Bit(29) == 0) {
+        VisitUnallocated(instr);
+      } else {
+        if ((instr->Bits(31, 30) == 0x3) ||
+            (instr->Mask(0xC4400000) == 0x40000000)) {
+          VisitUnallocated(instr);
+        } else {
+          if (instr->Bit(23) == 0) {
+            VisitLoadStorePairOffset(instr);
+          } else {
+            VisitLoadStorePairPreIndex(instr);
+          }
+        }
+      }
+    } else {
+      if (instr->Bit(29) == 0) {
+        VisitUnallocated(instr);
+      } else {
+        if ((instr->Mask(0x84C00000) == 0x80C00000) ||
+            (instr->Mask(0x44800000) == 0x44800000) ||
+            (instr->Mask(0x84800000) == 0x84800000)) {
+          VisitUnallocated(instr);
+        } else {
+          VisitLoadStoreUnsignedOffset(instr);
+        }
+      }
+    }
+  }
+}
+
+
+void Decoder::DecodeLogical(Instruction* instr) {
+  ASSERT(instr->Bits(27, 24) == 0x2);
+
+  if (instr->Mask(0x80400000) == 0x00400000) {
+    VisitUnallocated(instr);
+  } else {
+    if (instr->Bit(23) == 0) {
+      VisitLogicalImmediate(instr);
+    } else {
+      if (instr->Bits(30, 29) == 0x1) {
+        VisitUnallocated(instr);
+      } else {
+        VisitMoveWideImmediate(instr);
+      }
+    }
+  }
+}
+
+
+void Decoder::DecodeBitfieldExtract(Instruction* instr) {
+  ASSERT(instr->Bits(27, 24) == 0x3);
+
+  if ((instr->Mask(0x80400000) == 0x80000000) ||
+      (instr->Mask(0x80400000) == 0x00400000) ||
+      (instr->Mask(0x80008000) == 0x00008000)) {
+    VisitUnallocated(instr);
+  } else if (instr->Bit(23) == 0) {
+    if ((instr->Mask(0x80200000) == 0x00200000) ||
+        (instr->Mask(0x60000000) == 0x60000000)) {
+      VisitUnallocated(instr);
+    } else {
+      VisitBitfield(instr);
+    }
+  } else {
+    if ((instr->Mask(0x60200000) == 0x00200000) ||
+        (instr->Mask(0x60000000) != 0x00000000)) {
+      VisitUnallocated(instr);
+    } else {
+      VisitExtract(instr);
+    }
+  }
+}
+
+
+void Decoder::DecodeAddSubImmediate(Instruction* instr) {
+  ASSERT(instr->Bits(27, 24) == 0x1);
+  if (instr->Bit(23) == 1) {
+    VisitUnallocated(instr);
+  } else {
+    VisitAddSubImmediate(instr);
+  }
+}
+
+
+void Decoder::DecodeDataProcessing(Instruction* instr) {
+  ASSERT((instr->Bits(27, 24) == 0xA) ||
+         (instr->Bits(27, 24) == 0xB) );
+
+  if (instr->Bit(24) == 0) {
+    if (instr->Bit(28) == 0) {
+      if (instr->Mask(0x80008000) == 0x00008000) {
+        VisitUnallocated(instr);
+      } else {
+        VisitLogicalShifted(instr);
+      }
+    } else {
+      switch (instr->Bits(23, 21)) {
+        case 0: {
+          if (instr->Mask(0x0000FC00) != 0) {
+            VisitUnallocated(instr);
+          } else {
+            VisitAddSubWithCarry(instr);
+          }
+          break;
+        }
+        case 2: {
+          if ((instr->Bit(29) == 0) ||
+              (instr->Mask(0x00000410) != 0)) {
+            VisitUnallocated(instr);
+          } else {
+            if (instr->Bit(11) == 0) {
+              VisitConditionalCompareRegister(instr);
+            } else {
+              VisitConditionalCompareImmediate(instr);
+            }
+          }
+          break;
+        }
+        case 4: {
+          if (instr->Mask(0x20000800) != 0x00000000) {
+            VisitUnallocated(instr);
+          } else {
+            VisitConditionalSelect(instr);
+          }
+          break;
+        }
+        case 6: {
+          if (instr->Bit(29) == 0x1) {
+            VisitUnallocated(instr);
+          } else {
+            if (instr->Bit(30) == 0) {
+              if ((instr->Bit(15) == 0x1) ||
+                  (instr->Bits(15, 11) == 0) ||
+                  (instr->Bits(15, 12) == 0x1) ||
+                  (instr->Bits(15, 12) == 0x3) ||
+                  (instr->Bits(15, 13) == 0x3) ||
+                  (instr->Mask(0x8000EC00) == 0x00004C00) ||
+                  (instr->Mask(0x8000E800) == 0x80004000) ||
+                  (instr->Mask(0x8000E400) == 0x80004000)) {
+                VisitUnallocated(instr);
+              } else {
+                VisitDataProcessing2Source(instr);
+              }
+            } else {
+              if ((instr->Bit(13) == 1) ||
+                  (instr->Bits(20, 16) != 0) ||
+                  (instr->Bits(15, 14) != 0) ||
+                  (instr->Mask(0xA01FFC00) == 0x00000C00) ||
+                  (instr->Mask(0x201FF800) == 0x00001800)) {
+                VisitUnallocated(instr);
+              } else {
+                VisitDataProcessing1Source(instr);
+              }
+            }
+            break;
+          }
+        }
+        case 1:
+        case 3:
+        case 5:
+        case 7: VisitUnallocated(instr); break;
+      }
+    }
+  } else {
+    if (instr->Bit(28) == 0) {
+     if (instr->Bit(21) == 0) {
+        if ((instr->Bits(23, 22) == 0x3) ||
+            (instr->Mask(0x80008000) == 0x00008000)) {
+          VisitUnallocated(instr);
+        } else {
+          VisitAddSubShifted(instr);
+        }
+      } else {
+        if ((instr->Mask(0x00C00000) != 0x00000000) ||
+            (instr->Mask(0x00001400) == 0x00001400) ||
+            (instr->Mask(0x00001800) == 0x00001800)) {
+          VisitUnallocated(instr);
+        } else {
+          VisitAddSubExtended(instr);
+        }
+      }
+    } else {
+      if ((instr->Bit(30) == 0x1) ||
+          (instr->Bits(30, 29) == 0x1) ||
+          (instr->Mask(0xE0600000) == 0x00200000) ||
+          (instr->Mask(0xE0608000) == 0x00400000) ||
+          (instr->Mask(0x60608000) == 0x00408000) ||
+          (instr->Mask(0x60E00000) == 0x00E00000) ||
+          (instr->Mask(0x60E00000) == 0x00800000) ||
+          (instr->Mask(0x60E00000) == 0x00600000)) {
+        VisitUnallocated(instr);
+      } else {
+        VisitDataProcessing3Source(instr);
+      }
+    }
+  }
+}
+
+
+void Decoder::DecodeFP(Instruction* instr) {
+  ASSERT((instr->Bits(27, 24) == 0xE) ||
+         (instr->Bits(27, 24) == 0xF) );
+
+  if (instr->Bit(28) == 0) {
+    DecodeAdvSIMDDataProcessing(instr);
+  } else {
+    if (instr->Bit(29) == 1) {
+      VisitUnallocated(instr);
+    } else {
+      if (instr->Bits(31, 30) == 0x3) {
+        VisitUnallocated(instr);
+      } else if (instr->Bits(31, 30) == 0x1) {
+        DecodeAdvSIMDDataProcessing(instr);
+      } else {
+        if (instr->Bit(24) == 0) {
+          if (instr->Bit(21) == 0) {
+            if ((instr->Bit(23) == 1) ||
+                (instr->Bit(18) == 1) ||
+                (instr->Mask(0x80008000) == 0x00000000) ||
+                (instr->Mask(0x000E0000) == 0x00000000) ||
+                (instr->Mask(0x000E0000) == 0x000A0000) ||
+                (instr->Mask(0x00160000) == 0x00000000) ||
+                (instr->Mask(0x00160000) == 0x00120000)) {
+              VisitUnallocated(instr);
+            } else {
+              VisitFPFixedPointConvert(instr);
+            }
+          } else {
+            if (instr->Bits(15, 10) == 32) {
+              VisitUnallocated(instr);
+            } else if (instr->Bits(15, 10) == 0) {
+              if ((instr->Bits(23, 22) == 0x3) ||
+                  (instr->Mask(0x000E0000) == 0x000A0000) ||
+                  (instr->Mask(0x000E0000) == 0x000C0000) ||
+                  (instr->Mask(0x00160000) == 0x00120000) ||
+                  (instr->Mask(0x00160000) == 0x00140000) ||
+                  (instr->Mask(0x20C40000) == 0x00800000) ||
+                  (instr->Mask(0x20C60000) == 0x00840000) ||
+                  (instr->Mask(0xA0C60000) == 0x80060000) ||
+                  (instr->Mask(0xA0C60000) == 0x00860000) ||
+                  (instr->Mask(0xA0C60000) == 0x00460000) ||
+                  (instr->Mask(0xA0CE0000) == 0x80860000) ||
+                  (instr->Mask(0xA0CE0000) == 0x804E0000) ||
+                  (instr->Mask(0xA0CE0000) == 0x000E0000) ||
+                  (instr->Mask(0xA0D60000) == 0x00160000) ||
+                  (instr->Mask(0xA0D60000) == 0x80560000) ||
+                  (instr->Mask(0xA0D60000) == 0x80960000)) {
+                VisitUnallocated(instr);
+              } else {
+                VisitFPIntegerConvert(instr);
+              }
+            } else if (instr->Bits(14, 10) == 16) {
+              const Instr masked_A0DF8000 = instr->Mask(0xA0DF8000);
+              if ((instr->Mask(0x80180000) != 0) ||
+                  (masked_A0DF8000 == 0x00020000) ||
+                  (masked_A0DF8000 == 0x00030000) ||
+                  (masked_A0DF8000 == 0x00068000) ||
+                  (masked_A0DF8000 == 0x00428000) ||
+                  (masked_A0DF8000 == 0x00430000) ||
+                  (masked_A0DF8000 == 0x00468000) ||
+                  (instr->Mask(0xA0D80000) == 0x00800000) ||
+                  (instr->Mask(0xA0DE0000) == 0x00C00000) ||
+                  (instr->Mask(0xA0DF0000) == 0x00C30000) ||
+                  (instr->Mask(0xA0DC0000) == 0x00C40000)) {
+                VisitUnallocated(instr);
+              } else {
+                VisitFPDataProcessing1Source(instr);
+              }
+            } else if (instr->Bits(13, 10) == 8) {
+              if ((instr->Bits(15, 14) != 0) ||
+                  (instr->Bits(2, 0) != 0) ||
+                  (instr->Mask(0x80800000) != 0x00000000)) {
+                VisitUnallocated(instr);
+              } else {
+                VisitFPCompare(instr);
+              }
+            } else if (instr->Bits(12, 10) == 4) {
+              if ((instr->Bits(9, 5) != 0) ||
+                  (instr->Mask(0x80800000) != 0x00000000)) {
+                VisitUnallocated(instr);
+              } else {
+                VisitFPImmediate(instr);
+              }
+            } else {
+              if (instr->Mask(0x80800000) != 0x00000000) {
+                VisitUnallocated(instr);
+              } else {
+                switch (instr->Bits(11, 10)) {
+                  case 1: {
+                    VisitFPConditionalCompare(instr);
+                    break;
+                  }
+                  case 2: {
+                    if ((instr->Bits(15, 14) == 0x3) ||
+                        (instr->Mask(0x00009000) == 0x00009000) ||
+                        (instr->Mask(0x0000A000) == 0x0000A000)) {
+                      VisitUnallocated(instr);
+                    } else {
+                      VisitFPDataProcessing2Source(instr);
+                    }
+                    break;
+                  }
+                  case 3: {
+                    VisitFPConditionalSelect(instr);
+                    break;
+                  }
+                  default: UNREACHABLE();
+                }
+              }
+            }
+          }
+        } else {
+          // Bit 30 == 1 has been handled earlier.
+          ASSERT(instr->Bit(30) == 0);
+          if (instr->Mask(0xA0800000) != 0) {
+            VisitUnallocated(instr);
+          } else {
+            VisitFPDataProcessing3Source(instr);
+          }
+        }
+      }
+    }
+  }
+}
+
+
+void Decoder::DecodeAdvSIMDLoadStore(Instruction* instr) {
+  // TODO: Implement Advanced SIMD load/store instruction decode.
+  ASSERT(instr->Bits(29, 25) == 0x6);
+  VisitUnimplemented(instr);
+}
+
+
+void Decoder::DecodeAdvSIMDDataProcessing(Instruction* instr) {
+  // TODO: Implement Advanced SIMD data processing instruction decode.
+  ASSERT(instr->Bits(27, 25) == 0x7);
+  VisitUnimplemented(instr);
+}
+
+
+#define DEFINE_VISITOR_CALLERS(A)                                              \
+  void Decoder::Visit##A(Instruction *instr) {                                 \
+    ASSERT(instr->Mask(A##FMask) == A##Fixed);                                 \
+    std::list<DecoderVisitor*>::iterator it;                                   \
+    for (it = visitors_.begin(); it != visitors_.end(); it++) {                \
+      (*it)->Visit##A(instr);                                                  \
+    }                                                                          \
+  }
+VISITOR_LIST(DEFINE_VISITOR_CALLERS)
+#undef DEFINE_VISITOR_CALLERS
+}  // namespace vixl

disas/libvixl/a64/decoder-a64.h

@@ -0,0 +1,198 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef VIXL_A64_DECODER_A64_H_
+#define VIXL_A64_DECODER_A64_H_
+
+#include <list>
+
+#include "globals.h"
+#include "a64/instructions-a64.h"
+
+
+// List macro containing all visitors needed by the decoder class.
+
+#define VISITOR_LIST(V)             \
+  V(PCRelAddressing)                \
+  V(AddSubImmediate)                \
+  V(LogicalImmediate)               \
+  V(MoveWideImmediate)              \
+  V(Bitfield)                       \
+  V(Extract)                        \
+  V(UnconditionalBranch)            \
+  V(UnconditionalBranchToRegister)  \
+  V(CompareBranch)                  \
+  V(TestBranch)                     \
+  V(ConditionalBranch)              \
+  V(System)                         \
+  V(Exception)                      \
+  V(LoadStorePairPostIndex)         \
+  V(LoadStorePairOffset)            \
+  V(LoadStorePairPreIndex)          \
+  V(LoadStorePairNonTemporal)       \
+  V(LoadLiteral)                    \
+  V(LoadStoreUnscaledOffset)        \
+  V(LoadStorePostIndex)             \
+  V(LoadStorePreIndex)              \
+  V(LoadStoreRegisterOffset)        \
+  V(LoadStoreUnsignedOffset)        \
+  V(LogicalShifted)                 \
+  V(AddSubShifted)                  \
+  V(AddSubExtended)                 \
+  V(AddSubWithCarry)                \
+  V(ConditionalCompareRegister)     \
+  V(ConditionalCompareImmediate)    \
+  V(ConditionalSelect)              \
+  V(DataProcessing1Source)          \
+  V(DataProcessing2Source)          \
+  V(DataProcessing3Source)          \
+  V(FPCompare)                      \
+  V(FPConditionalCompare)           \
+  V(FPConditionalSelect)            \
+  V(FPImmediate)                    \
+  V(FPDataProcessing1Source)        \
+  V(FPDataProcessing2Source)        \
+  V(FPDataProcessing3Source)        \
+  V(FPIntegerConvert)               \
+  V(FPFixedPointConvert)            \
+  V(Unallocated)                    \
+  V(Unimplemented)
+
+namespace vixl {
+
+// The Visitor interface. Disassembler and simulator (and other tools)
+// must provide implementations for all of these functions.
+class DecoderVisitor {
+ public:
+  #define DECLARE(A) virtual void Visit##A(Instruction* instr) = 0;
+  VISITOR_LIST(DECLARE)
+  #undef DECLARE
+
+  virtual ~DecoderVisitor() {}
+
+ private:
+  // Visitors are registered in a list.
+  std::list<DecoderVisitor*> visitors_;
+
+  friend class Decoder;
+};
+
+
+class Decoder: public DecoderVisitor {
+ public:
+  Decoder() {}
+
+  // Top-level instruction decoder function. Decodes an instruction and calls
+  // the visitor functions registered with the Decoder class.
+  void Decode(Instruction *instr);
+
+  // Register a new visitor class with the decoder.
+  // Decode() will call the corresponding visitor method from all registered
+  // visitor classes when decoding reaches the leaf node of the instruction
+  // decode tree.
+  // Visitors are called in the order.
+  // A visitor can only be registered once.
+  // Registering an already registered visitor will update its position.
+  //
+  //   d.AppendVisitor(V1);
+  //   d.AppendVisitor(V2);
+  //   d.PrependVisitor(V2);            // Move V2 at the start of the list.
+  //   d.InsertVisitorBefore(V3, V2);
+  //   d.AppendVisitor(V4);
+  //   d.AppendVisitor(V4);             // No effect.
+  //
+  //   d.Decode(i);
+  //
+  // will call in order visitor methods in V3, V2, V1, V4.
+  void AppendVisitor(DecoderVisitor* visitor);
+  void PrependVisitor(DecoderVisitor* visitor);
+  void InsertVisitorBefore(DecoderVisitor* new_visitor,
+                           DecoderVisitor* registered_visitor);
+  void InsertVisitorAfter(DecoderVisitor* new_visitor,
+                          DecoderVisitor* registered_visitor);
+
+  // Remove a previously registered visitor class from the list of visitors
+  // stored by the decoder.
+  void RemoveVisitor(DecoderVisitor* visitor);
+
+  #define DECLARE(A) void Visit##A(Instruction* instr);
+  VISITOR_LIST(DECLARE)
+  #undef DECLARE
+
+ private:
+  // Decode the PC relative addressing instruction, and call the corresponding
+  // visitors.
+  // On entry, instruction bits 27:24 = 0x0.
+  void DecodePCRelAddressing(Instruction* instr);
+
+  // Decode the add/subtract immediate instruction, and call the correspoding
+  // visitors.
+  // On entry, instruction bits 27:24 = 0x1.
+  void DecodeAddSubImmediate(Instruction* instr);
+
+  // Decode the branch, system command, and exception generation parts of
+  // the instruction tree, and call the corresponding visitors.
+  // On entry, instruction bits 27:24 = {0x4, 0x5, 0x6, 0x7}.
+  void DecodeBranchSystemException(Instruction* instr);
+
+  // Decode the load and store parts of the instruction tree, and call
+  // the corresponding visitors.
+  // On entry, instruction bits 27:24 = {0x8, 0x9, 0xC, 0xD}.
+  void DecodeLoadStore(Instruction* instr);
+
+  // Decode the logical immediate and move wide immediate parts of the
+  // instruction tree, and call the corresponding visitors.
+  // On entry, instruction bits 27:24 = 0x2.
+  void DecodeLogical(Instruction* instr);
+
+  // Decode the bitfield and extraction parts of the instruction tree,
+  // and call the corresponding visitors.
+  // On entry, instruction bits 27:24 = 0x3.
+  void DecodeBitfieldExtract(Instruction* instr);
+
+  // Decode the data processing parts of the instruction tree, and call the
+  // corresponding visitors.
+  // On entry, instruction bits 27:24 = {0x1, 0xA, 0xB}.
+  void DecodeDataProcessing(Instruction* instr);
+
+  // Decode the floating point parts of the instruction tree, and call the
+  // corresponding visitors.
+  // On entry, instruction bits 27:24 = {0xE, 0xF}.
+  void DecodeFP(Instruction* instr);
+
+  // Decode the Advanced SIMD (NEON) load/store part of the instruction tree,
+  // and call the corresponding visitors.
+  // On entry, instruction bits 29:25 = 0x6.
+  void DecodeAdvSIMDLoadStore(Instruction* instr);
+
+  // Decode the Advanced SIMD (NEON) data processing part of the instruction
+  // tree, and call the corresponding visitors.
+  // On entry, instruction bits 27:25 = 0x7.
+  void DecodeAdvSIMDDataProcessing(Instruction* instr);
+};
+}  // namespace vixl
+
+#endif  // VIXL_A64_DECODER_A64_H_

