Update version for 5.0.1 release

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

MAINTAINERS

@@ -1853,6 +1853,18 @@ F: hw/display/virtio-gpu*
 F: hw/display/virtio-vga.*
 F: include/hw/virtio/virtio-gpu.h
 
+vhost-user-blk
+M: Raphael Norwitz <raphael.norwitz@nutanix.com>
+S: Maintained
+F: contrib/vhost-user-blk/
+F: contrib/vhost-user-scsi/
+F: hw/block/vhost-user-blk.c
+F: hw/scsi/vhost-user-scsi.c
+F: hw/virtio/vhost-user-blk-pci.c
+F: hw/virtio/vhost-user-scsi-pci.c
+F: include/hw/virtio/vhost-user-blk.h
+F: include/hw/virtio/vhost-user-scsi.h
+
 vhost-user-gpu
 M: Marc-André Lureau <marcandre.lureau@redhat.com>
 M: Gerd Hoffmann <kraxel@redhat.com>
@@ -2026,6 +2038,11 @@ M: Markus Armbruster <armbru@redhat.com>
 S: Supported
 F: scripts/coverity-model.c
 
+Coverity Scan integration
+M: Peter Maydell <peter.maydell@linaro.org>
+S: Maintained
+F: scripts/coverity-scan/
+
 Device Tree
 M: Alistair Francis <alistair.francis@wdc.com>
 R: David Gibson <david@gibson.dropbear.id.au>

Makefile

@@ -1076,7 +1076,7 @@ sphinxdocs: $(MANUAL_BUILDDIR)/devel/index.html \
 # Note the use of different doctree for each (manual, builder) tuple;
 # this works around Sphinx not handling parallel invocation on
 # a single doctree: https://github.com/sphinx-doc/sphinx/issues/2946
-build-manual = $(call quiet-command,CONFDIR="$(qemu_confdir)" $(SPHINX_BUILD) $(if $(V),,-q) -W -b $2 -D version=$(VERSION) -D release="$(FULL_VERSION)" -d .doctrees/$1-$2 $(SRC_PATH)/docs/$1 $(MANUAL_BUILDDIR)/$1 ,"SPHINX","$(MANUAL_BUILDDIR)/$1")
+build-manual = $(call quiet-command,CONFDIR="$(qemu_confdir)" $(SPHINX_BUILD) $(if $(V),,-q) $(SPHINX_WERROR) -b $2 -D version=$(VERSION) -D release="$(FULL_VERSION)" -d .doctrees/$1-$2 $(SRC_PATH)/docs/$1 $(MANUAL_BUILDDIR)/$1 ,"SPHINX","$(MANUAL_BUILDDIR)/$1")
 # We assume all RST files in the manual's directory are used in it
 manual-deps = $(wildcard $(SRC_PATH)/docs/$1/*.rst $(SRC_PATH)/docs/$1/*/*.rst) \
               $(SRC_PATH)/docs/defs.rst.inc \

VERSION

@@ -1 +1 @@
-4.2.92
+5.0.1

backends/hostmem.c

@@ -280,6 +280,7 @@ static void host_memory_backend_init(Object *obj)
     /* TODO: convert access to globals to compat properties */
     backend->merge = machine_mem_merge(machine);
     backend->dump = machine_dump_guest_core(machine);
+    backend->prealloc_threads = 1;
 }
 
 static void host_memory_backend_post_init(Object *obj)
@@ -382,8 +383,10 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
         assert(sizeof(backend->host_nodes) >=
                BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
         assert(maxnode <= MAX_NODES);
-        if (mbind(ptr, sz, backend->policy,
-                  maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
+
+        if (maxnode &&
+            mbind(ptr, sz, backend->policy, backend->host_nodes, maxnode + 1,
+                  flags)) {
             if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) {
                 error_setg_errno(errp, errno,
                                  "cannot bind memory to host NUMA nodes");

block.c

@@ -6710,8 +6710,11 @@ void bdrv_refresh_filename(BlockDriverState *bs)
         pstrcpy(bs->filename, sizeof(bs->filename), bs->exact_filename);
     } else {
         QString *json = qobject_to_json(QOBJECT(bs->full_open_options));
-        snprintf(bs->filename, sizeof(bs->filename), "json:%s",
-                 qstring_get_str(json));
+        if (snprintf(bs->filename, sizeof(bs->filename), "json:%s",
+                     qstring_get_str(json)) >= sizeof(bs->filename)) {
+            /* Give user a hint if we truncated things. */
+            strcpy(bs->filename + sizeof(bs->filename) - 4, "...");
+        }
         qobject_unref(json);
     }
 }

block/io.c

@@ -1501,12 +1501,13 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
             assert(num);
 
             ret = bdrv_driver_preadv(bs, offset + bytes - bytes_remaining,
-                                     num, qiov, bytes - bytes_remaining, 0);
+                                     num, qiov,
+                                     qiov_offset + bytes - bytes_remaining, 0);
             max_bytes -= num;
         } else {
             num = bytes_remaining;
-            ret = qemu_iovec_memset(qiov, bytes - bytes_remaining, 0,
-                                    bytes_remaining);
+            ret = qemu_iovec_memset(qiov, qiov_offset + bytes - bytes_remaining,
+                                    0, bytes_remaining);
         }
         if (ret < 0) {
             goto out;
@@ -2009,7 +2010,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child,
             }
 
             ret = bdrv_driver_pwritev(bs, offset + bytes - bytes_remaining,
-                                      num, qiov, bytes - bytes_remaining,
+                                      num, qiov,
+                                      qiov_offset + bytes - bytes_remaining,
                                       local_flags);
             if (ret < 0) {
                 break;

block/iscsi.c

@@ -991,8 +991,7 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
         acb->ioh->driver_status |= SG_ERR_DRIVER_SENSE;
 
         acb->ioh->sb_len_wr = acb->task->datain.size - 2;
-        ss = (acb->ioh->mx_sb_len >= acb->ioh->sb_len_wr) ?
-             acb->ioh->mx_sb_len : acb->ioh->sb_len_wr;
+        ss = MIN(acb->ioh->mx_sb_len, acb->ioh->sb_len_wr);
         memcpy(acb->ioh->sbp, &acb->task->datain.data[2], ss);
     }
 

block/nbd.c

@@ -1986,6 +1986,7 @@ static void nbd_refresh_filename(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
     const char *host = NULL, *port = NULL, *path = NULL;
+    size_t len = 0;
 
     if (s->saddr->type == SOCKET_ADDRESS_TYPE_INET) {
         const InetSocketAddress *inet = &s->saddr->u.inet;
@@ -1998,17 +1999,21 @@ static void nbd_refresh_filename(BlockDriverState *bs)
     } /* else can't represent as pseudo-filename */
 
     if (path && s->export) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nbd+unix:///%s?socket=%s", s->export, path);
+        len = snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                       "nbd+unix:///%s?socket=%s", s->export, path);
     } else if (path && !s->export) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nbd+unix://?socket=%s", path);
+        len = snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                       "nbd+unix://?socket=%s", path);
     } else if (host && s->export) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nbd://%s:%s/%s", host, port, s->export);
+        len = snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                       "nbd://%s:%s/%s", host, port, s->export);
     } else if (host && !s->export) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nbd://%s:%s", host, port);
+        len = snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                       "nbd://%s:%s", host, port);
+    }
+    if (len >= sizeof(bs->exact_filename)) {
+        /* Name is too long to represent exactly, so leave it empty. */
+        bs->exact_filename[0] = '\0';
     }
 }
 

chardev/char-socket.c

@@ -138,9 +138,12 @@ static void check_report_connect_error(Chardev *chr,
     SocketChardev *s = SOCKET_CHARDEV(chr);
 
     if (!s->connect_err_reported) {
-        error_report("Unable to connect character device %s: %s",
-                     chr->label, error_get_pretty(err));
+        error_reportf_err(err,
+                          "Unable to connect character device %s: ",
+                          chr->label);
         s->connect_err_reported = true;
+    } else {
+        error_free(err);
     }
     qemu_chr_socket_restart_timer(chr);
 }
@@ -1082,7 +1085,6 @@ static void qemu_chr_socket_connected(QIOTask *task, void *opaque)
     if (qio_task_propagate_error(task, &err)) {
         tcp_chr_change_state(s, TCP_CHARDEV_STATE_DISCONNECTED);
         check_report_connect_error(chr, err);
-        error_free(err);
         goto cleanup;
     }
 

configure

@@ -807,6 +807,7 @@ MINGW32*)
     audio_drv_list=""
   fi
   supported_os="yes"
+  pie="no"
 ;;
 GNU/kFreeBSD)
   bsd="yes"
@@ -4928,6 +4929,12 @@ if check_include sys/kcov.h ; then
     kcov=yes
 fi
 
+# If we're making warnings fatal, apply this to Sphinx runs as well
+sphinx_werror=""
+if test "$werror" = "yes"; then
+    sphinx_werror="-W"
+fi
+
 # Check we have a new enough version of sphinx-build
 has_sphinx_build() {
     # This is a bit awkward but works: create a trivial document and
@@ -4936,7 +4943,9 @@ has_sphinx_build() {
     # sphinx-build doesn't exist at all or if it is too old.
     mkdir -p "$TMPDIR1/sphinx"
     touch "$TMPDIR1/sphinx/index.rst"
-    "$sphinx_build" -c "$source_path/docs" -b html "$TMPDIR1/sphinx" "$TMPDIR1/sphinx/out" >/dev/null 2>&1
+    "$sphinx_build" $sphinx_werror -c "$source_path/docs" \
+                    -b html "$TMPDIR1/sphinx" \
+                    "$TMPDIR1/sphinx/out"  >> config.log 2>&1
 }
 
 # Check if tools are available to build documentation.
@@ -7631,6 +7640,7 @@ echo "INSTALL_PROG=$install -c -m 0755" >> $config_host_mak
 echo "INSTALL_LIB=$install -c -m 0644" >> $config_host_mak
 echo "PYTHON=$python" >> $config_host_mak
 echo "SPHINX_BUILD=$sphinx_build" >> $config_host_mak
+echo "SPHINX_WERROR=$sphinx_werror" >> $config_host_mak
 echo "GENISOIMAGE=$genisoimage" >> $config_host_mak
 echo "CC=$cc" >> $config_host_mak
 if $iasl -h > /dev/null 2>&1; then

contrib/libvhost-user/libvhost-user.c

@@ -1867,7 +1867,7 @@ virtqueue_get_head(VuDev *dev, VuVirtq *vq,
 
     /* If their number is silly, that's a fatal mistake. */
     if (*head >= vq->vring.num) {
-        vu_panic(dev, "Guest says index %u is available", head);
+        vu_panic(dev, "Guest says index %u is available", *head);
         return false;
     }
 
@@ -1926,7 +1926,7 @@ virtqueue_read_next_desc(VuDev *dev, struct vring_desc *desc,
     smp_wmb();
 
     if (*next >= max) {
-        vu_panic(dev, "Desc next is %u", next);
+        vu_panic(dev, "Desc next is %u", *next);
         return VIRTQUEUE_READ_DESC_ERROR;
     }
 

contrib/vhost-user-gpu/vhost-user-gpu.c

@@ -848,7 +848,7 @@ vg_handle_ctrl(VuDev *dev, int qidx)
             QTAILQ_INSERT_TAIL(&vg->fenceq, cmd, next);
             vg->inflight++;
         } else {
-            g_free(cmd);
+            free(cmd);
         }
     }
 }
@@ -939,7 +939,7 @@ vg_handle_cursor(VuDev *dev, int qidx)
         }
         vu_queue_push(dev, vq, elem, 0);
         vu_queue_notify(dev, vq);
-        g_free(elem);
+        free(elem);
     }
 }
 

contrib/vhost-user-gpu/virgl.c

@@ -519,7 +519,7 @@ virgl_write_fence(void *opaque, uint32_t fence)
         g_debug("FENCE %" PRIu64, cmd->cmd_hdr.fence_id);
         vg_ctrl_response_nodata(g, cmd, VIRTIO_GPU_RESP_OK_NODATA);
         QTAILQ_REMOVE(&g->fenceq, cmd, next);
-        g_free(cmd);
+        free(cmd);
         g->inflight--;
     }
 }

docs/conf.py

@@ -59,8 +59,10 @@ sys.path.insert(0, os.path.join(qemu_docdir, "sphinx"))
 
 # If your documentation needs a minimal Sphinx version, state it here.
 #
-# 1.3 is where the 'alabaster' theme was shipped with Sphinx.
-needs_sphinx = '1.3'
+# Sphinx 1.5 and earlier can't build our docs because they are too
+# picky about the syntax of the argument to the option:: directive
+# (see Sphinx bugs #646, #3366).
+needs_sphinx = '1.6'
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom

docs/devel/atomics.rst

@@ -0,0 +1,507 @@
+=========================
+Atomic operations in QEMU
+=========================
+
+CPUs perform independent memory operations effectively in random order.
+but this can be a problem for CPU-CPU interaction (including interactions
+between QEMU and the guest).  Multi-threaded programs use various tools
+to instruct the compiler and the CPU to restrict the order to something
+that is consistent with the expectations of the programmer.
+
+The most basic tool is locking.  Mutexes, condition variables and
+semaphores are used in QEMU, and should be the default approach to
+synchronization.  Anything else is considerably harder, but it's
+also justified more often than one would like;
+the most performance-critical parts of QEMU in particular require
+a very low level approach to concurrency, involving memory barriers
+and atomic operations.  The semantics of concurrent memory accesses are governed
+by the C11 memory model.
+
+QEMU provides a header, ``qemu/atomic.h``, which wraps C11 atomics to
+provide better portability and a less verbose syntax.  ``qemu/atomic.h``
+provides macros that fall in three camps:
+
+- compiler barriers: ``barrier()``;
+
+- weak atomic access and manual memory barriers: ``atomic_read()``,
+  ``atomic_set()``, ``smp_rmb()``, ``smp_wmb()``, ``smp_mb()``, ``smp_mb_acquire()``,
+  ``smp_mb_release()``, ``smp_read_barrier_depends()``;
+
+- sequentially consistent atomic access: everything else.
+
+In general, use of ``qemu/atomic.h`` should be wrapped with more easily
+used data structures (e.g. the lock-free singly-linked list operations
+``QSLIST_INSERT_HEAD_ATOMIC`` and ``QSLIST_MOVE_ATOMIC``) or synchronization
+primitives (such as RCU, ``QemuEvent`` or ``QemuLockCnt``).  Bare use of
+atomic operations and memory barriers should be limited to inter-thread
+checking of flags and documented thoroughly.
+
+
+
+Compiler memory barrier
+=======================
+
+``barrier()`` prevents the compiler from moving the memory accesses on
+either side of it to the other side.  The compiler barrier has no direct
+effect on the CPU, which may then reorder things however it wishes.
+
+``barrier()`` is mostly used within ``qemu/atomic.h`` itself.  On some
+architectures, CPU guarantees are strong enough that blocking compiler
+optimizations already ensures the correct order of execution.  In this
+case, ``qemu/atomic.h`` will reduce stronger memory barriers to simple
+compiler barriers.
+
+Still, ``barrier()`` can be useful when writing code that can be interrupted
+by signal handlers.
+
+
+Sequentially consistent atomic access
+=====================================
+
+Most of the operations in the ``qemu/atomic.h`` header ensure *sequential
+consistency*, where "the result of any execution is the same as if the
+operations of all the processors were executed in some sequential order,
+and the operations of each individual processor appear in this sequence
+in the order specified by its program".
+
+``qemu/atomic.h`` provides the following set of atomic read-modify-write
+operations::
+
+    void atomic_inc(ptr)
+    void atomic_dec(ptr)
+    void atomic_add(ptr, val)
+    void atomic_sub(ptr, val)
+    void atomic_and(ptr, val)
+    void atomic_or(ptr, val)
+
+    typeof(*ptr) atomic_fetch_inc(ptr)
+    typeof(*ptr) atomic_fetch_dec(ptr)
+    typeof(*ptr) atomic_fetch_add(ptr, val)
+    typeof(*ptr) atomic_fetch_sub(ptr, val)
+    typeof(*ptr) atomic_fetch_and(ptr, val)
+    typeof(*ptr) atomic_fetch_or(ptr, val)
+    typeof(*ptr) atomic_fetch_xor(ptr, val)
+    typeof(*ptr) atomic_fetch_inc_nonzero(ptr)
+    typeof(*ptr) atomic_xchg(ptr, val)
+    typeof(*ptr) atomic_cmpxchg(ptr, old, new)
+
+all of which return the old value of ``*ptr``.  These operations are
+polymorphic; they operate on any type that is as wide as a pointer or
+smaller.
+
+Similar operations return the new value of ``*ptr``::
+
+    typeof(*ptr) atomic_inc_fetch(ptr)
+    typeof(*ptr) atomic_dec_fetch(ptr)
+    typeof(*ptr) atomic_add_fetch(ptr, val)
+    typeof(*ptr) atomic_sub_fetch(ptr, val)
+    typeof(*ptr) atomic_and_fetch(ptr, val)
+    typeof(*ptr) atomic_or_fetch(ptr, val)
+    typeof(*ptr) atomic_xor_fetch(ptr, val)
+
+``qemu/atomic.h`` also provides loads and stores that cannot be reordered
+with each other::
+
+    typeof(*ptr) atomic_mb_read(ptr)
+    void         atomic_mb_set(ptr, val)
+
+However these do not provide sequential consistency and, in particular,
+they do not participate in the total ordering enforced by
+sequentially-consistent operations.  For this reason they are deprecated.
+They should instead be replaced with any of the following (ordered from
+easiest to hardest):
+
+- accesses inside a mutex or spinlock
+
+- lightweight synchronization primitives such as ``QemuEvent``
+
+- RCU operations (``atomic_rcu_read``, ``atomic_rcu_set``) when publishing
+  or accessing a new version of a data structure
+
+- other atomic accesses: ``atomic_read`` and ``atomic_load_acquire`` for
+  loads, ``atomic_set`` and ``atomic_store_release`` for stores, ``smp_mb``
+  to forbid reordering subsequent loads before a store.
+
+
+Weak atomic access and manual memory barriers
+=============================================
+
+Compared to sequentially consistent atomic access, programming with
+weaker consistency models can be considerably more complicated.
+The only guarantees that you can rely upon in this case are:
+
+- atomic accesses will not cause data races (and hence undefined behavior);
+  ordinary accesses instead cause data races if they are concurrent with
+  other accesses of which at least one is a write.  In order to ensure this,
+  the compiler will not optimize accesses out of existence, create unsolicited
+  accesses, or perform other similar optimzations.
+
+- acquire operations will appear to happen, with respect to the other
+  components of the system, before all the LOAD or STORE operations
+  specified afterwards.
+
+- release operations will appear to happen, with respect to the other
+  components of the system, after all the LOAD or STORE operations
+  specified before.
+
+- release operations will *synchronize with* acquire operations;
+  see :ref:`acqrel` for a detailed explanation.
+
+When using this model, variables are accessed with:
+
+- ``atomic_read()`` and ``atomic_set()``; these prevent the compiler from
+  optimizing accesses out of existence and creating unsolicited
+  accesses, but do not otherwise impose any ordering on loads and
+  stores: both the compiler and the processor are free to reorder
+  them.
+
+- ``atomic_load_acquire()``, which guarantees the LOAD to appear to
+  happen, with respect to the other components of the system,
+  before all the LOAD or STORE operations specified afterwards.
+  Operations coming before ``atomic_load_acquire()`` can still be
+  reordered after it.
+
+- ``atomic_store_release()``, which guarantees the STORE to appear to
+  happen, with respect to the other components of the system,
+  after all the LOAD or STORE operations specified before.
+  Operations coming after ``atomic_store_release()`` can still be
+  reordered before it.
+
+Restrictions to the ordering of accesses can also be specified
+using the memory barrier macros: ``smp_rmb()``, ``smp_wmb()``, ``smp_mb()``,
+``smp_mb_acquire()``, ``smp_mb_release()``, ``smp_read_barrier_depends()``.
+
+Memory barriers control the order of references to shared memory.
+They come in six kinds:
+
+- ``smp_rmb()`` guarantees that all the LOAD operations specified before
+  the barrier will appear to happen before all the LOAD operations
+  specified after the barrier with respect to the other components of
+  the system.
+
+  In other words, ``smp_rmb()`` puts a partial ordering on loads, but is not
+  required to have any effect on stores.
+
+- ``smp_wmb()`` guarantees that all the STORE operations specified before
+  the barrier will appear to happen before all the STORE operations
+  specified after the barrier with respect to the other components of
+  the system.
+
+  In other words, ``smp_wmb()`` puts a partial ordering on stores, but is not
+  required to have any effect on loads.
+
+- ``smp_mb_acquire()`` guarantees that all the LOAD operations specified before
+  the barrier will appear to happen before all the LOAD or STORE operations
+  specified after the barrier with respect to the other components of
+  the system.
+
+- ``smp_mb_release()`` guarantees that all the STORE operations specified *after*
+  the barrier will appear to happen after all the LOAD or STORE operations
+  specified *before* the barrier with respect to the other components of
+  the system.
+
+- ``smp_mb()`` guarantees that all the LOAD and STORE operations specified
+  before the barrier will appear to happen before all the LOAD and
+  STORE operations specified after the barrier with respect to the other
+  components of the system.
+
+  ``smp_mb()`` puts a partial ordering on both loads and stores.  It is
+  stronger than both a read and a write memory barrier; it implies both
+  ``smp_mb_acquire()`` and ``smp_mb_release()``, but it also prevents STOREs
+  coming before the barrier from overtaking LOADs coming after the
+  barrier and vice versa.
+
+- ``smp_read_barrier_depends()`` is a weaker kind of read barrier.  On
+  most processors, whenever two loads are performed such that the
+  second depends on the result of the first (e.g., the first load
+  retrieves the address to which the second load will be directed),
+  the processor will guarantee that the first LOAD will appear to happen
+  before the second with respect to the other components of the system.
+  However, this is not always true---for example, it was not true on
+  Alpha processors.  Whenever this kind of access happens to shared
+  memory (that is not protected by a lock), a read barrier is needed,
+  and ``smp_read_barrier_depends()`` can be used instead of ``smp_rmb()``.
+
+  Note that the first load really has to have a _data_ dependency and not
+  a control dependency.  If the address for the second load is dependent
+  on the first load, but the dependency is through a conditional rather
+  than actually loading the address itself, then it's a _control_
+  dependency and a full read barrier or better is required.
+
+
+Memory barriers and ``atomic_load_acquire``/``atomic_store_release`` are
+mostly used when a data structure has one thread that is always a writer
+and one thread that is always a reader:
+
+    +----------------------------------+----------------------------------+
+    | thread 1                         | thread 2                         |
+    +==================================+==================================+
+    | ::                               | ::                               |
+    |                                  |                                  |
+    |   atomic_store_release(&a, x);   |   y = atomic_load_acquire(&b);   |
+    |   atomic_store_release(&b, y);   |   x = atomic_load_acquire(&a);   |
+    +----------------------------------+----------------------------------+
+
+In this case, correctness is easy to check for using the "pairing"
+trick that is explained below.
+
+Sometimes, a thread is accessing many variables that are otherwise
+unrelated to each other (for example because, apart from the current
+thread, exactly one other thread will read or write each of these
+variables).  In this case, it is possible to "hoist" the barriers
+outside a loop.  For example:
+
+    +------------------------------------------+----------------------------------+
+    | before                                   | after                            |
+    +==========================================+==================================+
+    | ::                                       | ::                               |
+    |                                          |                                  |
+    |   n = 0;                                 |   n = 0;                         |
+    |   for (i = 0; i < 10; i++)               |   for (i = 0; i < 10; i++)       |
+    |     n += atomic_load_acquire(&a[i]);     |     n += atomic_read(&a[i]);     |
+    |                                          |   smp_mb_acquire();              |
+    +------------------------------------------+----------------------------------+
+    | ::                                       | ::                               |
+    |                                          |                                  |
+    |                                          |   smp_mb_release();              |
+    |   for (i = 0; i < 10; i++)               |   for (i = 0; i < 10; i++)       |
+    |     atomic_store_release(&a[i], false);  |     atomic_set(&a[i], false);    |
+    +------------------------------------------+----------------------------------+
+
+Splitting a loop can also be useful to reduce the number of barriers:
+
+    +------------------------------------------+----------------------------------+
+    | before                                   | after                            |
+    +==========================================+==================================+
+    | ::                                       | ::                               |
+    |                                          |                                  |
+    |   n = 0;                                 |     smp_mb_release();            |
+    |   for (i = 0; i < 10; i++) {             |     for (i = 0; i < 10; i++)     |
+    |     atomic_store_release(&a[i], false);  |       atomic_set(&a[i], false);  |
+    |     smp_mb();                            |     smb_mb();                    |
+    |     n += atomic_read(&b[i]);             |     n = 0;                       |
+    |   }                                      |     for (i = 0; i < 10; i++)     |
+    |                                          |       n += atomic_read(&b[i]);   |
+    +------------------------------------------+----------------------------------+
+
+In this case, a ``smp_mb_release()`` is also replaced with a (possibly cheaper, and clearer
+as well) ``smp_wmb()``:
+
+    +------------------------------------------+----------------------------------+
+    | before                                   | after                            |
+    +==========================================+==================================+
+    | ::                                       | ::                               |
+    |                                          |                                  |
+    |                                          |     smp_mb_release();            |
+    |   for (i = 0; i < 10; i++) {             |     for (i = 0; i < 10; i++)     |
+    |     atomic_store_release(&a[i], false);  |       atomic_set(&a[i], false);  |
+    |     atomic_store_release(&b[i], false);  |     smb_wmb();                   |
+    |   }                                      |     for (i = 0; i < 10; i++)     |
+    |                                          |       atomic_set(&b[i], false);  |
+    +------------------------------------------+----------------------------------+
+
+
+.. _acqrel:
+
+Acquire/release pairing and the *synchronizes-with* relation
+------------------------------------------------------------
+
+Atomic operations other than ``atomic_set()`` and ``atomic_read()`` have
+either *acquire* or *release* semantics [#rmw]_.  This has two effects:
+
+.. [#rmw] Read-modify-write operations can have both---acquire applies to the
+          read part, and release to the write.
+
+- within a thread, they are ordered either before subsequent operations
+  (for acquire) or after previous operations (for release).
+
+- if a release operation in one thread *synchronizes with* an acquire operation
+  in another thread, the ordering constraints propagates from the first to the
+  second thread.  That is, everything before the release operation in the
+  first thread is guaranteed to *happen before* everything after the
+  acquire operation in the second thread.
+
+The concept of acquire and release semantics is not exclusive to atomic
+operations; almost all higher-level synchronization primitives also have
+acquire or release semantics.  For example:
+
+- ``pthread_mutex_lock`` has acquire semantics, ``pthread_mutex_unlock`` has
+  release semantics and synchronizes with a ``pthread_mutex_lock`` for the
+  same mutex.
+
+- ``pthread_cond_signal`` and ``pthread_cond_broadcast`` have release semantics;
+  ``pthread_cond_wait`` has both release semantics (synchronizing with
+  ``pthread_mutex_lock``) and acquire semantics (synchronizing with
+  ``pthread_mutex_unlock`` and signaling of the condition variable).
+
+- ``pthread_create`` has release semantics and synchronizes with the start
+  of the new thread; ``pthread_join`` has acquire semantics and synchronizes
+  with the exiting of the thread.
+
+- ``qemu_event_set`` has release semantics, ``qemu_event_wait`` has
+  acquire semantics.
+
+For example, in the following example there are no atomic accesses, but still
+thread 2 is relying on the *synchronizes-with* relation between ``pthread_exit``
+(release) and ``pthread_join`` (acquire):
+
+      +----------------------+-------------------------------+
+      | thread 1             | thread 2                      |
+      +======================+===============================+
+      | ::                   | ::                            |
+      |                      |                               |
+      |   *a = 1;            |                               |
+      |   pthread_exit(a);   |   pthread_join(thread1, &a);  |
+      |                      |   x = *a;                     |
+      +----------------------+-------------------------------+
+
+Synchronization between threads basically descends from this pairing of
+a release operation and an acquire operation.  Therefore, atomic operations
+other than ``atomic_set()`` and ``atomic_read()`` will almost always be
+paired with another operation of the opposite kind: an acquire operation
+will pair with a release operation and vice versa.  This rule of thumb is
+extremely useful; in the case of QEMU, however, note that the other
+operation may actually be in a driver that runs in the guest!
+
+``smp_read_barrier_depends()``, ``smp_rmb()``, ``smp_mb_acquire()``,
+``atomic_load_acquire()`` and ``atomic_rcu_read()`` all count
+as acquire operations.  ``smp_wmb()``, ``smp_mb_release()``,
+``atomic_store_release()`` and ``atomic_rcu_set()`` all count as release
+operations.  ``smp_mb()`` counts as both acquire and release, therefore
+it can pair with any other atomic operation.  Here is an example:
+
+      +----------------------+------------------------------+
+      | thread 1             | thread 2                     |
+      +======================+==============================+
+      | ::                   | ::                           |
+      |                      |                              |
+      |   atomic_set(&a, 1); |                              |
+      |   smp_wmb();         |                              |
+      |   atomic_set(&b, 2); |   x = atomic_read(&b);       |
+      |                      |   smp_rmb();                 |
+      |                      |   y = atomic_read(&a);       |
+      +----------------------+------------------------------+
+
+Note that a load-store pair only counts if the two operations access the
+same variable: that is, a store-release on a variable ``x`` *synchronizes
+with* a load-acquire on a variable ``x``, while a release barrier
+synchronizes with any acquire operation.  The following example shows
+correct synchronization:
+
+      +--------------------------------+--------------------------------+
+      | thread 1                       | thread 2                       |
+      +================================+================================+
+      | ::                             | ::                             |
+      |                                |                                |
+      |   atomic_set(&a, 1);           |                                |
+      |   atomic_store_release(&b, 2); |   x = atomic_load_acquire(&b); |
+      |                                |   y = atomic_read(&a);         |
+      +--------------------------------+--------------------------------+
+
+Acquire and release semantics of higher-level primitives can also be
+relied upon for the purpose of establishing the *synchronizes with*
+relation.
+
+Note that the "writing" thread is accessing the variables in the
+opposite order as the "reading" thread.  This is expected: stores
+before a release operation will normally match the loads after
+the acquire operation, and vice versa.  In fact, this happened already
+in the ``pthread_exit``/``pthread_join`` example above.
+
+Finally, this more complex example has more than two accesses and data
+dependency barriers.  It also does not use atomic accesses whenever there
+cannot be a data race:
+
+      +----------------------+------------------------------+
+      | thread 1             | thread 2                     |
+      +======================+==============================+
+      | ::                   | ::                           |
+      |                      |                              |
+      |   b[2] = 1;          |                              |
+      |   smp_wmb();         |                              |
+      |   x->i = 2;          |                              |
+      |   smp_wmb();         |                              |
+      |   atomic_set(&a, x); |  x = atomic_read(&a);        |
+      |                      |  smp_read_barrier_depends(); |
+      |                      |  y = x->i;                   |
+      |                      |  smp_read_barrier_depends(); |
+      |                      |  z = b[y];                   |
+      +----------------------+------------------------------+
+
+Comparison with Linux kernel primitives
+=======================================
+
+Here is a list of differences between Linux kernel atomic operations
+and memory barriers, and the equivalents in QEMU:
+
+- atomic operations in Linux are always on a 32-bit int type and
+  use a boxed ``atomic_t`` type; atomic operations in QEMU are polymorphic
+  and use normal C types.
+
+- Originally, ``atomic_read`` and ``atomic_set`` in Linux gave no guarantee
+  at all. Linux 4.1 updated them to implement volatile
+  semantics via ``ACCESS_ONCE`` (or the more recent ``READ``/``WRITE_ONCE``).
+
+  QEMU's ``atomic_read`` and ``atomic_set`` implement C11 atomic relaxed
+  semantics if the compiler supports it, and volatile semantics otherwise.
+  Both semantics prevent the compiler from doing certain transformations;
+  the difference is that atomic accesses are guaranteed to be atomic,
+  while volatile accesses aren't. Thus, in the volatile case we just cross
+  our fingers hoping that the compiler will generate atomic accesses,
+  since we assume the variables passed are machine-word sized and
+  properly aligned.
+
+  No barriers are implied by ``atomic_read`` and ``atomic_set`` in either Linux
+  or QEMU.
+
+- atomic read-modify-write operations in Linux are of three kinds:
+
+         ===================== =========================================
+         ``atomic_OP``         returns void
+         ``atomic_OP_return``  returns new value of the variable
+         ``atomic_fetch_OP``   returns the old value of the variable
+         ``atomic_cmpxchg``    returns the old value of the variable
+         ===================== =========================================
+
+  In QEMU, the second kind is named ``atomic_OP_fetch``.
+
+- different atomic read-modify-write operations in Linux imply
+  a different set of memory barriers; in QEMU, all of them enforce
+  sequential consistency.
+
+- in QEMU, ``atomic_read()`` and ``atomic_set()`` do not participate in
+  the total ordering enforced by sequentially-consistent operations.
+  This is because QEMU uses the C11 memory model.  The following example
+  is correct in Linux but not in QEMU:
+
+      +----------------------------------+--------------------------------+
+      | Linux (correct)                  | QEMU (incorrect)               |
+      +==================================+================================+
+      | ::                               | ::                             |
+      |                                  |                                |
+      |   a = atomic_fetch_add(&x, 2);   |   a = atomic_fetch_add(&x, 2); |
+      |   b = READ_ONCE(&y);             |   b = atomic_read(&y);         |
+      +----------------------------------+--------------------------------+
+
+  because the read of ``y`` can be moved (by either the processor or the
+  compiler) before the write of ``x``.
+
+  Fixing this requires an ``smp_mb()`` memory barrier between the write
+  of ``x`` and the read of ``y``.  In the common case where only one thread
+  writes ``x``, it is also possible to write it like this:
+
+      +--------------------------------+
+      | QEMU (correct)                 |
+      +================================+
+      | ::                             |
+      |                                |
+      |   a = atomic_read(&x);         |
+      |   atomic_set(&x, a + 2);       |
+      |   smp_mb();                    |
+      |   b = atomic_read(&y);         |
+      +--------------------------------+
+
+Sources
+=======
+
+- ``Documentation/memory-barriers.txt`` from the Linux kernel

docs/devel/atomics.txt

@@ -1,403 +0,0 @@
-CPUs perform independent memory operations effectively in random order.
-but this can be a problem for CPU-CPU interaction (including interactions
-between QEMU and the guest).  Multi-threaded programs use various tools
-to instruct the compiler and the CPU to restrict the order to something
-that is consistent with the expectations of the programmer.
-
-The most basic tool is locking.  Mutexes, condition variables and
-semaphores are used in QEMU, and should be the default approach to
-synchronization.  Anything else is considerably harder, but it's
-also justified more often than one would like.  The two tools that
-are provided by qemu/atomic.h are memory barriers and atomic operations.
-
-Macros defined by qemu/atomic.h fall in three camps:
-
-- compiler barriers: barrier();
-
-- weak atomic access and manual memory barriers: atomic_read(),
-  atomic_set(), smp_rmb(), smp_wmb(), smp_mb(), smp_mb_acquire(),
-  smp_mb_release(), smp_read_barrier_depends();
-
-- sequentially consistent atomic access: everything else.
-
-
-COMPILER MEMORY BARRIER
-=======================
-
-barrier() prevents the compiler from moving the memory accesses either
-side of it to the other side.  The compiler barrier has no direct effect
-on the CPU, which may then reorder things however it wishes.
-
-barrier() is mostly used within qemu/atomic.h itself.  On some
-architectures, CPU guarantees are strong enough that blocking compiler
-optimizations already ensures the correct order of execution.  In this
-case, qemu/atomic.h will reduce stronger memory barriers to simple
-compiler barriers.
-
-Still, barrier() can be useful when writing code that can be interrupted
-by signal handlers.
-
-
-SEQUENTIALLY CONSISTENT ATOMIC ACCESS
-=====================================
-
-Most of the operations in the qemu/atomic.h header ensure *sequential
-consistency*, where "the result of any execution is the same as if the
-operations of all the processors were executed in some sequential order,
-and the operations of each individual processor appear in this sequence
-in the order specified by its program".
-
-qemu/atomic.h provides the following set of atomic read-modify-write
-operations:
-
-    void atomic_inc(ptr)
-    void atomic_dec(ptr)
-    void atomic_add(ptr, val)
-    void atomic_sub(ptr, val)
-    void atomic_and(ptr, val)
-    void atomic_or(ptr, val)
-
-    typeof(*ptr) atomic_fetch_inc(ptr)
-    typeof(*ptr) atomic_fetch_dec(ptr)
-    typeof(*ptr) atomic_fetch_add(ptr, val)
-    typeof(*ptr) atomic_fetch_sub(ptr, val)
-    typeof(*ptr) atomic_fetch_and(ptr, val)
-    typeof(*ptr) atomic_fetch_or(ptr, val)
-    typeof(*ptr) atomic_fetch_xor(ptr, val)
-    typeof(*ptr) atomic_fetch_inc_nonzero(ptr)
-    typeof(*ptr) atomic_xchg(ptr, val)
-    typeof(*ptr) atomic_cmpxchg(ptr, old, new)
-
-all of which return the old value of *ptr.  These operations are
-polymorphic; they operate on any type that is as wide as a pointer.
-
-Similar operations return the new value of *ptr:
-
-    typeof(*ptr) atomic_inc_fetch(ptr)
-    typeof(*ptr) atomic_dec_fetch(ptr)
-    typeof(*ptr) atomic_add_fetch(ptr, val)
-    typeof(*ptr) atomic_sub_fetch(ptr, val)
-    typeof(*ptr) atomic_and_fetch(ptr, val)
-    typeof(*ptr) atomic_or_fetch(ptr, val)
-    typeof(*ptr) atomic_xor_fetch(ptr, val)
-
-Sequentially consistent loads and stores can be done using:
-
-    atomic_fetch_add(ptr, 0) for loads
-    atomic_xchg(ptr, val) for stores
-
-However, they are quite expensive on some platforms, notably POWER and
-Arm.  Therefore, qemu/atomic.h provides two primitives with slightly
-weaker constraints:
-
-    typeof(*ptr) atomic_mb_read(ptr)
-    void         atomic_mb_set(ptr, val)
-
-The semantics of these primitives map to Java volatile variables,
-and are strongly related to memory barriers as used in the Linux
-kernel (see below).
-
-As long as you use atomic_mb_read and atomic_mb_set, accesses cannot
-be reordered with each other, and it is also not possible to reorder
-"normal" accesses around them.
-
-However, and this is the important difference between
-atomic_mb_read/atomic_mb_set and sequential consistency, it is important
-for both threads to access the same volatile variable.  It is not the
-case that everything visible to thread A when it writes volatile field f
-becomes visible to thread B after it reads volatile field g. The store
-and load have to "match" (i.e., be performed on the same volatile
-field) to achieve the right semantics.
-
-
-These operations operate on any type that is as wide as an int or smaller.
-
-
-WEAK ATOMIC ACCESS AND MANUAL MEMORY BARRIERS
-=============================================
-
-Compared to sequentially consistent atomic access, programming with
-weaker consistency models can be considerably more complicated.
-In general, if the algorithm you are writing includes both writes
-and reads on the same side, it is generally simpler to use sequentially
-consistent primitives.
-
-When using this model, variables are accessed with:
-
-- atomic_read() and atomic_set(); these prevent the compiler from
-  optimizing accesses out of existence and creating unsolicited
-  accesses, but do not otherwise impose any ordering on loads and
-  stores: both the compiler and the processor are free to reorder
-  them.
-
-- atomic_load_acquire(), which guarantees the LOAD to appear to
-  happen, with respect to the other components of the system,
-  before all the LOAD or STORE operations specified afterwards.
-  Operations coming before atomic_load_acquire() can still be
-  reordered after it.
-
-- atomic_store_release(), which guarantees the STORE to appear to
-  happen, with respect to the other components of the system,
-  after all the LOAD or STORE operations specified afterwards.
-  Operations coming after atomic_store_release() can still be
-  reordered after it.
-
-Restrictions to the ordering of accesses can also be specified
-using the memory barrier macros: smp_rmb(), smp_wmb(), smp_mb(),
-smp_mb_acquire(), smp_mb_release(), smp_read_barrier_depends().
-
-Memory barriers control the order of references to shared memory.
-They come in six kinds:
-
-- smp_rmb() guarantees that all the LOAD operations specified before
-  the barrier will appear to happen before all the LOAD operations
-  specified after the barrier with respect to the other components of
-  the system.
-
-  In other words, smp_rmb() puts a partial ordering on loads, but is not
-  required to have any effect on stores.
-
-- smp_wmb() guarantees that all the STORE operations specified before
-  the barrier will appear to happen before all the STORE operations
-  specified after the barrier with respect to the other components of
-  the system.
-
-  In other words, smp_wmb() puts a partial ordering on stores, but is not
-  required to have any effect on loads.
-
-- smp_mb_acquire() guarantees that all the LOAD operations specified before
-  the barrier will appear to happen before all the LOAD or STORE operations
-  specified after the barrier with respect to the other components of
-  the system.
-
-- smp_mb_release() guarantees that all the STORE operations specified *after*
-  the barrier will appear to happen after all the LOAD or STORE operations
-  specified *before* the barrier with respect to the other components of
-  the system.
-
-- smp_mb() guarantees that all the LOAD and STORE operations specified
-  before the barrier will appear to happen before all the LOAD and
-  STORE operations specified after the barrier with respect to the other
-  components of the system.
-
-  smp_mb() puts a partial ordering on both loads and stores.  It is
-  stronger than both a read and a write memory barrier; it implies both
-  smp_mb_acquire() and smp_mb_release(), but it also prevents STOREs
-  coming before the barrier from overtaking LOADs coming after the
-  barrier and vice versa.
-
-- smp_read_barrier_depends() is a weaker kind of read barrier.  On
-  most processors, whenever two loads are performed such that the
-  second depends on the result of the first (e.g., the first load
-  retrieves the address to which the second load will be directed),
-  the processor will guarantee that the first LOAD will appear to happen
-  before the second with respect to the other components of the system.
-  However, this is not always true---for example, it was not true on
-  Alpha processors.  Whenever this kind of access happens to shared
-  memory (that is not protected by a lock), a read barrier is needed,
-  and smp_read_barrier_depends() can be used instead of smp_rmb().
-
-  Note that the first load really has to have a _data_ dependency and not
-  a control dependency.  If the address for the second load is dependent
-  on the first load, but the dependency is through a conditional rather
-  than actually loading the address itself, then it's a _control_
-  dependency and a full read barrier or better is required.
-
-
-This is the set of barriers that is required *between* two atomic_read()
-and atomic_set() operations to achieve sequential consistency:
-
-                    |               2nd operation                   |
-                    |-----------------------------------------------|
-     1st operation  | (after last)   | atomic_read | atomic_set     |
-     ---------------+----------------+-------------+----------------|
-     (before first) |                | none        | smp_mb_release |
-     ---------------+----------------+-------------+----------------|
-     atomic_read    | smp_mb_acquire | smp_rmb     | **             |
-     ---------------+----------------+-------------+----------------|
-     atomic_set     | none           | smp_mb()*** | smp_wmb()      |
-     ---------------+----------------+-------------+----------------|
-
-       * Or smp_read_barrier_depends().
-
-      ** This requires a load-store barrier.  This is achieved by
-         either smp_mb_acquire() or smp_mb_release().
-
-     *** This requires a store-load barrier.  On most machines, the only
-         way to achieve this is a full barrier.
-
-
-You can see that the two possible definitions of atomic_mb_read()
-and atomic_mb_set() are the following:
-
-    1) atomic_mb_read(p)   = atomic_read(p); smp_mb_acquire()
-       atomic_mb_set(p, v) = smp_mb_release(); atomic_set(p, v); smp_mb()
-
-    2) atomic_mb_read(p)   = smp_mb() atomic_read(p); smp_mb_acquire()
-       atomic_mb_set(p, v) = smp_mb_release(); atomic_set(p, v);
-
-Usually the former is used, because smp_mb() is expensive and a program
-normally has more reads than writes.  Therefore it makes more sense to
-make atomic_mb_set() the more expensive operation.
-
-There are two common cases in which atomic_mb_read and atomic_mb_set
-generate too many memory barriers, and thus it can be useful to manually
-place barriers, or use atomic_load_acquire/atomic_store_release instead:
-
-- when a data structure has one thread that is always a writer
-  and one thread that is always a reader, manual placement of
-  memory barriers makes the write side faster.  Furthermore,
-  correctness is easy to check for in this case using the "pairing"
-  trick that is explained below:
-
-     thread 1                                thread 1
-     -------------------------               ------------------------
-     (other writes)
-     atomic_mb_set(&a, x)                    atomic_store_release(&a, x)
-     atomic_mb_set(&b, y)                    atomic_store_release(&b, y)
-
-                                       =>
-     thread 2                                thread 2
-     -------------------------               ------------------------
-     y = atomic_mb_read(&b)                  y = atomic_load_acquire(&b)
-     x = atomic_mb_read(&a)                  x = atomic_load_acquire(&a)
-     (other reads)
-
-  Note that the barrier between the stores in thread 1, and between
-  the loads in thread 2, has been optimized here to a write or a
-  read memory barrier respectively.  On some architectures, notably
-  ARMv7, smp_mb_acquire and smp_mb_release are just as expensive as
-  smp_mb, but smp_rmb and/or smp_wmb are more efficient.
-
-- sometimes, a thread is accessing many variables that are otherwise
-  unrelated to each other (for example because, apart from the current
-  thread, exactly one other thread will read or write each of these
-  variables).  In this case, it is possible to "hoist" the implicit
-  barriers provided by atomic_mb_read() and atomic_mb_set() outside
-  a loop.  For example, the above definition atomic_mb_read() gives
-  the following transformation:
-
-     n = 0;                                  n = 0;
-     for (i = 0; i < 10; i++)          =>    for (i = 0; i < 10; i++)
-       n += atomic_mb_read(&a[i]);             n += atomic_read(&a[i]);
-                                             smp_mb_acquire();
-
-  Similarly, atomic_mb_set() can be transformed as follows:
-
-                                             smp_mb_release();
-     for (i = 0; i < 10; i++)          =>    for (i = 0; i < 10; i++)
-       atomic_mb_set(&a[i], false);            atomic_set(&a[i], false);
-                                             smp_mb();
-
-
-  The other thread can still use atomic_mb_read()/atomic_mb_set().
-
-The two tricks can be combined.  In this case, splitting a loop in
-two lets you hoist the barriers out of the loops _and_ eliminate the
-expensive smp_mb():
-
-                                             smp_mb_release();
-     for (i = 0; i < 10; i++) {        =>    for (i = 0; i < 10; i++)
-       atomic_mb_set(&a[i], false);            atomic_set(&a[i], false);
-       atomic_mb_set(&b[i], false);          smb_wmb();
-     }                                       for (i = 0; i < 10; i++)
-                                               atomic_set(&a[i], false);
-                                             smp_mb();
-
-
-Memory barrier pairing
-----------------------
-
-A useful rule of thumb is that memory barriers should always, or almost
-always, be paired with another barrier.  In the case of QEMU, however,
-note that the other barrier may actually be in a driver that runs in
-the guest!
-
-For the purposes of pairing, smp_read_barrier_depends() and smp_rmb()
-both count as read barriers.  A read barrier shall pair with a write
-barrier or a full barrier; a write barrier shall pair with a read
-barrier or a full barrier.  A full barrier can pair with anything.
-For example:
-
-        thread 1             thread 2
-        ===============      ===============
-        a = 1;
-        smp_wmb();
-        b = 2;               x = b;
-                             smp_rmb();
-                             y = a;
-
-Note that the "writing" thread is accessing the variables in the
-opposite order as the "reading" thread.  This is expected: stores
-before the write barrier will normally match the loads after the
-read barrier, and vice versa.  The same is true for more than 2
-access and for data dependency barriers:
-
-        thread 1             thread 2
-        ===============      ===============
-        b[2] = 1;
-        smp_wmb();
-        x->i = 2;
-        smp_wmb();
-        a = x;               x = a;
-                             smp_read_barrier_depends();
-                             y = x->i;
-                             smp_read_barrier_depends();
-                             z = b[y];
-
-smp_wmb() also pairs with atomic_mb_read() and smp_mb_acquire().
-and smp_rmb() also pairs with atomic_mb_set() and smp_mb_release().
-
-
-COMPARISON WITH LINUX KERNEL MEMORY BARRIERS
-============================================
-
-Here is a list of differences between Linux kernel atomic operations
-and memory barriers, and the equivalents in QEMU:
-
-- atomic operations in Linux are always on a 32-bit int type and
-  use a boxed atomic_t type; atomic operations in QEMU are polymorphic
-  and use normal C types.
-
-- Originally, atomic_read and atomic_set in Linux gave no guarantee
-  at all. Linux 4.1 updated them to implement volatile
-  semantics via ACCESS_ONCE (or the more recent READ/WRITE_ONCE).
-
-  QEMU's atomic_read/set implement, if the compiler supports it, C11
-  atomic relaxed semantics, and volatile semantics otherwise.
-  Both semantics prevent the compiler from doing certain transformations;
-  the difference is that atomic accesses are guaranteed to be atomic,
-  while volatile accesses aren't. Thus, in the volatile case we just cross
-  our fingers hoping that the compiler will generate atomic accesses,
-  since we assume the variables passed are machine-word sized and
-  properly aligned.
-  No barriers are implied by atomic_read/set in either Linux or QEMU.
-
-- atomic read-modify-write operations in Linux are of three kinds:
-
-         atomic_OP          returns void
-         atomic_OP_return   returns new value of the variable
-         atomic_fetch_OP    returns the old value of the variable
-         atomic_cmpxchg     returns the old value of the variable
-
-  In QEMU, the second kind does not exist.  Currently Linux has
-  atomic_fetch_or only.  QEMU provides and, or, inc, dec, add, sub.
-
-- different atomic read-modify-write operations in Linux imply
-  a different set of memory barriers; in QEMU, all of them enforce
-  sequential consistency, which means they imply full memory barriers
-  before and after the operation.
-
-- Linux does not have an equivalent of atomic_mb_set().  In particular,
-  note that smp_store_mb() is a little weaker than atomic_mb_set().
-  atomic_mb_read() compiles to the same instructions as Linux's
-  smp_load_acquire(), but this should be treated as an implementation
-  detail.
-
-SOURCES
-=======
-
-* Documentation/memory-barriers.txt from the Linux kernel
-
-* "The JSR-133 Cookbook for Compiler Writers", available at
-  http://g.oswego.edu/dl/jmm/cookbook.html

