virtio_pci: fix level interrupts with irqfd

commit 62c96360ae
    virtio-pci: fix level interrupts
only helps systems without irqfd: on systems with irqfd support we
passed in flag requesting irqfd even when msix is disabled.

As a result, for level interrupts we didn't install an fd handler so
unmasking an fd had no effect.

Fix this up.

Cc: qemu-stable@nongnu.org
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

.mailmap

@@ -2,7 +2,7 @@
 # into proper addresses so that they are counted properly in git shortlog output.
 #
 Andrzej Zaborowski <balrogg@gmail.com> balrog <balrog@c046a42c-6fe2-441c-8c8c-71466251a162>
-Anthony Liguori <aliguori@us.ibm.com> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
+Anthony Liguori <anthony@codemonkey.ws> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
 Aurelien Jarno <aurelien@aurel32.net> aurel32 <aurel32@c046a42c-6fe2-441c-8c8c-71466251a162>
 Blue Swirl <blauwirbel@gmail.com> blueswir1 <blueswir1@c046a42c-6fe2-441c-8c8c-71466251a162>
 Edgar E. Iglesias <edgar.iglesias@gmail.com> edgar_igl <edgar_igl@c046a42c-6fe2-441c-8c8c-71466251a162>

MAINTAINERS

@@ -50,7 +50,7 @@ Descriptions of section entries:
 
 General Project Administration
 ------------------------------
-M: Anthony Liguori <aliguori@us.ibm.com>
+M: Anthony Liguori <anthony@codemonkey.ws>
 M: Paul Brook <paul@codesourcery.com>
 
 Guest CPU cores (TCG):
@@ -509,7 +509,7 @@ F: hw/unicore32/
 X86 Machines
 ------------
 PC
-M: Anthony Liguori <aliguori@us.ibm.com>
+M: Anthony Liguori <anthony@codemonkey.ws>
 S: Supported
 F: hw/i386/pc.[ch]
 F: hw/i386/pc_piix.c
@@ -593,7 +593,7 @@ S: Supported
 F: hw/*/*vhost*
 
 virtio
-M: Anthony Liguori <aliguori@us.ibm.com>
+M: Anthony Liguori <anthony@codemonkey.ws>
 S: Supported
 F: hw/*/virtio*
 
@@ -651,7 +651,7 @@ F: block/
 F: hw/block/
 
 Character Devices
-M: Anthony Liguori <aliguori@us.ibm.com>
+M: Anthony Liguori <anthony@codemonkey.ws>
 S: Maintained
 F: qemu-char.c
 
@@ -689,7 +689,7 @@ F: audio/spiceaudio.c
 F: hw/display/qxl*
 
 Graphics
-M: Anthony Liguori <aliguori@us.ibm.com>
+M: Anthony Liguori <anthony@codemonkey.ws>
 S: Maintained
 F: ui/
 
@@ -699,7 +699,7 @@ S: Odd Fixes
 F: ui/cocoa.m
 
 Main loop
-M: Anthony Liguori <aliguori@us.ibm.com>
+M: Anthony Liguori <anthony@codemonkey.ws>
 S: Supported
 F: vl.c
 
@@ -711,7 +711,7 @@ F: hmp.c
 F: hmp-commands.hx
 
 Network device layer
-M: Anthony Liguori <aliguori@us.ibm.com>
+M: Anthony Liguori <anthony@codemonkey.ws>
 M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Maintained
 F: net/

VERSION

@@ -1 +1 @@
-1.6.1
+1.6.50

aio-posix.c

@@ -23,7 +23,6 @@ struct AioHandler
     GPollFD pfd;
     IOHandler *io_read;
     IOHandler *io_write;
-    AioFlushHandler *io_flush;
     int deleted;
     int pollfds_idx;
     void *opaque;
@@ -47,7 +46,6 @@ void aio_set_fd_handler(AioContext *ctx,
                         int fd,
                         IOHandler *io_read,
                         IOHandler *io_write,
-                        AioFlushHandler *io_flush,
                         void *opaque)
 {
     AioHandler *node;
@@ -84,7 +82,6 @@ void aio_set_fd_handler(AioContext *ctx,
         /* Update handler with latest information */
         node->io_read = io_read;
         node->io_write = io_write;
-        node->io_flush = io_flush;
         node->opaque = opaque;
         node->pollfds_idx = -1;
 
@@ -97,12 +94,10 @@ void aio_set_fd_handler(AioContext *ctx,
 
 void aio_set_event_notifier(AioContext *ctx,
                             EventNotifier *notifier,
-                            EventNotifierHandler *io_read,
-                            AioFlushEventNotifierHandler *io_flush)
+                            EventNotifierHandler *io_read)
 {
     aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       (IOHandler *)io_read, NULL,
-                       (AioFlushHandler *)io_flush, notifier);
+                       (IOHandler *)io_read, NULL, notifier);
 }
 
 bool aio_pending(AioContext *ctx)
@@ -147,8 +142,12 @@ static bool aio_dispatch(AioContext *ctx)
             (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
             node->io_read) {
             node->io_read(node->opaque);
+
+            /* aio_notify() does not count as progress */
+            if (node->opaque != &ctx->notifier) {
                 progress = true;
             }
+        }
         if (!node->deleted &&
             (revents & (G_IO_OUT | G_IO_ERR)) &&
             node->io_write) {
@@ -173,7 +172,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
     int ret;
-    bool busy, progress;
+    bool progress;
 
     progress = false;
 
@@ -200,20 +199,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
     g_array_set_size(ctx->pollfds, 0);
 
     /* fill pollfds */
-    busy = false;
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
         node->pollfds_idx = -1;
-
-        /* If there aren't pending AIO operations, don't invoke callbacks.
-         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
-         * wait indefinitely.
-         */
-        if (!node->deleted && node->io_flush) {
-            if (node->io_flush(node->opaque) == 0) {
-                continue;
-            }
-            busy = true;
-        }
         if (!node->deleted && node->pfd.events) {
             GPollFD pfd = {
                 .fd = node->pfd.fd,
@@ -226,8 +213,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
     ctx->walking_handlers--;
 
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
+    /* early return if we only have the aio_notify() fd */
+    if (ctx->pollfds->len == 1) {
         return progress;
     }
 
@@ -250,6 +237,5 @@ bool aio_poll(AioContext *ctx, bool blocking)
         }
     }
 
-    assert(progress || busy);
-    return true;
+    return progress;
 }

aio-win32.c

@@ -23,7 +23,6 @@
 struct AioHandler {
     EventNotifier *e;
     EventNotifierHandler *io_notify;
-    AioFlushEventNotifierHandler *io_flush;
     GPollFD pfd;
     int deleted;
     QLIST_ENTRY(AioHandler) node;
@@ -31,8 +30,7 @@ struct AioHandler {
 
 void aio_set_event_notifier(AioContext *ctx,
                             EventNotifier *e,
-                            EventNotifierHandler *io_notify,
-                            AioFlushEventNotifierHandler *io_flush)
+                            EventNotifierHandler *io_notify)
 {
     AioHandler *node;
 
@@ -73,7 +71,6 @@ void aio_set_event_notifier(AioContext *ctx,
         }
         /* Update handler with latest information */
         node->io_notify = io_notify;
-        node->io_flush = io_flush;
     }
 
     aio_notify(ctx);
@@ -96,7 +93,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
     HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool busy, progress;
+    bool progress;
     int count;
 
     progress = false;
@@ -126,8 +123,12 @@ bool aio_poll(AioContext *ctx, bool blocking)
         if (node->pfd.revents && node->io_notify) {
             node->pfd.revents = 0;
             node->io_notify(node->e);
+
+            /* aio_notify() does not count as progress */
+            if (node->opaque != &ctx->notifier) {
                 progress = true;
             }
+        }
 
         tmp = node;
         node = QLIST_NEXT(node, node);
@@ -147,19 +148,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
     ctx->walking_handlers++;
 
     /* fill fd sets */
-    busy = false;
     count = 0;
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        /* If there aren't pending AIO operations, don't invoke callbacks.
-         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
-         * wait indefinitely.
-         */
-        if (!node->deleted && node->io_flush) {
-            if (node->io_flush(node->e) == 0) {
-                continue;
-            }
-            busy = true;
-        }
         if (!node->deleted && node->io_notify) {
             events[count++] = event_notifier_get_handle(node->e);
         }
@@ -167,8 +157,8 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
     ctx->walking_handlers--;
 
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
+    /* early return if we only have the aio_notify() fd */
+    if (count == 1) {
         return progress;
     }
 
@@ -196,8 +186,12 @@ bool aio_poll(AioContext *ctx, bool blocking)
                 event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
                 node->io_notify) {
                 node->io_notify(node->e);
+
+                /* aio_notify() does not count as progress */
+                if (node->opaque != &ctx->notifier) {
                     progress = true;
                 }
+            }
 
             tmp = node;
             node = QLIST_NEXT(node, node);
@@ -214,6 +208,5 @@ bool aio_poll(AioContext *ctx, bool blocking)
         events[ret - WAIT_OBJECT_0] = events[--count];
     }
 
-    assert(progress || busy);
-    return true;
+    return progress;
 }

arch_init.c

@@ -342,7 +342,8 @@ ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
 {
     unsigned long base = mr->ram_addr >> TARGET_PAGE_BITS;
     unsigned long nr = base + (start >> TARGET_PAGE_BITS);
-    unsigned long size = base + (int128_get64(mr->size) >> TARGET_PAGE_BITS);
+    uint64_t mr_size = TARGET_PAGE_ALIGN(memory_region_size(mr));
+    unsigned long size = base + (mr_size >> TARGET_PAGE_BITS);
 
     unsigned long next;
 

async.c

@@ -201,7 +201,7 @@ aio_ctx_finalize(GSource     *source)
     AioContext *ctx = (AioContext *) source;
 
     thread_pool_free(ctx->thread_pool);
-    aio_set_event_notifier(ctx, &ctx->notifier, NULL, NULL);
+    aio_set_event_notifier(ctx, &ctx->notifier, NULL);
     event_notifier_cleanup(&ctx->notifier);
     qemu_mutex_destroy(&ctx->bh_lock);
     g_array_free(ctx->pollfds, TRUE);
@@ -243,7 +243,7 @@ AioContext *aio_context_new(void)
     event_notifier_init(&ctx->notifier, false);
     aio_set_event_notifier(ctx, &ctx->notifier, 
                            (EventNotifierHandler *)
-                           event_notifier_test_and_clear, NULL);
+                           event_notifier_test_and_clear);
 
     return ctx;
 }

block.c

@@ -148,7 +148,6 @@ static void bdrv_block_timer(void *opaque)
 
 void bdrv_io_limits_enable(BlockDriverState *bs)
 {
-    qemu_co_queue_init(&bs->throttled_reqs);
     bs->block_timer = qemu_new_timer_ns(vm_clock, bdrv_block_timer, bs);
     bs->io_limits_enabled = true;
 }
@@ -306,6 +305,7 @@ BlockDriverState *bdrv_new(const char *device_name)
     bdrv_iostatus_disable(bs);
     notifier_list_init(&bs->close_notifiers);
     notifier_with_return_list_init(&bs->before_write_notifiers);
+    qemu_co_queue_init(&bs->throttled_reqs);
 
     return bs;
 }
@@ -1428,6 +1428,35 @@ void bdrv_close_all(void)
     }
 }
 
+/* Check if any requests are in-flight (including throttled requests) */
+static bool bdrv_requests_pending(BlockDriverState *bs)
+{
+    if (!QLIST_EMPTY(&bs->tracked_requests)) {
+        return true;
+    }
+    if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
+        return true;
+    }
+    if (bs->file && bdrv_requests_pending(bs->file)) {
+        return true;
+    }
+    if (bs->backing_hd && bdrv_requests_pending(bs->backing_hd)) {
+        return true;
+    }
+    return false;
+}
+
+static bool bdrv_requests_pending_all(void)
+{
+    BlockDriverState *bs;
+    QTAILQ_FOREACH(bs, &bdrv_states, list) {
+        if (bdrv_requests_pending(bs)) {
+            return true;
+        }
+    }
+    return false;
+}
+
 /*
  * Wait for pending requests to complete across all BlockDriverStates
  *
@@ -1442,12 +1471,11 @@ void bdrv_close_all(void)
  */
 void bdrv_drain_all(void)
 {
+    /* Always run first iteration so any pending completion BHs run */
+    bool busy = true;
     BlockDriverState *bs;
-    bool busy;
-
-    do {
-        busy = qemu_aio_wait();
 
+    while (busy) {
         /* FIXME: We do not have timer support here, so this is effectively
          * a busy wait.
          */
@@ -1456,12 +1484,9 @@ void bdrv_drain_all(void)
                 busy = true;
             }
         }
-    } while (busy);
 
-    /* If requests are still pending there is a bug somewhere */
-    QTAILQ_FOREACH(bs, &bdrv_states, list) {
-        assert(QLIST_EMPTY(&bs->tracked_requests));
-        assert(qemu_co_queue_empty(&bs->throttled_reqs));
+        busy = bdrv_requests_pending_all();
+        busy |= aio_poll(qemu_get_aio_context(), busy);
     }
 }
 
@@ -1803,11 +1828,8 @@ int bdrv_commit(BlockDriverState *bs)
     buf = g_malloc(COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE);
 
     for (sector = 0; sector < total_sectors; sector += n) {
-        ret = bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n);
-        if (ret < 0) {
-            goto ro_cleanup;
-        }
-        if (ret) {
+        if (bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n)) {
+
             if (bdrv_read(bs, sector, buf, n) != 0) {
                 ret = -EIO;
                 goto ro_cleanup;

block/cow.c

@@ -189,11 +189,7 @@ static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
     int ret, n;
 
     while (nb_sectors > 0) {
-        ret = bdrv_co_is_allocated(bs, sector_num, nb_sectors, &n);
-        if (ret < 0) {
-            return ret;
-        }
-        if (ret) {
+        if (bdrv_co_is_allocated(bs, sector_num, nb_sectors, &n)) {
             ret = bdrv_pread(bs->file,
                         s->cow_sectors_offset + sector_num * 512,
                         buf, n * 512);

block/curl.c

@@ -86,7 +86,6 @@ typedef struct BDRVCURLState {
 
 static void curl_clean_state(CURLState *s);
 static void curl_multi_do(void *arg);
-static int curl_aio_flush(void *opaque);
 
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
                         void *s, void *sp)
@@ -94,17 +93,16 @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
     DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
     switch (action) {
         case CURL_POLL_IN:
-            qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, curl_aio_flush, s);
+            qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, s);
             break;
         case CURL_POLL_OUT:
-            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, curl_aio_flush, s);
+            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, s);
             break;
         case CURL_POLL_INOUT:
-            qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do,
-                                    curl_aio_flush, s);
+            qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do, s);
             break;
         case CURL_POLL_REMOVE:
-            qemu_aio_set_fd_handler(fd, NULL, NULL, NULL, NULL);
+            qemu_aio_set_fd_handler(fd, NULL, NULL, NULL);
             break;
     }
 
@@ -495,21 +493,6 @@ out_noclean:
     return -EINVAL;
 }
 
-static int curl_aio_flush(void *opaque)
-{
-    BDRVCURLState *s = opaque;
-    int i, j;
-
-    for (i=0; i < CURL_NUM_STATES; i++) {
-        for(j=0; j < CURL_NUM_ACB; j++) {
-            if (s->states[i].acb[j]) {
-                return 1;
-            }
-        }
-    }
-    return 0;
-}
-
 static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     // Do we have to implement canceling? Seems to work without...

block/gluster.c

@@ -32,7 +32,6 @@ typedef struct BDRVGlusterState {
     struct glfs *glfs;
     int fds[2];
     struct glfs_fd *fd;
-    int qemu_aio_count;
     int event_reader_pos;
     GlusterAIOCB *event_acb;
 } BDRVGlusterState;
@@ -247,7 +246,6 @@ static void qemu_gluster_complete_aio(GlusterAIOCB *acb, BDRVGlusterState *s)
         ret = -EIO; /* Partial read/write - fail it */
     }
 
-    s->qemu_aio_count--;
     qemu_aio_release(acb);
     cb(opaque, ret);
     if (finished) {
@@ -275,13 +273,6 @@ static void qemu_gluster_aio_event_reader(void *opaque)
     } while (ret < 0 && errno == EINTR);
 }
 
-static int qemu_gluster_aio_flush_cb(void *opaque)
-{
-    BDRVGlusterState *s = opaque;
-
-    return (s->qemu_aio_count > 0);
-}
-
 /* TODO Convert to fine grained options */
 static QemuOptsList runtime_opts = {
     .name = "gluster",
@@ -348,7 +339,7 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
     }
     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, qemu_gluster_aio_flush_cb, s);
+        qemu_gluster_aio_event_reader, NULL, s);
 
 out:
     qemu_opts_del(opts);
@@ -445,11 +436,9 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
         qemu_mutex_lock_iothread(); /* We are in gluster thread context */
         acb->common.cb(acb->common.opaque, -EIO);
         qemu_aio_release(acb);
-        s->qemu_aio_count--;
         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,
-            NULL);
+        qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL);
         bs->drv = NULL; /* Make the disk inaccessible */
         qemu_mutex_unlock_iothread();
     }
@@ -467,7 +456,6 @@ static BlockDriverAIOCB *qemu_gluster_aio_rw(BlockDriverState *bs,
 
     offset = sector_num * BDRV_SECTOR_SIZE;
     size = nb_sectors * BDRV_SECTOR_SIZE;
-    s->qemu_aio_count++;
 
     acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
     acb->size = size;
@@ -488,7 +476,6 @@ static BlockDriverAIOCB *qemu_gluster_aio_rw(BlockDriverState *bs,
     return &acb->common;
 
 out:
-    s->qemu_aio_count--;
     qemu_aio_release(acb);
     return NULL;
 }
@@ -531,7 +518,6 @@ static BlockDriverAIOCB *qemu_gluster_aio_flush(BlockDriverState *bs,
     acb->size = 0;
     acb->ret = 0;
     acb->finished = NULL;
-    s->qemu_aio_count++;
 
     ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
     if (ret < 0) {
@@ -540,7 +526,6 @@ static BlockDriverAIOCB *qemu_gluster_aio_flush(BlockDriverState *bs,
     return &acb->common;
 
 out:
-    s->qemu_aio_count--;
     qemu_aio_release(acb);
     return NULL;
 }
@@ -563,7 +548,6 @@ static BlockDriverAIOCB *qemu_gluster_aio_discard(BlockDriverState *bs,
     acb->size = 0;
     acb->ret = 0;
     acb->finished = NULL;
-    s->qemu_aio_count++;
 
     ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
     if (ret < 0) {
@@ -572,7 +556,6 @@ static BlockDriverAIOCB *qemu_gluster_aio_discard(BlockDriverState *bs,
     return &acb->common;
 
 out:
-    s->qemu_aio_count--;
     qemu_aio_release(acb);
     return NULL;
 }
@@ -611,7 +594,7 @@ static void qemu_gluster_close(BlockDriverState *bs)
 
     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, NULL);
+    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL);
 
     if (s->fd) {
         glfs_close(s->fd);

block/iscsi.c

@@ -146,13 +146,6 @@ static const AIOCBInfo iscsi_aiocb_info = {
 static void iscsi_process_read(void *arg);
 static void iscsi_process_write(void *arg);
 
-static int iscsi_process_flush(void *arg)
-{
-    IscsiLun *iscsilun = arg;
-
-    return iscsi_queue_length(iscsilun->iscsi) > 0;
-}
-
 static void
 iscsi_set_events(IscsiLun *iscsilun)
 {
@@ -166,7 +159,6 @@ iscsi_set_events(IscsiLun *iscsilun)
         qemu_aio_set_fd_handler(iscsi_get_fd(iscsi),
                       iscsi_process_read,
                       (ev & POLLOUT) ? iscsi_process_write : NULL,
-                      iscsi_process_flush,
                       iscsilun);
 
     }
@@ -1215,7 +1207,7 @@ static void iscsi_close(BlockDriverState *bs)
         qemu_del_timer(iscsilun->nop_timer);
         qemu_free_timer(iscsilun->nop_timer);
     }
-    qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), NULL, NULL, NULL);
     iscsi_destroy_context(iscsi);
     memset(iscsilun, 0, sizeof(IscsiLun));
 }

block/linux-aio.c

@@ -39,7 +39,6 @@ struct qemu_laiocb {
 struct qemu_laio_state {
     io_context_t ctx;
     EventNotifier e;
-    int count;
 };
 
 static inline ssize_t io_event_ret(struct io_event *ev)
@@ -55,8 +54,6 @@ static void qemu_laio_process_completion(struct qemu_laio_state *s,
 {
     int ret;
 
-    s->count--;
-
     ret = laiocb->ret;
     if (ret != -ECANCELED) {
         if (ret == laiocb->nbytes) {
@@ -101,13 +98,6 @@ static void qemu_laio_completion_cb(EventNotifier *e)
     }
 }
 
-static int qemu_laio_flush_cb(EventNotifier *e)
-{
-    struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
-
-    return (s->count > 0) ? 1 : 0;
-}
-
 static void laio_cancel(BlockDriverAIOCB *blockacb)
 {
     struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
@@ -177,14 +167,11 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         goto out_free_aiocb;
     }
     io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
-    s->count++;
 
     if (io_submit(s->ctx, 1, &iocbs) < 0)
-        goto out_dec_count;
+        goto out_free_aiocb;
     return &laiocb->common;
 
-out_dec_count:
-    s->count--;
 out_free_aiocb:
     qemu_aio_release(laiocb);
     return NULL;
@@ -203,8 +190,7 @@ void *laio_init(void)
         goto out_close_efd;
     }
 
-    qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb,
-                                qemu_laio_flush_cb);
+    qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb);
 
     return s;
 

block/nbd.c

@@ -279,13 +279,6 @@ static void nbd_coroutine_start(BDRVNBDState *s, struct nbd_request *request)
     request->handle = INDEX_TO_HANDLE(s, i);
 }
 
-static int nbd_have_request(void *opaque)
-{
-    BDRVNBDState *s = opaque;
-
-    return s->in_flight > 0;
-}
-
 static void nbd_reply_ready(void *opaque)
 {
     BDRVNBDState *s = opaque;
@@ -341,8 +334,7 @@ static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
 
     qemu_co_mutex_lock(&s->send_mutex);
     s->send_coroutine = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write,
-                            nbd_have_request, s);
+    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
     if (qiov) {
         if (!s->is_unix) {
             socket_set_cork(s->sock, 1);
@@ -361,8 +353,7 @@ static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
     } else {
         rc = nbd_send_request(s->sock, request);
     }
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL,
-                            nbd_have_request, s);
+    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
     s->send_coroutine = NULL;
     qemu_co_mutex_unlock(&s->send_mutex);
     return rc;
@@ -438,8 +429,7 @@ static int nbd_establish_connection(BlockDriverState *bs)
     /* Now that we're connected, set the socket to be non-blocking and
      * kick the reply mechanism.  */
     qemu_set_nonblock(sock);
-    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL,
-                            nbd_have_request, s);
+    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, s);
 
     s->sock = sock;
     s->size = size;
@@ -459,7 +449,7 @@ static void nbd_teardown_connection(BlockDriverState *bs)
     request.len = 0;
     nbd_send_request(s->sock, &request);
 
-    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL);
     closesocket(s->sock);
 }
 

block/qcow2.c

@@ -648,11 +648,13 @@ static int coroutine_fn qcow2_co_is_allocated(BlockDriverState *bs,
     int ret;
 
     *pnum = nb_sectors;
+    /* FIXME We can get errors here, but the bdrv_co_is_allocated interface
+     * can't pass them on today */
     qemu_co_mutex_lock(&s->lock);
     ret = qcow2_get_cluster_offset(bs, sector_num << 9, pnum, &cluster_offset);
     qemu_co_mutex_unlock(&s->lock);
     if (ret < 0) {
-        return ret;
+        *pnum = 0;
     }
 
     return (cluster_offset != 0) || (ret == QCOW2_CLUSTER_ZERO);

block/raw-win32.c

@@ -535,29 +535,13 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVRawState *s = bs->opaque;
     int access_flags, create_flags;
-    int ret = 0;
     DWORD overlapped;
     char device_name[64];
-
-    Error *local_err = NULL;
-    const char *filename;
-
-    QemuOpts *opts = qemu_opts_create_nofail(&raw_runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        ret = -EINVAL;
-        goto done;
-    }
-
-    filename = qemu_opt_get(opts, "filename");
+    const char *filename = qdict_get_str(options, "filename");
 
     if (strstart(filename, "/dev/cdrom", NULL)) {
-        if (find_cdrom(device_name, sizeof(device_name)) < 0) {
-            ret = -ENOENT;
-            goto done;
-        }
+        if (find_cdrom(device_name, sizeof(device_name)) < 0)
+            return -ENOENT;
         filename = device_name;
     } else {
         /* transform drive letters into device name */
@@ -580,17 +564,11 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags)
     if (s->hfile == INVALID_HANDLE_VALUE) {
         int err = GetLastError();
 
-        if (err == ERROR_ACCESS_DENIED) {
-            ret = -EACCES;
-        } else {
-            ret = -1;
+        if (err == ERROR_ACCESS_DENIED)
+            return -EACCES;
+        return -1;
     }
-        goto done;
-    }
-
-done:
-    qemu_opts_del(opts);
-    return ret;
+    return 0;
 }
 
 static BlockDriver bdrv_host_device = {

block/rbd.c

@@ -100,7 +100,6 @@ typedef struct BDRVRBDState {
     rados_ioctx_t io_ctx;
     rbd_image_t image;
     char name[RBD_MAX_IMAGE_NAME_SIZE];
-    int qemu_aio_count;
     char *snap;
     int event_reader_pos;
     RADOSCB *event_rcb;
@@ -428,19 +427,11 @@ static void qemu_rbd_aio_event_reader(void *opaque)
             if (s->event_reader_pos == sizeof(s->event_rcb)) {
                 s->event_reader_pos = 0;
                 qemu_rbd_complete_aio(s->event_rcb);
-                s->qemu_aio_count--;
             }
         }
     } while (ret < 0 && errno == EINTR);
 }
 
-static int qemu_rbd_aio_flush_cb(void *opaque)
-{
-    BDRVRBDState *s = opaque;
-
-    return (s->qemu_aio_count > 0);
-}
-
 /* TODO Convert to fine grained options */
 static QemuOptsList runtime_opts = {
     .name = "rbd",
@@ -554,7 +545,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags)
     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, qemu_rbd_aio_flush_cb, s);
+                            NULL, s);
 
 
     qemu_opts_del(opts);
@@ -578,7 +569,7 @@ static void qemu_rbd_close(BlockDriverState *bs)
 
     close(s->fds[0]);
     close(s->fds[1]);
-    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL, NULL, NULL);
 
     rbd_close(s->image);
     rados_ioctx_destroy(s->io_ctx);
@@ -741,8 +732,6 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     off = sector_num * BDRV_SECTOR_SIZE;
     size = nb_sectors * BDRV_SECTOR_SIZE;
 
-    s->qemu_aio_count++; /* All the RADOSCB */
-
     rcb = g_malloc(sizeof(RADOSCB));
     rcb->done = 0;
     rcb->acb = acb;
@@ -779,7 +768,6 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
 
 failed:
     g_free(rcb);
-    s->qemu_aio_count--;
     qemu_aio_release(acb);
     return NULL;
 }
@@ -934,7 +922,7 @@ static int qemu_rbd_snap_list(BlockDriverState *bs,
     do {
         snaps = g_malloc(sizeof(*snaps) * max_snaps);
         snap_count = rbd_snap_list(s->image, snaps, &max_snaps);
-        if (snap_count <= 0) {
+        if (snap_count < 0) {
             g_free(snaps);
         }
     } while (snap_count == -ERANGE);
@@ -958,7 +946,6 @@ static int qemu_rbd_snap_list(BlockDriverState *bs,
         sn_info->vm_clock_nsec = 0;
     }
     rbd_snap_list_end(snaps);
-    g_free(snaps);
 
  done:
     *psn_tab = sn_tab;

block/sheepdog.c

@@ -509,13 +509,6 @@ static void restart_co_req(void *opaque)
     qemu_coroutine_enter(co, NULL);
 }
 
-static int have_co_req(void *opaque)
-{
-    /* this handler is set only when there is a pending request, so
-     * always returns 1. */
-    return 1;
-}
-
 typedef struct SheepdogReqCo {
     int sockfd;
     SheepdogReq *hdr;
@@ -538,14 +531,14 @@ static coroutine_fn void do_co_req(void *opaque)
     unsigned int *rlen = srco->rlen;
 
     co = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, have_co_req, co);
+    qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, co);
 
     ret = send_co_req(sockfd, hdr, data, wlen);
     if (ret < 0) {
         goto out;
     }
 
-    qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, have_co_req, co);
+    qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, co);
 
     ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr));
     if (ret < sizeof(*hdr)) {
@@ -570,7 +563,7 @@ static coroutine_fn void do_co_req(void *opaque)
 out:
     /* there is at most one request for this sockfd, so it is safe to
      * set each handler to NULL. */
-    qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL);
 
     srco->ret = ret;
     srco->finished = true;
@@ -796,14 +789,6 @@ static void co_write_request(void *opaque)
     qemu_coroutine_enter(s->co_send, NULL);
 }
 
-static int aio_flush_request(void *opaque)
-{
-    BDRVSheepdogState *s = opaque;
-
-    return !QLIST_EMPTY(&s->inflight_aio_head) ||
-        !QLIST_EMPTY(&s->pending_aio_head);
-}
-
 /*
  * Return a socket discriptor to read/write objects.
  *
@@ -819,7 +804,7 @@ static int get_sheep_fd(BDRVSheepdogState *s)
         return fd;
     }
 
-    qemu_aio_set_fd_handler(fd, co_read_response, NULL, aio_flush_request, s);
+    qemu_aio_set_fd_handler(fd, co_read_response, NULL, s);
     return fd;
 }
 
@@ -1069,8 +1054,7 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
 
     qemu_co_mutex_lock(&s->lock);
     s->co_send = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->fd, co_read_response, co_write_request,
-                            aio_flush_request, s);
+    qemu_aio_set_fd_handler(s->fd, co_read_response, co_write_request, s);
     socket_set_cork(s->fd, 1);
 
     /* send a header */
@@ -1091,8 +1075,7 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
     }
 
     socket_set_cork(s->fd, 0);
-    qemu_aio_set_fd_handler(s->fd, co_read_response, NULL,
-                            aio_flush_request, s);
+    qemu_aio_set_fd_handler(s->fd, co_read_response, NULL, s);
     qemu_co_mutex_unlock(&s->lock);
 
     return 0;
@@ -1350,7 +1333,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags)
     g_free(buf);
     return 0;
 out:
-    qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL);
     if (s->fd >= 0) {
         closesocket(s->fd);
     }
@@ -1578,7 +1561,7 @@ static void sd_close(BlockDriverState *bs)
         error_report("%s, %s", sd_strerror(rsp->result), s->name);
     }
 
-    qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL);
     closesocket(s->fd);
     g_free(s->host_spec);
 }

block/ssh.c

@@ -740,14 +740,6 @@ static void restart_coroutine(void *opaque)
     qemu_coroutine_enter(co, NULL);
 }
 
-/* Always true because when we have called set_fd_handler there is
- * always a request being processed.
- */
-static int return_true(void *opaque)
-{
-    return 1;
-}
-
 static coroutine_fn void set_fd_handler(BDRVSSHState *s)
 {
     int r;
@@ -766,13 +758,13 @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s)
     DPRINTF("s->sock=%d rd_handler=%p wr_handler=%p", s->sock,
             rd_handler, wr_handler);
 
-    qemu_aio_set_fd_handler(s->sock, rd_handler, wr_handler, return_true, co);
+    qemu_aio_set_fd_handler(s->sock, rd_handler, wr_handler, co);
 }
 
 static coroutine_fn void clear_fd_handler(BDRVSSHState *s)
 {
     DPRINTF("s->sock=%d", s->sock);
-    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL);
 }
 
 /* A non-blocking call returned EAGAIN, so yield, ensuring the

block/stream.c

@@ -57,6 +57,11 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
     BlockDriverState *intermediate;
     intermediate = top->backing_hd;
 
+    /* Must assign before bdrv_delete() to prevent traversing dangling pointer
+     * while we delete backing image instances.
+     */
+    top->backing_hd = base;
+
     while (intermediate) {
         BlockDriverState *unused;
 
@@ -70,7 +75,6 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
         unused->backing_hd = NULL;
         bdrv_delete(unused);
     }
-    top->backing_hd = base;
 }
 
 static void coroutine_fn stream_run(void *opaque)
@@ -120,7 +124,7 @@ wait:
         if (ret == 1) {
             /* Allocated in the top, no need to copy.  */
             copy = false;
-        } else if (ret >= 0) {
+        } else {
             /* Copy if allocated in the intermediate images.  Limit to the
              * known-unallocated area [sector_num, sector_num+n).  */
             ret = bdrv_co_is_allocated_above(bs->backing_hd, base,

block/vmdk.c

@@ -105,7 +105,7 @@ typedef struct VmdkExtent {
     uint32_t l2_cache_offsets[L2_CACHE_SIZE];
     uint32_t l2_cache_counts[L2_CACHE_SIZE];
 
-    int64_t cluster_sectors;
+    unsigned int cluster_sectors;
 } VmdkExtent;
 
 typedef struct BDRVVmdkState {
@@ -416,7 +416,7 @@ static int vmdk_add_extent(BlockDriverState *bs,
     extent->l1_size = l1_size;
     extent->l1_entry_sectors = l2_size * cluster_sectors;
     extent->l2_size = l2_size;
-    extent->cluster_sectors = flat ? sectors : cluster_sectors;
+    extent->cluster_sectors = cluster_sectors;
 
     if (s->num_extents > 1) {
         extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;
@@ -736,7 +736,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
             VmdkExtent *extent;
 
             ret = vmdk_add_extent(bs, extent_file, true, sectors,
-                            0, 0, 0, 0, 0, &extent);
+                            0, 0, 0, 0, sectors, &extent);
             if (ret < 0) {
                 return ret;
             }

blockdev.c

@@ -460,7 +460,7 @@ static DriveInfo *blockdev_init(QemuOpts *all_opts,
     if (qemu_opt_get_bool(opts, "cache.direct", false)) {
         bdrv_flags |= BDRV_O_NOCACHE;
     }
-    if (qemu_opt_get_bool(opts, "cache.no-flush", false)) {
+    if (qemu_opt_get_bool(opts, "cache.no-flush", true)) {
         bdrv_flags |= BDRV_O_NO_FLUSH;
     }
 

configure

@@ -235,7 +235,6 @@ guest_agent=""
 want_tools="yes"
 libiscsi=""
 coroutine=""
-coroutine_pool=""
 seccomp=""
 glusterfs=""
 glusterfs_discard="no"
@@ -872,10 +871,6 @@ for opt do
   ;;
   --with-coroutine=*) coroutine="$optarg"
   ;;
-  --disable-coroutine-pool) coroutine_pool="no"
-  ;;
-  --enable-coroutine-pool) coroutine_pool="yes"
-  ;;
   --disable-docs) docs="no"
   ;;
   --enable-docs) docs="yes"
@@ -1157,8 +1152,6 @@ 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"
@@ -3247,17 +3240,6 @@ else
   esac
 fi
 