disas/libvixl/a64/disasm-a64.h

@@ -0,0 +1,109 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef VIXL_A64_DISASM_A64_H
+#define VIXL_A64_DISASM_A64_H
+
+#include "globals.h"
+#include "utils.h"
+#include "instructions-a64.h"
+#include "decoder-a64.h"
+
+namespace vixl {
+
+class Disassembler: public DecoderVisitor {
+ public:
+  Disassembler();
+  Disassembler(char* text_buffer, int buffer_size);
+  virtual ~Disassembler();
+  char* GetOutput();
+
+  // Declare all Visitor functions.
+  #define DECLARE(A)  void Visit##A(Instruction* instr);
+  VISITOR_LIST(DECLARE)
+  #undef DECLARE
+
+ protected:
+  virtual void ProcessOutput(Instruction* instr);
+
+ private:
+  void Format(Instruction* instr, const char* mnemonic, const char* format);
+  void Substitute(Instruction* instr, const char* string);
+  int SubstituteField(Instruction* instr, const char* format);
+  int SubstituteRegisterField(Instruction* instr, const char* format);
+  int SubstituteImmediateField(Instruction* instr, const char* format);
+  int SubstituteLiteralField(Instruction* instr, const char* format);
+  int SubstituteBitfieldImmediateField(Instruction* instr, const char* format);
+  int SubstituteShiftField(Instruction* instr, const char* format);
+  int SubstituteExtendField(Instruction* instr, const char* format);
+  int SubstituteConditionField(Instruction* instr, const char* format);
+  int SubstitutePCRelAddressField(Instruction* instr, const char* format);
+  int SubstituteBranchTargetField(Instruction* instr, const char* format);
+  int SubstituteLSRegOffsetField(Instruction* instr, const char* format);
+  int SubstitutePrefetchField(Instruction* instr, const char* format);
+
+  inline bool RdIsZROrSP(Instruction* instr) const {
+    return (instr->Rd() == kZeroRegCode);
+  }
+
+  inline bool RnIsZROrSP(Instruction* instr) const {
+    return (instr->Rn() == kZeroRegCode);
+  }
+
+  inline bool RmIsZROrSP(Instruction* instr) const {
+    return (instr->Rm() == kZeroRegCode);
+  }
+
+  inline bool RaIsZROrSP(Instruction* instr) const {
+    return (instr->Ra() == kZeroRegCode);
+  }
+
+  bool IsMovzMovnImm(unsigned reg_size, uint64_t value);
+
+  void ResetOutput();
+  void AppendToOutput(const char* string, ...);
+
+  char* buffer_;
+  uint32_t buffer_pos_;
+  uint32_t buffer_size_;
+  bool own_buffer_;
+};
+
+
+class PrintDisassembler: public Disassembler {
+ public:
+  explicit PrintDisassembler(FILE* stream) : stream_(stream) { }
+  ~PrintDisassembler() { }
+
+ protected:
+  virtual void ProcessOutput(Instruction* instr);
+
+ private:
+  FILE *stream_;
+};
+}  // namespace vixl
+
+#endif  // VIXL_A64_DISASM_A64_H

disas/libvixl/a64/instructions-a64.cc

@@ -0,0 +1,238 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#include "a64/instructions-a64.h"
+#include "a64/assembler-a64.h"
+
+namespace vixl {
+
+
+static uint64_t RotateRight(uint64_t value,
+                            unsigned int rotate,
+                            unsigned int width) {
+  ASSERT(width <= 64);
+  rotate &= 63;
+  return ((value & ((1UL << rotate) - 1UL)) << (width - rotate)) |
+         (value >> rotate);
+}
+
+
+static uint64_t RepeatBitsAcrossReg(unsigned reg_size,
+                                    uint64_t value,
+                                    unsigned width) {
+  ASSERT((width == 2) || (width == 4) || (width == 8) || (width == 16) ||
+         (width == 32));
+  ASSERT((reg_size == kWRegSize) || (reg_size == kXRegSize));
+  uint64_t result = value & ((1UL << width) - 1UL);
+  for (unsigned i = width; i < reg_size; i *= 2) {
+    result |= (result << i);
+  }
+  return result;
+}
+
+
+// Logical immediates can't encode zero, so a return value of zero is used to
+// indicate a failure case. Specifically, where the constraints on imm_s are
+// not met.
+uint64_t Instruction::ImmLogical() {
+  unsigned reg_size = SixtyFourBits() ? kXRegSize : kWRegSize;
+  int64_t n = BitN();
+  int64_t imm_s = ImmSetBits();
+  int64_t imm_r = ImmRotate();
+
+  // An integer is constructed from the n, imm_s and imm_r bits according to
+  // the following table:
+  //
+  //  N   imms    immr    size        S             R
+  //  1  ssssss  rrrrrr    64    UInt(ssssss)  UInt(rrrrrr)
+  //  0  0sssss  xrrrrr    32    UInt(sssss)   UInt(rrrrr)
+  //  0  10ssss  xxrrrr    16    UInt(ssss)    UInt(rrrr)
+  //  0  110sss  xxxrrr     8    UInt(sss)     UInt(rrr)
+  //  0  1110ss  xxxxrr     4    UInt(ss)      UInt(rr)
+  //  0  11110s  xxxxxr     2    UInt(s)       UInt(r)
+  // (s bits must not be all set)
+  //
+  // A pattern is constructed of size bits, where the least significant S+1
+  // bits are set. The pattern is rotated right by R, and repeated across a
+  // 32 or 64-bit value, depending on destination register width.
+  //
+
+  if (n == 1) {
+    if (imm_s == 0x3F) {
+      return 0;
+    }
+    uint64_t bits = (1UL << (imm_s + 1)) - 1;
+    return RotateRight(bits, imm_r, 64);
+  } else {
+    if ((imm_s >> 1) == 0x1F) {
+      return 0;
+    }
+    for (int width = 0x20; width >= 0x2; width >>= 1) {
+      if ((imm_s & width) == 0) {
+        int mask = width - 1;
+        if ((imm_s & mask) == mask) {
+          return 0;
+        }
+        uint64_t bits = (1UL << ((imm_s & mask) + 1)) - 1;
+        return RepeatBitsAcrossReg(reg_size,
+                                   RotateRight(bits, imm_r & mask, width),
+                                   width);
+      }
+    }
+  }
+  UNREACHABLE();
+  return 0;
+}
+
+
+float Instruction::ImmFP32() {
+  //  ImmFP: abcdefgh (8 bits)
+  // Single: aBbb.bbbc.defg.h000.0000.0000.0000.0000 (32 bits)
+  // where B is b ^ 1
+  uint32_t bits = ImmFP();
+  uint32_t bit7 = (bits >> 7) & 0x1;
+  uint32_t bit6 = (bits >> 6) & 0x1;
+  uint32_t bit5_to_0 = bits & 0x3f;
+  uint32_t result = (bit7 << 31) | ((32 - bit6) << 25) | (bit5_to_0 << 19);
+
+  return rawbits_to_float(result);
+}
+
+
+double Instruction::ImmFP64() {
+  //  ImmFP: abcdefgh (8 bits)
+  // Double: aBbb.bbbb.bbcd.efgh.0000.0000.0000.0000
+  //         0000.0000.0000.0000.0000.0000.0000.0000 (64 bits)
+  // where B is b ^ 1
+  uint32_t bits = ImmFP();
+  uint64_t bit7 = (bits >> 7) & 0x1;
+  uint64_t bit6 = (bits >> 6) & 0x1;
+  uint64_t bit5_to_0 = bits & 0x3f;
+  uint64_t result = (bit7 << 63) | ((256 - bit6) << 54) | (bit5_to_0 << 48);
+
+  return rawbits_to_double(result);
+}
+
+
+LSDataSize CalcLSPairDataSize(LoadStorePairOp op) {
+  switch (op) {
+    case STP_x:
+    case LDP_x:
+    case STP_d:
+    case LDP_d: return LSDoubleWord;
+    default: return LSWord;
+  }
+}
+
+
+Instruction* Instruction::ImmPCOffsetTarget() {
+  ptrdiff_t offset;
+  if (IsPCRelAddressing()) {
+    // PC-relative addressing. Only ADR is supported.
+    offset = ImmPCRel();
+  } else {
+    // All PC-relative branches.
+    ASSERT(BranchType() != UnknownBranchType);
+    // Relative branch offsets are instruction-size-aligned.
+    offset = ImmBranch() << kInstructionSizeLog2;
+  }
+  return this + offset;
+}
+
+
+inline int Instruction::ImmBranch() const {
+  switch (BranchType()) {
+    case CondBranchType: return ImmCondBranch();
+    case UncondBranchType: return ImmUncondBranch();
+    case CompareBranchType: return ImmCmpBranch();
+    case TestBranchType: return ImmTestBranch();
+    default: UNREACHABLE();
+  }
+  return 0;
+}
+
+
+void Instruction::SetImmPCOffsetTarget(Instruction* target) {
+  if (IsPCRelAddressing()) {
+    SetPCRelImmTarget(target);
+  } else {
+    SetBranchImmTarget(target);
+  }
+}
+
+
+void Instruction::SetPCRelImmTarget(Instruction* target) {
+  // ADRP is not supported, so 'this' must point to an ADR instruction.
+  ASSERT(Mask(PCRelAddressingMask) == ADR);
+
+  Instr imm = Assembler::ImmPCRelAddress(target - this);
+
+  SetInstructionBits(Mask(~ImmPCRel_mask) | imm);
+}
+
+
+void Instruction::SetBranchImmTarget(Instruction* target) {
+  ASSERT(((target - this) & 3) == 0);
+  Instr branch_imm = 0;
+  uint32_t imm_mask = 0;
+  int offset = (target - this) >> kInstructionSizeLog2;
+  switch (BranchType()) {
+    case CondBranchType: {
+      branch_imm = Assembler::ImmCondBranch(offset);
+      imm_mask = ImmCondBranch_mask;
+      break;
+    }
+    case UncondBranchType: {
+      branch_imm = Assembler::ImmUncondBranch(offset);
+      imm_mask = ImmUncondBranch_mask;
+      break;
+    }
+    case CompareBranchType: {
+      branch_imm = Assembler::ImmCmpBranch(offset);
+      imm_mask = ImmCmpBranch_mask;
+      break;
+    }
+    case TestBranchType: {
+      branch_imm = Assembler::ImmTestBranch(offset);
+      imm_mask = ImmTestBranch_mask;
+      break;
+    }
+    default: UNREACHABLE();
+  }
+  SetInstructionBits(Mask(~imm_mask) | branch_imm);
+}
+
+
+void Instruction::SetImmLLiteral(Instruction* source) {
+  ASSERT(((source - this) & 3) == 0);
+  int offset = (source - this) >> kLiteralEntrySizeLog2;
+  Instr imm = Assembler::ImmLLiteral(offset);
+  Instr mask = ImmLLiteral_mask;
+
+  SetInstructionBits(Mask(~mask) | imm);
+}
+}  // namespace vixl
+

disas/libvixl/a64/instructions-a64.h

@@ -0,0 +1,344 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef VIXL_A64_INSTRUCTIONS_A64_H_
+#define VIXL_A64_INSTRUCTIONS_A64_H_
+
+#include "globals.h"
+#include "utils.h"
+#include "a64/constants-a64.h"
+
+namespace vixl {
+// ISA constants. --------------------------------------------------------------
+
+typedef uint32_t Instr;
+const unsigned kInstructionSize = 4;
+const unsigned kInstructionSizeLog2 = 2;
+const unsigned kLiteralEntrySize = 4;
+const unsigned kLiteralEntrySizeLog2 = 2;
+const unsigned kMaxLoadLiteralRange = 1 * MBytes;
+
+const unsigned kWRegSize = 32;
+const unsigned kWRegSizeLog2 = 5;
+const unsigned kWRegSizeInBytes = kWRegSize / 8;
+const unsigned kXRegSize = 64;
+const unsigned kXRegSizeLog2 = 6;
+const unsigned kXRegSizeInBytes = kXRegSize / 8;
+const unsigned kSRegSize = 32;
+const unsigned kSRegSizeLog2 = 5;
+const unsigned kSRegSizeInBytes = kSRegSize / 8;
+const unsigned kDRegSize = 64;
+const unsigned kDRegSizeLog2 = 6;
+const unsigned kDRegSizeInBytes = kDRegSize / 8;
+const int64_t kWRegMask = 0x00000000ffffffffLL;
+const int64_t kXRegMask = 0xffffffffffffffffLL;
+const int64_t kSRegMask = 0x00000000ffffffffLL;
+const int64_t kDRegMask = 0xffffffffffffffffLL;
+const int64_t kXSignMask = 0x1LL << 63;
+const int64_t kWSignMask = 0x1LL << 31;
+const int64_t kByteMask = 0xffL;
+const int64_t kHalfWordMask = 0xffffL;
+const int64_t kWordMask = 0xffffffffLL;
+const uint64_t kXMaxUInt = 0xffffffffffffffffULL;
+const uint64_t kWMaxUInt = 0xffffffffULL;
+const int64_t kXMaxInt = 0x7fffffffffffffffLL;
+const int64_t kXMinInt = 0x8000000000000000LL;
+const int32_t kWMaxInt = 0x7fffffff;
+const int32_t kWMinInt = 0x80000000;
+const unsigned kLinkRegCode = 30;
+const unsigned kZeroRegCode = 31;
+const unsigned kSPRegInternalCode = 63;
+const unsigned kRegCodeMask = 0x1f;
+
+// AArch64 floating-point specifics. These match IEEE-754.
+const unsigned kDoubleMantissaBits = 52;
+const unsigned kDoubleExponentBits = 11;
+const unsigned kFloatMantissaBits = 23;
+const unsigned kFloatExponentBits = 8;
+
+const float kFP32PositiveInfinity = rawbits_to_float(0x7f800000);
+const float kFP32NegativeInfinity = rawbits_to_float(0xff800000);
+const double kFP64PositiveInfinity = rawbits_to_double(0x7ff0000000000000ULL);
+const double kFP64NegativeInfinity = rawbits_to_double(0xfff0000000000000ULL);
+
+// This value is a signalling NaN as both a double and as a float (taking the
+// least-significant word).
+static const double kFP64SignallingNaN = rawbits_to_double(0x7ff000007f800001ULL);
+static const float kFP32SignallingNaN = rawbits_to_float(0x7f800001);
+
+// A similar value, but as a quiet NaN.
+static const double kFP64QuietNaN = rawbits_to_double(0x7ff800007fc00001ULL);
+static const float kFP32QuietNaN = rawbits_to_float(0x7fc00001);
+
+enum LSDataSize {
+  LSByte        = 0,
+  LSHalfword    = 1,
+  LSWord        = 2,
+  LSDoubleWord  = 3
+};
+
+LSDataSize CalcLSPairDataSize(LoadStorePairOp op);
+
+enum ImmBranchType {
+  UnknownBranchType = 0,
+  CondBranchType    = 1,
+  UncondBranchType  = 2,
+  CompareBranchType = 3,
+  TestBranchType    = 4
+};
+
+enum AddrMode {
+  Offset,
+  PreIndex,
+  PostIndex
+};
+
+enum FPRounding {
+  // The first four values are encodable directly by FPCR<RMode>.
+  FPTieEven = 0x0,
+  FPPositiveInfinity = 0x1,
+  FPNegativeInfinity = 0x2,
+  FPZero = 0x3,
+
+  // The final rounding mode is only available when explicitly specified by the
+  // instruction (such as with fcvta). It cannot be set in FPCR.
+  FPTieAway
+};
+
+enum Reg31Mode {
+  Reg31IsStackPointer,
+  Reg31IsZeroRegister
+};
+
+// Instructions. ---------------------------------------------------------------
+
+class Instruction {
+ public:
+  inline Instr InstructionBits() const {
+    return *(reinterpret_cast<const Instr*>(this));
+  }
+
+  inline void SetInstructionBits(Instr new_instr) {
+    *(reinterpret_cast<Instr*>(this)) = new_instr;
+  }
+
+  inline int Bit(int pos) const {
+    return (InstructionBits() >> pos) & 1;
+  }
+
+  inline uint32_t Bits(int msb, int lsb) const {
+    return unsigned_bitextract_32(msb, lsb, InstructionBits());
+  }
+
+  inline int32_t SignedBits(int msb, int lsb) const {
+    int32_t bits = *(reinterpret_cast<const int32_t*>(this));
+    return signed_bitextract_32(msb, lsb, bits);
+  }
+
+  inline Instr Mask(uint32_t mask) const {
+    return InstructionBits() & mask;
+  }
+
+  #define DEFINE_GETTER(Name, HighBit, LowBit, Func)             \
+  inline int64_t Name() const { return Func(HighBit, LowBit); }
+  INSTRUCTION_FIELDS_LIST(DEFINE_GETTER)
+  #undef DEFINE_GETTER
+
+  // ImmPCRel is a compound field (not present in INSTRUCTION_FIELDS_LIST),
+  // formed from ImmPCRelLo and ImmPCRelHi.
+  int ImmPCRel() const {
+    int const offset = ((ImmPCRelHi() << ImmPCRelLo_width) | ImmPCRelLo());
+    int const width = ImmPCRelLo_width + ImmPCRelHi_width;
+    return signed_bitextract_32(width-1, 0, offset);
+  }
+
+  uint64_t ImmLogical();
+  float ImmFP32();
+  double ImmFP64();
+
+  inline LSDataSize SizeLSPair() const {
+    return CalcLSPairDataSize(
+             static_cast<LoadStorePairOp>(Mask(LoadStorePairMask)));
+  }
+
+  // Helpers.
+  inline bool IsCondBranchImm() const {
+    return Mask(ConditionalBranchFMask) == ConditionalBranchFixed;
+  }
+
+  inline bool IsUncondBranchImm() const {
+    return Mask(UnconditionalBranchFMask) == UnconditionalBranchFixed;
+  }
+
+  inline bool IsCompareBranch() const {
+    return Mask(CompareBranchFMask) == CompareBranchFixed;
+  }
+
+  inline bool IsTestBranch() const {
+    return Mask(TestBranchFMask) == TestBranchFixed;
+  }
+
+  inline bool IsPCRelAddressing() const {
+    return Mask(PCRelAddressingFMask) == PCRelAddressingFixed;
+  }
+
+  inline bool IsLogicalImmediate() const {
+    return Mask(LogicalImmediateFMask) == LogicalImmediateFixed;
+  }
+
+  inline bool IsAddSubImmediate() const {
+    return Mask(AddSubImmediateFMask) == AddSubImmediateFixed;
+  }
+
+  inline bool IsAddSubExtended() const {
+    return Mask(AddSubExtendedFMask) == AddSubExtendedFixed;
+  }
+
+  inline bool IsLoadOrStore() const {
+    return Mask(LoadStoreAnyFMask) == LoadStoreAnyFixed;
+  }
+
+  inline bool IsMovn() const {
+    return (Mask(MoveWideImmediateMask) == MOVN_x) ||
+           (Mask(MoveWideImmediateMask) == MOVN_w);
+  }
+
+  // Indicate whether Rd can be the stack pointer or the zero register. This
+  // does not check that the instruction actually has an Rd field.
+  inline Reg31Mode RdMode() const {
+    // The following instructions use sp or wsp as Rd:
+    //  Add/sub (immediate) when not setting the flags.
+    //  Add/sub (extended) when not setting the flags.
+    //  Logical (immediate) when not setting the flags.
+    // Otherwise, r31 is the zero register.
+    if (IsAddSubImmediate() || IsAddSubExtended()) {
+      if (Mask(AddSubSetFlagsBit)) {
+        return Reg31IsZeroRegister;
+      } else {
+        return Reg31IsStackPointer;
+      }
+    }
+    if (IsLogicalImmediate()) {
+      // Of the logical (immediate) instructions, only ANDS (and its aliases)
+      // can set the flags. The others can all write into sp.
+      // Note that some logical operations are not available to
+      // immediate-operand instructions, so we have to combine two masks here.
+      if (Mask(LogicalImmediateMask & LogicalOpMask) == ANDS) {
+        return Reg31IsZeroRegister;
+      } else {
+        return Reg31IsStackPointer;
+      }
+    }
+    return Reg31IsZeroRegister;
+  }
+
+  // Indicate whether Rn can be the stack pointer or the zero register. This
+  // does not check that the instruction actually has an Rn field.
+  inline Reg31Mode RnMode() const {
+    // The following instructions use sp or wsp as Rn:
+    //  All loads and stores.
+    //  Add/sub (immediate).
+    //  Add/sub (extended).
+    // Otherwise, r31 is the zero register.
+    if (IsLoadOrStore() || IsAddSubImmediate() || IsAddSubExtended()) {
+      return Reg31IsStackPointer;
+    }
+    return Reg31IsZeroRegister;
+  }
+
+  inline ImmBranchType BranchType() const {
+    if (IsCondBranchImm()) {
+      return CondBranchType;
+    } else if (IsUncondBranchImm()) {
+      return UncondBranchType;
+    } else if (IsCompareBranch()) {
+      return CompareBranchType;
+    } else if (IsTestBranch()) {
+      return TestBranchType;
+    } else {
+      return UnknownBranchType;
+    }
+  }
+
+  // Find the target of this instruction. 'this' may be a branch or a
+  // PC-relative addressing instruction.
+  Instruction* ImmPCOffsetTarget();
+
+  // Patch a PC-relative offset to refer to 'target'. 'this' may be a branch or
+  // a PC-relative addressing instruction.
+  void SetImmPCOffsetTarget(Instruction* target);
+  // Patch a literal load instruction to load from 'source'.
+  void SetImmLLiteral(Instruction* source);
+
+  inline uint8_t* LiteralAddress() {
+    int offset = ImmLLiteral() << kLiteralEntrySizeLog2;
+    return reinterpret_cast<uint8_t*>(this) + offset;
+  }
+
+  inline uint32_t Literal32() {
+    uint32_t literal;
+    memcpy(&literal, LiteralAddress(), sizeof(literal));
+
+    return literal;
+  }
+
+  inline uint64_t Literal64() {
+    uint64_t literal;
+    memcpy(&literal, LiteralAddress(), sizeof(literal));
+
+    return literal;
+  }
+
+  inline float LiteralFP32() {
+    return rawbits_to_float(Literal32());
+  }
+
+  inline double LiteralFP64() {
+    return rawbits_to_double(Literal64());
+  }
+
+  inline Instruction* NextInstruction() {
+    return this + kInstructionSize;
+  }
+
+  inline Instruction* InstructionAtOffset(int64_t offset) {
+    ASSERT(IsWordAligned(this + offset));
+    return this + offset;
+  }
+
+  template<typename T> static inline Instruction* Cast(T src) {
+    return reinterpret_cast<Instruction*>(src);
+  }
+
+ private:
+  inline int ImmBranch() const;
+
+  void SetPCRelImmTarget(Instruction* target);
+  void SetBranchImmTarget(Instruction* target);
+};
+}  // namespace vixl
+
+#endif  // VIXL_A64_INSTRUCTIONS_A64_H_