docs/devel/index.rst

@@ -17,6 +17,7 @@ Contents:
    loads-stores
    memory
    migration
+   atomics
    stable-process
    testing
    decodetree

docs/devel/rcu.txt

@@ -132,7 +132,7 @@ The core RCU API is small:
 
      typeof(*p) atomic_rcu_read(p);
 
-        atomic_rcu_read() is similar to atomic_mb_read(), but it makes
+        atomic_rcu_read() is similar to atomic_load_acquire(), but it makes
         some assumptions on the code that calls it.  This allows a more
         optimized implementation.
 
@@ -154,7 +154,7 @@ The core RCU API is small:
 
      void atomic_rcu_set(p, typeof(*p) v);
 
-        atomic_rcu_set() is also similar to atomic_mb_set(), and it also
+        atomic_rcu_set() is similar to atomic_store_release(), though it also
         makes assumptions on the code that calls it in order to allow a more
         optimized implementation.
 

docs/sphinx/kerneldoc.py

@@ -99,6 +99,7 @@ class KernelDocDirective(Directive):
                 env.note_dependency(os.path.abspath(f))
                 cmd += ['-export-file', f]
 
+        cmd += ['-sphinx-version', sphinx.__version__]
         cmd += [filename]
 
         try:

docs/system/arm/orangepi.rst

@@ -127,6 +127,16 @@ can be downloaded from:
 Alternatively, you can also choose to build you own image with buildroot
 using the orangepi_pc_defconfig. Also see https://buildroot.org for more information.
 
+When using an image as an SD card, it must be resized to a power of two. This can be
+done with the qemu-img command. It is recommended to only increase the image size
+instead of shrinking it to a power of two, to avoid loss of data. For example,
+to prepare a downloaded Armbian image, first extract it and then increase
+its size to one gigabyte as follows:
+
+.. code-block:: bash
+
+  $ qemu-img resize Armbian_19.11.3_Orangepipc_bionic_current_5.3.9.img 1G
+
 You can choose to attach the selected image either as an SD card or as USB mass storage.
 For example, to boot using the Orange Pi PC Debian image on SD card, simply add the -sd
 argument and provide the proper root= kernel parameter:
@@ -213,12 +223,12 @@ Next, unzip the NetBSD image and write the U-Boot binary including SPL using:
   $ dd if=/path/to/u-boot-sunxi-with-spl.bin of=armv7.img bs=1024 seek=8 conv=notrunc
 
 Finally, before starting the machine the SD image must be extended such
-that the NetBSD kernel will not conclude the NetBSD partition is larger than
-the emulated SD card:
+that the size of the SD image is a power of two and that the NetBSD kernel
+will not conclude the NetBSD partition is larger than the emulated SD card:
 
 .. code-block:: bash
 
-  $ dd if=/dev/zero bs=1M count=64 >> armv7.img
+  $ qemu-img resize armv7.img 2G
 
 Start the machine using the following command:
 

docs/system/deprecated.rst

@@ -336,6 +336,14 @@ The ``compat`` property used to set backwards compatibility modes for
 the processor has been deprecated. The ``max-cpu-compat`` property of
 the ``pseries`` machine type should be used instead.
 
+KVM guest support on 32-bit Arm hosts (since 5.0)
+'''''''''''''''''''''''''''''''''''''''''''''''''
+
+The Linux kernel has dropped support for allowing 32-bit Arm systems
+to host KVM guests as of the 5.7 kernel. Accordingly, QEMU is deprecating
+its support for this configuration and will remove it in a future version.
+Running 32-bit guests on a 64-bit Arm host remains supported.
+
 System emulator devices
 -----------------------
 

docs/system/gdb.rst

@@ -3,17 +3,25 @@
 GDB usage
 ---------
 
-QEMU has a primitive support to work with gdb, so that you can do
-'Ctrl-C' while the virtual machine is running and inspect its state.
+QEMU supports working with gdb via gdb's remote-connection facility
+(the "gdbstub"). This allows you to debug guest code in the same
+way that you might with a low-level debug facility like JTAG
+on real hardware. You can stop and start the virtual machine,
+examine state like registers and memory, and set breakpoints and
+watchpoints.
 
-In order to use gdb, launch QEMU with the '-s' option. It will wait for
-a gdb connection:
+In order to use gdb, launch QEMU with the ``-s`` and ``-S`` options.
+The ``-s`` option will make QEMU listen for an incoming connection
+from gdb on TCP port 1234, and ``-S`` will make QEMU not start the
+guest until you tell it to from gdb. (If you want to specify which
+TCP port to use or to use something other than TCP for the gdbstub
+connection, use the ``-gdb dev`` option instead of ``-s``.)
 
 .. parsed-literal::
 
-   |qemu_system| -s -kernel bzImage -hda rootdisk.img -append "root=/dev/hda"
-   Connected to host network interface: tun0
-   Waiting gdb connection on port 1234
+   |qemu_system| -s -S -kernel bzImage -hda rootdisk.img -append "root=/dev/hda"
+
+QEMU will launch but will silently wait for gdb to connect.
 
 Then launch gdb on the 'vmlinux' executable::
 

exec.c

@@ -2074,11 +2074,23 @@ static int memory_try_enable_merging(void *addr, size_t len)
  */
 int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
 {
+    const ram_addr_t unaligned_size = newsize;
+
     assert(block);
 
     newsize = HOST_PAGE_ALIGN(newsize);
 
     if (block->used_length == newsize) {
+        /*
+         * We don't have to resize the ram block (which only knows aligned
+         * sizes), however, we have to notify if the unaligned size changed.
+         */
+        if (unaligned_size != memory_region_size(block->mr)) {
+            memory_region_set_size(block->mr, unaligned_size);
+            if (block->resized) {
+                block->resized(block->idstr, unaligned_size, block->host);
+            }
+        }
         return 0;
     }
 
@@ -2102,9 +2114,9 @@ int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
     block->used_length = newsize;
     cpu_physical_memory_set_dirty_range(block->offset, block->used_length,
                                         DIRTY_CLIENTS_ALL);
-    memory_region_set_size(block->mr, newsize);
+    memory_region_set_size(block->mr, unaligned_size);
     if (block->resized) {
-        block->resized(block->idstr, newsize, block->host);
+        block->resized(block->idstr, unaligned_size, block->host);
     }
     return 0;
 }

fsdev/qemu-fsdev.c

@@ -78,6 +78,7 @@ static FsDriverTable FsDrivers[] = {
             "throttling.iops-read-max-length",
             "throttling.iops-write-max-length",
             "throttling.iops-size",
+            NULL
         },
     },
     {
@@ -85,6 +86,7 @@ static FsDriverTable FsDrivers[] = {
         .ops = &synth_ops,
         .opts = (const char * []) {
             COMMON_FS_DRIVER_OPTIONS,
+            NULL
         },
     },
     {
@@ -95,6 +97,7 @@ static FsDriverTable FsDrivers[] = {
             "socket",
             "sock_fd",
             "writeout",
+            NULL
         },
     },
 };

hw/9pfs/9p-util.h

@@ -37,9 +37,22 @@ static inline int openat_file(int dirfd, const char *name, int flags,
 {
     int fd, serrno, ret;
 
+again:
     fd = openat(dirfd, name, flags | O_NOFOLLOW | O_NOCTTY | O_NONBLOCK,
                 mode);
     if (fd == -1) {
+        if (errno == EPERM && (flags & O_NOATIME)) {
+            /*
+             * The client passed O_NOATIME but we lack permissions to honor it.
+             * Rather than failing the open, fall back without O_NOATIME. This
+             * doesn't break the semantics on the client side, as the Linux
+             * open(2) man page notes that O_NOATIME "may not be effective on
+             * all filesystems". In particular, NFS and other network
+             * filesystems ignore it entirely.
+             */
+            flags &= ~O_NOATIME;
+            goto again;
+        }
         return -1;
     }
 

hw/9pfs/9p.c

@@ -28,6 +28,7 @@
 #include "sysemu/qtest.h"
 #include "qemu/xxhash.h"
 #include <math.h>
+#include <linux/limits.h>
 
 int open_fd_hw;
 int total_open_fd;
@@ -2102,29 +2103,22 @@ out_nofid:
  * with qemu_iovec_destroy().
  */
 static void v9fs_init_qiov_from_pdu(QEMUIOVector *qiov, V9fsPDU *pdu,
-                                    size_t skip, size_t *size,
+                                    size_t skip, size_t size,
                                     bool is_write)
 {
     QEMUIOVector elem;
     struct iovec *iov;
     unsigned int niov;
-    size_t alloc_size = *size + skip;
 
     if (is_write) {
-        pdu->s->transport->init_out_iov_from_pdu(pdu, &iov, &niov, alloc_size);
+        pdu->s->transport->init_out_iov_from_pdu(pdu, &iov, &niov, size + skip);
     } else {
-        pdu->s->transport->init_in_iov_from_pdu(pdu, &iov, &niov, &alloc_size);
-    }
-
-    if (alloc_size < skip) {
-        *size = 0;
-    } else {
-        *size = alloc_size - skip;
+        pdu->s->transport->init_in_iov_from_pdu(pdu, &iov, &niov, size + skip);
     }
 
     qemu_iovec_init_external(&elem, iov, niov);
     qemu_iovec_init(qiov, niov);
-    qemu_iovec_concat(qiov, &elem, skip, *size);
+    qemu_iovec_concat(qiov, &elem, skip, size);
 }
 
 static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp,
@@ -2132,14 +2126,15 @@ static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp,
 {
     ssize_t err;
     size_t offset = 7;
-    size_t read_count;
+    uint64_t read_count;
     QEMUIOVector qiov_full;
 
     if (fidp->fs.xattr.len < off) {
         read_count = 0;
-    } else if (fidp->fs.xattr.len - off < max_count) {
-        read_count = fidp->fs.xattr.len - off;
     } else {
+        read_count = fidp->fs.xattr.len - off;
+    }
+    if (read_count > max_count) {
         read_count = max_count;
     }
     err = pdu_marshal(pdu, offset, "d", read_count);
@@ -2148,7 +2143,7 @@ static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp,
     }
     offset += err;
 
-    v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, &read_count, false);
+    v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, read_count, false);
     err = v9fs_pack(qiov_full.iov, qiov_full.niov, 0,
                     ((char *)fidp->fs.xattr.value) + off,
                     read_count);
@@ -2277,11 +2272,9 @@ static void coroutine_fn v9fs_read(void *opaque)
         QEMUIOVector qiov_full;
         QEMUIOVector qiov;
         int32_t len;
-        size_t size = max_count;
 
-        v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset + 4, &size, false);
+        v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset + 4, max_count, false);
         qemu_iovec_init(&qiov, qiov_full.niov);
-        max_count = size;
         do {
             qemu_iovec_reset(&qiov);
             qemu_iovec_concat(&qiov, &qiov_full, count, qiov_full.size - count);
@@ -2532,7 +2525,6 @@ static void coroutine_fn v9fs_write(void *opaque)
     int32_t len = 0;
     int32_t total = 0;
     size_t offset = 7;
-    size_t size;
     V9fsFidState *fidp;
     V9fsPDU *pdu = opaque;
     V9fsState *s = pdu->s;
@@ -2545,9 +2537,7 @@ static void coroutine_fn v9fs_write(void *opaque)
         return;
     }
     offset += err;
-    size = count;
-    v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, &size, true);
-    count = size;
+    v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, count, true);
     trace_v9fs_write(pdu->tag, pdu->id, fid, off, count, qiov_full.niov);
 
     fidp = get_fid(pdu, fid);

hw/9pfs/9p.h

@@ -197,22 +197,22 @@ typedef struct V9fsXattr
 
 typedef struct V9fsDir {
     DIR *stream;
-    QemuMutex readdir_mutex;
+    CoMutex readdir_mutex;
 } V9fsDir;
 
 static inline void v9fs_readdir_lock(V9fsDir *dir)
 {
-    qemu_mutex_lock(&dir->readdir_mutex);
+    qemu_co_mutex_lock(&dir->readdir_mutex);
 }
 
 static inline void v9fs_readdir_unlock(V9fsDir *dir)
 {
-    qemu_mutex_unlock(&dir->readdir_mutex);
+    qemu_co_mutex_unlock(&dir->readdir_mutex);
 }
 
 static inline void v9fs_readdir_init(V9fsDir *dir)
 {
-    qemu_mutex_init(&dir->readdir_mutex);
+    qemu_co_mutex_init(&dir->readdir_mutex);
 }
 
 /*
@@ -436,7 +436,7 @@ struct V9fsTransport {
     ssize_t     (*pdu_vunmarshal)(V9fsPDU *pdu, size_t offset, const char *fmt,
                                   va_list ap);
     void        (*init_in_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov,
-                                        unsigned int *pniov, size_t *size);
+                                        unsigned int *pniov, size_t size);
     void        (*init_out_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov,
                                          unsigned int *pniov, size_t size);
     void        (*push_and_notify)(V9fsPDU *pdu);

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

@@ -147,22 +147,19 @@ static ssize_t virtio_pdu_vunmarshal(V9fsPDU *pdu, size_t offset,
 }
 
 static void virtio_init_in_iov_from_pdu(V9fsPDU *pdu, struct iovec **piov,
-                                        unsigned int *pniov, size_t *size)
+                                        unsigned int *pniov, size_t size)
 {
     V9fsState *s = pdu->s;
     V9fsVirtioState *v = container_of(s, V9fsVirtioState, state);
     VirtQueueElement *elem = v->elems[pdu->idx];
     size_t buf_size = iov_size(elem->in_sg, elem->in_num);
 
-    if (buf_size < P9_IOHDRSZ) {
+    if (buf_size < size) {
         VirtIODevice *vdev = VIRTIO_DEVICE(v);
 
         virtio_error(vdev,
-                     "VirtFS reply type %d needs %zu bytes, buffer has %zu, less than minimum",
-                     pdu->id + 1, *size, buf_size);
-    }
-    if (buf_size < *size) {
-        *size = buf_size;
+                     "VirtFS reply type %d needs %zu bytes, buffer has %zu",
+                     pdu->id + 1, size, buf_size);
     }
 
     *piov = elem->in_sg;

hw/9pfs/xen-9p-backend.c

@@ -37,6 +37,7 @@ typedef struct Xen9pfsRing {
 
     struct iovec *sg;
     QEMUBH *bh;
+    Coroutine *co;
 
