Update version for 7.2.10 release

Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>

.gitlab-ci.d/buildtest.yml

@@ -109,8 +109,8 @@ crash-test-debian:
     IMAGE: debian-amd64
   script:
     - cd build
-    - make check-venv
-    - tests/venv/bin/python3 scripts/device-crash-test -q ./qemu-system-i386
+    - make NINJA=":" check-venv
+    - tests/venv/bin/python3 scripts/device-crash-test -q --tcg-only ./qemu-system-i386
 
 build-system-fedora:
   extends: .native_build_job_template
@@ -155,7 +155,7 @@ crash-test-fedora:
     IMAGE: fedora
   script:
     - cd build
-    - make check-venv
+    - make NINJA=":" check-venv
     - tests/venv/bin/python3 scripts/device-crash-test -q ./qemu-system-ppc
     - tests/venv/bin/python3 scripts/device-crash-test -q ./qemu-system-riscv32
 
@@ -637,7 +637,10 @@ pages:
     - mkdir -p public
     # HTML-ised source tree
     - make gtags
-    - htags -anT --tree-view=filetree -m qemu_init
+    # We unset variables to work around a bug in some htags versions
+    # which causes it to fail when the environment is large
+    - CI_COMMIT_MESSAGE= CI_COMMIT_TAG_MESSAGE= htags
+        -anT --tree-view=filetree -m qemu_init
         -t "Welcome to the QEMU sourcecode"
     - mv HTML public/src
     # Project documentation

.gitlab-ci.d/check-dco.py

@@ -20,12 +20,12 @@ reponame = os.path.basename(cwd)
 repourl = "https://gitlab.com/%s/%s.git" % (namespace, reponame)
 
 subprocess.check_call(["git", "remote", "add", "check-dco", repourl])
-subprocess.check_call(["git", "fetch", "check-dco", "master"],
+subprocess.check_call(["git", "fetch", "check-dco", "stable-7.2"],
                       stdout=subprocess.DEVNULL,
                       stderr=subprocess.DEVNULL)
 
 ancestor = subprocess.check_output(["git", "merge-base",
-                                    "check-dco/master", "HEAD"],
+                                    "check-dco/stable-7.2", "HEAD"],
                                    universal_newlines=True)
 
 ancestor = ancestor.strip()
@@ -85,7 +85,7 @@ This can be achieved by passing the "-s" flag to the "git commit" command.
 
 To bulk update all commits on current branch "git rebase" can be used:
 
-  git rebase -i master -x 'git commit --amend --no-edit -s'
+  git rebase -i stable-7.2 -x 'git commit --amend --no-edit -s'
 
 """)
 

.gitlab-ci.d/cirrus/build.yml

@@ -19,7 +19,7 @@ build_task:
   install_script:
     - @UPDATE_COMMAND@
     - @INSTALL_COMMAND@ @PKGS@
-    - if test -n "@PYPI_PKGS@" ; then @PIP3@ install @PYPI_PKGS@ ; fi
+    - if test -n "@PYPI_PKGS@" ; then PYLIB=$(@PYTHON@ -c 'import sysconfig; print(sysconfig.get_path("stdlib"))'); rm -f $PYLIB/EXTERNALLY-MANAGED; @PIP3@ install @PYPI_PKGS@ ; fi
   clone_script:
     - git clone --depth 100 "$CI_REPOSITORY_URL" .
     - git fetch origin "$CI_COMMIT_REF_NAME"

.gitlab-ci.d/static_checks.yml

@@ -23,12 +23,12 @@ check-dco:
   before_script:
     - apk -U add git
 
-check-python-pipenv:
+check-python-minreqs:
   extends: .base_job_template
   stage: test
   image: $CI_REGISTRY_IMAGE/qemu/python:latest
   script:
-    - make -C python check-pipenv
+    - make -C python check-minreqs
   variables:
     GIT_DEPTH: 1
   needs:

.gitlab-ci.d/windows.yml

@@ -63,37 +63,3 @@ msys2-64bit:
       --enable-capstone --without-default-devices'
   - .\msys64\usr\bin\bash -lc 'make'
   - .\msys64\usr\bin\bash -lc 'make check || { cat build/meson-logs/testlog.txt; exit 1; } ;'
-
-msys2-32bit:
-  extends: .shared_msys2_builder
-  script:
-  - .\msys64\usr\bin\bash -lc "pacman -Sy --noconfirm --needed
-      bison diffutils flex
-      git grep make sed
-      mingw-w64-i686-capstone
-      mingw-w64-i686-curl
-      mingw-w64-i686-cyrus-sasl
-      mingw-w64-i686-gcc
-      mingw-w64-i686-glib2
-      mingw-w64-i686-gnutls
-      mingw-w64-i686-gtk3
-      mingw-w64-i686-libgcrypt
-      mingw-w64-i686-libjpeg-turbo
-      mingw-w64-i686-libssh
-      mingw-w64-i686-libtasn1
-      mingw-w64-i686-libusb
-      mingw-w64-i686-lzo2
-      mingw-w64-i686-ninja
-      mingw-w64-i686-pixman
-      mingw-w64-i686-pkgconf
-      mingw-w64-i686-python
-      mingw-w64-i686-snappy
-      mingw-w64-i686-usbredir "
-  - $env:CHERE_INVOKING = 'yes'  # Preserve the current working directory
-  - $env:MSYSTEM = 'MINGW32'     # Start a 32-bit MinG environment
-  - $env:MSYS = 'winsymlinks:native' # Enable native Windows symlink
-  - mkdir output
-  - cd output
-  - ..\msys64\usr\bin\bash -lc "../configure --target-list=ppc64-softmmu"
-  - ..\msys64\usr\bin\bash -lc 'make'
-  - ..\msys64\usr\bin\bash -lc 'make check || { cat meson-logs/testlog.txt; exit 1; } ;'

.readthedocs.yml

@@ -5,16 +5,21 @@
 # Required
 version: 2
 
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
   configuration: docs/conf.py
 
+# We recommend specifying your dependencies to enable reproducible builds:
+# https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+    - requirements: docs/requirements.txt
+
 # We want all the document formats
 formats: all
-
-# For consistency, we require that QEMU's Sphinx extensions
-# run with at least the same minimum version of Python that
-# we require for other Python in our codebase (our conf.py
-# enforces this, and some code needs it.)
-python:
-  version: 3.6

VERSION

@@ -1 +1 @@
-7.2.2
+7.2.10

accel/kvm/kvm-all.c

@@ -2294,7 +2294,7 @@ static int kvm_init(MachineState *ms)
     KVMState *s;
     const KVMCapabilityInfo *missing_cap;
     int ret;
-    int type = 0;
+    int type;
     uint64_t dirty_log_manual_caps;
 
     qemu_mutex_init(&kml_slots_lock);
@@ -2358,6 +2358,8 @@ static int kvm_init(MachineState *ms)
         type = mc->kvm_type(ms, kvm_type);
     } else if (mc->kvm_type) {
         type = mc->kvm_type(ms, NULL);
+    } else {
+        type = kvm_arch_get_default_type(ms);
     }
 
     do {

accel/tcg/cpu-exec.c

@@ -186,7 +186,7 @@ static bool tb_lookup_cmp(const void *p, const void *d)
     const TranslationBlock *tb = p;
     const struct tb_desc *desc = d;
 
-    if ((TARGET_TB_PCREL || tb_pc(tb) == desc->pc) &&
+    if (tb_pc(tb) == desc->pc &&
         tb_page_addr0(tb) == desc->page_addr0 &&
         tb->cs_base == desc->cs_base &&
         tb->flags == desc->flags &&
@@ -238,7 +238,7 @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
         return NULL;
     }
     desc.page_addr0 = phys_pc;
-    h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : pc),
+    h = tb_hash_func(phys_pc, pc,
                      flags, cflags, *cpu->trace_dstate);
     return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
 }

accel/tcg/cputlb.c

@@ -1817,7 +1817,7 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
     } else /* if (prot & PAGE_READ) */ {
         tlb_addr = tlbe->addr_read;
         if (!tlb_hit(tlb_addr, addr)) {
-            if (!VICTIM_TLB_HIT(addr_write, addr)) {
+            if (!VICTIM_TLB_HIT(addr_read, addr)) {
                 tlb_fill(env_cpu(env), addr, size,
                          MMU_DATA_LOAD, mmu_idx, retaddr);
                 index = tlb_index(env, mmu_idx, addr);

accel/tcg/tb-maint.c

@@ -34,7 +34,7 @@ static bool tb_cmp(const void *ap, const void *bp)
     const TranslationBlock *a = ap;
     const TranslationBlock *b = bp;
 
-    return ((TARGET_TB_PCREL || tb_pc(a) == tb_pc(b)) &&
+    return (tb_pc(a) == tb_pc(b) &&
             a->cs_base == b->cs_base &&
             a->flags == b->flags &&
             (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) &&
@@ -269,7 +269,7 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)
 
     /* remove the TB from the hash list */
     phys_pc = tb_page_addr0(tb);
-    h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)),
+    h = tb_hash_func(phys_pc, tb_pc(tb),
                      tb->flags, orig_cflags, tb->trace_vcpu_dstate);
     if (!qht_remove(&tb_ctx.htable, tb, h)) {
         return;
@@ -459,7 +459,7 @@ TranslationBlock *tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
     }
 
     /* add in the hash table */
-    h = tb_hash_func(phys_pc, (TARGET_TB_PCREL ? 0 : tb_pc(tb)),
+    h = tb_hash_func(phys_pc, tb_pc(tb),
                      tb->flags, tb->cflags, tb->trace_vcpu_dstate);
     qht_insert(&tb_ctx.htable, tb, h, &existing_tb);
 

accel/tcg/tcg-accel-ops-mttcg.c

@@ -100,14 +100,9 @@ static void *mttcg_cpu_thread_fn(void *arg)
                 break;
             case EXCP_HALTED:
                 /*
-                 * during start-up the vCPU is reset and the thread is
-                 * kicked several times. If we don't ensure we go back
-                 * to sleep in the halted state we won't cleanly
-                 * start-up when the vCPU is enabled.
-                 *
-                 * cpu->halted should ensure we sleep in wait_io_event
+                 * Usually cpu->halted is set, but may have already been
+                 * reset by another thread by the time we arrive here.
                  */
-                g_assert(cpu->halted);
                 break;
             case EXCP_ATOMIC:
                 qemu_mutex_unlock_iothread();

accel/tcg/translate-all.c

@@ -818,9 +818,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
 
     gen_code_buf = tcg_ctx->code_gen_ptr;
     tb->tc.ptr = tcg_splitwx_to_rx(gen_code_buf);
-#if !TARGET_TB_PCREL
     tb->pc = pc;
-#endif
     tb->cs_base = cs_base;
     tb->flags = flags;
     tb->cflags = cflags;

audio/meson.build

@@ -29,7 +29,8 @@ endforeach
 
 if dbus_display
     module_ss = ss.source_set()
-    module_ss.add(when: gio, if_true: files('dbusaudio.c'))
+    module_ss.add(when: [gio, dbus_display1_dep],
+                  if_true: files('dbusaudio.c'))
     audio_modules += {'dbus': module_ss}
 endif
 

backends/tpm/tpm_util.c

@@ -112,12 +112,8 @@ static int tpm_util_request(int fd,
                             void *response,
                             size_t responselen)
 {
-    fd_set readfds;
+    GPollFD fds[1] = { {.fd = fd, .events = G_IO_IN } };
     int n;
-    struct timeval tv = {
-        .tv_sec = 1,
-        .tv_usec = 0,
-    };
 
     n = write(fd, request, requestlen);
     if (n < 0) {
@@ -127,11 +123,8 @@ static int tpm_util_request(int fd,
         return -EFAULT;
     }
 
-    FD_ZERO(&readfds);
-    FD_SET(fd, &readfds);
-
     /* wait for a second */
-    n = select(fd + 1, &readfds, NULL, NULL, &tv);
+    TFR(n = g_poll(fds, 1, 1000));
     if (n != 1) {
         return -errno;
     }

block/blkio.c

@@ -74,7 +74,7 @@ typedef struct {
     CoQueue bounce_available;
 
     /* The value of the "mem-region-alignment" property */
-    size_t mem_region_alignment;
+    uint64_t mem_region_alignment;
 
     /* Can we skip adding/deleting blkio_mem_regions? */
     bool needs_mem_regions;

block/blklogwrites.c

@@ -321,22 +321,39 @@ typedef struct {
 static void coroutine_fn blk_log_writes_co_do_log(BlkLogWritesLogReq *lr)
 {
     BDRVBlkLogWritesState *s = lr->bs->opaque;
-    uint64_t cur_log_offset = s->cur_log_sector << s->sectorbits;
+
+    /*
+     * Determine the offsets and sizes of different parts of the entry, and
+     * update the state of the driver.
+     *
+     * This needs to be done in one go, before any actual I/O is done, as the
+     * log entry may have to be written in two parts, and the state of the
+     * driver may be modified by other driver operations while waiting for the
+     * I/O to complete.
+     */
+    const uint64_t entry_start_sector = s->cur_log_sector;
+    const uint64_t entry_offset = entry_start_sector << s->sectorbits;
+    const uint64_t qiov_aligned_size = ROUND_UP(lr->qiov->size, s->sectorsize);
+    const uint64_t entry_aligned_size = qiov_aligned_size +
+        ROUND_UP(lr->zero_size, s->sectorsize);
+    const uint64_t entry_nr_sectors = entry_aligned_size >> s->sectorbits;
 
     s->nr_entries++;
-    s->cur_log_sector +=
-            ROUND_UP(lr->qiov->size, s->sectorsize) >> s->sectorbits;
+    s->cur_log_sector += entry_nr_sectors;
 
-    lr->log_ret = bdrv_co_pwritev(s->log_file, cur_log_offset, lr->qiov->size,
+    /*
+     * Write the log entry. Note that if this is a "write zeroes" operation,
+     * only the entry header is written here, with the zeroing being done
+     * separately below.
+     */
+    lr->log_ret = bdrv_co_pwritev(s->log_file, entry_offset, lr->qiov->size,
                                   lr->qiov, 0);
 
     /* Logging for the "write zeroes" operation */
     if (lr->log_ret == 0 && lr->zero_size) {
-        cur_log_offset = s->cur_log_sector << s->sectorbits;
-        s->cur_log_sector +=
-                ROUND_UP(lr->zero_size, s->sectorsize) >> s->sectorbits;
+        const uint64_t zeroes_offset = entry_offset + qiov_aligned_size;
 
-        lr->log_ret = bdrv_co_pwrite_zeroes(s->log_file, cur_log_offset,
+        lr->log_ret = bdrv_co_pwrite_zeroes(s->log_file, zeroes_offset,
                                             lr->zero_size, 0);
     }
 

block/io.c

@@ -2595,6 +2595,16 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
                 ret |= (ret2 & BDRV_BLOCK_ZERO);
             }
         }
+
+        /*
+         * Now that the recursive search was done, clear the flag. Otherwise,
+         * with more complicated block graphs like snapshot-access ->
+         * copy-before-write -> qcow2, where the return value will be propagated
+         * further up to a parent bdrv_co_do_block_status() call, both the
+         * BDRV_BLOCK_RECURSE and BDRV_BLOCK_ZERO flags would be set, which is
+         * not allowed.
+         */
+        ret &= ~BDRV_BLOCK_RECURSE;
     }
 
 out:

block/monitor/block-hmp-cmds.c

@@ -213,15 +213,17 @@ void hmp_commit(Monitor *mon, const QDict *qdict)
             error_report("Device '%s' not found", device);
             return;
         }
-        if (!blk_is_available(blk)) {
-            error_report("Device '%s' has no medium", device);
-            return;
-        }
 
         bs = bdrv_skip_implicit_filters(blk_bs(blk));
         aio_context = bdrv_get_aio_context(bs);
         aio_context_acquire(aio_context);
 
+        if (!blk_is_available(blk)) {
+            error_report("Device '%s' has no medium", device);
+            aio_context_release(aio_context);
+            return;
+        }
+
         ret = bdrv_commit(bs);
 
         aio_context_release(aio_context);

block/nvme.c

@@ -419,9 +419,10 @@ static bool nvme_process_completion(NVMeQueuePair *q)
             q->cq_phase = !q->cq_phase;
         }
         cid = le16_to_cpu(c->cid);
-        if (cid == 0 || cid > NVME_QUEUE_SIZE) {
-            warn_report("NVMe: Unexpected CID in completion queue: %"PRIu32", "
-                        "queue size: %u", cid, NVME_QUEUE_SIZE);
+        if (cid == 0 || cid > NVME_NUM_REQS) {
+            warn_report("NVMe: Unexpected CID in completion queue: %" PRIu32
+                        ", should be within: 1..%u inclusively", cid,
+                        NVME_NUM_REQS);
             continue;
         }
         trace_nvme_complete_command(s, q->index, cid);

block/snapshot.c

@@ -190,8 +190,10 @@ static BlockDriverState *bdrv_snapshot_fallback(BlockDriverState *bs)
 int bdrv_can_snapshot(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
+
     GLOBAL_STATE_CODE();
-    if (!drv || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
+
+    if (!drv || !bdrv_is_inserted(bs) || !bdrv_is_writable(bs)) {
         return 0;
     }
 

block/vmdk.c

@@ -346,29 +346,41 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
     BDRVVmdkState *s = bs->opaque;
     int ret = 0;
 