-if test "$coroutine_pool" = ""; then
-  if test "$coroutine" = "gthread"; then
-    coroutine_pool=no
-  else
-    coroutine_pool=yes
-  fi
-fi
-if test "$coroutine" = "gthread" -a "$coroutine_pool" = "yes"; then
-  error_exit "'gthread' coroutine backend does not support pool (use --disable-coroutine-pool)"
-fi
-
 ##########################################
 # check if we have open_by_handle_at
 
@@ -3623,7 +3605,6 @@ echo "libiscsi support  $libiscsi"
 echo "build guest agent $guest_agent"
 echo "seccomp support   $seccomp"
 echo "coroutine backend $coroutine"
-echo "coroutine pool    $coroutine_pool"
 echo "GlusterFS support $glusterfs"
 echo "virtio-blk-data-plane $virtio_blk_data_plane"
 echo "gcov              $gcov_tool"
@@ -3973,11 +3954,6 @@ if test "$rbd" = "yes" ; then
 fi
 
 echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
-if test "$coroutine_pool" = "yes" ; then
-  echo "CONFIG_COROUTINE_POOL=1" >> $config_host_mak
-else
-  echo "CONFIG_COROUTINE_POOL=0" >> $config_host_mak
-fi
 
 if test "$open_by_handle_at" = "yes" ; then
   echo "CONFIG_OPEN_BY_HANDLE=y" >> $config_host_mak

cpus.c

@@ -62,12 +62,17 @@
 
 static CPUState *next_cpu;
 
+bool cpu_is_stopped(CPUState *cpu)
+{
+    return cpu->stopped || !runstate_is_running();
+}
+
 static bool cpu_thread_is_idle(CPUState *cpu)
 {
     if (cpu->stop || cpu->queued_work_first) {
         return false;
     }
-    if (cpu->stopped || !runstate_is_running()) {
+    if (cpu_is_stopped(cpu)) {
         return true;
     }
     if (!cpu->halted || qemu_cpu_has_work(cpu) ||
@@ -429,11 +434,6 @@ void cpu_synchronize_all_post_init(void)
     }
 }
 
-bool cpu_is_stopped(CPUState *cpu)
-{
-    return !runstate_is_running() || cpu->stopped;
-}
-
 static int do_vm_stop(RunState state)
 {
     int ret = 0;
@@ -457,7 +457,7 @@ static bool cpu_can_run(CPUState *cpu)
     if (cpu->stop) {
         return false;
     }
-    if (cpu->stopped || !runstate_is_running()) {
+    if (cpu_is_stopped(cpu)) {
         return false;
     }
     return true;

default-configs/arm-softmmu.mak

@@ -34,9 +34,9 @@ CONFIG_PFLASH_CFI02=y
 CONFIG_MICRODRIVE=y
 CONFIG_USB_MUSB=y
 
-CONFIG_ARM9MPCORE=y
 CONFIG_ARM11MPCORE=y
-CONFIG_ARM15MPCORE=y
+CONFIG_A9MPCORE=y
+CONFIG_A15MPCORE=y
 
 CONFIG_ARM_GIC=y
 CONFIG_ARM_GIC_KVM=$(CONFIG_KVM)

docs/q35-chipset.cfg

@@ -91,6 +91,29 @@
   port = "4"
   chassis = "4"
 
+##
+# Example PCIe switch with two downstream ports
+#
+#[device "pcie-switch-upstream-port-1"]
+#  driver = "x3130-upstream"
+#  bus = "ich9-pcie-port-4"
+#  addr = "00.0"
+#
+#[device "pcie-switch-downstream-port-1-1"]
+#  driver = "xio3130-downstream"
+#  multifunction = "on"
+#  bus = "pcie-switch-upstream-port-1"
+#  addr = "00.0"
+#  port = "1"
+#  chassis = "5"
+#
+#[device "pcie-switch-downstream-port-1-2"]
+#  driver = "xio3130-downstream"
+#  multifunction = "on"
+#  bus = "pcie-switch-upstream-port-1"
+#  addr = "00.1"
+#  port = "1"
+#  chassis = "6"
 
 [device "ich9-ehci-1"]
   driver = "ich9-usb-ehci1"

exec.c

@@ -869,7 +869,7 @@ static void mem_add(MemoryListener *listener, MemoryRegionSection *section)
         now = remain;
         if (int128_lt(remain.size, page_size)) {
             register_subpage(d, &now);
-        } else if (remain.offset_within_address_space & ~TARGET_PAGE_MASK) {
+        } else if (remain.offset_within_region & ~TARGET_PAGE_MASK) {
             now.size = page_size;
             register_subpage(d, &now);
         } else {
@@ -1172,7 +1172,6 @@ ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
 
     qemu_ram_setup_dump(new_block->host, size);
     qemu_madvise(new_block->host, size, QEMU_MADV_HUGEPAGE);
-    qemu_madvise(new_block->host, size, QEMU_MADV_DONTFORK);
 
     if (kvm_enabled())
         kvm_setup_guest_memory(new_block->host, size);
@@ -1821,8 +1820,7 @@ static void memory_map_init(void)
     address_space_init(&address_space_memory, system_memory, "memory");
 
     system_io = g_malloc(sizeof(*system_io));
-    memory_region_init_io(system_io, NULL, &unassigned_io_ops, NULL, "io",
-                          65536);
+    memory_region_init(system_io, NULL, "io", 65536);
     address_space_init(&address_space_io, system_io, "I/O");
 
     memory_listener_register(&core_memory_listener, &address_space_memory);
@@ -1930,9 +1928,6 @@ static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
     if (l > access_size_max) {
         l = access_size_max;
     }
-    if (l & (l - 1)) {
-        l = 1 << (qemu_fls(l) - 1);
-    }
 
     return l;
 }

hw/acpi/core.c

@@ -324,13 +324,12 @@ static void acpi_notify_wakeup(Notifier *notifier, void *data)
             (ACPI_BITMASK_WAKE_STATUS | ACPI_BITMASK_TIMER_STATUS);
         break;
     case QEMU_WAKEUP_REASON_OTHER:
+    default:
         /* ACPI_BITMASK_WAKE_STATUS should be set on resume.
            Pretend that resume was caused by power button */
         ar->pm1.evt.sts |=
             (ACPI_BITMASK_WAKE_STATUS | ACPI_BITMASK_POWER_BUTTON_STATUS);
         break;
-    default:
-        break;
     }
 }
 

hw/acpi/piix4.c

@@ -380,7 +380,6 @@ static void piix4_reset(void *opaque)
         /* Mark SMM as already inited (until KVM supports SMM). */
         pci_conf[0x5B] = 0x02;
     }
-    pm_io_space_update(s);
     piix4_update_hotplug(s);
 }
 

hw/alpha/dp264.c

@@ -173,7 +173,6 @@ static QEMUMachine clipper_machine = {
     .init = clipper_init,
     .max_cpus = 4,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void clipper_machine_init(void)

hw/alpha/typhoon.c

@@ -26,9 +26,9 @@ typedef struct TyphoonCchip {
 } TyphoonCchip;
 
 typedef struct TyphoonWindow {
-    uint32_t base_addr;
-    uint32_t mask;
-    uint32_t translated_base_pfn;
+    uint64_t wba;
+    uint64_t wsm;
+    uint64_t tba;
 } TyphoonWindow;
  
 typedef struct TyphoonPchip {
@@ -37,6 +37,10 @@ typedef struct TyphoonPchip {
     MemoryRegion reg_mem;
     MemoryRegion reg_io;
     MemoryRegion reg_conf;
+
+    AddressSpace iommu_as;
+    MemoryRegion iommu;
+
     uint64_t ctl;
     TyphoonWindow win[4];
 } TyphoonPchip;
@@ -209,53 +213,53 @@ static uint64_t pchip_read(void *opaque, hwaddr addr, unsigned size)
     switch (addr) {
     case 0x0000:
         /* WSBA0: Window Space Base Address Register.  */
-        ret = s->pchip.win[0].base_addr;
+        ret = s->pchip.win[0].wba;
         break;
     case 0x0040:
         /* WSBA1 */
-        ret = s->pchip.win[1].base_addr;
+        ret = s->pchip.win[1].wba;
         break;
     case 0x0080:
         /* WSBA2 */
-        ret = s->pchip.win[2].base_addr;
+        ret = s->pchip.win[2].wba;
         break;
     case 0x00c0:
         /* WSBA3 */
-        ret = s->pchip.win[3].base_addr;
+        ret = s->pchip.win[3].wba;
         break;
 
     case 0x0100:
         /* WSM0: Window Space Mask Register.  */
-        ret = s->pchip.win[0].mask;
+        ret = s->pchip.win[0].wsm;
         break;
     case 0x0140:
         /* WSM1 */
-        ret = s->pchip.win[1].mask;
+        ret = s->pchip.win[1].wsm;
         break;
     case 0x0180:
         /* WSM2 */
-        ret = s->pchip.win[2].mask;
+        ret = s->pchip.win[2].wsm;
         break;
     case 0x01c0:
         /* WSM3 */
-        ret = s->pchip.win[3].mask;
+        ret = s->pchip.win[3].wsm;
         break;
 
     case 0x0200:
         /* TBA0: Translated Base Address Register.  */
-        ret = (uint64_t)s->pchip.win[0].translated_base_pfn << 10;
+        ret = s->pchip.win[0].tba;
         break;
     case 0x0240:
         /* TBA1 */
-        ret = (uint64_t)s->pchip.win[1].translated_base_pfn << 10;
+        ret = s->pchip.win[1].tba;
         break;
     case 0x0280:
         /* TBA2 */
-        ret = (uint64_t)s->pchip.win[2].translated_base_pfn << 10;
+        ret = s->pchip.win[2].tba;
         break;
     case 0x02c0:
         /* TBA3 */
-        ret = (uint64_t)s->pchip.win[3].translated_base_pfn << 10;
+        ret = s->pchip.win[3].tba;
         break;
 
     case 0x0300:
@@ -458,53 +462,53 @@ static void pchip_write(void *opaque, hwaddr addr,
     switch (addr) {
     case 0x0000:
         /* WSBA0: Window Space Base Address Register.  */
-        s->pchip.win[0].base_addr = val;
+        s->pchip.win[0].wba = val & 0xfff00003u;
         break;
     case 0x0040:
         /* WSBA1 */
-        s->pchip.win[1].base_addr = val;
+        s->pchip.win[1].wba = val & 0xfff00003u;
         break;
     case 0x0080:
         /* WSBA2 */
-        s->pchip.win[2].base_addr = val;
+        s->pchip.win[2].wba = val & 0xfff00003u;
         break;
     case 0x00c0:
         /* WSBA3 */
-        s->pchip.win[3].base_addr = val;
+        s->pchip.win[3].wba = (val & 0x80fff00001ull) | 2;
         break;
 
     case 0x0100:
         /* WSM0: Window Space Mask Register.  */
-        s->pchip.win[0].mask = val;
+        s->pchip.win[0].wsm = val & 0xfff00000u;
         break;
     case 0x0140:
         /* WSM1 */
-        s->pchip.win[1].mask = val;
+        s->pchip.win[1].wsm = val & 0xfff00000u;
         break;
     case 0x0180:
         /* WSM2 */
-        s->pchip.win[2].mask = val;
+        s->pchip.win[2].wsm = val & 0xfff00000u;
         break;
     case 0x01c0:
         /* WSM3 */
-        s->pchip.win[3].mask = val;
+        s->pchip.win[3].wsm = val & 0xfff00000u;
         break;
 
     case 0x0200:
         /* TBA0: Translated Base Address Register.  */
-        s->pchip.win[0].translated_base_pfn = val >> 10;
+        s->pchip.win[0].tba = val & 0x7fffffc00ull;
         break;
     case 0x0240:
         /* TBA1 */
-        s->pchip.win[1].translated_base_pfn = val >> 10;
+        s->pchip.win[1].tba = val & 0x7fffffc00ull;
         break;
     case 0x0280:
         /* TBA2 */
-        s->pchip.win[2].translated_base_pfn = val >> 10;
+        s->pchip.win[2].tba = val & 0x7fffffc00ull;
         break;
     case 0x02c0:
         /* TBA3 */
-        s->pchip.win[3].translated_base_pfn = val >> 10;
+        s->pchip.win[3].tba = val & 0x7fffffc00ull;
         break;
 
     case 0x0300:
@@ -512,7 +516,6 @@ static void pchip_write(void *opaque, hwaddr addr,
         oldval = s->pchip.ctl;
         oldval &= ~0x00001cff0fc7ffull;       /* RW fields */
         oldval |= val & 0x00001cff0fc7ffull;
-
         s->pchip.ctl = oldval;
         break;
 
@@ -593,6 +596,140 @@ static const MemoryRegionOps pchip_ops = {
     },
 };
 
+/* A subroutine of typhoon_translate_iommu that builds an IOMMUTLBEntry
+   using the given translated address and mask.  */
+static bool make_iommu_tlbe(hwaddr taddr, hwaddr mask, IOMMUTLBEntry *ret)
+{
+    *ret = (IOMMUTLBEntry) {
+        .target_as = &address_space_memory,
+        .translated_addr = taddr,
+        .addr_mask = mask,
+        .perm = IOMMU_RW,
+    };
+    return true;
+}
+
+/* A subroutine of typhoon_translate_iommu that handles scatter-gather
+   translation, given the address of the PTE.  */
+static bool pte_translate(hwaddr pte_addr, IOMMUTLBEntry *ret)
+{
+    uint64_t pte = ldq_phys(pte_addr);
+
+    /* Check valid bit.  */
+    if ((pte & 1) == 0) {
+        return false;
+    }
+
+    return make_iommu_tlbe((pte & 0x3ffffe) << 12, 0x1fff, ret);
+}
+
+/* A subroutine of typhoon_translate_iommu that handles one of the
+   four single-address-cycle translation windows.  */
+static bool window_translate(TyphoonWindow *win, hwaddr addr,
+                             IOMMUTLBEntry *ret)
+{
+    uint32_t wba = win->wba;
+    uint64_t wsm = win->wsm;
+    uint64_t tba = win->tba;
+    uint64_t wsm_ext = wsm | 0xfffff;
+
+    /* Check for window disabled.  */
+    if ((wba & 1) == 0) {
+        return false;
+    }
+
+    /* Check for window hit.  */
+    if ((addr & ~wsm_ext) != (wba & 0xfff00000u)) {
+        return false;
+    }
+
+    if (wba & 2) {
+        /* Scatter-gather translation.  */
+        hwaddr pte_addr;
+
+        /* See table 10-6, Generating PTE address for PCI DMA Address.  */
+        pte_addr  = tba & ~(wsm >> 10);
+        pte_addr |= (addr & (wsm | 0xfe000)) >> 10;
+        return pte_translate(pte_addr, ret);
+    } else {
+	/* Direct-mapped translation.  */
+	return make_iommu_tlbe(tba & ~wsm_ext, wsm_ext, ret);
+    }
+}
+
+/* Handle PCI-to-system address translation.  */
+/* TODO: A translation failure here ought to set PCI error codes on the
+   Pchip and generate a machine check interrupt.  */
+static IOMMUTLBEntry typhoon_translate_iommu(MemoryRegion *iommu, hwaddr addr)
+{
+    TyphoonPchip *pchip = container_of(iommu, TyphoonPchip, iommu);
+    IOMMUTLBEntry ret;
+    int i;
+
+    if (addr <= 0xffffffffu) {
+        /* Single-address cycle.  */
+
+        /* Check for the Window Hole, inhibiting matching.  */
+        if ((pchip->ctl & 0x20)
+            && addr >= 0x80000
+            && addr <= 0xfffff) {
+            goto failure;
+        }
+
+        /* Check the first three windows.  */
+        for (i = 0; i < 3; ++i) {
+            if (window_translate(&pchip->win[i], addr, &ret)) {
+                goto success;
+            }
+        }
+
+        /* Check the fourth window for DAC disable.  */
+        if ((pchip->win[3].wba & 0x80000000000ull) == 0
+	    && window_translate(&pchip->win[3], addr, &ret)) {
+            goto success;
+        }
+    } else {
+        /* Double-address cycle.  */
+
+        if (addr >= 0x10000000000ull && addr < 0x20000000000ull) {
+            /* Check for the DMA monster window.  */
+            if (pchip->ctl & 0x40) {
+                /* See 10.1.4.4; in particular <39:35> is ignored.  */
+                make_iommu_tlbe(0, 0x007ffffffffull, &ret);
+		goto success;
+            }
+        }
+
+        if (addr >= 0x80000000000 && addr <= 0xfffffffffff) {
+            /* Check the fourth window for DAC enable and window enable.  */
+            if ((pchip->win[3].wba & 0x80000000001ull) == 0x80000000001ull) {
+                uint64_t pte_addr;
+
+                pte_addr  = pchip->win[3].tba & 0x7ffc00000ull;
+                pte_addr |= (addr & 0xffffe000u) >> 10;
+                if (pte_translate(pte_addr, &ret)) {
+			goto success;
+		}
+            }
+        }
+    }
+
+ failure:
+    ret = (IOMMUTLBEntry) { .perm = IOMMU_NONE };
+ success:
+    return ret;
+}
+
+static const MemoryRegionIOMMUOps typhoon_iommu_ops = {
+    .translate = typhoon_translate_iommu,
+};
+
+static AddressSpace *typhoon_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
+{
+    TyphoonState *s = opaque;
+    return &s->pchip.iommu_as;
+}
+
 static void typhoon_set_irq(void *opaque, int irq, int level)
 {
     TyphoonState *s = opaque;
@@ -688,6 +825,9 @@ PCIBus *typhoon_init(ram_addr_t ram_size, ISABus **isa_bus,
     s = TYPHOON_PCI_HOST_BRIDGE(dev);
     phb = PCI_HOST_BRIDGE(dev);
 