     /* local copies, so that we can read/write PDU data directly from
      * the ring */
@@ -137,7 +138,8 @@ static ssize_t xen_9pfs_pdu_vmarshal(V9fsPDU *pdu,
     ret = v9fs_iov_vmarshal(in_sg, num, offset, 0, fmt, ap);
     if (ret < 0) {
         xen_pv_printf(&xen_9pfs->xendev, 0,
-                      "Failed to encode VirtFS request type %d\n", pdu->id + 1);
+                      "Failed to encode VirtFS reply type %d\n",
+                      pdu->id + 1);
         xen_be_set_state(&xen_9pfs->xendev, XenbusStateClosing);
         xen_9pfs_disconnect(&xen_9pfs->xendev);
     }
@@ -187,7 +189,7 @@ static void xen_9pfs_init_out_iov_from_pdu(V9fsPDU *pdu,
 static void xen_9pfs_init_in_iov_from_pdu(V9fsPDU *pdu,
                                           struct iovec **piov,
                                           unsigned int *pniov,
-                                          size_t *size)
+                                          size_t size)
 {
     Xen9pfsDev *xen_9pfs = container_of(pdu->s, Xen9pfsDev, state);
     Xen9pfsRing *ring = &xen_9pfs->rings[pdu->tag % xen_9pfs->num_rings];
@@ -197,19 +199,20 @@ static void xen_9pfs_init_in_iov_from_pdu(V9fsPDU *pdu,
     g_free(ring->sg);
 
     ring->sg = g_new0(struct iovec, 2);
-    xen_9pfs_in_sg(ring, ring->sg, &num, pdu->idx, *size);
+    ring->co = qemu_coroutine_self();
+    /* make sure other threads see ring->co changes before continuing */
+    smp_wmb();
 
+again:
+    xen_9pfs_in_sg(ring, ring->sg, &num, pdu->idx, size);
     buf_size = iov_size(ring->sg, num);
-    if (buf_size  < P9_IOHDRSZ) {
-        xen_pv_printf(&xen_9pfs->xendev, 0, "Xen 9pfs request type %d"
-                "needs %zu bytes, buffer has %zu, less than minimum\n",
-                pdu->id, *size, buf_size);
-        xen_be_set_state(&xen_9pfs->xendev, XenbusStateClosing);
-        xen_9pfs_disconnect(&xen_9pfs->xendev);
-    }
-    if (buf_size  < *size) {
-        *size = buf_size;
+    if (buf_size  < size) {
+        qemu_coroutine_yield();
+        goto again;
     }
+    ring->co = NULL;
+    /* make sure other threads see ring->co changes before continuing */
+    smp_wmb();
 
     *piov = ring->sg;
     *pniov = num;
@@ -294,6 +297,20 @@ static int xen_9pfs_receive(Xen9pfsRing *ring)
 static void xen_9pfs_bh(void *opaque)
 {
     Xen9pfsRing *ring = opaque;
+    bool wait;
+
+again:
+    wait = ring->co != NULL && qemu_coroutine_entered(ring->co);
+    /* paired with the smb_wmb barriers in xen_9pfs_init_in_iov_from_pdu */
+    smp_rmb();
+    if (wait) {
+        cpu_relax();
+        goto again;
+    }
+
+    if (ring->co != NULL) {
+        qemu_coroutine_enter_if_inactive(ring->co);
+    }
     xen_9pfs_receive(ring);
 }
 

hw/acpi/core.c

@@ -461,7 +461,8 @@ static void acpi_pm_evt_write(void *opaque, hwaddr addr, uint64_t val,
 static const MemoryRegionOps acpi_pm_evt_ops = {
     .read = acpi_pm_evt_read,
     .write = acpi_pm_evt_write,
-    .valid.min_access_size = 2,
+    .impl.min_access_size = 2,
+    .valid.min_access_size = 1,
     .valid.max_access_size = 2,
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
@@ -530,7 +531,8 @@ static void acpi_pm_tmr_write(void *opaque, hwaddr addr, uint64_t val,
 static const MemoryRegionOps acpi_pm_tmr_ops = {
     .read = acpi_pm_tmr_read,
     .write = acpi_pm_tmr_write,
-    .valid.min_access_size = 4,
+    .impl.min_access_size = 4,
+    .valid.min_access_size = 1,
     .valid.max_access_size = 4,
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
@@ -602,7 +604,8 @@ static void acpi_pm_cnt_write(void *opaque, hwaddr addr, uint64_t val,
 static const MemoryRegionOps acpi_pm_cnt_ops = {
     .read = acpi_pm_cnt_read,
     .write = acpi_pm_cnt_write,
-    .valid.min_access_size = 2,
+    .impl.min_access_size = 2,
+    .valid.min_access_size = 1,
     .valid.max_access_size = 2,
     .endianness = DEVICE_LITTLE_ENDIAN,
 };

hw/arm/sbsa-ref.c

@@ -555,7 +555,7 @@ static void create_pcie(SBSAMachineState *sms)
 
     for (i = 0; i < GPEX_NUM_IRQS; i++) {
         sysbus_connect_irq(SYS_BUS_DEVICE(dev), i,
-                           qdev_get_gpio_in(sms->gic, irq + 1));
+                           qdev_get_gpio_in(sms->gic, irq + i));
         gpex_set_irq_num(GPEX_HOST(dev), i, irq + i);
     }
 

hw/arm/virt-acpi-build.c

@@ -929,7 +929,7 @@ void virt_acpi_setup(VirtMachineState *vms)
 
     build_state->linker_mr =
         acpi_add_rom_blob(virt_acpi_build_update, build_state,
-                          tables.linker->cmd_blob, "etc/table-loader", 0);
+                          tables.linker->cmd_blob, ACPI_BUILD_LOADER_FILE, 0);
 
     fw_cfg_add_file(vms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data,
                     acpi_data_len(tables.tcpalog));

hw/audio/es1370.c

@@ -643,6 +643,9 @@ static void es1370_transfer_audio (ES1370State *s, struct chan *d, int loop_sel,
     int csc_bytes = (csc + 1) << d->shift;
     int cnt = d->frame_cnt >> 16;
     int size = d->frame_cnt & 0xffff;
+    if (size < cnt) {
+        return;
+    }
     int left = ((size - cnt + 1) << 2) + d->leftover;
     int transferred = 0;
     int temp = MIN (max, MIN (left, csc_bytes));
@@ -651,7 +654,7 @@ static void es1370_transfer_audio (ES1370State *s, struct chan *d, int loop_sel,
     addr += (cnt << 2) + d->leftover;
 
     if (index == ADC_CHANNEL) {
-        while (temp) {
+        while (temp > 0) {
             int acquired, to_copy;
 
             to_copy = MIN ((size_t) temp, sizeof (tmpbuf));
@@ -669,7 +672,7 @@ static void es1370_transfer_audio (ES1370State *s, struct chan *d, int loop_sel,
     else {
         SWVoiceOut *voice = s->dac_voice[index];
 
-        while (temp) {
+        while (temp > 0) {
             int copied, to_copy;
 
             to_copy = MIN ((size_t) temp, sizeof (tmpbuf));

hw/audio/gusemu_hal.c

@@ -32,7 +32,7 @@
 
 #define GUSregb(position) (*            (gusptr+(position)))
 #define GUSregw(position) (*(uint16_t *) (gusptr+(position)))
-#define GUSregd(position) (*(uint16_t *)(gusptr+(position)))
+#define GUSregd(position) (*(uint32_t *)(gusptr + (position)))
 
 /* size given in bytes */
 unsigned int gus_read(GUSEmuState * state, int port, int size)

hw/audio/gusemu_mixer.c

@@ -28,7 +28,7 @@
 
 #define GUSregb(position)  (*            (gusptr+(position)))
 #define GUSregw(position)  (*(uint16_t *) (gusptr+(position)))
-#define GUSregd(position)  (*(uint16_t *)(gusptr+(position)))
+#define GUSregd(position)  (*(uint32_t *)(gusptr + (position)))
 
 #define GUSvoice(position) (*(uint16_t *)(voiceptr+(position)))
 

hw/core/machine.c

@@ -39,6 +39,7 @@ GlobalProperty hw_compat_4_2[] = {
     { "usb-redir", "suppress-remote-wake", "off" },
     { "qxl", "revision", "4" },
     { "qxl-vga", "revision", "4" },
+    { "fw_cfg", "acpi-mr-restore", "false" },
 };
 const size_t hw_compat_4_2_len = G_N_ELEMENTS(hw_compat_4_2);
 

hw/display/artist.c

@@ -1199,20 +1199,16 @@ static const MemoryRegionOps artist_reg_ops = {
     .read = artist_reg_read,
     .write = artist_reg_write,
     .endianness = DEVICE_NATIVE_ENDIAN,
-    .valid = {
-        .min_access_size = 1,
-        .max_access_size = 4,
-    },
+    .impl.min_access_size = 1,
+    .impl.max_access_size = 4,
 };
 
 static const MemoryRegionOps artist_vram_ops = {
     .read = artist_vram_read,
     .write = artist_vram_write,
     .endianness = DEVICE_NATIVE_ENDIAN,
-    .valid = {
-        .min_access_size = 1,
-        .max_access_size = 4,
-    },
+    .impl.min_access_size = 1,
+    .impl.max_access_size = 4,
 };
 
 static void artist_draw_cursor(ARTISTState *s)

hw/display/ati.c

@@ -285,8 +285,11 @@ static uint64_t ati_mm_read(void *opaque, hwaddr addr, unsigned int size)
             if (idx <= s->vga.vram_size - size) {
                 val = ldn_le_p(s->vga.vram_ptr + idx, size);
             }
-        } else {
+        } else if (s->regs.mm_index > MM_DATA + 3) {
             val = ati_mm_read(s, s->regs.mm_index + addr - MM_DATA, size);
+        } else {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                "ati_mm_read: mm_index too small: %u\n", s->regs.mm_index);
         }
         break;
     case BIOS_0_SCRATCH ... BUS_CNTL - 1:
@@ -520,8 +523,11 @@ static void ati_mm_write(void *opaque, hwaddr addr,
             if (idx <= s->vga.vram_size - size) {
                 stn_le_p(s->vga.vram_ptr + idx, size, data);
             }
-        } else {
+        } else if (s->regs.mm_index > MM_DATA + 3) {
             ati_mm_write(s, s->regs.mm_index + addr - MM_DATA, data, size);
+        } else {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                "ati_mm_write: mm_index too small: %u\n", s->regs.mm_index);
         }
         break;
     case BIOS_0_SCRATCH ... BUS_CNTL - 1:

hw/i386/acpi-build.c

@@ -3043,7 +3043,7 @@ void acpi_setup(void)
 
     build_state->linker_mr =
         acpi_add_rom_blob(acpi_build_update, build_state,
-                          tables.linker->cmd_blob, "etc/table-loader", 0);
+                          tables.linker->cmd_blob, ACPI_BUILD_LOADER_FILE, 0);
 
     fw_cfg_add_file(x86ms->fw_cfg, ACPI_BUILD_TPMLOG_FILE,
                     tables.tcpalog->data, acpi_data_len(tables.tcpalog));

hw/i386/intel_iommu.c

@@ -2549,6 +2549,11 @@ static bool vtd_process_inv_desc(IntelIOMMUState *s)
 /* Try to fetch and process more Invalidation Descriptors */
 static void vtd_fetch_inv_desc(IntelIOMMUState *s)
 {
+    int qi_shift;
+
+    /* Refer to 10.4.23 of VT-d spec 3.0 */
+    qi_shift = s->iq_dw ? VTD_IQH_QH_SHIFT_5 : VTD_IQH_QH_SHIFT_4;
+
     trace_vtd_inv_qi_fetch();
 
     if (s->iq_tail >= s->iq_size) {
@@ -2567,7 +2572,7 @@ static void vtd_fetch_inv_desc(IntelIOMMUState *s)
         }
         /* Must update the IQH_REG in time */
         vtd_set_quad_raw(s, DMAR_IQH_REG,
-                         (((uint64_t)(s->iq_head)) << VTD_IQH_QH_SHIFT) &
+                         (((uint64_t)(s->iq_head)) << qi_shift) &
                          VTD_IQH_QH_MASK);
     }
 }

hw/i386/intel_iommu_internal.h

@@ -230,7 +230,8 @@
 #define VTD_IQA_DW_MASK             0x800
 
 /* IQH_REG */
-#define VTD_IQH_QH_SHIFT            4
+#define VTD_IQH_QH_SHIFT_4          4
+#define VTD_IQH_QH_SHIFT_5          5
 #define VTD_IQH_QH_MASK             0x7fff0ULL
 
 /* ICS_REG */

hw/i386/pc_piix.c

@@ -948,13 +948,26 @@ DEFINE_PC_MACHINE(isapc, "isapc", pc_init_isa,
 
 
 #ifdef CONFIG_XEN
-static void xenfv_machine_options(MachineClass *m)
+static void xenfv_4_2_machine_options(MachineClass *m)
 {
+    pc_i440fx_4_2_machine_options(m);
     m->desc = "Xen Fully-virtualized PC";
     m->max_cpus = HVM_MAX_VCPUS;
     m->default_machine_opts = "accel=xen";
 }
 
-DEFINE_PC_MACHINE(xenfv, "xenfv", pc_xen_hvm_init,
-                  xenfv_machine_options);
+DEFINE_PC_MACHINE(xenfv_4_2, "xenfv-4.2", pc_xen_hvm_init,
+                  xenfv_4_2_machine_options);
+
+static void xenfv_3_1_machine_options(MachineClass *m)
+{
+    pc_i440fx_3_1_machine_options(m);
+    m->desc = "Xen Fully-virtualized PC";
+    m->alias = "xenfv";
+    m->max_cpus = HVM_MAX_VCPUS;
+    m->default_machine_opts = "accel=xen";
+}
+
+DEFINE_PC_MACHINE(xenfv, "xenfv-3.1", pc_xen_hvm_init,
+                  xenfv_3_1_machine_options);
 #endif

hw/net/e1000e_core.c

@@ -34,9 +34,9 @@
 */
 
 #include "qemu/osdep.h"
+#include "qemu/log.h"
 #include "net/net.h"
 #include "net/tap.h"
-#include "hw/hw.h"
 #include "hw/pci/msi.h"
 #include "hw/pci/msix.h"
 #include "sysemu/runstate.h"
@@ -2816,11 +2816,15 @@ e1000e_set_psrctl(E1000ECore *core, int index, uint32_t val)
     if (core->mac[RCTL] & E1000_RCTL_DTYP_MASK) {
 
         if ((val & E1000_PSRCTL_BSIZE0_MASK) == 0) {
-            hw_error("e1000e: PSRCTL.BSIZE0 cannot be zero");
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "e1000e: PSRCTL.BSIZE0 cannot be zero");
+            return;
         }
 
         if ((val & E1000_PSRCTL_BSIZE1_MASK) == 0) {
-            hw_error("e1000e: PSRCTL.BSIZE1 cannot be zero");
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "e1000e: PSRCTL.BSIZE1 cannot be zero");
+            return;
         }
     }
 

hw/net/tulip.c

@@ -171,9 +171,6 @@ static void tulip_copy_rx_bytes(TULIPState *s, struct tulip_descriptor *desc)
             len = s->rx_frame_len;
         }
 
-        if (s->rx_frame_len + len > sizeof(s->rx_frame)) {
-            return;
-        }
         pci_dma_write(&s->dev, desc->buf_addr1, s->rx_frame +
             (s->rx_frame_size - s->rx_frame_len), len);
         s->rx_frame_len -= len;
@@ -186,9 +183,6 @@ static void tulip_copy_rx_bytes(TULIPState *s, struct tulip_descriptor *desc)
             len = s->rx_frame_len;
         }
 
-        if (s->rx_frame_len + len > sizeof(s->rx_frame)) {
-            return;
-        }
         pci_dma_write(&s->dev, desc->buf_addr2, s->rx_frame +
             (s->rx_frame_size - s->rx_frame_len), len);
         s->rx_frame_len -= len;

hw/net/virtio-net.c

@@ -77,25 +77,6 @@
    tso/gso/gro 'off'. */
 #define VIRTIO_NET_RSC_DEFAULT_INTERVAL 300000
 
-/* temporary until standard header include it */
-#if !defined(VIRTIO_NET_HDR_F_RSC_INFO)
-
-#define VIRTIO_NET_HDR_F_RSC_INFO  4 /* rsc_ext data in csum_ fields */
-#define VIRTIO_NET_F_RSC_EXT       61
-
-static inline __virtio16 *virtio_net_rsc_ext_num_packets(
-    struct virtio_net_hdr *hdr)
-{
-    return &hdr->csum_start;
-}
-
-static inline __virtio16 *virtio_net_rsc_ext_num_dupacks(
-    struct virtio_net_hdr *hdr)
-{
-    return &hdr->csum_offset;
-}
-
-#endif
 
 static VirtIOFeature feature_sizes[] = {
     {.flags = 1ULL << VIRTIO_NET_F_MAC,
@@ -1539,15 +1520,15 @@ static size_t virtio_net_rsc_drain_seg(VirtioNetRscChain *chain,
                                        VirtioNetRscSeg *seg)
 {
     int ret;
-    struct virtio_net_hdr *h;
+    struct virtio_net_hdr_v1 *h;
 
-    h = (struct virtio_net_hdr *)seg->buf;
+    h = (struct virtio_net_hdr_v1 *)seg->buf;
     h->flags = 0;
     h->gso_type = VIRTIO_NET_HDR_GSO_NONE;
 
     if (seg->is_coalesced) {
-        *virtio_net_rsc_ext_num_packets(h) = seg->packets;
-        *virtio_net_rsc_ext_num_dupacks(h) = seg->dup_ack;
+        h->rsc.segments = seg->packets;
+        h->rsc.dup_acks = seg->dup_ack;
         h->flags = VIRTIO_NET_HDR_F_RSC_INFO;
         if (chain->proto == ETH_P_IP) {
             h->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
@@ -2828,7 +2809,7 @@ static bool failover_replug_primary(VirtIONet *n, Error **errp)
         if (err) {
             goto out;
         }
-        hotplug_handler_plug(hotplug_ctrl, n->primary_dev, errp);
+        hotplug_handler_plug(hotplug_ctrl, n->primary_dev, &err);
     }
 
 out:

hw/nvram/chrp_nvram.c

@@ -21,14 +21,21 @@
 
 #include "qemu/osdep.h"
 #include "qemu/cutils.h"
+#include "qemu/error-report.h"
 #include "hw/nvram/chrp_nvram.h"
 #include "sysemu/sysemu.h"
 
-static int chrp_nvram_set_var(uint8_t *nvram, int addr, const char *str)
+static int chrp_nvram_set_var(uint8_t *nvram, int addr, const char *str,
+                              int max_len)
 {
     int len;
 
     len = strlen(str) + 1;
+
+    if (max_len < len) {
+        return -1;
+    }
+
     memcpy(&nvram[addr], str, len);
 
     return addr + len;
@@ -38,19 +45,26 @@ static int chrp_nvram_set_var(uint8_t *nvram, int addr, const char *str)
  * Create a "system partition", used for the Open Firmware
  * environment variables.
  */
-int chrp_nvram_create_system_partition(uint8_t *data, int min_len)
+int chrp_nvram_create_system_partition(uint8_t *data, int min_len, int max_len)
 {
     ChrpNvramPartHdr *part_header;
     unsigned int i;
     int end;
 
+    if (max_len < sizeof(*part_header)) {
+        goto fail;
+    }
+
     part_header = (ChrpNvramPartHdr *)data;
     part_header->signature = CHRP_NVPART_SYSTEM;
     pstrcpy(part_header->name, sizeof(part_header->name), "system");
 
     end = sizeof(ChrpNvramPartHdr);
     for (i = 0; i < nb_prom_envs; i++) {
-        end = chrp_nvram_set_var(data, end, prom_envs[i]);
+        end = chrp_nvram_set_var(data, end, prom_envs[i], max_len - end);
+        if (end == -1) {
+            goto fail;
+        }
     }
 
     /* End marker */
@@ -65,6 +79,10 @@ int chrp_nvram_create_system_partition(uint8_t *data, int min_len)
     chrp_nvram_finish_partition(part_header, end);
 
     return end;
+
+fail:
+    error_report("NVRAM is too small. Try to pass less data to -prom-env");
+    exit(EXIT_FAILURE);
 }
 
 /**

hw/nvram/fw_cfg.c

@@ -39,6 +39,7 @@
 #include "qemu/config-file.h"
 #include "qemu/cutils.h"
 #include "qapi/error.h"
+#include "hw/acpi/aml-build.h"
 
 #define FW_CFG_FILE_SLOTS_DFLT 0x20
 
@@ -610,6 +611,55 @@ bool fw_cfg_dma_enabled(void *opaque)
     return s->dma_enabled;
 }
 
+static bool fw_cfg_acpi_mr_restore(void *opaque)
+{
+    FWCfgState *s = opaque;
+    bool mr_aligned;
+
+    mr_aligned = QEMU_IS_ALIGNED(s->table_mr_size, qemu_real_host_page_size) &&
+                 QEMU_IS_ALIGNED(s->linker_mr_size, qemu_real_host_page_size) &&
+                 QEMU_IS_ALIGNED(s->rsdp_mr_size, qemu_real_host_page_size);
+    return s->acpi_mr_restore && !mr_aligned;
+}
+
+static void fw_cfg_update_mr(FWCfgState *s, uint16_t key, size_t size)
+{
+    MemoryRegion *mr;
+    ram_addr_t offset;
+    int arch = !!(key & FW_CFG_ARCH_LOCAL);
+    void *ptr;
+
+    key &= FW_CFG_ENTRY_MASK;
+    assert(key < fw_cfg_max_entry(s));
+
+    ptr = s->entries[arch][key].data;
+    mr = memory_region_from_host(ptr, &offset);
+
+    memory_region_ram_resize(mr, size, &error_abort);
+}
+
+static int fw_cfg_acpi_mr_restore_post_load(void *opaque, int version_id)
+{
+    FWCfgState *s = opaque;
+    int i, index;
+
+    assert(s->files);
+
+    index = be32_to_cpu(s->files->count);
+
+    for (i = 0; i < index; i++) {
+        if (!strcmp(s->files->f[i].name, ACPI_BUILD_TABLE_FILE)) {
+            fw_cfg_update_mr(s, FW_CFG_FILE_FIRST + i, s->table_mr_size);
+        } else if (!strcmp(s->files->f[i].name, ACPI_BUILD_LOADER_FILE)) {
+            fw_cfg_update_mr(s, FW_CFG_FILE_FIRST + i, s->linker_mr_size);
+        } else if (!strcmp(s->files->f[i].name, ACPI_BUILD_RSDP_FILE)) {
+            fw_cfg_update_mr(s, FW_CFG_FILE_FIRST + i, s->rsdp_mr_size);
+        }
+    }
+
+    return 0;
+}
+
 static const VMStateDescription vmstate_fw_cfg_dma = {
     .name = "fw_cfg/dma",
     .needed = fw_cfg_dma_enabled,
@@ -619,6 +669,20 @@ static const VMStateDescription vmstate_fw_cfg_dma = {
     },
 };
 
