Update version for 2.3.1 release

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 9172f428af)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>

.gitignore

@@ -37,14 +37,8 @@
 /qemu-tech.html
 /qemu-doc.info
 /qemu-tech.info
-/qemu.1
-/qemu.pod
-/qemu-img.1
-/qemu-img.pod
 /qemu-img
 /qemu-nbd
-/qemu-nbd.8
-/qemu-nbd.pod
 /qemu-options.def
 /qemu-options.texi
 /qemu-img-cmds.texi
@@ -56,8 +50,7 @@
 /qmp-commands.txt
 /vscclient
 /fsdev/virtfs-proxy-helper
-/fsdev/virtfs-proxy-helper.1
-/fsdev/virtfs-proxy-helper.pod
+*.[1-9]
 *.a
 *.aux
 *.cp
@@ -70,6 +63,7 @@
 *.ky
 *.log
 *.pdf
+*.pod
 *.cps
 *.fns
 *.kys

VERSION

@@ -1 +1 @@
-2.2.92
+2.3.1

async.c

@@ -72,12 +72,13 @@ int aio_bh_poll(AioContext *ctx)
         /* Make sure that fetching bh happens before accessing its members */
         smp_read_barrier_depends();
         next = bh->next;
-        if (!bh->deleted && bh->scheduled) {
-            bh->scheduled = 0;
-            /* Paired with write barrier in bh schedule to ensure reading for
-             * idle & callbacks coming after bh's scheduling.
-             */
-            smp_rmb();
+        /* The atomic_xchg is paired with the one in qemu_bh_schedule.  The
+         * implicit memory barrier ensures that the callback sees all writes
+         * done by the scheduling thread.  It also ensures that the scheduling
+         * thread sees the zero before bh->cb has run, and thus will call
+         * aio_notify again if necessary.
+         */
+        if (!bh->deleted && atomic_xchg(&bh->scheduled, 0)) {
             if (!bh->idle)
                 ret = 1;
             bh->idle = 0;
@@ -108,33 +109,28 @@ int aio_bh_poll(AioContext *ctx)
 
 void qemu_bh_schedule_idle(QEMUBH *bh)
 {
-    if (bh->scheduled)
-        return;
     bh->idle = 1;
     /* Make sure that idle & any writes needed by the callback are done
      * before the locations are read in the aio_bh_poll.
      */
-    smp_wmb();
-    bh->scheduled = 1;
+    atomic_mb_set(&bh->scheduled, 1);
 }
 
 void qemu_bh_schedule(QEMUBH *bh)
 {
     AioContext *ctx;
 
-    if (bh->scheduled)
-        return;
     ctx = bh->ctx;
     bh->idle = 0;
-    /* Make sure that:
+    /* The memory barrier implicit in atomic_xchg makes sure that:
      * 1. idle & any writes needed by the callback are done before the
      *    locations are read in the aio_bh_poll.
      * 2. ctx is loaded before scheduled is set and the callback has a chance
      *    to execute.
      */
-    smp_mb();
-    bh->scheduled = 1;
-    aio_notify(ctx);
+    if (atomic_xchg(&bh->scheduled, 1) == 0) {
+        aio_notify(ctx);
+    }
 }
 
 

block.c

@@ -99,8 +99,6 @@ static QLIST_HEAD(, BlockDriver) bdrv_drivers =
 
 static void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
                            int nr_sectors);
-static void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
-                             int nr_sectors);
 /* If non-zero, use only whitelisted block drivers */
 static int use_bdrv_whitelist;
 
@@ -1382,7 +1380,7 @@ int bdrv_append_temp_snapshot(BlockDriverState *bs, int flags, Error **errp)
     QemuOpts *opts = NULL;
     QDict *snapshot_options;
     BlockDriverState *bs_snapshot;
-    Error *local_err;
+    Error *local_err = NULL;
     int ret;
 
     /* if snapshot, we create a temporary backing file and open it
@@ -3118,19 +3116,6 @@ out:
     return ret;
 }
 
-static inline uint64_t bdrv_get_align(BlockDriverState *bs)
-{
-    /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
-    return MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
-}
-
-static inline bool bdrv_req_is_aligned(BlockDriverState *bs,
-                                       int64_t offset, size_t bytes)
-{
-    int64_t align = bdrv_get_align(bs);
-    return !(offset & (align - 1) || (bytes & (align - 1)));
-}
-
 /*
  * Handle a read request in coroutine context
  */
@@ -3141,7 +3126,8 @@ static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
     BlockDriver *drv = bs->drv;
     BdrvTrackedRequest req;
 
-    uint64_t align = bdrv_get_align(bs);
+    /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
+    uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
     uint8_t *head_buf = NULL;
     uint8_t *tail_buf = NULL;
     QEMUIOVector local_qiov;
@@ -3375,6 +3361,94 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
     return ret;
 }
 
+static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
+                                                int64_t offset,
+                                                unsigned int bytes,
+                                                BdrvRequestFlags flags,
+                                                BdrvTrackedRequest *req)
+{
+    uint8_t *buf = NULL;
+    QEMUIOVector local_qiov;
+    struct iovec iov;
+    uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
+    unsigned int head_padding_bytes, tail_padding_bytes;
+    int ret = 0;
+
+    head_padding_bytes = offset & (align - 1);
+    tail_padding_bytes = align - ((offset + bytes) & (align - 1));
+
+
+    assert(flags & BDRV_REQ_ZERO_WRITE);
+    if (head_padding_bytes || tail_padding_bytes) {
+        buf = qemu_blockalign(bs, align);
+        iov = (struct iovec) {
+            .iov_base   = buf,
+            .iov_len    = align,
+        };
+        qemu_iovec_init_external(&local_qiov, &iov, 1);
+    }
+    if (head_padding_bytes) {
+        uint64_t zero_bytes = MIN(bytes, align - head_padding_bytes);
+
+        /* RMW the unaligned part before head. */
+        mark_request_serialising(req, align);
+        wait_serialising_requests(req);
+        BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_HEAD);
+        ret = bdrv_aligned_preadv(bs, req, offset & ~(align - 1), align,
+                                  align, &local_qiov, 0);
+        if (ret < 0) {
+            goto fail;
+        }
+        BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD);
+
+        memset(buf + head_padding_bytes, 0, zero_bytes);
+        ret = bdrv_aligned_pwritev(bs, req, offset & ~(align - 1), align,
+                                   &local_qiov,
+                                   flags & ~BDRV_REQ_ZERO_WRITE);
+        if (ret < 0) {
+            goto fail;
+        }
+        offset += zero_bytes;
+        bytes -= zero_bytes;
+    }
+
+    assert(!bytes || (offset & (align - 1)) == 0);
+    if (bytes >= align) {
+        /* Write the aligned part in the middle. */
+        uint64_t aligned_bytes = bytes & ~(align - 1);
+        ret = bdrv_aligned_pwritev(bs, req, offset, aligned_bytes,
+                                   NULL, flags);
+        if (ret < 0) {
+            goto fail;
+        }
+        bytes -= aligned_bytes;
+        offset += aligned_bytes;
+    }
+
+    assert(!bytes || (offset & (align - 1)) == 0);
+    if (bytes) {
+        assert(align == tail_padding_bytes + bytes);
+        /* RMW the unaligned part after tail. */
+        mark_request_serialising(req, align);
+        wait_serialising_requests(req);
+        BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_TAIL);
+        ret = bdrv_aligned_preadv(bs, req, offset, align,
+                                  align, &local_qiov, 0);
+        if (ret < 0) {
+            goto fail;
+        }
+        BLKDBG_EVENT(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
+
+        memset(buf, 0, bytes);
+        ret = bdrv_aligned_pwritev(bs, req, offset, align,
+                                   &local_qiov, flags & ~BDRV_REQ_ZERO_WRITE);
+    }
+fail:
+    qemu_vfree(buf);
+    return ret;
+
+}
+
 /*
  * Handle a write request in coroutine context
  */
@@ -3383,7 +3457,8 @@ static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
     BdrvRequestFlags flags)
 {
     BdrvTrackedRequest req;
-    uint64_t align = bdrv_get_align(bs);
+    /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
+    uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
     uint8_t *head_buf = NULL;
     uint8_t *tail_buf = NULL;
     QEMUIOVector local_qiov;
@@ -3414,6 +3489,11 @@ static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
      */
     tracked_request_begin(&req, bs, offset, bytes, true);
 
+    if (!qiov) {
+        ret = bdrv_co_do_zero_pwritev(bs, offset, bytes, flags, &req);
+        goto out;
+    }
+
     if (offset & (align - 1)) {
         QEMUIOVector head_qiov;
         struct iovec head_iov;
@@ -3482,23 +3562,19 @@ static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
         bytes = ROUND_UP(bytes, align);
     }
 
-    if (use_local_qiov) {
-        /* Local buffer may have non-zero data. */
-        flags &= ~BDRV_REQ_ZERO_WRITE;
-    }
     ret = bdrv_aligned_pwritev(bs, &req, offset, bytes,
                                use_local_qiov ? &local_qiov : qiov,
                                flags);
 
 fail:
-    tracked_request_end(&req);
 
     if (use_local_qiov) {
         qemu_iovec_destroy(&local_qiov);
     }
     qemu_vfree(head_buf);
     qemu_vfree(tail_buf);
-
+out:
+    tracked_request_end(&req);
     return ret;
 }
 
@@ -3526,32 +3602,14 @@ int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors,
                                       BdrvRequestFlags flags)
 {
-    int ret;
-
     trace_bdrv_co_write_zeroes(bs, sector_num, nb_sectors, flags);
 
     if (!(bs->open_flags & BDRV_O_UNMAP)) {
         flags &= ~BDRV_REQ_MAY_UNMAP;
     }
-    if (bdrv_req_is_aligned(bs, sector_num << BDRV_SECTOR_BITS,
-                            nb_sectors << BDRV_SECTOR_BITS)) {
-        ret = bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
-                                BDRV_REQ_ZERO_WRITE | flags);
-    } else {
-        uint8_t *buf;
-        QEMUIOVector local_qiov;
-        size_t bytes = nb_sectors << BDRV_SECTOR_BITS;
 
-        buf = qemu_memalign(bdrv_opt_mem_align(bs), bytes);
-        memset(buf, 0, bytes);
-        qemu_iovec_init(&local_qiov, 1);
-        qemu_iovec_add(&local_qiov, buf, bytes);
-
-        ret = bdrv_co_do_writev(bs, sector_num, nb_sectors, &local_qiov,
-                                BDRV_REQ_ZERO_WRITE | flags);
-        qemu_vfree(buf);
-    }
-    return ret;
+    return bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
+                             BDRV_REQ_ZERO_WRITE | flags);
 }
 
 /**
@@ -4142,28 +4200,54 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
     return ret;
 }
 
-/* Coroutine wrapper for bdrv_get_block_status() */
-static void coroutine_fn bdrv_get_block_status_co_entry(void *opaque)
+static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs,
+        BlockDriverState *base,
+        int64_t sector_num,
+        int nb_sectors,
+        int *pnum)
+{
+    BlockDriverState *p;
+    int64_t ret = 0;
+
+    assert(bs != base);
+    for (p = bs; p != base; p = p->backing_hd) {
+        ret = bdrv_co_get_block_status(p, sector_num, nb_sectors, pnum);
+        if (ret < 0 || ret & BDRV_BLOCK_ALLOCATED) {
+            break;
+        }
+        /* [sector_num, pnum] unallocated on this layer, which could be only
+         * the first part of [sector_num, nb_sectors].  */
+        nb_sectors = MIN(nb_sectors, *pnum);
+    }
+    return ret;
+}
+
+/* Coroutine wrapper for bdrv_get_block_status_above() */
+static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque)
 {
     BdrvCoGetBlockStatusData *data = opaque;
-    BlockDriverState *bs = data->bs;
 
-    data->ret = bdrv_co_get_block_status(bs, data->sector_num, data->nb_sectors,
-                                         data->pnum);
+    data->ret = bdrv_co_get_block_status_above(data->bs, data->base,
+                                               data->sector_num,
+                                               data->nb_sectors,
+                                               data->pnum);
     data->done = true;
 }
 
 /*
- * Synchronous wrapper around bdrv_co_get_block_status().
+ * Synchronous wrapper around bdrv_co_get_block_status_above().
  *
- * See bdrv_co_get_block_status() for details.
+ * See bdrv_co_get_block_status_above() for details.
  */
-int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num,
-                              int nb_sectors, int *pnum)
+int64_t bdrv_get_block_status_above(BlockDriverState *bs,
+                                    BlockDriverState *base,
+                                    int64_t sector_num,
+                                    int nb_sectors, int *pnum)
 {
     Coroutine *co;
     BdrvCoGetBlockStatusData data = {
         .bs = bs,
+        .base = base,
         .sector_num = sector_num,
         .nb_sectors = nb_sectors,
         .pnum = pnum,
@@ -4172,11 +4256,11 @@ int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num,
 
     if (qemu_in_coroutine()) {
         /* Fast-path if already in coroutine context */
-        bdrv_get_block_status_co_entry(&data);
+        bdrv_get_block_status_above_co_entry(&data);
     } else {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
-        co = qemu_coroutine_create(bdrv_get_block_status_co_entry);
+        co = qemu_coroutine_create(bdrv_get_block_status_above_co_entry);
         qemu_coroutine_enter(co, &data);
         while (!data.done) {
             aio_poll(aio_context, true);
@@ -4185,6 +4269,14 @@ int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num,
     return data.ret;
 }
 
+int64_t bdrv_get_block_status(BlockDriverState *bs,
+                              int64_t sector_num,
+                              int nb_sectors, int *pnum)
+{
+    return bdrv_get_block_status_above(bs, bs->backing_hd,
+                                       sector_num, nb_sectors, pnum);
+}
+
 int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num,
                                    int nb_sectors, int *pnum)
 {
@@ -5205,8 +5297,6 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
         return -EROFS;
     }
 
-    bdrv_reset_dirty(bs, sector_num, nb_sectors);
-
     /* Do nothing if disabled.  */
     if (!(bs->open_flags & BDRV_O_UNMAP)) {
         return 0;
@@ -5216,6 +5306,8 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
         return 0;
     }
 
+    bdrv_set_dirty(bs, sector_num, nb_sectors);
+
     max_discard = MIN_NON_ZERO(bs->bl.max_discard, BDRV_REQUEST_MAX_SECTORS);
     while (nb_sectors > 0) {
         int ret;
@@ -5526,15 +5618,6 @@ static void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
     }
 }
 
-static void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
-                             int nr_sectors)
-{
-    BdrvDirtyBitmap *bitmap;
-    QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
-        hbitmap_reset(bitmap->bitmap, cur_sector, nr_sectors);
-    }
-}
-
 int64_t bdrv_get_dirty_count(BlockDriverState *bs, BdrvDirtyBitmap *bitmap)
 {
     return hbitmap_count(bitmap->bitmap);

block/iscsi.c

@@ -56,6 +56,7 @@ typedef struct IscsiLun {
     uint64_t num_blocks;
     int events;
     QEMUTimer *nop_timer;
+    QEMUTimer *event_timer;
     uint8_t lbpme;
     uint8_t lbprz;
     uint8_t has_write_same;
@@ -95,6 +96,7 @@ typedef struct IscsiAIOCB {
 #endif
 } IscsiAIOCB;
 
+#define EVENT_INTERVAL 250
 #define NOP_INTERVAL 5000
 #define MAX_NOP_FAILURES 3
 #define ISCSI_CMD_RETRIES ARRAY_SIZE(iscsi_retry_times)
@@ -256,21 +258,30 @@ static void
 iscsi_set_events(IscsiLun *iscsilun)
 {
     struct iscsi_context *iscsi = iscsilun->iscsi;
-    int ev;
+    int ev = iscsi_which_events(iscsi);
 
-    /* We always register a read handler.  */
-    ev = POLLIN;
-    ev |= iscsi_which_events(iscsi);
     if (ev != iscsilun->events) {
         aio_set_fd_handler(iscsilun->aio_context,
                            iscsi_get_fd(iscsi),
-                           iscsi_process_read,
+                           (ev & POLLIN) ? iscsi_process_read : NULL,
                            (ev & POLLOUT) ? iscsi_process_write : NULL,
                            iscsilun);
-
+        iscsilun->events = ev;
     }
 
-    iscsilun->events = ev;
+    /* newer versions of libiscsi may return zero events. In this
+     * case start a timer to ensure we are able to return to service
+     * once this situation changes. */
+    if (!ev) {
+        timer_mod(iscsilun->event_timer,
+                  qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + EVENT_INTERVAL);
+    }
+}
+
+static void iscsi_timed_set_events(void *opaque)
+{
+    IscsiLun *iscsilun = opaque;
+    iscsi_set_events(iscsilun);
 }
 
 static void
@@ -1214,6 +1225,11 @@ static void iscsi_detach_aio_context(BlockDriverState *bs)
         timer_free(iscsilun->nop_timer);
         iscsilun->nop_timer = NULL;
     }
+    if (iscsilun->event_timer) {
+        timer_del(iscsilun->event_timer);
+        timer_free(iscsilun->event_timer);
+        iscsilun->event_timer = NULL;
+    }
 }
 
 static void iscsi_attach_aio_context(BlockDriverState *bs,
@@ -1230,6 +1246,11 @@ static void iscsi_attach_aio_context(BlockDriverState *bs,
                                         iscsi_nop_timed_event, iscsilun);
     timer_mod(iscsilun->nop_timer,
               qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
+
+    /* Prepare a timer for a delayed call to iscsi_set_events */
+    iscsilun->event_timer = aio_timer_new(iscsilun->aio_context,
+                                          QEMU_CLOCK_REALTIME, SCALE_MS,
+                                          iscsi_timed_set_events, iscsilun);
 }
 
 static bool iscsi_is_write_protected(IscsiLun *iscsilun)
@@ -1480,6 +1501,9 @@ out:
 
     if (ret) {
         if (iscsi != NULL) {
+            if (iscsi_is_logged_in(iscsi)) {
+                iscsi_logout_sync(iscsi);
+            }
             iscsi_destroy_context(iscsi);
         }
         memset(iscsilun, 0, sizeof(IscsiLun));
@@ -1493,6 +1517,9 @@ static void iscsi_close(BlockDriverState *bs)
     struct iscsi_context *iscsi = iscsilun->iscsi;
 
     iscsi_detach_aio_context(bs);
+    if (iscsi_is_logged_in(iscsi)) {
+        iscsi_logout_sync(iscsi);
+    }
     iscsi_destroy_context(iscsi);
     g_free(iscsilun->zeroblock);
     g_free(iscsilun->allocationmap);

block/mirror.c

@@ -57,6 +57,7 @@ typedef struct MirrorBlockJob {
     int in_flight;
     int sectors_in_flight;
     int ret;
+    bool unmap;
 } MirrorBlockJob;
 
 typedef struct MirrorOp {
@@ -167,6 +168,8 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
     int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
     uint64_t delay_ns = 0;
     MirrorOp *op;
+    int pnum;
+    int64_t ret;
 
     s->sector_num = hbitmap_iter_next(&s->hbi);
     if (s->sector_num < 0) {
@@ -295,8 +298,22 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
     s->in_flight++;
     s->sectors_in_flight += nb_sectors;
     trace_mirror_one_iteration(s, sector_num, nb_sectors);
-    bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
-                   mirror_read_complete, op);
+
+    ret = bdrv_get_block_status_above(source, NULL, sector_num,
+                                      nb_sectors, &pnum);
+    if (ret < 0 || pnum < nb_sectors ||
+            (ret & BDRV_BLOCK_DATA && !(ret & BDRV_BLOCK_ZERO))) {
+        bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
+                       mirror_read_complete, op);
+    } else if (ret & BDRV_BLOCK_ZERO) {
+        bdrv_aio_write_zeroes(s->target, sector_num, op->nb_sectors,
+                              s->unmap ? BDRV_REQ_MAY_UNMAP : 0,
+                              mirror_write_complete, op);
+    } else {
+        assert(!(ret & BDRV_BLOCK_DATA));
+        bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
+                         mirror_write_complete, op);
+    }
     return delay_ns;
 }
 