+    s->cchip.misc = 0x800000000ull; /* Revision: Typhoon.  */
+    s->pchip.win[3].wba = 2;        /* Window 3 SG always enabled. */
+
     /* Remember the CPUs so that we can deliver interrupts to them.  */
     for (i = 0; i < 4; i++) {
         AlphaCPU *cpu = cpus[i];
@@ -746,6 +886,12 @@ PCIBus *typhoon_init(ram_addr_t ram_size, ISABus **isa_bus,
                          0, 64, TYPE_PCI_BUS);
     phb->bus = b;
 
+    /* Host memory as seen from the PCI side, via the IOMMU.  */
+    memory_region_init_iommu(&s->pchip.iommu, OBJECT(s), &typhoon_iommu_ops,
+                             "iommu-typhoon", UINT64_MAX);
+    address_space_init(&s->pchip.iommu_as, &s->pchip.iommu, "pchip0-pci");
+    pci_setup_iommu(b, typhoon_pci_dma_iommu, s);
+
     /* Pchip0 PCI special/interrupt acknowledge, 0x801.F800.0000, 64MB.  */
     memory_region_init_io(&s->pchip.reg_iack, OBJECT(s), &alpha_pci_iack_ops,
                           b, "pci0-iack", 64*MB);

hw/arm/Makefile.objs

@@ -1,6 +1,6 @@
 obj-y += boot.o collie.o exynos4_boards.o gumstix.o highbank.o
 obj-y += integratorcp.o kzm.o mainstone.o musicpal.o nseries.o
-obj-y += omap_sx1.o palm.o pic_cpu.o realview.o spitz.o stellaris.o
+obj-y += omap_sx1.o palm.o realview.o spitz.o stellaris.o
 obj-y += tosa.o versatilepb.o vexpress.o xilinx_zynq.o z2.o
 
 obj-y += armv7m.o exynos4210.o pxa2xx.o pxa2xx_gpio.o pxa2xx_pic.o

hw/arm/armv7m.c

@@ -173,7 +173,6 @@ qemu_irq *armv7m_init(MemoryRegion *address_space_mem,
     DeviceState *nvic;
     /* FIXME: make this local state.  */
     static qemu_irq pic[64];
-    qemu_irq *cpu_pic;
     int image_size;
     uint64_t entry;
     uint64_t lowaddr;
@@ -221,8 +220,8 @@ qemu_irq *armv7m_init(MemoryRegion *address_space_mem,
     nvic = qdev_create(NULL, "armv7m_nvic");
     env->nvic = nvic;
     qdev_init_nofail(nvic);
-    cpu_pic = arm_pic_init_cpu(cpu);
-    sysbus_connect_irq(SYS_BUS_DEVICE(nvic), 0, cpu_pic[ARM_PIC_CPU_IRQ]);
+    sysbus_connect_irq(SYS_BUS_DEVICE(nvic), 0,
+                       qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ));
     for (i = 0; i < 64; i++) {
         pic[i] = qdev_get_gpio_in(nvic, i);
     }

hw/arm/collie.c

@@ -62,7 +62,6 @@ static QEMUMachine collie_machine = {
     .name = "collie",
     .desc = "Collie PDA (SA-1110)",
     .init = collie_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void collie_machine_init(void)

hw/arm/exynos4210.c

@@ -137,10 +137,8 @@ void exynos4210_write_secondary(ARMCPU *cpu,
 Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
         unsigned long ram_size)
 {
-    qemu_irq cpu_irq[EXYNOS4210_NCPUS];
     int i, n;
     Exynos4210State *s = g_new(Exynos4210State, 1);
-    qemu_irq *irqp;
     qemu_irq gate_irq[EXYNOS4210_NCPUS][EXYNOS4210_IRQ_GATE_NINPUTS];
     unsigned long mem_size;
     DeviceState *dev;
@@ -152,15 +150,6 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
             fprintf(stderr, "Unable to find CPU %d definition\n", n);
             exit(1);
         }
-
-        /* Create PIC controller for each processor instance */
-        irqp = arm_pic_init_cpu(s->cpu[n]);
-
-        /*
-         * Get GICs gpio_in cpu_irq to connect a combiner to them later.
-         * Use only IRQ for a while.
-         */
-        cpu_irq[n] = irqp[ARM_PIC_CPU_IRQ];
     }
 
     /*** IRQs ***/
@@ -178,8 +167,9 @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem,
         }
         busdev = SYS_BUS_DEVICE(dev);
 
-        /* Connect IRQ Gate output to cpu_irq */
-        sysbus_connect_irq(busdev, 0, cpu_irq[i]);
+        /* Connect IRQ Gate output to CPU's IRQ line */
+        sysbus_connect_irq(busdev, 0,
+                           qdev_get_gpio_in(DEVICE(s->cpu[i]), ARM_CPU_IRQ));
     }
 
     /* Private memory region and Internal GIC */

hw/arm/exynos4_boards.c

@@ -150,14 +150,12 @@ static QEMUMachine exynos4_machines[EXYNOS4_NUM_OF_BOARDS] = {
         .desc = "Samsung NURI board (Exynos4210)",
         .init = nuri_init,
         .max_cpus = EXYNOS4210_NCPUS,
-        DEFAULT_MACHINE_OPTIONS,
     },
     [EXYNOS4_BOARD_SMDKC210] = {
         .name = "smdkc210",
         .desc = "Samsung SMDKC210 board (Exynos4210)",
         .init = smdkc210_init,
         .max_cpus = EXYNOS4210_NCPUS,
-        DEFAULT_MACHINE_OPTIONS,
     },
 };
 

hw/arm/gumstix.c

@@ -122,14 +122,12 @@ static QEMUMachine connex_machine = {
     .name = "connex",
     .desc = "Gumstix Connex (PXA255)",
     .init = connex_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine verdex_machine = {
     .name = "verdex",
     .desc = "Gumstix Verdex (PXA270)",
     .init = verdex_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void gumstix_machine_init(void)

hw/arm/highbank.c

@@ -209,7 +209,6 @@ static void calxeda_init(QEMUMachineInitArgs *args, enum cxmachines machine)
     const char *initrd_filename = args->initrd_filename;
     DeviceState *dev = NULL;
     SysBusDevice *busdev;
-    qemu_irq *irqp;
     qemu_irq pic[128];
     int n;
     qemu_irq cpu_irq[4];
@@ -239,8 +238,7 @@ static void calxeda_init(QEMUMachineInitArgs *args, enum cxmachines machine)
 
         /* This will become a QOM property eventually */
         cpu->reset_cbar = GIC_BASE_ADDR;
-        irqp = arm_pic_init_cpu(cpu);
-        cpu_irq[n] = irqp[ARM_PIC_CPU_IRQ];
+        cpu_irq[n] = qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ);
     }
 
     sysmem = get_system_memory();
@@ -365,7 +363,6 @@ static QEMUMachine highbank_machine = {
     .init = highbank_init,
     .block_default_type = IF_SCSI,
     .max_cpus = 4,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine midway_machine = {
@@ -374,7 +371,6 @@ static QEMUMachine midway_machine = {
     .init = midway_init,
     .block_default_type = IF_SCSI,
     .max_cpus = 4,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void calxeda_machines_init(void)

hw/arm/integratorcp.c

@@ -465,7 +465,6 @@ static void integratorcp_init(QEMUMachineInitArgs *args)
     MemoryRegion *ram = g_new(MemoryRegion, 1);
     MemoryRegion *ram_alias = g_new(MemoryRegion, 1);
     qemu_irq pic[32];
-    qemu_irq *cpu_pic;
     DeviceState *dev;
     int i;
 
@@ -493,10 +492,10 @@ static void integratorcp_init(QEMUMachineInitArgs *args)
     qdev_init_nofail(dev);
     sysbus_mmio_map((SysBusDevice *)dev, 0, 0x10000000);
 
-    cpu_pic = arm_pic_init_cpu(cpu);
     dev = sysbus_create_varargs(TYPE_INTEGRATOR_PIC, 0x14000000,
-                                cpu_pic[ARM_PIC_CPU_IRQ],
-                                cpu_pic[ARM_PIC_CPU_FIQ], NULL);
+                                qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ),
+                                qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_FIQ),
+                                NULL);
     for (i = 0; i < 32; i++) {
         pic[i] = qdev_get_gpio_in(dev, i);
     }
@@ -527,7 +526,6 @@ static QEMUMachine integratorcp_machine = {
     .desc = "ARM Integrator/CP (ARM926EJ-S)",
     .init = integratorcp_init,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void integratorcp_machine_init(void)

hw/arm/kzm.c

@@ -82,7 +82,6 @@ static void kzm_init(QEMUMachineInitArgs *args)
     MemoryRegion *ram = g_new(MemoryRegion, 1);
     MemoryRegion *sram = g_new(MemoryRegion, 1);
     MemoryRegion *ram_alias = g_new(MemoryRegion, 1);
-    qemu_irq *cpu_pic;
     DeviceState *dev;
     DeviceState *ccm;
 
@@ -108,11 +107,10 @@ static void kzm_init(QEMUMachineInitArgs *args)
     memory_region_init_ram(sram, NULL, "kzm.sram", 0x4000);
     memory_region_add_subregion(address_space_mem, 0x1FFFC000, sram);
 
-    cpu_pic = arm_pic_init_cpu(cpu);
     dev = sysbus_create_varargs("imx_avic", 0x68000000,
-                                cpu_pic[ARM_PIC_CPU_IRQ],
-                                cpu_pic[ARM_PIC_CPU_FIQ], NULL);
-
+                                qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ),
+                                qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_FIQ),
+                                NULL);
 
     imx_serial_create(0, 0x43f90000, qdev_get_gpio_in(dev, 45));
     imx_serial_create(1, 0x43f94000, qdev_get_gpio_in(dev, 32));
@@ -146,7 +144,6 @@ static QEMUMachine kzm_machine = {
     .name = "kzm",
     .desc = "ARM KZM Emulation Baseboard (ARM1136)",
     .init = kzm_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void kzm_machine_init(void)

hw/arm/mainstone.c

@@ -179,7 +179,6 @@ static QEMUMachine mainstone2_machine = {
     .name = "mainstone",
     .desc = "Mainstone II (PXA27x)",
     .init = mainstone_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void mainstone_machine_init(void)

hw/arm/musicpal.c

@@ -1586,7 +1586,6 @@ static void musicpal_init(QEMUMachineInitArgs *args)
     const char *kernel_cmdline = args->kernel_cmdline;
     const char *initrd_filename = args->initrd_filename;
     ARMCPU *cpu;
-    qemu_irq *cpu_pic;
     qemu_irq pic[32];
     DeviceState *dev;
     DeviceState *i2c_dev;
@@ -1610,7 +1609,6 @@ static void musicpal_init(QEMUMachineInitArgs *args)
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
     }
-    cpu_pic = arm_pic_init_cpu(cpu);
 
     /* For now we use a fixed - the original - RAM size */
     memory_region_init_ram(ram, NULL, "musicpal.ram", MP_RAM_DEFAULT_SIZE);
@@ -1622,7 +1620,7 @@ static void musicpal_init(QEMUMachineInitArgs *args)
     memory_region_add_subregion(address_space_mem, MP_SRAM_BASE, sram);
 
     dev = sysbus_create_simple(TYPE_MV88W8618_PIC, MP_PIC_BASE,
-                               cpu_pic[ARM_PIC_CPU_IRQ]);
+                               qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ));
     for (i = 0; i < 32; i++) {
         pic[i] = qdev_get_gpio_in(dev, i);
     }
@@ -1731,7 +1729,6 @@ static QEMUMachine musicpal_machine = {
     .name = "musicpal",
     .desc = "Marvell 88w8618 / MusicPal (ARM926EJ-S)",
     .init = musicpal_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void musicpal_machine_init(void)

hw/arm/nseries.c

@@ -1340,7 +1340,7 @@ static void n8x0_init(QEMUMachineInitArgs *args,
     }
 
     if (option_rom[0].name &&
-        (args->boot_device[0] == 'n' || !args->kernel_filename)) {
+        (args->boot_order[0] == 'n' || !args->kernel_filename)) {
         uint8_t nolo_tags[0x10000];
         /* No, wait, better start at the ROM.  */
         s->mpu->cpu->env.regs[15] = OMAP2_Q2_BASE + 0x400000;
@@ -1396,14 +1396,14 @@ static QEMUMachine n800_machine = {
     .name = "n800",
     .desc = "Nokia N800 tablet aka. RX-34 (OMAP2420)",
     .init = n800_init,
-    DEFAULT_MACHINE_OPTIONS,
+    .default_boot_order = "",
 };
 
 static QEMUMachine n810_machine = {
     .name = "n810",
     .desc = "Nokia N810 tablet aka. RX-44 (OMAP2420)",
     .init = n810_init,
-    DEFAULT_MACHINE_OPTIONS,
+    .default_boot_order = "",
 };
 
 static void nseries_machine_init(void)

hw/arm/omap1.c

@@ -3827,7 +3827,6 @@ struct omap_mpu_state_s *omap310_mpu_init(MemoryRegion *system_memory,
     int i;
     struct omap_mpu_state_s *s = (struct omap_mpu_state_s *)
             g_malloc0(sizeof(struct omap_mpu_state_s));
-    qemu_irq *cpu_irq;
     qemu_irq dma_irqs[6];
     DriveInfo *dinfo;
     SysBusDevice *busdev;
@@ -3860,14 +3859,15 @@ struct omap_mpu_state_s *omap310_mpu_init(MemoryRegion *system_memory,
 
     omap_clkm_init(system_memory, 0xfffece00, 0xe1008000, s);
 
-    cpu_irq = arm_pic_init_cpu(s->cpu);
     s->ih[0] = qdev_create(NULL, "omap-intc");
     qdev_prop_set_uint32(s->ih[0], "size", 0x100);
     qdev_prop_set_ptr(s->ih[0], "clk", omap_findclk(s, "arminth_ck"));
     qdev_init_nofail(s->ih[0]);
     busdev = SYS_BUS_DEVICE(s->ih[0]);
-    sysbus_connect_irq(busdev, 0, cpu_irq[ARM_PIC_CPU_IRQ]);
-    sysbus_connect_irq(busdev, 1, cpu_irq[ARM_PIC_CPU_FIQ]);
+    sysbus_connect_irq(busdev, 0,
+                       qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ));
+    sysbus_connect_irq(busdev, 1,
+                       qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_FIQ));
     sysbus_mmio_map(busdev, 0, 0xfffecb00);
     s->ih[1] = qdev_create(NULL, "omap-intc");
     qdev_prop_set_uint32(s->ih[1], "size", 0x800);

hw/arm/omap2.c

@@ -2244,7 +2244,6 @@ struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sysmem,
 {
     struct omap_mpu_state_s *s = (struct omap_mpu_state_s *)
             g_malloc0(sizeof(struct omap_mpu_state_s));
-    qemu_irq *cpu_irq;
     qemu_irq dma_irqs[4];
     DriveInfo *dinfo;
     int i;
@@ -2277,15 +2276,16 @@ struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sysmem,
     s->l4 = omap_l4_init(sysmem, OMAP2_L4_BASE, 54);
 