+static const VMStateDescription vmstate_fw_cfg_acpi_mr = {
+    .name = "fw_cfg/acpi_mr",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = fw_cfg_acpi_mr_restore,
+    .post_load = fw_cfg_acpi_mr_restore_post_load,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(table_mr_size, FWCfgState),
+        VMSTATE_UINT64(linker_mr_size, FWCfgState),
+        VMSTATE_UINT64(rsdp_mr_size, FWCfgState),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 static const VMStateDescription vmstate_fw_cfg = {
     .name = "fw_cfg",
     .version_id = 2,
@@ -631,6 +695,7 @@ static const VMStateDescription vmstate_fw_cfg = {
     },
     .subsections = (const VMStateDescription*[]) {
         &vmstate_fw_cfg_dma,
+        &vmstate_fw_cfg_acpi_mr,
         NULL,
     }
 };
@@ -815,6 +880,23 @@ static struct {
 #define FW_CFG_ORDER_OVERRIDE_LAST 200
 };
 
+/*
+ * Any sub-page size update to these table MRs will be lost during migration,
+ * as we use aligned size in ram_load_precopy() -> qemu_ram_resize() path.
+ * In order to avoid the inconsistency in sizes save them seperately and
+ * migrate over in vmstate post_load().
+ */
+static void fw_cfg_acpi_mr_save(FWCfgState *s, const char *filename, size_t len)
+{
+    if (!strcmp(filename, ACPI_BUILD_TABLE_FILE)) {
+        s->table_mr_size = len;
+    } else if (!strcmp(filename, ACPI_BUILD_LOADER_FILE)) {
+        s->linker_mr_size = len;
+    } else if (!strcmp(filename, ACPI_BUILD_RSDP_FILE)) {
+        s->rsdp_mr_size = len;
+    }
+}
+
 static int get_fw_cfg_order(FWCfgState *s, const char *name)
 {
     int i;
@@ -914,6 +996,7 @@ void fw_cfg_add_file_callback(FWCfgState *s,  const char *filename,
     trace_fw_cfg_add_file(s, index, s->files->f[index].name, len);
 
     s->files->count = cpu_to_be32(count+1);
+    fw_cfg_acpi_mr_save(s, filename, len);
 }
 
 void fw_cfg_add_file(FWCfgState *s,  const char *filename,
@@ -937,6 +1020,7 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename,
             ptr = fw_cfg_modify_bytes_read(s, FW_CFG_FILE_FIRST + i,
                                            data, len);
             s->files->f[i].size   = cpu_to_be32(len);
+            fw_cfg_acpi_mr_save(s, filename, len);
             return ptr;
         }
     }
@@ -973,7 +1057,10 @@ static void fw_cfg_machine_ready(struct Notifier *n, void *data)
     qemu_register_reset(fw_cfg_machine_reset, s);
 }
 
-
+static Property fw_cfg_properties[] = {
+    DEFINE_PROP_BOOL("acpi-mr-restore", FWCfgState, acpi_mr_restore, true),
+    DEFINE_PROP_END_OF_LIST(),
+};
 
 static void fw_cfg_common_realize(DeviceState *dev, Error **errp)
 {
@@ -1097,6 +1184,8 @@ static void fw_cfg_class_init(ObjectClass *klass, void *data)
 
     dc->reset = fw_cfg_reset;
     dc->vmsd = &vmstate_fw_cfg;
+
+    device_class_set_props(dc, fw_cfg_properties);
 }
 
 static const TypeInfo fw_cfg_info = {

hw/nvram/mac_nvram.c

@@ -152,7 +152,7 @@ static void pmac_format_nvram_partition_of(MacIONVRAMState *nvr, int off,
 
     /* OpenBIOS nvram variables partition */
     sysp_end = chrp_nvram_create_system_partition(&nvr->data[off],
-                                                  DEF_SYSTEM_SIZE) + off;
+                                                  DEF_SYSTEM_SIZE, len) + off;
 
     /* Free space partition */
     chrp_nvram_create_free_partition(&nvr->data[sysp_end], len - sysp_end);

hw/nvram/spapr_nvram.c

@@ -188,7 +188,8 @@ static void spapr_nvram_realize(SpaprVioDevice *dev, Error **errp)
         }
     } else if (nb_prom_envs > 0) {
         /* Create a system partition to pass the -prom-env variables */
-        chrp_nvram_create_system_partition(nvram->buf, MIN_NVRAM_SIZE / 4);
+        chrp_nvram_create_system_partition(nvram->buf, MIN_NVRAM_SIZE / 4,
+                                           nvram->size);
         chrp_nvram_create_free_partition(&nvram->buf[MIN_NVRAM_SIZE / 4],
                                          nvram->size - MIN_NVRAM_SIZE / 4);
     }

hw/riscv/sifive_clint.c

@@ -180,7 +180,7 @@ static const MemoryRegionOps sifive_clint_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
     .valid = {
         .min_access_size = 4,
-        .max_access_size = 4
+        .max_access_size = 8
     }
 };
 

hw/riscv/sifive_test.c

@@ -58,7 +58,7 @@ static const MemoryRegionOps sifive_test_ops = {
     .write = sifive_test_write,
     .endianness = DEVICE_NATIVE_ENDIAN,
     .valid = {
-        .min_access_size = 4,
+        .min_access_size = 2,
         .max_access_size = 4
     }
 };

hw/s390x/virtio-ccw.c

@@ -786,9 +786,10 @@ static inline VirtioCcwDevice *to_virtio_ccw_dev_fast(DeviceState *d)
 static uint8_t virtio_set_ind_atomic(SubchDev *sch, uint64_t ind_loc,
                                      uint8_t to_be_set)
 {
-    uint8_t ind_old, ind_new;
+    uint8_t expected, actual;
     hwaddr len = 1;
-    uint8_t *ind_addr;
+    /* avoid  multiple fetches */
+    uint8_t volatile *ind_addr;
 
     ind_addr = cpu_physical_memory_map(ind_loc, &len, true);
     if (!ind_addr) {
@@ -796,14 +797,15 @@ static uint8_t virtio_set_ind_atomic(SubchDev *sch, uint64_t ind_loc,
                      __func__, sch->cssid, sch->ssid, sch->schid);
         return -1;
     }
+    actual = *ind_addr;
     do {
-        ind_old = *ind_addr;
-        ind_new = ind_old | to_be_set;
-    } while (atomic_cmpxchg(ind_addr, ind_old, ind_new) != ind_old);
-    trace_virtio_ccw_set_ind(ind_loc, ind_old, ind_new);
-    cpu_physical_memory_unmap(ind_addr, len, 1, len);
+        expected = actual;
+        actual = atomic_cmpxchg(ind_addr, expected, expected | to_be_set);
+    } while (actual != expected);
+    trace_virtio_ccw_set_ind(ind_loc, actual, actual | to_be_set);
+    cpu_physical_memory_unmap((void *)ind_addr, len, 1, len);
 
-    return ind_old;
+    return actual;
 }
 
 static void virtio_ccw_notify(DeviceState *d, uint16_t vector)

hw/sd/pxa2xx_mmci.c

@@ -497,12 +497,12 @@ PXA2xxMMCIState *pxa2xx_mmci_init(MemoryRegion *sysmem,
     carddev = qdev_create(qdev_get_child_bus(dev, "sd-bus"), TYPE_SD_CARD);
     qdev_prop_set_drive(carddev, "drive", blk, &err);
     if (err) {
-        error_report("failed to init SD card: %s", error_get_pretty(err));
+        error_reportf_err(err, "failed to init SD card: ");
         return NULL;
     }
     object_property_set_bool(OBJECT(carddev), true, "realized", &err);
     if (err) {
-        error_report("failed to init SD card: %s", error_get_pretty(err));
+        error_reportf_err(err, "failed to init SD card: ");
         return NULL;
     }
 

hw/sd/sd.c

@@ -32,6 +32,7 @@
 
 #include "qemu/osdep.h"
 #include "qemu/units.h"
+#include "qemu/cutils.h"
 #include "hw/irq.h"
 #include "hw/registerfields.h"
 #include "sysemu/block-backend.h"
@@ -703,13 +704,13 @@ SDState *sd_init(BlockBackend *blk, bool is_spi)
     dev = DEVICE(obj);
     qdev_prop_set_drive(dev, "drive", blk, &err);
     if (err) {
-        error_report("sd_init failed: %s", error_get_pretty(err));
+        error_reportf_err(err, "sd_init failed: ");
         return NULL;
     }
     qdev_prop_set_bit(dev, "spi", is_spi);
     object_property_set_bool(obj, true, "realized", &err);
     if (err) {
-        error_report("sd_init failed: %s", error_get_pretty(err));
+        error_reportf_err(err, "sd_init failed: ");
         return NULL;
     }
 
@@ -905,6 +906,11 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req)
         sd->multi_blk_cnt = 0;
     }
 
+    if (sd_cmd_class[req.cmd] == 6 && FIELD_EX32(sd->ocr, OCR, CARD_CAPACITY)) {
+        /* Only Standard Capacity cards support class 6 commands */
+        return sd_illegal;
+    }
+
     switch (req.cmd) {
     /* Basic commands (Class 0 and Class 1) */
     case 0:	/* CMD0:   GO_IDLE_STATE */
@@ -1150,12 +1156,15 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req)
     case 17:	/* CMD17:  READ_SINGLE_BLOCK */
         switch (sd->state) {
         case sd_transfer_state:
+
+            if (addr + sd->blk_len > sd->size) {
+                sd->card_status |= ADDRESS_ERROR;
+                return sd_r1;
+            }
+
             sd->state = sd_sendingdata_state;
             sd->data_start = addr;
             sd->data_offset = 0;
-
-            if (sd->data_start + sd->blk_len > sd->size)
-                sd->card_status |= ADDRESS_ERROR;
             return sd_r1;
 
         default:
@@ -1166,12 +1175,15 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req)
     case 18:	/* CMD18:  READ_MULTIPLE_BLOCK */
         switch (sd->state) {
         case sd_transfer_state:
+
+            if (addr + sd->blk_len > sd->size) {
+                sd->card_status |= ADDRESS_ERROR;
+                return sd_r1;
+            }
+
             sd->state = sd_sendingdata_state;
             sd->data_start = addr;
             sd->data_offset = 0;
-
-            if (sd->data_start + sd->blk_len > sd->size)
-                sd->card_status |= ADDRESS_ERROR;
             return sd_r1;
 
         default:
@@ -1211,17 +1223,23 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req)
             /* Writing in SPI mode not implemented.  */
             if (sd->spi)
                 break;
+
+            if (addr + sd->blk_len > sd->size) {
+                sd->card_status |= ADDRESS_ERROR;
+                return sd_r1;
+            }
+
             sd->state = sd_receivingdata_state;
             sd->data_start = addr;
             sd->data_offset = 0;
             sd->blk_written = 0;
 
-            if (sd->data_start + sd->blk_len > sd->size)
-                sd->card_status |= ADDRESS_ERROR;
-            if (sd_wp_addr(sd, sd->data_start))
+            if (sd_wp_addr(sd, sd->data_start)) {
                 sd->card_status |= WP_VIOLATION;
-            if (sd->csd[14] & 0x30)
+            }
+            if (sd->csd[14] & 0x30) {
                 sd->card_status |= WP_VIOLATION;
+            }
             return sd_r1;
 
         default:
@@ -1235,17 +1253,23 @@ static sd_rsp_type_t sd_normal_command(SDState *sd, SDRequest req)
             /* Writing in SPI mode not implemented.  */
             if (sd->spi)
                 break;
+
+            if (addr + sd->blk_len > sd->size) {
+                sd->card_status |= ADDRESS_ERROR;
+                return sd_r1;
+            }
+
             sd->state = sd_receivingdata_state;
             sd->data_start = addr;
             sd->data_offset = 0;
             sd->blk_written = 0;
 
-            if (sd->data_start + sd->blk_len > sd->size)
-                sd->card_status |= ADDRESS_ERROR;
-            if (sd_wp_addr(sd, sd->data_start))
+            if (sd_wp_addr(sd, sd->data_start)) {
                 sd->card_status |= WP_VIOLATION;
-            if (sd->csd[14] & 0x30)
+            }
+            if (sd->csd[14] & 0x30) {
                 sd->card_status |= WP_VIOLATION;
+            }
             return sd_r1;
 
         default:
@@ -2085,12 +2109,36 @@ static void sd_realize(DeviceState *dev, Error **errp)
         return;
     }
 
-    if (sd->blk && blk_is_read_only(sd->blk)) {
-        error_setg(errp, "Cannot use read-only drive as SD card");
-        return;
-    }
-
     if (sd->blk) {
+        int64_t blk_size;
+
+        if (blk_is_read_only(sd->blk)) {
+            error_setg(errp, "Cannot use read-only drive as SD card");
+            return;
+        }
+
+        blk_size = blk_getlength(sd->blk);
+        if (blk_size > 0 && !is_power_of_2(blk_size)) {
+            int64_t blk_size_aligned = pow2ceil(blk_size);
+            char *blk_size_str;
+
+            blk_size_str = size_to_str(blk_size);
+            error_setg(errp, "Invalid SD card size: %s", blk_size_str);
+            g_free(blk_size_str);
+
+            blk_size_str = size_to_str(blk_size_aligned);
+            error_append_hint(errp,
+                              "SD card size has to be a power of 2, e.g. %s.\n"
+                              "You can resize disk images with"
+                              " 'qemu-img resize <imagefile> <new-size>'\n"
+                              "(note that this will lose data if you make the"
+                              " image smaller than it currently is).\n",
+                              blk_size_str);
+            g_free(blk_size_str);
+
+            return;
+        }
+
         ret = blk_set_perm(sd->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE,
                            BLK_PERM_ALL, errp);
         if (ret < 0) {

hw/sparc/sun4m.c

@@ -142,7 +142,7 @@ static void nvram_init(Nvram *nvram, uint8_t *macaddr,
     memset(image, '\0', sizeof(image));
 
     /* OpenBIOS nvram variables partition */
-    sysp_end = chrp_nvram_create_system_partition(image, 0);
+    sysp_end = chrp_nvram_create_system_partition(image, 0, 0x1fd0);
 
     /* Free space partition */
     chrp_nvram_create_free_partition(&image[sysp_end], 0x1fd0 - sysp_end);

hw/sparc64/sun4u.c

@@ -136,7 +136,7 @@ static int sun4u_NVRAM_set_params(Nvram *nvram, uint16_t NVRAM_size,
     memset(image, '\0', sizeof(image));
 
     /* OpenBIOS nvram variables partition */
-    sysp_end = chrp_nvram_create_system_partition(image, 0);
+    sysp_end = chrp_nvram_create_system_partition(image, 0, 0x1fd0);
 
     /* Free space partition */
     chrp_nvram_create_free_partition(&image[sysp_end], 0x1fd0 - sysp_end);

hw/tpm/tpm_spapr.c

@@ -306,7 +306,10 @@ static void tpm_spapr_reset(SpaprVioDevice *dev)
                             TPM_SPAPR_BUFFER_MAX);
 
     tpm_backend_reset(s->be_driver);
-    tpm_spapr_do_startup_tpm(s, s->be_buffer_size);
+
+    if (tpm_spapr_do_startup_tpm(s, s->be_buffer_size) < 0) {
+        exit(1);
+    }
 }
 
 static enum TPMVersion tpm_spapr_get_version(TPMIf *ti)

hw/usb/core.c

@@ -129,6 +129,7 @@ void usb_wakeup(USBEndpoint *ep, unsigned int stream)
 static void do_token_setup(USBDevice *s, USBPacket *p)
 {
     int request, value, index;
+    unsigned int setup_len;
 
     if (p->iov.size != 8) {
         p->status = USB_RET_STALL;
@@ -138,14 +139,15 @@ static void do_token_setup(USBDevice *s, USBPacket *p)
     usb_packet_copy(p, s->setup_buf, p->iov.size);
     s->setup_index = 0;
     p->actual_length = 0;
-    s->setup_len   = (s->setup_buf[7] << 8) | s->setup_buf[6];
-    if (s->setup_len > sizeof(s->data_buf)) {
+    setup_len = (s->setup_buf[7] << 8) | s->setup_buf[6];
+    if (setup_len > sizeof(s->data_buf)) {
         fprintf(stderr,
                 "usb_generic_handle_packet: ctrl buffer too small (%d > %zu)\n",
-                s->setup_len, sizeof(s->data_buf));
+                setup_len, sizeof(s->data_buf));
         p->status = USB_RET_STALL;
         return;
     }
+    s->setup_len = setup_len;
 
     request = (s->setup_buf[0] << 8) | s->setup_buf[1];
     value   = (s->setup_buf[3] << 8) | s->setup_buf[2];
@@ -259,26 +261,28 @@ static void do_token_out(USBDevice *s, USBPacket *p)
 static void do_parameter(USBDevice *s, USBPacket *p)
 {
     int i, request, value, index;
+    unsigned int setup_len;
 
     for (i = 0; i < 8; i++) {
         s->setup_buf[i] = p->parameter >> (i*8);
     }
 
     s->setup_state = SETUP_STATE_PARAM;
-    s->setup_len   = (s->setup_buf[7] << 8) | s->setup_buf[6];
     s->setup_index = 0;
 
     request = (s->setup_buf[0] << 8) | s->setup_buf[1];
     value   = (s->setup_buf[3] << 8) | s->setup_buf[2];
     index   = (s->setup_buf[5] << 8) | s->setup_buf[4];
 
-    if (s->setup_len > sizeof(s->data_buf)) {
+    setup_len = (s->setup_buf[7] << 8) | s->setup_buf[6];
+    if (setup_len > sizeof(s->data_buf)) {
         fprintf(stderr,
                 "usb_generic_handle_packet: ctrl buffer too small (%d > %zu)\n",
-                s->setup_len, sizeof(s->data_buf));
+                setup_len, sizeof(s->data_buf));
         p->status = USB_RET_STALL;
         return;
     }
+    s->setup_len = setup_len;
 
     if (p->pid == USB_TOKEN_OUT) {
         usb_packet_copy(p, s->data_buf, s->setup_len);

hw/usb/dev-mtp.c

@@ -631,9 +631,9 @@ static void usb_mtp_object_readdir(MTPState *s, MTPObject *o)
         int64_t id = qemu_file_monitor_add_watch(s->file_monitor, o->path, NULL,
                                                  file_monitor_event, s, &err);
         if (id == -1) {
-            error_report("usb-mtp: failed to add watch for %s: %s", o->path,
-                         error_get_pretty(err));
-            error_free(err);
+            error_reportf_err(err,
+                              "usb-mtp: failed to add watch for %s: ",
+                              o->path);
         } else {
             trace_usb_mtp_file_monitor_event(s->dev.addr, o->path,
                                              "Watch Added");
@@ -1276,9 +1276,8 @@ static void usb_mtp_command(MTPState *s, MTPControl *c)
 
         s->file_monitor = qemu_file_monitor_new(&err);
         if (err) {
-            error_report("usb-mtp: file monitoring init failed: %s",
-                         error_get_pretty(err));
-            error_free(err);
+            error_reportf_err(err,
+                              "usb-mtp: file monitoring init failed: ");
         } else {
             QTAILQ_INIT(&s->events);
         }

hw/usb/hcd-xhci.c

@@ -3184,7 +3184,7 @@ static const MemoryRegionOps xhci_oper_ops = {
     .read = xhci_oper_read,
     .write = xhci_oper_write,
     .valid.min_access_size = 4,
-    .valid.max_access_size = 4,
+    .valid.max_access_size = sizeof(dma_addr_t),
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
@@ -3200,7 +3200,7 @@ static const MemoryRegionOps xhci_runtime_ops = {
     .read = xhci_runtime_read,
     .write = xhci_runtime_write,
     .valid.min_access_size = 4,
-    .valid.max_access_size = 4,
+    .valid.max_access_size = sizeof(dma_addr_t),
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 

hw/virtio/virtio-balloon.c

@@ -466,21 +466,22 @@ static bool get_free_page_hints(VirtIOBalloon *dev)
             ret = false;
             goto out;
         }
-        if (id == dev->free_page_report_cmd_id) {
-            dev->free_page_report_status = FREE_PAGE_REPORT_S_START;
+        if (dev->free_page_hint_status == FREE_PAGE_HINT_S_REQUESTED &&
+            id == dev->free_page_hint_cmd_id) {
+            dev->free_page_hint_status = FREE_PAGE_HINT_S_START;
         } else {
             /*
              * Stop the optimization only when it has started. This
              * avoids a stale stop sign for the previous command.
              */
-            if (dev->free_page_report_status == FREE_PAGE_REPORT_S_START) {
-                dev->free_page_report_status = FREE_PAGE_REPORT_S_STOP;
+            if (dev->free_page_hint_status == FREE_PAGE_HINT_S_START) {
+                dev->free_page_hint_status = FREE_PAGE_HINT_S_STOP;
             }
         }
     }
 
     if (elem->in_num) {
-        if (dev->free_page_report_status == FREE_PAGE_REPORT_S_START) {
+        if (dev->free_page_hint_status == FREE_PAGE_HINT_S_START) {
             qemu_guest_free_page_hint(elem->in_sg[0].iov_base,
                                       elem->in_sg[0].iov_len);
         }
@@ -506,11 +507,11 @@ static void virtio_ballloon_get_free_page_hints(void *opaque)
         qemu_mutex_unlock(&dev->free_page_lock);
         virtio_notify(vdev, vq);
       /*
-       * Start to poll the vq once the reporting started. Otherwise, continue
+       * Start to poll the vq once the hinting started. Otherwise, continue
        * only when there are entries on the vq, which need to be given back.
        */
     } while (continue_to_get_hints ||
-             dev->free_page_report_status == FREE_PAGE_REPORT_S_START);
+             dev->free_page_hint_status == FREE_PAGE_HINT_S_START);
     virtio_queue_set_notification(vq, 1);
 }
 
