Update version for 2.4.1 release

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>

.gitignore

@@ -17,6 +17,8 @@
 /trace/generated-tcg-tracers.h
 /trace/generated-ust-provider.h
 /trace/generated-ust.c
+/ui/shader/texture-blit-frag.h
+/ui/shader/texture-blit-vert.h
 /libcacard/trace/generated-tracers.c
 *-timestamp
 /*-softmmu

Makefile

@@ -135,7 +135,7 @@ endif
 	 else \
 	  mv $@.tmp $@; \
 	  cp -p $@ $@.old; \
-	 fi, "  GEN  $@");
+	 fi, "  GEN   $@");
 
 defconfig:
 	rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)

VERSION

@@ -1 +1 @@
-2.3.92
+2.4.1

async.c

@@ -79,8 +79,10 @@ int aio_bh_poll(AioContext *ctx)
          * aio_notify again if necessary.
          */
         if (!bh->deleted && atomic_xchg(&bh->scheduled, 0)) {
-            if (!bh->idle)
+            /* Idle BHs and the notify BH don't count as progress */
+            if (!bh->idle && bh != ctx->notify_dummy_bh) {
                 ret = 1;
+            }
             bh->idle = 0;
             bh->cb(bh->opaque);
         }
@@ -230,7 +232,21 @@ aio_ctx_finalize(GSource     *source)
 {
     AioContext *ctx = (AioContext *) source;
 
+    qemu_bh_delete(ctx->notify_dummy_bh);
     thread_pool_free(ctx->thread_pool);
+
+    qemu_mutex_lock(&ctx->bh_lock);
+    while (ctx->first_bh) {
+        QEMUBH *next = ctx->first_bh->next;
+
+        /* qemu_bh_delete() must have been called on BHs in this AioContext */
+        assert(ctx->first_bh->deleted);
+
+        g_free(ctx->first_bh);
+        ctx->first_bh = next;
+    }
+    qemu_mutex_unlock(&ctx->bh_lock);
+
     aio_set_event_notifier(ctx, &ctx->notifier, NULL);
     event_notifier_cleanup(&ctx->notifier);
     rfifolock_destroy(&ctx->lock);
@@ -285,8 +301,15 @@ static void aio_timerlist_notify(void *opaque)
 
 static void aio_rfifolock_cb(void *opaque)
 {
+    AioContext *ctx = opaque;
+
     /* Kick owner thread in case they are blocked in aio_poll() */
-    aio_notify(opaque);
+    qemu_bh_schedule(ctx->notify_dummy_bh);
+}
+
+static void notify_dummy_bh(void *opaque)
+{
+    /* Do nothing, we were invoked just to force the event loop to iterate */
 }
 
 static void event_notifier_dummy_cb(EventNotifier *e)
@@ -313,6 +336,8 @@ AioContext *aio_context_new(Error **errp)
     rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
     timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
 
+    ctx->notify_dummy_bh = aio_bh_new(ctx, notify_dummy_bh, NULL);
+
     return ctx;
 }
 

backends/hostmem.c

@@ -10,6 +10,7 @@
  * See the COPYING file in the top-level directory.
  */
 #include "sysemu/hostmem.h"
+#include "hw/boards.h"
 #include "qapi/visitor.h"
 #include "qapi-types.h"
 #include "qapi-visit.h"
@@ -222,11 +223,10 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
 static void host_memory_backend_init(Object *obj)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    MachineState *machine = MACHINE(qdev_get_machine());
 
-    backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                       "mem-merge", true);
-    backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                      "dump-guest-core", true);
+    backend->merge = machine_mem_merge(machine);
+    backend->dump = machine_dump_guest_core(machine);
     backend->prealloc = mem_prealloc;
 
     object_property_add_bool(obj, "merge",

block/iscsi.c

@@ -1214,6 +1214,10 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
 
     if (task == NULL || task->status != SCSI_STATUS_GOOD) {
         error_setg(errp, "iSCSI: failed to send readcapacity10 command.");
+    } else if (!iscsilun->block_size ||
+               iscsilun->block_size % BDRV_SECTOR_SIZE) {
+        error_setg(errp, "iSCSI: the target returned an invalid "
+                   "block size of %d.", iscsilun->block_size);
     }
     if (task) {
         scsi_free_scsi_task(task);

block/mirror.c

@@ -60,6 +60,7 @@ typedef struct MirrorBlockJob {
     int sectors_in_flight;
     int ret;
     bool unmap;
+    bool waiting_for_io;
 } MirrorBlockJob;
 
 typedef struct MirrorOp {
@@ -114,11 +115,7 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
     qemu_iovec_destroy(&op->qiov);
     g_slice_free(MirrorOp, op);
 
-    /* Enter coroutine when it is not sleeping.  The coroutine sleeps to
-     * rate-limit itself.  The coroutine will eventually resume since there is
-     * a sleep timeout so don't wake it early.
-     */
-    if (s->common.busy) {
+    if (s->waiting_for_io) {
         qemu_coroutine_enter(s->common.co, NULL);
     }
 }
@@ -203,7 +200,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
     /* Wait for I/O to this cluster (from a previous iteration) to be done.  */
     while (test_bit(next_chunk, s->in_flight_bitmap)) {
         trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
+        s->waiting_for_io = true;
         qemu_coroutine_yield();
+        s->waiting_for_io = false;
     }
 
     do {
@@ -239,7 +238,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
          */
         while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
             trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
+            s->waiting_for_io = true;
             qemu_coroutine_yield();
+            s->waiting_for_io = false;
         }
         if (s->buf_free_count < nb_chunks + added_chunks) {
             trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
@@ -333,7 +334,9 @@ static void mirror_free_init(MirrorBlockJob *s)
 static void mirror_drain(MirrorBlockJob *s)
 {
     while (s->in_flight > 0) {
+        s->waiting_for_io = true;
         qemu_coroutine_yield();
+        s->waiting_for_io = false;
     }
 }
 
@@ -506,7 +509,9 @@ static void coroutine_fn mirror_run(void *opaque)
             if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
                 (cnt == 0 && s->in_flight > 0)) {
                 trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
+                s->waiting_for_io = true;
                 qemu_coroutine_yield();
+                s->waiting_for_io = false;
                 continue;
             } else if (cnt != 0) {
                 delay_ns = mirror_iteration(s);

block/nfs.c

@@ -475,7 +475,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
         aio_poll(client->aio_context, true);
     }
 
-    return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
+    return (task.ret < 0 ? task.ret : st.st_blocks * 512);
 }
 
 static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)

block/qcow2-cluster.c

@@ -298,7 +298,7 @@ fail:
  * as contiguous. (This allows it, for example, to stop at the first compressed
  * cluster which may require a different handling)
  */
-static int count_contiguous_clusters(uint64_t nb_clusters, int cluster_size,
+static int count_contiguous_clusters(int nb_clusters, int cluster_size,
         uint64_t *l2_table, uint64_t stop_flags)
 {
     int i;
@@ -321,7 +321,7 @@ static int count_contiguous_clusters(uint64_t nb_clusters, int cluster_size,
 	return i;
 }
 
-static int count_contiguous_free_clusters(uint64_t nb_clusters, uint64_t *l2_table)
+static int count_contiguous_free_clusters(int nb_clusters, uint64_t *l2_table)
 {
     int i;
 
@@ -495,6 +495,7 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
     if (nb_needed > nb_available) {
         nb_needed = nb_available;
     }
+    assert(nb_needed <= INT_MAX);
 
     *cluster_offset = 0;
 
@@ -530,6 +531,8 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
 
     l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
     *cluster_offset = be64_to_cpu(l2_table[l2_index]);
+
+    /* nb_needed <= INT_MAX, thus nb_clusters <= INT_MAX, too */
     nb_clusters = size_to_clusters(s, nb_needed << 9);
 
     ret = qcow2_get_cluster_type(*cluster_offset);
@@ -960,7 +963,7 @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
     int l2_index;
     uint64_t cluster_offset;
     uint64_t *l2_table;
-    unsigned int nb_clusters;
+    uint64_t nb_clusters;
     unsigned int keep_clusters;
     int ret;
 
@@ -979,6 +982,7 @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
 
     l2_index = offset_to_l2_index(s, guest_offset);
     nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+    assert(nb_clusters <= INT_MAX);
 
     /* Find L2 entry for the first involved cluster */
     ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
@@ -1061,7 +1065,7 @@ out:
  * restarted, but the whole request should not be failed.
  */
 static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
-    uint64_t *host_offset, unsigned int *nb_clusters)
+                                   uint64_t *host_offset, uint64_t *nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
 
@@ -1079,7 +1083,7 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
         *host_offset = cluster_offset;
         return 0;
     } else {
-        int ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
+        int64_t ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
         if (ret < 0) {
             return ret;
         }
@@ -1115,7 +1119,7 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
     int l2_index;
     uint64_t *l2_table;
     uint64_t entry;
-    unsigned int nb_clusters;
+    uint64_t nb_clusters;
     int ret;
 
     uint64_t alloc_cluster_offset;
@@ -1133,6 +1137,7 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
 
     l2_index = offset_to_l2_index(s, guest_offset);
     nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+    assert(nb_clusters <= INT_MAX);
 
     /* Find L2 entry for the first involved cluster */
     ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
@@ -1426,7 +1431,8 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
  * clusters.
  */
 static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
-    unsigned int nb_clusters, enum qcow2_discard_type type, bool full_discard)
+                             uint64_t nb_clusters, enum qcow2_discard_type type,
+                             bool full_discard)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t *l2_table;
@@ -1441,6 +1447,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
 
     /* Limit nb_clusters to one L2 table */
     nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+    assert(nb_clusters <= INT_MAX);
 
     for (i = 0; i < nb_clusters; i++) {
         uint64_t old_l2_entry;
@@ -1503,7 +1510,7 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t end_offset;
-    unsigned int nb_clusters;
+    uint64_t nb_clusters;
     int ret;
 
     end_offset = offset + (nb_sectors << BDRV_SECTOR_BITS);
@@ -1545,7 +1552,7 @@ fail:
  * clusters.
  */
 static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
-    unsigned int nb_clusters)
+                          uint64_t nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t *l2_table;
@@ -1560,6 +1567,7 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
 
     /* Limit nb_clusters to one L2 table */
     nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+    assert(nb_clusters <= INT_MAX);
 
     for (i = 0; i < nb_clusters; i++) {
         uint64_t old_offset;
@@ -1584,7 +1592,7 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
 int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors)
 {
     BDRVQcowState *s = bs->opaque;
-    unsigned int nb_clusters;
+    uint64_t nb_clusters;
     int ret;
 
     /* The zero flag is only supported by version 3 and newer */

block/qcow2-refcount.c

@@ -875,8 +875,8 @@ int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size)
     return offset;
 }
 
-int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
-    int nb_clusters)
+int64_t qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
+                                int64_t nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t cluster_index, refcount;
@@ -1259,7 +1259,7 @@ static size_t refcount_array_byte_size(BDRVQcowState *s, uint64_t entries)
 static int realloc_refcount_array(BDRVQcowState *s, void **array,
                                   int64_t *size, int64_t new_size)
 {
-    size_t old_byte_size, new_byte_size;
+    int64_t old_byte_size, new_byte_size;
     void *new_ptr;
 
     /* Round to clusters so the array can be directly written to disk */
@@ -1275,13 +1275,17 @@ static int realloc_refcount_array(BDRVQcowState *s, void **array,
 
     assert(new_byte_size > 0);
 
+    if (new_byte_size > SIZE_MAX) {
+        return -ENOMEM;
+    }
+
     new_ptr = g_try_realloc(*array, new_byte_size);
     if (!new_ptr) {
         return -ENOMEM;
     }
 
     if (new_byte_size > old_byte_size) {
-        memset((void *)((uintptr_t)new_ptr + old_byte_size), 0,
+        memset((char *)new_ptr + old_byte_size, 0,
                new_byte_size - old_byte_size);
     }
 

block/qcow2.h

@@ -412,7 +412,7 @@ static inline int64_t offset_into_cluster(BDRVQcowState *s, int64_t offset)
     return offset & (s->cluster_size - 1);
 }
 
-static inline int size_to_clusters(BDRVQcowState *s, int64_t size)
+static inline uint64_t size_to_clusters(BDRVQcowState *s, uint64_t size)
 {
     return (size + (s->cluster_size - 1)) >> s->cluster_bits;
 }
@@ -506,8 +506,8 @@ int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index,
                                   enum qcow2_discard_type type);
 
 int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size);
-int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
-    int nb_clusters);
+int64_t qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
+                                int64_t nb_clusters);
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);
 void qcow2_free_clusters(BlockDriverState *bs,
                           int64_t offset, int64_t size,

block/quorum.c

@@ -865,12 +865,6 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     int i;
     int ret = 0;
 
-    if (!qcrypto_hash_supports(QCRYPTO_HASH_ALG_SHA256)) {
-        error_setg(errp,
-                   "SHA256 hash support is required for quorum device");
-        return -EINVAL;
-    }
-
     qdict_flatten(options);
 
     /* count how many different children are present */
@@ -1061,6 +1055,10 @@ static BlockDriver bdrv_quorum = {
 
 static void bdrv_quorum_init(void)
 {
+    if (!qcrypto_hash_supports(QCRYPTO_HASH_ALG_SHA256)) {
+        /* SHA256 hash support is required for quorum device */
+        return;
+    }
     bdrv_register(&bdrv_quorum);
 }
 

block/sheepdog.c

@@ -318,6 +318,10 @@ enum AIOCBState {
     AIOCB_DISCARD_OBJ,
 };
 
+#define AIOCBOverwrapping(x, y)                                 \
+    (!(x->max_affect_data_idx < y->min_affect_data_idx          \
+       || y->max_affect_data_idx < x->min_affect_data_idx))
+
 struct SheepdogAIOCB {
     BlockAIOCB common;
 
@@ -334,6 +338,11 @@ struct SheepdogAIOCB {
 
     bool cancelable;
     int nr_pending;
+
+    uint32_t min_affect_data_idx;
+    uint32_t max_affect_data_idx;
+
+    QLIST_ENTRY(SheepdogAIOCB) aiocb_siblings;
 };
 
 typedef struct BDRVSheepdogState {
@@ -362,8 +371,10 @@ typedef struct BDRVSheepdogState {
 
     /* Every aio request must be linked to either of these queues. */
     QLIST_HEAD(inflight_aio_head, AIOReq) inflight_aio_head;
-    QLIST_HEAD(pending_aio_head, AIOReq) pending_aio_head;
     QLIST_HEAD(failed_aio_head, AIOReq) failed_aio_head;
+
+    CoQueue overwrapping_queue;
+    QLIST_HEAD(inflight_aiocb_head, SheepdogAIOCB) inflight_aiocb_head;
 } BDRVSheepdogState;
 
 static const char * sd_strerror(int err)
@@ -498,13 +509,7 @@ static void sd_aio_cancel(BlockAIOCB *blockacb)
     AIOReq *aioreq, *next;
 
     if (sd_acb_cancelable(acb)) {
-        /* Remove outstanding requests from pending and failed queues.  */
-        QLIST_FOREACH_SAFE(aioreq, &s->pending_aio_head, aio_siblings,
-                           next) {
-            if (aioreq->aiocb == acb) {
-                free_aio_req(s, aioreq);
-            }
-        }
+        /* Remove outstanding requests from failed queue.  */
         QLIST_FOREACH_SAFE(aioreq, &s->failed_aio_head, aio_siblings,
                            next) {
             if (aioreq->aiocb == acb) {
@@ -529,6 +534,10 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
                                    int64_t sector_num, int nb_sectors)
 {
     SheepdogAIOCB *acb;
+    uint32_t object_size;
+    BDRVSheepdogState *s = bs->opaque;
+
+    object_size = (UINT32_C(1) << s->inode.block_size_shift);
 
     acb = qemu_aio_get(&sd_aiocb_info, bs, NULL, NULL);
 
@@ -542,6 +551,11 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
     acb->coroutine = qemu_coroutine_self();
     acb->ret = 0;
     acb->nr_pending = 0;
+
+    acb->min_affect_data_idx = acb->sector_num * BDRV_SECTOR_SIZE / object_size;
+    acb->max_affect_data_idx = (acb->sector_num * BDRV_SECTOR_SIZE +
+                              acb->nb_sectors * BDRV_SECTOR_SIZE) / object_size;
+
     return acb;
 }
 
@@ -703,38 +717,6 @@ static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag);
 static int get_sheep_fd(BDRVSheepdogState *s, Error **errp);
 static void co_write_request(void *opaque);
 
-static AIOReq *find_pending_req(BDRVSheepdogState *s, uint64_t oid)
-{
-    AIOReq *aio_req;
-
-    QLIST_FOREACH(aio_req, &s->pending_aio_head, aio_siblings) {
-        if (aio_req->oid == oid) {
-            return aio_req;
-        }
-    }
-
-    return NULL;
-}
-
-/*
- * This function searchs pending requests to the object `oid', and
- * sends them.
- */
-static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid)
-{
-    AIOReq *aio_req;
-    SheepdogAIOCB *acb;
-
-    while ((aio_req = find_pending_req(s, oid)) != NULL) {
-        acb = aio_req->aiocb;
-        /* move aio_req from pending list to inflight one */
-        QLIST_REMOVE(aio_req, aio_siblings);
-        QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
-        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
-                        acb->aiocb_type);
-    }
-}
-
 static coroutine_fn void reconnect_to_sdog(void *opaque)
 {
     BDRVSheepdogState *s = opaque;
@@ -840,12 +822,6 @@ static void coroutine_fn aio_read_response(void *opaque)
                 s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
                 s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
             }
-            /*
-             * Some requests may be blocked because simultaneous
-             * create requests are not allowed, so we search the
-             * pending requests here.
-             */
-            send_pending_req(s, aio_req->oid);
         }
         break;
     case AIOCB_READ_UDATA:
@@ -1341,30 +1317,6 @@ out:
     return ret;
 }
 