     /* Actually mapped at any 2K boundary in the ARM11 private-peripheral if */
-    cpu_irq = arm_pic_init_cpu(s->cpu);
     s->ih[0] = qdev_create(NULL, "omap2-intc");
     qdev_prop_set_uint8(s->ih[0], "revision", 0x21);
     qdev_prop_set_ptr(s->ih[0], "fclk", omap_findclk(s, "mpu_intc_fclk"));
     qdev_prop_set_ptr(s->ih[0], "iclk", omap_findclk(s, "mpu_intc_iclk"));
     qdev_init_nofail(s->ih[0]);
     busdev = SYS_BUS_DEVICE(s->ih[0]);
-    sysbus_connect_irq(busdev, 0, cpu_irq[ARM_PIC_CPU_IRQ]);
-    sysbus_connect_irq(busdev, 1, cpu_irq[ARM_PIC_CPU_FIQ]);
+    sysbus_connect_irq(busdev, 0,
+                       qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ));
+    sysbus_connect_irq(busdev, 1,
+                       qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_FIQ));
     sysbus_mmio_map(busdev, 0, 0x480fe000);
     s->prcm = omap_prcm_init(omap_l4tao(s->l4, 3),
                              qdev_get_gpio_in(s->ih[0],

hw/arm/omap_sx1.c

@@ -219,14 +219,12 @@ static QEMUMachine sx1_machine_v2 = {
     .name = "sx1",
     .desc = "Siemens SX1 (OMAP310) V2",
     .init = sx1_init_v2,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine sx1_machine_v1 = {
     .name = "sx1-v1",
     .desc = "Siemens SX1 (OMAP310) V1",
     .init = sx1_init_v1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void sx1_machine_init(void)

hw/arm/palm.c

@@ -273,7 +273,6 @@ static QEMUMachine palmte_machine = {
     .name = "cheetah",
     .desc = "Palm Tungsten|E aka. Cheetah PDA (OMAP310)",
     .init = palmte_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void palmte_machine_init(void)

hw/arm/pic_cpu.c

@@ -1,68 +0,0 @@
-/*
- * Generic ARM Programmable Interrupt Controller support.
- *
- * Copyright (c) 2006 CodeSourcery.
- * Written by Paul Brook
- *
- * This code is licensed under the LGPL
- */
-
-#include "hw/hw.h"
-#include "hw/arm/arm.h"
-#include "sysemu/kvm.h"
-
-/* Input 0 is IRQ and input 1 is FIQ.  */
-static void arm_pic_cpu_handler(void *opaque, int irq, int level)
-{
-    ARMCPU *cpu = opaque;
-    CPUState *cs = CPU(cpu);
-
-    switch (irq) {
-    case ARM_PIC_CPU_IRQ:
-        if (level) {
-            cpu_interrupt(cs, CPU_INTERRUPT_HARD);
-        } else {
-            cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);
-        }
-        break;
-    case ARM_PIC_CPU_FIQ:
-        if (level) {
-            cpu_interrupt(cs, CPU_INTERRUPT_FIQ);
-        } else {
-            cpu_reset_interrupt(cs, CPU_INTERRUPT_FIQ);
-        }
-        break;
-    default:
-        hw_error("arm_pic_cpu_handler: Bad interrupt line %d\n", irq);
-    }
-}
-
-static void kvm_arm_pic_cpu_handler(void *opaque, int irq, int level)
-{
-#ifdef CONFIG_KVM
-    ARMCPU *cpu = opaque;
-    CPUState *cs = CPU(cpu);
-    int kvm_irq = KVM_ARM_IRQ_TYPE_CPU << KVM_ARM_IRQ_TYPE_SHIFT;
-
-    switch (irq) {
-    case ARM_PIC_CPU_IRQ:
-        kvm_irq |= KVM_ARM_IRQ_CPU_IRQ;
-        break;
-    case ARM_PIC_CPU_FIQ:
-        kvm_irq |= KVM_ARM_IRQ_CPU_FIQ;
-        break;
-    default:
-        hw_error("kvm_arm_pic_cpu_handler: Bad interrupt line %d\n", irq);
-    }
-    kvm_irq |= cs->cpu_index << KVM_ARM_IRQ_VCPU_SHIFT;
-    kvm_set_irq(kvm_state, kvm_irq, level ? 1 : 0);
-#endif
-}
-
-qemu_irq *arm_pic_init_cpu(ARMCPU *cpu)
-{
-    if (kvm_enabled()) {
-        return qemu_allocate_irqs(kvm_arm_pic_cpu_handler, cpu, 2);
-    }
-    return qemu_allocate_irqs(arm_pic_cpu_handler, cpu, 2);
-}

hw/arm/realview.c

@@ -56,7 +56,6 @@ static void realview_init(QEMUMachineInitArgs *args,
     MemoryRegion *ram_hack = g_new(MemoryRegion, 1);
     DeviceState *dev, *sysctl, *gpio2, *pl041;
     SysBusDevice *busdev;
-    qemu_irq *irqp;
     qemu_irq pic[64];
     qemu_irq mmc_irq[2];
     PCIBus *pci_bus = NULL;
@@ -92,8 +91,7 @@ static void realview_init(QEMUMachineInitArgs *args,
             fprintf(stderr, "Unable to find CPU definition\n");
             exit(1);
         }
-        irqp = arm_pic_init_cpu(cpu);
-        cpu_irq[n] = irqp[ARM_PIC_CPU_IRQ];
+        cpu_irq[n] = qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ);
     }
     env = &cpu->env;
     if (arm_feature(env, ARM_FEATURE_V7)) {
@@ -371,7 +369,6 @@ static QEMUMachine realview_eb_machine = {
     .desc = "ARM RealView Emulation Baseboard (ARM926EJ-S)",
     .init = realview_eb_init,
     .block_default_type = IF_SCSI,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine realview_eb_mpcore_machine = {
@@ -380,14 +377,12 @@ static QEMUMachine realview_eb_mpcore_machine = {
     .init = realview_eb_mpcore_init,
     .block_default_type = IF_SCSI,
     .max_cpus = 4,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine realview_pb_a8_machine = {
     .name = "realview-pb-a8",
     .desc = "ARM RealView Platform Baseboard for Cortex-A8",
     .init = realview_pb_a8_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine realview_pbx_a9_machine = {
@@ -396,7 +391,6 @@ static QEMUMachine realview_pbx_a9_machine = {
     .init = realview_pbx_a9_init,
     .block_default_type = IF_SCSI,
     .max_cpus = 4,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void realview_machine_init(void)

hw/arm/spitz.c

@@ -966,28 +966,24 @@ static QEMUMachine akitapda_machine = {
     .name = "akita",
     .desc = "Akita PDA (PXA270)",
     .init = akita_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine spitzpda_machine = {
     .name = "spitz",
     .desc = "Spitz PDA (PXA270)",
     .init = spitz_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine borzoipda_machine = {
     .name = "borzoi",
     .desc = "Borzoi PDA (PXA270)",
     .init = borzoi_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine terrierpda_machine = {
     .name = "terrier",
     .desc = "Terrier PDA (PXA270)",
     .init = terrier_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void spitz_machine_init(void)

hw/arm/stellaris.c

@@ -1348,14 +1348,12 @@ static QEMUMachine lm3s811evb_machine = {
     .name = "lm3s811evb",
     .desc = "Stellaris LM3S811EVB",
     .init = lm3s811evb_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine lm3s6965evb_machine = {
     .name = "lm3s6965evb",
     .desc = "Stellaris LM3S6965EVB",
     .init = lm3s6965evb_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void stellaris_machine_init(void)

hw/arm/strongarm.c

@@ -1588,7 +1588,6 @@ StrongARMState *sa1110_init(MemoryRegion *sysmem,
                             unsigned int sdram_size, const char *rev)
 {
     StrongARMState *s;
-    qemu_irq *pic;
     int i;
 
     s = g_malloc0(sizeof(StrongARMState));
@@ -1613,9 +1612,10 @@ StrongARMState *sa1110_init(MemoryRegion *sysmem,
     vmstate_register_ram_global(&s->sdram);
     memory_region_add_subregion(sysmem, SA_SDCS0, &s->sdram);
 
-    pic = arm_pic_init_cpu(s->cpu);
     s->pic = sysbus_create_varargs("strongarm_pic", 0x90050000,
-                    pic[ARM_PIC_CPU_IRQ], pic[ARM_PIC_CPU_FIQ], NULL);
+                    qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ),
+                    qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_FIQ),
+                    NULL);
 
     sysbus_create_varargs("pxa25x-timer", 0x90000000,
                     qdev_get_gpio_in(s->pic, SA_PIC_OSTC0),

hw/arm/tosa.c

@@ -251,7 +251,6 @@ static QEMUMachine tosapda_machine = {
     .name = "tosa",
     .desc = "Tosa PDA (PXA255)",
     .init = tosa_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void tosapda_machine_init(void)

hw/arm/versatilepb.c

@@ -178,7 +178,6 @@ static void versatile_init(QEMUMachineInitArgs *args, int board_id)
     ARMCPU *cpu;
     MemoryRegion *sysmem = get_system_memory();
     MemoryRegion *ram = g_new(MemoryRegion, 1);
-    qemu_irq *cpu_pic;
     qemu_irq pic[32];
     qemu_irq sic[32];
     DeviceState *dev, *sysctl;
@@ -211,10 +210,10 @@ static void versatile_init(QEMUMachineInitArgs *args, int board_id)
     qdev_init_nofail(sysctl);
     sysbus_mmio_map(SYS_BUS_DEVICE(sysctl), 0, 0x10000000);
 
-    cpu_pic = arm_pic_init_cpu(cpu);
     dev = sysbus_create_varargs("pl190", 0x10140000,
-                                cpu_pic[ARM_PIC_CPU_IRQ],
-                                cpu_pic[ARM_PIC_CPU_FIQ], NULL);
+                                qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ),
+                                qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_FIQ),
+                                NULL);
     for (n = 0; n < 32; n++) {
         pic[n] = qdev_get_gpio_in(dev, n);
     }
@@ -368,7 +367,6 @@ static QEMUMachine versatilepb_machine = {
     .desc = "ARM Versatile/PB (ARM926EJ-S)",
     .init = vpb_init,
     .block_default_type = IF_SCSI,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine versatileab_machine = {
@@ -376,7 +374,6 @@ static QEMUMachine versatileab_machine = {
     .desc = "ARM Versatile/AB (ARM926EJ-S)",
     .init = vab_init,
     .block_default_type = IF_SCSI,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void versatile_machine_init(void)

hw/arm/vexpress.c

@@ -183,7 +183,6 @@ static void a9_daughterboard_init(const VEDBoardInfo *daughterboard,
     MemoryRegion *lowram = g_new(MemoryRegion, 1);
     DeviceState *dev;
     SysBusDevice *busdev;
-    qemu_irq *irqp;
     int n;
     qemu_irq cpu_irq[4];
     ram_addr_t low_ram_size;
@@ -198,8 +197,7 @@ static void a9_daughterboard_init(const VEDBoardInfo *daughterboard,
             fprintf(stderr, "Unable to find CPU definition\n");
             exit(1);
         }
-        irqp = arm_pic_init_cpu(cpu);
-        cpu_irq[n] = irqp[ARM_PIC_CPU_IRQ];
+        cpu_irq[n] = qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ);
     }
 
     if (ram_size > 0x40000000) {
@@ -312,15 +310,13 @@ static void a15_daughterboard_init(const VEDBoardInfo *daughterboard,
 
     for (n = 0; n < smp_cpus; n++) {
         ARMCPU *cpu;
-        qemu_irq *irqp;
 
         cpu = cpu_arm_init(cpu_model);
         if (!cpu) {
             fprintf(stderr, "Unable to find CPU definition\n");
             exit(1);
         }
-        irqp = arm_pic_init_cpu(cpu);
-        cpu_irq[n] = irqp[ARM_PIC_CPU_IRQ];
+        cpu_irq[n] = qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ);
     }
 
     {
@@ -651,7 +647,6 @@ static QEMUMachine vexpress_a9_machine = {
     .init = vexpress_a9_init,
     .block_default_type = IF_SCSI,
     .max_cpus = 4,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine vexpress_a15_machine = {
@@ -660,7 +655,6 @@ static QEMUMachine vexpress_a15_machine = {
     .init = vexpress_a15_init,
     .block_default_type = IF_SCSI,
     .max_cpus = 4,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void vexpress_machine_init(void)

hw/arm/xilinx_zynq.c

@@ -108,11 +108,9 @@ static void zynq_init(QEMUMachineInitArgs *args)
     MemoryRegion *ocm_ram = g_new(MemoryRegion, 1);
     DeviceState *dev;
     SysBusDevice *busdev;
-    qemu_irq *irqp;
     qemu_irq pic[64];
     NICInfo *nd;
     int n;
-    qemu_irq cpu_irq;
 
     if (!cpu_model) {
         cpu_model = "cortex-a9";
@@ -123,8 +121,6 @@ static void zynq_init(QEMUMachineInitArgs *args)
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
     }
-    irqp = arm_pic_init_cpu(cpu);
-    cpu_irq = irqp[ARM_PIC_CPU_IRQ];
 
     /* max 2GB ram */
     if (ram_size > 0x80000000) {
@@ -159,7 +155,8 @@ static void zynq_init(QEMUMachineInitArgs *args)
     qdev_init_nofail(dev);
     busdev = SYS_BUS_DEVICE(dev);
     sysbus_mmio_map(busdev, 0, 0xF8F00000);
-    sysbus_connect_irq(busdev, 0, cpu_irq);
+    sysbus_connect_irq(busdev, 0,
+                       qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ));
 
     for (n = 0; n < 64; n++) {
         pic[n] = qdev_get_gpio_in(dev, n);
@@ -236,7 +233,6 @@ static QEMUMachine zynq_machine = {
     .block_default_type = IF_SCSI,
     .max_cpus = 1,
     .no_sdcard = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void zynq_machine_init(void)

hw/arm/z2.c

@@ -373,7 +373,6 @@ static QEMUMachine z2_machine = {
     .name = "z2",
     .desc = "Zipit Z2 (PXA27x)",
     .init = z2_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void z2_machine_init(void)

hw/audio/adlib.c

@@ -284,9 +284,9 @@ static void Adlib_fini (AdlibState *s)
 }
 
 static MemoryRegionPortio adlib_portio_list[] = {
+    { 0x388, 4, 1, .read = adlib_read, .write = adlib_write, },
     { 0, 4, 1, .read = adlib_read, .write = adlib_write, },
     { 0, 2, 1, .read = adlib_read, .write = adlib_write, },
-    { 0x388, 4, 1, .read = adlib_read, .write = adlib_write, },
     PORTIO_END_OF_LIST(),
 };
 

hw/block/dataplane/virtio-blk.c

@@ -261,11 +261,6 @@ static int process_request(IOQueue *ioq, struct iovec iov[],
     }
 }
 
-static int flush_true(EventNotifier *e)
-{
-    return true;
-}
-
 static void handle_notify(EventNotifier *e)
 {
     VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
@@ -345,14 +340,6 @@ static void handle_notify(EventNotifier *e)
     }
 }
 
-static int flush_io(EventNotifier *e)
-{
-    VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
-                                           io_notifier);
-
-    return s->num_reqs > 0;
-}
-
 static void handle_io(EventNotifier *e)
 {
     VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
@@ -376,9 +363,9 @@ static void *data_plane_thread(void *opaque)
 {
     VirtIOBlockDataPlane *s = opaque;
 
-    do {
+    while (!s->stopping || s->num_reqs > 0) {
         aio_poll(s->ctx, true);
-    } while (!s->stopping || s->num_reqs > 0);
+    }
     return NULL;
 }
 
@@ -485,7 +472,7 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
         exit(1);
     }
     s->host_notifier = *virtio_queue_get_host_notifier(vq);
-    aio_set_event_notifier(s->ctx, &s->host_notifier, handle_notify, flush_true);
+    aio_set_event_notifier(s->ctx, &s->host_notifier, handle_notify);
 
     /* Set up ioqueue */
     ioq_init(&s->ioqueue, s->fd, REQ_MAX);
@@ -493,7 +480,7 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
         ioq_put_iocb(&s->ioqueue, &s->requests[i].iocb);
     }
     s->io_notifier = *ioq_get_notifier(&s->ioqueue);
-    aio_set_event_notifier(s->ctx, &s->io_notifier, handle_io, flush_io);
+    aio_set_event_notifier(s->ctx, &s->io_notifier, handle_io);
 
     s->started = true;
     trace_virtio_blk_data_plane_start(s);
@@ -525,10 +512,10 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
         qemu_thread_join(&s->thread);
     }
 
-    aio_set_event_notifier(s->ctx, &s->io_notifier, NULL, NULL);
+    aio_set_event_notifier(s->ctx, &s->io_notifier, NULL);
     ioq_cleanup(&s->ioqueue);
 
-    aio_set_event_notifier(s->ctx, &s->host_notifier, NULL, NULL);
+    aio_set_event_notifier(s->ctx, &s->host_notifier, NULL);
     k->set_host_notifier(qbus->parent, 0, false);
 
     aio_context_unref(s->ctx);

hw/block/virtio-blk.c

@@ -460,9 +460,9 @@ static void virtio_blk_dma_restart_cb(void *opaque, int running,
 
 static void virtio_blk_reset(VirtIODevice *vdev)
 {
+#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     VirtIOBlock *s = VIRTIO_BLK(vdev);
 
-#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     if (s->dataplane) {
         virtio_blk_data_plane_stop(s->dataplane);
     }
@@ -473,7 +473,6 @@ static void virtio_blk_reset(VirtIODevice *vdev)
      * are per-device request lists.
      */
     bdrv_drain_all();
-    bdrv_set_enable_write_cache(s->bs, s->original_wce);
 }
 
 /* coalesce internal state, copy to pci i/o region 0
@@ -565,26 +564,8 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
     }
 
     features = vdev->guest_features;
-
-    /* A guest that supports VIRTIO_BLK_F_CONFIG_WCE must be able to send
-     * cache flushes.  Thus, the "auto writethrough" behavior is never
-     * necessary for guests that support the VIRTIO_BLK_F_CONFIG_WCE feature.
-     * Leaving it enabled would break the following sequence:
-     *
-     *     Guest started with "-drive cache=writethrough"
-     *     Guest sets status to 0
-     *     Guest sets DRIVER bit in status field
-     *     Guest reads host features (WCE=0, CONFIG_WCE=1)
-     *     Guest writes guest features (WCE=0, CONFIG_WCE=1)
-     *     Guest writes 1 to the WCE configuration field (writeback mode)
-     *     Guest sets DRIVER_OK bit in status field
-     *
-     * s->bs would erroneously be placed in writethrough mode.
-     */
-    if (!(features & (1 << VIRTIO_BLK_F_CONFIG_WCE))) {
     bdrv_set_enable_write_cache(s->bs, !!(features & (1 << VIRTIO_BLK_F_WCE)));
 }
-}
 
 static void virtio_blk_save(QEMUFile *f, void *opaque)
 {
@@ -693,7 +674,6 @@ static int virtio_blk_device_init(VirtIODevice *vdev)
     }
 
     blkconf_serial(&blk->conf, &blk->serial);
-    s->original_wce = bdrv_enable_write_cache(blk->conf.bs);
     if (blkconf_geometry(&blk->conf, NULL, 65535, 255, 255) < 0) {
         return -1;
     }

hw/char/spapr_vty.c

@@ -47,8 +47,6 @@ static int vty_getchars(VIOsPAPRDevice *sdev, uint8_t *buf, int max)
         buf[n++] = dev->buf[dev->out++ % VTERM_BUFSIZE];
     }
 
-    qemu_chr_accept_input(dev->chardev);
-
     return n;
 }
 

hw/core/loader.c

@@ -54,6 +54,8 @@
 
 #include <zlib.h>
 
+bool rom_file_in_ram = true;
+
 static int roms_loaded;
 
 /* return the size or -1 if error */
@@ -576,6 +578,7 @@ struct Rom {
     size_t datasize;
 
     uint8_t *data;
+    MemoryRegion *mr;
     int isrom;
     char *fw_dir;
     char *fw_file;
@@ -605,6 +608,21 @@ static void rom_insert(Rom *rom)
     QTAILQ_INSERT_TAIL(&roms, rom, next);
 }
 