@@ -531,14 +532,18 @@ static void virtio_balloon_free_page_start(VirtIOBalloon *s)
         return;
     }
 
-    if (s->free_page_report_cmd_id == UINT_MAX) {
-        s->free_page_report_cmd_id =
-                       VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN;
+    qemu_mutex_lock(&s->free_page_lock);
+
+    if (s->free_page_hint_cmd_id == UINT_MAX) {
+        s->free_page_hint_cmd_id =
+                       VIRTIO_BALLOON_FREE_PAGE_HINT_CMD_ID_MIN;
     } else {
-        s->free_page_report_cmd_id++;
+        s->free_page_hint_cmd_id++;
     }
 
-    s->free_page_report_status = FREE_PAGE_REPORT_S_REQUESTED;
+    s->free_page_hint_status = FREE_PAGE_HINT_S_REQUESTED;
+    qemu_mutex_unlock(&s->free_page_lock);
+
     virtio_notify_config(vdev);
 }
 
@@ -546,18 +551,18 @@ static void virtio_balloon_free_page_stop(VirtIOBalloon *s)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
 
-    if (s->free_page_report_status != FREE_PAGE_REPORT_S_STOP) {
+    if (s->free_page_hint_status != FREE_PAGE_HINT_S_STOP) {
         /*
          * The lock also guarantees us that the
          * virtio_ballloon_get_free_page_hints exits after the
-         * free_page_report_status is set to S_STOP.
+         * free_page_hint_status is set to S_STOP.
          */
         qemu_mutex_lock(&s->free_page_lock);
         /*
-         * The guest hasn't done the reporting, so host sends a notification
-         * to the guest to actively stop the reporting.
+         * The guest isn't done hinting, so send a notification
+         * to the guest to actively stop the hinting.
          */
-        s->free_page_report_status = FREE_PAGE_REPORT_S_STOP;
+        s->free_page_hint_status = FREE_PAGE_HINT_S_STOP;
         qemu_mutex_unlock(&s->free_page_lock);
         virtio_notify_config(vdev);
     }
@@ -567,15 +572,20 @@ static void virtio_balloon_free_page_done(VirtIOBalloon *s)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
 
-    s->free_page_report_status = FREE_PAGE_REPORT_S_DONE;
-    virtio_notify_config(vdev);
+    if (s->free_page_hint_status != FREE_PAGE_HINT_S_DONE) {
+        /* See virtio_balloon_free_page_stop() */
+        qemu_mutex_lock(&s->free_page_lock);
+        s->free_page_hint_status = FREE_PAGE_HINT_S_DONE;
+        qemu_mutex_unlock(&s->free_page_lock);
+        virtio_notify_config(vdev);
+    }
 }
 
 static int
-virtio_balloon_free_page_report_notify(NotifierWithReturn *n, void *data)
+virtio_balloon_free_page_hint_notify(NotifierWithReturn *n, void *data)
 {
     VirtIOBalloon *dev = container_of(n, VirtIOBalloon,
-                                      free_page_report_notify);
+                                      free_page_hint_notify);
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     PrecopyNotifyData *pnd = data;
 
@@ -592,17 +602,26 @@ virtio_balloon_free_page_report_notify(NotifierWithReturn *n, void *data)
     case PRECOPY_NOTIFY_SETUP:
         precopy_enable_free_page_optimization();
         break;
-    case PRECOPY_NOTIFY_COMPLETE:
-    case PRECOPY_NOTIFY_CLEANUP:
     case PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC:
         virtio_balloon_free_page_stop(dev);
         break;
     case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC:
         if (vdev->vm_running) {
             virtio_balloon_free_page_start(dev);
-        } else {
-            virtio_balloon_free_page_done(dev);
+            break;
         }
+        /*
+         * Set S_DONE before migrating the vmstate, so the guest will reuse
+         * all hinted pages once running on the destination. Fall through.
+         */
+    case PRECOPY_NOTIFY_CLEANUP:
+        /*
+         * Especially, if something goes wrong during precopy or if migration
+         * is canceled, we have to properly communicate S_DONE to the VM.
+         */
+        virtio_balloon_free_page_done(dev);
+        break;
+    case PRECOPY_NOTIFY_COMPLETE:
         break;
     default:
         virtio_error(vdev, "%s: %d reason unknown", __func__, pnd->reason);
@@ -624,7 +643,7 @@ static size_t virtio_balloon_config_size(VirtIOBalloon *s)
     if (virtio_has_feature(features, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
         return offsetof(struct virtio_balloon_config, poison_val);
     }
-    return offsetof(struct virtio_balloon_config, free_page_report_cmd_id);
+    return offsetof(struct virtio_balloon_config, free_page_hint_cmd_id);
 }
 
 static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
@@ -635,14 +654,14 @@ static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
     config.num_pages = cpu_to_le32(dev->num_pages);
     config.actual = cpu_to_le32(dev->actual);
 
-    if (dev->free_page_report_status == FREE_PAGE_REPORT_S_REQUESTED) {
-        config.free_page_report_cmd_id =
-                       cpu_to_le32(dev->free_page_report_cmd_id);
-    } else if (dev->free_page_report_status == FREE_PAGE_REPORT_S_STOP) {
-        config.free_page_report_cmd_id =
+    if (dev->free_page_hint_status == FREE_PAGE_HINT_S_REQUESTED) {
+        config.free_page_hint_cmd_id =
+                       cpu_to_le32(dev->free_page_hint_cmd_id);
+    } else if (dev->free_page_hint_status == FREE_PAGE_HINT_S_STOP) {
+        config.free_page_hint_cmd_id =
                        cpu_to_le32(VIRTIO_BALLOON_CMD_ID_STOP);
-    } else if (dev->free_page_report_status == FREE_PAGE_REPORT_S_DONE) {
-        config.free_page_report_cmd_id =
+    } else if (dev->free_page_hint_status == FREE_PAGE_HINT_S_DONE) {
+        config.free_page_hint_cmd_id =
                        cpu_to_le32(VIRTIO_BALLOON_CMD_ID_DONE);
     }
 
@@ -743,14 +762,14 @@ static int virtio_balloon_post_load_device(void *opaque, int version_id)
     return 0;
 }
 
-static const VMStateDescription vmstate_virtio_balloon_free_page_report = {
+static const VMStateDescription vmstate_virtio_balloon_free_page_hint = {
     .name = "virtio-balloon-device/free-page-report",
     .version_id = 1,
     .minimum_version_id = 1,
     .needed = virtio_balloon_free_page_support,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT32(free_page_report_cmd_id, VirtIOBalloon),
-        VMSTATE_UINT32(free_page_report_status, VirtIOBalloon),
+        VMSTATE_UINT32(free_page_hint_cmd_id, VirtIOBalloon),
+        VMSTATE_UINT32(free_page_hint_status, VirtIOBalloon),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -766,7 +785,7 @@ static const VMStateDescription vmstate_virtio_balloon_device = {
         VMSTATE_END_OF_LIST()
     },
     .subsections = (const VMStateDescription * []) {
-        &vmstate_virtio_balloon_free_page_report,
+        &vmstate_virtio_balloon_free_page_hint,
         NULL
     }
 };
@@ -789,6 +808,13 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    if (virtio_has_feature(s->host_features, VIRTIO_BALLOON_F_FREE_PAGE_HINT) &&
+        !s->iothread) {
+        error_setg(errp, "'free-page-hint' requires 'iothread' to be set");
+        virtio_cleanup(vdev);
+        return;
+    }
+
     s->ivq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output);
     s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats);
@@ -797,24 +823,11 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp)
                            VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
         s->free_page_vq = virtio_add_queue(vdev, VIRTQUEUE_MAX_SIZE,
                                            virtio_balloon_handle_free_page_vq);
-        s->free_page_report_status = FREE_PAGE_REPORT_S_STOP;
-        s->free_page_report_cmd_id =
-                           VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN;
-        s->free_page_report_notify.notify =
-                                       virtio_balloon_free_page_report_notify;
-        precopy_add_notifier(&s->free_page_report_notify);
-        if (s->iothread) {
-            object_ref(OBJECT(s->iothread));
-            s->free_page_bh = aio_bh_new(iothread_get_aio_context(s->iothread),
-                                       virtio_ballloon_get_free_page_hints, s);
-            qemu_mutex_init(&s->free_page_lock);
-            qemu_cond_init(&s->free_page_cond);
-            s->block_iothread = false;
-        } else {
-            /* Simply disable this feature if the iothread wasn't created. */
-            s->host_features &= ~(1 << VIRTIO_BALLOON_F_FREE_PAGE_HINT);
-            virtio_error(vdev, "iothread is missing");
-        }
+        precopy_add_notifier(&s->free_page_hint_notify);
+
+        object_ref(OBJECT(s->iothread));
+        s->free_page_bh = aio_bh_new(iothread_get_aio_context(s->iothread),
+                                     virtio_ballloon_get_free_page_hints, s);
     }
     reset_stats(s);
 }
@@ -824,10 +837,11 @@ static void virtio_balloon_device_unrealize(DeviceState *dev, Error **errp)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOBalloon *s = VIRTIO_BALLOON(dev);
 
-    if (virtio_balloon_free_page_support(s)) {
+    if (s->free_page_bh) {
         qemu_bh_delete(s->free_page_bh);
+        object_unref(OBJECT(s->iothread));
         virtio_balloon_free_page_stop(s);
-        precopy_remove_notifier(&s->free_page_report_notify);
+        precopy_remove_notifier(&s->free_page_hint_notify);
     }
     balloon_stats_destroy_timer(s);
     qemu_remove_balloon_handler(s);
@@ -892,6 +906,11 @@ static void virtio_balloon_instance_init(Object *obj)
 {
     VirtIOBalloon *s = VIRTIO_BALLOON(obj);
 
+    qemu_mutex_init(&s->free_page_lock);
+    qemu_cond_init(&s->free_page_cond);
+    s->free_page_hint_cmd_id = VIRTIO_BALLOON_FREE_PAGE_HINT_CMD_ID_MIN;
+    s->free_page_hint_notify.notify = virtio_balloon_free_page_hint_notify;
+
     object_property_add(obj, "guest-stats", "guest statistics",
                         balloon_stats_get_all, NULL, NULL, s, NULL);
 

hw/virtio/virtio-pci.c

@@ -1317,11 +1317,12 @@ static uint64_t virtio_pci_notify_read(void *opaque, hwaddr addr,
 static void virtio_pci_notify_write(void *opaque, hwaddr addr,
                                     uint64_t val, unsigned size)
 {
-    VirtIODevice *vdev = opaque;
-    VirtIOPCIProxy *proxy = VIRTIO_PCI(DEVICE(vdev)->parent_bus->parent);
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
     unsigned queue = addr / virtio_pci_queue_mem_mult(proxy);
 
-    if (queue < VIRTIO_QUEUE_MAX) {
+    if (vdev != NULL && queue < VIRTIO_QUEUE_MAX) {
         virtio_queue_notify(vdev, queue);
     }
 }
@@ -1329,10 +1330,12 @@ static void virtio_pci_notify_write(void *opaque, hwaddr addr,
 static void virtio_pci_notify_write_pio(void *opaque, hwaddr addr,
                                         uint64_t val, unsigned size)
 {
-    VirtIODevice *vdev = opaque;
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
     unsigned queue = val;
 
-    if (queue < VIRTIO_QUEUE_MAX) {
+    if (vdev != NULL && queue < VIRTIO_QUEUE_MAX) {
         virtio_queue_notify(vdev, queue);
     }
 }
@@ -1356,9 +1359,14 @@ static void virtio_pci_isr_write(void *opaque, hwaddr addr,
 static uint64_t virtio_pci_device_read(void *opaque, hwaddr addr,
                                        unsigned size)
 {
-    VirtIODevice *vdev = opaque;
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     uint64_t val = 0;
 
+    if (vdev == NULL) {
+        return val;
+    }
+
     switch (size) {
     case 1:
         val = virtio_config_modern_readb(vdev, addr);
@@ -1376,7 +1384,13 @@ static uint64_t virtio_pci_device_read(void *opaque, hwaddr addr,
 static void virtio_pci_device_write(void *opaque, hwaddr addr,
                                     uint64_t val, unsigned size)
 {
-    VirtIODevice *vdev = opaque;
+    VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
+    if (vdev == NULL) {
+        return;
+    }
+
     switch (size) {
     case 1:
         virtio_config_modern_writeb(vdev, addr, val);
@@ -1453,19 +1467,19 @@ static void virtio_pci_modern_regions_init(VirtIOPCIProxy *proxy)
 
     memory_region_init_io(&proxy->device.mr, OBJECT(proxy),
                           &device_ops,
-                          virtio_bus_get_device(&proxy->bus),
+                          proxy,
                           "virtio-pci-device",
                           proxy->device.size);
 
     memory_region_init_io(&proxy->notify.mr, OBJECT(proxy),
                           &notify_ops,
-                          virtio_bus_get_device(&proxy->bus),
+                          proxy,
                           "virtio-pci-notify",
                           proxy->notify.size);
 
     memory_region_init_io(&proxy->notify_pio.mr, OBJECT(proxy),
                           &notify_pio_ops,
-                          virtio_bus_get_device(&proxy->bus),
+                          proxy,
                           "virtio-pci-notify-pio",
                           proxy->notify_pio.size);
 }

include/block/aio-wait.h

@@ -26,6 +26,7 @@
 #define QEMU_AIO_WAIT_H
 
 #include "block/aio.h"
+#include "qemu/main-loop.h"
 
 /**
  * AioWait:
@@ -124,4 +125,25 @@ void aio_wait_kick(void);
  */
 void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
 
+/**
+ * in_aio_context_home_thread:
+ * @ctx: the aio context
+ *
+ * Return whether we are running in the thread that normally runs @ctx.  Note
+ * that acquiring/releasing ctx does not affect the outcome, each AioContext
+ * still only has one home thread that is responsible for running it.
+ */
+static inline bool in_aio_context_home_thread(AioContext *ctx)
+{
+    if (ctx == qemu_get_current_aio_context()) {
+        return true;
+    }
+
+    if (ctx == qemu_get_aio_context()) {
+        return qemu_mutex_iothread_locked();
+    } else {
+        return false;
+    }
+}
+
 #endif /* QEMU_AIO_WAIT_H */

include/block/aio.h

@@ -133,12 +133,16 @@ struct AioContext {
     AioHandlerList deleted_aio_handlers;
 
     /* Used to avoid unnecessary event_notifier_set calls in aio_notify;
-     * accessed with atomic primitives.  If this field is 0, everything
-     * (file descriptors, bottom halves, timers) will be re-evaluated
-     * before the next blocking poll(), thus the event_notifier_set call
-     * can be skipped.  If it is non-zero, you may need to wake up a
-     * concurrent aio_poll or the glib main event loop, making
-     * event_notifier_set necessary.
+     * only written from the AioContext home thread, or under the BQL in
+     * the case of the main AioContext.  However, it is read from any
+     * thread so it is still accessed with atomic primitives.
+     *
+     * If this field is 0, everything (file descriptors, bottom halves,
+     * timers) will be re-evaluated before the next blocking poll() or
+     * io_uring wait; therefore, the event_notifier_set call can be
+     * skipped.  If it is non-zero, you may need to wake up a concurrent
+     * aio_poll or the glib main event loop, making event_notifier_set
+     * necessary.
      *
      * Bit 0 is reserved for GSource usage of the AioContext, and is 1
      * between a call to aio_ctx_prepare and the next call to aio_ctx_check.
@@ -681,19 +685,6 @@ void aio_co_enter(AioContext *ctx, struct Coroutine *co);
  */
 AioContext *qemu_get_current_aio_context(void);
 
-/**
- * in_aio_context_home_thread:
- * @ctx: the aio context
- *
- * Return whether we are running in the thread that normally runs @ctx.  Note
- * that acquiring/releasing ctx does not affect the outcome, each AioContext
- * still only has one home thread that is responsible for running it.
- */
-static inline bool in_aio_context_home_thread(AioContext *ctx)
-{
-    return ctx == qemu_get_current_aio_context();
-}
-
 /**
  * aio_context_setup:
  * @ctx: the aio context
@@ -710,6 +701,9 @@ void aio_context_setup(AioContext *ctx);
  */
 void aio_context_destroy(AioContext *ctx);
 
+/* Used internally, do not call outside AioContext code */
+void aio_context_use_g_source(AioContext *ctx);
+
 /**
  * aio_context_set_poll_params:
  * @ctx: the aio context

include/exec/gdbstub.h

@@ -125,6 +125,24 @@ static inline int gdb_get_reg128(GByteArray *buf, uint64_t val_hi,
     return 16;
 }
 
+static inline int gdb_get_float32(GByteArray *array, float32 val)
+{
+    uint8_t buf[sizeof(CPU_FloatU)];
+
+    stfl_p(buf, val);
+    g_byte_array_append(array, buf, sizeof(buf));
+
+    return sizeof(buf);
+}
+static inline int gdb_get_zeroes(GByteArray *array, size_t len)
+{
+    guint oldlen = array->len;
+    g_byte_array_set_size(array, oldlen + len);
+    memset(array->data + oldlen, 0, len);
+
+    return len;
+}
+
 /**
  * gdb_get_reg_ptr: get pointer to start of last element
  * @len: length of element

include/exec/memory.h

@@ -2351,8 +2351,8 @@ void address_space_write_cached_slow(MemoryRegionCache *cache,
 static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
 {
     if (is_write) {
-        return memory_region_is_ram(mr) &&
-               !mr->readonly && !memory_region_is_ram_device(mr);
+        return memory_region_is_ram(mr) && !mr->readonly &&
+               !mr->rom_device && !memory_region_is_ram_device(mr);
     } else {
         return (memory_region_is_ram(mr) && !memory_region_is_ram_device(mr)) ||
                memory_region_is_romd(mr);

include/hw/acpi/aml-build.h

@@ -13,6 +13,7 @@
 #define ACPI_BUILD_TABLE_FILE "etc/acpi/tables"
 #define ACPI_BUILD_RSDP_FILE "etc/acpi/rsdp"
 #define ACPI_BUILD_TPMLOG_FILE "etc/tpm/log"
+#define ACPI_BUILD_LOADER_FILE "etc/table-loader"
 
 #define AML_NOTIFY_METHOD "NTFY"
 

include/hw/nvram/chrp_nvram.h

@@ -50,7 +50,8 @@ chrp_nvram_finish_partition(ChrpNvramPartHdr *header, uint32_t size)
     header->checksum = sum & 0xff;
 }
 
-int chrp_nvram_create_system_partition(uint8_t *data, int min_len);
+/* chrp_nvram_create_system_partition() failure is fatal */
+int chrp_nvram_create_system_partition(uint8_t *data, int min_len, int max_len);
 int chrp_nvram_create_free_partition(uint8_t *data, int len);
 
 #endif

include/hw/nvram/fw_cfg.h

@@ -53,6 +53,12 @@ struct FWCfgState {
     dma_addr_t dma_addr;
     AddressSpace *dma_as;
     MemoryRegion dma_iomem;
+
+    /* restore during migration */
+    bool acpi_mr_restore;
+    uint64_t table_mr_size;
+    uint64_t linker_mr_size;
+    uint64_t rsdp_mr_size;
 };
 
 struct FWCfgIoState {

include/hw/virtio/virtio-balloon.h

@@ -23,7 +23,7 @@
 #define VIRTIO_BALLOON(obj) \
         OBJECT_CHECK(VirtIOBalloon, (obj), TYPE_VIRTIO_BALLOON)
 
-#define VIRTIO_BALLOON_FREE_PAGE_REPORT_CMD_ID_MIN 0x80000000
+#define VIRTIO_BALLOON_FREE_PAGE_HINT_CMD_ID_MIN 0x80000000
 
 typedef struct virtio_balloon_stat VirtIOBalloonStat;
 
@@ -33,20 +33,20 @@ typedef struct virtio_balloon_stat_modern {
        uint64_t val;
 } VirtIOBalloonStatModern;
 