disas/libvixl/globals.h

@@ -0,0 +1,65 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef VIXL_GLOBALS_H
+#define VIXL_GLOBALS_H
+
+// Get the standard printf format macros for C99 stdint types.
+#define __STDC_FORMAT_MACROS
+#include <inttypes.h>
+
+#include <assert.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <stddef.h>
+#include "platform.h"
+
+
+typedef uint8_t byte;
+
+const int KBytes = 1024;
+const int MBytes = 1024 * KBytes;
+
+  #define ABORT() printf("in %s, line %i", __FILE__, __LINE__); abort()
+#ifdef DEBUG
+  #define ASSERT(condition) assert(condition)
+  #define CHECK(condition) ASSERT(condition)
+  #define UNIMPLEMENTED() printf("UNIMPLEMENTED\t"); ABORT()
+  #define UNREACHABLE() printf("UNREACHABLE\t"); ABORT()
+#else
+  #define ASSERT(condition) ((void) 0)
+  #define CHECK(condition) assert(condition)
+  #define UNIMPLEMENTED() ((void) 0)
+  #define UNREACHABLE() ((void) 0)
+#endif
+
+template <typename T> inline void USE(T) {}
+
+#define ALIGNMENT_EXCEPTION() printf("ALIGNMENT EXCEPTION\t"); ABORT()
+
+#endif  // VIXL_GLOBALS_H

disas/libvixl/platform.h

@@ -0,0 +1,43 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef PLATFORM_H
+#define PLATFORM_H
+
+// Define platform specific functionalities.
+
+namespace vixl {
+#ifdef USE_SIMULATOR
+// Currently we assume running the simulator implies running on x86 hardware.
+inline void HostBreakpoint() { asm("int3"); }
+#else
+inline void HostBreakpoint() {
+  // TODO: Implement HostBreakpoint on a64.
+}
+#endif
+}  // namespace vixl
+
+#endif

disas/libvixl/utils.cc

@@ -0,0 +1,120 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#include "utils.h"
+#include <stdio.h>
+
+namespace vixl {
+
+uint32_t float_to_rawbits(float value) {
+  uint32_t bits = 0;
+  memcpy(&bits, &value, 4);
+  return bits;
+}
+
+
+uint64_t double_to_rawbits(double value) {
+  uint64_t bits = 0;
+  memcpy(&bits, &value, 8);
+  return bits;
+}
+
+
+float rawbits_to_float(uint32_t bits) {
+  float value = 0.0;
+  memcpy(&value, &bits, 4);
+  return value;
+}
+
+
+double rawbits_to_double(uint64_t bits) {
+  double value = 0.0;
+  memcpy(&value, &bits, 8);
+  return value;
+}
+
+
+int CountLeadingZeros(uint64_t value, int width) {
+  ASSERT((width == 32) || (width == 64));
+  int count = 0;
+  uint64_t bit_test = 1UL << (width - 1);
+  while ((count < width) && ((bit_test & value) == 0)) {
+    count++;
+    bit_test >>= 1;
+  }
+  return count;
+}
+
+
+int CountLeadingSignBits(int64_t value, int width) {
+  ASSERT((width == 32) || (width == 64));
+  if (value >= 0) {
+    return CountLeadingZeros(value, width) - 1;
+  } else {
+    return CountLeadingZeros(~value, width) - 1;
+  }
+}
+
+
+int CountTrailingZeros(uint64_t value, int width) {
+  ASSERT((width == 32) || (width == 64));
+  int count = 0;
+  while ((count < width) && (((value >> count) & 1) == 0)) {
+    count++;
+  }
+  return count;
+}
+
+
+int CountSetBits(uint64_t value, int width) {
+  // TODO: Other widths could be added here, as the implementation already
+  // supports them.
+  ASSERT((width == 32) || (width == 64));
+
+  // Mask out unused bits to ensure that they are not counted.
+  value &= (0xffffffffffffffffUL >> (64-width));
+
+  // Add up the set bits.
+  // The algorithm works by adding pairs of bit fields together iteratively,
+  // where the size of each bit field doubles each time.
+  // An example for an 8-bit value:
+  // Bits:  h  g  f  e  d  c  b  a
+  //         \ |   \ |   \ |   \ |
+  // value = h+g   f+e   d+c   b+a
+  //            \    |      \    |
+  // value =   h+g+f+e     d+c+b+a
+  //                  \          |
+  // value =       h+g+f+e+d+c+b+a
+  value = ((value >> 1) & 0x5555555555555555) + (value & 0x5555555555555555);
+  value = ((value >> 2) & 0x3333333333333333) + (value & 0x3333333333333333);
+  value = ((value >> 4) & 0x0f0f0f0f0f0f0f0f) + (value & 0x0f0f0f0f0f0f0f0f);
+  value = ((value >> 8) & 0x00ff00ff00ff00ff) + (value & 0x00ff00ff00ff00ff);
+  value = ((value >> 16) & 0x0000ffff0000ffff) + (value & 0x0000ffff0000ffff);
+  value = ((value >> 32) & 0x00000000ffffffff) + (value & 0x00000000ffffffff);
+
+  return value;
+}
+}  // namespace vixl

disas/libvixl/utils.h

@@ -0,0 +1,126 @@
+// Copyright 2013, ARM Limited
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+//
+//   * Redistributions of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//   * Redistributions in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//   * Neither the name of ARM Limited nor the names of its contributors may be
+//     used to endorse or promote products derived from this software without
+//     specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
+// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+#ifndef VIXL_UTILS_H
+#define VIXL_UTILS_H
+
+
+#include <string.h>
+#include "globals.h"
+
+namespace vixl {
+
+// Check number width.
+inline bool is_intn(unsigned n, int64_t x) {
+  ASSERT((0 < n) && (n < 64));
+  int64_t limit = 1ULL << (n - 1);
+  return (-limit <= x) && (x < limit);
+}
+
+inline bool is_uintn(unsigned n, int64_t x) {
+  ASSERT((0 < n) && (n < 64));
+  return !(x >> n);
+}
+
+inline unsigned truncate_to_intn(unsigned n, int64_t x) {
+  ASSERT((0 < n) && (n < 64));
+  return (x & ((1ULL << n) - 1));
+}
+
+#define INT_1_TO_63_LIST(V)                                                    \
+V(1)  V(2)  V(3)  V(4)  V(5)  V(6)  V(7)  V(8)                                 \
+V(9)  V(10) V(11) V(12) V(13) V(14) V(15) V(16)                                \
+V(17) V(18) V(19) V(20) V(21) V(22) V(23) V(24)                                \
+V(25) V(26) V(27) V(28) V(29) V(30) V(31) V(32)                                \
+V(33) V(34) V(35) V(36) V(37) V(38) V(39) V(40)                                \
+V(41) V(42) V(43) V(44) V(45) V(46) V(47) V(48)                                \
+V(49) V(50) V(51) V(52) V(53) V(54) V(55) V(56)                                \
+V(57) V(58) V(59) V(60) V(61) V(62) V(63)
+
+#define DECLARE_IS_INT_N(N)                                                    \
+inline bool is_int##N(int64_t x) { return is_intn(N, x); }
+#define DECLARE_IS_UINT_N(N)                                                   \
+inline bool is_uint##N(int64_t x) { return is_uintn(N, x); }
+#define DECLARE_TRUNCATE_TO_INT_N(N)                                           \
+inline int truncate_to_int##N(int x) { return truncate_to_intn(N, x); }
+INT_1_TO_63_LIST(DECLARE_IS_INT_N)
+INT_1_TO_63_LIST(DECLARE_IS_UINT_N)
+INT_1_TO_63_LIST(DECLARE_TRUNCATE_TO_INT_N)
+#undef DECLARE_IS_INT_N
+#undef DECLARE_IS_UINT_N
+#undef DECLARE_TRUNCATE_TO_INT_N
+
+// Bit field extraction.
+inline uint32_t unsigned_bitextract_32(int msb, int lsb, uint32_t x) {
+  return (x >> lsb) & ((1 << (1 + msb - lsb)) - 1);
+}
+
+inline uint64_t unsigned_bitextract_64(int msb, int lsb, uint64_t x) {
+  return (x >> lsb) & ((static_cast<uint64_t>(1) << (1 + msb - lsb)) - 1);
+}
+
+inline int32_t signed_bitextract_32(int msb, int lsb, int32_t x) {
+  return (x << (31 - msb)) >> (lsb + 31 - msb);
+}
+
+inline int64_t signed_bitextract_64(int msb, int lsb, int64_t x) {
+  return (x << (63 - msb)) >> (lsb + 63 - msb);
+}
+
+// floating point representation
+uint32_t float_to_rawbits(float value);
+uint64_t double_to_rawbits(double value);
+float rawbits_to_float(uint32_t bits);
+double rawbits_to_double(uint64_t bits);
+
+// Bits counting.
+int CountLeadingZeros(uint64_t value, int width);
+int CountLeadingSignBits(int64_t value, int width);
+int CountTrailingZeros(uint64_t value, int width);
+int CountSetBits(uint64_t value, int width);
+
+// Pointer alignment
+// TODO: rename/refactor to make it specific to instructions.
+template<typename T>
+bool IsWordAligned(T pointer) {
+  ASSERT(sizeof(pointer) == sizeof(intptr_t));   // NOLINT(runtime/sizeof)
+  return (reinterpret_cast<intptr_t>(pointer) & 3) == 0;
+}
+
+// Increment a pointer until it has the specified alignment.
+template<class T>
+T AlignUp(T pointer, size_t alignment) {
+  ASSERT(sizeof(pointer) == sizeof(uintptr_t));
+  uintptr_t pointer_raw = reinterpret_cast<uintptr_t>(pointer);
+  size_t align_step = (alignment - pointer_raw) % alignment;
+  ASSERT((pointer_raw + align_step) % alignment == 0);
+  return reinterpret_cast<T>(pointer_raw + align_step);
+}
+
+
+}  // namespace vixl
+
+#endif  // VIXL_UTILS_H

docs/qmp/qmp-events.txt

@@ -479,7 +479,7 @@ Data: None.
 
 Example:
 
-{ "event": "WATCHDOG",
+{ "event": "WAKEUP",
      "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
 
 WATCHDOG

docs/specs/acpi_cpu_hotplug.txt

@@ -10,7 +10,9 @@ ACPI GPE block (IO ports 0xafe0-0xafe3, byte access):
 Generic ACPI GPE block. Bit 2 (GPE.2) used to notify CPU
 hot-add/remove event to ACPI BIOS, via SCI interrupt.
 
-CPU present bitmap (IO port 0xaf00-0xaf1f, 1-byte access):
+CPU present bitmap for:
+  ICH9-LPC (IO port 0x0cd8-0xcf7, 1-byte access)
+  PIIX-PM  (IO port 0xaf00-0xaf1f, 1-byte access)
 ---------------------------------------------------------------
 One bit per CPU. Bit position reflects corresponding CPU APIC ID.
 Read-only.

exec.c

@@ -50,6 +50,7 @@
 #include "translate-all.h"
 
 #include "exec/memory-internal.h"
+#include "exec/ram_addr.h"
 #include "qemu/cache-utils.h"
 
 #include "qemu/range.h"
@@ -57,7 +58,7 @@
 //#define DEBUG_SUBPAGE
 
 #if !defined(CONFIG_USER_ONLY)
-static int in_migration;
+static bool in_migration;
 
 RAMList ram_list = { .blocks = QTAILQ_HEAD_INITIALIZER(ram_list.blocks) };
 
@@ -137,6 +138,7 @@ typedef struct subpage_t {
 
 static void io_mem_init(void);
 static void memory_map_init(void);
+static void tcg_commit(MemoryListener *listener);
 
 static MemoryRegion io_mem_watch;
 #endif
@@ -338,6 +340,18 @@ address_space_translate_internal(AddressSpaceDispatch *d, hwaddr addr, hwaddr *x
     return section;
 }
 
+static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
+{
+    if (memory_region_is_ram(mr)) {
+        return !(is_write && mr->readonly);
+    }
+    if (memory_region_is_romd(mr)) {
+        return !is_write;
+    }
+
+    return false;
+}
+
 MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr,
                                       hwaddr *xlat, hwaddr *plen,
                                       bool is_write)
@@ -367,6 +381,11 @@ MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr,
         as = iotlb.target_as;
     }
 
+    if (memory_access_is_direct(mr, is_write)) {
+        hwaddr page = ((addr & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE) - addr;
+        len = MIN(page, len);
+    }
+
     *plen = len;
     *xlat = addr;
     return mr;
@@ -435,6 +454,22 @@ CPUState *qemu_get_cpu(int index)
     return NULL;
 }
 
+#if !defined(CONFIG_USER_ONLY)
+void tcg_cpu_address_space_init(CPUState *cpu, AddressSpace *as)
+{
+    /* We only support one address space per cpu at the moment.  */
+    assert(cpu->as == as);
+
+    if (cpu->tcg_as_listener) {
+        memory_listener_unregister(cpu->tcg_as_listener);
+    } else {
+        cpu->tcg_as_listener = g_new0(MemoryListener, 1);
+    }
+    cpu->tcg_as_listener->commit = tcg_commit;
+    memory_listener_register(cpu->tcg_as_listener, as);
+}
+#endif
+
 void cpu_exec_init(CPUArchState *env)
 {
     CPUState *cpu = ENV_GET_CPU(env);
@@ -454,6 +489,7 @@ void cpu_exec_init(CPUArchState *env)
     QTAILQ_INIT(&env->breakpoints);
     QTAILQ_INIT(&env->watchpoints);
 #ifndef CONFIG_USER_ONLY
+    cpu->as = &address_space_memory;
     cpu->thread_id = qemu_get_thread_id();
 #endif
     QTAILQ_INSERT_TAIL(&cpus, cpu, node);
@@ -485,7 +521,8 @@ static void breakpoint_invalidate(CPUState *cpu, target_ulong pc)
 {
     hwaddr phys = cpu_get_phys_page_debug(cpu, pc);
     if (phys != -1) {
-        tb_invalidate_phys_addr(phys | (pc & ~TARGET_PAGE_MASK));
+        tb_invalidate_phys_addr(cpu->as,
+                                phys | (pc & ~TARGET_PAGE_MASK));
     }
 }
 #endif
@@ -724,11 +761,14 @@ found:
     return block;
 }
 