+static void *rom_set_mr(Rom *rom, Object *owner, const char *name)
+{
+    void *data;
+
+    rom->mr = g_malloc(sizeof(*rom->mr));
+    memory_region_init_ram(rom->mr, owner, name, rom->datasize);
+    memory_region_set_readonly(rom->mr, true);
+    vmstate_register_ram_global(rom->mr);
+
+    data = memory_region_get_ram_ptr(rom->mr);
+    memcpy(data, rom->data, rom->datasize);
+
+    return data;
+}
+
 int rom_add_file(const char *file, const char *fw_dir,
                  hwaddr addr, int32_t bootindex)
 {
@@ -646,6 +664,7 @@ int rom_add_file(const char *file, const char *fw_dir,
     if (rom->fw_file && fw_cfg) {
         const char *basename;
         char fw_file_name[56];
+        void *data;
 
         basename = strrchr(rom->fw_file, '/');
         if (basename) {
@@ -655,8 +674,15 @@ int rom_add_file(const char *file, const char *fw_dir,
         }
         snprintf(fw_file_name, sizeof(fw_file_name), "%s/%s", rom->fw_dir,
                  basename);
-        fw_cfg_add_file(fw_cfg, fw_file_name, rom->data, rom->romsize);
         snprintf(devpath, sizeof(devpath), "/rom@%s", fw_file_name);
+
+        if (rom_file_in_ram) {
+            data = rom_set_mr(rom, OBJECT(fw_cfg), devpath);
+        } else {
+            data = rom->data;
+        }
+
+        fw_cfg_add_file(fw_cfg, fw_file_name, data, rom->romsize);
     } else {
         snprintf(devpath, sizeof(devpath), "/rom@" TARGET_FMT_plx, addr);
     }
@@ -731,7 +757,12 @@ static void rom_reset(void *unused)
         if (rom->data == NULL) {
             continue;
         }
+        if (rom->mr) {
+            void *host = memory_region_get_ram_ptr(rom->mr);
+            memcpy(host, rom->data, rom->datasize);
+        } else {
             cpu_physical_memory_write_rom(rom->addr, rom->data, rom->datasize);
+        }
         if (rom->isrom) {
             /* rom needs to be written only once */
             g_free(rom->data);
@@ -781,6 +812,9 @@ static Rom *find_rom(hwaddr addr)
         if (rom->fw_file) {
             continue;
         }
+        if (rom->mr) {
+            continue;
+        }
         if (rom->addr > addr) {
             continue;
         }
@@ -808,6 +842,9 @@ int rom_copy(uint8_t *dest, hwaddr addr, size_t size)
         if (rom->fw_file) {
             continue;
         }
+        if (rom->mr) {
+            continue;
+        }
         if (rom->addr + rom->romsize < addr) {
             continue;
         }
@@ -866,7 +903,13 @@ void do_info_roms(Monitor *mon, const QDict *qdict)
     Rom *rom;
 
     QTAILQ_FOREACH(rom, &roms, next) {
-        if (!rom->fw_file) {
+        if (rom->mr) {
+            monitor_printf(mon, "%s"
+                           " size=0x%06zx name=\"%s\"\n",
+                           rom->mr->name,
+                           rom->romsize,
+                           rom->name);
+        } else if (!rom->fw_file) {
             monitor_printf(mon, "addr=" TARGET_FMT_plx
                            " size=0x%06zx mem=%s name=\"%s\"\n",
                            rom->addr, rom->romsize,

hw/core/null-machine.c

@@ -24,7 +24,6 @@ static QEMUMachine machine_none = {
     .desc = "empty machine",
     .init = machine_none_init,
     .max_cpus = 0,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void register_machines(void)

hw/core/qdev.c

@@ -752,7 +752,6 @@ static void device_initfn(Object *obj)
         }
         class = object_class_get_parent(class);
     } while (class != object_class_by_name(TYPE_DEVICE));
-    qdev_prop_set_globals(dev, &err);
     if (err != NULL) {
         qerror_report_err(err);
         error_free(err);
@@ -764,6 +763,15 @@ static void device_initfn(Object *obj)
     assert_no_error(err);
 }
 
+static void device_post_init(Object *obj)
+{
+    DeviceState *dev = DEVICE(obj);
+    Error *err = NULL;
+
+    qdev_prop_set_globals(dev, &err);
+    assert_no_error(err);
+}
+
 /* Unlink device from bus and free the structure.  */
 static void device_finalize(Object *obj)
 {
@@ -853,6 +861,7 @@ static const TypeInfo device_type_info = {
     .parent = TYPE_OBJECT,
     .instance_size = sizeof(DeviceState),
     .instance_init = device_initfn,
+    .instance_post_init = device_post_init,
     .instance_finalize = device_finalize,
     .class_base_init = device_class_base_init,
     .class_init = device_class_init,

hw/cpu/Makefile.objs

@@ -1,5 +1,5 @@
 obj-$(CONFIG_ARM11MPCORE) += arm11mpcore.o
-obj-$(CONFIG_ARM9MPCORE) += a9mpcore.o
-obj-$(CONFIG_ARM15MPCORE) += a15mpcore.o
+obj-$(CONFIG_A9MPCORE) += a9mpcore.o
+obj-$(CONFIG_A15MPCORE) += a15mpcore.o
 obj-$(CONFIG_ICC_BUS) += icc_bus.o
 

hw/cpu/a15mpcore.c

@@ -49,6 +49,8 @@ static int a15mp_priv_init(SysBusDevice *dev)
     A15MPPrivState *s = A15MPCORE_PRIV(dev);
     SysBusDevice *busdev;
     const char *gictype = "arm_gic";
+    int i;
+    CPUState *cpu;
 
     if (kvm_irqchip_in_kernel()) {
         gictype = "kvm-arm-gic";
@@ -67,6 +69,22 @@ static int a15mp_priv_init(SysBusDevice *dev)
     /* Pass through inbound GPIO lines to the GIC */
     qdev_init_gpio_in(DEVICE(dev), a15mp_priv_set_irq, s->num_irq - 32);
 
+    /* Wire the outputs from each CPU's generic timer to the
+     * appropriate GIC PPI inputs
+     */
+    for (i = 0, cpu = first_cpu; i < s->num_cpu; i++, cpu = cpu->next_cpu) {
+        DeviceState *cpudev = DEVICE(cpu);
+        int ppibase = s->num_irq - 32 + i * 32;
+        /* physical timer; we wire it up to the non-secure timer's ID,
+         * since a real A15 always has TrustZone but QEMU doesn't.
+         */
+        qdev_connect_gpio_out(cpudev, 0,
+                              qdev_get_gpio_in(s->gic, ppibase + 30));
+        /* virtual timer */
+        qdev_connect_gpio_out(cpudev, 1,
+                              qdev_get_gpio_in(s->gic, ppibase + 27));
+    }
+
     /* Memory map (addresses are offsets from PERIPHBASE):
      *  0x0000-0x0fff -- reserved
      *  0x1000-0x1fff -- GIC Distributor

hw/cris/axis_dev88.c

@@ -355,7 +355,6 @@ static QEMUMachine axisdev88_machine = {
     .desc = "AXIS devboard 88",
     .init = axisdev88_init,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void axisdev88_machine_init(void)

hw/display/qxl-render.c

@@ -31,6 +31,10 @@ static void qxl_blit(PCIQXLDevice *qxl, QXLRect *rect)
     if (is_buffer_shared(surface)) {
         return;
     }
+    if (!qxl->guest_primary.data) {
+        trace_qxl_render_blit_guest_primary_initialized();
+        qxl->guest_primary.data = memory_region_get_ram_ptr(&qxl->vga.vram);
+    }
     trace_qxl_render_blit(qxl->guest_primary.qxl_stride,
             rect->left, rect->right, rect->top, rect->bottom);
     src = qxl->guest_primary.data;
@@ -100,12 +104,7 @@ static void qxl_render_update_area_unlocked(PCIQXLDevice *qxl)
 
     if (qxl->guest_primary.resized) {
         qxl->guest_primary.resized = 0;
-        qxl->guest_primary.data = qxl_phys2virt(qxl,
-                                                qxl->guest_primary.surface.mem,
-                                                MEMSLOT_GROUP_GUEST);
-        if (!qxl->guest_primary.data) {
-            return;
-        }
+        qxl->guest_primary.data = memory_region_get_ram_ptr(&qxl->vga.vram);
         qxl_set_rect_to_surface(qxl, &qxl->dirty[0]);
         qxl->num_dirty_rects = 1;
         trace_qxl_render_guest_primary_resized(
@@ -129,10 +128,6 @@ static void qxl_render_update_area_unlocked(PCIQXLDevice *qxl)
         }
         dpy_gfx_replace_surface(vga->con, surface);
     }
-
-    if (!qxl->guest_primary.data) {
-        return;
-    }
     for (i = 0; i < qxl->num_dirty_rects; i++) {
         if (qemu_spice_rect_is_empty(qxl->dirty+i)) {
             break;

hw/i386/kvmvapic.c

@@ -510,8 +510,9 @@ static void vapic_reset(DeviceState *dev)
 {
     VAPICROMState *s = VAPIC(dev);
 
-    s->state = VAPIC_INACTIVE;
-    s->rom_state_paddr = 0;
+    if (s->state == VAPIC_ACTIVE) {
+        s->state = VAPIC_STANDBY;
+    }
     vapic_enable_tpr_reporting(false);
 }
 
@@ -577,7 +578,7 @@ static int patch_hypercalls(VAPICROMState *s)
  * enable write access to the option ROM so that variables can be updated by
  * the guest.
  */
-static int vapic_map_rom_writable(VAPICROMState *s)
+static void vapic_map_rom_writable(VAPICROMState *s)
 {
     hwaddr rom_paddr = s->rom_state_paddr & ROM_BLOCK_MASK;
     MemoryRegionSection section;
@@ -598,9 +599,6 @@ static int vapic_map_rom_writable(VAPICROMState *s)
     /* read ROM size from RAM region */
     ram = memory_region_get_ram_ptr(section.mr);
     rom_size = ram[rom_paddr + 2] * ROM_BLOCK_SIZE;
-    if (rom_size == 0) {
-        return -1;
-    }
     s->rom_size = rom_size;
 
     /* We need to round to avoid creating subpages
@@ -614,15 +612,11 @@ static int vapic_map_rom_writable(VAPICROMState *s)
     memory_region_add_subregion_overlap(as, rom_paddr, &s->rom, 1000);
     s->rom_mapped_writable = true;
     memory_region_unref(section.mr);
-
-    return 0;
 }
 
 static int vapic_prepare(VAPICROMState *s)
 {
-    if (vapic_map_rom_writable(s) < 0) {
-        return -1;
-    }
+    vapic_map_rom_writable(s);
 
     if (patch_hypercalls(s) < 0) {
         return -1;
@@ -665,7 +659,6 @@ static void vapic_write(void *opaque, hwaddr addr, uint64_t data,
         }
         if (vapic_prepare(s) < 0) {
             s->state = VAPIC_INACTIVE;
-            s->rom_state_paddr = 0;
             break;
         }
         break;

hw/i386/pc_piix.c

@@ -25,6 +25,7 @@
 #include <glib.h>
 
 #include "hw/hw.h"
+#include "hw/loader.h"
 #include "hw/i386/pc.h"
 #include "hw/i386/apic.h"
 #include "hw/pci/pci.h"
@@ -60,17 +61,12 @@ static bool has_pvpanic;
 static bool has_pci_info = true;
 
 /* PC hardware initialisation */
-static void pc_init1(MemoryRegion *system_memory,
-                     MemoryRegion *system_io,
-                     ram_addr_t ram_size,
-                     const char *boot_device,
-                     const char *kernel_filename,
-                     const char *kernel_cmdline,
-                     const char *initrd_filename,
-                     const char *cpu_model,
+static void pc_init1(QEMUMachineInitArgs *args,
                      int pci_enabled,
                      int kvmclock_enabled)
 {
+    MemoryRegion *system_memory = get_system_memory();
+    MemoryRegion *system_io = get_system_io();
     int i;
     ram_addr_t below_4g_mem_size, above_4g_mem_size;
     PCIBus *pci_bus;
@@ -93,7 +89,7 @@ static void pc_init1(MemoryRegion *system_memory,
     FWCfgState *fw_cfg = NULL;
     PcGuestInfo *guest_info;
 
-    if (xen_enabled() && xen_hvm_init(&ram_memory) != 0) {
+    if (xen_enabled() && xen_hvm_init() != 0) {
         fprintf(stderr, "xen hardware virtual machine initialisation failed\n");
         exit(1);
     }
@@ -102,18 +98,18 @@ static void pc_init1(MemoryRegion *system_memory,
     object_property_add_child(qdev_get_machine(), "icc-bridge",
                               OBJECT(icc_bridge), NULL);
 
-    pc_cpus_init(cpu_model, icc_bridge);
+    pc_cpus_init(args->cpu_model, icc_bridge);
 
     if (kvm_enabled() && kvmclock_enabled) {
         kvmclock_create();
     }
 
-    if (ram_size >= 0xe0000000 ) {
-        above_4g_mem_size = ram_size - 0xe0000000;
+    if (args->ram_size >= 0xe0000000) {
+        above_4g_mem_size = args->ram_size - 0xe0000000;
         below_4g_mem_size = 0xe0000000;
     } else {
         above_4g_mem_size = 0;
-        below_4g_mem_size = ram_size;
+        below_4g_mem_size = args->ram_size;
     }
 
     if (pci_enabled) {
@@ -132,7 +128,8 @@ static void pc_init1(MemoryRegion *system_memory,
     /* allocate ram and load rom/bios */
     if (!xen_enabled()) {
         fw_cfg = pc_memory_init(system_memory,
-                       kernel_filename, kernel_cmdline, initrd_filename,
+                       args->kernel_filename, args->kernel_cmdline,
+                       args->initrd_filename,
                        below_4g_mem_size, above_4g_mem_size,
                        rom_memory, &ram_memory, guest_info);
     }
@@ -148,7 +145,7 @@ static void pc_init1(MemoryRegion *system_memory,
 
     if (pci_enabled) {
         pci_bus = i440fx_init(&i440fx_state, &piix3_devfn, &isa_bus, gsi,
-                              system_memory, system_io, ram_size,
+                              system_memory, system_io, args->ram_size,
                               below_4g_mem_size,
                               0x100000000ULL - below_4g_mem_size,
                               above_4g_mem_size,
@@ -207,7 +204,7 @@ static void pc_init1(MemoryRegion *system_memory,
         }
     }
 
-    pc_cmos_init(below_4g_mem_size, above_4g_mem_size, boot_device,
+    pc_cmos_init(below_4g_mem_size, above_4g_mem_size, args->boot_order,
                  floppy, idebus[0], idebus[1], rtc_state);
 
     if (pci_enabled && usb_enabled(false)) {
@@ -236,95 +233,91 @@ static void pc_init1(MemoryRegion *system_memory,
 
 static void pc_init_pci(QEMUMachineInitArgs *args)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
-    pc_init1(get_system_memory(),
-             get_system_io(),
-             ram_size, boot_device,
-             kernel_filename, kernel_cmdline,
-             initrd_filename, cpu_model, 1, 1);
+    pc_init1(args, 1, 1);
+}
+
+static void pc_compat_1_6(QEMUMachineInitArgs *args)
+{
+    has_pci_info = false;
+    rom_file_in_ram = false;
+}
+
+static void pc_compat_1_5(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_6(args);
+    has_pvpanic = true;
+}
+
+static void pc_compat_1_4(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_5(args);
+    has_pvpanic = false;
+    x86_cpu_compat_set_features("n270", FEAT_1_ECX, 0, CPUID_EXT_MOVBE);
+    x86_cpu_compat_set_features("Westmere", FEAT_1_ECX, 0, CPUID_EXT_PCLMULQDQ);
+}
+
+static void pc_compat_1_3(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_4(args);
+    enable_compat_apic_id_mode();
+}
+
+/* PC compat function for pc-0.14 to pc-1.2 */
+static void pc_compat_1_2(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_3(args);
+    disable_kvm_pv_eoi();
 }
 
 static void pc_init_pci_1_6(QEMUMachineInitArgs *args)
 {
-    has_pci_info = false;
+    pc_compat_1_6(args);
     pc_init_pci(args);
 }
 
 static void pc_init_pci_1_5(QEMUMachineInitArgs *args)
 {
-    has_pvpanic = true;
-    pc_init_pci_1_6(args);
+    pc_compat_1_5(args);
+    pc_init_pci(args);
 }
 
 static void pc_init_pci_1_4(QEMUMachineInitArgs *args)
 {
-    x86_cpu_compat_set_features("n270", FEAT_1_ECX, 0, CPUID_EXT_MOVBE);
-    x86_cpu_compat_set_features("Westmere", FEAT_1_ECX, 0, CPUID_EXT_PCLMULQDQ);
-    has_pci_info = false;
+    pc_compat_1_4(args);
     pc_init_pci(args);
 }
 
 static void pc_init_pci_1_3(QEMUMachineInitArgs *args)
 {
-    enable_compat_apic_id_mode();
-    pc_init_pci_1_4(args);
+    pc_compat_1_3(args);
+    pc_init_pci(args);
 }
 
-/* PC machine init function for pc-1.1 to pc-1.2 */
+/* PC machine init function for pc-0.14 to pc-1.2 */
 static void pc_init_pci_1_2(QEMUMachineInitArgs *args)
 {
-    disable_kvm_pv_eoi();
-    pc_init_pci_1_3(args);
-}
-
-/* PC machine init function for pc-0.14 to pc-1.0 */
-static void pc_init_pci_1_0(QEMUMachineInitArgs *args)
-{
-    pc_init_pci_1_2(args);
+    pc_compat_1_2(args);
+    pc_init_pci(args);
 }
 