-/* Return true if the specified request is linked to the pending list. */
-static bool check_simultaneous_create(BDRVSheepdogState *s, AIOReq *aio_req)
-{
-    AIOReq *areq;
-    QLIST_FOREACH(areq, &s->inflight_aio_head, aio_siblings) {
-        if (areq != aio_req && areq->oid == aio_req->oid) {
-            /*
-             * Sheepdog cannot handle simultaneous create requests to the same
-             * object, so we cannot send the request until the previous request
-             * finishes.
-             */
-            DPRINTF("simultaneous create to %" PRIx64 "\n", aio_req->oid);
-            aio_req->flags = 0;
-            aio_req->base_oid = 0;
-            aio_req->create = false;
-            QLIST_REMOVE(aio_req, aio_siblings);
-            QLIST_INSERT_HEAD(&s->pending_aio_head, aio_req, aio_siblings);
-            return true;
-        }
-    }
-
-    return false;
-}
-
 static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req)
 {
     SheepdogAIOCB *acb = aio_req->aiocb;
@@ -1379,10 +1331,6 @@ static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req)
             goto out;
         }
 
-        if (check_simultaneous_create(s, aio_req)) {
-            return;
-        }
-
         if (s->inode.data_vdi_id[idx]) {
             aio_req->base_oid = vid_to_data_oid(s->inode.data_vdi_id[idx], idx);
             aio_req->flags |= SD_FLAG_CMD_COW;
@@ -1458,8 +1406,8 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     filename = qemu_opt_get(opts, "filename");
 
     QLIST_INIT(&s->inflight_aio_head);
-    QLIST_INIT(&s->pending_aio_head);
     QLIST_INIT(&s->failed_aio_head);
+    QLIST_INIT(&s->inflight_aiocb_head);
     s->fd = -1;
 
     memset(vdi, 0, sizeof(vdi));
@@ -1524,6 +1472,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     bs->total_sectors = s->inode.vdi_size / BDRV_SECTOR_SIZE;
     pstrcpy(s->name, sizeof(s->name), vdi);
     qemu_co_mutex_init(&s->lock);
+    qemu_co_queue_init(&s->overwrapping_queue);
     qemu_opts_del(opts);
     g_free(buf);
     return 0;
@@ -2195,12 +2144,6 @@ static int coroutine_fn sd_co_rw_vector(void *p)
                                 old_oid, done);
         QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
 
-        if (create) {
-            if (check_simultaneous_create(s, aio_req)) {
-                goto done;
-            }
-        }
-
         add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
                         acb->aiocb_type);
     done:
@@ -2215,6 +2158,20 @@ out:
     return 1;
 }
 
+static bool check_overwrapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *aiocb)
+{
+    SheepdogAIOCB *cb;
+
+    QLIST_FOREACH(cb, &s->inflight_aiocb_head, aiocb_siblings) {
+        if (AIOCBOverwrapping(aiocb, cb)) {
+            return true;
+        }
+    }
+
+    QLIST_INSERT_HEAD(&s->inflight_aiocb_head, aiocb, aiocb_siblings);
+    return false;
+}
+
 static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
@@ -2234,14 +2191,25 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
     acb->aio_done_func = sd_write_done;
     acb->aiocb_type = AIOCB_WRITE_UDATA;
 
+retry:
+    if (check_overwrapping_aiocb(s, acb)) {
+        qemu_co_queue_wait(&s->overwrapping_queue);
+        goto retry;
+    }
+
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
+        QLIST_REMOVE(acb, aiocb_siblings);
+        qemu_co_queue_restart_all(&s->overwrapping_queue);
         qemu_aio_unref(acb);
         return ret;
     }
 
     qemu_coroutine_yield();
 
+    QLIST_REMOVE(acb, aiocb_siblings);
+    qemu_co_queue_restart_all(&s->overwrapping_queue);
+
     return acb->ret;
 }
 
@@ -2250,19 +2218,30 @@ static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
 {
     SheepdogAIOCB *acb;
     int ret;
+    BDRVSheepdogState *s = bs->opaque;
 
     acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
     acb->aiocb_type = AIOCB_READ_UDATA;
     acb->aio_done_func = sd_finish_aiocb;
 
+retry:
+    if (check_overwrapping_aiocb(s, acb)) {
+        qemu_co_queue_wait(&s->overwrapping_queue);
+        goto retry;
+    }
+
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
+        QLIST_REMOVE(acb, aiocb_siblings);
+        qemu_co_queue_restart_all(&s->overwrapping_queue);
         qemu_aio_unref(acb);
         return ret;
     }
 
     qemu_coroutine_yield();
 
+    QLIST_REMOVE(acb, aiocb_siblings);
+    qemu_co_queue_restart_all(&s->overwrapping_queue);
     return acb->ret;
 }
 
@@ -2610,14 +2589,25 @@ static coroutine_fn int sd_co_discard(BlockDriverState *bs, int64_t sector_num,
     acb->aiocb_type = AIOCB_DISCARD_OBJ;
     acb->aio_done_func = sd_finish_aiocb;
 
+retry:
+    if (check_overwrapping_aiocb(s, acb)) {
+        qemu_co_queue_wait(&s->overwrapping_queue);
+        goto retry;
+    }
+
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
+        QLIST_REMOVE(acb, aiocb_siblings);
+        qemu_co_queue_restart_all(&s->overwrapping_queue);
         qemu_aio_unref(acb);
         return ret;
     }
 
     qemu_coroutine_yield();
 
+    QLIST_REMOVE(acb, aiocb_siblings);
+    qemu_co_queue_restart_all(&s->overwrapping_queue);
+
     return acb->ret;
 }
 

block/ssh.c

@@ -563,7 +563,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     /* Open the socket and connect. */
     s->sock = inet_connect(s->hostport, errp);
     if (s->sock < 0) {
-        ret = -errno;
+        ret = -EIO;
         goto err;
     }
 

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]);

bsd-user/main.c

@@ -173,7 +173,7 @@ void cpu_loop(CPUX86State *env)
     //target_siginfo_t info;
 
     for(;;) {
-        trapnr = cpu_x86_exec(env);
+        trapnr = cpu_x86_exec(cs);
         switch(trapnr) {
         case 0x80:
             /* syscall from int $0x80 */

configure

@@ -1337,7 +1337,6 @@ disabled with --disable-FEATURE, default is enabled if available:
   vnc-sasl        SASL encryption for VNC server
   vnc-jpeg        JPEG lossy compression for VNC server
   vnc-png         PNG compression for VNC server
-  vnc-ws          Websockets support for VNC server
   cocoa           Cocoa UI (Mac OS X only)
   virtfs          VirtFS
   xen             xen backend driver support
@@ -2116,10 +2115,26 @@ fi
 ##########################################
 # GNUTLS probe
 
+gnutls_works() {
+    # Unfortunately some distros have bad pkg-config information for gnutls
+    # such that it claims to exist but you get a compiler error if you try
+    # to use the options returned by --libs. Specifically, Ubuntu for --static
+    # builds doesn't work:
+    # https://bugs.launchpad.net/ubuntu/+source/gnutls26/+bug/1478035
+    #
+    # So sanity check the cflags/libs before assuming gnutls can be used.
+    if ! $pkg_config --exists "gnutls"; then
+        return 1
+    fi
+
+    write_c_skeleton
+    compile_prog "$($pkg_config --cflags gnutls)" "$($pkg_config --libs gnutls)"
+}
+
 gnutls_gcrypt=no
 gnutls_nettle=no
 if test "$gnutls" != "no"; then
-    if $pkg_config --exists "gnutls"; then
+    if gnutls_works; then
         gnutls_cflags=`$pkg_config --cflags gnutls`
         gnutls_libs=`$pkg_config --libs gnutls`
         libs_softmmu="$gnutls_libs $libs_softmmu"

cpus.c

@@ -954,6 +954,8 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
     CPUState *cpu = arg;
     int r;
 
+    rcu_register_thread();
+
     qemu_mutex_lock_iothread();
     qemu_thread_get_self(cpu->thread);
     cpu->thread_id = qemu_get_thread_id();
@@ -995,6 +997,8 @@ static void *qemu_dummy_cpu_thread_fn(void *arg)
     sigset_t waitset;
     int r;
 
+    rcu_register_thread();
+
     qemu_mutex_lock_iothread();
     qemu_thread_get_self(cpu->thread);
     cpu->thread_id = qemu_get_thread_id();
@@ -1034,6 +1038,8 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
 {
     CPUState *cpu = arg;
 
+    rcu_register_thread();
+
     qemu_mutex_lock_iothread();
     qemu_tcg_init_cpu_signals();
     qemu_thread_get_self(cpu->thread);
@@ -1160,7 +1166,7 @@ void qemu_mutex_lock_iothread(void)
      * TCG code execution.
      */
     if (!tcg_enabled() || qemu_in_vcpu_thread() ||
-        !first_cpu || !first_cpu->thread) {
+        !first_cpu || !first_cpu->created) {
         qemu_mutex_lock(&qemu_global_mutex);
         atomic_dec(&iothread_requesting_mutex);
     } else {

crypto/cipher-builtin.c

@@ -117,7 +117,7 @@ static int qcrypto_cipher_decrypt_aes(QCryptoCipher *cipher,
         uint8_t *outptr = out;
         while (len) {
             if (len > AES_BLOCK_SIZE) {
-                AES_decrypt(inptr, outptr, &ctxt->state.aes.encrypt_key);
+                AES_decrypt(inptr, outptr, &ctxt->state.aes.decrypt_key);
                 inptr += AES_BLOCK_SIZE;
                 outptr += AES_BLOCK_SIZE;
                 len -= AES_BLOCK_SIZE;
@@ -126,15 +126,15 @@ static int qcrypto_cipher_decrypt_aes(QCryptoCipher *cipher,
                 memcpy(tmp1, inptr, len);
                 /* Fill with 0 to avoid valgrind uninitialized reads */
                 memset(tmp1 + len, 0, sizeof(tmp1) - len);
-                AES_decrypt(tmp1, tmp2, &ctxt->state.aes.encrypt_key);
+                AES_decrypt(tmp1, tmp2, &ctxt->state.aes.decrypt_key);
                 memcpy(outptr, tmp2, len);
                 len = 0;
             }
         }
     } else {
         AES_cbc_encrypt(in, out, len,
-                        &ctxt->state.aes.encrypt_key,
-                        ctxt->state.aes.iv, 1);
+                        &ctxt->state.aes.decrypt_key,
+                        ctxt->state.aes.iv, 0);
     }
 
     return 0;

device_tree.c

@@ -241,7 +241,7 @@ uint32_t qemu_fdt_alloc_phandle(void *fdt)
 
     /*
      * We need to find out if the user gave us special instruction at
-     * which phandle id to start allocting phandles.
+     * which phandle id to start allocating phandles.
      */
     if (!phandle) {
         phandle = machine_phandle_start(current_machine);

exec.c

@@ -954,7 +954,10 @@ hwaddr memory_region_section_get_iotlb(CPUState *cpu,
             iotlb |= PHYS_SECTION_ROM;
         }
     } else {
-        iotlb = section - section->address_space->dispatch->map.sections;
+        AddressSpaceDispatch *d;
+
+        d = atomic_rcu_read(&section->address_space->dispatch);
+        iotlb = section - d->map.sections;
         iotlb += xlat;
     }
 

gdbstub.c

@@ -1285,6 +1285,7 @@ static void gdb_vm_state_change(void *opaque, int running, RunState state)
         ret = GDB_SIGNAL_UNKNOWN;
         break;
     }
+    gdb_set_stop_cpu(cpu);
     snprintf(buf, sizeof(buf), "T%02xthread:%02x;", ret, cpu_index(cpu));
 
 send_packet:

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

@@ -21,7 +21,8 @@
 #include "virtio-9p-coth.h"
 #include "hw/virtio/virtio-access.h"
 
-static uint64_t virtio_9p_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_9p_get_features(VirtIODevice *vdev, uint64_t features,
+                                       Error **errp)
 {
     virtio_add_feature(&features, VIRTIO_9P_MOUNT_TAG);
     return features;

hw/9pfs/virtio-9p.c

@@ -14,6 +14,7 @@
 #include "hw/virtio/virtio.h"
 #include "hw/i386/pc.h"
 #include "qemu/error-report.h"
+#include "qemu/iov.h"
 #include "qemu/sockets.h"
 #include "virtio-9p.h"
 #include "fsdev/qemu-fsdev.h"
@@ -3261,16 +3262,26 @@ void handle_9p_output(VirtIODevice *vdev, VirtQueue *vq)
 
     while ((pdu = alloc_pdu(s)) &&
             (len = virtqueue_pop(vq, &pdu->elem)) != 0) {
-        uint8_t *ptr;
+        struct {
+            uint32_t size_le;
+            uint8_t id;
+            uint16_t tag_le;
+        } QEMU_PACKED out;
+        int len;
+
         pdu->s = s;
         BUG_ON(pdu->elem.out_num == 0 || pdu->elem.in_num == 0);
-        BUG_ON(pdu->elem.out_sg[0].iov_len < 7);
+        QEMU_BUILD_BUG_ON(sizeof out != 7);
 
-        ptr = pdu->elem.out_sg[0].iov_base;
+        len = iov_to_buf(pdu->elem.out_sg, pdu->elem.out_num, 0,
+                         &out, sizeof out);
+        BUG_ON(len != sizeof out);
+
+        pdu->size = le32_to_cpu(out.size_le);
+
+        pdu->id = out.id;
+        pdu->tag = le16_to_cpu(out.tag_le);
 
-        pdu->size = le32_to_cpu(*(uint32_t *)ptr);
-        pdu->id = ptr[4];
-        pdu->tag = le16_to_cpu(*(uint16_t *)(ptr + 5));
         qemu_co_queue_init(&pdu->complete);
         submit_pdu(s, pdu);
     }

hw/acpi/ich9.c

@@ -221,9 +221,9 @@ static void pm_reset(void *opaque)
     acpi_pm_tmr_reset(&pm->acpi_regs);
     acpi_gpe_reset(&pm->acpi_regs);
 
+    pm->smi_en = 0;
     if (!pm->smm_enabled) {
-        /* Mark SMM as already inited to prevent SMM from running. KVM does not
-         * support SMM mode. */
+        /* Mark SMM as already inited to prevent SMM from running. */
         pm->smi_en |= ICH9_PMIO_SMI_EN_APMC_EN;
     }
     pm->smi_en_wmask = ~0;

hw/arm/allwinner-a10.c

@@ -103,6 +103,12 @@ static void aw_a10_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = aw_a10_realize;
+
+    /*
+     * Reason: creates an ARM CPU, thus use after free(), see
+     * arm_cpu_class_init()
+     */
+    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo aw_a10_type_info = {

hw/arm/digic.c

@@ -97,6 +97,12 @@ static void digic_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     dc->realize = digic_realize;
+
+    /*
+     * Reason: creates an ARM CPU, thus use after free(), see
+     * arm_cpu_class_init()
+     */
+    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo digic_type_info = {

hw/arm/pxa2xx.c

@@ -1959,7 +1959,7 @@ static void pxa2xx_fir_instance_init(Object *obj)
     PXA2xxFIrState *s = PXA2XX_FIR(obj);
     SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
 
-    memory_region_init_io(&s->iomem, NULL, &pxa2xx_fir_ops, s,
+    memory_region_init_io(&s->iomem, obj, &pxa2xx_fir_ops, s,
                           "pxa2xx-fir", 0x1000);
     sysbus_init_mmio(sbd, &s->iomem);
     sysbus_init_irq(sbd, &s->irq);

hw/arm/xlnx-zynqmp.c

@@ -248,6 +248,12 @@ static void xlnx_zynqmp_class_init(ObjectClass *oc, void *data)
 
     dc->props = xlnx_zynqmp_props;
     dc->realize = xlnx_zynqmp_realize;
+
+    /*
+     * Reason: creates an ARM CPU, thus use after free(), see
+     * arm_cpu_class_init()
+     */
+    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo xlnx_zynqmp_type_info = {

hw/block/dataplane/virtio-blk.c

@@ -223,8 +223,8 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
     virtio_blk_data_plane_stop(s);
     blk_op_unblock_all(s->conf->conf.blk, s->blocker);
     error_free(s->blocker);
-    object_unref(OBJECT(s->iothread));
     qemu_bh_delete(s->bh);
+    object_unref(OBJECT(s->iothread));
     g_free(s);
 }
 

hw/block/virtio-blk.c

@@ -722,7 +722,8 @@ static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
     aio_context_release(blk_get_aio_context(s->blk));
 }
 