-static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t end,
-                                      uintptr_t length)
+static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t length)
 {
-    RAMBlock *block;
     ram_addr_t start1;
+    RAMBlock *block;
+    ram_addr_t end;
+
+    end = TARGET_PAGE_ALIGN(start + length);
+    start &= TARGET_PAGE_MASK;
 
     block = qemu_get_ram_block(start);
     assert(block == qemu_get_ram_block(end - 1));
@@ -737,29 +777,21 @@ static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t end,
 }
 
 /* Note: start and end must be within the same ram block.  */
-void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
-                                     int dirty_flags)
+void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t length,
+                                     unsigned client)
 {
-    uintptr_t length;
-
-    start &= TARGET_PAGE_MASK;
-    end = TARGET_PAGE_ALIGN(end);
-
-    length = end - start;
     if (length == 0)
         return;
-    cpu_physical_memory_mask_dirty_range(start, length, dirty_flags);
+    cpu_physical_memory_clear_dirty_range(start, length, client);
 
     if (tcg_enabled()) {
-        tlb_reset_dirty_range_all(start, end, length);
+        tlb_reset_dirty_range_all(start, length);
     }
 }
 
-static int cpu_physical_memory_set_dirty_tracking(int enable)
+static void cpu_physical_memory_set_dirty_tracking(bool enable)
 {
-    int ret = 0;
     in_migration = enable;
-    return ret;
 }
 
 hwaddr memory_region_section_get_iotlb(CPUArchState *env,
@@ -782,7 +814,7 @@ hwaddr memory_region_section_get_iotlb(CPUArchState *env,
             iotlb |= PHYS_SECTION_ROM;
         }
     } else {
-        iotlb = section - address_space_memory.dispatch->map.sections;
+        iotlb = section - section->address_space->dispatch->map.sections;
         iotlb += xlat;
     }
 
@@ -878,6 +910,7 @@ static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *secti
 
     if (!(existing->mr->subpage)) {
         subpage = subpage_init(d->as, base);
+        subsection.address_space = d->as;
         subsection.mr = &subpage->iomem;
         phys_page_set(d, base >> TARGET_PAGE_BITS, 1,
                       phys_section_add(&d->map, &subsection));
@@ -1074,7 +1107,7 @@ static void *file_ram_alloc(RAMBlock *block,
         }
 
         /* MAP_POPULATE silently ignores failures */
-        for (i = 0; i < (memory/hpagesize)-1; i++) {
+        for (i = 0; i < (memory/hpagesize); i++) {
             memset(area + (hpagesize*i), 0, 1);
         }
 
@@ -1211,6 +1244,9 @@ ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
                                    MemoryRegion *mr)
 {
     RAMBlock *block, *new_block;
+    ram_addr_t old_ram_size, new_ram_size;
+
+    old_ram_size = last_ram_offset() >> TARGET_PAGE_BITS;
 
     size = TARGET_PAGE_ALIGN(size);
     new_block = g_malloc0(sizeof(*new_block));
@@ -1271,11 +1307,17 @@ ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
     ram_list.version++;
     qemu_mutex_unlock_ramlist();
 
-    ram_list.phys_dirty = g_realloc(ram_list.phys_dirty,
-                                       last_ram_offset() >> TARGET_PAGE_BITS);
-    memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),
-           0, size >> TARGET_PAGE_BITS);
-    cpu_physical_memory_set_dirty_range(new_block->offset, size, 0xff);
+    new_ram_size = last_ram_offset() >> TARGET_PAGE_BITS;
+
+    if (new_ram_size > old_ram_size) {
+        int i;
+        for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
+            ram_list.dirty_memory[i] =
+                bitmap_zero_extend(ram_list.dirty_memory[i],
+                                   old_ram_size, new_ram_size);
+       }
+    }
+    cpu_physical_memory_set_dirty_range(new_block->offset, size);
 
     qemu_ram_setup_dump(new_block->host, size);
     qemu_madvise(new_block->host, size, QEMU_MADV_HUGEPAGE);
@@ -1485,11 +1527,8 @@ found:
 static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
                                uint64_t val, unsigned size)
 {
-    int dirty_flags;
-    dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
-    if (!(dirty_flags & CODE_DIRTY_FLAG)) {
+    if (!cpu_physical_memory_get_dirty_flag(ram_addr, DIRTY_MEMORY_CODE)) {
         tb_invalidate_phys_page_fast(ram_addr, size);
-        dirty_flags = cpu_physical_memory_get_dirty_flags(ram_addr);
     }
     switch (size) {
     case 1:
@@ -1504,11 +1543,11 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
     default:
         abort();
     }
-    dirty_flags |= (0xff & ~CODE_DIRTY_FLAG);
-    cpu_physical_memory_set_dirty_flags(ram_addr, dirty_flags);
+    cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_MIGRATION);
+    cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_VGA);
     /* we remove the notdirty callback only if the code has been
        flushed */
-    if (dirty_flags == 0xff) {
+    if (!cpu_physical_memory_is_clean(ram_addr)) {
         CPUArchState *env = current_cpu->env_ptr;
         tlb_set_dirty(env, env->mem_io_vaddr);
     }
@@ -1573,9 +1612,9 @@ static uint64_t watch_mem_read(void *opaque, hwaddr addr,
 {
     check_watchpoint(addr & ~TARGET_PAGE_MASK, ~(size - 1), BP_MEM_READ);
     switch (size) {
-    case 1: return ldub_phys(addr);
-    case 2: return lduw_phys(addr);
-    case 4: return ldl_phys(addr);
+    case 1: return ldub_phys(&address_space_memory, addr);
+    case 2: return lduw_phys(&address_space_memory, addr);
+    case 4: return ldl_phys(&address_space_memory, addr);
     default: abort();
     }
 }
@@ -1586,13 +1625,13 @@ static void watch_mem_write(void *opaque, hwaddr addr,
     check_watchpoint(addr & ~TARGET_PAGE_MASK, ~(size - 1), BP_MEM_WRITE);
     switch (size) {
     case 1:
-        stb_phys(addr, val);
+        stb_phys(&address_space_memory, addr, val);
         break;
     case 2:
-        stw_phys(addr, val);
+        stw_phys(&address_space_memory, addr, val);
         break;
     case 4:
-        stl_phys(addr, val);
+        stl_phys(&address_space_memory, addr, val);
         break;
     default: abort();
     }
@@ -1717,6 +1756,7 @@ static subpage_t *subpage_init(AddressSpace *as, hwaddr base)
 static uint16_t dummy_section(PhysPageMap *map, MemoryRegion *mr)
 {
     MemoryRegionSection section = {
+        .address_space = &address_space_memory,
         .mr = mr,
         .offset_within_address_space = 0,
         .offset_within_region = 0,
@@ -1726,10 +1766,9 @@ static uint16_t dummy_section(PhysPageMap *map, MemoryRegion *mr)
     return phys_section_add(map, &section);
 }
 
-MemoryRegion *iotlb_to_region(hwaddr index)
+MemoryRegion *iotlb_to_region(AddressSpace *as, hwaddr index)
 {
-    return address_space_memory.dispatch->map.sections[
-           index & ~TARGET_PAGE_MASK].mr;
+    return as->dispatch->map.sections[index & ~TARGET_PAGE_MASK].mr;
 }
 
 static void io_mem_init(void)
@@ -1789,18 +1828,23 @@ static void tcg_commit(MemoryListener *listener)
     CPU_FOREACH(cpu) {
         CPUArchState *env = cpu->env_ptr;
 
+        /* FIXME: Disentangle the cpu.h circular files deps so we can
+           directly get the right CPU from listener.  */
+        if (cpu->tcg_as_listener != listener) {
+            continue;
+        }
         tlb_flush(env, 1);
     }
 }
 
 static void core_log_global_start(MemoryListener *listener)
 {
-    cpu_physical_memory_set_dirty_tracking(1);
+    cpu_physical_memory_set_dirty_tracking(true);
 }
 
 static void core_log_global_stop(MemoryListener *listener)
 {
-    cpu_physical_memory_set_dirty_tracking(0);
+    cpu_physical_memory_set_dirty_tracking(false);
 }
 
 static MemoryListener core_memory_listener = {
@@ -1809,10 +1853,6 @@ static MemoryListener core_memory_listener = {
     .priority = 1,
 };
 
-static MemoryListener tcg_memory_listener = {
-    .commit = tcg_commit,
-};
-
 void address_space_init_dispatch(AddressSpace *as)
 {
     as->dispatch = NULL;
@@ -1848,9 +1888,6 @@ static void memory_map_init(void)
     address_space_init(&address_space_io, system_io, "I/O");
 
     memory_listener_register(&core_memory_listener, &address_space_memory);
-    if (tcg_enabled()) {
-        memory_listener_register(&tcg_memory_listener, &address_space_memory);
-    }
 }
 
 MemoryRegion *get_system_memory(void)
@@ -1911,27 +1948,16 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr,
 static void invalidate_and_set_dirty(hwaddr addr,
                                      hwaddr length)
 {
-    if (!cpu_physical_memory_is_dirty(addr)) {
+    if (cpu_physical_memory_is_clean(addr)) {
         /* invalidate code */
         tb_invalidate_phys_page_range(addr, addr + length, 0);
         /* set dirty bit */
-        cpu_physical_memory_set_dirty_flags(addr, (0xff & ~CODE_DIRTY_FLAG));
+        cpu_physical_memory_set_dirty_flag(addr, DIRTY_MEMORY_VGA);
+        cpu_physical_memory_set_dirty_flag(addr, DIRTY_MEMORY_MIGRATION);
     }
     xen_modified_memory(addr, length);
 }
 
-static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
-{
-    if (memory_region_is_ram(mr)) {
-        return !(is_write && mr->readonly);
-    }
-    if (memory_region_is_romd(mr)) {
-        return !is_write;
-    }
-
-    return false;
-}
-
 static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
 {
     unsigned access_size_max = mr->ops->valid.max_access_size;
@@ -2076,7 +2102,7 @@ enum write_rom_type {
     FLUSH_CACHE,
 };
 
-static inline void cpu_physical_memory_write_rom_internal(
+static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as,
     hwaddr addr, const uint8_t *buf, int len, enum write_rom_type type)
 {
     hwaddr l;
@@ -2086,8 +2112,7 @@ static inline void cpu_physical_memory_write_rom_internal(
 
     while (len > 0) {
         l = len;
-        mr = address_space_translate(&address_space_memory,
-                                     addr, &addr1, &l, true);
+        mr = address_space_translate(as, addr, &addr1, &l, true);
 
         if (!(memory_region_is_ram(mr) ||
               memory_region_is_romd(mr))) {
@@ -2113,10 +2138,10 @@ static inline void cpu_physical_memory_write_rom_internal(
 }
 
 /* used for ROM loading : can write in RAM and ROM */
-void cpu_physical_memory_write_rom(hwaddr addr,
+void cpu_physical_memory_write_rom(AddressSpace *as, hwaddr addr,
                                    const uint8_t *buf, int len)
 {
-    cpu_physical_memory_write_rom_internal(addr, buf, len, WRITE_DATA);
+    cpu_physical_memory_write_rom_internal(as, addr, buf, len, WRITE_DATA);
 }
 
 void cpu_flush_icache_range(hwaddr start, int len)
@@ -2131,7 +2156,8 @@ void cpu_flush_icache_range(hwaddr start, int len)
         return;
     }
 
-    cpu_physical_memory_write_rom_internal(start, NULL, len, FLUSH_CACHE);
+    cpu_physical_memory_write_rom_internal(&address_space_memory,
+                                           start, NULL, len, FLUSH_CACHE);
 }
 
 typedef struct {
@@ -2322,7 +2348,7 @@ void cpu_physical_memory_unmap(void *buffer, hwaddr len,
 }
 
 /* warning: addr must be aligned */
-static inline uint32_t ldl_phys_internal(hwaddr addr,
+static inline uint32_t ldl_phys_internal(AddressSpace *as, hwaddr addr,
                                          enum device_endian endian)
 {
     uint8_t *ptr;
@@ -2331,8 +2357,7 @@ static inline uint32_t ldl_phys_internal(hwaddr addr,
     hwaddr l = 4;
     hwaddr addr1;
 
-    mr = address_space_translate(&address_space_memory, addr, &addr1, &l,
-                                 false);
+    mr = address_space_translate(as, addr, &addr1, &l, false);
     if (l < 4 || !memory_access_is_direct(mr, false)) {
         /* I/O case */
         io_mem_read(mr, addr1, &val, 4);
@@ -2365,23 +2390,23 @@ static inline uint32_t ldl_phys_internal(hwaddr addr,
     return val;
 }
 
-uint32_t ldl_phys(hwaddr addr)
+uint32_t ldl_phys(AddressSpace *as, hwaddr addr)
 {
-    return ldl_phys_internal(addr, DEVICE_NATIVE_ENDIAN);
+    return ldl_phys_internal(as, addr, DEVICE_NATIVE_ENDIAN);
 }
 
-uint32_t ldl_le_phys(hwaddr addr)
+uint32_t ldl_le_phys(AddressSpace *as, hwaddr addr)
 {
-    return ldl_phys_internal(addr, DEVICE_LITTLE_ENDIAN);
+    return ldl_phys_internal(as, addr, DEVICE_LITTLE_ENDIAN);
 }
 
-uint32_t ldl_be_phys(hwaddr addr)
+uint32_t ldl_be_phys(AddressSpace *as, hwaddr addr)
 {
-    return ldl_phys_internal(addr, DEVICE_BIG_ENDIAN);
+    return ldl_phys_internal(as, addr, DEVICE_BIG_ENDIAN);
 }
 
 /* warning: addr must be aligned */
-static inline uint64_t ldq_phys_internal(hwaddr addr,
+static inline uint64_t ldq_phys_internal(AddressSpace *as, hwaddr addr,
                                          enum device_endian endian)
 {
     uint8_t *ptr;
@@ -2390,7 +2415,7 @@ static inline uint64_t ldq_phys_internal(hwaddr addr,
     hwaddr l = 8;
     hwaddr addr1;
 
-    mr = address_space_translate(&address_space_memory, addr, &addr1, &l,
+    mr = address_space_translate(as, addr, &addr1, &l,
                                  false);
     if (l < 8 || !memory_access_is_direct(mr, false)) {
         /* I/O case */
@@ -2424,31 +2449,31 @@ static inline uint64_t ldq_phys_internal(hwaddr addr,
     return val;
 }
 
-uint64_t ldq_phys(hwaddr addr)
+uint64_t ldq_phys(AddressSpace *as, hwaddr addr)
 {
-    return ldq_phys_internal(addr, DEVICE_NATIVE_ENDIAN);
+    return ldq_phys_internal(as, addr, DEVICE_NATIVE_ENDIAN);
 }
 
-uint64_t ldq_le_phys(hwaddr addr)
+uint64_t ldq_le_phys(AddressSpace *as, hwaddr addr)
 {
-    return ldq_phys_internal(addr, DEVICE_LITTLE_ENDIAN);
+    return ldq_phys_internal(as, addr, DEVICE_LITTLE_ENDIAN);
 }
 
-uint64_t ldq_be_phys(hwaddr addr)
+uint64_t ldq_be_phys(AddressSpace *as, hwaddr addr)
 {
-    return ldq_phys_internal(addr, DEVICE_BIG_ENDIAN);
+    return ldq_phys_internal(as, addr, DEVICE_BIG_ENDIAN);
 }
 
 /* XXX: optimize */
-uint32_t ldub_phys(hwaddr addr)
+uint32_t ldub_phys(AddressSpace *as, hwaddr addr)
 {
     uint8_t val;
-    cpu_physical_memory_read(addr, &val, 1);
+    address_space_rw(as, addr, &val, 1, 0);
     return val;
 }
 
 /* warning: addr must be aligned */
-static inline uint32_t lduw_phys_internal(hwaddr addr,
+static inline uint32_t lduw_phys_internal(AddressSpace *as, hwaddr addr,
                                           enum device_endian endian)
 {
     uint8_t *ptr;
@@ -2457,7 +2482,7 @@ static inline uint32_t lduw_phys_internal(hwaddr addr,
     hwaddr l = 2;
     hwaddr addr1;
 
-    mr = address_space_translate(&address_space_memory, addr, &addr1, &l,
+    mr = address_space_translate(as, addr, &addr1, &l,
                                  false);
     if (l < 2 || !memory_access_is_direct(mr, false)) {
         /* I/O case */
@@ -2491,32 +2516,32 @@ static inline uint32_t lduw_phys_internal(hwaddr addr,
     return val;
 }
 
-uint32_t lduw_phys(hwaddr addr)
+uint32_t lduw_phys(AddressSpace *as, hwaddr addr)
 {
-    return lduw_phys_internal(addr, DEVICE_NATIVE_ENDIAN);
+    return lduw_phys_internal(as, addr, DEVICE_NATIVE_ENDIAN);
 }
 
-uint32_t lduw_le_phys(hwaddr addr)
+uint32_t lduw_le_phys(AddressSpace *as, hwaddr addr)
 {
-    return lduw_phys_internal(addr, DEVICE_LITTLE_ENDIAN);
+    return lduw_phys_internal(as, addr, DEVICE_LITTLE_ENDIAN);
 }
 
-uint32_t lduw_be_phys(hwaddr addr)
+uint32_t lduw_be_phys(AddressSpace *as, hwaddr addr)
 {
-    return lduw_phys_internal(addr, DEVICE_BIG_ENDIAN);
+    return lduw_phys_internal(as, addr, DEVICE_BIG_ENDIAN);
 }
 
 /* warning: addr must be aligned. The ram page is not masked as dirty
    and the code inside is not invalidated. It is useful if the dirty
    bits are used to track modified PTEs */
-void stl_phys_notdirty(hwaddr addr, uint32_t val)
+void stl_phys_notdirty(AddressSpace *as, hwaddr addr, uint32_t val)
 {
     uint8_t *ptr;
     MemoryRegion *mr;
     hwaddr l = 4;
     hwaddr addr1;
 
-    mr = address_space_translate(&address_space_memory, addr, &addr1, &l,
+    mr = address_space_translate(as, addr, &addr1, &l,
                                  true);
     if (l < 4 || !memory_access_is_direct(mr, true)) {
         io_mem_write(mr, addr1, val, 4);
@@ -2526,19 +2551,21 @@ void stl_phys_notdirty(hwaddr addr, uint32_t val)
         stl_p(ptr, val);
 
         if (unlikely(in_migration)) {
-            if (!cpu_physical_memory_is_dirty(addr1)) {
+            if (cpu_physical_memory_is_clean(addr1)) {
                 /* invalidate code */
                 tb_invalidate_phys_page_range(addr1, addr1 + 4, 0);
                 /* set dirty bit */
-                cpu_physical_memory_set_dirty_flags(
-                    addr1, (0xff & ~CODE_DIRTY_FLAG));
+                cpu_physical_memory_set_dirty_flag(addr1,
+                                                   DIRTY_MEMORY_MIGRATION);
+                cpu_physical_memory_set_dirty_flag(addr1, DIRTY_MEMORY_VGA);
             }
         }
     }
 }
 