 /* PC init function for pc-0.10 to pc-0.13, and reused by xenfv */
 static void pc_init_pci_no_kvmclock(QEMUMachineInitArgs *args)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
     has_pci_info = false;
     disable_kvm_pv_eoi();
     enable_compat_apic_id_mode();
-    pc_init1(get_system_memory(),
-             get_system_io(),
-             ram_size, boot_device,
-             kernel_filename, kernel_cmdline,
-             initrd_filename, cpu_model, 1, 0);
+    pc_init1(args, 1, 0);
 }
 
 static void pc_init_isa(QEMUMachineInitArgs *args)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
     has_pci_info = false;
-    if (cpu_model == NULL)
-        cpu_model = "486";
+    if (!args->cpu_model) {
+        args->cpu_model = "486";
+    }
     disable_kvm_pv_eoi();
     enable_compat_apic_id_mode();
-    pc_init1(get_system_memory(),
-             get_system_io(),
-             ram_size, boot_device,
-             kernel_filename, kernel_cmdline,
-             initrd_filename, cpu_model, 0, 1);
+    pc_init1(args, 0, 1);
 }
 
 #ifdef CONFIG_XEN
@@ -341,40 +334,43 @@ static void pc_xen_hvm_init(QEMUMachineInitArgs *args)
 }
 #endif
 
+#define PC_I440FX_MACHINE_OPTIONS \
+    PC_DEFAULT_MACHINE_OPTIONS, \
+    .desc = "Standard PC (i440FX + PIIX, 1996)", \
+    .hot_add_cpu = pc_hot_add_cpu
+
+#define PC_I440FX_1_6_MACHINE_OPTIONS PC_I440FX_MACHINE_OPTIONS
+
 static QEMUMachine pc_i440fx_machine_v1_6 = {
+    PC_I440FX_1_6_MACHINE_OPTIONS,
     .name = "pc-i440fx-1.6",
     .alias = "pc",
-    .desc = "Standard PC (i440FX + PIIX, 1996)",
     .init = pc_init_pci_1_6,
-    .hot_add_cpu = pc_hot_add_cpu,
-    .max_cpus = 255,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine pc_i440fx_machine_v1_5 = {
+    PC_I440FX_1_6_MACHINE_OPTIONS,
     .name = "pc-i440fx-1.5",
-    .desc = "Standard PC (i440FX + PIIX, 1996)",
     .init = pc_init_pci_1_5,
-    .hot_add_cpu = pc_hot_add_cpu,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_5,
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
+#define PC_I440FX_1_4_MACHINE_OPTIONS \
+    PC_I440FX_1_6_MACHINE_OPTIONS, \
+    .hot_add_cpu = NULL
+
 static QEMUMachine pc_i440fx_machine_v1_4 = {
+    PC_I440FX_1_4_MACHINE_OPTIONS,
     .name = "pc-i440fx-1.4",
-    .desc = "Standard PC (i440FX + PIIX, 1996)",
     .init = pc_init_pci_1_4,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_4,
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_1_3 \
@@ -398,15 +394,13 @@ static QEMUMachine pc_i440fx_machine_v1_4 = {
         }
 
 static QEMUMachine pc_machine_v1_3 = {
+    PC_I440FX_1_4_MACHINE_OPTIONS,
     .name = "pc-1.3",
-    .desc = "Standard PC",
     .init = pc_init_pci_1_3,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_3,
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_1_2 \
@@ -437,16 +431,17 @@ static QEMUMachine pc_machine_v1_3 = {
             .value    = "off",\
         }
 
+#define PC_I440FX_1_2_MACHINE_OPTIONS \
+    PC_I440FX_1_4_MACHINE_OPTIONS, \
+    .init = pc_init_pci_1_2
+
 static QEMUMachine pc_machine_v1_2 = {
+    PC_I440FX_1_2_MACHINE_OPTIONS,
     .name = "pc-1.2",
-    .desc = "Standard PC",
-    .init = pc_init_pci_1_2,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_2,
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_1_1 \
@@ -482,15 +477,12 @@ static QEMUMachine pc_machine_v1_2 = {
         }
 
 static QEMUMachine pc_machine_v1_1 = {
+    PC_I440FX_1_2_MACHINE_OPTIONS,
     .name = "pc-1.1",
-    .desc = "Standard PC",
-    .init = pc_init_pci_1_2,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_1,
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_1_0 \
@@ -514,32 +506,26 @@ static QEMUMachine pc_machine_v1_1 = {
         }
 
 static QEMUMachine pc_machine_v1_0 = {
+    PC_I440FX_1_2_MACHINE_OPTIONS,
     .name = "pc-1.0",
-    .desc = "Standard PC",
-    .init = pc_init_pci_1_0,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_0,
         { /* end of list */ }
     },
     .hw_version = "1.0",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_0_15 \
         PC_COMPAT_1_0
 
 static QEMUMachine pc_machine_v0_15 = {
+    PC_I440FX_1_2_MACHINE_OPTIONS,
     .name = "pc-0.15",
-    .desc = "Standard PC",
-    .init = pc_init_pci_1_0,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_15,
         { /* end of list */ }
     },
     .hw_version = "0.15",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_0_14 \
@@ -563,10 +549,8 @@ static QEMUMachine pc_machine_v0_15 = {
         }
 
 static QEMUMachine pc_machine_v0_14 = {
+    PC_I440FX_1_2_MACHINE_OPTIONS,
     .name = "pc-0.14",
-    .desc = "Standard PC",
-    .init = pc_init_pci_1_0,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_14, 
         {
@@ -581,7 +565,6 @@ static QEMUMachine pc_machine_v0_14 = {
         { /* end of list */ }
     },
     .hw_version = "0.14",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_0_13 \
@@ -596,11 +579,13 @@ static QEMUMachine pc_machine_v0_14 = {
             .value    = stringify(1),\
         }
 
+#define PC_I440FX_0_13_MACHINE_OPTIONS \
+    PC_I440FX_1_2_MACHINE_OPTIONS, \
+    .init = pc_init_pci_no_kvmclock
+
 static QEMUMachine pc_machine_v0_13 = {
+    PC_I440FX_0_13_MACHINE_OPTIONS,
     .name = "pc-0.13",
-    .desc = "Standard PC",
-    .init = pc_init_pci_no_kvmclock,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_13,
         {
@@ -619,7 +604,6 @@ static QEMUMachine pc_machine_v0_13 = {
         { /* end of list */ }
     },
     .hw_version = "0.13",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_0_12 \
@@ -647,10 +631,8 @@ static QEMUMachine pc_machine_v0_13 = {
         }
 
 static QEMUMachine pc_machine_v0_12 = {
+    PC_I440FX_0_13_MACHINE_OPTIONS,
     .name = "pc-0.12",
-    .desc = "Standard PC",
-    .init = pc_init_pci_no_kvmclock,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_12,
         {
@@ -665,7 +647,6 @@ static QEMUMachine pc_machine_v0_12 = {
         { /* end of list */ }
     },
     .hw_version = "0.12",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #define PC_COMPAT_0_11 \
@@ -681,10 +662,8 @@ static QEMUMachine pc_machine_v0_12 = {
         }
 
 static QEMUMachine pc_machine_v0_11 = {
+    PC_I440FX_0_13_MACHINE_OPTIONS,
     .name = "pc-0.11",
-    .desc = "Standard PC, qemu 0.11",
-    .init = pc_init_pci_no_kvmclock,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_11,
         {
@@ -699,14 +678,11 @@ static QEMUMachine pc_machine_v0_11 = {
         { /* end of list */ }
     },
     .hw_version = "0.11",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine pc_machine_v0_10 = {
+    PC_I440FX_0_13_MACHINE_OPTIONS,
     .name = "pc-0.10",
-    .desc = "Standard PC, qemu 0.10",
-    .init = pc_init_pci_no_kvmclock,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_0_11,
         {
@@ -733,10 +709,10 @@ static QEMUMachine pc_machine_v0_10 = {
         { /* end of list */ }
     },
     .hw_version = "0.10",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine isapc_machine = {
+    PC_COMMON_MACHINE_OPTIONS,
     .name = "isapc",
     .desc = "ISA-only PC",
     .init = pc_init_isa,
@@ -744,17 +720,16 @@ static QEMUMachine isapc_machine = {
     .compat_props = (GlobalProperty[]) {
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 #ifdef CONFIG_XEN
 static QEMUMachine xenfv_machine = {
+    PC_COMMON_MACHINE_OPTIONS,
     .name = "xenfv",
     .desc = "Xen Fully-virtualized PC",
     .init = pc_xen_hvm_init,
     .max_cpus = HVM_MAX_VCPUS,
     .default_machine_opts = "accel=xen",
-    DEFAULT_MACHINE_OPTIONS,
 };
 #endif
 

hw/i386/pc_q35.c

@@ -28,6 +28,7 @@
  * THE SOFTWARE.
  */
 #include "hw/hw.h"
+#include "hw/loader.h"
 #include "sysemu/arch_init.h"
 #include "hw/i2c/smbus.h"
 #include "hw/boards.h"
@@ -52,12 +53,6 @@ static bool has_pci_info = true;
 /* PC hardware initialisation */
 static void pc_q35_init(QEMUMachineInitArgs *args)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
     ram_addr_t below_4g_mem_size, above_4g_mem_size;
     Q35PCIHost *q35_host;
     PCIHostState *phb;
@@ -81,26 +76,21 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
     DeviceState *icc_bridge;
     PcGuestInfo *guest_info;
 
-    if (xen_enabled() && xen_hvm_init(&ram_memory) != 0) {
-        fprintf(stderr, "xen hardware virtual machine initialisation failed\n");
-        exit(1);
-    }
-
     icc_bridge = qdev_create(NULL, TYPE_ICC_BRIDGE);
     object_property_add_child(qdev_get_machine(), "icc-bridge",
                               OBJECT(icc_bridge), NULL);
 
-    pc_cpus_init(cpu_model, icc_bridge);
+    pc_cpus_init(args->cpu_model, icc_bridge);
     pc_acpi_init("q35-acpi-dsdt.aml");
 
     kvmclock_create();
 
-    if (ram_size >= 0xb0000000) {
-        above_4g_mem_size = ram_size - 0xb0000000;
+    if (args->ram_size >= 0xb0000000) {
+        above_4g_mem_size = args->ram_size - 0xb0000000;
         below_4g_mem_size = 0xb0000000;
     } else {
         above_4g_mem_size = 0;
-        below_4g_mem_size = ram_size;
+        below_4g_mem_size = args->ram_size;
     }
 
     /* pci enabled */
@@ -119,8 +109,10 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
 
     /* allocate ram and load rom/bios */
     if (!xen_enabled()) {
-        pc_memory_init(get_system_memory(), kernel_filename, kernel_cmdline,
-                       initrd_filename, below_4g_mem_size, above_4g_mem_size,
+        pc_memory_init(get_system_memory(),
+                       args->kernel_filename, args->kernel_cmdline,
+                       args->initrd_filename,
+                       below_4g_mem_size, above_4g_mem_size,
                        rom_memory, &ram_memory, guest_info);
     }
 
@@ -208,7 +200,7 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
                                     0xb100),
                       8, NULL, 0);
 
-    pc_cmos_init(below_4g_mem_size, above_4g_mem_size, boot_device,
+    pc_cmos_init(below_4g_mem_size, above_4g_mem_size, args->boot_order,
                  floppy, idebus[0], idebus[1], rtc_state);
 
     /* the rest devices to which pci devfn is automatically assigned */
@@ -223,59 +215,80 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
     }
 }
 
-static void pc_q35_init_1_6(QEMUMachineInitArgs *args)
+static void pc_compat_1_6(QEMUMachineInitArgs *args)
 {
     has_pci_info = false;
+    rom_file_in_ram = false;
+}
+
+static void pc_compat_1_5(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_6(args);
+    has_pvpanic = true;
+}
+
+static void pc_compat_1_4(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_5(args);
+    has_pvpanic = false;
+    x86_cpu_compat_set_features("n270", FEAT_1_ECX, 0, CPUID_EXT_MOVBE);
+    x86_cpu_compat_set_features("Westmere", FEAT_1_ECX, 0, CPUID_EXT_PCLMULQDQ);
+}
+
+static void pc_q35_init_1_6(QEMUMachineInitArgs *args)
+{
+    pc_compat_1_6(args);
     pc_q35_init(args);
 }
 
 static void pc_q35_init_1_5(QEMUMachineInitArgs *args)
 {
-    has_pvpanic = true;
-    pc_q35_init_1_6(args);
+    pc_compat_1_5(args);
+    pc_q35_init(args);
 }
 
 static void pc_q35_init_1_4(QEMUMachineInitArgs *args)
 {
-    x86_cpu_compat_set_features("n270", FEAT_1_ECX, 0, CPUID_EXT_MOVBE);
-    x86_cpu_compat_set_features("Westmere", FEAT_1_ECX, 0, CPUID_EXT_PCLMULQDQ);
-    has_pci_info = false;
+    pc_compat_1_4(args);
     pc_q35_init(args);
 }
 
+#define PC_Q35_MACHINE_OPTIONS \
+    PC_DEFAULT_MACHINE_OPTIONS, \
+    .desc = "Standard PC (Q35 + ICH9, 2009)", \
+    .hot_add_cpu = pc_hot_add_cpu
+
+#define PC_Q35_1_6_MACHINE_OPTIONS PC_Q35_MACHINE_OPTIONS
+
 static QEMUMachine pc_q35_machine_v1_6 = {
+    PC_Q35_1_6_MACHINE_OPTIONS,
     .name = "pc-q35-1.6",
     .alias = "q35",
-    .desc = "Standard PC (Q35 + ICH9, 2009)",
     .init = pc_q35_init_1_6,
-    .hot_add_cpu = pc_hot_add_cpu,
-    .max_cpus = 255,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine pc_q35_machine_v1_5 = {
+    PC_Q35_1_6_MACHINE_OPTIONS,
     .name = "pc-q35-1.5",
-    .desc = "Standard PC (Q35 + ICH9, 2009)",
     .init = pc_q35_init_1_5,
-    .hot_add_cpu = pc_hot_add_cpu,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_5,
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
+#define PC_Q35_1_4_MACHINE_OPTIONS \
+    PC_Q35_1_6_MACHINE_OPTIONS, \
+    .hot_add_cpu = NULL
+
 static QEMUMachine pc_q35_machine_v1_4 = {
+    PC_Q35_1_4_MACHINE_OPTIONS,
     .name = "pc-q35-1.4",
-    .desc = "Standard PC (Q35 + ICH9, 2009)",
     .init = pc_q35_init_1_4,
-    .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         PC_COMPAT_1_4,
         { /* end of list */ }
     },
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void pc_q35_machine_init(void)

hw/i386/xen_machine_pv.c

@@ -99,7 +99,6 @@ static QEMUMachine xenpv_machine = {
     .init = xen_init_pv,
     .max_cpus = 1,
     .default_machine_opts = "accel=xen",
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void xenpv_machine_init(void)

hw/lm32/lm32_boards.c

@@ -289,7 +289,6 @@ static QEMUMachine lm32_evr_machine = {
     .desc = "LatticeMico32 EVR32 eval system",
     .init = lm32_evr_init,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine lm32_uclinux_machine = {
@@ -297,7 +296,6 @@ static QEMUMachine lm32_uclinux_machine = {
     .desc = "lm32 platform for uClinux and u-boot by Theobroma Systems",
     .init = lm32_uclinux_init,
     .is_default = 0,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void lm32_machine_init(void)

hw/lm32/milkymist.c

@@ -208,7 +208,6 @@ static QEMUMachine milkymist_machine = {
     .desc = "Milkymist One",
     .init = milkymist_init,
     .is_default = 0,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void milkymist_machine_init(void)

hw/m68k/an5206.c

@@ -89,7 +89,6 @@ static QEMUMachine an5206_machine = {
     .name = "an5206",
     .desc = "Arnewsh 5206",
     .init = an5206_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void an5206_machine_init(void)

hw/m68k/dummy_m68k.c

@@ -73,7 +73,6 @@ static QEMUMachine dummy_m68k_machine = {
     .name = "dummy",
     .desc = "Dummy board",
     .init = dummy_m68k_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void dummy_m68k_machine_init(void)

hw/m68k/mcf5208.c

@@ -295,7 +295,6 @@ static QEMUMachine mcf5208evb_machine = {
     .desc = "MCF5206EVB",
     .init = mcf5208evb_init,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void mcf5208evb_machine_init(void)

hw/microblaze/petalogix_ml605_mmu.c

@@ -186,7 +186,6 @@ static QEMUMachine petalogix_ml605_machine = {
     .desc = "PetaLogix linux refdesign for xilinx ml605 little endian",
     .init = petalogix_ml605_init,
     .is_default = 0,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void petalogix_ml605_machine_init(void)

hw/microblaze/petalogix_s3adsp1800_mmu.c

@@ -116,7 +116,6 @@ static QEMUMachine petalogix_s3adsp1800_machine = {
     .desc = "PetaLogix linux refdesign for xilinx Spartan 3ADSP1800",
     .init = petalogix_s3adsp1800_init,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void petalogix_s3adsp1800_machine_init(void)

hw/mips/mips_fulong2e.c

@@ -403,7 +403,6 @@ static QEMUMachine mips_fulong2e_machine = {
     .name = "fulong2e",
     .desc = "Fulong 2e mini pc",
     .init = mips_fulong2e_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void mips_fulong2e_machine_init(void)

hw/mips/mips_jazz.c

@@ -327,7 +327,6 @@ static QEMUMachine mips_magnum_machine = {
     .desc = "MIPS Magnum",
     .init = mips_magnum_init,
     .block_default_type = IF_SCSI,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static QEMUMachine mips_pica61_machine = {
@@ -335,7 +334,6 @@ static QEMUMachine mips_pica61_machine = {
     .desc = "Acer Pica 61",
     .init = mips_pica61_init,
     .block_default_type = IF_SCSI,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void mips_jazz_machine_init(void)