-static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features,
+                                        Error **errp)
 {
     VirtIOBlock *s = VIRTIO_BLK(vdev);
 
@@ -730,7 +731,15 @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features)
     virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
     virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
     virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
-    virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
+    if (virtio_has_feature(features, VIRTIO_F_VERSION_1)) {
+        if (s->conf.scsi) {
+            error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0");
+            return 0;
+        }
+    } else {
+        virtio_clear_feature(&features, VIRTIO_F_ANY_LAYOUT);
+        virtio_add_feature(&features, VIRTIO_BLK_F_SCSI);
+    }
 
     if (s->conf.config_wce) {
         virtio_add_feature(&features, VIRTIO_BLK_F_CONFIG_WCE);
@@ -773,10 +782,11 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
      *
      * s->blk would erroneously be placed in writethrough mode.
      */
-    if (!virtio_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_BLK_F_CONFIG_WCE)) {
         aio_context_acquire(blk_get_aio_context(s->blk));
         blk_set_enable_write_cache(s->blk,
-                                   virtio_has_feature(vdev, VIRTIO_BLK_F_WCE));
+                                   virtio_vdev_has_feature(vdev,
+                                                           VIRTIO_BLK_F_WCE));
         aio_context_release(blk_get_aio_context(s->blk));
     }
 }
@@ -784,6 +794,11 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
 static void virtio_blk_save(QEMUFile *f, void *opaque)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
+    VirtIOBlock *s = VIRTIO_BLK(vdev);
+
+    if (s->dataplane) {
+        virtio_blk_data_plane_stop(s->dataplane);
+    }
 
     virtio_save(vdev, f);
 }

hw/char/virtio-serial-bus.c

@@ -76,7 +76,7 @@ static VirtIOSerialPort *find_port_by_name(char *name)
 static bool use_multiport(VirtIOSerial *vser)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(vser);
-    return virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT);
+    return virtio_vdev_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT);
 }
 
 static size_t write_to_port(VirtIOSerialPort *port,
@@ -195,7 +195,8 @@ static size_t send_control_msg(VirtIOSerial *vser, void *buf, size_t len)
         return 0;
     }
 
-    memcpy(elem.in_sg[0].iov_base, buf, len);
+    /* TODO: detect a buffer that's too short, set NEEDS_RESET */
+    iov_from_buf(elem.in_sg, elem.in_num, 0, buf, len);
 
     virtqueue_push(vq, &elem, len);
     virtio_notify(VIRTIO_DEVICE(vser), vq);
@@ -499,7 +500,8 @@ static void handle_input(VirtIODevice *vdev, VirtQueue *vq)
     }
 }
 
-static uint64_t get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t get_features(VirtIODevice *vdev, uint64_t features,
+                             Error **errp)
 {
     VirtIOSerial *vser;
 

hw/display/cg3.c

@@ -280,12 +280,12 @@ static void cg3_initfn(Object *obj)
     SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
     CG3State *s = CG3(obj);
 
-    memory_region_init_ram(&s->rom, NULL, "cg3.prom", FCODE_MAX_ROM_SIZE,
+    memory_region_init_ram(&s->rom, obj, "cg3.prom", FCODE_MAX_ROM_SIZE,
                            &error_abort);
     memory_region_set_readonly(&s->rom, true);
     sysbus_init_mmio(sbd, &s->rom);
 
-    memory_region_init_io(&s->reg, NULL, &cg3_reg_ops, s, "cg3.reg",
+    memory_region_init_io(&s->reg, obj, &cg3_reg_ops, s, "cg3.reg",
                           CG3_REG_SIZE);
     sysbus_init_mmio(sbd, &s->reg);
 }

hw/display/framebuffer.c

@@ -21,12 +21,40 @@
 #include "ui/console.h"
 #include "framebuffer.h"
 
+void framebuffer_update_memory_section(
+    MemoryRegionSection *mem_section,
+    MemoryRegion *root,
+    hwaddr base,
+    unsigned rows,
+    unsigned src_width)
+{
+    hwaddr src_len = (hwaddr)rows * src_width;
+
+    if (mem_section->mr) {
+        memory_region_set_log(mem_section->mr, false, DIRTY_MEMORY_VGA);
+        memory_region_unref(mem_section->mr);
+        mem_section->mr = NULL;
+    }
+
+    *mem_section = memory_region_find(root, base, src_len);
+    if (!mem_section->mr) {
+        return;
+    }
+
+    if (int128_get64(mem_section->size) < src_len ||
+            !memory_region_is_ram(mem_section->mr)) {
+        memory_region_unref(mem_section->mr);
+        mem_section->mr = NULL;
+        return;
+    }
+
+    memory_region_set_log(mem_section->mr, true, DIRTY_MEMORY_VGA);
+}
+
 /* Render an image from a shared memory framebuffer.  */
-   
 void framebuffer_update_display(
     DisplaySurface *ds,
-    MemoryRegion *address_space,
-    hwaddr base,
+    MemoryRegionSection *mem_section,
     int cols, /* Width in pixels.  */
     int rows, /* Height in pixels.  */
     int src_width, /* Length of source line, in bytes.  */
@@ -41,51 +69,33 @@ void framebuffer_update_display(
     hwaddr src_len;
     uint8_t *dest;
     uint8_t *src;
-    uint8_t *src_base;
     int first, last = 0;
     int dirty;
     int i;
     ram_addr_t addr;
-    MemoryRegionSection mem_section;
     MemoryRegion *mem;
 
     i = *first_row;
     *first_row = -1;
     src_len = src_width * rows;
 
-    mem_section = memory_region_find(address_space, base, src_len);
-    mem = mem_section.mr;
-    if (int128_get64(mem_section.size) != src_len ||
-            !memory_region_is_ram(mem_section.mr)) {
-        goto out;
+    mem = mem_section->mr;
+    if (!mem) {
+        return;
     }
-    assert(mem);
-    assert(mem_section.offset_within_address_space == base);
-
     memory_region_sync_dirty_bitmap(mem);
-    if (!memory_region_is_logging(mem, DIRTY_MEMORY_VGA)) {
-        invalidate = true;
-    }
 
-    src_base = cpu_physical_memory_map(base, &src_len, 0);
-    /* If we can't map the framebuffer then bail.  We could try harder,
-       but it's not really worth it as dirty flag tracking will probably
-       already have failed above.  */
-    if (!src_base)
-        goto out;
-    if (src_len != src_width * rows) {
-        cpu_physical_memory_unmap(src_base, src_len, 0, 0);
-        goto out;
-    }
-    src = src_base;
+    addr = mem_section->offset_within_region;
+    src = memory_region_get_ram_ptr(mem) + addr;
+
     dest = surface_data(ds);
-    if (dest_col_pitch < 0)
+    if (dest_col_pitch < 0) {
         dest -= dest_col_pitch * (cols - 1);
+    }
     if (dest_row_pitch < 0) {
         dest -= dest_row_pitch * (rows - 1);
     }
     first = -1;
-    addr = mem_section.offset_within_region;
 
     addr += i * src_width;
     src += i * src_width;
@@ -104,14 +114,11 @@ void framebuffer_update_display(
         src += src_width;
         dest += dest_row_pitch;
     }
-    cpu_physical_memory_unmap(src_base, src_len, 0, 0);
     if (first < 0) {
-        goto out;
+        return;
     }
-    memory_region_reset_dirty(mem, mem_section.offset_within_region, src_len,
+    memory_region_reset_dirty(mem, mem_section->offset_within_region, src_len,
                               DIRTY_MEMORY_VGA);
     *first_row = first;
     *last_row = last;
-out:
-    memory_region_unref(mem);
 }

hw/display/framebuffer.h

@@ -7,10 +7,50 @@
 
 typedef void (*drawfn)(void *, uint8_t *, const uint8_t *, int, int);
 
+/* framebuffer_update_memory_section: Update framebuffer
+ * #MemoryRegionSection, for example if the framebuffer is switched to
+ * a different memory area.
+ *
+ * @mem_section: Output #MemoryRegionSection, to be passed to
+ * framebuffer_update_display().
+ * @root: #MemoryRegion within which the framebuffer lies
+ * @base: Base address of the framebuffer within @root.
+ * @rows: Height of the screen.
+ * @src_width: Number of bytes in framebuffer memory between two rows.
+ */
+void framebuffer_update_memory_section(
+    MemoryRegionSection *mem_section,
+    MemoryRegion *root,
+    hwaddr base,
+    unsigned rows,
+    unsigned src_width);
+
+/* framebuffer_update_display: Draw the framebuffer on a surface.
+ *
+ * @ds: #DisplaySurface to draw to.
+ * @mem_section: #MemoryRegionSection provided by
+ * framebuffer_update_memory_section().
+ * @cols: Width the screen.
+ * @rows: Height of the screen.
+ * @src_width: Number of bytes in framebuffer memory between two rows.
+ * @dest_row_pitch: Number of bytes in the surface data between two rows.
+ * Negative if the framebuffer is stored in the opposite order (e.g.
+ * bottom-to-top) compared to the framebuffer.
+ * @dest_col_pitch: Number of bytes in the surface data between two pixels.
+ * Negative if the framebuffer is stored in the opposite order (e.g.
+ * right-to-left) compared to the framebuffer.
+ * @invalidate: True if the function should redraw the whole screen
+ * without checking the DIRTY_MEMORY_VGA dirty bitmap.
+ * @fn: Drawing function to be called for each row that has to be drawn.
+ * @opaque: Opaque pointer passed to @fn.
+ * @first_row: Pointer to an integer, receives the number of the first row
+ * that was drawn (either the first dirty row, or 0 if @invalidate is true).
+ * @last_row: Pointer to an integer, receives the number of the last row that
+ * was drawn (either the last dirty row, or @rows-1 if @invalidate is true).
+ */
 void framebuffer_update_display(
     DisplaySurface *ds,
-    MemoryRegion *address_space,
-    hwaddr base,
+    MemoryRegionSection *mem_section,
     int cols,
     int rows,
     int src_width,

hw/display/milkymist-vgafb.c

@@ -71,6 +71,7 @@ struct MilkymistVgafbState {
     SysBusDevice parent_obj;
 
     MemoryRegion regs_region;
+    MemoryRegionSection fbsection;
     QemuConsole *con;
 
     int invalidate;
@@ -91,6 +92,7 @@ static void vgafb_update_display(void *opaque)
     MilkymistVgafbState *s = opaque;
     SysBusDevice *sbd;
     DisplaySurface *surface = qemu_console_surface(s->con);
+    int src_width;
     int first = 0;
     int last = 0;
     drawfn fn;
@@ -129,11 +131,18 @@ static void vgafb_update_display(void *opaque)
         break;
     }
 
-    framebuffer_update_display(surface, sysbus_address_space(sbd),
-                               s->regs[R_BASEADDRESS] + s->fb_offset,
+    src_width = s->regs[R_HRES] * 2;
+    if (s->invalidate) {
+        framebuffer_update_memory_section(&s->fbsection,
+                                          sysbus_address_space(sbd),
+                                          s->regs[R_BASEADDRESS] + s->fb_offset,
+                                          s->regs[R_VRES], src_width);
+    }
+
+    framebuffer_update_display(surface, &s->fbsection,
                                s->regs[R_HRES],
                                s->regs[R_VRES],
-                               s->regs[R_HRES] * 2,
+                               src_width,
                                dest_width,
                                0,
                                s->invalidate,

hw/display/omap_lcdc.c

@@ -25,6 +25,7 @@
 struct omap_lcd_panel_s {
     MemoryRegion *sysmem;
     MemoryRegion iomem;
+    MemoryRegionSection fbsection;
     qemu_irq irq;
     QemuConsole *con;
 
@@ -215,12 +216,19 @@ static void omap_update_display(void *opaque)
 
     step = width * bpp >> 3;
     linesize = surface_stride(surface);
-    framebuffer_update_display(surface, omap_lcd->sysmem,
-                               frame_base, width, height,
+    if (omap_lcd->invalidate) {
+        framebuffer_update_memory_section(&omap_lcd->fbsection,
+                                          omap_lcd->sysmem, frame_base,
+                                          height, step);
+    }
+
+    framebuffer_update_display(surface, &omap_lcd->fbsection,
+                               width, height,
                                step, linesize, 0,
                                omap_lcd->invalidate,
                                draw_line, omap_lcd->palette,
                                &first, &last);
+
     if (first >= 0) {
         dpy_gfx_update(omap_lcd->con, 0, first, width, last - first + 1);
     }

hw/display/pl110.c

@@ -46,6 +46,7 @@ typedef struct PL110State {
     SysBusDevice parent_obj;
 
     MemoryRegion iomem;
+    MemoryRegionSection fbsection;
     QemuConsole *con;
 
     int version;
@@ -238,12 +239,20 @@ static void pl110_update_display(void *opaque)
     }
     dest_width *= s->cols;
     first = 0;
-    framebuffer_update_display(surface, sysbus_address_space(sbd),
-                               s->upbase, s->cols, s->rows,
+    if (s->invalidate) {
+        framebuffer_update_memory_section(&s->fbsection,
+                                          sysbus_address_space(sbd),
+                                          s->upbase,
+                                          s->rows, src_width);
+    }
+
+    framebuffer_update_display(surface, &s->fbsection,
+                               s->cols, s->rows,
                                src_width, dest_width, 0,
                                s->invalidate,
                                fn, s->palette,
                                &first, &last);
+
     if (first >= 0) {
         dpy_gfx_update(s->con, 0, first, s->cols, last - first + 1);
     }

hw/display/pxa2xx_lcd.c

@@ -35,6 +35,7 @@ struct DMAChannel {
 struct PXA2xxLCDState {
     MemoryRegion *sysmem;
     MemoryRegion iomem;
+    MemoryRegionSection fbsection;
     qemu_irq irq;
     int irqlevel;
 
@@ -687,8 +688,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot0(PXA2xxLCDState *s,
 
     dest_width = s->xres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, dest_width, s->dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette, miny, maxy);
@@ -715,8 +719,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot90(PXA2xxLCDState *s,
 
     dest_width = s->yres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, s->dest_width, -dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette,
@@ -747,8 +754,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot180(PXA2xxLCDState *s,
 
     dest_width = s->xres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, -dest_width, -s->dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette, miny, maxy);
@@ -778,8 +788,11 @@ static void pxa2xx_lcdc_dma0_redraw_rot270(PXA2xxLCDState *s,
 
     dest_width = s->yres * s->dest_width;
     *miny = 0;
-    framebuffer_update_display(surface, s->sysmem,
-                               addr, s->xres, s->yres,
+    if (s->invalidated) {
+        framebuffer_update_memory_section(&s->fbsection, s->sysmem,
+                                          addr, s->yres, src_width);
+    }
+    framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres,
                                src_width, -s->dest_width, dest_width,
                                s->invalidated,
                                fn, s->dma_ch[0].palette,

hw/display/tcx.c

@@ -944,7 +944,7 @@ static void tcx_initfn(Object *obj)
     SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
     TCXState *s = TCX(obj);
 
-    memory_region_init_ram(&s->rom, NULL, "tcx.prom", FCODE_MAX_ROM_SIZE,
+    memory_region_init_ram(&s->rom, OBJECT(s), "tcx.prom", FCODE_MAX_ROM_SIZE,
                            &error_abort);
     memory_region_set_readonly(&s->rom, true);
     sysbus_init_mmio(sbd, &s->rom);

hw/display/virtio-gpu.c

@@ -89,7 +89,8 @@ static void virtio_gpu_set_config(VirtIODevice *vdev, const uint8_t *config)
     }
 }
 
-static uint64_t virtio_gpu_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_gpu_get_features(VirtIODevice *vdev, uint64_t features,
+                                        Error **errp)
 {
     return features;
 }

hw/i386/acpi-build.c

@@ -1108,8 +1108,8 @@ build_ssdt(GArray *table_data, GArray *linker,
         aml_append(field, aml_named_field("PEPT", 8));
         aml_append(dev, field);
 
-        /* device present, functioning, decoding, not shown in UI */
-        aml_append(dev, aml_name_decl("_STA", aml_int(0xB)));
+        /* device present, functioning, decoding, shown in UI */
+        aml_append(dev, aml_name_decl("_STA", aml_int(0xF)));
 
         method = aml_method("RDPT", 0);
         aml_append(method, aml_store(aml_name("PEPT"), aml_local(0)));

hw/ide/ahci.c

@@ -50,7 +50,6 @@ static void ahci_reset_port(AHCIState *s, int port);
 static void ahci_write_fis_d2h(AHCIDevice *ad, uint8_t *cmd_fis);
 static void ahci_init_d2h(AHCIDevice *ad);
 static int ahci_dma_prepare_buf(IDEDMA *dma, int32_t limit);
-static void ahci_commit_buf(IDEDMA *dma, uint32_t tx_bytes);
 static bool ahci_map_clb_address(AHCIDevice *ad);
 static bool ahci_map_fis_address(AHCIDevice *ad);
 static void ahci_unmap_clb_address(AHCIDevice *ad);
@@ -1290,7 +1289,7 @@ out:
     s->data_ptr = s->data_end;
 
     /* Update number of transferred bytes, destroy sglist */
-    ahci_commit_buf(dma, size);
+    dma_buf_commit(s, size);
 
     s->end_transfer_func(s);
 