-enum virtio_balloon_free_page_report_status {
-    FREE_PAGE_REPORT_S_STOP = 0,
-    FREE_PAGE_REPORT_S_REQUESTED = 1,
-    FREE_PAGE_REPORT_S_START = 2,
-    FREE_PAGE_REPORT_S_DONE = 3,
+enum virtio_balloon_free_page_hint_status {
+    FREE_PAGE_HINT_S_STOP = 0,
+    FREE_PAGE_HINT_S_REQUESTED = 1,
+    FREE_PAGE_HINT_S_START = 2,
+    FREE_PAGE_HINT_S_DONE = 3,
 };
 
 typedef struct VirtIOBalloon {
     VirtIODevice parent_obj;
     VirtQueue *ivq, *dvq, *svq, *free_page_vq;
-    uint32_t free_page_report_status;
+    uint32_t free_page_hint_status;
     uint32_t num_pages;
     uint32_t actual;
-    uint32_t free_page_report_cmd_id;
+    uint32_t free_page_hint_cmd_id;
     uint64_t stats[VIRTIO_BALLOON_S_NR];
     VirtQueueElement *stats_vq_elem;
     size_t stats_vq_offset;
@@ -55,7 +55,7 @@ typedef struct VirtIOBalloon {
     QEMUBH *free_page_bh;
     /*
      * Lock to synchronize threads to access the free page reporting related
-     * fields (e.g. free_page_report_status).
+     * fields (e.g. free_page_hint_status).
      */
     QemuMutex free_page_lock;
     QemuCond  free_page_cond;
@@ -64,7 +64,7 @@ typedef struct VirtIOBalloon {
      * stopped.
      */
     bool block_iothread;
-    NotifierWithReturn free_page_report_notify;
+    NotifierWithReturn free_page_hint_notify;
     int64_t stats_last_update;
     int64_t stats_poll_interval;
     uint32_t host_features;

include/qemu/osdep.h

@@ -33,20 +33,6 @@
 #else
 #include "exec/poison.h"
 #endif
-#ifdef __COVERITY__
-/* Coverity does not like the new _Float* types that are used by
- * recent glibc, and croaks on every single file that includes
- * stdlib.h.  These typedefs are enough to please it.
- *
- * Note that these fix parse errors so they cannot be placed in
- * scripts/coverity-model.c.
- */
-typedef float _Float32;
-typedef double _Float32x;
-typedef double _Float64;
-typedef __float80 _Float64x;
-typedef __float128 _Float128;
-#endif
 
 #include "qemu/compiler.h"
 
@@ -621,4 +607,14 @@ static inline void qemu_reset_optind(void)
 #endif
 }
 
+/**
+ * qemu_get_host_name:
+ * @errp: Error object
+ *
+ * Operating system agnostic way of querying host name.
+ *
+ * Returns allocated hostname (caller should free), NULL on failure.
+ */
+char *qemu_get_host_name(Error **errp);
+
 #endif

include/qemu/thread.h

@@ -57,17 +57,17 @@ extern QemuCondTimedWaitFunc qemu_cond_timedwait_func;
  * hide them.
  */
 #define qemu_mutex_lock(m)                                              \
-            qemu_mutex_lock_impl(m, __FILE__, __LINE__);
+            qemu_mutex_lock_impl(m, __FILE__, __LINE__)
 #define qemu_mutex_trylock(m)                                           \
-            qemu_mutex_trylock_impl(m, __FILE__, __LINE__);
+            qemu_mutex_trylock_impl(m, __FILE__, __LINE__)
 #define qemu_rec_mutex_lock(m)                                          \
-            qemu_rec_mutex_lock_impl(m, __FILE__, __LINE__);
+            qemu_rec_mutex_lock_impl(m, __FILE__, __LINE__)
 #define qemu_rec_mutex_trylock(m)                                       \
-            qemu_rec_mutex_trylock_impl(m, __FILE__, __LINE__);
+            qemu_rec_mutex_trylock_impl(m, __FILE__, __LINE__)
 #define qemu_cond_wait(c, m)                                            \
-            qemu_cond_wait_impl(c, m, __FILE__, __LINE__);
+            qemu_cond_wait_impl(c, m, __FILE__, __LINE__)
 #define qemu_cond_timedwait(c, m, ms)                                   \
-            qemu_cond_wait_impl(c, m, ms, __FILE__, __LINE__);
+            qemu_cond_timedwait_impl(c, m, ms, __FILE__, __LINE__)
 #else
 #define qemu_mutex_lock(m) ({                                           \
             QemuMutexLockFunc _f = atomic_read(&qemu_mutex_lock_func);  \

include/standard-headers/linux/ethtool.h

@@ -596,6 +596,9 @@ struct ethtool_pauseparam {
  * @ETH_SS_LINK_MODES: link mode names
  * @ETH_SS_MSG_CLASSES: debug message class names
  * @ETH_SS_WOL_MODES: wake-on-lan modes
+ * @ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags
+ * @ETH_SS_TS_TX_TYPES: timestamping Tx types
+ * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters
  */
 enum ethtool_stringset {
 	ETH_SS_TEST		= 0,
@@ -610,6 +613,9 @@ enum ethtool_stringset {
 	ETH_SS_LINK_MODES,
 	ETH_SS_MSG_CLASSES,
 	ETH_SS_WOL_MODES,
+	ETH_SS_SOF_TIMESTAMPING,
+	ETH_SS_TS_TX_TYPES,
+	ETH_SS_TS_RX_FILTERS,
 
 	/* add new constants above here */
 	ETH_SS_COUNT
@@ -1330,6 +1336,7 @@ enum ethtool_fec_config_bits {
 	ETHTOOL_FEC_OFF_BIT,
 	ETHTOOL_FEC_RS_BIT,
 	ETHTOOL_FEC_BASER_BIT,
+	ETHTOOL_FEC_LLRS_BIT,
 };
 
 #define ETHTOOL_FEC_NONE		(1 << ETHTOOL_FEC_NONE_BIT)
@@ -1337,6 +1344,7 @@ enum ethtool_fec_config_bits {
 #define ETHTOOL_FEC_OFF			(1 << ETHTOOL_FEC_OFF_BIT)
 #define ETHTOOL_FEC_RS			(1 << ETHTOOL_FEC_RS_BIT)
 #define ETHTOOL_FEC_BASER		(1 << ETHTOOL_FEC_BASER_BIT)
+#define ETHTOOL_FEC_LLRS		(1 << ETHTOOL_FEC_LLRS_BIT)
 
 /* CMDs currently supported */
 #define ETHTOOL_GSET		0x00000001 /* DEPRECATED, Get settings.
@@ -1521,7 +1529,7 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT = 71,
 	ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT	 = 72,
 	ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT	 = 73,
-
+	ETHTOOL_LINK_MODE_FEC_LLRS_BIT			 = 74,
 	/* must be last entry */
 	__ETHTOOL_LINK_MODE_MASK_NBITS
 };

include/standard-headers/linux/input-event-codes.h

@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
 /*
  * Input event codes
  *
@@ -652,6 +652,9 @@
 /* Electronic privacy screen control */
 #define KEY_PRIVACY_SCREEN_TOGGLE	0x279
 
+/* Select an area of screen to be copied */
+#define KEY_SELECTIVE_SCREENSHOT	0x27a
+
 /*
  * Some keyboards have keys which do not have a defined meaning, these keys
  * are intended to be programmed / bound to macros by the user. For most

include/standard-headers/linux/pci_regs.h

@@ -605,6 +605,7 @@
 #define  PCI_EXP_SLTCTL_PWR_OFF        0x0400 /* Power Off */
 #define  PCI_EXP_SLTCTL_EIC	0x0800	/* Electromechanical Interlock Control */
 #define  PCI_EXP_SLTCTL_DLLSCE	0x1000	/* Data Link Layer State Changed Enable */
+#define  PCI_EXP_SLTCTL_IBPD_DISABLE	0x4000 /* In-band PD disable */
 #define PCI_EXP_SLTSTA		26	/* Slot Status */
 #define  PCI_EXP_SLTSTA_ABP	0x0001	/* Attention Button Pressed */
 #define  PCI_EXP_SLTSTA_PFD	0x0002	/* Power Fault Detected */
@@ -680,6 +681,7 @@
 #define PCI_EXP_LNKSTA2		50	/* Link Status 2 */
 #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	52	/* v2 endpoints with link end here */
 #define PCI_EXP_SLTCAP2		52	/* Slot Capabilities 2 */
+#define  PCI_EXP_SLTCAP2_IBPD	0x00000001 /* In-band PD Disable Supported */
 #define PCI_EXP_SLTCTL2		56	/* Slot Control 2 */
 #define PCI_EXP_SLTSTA2		58	/* Slot Status 2 */
 

include/standard-headers/linux/vhost_types.h

@@ -119,6 +119,14 @@ struct vhost_scsi_target {
 	unsigned short reserved;
 };
 
+/* VHOST_VDPA specific definitions */
+
+struct vhost_vdpa_config {
+	uint32_t off;
+	uint32_t len;
+	uint8_t buf[0];
+};
+
 /* Feature bits */
 /* Log all write descriptors. Can be changed while device is active. */
 #define VHOST_F_LOG_ALL 26

include/standard-headers/linux/virtio_balloon.h

@@ -36,6 +36,7 @@
 #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
 #define VIRTIO_BALLOON_F_FREE_PAGE_HINT	3 /* VQ to report free pages */
 #define VIRTIO_BALLOON_F_PAGE_POISON	4 /* Guest is using page poisoning */
+#define VIRTIO_BALLOON_F_REPORTING	5 /* Page reporting virtqueue */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
@@ -47,8 +48,15 @@ struct virtio_balloon_config {
 	uint32_t num_pages;
 	/* Number of pages we've actually got in balloon. */
 	uint32_t actual;
-	/* Free page report command id, readonly by guest */
-	uint32_t free_page_report_cmd_id;
+	/*
+	 * Free page hint command id, readonly by guest.
+	 * Was previously named free_page_report_cmd_id so we
+	 * need to carry that name for legacy support.
+	 */
+	union {
+		uint32_t free_page_hint_cmd_id;
+		uint32_t free_page_report_cmd_id;	/* deprecated */
+	};
 	/* Stores PAGE_POISON if page poisoning is in use */
 	uint32_t poison_val;
 };

include/standard-headers/linux/virtio_ids.h

@@ -46,5 +46,6 @@
 #define VIRTIO_ID_IOMMU        23 /* virtio IOMMU */
 #define VIRTIO_ID_FS           26 /* virtio filesystem */
 #define VIRTIO_ID_PMEM         27 /* virtio pmem */
+#define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */
 
 #endif /* _LINUX_VIRTIO_IDS_H */

include/standard-headers/linux/virtio_net.h

@@ -57,6 +57,9 @@
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
 
+#define VIRTIO_NET_F_HASH_REPORT  57	/* Supports hash report */
+#define VIRTIO_NET_F_RSS	  60	/* Supports RSS RX steering */
+#define VIRTIO_NET_F_RSC_EXT	  61	/* extended coalescing info */
 #define VIRTIO_NET_F_STANDBY	  62	/* Act as standby for another device
 					 * with the same MAC.
 					 */
@@ -69,6 +72,17 @@
 #define VIRTIO_NET_S_LINK_UP	1	/* Link is up */
 #define VIRTIO_NET_S_ANNOUNCE	2	/* Announcement is needed */
 
+/* supported/enabled hash types */
+#define VIRTIO_NET_RSS_HASH_TYPE_IPv4          (1 << 0)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCPv4         (1 << 1)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDPv4         (1 << 2)
+#define VIRTIO_NET_RSS_HASH_TYPE_IPv6          (1 << 3)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCPv6         (1 << 4)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDPv6         (1 << 5)
+#define VIRTIO_NET_RSS_HASH_TYPE_IP_EX         (1 << 6)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCP_EX        (1 << 7)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDP_EX        (1 << 8)
+
 struct virtio_net_config {
 	/* The config defining mac address (if VIRTIO_NET_F_MAC) */
 	uint8_t mac[ETH_ALEN];
@@ -92,6 +106,12 @@ struct virtio_net_config {
 	 * Any other value stands for unknown.
 	 */
 	uint8_t duplex;
+	/* maximum size of RSS key */
+	uint8_t rss_max_key_size;
+	/* maximum number of indirection table entries */
+	uint16_t rss_max_indirection_table_length;
+	/* bitmask of supported VIRTIO_NET_RSS_HASH_ types */
+	uint32_t supported_hash_types;
 } QEMU_PACKED;
 
 /*
@@ -104,6 +124,7 @@ struct virtio_net_config {
 struct virtio_net_hdr_v1 {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM	1	/* Use csum_start, csum_offset */
 #define VIRTIO_NET_HDR_F_DATA_VALID	2	/* Csum is valid */
+#define VIRTIO_NET_HDR_F_RSC_INFO	4	/* rsc info in csum_ fields */
 	uint8_t flags;
 #define VIRTIO_NET_HDR_GSO_NONE		0	/* Not a GSO frame */
 #define VIRTIO_NET_HDR_GSO_TCPV4	1	/* GSO frame, IPv4 TCP (TSO) */
@@ -113,11 +134,46 @@ struct virtio_net_hdr_v1 {
 	uint8_t gso_type;
 	__virtio16 hdr_len;	/* Ethernet + IP + tcp/udp hdrs */
 	__virtio16 gso_size;	/* Bytes to append to hdr_len per frame */
-	__virtio16 csum_start;	/* Position to start checksumming from */
-	__virtio16 csum_offset;	/* Offset after that to place checksum */
+	union {
+		struct {
+			__virtio16 csum_start;
+			__virtio16 csum_offset;
+		};
+		/* Checksum calculation */
+		struct {
+			/* Position to start checksumming from */
+			__virtio16 start;
+			/* Offset after that to place checksum */
+			__virtio16 offset;
+		} csum;
+		/* Receive Segment Coalescing */
+		struct {
+			/* Number of coalesced segments */
+			uint16_t segments;
+			/* Number of duplicated acks */
+			uint16_t dup_acks;
+		} rsc;
+	};
 	__virtio16 num_buffers;	/* Number of merged rx buffers */
 };
 
+struct virtio_net_hdr_v1_hash {
+	struct virtio_net_hdr_v1 hdr;
+	uint32_t hash_value;
+#define VIRTIO_NET_HASH_REPORT_NONE            0
+#define VIRTIO_NET_HASH_REPORT_IPv4            1
+#define VIRTIO_NET_HASH_REPORT_TCPv4           2
+#define VIRTIO_NET_HASH_REPORT_UDPv4           3
+#define VIRTIO_NET_HASH_REPORT_IPv6            4
+#define VIRTIO_NET_HASH_REPORT_TCPv6           5
+#define VIRTIO_NET_HASH_REPORT_UDPv6           6
+#define VIRTIO_NET_HASH_REPORT_IPv6_EX         7
+#define VIRTIO_NET_HASH_REPORT_TCPv6_EX        8
+#define VIRTIO_NET_HASH_REPORT_UDPv6_EX        9
+	uint16_t hash_report;
+	uint16_t padding;
+};
+
 #ifndef VIRTIO_NET_NO_LEGACY
 /* This header comes first in the scatter-gather list.
  * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must
@@ -228,7 +284,9 @@ struct virtio_net_ctrl_mac {
 
 /*
  * Control Receive Flow Steering
- *
+ */
+#define VIRTIO_NET_CTRL_MQ   4
+/*
  * The command VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET
  * enables Receive Flow Steering, specifying the number of the transmit and
  * receive queues that will be used. After the command is consumed and acked by
@@ -241,11 +299,47 @@ struct virtio_net_ctrl_mq {
 	__virtio16 virtqueue_pairs;
 };
 
-#define VIRTIO_NET_CTRL_MQ   4
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET        0
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN        1
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX        0x8000
 
+/*
+ * The command VIRTIO_NET_CTRL_MQ_RSS_CONFIG has the same effect as
+ * VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET does and additionally configures
+ * the receive steering to use a hash calculated for incoming packet
+ * to decide on receive virtqueue to place the packet. The command
+ * also provides parameters to calculate a hash and receive virtqueue.
+ */
+struct virtio_net_rss_config {
+	uint32_t hash_types;
+	uint16_t indirection_table_mask;
+	uint16_t unclassified_queue;
+	uint16_t indirection_table[1/* + indirection_table_mask */];
+	uint16_t max_tx_vq;
+	uint8_t hash_key_length;
+	uint8_t hash_key_data[/* hash_key_length */];
+};
+
+ #define VIRTIO_NET_CTRL_MQ_RSS_CONFIG          1
+
+/*
+ * The command VIRTIO_NET_CTRL_MQ_HASH_CONFIG requests the device
+ * to include in the virtio header of the packet the value of the
+ * calculated hash and the report type of hash. It also provides
+ * parameters for hash calculation. The command requires feature
+ * VIRTIO_NET_F_HASH_REPORT to be negotiated to extend the
+ * layout of virtio header as defined in virtio_net_hdr_v1_hash.
+ */
+struct virtio_net_hash_config {
+	uint32_t hash_types;
+	/* for compatibility with virtio_net_rss_config */
+	uint16_t reserved[4];
+	uint8_t hash_key_length;
+	uint8_t hash_key_data[/* hash_key_length */];
+};
+
+ #define VIRTIO_NET_CTRL_MQ_HASH_CONFIG         2
+
 /*
  * Control network offloads
  *

linux-headers/COPYING

@@ -16,3 +16,5 @@ In addition, other licenses may also apply. Please see:
 	Documentation/process/license-rules.rst
 
 for more details.
+
+All contributions to the Linux Kernel are subject to this COPYING file.

linux-headers/asm-x86/kvm.h

@@ -390,6 +390,7 @@ struct kvm_sync_regs {
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING	0x00000008
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002

linux-headers/asm-x86/unistd_32.h

@@ -429,4 +429,5 @@
 #define __NR_openat2 437
 #define __NR_pidfd_getfd 438
 
+
 #endif /* _ASM_X86_UNISTD_32_H */

linux-headers/asm-x86/unistd_64.h

@@ -351,4 +351,5 @@
 #define __NR_openat2 437
 #define __NR_pidfd_getfd 438
 
+
 #endif /* _ASM_X86_UNISTD_64_H */

linux-headers/asm-x86/unistd_x32.h

@@ -340,4 +340,5 @@
 #define __NR_preadv2 (__X32_SYSCALL_BIT + 546)
 #define __NR_pwritev2 (__X32_SYSCALL_BIT + 547)
 
+
 #endif /* _ASM_X86_UNISTD_X32_H */

linux-headers/linux/kvm.h

@@ -474,12 +474,17 @@ struct kvm_s390_mem_op {
 	__u32 size;		/* amount of bytes */
 	__u32 op;		/* type of operation */
 	__u64 buf;		/* buffer in userspace */
-	__u8 ar;		/* the access register number */
-	__u8 reserved[31];	/* should be set to 0 */
+	union {
+		__u8 ar;	/* the access register number */
+		__u32 sida_offset; /* offset into the sida */
+		__u8 reserved[32]; /* should be set to 0 */
+	};
 };
 /* types for kvm_s390_mem_op->op */
 #define KVM_S390_MEMOP_LOGICAL_READ	0
 #define KVM_S390_MEMOP_LOGICAL_WRITE	1
+#define KVM_S390_MEMOP_SIDA_READ	2
+#define KVM_S390_MEMOP_SIDA_WRITE	3
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
@@ -1010,6 +1015,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
 #define KVM_CAP_S390_VCPU_RESETS 179
+#define KVM_CAP_S390_PROTECTED 180
+#define KVM_CAP_PPC_SECURE_GUEST 181
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1478,6 +1485,39 @@ struct kvm_enc_region {
 #define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
 #define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
 
+struct kvm_s390_pv_sec_parm {
+	__u64 origin;
+	__u64 length;
+};
+
+struct kvm_s390_pv_unp {
+	__u64 addr;
+	__u64 size;
+	__u64 tweak;
+};
+
+enum pv_cmd_id {
+	KVM_PV_ENABLE,
+	KVM_PV_DISABLE,
+	KVM_PV_SET_SEC_PARMS,
+	KVM_PV_UNPACK,
+	KVM_PV_VERIFY,
+	KVM_PV_PREP_RESET,
+	KVM_PV_UNSHARE_ALL,
+};
+
+struct kvm_pv_cmd {
+	__u32 cmd;	/* Command to be executed */
+	__u16 rc;	/* Ultravisor return code */
+	__u16 rrc;	/* Ultravisor return reason code */
+	__u64 data;	/* Data or address */
+	__u32 flags;    /* flags for future extensions. Must be 0 for now */
+	__u32 reserved[3];
+};
+
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1628,4 +1668,7 @@ struct kvm_hyperv_eventfd {
 #define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
 #define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
 
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
+
 #endif /* __LINUX_KVM_H */

linux-headers/linux/mman.h

@@ -5,8 +5,9 @@
 #include <asm/mman.h>
 #include <asm-generic/hugetlb_encode.h>
 
-#define MREMAP_MAYMOVE	1
-#define MREMAP_FIXED	2
+#define MREMAP_MAYMOVE		1
+#define MREMAP_FIXED		2
+#define MREMAP_DONTUNMAP	4
 
 #define OVERCOMMIT_GUESS		0
 #define OVERCOMMIT_ALWAYS		1

linux-headers/linux/userfaultfd.h

@@ -19,7 +19,8 @@
  * means the userland is reading).
  */
 #define UFFD_API ((__u64)0xAA)
-#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |		\
+#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP |	\
+			   UFFD_FEATURE_EVENT_FORK |		\
 			   UFFD_FEATURE_EVENT_REMAP |		\
 			   UFFD_FEATURE_EVENT_REMOVE |	\
 			   UFFD_FEATURE_EVENT_UNMAP |		\
@@ -34,7 +35,8 @@
 #define UFFD_API_RANGE_IOCTLS			\
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
-	 (__u64)1 << _UFFDIO_ZEROPAGE)
+	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
+	 (__u64)1 << _UFFDIO_WRITEPROTECT)
 #define UFFD_API_RANGE_IOCTLS_BASIC		\
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY)
@@ -52,6 +54,7 @@
 #define _UFFDIO_WAKE			(0x02)
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_WRITEPROTECT		(0x06)
 #define _UFFDIO_API			(0x3F)
 
 /* userfaultfd ioctl ids */
@@ -68,6 +71,8 @@
 				      struct uffdio_copy)
 #define UFFDIO_ZEROPAGE		_IOWR(UFFDIO, _UFFDIO_ZEROPAGE,	\
 				      struct uffdio_zeropage)
+#define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
+				      struct uffdio_writeprotect)
 