@@ -660,6 +677,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
                              int64_t buf_size,
                              BlockdevOnError on_source_error,
                              BlockdevOnError on_target_error,
+                             bool unmap,
                              BlockCompletionFunc *cb,
                              void *opaque, Error **errp,
                              const BlockJobDriver *driver,
@@ -702,6 +720,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
     s->base = base;
     s->granularity = granularity;
     s->buf_size = MAX(buf_size, granularity);
+    s->unmap = unmap;
 
     s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, errp);
     if (!s->dirty_bitmap) {
@@ -720,6 +739,7 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                   int64_t speed, int64_t granularity, int64_t buf_size,
                   MirrorSyncMode mode, BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
+                  bool unmap,
                   BlockCompletionFunc *cb,
                   void *opaque, Error **errp)
 {
@@ -730,7 +750,7 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
     base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
     mirror_start_job(bs, target, replaces,
                      speed, granularity, buf_size,
-                     on_source_error, on_target_error, cb, opaque, errp,
+                     on_source_error, on_target_error, unmap, cb, opaque, errp,
                      &mirror_job_driver, is_none_mode, base);
 }
 
@@ -778,7 +798,7 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
 
     bdrv_ref(base);
     mirror_start_job(bs, base, NULL, speed, 0, 0,
-                     on_error, on_error, cb, opaque, &local_err,
+                     on_error, on_error, false, cb, opaque, &local_err,
                      &commit_active_job_driver, false, base);
     if (local_err) {
         error_propagate(errp, local_err);

block/nfs.c

@@ -35,6 +35,8 @@
 #include "sysemu/sysemu.h"
 #include <nfsc/libnfs.h>
 
+#define QEMU_NFS_MAX_READAHEAD_SIZE 1048576
+
 typedef struct NFSClient {
     struct nfs_context *context;
     struct nfsfh *fh;
@@ -327,6 +329,11 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
             nfs_set_tcp_syncnt(client->context, val);
 #ifdef LIBNFS_FEATURE_READAHEAD
         } else if (!strcmp(qp->p[i].name, "readahead")) {
+            if (val > QEMU_NFS_MAX_READAHEAD_SIZE) {
+                error_report("NFS Warning: Truncating NFS readahead"
+                             " size to %d", QEMU_NFS_MAX_READAHEAD_SIZE);
+                val = QEMU_NFS_MAX_READAHEAD_SIZE;
+            }
             nfs_set_readahead(client->context, val);
 #endif
         } else {

block/qcow2-refcount.c

@@ -833,6 +833,11 @@ static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size)
     uint64_t i, nb_clusters, refcount;
     int ret;
 
+    /* We can't allocate clusters if they may still be queued for discard. */
+    if (s->cache_discards) {
+        qcow2_process_discards(bs, 0);
+    }
+
     nb_clusters = size_to_clusters(s, size);
 retry:
     for(i = 0; i < nb_clusters; i++) {

block/qcow2.c

@@ -140,6 +140,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,
                 return 3;
             }
             bs->backing_format[ext.len] = '\0';
+            s->image_backing_format = g_strdup(bs->backing_format);
 #ifdef DEBUG_EXT
             printf("Qcow2: Got format extension %s\n", bs->backing_format);
 #endif
@@ -884,6 +885,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
         bs->backing_file[len] = '\0';
+        s->image_backing_file = g_strdup(bs->backing_file);
     }
 
     /* Internal snapshots */
@@ -1457,6 +1459,9 @@ static void qcow2_close(BlockDriverState *bs)
     g_free(s->unknown_header_fields);
     cleanup_unknown_header_ext(bs);
 
+    g_free(s->image_backing_file);
+    g_free(s->image_backing_format);
+
     g_free(s->cluster_cache);
     qemu_vfree(s->cluster_data);
     qcow2_refcount_close(bs);
@@ -1622,9 +1627,10 @@ int qcow2_update_header(BlockDriverState *bs)
     }
 
     /* Backing file format header extension */
-    if (*bs->backing_format) {
+    if (s->image_backing_format) {
         ret = header_ext_add(buf, QCOW2_EXT_MAGIC_BACKING_FORMAT,
-                             bs->backing_format, strlen(bs->backing_format),
+                             s->image_backing_format,
+                             strlen(s->image_backing_format),
                              buflen);
         if (ret < 0) {
             goto fail;
@@ -1682,8 +1688,8 @@ int qcow2_update_header(BlockDriverState *bs)
     buflen -= ret;
 
     /* Backing file name */
-    if (*bs->backing_file) {
-        size_t backing_file_len = strlen(bs->backing_file);
+    if (s->image_backing_file) {
+        size_t backing_file_len = strlen(s->image_backing_file);
 
         if (buflen < backing_file_len) {
             ret = -ENOSPC;
@@ -1691,7 +1697,7 @@ int qcow2_update_header(BlockDriverState *bs)
         }
 
         /* Using strncpy is ok here, since buf is not NUL-terminated. */
-        strncpy(buf, bs->backing_file, buflen);
+        strncpy(buf, s->image_backing_file, buflen);
 
         header->backing_file_offset = cpu_to_be64(buf - ((char*) header));
         header->backing_file_size   = cpu_to_be32(backing_file_len);
@@ -1712,9 +1718,17 @@ fail:
 static int qcow2_change_backing_file(BlockDriverState *bs,
     const char *backing_file, const char *backing_fmt)
 {
+    BDRVQcowState *s = bs->opaque;
+
     pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
     pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
 
+    g_free(s->image_backing_file);
+    g_free(s->image_backing_format);
+
+    s->image_backing_file = backing_file ? g_strdup(bs->backing_file) : NULL;
+    s->image_backing_format = backing_fmt ? g_strdup(bs->backing_format) : NULL;
+
     return qcow2_update_header(bs);
 }
 
@@ -2751,8 +2765,9 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
     }
 
     if (backing_file || backing_format) {
-        ret = qcow2_change_backing_file(bs, backing_file ?: bs->backing_file,
-                                        backing_format ?: bs->backing_format);
+        ret = qcow2_change_backing_file(bs,
+                    backing_file ?: s->image_backing_file,
+                    backing_format ?: s->image_backing_format);
         if (ret < 0) {
             return ret;
         }

block/qcow2.h

@@ -62,7 +62,8 @@
 #define MIN_CLUSTER_BITS 9
 #define MAX_CLUSTER_BITS 21
 
-#define MIN_L2_CACHE_SIZE 1 /* cluster */
+/* Must be at least 2 to cover COW */
+#define MIN_L2_CACHE_SIZE 2 /* clusters */
 
 /* Must be at least 4 to cover all cases of refcount table growth */
 #define MIN_REFCOUNT_CACHE_SIZE 4 /* clusters */
@@ -283,6 +284,12 @@ typedef struct BDRVQcowState {
     QLIST_HEAD(, Qcow2UnknownHeaderExtension) unknown_header_ext;
     QTAILQ_HEAD (, Qcow2DiscardRegion) discards;
     bool cache_discards;
+
+    /* Backing file path and format as stored in the image (this is not the
+     * effective path/format, which may be the result of a runtime option
+     * override) */
+    char *image_backing_file;
+    char *image_backing_format;
 } BDRVQcowState;
 
 struct QCowAIOCB;

block/vmdk.c

@@ -451,7 +451,8 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
                             Error **errp)
 {
     int ret;
-    int l1_size, i;
+    size_t l1_size;
+    int i;
 
     /* read the L1 table */
     l1_size = extent->l1_size * sizeof(uint32_t);
@@ -1247,6 +1248,17 @@ static VmdkExtent *find_extent(BDRVVmdkState *s,
     return NULL;
 }
 
+static inline uint64_t vmdk_find_index_in_cluster(VmdkExtent *extent,
+                                                  int64_t sector_num)
+{
+    uint64_t index_in_cluster, extent_begin_sector, extent_relative_sector_num;
+
+    extent_begin_sector = extent->end_sector - extent->sectors;
+    extent_relative_sector_num = sector_num - extent_begin_sector;
+    index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
+    return index_in_cluster;
+}
+
 static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -1284,7 +1296,7 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
         break;
     }
 
-    index_in_cluster = sector_num % extent->cluster_sectors;
+    index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
     n = extent->cluster_sectors - index_in_cluster;
     if (n > nb_sectors) {
         n = nb_sectors;
@@ -1302,6 +1314,8 @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
     uLongf buf_len;
     const uint8_t *write_buf = buf;
     int write_len = nb_sectors * 512;
+    int64_t write_offset;
+    int64_t write_end_sector;
 
     if (extent->compressed) {
         if (!extent->has_marker) {
@@ -1320,10 +1334,14 @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
         write_buf = (uint8_t *)data;
         write_len = buf_len + sizeof(VmdkGrainMarker);
     }
-    ret = bdrv_pwrite(extent->file,
-                        cluster_offset + offset_in_cluster,
-                        write_buf,
-                        write_len);
+    write_offset = cluster_offset + offset_in_cluster,
+    ret = bdrv_pwrite(extent->file, write_offset, write_buf, write_len);
+
+    write_end_sector = DIV_ROUND_UP(write_offset + write_len, BDRV_SECTOR_SIZE);
+
+    extent->next_cluster_sector = MAX(extent->next_cluster_sector,
+                                      write_end_sector);
+
     if (ret != write_len) {
         ret = ret < 0 ? ret : -EIO;
         goto out;
@@ -1406,7 +1424,6 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
     BDRVVmdkState *s = bs->opaque;
     int ret;
     uint64_t n, index_in_cluster;
-    uint64_t extent_begin_sector, extent_relative_sector_num;
     VmdkExtent *extent = NULL;
     uint64_t cluster_offset;
 
@@ -1418,9 +1435,7 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
         ret = get_cluster_offset(bs, extent, NULL,
                                  sector_num << 9, false, &cluster_offset,
                                  0, 0);
-        extent_begin_sector = extent->end_sector - extent->sectors;
-        extent_relative_sector_num = sector_num - extent_begin_sector;
-        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
+        index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
         n = extent->cluster_sectors - index_in_cluster;
         if (n > nb_sectors) {
             n = nb_sectors;
@@ -1482,7 +1497,6 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
     VmdkExtent *extent = NULL;
     int ret;
     int64_t index_in_cluster, n;
-    uint64_t extent_begin_sector, extent_relative_sector_num;
     uint64_t cluster_offset;
     VmdkMetaData m_data;
 
@@ -1498,9 +1512,7 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
         if (!extent) {
             return -EIO;
         }
-        extent_begin_sector = extent->end_sector - extent->sectors;
-        extent_relative_sector_num = sector_num - extent_begin_sector;
-        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
+        index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
         n = extent->cluster_sectors - index_in_cluster;
         if (n > nb_sectors) {
             n = nb_sectors;

block/vpc.c

@@ -168,6 +168,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     uint8_t buf[HEADER_SIZE];
     uint32_t checksum;
     uint64_t computed_size;
+    uint64_t pagetable_size;
     int disk_type = VHD_DYNAMIC;
     int ret;
 
@@ -269,7 +270,17 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
 
-        s->pagetable = qemu_try_blockalign(bs->file, s->max_table_entries * 4);
+        if (s->max_table_entries > SIZE_MAX / 4 ||
+            s->max_table_entries > (int) INT_MAX / 4) {
+            error_setg(errp, "Max Table Entries too large (%" PRId32 ")",
+                        s->max_table_entries);
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        pagetable_size = (uint64_t) s->max_table_entries * 4;
+
+        s->pagetable = qemu_try_blockalign(bs->file, pagetable_size);
         if (s->pagetable == NULL) {
             ret = -ENOMEM;
             goto fail;
@@ -277,14 +288,13 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
 
         s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
 
-        ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable,
-                         s->max_table_entries * 4);
+        ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable, pagetable_size);
         if (ret < 0) {
             goto fail;
         }
 
         s->free_data_block_offset =
-            (s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;
+            ROUND_UP(s->bat_offset + pagetable_size, 512);
 
         for (i = 0; i < s->max_table_entries; i++) {
             be32_to_cpus(&s->pagetable[i]);

blockdev.c

@@ -2461,6 +2461,7 @@ void qmp_drive_mirror(const char *device, const char *target,
                       bool has_buf_size, int64_t buf_size,
                       bool has_on_source_error, BlockdevOnError on_source_error,
                       bool has_on_target_error, BlockdevOnError on_target_error,
+                      bool has_unmap, bool unmap,
                       Error **errp)
 {
     BlockBackend *blk;
@@ -2492,6 +2493,9 @@ void qmp_drive_mirror(const char *device, const char *target,
     if (!has_buf_size) {
         buf_size = DEFAULT_MIRROR_BUF_SIZE;
     }
+    if (!has_unmap) {
+        unmap = true;
+    }
 
     if (granularity != 0 && (granularity < 512 || granularity > 1048576 * 64)) {
         error_set(errp, QERR_INVALID_PARAMETER_VALUE, "granularity",
@@ -2631,6 +2635,7 @@ void qmp_drive_mirror(const char *device, const char *target,
                  has_replaces ? replaces : NULL,
                  speed, granularity, buf_size, sync,
                  on_source_error, on_target_error,
+                 unmap,
                  block_job_cb, bs, &local_err);
     if (local_err != NULL) {
         bdrv_unref(target_bs);

configure

@@ -327,7 +327,7 @@ seccomp=""
 glusterfs=""
 glusterfs_discard="no"
 glusterfs_zerofill="no"
-archipelago=""
+archipelago="no"
 gtk=""
 gtkabi=""
 vte=""
@@ -1848,19 +1848,14 @@ fi
 # libseccomp check
 
 if test "$seccomp" != "no" ; then
-    if $pkg_config --atleast-version=2.2.0 libseccomp ||
-        (test "$cpu" = "i386" || test "$cpu" = "x86_64" &&
-        $pkg_config --atleast-version=2.1.1 libseccomp); then
+    if test "$cpu" = "i386" || test "$cpu" = "x86_64" &&
+        $pkg_config --atleast-version=2.1.1 libseccomp; then
         libs_softmmu="$libs_softmmu `$pkg_config --libs libseccomp`"
         QEMU_CFLAGS="$QEMU_CFLAGS `$pkg_config --cflags libseccomp`"
 	seccomp="yes"
     else
 	if test "$seccomp" = "yes"; then
-        if test "$cpu" = "i386" || test "$cpu" = "x86_64"; then
             feature_not_found "libseccomp" "Install libseccomp devel >= 2.1.1"
-        else
-            feature_not_found "libseccomp" "Install libseccomp devel >= 2.2.0"
-        fi
 	fi
 	seccomp="no"
     fi
@@ -3173,6 +3168,12 @@ EOF
         archipelago="yes"
         libs_tools="$archipelago_libs $libs_tools"
         libs_softmmu="$archipelago_libs $libs_softmmu"
+
+	echo "WARNING: Please check the licenses of QEMU and libxseg carefully."
+	echo "GPLv3 versions of libxseg may not be compatible with QEMU's"
+	echo "license and therefore prevent redistribution."
+	echo
+	echo "To disable Archipelago, use --disable-archipelago"
     else
       if test "$archipelago" = "yes" ; then
         feature_not_found "Archipelago backend support" "Install libxseg devel"