@@ -1332,9 +1331,8 @@ static void ahci_restart(IDEDMA *dma)
 }
 
 /**
- * Called in DMA R/W chains to read the PRDT, utilizing ahci_populate_sglist.
- * Not currently invoked by PIO R/W chains,
- * which invoke ahci_populate_sglist via ahci_start_transfer.
+ * Called in DMA and PIO R/W chains to read the PRDT.
+ * Not shared with NCQ pathways.
  */
 static int32_t ahci_dma_prepare_buf(IDEDMA *dma, int32_t limit)
 {
@@ -1353,21 +1351,16 @@ static int32_t ahci_dma_prepare_buf(IDEDMA *dma, int32_t limit)
 }
 
 /**
- * Destroys the scatter-gather list,
- * and updates the command header with a bytes-read value.
- * called explicitly via ahci_dma_rw_buf (ATAPI DMA),
- * and ahci_start_transfer (PIO R/W),
- * and called via callback from ide_dma_cb for DMA R/W paths.
+ * Updates the command header with a bytes-read value.
+ * Called via dma_buf_commit, for both DMA and PIO paths.
+ * sglist destruction is handled within dma_buf_commit.
  */
 static void ahci_commit_buf(IDEDMA *dma, uint32_t tx_bytes)
 {
     AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
-    IDEState *s = &ad->port.ifs[0];
 
     tx_bytes += le32_to_cpu(ad->cur_cmd->status);
     ad->cur_cmd->status = cpu_to_le32(tx_bytes);
-
-    qemu_sglist_destroy(&s->sg);
 }
 
 static int ahci_dma_rw_buf(IDEDMA *dma, int is_write)
@@ -1388,10 +1381,9 @@ static int ahci_dma_rw_buf(IDEDMA *dma, int is_write)
     }
 
     /* free sglist, update byte count */
-    ahci_commit_buf(dma, l);
+    dma_buf_commit(s, l);
 
     s->io_buffer_index += l;
-    s->io_buffer_offset += l;
 
     DPRINTF(ad->port_no, "len=%#x\n", l);
 

hw/ide/ahci.h

@@ -127,7 +127,7 @@
 #define PORT_CMD_SPIN_UP          (1 << 1) /* Spin up device */
 #define PORT_CMD_START            (1 << 0) /* Enable port DMA engine */
 
-#define PORT_CMD_ICC_MASK         (0xf << 28) /* i/f ICC state mask */
+#define PORT_CMD_ICC_MASK        (0xfU << 28) /* i/f ICC state mask */
 #define PORT_CMD_ICC_ACTIVE       (0x1 << 28) /* Put i/f in active state */
 #define PORT_CMD_ICC_PARTIAL      (0x2 << 28) /* Put i/f in partial state */
 #define PORT_CMD_ICC_SLUMBER      (0x6 << 28) /* Put i/f in slumber state */

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

@@ -591,7 +591,6 @@ static void ide_sector_read_cb(void *opaque, int ret)
     s->nsector -= n;
     /* Allow the guest to read the io_buffer */
     ide_transfer_start(s, s->io_buffer, n * BDRV_SECTOR_SIZE, ide_sector_read);
-    s->io_buffer_offset += 512 * n;
     ide_set_irq(s->bus);
 }
 
@@ -635,11 +634,12 @@ static void ide_sector_read(IDEState *s)
                                  ide_sector_read_cb, s);
 }
 
-static void dma_buf_commit(IDEState *s, uint32_t tx_bytes)
+void dma_buf_commit(IDEState *s, uint32_t tx_bytes)
 {
     if (s->bus->dma->ops->commit_buf) {
         s->bus->dma->ops->commit_buf(s->bus->dma, tx_bytes);
     }
+    s->io_buffer_offset += tx_bytes;
     qemu_sglist_destroy(&s->sg);
 }
 
@@ -842,7 +842,6 @@ static void ide_sector_write_cb(void *opaque, int ret)
         n = s->req_nb_sectors;
     }
     s->nsector -= n;
-    s->io_buffer_offset += 512 * n;
 
     ide_set_sector(s, ide_get_sector(s) + n);
     if (s->nsector == 0) {
@@ -1747,11 +1746,11 @@ static const struct {
 } ide_cmd_table[0x100] = {
     /* NOP not implemented, mandatory for CD */
     [CFA_REQ_EXT_ERROR_CODE]      = { cmd_cfa_req_ext_error_code, CFA_OK },
-    [WIN_DSM]                     = { cmd_data_set_management, ALL_OK },
+    [WIN_DSM]                     = { cmd_data_set_management, HD_CFA_OK },
     [WIN_DEVICE_RESET]            = { cmd_device_reset, CD_OK },
     [WIN_RECAL]                   = { cmd_nop, HD_CFA_OK | SET_DSC},
     [WIN_READ]                    = { cmd_read_pio, ALL_OK },
-    [WIN_READ_ONCE]               = { cmd_read_pio, ALL_OK },
+    [WIN_READ_ONCE]               = { cmd_read_pio, HD_CFA_OK },
     [WIN_READ_EXT]                = { cmd_read_pio, HD_CFA_OK },
     [WIN_READDMA_EXT]             = { cmd_read_dma, HD_CFA_OK },
     [WIN_READ_NATIVE_MAX_EXT]     = { cmd_read_native_max, HD_CFA_OK | SET_DSC },
@@ -1770,12 +1769,12 @@ static const struct {
     [CFA_TRANSLATE_SECTOR]        = { cmd_cfa_translate_sector, CFA_OK },
     [WIN_DIAGNOSE]                = { cmd_exec_dev_diagnostic, ALL_OK },
     [WIN_SPECIFY]                 = { cmd_nop, HD_CFA_OK | SET_DSC },
-    [WIN_STANDBYNOW2]             = { cmd_nop, ALL_OK },
-    [WIN_IDLEIMMEDIATE2]          = { cmd_nop, ALL_OK },
-    [WIN_STANDBY2]                = { cmd_nop, ALL_OK },
-    [WIN_SETIDLE2]                = { cmd_nop, ALL_OK },
-    [WIN_CHECKPOWERMODE2]         = { cmd_check_power_mode, ALL_OK | SET_DSC },
-    [WIN_SLEEPNOW2]               = { cmd_nop, ALL_OK },
+    [WIN_STANDBYNOW2]             = { cmd_nop, HD_CFA_OK },
+    [WIN_IDLEIMMEDIATE2]          = { cmd_nop, HD_CFA_OK },
+    [WIN_STANDBY2]                = { cmd_nop, HD_CFA_OK },
+    [WIN_SETIDLE2]                = { cmd_nop, HD_CFA_OK },
+    [WIN_CHECKPOWERMODE2]         = { cmd_check_power_mode, HD_CFA_OK | SET_DSC },
+    [WIN_SLEEPNOW2]               = { cmd_nop, HD_CFA_OK },
     [WIN_PACKETCMD]               = { cmd_packet, CD_OK },
     [WIN_PIDENTIFY]               = { cmd_identify_packet, CD_OK },
     [WIN_SMART]                   = { cmd_smart, HD_CFA_OK | SET_DSC },
@@ -1789,19 +1788,19 @@ static const struct {
     [WIN_WRITEDMA]                = { cmd_write_dma, HD_CFA_OK },
     [WIN_WRITEDMA_ONCE]           = { cmd_write_dma, HD_CFA_OK },
     [CFA_WRITE_MULTI_WO_ERASE]    = { cmd_write_multiple, CFA_OK },
-    [WIN_STANDBYNOW1]             = { cmd_nop, ALL_OK },
-    [WIN_IDLEIMMEDIATE]           = { cmd_nop, ALL_OK },
-    [WIN_STANDBY]                 = { cmd_nop, ALL_OK },
-    [WIN_SETIDLE1]                = { cmd_nop, ALL_OK },
-    [WIN_CHECKPOWERMODE1]         = { cmd_check_power_mode, ALL_OK | SET_DSC },
-    [WIN_SLEEPNOW1]               = { cmd_nop, ALL_OK },
+    [WIN_STANDBYNOW1]             = { cmd_nop, HD_CFA_OK },
+    [WIN_IDLEIMMEDIATE]           = { cmd_nop, HD_CFA_OK },
+    [WIN_STANDBY]                 = { cmd_nop, HD_CFA_OK },
+    [WIN_SETIDLE1]                = { cmd_nop, HD_CFA_OK },
+    [WIN_CHECKPOWERMODE1]         = { cmd_check_power_mode, HD_CFA_OK | SET_DSC },
+    [WIN_SLEEPNOW1]               = { cmd_nop, HD_CFA_OK },
     [WIN_FLUSH_CACHE]             = { cmd_flush_cache, ALL_OK },
     [WIN_FLUSH_CACHE_EXT]         = { cmd_flush_cache, HD_CFA_OK },
     [WIN_IDENTIFY]                = { cmd_identify, ALL_OK },
     [WIN_SETFEATURES]             = { cmd_set_features, ALL_OK | SET_DSC },
     [IBM_SENSE_CONDITION]         = { cmd_ibm_sense_condition, CFA_OK | SET_DSC },
     [CFA_WEAR_LEVEL]              = { cmd_cfa_erase_sectors, HD_CFA_OK | SET_DSC },
-    [WIN_READ_NATIVE_MAX]         = { cmd_read_native_max, ALL_OK | SET_DSC },
+    [WIN_READ_NATIVE_MAX]         = { cmd_read_native_max, HD_CFA_OK | SET_DSC },
 };
 
 static bool ide_cmd_permitted(IDEState *s, uint32_t cmd)
@@ -2021,11 +2020,17 @@ 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 +2047,17 @@ 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 +2074,17 @@ 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 +2101,17 @@ 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/internal.h

@@ -536,6 +536,7 @@ int64_t ide_get_sector(IDEState *s);
 void ide_set_sector(IDEState *s, int64_t sector_num);
 
 void ide_start_dma(IDEState *s, BlockCompletionFunc *cb);
+void dma_buf_commit(IDEState *s, uint32_t tx_bytes);
 void ide_dma_error(IDEState *s);
 
 void ide_atapi_cmd_ok(IDEState *s);

hw/ide/macio.c

@@ -208,6 +208,33 @@ static void pmac_dma_write(BlockBackend *blk,
                               cb, io);
 }
 
+static void pmac_dma_trim(BlockBackend *blk,
+                        int64_t offset, int bytes,
+                        void (*cb)(void *opaque, int ret), void *opaque)
+{
+    DBDMA_io *io = opaque;
+    MACIOIDEState *m = io->opaque;
+    IDEState *s = idebus_active_if(&m->bus);
+    dma_addr_t dma_addr, dma_len;
+    void *mem;
+
+    qemu_iovec_destroy(&io->iov);
+    qemu_iovec_init(&io->iov, io->len / MACIO_PAGE_SIZE + 1);
+
+    dma_addr = io->addr;
+    dma_len = io->len;
+    mem = dma_memory_map(&address_space_memory, dma_addr, &dma_len,
+                         DMA_DIRECTION_TO_DEVICE);
+
+    qemu_iovec_add(&io->iov, mem, io->len);
+    s->io_buffer_size -= io->len;
+    s->io_buffer_index += io->len;
+    io->len = 0;
+
+    m->aiocb = ide_issue_trim(blk, (offset >> 9), &io->iov, (bytes >> 9),
+                              cb, io);
+}
+
 static void pmac_ide_atapi_transfer_cb(void *opaque, int ret)
 {
     DBDMA_io *io = opaque;
@@ -313,6 +340,7 @@ static void pmac_ide_transfer_cb(void *opaque, int ret)
         pmac_dma_write(s->blk, offset, io->len, pmac_ide_transfer_cb, io);
         break;
     case IDE_DMA_TRIM:
+        pmac_dma_trim(s->blk, offset, io->len, pmac_ide_transfer_cb, io);
         break;
     }
 

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/input/virtio-input.c

@@ -20,6 +20,10 @@ void virtio_input_send(VirtIOInput *vinput, virtio_input_event *event)
     unsigned have, need;
     int i, len;
 
+    if (!vinput->active) {
+        return;
+    }
+
     /* queue up events ... */
     if (vinput->qindex == vinput->qsize) {
         vinput->qsize++;
@@ -166,7 +170,8 @@ static void virtio_input_set_config(VirtIODevice *vdev,
     virtio_notify_config(vdev);
 }
 
-static uint64_t virtio_input_get_features(VirtIODevice *vdev, uint64_t f)
+static uint64_t virtio_input_get_features(VirtIODevice *vdev, uint64_t f,
+                                          Error **errp)
 {
     return f;
 }

hw/misc/arm_integrator_debug.c

@@ -79,7 +79,7 @@ static void intdbg_control_init(Object *obj)
     SysBusDevice *sd = SYS_BUS_DEVICE(obj);
     IntegratorDebugState *s = INTEGRATOR_DEBUG(obj);
 
-    memory_region_init_io(&s->iomem, NULL, &intdbg_control_ops,
+    memory_region_init_io(&s->iomem, obj, &intdbg_control_ops,
                           NULL, "dbg-leds", 0x1000000);
     sysbus_init_mmio(sd, &s->iomem);
 }

hw/misc/macio/cuda.c

@@ -713,7 +713,7 @@ static void cuda_initfn(Object *obj)
     CUDAState *s = CUDA(obj);
     int i;
 
-    memory_region_init_io(&s->mem, NULL, &cuda_ops, s, "cuda", 0x2000);
+    memory_region_init_io(&s->mem, obj, &cuda_ops, s, "cuda", 0x2000);
     sysbus_init_mmio(d, &s->mem);
     sysbus_init_irq(d, &s->irq);
 

hw/misc/macio/mac_dbdma.c

@@ -590,10 +590,11 @@ dbdma_control_write(DBDMA_channel *ch)
     if ((ch->regs[DBDMA_STATUS] & RUN) && !(status & RUN)) {
         /* RUN is cleared */
         status &= ~(ACTIVE|DEAD);
-        if ((status & FLUSH) && ch->flush) {
-            ch->flush(&ch->io);
-            status &= ~FLUSH;
-        }
+    }
+
+    if ((status & FLUSH) && ch->flush) {
+        ch->flush(&ch->io);
+        status &= ~FLUSH;
     }
 
     DBDMA_DPRINTF("    status 0x%08x\n", status);
@@ -603,9 +604,6 @@ dbdma_control_write(DBDMA_channel *ch)
     if (status & ACTIVE) {
         DBDMA_kick(dbdma_from_ch(ch));
     }
-    if ((status & FLUSH) && ch->flush) {
-        ch->flush(&ch->io);
-    }
 }
 
 static void dbdma_write(void *opaque, hwaddr addr,

hw/misc/macio/macio.c

@@ -105,10 +105,10 @@ static void macio_escc_legacy_setup(MacIOState *macio_state)
         0xF0, 0xE0,
     };
 
-    memory_region_init(escc_legacy, NULL, "escc-legacy", 256);
+    memory_region_init(escc_legacy, OBJECT(macio_state), "escc-legacy", 256);
     for (i = 0; i < ARRAY_SIZE(maps); i += 2) {
         MemoryRegion *port = g_new(MemoryRegion, 1);
-        memory_region_init_alias(port, NULL, "escc-legacy-port",
+        memory_region_init_alias(port, OBJECT(macio_state), "escc-legacy-port",
                                  macio_state->escc_mem, maps[i+1], 0x2);
         memory_region_add_subregion(escc_legacy, maps[i], port);
     }
@@ -131,6 +131,10 @@ static void macio_common_realize(PCIDevice *d, Error **errp)
     MacIOState *s = MACIO(d);
     SysBusDevice *sysbus_dev;
     Error *err = NULL;
+    MemoryRegion *dbdma_mem;
+
+    s->dbdma = DBDMA_init(&dbdma_mem);
+    memory_region_add_subregion(&s->bar, 0x08000, dbdma_mem);
 
     object_property_set_bool(OBJECT(&s->cuda), true, "realized", &err);
     if (err) {
@@ -328,16 +332,12 @@ static void macio_newworld_init(Object *obj)
 static void macio_instance_init(Object *obj)
 {
     MacIOState *s = MACIO(obj);
-    MemoryRegion *dbdma_mem;
 
-    memory_region_init(&s->bar, NULL, "macio", 0x80000);
+    memory_region_init(&s->bar, obj, "macio", 0x80000);
 
     object_initialize(&s->cuda, sizeof(s->cuda), TYPE_CUDA);
     qdev_set_parent_bus(DEVICE(&s->cuda), sysbus_get_default());
     object_property_add_child(obj, "cuda", OBJECT(&s->cuda), NULL);
-
-    s->dbdma = DBDMA_init(&dbdma_mem);
-    memory_region_add_subregion(&s->bar, 0x08000, dbdma_mem);
 }
 
 static const VMStateDescription vmstate_macio_oldworld = {

hw/misc/zynq_slcr.c

@@ -393,12 +393,12 @@ static void zynq_slcr_write(void *opaque, hwaddr offset,
         return;
     }
 
-    if (!s->regs[LOCKSTA]) {
-        s->regs[offset / 4] = val;
-    } else {
-        DB_PRINT("SCLR registers are locked. Unlock them first\n");
+    if (s->regs[LOCKSTA]) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "SCLR registers are locked. Unlock them first\n");
         return;
     }
+    s->regs[offset] = val;
 
     switch (offset) {
     case PSS_RST_CTRL:

hw/net/dp8393x.c

@@ -327,9 +327,14 @@ static void dp8393x_do_stop_timer(dp8393xState *s)
     dp8393x_update_wt_regs(s);
 }
 