-    desc = g_malloc0(DESC_SIZE);
-    tmp_desc = g_malloc0(DESC_SIZE);
-    ret = bdrv_pread(bs->file, s->desc_offset, DESC_SIZE, desc, 0);
+    size_t desc_buf_size;
+
+    if (s->desc_offset == 0) {
+        desc_buf_size = bdrv_getlength(bs->file->bs);
+        if (desc_buf_size > 16ULL << 20) {
+            error_report("VMDK description file too big");
+            return -EFBIG;
+        }
+    } else {
+        desc_buf_size = DESC_SIZE;
+    }
+
+    desc = g_malloc0(desc_buf_size);
+    tmp_desc = g_malloc0(desc_buf_size);
+    ret = bdrv_pread(bs->file, s->desc_offset, desc_buf_size, desc, 0);
     if (ret < 0) {
         goto out;
     }
 
-    desc[DESC_SIZE - 1] = '\0';
+    desc[desc_buf_size - 1] = '\0';
     tmp_str = strstr(desc, "parentCID");
     if (tmp_str == NULL) {
         ret = -EINVAL;
         goto out;
     }
 
-    pstrcpy(tmp_desc, DESC_SIZE, tmp_str);
+    pstrcpy(tmp_desc, desc_buf_size, tmp_str);
     p_name = strstr(desc, "CID");
     if (p_name != NULL) {
         p_name += sizeof("CID");
-        snprintf(p_name, DESC_SIZE - (p_name - desc), "%" PRIx32 "\n", cid);
-        pstrcat(desc, DESC_SIZE, tmp_desc);
+        snprintf(p_name, desc_buf_size - (p_name - desc), "%" PRIx32 "\n", cid);
+        pstrcat(desc, desc_buf_size, tmp_desc);
     }
 
-    ret = bdrv_pwrite_sync(bs->file, s->desc_offset, DESC_SIZE, desc, 0);
+    ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc_buf_size, desc, 0);
 
 out:
     g_free(desc);

blockdev.c

@@ -152,12 +152,22 @@ void blockdev_mark_auto_del(BlockBackend *blk)
 
     JOB_LOCK_GUARD();
 
-    for (job = block_job_next_locked(NULL); job;
-         job = block_job_next_locked(job)) {
-        if (block_job_has_bdrv(job, blk_bs(blk))) {
+    do {
+        job = block_job_next_locked(NULL);
+        while (job && (job->job.cancelled ||
+                       job->job.deferred_to_main_loop ||
+                       !block_job_has_bdrv(job, blk_bs(blk))))
+        {
+            job = block_job_next_locked(job);
+        }
+        if (job) {
+            /*
+             * This drops the job lock temporarily and polls, so we need to
+             * restart processing the list from the start after this.
+             */
             job_cancel_locked(&job->job, false);
         }
-    }
+    } while (job);
 
     dinfo->auto_del = 1;
 }

chardev/char-pty.c

@@ -108,11 +108,27 @@ static void pty_chr_update_read_handler(Chardev *chr)
 static int char_pty_chr_write(Chardev *chr, const uint8_t *buf, int len)
 {
     PtyChardev *s = PTY_CHARDEV(chr);
+    GPollFD pfd;
+    int rc;
 
-    if (!s->connected) {
-        return len;
+    if (s->connected) {
+        return io_channel_send(s->ioc, buf, len);
     }
-    return io_channel_send(s->ioc, buf, len);
+
+    /*
+     * The other side might already be re-connected, but the timer might
+     * not have fired yet. So let's check here whether we can write again:
+     */
+    pfd.fd = QIO_CHANNEL_FILE(s->ioc)->fd;
+    pfd.events = G_IO_OUT;
+    pfd.revents = 0;
+    TFR(rc = g_poll(&pfd, 1, 0));
+    g_assert(rc >= 0);
+    if (!(pfd.revents & G_IO_HUP) && (pfd.revents & G_IO_OUT)) {
+        io_channel_send(s->ioc, buf, len);
+    }
+
+    return len;
 }
 
 static GSource *pty_chr_add_watch(Chardev *chr, GIOCondition cond)

chardev/char.c

@@ -519,7 +519,7 @@ static const ChardevClass *char_get_class(const char *driver, Error **errp)
 
     if (object_class_is_abstract(oc)) {
         error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "driver",
-                   "an abstract device type");
+                   "a non-abstract device type");
         return NULL;
     }
 

disas/riscv.c

@@ -2173,8 +2173,8 @@ static const char *csr_name(int csrno)
     case 0x03ba: return "pmpaddr10";
     case 0x03bb: return "pmpaddr11";
     case 0x03bc: return "pmpaddr12";
-    case 0x03bd: return "pmpaddr14";
-    case 0x03be: return "pmpaddr13";
+    case 0x03bd: return "pmpaddr13";
+    case 0x03be: return "pmpaddr14";
     case 0x03bf: return "pmpaddr15";
     case 0x0780: return "mtohost";
     case 0x0781: return "mfromhost";

docs/about/deprecated.rst

@@ -233,8 +233,8 @@ Use the more generic event ``DEVICE_UNPLUG_GUEST_ERROR`` instead.
 System emulator machines
 ------------------------
 
-Arm ``virt`` machine ``dtb-kaslr-seed`` property
-''''''''''''''''''''''''''''''''''''''''''''''''
+Arm ``virt`` machine ``dtb-kaslr-seed`` property (since 7.1)
+''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''
 
 The ``dtb-kaslr-seed`` property on the ``virt`` board has been
 deprecated; use the new name ``dtb-randomness`` instead. The new name

docs/about/license.rst

@@ -8,4 +8,4 @@ QEMU is a trademark of Fabrice Bellard.
 QEMU is released under the `GNU General Public
 License <https://www.gnu.org/licenses/gpl-2.0.txt>`__, version 2. Parts
 of QEMU have specific licenses, see file
-`LICENSE <https://git.qemu.org/?p=qemu.git;a=blob_plain;f=LICENSE>`__.
+`LICENSE <https://gitlab.com/qemu-project/qemu/-/raw/master/LICENSE>`__.

docs/devel/multiple-iothreads.txt

@@ -61,6 +61,7 @@ There are several old APIs that use the main loop AioContext:
  * LEGACY qemu_aio_set_event_notifier() - monitor an event notifier
  * LEGACY timer_new_ms() - create a timer
  * LEGACY qemu_bh_new() - create a BH
+ * LEGACY qemu_bh_new_guarded() - create a BH with a device re-entrancy guard
  * LEGACY qemu_aio_wait() - run an event loop iteration
 
 Since they implicitly work on the main loop they cannot be used in code that
@@ -72,8 +73,14 @@ Instead, use the AioContext functions directly (see include/block/aio.h):
  * aio_set_event_notifier() - monitor an event notifier
  * aio_timer_new() - create a timer
  * aio_bh_new() - create a BH
+ * aio_bh_new_guarded() - create a BH with a device re-entrancy guard
  * aio_poll() - run an event loop iteration
 
+The qemu_bh_new_guarded/aio_bh_new_guarded APIs accept a "MemReentrancyGuard"
+argument, which is used to check for and prevent re-entrancy problems. For
+BHs associated with devices, the reentrancy-guard is contained in the
+corresponding DeviceState and named "mem_reentrancy_guard".
+
 The AioContext can be obtained from the IOThread using
 iothread_get_aio_context() or for the main loop using qemu_get_aio_context().
 Code that takes an AioContext argument works both in IOThreads or the main

docs/devel/testing.rst

@@ -990,7 +990,7 @@ class.  Here's a simple usage example:
           self.vm.launch()
           res = self.vm.command('human-monitor-command',
                                 command_line='info version')
-          self.assertRegexpMatches(res, r'^(\d+\.\d+\.\d)')
+          self.assertRegex(res, r'^(\d+\.\d+\.\d)')
 
 To execute your test, run:
 
@@ -1051,7 +1051,7 @@ and hypothetical example follows:
               'human-monitor-command',
               command_line='info version')
 
-          self.assertEquals(first_res, second_res, third_res)
+          self.assertEqual(first_res, second_res, third_res)
 
 At test "tear down", ``avocado_qemu.Test`` handles all the QEMUMachines
 shutdown.

docs/interop/vhost-user.rst

@@ -111,9 +111,9 @@ A vring state description
 A vring address description
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-+-------+-------+------+------------+------+-----------+-----+
-| index | flags | size | descriptor | used | available | log |
-+-------+-------+------+------------+------+-----------+-----+
++-------+-------+------------+------+-----------+-----+
+| index | flags | descriptor | used | available | log |
++-------+-------+------------+------+-----------+-----+
 
 :index: a 32-bit vring index
 

docs/multi-thread-compression.txt

@@ -117,13 +117,13 @@ to support the multiple thread compression migration:
     {qemu} migrate_set_capability compress on
 
 3. Set the compression thread count on source:
-    {qemu} migrate_set_parameter compress_threads 12
+    {qemu} migrate_set_parameter compress-threads 12
 
 4. Set the compression level on the source:
-    {qemu} migrate_set_parameter compress_level 1
+    {qemu} migrate_set_parameter compress-level 1
 
 5. Set the decompression thread count on destination:
-    {qemu} migrate_set_parameter decompress_threads 3
+    {qemu} migrate_set_parameter decompress-threads 3
 
 6. Start outgoing migration:
     {qemu} migrate -d tcp:destination.host:4444
@@ -133,9 +133,9 @@ to support the multiple thread compression migration:
 
 The following are the default settings:
     compress: off
-    compress_threads: 8
-    decompress_threads: 2
-    compress_level: 1 (which means best speed)
+    compress-threads: 8
+    decompress-threads: 2
+    compress-level: 1 (which means best speed)
 
 So, only the first two steps are required to use the multiple
 thread compression in migration. You can do more if the default

docs/rdma.txt

@@ -89,7 +89,7 @@ RUNNING:
 First, set the migration speed to match your hardware's capabilities:
 
 QEMU Monitor Command:
-$ migrate_set_parameter max_bandwidth 40g # or whatever is the MAX of your RDMA device
+$ migrate_set_parameter max-bandwidth 40g # or whatever is the MAX of your RDMA device
 
 Next, on the destination machine, add the following to the QEMU command line:
 

docs/requirements.txt

@@ -0,0 +1,2 @@
+sphinx==5.3.0
+sphinx_rtd_theme==1.1.1

docs/system/keys.rst.inc

@@ -1,8 +1,9 @@
-During the graphical emulation, you can use special key combinations to
-change modes. The default key mappings are shown below, but if you use
-``-alt-grab`` then the modifier is Ctrl-Alt-Shift (instead of Ctrl-Alt)
-and if you use ``-ctrl-grab`` then the modifier is the right Ctrl key
-(instead of Ctrl-Alt):
+During the graphical emulation, you can use special key combinations from
+the following table to change modes. By default the modifier is Ctrl-Alt
+(used in the table below) which can be changed with ``-display`` suboption
+``mod=`` where appropriate. For example, ``-display sdl,
+grab-mod=lshift-lctrl-lalt`` changes the modifier key to Ctrl-Alt-Shift,
+while ``-display sdl,grab-mod=rctrl`` changes it to the right Ctrl key.
 
 Ctrl-Alt-f
    Toggle full screen
@@ -28,7 +29,7 @@ Ctrl-Alt-n
    *3*
       Serial port
 
-Ctrl-Alt
+Ctrl-Alt-g
    Toggle mouse and keyboard grab.
 
 In the virtual consoles, you can use Ctrl-Up, Ctrl-Down, Ctrl-PageUp and

docs/system/multi-process.rst

@@ -2,7 +2,7 @@ Multi-process QEMU
 ==================
 
 This document describes how to configure and use multi-process qemu.
-For the design document refer to docs/devel/qemu-multiprocess.
+For the design document refer to docs/devel/multi-process.rst.
 
 1) Configuration
 ----------------

dump/dump.c

@@ -1298,8 +1298,8 @@ static bool get_next_page(GuestPhysBlock **blockptr, uint64_t *pfnptr,
 
             memcpy(buf + addr % page_size, hbuf, n);
             addr += n;
-            if (addr % page_size == 0) {
-                /* we filled up the page */
+            if (addr % page_size == 0 || addr >= block->target_end) {
+                /* we filled up the page or the current block is finished */
                 break;
             }
         } else {

fpu/softfloat.c

@@ -5135,7 +5135,7 @@ float32 float32_exp2(float32 a, float_status *status)
     float64_unpack_canonical(&rp, float64_one, status);
     for (i = 0 ; i < 15 ; i++) {
         float64_unpack_canonical(&tp, float32_exp2_coefficients[i], status);
-        rp = *parts_muladd(&tp, &xp, &rp, 0, status);
+        rp = *parts_muladd(&tp, &xnp, &rp, 0, status);
         xnp = *parts_mul(&xnp, &xp, status);
     }
 

fsdev/virtfs-proxy-helper.c

@@ -26,6 +26,7 @@
 #include "qemu/xattr.h"
 #include "9p-iov-marshal.h"
 #include "hw/9pfs/9p-proxy.h"
+#include "hw/9pfs/9p-util.h"
 #include "fsdev/9p-iov-marshal.h"
 
 #define PROGNAME "virtfs-proxy-helper"
@@ -338,6 +339,28 @@ static void resetugid(int suid, int sgid)
     }
 }
 
+/*
+ * Open regular file or directory. Attempts to open any special file are
+ * rejected.
+ *
+ * returns file descriptor or -1 on error
+ */
+static int open_regular(const char *pathname, int flags, mode_t mode)
+{
+    int fd;
+
+    fd = open(pathname, flags, mode);
+    if (fd < 0) {
+        return fd;
+    }
+
+    if (close_if_special_file(fd) < 0) {
+        return -1;
+    }
+
+    return fd;
+}
+
 /*
  * send response in two parts
  * 1) ProxyHeader
@@ -682,7 +705,7 @@ static int do_create(struct iovec *iovec)
     if (ret < 0) {
         goto unmarshal_err_out;
     }
-    ret = open(path.data, flags, mode);
+    ret = open_regular(path.data, flags, mode);
     if (ret < 0) {
         ret = -errno;
     }
@@ -707,7 +730,7 @@ static int do_open(struct iovec *iovec)
     if (ret < 0) {
         goto err_out;
     }
-    ret = open(path.data, flags);
+    ret = open_regular(path.data, flags, 0);
     if (ret < 0) {
         ret = -errno;
     }

hw/9pfs/9p-util.h

@@ -13,6 +13,8 @@
 #ifndef QEMU_9P_UTIL_H
 #define QEMU_9P_UTIL_H
 
+#include "qemu/error-report.h"
+
 #ifdef O_PATH
 #define O_PATH_9P_UTIL O_PATH
 #else
@@ -112,6 +114,38 @@ static inline void close_preserve_errno(int fd)
     errno = serrno;
 }
 
+/**
+ * close_if_special_file() - Close @fd if neither regular file nor directory.
+ *
+ * @fd: file descriptor of open file
+ * Return: 0 on regular file or directory, -1 otherwise
+ *
+ * CVE-2023-2861: Prohibit opening any special file directly on host
+ * (especially device files), as a compromised client could potentially gain
+ * access outside exported tree under certain, unsafe setups. We expect
+ * client to handle I/O on special files exclusively on guest side.
+ */
+static inline int close_if_special_file(int fd)
+{
+    struct stat stbuf;
+
+    if (fstat(fd, &stbuf) < 0) {
+        close_preserve_errno(fd);
+        return -1;
+    }
+    if (!S_ISREG(stbuf.st_mode) && !S_ISDIR(stbuf.st_mode)) {
+        error_report_once(
+            "9p: broken or compromised client detected; attempt to open "
+            "special file (i.e. neither regular file, nor directory)"
+        );
+        close(fd);
+        errno = ENXIO;
+        return -1;
+    }
+
+    return 0;
+}
+
 static inline int openat_dir(int dirfd, const char *name)
 {
     return openat(dirfd, name,
@@ -146,6 +180,10 @@ again:
         return -1;
     }
 
+    if (close_if_special_file(fd) < 0) {
+        return -1;
+    }
+
     serrno = errno;
     /* O_NONBLOCK was only needed to open the file. Let's drop it. We don't
      * do that with O_PATH since fcntl(F_SETFL) isn't supported, and openat()

hw/9pfs/trace-events

@@ -48,3 +48,9 @@ v9fs_readlink(uint16_t tag, uint8_t id, int32_t fid) "tag %d id %d fid %d"
 v9fs_readlink_return(uint16_t tag, uint8_t id, char* target) "tag %d id %d name %s"
 v9fs_setattr(uint16_t tag, uint8_t id, int32_t fid, int32_t valid, int32_t mode, int32_t uid, int32_t gid, int64_t size, int64_t atime_sec, int64_t mtime_sec) "tag %u id %u fid %d iattr={valid %d mode %d uid %d gid %d size %"PRId64" atime=%"PRId64" mtime=%"PRId64" }"
 v9fs_setattr_return(uint16_t tag, uint8_t id) "tag %u id %u"
+
+# xen-9p-backend.c
+xen_9pfs_alloc(char *name) "name %s"
+xen_9pfs_connect(char *name) "name %s"
+xen_9pfs_disconnect(char *name) "name %s"
+xen_9pfs_free(char *name) "name %s"

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

@@ -24,6 +24,8 @@
 #include "qemu/option.h"
 #include "fsdev/qemu-fsdev.h"
 
+#include "trace.h"
+
 #define VERSIONS "1"
 #define MAX_RINGS 8
 #define MAX_RING_ORDER 9
@@ -60,6 +62,7 @@ typedef struct Xen9pfsDev {
 
     int num_rings;
     Xen9pfsRing *rings;
+    MemReentrancyGuard mem_reentrancy_guard;
 } Xen9pfsDev;
 
 static void xen_9pfs_disconnect(struct XenLegacyDevice *xendev);
@@ -335,6 +338,8 @@ static void xen_9pfs_disconnect(struct XenLegacyDevice *xendev)
     Xen9pfsDev *xen_9pdev = container_of(xendev, Xen9pfsDev, xendev);
     int i;
 