 /* warning: addr must be aligned */
-static inline void stl_phys_internal(hwaddr addr, uint32_t val,
+static inline void stl_phys_internal(AddressSpace *as,
+                                     hwaddr addr, uint32_t val,
                                      enum device_endian endian)
 {
     uint8_t *ptr;
@@ -2546,7 +2573,7 @@ static inline void stl_phys_internal(hwaddr addr, uint32_t val,
     hwaddr l = 4;
     hwaddr addr1;
 
-    mr = address_space_translate(&address_space_memory, addr, &addr1, &l,
+    mr = address_space_translate(as, addr, &addr1, &l,
                                  true);
     if (l < 4 || !memory_access_is_direct(mr, true)) {
 #if defined(TARGET_WORDS_BIGENDIAN)
@@ -2578,30 +2605,31 @@ static inline void stl_phys_internal(hwaddr addr, uint32_t val,
     }
 }
 
-void stl_phys(hwaddr addr, uint32_t val)
+void stl_phys(AddressSpace *as, hwaddr addr, uint32_t val)
 {
-    stl_phys_internal(addr, val, DEVICE_NATIVE_ENDIAN);
+    stl_phys_internal(as, addr, val, DEVICE_NATIVE_ENDIAN);
 }
 
-void stl_le_phys(hwaddr addr, uint32_t val)
+void stl_le_phys(AddressSpace *as, hwaddr addr, uint32_t val)
 {
-    stl_phys_internal(addr, val, DEVICE_LITTLE_ENDIAN);
+    stl_phys_internal(as, addr, val, DEVICE_LITTLE_ENDIAN);
 }
 
-void stl_be_phys(hwaddr addr, uint32_t val)
+void stl_be_phys(AddressSpace *as, hwaddr addr, uint32_t val)
 {
-    stl_phys_internal(addr, val, DEVICE_BIG_ENDIAN);
+    stl_phys_internal(as, addr, val, DEVICE_BIG_ENDIAN);
 }
 
 /* XXX: optimize */
-void stb_phys(hwaddr addr, uint32_t val)
+void stb_phys(AddressSpace *as, hwaddr addr, uint32_t val)
 {
     uint8_t v = val;
-    cpu_physical_memory_write(addr, &v, 1);
+    address_space_rw(as, addr, &v, 1, 1);
 }
 
 /* warning: addr must be aligned */
-static inline void stw_phys_internal(hwaddr addr, uint32_t val,
+static inline void stw_phys_internal(AddressSpace *as,
+                                     hwaddr addr, uint32_t val,
                                      enum device_endian endian)
 {
     uint8_t *ptr;
@@ -2609,8 +2637,7 @@ static inline void stw_phys_internal(hwaddr addr, uint32_t val,
     hwaddr l = 2;
     hwaddr addr1;
 
-    mr = address_space_translate(&address_space_memory, addr, &addr1, &l,
-                                 true);
+    mr = address_space_translate(as, addr, &addr1, &l, true);
     if (l < 2 || !memory_access_is_direct(mr, true)) {
 #if defined(TARGET_WORDS_BIGENDIAN)
         if (endian == DEVICE_LITTLE_ENDIAN) {
@@ -2641,38 +2668,38 @@ static inline void stw_phys_internal(hwaddr addr, uint32_t val,
     }
 }
 
-void stw_phys(hwaddr addr, uint32_t val)
+void stw_phys(AddressSpace *as, hwaddr addr, uint32_t val)
 {
-    stw_phys_internal(addr, val, DEVICE_NATIVE_ENDIAN);
+    stw_phys_internal(as, addr, val, DEVICE_NATIVE_ENDIAN);
 }
 
-void stw_le_phys(hwaddr addr, uint32_t val)
+void stw_le_phys(AddressSpace *as, hwaddr addr, uint32_t val)
 {
-    stw_phys_internal(addr, val, DEVICE_LITTLE_ENDIAN);
+    stw_phys_internal(as, addr, val, DEVICE_LITTLE_ENDIAN);
 }
 
-void stw_be_phys(hwaddr addr, uint32_t val)
+void stw_be_phys(AddressSpace *as, hwaddr addr, uint32_t val)
 {
-    stw_phys_internal(addr, val, DEVICE_BIG_ENDIAN);
+    stw_phys_internal(as, addr, val, DEVICE_BIG_ENDIAN);
 }
 
 /* XXX: optimize */
-void stq_phys(hwaddr addr, uint64_t val)
+void stq_phys(AddressSpace *as, hwaddr addr, uint64_t val)
 {
     val = tswap64(val);
-    cpu_physical_memory_write(addr, &val, 8);
+    address_space_rw(as, addr, (void *) &val, 8, 1);
 }
 
-void stq_le_phys(hwaddr addr, uint64_t val)
+void stq_le_phys(AddressSpace *as, hwaddr addr, uint64_t val)
 {
     val = cpu_to_le64(val);
-    cpu_physical_memory_write(addr, &val, 8);
+    address_space_rw(as, addr, (void *) &val, 8, 1);
 }
 
-void stq_be_phys(hwaddr addr, uint64_t val)
+void stq_be_phys(AddressSpace *as, hwaddr addr, uint64_t val)
 {
     val = cpu_to_be64(val);
-    cpu_physical_memory_write(addr, &val, 8);
+    address_space_rw(as, addr, (void *) &val, 8, 1);
 }
 
 /* virtual memory access for debug (includes writing to ROM) */
@@ -2693,10 +2720,11 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr,
         if (l > len)
             l = len;
         phys_addr += (addr & ~TARGET_PAGE_MASK);
-        if (is_write)
-            cpu_physical_memory_write_rom(phys_addr, buf, l);
-        else
-            cpu_physical_memory_rw(phys_addr, buf, l, is_write);
+        if (is_write) {
+            cpu_physical_memory_write_rom(cpu->as, phys_addr, buf, l);
+        } else {
+            address_space_rw(cpu->as, phys_addr, buf, l, 0);
+        }
         len -= l;
         buf += l;
         addr += l;

hmp-commands.hx

@@ -35,6 +35,11 @@ STEXI
 @item commit
 @findex commit
 Commit changes to the disk images (if -snapshot is used) or backing files.
+If the backing file is smaller than the snapshot, then the backing file will be
+resized to be the same size as the snapshot.  If the snapshot is smaller than
+the backing file, the backing file will not be truncated.  If you want the
+backing file to match the size of the smaller snapshot, you can safely truncate
+it yourself once the commit operation successfully completes.
 ETEXI
 
     {
@@ -1241,6 +1246,34 @@ STEXI
 @item netdev_del
 @findex netdev_del
 Remove host network device.
+ETEXI
+
+    {
+        .name       = "object_add",
+        .args_type  = "object:O",
+        .params     = "[qom-type=]type,id=str[,prop=value][,...]",
+        .help       = "create QOM object",
+        .mhandler.cmd = hmp_object_add,
+    },
+
+STEXI
+@item object_add
+@findex object_add
+Create QOM object.
+ETEXI
+
+    {
+        .name       = "object_del",
+        .args_type  = "id:s",
+        .params     = "id",
+        .help       = "destroy QOM object",
+        .mhandler.cmd = hmp_object_del,
+    },
+
+STEXI
+@item object_del
+@findex object_del
+Destroy QOM object.
 ETEXI
 
 #ifdef CONFIG_SLIRP
@@ -1617,6 +1650,19 @@ STEXI
 
 Executes a qemu-io command on the given block device.
 
+ETEXI
+
+    {
+        .name       = "cpu-add",
+        .args_type  = "id:i",
+        .params     = "id",
+        .help       = "add cpu",
+        .mhandler.cmd  = hmp_cpu_add,
+    },
+
+STEXI
+@item cpu-add @var{id}
+Add CPU with id @var{id}
 ETEXI
 
     {

hmp.c

@@ -21,6 +21,7 @@
 #include "qmp-commands.h"
 #include "qemu/sockets.h"
 #include "monitor/monitor.h"
+#include "qapi/opts-visitor.h"
 #include "ui/console.h"
 #include "block/qapi.h"
 #include "qemu-io.h"
@@ -870,7 +871,7 @@ void hmp_block_passwd(Monitor *mon, const QDict *qdict)
     const char *password = qdict_get_str(qdict, "password");
     Error *errp = NULL;
 
-    qmp_block_passwd(device, password, &errp);
+    qmp_block_passwd(true, device, false, NULL, password, &errp);
     hmp_handle_error(mon, &errp);
 }
 
@@ -892,7 +893,7 @@ void hmp_block_resize(Monitor *mon, const QDict *qdict)
     int64_t size = qdict_get_int(qdict, "size");
     Error *errp = NULL;
 
-    qmp_block_resize(device, size, &errp);
+    qmp_block_resize(true, device, false, NULL, size, &errp);
     hmp_handle_error(mon, &errp);
 }
 
@@ -971,7 +972,9 @@ void hmp_snapshot_blkdev(Monitor *mon, const QDict *qdict)
     }
 
     mode = reuse ? NEW_IMAGE_MODE_EXISTING : NEW_IMAGE_MODE_ABSOLUTE_PATHS;
-    qmp_blockdev_snapshot_sync(device, filename, !!format, format,
+    qmp_blockdev_snapshot_sync(true, device, false, NULL,
+                               filename, false, NULL,
+                               !!format, format,
                                true, mode, &errp);
     hmp_handle_error(mon, &errp);
 }
@@ -1091,11 +1094,11 @@ void hmp_eject(Monitor *mon, const QDict *qdict)
     hmp_handle_error(mon, &err);
 }
 
-static void hmp_change_read_arg(Monitor *mon, const char *password,
-                                void *opaque)
+static void hmp_change_read_arg(void *opaque, const char *password,
+                                void *readline_opaque)
 {
     qmp_change_vnc_password(password, NULL);
-    monitor_read_command(mon, 1);
+    monitor_read_command(opaque, 1);
 }
 
 void hmp_change(Monitor *mon, const QDict *qdict)
@@ -1354,6 +1357,63 @@ void hmp_netdev_del(Monitor *mon, const QDict *qdict)
     hmp_handle_error(mon, &err);
 }
 
+void hmp_object_add(Monitor *mon, const QDict *qdict)
+{
+    Error *err = NULL;
+    QemuOpts *opts;
+    char *type = NULL;
+    char *id = NULL;
+    void *dummy = NULL;
+    OptsVisitor *ov;
+    QDict *pdict;
+
+    opts = qemu_opts_from_qdict(qemu_find_opts("object"), qdict, &err);
+    if (err) {
+        goto out;
+    }
+
+    ov = opts_visitor_new(opts);
+    pdict = qdict_clone_shallow(qdict);
+
+    visit_start_struct(opts_get_visitor(ov), &dummy, NULL, NULL, 0, &err);
+    if (err) {
+        goto out_clean;
+    }
+
+    qdict_del(pdict, "qom-type");
+    visit_type_str(opts_get_visitor(ov), &type, "qom-type", &err);
+    if (err) {
+        goto out_clean;
+    }
+
+    qdict_del(pdict, "id");
+    visit_type_str(opts_get_visitor(ov), &id, "id", &err);
+    if (err) {
+        goto out_clean;
+    }
+
+    object_add(type, id, pdict, opts_get_visitor(ov), &err);
+    if (err) {
+        goto out_clean;
+    }
+    visit_end_struct(opts_get_visitor(ov), &err);
+    if (err) {
+        qmp_object_del(id, NULL);
+    }
+
+out_clean:
+    opts_visitor_cleanup(ov);
+
+    QDECREF(pdict);
+    qemu_opts_del(opts);
+    g_free(id);
+    g_free(type);
+    g_free(dummy);
+
+out:
+    hmp_handle_error(mon, &err);
+}
+
 void hmp_getfd(Monitor *mon, const QDict *qdict)
 {
     const char *fdname = qdict_get_str(qdict, "fdname");
@@ -1525,6 +1585,16 @@ void hmp_nbd_server_stop(Monitor *mon, const QDict *qdict)
     hmp_handle_error(mon, &errp);
 }
 
+void hmp_cpu_add(Monitor *mon, const QDict *qdict)
+{
+    int cpuid;
+    Error *err = NULL;
+
+    cpuid = qdict_get_int(qdict, "id");
+    qmp_cpu_add(cpuid, &err);
+    hmp_handle_error(mon, &err);
+}
+
 void hmp_chardev_add(Monitor *mon, const QDict *qdict)
 {
     const char *args = qdict_get_str(qdict, "args");
@@ -1564,3 +1634,12 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
 
     hmp_handle_error(mon, &err);
 }
+
+void hmp_object_del(Monitor *mon, const QDict *qdict)
+{
+    const char *id = qdict_get_str(qdict, "id");
+    Error *err = NULL;
+
+    qmp_object_del(id, &err);
+    hmp_handle_error(mon, &err);
+}

hmp.h

@@ -89,5 +89,8 @@ void hmp_nbd_server_stop(Monitor *mon, const QDict *qdict);
 void hmp_chardev_add(Monitor *mon, const QDict *qdict);
 void hmp_chardev_remove(Monitor *mon, const QDict *qdict);
 void hmp_qemu_io(Monitor *mon, const QDict *qdict);
+void hmp_cpu_add(Monitor *mon, const QDict *qdict);
+void hmp_object_add(Monitor *mon, const QDict *qdict);
+void hmp_object_del(Monitor *mon, const QDict *qdict);
 
 #endif

hw/9pfs/cofile.c

@@ -38,10 +38,6 @@ int v9fs_co_st_gen(V9fsPDU *pdu, V9fsPath *path, mode_t st_mode,
             });
         v9fs_path_unlock(s);
     }
-    /* The ioctl may not be supported depending on the path */
-    if (err == -ENOTTY) {
-        err = 0;
-    }
     return err;
 }
 

hw/9pfs/virtio-9p-handle.c

@@ -582,6 +582,7 @@ static int handle_unlinkat(FsContext *ctx, V9fsPath *dir,
 static int handle_ioc_getversion(FsContext *ctx, V9fsPath *path,
                                  mode_t st_mode, uint64_t *st_gen)
 {
+#ifdef FS_IOC_GETVERSION
     int err;
     V9fsFidOpenState fid_open;
 
@@ -590,7 +591,8 @@ static int handle_ioc_getversion(FsContext *ctx, V9fsPath *path,
      * We can get fd for regular files and directories only
      */
     if (!S_ISREG(st_mode) && !S_ISDIR(st_mode)) {
-            return 0;
+        errno = ENOTTY;
+        return -1;
     }
     err = handle_open(ctx, path, O_RDONLY, &fid_open);
     if (err < 0) {
@@ -599,6 +601,10 @@ static int handle_ioc_getversion(FsContext *ctx, V9fsPath *path,
     err = ioctl(fid_open.fd, FS_IOC_GETVERSION, st_gen);
     handle_close(ctx, &fid_open);
     return err;
+#else
+    errno = ENOTTY;
+    return -1;
+#endif
 }
 
 static int handle_init(FsContext *ctx)

hw/9pfs/virtio-9p-local.c

@@ -1068,8 +1068,8 @@ err_out:
 static int local_ioc_getversion(FsContext *ctx, V9fsPath *path,
                                 mode_t st_mode, uint64_t *st_gen)
 {
-    int err;
 #ifdef FS_IOC_GETVERSION
+    int err;
     V9fsFidOpenState fid_open;
 
     /*
@@ -1077,7 +1077,8 @@ static int local_ioc_getversion(FsContext *ctx, V9fsPath *path,
      * We can get fd for regular files and directories only
      */
     if (!S_ISREG(st_mode) && !S_ISDIR(st_mode)) {
-            return 0;
+        errno = ENOTTY;
+        return -1;
     }
     err = local_open(ctx, path, O_RDONLY, &fid_open);
     if (err < 0) {
@@ -1085,10 +1086,11 @@ static int local_ioc_getversion(FsContext *ctx, V9fsPath *path,
     }
     err = ioctl(fid_open.fd, FS_IOC_GETVERSION, st_gen);
     local_close(ctx, &fid_open);
-#else
-    err = -ENOTTY;
-#endif
     return err;
+#else
+    errno = ENOTTY;
+    return -1;
+#endif
 }
 
 static int local_init(FsContext *ctx)

hw/9pfs/virtio-9p-proxy.c

@@ -1086,7 +1086,8 @@ static int proxy_ioc_getversion(FsContext *fs_ctx, V9fsPath *path,
      * we can get fd for regular files and directories only
      */
     if (!S_ISREG(st_mode) && !S_ISDIR(st_mode)) {
-        return 0;
+        errno = ENOTTY;
+        return -1;
     }
     err = v9fs_request(fs_ctx->private, T_GETVERSION, st_gen, "s", path);
     if (err < 0) {

hw/9pfs/virtio-9p.c

@@ -1080,10 +1080,18 @@ static void v9fs_getattr(void *opaque)
     /*  fill st_gen if requested and supported by underlying fs */
     if (request_mask & P9_STATS_GEN) {
         retval = v9fs_co_st_gen(pdu, &fidp->path, stbuf.st_mode, &v9stat_dotl);
-        if (retval < 0) {
-            goto out;
-        }
+        switch (retval) {
+        case 0:
+            /* we have valid st_gen: update result mask */
             v9stat_dotl.st_result_mask |= P9_STATS_GEN;
+            break;
+        case -EINTR:
+            /* request cancelled, e.g. by Tflush */
+            goto out;
+        default:
+            /* failed to get st_gen: not fatal, ignore */
+            break;
+        }
     }
     retval = pdu_marshal(pdu, offset, "A", &v9stat_dotl);
     if (retval < 0) {

hw/acpi/Makefile.objs

@@ -1,2 +1 @@
-common-obj-$(CONFIG_ACPI) += core.o piix4.o ich9.o
-
+common-obj-$(CONFIG_ACPI) += core.o piix4.o ich9.o pcihp.o cpu_hotplug.o

hw/acpi/core.c

@@ -662,3 +662,21 @@ uint32_t acpi_gpe_ioport_readb(ACPIREGS *ar, uint32_t addr)
 
     return val;
 }
+
+void acpi_update_sci(ACPIREGS *regs, qemu_irq irq)
+{
+    int sci_level, pm1a_sts;
+
+    pm1a_sts = acpi_pm1_evt_get_sts(regs);
+
+    sci_level = ((pm1a_sts &
+                  regs->pm1.evt.en & ACPI_BITMASK_PM1_COMMON_ENABLED) != 0) ||
+                ((regs->gpe.sts[0] & regs->gpe.en[0]) != 0);
+
+    qemu_set_irq(irq, sci_level);
+
+    /* schedule a timer interruption if needed */
+    acpi_pm_tmr_update(regs,
+                       (regs->pm1.evt.en & ACPI_BITMASK_TIMER_ENABLE) &&
+                       !(pm1a_sts & ACPI_BITMASK_TIMER_STATUS));
+}

hw/acpi/cpu_hotplug.c

@@ -0,0 +1,64 @@
+/*
+ * QEMU ACPI hotplug utilities
+ *
+ * Copyright (C) 2013 Red Hat Inc
+ *
+ * Authors:
+ *   Igor Mammedov <imammedo@redhat.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.
+ */
+#include "hw/hw.h"
+#include "hw/acpi/cpu_hotplug.h"
+
+static uint64_t cpu_status_read(void *opaque, hwaddr addr, unsigned int size)
+{
+    AcpiCpuHotplug *cpus = opaque;
+    uint64_t val = cpus->sts[addr];
+
+    return val;
+}
+
+static void cpu_status_write(void *opaque, hwaddr addr, uint64_t data,
+                             unsigned int size)
+{
+    /* TODO: implement VCPU removal on guest signal that CPU can be removed */
+}
+
+static const MemoryRegionOps AcpiCpuHotplug_ops = {
+    .read = cpu_status_read,
+    .write = cpu_status_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 1,
+    },
+};
+
+void AcpiCpuHotplug_add(ACPIGPE *gpe, AcpiCpuHotplug *g, CPUState *cpu)
+{
+    CPUClass *k = CPU_GET_CLASS(cpu);
+    int64_t cpu_id;
+
+    *gpe->sts = *gpe->sts | ACPI_CPU_HOTPLUG_STATUS;
+    cpu_id = k->get_arch_id(CPU(cpu));
+    g->sts[cpu_id / 8] |= (1 << (cpu_id % 8));
+}
+
+void AcpiCpuHotplug_init(MemoryRegion *parent, Object *owner,
+                         AcpiCpuHotplug *gpe_cpu, uint16_t base)
+{
+    CPUState *cpu;
+
+    CPU_FOREACH(cpu) {
+        CPUClass *cc = CPU_GET_CLASS(cpu);
+        int64_t id = cc->get_arch_id(cpu);
+
+        g_assert((id / 8) < ACPI_GPE_PROC_LEN);
+        gpe_cpu->sts[id / 8] |= (1 << (id % 8));
+    }
+    memory_region_init_io(&gpe_cpu->io, owner, &AcpiCpuHotplug_ops,
+                          gpe_cpu, "acpi-cpu-hotplug", ACPI_GPE_PROC_LEN);
+    memory_region_add_subregion(parent, base, &gpe_cpu->io);
+}

hw/acpi/ich9.c

@@ -44,29 +44,10 @@ do { printf("%s "fmt, __func__, ## __VA_ARGS__); } while (0)
 #define ICH9_DEBUG(fmt, ...)    do { } while (0)
 #endif
 