+static int dp8393x_can_receive(NetClientState *nc);
+
 static void dp8393x_do_receiver_enable(dp8393xState *s)
 {
     s->regs[SONIC_CR] &= ~SONIC_CR_RXDIS;
+    if (dp8393x_can_receive(s->nic->ncs)) {
+        qemu_flush_queued_packets(qemu_get_queue(s->nic));
+    }
 }
 
 static void dp8393x_do_receiver_disable(dp8393xState *s)
@@ -569,6 +574,9 @@ static void dp8393x_write(void *opaque, hwaddr addr, uint64_t data,
                 dp8393x_do_read_rra(s);
             }
             dp8393x_update_irq(s);
+            if (dp8393x_can_receive(s->nic->ncs)) {
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
             break;
         /* Ignore least significant bit */
         case SONIC_RSA:
@@ -635,11 +643,6 @@ static int dp8393x_receive_filter(dp8393xState *s, const uint8_t * buf,
     static const uint8_t bcast[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
     int i;
 
-    /* Check for runt packet (remember that checksum is not there) */
-    if (size < 64 - 4) {
-        return (s->regs[SONIC_RCR] & SONIC_RCR_RNT) ? 0 : -1;
-    }
-
     /* Check promiscuous mode */
     if ((s->regs[SONIC_RCR] & SONIC_RCR_PRO) && (buf[0] & 1) == 0) {
         return 0;
@@ -828,6 +831,7 @@ static void dp8393x_realize(DeviceState *dev, Error **errp)
     dp8393xState *s = DP8393X(dev);
     int i, checksum;
     uint8_t *prom;
+    Error *local_err = NULL;
 
     address_space_init(&s->as, s->dma_mr, "dp8393x");
     memory_region_init_io(&s->mmio, OBJECT(dev), &dp8393x_ops, s,
@@ -840,8 +844,13 @@ static void dp8393x_realize(DeviceState *dev, Error **errp)
     s->watchdog = timer_new_ns(QEMU_CLOCK_VIRTUAL, dp8393x_watchdog, s);
     s->regs[SONIC_SR] = 0x0004; /* only revision recognized by Linux */
 
-    memory_region_init_rom_device(&s->prom, OBJECT(dev), NULL, NULL,
-                                  "dp8393x-prom", SONIC_PROM_SIZE, NULL);
+    memory_region_init_ram(&s->prom, OBJECT(dev),
+                           "dp8393x-prom", SONIC_PROM_SIZE, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+    memory_region_set_readonly(&s->prom, true);
     prom = memory_region_get_ram_ptr(&s->prom);
     checksum = 0;
     for (i = 0; i < 6; i++) {
@@ -881,6 +890,8 @@ static void dp8393x_class_init(ObjectClass *klass, void *data)
     dc->reset = dp8393x_reset;
     dc->vmsd = &vmstate_dp8393x;
     dc->props = dp8393x_properties;
+    /* Reason: dma_mr property can't be set */
+    dc->cannot_instantiate_with_device_add_yet = true;
 }
 
 static const TypeInfo dp8393x_info = {

hw/net/e1000.c

@@ -740,7 +740,8 @@ process_tx_desc(E1000State *s, struct e1000_tx_desc *dp)
                 memmove(tp->data, tp->header, tp->hdr_len);
                 tp->size = tp->hdr_len;
             }
-        } while (split_size -= bytes);
+            split_size -= bytes;
+        } while (bytes && split_size);
     } else if (!tp->tse && tp->cptse) {
         // context descriptor TSE is not set, while data descriptor TSE is set
         DBGOUT(TXERR, "TCP segmentation error\n");

hw/net/eepro100.c

@@ -1617,16 +1617,6 @@ static const MemoryRegionOps eepro100_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
-static int nic_can_receive(NetClientState *nc)
-{
-    EEPRO100State *s = qemu_get_nic_opaque(nc);
-    TRACE(RXTX, logout("%p\n", s));
-    return get_ru_state(s) == ru_ready;
-#if 0
-    return !eepro100_buffer_full(s);
-#endif
-}
-
 static ssize_t nic_receive(NetClientState *nc, const uint8_t * buf, size_t size)
 {
     /* TODO:
@@ -1844,7 +1834,6 @@ static void pci_nic_uninit(PCIDevice *pci_dev)
 static NetClientInfo net_eepro100_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = nic_can_receive,
     .receive = nic_receive,
 };
 

hw/net/fsl_etsec/etsec.c

@@ -338,25 +338,26 @@ static void etsec_reset(DeviceState *d)
         MII_SR_100X_FD_CAPS     | MII_SR_100T4_CAPS;
 }
 
-static int etsec_can_receive(NetClientState *nc)
-{
-    eTSEC *etsec = qemu_get_nic_opaque(nc);
-
-    return etsec->rx_buffer_len == 0;
-}
-
 static ssize_t etsec_receive(NetClientState *nc,
                              const uint8_t  *buf,
                              size_t          size)
 {
+    ssize_t ret;
     eTSEC *etsec = qemu_get_nic_opaque(nc);
 
 #if defined(HEX_DUMP)
     fprintf(stderr, "%s receive size:%d\n", etsec->nic->nc.name, size);
     qemu_hexdump(buf, stderr, "", size);
 #endif
-    etsec_rx_ring_write(etsec, buf, size);
-    return size;
+    /* Flush is unnecessary as are already in receiving path */
+    etsec->need_flush = false;
+    ret = etsec_rx_ring_write(etsec, buf, size);
+    if (ret == 0) {
+        /* The packet will be queued, let's flush it when buffer is avilable
+         * again. */
+        etsec->need_flush = true;
+    }
+    return ret;
 }
 
 
@@ -370,7 +371,6 @@ static void etsec_set_link_status(NetClientState *nc)
 static NetClientInfo net_etsec_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = etsec_can_receive,
     .receive = etsec_receive,
     .link_status_changed = etsec_set_link_status,
 };

hw/net/fsl_etsec/etsec.h

@@ -144,6 +144,8 @@ typedef struct eTSEC {
     QEMUBH *bh;
     struct ptimer_state *ptimer;
 
+    /* Whether we should flush the rx queue when buffer becomes available. */
+    bool need_flush;
 } eTSEC;
 
 #define TYPE_ETSEC_COMMON "eTSEC"
@@ -162,7 +164,7 @@ DeviceState *etsec_create(hwaddr        base,
 
 void etsec_walk_tx_ring(eTSEC *etsec, int ring_nbr);
 void etsec_walk_rx_ring(eTSEC *etsec, int ring_nbr);
-void etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size);
+ssize_t etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size);
 
 void etsec_write_miim(eTSEC          *etsec,
                       eTSEC_Register *reg,

hw/net/fsl_etsec/rings.c

@@ -481,40 +481,42 @@ static void rx_init_frame(eTSEC *etsec, const uint8_t *buf, size_t size)
                etsec->rx_buffer_len, etsec->rx_padding);
 }
 
-void etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size)
+ssize_t etsec_rx_ring_write(eTSEC *etsec, const uint8_t *buf, size_t size)
 {
     int ring_nbr = 0;           /* Always use ring0 (no filer) */
 
     if (etsec->rx_buffer_len != 0) {
         RING_DEBUG("%s: We can't receive now,"
                    " a buffer is already in the pipe\n", __func__);
-        return;
+        return 0;
     }
 
     if (etsec->regs[RSTAT].value & 1 << (23 - ring_nbr)) {
         RING_DEBUG("%s: The ring is halted\n", __func__);
-        return;
+        return -1;
     }
 
     if (etsec->regs[DMACTRL].value & DMACTRL_GRS) {
         RING_DEBUG("%s: Graceful receive stop\n", __func__);
-        return;
+        return -1;
     }
 
     if (!(etsec->regs[MACCFG1].value & MACCFG1_RX_EN)) {
         RING_DEBUG("%s: MAC Receive not enabled\n", __func__);
-        return;
+        return -1;
     }
 
     if ((etsec->regs[RCTRL].value & RCTRL_RSF) && (size < 60)) {
         /* CRC is not in the packet yet, so short frame is below 60 bytes */
         RING_DEBUG("%s: Drop short frame\n", __func__);
-        return;
+        return -1;
     }
 
     rx_init_frame(etsec, buf, size);
 
     etsec_walk_rx_ring(etsec, ring_nbr);
+
+    return size;
 }
 
 void etsec_walk_rx_ring(eTSEC *etsec, int ring_nbr)
@@ -644,6 +646,9 @@ void etsec_walk_rx_ring(eTSEC *etsec, int ring_nbr)
     } else {
         etsec->rx_buffer_len = 0;
         etsec->rx_buffer     = NULL;
+        if (etsec->need_flush) {
+            qemu_flush_queued_packets(qemu_get_queue(etsec->nic));
+        }
     }
 
     RING_DEBUG("eTSEC End of ring_write: remaining_data:%zu\n", remaining_data);

hw/net/lance.c

@@ -94,7 +94,6 @@ static const MemoryRegionOps lance_mem_ops = {
 static NetClientInfo net_lance_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = pcnet_can_receive,
     .receive = pcnet_receive,
     .link_status_changed = pcnet_set_link_status,
 };

hw/net/mcf_fec.c

@@ -8,6 +8,7 @@
 #include "hw/hw.h"
 #include "net/net.h"
 #include "hw/m68k/mcf.h"
+#include "hw/net/mii.h"
 /* For crc32 */
 #include <zlib.h>
 #include "exec/address-spaces.h"
@@ -195,12 +196,14 @@ static void mcf_fec_do_tx(mcf_fec_state *s)
 
 static void mcf_fec_enable_rx(mcf_fec_state *s)
 {
+    NetClientState *nc = qemu_get_queue(s->nic);
     mcf_fec_bd bd;
 
     mcf_fec_read_bd(&bd, s->rx_descriptor);
     s->rx_enabled = ((bd.flags & FEC_BD_E) != 0);
-    if (!s->rx_enabled)
-        DPRINTF("RX buffer full\n");
+    if (s->rx_enabled) {
+        qemu_flush_queued_packets(nc);
+    }
 }
 
 static void mcf_fec_reset(mcf_fec_state *s)
@@ -216,6 +219,51 @@ static void mcf_fec_reset(mcf_fec_state *s)
     s->rfsr = 0x500;
 }
 
+#define MMFR_WRITE_OP	(1 << 28)
+#define MMFR_READ_OP	(2 << 28)
+#define MMFR_PHYADDR(v)	(((v) >> 23) & 0x1f)
+#define MMFR_REGNUM(v)	(((v) >> 18) & 0x1f)
+
+static uint64_t mcf_fec_read_mdio(mcf_fec_state *s)
+{
+    uint64_t v;
+
+    if (s->mmfr & MMFR_WRITE_OP)
+        return s->mmfr;
+    if (MMFR_PHYADDR(s->mmfr) != 1)
+        return s->mmfr |= 0xffff;
+
+    switch (MMFR_REGNUM(s->mmfr)) {
+    case MII_BMCR:
+        v = MII_BMCR_SPEED | MII_BMCR_AUTOEN | MII_BMCR_FD;
+        break;
+    case MII_BMSR:
+        v = MII_BMSR_100TX_FD | MII_BMSR_100TX_HD | MII_BMSR_10T_FD |
+            MII_BMSR_10T_HD | MII_BMSR_MFPS | MII_BMSR_AN_COMP |
+            MII_BMSR_AUTONEG | MII_BMSR_LINK_ST;
+        break;
+    case MII_PHYID1:
+        v = DP83848_PHYID1;
+        break;
+    case MII_PHYID2:
+        v = DP83848_PHYID2;
+        break;
+    case MII_ANAR:
+        v = MII_ANAR_TXFD | MII_ANAR_TX | MII_ANAR_10FD |
+            MII_ANAR_10 | MII_ANAR_CSMACD;
+        break;
+    case MII_ANLPAR:
+        v = MII_ANLPAR_ACK | MII_ANLPAR_TXFD | MII_ANLPAR_TX |
+            MII_ANLPAR_10FD | MII_ANLPAR_10 | MII_ANLPAR_CSMACD;
+        break;
+    default:
+        v = 0xffff;
+        break;
+    }
+    s->mmfr = (s->mmfr & ~0xffff) | v;
+    return s->mmfr;
+}
+
 static uint64_t mcf_fec_read(void *opaque, hwaddr addr,
                              unsigned size)
 {
@@ -226,7 +274,7 @@ static uint64_t mcf_fec_read(void *opaque, hwaddr addr,
     case 0x010: return s->rx_enabled ? (1 << 24) : 0; /* RDAR */
     case 0x014: return 0; /* TDAR */
     case 0x024: return s->ecr;
-    case 0x040: return s->mmfr;
+    case 0x040: return mcf_fec_read_mdio(s);
     case 0x044: return s->mscr;
     case 0x064: return 0; /* MIBC */
     case 0x084: return s->rcr;
@@ -287,8 +335,8 @@ static void mcf_fec_write(void *opaque, hwaddr addr,
         }
         break;
     case 0x040:
-        /* TODO: Implement MII.  */
         s->mmfr = value;
+        s->eir |= FEC_INT_MII;
         break;
     case 0x044:
         s->mscr = value & 0xfe;
@@ -351,10 +399,30 @@ static void mcf_fec_write(void *opaque, hwaddr addr,
     mcf_fec_update(s);
 }
 
-static int mcf_fec_can_receive(NetClientState *nc)
+static int mcf_fec_have_receive_space(mcf_fec_state *s, size_t want)
 {
-    mcf_fec_state *s = qemu_get_nic_opaque(nc);
-    return s->rx_enabled;
+    mcf_fec_bd bd;
+    uint32_t addr;
+
+    /* Walk descriptor list to determine if we have enough buffer */
+    addr = s->rx_descriptor;
+    while (want > 0) {
+        mcf_fec_read_bd(&bd, addr);
+        if ((bd.flags & FEC_BD_E) == 0) {
+            return 0;
+        }
+        if (want < s->emrbr) {
+            return 1;
+        }
+        want -= s->emrbr;
+        /* Advance to the next descriptor.  */
+        if ((bd.flags & FEC_BD_W) != 0) {
+            addr = s->erdsr;
+        } else {
+            addr += 8;
+        }
+    }
+    return 0;
 }
 
 static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t size)
@@ -367,10 +435,11 @@ static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t si
     uint32_t buf_addr;
     uint8_t *crc_ptr;
     unsigned int buf_len;
+    size_t retsize;
 
     DPRINTF("do_rx len %d\n", size);
     if (!s->rx_enabled) {
-        fprintf(stderr, "mcf_fec_receive: Unexpected packet\n");
+        return -1;
     }
     /* 4 bytes for the CRC.  */
     size += 4;
@@ -385,17 +454,14 @@ static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t si
     if (size > (s->rcr >> 16)) {
         flags |= FEC_BD_LG;
     }
+    /* Check if we have enough space in current descriptors */
+    if (!mcf_fec_have_receive_space(s, size)) {
+        return 0;
+    }
     addr = s->rx_descriptor;
+    retsize = size;
     while (size > 0) {
         mcf_fec_read_bd(&bd, addr);
-        if ((bd.flags & FEC_BD_E) == 0) {
-            /* No descriptors available.  Bail out.  */
-            /* FIXME: This is wrong.  We should probably either save the
-               remainder for when more RX buffers are available, or
-               flag an error.  */
-            fprintf(stderr, "mcf_fec: Lost end of frame\n");
-            break;
-        }
         buf_len = (size <= s->emrbr) ? size: s->emrbr;
         bd.length = buf_len;
         size -= buf_len;
@@ -430,7 +496,7 @@ static ssize_t mcf_fec_receive(NetClientState *nc, const uint8_t *buf, size_t si
     s->rx_descriptor = addr;
     mcf_fec_enable_rx(s);
     mcf_fec_update(s);
-    return size;
+    return retsize;
 }
 
 static const MemoryRegionOps mcf_fec_ops = {
@@ -442,7 +508,6 @@ static const MemoryRegionOps mcf_fec_ops = {
 static NetClientInfo net_mcf_fec_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = mcf_fec_can_receive,
     .receive = mcf_fec_receive,
 };
 

hw/net/milkymist-minimac2.c

@@ -303,8 +303,7 @@ static ssize_t minimac2_rx(NetClientState *nc, const uint8_t *buf, size_t size)
         r_state = R_STATE1;
         rx_buf = s->rx1_buf;
     } else {
-        trace_milkymist_minimac2_drop_rx_frame(buf);
-        return size;
+        return 0;
     }
 
     /* assemble frame */
@@ -354,6 +353,18 @@ minimac2_read(void *opaque, hwaddr addr, unsigned size)
     return r;
 }
 