+    trace_xen_9pfs_disconnect(xendev->name);
+
     for (i = 0; i < xen_9pdev->num_rings; i++) {
         if (xen_9pdev->rings[i].evtchndev != NULL) {
             qemu_set_fd_handler(xenevtchn_fd(xen_9pdev->rings[i].evtchndev),
@@ -343,39 +348,40 @@ static void xen_9pfs_disconnect(struct XenLegacyDevice *xendev)
                              xen_9pdev->rings[i].local_port);
             xen_9pdev->rings[i].evtchndev = NULL;
         }
-    }
-}
-
-static int xen_9pfs_free(struct XenLegacyDevice *xendev)
-{
-    Xen9pfsDev *xen_9pdev = container_of(xendev, Xen9pfsDev, xendev);
-    int i;
-
-    if (xen_9pdev->rings[0].evtchndev != NULL) {
-        xen_9pfs_disconnect(xendev);
-    }
-
-    for (i = 0; i < xen_9pdev->num_rings; i++) {
         if (xen_9pdev->rings[i].data != NULL) {
             xen_be_unmap_grant_refs(&xen_9pdev->xendev,
                                     xen_9pdev->rings[i].data,
                                     (1 << xen_9pdev->rings[i].ring_order));
+            xen_9pdev->rings[i].data = NULL;
         }
         if (xen_9pdev->rings[i].intf != NULL) {
             xen_be_unmap_grant_refs(&xen_9pdev->xendev,
                                     xen_9pdev->rings[i].intf,
                                     1);
+            xen_9pdev->rings[i].intf = NULL;
         }
         if (xen_9pdev->rings[i].bh != NULL) {
             qemu_bh_delete(xen_9pdev->rings[i].bh);
+            xen_9pdev->rings[i].bh = NULL;
         }
     }
 
     g_free(xen_9pdev->id);
+    xen_9pdev->id = NULL;
     g_free(xen_9pdev->tag);
+    xen_9pdev->tag = NULL;
     g_free(xen_9pdev->path);
+    xen_9pdev->path = NULL;
     g_free(xen_9pdev->security_model);
+    xen_9pdev->security_model = NULL;
     g_free(xen_9pdev->rings);
+    xen_9pdev->rings = NULL;
+}
+
+static int xen_9pfs_free(struct XenLegacyDevice *xendev)
+{
+    trace_xen_9pfs_free(xendev->name);
+
     return 0;
 }
 
@@ -387,6 +393,8 @@ static int xen_9pfs_connect(struct XenLegacyDevice *xendev)
     V9fsState *s = &xen_9pdev->state;
     QemuOpts *fsdev;
 
+    trace_xen_9pfs_connect(xendev->name);
+
     if (xenstore_read_fe_int(&xen_9pdev->xendev, "num-rings",
                              &xen_9pdev->num_rings) == -1 ||
         xen_9pdev->num_rings > MAX_RINGS || xen_9pdev->num_rings < 1) {
@@ -441,7 +449,9 @@ static int xen_9pfs_connect(struct XenLegacyDevice *xendev)
         xen_9pdev->rings[i].ring.out = xen_9pdev->rings[i].data +
                                        XEN_FLEX_RING_SIZE(ring_order);
 
-        xen_9pdev->rings[i].bh = qemu_bh_new(xen_9pfs_bh, &xen_9pdev->rings[i]);
+        xen_9pdev->rings[i].bh = qemu_bh_new_guarded(xen_9pfs_bh,
+                                                     &xen_9pdev->rings[i],
+                                                     &xen_9pdev->mem_reentrancy_guard);
         xen_9pdev->rings[i].out_cons = 0;
         xen_9pdev->rings[i].out_size = 0;
         xen_9pdev->rings[i].inprogress = false;
@@ -494,6 +504,8 @@ out:
 
 static void xen_9pfs_alloc(struct XenLegacyDevice *xendev)
 {
+    trace_xen_9pfs_alloc(xendev->name);
+
     xenstore_write_be_str(xendev, "versions", VERSIONS);
     xenstore_write_be_int(xendev, "max-rings", MAX_RINGS);
     xenstore_write_be_int(xendev, "max-ring-page-order", MAX_RING_ORDER);

hw/acpi/erst.c

@@ -947,6 +947,7 @@ static const VMStateDescription erst_vmstate  = {
 
 static void erst_realizefn(PCIDevice *pci_dev, Error **errp)
 {
+    ERRP_GUARD();
     ERSTDeviceState *s = ACPIERST(pci_dev);
 
     trace_acpi_erst_realizefn_in();
@@ -964,9 +965,15 @@ static void erst_realizefn(PCIDevice *pci_dev, Error **errp)
 
     /* HostMemoryBackend size will be multiple of PAGE_SIZE */
     s->storage_size = object_property_get_int(OBJECT(s->hostmem), "size", errp);
+    if (*errp) {
+        return;
+    }
 
     /* Initialize backend storage and record_count */
     check_erst_backend_storage(s, errp);
+    if (*errp) {
+        return;
+    }
 
     /* BAR 0: Programming registers */
     memory_region_init_io(&s->iomem_mr, OBJECT(pci_dev), &erst_reg_ops, s,
@@ -977,6 +984,9 @@ static void erst_realizefn(PCIDevice *pci_dev, Error **errp)
     memory_region_init_ram(&s->exchange_mr, OBJECT(pci_dev),
                             "erst.exchange",
                             le32_to_cpu(s->header->record_size), errp);
+    if (*errp) {
+        return;
+    }
     pci_register_bar(pci_dev, 1, PCI_BASE_ADDRESS_SPACE_MEMORY,
                         &s->exchange_mr);
 

hw/acpi/pcihp.c

@@ -429,6 +429,16 @@ void acpi_pcihp_device_unplug_request_cb(HotplugHandler *hotplug_dev,
      * acpi_pcihp_eject_slot() when the operation is completed.
      */
     pdev->qdev.pending_deleted_event = true;
+    /* if unplug was requested before OSPM is initialized,
+     * linux kernel will clear GPE0.sts[] bits during boot, which effectively
+     * hides unplug event. And than followup qmp_device_del() calls remain
+     * blocked by above flag permanently.
+     * Unblock qmp_device_del() by setting expire limit, so user can
+     * repeat unplug request later when OSPM has been booted.
+     */
+    pdev->qdev.pending_deleted_expires_ms =
+        qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL); /* 1 msec */
+
     s->acpi_pcihp_pci_status[bsel].down |= (1U << slot);
     acpi_send_event(DEVICE(hotplug_dev), ACPI_PCI_HOTPLUG_STATUS);
 }

hw/arm/aspeed.c

@@ -188,33 +188,35 @@ struct AspeedMachineState {
 static void aspeed_write_smpboot(ARMCPU *cpu,
                                  const struct arm_boot_info *info)
 {
-    static const uint32_t poll_mailbox_ready[] = {
+    AddressSpace *as = arm_boot_address_space(cpu, info);
+    static const ARMInsnFixup poll_mailbox_ready[] = {
         /*
          * r2 = per-cpu go sign value
          * r1 = AST_SMP_MBOX_FIELD_ENTRY
          * r0 = AST_SMP_MBOX_FIELD_GOSIGN
          */
-        0xee100fb0,  /* mrc     p15, 0, r0, c0, c0, 5 */
-        0xe21000ff,  /* ands    r0, r0, #255          */
-        0xe59f201c,  /* ldr     r2, [pc, #28]         */
-        0xe1822000,  /* orr     r2, r2, r0            */
+        { 0xee100fb0 },  /* mrc     p15, 0, r0, c0, c0, 5 */
+        { 0xe21000ff },  /* ands    r0, r0, #255          */
+        { 0xe59f201c },  /* ldr     r2, [pc, #28]         */
+        { 0xe1822000 },  /* orr     r2, r2, r0            */
 
-        0xe59f1018,  /* ldr     r1, [pc, #24]         */
-        0xe59f0018,  /* ldr     r0, [pc, #24]         */
+        { 0xe59f1018 },  /* ldr     r1, [pc, #24]         */
+        { 0xe59f0018 },  /* ldr     r0, [pc, #24]         */
 
-        0xe320f002,  /* wfe                           */
-        0xe5904000,  /* ldr     r4, [r0]              */
-        0xe1520004,  /* cmp     r2, r4                */
-        0x1afffffb,  /* bne     <wfe>                 */
-        0xe591f000,  /* ldr     pc, [r1]              */
-        AST_SMP_MBOX_GOSIGN,
-        AST_SMP_MBOX_FIELD_ENTRY,
-        AST_SMP_MBOX_FIELD_GOSIGN,
+        { 0xe320f002 },  /* wfe                           */
+        { 0xe5904000 },  /* ldr     r4, [r0]              */
+        { 0xe1520004 },  /* cmp     r2, r4                */
+        { 0x1afffffb },  /* bne     <wfe>                 */
+        { 0xe591f000 },  /* ldr     pc, [r1]              */
+        { AST_SMP_MBOX_GOSIGN },
+        { AST_SMP_MBOX_FIELD_ENTRY },
+        { AST_SMP_MBOX_FIELD_GOSIGN },
+        { 0, FIXUP_TERMINATOR }
     };
+    static const uint32_t fixupcontext[FIXUP_MAX] = { 0 };
 
-    rom_add_blob_fixed("aspeed.smpboot", poll_mailbox_ready,
-                       sizeof(poll_mailbox_ready),
-                       info->smp_loader_start);
+    arm_write_bootloader("aspeed.smpboot", as, info->smp_loader_start,
+                         poll_mailbox_ready, fixupcontext);
 }
 
 static void aspeed_reset_secondary(ARMCPU *cpu,

hw/arm/boot.c

@@ -59,26 +59,6 @@ AddressSpace *arm_boot_address_space(ARMCPU *cpu,
     return cpu_get_address_space(cs, asidx);
 }
 
-typedef enum {
-    FIXUP_NONE = 0,     /* do nothing */
-    FIXUP_TERMINATOR,   /* end of insns */
-    FIXUP_BOARDID,      /* overwrite with board ID number */
-    FIXUP_BOARD_SETUP,  /* overwrite with board specific setup code address */
-    FIXUP_ARGPTR_LO,    /* overwrite with pointer to kernel args */
-    FIXUP_ARGPTR_HI,    /* overwrite with pointer to kernel args (high half) */
-    FIXUP_ENTRYPOINT_LO, /* overwrite with kernel entry point */
-    FIXUP_ENTRYPOINT_HI, /* overwrite with kernel entry point (high half) */
-    FIXUP_GIC_CPU_IF,   /* overwrite with GIC CPU interface address */
-    FIXUP_BOOTREG,      /* overwrite with boot register address */
-    FIXUP_DSB,          /* overwrite with correct DSB insn for cpu */
-    FIXUP_MAX,
-} FixupType;
-
-typedef struct ARMInsnFixup {
-    uint32_t insn;
-    FixupType fixup;
-} ARMInsnFixup;
-
 static const ARMInsnFixup bootloader_aarch64[] = {
     { 0x580000c0 }, /* ldr x0, arg ; Load the lower 32-bits of DTB */
     { 0xaa1f03e1 }, /* mov x1, xzr */
@@ -149,9 +129,10 @@ static const ARMInsnFixup smpboot[] = {
     { 0, FIXUP_TERMINATOR }
 };
 
-static void write_bootloader(const char *name, hwaddr addr,
-                             const ARMInsnFixup *insns, uint32_t *fixupcontext,
-                             AddressSpace *as)
+void arm_write_bootloader(const char *name,
+                          AddressSpace *as, hwaddr addr,
+                          const ARMInsnFixup *insns,
+                          const uint32_t *fixupcontext)
 {
     /* Fix up the specified bootloader fragment and write it into
      * guest memory using rom_add_blob_fixed(). fixupcontext is
@@ -213,8 +194,8 @@ static void default_write_secondary(ARMCPU *cpu,
         fixupcontext[FIXUP_DSB] = CP15_DSB_INSN;
     }
 
-    write_bootloader("smpboot", info->smp_loader_start,
-                     smpboot, fixupcontext, as);
+    arm_write_bootloader("smpboot", as, info->smp_loader_start,
+                         smpboot, fixupcontext);
 }
 
 void arm_write_secure_board_setup_dummy_smc(ARMCPU *cpu,
@@ -1174,8 +1155,8 @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu,
         fixupcontext[FIXUP_ENTRYPOINT_LO] = entry;
         fixupcontext[FIXUP_ENTRYPOINT_HI] = entry >> 32;
 
-        write_bootloader("bootloader", info->loader_start,
-                         primary_loader, fixupcontext, as);
+        arm_write_bootloader("bootloader", as, info->loader_start,
+                             primary_loader, fixupcontext);
 
         if (info->write_board_setup) {
             info->write_board_setup(cpu, info);

hw/arm/raspi.c

@@ -16,6 +16,7 @@
 #include "qemu/units.h"
 #include "qemu/cutils.h"
 #include "qapi/error.h"
+#include "hw/arm/boot.h"
 #include "hw/arm/bcm2836.h"
 #include "hw/registerfields.h"
 #include "qemu/error-report.h"
@@ -124,20 +125,22 @@ static const char *board_type(uint32_t board_rev)
 
 static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info)
 {
-    static const uint32_t smpboot[] = {
-        0xe1a0e00f, /*    mov     lr, pc */
-        0xe3a0fe00 + (BOARDSETUP_ADDR >> 4), /* mov pc, BOARDSETUP_ADDR */
-        0xee100fb0, /*    mrc     p15, 0, r0, c0, c0, 5;get core ID */
-        0xe7e10050, /*    ubfx    r0, r0, #0, #2       ;extract LSB */
-        0xe59f5014, /*    ldr     r5, =0x400000CC      ;load mbox base */
-        0xe320f001, /* 1: yield */
-        0xe7953200, /*    ldr     r3, [r5, r0, lsl #4] ;read mbox for our core*/
-        0xe3530000, /*    cmp     r3, #0               ;spin while zero */
-        0x0afffffb, /*    beq     1b */
-        0xe7853200, /*    str     r3, [r5, r0, lsl #4] ;clear mbox */
-        0xe12fff13, /*    bx      r3                   ;jump to target */
-        0x400000cc, /* (constant: mailbox 3 read/clear base) */
+    static const ARMInsnFixup smpboot[] = {
+        { 0xe1a0e00f }, /*    mov     lr, pc */
+        { 0xe3a0fe00 + (BOARDSETUP_ADDR >> 4) }, /* mov pc, BOARDSETUP_ADDR */
+        { 0xee100fb0 }, /*    mrc     p15, 0, r0, c0, c0, 5;get core ID */
+        { 0xe7e10050 }, /*    ubfx    r0, r0, #0, #2       ;extract LSB */
+        { 0xe59f5014 }, /*    ldr     r5, =0x400000CC      ;load mbox base */
+        { 0xe320f001 }, /* 1: yield */
+        { 0xe7953200 }, /*    ldr     r3, [r5, r0, lsl #4] ;read mbox for our core */
+        { 0xe3530000 }, /*    cmp     r3, #0               ;spin while zero */
+        { 0x0afffffb }, /*    beq     1b */
+        { 0xe7853200 }, /*    str     r3, [r5, r0, lsl #4] ;clear mbox */
+        { 0xe12fff13 }, /*    bx      r3                   ;jump to target */
+        { 0x400000cc }, /* (constant: mailbox 3 read/clear base) */
+        { 0, FIXUP_TERMINATOR }
     };
+    static const uint32_t fixupcontext[FIXUP_MAX] = { 0 };
 
     /* check that we don't overrun board setup vectors */
     QEMU_BUILD_BUG_ON(SMPBOOT_ADDR + sizeof(smpboot) > MVBAR_ADDR);
@@ -145,9 +148,8 @@ static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info)
     QEMU_BUILD_BUG_ON((BOARDSETUP_ADDR & 0xf) != 0
                       || (BOARDSETUP_ADDR >> 4) >= 0x100);
 
-    rom_add_blob_fixed_as("raspi_smpboot", smpboot, sizeof(smpboot),
-                          info->smp_loader_start,
-                          arm_boot_address_space(cpu, info));
+    arm_write_bootloader("raspi_smpboot", arm_boot_address_space(cpu, info),
+                         info->smp_loader_start, smpboot, fixupcontext);
 }
 
 static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info)
@@ -161,26 +163,28 @@ static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info)
      * the primary CPU goes into the kernel. We put these variables inside
      * a rom blob, so that the reset for ROM contents zeroes them for us.
      */
-    static const uint32_t smpboot[] = {
-        0xd2801b05, /*        mov     x5, 0xd8 */
-        0xd53800a6, /*        mrs     x6, mpidr_el1 */
-        0x924004c6, /*        and     x6, x6, #0x3 */
-        0xd503205f, /* spin:  wfe */
-        0xf86678a4, /*        ldr     x4, [x5,x6,lsl #3] */
-        0xb4ffffc4, /*        cbz     x4, spin */
-        0xd2800000, /*        mov     x0, #0x0 */
-        0xd2800001, /*        mov     x1, #0x0 */
-        0xd2800002, /*        mov     x2, #0x0 */
-        0xd2800003, /*        mov     x3, #0x0 */
-        0xd61f0080, /*        br      x4 */
+    static const ARMInsnFixup smpboot[] = {
+        { 0xd2801b05 }, /*        mov     x5, 0xd8 */
+        { 0xd53800a6 }, /*        mrs     x6, mpidr_el1 */
+        { 0x924004c6 }, /*        and     x6, x6, #0x3 */
+        { 0xd503205f }, /* spin:  wfe */
+        { 0xf86678a4 }, /*        ldr     x4, [x5,x6,lsl #3] */
+        { 0xb4ffffc4 }, /*        cbz     x4, spin */
+        { 0xd2800000 }, /*        mov     x0, #0x0 */
+        { 0xd2800001 }, /*        mov     x1, #0x0 */
+        { 0xd2800002 }, /*        mov     x2, #0x0 */
+        { 0xd2800003 }, /*        mov     x3, #0x0 */
+        { 0xd61f0080 }, /*        br      x4 */
+        { 0, FIXUP_TERMINATOR }
     };
+    static const uint32_t fixupcontext[FIXUP_MAX] = { 0 };
 
     static const uint64_t spintables[] = {
         0, 0, 0, 0
     };
 