docs/specs/fw_cfg.txt

@@ -0,0 +1,205 @@
+QEMU Firmware Configuration (fw_cfg) Device
+===========================================
+
+= Guest-side Hardware Interface =
+
+This hardware interface allows the guest to retrieve various data items
+(blobs) that can influence how the firmware configures itself, or may
+contain tables to be installed for the guest OS. Examples include device
+boot order, ACPI and SMBIOS tables, virtual machine UUID, SMP and NUMA
+information, kernel/initrd images for direct (Linux) kernel booting, etc.
+
+== Selector (Control) Register ==
+
+* Write only
+* Location: platform dependent (IOport or MMIO)
+* Width: 16-bit
+* Endianness: little-endian (if IOport), or big-endian (if MMIO)
+
+A write to this register sets the index of a firmware configuration
+item which can subsequently be accessed via the data register.
+
+Setting the selector register will cause the data offset to be set
+to zero. The data offset impacts which data is accessed via the data
+register, and is explained below.
+
+Bit14 of the selector register indicates whether the configuration
+setting is being written. A value of 0 means the item is only being
+read, and all write access to the data port will be ignored. A value
+of 1 means the item's data can be overwritten by writes to the data
+register. In other words, configuration write mode is enabled when
+the selector value is between 0x4000-0x7fff or 0xc000-0xffff.
+
+NOTE: As of QEMU v2.4, writes to the fw_cfg data register are no
+      longer supported, and will be ignored (treated as no-ops)!
+
+Bit15 of the selector register indicates whether the configuration
+setting is architecture specific. A value of 0 means the item is a
+generic configuration item. A value of 1 means the item is specific
+to a particular architecture. In other words, generic configuration
+items are accessed with a selector value between 0x0000-0x7fff, and
+architecture specific configuration items are accessed with a selector
+value between 0x8000-0xffff.
+
+== Data Register ==
+
+* Read/Write (writes ignored as of QEMU v2.4)
+* Location: platform dependent (IOport [*] or MMIO)
+* Width: 8-bit (if IOport), 8/16/32/64-bit (if MMIO)
+* Endianness: string-preserving
+
+[*] On platforms where the data register is exposed as an IOport, its
+port number will always be one greater than the port number of the
+selector register. In other words, the two ports overlap, and can not
+be mapped separately.
+
+The data register allows access to an array of bytes for each firmware
+configuration data item. The specific item is selected by writing to
+the selector register, as described above.
+
+Initially following a write to the selector register, the data offset
+will be set to zero. Each successful access to the data register will
+increment the data offset by the appropriate access width.
+
+Each firmware configuration item has a maximum length of data
+associated with the item. After the data offset has passed the
+end of this maximum data length, then any reads will return a data
+value of 0x00, and all writes will be ignored.
+
+An N-byte wide read of the data register will return the next available
+N bytes of the selected firmware configuration item, as a substring, in
+increasing address order, similar to memcpy().
+
+== Register Locations ==
+
+=== x86, x86_64 Register Locations ===
+
+Selector Register IOport: 0x510
+Data Register IOport:     0x511
+
+== Firmware Configuration Items ==
+
+=== Signature (Key 0x0000, FW_CFG_SIGNATURE) ===
+
+The presence of the fw_cfg selector and data registers can be verified
+by selecting the "signature" item using key 0x0000 (FW_CFG_SIGNATURE),
+and reading four bytes from the data register. If the fw_cfg device is
+present, the four bytes read will contain the characters "QEMU".
+
+=== Revision (Key 0x0001, FW_CFG_ID) ===
+
+A 32-bit little-endian unsigned int, this item is used as an interface
+revision number, and is currently set to 1 by QEMU when fw_cfg is
+initialized.
+
+=== File Directory (Key 0x0019, FW_CFG_FILE_DIR) ===
+
+Firmware configuration items stored at selector keys 0x0020 or higher
+(FW_CFG_FILE_FIRST or higher) have an associated entry in a directory
+structure, which makes it easier for guest-side firmware to identify
+and retrieve them. The format of this file directory (from fw_cfg.h in
+the QEMU source tree) is shown here, slightly annotated for clarity:
+
+struct FWCfgFiles {		/* the entire file directory fw_cfg item */
+    uint32_t count;		/* number of entries, in big-endian format */
+    struct FWCfgFile f[];	/* array of file entries, see below */
+};
+
+struct FWCfgFile {		/* an individual file entry, 64 bytes total */
+    uint32_t size;		/* size of referenced fw_cfg item, big-endian */
+    uint16_t select;		/* selector key of fw_cfg item, big-endian */
+    uint16_t reserved;
+    char name[56];		/* fw_cfg item name, NUL-terminated ascii */
+};
+
+=== All Other Data Items ===
+
+Please consult the QEMU source for the most up-to-date and authoritative
+list of selector keys and their respective items' purpose and format.
+
+=== Ranges ===
+
+Theoretically, there may be up to 0x4000 generic firmware configuration
+items, and up to 0x4000 architecturally specific ones.
+
+Selector Reg.    Range Usage
+---------------  -----------
+0x0000 - 0x3fff  Generic (0x0000 - 0x3fff, RO)
+0x4000 - 0x7fff  Generic (0x0000 - 0x3fff, RW, ignored in QEMU v2.4+)
+0x8000 - 0xbfff  Arch. Specific (0x0000 - 0x3fff, RO)
+0xc000 - 0xffff  Arch. Specific (0x0000 - 0x3fff, RW, ignored in v2.4+)
+
+In practice, the number of allowed firmware configuration items is given
+by the value of FW_CFG_MAX_ENTRY (see fw_cfg.h).
+
+= Host-side API =
+
+The following functions are available to the QEMU programmer for adding
+data to a fw_cfg device during guest initialization (see fw_cfg.h for
+each function's complete prototype):
+
+== fw_cfg_add_bytes() ==
+
+Given a selector key value, starting pointer, and size, create an item
+as a raw "blob" of the given size, available by selecting the given key.
+The data referenced by the starting pointer is only linked, NOT copied,
+into the data structure of the fw_cfg device.
+
+== fw_cfg_add_string() ==
+
+Instead of a starting pointer and size, this function accepts a pointer
+to a NUL-terminated ascii string, and inserts a newly allocated copy of
+the string (including the NUL terminator) into the fw_cfg device data
+structure.
+
+== fw_cfg_add_iXX() ==
+
+Insert an XX-bit item, where XX may be 16, 32, or 64. These functions
+will convert a 16-, 32-, or 64-bit integer to little-endian, then add
+a dynamically allocated copy of the appropriately sized item to fw_cfg
+under the given selector key value.
+
+== fw_cfg_add_file() ==
+
+Given a filename (i.e., fw_cfg item name), starting pointer, and size,
+create an item as a raw "blob" of the given size. Unlike fw_cfg_add_bytes()
+above, the next available selector key (above 0x0020, FW_CFG_FILE_FIRST)
+will be used, and a new entry will be added to the file directory structure
+(at key 0x0019), containing the item name, blob size, and automatically
+assigned selector key value. The data referenced by the starting pointer
+is only linked, NOT copied, into the fw_cfg data structure.
+
+== fw_cfg_add_file_callback() ==
+
+Like fw_cfg_add_file(), but additionally sets pointers to a callback
+function (and opaque argument), which will be executed host-side by
+QEMU each time a byte is read by the guest from this particular item.
+
+NOTE: The callback function is given the opaque argument set by
+fw_cfg_add_file_callback(), but also the current data offset,
+allowing it the option of only acting upon specific offset values
+(e.g., 0, before the first data byte of the selected item is
+returned to the guest).
+
+== fw_cfg_modify_file() ==
+
+Given a filename (i.e., fw_cfg item name), starting pointer, and size,
+completely replace the configuration item referenced by the given item
+name with the new given blob. If an existing blob is found, its
+callback information is removed, and a pointer to the old data is
+returned to allow the caller to free it, helping avoid memory leaks.
+If a configuration item does not already exist under the given item
+name, a new item will be created as with fw_cfg_add_file(), and NULL
+is returned to the caller. In any case, the data referenced by the
+starting pointer is only linked, NOT copied, into the fw_cfg data
+structure.
+
+== fw_cfg_add_callback() ==
+
+Like fw_cfg_add_bytes(), but additionally sets pointers to a callback
+function (and opaque argument), which will be executed host-side by
+QEMU each time a guest-side write operation to this particular item
+completes fully overwriting the item's data.
+
+NOTE: This function is deprecated, and will be completely removed
+starting with QEMU v2.4.

hmp.c

@@ -391,7 +391,8 @@ static void print_block_info(Monitor *mon, BlockInfo *info,
                         inserted->iops_size);
     }
 
-    if (verbose) {
+    /* TODO: inserted->image should never be null */
+    if (verbose && inserted->image) {
         monitor_printf(mon, "\nImages:\n");
         image_info = inserted->image;
         while (1) {
@@ -1033,7 +1034,7 @@ void hmp_drive_mirror(Monitor *mon, const QDict *qdict)
                      false, NULL, false, NULL,
                      full ? MIRROR_SYNC_MODE_FULL : MIRROR_SYNC_MODE_TOP,
                      true, mode, false, 0, false, 0, false, 0,
-                     false, 0, false, 0, &err);
+                     false, 0, false, 0, false, true, &err);
     hmp_handle_error(mon, &err);
 }
 

hw/acpi/aml-build.c

@@ -304,6 +304,7 @@ static void aml_free(gpointer data, gpointer user_data)
 {
     Aml *var = data;
     build_free_array(var->buf);
+    g_free(var);
 }
 
 Aml *init_aml_allocator(void)

hw/alpha/typhoon.c

@@ -844,9 +844,8 @@ PCIBus *typhoon_init(ram_addr_t ram_size, ISABus **isa_bus,
 
     /* Main memory region, 0x00.0000.0000.  Real hardware supports 32GB,
        but the address space hole reserved at this point is 8TB.  */
-    memory_region_init_ram(&s->ram_region, OBJECT(s), "ram", ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(&s->ram_region);
+    memory_region_allocate_system_memory(&s->ram_region, OBJECT(s), "ram",
+                                         ram_size);
     memory_region_add_subregion(addr_space, 0, &s->ram_region);
 
     /* TIGbus, 0x801.0000.0000, 1GB.  */

hw/arm/cubieboard.c

@@ -63,9 +63,8 @@ static void cubieboard_init(MachineState *machine)
         exit(1);
     }
 
-    memory_region_init_ram(&s->sdram, NULL, "cubieboard.ram",
-                           machine->ram_size, &error_abort);
-    vmstate_register_ram_global(&s->sdram);
+    memory_region_allocate_system_memory(&s->sdram, NULL, "cubieboard.ram",
+                                         machine->ram_size);
     memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE,
                                 &s->sdram);
 

hw/arm/digic_boards.c

@@ -51,9 +51,8 @@ typedef struct DigicBoard {
 
 static void digic4_board_setup_ram(DigicBoardState *s, hwaddr ram_size)
 {
-    memory_region_init_ram(&s->ram, NULL, "ram", ram_size, &error_abort);
+    memory_region_allocate_system_memory(&s->ram, NULL, "ram", ram_size);
     memory_region_add_subregion(get_system_memory(), 0, &s->ram);
-    vmstate_register_ram_global(&s->ram);
 }
 
 static void digic4_board_init(DigicBoard *board)

hw/arm/highbank.c

@@ -267,7 +267,7 @@ static void calxeda_init(MachineState *machine, enum cxmachines machine_id)
 
     sysmem = get_system_memory();
     dram = g_new(MemoryRegion, 1);
-    memory_region_init_ram(dram, NULL, "highbank.dram", ram_size, &error_abort);
+    memory_region_allocate_system_memory(dram, NULL, "highbank.dram", ram_size);
     /* SDRAM at address zero.  */
     memory_region_add_subregion(sysmem, 0, dram);
 

hw/arm/integratorcp.c

@@ -567,8 +567,8 @@ static void integratorcp_init(MachineState *machine)
 
     cpu = ARM_CPU(cpuobj);
 
-    memory_region_init_ram(ram, NULL, "integrator.ram", ram_size, &error_abort);
-    vmstate_register_ram_global(ram);
+    memory_region_allocate_system_memory(ram, NULL, "integrator.ram",
+                                         ram_size);
     /* ??? On a real system the first 1Mb is mapped as SSRAM or boot flash.  */
     /* ??? RAM should repeat to fill physical memory space.  */
     /* SDRAM at address zero*/

hw/arm/kzm.c

@@ -97,8 +97,7 @@ static void kzm_init(MachineState *machine)
 
     /* On a real system, the first 16k is a `secure boot rom' */
 
-    memory_region_init_ram(ram, NULL, "kzm.ram", ram_size, &error_abort);
-    vmstate_register_ram_global(ram);
+    memory_region_allocate_system_memory(ram, NULL, "kzm.ram", ram_size);
     memory_region_add_subregion(address_space_mem, KZM_RAMADDRESS, ram);
 
     memory_region_init_alias(ram_alias, NULL, "ram.alias", ram, 0, ram_size);

hw/arm/musicpal.c

@@ -1600,9 +1600,8 @@ static void musicpal_init(MachineState *machine)
     }
 
     /* For now we use a fixed - the original - RAM size */
-    memory_region_init_ram(ram, NULL, "musicpal.ram", MP_RAM_DEFAULT_SIZE,
-                           &error_abort);
-    vmstate_register_ram_global(ram);
+    memory_region_allocate_system_memory(ram, NULL, "musicpal.ram",
+                                         MP_RAM_DEFAULT_SIZE);
     memory_region_add_subregion(address_space_mem, 0, ram);
 
     memory_region_init_ram(sram, NULL, "musicpal.sram", MP_SRAM_SIZE,

hw/arm/omap1.c

@@ -16,6 +16,8 @@
  * You should have received a copy of the GNU General Public License along
  * with this program; if not, see <http://www.gnu.org/licenses/>.
  */
+
+#include "hw/boards.h"
 #include "hw/hw.h"
 #include "hw/arm/arm.h"
 #include "hw/arm/omap.h"
@@ -3878,9 +3880,8 @@ struct omap_mpu_state_s *omap310_mpu_init(MemoryRegion *system_memory,
     omap_clk_init(s);
 
     /* Memory-mapped stuff */
-    memory_region_init_ram(&s->emiff_ram, NULL, "omap1.dram", s->sdram_size,
-                           &error_abort);
-    vmstate_register_ram_global(&s->emiff_ram);
+    memory_region_allocate_system_memory(&s->emiff_ram, NULL, "omap1.dram",
+                                         s->sdram_size);
     memory_region_add_subregion(system_memory, OMAP_EMIFF_BASE, &s->emiff_ram);
     memory_region_init_ram(&s->imif_ram, NULL, "omap1.sram", s->sram_size,
                            &error_abort);

hw/arm/omap2.c

@@ -20,6 +20,7 @@
 
 #include "sysemu/block-backend.h"
 #include "sysemu/blockdev.h"
+#include "hw/boards.h"
 #include "hw/hw.h"
 #include "hw/arm/arm.h"
 #include "hw/arm/omap.h"
@@ -2271,9 +2272,8 @@ struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sysmem,
     omap_clk_init(s);
 
     /* Memory-mapped stuff */
-    memory_region_init_ram(&s->sdram, NULL, "omap2.dram", s->sdram_size,
-                           &error_abort);
-    vmstate_register_ram_global(&s->sdram);
+    memory_region_allocate_system_memory(&s->sdram, NULL, "omap2.dram",
+                                         s->sdram_size);
     memory_region_add_subregion(sysmem, OMAP2_Q2_BASE, &s->sdram);
     memory_region_init_ram(&s->sram, NULL, "omap2.sram", s->sram_size,
                            &error_abort);

hw/arm/strongarm.c

@@ -26,6 +26,8 @@
  *  Contributions after 2012-01-13 are licensed under the terms of the
  *  GNU GPL, version 2 or (at your option) any later version.
  */
+
+#include "hw/boards.h"
 #include "hw/sysbus.h"
 #include "strongarm.h"
 #include "qemu/error-report.h"
@@ -1604,9 +1606,8 @@ StrongARMState *sa1110_init(MemoryRegion *sysmem,
         exit(1);
     }
 
-    memory_region_init_ram(&s->sdram, NULL, "strongarm.sdram", sdram_size,
-                           &error_abort);
-    vmstate_register_ram_global(&s->sdram);
+    memory_region_allocate_system_memory(&s->sdram, NULL, "strongarm.sdram",
+                                         sdram_size);
     memory_region_add_subregion(sysmem, SA_SDCS0, &s->sdram);
 
     s->pic = sysbus_create_varargs("strongarm_pic", 0x90050000,

hw/arm/versatilepb.c

@@ -226,9 +226,8 @@ static void versatile_init(MachineState *machine, int board_id)
 
     cpu = ARM_CPU(cpuobj);
 
-    memory_region_init_ram(ram, NULL, "versatile.ram", machine->ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(ram);
+    memory_region_allocate_system_memory(ram, NULL, "versatile.ram",
+                                         machine->ram_size);
     /* ??? RAM should repeat to fill physical memory space.  */
     /* SDRAM at address zero.  */
     memory_region_add_subregion(sysmem, 0, ram);

hw/arm/vexpress.c

@@ -276,9 +276,8 @@ static void a9_daughterboard_init(const VexpressMachineState *vms,
         exit(1);
     }
 
-    memory_region_init_ram(ram, NULL, "vexpress.highmem", ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(ram);
+    memory_region_allocate_system_memory(ram, NULL, "vexpress.highmem",
+                                         ram_size);
     low_ram_size = ram_size;
     if (low_ram_size > 0x4000000) {
         low_ram_size = 0x4000000;
@@ -371,9 +370,8 @@ static void a15_daughterboard_init(const VexpressMachineState *vms,
         }
     }
 
-    memory_region_init_ram(ram, NULL, "vexpress.highmem", ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(ram);
+    memory_region_allocate_system_memory(ram, NULL, "vexpress.highmem",
+                                         ram_size);
     /* RAM is from 0x80000000 upwards; there is no low-memory alias for it. */
     memory_region_add_subregion(sysmem, 0x80000000, ram);
 

hw/arm/virt.c

@@ -805,9 +805,8 @@ static void machvirt_init(MachineState *machine)
     fdt_add_cpu_nodes(vbi);
     fdt_add_psci_node(vbi);
 
-    memory_region_init_ram(ram, NULL, "mach-virt.ram", machine->ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(ram);
+    memory_region_allocate_system_memory(ram, NULL, "mach-virt.ram",
+                                         machine->ram_size);
     memory_region_add_subregion(sysmem, vbi->memmap[VIRT_MEM].base, ram);
 
     create_flash(vbi);

hw/arm/xilinx_zynq.c

@@ -161,9 +161,8 @@ static void zynq_init(MachineState *machine)
     }
 
     /* DDR remapped to address zero.  */
-    memory_region_init_ram(ext_ram, NULL, "zynq.ext_ram", ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(ext_ram);
+    memory_region_allocate_system_memory(ext_ram, NULL, "zynq.ext_ram",
+                                         ram_size);
     memory_region_add_subregion(address_space_mem, 0, ext_ram);
 
     /* 256K of on-chip memory */

hw/audio/pcspk.c

@@ -167,7 +167,7 @@ static void pcspk_initfn(Object *obj)
 {
     PCSpkState *s = PC_SPEAKER(obj);
 
-    memory_region_init_io(&s->ioport, OBJECT(s), &pcspk_io_ops, s, "elcr", 1);
+    memory_region_init_io(&s->ioport, OBJECT(s), &pcspk_io_ops, s, "pcspk", 1);
 }
 
 static void pcspk_realizefn(DeviceState *dev, Error **errp)

hw/block/dataplane/virtio-blk.c

@@ -77,8 +77,7 @@ static void complete_request_vring(VirtIOBlockReq *req, unsigned char status)
     VirtIOBlockDataPlane *s = req->dev->dataplane;
     stb_p(&req->in->status, status);
 
-    vring_push(s->vdev, &req->dev->dataplane->vring, &req->elem,
-               req->qiov.size + sizeof(*req->in));
+    vring_push(s->vdev, &req->dev->dataplane->vring, &req->elem, req->in_len);
 
     /* Suppress notification to guest by BH and its scheduled
      * flag because requests are completed as a batch after io

hw/block/fdc.c

@@ -1512,7 +1512,7 @@ static uint32_t fdctrl_read_data(FDCtrl *fdctrl)
 {
     FDrive *cur_drv;
     uint32_t retval = 0;
-    int pos;
+    uint32_t pos;
 
     cur_drv = get_cur_drv(fdctrl);
     fdctrl->dsr &= ~FD_DSR_PWRDOWN;
@@ -1521,8 +1521,8 @@ static uint32_t fdctrl_read_data(FDCtrl *fdctrl)
         return 0;
     }
     pos = fdctrl->data_pos;
+    pos %= FD_SECTOR_LEN;
     if (fdctrl->msr & FD_MSR_NONDMA) {
-        pos %= FD_SECTOR_LEN;
         if (pos == 0) {
             if (fdctrl->data_pos != 0)
                 if (!fdctrl_seek_to_next_sect(fdctrl, cur_drv)) {
@@ -1867,10 +1867,13 @@ static void fdctrl_handle_option(FDCtrl *fdctrl, int direction)
 static void fdctrl_handle_drive_specification_command(FDCtrl *fdctrl, int direction)
 {
     FDrive *cur_drv = get_cur_drv(fdctrl);
+    uint32_t pos;
 
-    if (fdctrl->fifo[fdctrl->data_pos - 1] & 0x80) {
+    pos = fdctrl->data_pos - 1;
+    pos %= FD_SECTOR_LEN;
+    if (fdctrl->fifo[pos] & 0x80) {
         /* Command parameters done */
-        if (fdctrl->fifo[fdctrl->data_pos - 1] & 0x40) {
+        if (fdctrl->fifo[pos] & 0x40) {
             fdctrl->fifo[0] = fdctrl->fifo[1];
             fdctrl->fifo[2] = 0;
             fdctrl->fifo[3] = 0;
@@ -1970,7 +1973,7 @@ static uint8_t command_to_handler[256];
 static void fdctrl_write_data(FDCtrl *fdctrl, uint32_t value)
 {
     FDrive *cur_drv;
-    int pos;
+    uint32_t pos;
 