hw/mips/mips_malta.c

@@ -1136,7 +1136,6 @@ static QEMUMachine mips_malta_machine = {
     .init = mips_malta_init,
     .max_cpus = 16,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void mips_malta_register_types(void)

hw/mips/mips_mipssim.c

@@ -232,7 +232,6 @@ static QEMUMachine mips_mipssim_machine = {
     .name = "mipssim",
     .desc = "MIPS MIPSsim platform",
     .init = mips_mipssim_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void mips_mipssim_machine_init(void)

hw/mips/mips_r4k.c

@@ -306,7 +306,6 @@ static QEMUMachine mips_machine = {
     .name = "mips",
     .desc = "mips r4k platform",
     .init = mips_r4k_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void mips_machine_init(void)

hw/net/ne2000.c

@@ -693,7 +693,7 @@ static void ne2000_write(void *opaque, hwaddr addr,
 static const MemoryRegionOps ne2000_ops = {
     .read = ne2000_read,
     .write = ne2000_write,
-    .endianness = DEVICE_LITTLE_ENDIAN,
+    .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
 /***********************************************************/

hw/net/pcnet-pci.c

@@ -134,7 +134,7 @@ static void pcnet_ioport_write(void *opaque, hwaddr addr,
 static const MemoryRegionOps pcnet_io_ops = {
     .read = pcnet_ioport_read,
     .write = pcnet_ioport_write,
-    .endianness = DEVICE_LITTLE_ENDIAN,
+    .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
 static void pcnet_mmio_writeb(void *opaque, hwaddr addr, uint32_t val)
@@ -256,7 +256,7 @@ static const MemoryRegionOps pcnet_mmio_ops = {
         .read = { pcnet_mmio_readb, pcnet_mmio_readw, pcnet_mmio_readl },
         .write = { pcnet_mmio_writeb, pcnet_mmio_writew, pcnet_mmio_writel },
     },
-    .endianness = DEVICE_LITTLE_ENDIAN,
+    .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
 static void pci_physical_memory_write(void *dma_opaque, hwaddr addr,

hw/openrisc/openrisc_sim.c

@@ -139,7 +139,6 @@ static QEMUMachine openrisc_sim_machine = {
     .init = openrisc_sim_init,
     .max_cpus = 1,
     .is_default = 1,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void openrisc_sim_machine_init(void)

hw/pci/pci.c

@@ -812,12 +812,7 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
     }
 
     pci_dev->bus = bus;
-    if (bus->iommu_fn) {
-        dma_as = bus->iommu_fn(bus, bus->iommu_opaque, devfn);
-    } else {
-        /* FIXME: inherit memory region from bus creator */
-        dma_as = &address_space_memory;
-    }
+    dma_as = pci_device_iommu_address_space(pci_dev);
 
     memory_region_init_alias(&pci_dev->bus_master_enable_region,
                              OBJECT(pci_dev), "bus master",
@@ -2239,6 +2234,23 @@ static void pci_device_class_init(ObjectClass *klass, void *data)
     k->props = pci_props;
 }
 
+AddressSpace *pci_device_iommu_address_space(PCIDevice *dev)
+{
+    PCIBus *bus = PCI_BUS(dev->bus);
+
+    if (bus->iommu_fn) {
+        return bus->iommu_fn(bus, bus->iommu_opaque, dev->devfn);
+    }
+
+    if (bus->parent_dev) {
+        /** We are ignoring the bus master DMA bit of the bridge
+         *  as it would complicate things such as VFIO for no good reason */
+        return pci_device_iommu_address_space(bus->parent_dev);
+    }
+
+    return &address_space_memory;
+}
+
 void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn, void *opaque)
 {
     bus->iommu_fn = fn;

hw/pci/pci_host.c

@@ -20,6 +20,7 @@
 
 #include "hw/pci/pci.h"
 #include "hw/pci/pci_host.h"
+#include "trace.h"
 
 /* debug PCI */
 //#define DEBUG_PCI
@@ -51,14 +52,22 @@ void pci_host_config_write_common(PCIDevice *pci_dev, uint32_t addr,
                                   uint32_t limit, uint32_t val, uint32_t len)
 {
     assert(len <= 4);
+    trace_pci_cfg_write(pci_dev->name, PCI_SLOT(pci_dev->devfn),
+                        PCI_FUNC(pci_dev->devfn), addr, val);
     pci_dev->config_write(pci_dev, addr, val, MIN(len, limit - addr));
 }
 
 uint32_t pci_host_config_read_common(PCIDevice *pci_dev, uint32_t addr,
                                      uint32_t limit, uint32_t len)
 {
+    uint32_t ret;
+
     assert(len <= 4);
-    return pci_dev->config_read(pci_dev, addr, MIN(len, limit - addr));
+    ret = pci_dev->config_read(pci_dev, addr, MIN(len, limit - addr));
+    trace_pci_cfg_read(pci_dev->name, PCI_SLOT(pci_dev->devfn),
+                       PCI_FUNC(pci_dev->devfn), addr, ret);
+
+    return ret;
 }
 
 void pci_data_write(PCIBus *s, uint32_t addr, uint32_t val, int len)

hw/ppc/e500.c

@@ -124,13 +124,14 @@ static void dt_serial_create(void *fdt, unsigned long long offset,
 }
 
 static int ppce500_load_device_tree(CPUPPCState *env,
+                                    QEMUMachineInitArgs *args,
                                     PPCE500Params *params,
                                     hwaddr addr,
                                     hwaddr initrd_base,
                                     hwaddr initrd_size)
 {
     int ret = -1;
-    uint64_t mem_reg_property[] = { 0, cpu_to_be64(params->ram_size) };
+    uint64_t mem_reg_property[] = { 0, cpu_to_be64(args->ram_size) };
     int fdt_size;
     void *fdt;
     uint8_t hypercall[16];
@@ -205,7 +206,7 @@ static int ppce500_load_device_tree(CPUPPCState *env,
     }
 
     ret = qemu_devtree_setprop_string(fdt, "/chosen", "bootargs",
-                                      params->kernel_cmdline);
+                                      args->kernel_cmdline);
     if (ret < 0)
         fprintf(stderr, "couldn't set /chosen/bootargs\n");
 
@@ -559,7 +560,7 @@ static qemu_irq *ppce500_init_mpic(PPCE500Params *params, MemoryRegion *ccsr,
     return mpic;
 }
 
-void ppce500_init(PPCE500Params *params)
+void ppce500_init(QEMUMachineInitArgs *args, PPCE500Params *params)
 {
     MemoryRegion *address_space_mem = get_system_memory();
     MemoryRegion *ram = g_new(MemoryRegion, 1);
@@ -584,8 +585,8 @@ void ppce500_init(PPCE500Params *params)
     PPCE500CCSRState *ccsr;
 
     /* Setup CPUs */
-    if (params->cpu_model == NULL) {
-        params->cpu_model = "e500v2_v30";
+    if (args->cpu_model == NULL) {
+        args->cpu_model = "e500v2_v30";
     }
 
     irqs = g_malloc0(smp_cpus * sizeof(qemu_irq *));
@@ -595,7 +596,7 @@ void ppce500_init(PPCE500Params *params)
         CPUState *cs;
         qemu_irq *input;
 
-        cpu = cpu_ppc_init(params->cpu_model);
+        cpu = cpu_ppc_init(args->cpu_model);
         if (cpu == NULL) {
             fprintf(stderr, "Unable to initialize CPU!\n");
             exit(1);
@@ -634,7 +635,7 @@ void ppce500_init(PPCE500Params *params)
 
     /* Fixup Memory size on a alignment boundary */
     ram_size &= ~(RAM_SIZES_ALIGN - 1);
-    params->ram_size = ram_size;
+    args->ram_size = ram_size;
 
     /* Register Memory */
     memory_region_init_ram(ram, NULL, "mpc8544ds.ram", ram_size);
@@ -701,11 +702,11 @@ void ppce500_init(PPCE500Params *params)
     sysbus_create_simple("e500-spin", MPC8544_SPIN_BASE, NULL);
 
     /* Load kernel. */
-    if (params->kernel_filename) {
-        kernel_size = load_uimage(params->kernel_filename, &entry,
+    if (args->kernel_filename) {
+        kernel_size = load_uimage(args->kernel_filename, &entry,
                                   &loadaddr, NULL);
         if (kernel_size < 0) {
-            kernel_size = load_elf(params->kernel_filename, NULL, NULL,
+            kernel_size = load_elf(args->kernel_filename, NULL, NULL,
                                    &elf_entry, &elf_lowaddr, NULL, 1,
                                    ELF_MACHINE, 0);
             entry = elf_entry;
@@ -714,7 +715,7 @@ void ppce500_init(PPCE500Params *params)
         /* XXX try again as binary */
         if (kernel_size < 0) {
             fprintf(stderr, "qemu: could not load kernel '%s'\n",
-                    params->kernel_filename);
+                    args->kernel_filename);
             exit(1);
         }
 
@@ -726,14 +727,14 @@ void ppce500_init(PPCE500Params *params)
     }
 
     /* Load initrd. */
-    if (params->initrd_filename) {
+    if (args->initrd_filename) {
         initrd_base = (cur_base + INITRD_LOAD_PAD) & ~INITRD_PAD_MASK;
-        initrd_size = load_image_targphys(params->initrd_filename, initrd_base,
+        initrd_size = load_image_targphys(args->initrd_filename, initrd_base,
                                           ram_size - initrd_base);
 
         if (initrd_size < 0) {
             fprintf(stderr, "qemu: could not load initial ram disk '%s'\n",
-                    params->initrd_filename);
+                    args->initrd_filename);
             exit(1);
         }
 
@@ -741,12 +742,12 @@ void ppce500_init(PPCE500Params *params)
     }
 
     /* If we're loading a kernel directly, we must load the device tree too. */
-    if (params->kernel_filename) {
+    if (args->kernel_filename) {
         struct boot_info *boot_info;
         int dt_size;
 
-        dt_size = ppce500_load_device_tree(env, params, dt_base, initrd_base,
-                                           initrd_size);
+        dt_size = ppce500_load_device_tree(env, args, params, dt_base,
+                                           initrd_base, initrd_size);
         if (dt_size < 0) {
             fprintf(stderr, "couldn't load device tree\n");
             exit(1);

hw/ppc/e500.h

@@ -1,25 +1,18 @@
 #ifndef PPCE500_H
 #define PPCE500_H
 
+#include "hw/boards.h"
+
 typedef struct PPCE500Params {
-    /* Standard QEMU machine init params */
-    ram_addr_t ram_size;
-    const char *boot_device;
-    const char *kernel_filename;
-    const char *kernel_cmdline;
-    const char *initrd_filename;
-    const char *cpu_model;
     int pci_first_slot;
     int pci_nr_slots;
 
-    /* e500-specific params */
-
     /* required -- must at least add toplevel board compatible */
     void (*fixup_devtree)(struct PPCE500Params *params, void *fdt);
 
     int mpic_version;
 } PPCE500Params;
 
-void ppce500_init(PPCE500Params *params);
+void ppce500_init(QEMUMachineInitArgs *args, PPCE500Params *params);
 
 #endif

hw/ppc/e500plat.c

@@ -30,19 +30,7 @@ static void e500plat_fixup_devtree(PPCE500Params *params, void *fdt)
 
 static void e500plat_init(QEMUMachineInitArgs *args)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *boot_device = args->boot_device;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
     PPCE500Params params = {
-        .ram_size = ram_size,
-        .boot_device = boot_device,
-        .kernel_filename = kernel_filename,
-        .kernel_cmdline = kernel_cmdline,
-        .initrd_filename = initrd_filename,
-        .cpu_model = cpu_model,
         .pci_first_slot = 0x1,
         .pci_nr_slots = PCI_SLOT_MAX - 1,
         .fixup_devtree = e500plat_fixup_devtree,
@@ -55,7 +43,7 @@ static void e500plat_init(QEMUMachineInitArgs *args)
         params.mpic_version = OPENPIC_MODEL_FSL_MPIC_20;
     }
 
-    ppce500_init(&params);
+    ppce500_init(args, &params);
 }
 
 static QEMUMachine e500plat_machine = {
@@ -63,7 +51,6 @@ static QEMUMachine e500plat_machine = {
     .desc = "generic paravirt e500 platform",
     .init = e500plat_init,
     .max_cpus = 32,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void e500plat_machine_init(void)

hw/ppc/mac_newworld.c

@@ -147,7 +147,7 @@ static void ppc_core99_init(QEMUMachineInitArgs *args)
     const char *kernel_filename = args->kernel_filename;
     const char *kernel_cmdline = args->kernel_cmdline;
     const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
+    const char *boot_device = args->boot_order;
     PowerPCCPU *cpu = NULL;
     CPUPPCState *env = NULL;
     char *filename;
@@ -477,7 +477,7 @@ static QEMUMachine core99_machine = {
     .desc = "Mac99 based PowerMAC",
     .init = ppc_core99_init,
     .max_cpus = MAX_CPUS,
-    DEFAULT_MACHINE_OPTIONS,
+    .default_boot_order = "cd",
 };
 
 static void core99_machine_init(void)

hw/ppc/mac_oldworld.c

@@ -78,7 +78,7 @@ static void ppc_heathrow_init(QEMUMachineInitArgs *args)
     const char *kernel_filename = args->kernel_filename;
     const char *kernel_cmdline = args->kernel_cmdline;
     const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
+    const char *boot_device = args->boot_order;
     MemoryRegion *sysmem = get_system_memory();
     PowerPCCPU *cpu = NULL;
     CPUPPCState *env = NULL;
@@ -350,7 +350,7 @@ static QEMUMachine heathrow_machine = {
 #ifndef TARGET_PPC64
     .is_default = 1,
 #endif
-    DEFAULT_MACHINE_OPTIONS,
+    .default_boot_order = "cd", /* TOFIX "cad" when Mac floppy is implemented */
 };
 
 static void heathrow_machine_init(void)

hw/ppc/mpc8544ds.c

@@ -28,26 +28,14 @@ static void mpc8544ds_fixup_devtree(PPCE500Params *params, void *fdt)
 
 static void mpc8544ds_init(QEMUMachineInitArgs *args)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *boot_device = args->boot_device;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
     PPCE500Params params = {
-        .ram_size = ram_size,
-        .boot_device = boot_device,
-        .kernel_filename = kernel_filename,
-        .kernel_cmdline = kernel_cmdline,
-        .initrd_filename = initrd_filename,
-        .cpu_model = cpu_model,
         .pci_first_slot = 0x11,
         .pci_nr_slots = 2,
         .fixup_devtree = mpc8544ds_fixup_devtree,
         .mpic_version = OPENPIC_MODEL_FSL_MPIC_20,
     };
 
-    ppce500_init(&params);
+    ppce500_init(args, &params);
 }
 
 
@@ -56,7 +44,6 @@ static QEMUMachine ppce500_machine = {
     .desc = "mpc8544ds",
     .init = mpc8544ds_init,
     .max_cpus = 15,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void ppce500_machine_init(void)

hw/ppc/ppc405_boards.c

@@ -362,7 +362,6 @@ static QEMUMachine ref405ep_machine = {
     .name = "ref405ep",
     .desc = "ref405ep",
     .init = ref405ep_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 /*****************************************************************************/
@@ -650,7 +649,6 @@ static QEMUMachine taihu_machine = {
     .name = "taihu",
     .desc = "taihu",
     .init = taihu_405ep_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void ppc405_machine_init(void)

hw/ppc/ppc440_bamboo.c

@@ -296,7 +296,6 @@ static QEMUMachine bamboo_machine = {
     .name = "bamboo",
     .desc = "bamboo",
     .init = bamboo_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void bamboo_machine_init(void)

hw/ppc/prep.c

@@ -452,7 +452,7 @@ static void ppc_prep_init(QEMUMachineInitArgs *args)
     const char *kernel_filename = args->kernel_filename;
     const char *kernel_cmdline = args->kernel_cmdline;
     const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
+    const char *boot_device = args->boot_order;
     MemoryRegion *sysmem = get_system_memory();
     PowerPCCPU *cpu = NULL;
     CPUPPCState *env = NULL;
@@ -691,7 +691,7 @@ static QEMUMachine prep_machine = {
     .desc = "PowerPC PREP platform",
     .init = ppc_prep_init,
     .max_cpus = MAX_CPUS,
-    DEFAULT_MACHINE_OPTIONS,
+    .default_boot_order = "cad",
 };
 
 static void prep_machine_init(void)

hw/ppc/spapr.c

@@ -1071,7 +1071,7 @@ static void ppc_spapr_init(QEMUMachineInitArgs *args)
     const char *kernel_filename = args->kernel_filename;
     const char *kernel_cmdline = args->kernel_cmdline;
     const char *initrd_filename = args->initrd_filename;
-    const char *boot_device = args->boot_device;
+    const char *boot_device = args->boot_order;
     PowerPCCPU *cpu;
     CPUPPCState *env;
     PCIHostState *phb;
@@ -1325,7 +1325,7 @@ static QEMUMachine spapr_machine = {
     .block_default_type = IF_SCSI,
     .max_cpus = MAX_CPUS,
     .no_parallel = 1,
-    .boot_order = NULL,
+    .default_boot_order = NULL,
 };
 
 static void spapr_machine_init(void)

hw/ppc/virtex_ml507.c

@@ -245,7 +245,6 @@ static QEMUMachine virtex_machine = {
     .name = "virtex-ml507",
     .desc = "Xilinx Virtex ML507 reference design",
     .init = virtex_init,
-    DEFAULT_MACHINE_OPTIONS,
 };
 
 static void virtex_machine_init(void)