-    rom_add_blob_fixed_as("raspi_smpboot", smpboot, sizeof(smpboot),
-                          info->smp_loader_start, as);
+    arm_write_bootloader("raspi_smpboot", as, info->smp_loader_start,
+                         smpboot, fixupcontext);
     rom_add_blob_fixed_as("raspi_spintables", spintables, sizeof(spintables),
                           SPINTABLE_ADDR, as);
 }

hw/arm/smmu-common.c

@@ -193,8 +193,7 @@ static int get_pte(dma_addr_t baseaddr, uint32_t index, uint64_t *pte,
     dma_addr_t addr = baseaddr + index * sizeof(*pte);
 
     /* TODO: guarantee 64-bit single-copy atomicity */
-    ret = dma_memory_read(&address_space_memory, addr, pte, sizeof(*pte),
-                          MEMTXATTRS_UNSPECIFIED);
+    ret = ldq_le_dma(&address_space_memory, addr, pte, MEMTXATTRS_UNSPECIFIED);
 
     if (ret != MEMTX_OK) {
         info->type = SMMU_PTW_ERR_WALK_EABT;
@@ -530,6 +529,8 @@ static void smmu_base_reset(DeviceState *dev)
 {
     SMMUState *s = ARM_SMMU(dev);
 
+    memset(s->smmu_pcibus_by_bus_num, 0, sizeof(s->smmu_pcibus_by_bus_num));
+
     g_hash_table_remove_all(s->configs);
     g_hash_table_remove_all(s->iotlb);
 }

hw/arm/smmuv3.c

@@ -98,20 +98,34 @@ static void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t new_gerrorn)
     trace_smmuv3_write_gerrorn(toggled & pending, s->gerrorn);
 }
 
-static inline MemTxResult queue_read(SMMUQueue *q, void *data)
+static inline MemTxResult queue_read(SMMUQueue *q, Cmd *cmd)
 {
     dma_addr_t addr = Q_CONS_ENTRY(q);
+    MemTxResult ret;
+    int i;
 
-    return dma_memory_read(&address_space_memory, addr, data, q->entry_size,
-                           MEMTXATTRS_UNSPECIFIED);
+    ret = dma_memory_read(&address_space_memory, addr, cmd, sizeof(Cmd),
+                          MEMTXATTRS_UNSPECIFIED);
+    if (ret != MEMTX_OK) {
+        return ret;
+    }
+    for (i = 0; i < ARRAY_SIZE(cmd->word); i++) {
+        le32_to_cpus(&cmd->word[i]);
+    }
+    return ret;
 }
 
-static MemTxResult queue_write(SMMUQueue *q, void *data)
+static MemTxResult queue_write(SMMUQueue *q, Evt *evt_in)
 {
     dma_addr_t addr = Q_PROD_ENTRY(q);
     MemTxResult ret;
+    Evt evt = *evt_in;
+    int i;
 
-    ret = dma_memory_write(&address_space_memory, addr, data, q->entry_size,
+    for (i = 0; i < ARRAY_SIZE(evt.word); i++) {
+        cpu_to_le32s(&evt.word[i]);
+    }
+    ret = dma_memory_write(&address_space_memory, addr, &evt, sizeof(Evt),
                            MEMTXATTRS_UNSPECIFIED);
     if (ret != MEMTX_OK) {
         return ret;
@@ -290,7 +304,7 @@ static void smmuv3_init_regs(SMMUv3State *s)
 static int smmu_get_ste(SMMUv3State *s, dma_addr_t addr, STE *buf,
                         SMMUEventInfo *event)
 {
-    int ret;
+    int ret, i;
 
     trace_smmuv3_get_ste(addr);
     /* TODO: guarantee 64-bit single-copy atomicity */
@@ -303,6 +317,9 @@ static int smmu_get_ste(SMMUv3State *s, dma_addr_t addr, STE *buf,
         event->u.f_ste_fetch.addr = addr;
         return -EINVAL;
     }
+    for (i = 0; i < ARRAY_SIZE(buf->word); i++) {
+        le32_to_cpus(&buf->word[i]);
+    }
     return 0;
 
 }
@@ -312,7 +329,7 @@ static int smmu_get_cd(SMMUv3State *s, STE *ste, uint32_t ssid,
                        CD *buf, SMMUEventInfo *event)
 {
     dma_addr_t addr = STE_CTXPTR(ste);
-    int ret;
+    int ret, i;
 
     trace_smmuv3_get_cd(addr);
     /* TODO: guarantee 64-bit single-copy atomicity */
@@ -325,6 +342,9 @@ static int smmu_get_cd(SMMUv3State *s, STE *ste, uint32_t ssid,
         event->u.f_ste_fetch.addr = addr;
         return -EINVAL;
     }
+    for (i = 0; i < ARRAY_SIZE(buf->word); i++) {
+        le32_to_cpus(&buf->word[i]);
+    }
     return 0;
 }
 
@@ -406,7 +426,7 @@ static int smmu_find_ste(SMMUv3State *s, uint32_t sid, STE *ste,
         return -EINVAL;
     }
     if (s->features & SMMU_FEATURE_2LVL_STE) {
-        int l1_ste_offset, l2_ste_offset, max_l2_ste, span;
+        int l1_ste_offset, l2_ste_offset, max_l2_ste, span, i;
         dma_addr_t l1ptr, l2ptr;
         STEDesc l1std;
 
@@ -430,6 +450,9 @@ static int smmu_find_ste(SMMUv3State *s, uint32_t sid, STE *ste,
             event->u.f_ste_fetch.addr = l1ptr;
             return -EINVAL;
         }
+        for (i = 0; i < ARRAY_SIZE(l1std.word); i++) {
+            le32_to_cpus(&l1std.word[i]);
+        }
 
         span = L1STD_SPAN(&l1std);
 

hw/arm/xlnx-zynqmp.c

@@ -213,7 +213,7 @@ static void xlnx_zynqmp_create_rpu(MachineState *ms, XlnxZynqMPState *s,
                                    const char *boot_cpu, Error **errp)
 {
     int i;
-    int num_rpus = MIN(ms->smp.cpus - XLNX_ZYNQMP_NUM_APU_CPUS,
+    int num_rpus = MIN((int)(ms->smp.cpus - XLNX_ZYNQMP_NUM_APU_CPUS),
                        XLNX_ZYNQMP_NUM_RPU_CPUS);
 
     if (num_rpus <= 0) {

hw/audio/es1370.c

@@ -503,7 +503,7 @@ static void es1370_write(void *opaque, hwaddr addr, uint64_t val, unsigned size)
     case ES1370_REG_DAC2_SCOUNT:
     case ES1370_REG_ADC_SCOUNT:
         d += (addr - ES1370_REG_DAC1_SCOUNT) >> 2;
-        d->scount = (val & 0xffff) | (d->scount & ~0xffff);
+        d->scount = (val & 0xffff) << 16 | (val & 0xffff);
         ldebug ("chan %td CURR_SAMP_CT %d, SAMP_CT %d\n",
                 d - &s->chan[0], val >> 16, (val & 0xffff));
         break;

hw/audio/hda-codec.c

@@ -22,6 +22,7 @@
 #include "hw/qdev-properties.h"
 #include "intel-hda.h"
 #include "migration/vmstate.h"
+#include "qemu/host-utils.h"
 #include "qemu/module.h"
 #include "intel-hda-defs.h"
 #include "audio/audio.h"
@@ -190,9 +191,9 @@ struct HDAAudioState {
     bool     use_timer;
 };
 
-static inline int64_t hda_bytes_per_second(HDAAudioStream *st)
+static inline uint32_t hda_bytes_per_second(HDAAudioStream *st)
 {
-    return 2LL * st->as.nchannels * st->as.freq;
+    return 2 * (uint32_t)st->as.nchannels * (uint32_t)st->as.freq;
 }
 
 static inline void hda_timer_sync_adjust(HDAAudioStream *st, int64_t target_pos)
@@ -223,12 +224,18 @@ static void hda_audio_input_timer(void *opaque)
 
     int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
 
-    int64_t buft_start = st->buft_start;
+    int64_t uptime = now - st->buft_start;
     int64_t wpos = st->wpos;
     int64_t rpos = st->rpos;
+    int64_t wanted_rpos;
 
-    int64_t wanted_rpos = hda_bytes_per_second(st) * (now - buft_start)
-                          / NANOSECONDS_PER_SECOND;
+    if (uptime <= 0) {
+        /* wanted_rpos <= 0 */
+        goto out_timer;
+    }
+
+    wanted_rpos = muldiv64(uptime, hda_bytes_per_second(st),
+                           NANOSECONDS_PER_SECOND);
     wanted_rpos &= -4; /* IMPORTANT! clip to frames */
 
     if (wanted_rpos <= rpos) {
@@ -287,12 +294,18 @@ static void hda_audio_output_timer(void *opaque)
 
     int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
 
-    int64_t buft_start = st->buft_start;
+    int64_t uptime = now - st->buft_start;
     int64_t wpos = st->wpos;
     int64_t rpos = st->rpos;
+    int64_t wanted_wpos;
 
-    int64_t wanted_wpos = hda_bytes_per_second(st) * (now - buft_start)
-                          / NANOSECONDS_PER_SECOND;
+    if (uptime <= 0) {
+        /* wanted_wpos <= 0 */
+        goto out_timer;
+    }
+
+    wanted_wpos = muldiv64(uptime, hda_bytes_per_second(st),
+                           NANOSECONDS_PER_SECOND);
     wanted_wpos &= -4; /* IMPORTANT! clip to frames */
 
     if (wanted_wpos <= wpos) {

hw/block/dataplane/virtio-blk.c

@@ -127,7 +127,8 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
     } else {
         s->ctx = qemu_get_aio_context();
     }
-    s->bh = aio_bh_new(s->ctx, notify_guest_bh, s);
+    s->bh = aio_bh_new_guarded(s->ctx, notify_guest_bh, s,
+                               &DEVICE(vdev)->mem_reentrancy_guard);
     s->batch_notify_vqs = bitmap_new(conf->num_queues);
 
     *dataplane = s;

hw/block/dataplane/xen-block.c

@@ -632,8 +632,9 @@ XenBlockDataPlane *xen_block_dataplane_create(XenDevice *xendev,
     } else {
         dataplane->ctx = qemu_get_aio_context();
     }
-    dataplane->bh = aio_bh_new(dataplane->ctx, xen_block_dataplane_bh,
-                               dataplane);
+    dataplane->bh = aio_bh_new_guarded(dataplane->ctx, xen_block_dataplane_bh,
+                                       dataplane,
+                                       &DEVICE(xendev)->mem_reentrancy_guard);
 
     return dataplane;
 }

hw/block/pflash_cfi01.c

@@ -81,16 +81,39 @@ struct PFlashCFI01 {
     uint16_t ident3;
     uint8_t cfi_table[0x52];
     uint64_t counter;
-    unsigned int writeblock_size;
+    uint32_t writeblock_size;
     MemoryRegion mem;
     char *name;
     void *storage;
     VMChangeStateEntry *vmstate;
     bool old_multiple_chip_handling;
+
+    /* block update buffer */
+    unsigned char *blk_bytes;
+    uint32_t blk_offset;
 };
 
 static int pflash_post_load(void *opaque, int version_id);
 
+static bool pflash_blk_write_state_needed(void *opaque)
+{
+    PFlashCFI01 *pfl = opaque;
+
+    return (pfl->blk_offset != -1);
+}
+
+static const VMStateDescription vmstate_pflash_blk_write = {
+    .name = "pflash_cfi01_blk_write",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = pflash_blk_write_state_needed,
+    .fields = (const VMStateField[]) {
+        VMSTATE_VBUFFER_UINT32(blk_bytes, PFlashCFI01, 0, NULL, writeblock_size),
+        VMSTATE_UINT32(blk_offset, PFlashCFI01),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_pflash = {
     .name = "pflash_cfi01",
     .version_id = 1,
@@ -102,6 +125,10 @@ static const VMStateDescription vmstate_pflash = {
         VMSTATE_UINT8(status, PFlashCFI01),
         VMSTATE_UINT64(counter, PFlashCFI01),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription * []) {
+        &vmstate_pflash_blk_write,
+        NULL
     }
 };
 
@@ -226,34 +253,10 @@ static uint32_t pflash_data_read(PFlashCFI01 *pfl, hwaddr offset,
     uint32_t ret;
 
     p = pfl->storage;
-    switch (width) {
-    case 1:
-        ret = p[offset];
-        break;
-    case 2:
-        if (be) {
-            ret = p[offset] << 8;
-            ret |= p[offset + 1];
-        } else {
-            ret = p[offset];
-            ret |= p[offset + 1] << 8;
-        }
-        break;
-    case 4:
-        if (be) {
-            ret = p[offset] << 24;
-            ret |= p[offset + 1] << 16;
-            ret |= p[offset + 2] << 8;
-            ret |= p[offset + 3];
-        } else {
-            ret = p[offset];
-            ret |= p[offset + 1] << 8;
-            ret |= p[offset + 2] << 16;
-            ret |= p[offset + 3] << 24;
-        }
-        break;
-    default:
-        abort();
+    if (be) {
+        ret = ldn_be_p(p + offset, width);
+    } else {
+        ret = ldn_le_p(p + offset, width);
     }
     trace_pflash_data_read(pfl->name, offset, width, ret);
     return ret;
@@ -401,40 +404,61 @@ static void pflash_update(PFlashCFI01 *pfl, int offset,
     }
 }
 
+/* copy current flash content to block update buffer */
+static void pflash_blk_write_start(PFlashCFI01 *pfl, hwaddr offset)
+{
+    hwaddr mask = ~(pfl->writeblock_size - 1);
+
+    trace_pflash_write_block_start(pfl->name, pfl->counter);
+    pfl->blk_offset = offset & mask;
+    memcpy(pfl->blk_bytes, pfl->storage + pfl->blk_offset,
+           pfl->writeblock_size);
+}
+
+/* commit block update buffer changes */
+static void pflash_blk_write_flush(PFlashCFI01 *pfl)
+{
+    g_assert(pfl->blk_offset != -1);
+    trace_pflash_write_block_flush(pfl->name);
+    memcpy(pfl->storage + pfl->blk_offset, pfl->blk_bytes,
+           pfl->writeblock_size);
+    pflash_update(pfl, pfl->blk_offset, pfl->writeblock_size);
+    pfl->blk_offset = -1;
+}
+
+/* discard block update buffer changes */
+static void pflash_blk_write_abort(PFlashCFI01 *pfl)
+{
+    trace_pflash_write_block_abort(pfl->name);
+    pfl->blk_offset = -1;
+}
+
 static inline void pflash_data_write(PFlashCFI01 *pfl, hwaddr offset,
                                      uint32_t value, int width, int be)
 {
-    uint8_t *p = pfl->storage;
+    uint8_t *p;
 
-    trace_pflash_data_write(pfl->name, offset, width, value, pfl->counter);
-    switch (width) {
-    case 1:
-        p[offset] = value;
-        break;
-    case 2:
-        if (be) {
-            p[offset] = value >> 8;
-            p[offset + 1] = value;
-        } else {
-            p[offset] = value;
-            p[offset + 1] = value >> 8;
+    if (pfl->blk_offset != -1) {
+        /* block write: redirect writes to block update buffer */
+        if ((offset < pfl->blk_offset) ||
+            (offset + width > pfl->blk_offset + pfl->writeblock_size)) {
+            pfl->status |= 0x10; /* Programming error */
+            return;
         }
-        break;
-    case 4:
-        if (be) {
-            p[offset] = value >> 24;
-            p[offset + 1] = value >> 16;
-            p[offset + 2] = value >> 8;
-            p[offset + 3] = value;
-        } else {
-            p[offset] = value;
-            p[offset + 1] = value >> 8;
-            p[offset + 2] = value >> 16;
-            p[offset + 3] = value >> 24;
-        }
-        break;
+        trace_pflash_data_write_block(pfl->name, offset, width, value,
+                                      pfl->counter);
+        p = pfl->blk_bytes + (offset - pfl->blk_offset);
+    } else {
+        /* write directly to storage */
+        trace_pflash_data_write(pfl->name, offset, width, value);
+        p = pfl->storage + offset;
     }
 