+static int minimac2_can_rx(MilkymistMinimac2State *s)
+{
+    if (s->regs[R_STATE0] == STATE_LOADED) {
+        return 1;
+    }
+    if (s->regs[R_STATE1] == STATE_LOADED) {
+        return 1;
+    }
+
+    return 0;
+}
+
 static void
 minimac2_write(void *opaque, hwaddr addr, uint64_t value,
                unsigned size)
@@ -387,6 +398,9 @@ minimac2_write(void *opaque, hwaddr addr, uint64_t value,
     case R_STATE1:
         s->regs[addr] = value;
         update_rx_interrupt(s);
+        if (minimac2_can_rx(s)) {
+            qemu_flush_queued_packets(qemu_get_queue(s->nic));
+        }
         break;
     case R_SETUP:
     case R_COUNT0:
@@ -411,20 +425,6 @@ static const MemoryRegionOps minimac2_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
-static int minimac2_can_rx(NetClientState *nc)
-{
-    MilkymistMinimac2State *s = qemu_get_nic_opaque(nc);
-
-    if (s->regs[R_STATE0] == STATE_LOADED) {
-        return 1;
-    }
-    if (s->regs[R_STATE1] == STATE_LOADED) {
-        return 1;
-    }
-
-    return 0;
-}
-
 static void milkymist_minimac2_reset(DeviceState *d)
 {
     MilkymistMinimac2State *s = MILKYMIST_MINIMAC2(d);
@@ -445,7 +445,6 @@ static void milkymist_minimac2_reset(DeviceState *d)
 static NetClientInfo net_milkymist_minimac2_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = minimac2_can_rx,
     .receive = minimac2_rx,
 };
 

hw/net/mipsnet.c

@@ -80,7 +80,7 @@ static ssize_t mipsnet_receive(NetClientState *nc, const uint8_t *buf, size_t si
 
     trace_mipsnet_receive(size);
     if (!mipsnet_can_receive(nc))
-        return -1;
+        return 0;
 
     s->busy = 1;
 
@@ -134,6 +134,9 @@ static uint64_t mipsnet_ioport_read(void *opaque, hwaddr addr,
         if (s->rx_count) {
             s->rx_count--;
             ret = s->rx_buffer[s->rx_read++];
+            if (mipsnet_can_receive(s->nic->ncs)) {
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
         }
         break;
     /* Reads as zero. */
@@ -170,6 +173,9 @@ static void mipsnet_ioport_write(void *opaque, hwaddr addr,
         }
         s->busy = !!s->intctl;
         mipsnet_update_irq(s);
+        if (mipsnet_can_receive(s->nic->ncs)) {
+            qemu_flush_queued_packets(qemu_get_queue(s->nic));
+        }
         break;
     case MIPSNET_TX_DATA_BUFFER:
         s->tx_buffer[s->tx_written++] = val;
@@ -214,7 +220,6 @@ static const VMStateDescription vmstate_mipsnet = {
 static NetClientInfo net_mipsnet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = mipsnet_can_receive,
     .receive = mipsnet_receive,
 };
 

hw/net/ne2000.c

@@ -230,6 +230,9 @@ ssize_t ne2000_receive(NetClientState *nc, const uint8_t *buf, size_t size_)
     }
 
     index = s->curpag << 8;
+    if (index >= NE2000_PMEM_END) {
+        index = s->start;
+    }
     /* 4 bytes for header */
     total_len = size + 4;
     /* address for next packet (4 bytes for CRC) */
@@ -253,7 +256,7 @@ ssize_t ne2000_receive(NetClientState *nc, const uint8_t *buf, size_t size_)
         if (index <= s->stop)
             avail = s->stop - index;
         else
-            avail = 0;
+            break;
         len = size;
         if (len > avail)
             len = avail;
@@ -315,13 +318,19 @@ static void ne2000_ioport_write(void *opaque, uint32_t addr, uint32_t val)
         offset = addr | (page << 4);
         switch(offset) {
         case EN0_STARTPG:
-            s->start = val << 8;
+            if (val << 8 <= NE2000_PMEM_END) {
+                s->start = val << 8;
+            }
             break;
         case EN0_STOPPG:
-            s->stop = val << 8;
+            if (val << 8 <= NE2000_PMEM_END) {
+                s->stop = val << 8;
+            }
             break;
         case EN0_BOUNDARY:
-            s->boundary = val;
+            if (val << 8 < NE2000_PMEM_END) {
+                s->boundary = val;
+            }
             break;
         case EN0_IMR:
             s->imr = val;
@@ -362,7 +371,9 @@ static void ne2000_ioport_write(void *opaque, uint32_t addr, uint32_t val)
             s->phys[offset - EN1_PHYS] = val;
             break;
         case EN1_CURPAG:
-            s->curpag = val;
+            if (val << 8 < NE2000_PMEM_END) {
+                s->curpag = val;
+            }
             break;
         case EN1_MULT ... EN1_MULT + 7:
             s->mult[offset - EN1_MULT] = val;

hw/net/pcnet-pci.c

@@ -273,7 +273,6 @@ static void pci_pcnet_uninit(PCIDevice *dev)
 static NetClientInfo net_pci_pcnet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = pcnet_can_receive,
     .receive = pcnet_receive,
     .link_status_changed = pcnet_set_link_status,
 };

hw/net/pcnet.c

@@ -995,15 +995,6 @@ static int pcnet_tdte_poll(PCNetState *s)
     return !!(CSR_CXST(s) & 0x8000);
 }
 
-int pcnet_can_receive(NetClientState *nc)
-{
-    PCNetState *s = qemu_get_nic_opaque(nc);
-    if (CSR_STOP(s) || CSR_SPND(s))
-        return 0;
-
-    return sizeof(s->buffer)-16;
-}
-
 #define MIN_BUF_SIZE 60
 
 ssize_t pcnet_receive(NetClientState *nc, const uint8_t *buf, size_t size_)

hw/net/pcnet.h

@@ -60,7 +60,6 @@ uint32_t pcnet_ioport_readw(void *opaque, uint32_t addr);
 void pcnet_ioport_writel(void *opaque, uint32_t addr, uint32_t val);
 uint32_t pcnet_ioport_readl(void *opaque, uint32_t addr);
 uint32_t pcnet_bcr_readw(PCNetState *s, uint32_t rap);
-int pcnet_can_receive(NetClientState *nc);
 ssize_t pcnet_receive(NetClientState *nc, const uint8_t *buf, size_t size_);
 void pcnet_set_link_status(NetClientState *nc);
 void pcnet_common_init(DeviceState *dev, PCNetState *s, NetClientInfo *info);

hw/net/rtl8139.c

@@ -1148,7 +1148,9 @@ static ssize_t rtl8139_do_receive(NetClientState *nc, const uint8_t *buf, size_t
 
         /* if receiver buffer is empty then avail == 0 */
 
-        if (avail != 0 && size + 8 >= avail)
+#define RX_ALIGN(x) (((x) + 3) & ~0x3)
+
+        if (avail != 0 && RX_ALIGN(size + 8) >= avail)
         {
             DPRINTF("rx overflow: rx buffer length %d head 0x%04x "
                 "read 0x%04x === available 0x%04x need 0x%04x\n",
@@ -1157,7 +1159,7 @@ static ssize_t rtl8139_do_receive(NetClientState *nc, const uint8_t *buf, size_t
             s->IntrStatus |= RxOverflow;
             ++s->RxMissed;
             rtl8139_update_irq(s);
-            return size_;
+            return 0;
         }
 
         packet_header |= RxStatusOK;
@@ -1176,7 +1178,7 @@ static ssize_t rtl8139_do_receive(NetClientState *nc, const uint8_t *buf, size_t
         rtl8139_write_buffer(s, (uint8_t *)&val, 4);
 
         /* correct buffer write pointer */
-        s->RxBufAddr = MOD2((s->RxBufAddr + 3) & ~0x3, s->RxBufferSize);
+        s->RxBufAddr = MOD2(RX_ALIGN(s->RxBufAddr), s->RxBufferSize);
 
         /* now we can signal we have received something */
 
@@ -2150,6 +2152,11 @@ 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 +2167,235 @@ 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/stellaris_enet.c

@@ -228,8 +228,7 @@ static ssize_t stellaris_enet_receive(NetClientState *nc, const uint8_t *buf, si
     if ((s->rctl & SE_RCTL_RXEN) == 0)
         return -1;
     if (s->np >= 31) {
-        DPRINTF("Packet dropped\n");
-        return -1;
+        return 0;
     }
 
     DPRINTF("Received packet len=%zu\n", size);
@@ -260,13 +259,8 @@ static ssize_t stellaris_enet_receive(NetClientState *nc, const uint8_t *buf, si
     return size;
 }
 
-static int stellaris_enet_can_receive(NetClientState *nc)
+static int stellaris_enet_can_receive(stellaris_enet_state *s)
 {
-    stellaris_enet_state *s = qemu_get_nic_opaque(nc);
-
-    if ((s->rctl & SE_RCTL_RXEN) == 0)
-        return 1;
-
     return (s->np < 31);
 }
 
@@ -307,6 +301,9 @@ static uint64_t stellaris_enet_read(void *opaque, hwaddr offset,
                 s->next_packet = 0;
             s->np--;
             DPRINTF("RX done np=%d\n", s->np);
+            if (!s->np && stellaris_enet_can_receive(s)) {
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
         }
         return val;
     }
@@ -454,7 +451,6 @@ static void stellaris_enet_reset(stellaris_enet_state *s)
 static NetClientInfo net_stellaris_enet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = stellaris_enet_can_receive,
     .receive = stellaris_enet_receive,
 };
 

hw/net/vhost_net.c

@@ -197,7 +197,7 @@ static int vhost_net_set_vnet_endian(VirtIODevice *dev, NetClientState *peer,
 {
     int r = 0;
 
-    if (virtio_has_feature(dev, VIRTIO_F_VERSION_1) ||
+    if (virtio_vdev_has_feature(dev, VIRTIO_F_VERSION_1) ||
         (virtio_legacy_is_cross_endian(dev) && !virtio_is_big_endian(dev))) {
         r = qemu_set_vnet_le(peer, set);
         if (r) {

hw/net/virtio-net.c

@@ -86,8 +86,8 @@ static void virtio_net_set_config(VirtIODevice *vdev, const uint8_t *config)
 
     memcpy(&netcfg, config, n->config_size);
 
-    if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) &&
-        !virtio_has_feature(vdev, VIRTIO_F_VERSION_1) &&
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR) &&
+        !virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1) &&
         memcmp(netcfg.mac, n->mac, ETH_ALEN)) {
         memcpy(n->mac, netcfg.mac, ETH_ALEN);
         qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
@@ -304,7 +304,7 @@ static RxFilterInfo *virtio_net_query_rxfilter(NetClientState *nc)
     info->multicast_table = str_list;
     info->vlan_table = get_vlan_table(n);
 
-    if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VLAN)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VLAN)) {
         info->vlan = RX_STATE_ALL;
     } else if (!info->vlan_table) {
         info->vlan = RX_STATE_NONE;
@@ -446,7 +446,8 @@ static void virtio_net_set_queues(VirtIONet *n)
 
 static void virtio_net_set_multiqueue(VirtIONet *n, int multiqueue);
 
-static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features)
+static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features,
+                                        Error **errp)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
     NetClientState *nc = qemu_get_queue(n->nic);
@@ -528,13 +529,13 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
     int i;
 
     virtio_net_set_multiqueue(n,
-                              __virtio_has_feature(features, VIRTIO_NET_F_MQ));
+                              virtio_has_feature(features, VIRTIO_NET_F_MQ));
 
     virtio_net_set_mrg_rx_bufs(n,
-                               __virtio_has_feature(features,
-                                                    VIRTIO_NET_F_MRG_RXBUF),
-                               __virtio_has_feature(features,
-                                                    VIRTIO_F_VERSION_1));
+                               virtio_has_feature(features,
+                                                  VIRTIO_NET_F_MRG_RXBUF),
+                               virtio_has_feature(features,
+                                                  VIRTIO_F_VERSION_1));
 
     if (n->has_vnet_hdr) {
         n->curr_guest_offloads =
@@ -551,7 +552,7 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
         vhost_net_ack_features(get_vhost_net(nc->peer), features);
     }
 
-    if (__virtio_has_feature(features, VIRTIO_NET_F_CTRL_VLAN)) {
+    if (virtio_has_feature(features, VIRTIO_NET_F_CTRL_VLAN)) {
         memset(n->vlans, 0, MAX_VLAN >> 3);
     } else {
         memset(n->vlans, 0xff, MAX_VLAN >> 3);
@@ -598,7 +599,7 @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd,
     uint64_t offloads;
     size_t s;
 
-    if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
         return VIRTIO_NET_ERR;
     }
 
@@ -1085,13 +1086,7 @@ static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, size_t
          * must have consumed the complete packet.
          * Otherwise, drop it. */
         if (!n->mergeable_rx_bufs && offset < size) {
-#if 0
-            error_report("virtio-net truncated non-mergeable packet: "
-                         "i %zd mergeable %d offset %zd, size %zd, "
-                         "guest hdr len %zd, host hdr len %zd",
-                         i, n->mergeable_rx_bufs,
-                         offset, size, n->guest_hdr_len, n->host_hdr_len);
-#endif
+            virtqueue_discard(q->rx_vq, &elem, total);
             return size;
         }
 
@@ -1452,7 +1447,7 @@ static void virtio_net_save_device(VirtIODevice *vdev, QEMUFile *f)
         }
     }
 
-    if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
         qemu_put_be64(f, n->curr_guest_offloads);
     }
 }
@@ -1461,11 +1456,33 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
 {
     VirtIONet *n = opaque;
     VirtIODevice *vdev = VIRTIO_DEVICE(n);
+    int ret;
 
     if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION)
         return -EINVAL;
 
-    return virtio_load(vdev, f, version_id);
+    ret = virtio_load(vdev, f, version_id);
+    if (ret) {
+        return ret;
+    }
+
+    if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
+        n->curr_guest_offloads = qemu_get_be64(f);
+    } else {
+        n->curr_guest_offloads = virtio_net_supported_guest_offloads(n);
+    }
+
+    if (peer_has_vnet_hdr(n)) {
+        virtio_net_apply_guest_offloads(n);
+    }
+
+    if (virtio_vdev_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) &&
+        virtio_vdev_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) {
+        n->announce_counter = SELF_ANNOUNCE_ROUNDS;
+        timer_mod(n->announce_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL));
+    }
+
+    return 0;
 }
 
 static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
@@ -1478,7 +1495,8 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
     n->vqs[0].tx_waiting = qemu_get_be32(f);
 
     virtio_net_set_mrg_rx_bufs(n, qemu_get_be32(f),
-                               virtio_has_feature(vdev, VIRTIO_F_VERSION_1));
+                               virtio_vdev_has_feature(vdev,
+                                                       VIRTIO_F_VERSION_1));
 
     if (version_id >= 3)
         n->status = qemu_get_be16(f);
@@ -1561,16 +1579,6 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
         }
     }
 
-    if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) {
-        n->curr_guest_offloads = qemu_get_be64(f);
-    } else {
-        n->curr_guest_offloads = virtio_net_supported_guest_offloads(n);
-    }
-
-    if (peer_has_vnet_hdr(n)) {
-        virtio_net_apply_guest_offloads(n);
-    }
-
     virtio_net_set_queues(n);
 
     /* Find the first multicast entry in the saved MAC filter */
@@ -1588,12 +1596,6 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f,
         qemu_get_subqueue(n->nic, i)->link_down = link_down;
     }
 
-    if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE) &&
-        virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) {
-        n->announce_counter = SELF_ANNOUNCE_ROUNDS;
-        timer_mod(n->announce_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL));
-    }
-
     return 0;
 }
 
@@ -1777,8 +1779,6 @@ static void virtio_net_instance_init(Object *obj)
 }
 
 static Property virtio_net_properties[] = {
-    DEFINE_PROP_BIT("any_layout", VirtIONet, host_features,
-                    VIRTIO_F_ANY_LAYOUT, true),
     DEFINE_PROP_BIT("csum", VirtIONet, host_features, VIRTIO_NET_F_CSUM, true),
     DEFINE_PROP_BIT("guest_csum", VirtIONet, host_features,
                     VIRTIO_NET_F_GUEST_CSUM, true),

hw/net/vmxnet3.c

@@ -1988,7 +1988,6 @@ static void vmxnet3_set_link_status(NetClientState *nc)
 static NetClientInfo net_vmxnet3_info = {
         .type = NET_CLIENT_OPTIONS_KIND_NIC,
         .size = sizeof(NICState),
-        .can_receive = vmxnet3_can_receive,
         .receive = vmxnet3_receive,
         .link_status_changed = vmxnet3_set_link_status,
 };

hw/net/xen_nic.c

@@ -234,27 +234,6 @@ static void net_rx_response(struct XenNetDev *netdev,
 
 #define NET_IP_ALIGN 2
 
-static int net_rx_ok(NetClientState *nc)
-{
-    struct XenNetDev *netdev = qemu_get_nic_opaque(nc);
-    RING_IDX rc, rp;
-
-    if (netdev->xendev.be_state != XenbusStateConnected) {
-        return 0;
-    }
-
-    rc = netdev->rx_ring.req_cons;
-    rp = netdev->rx_ring.sring->req_prod;
-    xen_rmb();
-
-    if (rc == rp || RING_REQUEST_CONS_OVERFLOW(&netdev->rx_ring, rc)) {
-        xen_be_printf(&netdev->xendev, 2, "%s: no rx buffers (%d/%d)\n",
-                      __FUNCTION__, rc, rp);
-        return 0;
-    }
-    return 1;
-}
-
 static ssize_t net_rx_packet(NetClientState *nc, const uint8_t *buf, size_t size)
 {
     struct XenNetDev *netdev = qemu_get_nic_opaque(nc);
@@ -271,8 +250,7 @@ static ssize_t net_rx_packet(NetClientState *nc, const uint8_t *buf, size_t size
     xen_rmb(); /* Ensure we see queued requests up to 'rp'. */
 
     if (rc == rp || RING_REQUEST_CONS_OVERFLOW(&netdev->rx_ring, rc)) {
-        xen_be_printf(&netdev->xendev, 2, "no buffer, drop packet\n");
-        return -1;
+        return 0;
     }
     if (size > XC_PAGE_SIZE - NET_IP_ALIGN) {
         xen_be_printf(&netdev->xendev, 0, "packet too big (%lu > %ld)",
@@ -304,7 +282,6 @@ static ssize_t net_rx_packet(NetClientState *nc, const uint8_t *buf, size_t size
 static NetClientInfo net_xen_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = net_rx_ok,
     .receive = net_rx_packet,
 };
 

hw/net/xgmac.c

@@ -312,10 +312,8 @@ static const MemoryRegionOps enet_mem_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
-static int eth_can_rx(NetClientState *nc)
+static int eth_can_rx(XgmacState *s)
 {
-    XgmacState *s = qemu_get_nic_opaque(nc);
-
     /* RX enabled?  */
     return s->regs[DMA_CONTROL] & DMA_CONTROL_SR;
 }
@@ -329,6 +327,9 @@ static ssize_t eth_rx(NetClientState *nc, const uint8_t *buf, size_t size)
     struct desc bd;
     ssize_t ret;
 