     /* Reset mode */
     if (!(fdctrl->dor & FD_DOR_nRESET)) {
@@ -2019,7 +2022,9 @@ static void fdctrl_write_data(FDCtrl *fdctrl, uint32_t value)
     }
 
     FLOPPY_DPRINTF("%s: %02x\n", __func__, value);
-    fdctrl->fifo[fdctrl->data_pos++] = value;
+    pos = fdctrl->data_pos++;
+    pos %= FD_SECTOR_LEN;
+    fdctrl->fifo[pos] = value;
     if (fdctrl->data_pos == fdctrl->data_len) {
         /* We now have all parameters
          * and will be able to treat the command

hw/block/virtio-blk.c

@@ -33,6 +33,7 @@ VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s)
     VirtIOBlockReq *req = g_slice_new(VirtIOBlockReq);
     req->dev = s;
     req->qiov.size = 0;
+    req->in_len = 0;
     req->next = NULL;
     req->mr_next = NULL;
     return req;
@@ -54,7 +55,7 @@ static void virtio_blk_complete_request(VirtIOBlockReq *req,
     trace_virtio_blk_req_complete(req, status);
 
     stb_p(&req->in->status, status);
-    virtqueue_push(s->vq, &req->elem, req->qiov.size + sizeof(*req->in));
+    virtqueue_push(s->vq, &req->elem, req->in_len);
     virtio_notify(vdev, s->vq);
 }
 
@@ -102,6 +103,14 @@ static void virtio_blk_rw_complete(void *opaque, int ret)
         if (ret) {
             int p = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
             bool is_read = !(p & VIRTIO_BLK_T_OUT);
+            /* Note that memory may be dirtied on read failure.  If the
+             * virtio request is not completed here, as is the case for
+             * BLOCK_ERROR_ACTION_STOP, the memory may not be copied
+             * correctly during live migration.  While this is ugly,
+             * it is acceptable because the device is free to write to
+             * the memory until the request is completed (which will
+             * happen on the other side of the migration).
+             */
             if (virtio_blk_handle_rw_error(req, -ret, is_read)) {
                 continue;
             }
@@ -496,6 +505,8 @@ void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
         exit(1);
     }
 
+    /* We always touch the last byte, so just see how big in_iov is.  */
+    req->in_len = iov_size(in_iov, in_num);
     req->in = (void *)in_iov[in_num - 1].iov_base
               + in_iov[in_num - 1].iov_len
               - sizeof(struct virtio_blk_inhdr);

hw/bt/sdp.c

@@ -707,7 +707,7 @@ static void sdp_service_record_build(struct sdp_service_record_s *record,
         len += sdp_attr_max_size(&def->attributes[record->attributes ++].data,
                         &record->uuids);
     }
-    record->uuids = 1 << ffs(record->uuids - 1);
+    record->uuids = pow2ceil(record->uuids);
     record->attribute_list =
             g_malloc0(record->attributes * sizeof(*record->attribute_list));
     record->uuid =

hw/char/spapr_vty.c

@@ -228,6 +228,10 @@ VIOsPAPRDevice *vty_lookup(sPAPREnvironment *spapr, target_ulong reg)
         return spapr_vty_get_default(spapr->vio_bus);
     }
 
+    if (!object_dynamic_cast(OBJECT(sdev), TYPE_VIO_SPAPR_VTY_DEVICE)) {
+        return NULL;
+    }
+
     return sdev;
 }
 

hw/core/sysbus.c

@@ -281,19 +281,15 @@ static void sysbus_dev_print(Monitor *mon, DeviceState *dev, int indent)
 static char *sysbus_get_fw_dev_path(DeviceState *dev)
 {
     SysBusDevice *s = SYS_BUS_DEVICE(dev);
-    char path[40];
-    int off;
-
-    off = snprintf(path, sizeof(path), "%s", qdev_fw_name(dev));
 
     if (s->num_mmio) {
-        snprintf(path + off, sizeof(path) - off, "@"TARGET_FMT_plx,
-                 s->mmio[0].addr);
-    } else if (s->num_pio) {
-        snprintf(path + off, sizeof(path) - off, "@i%04x", s->pio[0]);
+        return g_strdup_printf("%s@" TARGET_FMT_plx, qdev_fw_name(dev),
+                               s->mmio[0].addr);
     }
-
-    return g_strdup(path);
+    if (s->num_pio) {
+        return g_strdup_printf("%s@i%04x", qdev_fw_name(dev), s->pio[0]);
+    }
+    return g_strdup(qdev_fw_name(dev));
 }
 
 void sysbus_add_io(SysBusDevice *dev, hwaddr addr,

hw/cris/axis_dev88.c

@@ -270,9 +270,8 @@ void axisdev88_init(MachineState *machine)
     env = &cpu->env;
 
     /* allocate RAM */
-    memory_region_init_ram(phys_ram, NULL, "axisdev88.ram", ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(phys_ram);
+    memory_region_allocate_system_memory(phys_ram, NULL, "axisdev88.ram",
+                                         ram_size);
     memory_region_add_subregion(address_space_mem, 0x40000000, phys_ram);
 
     /* The ETRAX-FS has 128Kb on chip ram, the docs refer to it as the 

hw/ide/atapi.c

@@ -983,6 +983,7 @@ static void cmd_start_stop_unit(IDEState *s, uint8_t* buf)
 
     if (pwrcnd) {
         /* eject/load only happens for power condition == 0 */
+        ide_atapi_cmd_ok(s);
         return;
     }
 

hw/ide/core.c

@@ -2021,11 +2021,17 @@ void ide_data_writew(void *opaque, uint32_t addr, uint32_t val)
     }
 
     p = s->data_ptr;
+    if (p + 2 > s->data_end) {
+        return;
+    }
+
     *(uint16_t *)p = le16_to_cpu(val);
     p += 2;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
 }
 
 uint32_t ide_data_readw(void *opaque, uint32_t addr)
@@ -2042,11 +2048,17 @@ uint32_t ide_data_readw(void *opaque, uint32_t addr)
     }
 
     p = s->data_ptr;
+    if (p + 2 > s->data_end) {
+        return 0;
+    }
+
     ret = cpu_to_le16(*(uint16_t *)p);
     p += 2;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
     return ret;
 }
 
@@ -2063,11 +2075,17 @@ void ide_data_writel(void *opaque, uint32_t addr, uint32_t val)
     }
 
     p = s->data_ptr;
+    if (p + 4 > s->data_end) {
+        return;
+    }
+
     *(uint32_t *)p = le32_to_cpu(val);
     p += 4;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
 }
 
 uint32_t ide_data_readl(void *opaque, uint32_t addr)
@@ -2084,11 +2102,17 @@ uint32_t ide_data_readl(void *opaque, uint32_t addr)
     }
 
     p = s->data_ptr;
+    if (p + 4 > s->data_end) {
+        return 0;
+    }
+
     ret = cpu_to_le32(*(uint32_t *)p);
     p += 4;
     s->data_ptr = p;
-    if (p >= s->data_end)
+    if (p >= s->data_end) {
+        s->status &= ~DRQ_STAT;
         s->end_transfer_func(s);
+    }
     return ret;
 }
 

hw/ide/piix.c

@@ -169,6 +169,7 @@ int pci_piix3_xen_ide_unplug(DeviceState *dev)
     PCIIDEState *pci_ide;
     DriveInfo *di;
     int i;
+    IDEDevice *idedev;
 
     pci_ide = PCI_IDE(dev);
 
@@ -181,6 +182,12 @@ int pci_piix3_xen_ide_unplug(DeviceState *dev)
                 blk_detach_dev(blk, ds);
             }
             pci_ide->bus[di->bus].ifs[di->unit].blk = NULL;
+            if (!(i % 2)) {
+                idedev = pci_ide->bus[di->bus].master;
+            } else {
+                idedev = pci_ide->bus[di->bus].slave;
+            }
+            idedev->conf.blk = NULL;
             blk_unref(blk);
         }
     }

hw/lm32/lm32_boards.c

@@ -111,9 +111,8 @@ static void lm32_evr_init(MachineState *machine)
 
     reset_info->flash_base = flash_base;
 
-    memory_region_init_ram(phys_ram, NULL, "lm32_evr.sdram", ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(phys_ram);
+    memory_region_allocate_system_memory(phys_ram, NULL, "lm32_evr.sdram",
+                                         ram_size);
     memory_region_add_subregion(address_space_mem, ram_base, phys_ram);
 
     dinfo = drive_get(IF_PFLASH, 0, 0);
@@ -214,9 +213,8 @@ static void lm32_uclinux_init(MachineState *machine)
 
     reset_info->flash_base = flash_base;
 
-    memory_region_init_ram(phys_ram, NULL, "lm32_uclinux.sdram", ram_size,
-                           &error_abort);
-    vmstate_register_ram_global(phys_ram);
+    memory_region_allocate_system_memory(phys_ram, NULL,
+                                         "lm32_uclinux.sdram", ram_size);
     memory_region_add_subregion(address_space_mem, ram_base, phys_ram);
 
     dinfo = drive_get(IF_PFLASH, 0, 0);

hw/lm32/milkymist.c

@@ -118,9 +118,8 @@ milkymist_init(MachineState *machine)
 
     cpu_lm32_set_phys_msb_ignore(env, 1);
 
-    memory_region_init_ram(phys_sdram, NULL, "milkymist.sdram", sdram_size,
-                           &error_abort);
-    vmstate_register_ram_global(phys_sdram);
+    memory_region_allocate_system_memory(phys_sdram, NULL, "milkymist.sdram",
+                                         sdram_size);
     memory_region_add_subregion(address_space_mem, sdram_base, phys_sdram);
 
     dinfo = drive_get(IF_PFLASH, 0, 0);

hw/net/rtl8139.c

@@ -2150,6 +2150,11 @@ static int rtl8139_cplus_transmit_one(RTL8139State *s)
         {
             DPRINTF("+++ C+ mode offloaded task checksum\n");
 
+            /* Large enough for Ethernet and IP headers? */
+            if (saved_size < ETH_HLEN + sizeof(ip_header)) {
+                goto skip_offload;
+            }
+
             /* ip packet header */
             ip_header *ip = NULL;
             int hlen = 0;
@@ -2160,223 +2165,235 @@ static int rtl8139_cplus_transmit_one(RTL8139State *s)
             size_t   eth_payload_len  = 0;
 
             int proto = be16_to_cpu(*(uint16_t *)(saved_buffer + 12));
-            if (proto == ETH_P_IP)
+            if (proto != ETH_P_IP)
             {
-                DPRINTF("+++ C+ mode has IP packet\n");
-
-                /* not aligned */
-                eth_payload_data = saved_buffer + ETH_HLEN;
-                eth_payload_len  = saved_size   - ETH_HLEN;
-
-                ip = (ip_header*)eth_payload_data;
-
-                if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) {
-                    DPRINTF("+++ C+ mode packet has bad IP version %d "
-                        "expected %d\n", IP_HEADER_VERSION(ip),
-                        IP_HEADER_VERSION_4);
-                    ip = NULL;
-                } else {
-                    hlen = IP_HEADER_LENGTH(ip);
-                    ip_protocol = ip->ip_p;
-                    ip_data_len = be16_to_cpu(ip->ip_len) - hlen;
-                }
+                goto skip_offload;
             }
 
-            if (ip)
+            DPRINTF("+++ C+ mode has IP packet\n");
+
+            /* not aligned */
+            eth_payload_data = saved_buffer + ETH_HLEN;
+            eth_payload_len  = saved_size   - ETH_HLEN;
+
+            ip = (ip_header*)eth_payload_data;
+
+            if (IP_HEADER_VERSION(ip) != IP_HEADER_VERSION_4) {
+                DPRINTF("+++ C+ mode packet has bad IP version %d "
+                    "expected %d\n", IP_HEADER_VERSION(ip),
+                    IP_HEADER_VERSION_4);
+                goto skip_offload;
+            }
+
+            hlen = IP_HEADER_LENGTH(ip);
+            if (hlen < sizeof(ip_header) || hlen > eth_payload_len) {
+                goto skip_offload;
+            }
+
+            ip_protocol = ip->ip_p;
+
+            ip_data_len = be16_to_cpu(ip->ip_len);
+            if (ip_data_len < hlen || ip_data_len > eth_payload_len) {
+                goto skip_offload;
+            }
+            ip_data_len -= hlen;
+
+            if (txdw0 & CP_TX_IPCS)
             {
-                if (txdw0 & CP_TX_IPCS)
-                {
-                    DPRINTF("+++ C+ mode need IP checksum\n");
+                DPRINTF("+++ C+ mode need IP checksum\n");
 
-                    if (hlen<sizeof(ip_header) || hlen>eth_payload_len) {/* min header length */
-                        /* bad packet header len */
-                        /* or packet too short */
-                    }
-                    else
-                    {
-                        ip->ip_sum = 0;
-                        ip->ip_sum = ip_checksum(ip, hlen);
-                        DPRINTF("+++ C+ mode IP header len=%d checksum=%04x\n",
-                            hlen, ip->ip_sum);
-                    }
+                ip->ip_sum = 0;
+                ip->ip_sum = ip_checksum(ip, hlen);
+                DPRINTF("+++ C+ mode IP header len=%d checksum=%04x\n",
+                    hlen, ip->ip_sum);
+            }
+
+            if ((txdw0 & CP_TX_LGSEN) && ip_protocol == IP_PROTO_TCP)
+            {
+                /* Large enough for the TCP header? */
+                if (ip_data_len < sizeof(tcp_header)) {
+                    goto skip_offload;
                 }
 
-                if ((txdw0 & CP_TX_LGSEN) && ip_protocol == IP_PROTO_TCP)
+                int large_send_mss = (txdw0 >> 16) & CP_TC_LGSEN_MSS_MASK;
+
+                DPRINTF("+++ C+ mode offloaded task TSO MTU=%d IP data %d "
+                    "frame data %d specified MSS=%d\n", ETH_MTU,
+                    ip_data_len, saved_size - ETH_HLEN, large_send_mss);
+
+                int tcp_send_offset = 0;
+                int send_count = 0;
+
+                /* maximum IP header length is 60 bytes */
+                uint8_t saved_ip_header[60];
+
+                /* save IP header template; data area is used in tcp checksum calculation */
+                memcpy(saved_ip_header, eth_payload_data, hlen);
+
+                /* a placeholder for checksum calculation routine in tcp case */
+                uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
+                //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
+
+                /* pointer to TCP header */
+                tcp_header *p_tcp_hdr = (tcp_header*)(eth_payload_data + hlen);
+
+                int tcp_hlen = TCP_HEADER_DATA_OFFSET(p_tcp_hdr);
+
+                /* Invalid TCP data offset? */
+                if (tcp_hlen < sizeof(tcp_header) || tcp_hlen > ip_data_len) {
+                    goto skip_offload;
+                }
+
+                /* ETH_MTU = ip header len + tcp header len + payload */
+                int tcp_data_len = ip_data_len - tcp_hlen;
+                int tcp_chunk_size = ETH_MTU - hlen - tcp_hlen;
+
+                DPRINTF("+++ C+ mode TSO IP data len %d TCP hlen %d TCP "
+                    "data len %d TCP chunk size %d\n", ip_data_len,
+                    tcp_hlen, tcp_data_len, tcp_chunk_size);
+
+                /* note the cycle below overwrites IP header data,
+                   but restores it from saved_ip_header before sending packet */
+
+                int is_last_frame = 0;
+
+                for (tcp_send_offset = 0; tcp_send_offset < tcp_data_len; tcp_send_offset += tcp_chunk_size)
                 {
-                    int large_send_mss = (txdw0 >> 16) & CP_TC_LGSEN_MSS_MASK;
+                    uint16_t chunk_size = tcp_chunk_size;
 
-                    DPRINTF("+++ C+ mode offloaded task TSO MTU=%d IP data %d "
-                        "frame data %d specified MSS=%d\n", ETH_MTU,
-                        ip_data_len, saved_size - ETH_HLEN, large_send_mss);
-
-                    int tcp_send_offset = 0;
-                    int send_count = 0;
-
-                    /* maximum IP header length is 60 bytes */
-                    uint8_t saved_ip_header[60];
-
-                    /* save IP header template; data area is used in tcp checksum calculation */
-                    memcpy(saved_ip_header, eth_payload_data, hlen);
-
-                    /* a placeholder for checksum calculation routine in tcp case */
-                    uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
-                    //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
-
-                    /* pointer to TCP header */
-                    tcp_header *p_tcp_hdr = (tcp_header*)(eth_payload_data + hlen);
-
-                    int tcp_hlen = TCP_HEADER_DATA_OFFSET(p_tcp_hdr);
-
-                    /* ETH_MTU = ip header len + tcp header len + payload */
-                    int tcp_data_len = ip_data_len - tcp_hlen;
-                    int tcp_chunk_size = ETH_MTU - hlen - tcp_hlen;
-
-                    DPRINTF("+++ C+ mode TSO IP data len %d TCP hlen %d TCP "
-                        "data len %d TCP chunk size %d\n", ip_data_len,
-                        tcp_hlen, tcp_data_len, tcp_chunk_size);
-
-                    /* note the cycle below overwrites IP header data,
-                       but restores it from saved_ip_header before sending packet */
-
-                    int is_last_frame = 0;
-
-                    for (tcp_send_offset = 0; tcp_send_offset < tcp_data_len; tcp_send_offset += tcp_chunk_size)
+                    /* check if this is the last frame */
+                    if (tcp_send_offset + tcp_chunk_size >= tcp_data_len)
                     {
-                        uint16_t chunk_size = tcp_chunk_size;
-
-                        /* check if this is the last frame */
-                        if (tcp_send_offset + tcp_chunk_size >= tcp_data_len)
-                        {
-                            is_last_frame = 1;
-                            chunk_size = tcp_data_len - tcp_send_offset;
-                        }
-
-                        DPRINTF("+++ C+ mode TSO TCP seqno %08x\n",
-                            be32_to_cpu(p_tcp_hdr->th_seq));
-
-                        /* add 4 TCP pseudoheader fields */
-                        /* copy IP source and destination fields */
-                        memcpy(data_to_checksum, saved_ip_header + 12, 8);
-
-                        DPRINTF("+++ C+ mode TSO calculating TCP checksum for "
-                            "packet with %d bytes data\n", tcp_hlen +
-                            chunk_size);
-
-                        if (tcp_send_offset)
-                        {
-                            memcpy((uint8_t*)p_tcp_hdr + tcp_hlen, (uint8_t*)p_tcp_hdr + tcp_hlen + tcp_send_offset, chunk_size);
-                        }
-
-                        /* keep PUSH and FIN flags only for the last frame */
-                        if (!is_last_frame)
-                        {
-                            TCP_HEADER_CLEAR_FLAGS(p_tcp_hdr, TCP_FLAG_PUSH|TCP_FLAG_FIN);
-                        }
-
-                        /* recalculate TCP checksum */
-                        ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
-                        p_tcpip_hdr->zeros      = 0;
-                        p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
-                        p_tcpip_hdr->ip_payload = cpu_to_be16(tcp_hlen + chunk_size);
-
-                        p_tcp_hdr->th_sum = 0;
-
-                        int tcp_checksum = ip_checksum(data_to_checksum, tcp_hlen + chunk_size + 12);
-                        DPRINTF("+++ C+ mode TSO TCP checksum %04x\n",
-                            tcp_checksum);
-
-                        p_tcp_hdr->th_sum = tcp_checksum;
-
-                        /* restore IP header */
-                        memcpy(eth_payload_data, saved_ip_header, hlen);
-
-                        /* set IP data length and recalculate IP checksum */
-                        ip->ip_len = cpu_to_be16(hlen + tcp_hlen + chunk_size);
-
-                        /* increment IP id for subsequent frames */
-                        ip->ip_id = cpu_to_be16(tcp_send_offset/tcp_chunk_size + be16_to_cpu(ip->ip_id));
-
-                        ip->ip_sum = 0;
-                        ip->ip_sum = ip_checksum(eth_payload_data, hlen);
-                        DPRINTF("+++ C+ mode TSO IP header len=%d "
-                            "checksum=%04x\n", hlen, ip->ip_sum);
-
-                        int tso_send_size = ETH_HLEN + hlen + tcp_hlen + chunk_size;
-                        DPRINTF("+++ C+ mode TSO transferring packet size "
-                            "%d\n", tso_send_size);
-                        rtl8139_transfer_frame(s, saved_buffer, tso_send_size,
-                            0, (uint8_t *) dot1q_buffer);
-
-                        /* add transferred count to TCP sequence number */
-                        p_tcp_hdr->th_seq = cpu_to_be32(chunk_size + be32_to_cpu(p_tcp_hdr->th_seq));
-                        ++send_count;
+                        is_last_frame = 1;
+                        chunk_size = tcp_data_len - tcp_send_offset;
                     }
 