+    if (be) {
+        stn_be_p(p, width, value);
+    } else {
+        stn_le_p(p, width, value);
+    }
 }
 
 static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
@@ -549,9 +573,9 @@ static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
             } else {
                 value = extract32(value, 0, pfl->bank_width * 8);
             }
-            trace_pflash_write_block(pfl->name, value);
             pfl->counter = value;
             pfl->wcycle++;
+            pflash_blk_write_start(pfl, offset);
             break;
         case 0x60:
             if (cmd == 0xd0) {
@@ -582,12 +606,7 @@ static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
         switch (pfl->cmd) {
         case 0xe8: /* Block write */
             /* FIXME check @offset, @width */
-            if (!pfl->ro) {
-                /*
-                 * FIXME writing straight to memory is *wrong*.  We
-                 * should write to a buffer, and flush it to memory
-                 * only on confirm command (see below).
-                 */
+            if (!pfl->ro && (pfl->blk_offset != -1)) {
                 pflash_data_write(pfl, offset, value, width, be);
             } else {
                 pfl->status |= 0x10; /* Programming error */
@@ -596,18 +615,8 @@ static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
             pfl->status |= 0x80;
 
             if (!pfl->counter) {
-                hwaddr mask = pfl->writeblock_size - 1;
-                mask = ~mask;
-
                 trace_pflash_write(pfl->name, "block write finished");
                 pfl->wcycle++;
-                if (!pfl->ro) {
-                    /* Flush the entire write buffer onto backing storage.  */
-                    /* FIXME premature! */
-                    pflash_update(pfl, offset & mask, pfl->writeblock_size);
-                } else {
-                    pfl->status |= 0x10; /* Programming error */
-                }
             }
 
             pfl->counter--;
@@ -619,20 +628,17 @@ static void pflash_write(PFlashCFI01 *pfl, hwaddr offset,
     case 3: /* Confirm mode */
         switch (pfl->cmd) {
         case 0xe8: /* Block write */
-            if (cmd == 0xd0) {
-                /* FIXME this is where we should write out the buffer */
+            if ((cmd == 0xd0) && !(pfl->status & 0x10)) {
+                pflash_blk_write_flush(pfl);
                 pfl->wcycle = 0;
                 pfl->status |= 0x80;
             } else {
-                qemu_log_mask(LOG_UNIMP,
-                    "%s: Aborting write to buffer not implemented,"
-                    " the data is already written to storage!\n"
-                    "Flash device reset into READ mode.\n",
-                    __func__);
+                pflash_blk_write_abort(pfl);
                 goto mode_read_array;
             }
             break;
         default:
+            pflash_blk_write_abort(pfl);
             goto error_flash;
         }
         break;
@@ -866,6 +872,9 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
     pfl->cmd = 0x00;
     pfl->status = 0x80; /* WSM ready */
     pflash_cfi01_fill_cfi_table(pfl);
+
+    pfl->blk_bytes = g_malloc(pfl->writeblock_size);
+    pfl->blk_offset = -1;
 }
 
 static void pflash_cfi01_system_reset(DeviceState *dev)
@@ -885,6 +894,8 @@ static void pflash_cfi01_system_reset(DeviceState *dev)
      * This model deliberately ignores this delay.
      */
     pfl->status = 0x80;
+
+    pfl->blk_offset = -1;
 }
 
 static Property pflash_cfi01_properties[] = {

hw/block/pflash_cfi02.c

@@ -546,7 +546,7 @@ static void pflash_write(void *opaque, hwaddr offset, uint64_t value,
                 }
                 goto reset_flash;
             }
-            trace_pflash_data_write(pfl->name, offset, width, value, 0);
+            trace_pflash_data_write(pfl->name, offset, width, value);
             if (!pfl->ro) {
                 p = (uint8_t *)pfl->storage + offset;
                 if (pfl->be) {

hw/block/trace-events

@@ -12,7 +12,8 @@ fdctrl_tc_pulse(int level) "TC pulse: %u"
 pflash_chip_erase_invalid(const char *name, uint64_t offset) "%s: chip erase: invalid address 0x%" PRIx64
 pflash_chip_erase_start(const char *name) "%s: start chip erase"
 pflash_data_read(const char *name, uint64_t offset, unsigned size, uint32_t value) "%s: data offset:0x%04"PRIx64" size:%u value:0x%04x"
-pflash_data_write(const char *name, uint64_t offset, unsigned size, uint32_t value, uint64_t counter) "%s: data offset:0x%04"PRIx64" size:%u value:0x%04x counter:0x%016"PRIx64
+pflash_data_write(const char *name, uint64_t offset, unsigned size, uint32_t value) "%s: data offset:0x%04"PRIx64" size:%u value:0x%04x"
+pflash_data_write_block(const char *name, uint64_t offset, unsigned size, uint32_t value, uint64_t counter) "%s: data offset:0x%04"PRIx64" size:%u value:0x%04x counter:0x%016"PRIx64
 pflash_device_id(const char *name, uint16_t id) "%s: read device ID: 0x%04x"
 pflash_device_info(const char *name, uint64_t offset) "%s: read device information offset:0x%04" PRIx64
 pflash_erase_complete(const char *name) "%s: sector erase complete"
@@ -32,7 +33,9 @@ pflash_unlock0_failed(const char *name, uint64_t offset, uint8_t cmd, uint16_t a
 pflash_unlock1_failed(const char *name, uint64_t offset, uint8_t cmd) "%s: unlock0 failed 0x%" PRIx64 " 0x%02x"
 pflash_unsupported_device_configuration(const char *name, uint8_t width, uint8_t max) "%s: unsupported device configuration: device_width:%d max_device_width:%d"
 pflash_write(const char *name, const char *str) "%s: %s"
-pflash_write_block(const char *name, uint32_t value) "%s: block write: bytes:0x%x"
+pflash_write_block_start(const char *name, uint32_t value) "%s: block write start: bytes:0x%x"
+pflash_write_block_flush(const char *name) "%s: block write flush"
+pflash_write_block_abort(const char *name) "%s: block write abort"
 pflash_write_block_erase(const char *name, uint64_t offset, uint64_t len) "%s: block erase offset:0x%" PRIx64 " bytes:0x%" PRIx64
 pflash_write_failed(const char *name, uint64_t offset, uint8_t cmd) "%s: command failed 0x%" PRIx64 " 0x%02x"
 pflash_write_invalid(const char *name, uint8_t cmd) "%s: invalid write for command 0x%02x"

hw/block/xen-block.c

@@ -759,14 +759,15 @@ static XenBlockDrive *xen_block_drive_create(const char *id,
     drive = g_new0(XenBlockDrive, 1);
     drive->id = g_strdup(id);
 
-    file_layer = qdict_new();
-    driver_layer = qdict_new();
-
     rc = stat(filename, &st);
     if (rc) {
         error_setg_errno(errp, errno, "Could not stat file '%s'", filename);
         goto done;
     }
+
+    file_layer = qdict_new();
+    driver_layer = qdict_new();
+
     if (S_ISBLK(st.st_mode)) {
         qdict_put_str(file_layer, "driver", "host_device");
     } else {
@@ -774,7 +775,6 @@ static XenBlockDrive *xen_block_drive_create(const char *id,
     }
 
     qdict_put_str(file_layer, "filename", filename);
-    g_free(filename);
 
     if (mode && *mode != 'w') {
         qdict_put_bool(file_layer, "read-only", true);
@@ -809,7 +809,6 @@ static XenBlockDrive *xen_block_drive_create(const char *id,
     qdict_put_str(file_layer, "locking", "off");
 
     qdict_put_str(driver_layer, "driver", driver);
-    g_free(driver);
 
     qdict_put(driver_layer, "file", file_layer);
 
@@ -820,6 +819,8 @@ static XenBlockDrive *xen_block_drive_create(const char *id,
     qobject_unref(driver_layer);
 
 done:
+    g_free(filename);
+    g_free(driver);
     if (*errp) {
         xen_block_drive_destroy(drive, NULL);
         return NULL;

hw/char/riscv_htif.c

@@ -146,7 +146,8 @@ static void htif_handle_tohost_write(HTIFState *htifstate, uint64_t val_written)
             htifstate->env->mtohost = 0; /* clear to indicate we read */
             return;
         } else if (cmd == 0x1) {
-            qemu_chr_fe_write(&htifstate->chr, (uint8_t *)&payload, 1);
+            uint8_t ch = (uint8_t)payload;
+            qemu_chr_fe_write(&htifstate->chr, &ch, 1);
             resp = 0x100 | (uint8_t)payload;
         } else {
             qemu_log("HTIF device %d: unknown command\n", device);

hw/char/virtio-serial-bus.c

@@ -985,7 +985,8 @@ static void virtser_port_device_realize(DeviceState *dev, Error **errp)
         return;
     }
 
-    port->bh = qemu_bh_new(flush_queued_data_bh, port);
+    port->bh = qemu_bh_new_guarded(flush_queued_data_bh, port,
+                                   &dev->mem_reentrancy_guard);
     port->elem = NULL;
 }
 

hw/core/machine-smp.c

@@ -193,3 +193,13 @@ void machine_parse_smp_config(MachineState *ms,
         return;
     }
 }
+
+unsigned int machine_topo_get_cores_per_socket(const MachineState *ms)
+{
+    return ms->smp.cores * ms->smp.clusters * ms->smp.dies;
+}
+
+unsigned int machine_topo_get_threads_per_socket(const MachineState *ms)
+{
+    return ms->smp.threads * machine_topo_get_cores_per_socket(ms);
+}

hw/core/machine.c

@@ -1329,6 +1329,14 @@ void machine_run_board_init(MachineState *machine, const char *mem_path, Error *
         }
     } else if (machine_class->default_ram_id && machine->ram_size &&
                numa_uses_legacy_mem()) {
+        if (object_property_find(object_get_objects_root(),
+                                 machine_class->default_ram_id)) {
+            error_setg(errp, "object name '%s' is reserved for the default"
+                " RAM backend, it can't be used for any other purposes."
+                " Change the object's 'id' to something else",
+                machine_class->default_ram_id);
+            return;
+        }
         if (!create_default_memdev(current_machine, mem_path, errp)) {
             return;
         }

hw/cxl/cxl-cdat.c

@@ -49,6 +49,7 @@ static void ct3_build_cdat(CDATObject *cdat, Error **errp)
     g_autofree CDATTableHeader *cdat_header = NULL;
     g_autofree CDATEntry *cdat_st = NULL;
     uint8_t sum = 0;
+    uint8_t *hdr_buf;
     int ent, i;
 
     /* Use default table if fopen == NULL */
@@ -62,7 +63,7 @@ static void ct3_build_cdat(CDATObject *cdat, Error **errp)
 
     cdat->built_buf_len = cdat->build_cdat_table(&cdat->built_buf, cdat->private);
 
-    if (!cdat->built_buf_len) {
+    if (cdat->built_buf_len <= 0) {
         /* Build later as not all data available yet */
         cdat->to_update = true;
         return;
@@ -94,8 +95,12 @@ static void ct3_build_cdat(CDATObject *cdat, Error **errp)
     /* For now, no runtime updates */
     cdat_header->sequence = 0;
     cdat_header->length += sizeof(CDATTableHeader);
-    sum += cdat_header->revision + cdat_header->sequence +
-        cdat_header->length;
+
+    hdr_buf = (uint8_t *)cdat_header;
+    for (i = 0; i < sizeof(*cdat_header); i++) {
+        sum += hdr_buf[i];
+    }
+
     /* Sum of all bytes including checksum must be 0 */
     cdat_header->checksum = ~sum + 1;
 

hw/cxl/cxl-component-utils.c

@@ -126,7 +126,7 @@ void cxl_component_register_block_init(Object *obj,
     /* io registers controls link which we don't care about in QEMU */
     memory_region_init_io(&cregs->io, obj, NULL, cregs, ".io",
                           CXL2_COMPONENT_IO_REGION_SIZE);
-    memory_region_init_io(&cregs->cache_mem, obj, &cache_mem_ops, cregs,
+    memory_region_init_io(&cregs->cache_mem, obj, &cache_mem_ops, cxl_cstate,
                           ".cache_mem", CXL2_COMPONENT_CM_REGION_SIZE);
 
     memory_region_add_subregion(&cregs->component_registers, 0, &cregs->io);

hw/cxl/cxl-host.c

@@ -39,12 +39,6 @@ static void cxl_fixed_memory_window_config(CXLState *cxl_state,
         return;
     }
 
-    fw->targets = g_malloc0_n(fw->num_targets, sizeof(*fw->targets));
-    for (i = 0, target = object->targets; target; i++, target = target->next) {
-        /* This link cannot be resolved yet, so stash the name for now */
-        fw->targets[i] = g_strdup(target->value);
-    }
-
     if (object->size % (256 * MiB)) {
         error_setg(errp,
                    "Size of a CXL fixed memory window must my a multiple of 256MiB");
@@ -64,6 +58,12 @@ static void cxl_fixed_memory_window_config(CXLState *cxl_state,
         fw->enc_int_gran = 0;
     }
 
+    fw->targets = g_malloc0_n(fw->num_targets, sizeof(*fw->targets));
+    for (i = 0, target = object->targets; target; i++, target = target->next) {
+        /* This link cannot be resolved yet, so stash the name for now */
+        fw->targets[i] = g_strdup(target->value);
+    }
+
     cxl_state->fixed_windows = g_list_append(cxl_state->fixed_windows,
                                              g_steal_pointer(&fw));
 

hw/display/ati.c

@@ -1014,6 +1014,7 @@ static Property ati_vga_properties[] = {
     DEFINE_PROP_UINT16("x-device-id", ATIVGAState, dev_id,
                        PCI_DEVICE_ID_ATI_RAGE128_PF),
     DEFINE_PROP_BOOL("guest_hwcursor", ATIVGAState, cursor_guest_mode, false),
+    DEFINE_PROP_UINT8("x-pixman", ATIVGAState, use_pixman, 3),
     DEFINE_PROP_END_OF_LIST()
 };
 
@@ -1035,11 +1036,18 @@ static void ati_vga_class_init(ObjectClass *klass, void *data)
     k->exit = ati_vga_exit;
 }
 
+static void ati_vga_init(Object *o)
+{
+    object_property_set_description(o, "x-pixman", "Use pixman for: "
+                                    "1: fill, 2: blit");
+}
+
 static const TypeInfo ati_vga_info = {
     .name = TYPE_ATI_VGA,
     .parent = TYPE_PCI_DEVICE,
     .instance_size = sizeof(ATIVGAState),
     .class_init = ati_vga_class_init,
+    .instance_init = ati_vga_init,
     .interfaces = (InterfaceInfo[]) {
           { INTERFACE_CONVENTIONAL_PCI_DEVICE },
           { },

hw/display/ati_2d.c

@@ -92,6 +92,7 @@ void ati_2d_blt(ATIVGAState *s)
     switch (s->regs.dp_mix & GMC_ROP3_MASK) {
     case ROP3_SRCCOPY:
     {
+        bool fallback = false;
         unsigned src_x = (s->regs.dp_cntl & DST_X_LEFT_TO_RIGHT ?
                        s->regs.src_x : s->regs.src_x + 1 - s->regs.dst_width);
         unsigned src_y = (s->regs.dp_cntl & DST_Y_TOP_TO_BOTTOM ?
@@ -122,27 +123,50 @@ void ati_2d_blt(ATIVGAState *s)
                 src_bits, dst_bits, src_stride, dst_stride, bpp, bpp,
                 src_x, src_y, dst_x, dst_y,
                 s->regs.dst_width, s->regs.dst_height);
-        if (s->regs.dp_cntl & DST_X_LEFT_TO_RIGHT &&
+        if ((s->use_pixman & BIT(1)) &&
+            s->regs.dp_cntl & DST_X_LEFT_TO_RIGHT &&
             s->regs.dp_cntl & DST_Y_TOP_TO_BOTTOM) {
-            pixman_blt((uint32_t *)src_bits, (uint32_t *)dst_bits,
-                       src_stride, dst_stride, bpp, bpp,
-                       src_x, src_y, dst_x, dst_y,
-                       s->regs.dst_width, s->regs.dst_height);
-        } else {
+            fallback = !pixman_blt((uint32_t *)src_bits, (uint32_t *)dst_bits,
+                                   src_stride, dst_stride, bpp, bpp,
+                                   src_x, src_y, dst_x, dst_y,
+                                   s->regs.dst_width, s->regs.dst_height);
+        } else if (s->use_pixman & BIT(1)) {
             /* FIXME: We only really need a temporary if src and dst overlap */
             int llb = s->regs.dst_width * (bpp / 8);
             int tmp_stride = DIV_ROUND_UP(llb, sizeof(uint32_t));
             uint32_t *tmp = g_malloc(tmp_stride * sizeof(uint32_t) *
                                      s->regs.dst_height);
-            pixman_blt((uint32_t *)src_bits, tmp,
-                       src_stride, tmp_stride, bpp, bpp,
-                       src_x, src_y, 0, 0,
-                       s->regs.dst_width, s->regs.dst_height);
-            pixman_blt(tmp, (uint32_t *)dst_bits,
-                       tmp_stride, dst_stride, bpp, bpp,
-                       0, 0, dst_x, dst_y,
-                       s->regs.dst_width, s->regs.dst_height);
+            fallback = !pixman_blt((uint32_t *)src_bits, tmp,
+                                   src_stride, tmp_stride, bpp, bpp,
+                                   src_x, src_y, 0, 0,
+                                   s->regs.dst_width, s->regs.dst_height);
+            if (!fallback) {
+                fallback = !pixman_blt(tmp, (uint32_t *)dst_bits,
+                                       tmp_stride, dst_stride, bpp, bpp,
+                                       0, 0, dst_x, dst_y,
+                                       s->regs.dst_width, s->regs.dst_height);
+            }
             g_free(tmp);
+        } else {
+            fallback = true;
+        }
+        if (fallback) {
+            unsigned int y, i, j, bypp = bpp / 8;
+            unsigned int src_pitch = src_stride * sizeof(uint32_t);
+            unsigned int dst_pitch = dst_stride * sizeof(uint32_t);
+
+            for (y = 0; y < s->regs.dst_height; y++) {
+                i = dst_x * bypp;
+                j = src_x * bypp;
+                if (s->regs.dp_cntl & DST_Y_TOP_TO_BOTTOM) {
+                    i += (dst_y + y) * dst_pitch;
+                    j += (src_y + y) * src_pitch;
+                } else {
+                    i += (dst_y + s->regs.dst_height - 1 - y) * dst_pitch;
+                    j += (src_y + s->regs.dst_height - 1 - y) * src_pitch;
+                }
+                memmove(&dst_bits[i], &src_bits[j], s->regs.dst_width * bypp);
+            }
         }
         if (dst_bits >= s->vga.vram_ptr + s->vga.vbe_start_addr &&
             dst_bits < s->vga.vram_ptr + s->vga.vbe_start_addr +
@@ -180,14 +204,21 @@ void ati_2d_blt(ATIVGAState *s)
 