+    if (!eth_can_rx(s)) {
+        return -1;
+    }
     unicast = ~buf[0] & 0x1;
     broadcast = memcmp(buf, sa_bcast, 6) == 0;
     multicast = !unicast && !broadcast;
@@ -371,7 +372,6 @@ out:
 static NetClientInfo net_xgmac_enet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = eth_can_rx,
     .receive = eth_rx,
 };
 

hw/net/xilinx_axienet.c

@@ -401,6 +401,9 @@ struct XilinxAXIEnet {
 
     uint8_t rxapp[CONTROL_PAYLOAD_SIZE];
     uint32_t rxappsize;
+
+    /* Whether axienet_eth_rx_notify should flush incoming queue. */
+    bool need_flush;
 };
 
 static void axienet_rx_reset(XilinxAXIEnet *s)
@@ -658,10 +661,8 @@ static const MemoryRegionOps enet_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
-static int eth_can_rx(NetClientState *nc)
+static int eth_can_rx(XilinxAXIEnet *s)
 {
-    XilinxAXIEnet *s = qemu_get_nic_opaque(nc);
-
     /* RX enabled?  */
     return !s->rxsize && !axienet_rx_resetting(s) && axienet_rx_enabled(s);
 }
@@ -701,6 +702,10 @@ static void axienet_eth_rx_notify(void *opaque)
         s->rxpos += ret;
         if (!s->rxsize) {
             s->regs[R_IS] |= IS_RX_COMPLETE;
+            if (s->need_flush) {
+                s->need_flush = false;
+                qemu_flush_queued_packets(qemu_get_queue(s->nic));
+            }
         }
     }
     enet_update_irq(s);
@@ -721,6 +726,11 @@ static ssize_t eth_rx(NetClientState *nc, const uint8_t *buf, size_t size)
 
     DENET(qemu_log("%s: %zd bytes\n", __func__, size));
 
+    if (!eth_can_rx(s)) {
+        s->need_flush = true;
+        return 0;
+    }
+
     unicast = ~buf[0] & 0x1;
     broadcast = memcmp(buf, sa_bcast, 6) == 0;
     multicast = !unicast && !broadcast;
@@ -925,7 +935,6 @@ xilinx_axienet_data_stream_push(StreamSlave *obj, uint8_t *buf, size_t size)
 static NetClientInfo net_xilinx_enet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = eth_can_rx,
     .receive = eth_rx,
 };
 

hw/pci-host/versatile.c

@@ -500,6 +500,8 @@ static void pci_vpb_class_init(ObjectClass *klass, void *data)
     dc->reset = pci_vpb_reset;
     dc->vmsd = &pci_vpb_vmstate;
     dc->props = pci_vpb_properties;
+    /* Reason: object_unref() hangs */
+    dc->cannot_destroy_with_object_finalize_yet = true;
 }
 
 static const TypeInfo pci_vpb_info = {
@@ -521,10 +523,19 @@ static void pci_realview_init(Object *obj)
     s->mem_win_size[2] = 0x08000000;
 }
 
+static void pci_realview_class_init(ObjectClass *class, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(class);
+
+    /* Reason: object_unref() hangs */
+    dc->cannot_destroy_with_object_finalize_yet = true;
+}
+
 static const TypeInfo pci_realview_info = {
     .name          = "realview_pci",
     .parent        = TYPE_VERSATILE_PCI,
     .instance_init = pci_realview_init,
+    .class_init    = pci_realview_class_init,
 };
 
 static void versatile_pci_register_types(void)

hw/pcmcia/pxa2xx.c

@@ -163,7 +163,7 @@ static void pxa2xx_pcmcia_initfn(Object *obj)
     sysbus_init_mmio(sbd, &s->container_mem);
 
     /* Socket I/O Memory Space */
-    memory_region_init_io(&s->iomem, NULL, &pxa2xx_pcmcia_io_ops, s,
+    memory_region_init_io(&s->iomem, obj, &pxa2xx_pcmcia_io_ops, s,
                           "pxa2xx-pcmcia-io", 0x04000000);
     memory_region_add_subregion(&s->container_mem, 0x00000000,
                                 &s->iomem);
@@ -171,13 +171,13 @@ static void pxa2xx_pcmcia_initfn(Object *obj)
     /* Then next 64 MB is reserved */
 
     /* Socket Attribute Memory Space */
-    memory_region_init_io(&s->attr_iomem, NULL, &pxa2xx_pcmcia_attr_ops, s,
+    memory_region_init_io(&s->attr_iomem, obj, &pxa2xx_pcmcia_attr_ops, s,
                           "pxa2xx-pcmcia-attribute", 0x04000000);
     memory_region_add_subregion(&s->container_mem, 0x08000000,
                                 &s->attr_iomem);
 
     /* Socket Common Memory Space */
-    memory_region_init_io(&s->common_iomem, NULL, &pxa2xx_pcmcia_common_ops, s,
+    memory_region_init_io(&s->common_iomem, obj, &pxa2xx_pcmcia_common_ops, s,
                           "pxa2xx-pcmcia-common", 0x04000000);
     memory_region_add_subregion(&s->container_mem, 0x0c000000,
                                 &s->common_iomem);

hw/ppc/spapr_pci.c

@@ -955,6 +955,7 @@ static int spapr_populate_pci_child_dt(PCIDevice *dev, void *fdt, int offset,
     int pci_status, err;
     char *buf = NULL;
     uint32_t drc_index = spapr_phb_get_pci_drc_index(sphb, dev);
+    uint32_t max_msi, max_msix;
 
     if (pci_default_read_config(dev, PCI_HEADER_TYPE, 1) ==
         PCI_HEADER_TYPE_BRIDGE) {
@@ -1035,8 +1036,15 @@ static int spapr_populate_pci_child_dt(PCIDevice *dev, void *fdt, int offset,
                           RESOURCE_CELLS_ADDRESS));
     _FDT(fdt_setprop_cell(fdt, offset, "#size-cells",
                           RESOURCE_CELLS_SIZE));
-    _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi-x",
-                          RESOURCE_CELLS_SIZE));
+
+    max_msi = msi_nr_vectors_allocated(dev);
+    if (max_msi) {
+        _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi", max_msi));
+    }
+    max_msix = dev->msix_entries_nr;
+    if (max_msix) {
+        _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi-x", max_msix));
+    }
 
     populate_resource_props(dev, &rp);
     _FDT(fdt_setprop(fdt, offset, "reg", (uint8_t *)rp.reg, rp.reg_len));

hw/s390x/css.c

@@ -392,6 +392,8 @@ static void sch_handle_start_func(SubchDev *sch, ORB *orb)
     path = 0x80;
 
     if (!(s->ctrl & SCSW_ACTL_SUSP)) {
+        s->cstat = 0;
+        s->dstat = 0;
         /* Look at the orb and try to execute the channel program. */
         assert(orb != NULL); /* resume does not pass an orb */
         p->intparm = orb->intparm;

hw/scsi/megasas.c

@@ -2202,8 +2202,15 @@ static uint64_t megasas_queue_read(void *opaque, hwaddr addr,
     return 0;
 }
 
+static void megasas_queue_write(void *opaque, hwaddr addr,
+                               uint64_t val, unsigned size)
+{
+    return;
+}
+
 static const MemoryRegionOps megasas_queue_ops = {
     .read = megasas_queue_read,
+    .write = megasas_queue_write,
     .endianness = DEVICE_LITTLE_ENDIAN,
     .impl = {
         .min_access_size = 8,

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/scsi/scsi-disk.c

@@ -765,6 +765,9 @@ static inline bool media_is_dvd(SCSIDiskState *s)
     if (!blk_is_inserted(s->qdev.conf.blk)) {
         return false;
     }
+    if (s->tray_open) {
+        return false;
+    }
     blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
     return nb_sectors > CD_MAX_SECTORS;
 }
@@ -778,6 +781,9 @@ static inline bool media_is_cd(SCSIDiskState *s)
     if (!blk_is_inserted(s->qdev.conf.blk)) {
         return false;
     }
+    if (s->tray_open) {
+        return false;
+    }
     blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
     return nb_sectors <= CD_MAX_SECTORS;
 }
@@ -975,7 +981,15 @@ static int scsi_get_configuration(SCSIDiskState *s, uint8_t *outbuf)
     if (s->qdev.type != TYPE_ROM) {
         return -1;
     }
-    current = media_is_dvd(s) ? MMC_PROFILE_DVD_ROM : MMC_PROFILE_CD_ROM;
+
+    if (media_is_dvd(s)) {
+        current = MMC_PROFILE_DVD_ROM;
+    } else if (media_is_cd(s)) {
+        current = MMC_PROFILE_CD_ROM;
+    } else {
+        current = MMC_PROFILE_NONE;
+    }
+
     memset(outbuf, 0, 40);
     stl_be_p(&outbuf[0], 36); /* Bytes after the data length field */
     stw_be_p(&outbuf[6], current);
@@ -1669,6 +1683,10 @@ static void scsi_write_same_complete(void *opaque, int ret)
     if (data->iov.iov_len) {
         block_acct_start(blk_get_stats(s->qdev.conf.blk), &r->acct,
                          data->iov.iov_len, BLOCK_ACCT_WRITE);
+        /* blk_aio_write doesn't like the qiov size being different from
+         * nb_sectors, make sure they match.
+         */
+        qemu_iovec_init_external(&data->qiov, &data->iov, 1);
         r->req.aiocb = blk_aio_writev(s->qdev.conf.blk, data->sector,
                                       &data->qiov, data->iov.iov_len / 512,
                                       scsi_write_same_complete, data);

hw/scsi/vhost-scsi.c

@@ -153,7 +153,8 @@ static void vhost_scsi_stop(VHostSCSI *s)
 }
 
 static uint64_t vhost_scsi_get_features(VirtIODevice *vdev,
-                                        uint64_t features)
+                                        uint64_t features,
+                                        Error **errp)
 {
     VHostSCSI *s = VHOST_SCSI(vdev);
 
@@ -290,7 +291,7 @@ static char *vhost_scsi_get_fw_dev_path(FWPathProvider *p, BusState *bus,
 {
     VHostSCSI *s = VHOST_SCSI(dev);
     /* format: channel@channel/vhost-scsi@target,lun */
-    return g_strdup_printf("channel@%x/%s@%x,%x", s->channel,
+    return g_strdup_printf("/channel@%x/%s@%x,%x", s->channel,
                            qdev_fw_name(dev), s->target, s->lun);
 }
 

hw/scsi/virtio-scsi.c

@@ -145,7 +145,7 @@ static int virtio_scsi_parse_req(VirtIOSCSIReq *req,
      *
      * TODO: always disable this workaround for virtio 1.0 devices.
      */
-    if (!virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_F_ANY_LAYOUT)) {
         if (req->elem.out_num) {
             req_size = req->elem.out_sg[0].iov_len;
         }
@@ -629,7 +629,8 @@ static void virtio_scsi_set_config(VirtIODevice *vdev,
 }
 
 static uint64_t virtio_scsi_get_features(VirtIODevice *vdev,
-                                         uint64_t requested_features)
+                                         uint64_t requested_features,
+                                         Error **errp)
 {
     VirtIOSCSI *s = VIRTIO_SCSI(vdev);
 
@@ -661,6 +662,11 @@ static void virtio_scsi_reset(VirtIODevice *vdev)
 static void virtio_scsi_save(QEMUFile *f, void *opaque)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(opaque);
+    VirtIOSCSI *s = VIRTIO_SCSI(vdev);
+
+    if (s->dataplane_started) {
+        virtio_scsi_dataplane_stop(s);
+    }
     virtio_save(vdev, f);
 }
 
@@ -753,7 +759,7 @@ static void virtio_scsi_change(SCSIBus *bus, SCSIDevice *dev, SCSISense sense)
     VirtIOSCSI *s = container_of(bus, VirtIOSCSI, bus);
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
 
-    if (virtio_has_feature(vdev, VIRTIO_SCSI_F_CHANGE) &&
+    if (virtio_vdev_has_feature(vdev, VIRTIO_SCSI_F_CHANGE) &&
         dev->type != TYPE_ROM) {
         virtio_scsi_push_event(s, dev, VIRTIO_SCSI_T_PARAM_CHANGE,
                                sense.asc | (sense.ascq << 8));
@@ -777,7 +783,7 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
         aio_context_release(s->ctx);
     }
 
-    if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG)) {
         virtio_scsi_push_event(s, sd,
                                VIRTIO_SCSI_T_TRANSPORT_RESET,
                                VIRTIO_SCSI_EVT_RESET_RESCAN);
@@ -791,7 +797,7 @@ static void virtio_scsi_hotunplug(HotplugHandler *hotplug_dev, DeviceState *dev,
     VirtIOSCSI *s = VIRTIO_SCSI(vdev);
     SCSIDevice *sd = SCSI_DEVICE(dev);
 
-    if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG)) {
         virtio_scsi_push_event(s, sd,
                                VIRTIO_SCSI_T_TRANSPORT_RESET,
                                VIRTIO_SCSI_EVT_RESET_REMOVED);
@@ -953,8 +959,6 @@ static Property virtio_scsi_properties[] = {
                                                   0xFFFF),
     DEFINE_PROP_UINT32("cmd_per_lun", VirtIOSCSI, parent_obj.conf.cmd_per_lun,
                                                   128),
-    DEFINE_PROP_BIT("any_layout", VirtIOSCSI, host_features,
-                                              VIRTIO_F_ANY_LAYOUT, true),
     DEFINE_PROP_BIT("hotplug", VirtIOSCSI, host_features,
                                            VIRTIO_SCSI_F_HOTPLUG, true),
     DEFINE_PROP_BIT("param_change", VirtIOSCSI, host_features,

hw/usb/dev-network.c

@@ -1268,6 +1268,10 @@ static ssize_t usbnet_receive(NetClientState *nc, const uint8_t *buf, size_t siz
     uint8_t *in_buf = s->in_buf;
     size_t total_size = size;
 
+    if (!s->dev.config) {
+        return -1;
+    }
+
     if (is_rndis(s)) {
         if (s->rndis_state != RNDIS_DATA_INITIALIZED) {
             return -1;
@@ -1309,21 +1313,6 @@ static ssize_t usbnet_receive(NetClientState *nc, const uint8_t *buf, size_t siz
     return size;
 }
 
-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;
-    }
-
-    return !s->in_len;
-}
-
 static void usbnet_cleanup(NetClientState *nc)
 {
     USBNetState *s = qemu_get_nic_opaque(nc);
@@ -1343,7 +1332,6 @@ static void usb_net_handle_destroy(USBDevice *dev)
 static NetClientInfo net_usbnet_info = {
     .type = NET_CLIENT_OPTIONS_KIND_NIC,
     .size = sizeof(NICState),
-    .can_receive = usbnet_can_receive,
     .receive = usbnet_receive,
     .cleanup = usbnet_cleanup,
 };

hw/vfio/pci.c

@@ -1517,7 +1517,7 @@ 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 */
@@ -1558,7 +1558,7 @@ 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(
@@ -1566,11 +1566,9 @@ static void vfio_rtl8168_window_quirk_write(void *opaque, hwaddr addr,
                         vdev->vbasedev.name);
 
                 memory_region_dispatch_write(&vdev->pdev.msix_table_mmio,
-                                             (hwaddr)(quirk->data.address_match
-                                                      & 0xfff),
-                                             data,
-                                             size,
-                                             MEMTXATTRS_UNSPECIFIED);
+                                             (hwaddr)(data & 0xfff),
+                                             (uint64_t)quirk->data.address_mask,
+                                             size, MEMTXATTRS_UNSPECIFIED);
             }
 
             quirk->data.flags = 1;
@@ -3751,7 +3749,6 @@ 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/dataplane/vring.c