-                    /* Stop sending this frame */
-                    saved_size = 0;
-                }
-                else if (txdw0 & (CP_TX_TCPCS|CP_TX_UDPCS))
-                {
-                    DPRINTF("+++ C+ mode need TCP or UDP checksum\n");
-
-                    /* maximum IP header length is 60 bytes */
-                    uint8_t saved_ip_header[60];
-                    memcpy(saved_ip_header, eth_payload_data, hlen);
-
-                    uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
-                    //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
+                    DPRINTF("+++ C+ mode TSO TCP seqno %08x\n",
+                        be32_to_cpu(p_tcp_hdr->th_seq));
 
                     /* add 4 TCP pseudoheader fields */
                     /* copy IP source and destination fields */
                     memcpy(data_to_checksum, saved_ip_header + 12, 8);
 
-                    if ((txdw0 & CP_TX_TCPCS) && ip_protocol == IP_PROTO_TCP)
+                    DPRINTF("+++ C+ mode TSO calculating TCP checksum for "
+                        "packet with %d bytes data\n", tcp_hlen +
+                        chunk_size);
+
+                    if (tcp_send_offset)
                     {
-                        DPRINTF("+++ C+ mode calculating TCP checksum for "
-                            "packet with %d bytes data\n", ip_data_len);
-
-                        ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
-                        p_tcpip_hdr->zeros      = 0;
-                        p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
-                        p_tcpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
-
-                        tcp_header* p_tcp_hdr = (tcp_header *) (data_to_checksum+12);
-
-                        p_tcp_hdr->th_sum = 0;
-
-                        int tcp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
-                        DPRINTF("+++ C+ mode TCP checksum %04x\n",
-                            tcp_checksum);
-
-                        p_tcp_hdr->th_sum = tcp_checksum;
+                        memcpy((uint8_t*)p_tcp_hdr + tcp_hlen, (uint8_t*)p_tcp_hdr + tcp_hlen + tcp_send_offset, chunk_size);
                     }
-                    else if ((txdw0 & CP_TX_UDPCS) && ip_protocol == IP_PROTO_UDP)
+
+                    /* keep PUSH and FIN flags only for the last frame */
+                    if (!is_last_frame)
                     {
-                        DPRINTF("+++ C+ mode calculating UDP checksum for "
-                            "packet with %d bytes data\n", ip_data_len);
-
-                        ip_pseudo_header *p_udpip_hdr = (ip_pseudo_header *)data_to_checksum;
-                        p_udpip_hdr->zeros      = 0;
-                        p_udpip_hdr->ip_proto   = IP_PROTO_UDP;
-                        p_udpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
-
-                        udp_header *p_udp_hdr = (udp_header *) (data_to_checksum+12);
-
-                        p_udp_hdr->uh_sum = 0;
-
-                        int udp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
-                        DPRINTF("+++ C+ mode UDP checksum %04x\n",
-                            udp_checksum);
-
-                        p_udp_hdr->uh_sum = udp_checksum;
+                        TCP_HEADER_CLEAR_FLAGS(p_tcp_hdr, TCP_FLAG_PUSH|TCP_FLAG_FIN);
                     }
 
+                    /* recalculate TCP checksum */
+                    ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
+                    p_tcpip_hdr->zeros      = 0;
+                    p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
+                    p_tcpip_hdr->ip_payload = cpu_to_be16(tcp_hlen + chunk_size);
+
+                    p_tcp_hdr->th_sum = 0;
+
+                    int tcp_checksum = ip_checksum(data_to_checksum, tcp_hlen + chunk_size + 12);
+                    DPRINTF("+++ C+ mode TSO TCP checksum %04x\n",
+                        tcp_checksum);
+
+                    p_tcp_hdr->th_sum = tcp_checksum;
+
                     /* restore IP header */
                     memcpy(eth_payload_data, saved_ip_header, hlen);
+
+                    /* set IP data length and recalculate IP checksum */
+                    ip->ip_len = cpu_to_be16(hlen + tcp_hlen + chunk_size);
+
+                    /* increment IP id for subsequent frames */
+                    ip->ip_id = cpu_to_be16(tcp_send_offset/tcp_chunk_size + be16_to_cpu(ip->ip_id));
+
+                    ip->ip_sum = 0;
+                    ip->ip_sum = ip_checksum(eth_payload_data, hlen);
+                    DPRINTF("+++ C+ mode TSO IP header len=%d "
+                        "checksum=%04x\n", hlen, ip->ip_sum);
+
+                    int tso_send_size = ETH_HLEN + hlen + tcp_hlen + chunk_size;
+                    DPRINTF("+++ C+ mode TSO transferring packet size "
+                        "%d\n", tso_send_size);
+                    rtl8139_transfer_frame(s, saved_buffer, tso_send_size,
+                        0, (uint8_t *) dot1q_buffer);
+
+                    /* add transferred count to TCP sequence number */
+                    p_tcp_hdr->th_seq = cpu_to_be32(chunk_size + be32_to_cpu(p_tcp_hdr->th_seq));
+                    ++send_count;
                 }
+
+                /* Stop sending this frame */
+                saved_size = 0;
+            }
+            else if (txdw0 & (CP_TX_TCPCS|CP_TX_UDPCS))
+            {
+                DPRINTF("+++ C+ mode need TCP or UDP checksum\n");
+
+                /* maximum IP header length is 60 bytes */
+                uint8_t saved_ip_header[60];
+                memcpy(saved_ip_header, eth_payload_data, hlen);
+
+                uint8_t *data_to_checksum     = eth_payload_data + hlen - 12;
+                //                    size_t   data_to_checksum_len = eth_payload_len  - hlen + 12;
+
+                /* add 4 TCP pseudoheader fields */
+                /* copy IP source and destination fields */
+                memcpy(data_to_checksum, saved_ip_header + 12, 8);
+
+                if ((txdw0 & CP_TX_TCPCS) && ip_protocol == IP_PROTO_TCP)
+                {
+                    DPRINTF("+++ C+ mode calculating TCP checksum for "
+                        "packet with %d bytes data\n", ip_data_len);
+
+                    ip_pseudo_header *p_tcpip_hdr = (ip_pseudo_header *)data_to_checksum;
+                    p_tcpip_hdr->zeros      = 0;
+                    p_tcpip_hdr->ip_proto   = IP_PROTO_TCP;
+                    p_tcpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
+
+                    tcp_header* p_tcp_hdr = (tcp_header *) (data_to_checksum+12);
+
+                    p_tcp_hdr->th_sum = 0;
+
+                    int tcp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
+                    DPRINTF("+++ C+ mode TCP checksum %04x\n",
+                        tcp_checksum);
+
+                    p_tcp_hdr->th_sum = tcp_checksum;
+                }
+                else if ((txdw0 & CP_TX_UDPCS) && ip_protocol == IP_PROTO_UDP)
+                {
+                    DPRINTF("+++ C+ mode calculating UDP checksum for "
+                        "packet with %d bytes data\n", ip_data_len);
+
+                    ip_pseudo_header *p_udpip_hdr = (ip_pseudo_header *)data_to_checksum;
+                    p_udpip_hdr->zeros      = 0;
+                    p_udpip_hdr->ip_proto   = IP_PROTO_UDP;
+                    p_udpip_hdr->ip_payload = cpu_to_be16(ip_data_len);
+
+                    udp_header *p_udp_hdr = (udp_header *) (data_to_checksum+12);
+
+                    p_udp_hdr->uh_sum = 0;
+
+                    int udp_checksum = ip_checksum(data_to_checksum, ip_data_len + 12);
+                    DPRINTF("+++ C+ mode UDP checksum %04x\n",
+                        udp_checksum);
+
+                    p_udp_hdr->uh_sum = udp_checksum;
+                }
+
+                /* restore IP header */
+                memcpy(eth_payload_data, saved_ip_header, hlen);
             }
         }
 
+skip_offload:
         /* update tally counter */
         ++s->tally_counters.TxOk;
 

hw/net/virtio-net.c

@@ -1138,7 +1138,8 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         ssize_t ret, len;
         unsigned int out_num = elem.out_num;
         struct iovec *out_sg = &elem.out_sg[0];
-        struct iovec sg[VIRTQUEUE_MAX_SIZE];
+        struct iovec sg[VIRTQUEUE_MAX_SIZE], sg2[VIRTQUEUE_MAX_SIZE + 1];
+        struct virtio_net_hdr_mrg_rxbuf mhdr;
 
         if (out_num < 1) {
             error_report("virtio-net header not in first element");
@@ -1146,13 +1147,25 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         }
 
         if (n->has_vnet_hdr) {
-            if (out_sg[0].iov_len < n->guest_hdr_len) {
+            if (iov_to_buf(out_sg, out_num, 0, &mhdr, n->guest_hdr_len) <
+                n->guest_hdr_len) {
                 error_report("virtio-net header incorrect");
                 exit(1);
             }
-            virtio_net_hdr_swap(vdev, (void *) out_sg[0].iov_base);
+            if (virtio_needs_swap(vdev)) {
+                virtio_net_hdr_swap(vdev, (void *) &mhdr);
+                sg2[0].iov_base = &mhdr;
+                sg2[0].iov_len = n->guest_hdr_len;
+                out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1,
+                                   out_sg, out_num,
+                                   n->guest_hdr_len, -1);
+                if (out_num == VIRTQUEUE_MAX_SIZE) {
+                    goto drop;
+		}
+                out_num += 1;
+                out_sg = sg2;
+	    }
         }
-
         /*
          * If host wants to see the guest header as is, we can
          * pass it on unchanged. Otherwise, copy just the parts
@@ -1182,7 +1195,7 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         }
 
         len += ret;
-
+drop:
         virtqueue_push(q->tx_vq, &elem, 0);
         virtio_notify(vdev, q->tx_vq);
 
@@ -1309,7 +1322,7 @@ static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue)
 
     n->multiqueue = multiqueue;
 
-    for (i = 2; i <= n->max_queues * 2 + 1; i++) {
+    for (i = 2; i < n->max_queues * 2 + 1; i++) {
         virtio_del_queue(vdev, i);
     }
 

hw/pci-host/bonito.c

@@ -233,7 +233,7 @@ static void bonito_writel(void *opaque, hwaddr addr,
     uint32_t saddr;
     int reset = 0;
 
-    saddr = (addr - BONITO_REGBASE) >> 2;
+    saddr = addr >> 2;
 
     DPRINTF("bonito_writel "TARGET_FMT_plx" val %x saddr %x\n", addr, val, saddr);
     switch (saddr) {
@@ -295,7 +295,7 @@ static uint64_t bonito_readl(void *opaque, hwaddr addr,
     PCIBonitoState *s = opaque;
     uint32_t saddr;
 
-    saddr = (addr - BONITO_REGBASE) >> 2;
+    saddr = addr >> 2;
 
     DPRINTF("bonito_readl "TARGET_FMT_plx"\n", addr);
     switch (saddr) {

hw/pci/pci.c

@@ -1660,7 +1660,9 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, PCIBus *rootbus,
 
     res = pci_nic_init(nd, rootbus, default_model, default_devaddr, &err);
     if (!res) {
-        error_report_err(err);
+        if (err) {
+            error_report_err(err);
+        }
         exit(1);
     }
     return res;

hw/s390x/ipl.c

@@ -218,7 +218,7 @@ static Property s390_ipl_properties[] = {
  * - -1 if no valid boot device was found
  * - ccw id of the boot device otherwise
  */
-static uint32_t s390_update_iplstate(CPUS390XState *env, S390IPLState *ipl)
+static uint64_t s390_update_iplstate(CPUS390XState *env, S390IPLState *ipl)
 {
     DeviceState *dev_st;
 
@@ -248,7 +248,7 @@ static uint32_t s390_update_iplstate(CPUS390XState *env, S390IPLState *ipl)
 
     return -1;
 out:
-    return ipl->cssid << 24 | ipl->ssid << 16 | ipl->devno;
+    return (uint32_t) (ipl->cssid << 24 | ipl->ssid << 16 | ipl->devno);
 }
 
 int s390_ipl_update_diag308(IplParameterBlock *iplb)

hw/s390x/virtio-ccw.c

@@ -295,6 +295,25 @@ static int virtio_ccw_set_vqs(SubchDev *sch, uint64_t addr, uint32_t align,
     return 0;
 }
 
+static void virtio_ccw_reset_virtio(VirtioCcwDevice *dev, VirtIODevice *vdev)
+{
+    virtio_ccw_stop_ioeventfd(dev);
+    virtio_reset(vdev);
+    if (dev->indicators) {
+        release_indicator(&dev->routes.adapter, dev->indicators);
+        dev->indicators = NULL;
+    }
+    if (dev->indicators2) {
+        release_indicator(&dev->routes.adapter, dev->indicators2);
+        dev->indicators2 = NULL;
+    }
+    if (dev->summary_indicator) {
+        release_indicator(&dev->routes.adapter, dev->summary_indicator);
+        dev->summary_indicator = NULL;
+    }
+    dev->sch->thinint_active = false;
+}
+
 static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
 {
     int ret;
@@ -351,8 +370,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
         }
         break;
     case CCW_CMD_VDEV_RESET:
-        virtio_ccw_stop_ioeventfd(dev);
-        virtio_reset(vdev);
+        virtio_ccw_reset_virtio(dev, vdev);
         ret = 0;
         break;
     case CCW_CMD_READ_FEAT:
@@ -480,7 +498,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             }
             virtio_set_status(vdev, status);
             if (vdev->status == 0) {
-                virtio_reset(vdev);
+                virtio_ccw_reset_virtio(dev, vdev);
             }
             if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
                 virtio_ccw_start_ioeventfd(dev);
@@ -1098,21 +1116,8 @@ static void virtio_ccw_reset(DeviceState *d)
     VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
     VirtIODevice *vdev = virtio_bus_get_device(&dev->bus);
 
-    virtio_ccw_stop_ioeventfd(dev);
-    virtio_reset(vdev);
+    virtio_ccw_reset_virtio(dev, vdev);
     css_reset_sch(dev->sch);
-    if (dev->indicators) {
-        release_indicator(&dev->routes.adapter, dev->indicators);
-        dev->indicators = NULL;
-    }
-    if (dev->indicators2) {
-        release_indicator(&dev->routes.adapter, dev->indicators2);
-        dev->indicators2 = NULL;
-    }
-    if (dev->summary_indicator) {
-        release_indicator(&dev->routes.adapter, dev->summary_indicator);
-        dev->summary_indicator = NULL;
-    }
 }
 
 static void virtio_ccw_vmstate_change(DeviceState *d, bool running)

hw/scsi/scsi-bus.c

@@ -1239,10 +1239,15 @@ int scsi_cdb_length(uint8_t *buf) {
 int scsi_req_parse_cdb(SCSIDevice *dev, SCSICommand *cmd, uint8_t *buf)
 {
     int rc;
+    int len;
 
     cmd->lba = -1;
-    cmd->len = scsi_cdb_length(buf);
+    len = scsi_cdb_length(buf);
+    if (len < 0) {
+        return -1;
+    }
 
+    cmd->len = len;
     switch (dev->type) {
     case TYPE_TAPE:
         rc = scsi_req_stream_xfer(cmd, dev, buf);

hw/timer/i8254.c

@@ -196,6 +196,12 @@ static uint64_t pit_ioport_read(void *opaque, hwaddr addr,
     PITChannelState *s;
 
     addr &= 3;
+
+    if (addr == 3) {
+        /* Mode/Command register is write only, read is ignored */
+        return 0;
+    }
+
     s = &pit->channels[addr];
     if (s->status_latched) {
         s->status_latched = 0;

hw/usb/dev-network.c

@@ -1310,6 +1310,10 @@ static int usbnet_can_receive(NetClientState *nc)
 {
     USBNetState *s = qemu_get_nic_opaque(nc);
 
+    if (!s->dev.config) {
+        return 0;
+    }
+
     if (is_rndis(s) && s->rndis_state != RNDIS_DATA_INITIALIZED) {
         return 1;
     }

hw/vfio/pci.c

@@ -1516,7 +1516,7 @@ static uint64_t vfio_rtl8168_window_quirk_read(void *opaque,
                     memory_region_name(&quirk->mem),
                     vdev->vbasedev.name);
 
-            return quirk->data.address_match ^ 0x10000000U;
+            return quirk->data.address_match ^ 0x80000000U;
         }
         break;
     case 0: /* data */
@@ -1554,7 +1554,7 @@ static void vfio_rtl8168_window_quirk_write(void *opaque, hwaddr addr,
     switch (addr) {
     case 4: /* address */
         if ((data & 0x7fff0000) == 0x10000) {
-            if (data & 0x10000000U &&
+            if (data & 0x80000000U &&
                 vdev->pdev.cap_present & QEMU_PCI_CAP_MSIX) {
 
                 trace_vfio_rtl8168_window_quirk_write_table(
@@ -1562,8 +1562,9 @@ static void vfio_rtl8168_window_quirk_write(void *opaque, hwaddr addr,
                         vdev->vbasedev.name);
 
                 io_mem_write(&vdev->pdev.msix_table_mmio,
-                             (hwaddr)(quirk->data.address_match & 0xfff),
-                             data, size);
+                             (hwaddr)(data & 0xfff),
+                             (uint64_t)quirk->data.address_mask,
+                             size);
             }
 
             quirk->data.flags = 1;
@@ -3555,7 +3556,6 @@ static Property vfio_pci_dev_properties[] = {
                     VFIO_FEATURE_ENABLE_VGA_BIT, false),
     DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features,
                     VFIO_FEATURE_ENABLE_REQ_BIT, true),
-    DEFINE_PROP_INT32("bootindex", VFIOPCIDevice, bootindex, -1),
     DEFINE_PROP_BOOL("x-mmap", VFIOPCIDevice, vbasedev.allow_mmap, true),
     /*
      * TODO - support passed fds... is this necessary?