         dst_stride /= sizeof(uint32_t);
         DPRINTF("pixman_fill(%p, %d, %d, %d, %d, %d, %d, %x)\n",
-                dst_bits, dst_stride, bpp,
-                dst_x, dst_y,
-                s->regs.dst_width, s->regs.dst_height,
-                filler);
-        pixman_fill((uint32_t *)dst_bits, dst_stride, bpp,
-                    dst_x, dst_y,
-                    s->regs.dst_width, s->regs.dst_height,
-                    filler);
+                dst_bits, dst_stride, bpp, dst_x, dst_y,
+                s->regs.dst_width, s->regs.dst_height, filler);
+        if (!(s->use_pixman & BIT(0)) ||
+            !pixman_fill((uint32_t *)dst_bits, dst_stride, bpp, dst_x, dst_y,
+                    s->regs.dst_width, s->regs.dst_height, filler)) {
+            /* fallback when pixman failed or we don't want to call it */
+            unsigned int x, y, i, bypp = bpp / 8;
+            unsigned int dst_pitch = dst_stride * sizeof(uint32_t);
+            for (y = 0; y < s->regs.dst_height; y++) {
+                i = dst_x * bypp + (dst_y + y) * dst_pitch;
+                for (x = 0; x < s->regs.dst_width; x++, i += bypp) {
+                    stn_he_p(&dst_bits[i], bypp, filler);
+                }
+            }
+        }
         if (dst_bits >= s->vga.vram_ptr + s->vga.vbe_start_addr &&
             dst_bits < s->vga.vram_ptr + s->vga.vbe_start_addr +
             s->vga.vbe_regs[VBE_DISPI_INDEX_YRES] * s->vga.vbe_line_offset) {

hw/display/ati_int.h

@@ -89,6 +89,7 @@ struct ATIVGAState {
     char *model;
     uint16_t dev_id;
     uint8_t mode;
+    uint8_t use_pixman;
     bool cursor_guest_mode;
     uint16_t cursor_size;
     uint32_t cursor_offset;

hw/display/qxl.c

@@ -1613,7 +1613,10 @@ static void qxl_set_mode(PCIQXLDevice *d, unsigned int modenr, int loadvm)
     }
 
     d->guest_slots[0].slot = slot;
-    assert(qxl_add_memslot(d, 0, devmem, QXL_SYNC) == 0);
+    if (qxl_add_memslot(d, 0, devmem, QXL_SYNC) != 0) {
+        qxl_set_guest_bug(d, "device isn't initialized yet");
+        return;
+    }
 
     d->guest_primary.surface = surface;
     qxl_create_guest_primary(d, 0, QXL_SYNC);
@@ -2223,11 +2226,14 @@ static void qxl_realize_common(PCIQXLDevice *qxl, Error **errp)
 
     qemu_add_vm_change_state_handler(qxl_vm_change_state_handler, qxl);
 
-    qxl->update_irq = qemu_bh_new(qxl_update_irq_bh, qxl);
+    qxl->update_irq = qemu_bh_new_guarded(qxl_update_irq_bh, qxl,
+                                          &DEVICE(qxl)->mem_reentrancy_guard);
     qxl_reset_state(qxl);
 
-    qxl->update_area_bh = qemu_bh_new(qxl_render_update_area_bh, qxl);
-    qxl->ssd.cursor_bh = qemu_bh_new(qemu_spice_cursor_refresh_bh, &qxl->ssd);
+    qxl->update_area_bh = qemu_bh_new_guarded(qxl_render_update_area_bh, qxl,
+                                              &DEVICE(qxl)->mem_reentrancy_guard);
+    qxl->ssd.cursor_bh = qemu_bh_new_guarded(qemu_spice_cursor_refresh_bh, &qxl->ssd,
+                                             &DEVICE(qxl)->mem_reentrancy_guard);
 }
 
 static void qxl_realize_primary(PCIDevice *dev, Error **errp)

hw/display/ramfb.c

@@ -97,6 +97,7 @@ static void ramfb_fw_cfg_write(void *dev, off_t offset, size_t len)
 
     s->width = width;
     s->height = height;
+    qemu_free_displaysurface(s->ds);
     s->ds = surface;
 }
 

hw/display/virtio-gpu.c

@@ -498,6 +498,8 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g,
     struct virtio_gpu_resource_flush rf;
     struct virtio_gpu_scanout *scanout;
     pixman_region16_t flush_region;
+    bool within_bounds = false;
+    bool update_submitted = false;
     int i;
 
     VIRTIO_GPU_FILL_CMD(rf);
@@ -518,13 +520,28 @@ static void virtio_gpu_resource_flush(VirtIOGPU *g,
                 rf.r.x < scanout->x + scanout->width &&
                 rf.r.x + rf.r.width >= scanout->x &&
                 rf.r.y < scanout->y + scanout->height &&
-                rf.r.y + rf.r.height >= scanout->y &&
-                console_has_gl(scanout->con)) {
-                dpy_gl_update(scanout->con, 0, 0, scanout->width,
-                              scanout->height);
+                rf.r.y + rf.r.height >= scanout->y) {
+                within_bounds = true;
+
+                if (console_has_gl(scanout->con)) {
+                    dpy_gl_update(scanout->con, 0, 0, scanout->width,
+                                  scanout->height);
+                    update_submitted = true;
+                }
             }
         }
-        return;
+
+        if (update_submitted) {
+            return;
+        }
+        if (!within_bounds) {
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: flush bounds outside scanouts"
+                          " bounds for flush %d: %d %d %d %d\n",
+                          __func__, rf.resource_id, rf.r.x, rf.r.y,
+                          rf.r.width, rf.r.height);
+            cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER;
+            return;
+        }
     }
 
     if (!res->blob &&
@@ -1339,8 +1356,10 @@ void virtio_gpu_device_realize(DeviceState *qdev, Error **errp)
 
     g->ctrl_vq = virtio_get_queue(vdev, 0);
     g->cursor_vq = virtio_get_queue(vdev, 1);
-    g->ctrl_bh = qemu_bh_new(virtio_gpu_ctrl_bh, g);
-    g->cursor_bh = qemu_bh_new(virtio_gpu_cursor_bh, g);
+    g->ctrl_bh = qemu_bh_new_guarded(virtio_gpu_ctrl_bh, g,
+                                     &qdev->mem_reentrancy_guard);
+    g->cursor_bh = qemu_bh_new_guarded(virtio_gpu_cursor_bh, g,
+                                       &qdev->mem_reentrancy_guard);
     QTAILQ_INIT(&g->reslist);
     QTAILQ_INIT(&g->cmdq);
     QTAILQ_INIT(&g->fenceq);

hw/dma/xilinx_axidma.c

@@ -168,6 +168,11 @@ static inline int stream_idle(struct Stream *s)
     return !!(s->regs[R_DMASR] & DMASR_IDLE);
 }
 
+static inline int stream_halted(struct Stream *s)
+{
+    return !!(s->regs[R_DMASR] & DMASR_HALTED);
+}
+
 static void stream_reset(struct Stream *s)
 {
     s->regs[R_DMASR] = DMASR_HALTED;  /* starts up halted.  */
@@ -269,7 +274,7 @@ static void stream_process_mem2s(struct Stream *s, StreamSink *tx_data_dev,
     uint64_t addr;
     bool eop;
 
-    if (!stream_running(s) || stream_idle(s)) {
+    if (!stream_running(s) || stream_idle(s) || stream_halted(s)) {
         return;
     }
 
@@ -326,7 +331,7 @@ static size_t stream_process_s2mem(struct Stream *s, unsigned char *buf,
     unsigned int rxlen;
     size_t pos = 0;
 
-    if (!stream_running(s) || stream_idle(s)) {
+    if (!stream_running(s) || stream_idle(s) || stream_halted(s)) {
         return 0;
     }
 
@@ -407,7 +412,7 @@ xilinx_axidma_data_stream_can_push(StreamSink *obj,
     XilinxAXIDMAStreamSink *ds = XILINX_AXI_DMA_DATA_STREAM(obj);
     struct Stream *s = &ds->dma->streams[1];
 
-    if (!stream_running(s) || stream_idle(s)) {
+    if (!stream_running(s) || stream_idle(s) || stream_halted(s)) {
         ds->dma->notify = notify;
         ds->dma->notify_opaque = notify_opaque;
         return false;

hw/hppa/machine.c

@@ -123,6 +123,7 @@ static FWCfgState *create_fw_cfg(MachineState *ms)
 {
     FWCfgState *fw_cfg;
     uint64_t val;
+    const char qemu_version[] = QEMU_VERSION;
 
     fw_cfg = fw_cfg_init_mem(FW_CFG_IO_BASE, FW_CFG_IO_BASE + 4);
     fw_cfg_add_i16(fw_cfg, FW_CFG_NB_CPUS, ms->smp.cpus);
@@ -148,6 +149,10 @@ static FWCfgState *create_fw_cfg(MachineState *ms)
     fw_cfg_add_i16(fw_cfg, FW_CFG_BOOT_DEVICE, ms->boot_config.order[0]);
     qemu_register_boot_set(fw_cfg_boot_set, fw_cfg);
 
+    fw_cfg_add_file(fw_cfg, "/etc/qemu-version",
+                    g_memdup(qemu_version, sizeof(qemu_version)),
+                    sizeof(qemu_version));
+
     return fw_cfg;
 }
 
@@ -418,10 +423,16 @@ static void hppa_machine_reset(MachineState *ms, ShutdownCause reason)
 
     /* Start all CPUs at the firmware entry point.
      *  Monarch CPU will initialize firmware, secondary CPUs
-     *  will enter a small idle look and wait for rendevouz. */
+     *  will enter a small idle loop and wait for rendevouz. */
     for (i = 0; i < smp_cpus; i++) {
-        cpu_set_pc(CPU(cpu[i]), firmware_entry);
+        CPUState *cs = CPU(cpu[i]);
+
+        cpu_set_pc(cs, firmware_entry);
+        cpu[i]->env.psw = PSW_Q;
         cpu[i]->env.gr[5] = CPU_HPA + i * 0x1000;
+
+        cs->exception_index = -1;
+        cs->halted = 0;
     }
 
     /* already initialized by machine_hppa_init()? */

hw/i2c/aspeed_i2c.c

@@ -226,7 +226,7 @@ static int aspeed_i2c_dma_read(AspeedI2CBus *bus, uint8_t *data)
     return 0;
 }
 
-static int aspeed_i2c_bus_send(AspeedI2CBus *bus, uint8_t pool_start)
+static int aspeed_i2c_bus_send(AspeedI2CBus *bus)
 {
     AspeedI2CClass *aic = ASPEED_I2C_GET_CLASS(bus->controller);
     int ret = -1;
@@ -236,10 +236,10 @@ static int aspeed_i2c_bus_send(AspeedI2CBus *bus, uint8_t pool_start)
     uint32_t reg_byte_buf = aspeed_i2c_bus_byte_buf_offset(bus);
     uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus);
     int pool_tx_count = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl,
-                                                TX_COUNT);
+                                                TX_COUNT) + 1;
 
     if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN)) {
-        for (i = pool_start; i < pool_tx_count; i++) {
+        for (i = 0; i < pool_tx_count; i++) {
             uint8_t *pool_base = aic->bus_pool_base(bus);
 
             trace_aspeed_i2c_bus_send("BUF", i + 1, pool_tx_count,
@@ -273,7 +273,7 @@ static int aspeed_i2c_bus_send(AspeedI2CBus *bus, uint8_t pool_start)
         }
         SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, TX_DMA_EN, 0);
     } else {
-        trace_aspeed_i2c_bus_send("BYTE", pool_start, 1,
+        trace_aspeed_i2c_bus_send("BYTE", 0, 1,
                                   bus->regs[reg_byte_buf]);
         ret = i2c_send(bus->bus, bus->regs[reg_byte_buf]);
     }
@@ -293,7 +293,7 @@ static void aspeed_i2c_bus_recv(AspeedI2CBus *bus)
     uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus);
     uint32_t reg_dma_addr = aspeed_i2c_bus_dma_addr_offset(bus);
     int pool_rx_count = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl,
-                                                RX_COUNT);
+                                                RX_SIZE) + 1;
 
     if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_BUFF_EN)) {
         uint8_t *pool_base = aic->bus_pool_base(bus);
@@ -418,7 +418,7 @@ static void aspeed_i2c_bus_cmd_dump(AspeedI2CBus *bus)
     uint32_t reg_intr_sts = aspeed_i2c_bus_intr_sts_offset(bus);
     uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus);
     if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_BUFF_EN)) {
-        count = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl, TX_COUNT);
+        count = SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl, TX_COUNT) + 1;
     } else if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, RX_DMA_EN)) {
         count = bus->regs[reg_dma_len];
     } else { /* BYTE mode */
@@ -446,10 +446,8 @@ static void aspeed_i2c_bus_cmd_dump(AspeedI2CBus *bus)
  */
 static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value)
 {
-    uint8_t pool_start = 0;
     uint32_t reg_intr_sts = aspeed_i2c_bus_intr_sts_offset(bus);
     uint32_t reg_cmd = aspeed_i2c_bus_cmd_offset(bus);
-    uint32_t reg_pool_ctrl = aspeed_i2c_bus_pool_ctrl_offset(bus);
     uint32_t reg_dma_len = aspeed_i2c_bus_dma_len_offset(bus);
 
     if (!aspeed_i2c_check_sram(bus)) {
@@ -483,27 +481,11 @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value)
 
         SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_START_CMD, 0);
 
-        /*
-         * The START command is also a TX command, as the slave
-         * address is sent on the bus. Drop the TX flag if nothing
-         * else needs to be sent in this sequence.
-         */
-        if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN)) {
-            if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_pool_ctrl, TX_COUNT)
-                == 1) {
-                SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_TX_CMD, 0);
-            } else {
-                /*
-                 * Increase the start index in the TX pool buffer to
-                 * skip the address byte.
-                 */
-                pool_start++;
-            }
-        } else if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_DMA_EN)) {
+        if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_DMA_EN)) {
             if (bus->regs[reg_dma_len] == 0) {
                 SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_TX_CMD, 0);
             }
-        } else {
+        } else if (!SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, TX_BUFF_EN)) {
             SHARED_ARRAY_FIELD_DP32(bus->regs, reg_cmd, M_TX_CMD, 0);
         }
 
@@ -520,7 +502,7 @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value)
 
     if (SHARED_ARRAY_FIELD_EX32(bus->regs, reg_cmd, M_TX_CMD)) {
         aspeed_i2c_set_state(bus, I2CD_MTXD);
-        if (aspeed_i2c_bus_send(bus, pool_start)) {
+        if (aspeed_i2c_bus_send(bus)) {
             SHARED_ARRAY_FIELD_DP32(bus->regs, reg_intr_sts, TX_NAK, 1);
             i2c_end_transfer(bus->bus);
         } else {

hw/i386/acpi-build.c

@@ -1311,7 +1311,7 @@ static void build_acpi0017(Aml *table)
     aml_append(dev, aml_name_decl("_HID", aml_string("ACPI0017")));
 
     method = aml_method("_STA", 0, AML_NOTSERIALIZED);
-    aml_append(method, aml_return(aml_int(0x01)));
+    aml_append(method, aml_return(aml_int(0x0B)));
     aml_append(dev, method);
 
     aml_append(scope, dev);

hw/i386/amd_iommu.c

@@ -1246,13 +1246,8 @@ static int amdvi_int_remap_msi(AMDVIState *iommu,
         return -AMDVI_IR_ERR;
     }
 
-    if (origin->address & AMDVI_MSI_ADDR_HI_MASK) {
-        trace_amdvi_err("MSI address high 32 bits non-zero when "
-                        "Interrupt Remapping enabled.");
-        return -AMDVI_IR_ERR;
-    }
-
-    if ((origin->address & AMDVI_MSI_ADDR_LO_MASK) != APIC_DEFAULT_ADDRESS) {
+    if (origin->address < AMDVI_INT_ADDR_FIRST ||
+        origin->address + sizeof(origin->data) > AMDVI_INT_ADDR_LAST + 1) {
         trace_amdvi_err("MSI is not from IOAPIC.");
         return -AMDVI_IR_ERR;
     }

hw/i386/amd_iommu.h

@@ -210,8 +210,6 @@
 #define AMDVI_INT_ADDR_FIRST    0xfee00000
 #define AMDVI_INT_ADDR_LAST     0xfeefffff
 #define AMDVI_INT_ADDR_SIZE     (AMDVI_INT_ADDR_LAST - AMDVI_INT_ADDR_FIRST + 1)
-#define AMDVI_MSI_ADDR_HI_MASK  (0xffffffff00000000ULL)
-#define AMDVI_MSI_ADDR_LO_MASK  (0x00000000ffffffffULL)
 