-static void pm_update_sci(ICH9LPCPMRegs *pm)
-{
-    int sci_level, pm1a_sts;
-
-    pm1a_sts = acpi_pm1_evt_get_sts(&pm->acpi_regs);
-
-    sci_level = (((pm1a_sts & pm->acpi_regs.pm1.evt.en) &
-                  (ACPI_BITMASK_RT_CLOCK_ENABLE |
-                   ACPI_BITMASK_POWER_BUTTON_ENABLE |
-                   ACPI_BITMASK_GLOBAL_LOCK_ENABLE |
-                   ACPI_BITMASK_TIMER_ENABLE)) != 0);
-    qemu_set_irq(pm->irq, sci_level);
-
-    /* schedule a timer interruption if needed */
-    acpi_pm_tmr_update(&pm->acpi_regs,
-                       (pm->acpi_regs.pm1.evt.en & ACPI_BITMASK_TIMER_ENABLE) &&
-                       !(pm1a_sts & ACPI_BITMASK_TIMER_STATUS));
-}
-
 static void ich9_pm_update_sci_fn(ACPIREGS *regs)
 {
     ICH9LPCPMRegs *pm = container_of(regs, ICH9LPCPMRegs, acpi_regs);
-    pm_update_sci(pm);
+    acpi_update_sci(&pm->acpi_regs, pm->irq);
 }
 
 static uint64_t ich9_gpe_readb(void *opaque, hwaddr addr, unsigned width)
@@ -80,6 +61,7 @@ static void ich9_gpe_writeb(void *opaque, hwaddr addr, uint64_t val,
 {
     ICH9LPCPMRegs *pm = opaque;
     acpi_gpe_ioport_writeb(&pm->acpi_regs, addr, val);
+    acpi_update_sci(&pm->acpi_regs, pm->irq);
 }
 
 static const MemoryRegionOps ich9_gpe_ops = {
@@ -193,7 +175,7 @@ static void pm_reset(void *opaque)
         pm->smi_en |= ICH9_PMIO_SMI_EN_APMC_EN;
     }
 
-    pm_update_sci(pm);
+    acpi_update_sci(&pm->acpi_regs, pm->irq);
 }
 
 static void pm_powerdown_req(Notifier *n, void *opaque)
@@ -203,6 +185,15 @@ static void pm_powerdown_req(Notifier *n, void *opaque)
     acpi_pm1_evt_power_down(&pm->acpi_regs);
 }
 
+static void ich9_cpu_added_req(Notifier *n, void *opaque)
+{
+    ICH9LPCPMRegs *pm = container_of(n, ICH9LPCPMRegs, cpu_added_notifier);
+
+    assert(pm != NULL);
+    AcpiCpuHotplug_add(&pm->acpi_regs.gpe, &pm->gpe_cpu, CPU(opaque));
+    acpi_update_sci(&pm->acpi_regs, pm->irq);
+}
+
 void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
                   qemu_irq sci_irq)
 {
@@ -228,6 +219,11 @@ void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
     qemu_register_reset(pm_reset, pm);
     pm->powerdown_notifier.notify = pm_powerdown_req;
     qemu_register_powerdown_notifier(&pm->powerdown_notifier);
+
+    AcpiCpuHotplug_init(pci_address_space_io(lpc_pci), OBJECT(lpc_pci),
+                        &pm->gpe_cpu, ICH9_CPU_HOTPLUG_IO_BASE);
+    pm->cpu_added_notifier.notify = ich9_cpu_added_req;
+    qemu_register_cpu_added_notifier(&pm->cpu_added_notifier);
 }
 
 static void ich9_pm_get_gpe0_blk(Object *obj, Visitor *v,

hw/acpi/pcihp.c

@@ -0,0 +1,331 @@
+/*
+ * QEMU<->ACPI BIOS PCI hotplug interface
+ *
+ * QEMU supports PCI hotplug via ACPI. This module
+ * implements the interface between QEMU and the ACPI BIOS.
+ * Interface specification - see docs/specs/acpi_pci_hotplug.txt
+ *
+ * Copyright (c) 2013, Red Hat Inc, Michael S. Tsirkin (mst@redhat.com)
+ * Copyright (c) 2006 Fabrice Bellard
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "hw/acpi/pcihp.h"
+
+#include "hw/hw.h"
+#include "hw/i386/pc.h"
+#include "hw/pci/pci.h"
+#include "hw/acpi/acpi.h"
+#include "sysemu/sysemu.h"
+#include "qemu/range.h"
+#include "exec/ioport.h"
+#include "exec/address-spaces.h"
+#include "hw/pci/pci_bus.h"
+#include "qom/qom-qobject.h"
+#include "qapi/qmp/qint.h"
+
+//#define DEBUG
+
+#ifdef DEBUG
+# define ACPI_PCIHP_DPRINTF(format, ...)     printf(format, ## __VA_ARGS__)
+#else
+# define ACPI_PCIHP_DPRINTF(format, ...)     do { } while (0)
+#endif
+
+#define ACPI_PCI_HOTPLUG_STATUS 2
+#define ACPI_PCIHP_ADDR 0xae00
+#define ACPI_PCIHP_SIZE 0x0014
+#define ACPI_PCIHP_LEGACY_SIZE 0x000f
+#define PCI_UP_BASE 0x0000
+#define PCI_DOWN_BASE 0x0004
+#define PCI_EJ_BASE 0x0008
+#define PCI_RMV_BASE 0x000c
+#define PCI_SEL_BASE 0x0010
+
+typedef struct AcpiPciHpFind {
+    int bsel;
+    PCIBus *bus;
+} AcpiPciHpFind;
+
+static int acpi_pcihp_get_bsel(PCIBus *bus)
+{
+    QObject *o = object_property_get_qobject(OBJECT(bus),
+                                             ACPI_PCIHP_PROP_BSEL, NULL);
+    int64_t bsel = -1;
+    if (o) {
+        bsel = qint_get_int(qobject_to_qint(o));
+    }
+    if (bsel < 0) {
+        return -1;
+    }
+    return bsel;
+}
+
+static void acpi_pcihp_test_hotplug_bus(PCIBus *bus, void *opaque)
+{
+    AcpiPciHpFind *find = opaque;
+    if (find->bsel == acpi_pcihp_get_bsel(bus)) {
+        find->bus = bus;
+    }
+}
+
+static PCIBus *acpi_pcihp_find_hotplug_bus(AcpiPciHpState *s, int bsel)
+{
+    AcpiPciHpFind find = { .bsel = bsel, .bus = NULL };
+
+    if (bsel < 0) {
+        return NULL;
+    }
+
+    pci_for_each_bus(s->root, acpi_pcihp_test_hotplug_bus, &find);
+
+    /* Make bsel 0 eject root bus if bsel property is not set,
+     * for compatibility with non acpi setups.
+     * TODO: really needed?
+     */
+    if (!bsel && !find.bus) {
+        find.bus = s->root;
+    }
+    return find.bus;
+}
+
+static bool acpi_pcihp_pc_no_hotplug(AcpiPciHpState *s, PCIDevice *dev)
+{
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
+    DeviceClass *dc = DEVICE_GET_CLASS(dev);
+    /*
+     * ACPI doesn't allow hotplug of bridge devices.  Don't allow
+     * hot-unplug of bridge devices unless they were added by hotplug
+     * (and so, not described by acpi).
+     */
+    return (pc->is_bridge && !dev->qdev.hotplugged) || !dc->hotpluggable;
+}
+
+static void acpi_pcihp_eject_slot(AcpiPciHpState *s, unsigned bsel, unsigned slots)
+{
+    BusChild *kid, *next;
+    int slot = ffs(slots) - 1;
+    PCIBus *bus = acpi_pcihp_find_hotplug_bus(s, bsel);
+
+    if (!bus) {
+        return;
+    }
+
+    /* Mark request as complete */
+    s->acpi_pcihp_pci_status[bsel].down &= ~(1U << slot);
+    s->acpi_pcihp_pci_status[bsel].up &= ~(1U << slot);
+
+    QTAILQ_FOREACH_SAFE(kid, &bus->qbus.children, sibling, next) {
+        DeviceState *qdev = kid->child;
+        PCIDevice *dev = PCI_DEVICE(qdev);
+        if (PCI_SLOT(dev->devfn) == slot) {
+            if (!acpi_pcihp_pc_no_hotplug(s, dev)) {
+                object_unparent(OBJECT(qdev));
+            }
+        }
+    }
+}
+
+static void acpi_pcihp_update_hotplug_bus(AcpiPciHpState *s, int bsel)
+{
+    BusChild *kid, *next;
+    PCIBus *bus = acpi_pcihp_find_hotplug_bus(s, bsel);
+
+    /* Execute any pending removes during reset */
+    while (s->acpi_pcihp_pci_status[bsel].down) {
+        acpi_pcihp_eject_slot(s, bsel, s->acpi_pcihp_pci_status[bsel].down);
+    }
+
+    s->acpi_pcihp_pci_status[bsel].hotplug_enable = ~0;
+
+    if (!bus) {
+        return;
+    }
+    QTAILQ_FOREACH_SAFE(kid, &bus->qbus.children, sibling, next) {
+        DeviceState *qdev = kid->child;
+        PCIDevice *pdev = PCI_DEVICE(qdev);
+        int slot = PCI_SLOT(pdev->devfn);
+
+        if (acpi_pcihp_pc_no_hotplug(s, pdev)) {
+            s->acpi_pcihp_pci_status[bsel].hotplug_enable &= ~(1U << slot);
+        }
+    }
+}
+
+static void acpi_pcihp_update(AcpiPciHpState *s)
+{
+    int i;
+
+    for (i = 0; i < ACPI_PCIHP_MAX_HOTPLUG_BUS; ++i) {
+        acpi_pcihp_update_hotplug_bus(s, i);
+    }
+}
+
+void acpi_pcihp_reset(AcpiPciHpState *s)
+{
+    acpi_pcihp_update(s);
+}
+
+void acpi_pcihp_device_plug_cb(ACPIREGS *ar, qemu_irq irq, AcpiPciHpState *s,
+                               DeviceState *dev, Error **errp)
+{
+    PCIDevice *pdev = PCI_DEVICE(dev);
+    int slot = PCI_SLOT(pdev->devfn);
+    int bsel = acpi_pcihp_get_bsel(pdev->bus);
+    if (bsel < 0) {
+        error_setg(errp, "Unsupported bus. Bus doesn't have property '"
+                   ACPI_PCIHP_PROP_BSEL "' set");
+        return;
+    }
+
+    /* Don't send event when device is enabled during qemu machine creation:
+     * it is present on boot, no hotplug event is necessary. We do send an
+     * event when the device is disabled later. */
+    if (!dev->hotplugged) {
+        return;
+    }
+
+    s->acpi_pcihp_pci_status[bsel].up |= (1U << slot);
+
+    ar->gpe.sts[0] |= ACPI_PCI_HOTPLUG_STATUS;
+    acpi_update_sci(ar, irq);
+}
+
+void acpi_pcihp_device_unplug_cb(ACPIREGS *ar, qemu_irq irq, AcpiPciHpState *s,
+                                 DeviceState *dev, Error **errp)
+{
+    PCIDevice *pdev = PCI_DEVICE(dev);
+    int slot = PCI_SLOT(pdev->devfn);
+    int bsel = acpi_pcihp_get_bsel(pdev->bus);
+    if (bsel < 0) {
+        error_setg(errp, "Unsupported bus. Bus doesn't have property '"
+                   ACPI_PCIHP_PROP_BSEL "' set");
+        return;
+    }
+
+    s->acpi_pcihp_pci_status[bsel].down |= (1U << slot);
+
+    ar->gpe.sts[0] |= ACPI_PCI_HOTPLUG_STATUS;
+    acpi_update_sci(ar, irq);
+}
+
+static uint64_t pci_read(void *opaque, hwaddr addr, unsigned int size)
+{
+    AcpiPciHpState *s = opaque;
+    uint32_t val = 0;
+    int bsel = s->hotplug_select;
+
+    if (bsel < 0 || bsel > ACPI_PCIHP_MAX_HOTPLUG_BUS) {
+        return 0;
+    }
+
+    switch (addr) {
+    case PCI_UP_BASE:
+        val = s->acpi_pcihp_pci_status[bsel].up;
+        if (!s->legacy_piix) {
+            s->acpi_pcihp_pci_status[bsel].up = 0;
+        }
+        ACPI_PCIHP_DPRINTF("pci_up_read %" PRIu32 "\n", val);
+        break;
+    case PCI_DOWN_BASE:
+        val = s->acpi_pcihp_pci_status[bsel].down;
+        ACPI_PCIHP_DPRINTF("pci_down_read %" PRIu32 "\n", val);
+        break;
+    case PCI_EJ_BASE:
+        /* No feature defined yet */
+        ACPI_PCIHP_DPRINTF("pci_features_read %" PRIu32 "\n", val);
+        break;
+    case PCI_RMV_BASE:
+        val = s->acpi_pcihp_pci_status[bsel].hotplug_enable;
+        ACPI_PCIHP_DPRINTF("pci_rmv_read %" PRIu32 "\n", val);
+        break;
+    case PCI_SEL_BASE:
+        val = s->hotplug_select;
+        ACPI_PCIHP_DPRINTF("pci_sel_read %" PRIu32 "\n", val);
+    default:
+        break;
+    }
+
+    return val;
+}
+
+static void pci_write(void *opaque, hwaddr addr, uint64_t data,
+                      unsigned int size)
+{
+    AcpiPciHpState *s = opaque;
+    switch (addr) {
+    case PCI_EJ_BASE:
+        if (s->hotplug_select >= ACPI_PCIHP_MAX_HOTPLUG_BUS) {
+            break;
+        }
+        acpi_pcihp_eject_slot(s, s->hotplug_select, data);
+        ACPI_PCIHP_DPRINTF("pciej write %" HWADDR_PRIx " <== %" PRIu64 "\n",
+                      addr, data);
+        break;
+    case PCI_SEL_BASE:
+        s->hotplug_select = data;
+        ACPI_PCIHP_DPRINTF("pcisel write %" HWADDR_PRIx " <== %" PRIu64 "\n",
+                      addr, data);
+    default:
+        break;
+    }
+}
+
+static const MemoryRegionOps acpi_pcihp_io_ops = {
+    .read = pci_read,
+    .write = pci_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+    },
+};
+
+void acpi_pcihp_init(AcpiPciHpState *s, PCIBus *root_bus,
+                     MemoryRegion *address_space_io, bool bridges_enabled)
+{
+    uint16_t io_size = ACPI_PCIHP_SIZE;
+
+    s->root= root_bus;
+    s->legacy_piix = !bridges_enabled;
+
+    if (s->legacy_piix) {
+        unsigned *bus_bsel = g_malloc(sizeof *bus_bsel);
+
+        io_size = ACPI_PCIHP_LEGACY_SIZE;
+
+        *bus_bsel = ACPI_PCIHP_BSEL_DEFAULT;
+        object_property_add_uint32_ptr(OBJECT(root_bus), ACPI_PCIHP_PROP_BSEL,
+                                       bus_bsel, NULL);
+    }
+
+    memory_region_init_io(&s->io, NULL, &acpi_pcihp_io_ops, s,
+                          "acpi-pci-hotplug", io_size);
+    memory_region_add_subregion(address_space_io, ACPI_PCIHP_ADDR, &s->io);
+}
+
+const VMStateDescription vmstate_acpi_pcihp_pci_status = {
+    .name = "acpi_pcihp_pci_status",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
+        VMSTATE_UINT32(up, AcpiPciHpPciStatus),
+        VMSTATE_UINT32(down, AcpiPciHpPciStatus),
+        VMSTATE_END_OF_LIST()
+    }
+};

hw/acpi/piix4.c

@@ -30,6 +30,9 @@
 #include "hw/nvram/fw_cfg.h"
 #include "exec/address-spaces.h"
 #include "hw/acpi/piix4.h"
+#include "hw/acpi/pcihp.h"
+#include "hw/acpi/cpu_hotplug.h"
+#include "hw/hotplug.h"
 