hw/virtio/vhost.c

@@ -288,7 +288,7 @@ static inline void vhost_dev_log_resize(struct vhost_dev* dev, uint64_t size)
     int r;
 
     log = g_malloc0(size * sizeof *log);
-    log_base = (uint64_t)(unsigned long)log;
+    log_base = (uintptr_t)log;
     r = dev->vhost_ops->vhost_call(dev, VHOST_SET_LOG_BASE, &log_base);
     assert(r >= 0);
     /* Sync only the range covered by the old log */
@@ -921,7 +921,7 @@ int vhost_dev_enable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
     VirtioBusState *vbus = VIRTIO_BUS(qbus);
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
-    int i, r;
+    int i, r, e;
     if (!k->set_host_notifier) {
         fprintf(stderr, "binding does not support host notifiers\n");
         r = -ENOSYS;
@@ -939,12 +939,12 @@ int vhost_dev_enable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
     return 0;
 fail_vq:
     while (--i >= 0) {
-        r = k->set_host_notifier(qbus->parent, hdev->vq_index + i, false);
-        if (r < 0) {
+        e = k->set_host_notifier(qbus->parent, hdev->vq_index + i, false);
+        if (e < 0) {
             fprintf(stderr, "vhost VQ %d notifier cleanup error: %d\n", i, -r);
             fflush(stderr);
         }
-        assert (r >= 0);
+        assert (e >= 0);
     }
 fail:
     return r;
@@ -1057,10 +1057,13 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
     }
 
     if (hdev->log_enabled) {
+        uint64_t log_base;
+
         hdev->log_size = vhost_get_log_size(hdev);
         hdev->log = hdev->log_size ?
             g_malloc0(hdev->log_size * sizeof *hdev->log) : NULL;
-        r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_LOG_BASE, hdev->log);
+        log_base = (uintptr_t)hdev->log;
+        r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_LOG_BASE, &log_base);
         if (r < 0) {
             r = -errno;
             goto fail_log;

hw/xen/xen_pt.c

@@ -388,7 +388,7 @@ static const MemoryRegionOps ops = {
     .write = xen_pt_bar_write,
 };
 
-static int xen_pt_register_regions(XenPCIPassthroughState *s)
+static int xen_pt_register_regions(XenPCIPassthroughState *s, uint16_t *cmd)
 {
     int i = 0;
     XenHostPCIDevice *d = &s->real_device;
@@ -406,6 +406,7 @@ static int xen_pt_register_regions(XenPCIPassthroughState *s)
 
         if (r->type & XEN_HOST_PCI_REGION_TYPE_IO) {
             type = PCI_BASE_ADDRESS_SPACE_IO;
+            *cmd |= PCI_COMMAND_IO;
         } else {
             type = PCI_BASE_ADDRESS_SPACE_MEMORY;
             if (r->type & XEN_HOST_PCI_REGION_TYPE_PREFETCH) {
@@ -414,6 +415,7 @@ static int xen_pt_register_regions(XenPCIPassthroughState *s)
             if (r->type & XEN_HOST_PCI_REGION_TYPE_MEM_64) {
                 type |= PCI_BASE_ADDRESS_MEM_TYPE_64;
             }
+            *cmd |= PCI_COMMAND_MEMORY;
         }
 
         memory_region_init_io(&s->bar[i], OBJECT(s), &ops, &s->dev,
@@ -638,6 +640,7 @@ static int xen_pt_initfn(PCIDevice *d)
     XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
     int rc = 0;
     uint8_t machine_irq = 0;
+    uint16_t cmd = 0;
     int pirq = XEN_PT_UNASSIGNED_PIRQ;
 
     /* register real device */
@@ -672,7 +675,7 @@ static int xen_pt_initfn(PCIDevice *d)
     s->io_listener = xen_pt_io_listener;
 
     /* Handle real device's MMIO/PIO BARs */
-    xen_pt_register_regions(s);
+    xen_pt_register_regions(s, &cmd);
 
     /* reinitialize each config register to be emulated */
     if (xen_pt_config_init(s)) {
@@ -736,6 +739,11 @@ static int xen_pt_initfn(PCIDevice *d)
     }
 
 out:
+    if (cmd) {
+        xen_host_pci_set_word(&s->real_device, PCI_COMMAND,
+                              pci_get_word(d->config + PCI_COMMAND) | cmd);
+    }
+
     memory_listener_register(&s->memory_listener, &s->dev.bus_master_as);
     memory_listener_register(&s->io_listener, &address_space_io);
     XEN_PT_LOG(d,

hw/xen/xen_pt_config_init.c

@@ -286,23 +286,6 @@ static int xen_pt_irqpin_reg_init(XenPCIPassthroughState *s,
 }
 
 /* Command register */
-static int xen_pt_cmd_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
-                               uint16_t *value, uint16_t valid_mask)
-{
-    XenPTRegInfo *reg = cfg_entry->reg;
-    uint16_t valid_emu_mask = 0;
-    uint16_t emu_mask = reg->emu_mask;
-
-    if (s->is_virtfn) {
-        emu_mask |= PCI_COMMAND_MEMORY;
-    }
-
-    /* emulate word register */
-    valid_emu_mask = emu_mask & valid_mask;
-    *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask);
-
-    return 0;
-}
 static int xen_pt_cmd_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
                                 uint16_t *val, uint16_t dev_value,
                                 uint16_t valid_mask)
@@ -310,18 +293,13 @@ static int xen_pt_cmd_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
     XenPTRegInfo *reg = cfg_entry->reg;
     uint16_t writable_mask = 0;
     uint16_t throughable_mask = 0;
-    uint16_t emu_mask = reg->emu_mask;
-
-    if (s->is_virtfn) {
-        emu_mask |= PCI_COMMAND_MEMORY;
-    }
 
     /* modify emulate register */
     writable_mask = ~reg->ro_mask & valid_mask;
     cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
 
     /* create value for writing to I/O device register */
-    throughable_mask = ~emu_mask & valid_mask;
+    throughable_mask = ~reg->emu_mask & valid_mask;
 
     if (*val & PCI_COMMAND_INTX_DISABLE) {
         throughable_mask |= PCI_COMMAND_INTX_DISABLE;
@@ -603,9 +581,9 @@ static XenPTRegInfo xen_pt_emu_reg_header0[] = {
         .size       = 2,
         .init_val   = 0x0000,
         .ro_mask    = 0xF880,
-        .emu_mask   = 0x0740,
+        .emu_mask   = 0x0743,
         .init       = xen_pt_common_reg_init,
-        .u.w.read   = xen_pt_cmd_reg_read,
+        .u.w.read   = xen_pt_word_reg_read,
         .u.w.write  = xen_pt_cmd_reg_write,
     },
     /* Capabilities Pointer reg */

include/block/block.h

@@ -361,6 +361,10 @@ bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs);
 bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
 int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num,
                               int nb_sectors, int *pnum);
+int64_t bdrv_get_block_status_above(BlockDriverState *bs,
+                                    BlockDriverState *base,
+                                    int64_t sector_num,
+                                    int nb_sectors, int *pnum);
 int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                       int *pnum);
 int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,

include/block/block_int.h

@@ -579,6 +579,7 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
  * @mode: Whether to collapse all images in the chain to the target.
  * @on_source_error: The action to take upon error reading from the source.
  * @on_target_error: The action to take upon error writing to the target.
+ * @unmap: Whether to unmap target where source sectors only contain zeroes.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
  * @errp: Error object.
@@ -593,6 +594,7 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                   int64_t speed, int64_t granularity, int64_t buf_size,
                   MirrorSyncMode mode, BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
+                  bool unmap,
                   BlockCompletionFunc *cb,
                   void *opaque, Error **errp);
 

include/hw/arm/stm32f205_soc.h

@@ -29,7 +29,7 @@
 #include "hw/timer/stm32f2xx_timer.h"
 #include "hw/char/stm32f2xx_usart.h"
 
-#define TYPE_STM32F205_SOC "stm32f205_soc"
+#define TYPE_STM32F205_SOC "stm32f205-soc"
 #define STM32F205_SOC(obj) \
     OBJECT_CHECK(STM32F205State, (obj), TYPE_STM32F205_SOC)
 

include/hw/virtio/vhost.h

@@ -36,7 +36,7 @@ struct vhost_dev {
     MemoryRegionSection *mem_sections;
     struct vhost_virtqueue *vqs;
     int nvqs;
-    /* the first virtuque which would be used by this vhost dev */
+    /* the first virtqueue which would be used by this vhost dev */
     int vq_index;
     unsigned long long features;
     unsigned long long acked_features;

include/hw/virtio/virtio-access.h

@@ -126,6 +126,15 @@ static inline uint64_t virtio_ldq_p(VirtIODevice *vdev, const void *ptr)
     }
 }
 
+static inline bool virtio_needs_swap(VirtIODevice *vdev)
+{
+#ifdef HOST_WORDS_BIGENDIAN
+    return virtio_access_is_big_endian(vdev) ? false : true;
+#else
+    return virtio_access_is_big_endian(vdev) ? true : false;
+#endif
+}
+
 static inline uint16_t virtio_tswap16(VirtIODevice *vdev, uint16_t s)
 {
 #ifdef HOST_WORDS_BIGENDIAN

include/hw/virtio/virtio-blk.h

@@ -67,6 +67,7 @@ typedef struct VirtIOBlockReq {
     struct virtio_blk_inhdr *in;
     struct virtio_blk_outhdr out;
     QEMUIOVector qiov;
+    size_t in_len;
     struct VirtIOBlockReq *next;
     struct VirtIOBlockReq *mr_next;
     BlockAcctCookie acct;

kvm-all.c

@@ -1142,9 +1142,17 @@ static int kvm_irqchip_get_virq(KVMState *s)
     uint32_t *word = s->used_gsi_bitmap;
     int max_words = ALIGN(s->gsi_count, 32) / 32;
     int i, bit;
-    bool retry = true;
 
-again:
+    /*
+     * PIC and IOAPIC share the first 16 GSI numbers, thus the available
+     * GSI numbers are more than the number of IRQ route. Allocating a GSI
+     * number can succeed even though a new route entry cannot be added.
+     * When this happens, flush dynamic MSI entries to free IRQ route entries.
+     */
+    if (!s->direct_msi && s->irq_routes->nr == s->gsi_count) {
+        kvm_flush_dynamic_msi_routes(s);
+    }
+
     /* Return the lowest unused GSI in the bitmap */
     for (i = 0; i < max_words; i++) {
         bit = ffs(~word[i]);
@@ -1154,11 +1162,6 @@ again:
 
         return bit - 1 + i * 32;
     }
-    if (!s->direct_msi && retry) {
-        retry = false;
-        kvm_flush_dynamic_msi_routes(s);
-        goto again;
-    }
     return -ENOSPC;
 
 }

nbd.c

@@ -681,7 +681,7 @@ int nbd_init(int fd, int csock, uint32_t flags, off_t size)
 
     TRACE("Setting size to %zd block(s)", (size_t)(size / BDRV_SECTOR_SIZE));
 
-    if (ioctl(fd, NBD_SET_SIZE_BLOCKS, size / (size_t)BDRV_SECTOR_SIZE) < 0) {
+    if (ioctl(fd, NBD_SET_SIZE_BLOCKS, (size_t)(size / BDRV_SECTOR_SIZE)) < 0) {
         int serrno = errno;
         LOG("Failed setting size (in blocks)");
         return -serrno;

qapi-schema.json

@@ -2669,6 +2669,7 @@
 # Since: 1.3.0
 #
 # 'unmapped' and 'pause' since 2.0
+# 'ro' and 'kp_comma' since 2.4
 ##
 { 'enum': 'QKeyCode',
   'data': [ 'unmapped',
@@ -2686,7 +2687,8 @@
             'kp_9', 'less', 'f11', 'f12', 'print', 'home', 'pgup', 'pgdn', 'end',
             'left', 'up', 'down', 'right', 'insert', 'delete', 'stop', 'again',
             'props', 'undo', 'front', 'copy', 'open', 'paste', 'find', 'cut',
-             'lf', 'help', 'meta_l', 'meta_r', 'compose', 'pause' ] }
+            'lf', 'help', 'meta_l', 'meta_r', 'compose', 'pause', 'ro',
+            'kp_comma' ] }
 
 ##
 # @KeyValue

qapi/block-core.json

@@ -943,6 +943,11 @@
 # @on-target-error: #optional the action to take on an error on the target,
 #                   default 'report' (no limitations, since this applies to
 #                   a different block device than @device).
+# @unmap: #optional Whether to try to unmap target sectors where source has
+#         only zero. If true, and target unallocated sectors will read as zero,
+#         target image sectors will be unmapped; otherwise, zeroes will be
+#         written. Both will result in identical contents.
+#         Default is true. (Since 2.4)
 #
 # Returns: nothing on success
 #          If @device is not a valid block device, DeviceNotFound
@@ -955,7 +960,8 @@
             'sync': 'MirrorSyncMode', '*mode': 'NewImageMode',
             '*speed': 'int', '*granularity': 'uint32',
             '*buf-size': 'int', '*on-source-error': 'BlockdevOnError',
-            '*on-target-error': 'BlockdevOnError' } }
+            '*on-target-error': 'BlockdevOnError',
+            '*unmap': 'bool' } }
 
 ##
 # @block_set_io_throttle:

qemu-char.c

@@ -2797,7 +2797,10 @@ static ssize_t tcp_chr_recv(CharDriverState *chr, char *buf, size_t len)
 #ifdef MSG_CMSG_CLOEXEC
     flags |= MSG_CMSG_CLOEXEC;
 #endif
-    ret = recvmsg(s->fd, &msg, flags);
+    do {
+        ret = recvmsg(s->fd, &msg, flags);
+    } while (ret == -1 && errno == EINTR);
+
     if (ret > 0 && s->is_unix) {
         unix_process_msgfd(chr, &msg);
     }
@@ -2808,7 +2811,13 @@ static ssize_t tcp_chr_recv(CharDriverState *chr, char *buf, size_t len)
 static ssize_t tcp_chr_recv(CharDriverState *chr, char *buf, size_t len)
 {
     TCPCharDriver *s = chr->opaque;
-    return qemu_recv(s->fd, buf, len, 0);
+    ssize_t ret;
+
+    do {
+        ret = qemu_recv(s->fd, buf, len, 0);
+    } while (ret == -1 && socket_error() == EINTR);
+
+    return ret;
 }
 #endif
 

qga/commands-posix.c

@@ -1332,11 +1332,7 @@ void qmp_guest_fstrim(bool has_minimum, int64_t minimum, Error **errp)
     struct FsMount *mount;
     int fd;
     Error *local_err = NULL;
-    struct fstrim_range r = {
-        .start = 0,
-        .len = -1,
-        .minlen = has_minimum ? minimum : 0,
-    };
+    struct fstrim_range r;
 
     slog("guest-fstrim called");
 
@@ -1360,6 +1356,9 @@ void qmp_guest_fstrim(bool has_minimum, int64_t minimum, Error **errp)
          * error means an unexpected error, so return it in those cases.  In
          * some other cases ENOTTY will be reported (e.g. CD-ROMs).
          */
+        r.start = 0;
+        r.len = -1;
+        r.minlen = has_minimum ? minimum : 0;
         ret = ioctl(fd, FITRIM, &r);
         if (ret == -1) {
             if (errno != ENOTTY && errno != EOPNOTSUPP) {

qmp-commands.hx

@@ -1380,6 +1380,7 @@ EQMP
         .args_type  = "sync:s,device:B,target:s,speed:i?,mode:s?,format:s?,"
                       "node-name:s?,replaces:s?,"
                       "on-source-error:s?,on-target-error:s?,"
+                      "unmap:b?,"
                       "granularity:i?,buf-size:i?",
         .mhandler.cmd_new = qmp_marshal_input_drive_mirror,
     },
@@ -1419,6 +1420,8 @@ Arguments:
   (BlockdevOnError, default 'report')
 - "on-target-error": the action to take on an error on the target
   (BlockdevOnError, default 'report')
+- "unmap": whether the target sectors should be discarded where source has only
+  zeroes. (json-bool, optional, default true)
 
 The default value of the granularity is the image cluster size clamped
 between 4096 and 65536, if the image format defines one.  If the format

scripts/qmp/qmp.py

@@ -21,6 +21,9 @@ class QMPConnectError(QMPError):
 class QMPCapabilitiesError(QMPError):
     pass
 
+class QMPTimeoutError(QMPError):
+    pass
+
 class QEMUMonitorProtocol:
     def __init__(self, address, server=False):
         """
@@ -72,6 +75,44 @@ class QEMUMonitorProtocol:
 
     error = socket.error
 
+    def __get_events(self, wait=False):
+        """
+        Check for new events in the stream and cache them in __events.
+
+        @param wait (bool): block until an event is available.
+        @param wait (float): If wait is a float, treat it as a timeout value.
+
+        @raise QMPTimeoutError: If a timeout float is provided and the timeout
+                                period elapses.
+        @raise QMPConnectError: If wait is True but no events could be retrieved
+                                or if some other error occurred.
+        """
+
+        # Check for new events regardless and pull them into the cache:
+        self.__sock.setblocking(0)
+        try:
+            self.__json_read()
+        except socket.error, err:
+            if err[0] == errno.EAGAIN:
+                # No data available
+                pass
+        self.__sock.setblocking(1)
+
+        # Wait for new events, if needed.
+        # if wait is 0.0, this means "no wait" and is also implicitly false.
+        if not self.__events and wait:
+            if isinstance(wait, float):
+                self.__sock.settimeout(wait)
+            try:
+                ret = self.__json_read(only_event=True)
+            except socket.timeout:
+                raise QMPTimeoutError("Timeout waiting for event")
+            except:
+                raise QMPConnectError("Error while reading from socket")
+            if ret is None:
+                raise QMPConnectError("Error while reading from socket")
+            self.__sock.settimeout(None)
+
     def connect(self, negotiate=True):
         """
         Connect to the QMP Monitor and perform capabilities negotiation.
@@ -140,43 +181,37 @@ class QEMUMonitorProtocol:
         """
         Get and delete the first available QMP event.
 
-        @param wait: block until an event is available (bool)
+        @param wait (bool): block until an event is available.
+        @param wait (float): If wait is a float, treat it as a timeout value.
+
+        @raise QMPTimeoutError: If a timeout float is provided and the timeout
+                                period elapses.
+        @raise QMPConnectError: If wait is True but no events could be retrieved
+                                or if some other error occurred.
+
+        @return The first available QMP event, or None.
         """
-        self.__sock.setblocking(0)
-        try:
-            self.__json_read()
-        except socket.error, err:
-            if err[0] == errno.EAGAIN:
-                # No data available
-                pass
-        self.__sock.setblocking(1)
-        if not self.__events and wait:
-            self.__json_read(only_event=True)
-        event = self.__events[0]
-        del self.__events[0]
-        return event
+        self.__get_events(wait)
+
+        if self.__events:
+            return self.__events.pop(0)
+        return None
 
     def get_events(self, wait=False):
         """
         Get a list of available QMP events.
 