 /* SB IOAPIC is always on this device in AMD systems */
 #define AMDVI_IOAPIC_SB_DEVID   PCI_BUILD_BDF(0, PCI_DEVFN(0x14, 0))

hw/i386/intel_iommu.c

@@ -755,6 +755,8 @@ static int vtd_get_pdire_from_pdir_table(dma_addr_t pasid_dir_base,
         return -VTD_FR_PASID_TABLE_INV;
     }
 
+    pdire->val = le64_to_cpu(pdire->val);
+
     return 0;
 }
 
@@ -779,6 +781,9 @@ static int vtd_get_pe_in_pasid_leaf_table(IntelIOMMUState *s,
                         pe, entry_size, MEMTXATTRS_UNSPECIFIED)) {
         return -VTD_FR_PASID_TABLE_INV;
     }
+    for (size_t i = 0; i < ARRAY_SIZE(pe->val); i++) {
+        pe->val[i] = le64_to_cpu(pe->val[i]);
+    }
 
     /* Do translation type check */
     if (!vtd_pe_type_check(x86_iommu, pe)) {
@@ -3318,14 +3323,15 @@ static int vtd_irte_get(IntelIOMMUState *iommu, uint16_t index,
         return -VTD_FR_IR_ROOT_INVAL;
     }
 
-    trace_vtd_ir_irte_get(index, le64_to_cpu(entry->data[1]),
-                          le64_to_cpu(entry->data[0]));
+    entry->data[0] = le64_to_cpu(entry->data[0]);
+    entry->data[1] = le64_to_cpu(entry->data[1]);
+
+    trace_vtd_ir_irte_get(index, entry->data[1], entry->data[0]);
 
     if (!entry->irte.present) {
         error_report_once("%s: detected non-present IRTE "
                           "(index=%u, high=0x%" PRIx64 ", low=0x%" PRIx64 ")",
-                          __func__, index, le64_to_cpu(entry->data[1]),
-                          le64_to_cpu(entry->data[0]));
+                          __func__, index, entry->data[1], entry->data[0]);
         return -VTD_FR_IR_ENTRY_P;
     }
 
@@ -3333,14 +3339,13 @@ static int vtd_irte_get(IntelIOMMUState *iommu, uint16_t index,
         entry->irte.__reserved_2) {
         error_report_once("%s: detected non-zero reserved IRTE "
                           "(index=%u, high=0x%" PRIx64 ", low=0x%" PRIx64 ")",
-                          __func__, index, le64_to_cpu(entry->data[1]),
-                          le64_to_cpu(entry->data[0]));
+                          __func__, index, entry->data[1], entry->data[0]);
         return -VTD_FR_IR_IRTE_RSVD;
     }
 
     if (sid != X86_IOMMU_SID_INVALID) {
         /* Validate IRTE SID */
-        source_id = le32_to_cpu(entry->irte.source_id);
+        source_id = entry->irte.source_id;
         switch (entry->irte.sid_vtype) {
         case VTD_SVT_NONE:
             break;
@@ -3394,7 +3399,7 @@ static int vtd_remap_irq_get(IntelIOMMUState *iommu, uint16_t index,
     irq->trigger_mode = irte.irte.trigger_mode;
     irq->vector = irte.irte.vector;
     irq->delivery_mode = irte.irte.delivery_mode;
-    irq->dest = le32_to_cpu(irte.irte.dest_id);
+    irq->dest = irte.irte.dest_id;
     if (!iommu->intr_eime) {
 #define  VTD_IR_APIC_DEST_MASK         (0xff00ULL)
 #define  VTD_IR_APIC_DEST_SHIFT        (8)
@@ -3449,7 +3454,7 @@ static int vtd_interrupt_remap_msi(IntelIOMMUState *iommu,
         goto out;
     }
 
-    index = addr.addr.index_h << 15 | le16_to_cpu(addr.addr.index_l);
+    index = addr.addr.index_h << 15 | addr.addr.index_l;
 
 #define  VTD_IR_MSI_DATA_SUBHANDLE       (0x0000ffff)
 #define  VTD_IR_MSI_DATA_RESERVED        (0xffff0000)

hw/i386/intel_iommu_internal.h

@@ -321,12 +321,21 @@ typedef enum VTDFaultReason {
 
 /* Interrupt Entry Cache Invalidation Descriptor: VT-d 6.5.2.7. */
 struct VTDInvDescIEC {
+#if HOST_BIG_ENDIAN
+    uint64_t reserved_2:16;
+    uint64_t index:16;          /* Start index to invalidate */
+    uint64_t index_mask:5;      /* 2^N for continuous int invalidation */
+    uint64_t resved_1:22;
+    uint64_t granularity:1;     /* If set, it's global IR invalidation */
+    uint64_t type:4;            /* Should always be 0x4 */
+#else
     uint32_t type:4;            /* Should always be 0x4 */
     uint32_t granularity:1;     /* If set, it's global IR invalidation */
     uint32_t resved_1:22;
     uint32_t index_mask:5;      /* 2^N for continuous int invalidation */
     uint32_t index:16;          /* Start index to invalidate */
     uint32_t reserved_2:16;
+#endif
 };
 typedef struct VTDInvDescIEC VTDInvDescIEC;
 

hw/i386/pc_piix.c

@@ -405,6 +405,7 @@ static void pc_xen_hvm_init(MachineState *machine)
     }
 
     pc_xen_hvm_init_pci(machine);
+    xen_igd_reserve_slot(pcms->bus);
     pci_create_simple(pcms->bus, -1, "xen-platform");
 }
 #endif

hw/i386/sgx-stub.c

@@ -34,5 +34,5 @@ void pc_machine_init_sgx_epc(PCMachineState *pcms)
 
 bool sgx_epc_get_section(int section_nr, uint64_t *addr, uint64_t *size)
 {
-    g_assert_not_reached();
+    return true;
 }

hw/i386/x86-iommu.c

@@ -63,7 +63,7 @@ void x86_iommu_irq_to_msi_message(X86IOMMUIrq *irq, MSIMessage *msg_out)
     msg.redir_hint = irq->redir_hint;
     msg.dest = irq->dest;
     msg.__addr_hi = irq->dest & 0xffffff00;
-    msg.__addr_head = cpu_to_le32(0xfee);
+    msg.__addr_head = 0xfee;
     /* Keep this from original MSI address bits */
     msg.__not_used = irq->msi_addr_last_bits;
 

hw/ide/ahci.c

@@ -40,9 +40,10 @@
 #include "trace.h"
 
 static void check_cmd(AHCIState *s, int port);
-static int handle_cmd(AHCIState *s, int port, uint8_t slot);
+static void handle_cmd(AHCIState *s, int port, uint8_t slot);
 static void ahci_reset_port(AHCIState *s, int port);
-static bool ahci_write_fis_d2h(AHCIDevice *ad);
+static bool ahci_write_fis_d2h(AHCIDevice *ad, bool d2h_fis_i);
+static void ahci_clear_cmd_issue(AHCIDevice *ad, uint8_t slot);
 static void ahci_init_d2h(AHCIDevice *ad);
 static int ahci_dma_prepare_buf(const IDEDMA *dma, int32_t limit);
 static bool ahci_map_clb_address(AHCIDevice *ad);
@@ -327,6 +328,11 @@ static void ahci_port_write(AHCIState *s, int port, int offset, uint32_t val)
         ahci_check_irq(s);
         break;
     case AHCI_PORT_REG_CMD:
+        if ((pr->cmd & PORT_CMD_START) && !(val & PORT_CMD_START)) {
+            pr->scr_act = 0;
+            pr->cmd_issue = 0;
+        }
+
         /* Block any Read-only fields from being set;
          * including LIST_ON and FIS_ON.
          * The spec requires to set ICC bits to zero after the ICC change
@@ -590,9 +596,8 @@ static void check_cmd(AHCIState *s, int port)
 
     if ((pr->cmd & PORT_CMD_START) && pr->cmd_issue) {
         for (slot = 0; (slot < 32) && pr->cmd_issue; slot++) {
-            if ((pr->cmd_issue & (1U << slot)) &&
-                !handle_cmd(s, port, slot)) {
-                pr->cmd_issue &= ~(1U << slot);
+            if (pr->cmd_issue & (1U << slot)) {
+                handle_cmd(s, port, slot);
             }
         }
     }
@@ -617,9 +622,13 @@ static void ahci_init_d2h(AHCIDevice *ad)
         return;
     }
 
-    if (ahci_write_fis_d2h(ad)) {
+    /*
+     * For simplicity, do not call ahci_clear_cmd_issue() for this
+     * ahci_write_fis_d2h(). (The reset value for PxCI is 0.)
+     */
+    if (ahci_write_fis_d2h(ad, true)) {
         ad->init_d2h_sent = true;
-        /* We're emulating receiving the first Reg H2D Fis from the device;
+        /* We're emulating receiving the first Reg D2H FIS from the device;
          * Update the SIG register, but otherwise proceed as normal. */
         pr->sig = ((uint32_t)ide_state->hcyl << 24) |
             (ide_state->lcyl << 16) |
@@ -657,6 +666,7 @@ static void ahci_reset_port(AHCIState *s, int port)
     pr->scr_act = 0;
     pr->tfdata = 0x7F;
     pr->sig = 0xFFFFFFFF;
+    pr->cmd_issue = 0;
     d->busy_slot = -1;
     d->init_d2h_sent = false;
 
@@ -800,8 +810,14 @@ static void ahci_write_fis_sdb(AHCIState *s, NCQTransferState *ncq_tfs)
     pr->scr_act &= ~ad->finished;
     ad->finished = 0;
 
-    /* Trigger IRQ if interrupt bit is set (which currently, it always is) */
-    if (sdb_fis->flags & 0x40) {
+    /*
+     * TFES IRQ is always raised if ERR_STAT is set, regardless of I bit.
+     * If ERR_STAT is not set, trigger SDBS IRQ if interrupt bit is set
+     * (which currently, it always is).
+     */
+    if (sdb_fis->status & ERR_STAT) {
+        ahci_trigger_irq(s, ad, AHCI_PORT_IRQ_BIT_TFES);
+    } else if (sdb_fis->flags & 0x40) {
         ahci_trigger_irq(s, ad, AHCI_PORT_IRQ_BIT_SDBS);
     }
 }
@@ -849,7 +865,7 @@ static void ahci_write_fis_pio(AHCIDevice *ad, uint16_t len, bool pio_fis_i)
     }
 }
 
-static bool ahci_write_fis_d2h(AHCIDevice *ad)
+static bool ahci_write_fis_d2h(AHCIDevice *ad, bool d2h_fis_i)
 {
     AHCIPortRegs *pr = &ad->port_regs;
     uint8_t *d2h_fis;
@@ -863,7 +879,7 @@ static bool ahci_write_fis_d2h(AHCIDevice *ad)
     d2h_fis = &ad->res_fis[RES_FIS_RFIS];
 
     d2h_fis[0] = SATA_FIS_TYPE_REGISTER_D2H;
-    d2h_fis[1] = (1 << 6); /* interrupt bit */
+    d2h_fis[1] = d2h_fis_i ? (1 << 6) : 0; /* interrupt bit */
     d2h_fis[2] = s->status;
     d2h_fis[3] = s->error;
 
@@ -889,7 +905,10 @@ static bool ahci_write_fis_d2h(AHCIDevice *ad)
         ahci_trigger_irq(ad->hba, ad, AHCI_PORT_IRQ_BIT_TFES);
     }
 
-    ahci_trigger_irq(ad->hba, ad, AHCI_PORT_IRQ_BIT_DHRS);
+    if (d2h_fis_i) {
+        ahci_trigger_irq(ad->hba, ad, AHCI_PORT_IRQ_BIT_DHRS);
+    }
+
     return true;
 }
 
@@ -997,7 +1016,6 @@ static void ncq_err(NCQTransferState *ncq_tfs)
 
     ide_state->error = ABRT_ERR;
     ide_state->status = READY_STAT | ERR_STAT;
-    ncq_tfs->drive->port_regs.scr_err |= (1 << ncq_tfs->tag);
     qemu_sglist_destroy(&ncq_tfs->sglist);
     ncq_tfs->used = 0;
 }
@@ -1007,7 +1025,7 @@ static void ncq_finish(NCQTransferState *ncq_tfs)
     /* If we didn't error out, set our finished bit. Errored commands
      * do not get a bit set for the SDB FIS ACT register, nor do they
      * clear the outstanding bit in scr_act (PxSACT). */
-    if (!(ncq_tfs->drive->port_regs.scr_err & (1 << ncq_tfs->tag))) {
+    if (ncq_tfs->used) {
         ncq_tfs->drive->finished |= (1 << ncq_tfs->tag);
     }
 
@@ -1119,6 +1137,24 @@ static void process_ncq_command(AHCIState *s, int port, const uint8_t *cmd_fis,
         return;
     }
 
+    /*
+     * A NCQ command clears the bit in PxCI after the command has been QUEUED
+     * successfully (ERROR not set, BUSY and DRQ cleared).
+     *
+     * For NCQ commands, PxCI will always be cleared here.
+     *
+     * (Once the NCQ command is COMPLETED, the device will send a SDB FIS with
+     * the interrupt bit set, which will clear PxSACT and raise an interrupt.)
+     */
+    ahci_clear_cmd_issue(ad, slot);
+
+    /*
+     * In reality, for NCQ commands, PxCI is cleared after receiving a D2H FIS
+     * without the interrupt bit set, but since ahci_write_fis_d2h() can raise
+     * an IRQ on error, we need to call them in reverse order.
+     */
+    ahci_write_fis_d2h(ad, false);
+
     ncq_tfs->used = 1;
     ncq_tfs->drive = ad;
     ncq_tfs->slot = slot;
@@ -1191,6 +1227,7 @@ static void handle_reg_h2d_fis(AHCIState *s, int port,
 {
     IDEState *ide_state = &s->dev[port].port.ifs[0];
     AHCICmdHdr *cmd = get_cmd_header(s, port, slot);
+    AHCIDevice *ad = &s->dev[port];
     uint16_t opts = le16_to_cpu(cmd->opts);
 
     if (cmd_fis[1] & 0x0F) {
@@ -1210,10 +1247,30 @@ static void handle_reg_h2d_fis(AHCIState *s, int port,
         case STATE_RUN:
             if (cmd_fis[15] & ATA_SRST) {
                 s->dev[port].port_state = STATE_RESET;
+                /*
+                 * When setting SRST in the first H2D FIS in the reset sequence,
+                 * the device does not send a D2H FIS. Host software thus has to
+                 * set the "Clear Busy upon R_OK" bit such that PxCI (and BUSY)
+                 * gets cleared. See AHCI 1.3.1, section 10.4.1 Software Reset.
+                 */
+                if (opts & AHCI_CMD_CLR_BUSY) {
+                    ahci_clear_cmd_issue(ad, slot);
+                }
             }
             break;
         case STATE_RESET:
             if (!(cmd_fis[15] & ATA_SRST)) {
+                /*
+                 * When clearing SRST in the second H2D FIS in the reset
+                 * sequence, the device will execute diagnostics. When this is
+                 * done, the device will send a D2H FIS with the good status.
+                 * See SATA 3.5a Gold, section 11.4 Software reset protocol.
+                 *
+                 * This D2H FIS is the first D2H FIS received from the device,
+                 * and is received regardless if the reset was performed by a
+                 * COMRESET or by setting and clearing the SRST bit. Therefore,
+                 * the logic for this is found in ahci_init_d2h() and not here.
+                 */
                 ahci_reset_port(s, port);
             }
             break;
@@ -1267,11 +1324,19 @@ static void handle_reg_h2d_fis(AHCIState *s, int port,
     /* Reset transferred byte counter */
     cmd->status = 0;
 
+    /*
+     * A non-NCQ command clears the bit in PxCI after the command has COMPLETED
+     * successfully (ERROR not set, BUSY and DRQ cleared).
+     *
+     * For non-NCQ commands, PxCI will always be cleared by ahci_cmd_done().
+     */
+    ad->busy_slot = slot;
+
     /* We're ready to process the command in FIS byte 2. */
     ide_exec_cmd(&s->dev[port].port, cmd_fis[2]);
 }
 
-static int handle_cmd(AHCIState *s, int port, uint8_t slot)
+static void handle_cmd(AHCIState *s, int port, uint8_t slot)
 {
     IDEState *ide_state;
     uint64_t tbl_addr;
@@ -1282,12 +1347,12 @@ static int handle_cmd(AHCIState *s, int port, uint8_t slot)
     if (s->dev[port].port.ifs[0].status & (BUSY_STAT|DRQ_STAT)) {
         /* Engine currently busy, try again later */
         trace_handle_cmd_busy(s, port);
-        return -1;
+        return;
     }
 
     if (!s->dev[port].lst) {
         trace_handle_cmd_nolist(s, port);
-        return -1;
+        return;
     }
     cmd = get_cmd_header(s, port, slot);
     /* remember current slot handle for later */
@@ -1297,7 +1362,7 @@ static int handle_cmd(AHCIState *s, int port, uint8_t slot)
     ide_state = &s->dev[port].port.ifs[0];
     if (!ide_state->blk) {
         trace_handle_cmd_badport(s, port);
-        return -1;
+        return;
     }
 
     tbl_addr = le64_to_cpu(cmd->tbl_addr);
@@ -1306,7 +1371,7 @@ static int handle_cmd(AHCIState *s, int port, uint8_t slot)
                              DMA_DIRECTION_TO_DEVICE, MEMTXATTRS_UNSPECIFIED);
     if (!cmd_fis) {
         trace_handle_cmd_badfis(s, port);
-        return -1;
+        return;
     } else if (cmd_len != 0x80) {
         ahci_trigger_irq(s, &s->dev[port], AHCI_PORT_IRQ_BIT_HBFS);
         trace_handle_cmd_badmap(s, port, cmd_len);
@@ -1330,15 +1395,6 @@ static int handle_cmd(AHCIState *s, int port, uint8_t slot)
 out:
     dma_memory_unmap(s->as, cmd_fis, cmd_len, DMA_DIRECTION_TO_DEVICE,
                      cmd_len);
-
-    if (s->dev[port].port.ifs[0].status & (BUSY_STAT|DRQ_STAT)) {
-        /* async command, complete later */
-        s->dev[port].busy_slot = slot;
-        return -1;
-    }
-
-    /* done handling the command */
-    return 0;
 }
 