 /* read() structure */
 struct uffd_msg {
@@ -203,13 +208,14 @@ struct uffdio_copy {
 	__u64 dst;
 	__u64 src;
 	__u64 len;
-	/*
-	 * There will be a wrprotection flag later that allows to map
-	 * pages wrprotected on the fly. And such a flag will be
-	 * available if the wrprotection ioctl are implemented for the
-	 * range according to the uffdio_register.ioctls.
-	 */
 #define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
+	/*
+	 * UFFDIO_COPY_MODE_WP will map the page write protected on
+	 * the fly.  UFFDIO_COPY_MODE_WP is available only if the
+	 * write protected ioctl is implemented for the range
+	 * according to the uffdio_register.ioctls.
+	 */
+#define UFFDIO_COPY_MODE_WP			((__u64)1<<1)
 	__u64 mode;
 
 	/*
@@ -231,4 +237,24 @@ struct uffdio_zeropage {
 	__s64 zeropage;
 };
 
+struct uffdio_writeprotect {
+	struct uffdio_range range;
+/*
+ * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range,
+ * unset the flag to undo protection of a range which was previously
+ * write protected.
+ *
+ * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up
+ * any wait thread after the operation succeeds.
+ *
+ * NOTE: Write protecting a region (WP=1) is unrelated to page faults,
+ * therefore DONTWAKE flag is meaningless with WP=1.  Removing write
+ * protection (WP=0) in response to a page fault wakes the faulting
+ * task unless DONTWAKE is set.
+ */
+#define UFFDIO_WRITEPROTECT_MODE_WP		((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE	((__u64)1<<1)
+	__u64 mode;
+};
+
 #endif /* _LINUX_USERFAULTFD_H */

linux-headers/linux/vfio.h

@@ -707,6 +707,43 @@ struct vfio_device_ioeventfd {
 
 #define VFIO_DEVICE_IOEVENTFD		_IO(VFIO_TYPE, VFIO_BASE + 16)
 
+/**
+ * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17,
+ *			       struct vfio_device_feature)
+ *
+ * Get, set, or probe feature data of the device.  The feature is selected
+ * using the FEATURE_MASK portion of the flags field.  Support for a feature
+ * can be probed by setting both the FEATURE_MASK and PROBE bits.  A probe
+ * may optionally include the GET and/or SET bits to determine read vs write
+ * access of the feature respectively.  Probing a feature will return success
+ * if the feature is supported and all of the optionally indicated GET/SET
+ * methods are supported.  The format of the data portion of the structure is
+ * specific to the given feature.  The data portion is not required for
+ * probing.  GET and SET are mutually exclusive, except for use with PROBE.
+ *
+ * Return 0 on success, -errno on failure.
+ */
+struct vfio_device_feature {
+	__u32	argsz;
+	__u32	flags;
+#define VFIO_DEVICE_FEATURE_MASK	(0xffff) /* 16-bit feature index */
+#define VFIO_DEVICE_FEATURE_GET		(1 << 16) /* Get feature into data[] */
+#define VFIO_DEVICE_FEATURE_SET		(1 << 17) /* Set feature from data[] */
+#define VFIO_DEVICE_FEATURE_PROBE	(1 << 18) /* Probe feature support */
+	__u8	data[];
+};
+
+#define VFIO_DEVICE_FEATURE		_IO(VFIO_TYPE, VFIO_BASE + 17)
+
+/*
+ * Provide support for setting a PCI VF Token, which is used as a shared
+ * secret between PF and VF drivers.  This feature may only be set on a
+ * PCI SR-IOV PF when SR-IOV is enabled on the PF and there are no existing
+ * open VFs.  Data provided when setting this feature is a 16-byte array
+ * (__u8 b[16]), representing a UUID.
+ */
+#define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN	(0)
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**

linux-headers/linux/vhost.h

@@ -116,4 +116,28 @@
 #define VHOST_VSOCK_SET_GUEST_CID	_IOW(VHOST_VIRTIO, 0x60, __u64)
 #define VHOST_VSOCK_SET_RUNNING		_IOW(VHOST_VIRTIO, 0x61, int)
 
+/* VHOST_VDPA specific defines */
+
+/* Get the device id. The device ids follow the same definition of
+ * the device id defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_DEVICE_ID	_IOR(VHOST_VIRTIO, 0x70, __u32)
+/* Get and set the status. The status bits follow the same definition
+ * of the device status defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_STATUS		_IOR(VHOST_VIRTIO, 0x71, __u8)
+#define VHOST_VDPA_SET_STATUS		_IOW(VHOST_VIRTIO, 0x72, __u8)
+/* Get and set the device config. The device config follows the same
+ * definition of the device config defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_CONFIG		_IOR(VHOST_VIRTIO, 0x73, \
+					     struct vhost_vdpa_config)
+#define VHOST_VDPA_SET_CONFIG		_IOW(VHOST_VIRTIO, 0x74, \
+					     struct vhost_vdpa_config)
+/* Enable/disable the ring. */
+#define VHOST_VDPA_SET_VRING_ENABLE	_IOW(VHOST_VIRTIO, 0x75, \
+					     struct vhost_vring_state)
+/* Get the max ring size. */
+#define VHOST_VDPA_GET_VRING_NUM	_IOR(VHOST_VIRTIO, 0x76, __u16)
+
 #endif

linux-user/flatload.c

@@ -37,7 +37,7 @@
 
 #include "qemu.h"
 #include "flat.h"
-#include <target_flat.h>
+#include "target_flat.h"
 
 //#define DEBUG
 

linux-user/ppc/signal.c

@@ -35,12 +35,26 @@ struct target_mcontext {
     target_ulong mc_gregs[48];
     /* Includes fpscr.  */
     uint64_t mc_fregs[33];
+
 #if defined(TARGET_PPC64)
     /* Pointer to the vector regs */
     target_ulong v_regs;
+    /*
+     * On ppc64, this mcontext structure is naturally *unaligned*,
+     * or rather it is aligned on a 8 bytes boundary but not on
+     * a 16 byte boundary.  This pad fixes it up.  This is why we
+     * cannot use ppc_avr_t, which would force alignment.  This is
+     * also why the vector regs are referenced in the ABI by the
+     * v_regs pointer above so any amount of padding can be added here.
+     */
+    target_ulong pad;
+    /* VSCR and VRSAVE are saved separately.  Also reserve space for VSX. */
+    struct {
+        uint64_t altivec[34 + 16][2];
+    } mc_vregs;
 #else
     target_ulong mc_pad[2];
-#endif
+
     /* We need to handle Altivec and SPE at the same time, which no
        kernel needs to do.  Fortunately, the kernel defines this bit to
        be Altivec-register-large all the time, rather than trying to
@@ -48,32 +62,14 @@ struct target_mcontext {
     union {
         /* SPE vector registers.  One extra for SPEFSCR.  */
         uint32_t spe[33];
-        /* Altivec vector registers.  The packing of VSCR and VRSAVE
-           varies depending on whether we're PPC64 or not: PPC64 splits
-           them apart; PPC32 stuffs them together.
-           We also need to account for the VSX registers on PPC64
-        */
-#if defined(TARGET_PPC64)
-#define QEMU_NVRREG (34 + 16)
-        /* On ppc64, this mcontext structure is naturally *unaligned*,
-         * or rather it is aligned on a 8 bytes boundary but not on
-         * a 16 bytes one. This pad fixes it up. This is also why the
-         * vector regs are referenced by the v_regs pointer above so
-         * any amount of padding can be added here
+        /*
+         * Altivec vector registers.  One extra for VRSAVE.
+         * On ppc32, we are already aligned to 16 bytes.  We could
+         * use ppc_avr_t, but choose to share the same type as ppc64.
          */
-        target_ulong pad;
-#else
-        /* On ppc32, we are already aligned to 16 bytes */
-#define QEMU_NVRREG 33
-#endif
-        /* We cannot use ppc_avr_t here as we do *not* want the implied
-         * 16-bytes alignment that would result from it. This would have
-         * the effect of making the whole struct target_mcontext aligned
-         * which breaks the layout of struct target_ucontext on ppc64.
-         */
-        uint64_t altivec[QEMU_NVRREG][2];
-#undef QEMU_NVRREG
+        uint64_t altivec[33][2];
     } mc_vregs;
+#endif
 };
 
 /* See arch/powerpc/include/asm/sigcontext.h.  */
@@ -278,6 +274,7 @@ static void save_user_regs(CPUPPCState *env, struct target_mcontext *frame)
         __put_user((uint32_t)env->spr[SPR_VRSAVE], vrsave);
     }
 
+#if defined(TARGET_PPC64)
     /* Save VSX second halves */
     if (env->insns_flags2 & PPC2_VSX) {
         uint64_t *vsregs = (uint64_t *)&frame->mc_vregs.altivec[34];
@@ -286,6 +283,7 @@ static void save_user_regs(CPUPPCState *env, struct target_mcontext *frame)
             __put_user(*vsrl, &vsregs[i]);
         }
     }
+#endif
 
     /* Save floating point registers.  */
     if (env->insns_flags & PPC_FLOAT) {
@@ -296,22 +294,18 @@ static void save_user_regs(CPUPPCState *env, struct target_mcontext *frame)
         __put_user((uint64_t) env->fpscr, &frame->mc_fregs[32]);
     }
 
+#if !defined(TARGET_PPC64)
     /* Save SPE registers.  The kernel only saves the high half.  */
     if (env->insns_flags & PPC_SPE) {
-#if defined(TARGET_PPC64)
-        for (i = 0; i < ARRAY_SIZE(env->gpr); i++) {
-            __put_user(env->gpr[i] >> 32, &frame->mc_vregs.spe[i]);
-        }
-#else
         for (i = 0; i < ARRAY_SIZE(env->gprh); i++) {
             __put_user(env->gprh[i], &frame->mc_vregs.spe[i]);
         }
-#endif
         /* Set MSR_SPE in the saved MSR value to indicate that
            frame->mc_vregs contains valid data.  */
         msr |= MSR_SPE;
         __put_user(env->spe_fscr, &frame->mc_vregs.spe[32]);
     }
+#endif
 
     /* Store MSR.  */
     __put_user(msr, &frame->mc_gregs[TARGET_PT_MSR]);
@@ -392,6 +386,7 @@ static void restore_user_regs(CPUPPCState *env,
         __get_user(env->spr[SPR_VRSAVE], vrsave);
     }
 
+#if defined(TARGET_PPC64)
     /* Restore VSX second halves */
     if (env->insns_flags2 & PPC2_VSX) {
         uint64_t *vsregs = (uint64_t *)&frame->mc_vregs.altivec[34];
@@ -400,6 +395,7 @@ static void restore_user_regs(CPUPPCState *env,
             __get_user(*vsrl, &vsregs[i]);
         }
     }
+#endif
 
     /* Restore floating point registers.  */
     if (env->insns_flags & PPC_FLOAT) {
@@ -412,22 +408,15 @@ static void restore_user_regs(CPUPPCState *env,
         env->fpscr = (uint32_t) fpscr;
     }
 
+#if !defined(TARGET_PPC64)
     /* Save SPE registers.  The kernel only saves the high half.  */
     if (env->insns_flags & PPC_SPE) {
-#if defined(TARGET_PPC64)
-        for (i = 0; i < ARRAY_SIZE(env->gpr); i++) {
-            uint32_t hi;
-
-            __get_user(hi, &frame->mc_vregs.spe[i]);
-            env->gpr[i] = ((uint64_t)hi << 32) | ((uint32_t) env->gpr[i]);
-        }
-#else
         for (i = 0; i < ARRAY_SIZE(env->gprh); i++) {
             __get_user(env->gprh[i], &frame->mc_vregs.spe[i]);
         }
-#endif
         __get_user(env->spe_fscr, &frame->mc_vregs.spe[32]);
     }
+#endif
 }
 
 #if !defined(TARGET_PPC64)

linux-user/strace.list

@@ -125,10 +125,10 @@
 { TARGET_NR_dup3, "dup3" , "%s(%d,%d,%d)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_epoll_create
-{ TARGET_NR_epoll_create, "%s(%d)", NULL, NULL, NULL },
+{ TARGET_NR_epoll_create, "epoll_create", "%s(%d)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_epoll_create1
-{ TARGET_NR_epoll_create1, "%s(%d)", NULL, NULL, NULL },
+{ TARGET_NR_epoll_create1, "epoll_create1", "%s(%d)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_epoll_ctl
 { TARGET_NR_epoll_ctl, "epoll_ctl" , NULL, NULL, NULL },

linux-user/syscall.c

@@ -7295,34 +7295,29 @@ static int open_self_stat(void *cpu_env, int fd)
 {
     CPUState *cpu = env_cpu((CPUArchState *)cpu_env);
     TaskState *ts = cpu->opaque;
-    abi_ulong start_stack = ts->info->start_stack;
+    g_autoptr(GString) buf = g_string_new(NULL);
     int i;
 
     for (i = 0; i < 44; i++) {
-      char buf[128];
-      int len;
-      uint64_t val = 0;
+        if (i == 0) {
+            /* pid */
+            g_string_printf(buf, FMT_pid " ", getpid());
+        } else if (i == 1) {
+            /* app name */
+            gchar *bin = g_strrstr(ts->bprm->argv[0], "/");
+            bin = bin ? bin + 1 : ts->bprm->argv[0];
+            g_string_printf(buf, "(%.15s) ", bin);
+        } else if (i == 27) {
+            /* stack bottom */
+            g_string_printf(buf, TARGET_ABI_FMT_ld " ", ts->info->start_stack);
+        } else {
+            /* for the rest, there is MasterCard */
+            g_string_printf(buf, "0%c", i == 43 ? '\n' : ' ');
+        }
 
-      if (i == 0) {
-        /* pid */
-        val = getpid();
-        snprintf(buf, sizeof(buf), "%"PRId64 " ", val);
-      } else if (i == 1) {
-        /* app name */
-        snprintf(buf, sizeof(buf), "(%s) ", ts->bprm->argv[0]);
-      } else if (i == 27) {
-        /* stack bottom */
-        val = start_stack;
-        snprintf(buf, sizeof(buf), "%"PRId64 " ", val);
-      } else {
-        /* for the rest, there is MasterCard */
-        snprintf(buf, sizeof(buf), "0%c", i == 43 ? '\n' : ' ');
-      }
-
-      len = strlen(buf);
-      if (write(fd, buf, len) != len) {
-          return -1;
-      }
+        if (write(fd, buf->str, buf->len) != buf->len) {
+            return -1;
+        }
     }
 
     return 0;
@@ -12017,7 +12012,7 @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1,
 #endif
 #if defined(TARGET_NR_epoll_create1) && defined(CONFIG_EPOLL_CREATE1)
     case TARGET_NR_epoll_create1:
-        return get_errno(epoll_create1(arg1));
+        return get_errno(epoll_create1(target_to_host_bitmask(arg1, fcntl_flags_tbl)));
 #endif
 #if defined(TARGET_NR_epoll_ctl)
     case TARGET_NR_epoll_ctl:

memory.c

@@ -1352,35 +1352,24 @@ bool memory_region_access_valid(MemoryRegion *mr,
                                 bool is_write,
                                 MemTxAttrs attrs)
 {
-    int access_size_min, access_size_max;
-    int access_size, i;
+    if (mr->ops->valid.accepts
+        && !mr->ops->valid.accepts(mr->opaque, addr, size, is_write, attrs)) {
+        return false;
+    }
 
     if (!mr->ops->valid.unaligned && (addr & (size - 1))) {
         return false;
     }
 
-    if (!mr->ops->valid.accepts) {
+    /* Treat zero as compatibility all valid */
+    if (!mr->ops->valid.max_access_size) {
         return true;
     }
 
-    access_size_min = mr->ops->valid.min_access_size;
-    if (!mr->ops->valid.min_access_size) {
-        access_size_min = 1;
+    if (size > mr->ops->valid.max_access_size
+        || size < mr->ops->valid.min_access_size) {
+        return false;
     }
-
-    access_size_max = mr->ops->valid.max_access_size;
-    if (!mr->ops->valid.max_access_size) {
-        access_size_max = 4;
-    }
-
-    access_size = MAX(MIN(size, access_size_max), access_size_min);
-    for (i = 0; i < size; i += access_size) {
-        if (!mr->ops->valid.accepts(mr->opaque, addr + i, access_size,
-                                    is_write, attrs)) {
-            return false;
-        }
-    }
-
     return true;
 }
 

migration/block-dirty-bitmap.c

@@ -498,7 +498,7 @@ void dirty_bitmap_mig_before_vm_start(void)
         DirtyBitmapLoadBitmapState *b = item->data;
 
         if (b->migrated) {
-            bdrv_enable_dirty_bitmap_locked(b->bitmap);
+            bdrv_enable_dirty_bitmap(b->bitmap);
         } else {
             bdrv_dirty_bitmap_enable_successor(b->bitmap);
         }

nbd/server.c

@@ -217,7 +217,7 @@ nbd_negotiate_send_rep_verr(NBDClient *client, uint32_t type,
 
     msg = g_strdup_vprintf(fmt, va);
     len = strlen(msg);
-    assert(len < 4096);
+    assert(len < NBD_MAX_STRING_SIZE);
     trace_nbd_negotiate_send_rep_err(msg);
     ret = nbd_negotiate_send_rep_len(client, type, len, errp);
     if (ret < 0) {
@@ -231,6 +231,19 @@ nbd_negotiate_send_rep_verr(NBDClient *client, uint32_t type,
     return 0;
 }
 
+/*
+ * Return a malloc'd copy of @name suitable for use in an error reply.
+ */
+static char *
+nbd_sanitize_name(const char *name)
+{
+    if (strnlen(name, 80) < 80) {
+        return g_strdup(name);
+    }
+    /* XXX Should we also try to sanitize any control characters? */
+    return g_strdup_printf("%.80s...", name);
+}
+
 /* Send an error reply.
  * Return -errno on error, 0 on success. */
 static int GCC_FMT_ATTR(4, 5)
@@ -595,9 +608,11 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp)
 
     exp = nbd_export_find(name);
     if (!exp) {
+        g_autofree char *sane_name = nbd_sanitize_name(name);
+
         return nbd_negotiate_send_rep_err(client, NBD_REP_ERR_UNKNOWN,
                                           errp, "export '%s' not present",
-                                          name);
+                                          sane_name);
     }
 
     /* Don't bother sending NBD_INFO_NAME unless client requested it */
@@ -995,8 +1010,10 @@ static int nbd_negotiate_meta_queries(NBDClient *client,
 
     meta->exp = nbd_export_find(export_name);
     if (meta->exp == NULL) {
+        g_autofree char *sane_name = nbd_sanitize_name(export_name);
+
         return nbd_opt_drop(client, NBD_REP_ERR_UNKNOWN, errp,
-                            "export '%s' not present", export_name);
+                            "export '%s' not present", sane_name);
     }
 
     ret = nbd_opt_read(client, &nb_queries, sizeof(nb_queries), errp);
@@ -2348,8 +2365,17 @@ static coroutine_fn int nbd_handle_request(NBDClient *client,
         if (request->flags & NBD_CMD_FLAG_FAST_ZERO) {
             flags |= BDRV_REQ_NO_FALLBACK;
         }
-        ret = blk_pwrite_zeroes(exp->blk, request->from + exp->dev_offset,
-                                request->len, flags);
+        ret = 0;
+        /* FIXME simplify this when blk_pwrite_zeroes switches to 64-bit */
+        while (ret >= 0 && request->len) {
+            int align = client->check_align ?: 1;
+            int len = MIN(request->len, QEMU_ALIGN_DOWN(BDRV_REQUEST_MAX_BYTES,
+                                                        align));
+            ret = blk_pwrite_zeroes(exp->blk, request->from + exp->dev_offset,
+                                    len, flags);
+            request->len -= len;
+            request->from += len;
+        }
         return nbd_send_generic_reply(client, request->handle, ret,
                                       "writing to file failed", errp);
 
@@ -2363,9 +2389,18 @@ static coroutine_fn int nbd_handle_request(NBDClient *client,
                                       "flush failed", errp);
 
     case NBD_CMD_TRIM:
-        ret = blk_co_pdiscard(exp->blk, request->from + exp->dev_offset,
-                              request->len);
-        if (ret == 0 && request->flags & NBD_CMD_FLAG_FUA) {
+        ret = 0;
+        /* FIXME simplify this when blk_co_pdiscard switches to 64-bit */
+        while (ret >= 0 && request->len) {
+            int align = client->check_align ?: 1;
+            int len = MIN(request->len, QEMU_ALIGN_DOWN(BDRV_REQUEST_MAX_BYTES,
+                                                        align));
+            ret = blk_co_pdiscard(exp->blk, request->from + exp->dev_offset,
+                                  len);
+            request->len -= len;
+            request->from += len;
+        }
+        if (ret >= 0 && request->flags & NBD_CMD_FLAG_FUA) {
             ret = blk_co_flush(exp->blk);
         }
         return nbd_send_generic_reply(client, request->handle, ret,

net/net.c

@@ -610,7 +610,7 @@ void qemu_flush_or_purge_queued_packets(NetClientState *nc, bool purge)
         qemu_notify_event();
     } else if (purge) {
         /* Unable to empty the queue, purge remaining packets */
-        qemu_net_queue_purge(nc->incoming_queue, nc);
+        qemu_net_queue_purge(nc->incoming_queue, nc->peer);
     }
 }
 
@@ -1506,7 +1506,7 @@ static int net_param_nic(void *dummy, QemuOpts *opts, Error **errp)
     /* Create an ID if the user did not specify one */
     nd_id = g_strdup(qemu_opts_id(opts));
     if (!nd_id) {
-        nd_id = g_strdup_printf("__org.qemu.nic%i\n", idx);
+        nd_id = g_strdup_printf("__org.qemu.nic%i", idx);
         qemu_opts_set_id(opts, nd_id);
     }