-        @param wait: block until an event is available (bool)
-        """
-        self.__sock.setblocking(0)
-        try:
-            self.__json_read()
-        except socket.error, err:
-            if err[0] == errno.EAGAIN:
-                # No data available
-                pass
-        self.__sock.setblocking(1)
-        if not self.__events and wait:
-            ret = self.__json_read(only_event=True)
-            if ret == None:
-                # We are in blocking mode, if don't get anything, something
-                # went wrong
-                raise QMPConnectError("Error while reading from socket")
+        @param wait (bool): block until an event is available.
+        @param wait (float): If wait is a float, treat it as a timeout value.
 
+        @raise QMPTimeoutError: If a timeout float is provided and the timeout
+                                period elapses.
+        @raise QMPConnectError: If wait is True but no events could be retrieved
+                                or if some other error occurred.
+
+        @return The list of available QMP events.
+        """
+        self.__get_events(wait)
         return self.__events
 
     def clear_events(self):

target-arm/translate.c

@@ -8423,18 +8423,53 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
                 }
             } else {
                 int address_offset;
-                int load;
+                bool load = insn & (1 << 20);
+                bool doubleword = false;
                 /* Misc load/store */
                 rn = (insn >> 16) & 0xf;
                 rd = (insn >> 12) & 0xf;
+
+                if (!load && (sh & 2)) {
+                    /* doubleword */
+                    ARCH(5TE);
+                    if (rd & 1) {
+                        /* UNPREDICTABLE; we choose to UNDEF */
+                        goto illegal_op;
+                    }
+                    load = (sh & 1) == 0;
+                    doubleword = true;
+                }
+
                 addr = load_reg(s, rn);
                 if (insn & (1 << 24))
                     gen_add_datah_offset(s, insn, 0, addr);
                 address_offset = 0;
-                if (insn & (1 << 20)) {
+
+                if (doubleword) {
+                    if (!load) {
+                        /* store */
+                        tmp = load_reg(s, rd);
+                        gen_aa32_st32(tmp, addr, get_mem_index(s));
+                        tcg_temp_free_i32(tmp);
+                        tcg_gen_addi_i32(addr, addr, 4);
+                        tmp = load_reg(s, rd + 1);
+                        gen_aa32_st32(tmp, addr, get_mem_index(s));
+                        tcg_temp_free_i32(tmp);
+                    } else {
+                        /* load */
+                        tmp = tcg_temp_new_i32();
+                        gen_aa32_ld32u(tmp, addr, get_mem_index(s));
+                        store_reg(s, rd, tmp);
+                        tcg_gen_addi_i32(addr, addr, 4);
+                        tmp = tcg_temp_new_i32();
+                        gen_aa32_ld32u(tmp, addr, get_mem_index(s));
+                        rd++;
+                    }
+                    address_offset = -4;
+                } else if (load) {
                     /* load */
                     tmp = tcg_temp_new_i32();
-                    switch(sh) {
+                    switch (sh) {
                     case 1:
                         gen_aa32_ld16u(tmp, addr, get_mem_index(s));
                         break;
@@ -8446,38 +8481,11 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
                         gen_aa32_ld16s(tmp, addr, get_mem_index(s));
                         break;
                     }
-                    load = 1;
-                } else if (sh & 2) {
-                    ARCH(5TE);
-                    /* doubleword */
-                    if (sh & 1) {
-                        /* store */
-                        tmp = load_reg(s, rd);
-                        gen_aa32_st32(tmp, addr, get_mem_index(s));
-                        tcg_temp_free_i32(tmp);
-                        tcg_gen_addi_i32(addr, addr, 4);
-                        tmp = load_reg(s, rd + 1);
-                        gen_aa32_st32(tmp, addr, get_mem_index(s));
-                        tcg_temp_free_i32(tmp);
-                        load = 0;
-                    } else {
-                        /* load */
-                        tmp = tcg_temp_new_i32();
-                        gen_aa32_ld32u(tmp, addr, get_mem_index(s));
-                        store_reg(s, rd, tmp);
-                        tcg_gen_addi_i32(addr, addr, 4);
-                        tmp = tcg_temp_new_i32();
-                        gen_aa32_ld32u(tmp, addr, get_mem_index(s));
-                        rd++;
-                        load = 1;
-                    }
-                    address_offset = -4;
                 } else {
                     /* store */
                     tmp = load_reg(s, rd);
                     gen_aa32_st16(tmp, addr, get_mem_index(s));
                     tcg_temp_free_i32(tmp);
-                    load = 0;
                 }
                 /* Perform base writeback before the loaded value to
                    ensure correct behavior with overlapping index registers.

target-i386/cpu.h

@@ -31,8 +31,6 @@
 /* Maximum instruction code size */
 #define TARGET_MAX_INSN_SIZE 16
 
-/* target supports implicit self modifying code */
-#define TARGET_HAS_SMC
 /* support for self modifying code even if the modified instruction is
    close to the modifying instruction */
 #define TARGET_HAS_PRECISE_SMC

target-mips/kvm.c

@@ -240,10 +240,9 @@ int kvm_mips_set_ipi_interrupt(MIPSCPU *cpu, int irq, int level)
 static inline int kvm_mips_put_one_reg(CPUState *cs, uint64_t reg_id,
                                        int32_t *addr)
 {
-    uint64_t val64 = *addr;
     struct kvm_one_reg cp0reg = {
         .id = reg_id,
-        .addr = (uintptr_t)&val64
+        .addr = (uintptr_t)addr
     };
 
     return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &cp0reg);
@@ -275,18 +274,12 @@ static inline int kvm_mips_put_one_reg64(CPUState *cs, uint64_t reg_id,
 static inline int kvm_mips_get_one_reg(CPUState *cs, uint64_t reg_id,
                                        int32_t *addr)
 {
-    int ret;
-    uint64_t val64 = 0;
     struct kvm_one_reg cp0reg = {
         .id = reg_id,
-        .addr = (uintptr_t)&val64
+        .addr = (uintptr_t)addr
     };
 
-    ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &cp0reg);
-    if (ret >= 0) {
-        *addr = val64;
-    }
-    return ret;
+    return kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &cp0reg);
 }
 
 static inline int kvm_mips_get_one_ulreg(CPUState *cs, uint64 reg_id,
@@ -640,12 +633,12 @@ int kvm_arch_put_registers(CPUState *cs, int level)
 
     /* Set the registers based on QEMU's view of things */
     for (i = 0; i < 32; i++) {
-        regs.gpr[i] = env->active_tc.gpr[i];
+        regs.gpr[i] = (int64_t)(target_long)env->active_tc.gpr[i];
     }
 
-    regs.hi = env->active_tc.HI[0];
-    regs.lo = env->active_tc.LO[0];
-    regs.pc = env->active_tc.PC;
+    regs.hi = (int64_t)(target_long)env->active_tc.HI[0];
+    regs.lo = (int64_t)(target_long)env->active_tc.LO[0];
+    regs.pc = (int64_t)(target_long)env->active_tc.PC;
 
     ret = kvm_vcpu_ioctl(cs, KVM_SET_REGS, &regs);
 

target-ppc/kvm.c

@@ -39,6 +39,7 @@
 #include "sysemu/watchdog.h"
 #include "trace.h"
 #include "exec/gdbstub.h"
+#include "sysemu/hostmem.h"
 
 //#define DEBUG_KVM
 
@@ -302,16 +303,11 @@ static void kvm_get_smmu_info(PowerPCCPU *cpu, struct kvm_ppc_smmu_info *info)
     kvm_get_fallback_smmu_info(cpu, info);
 }
 
-static long getrampagesize(void)
+static long gethugepagesize(const char *mem_path)
 {
     struct statfs fs;
     int ret;
 
-    if (!mem_path) {
-        /* guest RAM is backed by normal anonymous pages */
-        return getpagesize();
-    }
-
     do {
         ret = statfs(mem_path, &fs);
     } while (ret != 0 && errno == EINTR);
@@ -333,6 +329,55 @@ static long getrampagesize(void)
     return fs.f_bsize;
 }
 
+static int find_max_supported_pagesize(Object *obj, void *opaque)
+{
+    char *mem_path;
+    long *hpsize_min = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) {
+        mem_path = object_property_get_str(obj, "mem-path", NULL);
+        if (mem_path) {
+            long hpsize = gethugepagesize(mem_path);
+            if (hpsize < *hpsize_min) {
+                *hpsize_min = hpsize;
+            }
+        } else {
+            *hpsize_min = getpagesize();
+        }
+    }
+
+    return 0;
+}
+
+static long getrampagesize(void)
+{
+    long hpsize = LONG_MAX;
+    Object *memdev_root;
+
+    if (mem_path) {
+        return gethugepagesize(mem_path);
+    }
+
+    /* it's possible we have memory-backend objects with
+     * hugepage-backed RAM. these may get mapped into system
+     * address space via -numa parameters or memory hotplug
+     * hooks. we want to take these into account, but we
+     * also want to make sure these supported hugepage
+     * sizes are applicable across the entire range of memory
+     * we may boot from, so we take the min across all
+     * backends, and assume normal pages in cases where a
+     * backend isn't backed by hugepages.
+     */
+    memdev_root = object_resolve_path("/objects", NULL);
+    if (!memdev_root) {
+        return getpagesize();
+    }
+
+    object_child_foreach(memdev_root, find_max_supported_pagesize, &hpsize);
+
+    return (hpsize == LONG_MAX) ? getpagesize() : hpsize;
+}
+
 static bool kvm_valid_page_size(uint32_t flags, long rampgsize, uint32_t shift)
 {
     if (!(flags & KVM_PPC_PAGE_SIZES_REAL)) {

target-ppc/machine.c

@@ -192,9 +192,9 @@ static int cpu_post_load(void *opaque, int version_id)
         ppc_store_sdr1(env, env->spr[SPR_SDR1]);
     }
 
-    /* Mark msr bits except MSR_TGPR invalid before restoring */
+    /* Invalidate all msr bits except MSR_TGPR/MSR_HVB before restoring */
     msr = env->msr;
-    env->msr ^= ~(1ULL << MSR_TGPR);
+    env->msr ^= ~((1ULL << MSR_TGPR) | MSR_HVB);
     ppc_store_msr(env, msr);
 
     hreg_compute_mem_idx(env);

target-tricore/op_helper.c

@@ -2573,7 +2573,7 @@ void helper_rslcx(CPUTriCoreState *env)
         /* CSU trap */
     }
     /* if (PCXI.UL == 1) then trap(CTYP); */
-    if ((env->PCXI & MASK_PCXI_UL) == 1) {
+    if ((env->PCXI & MASK_PCXI_UL) != 0) {
         /* CTYP trap */
     }
     /* EA = {PCXI.PCXS, 6'b0, PCXI.PCXO, 6'b0}; */

tcg/mips/tcg-target.c

@@ -963,9 +963,11 @@ static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
     }
 
     /* Load the tlb comparator.  */
-    tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, TCG_REG_A0, cmp_off + LO_OFF);
     if (TARGET_LONG_BITS == 64) {
+        tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, TCG_REG_A0, cmp_off + LO_OFF);
         tcg_out_opc_imm(s, OPC_LW, base, TCG_REG_A0, cmp_off + HI_OFF);
+    } else {
+        tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, TCG_REG_A0, cmp_off);
     }
 
     /* Mask the page bits, keeping the alignment bits to compare against.
@@ -1267,6 +1269,9 @@ static void tcg_out_addsub2(TCGContext *s, TCGReg rl, TCGReg rh, TCGReg al,
         if (cbl) {
             tcg_out_opc_imm(s, OPC_ADDIU, rl, al, bl);
             tcg_out_opc_imm(s, OPC_SLTIU, TCG_TMP0, rl, bl);
+        } else if (rl == al && rl == bl) {
+            tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, al, 31);
+            tcg_out_opc_reg(s, OPC_ADDU, rl, al, bl);
         } else {
             tcg_out_opc_reg(s, OPC_ADDU, rl, al, bl);
             tcg_out_opc_reg(s, OPC_SLTU, TCG_TMP0, rl, (rl == bl ? al : bl));

tcg/tcg-op.c

@@ -808,7 +808,7 @@ void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
 {
     /* Since arg2 and ret have different types,
        they cannot be the same temporary */
-#ifdef TCG_TARGET_WORDS_BIGENDIAN
+#ifdef HOST_WORDS_BIGENDIAN
     tcg_gen_ld_i32(TCGV_HIGH(ret), arg2, offset);
     tcg_gen_ld_i32(TCGV_LOW(ret), arg2, offset + 4);
 #else
@@ -819,7 +819,7 @@ void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
 
 void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset)
 {
-#ifdef TCG_TARGET_WORDS_BIGENDIAN
+#ifdef HOST_WORDS_BIGENDIAN
     tcg_gen_st_i32(TCGV_HIGH(arg1), arg2, offset);
     tcg_gen_st_i32(TCGV_LOW(arg1), arg2, offset + 4);
 #else

tests/qemu-iotests/033

@@ -78,6 +78,19 @@ for align in 512 4k; do
 	echo
 	echo "== verifying patterns (2) =="
 	do_test $align "read -P 0x0 0x400 0x20000" "$TEST_IMG" | _filter_qemu_io
+
+	echo
+	echo "== rewriting unaligned zeroes =="
+	do_test $align "write -P 0xb 0x0 0x1000" "$TEST_IMG" | _filter_qemu_io
+	do_test $align "write -z 0x200 0x200" "$TEST_IMG" | _filter_qemu_io
+
+	echo
+	echo "== verifying patterns (3) =="
+	do_test $align "read -P 0xb 0x0 0x200" "$TEST_IMG" | _filter_qemu_io
+	do_test $align "read -P 0x0 0x200 0x200" "$TEST_IMG" | _filter_qemu_io
+	do_test $align "read -P 0xb 0x400 0xc00" "$TEST_IMG" | _filter_qemu_io
+
+	echo
 done
 
 # success, all done

tests/qemu-iotests/033.out

@@ -27,6 +27,21 @@ wrote 65536/65536 bytes at offset 65536
 read 131072/131072 bytes at offset 1024
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 
+== rewriting unaligned zeroes ==
+wrote 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 512/512 bytes at offset 512
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== verifying patterns (3) ==
+read 512/512 bytes at offset 0
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 512/512 bytes at offset 512
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 3072/3072 bytes at offset 1024
+3 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+
 == preparing image ==
 wrote 1024/1024 bytes at offset 512
 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
@@ -52,4 +67,19 @@ wrote 65536/65536 bytes at offset 65536
 == verifying patterns (2) ==
 read 131072/131072 bytes at offset 1024
 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== rewriting unaligned zeroes ==
+wrote 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+wrote 512/512 bytes at offset 512
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== verifying patterns (3) ==
+read 512/512 bytes at offset 0
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 512/512 bytes at offset 512
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+read 3072/3072 bytes at offset 1024
+3 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
 *** done

tests/qemu-iotests/041

@@ -34,38 +34,8 @@ quorum_img3 = os.path.join(iotests.test_dir, 'quorum3.img')
 quorum_repair_img = os.path.join(iotests.test_dir, 'quorum_repair.img')
 quorum_snapshot_file = os.path.join(iotests.test_dir, 'quorum_snapshot.img')
 
-class ImageMirroringTestCase(iotests.QMPTestCase):
-    '''Abstract base class for image mirroring test cases'''
 
-    def wait_ready(self, drive='drive0'):
-        '''Wait until a block job BLOCK_JOB_READY event'''
-        ready = False
-        while not ready:
-            for event in self.vm.get_qmp_events(wait=True):
-                if event['event'] == 'BLOCK_JOB_READY':
-                    self.assert_qmp(event, 'data/type', 'mirror')
-                    self.assert_qmp(event, 'data/device', drive)
-                    ready = True
-
-    def wait_ready_and_cancel(self, drive='drive0'):
-        self.wait_ready(drive=drive)
-        event = self.cancel_and_wait(drive=drive)
-        self.assertEquals(event['event'], 'BLOCK_JOB_COMPLETED')
-        self.assert_qmp(event, 'data/type', 'mirror')
-        self.assert_qmp(event, 'data/offset', event['data']['len'])
-
-    def complete_and_wait(self, drive='drive0', wait_ready=True):
-        '''Complete a block job and wait for it to finish'''
-        if wait_ready:
-            self.wait_ready(drive=drive)
-
-        result = self.vm.qmp('block-job-complete', device=drive)
-        self.assert_qmp(result, 'return', {})
-
-        event = self.wait_until_completed(drive=drive)
-        self.assert_qmp(event, 'data/type', 'mirror')
-
-class TestSingleDrive(ImageMirroringTestCase):
+class TestSingleDrive(iotests.QMPTestCase):
     image_len = 1 * 1024 * 1024 # MB
 
     def setUp(self):
@@ -221,17 +191,9 @@ class TestSingleDriveUnalignedLength(TestSingleDrive):
     test_small_buffer2 = None
     test_large_cluster = None
 
-class TestMirrorNoBacking(ImageMirroringTestCase):
+class TestMirrorNoBacking(iotests.QMPTestCase):
     image_len = 2 * 1024 * 1024 # MB
 
-    def complete_and_wait(self, drive='drive0', wait_ready=True):
-        iotests.create_image(target_backing_img, TestMirrorNoBacking.image_len)
-        return ImageMirroringTestCase.complete_and_wait(self, drive, wait_ready)
-
-    def compare_images(self, img1, img2):
-        iotests.create_image(target_backing_img, TestMirrorNoBacking.image_len)
-        return iotests.compare_images(img1, img2)
-
     def setUp(self):
         iotests.create_image(backing_img, TestMirrorNoBacking.image_len)
         qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % backing_img, test_img)
@@ -242,7 +204,10 @@ class TestMirrorNoBacking(ImageMirroringTestCase):
         self.vm.shutdown()
         os.remove(test_img)
         os.remove(backing_img)
-        os.remove(target_backing_img)
+        try:
+            os.remove(target_backing_img)
+        except:
+            pass
         os.remove(target_img)
 
     def test_complete(self):
@@ -257,7 +222,7 @@ class TestMirrorNoBacking(ImageMirroringTestCase):
         result = self.vm.qmp('query-block')
         self.assert_qmp(result, 'return[0]/inserted/file', target_img)
         self.vm.shutdown()
-        self.assertTrue(self.compare_images(test_img, target_img),
+        self.assertTrue(iotests.compare_images(test_img, target_img),
                         'target image does not match source after mirroring')
 
     def test_cancel(self):
@@ -272,7 +237,7 @@ class TestMirrorNoBacking(ImageMirroringTestCase):
         result = self.vm.qmp('query-block')
         self.assert_qmp(result, 'return[0]/inserted/file', test_img)
         self.vm.shutdown()
-        self.assertTrue(self.compare_images(test_img, target_img),
+        self.assertTrue(iotests.compare_images(test_img, target_img),
                         'target image does not match source after mirroring')
 
     def test_large_cluster(self):
@@ -283,7 +248,6 @@ class TestMirrorNoBacking(ImageMirroringTestCase):
                         %(TestMirrorNoBacking.image_len), target_backing_img)
         qemu_img('create', '-f', iotests.imgfmt, '-o', 'cluster_size=%d,backing_file=%s'
                         % (TestMirrorNoBacking.image_len, target_backing_img), target_img)
-        os.remove(target_backing_img)
 
         result = self.vm.qmp('drive-mirror', device='drive0', sync='full',
                              mode='existing', target=target_img)
@@ -293,10 +257,10 @@ class TestMirrorNoBacking(ImageMirroringTestCase):
         result = self.vm.qmp('query-block')
         self.assert_qmp(result, 'return[0]/inserted/file', target_img)
         self.vm.shutdown()
-        self.assertTrue(self.compare_images(test_img, target_img),
+        self.assertTrue(iotests.compare_images(test_img, target_img),
                         'target image does not match source after mirroring')
 