 /* Transfer PIO data between RAM and device */
@@ -1492,23 +1548,41 @@ static int ahci_dma_rw_buf(const IDEDMA *dma, bool is_write)
     return 1;
 }
 
+static void ahci_clear_cmd_issue(AHCIDevice *ad, uint8_t slot)
+{
+    IDEState *ide_state = &ad->port.ifs[0];
+
+    if (!(ide_state->status & ERR_STAT) &&
+        !(ide_state->status & (BUSY_STAT | DRQ_STAT))) {
+        ad->port_regs.cmd_issue &= ~(1 << slot);
+    }
+}
+
+/* Non-NCQ command is done - This function is never called for NCQ commands. */
 static void ahci_cmd_done(const IDEDMA *dma)
 {
     AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
+    IDEState *ide_state = &ad->port.ifs[0];
 
     trace_ahci_cmd_done(ad->hba, ad->port_no);
 
     /* no longer busy */
     if (ad->busy_slot != -1) {
-        ad->port_regs.cmd_issue &= ~(1 << ad->busy_slot);
+        ahci_clear_cmd_issue(ad, ad->busy_slot);
         ad->busy_slot = -1;
     }
 
-    /* update d2h status */
-    ahci_write_fis_d2h(ad);
+    /*
+     * In reality, for non-NCQ commands, PxCI is cleared after receiving a D2H
+     * FIS with the interrupt bit set, but since ahci_write_fis_d2h() will raise
+     * an IRQ, we need to call them in reverse order.
+     */
+    ahci_write_fis_d2h(ad, true);
 
-    if (ad->port_regs.cmd_issue && !ad->check_bh) {
-        ad->check_bh = qemu_bh_new(ahci_check_cmd_bh, ad);
+    if (!(ide_state->status & ERR_STAT) &&
+        ad->port_regs.cmd_issue && !ad->check_bh) {
+        ad->check_bh = qemu_bh_new_guarded(ahci_check_cmd_bh, ad,
+                                           &ad->mem_reentrancy_guard);
         qemu_bh_schedule(ad->check_bh);
     }
 }

hw/ide/ahci_internal.h

@@ -321,6 +321,7 @@ struct AHCIDevice {
     bool init_d2h_sent;
     AHCICmdHdr *cur_cmd;
     NCQTransferState ncq_tfs[AHCI_MAX_CMDS];
+    MemReentrancyGuard mem_reentrancy_guard;
 };
 
 struct AHCIPCIState {

hw/ide/core.c

@@ -512,6 +512,7 @@ BlockAIOCB *ide_issue_trim(
         BlockCompletionFunc *cb, void *cb_opaque, void *opaque)
 {
     IDEState *s = opaque;
+    IDEDevice *dev = s->unit ? s->bus->slave : s->bus->master;
     TrimAIOCB *iocb;
 
     /* Paired with a decrement in ide_trim_bh_cb() */
@@ -519,7 +520,8 @@ BlockAIOCB *ide_issue_trim(
 
     iocb = blk_aio_get(&trim_aiocb_info, s->blk, cb, cb_opaque);
     iocb->s = s;
-    iocb->bh = qemu_bh_new(ide_trim_bh_cb, iocb);
+    iocb->bh = qemu_bh_new_guarded(ide_trim_bh_cb, iocb,
+                                   &DEVICE(dev)->mem_reentrancy_guard);
     iocb->ret = 0;
     iocb->qiov = qiov;
     iocb->i = -1;
@@ -530,9 +532,9 @@ BlockAIOCB *ide_issue_trim(
 
 void ide_abort_command(IDEState *s)
 {
-    ide_transfer_stop(s);
     s->status = READY_STAT | ERR_STAT;
     s->error = ABRT_ERR;
+    ide_transfer_stop(s);
 }
 
 static void ide_set_retry(IDEState *s)
@@ -2489,19 +2491,19 @@ static void ide_dummy_transfer_stop(IDEState *s)
 
 void ide_bus_reset(IDEBus *bus)
 {
-    bus->unit = 0;
-    bus->cmd = 0;
-    ide_reset(&bus->ifs[0]);
-    ide_reset(&bus->ifs[1]);
-    ide_clear_hob(bus);
-
-    /* pending async DMA */
+    /* pending async DMA - needs the IDEState before it is reset */
     if (bus->dma->aiocb) {
         trace_ide_bus_reset_aio();
         blk_aio_cancel(bus->dma->aiocb);
         bus->dma->aiocb = NULL;
     }
 
+    bus->unit = 0;
+    bus->cmd = 0;
+    ide_reset(&bus->ifs[0]);
+    ide_reset(&bus->ifs[1]);
+    ide_clear_hob(bus);
+
     /* reset dma provider too */
     if (bus->dma->ops->reset) {
         bus->dma->ops->reset(bus->dma);

hw/ide/piix.c

@@ -123,7 +123,7 @@ static void piix_ide_reset(DeviceState *dev)
     pci_set_word(pci_conf + PCI_COMMAND, 0x0000);
     pci_set_word(pci_conf + PCI_STATUS,
                  PCI_STATUS_DEVSEL_MEDIUM | PCI_STATUS_FAST_BACK);
-    pci_set_byte(pci_conf + 0x20, 0x01);  /* BMIBA: 20-23h */
+    pci_set_long(pci_conf + 0x20, 0x1);  /* BMIBA: 20-23h */
 }
 
 static int pci_piix_init_ports(PCIIDEState *d)

hw/input/lasips2.c

@@ -351,6 +351,11 @@ static void lasips2_port_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
+    /*
+     * The PS/2 mouse port is integreal part of LASI and can not be
+     * created by users without LASI.
+     */
+    dc->user_creatable = false;
     dc->realize = lasips2_port_realize;
 }
 
@@ -397,6 +402,11 @@ static void lasips2_kbd_port_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
     LASIPS2PortDeviceClass *lpdc = LASIPS2_PORT_CLASS(klass);
 
+    /*
+     * The PS/2 keyboard port is integreal part of LASI and can not be
+     * created by users without LASI.
+     */
+    dc->user_creatable = false;
     device_class_set_parent_realize(dc, lasips2_kbd_port_realize,
                                     &lpdc->parent_realize);
 }

hw/intc/allwinner-a10-pic.c

@@ -49,12 +49,9 @@ static void aw_a10_pic_update(AwA10PICState *s)
 static void aw_a10_pic_set_irq(void *opaque, int irq, int level)
 {
     AwA10PICState *s = opaque;
+    uint32_t *pending_reg = &s->irq_pending[irq / 32];
 
-    if (level) {
-        set_bit(irq % 32, (void *)&s->irq_pending[irq / 32]);
-    } else {
-        clear_bit(irq % 32, (void *)&s->irq_pending[irq / 32]);
-    }
+    *pending_reg = deposit32(*pending_reg, irq % 32, 1, !!level);
     aw_a10_pic_update(s);
 }
 

hw/intc/apic.c

@@ -883,6 +883,13 @@ static void apic_realize(DeviceState *dev, Error **errp)
     memory_region_init_io(&s->io_memory, OBJECT(s), &apic_io_ops, s, "apic-msi",
                           APIC_SPACE_SIZE);
 
+    /*
+     * apic-msi's apic_mem_write can call into ioapic_eoi_broadcast, which can
+     * write back to apic-msi. As such mark the apic-msi region re-entrancy
+     * safe.
+     */
+    s->io_memory.disable_reentrancy_guard = true;
+
     s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, apic_timer, s);
     local_apics[s->id] = s;
 

hw/intc/arm_gicv3_cpuif.c

@@ -1432,16 +1432,25 @@ static void icv_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri,
     idx = icv_find_active(cs, irq);
 
     if (idx < 0) {
-        /* No valid list register corresponding to EOI ID */
-        icv_increment_eoicount(cs);
+        /*
+         * No valid list register corresponding to EOI ID; if this is a vLPI
+         * not in the list regs then do nothing; otherwise increment EOI count
+         */
+        if (irq < GICV3_LPI_INTID_START) {
+            icv_increment_eoicount(cs);
+        }
     } else {
         uint64_t lr = cs->ich_lr_el2[idx];
         int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0;
         int lr_gprio = ich_lr_prio(lr) & icv_gprio_mask(cs, grp);
 
         if (thisgrp == grp && lr_gprio == dropprio) {
-            if (!icv_eoi_split(env, cs)) {
-                /* Priority drop and deactivate not split: deactivate irq now */
+            if (!icv_eoi_split(env, cs) || irq >= GICV3_LPI_INTID_START) {
+                /*
+                 * Priority drop and deactivate not split: deactivate irq now.
+                 * LPIs always get their active state cleared immediately
+                 * because no separate deactivate is expected.
+                 */
                 icv_deactivate_irq(cs, idx);
             }
         }

hw/intc/loongarch_ipi.c

@@ -215,6 +215,10 @@ static void loongarch_ipi_init(Object *obj)
     for (cpu = 0; cpu < MAX_IPI_CORE_NUM; cpu++) {
         memory_region_init_io(&s->ipi_iocsr_mem[cpu], obj, &loongarch_ipi_ops,
                             &lams->ipi_core[cpu], "loongarch_ipi_iocsr", 0x48);
+
+        /* loongarch_ipi_iocsr performs re-entrant IO through ipi_send */
+        s->ipi_iocsr_mem[cpu].disable_reentrancy_guard = true;
+
         sysbus_init_mmio(sbd, &s->ipi_iocsr_mem[cpu]);
 
         memory_region_init_io(&s->ipi64_iocsr_mem[cpu], obj, &loongarch_ipi64_ops,

hw/intc/riscv_aclint.c

@@ -64,13 +64,13 @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
     uint64_t next;
     uint64_t diff;
 
-    uint64_t rtc_r = cpu_riscv_read_rtc(mtimer);
+    uint64_t rtc = cpu_riscv_read_rtc(mtimer);
 
     /* Compute the relative hartid w.r.t the socket */
     hartid = hartid - mtimer->hartid_base;
 
     mtimer->timecmp[hartid] = value;
-    if (mtimer->timecmp[hartid] <= rtc_r) {
+    if (mtimer->timecmp[hartid] <= rtc) {
         /*
          * If we're setting an MTIMECMP value in the "past",
          * immediately raise the timer interrupt
@@ -81,7 +81,7 @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
 
     /* otherwise, set up the future timer interrupt */
     qemu_irq_lower(mtimer->timer_irqs[hartid]);
-    diff = mtimer->timecmp[hartid] - rtc_r;
+    diff = mtimer->timecmp[hartid] - rtc;
     /* back to ns (note args switched in muldiv64) */
     uint64_t ns_diff = muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq);
 
@@ -208,11 +208,12 @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
         return;
     } else if (addr == mtimer->time_base || addr == mtimer->time_base + 4) {
         uint64_t rtc_r = cpu_riscv_read_rtc_raw(mtimer->timebase_freq);
+        uint64_t rtc = cpu_riscv_read_rtc(mtimer);
 
         if (addr == mtimer->time_base) {
             if (size == 4) {
                 /* time_lo for RV32/RV64 */
-                mtimer->time_delta = ((rtc_r & ~0xFFFFFFFFULL) | value) - rtc_r;
+                mtimer->time_delta = ((rtc & ~0xFFFFFFFFULL) | value) - rtc_r;
             } else {
                 /* time for RV64 */
                 mtimer->time_delta = value - rtc_r;
@@ -220,7 +221,7 @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
         } else {
             if (size == 4) {
                 /* time_hi for RV32/RV64 */
-                mtimer->time_delta = (value << 32 | (rtc_r & 0xFFFFFFFF)) - rtc_r;
+                mtimer->time_delta = (value << 32 | (rtc & 0xFFFFFFFF)) - rtc_r;
             } else {
                 qemu_log_mask(LOG_GUEST_ERROR,
                               "aclint-mtimer: invalid time_hi write: %08x",

hw/mips/loongson3_virt.c

@@ -29,7 +29,6 @@
 #include "qemu/datadir.h"
 #include "qapi/error.h"
 #include "elf.h"
-#include "kvm_mips.h"
 #include "hw/char/serial.h"
 #include "hw/intc/loongson_liointc.h"
 #include "hw/mips/mips.h"
@@ -617,7 +616,6 @@ static void loongson3v_machine_class_init(ObjectClass *oc, void *data)
     mc->max_cpus = LOONGSON_MAX_VCPUS;
     mc->default_ram_id = "loongson3.highram";
     mc->default_ram_size = 1600 * MiB;
-    mc->kvm_type = mips_kvm_type;
     mc->minimum_page_bits = 14;
 }
 

hw/mips/malta.c

@@ -877,9 +877,9 @@ static void write_bootloader(uint8_t *base, uint64_t run_addr,
 
     /* Bus endianess is always reversed */
 #if TARGET_BIG_ENDIAN
-#define cpu_to_gt32 cpu_to_le32
+#define cpu_to_gt32(x) (x)
 #else
-#define cpu_to_gt32 cpu_to_be32
+#define cpu_to_gt32(x) bswap32(x)
 #endif
 
     /* move GT64120 registers from 0x14000000 to 0x1be00000 */

hw/misc/aspeed_hace.c

@@ -189,7 +189,7 @@ static void do_hash_operation(AspeedHACEState *s, int algo, bool sg_mode,
                               bool acc_mode)
 {
     struct iovec iov[ASPEED_HACE_MAX_SG];
-    g_autofree uint8_t *digest_buf;
+    g_autofree uint8_t *digest_buf = NULL;
     size_t digest_len = 0;
     int niov = 0;
     int i;

hw/misc/bcm2835_property.c

@@ -382,6 +382,13 @@ static void bcm2835_property_init(Object *obj)
 
     memory_region_init_io(&s->iomem, OBJECT(s), &bcm2835_property_ops, s,
                           TYPE_BCM2835_PROPERTY, 0x10);
+
+    /*
+     * bcm2835_property_ops call into bcm2835_mbox, which in-turn reads from
+     * iomem. As such, mark iomem as re-entracy safe.
+     */
+    s->iomem.disable_reentrancy_guard = true;
+
     sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem);
     sysbus_init_irq(SYS_BUS_DEVICE(s), &s->mbox_irq);
 }

hw/misc/imx_rngc.c

@@ -228,8 +228,10 @@ static void imx_rngc_realize(DeviceState *dev, Error **errp)
     sysbus_init_mmio(sbd, &s->iomem);
 
     sysbus_init_irq(sbd, &s->irq);
-    s->self_test_bh = qemu_bh_new(imx_rngc_self_test, s);
-    s->seed_bh = qemu_bh_new(imx_rngc_seed, s);
+    s->self_test_bh = qemu_bh_new_guarded(imx_rngc_self_test, s,
+                                          &dev->mem_reentrancy_guard);
+    s->seed_bh = qemu_bh_new_guarded(imx_rngc_seed, s,
+                                     &dev->mem_reentrancy_guard);
 }
 
 static void imx_rngc_reset(DeviceState *dev)

hw/misc/led.c

@@ -63,7 +63,7 @@ static void led_set_state_gpio_handler(void *opaque, int line, int new_state)
     LEDState *s = LED(opaque);
 
     assert(line == 0);
-    led_set_state(s, !!new_state != s->gpio_active_high);
+    led_set_state(s, !!new_state == s->gpio_active_high);
 }
 
 static void led_reset(DeviceState *dev)

hw/misc/macio/mac_dbdma.c

@@ -914,7 +914,7 @@ static void mac_dbdma_realize(DeviceState *dev, Error **errp)
 {
     DBDMAState *s = MAC_DBDMA(dev);
 
-    s->bh = qemu_bh_new(DBDMA_run_bh, s);
+    s->bh = qemu_bh_new_guarded(DBDMA_run_bh, s, &dev->mem_reentrancy_guard);
 }
 
 static void mac_dbdma_class_init(ObjectClass *oc, void *data)

hw/misc/mps2-scc.c

@@ -329,6 +329,13 @@ static void mps2_scc_realize(DeviceState *dev, Error **errp)
     s->oscclk = g_new0(uint32_t, s->num_oscclk);
 }
 
+static void mps2_scc_finalize(Object *obj)
+{
+    MPS2SCC *s = MPS2_SCC(obj);
+
+    g_free(s->oscclk_reset);
+}
+
 static const VMStateDescription mps2_scc_vmstate = {
     .name = "mps2-scc",
     .version_id = 3,
@@ -385,6 +392,7 @@ static const TypeInfo mps2_scc_info = {
     .parent = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(MPS2SCC),
     .instance_init = mps2_scc_init,
+    .instance_finalize = mps2_scc_finalize,
     .class_init = mps2_scc_class_init,
 };