 //#define DEBUG
 
@@ -42,28 +45,11 @@
 #define GPE_BASE 0xafe0
 #define GPE_LEN 4
 
-#define PCI_HOTPLUG_ADDR 0xae00
-#define PCI_HOTPLUG_SIZE 0x000f
-#define PCI_UP_BASE 0xae00
-#define PCI_DOWN_BASE 0xae04
-#define PCI_EJ_BASE 0xae08
-#define PCI_RMV_BASE 0xae0c
-
-#define PIIX4_PROC_BASE 0xaf00
-#define PIIX4_PROC_LEN 32
-
-#define PIIX4_PCI_HOTPLUG_STATUS 2
-#define PIIX4_CPU_HOTPLUG_STATUS 4
-
 struct pci_status {
     uint32_t up; /* deprecated, maintained for migration compatibility */
     uint32_t down;
 };
 
-typedef struct CPUStatus {
-    uint8_t sts[PIIX4_PROC_LEN];
-} CPUStatus;
-
 typedef struct PIIX4PMState {
     /*< private >*/
     PCIDevice parent_obj;
@@ -73,8 +59,6 @@ typedef struct PIIX4PMState {
     uint32_t io_base;
 
     MemoryRegion io_gpe;
-    MemoryRegion io_pci;
-    MemoryRegion io_cpu;
     ACPIREGS ar;
 
     APMState apm;
@@ -88,16 +72,14 @@ typedef struct PIIX4PMState {
     Notifier machine_ready;
     Notifier powerdown_notifier;
 
-    /* for pci hotplug */
-    struct pci_status pci0_status;
-    uint32_t pci0_hotplug_enable;
-    uint32_t pci0_slot_device_present;
+    AcpiPciHpState acpi_pci_hotplug;
+    bool use_acpi_pci_hotplug;
 
     uint8_t disable_s3;
     uint8_t disable_s4;
     uint8_t s4_val;
 
-    CPUStatus gpe_cpu;
+    AcpiCpuHotplug gpe_cpu;
     Notifier cpu_added_notifier;
 } PIIX4PMState;
 
@@ -112,29 +94,10 @@ static void piix4_acpi_system_hot_add_init(MemoryRegion *parent,
 #define ACPI_ENABLE 0xf1
 #define ACPI_DISABLE 0xf0
 
-static void pm_update_sci(PIIX4PMState *s)
-{
-    int sci_level, pmsts;
-
-    pmsts = acpi_pm1_evt_get_sts(&s->ar);
-    sci_level = (((pmsts & s->ar.pm1.evt.en) &
-                  (ACPI_BITMASK_RT_CLOCK_ENABLE |
-                   ACPI_BITMASK_POWER_BUTTON_ENABLE |
-                   ACPI_BITMASK_GLOBAL_LOCK_ENABLE |
-                   ACPI_BITMASK_TIMER_ENABLE)) != 0) ||
-        (((s->ar.gpe.sts[0] & s->ar.gpe.en[0]) &
-          (PIIX4_PCI_HOTPLUG_STATUS | PIIX4_CPU_HOTPLUG_STATUS)) != 0);
-
-    qemu_set_irq(s->irq, sci_level);
-    /* schedule a timer interruption if needed */
-    acpi_pm_tmr_update(&s->ar, (s->ar.pm1.evt.en & ACPI_BITMASK_TIMER_ENABLE) &&
-                       !(pmsts & ACPI_BITMASK_TIMER_STATUS));
-}
-
 static void pm_tmr_timer(ACPIREGS *ar)
 {
     PIIX4PMState *s = container_of(ar, PIIX4PMState, ar);
-    pm_update_sci(s);
+    acpi_update_sci(&s->ar, s->irq);
 }
 
 static void apm_ctrl_changed(uint32_t val, void *arg)
@@ -192,17 +155,6 @@ static void pm_write_config(PCIDevice *d,
     }
 }
 
-static void vmstate_pci_status_pre_save(void *opaque)
-{
-    struct pci_status *pci0_status = opaque;
-    PIIX4PMState *s = container_of(pci0_status, PIIX4PMState, pci0_status);
-
-    /* We no longer track up, so build a safe value for migrating
-     * to a version that still does... of course these might get lost
-     * by an old buggy implementation, but we try. */
-    pci0_status->up = s->pci0_slot_device_present & s->pci0_hotplug_enable;
-}
-
 static int vmstate_acpi_post_load(void *opaque, int version_id)
 {
     PIIX4PMState *s = opaque;
@@ -238,10 +190,9 @@ static const VMStateDescription vmstate_pci_status = {
     .version_id = 1,
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
-    .pre_save = vmstate_pci_status_pre_save,
     .fields      = (VMStateField []) {
-        VMSTATE_UINT32(up, struct pci_status),
-        VMSTATE_UINT32(down, struct pci_status),
+        VMSTATE_UINT32(up, struct AcpiPciHpPciStatus),
+        VMSTATE_UINT32(down, struct AcpiPciHpPciStatus),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -278,10 +229,23 @@ static int acpi_load_old(QEMUFile *f, void *opaque, int version_id)
         qemu_get_be16s(f, &temp);
     }
 
-    ret = vmstate_load_state(f, &vmstate_pci_status, &s->pci0_status, 1);
+    ret = vmstate_load_state(f, &vmstate_pci_status,
+        &s->acpi_pci_hotplug.acpi_pcihp_pci_status[ACPI_PCIHP_BSEL_DEFAULT], 1);
     return ret;
 }
 
+static bool vmstate_test_use_acpi_pci_hotplug(void *opaque, int version_id)
+{
+    PIIX4PMState *s = opaque;
+    return s->use_acpi_pci_hotplug;
+}
+
+static bool vmstate_test_no_use_acpi_pci_hotplug(void *opaque, int version_id)
+{
+    PIIX4PMState *s = opaque;
+    return !s->use_acpi_pci_hotplug;
+}
+
 /* qemu-kvm 1.2 uses version 3 but advertised as 2
  * To support incoming qemu-kvm 1.2 migration, change version_id
  * and minimum_version_id to 2 below (which breaks migration from
@@ -304,66 +268,18 @@ static const VMStateDescription vmstate_acpi = {
         VMSTATE_TIMER(ar.tmr.timer, PIIX4PMState),
         VMSTATE_INT64(ar.tmr.overflow_time, PIIX4PMState),
         VMSTATE_STRUCT(ar.gpe, PIIX4PMState, 2, vmstate_gpe, ACPIGPE),
-        VMSTATE_STRUCT(pci0_status, PIIX4PMState, 2, vmstate_pci_status,
-                       struct pci_status),
+        VMSTATE_STRUCT_TEST(
+            acpi_pci_hotplug.acpi_pcihp_pci_status[ACPI_PCIHP_BSEL_DEFAULT],
+            PIIX4PMState,
+            vmstate_test_no_use_acpi_pci_hotplug,
+            2, vmstate_pci_status,
+            struct AcpiPciHpPciStatus),
+        VMSTATE_PCI_HOTPLUG(acpi_pci_hotplug, PIIX4PMState,
+                            vmstate_test_use_acpi_pci_hotplug),
         VMSTATE_END_OF_LIST()
     }
 };
 
-static void acpi_piix_eject_slot(PIIX4PMState *s, unsigned slots)
-{
-    BusChild *kid, *next;
-    BusState *bus = qdev_get_parent_bus(DEVICE(s));
-    int slot = ffs(slots) - 1;
-    bool slot_free = true;
-
-    /* Mark request as complete */
-    s->pci0_status.down &= ~(1U << slot);
-
-    QTAILQ_FOREACH_SAFE(kid, &bus->children, sibling, next) {
-        DeviceState *qdev = kid->child;
-        PCIDevice *dev = PCI_DEVICE(qdev);
-        PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
-        if (PCI_SLOT(dev->devfn) == slot) {
-            if (pc->no_hotplug) {
-                slot_free = false;
-            } else {
-                object_unparent(OBJECT(qdev));
-            }
-        }
-    }
-    if (slot_free) {
-        s->pci0_slot_device_present &= ~(1U << slot);
-    }
-}
-
-static void piix4_update_hotplug(PIIX4PMState *s)
-{
-    BusState *bus = qdev_get_parent_bus(DEVICE(s));
-    BusChild *kid, *next;
-
-    /* Execute any pending removes during reset */
-    while (s->pci0_status.down) {
-        acpi_piix_eject_slot(s, s->pci0_status.down);
-    }
-
-    s->pci0_hotplug_enable = ~0;
-    s->pci0_slot_device_present = 0;
-
-    QTAILQ_FOREACH_SAFE(kid, &bus->children, sibling, next) {
-        DeviceState *qdev = kid->child;
-        PCIDevice *pdev = PCI_DEVICE(qdev);
-        PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(pdev);
-        int slot = PCI_SLOT(pdev->devfn);
-
-        if (pc->no_hotplug) {
-            s->pci0_hotplug_enable &= ~(1U << slot);
-        }
-
-        s->pci0_slot_device_present |= (1U << slot);
-    }
-}
-
 static void piix4_reset(void *opaque)
 {
     PIIX4PMState *s = opaque;
@@ -383,7 +299,7 @@ static void piix4_reset(void *opaque)
         pci_conf[0x5B] = 0x02;
     }
     pm_io_space_update(s);
-    piix4_update_hotplug(s);
+    acpi_pcihp_reset(&s->acpi_pci_hotplug);
 }
 
 static void piix4_pm_powerdown_req(Notifier *n, void *opaque)
@@ -394,6 +310,28 @@ static void piix4_pm_powerdown_req(Notifier *n, void *opaque)
     acpi_pm1_evt_power_down(&s->ar);
 }
 
+static void piix4_pci_device_plug_cb(HotplugHandler *hotplug_dev,
+                                     DeviceState *dev, Error **errp)
+{
+    PIIX4PMState *s = PIIX4_PM(hotplug_dev);
+    acpi_pcihp_device_plug_cb(&s->ar, s->irq, &s->acpi_pci_hotplug, dev, errp);
+}
+
+static void piix4_pci_device_unplug_cb(HotplugHandler *hotplug_dev,
+                                       DeviceState *dev, Error **errp)
+{
+    PIIX4PMState *s = PIIX4_PM(hotplug_dev);
+    acpi_pcihp_device_unplug_cb(&s->ar, s->irq, &s->acpi_pci_hotplug, dev,
+                                errp);
+}
+
+static void piix4_update_bus_hotplug(PCIBus *pci_bus, void *opaque)
+{
+    PIIX4PMState *s = opaque;
+
+    qbus_set_hotplug_handler(BUS(pci_bus), DEVICE(s), &error_abort);
+}
+
 static void piix4_pm_machine_ready(Notifier *n, void *opaque)
 {
     PIIX4PMState *s = container_of(n, PIIX4PMState, machine_ready);
@@ -407,6 +345,12 @@ static void piix4_pm_machine_ready(Notifier *n, void *opaque)
     pci_conf[0x63] = 0x60;
     pci_conf[0x67] = (memory_region_present(io_as, 0x3f8) ? 0x08 : 0) |
         (memory_region_present(io_as, 0x2f8) ? 0x90 : 0);
+
+    if (s->use_acpi_pci_hotplug) {
+        pci_for_each_bus(d->bus, piix4_update_bus_hotplug, s);
+    } else {
+        piix4_update_bus_hotplug(d->bus, s);
+    }
 }
 
 static void piix4_pm_add_propeties(PIIX4PMState *s)
@@ -523,46 +467,6 @@ i2c_bus *piix4_pm_init(PCIBus *bus, int devfn, uint32_t smb_io_base,
     return s->smb.smbus;
 }
 
-static Property piix4_pm_properties[] = {
-    DEFINE_PROP_UINT32("smb_io_base", PIIX4PMState, smb_io_base, 0),
-    DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 0),
-    DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 0),
-    DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_VAL, PIIX4PMState, s4_val, 2),
-    DEFINE_PROP_END_OF_LIST(),
-};
-
-static void piix4_pm_class_init(ObjectClass *klass, void *data)
-{
-    DeviceClass *dc = DEVICE_CLASS(klass);
-    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
-
-    k->no_hotplug = 1;
-    k->init = piix4_pm_initfn;
-    k->config_write = pm_write_config;
-    k->vendor_id = PCI_VENDOR_ID_INTEL;
-    k->device_id = PCI_DEVICE_ID_INTEL_82371AB_3;
-    k->revision = 0x03;
-    k->class_id = PCI_CLASS_BRIDGE_OTHER;
-    dc->desc = "PM";
-    dc->no_user = 1;
-    dc->vmsd = &vmstate_acpi;
-    dc->props = piix4_pm_properties;
-}
-
-static const TypeInfo piix4_pm_info = {
-    .name          = TYPE_PIIX4_PM,
-    .parent        = TYPE_PCI_DEVICE,
-    .instance_size = sizeof(PIIX4PMState),
-    .class_init    = piix4_pm_class_init,
-};
-
-static void piix4_pm_register_types(void)
-{
-    type_register_static(&piix4_pm_info);
-}
-
-type_init(piix4_pm_register_types)
-
 static uint64_t gpe_readb(void *opaque, hwaddr addr, unsigned width)
 {
     PIIX4PMState *s = opaque;
@@ -578,7 +482,7 @@ static void gpe_writeb(void *opaque, hwaddr addr, uint64_t val,
     PIIX4PMState *s = opaque;
 
     acpi_gpe_ioport_writeb(&s->ar, addr, val);
-    pm_update_sci(s);
+    acpi_update_sci(&s->ar, s->irq);
 
     PIIX4_DPRINTF("gpe write %" HWADDR_PRIx " <== %" PRIu64 "\n", addr, val);
 }
@@ -593,182 +497,80 @@ static const MemoryRegionOps piix4_gpe_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
-static uint64_t pci_read(void *opaque, hwaddr addr, unsigned int size)
-{
-    PIIX4PMState *s = opaque;
-    uint32_t val = 0;
-
-    switch (addr) {
-    case PCI_UP_BASE - PCI_HOTPLUG_ADDR:
-        /* Manufacture an "up" value to cause a device check on any hotplug
-         * slot with a device.  Extra device checks are harmless. */
-        val = s->pci0_slot_device_present & s->pci0_hotplug_enable;
-        PIIX4_DPRINTF("pci_up_read %" PRIu32 "\n", val);
-        break;
-    case PCI_DOWN_BASE - PCI_HOTPLUG_ADDR:
-        val = s->pci0_status.down;
-        PIIX4_DPRINTF("pci_down_read %" PRIu32 "\n", val);
-        break;
-    case PCI_EJ_BASE - PCI_HOTPLUG_ADDR:
-        /* No feature defined yet */
-        PIIX4_DPRINTF("pci_features_read %" PRIu32 "\n", val);
-        break;
-    case PCI_RMV_BASE - PCI_HOTPLUG_ADDR:
-        val = s->pci0_hotplug_enable;
-        break;
-    default:
-        break;
-    }
-
-    return val;
-}
-
-static void pci_write(void *opaque, hwaddr addr, uint64_t data,
-                      unsigned int size)
-{
-    switch (addr) {
-    case PCI_EJ_BASE - PCI_HOTPLUG_ADDR:
-        acpi_piix_eject_slot(opaque, (uint32_t)data);
-        PIIX4_DPRINTF("pciej write %" HWADDR_PRIx " <== %" PRIu64 "\n",
-                      addr, data);
-        break;
-    default:
-        break;
-    }
-}
-
-static const MemoryRegionOps piix4_pci_ops = {
-    .read = pci_read,
-    .write = pci_write,
-    .endianness = DEVICE_LITTLE_ENDIAN,
-    .valid = {
-        .min_access_size = 4,
-        .max_access_size = 4,
-    },
-};
-
-static uint64_t cpu_status_read(void *opaque, hwaddr addr, unsigned int size)
-{
-    PIIX4PMState *s = opaque;
-    CPUStatus *cpus = &s->gpe_cpu;
-    uint64_t val = cpus->sts[addr];
-
-    return val;
-}
-
-static void cpu_status_write(void *opaque, hwaddr addr, uint64_t data,
-                             unsigned int size)
-{
-    /* TODO: implement VCPU removal on guest signal that CPU can be removed */
-}
-
-static const MemoryRegionOps cpu_hotplug_ops = {
-    .read = cpu_status_read,
-    .write = cpu_status_write,
-    .endianness = DEVICE_LITTLE_ENDIAN,
-    .valid = {
-        .min_access_size = 1,
-        .max_access_size = 1,
-    },
-};
-
-typedef enum {
-    PLUG,
-    UNPLUG,
-} HotplugEventType;
-
-static void piix4_cpu_hotplug_req(PIIX4PMState *s, CPUState *cpu,
-                                  HotplugEventType action)
-{
-    CPUStatus *g = &s->gpe_cpu;
-    ACPIGPE *gpe = &s->ar.gpe;
-    CPUClass *k = CPU_GET_CLASS(cpu);
-    int64_t cpu_id;
-
-    assert(s != NULL);
-
-    *gpe->sts = *gpe->sts | PIIX4_CPU_HOTPLUG_STATUS;
-    cpu_id = k->get_arch_id(CPU(cpu));
-    if (action == PLUG) {
-        g->sts[cpu_id / 8] |= (1 << (cpu_id % 8));
-    } else {
-        g->sts[cpu_id / 8] &= ~(1 << (cpu_id % 8));
-    }
-    pm_update_sci(s);
-}
-
 static void piix4_cpu_added_req(Notifier *n, void *opaque)
 {
     PIIX4PMState *s = container_of(n, PIIX4PMState, cpu_added_notifier);
 
-    piix4_cpu_hotplug_req(s, CPU(opaque), PLUG);
+    assert(s != NULL);
+    AcpiCpuHotplug_add(&s->ar.gpe, &s->gpe_cpu, CPU(opaque));
+    acpi_update_sci(&s->ar, s->irq);
 }
 
-static int piix4_device_hotplug(DeviceState *qdev, PCIDevice *dev,
-                                PCIHotplugState state);
-
 static void piix4_acpi_system_hot_add_init(MemoryRegion *parent,
                                            PCIBus *bus, PIIX4PMState *s)
 {
-    CPUState *cpu;
-
     memory_region_init_io(&s->io_gpe, OBJECT(s), &piix4_gpe_ops, s,
                           "acpi-gpe0", GPE_LEN);
     memory_region_add_subregion(parent, GPE_BASE, &s->io_gpe);
 
-    memory_region_init_io(&s->io_pci, OBJECT(s), &piix4_pci_ops, s,
-                          "acpi-pci-hotplug", PCI_HOTPLUG_SIZE);
-    memory_region_add_subregion(parent, PCI_HOTPLUG_ADDR,
-                                &s->io_pci);
-    pci_bus_hotplug(bus, piix4_device_hotplug, DEVICE(s));
+    acpi_pcihp_init(&s->acpi_pci_hotplug, bus, parent,
+                    s->use_acpi_pci_hotplug);
 
-    CPU_FOREACH(cpu) {
-        CPUClass *cc = CPU_GET_CLASS(cpu);
-        int64_t id = cc->get_arch_id(cpu);
-
-        g_assert((id / 8) < PIIX4_PROC_LEN);
-        s->gpe_cpu.sts[id / 8] |= (1 << (id % 8));
-    }
-    memory_region_init_io(&s->io_cpu, OBJECT(s), &cpu_hotplug_ops, s,
-                          "acpi-cpu-hotplug", PIIX4_PROC_LEN);
-    memory_region_add_subregion(parent, PIIX4_PROC_BASE, &s->io_cpu);
+    AcpiCpuHotplug_init(parent, OBJECT(s), &s->gpe_cpu,
+                        PIIX4_CPU_HOTPLUG_IO_BASE);
     s->cpu_added_notifier.notify = piix4_cpu_added_req;
     qemu_register_cpu_added_notifier(&s->cpu_added_notifier);
 }
 