-class TestMirrorResized(ImageMirroringTestCase):
+class TestMirrorResized(iotests.QMPTestCase):
     backing_len = 1 * 1024 * 1024 # MB
     image_len = 2 * 1024 * 1024 # MB
 
@@ -344,7 +308,7 @@ class TestMirrorResized(ImageMirroringTestCase):
         self.assertTrue(iotests.compare_images(test_img, target_img),
                         'target image does not match source after mirroring')
 
-class TestReadErrors(ImageMirroringTestCase):
+class TestReadErrors(iotests.QMPTestCase):
     image_len = 2 * 1024 * 1024 # MB
 
     # this should be a multiple of twice the default granularity
@@ -498,7 +462,7 @@ new_state = "1"
         self.assert_no_active_block_jobs()
         self.vm.shutdown()
 
-class TestWriteErrors(ImageMirroringTestCase):
+class TestWriteErrors(iotests.QMPTestCase):
     image_len = 2 * 1024 * 1024 # MB
 
     # this should be a multiple of twice the default granularity
@@ -624,7 +588,7 @@ new_state = "1"
         self.assert_no_active_block_jobs()
         self.vm.shutdown()
 
-class TestSetSpeed(ImageMirroringTestCase):
+class TestSetSpeed(iotests.QMPTestCase):
     image_len = 80 * 1024 * 1024 # MB
 
     def setUp(self):
@@ -690,7 +654,7 @@ class TestSetSpeed(ImageMirroringTestCase):
 
         self.wait_ready_and_cancel()
 
-class TestUnbackedSource(ImageMirroringTestCase):
+class TestUnbackedSource(iotests.QMPTestCase):
     image_len = 2 * 1024 * 1024 # MB
 
     def setUp(self):
@@ -731,7 +695,7 @@ class TestUnbackedSource(ImageMirroringTestCase):
         self.complete_and_wait()
         self.assert_no_active_block_jobs()
 
-class TestRepairQuorum(ImageMirroringTestCase):
+class TestRepairQuorum(iotests.QMPTestCase):
     """ This class test quorum file repair using drive-mirror.
         It's mostly a fork of TestSingleDrive """
     image_len = 1 * 1024 * 1024 # MB

tests/qemu-iotests/103

@@ -93,6 +93,16 @@ $QEMU_IO -c "open -o l2-cache-size=1M,refcount-cache-size=0.25M $TEST_IMG" \
          -c 'read -P 42 0 64k' \
     | _filter_qemu_io
 
+echo
+echo '=== Testing minimal L2 cache and COW ==='
+echo
+
+$QEMU_IMG snapshot -c foo "$TEST_IMG"
+# This requires a COW operation, which accesses two L2 tables simultaneously
+# (COW source and destination), so there must be enough space in the cache to
+# place both tables there (and qemu should not crash)
+$QEMU_IO -c "open -o cache-size=0 $TEST_IMG" -c 'write 0 64k' | _filter_qemu_io
+
 # success, all done
 echo '*** done'
 rm -f $seq.full

tests/qemu-iotests/103.out

@@ -26,4 +26,9 @@ read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+=== Testing minimal L2 cache and COW ===
+
+wrote 65536/65536 bytes at offset 0
+64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 *** done

tests/qemu-iotests/130

@@ -0,0 +1,95 @@
+#!/bin/bash
+#
+# Test that temporary backing file overrides (on the command line or in
+# blockdev-add) don't replace the original path stored in the image during
+# header updates.
+#
+# Copyright (C) 2015 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=kwolf@redhat.com
+
+seq="$(basename $0)"
+echo "QA output created by $seq"
+
+here="$PWD"
+tmp=/tmp/$$
+status=1	# failure is the default!
+
+_cleanup()
+{
+    _cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+. ./common.qemu
+
+_supported_fmt qcow2
+_supported_proto generic
+_supported_os Linux
+
+qemu_comm_method="monitor"
+
+
+TEST_IMG="$TEST_IMG.orig" _make_test_img 64M
+TEST_IMG="$TEST_IMG.base" _make_test_img 64M
+_make_test_img 64M
+_img_info | _filter_img_info
+
+echo
+echo "=== HMP commit ==="
+echo
+# bdrv_make_empty() involves a header update for qcow2
+
+# Test that a backing file isn't written
+_launch_qemu -drive file="$TEST_IMG",backing.file.filename="$TEST_IMG.base"
+_send_qemu_cmd $QEMU_HANDLE "commit ide0-hd0" "(qemu)"
+_send_qemu_cmd $QEMU_HANDLE '' '(qemu)'
+_cleanup_qemu
+_img_info | _filter_img_info
+
+# Make sure that if there was a backing file that was just overridden on the
+# command line, that backing file is retained, with the right format
+_make_test_img -F raw -b "$TEST_IMG.orig" 64M
+_launch_qemu -drive file="$TEST_IMG",backing.file.filename="$TEST_IMG.base",backing.driver=$IMGFMT
+_send_qemu_cmd $QEMU_HANDLE "commit ide0-hd0" "(qemu)"
+_send_qemu_cmd $QEMU_HANDLE '' '(qemu)'
+_cleanup_qemu
+_img_info | _filter_img_info
+
+echo
+echo "=== Marking image dirty (lazy refcounts) ==="
+echo
+
+# Test that a backing file isn't written
+_make_test_img 64M
+$QEMU_IO -c "open -o backing.file.filename=$TEST_IMG.base,lazy-refcounts=on $TEST_IMG" -c "write 0 4k" | _filter_qemu_io
+_img_info | _filter_img_info
+
+# Make sure that if there was a backing file that was just overridden on the
+# command line, that backing file is retained, with the right format
+_make_test_img -F raw -b "$TEST_IMG.orig" 64M
+$QEMU_IO -c "open -o backing.file.filename=$TEST_IMG.base,backing.driver=$IMGFMT,lazy-refcounts=on $TEST_IMG" -c "write 0 4k" | _filter_qemu_io
+_img_info | _filter_img_info
+
+# success, all done
+echo '*** done'
+rm -f $seq.full
+status=0

tests/qemu-iotests/130.out

@@ -0,0 +1,43 @@
+QA output created by 130
+Formatting 'TEST_DIR/t.IMGFMT.orig', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
+image: TEST_DIR/t.IMGFMT
+file format: IMGFMT
+virtual size: 64M (67108864 bytes)
+
+=== HMP commit ===
+
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) ccocomcommcommicommitcommit commit icommit idcommit idecommit ide0commit ide0-commit ide0-hcommit ide0-hdcommit ide0-hd0
+(qemu) 
+image: TEST_DIR/t.IMGFMT
+file format: IMGFMT
+virtual size: 64M (67108864 bytes)
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.orig' backing_fmt='raw'
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) ccocomcommcommicommitcommit commit icommit idcommit idecommit ide0commit ide0-commit ide0-hcommit ide0-hdcommit ide0-hd0
+(qemu) 
+image: TEST_DIR/t.IMGFMT
+file format: IMGFMT
+virtual size: 64M (67108864 bytes)
+backing file: TEST_DIR/t.IMGFMT.orig
+backing file format: raw
+
+=== Marking image dirty (lazy refcounts) ===
+
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864
+wrote 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+image: TEST_DIR/t.IMGFMT
+file format: IMGFMT
+virtual size: 64M (67108864 bytes)
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file='TEST_DIR/t.IMGFMT.orig' backing_fmt='raw'
+wrote 4096/4096 bytes at offset 0
+4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+image: TEST_DIR/t.IMGFMT
+file format: IMGFMT
+virtual size: 64M (67108864 bytes)
+backing file: TEST_DIR/t.IMGFMT.orig
+backing file format: raw
+*** done

tests/qemu-iotests/132

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+#
+# Test mirror with unmap
+#
+# Copyright (C) 2015 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+import time
+import os
+import iotests
+from iotests import qemu_img, qemu_io
+
+test_img = os.path.join(iotests.test_dir, 'test.img')
+target_img = os.path.join(iotests.test_dir, 'target.img')
+
+class TestSingleDrive(iotests.QMPTestCase):
+    image_len = 2 * 1024 * 1024 # MB
+
+    def setUp(self):
+        # Write data to the image so we can compare later
+        qemu_img('create', '-f', iotests.imgfmt, test_img, str(TestSingleDrive.image_len))
+        qemu_io('-f', iotests.imgfmt, '-c', 'write -P0x5d 0 2M', test_img)
+
+        self.vm = iotests.VM().add_drive(test_img, 'discard=unmap')
+        self.vm.launch()
+
+    def tearDown(self):
+        self.vm.shutdown()
+        os.remove(test_img)
+        try:
+            os.remove(target_img)
+        except OSError:
+            pass
+
+    def test_mirror_discard(self):
+        result = self.vm.qmp('drive-mirror', device='drive0', sync='full',
+                             target=target_img)
+        self.assert_qmp(result, 'return', {})
+        self.vm.hmp_qemu_io('drive0', 'discard 0 64k')
+        self.complete_and_wait('drive0')
+        self.vm.shutdown()
+        self.assertTrue(iotests.compare_images(test_img, target_img),
+                        'target image does not match source after mirroring')
+
+if __name__ == '__main__':
+    iotests.main(supported_fmts=['raw', 'qcow2'])

tests/qemu-iotests/132.out

@@ -0,0 +1,5 @@
+.
+----------------------------------------------------------------------
+Ran 1 tests
+
+OK

tests/qemu-iotests/135

@@ -0,0 +1,54 @@
+#!/bin/bash
+#
+# Test VPC open of image with large Max Table Entries value.
+#
+# Copyright (C) 2015 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=jcody@redhat.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+here=`pwd`
+tmp=/tmp/$$
+status=1	# failure is the default!
+
+_cleanup()
+{
+    _cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+
+_supported_fmt vpc
+_supported_proto generic
+_supported_os Linux
+
+_use_sample_img afl5.img.bz2
+
+echo
+echo "=== Verify image open and failure ===="
+$QEMU_IMG info "$TEST_IMG" 2>&1| _filter_testdir
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0

tests/qemu-iotests/135.out

@@ -0,0 +1,5 @@
+QA output created by 135
+
+=== Verify image open and failure ====
+qemu-img: Could not open 'TEST_DIR/afl5.img': Max Table Entries too large (1073741825)
+*** done

tests/qemu-iotests/group

@@ -124,3 +124,6 @@
 121 rw auto
 123 rw auto quick
 128 rw auto quick
+130 rw auto quick
+132 rw auto quick
+135 rw auto

tests/qemu-iotests/iotests.py

@@ -78,6 +78,23 @@ def create_image(name, size):
         i = i + 512
     file.close()
 
+# Test if 'match' is a recursive subset of 'event'
+def event_match(event, match=None):
+    if match is None:
+        return True
+
+    for key in match:
+        if key in event:
+            if isinstance(event[key], dict):
+                if not event_match(event[key], match[key]):
+                    return False
+            elif event[key] != match[key]:
+                return False
+        else:
+            return False
+
+    return True
+
 class VM(object):
     '''A QEMU VM'''
 
@@ -92,6 +109,7 @@ class VM(object):
                      '-machine', 'accel=qtest',
                      '-display', 'none', '-vga', 'none']
         self._num_drives = 0
+        self._events = []
 
     # This can be used to add an unused monitor instance.
     def add_monitor_telnet(self, ip, port):
@@ -202,14 +220,34 @@ class VM(object):
 
     def get_qmp_event(self, wait=False):
         '''Poll for one queued QMP events and return it'''
+        if len(self._events) > 0:
+            return self._events.pop(0)
         return self._qmp.pull_event(wait=wait)
 
     def get_qmp_events(self, wait=False):
         '''Poll for queued QMP events and return a list of dicts'''
         events = self._qmp.get_events(wait=wait)
+        events.extend(self._events)
+        del self._events[:]
         self._qmp.clear_events()
         return events
 
+    def event_wait(self, name='BLOCK_JOB_COMPLETED', timeout=60.0, match=None):
+        # Search cached events
+        for event in self._events:
+            if (event['event'] == name) and event_match(event, match):
+                self._events.remove(event)
+                return event
+
+        # Poll for new events
+        while True:
+            event = self._qmp.pull_event(wait=timeout)
+            if (event['event'] == name) and event_match(event, match):
+                return event
+            self._events.append(event)
+
+        return None
+
 index_re = re.compile(r'([^\[]+)\[([^\]]+)\]')
 
 class QMPTestCase(unittest.TestCase):
@@ -288,6 +326,29 @@ class QMPTestCase(unittest.TestCase):
         self.assert_no_active_block_jobs()
         return event
 
+    def wait_ready(self, drive='drive0'):
+        '''Wait until a block job BLOCK_JOB_READY event'''
+        f = {'data': {'type': 'mirror', 'device': drive } }
+        event = self.vm.event_wait(name='BLOCK_JOB_READY', match=f)
+
+    def wait_ready_and_cancel(self, drive='drive0'):
+        self.wait_ready(drive=drive)
+        event = self.cancel_and_wait(drive=drive)
+        self.assertEquals(event['event'], 'BLOCK_JOB_COMPLETED')
+        self.assert_qmp(event, 'data/type', 'mirror')
+        self.assert_qmp(event, 'data/offset', event['data']['len'])
+
+    def complete_and_wait(self, drive='drive0', wait_ready=True):
+        '''Complete a block job and wait for it to finish'''
+        if wait_ready:
+            self.wait_ready(drive=drive)
+
+        result = self.vm.qmp('block-job-complete', device=drive)
+        self.assert_qmp(result, 'return', {})
+
+        event = self.wait_until_completed(drive=drive)
+        self.assert_qmp(event, 'data/type', 'mirror')
+
 def notrun(reason):
     '''Skip this test suite'''
     # Each test in qemu-iotests has a number ("seq")

translate-all.c

@@ -1334,8 +1334,6 @@ static inline void tb_alloc_page(TranslationBlock *tb,
     p->first_tb = (TranslationBlock *)((uintptr_t)tb | n);
     invalidate_page_bitmap(p);
 
-#if defined(TARGET_HAS_SMC) || 1
-
 #if defined(CONFIG_USER_ONLY)
     if (p->flags & PAGE_WRITE) {
         target_ulong addr;
@@ -1371,8 +1369,6 @@ static inline void tb_alloc_page(TranslationBlock *tb,
         tlb_protect_code(page_addr);
     }
 #endif
-
-#endif /* TARGET_HAS_SMC */
 }
 
 /* add a new TB and link it to the physical page tables. phys_page2 is

ui/input-keymap.c

@@ -128,6 +128,10 @@ static const int qcode_to_number[] = {
 
     [Q_KEY_CODE_INSERT] = 0xd2,
     [Q_KEY_CODE_DELETE] = 0xd3,
+
+    [Q_KEY_CODE_RO] = 0x73,
+    [Q_KEY_CODE_KP_COMMA] = 0x7e,
+
     [Q_KEY_CODE_MAX] = 0,
 };
 

ui/sdl2.c

@@ -511,6 +511,10 @@ static void handle_windowevent(SDL_Event *ev)
 {
     struct sdl2_console *scon = get_scon_from_window(ev->window.windowID);
 
+    if (!scon) {
+        return;
+    }
+
     switch (ev->window.event) {
     case SDL_WINDOWEVENT_RESIZED:
         {

ui/spice-display.c

@@ -199,7 +199,7 @@ static void qemu_spice_create_update(SimpleSpiceDisplay *ssd)
     static const int blksize = 32;
     int blocks = (surface_width(ssd->ds) + blksize - 1) / blksize;
     int dirty_top[blocks];
-    int y, yoff, x, xoff, blk, bw;
+    int y, yoff1, yoff2, x, xoff, blk, bw;
     int bpp = surface_bytes_per_pixel(ssd->ds);
     uint8_t *guest, *mirror;
 
@@ -214,13 +214,14 @@ static void qemu_spice_create_update(SimpleSpiceDisplay *ssd)
     guest = surface_data(ssd->ds);
     mirror = (void *)pixman_image_get_data(ssd->mirror);
     for (y = ssd->dirty.top; y < ssd->dirty.bottom; y++) {
-        yoff = y * surface_stride(ssd->ds);
+        yoff1 = y * surface_stride(ssd->ds);
+        yoff2 = y * pixman_image_get_stride(ssd->mirror);
         for (x = ssd->dirty.left; x < ssd->dirty.right; x += blksize) {
             xoff = x * bpp;
             blk = x / blksize;
             bw = MIN(blksize, ssd->dirty.right - x);
-            if (memcmp(guest + yoff + xoff,
-                       mirror + yoff + xoff,
+            if (memcmp(guest + yoff1 + xoff,
+                       mirror + yoff2 + xoff,
                        bw * bpp) == 0) {
                 if (dirty_top[blk] != -1) {
                     QXLRect update = {

ui/vnc.c

@@ -3482,7 +3482,14 @@ void vnc_display_open(const char *id, Error **errp)
 
     h = strrchr(vnc, ':');
     if (h) {
-        char *host = g_strndup(vnc, h - vnc);
+        char *host;
+        size_t hlen = h - vnc;
+
+        if (vnc[0] == '[' && vnc[hlen - 1] == ']') {
+            host = g_strndup(vnc + 1, hlen - 2);
+        } else {
+            host = g_strndup(vnc, hlen);
+        }
         qemu_opt_set(sopts, "host", host, &error_abort);
         qemu_opt_set(wsopts, "host", host, &error_abort);
         qemu_opt_set(sopts, "port", h+1, &error_abort);

ui/x_keymap.c

@@ -94,7 +94,7 @@ static const uint8_t x_keycode_to_pc_keycode[115] = {
  */
 
 static const uint8_t evdev_keycode_to_pc_keycode[61] = {
-    0,         /*  97 EVDEV - RO   ("Internet" Keyboards) */
+    0x73,      /*  97 EVDEV - RO   ("Internet" Keyboards) */
     0,         /*  98 EVDEV - KATA (Katakana) */
     0,         /*  99 EVDEV - HIRA (Hiragana) */
     0x79,      /* 100 EVDEV - HENK (Henkan) */
@@ -126,7 +126,7 @@ static const uint8_t evdev_keycode_to_pc_keycode[61] = {
     0,         /* 126 EVDEV - I126 ("Internet" Keyboards) */
     0,         /* 127 EVDEV - PAUS */
     0,         /* 128 EVDEV - ???? */
-    0,         /* 129 EVDEV - I129 ("Internet" Keyboards) */
+    0x7e,      /* 129 EVDEV - KP_COMMA (brazilian) */
     0xf1,      /* 130 EVDEV - HNGL (Korean Hangul Latin toggle) */
     0xf2,      /* 131 EVDEV - HJCV (Korean Hangul Hanja toggle) */
     0x7d,      /* 132 AE13 (Yen)*/