@@ -67,22 +67,53 @@ static void vring_unmap(void *buffer, bool is_write)
 /* Map the guest's vring to host memory */
 bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
 {
-    hwaddr vring_addr = virtio_queue_get_ring_addr(vdev, n);
-    hwaddr vring_size = virtio_queue_get_ring_size(vdev, n);
-    void *vring_ptr;
+    struct vring *vr = &vring->vr;
+    hwaddr addr;
+    hwaddr size;
+    void *ptr;
 
     vring->broken = false;
+    vr->num = virtio_queue_get_num(vdev, n);
 
-    vring_ptr = vring_map(&vring->mr, vring_addr, vring_size, true);
-    if (!vring_ptr) {
-        error_report("Failed to map vring "
-                     "addr %#" HWADDR_PRIx " size %" HWADDR_PRIu,
-                     vring_addr, vring_size);
-        vring->broken = true;
-        return false;
+    addr = virtio_queue_get_desc_addr(vdev, n);
+    size = virtio_queue_get_desc_size(vdev, n);
+    /* Map the descriptor area as read only */
+    ptr = vring_map(&vring->mr_desc, addr, size, false);
+    if (!ptr) {
+        error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring desc "
+                     "at 0x%" HWADDR_PRIx,
+                      size, addr);
+        goto out_err_desc;
     }
+    vr->desc = ptr;
 
-    vring_init(&vring->vr, virtio_queue_get_num(vdev, n), vring_ptr, 4096);
+    addr = virtio_queue_get_avail_addr(vdev, n);
+    size = virtio_queue_get_avail_size(vdev, n);
+    /* Add the size of the used_event_idx */
+    size += sizeof(uint16_t);
+    /* Map the driver area as read only */
+    ptr = vring_map(&vring->mr_avail, addr, size, false);
+    if (!ptr) {
+        error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring avail "
+                     "at 0x%" HWADDR_PRIx,
+                      size, addr);
+        goto out_err_avail;
+    }
+    vr->avail = ptr;
+
+    addr = virtio_queue_get_used_addr(vdev, n);
+    size = virtio_queue_get_used_size(vdev, n);
+    /* Add the size of the avail_event_idx */
+    size += sizeof(uint16_t);
+    /* Map the device area as read-write */
+    ptr = vring_map(&vring->mr_used, addr, size, true);
+    if (!ptr) {
+        error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring used "
+                     "at 0x%" HWADDR_PRIx,
+                      size, addr);
+        goto out_err_used;
+    }
+    vr->used = ptr;
 
     vring->last_avail_idx = virtio_queue_get_last_avail_idx(vdev, n);
     vring->last_used_idx = vring_get_used_idx(vdev, vring);
@@ -92,6 +123,14 @@ bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
     trace_vring_setup(virtio_queue_get_ring_addr(vdev, n),
                       vring->vr.desc, vring->vr.avail, vring->vr.used);
     return true;
+
+out_err_used:
+    memory_region_unref(vring->mr_avail);
+out_err_avail:
+    memory_region_unref(vring->mr_desc);
+out_err_desc:
+    vring->broken = true;
+    return false;
 }
 
 void vring_teardown(Vring *vring, VirtIODevice *vdev, int n)
@@ -99,13 +138,15 @@ void vring_teardown(Vring *vring, VirtIODevice *vdev, int n)
     virtio_queue_set_last_avail_idx(vdev, n, vring->last_avail_idx);
     virtio_queue_invalidate_signalled_used(vdev, n);
 
-    memory_region_unref(vring->mr);
+    memory_region_unref(vring->mr_desc);
+    memory_region_unref(vring->mr_avail);
+    memory_region_unref(vring->mr_used);
 }
 
 /* Disable guest->host notifies */
 void vring_disable_notification(VirtIODevice *vdev, Vring *vring)
 {
-    if (!virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
         vring_set_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
     }
 }
@@ -116,7 +157,7 @@ void vring_disable_notification(VirtIODevice *vdev, Vring *vring)
  */
 bool vring_enable_notification(VirtIODevice *vdev, Vring *vring)
 {
-    if (virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
         vring_avail_event(&vring->vr) = vring->vr.avail->idx;
     } else {
         vring_clear_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
@@ -135,12 +176,12 @@ bool vring_should_notify(VirtIODevice *vdev, Vring *vring)
      * interrupts. */
     smp_mb();
 
-    if (virtio_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
         unlikely(!vring_more_avail(vdev, vring))) {
         return true;
     }
 
-    if (!virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
         return !(vring_get_avail_flags(vdev, vring) &
                  VRING_AVAIL_F_NO_INTERRUPT);
     }
@@ -402,7 +443,7 @@ int vring_pop(VirtIODevice *vdev, Vring *vring,
 
     /* On success, increment avail index. */
     vring->last_avail_idx++;
-    if (virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
         vring_avail_event(&vring->vr) =
             virtio_tswap16(vdev, vring->last_avail_idx);
     }

hw/virtio/vhost.c

@@ -742,7 +742,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
         return -errno;
     }
 
-    if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1) &&
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1) &&
         virtio_legacy_is_cross_endian(vdev)) {
         r = vhost_virtqueue_set_vring_endian_legacy(dev,
                                                     virtio_is_big_endian(vdev),
@@ -839,7 +839,7 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev,
     /* In the cross-endian case, we need to reset the vring endianness to
      * native as legacy devices expect so by default.
      */
-    if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1) &&
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1) &&
         virtio_legacy_is_cross_endian(vdev)) {
         r = vhost_virtqueue_set_vring_endian_legacy(dev,
                                                     !virtio_is_big_endian(vdev),

hw/virtio/virtio-balloon.c

@@ -70,7 +70,7 @@ static inline void reset_stats(VirtIOBalloon *dev)
 static bool balloon_stats_supported(const VirtIOBalloon *s)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
-    return virtio_has_feature(vdev, VIRTIO_BALLOON_F_STATS_VQ);
+    return virtio_vdev_has_feature(vdev, VIRTIO_BALLOON_F_STATS_VQ);
 }
 
 static bool balloon_stats_enabled(const VirtIOBalloon *s)
@@ -310,7 +310,8 @@ static void virtio_balloon_set_config(VirtIODevice *vdev,
     trace_virtio_balloon_set_config(dev->actual, oldactual);
 }
 
-static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f)
+static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f,
+                                            Error **errp)
 {
     VirtIOBalloon *dev = VIRTIO_BALLOON(vdev);
     f |= dev->host_features;

hw/virtio/virtio-bus.c

@@ -54,7 +54,8 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp)
 
     /* Get the features of the plugged device. */
     assert(vdc->get_features != NULL);
-    vdev->host_features = vdc->get_features(vdev, vdev->host_features);
+    vdev->host_features = vdc->get_features(vdev, vdev->host_features,
+                                            errp);
 }
 
 /* Reset the virtio_bus */

hw/virtio/virtio-pci.c

@@ -1095,7 +1095,8 @@ static uint64_t virtio_pci_common_read(void *opaque, hwaddr addr,
         break;
     case VIRTIO_PCI_COMMON_DF:
         if (proxy->dfselect <= 1) {
-            val = vdev->host_features >> (32 * proxy->dfselect);
+            val = (vdev->host_features & ~VIRTIO_LEGACY_FEATURES) >>
+                (32 * proxy->dfselect);
         }
         break;
     case VIRTIO_PCI_COMMON_GFSELECT:
@@ -1413,6 +1414,13 @@ static void virtio_pci_modern_region_map(VirtIOPCIProxy *proxy,
     virtio_pci_add_mem_cap(proxy, cap);
 }
 
+static void virtio_pci_modern_region_unmap(VirtIOPCIProxy *proxy,
+                                           VirtIOPCIRegion *region)
+{
+    memory_region_del_subregion(&proxy->modern_bar,
+                                &region->mr);
+}
+
 /* This is called by virtio-bus just after the device is plugged. */
 static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
 {
@@ -1519,8 +1527,16 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp)
 static void virtio_pci_device_unplugged(DeviceState *d)
 {
     VirtIOPCIProxy *proxy = VIRTIO_PCI(d);
+    bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN);
 
     virtio_pci_stop_ioeventfd(proxy);
+
+    if (modern) {
+        virtio_pci_modern_region_unmap(proxy, &proxy->common);
+        virtio_pci_modern_region_unmap(proxy, &proxy->isr);
+        virtio_pci_modern_region_unmap(proxy, &proxy->device);
+        virtio_pci_modern_region_unmap(proxy, &proxy->notify);
+    }
 }
 
 static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp)

hw/virtio/virtio-rng.c

@@ -104,7 +104,7 @@ static void handle_input(VirtIODevice *vdev, VirtQueue *vq)
     virtio_rng_process(vrng);
 }
 
-static uint64_t get_features(VirtIODevice *vdev, uint64_t f)
+static uint64_t get_features(VirtIODevice *vdev, uint64_t f, Error **errp)
 {
     return f;
 }

hw/virtio/virtio.c

@@ -220,7 +220,7 @@ static inline void vring_set_avail_event(VirtQueue *vq, uint16_t val)
 void virtio_queue_set_notification(VirtQueue *vq, int enable)
 {
     vq->notification = enable;
-    if (virtio_has_feature(vq->vdev, VIRTIO_RING_F_EVENT_IDX)) {
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_RING_F_EVENT_IDX)) {
         vring_set_avail_event(vq, vring_avail_idx(vq));
     } else if (enable) {
         vring_used_flags_unset_bit(vq, VRING_USED_F_NO_NOTIFY);
@@ -243,14 +243,12 @@ int virtio_queue_empty(VirtQueue *vq)
     return vring_avail_idx(vq) == vq->last_avail_idx;
 }
 
-void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
-                    unsigned int len, unsigned int idx)
+static void virtqueue_unmap_sg(VirtQueue *vq, const VirtQueueElement *elem,
+                               unsigned int len)
 {
     unsigned int offset;
     int i;
 
-    trace_virtqueue_fill(vq, elem, len, idx);
-
     offset = 0;
     for (i = 0; i < elem->in_num; i++) {
         size_t size = MIN(len - offset, elem->in_sg[i].iov_len);
@@ -266,6 +264,21 @@ void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
         cpu_physical_memory_unmap(elem->out_sg[i].iov_base,
                                   elem->out_sg[i].iov_len,
                                   0, elem->out_sg[i].iov_len);
+}
+
+void virtqueue_discard(VirtQueue *vq, const VirtQueueElement *elem,
+                       unsigned int len)
+{
+    vq->last_avail_idx--;
+    virtqueue_unmap_sg(vq, elem, len);
+}
+
+void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
+                    unsigned int len, unsigned int idx)
+{
+    trace_virtqueue_fill(vq, elem, len, idx);
+
+    virtqueue_unmap_sg(vq, elem, len);
 
     idx = (idx + vring_used_idx(vq)) % vq->vring.num;
 
@@ -471,7 +484,7 @@ int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem)
     max = vq->vring.num;
 
     i = head = virtqueue_get_head(vq, vq->last_avail_idx++);
-    if (virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
         vring_set_avail_event(vq, vq->last_avail_idx);
     }
 
@@ -560,7 +573,7 @@ int virtio_set_status(VirtIODevice *vdev, uint8_t val)
     VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
     trace_virtio_set_status(vdev, val);
 
-    if (virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) {
         if (!(vdev->status & VIRTIO_CONFIG_S_FEATURES_OK) &&
             val & VIRTIO_CONFIG_S_FEATURES_OK) {
             int ret = virtio_validate_features(vdev);
@@ -898,7 +911,7 @@ void virtio_queue_set_align(VirtIODevice *vdev, int n, int align)
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
 
     /* virtio-1 compliant devices cannot change the alignment */
-    if (virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) {
         error_report("tried to modify queue alignment for virtio-1 device");
         return;
     }
@@ -993,12 +1006,12 @@ static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq)
     /* We need to expose used array entries before checking used event. */
     smp_mb();
     /* Always notify when queue is empty (when feature acknowledge) */
-    if (virtio_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
         !vq->inuse && vring_avail_idx(vq) == vq->last_avail_idx) {
         return true;
     }
 
-    if (!virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
         return !(vring_avail_flags(vq) & VRING_AVAIL_F_NO_INTERRUPT);
     }
 
@@ -1035,7 +1048,7 @@ static bool virtio_device_endian_needed(void *opaque)
     VirtIODevice *vdev = opaque;
 
     assert(vdev->device_endian != VIRTIO_DEVICE_ENDIAN_UNKNOWN);
-    if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
+    if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) {
         return vdev->device_endian != virtio_default_endian();
     }
     /* Devices conforming to VIRTIO 1.0 or later are always LE. */
@@ -1049,6 +1062,61 @@ static bool virtio_64bit_features_needed(void *opaque)
     return (vdev->host_features >> 32) != 0;
 }
 
+static bool virtio_virtqueue_needed(void *opaque)
+{
+    VirtIODevice *vdev = opaque;
+
+    return virtio_host_has_feature(vdev, VIRTIO_F_VERSION_1);
+}
+
+static void put_virtqueue_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIODevice *vdev = pv;
+    int i;
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        qemu_put_be64(f, vdev->vq[i].vring.avail);
+        qemu_put_be64(f, vdev->vq[i].vring.used);
+    }
+}
+
+static int get_virtqueue_state(QEMUFile *f, void *pv, size_t size)
+{
+    VirtIODevice *vdev = pv;
+    int i;
+
+    for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+        vdev->vq[i].vring.avail = qemu_get_be64(f);
+        vdev->vq[i].vring.used = qemu_get_be64(f);
+    }
+    return 0;
+}
+
+static VMStateInfo vmstate_info_virtqueue = {
+    .name = "virtqueue_state",
+    .get = get_virtqueue_state,
+    .put = put_virtqueue_state,
+};
+
+static const VMStateDescription vmstate_virtio_virtqueues = {
+    .name = "virtio/virtqueues",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = &virtio_virtqueue_needed,
+    .fields = (VMStateField[]) {
+        {
+            .name         = "virtqueues",
+            .version_id   = 0,
+            .field_exists = NULL,
+            .size         = 0,
+            .info         = &vmstate_info_virtqueue,
+            .flags        = VMS_SINGLE,
+            .offset       = 0,
+        },
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_virtio_device_endian = {
     .name = "virtio/device_endian",
     .version_id = 1,
@@ -1082,6 +1150,7 @@ static const VMStateDescription vmstate_virtio = {
     .subsections = (const VMStateDescription*[]) {
         &vmstate_virtio_device_endian,
         &vmstate_virtio_64bit_features,
+        &vmstate_virtio_virtqueues,
         NULL
     }
 };

include/block/aio.h

@@ -114,6 +114,9 @@ struct AioContext {
     bool notified;
     EventNotifier notifier;
 
+    /* Scheduling this BH forces the event loop it iterate */
+    QEMUBH *notify_dummy_bh;
+
     /* Thread pool for performing work and receiving completion callbacks */
     struct ThreadPool *thread_pool;
 

include/exec/exec-all.h

@@ -308,11 +308,7 @@ extern uintptr_t tci_tb_ptr;
    to indicate the compressed mode; subtracting two works around that.  It
    is also the case that there are no host isas that contain a call insn
    smaller than 4 bytes, so we don't worry about special-casing this.  */
-#if defined(CONFIG_TCG_INTERPRETER)
-# define GETPC_ADJ   0
-#else
-# define GETPC_ADJ   2
-#endif
+#define GETPC_ADJ   2
 
 #define GETPC()  (GETRA() - GETPC_ADJ)
 

include/exec/memory.h

@@ -180,6 +180,7 @@ struct MemoryRegion {
     bool warning_printed; /* For reservations */
     bool flush_coalesced_mmio;
     bool global_locking;
+    uint8_t vga_logging_count;
     MemoryRegion *alias;
     hwaddr alias_offset;
     int32_t priority;

include/hw/compat.h

@@ -2,7 +2,27 @@
 #define HW_COMPAT_H
 
 #define HW_COMPAT_2_3 \
-        /* empty */
+        {\
+            .driver   = "virtio-blk-pci",\
+            .property = "any_layout",\
+            .value    = "off",\
+        },{\
+            .driver   = "virtio-balloon-pci",\
+            .property = "any_layout",\
+            .value    = "off",\
+        },{\
+            .driver   = "virtio-serial-pci",\
+            .property = "any_layout",\
+            .value    = "off",\
+        },{\
+            .driver   = "virtio-9p-pci",\
+            .property = "any_layout",\
+            .value    = "off",\
+        },{\
+            .driver   = "virtio-rng-pci",\
+            .property = "any_layout",\
+            .value    = "off",\
+        },
 
 #define HW_COMPAT_2_2 \
         /* empty */

include/hw/i386/pc.h

@@ -350,6 +350,10 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *);
             .driver   = "SandyBridge" "-" TYPE_X86_CPU,\
             .property = "xlevel",\
             .value    = stringify(0x8000000a),\
+        },{\
+            .driver   = "IvyBridge" "-" TYPE_X86_CPU,\
+            .property = "xlevel",\
+            .value    = stringify(0x8000000a),\
         },{\
             .driver   = "Haswell" "-" TYPE_X86_CPU,\
             .property = "xlevel",\