-static void enable_device(PIIX4PMState *s, int slot)
+static Property piix4_pm_properties[] = {
+    DEFINE_PROP_UINT32("smb_io_base", PIIX4PMState, smb_io_base, 0),
+    DEFINE_PROP_UINT8(ACPI_PM_PROP_S3_DISABLED, PIIX4PMState, disable_s3, 0),
+    DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_DISABLED, PIIX4PMState, disable_s4, 0),
+    DEFINE_PROP_UINT8(ACPI_PM_PROP_S4_VAL, PIIX4PMState, s4_val, 2),
+    DEFINE_PROP_BOOL("acpi-pci-hotplug-with-bridge-support", PIIX4PMState,
+                     use_acpi_pci_hotplug, true),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void piix4_pm_class_init(ObjectClass *klass, void *data)
 {
-    s->ar.gpe.sts[0] |= PIIX4_PCI_HOTPLUG_STATUS;
-    s->pci0_slot_device_present |= (1U << slot);
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+    HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass);
+
+    k->init = piix4_pm_initfn;
+    k->config_write = pm_write_config;
+    k->vendor_id = PCI_VENDOR_ID_INTEL;
+    k->device_id = PCI_DEVICE_ID_INTEL_82371AB_3;
+    k->revision = 0x03;
+    k->class_id = PCI_CLASS_BRIDGE_OTHER;
+    dc->desc = "PM";
+    dc->vmsd = &vmstate_acpi;
+    dc->props = piix4_pm_properties;
+    /*
+     * Reason: part of PIIX4 southbridge, needs to be wired up,
+     * e.g. by mips_malta_init()
+     */
+    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->hotpluggable = false;
+    hc->plug = piix4_pci_device_plug_cb;
+    hc->unplug = piix4_pci_device_unplug_cb;
 }
 
-static void disable_device(PIIX4PMState *s, int slot)
+static const TypeInfo piix4_pm_info = {
+    .name          = TYPE_PIIX4_PM,
+    .parent        = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PIIX4PMState),
+    .class_init    = piix4_pm_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_HOTPLUG_HANDLER },
+        { }
+    }
+};
+
+static void piix4_pm_register_types(void)
 {
-    s->ar.gpe.sts[0] |= PIIX4_PCI_HOTPLUG_STATUS;
-    s->pci0_status.down |= (1U << slot);
+    type_register_static(&piix4_pm_info);
 }
 
-static int piix4_device_hotplug(DeviceState *qdev, PCIDevice *dev,
-				PCIHotplugState state)
-{
-    int slot = PCI_SLOT(dev->devfn);
-    PIIX4PMState *s = PIIX4_PM(qdev);
-
-    /* Don't send event when device is enabled during qemu machine creation:
-     * it is present on boot, no hotplug event is necessary. We do send an
-     * event when the device is disabled later. */
-    if (state == PCI_COLDPLUG_ENABLED) {
-        s->pci0_slot_device_present |= (1U << slot);
-        return 0;
-    }
-
-    if (state == PCI_HOTPLUG_ENABLED) {
-        enable_device(s, slot);
-    } else {
-        disable_device(s, slot);
-    }
-
-    pm_update_sci(s);
-
-    return 0;
-}
+type_init(piix4_pm_register_types)

hw/alpha/dp264.c

@@ -161,8 +161,9 @@ static void clipper_init(QEMUMachineInitArgs *args)
             load_image_targphys(initrd_filename, initrd_base,
                                 ram_size - initrd_base);
 
-            stq_phys(param_offset + 0x100, initrd_base + 0xfffffc0000000000ULL);
-            stq_phys(param_offset + 0x108, initrd_size);
+            stq_phys(&address_space_memory,
+                     param_offset + 0x100, initrd_base + 0xfffffc0000000000ULL);
+            stq_phys(&address_space_memory, param_offset + 0x108, initrd_size);
         }
     }
 }

hw/alpha/typhoon.c

@@ -613,7 +613,7 @@ static bool make_iommu_tlbe(hwaddr taddr, hwaddr mask, IOMMUTLBEntry *ret)
    translation, given the address of the PTE.  */
 static bool pte_translate(hwaddr pte_addr, IOMMUTLBEntry *ret)
 {
-    uint64_t pte = ldq_phys(pte_addr);
+    uint64_t pte = ldq_phys(&address_space_memory, pte_addr);
 
     /* Check valid bit.  */
     if ((pte & 1) == 0) {
@@ -934,11 +934,9 @@ static int typhoon_pcihost_init(SysBusDevice *dev)
 
 static void typhoon_pcihost_class_init(ObjectClass *klass, void *data)
 {
-    DeviceClass *dc = DEVICE_CLASS(klass);
     SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass);
 
     k->init = typhoon_pcihost_init;
-    dc->no_user = 1;
 }
 
 static const TypeInfo typhoon_pcihost_info = {

hw/arm/allwinner-a10.c

@@ -31,6 +31,13 @@ static void aw_a10_init(Object *obj)
 
     object_initialize(&s->timer, sizeof(s->timer), TYPE_AW_A10_PIT);
     qdev_set_parent_bus(DEVICE(&s->timer), sysbus_get_default());
+
+    object_initialize(&s->emac, sizeof(s->emac), TYPE_AW_EMAC);
+    qdev_set_parent_bus(DEVICE(&s->emac), sysbus_get_default());
+    if (nd_table[0].used) {
+        qemu_check_nic_model(&nd_table[0], TYPE_AW_EMAC);
+        qdev_set_nic_properties(DEVICE(&s->emac), &nd_table[0]);
+    }
 }
 
 static void aw_a10_realize(DeviceState *dev, Error **errp)
@@ -76,6 +83,15 @@ static void aw_a10_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(sysbusdev, 4, s->irq[67]);
     sysbus_connect_irq(sysbusdev, 5, s->irq[68]);
 
+    object_property_set_bool(OBJECT(&s->emac), true, "realized", &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        return;
+    }
+    sysbusdev = SYS_BUS_DEVICE(&s->emac);
+    sysbus_mmio_map(sysbusdev, 0, AW_A10_EMAC_BASE);
+    sysbus_connect_irq(sysbusdev, 0, s->irq[55]);
+
     serial_mm_init(get_system_memory(), AW_A10_UART0_REG_BASE, 2, s->irq[1],
                    115200, serial_hds[0], DEVICE_NATIVE_ENDIAN);
 }

hw/arm/boot.c

@@ -16,6 +16,7 @@
 #include "elf.h"
 #include "sysemu/device_tree.h"
 #include "qemu/config-file.h"
+#include "exec/address-spaces.h"
 
 /* Kernel boot protocol is specified in the kernel docs
  * Documentation/arm/Booting and Documentation/arm64/booting.txt
@@ -169,12 +170,17 @@ static void default_reset_secondary(ARMCPU *cpu,
 {
     CPUARMState *env = &cpu->env;
 
-    stl_phys_notdirty(info->smp_bootreg_addr, 0);
+    stl_phys_notdirty(&address_space_memory, info->smp_bootreg_addr, 0);
     env->regs[15] = info->smp_loader_start;
 }
 
+static inline bool have_dtb(const struct arm_boot_info *info)
+{
+    return info->dtb_filename || info->get_dtb;
+}
+
 #define WRITE_WORD(p, value) do { \
-    stl_phys_notdirty(p, value);  \
+    stl_phys_notdirty(&address_space_memory, p, value);  \
     p += 4;                       \
 } while (0)
 
@@ -421,7 +427,7 @@ static void do_cpu_reset(void *opaque)
                     env->regs[15] = info->loader_start;
                 }
 
-                if (!info->dtb_filename) {
+                if (!have_dtb(info)) {
                     if (old_param) {
                         set_kernel_args_old(info);
                     } else {
@@ -542,7 +548,7 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info)
         /* for device tree boot, we pass the DTB directly in r2. Otherwise
          * we point to the kernel args.
          */
-        if (info->dtb_filename || info->get_dtb) {
+        if (have_dtb(info)) {
             /* Place the DTB after the initrd in memory. Note that some
              * kernels will trash anything in the 4K page the initrd
              * ends in, so make sure the DTB isn't caught up in that.

hw/arm/cubieboard.c

@@ -36,9 +36,16 @@ static void cubieboard_init(QEMUMachineInitArgs *args)
     Error *err = NULL;
 
     s->a10 = AW_A10(object_new(TYPE_AW_A10));
+
+    object_property_set_int(OBJECT(&s->a10->emac), 1, "phy-addr", &err);
+    if (err != NULL) {
+        error_report("Couldn't set phy address: %s", error_get_pretty(err));
+        exit(1);
+    }
+
     object_property_set_bool(OBJECT(s->a10), true, "realized", &err);
     if (err != NULL) {
-        error_report("Couldn't realize Allwinner A10: %s\n",
+        error_report("Couldn't realize Allwinner A10: %s",
                      error_get_pretty(err));
         exit(1);
     }

hw/arm/highbank.c

@@ -69,11 +69,11 @@ static void hb_reset_secondary(ARMCPU *cpu, const struct arm_boot_info *info)
 
     switch (info->nb_cpus) {
     case 4:
-        stl_phys_notdirty(SMP_BOOT_REG + 0x30, 0);
+        stl_phys_notdirty(&address_space_memory, SMP_BOOT_REG + 0x30, 0);
     case 3:
-        stl_phys_notdirty(SMP_BOOT_REG + 0x20, 0);
+        stl_phys_notdirty(&address_space_memory, SMP_BOOT_REG + 0x20, 0);
     case 2:
-        stl_phys_notdirty(SMP_BOOT_REG + 0x10, 0);
+        stl_phys_notdirty(&address_space_memory, SMP_BOOT_REG + 0x10, 0);
         env->regs[15] = SMP_BOOT_ADDR;
         break;
     default:
@@ -126,7 +126,7 @@ typedef struct {
     SysBusDevice parent_obj;
     /*< public >*/
 
-    MemoryRegion *iomem;
+    MemoryRegion iomem;
     uint32_t regs[NUM_REGS];
 } HighbankRegsState;
 
@@ -155,10 +155,9 @@ static int highbank_regs_init(SysBusDevice *dev)
 {
     HighbankRegsState *s = HIGHBANK_REGISTERS(dev);
 
-    s->iomem = g_new(MemoryRegion, 1);
-    memory_region_init_io(s->iomem, OBJECT(s), &hb_mem_ops, s->regs,
+    memory_region_init_io(&s->iomem, OBJECT(s), &hb_mem_ops, s->regs,
                           "highbank_regs", 0x1000);
-    sysbus_init_mmio(dev, s->iomem);
+    sysbus_init_mmio(dev, &s->iomem);
 
     return 0;
 }

hw/arm/mainstone.c

@@ -45,7 +45,7 @@
 #define S1_STSCHG_IRQ 14
 #define S1_IRQ        15
 
-static struct keymap map[0xE0] = {
+static const struct keymap map[0xE0] = {
     [0 ... 0xDF] = { -1, -1 },
     [0x1e] = {0,0}, /* a */
     [0x30] = {0,1}, /* b */
@@ -75,9 +75,18 @@ static struct keymap map[0xE0] = {
     [0x2c] = {4,3}, /* z */
     [0xc7] = {5,0}, /* Home */
     [0x2a] = {5,1}, /* shift */
-    [0x39] = {5,2}, /* space */
+    /*
+     * There are two matrix positions which map to space,
+     * but QEMU can only use one of them for the reverse
+     * mapping, so simply use the second one.
+     */
+    /* [0x39] = {5,2}, space */
     [0x39] = {5,3}, /* space */
-    [0x1c] = {5,5}, /*  enter */
+    /*
+     * Matrix position {5,4} and other keys are missing here.
+     * TODO: Compare with Linux code and test real hardware.
+     */
+    [0x1c] = {5,5}, /* enter (TODO: might be wrong) */
     [0xc8] = {6,0}, /* up */
     [0xd0] = {6,1}, /* down */
     [0xcb] = {6,2}, /* left */

hw/arm/pxa2xx.c

@@ -1448,7 +1448,7 @@ static const VMStateDescription vmstate_pxa2xx_i2c = {
         VMSTATE_UINT8(ibmr, PXA2xxI2CState),
         VMSTATE_UINT8(data, PXA2xxI2CState),
         VMSTATE_STRUCT_POINTER(slave, PXA2xxI2CState,
-                               vmstate_pxa2xx_i2c_slave, PXA2xxI2CSlaveState *),
+                               vmstate_pxa2xx_i2c_slave, PXA2xxI2CSlaveState),
         VMSTATE_END_OF_LIST()
     }
 };

hw/arm/versatilepb.c

@@ -390,7 +390,6 @@ static void vpb_sic_class_init(ObjectClass *klass, void *data)
     SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass);
 
     k->init = vpb_sic_init;
-    dc->no_user = 1;
     dc->vmsd = &vmstate_vpb_sic;
 }
 

hw/arm/xilinx_zynq.c

@@ -37,6 +37,7 @@
 #define IRQ_OFFSET 32 /* pic interrupts start from index 32 */
 
 #define MPCORE_PERIPHBASE 0xF8F00000
+#define ZYNQ_BOARD_MIDR 0x413FC090
 
 static const int dma_irqs[8] = {
     46, 47, 48, 49, 72, 73, 74, 75
@@ -49,9 +50,11 @@ static void gem_init(NICInfo *nd, uint32_t base, qemu_irq irq)
     DeviceState *dev;
     SysBusDevice *s;
 
-    qemu_check_nic_model(nd, "cadence_gem");
     dev = qdev_create(NULL, "cadence_gem");
+    if (nd->used) {
+        qemu_check_nic_model(nd, "cadence_gem");
         qdev_set_nic_properties(dev, nd);
+    }
     qdev_init_nofail(dev);
     s = SYS_BUS_DEVICE(dev);
     sysbus_mmio_map(s, 0, base);
@@ -113,7 +116,6 @@ static void zynq_init(QEMUMachineInitArgs *args)
     DeviceState *dev;
     SysBusDevice *busdev;
     qemu_irq pic[64];
-    NICInfo *nd;
     Error *err = NULL;
     int n;
 
@@ -124,6 +126,12 @@ static void zynq_init(QEMUMachineInitArgs *args)
 
     cpu = ARM_CPU(object_new(object_class_get_name(cpu_oc)));
 
+    object_property_set_int(OBJECT(cpu), ZYNQ_BOARD_MIDR, "midr", &err);
+    if (err) {
+        error_report("%s", error_get_pretty(err));
+        exit(1);
+    }
+
     object_property_set_int(OBJECT(cpu), MPCORE_PERIPHBASE, "reset-cbar", &err);
     if (err) {
         error_report("%s", error_get_pretty(err));
@@ -190,14 +198,8 @@ static void zynq_init(QEMUMachineInitArgs *args)
     sysbus_create_varargs("cadence_ttc", 0xF8002000,
             pic[69-IRQ_OFFSET], pic[70-IRQ_OFFSET], pic[71-IRQ_OFFSET], NULL);
 
-    for (n = 0; n < nb_nics; n++) {
-        nd = &nd_table[n];
-        if (n == 0) {
-            gem_init(nd, 0xE000B000, pic[54-IRQ_OFFSET]);
-        } else if (n == 1) {
-            gem_init(nd, 0xE000C000, pic[77-IRQ_OFFSET]);
-        }
-    }
+    gem_init(&nd_table[0], 0xE000B000, pic[54-IRQ_OFFSET]);
+    gem_init(&nd_table[1], 0xE000C000, pic[77-IRQ_OFFSET]);
 
     dev = qdev_create(NULL, "generic-sdhci");
     qdev_init_nofail(dev);

hw/arm/z2.c

@@ -33,7 +33,7 @@
 #define DPRINTF(fmt, ...)
 #endif
 
-static struct keymap map[0x100] = {
+static const struct keymap map[0x100] = {
     [0 ... 0xff] = { -1, -1 },
     [0x3b] = {0, 0}, /* Option = F1 */
     [0xc8] = {0, 1}, /* Up */

hw/audio/hda-codec.c

@@ -559,6 +559,21 @@ static int hda_audio_post_load(void *opaque, int version)
     return 0;
 }
 
+static void hda_audio_reset(DeviceState *dev)
+{
+    HDAAudioState *a = DO_UPCAST(HDAAudioState, hda.qdev, dev);
+    HDAAudioStream *st;
+    int i;
+
+    dprint(a, 1, "%s\n", __func__);
+    for (i = 0; i < ARRAY_SIZE(a->st); i++) {
+        st = a->st + i;
+        if (st->node != NULL) {
+            hda_audio_set_running(st, false);
+        }
+    }
+}
+
 static const VMStateDescription vmstate_hda_audio_stream = {
     .name = "hda-audio-stream",
     .version_id = 1,
@@ -640,6 +655,7 @@ static void hda_audio_output_class_init(ObjectClass *klass, void *data)
     k->stream = hda_audio_stream;
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
     dc->desc = "HDA Audio Codec, output-only (line-out)";
+    dc->reset = hda_audio_reset;
     dc->vmsd = &vmstate_hda_audio;
     dc->props = hda_audio_properties;
 }
@@ -662,6 +678,7 @@ static void hda_audio_duplex_class_init(ObjectClass *klass, void *data)
     k->stream = hda_audio_stream;
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
     dc->desc = "HDA Audio Codec, duplex (line-out, line-in)";
+    dc->reset = hda_audio_reset;
     dc->vmsd = &vmstate_hda_audio;
     dc->props = hda_audio_properties;
 }
@@ -684,6 +701,7 @@ static void hda_audio_micro_class_init(ObjectClass *klass, void *data)
     k->stream = hda_audio_stream;
     set_bit(DEVICE_CATEGORY_SOUND, dc->categories);
     dc->desc = "HDA Audio Codec, duplex (speaker, microphone)";
+    dc->reset = hda_audio_reset;
     dc->vmsd = &vmstate_hda_audio;
     dc->props = hda_audio_properties;
 }

hw/audio/intel-hda.c

@@ -900,7 +900,7 @@ static const IntelHDAReg *intel_hda_reg_find(IntelHDAState *d, hwaddr addr)
 {
     const IntelHDAReg *reg;
 
-    if (addr >= sizeof(regtab)/sizeof(regtab[0])) {
+    if (addr >= ARRAY_SIZE(regtab)) {
         goto noreg;
     }
     reg = regtab+addr;
@@ -1025,7 +1025,7 @@ static void intel_hda_regs_reset(IntelHDAState *d)
     uint32_t *addr;
     int i;
 
-    for (i = 0; i < sizeof(regtab)/sizeof(regtab[0]); i++) {
+    for (i = 0; i < ARRAY_SIZE(regtab); i++) {
         if (regtab[i].name == NULL) {
             continue;
         }